Merge branch 'master' into for-next

Conflicts:
	include/linux/mmzone.h

Synced with Linus' tree so that trivial patch can be applied
on top of up-to-date code properly.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>

221 files changed, 12515 insertions, 6036 deletions

diff --git a/Documentation/ABI/testing/sysfs-bus-i2c-devices-lm3533 b/Documentation/ABI/testing/sysfs-bus-i2c-devices-lm3533
new file mode 100644
index 000000000000..1b62230b33b9
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-i2c-devices-lm3533
@@ -0,0 +1,15 @@
+What:		/sys/bus/i2c/devices/.../output_hvled[n]
+Date:		April 2012
+KernelVersion:	3.5
+Contact:	Johan Hovold <jhovold@gmail.com>
+Description:
+		Set the controlling backlight device for high-voltage current
+		sink HVLED[n] (n = 1, 2) (0, 1).
+
+What:		/sys/bus/i2c/devices/.../output_lvled[n]
+Date:		April 2012
+KernelVersion:	3.5
+Contact:	Johan Hovold <jhovold@gmail.com>
+Description:
+		Set the controlling led device for low-voltage current sink
+		LVLED[n] (n = 1..5) (0..3).
diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index 9b1067afb224..6a066a270fc5 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -184,12 +184,14 @@ behind this approach is that a cgroup that aggressively uses a shared
 page will eventually get charged for it (once it is uncharged from
 the cgroup that brought it in -- this will happen on memory pressure).
 
+But see section 8.2: when moving a task to another cgroup, its pages may
+be recharged to the new cgroup, if move_charge_at_immigrate has been chosen.
+
 Exception: If CONFIG_CGROUP_CGROUP_MEM_RES_CTLR_SWAP is not used.
 When you do swapoff and make swapped-out pages of shmem(tmpfs) to
 be backed into memory in force, charges for pages are accounted against the
 caller of swapoff rather than the users of shmem.
 
-
 2.4 Swap Extension (CONFIG_CGROUP_MEM_RES_CTLR_SWAP)
 
 Swap Extension allows you to record charge for swap. A swapped-in page is
@@ -430,17 +432,10 @@ hierarchical_memory_limit - # of bytes of memory limit with regard to hierarchy
 hierarchical_memsw_limit - # of bytes of memory+swap limit with regard to
 			hierarchy under which memory cgroup is.
 
-total_cache		- sum of all children's "cache"
-total_rss		- sum of all children's "rss"
-total_mapped_file	- sum of all children's "cache"
-total_pgpgin		- sum of all children's "pgpgin"
-total_pgpgout		- sum of all children's "pgpgout"
-total_swap		- sum of all children's "swap"
-total_inactive_anon	- sum of all children's "inactive_anon"
-total_active_anon	- sum of all children's "active_anon"
-total_inactive_file	- sum of all children's "inactive_file"
-total_active_file	- sum of all children's "active_file"
-total_unevictable	- sum of all children's "unevictable"
+total_<counter>		- # hierarchical version of <counter>, which in
+			addition to the cgroup's own value includes the
+			sum of all hierarchical children's values of
+			<counter>, i.e. total_cache
 
 # The following additional stats are dependent on CONFIG_DEBUG_VM.
 
@@ -622,8 +617,7 @@ memory cgroup.
   bit | what type of charges would be moved ?
  -----+------------------------------------------------------------------------
    0  | A charge of an anonymous page(or swap of it) used by the target task.
-      | Those pages and swaps must be used only by the target task. You must
-      | enable Swap Extension(see 2.4) to enable move of swap charges.
+      | You must enable Swap Extension(see 2.4) to enable move of swap charges.
  -----+------------------------------------------------------------------------
    1  | A charge of file pages(normal file, tmpfs file(e.g. ipc shared memory)
       | and swaps of tmpfs file) mmapped by the target task. Unlike the case of
@@ -636,8 +630,6 @@ memory cgroup.
 
