Merge commit '9f12600fe425bc28f0ccba034a77783c09c15af4' into for-linus

Backmerge of dcache.c changes from mainline.  It's that, or complete
rebase...

Conflicts:
	fs/splice.c

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

599 files changed, 7374 insertions, 3790 deletions

diff --git a/Documentation/ABI/testing/sysfs-bus-pci b/Documentation/ABI/testing/sysfs-bus-pci
index a3c5a6685036..ab8d76dfaa80 100644
--- a/Documentation/ABI/testing/sysfs-bus-pci
+++ b/Documentation/ABI/testing/sysfs-bus-pci
@@ -117,7 +117,7 @@ Description:
 
 What:		/sys/bus/pci/devices/.../vpd
 Date:		February 2008
-Contact:	Ben Hutchings <bhutchings@solarflare.com>
+Contact:	Ben Hutchings <bwh@kernel.org>
 Description:
 		A file named vpd in a device directory will be a
 		binary file containing the Vital Product Data for the
diff --git a/Documentation/DocBook/drm.tmpl b/Documentation/DocBook/drm.tmpl
index 677a02553ec0..ba60d93c1855 100644
--- a/Documentation/DocBook/drm.tmpl
+++ b/Documentation/DocBook/drm.tmpl
@@ -79,7 +79,7 @@
   <partintro>
     <para>
       This first part of the DRM Developer's Guide documents core DRM code,
-      helper libraries for writting drivers and generic userspace interfaces
+      helper libraries for writing drivers and generic userspace interfaces
       exposed by DRM drivers.
     </para>
   </partintro>
@@ -459,7 +459,7 @@ char *date;</synopsis>
       providing a solution to every graphics memory-related problems, GEM
       identified common code between drivers and created a support library to
       share it. GEM has simpler initialization and execution requirements than
-      TTM, but has no video RAM management capabitilies and is thus limited to
+      TTM, but has no video RAM management capabilities and is thus limited to
       UMA devices.
     </para>
     <sect2>
@@ -889,7 +889,7 @@ int (*prime_fd_to_handle)(struct drm_device *dev,
 	    vice versa. Drivers must use the kernel dma-buf buffer sharing framework
 	    to manage the PRIME file descriptors. Similar to the mode setting
 	    API PRIME is agnostic to the underlying buffer object manager, as
-	    long as handles are 32bit unsinged integers.
+	    long as handles are 32bit unsigned integers.
 	  </para>
 	  <para>
 	    While non-GEM drivers must implement the operations themselves, GEM
@@ -2356,7 +2356,7 @@ void intel_crt_init(struct drm_device *dev)
       first create properties and then create and associate individual instances
       of those properties to objects. A property can be instantiated multiple
       times and associated with different objects. Values are stored in property
-      instances, and all other property information are stored in the propery
+      instances, and all other property information are stored in the property
       and shared between all instances of the property.
     </para>
     <para>
@@ -2697,10 +2697,10 @@ int num_ioctls;</synopsis>
   <sect1>
     <title>Legacy Support Code</title>
     <para>
-      The section very brievely covers some of the old legacy support code which
+      The section very briefly covers some of the old legacy support code which
       is only used by old DRM drivers which have done a so-called shadow-attach
       to the underlying device instead of registering as a real driver. This
-      also includes some of the old generic buffer mangement and command
+      also includes some of the old generic buffer management and command
       submission code. Do not use any of this in new and modern drivers.
     </para>
 
diff --git a/Documentation/DocBook/media/Makefile b/Documentation/DocBook/media/Makefile
index f9fd615427fb..1d27f0a1abd1 100644
--- a/Documentation/DocBook/media/Makefile
+++ b/Documentation/DocBook/media/Makefile
@@ -195,7 +195,7 @@ DVB_DOCUMENTED = \
 #
 
 install_media_images = \
-	$(Q)cp $(OBJIMGFILES) $(MEDIA_SRC_DIR)/v4l/*.svg $(MEDIA_OBJ_DIR)/media_api
+	$(Q)-cp $(OBJIMGFILES) $(MEDIA_SRC_DIR)/v4l/*.svg $(MEDIA_OBJ_DIR)/media_api
 
 $(MEDIA_OBJ_DIR)/%: $(MEDIA_SRC_DIR)/%.b64
 	$(Q)base64 -d $< >$@
diff --git a/Documentation/debugging-via-ohci1394.txt b/Documentation/debugging-via-ohci1394.txt
index fa0151a712f9..5c9a567b3fac 100644
--- a/Documentation/debugging-via-ohci1394.txt
+++ b/Documentation/debugging-via-ohci1394.txt
@@ -25,9 +25,11 @@ using data transfer rates in the order of 10MB/s or more.
 With most FireWire controllers, memory access is limited to the low 4 GB
 of physical address space.  This can be a problem on IA64 machines where
 memory is located mostly above that limit, but it is rarely a problem on
-more common hardware such as x86, x86-64 and PowerPC.  However, at least
-Agere/LSI FW643e and FW643e2 controllers are known to support access to
-physical addresses above 4 GB.
+more common hardware such as x86, x86-64 and PowerPC.
+
+At least LSI FW643e and FW643e2 controllers are known to support access to
+physical addresses above 4 GB, but this feature is currently not enabled by
+Linux.
 
 Together with a early initialization of the OHCI-1394 controller for debugging,
 this facility proved most useful for examining long debugs logs in the printk
@@ -101,8 +103,9 @@ Step-by-step instructions for using firescope with early OHCI initialization:
    compliant, they are based on TI PCILynx chips and require drivers for Win-
    dows operating systems.
 
-   The mentioned kernel log message contains ">4 GB phys DMA" in case of
-   OHCI-1394 controllers which support accesses above this limit.
+   The mentioned kernel log message contains the string "physUB" if the
+   controller implements a writable Physical Upper Bound register.  This is
+   required for physical DMA above 4 GB (but not utilized by Linux yet).
 
 2) Establish a working FireWire cable connection:
 
diff --git a/Documentation/device-mapper/thin-provisioning.txt b/Documentation/device-mapper/thin-provisioning.txt
index 05a27e9442bd..2f5173500bd9 100644
--- a/Documentation/device-mapper/thin-provisioning.txt
+++ b/Documentation/device-mapper/thin-provisioning.txt
@@ -309,7 +309,10 @@ ii) Status
     error_if_no_space|queue_if_no_space
 	If the pool runs out of data or metadata space, the pool will
 	either queue or error the IO destined to the data device.  The
-	default is to queue the IO until more space is added.
+	default is to queue the IO until more space is added or the
+	'no_space_timeout' expires.  The 'no_space_timeout' dm-thin-pool
+	module parameter can be used to change this timeout -- it
+	defaults to 60 seconds but may be disabled using a value of 0.
 
 iii) Messages
 
diff --git a/Documentation/devicetree/bindings/clock/at91-clock.txt b/Documentation/devicetree/bindings/clock/at91-clock.txt
index cd5e23912888..6794cdc96d8f 100644
--- a/Documentation/devicetree/bindings/clock/at91-clock.txt
+++ b/Documentation/devicetree/bindings/clock/at91-clock.txt
@@ -62,7 +62,7 @@ Required properties for PMC node:
 - interrupt-controller : tell that the PMC is an interrupt controller.
 - #interrupt-cells : must be set to 1. The first cell encodes the interrupt id,
 	and reflect the bit position in the PMC_ER/DR/SR registers.
-	You can use the dt macros defined in dt-bindings/clk/at91.h.
+	You can use the dt macros defined in dt-bindings/clock/at91.h.
 	0 (AT91_PMC_MOSCS) -> main oscillator ready
 	1 (AT91_PMC_LOCKA) -> PLL A ready
 	2 (AT91_PMC_LOCKB) -> PLL B ready
diff --git a/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt b/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt
index 5992dceec7af..02a25d99ca61 100644
--- a/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt
+++ b/Documentation/devicetree/bindings/clock/renesas,cpg-mstp-clocks.txt
@@ -43,7 +43,7 @@ Example
 		clock-output-names =
 			"tpu0", "mmcif1", "sdhi3", "sdhi2",
 			 "sdhi1", "sdhi0", "mmcif0";
-		renesas,clock-indices = <
+		clock-indices = <
 			R8A7790_CLK_TPU0 R8A7790_CLK_MMCIF1 R8A7790_CLK_SDHI3
 			R8A7790_CLK_SDHI2 R8A7790_CLK_SDHI1 R8A7790_CLK_SDHI0
 			R8A7790_CLK_MMCIF0
diff --git a/Documentation/devicetree/bindings/dma/ti-edma.txt b/Documentation/devicetree/bindings/dma/ti-edma.txt
index 9fbbdb783a72..68ff2137bae7 100644
--- a/Documentation/devicetree/bindings/dma/ti-edma.txt
+++ b/Documentation/devicetree/bindings/dma/ti-edma.txt
@@ -29,6 +29,6 @@ edma: edma@49000000 {
 	dma-channels = <64>;
 	ti,edma-regions = <4>;
 	ti,edma-slots = <256>;
-	ti,edma-xbar-event-map = <1 12
-				  2 13>;
+	ti,edma-xbar-event-map = /bits/ 16 <1 12
+					    2 13>;
 };
diff --git a/Documentation/devicetree/bindings/net/mdio-gpio.txt b/Documentation/devicetree/bindings/net/mdio-gpio.txt
index c79bab025369..8dbcf8295c6c 100644
--- a/Documentation/devicetree/bindings/net/mdio-gpio.txt
+++ b/Documentation/devicetree/bindings/net/mdio-gpio.txt
@@ -14,7 +14,7 @@ node.
 Example:
 
 aliases {
-	mdio-gpio0 = <&mdio0>;
+	mdio-gpio0 = &mdio0;
 };
 
 mdio0: mdio {
diff --git a/Documentation/email-clients.txt b/Documentation/email-clients.txt
index e9f5daccbd02..4e30ebaa9e5b 100644
--- a/Documentation/email-clients.txt
+++ b/Documentation/email-clients.txt
@@ -201,20 +201,15 @@ To beat some sense out of the internal editor, do this:
 
 - Edit your Thunderbird config settings so that it won't use format=flowed.
   Go to "edit->preferences->advanced->config editor" to bring up the
-  thunderbird's registry editor, and set "mailnews.send_plaintext_flowed" to
-  "false".
+  thunderbird's registry editor.
 
-- Disable HTML Format: Set "mail.identity.id1.compose_html" to "false".
+- Set "mailnews.send_plaintext_flowed" to "false"
 
-- Enable "preformat" mode: Set "editor.quotesPreformatted" to "true".
+- Set "mailnews.wraplength" from "72" to "0"
 
-- Enable UTF8: Set "prefs.converted-to-utf8" to "true".
+- "View" > "Message Body As" > "Plain Text"
 
-- Install the "toggle wordwrap" extension.  Download the file from:
-    https://addons.mozilla.org/thunderbird/addon/2351/
-  Then go to "tools->add ons", select "install" at the bottom of the screen,
-  and browse to where you saved the .xul file.  This adds an "Enable
-  Wordwrap" entry under the Options menu of the message composer.
+- "View" > "Character Encoding" > "Unicode (UTF-8)"
 
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 TkRat (GUI)
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 8b9cd8eb3f91..264bcde0c51c 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -1245,8 +1245,9 @@ second).  The meanings of the columns are as follows, from left to right:
 
 The "intr" line gives counts of interrupts  serviced since boot time, for each
 of the  possible system interrupts.   The first  column  is the  total of  all
-interrupts serviced; each  subsequent column is the  total for that particular
-interrupt.
+interrupts serviced  including  unnumbered  architecture specific  interrupts;
+each  subsequent column is the  total for that particular numbered interrupt.
+Unnumbered interrupts are not shown, only summed into the total.
 
 The "ctxt" line gives the total number of context switches across all CPUs.
 
diff --git a/Documentation/hwmon/sysfs-interface b/Documentation/hwmon/sysfs-interface
index 79f8257dd790..2cc95ad46604 100644
--- a/Documentation/hwmon/sysfs-interface
+++ b/Documentation/hwmon/sysfs-interface
@@ -327,6 +327,13 @@ temp[1-*]_max_hyst
 		from the max value.
 		RW
 
+temp[1-*]_min_hyst
+		Temperature hysteresis value for min limit.
+		Unit: millidegree Celsius
+		Must be reported as an absolute temperature, NOT a delta
+		from the min value.
+		RW
+
 temp[1-*]_input Temperature input value.
 		Unit: millidegree Celsius
 		RO
@@ -362,6 +369,13 @@ temp[1-*]_lcrit	Temperature critical min value, typically lower than
 		Unit: millidegree Celsius
 		RW
 
+temp[1-*]_lcrit_hyst
+		Temperature hysteresis value for critical min limit.
+		Unit: millidegree Celsius
+		Must be reported as an absolute temperature, NOT a delta
+		from the critical min value.
+		RW
+
 temp[1-*]_offset
 		Temperature offset which is added to the temperature reading
 		by the chip.
diff --git a/Documentation/input/elantech.txt b/Documentation/input/elantech.txt
index 5602eb71ad5d..e1ae127ed099 100644
--- a/Documentation/input/elantech.txt
+++ b/Documentation/input/elantech.txt
@@ -504,9 +504,12 @@ byte 5:
 * reg_10
 
    bit   7   6   5   4   3   2   1   0
-         0   0   0   0   0   0   0   A
+         0   0   0   0   R   F   T   A
 
          A: 1 = enable absolute tracking
+         T: 1 = enable two finger mode auto correct
+         F: 1 = disable ABS Position Filter
+         R: 1 = enable real hardware resolution
 
 6.2 Native absolute mode 6 byte packet format
     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
diff --git a/Documentation/java.txt b/Documentation/java.txt
index e6a723281547..418020584ccc 100644
--- a/Documentation/java.txt
+++ b/Documentation/java.txt
@@ -188,6 +188,9 @@ shift
 #define CP_METHODREF 10
 #define CP_INTERFACEMETHODREF 11
 #define CP_NAMEANDTYPE 12
+#define CP_METHODHANDLE 15
+#define CP_METHODTYPE 16
+#define CP_INVOKEDYNAMIC 18
 
 /* Define some commonly used error messages */
 
@@ -242,14 +245,19 @@ void skip_constant(FILE *classfile, u_int16_t *cur)
 		break;
 	case CP_CLASS:
 	case CP_STRING:
+	case CP_METHODTYPE:
 		seekerr = fseek(classfile, 2, SEEK_CUR);
 		break;
+	case CP_METHODHANDLE:
+		seekerr = fseek(classfile, 3, SEEK_CUR);
+		break;
 	case CP_INTEGER:
 	case CP_FLOAT:
 	case CP_FIELDREF:
 	case CP_METHODREF:
 	case CP_INTERFACEMETHODREF:
 	case CP_NAMEANDTYPE:
+	case CP_INVOKEDYNAMIC:
 		seekerr = fseek(classfile, 4, SEEK_CUR);
 		break;
 	case CP_LONG:
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 43842177b771..30a8ad0dae53 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2218,10 +2218,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	noreplace-smp	[X86-32,SMP] Don't replace SMP instructions
 			with UP alternatives
 
-	nordrand	[X86] Disable the direct use of the RDRAND
-			instruction even if it is supported by the
-			processor.  RDRAND is still available to user
-			space applications.
+	nordrand	[X86] Disable kernel use of the RDRAND and
+			RDSEED instructions even if they are supported
+			by the processor.  RDRAND and RDSEED are still
+			available to user space applications.
 
 	noresume	[SWSUSP] Disables resume and restores original swap
 			space.
diff --git a/Documentation/networking/filter.txt b/Documentation/networking/filter.txt
index 81f940f4e884..e3ba753cb714 100644
--- a/Documentation/networking/filter.txt
+++ b/Documentation/networking/filter.txt
@@ -277,7 +277,7 @@ Possible BPF extensions are shown in the following table:
   mark                                  skb->mark
   queue                                 skb->queue_mapping
   hatype                                skb->dev->type
-  rxhash                                skb->rxhash
+  rxhash                                skb->hash
   cpu                                   raw_smp_processor_id()
   vlan_tci                              vlan_tx_tag_get(skb)
   vlan_pr                               vlan_tx_tag_present(skb)
diff --git a/Documentation/networking/packet_mmap.txt b/Documentation/networking/packet_mmap.txt
index 6fea79efb4cb..38112d512f47 100644
--- a/Documentation/networking/packet_mmap.txt
+++ b/Documentation/networking/packet_mmap.txt
@@ -578,7 +578,7 @@ processes. This also works in combination with mmap(2) on packet sockets.
 
 Currently implemented fanout policies are:
 
-  - PACKET_FANOUT_HASH: schedule to socket by skb's rxhash
+  - PACKET_FANOUT_HASH: schedule to socket by skb's packet hash
   - PACKET_FANOUT_LB: schedule to socket by round-robin
   - PACKET_FANOUT_CPU: schedule to socket by CPU packet arrives on
   - PACKET_FANOUT_RND: schedule to socket by random selection
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index a9380ba54c8e..b4f53653c106 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -2126,7 +2126,7 @@ into the hash PTE second double word).
 4.75 KVM_IRQFD
 
 Capability: KVM_CAP_IRQFD
-Architectures: x86
+Architectures: x86 s390
 Type: vm ioctl
 Parameters: struct kvm_irqfd (in)
 Returns: 0 on success, -1 on error
diff --git a/MAINTAINERS b/MAINTAINERS
index 51ebb779c5f3..8ccf31c95a15 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -537,7 +537,7 @@ L:	linux-alpha@vger.kernel.org
 F:	arch/alpha/
 
 ALTERA TRIPLE SPEED ETHERNET DRIVER
-M:	Vince Bridgers <vbridgers2013@gmail.com
+M:	Vince Bridgers <vbridgers2013@gmail.com>
 L:	netdev@vger.kernel.org
 L:	nios2-dev@lists.rocketboards.org (moderated for non-subscribers)
 S:	Maintained
@@ -1893,14 +1893,15 @@ L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/broadcom/bnx2x/
 
-BROADCOM BCM281XX/BCM11XXX ARM ARCHITECTURE
+BROADCOM BCM281XX/BCM11XXX/BCM216XX ARM ARCHITECTURE
 M:	Christian Daudt <bcm@fixthebug.org>
 M:	Matt Porter <mporter@linaro.org>
 L:	bcm-kernel-feedback-list@broadcom.com
-T:	git git://git.github.com/broadcom/bcm11351
+T:	git git://github.com/broadcom/mach-bcm
 S:	Maintained
 F:	arch/arm/mach-bcm/
 F:	arch/arm/boot/dts/bcm113*
+F:	arch/arm/boot/dts/bcm216*
 F:	arch/arm/boot/dts/bcm281*
 F:	arch/arm/configs/bcm_defconfig
 F:	drivers/mmc/host/sdhci_bcm_kona.c
@@ -2245,12 +2246,6 @@ L:	linux-usb@vger.kernel.org
 S:	Maintained
 F:	drivers/usb/host/ohci-ep93xx.c
 
-CIRRUS LOGIC CS4270 SOUND DRIVER
-M:	Timur Tabi <timur@tabi.org>
-L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
-S:	Odd Fixes
-F:	sound/soc/codecs/cs4270*
-
 CIRRUS LOGIC AUDIO CODEC DRIVERS
 M:	Brian Austin <brian.austin@cirrus.com>
 M:	Paul Handrigan <Paul.Handrigan@cirrus.com>
@@ -4818,6 +4813,14 @@ L:	linux-kernel@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq/core
 F:	kernel/irq/
+
+IRQCHIP DRIVERS
+M:	Thomas Gleixner <tglx@linutronix.de>
+M:	Jason Cooper <jason@lakedaemon.net>
+L:	linux-kernel@vger.kernel.org
+S:	Maintained
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq/core
+T:	git git://git.infradead.org/users/jcooper/linux.git irqchip/core
 F:	drivers/irqchip/
 
 IRQ DOMAINS (IRQ NUMBER MAPPING LIBRARY)
@@ -5490,15 +5493,15 @@ F:	Documentation/hwmon/ltc4261
 F:	drivers/hwmon/ltc4261.c
 
 LTP (Linux Test Project)
-M:	Shubham Goyal <shubham@linux.vnet.ibm.com>
 M:	Mike Frysinger <vapier@gentoo.org>
 M:	Cyril Hrubis <chrubis@suse.cz>
-M:	Caspar Zhang <caspar@casparzhang.com>
 M:	Wanlong Gao <gaowanlong@cn.fujitsu.com>
+M:	Jan Stancek <jstancek@redhat.com>
+M:	Stanislav Kholmanskikh <stanislav.kholmanskikh@oracle.com>
+M:	Alexey Kodanev <alexey.kodanev@oracle.com>
 L:	ltp-list@lists.sourceforge.net (subscribers-only)
-W:	http://ltp.sourceforge.net/
+W:	http://linux-test-project.github.io/
 T:	git git://github.com/linux-test-project/ltp.git
-T:	git git://ltp.git.sourceforge.net/gitroot/ltp/ltp-dev
 S:	Maintained
 
 M32R ARCHITECTURE
@@ -6511,10 +6514,10 @@ T:	git git://openrisc.net/~jonas/linux
 F:	arch/openrisc/
 
 OPENVSWITCH
-M:	Jesse Gross <jesse@nicira.com>
+M:	Pravin Shelar <pshelar@nicira.com>
 L:	dev@openvswitch.org
 W:	http://openvswitch.org
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jesse/openvswitch.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/pshelar/openvswitch.git
 S:	Maintained
 F:	net/openvswitch/
 
@@ -7402,6 +7405,14 @@ F:	drivers/rpmsg/
 F:	Documentation/rpmsg.txt
 F:	include/linux/rpmsg.h
 
+RESET CONTROLLER FRAMEWORK
+M:	Philipp Zabel <p.zabel@pengutronix.de>
+S:	Maintained
+F:	drivers/reset/
+F:	Documentation/devicetree/bindings/reset/
+F:	include/linux/reset.h
+F:	include/linux/reset-controller.h
+
 RFKILL
 M:	Johannes Berg <johannes@sipsolutions.net>
 L:	linux-wireless@vger.kernel.org
@@ -9107,6 +9118,9 @@ F:	arch/um/os-Linux/drivers/
 
 TURBOCHANNEL SUBSYSTEM
 M:	"Maciej W. Rozycki" <macro@linux-mips.org>
+M:	Ralf Baechle <ralf@linux-mips.org>
+L:	linux-mips@linux-mips.org
+Q:	http://patchwork.linux-mips.org/project/linux-mips/list/
 S:	Maintained
 F:	drivers/tc/
 F:	include/linux/tc.h
diff --git a/Makefile b/Makefile
index 28a7259e0f3b..cf3412d78ff1 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 3
 PATCHLEVEL = 15
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc7
 NAME = Shuffling Zombie Juror
 
 # *DOCUMENTATION*
diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi
index cb6811e5ae5a..7ad75b4e0663 100644
--- a/arch/arm/boot/dts/am33xx.dtsi
+++ b/arch/arm/boot/dts/am33xx.dtsi
@@ -144,7 +144,7 @@
 			compatible = "ti,edma3";
 			ti,hwmods = "tpcc", "tptc0", "tptc1", "tptc2";
 			reg =	<0x49000000 0x10000>,
-				<0x44e10f90 0x10>;
+				<0x44e10f90 0x40>;
 			interrupts = <12 13 14>;
 			#dma-cells = <1>;
 			dma-channels = <64>;
diff --git a/arch/arm/boot/dts/am3517.dtsi b/arch/arm/boot/dts/am3517.dtsi
index 788391f91684..5a452fdd7c5d 100644
--- a/arch/arm/boot/dts/am3517.dtsi
+++ b/arch/arm/boot/dts/am3517.dtsi
@@ -62,5 +62,21 @@
 	};
 };
 
+&iva {
+	status = "disabled";
+};
+
+&mailbox {
+	status = "disabled";
+};
+
+&mmu_isp {
+	status = "disabled";
+};
+
+&smartreflex_mpu_iva {
+	status = "disabled";
+};
+
 /include/ "am35xx-clocks.dtsi"
 /include/ "omap36xx-am35xx-omap3430es2plus-clocks.dtsi"
diff --git a/arch/arm/boot/dts/am437x-gp-evm.dts b/arch/arm/boot/dts/am437x-gp-evm.dts
index df8798e8bd25..a055f7f0f14a 100644
--- a/arch/arm/boot/dts/am437x-gp-evm.dts
+++ b/arch/arm/boot/dts/am437x-gp-evm.dts
@@ -117,6 +117,11 @@
 	status = "okay";
 };
 
+&gpio5 {
+	status = "okay";
+	ti,no-reset-on-init;
+};
+
 &mmc1 {
 	status = "okay";
 	vmmc-supply = <&vmmcsd_fixed>;
diff --git a/arch/arm/boot/dts/armada-370-db.dts b/arch/arm/boot/dts/armada-370-db.dts
index 82f238a9063f..3383c4b66803 100644
--- a/arch/arm/boot/dts/armada-370-db.dts
+++ b/arch/arm/boot/dts/armada-370-db.dts
@@ -67,6 +67,7 @@
 			i2c@11000 {
 				pinctrl-0 = <&i2c0_pins>;
 				pinctrl-names = "default";
+				clock-frequency = <100000>;
 				status = "okay";
 				audio_codec: audio-codec@4a {
 					compatible = "cirrus,cs42l51";
diff --git a/arch/arm/boot/dts/armada-375-db.dts b/arch/arm/boot/dts/armada-375-db.dts
index 9378d3136b41..0451124e8ebf 100644
--- a/arch/arm/boot/dts/armada-375-db.dts
+++ b/arch/arm/boot/dts/armada-375-db.dts
@@ -79,6 +79,11 @@
 				};
 			};
 
+			sata@a0000 {
+				status = "okay";
+				nr-ports = <2>;
+			};
+
 			nand: nand@d0000 {
 				pinctrl-0 = <&nand_pins>;
 				pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/armada-380.dtsi b/arch/arm/boot/dts/armada-380.dtsi
index 068031f0f263..6d0f03c98ee9 100644
--- a/arch/arm/boot/dts/armada-380.dtsi
+++ b/arch/arm/boot/dts/armada-380.dtsi
@@ -99,7 +99,7 @@
 			pcie@3,0 {
 				device_type = "pci";
 				assigned-addresses = <0x82000800 0 0x44000 0 0x2000>;
-				reg = <0x1000 0 0 0 0>;
+				reg = <0x1800 0 0 0 0>;
 				#address-cells = <3>;
 				#size-cells = <2>;
 				#interrupt-cells = <1>;
diff --git a/arch/arm/boot/dts/armada-385.dtsi b/arch/arm/boot/dts/armada-385.dtsi
index e2919f02e1d4..da801964a257 100644
--- a/arch/arm/boot/dts/armada-385.dtsi
+++ b/arch/arm/boot/dts/armada-385.dtsi
@@ -110,7 +110,7 @@
 			pcie@3,0 {
 				device_type = "pci";
 				assigned-addresses = <0x82000800 0 0x44000 0 0x2000>;
-				reg = <0x1000 0 0 0 0>;
+				reg = <0x1800 0 0 0 0>;
 				#address-cells = <3>;
 				#size-cells = <2>;
 				#interrupt-cells = <1>;
@@ -131,7 +131,7 @@
 			pcie@4,0 {
 				device_type = "pci";
 				assigned-addresses = <0x82000800 0 0x48000 0 0x2000>;
-				reg = <0x1000 0 0 0 0>;
+				reg = <0x2000 0 0 0 0>;
 				#address-cells = <3>;
 				#size-cells = <2>;
 				#interrupt-cells = <1>;
diff --git a/arch/arm/boot/dts/armada-xp-db.dts b/arch/arm/boot/dts/armada-xp-db.dts
index 448373c4b0e5..90f0bf6f9271 100644
--- a/arch/arm/boot/dts/armada-xp-db.dts
+++ b/arch/arm/boot/dts/armada-xp-db.dts
@@ -49,7 +49,7 @@
 			/* Device Bus parameters are required */
 
 			/* Read parameters */
-			devbus,bus-width    = <8>;
+			devbus,bus-width    = <16>;
 			devbus,turn-off-ps  = <60000>;
 			devbus,badr-skew-ps = <0>;
 			devbus,acc-first-ps = <124000>;
diff --git a/arch/arm/boot/dts/armada-xp-gp.dts b/arch/arm/boot/dts/armada-xp-gp.dts
index 61bda687f782..0c756421ae6a 100644
--- a/arch/arm/boot/dts/armada-xp-gp.dts
+++ b/arch/arm/boot/dts/armada-xp-gp.dts
@@ -59,7 +59,7 @@
 			/* Device Bus parameters are required */
 
 			/* Read parameters */
-			devbus,bus-width    = <8>;
+			devbus,bus-width    = <16>;
 			devbus,turn-off-ps  = <60000>;
 			devbus,badr-skew-ps = <0>;
 			devbus,acc-first-ps = <124000>;
@@ -146,22 +146,22 @@
 			ethernet@70000 {
 				status = "okay";
 				phy = <&phy0>;
-				phy-mode = "rgmii-id";
+				phy-mode = "qsgmii";
 			};
 			ethernet@74000 {
 				status = "okay";
 				phy = <&phy1>;
-				phy-mode = "rgmii-id";
+				phy-mode = "qsgmii";
 			};
 			ethernet@30000 {
 				status = "okay";
 				phy = <&phy2>;
-				phy-mode = "rgmii-id";
+				phy-mode = "qsgmii";
 			};
 			ethernet@34000 {
 				status = "okay";
 				phy = <&phy3>;
-				phy-mode = "rgmii-id";
+				phy-mode = "qsgmii";
 			};
 
 			/* Front-side USB slot */
diff --git a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
index 985948ce67b3..5d42feb31049 100644
--- a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
+++ b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts
@@ -39,7 +39,7 @@
 			/* Device Bus parameters are required */
 
 			/* Read parameters */
-			devbus,bus-width    = <8>;
+			devbus,bus-width    = <16>;
 			devbus,turn-off-ps  = <60000>;
 			devbus,badr-skew-ps = <0>;
 			devbus,acc-first-ps = <124000>;
diff --git a/arch/arm/boot/dts/at91-sama5d3_xplained.dts b/arch/arm/boot/dts/at91-sama5d3_xplained.dts
index ce1375595e5f..4537259ce529 100644
--- a/arch/arm/boot/dts/at91-sama5d3_xplained.dts
+++ b/arch/arm/boot/dts/at91-sama5d3_xplained.dts
@@ -34,7 +34,7 @@
 			};
 
 			spi0: spi@f0004000 {
-				cs-gpios = <&pioD 13 0>;
+				cs-gpios = <&pioD 13 0>, <0>, <0>, <&pioD 16 0>;
 				status = "okay";
 			};
 
@@ -79,7 +79,7 @@
 			};
 
 			spi1: spi@f8008000 {
-				cs-gpios = <&pioC 25 0>, <0>, <0>, <&pioD 16 0>;
+				cs-gpios = <&pioC 25 0>;
 				status = "okay";
 			};
 
diff --git a/arch/arm/boot/dts/at91sam9260.dtsi b/arch/arm/boot/dts/at91sam9260.dtsi
index 366fc2cbcd64..c0e0eae16a27 100644
--- a/arch/arm/boot/dts/at91sam9260.dtsi
+++ b/arch/arm/boot/dts/at91sam9260.dtsi
@@ -641,7 +641,7 @@
 				trigger@3 {
 					reg = <3>;
 					trigger-name = "external";
-					trigger-value = <0x13>;
+					trigger-value = <0xd>;
 					trigger-external;
 				};
 			};
diff --git a/arch/arm/boot/dts/at91sam9261.dtsi b/arch/arm/boot/dts/at91sam9261.dtsi
index e21dda0e8986..3be973e9889a 100644
--- a/arch/arm/boot/dts/at91sam9261.dtsi
+++ b/arch/arm/boot/dts/at91sam9261.dtsi
@@ -10,7 +10,7 @@
 #include <dt-bindings/pinctrl/at91.h>
 #include <dt-bindings/interrupt-controller/irq.h>
 #include <dt-bindings/gpio/gpio.h>
-#include <dt-bindings/clk/at91.h>
+#include <dt-bindings/clock/at91.h>
 
 / {
 	model = "Atmel AT91SAM9261 family SoC";
diff --git a/arch/arm/boot/dts/at91sam9rl.dtsi b/arch/arm/boot/dts/at91sam9rl.dtsi
index 63e1784d272c..92a52faebef7 100644
--- a/arch/arm/boot/dts/at91sam9rl.dtsi
+++ b/arch/arm/boot/dts/at91sam9rl.dtsi
@@ -8,7 +8,7 @@
 
 #include "skeleton.dtsi"
 #include <dt-bindings/pinctrl/at91.h>
-#include <dt-bindings/clk/at91.h>
+#include <dt-bindings/clock/at91.h>
 #include <dt-bindings/interrupt-controller/irq.h>
 #include <dt-bindings/gpio/gpio.h>
 
diff --git a/arch/arm/boot/dts/exynos4412-trats2.dts b/arch/arm/boot/dts/exynos4412-trats2.dts
index 9583563dd0ef..8a558b7ac999 100644
--- a/arch/arm/boot/dts/exynos4412-trats2.dts
+++ b/arch/arm/boot/dts/exynos4412-trats2.dts
@@ -503,7 +503,7 @@
 		status = "okay";
 
 		ak8975@0c {
-			compatible = "ak,ak8975";
+			compatible = "asahi-kasei,ak8975";
 			reg = <0x0c>;
 			gpios = <&gpj0 7 0>;
 		};
diff --git a/arch/arm/boot/dts/exynos5250-arndale.dts b/arch/arm/boot/dts/exynos5250-arndale.dts
index 090f9830b129..cde19c818667 100644
--- a/arch/arm/boot/dts/exynos5250-arndale.dts
+++ b/arch/arm/boot/dts/exynos5250-arndale.dts
@@ -107,6 +107,7 @@
 					regulator-name = "VDD_IOPERI_1.8V";
 					regulator-min-microvolt = <1800000>;
 					regulator-max-microvolt = <1800000>;
+					regulator-always-on;
 					op_mode = <1>;
 				};
 
diff --git a/arch/arm/boot/dts/exynos5420-arndale-octa.dts b/arch/arm/boot/dts/exynos5420-arndale-octa.dts
index 80a3bf4c5986..896a2a6619e0 100644
--- a/arch/arm/boot/dts/exynos5420-arndale-octa.dts
+++ b/arch/arm/boot/dts/exynos5420-arndale-octa.dts
@@ -364,16 +364,4 @@
 			gpio-key,wakeup;
 		};
 	};
-
-	amba {
-		mdma1: mdma@11C10000 {
-			/*
-			 * MDMA1 can support both secure and non-secure
-			 * AXI transactions. When this is enabled in the kernel
-			 * for boards that run in secure mode, we are getting
-			 * imprecise external aborts causing the kernel to oops.
-			 */
-			status = "disabled";
-		};
-	};
 };
diff --git a/arch/arm/boot/dts/exynos5420.dtsi b/arch/arm/boot/dts/exynos5420.dtsi
index c3a9a66c5767..b69fbcb7dcb8 100644
--- a/arch/arm/boot/dts/exynos5420.dtsi
+++ b/arch/arm/boot/dts/exynos5420.dtsi
@@ -219,16 +219,6 @@
 		reg = <0x100440C0 0x20>;
 	};
 
-	mau_pd: power-domain@100440E0 {
-		compatible = "samsung,exynos4210-pd";
-		reg = <0x100440E0 0x20>;
-	};
-
-	g2d_pd: power-domain@10044100 {
-		compatible = "samsung,exynos4210-pd";
-		reg = <0x10044100 0x20>;
-	};
-
 	msc_pd: power-domain@10044120 {
 		compatible = "samsung,exynos4210-pd";
 		reg = <0x10044120 0x20>;
@@ -336,6 +326,13 @@
 			#dma-cells = <1>;
 			#dma-channels = <8>;
 			#dma-requests = <1>;
+			/*
+			 * MDMA1 can support both secure and non-secure
+			 * AXI transactions. When this is enabled in the kernel
+			 * for boards that run in secure mode, we are getting
+			 * imprecise external aborts causing the kernel to oops.
+			 */
+			status = "disabled";
 		};
 	};
 
@@ -385,7 +382,7 @@
 	spi_0: spi@12d20000 {
 		compatible = "samsung,exynos4210-spi";
 		reg = <0x12d20000 0x100>;
-		interrupts = <0 66 0>;
+		interrupts = <0 68 0>;
 		dmas = <&pdma0 5
 			&pdma0 4>;
 		dma-names = "tx", "rx";
@@ -401,7 +398,7 @@
 	spi_1: spi@12d30000 {
 		compatible = "samsung,exynos4210-spi";
 		reg = <0x12d30000 0x100>;
-		interrupts = <0 67 0>;
+		interrupts = <0 69 0>;
 		dmas = <&pdma1 5
 			&pdma1 4>;
 		dma-names = "tx", "rx";
@@ -417,7 +414,7 @@
 	spi_2: spi@12d40000 {
 		compatible = "samsung,exynos4210-spi";
 		reg = <0x12d40000 0x100>;
-		interrupts = <0 68 0>;
+		interrupts = <0 70 0>;
 		dmas = <&pdma0 7
 			&pdma0 6>;
 		dma-names = "tx", "rx";
@@ -730,6 +727,5 @@
 		interrupts = <0 112 0>;
 		clocks = <&clock 471>;
 		clock-names = "secss";
-		samsung,power-domain = <&g2d_pd>;
 	};
 };
diff --git a/arch/arm/boot/dts/imx53-mba53.dts b/arch/arm/boot/dts/imx53-mba53.dts
index 7c8c12969892..a3431d784870 100644
--- a/arch/arm/boot/dts/imx53-mba53.dts
+++ b/arch/arm/boot/dts/imx53-mba53.dts
@@ -244,7 +244,7 @@
 &tve {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_vga_sync_1>;
-	i2c-ddc-bus = <&i2c3>;
+	ddc-i2c-bus = <&i2c3>;
 	fsl,tve-mode = "vga";
 	fsl,hsync-pin = <4>;
 	fsl,vsync-pin = <6>;
diff --git a/arch/arm/boot/dts/imx53.dtsi b/arch/arm/boot/dts/imx53.dtsi
index 9c2bff2252d0..6a1bf4ff83d5 100644
--- a/arch/arm/boot/dts/imx53.dtsi
+++ b/arch/arm/boot/dts/imx53.dtsi
@@ -115,7 +115,7 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			compatible = "fsl,imx53-ipu";
-			reg = <0x18000000 0x080000000>;
+			reg = <0x18000000 0x08000000>;
 			interrupts = <11 10>;
 			clocks = <&clks IMX5_CLK_IPU_GATE>,
 			         <&clks IMX5_CLK_IPU_DI0_GATE>,
diff --git a/arch/arm/boot/dts/kirkwood-mv88f6281gtw-ge.dts b/arch/arm/boot/dts/kirkwood-mv88f6281gtw-ge.dts
index 32c6fb4a1162..b939f4f52d16 100644
--- a/arch/arm/boot/dts/kirkwood-mv88f6281gtw-ge.dts
+++ b/arch/arm/boot/dts/kirkwood-mv88f6281gtw-ge.dts
@@ -30,6 +30,16 @@
 		bootargs = "console=ttyS0,115200n8 earlyprintk";
 	};
 
+	mbus {
+		pcie-controller {
+			status = "okay";
+
+			pcie@1,0 {
+				status = "okay";
+			};
+		};
+        };
+
 	ocp@f1000000 {
 		pinctrl@10000 {
 			pmx_usb_led: pmx-usb-led {
@@ -73,14 +83,6 @@
 		ehci@50000 {
 			status = "okay";
 		};
-
-		pcie-controller {
-			status = "okay";
-
-			pcie@1,0 {
-				status = "okay";
-			};
-		};
 	};
 
 	gpio-leds {
diff --git a/arch/arm/boot/dts/kirkwood-nsa310-common.dtsi b/arch/arm/boot/dts/kirkwood-nsa310-common.dtsi
index aa78c2d11fe7..e2cc85cc3b87 100644
--- a/arch/arm/boot/dts/kirkwood-nsa310-common.dtsi
+++ b/arch/arm/boot/dts/kirkwood-nsa310-common.dtsi
@@ -4,6 +4,16 @@
 / {
 	model = "ZyXEL NSA310";
 
+	mbus {
+		pcie-controller {
+			status = "okay";
+
+			pcie@1,0 {
+				status = "okay";
+			};
+		};
+	};
+
 	ocp@f1000000 {
 		pinctrl: pinctrl@10000 {
 
@@ -26,14 +36,6 @@
 			status = "okay";
 			nr-ports = <2>;
 		};
-
-		pcie-controller {
-			status = "okay";
-
-			pcie@1,0 {
-				status = "okay";
-			};
-		};
 	};
 
 	gpio_poweroff {
diff --git a/arch/arm/boot/dts/kirkwood-t5325.dts b/arch/arm/boot/dts/kirkwood-t5325.dts
index 7d1c7677a18f..0bd70d928c69 100644
--- a/arch/arm/boot/dts/kirkwood-t5325.dts
+++ b/arch/arm/boot/dts/kirkwood-t5325.dts
@@ -127,11 +127,6 @@
 
 		i2c@11000 {
 			status = "okay";
-
-			alc5621: alc5621@1a {
-				compatible = "realtek,alc5621";
-				reg = <0x1a>;
-			};
 		};
 
 		serial@12000 {
diff --git a/arch/arm/boot/dts/omap-gpmc-smsc911x.dtsi b/arch/arm/boot/dts/omap-gpmc-smsc911x.dtsi
index f577b7df9a29..521c587acaee 100644
--- a/arch/arm/boot/dts/omap-gpmc-smsc911x.dtsi
+++ b/arch/arm/boot/dts/omap-gpmc-smsc911x.dtsi
@@ -24,11 +24,10 @@
 		compatible = "smsc,lan9221", "smsc,lan9115";
 		bank-width = <2>;
 		gpmc,mux-add-data;
-		gpmc,cs-on-ns = <0>;
-		gpmc,cs-rd-off-ns = <186>;
-		gpmc,cs-wr-off-ns = <186>;
-		gpmc,adv-on-ns = <12>;
-		gpmc,adv-rd-off-ns = <48>;
+		gpmc,cs-on-ns = <1>;
+		gpmc,cs-rd-off-ns = <180>;
+		gpmc,cs-wr-off-ns = <180>;
+		gpmc,adv-rd-off-ns = <18>;
 		gpmc,adv-wr-off-ns = <48>;
 		gpmc,oe-on-ns = <54>;
 		gpmc,oe-off-ns = <168>;
@@ -36,12 +35,10 @@
 		gpmc,we-off-ns = <168>;
 		gpmc,rd-cycle-ns = <186>;
 		gpmc,wr-cycle-ns = <186>;
-		gpmc,access-ns = <114>;
-		gpmc,page-burst-access-ns = <6>;
-		gpmc,bus-turnaround-ns = <12>;
-		gpmc,cycle2cycle-delay-ns = <18>;
-		gpmc,wr-data-mux-bus-ns = <90>;
-		gpmc,wr-access-ns = <186>;
+		gpmc,access-ns = <144>;
+		gpmc,page-burst-access-ns = <24>;
+		gpmc,bus-turnaround-ns = <90>;
+		gpmc,cycle2cycle-delay-ns = <90>;
 		gpmc,cycle2cycle-samecsen;
 		gpmc,cycle2cycle-diffcsen;
 		vddvario-supply = <&vddvario>;
diff --git a/arch/arm/boot/dts/omap2.dtsi b/arch/arm/boot/dts/omap2.dtsi
index 22f35ea142c1..8f8c07da4ac1 100644
--- a/arch/arm/boot/dts/omap2.dtsi
+++ b/arch/arm/boot/dts/omap2.dtsi
@@ -71,13 +71,6 @@
 			interrupts = <58>;
 		};
 
-		mailbox: mailbox@48094000 {
-			compatible = "ti,omap2-mailbox";
-			ti,hwmods = "mailbox";
-			reg = <0x48094000 0x200>;
-			interrupts = <26>;
-		};
-
 		intc: interrupt-controller@1 {
 			compatible = "ti,omap2-intc";
 			interrupt-controller;
diff --git a/arch/arm/boot/dts/omap2420.dtsi b/arch/arm/boot/dts/omap2420.dtsi
index 85b1fb014c43..2d9979835f24 100644
--- a/arch/arm/boot/dts/omap2420.dtsi
+++ b/arch/arm/boot/dts/omap2420.dtsi
@@ -125,6 +125,14 @@
 			dma-names = "tx", "rx";
 		};
 
+		mailbox: mailbox@48094000 {
+			compatible = "ti,omap2-mailbox";
+			reg = <0x48094000 0x200>;
+			interrupts = <26>, <34>;
+			interrupt-names = "dsp", "iva";
+			ti,hwmods = "mailbox";
+		};
+
 		timer1: timer@48028000 {
 			compatible = "ti,omap2420-timer";
 			reg = <0x48028000 0x400>;
diff --git a/arch/arm/boot/dts/omap2430.dtsi b/arch/arm/boot/dts/omap2430.dtsi
index d09697dab55e..42d2c61c9e2d 100644
--- a/arch/arm/boot/dts/omap2430.dtsi
+++ b/arch/arm/boot/dts/omap2430.dtsi
@@ -216,6 +216,13 @@
 			dma-names = "tx", "rx";
 		};
 
+		mailbox: mailbox@48094000 {
+			compatible = "ti,omap2-mailbox";
+			reg = <0x48094000 0x200>;
+			interrupts = <26>;
+			ti,hwmods = "mailbox";
+		};
+
 		timer1: timer@49018000 {
 			compatible = "ti,omap2420-timer";
 			reg = <0x49018000 0x400>;
diff --git a/arch/arm/boot/dts/omap3-cm-t3x30.dtsi b/arch/arm/boot/dts/omap3-cm-t3x30.dtsi
index d00055809e31..25ba08331d88 100644
--- a/arch/arm/boot/dts/omap3-cm-t3x30.dtsi
+++ b/arch/arm/boot/dts/omap3-cm-t3x30.dtsi
@@ -10,18 +10,6 @@
 			cpu0-supply = <&vcc>;
 		};
 	};
-
-	vddvario: regulator-vddvario {
-		compatible = "regulator-fixed";
-		regulator-name = "vddvario";
-		regulator-always-on;
-	};
-
-	vdd33a: regulator-vdd33a {
-		compatible = "regulator-fixed";
-		regulator-name = "vdd33a";
-		regulator-always-on;
-	};
 };
 
 &omap3_pmx_core {
@@ -35,58 +23,34 @@
 
  	hsusb0_pins: pinmux_hsusb0_pins {
 		pinctrl-single,pins = <
-			OMAP3_CORE1_IOPAD(0x21a0, PIN_OUTPUT | MUX_MODE0)		/* hsusb0_clk.hsusb0_clk */
-			OMAP3_CORE1_IOPAD(0x21a2, PIN_OUTPUT | MUX_MODE0)		/* hsusb0_stp.hsusb0_stp */
-			OMAP3_CORE1_IOPAD(0x21a4, PIN_INPUT_PULLDOWN | MUX_MODE0)	/* hsusb0_dir.hsusb0_dir */
-			OMAP3_CORE1_IOPAD(0x21a6, PIN_INPUT_PULLDOWN | MUX_MODE0)	/* hsusb0_nxt.hsusb0_nxt */
-			OMAP3_CORE1_IOPAD(0x21a8, PIN_INPUT_PULLDOWN | MUX_MODE0)	/* hsusb0_data0.hsusb2_data0 */
-			OMAP3_CORE1_IOPAD(0x21aa, PIN_INPUT_PULLDOWN | MUX_MODE0)	/* hsusb0_data1.hsusb0_data1 */
-			OMAP3_CORE1_IOPAD(0x21ac, PIN_INPUT_PULLDOWN | MUX_MODE0)	/* hsusb0_data2.hsusb0_data2 */
-			OMAP3_CORE1_IOPAD(0x21ae, PIN_INPUT_PULLDOWN | MUX_MODE0)	/* hsusb0_data7.hsusb0_data3 */
-			OMAP3_CORE1_IOPAD(0x21b0, PIN_INPUT_PULLDOWN | MUX_MODE0)	/* hsusb0_data7.hsusb0_data4 */
-			OMAP3_CORE1_IOPAD(0x21b2, PIN_INPUT_PULLDOWN | MUX_MODE0)	/* hsusb0_data7.hsusb0_data5 */
-			OMAP3_CORE1_IOPAD(0x21b4, PIN_INPUT_PULLDOWN | MUX_MODE0)	/* hsusb0_data7.hsusb0_data6 */
-			OMAP3_CORE1_IOPAD(0x21b6, PIN_INPUT_PULLDOWN | MUX_MODE0)	/* hsusb0_data7.hsusb0_data7 */
+			OMAP3_CORE1_IOPAD(0x21a2, PIN_OUTPUT | MUX_MODE0)		/* hsusb0_clk.hsusb0_clk */
+			OMAP3_CORE1_IOPAD(0x21a4, PIN_OUTPUT | MUX_MODE0)		/* hsusb0_stp.hsusb0_stp */
+			OMAP3_CORE1_IOPAD(0x21a6, PIN_INPUT_PULLDOWN | MUX_MODE0)	/* hsusb0_dir.hsusb0_dir */
+			OMAP3_CORE1_IOPAD(0x21a8, PIN_INPUT_PULLDOWN | MUX_MODE0)	/* hsusb0_nxt.hsusb0_nxt */
+			OMAP3_CORE1_IOPAD(0x21aa, PIN_INPUT_PULLDOWN | MUX_MODE0)	/* hsusb0_data0.hsusb2_data0 */
+			OMAP3_CORE1_IOPAD(0x21ac, PIN_INPUT_PULLDOWN | MUX_MODE0)	/* hsusb0_data1.hsusb0_data1 */
+			OMAP3_CORE1_IOPAD(0x21ae, PIN_INPUT_PULLDOWN | MUX_MODE0)	/* hsusb0_data2.hsusb0_data2 */
+			OMAP3_CORE1_IOPAD(0x21b0, PIN_INPUT_PULLDOWN | MUX_MODE0)	/* hsusb0_data7.hsusb0_data3 */
+			OMAP3_CORE1_IOPAD(0x21b2, PIN_INPUT_PULLDOWN | MUX_MODE0)	/* hsusb0_data7.hsusb0_data4 */
+			OMAP3_CORE1_IOPAD(0x21b4, PIN_INPUT_PULLDOWN | MUX_MODE0)	/* hsusb0_data7.hsusb0_data5 */
+			OMAP3_CORE1_IOPAD(0x21b6, PIN_INPUT_PULLDOWN | MUX_MODE0)	/* hsusb0_data7.hsusb0_data6 */
+			OMAP3_CORE1_IOPAD(0x21b8, PIN_INPUT_PULLDOWN | MUX_MODE0)	/* hsusb0_data7.hsusb0_data7 */
 		>;
 	};
 };
 
+#include "omap-gpmc-smsc911x.dtsi"
+
 &gpmc {
 	ranges = <5 0 0x2c000000 0x01000000>;
 
-	smsc1: ethernet@5,0 {
+	smsc1: ethernet@gpmc {
 		compatible = "smsc,lan9221", "smsc,lan9115";
 		pinctrl-names = "default";
 		pinctrl-0 = <&smsc1_pins>;
 		interrupt-parent = <&gpio6>;
 		interrupts = <3 IRQ_TYPE_LEVEL_LOW>;
 		reg = <5 0 0xff>;
-		bank-width = <2>;
-		gpmc,mux-add-data;
-		gpmc,cs-on-ns = <0>;
-		gpmc,cs-rd-off-ns = <186>;
-		gpmc,cs-wr-off-ns = <186>;
-		gpmc,adv-on-ns = <12>;
-		gpmc,adv-rd-off-ns = <48>;
-		gpmc,adv-wr-off-ns = <48>;
-		gpmc,oe-on-ns = <54>;
-		gpmc,oe-off-ns = <168>;
-		gpmc,we-on-ns = <54>;
-		gpmc,we-off-ns = <168>;
-		gpmc,rd-cycle-ns = <186>;
-		gpmc,wr-cycle-ns = <186>;
-		gpmc,access-ns = <114>;
-		gpmc,page-burst-access-ns = <6>;
-		gpmc,bus-turnaround-ns = <12>;
-		gpmc,cycle2cycle-delay-ns = <18>;
-		gpmc,wr-data-mux-bus-ns = <90>;
-		gpmc,wr-access-ns = <186>;
-		gpmc,cycle2cycle-samecsen;
-		gpmc,cycle2cycle-diffcsen;
-		vddvario-supply = <&vddvario>;
-		vdd33a-supply = <&vdd33a>;
-		reg-io-width = <4>;
-		smsc,save-mac-address;
 	};
 };
 
diff --git a/arch/arm/boot/dts/omap3-igep.dtsi b/arch/arm/boot/dts/omap3-igep.dtsi
index b97736d98a64..e2d163bf0619 100644
--- a/arch/arm/boot/dts/omap3-igep.dtsi
+++ b/arch/arm/boot/dts/omap3-igep.dtsi
@@ -107,7 +107,7 @@
 		>;
 	};
 
-	smsc911x_pins: pinmux_smsc911x_pins {
+	smsc9221_pins: pinmux_smsc9221_pins {
 		pinctrl-single,pins = <
 			0x1a2 (PIN_INPUT | MUX_MODE4)		/* mcspi1_cs2.gpio_176 */
 		>;
diff --git a/arch/arm/boot/dts/omap3-igep0020.dts b/arch/arm/boot/dts/omap3-igep0020.dts
index 7abd64f6ae21..b22caaaf774b 100644
--- a/arch/arm/boot/dts/omap3-igep0020.dts
+++ b/arch/arm/boot/dts/omap3-igep0020.dts
@@ -10,7 +10,7 @@
  */
 
 #include "omap3-igep.dtsi"
-#include "omap-gpmc-smsc911x.dtsi"
+#include "omap-gpmc-smsc9221.dtsi"
 
 / {
 	model = "IGEPv2 (TI OMAP AM/DM37x)";
@@ -248,7 +248,7 @@
 
 	ethernet@gpmc {
 		pinctrl-names = "default";
-		pinctrl-0 = <&smsc911x_pins>;
+		pinctrl-0 = <&smsc9221_pins>;
 		reg = <5 0 0xff>;
 		interrupt-parent = <&gpio6>;
 		interrupts = <16 IRQ_TYPE_LEVEL_LOW>;
diff --git a/arch/arm/boot/dts/omap3-sb-t35.dtsi b/arch/arm/boot/dts/omap3-sb-t35.dtsi
index 7909c51b05a5..d59e3de1441e 100644
--- a/arch/arm/boot/dts/omap3-sb-t35.dtsi
+++ b/arch/arm/boot/dts/omap3-sb-t35.dtsi
@@ -2,20 +2,6 @@
  * Common support for CompuLab SB-T35 used on SBC-T3530, SBC-T3517 and SBC-T3730
  */
 
-/ {
-	vddvario_sb_t35: regulator-vddvario-sb-t35 {
-		compatible = "regulator-fixed";
-		regulator-name = "vddvario";
-		regulator-always-on;
-	};
-
-	vdd33a_sb_t35: regulator-vdd33a-sb-t35 {
-		compatible = "regulator-fixed";
-		regulator-name = "vdd33a";
-		regulator-always-on;
-	};
-};
-
 &omap3_pmx_core {
 	smsc2_pins: pinmux_smsc2_pins {
 		pinctrl-single,pins = <
@@ -37,11 +23,10 @@
 		reg = <4 0 0xff>;
 		bank-width = <2>;
 		gpmc,mux-add-data;
-		gpmc,cs-on-ns = <0>;
-		gpmc,cs-rd-off-ns = <186>;
-		gpmc,cs-wr-off-ns = <186>;
-		gpmc,adv-on-ns = <12>;
-		gpmc,adv-rd-off-ns = <48>;
+		gpmc,cs-on-ns = <1>;
+		gpmc,cs-rd-off-ns = <180>;
+		gpmc,cs-wr-off-ns = <180>;
+		gpmc,adv-rd-off-ns = <18>;
 		gpmc,adv-wr-off-ns = <48>;
 		gpmc,oe-on-ns = <54>;
 		gpmc,oe-off-ns = <168>;
@@ -49,16 +34,14 @@
 		gpmc,we-off-ns = <168>;
 		gpmc,rd-cycle-ns = <186>;
 		gpmc,wr-cycle-ns = <186>;
-		gpmc,access-ns = <114>;
-		gpmc,page-burst-access-ns = <6>;
-		gpmc,bus-turnaround-ns = <12>;
-		gpmc,cycle2cycle-delay-ns = <18>;
-		gpmc,wr-data-mux-bus-ns = <90>;
-		gpmc,wr-access-ns = <186>;
+		gpmc,access-ns = <144>;
+		gpmc,page-burst-access-ns = <24>;
+		gpmc,bus-turnaround-ns = <90>;
+		gpmc,cycle2cycle-delay-ns = <90>;
 		gpmc,cycle2cycle-samecsen;
 		gpmc,cycle2cycle-diffcsen;
-		vddvario-supply = <&vddvario_sb_t35>;
-		vdd33a-supply = <&vdd33a_sb_t35>;
+		vddvario-supply = <&vddvario>;
+		vdd33a-supply = <&vdd33a>;
 		reg-io-width = <4>;
 		smsc,save-mac-address;
 	};
diff --git a/arch/arm/boot/dts/omap3-sbc-t3517.dts b/arch/arm/boot/dts/omap3-sbc-t3517.dts
index 024c9c6c682d..42189b65d393 100644
--- a/arch/arm/boot/dts/omap3-sbc-t3517.dts
+++ b/arch/arm/boot/dts/omap3-sbc-t3517.dts
@@ -8,6 +8,19 @@
 / {
 	model = "CompuLab SBC-T3517 with CM-T3517";
 	compatible = "compulab,omap3-sbc-t3517", "compulab,omap3-cm-t3517", "ti,am3517", "ti,omap3";
+
+	/* Only one GPMC smsc9220 on SBC-T3517, CM-T3517 uses am35x Ethernet */
+	vddvario: regulator-vddvario-sb-t35 {
+		compatible = "regulator-fixed";
+		regulator-name = "vddvario";
+		regulator-always-on;
+	};
+
+	vdd33a: regulator-vdd33a-sb-t35 {
+		compatible = "regulator-fixed";
+		regulator-name = "vdd33a";
+		regulator-always-on;
+	};
 };
 
 &omap3_pmx_core {
diff --git a/arch/arm/boot/dts/omap3.dtsi b/arch/arm/boot/dts/omap3.dtsi
index acb9019dc437..4231191ade06 100644
--- a/arch/arm/boot/dts/omap3.dtsi
+++ b/arch/arm/boot/dts/omap3.dtsi
@@ -61,7 +61,7 @@
 			ti,hwmods = "mpu";
 		};
 
-		iva {
+		iva: iva {
 			compatible = "ti,iva2.2";
 			ti,hwmods = "iva";
 
diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi
index f8c9855ce587..36b4312a5e0d 100644
--- a/arch/arm/boot/dts/omap5.dtsi
+++ b/arch/arm/boot/dts/omap5.dtsi
@@ -630,6 +630,13 @@
 			status = "disabled";
 		};
 
+		mailbox: mailbox@4a0f4000 {
+			compatible = "ti,omap4-mailbox";
+			reg = <0x4a0f4000 0x200>;
+			interrupts = <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>;
+			ti,hwmods = "mailbox";
+		};
+
 		timer1: timer@4ae18000 {
 			compatible = "ti,omap5430-timer";
 			reg = <0x4ae18000 0x80>;
diff --git a/arch/arm/boot/dts/sama5d3.dtsi b/arch/arm/boot/dts/sama5d3.dtsi
index eabcfdbb403a..a106b0872910 100644
--- a/arch/arm/boot/dts/sama5d3.dtsi
+++ b/arch/arm/boot/dts/sama5d3.dtsi
@@ -13,7 +13,7 @@
 #include <dt-bindings/pinctrl/at91.h>
 #include <dt-bindings/interrupt-controller/irq.h>
 #include <dt-bindings/gpio/gpio.h>
-#include <dt-bindings/clk/at91.h>
+#include <dt-bindings/clock/at91.h>
 
 / {
 	model = "Atmel SAMA5D3 family SoC";
diff --git a/arch/arm/boot/dts/sama5d3_mci2.dtsi b/arch/arm/boot/dts/sama5d3_mci2.dtsi
index b029fe7ef17a..1b02208ea6ff 100644
--- a/arch/arm/boot/dts/sama5d3_mci2.dtsi
+++ b/arch/arm/boot/dts/sama5d3_mci2.dtsi
@@ -9,7 +9,7 @@
 
 #include <dt-bindings/pinctrl/at91.h>
 #include <dt-bindings/interrupt-controller/irq.h>
-#include <dt-bindings/clk/at91.h>
+#include <dt-bindings/clock/at91.h>
 
 / {
 	ahb {
diff --git a/arch/arm/boot/dts/sama5d3_tcb1.dtsi b/arch/arm/boot/dts/sama5d3_tcb1.dtsi
index 382b04431f66..02848453ca0c 100644
--- a/arch/arm/boot/dts/sama5d3_tcb1.dtsi
+++ b/arch/arm/boot/dts/sama5d3_tcb1.dtsi
@@ -9,7 +9,7 @@
 
 #include <dt-bindings/pinctrl/at91.h>
 #include <dt-bindings/interrupt-controller/irq.h>
-#include <dt-bindings/clk/at91.h>
+#include <dt-bindings/clock/at91.h>
 
 / {
 	aliases {
diff --git a/arch/arm/boot/dts/sama5d3_uart.dtsi b/arch/arm/boot/dts/sama5d3_uart.dtsi
index a9fa75e41652..7a8d4c6115f7 100644
--- a/arch/arm/boot/dts/sama5d3_uart.dtsi
+++ b/arch/arm/boot/dts/sama5d3_uart.dtsi
@@ -9,7 +9,7 @@
 
 #include <dt-bindings/pinctrl/at91.h>
 #include <dt-bindings/interrupt-controller/irq.h>
-#include <dt-bindings/clk/at91.h>
+#include <dt-bindings/clock/at91.h>
 
 / {
 	aliases {
diff --git a/arch/arm/boot/dts/ste-ccu8540.dts b/arch/arm/boot/dts/ste-ccu8540.dts
index 7f3baf51a3a9..32dd55e5f4e6 100644
--- a/arch/arm/boot/dts/ste-ccu8540.dts
+++ b/arch/arm/boot/dts/ste-ccu8540.dts
@@ -18,6 +18,7 @@
 	compatible = "st-ericsson,ccu8540", "st-ericsson,u8540";
 
 	memory@0 {
+		device_type = "memory";
 		reg = <0x20000000 0x1f000000>, <0xc0000000 0x3f000000>;
 	};
 
diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi
index 32efc105df83..aba1c8a3f388 100644
--- a/arch/arm/boot/dts/sun7i-a20.dtsi
+++ b/arch/arm/boot/dts/sun7i-a20.dtsi
@@ -87,7 +87,7 @@
 
 		pll4: clk@01c20018 {
 			#clock-cells = <0>;
-			compatible = "allwinner,sun4i-a10-pll1-clk";
+			compatible = "allwinner,sun7i-a20-pll4-clk";
 			reg = <0x01c20018 0x4>;
 			clocks = <&osc24M>;
 			clock-output-names = "pll4";
@@ -109,6 +109,14 @@
 			clock-output-names = "pll6_sata", "pll6_other", "pll6";
 		};
 
+		pll8: clk@01c20040 {
+			#clock-cells = <0>;
+			compatible = "allwinner,sun7i-a20-pll4-clk";
+			reg = <0x01c20040 0x4>;
+			clocks = <&osc24M>;
+			clock-output-names = "pll8";
+		};
+
 		cpu: cpu@01c20054 {
 			#clock-cells = <0>;
 			compatible = "allwinner,sun4i-a10-cpu-clk";
@@ -805,9 +813,9 @@
 			status = "disabled";
 		};
 
-		i2c4: i2c@01c2bc00 {
+		i2c4: i2c@01c2c000 {
 			compatible = "allwinner,sun4i-i2c";
-			reg = <0x01c2bc00 0x400>;
+			reg = <0x01c2c000 0x400>;
 			interrupts = <0 89 4>;
 			clocks = <&apb1_gates 15>;
 			clock-frequency = <100000>;
diff --git a/arch/arm/common/bL_switcher.c b/arch/arm/common/bL_switcher.c
index f01c0ee0c87e..490f3dced749 100644
--- a/arch/arm/common/bL_switcher.c
+++ b/arch/arm/common/bL_switcher.c
@@ -433,8 +433,12 @@ static void bL_switcher_restore_cpus(void)
 {
 	int i;
 
-	for_each_cpu(i, &bL_switcher_removed_logical_cpus)
-		cpu_up(i);
+	for_each_cpu(i, &bL_switcher_removed_logical_cpus) {
+		struct device *cpu_dev = get_cpu_device(i);
+		int ret = device_online(cpu_dev);
+		if (ret)
+			dev_err(cpu_dev, "switcher: unable to restore CPU\n");
+	}
 }
 
 static int bL_switcher_halve_cpus(void)
@@ -521,7 +525,7 @@ static int bL_switcher_halve_cpus(void)
 			continue;
 		}
 
-		ret = cpu_down(i);
+		ret = device_offline(get_cpu_device(i));
 		if (ret) {
 			bL_switcher_restore_cpus();
 			return ret;
diff --git a/arch/arm/common/edma.c b/arch/arm/common/edma.c
index 41bca32409fc..5339009b3c0c 100644
--- a/arch/arm/common/edma.c
+++ b/arch/arm/common/edma.c
@@ -1423,55 +1423,38 @@ EXPORT_SYMBOL(edma_clear_event);
 
 #if IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_DMADEVICES)
 
-static int edma_of_read_u32_to_s16_array(const struct device_node *np,
-					 const char *propname, s16 *out_values,
-					 size_t sz)
+static int edma_xbar_event_map(struct device *dev, struct device_node *node,
+			       struct edma_soc_info *pdata, size_t sz)
 {
-	int ret;
-
-	ret = of_property_read_u16_array(np, propname, out_values, sz);
-	if (ret)
-		return ret;
-
-	/* Terminate it */
-	*out_values++ = -1;
-	*out_values++ = -1;
-
-	return 0;
-}
-
-static int edma_xbar_event_map(struct device *dev,
-			       struct device_node *node,
-			       struct edma_soc_info *pdata, int len)
-{
-	int ret, i;
+	const char pname[] = "ti,edma-xbar-event-map";
 	struct resource res;
 	void __iomem *xbar;
-	const s16 (*xbar_chans)[2];
+	s16 (*xbar_chans)[2];
+	size_t nelm = sz / sizeof(s16);
 	u32 shift, offset, mux;
+	int ret, i;
 
-	xbar_chans = devm_kzalloc(dev,
-				  len/sizeof(s16) + 2*sizeof(s16),
-				  GFP_KERNEL);
+	xbar_chans = devm_kzalloc(dev, (nelm + 2) * sizeof(s16), GFP_KERNEL);
 	if (!xbar_chans)
 		return -ENOMEM;
 
 	ret = of_address_to_resource(node, 1, &res);
 	if (ret)
-		return -EIO;
+		return -ENOMEM;
 
 	xbar = devm_ioremap(dev, res.start, resource_size(&res));
 	if (!xbar)
 		return -ENOMEM;
 
-	ret = edma_of_read_u32_to_s16_array(node,
-					    "ti,edma-xbar-event-map",
-					    (s16 *)xbar_chans,
-					    len/sizeof(u32));
+	ret = of_property_read_u16_array(node, pname, (u16 *)xbar_chans, nelm);
 	if (ret)
 		return -EIO;
 
-	for (i = 0; xbar_chans[i][0] != -1; i++) {
+	/* Invalidate last entry for the other user of this mess */
+	nelm >>= 1;
+	xbar_chans[nelm][0] = xbar_chans[nelm][1] = -1;
+
+	for (i = 0; i < nelm; i++) {
 		shift = (xbar_chans[i][1] & 0x03) << 3;
 		offset = xbar_chans[i][1] & 0xfffffffc;
 		mux = readl(xbar + offset);
@@ -1480,8 +1463,7 @@ static int edma_xbar_event_map(struct device *dev,
 		writel(mux, (xbar + offset));
 	}
 
-	pdata->xbar_chans = xbar_chans;
-
+	pdata->xbar_chans = (const s16 (*)[2]) xbar_chans;
 	return 0;
 }
 
diff --git a/arch/arm/configs/exynos_defconfig b/arch/arm/configs/exynos_defconfig
index 4ce7b70ea901..e07a227ec0db 100644
--- a/arch/arm/configs/exynos_defconfig
+++ b/arch/arm/configs/exynos_defconfig
@@ -65,6 +65,7 @@ CONFIG_TCG_TIS_I2C_INFINEON=y
 CONFIG_I2C=y
 CONFIG_I2C_MUX=y
 CONFIG_I2C_ARB_GPIO_CHALLENGE=y
+CONFIG_I2C_EXYNOS5=y
 CONFIG_I2C_S3C2410=y
 CONFIG_DEBUG_GPIO=y
 # CONFIG_HWMON is not set
diff --git a/arch/arm/configs/sunxi_defconfig b/arch/arm/configs/sunxi_defconfig
index b5df4a511b0a..81ba78eaf54a 100644
--- a/arch/arm/configs/sunxi_defconfig
+++ b/arch/arm/configs/sunxi_defconfig
@@ -37,7 +37,7 @@ CONFIG_SUN4I_EMAC=y
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_SEEQ is not set
 # CONFIG_NET_VENDOR_SMSC is not set
-# CONFIG_NET_VENDOR_STMICRO is not set
+CONFIG_STMMAC_ETH=y
 # CONFIG_NET_VENDOR_WIZNET is not set
 # CONFIG_WLAN is not set
 CONFIG_SERIAL_8250=y
diff --git a/arch/arm/include/asm/trusted_foundations.h b/arch/arm/include/asm/trusted_foundations.h
index b5f7705abcb0..624e1d436c6c 100644
--- a/arch/arm/include/asm/trusted_foundations.h
+++ b/arch/arm/include/asm/trusted_foundations.h
@@ -54,7 +54,9 @@ static inline void register_trusted_foundations(
 	 */
 	pr_err("No support for Trusted Foundations, continuing in degraded mode.\n");
 	pr_err("Secondary processors as well as CPU PM will be disabled.\n");
+#if IS_ENABLED(CONFIG_SMP)
 	setup_max_cpus = 0;
+#endif
 	cpu_idle_poll_ctrl(true);
 }
 
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 12c3a5decc60..75d95799b6e6 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -171,8 +171,9 @@ extern int __put_user_8(void *, unsigned long long);
 #define __put_user_check(x,p)							\
 	({								\
 		unsigned long __limit = current_thread_info()->addr_limit - 1; \
+		const typeof(*(p)) __user *__tmp_p = (p);		\
 		register const typeof(*(p)) __r2 asm("r2") = (x);	\
-		register const typeof(*(p)) __user *__p asm("r0") = (p);\
+		register const typeof(*(p)) __user *__p asm("r0") = __tmp_p; \
 		register unsigned long __l asm("r1") = __limit;		\
 		register int __e asm("r0");				\
 		switch (sizeof(*(__p))) {				\
diff --git a/arch/arm/include/asm/xen/page.h b/arch/arm/include/asm/xen/page.h
index cf4f3e867395..ded062f9b358 100644
--- a/arch/arm/include/asm/xen/page.h
+++ b/arch/arm/include/asm/xen/page.h
@@ -77,7 +77,6 @@ static inline xpaddr_t machine_to_phys(xmaddr_t machine)
 }
 /* VIRT <-> MACHINE conversion */
 #define virt_to_machine(v)	(phys_to_machine(XPADDR(__pa(v))))
-#define virt_to_pfn(v)          (PFN_DOWN(__pa(v)))
 #define virt_to_mfn(v)		(pfn_to_mfn(virt_to_pfn(v)))
 #define mfn_to_virt(m)		(__va(mfn_to_pfn(m) << PAGE_SHIFT))
 
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 1420725142ca..efb208de75ec 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -132,6 +132,10 @@
 	orrne	r5, V7M_xPSR_FRAMEPTRALIGN
 	biceq	r5, V7M_xPSR_FRAMEPTRALIGN
 
+	@ ensure bit 0 is cleared in the PC, otherwise behaviour is
+	@ unpredictable
+	bic	r4, #1
+
 	@ write basic exception frame
 	stmdb	r2!, {r1, r3-r5}
 	ldmia	sp, {r1, r3-r5}
diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c
index 3c217694ebec..cb791ac6a003 100644
--- a/arch/arm/kernel/unwind.c
+++ b/arch/arm/kernel/unwind.c
@@ -285,7 +285,7 @@ static int unwind_exec_pop_r4_to_rN(struct unwind_ctrl_block *ctrl,
 		if (unwind_pop_register(ctrl, &vsp, reg))
 				return -URC_FAILURE;
 
-	if (insn & 0x80)
+	if (insn & 0x8)
 		if (unwind_pop_register(ctrl, &vsp, 14))
 				return -URC_FAILURE;
 
diff --git a/arch/arm/mach-at91/at91sam9260_devices.c b/arch/arm/mach-at91/at91sam9260_devices.c
index a0282928e9c1..7cd6f19945ed 100644
--- a/arch/arm/mach-at91/at91sam9260_devices.c
+++ b/arch/arm/mach-at91/at91sam9260_devices.c
@@ -1308,19 +1308,19 @@ static struct platform_device at91_adc_device = {
 static struct at91_adc_trigger at91_adc_triggers[] = {
 	[0] = {
 		.name = "timer-counter-0",
-		.value = AT91_ADC_TRGSEL_TC0 | AT91_ADC_TRGEN,
+		.value = 0x1,
 	},
 	[1] = {
 		.name = "timer-counter-1",
-		.value = AT91_ADC_TRGSEL_TC1 | AT91_ADC_TRGEN,
+		.value = 0x3,
 	},
 	[2] = {
 		.name = "timer-counter-2",
-		.value = AT91_ADC_TRGSEL_TC2 | AT91_ADC_TRGEN,
+		.value = 0x5,
 	},
 	[3] = {
 		.name = "external",
-		.value = AT91_ADC_TRGSEL_EXTERNAL | AT91_ADC_TRGEN,
+		.value = 0xd,
 		.is_external = true,
 	},
 };
diff --git a/arch/arm/mach-exynos/firmware.c b/arch/arm/mach-exynos/firmware.c
index 932129ef26c6..aa01c4222b40 100644
--- a/arch/arm/mach-exynos/firmware.c
+++ b/arch/arm/mach-exynos/firmware.c
@@ -18,6 +18,8 @@
 
 #include <mach/map.h>
 
+#include <plat/cpu.h>
+
 #include "smc.h"
 
 static int exynos_do_idle(void)
@@ -28,13 +30,24 @@ static int exynos_do_idle(void)
 
 static int exynos_cpu_boot(int cpu)
 {
+	/*
+	 * The second parameter of SMC_CMD_CPU1BOOT command means CPU id.
+	 * But, Exynos4212 has only one secondary CPU so second parameter
+	 * isn't used for informing secure firmware about CPU id.
+	 */
+	if (soc_is_exynos4212())
+		cpu = 0;
+
 	exynos_smc(SMC_CMD_CPU1BOOT, cpu, 0, 0);
 	return 0;
 }
 
 static int exynos_set_cpu_boot_addr(int cpu, unsigned long boot_addr)
 {
-	void __iomem *boot_reg = S5P_VA_SYSRAM_NS + 0x1c + 4*cpu;
+	void __iomem *boot_reg = S5P_VA_SYSRAM_NS + 0x1c;
+
+	if (!soc_is_exynos4212())
+		boot_reg += 4*cpu;
 
 	__raw_writel(boot_addr, boot_reg);
 	return 0;
diff --git a/arch/arm/mach-imx/devices/platform-ipu-core.c b/arch/arm/mach-imx/devices/platform-ipu-core.c
index fc4dd7cedc11..6bd7c3f37ac0 100644
--- a/arch/arm/mach-imx/devices/platform-ipu-core.c
+++ b/arch/arm/mach-imx/devices/platform-ipu-core.c
@@ -77,7 +77,7 @@ struct platform_device *__init imx_alloc_mx3_camera(
 
 	pdev = platform_device_alloc("mx3-camera", 0);
 	if (!pdev)
-		goto err;
+		return ERR_PTR(-ENOMEM);
 
 	pdev->dev.dma_mask = kmalloc(sizeof(*pdev->dev.dma_mask), GFP_KERNEL);
 	if (!pdev->dev.dma_mask)
diff --git a/arch/arm/mach-mvebu/mvebu-soc-id.c b/arch/arm/mach-mvebu/mvebu-soc-id.c
index f3d4cf53f746..09520e19b78e 100644
--- a/arch/arm/mach-mvebu/mvebu-soc-id.c
+++ b/arch/arm/mach-mvebu/mvebu-soc-id.c
@@ -108,7 +108,18 @@ static int __init mvebu_soc_id_init(void)
 	iounmap(pci_base);
 
 res_ioremap:
-	clk_disable_unprepare(clk);
+	/*
+	 * If the PCIe unit is actually enabled and we have PCI
+	 * support in the kernel, we intentionally do not release the
+	 * reference to the clock. We want to keep it running since
+	 * the bootloader does some PCIe link configuration that the
+	 * kernel is for now unable to do, and gating the clock would
+	 * make us loose this precious configuration.
+	 */
+	if (!of_device_is_available(child) || !IS_ENABLED(CONFIG_PCI_MVEBU)) {
+		clk_disable_unprepare(clk);
+		clk_put(clk);
+	}
 
 clk_err:
 	of_node_put(child);
diff --git a/arch/arm/mach-omap2/board-flash.c b/arch/arm/mach-omap2/board-flash.c
index ac82512b9c8c..b6885e42c0a0 100644
--- a/arch/arm/mach-omap2/board-flash.c
+++ b/arch/arm/mach-omap2/board-flash.c
@@ -142,7 +142,7 @@ __init board_nand_init(struct mtd_partition *nand_parts, u8 nr_parts, u8 cs,
 	board_nand_data.nr_parts	= nr_parts;
 	board_nand_data.devsize		= nand_type;
 
-	board_nand_data.ecc_opt = OMAP_ECC_BCH8_CODE_HW;
+	board_nand_data.ecc_opt = OMAP_ECC_HAM1_CODE_HW;
 	gpmc_nand_init(&board_nand_data, gpmc_t);
 }
 #endif /* CONFIG_MTD_NAND_OMAP2 || CONFIG_MTD_NAND_OMAP2_MODULE */
diff --git a/arch/arm/mach-omap2/cclock3xxx_data.c b/arch/arm/mach-omap2/cclock3xxx_data.c
index 8f5121b89688..eb8c75ec3b1a 100644
--- a/arch/arm/mach-omap2/cclock3xxx_data.c
+++ b/arch/arm/mach-omap2/cclock3xxx_data.c
@@ -456,7 +456,8 @@ static struct clk_hw_omap dpll4_m5x2_ck_hw = {
 	.clkdm_name	= "dpll4_clkdm",
 };
 
-DEFINE_STRUCT_CLK(dpll4_m5x2_ck, dpll4_m5x2_ck_parent_names, dpll4_m5x2_ck_ops);
+DEFINE_STRUCT_CLK_FLAGS(dpll4_m5x2_ck, dpll4_m5x2_ck_parent_names,
+			dpll4_m5x2_ck_ops, CLK_SET_RATE_PARENT);
 
 static struct clk dpll4_m5x2_ck_3630 = {
 	.name		= "dpll4_m5x2_ck",
diff --git a/arch/arm/mach-omap2/cpuidle44xx.c b/arch/arm/mach-omap2/cpuidle44xx.c
index 01fc710c8181..2498ab025fa2 100644
--- a/arch/arm/mach-omap2/cpuidle44xx.c
+++ b/arch/arm/mach-omap2/cpuidle44xx.c
@@ -14,6 +14,7 @@
 #include <linux/cpuidle.h>
 #include <linux/cpu_pm.h>
 #include <linux/export.h>
+#include <linux/clockchips.h>
 
 #include <asm/cpuidle.h>
 #include <asm/proc-fns.h>
@@ -83,6 +84,7 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev,
 {
 	struct idle_statedata *cx = state_ptr + index;
 	u32 mpuss_can_lose_context = 0;
+	int cpu_id = smp_processor_id();
 
 	/*
 	 * CPU0 has to wait and stay ON until CPU1 is OFF state.
@@ -110,6 +112,8 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev,
 	mpuss_can_lose_context = (cx->mpu_state == PWRDM_POWER_RET) &&
 				 (cx->mpu_logic_state == PWRDM_POWER_OFF);
 
+	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu_id);
+
 	/*
 	 * Call idle CPU PM enter notifier chain so that
 	 * VFP and per CPU interrupt context is saved.
@@ -165,6 +169,8 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev,
 	if (dev->cpu == 0 && mpuss_can_lose_context)
 		cpu_cluster_pm_exit();
 
+	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu_id);
+
 fail:
 	cpuidle_coupled_parallel_barrier(dev, &abort_barrier);
 	cpu_done[dev->cpu] = false;
@@ -172,6 +178,16 @@ fail:
 	return index;
 }
 
+/*
+ * For each cpu, setup the broadcast timer because local timers
+ * stops for the states above C1.
+ */
+static void omap_setup_broadcast_timer(void *arg)
+{
+	int cpu = smp_processor_id();
+	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ON, &cpu);
+}
+
 static struct cpuidle_driver omap4_idle_driver = {
 	.name				= "omap4_idle",
 	.owner				= THIS_MODULE,
@@ -189,8 +205,7 @@ static struct cpuidle_driver omap4_idle_driver = {
 			/* C2 - CPU0 OFF + CPU1 OFF + MPU CSWR */
 			.exit_latency = 328 + 440,
 			.target_residency = 960,
-			.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_COUPLED |
-			         CPUIDLE_FLAG_TIMER_STOP,
+			.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_COUPLED,
 			.enter = omap_enter_idle_coupled,
 			.name = "C2",
 			.desc = "CPUx OFF, MPUSS CSWR",
@@ -199,8 +214,7 @@ static struct cpuidle_driver omap4_idle_driver = {
 			/* C3 - CPU0 OFF + CPU1 OFF + MPU OSWR */
 			.exit_latency = 460 + 518,
 			.target_residency = 1100,
-			.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_COUPLED |
-			         CPUIDLE_FLAG_TIMER_STOP,
+			.flags = CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_COUPLED,
 			.enter = omap_enter_idle_coupled,
 			.name = "C3",
 			.desc = "CPUx OFF, MPUSS OSWR",
@@ -231,5 +245,8 @@ int __init omap4_idle_init(void)
 	if (!cpu_clkdm[0] || !cpu_clkdm[1])
 		return -ENODEV;
 
+	/* Configure the broadcast timer on each cpu */
+	on_each_cpu(omap_setup_broadcast_timer, NULL, 1);
+
 	return cpuidle_register(&omap4_idle_driver, cpu_online_mask);
 }
diff --git a/arch/arm/mach-omap2/omap-headsmp.S b/arch/arm/mach-omap2/omap-headsmp.S
index 75e92952c18e..40c5d5f1451c 100644
--- a/arch/arm/mach-omap2/omap-headsmp.S
+++ b/arch/arm/mach-omap2/omap-headsmp.S
@@ -1,7 +1,7 @@
 /*
  * Secondary CPU startup routine source file.
  *
- * Copyright (C) 2009 Texas Instruments, Inc.
+ * Copyright (C) 2009-2014 Texas Instruments, Inc.
  *
  * Author:
  *      Santosh Shilimkar <santosh.shilimkar@ti.com>
@@ -28,9 +28,13 @@
  * code.  This routine also provides a holding flag into which
  * secondary core is held until we're ready for it to initialise.
  * The primary core will update this flag using a hardware
-+ * register AuxCoreBoot0.
+ * register AuxCoreBoot0.
  */
 ENTRY(omap5_secondary_startup)
+.arm
+THUMB( adr     r9, BSYM(wait)  )       @ CPU may be entered in ARM mode.
+THUMB( bx      r9              )       @ If this is a Thumb-2 kernel,
+THUMB( .thumb                  )       @ switch to Thumb now.
 wait:	ldr	r2, =AUX_CORE_BOOT0_PA	@ read from AuxCoreBoot0
 	ldr	r0, [r2]
 	mov	r0, r0, lsr #5
diff --git a/arch/arm/mach-omap2/omap_hwmod_54xx_data.c b/arch/arm/mach-omap2/omap_hwmod_54xx_data.c
index 892317294fdc..e829664e6a6c 100644
--- a/arch/arm/mach-omap2/omap_hwmod_54xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_54xx_data.c
@@ -895,7 +895,7 @@ static struct omap_hwmod omap54xx_mcpdm_hwmod = {
 	 * current exception.
 	 */
 
-	.flags		= HWMOD_EXT_OPT_MAIN_CLK,
+	.flags		= HWMOD_EXT_OPT_MAIN_CLK | HWMOD_SWSUP_SIDLE,
 	.main_clk	= "pad_clks_ck",
 	.prcm = {
 		.omap4 = {
diff --git a/arch/arm/mach-orion5x/common.h b/arch/arm/mach-orion5x/common.h
index f565f9944af2..7548db2bfb8a 100644
--- a/arch/arm/mach-orion5x/common.h
+++ b/arch/arm/mach-orion5x/common.h
@@ -21,7 +21,7 @@ struct mv_sata_platform_data;
 #define ORION_MBUS_DEVBUS_BOOT_ATTR   0x0f
 #define ORION_MBUS_DEVBUS_TARGET(cs)  0x01
 #define ORION_MBUS_DEVBUS_ATTR(cs)    (~(1 << cs))
-#define ORION_MBUS_SRAM_TARGET        0x00
+#define ORION_MBUS_SRAM_TARGET        0x09
 #define ORION_MBUS_SRAM_ATTR          0x00
 
 /*
diff --git a/arch/arm/mm/proc-v7m.S b/arch/arm/mm/proc-v7m.S
index 0c93588fcb91..1ca37c72f12f 100644
--- a/arch/arm/mm/proc-v7m.S
+++ b/arch/arm/mm/proc-v7m.S
@@ -123,6 +123,11 @@ __v7m_setup:
 	mov	pc, lr
 ENDPROC(__v7m_setup)
 
+	.align 2
+__v7m_setup_stack:
+	.space	4 * 8				@ 8 registers
+__v7m_setup_stack_top:
+
 	define_processor_functions v7m, dabort=nommu_early_abort, pabort=legacy_pabort, nommu=1
 
 	.section ".rodata"
@@ -152,6 +157,3 @@ __v7m_proc_info:
 	.long	nop_cache_fns		@ proc_info_list.cache
 	.size	__v7m_proc_info, . - __v7m_proc_info
 
-__v7m_setup_stack:
-	.space	4 * 8				@ 8 registers
-__v7m_setup_stack_top:
diff --git a/arch/arm/plat-omap/dma.c b/arch/arm/plat-omap/dma.c
index 5f5b975887fc..b5608b1f9fbd 100644
--- a/arch/arm/plat-omap/dma.c
+++ b/arch/arm/plat-omap/dma.c
@@ -70,6 +70,7 @@ static u32 errata;
 
 static struct omap_dma_global_context_registers {
 	u32 dma_irqenable_l0;
+	u32 dma_irqenable_l1;
 	u32 dma_ocp_sysconfig;
 	u32 dma_gcr;
 } omap_dma_global_context;
@@ -1973,10 +1974,17 @@ static struct irqaction omap24xx_dma_irq;
 
 /*----------------------------------------------------------------------------*/
 
+/*
+ * Note that we are currently using only IRQENABLE_L0 and L1.
+ * As the DSP may be using IRQENABLE_L2 and L3, let's not
+ * touch those for now.
+ */
 void omap_dma_global_context_save(void)
 {
 	omap_dma_global_context.dma_irqenable_l0 =
 		p->dma_read(IRQENABLE_L0, 0);
+	omap_dma_global_context.dma_irqenable_l1 =
+		p->dma_read(IRQENABLE_L1, 0);
 	omap_dma_global_context.dma_ocp_sysconfig =
 		p->dma_read(OCP_SYSCONFIG, 0);
 	omap_dma_global_context.dma_gcr = p->dma_read(GCR, 0);
@@ -1991,6 +1999,8 @@ void omap_dma_global_context_restore(void)
 		OCP_SYSCONFIG, 0);
 	p->dma_write(omap_dma_global_context.dma_irqenable_l0,
 		IRQENABLE_L0, 0);
+	p->dma_write(omap_dma_global_context.dma_irqenable_l1,
+		IRQENABLE_L1, 0);
 
 	if (IS_DMA_ERRATA(DMA_ROMCODE_BUG))
 		p->dma_write(0x3 , IRQSTATUS_L0, 0);
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index e94f9458aa6f..993bce527b85 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -138,6 +138,7 @@ static inline void *phys_to_virt(phys_addr_t x)
 #define __pa(x)			__virt_to_phys((unsigned long)(x))
 #define __va(x)			((void *)__phys_to_virt((phys_addr_t)(x)))
 #define pfn_to_kaddr(pfn)	__va((pfn) << PAGE_SHIFT)
+#define virt_to_pfn(x)      __phys_to_pfn(__virt_to_phys(x))
 
 /*
  *  virt_to_page(k)	convert a _valid_ virtual address to struct page *
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 90c811f05a2e..7b1c67a0b485 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -266,7 +266,7 @@ static inline pmd_t pte_pmd(pte_t pte)
 
 #define pmd_page(pmd)           pfn_to_page(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK))
 
-#define set_pmd_at(mm, addr, pmdp, pmd)	set_pmd(pmdp, pmd)
+#define set_pmd_at(mm, addr, pmdp, pmd)	set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd))
 
 static inline int has_transparent_hugepage(void)
 {
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index 473e5dbf8f39..0f08dfd69ebc 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -97,11 +97,15 @@ static bool migrate_one_irq(struct irq_desc *desc)
 	if (irqd_is_per_cpu(d) || !cpumask_test_cpu(smp_processor_id(), affinity))
 		return false;
 
-	if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
-		affinity = cpu_online_mask;
+	if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids)
 		ret = true;
-	}
 
+	/*
+	 * when using forced irq_set_affinity we must ensure that the cpu
+	 * being offlined is not present in the affinity mask, it may be
+	 * selected as the target CPU otherwise
+	 */
+	affinity = cpu_online_mask;
 	c = irq_data_get_irq_chip(d);
 	if (!c->irq_set_affinity)
 		pr_debug("IRQ%u: unable to set affinity\n", d->irq);
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 5e9aec358306..31eb959e9aa8 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -51,7 +51,11 @@ int pmd_huge(pmd_t pmd)
 
 int pud_huge(pud_t pud)
 {
+#ifndef __PAGETABLE_PMD_FOLDED
 	return !(pud_val(pud) & PUD_TABLE_BIT);
+#else
+	return 0;
+#endif
 }
 
 int pmd_huge_support(void)
diff --git a/arch/ia64/include/asm/unistd.h b/arch/ia64/include/asm/unistd.h
index ae763d8bf55a..fb13dc5e8f8c 100644
--- a/arch/ia64/include/asm/unistd.h
+++ b/arch/ia64/include/asm/unistd.h
@@ -11,7 +11,7 @@
 
 
 
-#define NR_syscalls			314 /* length of syscall table */
+#define NR_syscalls			315 /* length of syscall table */
 
 /*
  * The following defines stop scripts/checksyscalls.sh from complaining about
diff --git a/arch/ia64/include/uapi/asm/unistd.h b/arch/ia64/include/uapi/asm/unistd.h
index 715e85f858de..7de0a2d65da4 100644
--- a/arch/ia64/include/uapi/asm/unistd.h
+++ b/arch/ia64/include/uapi/asm/unistd.h
@@ -327,5 +327,6 @@
 #define __NR_finit_module		1335
 #define __NR_sched_setattr		1336
 #define __NR_sched_getattr		1337
+#define __NR_renameat2			1338
 
 #endif /* _UAPI_ASM_IA64_UNISTD_H */
diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index fa8d61a312a7..ba3d03503e84 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -1775,6 +1775,7 @@ sys_call_table:
 	data8 sys_finit_module			// 1335
 	data8 sys_sched_setattr
 	data8 sys_sched_getattr
+	data8 sys_renameat2
 
 	.org sys_call_table + 8*NR_syscalls	// guard against failures to increase NR_syscalls
 #endif /* __IA64_ASM_PARAVIRTUALIZED_NATIVE */
diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h
index 9d38b73989eb..33afa56ad47a 100644
--- a/arch/m68k/include/asm/unistd.h
+++ b/arch/m68k/include/asm/unistd.h
@@ -4,7 +4,7 @@
 #include <uapi/asm/unistd.h>
 
 
-#define NR_syscalls		351
+#define NR_syscalls		352
 
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_OLD_STAT
diff --git a/arch/m68k/include/uapi/asm/unistd.h b/arch/m68k/include/uapi/asm/unistd.h
index b932dd470041..9cd82fbc7817 100644
--- a/arch/m68k/include/uapi/asm/unistd.h
+++ b/arch/m68k/include/uapi/asm/unistd.h
@@ -356,5 +356,6 @@
 #define __NR_finit_module	348
 #define __NR_sched_setattr	349
 #define __NR_sched_getattr	350
+#define __NR_renameat2		351
 
 #endif /* _UAPI_ASM_M68K_UNISTD_H_ */
diff --git a/arch/m68k/kernel/syscalltable.S b/arch/m68k/kernel/syscalltable.S
index b6223dc41d82..501e10212789 100644
--- a/arch/m68k/kernel/syscalltable.S
+++ b/arch/m68k/kernel/syscalltable.S
@@ -371,4 +371,5 @@ ENTRY(sys_call_table)
 	.long sys_finit_module
 	.long sys_sched_setattr
 	.long sys_sched_getattr		/* 350 */
+	.long sys_renameat2
 
diff --git a/arch/metag/include/asm/barrier.h b/arch/metag/include/asm/barrier.h
index 5d6b4b407dda..2d6f0de77325 100644
--- a/arch/metag/include/asm/barrier.h
+++ b/arch/metag/include/asm/barrier.h
@@ -15,6 +15,7 @@ static inline void wr_fence(void)
 	volatile int *flushptr = (volatile int *) LINSYSEVENT_WR_FENCE;
 	barrier();
 	*flushptr = 0;
+	barrier();
 }
 
 #else /* CONFIG_METAG_META21 */
@@ -35,6 +36,7 @@ static inline void wr_fence(void)
 	*flushptr = 0;
 	*flushptr = 0;
 	*flushptr = 0;
+	barrier();
 }
 
 #endif /* !CONFIG_METAG_META21 */
@@ -68,6 +70,7 @@ static inline void fence(void)
 	volatile int *flushptr = (volatile int *) LINSYSEVENT_WR_ATOMIC_UNLOCK;
 	barrier();
 	*flushptr = 0;
+	barrier();
 }
 #define smp_mb()        fence()
 #define smp_rmb()       fence()
diff --git a/arch/metag/include/asm/processor.h b/arch/metag/include/asm/processor.h
index f16477d1f571..a8a37477c66e 100644
--- a/arch/metag/include/asm/processor.h
+++ b/arch/metag/include/asm/processor.h
@@ -22,6 +22,8 @@
 /* Add an extra page of padding at the top of the stack for the guard page. */
 #define STACK_TOP	(TASK_SIZE - PAGE_SIZE)
 #define STACK_TOP_MAX	STACK_TOP
+/* Maximum virtual space for stack */
+#define STACK_SIZE_MAX	(CONFIG_MAX_STACK_SIZE_MB*1024*1024)
 
 /* This decides where the kernel will search for a free chunk of vm
  * space during mmap's.
diff --git a/arch/metag/include/uapi/asm/Kbuild b/arch/metag/include/uapi/asm/Kbuild
index 84e09feb4d54..ab78be2b6eb0 100644
--- a/arch/metag/include/uapi/asm/Kbuild
+++ b/arch/metag/include/uapi/asm/Kbuild
@@ -4,11 +4,11 @@ include include/uapi/asm-generic/Kbuild.asm
 header-y += byteorder.h
 header-y += ech.h
 header-y += ptrace.h
-header-y += resource.h
 header-y += sigcontext.h
 header-y += siginfo.h
 header-y += swab.h
 header-y += unistd.h
 
 generic-y += mman.h
+generic-y += resource.h
 generic-y += setup.h
diff --git a/arch/metag/include/uapi/asm/resource.h b/arch/metag/include/uapi/asm/resource.h
deleted file mode 100644
index 526d23cc3054..000000000000
--- a/arch/metag/include/uapi/asm/resource.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef _UAPI_METAG_RESOURCE_H
-#define _UAPI_METAG_RESOURCE_H
-
-#define _STK_LIM_MAX    (1 << 28)
-#include <asm-generic/resource.h>
-
-#endif /* _UAPI_METAG_RESOURCE_H */
diff --git a/arch/mips/dec/ecc-berr.c b/arch/mips/dec/ecc-berr.c
index 5abf4e894216..2a66e908f6a9 100644
--- a/arch/mips/dec/ecc-berr.c
+++ b/arch/mips/dec/ecc-berr.c
@@ -21,6 +21,7 @@
 #include <asm/addrspace.h>
 #include <asm/bootinfo.h>
 #include <asm/cpu.h>
+#include <asm/cpu-type.h>
 #include <asm/irq_regs.h>
 #include <asm/processor.h>
 #include <asm/ptrace.h>
diff --git a/arch/mips/dec/kn02xa-berr.c b/arch/mips/dec/kn02xa-berr.c
index f434b759e3b9..ec606363b806 100644
--- a/arch/mips/dec/kn02xa-berr.c
+++ b/arch/mips/dec/kn02xa-berr.c
@@ -19,6 +19,7 @@
 #include <linux/types.h>
 
 #include <asm/addrspace.h>
+#include <asm/cpu-type.h>
 #include <asm/irq_regs.h>
 #include <asm/ptrace.h>
 #include <asm/traps.h>
diff --git a/arch/mips/dec/prom/Makefile b/arch/mips/dec/prom/Makefile
index 064ae7a76bdc..ae73e42ac20b 100644
--- a/arch/mips/dec/prom/Makefile
+++ b/arch/mips/dec/prom/Makefile
@@ -6,4 +6,3 @@
 lib-y			+= init.o memory.o cmdline.o identify.o console.o
 
 lib-$(CONFIG_32BIT)	+= locore.o
-lib-$(CONFIG_64BIT)	+= call_o32.o
diff --git a/arch/mips/dec/prom/call_o32.S b/arch/mips/dec/prom/call_o32.S
deleted file mode 100644
index 8c8498159e43..000000000000
--- a/arch/mips/dec/prom/call_o32.S
+++ /dev/null
@@ -1,89 +0,0 @@
-/*
- *	O32 interface for the 64 (or N32) ABI.
- *
- *	Copyright (C) 2002  Maciej W. Rozycki
- *
- *	This program is free software; you can redistribute it and/or
- *	modify it under the terms of the GNU General Public License
- *	as published by the Free Software Foundation; either version
- *	2 of the License, or (at your option) any later version.
- */
-
-#include <asm/asm.h>
-#include <asm/regdef.h>
-
-/* Maximum number of arguments supported.  Must be even!  */
-#define O32_ARGC	32
-/* Number of static registers we save.  */
-#define O32_STATC	11
-/* Frame size for both of the above.  */
-#define O32_FRAMESZ	(4 * O32_ARGC + SZREG * O32_STATC)
-
-		.text
-
-/*
- * O32 function call dispatcher, for interfacing 32-bit ROM routines.
- *
- * The standard 64 (N32) calling sequence is supported, with a0
- * holding a function pointer, a1-a7 -- its first seven arguments
- * and the stack -- remaining ones (up to O32_ARGC, including a1-a7).
- * Static registers, gp and fp are preserved, v0 holds a result.
- * This code relies on the called o32 function for sp and ra
- * restoration and thus both this dispatcher and the current stack
- * have to be placed in a KSEGx (or KUSEG) address space.  Any
- * pointers passed have to point to addresses within one of these
- * spaces as well.
- */
-NESTED(call_o32, O32_FRAMESZ, ra)
-		REG_SUBU	sp,O32_FRAMESZ
-
-		REG_S		ra,O32_FRAMESZ-1*SZREG(sp)
-		REG_S		fp,O32_FRAMESZ-2*SZREG(sp)
-		REG_S		gp,O32_FRAMESZ-3*SZREG(sp)
-		REG_S		s7,O32_FRAMESZ-4*SZREG(sp)
-		REG_S		s6,O32_FRAMESZ-5*SZREG(sp)
-		REG_S		s5,O32_FRAMESZ-6*SZREG(sp)
-		REG_S		s4,O32_FRAMESZ-7*SZREG(sp)
-		REG_S		s3,O32_FRAMESZ-8*SZREG(sp)
-		REG_S		s2,O32_FRAMESZ-9*SZREG(sp)
-		REG_S		s1,O32_FRAMESZ-10*SZREG(sp)
-		REG_S		s0,O32_FRAMESZ-11*SZREG(sp)
-
-		move		jp,a0
-
-		sll		a0,a1,zero
-		sll		a1,a2,zero
-		sll		a2,a3,zero
-		sll		a3,a4,zero
-		sw		a5,0x10(sp)
-		sw		a6,0x14(sp)
-		sw		a7,0x18(sp)
-
-		PTR_LA		t0,O32_FRAMESZ(sp)
-		PTR_LA		t1,0x1c(sp)
-		li		t2,O32_ARGC-7
-1:
-		lw		t3,(t0)
-		REG_ADDU	t0,SZREG
-		sw		t3,(t1)
-		REG_SUBU	t2,1
-		REG_ADDU	t1,4
-		bnez		t2,1b
-
-		jalr		jp
-
-		REG_L		s0,O32_FRAMESZ-11*SZREG(sp)
-		REG_L		s1,O32_FRAMESZ-10*SZREG(sp)
-		REG_L		s2,O32_FRAMESZ-9*SZREG(sp)
-		REG_L		s3,O32_FRAMESZ-8*SZREG(sp)
-		REG_L		s4,O32_FRAMESZ-7*SZREG(sp)
-		REG_L		s5,O32_FRAMESZ-6*SZREG(sp)
-		REG_L		s6,O32_FRAMESZ-5*SZREG(sp)
-		REG_L		s7,O32_FRAMESZ-4*SZREG(sp)
-		REG_L		gp,O32_FRAMESZ-3*SZREG(sp)
-		REG_L		fp,O32_FRAMESZ-2*SZREG(sp)
-		REG_L		ra,O32_FRAMESZ-1*SZREG(sp)
-
-		REG_ADDU	sp,O32_FRAMESZ
-		jr		ra
-END(call_o32)
diff --git a/arch/mips/fw/lib/call_o32.S b/arch/mips/fw/lib/call_o32.S
index b308b2a0613e..4703fe4dbd9a 100644
--- a/arch/mips/fw/lib/call_o32.S
+++ b/arch/mips/fw/lib/call_o32.S
@@ -1,7 +1,7 @@
 /*
  *	O32 interface for the 64 (or N32) ABI.
  *
- *	Copyright (C) 2002  Maciej W. Rozycki
+ *	Copyright (C) 2002, 2014  Maciej W. Rozycki
  *
  *	This program is free software; you can redistribute it and/or
  *	modify it under the terms of the GNU General Public License
@@ -12,28 +12,37 @@
 #include <asm/asm.h>
 #include <asm/regdef.h>
 
+/* O32 register size.  */
+#define O32_SZREG	4
 /* Maximum number of arguments supported.  Must be even!  */
 #define O32_ARGC	32
-/* Number of static registers we save.	*/
+/* Number of static registers we save.  */
 #define O32_STATC	11
-/* Frame size for static register  */
-#define O32_FRAMESZ	(SZREG * O32_STATC)
-/* Frame size on new stack */
-#define O32_FRAMESZ_NEW (SZREG + 4 * O32_ARGC)
+/* Argument area frame size.  */
+#define O32_ARGSZ	(O32_SZREG * O32_ARGC)
+/* Static register save area frame size.  */
+#define O32_STATSZ	(SZREG * O32_STATC)
+/* Stack pointer register save area frame size.  */
+#define O32_SPSZ	SZREG
+/* Combined area frame size.  */
+#define O32_FRAMESZ	(O32_ARGSZ + O32_SPSZ + O32_STATSZ)
+/* Switched stack frame size.  */
+#define O32_NFRAMESZ	(O32_ARGSZ + O32_SPSZ)
 
 		.text
 
 /*
  * O32 function call dispatcher, for interfacing 32-bit ROM routines.
  *
- * The standard 64 (N32) calling sequence is supported, with a0
- * holding a function pointer, a1 a new stack pointer, a2-a7 -- its
- * first six arguments and the stack -- remaining ones (up to O32_ARGC,
- * including a2-a7). Static registers, gp and fp are preserved, v0 holds
- * a result. This code relies on the called o32 function for sp and ra
- * restoration and this dispatcher has to be placed in a KSEGx (or KUSEG)
- * address space.  Any pointers passed have to point to addresses within
- * one of these spaces as well.
+ * The standard 64 (N32) calling sequence is supported, with a0 holding
+ * a function pointer, a1 a pointer to the new stack to call the
+ * function with or 0 if no stack switching is requested, a2-a7 -- the
+ * function call's first six arguments, and the stack -- the remaining
+ * arguments (up to O32_ARGC, including a2-a7).  Static registers, gp
+ * and fp are preserved, v0 holds the result.  This code relies on the
+ * called o32 function for sp and ra restoration and this dispatcher has
+ * to be placed in a KSEGx (or KUSEG) address space.  Any pointers
+ * passed have to point to addresses within one of these spaces as well.
  */
 NESTED(call_o32, O32_FRAMESZ, ra)
 		REG_SUBU	sp,O32_FRAMESZ
@@ -51,32 +60,36 @@ NESTED(call_o32, O32_FRAMESZ, ra)
 		REG_S		s0,O32_FRAMESZ-11*SZREG(sp)
 
 		move		jp,a0
-		REG_SUBU	s0,a1,O32_FRAMESZ_NEW
-		REG_S		sp,O32_FRAMESZ_NEW-1*SZREG(s0)
+
+		move		fp,sp
+		beqz		a1,0f
+		REG_SUBU	fp,a1,O32_NFRAMESZ
+0:
+		REG_S		sp,O32_NFRAMESZ-1*SZREG(fp)
 
 		sll		a0,a2,zero
 		sll		a1,a3,zero
 		sll		a2,a4,zero
 		sll		a3,a5,zero
-		sw		a6,0x10(s0)
-		sw		a7,0x14(s0)
+		sw		a6,4*O32_SZREG(fp)
+		sw		a7,5*O32_SZREG(fp)
 
 		PTR_LA		t0,O32_FRAMESZ(sp)
-		PTR_LA		t1,0x18(s0)
+		PTR_LA		t1,6*O32_SZREG(fp)
 		li		t2,O32_ARGC-6
 1:
 		lw		t3,(t0)
 		REG_ADDU	t0,SZREG
 		sw		t3,(t1)
 		REG_SUBU	t2,1
-		REG_ADDU	t1,4
+		REG_ADDU	t1,O32_SZREG
 		bnez		t2,1b
 
-		move		sp,s0
+		move		sp,fp
 
 		jalr		jp
 
-		REG_L		sp,O32_FRAMESZ_NEW-1*SZREG(sp)
+		REG_L		sp,O32_NFRAMESZ-1*SZREG(sp)
 
 		REG_L		s0,O32_FRAMESZ-11*SZREG(sp)
 		REG_L		s1,O32_FRAMESZ-10*SZREG(sp)
diff --git a/arch/mips/fw/sni/sniprom.c b/arch/mips/fw/sni/sniprom.c
index 2c2cb182af4e..6aa264b9856a 100644
--- a/arch/mips/fw/sni/sniprom.c
+++ b/arch/mips/fw/sni/sniprom.c
@@ -40,7 +40,8 @@
 
 #ifdef CONFIG_64BIT
 
-static u8 o32_stk[16384];
+/* O32 stack has to be 8-byte aligned. */
+static u64 o32_stk[4096];
 #define O32_STK	  &o32_stk[sizeof(o32_stk)]
 
 #define __PROM_O32(fun, arg) fun arg __asm__(#fun); \
diff --git a/arch/mips/include/asm/dec/prom.h b/arch/mips/include/asm/dec/prom.h
index c0ead6313845..b59a2103b61a 100644
--- a/arch/mips/include/asm/dec/prom.h
+++ b/arch/mips/include/asm/dec/prom.h
@@ -113,31 +113,31 @@ extern int (*__pmax_close)(int);
 #define __DEC_PROM_O32(fun, arg) fun arg __asm__(#fun); \
 				 __asm__(#fun " = call_o32")
 
-int __DEC_PROM_O32(_rex_bootinit, (int (*)(void)));
-int __DEC_PROM_O32(_rex_bootread, (int (*)(void)));
-int __DEC_PROM_O32(_rex_getbitmap, (int (*)(memmap *), memmap *));
+int __DEC_PROM_O32(_rex_bootinit, (int (*)(void), void *));
+int __DEC_PROM_O32(_rex_bootread, (int (*)(void), void *));
+int __DEC_PROM_O32(_rex_getbitmap, (int (*)(memmap *), void *, memmap *));
 unsigned long *__DEC_PROM_O32(_rex_slot_address,
-			     (unsigned long *(*)(int), int));
-void *__DEC_PROM_O32(_rex_gettcinfo, (void *(*)(void)));
-int __DEC_PROM_O32(_rex_getsysid, (int (*)(void)));
-void __DEC_PROM_O32(_rex_clear_cache, (void (*)(void)));
-
-int __DEC_PROM_O32(_prom_getchar, (int (*)(void)));
-char *__DEC_PROM_O32(_prom_getenv, (char *(*)(char *), char *));
-int __DEC_PROM_O32(_prom_printf, (int (*)(char *, ...), char *, ...));
-
-
-#define rex_bootinit()		_rex_bootinit(__rex_bootinit)
-#define rex_bootread()		_rex_bootread(__rex_bootread)
-#define rex_getbitmap(x)	_rex_getbitmap(__rex_getbitmap, x)
-#define rex_slot_address(x)	_rex_slot_address(__rex_slot_address, x)
-#define rex_gettcinfo()		_rex_gettcinfo(__rex_gettcinfo)
-#define rex_getsysid()		_rex_getsysid(__rex_getsysid)
-#define rex_clear_cache()	_rex_clear_cache(__rex_clear_cache)
-
-#define prom_getchar()		_prom_getchar(__prom_getchar)
-#define prom_getenv(x)		_prom_getenv(__prom_getenv, x)
-#define prom_printf(x...)	_prom_printf(__prom_printf, x)
+			     (unsigned long *(*)(int), void *, int));
+void *__DEC_PROM_O32(_rex_gettcinfo, (void *(*)(void), void *));
+int __DEC_PROM_O32(_rex_getsysid, (int (*)(void), void *));
+void __DEC_PROM_O32(_rex_clear_cache, (void (*)(void), void *));
+
+int __DEC_PROM_O32(_prom_getchar, (int (*)(void), void *));
+char *__DEC_PROM_O32(_prom_getenv, (char *(*)(char *), void *, char *));
+int __DEC_PROM_O32(_prom_printf, (int (*)(char *, ...), void *, char *, ...));
+
+
+#define rex_bootinit()		_rex_bootinit(__rex_bootinit, NULL)
+#define rex_bootread()		_rex_bootread(__rex_bootread, NULL)
+#define rex_getbitmap(x)	_rex_getbitmap(__rex_getbitmap, NULL, x)
+#define rex_slot_address(x)	_rex_slot_address(__rex_slot_address, NULL, x)
+#define rex_gettcinfo()		_rex_gettcinfo(__rex_gettcinfo, NULL)
+#define rex_getsysid()		_rex_getsysid(__rex_getsysid, NULL)
+#define rex_clear_cache()	_rex_clear_cache(__rex_clear_cache, NULL)
+
+#define prom_getchar()		_prom_getchar(__prom_getchar, NULL)
+#define prom_getenv(x)		_prom_getenv(__prom_getenv, NULL, x)
+#define prom_printf(x...)	_prom_printf(__prom_printf, NULL, x)
 
 #else /* !CONFIG_64BIT */
 
diff --git a/arch/mips/include/asm/rm9k-ocd.h b/arch/mips/include/asm/rm9k-ocd.h
deleted file mode 100644
index b0b80d9ecf96..000000000000
--- a/arch/mips/include/asm/rm9k-ocd.h
+++ /dev/null
@@ -1,56 +0,0 @@
-/*
- *  Copyright (C) 2004 by Basler Vision Technologies AG
- *  Author: Thomas Koeller <thomas.koeller@baslerweb.com>
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; either version 2 of the License, or
- *  (at your option) any later version.
- *
- *  This program is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
-
-#if !defined(_ASM_RM9K_OCD_H)
-#define _ASM_RM9K_OCD_H
-
-#include <linux/types.h>
-#include <linux/spinlock.h>
-#include <asm/io.h>
-
-extern volatile void __iomem * const ocd_base;
-extern volatile void __iomem * const titan_base;
-
-#define ocd_addr(__x__)		(ocd_base + (__x__))
-#define titan_addr(__x__)	(titan_base + (__x__))
-#define scram_addr(__x__)	(scram_base + (__x__))
-
-/* OCD register access */
-#define ocd_readl(__offs__) __raw_readl(ocd_addr(__offs__))
-#define ocd_readw(__offs__) __raw_readw(ocd_addr(__offs__))
-#define ocd_readb(__offs__) __raw_readb(ocd_addr(__offs__))
-#define ocd_writel(__val__, __offs__) \
-	__raw_writel((__val__), ocd_addr(__offs__))
-#define ocd_writew(__val__, __offs__) \
-	__raw_writew((__val__), ocd_addr(__offs__))
-#define ocd_writeb(__val__, __offs__) \
-	__raw_writeb((__val__), ocd_addr(__offs__))
-
-/* TITAN register access - 32 bit-wide only */
-#define titan_readl(__offs__) __raw_readl(titan_addr(__offs__))
-#define titan_writel(__val__, __offs__) \
-	__raw_writel((__val__), titan_addr(__offs__))
-
-/* Protect access to shared TITAN registers */
-extern spinlock_t titan_lock;
-extern int titan_irqflags;
-#define lock_titan_regs() spin_lock_irqsave(&titan_lock, titan_irqflags)
-#define unlock_titan_regs() spin_unlock_irqrestore(&titan_lock, titan_irqflags)
-
-#endif	/* !defined(_ASM_RM9K_OCD_H) */
diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h
index c6e9cd2bca8d..17960fe7a8ce 100644
--- a/arch/mips/include/asm/syscall.h
+++ b/arch/mips/include/asm/syscall.h
@@ -133,6 +133,8 @@ static inline int syscall_get_arch(void)
 #ifdef CONFIG_64BIT
 	if (!test_thread_flag(TIF_32BIT_REGS))
 		arch |= __AUDIT_ARCH_64BIT;
+	if (test_thread_flag(TIF_32BIT_ADDR))
+		arch |= __AUDIT_ARCH_CONVENTION_MIPS64_N32;
 #endif
 #if defined(__LITTLE_ENDIAN)
 	arch |=  __AUDIT_ARCH_LE;
diff --git a/arch/mips/include/uapi/asm/inst.h b/arch/mips/include/uapi/asm/inst.h
index df6e775f3fef..3125797f2a88 100644
--- a/arch/mips/include/uapi/asm/inst.h
+++ b/arch/mips/include/uapi/asm/inst.h
@@ -484,13 +484,13 @@ enum MIPS6e_i8_func {
  * Damn ...  bitfields depend from byteorder :-(
  */
 #ifdef __MIPSEB__
-#define BITFIELD_FIELD(field, more)					\
+#define __BITFIELD_FIELD(field, more)					\
 	field;								\
 	more
 
 #elif defined(__MIPSEL__)
 
-#define BITFIELD_FIELD(field, more)					\
+#define __BITFIELD_FIELD(field, more)					\
 	more								\
 	field;
 
@@ -499,112 +499,112 @@ enum MIPS6e_i8_func {
 #endif
 
 struct j_format {
-	BITFIELD_FIELD(unsigned int opcode : 6, /* Jump format */
-	BITFIELD_FIELD(unsigned int target : 26,
+	__BITFIELD_FIELD(unsigned int opcode : 6, /* Jump format */
+	__BITFIELD_FIELD(unsigned int target : 26,
 	;))
 };
 
 struct i_format {			/* signed immediate format */
-	BITFIELD_FIELD(unsigned int opcode : 6,
-	BITFIELD_FIELD(unsigned int rs : 5,
-	BITFIELD_FIELD(unsigned int rt : 5,
-	BITFIELD_FIELD(signed int simmediate : 16,
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(unsigned int rs : 5,
+	__BITFIELD_FIELD(unsigned int rt : 5,
+	__BITFIELD_FIELD(signed int simmediate : 16,
 	;))))
 };
 
 struct u_format {			/* unsigned immediate format */
-	BITFIELD_FIELD(unsigned int opcode : 6,
-	BITFIELD_FIELD(unsigned int rs : 5,
-	BITFIELD_FIELD(unsigned int rt : 5,
-	BITFIELD_FIELD(unsigned int uimmediate : 16,
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(unsigned int rs : 5,
+	__BITFIELD_FIELD(unsigned int rt : 5,
+	__BITFIELD_FIELD(unsigned int uimmediate : 16,
 	;))))
 };
 
 struct c_format {			/* Cache (>= R6000) format */
-	BITFIELD_FIELD(unsigned int opcode : 6,
-	BITFIELD_FIELD(unsigned int rs : 5,
-	BITFIELD_FIELD(unsigned int c_op : 3,
-	BITFIELD_FIELD(unsigned int cache : 2,
-	BITFIELD_FIELD(unsigned int simmediate : 16,
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(unsigned int rs : 5,
+	__BITFIELD_FIELD(unsigned int c_op : 3,
+	__BITFIELD_FIELD(unsigned int cache : 2,
+	__BITFIELD_FIELD(unsigned int simmediate : 16,
 	;)))))
 };
 
 struct r_format {			/* Register format */
-	BITFIELD_FIELD(unsigned int opcode : 6,
-	BITFIELD_FIELD(unsigned int rs : 5,
-	BITFIELD_FIELD(unsigned int rt : 5,
-	BITFIELD_FIELD(unsigned int rd : 5,
-	BITFIELD_FIELD(unsigned int re : 5,
-	BITFIELD_FIELD(unsigned int func : 6,
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(unsigned int rs : 5,
+	__BITFIELD_FIELD(unsigned int rt : 5,
+	__BITFIELD_FIELD(unsigned int rd : 5,
+	__BITFIELD_FIELD(unsigned int re : 5,
+	__BITFIELD_FIELD(unsigned int func : 6,
 	;))))))
 };
 
 struct p_format {		/* Performance counter format (R10000) */
-	BITFIELD_FIELD(unsigned int opcode : 6,
-	BITFIELD_FIELD(unsigned int rs : 5,
-	BITFIELD_FIELD(unsigned int rt : 5,
-	BITFIELD_FIELD(unsigned int rd : 5,
-	BITFIELD_FIELD(unsigned int re : 5,
-	BITFIELD_FIELD(unsigned int func : 6,
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(unsigned int rs : 5,
+	__BITFIELD_FIELD(unsigned int rt : 5,
+	__BITFIELD_FIELD(unsigned int rd : 5,
+	__BITFIELD_FIELD(unsigned int re : 5,
+	__BITFIELD_FIELD(unsigned int func : 6,
 	;))))))
 };
 
 struct f_format {			/* FPU register format */
-	BITFIELD_FIELD(unsigned int opcode : 6,
-	BITFIELD_FIELD(unsigned int : 1,
-	BITFIELD_FIELD(unsigned int fmt : 4,
-	BITFIELD_FIELD(unsigned int rt : 5,
-	BITFIELD_FIELD(unsigned int rd : 5,
-	BITFIELD_FIELD(unsigned int re : 5,
-	BITFIELD_FIELD(unsigned int func : 6,
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(unsigned int : 1,
+	__BITFIELD_FIELD(unsigned int fmt : 4,
+	__BITFIELD_FIELD(unsigned int rt : 5,
+	__BITFIELD_FIELD(unsigned int rd : 5,
+	__BITFIELD_FIELD(unsigned int re : 5,
+	__BITFIELD_FIELD(unsigned int func : 6,
 	;)))))))
 };
 
 struct ma_format {		/* FPU multiply and add format (MIPS IV) */
-	BITFIELD_FIELD(unsigned int opcode : 6,
-	BITFIELD_FIELD(unsigned int fr : 5,
-	BITFIELD_FIELD(unsigned int ft : 5,
-	BITFIELD_FIELD(unsigned int fs : 5,
-	BITFIELD_FIELD(unsigned int fd : 5,
-	BITFIELD_FIELD(unsigned int func : 4,
-	BITFIELD_FIELD(unsigned int fmt : 2,
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(unsigned int fr : 5,
+	__BITFIELD_FIELD(unsigned int ft : 5,
+	__BITFIELD_FIELD(unsigned int fs : 5,
+	__BITFIELD_FIELD(unsigned int fd : 5,
+	__BITFIELD_FIELD(unsigned int func : 4,
+	__BITFIELD_FIELD(unsigned int fmt : 2,
 	;)))))))
 };
 
 struct b_format {			/* BREAK and SYSCALL */
-	BITFIELD_FIELD(unsigned int opcode : 6,
-	BITFIELD_FIELD(unsigned int code : 20,
-	BITFIELD_FIELD(unsigned int func : 6,
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(unsigned int code : 20,
+	__BITFIELD_FIELD(unsigned int func : 6,
 	;)))
 };
 
 struct ps_format {			/* MIPS-3D / paired single format */
-	BITFIELD_FIELD(unsigned int opcode : 6,
-	BITFIELD_FIELD(unsigned int rs : 5,
-	BITFIELD_FIELD(unsigned int ft : 5,
-	BITFIELD_FIELD(unsigned int fs : 5,
-	BITFIELD_FIELD(unsigned int fd : 5,
-	BITFIELD_FIELD(unsigned int func : 6,
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(unsigned int rs : 5,
+	__BITFIELD_FIELD(unsigned int ft : 5,
+	__BITFIELD_FIELD(unsigned int fs : 5,
+	__BITFIELD_FIELD(unsigned int fd : 5,
+	__BITFIELD_FIELD(unsigned int func : 6,
 	;))))))
 };
 
 struct v_format {				/* MDMX vector format */
-	BITFIELD_FIELD(unsigned int opcode : 6,
-	BITFIELD_FIELD(unsigned int sel : 4,
-	BITFIELD_FIELD(unsigned int fmt : 1,
-	BITFIELD_FIELD(unsigned int vt : 5,
-	BITFIELD_FIELD(unsigned int vs : 5,
-	BITFIELD_FIELD(unsigned int vd : 5,
-	BITFIELD_FIELD(unsigned int func : 6,
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(unsigned int sel : 4,
+	__BITFIELD_FIELD(unsigned int fmt : 1,
+	__BITFIELD_FIELD(unsigned int vt : 5,
+	__BITFIELD_FIELD(unsigned int vs : 5,
+	__BITFIELD_FIELD(unsigned int vd : 5,
+	__BITFIELD_FIELD(unsigned int func : 6,
 	;)))))))
 };
 
 struct spec3_format {   /* SPEC3 */
-	BITFIELD_FIELD(unsigned int opcode:6,
-	BITFIELD_FIELD(unsigned int rs:5,
-	BITFIELD_FIELD(unsigned int rt:5,
-	BITFIELD_FIELD(signed int simmediate:9,
-	BITFIELD_FIELD(unsigned int func:7,
+	__BITFIELD_FIELD(unsigned int opcode:6,
+	__BITFIELD_FIELD(unsigned int rs:5,
+	__BITFIELD_FIELD(unsigned int rt:5,
+	__BITFIELD_FIELD(signed int simmediate:9,
+	__BITFIELD_FIELD(unsigned int func:7,
 	;)))))
 };
 
@@ -616,141 +616,141 @@ struct spec3_format {   /* SPEC3 */
  *	if it is MIPS32 instruction re-encoded for use in the microMIPS ASE.
  */
 struct fb_format {		/* FPU branch format (MIPS32) */
-	BITFIELD_FIELD(unsigned int opcode : 6,
-	BITFIELD_FIELD(unsigned int bc : 5,
-	BITFIELD_FIELD(unsigned int cc : 3,
-	BITFIELD_FIELD(unsigned int flag : 2,
-	BITFIELD_FIELD(signed int simmediate : 16,
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(unsigned int bc : 5,
+	__BITFIELD_FIELD(unsigned int cc : 3,
+	__BITFIELD_FIELD(unsigned int flag : 2,
+	__BITFIELD_FIELD(signed int simmediate : 16,
 	;)))))
 };
 
 struct fp0_format {		/* FPU multiply and add format (MIPS32) */
-	BITFIELD_FIELD(unsigned int opcode : 6,
-	BITFIELD_FIELD(unsigned int fmt : 5,
-	BITFIELD_FIELD(unsigned int ft : 5,
-	BITFIELD_FIELD(unsigned int fs : 5,
-	BITFIELD_FIELD(unsigned int fd : 5,
-	BITFIELD_FIELD(unsigned int func : 6,
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(unsigned int fmt : 5,
+	__BITFIELD_FIELD(unsigned int ft : 5,
+	__BITFIELD_FIELD(unsigned int fs : 5,
+	__BITFIELD_FIELD(unsigned int fd : 5,
+	__BITFIELD_FIELD(unsigned int func : 6,
 	;))))))
 };
 
 struct mm_fp0_format {		/* FPU multipy and add format (microMIPS) */
-	BITFIELD_FIELD(unsigned int opcode : 6,
-	BITFIELD_FIELD(unsigned int ft : 5,
-	BITFIELD_FIELD(unsigned int fs : 5,
-	BITFIELD_FIELD(unsigned int fd : 5,
-	BITFIELD_FIELD(unsigned int fmt : 3,
-	BITFIELD_FIELD(unsigned int op : 2,
-	BITFIELD_FIELD(unsigned int func : 6,
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(unsigned int ft : 5,
+	__BITFIELD_FIELD(unsigned int fs : 5,
+	__BITFIELD_FIELD(unsigned int fd : 5,
+	__BITFIELD_FIELD(unsigned int fmt : 3,
+	__BITFIELD_FIELD(unsigned int op : 2,
+	__BITFIELD_FIELD(unsigned int func : 6,
 	;)))))))
 };
 
 struct fp1_format {		/* FPU mfc1 and cfc1 format (MIPS32) */
-	BITFIELD_FIELD(unsigned int opcode : 6,
-	BITFIELD_FIELD(unsigned int op : 5,
-	BITFIELD_FIELD(unsigned int rt : 5,
-	BITFIELD_FIELD(unsigned int fs : 5,
-	BITFIELD_FIELD(unsigned int fd : 5,
-	BITFIELD_FIELD(unsigned int func : 6,
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(unsigned int op : 5,
+	__BITFIELD_FIELD(unsigned int rt : 5,
+	__BITFIELD_FIELD(unsigned int fs : 5,
+	__BITFIELD_FIELD(unsigned int fd : 5,
+	__BITFIELD_FIELD(unsigned int func : 6,
 	;))))))
 };
 
 struct mm_fp1_format {		/* FPU mfc1 and cfc1 format (microMIPS) */
-	BITFIELD_FIELD(unsigned int opcode : 6,
-	BITFIELD_FIELD(unsigned int rt : 5,
-	BITFIELD_FIELD(unsigned int fs : 5,
-	BITFIELD_FIELD(unsigned int fmt : 2,
-	BITFIELD_FIELD(unsigned int op : 8,
-	BITFIELD_FIELD(unsigned int func : 6,
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(unsigned int rt : 5,
+	__BITFIELD_FIELD(unsigned int fs : 5,
+	__BITFIELD_FIELD(unsigned int fmt : 2,
+	__BITFIELD_FIELD(unsigned int op : 8,
+	__BITFIELD_FIELD(unsigned int func : 6,
 	;))))))
 };
 
 struct mm_fp2_format {		/* FPU movt and movf format (microMIPS) */
-	BITFIELD_FIELD(unsigned int opcode : 6,
-	BITFIELD_FIELD(unsigned int fd : 5,
-	BITFIELD_FIELD(unsigned int fs : 5,
-	BITFIELD_FIELD(unsigned int cc : 3,
-	BITFIELD_FIELD(unsigned int zero : 2,
-	BITFIELD_FIELD(unsigned int fmt : 2,
-	BITFIELD_FIELD(unsigned int op : 3,
-	BITFIELD_FIELD(unsigned int func : 6,
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(unsigned int fd : 5,
+	__BITFIELD_FIELD(unsigned int fs : 5,
+	__BITFIELD_FIELD(unsigned int cc : 3,
+	__BITFIELD_FIELD(unsigned int zero : 2,
+	__BITFIELD_FIELD(unsigned int fmt : 2,
+	__BITFIELD_FIELD(unsigned int op : 3,
+	__BITFIELD_FIELD(unsigned int func : 6,
 	;))))))))
 };
 
 struct mm_fp3_format {		/* FPU abs and neg format (microMIPS) */
-	BITFIELD_FIELD(unsigned int opcode : 6,
-	BITFIELD_FIELD(unsigned int rt : 5,
-	BITFIELD_FIELD(unsigned int fs : 5,
-	BITFIELD_FIELD(unsigned int fmt : 3,
-	BITFIELD_FIELD(unsigned int op : 7,
-	BITFIELD_FIELD(unsigned int func : 6,
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(unsigned int rt : 5,
+	__BITFIELD_FIELD(unsigned int fs : 5,
+	__BITFIELD_FIELD(unsigned int fmt : 3,
+	__BITFIELD_FIELD(unsigned int op : 7,
+	__BITFIELD_FIELD(unsigned int func : 6,
 	;))))))
 };
 
 struct mm_fp4_format {		/* FPU c.cond format (microMIPS) */
-	BITFIELD_FIELD(unsigned int opcode : 6,
-	BITFIELD_FIELD(unsigned int rt : 5,
-	BITFIELD_FIELD(unsigned int fs : 5,
-	BITFIELD_FIELD(unsigned int cc : 3,
-	BITFIELD_FIELD(unsigned int fmt : 3,
-	BITFIELD_FIELD(unsigned int cond : 4,
-	BITFIELD_FIELD(unsigned int func : 6,
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(unsigned int rt : 5,
+	__BITFIELD_FIELD(unsigned int fs : 5,
+	__BITFIELD_FIELD(unsigned int cc : 3,
+	__BITFIELD_FIELD(unsigned int fmt : 3,
+	__BITFIELD_FIELD(unsigned int cond : 4,
+	__BITFIELD_FIELD(unsigned int func : 6,
 	;)))))))
 };
 
 struct mm_fp5_format {		/* FPU lwxc1 and swxc1 format (microMIPS) */
-	BITFIELD_FIELD(unsigned int opcode : 6,
-	BITFIELD_FIELD(unsigned int index : 5,
-	BITFIELD_FIELD(unsigned int base : 5,
-	BITFIELD_FIELD(unsigned int fd : 5,
-	BITFIELD_FIELD(unsigned int op : 5,
-	BITFIELD_FIELD(unsigned int func : 6,
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(unsigned int index : 5,
+	__BITFIELD_FIELD(unsigned int base : 5,
+	__BITFIELD_FIELD(unsigned int fd : 5,
+	__BITFIELD_FIELD(unsigned int op : 5,
+	__BITFIELD_FIELD(unsigned int func : 6,
 	;))))))
 };
 
 struct fp6_format {		/* FPU madd and msub format (MIPS IV) */
-	BITFIELD_FIELD(unsigned int opcode : 6,
-	BITFIELD_FIELD(unsigned int fr : 5,
-	BITFIELD_FIELD(unsigned int ft : 5,
-	BITFIELD_FIELD(unsigned int fs : 5,
-	BITFIELD_FIELD(unsigned int fd : 5,
-	BITFIELD_FIELD(unsigned int func : 6,
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(unsigned int fr : 5,
+	__BITFIELD_FIELD(unsigned int ft : 5,
+	__BITFIELD_FIELD(unsigned int fs : 5,
+	__BITFIELD_FIELD(unsigned int fd : 5,
+	__BITFIELD_FIELD(unsigned int func : 6,
 	;))))))
 };
 
 struct mm_fp6_format {		/* FPU madd and msub format (microMIPS) */
-	BITFIELD_FIELD(unsigned int opcode : 6,
-	BITFIELD_FIELD(unsigned int ft : 5,
-	BITFIELD_FIELD(unsigned int fs : 5,
-	BITFIELD_FIELD(unsigned int fd : 5,
-	BITFIELD_FIELD(unsigned int fr : 5,
-	BITFIELD_FIELD(unsigned int func : 6,
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(unsigned int ft : 5,
+	__BITFIELD_FIELD(unsigned int fs : 5,
+	__BITFIELD_FIELD(unsigned int fd : 5,
+	__BITFIELD_FIELD(unsigned int fr : 5,
+	__BITFIELD_FIELD(unsigned int func : 6,
 	;))))))
 };
 
 struct mm_i_format {		/* Immediate format (microMIPS) */
-	BITFIELD_FIELD(unsigned int opcode : 6,
-	BITFIELD_FIELD(unsigned int rt : 5,
-	BITFIELD_FIELD(unsigned int rs : 5,
-	BITFIELD_FIELD(signed int simmediate : 16,
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(unsigned int rt : 5,
+	__BITFIELD_FIELD(unsigned int rs : 5,
+	__BITFIELD_FIELD(signed int simmediate : 16,
 	;))))
 };
 
 struct mm_m_format {		/* Multi-word load/store format (microMIPS) */
-	BITFIELD_FIELD(unsigned int opcode : 6,
-	BITFIELD_FIELD(unsigned int rd : 5,
-	BITFIELD_FIELD(unsigned int base : 5,
-	BITFIELD_FIELD(unsigned int func : 4,
-	BITFIELD_FIELD(signed int simmediate : 12,
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(unsigned int rd : 5,
+	__BITFIELD_FIELD(unsigned int base : 5,
+	__BITFIELD_FIELD(unsigned int func : 4,
+	__BITFIELD_FIELD(signed int simmediate : 12,
 	;)))))
 };
 
 struct mm_x_format {		/* Scaled indexed load format (microMIPS) */
-	BITFIELD_FIELD(unsigned int opcode : 6,
-	BITFIELD_FIELD(unsigned int index : 5,
-	BITFIELD_FIELD(unsigned int base : 5,
-	BITFIELD_FIELD(unsigned int rd : 5,
-	BITFIELD_FIELD(unsigned int func : 11,
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(unsigned int index : 5,
+	__BITFIELD_FIELD(unsigned int base : 5,
+	__BITFIELD_FIELD(unsigned int rd : 5,
+	__BITFIELD_FIELD(unsigned int func : 11,
 	;)))))
 };
 
@@ -758,51 +758,51 @@ struct mm_x_format {		/* Scaled indexed load format (microMIPS) */
  * microMIPS instruction formats (16-bit length)
  */
 struct mm_b0_format {		/* Unconditional branch format (microMIPS) */
-	BITFIELD_FIELD(unsigned int opcode : 6,
-	BITFIELD_FIELD(signed int simmediate : 10,
-	BITFIELD_FIELD(unsigned int : 16, /* Ignored */
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(signed int simmediate : 10,
+	__BITFIELD_FIELD(unsigned int : 16, /* Ignored */
 	;)))
 };
 
 struct mm_b1_format {		/* Conditional branch format (microMIPS) */
-	BITFIELD_FIELD(unsigned int opcode : 6,
-	BITFIELD_FIELD(unsigned int rs : 3,
-	BITFIELD_FIELD(signed int simmediate : 7,
-	BITFIELD_FIELD(unsigned int : 16, /* Ignored */
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(unsigned int rs : 3,
+	__BITFIELD_FIELD(signed int simmediate : 7,
+	__BITFIELD_FIELD(unsigned int : 16, /* Ignored */
 	;))))
 };
 
 struct mm16_m_format {		/* Multi-word load/store format */
-	BITFIELD_FIELD(unsigned int opcode : 6,
-	BITFIELD_FIELD(unsigned int func : 4,
-	BITFIELD_FIELD(unsigned int rlist : 2,
-	BITFIELD_FIELD(unsigned int imm : 4,
-	BITFIELD_FIELD(unsigned int : 16, /* Ignored */
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(unsigned int func : 4,
+	__BITFIELD_FIELD(unsigned int rlist : 2,
+	__BITFIELD_FIELD(unsigned int imm : 4,
+	__BITFIELD_FIELD(unsigned int : 16, /* Ignored */
 	;)))))
 };
 
 struct mm16_rb_format {		/* Signed immediate format */
-	BITFIELD_FIELD(unsigned int opcode : 6,
-	BITFIELD_FIELD(unsigned int rt : 3,
-	BITFIELD_FIELD(unsigned int base : 3,
-	BITFIELD_FIELD(signed int simmediate : 4,
-	BITFIELD_FIELD(unsigned int : 16, /* Ignored */
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(unsigned int rt : 3,
+	__BITFIELD_FIELD(unsigned int base : 3,
+	__BITFIELD_FIELD(signed int simmediate : 4,
+	__BITFIELD_FIELD(unsigned int : 16, /* Ignored */
 	;)))))
 };
 
 struct mm16_r3_format {		/* Load from global pointer format */
-	BITFIELD_FIELD(unsigned int opcode : 6,
-	BITFIELD_FIELD(unsigned int rt : 3,
-	BITFIELD_FIELD(signed int simmediate : 7,
-	BITFIELD_FIELD(unsigned int : 16, /* Ignored */
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(unsigned int rt : 3,
+	__BITFIELD_FIELD(signed int simmediate : 7,
+	__BITFIELD_FIELD(unsigned int : 16, /* Ignored */
 	;))))
 };
 
 struct mm16_r5_format {		/* Load/store from stack pointer format */
-	BITFIELD_FIELD(unsigned int opcode : 6,
-	BITFIELD_FIELD(unsigned int rt : 5,
-	BITFIELD_FIELD(signed int simmediate : 5,
-	BITFIELD_FIELD(unsigned int : 16, /* Ignored */
+	__BITFIELD_FIELD(unsigned int opcode : 6,
+	__BITFIELD_FIELD(unsigned int rt : 5,
+	__BITFIELD_FIELD(signed int simmediate : 5,
+	__BITFIELD_FIELD(unsigned int : 16, /* Ignored */
 	;))))
 };
 
@@ -810,57 +810,57 @@ struct mm16_r5_format {		/* Load/store from stack pointer format */
  * MIPS16e instruction formats (16-bit length)
  */
 struct m16e_rr {
-	BITFIELD_FIELD(unsigned int opcode : 5,
-	BITFIELD_FIELD(unsigned int rx : 3,
-	BITFIELD_FIELD(unsigned int nd : 1,
-	BITFIELD_FIELD(unsigned int l : 1,
-	BITFIELD_FIELD(unsigned int ra : 1,
-	BITFIELD_FIELD(unsigned int func : 5,
+	__BITFIELD_FIELD(unsigned int opcode : 5,
+	__BITFIELD_FIELD(unsigned int rx : 3,
+	__BITFIELD_FIELD(unsigned int nd : 1,
+	__BITFIELD_FIELD(unsigned int l : 1,
+	__BITFIELD_FIELD(unsigned int ra : 1,
+	__BITFIELD_FIELD(unsigned int func : 5,
 	;))))))
 };
 
 struct m16e_jal {
-	BITFIELD_FIELD(unsigned int opcode : 5,
-	BITFIELD_FIELD(unsigned int x : 1,
-	BITFIELD_FIELD(unsigned int imm20_16 : 5,
-	BITFIELD_FIELD(signed int imm25_21 : 5,
+	__BITFIELD_FIELD(unsigned int opcode : 5,
+	__BITFIELD_FIELD(unsigned int x : 1,
+	__BITFIELD_FIELD(unsigned int imm20_16 : 5,
+	__BITFIELD_FIELD(signed int imm25_21 : 5,
 	;))))
 };
 
 struct m16e_i64 {
-	BITFIELD_FIELD(unsigned int opcode : 5,
-	BITFIELD_FIELD(unsigned int func : 3,
-	BITFIELD_FIELD(unsigned int imm : 8,
+	__BITFIELD_FIELD(unsigned int opcode : 5,
+	__BITFIELD_FIELD(unsigned int func : 3,
+	__BITFIELD_FIELD(unsigned int imm : 8,
 	;)))
 };
 
 struct m16e_ri64 {
-	BITFIELD_FIELD(unsigned int opcode : 5,
-	BITFIELD_FIELD(unsigned int func : 3,
-	BITFIELD_FIELD(unsigned int ry : 3,
-	BITFIELD_FIELD(unsigned int imm : 5,
+	__BITFIELD_FIELD(unsigned int opcode : 5,
+	__BITFIELD_FIELD(unsigned int func : 3,
+	__BITFIELD_FIELD(unsigned int ry : 3,
+	__BITFIELD_FIELD(unsigned int imm : 5,
 	;))))
 };
 
 struct m16e_ri {
-	BITFIELD_FIELD(unsigned int opcode : 5,
-	BITFIELD_FIELD(unsigned int rx : 3,
-	BITFIELD_FIELD(unsigned int imm : 8,
+	__BITFIELD_FIELD(unsigned int opcode : 5,
+	__BITFIELD_FIELD(unsigned int rx : 3,
+	__BITFIELD_FIELD(unsigned int imm : 8,
 	;)))
 };
 
 struct m16e_rri {
-	BITFIELD_FIELD(unsigned int opcode : 5,
-	BITFIELD_FIELD(unsigned int rx : 3,
-	BITFIELD_FIELD(unsigned int ry : 3,
-	BITFIELD_FIELD(unsigned int imm : 5,
+	__BITFIELD_FIELD(unsigned int opcode : 5,
+	__BITFIELD_FIELD(unsigned int rx : 3,
+	__BITFIELD_FIELD(unsigned int ry : 3,
+	__BITFIELD_FIELD(unsigned int imm : 5,
 	;))))
 };
 
 struct m16e_i8 {
-	BITFIELD_FIELD(unsigned int opcode : 5,
-	BITFIELD_FIELD(unsigned int func : 3,
-	BITFIELD_FIELD(unsigned int imm : 8,
+	__BITFIELD_FIELD(unsigned int opcode : 5,
+	__BITFIELD_FIELD(unsigned int func : 3,
+	__BITFIELD_FIELD(unsigned int imm : 8,
 	;)))
 };
 
diff --git a/arch/mips/include/uapi/asm/unistd.h b/arch/mips/include/uapi/asm/unistd.h
index d6e154a9e6a5..2692abb28e36 100644
--- a/arch/mips/include/uapi/asm/unistd.h
+++ b/arch/mips/include/uapi/asm/unistd.h
@@ -371,11 +371,12 @@
 #define __NR_finit_module		(__NR_Linux + 348)
 #define __NR_sched_setattr		(__NR_Linux + 349)
 #define __NR_sched_getattr		(__NR_Linux + 350)
+#define __NR_renameat2			(__NR_Linux + 351)
 
 /*
  * Offset of the last Linux o32 flavoured syscall
  */
-#define __NR_Linux_syscalls		350
+#define __NR_Linux_syscalls		351
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
 
@@ -699,11 +700,12 @@
 #define __NR_getdents64			(__NR_Linux + 308)
 #define __NR_sched_setattr		(__NR_Linux + 309)
 #define __NR_sched_getattr		(__NR_Linux + 310)
+#define __NR_renameat2			(__NR_Linux + 311)
 
 /*
  * Offset of the last Linux 64-bit flavoured syscall
  */
-#define __NR_Linux_syscalls		310
+#define __NR_Linux_syscalls		311
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
 
@@ -1031,11 +1033,12 @@
 #define __NR_finit_module		(__NR_Linux + 312)
 #define __NR_sched_setattr		(__NR_Linux + 313)
 #define __NR_sched_getattr		(__NR_Linux + 314)
+#define __NR_renameat2			(__NR_Linux + 315)
 
 /*
  * Offset of the last N32 flavoured syscall
  */
-#define __NR_Linux_syscalls		314
+#define __NR_Linux_syscalls		315
 
 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
 
diff --git a/arch/mips/kernel/proc.c b/arch/mips/kernel/proc.c
index e40971b51d2f..037a44d962f3 100644
--- a/arch/mips/kernel/proc.c
+++ b/arch/mips/kernel/proc.c
@@ -124,14 +124,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 	seq_printf(m, "kscratch registers\t: %d\n",
 		      hweight8(cpu_data[n].kscratch_mask));
 	seq_printf(m, "core\t\t\t: %d\n", cpu_data[n].core);
-#if defined(CONFIG_MIPS_MT_SMP) || defined(CONFIG_MIPS_MT_SMTC)
-	if (cpu_has_mipsmt) {
-		seq_printf(m, "VPE\t\t\t: %d\n", cpu_data[n].vpe_id);
-#if defined(CONFIG_MIPS_MT_SMTC)
-		seq_printf(m, "TC\t\t\t: %d\n", cpu_data[n].tc_id);
-#endif
-	}
-#endif
+
 	sprintf(fmt, "VCE%%c exceptions\t\t: %s\n",
 		      cpu_has_vce ? "%u" : "not available");
 	seq_printf(m, fmt, 'D', vced_count);
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index fdc70b400442..3245474f19d5 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -577,3 +577,4 @@ EXPORT(sys_call_table)
 	PTR	sys_finit_module
 	PTR	sys_sched_setattr
 	PTR	sys_sched_getattr		/* 4350 */
+	PTR	sys_renameat2
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index dd99c3285aea..be2fedd4ae33 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -430,4 +430,5 @@ EXPORT(sys_call_table)
 	PTR	sys_getdents64
 	PTR	sys_sched_setattr
 	PTR	sys_sched_getattr		/* 5310 */
+	PTR	sys_renameat2
 	.size	sys_call_table,.-sys_call_table
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index f68d2f4f0090..c1dbcda4b816 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -423,4 +423,5 @@ EXPORT(sysn32_call_table)
 	PTR	sys_finit_module
 	PTR	sys_sched_setattr
 	PTR	sys_sched_getattr
+	PTR	sys_renameat2			/* 6315 */
 	.size	sysn32_call_table,.-sysn32_call_table
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index 70f6acecd928..f1343ccd7ed7 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -556,4 +556,5 @@ EXPORT(sys32_call_table)
 	PTR	sys_finit_module
 	PTR	sys_sched_setattr
 	PTR	sys_sched_getattr		/* 4350 */
+	PTR	sys_renameat2
 	.size	sys32_call_table,.-sys32_call_table
diff --git a/arch/mips/lantiq/dts/easy50712.dts b/arch/mips/lantiq/dts/easy50712.dts
index fac1f5b178eb..143b8a37b5e4 100644
--- a/arch/mips/lantiq/dts/easy50712.dts
+++ b/arch/mips/lantiq/dts/easy50712.dts
@@ -8,6 +8,7 @@
 	};
 
 	memory@0 {
+		device_type = "memory";
 		reg = <0x0 0x2000000>;
 	};
 
diff --git a/arch/mips/lib/csum_partial.S b/arch/mips/lib/csum_partial.S
index 2e4825e48388..9901237563c5 100644
--- a/arch/mips/lib/csum_partial.S
+++ b/arch/mips/lib/csum_partial.S
@@ -56,14 +56,20 @@
 #define UNIT(unit)  ((unit)*NBYTES)
 
 #define ADDC(sum,reg)						\
+	.set	push;						\
+	.set	noat;						\
 	ADD	sum, reg;					\
 	sltu	v1, sum, reg;					\
 	ADD	sum, v1;					\
+	.set	pop
 
 #define ADDC32(sum,reg)						\
+	.set	push;						\
+	.set	noat;						\
 	addu	sum, reg;					\
 	sltu	v1, sum, reg;					\
 	addu	sum, v1;					\
+	.set	pop
 
 #define CSUM_BIGCHUNK1(src, offset, sum, _t0, _t1, _t2, _t3)	\
 	LOAD	_t0, (offset + UNIT(0))(src);			\
@@ -710,6 +716,8 @@ LEAF(csum_partial)
 	ADDC(sum, t2)
 .Ldone\@:
 	/* fold checksum */
+	.set	push
+	.set	noat
 #ifdef USE_DOUBLE
 	dsll32	v1, sum, 0
 	daddu	sum, v1
@@ -732,6 +740,7 @@ LEAF(csum_partial)
 	or	sum, sum, t0
 1:
 #endif
+	.set	pop
 	.set reorder
 	ADDC32(sum, psum)
 	jr	ra
diff --git a/arch/mips/lib/delay.c b/arch/mips/lib/delay.c
index 44713af15a62..705cfb7c1a74 100644
--- a/arch/mips/lib/delay.c
+++ b/arch/mips/lib/delay.c
@@ -6,7 +6,7 @@
  * Copyright (C) 1994 by Waldorf Electronics
  * Copyright (C) 1995 - 2000, 01, 03 by Ralf Baechle
  * Copyright (C) 1999, 2000 Silicon Graphics, Inc.
- * Copyright (C) 2007  Maciej W. Rozycki
+ * Copyright (C) 2007, 2014 Maciej W. Rozycki
  */
 #include <linux/module.h>
 #include <linux/param.h>
@@ -15,6 +15,12 @@
 #include <asm/compiler.h>
 #include <asm/war.h>
 
+#ifndef CONFIG_CPU_DADDI_WORKAROUNDS
+#define GCC_DADDI_IMM_ASM() "I"
+#else
+#define GCC_DADDI_IMM_ASM() "r"
+#endif
+
 void __delay(unsigned long loops)
 {
 	__asm__ __volatile__ (
@@ -22,13 +28,13 @@ void __delay(unsigned long loops)
 	"	.align	3					\n"
 	"1:	bnez	%0, 1b					\n"
 #if BITS_PER_LONG == 32
-	"	subu	%0, 1					\n"
+	"	subu	%0, %1					\n"
 #else
-	"	dsubu	%0, 1					\n"
+	"	dsubu	%0, %1					\n"
 #endif
 	"	.set	reorder					\n"
 	: "=r" (loops)
-	: "0" (loops));
+	: GCC_DADDI_IMM_ASM() (1), "0" (loops));
 }
 EXPORT_SYMBOL(__delay);
 
diff --git a/arch/mips/lib/strncpy_user.S b/arch/mips/lib/strncpy_user.S
index d3301cd1e9a5..3c32baf8b494 100644
--- a/arch/mips/lib/strncpy_user.S
+++ b/arch/mips/lib/strncpy_user.S
@@ -35,7 +35,6 @@ LEAF(__strncpy_from_\func\()_asm)
 	bnez		v0, .Lfault\@
 
 FEXPORT(__strncpy_from_\func\()_nocheck_asm)
-	.set		noreorder
 	move		t0, zero
 	move		v1, a1
 .ifeqs "\func","kernel"
@@ -45,21 +44,21 @@ FEXPORT(__strncpy_from_\func\()_nocheck_asm)
 .endif
 	PTR_ADDIU	v1, 1
 	R10KCBARRIER(0(ra))
+	sb		v0, (a0)
 	beqz		v0, 2f
-	 sb		v0, (a0)
 	PTR_ADDIU	t0, 1
+	PTR_ADDIU	a0, 1
 	bne		t0, a2, 1b
-	 PTR_ADDIU	a0, 1
 2:	PTR_ADDU	v0, a1, t0
 	xor		v0, a1
 	bltz		v0, .Lfault\@
-	 nop
+	move		v0, t0
 	jr		ra			# return n
-	 move		v0, t0
 	END(__strncpy_from_\func\()_asm)
 
-.Lfault\@: jr		ra
-	  li		v0, -EFAULT
+.Lfault\@:
+	li		v0, -EFAULT
+	jr		ra
 
 	.section	__ex_table,"a"
 	PTR		1b, .Lfault\@
diff --git a/arch/mips/loongson/Kconfig b/arch/mips/loongson/Kconfig
index 7397be226a06..603d79a95f47 100644
--- a/arch/mips/loongson/Kconfig
+++ b/arch/mips/loongson/Kconfig
@@ -64,7 +64,6 @@ config LEMOTE_MACH3A
 	bool "Lemote Loongson 3A family machines"
 	select ARCH_SPARSEMEM_ENABLE
 	select GENERIC_ISA_DMA_SUPPORT_BROKEN
-	select GENERIC_HARDIRQS_NO__DO_IRQ
 	select BOOT_ELF32
 	select BOARD_SCACHE
 	select CSRC_R4K
diff --git a/arch/mips/loongson/lemote-2f/clock.c b/arch/mips/loongson/lemote-2f/clock.c
index e1f427f4f5f3..67dd94ef28e6 100644
--- a/arch/mips/loongson/lemote-2f/clock.c
+++ b/arch/mips/loongson/lemote-2f/clock.c
@@ -91,6 +91,7 @@ EXPORT_SYMBOL(clk_put);
 
 int clk_set_rate(struct clk *clk, unsigned long rate)
 {
+	unsigned int rate_khz = rate / 1000;
 	int ret = 0;
 	int regval;
 	int i;
@@ -111,10 +112,10 @@ int clk_set_rate(struct clk *clk, unsigned long rate)
 		if (loongson2_clockmod_table[i].frequency ==
 		    CPUFREQ_ENTRY_INVALID)
 			continue;
-		if (rate == loongson2_clockmod_table[i].frequency)
+		if (rate_khz == loongson2_clockmod_table[i].frequency)
 			break;
 	}
-	if (rate != loongson2_clockmod_table[i].frequency)
+	if (rate_khz != loongson2_clockmod_table[i].frequency)
 		return -ENOTSUPP;
 
 	clk->rate = rate;
diff --git a/arch/mips/mm/tlb-funcs.S b/arch/mips/mm/tlb-funcs.S
index 30a494db99c2..a5427c6e9757 100644
--- a/arch/mips/mm/tlb-funcs.S
+++ b/arch/mips/mm/tlb-funcs.S
@@ -16,8 +16,10 @@
 
 #define FASTPATH_SIZE	128
 
+EXPORT(tlbmiss_handler_setup_pgd_start)
 LEAF(tlbmiss_handler_setup_pgd)
-	.space		16 * 4
+1:	j	1b		/* Dummy, will be replaced. */
+	.space	64
 END(tlbmiss_handler_setup_pgd)
 EXPORT(tlbmiss_handler_setup_pgd_end)
 
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index ee88367ab3ad..f99ec587b151 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -1422,16 +1422,17 @@ static void build_r4000_tlb_refill_handler(void)
 extern u32 handle_tlbl[], handle_tlbl_end[];
 extern u32 handle_tlbs[], handle_tlbs_end[];
 extern u32 handle_tlbm[], handle_tlbm_end[];
-extern u32 tlbmiss_handler_setup_pgd[], tlbmiss_handler_setup_pgd_end[];
+extern u32 tlbmiss_handler_setup_pgd_start[], tlbmiss_handler_setup_pgd[];
+extern u32 tlbmiss_handler_setup_pgd_end[];
 
 static void build_setup_pgd(void)
 {
 	const int a0 = 4;
 	const int __maybe_unused a1 = 5;
 	const int __maybe_unused a2 = 6;
-	u32 *p = tlbmiss_handler_setup_pgd;
+	u32 *p = tlbmiss_handler_setup_pgd_start;
 	const int tlbmiss_handler_setup_pgd_size =
-		tlbmiss_handler_setup_pgd_end - tlbmiss_handler_setup_pgd;
+		tlbmiss_handler_setup_pgd_end - tlbmiss_handler_setup_pgd_start;
 #ifndef CONFIG_MIPS_PGD_C0_CONTEXT
 	long pgdc = (long)pgd_current;
 #endif
diff --git a/arch/mips/ralink/dts/mt7620a_eval.dts b/arch/mips/ralink/dts/mt7620a_eval.dts
index 35eb874ab7f1..709f58132f5c 100644
--- a/arch/mips/ralink/dts/mt7620a_eval.dts
+++ b/arch/mips/ralink/dts/mt7620a_eval.dts
@@ -7,6 +7,7 @@
 	model = "Ralink MT7620A evaluation board";
 
 	memory@0 {
+		device_type = "memory";
 		reg = <0x0 0x2000000>;
 	};
 
diff --git a/arch/mips/ralink/dts/rt2880_eval.dts b/arch/mips/ralink/dts/rt2880_eval.dts
index 322d7002595b..0a685db093d4 100644
--- a/arch/mips/ralink/dts/rt2880_eval.dts
+++ b/arch/mips/ralink/dts/rt2880_eval.dts
@@ -7,6 +7,7 @@
 	model = "Ralink RT2880 evaluation board";
 
 	memory@0 {
+		device_type = "memory";
 		reg = <0x8000000 0x2000000>;
 	};
 
diff --git a/arch/mips/ralink/dts/rt3052_eval.dts b/arch/mips/ralink/dts/rt3052_eval.dts
index 0ac73ea28198..ec9e9a035541 100644
--- a/arch/mips/ralink/dts/rt3052_eval.dts
+++ b/arch/mips/ralink/dts/rt3052_eval.dts
@@ -7,6 +7,7 @@
 	model = "Ralink RT3052 evaluation board";
 
 	memory@0 {
+		device_type = "memory";
 		reg = <0x0 0x2000000>;
 	};
 
diff --git a/arch/mips/ralink/dts/rt3883_eval.dts b/arch/mips/ralink/dts/rt3883_eval.dts
index 2fa6b330bf4f..e8df21a5d10d 100644
--- a/arch/mips/ralink/dts/rt3883_eval.dts
+++ b/arch/mips/ralink/dts/rt3883_eval.dts
@@ -7,6 +7,7 @@
 	model = "Ralink RT3883 evaluation board";
 
 	memory@0 {
+		device_type = "memory";
 		reg = <0x0 0x2000000>;
 	};
 
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index 1faefed32749..108d48e652af 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -22,6 +22,7 @@ config PARISC
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_STRNCPY_FROM_USER
 	select SYSCTL_ARCH_UNALIGN_ALLOW
+	select SYSCTL_EXCEPTION_TRACE
 	select HAVE_MOD_ARCH_SPECIFIC
 	select VIRT_TO_BUS
 	select MODULES_USE_ELF_RELA
diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h
index 198a86feb574..d951c9681ab3 100644
--- a/arch/parisc/include/asm/processor.h
+++ b/arch/parisc/include/asm/processor.h
@@ -55,6 +55,11 @@
 #define STACK_TOP	TASK_SIZE
 #define STACK_TOP_MAX	DEFAULT_TASK_SIZE
 
+/* Allow bigger stacks for 64-bit processes */
+#define STACK_SIZE_MAX	(USER_WIDE_MODE					\
+			 ? (1 << 30)	/* 1 GB */			\
+			 : (CONFIG_MAX_STACK_SIZE_MB*1024*1024))
+
 #endif
 
 #ifndef __ASSEMBLY__
diff --git a/arch/parisc/include/uapi/asm/unistd.h b/arch/parisc/include/uapi/asm/unistd.h
index 265ae5190b0a..47e0e21d2272 100644
--- a/arch/parisc/include/uapi/asm/unistd.h
+++ b/arch/parisc/include/uapi/asm/unistd.h
@@ -829,8 +829,9 @@
 #define __NR_sched_setattr	(__NR_Linux + 334)
 #define __NR_sched_getattr	(__NR_Linux + 335)
 #define __NR_utimes		(__NR_Linux + 336)
+#define __NR_renameat2		(__NR_Linux + 337)
 
-#define __NR_Linux_syscalls	(__NR_utimes + 1)
+#define __NR_Linux_syscalls	(__NR_renameat2 + 1)
 
 
 #define __IGNORE_select		/* newselect */
diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c
index 31ffa9b55322..e1ffea2f9a0b 100644
--- a/arch/parisc/kernel/sys_parisc.c
+++ b/arch/parisc/kernel/sys_parisc.c
@@ -72,10 +72,10 @@ static unsigned long mmap_upper_limit(void)
 {
 	unsigned long stack_base;
 
-	/* Limit stack size to 1GB - see setup_arg_pages() in fs/exec.c */
+	/* Limit stack size - see setup_arg_pages() in fs/exec.c */
 	stack_base = rlimit_max(RLIMIT_STACK);
-	if (stack_base > (1 << 30))
-		stack_base = 1 << 30;
+	if (stack_base > STACK_SIZE_MAX)
+		stack_base = STACK_SIZE_MAX;
 
 	return PAGE_ALIGN(STACK_TOP - stack_base);
 }
diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S
index a63bb179f79a..838786011037 100644
--- a/arch/parisc/kernel/syscall.S
+++ b/arch/parisc/kernel/syscall.S
@@ -589,10 +589,13 @@ cas_nocontend:
 # endif
 /* ENABLE_LWS_DEBUG */
 
+	rsm	PSW_SM_I, %r0				/* Disable interrupts */
+	/* COW breaks can cause contention on UP systems */
 	LDCW	0(%sr2,%r20), %r28			/* Try to acquire the lock */
 	cmpb,<>,n	%r0, %r28, cas_action		/* Did we get it? */
 cas_wouldblock:
 	ldo	2(%r0), %r28				/* 2nd case */
+	ssm	PSW_SM_I, %r0
 	b	lws_exit				/* Contended... */
 	ldo	-EAGAIN(%r0), %r21			/* Spin in userspace */
 
@@ -619,15 +622,17 @@ cas_action:
 	stw	%r1, 4(%sr2,%r20)
 #endif
 	/* The load and store could fail */
-1:	ldw	0(%sr3,%r26), %r28
+1:	ldw,ma	0(%sr3,%r26), %r28
 	sub,<>	%r28, %r25, %r0
-2:	stw	%r24, 0(%sr3,%r26)
+2:	stw,ma	%r24, 0(%sr3,%r26)
 	/* Free lock */
-	stw	%r20, 0(%sr2,%r20)
+	stw,ma	%r20, 0(%sr2,%r20)
 #if ENABLE_LWS_DEBUG
 	/* Clear thread register indicator */
 	stw	%r0, 4(%sr2,%r20)
 #endif
+	/* Enable interrupts */
+	ssm	PSW_SM_I, %r0
 	/* Return to userspace, set no error */
 	b	lws_exit
 	copy	%r0, %r21
@@ -639,6 +644,7 @@ cas_action:
 #if ENABLE_LWS_DEBUG
 	stw	%r0, 4(%sr2,%r20)
 #endif
+	ssm	PSW_SM_I, %r0
 	b	lws_exit
 	ldo	-EFAULT(%r0),%r21	/* set errno */
 	nop
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index 83ead0ea127d..c5fa7a697fba 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -432,6 +432,7 @@
 	ENTRY_SAME(sched_setattr)
 	ENTRY_SAME(sched_getattr)	/* 335 */
 	ENTRY_COMP(utimes)
+	ENTRY_SAME(renameat2)
 
 	/* Nothing yet */
 
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index 1cd1d0c83b6d..47ee620d15d2 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -25,6 +25,7 @@
 #include <linux/interrupt.h>
 #include <linux/console.h>
 #include <linux/bug.h>
+#include <linux/ratelimit.h>
 
 #include <asm/assembly.h>
 #include <asm/uaccess.h>
@@ -42,9 +43,6 @@
 
 #include "../math-emu/math-emu.h"	/* for handle_fpe() */
 
-#define PRINT_USER_FAULTS /* (turn this on if you want user faults to be */
-			  /*  dumped to the console via printk)          */
-
 #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
 DEFINE_SPINLOCK(pa_dbit_lock);
 #endif
@@ -160,6 +158,17 @@ void show_regs(struct pt_regs *regs)
 	}
 }
 
+static DEFINE_RATELIMIT_STATE(_hppa_rs,
+	DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST);
+
+#define parisc_printk_ratelimited(critical, regs, fmt, ...)	{	      \
+	if ((critical || show_unhandled_signals) && __ratelimit(&_hppa_rs)) { \
+		printk(fmt, ##__VA_ARGS__);				      \
+		show_regs(regs);					      \
+	}								      \
+}
+
+
 static void do_show_stack(struct unwind_frame_info *info)
 {
 	int i = 1;
@@ -229,12 +238,10 @@ void die_if_kernel(char *str, struct pt_regs *regs, long err)
 		if (err == 0)
 			return; /* STFU */
 
-		printk(KERN_CRIT "%s (pid %d): %s (code %ld) at " RFMT "\n",
+		parisc_printk_ratelimited(1, regs,
+			KERN_CRIT "%s (pid %d): %s (code %ld) at " RFMT "\n",
 			current->comm, task_pid_nr(current), str, err, regs->iaoq[0]);
-#ifdef PRINT_USER_FAULTS
-		/* XXX for debugging only */
-		show_regs(regs);
-#endif
+
 		return;
 	}
 
@@ -321,14 +328,11 @@ static void handle_break(struct pt_regs *regs)
 			(tt == BUG_TRAP_TYPE_NONE) ? 9 : 0);
 	}
 
-#ifdef PRINT_USER_FAULTS
-	if (unlikely(iir != GDB_BREAK_INSN)) {
-		printk(KERN_DEBUG "break %d,%d: pid=%d command='%s'\n",
+	if (unlikely(iir != GDB_BREAK_INSN))
+		parisc_printk_ratelimited(0, regs,
+			KERN_DEBUG "break %d,%d: pid=%d command='%s'\n",
 			iir & 31, (iir>>13) & ((1<<13)-1),
 			task_pid_nr(current), current->comm);
-		show_regs(regs);
-	}
-#endif
 
 	/* send standard GDB signal */
 	handle_gdb_break(regs, TRAP_BRKPT);
@@ -758,11 +762,9 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
 
 	default:
 		if (user_mode(regs)) {
-#ifdef PRINT_USER_FAULTS
-			printk(KERN_DEBUG "\nhandle_interruption() pid=%d command='%s'\n",
-			    task_pid_nr(current), current->comm);
-			show_regs(regs);
-#endif
+			parisc_printk_ratelimited(0, regs, KERN_DEBUG
+				"handle_interruption() pid=%d command='%s'\n",
+				task_pid_nr(current), current->comm);
 			/* SIGBUS, for lack of a better one. */
 			si.si_signo = SIGBUS;
 			si.si_code = BUS_OBJERR;
@@ -779,16 +781,10 @@ void notrace handle_interruption(int code, struct pt_regs *regs)
 
 	if (user_mode(regs)) {
 	    if ((fault_space >> SPACEID_SHIFT) != (regs->sr[7] >> SPACEID_SHIFT)) {
-#ifdef PRINT_USER_FAULTS
-		if (fault_space == 0)
-			printk(KERN_DEBUG "User Fault on Kernel Space ");
-		else
-			printk(KERN_DEBUG "User Fault (long pointer) (fault %d) ",
-			       code);
-		printk(KERN_CONT "pid=%d command='%s'\n",
-		       task_pid_nr(current), current->comm);
-		show_regs(regs);
-#endif
+		parisc_printk_ratelimited(0, regs, KERN_DEBUG
+				"User fault %d on space 0x%08lx, pid=%d command='%s'\n",
+				code, fault_space,
+				task_pid_nr(current), current->comm);
 		si.si_signo = SIGSEGV;
 		si.si_errno = 0;
 		si.si_code = SEGV_MAPERR;
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index 747550762f3c..3ca9c1131cfe 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -19,10 +19,6 @@
 #include <asm/uaccess.h>
 #include <asm/traps.h>
 
-#define PRINT_USER_FAULTS /* (turn this on if you want user faults to be */
-			 /*  dumped to the console via printk)          */
-
-
 /* Various important other fields */
 #define bit22set(x)		(x & 0x00000200)
 #define bits23_25set(x)		(x & 0x000001c0)
@@ -34,6 +30,8 @@
 
 DEFINE_PER_CPU(struct exception_data, exception_data);
 
+int show_unhandled_signals = 1;
+
 /*
  * parisc_acctyp(unsigned int inst) --
  *    Given a PA-RISC memory access instruction, determine if the
@@ -173,6 +171,32 @@ int fixup_exception(struct pt_regs *regs)
 	return 0;
 }
 
+/*
+ * Print out info about fatal segfaults, if the show_unhandled_signals
+ * sysctl is set:
+ */
+static inline void
+show_signal_msg(struct pt_regs *regs, unsigned long code,
+		unsigned long address, struct task_struct *tsk,
+		struct vm_area_struct *vma)
+{
+	if (!unhandled_signal(tsk, SIGSEGV))
+		return;
+
+	if (!printk_ratelimit())
+		return;
+
+	pr_warn("\n");
+	pr_warn("do_page_fault() command='%s' type=%lu address=0x%08lx",
+	    tsk->comm, code, address);
+	print_vma_addr(KERN_CONT " in ", regs->iaoq[0]);
+	if (vma)
+		pr_warn(" vm_start = 0x%08lx, vm_end = 0x%08lx\n",
+				vma->vm_start, vma->vm_end);
+
+	show_regs(regs);
+}
+
 void do_page_fault(struct pt_regs *regs, unsigned long code,
 			      unsigned long address)
 {
@@ -270,16 +294,8 @@ bad_area:
 	if (user_mode(regs)) {
 		struct siginfo si;
 
-#ifdef PRINT_USER_FAULTS
-		printk(KERN_DEBUG "\n");
-		printk(KERN_DEBUG "do_page_fault() pid=%d command='%s' type=%lu address=0x%08lx\n",
-		    task_pid_nr(tsk), tsk->comm, code, address);
-		if (vma) {
-			printk(KERN_DEBUG "vm_start = 0x%08lx, vm_end = 0x%08lx\n",
-					vma->vm_start, vma->vm_end);
-		}
-		show_regs(regs);
-#endif
+		show_signal_msg(regs, code, address, tsk, vma);
+
 		switch (code) {
 		case 15:	/* Data TLB miss fault/Data page fault */
 			/* send SIGSEGV when outside of vma */
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 4c0cedf4e2c7..ce4c68a4a823 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -150,7 +150,9 @@ endif
 
 CFLAGS-$(CONFIG_TUNE_CELL) += $(call cc-option,-mtune=cell)
 
-KBUILD_CPPFLAGS	+= -Iarch/$(ARCH)
+asinstr := $(call as-instr,lis 9$(comma)foo@high,-DHAVE_AS_ATHIGH=1)
+
+KBUILD_CPPFLAGS	+= -Iarch/$(ARCH) $(asinstr)
 KBUILD_AFLAGS	+= -Iarch/$(ARCH)
 KBUILD_CFLAGS	+= -msoft-float -pipe -Iarch/$(ARCH) $(CFLAGS-y)
 CPP		= $(CC) -E $(KBUILD_CFLAGS)
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 6586a40a46ce..cded7c1278ef 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -318,11 +318,16 @@ n:
 	addi	reg,reg,(name - 0b)@l;
 
 #ifdef __powerpc64__
+#ifdef HAVE_AS_ATHIGH
+#define __AS_ATHIGH high
+#else
+#define __AS_ATHIGH h
+#endif
 #define LOAD_REG_IMMEDIATE(reg,expr)		\
 	lis     reg,(expr)@highest;		\
 	ori     reg,reg,(expr)@higher;	\
 	rldicr  reg,reg,32,31;		\
-	oris    reg,reg,(expr)@h;		\
+	oris    reg,reg,(expr)@__AS_ATHIGH;	\
 	ori     reg,reg,(expr)@l;
 
 #define LOAD_REG_ADDR(reg,name)			\
diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h
index d0e784e0ff48..521790330672 100644
--- a/arch/powerpc/include/asm/sections.h
+++ b/arch/powerpc/include/asm/sections.h
@@ -39,6 +39,17 @@ static inline int overlaps_kernel_text(unsigned long start, unsigned long end)
 		(unsigned long)_stext < end;
 }
 
+static inline int overlaps_kvm_tmp(unsigned long start, unsigned long end)
+{
+#ifdef CONFIG_KVM_GUEST
+	extern char kvm_tmp[];
+	return start < (unsigned long)kvm_tmp &&
+		(unsigned long)&kvm_tmp[1024 * 1024] < end;
+#else
+	return 0;
+#endif
+}
+
 #undef dereference_function_descriptor
 static inline void *dereference_function_descriptor(void *ptr)
 {
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 6a0175297b0d..dd8695f6cb6d 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -74,7 +74,7 @@
 #define KVM_INST_MTSRIN		0x7c0001e4
 
 static bool kvm_patching_worked = true;
-static char kvm_tmp[1024 * 1024];
+char kvm_tmp[1024 * 1024];
 static int kvm_tmp_index;
 
 static inline void kvm_patch_ins(u32 *inst, u32 new_inst)
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index 59d229a2a3e0..879b3aacac32 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -237,7 +237,7 @@ static void wake_offline_cpus(void)
 		if (!cpu_online(cpu)) {
 			printk(KERN_INFO "kexec: Waking offline cpu %d.\n",
 			       cpu);
-			cpu_up(cpu);
+			WARN_ON(cpu_up(cpu));
 		}
 	}
 }
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 122a580f7322..7e711bdcc6da 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -813,9 +813,6 @@ static void __init clocksource_init(void)
 static int decrementer_set_next_event(unsigned long evt,
 				      struct clock_event_device *dev)
 {
-	/* Don't adjust the decrementer if some irq work is pending */
-	if (test_irq_work_pending())
-		return 0;
 	__get_cpu_var(decrementers_next_tb) = get_tb_or_rtc() + evt;
 	set_dec(evt);
 
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 94e597e6f15c..7af190a266b3 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -886,7 +886,7 @@ static int kvmppc_book3s_init(void)
 	r = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
 	if (r)
 		return r;
-#ifdef CONFIG_KVM_BOOK3S_32
+#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 	r = kvmppc_book3s_init_pr();
 #endif
 	return r;
@@ -895,7 +895,7 @@ static int kvmppc_book3s_init(void)
 
 static void kvmppc_book3s_exit(void)
 {
-#ifdef CONFIG_KVM_BOOK3S_32
+#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 	kvmppc_book3s_exit_pr();
 #endif
 	kvm_exit();
@@ -905,7 +905,7 @@ module_init(kvmppc_book3s_init);
 module_exit(kvmppc_book3s_exit);
 
 /* On 32bit this is our one and only kernel module */
-#ifdef CONFIG_KVM_BOOK3S_32
+#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 MODULE_ALIAS_MISCDEV(KVM_MINOR);
 MODULE_ALIAS("devname:kvm");
 #endif
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 1d6c56ad5b60..8fcc36306a02 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -234,7 +234,7 @@ long kvmppc_do_h_enter(struct kvm *kvm, unsigned long flags,
 		pte_size = psize;
 		pte = lookup_linux_pte_and_update(pgdir, hva, writing,
 						  &pte_size);
-		if (pte_present(pte)) {
+		if (pte_present(pte) && !pte_numa(pte)) {
 			if (writing && !pte_write(pte))
 				/* make the actual HPTE be read-only */
 				ptel = hpte_make_readonly(ptel);
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index b031f932c0cc..07c8b5b0f9d2 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1323,6 +1323,110 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
 	mr	r3, r9
 	bl	kvmppc_save_fp
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+BEGIN_FTR_SECTION
+	b	2f
+END_FTR_SECTION_IFCLR(CPU_FTR_TM)
+	/* Turn on TM. */
+	mfmsr	r8
+	li	r0, 1
+	rldimi	r8, r0, MSR_TM_LG, 63-MSR_TM_LG
+	mtmsrd	r8
+
+	ld	r5, VCPU_MSR(r9)
+	rldicl. r5, r5, 64 - MSR_TS_S_LG, 62
+	beq	1f	/* TM not active in guest. */
+
+	li	r3, TM_CAUSE_KVM_RESCHED
+
+	/* Clear the MSR RI since r1, r13 are all going to be foobar. */
+	li	r5, 0
+	mtmsrd	r5, 1
+
+	/* All GPRs are volatile at this point. */
+	TRECLAIM(R3)
+
+	/* Temporarily store r13 and r9 so we have some regs to play with */
+	SET_SCRATCH0(r13)
+	GET_PACA(r13)
+	std	r9, PACATMSCRATCH(r13)
+	ld	r9, HSTATE_KVM_VCPU(r13)
+
+	/* Get a few more GPRs free. */
+	std	r29, VCPU_GPRS_TM(29)(r9)
+	std	r30, VCPU_GPRS_TM(30)(r9)
+	std	r31, VCPU_GPRS_TM(31)(r9)
+
+	/* Save away PPR and DSCR soon so don't run with user values. */
+	mfspr	r31, SPRN_PPR
+	HMT_MEDIUM
+	mfspr	r30, SPRN_DSCR
+	ld	r29, HSTATE_DSCR(r13)
+	mtspr	SPRN_DSCR, r29
+
+	/* Save all but r9, r13 & r29-r31 */
+	reg = 0
+	.rept	29
+	.if (reg != 9) && (reg != 13)
+	std	reg, VCPU_GPRS_TM(reg)(r9)
+	.endif
+	reg = reg + 1
+	.endr
+	/* ... now save r13 */
+	GET_SCRATCH0(r4)
+	std	r4, VCPU_GPRS_TM(13)(r9)
+	/* ... and save r9 */
+	ld	r4, PACATMSCRATCH(r13)
+	std	r4, VCPU_GPRS_TM(9)(r9)
+
+	/* Reload stack pointer and TOC. */
+	ld	r1, HSTATE_HOST_R1(r13)
+	ld	r2, PACATOC(r13)
+
+	/* Set MSR RI now we have r1 and r13 back. */
+	li	r5, MSR_RI
+	mtmsrd	r5, 1
+
+	/* Save away checkpinted SPRs. */
+	std	r31, VCPU_PPR_TM(r9)
+	std	r30, VCPU_DSCR_TM(r9)
+	mflr	r5
+	mfcr	r6
+	mfctr	r7
+	mfspr	r8, SPRN_AMR
+	mfspr	r10, SPRN_TAR
+	std	r5, VCPU_LR_TM(r9)
+	stw	r6, VCPU_CR_TM(r9)
+	std	r7, VCPU_CTR_TM(r9)
+	std	r8, VCPU_AMR_TM(r9)
+	std	r10, VCPU_TAR_TM(r9)
+
+	/* Restore r12 as trap number. */
+	lwz	r12, VCPU_TRAP(r9)
+
+	/* Save FP/VSX. */
+	addi	r3, r9, VCPU_FPRS_TM
+	bl	.store_fp_state
+	addi	r3, r9, VCPU_VRS_TM
+	bl	.store_vr_state
+	mfspr	r6, SPRN_VRSAVE
+	stw	r6, VCPU_VRSAVE_TM(r9)
+1:
+	/*
+	 * We need to save these SPRs after the treclaim so that the software
+	 * error code is recorded correctly in the TEXASR.  Also the user may
+	 * change these outside of a transaction, so they must always be
+	 * context switched.
+	 */
+	mfspr	r5, SPRN_TFHAR
+	mfspr	r6, SPRN_TFIAR
+	mfspr	r7, SPRN_TEXASR
+	std	r5, VCPU_TFHAR(r9)
+	std	r6, VCPU_TFIAR(r9)
+	std	r7, VCPU_TEXASR(r9)
+2:
+#endif
+
 	/* Increment yield count if they have a VPA */
 	ld	r8, VCPU_VPA(r9)	/* do they have a VPA? */
 	cmpdi	r8, 0
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index c5c052a9729c..02f1defd8bb9 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -1153,7 +1153,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_pr(struct kvm *kvm,
 		goto free_vcpu;
 	vcpu->arch.book3s = vcpu_book3s;
 
-#ifdef CONFIG_KVM_BOOK3S_32
+#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 	vcpu->arch.shadow_vcpu =
 		kzalloc(sizeof(*vcpu->arch.shadow_vcpu), GFP_KERNEL);
 	if (!vcpu->arch.shadow_vcpu)
@@ -1198,7 +1198,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_pr(struct kvm *kvm,
 uninit_vcpu:
 	kvm_vcpu_uninit(vcpu);
 free_shadow_vcpu:
-#ifdef CONFIG_KVM_BOOK3S_32
+#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 	kfree(vcpu->arch.shadow_vcpu);
 free_vcpu3s:
 #endif
@@ -1215,7 +1215,7 @@ static void kvmppc_core_vcpu_free_pr(struct kvm_vcpu *vcpu)
 
 	free_page((unsigned long)vcpu->arch.shared & PAGE_MASK);
 	kvm_vcpu_uninit(vcpu);
-#ifdef CONFIG_KVM_BOOK3S_32
+#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 	kfree(vcpu->arch.shadow_vcpu);
 #endif
 	vfree(vcpu_book3s);
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index d766d6ee33fe..06ba83b036d3 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -207,6 +207,10 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
 		if (overlaps_kernel_text(vaddr, vaddr + step))
 			tprot &= ~HPTE_R_N;
 
+		/* Make kvm guest trampolines executable */
+		if (overlaps_kvm_tmp(vaddr, vaddr + step))
+			tprot &= ~HPTE_R_N;
+
 		/*
 		 * If relocatable, check if it overlaps interrupt vectors that
 		 * are copied down to real 0. For relocatable kernel
diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index 253fefe3d1a0..5b51079f3e3b 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -549,7 +549,8 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option)
 		ret = ioda_eeh_phb_reset(hose, option);
 	} else {
 		bus = eeh_pe_bus_get(pe);
-		if (pci_is_root_bus(bus))
+		if (pci_is_root_bus(bus) ||
+		    pci_is_root_bus(bus->parent))
 			ret = ioda_eeh_root_reset(hose, option);
 		else
 			ret = ioda_eeh_bridge_reset(hose, bus->self, option);
diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c
index cf3c0089bef2..23223cd63e54 100644
--- a/arch/s390/crypto/aes_s390.c
+++ b/arch/s390/crypto/aes_s390.c
@@ -820,6 +820,9 @@ static int ctr_aes_crypt(struct blkcipher_desc *desc, long func,
 		else
 			memcpy(walk->iv, ctrptr, AES_BLOCK_SIZE);
 		spin_unlock(&ctrblk_lock);
+	} else {
+		if (!nbytes)
+			memcpy(walk->iv, ctrptr, AES_BLOCK_SIZE);
 	}
 	/*
 	 * final block may be < AES_BLOCK_SIZE, copy only nbytes
diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c
index 0a5aac8a9412..7acb77f7ef1a 100644
--- a/arch/s390/crypto/des_s390.c
+++ b/arch/s390/crypto/des_s390.c
@@ -429,6 +429,9 @@ static int ctr_desall_crypt(struct blkcipher_desc *desc, long func,
 		else
 			memcpy(walk->iv, ctrptr, DES_BLOCK_SIZE);
 		spin_unlock(&ctrblk_lock);
+	} else {
+		if (!nbytes)
+			memcpy(walk->iv, ctrptr, DES_BLOCK_SIZE);
 	}
 	/* final block may be < DES_BLOCK_SIZE, copy only nbytes */
 	if (nbytes) {
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index b3ecb8f5b6ce..9ae6664ff08c 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -158,6 +158,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_ONE_REG:
 	case KVM_CAP_ENABLE_CAP:
 	case KVM_CAP_S390_CSS_SUPPORT:
+	case KVM_CAP_IRQFD:
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_DEVICE_CTRL:
 	case KVM_CAP_ENABLE_CAP_VM:
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 452d3ebd9d0f..e9f8fa9337fe 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -811,7 +811,7 @@ static struct bpf_binary_header *bpf_alloc_binary(unsigned int bpfsize,
 		return NULL;
 	memset(header, 0, sz);
 	header->pages = sz / PAGE_SIZE;
-	hole = sz - (bpfsize + sizeof(*header));
+	hole = min(sz - (bpfsize + sizeof(*header)), PAGE_SIZE - sizeof(*header));
 	/* Insert random number of illegal instructions before BPF code
 	 * and make sure the first instruction starts at an even address.
 	 */
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index fde5abaac0cc..1a49ffdf9da9 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -24,7 +24,8 @@
 
 /* The kernel image occupies 0x4000000 to 0x6000000 (4MB --> 96MB).
  * The page copy blockops can use 0x6000000 to 0x8000000.
- * The TSB is mapped in the 0x8000000 to 0xa000000 range.
+ * The 8K TSB is mapped in the 0x8000000 to 0x8400000 range.
+ * The 4M TSB is mapped in the 0x8400000 to 0x8800000 range.
  * The PROM resides in an area spanning 0xf0000000 to 0x100000000.
  * The vmalloc area spans 0x100000000 to 0x200000000.
  * Since modules need to be in the lowest 32-bits of the address space,
@@ -33,7 +34,8 @@
  * 0x400000000.
  */
 #define	TLBTEMP_BASE		_AC(0x0000000006000000,UL)
-#define	TSBMAP_BASE		_AC(0x0000000008000000,UL)
+#define	TSBMAP_8K_BASE		_AC(0x0000000008000000,UL)
+#define	TSBMAP_4M_BASE		_AC(0x0000000008400000,UL)
 #define MODULES_VADDR		_AC(0x0000000010000000,UL)
 #define MODULES_LEN		_AC(0x00000000e0000000,UL)
 #define MODULES_END		_AC(0x00000000f0000000,UL)
diff --git a/arch/sparc/kernel/sysfs.c b/arch/sparc/kernel/sysfs.c
index a364000ca1aa..7f41d40b7e6e 100644
--- a/arch/sparc/kernel/sysfs.c
+++ b/arch/sparc/kernel/sysfs.c
@@ -151,7 +151,7 @@ static ssize_t store_mmustat_enable(struct device *s,
 			size_t count)
 {
 	unsigned long val, err;
-	int ret = sscanf(buf, "%ld", &val);
+	int ret = sscanf(buf, "%lu", &val);
 
 	if (ret != 1)
 		return -EINVAL;
diff --git a/arch/sparc/lib/NG2memcpy.S b/arch/sparc/lib/NG2memcpy.S
index 2c20ad63ddbf..30eee6e8a81b 100644
--- a/arch/sparc/lib/NG2memcpy.S
+++ b/arch/sparc/lib/NG2memcpy.S
@@ -236,6 +236,7 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	 */
 	VISEntryHalf
 
+	membar		#Sync
 	alignaddr	%o1, %g0, %g0
 
 	add		%o1, (64 - 1), %o4
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index a8ff0d1a3b69..4ced3fc66130 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -281,18 +281,6 @@ static void noinline __kprobes bogus_32bit_fault_tpc(struct pt_regs *regs)
 	show_regs(regs);
 }
 
-static void noinline __kprobes bogus_32bit_fault_address(struct pt_regs *regs,
-							 unsigned long addr)
-{
-	static int times;
-
-	if (times++ < 10)
-		printk(KERN_ERR "FAULT[%s:%d]: 32-bit process "
-		       "reports 64-bit fault address [%lx]\n",
-		       current->comm, current->pid, addr);
-	show_regs(regs);
-}
-
 asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
 {
 	enum ctx_state prev_state = exception_enter();
@@ -322,10 +310,8 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs)
 				goto intr_or_no_mm;
 			}
 		}
-		if (unlikely((address >> 32) != 0)) {
-			bogus_32bit_fault_address(regs, address);
+		if (unlikely((address >> 32) != 0))
 			goto intr_or_no_mm;
-		}
 	}
 
 	if (regs->tstate & TSTATE_PRIV) {
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index f5d506fdddad..fe19b81acc09 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -133,7 +133,19 @@ static void setup_tsb_params(struct mm_struct *mm, unsigned long tsb_idx, unsign
 	mm->context.tsb_block[tsb_idx].tsb_nentries =
 		tsb_bytes / sizeof(struct tsb);
 
-	base = TSBMAP_BASE;
+	switch (tsb_idx) {
+	case MM_TSB_BASE:
+		base = TSBMAP_8K_BASE;
+		break;
+#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
+	case MM_TSB_HUGE:
+		base = TSBMAP_4M_BASE;
+		break;
+#endif
+	default:
+		BUG();
+	}
+
 	tte = pgprot_val(PAGE_KERNEL_LOCKED);
 	tsb_paddr = __pa(mm->context.tsb_block[tsb_idx].tsb);
 	BUG_ON(tsb_paddr & (tsb_bytes - 1UL));
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index ce6ad7e6a7d7..33f71b01fd22 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -79,6 +79,7 @@ else
         UTS_MACHINE := x86_64
         CHECKFLAGS += -D__x86_64__ -m64
 
+        biarch := -m64
         KBUILD_AFLAGS += -m64
         KBUILD_CFLAGS += -m64
 
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index abb9eba61b50..dbe8dd2fe247 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -71,7 +71,7 @@ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE
 
 SETUP_OBJS = $(addprefix $(obj)/,$(setup-y))
 
-sed-voffset := -e 's/^\([0-9a-fA-F]*\) . \(_text\|_end\)$$/\#define VO_\2 0x\1/p'
+sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(_text\|_end\)$$/\#define VO_\2 0x\1/p'
 
 quiet_cmd_voffset = VOFFSET $@
       cmd_voffset = $(NM) $< | sed -n $(sed-voffset) > $@
@@ -80,7 +80,7 @@ targets += voffset.h
 $(obj)/voffset.h: vmlinux FORCE
 	$(call if_changed,voffset)
 
-sed-zoffset := -e 's/^\([0-9a-fA-F]*\) . \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|_end\|z_.*\)$$/\#define ZO_\2 0x\1/p'
+sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|_end\|z_.*\)$$/\#define ZO_\2 0x\1/p'
 
 quiet_cmd_zoffset = ZOFFSET $@
       cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 17684615374b..57ab74df7eea 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -354,7 +354,7 @@ static void parse_elf(void *output)
 	free(phdrs);
 }
 
-asmlinkage void *decompress_kernel(void *rmode, memptr heap,
+asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap,
 				  unsigned char *input_data,
 				  unsigned long input_len,
 				  unsigned char *output,
diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h
index b18df579c0e9..36f7125945e3 100644
--- a/arch/x86/include/asm/hpet.h
+++ b/arch/x86/include/asm/hpet.h
@@ -63,6 +63,7 @@
 /* hpet memory map physical address */
 extern unsigned long hpet_address;
 extern unsigned long force_hpet_address;
+extern int boot_hpet_disable;
 extern u8 hpet_blockid;
 extern int hpet_force_user;
 extern u8 hpet_msi_disable;
diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index a8091216963b..68c05398bba9 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -52,6 +52,7 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 					 unsigned long addr, pte_t *ptep)
 {
+	ptep_clear_flush(vma, addr, ptep);
 }
 
 static inline int huge_pte_none(pte_t pte)
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 8de6d9cf3b95..678205195ae1 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -1,7 +1,7 @@
 #ifndef _ASM_X86_PAGE_64_DEFS_H
 #define _ASM_X86_PAGE_64_DEFS_H
 
-#define THREAD_SIZE_ORDER	1
+#define THREAD_SIZE_ORDER	2
 #define THREAD_SIZE  (PAGE_SIZE << THREAD_SIZE_ORDER)
 #define CURRENT_MASK (~(THREAD_SIZE - 1))
 
diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h
index c827ace3121b..fcf2b3ae1bf0 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/uapi/asm/msr-index.h
@@ -384,7 +384,7 @@
 #define MSR_IA32_MISC_ENABLE_MWAIT_BIT			18
 #define MSR_IA32_MISC_ENABLE_MWAIT			(1ULL << MSR_IA32_MISC_ENABLE_MWAIT_BIT)
 #define MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT		22
-#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID		(1ULL << MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT);
+#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID		(1ULL << MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT)
 #define MSR_IA32_MISC_ENABLE_XTPR_DISABLE_BIT		23
 #define MSR_IA32_MISC_ENABLE_XTPR_DISABLE		(1ULL << MSR_IA32_MISC_ENABLE_XTPR_DISABLE_BIT)
 #define MSR_IA32_MISC_ENABLE_XD_DISABLE_BIT		34
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 3a2ae4c88948..31368207837c 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -31,7 +31,7 @@ static char temp_stack[4096];
  *
  * Wrapper around acpi_enter_sleep_state() to be called by assmebly.
  */
-acpi_status asmlinkage x86_acpi_enter_sleep_state(u8 state)
+acpi_status asmlinkage __visible x86_acpi_enter_sleep_state(u8 state)
 {
 	return acpi_enter_sleep_state(state);
 }
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index d23aa82e7a7b..992060e09897 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2189,7 +2189,7 @@ void send_cleanup_vector(struct irq_cfg *cfg)
 	cfg->move_in_progress = 0;
 }
 
-asmlinkage void smp_irq_move_cleanup_interrupt(void)
+asmlinkage __visible void smp_irq_move_cleanup_interrupt(void)
 {
 	unsigned vector, me;
 
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index d921b7ee6595..36a1bb6d1ee0 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -429,14 +429,14 @@ static inline void __smp_thermal_interrupt(void)
 	smp_thermal_vector();
 }
 
-asmlinkage void smp_thermal_interrupt(struct pt_regs *regs)
+asmlinkage __visible void smp_thermal_interrupt(struct pt_regs *regs)
 {
 	entering_irq();
 	__smp_thermal_interrupt();
 	exiting_ack_irq();
 }
 
-asmlinkage void smp_trace_thermal_interrupt(struct pt_regs *regs)
+asmlinkage __visible void smp_trace_thermal_interrupt(struct pt_regs *regs)
 {
 	entering_irq();
 	trace_thermal_apic_entry(THERMAL_APIC_VECTOR);
diff --git a/arch/x86/kernel/cpu/mcheck/threshold.c b/arch/x86/kernel/cpu/mcheck/threshold.c
index fe6b1c86645b..7245980186ee 100644
--- a/arch/x86/kernel/cpu/mcheck/threshold.c
+++ b/arch/x86/kernel/cpu/mcheck/threshold.c
@@ -24,14 +24,14 @@ static inline void __smp_threshold_interrupt(void)
 	mce_threshold_vector();
 }
 
-asmlinkage void smp_threshold_interrupt(void)
+asmlinkage __visible void smp_threshold_interrupt(void)
 {
 	entering_irq();
 	__smp_threshold_interrupt();
 	exiting_ack_irq();
 }
 
-asmlinkage void smp_trace_threshold_interrupt(void)
+asmlinkage __visible void smp_trace_threshold_interrupt(void)
 {
 	entering_irq();
 	trace_threshold_apic_entry(THRESHOLD_APIC_VECTOR);
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index aa333d966886..adb02aa62af5 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -169,7 +169,6 @@ static struct event_constraint intel_slm_event_constraints[] __read_mostly =
 {
 	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
 	FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
-	FIXED_EVENT_CONSTRAINT(0x013c, 2), /* CPU_CLK_UNHALTED.REF */
 	FIXED_EVENT_CONSTRAINT(0x0300, 2), /* pseudo CPU_CLK_UNHALTED.REF */
 	EVENT_CONSTRAINT_END
 };
diff --git a/arch/x86/kernel/cpu/rdrand.c b/arch/x86/kernel/cpu/rdrand.c
index 384df5105fbc..136ac74dee82 100644
--- a/arch/x86/kernel/cpu/rdrand.c
+++ b/arch/x86/kernel/cpu/rdrand.c
@@ -27,6 +27,7 @@
 static int __init x86_rdrand_setup(char *s)
 {
 	setup_clear_cpu_cap(X86_FEATURE_RDRAND);
+	setup_clear_cpu_cap(X86_FEATURE_RDSEED);
 	return 1;
 }
 __setup("nordrand", x86_rdrand_setup);
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 6e2537c32190..6cda0baeac9d 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -17,6 +17,7 @@
 #include <asm/dma.h>
 #include <asm/io_apic.h>
 #include <asm/apic.h>
+#include <asm/hpet.h>
 #include <asm/iommu.h>
 #include <asm/gart.h>
 #include <asm/irq_remapping.h>
@@ -530,6 +531,15 @@ static void __init intel_graphics_stolen(int num, int slot, int func)
 	}
 }
 
+static void __init force_disable_hpet(int num, int slot, int func)
+{
+#ifdef CONFIG_HPET_TIMER
+	boot_hpet_disable = 1;
+	pr_info("x86/hpet: Will disable the HPET for this platform because it's not reliable\n");
+#endif
+}
+
+
 #define QFLAG_APPLY_ONCE 	0x1
 #define QFLAG_APPLIED		0x2
 #define QFLAG_DONE		(QFLAG_APPLY_ONCE|QFLAG_APPLIED)
@@ -567,6 +577,12 @@ static struct chipset early_qrk[] __initdata = {
 	  PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check },
 	{ PCI_VENDOR_ID_INTEL, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA, PCI_ANY_ID,
 	  QFLAG_APPLY_ONCE, intel_graphics_stolen },
+	/*
+	 * HPET on current version of Baytrail platform has accuracy
+	 * problems, disable it for now:
+	 */
+	{ PCI_VENDOR_ID_INTEL, 0x0f00,
+		PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, force_disable_hpet},
 	{}
 };
 
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index c61a14a4a310..d6c1b9836995 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -29,7 +29,7 @@ static void __init i386_default_early_setup(void)
 	reserve_ebda_region();
 }
 
-asmlinkage void __init i386_start_kernel(void)
+asmlinkage __visible void __init i386_start_kernel(void)
 {
 	sanitize_boot_params(&boot_params);
 
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 85126ccbdf6b..068054f4bf20 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -137,7 +137,7 @@ static void __init copy_bootdata(char *real_mode_data)
 	}
 }
 
-asmlinkage void __init x86_64_start_kernel(char * real_mode_data)
+asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data)
 {
 	int i;
 
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 8d80ae011603..4177bfbc80b0 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -88,7 +88,7 @@ static inline void hpet_clear_mapping(void)
 /*
  * HPET command line enable / disable
  */
-static int boot_hpet_disable;
+int boot_hpet_disable;
 int hpet_force_user;
 static int hpet_verbose;
 
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index af1d14a9ebda..dcbbaa165bde 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -20,6 +20,8 @@
 #include <asm/mmu_context.h>
 #include <asm/syscalls.h>
 
+int sysctl_ldt16 = 0;
+
 #ifdef CONFIG_SMP
 static void flush_ldt(void *current_mm)
 {
@@ -234,7 +236,7 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 	 * IRET leaking the high bits of the kernel stack address.
 	 */
 #ifdef CONFIG_X86_64
-	if (!ldt_info.seg_32bit) {
+	if (!ldt_info.seg_32bit && !sysctl_ldt16) {
 		error = -EINVAL;
 		goto out_unlock;
 	}
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 9c0280f93d05..898d077617a9 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -52,7 +52,7 @@
 
 asmlinkage extern void ret_from_fork(void);
 
-asmlinkage DEFINE_PER_CPU(unsigned long, old_rsp);
+__visible DEFINE_PER_CPU(unsigned long, old_rsp);
 
 /* Prints also some state that isn't saved in the pt_regs */
 void __show_regs(struct pt_regs *regs, int all)
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 3399d3a99730..52b1157c53eb 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -191,6 +191,16 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 		},
 	},
 
+	/* Certec */
+	{       /* Handle problems with rebooting on Certec BPC600 */
+		.callback = set_pci_reboot,
+		.ident = "Certec BPC600",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Certec"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "BPC600"),
+		},
+	},
+
 	/* Dell */
 	{	/* Handle problems with rebooting on Dell DXP061 */
 		.callback = set_bios_reboot,
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 7c3a5a61f2e4..be8e1bde07aa 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -168,7 +168,7 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs)
  * this function calls the 'stop' function on all other CPUs in the system.
  */
 
-asmlinkage void smp_reboot_interrupt(void)
+asmlinkage __visible void smp_reboot_interrupt(void)
 {
 	ack_APIC_irq();
 	irq_enter();
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 57409f6b8c62..f73b5d435bdc 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -357,7 +357,7 @@ exit:
  * for scheduling or signal handling. The actual stack switch is done in
  * entry.S
  */
-asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs)
+asmlinkage __visible __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs)
 {
 	struct pt_regs *regs = eregs;
 	/* Did already sync */
@@ -601,11 +601,11 @@ do_spurious_interrupt_bug(struct pt_regs *regs, long error_code)
 #endif
 }
 
-asmlinkage void __attribute__((weak)) smp_thermal_interrupt(void)
+asmlinkage __visible void __attribute__((weak)) smp_thermal_interrupt(void)
 {
 }
 
-asmlinkage void __attribute__((weak)) smp_threshold_interrupt(void)
+asmlinkage __visible void __attribute__((weak)) smp_threshold_interrupt(void)
 {
 }
 
diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c
index 5edc34b5b951..b99b9ad8540c 100644
--- a/arch/x86/kernel/vsmp_64.c
+++ b/arch/x86/kernel/vsmp_64.c
@@ -36,7 +36,7 @@ static int irq_routing_comply = 1;
  * and vice versa.
  */
 
-asmlinkage unsigned long vsmp_save_fl(void)
+asmlinkage __visible unsigned long vsmp_save_fl(void)
 {
 	unsigned long flags = native_save_fl();
 
@@ -56,7 +56,7 @@ __visible void vsmp_restore_fl(unsigned long flags)
 }
 PV_CALLEE_SAVE_REGS_THUNK(vsmp_restore_fl);
 
-asmlinkage void vsmp_irq_disable(void)
+asmlinkage __visible void vsmp_irq_disable(void)
 {
 	unsigned long flags = native_save_fl();
 
@@ -64,7 +64,7 @@ asmlinkage void vsmp_irq_disable(void)
 }
 PV_CALLEE_SAVE_REGS_THUNK(vsmp_irq_disable);
 
-asmlinkage void vsmp_irq_enable(void)
+asmlinkage __visible void vsmp_irq_enable(void)
 {
 	unsigned long flags = native_save_fl();
 
diff --git a/arch/x86/kernel/vsyscall_gtod.c b/arch/x86/kernel/vsyscall_gtod.c
index f9c6e56e14b5..9531fbb123ba 100644
--- a/arch/x86/kernel/vsyscall_gtod.c
+++ b/arch/x86/kernel/vsyscall_gtod.c
@@ -43,7 +43,7 @@ void update_vsyscall(struct timekeeper *tk)
 	vdata->monotonic_time_sec	= tk->xtime_sec
 					+ tk->wall_to_monotonic.tv_sec;
 	vdata->monotonic_time_snsec	= tk->xtime_nsec
-					+ (tk->wall_to_monotonic.tv_nsec
+					+ ((u64)tk->wall_to_monotonic.tv_nsec
 						<< tk->shift);
 	while (vdata->monotonic_time_snsec >=
 					(((u64)NSEC_PER_SEC) << tk->shift)) {
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 33e8c028842f..138ceffc6377 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -7778,7 +7778,8 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 
 	exec_control = vmcs12->pin_based_vm_exec_control;
 	exec_control |= vmcs_config.pin_based_exec_ctrl;
-	exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
+	exec_control &= ~(PIN_BASED_VMX_PREEMPTION_TIMER |
+                          PIN_BASED_POSTED_INTR);
 	vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, exec_control);
 
 	vmx->nested.preemption_timer_expired = false;
@@ -7815,7 +7816,9 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 		if (!vmx->rdtscp_enabled)
 			exec_control &= ~SECONDARY_EXEC_RDTSCP;
 		/* Take the following fields only from vmcs12 */
-		exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+		exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
+				  SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
+                                  SECONDARY_EXEC_APIC_REGISTER_VIRT);
 		if (nested_cpu_has(vmcs12,
 				CPU_BASED_ACTIVATE_SECONDARY_CONTROLS))
 			exec_control |= vmcs12->secondary_vm_exec_control;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 8b8fc0b792ba..20316c67b824 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -106,6 +106,8 @@ EXPORT_SYMBOL_GPL(kvm_max_guest_tsc_khz);
 static u32 tsc_tolerance_ppm = 250;
 module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);
 
+static bool backwards_tsc_observed = false;
+
 #define KVM_NR_SHARED_MSRS 16
 
 struct kvm_shared_msrs_global {
@@ -280,7 +282,7 @@ int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 }
 EXPORT_SYMBOL_GPL(kvm_set_apic_base);
 
-asmlinkage void kvm_spurious_fault(void)
+asmlinkage __visible void kvm_spurious_fault(void)
 {
 	/* Fault while not rebooting.  We want the trace. */
 	BUG();
@@ -1486,7 +1488,8 @@ static void pvclock_update_vm_gtod_copy(struct kvm *kvm)
 					&ka->master_kernel_ns,
 					&ka->master_cycle_now);
 
-	ka->use_master_clock = host_tsc_clocksource & vcpus_matched;
+	ka->use_master_clock = host_tsc_clocksource && vcpus_matched
+				&& !backwards_tsc_observed;
 
 	if (ka->use_master_clock)
 		atomic_set(&kvm_guest_has_master_clock, 1);
@@ -6945,6 +6948,7 @@ int kvm_arch_hardware_enable(void *garbage)
 	 */
 	if (backwards_tsc) {
 		u64 delta_cyc = max_tsc - local_tsc;
+		backwards_tsc_observed = true;
 		list_for_each_entry(kvm, &vm_list, vm_list) {
 			kvm_for_each_vcpu(i, vcpu, kvm) {
 				vcpu->arch.tsc_offset_adjustment += delta_cyc;
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index ad1fb5f53925..aae94132bc24 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -233,13 +233,13 @@ static void lguest_end_context_switch(struct task_struct *next)
  * flags word contains all kind of stuff, but in practice Linux only cares
  * about the interrupt flag.  Our "save_flags()" just returns that.
  */
-asmlinkage unsigned long lguest_save_fl(void)
+asmlinkage __visible unsigned long lguest_save_fl(void)
 {
 	return lguest_data.irq_enabled;
 }
 
 /* Interrupts go off... */
-asmlinkage void lguest_irq_disable(void)
+asmlinkage __visible void lguest_irq_disable(void)
 {
 	lguest_data.irq_enabled = 0;
 }
diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c
index db9db446b71a..43623739c7cf 100644
--- a/arch/x86/lib/msr.c
+++ b/arch/x86/lib/msr.c
@@ -76,7 +76,7 @@ static inline int __flip_bit(u32 msr, u8 bit, bool set)
 	if (m1.q == m.q)
 		return 0;
 
-	err = msr_write(msr, &m);
+	err = msr_write(msr, &m1);
 	if (err)
 		return err;
 
diff --git a/arch/x86/math-emu/errors.c b/arch/x86/math-emu/errors.c
index a5449089cd9f..9e6545f269e5 100644
--- a/arch/x86/math-emu/errors.c
+++ b/arch/x86/math-emu/errors.c
@@ -302,7 +302,7 @@ static struct {
 	      0x242  in div_Xsig.S
  */
 
-asmlinkage void FPU_exception(int n)
+asmlinkage __visible void FPU_exception(int n)
 {
 	int i, int_type;
 
@@ -492,7 +492,7 @@ int real_2op_NaN(FPU_REG const *b, u_char tagb,
 
 /* Invalid arith operation on Valid registers */
 /* Returns < 0 if the exception is unmasked */
-asmlinkage int arith_invalid(int deststnr)
+asmlinkage __visible int arith_invalid(int deststnr)
 {
 
 	EXCEPTION(EX_Invalid);
@@ -507,7 +507,7 @@ asmlinkage int arith_invalid(int deststnr)
 }
 
 /* Divide a finite number by zero */
-asmlinkage int FPU_divide_by_zero(int deststnr, u_char sign)
+asmlinkage __visible int FPU_divide_by_zero(int deststnr, u_char sign)
 {
 	FPU_REG *dest = &st(deststnr);
 	int tag = TAG_Valid;
@@ -539,7 +539,7 @@ int set_precision_flag(int flags)
 }
 
 /* This may be called often, so keep it lean */
-asmlinkage void set_precision_flag_up(void)
+asmlinkage __visible void set_precision_flag_up(void)
 {
 	if (control_word & CW_Precision)
 		partial_status |= (SW_Precision | SW_C1);	/* The masked response */
@@ -548,7 +548,7 @@ asmlinkage void set_precision_flag_up(void)
 }
 
 /* This may be called often, so keep it lean */
-asmlinkage void set_precision_flag_down(void)
+asmlinkage __visible void set_precision_flag_down(void)
 {
 	if (control_word & CW_Precision) {	/* The masked response */
 		partial_status &= ~SW_C1;
@@ -557,7 +557,7 @@ asmlinkage void set_precision_flag_down(void)
 		EXCEPTION(EX_Precision);
 }
 
-asmlinkage int denormal_operand(void)
+asmlinkage __visible int denormal_operand(void)
 {
 	if (control_word & CW_Denormal) {	/* The masked response */
 		partial_status |= SW_Denorm_Op;
@@ -568,7 +568,7 @@ asmlinkage int denormal_operand(void)
 	}
 }
 
-asmlinkage int arith_overflow(FPU_REG *dest)
+asmlinkage __visible int arith_overflow(FPU_REG *dest)
 {
 	int tag = TAG_Valid;
 
@@ -596,7 +596,7 @@ asmlinkage int arith_overflow(FPU_REG *dest)
 
 }
 
-asmlinkage int arith_underflow(FPU_REG *dest)
+asmlinkage __visible int arith_underflow(FPU_REG *dest)
 {
 	int tag = TAG_Valid;
 
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index dc017735bb91..6d5663a599a7 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -171,7 +171,7 @@ static struct bpf_binary_header *bpf_alloc_binary(unsigned int proglen,
 	memset(header, 0xcc, sz); /* fill whole space with int3 instructions */
 
 	header->pages = sz / PAGE_SIZE;
-	hole = sz - (proglen + sizeof(*header));
+	hole = min(sz - (proglen + sizeof(*header)), PAGE_SIZE - sizeof(*header));
 
 	/* insert a random number of int3 instructions before BPF code */
 	*image_ptr = &header->image[prandom_u32() % hole];
diff --git a/arch/x86/platform/efi/early_printk.c b/arch/x86/platform/efi/early_printk.c
index 81b506d5befd..524142117296 100644
--- a/arch/x86/platform/efi/early_printk.c
+++ b/arch/x86/platform/efi/early_printk.c
@@ -14,48 +14,92 @@
 
 static const struct font_desc *font;
 static u32 efi_x, efi_y;
+static void *efi_fb;
+static bool early_efi_keep;
 
-static __init void early_efi_clear_scanline(unsigned int y)
+/*
+ * efi earlyprintk need use early_ioremap to map the framebuffer.
+ * But early_ioremap is not usable for earlyprintk=efi,keep, ioremap should
+ * be used instead. ioremap will be available after paging_init() which is
+ * earlier than initcall callbacks. Thus adding this early initcall function
+ * early_efi_map_fb to map the whole efi framebuffer.
+ */
+static __init int early_efi_map_fb(void)
 {
-	unsigned long base, *dst;
-	u16 len;
+	unsigned long base, size;
+
+	if (!early_efi_keep)
+		return 0;
 
 	base = boot_params.screen_info.lfb_base;
-	len = boot_params.screen_info.lfb_linelength;
+	size = boot_params.screen_info.lfb_size;
+	efi_fb = ioremap(base, size);
+
+	return efi_fb ? 0 : -ENOMEM;
+}
+early_initcall(early_efi_map_fb);
+
+/*
+ * early_efi_map maps efi framebuffer region [start, start + len -1]
+ * In case earlyprintk=efi,keep we have the whole framebuffer mapped already
+ * so just return the offset efi_fb + start.
+ */
+static __init_refok void *early_efi_map(unsigned long start, unsigned long len)
+{
+	unsigned long base;
+
+	base = boot_params.screen_info.lfb_base;
+
+	if (efi_fb)
+		return (efi_fb + start);
+	else
+		return early_ioremap(base + start, len);
+}
 
-	dst = early_ioremap(base + y*len, len);
+static __init_refok void early_efi_unmap(void *addr, unsigned long len)
+{
+	if (!efi_fb)
+		early_iounmap(addr, len);
+}
+
+static void early_efi_clear_scanline(unsigned int y)
+{
+	unsigned long *dst;
+	u16 len;
+
+	len = boot_params.screen_info.lfb_linelength;
+	dst = early_efi_map(y*len, len);
 	if (!dst)
 		return;
 
 	memset(dst, 0, len);
-	early_iounmap(dst, len);
+	early_efi_unmap(dst, len);
 }
 
-static __init void early_efi_scroll_up(void)
+static void early_efi_scroll_up(void)
 {
-	unsigned long base, *dst, *src;
+	unsigned long *dst, *src;
 	u16 len;
 	u32 i, height;
 
-	base = boot_params.screen_info.lfb_base;
 	len = boot_params.screen_info.lfb_linelength;
 	height = boot_params.screen_info.lfb_height;
 
 	for (i = 0; i < height - font->height; i++) {
-		dst = early_ioremap(base + i*len, len);
+		dst = early_efi_map(i*len, len);
 		if (!dst)
 			return;
 
-		src = early_ioremap(base + (i + font->height) * len, len);
+		src = early_efi_map((i + font->height) * len, len);
 		if (!src) {
-			early_iounmap(dst, len);
+			early_efi_unmap(dst, len);
 			return;
 		}
 
 		memmove(dst, src, len);
 
-		early_iounmap(src, len);
-		early_iounmap(dst, len);
+		early_efi_unmap(src, len);
+		early_efi_unmap(dst, len);
 	}
 }
 
@@ -79,16 +123,14 @@ static void early_efi_write_char(u32 *dst, unsigned char c, unsigned int h)
 	}
 }
 
-static __init void
+static void
 early_efi_write(struct console *con, const char *str, unsigned int num)
 {
 	struct screen_info *si;
-	unsigned long base;
 	unsigned int len;
 	const char *s;
 	void *dst;
 
-	base = boot_params.screen_info.lfb_base;
 	si = &boot_params.screen_info;
 	len = si->lfb_linelength;
 
@@ -109,7 +151,7 @@ early_efi_write(struct console *con, const char *str, unsigned int num)
 		for (h = 0; h < font->height; h++) {
 			unsigned int n, x;
 
-			dst = early_ioremap(base + (efi_y + h) * len, len);
+			dst = early_efi_map((efi_y + h) * len, len);
 			if (!dst)
 				return;
 
@@ -123,7 +165,7 @@ early_efi_write(struct console *con, const char *str, unsigned int num)
 				s++;
 			}
 
-			early_iounmap(dst, len);
+			early_efi_unmap(dst, len);
 		}
 
 		num -= count;
@@ -179,6 +221,9 @@ static __init int early_efi_setup(struct console *con, char *options)
 	for (i = 0; i < (yres - efi_y) / font->height; i++)
 		early_efi_scroll_up();
 
+	/* early_console_register will unset CON_BOOT in case ,keep */
+	if (!(con->flags & CON_BOOT))
+		early_efi_keep = true;
 	return 0;
 }
 
diff --git a/arch/x86/platform/olpc/olpc-xo1-pm.c b/arch/x86/platform/olpc/olpc-xo1-pm.c
index ff0174dda810..a9acde72d4ed 100644
--- a/arch/x86/platform/olpc/olpc-xo1-pm.c
+++ b/arch/x86/platform/olpc/olpc-xo1-pm.c
@@ -75,7 +75,7 @@ static int xo1_power_state_enter(suspend_state_t pm_state)
 	return 0;
 }
 
-asmlinkage int xo1_do_sleep(u8 sleep_state)
+asmlinkage __visible int xo1_do_sleep(u8 sleep_state)
 {
 	void *pgd_addr = __va(read_cr3());
 
diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c
index 304fca20d96e..35e2bb6c0f37 100644
--- a/arch/x86/power/hibernate_64.c
+++ b/arch/x86/power/hibernate_64.c
@@ -23,7 +23,7 @@
 extern __visible const void __nosave_begin, __nosave_end;
 
 /* Defined in hibernate_asm_64.S */
-extern asmlinkage int restore_image(void);
+extern asmlinkage __visible int restore_image(void);
 
 /*
  * Address to jump to in the last phase of restore in order to get to the image
diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c
index 00348980a3a6..e1f220e3ca68 100644
--- a/arch/x86/vdso/vdso32-setup.c
+++ b/arch/x86/vdso/vdso32-setup.c
@@ -39,6 +39,7 @@
 #ifdef CONFIG_X86_64
 #define vdso_enabled			sysctl_vsyscall32
 #define arch_setup_additional_pages	syscall32_setup_pages
+extern int sysctl_ldt16;
 #endif
 
 /*
@@ -249,6 +250,13 @@ static struct ctl_table abi_table2[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec
 	},
+	{
+		.procname	= "ldt16",
+		.data		= &sysctl_ldt16,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
 	{}
 };
 
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 201d09a7c46b..c34bfc4bbe7f 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1515,7 +1515,7 @@ static void __init xen_pvh_early_guest_init(void)
 }
 
 /* First C function to be called on Xen boot */
-asmlinkage void __init xen_start_kernel(void)
+asmlinkage __visible void __init xen_start_kernel(void)
 {
 	struct physdev_set_iopl set_iopl;
 	int rc;
diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c
index 08f763de26fe..a1207cb6472a 100644
--- a/arch/x86/xen/irq.c
+++ b/arch/x86/xen/irq.c
@@ -23,7 +23,7 @@ void xen_force_evtchn_callback(void)
 	(void)HYPERVISOR_xen_version(0, NULL);
 }
 
-asmlinkage unsigned long xen_save_fl(void)
+asmlinkage __visible unsigned long xen_save_fl(void)
 {
 	struct vcpu_info *vcpu;
 	unsigned long flags;
@@ -63,7 +63,7 @@ __visible void xen_restore_fl(unsigned long flags)
 }
 PV_CALLEE_SAVE_REGS_THUNK(xen_restore_fl);
 
-asmlinkage void xen_irq_disable(void)
+asmlinkage __visible void xen_irq_disable(void)
 {
 	/* There's a one instruction preempt window here.  We need to
 	   make sure we're don't switch CPUs between getting the vcpu
@@ -74,7 +74,7 @@ asmlinkage void xen_irq_disable(void)
 }
 PV_CALLEE_SAVE_REGS_THUNK(xen_irq_disable);
 
-asmlinkage void xen_irq_enable(void)
+asmlinkage __visible void xen_irq_enable(void)
 {
 	struct vcpu_info *vcpu;
 
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index e4a4145926f6..1039fb9ff5f5 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -451,7 +451,20 @@ static int blkcg_reset_stats(struct cgroup_subsys_state *css,
 	struct blkcg_gq *blkg;
 	int i;
 
-	mutex_lock(&blkcg_pol_mutex);
+	/*
+	 * XXX: We invoke cgroup_add/rm_cftypes() under blkcg_pol_mutex
+	 * which ends up putting cgroup's internal cgroup_tree_mutex under
+	 * it; however, cgroup_tree_mutex is nested above cgroup file
+	 * active protection and grabbing blkcg_pol_mutex from a cgroup
+	 * file operation creates a possible circular dependency.  cgroup
+	 * internal locking is planned to go through further simplification
+	 * and this issue should go away soon.  For now, let's trylock
+	 * blkcg_pol_mutex and restart the write on failure.
+	 *
+	 * http://lkml.kernel.org/g/5363C04B.4010400@oracle.com
+	 */
+	if (!mutex_trylock(&blkcg_pol_mutex))
+		return restart_syscall();
 	spin_lock_irq(&blkcg->lock);
 
 	/*
diff --git a/drivers/Makefile b/drivers/Makefile
index d05d81b19b50..7183b6af5dac 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -119,7 +119,7 @@ obj-$(CONFIG_SGI_SN)		+= sn/
 obj-y				+= firmware/
 obj-$(CONFIG_CRYPTO)		+= crypto/
 obj-$(CONFIG_SUPERH)		+= sh/
-obj-$(CONFIG_ARCH_SHMOBILE_LEGACY)	+= sh/
+obj-$(CONFIG_ARCH_SHMOBILE)	+= sh/
 ifndef CONFIG_ARCH_USES_GETTIMEOFFSET
 obj-y				+= clocksource/
 endif
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index ab686b310100..a34a22841002 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -47,6 +47,23 @@ config ACPI_SLEEP
 	depends on SUSPEND || HIBERNATION
 	default y
 
+config ACPI_PROCFS_POWER
+	bool "Deprecated power /proc/acpi directories"
+	depends on PROC_FS
+	help
+	  For backwards compatibility, this option allows
+          deprecated power /proc/acpi/ directories to exist, even when
+          they have been replaced by functions in /sys.
+          The deprecated directories (and their replacements) include:
+	  /proc/acpi/battery/* (/sys/class/power_supply/*)
+	  /proc/acpi/ac_adapter/* (sys/class/power_supply/*)
+	  This option has no effect on /proc/acpi/ directories
+	  and functions, which do not yet exist in /sys
+	  This option, together with the proc directories, will be
+	  deleted in the future.
+
+	  Say N to delete power /proc/acpi/ directories that have moved to /sys/
+
 config ACPI_EC_DEBUGFS
 	tristate "EC read/write access through /sys/kernel/debug/ec"
 	default n
diff --git a/drivers/acpi/Makefile b/drivers/acpi/Makefile
index 0331f91d56e6..bce34afadcd0 100644
--- a/drivers/acpi/Makefile
+++ b/drivers/acpi/Makefile
@@ -47,6 +47,7 @@ acpi-y				+= sysfs.o
 acpi-$(CONFIG_X86)		+= acpi_cmos_rtc.o
 acpi-$(CONFIG_DEBUG_FS)		+= debugfs.o
 acpi-$(CONFIG_ACPI_NUMA)	+= numa.o
+acpi-$(CONFIG_ACPI_PROCFS_POWER) += cm_sbs.o
 ifdef CONFIG_ACPI_VIDEO
 acpi-y				+= video_detect.o
 endif
diff --git a/drivers/acpi/ac.c b/drivers/acpi/ac.c
index 2c01c1da29ce..c67f6f5ad611 100644
--- a/drivers/acpi/ac.c
+++ b/drivers/acpi/ac.c
@@ -52,11 +52,39 @@ MODULE_AUTHOR("Paul Diefenbaugh");
 MODULE_DESCRIPTION("ACPI AC Adapter Driver");
 MODULE_LICENSE("GPL");
 
+static int acpi_ac_add(struct acpi_device *device);
+static int acpi_ac_remove(struct acpi_device *device);
+static void acpi_ac_notify(struct acpi_device *device, u32 event);
+
+static const struct acpi_device_id ac_device_ids[] = {
+	{"ACPI0003", 0},
+	{"", 0},
+};
+MODULE_DEVICE_TABLE(acpi, ac_device_ids);
+
+#ifdef CONFIG_PM_SLEEP
+static int acpi_ac_resume(struct device *dev);
+#endif
+static SIMPLE_DEV_PM_OPS(acpi_ac_pm, NULL, acpi_ac_resume);
+
 static int ac_sleep_before_get_state_ms;
 
+static struct acpi_driver acpi_ac_driver = {
+	.name = "ac",
+	.class = ACPI_AC_CLASS,
+	.ids = ac_device_ids,
+	.flags = ACPI_DRIVER_ALL_NOTIFY_EVENTS,
+	.ops = {
+		.add = acpi_ac_add,
+		.remove = acpi_ac_remove,
+		.notify = acpi_ac_notify,
+		},
+	.drv.pm = &acpi_ac_pm,
+};
+
 struct acpi_ac {
 	struct power_supply charger;
-	struct platform_device *pdev;
+	struct acpi_device * device;
 	unsigned long long state;
 	struct notifier_block battery_nb;
 };
@@ -69,10 +97,12 @@ struct acpi_ac {
 
 static int acpi_ac_get_state(struct acpi_ac *ac)
 {
-	acpi_status status;
-	acpi_handle handle = ACPI_HANDLE(&ac->pdev->dev);
+	acpi_status status = AE_OK;
+
+	if (!ac)
+		return -EINVAL;
 
-	status = acpi_evaluate_integer(handle, "_PSR", NULL,
+	status = acpi_evaluate_integer(ac->device->handle, "_PSR", NULL,
 				       &ac->state);
 	if (ACPI_FAILURE(status)) {
 		ACPI_EXCEPTION((AE_INFO, status,
@@ -117,10 +147,9 @@ static enum power_supply_property ac_props[] = {
                                    Driver Model
    -------------------------------------------------------------------------- */
 
-static void acpi_ac_notify_handler(acpi_handle handle, u32 event, void *data)
+static void acpi_ac_notify(struct acpi_device *device, u32 event)
 {
-	struct acpi_ac *ac = data;
-	struct acpi_device *adev;
+	struct acpi_ac *ac = acpi_driver_data(device);
 
 	if (!ac)
 		return;
@@ -143,11 +172,10 @@ static void acpi_ac_notify_handler(acpi_handle handle, u32 event, void *data)
 			msleep(ac_sleep_before_get_state_ms);
 
 		acpi_ac_get_state(ac);
-		adev = ACPI_COMPANION(&ac->pdev->dev);
-		acpi_bus_generate_netlink_event(adev->pnp.device_class,
-						dev_name(&ac->pdev->dev),
-						event, (u32) ac->state);
-		acpi_notifier_call_chain(adev, event, (u32) ac->state);
+		acpi_bus_generate_netlink_event(device->pnp.device_class,
+						  dev_name(&device->dev), event,
+						  (u32) ac->state);
+		acpi_notifier_call_chain(device, event, (u32) ac->state);
 		kobject_uevent(&ac->charger.dev->kobj, KOBJ_CHANGE);
 	}
 
@@ -192,49 +220,39 @@ static struct dmi_system_id ac_dmi_table[] = {
 	{},
 };
 
-static int acpi_ac_probe(struct platform_device *pdev)
+static int acpi_ac_add(struct acpi_device *device)
 {
 	int result = 0;
 	struct acpi_ac *ac = NULL;
-	struct acpi_device *adev;
 
-	if (!pdev)
-		return -EINVAL;
 
-	adev = ACPI_COMPANION(&pdev->dev);
-	if (!adev)
-		return -ENODEV;
+	if (!device)
+		return -EINVAL;
 
 	ac = kzalloc(sizeof(struct acpi_ac), GFP_KERNEL);
 	if (!ac)
 		return -ENOMEM;
 
-	strcpy(acpi_device_name(adev), ACPI_AC_DEVICE_NAME);
-	strcpy(acpi_device_class(adev), ACPI_AC_CLASS);
-	ac->pdev = pdev;
-	platform_set_drvdata(pdev, ac);
+	ac->device = device;
+	strcpy(acpi_device_name(device), ACPI_AC_DEVICE_NAME);
+	strcpy(acpi_device_class(device), ACPI_AC_CLASS);
+	device->driver_data = ac;
 
 	result = acpi_ac_get_state(ac);
 	if (result)
 		goto end;
 
-	ac->charger.name = acpi_device_bid(adev);
+	ac->charger.name = acpi_device_bid(device);
 	ac->charger.type = POWER_SUPPLY_TYPE_MAINS;
 	ac->charger.properties = ac_props;
 	ac->charger.num_properties = ARRAY_SIZE(ac_props);
 	ac->charger.get_property = get_ac_property;
-	result = power_supply_register(&pdev->dev, &ac->charger);
+	result = power_supply_register(&ac->device->dev, &ac->charger);
 	if (result)
 		goto end;
 
-	result = acpi_install_notify_handler(ACPI_HANDLE(&pdev->dev),
-			ACPI_ALL_NOTIFY, acpi_ac_notify_handler, ac);
-	if (result) {
-		power_supply_unregister(&ac->charger);
-		goto end;
-	}
 	printk(KERN_INFO PREFIX "%s [%s] (%s)\n",
-	       acpi_device_name(adev), acpi_device_bid(adev),
+	       acpi_device_name(device), acpi_device_bid(device),
 	       ac->state ? "on-line" : "off-line");
 
 	ac->battery_nb.notifier_call = acpi_ac_battery_notify;
@@ -256,7 +274,7 @@ static int acpi_ac_resume(struct device *dev)
 	if (!dev)
 		return -EINVAL;
 
-	ac = platform_get_drvdata(to_platform_device(dev));
+	ac = acpi_driver_data(to_acpi_device(dev));
 	if (!ac)
 		return -EINVAL;
 
@@ -270,19 +288,17 @@ static int acpi_ac_resume(struct device *dev)
 #else
 #define acpi_ac_resume NULL
 #endif
-static SIMPLE_DEV_PM_OPS(acpi_ac_pm_ops, NULL, acpi_ac_resume);
 
-static int acpi_ac_remove(struct platform_device *pdev)
+static int acpi_ac_remove(struct acpi_device *device)
 {
-	struct acpi_ac *ac;
+	struct acpi_ac *ac = NULL;
+
 
-	if (!pdev)
+	if (!device || !acpi_driver_data(device))
 		return -EINVAL;
 
-	acpi_remove_notify_handler(ACPI_HANDLE(&pdev->dev),
-			ACPI_ALL_NOTIFY, acpi_ac_notify_handler);
+	ac = acpi_driver_data(device);
 
-	ac = platform_get_drvdata(pdev);
 	if (ac->charger.dev)
 		power_supply_unregister(&ac->charger);
 	unregister_acpi_notifier(&ac->battery_nb);
@@ -292,23 +308,6 @@ static int acpi_ac_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static const struct acpi_device_id acpi_ac_match[] = {
-	{ "ACPI0003", 0 },
-	{ }
-};
-MODULE_DEVICE_TABLE(acpi, acpi_ac_match);
-
-static struct platform_driver acpi_ac_driver = {
-	.probe          = acpi_ac_probe,
-	.remove         = acpi_ac_remove,
-	.driver         = {
-		.name   = "acpi-ac",
-		.owner  = THIS_MODULE,
-		.pm     = &acpi_ac_pm_ops,
-		.acpi_match_table = ACPI_PTR(acpi_ac_match),
-	},
-};
-
 static int __init acpi_ac_init(void)
 {
 	int result;
@@ -316,7 +315,7 @@ static int __init acpi_ac_init(void)
 	if (acpi_disabled)
 		return -ENODEV;
 
-	result = platform_driver_register(&acpi_ac_driver);
+	result = acpi_bus_register_driver(&acpi_ac_driver);
 	if (result < 0)
 		return -ENODEV;
 
@@ -325,7 +324,7 @@ static int __init acpi_ac_init(void)
 
 static void __exit acpi_ac_exit(void)
 {
-	platform_driver_unregister(&acpi_ac_driver);
+	acpi_bus_unregister_driver(&acpi_ac_driver);
 }
 module_init(acpi_ac_init);
 module_exit(acpi_ac_exit);
diff --git a/drivers/acpi/acpi_platform.c b/drivers/acpi/acpi_platform.c
index dbfe49e5fd63..1d4950388fa1 100644
--- a/drivers/acpi/acpi_platform.c
+++ b/drivers/acpi/acpi_platform.c
@@ -29,7 +29,6 @@ ACPI_MODULE_NAME("platform");
 static const struct acpi_device_id acpi_platform_device_ids[] = {
 
 	{ "PNP0D40" },
-	{ "ACPI0003" },
 	{ "VPC2004" },
 	{ "BCM4752" },
 
diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
index b06f5f55ada9..52c81c49cc7d 100644
--- a/drivers/acpi/acpi_processor.c
+++ b/drivers/acpi/acpi_processor.c
@@ -405,7 +405,6 @@ static int acpi_processor_add(struct acpi_device *device,
 		goto err;
 
 	pr->dev = dev;
-	dev->offline = pr->flags.need_hotplug_init;
 
 	/* Trigger the processor driver's .probe() if present. */
 	if (device_attach(dev) >= 0)
diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h
index 49bbc71fad54..a08a448068dd 100644
--- a/drivers/acpi/acpica/acglobal.h
+++ b/drivers/acpi/acpica/acglobal.h
@@ -141,9 +141,9 @@ ACPI_INIT_GLOBAL(u8, acpi_gbl_do_not_use_xsdt, FALSE);
  * address. Although ACPICA adheres to the ACPI specification which
  * requires the use of the corresponding 64-bit address if it is non-zero,
  * some machines have been found to have a corrupted non-zero 64-bit
- * address. Default is FALSE, do not favor the 32-bit addresses.
+ * address. Default is TRUE, favor the 32-bit addresses.
  */
-ACPI_INIT_GLOBAL(u8, acpi_gbl_use32_bit_fadt_addresses, FALSE);
+ACPI_INIT_GLOBAL(u8, acpi_gbl_use32_bit_fadt_addresses, TRUE);
 
 /*
  * Optionally truncate I/O addresses to 16 bits. Provides compatibility
diff --git a/drivers/acpi/acpica/tbutils.c b/drivers/acpi/acpica/tbutils.c
index a4702eee91a8..9fb85f38de90 100644
--- a/drivers/acpi/acpica/tbutils.c
+++ b/drivers/acpi/acpica/tbutils.c
@@ -461,6 +461,7 @@ acpi_status __init acpi_tb_parse_root_table(acpi_physical_address rsdp_address)
 	u32 table_count;
 	struct acpi_table_header *table;
 	acpi_physical_address address;
+	acpi_physical_address rsdt_address;
 	u32 length;
 	u8 *table_entry;
 	acpi_status status;
@@ -488,11 +489,14 @@ acpi_status __init acpi_tb_parse_root_table(acpi_physical_address rsdp_address)
 		 * as per the ACPI specification.
 		 */
 		address = (acpi_physical_address) rsdp->xsdt_physical_address;
+		rsdt_address =
+		    (acpi_physical_address) rsdp->rsdt_physical_address;
 		table_entry_size = ACPI_XSDT_ENTRY_SIZE;
 	} else {
 		/* Root table is an RSDT (32-bit physical addresses) */
 
 		address = (acpi_physical_address) rsdp->rsdt_physical_address;
+		rsdt_address = address;
 		table_entry_size = ACPI_RSDT_ENTRY_SIZE;
 	}
 
@@ -515,8 +519,7 @@ acpi_status __init acpi_tb_parse_root_table(acpi_physical_address rsdp_address)
 
 			/* Fall back to the RSDT */
 
-			address =
-			    (acpi_physical_address) rsdp->rsdt_physical_address;
+			address = rsdt_address;
 			table_entry_size = ACPI_RSDT_ENTRY_SIZE;
 		}
 	}
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index 9a2c63b20050..6e7b2a12860d 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -36,6 +36,12 @@
 #include <linux/suspend.h>
 #include <asm/unaligned.h>
 
+#ifdef CONFIG_ACPI_PROCFS_POWER
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <asm/uaccess.h>
+#endif
+
 #include <linux/acpi.h>
 #include <linux/power_supply.h>
 
@@ -64,6 +70,19 @@ static unsigned int cache_time = 1000;
 module_param(cache_time, uint, 0644);
 MODULE_PARM_DESC(cache_time, "cache time in milliseconds");
 
+#ifdef CONFIG_ACPI_PROCFS_POWER
+extern struct proc_dir_entry *acpi_lock_battery_dir(void);
+extern void *acpi_unlock_battery_dir(struct proc_dir_entry *acpi_battery_dir);
+
+enum acpi_battery_files {
+	info_tag = 0,
+	state_tag,
+	alarm_tag,
+	ACPI_BATTERY_NUMFILES,
+};
+
+#endif
+
 static const struct acpi_device_id battery_device_ids[] = {
 	{"PNP0C0A", 0},
 	{"", 0},
@@ -299,6 +318,14 @@ static enum power_supply_property energy_battery_props[] = {
 	POWER_SUPPLY_PROP_SERIAL_NUMBER,
 };
 
+#ifdef CONFIG_ACPI_PROCFS_POWER
+inline char *acpi_battery_units(struct acpi_battery *battery)
+{
+	return (battery->power_unit == ACPI_BATTERY_POWER_UNIT_MA) ?
+		"mA" : "mW";
+}
+#endif
+
 /* --------------------------------------------------------------------------
                                Battery Management
    -------------------------------------------------------------------------- */
@@ -717,6 +744,279 @@ static void acpi_battery_refresh(struct acpi_battery *battery)
 }
 
 /* --------------------------------------------------------------------------
+                              FS Interface (/proc)
+   -------------------------------------------------------------------------- */
+
+#ifdef CONFIG_ACPI_PROCFS_POWER
+static struct proc_dir_entry *acpi_battery_dir;
+
+static int acpi_battery_print_info(struct seq_file *seq, int result)
+{
+	struct acpi_battery *battery = seq->private;
+
+	if (result)
+		goto end;
+
+	seq_printf(seq, "present:                 %s\n",
+		   acpi_battery_present(battery) ? "yes" : "no");
+	if (!acpi_battery_present(battery))
+		goto end;
+	if (battery->design_capacity == ACPI_BATTERY_VALUE_UNKNOWN)
+		seq_printf(seq, "design capacity:         unknown\n");
+	else
+		seq_printf(seq, "design capacity:         %d %sh\n",
+			   battery->design_capacity,
+			   acpi_battery_units(battery));
+
+	if (battery->full_charge_capacity == ACPI_BATTERY_VALUE_UNKNOWN)
+		seq_printf(seq, "last full capacity:      unknown\n");
+	else
+		seq_printf(seq, "last full capacity:      %d %sh\n",
+			   battery->full_charge_capacity,
+			   acpi_battery_units(battery));
+
+	seq_printf(seq, "battery technology:      %srechargeable\n",
+		   (!battery->technology)?"non-":"");
+
+	if (battery->design_voltage == ACPI_BATTERY_VALUE_UNKNOWN)
+		seq_printf(seq, "design voltage:          unknown\n");
+	else
+		seq_printf(seq, "design voltage:          %d mV\n",
+			   battery->design_voltage);
+	seq_printf(seq, "design capacity warning: %d %sh\n",
+		   battery->design_capacity_warning,
+		   acpi_battery_units(battery));
+	seq_printf(seq, "design capacity low:     %d %sh\n",
+		   battery->design_capacity_low,
+		   acpi_battery_units(battery));
+	seq_printf(seq, "cycle count:		  %i\n", battery->cycle_count);
+	seq_printf(seq, "capacity granularity 1:  %d %sh\n",
+		   battery->capacity_granularity_1,
+		   acpi_battery_units(battery));
+	seq_printf(seq, "capacity granularity 2:  %d %sh\n",
+		   battery->capacity_granularity_2,
+		   acpi_battery_units(battery));
+	seq_printf(seq, "model number:            %s\n", battery->model_number);
+	seq_printf(seq, "serial number:           %s\n", battery->serial_number);
+	seq_printf(seq, "battery type:            %s\n", battery->type);
+	seq_printf(seq, "OEM info:                %s\n", battery->oem_info);
+      end:
+	if (result)
+		seq_printf(seq, "ERROR: Unable to read battery info\n");
+	return result;
+}
+
+static int acpi_battery_print_state(struct seq_file *seq, int result)
+{
+	struct acpi_battery *battery = seq->private;
+
+	if (result)
+		goto end;
+
+	seq_printf(seq, "present:                 %s\n",
+		   acpi_battery_present(battery) ? "yes" : "no");
+	if (!acpi_battery_present(battery))
+		goto end;
+
+	seq_printf(seq, "capacity state:          %s\n",
+			(battery->state & 0x04) ? "critical" : "ok");
+	if ((battery->state & 0x01) && (battery->state & 0x02))
+		seq_printf(seq,
+			   "charging state:          charging/discharging\n");
+	else if (battery->state & 0x01)
+		seq_printf(seq, "charging state:          discharging\n");
+	else if (battery->state & 0x02)
+		seq_printf(seq, "charging state:          charging\n");
+	else
+		seq_printf(seq, "charging state:          charged\n");
+
+	if (battery->rate_now == ACPI_BATTERY_VALUE_UNKNOWN)
+		seq_printf(seq, "present rate:            unknown\n");
+	else
+		seq_printf(seq, "present rate:            %d %s\n",
+			   battery->rate_now, acpi_battery_units(battery));
+
+	if (battery->capacity_now == ACPI_BATTERY_VALUE_UNKNOWN)
+		seq_printf(seq, "remaining capacity:      unknown\n");
+	else
+		seq_printf(seq, "remaining capacity:      %d %sh\n",
+			   battery->capacity_now, acpi_battery_units(battery));
+	if (battery->voltage_now == ACPI_BATTERY_VALUE_UNKNOWN)
+		seq_printf(seq, "present voltage:         unknown\n");
+	else
+		seq_printf(seq, "present voltage:         %d mV\n",
+			   battery->voltage_now);
+      end:
+	if (result)
+		seq_printf(seq, "ERROR: Unable to read battery state\n");
+
+	return result;
+}
+
+static int acpi_battery_print_alarm(struct seq_file *seq, int result)
+{
+	struct acpi_battery *battery = seq->private;
+
+	if (result)
+		goto end;
+
+	if (!acpi_battery_present(battery)) {
+		seq_printf(seq, "present:                 no\n");
+		goto end;
+	}
+	seq_printf(seq, "alarm:                   ");
+	if (!battery->alarm)
+		seq_printf(seq, "unsupported\n");
+	else
+		seq_printf(seq, "%u %sh\n", battery->alarm,
+				acpi_battery_units(battery));
+      end:
+	if (result)
+		seq_printf(seq, "ERROR: Unable to read battery alarm\n");
+	return result;
+}
+
+static ssize_t acpi_battery_write_alarm(struct file *file,
+					const char __user * buffer,
+					size_t count, loff_t * ppos)
+{
+	int result = 0;
+	char alarm_string[12] = { '\0' };
+	struct seq_file *m = file->private_data;
+	struct acpi_battery *battery = m->private;
+
+	if (!battery || (count > sizeof(alarm_string) - 1))
+		return -EINVAL;
+	if (!acpi_battery_present(battery)) {
+		result = -ENODEV;
+		goto end;
+	}
+	if (copy_from_user(alarm_string, buffer, count)) {
+		result = -EFAULT;
+		goto end;
+	}
+	alarm_string[count] = '\0';
+	battery->alarm = simple_strtol(alarm_string, NULL, 0);
+	result = acpi_battery_set_alarm(battery);
+      end:
+	if (!result)
+		return count;
+	return result;
+}
+
+typedef int(*print_func)(struct seq_file *seq, int result);
+
+static print_func acpi_print_funcs[ACPI_BATTERY_NUMFILES] = {
+	acpi_battery_print_info,
+	acpi_battery_print_state,
+	acpi_battery_print_alarm,
+};
+
+static int acpi_battery_read(int fid, struct seq_file *seq)
+{
+	struct acpi_battery *battery = seq->private;
+	int result = acpi_battery_update(battery);
+	return acpi_print_funcs[fid](seq, result);
+}
+
+#define DECLARE_FILE_FUNCTIONS(_name) \
+static int acpi_battery_read_##_name(struct seq_file *seq, void *offset) \
+{ \
+	return acpi_battery_read(_name##_tag, seq); \
+} \
+static int acpi_battery_##_name##_open_fs(struct inode *inode, struct file *file) \
+{ \
+	return single_open(file, acpi_battery_read_##_name, PDE_DATA(inode)); \
+}
+
+DECLARE_FILE_FUNCTIONS(info);
+DECLARE_FILE_FUNCTIONS(state);
+DECLARE_FILE_FUNCTIONS(alarm);
+
+#undef DECLARE_FILE_FUNCTIONS
+
+#define FILE_DESCRIPTION_RO(_name) \
+	{ \
+	.name = __stringify(_name), \
+	.mode = S_IRUGO, \
+	.ops = { \
+		.open = acpi_battery_##_name##_open_fs, \
+		.read = seq_read, \
+		.llseek = seq_lseek, \
+		.release = single_release, \
+		.owner = THIS_MODULE, \
+		}, \
+	}
+
+#define FILE_DESCRIPTION_RW(_name) \
+	{ \
+	.name = __stringify(_name), \
+	.mode = S_IFREG | S_IRUGO | S_IWUSR, \
+	.ops = { \
+		.open = acpi_battery_##_name##_open_fs, \
+		.read = seq_read, \
+		.llseek = seq_lseek, \
+		.write = acpi_battery_write_##_name, \
+		.release = single_release, \
+		.owner = THIS_MODULE, \
+		}, \
+	}
+
+static const struct battery_file {
+	struct file_operations ops;
+	umode_t mode;
+	const char *name;
+} acpi_battery_file[] = {
+	FILE_DESCRIPTION_RO(info),
+	FILE_DESCRIPTION_RO(state),
+	FILE_DESCRIPTION_RW(alarm),
+};
+
+#undef FILE_DESCRIPTION_RO
+#undef FILE_DESCRIPTION_RW
+
+static int acpi_battery_add_fs(struct acpi_device *device)
+{
+	struct proc_dir_entry *entry = NULL;
+	int i;
+
+	printk(KERN_WARNING PREFIX "Deprecated procfs I/F for battery is loaded,"
+			" please retry with CONFIG_ACPI_PROCFS_POWER cleared\n");
+	if (!acpi_device_dir(device)) {
+		acpi_device_dir(device) = proc_mkdir(acpi_device_bid(device),
+						     acpi_battery_dir);
+		if (!acpi_device_dir(device))
+			return -ENODEV;
+	}
+
+	for (i = 0; i < ACPI_BATTERY_NUMFILES; ++i) {
+		entry = proc_create_data(acpi_battery_file[i].name,
+					 acpi_battery_file[i].mode,
+					 acpi_device_dir(device),
+					 &acpi_battery_file[i].ops,
+					 acpi_driver_data(device));
+		if (!entry)
+			return -ENODEV;
+	}
+	return 0;
+}
+
+static void acpi_battery_remove_fs(struct acpi_device *device)
+{
+	int i;
+	if (!acpi_device_dir(device))
+		return;
+	for (i = 0; i < ACPI_BATTERY_NUMFILES; ++i)
+		remove_proc_entry(acpi_battery_file[i].name,
+				  acpi_device_dir(device));
+
+	remove_proc_entry(acpi_device_bid(device), acpi_battery_dir);
+	acpi_device_dir(device) = NULL;
+}
+
+#endif
+
+/* --------------------------------------------------------------------------
                                  Driver Interface
    -------------------------------------------------------------------------- */
 
@@ -790,6 +1090,15 @@ static int acpi_battery_add(struct acpi_device *device)
 	result = acpi_battery_update(battery);
 	if (result)
 		goto fail;
+#ifdef CONFIG_ACPI_PROCFS_POWER
+	result = acpi_battery_add_fs(device);
+#endif
+	if (result) {
+#ifdef CONFIG_ACPI_PROCFS_POWER
+		acpi_battery_remove_fs(device);
+#endif
+		goto fail;
+	}
 
 	printk(KERN_INFO PREFIX "%s Slot [%s] (battery %s)\n",
 		ACPI_BATTERY_DEVICE_NAME, acpi_device_bid(device),
@@ -816,6 +1125,9 @@ static int acpi_battery_remove(struct acpi_device *device)
 		return -EINVAL;
 	battery = acpi_driver_data(device);
 	unregister_pm_notifier(&battery->pm_nb);
+#ifdef CONFIG_ACPI_PROCFS_POWER
+	acpi_battery_remove_fs(device);
+#endif
 	sysfs_remove_battery(battery);
 	mutex_destroy(&battery->lock);
 	mutex_destroy(&battery->sysfs_lock);
@@ -866,7 +1178,19 @@ static void __init acpi_battery_init_async(void *unused, async_cookie_t cookie)
 
 	if (dmi_check_system(bat_dmi_table))
 		battery_bix_broken_package = 1;
-	acpi_bus_register_driver(&acpi_battery_driver);
+	
+#ifdef CONFIG_ACPI_PROCFS_POWER
+	acpi_battery_dir = acpi_lock_battery_dir();
+	if (!acpi_battery_dir)
+		return;
+#endif
+	if (acpi_bus_register_driver(&acpi_battery_driver) < 0) {
+#ifdef CONFIG_ACPI_PROCFS_POWER
+		acpi_unlock_battery_dir(acpi_battery_dir);
+#endif
+		return;
+	}
+	return;
 }
 
 static int __init acpi_battery_init(void)
@@ -878,6 +1202,9 @@ static int __init acpi_battery_init(void)
 static void __exit acpi_battery_exit(void)
 {
 	acpi_bus_unregister_driver(&acpi_battery_driver);
+#ifdef CONFIG_ACPI_PROCFS_POWER
+	acpi_unlock_battery_dir(acpi_battery_dir);
+#endif
 }
 
 module_init(acpi_battery_init);
diff --git a/drivers/acpi/blacklist.c b/drivers/acpi/blacklist.c
index afec4526c48a..3d8413d02a97 100644
--- a/drivers/acpi/blacklist.c
+++ b/drivers/acpi/blacklist.c
@@ -314,6 +314,14 @@ static struct dmi_system_id acpi_osi_dmi_table[] __initdata = {
 		     DMI_MATCH(DMI_PRODUCT_VERSION, "2349D15"),
 		},
 	},
+	{
+	.callback = dmi_disable_osi_win8,
+	.ident = "Dell Inspiron 7737",
+	.matches = {
+		    DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		    DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 7737"),
+		},
+	},
 
 	/*
 	 * BIOS invocation of _OSI(Linux) is almost always a BIOS bug.
@@ -374,6 +382,19 @@ static struct dmi_system_id acpi_osi_dmi_table[] __initdata = {
 		     DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T500"),
 		},
 	},
+	/*
+	 * Without this this EEEpc exports a non working WMI interface, with
+	 * this it exports a working "good old" eeepc_laptop interface, fixing
+	 * both brightness control, and rfkill not working.
+	 */
+	{
+	.callback = dmi_enable_osi_linux,
+	.ident = "Asus EEE PC 1015PX",
+	.matches = {
+		     DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer INC."),
+		     DMI_MATCH(DMI_PRODUCT_NAME, "1015PX"),
+		},
+	},
 	{}
 };
 
diff --git a/drivers/acpi/cm_sbs.c b/drivers/acpi/cm_sbs.c
new file mode 100644
index 000000000000..6c9ee68e46fb
--- /dev/null
+++ b/drivers/acpi/cm_sbs.c
@@ -0,0 +1,105 @@
+/*
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or (at
+ *  your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful, but
+ *  WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *  General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License along
+ *  with this program; if not, write to the Free Software Foundation, Inc.,
+ *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/acpi.h>
+#include <linux/types.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <acpi/acpi_bus.h>
+#include <acpi/acpi_drivers.h>
+
+#define PREFIX "ACPI: "
+
+ACPI_MODULE_NAME("cm_sbs");
+#define ACPI_AC_CLASS		"ac_adapter"
+#define ACPI_BATTERY_CLASS	"battery"
+#define _COMPONENT		ACPI_SBS_COMPONENT
+static struct proc_dir_entry *acpi_ac_dir;
+static struct proc_dir_entry *acpi_battery_dir;
+
+static DEFINE_MUTEX(cm_sbs_mutex);
+
+static int lock_ac_dir_cnt;
+static int lock_battery_dir_cnt;
+
+struct proc_dir_entry *acpi_lock_ac_dir(void)
+{
+	mutex_lock(&cm_sbs_mutex);
+	if (!acpi_ac_dir)
+		acpi_ac_dir = proc_mkdir(ACPI_AC_CLASS, acpi_root_dir);
+	if (acpi_ac_dir) {
+		lock_ac_dir_cnt++;
+	} else {
+		printk(KERN_ERR PREFIX
+				  "Cannot create %s\n", ACPI_AC_CLASS);
+	}
+	mutex_unlock(&cm_sbs_mutex);
+	return acpi_ac_dir;
+}
+EXPORT_SYMBOL(acpi_lock_ac_dir);
+
+void acpi_unlock_ac_dir(struct proc_dir_entry *acpi_ac_dir_param)
+{
+	mutex_lock(&cm_sbs_mutex);
+	if (acpi_ac_dir_param)
+		lock_ac_dir_cnt--;
+	if (lock_ac_dir_cnt == 0 && acpi_ac_dir_param && acpi_ac_dir) {
+		remove_proc_entry(ACPI_AC_CLASS, acpi_root_dir);
+		acpi_ac_dir = NULL;
+	}
+	mutex_unlock(&cm_sbs_mutex);
+}
+EXPORT_SYMBOL(acpi_unlock_ac_dir);
+
+struct proc_dir_entry *acpi_lock_battery_dir(void)
+{
+	mutex_lock(&cm_sbs_mutex);
+	if (!acpi_battery_dir) {
+		acpi_battery_dir =
+		    proc_mkdir(ACPI_BATTERY_CLASS, acpi_root_dir);
+	}
+	if (acpi_battery_dir) {
+		lock_battery_dir_cnt++;
+	} else {
+		printk(KERN_ERR PREFIX
+				  "Cannot create %s\n", ACPI_BATTERY_CLASS);
+	}
+	mutex_unlock(&cm_sbs_mutex);
+	return acpi_battery_dir;
+}
+EXPORT_SYMBOL(acpi_lock_battery_dir);
+
+void acpi_unlock_battery_dir(struct proc_dir_entry *acpi_battery_dir_param)
+{
+	mutex_lock(&cm_sbs_mutex);
+	if (acpi_battery_dir_param)
+		lock_battery_dir_cnt--;
+	if (lock_battery_dir_cnt == 0 && acpi_battery_dir_param
+	    && acpi_battery_dir) {
+		remove_proc_entry(ACPI_BATTERY_CLASS, acpi_root_dir);
+		acpi_battery_dir = NULL;
+	}
+	mutex_unlock(&cm_sbs_mutex);
+	return;
+}
+EXPORT_SYMBOL(acpi_unlock_battery_dir);
diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c
index c1e31a41f949..25bbc55dca89 100644
--- a/drivers/acpi/thermal.c
+++ b/drivers/acpi/thermal.c
@@ -1278,8 +1278,8 @@ static int __init acpi_thermal_init(void)
 
 static void __exit acpi_thermal_exit(void)
 {
-	destroy_workqueue(acpi_thermal_pm_queue);
 	acpi_bus_unregister_driver(&acpi_thermal_driver);
+	destroy_workqueue(acpi_thermal_pm_queue);
 
 	return;
 }
diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c
index 8b6990e417ec..f8bc5a755dda 100644
--- a/drivers/acpi/video.c
+++ b/drivers/acpi/video.c
@@ -457,10 +457,10 @@ static struct dmi_system_id video_dmi_table[] __initdata = {
 	},
 	{
 	 .callback = video_set_use_native_backlight,
-	 .ident = "ThinkPad T430s",
+	 .ident = "ThinkPad T430 and T430s",
 	 .matches = {
 		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-		DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T430s"),
+		DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T430"),
 		},
 	},
 	{
@@ -472,7 +472,7 @@ static struct dmi_system_id video_dmi_table[] __initdata = {
 		},
 	},
 	{
-	.callback = video_set_use_native_backlight,
+	 .callback = video_set_use_native_backlight,
 	.ident = "ThinkPad X1 Carbon",
 	.matches = {
 		DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
@@ -500,7 +500,7 @@ static struct dmi_system_id video_dmi_table[] __initdata = {
 	 .ident = "Dell Inspiron 7520",
 	 .matches = {
 		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
-		DMI_MATCH(DMI_PRODUCT_VERSION, "Inspiron 7520"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 7520"),
 		},
 	},
 	{
@@ -513,6 +513,14 @@ static struct dmi_system_id video_dmi_table[] __initdata = {
 	},
 	{
 	 .callback = video_set_use_native_backlight,
+	 .ident = "Acer Aspire 5742G",
+	 .matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 5742G"),
+		},
+	},
+	{
+	 .callback = video_set_use_native_backlight,
 	 .ident = "Acer Aspire V5-431",
 	 .matches = {
 		DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig
index c2706047337f..0033fafc470b 100644
--- a/drivers/ata/Kconfig
+++ b/drivers/ata/Kconfig
@@ -815,7 +815,7 @@ config PATA_AT32
 
 config PATA_AT91
 	tristate "PATA support for AT91SAM9260"
-	depends on ARM && ARCH_AT91
+	depends on ARM && SOC_AT91SAM9
 	help
 	  This option enables support for IDE devices on the Atmel AT91SAM9260 SoC.
 