 8.3 TODO
 
-- Implement madvise(2) to let users decide the vma to be moved or not to be
-  moved.
 - All of moving charge operations are done under cgroup_mutex. It's not good
   behavior to hold the mutex too long, so we may need some trick.
 
diff --git a/Documentation/devicetree/bindings/mfd/da9052-i2c.txt b/Documentation/devicetree/bindings/mfd/da9052-i2c.txt
new file mode 100644
index 000000000000..1857f4a6b9a9
--- /dev/null
+++ b/Documentation/devicetree/bindings/mfd/da9052-i2c.txt
@@ -0,0 +1,60 @@
+* Dialog DA9052/53 Power Management Integrated Circuit (PMIC)
+
+Required properties:
+- compatible : Should be "dlg,da9052", "dlg,da9053-aa",
+			 "dlg,da9053-ab", or "dlg,da9053-bb"
+
+Sub-nodes:
+- regulators : Contain the regulator nodes. The DA9052/53 regulators are
+  bound using their names as listed below:
+
+    buck0     : regulator BUCK0
+    buck1     : regulator BUCK1
+    buck2     : regulator BUCK2
+    buck3     : regulator BUCK3
+    ldo4      : regulator LDO4
+    ldo5      : regulator LDO5
+    ldo6      : regulator LDO6
+    ldo7      : regulator LDO7
+    ldo8      : regulator LDO8
+    ldo9      : regulator LDO9
+    ldo10     : regulator LDO10
+    ldo11     : regulator LDO11
+    ldo12     : regulator LDO12
+    ldo13     : regulator LDO13
+
+  The bindings details of individual regulator device can be found in:
+  Documentation/devicetree/bindings/regulator/regulator.txt
+
+Examples:
+
+i2c@63fc8000 { /* I2C1 */
+	status = "okay";
+
+	pmic: dialog@48 {
+		compatible = "dlg,da9053-aa";
+		reg = <0x48>;
+
+		regulators {
+			buck0 {
+				regulator-min-microvolt = <500000>;
+				regulator-max-microvolt = <2075000>;
+			};
+
+			buck1 {
+				regulator-min-microvolt = <500000>;
+				regulator-max-microvolt = <2075000>;
+			};
+
+			buck2 {
+				regulator-min-microvolt = <925000>;
+				regulator-max-microvolt = <2500000>;
+			};
+
+			buck3 {
+				regulator-min-microvolt = <925000>;
+				regulator-max-microvolt = <2500000>;
+			};
+		};
+	};
+};
diff --git a/Documentation/devicetree/bindings/mfd/tps65910.txt b/Documentation/devicetree/bindings/mfd/tps65910.txt
new file mode 100644
index 000000000000..645f5eaadb3f
--- /dev/null
+++ b/Documentation/devicetree/bindings/mfd/tps65910.txt
@@ -0,0 +1,133 @@
+TPS65910 Power Management Integrated Circuit
+
+Required properties:
+- compatible: "ti,tps65910" or "ti,tps65911"
+- reg: I2C slave address
+- interrupts: the interrupt outputs of the controller
+- #gpio-cells: number of cells to describe a GPIO, this should be 2.
+  The first cell is the GPIO number.
+  The second cell is used to specify additional options <unused>.
+- gpio-controller: mark the device as a GPIO controller
+- #interrupt-cells: the number of cells to describe an IRQ, this should be 2.
+  The first cell is the IRQ number.
+  The second cell is the flags, encoded as the trigger masks from
+  Documentation/devicetree/bindings/interrupts.txt
+- regulators: This is the list of child nodes that specify the regulator
+  initialization data for defined regulators. Not all regulators for the given
+  device need to be present. The definition for each of these nodes is defined
+  using the standard binding for regulators found at
+  Documentation/devicetree/bindings/regulator/regulator.txt.
+
+  The valid names for regulators are:
+  tps65910: vrtc, vio, vdd1, vdd2, vdd3, vdig1, vdig2, vpll, vdac, vaux1,
+            vaux2, vaux33, vmmc
+  tps65911: vrtc, vio, vdd1, vdd3, vddctrl, ldo1, ldo2, ldo3, ldo4, ldo5,
+            ldo6, ldo7, ldo8
+
+Optional properties:
+- ti,vmbch-threshold: (tps65911) main battery charged threshold
+  comparator. (see VMBCH_VSEL in TPS65910 datasheet)
+- ti,vmbch2-threshold: (tps65911) main battery discharged threshold
+  comparator. (see VMBCH_VSEL in TPS65910 datasheet)
+- ti,en-gpio-sleep: enable sleep control for gpios
+  There should be 9 entries here, one for each gpio.
+
+Regulator Optional properties:
+- ti,regulator-ext-sleep-control: enable external sleep
+  control through external inputs [0 (not enabled), 1 (EN1), 2 (EN2) or 4(EN3)]
+  If this property is not defined, it defaults to 0 (not enabled).
+
+Example:
+
+	pmu: tps65910@d2 {
+		compatible = "ti,tps65910";
+		reg = <0xd2>;
+		interrupt-parent = <&intc>;
+		interrupts = < 0 118 0x04 >;
+
+		#gpio-cells = <2>;
+		gpio-controller;
+
+		#interrupt-cells = <2>;
+		interrupt-controller;
+
+		ti,vmbch-threshold = 0;
+		ti,vmbch2-threshold = 0;
+
+		ti,en-gpio-sleep = <0 0 1 0 0 0 0 0 0>;
+
+		regulators {
+			vdd1_reg: vdd1 {
+				regulator-min-microvolt = < 600000>;
+				regulator-max-microvolt = <1500000>;
+				regulator-always-on;