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 71e15b73513d..60707814a84b 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -1115,6 +1115,17 @@ static bool ahci_broken_online(struct pci_dev *pdev)
 	return pdev->bus->number == (val >> 8) && pdev->devfn == (val & 0xff);
 }
 
+static bool ahci_broken_devslp(struct pci_dev *pdev)
+{
+	/* device with broken DEVSLP but still showing SDS capability */
+	static const struct pci_device_id ids[] = {
+		{ PCI_VDEVICE(INTEL, 0x0f23)}, /* Valleyview SoC */
+		{}
+	};
+
+	return pci_match_id(ids, pdev);
+}
+
 #ifdef CONFIG_ATA_ACPI
 static void ahci_gtf_filter_workaround(struct ata_host *host)
 {
@@ -1364,6 +1375,10 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	hpriv->mmio = pcim_iomap_table(pdev)[ahci_pci_bar];
 
+	/* must set flag prior to save config in order to take effect */
+	if (ahci_broken_devslp(pdev))
+		hpriv->flags |= AHCI_HFLAG_NO_DEVSLP;
+
 	/* save initial config */
 	ahci_pci_save_initial_config(pdev, hpriv);
 
diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index b5eb886da226..af63c75c2001 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -236,6 +236,7 @@ enum {
 						        port start (wait until
 						        error-handling stage) */
 	AHCI_HFLAG_MULTI_MSI		= (1 << 16), /* multiple PCI MSIs */
+	AHCI_HFLAG_NO_DEVSLP		= (1 << 17), /* no device sleep */
 
 	/* ap->flags bits */
 
diff --git a/drivers/ata/ahci_imx.c b/drivers/ata/ahci_imx.c
index 497c7abe1c7d..8befeb69eeb1 100644
--- a/drivers/ata/ahci_imx.c
+++ b/drivers/ata/ahci_imx.c
@@ -29,9 +29,25 @@
 #include "ahci.h"
 
 enum {
-	PORT_PHY_CTL = 0x178,			/* Port0 PHY Control */
-	PORT_PHY_CTL_PDDQ_LOC = 0x100000,	/* PORT_PHY_CTL bits */
-	HOST_TIMER1MS = 0xe0,			/* Timer 1-ms */
+	/* Timer 1-ms Register */
+	IMX_TIMER1MS				= 0x00e0,
+	/* Port0 PHY Control Register */
+	IMX_P0PHYCR				= 0x0178,
+	IMX_P0PHYCR_TEST_PDDQ			= 1 << 20,
+	IMX_P0PHYCR_CR_READ			= 1 << 19,
+	IMX_P0PHYCR_CR_WRITE			= 1 << 18,
+	IMX_P0PHYCR_CR_CAP_DATA			= 1 << 17,
+	IMX_P0PHYCR_CR_CAP_ADDR			= 1 << 16,
+	/* Port0 PHY Status Register */
+	IMX_P0PHYSR				= 0x017c,
+	IMX_P0PHYSR_CR_ACK			= 1 << 18,
+	IMX_P0PHYSR_CR_DATA_OUT			= 0xffff << 0,
+	/* Lane0 Output Status Register */
+	IMX_LANE0_OUT_STAT			= 0x2003,
+	IMX_LANE0_OUT_STAT_RX_PLL_STATE		= 1 << 1,
+	/* Clock Reset Register */
+	IMX_CLOCK_RESET				= 0x7f3f,
+	IMX_CLOCK_RESET_RESET			= 1 << 0,
 };
 
 enum ahci_imx_type {
@@ -54,9 +70,149 @@ MODULE_PARM_DESC(hotplug, "AHCI IMX hot-plug support (0=Don't support, 1=support
 
 static void ahci_imx_host_stop(struct ata_host *host);
 
+static int imx_phy_crbit_assert(void __iomem *mmio, u32 bit, bool assert)
+{
+	int timeout = 10;
+	u32 crval;
+	u32 srval;
+
+	/* Assert or deassert the bit */
+	crval = readl(mmio + IMX_P0PHYCR);
+	if (assert)
+		crval |= bit;
+	else
+		crval &= ~bit;
+	writel(crval, mmio + IMX_P0PHYCR);
+
+	/* Wait for the cr_ack signal */
+	do {
+		srval = readl(mmio + IMX_P0PHYSR);
+		if ((assert ? srval : ~srval) & IMX_P0PHYSR_CR_ACK)
+			break;
+		usleep_range(100, 200);
+	} while (--timeout);
+
+	return timeout ? 0 : -ETIMEDOUT;
+}
+
+static int imx_phy_reg_addressing(u16 addr, void __iomem *mmio)
+{
+	u32 crval = addr;
+	int ret;
+
+	/* Supply the address on cr_data_in */
+	writel(crval, mmio + IMX_P0PHYCR);
+
+	/* Assert the cr_cap_addr signal */
+	ret = imx_phy_crbit_assert(mmio, IMX_P0PHYCR_CR_CAP_ADDR, true);
+	if (ret)
+		return ret;
+
+	/* Deassert cr_cap_addr */
+	ret = imx_phy_crbit_assert(mmio, IMX_P0PHYCR_CR_CAP_ADDR, false);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int imx_phy_reg_write(u16 val, void __iomem *mmio)
+{
+	u32 crval = val;
+	int ret;
+
+	/* Supply the data on cr_data_in */
+	writel(crval, mmio + IMX_P0PHYCR);
+
+	/* Assert the cr_cap_data signal */
+	ret = imx_phy_crbit_assert(mmio, IMX_P0PHYCR_CR_CAP_DATA, true);
+	if (ret)
+		return ret;
+
+	/* Deassert cr_cap_data */
+	ret = imx_phy_crbit_assert(mmio, IMX_P0PHYCR_CR_CAP_DATA, false);
+	if (ret)
+		return ret;
+
+	if (val & IMX_CLOCK_RESET_RESET) {
+		/*
+		 * In case we're resetting the phy, it's unable to acknowledge,
+		 * so we return immediately here.
+		 */
+		crval |= IMX_P0PHYCR_CR_WRITE;
+		writel(crval, mmio + IMX_P0PHYCR);
+		goto out;
+	}
+
+	/* Assert the cr_write signal */
+	ret = imx_phy_crbit_assert(mmio, IMX_P0PHYCR_CR_WRITE, true);
+	if (ret)
+		return ret;
+
+	/* Deassert cr_write */
+	ret = imx_phy_crbit_assert(mmio, IMX_P0PHYCR_CR_WRITE, false);
+	if (ret)
+		return ret;
+
+out:
+	return 0;
+}
+
+static int imx_phy_reg_read(u16 *val, void __iomem *mmio)
+{
+	int ret;
+
+	/* Assert the cr_read signal */
+	ret = imx_phy_crbit_assert(mmio, IMX_P0PHYCR_CR_READ, true);
+	if (ret)
+		return ret;
+
+	/* Capture the data from cr_data_out[] */
+	*val = readl(mmio + IMX_P0PHYSR) & IMX_P0PHYSR_CR_DATA_OUT;
+
+	/* Deassert cr_read */
+	ret = imx_phy_crbit_assert(mmio, IMX_P0PHYCR_CR_READ, false);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int imx_sata_phy_reset(struct ahci_host_priv *hpriv)
+{
+	void __iomem *mmio = hpriv->mmio;
+	int timeout = 10;
+	u16 val;
+	int ret;
+
+	/* Reset SATA PHY by setting RESET bit of PHY register CLOCK_RESET */
+	ret = imx_phy_reg_addressing(IMX_CLOCK_RESET, mmio);
+	if (ret)
+		return ret;
+	ret = imx_phy_reg_write(IMX_CLOCK_RESET_RESET, mmio);
+	if (ret)
+		return ret;
+
+	/* Wait for PHY RX_PLL to be stable */
+	do {
+		usleep_range(100, 200);
+		ret = imx_phy_reg_addressing(IMX_LANE0_OUT_STAT, mmio);
+		if (ret)
+			return ret;
+		ret = imx_phy_reg_read(&val, mmio);
+		if (ret)
+			return ret;
+		if (val & IMX_LANE0_OUT_STAT_RX_PLL_STATE)
+			break;
+	} while (--timeout);
+
+	return timeout ? 0 : -ETIMEDOUT;
+}
+
 static int imx_sata_enable(struct ahci_host_priv *hpriv)
 {
 	struct imx_ahci_priv *imxpriv = hpriv->plat_data;
+	struct device *dev = &imxpriv->ahci_pdev->dev;
 	int ret;
 
 	if (imxpriv->no_device)
@@ -101,6 +257,14 @@ static int imx_sata_enable(struct ahci_host_priv *hpriv)
 		regmap_update_bits(imxpriv->gpr, IOMUXC_GPR13,
 				   IMX6Q_GPR13_SATA_MPLL_CLK_EN,
 				   IMX6Q_GPR13_SATA_MPLL_CLK_EN);
+
+		usleep_range(100, 200);
+
+		ret = imx_sata_phy_reset(hpriv);
+		if (ret) {
+			dev_err(dev, "failed to reset phy: %d\n", ret);
+			goto disable_regulator;
+		}
 	}
 
 	usleep_range(1000, 2000);
@@ -156,8 +320,8 @@ static void ahci_imx_error_handler(struct ata_port *ap)
 	 * without full reset once the pddq mode is enabled making it
 	 * impossible to use as part of libata LPM.
 	 */
-	reg_val = readl(mmio + PORT_PHY_CTL);
-	writel(reg_val | PORT_PHY_CTL_PDDQ_LOC, mmio + PORT_PHY_CTL);
+	reg_val = readl(mmio + IMX_P0PHYCR);
+	writel(reg_val | IMX_P0PHYCR_TEST_PDDQ, mmio + IMX_P0PHYCR);
 	imx_sata_disable(hpriv);
 	imxpriv->no_device = true;
 }
@@ -217,6 +381,7 @@ static int imx_ahci_probe(struct platform_device *pdev)
 	if (!imxpriv)
 		return -ENOMEM;
 
+	imxpriv->ahci_pdev = pdev;
 	imxpriv->no_device = false;
 	imxpriv->first_time = true;
 	imxpriv->type = (enum ahci_imx_type)of_id->data;
@@ -248,7 +413,7 @@ static int imx_ahci_probe(struct platform_device *pdev)
 
 	/*
 	 * Configure the HWINIT bits of the HOST_CAP and HOST_PORTS_IMPL,
-	 * and IP vendor specific register HOST_TIMER1MS.
+	 * and IP vendor specific register IMX_TIMER1MS.
 	 * Configure CAP_SSS (support stagered spin up).
 	 * Implement the port0.
 	 * Get the ahb clock rate, and configure the TIMER1MS register.
@@ -265,7 +430,7 @@ static int imx_ahci_probe(struct platform_device *pdev)
 	}
 
 	reg_val = clk_get_rate(imxpriv->ahb_clk) / 1000;
-	writel(reg_val, hpriv->mmio + HOST_TIMER1MS);
+	writel(reg_val, hpriv->mmio + IMX_TIMER1MS);
 
 	ret = ahci_platform_init_host(pdev, hpriv, &ahci_imx_port_info, 0, 0);
 	if (ret)
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index 6bd4f660b4e1..b9861453fc81 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -452,6 +452,13 @@ void ahci_save_initial_config(struct device *dev,
 		cap &= ~HOST_CAP_SNTF;
 	}
 
+	if ((cap2 & HOST_CAP2_SDS) && (hpriv->flags & AHCI_HFLAG_NO_DEVSLP)) {
+		dev_info(dev,
+			 "controller can't do DEVSLP, turning off\n");
+		cap2 &= ~HOST_CAP2_SDS;
+		cap2 &= ~HOST_CAP2_SADM;
+	}
+
 	if (!(cap & HOST_CAP_FBS) && (hpriv->flags & AHCI_HFLAG_YES_FBS)) {
 		dev_info(dev, "controller can do FBS, turning on CAP_FBS\n");
 		cap |= HOST_CAP_FBS;
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 943cc8b83e59..ea83828bfea9 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -6314,6 +6314,8 @@ int ata_host_activate(struct ata_host *host, int irq,
 static void ata_port_detach(struct ata_port *ap)
 {
 	unsigned long flags;
+	struct ata_link *link;
+	struct ata_device *dev;
 
 	if (!ap->ops->error_handler)
 		goto skip_eh;
@@ -6333,6 +6335,13 @@ static void ata_port_detach(struct ata_port *ap)
 	cancel_delayed_work_sync(&ap->hotplug_task);
 
  skip_eh:
+	/* clean up zpodd on port removal */
+	ata_for_each_link(link, ap, HOST_FIRST) {
+		ata_for_each_dev(dev, link, ALL) {
+			if (zpodd_dev_enabled(dev))
+				zpodd_exit(dev);
+		}
+	}
 	if (ap->pmp_link) {
 		int i;
 		for (i = 0; i < SATA_PMP_MAX_PORTS; i++)
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 6d8a87f252de..cb9b1f8326c3 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -144,11 +144,11 @@ static void virtblk_done(struct virtqueue *vq)
 		if (unlikely(virtqueue_is_broken(vq)))
 			break;
 	} while (!virtqueue_enable_cb(vq));
-	spin_unlock_irqrestore(&vblk->vq_lock, flags);
 
 	/* In case queue is stopped waiting for more buffers. */
 	if (req_done)
 		blk_mq_start_stopped_hw_queues(vblk->disk->queue);
+	spin_unlock_irqrestore(&vblk->vq_lock, flags);
 }
 
 static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
@@ -202,8 +202,8 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *req)
 	err = __virtblk_add_req(vblk->vq, vbr, vbr->sg, num);
 	if (err) {
 		virtqueue_kick(vblk->vq);
-		spin_unlock_irqrestore(&vblk->vq_lock, flags);
 		blk_mq_stop_hw_queue(hctx);
+		spin_unlock_irqrestore(&vblk->vq_lock, flags);
 		/* Out of mem doesn't actually happen, since we fall back
 		 * to direct descriptors */
 		if (err == -ENOMEM || err == -ENOSPC)
diff --git a/drivers/bus/mvebu-mbus.c b/drivers/bus/mvebu-mbus.c
index 293e2e0a0a87..00b73448b22e 100644
--- a/drivers/bus/mvebu-mbus.c
+++ b/drivers/bus/mvebu-mbus.c
@@ -56,6 +56,7 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/debugfs.h>
+#include <linux/log2.h>
 
 /*
  * DDR target is the same on all platforms.
@@ -222,12 +223,6 @@ static int mvebu_mbus_window_conflicts(struct mvebu_mbus_state *mbus,
 		 */
 		if ((u64)base < wend && end > wbase)
 			return 0;
-
-		/*
-		 * Check if target/attribute conflicts
-		 */
-		if (target == wtarget && attr == wattr)
-			return 0;
 	}
 
 	return 1;
@@ -266,6 +261,17 @@ static int mvebu_mbus_setup_window(struct mvebu_mbus_state *mbus,
 		mbus->soc->win_cfg_offset(win);
 	u32 ctrl, remap_addr;
 
+	if (!is_power_of_2(size)) {
+		WARN(true, "Invalid MBus window size: 0x%zx\n", size);
+		return -EINVAL;
+	}
+
+	if ((base & (phys_addr_t)(size - 1)) != 0) {
+		WARN(true, "Invalid MBus base/size: %pa len 0x%zx\n", &base,
+		     size);
+		return -EINVAL;
+	}
+
 	ctrl = ((size - 1) & WIN_CTRL_SIZE_MASK) |
 		(attr << WIN_CTRL_ATTR_SHIFT)    |
 		(target << WIN_CTRL_TGT_SHIFT)   |
@@ -413,6 +419,10 @@ static int mvebu_devs_debug_show(struct seq_file *seq, void *v)
 			   win, (unsigned long long)wbase,
 			   (unsigned long long)(wbase + wsize), wtarget, wattr);
 
+		if (!is_power_of_2(wsize) ||
+		    ((wbase & (u64)(wsize - 1)) != 0))
+			seq_puts(seq, " (Invalid base/size!!)");
+
 		if (win < mbus->soc->num_remappable_wins) {
 			seq_printf(seq, " (remap %016llx)\n",
 				   (unsigned long long)wremap);
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 6b75713d953a..102c50d38902 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -995,8 +995,11 @@ retry:
 		ibytes = min_t(size_t, ibytes, have_bytes - reserved);
 	if (ibytes < min)
 		ibytes = 0;
-	entropy_count = max_t(int, 0,
-			      entropy_count - (ibytes << (ENTROPY_SHIFT + 3)));
+	if (have_bytes >= ibytes + reserved)
+		entropy_count -= ibytes << (ENTROPY_SHIFT + 3);
+	else
+		entropy_count = reserved << (ENTROPY_SHIFT + 3);
+
 	if (cmpxchg(&r->entropy_count, orig, entropy_count) != orig)
 		goto retry;
 
diff --git a/drivers/char/tpm/tpm_ppi.c b/drivers/char/tpm/tpm_ppi.c
index b3ea223585bd..61dcc8011ec7 100644
--- a/drivers/char/tpm/tpm_ppi.c
+++ b/drivers/char/tpm/tpm_ppi.c
@@ -328,13 +328,11 @@ int tpm_add_ppi(struct kobject *parent)
 	/* Cache TPM ACPI handle and version string */
 	acpi_walk_namespace(ACPI_TYPE_DEVICE, ACPI_ROOT_OBJECT, ACPI_UINT32_MAX,
 			    ppi_callback, NULL, NULL, &tpm_ppi_handle);
-	if (tpm_ppi_handle == NULL)
-		return -ENODEV;
-
-	return sysfs_create_group(parent, &ppi_attr_grp);
+	return tpm_ppi_handle ? sysfs_create_group(parent, &ppi_attr_grp) : 0;
 }
 
 void tpm_remove_ppi(struct kobject *parent)
 {
-	sysfs_remove_group(parent, &ppi_attr_grp);
+	if (tpm_ppi_handle)
+		sysfs_remove_group(parent, &ppi_attr_grp);
 }
diff --git a/drivers/clk/bcm/clk-kona-setup.c b/drivers/clk/bcm/clk-kona-setup.c
index c7607feb18dd..54a06526f64f 100644
--- a/drivers/clk/bcm/clk-kona-setup.c
+++ b/drivers/clk/bcm/clk-kona-setup.c
@@ -27,7 +27,7 @@ LIST_HEAD(ccu_list);	/* The list of set up CCUs */
 
 static bool clk_requires_trigger(struct kona_clk *bcm_clk)
 {
-	struct peri_clk_data *peri = bcm_clk->peri;
+	struct peri_clk_data *peri = bcm_clk->u.peri;
 	struct bcm_clk_sel *sel;
 	struct bcm_clk_div *div;
 
@@ -63,7 +63,7 @@ static bool peri_clk_data_offsets_valid(struct kona_clk *bcm_clk)
 	u32 limit;
 
 	BUG_ON(bcm_clk->type != bcm_clk_peri);
-	peri = bcm_clk->peri;
+	peri = bcm_clk->u.peri;
 	name = bcm_clk->name;
 	range = bcm_clk->ccu->range;
 
@@ -81,19 +81,19 @@ static bool peri_clk_data_offsets_valid(struct kona_clk *bcm_clk)
 
 	div = &peri->div;
 	if (divider_exists(div)) {
-		if (div->offset > limit) {
+		if (div->u.s.offset > limit) {
 			pr_err("%s: bad divider offset for %s (%u > %u)\n",
-				__func__, name, div->offset, limit);
+				__func__, name, div->u.s.offset, limit);
 			return false;
 		}
 	}
 
 	div = &peri->pre_div;
 	if (divider_exists(div)) {
-		if (div->offset > limit) {
+		if (div->u.s.offset > limit) {
 			pr_err("%s: bad pre-divider offset for %s "
 					"(%u > %u)\n",
-				__func__, name, div->offset, limit);
+				__func__, name, div->u.s.offset, limit);
 			return false;
 		}
 	}
@@ -249,21 +249,22 @@ static bool div_valid(struct bcm_clk_div *div, const char *field_name,
 {
 	if (divider_is_fixed(div)) {
 		/* Any fixed divider value but 0 is OK */
-		if (div->fixed == 0) {
+		if (div->u.fixed == 0) {
 			pr_err("%s: bad %s fixed value 0 for %s\n", __func__,
 				field_name, clock_name);
 			return false;
 		}
 		return true;
 	}
-	if (!bitfield_valid(div->shift, div->width, field_name, clock_name))
+	if (!bitfield_valid(div->u.s.shift, div->u.s.width,
+				field_name, clock_name))
 		return false;
 
 	if (divider_has_fraction(div))
-		if (div->frac_width > div->width) {
+		if (div->u.s.frac_width > div->u.s.width) {
 			pr_warn("%s: bad %s fraction width for %s (%u > %u)\n",
 				__func__, field_name, clock_name,
-				div->frac_width, div->width);
+				div->u.s.frac_width, div->u.s.width);
 			return false;
 		}
 
@@ -278,7 +279,7 @@ static bool div_valid(struct bcm_clk_div *div, const char *field_name,
  */
 static bool kona_dividers_valid(struct kona_clk *bcm_clk)
 {
-	struct peri_clk_data *peri = bcm_clk->peri;
+	struct peri_clk_data *peri = bcm_clk->u.peri;
 	struct bcm_clk_div *div;
 	struct bcm_clk_div *pre_div;
 	u32 limit;
@@ -295,7 +296,7 @@ static bool kona_dividers_valid(struct kona_clk *bcm_clk)
 
 	limit = BITS_PER_BYTE * sizeof(u32);
 
-	return div->frac_width + pre_div->frac_width <= limit;
+	return div->u.s.frac_width + pre_div->u.s.frac_width <= limit;
 }
 
 
@@ -328,7 +329,7 @@ peri_clk_data_valid(struct kona_clk *bcm_clk)
 	if (!peri_clk_data_offsets_valid(bcm_clk))
 		return false;
 
-	peri = bcm_clk->peri;
+	peri = bcm_clk->u.peri;
 	name = bcm_clk->name;
 	gate = &peri->gate;
 	if (gate_exists(gate) && !gate_valid(gate, "gate", name))
@@ -588,12 +589,12 @@ static void bcm_clk_teardown(struct kona_clk *bcm_clk)
 {
 	switch (bcm_clk->type) {
 	case bcm_clk_peri:
-		peri_clk_teardown(bcm_clk->data, &bcm_clk->init_data);
+		peri_clk_teardown(bcm_clk->u.data, &bcm_clk->init_data);
 		break;
 	default:
 		break;
 	}
-	bcm_clk->data = NULL;
+	bcm_clk->u.data = NULL;
 	bcm_clk->type = bcm_clk_none;
 }
 
@@ -644,7 +645,7 @@ struct clk *kona_clk_setup(struct ccu_data *ccu, const char *name,
 		break;
 	}
 	bcm_clk->type = type;
-	bcm_clk->data = data;
+	bcm_clk->u.data = data;
 
 	/* Make sure everything makes sense before we set it up */
 	if (!kona_clk_valid(bcm_clk)) {
diff --git a/drivers/clk/bcm/clk-kona.c b/drivers/clk/bcm/clk-kona.c
index e3d339e08309..db11a87449f2 100644
--- a/drivers/clk/bcm/clk-kona.c
+++ b/drivers/clk/bcm/clk-kona.c
@@ -61,7 +61,7 @@ u64 do_div_round_closest(u64 dividend, unsigned long divisor)
 /* Convert a divider into the scaled divisor value it represents. */
 static inline u64 scaled_div_value(struct bcm_clk_div *div, u32 reg_div)
 {
-	return (u64)reg_div + ((u64)1 << div->frac_width);
+	return (u64)reg_div + ((u64)1 << div->u.s.frac_width);
 }
 
 /*
@@ -77,7 +77,7 @@ u64 scaled_div_build(struct bcm_clk_div *div, u32 div_value, u32 billionths)
 	BUG_ON(billionths >= BILLION);
 
 	combined = (u64)div_value * BILLION + billionths;
-	combined <<= div->frac_width;
+	combined <<= div->u.s.frac_width;
 
 	return do_div_round_closest(combined, BILLION);
 }
@@ -87,7 +87,7 @@ static inline u64
 scaled_div_min(struct bcm_clk_div *div)
 {
 	if (divider_is_fixed(div))
-		return (u64)div->fixed;
+		return (u64)div->u.fixed;
 
 	return scaled_div_value(div, 0);
 }
@@ -98,9 +98,9 @@ u64 scaled_div_max(struct bcm_clk_div *div)
 	u32 reg_div;
 
 	if (divider_is_fixed(div))
-		return (u64)div->fixed;
+		return (u64)div->u.fixed;
 
-	reg_div = ((u32)1 << div->width) - 1;
+	reg_div = ((u32)1 << div->u.s.width) - 1;
 
 	return scaled_div_value(div, reg_div);
 }
@@ -115,7 +115,7 @@ divider(struct bcm_clk_div *div, u64 scaled_div)
 	BUG_ON(scaled_div < scaled_div_min(div));
 	BUG_ON(scaled_div > scaled_div_max(div));
 
-	return (u32)(scaled_div - ((u64)1 << div->frac_width));
+	return (u32)(scaled_div - ((u64)1 << div->u.s.frac_width));
 }
 
 /* Return a rate scaled for use when dividing by a scaled divisor. */
@@ -125,7 +125,7 @@ scale_rate(struct bcm_clk_div *div, u32 rate)
 	if (divider_is_fixed(div))
 		return (u64)rate;
 
-	return (u64)rate << div->frac_width;
+	return (u64)rate << div->u.s.frac_width;
 }
 
 /* CCU access */
@@ -398,14 +398,14 @@ static u64 divider_read_scaled(struct ccu_data *ccu, struct bcm_clk_div *div)
 	u32 reg_div;
 
 	if (divider_is_fixed(div))
-		return (u64)div->fixed;
+		return (u64)div->u.fixed;
 
 	flags = ccu_lock(ccu);
-	reg_val = __ccu_read(ccu, div->offset);
+	reg_val = __ccu_read(ccu, div->u.s.offset);
 	ccu_unlock(ccu, flags);
 
 	/* Extract the full divider field from the register value */
-	reg_div = bitfield_extract(reg_val, div->shift, div->width);
+	reg_div = bitfield_extract(reg_val, div->u.s.shift, div->u.s.width);
 
 	/* Return the scaled divisor value it represents */
 	return scaled_div_value(div, reg_div);
@@ -433,16 +433,17 @@ static int __div_commit(struct ccu_data *ccu, struct bcm_clk_gate *gate,
 	 * state was defined in the device tree, we just find out
 	 * what its current value is rather than updating it.
 	 */
-	if (div->scaled_div == BAD_SCALED_DIV_VALUE) {
-		reg_val = __ccu_read(ccu, div->offset);
-		reg_div = bitfield_extract(reg_val, div->shift, div->width);
-		div->scaled_div = scaled_div_value(div, reg_div);
+	if (div->u.s.scaled_div == BAD_SCALED_DIV_VALUE) {
+		reg_val = __ccu_read(ccu, div->u.s.offset);
+		reg_div = bitfield_extract(reg_val, div->u.s.shift,
+						div->u.s.width);
+		div->u.s.scaled_div = scaled_div_value(div, reg_div);
 
 		return 0;
 	}
 
 	/* Convert the scaled divisor to the value we need to record */
-	reg_div = divider(div, div->scaled_div);
+	reg_div = divider(div, div->u.s.scaled_div);
 
 	/* Clock needs to be enabled before changing the rate */
 	enabled = __is_clk_gate_enabled(ccu, gate);
@@ -452,9 +453,10 @@ static int __div_commit(struct ccu_data *ccu, struct bcm_clk_gate *gate,
 	}
 
 	/* Replace the divider value and record the result */
-	reg_val = __ccu_read(ccu, div->offset);
-	reg_val = bitfield_replace(reg_val, div->shift, div->width, reg_div);
-	__ccu_write(ccu, div->offset, reg_val);
+	reg_val = __ccu_read(ccu, div->u.s.offset);
+	reg_val = bitfield_replace(reg_val, div->u.s.shift, div->u.s.width,
+					reg_div);
+	__ccu_write(ccu, div->u.s.offset, reg_val);
 
 	/* If the trigger fails we still want to disable the gate */
 	if (!__clk_trigger(ccu, trig))
@@ -490,11 +492,11 @@ static int divider_write(struct ccu_data *ccu, struct bcm_clk_gate *gate,
 
 	BUG_ON(divider_is_fixed(div));
 
-	previous = div->scaled_div;
+	previous = div->u.s.scaled_div;
 	if (previous == scaled_div)
 		return 0;	/* No change */
 
-	div->scaled_div = scaled_div;
+	div->u.s.scaled_div = scaled_div;
 
 	flags = ccu_lock(ccu);
 	__ccu_write_enable(ccu);
@@ -505,7 +507,7 @@ static int divider_write(struct ccu_data *ccu, struct bcm_clk_gate *gate,
 	ccu_unlock(ccu, flags);
 
 	if (ret)
-		div->scaled_div = previous;		/* Revert the change */
+		div->u.s.scaled_div = previous;		/* Revert the change */
 
 	return ret;
 
@@ -802,7 +804,7 @@ static int selector_write(struct ccu_data *ccu, struct bcm_clk_gate *gate,
 static int kona_peri_clk_enable(struct clk_hw *hw)
 {
 	struct kona_clk *bcm_clk = to_kona_clk(hw);
-	struct bcm_clk_gate *gate = &bcm_clk->peri->gate;
+	struct bcm_clk_gate *gate = &bcm_clk->u.peri->gate;
 
 	return clk_gate(bcm_clk->ccu, bcm_clk->name, gate, true);
 }
@@ -810,7 +812,7 @@ static int kona_peri_clk_enable(struct clk_hw *hw)
 static void kona_peri_clk_disable(struct clk_hw *hw)
 {
 	struct kona_clk *bcm_clk = to_kona_clk(hw);
-	struct bcm_clk_gate *gate = &bcm_clk->peri->gate;
+	struct bcm_clk_gate *gate = &bcm_clk->u.peri->gate;
 
 	(void)clk_gate(bcm_clk->ccu, bcm_clk->name, gate, false);
 }
@@ -818,7 +820,7 @@ static void kona_peri_clk_disable(struct clk_hw *hw)
 static int kona_peri_clk_is_enabled(struct clk_hw *hw)
 {
 	struct kona_clk *bcm_clk = to_kona_clk(hw);
-	struct bcm_clk_gate *gate = &bcm_clk->peri->gate;
+	struct bcm_clk_gate *gate = &bcm_clk->u.peri->gate;
 
 	return is_clk_gate_enabled(bcm_clk->ccu, gate) ? 1 : 0;
 }
@@ -827,7 +829,7 @@ static unsigned long kona_peri_clk_recalc_rate(struct clk_hw *hw,
 			unsigned long parent_rate)
 {
 	struct kona_clk *bcm_clk = to_kona_clk(hw);
-	struct peri_clk_data *data = bcm_clk->peri;
+	struct peri_clk_data *data = bcm_clk->u.peri;
 
 	return clk_recalc_rate(bcm_clk->ccu, &data->div, &data->pre_div,
 				parent_rate);
@@ -837,20 +839,20 @@ static long kona_peri_clk_round_rate(struct clk_hw *hw, unsigned long rate,
 			unsigned long *parent_rate)
 {
 	struct kona_clk *bcm_clk = to_kona_clk(hw);
-	struct bcm_clk_div *div = &bcm_clk->peri->div;
+	struct bcm_clk_div *div = &bcm_clk->u.peri->div;
 
 	if (!divider_exists(div))
 		return __clk_get_rate(hw->clk);
 
 	/* Quietly avoid a zero rate */
-	return round_rate(bcm_clk->ccu, div, &bcm_clk->peri->pre_div,
+	return round_rate(bcm_clk->ccu, div, &bcm_clk->u.peri->pre_div,
 				rate ? rate : 1, *parent_rate, NULL);
 }
 
 static int kona_peri_clk_set_parent(struct clk_hw *hw, u8 index)
 {
 	struct kona_clk *bcm_clk = to_kona_clk(hw);
-	struct peri_clk_data *data = bcm_clk->peri;
+	struct peri_clk_data *data = bcm_clk->u.peri;
 	struct bcm_clk_sel *sel = &data->sel;
 	struct bcm_clk_trig *trig;
 	int ret;
@@ -884,7 +886,7 @@ static int kona_peri_clk_set_parent(struct clk_hw *hw, u8 index)
 static u8 kona_peri_clk_get_parent(struct clk_hw *hw)
 {
 	struct kona_clk *bcm_clk = to_kona_clk(hw);
-	struct peri_clk_data *data = bcm_clk->peri;
+	struct peri_clk_data *data = bcm_clk->u.peri;
 	u8 index;
 
 	index = selector_read_index(bcm_clk->ccu, &data->sel);
@@ -897,7 +899,7 @@ static int kona_peri_clk_set_rate(struct clk_hw *hw, unsigned long rate,
 			unsigned long parent_rate)
 {
 	struct kona_clk *bcm_clk = to_kona_clk(hw);
-	struct peri_clk_data *data = bcm_clk->peri;
+	struct peri_clk_data *data = bcm_clk->u.peri;
 	struct bcm_clk_div *div = &data->div;
 	u64 scaled_div = 0;
 	int ret;
@@ -958,7 +960,7 @@ struct clk_ops kona_peri_clk_ops = {
 static bool __peri_clk_init(struct kona_clk *bcm_clk)
 {
 	struct ccu_data *ccu = bcm_clk->ccu;
-	struct peri_clk_data *peri = bcm_clk->peri;
+	struct peri_clk_data *peri = bcm_clk->u.peri;
 	const char *name = bcm_clk->name;
 	struct bcm_clk_trig *trig;
 
diff --git a/drivers/clk/bcm/clk-kona.h b/drivers/clk/bcm/clk-kona.h
index 5e139adc3dc5..dee690951bb6 100644
--- a/drivers/clk/bcm/clk-kona.h
+++ b/drivers/clk/bcm/clk-kona.h
@@ -57,7 +57,7 @@
 #define divider_exists(div)		FLAG_TEST(div, DIV, EXISTS)
 #define divider_is_fixed(div)		FLAG_TEST(div, DIV, FIXED)
 #define divider_has_fraction(div)	(!divider_is_fixed(div) && \
-						(div)->frac_width > 0)
+						(div)->u.s.frac_width > 0)
 
 #define selector_exists(sel)		((sel)->width != 0)
 #define trigger_exists(trig)		FLAG_TEST(trig, TRIG, EXISTS)
@@ -244,9 +244,9 @@ struct bcm_clk_div {
 			u32 frac_width;	/* field fraction width */
 
 			u64 scaled_div;	/* scaled divider value */
-		};
+		} s;
 		u32 fixed;	/* non-zero fixed divider value */
-	};
+	} u;
 	u32 flags;		/* BCM_CLK_DIV_FLAGS_* below */
 };
 
@@ -263,28 +263,28 @@ struct bcm_clk_div {
 /* A fixed (non-zero) divider */
 #define FIXED_DIVIDER(_value)						\
 	{								\
-		.fixed = (_value),					\
+		.u.fixed = (_value),					\
 		.flags = FLAG(DIV, EXISTS)|FLAG(DIV, FIXED),		\
 	}
 
 /* A divider with an integral divisor */
 #define DIVIDER(_offset, _shift, _width)				\
 	{								\
-		.offset = (_offset),					\
-		.shift = (_shift),					\
-		.width = (_width),					\
-		.scaled_div = BAD_SCALED_DIV_VALUE,			\
+		.u.s.offset = (_offset),				\
+		.u.s.shift = (_shift),					\
+		.u.s.width = (_width),					\
+		.u.s.scaled_div = BAD_SCALED_DIV_VALUE,			\
 		.flags = FLAG(DIV, EXISTS),				\
 	}
 
 /* A divider whose divisor has an integer and fractional part */
 #define FRAC_DIVIDER(_offset, _shift, _width, _frac_width)		\
 	{								\
-		.offset = (_offset),					\
-		.shift = (_shift),					\
-		.width = (_width),					\
-		.frac_width = (_frac_width),				\
-		.scaled_div = BAD_SCALED_DIV_VALUE,			\
+		.u.s.offset = (_offset),				\
+		.u.s.shift = (_shift),					\
+		.u.s.width = (_width),					\
+		.u.s.frac_width = (_frac_width),			\
+		.u.s.scaled_div = BAD_SCALED_DIV_VALUE,			\
 		.flags = FLAG(DIV, EXISTS),				\
 	}
 
@@ -380,7 +380,7 @@ struct kona_clk {
 	union {
 		void *data;
 		struct peri_clk_data *peri;
-	};
+	} u;
 };
 #define to_kona_clk(_hw) \
 	container_of(_hw, struct kona_clk, hw)
diff --git a/drivers/clk/clk-divider.c b/drivers/clk/clk-divider.c
index ec22112e569f..3fbee4540228 100644
--- a/drivers/clk/clk-divider.c
+++ b/drivers/clk/clk-divider.c
@@ -144,6 +144,37 @@ static bool _is_valid_div(struct clk_divider *divider, unsigned int div)
 	return true;
 }
 
+static int _round_up_table(const struct clk_div_table *table, int div)
+{
+	const struct clk_div_table *clkt;
+	int up = INT_MAX;
+
+	for (clkt = table; clkt->div; clkt++) {
+		if (clkt->div == div)
+			return clkt->div;
+		else if (clkt->div < div)
+			continue;
+
+		if ((clkt->div - div) < (up - div))
+			up = clkt->div;
+	}
+
+	return up;
+}
+
+static int _div_round_up(struct clk_divider *divider,
+		unsigned long parent_rate, unsigned long rate)
+{
+	int div = DIV_ROUND_UP(parent_rate, rate);
+
+	if (divider->flags & CLK_DIVIDER_POWER_OF_TWO)
+		div = __roundup_pow_of_two(div);
+	if (divider->table)
+		div = _round_up_table(divider->table, div);
+
+	return div;
+}
+
 static int clk_divider_bestdiv(struct clk_hw *hw, unsigned long rate,
 		unsigned long *best_parent_rate)
 {
@@ -159,7 +190,7 @@ static int clk_divider_bestdiv(struct clk_hw *hw, unsigned long rate,
 
 	if (!(__clk_get_flags(hw->clk) & CLK_SET_RATE_PARENT)) {
 		parent_rate = *best_parent_rate;
-		bestdiv = DIV_ROUND_UP(parent_rate, rate);
+		bestdiv = _div_round_up(divider, parent_rate, rate);
 		bestdiv = bestdiv == 0 ? 1 : bestdiv;
 		bestdiv = bestdiv > maxdiv ? maxdiv : bestdiv;
 		return bestdiv;
@@ -219,6 +250,10 @@ static int clk_divider_set_rate(struct clk_hw *hw, unsigned long rate,
 	u32 val;
 
 	div = DIV_ROUND_UP(parent_rate, rate);
+
+	if (!_is_valid_div(divider, div))
+		return -EINVAL;
+
 	value = _get_val(divider, div);
 
 	if (value > div_mask(divider))
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index dff0373f53c1..7cf2c093cc54 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -1984,9 +1984,28 @@ struct clk *__clk_register(struct device *dev, struct clk_hw *hw)
 }
 EXPORT_SYMBOL_GPL(__clk_register);
 
-static int _clk_register(struct device *dev, struct clk_hw *hw, struct clk *clk)
+/**
+ * clk_register - allocate a new clock, register it and return an opaque cookie
+ * @dev: device that is registering this clock
+ * @hw: link to hardware-specific clock data
+ *
+ * clk_register is the primary interface for populating the clock tree with new
+ * clock nodes.  It returns a pointer to the newly allocated struct clk which
+ * cannot be dereferenced by driver code but may be used in conjuction with the
+ * rest of the clock API.  In the event of an error clk_register will return an
+ * error code; drivers must test for an error code after calling clk_register.
+ */
+struct clk *clk_register(struct device *dev, struct clk_hw *hw)
 {
 	int i, ret;
+	struct clk *clk;
+
+	clk = kzalloc(sizeof(*clk), GFP_KERNEL);
+	if (!clk) {
+		pr_err("%s: could not allocate clk\n", __func__);
+		ret = -ENOMEM;
+		goto fail_out;
+	}
 
 	clk->name = kstrdup(hw->init->name, GFP_KERNEL);
 	if (!clk->name) {
@@ -2026,7 +2045,7 @@ static int _clk_register(struct device *dev, struct clk_hw *hw, struct clk *clk)
 
 	ret = __clk_init(dev, clk);
 	if (!ret)
-		return 0;
+		return clk;
 
 fail_parent_names_copy:
 	while (--i >= 0)
@@ -2035,36 +2054,6 @@ fail_parent_names_copy:
 fail_parent_names:
 	kfree(clk->name);
 fail_name:
-	return ret;
-}
-
-/**
- * clk_register - allocate a new clock, register it and return an opaque cookie
- * @dev: device that is registering this clock
- * @hw: link to hardware-specific clock data
- *
- * clk_register is the primary interface for populating the clock tree with new
- * clock nodes.  It returns a pointer to the newly allocated struct clk which
- * cannot be dereferenced by driver code but may be used in conjuction with the
- * rest of the clock API.  In the event of an error clk_register will return an
- * error code; drivers must test for an error code after calling clk_register.
- */
-struct clk *clk_register(struct device *dev, struct clk_hw *hw)
-{
-	int ret;
-	struct clk *clk;
-
-	clk = kzalloc(sizeof(*clk), GFP_KERNEL);
-	if (!clk) {
-		pr_err("%s: could not allocate clk\n", __func__);
-		ret = -ENOMEM;
-		goto fail_out;
-	}
-
-	ret = _clk_register(dev, hw, clk);
-	if (!ret)
-		return clk;
-
 	kfree(clk);
 fail_out:
 	return ERR_PTR(ret);
@@ -2151,9 +2140,10 @@ void clk_unregister(struct clk *clk)
 
 	if (!hlist_empty(&clk->children)) {
 		struct clk *child;
+		struct hlist_node *t;
 
 		/* Reparent all children to the orphan list. */
-		hlist_for_each_entry(child, &clk->children, child_node)
+		hlist_for_each_entry_safe(child, t, &clk->children, child_node)
 			clk_set_parent(child, NULL);
 	}
 
@@ -2173,7 +2163,7 @@ EXPORT_SYMBOL_GPL(clk_unregister);
 
 static void devm_clk_release(struct device *dev, void *res)
 {
-	clk_unregister(res);
+	clk_unregister(*(struct clk **)res);
 }
 
 /**
@@ -2188,18 +2178,18 @@ static void devm_clk_release(struct device *dev, void *res)
 struct clk *devm_clk_register(struct device *dev, struct clk_hw *hw)
 {
 	struct clk *clk;
-	int ret;
+	struct clk **clkp;
 
-	clk = devres_alloc(devm_clk_release, sizeof(*clk), GFP_KERNEL);
-	if (!clk)
+	clkp = devres_alloc(devm_clk_release, sizeof(*clkp), GFP_KERNEL);
+	if (!clkp)
 		return ERR_PTR(-ENOMEM);
 
-	ret = _clk_register(dev, hw, clk);
-	if (!ret) {
-		devres_add(dev, clk);
+	clk = clk_register(dev, hw);
+	if (!IS_ERR(clk)) {
+		*clkp = clk;
+		devres_add(dev, clkp);
 	} else {
-		devres_free(clk);
-		clk = ERR_PTR(ret);
+		devres_free(clkp);
 	}
 
 	return clk;
diff --git a/drivers/clk/shmobile/clk-mstp.c b/drivers/clk/shmobile/clk-mstp.c
index 2e5810c88d11..1f6324e29a80 100644
--- a/drivers/clk/shmobile/clk-mstp.c
+++ b/drivers/clk/shmobile/clk-mstp.c
@@ -156,6 +156,7 @@ cpg_mstp_clock_register(const char *name, const char *parent_name,
 static void __init cpg_mstp_clocks_init(struct device_node *np)
 {
 	struct mstp_clock_group *group;
+	const char *idxname;
 	struct clk **clks;
 	unsigned int i;
 
@@ -184,6 +185,11 @@ static void __init cpg_mstp_clocks_init(struct device_node *np)
 	for (i = 0; i < MSTP_MAX_CLOCKS; ++i)
 		clks[i] = ERR_PTR(-ENOENT);
 
+	if (of_find_property(np, "clock-indices", &i))
+		idxname = "clock-indices";
+	else
+		idxname = "renesas,clock-indices";
+
 	for (i = 0; i < MSTP_MAX_CLOCKS; ++i) {
 		const char *parent_name;
 		const char *name;
@@ -197,8 +203,7 @@ static void __init cpg_mstp_clocks_init(struct device_node *np)
 			continue;
 
 		parent_name = of_clk_get_parent_name(np, i);
-		ret = of_property_read_u32_index(np, "renesas,clock-indices", i,
-						 &clkidx);
+		ret = of_property_read_u32_index(np, idxname, i, &clkidx);
 		if (parent_name == NULL || ret < 0)
 			break;
 
diff --git a/drivers/clk/socfpga/clk-pll.c b/drivers/clk/socfpga/clk-pll.c
index 88dafb5e9627..de6da957a09d 100644
--- a/drivers/clk/socfpga/clk-pll.c
+++ b/drivers/clk/socfpga/clk-pll.c
@@ -20,6 +20,7 @@
 #include <linux/clk-provider.h>
 #include <linux/io.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
 
 #include "clk.h"
 
@@ -43,6 +44,8 @@
 
 #define to_socfpga_clk(p) container_of(p, struct socfpga_pll, hw.hw)
 
+void __iomem *clk_mgr_base_addr;
+
 static unsigned long clk_pll_recalc_rate(struct clk_hw *hwclk,
 					 unsigned long parent_rate)
 {
@@ -87,6 +90,7 @@ static __init struct clk *__socfpga_pll_init(struct device_node *node,
 	const char *clk_name = node->name;
 	const char *parent_name[SOCFPGA_MAX_PARENTS];
 	struct clk_init_data init;
+	struct device_node *clkmgr_np;
 	int rc;
 	int i = 0;
 
@@ -96,6 +100,9 @@ static __init struct clk *__socfpga_pll_init(struct device_node *node,
 	if (WARN_ON(!pll_clk))
 		return NULL;
 
+	clkmgr_np = of_find_compatible_node(NULL, NULL, "altr,clk-mgr");
+	clk_mgr_base_addr = of_iomap(clkmgr_np, 0);
+	BUG_ON(!clk_mgr_base_addr);
 	pll_clk->hw.reg = clk_mgr_base_addr + reg;
 
 	of_property_read_string(node, "clock-output-names", &clk_name);
diff --git a/drivers/clk/socfpga/clk.c b/drivers/clk/socfpga/clk.c
index 35a960a993f9..43db947e5f0e 100644
--- a/drivers/clk/socfpga/clk.c
+++ b/drivers/clk/socfpga/clk.c
@@ -17,28 +17,11 @@
  * You should have received a copy of the GNU General Public License
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
-#include <linux/clk.h>
-#include <linux/clkdev.h>
-#include <linux/clk-provider.h>
-#include <linux/io.h>
 #include <linux/of.h>
-#include <linux/of_address.h>
 
 #include "clk.h"
 
-void __iomem *clk_mgr_base_addr;
-
-static const struct of_device_id socfpga_child_clocks[] __initconst = {
-	{ .compatible = "altr,socfpga-pll-clock", socfpga_pll_init, },
-	{ .compatible = "altr,socfpga-perip-clk", socfpga_periph_init, },
-	{ .compatible = "altr,socfpga-gate-clk", socfpga_gate_init, },
-	{},
-};
-
-static void __init socfpga_clkmgr_init(struct device_node *node)
-{
-	clk_mgr_base_addr = of_iomap(node, 0);
-	of_clk_init(socfpga_child_clocks);
-}
-CLK_OF_DECLARE(socfpga_mgr, "altr,clk-mgr", socfpga_clkmgr_init);
+CLK_OF_DECLARE(socfpga_pll_clk, "altr,socfpga-pll-clock", socfpga_pll_init);
+CLK_OF_DECLARE(socfpga_perip_clk, "altr,socfpga-perip-clk", socfpga_periph_init);
+CLK_OF_DECLARE(socfpga_gate_clk, "altr,socfpga-gate-clk", socfpga_gate_init);
 
diff --git a/drivers/clk/st/clkgen-pll.c b/drivers/clk/st/clkgen-pll.c
index bca0a0badbfa..a886702f7c8b 100644
--- a/drivers/clk/st/clkgen-pll.c
+++ b/drivers/clk/st/clkgen-pll.c
@@ -521,8 +521,10 @@ static struct clk * __init clkgen_odf_register(const char *parent_name,
 	gate->lock = odf_lock;
 
 	div = kzalloc(sizeof(*div), GFP_KERNEL);
-	if (!div)
+	if (!div) {
+		kfree(gate);
 		return ERR_PTR(-ENOMEM);
+	}
 
 	div->flags = CLK_DIVIDER_ONE_BASED | CLK_DIVIDER_ALLOW_ZERO;
 	div->reg = reg + pll_data->odf[odf].offset;
diff --git a/drivers/clk/tegra/clk-pll.c b/drivers/clk/tegra/clk-pll.c
index 0d20241e0770..6aad8abc69a2 100644
--- a/drivers/clk/tegra/clk-pll.c
+++ b/drivers/clk/tegra/clk-pll.c
@@ -58,9 +58,9 @@
 #define PLLDU_LFCON_SET_DIVN 600
 
 #define PLLE_BASE_DIVCML_SHIFT 24
-#define PLLE_BASE_DIVCML_WIDTH 4
+#define PLLE_BASE_DIVCML_MASK 0xf
 #define PLLE_BASE_DIVP_SHIFT 16
-#define PLLE_BASE_DIVP_WIDTH 7
+#define PLLE_BASE_DIVP_WIDTH 6
 #define PLLE_BASE_DIVN_SHIFT 8
 #define PLLE_BASE_DIVN_WIDTH 8
 #define PLLE_BASE_DIVM_SHIFT 0
@@ -183,6 +183,14 @@
 #define divp_mask(p) (p->params->flags & TEGRA_PLLU ? PLLU_POST_DIVP_MASK :\
 		      mask(p->params->div_nmp->divp_width))
 
+#define divm_shift(p) (p)->params->div_nmp->divm_shift
+#define divn_shift(p) (p)->params->div_nmp->divn_shift
+#define divp_shift(p) (p)->params->div_nmp->divp_shift
+
+#define divm_mask_shifted(p) (divm_mask(p) << divm_shift(p))
+#define divn_mask_shifted(p) (divn_mask(p) << divn_shift(p))
+#define divp_mask_shifted(p) (divp_mask(p) << divp_shift(p))
+
 #define divm_max(p) (divm_mask(p))
 #define divn_max(p) (divn_mask(p))
 #define divp_max(p) (1 << (divp_mask(p)))
@@ -476,13 +484,12 @@ static void _update_pll_mnp(struct tegra_clk_pll *pll,
 	} else {
 		val = pll_readl_base(pll);
 
-		val &= ~((divm_mask(pll) << div_nmp->divm_shift) |
-		 (divn_mask(pll) << div_nmp->divn_shift) |
-		 (divp_mask(pll) << div_nmp->divp_shift));
+		val &= ~(divm_mask_shifted(pll) | divn_mask_shifted(pll) |
+			 divp_mask_shifted(pll));
 
-		val |= ((cfg->m << div_nmp->divm_shift) |
-			(cfg->n << div_nmp->divn_shift) |
-			(cfg->p << div_nmp->divp_shift));
+		val |= (cfg->m << divm_shift(pll)) |
+		       (cfg->n << divn_shift(pll)) |
+		       (cfg->p << divp_shift(pll));
 
 		pll_writel_base(val, pll);
 	}
@@ -730,11 +737,12 @@ static int clk_plle_enable(struct clk_hw *hw)
 	if (pll->params->flags & TEGRA_PLLE_CONFIGURE) {
 		/* configure dividers */
 		val = pll_readl_base(pll);
-		val &= ~(divm_mask(pll) | divn_mask(pll) | divp_mask(pll));
-		val &= ~(PLLE_BASE_DIVCML_WIDTH << PLLE_BASE_DIVCML_SHIFT);
-		val |= sel.m << pll->params->div_nmp->divm_shift;
-		val |= sel.n << pll->params->div_nmp->divn_shift;
-		val |= sel.p << pll->params->div_nmp->divp_shift;
+		val &= ~(divp_mask_shifted(pll) | divn_mask_shifted(pll) |
+			 divm_mask_shifted(pll));
+		val &= ~(PLLE_BASE_DIVCML_MASK << PLLE_BASE_DIVCML_SHIFT);
+		val |= sel.m << divm_shift(pll);
+		val |= sel.n << divn_shift(pll);
+		val |= sel.p << divp_shift(pll);
 		val |= sel.cpcon << PLLE_BASE_DIVCML_SHIFT;
 		pll_writel_base(val, pll);
 	}
@@ -745,10 +753,11 @@ static int clk_plle_enable(struct clk_hw *hw)
 	pll_writel_misc(val, pll);
 
 	val = readl(pll->clk_base + PLLE_SS_CTRL);
+	val &= ~PLLE_SS_COEFFICIENTS_MASK;
 	val |= PLLE_SS_DISABLE;
 	writel(val, pll->clk_base + PLLE_SS_CTRL);
 
-	val |= pll_readl_base(pll);
+	val = pll_readl_base(pll);
 	val |= (PLL_BASE_BYPASS | PLL_BASE_ENABLE);
 	pll_writel_base(val, pll);
 
@@ -1292,10 +1301,11 @@ static int clk_plle_tegra114_enable(struct clk_hw *hw)
 	pll_writel(val, PLLE_SS_CTRL, pll);
 
 	val = pll_readl_base(pll);
-	val &= ~(divm_mask(pll) | divn_mask(pll) | divp_mask(pll));
-	val &= ~(PLLE_BASE_DIVCML_WIDTH << PLLE_BASE_DIVCML_SHIFT);
-	val |= sel.m << pll->params->div_nmp->divm_shift;
-	val |= sel.n << pll->params->div_nmp->divn_shift;
+	val &= ~(divp_mask_shifted(pll) | divn_mask_shifted(pll) |
+		 divm_mask_shifted(pll));
+	val &= ~(PLLE_BASE_DIVCML_MASK << PLLE_BASE_DIVCML_SHIFT);
+	val |= sel.m << divm_shift(pll);
+	val |= sel.n << divn_shift(pll);
 	val |= sel.cpcon << PLLE_BASE_DIVCML_SHIFT;
 	pll_writel_base(val, pll);
 	udelay(1);
@@ -1410,6 +1420,15 @@ struct clk *tegra_clk_register_pll(const char *name, const char *parent_name,
 	return clk;
 }
 
+static struct div_nmp pll_e_nmp = {
+	.divn_shift = PLLE_BASE_DIVN_SHIFT,
+	.divn_width = PLLE_BASE_DIVN_WIDTH,
+	.divm_shift = PLLE_BASE_DIVM_SHIFT,
+	.divm_width = PLLE_BASE_DIVM_WIDTH,
+	.divp_shift = PLLE_BASE_DIVP_SHIFT,
+	.divp_width = PLLE_BASE_DIVP_WIDTH,
+};
+
 struct clk *tegra_clk_register_plle(const char *name, const char *parent_name,
 		void __iomem *clk_base, void __iomem *pmc,
 		unsigned long flags, struct tegra_clk_pll_params *pll_params,
@@ -1420,6 +1439,10 @@ struct clk *tegra_clk_register_plle(const char *name, const char *parent_name,
 
 	pll_params->flags |= TEGRA_PLL_LOCK_MISC | TEGRA_PLL_BYPASS;
 	pll_params->flags |= TEGRA_PLL_HAS_LOCK_ENABLE;
+
+	if (!pll_params->div_nmp)
+		pll_params->div_nmp = &pll_e_nmp;
+
 	pll = _tegra_init_pll(clk_base, pmc, pll_params, lock);
 	if (IS_ERR(pll))
 		return ERR_CAST(pll);
@@ -1557,9 +1580,8 @@ struct clk *tegra_clk_register_pllre(const char *name, const char *parent_name,
 		int m;
 
 		m = _pll_fixed_mdiv(pll_params, parent_rate);
-		val = m << PLL_BASE_DIVM_SHIFT;
-		val |= (pll_params->vco_min / parent_rate)
-				<< PLL_BASE_DIVN_SHIFT;
+		val = m << divm_shift(pll);
+		val |= (pll_params->vco_min / parent_rate) << divn_shift(pll);
 		pll_writel_base(val, pll);
 	}
 
@@ -1718,7 +1740,7 @@ struct clk *tegra_clk_register_plle_tegra114(const char *name,
 					"pll_re_vco");
 	} else {
 		val_aux &= ~(PLLE_AUX_PLLRE_SEL | PLLE_AUX_PLLP_SEL);
-		pll_writel(val, pll_params->aux_reg, pll);
+		pll_writel(val_aux, pll_params->aux_reg, pll);
 	}
 
 	clk = _tegra_clk_register_pll(pll, name, parent_name, flags,
diff --git a/drivers/clocksource/tcb_clksrc.c b/drivers/clocksource/tcb_clksrc.c
index 00fdd1170284..a8d7ea14f183 100644
--- a/drivers/clocksource/tcb_clksrc.c
+++ b/drivers/clocksource/tcb_clksrc.c
@@ -100,7 +100,7 @@ static void tc_mode(enum clock_event_mode m, struct clock_event_device *d)
 			|| tcd->clkevt.mode == CLOCK_EVT_MODE_ONESHOT) {
 		__raw_writel(0xff, regs + ATMEL_TC_REG(2, IDR));
 		__raw_writel(ATMEL_TC_CLKDIS, regs + ATMEL_TC_REG(2, CCR));
-		clk_disable_unprepare(tcd->clk);
+		clk_disable(tcd->clk);
 	}
 
 	switch (m) {
@@ -109,7 +109,7 @@ static void tc_mode(enum clock_event_mode m, struct clock_event_device *d)
 	 * of oneshot, we get lower overhead and improved accuracy.
 	 */
 	case CLOCK_EVT_MODE_PERIODIC:
-		clk_prepare_enable(tcd->clk);
+		clk_enable(tcd->clk);
 
 		/* slow clock, count up to RC, then irq and restart */
 		__raw_writel(timer_clock
@@ -126,7 +126,7 @@ static void tc_mode(enum clock_event_mode m, struct clock_event_device *d)
 		break;
 
 	case CLOCK_EVT_MODE_ONESHOT:
-		clk_prepare_enable(tcd->clk);
+		clk_enable(tcd->clk);
 
 		/* slow clock, count up to RC, then irq and stop */
 		__raw_writel(timer_clock | ATMEL_TC_CPCSTOP
@@ -194,7 +194,7 @@ static int __init setup_clkevents(struct atmel_tc *tc, int clk32k_divisor_idx)
 	ret = clk_prepare_enable(t2_clk);
 	if (ret)
 		return ret;
-	clk_disable_unprepare(t2_clk);
+	clk_disable(t2_clk);
 
 	clkevt.regs = tc->regs;
 	clkevt.clk = t2_clk;
diff --git a/drivers/clocksource/timer-marco.c b/drivers/clocksource/timer-marco.c
index b52e1c078b99..7f5374dbefd9 100644
--- a/drivers/clocksource/timer-marco.c
+++ b/drivers/clocksource/timer-marco.c
@@ -199,7 +199,7 @@ static int sirfsoc_local_timer_setup(struct clock_event_device *ce)
 
 	action->dev_id = ce;
 	BUG_ON(setup_irq(ce->irq, action));
-	irq_set_affinity(action->irq, cpumask_of(cpu));
+	irq_force_affinity(action->irq, cpumask_of(cpu));
 
 	clockevents_register_device(ce);
 	return 0;
diff --git a/drivers/cpufreq/cpufreq-cpu0.c b/drivers/cpufreq/cpufreq-cpu0.c
index 1bf6bbac3e03..09b9129c7bd3 100644
--- a/drivers/cpufreq/cpufreq-cpu0.c
+++ b/drivers/cpufreq/cpufreq-cpu0.c
@@ -130,7 +130,7 @@ static int cpu0_cpufreq_probe(struct platform_device *pdev)
 		return -ENOENT;
 	}
 
-	cpu_reg = devm_regulator_get_optional(cpu_dev, "cpu0");
+	cpu_reg = regulator_get_optional(cpu_dev, "cpu0");
 	if (IS_ERR(cpu_reg)) {
 		/*
 		 * If cpu0 regulator supply node is present, but regulator is
@@ -145,23 +145,23 @@ static int cpu0_cpufreq_probe(struct platform_device *pdev)
 			PTR_ERR(cpu_reg));
 	}
 
-	cpu_clk = devm_clk_get(cpu_dev, NULL);
+	cpu_clk = clk_get(cpu_dev, NULL);
 	if (IS_ERR(cpu_clk)) {
 		ret = PTR_ERR(cpu_clk);
 		pr_err("failed to get cpu0 clock: %d\n", ret);
-		goto out_put_node;
+		goto out_put_reg;
 	}
 
 	ret = of_init_opp_table(cpu_dev);
 	if (ret) {
 		pr_err("failed to init OPP table: %d\n", ret);
-		goto out_put_node;
+		goto out_put_clk;
 	}
 
 	ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table);
 	if (ret) {
 		pr_err("failed to init cpufreq table: %d\n", ret);
-		goto out_put_node;
+		goto out_put_clk;
 	}
 
 	of_property_read_u32(np, "voltage-tolerance", &voltage_tolerance);
@@ -216,6 +216,12 @@ static int cpu0_cpufreq_probe(struct platform_device *pdev)
 
 out_free_table:
 	dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table);
+out_put_clk:
+	if (!IS_ERR(cpu_clk))
+		clk_put(cpu_clk);
+out_put_reg:
+	if (!IS_ERR(cpu_reg))
+		regulator_put(cpu_reg);
 out_put_node:
 	of_node_put(np);
 	return ret;
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index ba43991ba98a..e1c6433b16e0 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -366,6 +366,11 @@ int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 		break;
 
 	case CPUFREQ_GOV_LIMITS:
+		mutex_lock(&dbs_data->mutex);
+		if (!cpu_cdbs->cur_policy) {
+			mutex_unlock(&dbs_data->mutex);
+			break;
+		}
 		mutex_lock(&cpu_cdbs->timer_mutex);
 		if (policy->max < cpu_cdbs->cur_policy->cur)
 			__cpufreq_driver_target(cpu_cdbs->cur_policy,
@@ -375,6 +380,7 @@ int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 					policy->min, CPUFREQ_RELATION_L);
 		dbs_check_cpu(dbs_data, cpu);
 		mutex_unlock(&cpu_cdbs->timer_mutex);
+		mutex_unlock(&dbs_data->mutex);
 		break;
 	}
 	return 0;
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 099967302bf2..eab8ccfe6beb 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -37,6 +37,7 @@
 #define BYT_RATIOS		0x66a
 #define BYT_VIDS		0x66b
 #define BYT_TURBO_RATIOS	0x66c
+#define BYT_TURBO_VIDS		0x66d
 
 
 #define FRAC_BITS 6
@@ -70,8 +71,9 @@ struct pstate_data {
 };
 
 struct vid_data {
-	int32_t min;
-	int32_t max;
+	int min;
+	int max;
+	int turbo;
 	int32_t ratio;
 };
 
@@ -359,14 +361,14 @@ static int byt_get_min_pstate(void)
 {
 	u64 value;
 	rdmsrl(BYT_RATIOS, value);
-	return (value >> 8) & 0xFF;
+	return (value >> 8) & 0x3F;
 }
 
 static int byt_get_max_pstate(void)
 {
 	u64 value;
 	rdmsrl(BYT_RATIOS, value);
-	return (value >> 16) & 0xFF;
+	return (value >> 16) & 0x3F;
 }
 
 static int byt_get_turbo_pstate(void)
@@ -393,6 +395,9 @@ static void byt_set_pstate(struct cpudata *cpudata, int pstate)
 	vid_fp = clamp_t(int32_t, vid_fp, cpudata->vid.min, cpudata->vid.max);
 	vid = fp_toint(vid_fp);
 
+	if (pstate > cpudata->pstate.max_pstate)
+		vid = cpudata->vid.turbo;
+
 	val |= vid;
 
 	wrmsrl(MSR_IA32_PERF_CTL, val);
@@ -402,13 +407,17 @@ static void byt_get_vid(struct cpudata *cpudata)
 {
 	u64 value;
 
+
 	rdmsrl(BYT_VIDS, value);
-	cpudata->vid.min = int_tofp((value >> 8) & 0x7f);
-	cpudata->vid.max = int_tofp((value >> 16) & 0x7f);
+	cpudata->vid.min = int_tofp((value >> 8) & 0x3f);
+	cpudata->vid.max = int_tofp((value >> 16) & 0x3f);
 	cpudata->vid.ratio = div_fp(
 		cpudata->vid.max - cpudata->vid.min,
 		int_tofp(cpudata->pstate.max_pstate -
 			cpudata->pstate.min_pstate));
+
+	rdmsrl(BYT_TURBO_VIDS, value);
+	cpudata->vid.turbo = value & 0x7f;
 }
 
 
@@ -545,12 +554,7 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
 
 	if (pstate_funcs.get_vid)
 		pstate_funcs.get_vid(cpu);
-
-	/*
-	 * goto max pstate so we don't slow up boot if we are built-in if we are
-	 * a module we will take care of it during normal operation
-	 */
-	intel_pstate_set_pstate(cpu, cpu->pstate.max_pstate);
+	intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate);
 }
 
 static inline void intel_pstate_calc_busy(struct cpudata *cpu,
@@ -695,11 +699,6 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
 	cpu = all_cpu_data[cpunum];
 
 	intel_pstate_get_cpu_pstates(cpu);
-	if (!cpu->pstate.current_pstate) {
-		all_cpu_data[cpunum] = NULL;
-		kfree(cpu);
-		return -ENODATA;
-	}
 
 	cpu->cpu = cpunum;
 
@@ -710,7 +709,6 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
 	cpu->timer.expires = jiffies + HZ/100;
 	intel_pstate_busy_pid_reset(cpu);
 	intel_pstate_sample(cpu);
-	intel_pstate_set_pstate(cpu, cpu->pstate.max_pstate);
 
 	add_timer_on(&cpu->timer, cpunum);
 
diff --git a/drivers/cpufreq/loongson2_cpufreq.c b/drivers/cpufreq/loongson2_cpufreq.c
index f0bc31f5db27..d4add8621944 100644
--- a/drivers/cpufreq/loongson2_cpufreq.c
+++ b/drivers/cpufreq/loongson2_cpufreq.c
@@ -62,7 +62,7 @@ static int loongson2_cpufreq_target(struct cpufreq_policy *policy,
 	set_cpus_allowed_ptr(current, &cpus_allowed);
 
 	/* setting the cpu frequency */
-	clk_set_rate(policy->clk, freq);
+	clk_set_rate(policy->clk, freq * 1000);
 
 	return 0;
 }
@@ -92,7 +92,7 @@ static int loongson2_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	     i++)
 		loongson2_clockmod_table[i].frequency = (rate * i) / 8;
 
-	ret = clk_set_rate(cpuclk, rate);
+	ret = clk_set_rate(cpuclk, rate * 1000);
 	if (ret) {
 		clk_put(cpuclk);
 		return ret;
diff --git a/drivers/crypto/caam/error.c b/drivers/crypto/caam/error.c
index 9f25f5296029..0eabd81e1a90 100644
--- a/drivers/crypto/caam/error.c
+++ b/drivers/crypto/caam/error.c
@@ -16,9 +16,13 @@
 	char *tmp;						\
 								\
 	tmp = kmalloc(sizeof(format) + max_alloc, GFP_ATOMIC);	\
-	sprintf(tmp, format, param);				\
-	strcat(str, tmp);					\
-	kfree(tmp);						\
+	if (likely(tmp)) {					\
+		sprintf(tmp, format, param);			\
+		strcat(str, tmp);				\
+		kfree(tmp);					\
+	} else {						\
+		strcat(str, "kmalloc failure in SPRINTFCAT");	\
+	}							\
 }
 
 static void report_jump_idx(u32 status, char *outstr)
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index a886713937fd..d5d30ed863ce 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -1009,6 +1009,7 @@ static void dmaengine_unmap(struct kref *kref)
 		dma_unmap_page(dev, unmap->addr[i], unmap->len,
 			       DMA_BIDIRECTIONAL);
 	}
+	cnt = unmap->map_cnt;
 	mempool_free(unmap, __get_unmap_pool(cnt)->pool);
 }
 
@@ -1074,6 +1075,7 @@ dmaengine_get_unmap_data(struct device *dev, int nr, gfp_t flags)
 	memset(unmap, 0, sizeof(*unmap));
 	kref_init(&unmap->kref);
 	unmap->dev = dev;
+	unmap->map_cnt = nr;
 
 	return unmap;
 }
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index cfdbb92aae1d..7a740769c2fa 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -1548,11 +1548,6 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 	/* Disable BLOCK interrupts as well */
 	channel_clear_bit(dw, MASK.BLOCK, dw->all_chan_mask);
 
-	err = devm_request_irq(chip->dev, chip->irq, dw_dma_interrupt,
-			       IRQF_SHARED, "dw_dmac", dw);
-	if (err)
-		return err;
-
 	/* Create a pool of consistent memory blocks for hardware descriptors */
 	dw->desc_pool = dmam_pool_create("dw_dmac_desc_pool", chip->dev,
 					 sizeof(struct dw_desc), 4, 0);
@@ -1563,6 +1558,11 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 
 	tasklet_init(&dw->tasklet, dw_dma_tasklet, (unsigned long)dw);
 
+	err = request_irq(chip->irq, dw_dma_interrupt, IRQF_SHARED,
+			  "dw_dmac", dw);
+	if (err)
+		return err;
+
 	INIT_LIST_HEAD(&dw->dma.channels);
 	for (i = 0; i < nr_channels; i++) {
 		struct dw_dma_chan	*dwc = &dw->chan[i];
@@ -1667,6 +1667,7 @@ int dw_dma_remove(struct dw_dma_chip *chip)
 	dw_dma_off(dw);
 	dma_async_device_unregister(&dw->dma);
 
+	free_irq(chip->irq, dw);
 	tasklet_kill(&dw->tasklet);
 
 	list_for_each_entry_safe(dwc, _dwc, &dw->dma.channels,
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index 766b68ed505c..394cbc5c93e3 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -191,12 +191,10 @@ static void mv_set_mode(struct mv_xor_chan *chan,
 
 static void mv_chan_activate(struct mv_xor_chan *chan)
 {
-	u32 activation;
-
 	dev_dbg(mv_chan_to_devp(chan), " activate chan.\n");
-	activation = readl_relaxed(XOR_ACTIVATION(chan));
-	activation |= 0x1;
-	writel_relaxed(activation, XOR_ACTIVATION(chan));
+
+	/* writel ensures all descriptors are flushed before activation */
+	writel(BIT(0), XOR_ACTIVATION(chan));
 }
 
 static char mv_chan_is_busy(struct mv_xor_chan *chan)
diff --git a/drivers/dma/sa11x0-dma.c b/drivers/dma/sa11x0-dma.c
index ab26d46bbe15..5ebdfbc1051e 100644
--- a/drivers/dma/sa11x0-dma.c
+++ b/drivers/dma/sa11x0-dma.c
@@ -113,11 +113,9 @@ struct sa11x0_dma_phy {
 	struct sa11x0_dma_desc	*txd_load;
 	unsigned		sg_done;
 	struct sa11x0_dma_desc	*txd_done;
-#ifdef CONFIG_PM_SLEEP
 	u32			dbs[2];
 	u32			dbt[2];
 	u32			dcsr;
-#endif
 };
 
 struct sa11x0_dma_dev {
@@ -984,7 +982,6 @@ static int sa11x0_dma_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM_SLEEP
 static int sa11x0_dma_suspend(struct device *dev)
 {
 	struct sa11x0_dma_dev *d = dev_get_drvdata(dev);
@@ -1054,7 +1051,6 @@ static int sa11x0_dma_resume(struct device *dev)
 
 	return 0;
 }
-#endif
 
 static const struct dev_pm_ops sa11x0_dma_pm_ops = {
 	.suspend_noirq = sa11x0_dma_suspend,
diff --git a/drivers/firewire/core.h b/drivers/firewire/core.h
index c98764aeeec6..f477308b6e9c 100644
--- a/drivers/firewire/core.h
+++ b/drivers/firewire/core.h
@@ -237,8 +237,8 @@ static inline bool is_next_generation(int new_generation, int old_generation)
 
 #define LOCAL_BUS 0xffc0
 
-/* arbitrarily chosen maximum range for physical DMA: 128 TB */
-#define FW_MAX_PHYSICAL_RANGE		(128ULL << 40)
+/* OHCI-1394's default upper bound for physical DMA: 4 GB */
+#define FW_MAX_PHYSICAL_RANGE		(1ULL << 32)
 
 void fw_core_handle_request(struct fw_card *card, struct fw_packet *request);
 void fw_core_handle_response(struct fw_card *card, struct fw_packet *packet);
diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c
index 8db663219560..586f2f7f6993 100644
--- a/drivers/firewire/ohci.c
+++ b/drivers/firewire/ohci.c
@@ -3716,7 +3716,7 @@ static int pci_probe(struct pci_dev *dev,
 		    version >> 16, version & 0xff, ohci->card.index,
 		    ohci->n_ir, ohci->n_it, ohci->quirks,
 		    reg_read(ohci, OHCI1394_PhyUpperBound) ?
-			", >4 GB phys DMA" : "");
+			", physUB" : "");
 
 	return 0;
 
diff --git a/drivers/firmware/iscsi_ibft.c b/drivers/firmware/iscsi_ibft.c
index 3ee852c9925b..071c2c969eec 100644
--- a/drivers/firmware/iscsi_ibft.c
+++ b/drivers/firmware/iscsi_ibft.c
@@ -756,6 +756,7 @@ static const struct {
 	 */
 	{ ACPI_SIG_IBFT },
 	{ "iBFT" },
+	{ "BIFT" },	/* Broadcom iSCSI Offload */
 };
 
 static void __init acpi_find_ibft_region(void)
diff --git a/drivers/gpio/gpio-ich.c b/drivers/gpio/gpio-ich.c
index e73c6755a5eb..70304220a479 100644
--- a/drivers/gpio/gpio-ich.c
+++ b/drivers/gpio/gpio-ich.c
@@ -305,6 +305,8 @@ static struct ichx_desc ich6_desc = {
 
 	.ngpio = 50,
 	.have_blink = true,
+	.regs = ichx_regs,
+	.reglen = ichx_reglen,
 };
 
 /* Intel 3100 */
@@ -324,6 +326,8 @@ static struct ichx_desc i3100_desc = {
 	.uses_gpe0 = true,
 
 	.ngpio = 50,
+	.regs = ichx_regs,
+	.reglen = ichx_reglen,
 };
 
 /* ICH7 and ICH8-based */
diff --git a/drivers/gpio/gpio-mcp23s08.c b/drivers/gpio/gpio-mcp23s08.c
index 99a68310e7c0..3d53fd6880d1 100644
--- a/drivers/gpio/gpio-mcp23s08.c
+++ b/drivers/gpio/gpio-mcp23s08.c
@@ -894,9 +894,11 @@ static int mcp23s08_probe(struct spi_device *spi)
 			dev_err(&spi->dev, "invalid spi-present-mask\n");
 			return -ENODEV;
 		}
-
-		for (addr = 0; addr < ARRAY_SIZE(pdata->chip); addr++)
+		for (addr = 0; addr < ARRAY_SIZE(pdata->chip); addr++) {
+			if ((spi_present_mask & (1 << addr)))
+				chips++;
 			pullups[addr] = 0;
+		}
 	} else {
 		type = spi_get_device_id(spi)->driver_data;
 		pdata = dev_get_platdata(&spi->dev);
@@ -919,12 +921,12 @@ static int mcp23s08_probe(struct spi_device *spi)
 			pullups[addr] = pdata->chip[addr].pullups;
 		}
 
-		if (!chips)
-			return -ENODEV;
-
 		base = pdata->base;
 	}
 
+	if (!chips)
+		return -ENODEV;
+
 	data = kzalloc(sizeof(*data) + chips * sizeof(struct mcp23s08),
 			GFP_KERNEL);
 	if (!data)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index ec82f6bff122..108e1ec2fa4b 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1954,6 +1954,9 @@ struct drm_i915_cmd_table {
 #define IS_ULT(dev)		(IS_HSW_ULT(dev) || IS_BDW_ULT(dev))
 #define IS_HSW_GT3(dev)		(IS_HASWELL(dev) && \
 				 ((dev)->pdev->device & 0x00F0) == 0x0020)
+/* ULX machines are also considered ULT. */
+#define IS_HSW_ULX(dev)		((dev)->pdev->device == 0x0A0E || \
+				 (dev)->pdev->device == 0x0A1E)
 #define IS_PRELIMINARY_HW(intel_info) ((intel_info)->is_preliminary)
 
 /*
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 62a5c3627b90..154b0f8bb88d 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -34,25 +34,35 @@ static void gen8_setup_private_ppat(struct drm_i915_private *dev_priv);
 
 bool intel_enable_ppgtt(struct drm_device *dev, bool full)
 {
-	if (i915.enable_ppgtt == 0 || !HAS_ALIASING_PPGTT(dev))
+	if (i915.enable_ppgtt == 0)
 		return false;
 
 	if (i915.enable_ppgtt == 1 && full)
 		return false;
 
+	return true;
+}
+
+static int sanitize_enable_ppgtt(struct drm_device *dev, int enable_ppgtt)
+{
+	if (enable_ppgtt == 0 || !HAS_ALIASING_PPGTT(dev))
+		return 0;
+
+	if (enable_ppgtt == 1)
+		return 1;
+
+	if (enable_ppgtt == 2 && HAS_PPGTT(dev))
+		return 2;
+
 #ifdef CONFIG_INTEL_IOMMU
 	/* Disable ppgtt on SNB if VT-d is on. */
 	if (INTEL_INFO(dev)->gen == 6 && intel_iommu_gfx_mapped) {
 		DRM_INFO("Disabling PPGTT because VT-d is on\n");
-		return false;
+		return 0;
 	}
 #endif
 
-	/* Full ppgtt disabled by default for now due to issues. */
-	if (full)
-		return HAS_PPGTT(dev) && (i915.enable_ppgtt == 2);
-	else
-		return HAS_ALIASING_PPGTT(dev);
+	return HAS_ALIASING_PPGTT(dev) ? 1 : 0;
 }
 
 #define GEN6_PPGTT_PD_ENTRIES 512
@@ -2031,6 +2041,14 @@ int i915_gem_gtt_init(struct drm_device *dev)
 		 gtt->base.total >> 20);
 	DRM_DEBUG_DRIVER("GMADR size = %ldM\n", gtt->mappable_end >> 20);
 	DRM_DEBUG_DRIVER("GTT stolen size = %zdM\n", gtt->stolen_size >> 20);
+	/*
+	 * i915.enable_ppgtt is read-only, so do an early pass to validate the
+	 * user's requested state against the hardware/driver capabilities.  We
+	 * do this now so that we can print out any log messages once rather
+	 * than every time we check intel_enable_ppgtt().
+	 */
+	i915.enable_ppgtt = sanitize_enable_ppgtt(dev, i915.enable_ppgtt);
+	DRM_DEBUG_DRIVER("ppgtt mode: %i\n", i915.enable_ppgtt);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index fa486c5fbb02..aff4a113cda3 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -560,47 +560,71 @@ parse_edp(struct drm_i915_private *dev_priv, struct bdb_header *bdb)
 
 	dev_priv->vbt.edp_pps = *edp_pps;
 
-	dev_priv->vbt.edp_rate = edp_link_params->rate ? DP_LINK_BW_2_7 :
-		DP_LINK_BW_1_62;
+	switch (edp_link_params->rate) {
+	case EDP_RATE_1_62:
+		dev_priv->vbt.edp_rate = DP_LINK_BW_1_62;
+		break;
+	case EDP_RATE_2_7:
+		dev_priv->vbt.edp_rate = DP_LINK_BW_2_7;
+		break;
+	default:
+		DRM_DEBUG_KMS("VBT has unknown eDP link rate value %u\n",
+			      edp_link_params->rate);
+		break;
+	}
+
 	switch (edp_link_params->lanes) {
-	case 0:
+	case EDP_LANE_1:
 		dev_priv->vbt.edp_lanes = 1;
 		break;
-	case 1:
+	case EDP_LANE_2:
 		dev_priv->vbt.edp_lanes = 2;
 		break;
-	case 3:
-	default:
+	case EDP_LANE_4:
 		dev_priv->vbt.edp_lanes = 4;
 		break;
+	default:
+		DRM_DEBUG_KMS("VBT has unknown eDP lane count value %u\n",
+			      edp_link_params->lanes);
+		break;
 	}
+
 	switch (edp_link_params->preemphasis) {
-	case 0:
+	case EDP_PREEMPHASIS_NONE:
 		dev_priv->vbt.edp_preemphasis = DP_TRAIN_PRE_EMPHASIS_0;
 		break;
-	case 1:
+	case EDP_PREEMPHASIS_3_5dB:
 		dev_priv->vbt.edp_preemphasis = DP_TRAIN_PRE_EMPHASIS_3_5;
 		break;
-	case 2:
+	case EDP_PREEMPHASIS_6dB:
 		dev_priv->vbt.edp_preemphasis = DP_TRAIN_PRE_EMPHASIS_6;
 		break;
-	case 3:
+	case EDP_PREEMPHASIS_9_5dB:
 		dev_priv->vbt.edp_preemphasis = DP_TRAIN_PRE_EMPHASIS_9_5;
 		break;
+	default:
+		DRM_DEBUG_KMS("VBT has unknown eDP pre-emphasis value %u\n",
+			      edp_link_params->preemphasis);
+		break;
 	}
+
 	switch (edp_link_params->vswing) {
-	case 0:
+	case EDP_VSWING_0_4V:
 		dev_priv->vbt.edp_vswing = DP_TRAIN_VOLTAGE_SWING_400;
 		break;
-	case 1:
+	case EDP_VSWING_0_6V:
 		dev_priv->vbt.edp_vswing = DP_TRAIN_VOLTAGE_SWING_600;
 		break;
-	case 2:
+	case EDP_VSWING_0_8V:
 		dev_priv->vbt.edp_vswing = DP_TRAIN_VOLTAGE_SWING_800;
 		break;
-	case 3:
+	case EDP_VSWING_1_2V:
 		dev_priv->vbt.edp_vswing = DP_TRAIN_VOLTAGE_SWING_1200;
 		break;
+	default:
+		DRM_DEBUG_KMS("VBT has unknown eDP voltage swing value %u\n",
+			      edp_link_params->vswing);
+		break;
 	}
 }
 
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 69bcc42a0e44..48aa516a1ac0 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -11395,15 +11395,6 @@ void intel_modeset_init(struct drm_device *dev)
 	}
 }
 
-static void
-intel_connector_break_all_links(struct intel_connector *connector)
-{
-	connector->base.dpms = DRM_MODE_DPMS_OFF;
-	connector->base.encoder = NULL;
-	connector->encoder->connectors_active = false;
-	connector->encoder->base.crtc = NULL;
-}
-
 static void intel_enable_pipe_a(struct drm_device *dev)
 {
 	struct intel_connector *connector;
@@ -11485,8 +11476,17 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc)
 			if (connector->encoder->base.crtc != &crtc->base)
 				continue;
 
-			intel_connector_break_all_links(connector);
+			connector->base.dpms = DRM_MODE_DPMS_OFF;
+			connector->base.encoder = NULL;
 		}
+		/* multiple connectors may have the same encoder:
+		 *  handle them and break crtc link separately */
+		list_for_each_entry(connector, &dev->mode_config.connector_list,
+				    base.head)
+			if (connector->encoder->base.crtc == &crtc->base) {
+				connector->encoder->base.crtc = NULL;
+				connector->encoder->connectors_active = false;
+			}
 
 		WARN_ON(crtc->active);
 		crtc->base.enabled = false;
@@ -11568,6 +11568,8 @@ static void intel_sanitize_encoder(struct intel_encoder *encoder)
 				      drm_get_encoder_name(&encoder->base));
 			encoder->disable(encoder);
 		}
+		encoder->base.crtc = NULL;
+		encoder->connectors_active = false;
 
 		/* Inconsistent output/port/pipe state happens presumably due to
 		 * a bug in one of the get_hw_state functions. Or someplace else
@@ -11578,8 +11580,8 @@ static void intel_sanitize_encoder(struct intel_encoder *encoder)
 				    base.head) {
 			if (connector->encoder != encoder)
 				continue;
-
-			intel_connector_break_all_links(connector);
+			connector->base.dpms = DRM_MODE_DPMS_OFF;
+			connector->base.encoder = NULL;
 		}
 	}
 	/* Enabled encoders without active connectors will be fixed in
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index dfa85289f28f..2a00cb828d20 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -105,7 +105,8 @@ intel_dp_max_link_bw(struct intel_dp *intel_dp)
 	case DP_LINK_BW_2_7:
 		break;
 	case DP_LINK_BW_5_4: /* 1.2 capable displays may advertise higher bw */
-		if ((IS_HASWELL(dev) || INTEL_INFO(dev)->gen >= 8) &&
+		if (((IS_HASWELL(dev) && !IS_HSW_ULX(dev)) ||
+		     INTEL_INFO(dev)->gen >= 8) &&
 		    intel_dp->dpcd[DP_DPCD_REV] >= 0x12)
 			max_link_bw = DP_LINK_BW_5_4;
 		else
@@ -120,6 +121,22 @@ intel_dp_max_link_bw(struct intel_dp *intel_dp)
 	return max_link_bw;
 }
 
+static u8 intel_dp_max_lane_count(struct intel_dp *intel_dp)
+{
+	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	struct drm_device *dev = intel_dig_port->base.base.dev;
+	u8 source_max, sink_max;
+
+	source_max = 4;
+	if (HAS_DDI(dev) && intel_dig_port->port == PORT_A &&
+	    (intel_dig_port->saved_port_bits & DDI_A_4_LANES) == 0)
+		source_max = 2;
+
+	sink_max = drm_dp_max_lane_count(intel_dp->dpcd);
+
+	return min(source_max, sink_max);
+}
+
 /*
  * The units on the numbers in the next two are... bizarre.  Examples will
  * make it clearer; this one parallels an example in the eDP spec.
@@ -170,7 +187,7 @@ intel_dp_mode_valid(struct drm_connector *connector,
 	}
 
 	max_link_clock = drm_dp_bw_code_to_link_rate(intel_dp_max_link_bw(intel_dp));
-	max_lanes = drm_dp_max_lane_count(intel_dp->dpcd);
+	max_lanes = intel_dp_max_lane_count(intel_dp);
 
 	max_rate = intel_dp_max_data_rate(max_link_clock, max_lanes);
 	mode_rate = intel_dp_link_required(target_clock, 18);
@@ -750,8 +767,10 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 	struct intel_crtc *intel_crtc = encoder->new_crtc;
 	struct intel_connector *intel_connector = intel_dp->attached_connector;
 	int lane_count, clock;
-	int max_lane_count = drm_dp_max_lane_count(intel_dp->dpcd);
+	int min_lane_count = 1;
+	int max_lane_count = intel_dp_max_lane_count(intel_dp);
 	/* Conveniently, the link BW constants become indices with a shift...*/
+	int min_clock = 0;
 	int max_clock = intel_dp_max_link_bw(intel_dp) >> 3;
 	int bpp, mode_rate;
 	static int bws[] = { DP_LINK_BW_1_62, DP_LINK_BW_2_7, DP_LINK_BW_5_4 };
@@ -784,19 +803,38 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 	/* Walk through all bpp values. Luckily they're all nicely spaced with 2
 	 * bpc in between. */
 	bpp = pipe_config->pipe_bpp;
-	if (is_edp(intel_dp) && dev_priv->vbt.edp_bpp &&
-	    dev_priv->vbt.edp_bpp < bpp) {
-		DRM_DEBUG_KMS("clamping bpp for eDP panel to BIOS-provided %i\n",
-			      dev_priv->vbt.edp_bpp);
-		bpp = dev_priv->vbt.edp_bpp;
+	if (is_edp(intel_dp)) {
+		if (dev_priv->vbt.edp_bpp && dev_priv->vbt.edp_bpp < bpp) {
+			DRM_DEBUG_KMS("clamping bpp for eDP panel to BIOS-provided %i\n",
+				      dev_priv->vbt.edp_bpp);
+			bpp = dev_priv->vbt.edp_bpp;
+		}
+
+		if (IS_BROADWELL(dev)) {
+			/* Yes, it's an ugly hack. */
+			min_lane_count = max_lane_count;
+			DRM_DEBUG_KMS("forcing lane count to max (%u) on BDW\n",
+				      min_lane_count);
+		} else if (dev_priv->vbt.edp_lanes) {
+			min_lane_count = min(dev_priv->vbt.edp_lanes,
+					     max_lane_count);
+			DRM_DEBUG_KMS("using min %u lanes per VBT\n",
+				      min_lane_count);
+		}
+
+		if (dev_priv->vbt.edp_rate) {
+			min_clock = min(dev_priv->vbt.edp_rate >> 3, max_clock);
+			DRM_DEBUG_KMS("using min %02x link bw per VBT\n",
+				      bws[min_clock]);
+		}
 	}
 
 	for (; bpp >= 6*3; bpp -= 2*3) {
 		mode_rate = intel_dp_link_required(adjusted_mode->crtc_clock,
 						   bpp);
 
-		for (lane_count = 1; lane_count <= max_lane_count; lane_count <<= 1) {
-			for (clock = 0; clock <= max_clock; clock++) {
+		for (lane_count = min_lane_count; lane_count <= max_lane_count; lane_count <<= 1) {
+			for (clock = min_clock; clock <= max_clock; clock++) {
 				link_clock = drm_dp_bw_code_to_link_rate(bws[clock]);
 				link_avail = intel_dp_max_data_rate(link_clock,
 								    lane_count);
diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c
index fce4a0d93c0b..f73ba5e6b7a8 100644
--- a/drivers/gpu/drm/i915/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/intel_fbdev.c
@@ -387,6 +387,15 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
 							  height);
 		}
 
+		/* No preferred mode marked by the EDID? Are there any modes? */
+		if (!modes[i] && !list_empty(&connector->modes)) {
+			DRM_DEBUG_KMS("using first mode listed on connector %s\n",
+				      drm_get_connector_name(connector));
+			modes[i] = list_first_entry(&connector->modes,
+						    struct drm_display_mode,
+						    head);
+		}
+
 		/* last resort: use current mode */
 		if (!modes[i]) {
 			/*
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index 0eead16aeda7..cb8cfb7e0974 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -492,6 +492,7 @@ void intel_panel_set_backlight(struct intel_connector *connector, u32 level,
 	enum pipe pipe = intel_get_pipe_from_connector(connector);
 	u32 freq;
 	unsigned long flags;
+	u64 n;
 
 	if (!panel->backlight.present || pipe == INVALID_PIPE)
 		return;
@@ -502,10 +503,9 @@ void intel_panel_set_backlight(struct intel_connector *connector, u32 level,
 
 	/* scale to hardware max, but be careful to not overflow */
 	freq = panel->backlight.max;
-	if (freq < max)
-		level = level * freq / max;
-	else
-		level = freq / max * level;
+	n = (u64)level * freq;
+	do_div(n, max);
+	level = n;
 
 	panel->backlight.level = level;
 	if (panel->backlight.device)
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 19e94c3edc19..d93dcf683e8c 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -2095,6 +2095,43 @@ static void intel_print_wm_latency(struct drm_device *dev,
 	}
 }
 
+static bool ilk_increase_wm_latency(struct drm_i915_private *dev_priv,
+				    uint16_t wm[5], uint16_t min)
+{
+	int level, max_level = ilk_wm_max_level(dev_priv->dev);
+
+	if (wm[0] >= min)
+		return false;
+
+	wm[0] = max(wm[0], min);
+	for (level = 1; level <= max_level; level++)
+		wm[level] = max_t(uint16_t, wm[level], DIV_ROUND_UP(min, 5));
+
+	return true;
+}
+
+static void snb_wm_latency_quirk(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	bool changed;
+
+	/*
+	 * The BIOS provided WM memory latency values are often
+	 * inadequate for high resolution displays. Adjust them.
+	 */
+	changed = ilk_increase_wm_latency(dev_priv, dev_priv->wm.pri_latency, 12) |
+		ilk_increase_wm_latency(dev_priv, dev_priv->wm.spr_latency, 12) |
+		ilk_increase_wm_latency(dev_priv, dev_priv->wm.cur_latency, 12);
+
+	if (!changed)
+		return;
+
+	DRM_DEBUG_KMS("WM latency values increased to avoid potential underruns\n");
+	intel_print_wm_latency(dev, "Primary", dev_priv->wm.pri_latency);
+	intel_print_wm_latency(dev, "Sprite", dev_priv->wm.spr_latency);
+	intel_print_wm_latency(dev, "Cursor", dev_priv->wm.cur_latency);
+}
+
 static void ilk_setup_wm_latency(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
@@ -2112,6 +2149,9 @@ static void ilk_setup_wm_latency(struct drm_device *dev)
 	intel_print_wm_latency(dev, "Primary", dev_priv->wm.pri_latency);
 	intel_print_wm_latency(dev, "Sprite", dev_priv->wm.spr_latency);
 	intel_print_wm_latency(dev, "Cursor", dev_priv->wm.cur_latency);
+
+	if (IS_GEN6(dev))
+		snb_wm_latency_quirk(dev);
 }
 
 static void ilk_compute_wm_parameters(struct drm_crtc *crtc,
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index d27155adf5db..46be00d66df3 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -2424,8 +2424,8 @@ intel_sdvo_connector_init(struct intel_sdvo_connector *connector,
 	if (ret < 0)
 		goto err1;
 
-	ret = sysfs_create_link(&encoder->ddc.dev.kobj,
-				&drm_connector->kdev->kobj,
+	ret = sysfs_create_link(&drm_connector->kdev->kobj,
+				&encoder->ddc.dev.kobj,
 				encoder->ddc.dev.kobj.name);
 	if (ret < 0)
 		goto err2;
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index f729dc71d5be..d0c75779d3f6 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -185,6 +185,8 @@ static void vlv_force_wake_reset(struct drm_i915_private *dev_priv)
 {
 	__raw_i915_write32(dev_priv, FORCEWAKE_VLV,
 			   _MASKED_BIT_DISABLE(0xffff));
+	__raw_i915_write32(dev_priv, FORCEWAKE_MEDIA_VLV,
+			   _MASKED_BIT_DISABLE(0xffff));
 	/* something from same cacheline, but !FORCEWAKE_VLV */
 	__raw_posting_read(dev_priv, FORCEWAKE_ACK_VLV);
 }
diff --git a/drivers/gpu/drm/nouveau/core/engine/disp/nvd0.c b/drivers/gpu/drm/nouveau/core/engine/disp/nvd0.c
index 7762665ad8fd..876de9ac3793 100644
--- a/drivers/gpu/drm/nouveau/core/engine/disp/nvd0.c
+++ b/drivers/gpu/drm/nouveau/core/engine/disp/nvd0.c
@@ -1009,7 +1009,7 @@ exec_clkcmp(struct nv50_disp_priv *priv, int head, int id,
 	}
 
 	if (outp == 8)
-		return false;
+		return conf;
 
 	data = exec_lookup(priv, head, outp, ctrl, dcb, &ver, &hdr, &cnt, &len, &info1);
 	if (data == 0x0000)
diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/ctxgm107.c b/drivers/gpu/drm/nouveau/core/engine/graph/ctxgm107.c
index 1dc37b1ddbfa..b0d0fb2f4d08 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/ctxgm107.c
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/ctxgm107.c
@@ -863,7 +863,7 @@ gm107_grctx_generate_mods(struct nvc0_graph_priv *priv, struct nvc0_grctx *info)
 {
 	mmio_data(0x003000, 0x0100, NV_MEM_ACCESS_RW | NV_MEM_ACCESS_SYS);
 	mmio_data(0x008000, 0x0100, NV_MEM_ACCESS_RW | NV_MEM_ACCESS_SYS);
-	mmio_data(0x060000, 0x1000, NV_MEM_ACCESS_RW);
+	mmio_data(0x200000, 0x1000, NV_MEM_ACCESS_RW);
 
 	mmio_list(0x40800c, 0x00000000,  8, 1);
 	mmio_list(0x408010, 0x80000000,  0, 0);
@@ -877,6 +877,8 @@ gm107_grctx_generate_mods(struct nvc0_graph_priv *priv, struct nvc0_grctx *info)
 	mmio_list(0x418e24, 0x00000000,  8, 0);
 	mmio_list(0x418e28, 0x80000030,  0, 0);
 
+	mmio_list(0x4064c8, 0x018002c0,  0, 0);
+
 	mmio_list(0x418810, 0x80000000, 12, 2);
 	mmio_list(0x419848, 0x10000000, 12, 2);
 	mmio_list(0x419c2c, 0x10000000, 12, 2);
diff --git a/drivers/gpu/drm/nouveau/core/subdev/bios/base.c b/drivers/gpu/drm/nouveau/core/subdev/bios/base.c
index fb0b6b2d1427..222e8ebb669d 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/bios/base.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/bios/base.c
@@ -168,7 +168,8 @@ nouveau_bios_shadow_prom(struct nouveau_bios *bios)
 	 */
 	i = 16;
 	do {
-		if ((nv_rd32(bios, 0x300000) & 0xffff) == 0xaa55)
+		u32 data = le32_to_cpu(nv_rd32(bios, 0x300000)) & 0xffff;
+		if (data == 0xaa55)
 			break;
 	} while (i--);
 
@@ -176,14 +177,15 @@ nouveau_bios_shadow_prom(struct nouveau_bios *bios)
 		goto out;
 
 	/* read entire bios image to system memory */
-	bios->size = ((nv_rd32(bios, 0x300000) >> 16) & 0xff) * 512;
+	bios->size = (le32_to_cpu(nv_rd32(bios, 0x300000)) >> 16) & 0xff;
+	bios->size = bios->size * 512;
 	if (!bios->size)
 		goto out;
 
 	bios->data = kmalloc(bios->size, GFP_KERNEL);
 	if (bios->data) {
-		for (i = 0; i < bios->size; i+=4)
-			nv_wo32(bios, i, nv_rd32(bios, 0x300000 + i));
+		for (i = 0; i < bios->size; i += 4)
+			((u32 *)bios->data)[i/4] = nv_rd32(bios, 0x300000 + i);
 	}
 
 	/* check the PCI record header */
diff --git a/drivers/gpu/drm/nouveau/core/subdev/therm/nvd0.c b/drivers/gpu/drm/nouveau/core/subdev/therm/nvd0.c
index 43fec17ea540..bbf117be572f 100644
--- a/drivers/gpu/drm/nouveau/core/subdev/therm/nvd0.c
+++ b/drivers/gpu/drm/nouveau/core/subdev/therm/nvd0.c
@@ -40,6 +40,7 @@ pwm_info(struct nouveau_therm *therm, int line)
 		case 0x00: return 2;
 		case 0x19: return 1;
 		case 0x1c: return 0;
+		case 0x1e: return 2;
 		default:
 			break;
 		}
diff --git a/drivers/gpu/drm/nouveau/nouveau_acpi.c b/drivers/gpu/drm/nouveau/nouveau_acpi.c
index 83face3f608f..279206997e5c 100644
--- a/drivers/gpu/drm/nouveau/nouveau_acpi.c
+++ b/drivers/gpu/drm/nouveau/nouveau_acpi.c
@@ -389,9 +389,6 @@ bool nouveau_acpi_rom_supported(struct pci_dev *pdev)
 	acpi_status status;
 	acpi_handle dhandle, rom_handle;
 
-	if (!nouveau_dsm_priv.dsm_detected && !nouveau_dsm_priv.optimus_detected)
-		return false;
-
 	dhandle = ACPI_HANDLE(&pdev->dev);
 	if (!dhandle)
 		return false;
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index 3ff030dc1ee3..da764a4ed958 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -764,9 +764,9 @@ nouveau_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 	}
 
 	ret = nouveau_page_flip_emit(chan, old_bo, new_bo, s, &fence);
-	mutex_unlock(&chan->cli->mutex);
 	if (ret)
 		goto fail_unreserve;
+	mutex_unlock(&chan->cli->mutex);
 
 	/* Update the crtc struct and cleanup */
 	crtc->primary->fb = fb;
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index fb187c78978f..c31c12b4e666 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -1177,27 +1177,43 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc,
 
 		/* Set NUM_BANKS. */
 		if (rdev->family >= CHIP_TAHITI) {
-			unsigned tileb, index, num_banks, tile_split_bytes;
+			unsigned index, num_banks;
 
-			/* Calculate the macrotile mode index. */
-			tile_split_bytes = 64 << tile_split;
-			tileb = 8 * 8 * target_fb->bits_per_pixel / 8;
-			tileb = min(tile_split_bytes, tileb);
+			if (rdev->family >= CHIP_BONAIRE) {
+				unsigned tileb, tile_split_bytes;
 
-			for (index = 0; tileb > 64; index++) {
-				tileb >>= 1;
-			}
+				/* Calculate the macrotile mode index. */
+				tile_split_bytes = 64 << tile_split;
+				tileb = 8 * 8 * target_fb->bits_per_pixel / 8;
+				tileb = min(tile_split_bytes, tileb);
 
-			if (index >= 16) {
-				DRM_ERROR("Wrong screen bpp (%u) or tile split (%u)\n",
-					  target_fb->bits_per_pixel, tile_split);
-				return -EINVAL;
-			}
+				for (index = 0; tileb > 64; index++)
+					tileb >>= 1;
+
+				if (index >= 16) {
+					DRM_ERROR("Wrong screen bpp (%u) or tile split (%u)\n",
+						  target_fb->bits_per_pixel, tile_split);
+					return -EINVAL;
+				}
 
-			if (rdev->family >= CHIP_BONAIRE)
 				num_banks = (rdev->config.cik.macrotile_mode_array[index] >> 6) & 0x3;
-			else
+			} else {
+				switch (target_fb->bits_per_pixel) {
+				case 8:
+					index = 10;
+					break;
+				case 16:
+					index = SI_TILE_MODE_COLOR_2D_SCANOUT_16BPP;
+					break;
+				default:
+				case 32:
+					index = SI_TILE_MODE_COLOR_2D_SCANOUT_32BPP;
+					break;
+				}
+
 				num_banks = (rdev->config.si.tile_mode_array[index] >> 20) & 0x3;
+			}
+
 			fb_format |= EVERGREEN_GRPH_NUM_BANKS(num_banks);
 		} else {
 			/* NI and older. */
@@ -1720,8 +1736,9 @@ static int radeon_atom_pick_pll(struct drm_crtc *crtc)
 		}
 		/* otherwise, pick one of the plls */
 		if ((rdev->family == CHIP_KAVERI) ||
-		    (rdev->family == CHIP_KABINI)) {
-			/* KB/KV has PPLL1 and PPLL2 */
+		    (rdev->family == CHIP_KABINI) ||
+		    (rdev->family == CHIP_MULLINS)) {
+			/* KB/KV/ML has PPLL1 and PPLL2 */
 			pll_in_use = radeon_get_pll_use_mask(crtc);
 			if (!(pll_in_use & (1 << ATOM_PPLL2)))
 				return ATOM_PPLL2;
@@ -1885,6 +1902,9 @@ int atombios_crtc_mode_set(struct drm_crtc *crtc,
 	    (ATOM_DEVICE_TV_SUPPORT | ATOM_DEVICE_CV_SUPPORT))
 		is_tvcv = true;
 
+	if (!radeon_crtc->adjusted_clock)
+		return -EINVAL;
+
 	atombios_crtc_set_pll(crtc, adjusted_mode);
 
 	if (ASIC_IS_DCE4(rdev))
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index bc0119fb6c12..54e4f52549af 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -366,11 +366,11 @@ static void radeon_dp_probe_oui(struct radeon_connector *radeon_connector)
 	if (!(dig_connector->dpcd[DP_DOWN_STREAM_PORT_COUNT] & DP_OUI_SUPPORT))
 		return;
 
-	if (drm_dp_dpcd_read(&radeon_connector->ddc_bus->aux, DP_SINK_OUI, buf, 3))
+	if (drm_dp_dpcd_read(&radeon_connector->ddc_bus->aux, DP_SINK_OUI, buf, 3) == 3)
 		DRM_DEBUG_KMS("Sink OUI: %02hx%02hx%02hx\n",
 			      buf[0], buf[1], buf[2]);
 
-	if (drm_dp_dpcd_read(&radeon_connector->ddc_bus->aux, DP_BRANCH_OUI, buf, 3))
+	if (drm_dp_dpcd_read(&radeon_connector->ddc_bus->aux, DP_BRANCH_OUI, buf, 3) == 3)
 		DRM_DEBUG_KMS("Branch OUI: %02hx%02hx%02hx\n",
 			      buf[0], buf[1], buf[2]);
 }
@@ -419,21 +419,23 @@ int radeon_dp_get_panel_mode(struct drm_encoder *encoder,
 
 	if (dp_bridge != ENCODER_OBJECT_ID_NONE) {
 		/* DP bridge chips */
-		drm_dp_dpcd_readb(&radeon_connector->ddc_bus->aux,
-				  DP_EDP_CONFIGURATION_CAP, &tmp);
-		if (tmp & 1)
-			panel_mode = DP_PANEL_MODE_INTERNAL_DP2_MODE;
-		else if ((dp_bridge == ENCODER_OBJECT_ID_NUTMEG) ||
-			 (dp_bridge == ENCODER_OBJECT_ID_TRAVIS))
-			panel_mode = DP_PANEL_MODE_INTERNAL_DP1_MODE;
-		else
-			panel_mode = DP_PANEL_MODE_EXTERNAL_DP_MODE;
+		if (drm_dp_dpcd_readb(&radeon_connector->ddc_bus->aux,
+				      DP_EDP_CONFIGURATION_CAP, &tmp) == 1) {
+			if (tmp & 1)
+				panel_mode = DP_PANEL_MODE_INTERNAL_DP2_MODE;
+			else if ((dp_bridge == ENCODER_OBJECT_ID_NUTMEG) ||
+				 (dp_bridge == ENCODER_OBJECT_ID_TRAVIS))
+				panel_mode = DP_PANEL_MODE_INTERNAL_DP1_MODE;
+			else
+				panel_mode = DP_PANEL_MODE_EXTERNAL_DP_MODE;
+		}
 	} else if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) {
 		/* eDP */
-		drm_dp_dpcd_readb(&radeon_connector->ddc_bus->aux,
-				  DP_EDP_CONFIGURATION_CAP, &tmp);
-		if (tmp & 1)
-			panel_mode = DP_PANEL_MODE_INTERNAL_DP2_MODE;
+		if (drm_dp_dpcd_readb(&radeon_connector->ddc_bus->aux,
+				      DP_EDP_CONFIGURATION_CAP, &tmp) == 1) {
+			if (tmp & 1)
+				panel_mode = DP_PANEL_MODE_INTERNAL_DP2_MODE;
+		}
 	}
 
 	return panel_mode;
@@ -809,11 +811,15 @@ void radeon_dp_link_train(struct drm_encoder *encoder,
 	else
 		dp_info.enc_id |= ATOM_DP_CONFIG_LINK_A;
 
-	drm_dp_dpcd_readb(&radeon_connector->ddc_bus->aux, DP_MAX_LANE_COUNT, &tmp);
-	if (ASIC_IS_DCE5(rdev) && (tmp & DP_TPS3_SUPPORTED))
-		dp_info.tp3_supported = true;
-	else
+	if (drm_dp_dpcd_readb(&radeon_connector->ddc_bus->aux, DP_MAX_LANE_COUNT, &tmp)
+	    == 1) {
+		if (ASIC_IS_DCE5(rdev) && (tmp & DP_TPS3_SUPPORTED))
+			dp_info.tp3_supported = true;
+		else
+			dp_info.tp3_supported = false;
+	} else {
 		dp_info.tp3_supported = false;
+	}
 
 	memcpy(dp_info.dpcd, dig_connector->dpcd, DP_RECEIVER_CAP_SIZE);
 	dp_info.rdev = rdev;
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index 199eb194716f..d2fd98968085 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -63,6 +63,12 @@ MODULE_FIRMWARE("radeon/KABINI_ce.bin");
 MODULE_FIRMWARE("radeon/KABINI_mec.bin");
 MODULE_FIRMWARE("radeon/KABINI_rlc.bin");
 MODULE_FIRMWARE("radeon/KABINI_sdma.bin");
+MODULE_FIRMWARE("radeon/MULLINS_pfp.bin");
+MODULE_FIRMWARE("radeon/MULLINS_me.bin");
+MODULE_FIRMWARE("radeon/MULLINS_ce.bin");
+MODULE_FIRMWARE("radeon/MULLINS_mec.bin");
+MODULE_FIRMWARE("radeon/MULLINS_rlc.bin");
+MODULE_FIRMWARE("radeon/MULLINS_sdma.bin");
 
 extern int r600_ih_ring_alloc(struct radeon_device *rdev);
 extern void r600_ih_ring_fini(struct radeon_device *rdev);
@@ -1473,6 +1479,43 @@ static const u32 hawaii_mgcg_cgcg_init[] =
 	0xd80c, 0xff000ff0, 0x00000100
 };
 
+static const u32 godavari_golden_registers[] =
+{
+	0x55e4, 0xff607fff, 0xfc000100,
+	0x6ed8, 0x00010101, 0x00010000,
+	0x9830, 0xffffffff, 0x00000000,
+	0x98302, 0xf00fffff, 0x00000400,
+	0x6130, 0xffffffff, 0x00010000,
+	0x5bb0, 0x000000f0, 0x00000070,
+	0x5bc0, 0xf0311fff, 0x80300000,
+	0x98f8, 0x73773777, 0x12010001,
+	0x98fc, 0xffffffff, 0x00000010,
+	0x8030, 0x00001f0f, 0x0000100a,
+	0x2f48, 0x73773777, 0x12010001,
+	0x2408, 0x000fffff, 0x000c007f,
+	0x8a14, 0xf000003f, 0x00000007,
+	0x8b24, 0xffffffff, 0x00ff0fff,
+	0x30a04, 0x0000ff0f, 0x00000000,
+	0x28a4c, 0x07ffffff, 0x06000000,
+	0x4d8, 0x00000fff, 0x00000100,
+	0xd014, 0x00010000, 0x00810001,
+	0xd814, 0x00010000, 0x00810001,
+	0x3e78, 0x00000001, 0x00000002,
+	0xc768, 0x00000008, 0x00000008,
+	0xc770, 0x00000f00, 0x00000800,
+	0xc774, 0x00000f00, 0x00000800,
+	0xc798, 0x00ffffff, 0x00ff7fbf,
+	0xc79c, 0x00ffffff, 0x00ff7faf,
+	0x8c00, 0x000000ff, 0x00000001,
+	0x214f8, 0x01ff01ff, 0x00000002,
+	0x21498, 0x007ff800, 0x00200000,
+	0x2015c, 0xffffffff, 0x00000f40,
+	0x88c4, 0x001f3ae3, 0x00000082,
+	0x88d4, 0x0000001f, 0x00000010,
+	0x30934, 0xffffffff, 0x00000000
+};
+
+
 static void cik_init_golden_registers(struct radeon_device *rdev)
 {
 	switch (rdev->family) {
@@ -1504,6 +1547,20 @@ static void cik_init_golden_registers(struct radeon_device *rdev)
 						 kalindi_golden_spm_registers,
 						 (const u32)ARRAY_SIZE(kalindi_golden_spm_registers));
 		break;
+	case CHIP_MULLINS:
+		radeon_program_register_sequence(rdev,
+						 kalindi_mgcg_cgcg_init,
+						 (const u32)ARRAY_SIZE(kalindi_mgcg_cgcg_init));
+		radeon_program_register_sequence(rdev,
+						 godavari_golden_registers,
+						 (const u32)ARRAY_SIZE(godavari_golden_registers));
+		radeon_program_register_sequence(rdev,
+						 kalindi_golden_common_registers,
+						 (const u32)ARRAY_SIZE(kalindi_golden_common_registers));
+		radeon_program_register_sequence(rdev,
+						 kalindi_golden_spm_registers,
+						 (const u32)ARRAY_SIZE(kalindi_golden_spm_registers));
+		break;
 	case CHIP_KAVERI:
 		radeon_program_register_sequence(rdev,
 						 spectre_mgcg_cgcg_init,
@@ -1834,6 +1891,15 @@ static int cik_init_microcode(struct radeon_device *rdev)
 		rlc_req_size = KB_RLC_UCODE_SIZE * 4;
 		sdma_req_size = CIK_SDMA_UCODE_SIZE * 4;
 		break;
+	case CHIP_MULLINS:
+		chip_name = "MULLINS";
+		pfp_req_size = CIK_PFP_UCODE_SIZE * 4;
+		me_req_size = CIK_ME_UCODE_SIZE * 4;
+		ce_req_size = CIK_CE_UCODE_SIZE * 4;
+		mec_req_size = CIK_MEC_UCODE_SIZE * 4;
+		rlc_req_size = ML_RLC_UCODE_SIZE * 4;
+		sdma_req_size = CIK_SDMA_UCODE_SIZE * 4;
+		break;
 	default: BUG();
 	}
 
@@ -3272,6 +3338,7 @@ static void cik_gpu_init(struct radeon_device *rdev)
 		gb_addr_config = BONAIRE_GB_ADDR_CONFIG_GOLDEN;
 		break;
 	case CHIP_KABINI:
+	case CHIP_MULLINS:
 	default:
 		rdev->config.cik.max_shader_engines = 1;
 		rdev->config.cik.max_tile_pipes = 2;
@@ -3702,6 +3769,7 @@ int cik_copy_cpdma(struct radeon_device *rdev,
 	r = radeon_fence_emit(rdev, fence, ring->idx);
 	if (r) {
 		radeon_ring_unlock_undo(rdev, ring);
+		radeon_semaphore_free(rdev, &sem, NULL);
 		return r;
 	}
 
@@ -5800,6 +5868,9 @@ static int cik_rlc_resume(struct radeon_device *rdev)
 	case CHIP_KABINI:
 		size = KB_RLC_UCODE_SIZE;
 		break;
+	case CHIP_MULLINS:
+		size = ML_RLC_UCODE_SIZE;
+		break;
 	}
 
 	cik_rlc_stop(rdev);
@@ -6548,6 +6619,7 @@ void cik_get_csb_buffer(struct radeon_device *rdev, volatile u32 *buffer)
 		buffer[count++] = cpu_to_le32(0x00000000);
 		break;
 	case CHIP_KABINI:
+	case CHIP_MULLINS:
 		buffer[count++] = cpu_to_le32(0x00000000); /* XXX */
 		buffer[count++] = cpu_to_le32(0x00000000);
 		break;
@@ -6693,6 +6765,19 @@ static void cik_disable_interrupt_state(struct radeon_device *rdev)
 		WREG32(LB_INTERRUPT_MASK + EVERGREEN_CRTC4_REGISTER_OFFSET, 0);
 		WREG32(LB_INTERRUPT_MASK + EVERGREEN_CRTC5_REGISTER_OFFSET, 0);
 	}
+	/* pflip */
+	if (rdev->num_crtc >= 2) {
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET, 0);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET, 0);
+	}
+	if (rdev->num_crtc >= 4) {
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET, 0);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET, 0);
+	}
+	if (rdev->num_crtc >= 6) {
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET, 0);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, 0);
+	}
 
 	/* dac hotplug */
 	WREG32(DAC_AUTODETECT_INT_CONTROL, 0);
@@ -7049,6 +7134,25 @@ int cik_irq_set(struct radeon_device *rdev)
 		WREG32(LB_INTERRUPT_MASK + EVERGREEN_CRTC5_REGISTER_OFFSET, crtc6);
 	}
 
+	if (rdev->num_crtc >= 2) {
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
+	}
+	if (rdev->num_crtc >= 4) {
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
+	}
+	if (rdev->num_crtc >= 6) {
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
+	}
+
 	WREG32(DC_HPD1_INT_CONTROL, hpd1);
 	WREG32(DC_HPD2_INT_CONTROL, hpd2);
 	WREG32(DC_HPD3_INT_CONTROL, hpd3);
@@ -7085,6 +7189,29 @@ static inline void cik_irq_ack(struct radeon_device *rdev)
 	rdev->irq.stat_regs.cik.disp_int_cont5 = RREG32(DISP_INTERRUPT_STATUS_CONTINUE5);
 	rdev->irq.stat_regs.cik.disp_int_cont6 = RREG32(DISP_INTERRUPT_STATUS_CONTINUE6);
 
+	rdev->irq.stat_regs.cik.d1grph_int = RREG32(GRPH_INT_STATUS +
+		EVERGREEN_CRTC0_REGISTER_OFFSET);
+	rdev->irq.stat_regs.cik.d2grph_int = RREG32(GRPH_INT_STATUS +
+		EVERGREEN_CRTC1_REGISTER_OFFSET);
+	if (rdev->num_crtc >= 4) {
+		rdev->irq.stat_regs.cik.d3grph_int = RREG32(GRPH_INT_STATUS +
+			EVERGREEN_CRTC2_REGISTER_OFFSET);
+		rdev->irq.stat_regs.cik.d4grph_int = RREG32(GRPH_INT_STATUS +
+			EVERGREEN_CRTC3_REGISTER_OFFSET);
+	}
+	if (rdev->num_crtc >= 6) {
+		rdev->irq.stat_regs.cik.d5grph_int = RREG32(GRPH_INT_STATUS +
+			EVERGREEN_CRTC4_REGISTER_OFFSET);
+		rdev->irq.stat_regs.cik.d6grph_int = RREG32(GRPH_INT_STATUS +
+			EVERGREEN_CRTC5_REGISTER_OFFSET);
+	}
+
+	if (rdev->irq.stat_regs.cik.d1grph_int & GRPH_PFLIP_INT_OCCURRED)
+		WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC0_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_CLEAR);
+	if (rdev->irq.stat_regs.cik.d2grph_int & GRPH_PFLIP_INT_OCCURRED)
+		WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC1_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_CLEAR);
 	if (rdev->irq.stat_regs.cik.disp_int & LB_D1_VBLANK_INTERRUPT)
 		WREG32(LB_VBLANK_STATUS + EVERGREEN_CRTC0_REGISTER_OFFSET, VBLANK_ACK);
 	if (rdev->irq.stat_regs.cik.disp_int & LB_D1_VLINE_INTERRUPT)
@@ -7095,6 +7222,12 @@ static inline void cik_irq_ack(struct radeon_device *rdev)
 		WREG32(LB_VLINE_STATUS + EVERGREEN_CRTC1_REGISTER_OFFSET, VLINE_ACK);
 
 	if (rdev->num_crtc >= 4) {
+		if (rdev->irq.stat_regs.cik.d3grph_int & GRPH_PFLIP_INT_OCCURRED)
+			WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC2_REGISTER_OFFSET,
+			       GRPH_PFLIP_INT_CLEAR);
+		if (rdev->irq.stat_regs.cik.d4grph_int & GRPH_PFLIP_INT_OCCURRED)
+			WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC3_REGISTER_OFFSET,
+			       GRPH_PFLIP_INT_CLEAR);
 		if (rdev->irq.stat_regs.cik.disp_int_cont2 & LB_D3_VBLANK_INTERRUPT)
 			WREG32(LB_VBLANK_STATUS + EVERGREEN_CRTC2_REGISTER_OFFSET, VBLANK_ACK);
 		if (rdev->irq.stat_regs.cik.disp_int_cont2 & LB_D3_VLINE_INTERRUPT)
@@ -7106,6 +7239,12 @@ static inline void cik_irq_ack(struct radeon_device *rdev)
 	}
 
 	if (rdev->num_crtc >= 6) {
+		if (rdev->irq.stat_regs.cik.d5grph_int & GRPH_PFLIP_INT_OCCURRED)
+			WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC4_REGISTER_OFFSET,
+			       GRPH_PFLIP_INT_CLEAR);
+		if (rdev->irq.stat_regs.cik.d6grph_int & GRPH_PFLIP_INT_OCCURRED)
+			WREG32(GRPH_INT_STATUS + EVERGREEN_CRTC5_REGISTER_OFFSET,
+			       GRPH_PFLIP_INT_CLEAR);
 		if (rdev->irq.stat_regs.cik.disp_int_cont4 & LB_D5_VBLANK_INTERRUPT)
 			WREG32(LB_VBLANK_STATUS + EVERGREEN_CRTC4_REGISTER_OFFSET, VBLANK_ACK);
 		if (rdev->irq.stat_regs.cik.disp_int_cont4 & LB_D5_VLINE_INTERRUPT)
@@ -7457,6 +7596,15 @@ restart_ih:
 				break;
 			}
 			break;
+		case 8: /* D1 page flip */
+		case 10: /* D2 page flip */
+		case 12: /* D3 page flip */
+		case 14: /* D4 page flip */
+		case 16: /* D5 page flip */
+		case 18: /* D6 page flip */
+			DRM_DEBUG("IH: D%d flip\n", ((src_id - 8) >> 1) + 1);
+			radeon_crtc_handle_flip(rdev, (src_id - 8) >> 1);
+			break;
 		case 42: /* HPD hotplug */
 			switch (src_data) {
 			case 0:
diff --git a/drivers/gpu/drm/radeon/cik_sdma.c b/drivers/gpu/drm/radeon/cik_sdma.c
index f7e46cf682af..72e464c79a88 100644
--- a/drivers/gpu/drm/radeon/cik_sdma.c
+++ b/drivers/gpu/drm/radeon/cik_sdma.c
@@ -562,6 +562,7 @@ int cik_copy_dma(struct radeon_device *rdev,
 	r = radeon_fence_emit(rdev, fence, ring->idx);
 	if (r) {
 		radeon_ring_unlock_undo(rdev, ring);
+		radeon_semaphore_free(rdev, &sem, NULL);
 		return r;
 	}
 
diff --git a/drivers/gpu/drm/radeon/cikd.h b/drivers/gpu/drm/radeon/cikd.h
index 213873270d5f..dd7926394a8f 100644
--- a/drivers/gpu/drm/radeon/cikd.h
+++ b/drivers/gpu/drm/radeon/cikd.h
@@ -888,6 +888,15 @@
 #       define DC_HPD6_RX_INTERRUPT                     (1 << 18)
 #define DISP_INTERRUPT_STATUS_CONTINUE6                 0x6780
 
+/* 0x6858, 0x7458, 0x10058, 0x10c58, 0x11858, 0x12458 */
+#define GRPH_INT_STATUS                                 0x6858
+#       define GRPH_PFLIP_INT_OCCURRED                  (1 << 0)
+#       define GRPH_PFLIP_INT_CLEAR                     (1 << 8)
+/* 0x685c, 0x745c, 0x1005c, 0x10c5c, 0x1185c, 0x1245c */
+#define GRPH_INT_CONTROL                                0x685c
+#       define GRPH_PFLIP_INT_MASK                      (1 << 0)
+#       define GRPH_PFLIP_INT_TYPE                      (1 << 8)
+
 #define	DAC_AUTODETECT_INT_CONTROL			0x67c8
 
 #define DC_HPD1_INT_STATUS                              0x601c
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index b406546440da..0f7a51a3694f 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -4371,7 +4371,6 @@ int evergreen_irq_set(struct radeon_device *rdev)
 	u32 crtc1 = 0, crtc2 = 0, crtc3 = 0, crtc4 = 0, crtc5 = 0, crtc6 = 0;
 	u32 hpd1, hpd2, hpd3, hpd4, hpd5, hpd6;
 	u32 grbm_int_cntl = 0;
-	u32 grph1 = 0, grph2 = 0, grph3 = 0, grph4 = 0, grph5 = 0, grph6 = 0;
 	u32 afmt1 = 0, afmt2 = 0, afmt3 = 0, afmt4 = 0, afmt5 = 0, afmt6 = 0;
 	u32 dma_cntl, dma_cntl1 = 0;
 	u32 thermal_int = 0;
@@ -4554,15 +4553,21 @@ int evergreen_irq_set(struct radeon_device *rdev)
 		WREG32(INT_MASK + EVERGREEN_CRTC5_REGISTER_OFFSET, crtc6);
 	}
 
-	WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET, grph1);
-	WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET, grph2);
+	WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET,
+	       GRPH_PFLIP_INT_MASK);
+	WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET,
+	       GRPH_PFLIP_INT_MASK);
 	if (rdev->num_crtc >= 4) {
-		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET, grph3);
-		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET, grph4);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
 	}
 	if (rdev->num_crtc >= 6) {
-		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET, grph5);
-		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, grph6);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
 	}
 
 	WREG32(DC_HPD1_INT_CONTROL, hpd1);
@@ -4951,6 +4956,15 @@ restart_ih:
 				break;
 			}
 			break;
+		case 8: /* D1 page flip */
+		case 10: /* D2 page flip */
+		case 12: /* D3 page flip */
+		case 14: /* D4 page flip */
+		case 16: /* D5 page flip */
+		case 18: /* D6 page flip */
+			DRM_DEBUG("IH: D%d flip\n", ((src_id - 8) >> 1) + 1);
+			radeon_crtc_handle_flip(rdev, (src_id - 8) >> 1);
+			break;
 		case 42: /* HPD hotplug */
 			switch (src_data) {
 			case 0:
diff --git a/drivers/gpu/drm/radeon/evergreen_dma.c b/drivers/gpu/drm/radeon/evergreen_dma.c
index 287fe966d7de..478caefe0fef 100644
--- a/drivers/gpu/drm/radeon/evergreen_dma.c
+++ b/drivers/gpu/drm/radeon/evergreen_dma.c
@@ -151,6 +151,7 @@ int evergreen_copy_dma(struct radeon_device *rdev,
 	r = radeon_fence_emit(rdev, fence, ring->idx);
 	if (r) {
 		radeon_ring_unlock_undo(rdev, ring);
+		radeon_semaphore_free(rdev, &sem, NULL);
 		return r;
 	}
 
diff --git a/drivers/gpu/drm/radeon/kv_dpm.c b/drivers/gpu/drm/radeon/kv_dpm.c
index 16ec9d56a234..3f6e817d97ee 100644
--- a/drivers/gpu/drm/radeon/kv_dpm.c
+++ b/drivers/gpu/drm/radeon/kv_dpm.c
@@ -546,6 +546,52 @@ static int kv_set_divider_value(struct radeon_device *rdev,
 	return 0;
 }
 
+static u32 kv_convert_vid2_to_vid7(struct radeon_device *rdev,
+				   struct sumo_vid_mapping_table *vid_mapping_table,
+				   u32 vid_2bit)
+{
+	struct radeon_clock_voltage_dependency_table *vddc_sclk_table =
+		&rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk;
+	u32 i;
+
+	if (vddc_sclk_table && vddc_sclk_table->count) {
+		if (vid_2bit < vddc_sclk_table->count)
+			return vddc_sclk_table->entries[vid_2bit].v;
+		else
+			return vddc_sclk_table->entries[vddc_sclk_table->count - 1].v;
+	} else {
+		for (i = 0; i < vid_mapping_table->num_entries; i++) {
+			if (vid_mapping_table->entries[i].vid_2bit == vid_2bit)
+				return vid_mapping_table->entries[i].vid_7bit;
+		}
+		return vid_mapping_table->entries[vid_mapping_table->num_entries - 1].vid_7bit;
+	}
+}
+
+static u32 kv_convert_vid7_to_vid2(struct radeon_device *rdev,
+				   struct sumo_vid_mapping_table *vid_mapping_table,
+				   u32 vid_7bit)
+{
+	struct radeon_clock_voltage_dependency_table *vddc_sclk_table =
+		&rdev->pm.dpm.dyn_state.vddc_dependency_on_sclk;
+	u32 i;
+
+	if (vddc_sclk_table && vddc_sclk_table->count) {
+		for (i = 0; i < vddc_sclk_table->count; i++) {
+			if (vddc_sclk_table->entries[i].v == vid_7bit)
+				return i;
+		}
+		return vddc_sclk_table->count - 1;
+	} else {
+		for (i = 0; i < vid_mapping_table->num_entries; i++) {
+			if (vid_mapping_table->entries[i].vid_7bit == vid_7bit)
+				return vid_mapping_table->entries[i].vid_2bit;
+		}
+
+		return vid_mapping_table->entries[vid_mapping_table->num_entries - 1].vid_2bit;
+	}
+}
+
 static u16 kv_convert_8bit_index_to_voltage(struct radeon_device *rdev,
 					    u16 voltage)
 {
@@ -556,9 +602,9 @@ static u16 kv_convert_2bit_index_to_voltage(struct radeon_device *rdev,
 					    u32 vid_2bit)
 {
 	struct kv_power_info *pi = kv_get_pi(rdev);
-	u32 vid_8bit = sumo_convert_vid2_to_vid7(rdev,
-						 &pi->sys_info.vid_mapping_table,
-						 vid_2bit);
+	u32 vid_8bit = kv_convert_vid2_to_vid7(rdev,
+					       &pi->sys_info.vid_mapping_table,
+					       vid_2bit);
 
 	return kv_convert_8bit_index_to_voltage(rdev, (u16)vid_8bit);
 }
@@ -639,7 +685,7 @@ static int kv_force_lowest_valid(struct radeon_device *rdev)
 
 static int kv_unforce_levels(struct radeon_device *rdev)
 {
-	if (rdev->family == CHIP_KABINI)
+	if (rdev->family == CHIP_KABINI || rdev->family == CHIP_MULLINS)
 		return kv_notify_message_to_smu(rdev, PPSMC_MSG_NoForcedLevel);
 	else
 		return kv_set_enabled_levels(rdev);
@@ -1362,13 +1408,20 @@ static int kv_update_uvd_dpm(struct radeon_device *rdev, bool gate)
 	struct radeon_uvd_clock_voltage_dependency_table *table =
 		&rdev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table;
 	int ret;
+	u32 mask;
 
 	if (!gate) {
-		if (!pi->caps_uvd_dpm || table->count || pi->caps_stable_p_state)
+		if (table->count)
 			pi->uvd_boot_level = table->count - 1;
 		else
 			pi->uvd_boot_level = 0;
 
+		if (!pi->caps_uvd_dpm || pi->caps_stable_p_state) {
+			mask = 1 << pi->uvd_boot_level;
+		} else {
+			mask = 0x1f;
+		}
+
 		ret = kv_copy_bytes_to_smc(rdev,
 					   pi->dpm_table_start +
 					   offsetof(SMU7_Fusion_DpmTable, UvdBootLevel),
@@ -1377,11 +1430,9 @@ static int kv_update_uvd_dpm(struct radeon_device *rdev, bool gate)
 		if (ret)
 			return ret;
 
-		if (!pi->caps_uvd_dpm ||
-		    pi->caps_stable_p_state)
-			kv_send_msg_to_smc_with_parameter(rdev,
-							  PPSMC_MSG_UVDDPM_SetEnabledMask,
-							  (1 << pi->uvd_boot_level));
+		kv_send_msg_to_smc_with_parameter(rdev,
+						  PPSMC_MSG_UVDDPM_SetEnabledMask,
+						  mask);
 	}
 
 	return kv_enable_uvd_dpm(rdev, !gate);
@@ -1617,7 +1668,7 @@ static void kv_dpm_powergate_acp(struct radeon_device *rdev, bool gate)
 	if (pi->acp_power_gated == gate)
 		return;
 
-	if (rdev->family == CHIP_KABINI)
+	if (rdev->family == CHIP_KABINI || rdev->family == CHIP_MULLINS)
 		return;
 
 	pi->acp_power_gated = gate;
@@ -1786,7 +1837,7 @@ int kv_dpm_set_power_state(struct radeon_device *rdev)
 		}
 	}
 
-	if (rdev->family == CHIP_KABINI) {
+	if (rdev->family == CHIP_KABINI || rdev->family == CHIP_MULLINS) {
 		if (pi->enable_dpm) {
 			kv_set_valid_clock_range(rdev, new_ps);
 			kv_update_dfs_bypass_settings(rdev, new_ps);
@@ -1812,6 +1863,8 @@ int kv_dpm_set_power_state(struct radeon_device *rdev)
 				return ret;
 			}
 			kv_update_sclk_t(rdev);
+			if (rdev->family == CHIP_MULLINS)
+				kv_enable_nb_dpm(rdev);
 		}
 	} else {
 		if (pi->enable_dpm) {
@@ -1862,7 +1915,7 @@ void kv_dpm_reset_asic(struct radeon_device *rdev)
 {
 	struct kv_power_info *pi = kv_get_pi(rdev);
 
-	if (rdev->family == CHIP_KABINI) {
+	if (rdev->family == CHIP_KABINI || rdev->family == CHIP_MULLINS) {
 		kv_force_lowest_valid(rdev);
 		kv_init_graphics_levels(rdev);
 		kv_program_bootup_state(rdev);
@@ -1901,14 +1954,41 @@ static void kv_construct_max_power_limits_table(struct radeon_device *rdev,
 static void kv_patch_voltage_values(struct radeon_device *rdev)
 {
 	int i;
-	struct radeon_uvd_clock_voltage_dependency_table *table =
+	struct radeon_uvd_clock_voltage_dependency_table *uvd_table =
 		&rdev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table;
+	struct radeon_vce_clock_voltage_dependency_table *vce_table =
+		&rdev->pm.dpm.dyn_state.vce_clock_voltage_dependency_table;
+	struct radeon_clock_voltage_dependency_table *samu_table =
+		&rdev->pm.dpm.dyn_state.samu_clock_voltage_dependency_table;
+	struct radeon_clock_voltage_dependency_table *acp_table =
+		&rdev->pm.dpm.dyn_state.acp_clock_voltage_dependency_table;
 
-	if (table->count) {
-		for (i = 0; i < table->count; i++)
-			table->entries[i].v =
+	if (uvd_table->count) {
+		for (i = 0; i < uvd_table->count; i++)
+			uvd_table->entries[i].v =
 				kv_convert_8bit_index_to_voltage(rdev,
-								 table->entries[i].v);
+								 uvd_table->entries[i].v);
+	}
+
+	if (vce_table->count) {
+		for (i = 0; i < vce_table->count; i++)
+			vce_table->entries[i].v =
+				kv_convert_8bit_index_to_voltage(rdev,
+								 vce_table->entries[i].v);
+	}
+
+	if (samu_table->count) {
+		for (i = 0; i < samu_table->count; i++)
+			samu_table->entries[i].v =
+				kv_convert_8bit_index_to_voltage(rdev,
+								 samu_table->entries[i].v);
+	}
+
+	if (acp_table->count) {
+		for (i = 0; i < acp_table->count; i++)
+			acp_table->entries[i].v =
+				kv_convert_8bit_index_to_voltage(rdev,
+								 acp_table->entries[i].v);
 	}
 
 }
@@ -1941,7 +2021,7 @@ static int kv_force_dpm_highest(struct radeon_device *rdev)
 			break;
 	}
 
-	if (rdev->family == CHIP_KABINI)
+	if (rdev->family == CHIP_KABINI || rdev->family == CHIP_MULLINS)
 		return kv_send_msg_to_smc_with_parameter(rdev, PPSMC_MSG_DPM_ForceState, i);
 	else
 		return kv_set_enabled_level(rdev, i);
@@ -1961,7 +2041,7 @@ static int kv_force_dpm_lowest(struct radeon_device *rdev)
 			break;
 	}
 
-	if (rdev->family == CHIP_KABINI)
+	if (rdev->family == CHIP_KABINI || rdev->family == CHIP_MULLINS)
 		return kv_send_msg_to_smc_with_parameter(rdev, PPSMC_MSG_DPM_ForceState, i);
 	else
 		return kv_set_enabled_level(rdev, i);
@@ -2118,7 +2198,7 @@ static void kv_apply_state_adjust_rules(struct radeon_device *rdev,
 	else
 		pi->battery_state = false;
 
-	if (rdev->family == CHIP_KABINI) {
+	if (rdev->family == CHIP_KABINI || rdev->family == CHIP_MULLINS) {
 		ps->dpm0_pg_nb_ps_lo = 0x1;
 		ps->dpm0_pg_nb_ps_hi = 0x0;
 		ps->dpmx_nb_ps_lo = 0x1;
@@ -2179,7 +2259,7 @@ static int kv_calculate_nbps_level_settings(struct radeon_device *rdev)
 	if (pi->lowest_valid > pi->highest_valid)
 		return -EINVAL;
 
-	if (rdev->family == CHIP_KABINI) {
+	if (rdev->family == CHIP_KABINI || rdev->family == CHIP_MULLINS) {
 		for (i = pi->lowest_valid; i <= pi->highest_valid; i++) {
 			pi->graphics_level[i].GnbSlow = 1;
 			pi->graphics_level[i].ForceNbPs1 = 0;
@@ -2253,9 +2333,9 @@ static void kv_init_graphics_levels(struct radeon_device *rdev)
 				break;
 
 			kv_set_divider_value(rdev, i, table->entries[i].clk);
-			vid_2bit = sumo_convert_vid7_to_vid2(rdev,
-							     &pi->sys_info.vid_mapping_table,
-							     table->entries[i].v);
+			vid_2bit = kv_convert_vid7_to_vid2(rdev,
+							   &pi->sys_info.vid_mapping_table,
+							   table->entries[i].v);
 			kv_set_vid(rdev, i, vid_2bit);
 			kv_set_at(rdev, i, pi->at[i]);
 			kv_dpm_power_level_enabled_for_throttle(rdev, i, true);
@@ -2324,7 +2404,7 @@ static void kv_program_nbps_index_settings(struct radeon_device *rdev,
 	struct kv_power_info *pi = kv_get_pi(rdev);
 	u32 nbdpmconfig1;
 
-	if (rdev->family == CHIP_KABINI)
+	if (rdev->family == CHIP_KABINI || rdev->family == CHIP_MULLINS)
 		return;
 
 	if (pi->sys_info.nb_dpm_enable) {
@@ -2631,9 +2711,6 @@ int kv_dpm_init(struct radeon_device *rdev)
 
         pi->sram_end = SMC_RAM_END;
 
-	if (rdev->family == CHIP_KABINI)
-		pi->high_voltage_t = 4001;
-
 	pi->enable_nb_dpm = true;
 
 	pi->caps_power_containment = true;
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 6e887d004eba..bbc189fd3ddc 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -2839,6 +2839,7 @@ int r600_copy_cpdma(struct radeon_device *rdev,
 	r = radeon_fence_emit(rdev, fence, ring->idx);
 	if (r) {
 		radeon_ring_unlock_undo(rdev, ring);
+		radeon_semaphore_free(rdev, &sem, NULL);
 		return r;
 	}
 
@@ -3505,7 +3506,6 @@ int r600_irq_set(struct radeon_device *rdev)
 	u32 hpd1, hpd2, hpd3, hpd4 = 0, hpd5 = 0, hpd6 = 0;
 	u32 grbm_int_cntl = 0;
 	u32 hdmi0, hdmi1;
-	u32 d1grph = 0, d2grph = 0;
 	u32 dma_cntl;
 	u32 thermal_int = 0;
 
@@ -3614,8 +3614,8 @@ int r600_irq_set(struct radeon_device *rdev)
 	WREG32(CP_INT_CNTL, cp_int_cntl);
 	WREG32(DMA_CNTL, dma_cntl);
 	WREG32(DxMODE_INT_MASK, mode_int);
-	WREG32(D1GRPH_INTERRUPT_CONTROL, d1grph);
-	WREG32(D2GRPH_INTERRUPT_CONTROL, d2grph);
+	WREG32(D1GRPH_INTERRUPT_CONTROL, DxGRPH_PFLIP_INT_MASK);
+	WREG32(D2GRPH_INTERRUPT_CONTROL, DxGRPH_PFLIP_INT_MASK);
 	WREG32(GRBM_INT_CNTL, grbm_int_cntl);
 	if (ASIC_IS_DCE3(rdev)) {
 		WREG32(DC_HPD1_INT_CONTROL, hpd1);
@@ -3918,6 +3918,14 @@ restart_ih:
 				break;
 			}
 			break;
+		case 9: /* D1 pflip */
+			DRM_DEBUG("IH: D1 flip\n");
+			radeon_crtc_handle_flip(rdev, 0);
+			break;
+		case 11: /* D2 pflip */
+			DRM_DEBUG("IH: D2 flip\n");
+			radeon_crtc_handle_flip(rdev, 1);
+			break;
 		case 19: /* HPD/DAC hotplug */
 			switch (src_data) {
 			case 0:
diff --git a/drivers/gpu/drm/radeon/r600_dma.c b/drivers/gpu/drm/radeon/r600_dma.c
index 53fcb28f5578..4969cef44a19 100644
--- a/drivers/gpu/drm/radeon/r600_dma.c
+++ b/drivers/gpu/drm/radeon/r600_dma.c
@@ -489,6 +489,7 @@ int r600_copy_dma(struct radeon_device *rdev,
 	r = radeon_fence_emit(rdev, fence, ring->idx);
 	if (r) {
 		radeon_ring_unlock_undo(rdev, ring);
+		radeon_semaphore_free(rdev, &sem, NULL);
 		return r;
 	}
 
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index b58e1afdda76..8149e7cf4303 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -730,6 +730,12 @@ struct cik_irq_stat_regs {
 	u32 disp_int_cont4;
 	u32 disp_int_cont5;
 	u32 disp_int_cont6;
+	u32 d1grph_int;
+	u32 d2grph_int;
+	u32 d3grph_int;
+	u32 d4grph_int;
+	u32 d5grph_int;
+	u32 d6grph_int;
 };
 
 union radeon_irq_stat_regs {
@@ -1636,6 +1642,7 @@ struct radeon_vce {
 	unsigned		fb_version;
 	atomic_t		handles[RADEON_MAX_VCE_HANDLES];
 	struct drm_file		*filp[RADEON_MAX_VCE_HANDLES];
+	unsigned		img_size[RADEON_MAX_VCE_HANDLES];
 	struct delayed_work	idle_work;
 };
 
@@ -1649,7 +1656,7 @@ int radeon_vce_get_destroy_msg(struct radeon_device *rdev, int ring,
 			       uint32_t handle, struct radeon_fence **fence);
 void radeon_vce_free_handles(struct radeon_device *rdev, struct drm_file *filp);
 void radeon_vce_note_usage(struct radeon_device *rdev);
-int radeon_vce_cs_reloc(struct radeon_cs_parser *p, int lo, int hi);
+int radeon_vce_cs_reloc(struct radeon_cs_parser *p, int lo, int hi, unsigned size);
 int radeon_vce_cs_parse(struct radeon_cs_parser *p);
 bool radeon_vce_semaphore_emit(struct radeon_device *rdev,
 			       struct radeon_ring *ring,
@@ -2634,7 +2641,8 @@ void r100_pll_errata_after_index(struct radeon_device *rdev);
 #define ASIC_IS_DCE8(rdev) ((rdev->family >= CHIP_BONAIRE))
 #define ASIC_IS_DCE81(rdev) ((rdev->family == CHIP_KAVERI))
 #define ASIC_IS_DCE82(rdev) ((rdev->family == CHIP_BONAIRE))
-#define ASIC_IS_DCE83(rdev) ((rdev->family == CHIP_KABINI))
+#define ASIC_IS_DCE83(rdev) ((rdev->family == CHIP_KABINI) || \
+			     (rdev->family == CHIP_MULLINS))
 
 #define ASIC_IS_LOMBOK(rdev) ((rdev->ddev->pdev->device == 0x6849) || \
 			      (rdev->ddev->pdev->device == 0x6850) || \
diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index b8a24a75d4ff..be20e62dac83 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -2516,6 +2516,7 @@ int radeon_asic_init(struct radeon_device *rdev)
 		break;
 	case CHIP_KAVERI:
 	case CHIP_KABINI:
+	case CHIP_MULLINS:
 		rdev->asic = &kv_asic;
 		/* set num crtcs */
 		if (rdev->family == CHIP_KAVERI) {
diff --git a/drivers/gpu/drm/radeon/radeon_bios.c b/drivers/gpu/drm/radeon/radeon_bios.c
index b3633d9a5317..9ab30976287d 100644
--- a/drivers/gpu/drm/radeon/radeon_bios.c
+++ b/drivers/gpu/drm/radeon/radeon_bios.c
@@ -196,6 +196,20 @@ static bool radeon_atrm_get_bios(struct radeon_device *rdev)
 		}
 	}
 
+	if (!found) {
+		while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_OTHER << 8, pdev)) != NULL) {
+			dhandle = ACPI_HANDLE(&pdev->dev);
+			if (!dhandle)
+				continue;
+
+			status = acpi_get_handle(dhandle, "ATRM", &atrm_handle);
+			if (!ACPI_FAILURE(status)) {
+				found = true;
+				break;
+			}
+		}
+	}
+
 	if (!found)
 		return false;
 
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 511fe26198e4..0e770bbf7e29 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -99,6 +99,7 @@ static const char radeon_family_name[][16] = {
 	"KAVERI",
 	"KABINI",
 	"HAWAII",
+	"MULLINS",
 	"LAST",
 };
 
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index 8d99d5ee8014..f00dbbf4d806 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -284,6 +284,10 @@ void radeon_crtc_handle_flip(struct radeon_device *rdev, int crtc_id)
 	u32 update_pending;
 	int vpos, hpos;
 
+	/* can happen during initialization */
+	if (radeon_crtc == NULL)
+		return;
+
 	spin_lock_irqsave(&rdev->ddev->event_lock, flags);
 	work = radeon_crtc->unpin_work;
 	if (work == NULL ||
@@ -826,14 +830,14 @@ static void avivo_reduce_ratio(unsigned *nom, unsigned *den,
 
 	/* make sure nominator is large enough */
         if (*nom < nom_min) {
-		tmp = (nom_min + *nom - 1) / *nom;
+		tmp = DIV_ROUND_UP(nom_min, *nom);
 		*nom *= tmp;
 		*den *= tmp;
 	}
 
 	/* make sure the denominator is large enough */
 	if (*den < den_min) {
-		tmp = (den_min + *den - 1) / *den;
+		tmp = DIV_ROUND_UP(den_min, *den);
 		*nom *= tmp;
 		*den *= tmp;
 	}
@@ -858,7 +862,7 @@ static void avivo_get_fb_ref_div(unsigned nom, unsigned den, unsigned post_div,
 				 unsigned *fb_div, unsigned *ref_div)
 {
 	/* limit reference * post divider to a maximum */
-	ref_div_max = min(210 / post_div, ref_div_max);
+	ref_div_max = min(128 / post_div, ref_div_max);
 
 	/* get matching reference and feedback divider */
 	*ref_div = min(max(DIV_ROUND_CLOSEST(den, post_div), 1u), ref_div_max);
@@ -993,6 +997,16 @@ void radeon_compute_pll_avivo(struct radeon_pll *pll,
 	/* this also makes sure that the reference divider is large enough */
 	avivo_reduce_ratio(&fb_div, &ref_div, fb_div_min, ref_div_min);
 
+	/* avoid high jitter with small fractional dividers */
+	if (pll->flags & RADEON_PLL_USE_FRAC_FB_DIV && (fb_div % 10)) {
+		fb_div_min = max(fb_div_min, (9 - (fb_div % 10)) * 20 + 50);
+		if (fb_div < fb_div_min) {
+			unsigned tmp = DIV_ROUND_UP(fb_div_min, fb_div);
+			fb_div *= tmp;
+			ref_div *= tmp;
+		}
+	}
+
 	/* and finally save the result */
 	if (pll->flags & RADEON_PLL_USE_FRAC_FB_DIV) {
 		*fb_div_p = fb_div / 10;
diff --git a/drivers/gpu/drm/radeon/radeon_family.h b/drivers/gpu/drm/radeon/radeon_family.h
index 9da5da4ffd17..4b7b87f71a63 100644
--- a/drivers/gpu/drm/radeon/radeon_family.h
+++ b/drivers/gpu/drm/radeon/radeon_family.h
@@ -97,6 +97,7 @@ enum radeon_family {
 	CHIP_KAVERI,
 	CHIP_KABINI,
 	CHIP_HAWAII,
+	CHIP_MULLINS,
 	CHIP_LAST,
 };
 
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 0cc47f12d995..eaaedba04675 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -577,28 +577,29 @@ int radeon_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
 			return r;
 		}
 
-		r = radeon_bo_reserve(rdev->ring_tmp_bo.bo, false);
-		if (r) {
-			radeon_vm_fini(rdev, &fpriv->vm);
-			kfree(fpriv);
-			return r;
-		}
+		if (rdev->accel_working) {
+			r = radeon_bo_reserve(rdev->ring_tmp_bo.bo, false);
+			if (r) {
+				radeon_vm_fini(rdev, &fpriv->vm);
+				kfree(fpriv);
+				return r;
+			}
 
-		/* map the ib pool buffer read only into
-		 * virtual address space */
-		bo_va = radeon_vm_bo_add(rdev, &fpriv->vm,
-					 rdev->ring_tmp_bo.bo);
-		r = radeon_vm_bo_set_addr(rdev, bo_va, RADEON_VA_IB_OFFSET,
-					  RADEON_VM_PAGE_READABLE |
-					  RADEON_VM_PAGE_SNOOPED);
+			/* map the ib pool buffer read only into
+			 * virtual address space */
+			bo_va = radeon_vm_bo_add(rdev, &fpriv->vm,
+						 rdev->ring_tmp_bo.bo);
+			r = radeon_vm_bo_set_addr(rdev, bo_va, RADEON_VA_IB_OFFSET,
+						  RADEON_VM_PAGE_READABLE |
+						  RADEON_VM_PAGE_SNOOPED);
 
-		radeon_bo_unreserve(rdev->ring_tmp_bo.bo);
-		if (r) {
-			radeon_vm_fini(rdev, &fpriv->vm);
-			kfree(fpriv);
-			return r;
+			radeon_bo_unreserve(rdev->ring_tmp_bo.bo);
+			if (r) {
+				radeon_vm_fini(rdev, &fpriv->vm);
+				kfree(fpriv);
+				return r;
+			}
 		}
-
 		file_priv->driver_priv = fpriv;
 	}
 
@@ -626,13 +627,15 @@ void radeon_driver_postclose_kms(struct drm_device *dev,
 		struct radeon_bo_va *bo_va;
 		int r;
 
-		r = radeon_bo_reserve(rdev->ring_tmp_bo.bo, false);
-		if (!r) {
-			bo_va = radeon_vm_bo_find(&fpriv->vm,
-						  rdev->ring_tmp_bo.bo);
-			if (bo_va)
-				radeon_vm_bo_rmv(rdev, bo_va);
-			radeon_bo_unreserve(rdev->ring_tmp_bo.bo);
+		if (rdev->accel_working) {
+			r = radeon_bo_reserve(rdev->ring_tmp_bo.bo, false);
+			if (!r) {
+				bo_va = radeon_vm_bo_find(&fpriv->vm,
+							  rdev->ring_tmp_bo.bo);
+				if (bo_va)
+					radeon_vm_bo_rmv(rdev, bo_va);
+				radeon_bo_unreserve(rdev->ring_tmp_bo.bo);
+			}
 		}
 
 		radeon_vm_fini(rdev, &fpriv->vm);
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 19bec0dbfa38..4faa4d6f9bb4 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -458,7 +458,7 @@ int radeon_bo_list_validate(struct radeon_device *rdev,
 			 * into account. We don't want to disallow buffer moves
 			 * completely.
 			 */
-			if (current_domain != RADEON_GEM_DOMAIN_CPU &&
+			if ((lobj->alt_domain & current_domain) != 0 &&
 			    (domain & current_domain) == 0 && /* will be moved */
 			    bytes_moved > bytes_moved_threshold) {
 				/* don't move it */
@@ -699,22 +699,30 @@ int radeon_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 	rbo = container_of(bo, struct radeon_bo, tbo);
 	radeon_bo_check_tiling(rbo, 0, 0);
 	rdev = rbo->rdev;
-	if (bo->mem.mem_type == TTM_PL_VRAM) {
-		size = bo->mem.num_pages << PAGE_SHIFT;
-		offset = bo->mem.start << PAGE_SHIFT;
-		if ((offset + size) > rdev->mc.visible_vram_size) {
-			/* hurrah the memory is not visible ! */
-			radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_VRAM);
-			rbo->placement.lpfn = rdev->mc.visible_vram_size >> PAGE_SHIFT;
-			r = ttm_bo_validate(bo, &rbo->placement, false, false);
-			if (unlikely(r != 0))
-				return r;
-			offset = bo->mem.start << PAGE_SHIFT;
-			/* this should not happen */
-			if ((offset + size) > rdev->mc.visible_vram_size)
-				return -EINVAL;
-		}
+	if (bo->mem.mem_type != TTM_PL_VRAM)
+		return 0;
+
+	size = bo->mem.num_pages << PAGE_SHIFT;
+	offset = bo->mem.start << PAGE_SHIFT;
+	if ((offset + size) <= rdev->mc.visible_vram_size)
+		return 0;
+
+	/* hurrah the memory is not visible ! */
+	radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_VRAM);
+	rbo->placement.lpfn = rdev->mc.visible_vram_size >> PAGE_SHIFT;
+	r = ttm_bo_validate(bo, &rbo->placement, false, false);
+	if (unlikely(r == -ENOMEM)) {
+		radeon_ttm_placement_from_domain(rbo, RADEON_GEM_DOMAIN_GTT);
+		return ttm_bo_validate(bo, &rbo->placement, false, false);
+	} else if (unlikely(r != 0)) {
+		return r;
 	}
+
+	offset = bo->mem.start << PAGE_SHIFT;
+	/* this should never happen */
+	if ((offset + size) > rdev->mc.visible_vram_size)
+		return -EINVAL;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index 6fac8efe8340..53d6e1bb48dc 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -361,6 +361,11 @@ static ssize_t radeon_set_pm_profile(struct device *dev,
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct radeon_device *rdev = ddev->dev_private;
 
+	/* Can't set profile when the card is off */
+	if  ((rdev->flags & RADEON_IS_PX) &&
+	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
+		return -EINVAL;
+
 	mutex_lock(&rdev->pm.mutex);
 	if (rdev->pm.pm_method == PM_METHOD_PROFILE) {
 		if (strncmp("default", buf, strlen("default")) == 0)
@@ -409,6 +414,13 @@ static ssize_t radeon_set_pm_method(struct device *dev,
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct radeon_device *rdev = ddev->dev_private;
 
+	/* Can't set method when the card is off */
+	if  ((rdev->flags & RADEON_IS_PX) &&
+	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON)) {
+		count = -EINVAL;
+		goto fail;
+	}
+
 	/* we don't support the legacy modes with dpm */
 	if (rdev->pm.pm_method == PM_METHOD_DPM) {
 		count = -EINVAL;
@@ -446,6 +458,10 @@ static ssize_t radeon_get_dpm_state(struct device *dev,
 	struct radeon_device *rdev = ddev->dev_private;
 	enum radeon_pm_state_type pm = rdev->pm.dpm.user_state;
 
+	if  ((rdev->flags & RADEON_IS_PX) &&
+	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
+		return snprintf(buf, PAGE_SIZE, "off\n");
+
 	return snprintf(buf, PAGE_SIZE, "%s\n",
 			(pm == POWER_STATE_TYPE_BATTERY) ? "battery" :
 			(pm == POWER_STATE_TYPE_BALANCED) ? "balanced" : "performance");
@@ -459,6 +475,11 @@ static ssize_t radeon_set_dpm_state(struct device *dev,
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct radeon_device *rdev = ddev->dev_private;
 
+	/* Can't set dpm state when the card is off */
+	if  ((rdev->flags & RADEON_IS_PX) &&
+	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
+		return -EINVAL;
+
 	mutex_lock(&rdev->pm.mutex);
 	if (strncmp("battery", buf, strlen("battery")) == 0)
 		rdev->pm.dpm.user_state = POWER_STATE_TYPE_BATTERY;
@@ -485,6 +506,10 @@ static ssize_t radeon_get_dpm_forced_performance_level(struct device *dev,
 	struct radeon_device *rdev = ddev->dev_private;
 	enum radeon_dpm_forced_level level = rdev->pm.dpm.forced_level;
 
+	if  ((rdev->flags & RADEON_IS_PX) &&
+	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
+		return snprintf(buf, PAGE_SIZE, "off\n");
+
 	return snprintf(buf, PAGE_SIZE, "%s\n",
 			(level == RADEON_DPM_FORCED_LEVEL_AUTO) ? "auto" :
 			(level == RADEON_DPM_FORCED_LEVEL_LOW) ? "low" : "high");
@@ -500,6 +525,11 @@ static ssize_t radeon_set_dpm_forced_performance_level(struct device *dev,
 	enum radeon_dpm_forced_level level;
 	int ret = 0;
 
+	/* Can't force performance level when the card is off */
+	if  ((rdev->flags & RADEON_IS_PX) &&
+	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
+		return -EINVAL;
+
 	mutex_lock(&rdev->pm.mutex);
 	if (strncmp("low", buf, strlen("low")) == 0) {
 		level = RADEON_DPM_FORCED_LEVEL_LOW;
@@ -538,8 +568,14 @@ static ssize_t radeon_hwmon_show_temp(struct device *dev,
 				      char *buf)
 {
 	struct radeon_device *rdev = dev_get_drvdata(dev);
+	struct drm_device *ddev = rdev->ddev;
 	int temp;
 
+	/* Can't get temperature when the card is off */
+	if  ((rdev->flags & RADEON_IS_PX) &&
+	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON))
+		return -EINVAL;
+
 	if (rdev->asic->pm.get_temperature)
 		temp = radeon_get_temperature(rdev);
 	else
@@ -1300,6 +1336,7 @@ int radeon_pm_init(struct radeon_device *rdev)
 	case CHIP_KABINI:
 	case CHIP_KAVERI:
 	case CHIP_HAWAII:
+	case CHIP_MULLINS:
 		/* DPM requires the RLC, RV770+ dGPU requires SMC */
 		if (!rdev->rlc_fw)
 			rdev->pm.pm_method = PM_METHOD_PROFILE;
@@ -1613,8 +1650,12 @@ static int radeon_debugfs_pm_info(struct seq_file *m, void *data)
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct radeon_device *rdev = dev->dev_private;
+	struct drm_device *ddev = rdev->ddev;
 
-	if (rdev->pm.dpm_enabled) {
+	if  ((rdev->flags & RADEON_IS_PX) &&
+	     (ddev->switch_power_state != DRM_SWITCH_POWER_ON)) {
+		seq_printf(m, "PX asic powered off\n");
+	} else if (rdev->pm.dpm_enabled) {
 		mutex_lock(&rdev->pm.mutex);
 		if (rdev->asic->dpm.debugfs_print_current_performance_level)
 			radeon_dpm_debugfs_print_current_performance_level(rdev, m);
diff --git a/drivers/gpu/drm/radeon/radeon_ucode.h b/drivers/gpu/drm/radeon/radeon_ucode.h
index 58d12938c0b8..4e7c3269b183 100644
--- a/drivers/gpu/drm/radeon/radeon_ucode.h
+++ b/drivers/gpu/drm/radeon/radeon_ucode.h
@@ -52,6 +52,7 @@
 #define BONAIRE_RLC_UCODE_SIZE       2048
 #define KB_RLC_UCODE_SIZE            2560
 #define KV_RLC_UCODE_SIZE            2560
+#define ML_RLC_UCODE_SIZE            2560
 
 /* MC */
 #define BTC_MC_UCODE_SIZE            6024
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c
index 5748bdaeacce..1b65ae2433cd 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
+++ b/drivers/gpu/drm/radeon/radeon_uvd.c
@@ -99,6 +99,7 @@ int radeon_uvd_init(struct radeon_device *rdev)
 	case CHIP_KABINI:
 	case CHIP_KAVERI:
 	case CHIP_HAWAII:
+	case CHIP_MULLINS:
 		fw_name = FIRMWARE_BONAIRE;
 		break;
 
@@ -465,6 +466,10 @@ static int radeon_uvd_cs_reloc(struct radeon_cs_parser *p,
 	cmd = radeon_get_ib_value(p, p->idx) >> 1;
 
 	if (cmd < 0x4) {
+		if (end <= start) {
+			DRM_ERROR("invalid reloc offset %X!\n", offset);
+			return -EINVAL;
+		}
 		if ((end - start) < buf_sizes[cmd]) {
 			DRM_ERROR("buffer (%d) to small (%d / %d)!\n", cmd,
 				  (unsigned)(end - start), buf_sizes[cmd]);
diff --git a/drivers/gpu/drm/radeon/radeon_vce.c b/drivers/gpu/drm/radeon/radeon_vce.c
index ced53dd03e7c..3971d968af6c 100644
--- a/drivers/gpu/drm/radeon/radeon_vce.c
+++ b/drivers/gpu/drm/radeon/radeon_vce.c
@@ -66,6 +66,7 @@ int radeon_vce_init(struct radeon_device *rdev)
 	case CHIP_BONAIRE:
 	case CHIP_KAVERI:
 	case CHIP_KABINI:
+	case CHIP_MULLINS:
 		fw_name = FIRMWARE_BONAIRE;
 		break;
 
@@ -442,13 +443,16 @@ int radeon_vce_get_destroy_msg(struct radeon_device *rdev, int ring,
  * @p: parser context
  * @lo: address of lower dword
  * @hi: address of higher dword
+ * @size: size of checker for relocation buffer
  *
  * Patch relocation inside command stream with real buffer address
  */
-int radeon_vce_cs_reloc(struct radeon_cs_parser *p, int lo, int hi)
+int radeon_vce_cs_reloc(struct radeon_cs_parser *p, int lo, int hi,
+			unsigned size)
 {
 	struct radeon_cs_chunk *relocs_chunk;
-	uint64_t offset;
+	struct radeon_cs_reloc *reloc;
+	uint64_t start, end, offset;
 	unsigned idx;
 
 	relocs_chunk = &p->chunks[p->chunk_relocs_idx];
@@ -461,15 +465,60 @@ int radeon_vce_cs_reloc(struct radeon_cs_parser *p, int lo, int hi)
 		return -EINVAL;
 	}
 
-	offset += p->relocs_ptr[(idx / 4)]->gpu_offset;
+	reloc = p->relocs_ptr[(idx / 4)];
+	start = reloc->gpu_offset;
+	end = start + radeon_bo_size(reloc->robj);
+	start += offset;
 
-        p->ib.ptr[lo] = offset & 0xFFFFFFFF;
-        p->ib.ptr[hi] = offset >> 32;
+	p->ib.ptr[lo] = start & 0xFFFFFFFF;
+	p->ib.ptr[hi] = start >> 32;
+
+	if (end <= start) {
+		DRM_ERROR("invalid reloc offset %llX!\n", offset);
+		return -EINVAL;
+	}
+	if ((end - start) < size) {
+		DRM_ERROR("buffer to small (%d / %d)!\n",
+			(unsigned)(end - start), size);
+		return -EINVAL;
+	}
 
 	return 0;
 }
 
 /**
+ * radeon_vce_validate_handle - validate stream handle
+ *
+ * @p: parser context
+ * @handle: handle to validate
+ *
+ * Validates the handle and return the found session index or -EINVAL
+ * we we don't have another free session index.
+ */
+int radeon_vce_validate_handle(struct radeon_cs_parser *p, uint32_t handle)
+{
+	unsigned i;
+
+	/* validate the handle */
+	for (i = 0; i < RADEON_MAX_VCE_HANDLES; ++i) {
+		if (atomic_read(&p->rdev->vce.handles[i]) == handle)
+			return i;
+	}
+
+	/* handle not found try to alloc a new one */
+	for (i = 0; i < RADEON_MAX_VCE_HANDLES; ++i) {
+		if (!atomic_cmpxchg(&p->rdev->vce.handles[i], 0, handle)) {
+			p->rdev->vce.filp[i] = p->filp;
+			p->rdev->vce.img_size[i] = 0;
+			return i;
+		}
+	}
+
+	DRM_ERROR("No more free VCE handles!\n");
+	return -EINVAL;
+}
+
+/**
  * radeon_vce_cs_parse - parse and validate the command stream
  *
  * @p: parser context
@@ -477,8 +526,10 @@ int radeon_vce_cs_reloc(struct radeon_cs_parser *p, int lo, int hi)
  */
 int radeon_vce_cs_parse(struct radeon_cs_parser *p)
 {
-	uint32_t handle = 0;
-	bool destroy = false;
+	int session_idx = -1;
+	bool destroyed = false;
+	uint32_t tmp, handle = 0;
+	uint32_t *size = &tmp;
 	int i, r;
 
 	while (p->idx < p->chunks[p->chunk_ib_idx].length_dw) {
@@ -490,13 +541,29 @@ int radeon_vce_cs_parse(struct radeon_cs_parser *p)
                 	return -EINVAL;
 		}
 
+		if (destroyed) {
+			DRM_ERROR("No other command allowed after destroy!\n");
+			return -EINVAL;
+		}
+
 		switch (cmd) {
 		case 0x00000001: // session
 			handle = radeon_get_ib_value(p, p->idx + 2);
+			session_idx = radeon_vce_validate_handle(p, handle);
+			if (session_idx < 0)
+				return session_idx;
+			size = &p->rdev->vce.img_size[session_idx];
 			break;
 
 		case 0x00000002: // task info
+			break;
+
 		case 0x01000001: // create
+			*size = radeon_get_ib_value(p, p->idx + 8) *
+				radeon_get_ib_value(p, p->idx + 10) *
+				8 * 3 / 2;
+			break;
+
 		case 0x04000001: // config extension
 		case 0x04000002: // pic control
 		case 0x04000005: // rate control
@@ -505,23 +572,39 @@ int radeon_vce_cs_parse(struct radeon_cs_parser *p)
 			break;
 
 		case 0x03000001: // encode
-			r = radeon_vce_cs_reloc(p, p->idx + 10, p->idx + 9);
+			r = radeon_vce_cs_reloc(p, p->idx + 10, p->idx + 9,
+						*size);
 			if (r)
 				return r;
 
-			r = radeon_vce_cs_reloc(p, p->idx + 12, p->idx + 11);
+			r = radeon_vce_cs_reloc(p, p->idx + 12, p->idx + 11,
+						*size / 3);
 			if (r)
 				return r;
 			break;
 
 		case 0x02000001: // destroy
-			destroy = true;
+			destroyed = true;
 			break;
 
 		case 0x05000001: // context buffer
+			r = radeon_vce_cs_reloc(p, p->idx + 3, p->idx + 2,
+						*size * 2);
+			if (r)
+				return r;
+			break;
+
 		case 0x05000004: // video bitstream buffer
+			tmp = radeon_get_ib_value(p, p->idx + 4);
+			r = radeon_vce_cs_reloc(p, p->idx + 3, p->idx + 2,
+						tmp);
+			if (r)
+				return r;
+			break;
+
 		case 0x05000005: // feedback buffer
-			r = radeon_vce_cs_reloc(p, p->idx + 3, p->idx + 2);
+			r = radeon_vce_cs_reloc(p, p->idx + 3, p->idx + 2,
+						4096);
 			if (r)
 				return r;
 			break;
@@ -531,33 +614,21 @@ int radeon_vce_cs_parse(struct radeon_cs_parser *p)
 			return -EINVAL;
 		}
 
+		if (session_idx == -1) {
+			DRM_ERROR("no session command at start of IB\n");
+			return -EINVAL;
+		}
+
 		p->idx += len / 4;
 	}
 
-	if (destroy) {
+	if (destroyed) {
 		/* IB contains a destroy msg, free the handle */
 		for (i = 0; i < RADEON_MAX_VCE_HANDLES; ++i)
 			atomic_cmpxchg(&p->rdev->vce.handles[i], handle, 0);
-
-		return 0;
-        }
-
-	/* create or encode, validate the handle */
-	for (i = 0; i < RADEON_MAX_VCE_HANDLES; ++i) {
-		if (atomic_read(&p->rdev->vce.handles[i]) == handle)
-			return 0;
 	}
 
-	/* handle not found try to alloc a new one */
-	for (i = 0; i < RADEON_MAX_VCE_HANDLES; ++i) {
-		if (!atomic_cmpxchg(&p->rdev->vce.handles[i], 0, handle)) {
-			p->rdev->vce.filp[i] = p->filp;
-			return 0;
-		}
-	}
-
-	DRM_ERROR("No more free VCE handles!\n");
-	return -EINVAL;
+	return 0;
 }
 
 /**
diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c
index 2aae6ce49d32..d9ab99f47612 100644
--- a/drivers/gpu/drm/radeon/radeon_vm.c
+++ b/drivers/gpu/drm/radeon/radeon_vm.c
@@ -595,7 +595,7 @@ int radeon_vm_update_page_directory(struct radeon_device *rdev,
 	ndw = 64;
 
 	/* assume the worst case */
-	ndw += vm->max_pde_used * 12;
+	ndw += vm->max_pde_used * 16;
 
 	/* update too big for an IB */
 	if (ndw > 0xfffff)
diff --git a/drivers/gpu/drm/radeon/rv770_dma.c b/drivers/gpu/drm/radeon/rv770_dma.c
index aca8cbe8a335..bbf2e076ee45 100644
--- a/drivers/gpu/drm/radeon/rv770_dma.c
+++ b/drivers/gpu/drm/radeon/rv770_dma.c
@@ -86,6 +86,7 @@ int rv770_copy_dma(struct radeon_device *rdev,
 	r = radeon_fence_emit(rdev, fence, ring->idx);
 	if (r) {
 		radeon_ring_unlock_undo(rdev, ring);
+		radeon_semaphore_free(rdev, &sem, NULL);
 		return r;
 	}
 
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index ac708e006180..22a63c98ba14 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -5780,7 +5780,6 @@ int si_irq_set(struct radeon_device *rdev)
 	u32 crtc1 = 0, crtc2 = 0, crtc3 = 0, crtc4 = 0, crtc5 = 0, crtc6 = 0;
 	u32 hpd1 = 0, hpd2 = 0, hpd3 = 0, hpd4 = 0, hpd5 = 0, hpd6 = 0;
 	u32 grbm_int_cntl = 0;
-	u32 grph1 = 0, grph2 = 0, grph3 = 0, grph4 = 0, grph5 = 0, grph6 = 0;
 	u32 dma_cntl, dma_cntl1;
 	u32 thermal_int = 0;
 
@@ -5919,16 +5918,22 @@ int si_irq_set(struct radeon_device *rdev)
 	}
 
 	if (rdev->num_crtc >= 2) {
-		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET, grph1);
-		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET, grph2);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC0_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC1_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
 	}
 	if (rdev->num_crtc >= 4) {
-		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET, grph3);
-		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET, grph4);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC2_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC3_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
 	}
 	if (rdev->num_crtc >= 6) {
-		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET, grph5);
-		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET, grph6);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC4_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
+		WREG32(GRPH_INT_CONTROL + EVERGREEN_CRTC5_REGISTER_OFFSET,
+		       GRPH_PFLIP_INT_MASK);
 	}
 
 	if (!ASIC_IS_NODCE(rdev)) {
@@ -6292,6 +6297,15 @@ restart_ih:
 				break;
 			}
 			break;
+		case 8: /* D1 page flip */
+		case 10: /* D2 page flip */
+		case 12: /* D3 page flip */
+		case 14: /* D4 page flip */
+		case 16: /* D5 page flip */
+		case 18: /* D6 page flip */
+			DRM_DEBUG("IH: D%d flip\n", ((src_id - 8) >> 1) + 1);
+			radeon_crtc_handle_flip(rdev, (src_id - 8) >> 1);
+			break;
 		case 42: /* HPD hotplug */
 			switch (src_data) {
 			case 0:
diff --git a/drivers/gpu/drm/radeon/si_dma.c b/drivers/gpu/drm/radeon/si_dma.c
index cf0fdad8c278..de0ca070122f 100644
--- a/drivers/gpu/drm/radeon/si_dma.c
+++ b/drivers/gpu/drm/radeon/si_dma.c
@@ -213,6 +213,7 @@ int si_copy_dma(struct radeon_device *rdev,
 	r = radeon_fence_emit(rdev, fence, ring->idx);
 	if (r) {
 		radeon_ring_unlock_undo(rdev, ring);
+		radeon_semaphore_free(rdev, &sem, NULL);
 		return r;
 	}
 
diff --git a/drivers/gpu/drm/radeon/sid.h b/drivers/gpu/drm/radeon/sid.h
index 683532f84931..7321283602ce 100644
--- a/drivers/gpu/drm/radeon/sid.h
+++ b/drivers/gpu/drm/radeon/sid.h
@@ -107,8 +107,8 @@
 #define		SPLL_CHG_STATUS				(1 << 1)
 #define	SPLL_CNTL_MODE					0x618
 #define		SPLL_SW_DIR_CONTROL			(1 << 0)
-#	define SPLL_REFCLK_SEL(x)			((x) << 8)
-#	define SPLL_REFCLK_SEL_MASK			0xFF00
+#	define SPLL_REFCLK_SEL(x)			((x) << 26)
+#	define SPLL_REFCLK_SEL_MASK			(3 << 26)
 
 #define	CG_SPLL_SPREAD_SPECTRUM				0x620
 #define		SSEN					(1 << 0)
diff --git a/drivers/gpu/drm/radeon/uvd_v1_0.c b/drivers/gpu/drm/radeon/uvd_v1_0.c
index 0a243f0e5d68..be42c8125203 100644
--- a/drivers/gpu/drm/radeon/uvd_v1_0.c
+++ b/drivers/gpu/drm/radeon/uvd_v1_0.c
@@ -83,7 +83,10 @@ int uvd_v1_0_init(struct radeon_device *rdev)
 	int r;
 
 	/* raise clocks while booting up the VCPU */
-	radeon_set_uvd_clocks(rdev, 53300, 40000);
+	if (rdev->family < CHIP_RV740)
+		radeon_set_uvd_clocks(rdev, 10000, 10000);
+	else
+		radeon_set_uvd_clocks(rdev, 53300, 40000);
 
 	r = uvd_v1_0_start(rdev);
 	if (r)
@@ -407,7 +410,10 @@ int uvd_v1_0_ib_test(struct radeon_device *rdev, struct radeon_ring *ring)
 	struct radeon_fence *fence = NULL;
 	int r;
 
-	r = radeon_set_uvd_clocks(rdev, 53300, 40000);
+	if (rdev->family < CHIP_RV740)
+		r = radeon_set_uvd_clocks(rdev, 10000, 10000);
+	else
+		r = radeon_set_uvd_clocks(rdev, 53300, 40000);
 	if (r) {
 		DRM_ERROR("radeon: failed to raise UVD clocks (%d).\n", r);
 		return r;
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 10a2c0866459..da52279de939 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1253,7 +1253,8 @@ EXPORT_SYMBOL_GPL(hid_output_report);
 
 static int hid_report_len(struct hid_report *report)
 {
-	return ((report->size - 1) >> 3) + 1 + (report->id > 0) + 7;
+	/* equivalent to DIV_ROUND_UP(report->size, 8) + !!(report->id > 0) */
+	return ((report->size - 1) >> 3) + 1 + (report->id > 0);
 }
 
 /*
@@ -1266,7 +1267,7 @@ u8 *hid_alloc_report_buf(struct hid_report *report, gfp_t flags)
 	 * of implement() working on 8 byte chunks
 	 */
 
-	int len = hid_report_len(report);
+	int len = hid_report_len(report) + 7;
 
 	return kmalloc(len, flags);
 }
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index c8af7202c28d..34bb2205d2ea 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -301,6 +301,9 @@
 
 #define USB_VENDOR_ID_DREAM_CHEEKY	0x1d34
 
+#define USB_VENDOR_ID_ELITEGROUP	0x03fc
+#define USB_DEVICE_ID_ELITEGROUP_05D8	0x05d8
+
 #define USB_VENDOR_ID_ELO		0x04E7
 #define USB_DEVICE_ID_ELO_TS2515	0x0022
 #define USB_DEVICE_ID_ELO_TS2700	0x0020
@@ -834,6 +837,10 @@
 #define USB_DEVICE_ID_SYNAPTICS_LTS2	0x1d10
 #define USB_DEVICE_ID_SYNAPTICS_HD	0x0ac3
 #define USB_DEVICE_ID_SYNAPTICS_QUAD_HD	0x1ac3
+#define USB_DEVICE_ID_SYNAPTICS_TP_V103	0x5710
+
+#define USB_VENDOR_ID_TEXAS_INSTRUMENTS	0x2047
+#define USB_DEVICE_ID_TEXAS_INSTRUMENTS_LENOVO_YOGA	0x0855
 
 #define USB_VENDOR_ID_THINGM		0x27b8
 #define USB_DEVICE_ID_BLINK1		0x01ed
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index 35278e43c7a4..51e25b9407f2 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -1155,6 +1155,11 @@ static const struct hid_device_id mt_devices[] = {
 		MT_USB_DEVICE(USB_VENDOR_ID_DWAV,
 			USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_A001) },
 
+	/* Elitegroup panel */
+	{ .driver_data = MT_CLS_SERIAL,
+		MT_USB_DEVICE(USB_VENDOR_ID_ELITEGROUP,
+			USB_DEVICE_ID_ELITEGROUP_05D8) },
+
 	/* Flatfrog Panels */
 	{ .driver_data = MT_CLS_FLATFROG,
 		MT_USB_DEVICE(USB_VENDOR_ID_FLATFROG,
diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c
index af8244b1c1f4..be14b5690e94 100644
--- a/drivers/hid/hid-sensor-hub.c
+++ b/drivers/hid/hid-sensor-hub.c
@@ -708,6 +708,9 @@ static const struct hid_device_id sensor_hub_devices[] = {
 	{ HID_DEVICE(HID_BUS_ANY, HID_GROUP_SENSOR_HUB, USB_VENDOR_ID_STM_0,
 			USB_DEVICE_ID_STM_HID_SENSOR),
 			.driver_data = HID_SENSOR_HUB_ENUM_QUIRK},
+	{ HID_DEVICE(HID_BUS_ANY, HID_GROUP_SENSOR_HUB, USB_VENDOR_ID_TEXAS_INSTRUMENTS,
+			USB_DEVICE_ID_TEXAS_INSTRUMENTS_LENOVO_YOGA),
+			.driver_data = HID_SENSOR_HUB_ENUM_QUIRK},
 	{ HID_DEVICE(HID_BUS_ANY, HID_GROUP_SENSOR_HUB, HID_ANY_ID,
 		     HID_ANY_ID) },
 	{ }
diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c
index dbd83878ff99..8e4ddb369883 100644
--- a/drivers/hid/usbhid/hid-quirks.c
+++ b/drivers/hid/usbhid/hid-quirks.c
@@ -119,6 +119,7 @@ static const struct hid_blacklist {
 	{ USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_LTS2, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_HD, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_QUAD_HD, HID_QUIRK_NO_INIT_REPORTS },
+	{ USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_TP_V103, HID_QUIRK_NO_INIT_REPORTS },
 
 	{ 0, 0 }
 };
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index bc196f49ec53..4af0da96c2e2 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -1053,7 +1053,7 @@ config SENSORS_PC87427
 
 config SENSORS_NTC_THERMISTOR
 	tristate "NTC thermistor support"
-	depends on (!OF && !IIO) || (OF && IIO)
+	depends on !OF || IIO=n || IIO
 	help
 	  This driver supports NTC thermistors sensor reading and its
 	  interpretation. The driver can also monitor the temperature and
diff --git a/drivers/hwmon/emc1403.c b/drivers/hwmon/emc1403.c
index 90ec1173b8a1..01723f04fe45 100644
--- a/drivers/hwmon/emc1403.c
+++ b/drivers/hwmon/emc1403.c
@@ -163,7 +163,7 @@ static ssize_t store_hyst(struct device *dev,
 	if (retval < 0)
 		goto fail;
 
-	hyst = val - retval * 1000;
+	hyst = retval * 1000 - val;
 	hyst = DIV_ROUND_CLOSEST(hyst, 1000);
 	if (hyst < 0 || hyst > 255) {
 		retval = -ERANGE;
@@ -330,7 +330,7 @@ static int emc1403_detect(struct i2c_client *client,
 	}
 
 	id = i2c_smbus_read_byte_data(client, THERMAL_REVISION_REG);
-	if (id != 0x01)
+	if (id < 0x01 || id > 0x04)
 		return -ENODEV;
 
 	return 0;
@@ -355,9 +355,9 @@ static int emc1403_probe(struct i2c_client *client,
 	if (id->driver_data)
 		data->groups[1] = &emc1404_group;
 
-	hwmon_dev = hwmon_device_register_with_groups(&client->dev,
-						      client->name, data,
-						      data->groups);
+	hwmon_dev = devm_hwmon_device_register_with_groups(&client->dev,
+							   client->name, data,
+							   data->groups);
 	if (IS_ERR(hwmon_dev))
 		return PTR_ERR(hwmon_dev);
 
diff --git a/drivers/hwmon/ntc_thermistor.c b/drivers/hwmon/ntc_thermistor.c
index 8a17f01e8672..e76feb86a1d4 100644
--- a/drivers/hwmon/ntc_thermistor.c
+++ b/drivers/hwmon/ntc_thermistor.c
@@ -44,6 +44,7 @@ struct ntc_compensation {
 	unsigned int	ohm;
 };
 
+/* Order matters, ntc_match references the entries by index */
 static const struct platform_device_id ntc_thermistor_id[] = {
 	{ "ncp15wb473", TYPE_NCPXXWB473 },
 	{ "ncp18wb473", TYPE_NCPXXWB473 },
@@ -141,7 +142,7 @@ struct ntc_data {
 	char name[PLATFORM_NAME_SIZE];
 };
 
-#ifdef CONFIG_OF
+#if defined(CONFIG_OF) && IS_ENABLED(CONFIG_IIO)
 static int ntc_adc_iio_read(struct ntc_thermistor_platform_data *pdata)
 {
 	struct iio_channel *channel = pdata->chan;
@@ -163,15 +164,15 @@ static int ntc_adc_iio_read(struct ntc_thermistor_platform_data *pdata)
 
 static const struct of_device_id ntc_match[] = {
 	{ .compatible = "ntc,ncp15wb473",
-		.data = &ntc_thermistor_id[TYPE_NCPXXWB473] },
+		.data = &ntc_thermistor_id[0] },
 	{ .compatible = "ntc,ncp18wb473",
-		.data = &ntc_thermistor_id[TYPE_NCPXXWB473] },
+		.data = &ntc_thermistor_id[1] },
 	{ .compatible = "ntc,ncp21wb473",
-		.data = &ntc_thermistor_id[TYPE_NCPXXWB473] },
+		.data = &ntc_thermistor_id[2] },
 	{ .compatible = "ntc,ncp03wb473",
-		.data = &ntc_thermistor_id[TYPE_NCPXXWB473] },
+		.data = &ntc_thermistor_id[3] },
 	{ .compatible = "ntc,ncp15wl333",
-		.data = &ntc_thermistor_id[TYPE_NCPXXWL333] },
+		.data = &ntc_thermistor_id[4] },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, ntc_match);
@@ -223,6 +224,8 @@ ntc_thermistor_parse_dt(struct platform_device *pdev)
 	return NULL;
 }
 
+#define ntc_match	NULL
+
 static void ntc_iio_channel_release(struct ntc_thermistor_platform_data *pdata)
 { }
 #endif
diff --git a/drivers/i2c/busses/i2c-designware-core.c b/drivers/i2c/busses/i2c-designware-core.c
index 22e92c3d3d07..3c20e4bd6dd1 100644
--- a/drivers/i2c/busses/i2c-designware-core.c
+++ b/drivers/i2c/busses/i2c-designware-core.c
@@ -422,6 +422,9 @@ static void i2c_dw_xfer_init(struct dw_i2c_dev *dev)
 	 */
 	dw_writel(dev, msgs[dev->msg_write_idx].addr | ic_tar, DW_IC_TAR);
 
+	/* enforce disabled interrupts (due to HW issues) */
+	i2c_dw_disable_int(dev);
+
 	/* Enable the adapter */
 	__i2c_dw_enable(dev, true);
 
diff --git a/drivers/i2c/busses/i2c-nomadik.c b/drivers/i2c/busses/i2c-nomadik.c
index 28cbe1b2a2ec..32c85e9ecdae 100644
--- a/drivers/i2c/busses/i2c-nomadik.c
+++ b/drivers/i2c/busses/i2c-nomadik.c
@@ -999,7 +999,7 @@ static int nmk_i2c_probe(struct amba_device *adev, const struct amba_id *id)
 
 	dev->virtbase = devm_ioremap(&adev->dev, adev->res.start,
 				resource_size(&adev->res));
-	if (IS_ERR(dev->virtbase)) {
+	if (!dev->virtbase) {
 		ret = -ENOMEM;
 		goto err_no_mem;
 	}
diff --git a/drivers/i2c/busses/i2c-qup.c b/drivers/i2c/busses/i2c-qup.c
index 1b4cf14f1106..2a5efb5b487c 100644
--- a/drivers/i2c/busses/i2c-qup.c
+++ b/drivers/i2c/busses/i2c-qup.c
@@ -479,7 +479,7 @@ static int qup_i2c_xfer(struct i2c_adapter *adap,
 	int ret, idx;
 
 	ret = pm_runtime_get_sync(qup->dev);
-	if (ret)
+	if (ret < 0)
 		goto out;
 
 	writel(1, qup->base + QUP_SW_RESET);
diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c
index d4fa8eba6e9d..06d47aafbb79 100644
--- a/drivers/i2c/busses/i2c-rcar.c
+++ b/drivers/i2c/busses/i2c-rcar.c
@@ -561,6 +561,12 @@ static int rcar_i2c_master_xfer(struct i2c_adapter *adap,
 
 	ret = -EINVAL;
 	for (i = 0; i < num; i++) {
+		/* This HW can't send STOP after address phase */
+		if (msgs[i].len == 0) {
+			ret = -EOPNOTSUPP;
+			break;
+		}
+
 		/*-------------- spin lock -----------------*/
 		spin_lock_irqsave(&priv->lock, flags);
 
@@ -625,7 +631,8 @@ static int rcar_i2c_master_xfer(struct i2c_adapter *adap,
 
 static u32 rcar_i2c_func(struct i2c_adapter *adap)
 {
-	return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL;
+	/* This HW can't do SMBUS_QUICK and NOSTART */
+	return I2C_FUNC_I2C | (I2C_FUNC_SMBUS_EMUL & ~I2C_FUNC_SMBUS_QUICK);
 }
 
 static const struct i2c_algorithm rcar_i2c_algo = {
diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c
index ae4491062e41..bb3a9964f7e0 100644
--- a/drivers/i2c/busses/i2c-s3c2410.c
+++ b/drivers/i2c/busses/i2c-s3c2410.c
@@ -1276,10 +1276,10 @@ static int s3c24xx_i2c_resume(struct device *dev)
 	struct platform_device *pdev = to_platform_device(dev);
 	struct s3c24xx_i2c *i2c = platform_get_drvdata(pdev);
 
-	i2c->suspended = 0;
 	clk_prepare_enable(i2c->clk);
 	s3c24xx_i2c_init(i2c);
 	clk_disable_unprepare(i2c->clk);
+	i2c->suspended = 0;
 
 	return 0;
 }
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 1b6dbe156a37..199c7896f081 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -48,6 +48,7 @@
 
 #include <linux/mlx4/driver.h>
 #include <linux/mlx4/cmd.h>
+#include <linux/mlx4/qp.h>
 
 #include "mlx4_ib.h"
 #include "user.h"
@@ -1614,6 +1615,53 @@ static int mlx4_ib_inet6_event(struct notifier_block *this, unsigned long event,
 }
 #endif
 
+#define MLX4_IB_INVALID_MAC	((u64)-1)
+static void mlx4_ib_update_qps(struct mlx4_ib_dev *ibdev,
+			       struct net_device *dev,
+			       int port)
+{
+	u64 new_smac = 0;
+	u64 release_mac = MLX4_IB_INVALID_MAC;
+	struct mlx4_ib_qp *qp;
+
+	read_lock(&dev_base_lock);
+	new_smac = mlx4_mac_to_u64(dev->dev_addr);
+	read_unlock(&dev_base_lock);
+
+	mutex_lock(&ibdev->qp1_proxy_lock[port - 1]);
+	qp = ibdev->qp1_proxy[port - 1];
+	if (qp) {
+		int new_smac_index;
+		u64 old_smac = qp->pri.smac;
+		struct mlx4_update_qp_params update_params;
+
+		if (new_smac == old_smac)
+			goto unlock;
+
+		new_smac_index = mlx4_register_mac(ibdev->dev, port, new_smac);
+
+		if (new_smac_index < 0)
+			goto unlock;
+
+		update_params.smac_index = new_smac_index;
+		if (mlx4_update_qp(ibdev->dev, &qp->mqp, MLX4_UPDATE_QP_SMAC,
+				   &update_params)) {
+			release_mac = new_smac;
+			goto unlock;
+		}
+
+		qp->pri.smac = new_smac;
+		qp->pri.smac_index = new_smac_index;
+
+		release_mac = old_smac;
+	}
+
+unlock:
+	mutex_unlock(&ibdev->qp1_proxy_lock[port - 1]);
+	if (release_mac != MLX4_IB_INVALID_MAC)
+		mlx4_unregister_mac(ibdev->dev, port, release_mac);
+}
+
 static void mlx4_ib_get_dev_addr(struct net_device *dev,
 				 struct mlx4_ib_dev *ibdev, u8 port)
 {
@@ -1689,9 +1737,13 @@ static int mlx4_ib_init_gid_table(struct mlx4_ib_dev *ibdev)
 	return 0;
 }
 
-static void mlx4_ib_scan_netdevs(struct mlx4_ib_dev *ibdev)
+static void mlx4_ib_scan_netdevs(struct mlx4_ib_dev *ibdev,
+				 struct net_device *dev,
+				 unsigned long event)
+
 {
 	struct mlx4_ib_iboe *iboe;
+	int update_qps_port = -1;
 	int port;
 
 	iboe = &ibdev->iboe;
@@ -1719,6 +1771,11 @@ static void mlx4_ib_scan_netdevs(struct mlx4_ib_dev *ibdev)
 		}
 		curr_master = iboe->masters[port - 1];
 
+		if (dev == iboe->netdevs[port - 1] &&
+		    (event == NETDEV_CHANGEADDR || event == NETDEV_REGISTER ||
+		     event == NETDEV_UP || event == NETDEV_CHANGE))
+			update_qps_port = port;
+
 		if (curr_netdev) {
 			port_state = (netif_running(curr_netdev) && netif_carrier_ok(curr_netdev)) ?
 						IB_PORT_ACTIVE : IB_PORT_DOWN;
@@ -1752,6 +1809,9 @@ static void mlx4_ib_scan_netdevs(struct mlx4_ib_dev *ibdev)
 	}
 
 	spin_unlock(&iboe->lock);
+
+	if (update_qps_port > 0)
+		mlx4_ib_update_qps(ibdev, dev, update_qps_port);
 }
 
 static int mlx4_ib_netdev_event(struct notifier_block *this,
@@ -1764,7 +1824,7 @@ static int mlx4_ib_netdev_event(struct notifier_block *this,
 		return NOTIFY_DONE;
 
 	ibdev = container_of(this, struct mlx4_ib_dev, iboe.nb);
-	mlx4_ib_scan_netdevs(ibdev);
+	mlx4_ib_scan_netdevs(ibdev, dev, event);
 
 	return NOTIFY_DONE;
 }
@@ -2043,6 +2103,7 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 		goto err_map;
 
 	for (i = 0; i < ibdev->num_ports; ++i) {
+		mutex_init(&ibdev->qp1_proxy_lock[i]);
 		if (mlx4_ib_port_link_layer(&ibdev->ib_dev, i + 1) ==
 						IB_LINK_LAYER_ETHERNET) {
 			err = mlx4_counter_alloc(ibdev->dev, &ibdev->counters[i]);
@@ -2126,7 +2187,7 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 		for (i = 1 ; i <= ibdev->num_ports ; ++i)
 			reset_gid_table(ibdev, i);
 		rtnl_lock();
-		mlx4_ib_scan_netdevs(ibdev);
+		mlx4_ib_scan_netdevs(ibdev, NULL, 0);
 		rtnl_unlock();
 		mlx4_ib_init_gid_table(ibdev);
 	}
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index f589522fddfd..66b0b7dbd9f4 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -522,6 +522,9 @@ struct mlx4_ib_dev {
 	int steer_qpn_count;
 	int steer_qpn_base;
 	int steering_support;
+	struct mlx4_ib_qp      *qp1_proxy[MLX4_MAX_PORTS];
+	/* lock when destroying qp1_proxy and getting netdev events */
+	struct mutex		qp1_proxy_lock[MLX4_MAX_PORTS];
 };
 
 struct ib_event_work {
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 41308af4163c..dc57482ae7af 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -1132,6 +1132,12 @@ int mlx4_ib_destroy_qp(struct ib_qp *qp)
 	if (is_qp0(dev, mqp))
 		mlx4_CLOSE_PORT(dev->dev, mqp->port);
 
+	if (dev->qp1_proxy[mqp->port - 1] == mqp) {
+		mutex_lock(&dev->qp1_proxy_lock[mqp->port - 1]);
+		dev->qp1_proxy[mqp->port - 1] = NULL;
+		mutex_unlock(&dev->qp1_proxy_lock[mqp->port - 1]);
+	}
+
 	pd = get_pd(mqp);
 	destroy_qp_common(dev, mqp, !!pd->ibpd.uobject);
 
@@ -1646,6 +1652,8 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 				err = handle_eth_ud_smac_index(dev, qp, (u8 *)attr->smac, context);
 				if (err)
 					return -EINVAL;
+				if (qp->mlx4_ib_qp_type == MLX4_IB_QPT_PROXY_GSI)
+					dev->qp1_proxy[qp->port - 1] = qp;
 			}
 		}
 	}
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index c98fdb185931..a1710465faaf 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -28,6 +28,7 @@
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
 #include <target/iscsi/iscsi_transport.h>
+#include <linux/semaphore.h>
 
 #include "isert_proto.h"
 #include "ib_isert.h"
@@ -561,7 +562,15 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 	struct isert_device *device;
 	struct ib_device *ib_dev = cma_id->device;
 	int ret = 0;
-	u8 pi_support = np->tpg_np->tpg->tpg_attrib.t10_pi;
+	u8 pi_support;
+
+	spin_lock_bh(&np->np_thread_lock);
+	if (!np->enabled) {
+		spin_unlock_bh(&np->np_thread_lock);
+		pr_debug("iscsi_np is not enabled, reject connect request\n");
+		return rdma_reject(cma_id, NULL, 0);
+	}
+	spin_unlock_bh(&np->np_thread_lock);
 
 	pr_debug("Entering isert_connect_request cma_id: %p, context: %p\n",
 		 cma_id, cma_id->context);
@@ -652,6 +661,7 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 		goto out_mr;
 	}
 
+	pi_support = np->tpg_np->tpg->tpg_attrib.t10_pi;
 	if (pi_support && !device->pi_capable) {
 		pr_err("Protection information requested but not supported\n");
 		ret = -EINVAL;
@@ -663,11 +673,11 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 		goto out_conn_dev;
 
 	mutex_lock(&isert_np->np_accept_mutex);
-	list_add_tail(&isert_np->np_accept_list, &isert_conn->conn_accept_node);
+	list_add_tail(&isert_conn->conn_accept_node, &isert_np->np_accept_list);
 	mutex_unlock(&isert_np->np_accept_mutex);
 
-	pr_debug("isert_connect_request() waking up np_accept_wq: %p\n", np);
-	wake_up(&isert_np->np_accept_wq);
+	pr_debug("isert_connect_request() up np_sem np: %p\n", np);
+	up(&isert_np->np_sem);
 	return 0;
 
 out_conn_dev:
@@ -2999,7 +3009,7 @@ isert_setup_np(struct iscsi_np *np,
 		pr_err("Unable to allocate struct isert_np\n");
 		return -ENOMEM;
 	}
-	init_waitqueue_head(&isert_np->np_accept_wq);
+	sema_init(&isert_np->np_sem, 0);
 	mutex_init(&isert_np->np_accept_mutex);
 	INIT_LIST_HEAD(&isert_np->np_accept_list);
 	init_completion(&isert_np->np_login_comp);
@@ -3048,18 +3058,6 @@ out:
 }
 
 static int
-isert_check_accept_queue(struct isert_np *isert_np)
-{
-	int empty;
-
-	mutex_lock(&isert_np->np_accept_mutex);
-	empty = list_empty(&isert_np->np_accept_list);
-	mutex_unlock(&isert_np->np_accept_mutex);
-
-	return empty;
-}
-
-static int
 isert_rdma_accept(struct isert_conn *isert_conn)
 {
 	struct rdma_cm_id *cm_id = isert_conn->conn_cm_id;
@@ -3151,16 +3149,14 @@ isert_accept_np(struct iscsi_np *np, struct iscsi_conn *conn)
 	int max_accept = 0, ret;
 
 accept_wait:
-	ret = wait_event_interruptible(isert_np->np_accept_wq,
-			!isert_check_accept_queue(isert_np) ||
-			np->np_thread_state == ISCSI_NP_THREAD_RESET);
+	ret = down_interruptible(&isert_np->np_sem);
 	if (max_accept > 5)
 		return -ENODEV;
 
 	spin_lock_bh(&np->np_thread_lock);
 	if (np->np_thread_state == ISCSI_NP_THREAD_RESET) {
 		spin_unlock_bh(&np->np_thread_lock);
-		pr_err("ISCSI_NP_THREAD_RESET for isert_accept_np\n");
+		pr_debug("ISCSI_NP_THREAD_RESET for isert_accept_np\n");
 		return -ENODEV;
 	}
 	spin_unlock_bh(&np->np_thread_lock);
diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h
index 4c072ae34c01..da6612e68000 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.h
+++ b/drivers/infiniband/ulp/isert/ib_isert.h
@@ -182,7 +182,7 @@ struct isert_device {
 };
 
 struct isert_np {
-	wait_queue_head_t	np_accept_wq;
+	struct semaphore	np_sem;
 	struct rdma_cm_id	*np_cm_id;
 	struct mutex		np_accept_mutex;
 	struct list_head	np_accept_list;
diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig
index 76842d7dc2e3..ffc7ad3a2c88 100644
--- a/drivers/input/keyboard/Kconfig
+++ b/drivers/input/keyboard/Kconfig
@@ -71,7 +71,7 @@ config KEYBOARD_ATKBD
 	default y
 	select SERIO
 	select SERIO_LIBPS2
-	select SERIO_I8042 if X86
+	select SERIO_I8042 if ARCH_MIGHT_HAVE_PC_SERIO
 	select SERIO_GSCPS2 if GSC
 	help
 	  Say Y here if you want to use a standard AT or PS/2 keyboard. Usually
diff --git a/drivers/input/keyboard/atkbd.c b/drivers/input/keyboard/atkbd.c
index 2626773ff29b..2dd1d0dd4f7d 100644
--- a/drivers/input/keyboard/atkbd.c
+++ b/drivers/input/keyboard/atkbd.c
@@ -243,6 +243,12 @@ static void (*atkbd_platform_fixup)(struct atkbd *, const void *data);
 static void *atkbd_platform_fixup_data;
 static unsigned int (*atkbd_platform_scancode_fixup)(struct atkbd *, unsigned int);
 
+/*
+ * Certain keyboards to not like ATKBD_CMD_RESET_DIS and stop responding
+ * to many commands until full reset (ATKBD_CMD_RESET_BAT) is performed.
+ */
+static bool atkbd_skip_deactivate;
+
 static ssize_t atkbd_attr_show_helper(struct device *dev, char *buf,
 				ssize_t (*handler)(struct atkbd *, char *));
 static ssize_t atkbd_attr_set_helper(struct device *dev, const char *buf, size_t count,
@@ -768,7 +774,8 @@ static int atkbd_probe(struct atkbd *atkbd)
  * Make sure nothing is coming from the keyboard and disturbs our
  * internal state.
  */
-	atkbd_deactivate(atkbd);
+	if (!atkbd_skip_deactivate)
+		atkbd_deactivate(atkbd);
 
 	return 0;
 }
@@ -1638,6 +1645,12 @@ static int __init atkbd_setup_scancode_fixup(const struct dmi_system_id *id)
 	return 1;
 }
 
+static int __init atkbd_deactivate_fixup(const struct dmi_system_id *id)
+{
+	atkbd_skip_deactivate = true;
+	return 1;
+}
+
 static const struct dmi_system_id atkbd_dmi_quirk_table[] __initconst = {
 	{
 		.matches = {
@@ -1775,6 +1788,20 @@ static const struct dmi_system_id atkbd_dmi_quirk_table[] __initconst = {
 		.callback = atkbd_setup_scancode_fixup,
 		.driver_data = atkbd_oqo_01plus_scancode_fixup,
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LG Electronics"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LW25-B7HV"),
+		},
+		.callback = atkbd_deactivate_fixup,
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LG Electronics"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "P1-J273B"),
+		},
+		.callback = atkbd_deactivate_fixup,
+	},
 	{ }
 };
 
diff --git a/drivers/input/keyboard/pxa27x_keypad.c b/drivers/input/keyboard/pxa27x_keypad.c
index d8241ba0afa0..a15063bea700 100644
--- a/drivers/input/keyboard/pxa27x_keypad.c
+++ b/drivers/input/keyboard/pxa27x_keypad.c
@@ -111,6 +111,8 @@ struct pxa27x_keypad {
 	unsigned short keycodes[MAX_KEYPAD_KEYS];
 	int rotary_rel_code[2];
 
+	unsigned int row_shift;
+
 	/* state row bits of each column scan */
 	uint32_t matrix_key_state[MAX_MATRIX_KEY_COLS];
 	uint32_t direct_key_state;
@@ -467,7 +469,8 @@ scan:
 			if ((bits_changed & (1 << row)) == 0)
 				continue;
 
-			code = MATRIX_SCAN_CODE(row, col, MATRIX_ROW_SHIFT);
+			code = MATRIX_SCAN_CODE(row, col, keypad->row_shift);
+
 			input_event(input_dev, EV_MSC, MSC_SCAN, code);
 			input_report_key(input_dev, keypad->keycodes[code],
 					 new_state[col] & (1 << row));
@@ -802,6 +805,8 @@ static int pxa27x_keypad_probe(struct platform_device *pdev)
 		goto failed_put_clk;
 	}
 
+	keypad->row_shift = get_count_order(pdata->matrix_key_cols);
+
 	if ((pdata->enable_rotary0 && keypad->rotary_rel_code[0] != -1) ||
 	    (pdata->enable_rotary1 && keypad->rotary_rel_code[1] != -1)) {
 		input_dev->evbit[0] |= BIT_MASK(EV_REL);
diff --git a/drivers/input/keyboard/tca8418_keypad.c b/drivers/input/keyboard/tca8418_keypad.c
index 55c15304ddbc..4e491c1762cf 100644
--- a/drivers/input/keyboard/tca8418_keypad.c
+++ b/drivers/input/keyboard/tca8418_keypad.c
@@ -392,6 +392,13 @@ static const struct of_device_id tca8418_dt_ids[] = {
 	{ }
 };
 MODULE_DEVICE_TABLE(of, tca8418_dt_ids);
+
+/*
+ * The device tree based i2c loader looks for
+ * "i2c:" + second_component_of(property("compatible"))
+ * and therefore we need an alias to be found.
+ */
+MODULE_ALIAS("i2c:tca8418");
 #endif
 
 static struct i2c_driver tca8418_keypad_driver = {
diff --git a/drivers/input/misc/bma150.c b/drivers/input/misc/bma150.c
index 52d3a9b28f0b..b36831c828d3 100644
--- a/drivers/input/misc/bma150.c
+++ b/drivers/input/misc/bma150.c
@@ -70,6 +70,7 @@
 #define BMA150_CFG_5_REG	0x11
 
 #define BMA150_CHIP_ID		2
+#define BMA180_CHIP_ID		3
 #define BMA150_CHIP_ID_REG	BMA150_DATA_0_REG
 
 #define BMA150_ACC_X_LSB_REG	BMA150_DATA_2_REG
@@ -539,7 +540,7 @@ static int bma150_probe(struct i2c_client *client,
 	}
 
 	chip_id = i2c_smbus_read_byte_data(client, BMA150_CHIP_ID_REG);
-	if (chip_id != BMA150_CHIP_ID) {
+	if (chip_id != BMA150_CHIP_ID && chip_id != BMA180_CHIP_ID) {
 		dev_err(&client->dev, "BMA150 chip id error: %d\n", chip_id);
 		return -EINVAL;
 	}
@@ -643,6 +644,7 @@ static UNIVERSAL_DEV_PM_OPS(bma150_pm, bma150_suspend, bma150_resume, NULL);
 
 static const struct i2c_device_id bma150_id[] = {
 	{ "bma150", 0 },
+	{ "bma180", 0 },
 	{ "smb380", 0 },
 	{ "bma023", 0 },
 	{ }
diff --git a/drivers/input/mouse/Kconfig b/drivers/input/mouse/Kconfig
index effa9c5f2c5c..6b8441f7bc32 100644
--- a/drivers/input/mouse/Kconfig
+++ b/drivers/input/mouse/Kconfig
@@ -17,7 +17,7 @@ config MOUSE_PS2
 	default y
 	select SERIO
 	select SERIO_LIBPS2
-	select SERIO_I8042 if X86
+	select SERIO_I8042 if ARCH_MIGHT_HAVE_PC_SERIO
 	select SERIO_GSCPS2 if GSC
 	help
 	  Say Y here if you have a PS/2 mouse connected to your system. This
diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c
index 088d3541c7d3..b96e978a37b7 100644
--- a/drivers/input/mouse/elantech.c
+++ b/drivers/input/mouse/elantech.c
@@ -11,6 +11,7 @@
  */
 
 #include <linux/delay.h>
+#include <linux/dmi.h>
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/input.h>
@@ -831,7 +832,11 @@ static int elantech_set_absolute_mode(struct psmouse *psmouse)
 		break;
 
 	case 3:
-		etd->reg_10 = 0x0b;
+		if (etd->set_hw_resolution)
+			etd->reg_10 = 0x0b;
+		else
+			etd->reg_10 = 0x03;
+
 		if (elantech_write_reg(psmouse, 0x10, etd->reg_10))
 			rc = -1;
 
@@ -1331,6 +1336,22 @@ static int elantech_reconnect(struct psmouse *psmouse)
 }
 
 /*
+ * Some hw_version 3 models go into error state when we try to set bit 3 of r10
+ */
+static const struct dmi_system_id no_hw_res_dmi_table[] = {
+#if defined(CONFIG_DMI) && defined(CONFIG_X86)
+	{
+		/* Gigabyte U2442 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "U2442"),
+		},
+	},
+#endif
+	{ }
+};
+
+/*
  * determine hardware version and set some properties according to it.
  */
 static int elantech_set_properties(struct elantech_data *etd)
@@ -1390,6 +1411,9 @@ static int elantech_set_properties(struct elantech_data *etd)
 	 */
 	etd->crc_enabled = ((etd->fw_version & 0x4000) == 0x4000);
 
+	/* Enable real hardware resolution on hw_version 3 ? */
+	etd->set_hw_resolution = !dmi_check_system(no_hw_res_dmi_table);
+
 	return 0;
 }
 
diff --git a/drivers/input/mouse/elantech.h b/drivers/input/mouse/elantech.h
index 036a04abaef7..9e0e2a1f340d 100644
--- a/drivers/input/mouse/elantech.h
+++ b/drivers/input/mouse/elantech.h
@@ -130,6 +130,7 @@ struct elantech_data {
 	bool jumpy_cursor;
 	bool reports_pressure;
 	bool crc_enabled;
+	bool set_hw_resolution;
 	unsigned char hw_version;
 	unsigned int fw_version;
 	unsigned int single_finger_reports;
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index ef9f4913450d..c5ec703c727e 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -117,6 +117,31 @@ void synaptics_reset(struct psmouse *psmouse)
 }
 
 #ifdef CONFIG_MOUSE_PS2_SYNAPTICS
+struct min_max_quirk {
+	const char * const *pnp_ids;
+	int x_min, x_max, y_min, y_max;
+};
+
+static const struct min_max_quirk min_max_pnpid_table[] = {
+	{
+		(const char * const []){"LEN0033", NULL},
+		1024, 5052, 2258, 4832
+	},
+	{
+		(const char * const []){"LEN0035", "LEN0042", NULL},
+		1232, 5710, 1156, 4696
+	},
+	{
+		(const char * const []){"LEN0034", "LEN0036", "LEN2004", NULL},
+		1024, 5112, 2024, 4832
+	},
+	{
+		(const char * const []){"LEN2001", NULL},
+		1024, 5022, 2508, 4832
+	},
+	{ }
+};
+
 /* This list has been kindly provided by Synaptics. */
 static const char * const topbuttonpad_pnp_ids[] = {
 	"LEN0017",
@@ -129,7 +154,7 @@ static const char * const topbuttonpad_pnp_ids[] = {
 	"LEN002D",
 	"LEN002E",
 	"LEN0033", /* Helix */
-	"LEN0034", /* T431s, T540, X1 Carbon 2nd */
+	"LEN0034", /* T431s, L440, L540, T540, W540, X1 Carbon 2nd */
 	"LEN0035", /* X240 */
 	"LEN0036", /* T440 */
 	"LEN0037",
@@ -142,7 +167,7 @@ static const char * const topbuttonpad_pnp_ids[] = {
 	"LEN0048",
 	"LEN0049",
 	"LEN2000",
-	"LEN2001",
+	"LEN2001", /* Edge E431 */
 	"LEN2002",
 	"LEN2003",
 	"LEN2004", /* L440 */
@@ -156,6 +181,18 @@ static const char * const topbuttonpad_pnp_ids[] = {
 	NULL
 };
 
+static bool matches_pnp_id(struct psmouse *psmouse, const char * const ids[])
+{
+	int i;
+
+	if (!strncmp(psmouse->ps2dev.serio->firmware_id, "PNP:", 4))
+		for (i = 0; ids[i]; i++)
+			if (strstr(psmouse->ps2dev.serio->firmware_id, ids[i]))
+				return true;
+
+	return false;
+}
+
 /*****************************************************************************
  *	Synaptics communications functions
  ****************************************************************************/
@@ -304,20 +341,20 @@ static int synaptics_identify(struct psmouse *psmouse)
  * Resolution is left zero if touchpad does not support the query
  */
 
-static const int *quirk_min_max;
-
 static int synaptics_resolution(struct psmouse *psmouse)
 {
 	struct synaptics_data *priv = psmouse->private;
 	unsigned char resp[3];
+	int i;
 
-	if (quirk_min_max) {
-		priv->x_min = quirk_min_max[0];
-		priv->x_max = quirk_min_max[1];
-		priv->y_min = quirk_min_max[2];
-		priv->y_max = quirk_min_max[3];
-		return 0;
-	}
+	for (i = 0; min_max_pnpid_table[i].pnp_ids; i++)
+		if (matches_pnp_id(psmouse, min_max_pnpid_table[i].pnp_ids)) {
+			priv->x_min = min_max_pnpid_table[i].x_min;
+			priv->x_max = min_max_pnpid_table[i].x_max;
+			priv->y_min = min_max_pnpid_table[i].y_min;
+			priv->y_max = min_max_pnpid_table[i].y_max;
+			return 0;
+		}
 
 	if (SYN_ID_MAJOR(priv->identity) < 4)
 		return 0;
@@ -1365,17 +1402,8 @@ static void set_input_params(struct psmouse *psmouse,
 
 	if (SYN_CAP_CLICKPAD(priv->ext_cap_0c)) {
 		__set_bit(INPUT_PROP_BUTTONPAD, dev->propbit);
-		/* See if this buttonpad has a top button area */
-		if (!strncmp(psmouse->ps2dev.serio->firmware_id, "PNP:", 4)) {
-			for (i = 0; topbuttonpad_pnp_ids[i]; i++) {
-				if (strstr(psmouse->ps2dev.serio->firmware_id,
-					   topbuttonpad_pnp_ids[i])) {
-					__set_bit(INPUT_PROP_TOPBUTTONPAD,
-						  dev->propbit);
-					break;
-				}
-			}
-		}
+		if (matches_pnp_id(psmouse, topbuttonpad_pnp_ids))
+			__set_bit(INPUT_PROP_TOPBUTTONPAD, dev->propbit);
 		/* Clickpads report only left button */
 		__clear_bit(BTN_RIGHT, dev->keybit);
 		__clear_bit(BTN_MIDDLE, dev->keybit);
@@ -1547,96 +1575,10 @@ static const struct dmi_system_id olpc_dmi_table[] __initconst = {
 	{ }
 };
 
-static const struct dmi_system_id min_max_dmi_table[] __initconst = {
-#if defined(CONFIG_DMI)
-	{
-		/* Lenovo ThinkPad Helix */
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad Helix"),
-		},
-		.driver_data = (int []){1024, 5052, 2258, 4832},
-	},
-	{
-		/* Lenovo ThinkPad X240 */
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X240"),
-		},
-		.driver_data = (int []){1232, 5710, 1156, 4696},
-	},
-	{
-		/* Lenovo ThinkPad T431s */
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T431"),
-		},
-		.driver_data = (int []){1024, 5112, 2024, 4832},
-	},
-	{
-		/* Lenovo ThinkPad T440s */
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T440"),
-		},
-		.driver_data = (int []){1024, 5112, 2024, 4832},
-	},
-	{
-		/* Lenovo ThinkPad L440 */
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad L440"),
-		},
-		.driver_data = (int []){1024, 5112, 2024, 4832},
-	},
-	{
-		/* Lenovo ThinkPad T540p */
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T540"),
-		},
-		.driver_data = (int []){1024, 5056, 2058, 4832},
-	},
-	{
-		/* Lenovo ThinkPad L540 */
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad L540"),
-		},
-		.driver_data = (int []){1024, 5112, 2024, 4832},
-	},
-	{
-		/* Lenovo Yoga S1 */
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-			DMI_EXACT_MATCH(DMI_PRODUCT_VERSION,
-					"ThinkPad S1 Yoga"),
-		},
-		.driver_data = (int []){1232, 5710, 1156, 4696},
-	},
-	{
-		/* Lenovo ThinkPad X1 Carbon Haswell (3rd generation) */
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-			DMI_MATCH(DMI_PRODUCT_VERSION,
-					"ThinkPad X1 Carbon 2nd"),
-		},
-		.driver_data = (int []){1024, 5112, 2024, 4832},
-	},
-#endif
-	{ }
-};
-
 void __init synaptics_module_init(void)
 {
-	const struct dmi_system_id *min_max_dmi;
-
 	impaired_toshiba_kbc = dmi_check_system(toshiba_dmi_table);
 	broken_olpc_ec = dmi_check_system(olpc_dmi_table);
-
-	min_max_dmi = dmi_first_match(min_max_dmi_table);
-	if (min_max_dmi)
-		quirk_min_max = min_max_dmi->driver_data;
 }
 
 static int __synaptics_init(struct psmouse *psmouse, bool absolute_mode)
diff --git a/drivers/input/serio/ambakmi.c b/drivers/input/serio/ambakmi.c
index 762b08432de0..8b748d99b934 100644
--- a/drivers/input/serio/ambakmi.c
+++ b/drivers/input/serio/ambakmi.c
@@ -79,7 +79,8 @@ static int amba_kmi_open(struct serio *io)
 	writeb(divisor, KMICLKDIV);
 	writeb(KMICR_EN, KMICR);
 
-	ret = request_irq(kmi->irq, amba_kmi_int, 0, "kmi-pl050", kmi);
+	ret = request_irq(kmi->irq, amba_kmi_int, IRQF_SHARED, "kmi-pl050",
+			  kmi);
 	if (ret) {
 		printk(KERN_ERR "kmi: failed to claim IRQ%d\n", kmi->irq);
 		writeb(0, KMICR);
diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig
index 68edc9db2c64..b845e9370871 100644
--- a/drivers/input/touchscreen/Kconfig
+++ b/drivers/input/touchscreen/Kconfig
@@ -640,7 +640,7 @@ config TOUCHSCREEN_WM9713
 
 config TOUCHSCREEN_WM97XX_ATMEL
 	tristate "WM97xx Atmel accelerated touch"
-	depends on TOUCHSCREEN_WM97XX && (AVR32 || ARCH_AT91)
+	depends on TOUCHSCREEN_WM97XX && AVR32
 	help
 	  Say Y here for support for streaming mode with WM97xx touchscreens
 	  on Atmel AT91 or AVR32 systems with an AC97C module.
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index c949520bd196..57068e8035b5 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -3999,7 +3999,7 @@ static struct irq_remap_table *get_irq_table(u16 devid, bool ioapic)
 	iommu_flush_dte(iommu, devid);
 	if (devid != alias) {
 		irq_lookup_table[alias] = table;
-		set_dte_irq_entry(devid, table);
+		set_dte_irq_entry(alias, table);
 		iommu_flush_dte(iommu, alias);
 	}
 
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index b76c58dbe30c..0e08545d7298 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -788,7 +788,7 @@ static void __init set_device_exclusion_range(u16 devid, struct ivmd_header *m)
 		 * per device. But we can enable the exclusion range per
 		 * device. This is done here
 		 */
-		set_dev_entry_bit(m->devid, DEV_ENTRY_EX);
+		set_dev_entry_bit(devid, DEV_ENTRY_EX);
 		iommu->exclusion_start = m->range_start;
 		iommu->exclusion_length = m->range_length;
 	}
diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c
index 5208828792e6..203b2e6a91cf 100644
--- a/drivers/iommu/amd_iommu_v2.c
+++ b/drivers/iommu/amd_iommu_v2.c
@@ -504,8 +504,10 @@ static void do_fault(struct work_struct *work)
 
 	write = !!(fault->flags & PPR_FAULT_WRITE);
 
+	down_read(&fault->state->mm->mmap_sem);
 	npages = get_user_pages(fault->state->task, fault->state->mm,
 				fault->address, 1, write, 0, &page, NULL);
+	up_read(&fault->state->mm->mmap_sem);
 
 	if (npages == 1) {
 		put_page(page);
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 9380be7b1895..5f054c44b485 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -2178,6 +2178,8 @@ static int cache_create(struct cache_args *ca, struct cache **result)
 	ti->num_discard_bios = 1;
 	ti->discards_supported = true;
 	ti->discard_zeroes_data_unsupported = true;
+	/* Discard bios must be split on a block boundary */
+	ti->split_discard_bios = true;
 
 	cache->features = ca->features;
 	ti->per_bio_data_size = get_per_bio_data_size(cache);
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 784695d22fde..53b213226c01 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -19,7 +19,6 @@
 #include <linux/crypto.h>
 #include <linux/workqueue.h>
 #include <linux/backing-dev.h>
-#include <linux/percpu.h>
 #include <linux/atomic.h>
 #include <linux/scatterlist.h>
 #include <asm/page.h>
@@ -43,6 +42,7 @@ struct convert_context {
 	struct bvec_iter iter_out;
 	sector_t cc_sector;
 	atomic_t cc_pending;
+	struct ablkcipher_request *req;
 };
 
 /*
@@ -111,15 +111,7 @@ struct iv_tcw_private {
 enum flags { DM_CRYPT_SUSPENDED, DM_CRYPT_KEY_VALID };
 
 /*
- * Duplicated per-CPU state for cipher.
- */
-struct crypt_cpu {
-	struct ablkcipher_request *req;
-};
-
-/*
- * The fields in here must be read only after initialization,
- * changing state should be in crypt_cpu.
+ * The fields in here must be read only after initialization.
  */
 struct crypt_config {
 	struct dm_dev *dev;
@@ -150,12 +142,6 @@ struct crypt_config {
 	sector_t iv_offset;
 	unsigned int iv_size;
 
-	/*
-	 * Duplicated per cpu state. Access through
-	 * per_cpu_ptr() only.
-	 */
-	struct crypt_cpu __percpu *cpu;
-
 	/* ESSIV: struct crypto_cipher *essiv_tfm */
 	void *iv_private;
 	struct crypto_ablkcipher **tfms;
@@ -192,11 +178,6 @@ static void clone_init(struct dm_crypt_io *, struct bio *);
 static void kcryptd_queue_crypt(struct dm_crypt_io *io);
 static u8 *iv_of_dmreq(struct crypt_config *cc, struct dm_crypt_request *dmreq);
 
-static struct crypt_cpu *this_crypt_config(struct crypt_config *cc)
-{
-	return this_cpu_ptr(cc->cpu);
-}
-
 /*
  * Use this to access cipher attributes that are the same for each CPU.
  */
@@ -903,16 +884,15 @@ static void kcryptd_async_done(struct crypto_async_request *async_req,
 static void crypt_alloc_req(struct crypt_config *cc,
 			    struct convert_context *ctx)
 {
-	struct crypt_cpu *this_cc = this_crypt_config(cc);
 	unsigned key_index = ctx->cc_sector & (cc->tfms_count - 1);
 
-	if (!this_cc->req)
-		this_cc->req = mempool_alloc(cc->req_pool, GFP_NOIO);
+	if (!ctx->req)
+		ctx->req = mempool_alloc(cc->req_pool, GFP_NOIO);
 
-	ablkcipher_request_set_tfm(this_cc->req, cc->tfms[key_index]);
-	ablkcipher_request_set_callback(this_cc->req,
+	ablkcipher_request_set_tfm(ctx->req, cc->tfms[key_index]);
+	ablkcipher_request_set_callback(ctx->req,
 	    CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
-	    kcryptd_async_done, dmreq_of_req(cc, this_cc->req));
+	    kcryptd_async_done, dmreq_of_req(cc, ctx->req));
 }
 
 /*
@@ -921,7 +901,6 @@ static void crypt_alloc_req(struct crypt_config *cc,
 static int crypt_convert(struct crypt_config *cc,
 			 struct convert_context *ctx)
 {
-	struct crypt_cpu *this_cc = this_crypt_config(cc);
 	int r;
 
 	atomic_set(&ctx->cc_pending, 1);
@@ -932,7 +911,7 @@ static int crypt_convert(struct crypt_config *cc,
 
 		atomic_inc(&ctx->cc_pending);
 
-		r = crypt_convert_block(cc, ctx, this_cc->req);
+		r = crypt_convert_block(cc, ctx, ctx->req);
 
 		switch (r) {
 		/* async */
@@ -941,7 +920,7 @@ static int crypt_convert(struct crypt_config *cc,
 			reinit_completion(&ctx->restart);
 			/* fall through*/
 		case -EINPROGRESS:
-			this_cc->req = NULL;
+			ctx->req = NULL;
 			ctx->cc_sector++;
 			continue;
 
@@ -1040,6 +1019,7 @@ static struct dm_crypt_io *crypt_io_alloc(struct crypt_config *cc,
 	io->sector = sector;
 	io->error = 0;
 	io->base_io = NULL;
+	io->ctx.req = NULL;
 	atomic_set(&io->io_pending, 0);
 
 	return io;
@@ -1065,6 +1045,8 @@ static void crypt_dec_pending(struct dm_crypt_io *io)
 	if (!atomic_dec_and_test(&io->io_pending))
 		return;
 
+	if (io->ctx.req)
+		mempool_free(io->ctx.req, cc->req_pool);
 	mempool_free(io, cc->io_pool);
 
 	if (likely(!base_io))
@@ -1492,8 +1474,6 @@ static int crypt_wipe_key(struct crypt_config *cc)
 static void crypt_dtr(struct dm_target *ti)
 {
 	struct crypt_config *cc = ti->private;
-	struct crypt_cpu *cpu_cc;
-	int cpu;
 
 	ti->private = NULL;
 
@@ -1505,13 +1485,6 @@ static void crypt_dtr(struct dm_target *ti)
 	if (cc->crypt_queue)
 		destroy_workqueue(cc->crypt_queue);
 
-	if (cc->cpu)
-		for_each_possible_cpu(cpu) {
-			cpu_cc = per_cpu_ptr(cc->cpu, cpu);
-			if (cpu_cc->req)
-				mempool_free(cpu_cc->req, cc->req_pool);
-		}
-
 	crypt_free_tfms(cc);
 
 	if (cc->bs)
@@ -1530,9 +1503,6 @@ static void crypt_dtr(struct dm_target *ti)
 	if (cc->dev)
 		dm_put_device(ti, cc->dev);
 
-	if (cc->cpu)
-		free_percpu(cc->cpu);
-
 	kzfree(cc->cipher);
 	kzfree(cc->cipher_string);
 
@@ -1588,13 +1558,6 @@ static int crypt_ctr_cipher(struct dm_target *ti,
 	if (tmp)
 		DMWARN("Ignoring unexpected additional cipher options");
 
-	cc->cpu = __alloc_percpu(sizeof(*(cc->cpu)),
-				 __alignof__(struct crypt_cpu));
-	if (!cc->cpu) {
-		ti->error = "Cannot allocate per cpu state";
-		goto bad_mem;
-	}
-
 	/*
 	 * For compatibility with the original dm-crypt mapping format, if
 	 * only the cipher name is supplied, use cbc-plain.
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index aa009e865871..ebfa411d1a7d 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -445,11 +445,11 @@ static int queue_if_no_path(struct multipath *m, unsigned queue_if_no_path,
 	else
 		m->saved_queue_if_no_path = queue_if_no_path;
 	m->queue_if_no_path = queue_if_no_path;
-	if (!m->queue_if_no_path)
-		dm_table_run_md_queue_async(m->ti->table);
-
 	spin_unlock_irqrestore(&m->lock, flags);
 
+	if (!queue_if_no_path)
+		dm_table_run_md_queue_async(m->ti->table);
+
 	return 0;
 }
 
@@ -954,7 +954,7 @@ out:
  */
 static int reinstate_path(struct pgpath *pgpath)
 {
-	int r = 0;
+	int r = 0, run_queue = 0;
 	unsigned long flags;
 	struct multipath *m = pgpath->pg->m;
 
@@ -978,7 +978,7 @@ static int reinstate_path(struct pgpath *pgpath)
 
 	if (!m->nr_valid_paths++) {
 		m->current_pgpath = NULL;
-		dm_table_run_md_queue_async(m->ti->table);
+		run_queue = 1;
 	} else if (m->hw_handler_name && (m->current_pg == pgpath->pg)) {
 		if (queue_work(kmpath_handlerd, &pgpath->activate_path.work))
 			m->pg_init_in_progress++;
@@ -991,6 +991,8 @@ static int reinstate_path(struct pgpath *pgpath)
 
 out:
 	spin_unlock_irqrestore(&m->lock, flags);
+	if (run_queue)
+		dm_table_run_md_queue_async(m->ti->table);
 
 	return r;
 }
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 13abade76ad9..242ac2ea5f29 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -27,6 +27,9 @@
 #define MAPPING_POOL_SIZE 1024
 #define PRISON_CELLS 1024
 #define COMMIT_PERIOD HZ
+#define NO_SPACE_TIMEOUT_SECS 60
+
+static unsigned no_space_timeout_secs = NO_SPACE_TIMEOUT_SECS;
 
 DECLARE_DM_KCOPYD_THROTTLE_WITH_MODULE_PARM(snapshot_copy_throttle,
 		"A percentage of time allocated for copy on write");
@@ -175,6 +178,7 @@ struct pool {
 	struct workqueue_struct *wq;
 	struct work_struct worker;
 	struct delayed_work waker;
+	struct delayed_work no_space_timeout;
 
 	unsigned long last_commit_jiffies;
 	unsigned ref_count;
@@ -935,7 +939,7 @@ static int commit(struct pool *pool)
 {
 	int r;
 
-	if (get_pool_mode(pool) != PM_WRITE)
+	if (get_pool_mode(pool) >= PM_READ_ONLY)
 		return -EINVAL;
 
 	r = dm_pool_commit_metadata(pool->pmd);
@@ -1590,6 +1594,20 @@ static void do_waker(struct work_struct *ws)
 	queue_delayed_work(pool->wq, &pool->waker, COMMIT_PERIOD);
 }
 
+/*
+ * We're holding onto IO to allow userland time to react.  After the
+ * timeout either the pool will have been resized (and thus back in
+ * PM_WRITE mode), or we degrade to PM_READ_ONLY and start erroring IO.
+ */
+static void do_no_space_timeout(struct work_struct *ws)
+{
+	struct pool *pool = container_of(to_delayed_work(ws), struct pool,
+					 no_space_timeout);
+
+	if (get_pool_mode(pool) == PM_OUT_OF_DATA_SPACE && !pool->pf.error_if_no_space)
+		set_pool_mode(pool, PM_READ_ONLY);
+}
+
 /*----------------------------------------------------------------*/
 
 struct noflush_work {
@@ -1654,6 +1672,7 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
 	struct pool_c *pt = pool->ti->private;
 	bool needs_check = dm_pool_metadata_needs_check(pool->pmd);
 	enum pool_mode old_mode = get_pool_mode(pool);
+	unsigned long no_space_timeout = ACCESS_ONCE(no_space_timeout_secs) * HZ;
 
 	/*
 	 * Never allow the pool to transition to PM_WRITE mode if user
@@ -1715,6 +1734,9 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
 		pool->process_discard = process_discard;
 		pool->process_prepared_mapping = process_prepared_mapping;
 		pool->process_prepared_discard = process_prepared_discard_passdown;
+
+		if (!pool->pf.error_if_no_space && no_space_timeout)
+			queue_delayed_work(pool->wq, &pool->no_space_timeout, no_space_timeout);
 		break;
 
 	case PM_WRITE:
@@ -2100,6 +2122,7 @@ static struct pool *pool_create(struct mapped_device *pool_md,
 
 	INIT_WORK(&pool->worker, do_worker);
 	INIT_DELAYED_WORK(&pool->waker, do_waker);
+	INIT_DELAYED_WORK(&pool->no_space_timeout, do_no_space_timeout);
 	spin_lock_init(&pool->lock);
 	bio_list_init(&pool->deferred_flush_bios);
 	INIT_LIST_HEAD(&pool->prepared_mappings);
@@ -2662,6 +2685,7 @@ static void pool_postsuspend(struct dm_target *ti)
 	struct pool *pool = pt->pool;
 
 	cancel_delayed_work(&pool->waker);
+	cancel_delayed_work(&pool->no_space_timeout);
 	flush_workqueue(pool->wq);
 	(void) commit(pool);
 }
@@ -3487,6 +3511,9 @@ static void dm_thin_exit(void)
 module_init(dm_thin_init);
 module_exit(dm_thin_exit);
 
+module_param_named(no_space_timeout, no_space_timeout_secs, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(no_space_timeout, "Out of data space queue IO timeout in seconds");
+
 MODULE_DESCRIPTION(DM_NAME " thin provisioning target");
 MODULE_AUTHOR("Joe Thornber <dm-devel@redhat.com>");
 MODULE_LICENSE("GPL");
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 8fda38d23e38..237b7e0ddc7a 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -8516,7 +8516,8 @@ static int md_notify_reboot(struct notifier_block *this,
 		if (mddev_trylock(mddev)) {
 			if (mddev->pers)
 				__md_stop_writes(mddev);
-			mddev->safemode = 2;
+			if (mddev->persistent)
+				mddev->safemode = 2;
 			mddev_unlock(mddev);
 		}
 		need_delay = 1;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 33fc408e5eac..cb882aae9e20 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1172,6 +1172,13 @@ static void __make_request(struct mddev *mddev, struct bio *bio)
 	int max_sectors;
 	int sectors;
 
+	/*
+	 * Register the new request and wait if the reconstruction
+	 * thread has put up a bar for new requests.
+	 * Continue immediately if no resync is active currently.
+	 */
+	wait_barrier(conf);
+
 	sectors = bio_sectors(bio);
 	while (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
 	    bio->bi_iter.bi_sector < conf->reshape_progress &&
@@ -1552,12 +1559,6 @@ static void make_request(struct mddev *mddev, struct bio *bio)
 
 	md_write_start(mddev, bio);
 
-	/*
-	 * Register the new request and wait if the reconstruction
-	 * thread has put up a bar for new requests.
-	 * Continue immediately if no resync is active currently.
-	 */
-	wait_barrier(conf);
 
 	do {
 
diff --git a/drivers/media/i2c/ov7670.c b/drivers/media/i2c/ov7670.c
index e8a1ce204036..cdd7c1b7259b 100644
--- a/drivers/media/i2c/ov7670.c
+++ b/drivers/media/i2c/ov7670.c
@@ -1109,7 +1109,7 @@ static int ov7670_enum_framesizes(struct v4l2_subdev *sd,
 	 * windows that fall outside that.
 	 */
 	for (i = 0; i < n_win_sizes; i++) {
-		struct ov7670_win_size *win = &info->devtype->win_sizes[index];
+		struct ov7670_win_size *win = &info->devtype->win_sizes[i];
 		if (info->min_width && win->width < info->min_width)
 			continue;
 		if (info->min_height && win->height < info->min_height)
diff --git a/drivers/media/i2c/s5c73m3/s5c73m3-core.c b/drivers/media/i2c/s5c73m3/s5c73m3-core.c
index a4459301b5f8..ee0f57e01b56 100644
--- a/drivers/media/i2c/s5c73m3/s5c73m3-core.c
+++ b/drivers/media/i2c/s5c73m3/s5c73m3-core.c
@@ -1616,7 +1616,7 @@ static int s5c73m3_get_platform_data(struct s5c73m3 *state)
 	if (ret < 0)
 		return -EINVAL;
 
-	node_ep = v4l2_of_get_next_endpoint(node, NULL);
+	node_ep = of_graph_get_next_endpoint(node, NULL);
 	if (!node_ep) {
 		dev_warn(dev, "no endpoint defined for node: %s\n",
 						node->full_name);
diff --git a/drivers/media/media-device.c b/drivers/media/media-device.c
index d5a7a135f75d..703560fa5e73 100644
--- a/drivers/media/media-device.c
+++ b/drivers/media/media-device.c
@@ -93,6 +93,7 @@ static long media_device_enum_entities(struct media_device *mdev,
 	struct media_entity *ent;
 	struct media_entity_desc u_ent;
 
+	memset(&u_ent, 0, sizeof(u_ent));
 	if (copy_from_user(&u_ent.id, &uent->id, sizeof(u_ent.id)))
 		return -EFAULT;
 
diff --git a/drivers/media/platform/davinci/vpbe_display.c b/drivers/media/platform/davinci/vpbe_display.c
index b4f12d00be05..656708252962 100644
--- a/drivers/media/platform/davinci/vpbe_display.c
+++ b/drivers/media/platform/davinci/vpbe_display.c
@@ -372,18 +372,32 @@ static int vpbe_stop_streaming(struct vb2_queue *vq)
 {
 	struct vpbe_fh *fh = vb2_get_drv_priv(vq);
 	struct vpbe_layer *layer = fh->layer;
+	struct vpbe_display *disp = fh->disp_dev;
+	unsigned long flags;
 
 	if (!vb2_is_streaming(vq))
 		return 0;
 
 	/* release all active buffers */
+	spin_lock_irqsave(&disp->dma_queue_lock, flags);
+	if (layer->cur_frm == layer->next_frm) {
+		vb2_buffer_done(&layer->cur_frm->vb, VB2_BUF_STATE_ERROR);
+	} else {
+		if (layer->cur_frm != NULL)
+			vb2_buffer_done(&layer->cur_frm->vb,
+					VB2_BUF_STATE_ERROR);
+		if (layer->next_frm != NULL)
+			vb2_buffer_done(&layer->next_frm->vb,
+					VB2_BUF_STATE_ERROR);
+	}
+
 	while (!list_empty(&layer->dma_queue)) {
 		layer->next_frm = list_entry(layer->dma_queue.next,
 						struct vpbe_disp_buffer, list);
 		list_del(&layer->next_frm->list);
 		vb2_buffer_done(&layer->next_frm->vb, VB2_BUF_STATE_ERROR);
 	}
-
+	spin_unlock_irqrestore(&disp->dma_queue_lock, flags);
 	return 0;
 }
 
diff --git a/drivers/media/platform/davinci/vpfe_capture.c b/drivers/media/platform/davinci/vpfe_capture.c
index d762246eabf5..0379cb9f9a9c 100644
--- a/drivers/media/platform/davinci/vpfe_capture.c
+++ b/drivers/media/platform/davinci/vpfe_capture.c
@@ -734,6 +734,8 @@ static int vpfe_release(struct file *file)
 		}
 		vpfe_dev->io_usrs = 0;
 		vpfe_dev->numbuffers = config_params.numbuffers;
+		videobuf_stop(&vpfe_dev->buffer_queue);
+		videobuf_mmap_free(&vpfe_dev->buffer_queue);
 	}
 
 	/* Decrement device usrs counter */
diff --git a/drivers/media/platform/davinci/vpif_capture.c b/drivers/media/platform/davinci/vpif_capture.c
index 756da78bac23..8dea0b84a3ad 100644
--- a/drivers/media/platform/davinci/vpif_capture.c
+++ b/drivers/media/platform/davinci/vpif_capture.c
@@ -358,8 +358,31 @@ static int vpif_stop_streaming(struct vb2_queue *vq)
 
 	common = &ch->common[VPIF_VIDEO_INDEX];
 
+	/* Disable channel as per its device type and channel id */
+	if (VPIF_CHANNEL0_VIDEO == ch->channel_id) {
+		enable_channel0(0);
+		channel0_intr_enable(0);
+	}
+	if ((VPIF_CHANNEL1_VIDEO == ch->channel_id) ||
+		(2 == common->started)) {
+		enable_channel1(0);
+		channel1_intr_enable(0);
+	}
+	common->started = 0;
+
 	/* release all active buffers */
 	spin_lock_irqsave(&common->irqlock, flags);
+	if (common->cur_frm == common->next_frm) {
+		vb2_buffer_done(&common->cur_frm->vb, VB2_BUF_STATE_ERROR);
+	} else {
+		if (common->cur_frm != NULL)
+			vb2_buffer_done(&common->cur_frm->vb,
+					VB2_BUF_STATE_ERROR);
+		if (common->next_frm != NULL)
+			vb2_buffer_done(&common->next_frm->vb,
+					VB2_BUF_STATE_ERROR);
+	}
+
 	while (!list_empty(&common->dma_queue)) {
 		common->next_frm = list_entry(common->dma_queue.next,
 						struct vpif_cap_buffer, list);
@@ -933,17 +956,6 @@ static int vpif_release(struct file *filep)
 	if (fh->io_allowed[VPIF_VIDEO_INDEX]) {
 		/* Reset io_usrs member of channel object */
 		common->io_usrs = 0;
-		/* Disable channel as per its device type and channel id */
-		if (VPIF_CHANNEL0_VIDEO == ch->channel_id) {
-			enable_channel0(0);
-			channel0_intr_enable(0);
-		}
-		if ((VPIF_CHANNEL1_VIDEO == ch->channel_id) ||
-		    (2 == common->started)) {
-			enable_channel1(0);
-			channel1_intr_enable(0);
-		}
-		common->started = 0;
 		/* Free buffers allocated */
 		vb2_queue_release(&common->buffer_queue);
 		vb2_dma_contig_cleanup_ctx(common->alloc_ctx);
diff --git a/drivers/media/platform/davinci/vpif_display.c b/drivers/media/platform/davinci/vpif_display.c
index 0ac841e35aa4..aed41edd0501 100644
--- a/drivers/media/platform/davinci/vpif_display.c
+++ b/drivers/media/platform/davinci/vpif_display.c
@@ -320,8 +320,31 @@ static int vpif_stop_streaming(struct vb2_queue *vq)
 
 	common = &ch->common[VPIF_VIDEO_INDEX];
 
+	/* Disable channel */
+	if (VPIF_CHANNEL2_VIDEO == ch->channel_id) {
+		enable_channel2(0);
+		channel2_intr_enable(0);
+	}
+	if ((VPIF_CHANNEL3_VIDEO == ch->channel_id) ||
+		(2 == common->started)) {
+		enable_channel3(0);
+		channel3_intr_enable(0);
+	}
+	common->started = 0;
+
 	/* release all active buffers */
 	spin_lock_irqsave(&common->irqlock, flags);
+	if (common->cur_frm == common->next_frm) {
+		vb2_buffer_done(&common->cur_frm->vb, VB2_BUF_STATE_ERROR);
+	} else {
+		if (common->cur_frm != NULL)
+			vb2_buffer_done(&common->cur_frm->vb,
+					VB2_BUF_STATE_ERROR);
+		if (common->next_frm != NULL)
+			vb2_buffer_done(&common->next_frm->vb,
+					VB2_BUF_STATE_ERROR);
+	}
+
 	while (!list_empty(&common->dma_queue)) {
 		common->next_frm = list_entry(common->dma_queue.next,
 						struct vpif_disp_buffer, list);
@@ -773,18 +796,6 @@ static int vpif_release(struct file *filep)
 	if (fh->io_allowed[VPIF_VIDEO_INDEX]) {
 		/* Reset io_usrs member of channel object */
 		common->io_usrs = 0;
-		/* Disable channel */
-		if (VPIF_CHANNEL2_VIDEO == ch->channel_id) {
-			enable_channel2(0);
-			channel2_intr_enable(0);
-		}
-		if ((VPIF_CHANNEL3_VIDEO == ch->channel_id) ||
-		    (2 == common->started)) {
-			enable_channel3(0);
-			channel3_intr_enable(0);
-		}
-		common->started = 0;
-
 		/* Free buffers allocated */
 		vb2_queue_release(&common->buffer_queue);
 		vb2_dma_contig_cleanup_ctx(common->alloc_ctx);
diff --git a/drivers/media/platform/exynos4-is/fimc-core.c b/drivers/media/platform/exynos4-is/fimc-core.c
index da2fc86cc524..25dbf5b05a96 100644
--- a/drivers/media/platform/exynos4-is/fimc-core.c
+++ b/drivers/media/platform/exynos4-is/fimc-core.c
@@ -122,7 +122,7 @@ static struct fimc_fmt fimc_formats[] = {
 	}, {
 		.name		= "YUV 4:2:2 planar, Y/Cb/Cr",
 		.fourcc		= V4L2_PIX_FMT_YUV422P,
-		.depth		= { 12 },
+		.depth		= { 16 },
 		.color		= FIMC_FMT_YCBYCR422,
 		.memplanes	= 1,
 		.colplanes	= 3,
diff --git a/drivers/media/tuners/fc2580.c b/drivers/media/tuners/fc2580.c
index 3aecaf465094..f0c9c42867de 100644
--- a/drivers/media/tuners/fc2580.c
+++ b/drivers/media/tuners/fc2580.c
@@ -195,7 +195,7 @@ static int fc2580_set_params(struct dvb_frontend *fe)
 
 	f_ref = 2UL * priv->cfg->clock / r_val;
 	n_val = div_u64_rem(f_vco, f_ref, &k_val);
-	k_val_reg = 1UL * k_val * (1 << 20) / f_ref;
+	k_val_reg = div_u64(1ULL * k_val * (1 << 20), f_ref);
 
 	ret = fc2580_wr_reg(priv, 0x18, r18_val | ((k_val_reg >> 16) & 0xff));
 	if (ret < 0)
@@ -348,8 +348,8 @@ static int fc2580_set_params(struct dvb_frontend *fe)
 	if (ret < 0)
 		goto err;
 
-	ret = fc2580_wr_reg(priv, 0x37, 1UL * priv->cfg->clock * \
-			fc2580_if_filter_lut[i].mul / 1000000000);
+	ret = fc2580_wr_reg(priv, 0x37, div_u64(1ULL * priv->cfg->clock *
+			fc2580_if_filter_lut[i].mul, 1000000000));
 	if (ret < 0)
 		goto err;
 
diff --git a/drivers/media/tuners/fc2580_priv.h b/drivers/media/tuners/fc2580_priv.h
index be38a9e637e0..646c99452136 100644
--- a/drivers/media/tuners/fc2580_priv.h
+++ b/drivers/media/tuners/fc2580_priv.h
@@ -22,6 +22,7 @@
 #define FC2580_PRIV_H
 
 #include "fc2580.h"
+#include <linux/math64.h>
 
 struct fc2580_reg_val {
 	u8 reg;
diff --git a/drivers/media/usb/dvb-usb-v2/Makefile b/drivers/media/usb/dvb-usb-v2/Makefile
index 7407b8338ccf..bc38f03394cd 100644
--- a/drivers/media/usb/dvb-usb-v2/Makefile
+++ b/drivers/media/usb/dvb-usb-v2/Makefile
@@ -41,4 +41,3 @@ ccflags-y += -I$(srctree)/drivers/media/dvb-core
 ccflags-y += -I$(srctree)/drivers/media/dvb-frontends
 ccflags-y += -I$(srctree)/drivers/media/tuners
 ccflags-y += -I$(srctree)/drivers/media/common
-ccflags-y += -I$(srctree)/drivers/staging/media/rtl2832u_sdr
diff --git a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
index 61d196e8b3ab..dcbd392e6efc 100644
--- a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
+++ b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
@@ -24,7 +24,6 @@
 
 #include "rtl2830.h"
 #include "rtl2832.h"
-#include "rtl2832_sdr.h"
 
 #include "qt1010.h"
 #include "mt2060.h"
@@ -36,6 +35,45 @@
 #include "tua9001.h"
 #include "r820t.h"
 
+/*
+ * RTL2832_SDR module is in staging. That logic is added in order to avoid any
+ * hard dependency to drivers/staging/ directory as we want compile mainline
+ * driver even whole staging directory is missing.
+ */
+#include <media/v4l2-subdev.h>
+
+#if IS_ENABLED(CONFIG_DVB_RTL2832_SDR)
+struct dvb_frontend *rtl2832_sdr_attach(struct dvb_frontend *fe,
+	struct i2c_adapter *i2c, const struct rtl2832_config *cfg,
+	struct v4l2_subdev *sd);
+#else
+static inline struct dvb_frontend *rtl2832_sdr_attach(struct dvb_frontend *fe,
+	struct i2c_adapter *i2c, const struct rtl2832_config *cfg,
+	struct v4l2_subdev *sd)
+{
+	return NULL;
+}
+#endif
+
+#ifdef CONFIG_MEDIA_ATTACH
+#define dvb_attach_sdr(FUNCTION, ARGS...) ({ \
+	void *__r = NULL; \
+	typeof(&FUNCTION) __a = symbol_request(FUNCTION); \
+	if (__a) { \
+		__r = (void *) __a(ARGS); \
+		if (__r == NULL) \
+			symbol_put(FUNCTION); \
+	} \
+	__r; \
+})
+
+#else
+#define dvb_attach_sdr(FUNCTION, ARGS...) ({ \
+	FUNCTION(ARGS); \
+})
+
+#endif
+
 static int rtl28xxu_disable_rc;
 module_param_named(disable_rc, rtl28xxu_disable_rc, int, 0644);
 MODULE_PARM_DESC(disable_rc, "disable RTL2832U remote controller");
@@ -908,7 +946,7 @@ static int rtl2832u_tuner_attach(struct dvb_usb_adapter *adap)
 				adap->fe[0]->ops.tuner_ops.get_rf_strength;
 
 		/* attach SDR */
-		dvb_attach(rtl2832_sdr_attach, adap->fe[0], &d->i2c_adap,
+		dvb_attach_sdr(rtl2832_sdr_attach, adap->fe[0], &d->i2c_adap,
 				&rtl28xxu_rtl2832_fc0012_config, NULL);
 		break;
 	case TUNER_RTL2832_FC0013:
@@ -920,7 +958,7 @@ static int rtl2832u_tuner_attach(struct dvb_usb_adapter *adap)
 				adap->fe[0]->ops.tuner_ops.get_rf_strength;
 
 		/* attach SDR */
-		dvb_attach(rtl2832_sdr_attach, adap->fe[0], &d->i2c_adap,
+		dvb_attach_sdr(rtl2832_sdr_attach, adap->fe[0], &d->i2c_adap,
 				&rtl28xxu_rtl2832_fc0013_config, NULL);
 		break;
 	case TUNER_RTL2832_E4000: {
@@ -951,7 +989,7 @@ static int rtl2832u_tuner_attach(struct dvb_usb_adapter *adap)
 			i2c_set_adapdata(i2c_adap_internal, d);
 
 			/* attach SDR */
-			dvb_attach(rtl2832_sdr_attach, adap->fe[0],
+			dvb_attach_sdr(rtl2832_sdr_attach, adap->fe[0],
 					i2c_adap_internal,
 					&rtl28xxu_rtl2832_e4000_config, sd);
 		}
@@ -982,7 +1020,7 @@ static int rtl2832u_tuner_attach(struct dvb_usb_adapter *adap)
 				adap->fe[0]->ops.tuner_ops.get_rf_strength;
 
 		/* attach SDR */
-		dvb_attach(rtl2832_sdr_attach, adap->fe[0], &d->i2c_adap,
+		dvb_attach_sdr(rtl2832_sdr_attach, adap->fe[0], &d->i2c_adap,
 				&rtl28xxu_rtl2832_r820t_config, NULL);
 		break;
 	case TUNER_RTL2832_R828D:
diff --git a/drivers/media/usb/gspca/sonixb.c b/drivers/media/usb/gspca/sonixb.c
index 7277dbd2afcd..ecbcb39feb71 100644
--- a/drivers/media/usb/gspca/sonixb.c
+++ b/drivers/media/usb/gspca/sonixb.c
@@ -1430,10 +1430,8 @@ static const struct usb_device_id device_table[] = {
 	{USB_DEVICE(0x0c45, 0x600d), SB(PAS106, 101)},
 	{USB_DEVICE(0x0c45, 0x6011), SB(OV6650, 101)},
 	{USB_DEVICE(0x0c45, 0x6019), SB(OV7630, 101)},
-#if !IS_ENABLED(CONFIG_USB_SN9C102)
 	{USB_DEVICE(0x0c45, 0x6024), SB(TAS5130CXX, 102)},
 	{USB_DEVICE(0x0c45, 0x6025), SB(TAS5130CXX, 102)},
-#endif
 	{USB_DEVICE(0x0c45, 0x6027), SB(OV7630, 101)}, /* Genius Eye 310 */
 	{USB_DEVICE(0x0c45, 0x6028), SB(PAS202, 102)},
 	{USB_DEVICE(0x0c45, 0x6029), SB(PAS106, 102)},
diff --git a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
index 04b2daf567be..7e2411c36419 100644
--- a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
+++ b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c
@@ -178,6 +178,9 @@ struct v4l2_create_buffers32 {
 
 static int __get_v4l2_format32(struct v4l2_format *kp, struct v4l2_format32 __user *up)
 {
+	if (get_user(kp->type, &up->type))
+		return -EFAULT;
+
 	switch (kp->type) {
 	case V4L2_BUF_TYPE_VIDEO_CAPTURE:
 	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
@@ -204,17 +207,16 @@ static int __get_v4l2_format32(struct v4l2_format *kp, struct v4l2_format32 __us
 
 static int get_v4l2_format32(struct v4l2_format *kp, struct v4l2_format32 __user *up)
 {
-	if (!access_ok(VERIFY_READ, up, sizeof(struct v4l2_format32)) ||
-			get_user(kp->type, &up->type))
-			return -EFAULT;
+	if (!access_ok(VERIFY_READ, up, sizeof(struct v4l2_format32)))
+		return -EFAULT;
 	return __get_v4l2_format32(kp, up);
 }
 
 static int get_v4l2_create32(struct v4l2_create_buffers *kp, struct v4l2_create_buffers32 __user *up)
 {
 	if (!access_ok(VERIFY_READ, up, sizeof(struct v4l2_create_buffers32)) ||
-	    copy_from_user(kp, up, offsetof(struct v4l2_create_buffers32, format.fmt)))
-			return -EFAULT;
+	    copy_from_user(kp, up, offsetof(struct v4l2_create_buffers32, format)))
+		return -EFAULT;
 	return __get_v4l2_format32(&kp->format, &up->format);
 }
 
diff --git a/drivers/memory/mvebu-devbus.c b/drivers/memory/mvebu-devbus.c
index 110c03627051..b59a17fb7c3e 100644
--- a/drivers/memory/mvebu-devbus.c
+++ b/drivers/memory/mvebu-devbus.c
@@ -108,8 +108,19 @@ static int devbus_set_timing_params(struct devbus *devbus,
 			node->full_name);
 		return err;
 	}
-	/* Convert bit width to byte width */
-	r.bus_width /= 8;
+
+	/*
+	 * The bus width is encoded into the register as 0 for 8 bits,
+	 * and 1 for 16 bits, so we do the necessary conversion here.
+	 */
+	if (r.bus_width == 8)
+		r.bus_width = 0;
+	else if (r.bus_width == 16)
+		r.bus_width = 1;
+	else {
+		dev_err(devbus->dev, "invalid bus width %d\n", r.bus_width);
+		return -EINVAL;
+	}
 
 	err = get_timing_param_ps(devbus, node, "devbus,badr-skew-ps",
 				 &r.badr_skew);
diff --git a/drivers/mfd/rtsx_pcr.c b/drivers/mfd/rtsx_pcr.c
index c9de3d598ea5..1d15735f9ef9 100644
--- a/drivers/mfd/rtsx_pcr.c
+++ b/drivers/mfd/rtsx_pcr.c
@@ -338,28 +338,58 @@ int rtsx_pci_transfer_data(struct rtsx_pcr *pcr, struct scatterlist *sglist,
 		int num_sg, bool read, int timeout)
 {
 	struct completion trans_done;
-	int err = 0, count;
+	u8 dir;
+	int err = 0, i, count;
 	long timeleft;
 	unsigned long flags;
+	struct scatterlist *sg;
+	enum dma_data_direction dma_dir;
+	u32 val;
+	dma_addr_t addr;
+	unsigned int len;
+
+	dev_dbg(&(pcr->pci->dev), "--> %s: num_sg = %d\n", __func__, num_sg);
+
+	/* don't transfer data during abort processing */
+	if (pcr->remove_pci)
+		return -EINVAL;
+
+	if ((sglist == NULL) || (num_sg <= 0))
+		return -EINVAL;
 
-	count = rtsx_pci_dma_map_sg(pcr, sglist, num_sg, read);
+	if (read) {
+		dir = DEVICE_TO_HOST;
+		dma_dir = DMA_FROM_DEVICE;
+	} else {
+		dir = HOST_TO_DEVICE;
+		dma_dir = DMA_TO_DEVICE;
+	}
+
+	count = dma_map_sg(&(pcr->pci->dev), sglist, num_sg, dma_dir);
 	if (count < 1) {
 		dev_err(&(pcr->pci->dev), "scatterlist map failed\n");
 		return -EINVAL;
 	}
 	dev_dbg(&(pcr->pci->dev), "DMA mapping count: %d\n", count);
 
+	val = ((u32)(dir & 0x01) << 29) | TRIG_DMA | ADMA_MODE;
+	pcr->sgi = 0;
+	for_each_sg(sglist, sg, count, i) {
+		addr = sg_dma_address(sg);
+		len = sg_dma_len(sg);
+		rtsx_pci_add_sg_tbl(pcr, addr, len, i == count - 1);
+	}
 
 	spin_lock_irqsave(&pcr->lock, flags);
 
 	pcr->done = &trans_done;
 	pcr->trans_result = TRANS_NOT_READY;
 	init_completion(&trans_done);
+	rtsx_pci_writel(pcr, RTSX_HDBAR, pcr->host_sg_tbl_addr);
+	rtsx_pci_writel(pcr, RTSX_HDBCTLR, val);
 
 	spin_unlock_irqrestore(&pcr->lock, flags);
 
-	rtsx_pci_dma_transfer(pcr, sglist, count, read);
-
 	timeleft = wait_for_completion_interruptible_timeout(
 			&trans_done, msecs_to_jiffies(timeout));
 	if (timeleft <= 0) {
@@ -383,7 +413,7 @@ out:
 	pcr->done = NULL;
 	spin_unlock_irqrestore(&pcr->lock, flags);
 