+				regulator-boot-on;
+				ti,regulator-ext-sleep-control = <0>;
+			};
+			vdd2_reg: vdd2 {
+				regulator-min-microvolt = < 600000>;
+				regulator-max-microvolt = <1500000>;
+				regulator-always-on;
+				regulator-boot-on;
+				ti,regulator-ext-sleep-control = <4>;
+			};
+			vddctrl_reg: vddctrl {
+				regulator-min-microvolt = < 600000>;
+				regulator-max-microvolt = <1400000>;
+				regulator-always-on;
+				regulator-boot-on;
+				ti,regulator-ext-sleep-control = <0>;
+			};
+			vio_reg: vio {
+				regulator-min-microvolt = <1500000>;
+				regulator-max-microvolt = <1800000>;
+				regulator-always-on;
+				regulator-boot-on;
+				ti,regulator-ext-sleep-control = <1>;
+			};
+			ldo1_reg: ldo1 {
+				regulator-min-microvolt = <1000000>;
+				regulator-max-microvolt = <3300000>;
+				ti,regulator-ext-sleep-control = <0>;
+			};
+			ldo2_reg: ldo2 {
+				regulator-min-microvolt = <1050000>;
+				regulator-max-microvolt = <1050000>;
+				ti,regulator-ext-sleep-control = <0>;
+			};
+			ldo3_reg: ldo3 {
+				regulator-min-microvolt = <1000000>;
+				regulator-max-microvolt = <3300000>;
+				ti,regulator-ext-sleep-control = <0>;
+			};
+			ldo4_reg: ldo4 {
+				regulator-min-microvolt = <1000000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+				ti,regulator-ext-sleep-control = <0>;
+			};
+			ldo5_reg: ldo5 {
+				regulator-min-microvolt = <1000000>;
+				regulator-max-microvolt = <3300000>;
+				ti,regulator-ext-sleep-control = <0>;
+			};
+			ldo6_reg: ldo6 {
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1200000>;
+				ti,regulator-ext-sleep-control = <0>;
+			};
+			ldo7_reg: ldo7 {
+				regulator-min-microvolt = <1200000>;
+				regulator-max-microvolt = <1200000>;
+				regulator-always-on;
+				regulator-boot-on;
+				ti,regulator-ext-sleep-control = <1>;
+			};
+			ldo8_reg: ldo8 {
+				regulator-min-microvolt = <1000000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+				ti,regulator-ext-sleep-control = <1>;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/mfd/twl6040.txt b/Documentation/devicetree/bindings/mfd/twl6040.txt
new file mode 100644
index 000000000000..bc67c6f424aa
--- /dev/null
+++ b/Documentation/devicetree/bindings/mfd/twl6040.txt
@@ -0,0 +1,62 @@
+Texas Instruments TWL6040 family
+
+The TWL6040s are 8-channel high quality low-power audio codecs providing audio
+and vibra functionality on OMAP4+ platforms.
+They are connected ot the host processor via i2c for commands, McPDM for audio
+data and commands.
+
+Required properties:
+- compatible : Must be "ti,twl6040";
+- reg: must be 0x4b for i2c address
+- interrupts: twl6040 has one interrupt line connecteded to the main SoC
+- interrupt-parent: The parent interrupt controller
+- twl6040,audpwron-gpio: Power on GPIO line for the twl6040
+
+- vio-supply: Regulator for the twl6040 VIO supply
+- v2v1-supply: Regulator for the twl6040 V2V1 supply
+
+Optional properties, nodes:
+- enable-active-high: To power on the twl6040 during boot.
+
+Vibra functionality
+Required properties:
+- vddvibl-supply: Regulator for the left vibra motor
+- vddvibr-supply: Regulator for the right vibra motor
+- vibra { }: Configuration section for vibra parameters containing the following
+	     properties:
+- ti,vibldrv-res: Resistance parameter for left driver
+- ti,vibrdrv-res: Resistance parameter for right driver
+- ti,viblmotor-res: Resistance parameter for left motor
+- ti,viblmotor-res: Resistance parameter for right motor
+
+Optional properties within vibra { } section:
+- vddvibl_uV: If the vddvibl default voltage need to be changed
+- vddvibr_uV: If the vddvibr default voltage need to be changed
+
+Example:
+&i2c1 {
+	twl6040: twl@4b {
+		compatible = "ti,twl6040";
+		reg = <0x4b>;
+
+		interrupts = <0 119 4>;
+		interrupt-parent = <&gic>;
+		twl6040,audpwron-gpio = <&gpio4 31 0>;
+
+		vio-supply = <&v1v8>;
+		v2v1-supply = <&v2v1>;
+		enable-active-high;
+
+		/* regulators for vibra motor */
+		vddvibl-supply = <&vbat>;
+		vddvibr-supply = <&vbat>;
+
+		vibra {
+			/* Vibra driver, motor resistance parameters */
+			ti,vibldrv-res = <8>;
+			ti,vibrdrv-res = <3>;
+			ti,viblmotor-res = <10>;
+			ti,vibrmotor-res = <10>;
+		};
+	};
+};
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 4fca82e5276e..d449e632e6a0 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -60,7 +60,6 @@ ata *);
 	ssize_t (*getxattr) (struct dentry *, const char *, void *, size_t);
 	ssize_t (*listxattr) (struct dentry *, char *, size_t);
 	int (*removexattr) (struct dentry *, const char *);
-	void (*truncate_range)(struct inode *, loff_t, loff_t);
 	int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len);
 