-	rtsx_pci_dma_unmap_sg(pcr, sglist, num_sg, read);
+	dma_unmap_sg(&(pcr->pci->dev), sglist, num_sg, dma_dir);
 
 	if ((err < 0) && (err != -ENODEV))
 		rtsx_pci_stop_cmd(pcr);
@@ -395,73 +425,6 @@ out:
 }
 EXPORT_SYMBOL_GPL(rtsx_pci_transfer_data);
 
-int rtsx_pci_dma_map_sg(struct rtsx_pcr *pcr, struct scatterlist *sglist,
-		int num_sg, bool read)
-{
-	enum dma_data_direction dir = read ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
-
-	if (pcr->remove_pci)
-		return -EINVAL;
-
-	if ((sglist == NULL) || num_sg < 1)
-		return -EINVAL;
-
-	return dma_map_sg(&(pcr->pci->dev), sglist, num_sg, dir);
-}
-EXPORT_SYMBOL_GPL(rtsx_pci_dma_map_sg);
-
-int rtsx_pci_dma_unmap_sg(struct rtsx_pcr *pcr, struct scatterlist *sglist,
-		int num_sg, bool read)
-{
-	enum dma_data_direction dir = read ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
-
-	if (pcr->remove_pci)
-		return -EINVAL;
-
-	if (sglist == NULL || num_sg < 1)
-		return -EINVAL;
-
-	dma_unmap_sg(&(pcr->pci->dev), sglist, num_sg, dir);
-	return num_sg;
-}
-EXPORT_SYMBOL_GPL(rtsx_pci_dma_unmap_sg);
-
-int rtsx_pci_dma_transfer(struct rtsx_pcr *pcr, struct scatterlist *sglist,
-		int sg_count, bool read)
-{
-	struct scatterlist *sg;
-	dma_addr_t addr;
-	unsigned int len;
-	int i;
-	u32 val;
-	u8 dir = read ? DEVICE_TO_HOST : HOST_TO_DEVICE;
-	unsigned long flags;
-
-	if (pcr->remove_pci)
-		return -EINVAL;
-
-	if ((sglist == NULL) || (sg_count < 1))
-		return -EINVAL;
-
-	val = ((u32)(dir & 0x01) << 29) | TRIG_DMA | ADMA_MODE;
-	pcr->sgi = 0;
-	for_each_sg(sglist, sg, sg_count, i) {
-		addr = sg_dma_address(sg);
-		len = sg_dma_len(sg);
-		rtsx_pci_add_sg_tbl(pcr, addr, len, i == sg_count - 1);
-	}
-
-	spin_lock_irqsave(&pcr->lock, flags);
-
-	rtsx_pci_writel(pcr, RTSX_HDBAR, pcr->host_sg_tbl_addr);
-	rtsx_pci_writel(pcr, RTSX_HDBCTLR, val);
-
-	spin_unlock_irqrestore(&pcr->lock, flags);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(rtsx_pci_dma_transfer);
-
 int rtsx_pci_read_ppbuf(struct rtsx_pcr *pcr, u8 *buf, int buf_len)
 {
 	int err;
@@ -873,8 +836,6 @@ static irqreturn_t rtsx_pci_isr(int irq, void *dev_id)
 	int_reg = rtsx_pci_readl(pcr, RTSX_BIPR);
 	/* Clear interrupt flag */
 	rtsx_pci_writel(pcr, RTSX_BIPR, int_reg);
-	dev_dbg(&pcr->pci->dev, "=========== BIPR 0x%8x ==========\n", int_reg);
-
 	if ((int_reg & pcr->bier) == 0) {
 		spin_unlock(&pcr->lock);
 		return IRQ_NONE;
@@ -905,28 +866,17 @@ static irqreturn_t rtsx_pci_isr(int irq, void *dev_id)
 	}
 
 	if (int_reg & (NEED_COMPLETE_INT | DELINK_INT)) {
-		if (int_reg & (TRANS_FAIL_INT | DELINK_INT))
+		if (int_reg & (TRANS_FAIL_INT | DELINK_INT)) {
 			pcr->trans_result = TRANS_RESULT_FAIL;
-		else if (int_reg & TRANS_OK_INT)
+			if (pcr->done)
+				complete(pcr->done);
+		} else if (int_reg & TRANS_OK_INT) {
 			pcr->trans_result = TRANS_RESULT_OK;
-
-		if (pcr->done)
-			complete(pcr->done);
-
-		if (int_reg & SD_EXIST) {
-			struct rtsx_slot *slot = &pcr->slots[RTSX_SD_CARD];
-			if (slot && slot->done_transfer)
-				slot->done_transfer(slot->p_dev);
-		}
-
-		if (int_reg & MS_EXIST) {
-			struct rtsx_slot *slot = &pcr->slots[RTSX_SD_CARD];
-			if (slot && slot->done_transfer)
-				slot->done_transfer(slot->p_dev);
+			if (pcr->done)
+				complete(pcr->done);
 		}
 	}
 
-
 	if (pcr->card_inserted || pcr->card_removed)
 		schedule_delayed_work(&pcr->carddet_work,
 				msecs_to_jiffies(200));
diff --git a/drivers/mmc/host/rtsx_pci_sdmmc.c b/drivers/mmc/host/rtsx_pci_sdmmc.c
index 5fb994f9a653..0b9ded13a3ae 100644
--- a/drivers/mmc/host/rtsx_pci_sdmmc.c
+++ b/drivers/mmc/host/rtsx_pci_sdmmc.c
@@ -31,28 +31,14 @@
 #include <linux/mfd/rtsx_pci.h>
 #include <asm/unaligned.h>
 
-struct realtek_next {
-	unsigned int	sg_count;
-	s32		cookie;
-};
-
 struct realtek_pci_sdmmc {
 	struct platform_device	*pdev;
 	struct rtsx_pcr		*pcr;
 	struct mmc_host		*mmc;
 	struct mmc_request	*mrq;
-	struct mmc_command	*cmd;
-	struct mmc_data		*data;
-
-	spinlock_t		lock;
-	struct timer_list	timer;
-	struct tasklet_struct	cmd_tasklet;
-	struct tasklet_struct	data_tasklet;
-	struct tasklet_struct	finish_tasklet;
-
-	u8			rsp_type;
-	u8			rsp_len;
-	int			sg_count;
+
+	struct mutex		host_mutex;
+
 	u8			ssc_depth;
 	unsigned int		clock;
 	bool			vpclk;
@@ -62,13 +48,8 @@ struct realtek_pci_sdmmc {
 	int			power_state;
 #define SDMMC_POWER_ON		1
 #define SDMMC_POWER_OFF		0
-
-	struct realtek_next	next_data;
 };
 
-static int sd_start_multi_rw(struct realtek_pci_sdmmc *host,
-		struct mmc_request *mrq);
-
 static inline struct device *sdmmc_dev(struct realtek_pci_sdmmc *host)
 {
 	return &(host->pdev->dev);
@@ -105,95 +86,6 @@ static void sd_print_debug_regs(struct realtek_pci_sdmmc *host)
 #define sd_print_debug_regs(host)
 #endif /* DEBUG */
 
-static void sd_isr_done_transfer(struct platform_device *pdev)
-{
-	struct realtek_pci_sdmmc *host = platform_get_drvdata(pdev);
-
-	spin_lock(&host->lock);
-	if (host->cmd)
-		tasklet_schedule(&host->cmd_tasklet);
-	if (host->data)
-		tasklet_schedule(&host->data_tasklet);
-	spin_unlock(&host->lock);
-}
-
-static void sd_request_timeout(unsigned long host_addr)
-{
-	struct realtek_pci_sdmmc *host = (struct realtek_pci_sdmmc *)host_addr;
-	unsigned long flags;
-
-	spin_lock_irqsave(&host->lock, flags);
-
-	if (!host->mrq) {
-		dev_err(sdmmc_dev(host), "error: no request exist\n");
-		goto out;
-	}
-
-	if (host->cmd)
-		host->cmd->error = -ETIMEDOUT;
-	if (host->data)
-		host->data->error = -ETIMEDOUT;
-
-	dev_dbg(sdmmc_dev(host), "timeout for request\n");
-
-out:
-	tasklet_schedule(&host->finish_tasklet);
-	spin_unlock_irqrestore(&host->lock, flags);
-}
-
-static void sd_finish_request(unsigned long host_addr)
-{
-	struct realtek_pci_sdmmc *host = (struct realtek_pci_sdmmc *)host_addr;
-	struct rtsx_pcr *pcr = host->pcr;
-	struct mmc_request *mrq;
-	struct mmc_command *cmd;
-	struct mmc_data *data;
-	unsigned long flags;
-	bool any_error;
-
-	spin_lock_irqsave(&host->lock, flags);
-
-	del_timer(&host->timer);
-	mrq = host->mrq;
-	if (!mrq) {
-		dev_err(sdmmc_dev(host), "error: no request need finish\n");
-		goto out;
-	}
-
-	cmd = mrq->cmd;
-	data = mrq->data;
-
-	any_error = (mrq->sbc && mrq->sbc->error) ||
-		(mrq->stop && mrq->stop->error) ||
-		(cmd && cmd->error) || (data && data->error);
-
-	if (any_error) {
-		rtsx_pci_stop_cmd(pcr);
-		sd_clear_error(host);
-	}
-
-	if (data) {
-		if (any_error)
-			data->bytes_xfered = 0;
-		else
-			data->bytes_xfered = data->blocks * data->blksz;
-
-		if (!data->host_cookie)
-			rtsx_pci_dma_unmap_sg(pcr, data->sg, data->sg_len,
-					data->flags & MMC_DATA_READ);
-
-	}
-
-	host->mrq = NULL;
-	host->cmd = NULL;
-	host->data = NULL;
-
-out:
-	spin_unlock_irqrestore(&host->lock, flags);
-	mutex_unlock(&pcr->pcr_mutex);
-	mmc_request_done(host->mmc, mrq);
-}
-
 static int sd_read_data(struct realtek_pci_sdmmc *host, u8 *cmd, u16 byte_cnt,
 		u8 *buf, int buf_len, int timeout)
 {
@@ -311,7 +203,8 @@ static int sd_write_data(struct realtek_pci_sdmmc *host, u8 *cmd, u16 byte_cnt,
 	return 0;
 }
 
-static void sd_send_cmd(struct realtek_pci_sdmmc *host, struct mmc_command *cmd)
+static void sd_send_cmd_get_rsp(struct realtek_pci_sdmmc *host,
+		struct mmc_command *cmd)
 {
 	struct rtsx_pcr *pcr = host->pcr;
 	u8 cmd_idx = (u8)cmd->opcode;
@@ -319,14 +212,11 @@ static void sd_send_cmd(struct realtek_pci_sdmmc *host, struct mmc_command *cmd)
 	int err = 0;
 	int timeout = 100;
 	int i;
+	u8 *ptr;
+	int stat_idx = 0;
 	u8 rsp_type;
 	int rsp_len = 5;
-	unsigned long flags;
-
-	if (host->cmd)
-		dev_err(sdmmc_dev(host), "error: cmd already exist\n");
-
-	host->cmd = cmd;
+	bool clock_toggled = false;
 
 	dev_dbg(sdmmc_dev(host), "%s: SD/MMC CMD %d, arg = 0x%08x\n",
 			__func__, cmd_idx, arg);
@@ -361,8 +251,6 @@ static void sd_send_cmd(struct realtek_pci_sdmmc *host, struct mmc_command *cmd)
 		err = -EINVAL;
 		goto out;
 	}
-	host->rsp_type = rsp_type;
-	host->rsp_len = rsp_len;
 
 	if (rsp_type == SD_RSP_TYPE_R1b)
 		timeout = 3000;
@@ -372,6 +260,8 @@ static void sd_send_cmd(struct realtek_pci_sdmmc *host, struct mmc_command *cmd)
 				0xFF, SD_CLK_TOGGLE_EN);
 		if (err < 0)
 			goto out;
+
+		clock_toggled = true;
 	}
 
 	rtsx_pci_init_cmd(pcr);
@@ -395,60 +285,25 @@ static void sd_send_cmd(struct realtek_pci_sdmmc *host, struct mmc_command *cmd)
 		/* Read data from ping-pong buffer */
 		for (i = PPBUF_BASE2; i < PPBUF_BASE2 + 16; i++)
 			rtsx_pci_add_cmd(pcr, READ_REG_CMD, (u16)i, 0, 0);
+		stat_idx = 16;
 	} else if (rsp_type != SD_RSP_TYPE_R0) {
 		/* Read data from SD_CMDx registers */
 		for (i = SD_CMD0; i <= SD_CMD4; i++)
 			rtsx_pci_add_cmd(pcr, READ_REG_CMD, (u16)i, 0, 0);
+		stat_idx = 5;
 	}
 
 	rtsx_pci_add_cmd(pcr, READ_REG_CMD, SD_STAT1, 0, 0);
 
-	mod_timer(&host->timer, jiffies + msecs_to_jiffies(timeout));
-
-	spin_lock_irqsave(&pcr->lock, flags);
-	pcr->trans_result = TRANS_NOT_READY;
-	rtsx_pci_send_cmd_no_wait(pcr);
-	spin_unlock_irqrestore(&pcr->lock, flags);
-
-	return;
-
-out:
-	cmd->error = err;
-	tasklet_schedule(&host->finish_tasklet);
-}
-
-static void sd_get_rsp(unsigned long host_addr)
-{
-	struct realtek_pci_sdmmc *host = (struct realtek_pci_sdmmc *)host_addr;
-	struct rtsx_pcr *pcr = host->pcr;
-	struct mmc_command *cmd;
-	int i, err = 0, stat_idx;
-	u8 *ptr, rsp_type;
-	unsigned long flags;
-
-	spin_lock_irqsave(&host->lock, flags);
-
-	cmd = host->cmd;
-	host->cmd = NULL;
-
-	if (!cmd) {
-		dev_err(sdmmc_dev(host), "error: cmd not exist\n");
+	err = rtsx_pci_send_cmd(pcr, timeout);
+	if (err < 0) {
+		sd_print_debug_regs(host);
+		sd_clear_error(host);
+		dev_dbg(sdmmc_dev(host),
+			"rtsx_pci_send_cmd error (err = %d)\n", err);
 		goto out;
 	}
 
-	spin_lock(&pcr->lock);
-	if (pcr->trans_result == TRANS_NO_DEVICE)
-		err = -ENODEV;
-	else if (pcr->trans_result != TRANS_RESULT_OK)
-		err = -EINVAL;
-	spin_unlock(&pcr->lock);
-
-	if (err < 0)
-		goto out;
-
-	rsp_type = host->rsp_type;
-	stat_idx = host->rsp_len;
-
 	if (rsp_type == SD_RSP_TYPE_R0) {
 		err = 0;
 		goto out;
@@ -485,106 +340,26 @@ static void sd_get_rsp(unsigned long host_addr)
 				cmd->resp[0]);
 	}
 
-	if (cmd == host->mrq->sbc) {
-		sd_send_cmd(host, host->mrq->cmd);
-		spin_unlock_irqrestore(&host->lock, flags);
-		return;
-	}
-
-	if (cmd == host->mrq->stop)
-		goto out;
-
-	if (cmd->data) {
-		sd_start_multi_rw(host, host->mrq);
-		spin_unlock_irqrestore(&host->lock, flags);
-		return;
-	}
-
 out:
 	cmd->error = err;
 
-	tasklet_schedule(&host->finish_tasklet);
-	spin_unlock_irqrestore(&host->lock, flags);
-}
-
-static int sd_pre_dma_transfer(struct realtek_pci_sdmmc *host,
-			struct mmc_data *data, struct realtek_next *next)
-{
-	struct rtsx_pcr *pcr = host->pcr;
-	int read = data->flags & MMC_DATA_READ;
-	int sg_count = 0;
-
-	if (!next && data->host_cookie &&
-		data->host_cookie != host->next_data.cookie) {
-		dev_err(sdmmc_dev(host),
-			"error: invalid cookie data[%d] host[%d]\n",
-			data->host_cookie, host->next_data.cookie);
-		data->host_cookie = 0;
-	}
-
-	if (next || (!next && data->host_cookie != host->next_data.cookie))
-		sg_count = rtsx_pci_dma_map_sg(pcr,
-				data->sg, data->sg_len, read);
-	else
-		sg_count = host->next_data.sg_count;
-
-	if (next) {
-		next->sg_count = sg_count;
-		if (++next->cookie < 0)
-			next->cookie = 1;
-		data->host_cookie = next->cookie;
-	}
-
-	return sg_count;
-}
-
-static void sdmmc_pre_req(struct mmc_host *mmc, struct mmc_request *mrq,
-		bool is_first_req)
-{
-	struct realtek_pci_sdmmc *host = mmc_priv(mmc);
-	struct mmc_data *data = mrq->data;
-
-	if (data->host_cookie) {
-		dev_err(sdmmc_dev(host),
-			"error: descard already cookie data[%d]\n",
-			data->host_cookie);
-		data->host_cookie = 0;
-	}
-
-	dev_dbg(sdmmc_dev(host), "dma sg prepared: %d\n",
-		sd_pre_dma_transfer(host, data, &host->next_data));
-}
-
-static void sdmmc_post_req(struct mmc_host *mmc, struct mmc_request *mrq,
-		int err)
-{
-	struct realtek_pci_sdmmc *host = mmc_priv(mmc);
-	struct rtsx_pcr *pcr = host->pcr;
-	struct mmc_data *data = mrq->data;
-	int read = data->flags & MMC_DATA_READ;
-
-	rtsx_pci_dma_unmap_sg(pcr, data->sg, data->sg_len, read);
-	data->host_cookie = 0;
+	if (err && clock_toggled)
+		rtsx_pci_write_register(pcr, SD_BUS_STAT,
+				SD_CLK_TOGGLE_EN | SD_CLK_FORCE_STOP, 0);
 }
 
-static int sd_start_multi_rw(struct realtek_pci_sdmmc *host,
-		struct mmc_request *mrq)
+static int sd_rw_multi(struct realtek_pci_sdmmc *host, struct mmc_request *mrq)
 {
 	struct rtsx_pcr *pcr = host->pcr;
 	struct mmc_host *mmc = host->mmc;
 	struct mmc_card *card = mmc->card;
 	struct mmc_data *data = mrq->data;
 	int uhs = mmc_card_uhs(card);
-	int read = data->flags & MMC_DATA_READ;
+	int read = (data->flags & MMC_DATA_READ) ? 1 : 0;
 	u8 cfg2, trans_mode;
 	int err;
 	size_t data_len = data->blksz * data->blocks;
 
-	if (host->data)
-		dev_err(sdmmc_dev(host), "error: data already exist\n");
-
-	host->data = data;
-
 	if (read) {
 		cfg2 = SD_CALCULATE_CRC7 | SD_CHECK_CRC16 |
 			SD_NO_WAIT_BUSY_END | SD_CHECK_CRC7 | SD_RSP_LEN_0;
@@ -635,54 +410,15 @@ static int sd_start_multi_rw(struct realtek_pci_sdmmc *host,
 	rtsx_pci_add_cmd(pcr, CHECK_REG_CMD, SD_TRANSFER,
 			SD_TRANSFER_END, SD_TRANSFER_END);
 
-	mod_timer(&host->timer, jiffies + 10 * HZ);
 	rtsx_pci_send_cmd_no_wait(pcr);
 
-	err = rtsx_pci_dma_transfer(pcr, data->sg, host->sg_count, read);
-	if (err < 0) {
-		data->error = err;
-		tasklet_schedule(&host->finish_tasklet);
-	}
-	return 0;
-}
-
-static void sd_finish_multi_rw(unsigned long host_addr)
-{
-	struct realtek_pci_sdmmc *host = (struct realtek_pci_sdmmc *)host_addr;
-	struct rtsx_pcr *pcr = host->pcr;
-	struct mmc_data *data;
-	int err = 0;
-	unsigned long flags;
-
-	spin_lock_irqsave(&host->lock, flags);
-
-	if (!host->data) {
-		dev_err(sdmmc_dev(host), "error: no data exist\n");
-		goto out;
-	}
-
-	data = host->data;
-	host->data = NULL;
-
-	if (pcr->trans_result == TRANS_NO_DEVICE)
-		err = -ENODEV;
-	else if (pcr->trans_result != TRANS_RESULT_OK)
-		err = -EINVAL;
-
+	err = rtsx_pci_transfer_data(pcr, data->sg, data->sg_len, read, 10000);
 	if (err < 0) {
-		data->error = err;
-		goto out;
-	}
-
-	if (!host->mrq->sbc && data->stop) {
-		sd_send_cmd(host, data->stop);
-		spin_unlock_irqrestore(&host->lock, flags);
-		return;
+		sd_clear_error(host);
+		return err;
 	}
 
-out:
-	tasklet_schedule(&host->finish_tasklet);
-	spin_unlock_irqrestore(&host->lock, flags);
+	return 0;
 }
 
 static inline void sd_enable_initial_mode(struct realtek_pci_sdmmc *host)
@@ -901,13 +637,6 @@ static int sd_tuning_rx(struct realtek_pci_sdmmc *host, u8 opcode)
 	return 0;
 }
 
-static inline bool sd_use_muti_rw(struct mmc_command *cmd)
-{
-	return mmc_op_multi(cmd->opcode) ||
-		(cmd->opcode == MMC_READ_SINGLE_BLOCK) ||
-		(cmd->opcode == MMC_WRITE_BLOCK);
-}
-
 static void sdmmc_request(struct mmc_host *mmc, struct mmc_request *mrq)
 {
 	struct realtek_pci_sdmmc *host = mmc_priv(mmc);
@@ -916,14 +645,6 @@ static void sdmmc_request(struct mmc_host *mmc, struct mmc_request *mrq)
 	struct mmc_data *data = mrq->data;
 	unsigned int data_size = 0;
 	int err;
-	unsigned long flags;
-
-	mutex_lock(&pcr->pcr_mutex);
-	spin_lock_irqsave(&host->lock, flags);
-
-	if (host->mrq)
-		dev_err(sdmmc_dev(host), "error: request already exist\n");
-	host->mrq = mrq;
 
 	if (host->eject) {
 		cmd->error = -ENOMEDIUM;
@@ -936,6 +657,8 @@ static void sdmmc_request(struct mmc_host *mmc, struct mmc_request *mrq)
 		goto finish;
 	}
 
+	mutex_lock(&pcr->pcr_mutex);
+
 	rtsx_pci_start_run(pcr);
 
 	rtsx_pci_switch_clock(pcr, host->clock, host->ssc_depth,
@@ -944,28 +667,46 @@ static void sdmmc_request(struct mmc_host *mmc, struct mmc_request *mrq)
 	rtsx_pci_write_register(pcr, CARD_SHARE_MODE,
 			CARD_SHARE_MASK, CARD_SHARE_48_SD);
 
+	mutex_lock(&host->host_mutex);
+	host->mrq = mrq;
+	mutex_unlock(&host->host_mutex);
+
 	if (mrq->data)
 		data_size = data->blocks * data->blksz;
 
-	if (sd_use_muti_rw(cmd))
-		host->sg_count = sd_pre_dma_transfer(host, data, NULL);
+	if (!data_size || mmc_op_multi(cmd->opcode) ||
+			(cmd->opcode == MMC_READ_SINGLE_BLOCK) ||
+			(cmd->opcode == MMC_WRITE_BLOCK)) {
+		sd_send_cmd_get_rsp(host, cmd);
 
-	if (!data_size || sd_use_muti_rw(cmd)) {
-		if (mrq->sbc)
-			sd_send_cmd(host, mrq->sbc);
-		else
-			sd_send_cmd(host, cmd);
-		spin_unlock_irqrestore(&host->lock, flags);
+		if (!cmd->error && data_size) {
+			sd_rw_multi(host, mrq);
+
+			if (mmc_op_multi(cmd->opcode) && mrq->stop)
+				sd_send_cmd_get_rsp(host, mrq->stop);
+		}
 	} else {
-		spin_unlock_irqrestore(&host->lock, flags);
 		sd_normal_rw(host, mrq);
-		tasklet_schedule(&host->finish_tasklet);
 	}
-	return;
+
+	if (mrq->data) {
+		if (cmd->error || data->error)
+			data->bytes_xfered = 0;
+		else
+			data->bytes_xfered = data->blocks * data->blksz;
+	}
+
+	mutex_unlock(&pcr->pcr_mutex);
 
 finish:
-	tasklet_schedule(&host->finish_tasklet);
-	spin_unlock_irqrestore(&host->lock, flags);
+	if (cmd->error)
+		dev_dbg(sdmmc_dev(host), "cmd->error = %d\n", cmd->error);
+
+	mutex_lock(&host->host_mutex);
+	host->mrq = NULL;
+	mutex_unlock(&host->host_mutex);
+
+	mmc_request_done(mmc, mrq);
 }
 
 static int sd_set_bus_width(struct realtek_pci_sdmmc *host,
@@ -1400,8 +1141,6 @@ out:
 }
 
 static const struct mmc_host_ops realtek_pci_sdmmc_ops = {
-	.pre_req = sdmmc_pre_req,
-	.post_req = sdmmc_post_req,
 	.request = sdmmc_request,
 	.set_ios = sdmmc_set_ios,
 	.get_ro = sdmmc_get_ro,
@@ -1465,7 +1204,6 @@ static int rtsx_pci_sdmmc_drv_probe(struct platform_device *pdev)
 	struct realtek_pci_sdmmc *host;
 	struct rtsx_pcr *pcr;
 	struct pcr_handle *handle = pdev->dev.platform_data;
-	unsigned long host_addr;
 
 	if (!handle)
 		return -ENXIO;
@@ -1489,15 +1227,8 @@ static int rtsx_pci_sdmmc_drv_probe(struct platform_device *pdev)
 	pcr->slots[RTSX_SD_CARD].p_dev = pdev;
 	pcr->slots[RTSX_SD_CARD].card_event = rtsx_pci_sdmmc_card_event;
 
-	host_addr = (unsigned long)host;
-	host->next_data.cookie = 1;
-	setup_timer(&host->timer, sd_request_timeout, host_addr);
-	tasklet_init(&host->cmd_tasklet, sd_get_rsp, host_addr);
-	tasklet_init(&host->data_tasklet, sd_finish_multi_rw, host_addr);
-	tasklet_init(&host->finish_tasklet, sd_finish_request, host_addr);
-	spin_lock_init(&host->lock);
+	mutex_init(&host->host_mutex);
 
-	pcr->slots[RTSX_SD_CARD].done_transfer = sd_isr_done_transfer;
 	realtek_init_host(host);
 
 	mmc_add_host(mmc);
@@ -1510,8 +1241,6 @@ static int rtsx_pci_sdmmc_drv_remove(struct platform_device *pdev)
 	struct realtek_pci_sdmmc *host = platform_get_drvdata(pdev);
 	struct rtsx_pcr *pcr;
 	struct mmc_host *mmc;
-	struct mmc_request *mrq;
-	unsigned long flags;
 
 	if (!host)
 		return 0;
@@ -1519,33 +1248,22 @@ static int rtsx_pci_sdmmc_drv_remove(struct platform_device *pdev)
 	pcr = host->pcr;
 	pcr->slots[RTSX_SD_CARD].p_dev = NULL;
 	pcr->slots[RTSX_SD_CARD].card_event = NULL;
-	pcr->slots[RTSX_SD_CARD].done_transfer = NULL;
 	mmc = host->mmc;
-	mrq = host->mrq;
 
-	spin_lock_irqsave(&host->lock, flags);
+	mutex_lock(&host->host_mutex);
 	if (host->mrq) {
 		dev_dbg(&(pdev->dev),
 			"%s: Controller removed during transfer\n",
 			mmc_hostname(mmc));
 
-		if (mrq->sbc)
-			mrq->sbc->error = -ENOMEDIUM;
-		if (mrq->cmd)
-			mrq->cmd->error = -ENOMEDIUM;
-		if (mrq->stop)
-			mrq->stop->error = -ENOMEDIUM;
-		if (mrq->data)
-			mrq->data->error = -ENOMEDIUM;
+		rtsx_pci_complete_unfinished_transfer(pcr);
 
-		tasklet_schedule(&host->finish_tasklet);
+		host->mrq->cmd->error = -ENOMEDIUM;
+		if (host->mrq->stop)
+			host->mrq->stop->error = -ENOMEDIUM;
+		mmc_request_done(mmc, host->mrq);
 	}
-	spin_unlock_irqrestore(&host->lock, flags);
-
-	del_timer_sync(&host->timer);
-	tasklet_kill(&host->cmd_tasklet);
-	tasklet_kill(&host->data_tasklet);
-	tasklet_kill(&host->finish_tasklet);
+	mutex_unlock(&host->host_mutex);
 
 	mmc_remove_host(mmc);
 	host->eject = true;
diff --git a/drivers/mtd/nand/davinci_nand.c b/drivers/mtd/nand/davinci_nand.c
index 4615d79fc93f..b922c8efcf40 100644
--- a/drivers/mtd/nand/davinci_nand.c
+++ b/drivers/mtd/nand/davinci_nand.c
@@ -523,6 +523,7 @@ static struct nand_ecclayout hwecc4_2048 = {
 #if defined(CONFIG_OF)
 static const struct of_device_id davinci_nand_of_match[] = {
 	{.compatible = "ti,davinci-nand", },
+	{.compatible = "ti,keystone-nand", },
 	{},
 };
 MODULE_DEVICE_TABLE(of, davinci_nand_of_match);
@@ -581,6 +582,11 @@ static struct davinci_nand_pdata
 		    of_property_read_bool(pdev->dev.of_node,
 			"ti,davinci-nand-use-bbt"))
 			pdata->bbt_options = NAND_BBT_USE_FLASH;
+
+		if (of_device_is_compatible(pdev->dev.of_node,
+					    "ti,keystone-nand")) {
+			pdata->options |= NAND_NO_SUBPAGE_WRITE;
+		}
 	}
 
 	return dev_get_platdata(&pdev->dev);
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 9f69e818b000..93580a47cc54 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -82,7 +82,8 @@ static inline struct arp_pkt *arp_pkt(const struct sk_buff *skb)
 }
 
 /* Forward declaration */
-static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[]);
+static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[],
+				      bool strict_match);
 static void rlb_purge_src_ip(struct bonding *bond, struct arp_pkt *arp);
 static void rlb_src_unlink(struct bonding *bond, u32 index);
 static void rlb_src_link(struct bonding *bond, u32 ip_src_hash,
@@ -459,7 +460,7 @@ static void rlb_teach_disabled_mac_on_primary(struct bonding *bond, u8 addr[])
 
 	bond->alb_info.rlb_promisc_timeout_counter = 0;
 
-	alb_send_learning_packets(bond->curr_active_slave, addr);
+	alb_send_learning_packets(bond->curr_active_slave, addr, true);
 }
 
 /* slave being removed should not be active at this point
@@ -995,7 +996,7 @@ static void rlb_clear_vlan(struct bonding *bond, unsigned short vlan_id)
 /*********************** tlb/rlb shared functions *********************/
 
 static void alb_send_lp_vid(struct slave *slave, u8 mac_addr[],
-			    u16 vid)
+			    __be16 vlan_proto, u16 vid)
 {
 	struct learning_pkt pkt;
 	struct sk_buff *skb;
@@ -1021,7 +1022,7 @@ static void alb_send_lp_vid(struct slave *slave, u8 mac_addr[],
 	skb->dev = slave->dev;
 
 	if (vid) {
-		skb = vlan_put_tag(skb, htons(ETH_P_8021Q), vid);
+		skb = vlan_put_tag(skb, vlan_proto, vid);
 		if (!skb) {
 			pr_err("%s: Error: failed to insert VLAN tag\n",
 			       slave->bond->dev->name);
@@ -1032,22 +1033,32 @@ static void alb_send_lp_vid(struct slave *slave, u8 mac_addr[],
 	dev_queue_xmit(skb);
 }
 
-
-static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[])
+static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[],
+				      bool strict_match)
 {
 	struct bonding *bond = bond_get_bond_by_slave(slave);
 	struct net_device *upper;
 	struct list_head *iter;
 
 	/* send untagged */
-	alb_send_lp_vid(slave, mac_addr, 0);
+	alb_send_lp_vid(slave, mac_addr, 0, 0);
 
 	/* loop through vlans and send one packet for each */
 	rcu_read_lock();
 	netdev_for_each_all_upper_dev_rcu(bond->dev, upper, iter) {
-		if (upper->priv_flags & IFF_802_1Q_VLAN)
-			alb_send_lp_vid(slave, mac_addr,
-					vlan_dev_vlan_id(upper));
+		if (is_vlan_dev(upper) && vlan_get_encap_level(upper) == 0) {
+			if (strict_match &&
+			    ether_addr_equal_64bits(mac_addr,
+						    upper->dev_addr)) {
+				alb_send_lp_vid(slave, mac_addr,
+						vlan_dev_vlan_proto(upper),
+						vlan_dev_vlan_id(upper));
+			} else if (!strict_match) {
+				alb_send_lp_vid(slave, upper->dev_addr,
+						vlan_dev_vlan_proto(upper),
+						vlan_dev_vlan_id(upper));
+			}
+		}
 	}
 	rcu_read_unlock();
 }
@@ -1107,7 +1118,7 @@ static void alb_fasten_mac_swap(struct bonding *bond, struct slave *slave1,
 
 	/* fasten the change in the switch */
 	if (SLAVE_IS_OK(slave1)) {
-		alb_send_learning_packets(slave1, slave1->dev->dev_addr);
+		alb_send_learning_packets(slave1, slave1->dev->dev_addr, false);
 		if (bond->alb_info.rlb_enabled) {
 			/* inform the clients that the mac address
 			 * has changed
@@ -1119,7 +1130,7 @@ static void alb_fasten_mac_swap(struct bonding *bond, struct slave *slave1,
 	}
 
 	if (SLAVE_IS_OK(slave2)) {
-		alb_send_learning_packets(slave2, slave2->dev->dev_addr);
+		alb_send_learning_packets(slave2, slave2->dev->dev_addr, false);
 		if (bond->alb_info.rlb_enabled) {
 			/* inform the clients that the mac address
 			 * has changed
@@ -1490,6 +1501,8 @@ void bond_alb_monitor(struct work_struct *work)
 
 	/* send learning packets */
 	if (bond_info->lp_counter >= BOND_ALB_LP_TICKS(bond)) {
+		bool strict_match;
+
 		/* change of curr_active_slave involves swapping of mac addresses.
 		 * in order to avoid this swapping from happening while
 		 * sending the learning packets, the curr_slave_lock must be held for
@@ -1497,8 +1510,15 @@ void bond_alb_monitor(struct work_struct *work)
 		 */
 		read_lock(&bond->curr_slave_lock);
 
-		bond_for_each_slave_rcu(bond, slave, iter)
-			alb_send_learning_packets(slave, slave->dev->dev_addr);
+		bond_for_each_slave_rcu(bond, slave, iter) {
+			/* If updating current_active, use all currently
+			 * user mac addreses (!strict_match).  Otherwise, only
+			 * use mac of the slave device.
+			 */
+			strict_match = (slave != bond->curr_active_slave);
+			alb_send_learning_packets(slave, slave->dev->dev_addr,
+						  strict_match);
+		}
 
 		read_unlock(&bond->curr_slave_lock);
 
@@ -1721,7 +1741,8 @@ void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave
 	} else {
 		/* set the new_slave to the bond mac address */
 		alb_set_slave_mac_addr(new_slave, bond->dev->dev_addr);
-		alb_send_learning_packets(new_slave, bond->dev->dev_addr);
+		alb_send_learning_packets(new_slave, bond->dev->dev_addr,
+					  false);
 	}
 
 	write_lock_bh(&bond->curr_slave_lock);
@@ -1764,7 +1785,8 @@ int bond_alb_set_mac_address(struct net_device *bond_dev, void *addr)
 		alb_set_slave_mac_addr(bond->curr_active_slave, bond_dev->dev_addr);
 
 		read_lock(&bond->lock);
-		alb_send_learning_packets(bond->curr_active_slave, bond_dev->dev_addr);
+		alb_send_learning_packets(bond->curr_active_slave,
+					  bond_dev->dev_addr, false);
 		if (bond->alb_info.rlb_enabled) {
 			/* inform clients mac address has changed */
 			rlb_req_update_slave_clients(bond, bond->curr_active_slave);
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 69aff72c8957..d3a67896d435 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2126,10 +2126,10 @@ static bool bond_has_this_ip(struct bonding *bond, __be32 ip)
  */
 static void bond_arp_send(struct net_device *slave_dev, int arp_op,
 			  __be32 dest_ip, __be32 src_ip,
-			  struct bond_vlan_tag *inner,
-			  struct bond_vlan_tag *outer)
+			  struct bond_vlan_tag *tags)
 {
 	struct sk_buff *skb;
+	int i;
 
 	pr_debug("arp %d on slave %s: dst %pI4 src %pI4\n",
 		 arp_op, slave_dev->name, &dest_ip, &src_ip);
@@ -2141,21 +2141,26 @@ static void bond_arp_send(struct net_device *slave_dev, int arp_op,
 		net_err_ratelimited("ARP packet allocation failed\n");
 		return;
 	}
-	if (outer->vlan_id) {
-		if (inner->vlan_id) {
-			pr_debug("inner tag: proto %X vid %X\n",
-				 ntohs(inner->vlan_proto), inner->vlan_id);
-			skb = __vlan_put_tag(skb, inner->vlan_proto,
-					     inner->vlan_id);
-			if (!skb) {
-				net_err_ratelimited("failed to insert inner VLAN tag\n");
-				return;
-			}
-		}
 
-		pr_debug("outer reg: proto %X vid %X\n",
-			 ntohs(outer->vlan_proto), outer->vlan_id);
-		skb = vlan_put_tag(skb, outer->vlan_proto, outer->vlan_id);
+	/* Go through all the tags backwards and add them to the packet */
+	for (i = BOND_MAX_VLAN_ENCAP - 1; i > 0; i--) {
+		if (!tags[i].vlan_id)
+			continue;
+
+		pr_debug("inner tag: proto %X vid %X\n",
+			 ntohs(tags[i].vlan_proto), tags[i].vlan_id);
+		skb = __vlan_put_tag(skb, tags[i].vlan_proto,
+				     tags[i].vlan_id);
+		if (!skb) {
+			net_err_ratelimited("failed to insert inner VLAN tag\n");
+			return;
+		}
+	}
+	/* Set the outer tag */
+	if (tags[0].vlan_id) {
+		pr_debug("outer tag: proto %X vid %X\n",
+			 ntohs(tags[0].vlan_proto), tags[0].vlan_id);
+		skb = vlan_put_tag(skb, tags[0].vlan_proto, tags[0].vlan_id);
 		if (!skb) {
 			net_err_ratelimited("failed to insert outer VLAN tag\n");
 			return;
@@ -2164,22 +2169,52 @@ static void bond_arp_send(struct net_device *slave_dev, int arp_op,
 	arp_xmit(skb);
 }
 
+/* Validate the device path between the @start_dev and the @end_dev.
+ * The path is valid if the @end_dev is reachable through device
+ * stacking.
+ * When the path is validated, collect any vlan information in the
+ * path.
+ */
+static bool bond_verify_device_path(struct net_device *start_dev,
+				    struct net_device *end_dev,
+				    struct bond_vlan_tag *tags)
+{
+	struct net_device *upper;
+	struct list_head  *iter;
+	int  idx;
+
+	if (start_dev == end_dev)
+		return true;
+
+	netdev_for_each_upper_dev_rcu(start_dev, upper, iter) {
+		if (bond_verify_device_path(upper, end_dev, tags)) {
+			if (is_vlan_dev(upper)) {
+				idx = vlan_get_encap_level(upper);
+				if (idx >= BOND_MAX_VLAN_ENCAP)
+					return false;
+
+				tags[idx].vlan_proto =
+						    vlan_dev_vlan_proto(upper);
+				tags[idx].vlan_id = vlan_dev_vlan_id(upper);
+			}
+			return true;
+		}
+	}
+
+	return false;
+}
 
 static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
 {
-	struct net_device *upper, *vlan_upper;
-	struct list_head *iter, *vlan_iter;
 	struct rtable *rt;
-	struct bond_vlan_tag inner, outer;
+	struct bond_vlan_tag tags[BOND_MAX_VLAN_ENCAP];
 	__be32 *targets = bond->params.arp_targets, addr;
 	int i;
+	bool ret;
 
 	for (i = 0; i < BOND_MAX_ARP_TARGETS && targets[i]; i++) {
 		pr_debug("basa: target %pI4\n", &targets[i]);
-		inner.vlan_proto = 0;
-		inner.vlan_id = 0;
-		outer.vlan_proto = 0;
-		outer.vlan_id = 0;
+		memset(tags, 0, sizeof(tags));
 
 		/* Find out through which dev should the packet go */
 		rt = ip_route_output(dev_net(bond->dev), targets[i], 0,
@@ -2192,7 +2227,8 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
 				net_warn_ratelimited("%s: no route to arp_ip_target %pI4 and arp_validate is set\n",
 						     bond->dev->name,
 						     &targets[i]);
-			bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], 0, &inner, &outer);
+			bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i],
+				      0, tags);
 			continue;
 		}
 
@@ -2201,52 +2237,12 @@ static void bond_arp_send_all(struct bonding *bond, struct slave *slave)
 			goto found;
 
 		rcu_read_lock();
-		/* first we search only for vlan devices. for every vlan
-		 * found we verify its upper dev list, searching for the
-		 * rt->dst.dev. If found we save the tag of the vlan and
-		 * proceed to send the packet.
-		 */
-		netdev_for_each_all_upper_dev_rcu(bond->dev, vlan_upper,
-						  vlan_iter) {
-			if (!is_vlan_dev(vlan_upper))
-				continue;
-
-			if (vlan_upper == rt->dst.dev) {
-				outer.vlan_proto = vlan_dev_vlan_proto(vlan_upper);
-				outer.vlan_id = vlan_dev_vlan_id(vlan_upper);
-				rcu_read_unlock();
-				goto found;
-			}
-			netdev_for_each_all_upper_dev_rcu(vlan_upper, upper,
-							  iter) {
-				if (upper == rt->dst.dev) {
-					/* If the upper dev is a vlan dev too,
-					 *  set the vlan tag to inner tag.
-					 */
-					if (is_vlan_dev(upper)) {
-						inner.vlan_proto = vlan_dev_vlan_proto(upper);
-						inner.vlan_id = vlan_dev_vlan_id(upper);
-					}
-					outer.vlan_proto = vlan_dev_vlan_proto(vlan_upper);
-					outer.vlan_id = vlan_dev_vlan_id(vlan_upper);
-					rcu_read_unlock();
-					goto found;
-				}
-			}
-		}
-
-		/* if the device we're looking for is not on top of any of
-		 * our upper vlans, then just search for any dev that
-		 * matches, and in case it's a vlan - save the id
-		 */
-		netdev_for_each_all_upper_dev_rcu(bond->dev, upper, iter) {
-			if (upper == rt->dst.dev) {
-				rcu_read_unlock();
-				goto found;
-			}
-		}
+		ret = bond_verify_device_path(bond->dev, rt->dst.dev, tags);
 		rcu_read_unlock();
 
+		if (ret)
+			goto found;
+
 		/* Not our device - skip */
 		pr_debug("%s: no path to arp_ip_target %pI4 via rt.dev %s\n",
 			 bond->dev->name, &targets[i],
@@ -2259,7 +2255,7 @@ found:
 		addr = bond_confirm_addr(rt->dst.dev, targets[i], 0);
 		ip_rt_put(rt);
 		bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i],
-			      addr, &inner, &outer);
+			      addr, tags);
 	}
 }
 
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 724e30fa20b9..832070298446 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -125,6 +125,7 @@ static const struct bond_opt_value bond_fail_over_mac_tbl[] = {
 static const struct bond_opt_value bond_intmax_tbl[] = {
 	{ "off",     0,       BOND_VALFLAG_DEFAULT},
 	{ "maxval",  INT_MAX, BOND_VALFLAG_MAX},
+	{ NULL,      -1,      0}
 };
 
 static const struct bond_opt_value bond_lacp_rate_tbl[] = {
diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h
index b8bdd0acc8f3..00bea320e3b5 100644
--- a/drivers/net/bonding/bonding.h
+++ b/drivers/net/bonding/bonding.h
@@ -36,6 +36,7 @@
 
 #define bond_version DRV_DESCRIPTION ": v" DRV_VERSION " (" DRV_RELDATE ")\n"
 
+#define BOND_MAX_VLAN_ENCAP	2
 #define BOND_MAX_ARP_TARGETS	16
 
 #define BOND_DEFAULT_MIIMON	100
diff --git a/drivers/net/can/c_can/Kconfig b/drivers/net/can/c_can/Kconfig
index 8ab7103d4f44..61ffc12d8fd8 100644
--- a/drivers/net/can/c_can/Kconfig
+++ b/drivers/net/can/c_can/Kconfig
@@ -14,13 +14,6 @@ config CAN_C_CAN_PLATFORM
 	  SPEAr1310 and SPEAr320 evaluation boards & TI (www.ti.com)
 	  boards like am335x, dm814x, dm813x and dm811x.
 
-config CAN_C_CAN_STRICT_FRAME_ORDERING
-	bool "Force a strict RX CAN frame order (may cause frame loss)"
-	---help---
-	  The RX split buffer prevents packet reordering but can cause packet
-	  loss. Only enable this option when you accept to lose CAN frames
-	  in favour of getting the received CAN frames in the correct order.
-
 config CAN_C_CAN_PCI
 	tristate "Generic PCI Bus based C_CAN/D_CAN driver"
 	depends on PCI
diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c
index a2ca820b5373..95e04e2002da 100644
--- a/drivers/net/can/c_can/c_can.c
+++ b/drivers/net/can/c_can/c_can.c
@@ -732,26 +732,12 @@ static u32 c_can_adjust_pending(u32 pend)
 static inline void c_can_rx_object_get(struct net_device *dev,
 				       struct c_can_priv *priv, u32 obj)
 {
-#ifdef CONFIG_CAN_C_CAN_STRICT_FRAME_ORDERING
-	if (obj < C_CAN_MSG_RX_LOW_LAST)
-		c_can_object_get(dev, IF_RX, obj, IF_COMM_RCV_LOW);
-	else
-#endif
 		c_can_object_get(dev, IF_RX, obj, priv->comm_rcv_high);
 }
 
 static inline void c_can_rx_finalize(struct net_device *dev,
 				     struct c_can_priv *priv, u32 obj)
 {
-#ifdef CONFIG_CAN_C_CAN_STRICT_FRAME_ORDERING
-	if (obj < C_CAN_MSG_RX_LOW_LAST)
-		priv->rxmasked |= BIT(obj - 1);
-	else if (obj == C_CAN_MSG_RX_LOW_LAST) {
-		priv->rxmasked = 0;
-		/* activate all lower message objects */
-		c_can_activate_all_lower_rx_msg_obj(dev, IF_RX);
-	}
-#endif
 	if (priv->type != BOSCH_D_CAN)
 		c_can_object_get(dev, IF_RX, obj, IF_COMM_CLR_NEWDAT);
 }
@@ -799,9 +785,6 @@ static inline u32 c_can_get_pending(struct c_can_priv *priv)
 {
 	u32 pend = priv->read_reg(priv, C_CAN_NEWDAT1_REG);
 
-#ifdef CONFIG_CAN_C_CAN_STRICT_FRAME_ORDERING
-	pend &= ~priv->rxmasked;
-#endif
 	return pend;
 }
 
@@ -814,25 +797,6 @@ static inline u32 c_can_get_pending(struct c_can_priv *priv)
  * has arrived. To work-around this issue, we keep two groups of message
  * objects whose partitioning is defined by C_CAN_MSG_OBJ_RX_SPLIT.
  *
- * If CONFIG_CAN_C_CAN_STRICT_FRAME_ORDERING = y
- *
- * To ensure in-order frame reception we use the following
- * approach while re-activating a message object to receive further
- * frames:
- * - if the current message object number is lower than
- *   C_CAN_MSG_RX_LOW_LAST, do not clear the NEWDAT bit while clearing
- *   the INTPND bit.
- * - if the current message object number is equal to
- *   C_CAN_MSG_RX_LOW_LAST then clear the NEWDAT bit of all lower
- *   receive message objects.
- * - if the current message object number is greater than
- *   C_CAN_MSG_RX_LOW_LAST then clear the NEWDAT bit of
- *   only this message object.
- *
- * This can cause packet loss!
- *
- * If CONFIG_CAN_C_CAN_STRICT_FRAME_ORDERING = n
- *
  * We clear the newdat bit right away.
  *
  * This can result in packet reordering when the readout is slow.
diff --git a/drivers/net/can/sja1000/peak_pci.c b/drivers/net/can/sja1000/peak_pci.c
index c540e3d12e3d..564933ae218c 100644
--- a/drivers/net/can/sja1000/peak_pci.c
+++ b/drivers/net/can/sja1000/peak_pci.c
@@ -551,7 +551,7 @@ static int peak_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct sja1000_priv *priv;
 	struct peak_pci_chan *chan;
-	struct net_device *dev;
+	struct net_device *dev, *prev_dev;
 	void __iomem *cfg_base, *reg_base;
 	u16 sub_sys_id, icr;
 	int i, err, channels;
@@ -688,11 +688,13 @@ failure_remove_channels:
 	writew(0x0, cfg_base + PITA_ICR + 2);
 
 	chan = NULL;
-	for (dev = pci_get_drvdata(pdev); dev; dev = chan->prev_dev) {
-		unregister_sja1000dev(dev);
-		free_sja1000dev(dev);
+	for (dev = pci_get_drvdata(pdev); dev; dev = prev_dev) {
 		priv = netdev_priv(dev);
 		chan = priv->priv;
+		prev_dev = chan->prev_dev;
+
+		unregister_sja1000dev(dev);
+		free_sja1000dev(dev);
 	}
 
 	/* free any PCIeC resources too */
@@ -726,10 +728,12 @@ static void peak_pci_remove(struct pci_dev *pdev)
 
 	/* Loop over all registered devices */
 	while (1) {
+		struct net_device *prev_dev = chan->prev_dev;
+
 		dev_info(&pdev->dev, "removing device %s\n", dev->name);
 		unregister_sja1000dev(dev);
 		free_sja1000dev(dev);
-		dev = chan->prev_dev;
+		dev = prev_dev;
 
 		if (!dev) {
 			/* do that only for first channel */
diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig
index 39b26fe28d10..d7401017a3f1 100644
--- a/drivers/net/ethernet/Kconfig
+++ b/drivers/net/ethernet/Kconfig
@@ -35,6 +35,18 @@ source "drivers/net/ethernet/calxeda/Kconfig"
 source "drivers/net/ethernet/chelsio/Kconfig"
 source "drivers/net/ethernet/cirrus/Kconfig"
 source "drivers/net/ethernet/cisco/Kconfig"
+
+config CX_ECAT
+	tristate "Beckhoff CX5020 EtherCAT master support"
+	depends on PCI
+	---help---
+	  Driver for EtherCAT master module located on CCAT FPGA
+	  that can be found on Beckhoff CX5020, and possibly other of CX
+	  Beckhoff CX series industrial PCs.
+
+	  To compile this driver as a module, choose M here. The module
+	  will be called ec_bhf.
+
 source "drivers/net/ethernet/davicom/Kconfig"
 
 config DNET
diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile
index 545d0b3b9cb4..35190e36c456 100644
--- a/drivers/net/ethernet/Makefile
+++ b/drivers/net/ethernet/Makefile
@@ -21,6 +21,7 @@ obj-$(CONFIG_NET_CALXEDA_XGMAC) += calxeda/
 obj-$(CONFIG_NET_VENDOR_CHELSIO) += chelsio/
 obj-$(CONFIG_NET_VENDOR_CIRRUS) += cirrus/
 obj-$(CONFIG_NET_VENDOR_CISCO) += cisco/
+obj-$(CONFIG_CX_ECAT) += ec_bhf.o
 obj-$(CONFIG_DM9000) += davicom/
 obj-$(CONFIG_DNET) += dnet.o
 obj-$(CONFIG_NET_VENDOR_DEC) += dec/
diff --git a/drivers/net/ethernet/altera/Makefile b/drivers/net/ethernet/altera/Makefile
index d4a187e45369..3eff2fd3997e 100644
--- a/drivers/net/ethernet/altera/Makefile
+++ b/drivers/net/ethernet/altera/Makefile
@@ -5,3 +5,4 @@
 obj-$(CONFIG_ALTERA_TSE) += altera_tse.o
 altera_tse-objs := altera_tse_main.o altera_tse_ethtool.o \
 altera_msgdma.o altera_sgdma.o altera_utils.o
+ccflags-y += -D__CHECK_ENDIAN__
diff --git a/drivers/net/ethernet/altera/altera_msgdma.c b/drivers/net/ethernet/altera/altera_msgdma.c
index 4d1f2fdd5c32..0fb986ba3290 100644
--- a/drivers/net/ethernet/altera/altera_msgdma.c
+++ b/drivers/net/ethernet/altera/altera_msgdma.c
@@ -37,18 +37,16 @@ void msgdma_start_rxdma(struct altera_tse_private *priv)
 void msgdma_reset(struct altera_tse_private *priv)
 {
 	int counter;
-	struct msgdma_csr *txcsr =
-		(struct msgdma_csr *)priv->tx_dma_csr;
-	struct msgdma_csr *rxcsr =
-		(struct msgdma_csr *)priv->rx_dma_csr;
 
 	/* Reset Rx mSGDMA */
-	iowrite32(MSGDMA_CSR_STAT_MASK, &rxcsr->status);
-	iowrite32(MSGDMA_CSR_CTL_RESET, &rxcsr->control);
+	csrwr32(MSGDMA_CSR_STAT_MASK, priv->rx_dma_csr,
+		msgdma_csroffs(status));
+	csrwr32(MSGDMA_CSR_CTL_RESET, priv->rx_dma_csr,
+		msgdma_csroffs(control));
 
 	counter = 0;
 	while (counter++ < ALTERA_TSE_SW_RESET_WATCHDOG_CNTR) {
-		if (tse_bit_is_clear(&rxcsr->status,
+		if (tse_bit_is_clear(priv->rx_dma_csr, msgdma_csroffs(status),
 				     MSGDMA_CSR_STAT_RESETTING))
 			break;
 		udelay(1);
@@ -59,15 +57,18 @@ void msgdma_reset(struct altera_tse_private *priv)
 			   "TSE Rx mSGDMA resetting bit never cleared!\n");
 
 	/* clear all status bits */
-	iowrite32(MSGDMA_CSR_STAT_MASK, &rxcsr->status);
+	csrwr32(MSGDMA_CSR_STAT_MASK, priv->rx_dma_csr, msgdma_csroffs(status));
 
 	/* Reset Tx mSGDMA */
-	iowrite32(MSGDMA_CSR_STAT_MASK, &txcsr->status);
-	iowrite32(MSGDMA_CSR_CTL_RESET, &txcsr->control);
+	csrwr32(MSGDMA_CSR_STAT_MASK, priv->tx_dma_csr,
+		msgdma_csroffs(status));
+
+	csrwr32(MSGDMA_CSR_CTL_RESET, priv->tx_dma_csr,
+		msgdma_csroffs(control));
 
 	counter = 0;
 	while (counter++ < ALTERA_TSE_SW_RESET_WATCHDOG_CNTR) {
-		if (tse_bit_is_clear(&txcsr->status,
+		if (tse_bit_is_clear(priv->tx_dma_csr, msgdma_csroffs(status),
 				     MSGDMA_CSR_STAT_RESETTING))
 			break;
 		udelay(1);
@@ -78,58 +79,58 @@ void msgdma_reset(struct altera_tse_private *priv)
 			   "TSE Tx mSGDMA resetting bit never cleared!\n");
 
 	/* clear all status bits */
-	iowrite32(MSGDMA_CSR_STAT_MASK, &txcsr->status);
+	csrwr32(MSGDMA_CSR_STAT_MASK, priv->tx_dma_csr, msgdma_csroffs(status));
 }
 
 void msgdma_disable_rxirq(struct altera_tse_private *priv)
 {
-	struct msgdma_csr *csr = priv->rx_dma_csr;
-	tse_clear_bit(&csr->control, MSGDMA_CSR_CTL_GLOBAL_INTR);
+	tse_clear_bit(priv->rx_dma_csr, msgdma_csroffs(control),
+		      MSGDMA_CSR_CTL_GLOBAL_INTR);
 }
 
 void msgdma_enable_rxirq(struct altera_tse_private *priv)
 {
-	struct msgdma_csr *csr = priv->rx_dma_csr;
-	tse_set_bit(&csr->control, MSGDMA_CSR_CTL_GLOBAL_INTR);
+	tse_set_bit(priv->rx_dma_csr, msgdma_csroffs(control),
+		    MSGDMA_CSR_CTL_GLOBAL_INTR);
 }
 
 void msgdma_disable_txirq(struct altera_tse_private *priv)
 {
-	struct msgdma_csr *csr = priv->tx_dma_csr;
-	tse_clear_bit(&csr->control, MSGDMA_CSR_CTL_GLOBAL_INTR);
+	tse_clear_bit(priv->tx_dma_csr, msgdma_csroffs(control),
+		      MSGDMA_CSR_CTL_GLOBAL_INTR);
 }
 
 void msgdma_enable_txirq(struct altera_tse_private *priv)
 {
-	struct msgdma_csr *csr = priv->tx_dma_csr;
-	tse_set_bit(&csr->control, MSGDMA_CSR_CTL_GLOBAL_INTR);
+	tse_set_bit(priv->tx_dma_csr, msgdma_csroffs(control),
+		    MSGDMA_CSR_CTL_GLOBAL_INTR);
 }
 
 void msgdma_clear_rxirq(struct altera_tse_private *priv)
 {
-	struct msgdma_csr *csr = priv->rx_dma_csr;
-	iowrite32(MSGDMA_CSR_STAT_IRQ, &csr->status);
+	csrwr32(MSGDMA_CSR_STAT_IRQ, priv->rx_dma_csr, msgdma_csroffs(status));
 }
 
 void msgdma_clear_txirq(struct altera_tse_private *priv)
 {
-	struct msgdma_csr *csr = priv->tx_dma_csr;
-	iowrite32(MSGDMA_CSR_STAT_IRQ, &csr->status);
+	csrwr32(MSGDMA_CSR_STAT_IRQ, priv->tx_dma_csr, msgdma_csroffs(status));
 }
 
 /* return 0 to indicate transmit is pending */
 int msgdma_tx_buffer(struct altera_tse_private *priv, struct tse_buffer *buffer)
 {
-	struct msgdma_extended_desc *desc = priv->tx_dma_desc;
-
-	iowrite32(lower_32_bits(buffer->dma_addr), &desc->read_addr_lo);
-	iowrite32(upper_32_bits(buffer->dma_addr), &desc->read_addr_hi);
-	iowrite32(0, &desc->write_addr_lo);
-	iowrite32(0, &desc->write_addr_hi);
-	iowrite32(buffer->len, &desc->len);
-	iowrite32(0, &desc->burst_seq_num);
-	iowrite32(MSGDMA_DESC_TX_STRIDE, &desc->stride);
-	iowrite32(MSGDMA_DESC_CTL_TX_SINGLE, &desc->control);
+	csrwr32(lower_32_bits(buffer->dma_addr), priv->tx_dma_desc,
+		msgdma_descroffs(read_addr_lo));
+	csrwr32(upper_32_bits(buffer->dma_addr), priv->tx_dma_desc,
+		msgdma_descroffs(read_addr_hi));
+	csrwr32(0, priv->tx_dma_desc, msgdma_descroffs(write_addr_lo));
+	csrwr32(0, priv->tx_dma_desc, msgdma_descroffs(write_addr_hi));
+	csrwr32(buffer->len, priv->tx_dma_desc, msgdma_descroffs(len));
+	csrwr32(0, priv->tx_dma_desc, msgdma_descroffs(burst_seq_num));
+	csrwr32(MSGDMA_DESC_TX_STRIDE, priv->tx_dma_desc,
+		msgdma_descroffs(stride));
+	csrwr32(MSGDMA_DESC_CTL_TX_SINGLE, priv->tx_dma_desc,
+		msgdma_descroffs(control));
 	return 0;
 }
 
@@ -138,17 +139,16 @@ u32 msgdma_tx_completions(struct altera_tse_private *priv)
 	u32 ready = 0;
 	u32 inuse;
 	u32 status;
-	struct msgdma_csr *txcsr =
-		(struct msgdma_csr *)priv->tx_dma_csr;
 
 	/* Get number of sent descriptors */
-	inuse = ioread32(&txcsr->rw_fill_level) & 0xffff;
+	inuse = csrrd32(priv->tx_dma_csr, msgdma_csroffs(rw_fill_level))
+			& 0xffff;
 
 	if (inuse) { /* Tx FIFO is not empty */
 		ready = priv->tx_prod - priv->tx_cons - inuse - 1;
 	} else {
 		/* Check for buffered last packet */
-		status = ioread32(&txcsr->status);
+		status = csrrd32(priv->tx_dma_csr, msgdma_csroffs(status));
 		if (status & MSGDMA_CSR_STAT_BUSY)
 			ready = priv->tx_prod - priv->tx_cons - 1;
 		else
@@ -162,7 +162,6 @@ u32 msgdma_tx_completions(struct altera_tse_private *priv)
 void msgdma_add_rx_desc(struct altera_tse_private *priv,
 			struct tse_buffer *rxbuffer)
 {
-	struct msgdma_extended_desc *desc = priv->rx_dma_desc;
 	u32 len = priv->rx_dma_buf_sz;
 	dma_addr_t dma_addr = rxbuffer->dma_addr;
 	u32 control = (MSGDMA_DESC_CTL_END_ON_EOP
@@ -172,14 +171,16 @@ void msgdma_add_rx_desc(struct altera_tse_private *priv,
 			| MSGDMA_DESC_CTL_TR_ERR_IRQ
 			| MSGDMA_DESC_CTL_GO);
 
-	iowrite32(0, &desc->read_addr_lo);
-	iowrite32(0, &desc->read_addr_hi);
-	iowrite32(lower_32_bits(dma_addr), &desc->write_addr_lo);
-	iowrite32(upper_32_bits(dma_addr), &desc->write_addr_hi);
-	iowrite32(len, &desc->len);
-	iowrite32(0, &desc->burst_seq_num);
-	iowrite32(0x00010001, &desc->stride);
-	iowrite32(control, &desc->control);
+	csrwr32(0, priv->rx_dma_desc, msgdma_descroffs(read_addr_lo));
+	csrwr32(0, priv->rx_dma_desc, msgdma_descroffs(read_addr_hi));
+	csrwr32(lower_32_bits(dma_addr), priv->rx_dma_desc,
+		msgdma_descroffs(write_addr_lo));
+	csrwr32(upper_32_bits(dma_addr), priv->rx_dma_desc,
+		msgdma_descroffs(write_addr_hi));
+	csrwr32(len, priv->rx_dma_desc, msgdma_descroffs(len));
+	csrwr32(0, priv->rx_dma_desc, msgdma_descroffs(burst_seq_num));
+	csrwr32(0x00010001, priv->rx_dma_desc, msgdma_descroffs(stride));
+	csrwr32(control, priv->rx_dma_desc, msgdma_descroffs(control));
 }
 
 /* status is returned on upper 16 bits,
@@ -190,14 +191,13 @@ u32 msgdma_rx_status(struct altera_tse_private *priv)
 	u32 rxstatus = 0;
 	u32 pktlength;
 	u32 pktstatus;
-	struct msgdma_csr *rxcsr =
-		(struct msgdma_csr *)priv->rx_dma_csr;
-	struct msgdma_response *rxresp =
-		(struct msgdma_response *)priv->rx_dma_resp;
-
-	if (ioread32(&rxcsr->resp_fill_level) & 0xffff) {
-		pktlength = ioread32(&rxresp->bytes_transferred);
-		pktstatus = ioread32(&rxresp->status);
+
+	if (csrrd32(priv->rx_dma_csr, msgdma_csroffs(resp_fill_level))
+	    & 0xffff) {
+		pktlength = csrrd32(priv->rx_dma_resp,
+				    msgdma_respoffs(bytes_transferred));
+		pktstatus = csrrd32(priv->rx_dma_resp,
+				    msgdma_respoffs(status));
 		rxstatus = pktstatus;
 		rxstatus = rxstatus << 16;
 		rxstatus |= (pktlength & 0xffff);
diff --git a/drivers/net/ethernet/altera/altera_msgdmahw.h b/drivers/net/ethernet/altera/altera_msgdmahw.h
index d7b59ba4019c..e335626e1b6b 100644
--- a/drivers/net/ethernet/altera/altera_msgdmahw.h
+++ b/drivers/net/ethernet/altera/altera_msgdmahw.h
@@ -17,15 +17,6 @@
 #ifndef __ALTERA_MSGDMAHW_H__
 #define __ALTERA_MSGDMAHW_H__
 
-/* mSGDMA standard descriptor format
- */
-struct msgdma_desc {
-	u32 read_addr;	/* data buffer source address */
-	u32 write_addr;	/* data buffer destination address */
-	u32 len;	/* the number of bytes to transfer per descriptor */
-	u32 control;	/* characteristics of the transfer */
-};
-
 /* mSGDMA extended descriptor format
  */
 struct msgdma_extended_desc {
@@ -159,6 +150,10 @@ struct msgdma_response {
 	u32 status;
 };
 
+#define msgdma_respoffs(a) (offsetof(struct msgdma_response, a))
+#define msgdma_csroffs(a) (offsetof(struct msgdma_csr, a))
+#define msgdma_descroffs(a) (offsetof(struct msgdma_extended_desc, a))
+
 /* mSGDMA response register bit definitions
  */
 #define MSGDMA_RESP_EARLY_TERM	BIT(8)
diff --git a/drivers/net/ethernet/altera/altera_sgdma.c b/drivers/net/ethernet/altera/altera_sgdma.c
index 9ce8630692b6..99cc56f451cf 100644
--- a/drivers/net/ethernet/altera/altera_sgdma.c
+++ b/drivers/net/ethernet/altera/altera_sgdma.c
@@ -20,8 +20,8 @@
 #include "altera_sgdmahw.h"
 #include "altera_sgdma.h"
 
-static void sgdma_setup_descrip(struct sgdma_descrip *desc,
-				struct sgdma_descrip *ndesc,
+static void sgdma_setup_descrip(struct sgdma_descrip __iomem *desc,
+				struct sgdma_descrip __iomem *ndesc,
 				dma_addr_t ndesc_phys,
 				dma_addr_t raddr,
 				dma_addr_t waddr,
@@ -31,17 +31,17 @@ static void sgdma_setup_descrip(struct sgdma_descrip *desc,
 				int wfixed);
 
 static int sgdma_async_write(struct altera_tse_private *priv,
-			      struct sgdma_descrip *desc);
+			      struct sgdma_descrip __iomem *desc);
 
 static int sgdma_async_read(struct altera_tse_private *priv);
 
 static dma_addr_t
 sgdma_txphysaddr(struct altera_tse_private *priv,
-		 struct sgdma_descrip *desc);
+		 struct sgdma_descrip __iomem *desc);
 
 static dma_addr_t
 sgdma_rxphysaddr(struct altera_tse_private *priv,
-		 struct sgdma_descrip *desc);
+		 struct sgdma_descrip __iomem *desc);
 
 static int sgdma_txbusy(struct altera_tse_private *priv);
 
@@ -79,7 +79,8 @@ int sgdma_initialize(struct altera_tse_private *priv)
 	priv->rxdescphys = (dma_addr_t) 0;
 	priv->txdescphys = (dma_addr_t) 0;
 
-	priv->rxdescphys = dma_map_single(priv->device, priv->rx_dma_desc,
+	priv->rxdescphys = dma_map_single(priv->device,
+					  (void __force *)priv->rx_dma_desc,
 					  priv->rxdescmem, DMA_BIDIRECTIONAL);
 
 	if (dma_mapping_error(priv->device, priv->rxdescphys)) {
@@ -88,7 +89,8 @@ int sgdma_initialize(struct altera_tse_private *priv)
 		return -EINVAL;
 	}
 
-	priv->txdescphys = dma_map_single(priv->device, priv->tx_dma_desc,
+	priv->txdescphys = dma_map_single(priv->device,
+					  (void __force *)priv->tx_dma_desc,
 					  priv->txdescmem, DMA_TO_DEVICE);
 
 	if (dma_mapping_error(priv->device, priv->txdescphys)) {
@@ -98,8 +100,8 @@ int sgdma_initialize(struct altera_tse_private *priv)
 	}
 
 	/* Initialize descriptor memory to all 0's, sync memory to cache */
-	memset(priv->tx_dma_desc, 0, priv->txdescmem);
-	memset(priv->rx_dma_desc, 0, priv->rxdescmem);
+	memset_io(priv->tx_dma_desc, 0, priv->txdescmem);
+	memset_io(priv->rx_dma_desc, 0, priv->rxdescmem);
 
 	dma_sync_single_for_device(priv->device, priv->txdescphys,
 				   priv->txdescmem, DMA_TO_DEVICE);
@@ -126,22 +128,15 @@ void sgdma_uninitialize(struct altera_tse_private *priv)
  */
 void sgdma_reset(struct altera_tse_private *priv)
 {
-	u32 *ptxdescripmem = (u32 *)priv->tx_dma_desc;
-	u32 txdescriplen   = priv->txdescmem;
-	u32 *prxdescripmem = (u32 *)priv->rx_dma_desc;
-	u32 rxdescriplen   = priv->rxdescmem;
-	struct sgdma_csr *ptxsgdma = (struct sgdma_csr *)priv->tx_dma_csr;
-	struct sgdma_csr *prxsgdma = (struct sgdma_csr *)priv->rx_dma_csr;
-
 	/* Initialize descriptor memory to 0 */
-	memset(ptxdescripmem, 0, txdescriplen);
-	memset(prxdescripmem, 0, rxdescriplen);
+	memset_io(priv->tx_dma_desc, 0, priv->txdescmem);
+	memset_io(priv->rx_dma_desc, 0, priv->rxdescmem);
 
-	iowrite32(SGDMA_CTRLREG_RESET, &ptxsgdma->control);
-	iowrite32(0, &ptxsgdma->control);
+	csrwr32(SGDMA_CTRLREG_RESET, priv->tx_dma_csr, sgdma_csroffs(control));
+	csrwr32(0, priv->tx_dma_csr, sgdma_csroffs(control));
 
-	iowrite32(SGDMA_CTRLREG_RESET, &prxsgdma->control);
-	iowrite32(0, &prxsgdma->control);
+	csrwr32(SGDMA_CTRLREG_RESET, priv->rx_dma_csr, sgdma_csroffs(control));
+	csrwr32(0, priv->rx_dma_csr, sgdma_csroffs(control));
 }
 
 /* For SGDMA, interrupts remain enabled after initially enabling,
@@ -167,14 +162,14 @@ void sgdma_disable_txirq(struct altera_tse_private *priv)
 
 void sgdma_clear_rxirq(struct altera_tse_private *priv)
 {
-	struct sgdma_csr *csr = (struct sgdma_csr *)priv->rx_dma_csr;
-	tse_set_bit(&csr->control, SGDMA_CTRLREG_CLRINT);
+	tse_set_bit(priv->rx_dma_csr, sgdma_csroffs(control),
+		    SGDMA_CTRLREG_CLRINT);
 }
 
 void sgdma_clear_txirq(struct altera_tse_private *priv)
 {
-	struct sgdma_csr *csr = (struct sgdma_csr *)priv->tx_dma_csr;
-	tse_set_bit(&csr->control, SGDMA_CTRLREG_CLRINT);
+	tse_set_bit(priv->tx_dma_csr, sgdma_csroffs(control),
+		    SGDMA_CTRLREG_CLRINT);
 }
 
 /* transmits buffer through SGDMA. Returns number of buffers
@@ -184,12 +179,11 @@ void sgdma_clear_txirq(struct altera_tse_private *priv)
  */
 int sgdma_tx_buffer(struct altera_tse_private *priv, struct tse_buffer *buffer)
 {
-	int pktstx = 0;
-	struct sgdma_descrip *descbase =
-		(struct sgdma_descrip *)priv->tx_dma_desc;
+	struct sgdma_descrip __iomem *descbase =
+		(struct sgdma_descrip __iomem *)priv->tx_dma_desc;
 
-	struct sgdma_descrip *cdesc = &descbase[0];
-	struct sgdma_descrip *ndesc = &descbase[1];
+	struct sgdma_descrip __iomem *cdesc = &descbase[0];
+	struct sgdma_descrip __iomem *ndesc = &descbase[1];
 
 	/* wait 'til the tx sgdma is ready for the next transmit request */
 	if (sgdma_txbusy(priv))
@@ -205,7 +199,7 @@ int sgdma_tx_buffer(struct altera_tse_private *priv, struct tse_buffer *buffer)
 			    0,				/* read fixed */
 			    SGDMA_CONTROL_WR_FIXED);	/* Generate SOP */
 
-	pktstx = sgdma_async_write(priv, cdesc);
+	sgdma_async_write(priv, cdesc);
 
 	/* enqueue the request to the pending transmit queue */
 	queue_tx(priv, buffer);
@@ -219,10 +213,10 @@ int sgdma_tx_buffer(struct altera_tse_private *priv, struct tse_buffer *buffer)
 u32 sgdma_tx_completions(struct altera_tse_private *priv)
 {
 	u32 ready = 0;
-	struct sgdma_descrip *desc = (struct sgdma_descrip *)priv->tx_dma_desc;
 
 	if (!sgdma_txbusy(priv) &&
-	    ((desc->control & SGDMA_CONTROL_HW_OWNED) == 0) &&
+	    ((csrrd8(priv->tx_dma_desc, sgdma_descroffs(control))
+	     & SGDMA_CONTROL_HW_OWNED) == 0) &&
 	    (dequeue_tx(priv))) {
 		ready = 1;
 	}
@@ -246,32 +240,31 @@ void sgdma_add_rx_desc(struct altera_tse_private *priv,
  */
 u32 sgdma_rx_status(struct altera_tse_private *priv)
 {
-	struct sgdma_csr *csr = (struct sgdma_csr *)priv->rx_dma_csr;
-	struct sgdma_descrip *base = (struct sgdma_descrip *)priv->rx_dma_desc;
-	struct sgdma_descrip *desc = NULL;
-	int pktsrx;
-	unsigned int rxstatus = 0;
-	unsigned int pktlength = 0;
-	unsigned int pktstatus = 0;
+	struct sgdma_descrip __iomem *base =
+		(struct sgdma_descrip __iomem *)priv->rx_dma_desc;
+	struct sgdma_descrip __iomem *desc = NULL;
 	struct tse_buffer *rxbuffer = NULL;
+	unsigned int rxstatus = 0;
 
-	u32 sts = ioread32(&csr->status);
+	u32 sts = csrrd32(priv->rx_dma_csr, sgdma_csroffs(status));
 
 	desc = &base[0];
 	if (sts & SGDMA_STSREG_EOP) {
+		unsigned int pktlength = 0;
+		unsigned int pktstatus = 0;
 		dma_sync_single_for_cpu(priv->device,
 					priv->rxdescphys,
 					priv->sgdmadesclen,
 					DMA_FROM_DEVICE);
 
-		pktlength = desc->bytes_xferred;
-		pktstatus = desc->status & 0x3f;
-		rxstatus = pktstatus;
+		pktlength = csrrd16(desc, sgdma_descroffs(bytes_xferred));
+		pktstatus = csrrd8(desc, sgdma_descroffs(status));
+		rxstatus = pktstatus & ~SGDMA_STATUS_EOP;
 		rxstatus = rxstatus << 16;
 		rxstatus |= (pktlength & 0xffff);
 
 		if (rxstatus) {
-			desc->status = 0;
+			csrwr8(0, desc, sgdma_descroffs(status));
 
 			rxbuffer = dequeue_rx(priv);
 			if (rxbuffer == NULL)
@@ -279,12 +272,12 @@ u32 sgdma_rx_status(struct altera_tse_private *priv)
 					    "sgdma rx and rx queue empty!\n");
 
 			/* Clear control */
-			iowrite32(0, &csr->control);
+			csrwr32(0, priv->rx_dma_csr, sgdma_csroffs(control));
 			/* clear status */
-			iowrite32(0xf, &csr->status);
+			csrwr32(0xf, priv->rx_dma_csr, sgdma_csroffs(status));
 
 			/* kick the rx sgdma after reaping this descriptor */
-			pktsrx = sgdma_async_read(priv);
+			sgdma_async_read(priv);
 
 		} else {
 			/* If the SGDMA indicated an end of packet on recv,
@@ -298,10 +291,11 @@ u32 sgdma_rx_status(struct altera_tse_private *priv)
 			 */
 			netdev_err(priv->dev,
 				   "SGDMA RX Error Info: %x, %x, %x\n",
-				   sts, desc->status, rxstatus);
+				   sts, csrrd8(desc, sgdma_descroffs(status)),
+				   rxstatus);
 		}
 	} else if (sts == 0) {
-		pktsrx = sgdma_async_read(priv);
+		sgdma_async_read(priv);
 	}
 
 	return rxstatus;
@@ -309,8 +303,8 @@ u32 sgdma_rx_status(struct altera_tse_private *priv)
 
 
 /* Private functions */
-static void sgdma_setup_descrip(struct sgdma_descrip *desc,
-				struct sgdma_descrip *ndesc,
+static void sgdma_setup_descrip(struct sgdma_descrip __iomem *desc,
+				struct sgdma_descrip __iomem *ndesc,
 				dma_addr_t ndesc_phys,
 				dma_addr_t raddr,
 				dma_addr_t waddr,
@@ -320,27 +314,30 @@ static void sgdma_setup_descrip(struct sgdma_descrip *desc,
 				int wfixed)
 {
 	/* Clear the next descriptor as not owned by hardware */
-	u32 ctrl = ndesc->control;
+
+	u32 ctrl = csrrd8(ndesc, sgdma_descroffs(control));
 	ctrl &= ~SGDMA_CONTROL_HW_OWNED;
-	ndesc->control = ctrl;
+	csrwr8(ctrl, ndesc, sgdma_descroffs(control));
 
-	ctrl = 0;
 	ctrl = SGDMA_CONTROL_HW_OWNED;
 	ctrl |= generate_eop;
 	ctrl |= rfixed;
 	ctrl |= wfixed;
 
 	/* Channel is implicitly zero, initialized to 0 by default */
-
-	desc->raddr = raddr;
-	desc->waddr = waddr;
-	desc->next = lower_32_bits(ndesc_phys);
-	desc->control = ctrl;
-	desc->status = 0;
-	desc->rburst = 0;
-	desc->wburst = 0;
-	desc->bytes = length;
-	desc->bytes_xferred = 0;
+	csrwr32(lower_32_bits(raddr), desc, sgdma_descroffs(raddr));
+	csrwr32(lower_32_bits(waddr), desc, sgdma_descroffs(waddr));
+
+	csrwr32(0, desc, sgdma_descroffs(pad1));
+	csrwr32(0, desc, sgdma_descroffs(pad2));
+	csrwr32(lower_32_bits(ndesc_phys), desc, sgdma_descroffs(next));
+
+	csrwr8(ctrl, desc, sgdma_descroffs(control));
+	csrwr8(0, desc, sgdma_descroffs(status));
+	csrwr8(0, desc, sgdma_descroffs(wburst));
+	csrwr8(0, desc, sgdma_descroffs(rburst));
+	csrwr16(length, desc, sgdma_descroffs(bytes));
+	csrwr16(0, desc, sgdma_descroffs(bytes_xferred));
 }
 
 /* If hardware is busy, don't restart async read.
@@ -351,12 +348,11 @@ static void sgdma_setup_descrip(struct sgdma_descrip *desc,
  */
 static int sgdma_async_read(struct altera_tse_private *priv)
 {
-	struct sgdma_csr *csr = (struct sgdma_csr *)priv->rx_dma_csr;
-	struct sgdma_descrip *descbase =
-		(struct sgdma_descrip *)priv->rx_dma_desc;
+	struct sgdma_descrip __iomem *descbase =
+		(struct sgdma_descrip __iomem *)priv->rx_dma_desc;
 
-	struct sgdma_descrip *cdesc = &descbase[0];
-	struct sgdma_descrip *ndesc = &descbase[1];
+	struct sgdma_descrip __iomem *cdesc = &descbase[0];
+	struct sgdma_descrip __iomem *ndesc = &descbase[1];
 
 	struct tse_buffer *rxbuffer = NULL;
 
@@ -382,11 +378,13 @@ static int sgdma_async_read(struct altera_tse_private *priv)
 					   priv->sgdmadesclen,
 					   DMA_TO_DEVICE);
 
-		iowrite32(lower_32_bits(sgdma_rxphysaddr(priv, cdesc)),
-			  &csr->next_descrip);
+		csrwr32(lower_32_bits(sgdma_rxphysaddr(priv, cdesc)),
+			priv->rx_dma_csr,
+			sgdma_csroffs(next_descrip));
 
-		iowrite32((priv->rxctrlreg | SGDMA_CTRLREG_START),
-			  &csr->control);
+		csrwr32((priv->rxctrlreg | SGDMA_CTRLREG_START),
+			priv->rx_dma_csr,
+			sgdma_csroffs(control));
 
 		return 1;
 	}
@@ -395,32 +393,32 @@ static int sgdma_async_read(struct altera_tse_private *priv)
 }
 
 static int sgdma_async_write(struct altera_tse_private *priv,
-			     struct sgdma_descrip *desc)
+			     struct sgdma_descrip __iomem *desc)
 {
-	struct sgdma_csr *csr = (struct sgdma_csr *)priv->tx_dma_csr;
-
 	if (sgdma_txbusy(priv))
 		return 0;
 
 	/* clear control and status */
-	iowrite32(0, &csr->control);
-	iowrite32(0x1f, &csr->status);
+	csrwr32(0, priv->tx_dma_csr, sgdma_csroffs(control));
+	csrwr32(0x1f, priv->tx_dma_csr, sgdma_csroffs(status));
 
 	dma_sync_single_for_device(priv->device, priv->txdescphys,
 				   priv->sgdmadesclen, DMA_TO_DEVICE);
 
-	iowrite32(lower_32_bits(sgdma_txphysaddr(priv, desc)),
-		  &csr->next_descrip);
+	csrwr32(lower_32_bits(sgdma_txphysaddr(priv, desc)),
+		priv->tx_dma_csr,
+		sgdma_csroffs(next_descrip));
 
-	iowrite32((priv->txctrlreg | SGDMA_CTRLREG_START),
-		  &csr->control);
+	csrwr32((priv->txctrlreg | SGDMA_CTRLREG_START),
+		priv->tx_dma_csr,
+		sgdma_csroffs(control));
 
 	return 1;
 }
 
 static dma_addr_t
 sgdma_txphysaddr(struct altera_tse_private *priv,
-		 struct sgdma_descrip *desc)
+		 struct sgdma_descrip __iomem *desc)
 {
 	dma_addr_t paddr = priv->txdescmem_busaddr;
 	uintptr_t offs = (uintptr_t)desc - (uintptr_t)priv->tx_dma_desc;
@@ -429,7 +427,7 @@ sgdma_txphysaddr(struct altera_tse_private *priv,
 
 static dma_addr_t
 sgdma_rxphysaddr(struct altera_tse_private *priv,
-		 struct sgdma_descrip *desc)
+		 struct sgdma_descrip __iomem *desc)
 {
 	dma_addr_t paddr = priv->rxdescmem_busaddr;
 	uintptr_t offs = (uintptr_t)desc - (uintptr_t)priv->rx_dma_desc;
@@ -518,8 +516,8 @@ queue_rx_peekhead(struct altera_tse_private *priv)
  */
 static int sgdma_rxbusy(struct altera_tse_private *priv)
 {
-	struct sgdma_csr *csr = (struct sgdma_csr *)priv->rx_dma_csr;
-	return ioread32(&csr->status) & SGDMA_STSREG_BUSY;
+	return csrrd32(priv->rx_dma_csr, sgdma_csroffs(status))
+		       & SGDMA_STSREG_BUSY;
 }
 
 /* waits for the tx sgdma to finish it's current operation, returns 0
@@ -528,13 +526,14 @@ static int sgdma_rxbusy(struct altera_tse_private *priv)
 static int sgdma_txbusy(struct altera_tse_private *priv)
 {
 	int delay = 0;
-	struct sgdma_csr *csr = (struct sgdma_csr *)priv->tx_dma_csr;
 
 	/* if DMA is busy, wait for current transactino to finish */
-	while ((ioread32(&csr->status) & SGDMA_STSREG_BUSY) && (delay++ < 100))
+	while ((csrrd32(priv->tx_dma_csr, sgdma_csroffs(status))
+		& SGDMA_STSREG_BUSY) && (delay++ < 100))
 		udelay(1);
 
-	if (ioread32(&csr->status) & SGDMA_STSREG_BUSY) {
+	if (csrrd32(priv->tx_dma_csr, sgdma_csroffs(status))
+	    & SGDMA_STSREG_BUSY) {
 		netdev_err(priv->dev, "timeout waiting for tx dma\n");
 		return 1;
 	}
diff --git a/drivers/net/ethernet/altera/altera_sgdmahw.h b/drivers/net/ethernet/altera/altera_sgdmahw.h
index ba3334f35383..85bc33b218d9 100644
--- a/drivers/net/ethernet/altera/altera_sgdmahw.h
+++ b/drivers/net/ethernet/altera/altera_sgdmahw.h
@@ -19,16 +19,16 @@
 
 /* SGDMA descriptor structure */
 struct sgdma_descrip {
-	unsigned int	raddr; /* address of data to be read */
-	unsigned int	pad1;
-	unsigned int	waddr;
-	unsigned int    pad2;
-	unsigned int	next;
-	unsigned int	pad3;
-	unsigned short  bytes;
-	unsigned char   rburst;
-	unsigned char	wburst;
-	unsigned short	bytes_xferred;	/* 16 bits, bytes xferred */
+	u32	raddr; /* address of data to be read */
+	u32	pad1;
+	u32	waddr;
+	u32	pad2;
+	u32	next;
+	u32	pad3;
+	u16	bytes;
+	u8	rburst;
+	u8	wburst;
+	u16	bytes_xferred;	/* 16 bits, bytes xferred */
 
 	/* bit 0: error
 	 * bit 1: length error
@@ -39,7 +39,7 @@ struct sgdma_descrip {
 	 * bit 6: reserved
 	 * bit 7: status eop for recv case
 	 */
-	unsigned char	status;
+	u8	status;
 
 	/* bit 0: eop
 	 * bit 1: read_fixed
@@ -47,7 +47,7 @@ struct sgdma_descrip {
 	 * bits 3,4,5,6: Channel (always 0)
 	 * bit 7: hardware owned
 	 */
-	unsigned char	control;
+	u8	control;
 } __packed;
 
 
@@ -101,6 +101,8 @@ struct sgdma_csr {
 	u32	pad3[3];
 };
 
+#define sgdma_csroffs(a) (offsetof(struct sgdma_csr, a))
+#define sgdma_descroffs(a) (offsetof(struct sgdma_descrip, a))
 
 #define SGDMA_STSREG_ERR	BIT(0) /* Error */
 #define SGDMA_STSREG_EOP	BIT(1) /* EOP */
diff --git a/drivers/net/ethernet/altera/altera_tse.h b/drivers/net/ethernet/altera/altera_tse.h
index 465c4aabebbd..2adb24d4523c 100644
--- a/drivers/net/ethernet/altera/altera_tse.h
+++ b/drivers/net/ethernet/altera/altera_tse.h
@@ -357,6 +357,8 @@ struct altera_tse_mac {
 	u32 reserved5[42];
 };
 
+#define tse_csroffs(a) (offsetof(struct altera_tse_mac, a))
+
 /* Transmit and Receive Command Registers Bit Definitions
  */
 #define ALTERA_TSE_TX_CMD_STAT_OMIT_CRC		BIT(17)
@@ -487,4 +489,49 @@ struct altera_tse_private {
  */
 void altera_tse_set_ethtool_ops(struct net_device *);
 
+static inline
+u32 csrrd32(void __iomem *mac, size_t offs)
+{
+	void __iomem *paddr = (void __iomem *)((uintptr_t)mac + offs);
+	return readl(paddr);
+}
+
+static inline
+u16 csrrd16(void __iomem *mac, size_t offs)
+{
+	void __iomem *paddr = (void __iomem *)((uintptr_t)mac + offs);
+	return readw(paddr);
+}
+
+static inline
+u8 csrrd8(void __iomem *mac, size_t offs)
+{
+	void __iomem *paddr = (void __iomem *)((uintptr_t)mac + offs);
+	return readb(paddr);
+}
+
+static inline
+void csrwr32(u32 val, void __iomem *mac, size_t offs)
+{
+	void __iomem *paddr = (void __iomem *)((uintptr_t)mac + offs);
+
+	writel(val, paddr);
+}
+
+static inline
+void csrwr16(u16 val, void __iomem *mac, size_t offs)
+{
+	void __iomem *paddr = (void __iomem *)((uintptr_t)mac + offs);
+
+	writew(val, paddr);
+}
+
+static inline
+void csrwr8(u8 val, void __iomem *mac, size_t offs)
+{
+	void __iomem *paddr = (void __iomem *)((uintptr_t)mac + offs);
+
+	writeb(val, paddr);
+}
+
 #endif /* __ALTERA_TSE_H__ */
diff --git a/drivers/net/ethernet/altera/altera_tse_ethtool.c b/drivers/net/ethernet/altera/altera_tse_ethtool.c
index 76133caffa78..54c25eff7952 100644
--- a/drivers/net/ethernet/altera/altera_tse_ethtool.c
+++ b/drivers/net/ethernet/altera/altera_tse_ethtool.c
@@ -96,54 +96,89 @@ static void tse_fill_stats(struct net_device *dev, struct ethtool_stats *dummy,
 			   u64 *buf)
 {
 	struct altera_tse_private *priv = netdev_priv(dev);
-	struct altera_tse_mac *mac = priv->mac_dev;
 	u64 ext;
 
-	buf[0] = ioread32(&mac->frames_transmitted_ok);
-	buf[1] = ioread32(&mac->frames_received_ok);
-	buf[2] = ioread32(&mac->frames_check_sequence_errors);
-	buf[3] = ioread32(&mac->alignment_errors);
+	buf[0] = csrrd32(priv->mac_dev,
+			 tse_csroffs(frames_transmitted_ok));
+	buf[1] = csrrd32(priv->mac_dev,
+			 tse_csroffs(frames_received_ok));
+	buf[2] = csrrd32(priv->mac_dev,
+			 tse_csroffs(frames_check_sequence_errors));
+	buf[3] = csrrd32(priv->mac_dev,
+			 tse_csroffs(alignment_errors));
 
 	/* Extended aOctetsTransmittedOK counter */
-	ext = (u64) ioread32(&mac->msb_octets_transmitted_ok) << 32;
-	ext |= ioread32(&mac->octets_transmitted_ok);
+	ext = (u64) csrrd32(priv->mac_dev,
+			    tse_csroffs(msb_octets_transmitted_ok)) << 32;
+
+	ext |= csrrd32(priv->mac_dev,
+		       tse_csroffs(octets_transmitted_ok));
 	buf[4] = ext;
 
 	/* Extended aOctetsReceivedOK counter */
-	ext = (u64) ioread32(&mac->msb_octets_received_ok) << 32;
-	ext |= ioread32(&mac->octets_received_ok);
+	ext = (u64) csrrd32(priv->mac_dev,
+			    tse_csroffs(msb_octets_received_ok)) << 32;
+
+	ext |= csrrd32(priv->mac_dev,
+		       tse_csroffs(octets_received_ok));
 	buf[5] = ext;
 
-	buf[6] = ioread32(&mac->tx_pause_mac_ctrl_frames);
-	buf[7] = ioread32(&mac->rx_pause_mac_ctrl_frames);
-	buf[8] = ioread32(&mac->if_in_errors);
-	buf[9] = ioread32(&mac->if_out_errors);
-	buf[10] = ioread32(&mac->if_in_ucast_pkts);
-	buf[11] = ioread32(&mac->if_in_multicast_pkts);
-	buf[12] = ioread32(&mac->if_in_broadcast_pkts);
-	buf[13] = ioread32(&mac->if_out_discards);
-	buf[14] = ioread32(&mac->if_out_ucast_pkts);
-	buf[15] = ioread32(&mac->if_out_multicast_pkts);
-	buf[16] = ioread32(&mac->if_out_broadcast_pkts);
-	buf[17] = ioread32(&mac->ether_stats_drop_events);
+	buf[6] = csrrd32(priv->mac_dev,
+			 tse_csroffs(tx_pause_mac_ctrl_frames));
+	buf[7] = csrrd32(priv->mac_dev,
+			 tse_csroffs(rx_pause_mac_ctrl_frames));
+	buf[8] = csrrd32(priv->mac_dev,
+			 tse_csroffs(if_in_errors));
+	buf[9] = csrrd32(priv->mac_dev,
+			 tse_csroffs(if_out_errors));
+	buf[10] = csrrd32(priv->mac_dev,
+			  tse_csroffs(if_in_ucast_pkts));
+	buf[11] = csrrd32(priv->mac_dev,
+			  tse_csroffs(if_in_multicast_pkts));
+	buf[12] = csrrd32(priv->mac_dev,
+			  tse_csroffs(if_in_broadcast_pkts));
+	buf[13] = csrrd32(priv->mac_dev,
+			  tse_csroffs(if_out_discards));
+	buf[14] = csrrd32(priv->mac_dev,
+			  tse_csroffs(if_out_ucast_pkts));
+	buf[15] = csrrd32(priv->mac_dev,
+			  tse_csroffs(if_out_multicast_pkts));
+	buf[16] = csrrd32(priv->mac_dev,
+			  tse_csroffs(if_out_broadcast_pkts));
+	buf[17] = csrrd32(priv->mac_dev,
+			  tse_csroffs(ether_stats_drop_events));
 
 	/* Extended etherStatsOctets counter */
-	ext = (u64) ioread32(&mac->msb_ether_stats_octets) << 32;
-	ext |= ioread32(&mac->ether_stats_octets);
+	ext = (u64) csrrd32(priv->mac_dev,
+			    tse_csroffs(msb_ether_stats_octets)) << 32;
+	ext |= csrrd32(priv->mac_dev,
+		       tse_csroffs(ether_stats_octets));
 	buf[18] = ext;
 
-	buf[19] = ioread32(&mac->ether_stats_pkts);
-	buf[20] = ioread32(&mac->ether_stats_undersize_pkts);
-	buf[21] = ioread32(&mac->ether_stats_oversize_pkts);
-	buf[22] = ioread32(&mac->ether_stats_pkts_64_octets);
-	buf[23] = ioread32(&mac->ether_stats_pkts_65to127_octets);
-	buf[24] = ioread32(&mac->ether_stats_pkts_128to255_octets);
-	buf[25] = ioread32(&mac->ether_stats_pkts_256to511_octets);
-	buf[26] = ioread32(&mac->ether_stats_pkts_512to1023_octets);
-	buf[27] = ioread32(&mac->ether_stats_pkts_1024to1518_octets);
-	buf[28] = ioread32(&mac->ether_stats_pkts_1519tox_octets);
-	buf[29] = ioread32(&mac->ether_stats_jabbers);
-	buf[30] = ioread32(&mac->ether_stats_fragments);
+	buf[19] = csrrd32(priv->mac_dev,
+			  tse_csroffs(ether_stats_pkts));
+	buf[20] = csrrd32(priv->mac_dev,
+			  tse_csroffs(ether_stats_undersize_pkts));
+	buf[21] = csrrd32(priv->mac_dev,
+			  tse_csroffs(ether_stats_oversize_pkts));
+	buf[22] = csrrd32(priv->mac_dev,
+			  tse_csroffs(ether_stats_pkts_64_octets));
+	buf[23] = csrrd32(priv->mac_dev,
+			  tse_csroffs(ether_stats_pkts_65to127_octets));
+	buf[24] = csrrd32(priv->mac_dev,
+			  tse_csroffs(ether_stats_pkts_128to255_octets));
+	buf[25] = csrrd32(priv->mac_dev,
+			  tse_csroffs(ether_stats_pkts_256to511_octets));
+	buf[26] = csrrd32(priv->mac_dev,
+			  tse_csroffs(ether_stats_pkts_512to1023_octets));
+	buf[27] = csrrd32(priv->mac_dev,
+			  tse_csroffs(ether_stats_pkts_1024to1518_octets));
+	buf[28] = csrrd32(priv->mac_dev,
+			  tse_csroffs(ether_stats_pkts_1519tox_octets));
+	buf[29] = csrrd32(priv->mac_dev,
+			  tse_csroffs(ether_stats_jabbers));
+	buf[30] = csrrd32(priv->mac_dev,
+			  tse_csroffs(ether_stats_fragments));
 }
 
 static int tse_sset_count(struct net_device *dev, int sset)
@@ -178,7 +213,6 @@ static void tse_get_regs(struct net_device *dev, struct ethtool_regs *regs,
 {
 	int i;
 	struct altera_tse_private *priv = netdev_priv(dev);
-	u32 *tse_mac_regs = (u32 *)priv->mac_dev;
 	u32 *buf = regbuf;
 
 	/* Set version to a known value, so ethtool knows
@@ -196,7 +230,7 @@ static void tse_get_regs(struct net_device *dev, struct ethtool_regs *regs,
 	regs->version = 1;
 
 	for (i = 0; i < TSE_NUM_REGS; i++)
-		buf[i] = ioread32(&tse_mac_regs[i]);
+		buf[i] = csrrd32(priv->mac_dev, i * 4);
 }
 
 static int tse_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c
index e44a4aeb9701..7330681574d2 100644
--- a/drivers/net/ethernet/altera/altera_tse_main.c
+++ b/drivers/net/ethernet/altera/altera_tse_main.c
@@ -100,29 +100,30 @@ static inline u32 tse_tx_avail(struct altera_tse_private *priv)
  */
 static int altera_tse_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 {
-	struct altera_tse_mac *mac = (struct altera_tse_mac *)bus->priv;
-	unsigned int *mdio_regs = (unsigned int *)&mac->mdio_phy0;
-	u32 data;
+	struct net_device *ndev = bus->priv;
+	struct altera_tse_private *priv = netdev_priv(ndev);
 
 	/* set MDIO address */
-	iowrite32((mii_id & 0x1f), &mac->mdio_phy0_addr);
+	csrwr32((mii_id & 0x1f), priv->mac_dev,
+		tse_csroffs(mdio_phy0_addr));
 
 	/* get the data */
-	data = ioread32(&mdio_regs[regnum]) & 0xffff;
-	return data;
+	return csrrd32(priv->mac_dev,
+		       tse_csroffs(mdio_phy0) + regnum * 4) & 0xffff;
 }
 
 static int altera_tse_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 				 u16 value)
 {
-	struct altera_tse_mac *mac = (struct altera_tse_mac *)bus->priv;
-	unsigned int *mdio_regs = (unsigned int *)&mac->mdio_phy0;
+	struct net_device *ndev = bus->priv;
+	struct altera_tse_private *priv = netdev_priv(ndev);
 
 	/* set MDIO address */
-	iowrite32((mii_id & 0x1f), &mac->mdio_phy0_addr);
+	csrwr32((mii_id & 0x1f), priv->mac_dev,
+		tse_csroffs(mdio_phy0_addr));
 
 	/* write the data */
-	iowrite32((u32) value, &mdio_regs[regnum]);
+	csrwr32(value, priv->mac_dev, tse_csroffs(mdio_phy0) + regnum * 4);
 	return 0;
 }
 
@@ -168,7 +169,7 @@ static int altera_tse_mdio_create(struct net_device *dev, unsigned int id)
 	for (i = 0; i < PHY_MAX_ADDR; i++)
 		mdio->irq[i] = PHY_POLL;
 
-	mdio->priv = priv->mac_dev;
+	mdio->priv = dev;
 	mdio->parent = priv->device;
 
 	ret = of_mdiobus_register(mdio, mdio_node);
@@ -563,7 +564,6 @@ static int tse_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	unsigned int nopaged_len = skb_headlen(skb);
 	enum netdev_tx ret = NETDEV_TX_OK;
 	dma_addr_t dma_addr;
-	int txcomplete = 0;
 
 	spin_lock_bh(&priv->tx_lock);
 
@@ -599,7 +599,7 @@ static int tse_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	dma_sync_single_for_device(priv->device, buffer->dma_addr,
 				   buffer->len, DMA_TO_DEVICE);
 
-	txcomplete = priv->dmaops->tx_buffer(priv, buffer);
+	priv->dmaops->tx_buffer(priv, buffer);
 
 	skb_tx_timestamp(skb);
 
@@ -698,7 +698,6 @@ static struct phy_device *connect_local_phy(struct net_device *dev)
 	struct altera_tse_private *priv = netdev_priv(dev);
 	struct phy_device *phydev = NULL;
 	char phy_id_fmt[MII_BUS_ID_SIZE + 3];
-	int ret;
 
 	if (priv->phy_addr != POLL_PHY) {
 		snprintf(phy_id_fmt, MII_BUS_ID_SIZE + 3, PHY_ID_FMT,
@@ -712,6 +711,7 @@ static struct phy_device *connect_local_phy(struct net_device *dev)
 			netdev_err(dev, "Could not attach to PHY\n");
 
 	} else {
+		int ret;
 		phydev = phy_find_first(priv->mdio);
 		if (phydev == NULL) {
 			netdev_err(dev, "No PHY found\n");
@@ -791,7 +791,6 @@ static int init_phy(struct net_device *dev)
 
 static void tse_update_mac_addr(struct altera_tse_private *priv, u8 *addr)
 {
-	struct altera_tse_mac *mac = priv->mac_dev;
 	u32 msb;
 	u32 lsb;
 
@@ -799,8 +798,8 @@ static void tse_update_mac_addr(struct altera_tse_private *priv, u8 *addr)
 	lsb = ((addr[5] << 8) | addr[4]) & 0xffff;
 
 	/* Set primary MAC address */
-	iowrite32(msb, &mac->mac_addr_0);
-	iowrite32(lsb, &mac->mac_addr_1);
+	csrwr32(msb, priv->mac_dev, tse_csroffs(mac_addr_0));
+	csrwr32(lsb, priv->mac_dev, tse_csroffs(mac_addr_1));
 }
 
 /* MAC software reset.
@@ -811,26 +810,26 @@ static void tse_update_mac_addr(struct altera_tse_private *priv, u8 *addr)
  */
 static int reset_mac(struct altera_tse_private *priv)
 {
-	void __iomem *cmd_cfg_reg = &priv->mac_dev->command_config;
 	int counter;
 	u32 dat;
 
-	dat = ioread32(cmd_cfg_reg);
+	dat = csrrd32(priv->mac_dev, tse_csroffs(command_config));
 	dat &= ~(MAC_CMDCFG_TX_ENA | MAC_CMDCFG_RX_ENA);
 	dat |= MAC_CMDCFG_SW_RESET | MAC_CMDCFG_CNT_RESET;
-	iowrite32(dat, cmd_cfg_reg);
+	csrwr32(dat, priv->mac_dev, tse_csroffs(command_config));
 
 	counter = 0;
 	while (counter++ < ALTERA_TSE_SW_RESET_WATCHDOG_CNTR) {
-		if (tse_bit_is_clear(cmd_cfg_reg, MAC_CMDCFG_SW_RESET))
+		if (tse_bit_is_clear(priv->mac_dev, tse_csroffs(command_config),
+				     MAC_CMDCFG_SW_RESET))
 			break;
 		udelay(1);
 	}
 
 	if (counter >= ALTERA_TSE_SW_RESET_WATCHDOG_CNTR) {
-		dat = ioread32(cmd_cfg_reg);
+		dat = csrrd32(priv->mac_dev, tse_csroffs(command_config));
 		dat &= ~MAC_CMDCFG_SW_RESET;
-		iowrite32(dat, cmd_cfg_reg);
+		csrwr32(dat, priv->mac_dev, tse_csroffs(command_config));
 		return -1;
 	}
 	return 0;
@@ -840,41 +839,57 @@ static int reset_mac(struct altera_tse_private *priv)
 */
 static int init_mac(struct altera_tse_private *priv)
 {
-	struct altera_tse_mac *mac = priv->mac_dev;
 	unsigned int cmd = 0;
 	u32 frm_length;
 
 	/* Setup Rx FIFO */
-	iowrite32(priv->rx_fifo_depth - ALTERA_TSE_RX_SECTION_EMPTY,
-		  &mac->rx_section_empty);
-	iowrite32(ALTERA_TSE_RX_SECTION_FULL, &mac->rx_section_full);
-	iowrite32(ALTERA_TSE_RX_ALMOST_EMPTY, &mac->rx_almost_empty);
-	iowrite32(ALTERA_TSE_RX_ALMOST_FULL, &mac->rx_almost_full);
+	csrwr32(priv->rx_fifo_depth - ALTERA_TSE_RX_SECTION_EMPTY,
+		priv->mac_dev, tse_csroffs(rx_section_empty));
+
+	csrwr32(ALTERA_TSE_RX_SECTION_FULL, priv->mac_dev,
+		tse_csroffs(rx_section_full));
+
+	csrwr32(ALTERA_TSE_RX_ALMOST_EMPTY, priv->mac_dev,
+		tse_csroffs(rx_almost_empty));
+
+	csrwr32(ALTERA_TSE_RX_ALMOST_FULL, priv->mac_dev,
+		tse_csroffs(rx_almost_full));
 
 	/* Setup Tx FIFO */
-	iowrite32(priv->tx_fifo_depth - ALTERA_TSE_TX_SECTION_EMPTY,
-		  &mac->tx_section_empty);
-	iowrite32(ALTERA_TSE_TX_SECTION_FULL, &mac->tx_section_full);
-	iowrite32(ALTERA_TSE_TX_ALMOST_EMPTY, &mac->tx_almost_empty);
-	iowrite32(ALTERA_TSE_TX_ALMOST_FULL, &mac->tx_almost_full);
+	csrwr32(priv->tx_fifo_depth - ALTERA_TSE_TX_SECTION_EMPTY,
+		priv->mac_dev, tse_csroffs(tx_section_empty));
+
+	csrwr32(ALTERA_TSE_TX_SECTION_FULL, priv->mac_dev,
+		tse_csroffs(tx_section_full));
+
+	csrwr32(ALTERA_TSE_TX_ALMOST_EMPTY, priv->mac_dev,
+		tse_csroffs(tx_almost_empty));
+
+	csrwr32(ALTERA_TSE_TX_ALMOST_FULL, priv->mac_dev,
+		tse_csroffs(tx_almost_full));
 
 	/* MAC Address Configuration */
 	tse_update_mac_addr(priv, priv->dev->dev_addr);
 
 	/* MAC Function Configuration */
 	frm_length = ETH_HLEN + priv->dev->mtu + ETH_FCS_LEN;
-	iowrite32(frm_length, &mac->frm_length);
-	iowrite32(ALTERA_TSE_TX_IPG_LENGTH, &mac->tx_ipg_length);
+	csrwr32(frm_length, priv->mac_dev, tse_csroffs(frm_length));
+
+	csrwr32(ALTERA_TSE_TX_IPG_LENGTH, priv->mac_dev,
+		tse_csroffs(tx_ipg_length));
 
 	/* Disable RX/TX shift 16 for alignment of all received frames on 16-bit
 	 * start address
 	 */
-	tse_set_bit(&mac->rx_cmd_stat, ALTERA_TSE_RX_CMD_STAT_RX_SHIFT16);
-	tse_clear_bit(&mac->tx_cmd_stat, ALTERA_TSE_TX_CMD_STAT_TX_SHIFT16 |
-					 ALTERA_TSE_TX_CMD_STAT_OMIT_CRC);
+	tse_set_bit(priv->mac_dev, tse_csroffs(rx_cmd_stat),
+		    ALTERA_TSE_RX_CMD_STAT_RX_SHIFT16);
+
+	tse_clear_bit(priv->mac_dev, tse_csroffs(tx_cmd_stat),
+		      ALTERA_TSE_TX_CMD_STAT_TX_SHIFT16 |
+		      ALTERA_TSE_TX_CMD_STAT_OMIT_CRC);
 
 	/* Set the MAC options */
-	cmd = ioread32(&mac->command_config);
+	cmd = csrrd32(priv->mac_dev, tse_csroffs(command_config));
 	cmd &= ~MAC_CMDCFG_PAD_EN;	/* No padding Removal on Receive */
 	cmd &= ~MAC_CMDCFG_CRC_FWD;	/* CRC Removal */
 	cmd |= MAC_CMDCFG_RX_ERR_DISC;	/* Automatically discard frames
@@ -889,9 +904,10 @@ static int init_mac(struct altera_tse_private *priv)
 	cmd &= ~MAC_CMDCFG_ETH_SPEED;
 	cmd &= ~MAC_CMDCFG_ENA_10;
 
-	iowrite32(cmd, &mac->command_config);
+	csrwr32(cmd, priv->mac_dev, tse_csroffs(command_config));
 
-	iowrite32(ALTERA_TSE_PAUSE_QUANTA, &mac->pause_quanta);
+	csrwr32(ALTERA_TSE_PAUSE_QUANTA, priv->mac_dev,
+		tse_csroffs(pause_quanta));
 
 	if (netif_msg_hw(priv))
 		dev_dbg(priv->device,
@@ -904,15 +920,14 @@ static int init_mac(struct altera_tse_private *priv)
  */
 static void tse_set_mac(struct altera_tse_private *priv, bool enable)
 {
-	struct altera_tse_mac *mac = priv->mac_dev;
-	u32 value = ioread32(&mac->command_config);
+	u32 value = csrrd32(priv->mac_dev, tse_csroffs(command_config));
 
 	if (enable)
 		value |= MAC_CMDCFG_TX_ENA | MAC_CMDCFG_RX_ENA;
 	else
 		value &= ~(MAC_CMDCFG_TX_ENA | MAC_CMDCFG_RX_ENA);
 
-	iowrite32(value, &mac->command_config);
+	csrwr32(value, priv->mac_dev, tse_csroffs(command_config));
 }
 
 /* Change the MTU
@@ -942,13 +957,12 @@ static int tse_change_mtu(struct net_device *dev, int new_mtu)
 static void altera_tse_set_mcfilter(struct net_device *dev)
 {
 	struct altera_tse_private *priv = netdev_priv(dev);
-	struct altera_tse_mac *mac = priv->mac_dev;
 	int i;
 	struct netdev_hw_addr *ha;
 
 	/* clear the hash filter */
 	for (i = 0; i < 64; i++)
-		iowrite32(0, &(mac->hash_table[i]));
+		csrwr32(0, priv->mac_dev, tse_csroffs(hash_table) + i * 4);
 
 	netdev_for_each_mc_addr(ha, dev) {
 		unsigned int hash = 0;
@@ -964,7 +978,7 @@ static void altera_tse_set_mcfilter(struct net_device *dev)
 
 			hash = (hash << 1) | xor_bit;
 		}
-		iowrite32(1, &(mac->hash_table[hash]));
+		csrwr32(1, priv->mac_dev, tse_csroffs(hash_table) + hash * 4);
 	}
 }
 
@@ -972,12 +986,11 @@ static void altera_tse_set_mcfilter(struct net_device *dev)
 static void altera_tse_set_mcfilterall(struct net_device *dev)
 {
 	struct altera_tse_private *priv = netdev_priv(dev);
-	struct altera_tse_mac *mac = priv->mac_dev;
 	int i;
 
 	/* set the hash filter */
 	for (i = 0; i < 64; i++)
-		iowrite32(1, &(mac->hash_table[i]));
+		csrwr32(1, priv->mac_dev, tse_csroffs(hash_table) + i * 4);
 }
 
 /* Set or clear the multicast filter for this adaptor
@@ -985,12 +998,12 @@ static void altera_tse_set_mcfilterall(struct net_device *dev)
 static void tse_set_rx_mode_hashfilter(struct net_device *dev)
 {
 	struct altera_tse_private *priv = netdev_priv(dev);
-	struct altera_tse_mac *mac = priv->mac_dev;
 
 	spin_lock(&priv->mac_cfg_lock);
 
 	if (dev->flags & IFF_PROMISC)
-		tse_set_bit(&mac->command_config, MAC_CMDCFG_PROMIS_EN);
+		tse_set_bit(priv->mac_dev, tse_csroffs(command_config),
+			    MAC_CMDCFG_PROMIS_EN);
 
 	if (dev->flags & IFF_ALLMULTI)
 		altera_tse_set_mcfilterall(dev);
@@ -1005,15 +1018,16 @@ static void tse_set_rx_mode_hashfilter(struct net_device *dev)
 static void tse_set_rx_mode(struct net_device *dev)
 {
 	struct altera_tse_private *priv = netdev_priv(dev);
-	struct altera_tse_mac *mac = priv->mac_dev;
 
 	spin_lock(&priv->mac_cfg_lock);
 
 	if ((dev->flags & IFF_PROMISC) || (dev->flags & IFF_ALLMULTI) ||
 	    !netdev_mc_empty(dev) || !netdev_uc_empty(dev))
-		tse_set_bit(&mac->command_config, MAC_CMDCFG_PROMIS_EN);
+		tse_set_bit(priv->mac_dev, tse_csroffs(command_config),
+			    MAC_CMDCFG_PROMIS_EN);
 	else
-		tse_clear_bit(&mac->command_config, MAC_CMDCFG_PROMIS_EN);
+		tse_clear_bit(priv->mac_dev, tse_csroffs(command_config),
+			      MAC_CMDCFG_PROMIS_EN);
 
 	spin_unlock(&priv->mac_cfg_lock);
 }
@@ -1362,6 +1376,11 @@ static int altera_tse_probe(struct platform_device *pdev)
 		of_property_read_bool(pdev->dev.of_node,
 				      "altr,has-hash-multicast-filter");
 
+	/* Set hash filter to not set for now until the
+	 * multicast filter receive issue is debugged
+	 */
+	priv->hash_filter = 0;
+
 	/* get supplemental address settings for this instance */
 	priv->added_unicast =
 		of_property_read_bool(pdev->dev.of_node,
@@ -1493,7 +1512,7 @@ static int altera_tse_remove(struct platform_device *pdev)
 	return 0;
 }
 
-struct altera_dmaops altera_dtype_sgdma = {
+static const struct altera_dmaops altera_dtype_sgdma = {
 	.altera_dtype = ALTERA_DTYPE_SGDMA,
 	.dmamask = 32,
 	.reset_dma = sgdma_reset,
@@ -1512,7 +1531,7 @@ struct altera_dmaops altera_dtype_sgdma = {
 	.start_rxdma = sgdma_start_rxdma,
 };
 
-struct altera_dmaops altera_dtype_msgdma = {
+static const struct altera_dmaops altera_dtype_msgdma = {
 	.altera_dtype = ALTERA_DTYPE_MSGDMA,
 	.dmamask = 64,
 	.reset_dma = msgdma_reset,
diff --git a/drivers/net/ethernet/altera/altera_utils.c b/drivers/net/ethernet/altera/altera_utils.c
index 70fa13f486b2..d7eeb1713ad2 100644
--- a/drivers/net/ethernet/altera/altera_utils.c
+++ b/drivers/net/ethernet/altera/altera_utils.c
@@ -17,28 +17,28 @@
 #include "altera_tse.h"
 #include "altera_utils.h"
 
-void tse_set_bit(void __iomem *ioaddr, u32 bit_mask)
+void tse_set_bit(void __iomem *ioaddr, size_t offs, u32 bit_mask)
 {
-	u32 value = ioread32(ioaddr);
+	u32 value = csrrd32(ioaddr, offs);
 	value |= bit_mask;
-	iowrite32(value, ioaddr);
+	csrwr32(value, ioaddr, offs);
 }
 
-void tse_clear_bit(void __iomem *ioaddr, u32 bit_mask)
+void tse_clear_bit(void __iomem *ioaddr, size_t offs, u32 bit_mask)
 {
-	u32 value = ioread32(ioaddr);
+	u32 value = csrrd32(ioaddr, offs);
 	value &= ~bit_mask;
-	iowrite32(value, ioaddr);
+	csrwr32(value, ioaddr, offs);
 }
 
-int tse_bit_is_set(void __iomem *ioaddr, u32 bit_mask)
+int tse_bit_is_set(void __iomem *ioaddr, size_t offs, u32 bit_mask)
 {
-	u32 value = ioread32(ioaddr);
+	u32 value = csrrd32(ioaddr, offs);
 	return (value & bit_mask) ? 1 : 0;
 }
 
-int tse_bit_is_clear(void __iomem *ioaddr, u32 bit_mask)
+int tse_bit_is_clear(void __iomem *ioaddr, size_t offs, u32 bit_mask)
 {
-	u32 value = ioread32(ioaddr);
+	u32 value = csrrd32(ioaddr, offs);
 	return (value & bit_mask) ? 0 : 1;
 }
diff --git a/drivers/net/ethernet/altera/altera_utils.h b/drivers/net/ethernet/altera/altera_utils.h
index ce1db36d3583..baf100ccf587 100644
--- a/drivers/net/ethernet/altera/altera_utils.h
+++ b/drivers/net/ethernet/altera/altera_utils.h
@@ -19,9 +19,9 @@
 #ifndef __ALTERA_UTILS_H__
 #define __ALTERA_UTILS_H__
 
-void tse_set_bit(void __iomem *ioaddr, u32 bit_mask);
-void tse_clear_bit(void __iomem *ioaddr, u32 bit_mask);
-int tse_bit_is_set(void __iomem *ioaddr, u32 bit_mask);
-int tse_bit_is_clear(void __iomem *ioaddr, u32 bit_mask);
+void tse_set_bit(void __iomem *ioaddr, size_t offs, u32 bit_mask);
+void tse_clear_bit(void __iomem *ioaddr, size_t offs, u32 bit_mask);
+int tse_bit_is_set(void __iomem *ioaddr, size_t offs, u32 bit_mask);
+int tse_bit_is_clear(void __iomem *ioaddr, size_t offs, u32 bit_mask);
 
 #endif /* __ALTERA_UTILS_H__*/
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index b260913db236..3b0d43154e67 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -10051,8 +10051,8 @@ static void bnx2x_prev_unload_close_mac(struct bnx2x *bp,
 #define BCM_5710_UNDI_FW_MF_MAJOR	(0x07)
 #define BCM_5710_UNDI_FW_MF_MINOR	(0x08)
 #define BCM_5710_UNDI_FW_MF_VERS	(0x05)
-#define BNX2X_PREV_UNDI_MF_PORT(p)	(0x1a150c + ((p) << 4))
-#define BNX2X_PREV_UNDI_MF_FUNC(f)	(0x1a184c + ((f) << 4))
+#define BNX2X_PREV_UNDI_MF_PORT(p) (BAR_TSTRORM_INTMEM + 0x150c + ((p) << 4))
+#define BNX2X_PREV_UNDI_MF_FUNC(f) (BAR_TSTRORM_INTMEM + 0x184c + ((f) << 4))
 static bool bnx2x_prev_unload_undi_fw_supports_mf(struct bnx2x *bp)
 {
 	u8 major, minor, version;
@@ -10352,6 +10352,7 @@ static int bnx2x_prev_unload_common(struct bnx2x *bp)
 	/* Reset should be performed after BRB is emptied */
 	if (reset_reg & MISC_REGISTERS_RESET_REG_1_RST_BRB1) {
 		u32 timer_count = 1000;
+		bool need_write = true;
 
 		/* Close the MAC Rx to prevent BRB from filling up */
 		bnx2x_prev_unload_close_mac(bp, &mac_vals);
@@ -10398,7 +10399,10 @@ static int bnx2x_prev_unload_common(struct bnx2x *bp)
 			 * cleaning methods - might be redundant but harmless.
 			 */
 			if (bnx2x_prev_unload_undi_fw_supports_mf(bp)) {
-				bnx2x_prev_unload_undi_mf(bp);
+				if (need_write) {
+					bnx2x_prev_unload_undi_mf(bp);
+					need_write = false;
+				}
 			} else if (prev_undi) {
 				/* If UNDI resides in memory,
 				 * manually increment it
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index 81cc2d9831c2..b8078d50261b 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -2695,7 +2695,7 @@ out:
 		bnx2x_unlock_vf_pf_channel(bp, vf, CHANNEL_TLV_PF_SET_MAC);
 	}
 
-	return 0;
+	return rc;
 }
 
 int bnx2x_set_vf_vlan(struct net_device *dev, int vfidx, u16 vlan, u8 qos)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
index 0c067e8564dd..784c7155b98a 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
@@ -747,7 +747,7 @@ int bnx2x_vfpf_config_mac(struct bnx2x *bp, u8 *addr, u8 vf_qid, bool set)
 out:
 	bnx2x_vfpf_finalize(bp, &req->first_tlv);
 