 locking rules:
@@ -87,7 +86,6 @@ setxattr:	yes
 getxattr:	no
 listxattr:	no
 removexattr:	yes
-truncate_range:	yes
 fiemap:		no
 	Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on
 victim.
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index ef088e55ab2e..912af6ce5626 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -743,6 +743,7 @@ Committed_AS:   100056 kB
 VmallocTotal:   112216 kB
 VmallocUsed:       428 kB
 VmallocChunk:   111088 kB
+AnonHugePages:   49152 kB
 
     MemTotal: Total usable ram (i.e. physical ram minus a few reserved
               bits and the kernel binary code)
@@ -776,6 +777,7 @@ VmallocChunk:   111088 kB
        Dirty: Memory which is waiting to get written back to the disk
    Writeback: Memory which is actively being written back to the disk
    AnonPages: Non-file backed pages mapped into userspace page tables
+AnonHugePages: Non-file backed huge pages mapped into userspace page tables
       Mapped: files which have been mmaped, such as libraries
         Slab: in-kernel data structures cache
 SReclaimable: Part of Slab, that might be reclaimed, such as caches
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 0d0492028082..ef19f91a0f12 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -363,7 +363,6 @@ struct inode_operations {
 	ssize_t (*getxattr) (struct dentry *, const char *, void *, size_t);
 	ssize_t (*listxattr) (struct dentry *, char *, size_t);
 	int (*removexattr) (struct dentry *, const char *);
-	void (*truncate_range)(struct inode *, loff_t, loff_t);
 };
 
 Again, all methods are called without any locks being held, unless
@@ -472,9 +471,6 @@ otherwise noted.
   removexattr: called by the VFS to remove an extended attribute from
   	a file. This method is called by removexattr(2) system call.
 
-  truncate_range: a method provided by the underlying filesystem to truncate a
-  	range of blocks , i.e. punch a hole somewhere in a file.
-
 
 The Address Space Object
 ========================
@@ -760,7 +756,7 @@ struct file_operations
 ----------------------
 
 This describes how the VFS can manipulate an open file. As of kernel
-2.6.22, the following members are defined:
+3.5, the following members are defined:
 
 struct file_operations {
 	struct module *owner;
@@ -790,6 +786,8 @@ struct file_operations {
 	int (*flock) (struct file *, int, struct file_lock *);
 	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, size_t, unsigned int);
 	ssize_t (*splice_read)(struct file *, struct pipe_inode_info *, size_t, unsigned int);
+	int (*setlease)(struct file *, long arg, struct file_lock **);
+	long (*fallocate)(struct file *, int mode, loff_t offset, loff_t len);
 };
 
 Again, all methods are called without any locks being held, unless
@@ -858,6 +856,11 @@ otherwise noted.
   splice_read: called by the VFS to splice data from file to a pipe. This
 	       method is used by the splice(2) system call
 
+  setlease: called by the VFS to set or release a file lock lease.
+	    setlease has the file_lock_lock held and must not sleep.
+
+  fallocate: called by the VFS to preallocate blocks or punch a hole.
+
 Note that the file operations are implemented by the specific
 filesystem in which the inode resides. When opening a device node
 (character or block special) most filesystems will call special
diff --git a/Documentation/vm/transhuge.txt b/Documentation/vm/transhuge.txt
index 29bdf62aac09..f734bb2a78dc 100644
--- a/Documentation/vm/transhuge.txt
+++ b/Documentation/vm/transhuge.txt
@@ -166,6 +166,68 @@ behavior. So to make them effective you need to restart any
 application that could have been using hugepages. This also applies to
 the regions registered in khugepaged.
 
+== Monitoring usage ==
+
+The number of transparent huge pages currently used by the system is
+available by reading the AnonHugePages field in /proc/meminfo. To
+identify what applications are using transparent huge pages, it is
+necessary to read /proc/PID/smaps and count the AnonHugePages fields
+for each mapping. Note that reading the smaps file is expensive and
+reading it frequently will incur overhead.
+
+There are a number of counters in /proc/vmstat that may be used to
+monitor how successfully the system is providing huge pages for use.
+
+thp_fault_alloc is incremented every time a huge page is successfully
+	allocated to handle a page fault. This applies to both the
+	first time a page is faulted and for COW faults.
+
+thp_collapse_alloc is incremented by khugepaged when it has found
+	a range of pages to collapse into one huge page and has
+	successfully allocated a new huge page to store the data.
+
+thp_fault_fallback is incremented if a page fault fails to allocate
+	a huge page and instead falls back to using small pages.
+
+thp_collapse_alloc_failed is incremented if khugepaged found a range
+	of pages that should be collapsed into one huge page but failed
+	the allocation.
+
+thp_split is incremented every time a huge page is split into base
+	pages. This can happen for a variety of reasons but a common
+	reason is that a huge page is old and is being reclaimed.
+
+As the system ages, allocating huge pages may be expensive as the
+system uses memory compaction to copy data around memory to free a
+huge page for use. There are some counters in /proc/vmstat to help
+monitor this overhead.
+
+compact_stall is incremented every time a process stalls to run
+	memory compaction so that a huge page is free for use.
+
+compact_success is incremented if the system compacted memory and
+	freed a huge page for use.
+
+compact_fail is incremented if the system tries to compact memory
+	but failed.
+
+compact_pages_moved is incremented each time a page is moved. If
+	this value is increasing rapidly, it implies that the system
+	is copying a lot of data to satisfy the huge page allocation.
+	It is possible that the cost of copying exceeds any savings
+	from reduced TLB misses.
+
+compact_pagemigrate_failed is incremented when the underlying mechanism
+	for moving a page failed.
+
+compact_blocks_moved is incremented each time memory compaction examines
+	a huge page aligned range of pages.
+
+It is possible to establish how long the stalls were using the function
+tracer to record how long was spent in __alloc_pages_nodemask and
+using the mm_page_alloc tracepoint to identify which allocations were
+for huge pages.
+
 == get_user_pages and follow_page ==
 