-	return 0;
+	return rc;
 }
 
 /* request pf to config rss table for vf queues*/
diff --git a/drivers/net/ethernet/ec_bhf.c b/drivers/net/ethernet/ec_bhf.c
new file mode 100644
index 000000000000..4884205e56ee
--- /dev/null
+++ b/drivers/net/ethernet/ec_bhf.c
@@ -0,0 +1,706 @@
+ /*
+ * drivers/net/ethernet/beckhoff/ec_bhf.c
+ *
+ * Copyright (C) 2014 Darek Marcinkiewicz <reksio@newterm.pl>
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+/* This is a driver for EtherCAT master module present on CCAT FPGA.
+ * Those can be found on Bechhoff CX50xx industrial PCs.
+ */
+
+#if 0
+#define DEBUG
+#endif
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/pci.h>
+#include <linux/init.h>
+
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/ip.h>
+#include <linux/skbuff.h>
+#include <linux/hrtimer.h>
+#include <linux/interrupt.h>
+#include <linux/stat.h>
+
+#define TIMER_INTERVAL_NSEC	20000
+
+#define INFO_BLOCK_SIZE		0x10
+#define INFO_BLOCK_TYPE		0x0
+#define INFO_BLOCK_REV		0x2
+#define INFO_BLOCK_BLK_CNT	0x4
+#define INFO_BLOCK_TX_CHAN	0x4
+#define INFO_BLOCK_RX_CHAN	0x5
+#define INFO_BLOCK_OFFSET	0x8
+
+#define EC_MII_OFFSET		0x4
+#define EC_FIFO_OFFSET		0x8
+#define EC_MAC_OFFSET		0xc
+
+#define MAC_FRAME_ERR_CNT	0x0
+#define MAC_RX_ERR_CNT		0x1
+#define MAC_CRC_ERR_CNT		0x2
+#define MAC_LNK_LST_ERR_CNT	0x3
+#define MAC_TX_FRAME_CNT	0x10
+#define MAC_RX_FRAME_CNT	0x14
+#define MAC_TX_FIFO_LVL		0x20
+#define MAC_DROPPED_FRMS	0x28
+#define MAC_CONNECTED_CCAT_FLAG	0x78
+
+#define MII_MAC_ADDR		0x8
+#define MII_MAC_FILT_FLAG	0xe
+#define MII_LINK_STATUS		0xf
+
+#define FIFO_TX_REG		0x0
+#define FIFO_TX_RESET		0x8
+#define FIFO_RX_REG		0x10
+#define FIFO_RX_ADDR_VALID	(1u << 31)
+#define FIFO_RX_RESET		0x18
+
+#define DMA_CHAN_OFFSET		0x1000
+#define DMA_CHAN_SIZE		0x8
+
+#define DMA_WINDOW_SIZE_MASK	0xfffffffc
+
+static struct pci_device_id ids[] = {
+	{ PCI_DEVICE(0x15ec, 0x5000), },
+	{ 0, }
+};
+MODULE_DEVICE_TABLE(pci, ids);
+
+struct rx_header {
+#define RXHDR_NEXT_ADDR_MASK	0xffffffu
+#define RXHDR_NEXT_VALID	(1u << 31)
+	__le32 next;
+#define RXHDR_NEXT_RECV_FLAG	0x1
+	__le32 recv;
+#define RXHDR_LEN_MASK		0xfffu
+	__le16 len;
+	__le16 port;
+	__le32 reserved;
+	u8 timestamp[8];
+} __packed;
+
+#define PKT_PAYLOAD_SIZE	0x7e8
+struct rx_desc {
+	struct rx_header header;
+	u8 data[PKT_PAYLOAD_SIZE];
+} __packed;
+
+struct tx_header {
+	__le16 len;
+#define TX_HDR_PORT_0		0x1
+#define TX_HDR_PORT_1		0x2
+	u8 port;
+	u8 ts_enable;
+#define TX_HDR_SENT		0x1
+	__le32 sent;
+	u8 timestamp[8];
+} __packed;
+
+struct tx_desc {
+	struct tx_header header;
+	u8 data[PKT_PAYLOAD_SIZE];
+} __packed;
+
+#define FIFO_SIZE		64
+
+static long polling_frequency = TIMER_INTERVAL_NSEC;
+
+struct bhf_dma {
+	u8 *buf;
+	size_t len;
+	dma_addr_t buf_phys;
+
+	u8 *alloc;
+	size_t alloc_len;
+	dma_addr_t alloc_phys;
+};
+
+struct ec_bhf_priv {
+	struct net_device *net_dev;
+
+	struct pci_dev *dev;
+
+	void * __iomem io;
+	void * __iomem dma_io;
+
+	struct hrtimer hrtimer;
+
+	int tx_dma_chan;
+	int rx_dma_chan;
+	void * __iomem ec_io;
+	void * __iomem fifo_io;
+	void * __iomem mii_io;
+	void * __iomem mac_io;
+
+	struct bhf_dma rx_buf;
+	struct rx_desc *rx_descs;
+	int rx_dnext;
+	int rx_dcount;
+
+	struct bhf_dma tx_buf;
+	struct tx_desc *tx_descs;
+	int tx_dcount;
+	int tx_dnext;
+
+	u64 stat_rx_bytes;
+	u64 stat_tx_bytes;
+};
+
+#define PRIV_TO_DEV(priv) (&(priv)->dev->dev)
+
+#define ETHERCAT_MASTER_ID	0x14
+
+static void ec_bhf_print_status(struct ec_bhf_priv *priv)
+{
+	struct device *dev = PRIV_TO_DEV(priv);
+
+	dev_dbg(dev, "Frame error counter: %d\n",
+		ioread8(priv->mac_io + MAC_FRAME_ERR_CNT));
+	dev_dbg(dev, "RX error counter: %d\n",
+		ioread8(priv->mac_io + MAC_RX_ERR_CNT));
+	dev_dbg(dev, "CRC error counter: %d\n",
+		ioread8(priv->mac_io + MAC_CRC_ERR_CNT));
+	dev_dbg(dev, "TX frame counter: %d\n",
+		ioread32(priv->mac_io + MAC_TX_FRAME_CNT));
+	dev_dbg(dev, "RX frame counter: %d\n",
+		ioread32(priv->mac_io + MAC_RX_FRAME_CNT));
+	dev_dbg(dev, "TX fifo level: %d\n",
+		ioread8(priv->mac_io + MAC_TX_FIFO_LVL));
+	dev_dbg(dev, "Dropped frames: %d\n",
+		ioread8(priv->mac_io + MAC_DROPPED_FRMS));
+	dev_dbg(dev, "Connected with CCAT slot: %d\n",
+		ioread8(priv->mac_io + MAC_CONNECTED_CCAT_FLAG));
+	dev_dbg(dev, "Link status: %d\n",
+		ioread8(priv->mii_io + MII_LINK_STATUS));
+}
+
+static void ec_bhf_reset(struct ec_bhf_priv *priv)
+{
+	iowrite8(0, priv->mac_io + MAC_FRAME_ERR_CNT);
+	iowrite8(0, priv->mac_io + MAC_RX_ERR_CNT);
+	iowrite8(0, priv->mac_io + MAC_CRC_ERR_CNT);
+	iowrite8(0, priv->mac_io + MAC_LNK_LST_ERR_CNT);
+	iowrite32(0, priv->mac_io + MAC_TX_FRAME_CNT);
+	iowrite32(0, priv->mac_io + MAC_RX_FRAME_CNT);
+	iowrite8(0, priv->mac_io + MAC_DROPPED_FRMS);
+
+	iowrite8(0, priv->fifo_io + FIFO_TX_RESET);
+	iowrite8(0, priv->fifo_io + FIFO_RX_RESET);
+
+	iowrite8(0, priv->mac_io + MAC_TX_FIFO_LVL);
+}
+
+static void ec_bhf_send_packet(struct ec_bhf_priv *priv, struct tx_desc *desc)
+{
+	u32 len = le16_to_cpu(desc->header.len) + sizeof(desc->header);
+	u32 addr = (u8 *)desc - priv->tx_buf.buf;
+
+	iowrite32((ALIGN(len, 8) << 24) | addr, priv->fifo_io + FIFO_TX_REG);
+
+	dev_dbg(PRIV_TO_DEV(priv), "Done sending packet\n");
+}
+
+static int ec_bhf_desc_sent(struct tx_desc *desc)
+{
+	return le32_to_cpu(desc->header.sent) & TX_HDR_SENT;
+}
+
+static void ec_bhf_process_tx(struct ec_bhf_priv *priv)
+{
+	if (unlikely(netif_queue_stopped(priv->net_dev))) {
+		/* Make sure that we perceive changes to tx_dnext. */
+		smp_rmb();
+
+		if (ec_bhf_desc_sent(&priv->tx_descs[priv->tx_dnext]))
+			netif_wake_queue(priv->net_dev);
+	}
+}
+
+static int ec_bhf_pkt_received(struct rx_desc *desc)
+{
+	return le32_to_cpu(desc->header.recv) & RXHDR_NEXT_RECV_FLAG;
+}
+
+static void ec_bhf_add_rx_desc(struct ec_bhf_priv *priv, struct rx_desc *desc)
+{
+	iowrite32(FIFO_RX_ADDR_VALID | ((u8 *)(desc) - priv->rx_buf.buf),
+		  priv->fifo_io + FIFO_RX_REG);
+}
+
+static void ec_bhf_process_rx(struct ec_bhf_priv *priv)
+{
+	struct rx_desc *desc = &priv->rx_descs[priv->rx_dnext];
+	struct device *dev = PRIV_TO_DEV(priv);
+
+	while (ec_bhf_pkt_received(desc)) {
+		int pkt_size = (le16_to_cpu(desc->header.len) &
+			       RXHDR_LEN_MASK) - sizeof(struct rx_header) - 4;
+		u8 *data = desc->data;
+		struct sk_buff *skb;
+
+		skb = netdev_alloc_skb_ip_align(priv->net_dev, pkt_size);
+		dev_dbg(dev, "Received packet, size: %d\n", pkt_size);
+
+		if (skb) {
+			memcpy(skb_put(skb, pkt_size), data, pkt_size);
+			skb->protocol = eth_type_trans(skb, priv->net_dev);
+			dev_dbg(dev, "Protocol type: %x\n", skb->protocol);
+
+			priv->stat_rx_bytes += pkt_size;
+
+			netif_rx(skb);
+		} else {
+			dev_err_ratelimited(dev,
+				"Couldn't allocate a skb_buff for a packet of size %u\n",
+				pkt_size);
+		}
+
+		desc->header.recv = 0;
+
+		ec_bhf_add_rx_desc(priv, desc);
+
+		priv->rx_dnext = (priv->rx_dnext + 1) % priv->rx_dcount;
+		desc = &priv->rx_descs[priv->rx_dnext];
+	}
+
+}
+
+static enum hrtimer_restart ec_bhf_timer_fun(struct hrtimer *timer)
+{
+	struct ec_bhf_priv *priv = container_of(timer, struct ec_bhf_priv,
+						hrtimer);
+	ec_bhf_process_rx(priv);
+	ec_bhf_process_tx(priv);
+
+	if (!netif_running(priv->net_dev))
+		return HRTIMER_NORESTART;
+
+	hrtimer_forward_now(timer, ktime_set(0, polling_frequency));
+	return HRTIMER_RESTART;
+}
+
+static int ec_bhf_setup_offsets(struct ec_bhf_priv *priv)
+{
+	struct device *dev = PRIV_TO_DEV(priv);
+	unsigned block_count, i;
+	void * __iomem ec_info;
+
+	dev_dbg(dev, "Info block:\n");
+	dev_dbg(dev, "Type of function: %x\n", (unsigned)ioread16(priv->io));
+	dev_dbg(dev, "Revision of function: %x\n",
+		(unsigned)ioread16(priv->io + INFO_BLOCK_REV));
+
+	block_count = ioread8(priv->io + INFO_BLOCK_BLK_CNT);
+	dev_dbg(dev, "Number of function blocks: %x\n", block_count);
+
+	for (i = 0; i < block_count; i++) {
+		u16 type = ioread16(priv->io + i * INFO_BLOCK_SIZE +
+				    INFO_BLOCK_TYPE);
+		if (type == ETHERCAT_MASTER_ID)
+			break;
+	}
+	if (i == block_count) {
+		dev_err(dev, "EtherCAT master with DMA block not found\n");
+		return -ENODEV;
+	}
+	dev_dbg(dev, "EtherCAT master with DMA block found at pos: %d\n", i);
+
+	ec_info = priv->io + i * INFO_BLOCK_SIZE;
+	dev_dbg(dev, "EtherCAT master revision: %d\n",
+		ioread16(ec_info + INFO_BLOCK_REV));
+
+	priv->tx_dma_chan = ioread8(ec_info + INFO_BLOCK_TX_CHAN);
+	dev_dbg(dev, "EtherCAT master tx dma channel: %d\n",
+		priv->tx_dma_chan);
+
+	priv->rx_dma_chan = ioread8(ec_info + INFO_BLOCK_RX_CHAN);
+	dev_dbg(dev, "EtherCAT master rx dma channel: %d\n",
+		 priv->rx_dma_chan);
+
+	priv->ec_io = priv->io + ioread32(ec_info + INFO_BLOCK_OFFSET);
+	priv->mii_io = priv->ec_io + ioread32(priv->ec_io + EC_MII_OFFSET);
+	priv->fifo_io = priv->ec_io + ioread32(priv->ec_io + EC_FIFO_OFFSET);
+	priv->mac_io = priv->ec_io + ioread32(priv->ec_io + EC_MAC_OFFSET);
+
+	dev_dbg(dev,
+		"EtherCAT block addres: %p, fifo address: %p, mii address: %p, mac address: %p\n",
+		priv->ec_io, priv->fifo_io, priv->mii_io, priv->mac_io);
+
+	return 0;
+}
+
+static netdev_tx_t ec_bhf_start_xmit(struct sk_buff *skb,
+				     struct net_device *net_dev)
+{
+	struct ec_bhf_priv *priv = netdev_priv(net_dev);
+	struct tx_desc *desc;
+	unsigned len;
+
+	dev_dbg(PRIV_TO_DEV(priv), "Starting xmit\n");
+
+	desc = &priv->tx_descs[priv->tx_dnext];
+
+	skb_copy_and_csum_dev(skb, desc->data);
+	len = skb->len;
+
+	memset(&desc->header, 0, sizeof(desc->header));
+	desc->header.len = cpu_to_le16(len);
+	desc->header.port = TX_HDR_PORT_0;
+
+	ec_bhf_send_packet(priv, desc);
+
+	priv->tx_dnext = (priv->tx_dnext + 1) % priv->tx_dcount;
+
+	if (!ec_bhf_desc_sent(&priv->tx_descs[priv->tx_dnext])) {
+		/* Make sure that update updates to tx_dnext are perceived
+		 * by timer routine.
+		 */
+		smp_wmb();
+
+		netif_stop_queue(net_dev);
+
+		dev_dbg(PRIV_TO_DEV(priv), "Stopping netif queue\n");
+		ec_bhf_print_status(priv);
+	}
+
+	priv->stat_tx_bytes += len;
+
+	dev_kfree_skb(skb);
+
+	return NETDEV_TX_OK;
+}
+
+static int ec_bhf_alloc_dma_mem(struct ec_bhf_priv *priv,
+				struct bhf_dma *buf,
+				int channel,
+				int size)
+{
+	int offset = channel * DMA_CHAN_SIZE + DMA_CHAN_OFFSET;
+	struct device *dev = PRIV_TO_DEV(priv);
+	u32 mask;
+
+	iowrite32(0xffffffff, priv->dma_io + offset);
+
+	mask = ioread32(priv->dma_io + offset);
+	mask &= DMA_WINDOW_SIZE_MASK;
+	dev_dbg(dev, "Read mask %x for channel %d\n", mask, channel);
+
+	/* We want to allocate a chunk of memory that is:
+	 * - aligned to the mask we just read
+	 * - is of size 2^mask bytes (at most)
+	 * In order to ensure that we will allocate buffer of
+	 * 2 * 2^mask bytes.
+	 */
+	buf->len = min_t(int, ~mask + 1, size);
+	buf->alloc_len = 2 * buf->len;
+
+	dev_dbg(dev, "Allocating %d bytes for channel %d",
+		(int)buf->alloc_len, channel);
+	buf->alloc = dma_alloc_coherent(dev, buf->alloc_len, &buf->alloc_phys,
+					GFP_KERNEL);
+	if (buf->alloc == NULL) {
+		dev_info(dev, "Failed to allocate buffer\n");
+		return -ENOMEM;
+	}
+
+	buf->buf_phys = (buf->alloc_phys + buf->len) & mask;
+	buf->buf = buf->alloc + (buf->buf_phys - buf->alloc_phys);
+
+	iowrite32(0, priv->dma_io + offset + 4);
+	iowrite32(buf->buf_phys, priv->dma_io + offset);
+	dev_dbg(dev, "Buffer: %x and read from dev: %x",
+		(unsigned)buf->buf_phys, ioread32(priv->dma_io + offset));
+
+	return 0;
+}
+
+static void ec_bhf_setup_tx_descs(struct ec_bhf_priv *priv)
+{
+	int i = 0;
+
+	priv->tx_dcount = priv->tx_buf.len / sizeof(struct tx_desc);
+	priv->tx_descs = (struct tx_desc *) priv->tx_buf.buf;
+	priv->tx_dnext = 0;
+
+	for (i = 0; i < priv->tx_dcount; i++)
+		priv->tx_descs[i].header.sent = cpu_to_le32(TX_HDR_SENT);
+}
+
+static void ec_bhf_setup_rx_descs(struct ec_bhf_priv *priv)
+{
+	int i;
+
+	priv->rx_dcount = priv->rx_buf.len / sizeof(struct rx_desc);
+	priv->rx_descs = (struct rx_desc *) priv->rx_buf.buf;
+	priv->rx_dnext = 0;
+
+	for (i = 0; i < priv->rx_dcount; i++) {
+		struct rx_desc *desc = &priv->rx_descs[i];
+		u32 next;
+
+		if (i != priv->rx_dcount - 1)
+			next = (u8 *)(desc + 1) - priv->rx_buf.buf;
+		else
+			next = 0;
+		next |= RXHDR_NEXT_VALID;
+		desc->header.next = cpu_to_le32(next);
+		desc->header.recv = 0;
+		ec_bhf_add_rx_desc(priv, desc);
+	}
+}
+
+static int ec_bhf_open(struct net_device *net_dev)
+{
+	struct ec_bhf_priv *priv = netdev_priv(net_dev);
+	struct device *dev = PRIV_TO_DEV(priv);
+	int err = 0;
+
+	dev_info(dev, "Opening device\n");
+
+	ec_bhf_reset(priv);
+
+	err = ec_bhf_alloc_dma_mem(priv, &priv->rx_buf, priv->rx_dma_chan,
+				   FIFO_SIZE * sizeof(struct rx_desc));
+	if (err) {
+		dev_err(dev, "Failed to allocate rx buffer\n");
+		goto out;
+	}
+	ec_bhf_setup_rx_descs(priv);
+
+	dev_info(dev, "RX buffer allocated, address: %x\n",
+		 (unsigned)priv->rx_buf.buf_phys);
+
+	err = ec_bhf_alloc_dma_mem(priv, &priv->tx_buf, priv->tx_dma_chan,
+				   FIFO_SIZE * sizeof(struct tx_desc));
+	if (err) {
+		dev_err(dev, "Failed to allocate tx buffer\n");
+		goto error_rx_free;
+	}
+	dev_dbg(dev, "TX buffer allocated, addres: %x\n",
+		(unsigned)priv->tx_buf.buf_phys);
+
+	iowrite8(0, priv->mii_io + MII_MAC_FILT_FLAG);
+
+	ec_bhf_setup_tx_descs(priv);
+
+	netif_start_queue(net_dev);
+
+	hrtimer_init(&priv->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	priv->hrtimer.function = ec_bhf_timer_fun;
+	hrtimer_start(&priv->hrtimer, ktime_set(0, polling_frequency),
+		      HRTIMER_MODE_REL);
+
+	dev_info(PRIV_TO_DEV(priv), "Device open\n");
+
+	ec_bhf_print_status(priv);
+
+	return 0;
+
+error_rx_free:
+	dma_free_coherent(dev, priv->rx_buf.alloc_len, priv->rx_buf.alloc,
+			  priv->rx_buf.alloc_len);
+out:
+	return err;
+}
+
+static int ec_bhf_stop(struct net_device *net_dev)
+{
+	struct ec_bhf_priv *priv = netdev_priv(net_dev);
+	struct device *dev = PRIV_TO_DEV(priv);
+
+	hrtimer_cancel(&priv->hrtimer);
+
+	ec_bhf_reset(priv);
+
+	netif_tx_disable(net_dev);
+
+	dma_free_coherent(dev, priv->tx_buf.alloc_len,
+			  priv->tx_buf.alloc, priv->tx_buf.alloc_phys);
+	dma_free_coherent(dev, priv->rx_buf.alloc_len,
+			  priv->rx_buf.alloc, priv->rx_buf.alloc_phys);
+
+	return 0;
+}
+
+static struct rtnl_link_stats64 *
+ec_bhf_get_stats(struct net_device *net_dev,
+		 struct rtnl_link_stats64 *stats)
+{
+	struct ec_bhf_priv *priv = netdev_priv(net_dev);
+
+	stats->rx_errors = ioread8(priv->mac_io + MAC_RX_ERR_CNT) +
+				ioread8(priv->mac_io + MAC_CRC_ERR_CNT) +
+				ioread8(priv->mac_io + MAC_FRAME_ERR_CNT);
+	stats->rx_packets = ioread32(priv->mac_io + MAC_RX_FRAME_CNT);
+	stats->tx_packets = ioread32(priv->mac_io + MAC_TX_FRAME_CNT);
+	stats->rx_dropped = ioread8(priv->mac_io + MAC_DROPPED_FRMS);
+
+	stats->tx_bytes = priv->stat_tx_bytes;
+	stats->rx_bytes = priv->stat_rx_bytes;
+
+	return stats;
+}
+
+static const struct net_device_ops ec_bhf_netdev_ops = {
+	.ndo_start_xmit		= ec_bhf_start_xmit,
+	.ndo_open		= ec_bhf_open,
+	.ndo_stop		= ec_bhf_stop,
+	.ndo_get_stats64	= ec_bhf_get_stats,
+	.ndo_change_mtu		= eth_change_mtu,
+	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_set_mac_address	= eth_mac_addr
+};
+
+static int ec_bhf_probe(struct pci_dev *dev, const struct pci_device_id *id)
+{
+	struct net_device *net_dev;
+	struct ec_bhf_priv *priv;
+	void * __iomem dma_io;
+	void * __iomem io;
+	int err = 0;
+
+	err = pci_enable_device(dev);
+	if (err)
+		return err;
+
+	pci_set_master(dev);
+
+	err = pci_set_dma_mask(dev, DMA_BIT_MASK(32));
+	if (err) {
+		dev_err(&dev->dev,
+			"Required dma mask not supported, failed to initialize device\n");
+		err = -EIO;
+		goto err_disable_dev;
+	}
+
+	err = pci_set_consistent_dma_mask(dev, DMA_BIT_MASK(32));
+	if (err) {
+		dev_err(&dev->dev,
+			"Required dma mask not supported, failed to initialize device\n");
+		goto err_disable_dev;
+	}
+
+	err = pci_request_regions(dev, "ec_bhf");
+	if (err) {
+		dev_err(&dev->dev, "Failed to request pci memory regions\n");
+		goto err_disable_dev;
+	}
+
+	io = pci_iomap(dev, 0, 0);
+	if (!io) {
+		dev_err(&dev->dev, "Failed to map pci card memory bar 0");
+		err = -EIO;
+		goto err_release_regions;
+	}
+
+	dma_io = pci_iomap(dev, 2, 0);
+	if (!dma_io) {
+		dev_err(&dev->dev, "Failed to map pci card memory bar 2");
+		err = -EIO;
+		goto err_unmap;
+	}
+
+	net_dev = alloc_etherdev(sizeof(struct ec_bhf_priv));
+	if (net_dev == 0) {
+		err = -ENOMEM;
+		goto err_unmap_dma_io;
+	}
+
+	pci_set_drvdata(dev, net_dev);
+	SET_NETDEV_DEV(net_dev, &dev->dev);
+
+	net_dev->features = 0;
+	net_dev->flags |= IFF_NOARP;
+
+	net_dev->netdev_ops = &ec_bhf_netdev_ops;
+
+	priv = netdev_priv(net_dev);
+	priv->net_dev = net_dev;
+	priv->io = io;
+	priv->dma_io = dma_io;
+	priv->dev = dev;
+
+	err = ec_bhf_setup_offsets(priv);
+	if (err < 0)
+		goto err_free_net_dev;
+
+	memcpy_fromio(net_dev->dev_addr, priv->mii_io + MII_MAC_ADDR, 6);
+
+	dev_dbg(&dev->dev, "CX5020 Ethercat master address: %pM\n",
+		net_dev->dev_addr);
+
+	err = register_netdev(net_dev);
+	if (err < 0)
+		goto err_free_net_dev;
+
+	return 0;
+
+err_free_net_dev:
+	free_netdev(net_dev);
+err_unmap_dma_io:
+	pci_iounmap(dev, dma_io);
+err_unmap:
+	pci_iounmap(dev, io);
+err_release_regions:
+	pci_release_regions(dev);
+err_disable_dev:
+	pci_clear_master(dev);
+	pci_disable_device(dev);
+
+	return err;
+}
+
+static void ec_bhf_remove(struct pci_dev *dev)
+{
+	struct net_device *net_dev = pci_get_drvdata(dev);
+	struct ec_bhf_priv *priv = netdev_priv(net_dev);
+
+	unregister_netdev(net_dev);
+	free_netdev(net_dev);
+
+	pci_iounmap(dev, priv->dma_io);
+	pci_iounmap(dev, priv->io);
+	pci_release_regions(dev);
+	pci_clear_master(dev);
+	pci_disable_device(dev);
+}
+
+static struct pci_driver pci_driver = {
+	.name		= "ec_bhf",
+	.id_table	= ids,
+	.probe		= ec_bhf_probe,
+	.remove		= ec_bhf_remove,
+};
+
+static int __init ec_bhf_init(void)
+{
+	return pci_register_driver(&pci_driver);
+}
+
+static void __exit ec_bhf_exit(void)
+{
+	pci_unregister_driver(&pci_driver);
+}
+
+module_init(ec_bhf_init);
+module_exit(ec_bhf_exit);
+
+module_param(polling_frequency, long, S_IRUGO);
+MODULE_PARM_DESC(polling_frequency, "Polling timer frequency in ns");
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Dariusz Marcinkiewicz <reksio@newterm.pl>");
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index a18645407d21..dc19bc5dec77 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -4949,6 +4949,12 @@ static void be_eeh_resume(struct pci_dev *pdev)
 	if (status)
 		goto err;
 
+	/* On some BE3 FW versions, after a HW reset,
+	 * interrupts will remain disabled for each function.
+	 * So, explicitly enable interrupts
+	 */
+	be_intr_set(adapter, true);
+
 	/* tell fw we're ready to fire cmds */
 	status = be_cmd_fw_init(adapter);
 	if (status)
diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c
index b0c6050479eb..b78378cea5e3 100644
--- a/drivers/net/ethernet/jme.c
+++ b/drivers/net/ethernet/jme.c
@@ -1988,7 +1988,7 @@ jme_alloc_txdesc(struct jme_adapter *jme,
 	return idx;
 }
 
-static void
+static int
 jme_fill_tx_map(struct pci_dev *pdev,
 		struct txdesc *txdesc,
 		struct jme_buffer_info *txbi,
@@ -2005,6 +2005,9 @@ jme_fill_tx_map(struct pci_dev *pdev,
 				len,
 				PCI_DMA_TODEVICE);
 
+	if (unlikely(pci_dma_mapping_error(pdev, dmaaddr)))
+		return -EINVAL;
+
 	pci_dma_sync_single_for_device(pdev,
 				       dmaaddr,
 				       len,
@@ -2021,9 +2024,30 @@ jme_fill_tx_map(struct pci_dev *pdev,
 
 	txbi->mapping = dmaaddr;
 	txbi->len = len;
+	return 0;
 }
 
-static void
+static void jme_drop_tx_map(struct jme_adapter *jme, int startidx, int count)
+{
+	struct jme_ring *txring = &(jme->txring[0]);
+	struct jme_buffer_info *txbi = txring->bufinf, *ctxbi;
+	int mask = jme->tx_ring_mask;
+	int j;
+
+	for (j = 0 ; j < count ; j++) {
+		ctxbi = txbi + ((startidx + j + 2) & (mask));
+		pci_unmap_page(jme->pdev,
+				ctxbi->mapping,
+				ctxbi->len,
+				PCI_DMA_TODEVICE);
+
+				ctxbi->mapping = 0;
+				ctxbi->len = 0;
+	}
+
+}
+
+static int
 jme_map_tx_skb(struct jme_adapter *jme, struct sk_buff *skb, int idx)
 {
 	struct jme_ring *txring = &(jme->txring[0]);
@@ -2034,25 +2058,37 @@ jme_map_tx_skb(struct jme_adapter *jme, struct sk_buff *skb, int idx)
 	int mask = jme->tx_ring_mask;
 	const struct skb_frag_struct *frag;
 	u32 len;
+	int ret = 0;
 
 	for (i = 0 ; i < nr_frags ; ++i) {
 		frag = &skb_shinfo(skb)->frags[i];
 		ctxdesc = txdesc + ((idx + i + 2) & (mask));
 		ctxbi = txbi + ((idx + i + 2) & (mask));
 
-		jme_fill_tx_map(jme->pdev, ctxdesc, ctxbi,
+		ret = jme_fill_tx_map(jme->pdev, ctxdesc, ctxbi,
 				skb_frag_page(frag),
 				frag->page_offset, skb_frag_size(frag), hidma);
+		if (ret) {
+			jme_drop_tx_map(jme, idx, i);
+			goto out;
+		}
+
 	}
 
 	len = skb_is_nonlinear(skb) ? skb_headlen(skb) : skb->len;
 	ctxdesc = txdesc + ((idx + 1) & (mask));
 	ctxbi = txbi + ((idx + 1) & (mask));
-	jme_fill_tx_map(jme->pdev, ctxdesc, ctxbi, virt_to_page(skb->data),
+	ret = jme_fill_tx_map(jme->pdev, ctxdesc, ctxbi, virt_to_page(skb->data),
 			offset_in_page(skb->data), len, hidma);
+	if (ret)
+		jme_drop_tx_map(jme, idx, i);
+
+out:
+	return ret;
 
 }
 
+
 static int
 jme_tx_tso(struct sk_buff *skb, __le16 *mss, u8 *flags)
 {
@@ -2131,6 +2167,7 @@ jme_fill_tx_desc(struct jme_adapter *jme, struct sk_buff *skb, int idx)
 	struct txdesc *txdesc;
 	struct jme_buffer_info *txbi;
 	u8 flags;
+	int ret = 0;
 
 	txdesc = (struct txdesc *)txring->desc + idx;
 	txbi = txring->bufinf + idx;
@@ -2155,7 +2192,10 @@ jme_fill_tx_desc(struct jme_adapter *jme, struct sk_buff *skb, int idx)
 	if (jme_tx_tso(skb, &txdesc->desc1.mss, &flags))
 		jme_tx_csum(jme, skb, &flags);
 	jme_tx_vlan(skb, &txdesc->desc1.vlan, &flags);
-	jme_map_tx_skb(jme, skb, idx);
+	ret = jme_map_tx_skb(jme, skb, idx);
+	if (ret)
+		return ret;
+
 	txdesc->desc1.flags = flags;
 	/*
 	 * Set tx buffer info after telling NIC to send
@@ -2228,7 +2268,8 @@ jme_start_xmit(struct sk_buff *skb, struct net_device *netdev)
 		return NETDEV_TX_BUSY;
 	}
 
-	jme_fill_tx_desc(jme, skb, idx);
+	if (jme_fill_tx_desc(jme, skb, idx))
+		return NETDEV_TX_OK;
 
 	jwrite32(jme, JME_TXCS, jme->reg_txcs |
 				TXCS_SELECT_QUEUE0 |
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 78099eab7673..92d3249f63f1 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -1253,12 +1253,12 @@ static struct mlx4_cmd_info cmd_info[] = {
 	},
 	{
 		.opcode = MLX4_CMD_UPDATE_QP,
-		.has_inbox = false,
+		.has_inbox = true,
 		.has_outbox = false,
 		.out_is_imm = false,
 		.encode_slave_id = false,
 		.verify = NULL,
-		.wrapper = mlx4_CMD_EPERM_wrapper
+		.wrapper = mlx4_UPDATE_QP_wrapper
 	},
 	{
 		.opcode = MLX4_CMD_GET_OP_REQ,
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index f9c465101963..212cea440f90 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -1195,6 +1195,12 @@ int mlx4_QP_ATTACH_wrapper(struct mlx4_dev *dev, int slave,
 			   struct mlx4_cmd_mailbox *outbox,
 			   struct mlx4_cmd_info *cmd);
 
+int mlx4_UPDATE_QP_wrapper(struct mlx4_dev *dev, int slave,
+			   struct mlx4_vhcr *vhcr,
+			   struct mlx4_cmd_mailbox *inbox,
+			   struct mlx4_cmd_mailbox *outbox,
+			   struct mlx4_cmd_info *cmd);
+
 int mlx4_PROMISC_wrapper(struct mlx4_dev *dev, int slave,
 			 struct mlx4_vhcr *vhcr,
 			 struct mlx4_cmd_mailbox *inbox,
diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c
index 61d64ebffd56..fbd32af89c7c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx4/qp.c
@@ -389,6 +389,41 @@ err_icm:
 
 EXPORT_SYMBOL_GPL(mlx4_qp_alloc);
 
+#define MLX4_UPDATE_QP_SUPPORTED_ATTRS MLX4_UPDATE_QP_SMAC
+int mlx4_update_qp(struct mlx4_dev *dev, struct mlx4_qp *qp,
+		   enum mlx4_update_qp_attr attr,
+		   struct mlx4_update_qp_params *params)
+{
+	struct mlx4_cmd_mailbox *mailbox;
+	struct mlx4_update_qp_context *cmd;
+	u64 pri_addr_path_mask = 0;
+	int err = 0;
+
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox))
+		return PTR_ERR(mailbox);
+
+	cmd = (struct mlx4_update_qp_context *)mailbox->buf;
+
+	if (!attr || (attr & ~MLX4_UPDATE_QP_SUPPORTED_ATTRS))
+		return -EINVAL;
+
+	if (attr & MLX4_UPDATE_QP_SMAC) {
+		pri_addr_path_mask |= 1ULL << MLX4_UPD_QP_PATH_MASK_MAC_INDEX;
+		cmd->qp_context.pri_path.grh_mylmc = params->smac_index;
+	}
+
+	cmd->primary_addr_path_mask = cpu_to_be64(pri_addr_path_mask);
+
+	err = mlx4_cmd(dev, mailbox->dma, qp->qpn & 0xffffff, 0,
+		       MLX4_CMD_UPDATE_QP, MLX4_CMD_TIME_CLASS_A,
+		       MLX4_CMD_NATIVE);
+
+	mlx4_free_cmd_mailbox(dev, mailbox);
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx4_update_qp);
+
 void mlx4_qp_remove(struct mlx4_dev *dev, struct mlx4_qp *qp)
 {
 	struct mlx4_qp_table *qp_table = &mlx4_priv(dev)->qp_table;
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 1c3fdd4a1f7d..8f1254a79832 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -3895,6 +3895,60 @@ static int add_eth_header(struct mlx4_dev *dev, int slave,
 
 }
 
+#define MLX4_UPD_QP_PATH_MASK_SUPPORTED (1ULL << MLX4_UPD_QP_PATH_MASK_MAC_INDEX)
+int mlx4_UPDATE_QP_wrapper(struct mlx4_dev *dev, int slave,
+			   struct mlx4_vhcr *vhcr,
+			   struct mlx4_cmd_mailbox *inbox,
+			   struct mlx4_cmd_mailbox *outbox,
+			   struct mlx4_cmd_info *cmd_info)
+{
+	int err;
+	u32 qpn = vhcr->in_modifier & 0xffffff;
+	struct res_qp *rqp;
+	u64 mac;
+	unsigned port;
+	u64 pri_addr_path_mask;
+	struct mlx4_update_qp_context *cmd;
+	int smac_index;
+
+	cmd = (struct mlx4_update_qp_context *)inbox->buf;
+
+	pri_addr_path_mask = be64_to_cpu(cmd->primary_addr_path_mask);
+	if (cmd->qp_mask || cmd->secondary_addr_path_mask ||
+	    (pri_addr_path_mask & ~MLX4_UPD_QP_PATH_MASK_SUPPORTED))
+		return -EPERM;
+
+	/* Just change the smac for the QP */
+	err = get_res(dev, slave, qpn, RES_QP, &rqp);
+	if (err) {
+		mlx4_err(dev, "Updating qpn 0x%x for slave %d rejected\n", qpn, slave);
+		return err;
+	}
+
+	port = (rqp->sched_queue >> 6 & 1) + 1;
+	smac_index = cmd->qp_context.pri_path.grh_mylmc;
+	err = mac_find_smac_ix_in_slave(dev, slave, port,
+					smac_index, &mac);
+	if (err) {
+		mlx4_err(dev, "Failed to update qpn 0x%x, MAC is invalid. smac_ix: %d\n",
+			 qpn, smac_index);
+		goto err_mac;
+	}
+
+	err = mlx4_cmd(dev, inbox->dma,
+		       vhcr->in_modifier, 0,
+		       MLX4_CMD_UPDATE_QP, MLX4_CMD_TIME_CLASS_A,
+		       MLX4_CMD_NATIVE);
+	if (err) {
+		mlx4_err(dev, "Failed to update qpn on qpn 0x%x, command failed\n", qpn);
+		goto err_mac;
+	}
+
+err_mac:
+	put_res(dev, slave, qpn, RES_QP);
+	return err;
+}
+
 int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave,
 					 struct mlx4_vhcr *vhcr,
 					 struct mlx4_cmd_mailbox *inbox,
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
index 7b52a88923ef..f785d01c7d12 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
@@ -1719,22 +1719,6 @@ static inline u32 qlcnic_tx_avail(struct qlcnic_host_tx_ring *tx_ring)
 				tx_ring->producer;
 }
 
-static inline int qlcnic_set_real_num_queues(struct qlcnic_adapter *adapter,
-					     struct net_device *netdev)
-{
-	int err;
-
-	netdev->num_tx_queues = adapter->drv_tx_rings;
-	netdev->real_num_tx_queues = adapter->drv_tx_rings;
-
-	err = netif_set_real_num_tx_queues(netdev, adapter->drv_tx_rings);
-	if (err)
-		netdev_err(netdev, "failed to set %d Tx queues\n",
-			   adapter->drv_tx_rings);
-
-	return err;
-}
-
 struct qlcnic_nic_template {
 	int (*config_bridged_mode) (struct qlcnic_adapter *, u32);
 	int (*config_led) (struct qlcnic_adapter *, u32, u32);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index 0bc914859e38..7e55e88a81bf 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -2206,6 +2206,31 @@ static void qlcnic_82xx_set_mac_filter_count(struct qlcnic_adapter *adapter)
 	ahw->max_uc_count = count;
 }
 
+static int qlcnic_set_real_num_queues(struct qlcnic_adapter *adapter,
+				      u8 tx_queues, u8 rx_queues)
+{
+	struct net_device *netdev = adapter->netdev;
+	int err = 0;
+
+	if (tx_queues) {
+		err = netif_set_real_num_tx_queues(netdev, tx_queues);
+		if (err) {
+			netdev_err(netdev, "failed to set %d Tx queues\n",
+				   tx_queues);
+			return err;
+		}
+	}
+
+	if (rx_queues) {
+		err = netif_set_real_num_rx_queues(netdev, rx_queues);
+		if (err)
+			netdev_err(netdev, "failed to set %d Rx queues\n",
+				   rx_queues);
+	}
+
+	return err;
+}
+
 int
 qlcnic_setup_netdev(struct qlcnic_adapter *adapter, struct net_device *netdev,
 		    int pci_using_dac)
@@ -2269,7 +2294,8 @@ qlcnic_setup_netdev(struct qlcnic_adapter *adapter, struct net_device *netdev,
 	netdev->priv_flags |= IFF_UNICAST_FLT;
 	netdev->irq = adapter->msix_entries[0].vector;
 
-	err = qlcnic_set_real_num_queues(adapter, netdev);
+	err = qlcnic_set_real_num_queues(adapter, adapter->drv_tx_rings,
+					 adapter->drv_sds_rings);
 	if (err)
 		return err;
 
@@ -2943,9 +2969,13 @@ static void qlcnic_dump_tx_rings(struct qlcnic_adapter *adapter)
 			    tx_ring->tx_stats.xmit_called,
 			    tx_ring->tx_stats.xmit_on,
 			    tx_ring->tx_stats.xmit_off);
+
+		if (tx_ring->crb_intr_mask)
+			netdev_info(netdev, "crb_intr_mask=%d\n",
+				    readl(tx_ring->crb_intr_mask));
+
 		netdev_info(netdev,
-			    "crb_intr_mask=%d, hw_producer=%d, sw_producer=%d sw_consumer=%d, hw_consumer=%d\n",
-			    readl(tx_ring->crb_intr_mask),
+			    "hw_producer=%d, sw_producer=%d sw_consumer=%d, hw_consumer=%d\n",
 			    readl(tx_ring->crb_cmd_producer),
 			    tx_ring->producer, tx_ring->sw_consumer,
 			    le32_to_cpu(*(tx_ring->hw_consumer)));
@@ -3978,12 +4008,21 @@ int qlcnic_validate_rings(struct qlcnic_adapter *adapter, __u32 ring_cnt,
 int qlcnic_setup_rings(struct qlcnic_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
+	u8 tx_rings, rx_rings;
 	int err;
 
 	if (test_bit(__QLCNIC_RESETTING, &adapter->state))
 		return -EBUSY;
 
+	tx_rings = adapter->drv_tss_rings;
+	rx_rings = adapter->drv_rss_rings;
+
 	netif_device_detach(netdev);
+
+	err = qlcnic_set_real_num_queues(adapter, tx_rings, rx_rings);
+	if (err)
+		goto done;
+
 	if (netif_running(netdev))
 		__qlcnic_down(adapter, netdev);
 
@@ -4003,7 +4042,17 @@ int qlcnic_setup_rings(struct qlcnic_adapter *adapter)
 		return err;
 	}
 
-	netif_set_real_num_tx_queues(netdev, adapter->drv_tx_rings);
+	/* Check if we need to update real_num_{tx|rx}_queues because
+	 * qlcnic_setup_intr() may change Tx/Rx rings size
+	 */
+	if ((tx_rings != adapter->drv_tx_rings) ||
+	    (rx_rings != adapter->drv_sds_rings)) {
+		err = qlcnic_set_real_num_queues(adapter,
+						 adapter->drv_tx_rings,
+						 adapter->drv_sds_rings);
+		if (err)
+			goto done;
+	}
 
 	if (qlcnic_83xx_check(adapter)) {
 		qlcnic_83xx_initialize_nic(adapter, 1);
diff --git a/drivers/net/ethernet/sfc/nic.c b/drivers/net/ethernet/sfc/nic.c
index 32d969e857f7..89b83e59e1dc 100644
--- a/drivers/net/ethernet/sfc/nic.c
+++ b/drivers/net/ethernet/sfc/nic.c
@@ -156,13 +156,15 @@ void efx_nic_fini_interrupt(struct efx_nic *efx)
 	efx->net_dev->rx_cpu_rmap = NULL;
 #endif
 
-	/* Disable MSI/MSI-X interrupts */
-	efx_for_each_channel(channel, efx)
-		free_irq(channel->irq, &efx->msi_context[channel->channel]);
-
-	/* Disable legacy interrupt */
-	if (efx->legacy_irq)
+	if (EFX_INT_MODE_USE_MSI(efx)) {
+		/* Disable MSI/MSI-X interrupts */
+		efx_for_each_channel(channel, efx)
+			free_irq(channel->irq,
+				 &efx->msi_context[channel->channel]);
+	} else {
+		/* Disable legacy interrupt */
 		free_irq(efx->legacy_irq, efx);
+	}
 }
 
 /* Register dump */
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index d940034acdd4..0f4841d2e8dc 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1704,7 +1704,7 @@ static int stmmac_open(struct net_device *dev)
 		if (ret) {
 			pr_err("%s: Cannot attach to PHY (error: %d)\n",
 			       __func__, ret);
-			goto phy_error;
+			return ret;
 		}
 	}
 
@@ -1779,8 +1779,6 @@ init_error:
 dma_desc_error:
 	if (priv->phydev)
 		phy_disconnect(priv->phydev);
-phy_error:
-	clk_disable_unprepare(priv->stmmac_clk);
 
 	return ret;
 }
diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c
index df8d383acf48..b9ac20f42651 100644
--- a/drivers/net/ethernet/sun/cassini.c
+++ b/drivers/net/ethernet/sun/cassini.c
@@ -246,7 +246,7 @@ static inline void cas_lock_tx(struct cas *cp)
 	int i;
 
 	for (i = 0; i < N_TX_RINGS; i++)
-		spin_lock(&cp->tx_lock[i]);
+		spin_lock_nested(&cp->tx_lock[i], i);
 }
 
 static inline void cas_lock_all(struct cas *cp)
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 36aa109416c4..c331b7ebc812 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -1871,18 +1871,13 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data,
 		mdio_node = of_find_node_by_phandle(be32_to_cpup(parp));
 		phyid = be32_to_cpup(parp+1);
 		mdio = of_find_device_by_node(mdio_node);
-
-		if (strncmp(mdio->name, "gpio", 4) == 0) {
-			/* GPIO bitbang MDIO driver attached */
-			struct mii_bus *bus = dev_get_drvdata(&mdio->dev);
-
-			snprintf(slave_data->phy_id, sizeof(slave_data->phy_id),
-				 PHY_ID_FMT, bus->id, phyid);
-		} else {
-			/* davinci MDIO driver attached */
-			snprintf(slave_data->phy_id, sizeof(slave_data->phy_id),
-				 PHY_ID_FMT, mdio->name, phyid);
+		of_node_put(mdio_node);
+		if (!mdio) {
+			pr_err("Missing mdio platform device\n");
+			return -EINVAL;
 		}
+		snprintf(slave_data->phy_id, sizeof(slave_data->phy_id),
+			 PHY_ID_FMT, mdio->name, phyid);
 
 		mac_addr = of_get_mac_address(slave_node);
 		if (mac_addr)
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index b0e2865a6810..d53e299ae1d9 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -458,8 +458,10 @@ static void macvlan_change_rx_flags(struct net_device *dev, int change)
 	struct macvlan_dev *vlan = netdev_priv(dev);
 	struct net_device *lowerdev = vlan->lowerdev;
 
-	if (change & IFF_ALLMULTI)
-		dev_set_allmulti(lowerdev, dev->flags & IFF_ALLMULTI ? 1 : -1);
+	if (dev->flags & IFF_UP) {
+		if (change & IFF_ALLMULTI)
+			dev_set_allmulti(lowerdev, dev->flags & IFF_ALLMULTI ? 1 : -1);
+	}
 }
 
 static void macvlan_set_mac_lists(struct net_device *dev)
@@ -515,6 +517,11 @@ static struct lock_class_key macvlan_netdev_addr_lock_key;
 #define MACVLAN_STATE_MASK \
 	((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT))
 
+static int macvlan_get_nest_level(struct net_device *dev)
+{
+	return ((struct macvlan_dev *)netdev_priv(dev))->nest_level;
+}
+
 static void macvlan_set_lockdep_class_one(struct net_device *dev,
 					  struct netdev_queue *txq,
 					  void *_unused)
@@ -525,8 +532,9 @@ static void macvlan_set_lockdep_class_one(struct net_device *dev,
 
 static void macvlan_set_lockdep_class(struct net_device *dev)
 {
-	lockdep_set_class(&dev->addr_list_lock,
-			  &macvlan_netdev_addr_lock_key);
+	lockdep_set_class_and_subclass(&dev->addr_list_lock,
+				       &macvlan_netdev_addr_lock_key,
+				       macvlan_get_nest_level(dev));
 	netdev_for_each_tx_queue(dev, macvlan_set_lockdep_class_one, NULL);
 }
 
@@ -721,6 +729,7 @@ static const struct net_device_ops macvlan_netdev_ops = {
 	.ndo_fdb_add		= macvlan_fdb_add,
 	.ndo_fdb_del		= macvlan_fdb_del,
 	.ndo_fdb_dump		= ndo_dflt_fdb_dump,
+	.ndo_get_lock_subclass  = macvlan_get_nest_level,
 };
 
 void macvlan_common_setup(struct net_device *dev)
@@ -849,6 +858,7 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
 	vlan->dev      = dev;
 	vlan->port     = port;
 	vlan->set_features = MACVLAN_FEATURES;
+	vlan->nest_level = dev_get_nest_level(lowerdev, netif_is_macvlan) + 1;
 
 	vlan->mode     = MACVLAN_MODE_VEPA;
 	if (data && data[IFLA_MACVLAN_MODE])
diff --git a/drivers/net/phy/mdio-gpio.c b/drivers/net/phy/mdio-gpio.c
index 9c4defdec67b..5f1a2250018f 100644
--- a/drivers/net/phy/mdio-gpio.c
+++ b/drivers/net/phy/mdio-gpio.c
@@ -215,6 +215,10 @@ static int mdio_gpio_probe(struct platform_device *pdev)
 	if (pdev->dev.of_node) {
 		pdata = mdio_gpio_of_get_data(pdev);
 		bus_id = of_alias_get_id(pdev->dev.of_node, "mdio-gpio");
+		if (bus_id < 0) {
+			dev_warn(&pdev->dev, "failed to get alias id\n");
+			bus_id = 0;
+		}
 	} else {
 		pdata = dev_get_platdata(&pdev->dev);
 		bus_id = pdev->id;
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index a972056b2249..3bc079a67a3d 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -715,7 +715,7 @@ void phy_state_machine(struct work_struct *work)
 	struct delayed_work *dwork = to_delayed_work(work);
 	struct phy_device *phydev =
 			container_of(dwork, struct phy_device, state_queue);
-	int needs_aneg = 0, do_suspend = 0;
+	bool needs_aneg = false, do_suspend = false, do_resume = false;
 	int err = 0;
 
 	mutex_lock(&phydev->lock);
@@ -727,7 +727,7 @@ void phy_state_machine(struct work_struct *work)
 	case PHY_PENDING:
 		break;
 	case PHY_UP:
-		needs_aneg = 1;
+		needs_aneg = true;
 
 		phydev->link_timeout = PHY_AN_TIMEOUT;
 
@@ -757,7 +757,7 @@ void phy_state_machine(struct work_struct *work)
 			phydev->adjust_link(phydev->attached_dev);
 
 		} else if (0 == phydev->link_timeout--)
-			needs_aneg = 1;
+			needs_aneg = true;
 		break;
 	case PHY_NOLINK:
 		err = phy_read_status(phydev);
@@ -791,7 +791,7 @@ void phy_state_machine(struct work_struct *work)
 			netif_carrier_on(phydev->attached_dev);
 		} else {
 			if (0 == phydev->link_timeout--)
-				needs_aneg = 1;
+				needs_aneg = true;
 		}
 
 		phydev->adjust_link(phydev->attached_dev);
@@ -827,7 +827,7 @@ void phy_state_machine(struct work_struct *work)
 			phydev->link = 0;
 			netif_carrier_off(phydev->attached_dev);
 			phydev->adjust_link(phydev->attached_dev);
-			do_suspend = 1;
+			do_suspend = true;
 		}
 		break;
 	case PHY_RESUMING:
@@ -876,6 +876,7 @@ void phy_state_machine(struct work_struct *work)
 			}
 			phydev->adjust_link(phydev->attached_dev);
 		}
+		do_resume = true;
 		break;
 	}
 
@@ -883,9 +884,10 @@ void phy_state_machine(struct work_struct *work)
 
 	if (needs_aneg)
 		err = phy_start_aneg(phydev);
-
-	if (do_suspend)
+	else if (do_suspend)
 		phy_suspend(phydev);
+	else if (do_resume)
+		phy_resume(phydev);
 
 	if (err < 0)
 		phy_error(phydev);
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 0ce606624296..4987a1c6dc52 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -614,8 +614,8 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 	err = phy_init_hw(phydev);
 	if (err)
 		phy_detach(phydev);
-
-	phy_resume(phydev);
+	else
+		phy_resume(phydev);
 
 	return err;
 }
diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c
index c9f3281506af..2e025ddcef21 100644
--- a/drivers/net/usb/cdc_mbim.c
+++ b/drivers/net/usb/cdc_mbim.c
@@ -120,6 +120,16 @@ static void cdc_mbim_unbind(struct usbnet *dev, struct usb_interface *intf)
 	cdc_ncm_unbind(dev, intf);
 }
 
+/* verify that the ethernet protocol is IPv4 or IPv6 */
+static bool is_ip_proto(__be16 proto)
+{
+	switch (proto) {
+	case htons(ETH_P_IP):
+	case htons(ETH_P_IPV6):
+		return true;
+	}
+	return false;
+}
 
 static struct sk_buff *cdc_mbim_tx_fixup(struct usbnet *dev, struct sk_buff *skb, gfp_t flags)
 {
@@ -128,6 +138,7 @@ static struct sk_buff *cdc_mbim_tx_fixup(struct usbnet *dev, struct sk_buff *skb
 	struct cdc_ncm_ctx *ctx = info->ctx;
 	__le32 sign = cpu_to_le32(USB_CDC_MBIM_NDP16_IPS_SIGN);
 	u16 tci = 0;
+	bool is_ip;
 	u8 *c;
 
 	if (!ctx)
@@ -137,25 +148,32 @@ static struct sk_buff *cdc_mbim_tx_fixup(struct usbnet *dev, struct sk_buff *skb
 		if (skb->len <= ETH_HLEN)
 			goto error;
 
+		/* Some applications using e.g. packet sockets will
+		 * bypass the VLAN acceleration and create tagged
+		 * ethernet frames directly.  We primarily look for
+		 * the accelerated out-of-band tag, but fall back if
+		 * required
+		 */
+		skb_reset_mac_header(skb);
+		if (vlan_get_tag(skb, &tci) < 0 && skb->len > VLAN_ETH_HLEN &&
+		    __vlan_get_tag(skb, &tci) == 0) {
+			is_ip = is_ip_proto(vlan_eth_hdr(skb)->h_vlan_encapsulated_proto);
+			skb_pull(skb, VLAN_ETH_HLEN);
+		} else {
+			is_ip = is_ip_proto(eth_hdr(skb)->h_proto);
+			skb_pull(skb, ETH_HLEN);
+		}
+
 		/* mapping VLANs to MBIM sessions:
 		 *   no tag     => IPS session <0>
 		 *   1 - 255    => IPS session <vlanid>
 		 *   256 - 511  => DSS session <vlanid - 256>
 		 *   512 - 4095 => unsupported, drop
 		 */
-		vlan_get_tag(skb, &tci);
-
 		switch (tci & 0x0f00) {
 		case 0x0000: /* VLAN ID 0 - 255 */
-			/* verify that datagram is IPv4 or IPv6 */
-			skb_reset_mac_header(skb);
-			switch (eth_hdr(skb)->h_proto) {
-			case htons(ETH_P_IP):
-			case htons(ETH_P_IPV6):
-				break;
-			default:
+			if (!is_ip)
 				goto error;
-			}
 			c = (u8 *)&sign;
 			c[3] = tci;
 			break;
@@ -169,7 +187,6 @@ static struct sk_buff *cdc_mbim_tx_fixup(struct usbnet *dev, struct sk_buff *skb
 				  "unsupported tci=0x%04x\n", tci);
 			goto error;
 		}
-		skb_pull(skb, ETH_HLEN);
 	}
 
 	spin_lock_bh(&ctx->mtx);
@@ -204,17 +221,23 @@ static void do_neigh_solicit(struct usbnet *dev, u8 *buf, u16 tci)
 		return;
 
 	/* need to send the NA on the VLAN dev, if any */
-	if (tci)
+	rcu_read_lock();
+	if (tci) {
 		netdev = __vlan_find_dev_deep(dev->net, htons(ETH_P_8021Q),
 					      tci);
-	else
+		if (!netdev) {
+			rcu_read_unlock();
+			return;
+		}
+	} else {
 		netdev = dev->net;
-	if (!netdev)
-		return;
+	}
+	dev_hold(netdev);
+	rcu_read_unlock();
 
 	in6_dev = in6_dev_get(netdev);
 	if (!in6_dev)
-		return;
+		goto out;
 	is_router = !!in6_dev->cnf.forwarding;
 	in6_dev_put(in6_dev);
 
@@ -224,6 +247,8 @@ static void do_neigh_solicit(struct usbnet *dev, u8 *buf, u16 tci)
 				 true /* solicited */,
 				 false /* override */,
 				 true /* inc_opt */);
+out:
+	dev_put(netdev);
 }
 
 static bool is_neigh_solicit(u8 *buf, size_t len)
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_main.c b/drivers/net/wireless/ath/ath9k/htc_drv_main.c
index f46cd0250e48..5627917c5ff7 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_main.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_main.c
@@ -95,8 +95,10 @@ static void ath9k_htc_vif_iter(void *data, u8 *mac, struct ieee80211_vif *vif)
 
 	if ((vif->type == NL80211_IFTYPE_AP ||
 	     vif->type == NL80211_IFTYPE_MESH_POINT) &&
-	    bss_conf->enable_beacon)
+	    bss_conf->enable_beacon) {
 		priv->reconfig_beacon = true;
+		priv->rearm_ani = true;
+	}
 
 	if (bss_conf->assoc) {
 		priv->rearm_ani = true;
@@ -257,6 +259,7 @@ static int ath9k_htc_set_channel(struct ath9k_htc_priv *priv,
 
 	ath9k_htc_ps_wakeup(priv);
 
+	ath9k_htc_stop_ani(priv);
 	del_timer_sync(&priv->tx.cleanup_timer);
 	ath9k_htc_tx_drain(priv);
 
diff --git a/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c b/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c
index afb3d15e38ff..be1985296bdc 100644
--- a/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c
+++ b/drivers/net/wireless/brcm80211/brcmfmac/wl_cfg80211.c
@@ -4948,7 +4948,7 @@ static int brcmf_enable_bw40_2g(struct brcmf_if *ifp)
 	if (!err) {
 		/* only set 2G bandwidth using bw_cap command */
 		band_bwcap.band = cpu_to_le32(WLC_BAND_2G);
-		band_bwcap.bw_cap = cpu_to_le32(WLC_BW_40MHZ_BIT);
+		band_bwcap.bw_cap = cpu_to_le32(WLC_BW_CAP_40MHZ);
 		err = brcmf_fil_iovar_data_set(ifp, "bw_cap", &band_bwcap,
 					       sizeof(band_bwcap));
 	} else {
diff --git a/drivers/net/wireless/iwlwifi/mvm/coex.c b/drivers/net/wireless/iwlwifi/mvm/coex.c
index fa858d548d13..0489314425cb 100644
--- a/drivers/net/wireless/iwlwifi/mvm/coex.c
+++ b/drivers/net/wireless/iwlwifi/mvm/coex.c
@@ -611,14 +611,14 @@ int iwl_send_bt_init_conf(struct iwl_mvm *mvm)
 		bt_cmd->flags |= cpu_to_le32(BT_COEX_SYNC2SCO);
 
 	if (IWL_MVM_BT_COEX_CORUNNING) {
-		bt_cmd->valid_bit_msk = cpu_to_le32(BT_VALID_CORUN_LUT_20 |
-						    BT_VALID_CORUN_LUT_40);
+		bt_cmd->valid_bit_msk |= cpu_to_le32(BT_VALID_CORUN_LUT_20 |
+						     BT_VALID_CORUN_LUT_40);
 		bt_cmd->flags |= cpu_to_le32(BT_COEX_CORUNNING);
 	}
 
 	if (IWL_MVM_BT_COEX_MPLUT) {
 		bt_cmd->flags |= cpu_to_le32(BT_COEX_MPLUT);
-		bt_cmd->valid_bit_msk = cpu_to_le32(BT_VALID_MULTI_PRIO_LUT);
+		bt_cmd->valid_bit_msk |= cpu_to_le32(BT_VALID_MULTI_PRIO_LUT);
 	}
 
 	if (mvm->cfg->bt_shared_single_ant)
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h b/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h
index 9426905de6b2..d73a89ecd78a 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h
+++ b/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h
@@ -183,9 +183,9 @@ enum iwl_scan_type {
  *	this number of packets were received (typically 1)
  * @passive2active: is auto switching from passive to active during scan allowed
  * @rxchain_sel_flags: RXON_RX_CHAIN_*
- * @max_out_time: in usecs, max out of serving channel time
+ * @max_out_time: in TUs, max out of serving channel time
  * @suspend_time: how long to pause scan when returning to service channel:
- *	bits 0-19: beacon interal in usecs (suspend before executing)
+ *	bits 0-19: beacon interal in TUs (suspend before executing)
  *	bits 20-23: reserved
  *	bits 24-31: number of beacons (suspend between channels)
  * @rxon_flags: RXON_FLG_*
@@ -383,8 +383,8 @@ enum scan_framework_client {
  * @quiet_plcp_th:	quiet channel num of packets threshold
  * @good_CRC_th:	passive to active promotion threshold
  * @rx_chain:		RXON rx chain.
- * @max_out_time:	max uSec to be out of assoceated channel
- * @suspend_time:	pause scan this long when returning to service channel
+ * @max_out_time:	max TUs to be out of assoceated channel
+ * @suspend_time:	pause scan this TUs when returning to service channel
  * @flags:		RXON flags
  * @filter_flags:	RXONfilter
  * @tx_cmd:		tx command for active scan; for 2GHz and for 5GHz.
diff --git a/drivers/net/wireless/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
index f0cebf12c7b8..b41dc84e9431 100644
--- a/drivers/net/wireless/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/iwlwifi/mvm/mac80211.c
@@ -1007,7 +1007,7 @@ static void iwl_mvm_mc_iface_iterator(void *_data, u8 *mac,
 	memcpy(cmd->bssid, vif->bss_conf.bssid, ETH_ALEN);
 	len = roundup(sizeof(*cmd) + cmd->count * ETH_ALEN, 4);
 
-	ret = iwl_mvm_send_cmd_pdu(mvm, MCAST_FILTER_CMD, CMD_SYNC, len, cmd);
+	ret = iwl_mvm_send_cmd_pdu(mvm, MCAST_FILTER_CMD, CMD_ASYNC, len, cmd);
 	if (ret)
 		IWL_ERR(mvm, "mcast filter cmd error. ret=%d\n", ret);
 }
@@ -1023,7 +1023,7 @@ static void iwl_mvm_recalc_multicast(struct iwl_mvm *mvm)
 	if (WARN_ON_ONCE(!mvm->mcast_filter_cmd))
 		return;
 
-	ieee80211_iterate_active_interfaces(
+	ieee80211_iterate_active_interfaces_atomic(
 		mvm->hw, IEEE80211_IFACE_ITER_NORMAL,
 		iwl_mvm_mc_iface_iterator, &iter_data);
 }
@@ -1807,6 +1807,11 @@ static int iwl_mvm_mac_sched_scan_start(struct ieee80211_hw *hw,
 
 	mutex_lock(&mvm->mutex);
 
+	if (!iwl_mvm_is_idle(mvm)) {
+		ret = -EBUSY;
+		goto out;
+	}
+
 	switch (mvm->scan_status) {
 	case IWL_MVM_SCAN_OS:
 		IWL_DEBUG_SCAN(mvm, "Stopping previous scan for sched_scan\n");
diff --git a/drivers/net/wireless/iwlwifi/mvm/mvm.h b/drivers/net/wireless/iwlwifi/mvm/mvm.h
index d564233a65da..f1ec0986c3c9 100644
--- a/drivers/net/wireless/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/iwlwifi/mvm/mvm.h
@@ -1003,6 +1003,9 @@ static inline bool iwl_mvm_vif_low_latency(struct iwl_mvm_vif *mvmvif)
 	return mvmvif->low_latency;
 }
 
+/* Assoc status */
+bool iwl_mvm_is_idle(struct iwl_mvm *mvm);
+
 /* Thermal management and CT-kill */
 void iwl_mvm_tt_tx_backoff(struct iwl_mvm *mvm, u32 backoff);
 void iwl_mvm_tt_handler(struct iwl_mvm *mvm);
diff --git a/drivers/net/wireless/iwlwifi/mvm/rs.c b/drivers/net/wireless/iwlwifi/mvm/rs.c
index 9f52c5b3f0ec..e1c838899363 100644
--- a/drivers/net/wireless/iwlwifi/mvm/rs.c
+++ b/drivers/net/wireless/iwlwifi/mvm/rs.c
@@ -1010,7 +1010,7 @@ static void rs_tx_status(void *mvm_r, struct ieee80211_supported_band *sband,
 		return;
 	}
 
-#ifdef CPTCFG_MAC80211_DEBUGFS
+#ifdef CONFIG_MAC80211_DEBUGFS
 	/* Disable last tx check if we are debugging with fixed rate */
 	if (lq_sta->dbg_fixed_rate) {
 		IWL_DEBUG_RATE(mvm, "Fixed rate. avoid rate scaling\n");
diff --git a/drivers/net/wireless/iwlwifi/mvm/scan.c b/drivers/net/wireless/iwlwifi/mvm/scan.c
index c91dc8498852..c28de54c75d4 100644
--- a/drivers/net/wireless/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/iwlwifi/mvm/scan.c
@@ -277,51 +277,22 @@ static void iwl_mvm_scan_calc_params(struct iwl_mvm *mvm,
 					    IEEE80211_IFACE_ITER_NORMAL,
 					    iwl_mvm_scan_condition_iterator,
 					    &global_bound);
-	/*
-	 * Under low latency traffic passive scan is fragmented meaning
-	 * that dwell on a particular channel will be fragmented. Each fragment
-	 * dwell time is 20ms and fragments period is 105ms. Skipping to next
-	 * channel will be delayed by the same period - 105ms. So suspend_time
-	 * parameter describing both fragments and channels skipping periods is
-	 * set to 105ms. This value is chosen so that overall passive scan
-	 * duration will not be too long. Max_out_time in this case is set to
-	 * 70ms, so for active scanning operating channel will be left for 70ms
-	 * while for passive still for 20ms (fragment dwell).
-	 */
-	if (global_bound) {
-		if (!iwl_mvm_low_latency(mvm)) {
-			params->suspend_time = ieee80211_tu_to_usec(100);
-			params->max_out_time = ieee80211_tu_to_usec(600);
-		} else {
-			params->suspend_time = ieee80211_tu_to_usec(105);
-			/* P2P doesn't support fragmented passive scan, so
-			 * configure max_out_time to be at least longest dwell
-			 * time for passive scan.
-			 */
-			if (vif->type == NL80211_IFTYPE_STATION && !vif->p2p) {
-				params->max_out_time = ieee80211_tu_to_usec(70);
-				params->passive_fragmented = true;
-			} else {
-				u32 passive_dwell;
 
-				/*
-				 * Use band G so that passive channel dwell time
-				 * will be assigned with maximum value.
-				 */
-				band = IEEE80211_BAND_2GHZ;
-				passive_dwell = iwl_mvm_get_passive_dwell(band);
-				params->max_out_time =
-					ieee80211_tu_to_usec(passive_dwell);
-			}
-		}
+	if (!global_bound)
+		goto not_bound;
+
+	params->suspend_time = 100;
+	params->max_out_time = 600;
+
+	if (iwl_mvm_low_latency(mvm)) {
+		params->suspend_time = 250;
+		params->max_out_time = 250;
 	}
 
+not_bound:
+
 	for (band = IEEE80211_BAND_2GHZ; band < IEEE80211_NUM_BANDS; band++) {
-		if (params->passive_fragmented)
-			params->dwell[band].passive = 20;
-		else
-			params->dwell[band].passive =
-				iwl_mvm_get_passive_dwell(band);
+		params->dwell[band].passive = iwl_mvm_get_passive_dwell(band);
 		params->dwell[band].active = iwl_mvm_get_active_dwell(band,
 								      n_ssids);
 	}
@@ -761,7 +732,7 @@ int iwl_mvm_config_sched_scan(struct iwl_mvm *mvm,
 	int band_2ghz = mvm->nvm_data->bands[IEEE80211_BAND_2GHZ].n_channels;
 	int band_5ghz = mvm->nvm_data->bands[IEEE80211_BAND_5GHZ].n_channels;
 	int head = 0;
-	int tail = band_2ghz + band_5ghz;
+	int tail = band_2ghz + band_5ghz - 1;
 	u32 ssid_bitmap;
 	int cmd_len;
 	int ret;
diff --git a/drivers/net/wireless/iwlwifi/mvm/utils.c b/drivers/net/wireless/iwlwifi/mvm/utils.c
index d619851745a1..2180902266ae 100644
--- a/drivers/net/wireless/iwlwifi/mvm/utils.c
+++ b/drivers/net/wireless/iwlwifi/mvm/utils.c
@@ -644,3 +644,22 @@ bool iwl_mvm_low_latency(struct iwl_mvm *mvm)
 
 	return result;
 }
+
+static void iwl_mvm_idle_iter(void *_data, u8 *mac, struct ieee80211_vif *vif)
+{
+	bool *idle = _data;
+
+	if (!vif->bss_conf.idle)
+		*idle = false;
+}
+
+bool iwl_mvm_is_idle(struct iwl_mvm *mvm)
+{
+	bool idle = true;
+
+	ieee80211_iterate_active_interfaces_atomic(
+			mvm->hw, IEEE80211_IFACE_ITER_NORMAL,
+			iwl_mvm_idle_iter, &idle);
+
+	return idle;
+}
diff --git a/drivers/net/wireless/iwlwifi/pcie/trans.c b/drivers/net/wireless/iwlwifi/pcie/trans.c
index dcfd6d866d09..2365553f1ef7 100644
--- a/drivers/net/wireless/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/iwlwifi/pcie/trans.c
@@ -1749,6 +1749,10 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 	 * PCI Tx retries from interfering with C3 CPU state */
 	pci_write_config_byte(pdev, PCI_CFG_RETRY_TIMEOUT, 0x00);
 
+	trans->dev = &pdev->dev;
+	trans_pcie->pci_dev = pdev;
+	iwl_disable_interrupts(trans);
+
 	err = pci_enable_msi(pdev);
 	if (err) {
 		dev_err(&pdev->dev, "pci_enable_msi failed(0X%x)\n", err);
@@ -1760,8 +1764,6 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 		}
 	}
 
-	trans->dev = &pdev->dev;
-	trans_pcie->pci_dev = pdev;
 	trans->hw_rev = iwl_read32(trans, CSR_HW_REV);
 	trans->hw_id = (pdev->device << 16) + pdev->subsystem_device;
 	snprintf(trans->hw_id_str, sizeof(trans->hw_id_str),
@@ -1787,8 +1789,6 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 		goto out_pci_disable_msi;
 	}
 
-	trans_pcie->inta_mask = CSR_INI_SET_MASK;
-
 	if (iwl_pcie_alloc_ict(trans))
 		goto out_free_cmd_pool;
 
@@ -1800,6 +1800,8 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 		goto out_free_ict;
 	}
 
+	trans_pcie->inta_mask = CSR_INI_SET_MASK;
+
 	return trans;
 
 out_free_ict:
diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index 630a3fcf65bc..0d4a285cbd7e 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -226,7 +226,7 @@ int xenvif_map_frontend_rings(struct xenvif *vif,
 			      grant_ref_t rx_ring_ref);
 
 /* Check for SKBs from frontend and schedule backend processing */
-void xenvif_check_rx_xenvif(struct xenvif *vif);
+void xenvif_napi_schedule_or_enable_events(struct xenvif *vif);
 
 /* Prevent the device from generating any further traffic. */
 void xenvif_carrier_off(struct xenvif *vif);
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index ef05c5c49d41..20e9defa1060 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -75,32 +75,8 @@ static int xenvif_poll(struct napi_struct *napi, int budget)
 	work_done = xenvif_tx_action(vif, budget);
 
 	if (work_done < budget) {
-		int more_to_do = 0;
-		unsigned long flags;
-
-		/* It is necessary to disable IRQ before calling
-		 * RING_HAS_UNCONSUMED_REQUESTS. Otherwise we might
-		 * lose event from the frontend.
-		 *
-		 * Consider:
-		 *   RING_HAS_UNCONSUMED_REQUESTS
-		 *   <frontend generates event to trigger napi_schedule>
-		 *   __napi_complete
-		 *
-		 * This handler is still in scheduled state so the
-		 * event has no effect at all. After __napi_complete
-		 * this handler is descheduled and cannot get
-		 * scheduled again. We lose event in this case and the ring
-		 * will be completely stalled.
-		 */
-
-		local_irq_save(flags);
-
-		RING_FINAL_CHECK_FOR_REQUESTS(&vif->tx, more_to_do);
-		if (!more_to_do)
-			__napi_complete(napi);
-
-		local_irq_restore(flags);
+		napi_complete(napi);
+		xenvif_napi_schedule_or_enable_events(vif);
 	}
 
 	return work_done;
@@ -194,7 +170,7 @@ static void xenvif_up(struct xenvif *vif)
 	enable_irq(vif->tx_irq);
 	if (vif->tx_irq != vif->rx_irq)
 		enable_irq(vif->rx_irq);
-	xenvif_check_rx_xenvif(vif);
+	xenvif_napi_schedule_or_enable_events(vif);
 }
 
 static void xenvif_down(struct xenvif *vif)
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 76665405c5aa..7367208ee8cd 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -104,7 +104,7 @@ static inline unsigned long idx_to_kaddr(struct xenvif *vif,
 
 /* Find the containing VIF's structure from a pointer in pending_tx_info array
  */
-static inline struct xenvif* ubuf_to_vif(struct ubuf_info *ubuf)
+static inline struct xenvif *ubuf_to_vif(const struct ubuf_info *ubuf)
 {
 	u16 pending_idx = ubuf->desc;
 	struct pending_tx_info *temp =
@@ -323,6 +323,35 @@ static void xenvif_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb,
 }
 
 /*
+ * Find the grant ref for a given frag in a chain of struct ubuf_info's
+ * skb: the skb itself
+ * i: the frag's number
+ * ubuf: a pointer to an element in the chain. It should not be NULL
+ *
+ * Returns a pointer to the element in the chain where the page were found. If
+ * not found, returns NULL.
+ * See the definition of callback_struct in common.h for more details about
+ * the chain.
+ */
+static const struct ubuf_info *xenvif_find_gref(const struct sk_buff *const skb,
+						const int i,
+						const struct ubuf_info *ubuf)
+{
+	struct xenvif *foreign_vif = ubuf_to_vif(ubuf);
+
+	do {
+		u16 pending_idx = ubuf->desc;
+
+		if (skb_shinfo(skb)->frags[i].page.p ==
+		    foreign_vif->mmap_pages[pending_idx])
+			break;
+		ubuf = (struct ubuf_info *) ubuf->ctx;
+	} while (ubuf);
+
+	return ubuf;
+}
+
+/*
  * Prepare an SKB to be transmitted to the frontend.
  *
  * This function is responsible for allocating grant operations, meta
@@ -346,9 +375,8 @@ static int xenvif_gop_skb(struct sk_buff *skb,
 	int head = 1;
 	int old_meta_prod;
 	int gso_type;
-	struct ubuf_info *ubuf = skb_shinfo(skb)->destructor_arg;
-	grant_ref_t foreign_grefs[MAX_SKB_FRAGS];
-	struct xenvif *foreign_vif = NULL;
+	const struct ubuf_info *ubuf = skb_shinfo(skb)->destructor_arg;
+	const struct ubuf_info *const head_ubuf = ubuf;
 
 	old_meta_prod = npo->meta_prod;
 
@@ -386,19 +414,6 @@ static int xenvif_gop_skb(struct sk_buff *skb,
 	npo->copy_off = 0;
 	npo->copy_gref = req->gref;
 
-	if ((skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) &&
-		 (ubuf->callback == &xenvif_zerocopy_callback)) {
-		int i = 0;
-		foreign_vif = ubuf_to_vif(ubuf);
-
-		do {
-			u16 pending_idx = ubuf->desc;
-			foreign_grefs[i++] =
-				foreign_vif->pending_tx_info[pending_idx].req.gref;
-			ubuf = (struct ubuf_info *) ubuf->ctx;
-		} while (ubuf);
-	}
-
 	data = skb->data;
 	while (data < skb_tail_pointer(skb)) {
 		unsigned int offset = offset_in_page(data);
@@ -415,13 +430,60 @@ static int xenvif_gop_skb(struct sk_buff *skb,
 	}
 
 	for (i = 0; i < nr_frags; i++) {
+		/* This variable also signals whether foreign_gref has a real
+		 * value or not.
+		 */
+		struct xenvif *foreign_vif = NULL;
+		grant_ref_t foreign_gref;
+
+		if ((skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) &&
+			(ubuf->callback == &xenvif_zerocopy_callback)) {
+			const struct ubuf_info *const startpoint = ubuf;
+
+			/* Ideally ubuf points to the chain element which
+			 * belongs to this frag. Or if frags were removed from
+			 * the beginning, then shortly before it.
+			 */
+			ubuf = xenvif_find_gref(skb, i, ubuf);
+
+			/* Try again from the beginning of the list, if we
+			 * haven't tried from there. This only makes sense in
+			 * the unlikely event of reordering the original frags.
+			 * For injected local pages it's an unnecessary second
+			 * run.
+			 */
+			if (unlikely(!ubuf) && startpoint != head_ubuf)
+				ubuf = xenvif_find_gref(skb, i, head_ubuf);
+
+			if (likely(ubuf)) {
+				u16 pending_idx = ubuf->desc;
+
+				foreign_vif = ubuf_to_vif(ubuf);
+				foreign_gref = foreign_vif->pending_tx_info[pending_idx].req.gref;
+				/* Just a safety measure. If this was the last
+				 * element on the list, the for loop will
+				 * iterate again if a local page were added to
+				 * the end. Using head_ubuf here prevents the
+				 * second search on the chain. Or the original
+				 * frags changed order, but that's less likely.
+				 * In any way, ubuf shouldn't be NULL.
+				 */
+				ubuf = ubuf->ctx ?
+					(struct ubuf_info *) ubuf->ctx :
+					head_ubuf;
+			} else
+				/* This frag was a local page, added to the
+				 * array after the skb left netback.
+				 */
+				ubuf = head_ubuf;
+		}
 		xenvif_gop_frag_copy(vif, skb, npo,
 				     skb_frag_page(&skb_shinfo(skb)->frags[i]),
 				     skb_frag_size(&skb_shinfo(skb)->frags[i]),
 				     skb_shinfo(skb)->frags[i].page_offset,
 				     &head,
 				     foreign_vif,
-				     foreign_grefs[i]);
+				     foreign_vif ? foreign_gref : UINT_MAX);
 	}
 
 	return npo->meta_prod - old_meta_prod;
@@ -654,7 +716,7 @@ done:
 		notify_remote_via_irq(vif->rx_irq);
 }
 
-void xenvif_check_rx_xenvif(struct xenvif *vif)
+void xenvif_napi_schedule_or_enable_events(struct xenvif *vif)
 {
 	int more_to_do;
 
@@ -688,7 +750,7 @@ static void tx_credit_callback(unsigned long data)
 {
 	struct xenvif *vif = (struct xenvif *)data;
 	tx_add_credit(vif);
-	xenvif_check_rx_xenvif(vif);
+	xenvif_napi_schedule_or_enable_events(vif);
 }
 
 static void xenvif_tx_err(struct xenvif *vif,
diff --git a/drivers/of/base.c b/drivers/of/base.c
index 6d4ee22708c9..32e969d95319 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -1831,6 +1831,10 @@ int of_update_property(struct device_node *np, struct property *newprop)
 	if (!found)
 		return -ENODEV;
 
+	/* At early boot, bail out and defer setup to of_init() */
+	if (!of_kset)
+		return found ? 0 : -ENODEV;
+
 	/* Update the sysfs attribute */
 	sysfs_remove_bin_file(&np->kobj, &oldprop->attr);
 	__of_add_property_sysfs(np, newprop);
diff --git a/drivers/pci/host/pci-mvebu.c b/drivers/pci/host/pci-mvebu.c
index d3d1cfd51e09..e384e2534594 100644
--- a/drivers/pci/host/pci-mvebu.c
+++ b/drivers/pci/host/pci-mvebu.c
@@ -293,6 +293,58 @@ static int mvebu_pcie_hw_wr_conf(struct mvebu_pcie_port *port,
 	return PCIBIOS_SUCCESSFUL;
 }
 
+/*
+ * Remove windows, starting from the largest ones to the smallest
+ * ones.
+ */
+static void mvebu_pcie_del_windows(struct mvebu_pcie_port *port,
+				   phys_addr_t base, size_t size)
+{
+	while (size) {
+		size_t sz = 1 << (fls(size) - 1);
+
+		mvebu_mbus_del_window(base, sz);
+		base += sz;
+		size -= sz;
+	}
+}
+
+/*
+ * MBus windows can only have a power of two size, but PCI BARs do not
+ * have this constraint. Therefore, we have to split the PCI BAR into
+ * areas each having a power of two size. We start from the largest
+ * one (i.e highest order bit set in the size).
+ */
+static void mvebu_pcie_add_windows(struct mvebu_pcie_port *port,
+				   unsigned int target, unsigned int attribute,
+				   phys_addr_t base, size_t size,
+				   phys_addr_t remap)
+{
+	size_t size_mapped = 0;
+
+	while (size) {
+		size_t sz = 1 << (fls(size) - 1);
+		int ret;
+
+		ret = mvebu_mbus_add_window_remap_by_id(target, attribute, base,
+							sz, remap);
+		if (ret) {
+			dev_err(&port->pcie->pdev->dev,
+				"Could not create MBus window at 0x%x, size 0x%x: %d\n",
+				base, sz, ret);
+			mvebu_pcie_del_windows(port, base - size_mapped,
+					       size_mapped);
+			return;
+		}
+
+		size -= sz;
+		size_mapped += sz;
+		base += sz;
+		if (remap != MVEBU_MBUS_NO_REMAP)
+			remap += sz;
+	}
+}
+
 static void mvebu_pcie_handle_iobase_change(struct mvebu_pcie_port *port)
 {
 	phys_addr_t iobase;
@@ -304,8 +356,8 @@ static void mvebu_pcie_handle_iobase_change(struct mvebu_pcie_port *port)
 
 		/* If a window was configured, remove it */
 		if (port->iowin_base) {
-			mvebu_mbus_del_window(port->iowin_base,
-					      port->iowin_size);
+			mvebu_pcie_del_windows(port, port->iowin_base,
+					       port->iowin_size);
 			port->iowin_base = 0;
 			port->iowin_size = 0;
 		}
@@ -331,11 +383,11 @@ static void mvebu_pcie_handle_iobase_change(struct mvebu_pcie_port *port)
 	port->iowin_base = port->pcie->io.start + iobase;
 	port->iowin_size = ((0xFFF | ((port->bridge.iolimit & 0xF0) << 8) |
 			    (port->bridge.iolimitupper << 16)) -
-			    iobase);
+			    iobase) + 1;
 
-	mvebu_mbus_add_window_remap_by_id(port->io_target, port->io_attr,
-					  port->iowin_base, port->iowin_size,
-					  iobase);
+	mvebu_pcie_add_windows(port, port->io_target, port->io_attr,
+			       port->iowin_base, port->iowin_size,
+			       iobase);
 }
 
 static void mvebu_pcie_handle_membase_change(struct mvebu_pcie_port *port)
@@ -346,8 +398,8 @@ static void mvebu_pcie_handle_membase_change(struct mvebu_pcie_port *port)
 
 		/* If a window was configured, remove it */
 		if (port->memwin_base) {
-			mvebu_mbus_del_window(port->memwin_base,
-					      port->memwin_size);
+			mvebu_pcie_del_windows(port, port->memwin_base,
+					       port->memwin_size);
 			port->memwin_base = 0;
 			port->memwin_size = 0;
 		}
@@ -364,10 +416,11 @@ static void mvebu_pcie_handle_membase_change(struct mvebu_pcie_port *port)
 	port->memwin_base  = ((port->bridge.membase & 0xFFF0) << 16);
 	port->memwin_size  =
 		(((port->bridge.memlimit & 0xFFF0) << 16) | 0xFFFFF) -
-		port->memwin_base;
+		port->memwin_base + 1;
 
-	mvebu_mbus_add_window_by_id(port->mem_target, port->mem_attr,
-				    port->memwin_base, port->memwin_size);
+	mvebu_pcie_add_windows(port, port->mem_target, port->mem_attr,
+			       port->memwin_base, port->memwin_size,
+			       MVEBU_MBUS_NO_REMAP);
 }
 
 /*
@@ -743,14 +796,21 @@ static resource_size_t mvebu_pcie_align_resource(struct pci_dev *dev,
 
 	/*
 	 * On the PCI-to-PCI bridge side, the I/O windows must have at
-	 * least a 64 KB size and be aligned on their size, and the
-	 * memory windows must have at least a 1 MB size and be
-	 * aligned on their size
+	 * least a 64 KB size and the memory windows must have at
+	 * least a 1 MB size. Moreover, MBus windows need to have a
+	 * base address aligned on their size, and their size must be
+	 * a power of two. This means that if the BAR doesn't have a
+	 * power of two size, several MBus windows will actually be
+	 * created. We need to ensure that the biggest MBus window
+	 * (which will be the first one) is aligned on its size, which
+	 * explains the rounddown_pow_of_two() being done here.
 	 */
 	if (res->flags & IORESOURCE_IO)
-		return round_up(start, max_t(resource_size_t, SZ_64K, size));
+		return round_up(start, max_t(resource_size_t, SZ_64K,
+					     rounddown_pow_of_two(size)));
 	else if (res->flags & IORESOURCE_MEM)
-		return round_up(start, max_t(resource_size_t, SZ_1M, size));
+		return round_up(start, max_t(resource_size_t, SZ_1M,
+					     rounddown_pow_of_two(size)));
 	else
 		return start;
 }
diff --git a/drivers/pci/hotplug/shpchp_ctrl.c b/drivers/pci/hotplug/shpchp_ctrl.c
index 58499277903a..6efc2ec5e4db 100644
--- a/drivers/pci/hotplug/shpchp_ctrl.c
+++ b/drivers/pci/hotplug/shpchp_ctrl.c
@@ -282,8 +282,8 @@ static int board_added(struct slot *p_slot)
 		return WRONG_BUS_FREQUENCY;
 	}
 
-	bsp = ctrl->pci_dev->bus->cur_bus_speed;
-	msp = ctrl->pci_dev->bus->max_bus_speed;
+	bsp = ctrl->pci_dev->subordinate->cur_bus_speed;
+	msp = ctrl->pci_dev->subordinate->max_bus_speed;
 
 	/* Check if there are other slots or devices on the same bus */
 	if (!list_empty(&ctrl->pci_dev->subordinate->devices))
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 7325d43bf030..759475ef6ff3 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -3067,7 +3067,8 @@ int pci_wait_for_pending_transaction(struct pci_dev *dev)
 	if (!pci_is_pcie(dev))
 		return 1;
 
-	return pci_wait_for_pending(dev, PCI_EXP_DEVSTA, PCI_EXP_DEVSTA_TRPND);
+	return pci_wait_for_pending(dev, pci_pcie_cap(dev) + PCI_EXP_DEVSTA,
+				    PCI_EXP_DEVSTA_TRPND);
 }
 EXPORT_SYMBOL(pci_wait_for_pending_transaction);
 
@@ -3109,7 +3110,7 @@ static int pci_af_flr(struct pci_dev *dev, int probe)
 		return 0;
 
 	/* Wait for Transaction Pending bit clean */
-	if (pci_wait_for_pending(dev, PCI_AF_STATUS, PCI_AF_STATUS_TP))
+	if (pci_wait_for_pending(dev, pos + PCI_AF_STATUS, PCI_AF_STATUS_TP))
 		goto clear;
 
 	dev_err(&dev->dev, "transaction is not cleared; "
diff --git a/drivers/pinctrl/vt8500/pinctrl-wmt.c b/drivers/pinctrl/vt8500/pinctrl-wmt.c
index 9802b67040cc..2c61281bebd7 100644
--- a/drivers/pinctrl/vt8500/pinctrl-wmt.c
+++ b/drivers/pinctrl/vt8500/pinctrl-wmt.c
@@ -523,17 +523,6 @@ static int wmt_gpio_get_direction(struct gpio_chip *chip, unsigned offset)
 		return GPIOF_DIR_IN;
 }
 
-static int wmt_gpio_direction_input(struct gpio_chip *chip, unsigned offset)
-{
-	return pinctrl_gpio_direction_input(chip->base + offset);
-}
-
-static int wmt_gpio_direction_output(struct gpio_chip *chip, unsigned offset,
-				     int value)
-{
-	return pinctrl_gpio_direction_output(chip->base + offset);
-}
-
 static int wmt_gpio_get_value(struct gpio_chip *chip, unsigned offset)
 {
 	struct wmt_pinctrl_data *data = dev_get_drvdata(chip->dev);
@@ -568,6 +557,18 @@ static void wmt_gpio_set_value(struct gpio_chip *chip, unsigned offset,
 		wmt_clearbits(data, reg_data_out, BIT(bit));
 }
 
+static int wmt_gpio_direction_input(struct gpio_chip *chip, unsigned offset)
+{
+	return pinctrl_gpio_direction_input(chip->base + offset);
+}
+
+static int wmt_gpio_direction_output(struct gpio_chip *chip, unsigned offset,
+				     int value)
+{
+	wmt_gpio_set_value(chip, offset, value);
+	return pinctrl_gpio_direction_output(chip->base + offset);
+}
+
 static struct gpio_chip wmt_gpio_chip = {
 	.label = "gpio-wmt",
 	.owner = THIS_MODULE,
diff --git a/drivers/pnp/pnpbios/bioscalls.c b/drivers/pnp/pnpbios/bioscalls.c
index deb7f4bcdb7b..438d4c72c7b3 100644
--- a/drivers/pnp/pnpbios/bioscalls.c
+++ b/drivers/pnp/pnpbios/bioscalls.c
@@ -37,7 +37,7 @@ __visible struct {
  * kernel begins at offset 3GB...
  */
 
-asmlinkage void pnp_bios_callfunc(void);
+asmlinkage __visible void pnp_bios_callfunc(void);
 
 __asm__(".text			\n"
 	__ALIGN_STR "\n"
diff --git a/drivers/ptp/Kconfig b/drivers/ptp/Kconfig
index 6963bdf54175..6aea373547f6 100644
--- a/drivers/ptp/Kconfig
+++ b/drivers/ptp/Kconfig
@@ -6,6 +6,7 @@ menu "PTP clock support"
 
 config PTP_1588_CLOCK
 	tristate "PTP clock support"
+	depends on NET
 	select PPS
 	select NET_PTP_CLASSIFY
 	help
@@ -74,7 +75,7 @@ config DP83640_PHY
 config PTP_1588_CLOCK_PCH
 	tristate "Intel PCH EG20T as PTP clock"
 	depends on X86 || COMPILE_TEST
-	depends on HAS_IOMEM
+	depends on HAS_IOMEM && NET
 	select PTP_1588_CLOCK
 	help
 	  This driver adds support for using the PCH EG20T as a PTP
diff --git a/drivers/rtc/rtc-hym8563.c b/drivers/rtc/rtc-hym8563.c
index bd628a6f981d..e5f13c4310fe 100644
--- a/drivers/rtc/rtc-hym8563.c
+++ b/drivers/rtc/rtc-hym8563.c
@@ -569,6 +569,9 @@ static int hym8563_probe(struct i2c_client *client,
 	if (IS_ERR(hym8563->rtc))
 		return PTR_ERR(hym8563->rtc);
 
+	/* the hym8563 alarm only supports a minute accuracy */
+	hym8563->rtc->uie_unsupported = 1;
+
 #ifdef CONFIG_COMMON_CLK
 	hym8563_clkout_register_clk(hym8563);
 #endif
diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c
index 1b681427dde0..c341f855fadc 100644
--- a/drivers/scsi/scsi_transport_sas.c
+++ b/drivers/scsi/scsi_transport_sas.c
@@ -1621,8 +1621,6 @@ void sas_rphy_free(struct sas_rphy *rphy)
 	list_del(&rphy->list);
 	mutex_unlock(&sas_host->lock);
 
-	sas_bsg_remove(shost, rphy);
-
 	transport_destroy_device(dev);
 
 	put_device(dev);
@@ -1681,6 +1679,7 @@ sas_rphy_remove(struct sas_rphy *rphy)
 	}
 
 	sas_rphy_unlink(rphy);
+	sas_bsg_remove(NULL, rphy);
 	transport_remove_device(dev);
 	device_del(dev);
 }
diff --git a/drivers/sh/Makefile b/drivers/sh/Makefile
index fc67f564f02c..788ed9b59b4e 100644
--- a/drivers/sh/Makefile
+++ b/drivers/sh/Makefile
@@ -1,10 +1,12 @@
 #
 # Makefile for the SuperH specific drivers.
 #
-obj-y	:= intc/
+obj-$(CONFIG_SUPERH)			+= intc/
+obj-$(CONFIG_ARCH_SHMOBILE_LEGACY)	+= intc/
+ifneq ($(CONFIG_COMMON_CLK),y)
+obj-$(CONFIG_HAVE_CLK)			+= clk/
+endif
+obj-$(CONFIG_MAPLE)			+= maple/
+obj-$(CONFIG_SUPERHYWAY)		+= superhyway/
 
-obj-$(CONFIG_HAVE_CLK)		+= clk/
-obj-$(CONFIG_MAPLE)		+= maple/
-obj-$(CONFIG_SUPERHYWAY)	+= superhyway/
-
-obj-y				+= pm_runtime.o
+obj-y					+= pm_runtime.o
diff --git a/drivers/sh/pm_runtime.c b/drivers/sh/pm_runtime.c
index 8afa5a4589f2..10c65eb51f85 100644
--- a/drivers/sh/pm_runtime.c
+++ b/drivers/sh/pm_runtime.c
@@ -50,8 +50,25 @@ static struct pm_clk_notifier_block platform_bus_notifier = {
 	.con_ids = { NULL, },
 };
 
+static bool default_pm_on;
+
 static int __init sh_pm_runtime_init(void)
 {
+	if (IS_ENABLED(CONFIG_ARCH_SHMOBILE_MULTI)) {
+		if (!of_machine_is_compatible("renesas,emev2") &&
+		    !of_machine_is_compatible("renesas,r7s72100") &&
+		    !of_machine_is_compatible("renesas,r8a73a4") &&
+		    !of_machine_is_compatible("renesas,r8a7740") &&
+		    !of_machine_is_compatible("renesas,r8a7778") &&
+		    !of_machine_is_compatible("renesas,r8a7779") &&
+		    !of_machine_is_compatible("renesas,r8a7790") &&
+		    !of_machine_is_compatible("renesas,r8a7791") &&
+		    !of_machine_is_compatible("renesas,sh7372") &&
+		    !of_machine_is_compatible("renesas,sh73a0"))
+			return 0;
+	}
+
+	default_pm_on = true;
 	pm_clk_add_notifier(&platform_bus_type, &platform_bus_notifier);
 	return 0;
 }
@@ -59,7 +76,8 @@ core_initcall(sh_pm_runtime_init);
 
 static int __init sh_pm_runtime_late_init(void)
 {
-	pm_genpd_poweroff_unused();
+	if (default_pm_on)
+		pm_genpd_poweroff_unused();
 	return 0;
 }
 late_initcall(sh_pm_runtime_late_init);
diff --git a/drivers/spi/spi-pxa2xx-dma.c b/drivers/spi/spi-pxa2xx-dma.c
index 713af4806f26..f6759dc0153b 100644
--- a/drivers/spi/spi-pxa2xx-dma.c
+++ b/drivers/spi/spi-pxa2xx-dma.c
@@ -29,18 +29,6 @@ static int pxa2xx_spi_map_dma_buffer(struct driver_data *drv_data,
 	struct sg_table *sgt;
 	void *buf, *pbuf;
 
-	/*
-	 * Some DMA controllers have problems transferring buffers that are
-	 * not multiple of 4 bytes. So we truncate the transfer so that it
-	 * is suitable for such controllers, and handle the trailing bytes
-	 * manually after the DMA completes.
-	 *
-	 * REVISIT: It would be better if this information could be
-	 * retrieved directly from the DMA device in a similar way than
-	 * ->copy_align etc. is done.
-	 */
-	len = ALIGN(drv_data->len, 4);
-
 	if (dir == DMA_TO_DEVICE) {
 		dmadev = drv_data->tx_chan->device->dev;
 		sgt = &drv_data->tx_sgt;
@@ -144,12 +132,8 @@ static void pxa2xx_spi_dma_transfer_complete(struct driver_data *drv_data,
 		if (!error) {
 			pxa2xx_spi_unmap_dma_buffers(drv_data);
 
-			/* Handle the last bytes of unaligned transfer */
 			drv_data->tx += drv_data->tx_map_len;
-			drv_data->write(drv_data);
-
 			drv_data->rx += drv_data->rx_map_len;
-			drv_data->read(drv_data);
 
 			msg->actual_length += drv_data->len;
 			msg->state = pxa2xx_spi_next_transfer(drv_data);
diff --git a/drivers/spi/spi-qup.c b/drivers/spi/spi-qup.c
index b032e8885e24..78c66e3c53ed 100644
--- a/drivers/spi/spi-qup.c
+++ b/drivers/spi/spi-qup.c
@@ -734,7 +734,7 @@ static int spi_qup_remove(struct platform_device *pdev)
 	int ret;
 
 	ret = pm_runtime_get_sync(&pdev->dev);
-	if (ret)
+	if (ret < 0)
 		return ret;
 
 	ret = spi_qup_set_state(controller, QUP_STATE_RESET);
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 4eb9bf02996c..939edf473235 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -580,6 +580,7 @@ static void spi_set_cs(struct spi_device *spi, bool enable)
 		spi->master->set_cs(spi, !enable);
 }
 
+#ifdef CONFIG_HAS_DMA
 static int spi_map_buf(struct spi_master *master, struct device *dev,
 		       struct sg_table *sgt, void *buf, size_t len,
 		       enum dma_data_direction dir)
@@ -637,55 +638,12 @@ static void spi_unmap_buf(struct spi_master *master, struct device *dev,
 	}
 }
 
-static int spi_map_msg(struct spi_master *master, struct spi_message *msg)
+static int __spi_map_msg(struct spi_master *master, struct spi_message *msg)
 {
 	struct device *tx_dev, *rx_dev;
 	struct spi_transfer *xfer;
-	void *tmp;
-	unsigned int max_tx, max_rx;
 	int ret;
 
-	if (master->flags & (SPI_MASTER_MUST_RX | SPI_MASTER_MUST_TX)) {
-		max_tx = 0;
-		max_rx = 0;
-
-		list_for_each_entry(xfer, &msg->transfers, transfer_list) {
-			if ((master->flags & SPI_MASTER_MUST_TX) &&
-			    !xfer->tx_buf)
-				max_tx = max(xfer->len, max_tx);
-			if ((master->flags & SPI_MASTER_MUST_RX) &&
-			    !xfer->rx_buf)
-				max_rx = max(xfer->len, max_rx);
-		}
-
-		if (max_tx) {
-			tmp = krealloc(master->dummy_tx, max_tx,
-				       GFP_KERNEL | GFP_DMA);
-			if (!tmp)
-				return -ENOMEM;
-			master->dummy_tx = tmp;
-			memset(tmp, 0, max_tx);
-		}
-
-		if (max_rx) {
-			tmp = krealloc(master->dummy_rx, max_rx,
-				       GFP_KERNEL | GFP_DMA);
-			if (!tmp)
-				return -ENOMEM;
-			master->dummy_rx = tmp;
-		}
-
-		if (max_tx || max_rx) {
-			list_for_each_entry(xfer, &msg->transfers,
-					    transfer_list) {
-				if (!xfer->tx_buf)
-					xfer->tx_buf = master->dummy_tx;
-				if (!xfer->rx_buf)
-					xfer->rx_buf = master->dummy_rx;
-			}
-		}
-	}
-
 	if (!master->can_dma)
 		return 0;
 
@@ -742,6 +700,69 @@ static int spi_unmap_msg(struct spi_master *master, struct spi_message *msg)
 
 	return 0;
 }
+#else /* !CONFIG_HAS_DMA */
+static inline int __spi_map_msg(struct spi_master *master,
+				struct spi_message *msg)
+{
+	return 0;
+}
+
+static inline int spi_unmap_msg(struct spi_master *master,
+				struct spi_message *msg)
+{
+	return 0;
+}
+#endif /* !CONFIG_HAS_DMA */
+
+static int spi_map_msg(struct spi_master *master, struct spi_message *msg)
+{
+	struct spi_transfer *xfer;
+	void *tmp;
+	unsigned int max_tx, max_rx;
+
+	if (master->flags & (SPI_MASTER_MUST_RX | SPI_MASTER_MUST_TX)) {
+		max_tx = 0;
+		max_rx = 0;
+
+		list_for_each_entry(xfer, &msg->transfers, transfer_list) {
+			if ((master->flags & SPI_MASTER_MUST_TX) &&
+			    !xfer->tx_buf)
+				max_tx = max(xfer->len, max_tx);
+			if ((master->flags & SPI_MASTER_MUST_RX) &&
+			    !xfer->rx_buf)
+				max_rx = max(xfer->len, max_rx);
+		}
+
+		if (max_tx) {
+			tmp = krealloc(master->dummy_tx, max_tx,
+				       GFP_KERNEL | GFP_DMA);
+			if (!tmp)
+				return -ENOMEM;
+			master->dummy_tx = tmp;
+			memset(tmp, 0, max_tx);
+		}
+
+		if (max_rx) {
+			tmp = krealloc(master->dummy_rx, max_rx,
+				       GFP_KERNEL | GFP_DMA);
+			if (!tmp)
+				return -ENOMEM;
+			master->dummy_rx = tmp;
+		}
+
+		if (max_tx || max_rx) {
+			list_for_each_entry(xfer, &msg->transfers,
+					    transfer_list) {
+				if (!xfer->tx_buf)
+					xfer->tx_buf = master->dummy_tx;
+				if (!xfer->rx_buf)
+					xfer->rx_buf = master->dummy_rx;
+			}
+		}
+	}
+
+	return __spi_map_msg(master, msg);
+}
 
 /*
  * spi_transfer_one_message - Default implementation of transfer_one_message()
@@ -1151,7 +1172,6 @@ static int spi_master_initialize_queue(struct spi_master *master)
 {
 	int ret;
 
-	master->queued = true;
 	master->transfer = spi_queued_transfer;
 	if (!master->transfer_one_message)
 		master->transfer_one_message = spi_transfer_one_message;
@@ -1162,6 +1182,7 @@ static int spi_master_initialize_queue(struct spi_master *master)
 		dev_err(&master->dev, "problem initializing queue\n");
 		goto err_init_queue;
 	}
+	master->queued = true;
 	ret = spi_start_queue(master);
 	if (ret) {
 		dev_err(&master->dev, "problem starting queue\n");
@@ -1171,8 +1192,8 @@ static int spi_master_initialize_queue(struct spi_master *master)
 	return 0;
 
 err_start_queue:
-err_init_queue:
 	spi_destroy_queue(master);
+err_init_queue:
 	return ret;
 }
 
@@ -1756,7 +1777,7 @@ EXPORT_SYMBOL_GPL(spi_busnum_to_master);
  */
 int spi_setup(struct spi_device *spi)
 {
-	unsigned	bad_bits;
+	unsigned	bad_bits, ugly_bits;
 	int		status = 0;
 
 	/* check mode to prevent that DUAL and QUAD set at the same time
@@ -1776,6 +1797,15 @@ int spi_setup(struct spi_device *spi)
 	 * that aren't supported with their current master
 	 */
 	bad_bits = spi->mode & ~spi->master->mode_bits;
+	ugly_bits = bad_bits &
+		    (SPI_TX_DUAL | SPI_TX_QUAD | SPI_RX_DUAL | SPI_RX_QUAD);
+	if (ugly_bits) {
+		dev_warn(&spi->dev,
+			 "setup: ignoring unsupported mode bits %x\n",
+			 ugly_bits);
+		spi->mode &= ~ugly_bits;
+		bad_bits &= ~ugly_bits;
+	}
 	if (bad_bits) {
 		dev_err(&spi->dev, "setup: unsupported mode bits %x\n",
 			bad_bits);
diff --git a/drivers/staging/imx-drm/imx-drm-core.c b/drivers/staging/imx-drm/imx-drm-core.c
index 4144a75e5f71..c270c9ae6d27 100644
--- a/drivers/staging/imx-drm/imx-drm-core.c
+++ b/drivers/staging/imx-drm/imx-drm-core.c
@@ -517,7 +517,7 @@ int imx_drm_encoder_get_mux_id(struct device_node *node,
 		of_node_put(port);
 		if (port == imx_crtc->port) {
 			ret = of_graph_parse_endpoint(ep, &endpoint);
-			return ret ? ret : endpoint.id;
+			return ret ? ret : endpoint.port;
 		}
 	} while (ep);
 
@@ -675,6 +675,11 @@ static int imx_drm_platform_probe(struct platform_device *pdev)
 			if (!remote || !of_device_is_available(remote)) {
 				of_node_put(remote);
 				continue;
+			} else if (!of_device_is_available(remote->parent)) {
+				dev_warn(&pdev->dev, "parent device of %s is not available\n",
+					 remote->full_name);
+				of_node_put(remote);
+				continue;
 			}
 
 			ret = imx_drm_add_component(&pdev->dev, remote);
diff --git a/drivers/staging/imx-drm/imx-tve.c b/drivers/staging/imx-drm/imx-tve.c
index 575533f4fd64..a23f4f773146 100644
--- a/drivers/staging/imx-drm/imx-tve.c
+++ b/drivers/staging/imx-drm/imx-tve.c
@@ -582,7 +582,7 @@ static int imx_tve_bind(struct device *dev, struct device *master, void *data)
 	tve->dev = dev;
 	spin_lock_init(&tve->lock);
 
-	ddc_node = of_parse_phandle(np, "i2c-ddc-bus", 0);
+	ddc_node = of_parse_phandle(np, "ddc-i2c-bus", 0);
 	if (ddc_node) {
 		tve->ddc = of_find_i2c_adapter_by_node(ddc_node);
 		of_node_put(ddc_node);
diff --git a/drivers/staging/media/davinci_vpfe/vpfe_video.c b/drivers/staging/media/davinci_vpfe/vpfe_video.c
index 8c101cbbee97..acc8184c46cd 100644
--- a/drivers/staging/media/davinci_vpfe/vpfe_video.c
+++ b/drivers/staging/media/davinci_vpfe/vpfe_video.c
@@ -1247,9 +1247,18 @@ static int vpfe_stop_streaming(struct vb2_queue *vq)
 	struct vpfe_fh *fh = vb2_get_drv_priv(vq);
 	struct vpfe_video_device *video = fh->video;
 
-	if (!vb2_is_streaming(vq))
-		return 0;
 	/* release all active buffers */
+	if (video->cur_frm == video->next_frm) {
+		vb2_buffer_done(&video->cur_frm->vb, VB2_BUF_STATE_ERROR);
+	} else {
+		if (video->cur_frm != NULL)
+			vb2_buffer_done(&video->cur_frm->vb,
+					VB2_BUF_STATE_ERROR);
+		if (video->next_frm != NULL)
+			vb2_buffer_done(&video->next_frm->vb,
+					VB2_BUF_STATE_ERROR);
+	}
+
 	while (!list_empty(&video->dma_queue)) {
 		video->next_frm = list_entry(video->dma_queue.next,
 						struct vpfe_cap_buffer, list);
diff --git a/drivers/staging/media/sn9c102/sn9c102_devtable.h b/drivers/staging/media/sn9c102/sn9c102_devtable.h
index b3d2cc729657..4ba569258498 100644
--- a/drivers/staging/media/sn9c102/sn9c102_devtable.h
+++ b/drivers/staging/media/sn9c102/sn9c102_devtable.h
@@ -48,10 +48,8 @@ static const struct usb_device_id sn9c102_id_table[] = {
 	{ SN9C102_USB_DEVICE(0x0c45, 0x600d, BRIDGE_SN9C102), },
 /*	{ SN9C102_USB_DEVICE(0x0c45, 0x6011, BRIDGE_SN9C102), }, OV6650 */
 	{ SN9C102_USB_DEVICE(0x0c45, 0x6019, BRIDGE_SN9C102), },
-#endif
 	{ SN9C102_USB_DEVICE(0x0c45, 0x6024, BRIDGE_SN9C102), },
 	{ SN9C102_USB_DEVICE(0x0c45, 0x6025, BRIDGE_SN9C102), },
-#if !defined CONFIG_USB_GSPCA_SONIXB && !defined CONFIG_USB_GSPCA_SONIXB_MODULE
 	{ SN9C102_USB_DEVICE(0x0c45, 0x6028, BRIDGE_SN9C102), },
 	{ SN9C102_USB_DEVICE(0x0c45, 0x6029, BRIDGE_SN9C102), },
 	{ SN9C102_USB_DEVICE(0x0c45, 0x602a, BRIDGE_SN9C102), },
diff --git a/drivers/staging/rtl8723au/os_dep/os_intfs.c b/drivers/staging/rtl8723au/os_dep/os_intfs.c
index 57eca7a45672..4fe751f7c2bf 100644
--- a/drivers/staging/rtl8723au/os_dep/os_intfs.c
+++ b/drivers/staging/rtl8723au/os_dep/os_intfs.c
@@ -953,8 +953,6 @@ static int netdev_close(struct net_device *pnetdev)
 #endif /* CONFIG_8723AU_P2P */
 
 	rtw_scan_abort23a(padapter);
-	 /* set this at the end */
-	padapter->rtw_wdev->iftype = NL80211_IFTYPE_MONITOR;
 
 	RT_TRACE(_module_os_intfs_c_, _drv_info_, ("-871x_drv - drv_close\n"));
 	DBG_8723A("-871x_drv - drv_close, bup =%d\n", padapter->bup);
diff --git a/drivers/staging/rtl8723au/os_dep/usb_ops_linux.c b/drivers/staging/rtl8723au/os_dep/usb_ops_linux.c
index c49160e477d8..07e542e5d156 100644
--- a/drivers/staging/rtl8723au/os_dep/usb_ops_linux.c
+++ b/drivers/staging/rtl8723au/os_dep/usb_ops_linux.c
@@ -26,7 +26,7 @@ unsigned int ffaddr2pipehdl23a(struct dvobj_priv *pdvobj, u32 addr)
 	if (addr == RECV_BULK_IN_ADDR) {
 		pipe = usb_rcvbulkpipe(pusbd, pdvobj->RtInPipe[0]);
 	} else if (addr == RECV_INT_IN_ADDR) {
-		pipe = usb_rcvbulkpipe(pusbd, pdvobj->RtInPipe[1]);
+		pipe = usb_rcvintpipe(pusbd, pdvobj->RtInPipe[1]);
 	} else if (addr < HW_QUEUE_ENTRY) {
 		ep_num = pdvobj->Queue2Pipe[addr];
 		pipe = usb_sndbulkpipe(pusbd, ep_num);
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 78cab13bbb1b..46588c85d39b 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -1593,7 +1593,9 @@ int iscsit_process_nop_out(struct iscsi_conn *conn, struct iscsi_cmd *cmd,
 	 * Initiator is expecting a NopIN ping reply..
 	 */
 	if (hdr->itt != RESERVED_ITT) {
-		BUG_ON(!cmd);
+		if (!cmd)
+			return iscsit_add_reject(conn, ISCSI_REASON_PROTOCOL_ERROR,
+						(unsigned char *)hdr);
 
 		spin_lock_bh(&conn->cmd_lock);
 		list_add_tail(&cmd->i_conn_node, &conn->conn_cmd_list);
diff --git a/drivers/target/iscsi/iscsi_target_core.h b/drivers/target/iscsi/iscsi_target_core.h
index 6960f22909ae..302eb3b78715 100644
--- a/drivers/target/iscsi/iscsi_target_core.h
+++ b/drivers/target/iscsi/iscsi_target_core.h
@@ -775,6 +775,7 @@ struct iscsi_np {
 	int			np_ip_proto;
 	int			np_sock_type;
 	enum np_thread_state_table np_thread_state;
+	bool                    enabled;
 	enum iscsi_timer_flags_table np_login_timer_flags;
 	u32			np_exports;
 	enum np_flags_table	np_flags;
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index 8739b98f6f93..ca31fa1b8a4b 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -436,7 +436,7 @@ static int iscsi_login_zero_tsih_s2(
 		}
 		off = mrdsl % PAGE_SIZE;
 		if (!off)
-			return 0;
+			goto check_prot;
 
 		if (mrdsl < PAGE_SIZE)
 			mrdsl = PAGE_SIZE;
@@ -452,6 +452,31 @@ static int iscsi_login_zero_tsih_s2(
 				ISCSI_LOGIN_STATUS_NO_RESOURCES);
 			return -1;
 		}
+		/*
+		 * ISER currently requires that ImmediateData + Unsolicited
+		 * Data be disabled when protection / signature MRs are enabled.
+		 */
+check_prot:
+		if (sess->se_sess->sup_prot_ops &
+		   (TARGET_PROT_DOUT_STRIP | TARGET_PROT_DOUT_PASS |
+		    TARGET_PROT_DOUT_INSERT)) {
+
+			sprintf(buf, "ImmediateData=No");
+			if (iscsi_change_param_value(buf, conn->param_list, 0) < 0) {
+				iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
+						    ISCSI_LOGIN_STATUS_NO_RESOURCES);
+				return -1;
+			}
+
+			sprintf(buf, "InitialR2T=Yes");
+			if (iscsi_change_param_value(buf, conn->param_list, 0) < 0) {
+				iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
+						    ISCSI_LOGIN_STATUS_NO_RESOURCES);
+				return -1;
+			}
+			pr_debug("Forcing ImmediateData=No + InitialR2T=Yes for"
+				 " T10-PI enabled ISER session\n");
+		}
 	}
 
 	return 0;
@@ -984,6 +1009,7 @@ int iscsi_target_setup_login_socket(
 	}
 
 	np->np_transport = t;
+	np->enabled = true;
 	return 0;
 }
 
diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c
index eb96b20dc09e..ca1811858afd 100644
--- a/drivers/target/iscsi/iscsi_target_tpg.c
+++ b/drivers/target/iscsi/iscsi_target_tpg.c
@@ -184,6 +184,7 @@ static void iscsit_clear_tpg_np_login_thread(
 		return;
 	}
 
+	tpg_np->tpg_np->enabled = false;
 	iscsit_reset_np_thread(tpg_np->tpg_np, tpg_np, tpg, shutdown);
 }
 
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 65001e133670..26416c15d65c 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -798,10 +798,10 @@ int se_dev_set_emulate_write_cache(struct se_device *dev, int flag)
 		pr_err("emulate_write_cache not supported for pSCSI\n");
 		return -EINVAL;
 	}
-	if (dev->transport->get_write_cache) {
-		pr_warn("emulate_write_cache cannot be changed when underlying"
-			" HW reports WriteCacheEnabled, ignoring request\n");
-		return 0;
+	if (flag &&
+	    dev->transport->get_write_cache) {
+		pr_err("emulate_write_cache not supported for this device\n");
+		return -EINVAL;
 	}
 
 	dev->dev_attrib.emulate_write_cache = flag;
@@ -936,6 +936,10 @@ int se_dev_set_pi_prot_type(struct se_device *dev, int flag)
 		return 0;
 	}
 	if (!dev->transport->init_prot || !dev->transport->free_prot) {
+		/* 0 is only allowed value for non-supporting backends */
+		if (flag == 0)
+			return 0;
+
 		pr_err("DIF protection not supported by backend: %s\n",
 		       dev->transport->name);
 		return -ENOSYS;
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index d4b98690a736..789aa9eb0a1e 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -1113,6 +1113,7 @@ void transport_init_se_cmd(
 	init_completion(&cmd->cmd_wait_comp);
 	init_completion(&cmd->task_stop_comp);
 	spin_lock_init(&cmd->t_state_lock);
+	kref_init(&cmd->cmd_kref);
 	cmd->transport_state = CMD_T_DEV_ACTIVE;
 
 	cmd->se_tfo = tfo;
@@ -2357,7 +2358,6 @@ int target_get_sess_cmd(struct se_session *se_sess, struct se_cmd *se_cmd,
 	unsigned long flags;
 	int ret = 0;
 
-	kref_init(&se_cmd->cmd_kref);
 	/*
 	 * Add a second kref if the fabric caller is expecting to handle
 	 * fabric acknowledgement that requires two target_put_sess_cmd()
diff --git a/drivers/target/tcm_fc/tfc_cmd.c b/drivers/target/tcm_fc/tfc_cmd.c
index 01cf37f212c3..f5fd515b2bee 100644
--- a/drivers/target/tcm_fc/tfc_cmd.c
+++ b/drivers/target/tcm_fc/tfc_cmd.c
@@ -90,18 +90,18 @@ static void ft_free_cmd(struct ft_cmd *cmd)
 {
 	struct fc_frame *fp;
 	struct fc_lport *lport;
-	struct se_session *se_sess;
+	struct ft_sess *sess;
 
 	if (!cmd)
 		return;
-	se_sess = cmd->sess->se_sess;
+	sess = cmd->sess;
 	fp = cmd->req_frame;
 	lport = fr_dev(fp);
 	if (fr_seq(fp))
 		lport->tt.seq_release(fr_seq(fp));
 	fc_frame_free(fp);
-	percpu_ida_free(&se_sess->sess_tag_pool, cmd->se_cmd.map_tag);
-	ft_sess_put(cmd->sess);	/* undo get from lookup at recv */
+	percpu_ida_free(&sess->se_sess->sess_tag_pool, cmd->se_cmd.map_tag);
+	ft_sess_put(sess);	/* undo get from lookup at recv */
 }
 
 void ft_release_cmd(struct se_cmd *se_cmd)
diff --git a/drivers/xen/events/events_fifo.c b/drivers/xen/events/events_fifo.c
index 96109a9972b6..84b4bfb84344 100644
--- a/drivers/xen/events/events_fifo.c
+++ b/drivers/xen/events/events_fifo.c
@@ -66,7 +66,22 @@ static DEFINE_PER_CPU(struct evtchn_fifo_queue, cpu_queue);
 static event_word_t *event_array[MAX_EVENT_ARRAY_PAGES] __read_mostly;
 static unsigned event_array_pages __read_mostly;
 
+/*
+ * sync_set_bit() and friends must be unsigned long aligned on non-x86
+ * platforms.
+ */
+#if !defined(CONFIG_X86) && BITS_PER_LONG > 32
+
+#define BM(w) (unsigned long *)((unsigned long)w & ~0x7UL)
+#define EVTCHN_FIFO_BIT(b, w) \
+    (((unsigned long)w & 0x4UL) ? (EVTCHN_FIFO_ ##b + 32) : EVTCHN_FIFO_ ##b)
+
+#else
+
 #define BM(w) ((unsigned long *)(w))
+#define EVTCHN_FIFO_BIT(b, w) EVTCHN_FIFO_ ##b
+
+#endif
 
 static inline event_word_t *event_word_from_port(unsigned port)
 {
@@ -161,33 +176,38 @@ static void evtchn_fifo_bind_to_cpu(struct irq_info *info, unsigned cpu)
 static void evtchn_fifo_clear_pending(unsigned port)
 {
 	event_word_t *word = event_word_from_port(port);
-	sync_clear_bit(EVTCHN_FIFO_PENDING, BM(word));
+	sync_clear_bit(EVTCHN_FIFO_BIT(PENDING, word), BM(word));
 }
 
 static void evtchn_fifo_set_pending(unsigned port)
 {
 	event_word_t *word = event_word_from_port(port);
-	sync_set_bit(EVTCHN_FIFO_PENDING, BM(word));
+	sync_set_bit(EVTCHN_FIFO_BIT(PENDING, word), BM(word));
 }
 
 static bool evtchn_fifo_is_pending(unsigned port)
 {
 	event_word_t *word = event_word_from_port(port);
-	return sync_test_bit(EVTCHN_FIFO_PENDING, BM(word));
+	return sync_test_bit(EVTCHN_FIFO_BIT(PENDING, word), BM(word));
 }
 
 static bool evtchn_fifo_test_and_set_mask(unsigned port)
 {
 	event_word_t *word = event_word_from_port(port);
-	return sync_test_and_set_bit(EVTCHN_FIFO_MASKED, BM(word));
+	return sync_test_and_set_bit(EVTCHN_FIFO_BIT(MASKED, word), BM(word));
 }
 
 static void evtchn_fifo_mask(unsigned port)
 {
 	event_word_t *word = event_word_from_port(port);
-	sync_set_bit(EVTCHN_FIFO_MASKED, BM(word));
+	sync_set_bit(EVTCHN_FIFO_BIT(MASKED, word), BM(word));
 }
 
+static bool evtchn_fifo_is_masked(unsigned port)
+{
+	event_word_t *word = event_word_from_port(port);
+	return sync_test_bit(EVTCHN_FIFO_BIT(MASKED, word), BM(word));
+}
 /*
  * Clear MASKED, spinning if BUSY is set.
  */
@@ -211,7 +231,7 @@ static void evtchn_fifo_unmask(unsigned port)
 	BUG_ON(!irqs_disabled());
 
 	clear_masked(word);
-	if (sync_test_bit(EVTCHN_FIFO_PENDING, BM(word))) {
+	if (evtchn_fifo_is_pending(port)) {
 		struct evtchn_unmask unmask = { .port = port };
 		(void)HYPERVISOR_event_channel_op(EVTCHNOP_unmask, &unmask);
 	}
@@ -243,7 +263,7 @@ static void handle_irq_for_port(unsigned port)
 
 static void consume_one_event(unsigned cpu,
 			      struct evtchn_fifo_control_block *control_block,
-			      unsigned priority, uint32_t *ready)
+			      unsigned priority, unsigned long *ready)
 {
 	struct evtchn_fifo_queue *q = &per_cpu(cpu_queue, cpu);
 	uint32_t head;
@@ -273,10 +293,9 @@ static void consume_one_event(unsigned cpu,
 	 * copy of the ready word.
 	 */
 	if (head == 0)
-		clear_bit(priority, BM(ready));
+		clear_bit(priority, ready);
 
-	if (sync_test_bit(EVTCHN_FIFO_PENDING, BM(word))
-	    && !sync_test_bit(EVTCHN_FIFO_MASKED, BM(word)))
+	if (evtchn_fifo_is_pending(port) && !evtchn_fifo_is_masked(port))
 		handle_irq_for_port(port);
 
 	q->head[priority] = head;
@@ -285,7 +304,7 @@ static void consume_one_event(unsigned cpu,
 static void evtchn_fifo_handle_events(unsigned cpu)
 {
 	struct evtchn_fifo_control_block *control_block;
-	uint32_t ready;
+	unsigned long ready;
 	unsigned q;
 
 	control_block = per_cpu(cpu_control_block, cpu);
diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c
index 1c8c6cc6de30..4b0eff6da674 100644
--- a/fs/afs/cmservice.c
+++ b/fs/afs/cmservice.c
@@ -130,6 +130,15 @@ static void afs_cm_destructor(struct afs_call *call)
 {
 	_enter("");
 
+	/* Break the callbacks here so that we do it after the final ACK is
+	 * received.  The step number here must match the final number in
+	 * afs_deliver_cb_callback().
+	 */
+	if (call->unmarshall == 6) {
+		ASSERT(call->server && call->count && call->request);
+		afs_break_callbacks(call->server, call->count, call->request);
+	}
+
 	afs_put_server(call->server);
 	call->server = NULL;
 	kfree(call->buffer);
@@ -272,6 +281,16 @@ static int afs_deliver_cb_callback(struct afs_call *call, struct sk_buff *skb,
 		_debug("trailer");
 		if (skb->len != 0)
 			return -EBADMSG;
+
+		/* Record that the message was unmarshalled successfully so
+		 * that the call destructor can know do the callback breaking
+		 * work, even if the final ACK isn't received.
+		 *
+		 * If the step number changes, then afs_cm_destructor() must be
+		 * updated also.
+		 */
+		call->unmarshall++;
+	case 6:
 		break;
 	}
 
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index d2f91bd615a9..71d5982312f3 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -75,7 +75,7 @@ struct afs_call {
 	const struct afs_call_type *type;	/* type of call */
 	const struct afs_wait_mode *wait_mode;	/* completion wait mode */
 	wait_queue_head_t	waitq;		/* processes awaiting completion */
-	work_func_t		async_workfn;
+	void (*async_workfn)(struct afs_call *call); /* asynchronous work function */
 	struct work_struct	async_work;	/* asynchronous work processor */
 	struct work_struct	work;		/* actual work processor */
 	struct sk_buff_head	rx_queue;	/* received packets */
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index ef943df73b8c..03a3beb17004 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -25,7 +25,7 @@ static void afs_wake_up_call_waiter(struct afs_call *);
 static int afs_wait_for_call_to_complete(struct afs_call *);
 static void afs_wake_up_async_call(struct afs_call *);
 static int afs_dont_wait_for_call_to_complete(struct afs_call *);
-static void afs_process_async_call(struct work_struct *);
+static void afs_process_async_call(struct afs_call *);
 static void afs_rx_interceptor(struct sock *, unsigned long, struct sk_buff *);
 static int afs_deliver_cm_op_id(struct afs_call *, struct sk_buff *, bool);
 
@@ -58,6 +58,13 @@ static void afs_collect_incoming_call(struct work_struct *);
 static struct sk_buff_head afs_incoming_calls;
 static DECLARE_WORK(afs_collect_incoming_call_work, afs_collect_incoming_call);
 
+static void afs_async_workfn(struct work_struct *work)
+{
+	struct afs_call *call = container_of(work, struct afs_call, async_work);
+
+	call->async_workfn(call);
+}
+
 /*
  * open an RxRPC socket and bind it to be a server for callback notifications
  * - the socket is left in blocking mode and non-blocking ops use MSG_DONTWAIT
@@ -184,6 +191,28 @@ static void afs_free_call(struct afs_call *call)
 }
 
 /*
+ * End a call but do not free it
+ */
+static void afs_end_call_nofree(struct afs_call *call)
+{
+	if (call->rxcall) {
+		rxrpc_kernel_end_call(call->rxcall);
+		call->rxcall = NULL;
+	}
+	if (call->type->destructor)
+		call->type->destructor(call);
+}
+
+/*
+ * End a call and free it
+ */
+static void afs_end_call(struct afs_call *call)
+{
+	afs_end_call_nofree(call);
+	afs_free_call(call);
+}
+
+/*
  * allocate a call with flat request and reply buffers
  */
 struct afs_call *afs_alloc_flat_call(const struct afs_call_type *type,
@@ -326,7 +355,8 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp,
 	       atomic_read(&afs_outstanding_calls));
 
 	call->wait_mode = wait_mode;
-	INIT_WORK(&call->async_work, afs_process_async_call);
+	call->async_workfn = afs_process_async_call;
+	INIT_WORK(&call->async_work, afs_async_workfn);
 
 	memset(&srx, 0, sizeof(srx));
 	srx.srx_family = AF_RXRPC;
@@ -383,11 +413,8 @@ error_do_abort:
 	rxrpc_kernel_abort_call(rxcall, RX_USER_ABORT);
 	while ((skb = skb_dequeue(&call->rx_queue)))
 		afs_free_skb(skb);
-	rxrpc_kernel_end_call(rxcall);
-	call->rxcall = NULL;
 error_kill_call:
-	call->type->destructor(call);
-	afs_free_call(call);
+	afs_end_call(call);
 	_leave(" = %d", ret);
 	return ret;
 }
@@ -509,12 +536,8 @@ static void afs_deliver_to_call(struct afs_call *call)
 	if (call->state >= AFS_CALL_COMPLETE) {
 		while ((skb = skb_dequeue(&call->rx_queue)))
 			afs_free_skb(skb);
-		if (call->incoming) {
-			rxrpc_kernel_end_call(call->rxcall);
-			call->rxcall = NULL;
-			call->type->destructor(call);
-			afs_free_call(call);
-		}
+		if (call->incoming)
+			afs_end_call(call);
 	}
 
 	_leave("");
@@ -564,10 +587,7 @@ static int afs_wait_for_call_to_complete(struct afs_call *call)
 	}
 
 	_debug("call complete");
-	rxrpc_kernel_end_call(call->rxcall);
-	call->rxcall = NULL;
-	call->type->destructor(call);
-	afs_free_call(call);
+	afs_end_call(call);
 	_leave(" = %d", ret);
 	return ret;
 }
@@ -603,11 +623,8 @@ static int afs_dont_wait_for_call_to_complete(struct afs_call *call)
 /*
  * delete an asynchronous call
  */
-static void afs_delete_async_call(struct work_struct *work)
+static void afs_delete_async_call(struct afs_call *call)
 {
-	struct afs_call *call =
-		container_of(work, struct afs_call, async_work);
-
 	_enter("");
 
 	afs_free_call(call);
@@ -620,11 +637,8 @@ static void afs_delete_async_call(struct work_struct *work)
  * - on a multiple-thread workqueue this work item may try to run on several
  *   CPUs at the same time
  */
-static void afs_process_async_call(struct work_struct *work)
+static void afs_process_async_call(struct afs_call *call)
 {
-	struct afs_call *call =
-		container_of(work, struct afs_call, async_work);
-
 	_enter("");
 
 	if (!skb_queue_empty(&call->rx_queue))
@@ -637,10 +651,7 @@ static void afs_process_async_call(struct work_struct *work)
 		call->reply = NULL;
 
 		/* kill the call */
-		rxrpc_kernel_end_call(call->rxcall);
-		call->rxcall = NULL;
-		if (call->type->destructor)
-			call->type->destructor(call);
+		afs_end_call_nofree(call);
 
 		/* we can't just delete the call because the work item may be
 		 * queued */
@@ -663,13 +674,6 @@ void afs_transfer_reply(struct afs_call *call, struct sk_buff *skb)
 	call->reply_size += len;
 }
 
-static void afs_async_workfn(struct work_struct *work)
-{
-	struct afs_call *call = container_of(work, struct afs_call, async_work);
-
-	call->async_workfn(work);
-}
-
 /*
  * accept the backlog of incoming calls
  */
@@ -790,10 +794,7 @@ void afs_send_empty_reply(struct afs_call *call)
 		_debug("oom");
 		rxrpc_kernel_abort_call(call->rxcall, RX_USER_ABORT);
 	default:
-		rxrpc_kernel_end_call(call->rxcall);
-		call->rxcall = NULL;
-		call->type->destructor(call);
-		afs_free_call(call);
+		afs_end_call(call);
 		_leave(" [error]");
 		return;
 	}
@@ -823,17 +824,16 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len)
 	call->state = AFS_CALL_AWAIT_ACK;
 	n = rxrpc_kernel_send_data(call->rxcall, &msg, len);
 	if (n >= 0) {
+		/* Success */
 		_leave(" [replied]");
 		return;
 	}
+
 	if (n == -ENOMEM) {
 		_debug("oom");
 		rxrpc_kernel_abort_call(call->rxcall, RX_USER_ABORT);
 	}
-	rxrpc_kernel_end_call(call->rxcall);
-	call->rxcall = NULL;
-	call->type->destructor(call);
-	afs_free_call(call);
+	afs_end_call(call);
 	_leave(" [error]");
 }
 
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 2ad7de94efef..2f6d7b13b5bd 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3120,6 +3120,8 @@ process_slot:
 			} else if (type == BTRFS_FILE_EXTENT_INLINE) {
 				u64 skip = 0;
 				u64 trim = 0;
+				u64 aligned_end = 0;
+
 				if (off > key.offset) {
 					skip = off - key.offset;
 					new_key.offset += skip;
@@ -3136,9 +3138,11 @@ process_slot:
 				size -= skip + trim;
 				datal -= skip + trim;
 
+				aligned_end = ALIGN(new_key.offset + datal,
+						    root->sectorsize);
 				ret = btrfs_drop_extents(trans, root, inode,
 							 new_key.offset,
-							 new_key.offset + datal,
+							 aligned_end,
 							 1);
 				if (ret) {
 					if (ret != -EOPNOTSUPP)
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index eb6537a08c1b..fd38b5053479 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -1668,7 +1668,7 @@ static int get_first_ref(struct btrfs_root *root, u64 ino,
 		goto out;
 	}
 
-	if (key.type == BTRFS_INODE_REF_KEY) {
+	if (found_key.type == BTRFS_INODE_REF_KEY) {
 		struct btrfs_inode_ref *iref;
 		iref = btrfs_item_ptr(path->nodes[0], path->slots[0],
 				      struct btrfs_inode_ref);
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index aadc2b68678b..a22d667f1069 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -1737,6 +1737,9 @@ cifs_inode_needs_reval(struct inode *inode)
 	if (cifs_i->time == 0)
 		return true;
 
+	if (!cifs_sb->actimeo)
+		return true;
+
 	if (!time_in_range(jiffies, cifs_i->time,
 				cifs_i->time + cifs_sb->actimeo))
 		return true;
diff --git a/fs/dcache.c b/fs/dcache.c
index 42ae01eefc07..be2bea834bf4 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -441,42 +441,12 @@ void d_drop(struct dentry *dentry)
 }
 EXPORT_SYMBOL(d_drop);
 
-/*
- * Finish off a dentry we've decided to kill.
- * dentry->d_lock must be held, returns with it unlocked.
- * If ref is non-zero, then decrement the refcount too.
- * Returns dentry requiring refcount drop, or NULL if we're done.
- */
-static struct dentry *
-dentry_kill(struct dentry *dentry, int unlock_on_failure)
-	__releases(dentry->d_lock)
+static void __dentry_kill(struct dentry *dentry)
 {
-	struct inode *inode;
 	struct dentry *parent = NULL;
 	bool can_free = true;
-
-	if (unlikely(dentry->d_flags & DCACHE_DENTRY_KILLED)) {
-		can_free = dentry->d_flags & DCACHE_MAY_FREE;
-		spin_unlock(&dentry->d_lock);
-		goto out;
-	}
-
-	inode = dentry->d_inode;
-	if (inode && !spin_trylock(&inode->i_lock)) {
-relock:
-		if (unlock_on_failure) {
-			spin_unlock(&dentry->d_lock);
-			cpu_relax();
-		}
-		return dentry; /* try again with same dentry */
-	}
 	if (!IS_ROOT(dentry))
 		parent = dentry->d_parent;
-	if (parent && !spin_trylock(&parent->d_lock)) {
-		if (inode)
-			spin_unlock(&inode->i_lock);
-		goto relock;
-	}
 
 	/*
 	 * The dentry is now unrecoverably dead to the world.
@@ -520,9 +490,72 @@ relock:
 		can_free = false;
 	}
 	spin_unlock(&dentry->d_lock);
-out:
 	if (likely(can_free))
 		dentry_free(dentry);
+}
+
+/*
+ * Finish off a dentry we've decided to kill.
+ * dentry->d_lock must be held, returns with it unlocked.
+ * If ref is non-zero, then decrement the refcount too.
+ * Returns dentry requiring refcount drop, or NULL if we're done.
+ */
+static struct dentry *dentry_kill(struct dentry *dentry)
+	__releases(dentry->d_lock)
+{
+	struct inode *inode = dentry->d_inode;
+	struct dentry *parent = NULL;
+
+	if (inode && unlikely(!spin_trylock(&inode->i_lock)))
+		goto failed;
+
+	if (!IS_ROOT(dentry)) {
+		parent = dentry->d_parent;
+		if (unlikely(!spin_trylock(&parent->d_lock))) {
+			if (inode)
+				spin_unlock(&inode->i_lock);
+			goto failed;
+		}
+	}
+
+	__dentry_kill(dentry);
+	return parent;
+
+failed:
+	spin_unlock(&dentry->d_lock);
+	cpu_relax();
+	return dentry; /* try again with same dentry */
+}
+
+static inline struct dentry *lock_parent(struct dentry *dentry)
+{
+	struct dentry *parent = dentry->d_parent;
+	if (IS_ROOT(dentry))
+		return NULL;
+	if (likely(spin_trylock(&parent->d_lock)))
+		return parent;
+	spin_unlock(&dentry->d_lock);
+	rcu_read_lock();
+again:
+	parent = ACCESS_ONCE(dentry->d_parent);
+	spin_lock(&parent->d_lock);
+	/*
+	 * We can't blindly lock dentry until we are sure
+	 * that we won't violate the locking order.
+	 * Any changes of dentry->d_parent must have
+	 * been done with parent->d_lock held, so
+	 * spin_lock() above is enough of a barrier
+	 * for checking if it's still our child.
+	 */
+	if (unlikely(parent != dentry->d_parent)) {
+		spin_unlock(&parent->d_lock);
+		goto again;
+	}
+	rcu_read_unlock();
+	if (parent != dentry)
+		spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
+	else
+		parent = NULL;
 	return parent;
 }
 
@@ -579,7 +612,7 @@ repeat:
 	return;
 
 kill_it:
-	dentry = dentry_kill(dentry, 1);
+	dentry = dentry_kill(dentry);
 	if (dentry)
 		goto repeat;
 }
@@ -797,8 +830,11 @@ static void shrink_dentry_list(struct list_head *list)
 	struct dentry *dentry, *parent;
 
 	while (!list_empty(list)) {
+		struct inode *inode;
 		dentry = list_entry(list->prev, struct dentry, d_lru);
 		spin_lock(&dentry->d_lock);
+		parent = lock_parent(dentry);
+
 		/*
 		 * The dispose list is isolated and dentries are not accounted
 		 * to the LRU here, so we can simply remove it from the list
@@ -812,26 +848,33 @@ static void shrink_dentry_list(struct list_head *list)
 		 */
 		if ((int)dentry->d_lockref.count > 0) {
 			spin_unlock(&dentry->d_lock);
+			if (parent)
+				spin_unlock(&parent->d_lock);
 			continue;
 		}
 
-		parent = dentry_kill(dentry, 0);
-		/*
-		 * If dentry_kill returns NULL, we have nothing more to do.
-		 */
-		if (!parent)
+
+		if (unlikely(dentry->d_flags & DCACHE_DENTRY_KILLED)) {
+			bool can_free = dentry->d_flags & DCACHE_MAY_FREE;
+			spin_unlock(&dentry->d_lock);
+			if (parent)
+				spin_unlock(&parent->d_lock);
+			if (can_free)
+				dentry_free(dentry);
 			continue;
+		}
 
-		if (unlikely(parent == dentry)) {
-			/*
-			 * trylocks have failed and d_lock has been held the
-			 * whole time, so it could not have been added to any
-			 * other lists. Just add it back to the shrink list.
-			 */
+		inode = dentry->d_inode;
+		if (inode && unlikely(!spin_trylock(&inode->i_lock))) {
 			d_shrink_add(dentry, list);
 			spin_unlock(&dentry->d_lock);
+			if (parent)
+				spin_unlock(&parent->d_lock);
 			continue;
 		}
+
+		__dentry_kill(dentry);
+
 		/*
 		 * We need to prune ancestors too. This is necessary to prevent
 		 * quadratic behavior of shrink_dcache_parent(), but is also
@@ -839,8 +882,26 @@ static void shrink_dentry_list(struct list_head *list)
 		 * fragmentation.
 		 */
 		dentry = parent;
-		while (dentry && !lockref_put_or_lock(&dentry->d_lockref))
-			dentry = dentry_kill(dentry, 1);
+		while (dentry && !lockref_put_or_lock(&dentry->d_lockref)) {
+			parent = lock_parent(dentry);
+			if (dentry->d_lockref.count != 1) {
+				dentry->d_lockref.count--;
+				spin_unlock(&dentry->d_lock);
+				if (parent)
+					spin_unlock(&parent->d_lock);
+				break;
+			}
+			inode = dentry->d_inode;	/* can't be NULL */
+			if (unlikely(!spin_trylock(&inode->i_lock))) {
+				spin_unlock(&dentry->d_lock);
+				if (parent)
+					spin_unlock(&parent->d_lock);
+				cpu_relax();
+				continue;
+			}
+			__dentry_kill(dentry);
+			dentry = parent;
+		}
 	}
 }
 
diff --git a/fs/exec.c b/fs/exec.c
index 476f3ebf437e..238b7aa26f68 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -657,10 +657,10 @@ int setup_arg_pages(struct linux_binprm *bprm,
 	unsigned long rlim_stack;
 
 #ifdef CONFIG_STACK_GROWSUP
-	/* Limit stack size to 1GB */
+	/* Limit stack size */
 	stack_base = rlimit_max(RLIMIT_STACK);
-	if (stack_base > (1 << 30))
-		stack_base = 1 << 30;
+	if (stack_base > STACK_SIZE_MAX)
+		stack_base = STACK_SIZE_MAX;
 
 	/* Make sure we didn't let the argument array grow too large. */
 	if (vma->vm_end - vma->vm_start > stack_base)
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index e01ea4a14a01..5e9a80cfc3d8 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -610,6 +610,7 @@ static void kernfs_put_open_node(struct kernfs_node *kn,
 static int kernfs_fop_open(struct inode *inode, struct file *file)
 {
 	struct kernfs_node *kn = file->f_path.dentry->d_fsdata;
+	struct kernfs_root *root = kernfs_root(kn);
 	const struct kernfs_ops *ops;
 	struct kernfs_open_file *of;
 	bool has_read, has_write, has_mmap;
@@ -624,14 +625,16 @@ static int kernfs_fop_open(struct inode *inode, struct file *file)
 	has_write = ops->write || ops->mmap;
 	has_mmap = ops->mmap;
 
-	/* check perms and supported operations */
-	if ((file->f_mode & FMODE_WRITE) &&
-	    (!(inode->i_mode & S_IWUGO) || !has_write))
-		goto err_out;
+	/* see the flag definition for details */
+	if (root->flags & KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK) {
+		if ((file->f_mode & FMODE_WRITE) &&
+		    (!(inode->i_mode & S_IWUGO) || !has_write))
+			goto err_out;
 
-	if ((file->f_mode & FMODE_READ) &&
-	    (!(inode->i_mode & S_IRUGO) || !has_read))
-		goto err_out;
+		if ((file->f_mode & FMODE_READ) &&
+		    (!(inode->i_mode & S_IRUGO) || !has_read))
+			goto err_out;
+	}
 
 	/* allocate a kernfs_open_file for the file */
 	error = -ENOMEM;
diff --git a/fs/locks.c b/fs/locks.c
index e663aeac579e..e390bd9ae068 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -389,18 +389,6 @@ static int flock64_to_posix_lock(struct file *filp, struct file_lock *fl,
 	fl->fl_ops = NULL;
 	fl->fl_lmops = NULL;
 
-	/* Ensure that fl->fl_filp has compatible f_mode */
-	switch (l->l_type) {
-	case F_RDLCK:
-		if (!(filp->f_mode & FMODE_READ))
-			return -EBADF;
-		break;
-	case F_WRLCK:
-		if (!(filp->f_mode & FMODE_WRITE))
-			return -EBADF;
-		break;
-	}
-
 	return assign_type(fl, l->l_type);
 }
 
@@ -2034,6 +2022,22 @@ static int do_lock_file_wait(struct file *filp, unsigned int cmd,
 	return error;
 }
 
+/* Ensure that fl->fl_filp has compatible f_mode for F_SETLK calls */
+static int
+check_fmode_for_setlk(struct file_lock *fl)
+{
+	switch (fl->fl_type) {
+	case F_RDLCK:
+		if (!(fl->fl_file->f_mode & FMODE_READ))
+			return -EBADF;
+		break;
+	case F_WRLCK:
+		if (!(fl->fl_file->f_mode & FMODE_WRITE))
+			return -EBADF;
+	}
+	return 0;
+}
+
 /* Apply the lock described by l to an open file descriptor.
  * This implements both the F_SETLK and F_SETLKW commands of fcntl().
  */
@@ -2071,6 +2075,10 @@ again:
 	if (error)
 		goto out;
 
+	error = check_fmode_for_setlk(file_lock);
+	if (error)
+		goto out;
+
 	/*
 	 * If the cmd is requesting file-private locks, then set the
 	 * FL_OFDLCK flag and override the owner.
@@ -2206,6 +2214,10 @@ again:
 	if (error)
 		goto out;
 
+	error = check_fmode_for_setlk(file_lock);
+	if (error)
+		goto out;
+
 	/*
 	 * If the cmd is requesting file-private locks, then set the
 	 * FL_OFDLCK flag and override the owner.
diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c
index 6f3f392d48af..f66c66b9f182 100644
--- a/fs/nfsd/nfs4acl.c
+++ b/fs/nfsd/nfs4acl.c
@@ -402,8 +402,10 @@ sort_pacl(struct posix_acl *pacl)
 	 * by uid/gid. */
 	int i, j;
 
-	if (pacl->a_count <= 4)
-		return; /* no users or groups */
+	/* no users or groups */
+	if (!pacl || pacl->a_count <= 4)
+		return;
+
 	i = 1;
 	while (pacl->a_entries[i].e_tag == ACL_USER)
 		i++;
@@ -530,13 +532,12 @@ posix_state_to_acl(struct posix_acl_state *state, unsigned int flags)
 
 	/*
 	 * ACLs with no ACEs are treated differently in the inheritable
-	 * and effective cases: when there are no inheritable ACEs, we
-	 * set a zero-length default posix acl:
+	 * and effective cases: when there are no inheritable ACEs,
+	 * calls ->set_acl with a NULL ACL structure.
 	 */
-	if (state->empty && (flags & NFS4_ACL_TYPE_DEFAULT)) {
-		pacl = posix_acl_alloc(0, GFP_KERNEL);
-		return pacl ? pacl : ERR_PTR(-ENOMEM);
-	}
+	if (state->empty && (flags & NFS4_ACL_TYPE_DEFAULT))
+		return NULL;
+
 	/*
 	 * When there are no effective ACEs, the following will end
 	 * up setting a 3-element effective posix ACL with all
@@ -589,7 +590,7 @@ posix_state_to_acl(struct posix_acl_state *state, unsigned int flags)
 		add_to_mask(state, &state->groups->aces[i].perms);
 	}
 
-	if (!state->users->n && !state->groups->n) {
+	if (state->users->n || state->groups->n) {
 		pace++;
 		pace->e_tag = ACL_MASK;
 		low_mode_from_nfs4(state->mask.allow, &pace->e_perm, flags);
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 3ba65979a3cd..9a77a5a21557 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1078,6 +1078,18 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name)
 		return NULL;
 	}
 	clp->cl_name.len = name.len;
+	INIT_LIST_HEAD(&clp->cl_sessions);
+	idr_init(&clp->cl_stateids);
+	atomic_set(&clp->cl_refcount, 0);
+	clp->cl_cb_state = NFSD4_CB_UNKNOWN;
+	INIT_LIST_HEAD(&clp->cl_idhash);
+	INIT_LIST_HEAD(&clp->cl_openowners);
+	INIT_LIST_HEAD(&clp->cl_delegations);
+	INIT_LIST_HEAD(&clp->cl_lru);
+	INIT_LIST_HEAD(&clp->cl_callbacks);
+	INIT_LIST_HEAD(&clp->cl_revoked);
+	spin_lock_init(&clp->cl_lock);
+	rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table");
 	return clp;
 }
 
@@ -1095,6 +1107,7 @@ free_client(struct nfs4_client *clp)
 		WARN_ON_ONCE(atomic_read(&ses->se_ref));
 		free_session(ses);
 	}
+	rpc_destroy_wait_queue(&clp->cl_cb_waitq);
 	free_svc_cred(&clp->cl_cred);
 	kfree(clp->cl_name.data);
 	idr_destroy(&clp->cl_stateids);
@@ -1347,7 +1360,6 @@ static struct nfs4_client *create_client(struct xdr_netobj name,
 	if (clp == NULL)
 		return NULL;
 
-	INIT_LIST_HEAD(&clp->cl_sessions);
 	ret = copy_cred(&clp->cl_cred, &rqstp->rq_cred);
 	if (ret) {
 		spin_lock(&nn->client_lock);
@@ -1355,20 +1367,9 @@ static struct nfs4_client *create_client(struct xdr_netobj name,
 		spin_unlock(&nn->client_lock);
 		return NULL;
 	}
-	idr_init(&clp->cl_stateids);
-	atomic_set(&clp->cl_refcount, 0);
-	clp->cl_cb_state = NFSD4_CB_UNKNOWN;
-	INIT_LIST_HEAD(&clp->cl_idhash);
-	INIT_LIST_HEAD(&clp->cl_openowners);
-	INIT_LIST_HEAD(&clp->cl_delegations);
-	INIT_LIST_HEAD(&clp->cl_lru);
-	INIT_LIST_HEAD(&clp->cl_callbacks);
-	INIT_LIST_HEAD(&clp->cl_revoked);
-	spin_lock_init(&clp->cl_lock);
 	nfsd4_init_callback(&clp->cl_cb_null);
 	clp->cl_time = get_seconds();
 	clear_bit(0, &clp->cl_cb_slot_busy);
-	rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table");
 	copy_verf(clp, verf);
 	rpc_copy_addr((struct sockaddr *) &clp->cl_addr, sa);
 	gen_confirm(clp);
@@ -3716,9 +3717,16 @@ out:
 static __be32
 nfsd4_free_lock_stateid(struct nfs4_ol_stateid *stp)
 {
-	if (check_for_locks(stp->st_file, lockowner(stp->st_stateowner)))
+	struct nfs4_lockowner *lo = lockowner(stp->st_stateowner);
+
+	if (check_for_locks(stp->st_file, lo))
 		return nfserr_locks_held;
-	release_lock_stateid(stp);
+	/*
+	 * Currently there's a 1-1 lock stateid<->lockowner
+	 * correspondance, and we have to delete the lockowner when we
+	 * delete the lock stateid:
+	 */
+	unhash_lockowner(lo);
 	return nfs_ok;
 }
 
@@ -4158,6 +4166,10 @@ static bool same_lockowner_ino(struct nfs4_lockowner *lo, struct inode *inode, c
 
 	if (!same_owner_str(&lo->lo_owner, owner, clid))
 		return false;
+	if (list_empty(&lo->lo_owner.so_stateids)) {
+		WARN_ON_ONCE(1);
+		return false;
+	}
 	lst = list_first_entry(&lo->lo_owner.so_stateids,
 			       struct nfs4_ol_stateid, st_perstateowner);
 	return lst->st_file->fi_inode == inode;
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index af3f7aa73e13..ee1f88419cb0 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -472,11 +472,15 @@ bail:
 
 void dlm_destroy_master_caches(void)
 {
-	if (dlm_lockname_cache)
+	if (dlm_lockname_cache) {
 		kmem_cache_destroy(dlm_lockname_cache);
+		dlm_lockname_cache = NULL;
+	}
 
-	if (dlm_lockres_cache)
+	if (dlm_lockres_cache) {
 		kmem_cache_destroy(dlm_lockres_cache);
+		dlm_lockres_cache = NULL;
+	}
 }
 
 static void dlm_lockres_release(struct kref *kref)
diff --git a/fs/splice.c b/fs/splice.c
index 8e7eef755a9b..f5cb9ba84510 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -1548,7 +1548,7 @@ static long vmsplice_to_user(struct file *file, const struct iovec __user *uiov,
 	struct iovec iovstack[UIO_FASTIOV];
 	struct iovec *iov = iovstack;
 	struct iov_iter iter;
-	ssize_t count = 0;
+	ssize_t count;
 
 	pipe = get_pipe_info(file);
 	if (!pipe)
@@ -1557,8 +1557,9 @@ static long vmsplice_to_user(struct file *file, const struct iovec __user *uiov,
 	ret = rw_copy_check_uvector(READ, uiov, nr_segs,
 				    ARRAY_SIZE(iovstack), iovstack, &iov);
 	if (ret <= 0)
-		return ret;
+		goto out;
 
+	count = ret;
 	iov_iter_init(&iter, READ, iov, nr_segs, count);
 
 	sd.len = 0;
@@ -1571,6 +1572,7 @@ static long vmsplice_to_user(struct file *file, const struct iovec __user *uiov,
 	ret = __splice_from_pipe(pipe, &sd, pipe_to_user);
 	pipe_unlock(pipe);
 
+out:
 	if (iov != iovstack)
 		kfree(iov);
 
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index 28cc1acd5439..e9ef59b3abb1 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -47,12 +47,13 @@ static int sysfs_kf_seq_show(struct seq_file *sf, void *v)
 	ssize_t count;
 	char *buf;
 
-	/* acquire buffer and ensure that it's >= PAGE_SIZE */
+	/* acquire buffer and ensure that it's >= PAGE_SIZE and clear */
 	count = seq_get_buf(sf, &buf);
 	if (count < PAGE_SIZE) {
 		seq_commit(sf, -1);
 		return 0;
 	}
+	memset(buf, 0, PAGE_SIZE);
 
 	/*
 	 * Invoke show().  Control may reach here via seq file lseek even
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index a66ad6196f59..8794423f7efb 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -63,7 +63,8 @@ int __init sysfs_init(void)
 {
 	int err;
 
-	sysfs_root = kernfs_create_root(NULL, 0, NULL);
+	sysfs_root = kernfs_create_root(NULL, KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK,
+					NULL);
 	if (IS_ERR(sysfs_root))
 		return PTR_ERR(sysfs_root);
 
diff --git a/fs/xfs/xfs_attr.c b/fs/xfs/xfs_attr.c
index 01b6a0102fbd..abda1124a70f 100644
--- a/fs/xfs/xfs_attr.c
+++ b/fs/xfs/xfs_attr.c
@@ -213,7 +213,7 @@ xfs_attr_calc_size(
 		 * Out of line attribute, cannot double split, but
 		 * make room for the attribute value itself.
 		 */
-		uint	dblocks = XFS_B_TO_FSB(mp, valuelen);
+		uint	dblocks = xfs_attr3_rmt_blocks(mp, valuelen);
 		nblks += dblocks;
 		nblks += XFS_NEXTENTADD_SPACE_RES(mp, dblocks, XFS_ATTR_FORK);
 	}
@@ -698,11 +698,22 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
 
 		trace_xfs_attr_leaf_replace(args);
 
+		/* save the attribute state for later removal*/
 		args->op_flags |= XFS_DA_OP_RENAME;	/* an atomic rename */
 		args->blkno2 = args->blkno;		/* set 2nd entry info*/
 		args->index2 = args->index;
 		args->rmtblkno2 = args->rmtblkno;
 		args->rmtblkcnt2 = args->rmtblkcnt;
+		args->rmtvaluelen2 = args->rmtvaluelen;
+
+		/*
+		 * clear the remote attr state now that it is saved so that the
+		 * values reflect the state of the attribute we are about to
+		 * add, not the attribute we just found and will remove later.
+		 */
+		args->rmtblkno = 0;
+		args->rmtblkcnt = 0;
+		args->rmtvaluelen = 0;
 	}
 
 	/*
@@ -794,6 +805,7 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
 		args->blkno = args->blkno2;
 		args->rmtblkno = args->rmtblkno2;
 		args->rmtblkcnt = args->rmtblkcnt2;
+		args->rmtvaluelen = args->rmtvaluelen2;
 		if (args->rmtblkno) {
 			error = xfs_attr_rmtval_remove(args);
 			if (error)
@@ -999,13 +1011,22 @@ restart:
 
 		trace_xfs_attr_node_replace(args);
 
+		/* save the attribute state for later removal*/
 		args->op_flags |= XFS_DA_OP_RENAME;	/* atomic rename op */
 		args->blkno2 = args->blkno;		/* set 2nd entry info*/
 		args->index2 = args->index;
 		args->rmtblkno2 = args->rmtblkno;
 		args->rmtblkcnt2 = args->rmtblkcnt;
+		args->rmtvaluelen2 = args->rmtvaluelen;
+
+		/*
+		 * clear the remote attr state now that it is saved so that the
+		 * values reflect the state of the attribute we are about to
+		 * add, not the attribute we just found and will remove later.
+		 */
 		args->rmtblkno = 0;
 		args->rmtblkcnt = 0;
+		args->rmtvaluelen = 0;
 	}
 
 	retval = xfs_attr3_leaf_add(blk->bp, state->args);
@@ -1133,6 +1154,7 @@ restart:
 		args->blkno = args->blkno2;
 		args->rmtblkno = args->rmtblkno2;
 		args->rmtblkcnt = args->rmtblkcnt2;
+		args->rmtvaluelen = args->rmtvaluelen2;
 		if (args->rmtblkno) {
 			error = xfs_attr_rmtval_remove(args);
 			if (error)
diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c
index fe9587fab17a..511c283459b1 100644
--- a/fs/xfs/xfs_attr_leaf.c
+++ b/fs/xfs/xfs_attr_leaf.c
@@ -1229,6 +1229,7 @@ xfs_attr3_leaf_add_work(
 		name_rmt->valueblk = 0;
 		args->rmtblkno = 1;
 		args->rmtblkcnt = xfs_attr3_rmt_blocks(mp, args->valuelen);
+		args->rmtvaluelen = args->valuelen;
 	}
 	xfs_trans_log_buf(args->trans, bp,
 	     XFS_DA_LOGRANGE(leaf, xfs_attr3_leaf_name(leaf, args->index),
@@ -2167,11 +2168,11 @@ xfs_attr3_leaf_lookup_int(
 			if (!xfs_attr_namesp_match(args->flags, entry->flags))
 				continue;
 			args->index = probe;
-			args->valuelen = be32_to_cpu(name_rmt->valuelen);
+			args->rmtvaluelen = be32_to_cpu(name_rmt->valuelen);
 			args->rmtblkno = be32_to_cpu(name_rmt->valueblk);
 			args->rmtblkcnt = xfs_attr3_rmt_blocks(
 							args->dp->i_mount,
-							args->valuelen);
+							args->rmtvaluelen);
 			return XFS_ERROR(EEXIST);
 		}
 	}
@@ -2220,19 +2221,19 @@ xfs_attr3_leaf_getvalue(
 		name_rmt = xfs_attr3_leaf_name_remote(leaf, args->index);
 		ASSERT(name_rmt->namelen == args->namelen);
 		ASSERT(memcmp(args->name, name_rmt->name, args->namelen) == 0);
-		valuelen = be32_to_cpu(name_rmt->valuelen);
+		args->rmtvaluelen = be32_to_cpu(name_rmt->valuelen);
 		args->rmtblkno = be32_to_cpu(name_rmt->valueblk);
 		args->rmtblkcnt = xfs_attr3_rmt_blocks(args->dp->i_mount,
-						       valuelen);
+						       args->rmtvaluelen);
 		if (args->flags & ATTR_KERNOVAL) {
-			args->valuelen = valuelen;
+			args->valuelen = args->rmtvaluelen;
 			return 0;
 		}
-		if (args->valuelen < valuelen) {
-			args->valuelen = valuelen;
+		if (args->valuelen < args->rmtvaluelen) {
+			args->valuelen = args->rmtvaluelen;
 			return XFS_ERROR(ERANGE);
 		}
-		args->valuelen = valuelen;
+		args->valuelen = args->rmtvaluelen;
 	}
 	return 0;
 }
@@ -2519,7 +2520,7 @@ xfs_attr3_leaf_clearflag(
 		ASSERT((entry->flags & XFS_ATTR_LOCAL) == 0);
 		name_rmt = xfs_attr3_leaf_name_remote(leaf, args->index);
 		name_rmt->valueblk = cpu_to_be32(args->rmtblkno);
-		name_rmt->valuelen = cpu_to_be32(args->valuelen);
+		name_rmt->valuelen = cpu_to_be32(args->rmtvaluelen);
 		xfs_trans_log_buf(args->trans, bp,
 			 XFS_DA_LOGRANGE(leaf, name_rmt, sizeof(*name_rmt)));
 	}
@@ -2677,7 +2678,7 @@ xfs_attr3_leaf_flipflags(
 		ASSERT((entry1->flags & XFS_ATTR_LOCAL) == 0);
 		name_rmt = xfs_attr3_leaf_name_remote(leaf1, args->index);
 		name_rmt->valueblk = cpu_to_be32(args->rmtblkno);
-		name_rmt->valuelen = cpu_to_be32(args->valuelen);
+		name_rmt->valuelen = cpu_to_be32(args->rmtvaluelen);
 		xfs_trans_log_buf(args->trans, bp1,
 			 XFS_DA_LOGRANGE(leaf1, name_rmt, sizeof(*name_rmt)));
 	}
diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c
index 01db96f60cf0..833fe5d98d80 100644
--- a/fs/xfs/xfs_attr_list.c
+++ b/fs/xfs/xfs_attr_list.c
@@ -447,6 +447,7 @@ xfs_attr3_leaf_list_int(
 				args.dp = context->dp;
 				args.whichfork = XFS_ATTR_FORK;
 				args.valuelen = valuelen;
+				args.rmtvaluelen = valuelen;
 				args.value = kmem_alloc(valuelen, KM_SLEEP | KM_NOFS);
 				args.rmtblkno = be32_to_cpu(name_rmt->valueblk);
 				args.rmtblkcnt = xfs_attr3_rmt_blocks(
diff --git a/fs/xfs/xfs_attr_remote.c b/fs/xfs/xfs_attr_remote.c
index 6e37823e2932..d2e6e948cec7 100644
--- a/fs/xfs/xfs_attr_remote.c
+++ b/fs/xfs/xfs_attr_remote.c
@@ -337,7 +337,7 @@ xfs_attr_rmtval_get(
 	struct xfs_buf		*bp;
 	xfs_dablk_t		lblkno = args->rmtblkno;
 	__uint8_t		*dst = args->value;
-	int			valuelen = args->valuelen;
+	int			valuelen;
 	int			nmap;
 	int			error;
 	int			blkcnt = args->rmtblkcnt;
@@ -347,7 +347,9 @@ xfs_attr_rmtval_get(
 	trace_xfs_attr_rmtval_get(args);
 
 	ASSERT(!(args->flags & ATTR_KERNOVAL));
+	ASSERT(args->rmtvaluelen == args->valuelen);
 
+	valuelen = args->rmtvaluelen;
 	while (valuelen > 0) {
 		nmap = ATTR_RMTVALUE_MAPSIZE;
 		error = xfs_bmapi_read(args->dp, (xfs_fileoff_t)lblkno,
@@ -415,7 +417,7 @@ xfs_attr_rmtval_set(
 	 * attributes have headers, we can't just do a straight byte to FSB
 	 * conversion and have to take the header space into account.
 	 */
-	blkcnt = xfs_attr3_rmt_blocks(mp, args->valuelen);
+	blkcnt = xfs_attr3_rmt_blocks(mp, args->rmtvaluelen);
 	error = xfs_bmap_first_unused(args->trans, args->dp, blkcnt, &lfileoff,
 						   XFS_ATTR_FORK);
 	if (error)
@@ -480,7 +482,7 @@ xfs_attr_rmtval_set(
 	 */
 	lblkno = args->rmtblkno;
 	blkcnt = args->rmtblkcnt;
-	valuelen = args->valuelen;
+	valuelen = args->rmtvaluelen;
 	while (valuelen > 0) {
 		struct xfs_buf	*bp;
 		xfs_daddr_t	dblkno;
diff --git a/fs/xfs/xfs_da_btree.h b/fs/xfs/xfs_da_btree.h
index 6e95ea79f5d7..201c6091d26a 100644
--- a/fs/xfs/xfs_da_btree.h
+++ b/fs/xfs/xfs_da_btree.h
@@ -60,10 +60,12 @@ typedef struct xfs_da_args {
 	int		index;		/* index of attr of interest in blk */
 	xfs_dablk_t	rmtblkno;	/* remote attr value starting blkno */
 	int		rmtblkcnt;	/* remote attr value block count */
+	int		rmtvaluelen;	/* remote attr value length in bytes */
 	xfs_dablk_t	blkno2;		/* blkno of 2nd attr leaf of interest */
 	int		index2;		/* index of 2nd attr in blk */
 	xfs_dablk_t	rmtblkno2;	/* remote attr value starting blkno */
 	int		rmtblkcnt2;	/* remote attr value block count */
+	int		rmtvaluelen2;	/* remote attr value length in bytes */
 	int		op_flags;	/* operation flags */
 	enum xfs_dacmp	cmpresult;	/* name compare result for lookups */
 } xfs_da_args_t;
diff --git a/fs/xfs/xfs_export.c b/fs/xfs/xfs_export.c
index 1399e187d425..753e467aa1a5 100644
--- a/fs/xfs/xfs_export.c
+++ b/fs/xfs/xfs_export.c
@@ -237,7 +237,7 @@ xfs_fs_nfs_commit_metadata(
 
 	if (!lsn)
 		return 0;
-	return _xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, NULL);
+	return -_xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, NULL);
 }
 
 const struct export_operations xfs_export_operations = {
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index b1c489c1fb2e..500c3f0656d0 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -155,7 +155,7 @@ xfs_dir_fsync(
 
 	if (!lsn)
 		return 0;
-	return _xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, NULL);
+	return -_xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, NULL);
 }
 
 STATIC int
@@ -288,7 +288,7 @@ xfs_file_read_iter(
 		xfs_rw_ilock(ip, XFS_IOLOCK_EXCL);
 
 		if (inode->i_mapping->nrpages) {
-			ret = -filemap_write_and_wait_range(
+			ret = filemap_write_and_wait_range(
 							VFS_I(ip)->i_mapping,
 							pos, -1);
 			if (ret) {
@@ -772,7 +772,7 @@ xfs_file_fallocate(
 		unsigned blksize_mask = (1 << inode->i_blkbits) - 1;
 
 		if (offset & blksize_mask || len & blksize_mask) {
-			error = -EINVAL;
+			error = EINVAL;
 			goto out_unlock;
 		}
 
@@ -781,7 +781,7 @@ xfs_file_fallocate(
 		 * in which case it is effectively a truncate operation
 		 */
 		if (offset + len >= i_size_read(inode)) {
-			error = -EINVAL;
+			error = EINVAL;
 			goto out_unlock;
 		}
 
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index ef1ca010f417..36d630319a27 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -72,8 +72,8 @@ xfs_initxattrs(
 	int			error = 0;
 
 	for (xattr = xattr_array; xattr->name != NULL; xattr++) {
-		error = xfs_attr_set(ip, xattr->name, xattr->value,
-				     xattr->value_len, ATTR_SECURE);
+		error = -xfs_attr_set(ip, xattr->name, xattr->value,
+				      xattr->value_len, ATTR_SECURE);
 		if (error < 0)
 			break;
 	}
@@ -93,8 +93,8 @@ xfs_init_security(
 	struct inode	*dir,
 	const struct qstr *qstr)
 {
-	return security_inode_init_security(inode, dir, qstr,
-					    &xfs_initxattrs, NULL);
+	return -security_inode_init_security(inode, dir, qstr,
+					     &xfs_initxattrs, NULL);
 }
 
 static void
@@ -124,15 +124,15 @@ xfs_cleanup_inode(
 	xfs_dentry_to_name(&teardown, dentry, 0);
 
 	xfs_remove(XFS_I(dir), &teardown, XFS_I(inode));
-	iput(inode);
 }
 
 STATIC int
-xfs_vn_mknod(
+xfs_generic_create(
 	struct inode	*dir,
 	struct dentry	*dentry,
 	umode_t		mode,
-	dev_t		rdev)
+	dev_t		rdev,
+	bool		tmpfile)	/* unnamed file */
 {
 	struct inode	*inode;
 	struct xfs_inode *ip = NULL;
@@ -156,8 +156,12 @@ xfs_vn_mknod(
 	if (error)
 		return error;
 
-	xfs_dentry_to_name(&name, dentry, mode);
-	error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip);
+	if (!tmpfile) {
+		xfs_dentry_to_name(&name, dentry, mode);
+		error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip);
+	} else {
+		error = xfs_create_tmpfile(XFS_I(dir), dentry, mode, &ip);
+	}
 	if (unlikely(error))
 		goto out_free_acl;
 
@@ -169,18 +173,22 @@ xfs_vn_mknod(
 
 #ifdef CONFIG_XFS_POSIX_ACL
 	if (default_acl) {
-		error = xfs_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
+		error = -xfs_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
 		if (error)
 			goto out_cleanup_inode;
 	}
 	if (acl) {
-		error = xfs_set_acl(inode, acl, ACL_TYPE_ACCESS);
+		error = -xfs_set_acl(inode, acl, ACL_TYPE_ACCESS);
 		if (error)
 			goto out_cleanup_inode;
 	}
 #endif
 
-	d_instantiate(dentry, inode);
+	if (tmpfile)
+		d_tmpfile(dentry, inode);
+	else
+		d_instantiate(dentry, inode);
+
  out_free_acl:
 	if (default_acl)
 		posix_acl_release(default_acl);
@@ -189,11 +197,23 @@ xfs_vn_mknod(
 	return -error;
 
  out_cleanup_inode:
-	xfs_cleanup_inode(dir, inode, dentry);
+	if (!tmpfile)
+		xfs_cleanup_inode(dir, inode, dentry);
+	iput(inode);
 	goto out_free_acl;
 }
 
 STATIC int
+xfs_vn_mknod(
+	struct inode	*dir,
+	struct dentry	*dentry,
+	umode_t		mode,
+	dev_t		rdev)
+{
+	return xfs_generic_create(dir, dentry, mode, rdev, false);
+}
+
+STATIC int
 xfs_vn_create(
 	struct inode	*dir,
 	struct dentry	*dentry,
@@ -353,6 +373,7 @@ xfs_vn_symlink(
 
  out_cleanup_inode:
 	xfs_cleanup_inode(dir, inode, dentry);
+	iput(inode);
  out:
 	return -error;
 }
@@ -1053,25 +1074,7 @@ xfs_vn_tmpfile(
 	struct dentry	*dentry,
 	umode_t		mode)
 {
-	int			error;
-	struct xfs_inode	*ip;
-	struct inode		*inode;
-
-	error = xfs_create_tmpfile(XFS_I(dir), dentry, mode, &ip);
-	if (unlikely(error))
-		return -error;
-
-	inode = VFS_I(ip);
-
-	error = xfs_init_security(inode, dir, &dentry->d_name);
-	if (unlikely(error)) {
-		iput(inode);
-		return -error;
-	}
-
-	d_tmpfile(dentry, inode);
-
-	return 0;
+	return xfs_generic_create(dir, dentry, mode, 0, true);
 }
 
 static const struct inode_operations xfs_inode_operations = {
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 08624dc67317..a5f8bd9899d3 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -616,11 +616,13 @@ xfs_log_mount(
 	int		error = 0;
 	int		min_logfsbs;
 
-	if (!(mp->m_flags & XFS_MOUNT_NORECOVERY))
-		xfs_notice(mp, "Mounting Filesystem");
-	else {
+	if (!(mp->m_flags & XFS_MOUNT_NORECOVERY)) {
+		xfs_notice(mp, "Mounting V%d Filesystem",
+			   XFS_SB_VERSION_NUM(&mp->m_sb));
+	} else {
 		xfs_notice(mp,
-"Mounting filesystem in no-recovery mode.  Filesystem will be inconsistent.");
+"Mounting V%d filesystem in no-recovery mode. Filesystem will be inconsistent.",
+			   XFS_SB_VERSION_NUM(&mp->m_sb));
 		ASSERT(mp->m_flags & XFS_MOUNT_RDONLY);
 	}
 
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 993cb19e7d39..944f3d9456a8 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -743,8 +743,6 @@ xfs_mountfs(
 		new_size *= mp->m_sb.sb_inodesize / XFS_DINODE_MIN_SIZE;
 		if (mp->m_sb.sb_inoalignmt >= XFS_B_TO_FSBT(mp, new_size))
 			mp->m_inode_cluster_size = new_size;
-		xfs_info(mp, "Using inode cluster size of %d bytes",
-			 mp->m_inode_cluster_size);
 	}
 
 	/*
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 348e4d2ed6e6..dc977b6e6a36 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -843,22 +843,17 @@ xfs_qm_init_quotainfo(
 
 	qinf = mp->m_quotainfo = kmem_zalloc(sizeof(xfs_quotainfo_t), KM_SLEEP);
 
-	if ((error = list_lru_init(&qinf->qi_lru))) {
-		kmem_free(qinf);
-		mp->m_quotainfo = NULL;
-		return error;
-	}
+	error = -list_lru_init(&qinf->qi_lru);
+	if (error)
+		goto out_free_qinf;
 
 	/*
 	 * See if quotainodes are setup, and if not, allocate them,
 	 * and change the superblock accordingly.
 	 */
-	if ((error = xfs_qm_init_quotainos(mp))) {
-		list_lru_destroy(&qinf->qi_lru);
-		kmem_free(qinf);
-		mp->m_quotainfo = NULL;
-		return error;
-	}
+	error = xfs_qm_init_quotainos(mp);
+	if (error)
+		goto out_free_lru;
 
 	INIT_RADIX_TREE(&qinf->qi_uquota_tree, GFP_NOFS);
 	INIT_RADIX_TREE(&qinf->qi_gquota_tree, GFP_NOFS);
@@ -918,7 +913,7 @@ xfs_qm_init_quotainfo(
 		qinf->qi_isoftlimit = be64_to_cpu(ddqp->d_ino_softlimit);
 		qinf->qi_rtbhardlimit = be64_to_cpu(ddqp->d_rtb_hardlimit);
 		qinf->qi_rtbsoftlimit = be64_to_cpu(ddqp->d_rtb_softlimit);
- 
+
 		xfs_qm_dqdestroy(dqp);
 	} else {
 		qinf->qi_btimelimit = XFS_QM_BTIMELIMIT;
@@ -935,6 +930,13 @@ xfs_qm_init_quotainfo(
 	qinf->qi_shrinker.flags = SHRINKER_NUMA_AWARE;
 	register_shrinker(&qinf->qi_shrinker);
 	return 0;
+
+out_free_lru:
+	list_lru_destroy(&qinf->qi_lru);
+out_free_qinf:
+	kmem_free(qinf);
+	mp->m_quotainfo = NULL;
+	return error;
 }
 
 
diff --git a/fs/xfs/xfs_sb.c b/fs/xfs/xfs_sb.c
index 0c0e41bbe4e3..8baf61afae1d 100644
--- a/fs/xfs/xfs_sb.c
+++ b/fs/xfs/xfs_sb.c
@@ -201,10 +201,6 @@ xfs_mount_validate_sb(
 	 * write validation, we don't need to check feature masks.
 	 */
 	if (check_version && XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) {
-		xfs_alert(mp,
-"Version 5 superblock detected. This kernel has EXPERIMENTAL support enabled!\n"
-"Use of these features in this kernel is at your own risk!");
-
 		if (xfs_sb_has_compat_feature(sbp,
 					XFS_SB_FEAT_COMPAT_UNKNOWN)) {
 			xfs_warn(mp,
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 205376776377..3494eff8e4eb 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1433,11 +1433,11 @@ xfs_fs_fill_super(
 	if (error)
 		goto out_free_fsname;
 
-	error = xfs_init_mount_workqueues(mp);
+	error = -xfs_init_mount_workqueues(mp);
 	if (error)
 		goto out_close_devices;
 
-	error = xfs_icsb_init_counters(mp);
+	error = -xfs_icsb_init_counters(mp);
 	if (error)
 		goto out_destroy_workqueues;
 
diff --git a/include/asm-generic/resource.h b/include/asm-generic/resource.h
index b4ea8f50fc65..5e752b959054 100644
--- a/include/asm-generic/resource.h
+++ b/include/asm-generic/resource.h
@@ -12,7 +12,7 @@
 	[RLIMIT_CPU]		= {  RLIM_INFINITY,  RLIM_INFINITY },	\
 	[RLIMIT_FSIZE]		= {  RLIM_INFINITY,  RLIM_INFINITY },	\
 	[RLIMIT_DATA]		= {  RLIM_INFINITY,  RLIM_INFINITY },	\
-	[RLIMIT_STACK]		= {       _STK_LIM,   _STK_LIM_MAX },	\
+	[RLIMIT_STACK]		= {       _STK_LIM,  RLIM_INFINITY },	\
 	[RLIMIT_CORE]		= {              0,  RLIM_INFINITY },	\
 	[RLIMIT_RSS]		= {  RLIM_INFINITY,  RLIM_INFINITY },	\
 	[RLIMIT_NPROC]		= {              0,              0 },	\
diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h
index 49376aec2fbb..6dfd64b3a604 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -637,6 +637,22 @@
 	{0x1002, 0x983d, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KABINI|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x983e, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KABINI|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x983f, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_KABINI|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9850, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9851, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9852, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9853, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9854, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9855, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9856, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9857, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9858, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9859, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x985A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x985B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x985C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x985D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x985E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x985F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_MULLINS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9900, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9901, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9903, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARUBA|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h
index 940ece4934ba..012d58fa8ff0 100644
--- a/include/drm/i915_pciids.h
+++ b/include/drm/i915_pciids.h
@@ -191,8 +191,8 @@
 	INTEL_VGA_DEVICE(0x0A06, info), /* ULT GT1 mobile */ \
 	INTEL_VGA_DEVICE(0x0A16, info), /* ULT GT2 mobile */ \
 	INTEL_VGA_DEVICE(0x0A26, info), /* ULT GT3 mobile */ \
-	INTEL_VGA_DEVICE(0x0A0E, info), /* ULT GT1 reserved */ \
-	INTEL_VGA_DEVICE(0x0A1E, info), /* ULT GT2 reserved */ \
+	INTEL_VGA_DEVICE(0x0A0E, info), /* ULX GT1 mobile */ \
+	INTEL_VGA_DEVICE(0x0A1E, info), /* ULX GT2 mobile */ \
 	INTEL_VGA_DEVICE(0x0A2E, info), /* ULT GT3 reserved */ \
 	INTEL_VGA_DEVICE(0x0D06, info), /* CRW GT1 mobile */ \
 	INTEL_VGA_DEVICE(0x0D16, info), /* CRW GT2 mobile */ \
diff --git a/include/dt-bindings/clk/at91.h b/include/dt-bindings/clock/at91.h
index 0b4cb999a3f7..0b4cb999a3f7 100644
--- a/include/dt-bindings/clk/at91.h
+++ b/include/dt-bindings/clock/at91.h
diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h
index 63b5eff0a80f..fdd7e1b61f60 100644
--- a/include/linux/amba/bus.h
+++ b/include/linux/amba/bus.h
@@ -47,6 +47,7 @@ struct amba_driver {
 enum amba_vendor {
 	AMBA_VENDOR_ARM = 0x41,
 	AMBA_VENDOR_ST = 0x80,
+	AMBA_VENDOR_QCOM = 0x51,
 };
 
 extern struct bus_type amba_bustype;
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index c2515851c1aa..d60904b9e505 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -473,6 +473,7 @@ struct cftype {
 };
 
 extern struct cgroup_root cgrp_dfl_root;
+extern struct css_set init_css_set;
 
 static inline bool cgroup_on_dfl(const struct cgroup *cgrp)
 {
@@ -700,6 +701,20 @@ static inline struct cgroup_subsys_state *task_css(struct task_struct *task,
 	return task_css_check(task, subsys_id, false);
 }
 
+/**
+ * task_css_is_root - test whether a task belongs to the root css
+ * @task: the target task
+ * @subsys_id: the target subsystem ID
+ *
+ * Test whether @task belongs to the root css on the specified subsystem.
+ * May be invoked in any context.
+ */
+static inline bool task_css_is_root(struct task_struct *task, int subsys_id)
+{
+	return task_css_check(task, subsys_id, true) ==
+		init_css_set.subsys[subsys_id];
+}
+
 static inline struct cgroup *task_cgroup(struct task_struct *task,
 					 int subsys_id)
 {
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 8300fb87b84a..72cb0ddb9678 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -429,6 +429,7 @@ typedef bool (*dma_filter_fn)(struct dma_chan *chan, void *filter_param);
 typedef void (*dma_async_tx_callback)(void *dma_async_param);
 
 struct dmaengine_unmap_data {
+	u8 map_cnt;
 	u8 to_cnt;
 	u8 from_cnt;
 	u8 bidi_cnt;
diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h
index 7c8b20b120ea..a9a53b12397b 100644
--- a/include/linux/if_macvlan.h
+++ b/include/linux/if_macvlan.h
@@ -56,6 +56,7 @@ struct macvlan_dev {
 	int			numqueues;
 	netdev_features_t	tap_features;
 	int			minor;
+	int			nest_level;
 };
 
 static inline void macvlan_count_rx(const struct macvlan_dev *vlan,
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 13bbbde00e68..b2acc4a1b13c 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -73,7 +73,7 @@ static inline struct vlan_ethhdr *vlan_eth_hdr(const struct sk_buff *skb)
 /* found in socket.c */
 extern void vlan_ioctl_set(int (*hook)(struct net *, void __user *));
 
-static inline int is_vlan_dev(struct net_device *dev)
+static inline bool is_vlan_dev(struct net_device *dev)
 {
         return dev->priv_flags & IFF_802_1Q_VLAN;
 }
@@ -159,6 +159,7 @@ struct vlan_dev_priv {
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	struct netpoll				*netpoll;
 #endif
+	unsigned int				nest_level;
 };
 
 static inline struct vlan_dev_priv *vlan_dev_priv(const struct net_device *dev)
@@ -197,6 +198,12 @@ extern void vlan_vids_del_by_dev(struct net_device *dev,
 				 const struct net_device *by_dev);
 
 extern bool vlan_uses_dev(const struct net_device *dev);
+
+static inline int vlan_get_encap_level(struct net_device *dev)
+{
+	BUG_ON(!is_vlan_dev(dev));
+	return vlan_dev_priv(dev)->nest_level;
+}
 #else
 static inline struct net_device *
 __vlan_find_dev_deep(struct net_device *real_dev,
@@ -263,6 +270,11 @@ static inline bool vlan_uses_dev(const struct net_device *dev)
 {
 	return false;
 }
+static inline int vlan_get_encap_level(struct net_device *dev)
+{
+	BUG();
+	return 0;
+}
 #endif
 
 static inline bool vlan_hw_offload_capable(netdev_features_t features,
@@ -483,4 +495,5 @@ static inline void vlan_set_encap_proto(struct sk_buff *skb,
 		 */
 		skb->protocol = htons(ETH_P_802_2);
 }
+
 #endif /* !(_LINUX_IF_VLAN_H_) */
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 97ac926c78a7..051c85032f48 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -272,6 +272,11 @@ static inline int irq_set_affinity(unsigned int irq, const struct cpumask *m)
 	return -EINVAL;
 }
 
+static inline int irq_force_affinity(unsigned int irq, const struct cpumask *cpumask)
+{
+	return 0;
+}
+
 static inline int irq_can_set_affinity(unsigned int irq)
 {
 	return 0;
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index b0122dc6f96a..ca1be5c9136c 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -50,7 +50,24 @@ enum kernfs_node_flag {
 
 /* @flags for kernfs_create_root() */
 enum kernfs_root_flag {
-	KERNFS_ROOT_CREATE_DEACTIVATED = 0x0001,
+	/*
+	 * kernfs_nodes are created in the deactivated state and invisible.
+	 * They require explicit kernfs_activate() to become visible.  This
+	 * can be used to make related nodes become visible atomically
+	 * after all nodes are created successfully.
+	 */
+	KERNFS_ROOT_CREATE_DEACTIVATED		= 0x0001,
+
+	/*
+	 * For regular flies, if the opener has CAP_DAC_OVERRIDE, open(2)
+	 * succeeds regardless of the RW permissions.  sysfs had an extra
+	 * layer of enforcement where open(2) fails with -EACCES regardless
+	 * of CAP_DAC_OVERRIDE if the permission doesn't have the
+	 * respective read or write access at all (none of S_IRUGO or
+	 * S_IWUGO) or the respective operation isn't implemented.  The
+	 * following flag enables that behavior.
+	 */
+	KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK	= 0x0002,
 };
 
 /* type-specific structures for kernfs_node union members */
diff --git a/include/linux/linkage.h b/include/linux/linkage.h
index 34a513a2727b..a6a42dd02466 100644
--- a/include/linux/linkage.h
+++ b/include/linux/linkage.h
@@ -12,9 +12,9 @@
 #endif
 
 #ifdef __cplusplus
-#define CPP_ASMLINKAGE extern "C" __visible
+#define CPP_ASMLINKAGE extern "C"
 #else
-#define CPP_ASMLINKAGE __visible
+#define CPP_ASMLINKAGE
 #endif
 
 #ifndef asmlinkage
diff --git a/include/linux/mfd/rtsx_common.h b/include/linux/mfd/rtsx_common.h
index 7c36cc55d2c7..443176ee1ab0 100644
--- a/include/linux/mfd/rtsx_common.h
+++ b/include/linux/mfd/rtsx_common.h
@@ -45,7 +45,6 @@ struct platform_device;
 struct rtsx_slot {
 	struct platform_device	*p_dev;
 	void			(*card_event)(struct platform_device *p_dev);
-	void			(*done_transfer)(struct platform_device *p_dev);
 };
 
 #endif
diff --git a/include/linux/mfd/rtsx_pci.h b/include/linux/mfd/rtsx_pci.h
index 8d6bbd609ad9..a3835976f7c6 100644
--- a/include/linux/mfd/rtsx_pci.h
+++ b/include/linux/mfd/rtsx_pci.h
@@ -943,12 +943,6 @@ void rtsx_pci_send_cmd_no_wait(struct rtsx_pcr *pcr);
 int rtsx_pci_send_cmd(struct rtsx_pcr *pcr, int timeout);
 int rtsx_pci_transfer_data(struct rtsx_pcr *pcr, struct scatterlist *sglist,
 		int num_sg, bool read, int timeout);
-int rtsx_pci_dma_map_sg(struct rtsx_pcr *pcr, struct scatterlist *sglist,
-		int num_sg, bool read);
-int rtsx_pci_dma_unmap_sg(struct rtsx_pcr *pcr, struct scatterlist *sglist,
-		int num_sg, bool read);
-int rtsx_pci_dma_transfer(struct rtsx_pcr *pcr, struct scatterlist *sglist,
-		int sg_count, bool read);
 int rtsx_pci_read_ppbuf(struct rtsx_pcr *pcr, u8 *buf, int buf_len);
 int rtsx_pci_write_ppbuf(struct rtsx_pcr *pcr, u8 *buf, int buf_len);
 int rtsx_pci_card_pull_ctl_enable(struct rtsx_pcr *pcr, int card);
diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h
index b66e7610d4ee..7040dc98ff8b 100644
--- a/include/linux/mlx4/qp.h
+++ b/include/linux/mlx4/qp.h
@@ -421,6 +421,17 @@ struct mlx4_wqe_inline_seg {
 	__be32			byte_count;
 };
 
+enum mlx4_update_qp_attr {
+	MLX4_UPDATE_QP_SMAC		= 1 << 0,
+};
+
+struct mlx4_update_qp_params {
+	u8	smac_index;
+};
+
+int mlx4_update_qp(struct mlx4_dev *dev, struct mlx4_qp *qp,
+		   enum mlx4_update_qp_attr attr,
+		   struct mlx4_update_qp_params *params);
 int mlx4_qp_modify(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 		   enum mlx4_qp_state cur_state, enum mlx4_qp_state new_state,
 		   struct mlx4_qp_context *context, enum mlx4_qp_optpar optpar,
diff --git a/include/linux/net.h b/include/linux/net.h
index 94734a6259a4..17d83393afcc 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -248,24 +248,17 @@ do {								\
 bool __net_get_random_once(void *buf, int nbytes, bool *done,
 			   struct static_key *done_key);
 
-#ifdef HAVE_JUMP_LABEL
-#define ___NET_RANDOM_STATIC_KEY_INIT ((struct static_key) \
-		{ .enabled = ATOMIC_INIT(0), .entries = (void *)1 })
-#else /* !HAVE_JUMP_LABEL */
-#define ___NET_RANDOM_STATIC_KEY_INIT STATIC_KEY_INIT_FALSE
-#endif /* HAVE_JUMP_LABEL */
-
 #define net_get_random_once(buf, nbytes)				\
 	({								\
 		bool ___ret = false;					\
 		static bool ___done = false;				\
-		static struct static_key ___done_key =			\
-			___NET_RANDOM_STATIC_KEY_INIT;			\
-		if (!static_key_true(&___done_key))			\
+		static struct static_key ___once_key =			\
+			STATIC_KEY_INIT_TRUE;				\
+		if (static_key_true(&___once_key))			\
 			___ret = __net_get_random_once(buf,		\
 						       nbytes,		\
 						       &___done,	\
-						       &___done_key);	\
+						       &___once_key);	\
 		___ret;							\
 	})
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7ed3a3aa6604..b42d07b0390b 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1144,6 +1144,7 @@ struct net_device_ops {
 	netdev_tx_t		(*ndo_dfwd_start_xmit) (struct sk_buff *skb,
 							struct net_device *dev,
 							void *priv);
+	int			(*ndo_get_lock_subclass)(struct net_device *dev);
 };
 
 /**
@@ -2950,7 +2951,12 @@ static inline void netif_addr_lock(struct net_device *dev)
 
 static inline void netif_addr_lock_nested(struct net_device *dev)
 {
-	spin_lock_nested(&dev->addr_list_lock, SINGLE_DEPTH_NESTING);
+	int subclass = SINGLE_DEPTH_NESTING;
+
+	if (dev->netdev_ops->ndo_get_lock_subclass)
+		subclass = dev->netdev_ops->ndo_get_lock_subclass(dev);
+
+	spin_lock_nested(&dev->addr_list_lock, subclass);
 }
 
 static inline void netif_addr_lock_bh(struct net_device *dev)
@@ -3050,10 +3056,19 @@ extern int		weight_p;
 extern int		bpf_jit_enable;
 
 bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev);
+struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
+						     struct list_head **iter);
 struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev,
 						     struct list_head **iter);
 
 /* iterate through upper list, must be called under RCU read lock */
+#define netdev_for_each_upper_dev_rcu(dev, updev, iter) \
+	for (iter = &(dev)->adj_list.upper, \
+	     updev = netdev_upper_get_next_dev_rcu(dev, &(iter)); \
+	     updev; \
+	     updev = netdev_upper_get_next_dev_rcu(dev, &(iter)))
+
+/* iterate through upper list, must be called under RCU read lock */
 #define netdev_for_each_all_upper_dev_rcu(dev, updev, iter) \
 	for (iter = &(dev)->all_adj_list.upper, \
 	     updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter)); \
@@ -3077,6 +3092,14 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev,
 	     priv; \
 	     priv = netdev_lower_get_next_private_rcu(dev, &(iter)))
 
+void *netdev_lower_get_next(struct net_device *dev,
+				struct list_head **iter);
+#define netdev_for_each_lower_dev(dev, ldev, iter) \
+	for (iter = &(dev)->adj_list.lower, \
+	     ldev = netdev_lower_get_next(dev, &(iter)); \
+	     ldev; \
+	     ldev = netdev_lower_get_next(dev, &(iter)))
+
 void *netdev_adjacent_get_private(struct list_head *adj_list);
 void *netdev_lower_get_first_private_rcu(struct net_device *dev);
 struct net_device *netdev_master_upper_dev_get(struct net_device *dev);
@@ -3092,6 +3115,8 @@ void netdev_upper_dev_unlink(struct net_device *dev,
 void netdev_adjacent_rename_links(struct net_device *dev, char *oldname);
 void *netdev_lower_dev_get_private(struct net_device *dev,
 				   struct net_device *lower_dev);
+int dev_get_nest_level(struct net_device *dev,
+		       bool (*type_check)(struct net_device *dev));
 int skb_checksum_help(struct sk_buff *skb);
 struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
 				  netdev_features_t features, bool tx_path);
@@ -3180,12 +3205,7 @@ void netdev_change_features(struct net_device *dev);
 void netif_stacked_transfer_operstate(const struct net_device *rootdev,
 					struct net_device *dev);
 
-netdev_features_t netif_skb_dev_features(struct sk_buff *skb,
-					 const struct net_device *dev);
-static inline netdev_features_t netif_skb_features(struct sk_buff *skb)
-{
-	return netif_skb_dev_features(skb, skb->dev);
-}
+netdev_features_t netif_skb_features(struct sk_buff *skb);
 
 static inline bool net_gso_ok(netdev_features_t features, int gso_type)
 {
diff --git a/include/linux/of.h b/include/linux/of.h
index 3bad8d106e0e..e6f0988c1c68 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -349,7 +349,7 @@ int of_device_is_stdout_path(struct device_node *dn);
 
 #else /* CONFIG_OF */
 
-static inline const char* of_node_full_name(struct device_node *np)
+static inline const char* of_node_full_name(const struct device_node *np)
 {
 	return "<no-node>";
 }
diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h
index 6fe8464ed767..881a7c3571f4 100644
--- a/include/linux/of_mdio.h
+++ b/include/linux/of_mdio.h
@@ -31,7 +31,12 @@ extern struct mii_bus *of_mdio_find_bus(struct device_node *mdio_np);
 #else /* CONFIG_OF */
 static inline int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np)
 {
-	return -ENOSYS;
+	/*
+	 * Fall back to the non-DT function to register a bus.
+	 * This way, we don't have to keep compat bits around in drivers.
+	 */
+
+	return mdiobus_register(mdio);
 }
 
 static inline struct phy_device *of_phy_find_device(struct device_node *phy_np)
diff --git a/include/linux/omap-dma.h b/include/linux/omap-dma.h
index 41a13e70f41f..7944cdc27bed 100644
--- a/include/linux/omap-dma.h
+++ b/include/linux/omap-dma.h
@@ -10,7 +10,7 @@
 
 struct dma_chan;
 
-#if defined(CONFIG_DMA_OMAP) || defined(CONFIG_DMA_OMAP_MODULE)
+#if defined(CONFIG_DMA_OMAP) || (defined(CONFIG_DMA_OMAP_MODULE) && defined(MODULE))
 bool omap_dma_filter_fn(struct dma_chan *, void *);
 #else
 static inline bool omap_dma_filter_fn(struct dma_chan *c, void *d)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 3356abcfff18..3ef6ea12806a 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -402,6 +402,8 @@ struct perf_event {
 
 	struct ring_buffer		*rb;
 	struct list_head		rb_entry;
+	unsigned long			rcu_batches;
+	int				rcu_pending;
 
 	/* poll related */
 	wait_queue_head_t		waitq;
diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 8e3e66ac0a52..953937ea5233 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -4,6 +4,7 @@
 
 #include <linux/mutex.h>
 #include <linux/netdevice.h>
+#include <linux/wait.h>
 #include <uapi/linux/rtnetlink.h>
 
 extern int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, u32 group, int echo);
@@ -22,6 +23,10 @@ extern void rtnl_lock(void);
 extern void rtnl_unlock(void);
 extern int rtnl_trylock(void);
 extern int rtnl_is_locked(void);
+
+extern wait_queue_head_t netdev_unregistering_wq;
+extern struct mutex net_mutex;
+
 #ifdef CONFIG_PROVE_LOCKING
 extern int lockdep_rtnl_is_held(void);
 #else
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 25f54c79f757..221b2bde3723 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -220,7 +220,7 @@ print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
 #define TASK_PARKED		512
 #define TASK_STATE_MAX		1024
 
-#define TASK_STATE_TO_CHAR_STR "RSDTtZXxKWP"
+#define TASK_STATE_TO_CHAR_STR "RSDTtXZxKWP"
 
 extern char ___assert_task_state[1 - 2*!!(
 		sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1)];
@@ -1153,9 +1153,12 @@ struct sched_dl_entity {
 	 *
 	 * @dl_boosted tells if we are boosted due to DI. If so we are
 	 * outside bandwidth enforcement mechanism (but only until we
-	 * exit the critical section).
+	 * exit the critical section);
+	 *
+	 * @dl_yielded tells if task gave up the cpu before consuming
+	 * all its available runtime during the last job.
 	 */
-	int dl_throttled, dl_new, dl_boosted;
+	int dl_throttled, dl_new, dl_boosted, dl_yielded;
 
 	/*
 	 * Bandwidth enforcement timer. Each -deadline task has its
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index f3539a15c411..f856e5a746fa 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -3669,6 +3669,18 @@ void cfg80211_sched_scan_results(struct wiphy *wiphy);
 void cfg80211_sched_scan_stopped(struct wiphy *wiphy);
 
 /**
+ * cfg80211_sched_scan_stopped_rtnl - notify that the scheduled scan has stopped
+ *
+ * @wiphy: the wiphy on which the scheduled scan stopped
+ *
+ * The driver can call this function to inform cfg80211 that the
+ * scheduled scan had to be stopped, for whatever reason.  The driver
+ * is then called back via the sched_scan_stop operation when done.
+ * This function should be called with rtnl locked.
+ */
+void cfg80211_sched_scan_stopped_rtnl(struct wiphy *wiphy);
+
+/**
  * cfg80211_inform_bss_width_frame - inform cfg80211 of a received BSS frame
  *
  * @wiphy: the wiphy reporting the BSS
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 6c4f5eac98e7..216cecce65e9 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -127,6 +127,7 @@ int rt6_dump_route(struct rt6_info *rt, void *p_arg);
 void rt6_ifdown(struct net *net, struct net_device *dev);
 void rt6_mtu_change(struct net_device *dev, unsigned int mtu);
 void rt6_remove_prefsrc(struct inet6_ifaddr *ifp);
+void rt6_clean_tohost(struct net *net, struct in6_addr *gateway);
 
 
 /*
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 80f500a29498..b2704fd0ec80 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -20,6 +20,11 @@ struct local_ports {
 	int		range[2];
 };
 
+struct ping_group_range {
+	seqlock_t	lock;
+	kgid_t		range[2];
+};
+
 struct netns_ipv4 {
 #ifdef CONFIG_SYSCTL
 	struct ctl_table_header	*forw_hdr;
@@ -66,13 +71,13 @@ struct netns_ipv4 {
 	int sysctl_icmp_ratemask;
 	int sysctl_icmp_errors_use_inbound_ifaddr;
 
-	struct local_ports sysctl_local_ports;
+	struct local_ports ip_local_ports;
 
 	int sysctl_tcp_ecn;
 	int sysctl_ip_no_pmtu_disc;
 	int sysctl_ip_fwd_use_pmtu;
 
-	kgid_t sysctl_ping_group_range[2];
+	struct ping_group_range ping_group_range;
 
 	atomic_t dev_addr_genid;
 
diff --git a/include/trace/events/module.h b/include/trace/events/module.h
index ed0b2c599a64..7c5cbfe3fc49 100644
--- a/include/trace/events/module.h
+++ b/include/trace/events/module.h
@@ -80,7 +80,7 @@ DECLARE_EVENT_CLASS(module_refcnt,
 
 	TP_fast_assign(
 		__entry->ip	= ip;
-		__entry->refcnt	= __this_cpu_read(mod->refptr->incs) + __this_cpu_read(mod->refptr->decs);
+		__entry->refcnt	= __this_cpu_read(mod->refptr->incs) - __this_cpu_read(mod->refptr->decs);
 		__assign_str(name, mod->name);
 	),
 
diff --git a/include/uapi/asm-generic/resource.h b/include/uapi/asm-generic/resource.h
index f863428796d5..c6d10af50123 100644
--- a/include/uapi/asm-generic/resource.h
+++ b/include/uapi/asm-generic/resource.h
@@ -57,12 +57,5 @@
 # define RLIM_INFINITY		(~0UL)
 #endif
 
-/*
- * RLIMIT_STACK default maximum - some architectures override it:
- */
-#ifndef _STK_LIM_MAX
-# define _STK_LIM_MAX		RLIM_INFINITY
-#endif
-
 
 #endif /* _UAPI_ASM_GENERIC_RESOURCE_H */
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 6db66783d268..333640608087 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -697,9 +697,11 @@ __SYSCALL(__NR_finit_module, sys_finit_module)
 __SYSCALL(__NR_sched_setattr, sys_sched_setattr)
 #define __NR_sched_getattr 275
 __SYSCALL(__NR_sched_getattr, sys_sched_getattr)
+#define __NR_renameat2 276
+__SYSCALL(__NR_renameat2, sys_renameat2)
 
 #undef __NR_syscalls
-#define __NR_syscalls 276
+#define __NR_syscalls 277
 
 /*
  * All syscalls below here should go away really,
diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h
index 11917f747cb4..1b1efddb91cd 100644
--- a/include/uapi/linux/audit.h
+++ b/include/uapi/linux/audit.h
@@ -331,9 +331,17 @@ enum {
 #define AUDIT_FAIL_PRINTK	1
 #define AUDIT_FAIL_PANIC	2
 
+/*
+ * These bits disambiguate different calling conventions that share an
+ * ELF machine type, bitness, and endianness
+ */
+#define __AUDIT_ARCH_CONVENTION_MASK 0x30000000
+#define __AUDIT_ARCH_CONVENTION_MIPS64_N32 0x20000000
+
 /* distinguish syscall tables */
 #define __AUDIT_ARCH_64BIT 0x80000000
 #define __AUDIT_ARCH_LE	   0x40000000
+
 #define AUDIT_ARCH_ALPHA	(EM_ALPHA|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE)
 #define AUDIT_ARCH_ARM		(EM_ARM|__AUDIT_ARCH_LE)
 #define AUDIT_ARCH_ARMEB	(EM_ARM)
@@ -346,7 +354,11 @@ enum {
 #define AUDIT_ARCH_MIPS		(EM_MIPS)
 #define AUDIT_ARCH_MIPSEL	(EM_MIPS|__AUDIT_ARCH_LE)
 #define AUDIT_ARCH_MIPS64	(EM_MIPS|__AUDIT_ARCH_64BIT)
+#define AUDIT_ARCH_MIPS64N32	(EM_MIPS|__AUDIT_ARCH_64BIT|\
+				 __AUDIT_ARCH_CONVENTION_MIPS64_N32)
 #define AUDIT_ARCH_MIPSEL64	(EM_MIPS|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE)
+#define AUDIT_ARCH_MIPSEL64N32	(EM_MIPS|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE\
+				 __AUDIT_ARCH_CONVENTION_MIPS64_N32)
 #define AUDIT_ARCH_OPENRISC	(EM_OPENRISC)
 #define AUDIT_ARCH_PARISC	(EM_PARISC)
 #define AUDIT_ARCH_PARISC64	(EM_PARISC|__AUDIT_ARCH_64BIT)
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 1ba9d626aa83..194c1eab04d8 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -3856,6 +3856,8 @@ enum nl80211_ap_sme_features {
  * @NL80211_FEATURE_CELL_BASE_REG_HINTS: This driver has been tested
  *	to work properly to suppport receiving regulatory hints from
  *	cellular base stations.
+ * @NL80211_FEATURE_P2P_DEVICE_NEEDS_CHANNEL: (no longer available, only
+ *	here to reserve the value for API/ABI compatibility)
  * @NL80211_FEATURE_SAE: This driver supports simultaneous authentication of
  *	equals (SAE) with user space SME (NL80211_CMD_AUTHENTICATE) in station
  *	mode
@@ -3897,7 +3899,7 @@ enum nl80211_feature_flags {
 	NL80211_FEATURE_HT_IBSS				= 1 << 1,
 	NL80211_FEATURE_INACTIVITY_TIMER		= 1 << 2,
 	NL80211_FEATURE_CELL_BASE_REG_HINTS		= 1 << 3,
-	/* bit 4 is reserved - don't use */
+	NL80211_FEATURE_P2P_DEVICE_NEEDS_CHANNEL	= 1 << 4,
 	NL80211_FEATURE_SAE				= 1 << 5,
 	NL80211_FEATURE_LOW_PRIORITY_SCAN		= 1 << 6,
 	NL80211_FEATURE_SCAN_FLUSH			= 1 << 7,
diff --git a/init/main.c b/init/main.c
index 9c7fd4c9249f..48655ceb66f4 100644
--- a/init/main.c
+++ b/init/main.c
@@ -476,7 +476,7 @@ static void __init mm_init(void)
 	vmalloc_init();
 }
 
-asmlinkage void __init start_kernel(void)
+asmlinkage __visible void __init start_kernel(void)
 {
 	char * command_line;
 	extern const struct kernel_param __start___param[], __stop___param[];
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 9fcdaa705b6c..3f1ca934a237 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -348,7 +348,7 @@ struct cgrp_cset_link {
  * reference-counted, to improve performance when child cgroups
  * haven't been created.
  */
-static struct css_set init_css_set = {
+struct css_set init_css_set = {
 	.refcount		= ATOMIC_INIT(1),
 	.cgrp_links		= LIST_HEAD_INIT(init_css_set.cgrp_links),
 	.tasks			= LIST_HEAD_INIT(init_css_set.tasks),
@@ -1495,7 +1495,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 	 */
 	if (!use_task_css_set_links)
 		cgroup_enable_task_cg_lists();
-retry:
+
 	mutex_lock(&cgroup_tree_mutex);
 	mutex_lock(&cgroup_mutex);
 
@@ -1503,7 +1503,7 @@ retry:
 	ret = parse_cgroupfs_options(data, &opts);
 	if (ret)
 		goto out_unlock;
-
+retry:
 	/* look for a matching existing root */
 	if (!opts.subsys_mask && !opts.none && !opts.name) {
 		cgrp_dfl_root_visible = true;
@@ -1562,9 +1562,9 @@ retry:
 		if (!atomic_inc_not_zero(&root->cgrp.refcnt)) {
 			mutex_unlock(&cgroup_mutex);
 			mutex_unlock(&cgroup_tree_mutex);
-			kfree(opts.release_agent);
-			kfree(opts.name);
 			msleep(10);
+			mutex_lock(&cgroup_tree_mutex);
+			mutex_lock(&cgroup_mutex);
 			goto retry;
 		}
 
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index 2bc4a2256444..345628c78b5b 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -21,6 +21,7 @@
 #include <linux/uaccess.h>
 #include <linux/freezer.h>
 #include <linux/seq_file.h>
+#include <linux/mutex.h>
 
 /*
  * A cgroup is freezing if any FREEZING flags are set.  FREEZING_SELF is
@@ -42,9 +43,10 @@ enum freezer_state_flags {
 struct freezer {
 	struct cgroup_subsys_state	css;
 	unsigned int			state;
-	spinlock_t			lock;
 };
 
+static DEFINE_MUTEX(freezer_mutex);
+
 static inline struct freezer *css_freezer(struct cgroup_subsys_state *css)
 {
 	return css ? container_of(css, struct freezer, css) : NULL;
@@ -93,7 +95,6 @@ freezer_css_alloc(struct cgroup_subsys_state *parent_css)
 	if (!freezer)
 		return ERR_PTR(-ENOMEM);
 
-	spin_lock_init(&freezer->lock);
 	return &freezer->css;
 }
 
@@ -110,14 +111,7 @@ static int freezer_css_online(struct cgroup_subsys_state *css)
 	struct freezer *freezer = css_freezer(css);
 	struct freezer *parent = parent_freezer(freezer);
 
-	/*
-	 * The following double locking and freezing state inheritance
-	 * guarantee that @cgroup can never escape ancestors' freezing
-	 * states.  See css_for_each_descendant_pre() for details.
-	 */
-	if (parent)
-		spin_lock_irq(&parent->lock);
-	spin_lock_nested(&freezer->lock, SINGLE_DEPTH_NESTING);
+	mutex_lock(&freezer_mutex);
 
 	freezer->state |= CGROUP_FREEZER_ONLINE;
 
@@ -126,10 +120,7 @@ static int freezer_css_online(struct cgroup_subsys_state *css)
 		atomic_inc(&system_freezing_cnt);
 	}
 
-	spin_unlock(&freezer->lock);
-	if (parent)
-		spin_unlock_irq(&parent->lock);
-
+	mutex_unlock(&freezer_mutex);
 	return 0;
 }
 
@@ -144,14 +135,14 @@ static void freezer_css_offline(struct cgroup_subsys_state *css)
 {
 	struct freezer *freezer = css_freezer(css);
 
-	spin_lock_irq(&freezer->lock);
+	mutex_lock(&freezer_mutex);
 
 	if (freezer->state & CGROUP_FREEZING)
 		atomic_dec(&system_freezing_cnt);
 
 	freezer->state = 0;
 
-	spin_unlock_irq(&freezer->lock);
+	mutex_unlock(&freezer_mutex);
 }
 
 static void freezer_css_free(struct cgroup_subsys_state *css)
@@ -175,7 +166,7 @@ static void freezer_attach(struct cgroup_subsys_state *new_css,
 	struct task_struct *task;
 	bool clear_frozen = false;
 
-	spin_lock_irq(&freezer->lock);
+	mutex_lock(&freezer_mutex);
 
 	/*
 	 * Make the new tasks conform to the current state of @new_css.
@@ -197,21 +188,13 @@ static void freezer_attach(struct cgroup_subsys_state *new_css,
 		}
 	}
 
-	spin_unlock_irq(&freezer->lock);
-
-	/*
-	 * Propagate FROZEN clearing upwards.  We may race with
-	 * update_if_frozen(), but as long as both work bottom-up, either
-	 * update_if_frozen() sees child's FROZEN cleared or we clear the
-	 * parent's FROZEN later.  No parent w/ !FROZEN children can be
-	 * left FROZEN.
-	 */
+	/* propagate FROZEN clearing upwards */
 	while (clear_frozen && (freezer = parent_freezer(freezer))) {
-		spin_lock_irq(&freezer->lock);
 		freezer->state &= ~CGROUP_FROZEN;
 		clear_frozen = freezer->state & CGROUP_FREEZING;
-		spin_unlock_irq(&freezer->lock);
 	}
+
+	mutex_unlock(&freezer_mutex);
 }
 
 /**
@@ -228,9 +211,6 @@ static void freezer_fork(struct task_struct *task)
 {
 	struct freezer *freezer;
 
-	rcu_read_lock();
-	freezer = task_freezer(task);
-
 	/*
 	 * The root cgroup is non-freezable, so we can skip locking the
 	 * freezer.  This is safe regardless of race with task migration.
@@ -238,24 +218,18 @@ static void freezer_fork(struct task_struct *task)
 	 * to do.  If we lost and root is the new cgroup, noop is still the
 	 * right thing to do.
 	 */
-	if (!parent_freezer(freezer))
-		goto out;
+	if (task_css_is_root(task, freezer_cgrp_id))
+		return;
 
-	/*
-	 * Grab @freezer->lock and freeze @task after verifying @task still
-	 * belongs to @freezer and it's freezing.  The former is for the
-	 * case where we have raced against task migration and lost and
-	 * @task is already in a different cgroup which may not be frozen.
-	 * This isn't strictly necessary as freeze_task() is allowed to be
-	 * called spuriously but let's do it anyway for, if nothing else,
-	 * documentation.
-	 */
-	spin_lock_irq(&freezer->lock);
-	if (freezer == task_freezer(task) && (freezer->state & CGROUP_FREEZING))
+	mutex_lock(&freezer_mutex);
+	rcu_read_lock();
+
+	freezer = task_freezer(task);
+	if (freezer->state & CGROUP_FREEZING)
 		freeze_task(task);
-	spin_unlock_irq(&freezer->lock);
-out:
+
 	rcu_read_unlock();
+	mutex_unlock(&freezer_mutex);
 }
 
 /**
@@ -281,22 +255,24 @@ static void update_if_frozen(struct cgroup_subsys_state *css)
 	struct css_task_iter it;
 	struct task_struct *task;
 
-	WARN_ON_ONCE(!rcu_read_lock_held());
-
-	spin_lock_irq(&freezer->lock);
+	lockdep_assert_held(&freezer_mutex);
 
 	if (!(freezer->state & CGROUP_FREEZING) ||
 	    (freezer->state & CGROUP_FROZEN))
-		goto out_unlock;
+		return;
 
 	/* are all (live) children frozen? */
+	rcu_read_lock();
 	css_for_each_child(pos, css) {
 		struct freezer *child = css_freezer(pos);
 
 		if ((child->state & CGROUP_FREEZER_ONLINE) &&
-		    !(child->state & CGROUP_FROZEN))
-			goto out_unlock;
+		    !(child->state & CGROUP_FROZEN)) {
+			rcu_read_unlock();
+			return;
+		}
 	}
+	rcu_read_unlock();
 
 	/* are all tasks frozen? */
 	css_task_iter_start(css, &it);
@@ -317,21 +293,29 @@ static void update_if_frozen(struct cgroup_subsys_state *css)
 	freezer->state |= CGROUP_FROZEN;
 out_iter_end:
 	css_task_iter_end(&it);
-out_unlock:
-	spin_unlock_irq(&freezer->lock);
 }
 
 static int freezer_read(struct seq_file *m, void *v)
 {
 	struct cgroup_subsys_state *css = seq_css(m), *pos;
 
+	mutex_lock(&freezer_mutex);
 	rcu_read_lock();
 
 	/* update states bottom-up */
-	css_for_each_descendant_post(pos, css)
+	css_for_each_descendant_post(pos, css) {
+		if (!css_tryget(pos))
+			continue;
+		rcu_read_unlock();
+
 		update_if_frozen(pos);
 
+		rcu_read_lock();
+		css_put(pos);
+	}
+
 	rcu_read_unlock();
+	mutex_unlock(&freezer_mutex);
 
 	seq_puts(m, freezer_state_strs(css_freezer(css)->state));
 	seq_putc(m, '\n');
@@ -373,7 +357,7 @@ static void freezer_apply_state(struct freezer *freezer, bool freeze,
 				unsigned int state)
 {
 	/* also synchronizes against task migration, see freezer_attach() */
-	lockdep_assert_held(&freezer->lock);
+	lockdep_assert_held(&freezer_mutex);
 
 	if (!(freezer->state & CGROUP_FREEZER_ONLINE))
 		return;
@@ -414,31 +398,29 @@ static void freezer_change_state(struct freezer *freezer, bool freeze)
 	 * descendant will try to inherit its parent's FREEZING state as
 	 * CGROUP_FREEZING_PARENT.
 	 */
+	mutex_lock(&freezer_mutex);
 	rcu_read_lock();
 	css_for_each_descendant_pre(pos, &freezer->css) {
 		struct freezer *pos_f = css_freezer(pos);
 		struct freezer *parent = parent_freezer(pos_f);
 
-		spin_lock_irq(&pos_f->lock);
+		if (!css_tryget(pos))
+			continue;
+		rcu_read_unlock();
 
-		if (pos_f == freezer) {
+		if (pos_f == freezer)
 			freezer_apply_state(pos_f, freeze,
 					    CGROUP_FREEZING_SELF);
-		} else {
-			/*
-			 * Our update to @parent->state is already visible
-			 * which is all we need.  No need to lock @parent.
-			 * For more info on synchronization, see
-			 * freezer_post_create().
-			 */
+		else
 			freezer_apply_state(pos_f,
 					    parent->state & CGROUP_FREEZING,
 					    CGROUP_FREEZING_PARENT);
-		}
 
-		spin_unlock_irq(&pos_f->lock);
+		rcu_read_lock();
+		css_put(pos);
 	}
 	rcu_read_unlock();
+	mutex_unlock(&freezer_mutex);
 }
 
 static int freezer_write(struct cgroup_subsys_state *css, struct cftype *cft,
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index 6cb20d2e7ee0..019d45008448 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -120,7 +120,7 @@ void context_tracking_user_enter(void)
  * instead of preempt_schedule() to exit user context if needed before
  * calling the scheduler.
  */
-asmlinkage void __sched notrace preempt_schedule_context(void)
+asmlinkage __visible void __sched notrace preempt_schedule_context(void)
 {
 	enum ctx_state prev_ctx;
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index f83a71a3e46d..440eefc67397 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1443,6 +1443,11 @@ group_sched_out(struct perf_event *group_event,
 		cpuctx->exclusive = 0;
 }
 
+struct remove_event {
+	struct perf_event *event;
+	bool detach_group;
+};
+
 /*
  * Cross CPU call to remove a performance event
  *
@@ -1451,12 +1456,15 @@ group_sched_out(struct perf_event *group_event,
  */
 static int __perf_remove_from_context(void *info)
 {
-	struct perf_event *event = info;
+	struct remove_event *re = info;
+	struct perf_event *event = re->event;
 	struct perf_event_context *ctx = event->ctx;
 	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
 
 	raw_spin_lock(&ctx->lock);
 	event_sched_out(event, cpuctx, ctx);
+	if (re->detach_group)
+		perf_group_detach(event);
 	list_del_event(event, ctx);
 	if (!ctx->nr_events && cpuctx->task_ctx == ctx) {
 		ctx->is_active = 0;
@@ -1481,10 +1489,14 @@ static int __perf_remove_from_context(void *info)
  * When called from perf_event_exit_task, it's OK because the
  * context has been detached from its task.
  */
-static void perf_remove_from_context(struct perf_event *event)
+static void perf_remove_from_context(struct perf_event *event, bool detach_group)
 {
 	struct perf_event_context *ctx = event->ctx;
 	struct task_struct *task = ctx->task;
+	struct remove_event re = {
+		.event = event,
+		.detach_group = detach_group,
+	};
 
 	lockdep_assert_held(&ctx->mutex);
 
@@ -1493,12 +1505,12 @@ static void perf_remove_from_context(struct perf_event *event)
 		 * Per cpu events are removed via an smp call and
 		 * the removal is always successful.
 		 */
-		cpu_function_call(event->cpu, __perf_remove_from_context, event);
+		cpu_function_call(event->cpu, __perf_remove_from_context, &re);
 		return;
 	}
 
 retry:
-	if (!task_function_call(task, __perf_remove_from_context, event))
+	if (!task_function_call(task, __perf_remove_from_context, &re))
 		return;
 
 	raw_spin_lock_irq(&ctx->lock);
@@ -1515,6 +1527,8 @@ retry:
 	 * Since the task isn't running, its safe to remove the event, us
 	 * holding the ctx->lock ensures the task won't get scheduled in.
 	 */
+	if (detach_group)
+		perf_group_detach(event);
 	list_del_event(event, ctx);
 	raw_spin_unlock_irq(&ctx->lock);
 }
@@ -3178,7 +3192,8 @@ static void free_event_rcu(struct rcu_head *head)
 }
 
 static void ring_buffer_put(struct ring_buffer *rb);
-static void ring_buffer_detach(struct perf_event *event, struct ring_buffer *rb);
+static void ring_buffer_attach(struct perf_event *event,
+			       struct ring_buffer *rb);
 
 static void unaccount_event_cpu(struct perf_event *event, int cpu)
 {
@@ -3238,8 +3253,6 @@ static void free_event(struct perf_event *event)
 	unaccount_event(event);
 
 	if (event->rb) {
-		struct ring_buffer *rb;
-
 		/*
 		 * Can happen when we close an event with re-directed output.
 		 *
@@ -3247,12 +3260,7 @@ static void free_event(struct perf_event *event)
 		 * over us; possibly making our ring_buffer_put() the last.
 		 */
 		mutex_lock(&event->mmap_mutex);
-		rb = event->rb;
-		if (rb) {
-			rcu_assign_pointer(event->rb, NULL);
-			ring_buffer_detach(event, rb);
-			ring_buffer_put(rb); /* could be last */
-		}
+		ring_buffer_attach(event, NULL);
 		mutex_unlock(&event->mmap_mutex);
 	}
 
@@ -3281,10 +3289,7 @@ int perf_event_release_kernel(struct perf_event *event)
 	 *     to trigger the AB-BA case.
 	 */
 	mutex_lock_nested(&ctx->mutex, SINGLE_DEPTH_NESTING);
-	raw_spin_lock_irq(&ctx->lock);
-	perf_group_detach(event);
-	raw_spin_unlock_irq(&ctx->lock);
-	perf_remove_from_context(event);
+	perf_remove_from_context(event, true);
 	mutex_unlock(&ctx->mutex);
 
 	free_event(event);
@@ -3839,28 +3844,47 @@ unlock:
 static void ring_buffer_attach(struct perf_event *event,
 			       struct ring_buffer *rb)
 {
+	struct ring_buffer *old_rb = NULL;
 	unsigned long flags;
 
-	if (!list_empty(&event->rb_entry))
-		return;
+	if (event->rb) {
+		/*
+		 * Should be impossible, we set this when removing
+		 * event->rb_entry and wait/clear when adding event->rb_entry.
+		 */
+		WARN_ON_ONCE(event->rcu_pending);
 
-	spin_lock_irqsave(&rb->event_lock, flags);
-	if (list_empty(&event->rb_entry))
-		list_add(&event->rb_entry, &rb->event_list);
-	spin_unlock_irqrestore(&rb->event_lock, flags);
-}
+		old_rb = event->rb;
+		event->rcu_batches = get_state_synchronize_rcu();
+		event->rcu_pending = 1;
 
-static void ring_buffer_detach(struct perf_event *event, struct ring_buffer *rb)
-{
-	unsigned long flags;
+		spin_lock_irqsave(&old_rb->event_lock, flags);
+		list_del_rcu(&event->rb_entry);
+		spin_unlock_irqrestore(&old_rb->event_lock, flags);
+	}
 
-	if (list_empty(&event->rb_entry))
-		return;
+	if (event->rcu_pending && rb) {
+		cond_synchronize_rcu(event->rcu_batches);
+		event->rcu_pending = 0;
+	}
+
+	if (rb) {
+		spin_lock_irqsave(&rb->event_lock, flags);
+		list_add_rcu(&event->rb_entry, &rb->event_list);
+		spin_unlock_irqrestore(&rb->event_lock, flags);
+	}
+
+	rcu_assign_pointer(event->rb, rb);
 
-	spin_lock_irqsave(&rb->event_lock, flags);
-	list_del_init(&event->rb_entry);
-	wake_up_all(&event->waitq);
-	spin_unlock_irqrestore(&rb->event_lock, flags);
+	if (old_rb) {
+		ring_buffer_put(old_rb);
+		/*
+		 * Since we detached before setting the new rb, so that we
+		 * could attach the new rb, we could have missed a wakeup.
+		 * Provide it now.
+		 */
+		wake_up_all(&event->waitq);
+	}
 }
 
 static void ring_buffer_wakeup(struct perf_event *event)
@@ -3929,7 +3953,7 @@ static void perf_mmap_close(struct vm_area_struct *vma)
 {
 	struct perf_event *event = vma->vm_file->private_data;
 
-	struct ring_buffer *rb = event->rb;
+	struct ring_buffer *rb = ring_buffer_get(event);
 	struct user_struct *mmap_user = rb->mmap_user;
 	int mmap_locked = rb->mmap_locked;
 	unsigned long size = perf_data_size(rb);
@@ -3937,18 +3961,14 @@ static void perf_mmap_close(struct vm_area_struct *vma)
 	atomic_dec(&rb->mmap_count);
 
 	if (!atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex))
-		return;
+		goto out_put;
 
-	/* Detach current event from the buffer. */
-	rcu_assign_pointer(event->rb, NULL);
-	ring_buffer_detach(event, rb);
+	ring_buffer_attach(event, NULL);
 	mutex_unlock(&event->mmap_mutex);
 
 	/* If there's still other mmap()s of this buffer, we're done. */
-	if (atomic_read(&rb->mmap_count)) {
-		ring_buffer_put(rb); /* can't be last */
-		return;
-	}
+	if (atomic_read(&rb->mmap_count))
+		goto out_put;
 
 	/*
 	 * No other mmap()s, detach from all other events that might redirect
@@ -3978,11 +3998,9 @@ again:
 		 * still restart the iteration to make sure we're not now
 		 * iterating the wrong list.
 		 */
-		if (event->rb == rb) {
-			rcu_assign_pointer(event->rb, NULL);
-			ring_buffer_detach(event, rb);
-			ring_buffer_put(rb); /* can't be last, we still have one */
-		}
+		if (event->rb == rb)
+			ring_buffer_attach(event, NULL);
+
 		mutex_unlock(&event->mmap_mutex);
 		put_event(event);
 
@@ -4007,6 +4025,7 @@ again:
 	vma->vm_mm->pinned_vm -= mmap_locked;
 	free_uid(mmap_user);
 
+out_put:
 	ring_buffer_put(rb); /* could be last */
 }
 
@@ -4124,7 +4143,6 @@ again:
 	vma->vm_mm->pinned_vm += extra;
 
 	ring_buffer_attach(event, rb);
-	rcu_assign_pointer(event->rb, rb);
 
 	perf_event_init_userpage(event);
 	perf_event_update_userpage(event);
@@ -5408,6 +5426,9 @@ struct swevent_htable {
 
 	/* Recursion avoidance in each contexts */
 	int				recursion[PERF_NR_CONTEXTS];
+
+	/* Keeps track of cpu being initialized/exited */
+	bool				online;
 };
 
 static DEFINE_PER_CPU(struct swevent_htable, swevent_htable);
@@ -5654,8 +5675,14 @@ static int perf_swevent_add(struct perf_event *event, int flags)
 	hwc->state = !(flags & PERF_EF_START);
 
 	head = find_swevent_head(swhash, event);
-	if (WARN_ON_ONCE(!head))
+	if (!head) {
+		/*
+		 * We can race with cpu hotplug code. Do not
+		 * WARN if the cpu just got unplugged.
+		 */
+		WARN_ON_ONCE(swhash->online);
 		return -EINVAL;
+	}
 
 	hlist_add_head_rcu(&event->hlist_entry, head);
 
@@ -6914,7 +6941,7 @@ err_size:
 static int
 perf_event_set_output(struct perf_event *event, struct perf_event *output_event)
 {
-	struct ring_buffer *rb = NULL, *old_rb = NULL;
+	struct ring_buffer *rb = NULL;
 	int ret = -EINVAL;
 
 	if (!output_event)
@@ -6942,8 +6969,6 @@ set:
 	if (atomic_read(&event->mmap_count))
 		goto unlock;
 
-	old_rb = event->rb;
-
 	if (output_event) {
 		/* get the rb we want to redirect to */
 		rb = ring_buffer_get(output_event);
@@ -6951,23 +6976,7 @@ set:
 			goto unlock;
 	}
 
-	if (old_rb)
-		ring_buffer_detach(event, old_rb);
-
-	if (rb)
-		ring_buffer_attach(event, rb);
-
-	rcu_assign_pointer(event->rb, rb);
-
-	if (old_rb) {
-		ring_buffer_put(old_rb);
-		/*
-		 * Since we detached before setting the new rb, so that we
-		 * could attach the new rb, we could have missed a wakeup.
-		 * Provide it now.
-		 */
-		wake_up_all(&event->waitq);
-	}
+	ring_buffer_attach(event, rb);
 
 	ret = 0;
 unlock:
@@ -7018,6 +7027,9 @@ SYSCALL_DEFINE5(perf_event_open,
 	if (attr.freq) {
 		if (attr.sample_freq > sysctl_perf_event_sample_rate)
 			return -EINVAL;
+	} else {
+		if (attr.sample_period & (1ULL << 63))
+			return -EINVAL;
 	}
 
 	/*
@@ -7165,7 +7177,7 @@ SYSCALL_DEFINE5(perf_event_open,
 		struct perf_event_context *gctx = group_leader->ctx;
 
 		mutex_lock(&gctx->mutex);
-		perf_remove_from_context(group_leader);
+		perf_remove_from_context(group_leader, false);
 
 		/*
 		 * Removing from the context ends up with disabled
@@ -7175,7 +7187,7 @@ SYSCALL_DEFINE5(perf_event_open,
 		perf_event__state_init(group_leader);
 		list_for_each_entry(sibling, &group_leader->sibling_list,
 				    group_entry) {
-			perf_remove_from_context(sibling);
+			perf_remove_from_context(sibling, false);
 			perf_event__state_init(sibling);
 			put_ctx(gctx);
 		}
@@ -7305,7 +7317,7 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
 	mutex_lock(&src_ctx->mutex);
 	list_for_each_entry_safe(event, tmp, &src_ctx->event_list,
 				 event_entry) {
-		perf_remove_from_context(event);
+		perf_remove_from_context(event, false);
 		unaccount_event_cpu(event, src_cpu);
 		put_ctx(src_ctx);
 		list_add(&event->migrate_entry, &events);
@@ -7367,13 +7379,7 @@ __perf_event_exit_task(struct perf_event *child_event,
 			 struct perf_event_context *child_ctx,
 			 struct task_struct *child)
 {
-	if (child_event->parent) {
-		raw_spin_lock_irq(&child_ctx->lock);
-		perf_group_detach(child_event);
-		raw_spin_unlock_irq(&child_ctx->lock);
-	}
-
-	perf_remove_from_context(child_event);
+	perf_remove_from_context(child_event, !!child_event->parent);
 
 	/*
 	 * It can happen that the parent exits first, and has events
@@ -7724,6 +7730,8 @@ int perf_event_init_context(struct task_struct *child, int ctxn)
 	 * swapped under us.
 	 */
 	parent_ctx = perf_pin_task_context(parent, ctxn);
+	if (!parent_ctx)
+		return 0;
 
 	/*
 	 * No need to check if parent_ctx != NULL here; since we saw
@@ -7835,6 +7843,7 @@ static void perf_event_init_cpu(int cpu)
 	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
 	mutex_lock(&swhash->hlist_mutex);
+	swhash->online = true;
 	if (swhash->hlist_refcount > 0) {
 		struct swevent_hlist *hlist;
 
@@ -7857,14 +7866,14 @@ static void perf_pmu_rotate_stop(struct pmu *pmu)
 
 static void __perf_event_exit_context(void *__info)
 {
+	struct remove_event re = { .detach_group = false };
 	struct perf_event_context *ctx = __info;
-	struct perf_event *event;
 
 	perf_pmu_rotate_stop(ctx->pmu);
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(event, &ctx->event_list, event_entry)
-		__perf_remove_from_context(event);
+	list_for_each_entry_rcu(re.event, &ctx->event_list, event_entry)
+		__perf_remove_from_context(&re);
 	rcu_read_unlock();
 }
 
@@ -7892,6 +7901,7 @@ static void perf_event_exit_cpu(int cpu)
 	perf_event_exit_cpu_context(cpu);
 
 	mutex_lock(&swhash->hlist_mutex);
+	swhash->online = false;
 	swevent_hlist_release(swhash);
 	mutex_unlock(&swhash->hlist_mutex);
 }
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 6b715c0af1b1..e0501fe7140d 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -990,11 +990,8 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 	/* Remove an active timer from the queue: */
 	ret = remove_hrtimer(timer, base);
 
-	/* Switch the timer base, if necessary: */
-	new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED);
-
 	if (mode & HRTIMER_MODE_REL) {
-		tim = ktime_add_safe(tim, new_base->get_time());
+		tim = ktime_add_safe(tim, base->get_time());
 		/*
 		 * CONFIG_TIME_LOW_RES is a temporary way for architectures
 		 * to signal that they simply return xtime in
@@ -1009,6 +1006,9 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 
 	hrtimer_set_expires_range_ns(timer, tim, delta_ns);
 
+	/* Switch the timer base, if necessary: */
+	new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED);
+
 	timer_stats_hrtimer_set_start_info(timer);
 
 	leftmost = enqueue_hrtimer(timer, new_base);
diff --git a/kernel/kexec.c b/kernel/kexec.c
index c8380ad203bc..28c57069ef68 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1683,6 +1683,14 @@ int kernel_kexec(void)
 		kexec_in_progress = true;
 		kernel_restart_prepare(NULL);
 		migrate_to_reboot_cpu();
+
+		/*
+		 * migrate_to_reboot_cpu() disables CPU hotplug assuming that
+		 * no further code needs to use CPU hotplug (which is true in
+		 * the reboot case). However, the kexec path depends on using
+		 * CPU hotplug again; so re-enable it here.
+		 */
+		cpu_hotplug_enable();
 		printk(KERN_EMERG "Starting new kernel\n");
 		machine_shutdown();
 	}
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index b0e9467922e1..d24e4339b46d 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -4188,7 +4188,7 @@ void debug_show_held_locks(struct task_struct *task)
 }
 EXPORT_SYMBOL_GPL(debug_show_held_locks);
 
-asmlinkage void lockdep_sys_exit(void)
+asmlinkage __visible void lockdep_sys_exit(void)
 {
 	struct task_struct *curr = current;
 
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 18fb7a2fb14b..1ea328aafdc9 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1586,7 +1586,7 @@ swsusp_alloc(struct memory_bitmap *orig_bm, struct memory_bitmap *copy_bm,
 	return -ENOMEM;
 }
 
-asmlinkage int swsusp_save(void)
+asmlinkage __visible int swsusp_save(void)
 {
 	unsigned int nr_pages, nr_highmem;
 
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index a45b50962295..7228258b85ec 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1674,7 +1674,7 @@ EXPORT_SYMBOL(printk_emit);
  *
  * See the vsnprintf() documentation for format string extensions over C99.
  */
-asmlinkage int printk(const char *fmt, ...)
+asmlinkage __visible int printk(const char *fmt, ...)
 {
 	va_list args;
 	int r;
@@ -1737,7 +1737,7 @@ void early_vprintk(const char *fmt, va_list ap)
 	}
 }
 
-asmlinkage void early_printk(const char *fmt, ...)
+asmlinkage __visible void early_printk(const char *fmt, ...)
 {
 	va_list ap;
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 268a45ea238c..204d3d281809 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2192,7 +2192,7 @@ static inline void post_schedule(struct rq *rq)
  * schedule_tail - first thing a freshly forked thread must call.
  * @prev: the thread we just switched away from.
  */
-asmlinkage void schedule_tail(struct task_struct *prev)
+asmlinkage __visible void schedule_tail(struct task_struct *prev)
 	__releases(rq->lock)
 {
 	struct rq *rq = this_rq();
@@ -2592,8 +2592,14 @@ pick_next_task(struct rq *rq, struct task_struct *prev)
 	if (likely(prev->sched_class == class &&
 		   rq->nr_running == rq->cfs.h_nr_running)) {
 		p = fair_sched_class.pick_next_task(rq, prev);
-		if (likely(p && p != RETRY_TASK))
-			return p;
+		if (unlikely(p == RETRY_TASK))
+			goto again;
+
+		/* assumes fair_sched_class->next == idle_sched_class */
+		if (unlikely(!p))
+			p = idle_sched_class.pick_next_task(rq, prev);
+
+		return p;
 	}
 
 again:
@@ -2741,7 +2747,7 @@ static inline void sched_submit_work(struct task_struct *tsk)
 		blk_schedule_flush_plug(tsk);
 }
 
-asmlinkage void __sched schedule(void)
+asmlinkage __visible void __sched schedule(void)
 {
 	struct task_struct *tsk = current;
 
@@ -2751,7 +2757,7 @@ asmlinkage void __sched schedule(void)
 EXPORT_SYMBOL(schedule);
 
 #ifdef CONFIG_CONTEXT_TRACKING
-asmlinkage void __sched schedule_user(void)
+asmlinkage __visible void __sched schedule_user(void)
 {
 	/*
 	 * If we come here after a random call to set_need_resched(),
@@ -2783,7 +2789,7 @@ void __sched schedule_preempt_disabled(void)
  * off of preempt_enable. Kernel preemptions off return from interrupt
  * occur there and call schedule directly.
  */
-asmlinkage void __sched notrace preempt_schedule(void)
+asmlinkage __visible void __sched notrace preempt_schedule(void)
 {
 	/*
 	 * If there is a non-zero preempt_count or interrupts are disabled,
@@ -2813,7 +2819,7 @@ EXPORT_SYMBOL(preempt_schedule);
  * Note, that this is called and return with irqs disabled. This will
  * protect us against recursive calling from irq.
  */
-asmlinkage void __sched preempt_schedule_irq(void)
+asmlinkage __visible void __sched preempt_schedule_irq(void)
 {
 	enum ctx_state prev_state;
 
@@ -3124,6 +3130,7 @@ __setparam_dl(struct task_struct *p, const struct sched_attr *attr)
 	dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);
 	dl_se->dl_throttled = 0;
 	dl_se->dl_new = 1;
+	dl_se->dl_yielded = 0;
 }
 
 static void __setscheduler_params(struct task_struct *p,
@@ -3639,6 +3646,7 @@ SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
  * sys_sched_setattr - same as above, but with extended sched_attr
  * @pid: the pid in question.
  * @uattr: structure containing the extended parameters.
+ * @flags: for future extension.
  */
 SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
 			       unsigned int, flags)
@@ -3783,6 +3791,7 @@ err_size:
  * @pid: the pid in question.
  * @uattr: structure containing the extended parameters.
  * @size: sizeof(attr) for fwd/bwd comp.
+ * @flags: for future extension.
  */
 SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
 		unsigned int, size, unsigned int, flags)
@@ -6017,6 +6026,8 @@ sd_numa_init(struct sched_domain_topology_level *tl, int cpu)
 					,
 		.last_balance		= jiffies,
 		.balance_interval	= sd_weight,
+		.max_newidle_lb_cost	= 0,
+		.next_decay_max_lb_cost	= jiffies,
 	};
 	SD_INIT_NAME(sd, NUMA);
 	sd->private = &tl->data;
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index 5b9bb42b2d47..ab001b5d5048 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -210,7 +210,5 @@ int cpudl_init(struct cpudl *cp)
  */
 void cpudl_cleanup(struct cpudl *cp)
 {
-	/*
-	 * nothing to do for the moment
-	 */
+	free_cpumask_var(cp->free_cpus);
 }
diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c
index 8b836b376d91..3031bac8aa3e 100644
--- a/kernel/sched/cpupri.c
+++ b/kernel/sched/cpupri.c
@@ -70,8 +70,7 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p,
 	int idx = 0;
 	int task_pri = convert_prio(p->prio);
 
-	if (task_pri >= MAX_RT_PRIO)
-		return 0;
+	BUG_ON(task_pri >= CPUPRI_NR_PRIORITIES);
 
 	for (idx = 0; idx < task_pri; idx++) {
 		struct cpupri_vec *vec  = &cp->pri_to_cpu[idx];
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index a95097cb4591..72fdf06ef865 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -332,50 +332,50 @@ out:
  * softirq as those do not count in task exec_runtime any more.
  */
 static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
-						struct rq *rq)
+					 struct rq *rq, int ticks)
 {
-	cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
+	cputime_t scaled = cputime_to_scaled(cputime_one_jiffy);
+	u64 cputime = (__force u64) cputime_one_jiffy;
 	u64 *cpustat = kcpustat_this_cpu->cpustat;
 
 	if (steal_account_process_tick())
 		return;
 
+	cputime *= ticks;
+	scaled *= ticks;
+
 	if (irqtime_account_hi_update()) {
-		cpustat[CPUTIME_IRQ] += (__force u64) cputime_one_jiffy;
+		cpustat[CPUTIME_IRQ] += cputime;
 	} else if (irqtime_account_si_update()) {
-		cpustat[CPUTIME_SOFTIRQ] += (__force u64) cputime_one_jiffy;
+		cpustat[CPUTIME_SOFTIRQ] += cputime;
 	} else if (this_cpu_ksoftirqd() == p) {
 		/*
 		 * ksoftirqd time do not get accounted in cpu_softirq_time.
 		 * So, we have to handle it separately here.
 		 * Also, p->stime needs to be updated for ksoftirqd.
 		 */
-		__account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
-					CPUTIME_SOFTIRQ);
+		__account_system_time(p, cputime, scaled, CPUTIME_SOFTIRQ);
 	} else if (user_tick) {
-		account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
+		account_user_time(p, cputime, scaled);
 	} else if (p == rq->idle) {
-		account_idle_time(cputime_one_jiffy);
+		account_idle_time(cputime);
 	} else if (p->flags & PF_VCPU) { /* System time or guest time */
-		account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled);
+		account_guest_time(p, cputime, scaled);
 	} else {
-		__account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
-					CPUTIME_SYSTEM);
+		__account_system_time(p, cputime, scaled,	CPUTIME_SYSTEM);
 	}
 }
 
 static void irqtime_account_idle_ticks(int ticks)
 {
-	int i;
 	struct rq *rq = this_rq();
 
-	for (i = 0; i < ticks; i++)
-		irqtime_account_process_tick(current, 0, rq);
+	irqtime_account_process_tick(current, 0, rq, ticks);
 }
 #else /* CONFIG_IRQ_TIME_ACCOUNTING */
 static inline void irqtime_account_idle_ticks(int ticks) {}
 static inline void irqtime_account_process_tick(struct task_struct *p, int user_tick,
-						struct rq *rq) {}
+						struct rq *rq, int nr_ticks) {}
 #endif /* CONFIG_IRQ_TIME_ACCOUNTING */
 
 /*
@@ -464,7 +464,7 @@ void account_process_tick(struct task_struct *p, int user_tick)
 		return;
 
 	if (sched_clock_irqtime) {
-		irqtime_account_process_tick(p, user_tick, rq);
+		irqtime_account_process_tick(p, user_tick, rq, 1);
 		return;
 	}
 
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index b08095786cb8..800e99b99075 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -528,6 +528,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 	sched_clock_tick();
 	update_rq_clock(rq);
 	dl_se->dl_throttled = 0;
+	dl_se->dl_yielded = 0;
 	if (p->on_rq) {
 		enqueue_task_dl(rq, p, ENQUEUE_REPLENISH);
 		if (task_has_dl_policy(rq->curr))
@@ -893,10 +894,10 @@ static void yield_task_dl(struct rq *rq)
 	 * We make the task go to sleep until its current deadline by
 	 * forcing its runtime to zero. This way, update_curr_dl() stops
 	 * it and the bandwidth timer will wake it up and will give it
-	 * new scheduling parameters (thanks to dl_new=1).
+	 * new scheduling parameters (thanks to dl_yielded=1).
 	 */
 	if (p->dl.runtime > 0) {
-		rq->curr->dl.dl_new = 1;
+		rq->curr->dl.dl_yielded = 1;
 		p->dl.runtime = 0;
 	}
 	update_curr_dl(rq);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7570dd969c28..0fdb96de81a5 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6653,6 +6653,7 @@ static int idle_balance(struct rq *this_rq)
 	int this_cpu = this_rq->cpu;
 
 	idle_enter_fair(this_rq);
+
 	/*
 	 * We must set idle_stamp _before_ calling idle_balance(), such that we
 	 * measure the duration of idle_balance() as idle time.
@@ -6705,14 +6706,16 @@ static int idle_balance(struct rq *this_rq)
 
 	raw_spin_lock(&this_rq->lock);
 
+	if (curr_cost > this_rq->max_idle_balance_cost)
+		this_rq->max_idle_balance_cost = curr_cost;
+
 	/*
-	 * While browsing the domains, we released the rq lock.
-	 * A task could have be enqueued in the meantime
+	 * While browsing the domains, we released the rq lock, a task could
+	 * have been enqueued in the meantime. Since we're not going idle,
+	 * pretend we pulled a task.
 	 */
-	if (this_rq->cfs.h_nr_running && !pulled_task) {
+	if (this_rq->cfs.h_nr_running && !pulled_task)
 		pulled_task = 1;
-		goto out;
-	}
 
 	if (pulled_task || time_after(jiffies, this_rq->next_balance)) {
 		/*
@@ -6722,9 +6725,6 @@ static int idle_balance(struct rq *this_rq)
 		this_rq->next_balance = next_balance;
 	}
 
-	if (curr_cost > this_rq->max_idle_balance_cost)
-		this_rq->max_idle_balance_cost = curr_cost;
-
 out:
 	/* Is there a task of a high priority class? */
 	if (this_rq->nr_running != this_rq->cfs.h_nr_running &&
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 33e4648ae0e7..92f24f5e8d52 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -223,7 +223,7 @@ static inline bool lockdep_softirq_start(void) { return false; }
 static inline void lockdep_softirq_end(bool in_hardirq) { }
 #endif
 
-asmlinkage void __do_softirq(void)
+asmlinkage __visible void __do_softirq(void)
 {
 	unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
 	unsigned long old_flags = current->flags;
@@ -299,7 +299,7 @@ restart:
 	tsk_restore_flags(current, old_flags, PF_MEMALLOC);
 }
 
-asmlinkage void do_softirq(void)
+asmlinkage __visible void do_softirq(void)
 {
 	__u32 pending;
 	unsigned long flags;
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index ac5b23cf7212..6620e5837ce2 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -188,7 +188,6 @@ static int tracepoint_add_func(struct tracepoint *tp,
 		WARN_ON_ONCE(1);
 		return PTR_ERR(old);
 	}
-	release_probes(old);
 
 	/*
 	 * rcu_assign_pointer has a smp_wmb() which makes sure that the new
@@ -200,6 +199,7 @@ static int tracepoint_add_func(struct tracepoint *tp,
 	rcu_assign_pointer(tp->funcs, tp_funcs);
 	if (!static_key_enabled(&tp->key))
 		static_key_slow_inc(&tp->key);
+	release_probes(old);
 	return 0;
 }
 
@@ -221,7 +221,6 @@ static int tracepoint_remove_func(struct tracepoint *tp,
 		WARN_ON_ONCE(1);
 		return PTR_ERR(old);
 	}
-	release_probes(old);
 
 	if (!tp_funcs) {
 		/* Removed last function */
@@ -232,6 +231,7 @@ static int tracepoint_remove_func(struct tracepoint *tp,
 			static_key_slow_dec(&tp->key);
 	}
 	rcu_assign_pointer(tp->funcs, tp_funcs);
+	release_probes(old);
 	return 0;
 }
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 0ee63af30bd1..8edc87185427 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1916,6 +1916,12 @@ static void send_mayday(struct work_struct *work)
 
 	/* mayday mayday mayday */
 	if (list_empty(&pwq->mayday_node)) {
+		/*
+		 * If @pwq is for an unbound wq, its base ref may be put at
+		 * any time due to an attribute change.  Pin @pwq until the
+		 * rescuer is done with it.
+		 */
+		get_pwq(pwq);
 		list_add_tail(&pwq->mayday_node, &wq->maydays);
 		wake_up_process(wq->rescuer->task);
 	}
@@ -2398,6 +2404,7 @@ static int rescuer_thread(void *__rescuer)
 	struct worker *rescuer = __rescuer;
 	struct workqueue_struct *wq = rescuer->rescue_wq;
 	struct list_head *scheduled = &rescuer->scheduled;
+	bool should_stop;
 
 	set_user_nice(current, RESCUER_NICE_LEVEL);
 
@@ -2409,11 +2416,15 @@ static int rescuer_thread(void *__rescuer)
 repeat:
 	set_current_state(TASK_INTERRUPTIBLE);
 
-	if (kthread_should_stop()) {
-		__set_current_state(TASK_RUNNING);
-		rescuer->task->flags &= ~PF_WQ_WORKER;
-		return 0;
-	}
+	/*
+	 * By the time the rescuer is requested to stop, the workqueue
+	 * shouldn't have any work pending, but @wq->maydays may still have
+	 * pwq(s) queued.  This can happen by non-rescuer workers consuming
+	 * all the work items before the rescuer got to them.  Go through
+	 * @wq->maydays processing before acting on should_stop so that the
+	 * list is always empty on exit.
+	 */
+	should_stop = kthread_should_stop();
 
 	/* see whether any pwq is asking for help */
 	spin_lock_irq(&wq_mayday_lock);
@@ -2445,6 +2456,12 @@ repeat:
 		process_scheduled_works(rescuer);
 
 		/*
+		 * Put the reference grabbed by send_mayday().  @pool won't
+		 * go away while we're holding its lock.
+		 */
+		put_pwq(pwq);
+
+		/*
 		 * Leave this pool.  If keep_working() is %true, notify a
 		 * regular worker; otherwise, we end up with 0 concurrency
 		 * and stalling the execution.
@@ -2459,6 +2476,12 @@ repeat:
 
 	spin_unlock_irq(&wq_mayday_lock);
 
+	if (should_stop) {
+		__set_current_state(TASK_RUNNING);
+		rescuer->task->flags &= ~PF_WQ_WORKER;
+		return 0;
+	}
+
 	/* rescuers should never participate in concurrency management */
 	WARN_ON_ONCE(!(rescuer->flags & WORKER_NOT_RUNNING));
 	schedule();
@@ -4100,7 +4123,8 @@ static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu,
 	if (!pwq) {
 		pr_warning("workqueue: allocation failed while updating NUMA affinity of \"%s\"\n",
 			   wq->name);
-		goto out_unlock;
+		mutex_lock(&wq->mutex);
+		goto use_dfl_pwq;
 	}
 
 	/*
diff --git a/lib/dump_stack.c b/lib/dump_stack.c
index f23b63f0a1c3..6745c6230db3 100644
--- a/lib/dump_stack.c
+++ b/lib/dump_stack.c
@@ -23,7 +23,7 @@ static void __dump_stack(void)
 #ifdef CONFIG_SMP
 static atomic_t dump_lock = ATOMIC_INIT(-1);
 
-asmlinkage void dump_stack(void)
+asmlinkage __visible void dump_stack(void)
 {
 	int was_locked;
 	int old;
@@ -55,7 +55,7 @@ retry:
 	preempt_enable();
 }
 #else
-asmlinkage void dump_stack(void)
+asmlinkage __visible void dump_stack(void)
 {
 	__dump_stack();
 }
diff --git a/mm/Kconfig b/mm/Kconfig
index ebe5880c29d6..1b5a95f0fa01 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -581,3 +581,18 @@ config PGTABLE_MAPPING
 
 config GENERIC_EARLY_IOREMAP
 	bool
+
+config MAX_STACK_SIZE_MB
+	int "Maximum user stack size for 32-bit processes (MB)"
+	default 80
+	range 8 256 if METAG
+	range 8 2048
+	depends on STACK_GROWSUP && (!64BIT || COMPAT)
+	help
+	  This is the maximum stack size in Megabytes in the VM layout of 32-bit
+	  user processes when the stack grows upwards (currently only on parisc
+	  and metag arch). The stack will be located at the highest memory
+	  address minus the given value, unless the RLIMIT_STACK hard limit is
+	  changed to a smaller value in which case that is used.
+
+	  A sane initial value is 80 MB.
diff --git a/mm/filemap.c b/mm/filemap.c
index 2f724e3cdf24..7499ef19f1c1 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -257,9 +257,11 @@ static int filemap_check_errors(struct address_space *mapping)
 {
 	int ret = 0;
 	/* Check for outstanding write errors */
-	if (test_and_clear_bit(AS_ENOSPC, &mapping->flags))
+	if (test_bit(AS_ENOSPC, &mapping->flags) &&
+	    test_and_clear_bit(AS_ENOSPC, &mapping->flags))
 		ret = -ENOSPC;
-	if (test_and_clear_bit(AS_EIO, &mapping->flags))
+	if (test_bit(AS_EIO, &mapping->flags) &&
+	    test_and_clear_bit(AS_EIO, &mapping->flags))
 		ret = -EIO;
 	return ret;
 }
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 91d67eaee050..8d2fcdfeff7f 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1775,10 +1775,9 @@ void __init kmemleak_init(void)
 	int i;
 	unsigned long flags;
 
-	kmemleak_early_log = 0;
-
 #ifdef CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF
 	if (!kmemleak_skip_disable) {
+		kmemleak_early_log = 0;
 		kmemleak_disable();
 		return;
 	}
@@ -1796,6 +1795,7 @@ void __init kmemleak_init(void)
 
 	/* the kernel is still in UP mode, so disabling the IRQs is enough */
 	local_irq_save(flags);
+	kmemleak_early_log = 0;
 	if (kmemleak_error) {
 		local_irq_restore(flags);
 		return;
diff --git a/mm/madvise.c b/mm/madvise.c
index 539eeb96b323..a402f8fdc68e 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -195,7 +195,7 @@ static void force_shm_swapin_readahead(struct vm_area_struct *vma,
 	for (; start < end; start += PAGE_SIZE) {
 		index = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
 
-		page = find_get_page(mapping, index);
+		page = find_get_entry(mapping, index);
 		if (!radix_tree_exceptional_entry(page)) {
 			if (page)
 				page_cache_release(page);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c47dffdcb246..5177c6d4a2dd 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1077,9 +1077,18 @@ static struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
 
 	rcu_read_lock();
 	do {
-		memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
-		if (unlikely(!memcg))
+		/*
+		 * Page cache insertions can happen withou an
+		 * actual mm context, e.g. during disk probing
+		 * on boot, loopback IO, acct() writes etc.
+		 */
+		if (unlikely(!mm))
 			memcg = root_mem_cgroup;
+		else {
+			memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
+			if (unlikely(!memcg))
+				memcg = root_mem_cgroup;
+		}
 	} while (!css_tryget(&memcg->css));
 	rcu_read_unlock();
 	return memcg;
@@ -3958,17 +3967,9 @@ int mem_cgroup_charge_file(struct page *page, struct mm_struct *mm,
 		return 0;
 	}
 
-	/*
-	 * Page cache insertions can happen without an actual mm
-	 * context, e.g. during disk probing on boot.
-	 */
-	if (unlikely(!mm))
-		memcg = root_mem_cgroup;
-	else {
-		memcg = mem_cgroup_try_charge_mm(mm, gfp_mask, 1, true);
-		if (!memcg)
-			return -ENOMEM;
-	}
+	memcg = mem_cgroup_try_charge_mm(mm, gfp_mask, 1, true);
+	if (!memcg)
+		return -ENOMEM;
 	__mem_cgroup_commit_charge(memcg, page, 1, type, false);
 	return 0;
 }
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 35ef28acf137..9ccef39a9de2 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1081,15 +1081,16 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 			return 0;
 		} else if (PageHuge(hpage)) {
 			/*
-			 * Check "just unpoisoned", "filter hit", and
-			 * "race with other subpage."
+			 * Check "filter hit" and "race with other subpage."
 			 */
 			lock_page(hpage);
-			if (!PageHWPoison(hpage)
-			    || (hwpoison_filter(p) && TestClearPageHWPoison(p))
-			    || (p != hpage && TestSetPageHWPoison(hpage))) {
-				atomic_long_sub(nr_pages, &num_poisoned_pages);
-				return 0;
+			if (PageHWPoison(hpage)) {
+				if ((hwpoison_filter(p) && TestClearPageHWPoison(p))
+				    || (p != hpage && TestSetPageHWPoison(hpage))) {
+					atomic_long_sub(nr_pages, &num_poisoned_pages);
+					unlock_page(hpage);
+					return 0;
+				}
 			}
 			set_page_hwpoison_huge_page(hpage);
 			res = dequeue_hwpoisoned_huge_page(hpage);
@@ -1152,6 +1153,8 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 	 */
 	if (!PageHWPoison(p)) {
 		printk(KERN_ERR "MCE %#lx: just unpoisoned\n", pfn);
+		atomic_long_sub(nr_pages, &num_poisoned_pages);
+		put_page(hpage);
 		res = 0;
 		goto out;
 	}
diff --git a/mm/mremap.c b/mm/mremap.c
index 0843feb66f3d..05f1180e9f21 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -194,10 +194,17 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 			break;
 		if (pmd_trans_huge(*old_pmd)) {
 			int err = 0;
-			if (extent == HPAGE_PMD_SIZE)
+			if (extent == HPAGE_PMD_SIZE) {
+				VM_BUG_ON(vma->vm_file || !vma->anon_vma);
+				/* See comment in move_ptes() */
+				if (need_rmap_locks)
+					anon_vma_lock_write(vma->anon_vma);
 				err = move_huge_pmd(vma, new_vma, old_addr,
 						    new_addr, old_end,
 						    old_pmd, new_pmd);
+				if (need_rmap_locks)
+					anon_vma_unlock_write(vma->anon_vma);
+			}
 			if (err > 0) {
 				need_flush = true;
 				continue;
diff --git a/mm/percpu.c b/mm/percpu.c
index 63e24fb4387b..2ddf9a990dbd 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -610,7 +610,7 @@ static struct pcpu_chunk *pcpu_alloc_chunk(void)
 	chunk->map = pcpu_mem_zalloc(PCPU_DFL_MAP_ALLOC *
 						sizeof(chunk->map[0]));
 	if (!chunk->map) {
-		kfree(chunk);
+		pcpu_mem_free(chunk, pcpu_chunk_struct_size);
 		return NULL;
 	}
 
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 175273f38cb1..44ebd5c2cd4a 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -169,6 +169,7 @@ int register_vlan_dev(struct net_device *dev)
 	if (err < 0)
 		goto out_uninit_mvrp;
 
+	vlan->nest_level = dev_get_nest_level(real_dev, is_vlan_dev) + 1;
 	err = register_netdevice(dev);
 	if (err < 0)
 		goto out_uninit_mvrp;
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 733ec283ed1b..019efb79708f 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -493,48 +493,10 @@ static void vlan_dev_change_rx_flags(struct net_device *dev, int change)
 	}
 }
 
-static int vlan_calculate_locking_subclass(struct net_device *real_dev)
-{
-	int subclass = 0;
-
-	while (is_vlan_dev(real_dev)) {
-		subclass++;
-		real_dev = vlan_dev_priv(real_dev)->real_dev;
-	}
-
-	return subclass;
-}
-
-static void vlan_dev_mc_sync(struct net_device *to, struct net_device *from)
-{
-	int err = 0, subclass;
-
-	subclass = vlan_calculate_locking_subclass(to);
-
-	spin_lock_nested(&to->addr_list_lock, subclass);
-	err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len);
-	if (!err)
-		__dev_set_rx_mode(to);
-	spin_unlock(&to->addr_list_lock);
-}
-
-static void vlan_dev_uc_sync(struct net_device *to, struct net_device *from)
-{
-	int err = 0, subclass;
-
-	subclass = vlan_calculate_locking_subclass(to);
-
-	spin_lock_nested(&to->addr_list_lock, subclass);
-	err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len);
-	if (!err)
-		__dev_set_rx_mode(to);
-	spin_unlock(&to->addr_list_lock);
-}
-
 static void vlan_dev_set_rx_mode(struct net_device *vlan_dev)
 {
-	vlan_dev_mc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
-	vlan_dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
+	dev_mc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
+	dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
 }
 
 /*
@@ -562,6 +524,11 @@ static void vlan_dev_set_lockdep_class(struct net_device *dev, int subclass)
 	netdev_for_each_tx_queue(dev, vlan_dev_set_lockdep_one, &subclass);
 }
 
+static int vlan_dev_get_lock_subclass(struct net_device *dev)
+{
+	return vlan_dev_priv(dev)->nest_level;
+}
+
 static const struct header_ops vlan_header_ops = {
 	.create	 = vlan_dev_hard_header,
 	.rebuild = vlan_dev_rebuild_header,
@@ -597,7 +564,6 @@ static const struct net_device_ops vlan_netdev_ops;
 static int vlan_dev_init(struct net_device *dev)
 {
 	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
-	int subclass = 0;
 
 	netif_carrier_off(dev);
 
@@ -646,8 +612,7 @@ static int vlan_dev_init(struct net_device *dev)
 
 	SET_NETDEV_DEVTYPE(dev, &vlan_type);
 
-	subclass = vlan_calculate_locking_subclass(dev);
-	vlan_dev_set_lockdep_class(dev, subclass);
+	vlan_dev_set_lockdep_class(dev, vlan_dev_get_lock_subclass(dev));
 
 	vlan_dev_priv(dev)->vlan_pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats);
 	if (!vlan_dev_priv(dev)->vlan_pcpu_stats)
@@ -819,6 +784,7 @@ static const struct net_device_ops vlan_netdev_ops = {
 	.ndo_netpoll_cleanup	= vlan_dev_netpoll_cleanup,
 #endif
 	.ndo_fix_features	= vlan_dev_fix_features,
+	.ndo_get_lock_subclass  = vlan_dev_get_lock_subclass,
 };
 
 void vlan_setup(struct net_device *dev)
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index b3bd4ec3fd94..f04224c32005 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -1545,6 +1545,8 @@ out_neigh:
 	if ((orig_neigh_node) && (!is_single_hop_neigh))
 		batadv_orig_node_free_ref(orig_neigh_node);
 out:
+	if (router_ifinfo)
+		batadv_neigh_ifinfo_free_ref(router_ifinfo);
 	if (router)
 		batadv_neigh_node_free_ref(router);
 	if (router_router)
diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index b25fd64d727b..aa5d4946d0d7 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -940,8 +940,7 @@ bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv,
 		 * additional DAT answer may trigger kernel warnings about
 		 * a packet coming from the wrong port.
 		 */
-		if (batadv_is_my_client(bat_priv, dat_entry->mac_addr,
-					BATADV_NO_FLAGS)) {
+		if (batadv_is_my_client(bat_priv, dat_entry->mac_addr, vid)) {
 			ret = true;
 			goto out;
 		}
diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c
index bcc4bea632fa..f14e54a05691 100644
--- a/net/batman-adv/fragmentation.c
+++ b/net/batman-adv/fragmentation.c
@@ -418,12 +418,13 @@ bool batadv_frag_send_packet(struct sk_buff *skb,
 			     struct batadv_neigh_node *neigh_node)
 {
 	struct batadv_priv *bat_priv;
-	struct batadv_hard_iface *primary_if;
+	struct batadv_hard_iface *primary_if = NULL;
 	struct batadv_frag_packet frag_header;
 	struct sk_buff *skb_fragment;
 	unsigned mtu = neigh_node->if_incoming->net_dev->mtu;
 	unsigned header_size = sizeof(frag_header);
 	unsigned max_fragment_size, max_packet_size;
+	bool ret = false;
 
 	/* To avoid merge and refragmentation at next-hops we never send
 	 * fragments larger than BATADV_FRAG_MAX_FRAG_SIZE
@@ -483,7 +484,11 @@ bool batadv_frag_send_packet(struct sk_buff *skb,
 			   skb->len + ETH_HLEN);
 	batadv_send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr);
 
-	return true;
+	ret = true;
+
 out_err:
-	return false;
+	if (primary_if)
+		batadv_hardif_free_ref(primary_if);
+
+	return ret;
 }
diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c
index c835e137423b..90cff585b37d 100644
--- a/net/batman-adv/gateway_client.c
+++ b/net/batman-adv/gateway_client.c
@@ -42,8 +42,10 @@
 
 static void batadv_gw_node_free_ref(struct batadv_gw_node *gw_node)
 {
-	if (atomic_dec_and_test(&gw_node->refcount))
+	if (atomic_dec_and_test(&gw_node->refcount)) {
+		batadv_orig_node_free_ref(gw_node->orig_node);
 		kfree_rcu(gw_node, rcu);
+	}
 }
 
 static struct batadv_gw_node *
@@ -406,9 +408,14 @@ static void batadv_gw_node_add(struct batadv_priv *bat_priv,
 	if (gateway->bandwidth_down == 0)
 		return;
 
+	if (!atomic_inc_not_zero(&orig_node->refcount))
+		return;
+
 	gw_node = kzalloc(sizeof(*gw_node), GFP_ATOMIC);
-	if (!gw_node)
+	if (!gw_node) {
+		batadv_orig_node_free_ref(orig_node);
 		return;
+	}
 
 	INIT_HLIST_NODE(&gw_node->list);
 	gw_node->orig_node = orig_node;
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index b851cc580853..fbda6b54baff 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -83,7 +83,7 @@ static bool batadv_is_on_batman_iface(const struct net_device *net_dev)
 		return true;
 