 get_user_pages and follow_page if run on a hugepage, will return the
diff --git a/MAINTAINERS b/MAINTAINERS
index 6f90c64a2539..cc710d2ef009 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3382,6 +3382,12 @@ W:	http://www.developer.ibm.com/welcome/netfinity/serveraid.html
 S:	Supported
 F:	drivers/scsi/ips.*
 
+ICH LPC AND GPIO DRIVER
+M:	Peter Tyser <ptyser@xes-inc.com>
+S:	Maintained
+F:	drivers/mfd/lpc_ich.c
+F:	drivers/gpio/gpio-ich.c
+
 IDE SUBSYSTEM
 M:	"David S. Miller" <davem@davemloft.net>
 L:	linux-ide@vger.kernel.org
diff --git a/arch/arm/mach-ux500/board-mop500.c b/arch/arm/mach-ux500/board-mop500.c
index b23a643f03f4..fba8adea421e 100644
--- a/arch/arm/mach-ux500/board-mop500.c
+++ b/arch/arm/mach-ux500/board-mop500.c
@@ -206,7 +206,7 @@ static struct resource ab8500_resources[] = {
 };
 
 struct platform_device ab8500_device = {
-	.name = "ab8500-i2c",
+	.name = "ab8500-core",
 	.id = 0,
 	.dev = {
 		.platform_data = &ab8500_platdata,
diff --git a/arch/cris/Kconfig b/arch/cris/Kconfig
index 22d34d64cc81..bb344650a14f 100644
--- a/arch/cris/Kconfig
+++ b/arch/cris/Kconfig
@@ -40,6 +40,7 @@ config CRIS
 	bool
 	default y
 	select HAVE_IDE
+	select GENERIC_ATOMIC64
 	select HAVE_GENERIC_HARDIRQS
 	select GENERIC_IRQ_SHOW
 	select GENERIC_IOMAP
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index effff47a3c82..43876f16caf1 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -31,6 +31,56 @@ static inline void native_set_pte(pte_t *ptep, pte_t pte)
 	ptep->pte_low = pte.pte_low;
 }
 
+#define pmd_read_atomic pmd_read_atomic
+/*
+ * pte_offset_map_lock on 32bit PAE kernels was reading the pmd_t with
+ * a "*pmdp" dereference done by gcc. Problem is, in certain places
+ * where pte_offset_map_lock is called, concurrent page faults are
+ * allowed, if the mmap_sem is hold for reading. An example is mincore
+ * vs page faults vs MADV_DONTNEED. On the page fault side
+ * pmd_populate rightfully does a set_64bit, but if we're reading the
+ * pmd_t with a "*pmdp" on the mincore side, a SMP race can happen
+ * because gcc will not read the 64bit of the pmd atomically. To fix
+ * this all places running pmd_offset_map_lock() while holding the
+ * mmap_sem in read mode, shall read the pmdp pointer using this
+ * function to know if the pmd is null nor not, and in turn to know if
+ * they can run pmd_offset_map_lock or pmd_trans_huge or other pmd
+ * operations.
+ *
+ * Without THP if the mmap_sem is hold for reading, the
+ * pmd can only transition from null to not null while pmd_read_atomic runs.
+ * So there's no need of literally reading it atomically.
+ *
+ * With THP if the mmap_sem is hold for reading, the pmd can become
+ * THP or null or point to a pte (and in turn become "stable") at any
+ * time under pmd_read_atomic, so it's mandatory to read it atomically
+ * with cmpxchg8b.
+ */
+#ifndef CONFIG_TRANSPARENT_HUGEPAGE
+static inline pmd_t pmd_read_atomic(pmd_t *pmdp)
+{
+	pmdval_t ret;
+	u32 *tmp = (u32 *)pmdp;
+
+	ret = (pmdval_t) (*tmp);
+	if (ret) {
+		/*
+		 * If the low part is null, we must not read the high part
+		 * or we can end up with a partial pmd.
+		 */
+		smp_rmb();
+		ret |= ((pmdval_t)*(tmp + 1)) << 32;
+	}
+
+	return (pmd_t) { ret };
+}
+#else /* CONFIG_TRANSPARENT_HUGEPAGE */
+static inline pmd_t pmd_read_atomic(pmd_t *pmdp)
+{
+	return (pmd_t) { atomic64_read((atomic64_t *)pmdp) };
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
 static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte)
 {
 	set_64bit((unsigned long long *)(ptep), native_pte_val(pte));
diff --git a/arch/x86/include/asm/sta2x11.h b/arch/x86/include/asm/sta2x11.h
new file mode 100644
index 000000000000..e9d32df89ccc
--- /dev/null
+++ b/arch/x86/include/asm/sta2x11.h
@@ -0,0 +1,12 @@
+/*
+ * Header file for STMicroelectronics ConneXt (STA2X11) IOHub
+ */
+#ifndef __ASM_STA2X11_H
+#define __ASM_STA2X11_H
+
+#include <linux/pci.h>
+
+/* This needs to be called from the MFD to configure its sub-devices */
+struct sta2x11_instance *sta2x11_get_instance(struct pci_dev *pdev);
+
+#endif /* __ASM_STA2X11_H */
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 62d61e9976eb..41857970517f 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -113,7 +113,9 @@ static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size,
 	int x = e820x->nr_map;
 
 	if (x >= ARRAY_SIZE(e820x->map)) {
-		printk(KERN_ERR "Ooops! Too many entries in the memory map!\n");
+		printk(KERN_ERR "e820: too many entries; ignoring [mem %#010llx-%#010llx]\n",
+		       (unsigned long long) start,
+		       (unsigned long long) (start + size - 1));
 		return;
 	}
 
@@ -133,19 +135,19 @@ static void __init e820_print_type(u32 type)
 	switch (type) {
 	case E820_RAM:
 	case E820_RESERVED_KERN:
-		printk(KERN_CONT "(usable)");
+		printk(KERN_CONT "usable");
 		break;
 	case E820_RESERVED:
-		printk(KERN_CONT "(reserved)");
+		printk(KERN_CONT "reserved");
 		break;
 	case E820_ACPI:
-		printk(KERN_CONT "(ACPI data)");
+		printk(KERN_CONT "ACPI data");
 		break;
 	case E820_NVS:
-		printk(KERN_CONT "(ACPI NVS)");
+		printk(KERN_CONT "ACPI NVS");
 		break;
 	case E820_UNUSABLE:
-		printk(KERN_CONT "(unusable)");
+		printk(KERN_CONT "unusable");
 		break;
 	default:
 		printk(KERN_CONT "type %u", type);
@@ -158,10 +160,10 @@ void __init e820_print_map(char *who)
 	int i;
 
 	for (i = 0; i < e820.nr_map; i++) {
-		printk(KERN_INFO " %s: %016Lx - %016Lx ", who,
+		printk(KERN_INFO "%s: [mem %#018Lx-%#018Lx] ", who,
 		       (unsigned long long) e820.map[i].addr,
 		       (unsigned long long)
-		       (e820.map[i].addr + e820.map[i].size));
+		       (e820.map[i].addr + e820.map[i].size - 1));
 		e820_print_type(e820.map[i].type);
 		printk(KERN_CONT "\n");
 	}
@@ -428,9 +430,8 @@ static u64 __init __e820_update_range(struct e820map *e820x, u64 start,
 		size = ULLONG_MAX - start;
 