 	/* no more parents..stop recursion */
-	if (net_dev->iflink == net_dev->ifindex)
+	if (net_dev->iflink == 0 || net_dev->iflink == net_dev->ifindex)
 		return false;
 
 	/* recurse over the parent device */
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index ffd9dfbd9b0e..6a484514cd3e 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -501,12 +501,17 @@ batadv_neigh_node_get(const struct batadv_orig_node *orig_node,
 static void batadv_orig_ifinfo_free_rcu(struct rcu_head *rcu)
 {
 	struct batadv_orig_ifinfo *orig_ifinfo;
+	struct batadv_neigh_node *router;
 
 	orig_ifinfo = container_of(rcu, struct batadv_orig_ifinfo, rcu);
 
 	if (orig_ifinfo->if_outgoing != BATADV_IF_DEFAULT)
 		batadv_hardif_free_ref_now(orig_ifinfo->if_outgoing);
 
+	/* this is the last reference to this object */
+	router = rcu_dereference_protected(orig_ifinfo->router, true);
+	if (router)
+		batadv_neigh_node_free_ref_now(router);
 	kfree(orig_ifinfo);
 }
 
@@ -702,6 +707,47 @@ free_orig_node:
 }
 
 /**
+ * batadv_purge_neigh_ifinfo - purge obsolete ifinfo entries from neighbor
+ * @bat_priv: the bat priv with all the soft interface information
+ * @neigh: orig node which is to be checked
+ */
+static void
+batadv_purge_neigh_ifinfo(struct batadv_priv *bat_priv,
+			  struct batadv_neigh_node *neigh)
+{
+	struct batadv_neigh_ifinfo *neigh_ifinfo;
+	struct batadv_hard_iface *if_outgoing;
+	struct hlist_node *node_tmp;
+
+	spin_lock_bh(&neigh->ifinfo_lock);
+
+	/* for all ifinfo objects for this neighinator */
+	hlist_for_each_entry_safe(neigh_ifinfo, node_tmp,
+				  &neigh->ifinfo_list, list) {
+		if_outgoing = neigh_ifinfo->if_outgoing;
+
+		/* always keep the default interface */
+		if (if_outgoing == BATADV_IF_DEFAULT)
+			continue;
+
+		/* don't purge if the interface is not (going) down */
+		if ((if_outgoing->if_status != BATADV_IF_INACTIVE) &&
+		    (if_outgoing->if_status != BATADV_IF_NOT_IN_USE) &&
+		    (if_outgoing->if_status != BATADV_IF_TO_BE_REMOVED))
+			continue;
+
+		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
+			   "neighbor/ifinfo purge: neighbor %pM, iface: %s\n",
+			   neigh->addr, if_outgoing->net_dev->name);
+
+		hlist_del_rcu(&neigh_ifinfo->list);
+		batadv_neigh_ifinfo_free_ref(neigh_ifinfo);
+	}
+
+	spin_unlock_bh(&neigh->ifinfo_lock);
+}
+
+/**
  * batadv_purge_orig_ifinfo - purge obsolete ifinfo entries from originator
  * @bat_priv: the bat priv with all the soft interface information
  * @orig_node: orig node which is to be checked
@@ -800,6 +846,11 @@ batadv_purge_orig_neighbors(struct batadv_priv *bat_priv,
 
 			hlist_del_rcu(&neigh_node->list);
 			batadv_neigh_node_free_ref(neigh_node);
+		} else {
+			/* only necessary if not the whole neighbor is to be
+			 * deleted, but some interface has been removed.
+			 */
+			batadv_purge_neigh_ifinfo(bat_priv, neigh_node);
 		}
 	}
 
@@ -857,7 +908,7 @@ static bool batadv_purge_orig_node(struct batadv_priv *bat_priv,
 {
 	struct batadv_neigh_node *best_neigh_node;
 	struct batadv_hard_iface *hard_iface;
-	bool changed;
+	bool changed_ifinfo, changed_neigh;
 
 	if (batadv_has_timed_out(orig_node->last_seen,
 				 2 * BATADV_PURGE_TIMEOUT)) {
@@ -867,10 +918,10 @@ static bool batadv_purge_orig_node(struct batadv_priv *bat_priv,
 			   jiffies_to_msecs(orig_node->last_seen));
 		return true;
 	}
-	changed = batadv_purge_orig_ifinfo(bat_priv, orig_node);
-	changed = changed || batadv_purge_orig_neighbors(bat_priv, orig_node);
+	changed_ifinfo = batadv_purge_orig_ifinfo(bat_priv, orig_node);
+	changed_neigh = batadv_purge_orig_neighbors(bat_priv, orig_node);
 
-	if (!changed)
+	if (!changed_ifinfo && !changed_neigh)
 		return false;
 
 	/* first for NULL ... */
@@ -1028,7 +1079,8 @@ int batadv_orig_hardif_seq_print_text(struct seq_file *seq, void *offset)
 	bat_priv->bat_algo_ops->bat_orig_print(bat_priv, seq, hard_iface);
 
 out:
-	batadv_hardif_free_ref(hard_iface);
+	if (hard_iface)
+		batadv_hardif_free_ref(hard_iface);
 	return 0;
 }
 
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index 80e1b0f60a30..2acf7fa1fec6 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -859,12 +859,12 @@ static unsigned int br_nf_forward_arp(const struct nf_hook_ops *ops,
 	return NF_STOLEN;
 }
 
-#if IS_ENABLED(CONFIG_NF_CONNTRACK_IPV4)
+#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4)
 static int br_nf_dev_queue_xmit(struct sk_buff *skb)
 {
 	int ret;
 
-	if (skb->nfct != NULL && skb->protocol == htons(ETH_P_IP) &&
+	if (skb->protocol == htons(ETH_P_IP) &&
 	    skb->len + nf_bridge_mtu_reduction(skb) > skb->dev->mtu &&
 	    !skb_is_gso(skb)) {
 		if (br_parse_ip_options(skb))
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index dac7f9b98687..1948d592aa54 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -557,7 +557,7 @@ static int ceph_tcp_sendmsg(struct socket *sock, struct kvec *iov,
 	return r;
 }
 
-static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
+static int __ceph_tcp_sendpage(struct socket *sock, struct page *page,
 		     int offset, size_t size, bool more)
 {
 	int flags = MSG_DONTWAIT | MSG_NOSIGNAL | (more ? MSG_MORE : MSG_EOR);
@@ -570,6 +570,24 @@ static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
 	return ret;
 }
 
+static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
+		     int offset, size_t size, bool more)
+{
+	int ret;
+	struct kvec iov;
+
+	/* sendpage cannot properly handle pages with page_count == 0,
+	 * we need to fallback to sendmsg if that's the case */
+	if (page_count(page) >= 1)
+		return __ceph_tcp_sendpage(sock, page, offset, size, more);
+
+	iov.iov_base = kmap(page) + offset;
+	iov.iov_len = size;
+	ret = ceph_tcp_sendmsg(sock, &iov, 1, size, more);
+	kunmap(page);
+
+	return ret;
+}
 
 /*
  * Shutdown/close the socket for the given connection.
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 8b8a5a24b223..c547e46084d3 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -329,6 +329,11 @@ static struct crush_map *crush_decode(void *pbyval, void *end)
 	dout("crush decode tunable chooseleaf_descend_once = %d",
 	     c->chooseleaf_descend_once);
 
+	ceph_decode_need(p, end, sizeof(u8), done);
+	c->chooseleaf_vary_r = ceph_decode_8(p);
+	dout("crush decode tunable chooseleaf_vary_r = %d",
+	     c->chooseleaf_vary_r);
+
 done:
 	dout("crush_decode success\n");
 	return c;
diff --git a/net/core/dev.c b/net/core/dev.c
index d2c8a06b3a98..9abc503b19b7 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2418,7 +2418,7 @@ EXPORT_SYMBOL(netdev_rx_csum_fault);
  * 2. No high memory really exists on this machine.
  */
 
-static int illegal_highdma(const struct net_device *dev, struct sk_buff *skb)
+static int illegal_highdma(struct net_device *dev, struct sk_buff *skb)
 {
 #ifdef CONFIG_HIGHMEM
 	int i;
@@ -2493,38 +2493,36 @@ static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features)
 }
 
 static netdev_features_t harmonize_features(struct sk_buff *skb,
-					    const struct net_device *dev,
-					    netdev_features_t features)
+	netdev_features_t features)
 {
 	int tmp;
 
 	if (skb->ip_summed != CHECKSUM_NONE &&
 	    !can_checksum_protocol(features, skb_network_protocol(skb, &tmp))) {
 		features &= ~NETIF_F_ALL_CSUM;
-	} else if (illegal_highdma(dev, skb)) {
+	} else if (illegal_highdma(skb->dev, skb)) {
 		features &= ~NETIF_F_SG;
 	}
 
 	return features;
 }
 
-netdev_features_t netif_skb_dev_features(struct sk_buff *skb,
-					 const struct net_device *dev)
+netdev_features_t netif_skb_features(struct sk_buff *skb)
 {
 	__be16 protocol = skb->protocol;
-	netdev_features_t features = dev->features;
+	netdev_features_t features = skb->dev->features;
 
-	if (skb_shinfo(skb)->gso_segs > dev->gso_max_segs)
+	if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs)
 		features &= ~NETIF_F_GSO_MASK;
 
 	if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) {
 		struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
 		protocol = veh->h_vlan_encapsulated_proto;
 	} else if (!vlan_tx_tag_present(skb)) {
-		return harmonize_features(skb, dev, features);
+		return harmonize_features(skb, features);
 	}
 
-	features &= (dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX |
+	features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX |
 					       NETIF_F_HW_VLAN_STAG_TX);
 
 	if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD))
@@ -2532,9 +2530,9 @@ netdev_features_t netif_skb_dev_features(struct sk_buff *skb,
 				NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_CTAG_TX |
 				NETIF_F_HW_VLAN_STAG_TX;
 
-	return harmonize_features(skb, dev, features);
+	return harmonize_features(skb, features);
 }
-EXPORT_SYMBOL(netif_skb_dev_features);
+EXPORT_SYMBOL(netif_skb_features);
 
 int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 			struct netdev_queue *txq)
@@ -3953,6 +3951,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	}
 	NAPI_GRO_CB(skb)->count = 1;
 	NAPI_GRO_CB(skb)->age = jiffies;
+	NAPI_GRO_CB(skb)->last = skb;
 	skb_shinfo(skb)->gso_size = skb_gro_len(skb);
 	skb->next = napi->gro_list;
 	napi->gro_list = skb;
@@ -4543,6 +4542,32 @@ void *netdev_adjacent_get_private(struct list_head *adj_list)
 EXPORT_SYMBOL(netdev_adjacent_get_private);
 
 /**
+ * netdev_upper_get_next_dev_rcu - Get the next dev from upper list
+ * @dev: device
+ * @iter: list_head ** of the current position
+ *
+ * Gets the next device from the dev's upper list, starting from iter
+ * position. The caller must hold RCU read lock.
+ */
+struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
+						 struct list_head **iter)
+{
+	struct netdev_adjacent *upper;
+
+	WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held());
+
+	upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list);
+
+	if (&upper->list == &dev->adj_list.upper)
+		return NULL;
+
+	*iter = &upper->list;
+
+	return upper->dev;
+}
+EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu);
+
+/**
  * netdev_all_upper_get_next_dev_rcu - Get the next dev from upper list
  * @dev: device
  * @iter: list_head ** of the current position
@@ -4624,6 +4649,32 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev,
 EXPORT_SYMBOL(netdev_lower_get_next_private_rcu);
 
 /**
+ * netdev_lower_get_next - Get the next device from the lower neighbour
+ *                         list
+ * @dev: device
+ * @iter: list_head ** of the current position
+ *
+ * Gets the next netdev_adjacent from the dev's lower neighbour
+ * list, starting from iter position. The caller must hold RTNL lock or
+ * its own locking that guarantees that the neighbour lower
+ * list will remain unchainged.
+ */
+void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter)
+{
+	struct netdev_adjacent *lower;
+
+	lower = list_entry((*iter)->next, struct netdev_adjacent, list);
+
+	if (&lower->list == &dev->adj_list.lower)
+		return NULL;
+
+	*iter = &lower->list;
+
+	return lower->dev;
+}
+EXPORT_SYMBOL(netdev_lower_get_next);
+
+/**
  * netdev_lower_get_first_private_rcu - Get the first ->private from the
  *				       lower neighbour list, RCU
  *				       variant
@@ -5073,6 +5124,30 @@ void *netdev_lower_dev_get_private(struct net_device *dev,
 }
 EXPORT_SYMBOL(netdev_lower_dev_get_private);
 
+
+int dev_get_nest_level(struct net_device *dev,
+		       bool (*type_check)(struct net_device *dev))
+{
+	struct net_device *lower = NULL;
+	struct list_head *iter;
+	int max_nest = -1;
+	int nest;
+
+	ASSERT_RTNL();
+
+	netdev_for_each_lower_dev(dev, lower, iter) {
+		nest = dev_get_nest_level(lower, type_check);
+		if (max_nest < nest)
+			max_nest = nest;
+	}
+
+	if (type_check(dev))
+		max_nest++;
+
+	return max_nest;
+}
+EXPORT_SYMBOL(dev_get_nest_level);
+
 static void dev_change_rx_flags(struct net_device *dev, int flags)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
@@ -5238,7 +5313,6 @@ void __dev_set_rx_mode(struct net_device *dev)
 	if (ops->ndo_set_rx_mode)
 		ops->ndo_set_rx_mode(dev);
 }
-EXPORT_SYMBOL(__dev_set_rx_mode);
 
 void dev_set_rx_mode(struct net_device *dev)
 {
@@ -5543,7 +5617,7 @@ static int dev_new_index(struct net *net)
 
 /* Delayed registration/unregisteration */
 static LIST_HEAD(net_todo_list);
-static DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq);
+DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq);
 
 static void net_set_todo(struct net_device *dev)
 {
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 8f8a96ef9f3f..32d872eec7f5 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1248,8 +1248,8 @@ void __neigh_set_probe_once(struct neighbour *neigh)
 	neigh->updated = jiffies;
 	if (!(neigh->nud_state & NUD_FAILED))
 		return;
-	neigh->nud_state = NUD_PROBE;
-	atomic_set(&neigh->probes, NEIGH_VAR(neigh->parms, UCAST_PROBES));
+	neigh->nud_state = NUD_INCOMPLETE;
+	atomic_set(&neigh->probes, neigh_max_probes(neigh));
 	neigh_add_timer(neigh,
 			jiffies + NEIGH_VAR(neigh->parms, RETRANS_TIME));
 }
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 81d3a9a08453..7c8ffd974961 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -24,7 +24,7 @@
 
 static LIST_HEAD(pernet_list);
 static struct list_head *first_device = &pernet_list;
-static DEFINE_MUTEX(net_mutex);
+DEFINE_MUTEX(net_mutex);
 
 LIST_HEAD(net_namespace_list);
 EXPORT_SYMBOL_GPL(net_namespace_list);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 9837bebf93ce..2d8d8fcfa060 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -353,15 +353,46 @@ void __rtnl_link_unregister(struct rtnl_link_ops *ops)
 }
 EXPORT_SYMBOL_GPL(__rtnl_link_unregister);
 
+/* Return with the rtnl_lock held when there are no network
+ * devices unregistering in any network namespace.
+ */
+static void rtnl_lock_unregistering_all(void)
+{
+	struct net *net;
+	bool unregistering;
+	DEFINE_WAIT(wait);
+
+	for (;;) {
+		prepare_to_wait(&netdev_unregistering_wq, &wait,
+				TASK_UNINTERRUPTIBLE);
+		unregistering = false;
+		rtnl_lock();
+		for_each_net(net) {
+			if (net->dev_unreg_count > 0) {
+				unregistering = true;
+				break;
+			}
+		}
+		if (!unregistering)
+			break;
+		__rtnl_unlock();
+		schedule();
+	}
+	finish_wait(&netdev_unregistering_wq, &wait);
+}
+
 /**
  * rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink.
  * @ops: struct rtnl_link_ops * to unregister
  */
 void rtnl_link_unregister(struct rtnl_link_ops *ops)
 {
-	rtnl_lock();
+	/* Close the race with cleanup_net() */
+	mutex_lock(&net_mutex);
+	rtnl_lock_unregistering_all();
 	__rtnl_link_unregister(ops);
 	rtnl_unlock();
+	mutex_unlock(&net_mutex);
 }
 EXPORT_SYMBOL_GPL(rtnl_link_unregister);
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 1b62343f5837..8383b2bddeb9 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3076,7 +3076,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 	if (unlikely(p->len + len >= 65536))
 		return -E2BIG;
 
-	lp = NAPI_GRO_CB(p)->last ?: p;
+	lp = NAPI_GRO_CB(p)->last;
 	pinfo = skb_shinfo(lp);
 
 	if (headlen <= offset) {
@@ -3192,7 +3192,7 @@ merge:
 
 	__skb_pull(skb, offset);
 
-	if (!NAPI_GRO_CB(p)->last)
+	if (NAPI_GRO_CB(p)->last == p)
 		skb_shinfo(p)->frag_list = skb;
 	else
 		NAPI_GRO_CB(p)->last->next = skb;
diff --git a/net/core/utils.c b/net/core/utils.c
index 2f737bf90b3f..eed34338736c 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -348,8 +348,8 @@ static void __net_random_once_deferred(struct work_struct *w)
 {
 	struct __net_random_once_work *work =
 		container_of(w, struct __net_random_once_work, work);
-	if (!static_key_enabled(work->key))
-		static_key_slow_inc(work->key);
+	BUG_ON(!static_key_enabled(work->key));
+	static_key_slow_dec(work->key);
 	kfree(work);
 }
 
@@ -367,7 +367,7 @@ static void __net_random_once_disable_jump(struct static_key *key)
 }
 
 bool __net_get_random_once(void *buf, int nbytes, bool *done,
-			   struct static_key *done_key)
+			   struct static_key *once_key)
 {
 	static DEFINE_SPINLOCK(lock);
 	unsigned long flags;
@@ -382,7 +382,7 @@ bool __net_get_random_once(void *buf, int nbytes, bool *done,
 	*done = true;
 	spin_unlock_irqrestore(&lock, flags);
 
-	__net_random_once_disable_jump(done_key);
+	__net_random_once_disable_jump(once_key);
 
 	return true;
 }
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 0eb5d5e76dfb..5db37cef50a9 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -406,8 +406,9 @@ static int dsa_of_probe(struct platform_device *pdev)
 		goto out_free;
 	}
 
-	chip_index = 0;
+	chip_index = -1;
 	for_each_available_child_of_node(np, child) {
+		chip_index++;
 		cd = &pd->chip[chip_index];
 
 		cd->mii_bus = &mdio_bus->dev;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 8c54870db792..6d6dd345bc4d 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1650,6 +1650,39 @@ static int __init init_ipv4_mibs(void)
 	return register_pernet_subsys(&ipv4_mib_ops);
 }
 
+static __net_init int inet_init_net(struct net *net)
+{
+	/*
+	 * Set defaults for local port range
+	 */
+	seqlock_init(&net->ipv4.ip_local_ports.lock);
+	net->ipv4.ip_local_ports.range[0] =  32768;
+	net->ipv4.ip_local_ports.range[1] =  61000;
+
+	seqlock_init(&net->ipv4.ping_group_range.lock);
+	/*
+	 * Sane defaults - nobody may create ping sockets.
+	 * Boot scripts should set this to distro-specific group.
+	 */
+	net->ipv4.ping_group_range.range[0] = make_kgid(&init_user_ns, 1);
+	net->ipv4.ping_group_range.range[1] = make_kgid(&init_user_ns, 0);
+	return 0;
+}
+
+static __net_exit void inet_exit_net(struct net *net)
+{
+}
+
+static __net_initdata struct pernet_operations af_inet_ops = {
+	.init = inet_init_net,
+	.exit = inet_exit_net,
+};
+
+static int __init init_inet_pernet_ops(void)
+{
+	return register_pernet_subsys(&af_inet_ops);
+}
+
 static int ipv4_proc_init(void);
 
 /*
@@ -1794,6 +1827,9 @@ static int __init inet_init(void)
 	if (ip_mr_init())
 		pr_crit("%s: Cannot init ipv4 mroute\n", __func__);
 #endif
+
+	if (init_inet_pernet_ops())
+		pr_crit("%s: Cannot init ipv4 inet pernet ops\n", __func__);
 	/*
 	 *	Initialise per-cpu ipv4 mibs
 	 */
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 8a043f03c88e..b10cd43a4722 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -821,13 +821,13 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 	fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL);
 	if (fi == NULL)
 		goto failure;
+	fib_info_cnt++;
 	if (cfg->fc_mx) {
 		fi->fib_metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
 		if (!fi->fib_metrics)
 			goto failure;
 	} else
 		fi->fib_metrics = (u32 *) dst_default_metrics;
-	fib_info_cnt++;
 
 	fi->fib_net = hold_net(net);
 	fi->fib_protocol = cfg->fc_protocol;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 0d1e2cb877ec..a56b8e6e866a 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -37,11 +37,11 @@ void inet_get_local_port_range(struct net *net, int *low, int *high)
 	unsigned int seq;
 
 	do {
-		seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock);
+		seq = read_seqbegin(&net->ipv4.ip_local_ports.lock);
 
-		*low = net->ipv4.sysctl_local_ports.range[0];
-		*high = net->ipv4.sysctl_local_ports.range[1];
-	} while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq));
+		*low = net->ipv4.ip_local_ports.range[0];
+		*high = net->ipv4.ip_local_ports.range[1];
+	} while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq));
 }
 EXPORT_SYMBOL(inet_get_local_port_range);
 
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index be8abe73bb9f..6f111e48e11c 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -42,12 +42,12 @@
 static bool ip_may_fragment(const struct sk_buff *skb)
 {
 	return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) ||
-	       !skb->local_df;
+		skb->local_df;
 }
 
 static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
 {
-	if (skb->len <= mtu || skb->local_df)
+	if (skb->len <= mtu)
 		return false;
 
 	if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
@@ -56,53 +56,6 @@ static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu)
 	return true;
 }
 
-static bool ip_gso_exceeds_dst_mtu(const struct sk_buff *skb)
-{
-	unsigned int mtu;
-
-	if (skb->local_df || !skb_is_gso(skb))
-		return false;
-
-	mtu = ip_dst_mtu_maybe_forward(skb_dst(skb), true);
-
-	/* if seglen > mtu, do software segmentation for IP fragmentation on
-	 * output.  DF bit cannot be set since ip_forward would have sent
-	 * icmp error.
-	 */
-	return skb_gso_network_seglen(skb) > mtu;
-}
-
-/* called if GSO skb needs to be fragmented on forward */
-static int ip_forward_finish_gso(struct sk_buff *skb)
-{
-	struct dst_entry *dst = skb_dst(skb);
-	netdev_features_t features;
-	struct sk_buff *segs;
-	int ret = 0;
-
-	features = netif_skb_dev_features(skb, dst->dev);
-	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
-	if (IS_ERR(segs)) {
-		kfree_skb(skb);
-		return -ENOMEM;
-	}
-
-	consume_skb(skb);
-
-	do {
-		struct sk_buff *nskb = segs->next;
-		int err;
-
-		segs->next = NULL;
-		err = dst_output(segs);
-
-		if (err && ret == 0)
-			ret = err;
-		segs = nskb;
-	} while (segs);
-
-	return ret;
-}
 
 static int ip_forward_finish(struct sk_buff *skb)
 {
@@ -114,9 +67,6 @@ static int ip_forward_finish(struct sk_buff *skb)
 	if (unlikely(opt->optlen))
 		ip_forward_options(skb);
 
-	if (ip_gso_exceeds_dst_mtu(skb))
-		return ip_forward_finish_gso(skb);
-
 	return dst_output(skb);
 }
 
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index c10a3ce5cbff..ed32313e307c 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -232,8 +232,9 @@ static void ip_expire(unsigned long arg)
 		 * "Fragment Reassembly Timeout" message, per RFC792.
 		 */
 		if (qp->user == IP_DEFRAG_AF_PACKET ||
-		    (qp->user == IP_DEFRAG_CONNTRACK_IN &&
-		     skb_rtable(head)->rt_type != RTN_LOCAL))
+		    ((qp->user >= IP_DEFRAG_CONNTRACK_IN) &&
+		     (qp->user <= __IP_DEFRAG_CONNTRACK_IN_END) &&
+		     (skb_rtable(head)->rt_type != RTN_LOCAL)))
 			goto out_rcu_unlock;
 
 
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 1cbeba5edff9..a52f50187b54 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -211,6 +211,48 @@ static inline int ip_finish_output2(struct sk_buff *skb)
 	return -EINVAL;
 }
 
+static int ip_finish_output_gso(struct sk_buff *skb)
+{
+	netdev_features_t features;
+	struct sk_buff *segs;
+	int ret = 0;
+
+	/* common case: locally created skb or seglen is <= mtu */
+	if (((IPCB(skb)->flags & IPSKB_FORWARDED) == 0) ||
+	      skb_gso_network_seglen(skb) <= ip_skb_dst_mtu(skb))
+		return ip_finish_output2(skb);
+
+	/* Slowpath -  GSO segment length is exceeding the dst MTU.
+	 *
+	 * This can happen in two cases:
+	 * 1) TCP GRO packet, DF bit not set
+	 * 2) skb arrived via virtio-net, we thus get TSO/GSO skbs directly
+	 * from host network stack.
+	 */
+	features = netif_skb_features(skb);
+	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+	if (IS_ERR(segs)) {
+		kfree_skb(skb);
+		return -ENOMEM;
+	}
+
+	consume_skb(skb);
+
+	do {
+		struct sk_buff *nskb = segs->next;
+		int err;
+
+		segs->next = NULL;
+		err = ip_fragment(segs, ip_finish_output2);
+
+		if (err && ret == 0)
+			ret = err;
+		segs = nskb;
+	} while (segs);
+
+	return ret;
+}
+
 static int ip_finish_output(struct sk_buff *skb)
 {
 #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
@@ -220,10 +262,13 @@ static int ip_finish_output(struct sk_buff *skb)
 		return dst_output(skb);
 	}
 #endif
-	if (skb->len > ip_skb_dst_mtu(skb) && !skb_is_gso(skb))
+	if (skb_is_gso(skb))
+		return ip_finish_output_gso(skb);
+
+	if (skb->len > ip_skb_dst_mtu(skb))
 		return ip_fragment(skb, ip_finish_output2);
-	else
-		return ip_finish_output2(skb);
+
+	return ip_finish_output2(skb);
 }
 
 int ip_mc_output(struct sock *sk, struct sk_buff *skb)
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index b3f859731c60..2acc2337d38b 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -540,9 +540,10 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 	unsigned int max_headroom;	/* The extra header space needed */
 	__be32 dst;
 	int err;
-	bool connected = true;
+	bool connected;
 
 	inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
+	connected = (tunnel->parms.iph.daddr != 0);
 
 	dst = tnl_params->daddr;
 	if (dst == 0) {
@@ -882,6 +883,7 @@ int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id,
 	 */
 	if (!IS_ERR(itn->fb_tunnel_dev)) {
 		itn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL;
+		itn->fb_tunnel_dev->mtu = ip_tunnel_bind_dev(itn->fb_tunnel_dev);
 		ip_tunnel_add(itn, netdev_priv(itn->fb_tunnel_dev));
 	}
 	rtnl_unlock();
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index afcee51b90ed..13ef00f1e17b 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -239,6 +239,7 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 static int vti4_err(struct sk_buff *skb, u32 info)
 {
 	__be32 spi;
+	__u32 mark;
 	struct xfrm_state *x;
 	struct ip_tunnel *tunnel;
 	struct ip_esp_hdr *esph;
@@ -254,6 +255,8 @@ static int vti4_err(struct sk_buff *skb, u32 info)
 	if (!tunnel)
 		return -1;
 
+	mark = be32_to_cpu(tunnel->parms.o_key);
+
 	switch (protocol) {
 	case IPPROTO_ESP:
 		esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2));
@@ -281,7 +284,7 @@ static int vti4_err(struct sk_buff *skb, u32 info)
 		return 0;
 	}
 
-	x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
+	x = xfrm_state_lookup(net, mark, (const xfrm_address_t *)&iph->daddr,
 			      spi, protocol, AF_INET);
 	if (!x)
 		return 0;
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index 12e13bd82b5b..f40f321b41fc 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -22,7 +22,6 @@
 #endif
 #include <net/netfilter/nf_conntrack_zones.h>
 
-/* Returns new sk_buff, or NULL */
 static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user)
 {
 	int err;
@@ -33,8 +32,10 @@ static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user)
 	err = ip_defrag(skb, user);
 	local_bh_enable();
 
-	if (!err)
+	if (!err) {
 		ip_send_check(ip_hdr(skb));
+		skb->local_df = 1;
+	}
 
 	return err;
 }
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 8210964a9f19..044a0ddf6a79 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -236,15 +236,15 @@ exit:
 static void inet_get_ping_group_range_net(struct net *net, kgid_t *low,
 					  kgid_t *high)
 {
-	kgid_t *data = net->ipv4.sysctl_ping_group_range;
+	kgid_t *data = net->ipv4.ping_group_range.range;
 	unsigned int seq;
 
 	do {
-		seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock);
+		seq = read_seqbegin(&net->ipv4.ping_group_range.lock);
 
 		*low = data[0];
 		*high = data[1];
-	} while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq));
+	} while (read_seqretry(&net->ipv4.ping_group_range.lock, seq));
 }
 
 
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index db1e0da871f4..5e676be3daeb 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1519,7 +1519,7 @@ static int __mkroute_input(struct sk_buff *skb,
 	struct in_device *out_dev;
 	unsigned int flags = 0;
 	bool do_cache;
-	u32 itag;
+	u32 itag = 0;
 
 	/* get a working reference to the output device */
 	out_dev = __in_dev_get_rcu(FIB_RES_DEV(*res));
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 44eba052b43d..5cde8f263d40 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -45,10 +45,10 @@ static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
 /* Update system visible IP port range */
 static void set_local_port_range(struct net *net, int range[2])
 {
-	write_seqlock(&net->ipv4.sysctl_local_ports.lock);
-	net->ipv4.sysctl_local_ports.range[0] = range[0];
-	net->ipv4.sysctl_local_ports.range[1] = range[1];
-	write_sequnlock(&net->ipv4.sysctl_local_ports.lock);
+	write_seqlock(&net->ipv4.ip_local_ports.lock);
+	net->ipv4.ip_local_ports.range[0] = range[0];
+	net->ipv4.ip_local_ports.range[1] = range[1];
+	write_sequnlock(&net->ipv4.ip_local_ports.lock);
 }
 
 /* Validate changes from /proc interface. */
@@ -57,7 +57,7 @@ static int ipv4_local_port_range(struct ctl_table *table, int write,
 				 size_t *lenp, loff_t *ppos)
 {
 	struct net *net =
-		container_of(table->data, struct net, ipv4.sysctl_local_ports.range);
+		container_of(table->data, struct net, ipv4.ip_local_ports.range);
 	int ret;
 	int range[2];
 	struct ctl_table tmp = {
@@ -87,14 +87,14 @@ static void inet_get_ping_group_range_table(struct ctl_table *table, kgid_t *low
 {
 	kgid_t *data = table->data;
 	struct net *net =
-		container_of(table->data, struct net, ipv4.sysctl_ping_group_range);
+		container_of(table->data, struct net, ipv4.ping_group_range.range);
 	unsigned int seq;
 	do {
-		seq = read_seqbegin(&net->ipv4.sysctl_local_ports.lock);
+		seq = read_seqbegin(&net->ipv4.ip_local_ports.lock);
 
 		*low = data[0];
 		*high = data[1];
-	} while (read_seqretry(&net->ipv4.sysctl_local_ports.lock, seq));
+	} while (read_seqretry(&net->ipv4.ip_local_ports.lock, seq));
 }
 
 /* Update system visible IP port range */
@@ -102,11 +102,11 @@ static void set_ping_group_range(struct ctl_table *table, kgid_t low, kgid_t hig
 {
 	kgid_t *data = table->data;
 	struct net *net =
-		container_of(table->data, struct net, ipv4.sysctl_ping_group_range);
-	write_seqlock(&net->ipv4.sysctl_local_ports.lock);
+		container_of(table->data, struct net, ipv4.ping_group_range.range);
+	write_seqlock(&net->ipv4.ip_local_ports.lock);
 	data[0] = low;
 	data[1] = high;
-	write_sequnlock(&net->ipv4.sysctl_local_ports.lock);
+	write_sequnlock(&net->ipv4.ip_local_ports.lock);
 }
 
 /* Validate changes from /proc interface. */
@@ -805,7 +805,7 @@ static struct ctl_table ipv4_net_table[] = {
 	},
 	{
 		.procname	= "ping_group_range",
-		.data		= &init_net.ipv4.sysctl_ping_group_range,
+		.data		= &init_net.ipv4.ping_group_range.range,
 		.maxlen		= sizeof(gid_t)*2,
 		.mode		= 0644,
 		.proc_handler	= ipv4_ping_group_range,
@@ -819,8 +819,8 @@ static struct ctl_table ipv4_net_table[] = {
 	},
 	{
 		.procname	= "ip_local_port_range",
-		.maxlen		= sizeof(init_net.ipv4.sysctl_local_ports.range),
-		.data		= &init_net.ipv4.sysctl_local_ports.range,
+		.maxlen		= sizeof(init_net.ipv4.ip_local_ports.range),
+		.data		= &init_net.ipv4.ip_local_ports.range,
 		.mode		= 0644,
 		.proc_handler	= ipv4_local_port_range,
 	},
@@ -858,20 +858,6 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
 			table[i].data += (void *)net - (void *)&init_net;
 	}
 
-	/*
-	 * Sane defaults - nobody may create ping sockets.
-	 * Boot scripts should set this to distro-specific group.
-	 */
-	net->ipv4.sysctl_ping_group_range[0] = make_kgid(&init_user_ns, 1);
-	net->ipv4.sysctl_ping_group_range[1] = make_kgid(&init_user_ns, 0);
-
-	/*
-	 * Set defaults for local port range
-	 */
-	seqlock_init(&net->ipv4.sysctl_local_ports.lock);
-	net->ipv4.sysctl_local_ports.range[0] =  32768;
-	net->ipv4.sysctl_local_ports.range[1] =  61000;
-
 	net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table);
 	if (net->ipv4.ipv4_hdr == NULL)
 		goto err_reg;
diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c
index 40e701f2e1e0..186a8ecf92fa 100644
--- a/net/ipv4/xfrm4_output.c
+++ b/net/ipv4/xfrm4_output.c
@@ -62,10 +62,7 @@ int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
 	if (err)
 		return err;
 
-	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
-	IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED;
-
-	skb->protocol = htons(ETH_P_IP);
+	IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE;
 
 	return x->outer_mode->output2(x, skb);
 }
@@ -73,27 +70,34 @@ EXPORT_SYMBOL(xfrm4_prepare_output);
 
 int xfrm4_output_finish(struct sk_buff *skb)
 {
+	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+	skb->protocol = htons(ETH_P_IP);
+
+#ifdef CONFIG_NETFILTER
+	IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED;
+#endif
+
+	return xfrm_output(skb);
+}
+
+static int __xfrm4_output(struct sk_buff *skb)
+{
+	struct xfrm_state *x = skb_dst(skb)->xfrm;
+
 #ifdef CONFIG_NETFILTER
-	if (!skb_dst(skb)->xfrm) {
+	if (!x) {
 		IPCB(skb)->flags |= IPSKB_REROUTED;
 		return dst_output(skb);
 	}
-
-	IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED;
 #endif
 
-	skb->protocol = htons(ETH_P_IP);
-	return xfrm_output(skb);
+	return x->outer_mode->afinfo->output_finish(skb);
 }
 
 int xfrm4_output(struct sock *sk, struct sk_buff *skb)
 {
-	struct dst_entry *dst = skb_dst(skb);
-	struct xfrm_state *x = dst->xfrm;
-
 	return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, skb,
-			    NULL, dst->dev,
-			    x->outer_mode->afinfo->output_finish,
+			    NULL, skb_dst(skb)->dev, __xfrm4_output,
 			    !(IPCB(skb)->flags & IPSKB_REROUTED));
 }
 
diff --git a/net/ipv4/xfrm4_protocol.c b/net/ipv4/xfrm4_protocol.c
index 7f7b243e8139..a2ce0101eaac 100644
--- a/net/ipv4/xfrm4_protocol.c
+++ b/net/ipv4/xfrm4_protocol.c
@@ -50,8 +50,12 @@ int xfrm4_rcv_cb(struct sk_buff *skb, u8 protocol, int err)
 {
 	int ret;
 	struct xfrm4_protocol *handler;
+	struct xfrm4_protocol __rcu **head = proto_handlers(protocol);
 
-	for_each_protocol_rcu(*proto_handlers(protocol), handler)
+	if (!head)
+		return 0;
+
+	for_each_protocol_rcu(*head, handler)
 		if ((ret = handler->cb_handler(skb, err)) <= 0)
 			return ret;
 
@@ -64,15 +68,20 @@ int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi,
 {
 	int ret;
 	struct xfrm4_protocol *handler;
+	struct xfrm4_protocol __rcu **head = proto_handlers(nexthdr);
 
 	XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL;
 	XFRM_SPI_SKB_CB(skb)->family = AF_INET;
 	XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
 
-	for_each_protocol_rcu(*proto_handlers(nexthdr), handler)
+	if (!head)
+		goto out;
+
+	for_each_protocol_rcu(*head, handler)
 		if ((ret = handler->input_handler(skb, nexthdr, spi, encap_type)) != -EINVAL)
 			return ret;
 
+out:
 	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
 
 	kfree_skb(skb);
@@ -208,6 +217,9 @@ int xfrm4_protocol_register(struct xfrm4_protocol *handler,
 	int ret = -EEXIST;
 	int priority = handler->priority;
 
+	if (!proto_handlers(protocol) || !netproto(protocol))
+		return -EINVAL;
+
 	mutex_lock(&xfrm4_protocol_mutex);
 
 	if (!rcu_dereference_protected(*proto_handlers(protocol),
@@ -250,6 +262,9 @@ int xfrm4_protocol_deregister(struct xfrm4_protocol *handler,
 	struct xfrm4_protocol *t;
 	int ret = -ENOENT;
 
+	if (!proto_handlers(protocol) || !netproto(protocol))
+		return -EINVAL;
+
 	mutex_lock(&xfrm4_protocol_mutex);
 
 	for (pprev = proto_handlers(protocol);
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 59f95affceb0..b2f091566f88 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -196,7 +196,6 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 	unsigned int off;
 	u16 flush = 1;
 	int proto;
-	__wsum csum;
 
 	off = skb_gro_offset(skb);
 	hlen = off + sizeof(*iph);
@@ -264,13 +263,10 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 
 	NAPI_GRO_CB(skb)->flush |= flush;
 
-	csum = skb->csum;
-	skb_postpull_rcsum(skb, iph, skb_network_header_len(skb));
+	skb_gro_postpull_rcsum(skb, iph, nlen);
 
 	pp = ops->callbacks.gro_receive(head, skb);
 
-	skb->csum = csum;
-
 out_unlock:
 	rcu_read_unlock();
 
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 40e7581374f7..fbf11562b54c 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -344,12 +344,16 @@ static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst)
 
 static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
 {
-	if (skb->len <= mtu || skb->local_df)
+	if (skb->len <= mtu)
 		return false;
 
+	/* ipv6 conntrack defrag sets max_frag_size + local_df */
 	if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)
 		return true;
 
+	if (skb->local_df)
+		return false;
+
 	if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu)
 		return false;
 
@@ -1225,7 +1229,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 		unsigned int maxnonfragsize, headersize;
 
 		headersize = sizeof(struct ipv6hdr) +
-			     (opt ? opt->tot_len : 0) +
+			     (opt ? opt->opt_flen + opt->opt_nflen : 0) +
 			     (dst_allfrag(&rt->dst) ?
 			      sizeof(struct frag_hdr) : 0) +
 			     rt->rt6i_nfheader_len;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index b05b609f69d1..f6a66bb4114d 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1557,7 +1557,7 @@ static int ip6_tnl_validate(struct nlattr *tb[], struct nlattr *data[])
 {
 	u8 proto;
 
-	if (!data)
+	if (!data || !data[IFLA_IPTUN_PROTO])
 		return 0;
 
 	proto = nla_get_u8(data[IFLA_IPTUN_PROTO]);
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index b7c0f827140b..6cc9f9371cc5 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -511,6 +511,7 @@ static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		    u8 type, u8 code, int offset, __be32 info)
 {
 	__be32 spi;
+	__u32 mark;
 	struct xfrm_state *x;
 	struct ip6_tnl *t;
 	struct ip_esp_hdr *esph;
@@ -524,6 +525,8 @@ static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	if (!t)
 		return -1;
 
+	mark = be32_to_cpu(t->parms.o_key);
+
 	switch (protocol) {
 	case IPPROTO_ESP:
 		esph = (struct ip_esp_hdr *)(skb->data + offset);
@@ -545,7 +548,7 @@ static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	    type != NDISC_REDIRECT)
 		return 0;
 
-	x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
+	x = xfrm_state_lookup(net, mark, (const xfrm_address_t *)&iph->daddr,
 			      spi, protocol, AF_INET6);
 	if (!x)
 		return 0;
@@ -1097,7 +1100,6 @@ static int __init vti6_tunnel_init(void)
 
 	err = xfrm6_protocol_register(&vti_esp6_protocol, IPPROTO_ESP);
 	if (err < 0) {
-		unregister_pernet_device(&vti6_net_ops);
 		pr_err("%s: can't register vti6 protocol\n", __func__);
 
 		goto out;
@@ -1106,7 +1108,6 @@ static int __init vti6_tunnel_init(void)
 	err = xfrm6_protocol_register(&vti_ah6_protocol, IPPROTO_AH);
 	if (err < 0) {
 		xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP);
-		unregister_pernet_device(&vti6_net_ops);
 		pr_err("%s: can't register vti6 protocol\n", __func__);
 
 		goto out;
@@ -1116,7 +1117,6 @@ static int __init vti6_tunnel_init(void)
 	if (err < 0) {
 		xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH);
 		xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP);
-		unregister_pernet_device(&vti6_net_ops);
 		pr_err("%s: can't register vti6 protocol\n", __func__);
 
 		goto out;
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 09a22f4f36c9..ca8d4ea48a5d 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -851,7 +851,7 @@ out:
 static void ndisc_recv_na(struct sk_buff *skb)
 {
 	struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb);
-	const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr;
+	struct in6_addr *saddr = &ipv6_hdr(skb)->saddr;
 	const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr;
 	u8 *lladdr = NULL;
 	u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) +
@@ -944,10 +944,7 @@ static void ndisc_recv_na(struct sk_buff *skb)
 			/*
 			 * Change: router to host
 			 */
-			struct rt6_info *rt;
-			rt = rt6_get_dflt_router(saddr, dev);
-			if (rt)
-				ip6_del_rt(rt);
+			rt6_clean_tohost(dev_net(dev),  saddr);
 		}
 
 out:
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 95f3f1da0d7f..d38e6a8d8b9f 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -30,13 +30,15 @@ int ip6_route_me_harder(struct sk_buff *skb)
 		.daddr = iph->daddr,
 		.saddr = iph->saddr,
 	};
+	int err;
 
 	dst = ip6_route_output(net, skb->sk, &fl6);
-	if (dst->error) {
+	err = dst->error;
+	if (err) {
 		IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
 		LIMIT_NETDEBUG(KERN_DEBUG "ip6_route_me_harder: No more route.\n");
 		dst_release(dst);
-		return dst->error;
+		return err;
 	}
 
 	/* Drop old route. */
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 004fffb6c221..6ebdb7b6744c 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2234,6 +2234,27 @@ void rt6_remove_prefsrc(struct inet6_ifaddr *ifp)
 	fib6_clean_all(net, fib6_remove_prefsrc, &adni);
 }
 
+#define RTF_RA_ROUTER		(RTF_ADDRCONF | RTF_DEFAULT | RTF_GATEWAY)
+#define RTF_CACHE_GATEWAY	(RTF_GATEWAY | RTF_CACHE)
+
+/* Remove routers and update dst entries when gateway turn into host. */
+static int fib6_clean_tohost(struct rt6_info *rt, void *arg)
+{
+	struct in6_addr *gateway = (struct in6_addr *)arg;
+
+	if ((((rt->rt6i_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) ||
+	     ((rt->rt6i_flags & RTF_CACHE_GATEWAY) == RTF_CACHE_GATEWAY)) &&
+	     ipv6_addr_equal(gateway, &rt->rt6i_gateway)) {
+		return -1;
+	}
+	return 0;
+}
+
+void rt6_clean_tohost(struct net *net, struct in6_addr *gateway)
+{
+	fib6_clean_all(net, fib6_clean_tohost, gateway);
+}
+
 struct arg_dev_net {
 	struct net_device *dev;
 	struct net *net;
@@ -2709,6 +2730,9 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh)
 	if (tb[RTA_OIF])
 		oif = nla_get_u32(tb[RTA_OIF]);
 
+	if (tb[RTA_MARK])
+		fl6.flowi6_mark = nla_get_u32(tb[RTA_MARK]);
+
 	if (iif) {
 		struct net_device *dev;
 		int flags = 0;
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index 0d78132ff18a..8517d3cd1aed 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -42,7 +42,7 @@ static struct sk_buff **tcp6_gro_receive(struct sk_buff **head,
 	if (NAPI_GRO_CB(skb)->flush)
 		goto skip_csum;
 
-	wsum = skb->csum;
+	wsum = NAPI_GRO_CB(skb)->csum;
 
 	switch (skb->ip_summed) {
 	case CHECKSUM_NONE:
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index 19ef329bdbf8..b930d080c66f 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -114,12 +114,6 @@ int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
 	if (err)
 		return err;
 
-	memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
-#ifdef CONFIG_NETFILTER
-	IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED;
-#endif
-
-	skb->protocol = htons(ETH_P_IPV6);
 	skb->local_df = 1;
 
 	return x->outer_mode->output2(x, skb);
@@ -128,11 +122,13 @@ EXPORT_SYMBOL(xfrm6_prepare_output);
 
 int xfrm6_output_finish(struct sk_buff *skb)
 {
+	memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+	skb->protocol = htons(ETH_P_IPV6);
+
 #ifdef CONFIG_NETFILTER
 	IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED;
 #endif
 
-	skb->protocol = htons(ETH_P_IPV6);
 	return xfrm_output(skb);
 }
 
@@ -142,6 +138,13 @@ static int __xfrm6_output(struct sk_buff *skb)
 	struct xfrm_state *x = dst->xfrm;
 	int mtu;
 
+#ifdef CONFIG_NETFILTER
+	if (!x) {
+		IP6CB(skb)->flags |= IP6SKB_REROUTED;
+		return dst_output(skb);
+	}
+#endif
+
 	if (skb->protocol == htons(ETH_P_IPV6))
 		mtu = ip6_skb_dst_mtu(skb);
 	else
@@ -165,6 +168,7 @@ static int __xfrm6_output(struct sk_buff *skb)
 
 int xfrm6_output(struct sock *sk, struct sk_buff *skb)
 {
-	return NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb, NULL,
-		       skb_dst(skb)->dev, __xfrm6_output);
+	return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, skb,
+			    NULL, skb_dst(skb)->dev, __xfrm6_output,
+			    !(IP6CB(skb)->flags & IP6SKB_REROUTED));
 }
diff --git a/net/ipv6/xfrm6_protocol.c b/net/ipv6/xfrm6_protocol.c
index 6ab989c486f7..54d13f8dbbae 100644
--- a/net/ipv6/xfrm6_protocol.c
+++ b/net/ipv6/xfrm6_protocol.c
@@ -50,6 +50,10 @@ int xfrm6_rcv_cb(struct sk_buff *skb, u8 protocol, int err)
 {
 	int ret;
 	struct xfrm6_protocol *handler;
+	struct xfrm6_protocol __rcu **head = proto_handlers(protocol);
+
+	if (!head)
+		return 0;
 
 	for_each_protocol_rcu(*proto_handlers(protocol), handler)
 		if ((ret = handler->cb_handler(skb, err)) <= 0)
@@ -184,10 +188,12 @@ int xfrm6_protocol_register(struct xfrm6_protocol *handler,
 	struct xfrm6_protocol __rcu **pprev;
 	struct xfrm6_protocol *t;
 	bool add_netproto = false;
-
 	int ret = -EEXIST;
 	int priority = handler->priority;
 
+	if (!proto_handlers(protocol) || !netproto(protocol))
+		return -EINVAL;
+
 	mutex_lock(&xfrm6_protocol_mutex);
 
 	if (!rcu_dereference_protected(*proto_handlers(protocol),
@@ -230,6 +236,9 @@ int xfrm6_protocol_deregister(struct xfrm6_protocol *handler,
 	struct xfrm6_protocol *t;
 	int ret = -ENOENT;
 
+	if (!proto_handlers(protocol) || !netproto(protocol))
+		return -EINVAL;
+
 	mutex_lock(&xfrm6_protocol_mutex);
 
 	for (pprev = proto_handlers(protocol);
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 01e77b0ae075..8c9d7302c846 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1830,7 +1830,7 @@ static void iucv_callback_txdone(struct iucv_path *path,
 		spin_lock_irqsave(&list->lock, flags);
 
 		while (list_skb != (struct sk_buff *)list) {
-			if (msg->tag != IUCV_SKB_CB(list_skb)->tag) {
+			if (msg->tag == IUCV_SKB_CB(list_skb)->tag) {
 				this = list_skb;
 				break;
 			}
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 222c28b75315..f169b6ee94ee 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -317,6 +317,7 @@ struct ieee80211_roc_work {
 
 	bool started, abort, hw_begun, notified;
 	bool to_be_freed;
+	bool on_channel;
 
 	unsigned long hw_start_time;
 
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index dee50aefd6e8..27600a9808ba 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -3598,18 +3598,24 @@ void ieee80211_mgd_quiesce(struct ieee80211_sub_if_data *sdata)
 
 	sdata_lock(sdata);
 
-	if (ifmgd->auth_data) {
+	if (ifmgd->auth_data || ifmgd->assoc_data) {
+		const u8 *bssid = ifmgd->auth_data ?
+				ifmgd->auth_data->bss->bssid :
+				ifmgd->assoc_data->bss->bssid;
+
 		/*
-		 * If we are trying to authenticate while suspending, cfg80211
-		 * won't know and won't actually abort those attempts, thus we
-		 * need to do that ourselves.
+		 * If we are trying to authenticate / associate while suspending,
+		 * cfg80211 won't know and won't actually abort those attempts,
+		 * thus we need to do that ourselves.
 		 */
-		ieee80211_send_deauth_disassoc(sdata,
-					       ifmgd->auth_data->bss->bssid,
+		ieee80211_send_deauth_disassoc(sdata, bssid,
 					       IEEE80211_STYPE_DEAUTH,
 					       WLAN_REASON_DEAUTH_LEAVING,
 					       false, frame_buf);
-		ieee80211_destroy_auth_data(sdata, false);
+		if (ifmgd->assoc_data)
+			ieee80211_destroy_assoc_data(sdata, false);
+		if (ifmgd->auth_data)
+			ieee80211_destroy_auth_data(sdata, false);
 		cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf,
 				      IEEE80211_DEAUTH_FRAME_LEN);
 	}
diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c
index 6fb38558a5e6..7a17decd27f9 100644
--- a/net/mac80211/offchannel.c
+++ b/net/mac80211/offchannel.c
@@ -333,7 +333,7 @@ void ieee80211_sw_roc_work(struct work_struct *work)
 		container_of(work, struct ieee80211_roc_work, work.work);
 	struct ieee80211_sub_if_data *sdata = roc->sdata;
 	struct ieee80211_local *local = sdata->local;
-	bool started;
+	bool started, on_channel;
 
 	mutex_lock(&local->mtx);
 
@@ -354,14 +354,26 @@ void ieee80211_sw_roc_work(struct work_struct *work)
 	if (!roc->started) {
 		struct ieee80211_roc_work *dep;
 
-		/* start this ROC */
-		ieee80211_offchannel_stop_vifs(local);
+		WARN_ON(local->use_chanctx);
+
+		/* If actually operating on the desired channel (with at least
+		 * 20 MHz channel width) don't stop all the operations but still
+		 * treat it as though the ROC operation started properly, so
+		 * other ROC operations won't interfere with this one.
+		 */
+		roc->on_channel = roc->chan == local->_oper_chandef.chan &&
+				  local->_oper_chandef.width != NL80211_CHAN_WIDTH_5 &&
+				  local->_oper_chandef.width != NL80211_CHAN_WIDTH_10;
 
-		/* switch channel etc */
+		/* start this ROC */
 		ieee80211_recalc_idle(local);
 
-		local->tmp_channel = roc->chan;
-		ieee80211_hw_config(local, 0);
+		if (!roc->on_channel) {
+			ieee80211_offchannel_stop_vifs(local);
+
+			local->tmp_channel = roc->chan;
+			ieee80211_hw_config(local, 0);
+		}
 
 		/* tell userspace or send frame */
 		ieee80211_handle_roc_started(roc);
@@ -380,9 +392,10 @@ void ieee80211_sw_roc_work(struct work_struct *work)
  finish:
 		list_del(&roc->list);
 		started = roc->started;
+		on_channel = roc->on_channel;
 		ieee80211_roc_notify_destroy(roc, !roc->abort);
 
-		if (started) {
+		if (started && !on_channel) {
 			ieee80211_flush_queues(local, NULL);
 
 			local->tmp_channel = NULL;
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 216c45b949e5..2b608b2b70ec 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1231,7 +1231,8 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx)
 		if (ether_addr_equal(bssid, rx->sdata->u.ibss.bssid) &&
 		    test_sta_flag(sta, WLAN_STA_AUTHORIZED)) {
 			sta->last_rx = jiffies;
-			if (ieee80211_is_data(hdr->frame_control)) {
+			if (ieee80211_is_data(hdr->frame_control) &&
+			    !is_multicast_ether_addr(hdr->addr1)) {
 				sta->last_rx_rate_idx = status->rate_idx;
 				sta->last_rx_rate_flag = status->flag;
 				sta->last_rx_rate_vht_flag = status->vht_flag;
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 137a192e64bc..847d92f6bef6 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -1148,7 +1148,8 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
 	atomic_dec(&ps->num_sta_ps);
 
 	/* This station just woke up and isn't aware of our SMPS state */
-	if (!ieee80211_smps_is_restrictive(sta->known_smps_mode,
+	if (!ieee80211_vif_is_mesh(&sdata->vif) &&
+	    !ieee80211_smps_is_restrictive(sta->known_smps_mode,
 					   sdata->smps_mode) &&
 	    sta->known_smps_mode != sdata->bss->req_smps &&
 	    sta_info_tx_streams(sta) != 1) {
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 00ba90b02ab2..60cb7a665976 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -314,10 +314,9 @@ ieee80211_add_tx_radiotap_header(struct ieee80211_local *local,
 	    !is_multicast_ether_addr(hdr->addr1))
 		txflags |= IEEE80211_RADIOTAP_F_TX_FAIL;
 
-	if ((info->status.rates[0].flags & IEEE80211_TX_RC_USE_RTS_CTS) ||
-	    (info->status.rates[0].flags & IEEE80211_TX_RC_USE_CTS_PROTECT))
+	if (info->status.rates[0].flags & IEEE80211_TX_RC_USE_CTS_PROTECT)
 		txflags |= IEEE80211_RADIOTAP_F_TX_CTS;
-	else if (info->status.rates[0].flags & IEEE80211_TX_RC_USE_RTS_CTS)
+	if (info->status.rates[0].flags & IEEE80211_TX_RC_USE_RTS_CTS)
 		txflags |= IEEE80211_RADIOTAP_F_TX_RTS;
 
 	put_unaligned_le16(txflags, pos);
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index a0b0aea76525..cec5b60487a4 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -21,10 +21,10 @@
 
 #define VIF_ENTRY	__field(enum nl80211_iftype, vif_type) __field(void *, sdata)	\
 			__field(bool, p2p)						\
-			__string(vif_name, sdata->dev ? sdata->dev->name : "<nodev>")
+			__string(vif_name, sdata->name)
 #define VIF_ASSIGN	__entry->vif_type = sdata->vif.type; __entry->sdata = sdata;	\
 			__entry->p2p = sdata->vif.p2p;					\
-			__assign_str(vif_name, sdata->dev ? sdata->dev->name : sdata->name)
+			__assign_str(vif_name, sdata->name)
 #define VIF_PR_FMT	" vif:%s(%d%s)"
 #define VIF_PR_ARG	__get_str(vif_name), __entry->vif_type, __entry->p2p ? "/p2p" : ""
 
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 275c94f995f7..3c365837e910 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1780,7 +1780,7 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 	mutex_unlock(&local->mtx);
 
 	if (sched_scan_stopped)
-		cfg80211_sched_scan_stopped(local->hw.wiphy);
+		cfg80211_sched_scan_stopped_rtnl(local->hw.wiphy);
 
 	/*
 	 * If this is for hw restart things are still running.
diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c
index e9e36a256165..9265adfdabfc 100644
--- a/net/mac80211/vht.c
+++ b/net/mac80211/vht.c
@@ -129,9 +129,12 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata,
 	if (!vht_cap_ie || !sband->vht_cap.vht_supported)
 		return;
 
-	/* A VHT STA must support 40 MHz */
-	if (!(sta->sta.ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40))
-		return;
+	/*
+	 * A VHT STA must support 40 MHz, but if we verify that here
+	 * then we break a few things - some APs (e.g. Netgear R6300v2
+	 * and others based on the BCM4360 chipset) will unset this
+	 * capability bit when operating in 20 MHz.
+	 */
 
 	vht_cap->vht_supported = true;
 
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index ccc46fa5edbc..58579634427d 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1336,6 +1336,9 @@ ctnetlink_setup_nat(struct nf_conn *ct, const struct nlattr * const cda[])
 #ifdef CONFIG_NF_NAT_NEEDED
 	int ret;
 
+	if (!cda[CTA_NAT_DST] && !cda[CTA_NAT_SRC])
+		return 0;
+
 	ret = ctnetlink_parse_nat_setup(ct, NF_NAT_MANIP_DST,
 					cda[CTA_NAT_DST]);
 	if (ret < 0)
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index 804105391b9a..345acfb1720b 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -66,20 +66,6 @@ struct nft_jumpstack {
 	int			rulenum;
 };
 
-static inline void
-nft_chain_stats(const struct nft_chain *this, const struct nft_pktinfo *pkt,
-		struct nft_jumpstack *jumpstack, unsigned int stackptr)
-{
-	struct nft_stats __percpu *stats;
-	const struct nft_chain *chain = stackptr ? jumpstack[0].chain : this;
-
-	rcu_read_lock_bh();
-	stats = rcu_dereference(nft_base_chain(chain)->stats);
-	__this_cpu_inc(stats->pkts);
-	__this_cpu_add(stats->bytes, pkt->skb->len);
-	rcu_read_unlock_bh();
-}
-
 enum nft_trace {
 	NFT_TRACE_RULE,
 	NFT_TRACE_RETURN,
@@ -117,13 +103,14 @@ static void nft_trace_packet(const struct nft_pktinfo *pkt,
 unsigned int
 nft_do_chain(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops)
 {
-	const struct nft_chain *chain = ops->priv;
+	const struct nft_chain *chain = ops->priv, *basechain = chain;
 	const struct nft_rule *rule;
 	const struct nft_expr *expr, *last;
 	struct nft_data data[NFT_REG_MAX + 1];
 	unsigned int stackptr = 0;
 	struct nft_jumpstack jumpstack[NFT_JUMP_STACK_SIZE];
-	int rulenum = 0;
+	struct nft_stats __percpu *stats;
+	int rulenum;
 	/*
 	 * Cache cursor to avoid problems in case that the cursor is updated
 	 * while traversing the ruleset.
@@ -131,6 +118,7 @@ nft_do_chain(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops)
 	unsigned int gencursor = ACCESS_ONCE(chain->net->nft.gencursor);
 
 do_chain:
+	rulenum = 0;
 	rule = list_entry(&chain->rules, struct nft_rule, list);
 next_rule:
 	data[NFT_REG_VERDICT].verdict = NFT_CONTINUE;
@@ -156,8 +144,10 @@ next_rule:
 		switch (data[NFT_REG_VERDICT].verdict) {
 		case NFT_BREAK:
 			data[NFT_REG_VERDICT].verdict = NFT_CONTINUE;
-			/* fall through */
+			continue;
 		case NFT_CONTINUE:
+			if (unlikely(pkt->skb->nf_trace))
+				nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE);
 			continue;
 		}
 		break;
@@ -183,37 +173,44 @@ next_rule:
 		jumpstack[stackptr].rule  = rule;
 		jumpstack[stackptr].rulenum = rulenum;
 		stackptr++;
-		/* fall through */
+		chain = data[NFT_REG_VERDICT].chain;
+		goto do_chain;
 	case NFT_GOTO:
+		if (unlikely(pkt->skb->nf_trace))
+			nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RULE);
+
 		chain = data[NFT_REG_VERDICT].chain;
 		goto do_chain;
 	case NFT_RETURN:
 		if (unlikely(pkt->skb->nf_trace))
 			nft_trace_packet(pkt, chain, rulenum, NFT_TRACE_RETURN);
-
-		/* fall through */
+		break;
 	case NFT_CONTINUE:
+		if (unlikely(pkt->skb->nf_trace && !(chain->flags & NFT_BASE_CHAIN)))
+			nft_trace_packet(pkt, chain, ++rulenum, NFT_TRACE_RETURN);
 		break;
 	default:
 		WARN_ON(1);
 	}
 
 	if (stackptr > 0) {
-		if (unlikely(pkt->skb->nf_trace))
-			nft_trace_packet(pkt, chain, ++rulenum, NFT_TRACE_RETURN);
-
 		stackptr--;
 		chain = jumpstack[stackptr].chain;
 		rule  = jumpstack[stackptr].rule;
 		rulenum = jumpstack[stackptr].rulenum;
 		goto next_rule;
 	}
-	nft_chain_stats(chain, pkt, jumpstack, stackptr);
 
 	if (unlikely(pkt->skb->nf_trace))
-		nft_trace_packet(pkt, chain, ++rulenum, NFT_TRACE_POLICY);
+		nft_trace_packet(pkt, basechain, -1, NFT_TRACE_POLICY);
+
+	rcu_read_lock_bh();
+	stats = rcu_dereference(nft_base_chain(basechain)->stats);
+	__this_cpu_inc(stats->pkts);
+	__this_cpu_add(stats->bytes, pkt->skb->len);
+	rcu_read_unlock_bh();
 
-	return nft_base_chain(chain)->policy;
+	return nft_base_chain(basechain)->policy;
 }
 EXPORT_SYMBOL_GPL(nft_do_chain);
 
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index e009087620e3..23ef77c60fff 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -256,15 +256,15 @@ replay:
 #endif
 		{
 			nfnl_unlock(subsys_id);
-			kfree_skb(nskb);
-			return netlink_ack(skb, nlh, -EOPNOTSUPP);
+			netlink_ack(skb, nlh, -EOPNOTSUPP);
+			return kfree_skb(nskb);
 		}
 	}
 
 	if (!ss->commit || !ss->abort) {
 		nfnl_unlock(subsys_id);
-		kfree_skb(nskb);
-		return netlink_ack(skb, nlh, -EOPNOTSUPP);
+		netlink_ack(skb, nlh, -EOPNOTSUPP);
+		return kfree_skb(skb);
 	}
 
 	while (skb->len >= nlmsg_total_size(0)) {
diff --git a/net/rxrpc/ar-key.c b/net/rxrpc/ar-key.c
index 7633a752c65e..0ad080790a32 100644
--- a/net/rxrpc/ar-key.c
+++ b/net/rxrpc/ar-key.c
@@ -99,7 +99,7 @@ static int rxrpc_instantiate_xdr_rxkad(struct key *key, const __be32 *xdr,
 	_debug("tktlen: %x", tktlen);
 	if (tktlen > AFSTOKEN_RK_TIX_MAX)
 		return -EKEYREJECTED;
-	if (8 * 4 + tktlen != toklen)
+	if (toklen < 8 * 4 + tktlen)
 		return -EKEYREJECTED;
 
 	plen = sizeof(*token) + sizeof(*token->kad) + tktlen;
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index eed8404443d8..f435a88d899a 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -188,6 +188,12 @@ static const struct nla_policy tcindex_policy[TCA_TCINDEX_MAX + 1] = {
 	[TCA_TCINDEX_CLASSID]		= { .type = NLA_U32 },
 };
 
+static void tcindex_filter_result_init(struct tcindex_filter_result *r)
+{
+	memset(r, 0, sizeof(*r));
+	tcf_exts_init(&r->exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
+}
+
 static int
 tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 		  u32 handle, struct tcindex_data *p,
@@ -207,15 +213,11 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 		return err;
 
 	memcpy(&cp, p, sizeof(cp));
-	memset(&new_filter_result, 0, sizeof(new_filter_result));
-	tcf_exts_init(&new_filter_result.exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
+	tcindex_filter_result_init(&new_filter_result);
 
+	tcindex_filter_result_init(&cr);
 	if (old_r)
-		memcpy(&cr, r, sizeof(cr));
-	else {
-		memset(&cr, 0, sizeof(cr));
-		tcf_exts_init(&cr.exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE);
-	}
+		cr.res = r->res;
 
 	if (tb[TCA_TCINDEX_HASH])
 		cp.hash = nla_get_u32(tb[TCA_TCINDEX_HASH]);
@@ -267,9 +269,14 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	err = -ENOMEM;
 	if (!cp.perfect && !cp.h) {
 		if (valid_perfect_hash(&cp)) {
+			int i;
+
 			cp.perfect = kcalloc(cp.hash, sizeof(*r), GFP_KERNEL);
 			if (!cp.perfect)
 				goto errout;
+			for (i = 0; i < cp.hash; i++)
+				tcf_exts_init(&cp.perfect[i].exts, TCA_TCINDEX_ACT,
+					      TCA_TCINDEX_POLICE);
 			balloc = 1;
 		} else {
 			cp.h = kcalloc(cp.hash, sizeof(f), GFP_KERNEL);
@@ -295,14 +302,17 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 		tcf_bind_filter(tp, &cr.res, base);
 	}
 
-	tcf_exts_change(tp, &cr.exts, &e);
+	if (old_r)
+		tcf_exts_change(tp, &r->exts, &e);
+	else
+		tcf_exts_change(tp, &cr.exts, &e);
 
 	tcf_tree_lock(tp);
 	if (old_r && old_r != r)
-		memset(old_r, 0, sizeof(*old_r));
+		tcindex_filter_result_init(old_r);
 
 	memcpy(p, &cp, sizeof(cp));
-	memcpy(r, &cr, sizeof(cr));
+	r->res = cr.res;
 
 	if (r == &new_filter_result) {
 		struct tcindex_filter **fp;
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 7d09a712cb1f..88f108edfb58 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -284,14 +284,22 @@ void cfg80211_sched_scan_results(struct wiphy *wiphy)
 }
 EXPORT_SYMBOL(cfg80211_sched_scan_results);
 
-void cfg80211_sched_scan_stopped(struct wiphy *wiphy)
+void cfg80211_sched_scan_stopped_rtnl(struct wiphy *wiphy)
 {
 	struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy);
 
+	ASSERT_RTNL();
+
 	trace_cfg80211_sched_scan_stopped(wiphy);
 
-	rtnl_lock();
 	__cfg80211_stop_sched_scan(rdev, true);
+}
+EXPORT_SYMBOL(cfg80211_sched_scan_stopped_rtnl);
+
+void cfg80211_sched_scan_stopped(struct wiphy *wiphy)
+{
+	rtnl_lock();
+	cfg80211_sched_scan_stopped_rtnl(wiphy);
 	rtnl_unlock();
 }
 EXPORT_SYMBOL(cfg80211_sched_scan_stopped);
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index acdcb4a81817..3546a77033de 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -234,7 +234,6 @@ void cfg80211_conn_work(struct work_struct *work)
 					NULL, 0, NULL, 0,
 					WLAN_STATUS_UNSPECIFIED_FAILURE,
 					false, NULL);
-			cfg80211_sme_free(wdev);
 		}
 		wdev_unlock(wdev);
 	}
@@ -648,6 +647,7 @@ void __cfg80211_connect_result(struct net_device *dev, const u8 *bssid,
 			cfg80211_unhold_bss(bss_from_pub(bss));
 			cfg80211_put_bss(wdev->wiphy, bss);
 		}
+		cfg80211_sme_free(wdev);
 		return;
 	}
 
diff --git a/scripts/checksyscalls.sh b/scripts/checksyscalls.sh
index fd8fa9aa7c4e..5b3add31f9f1 100755
--- a/scripts/checksyscalls.sh
+++ b/scripts/checksyscalls.sh
@@ -25,7 +25,7 @@ cat << EOF
 #define __IGNORE_rmdir		/* unlinkat */
 #define __IGNORE_lchown		/* fchownat */
 #define __IGNORE_access		/* faccessat */
-#define __IGNORE_rename		/* renameat */
+#define __IGNORE_rename		/* renameat2 */
 #define __IGNORE_readlink	/* readlinkat */
 #define __IGNORE_symlink	/* symlinkat */
 #define __IGNORE_utimes		/* futimesat */
@@ -37,6 +37,9 @@ cat << EOF
 #define __IGNORE_lstat64	/* fstatat64 */
 #endif
 
+/* Missing flags argument */
+#define __IGNORE_renameat	/* renameat2 */
+
 /* CLOEXEC flag */
 #define __IGNORE_pipe		/* pipe2 */
 #define __IGNORE_dup2		/* dup3 */
diff --git a/security/device_cgroup.c b/security/device_cgroup.c
index 8365909f5f8c..9134dbf70d3e 100644
--- a/security/device_cgroup.c
+++ b/security/device_cgroup.c
@@ -306,57 +306,138 @@ static int devcgroup_seq_show(struct seq_file *m, void *v)
 }
 
 /**
- * may_access - verifies if a new exception is part of what is allowed
- *		by a dev cgroup based on the default policy +
- *		exceptions. This is used to make sure a child cgroup
- *		won't have more privileges than its parent or to
- *		verify if a certain access is allowed.
- * @dev_cgroup: dev cgroup to be tested against
- * @refex: new exception
- * @behavior: behavior of the exception
+ * match_exception	- iterates the exception list trying to find a complete match
+ * @exceptions: list of exceptions
+ * @type: device type (DEV_BLOCK or DEV_CHAR)
+ * @major: device file major number, ~0 to match all
+ * @minor: device file minor number, ~0 to match all
+ * @access: permission mask (ACC_READ, ACC_WRITE, ACC_MKNOD)
+ *
+ * It is considered a complete match if an exception is found that will
+ * contain the entire range of provided parameters.
+ *
+ * Return: true in case it matches an exception completely
  */
-static bool may_access(struct dev_cgroup *dev_cgroup,
-		       struct dev_exception_item *refex,
-		       enum devcg_behavior behavior)
+static bool match_exception(struct list_head *exceptions, short type,
+			    u32 major, u32 minor, short access)
 {
 	struct dev_exception_item *ex;
-	bool match = false;
 
-	rcu_lockdep_assert(rcu_read_lock_held() ||
-			   lockdep_is_held(&devcgroup_mutex),
-			   "device_cgroup::may_access() called without proper synchronization");
+	list_for_each_entry_rcu(ex, exceptions, list) {
+		if ((type & DEV_BLOCK) && !(ex->type & DEV_BLOCK))
+			continue;
+		if ((type & DEV_CHAR) && !(ex->type & DEV_CHAR))
+			continue;
+		if (ex->major != ~0 && ex->major != major)
+			continue;
+		if (ex->minor != ~0 && ex->minor != minor)
+			continue;
+		/* provided access cannot have more than the exception rule */
+		if (access & (~ex->access))
+			continue;
+		return true;
+	}
+	return false;
+}
+
+/**
+ * match_exception_partial - iterates the exception list trying to find a partial match
+ * @exceptions: list of exceptions
+ * @type: device type (DEV_BLOCK or DEV_CHAR)
+ * @major: device file major number, ~0 to match all
+ * @minor: device file minor number, ~0 to match all
+ * @access: permission mask (ACC_READ, ACC_WRITE, ACC_MKNOD)
+ *
+ * It is considered a partial match if an exception's range is found to
+ * contain *any* of the devices specified by provided parameters. This is
+ * used to make sure no extra access is being granted that is forbidden by
+ * any of the exception list.
+ *
+ * Return: true in case the provided range mat matches an exception completely
+ */
+static bool match_exception_partial(struct list_head *exceptions, short type,
+				    u32 major, u32 minor, short access)
+{
+	struct dev_exception_item *ex;
 
-	list_for_each_entry_rcu(ex, &dev_cgroup->exceptions, list) {
-		if ((refex->type & DEV_BLOCK) && !(ex->type & DEV_BLOCK))
+	list_for_each_entry_rcu(ex, exceptions, list) {
+		if ((type & DEV_BLOCK) && !(ex->type & DEV_BLOCK))
 			continue;
-		if ((refex->type & DEV_CHAR) && !(ex->type & DEV_CHAR))
+		if ((type & DEV_CHAR) && !(ex->type & DEV_CHAR))
 			continue;
-		if (ex->major != ~0 && ex->major != refex->major)
+		/*
+		 * We must be sure that both the exception and the provided
+		 * range aren't masking all devices
+		 */
+		if (ex->major != ~0 && major != ~0 && ex->major != major)
 			continue;
-		if (ex->minor != ~0 && ex->minor != refex->minor)
+		if (ex->minor != ~0 && minor != ~0 && ex->minor != minor)
 			continue;
-		if (refex->access & (~ex->access))
+		/*
+		 * In order to make sure the provided range isn't matching
+		 * an exception, all its access bits shouldn't match the
+		 * exception's access bits
+		 */
+		if (!(access & ex->access))
 			continue;
-		match = true;
-		break;
+		return true;
 	}
+	return false;
+}
+
+/**
+ * verify_new_ex - verifies if a new exception is allowed by parent cgroup's permissions
+ * @dev_cgroup: dev cgroup to be tested against
+ * @refex: new exception
+ * @behavior: behavior of the exception's dev_cgroup
+ *
+ * This is used to make sure a child cgroup won't have more privileges
+ * than its parent
+ */
+static bool verify_new_ex(struct dev_cgroup *dev_cgroup,
+		          struct dev_exception_item *refex,
+		          enum devcg_behavior behavior)
+{
+	bool match = false;
+
+	rcu_lockdep_assert(rcu_read_lock_held() ||
+			   lockdep_is_held(&devcgroup_mutex),
+			   "device_cgroup:verify_new_ex called without proper synchronization");
 
 	if (dev_cgroup->behavior == DEVCG_DEFAULT_ALLOW) {
 		if (behavior == DEVCG_DEFAULT_ALLOW) {
-			/* the exception will deny access to certain devices */
+			/*
+			 * new exception in the child doesn't matter, only
+			 * adding extra restrictions
+			 */ 
 			return true;
 		} else {
-			/* the exception will allow access to certain devices */
+			/*
+			 * new exception in the child will add more devices
+			 * that can be acessed, so it can't match any of
+			 * parent's exceptions, even slightly
+			 */ 
+			match = match_exception_partial(&dev_cgroup->exceptions,
+							refex->type,
+							refex->major,
+							refex->minor,
+							refex->access);
+
 			if (match)
-				/*
-				 * a new exception allowing access shouldn't
-				 * match an parent's exception
-				 */
 				return false;
 			return true;
 		}
 	} else {
-		/* only behavior == DEVCG_DEFAULT_DENY allowed here */
+		/*
+		 * Only behavior == DEVCG_DEFAULT_DENY allowed here, therefore
+		 * the new exception will add access to more devices and must
+		 * be contained completely in an parent's exception to be
+		 * allowed
+		 */
+		match = match_exception(&dev_cgroup->exceptions, refex->type,
+					refex->major, refex->minor,
+					refex->access);
+
 		if (match)
 			/* parent has an exception that matches the proposed */
 			return true;
@@ -378,7 +459,38 @@ static int parent_has_perm(struct dev_cgroup *childcg,
 
 	if (!parent)
 		return 1;
-	return may_access(parent, ex, childcg->behavior);
+	return verify_new_ex(parent, ex, childcg->behavior);
+}
+
+/**
+ * parent_allows_removal - verify if it's ok to remove an exception
+ * @childcg: child cgroup from where the exception will be removed
+ * @ex: exception being removed
+ *
+ * When removing an exception in cgroups with default ALLOW policy, it must
+ * be checked if removing it will give the child cgroup more access than the
+ * parent.
+ *
+ * Return: true if it's ok to remove exception, false otherwise
+ */
+static bool parent_allows_removal(struct dev_cgroup *childcg,
+				  struct dev_exception_item *ex)
+{
+	struct dev_cgroup *parent = css_to_devcgroup(css_parent(&childcg->css));
+
+	if (!parent)
+		return true;
+
+	/* It's always allowed to remove access to devices */
+	if (childcg->behavior == DEVCG_DEFAULT_DENY)
+		return true;
+
+	/*
+	 * Make sure you're not removing part or a whole exception existing in
+	 * the parent cgroup
+	 */
+	return !match_exception_partial(&parent->exceptions, ex->type,
+					ex->major, ex->minor, ex->access);
 }
 
 /**
@@ -616,17 +728,21 @@ static int devcgroup_update_access(struct dev_cgroup *devcgroup,
 
 	switch (filetype) {
 	case DEVCG_ALLOW:
-		if (!parent_has_perm(devcgroup, &ex))
-			return -EPERM;
 		/*
 		 * If the default policy is to allow by default, try to remove
 		 * an matching exception instead. And be silent about it: we
 		 * don't want to break compatibility
 		 */
 		if (devcgroup->behavior == DEVCG_DEFAULT_ALLOW) {
+			/* Check if the parent allows removing it first */
+			if (!parent_allows_removal(devcgroup, &ex))
+				return -EPERM;
 			dev_exception_rm(devcgroup, &ex);
-			return 0;
+			break;
 		}
+
+		if (!parent_has_perm(devcgroup, &ex))
+			return -EPERM;
 		rc = dev_exception_add(devcgroup, &ex);
 		break;
 	case DEVCG_DENY:
@@ -704,18 +820,18 @@ static int __devcgroup_check_permission(short type, u32 major, u32 minor,
 				        short access)
 {
 	struct dev_cgroup *dev_cgroup;
-	struct dev_exception_item ex;
-	int rc;
-
-	memset(&ex, 0, sizeof(ex));
-	ex.type = type;
-	ex.major = major;
-	ex.minor = minor;
-	ex.access = access;
+	bool rc;
 
 	rcu_read_lock();
 	dev_cgroup = task_devcgroup(current);
-	rc = may_access(dev_cgroup, &ex, dev_cgroup->behavior);
+	if (dev_cgroup->behavior == DEVCG_DEFAULT_ALLOW)
+		/* Can't match any of the exceptions, even partially */
+		rc = !match_exception_partial(&dev_cgroup->exceptions,
+					      type, major, minor, access);
+	else
+		/* Need to match completely one exception to be allowed */
+		rc = match_exception(&dev_cgroup->exceptions, type, major,
+				     minor, access);
 	rcu_read_unlock();
 
 	if (!rc)
diff --git a/sound/core/pcm_dmaengine.c b/sound/core/pcm_dmaengine.c
index 94d08733cb38..76cbb9ec953a 100644
--- a/sound/core/pcm_dmaengine.c
+++ b/sound/core/pcm_dmaengine.c
@@ -182,6 +182,7 @@ static int dmaengine_pcm_prepare_and_submit(struct snd_pcm_substream *substream)
 int snd_dmaengine_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 {
 	struct dmaengine_pcm_runtime_data *prtd = substream_to_prtd(substream);
+	struct snd_pcm_runtime *runtime = substream->runtime;
 	int ret;
 
 	switch (cmd) {
@@ -196,6 +197,11 @@ int snd_dmaengine_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 		dmaengine_resume(prtd->dma_chan);
 		break;
 	case SNDRV_PCM_TRIGGER_SUSPEND:
+		if (runtime->info & SNDRV_PCM_INFO_PAUSE)
+			dmaengine_pause(prtd->dma_chan);
+		else
+			dmaengine_terminate_all(prtd->dma_chan);
+		break;
 	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
 		dmaengine_pause(prtd->dma_chan);
 		break;
diff --git a/sound/isa/sb/sb_mixer.c b/sound/isa/sb/sb_mixer.c
index 6496822c1808..1ff78ec9f0ac 100644
--- a/sound/isa/sb/sb_mixer.c
+++ b/sound/isa/sb/sb_mixer.c
@@ -818,12 +818,14 @@ int snd_sbmixer_new(struct snd_sb *chip)
 			return err;
 		break;
 	case SB_HW_DT019X:
-		if ((err = snd_sbmixer_init(chip,
-					    snd_dt019x_controls,
-					    ARRAY_SIZE(snd_dt019x_controls),
-					    snd_dt019x_init_values,
-					    ARRAY_SIZE(snd_dt019x_init_values),
-					    "DT019X")) < 0)
+		err = snd_sbmixer_init(chip,
+				       snd_dt019x_controls,
+				       ARRAY_SIZE(snd_dt019x_controls),
+				       snd_dt019x_init_values,
+				       ARRAY_SIZE(snd_dt019x_init_values),
+				       "DT019X");
+		if (err < 0)
+			return err;
 		break;
 	default:
 		strcpy(card->mixername, "???");
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index b540ad71eb0d..6cc3cf285558 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -1367,6 +1367,12 @@ static int azx_first_init(struct azx *chip)
 	/* initialize streams */
 	azx_init_stream(chip);
 
+	/* workaround for Broadwell HDMI: the first stream is broken,
+	 * so mask it by keeping it as if opened
+	 */
+	if (pci->vendor == 0x8086 && pci->device == 0x160c)
+		chip->azx_dev[0].opened = 1;
+
 	/* initialize chip */
 	azx_init_pci(chip);
 	azx_init_chip(chip, (probe_only[dev] & 2) == 0);
@@ -1737,6 +1743,9 @@ static DEFINE_PCI_DEVICE_TABLE(azx_ids) = {
 	/* Lynx Point */
 	{ PCI_DEVICE(0x8086, 0x8c20),
 	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH },
+	/* 9 Series */
+	{ PCI_DEVICE(0x8086, 0x8ca0),
+	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH },
 	/* Wellsburg */
 	{ PCI_DEVICE(0x8086, 0x8d20),
 	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH },
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 0cb5b89cd0c8..b4218a19df22 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -1127,8 +1127,10 @@ static void hdmi_setup_audio_infoframe(struct hda_codec *codec,
 					    AMP_OUT_UNMUTE);
 
 	eld = &per_pin->sink_eld;
-	if (!eld->monitor_present)
+	if (!eld->monitor_present) {
+		hdmi_set_channel_count(codec, per_pin->cvt_nid, channels);
 		return;
+	}
 
 	if (!non_pcm && per_pin->chmap_set)
 		ca = hdmi_manual_channel_allocation(channels, per_pin->chmap);
@@ -3330,6 +3332,7 @@ static const struct hda_codec_preset snd_hda_preset_hdmi[] = {
 { .id = 0x10de0051, .name = "GPU 51 HDMI/DP",	.patch = patch_nvhdmi },
 { .id = 0x10de0060, .name = "GPU 60 HDMI/DP",	.patch = patch_nvhdmi },
 { .id = 0x10de0067, .name = "MCP67 HDMI",	.patch = patch_nvhdmi_2ch },
+{ .id = 0x10de0071, .name = "GPU 71 HDMI/DP",	.patch = patch_nvhdmi },
 { .id = 0x10de8001, .name = "MCP73 HDMI",	.patch = patch_nvhdmi_2ch },
 { .id = 0x11069f80, .name = "VX900 HDMI/DP",	.patch = patch_via_hdmi },
 { .id = 0x11069f81, .name = "VX900 HDMI/DP",	.patch = patch_via_hdmi },
@@ -3385,6 +3388,7 @@ MODULE_ALIAS("snd-hda-codec-id:10de0044");
 MODULE_ALIAS("snd-hda-codec-id:10de0051");
 MODULE_ALIAS("snd-hda-codec-id:10de0060");
 MODULE_ALIAS("snd-hda-codec-id:10de0067");
+MODULE_ALIAS("snd-hda-codec-id:10de0071");
 MODULE_ALIAS("snd-hda-codec-id:10de8001");
 MODULE_ALIAS("snd-hda-codec-id:11069f80");
 MODULE_ALIAS("snd-hda-codec-id:11069f81");
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index c1952c910339..49e884fb3e5d 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -4616,13 +4616,17 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x0653, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0657, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0658, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1028, 0x065c, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x065f, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0662, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0667, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0668, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0669, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0674, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1028, 0x067e, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x067f, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1028, 0x0680, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1028, 0x0684, "Dell", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x15cc, "Dell X5 Precision", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x15cd, "Dell X5 Precision", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2),
diff --git a/sound/soc/codecs/tlv320aic31xx.c b/sound/soc/codecs/tlv320aic31xx.c
index fa158cfe9b32..d1929de641e2 100644
--- a/sound/soc/codecs/tlv320aic31xx.c
+++ b/sound/soc/codecs/tlv320aic31xx.c
@@ -376,7 +376,7 @@ static int aic31xx_dapm_power_event(struct snd_soc_dapm_widget *w,
 		reg = AIC31XX_ADCFLAG;
 		break;
 	default:
-		dev_err(w->codec->dev, "Unknown widget '%s' calling %s/n",
+		dev_err(w->codec->dev, "Unknown widget '%s' calling %s\n",
 			w->name, __func__);
 		return -EINVAL;
 	}
diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c
index 5522d2566c67..ecd26dd2e442 100644
--- a/sound/soc/codecs/wm8962.c
+++ b/sound/soc/codecs/wm8962.c
@@ -154,6 +154,7 @@ static struct reg_default wm8962_reg[] = {
 	{ 40, 0x0000 },   /* R40    - SPKOUTL volume */
 	{ 41, 0x0000 },   /* R41    - SPKOUTR volume */
 
+	{ 49, 0x0010 },   /* R49    - Class D Control 1 */
 	{ 51, 0x0003 },   /* R51    - Class D Control 2 */
 
 	{ 56, 0x0506 },   /* R56    - Clocking 4 */
@@ -795,7 +796,6 @@ static bool wm8962_volatile_register(struct device *dev, unsigned int reg)
 	case WM8962_ALC2:
 	case WM8962_THERMAL_SHUTDOWN_STATUS:
 	case WM8962_ADDITIONAL_CONTROL_4:
-	case WM8962_CLASS_D_CONTROL_1:
 	case WM8962_DC_SERVO_6:
 	case WM8962_INTERRUPT_STATUS_1:
 	case WM8962_INTERRUPT_STATUS_2:
@@ -2929,13 +2929,22 @@ static int wm8962_set_fll(struct snd_soc_codec *codec, int fll_id, int source,
 static int wm8962_mute(struct snd_soc_dai *dai, int mute)
 {
 	struct snd_soc_codec *codec = dai->codec;
-	int val;
+	int val, ret;
 
 	if (mute)
-		val = WM8962_DAC_MUTE;
+		val = WM8962_DAC_MUTE | WM8962_DAC_MUTE_ALT;
 	else
 		val = 0;
 
+	/**
+	 * The DAC mute bit is mirrored in two registers, update both to keep
+	 * the register cache consistent.
+	 */
+	ret = snd_soc_update_bits(codec, WM8962_CLASS_D_CONTROL_1,
+				  WM8962_DAC_MUTE_ALT, val);
+	if (ret < 0)
+		return ret;
+
 	return snd_soc_update_bits(codec, WM8962_ADC_DAC_CONTROL_1,
 				   WM8962_DAC_MUTE, val);
 }
diff --git a/sound/soc/codecs/wm8962.h b/sound/soc/codecs/wm8962.h
index a1a5d5294c19..910aafd09d21 100644
--- a/sound/soc/codecs/wm8962.h
+++ b/sound/soc/codecs/wm8962.h
@@ -1954,6 +1954,10 @@
 #define WM8962_SPKOUTL_ENA_MASK                 0x0040  /* SPKOUTL_ENA */
 #define WM8962_SPKOUTL_ENA_SHIFT                     6  /* SPKOUTL_ENA */
 #define WM8962_SPKOUTL_ENA_WIDTH                     1  /* SPKOUTL_ENA */
+#define WM8962_DAC_MUTE_ALT                     0x0010  /* DAC_MUTE */
+#define WM8962_DAC_MUTE_ALT_MASK                0x0010  /* DAC_MUTE */
+#define WM8962_DAC_MUTE_ALT_SHIFT                    4  /* DAC_MUTE */
+#define WM8962_DAC_MUTE_ALT_WIDTH                    1  /* DAC_MUTE */
 #define WM8962_SPKOUTL_PGA_MUTE                 0x0002  /* SPKOUTL_PGA_MUTE */
 #define WM8962_SPKOUTL_PGA_MUTE_MASK            0x0002  /* SPKOUTL_PGA_MUTE */
 #define WM8962_SPKOUTL_PGA_MUTE_SHIFT                1  /* SPKOUTL_PGA_MUTE */
diff --git a/sound/soc/fsl/fsl_esai.c b/sound/soc/fsl/fsl_esai.c
index c8e5db1414d7..496ce2eb2f1f 100644
--- a/sound/soc/fsl/fsl_esai.c
+++ b/sound/soc/fsl/fsl_esai.c
@@ -258,10 +258,16 @@ static int fsl_esai_set_dai_sysclk(struct snd_soc_dai *dai, int clk_id,
 		return -EINVAL;
 	}
 
-	if (ratio == 1) {
+	/* Only EXTAL source can be output directly without using PSR and PM */
+	if (ratio == 1 && clksrc == esai_priv->extalclk) {
 		/* Bypass all the dividers if not being needed */
 		ecr |= tx ? ESAI_ECR_ETO : ESAI_ECR_ERO;
 		goto out;
+	} else if (ratio < 2) {
+		/* The ratio should be no less than 2 if using other sources */
+		dev_err(dai->dev, "failed to derive required HCK%c rate\n",
+				tx ? 'T' : 'R');
+		return -EINVAL;
 	}
 
 	ret = fsl_esai_divisor_cal(dai, tx, ratio, false, 0);
@@ -307,7 +313,8 @@ static int fsl_esai_set_bclk(struct snd_soc_dai *dai, bool tx, u32 freq)
 		return -EINVAL;
 	}
 
-	if (esai_priv->sck_div[tx] && (ratio > 16 || ratio == 0)) {
+	/* The ratio should be contented by FP alone if bypassing PM and PSR */
+	if (!esai_priv->sck_div[tx] && (ratio > 16 || ratio == 0)) {
 		dev_err(dai->dev, "the ratio is out of range (1 ~ 16)\n");
 		return -EINVAL;
 	}
@@ -454,12 +461,6 @@ static int fsl_esai_startup(struct snd_pcm_substream *substream,
 	}
 
 	if (!dai->active) {
-		/* Reset Port C */
-		regmap_update_bits(esai_priv->regmap, REG_ESAI_PRRC,
-				   ESAI_PRRC_PDC_MASK, ESAI_PRRC_PDC(ESAI_GPIO));
-		regmap_update_bits(esai_priv->regmap, REG_ESAI_PCRC,
-				   ESAI_PCRC_PC_MASK, ESAI_PCRC_PC(ESAI_GPIO));
-
 		/* Set synchronous mode */
 		regmap_update_bits(esai_priv->regmap, REG_ESAI_SAICR,
 				   ESAI_SAICR_SYNC, esai_priv->synchronous ?
@@ -519,6 +520,11 @@ static int fsl_esai_hw_params(struct snd_pcm_substream *substream,
 
 	regmap_update_bits(esai_priv->regmap, REG_ESAI_xCR(tx), mask, val);
 
+	/* Remove ESAI personal reset by configuring ESAI_PCRC and ESAI_PRRC */
+	regmap_update_bits(esai_priv->regmap, REG_ESAI_PRRC,
+			   ESAI_PRRC_PDC_MASK, ESAI_PRRC_PDC(ESAI_GPIO));
+	regmap_update_bits(esai_priv->regmap, REG_ESAI_PCRC,
+			   ESAI_PCRC_PC_MASK, ESAI_PCRC_PC(ESAI_GPIO));
 	return 0;
 }
 
diff --git a/sound/soc/fsl/imx-audmux.c b/sound/soc/fsl/imx-audmux.c
index ac869931d7f1..267717aa96c1 100644
--- a/sound/soc/fsl/imx-audmux.c
+++ b/sound/soc/fsl/imx-audmux.c
@@ -145,7 +145,7 @@ static const struct file_operations audmux_debugfs_fops = {
 	.llseek = default_llseek,
 };
 
-static void __init audmux_debugfs_init(void)
+static void audmux_debugfs_init(void)
 {
 	int i;
 	char buf[20];
diff --git a/sound/soc/intel/sst-acpi.c b/sound/soc/intel/sst-acpi.c
index 5d06eecb6198..18aee77f8d4a 100644
--- a/sound/soc/intel/sst-acpi.c
+++ b/sound/soc/intel/sst-acpi.c
@@ -138,6 +138,7 @@ static int sst_acpi_probe(struct platform_device *pdev)
 
 	sst_pdata = &sst_acpi->sst_pdata;
 	sst_pdata->id = desc->sst_id;
+	sst_pdata->dma_dev = dev;
 	sst_acpi->desc = desc;
 	sst_acpi->mach = mach;
 
diff --git a/sound/soc/intel/sst-baytrail-dsp.c b/sound/soc/intel/sst-baytrail-dsp.c
index a50bf7fc0e3a..adf0aca5aca6 100644
--- a/sound/soc/intel/sst-baytrail-dsp.c
+++ b/sound/soc/intel/sst-baytrail-dsp.c
@@ -324,7 +324,7 @@ static int sst_byt_init(struct sst_dsp *sst, struct sst_pdata *pdata)
 	memcpy_toio(sst->addr.lpe + SST_BYT_MAILBOX_OFFSET,
 	       &pdata->fw_base, sizeof(u32));
 
-	ret = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(32));
+	ret = dma_coerce_mask_and_coherent(sst->dma_dev, DMA_BIT_MASK(32));
 	if (ret)
 		return ret;
 
diff --git a/sound/soc/intel/sst-baytrail-ipc.c b/sound/soc/intel/sst-baytrail-ipc.c
index d0eaeee21be4..0d31dbbf4806 100644
--- a/sound/soc/intel/sst-baytrail-ipc.c
+++ b/sound/soc/intel/sst-baytrail-ipc.c
@@ -542,16 +542,20 @@ struct sst_byt_stream *sst_byt_stream_new(struct sst_byt *byt, int id,
 	void *data)
 {
 	struct sst_byt_stream *stream;
+	struct sst_dsp *sst = byt->dsp;
+	unsigned long flags;
 
 	stream = kzalloc(sizeof(*stream), GFP_KERNEL);
 	if (stream == NULL)
 		return NULL;
 
+	spin_lock_irqsave(&sst->spinlock, flags);
 	list_add(&stream->node, &byt->stream_list);
 	stream->notify_position = notify_position;
 	stream->pdata = data;
 	stream->byt = byt;
 	stream->str_id = id;
+	spin_unlock_irqrestore(&sst->spinlock, flags);
 
 	return stream;
 }
@@ -630,6 +634,8 @@ int sst_byt_stream_free(struct sst_byt *byt, struct sst_byt_stream *stream)
 {
 	u64 header;
 	int ret = 0;
+	struct sst_dsp *sst = byt->dsp;
+	unsigned long flags;
 
 	if (!stream->commited)
 		goto out;
@@ -644,8 +650,10 @@ int sst_byt_stream_free(struct sst_byt *byt, struct sst_byt_stream *stream)
 
 	stream->commited = false;
 out:
+	spin_lock_irqsave(&sst->spinlock, flags);
 	list_del(&stream->node);
 	kfree(stream);
+	spin_unlock_irqrestore(&sst->spinlock, flags);
 
 	return ret;
 }
diff --git a/sound/soc/intel/sst-dsp-priv.h b/sound/soc/intel/sst-dsp-priv.h
index 30ca14a6a835..401213455497 100644
--- a/sound/soc/intel/sst-dsp-priv.h
+++ b/sound/soc/intel/sst-dsp-priv.h
@@ -228,6 +228,7 @@ struct sst_dsp {
 	spinlock_t spinlock;	/* IPC locking */
 	struct mutex mutex;	/* DSP FW lock */
 	struct device *dev;
+	struct device *dma_dev;
 	void *thread_context;
 	int irq;
 	u32 id;
diff --git a/sound/soc/intel/sst-dsp.c b/sound/soc/intel/sst-dsp.c
index 0c129fd85ecf..0b715b20a2d7 100644
--- a/sound/soc/intel/sst-dsp.c
+++ b/sound/soc/intel/sst-dsp.c
@@ -337,6 +337,7 @@ struct sst_dsp *sst_dsp_new(struct device *dev,
 	spin_lock_init(&sst->spinlock);
 	mutex_init(&sst->mutex);
 	sst->dev = dev;
+	sst->dma_dev = pdata->dma_dev;
 	sst->thread_context = sst_dev->thread_context;
 	sst->sst_dev = sst_dev;
 	sst->id = pdata->id;
diff --git a/sound/soc/intel/sst-dsp.h b/sound/soc/intel/sst-dsp.h
index 74052b59485c..e44423be66c4 100644
--- a/sound/soc/intel/sst-dsp.h
+++ b/sound/soc/intel/sst-dsp.h
@@ -169,6 +169,7 @@ struct sst_pdata {
 	u32 dma_base;
 	u32 dma_size;
 	int dma_engine;
+	struct device *dma_dev;
 
 	/* DSP */
 	u32 id;
diff --git a/sound/soc/intel/sst-firmware.c b/sound/soc/intel/sst-firmware.c
index f7687107cf7f..928f228c38e7 100644
--- a/sound/soc/intel/sst-firmware.c
+++ b/sound/soc/intel/sst-firmware.c
@@ -57,14 +57,8 @@ struct sst_fw *sst_fw_new(struct sst_dsp *dsp,
 	sst_fw->private = private;
 	sst_fw->size = fw->size;
 
-	err = dma_coerce_mask_and_coherent(dsp->dev, DMA_BIT_MASK(32));
-	if (err < 0) {
-		kfree(sst_fw);
-		return NULL;
-	}
-
 	/* allocate DMA buffer to store FW data */
-	sst_fw->dma_buf = dma_alloc_coherent(dsp->dev, sst_fw->size,
+	sst_fw->dma_buf = dma_alloc_coherent(dsp->dma_dev, sst_fw->size,
 				&sst_fw->dmable_fw_paddr, GFP_DMA | GFP_KERNEL);
 	if (!sst_fw->dma_buf) {
 		dev_err(dsp->dev, "error: DMA alloc failed\n");
@@ -106,7 +100,7 @@ void sst_fw_free(struct sst_fw *sst_fw)
 	list_del(&sst_fw->list);
 	mutex_unlock(&dsp->mutex);
 
-	dma_free_coherent(dsp->dev, sst_fw->size, sst_fw->dma_buf,
+	dma_free_coherent(dsp->dma_dev, sst_fw->size, sst_fw->dma_buf,
 			sst_fw->dmable_fw_paddr);
 	kfree(sst_fw);
 }
@@ -202,6 +196,9 @@ static int block_alloc_contiguous(struct sst_module *module,
 		size -= block->size;
 	}
 
+	list_for_each_entry(block, &tmp, list)
+		list_add(&block->module_list, &module->block_list);
+
 	list_splice(&tmp, &dsp->used_block_list);
 	return 0;
 }
@@ -247,8 +244,7 @@ static int block_alloc(struct sst_module *module,
 		/* do we span > 1 blocks */
 		if (data->size > block->size) {
 			ret = block_alloc_contiguous(module, data,
-				block->offset + block->size,
-				data->size - block->size);
+				block->offset, data->size);
 			if (ret == 0)
 				return ret;
 		}
@@ -344,7 +340,7 @@ static int block_alloc_fixed(struct sst_module *module,
 
 			err = block_alloc_contiguous(module, data,
 				block->offset + block->size,
-				data->size - block->size + data->offset - block->offset);
+				data->size - block->size);
 			if (err < 0)
 				return -ENOMEM;
 
@@ -371,15 +367,10 @@ static int block_alloc_fixed(struct sst_module *module,
 		if (data->offset >= block->offset && data->offset < block_end) {
 
 			err = block_alloc_contiguous(module, data,
-				block->offset + block->size,
-				data->size - block->size);
+				block->offset, data->size);
 			if (err < 0)
 				return -ENOMEM;
 
-			/* add block */
-			block->data_type = data->data_type;
-			list_move(&block->list, &dsp->used_block_list);
-			list_add(&block->module_list, &module->block_list);
 			return 0;
 		}
 
diff --git a/sound/soc/intel/sst-haswell-dsp.c b/sound/soc/intel/sst-haswell-dsp.c
index f5ebf36af889..535f517629fd 100644
--- a/sound/soc/intel/sst-haswell-dsp.c
+++ b/sound/soc/intel/sst-haswell-dsp.c
@@ -433,7 +433,7 @@ static int hsw_init(struct sst_dsp *sst, struct sst_pdata *pdata)
 	int ret = -ENODEV, i, j, region_count;
 	u32 offset, size;
 
-	dev = sst->dev;
+	dev = sst->dma_dev;
 
 	switch (sst->id) {
 	case SST_DEV_ID_LYNX_POINT:
@@ -466,7 +466,7 @@ static int hsw_init(struct sst_dsp *sst, struct sst_pdata *pdata)
 		return ret;
 	}
 
-	ret = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(32));
+	ret = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(31));
 	if (ret)
 		return ret;
 
diff --git a/sound/soc/intel/sst-haswell-ipc.c b/sound/soc/intel/sst-haswell-ipc.c
index 50e4246d4b57..e7996b39a484 100644
--- a/sound/soc/intel/sst-haswell-ipc.c
+++ b/sound/soc/intel/sst-haswell-ipc.c
@@ -1159,11 +1159,14 @@ struct sst_hsw_stream *sst_hsw_stream_new(struct sst_hsw *hsw, int id,
 	void *data)
 {
 	struct sst_hsw_stream *stream;
+	struct sst_dsp *sst = hsw->dsp;
+	unsigned long flags;
 
 	stream = kzalloc(sizeof(*stream), GFP_KERNEL);
 	if (stream == NULL)
 		return NULL;
 
+	spin_lock_irqsave(&sst->spinlock, flags);
 	list_add(&stream->node, &hsw->stream_list);
 	stream->notify_position = notify_position;
 	stream->pdata = data;
@@ -1172,6 +1175,7 @@ struct sst_hsw_stream *sst_hsw_stream_new(struct sst_hsw *hsw, int id,
 
 	/* work to process notification messages */
 	INIT_WORK(&stream->notify_work, hsw_notification_work);
+	spin_unlock_irqrestore(&sst->spinlock, flags);
 
 	return stream;
 }
@@ -1180,6 +1184,8 @@ int sst_hsw_stream_free(struct sst_hsw *hsw, struct sst_hsw_stream *stream)
 {
 	u32 header;
 	int ret = 0;
+	struct sst_dsp *sst = hsw->dsp;
+	unsigned long flags;
 
 	/* dont free DSP streams that are not commited */
 	if (!stream->commited)
@@ -1201,8 +1207,11 @@ int sst_hsw_stream_free(struct sst_hsw *hsw, struct sst_hsw_stream *stream)
 	trace_hsw_stream_free_req(stream, &stream->free_req);
 
 out:
+	cancel_work_sync(&stream->notify_work);
+	spin_lock_irqsave(&sst->spinlock, flags);
 	list_del(&stream->node);
 	kfree(stream);
+	spin_unlock_irqrestore(&sst->spinlock, flags);
 
 	return ret;
 }
@@ -1538,10 +1547,28 @@ int sst_hsw_stream_reset(struct sst_hsw *hsw, struct sst_hsw_stream *stream)
 }
 
 /* Stream pointer positions */
-int sst_hsw_get_dsp_position(struct sst_hsw *hsw,
+u32 sst_hsw_get_dsp_position(struct sst_hsw *hsw,
 	struct sst_hsw_stream *stream)
 {
-	return stream->rpos.position;
+	u32 rpos;
+
+	sst_dsp_read(hsw->dsp, &rpos,
+		stream->reply.read_position_register_address, sizeof(rpos));
+
+	return rpos;
+}
+
+/* Stream presentation (monotonic) positions */
+u64 sst_hsw_get_dsp_presentation_position(struct sst_hsw *hsw,
+	struct sst_hsw_stream *stream)
+{
+	u64 ppos;
+
+	sst_dsp_read(hsw->dsp, &ppos,
+		stream->reply.presentation_position_register_address,
+		sizeof(ppos));
+
+	return ppos;
 }
 
 int sst_hsw_stream_set_write_position(struct sst_hsw *hsw,
diff --git a/sound/soc/intel/sst-haswell-ipc.h b/sound/soc/intel/sst-haswell-ipc.h
index d517929ccc38..2ac194a6d04b 100644
--- a/sound/soc/intel/sst-haswell-ipc.h
+++ b/sound/soc/intel/sst-haswell-ipc.h
@@ -464,7 +464,9 @@ int sst_hsw_stream_get_write_pos(struct sst_hsw *hsw,
 	struct sst_hsw_stream *stream, u32 *position);
 int sst_hsw_stream_set_write_position(struct sst_hsw *hsw,
 	struct sst_hsw_stream *stream, u32 stage_id, u32 position);
-int sst_hsw_get_dsp_position(struct sst_hsw *hsw,
+u32 sst_hsw_get_dsp_position(struct sst_hsw *hsw,
+	struct sst_hsw_stream *stream);
+u64 sst_hsw_get_dsp_presentation_position(struct sst_hsw *hsw,
 	struct sst_hsw_stream *stream);
 
 /* HW port config */
diff --git a/sound/soc/intel/sst-haswell-pcm.c b/sound/soc/intel/sst-haswell-pcm.c
index 0a32dd13a23d..9d5f64a583a3 100644
--- a/sound/soc/intel/sst-haswell-pcm.c
+++ b/sound/soc/intel/sst-haswell-pcm.c
@@ -99,6 +99,7 @@ struct hsw_pcm_data {
 	struct snd_compr_stream *cstream;
 	unsigned int wpos;
 	struct mutex mutex;
+	bool allocated;
 };
 
 /* private data for the driver */
@@ -107,12 +108,14 @@ struct hsw_priv_data {
 	struct sst_hsw *hsw;
 
 	/* page tables */
-	unsigned char *pcm_pg[HSW_PCM_COUNT][2];
+	struct snd_dma_buffer dmab[HSW_PCM_COUNT][2];
 
 	/* DAI data */
 	struct hsw_pcm_data pcm[HSW_PCM_COUNT];
 };
 
+static u32 hsw_notify_pointer(struct sst_hsw_stream *stream, void *data);
+
 static inline u32 hsw_mixer_to_ipc(unsigned int value)
 {
 	if (value >= ARRAY_SIZE(volume_map))
@@ -273,28 +276,26 @@ static const struct snd_kcontrol_new hsw_volume_controls[] = {
 };
 
 /* Create DMA buffer page table for DSP */
-static int create_adsp_page_table(struct hsw_priv_data *pdata,
-	struct snd_soc_pcm_runtime *rtd,
-	unsigned char *dma_area, size_t size, int pcm, int stream)
+static int create_adsp_page_table(struct snd_pcm_substream *substream,
+	struct hsw_priv_data *pdata, struct snd_soc_pcm_runtime *rtd,
+	unsigned char *dma_area, size_t size, int pcm)
 {
-	int i, pages;
+	struct snd_dma_buffer *dmab = snd_pcm_get_dma_buf(substream);
+	int i, pages, stream = substream->stream;
 
-	if (size % PAGE_SIZE)
-		pages = (size / PAGE_SIZE) + 1;
-	else
-		pages = size / PAGE_SIZE;
+	pages = snd_sgbuf_aligned_pages(size);
 
 	dev_dbg(rtd->dev, "generating page table for %p size 0x%zu pages %d\n",
 		dma_area, size, pages);
 
 	for (i = 0; i < pages; i++) {
 		u32 idx = (((i << 2) + i)) >> 1;
-		u32 pfn = (virt_to_phys(dma_area + i * PAGE_SIZE)) >> PAGE_SHIFT;
+		u32 pfn = snd_sgbuf_get_addr(dmab, i * PAGE_SIZE) >> PAGE_SHIFT;
 		u32 *pg_table;
 
 		dev_dbg(rtd->dev, "pfn i %i idx %d pfn %x\n", i, idx, pfn);
 
-		pg_table = (u32*)(pdata->pcm_pg[pcm][stream] + idx);
+		pg_table = (u32 *)(pdata->dmab[pcm][stream].area + idx);
 
 		if (i & 1)
 			*pg_table |= (pfn << 4);
@@ -317,12 +318,36 @@ static int hsw_pcm_hw_params(struct snd_pcm_substream *substream,
 	struct sst_hsw *hsw = pdata->hsw;
 	struct sst_module *module_data;
 	struct sst_dsp *dsp;
+	struct snd_dma_buffer *dmab;
 	enum sst_hsw_stream_type stream_type;
 	enum sst_hsw_stream_path_id path_id;
 	u32 rate, bits, map, pages, module_id;
 	u8 channels;
 	int ret;
 
+	/* check if we are being called a subsequent time */
+	if (pcm_data->allocated) {
+		ret = sst_hsw_stream_reset(hsw, pcm_data->stream);
+		if (ret < 0)
+			dev_dbg(rtd->dev, "error: reset stream failed %d\n",
+				ret);
+
+		ret = sst_hsw_stream_free(hsw, pcm_data->stream);
+		if (ret < 0) {
+			dev_dbg(rtd->dev, "error: free stream failed %d\n",
+				ret);
+			return ret;
+		}
+		pcm_data->allocated = false;
+
+		pcm_data->stream = sst_hsw_stream_new(hsw, rtd->cpu_dai->id,
+			hsw_notify_pointer, pcm_data);
+		if (pcm_data->stream == NULL) {
+			dev_err(rtd->dev, "error: failed to create stream\n");
+			return -EINVAL;
+		}
+	}
+
 	/* stream direction */
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
 		path_id = SST_HSW_STREAM_PATH_SSP0_OUT;
@@ -416,8 +441,10 @@ static int hsw_pcm_hw_params(struct snd_pcm_substream *substream,
 		return ret;
 	}
 
-	ret = create_adsp_page_table(pdata, rtd, runtime->dma_area,
-		runtime->dma_bytes, rtd->cpu_dai->id, substream->stream);
+	dmab = snd_pcm_get_dma_buf(substream);
+
+	ret = create_adsp_page_table(substream, pdata, rtd, runtime->dma_area,
+		runtime->dma_bytes, rtd->cpu_dai->id);
 	if (ret < 0)
 		return ret;
 
@@ -430,9 +457,9 @@ static int hsw_pcm_hw_params(struct snd_pcm_substream *substream,
 		pages = runtime->dma_bytes / PAGE_SIZE;
 
 	ret = sst_hsw_stream_buffer(hsw, pcm_data->stream,
-		virt_to_phys(pdata->pcm_pg[rtd->cpu_dai->id][substream->stream]),
+		pdata->dmab[rtd->cpu_dai->id][substream->stream].addr,
 		pages, runtime->dma_bytes, 0,
-		(u32)(virt_to_phys(runtime->dma_area) >> PAGE_SHIFT));
+		snd_sgbuf_get_addr(dmab, 0) >> PAGE_SHIFT);
 	if (ret < 0) {
 		dev_err(rtd->dev, "error: failed to set DMA buffer %d\n", ret);
 		return ret;
@@ -474,6 +501,7 @@ static int hsw_pcm_hw_params(struct snd_pcm_substream *substream,
 		dev_err(rtd->dev, "error: failed to commit stream %d\n", ret);
 		return ret;
 	}
+	pcm_data->allocated = true;
 
 	ret = sst_hsw_stream_pause(hsw, pcm_data->stream, 1);
 	if (ret < 0)
@@ -541,12 +569,14 @@ static snd_pcm_uframes_t hsw_pcm_pointer(struct snd_pcm_substream *substream)
 	struct hsw_pcm_data *pcm_data = snd_soc_pcm_get_drvdata(rtd);
 	struct sst_hsw *hsw = pdata->hsw;
 	snd_pcm_uframes_t offset;
+	uint64_t ppos;
+	u32 position = sst_hsw_get_dsp_position(hsw, pcm_data->stream);
 
-	offset = bytes_to_frames(runtime,
-		sst_hsw_get_dsp_position(hsw, pcm_data->stream));
+	offset = bytes_to_frames(runtime, position);
+	ppos = sst_hsw_get_dsp_presentation_position(hsw, pcm_data->stream);
 
-	dev_dbg(rtd->dev, "PCM: DMA pointer %zu bytes\n",
-		frames_to_bytes(runtime, (u32)offset));
+	dev_dbg(rtd->dev, "PCM: DMA pointer %du bytes, pos %llu\n",
+		position, ppos);
 	return offset;
 }
 
@@ -606,6 +636,7 @@ static int hsw_pcm_close(struct snd_pcm_substream *substream)
 		dev_dbg(rtd->dev, "error: free stream failed %d\n", ret);
 		goto out;
 	}
+	pcm_data->allocated = 0;
 	pcm_data->stream = NULL;
 
 out:
@@ -621,7 +652,7 @@ static struct snd_pcm_ops hsw_pcm_ops = {
 	.hw_free	= hsw_pcm_hw_free,
 	.trigger	= hsw_pcm_trigger,
 	.pointer	= hsw_pcm_pointer,
-	.mmap		= snd_pcm_lib_default_mmap,
+	.page		= snd_pcm_sgbuf_ops_page,
 };
 
 static void hsw_pcm_free(struct snd_pcm *pcm)
@@ -632,17 +663,16 @@ static void hsw_pcm_free(struct snd_pcm *pcm)
 static int hsw_pcm_new(struct snd_soc_pcm_runtime *rtd)
 {
 	struct snd_pcm *pcm = rtd->pcm;
+	struct snd_soc_platform *platform = rtd->platform;
+	struct sst_pdata *pdata = dev_get_platdata(platform->dev);
+	struct device *dev = pdata->dma_dev;
 	int ret = 0;
 
-	ret = dma_coerce_mask_and_coherent(rtd->card->dev, DMA_BIT_MASK(32));
-	if (ret)
-		return ret;
-
 	if (pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream ||
 			pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream) {
 		ret = snd_pcm_lib_preallocate_pages_for_all(pcm,
-			SNDRV_DMA_TYPE_DEV,
-			rtd->card->dev,
+			SNDRV_DMA_TYPE_DEV_SG,
+			dev,
 			hsw_pcm_hardware.buffer_bytes_max,
 			hsw_pcm_hardware.buffer_bytes_max);
 		if (ret) {
@@ -742,11 +772,14 @@ static int hsw_pcm_probe(struct snd_soc_platform *platform)
 {
 	struct sst_pdata *pdata = dev_get_platdata(platform->dev);
 	struct hsw_priv_data *priv_data;
-	int i;
+	struct device *dma_dev;
+	int i, ret = 0;
 
 	if (!pdata)
 		return -ENODEV;
 
+	dma_dev = pdata->dma_dev;
+
 	priv_data = devm_kzalloc(platform->dev, sizeof(*priv_data), GFP_KERNEL);
 	priv_data->hsw = pdata->dsp;
 	snd_soc_platform_set_drvdata(platform, priv_data);
@@ -758,15 +791,17 @@ static int hsw_pcm_probe(struct snd_soc_platform *platform)
 
 		/* playback */
 		if (hsw_dais[i].playback.channels_min) {
-			priv_data->pcm_pg[i][0] = kzalloc(PAGE_SIZE, GFP_DMA);
-			if (priv_data->pcm_pg[i][0] == NULL)
+			ret = snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, dma_dev,
+				PAGE_SIZE, &priv_data->dmab[i][0]);
+			if (ret < 0)
 				goto err;
 		}
 
 		/* capture */
 		if (hsw_dais[i].capture.channels_min) {
-			priv_data->pcm_pg[i][1] = kzalloc(PAGE_SIZE, GFP_DMA);
-			if (priv_data->pcm_pg[i][1] == NULL)
+			ret = snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, dma_dev,
+				PAGE_SIZE, &priv_data->dmab[i][1]);
+			if (ret < 0)
 				goto err;
 		}
 	}
@@ -776,11 +811,11 @@ static int hsw_pcm_probe(struct snd_soc_platform *platform)
 err:
 	for (;i >= 0; i--) {
 		if (hsw_dais[i].playback.channels_min)
-			kfree(priv_data->pcm_pg[i][0]);
+			snd_dma_free_pages(&priv_data->dmab[i][0]);
 		if (hsw_dais[i].capture.channels_min)
-			kfree(priv_data->pcm_pg[i][1]);
+			snd_dma_free_pages(&priv_data->dmab[i][1]);
 	}
-	return -ENOMEM;
+	return ret;
 }
 
 static int hsw_pcm_remove(struct snd_soc_platform *platform)
@@ -791,9 +826,9 @@ static int hsw_pcm_remove(struct snd_soc_platform *platform)
 
 	for (i = 0; i < ARRAY_SIZE(hsw_dais); i++) {
 		if (hsw_dais[i].playback.channels_min)
-			kfree(priv_data->pcm_pg[i][0]);
+			snd_dma_free_pages(&priv_data->dmab[i][0]);
 		if (hsw_dais[i].capture.channels_min)
-			kfree(priv_data->pcm_pg[i][1]);
+			snd_dma_free_pages(&priv_data->dmab[i][1]);
 	}
 
 	return 0;
diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c
index 215b668166be..89424470a1f3 100644
--- a/sound/soc/sh/rcar/core.c
+++ b/sound/soc/sh/rcar/core.c
@@ -197,13 +197,12 @@ static void rsnd_dma_complete(void *data)
 	 * rsnd_dai_pointer_update() will be called twice,
 	 * ant it will breaks io->byte_pos
 	 */
-
-	rsnd_dai_pointer_update(io, io->byte_per_period);
-
 	if (dma->submit_loop)
 		rsnd_dma_continue(dma);
 
 	rsnd_unlock(priv, flags);
+
+	rsnd_dai_pointer_update(io, io->byte_per_period);
 }
 
 static void __rsnd_dma_start(struct rsnd_dma *dma)
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 7769b0a2bc5a..6d6ceee447d5 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -1612,8 +1612,11 @@ static void dapm_pre_sequence_async(void *data, async_cookie_t cookie)
 				"ASoC: Failed to turn on bias: %d\n", ret);
 	}
 
-	/* Prepare for a STADDBY->ON or ON->STANDBY transition */
-	if (d->bias_level != d->target_bias_level) {
+	/* Prepare for a transition to ON or away from ON */
+	if ((d->target_bias_level == SND_SOC_BIAS_ON &&
+	     d->bias_level != SND_SOC_BIAS_ON) ||
+	    (d->target_bias_level != SND_SOC_BIAS_ON &&
+	     d->bias_level == SND_SOC_BIAS_ON)) {
 		ret = snd_soc_dapm_set_bias_level(d, SND_SOC_BIAS_PREPARE);
 		if (ret != 0)
 			dev_err(d->dev,
@@ -3475,8 +3478,11 @@ void snd_soc_dapm_connect_dai_link_widgets(struct snd_soc_card *card)
 		cpu_dai = rtd->cpu_dai;
 		codec_dai = rtd->codec_dai;
 
-		/* dynamic FE links have no fixed DAI mapping */
-		if (rtd->dai_link->dynamic)
+		/*
+		 * dynamic FE links have no fixed DAI mapping.
+		 * CODEC<->CODEC links have no direct connection.
+		 */
+		if (rtd->dai_link->dynamic || rtd->dai_link->params)
 			continue;
 
 		/* there is no point in connecting BE DAI links with dummies */
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 2cedf09f6d96..a391de058037 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -1675,7 +1675,7 @@ int dpcm_be_dai_trigger(struct snd_soc_pcm_runtime *fe, int stream,
 			be->dpcm[stream].state = SND_SOC_DPCM_STATE_STOP;
 			break;
 		case SNDRV_PCM_TRIGGER_SUSPEND:
-			if (be->dpcm[stream].state != SND_SOC_DPCM_STATE_STOP)
+			if (be->dpcm[stream].state != SND_SOC_DPCM_STATE_START)
 				continue;
 
 			if (!snd_soc_dpcm_can_be_free_stop(fe, be, stream))
diff --git a/sound/usb/card.c b/sound/usb/card.c
index 893d5a1afc3c..c3b5b7dca1c3 100644
--- a/sound/usb/card.c
+++ b/sound/usb/card.c
@@ -651,7 +651,7 @@ int snd_usb_autoresume(struct snd_usb_audio *chip)
 	int err = -ENODEV;
 
 	down_read(&chip->shutdown_rwsem);
-	if (chip->probing)
+	if (chip->probing && chip->in_pm)
 		err = 0;
 	else if (!chip->shutdown)
 		err = usb_autopm_get_interface(chip->pm_intf);
@@ -663,7 +663,7 @@ int snd_usb_autoresume(struct snd_usb_audio *chip)
 void snd_usb_autosuspend(struct snd_usb_audio *chip)
 {
 	down_read(&chip->shutdown_rwsem);
-	if (!chip->shutdown && !chip->probing)
+	if (!chip->shutdown && !chip->probing && !chip->in_pm)
 		usb_autopm_put_interface(chip->pm_intf);
 	up_read(&chip->shutdown_rwsem);
 }
@@ -695,8 +695,9 @@ static int usb_audio_suspend(struct usb_interface *intf, pm_message_t message)
 			chip->autosuspended = 1;
 	}
 
-	list_for_each_entry(mixer, &chip->mixer_list, list)
-		snd_usb_mixer_suspend(mixer);
+	if (chip->num_suspended_intf == 1)
+		list_for_each_entry(mixer, &chip->mixer_list, list)
+			snd_usb_mixer_suspend(mixer);
 
 	return 0;
 }
@@ -711,6 +712,8 @@ static int __usb_audio_resume(struct usb_interface *intf, bool reset_resume)
 		return 0;
 	if (--chip->num_suspended_intf)
 		return 0;
+
+	chip->in_pm = 1;
 	/*
 	 * ALSA leaves material resumption to user space
 	 * we just notify and restart the mixers
@@ -726,6 +729,7 @@ static int __usb_audio_resume(struct usb_interface *intf, bool reset_resume)
 	chip->autosuspended = 0;
 
 err_out:
+	chip->in_pm = 0;
 	return err;
 }
 
diff --git a/sound/usb/card.h b/sound/usb/card.h
index 9867ab866857..97acb906acc2 100644
--- a/sound/usb/card.h
+++ b/sound/usb/card.h
@@ -92,6 +92,7 @@ struct snd_usb_endpoint {
 	unsigned int curframesize;      /* current packet size in frames (for capture) */
 	unsigned int syncmaxsize;	/* sync endpoint packet size */
 	unsigned int fill_max:1;	/* fill max packet size always */
+	unsigned int udh01_fb_quirk:1;	/* corrupted feedback data */
 	unsigned int datainterval;      /* log_2 of data packet interval */
 	unsigned int syncinterval;	/* P for adaptive mode, 0 otherwise */
 	unsigned char silence_value;
diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c
index e70a87e0d9fe..289f582c9130 100644
--- a/sound/usb/endpoint.c
+++ b/sound/usb/endpoint.c
@@ -471,6 +471,10 @@ struct snd_usb_endpoint *snd_usb_add_endpoint(struct snd_usb_audio *chip,
 			ep->syncinterval = 3;
 
 		ep->syncmaxsize = le16_to_cpu(get_endpoint(alts, 1)->wMaxPacketSize);
+
+		if (chip->usb_id == USB_ID(0x0644, 0x8038) /* TEAC UD-H01 */ &&
+		    ep->syncmaxsize == 4)
+			ep->udh01_fb_quirk = 1;
 	}
 
 	list_add_tail(&ep->list, &chip->ep_list);
@@ -1105,7 +1109,16 @@ void snd_usb_handle_sync_urb(struct snd_usb_endpoint *ep,
 	if (f == 0)
 		return;
 
-	if (unlikely(ep->freqshift == INT_MIN)) {
+	if (unlikely(sender->udh01_fb_quirk)) {
+		/*
+		 * The TEAC UD-H01 firmware sometimes changes the feedback value
+		 * by +/- 0x1.0000.
+		 */
+		if (f < ep->freqn - 0x8000)
+			f += 0x10000;
+		else if (f > ep->freqn + 0x8000)
+			f -= 0x10000;
+	} else if (unlikely(ep->freqshift == INT_MIN)) {
 		/*
 		 * The first time we see a feedback value, determine its format
 		 * by shifting it left or right until it matches the nominal
diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index 131336d40492..c62a1659106d 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -1501,9 +1501,8 @@ static void retire_playback_urb(struct snd_usb_substream *subs,
 	 * The error should be lower than 2ms since the estimate relies
 	 * on two reads of a counter updated every ms.
 	 */
-	if (printk_ratelimit() &&
-	    abs(est_delay - subs->last_delay) * 1000 > runtime->rate * 2)
-		dev_dbg(&subs->dev->dev,
+	if (abs(est_delay - subs->last_delay) * 1000 > runtime->rate * 2)
+		dev_dbg_ratelimited(&subs->dev->dev,
 			"delay: estimated %d, actual %d\n",
 			est_delay, subs->last_delay);
 
diff --git a/sound/usb/usbaudio.h b/sound/usb/usbaudio.h
index 25c4c7e217de..91d0380431b4 100644
--- a/sound/usb/usbaudio.h
+++ b/sound/usb/usbaudio.h
@@ -40,6 +40,7 @@ struct snd_usb_audio {
 	struct rw_semaphore shutdown_rwsem;
 	unsigned int shutdown:1;
 	unsigned int probing:1;
+	unsigned int in_pm:1;
 	unsigned int autosuspended:1;	
 	unsigned int txfr_quirk:1; /* Subframe boundaries on transfers */
 	
diff --git a/tools/Makefile b/tools/Makefile
index bcae806b0c39..9a617adc6675 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -44,6 +44,9 @@ cpupower: FORCE
 cgroup firewire hv guest usb virtio vm net: FORCE
 	$(call descend,$@)
 
+liblockdep: FORCE
+	$(call descend,lib/lockdep)
+
 libapikfs: FORCE
 	$(call descend,lib/api)
 
@@ -91,6 +94,9 @@ cpupower_clean:
 cgroup_clean hv_clean firewire_clean lguest_clean usb_clean virtio_clean vm_clean net_clean:
 	$(call descend,$(@:_clean=),clean)
 
+liblockdep_clean:
+	$(call descend,lib/lockdep,clean)
+
 libapikfs_clean:
 	$(call descend,lib/api,clean)
 
diff --git a/tools/lib/lockdep/Makefile b/tools/lib/lockdep/Makefile
index cb09d3ff8f58..bba2f5253b6e 100644
--- a/tools/lib/lockdep/Makefile
+++ b/tools/lib/lockdep/Makefile
@@ -1,8 +1,7 @@
 # file format version
 FILE_VERSION = 1
 
-MAKEFLAGS += --no-print-directory
-LIBLOCKDEP_VERSION=$(shell make -sC ../../.. kernelversion)
+LIBLOCKDEP_VERSION=$(shell make --no-print-directory -sC ../../.. kernelversion)
 
 # Makefiles suck: This macro sets a default value of $(2) for the
 # variable named by $(1), unless the variable has been set by
@@ -231,7 +230,7 @@ install_lib: all_cmd
 install: install_lib
 
 clean:
-	$(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d
+	$(RM) *.o *~ $(TARGETS) *.a *liblockdep*.so* $(VERSION_FILES) .*.d
 	$(RM) tags TAGS
 
 endif # skip-makefile