 	end = start + size;
-	printk(KERN_DEBUG "e820 update range: %016Lx - %016Lx ",
-		       (unsigned long long) start,
-		       (unsigned long long) end);
+	printk(KERN_DEBUG "e820: update [mem %#010Lx-%#010Lx] ",
+	       (unsigned long long) start, (unsigned long long) (end - 1));
 	e820_print_type(old_type);
 	printk(KERN_CONT " ==> ");
 	e820_print_type(new_type);
@@ -509,9 +510,8 @@ u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type,
 		size = ULLONG_MAX - start;
 
 	end = start + size;
-	printk(KERN_DEBUG "e820 remove range: %016Lx - %016Lx ",
-		       (unsigned long long) start,
-		       (unsigned long long) end);
+	printk(KERN_DEBUG "e820: remove [mem %#010Lx-%#010Lx] ",
+	       (unsigned long long) start, (unsigned long long) (end - 1));
 	if (checktype)
 		e820_print_type(old_type);
 	printk(KERN_CONT "\n");
@@ -567,7 +567,7 @@ void __init update_e820(void)
 	if (sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &nr_map))
 		return;
 	e820.nr_map = nr_map;
-	printk(KERN_INFO "modified physical RAM map:\n");
+	printk(KERN_INFO "e820: modified physical RAM map:\n");
 	e820_print_map("modified");
 }
 static void __init update_e820_saved(void)
@@ -637,8 +637,8 @@ __init void e820_setup_gap(void)
 	if (!found) {
 		gapstart = (max_pfn << PAGE_SHIFT) + 1024*1024;
 		printk(KERN_ERR
-	"PCI: Warning: Cannot find a gap in the 32bit address range\n"
-	"PCI: Unassigned devices with 32bit resource registers may break!\n");
+	"e820: cannot find a gap in the 32bit address range\n"
+	"e820: PCI devices with unassigned 32bit BARs may break!\n");
 	}
 #endif
 
@@ -648,8 +648,8 @@ __init void e820_setup_gap(void)
 	pci_mem_start = gapstart;
 
 	printk(KERN_INFO
-	       "Allocating PCI resources starting at %lx (gap: %lx:%lx)\n",
-	       pci_mem_start, gapstart, gapsize);
+	       "e820: [mem %#010lx-%#010lx] available for PCI devices\n",
+	       gapstart, gapstart + gapsize - 1);
 }
 
 /**
@@ -667,7 +667,7 @@ void __init parse_e820_ext(struct setup_data *sdata)
 	extmap = (struct e820entry *)(sdata->data);
 	__append_e820_map(extmap, entries);
 	sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
-	printk(KERN_INFO "extended physical RAM map:\n");
+	printk(KERN_INFO "e820: extended physical RAM map:\n");
 	e820_print_map("extended");
 }
 
@@ -734,7 +734,7 @@ u64 __init early_reserve_e820(u64 size, u64 align)
 	addr = __memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
 	if (addr) {
 		e820_update_range_saved(addr, size, E820_RAM, E820_RESERVED);
-		printk(KERN_INFO "update e820_saved for early_reserve_e820\n");
+		printk(KERN_INFO "e820: update e820_saved for early_reserve_e820\n");
 		update_e820_saved();
 	}
 
@@ -784,7 +784,7 @@ static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type)
 	if (last_pfn > max_arch_pfn)
 		last_pfn = max_arch_pfn;
 
-	printk(KERN_INFO "last_pfn = %#lx max_arch_pfn = %#lx\n",
+	printk(KERN_INFO "e820: last_pfn = %#lx max_arch_pfn = %#lx\n",
 			 last_pfn, max_arch_pfn);
 	return last_pfn;
 }
@@ -888,7 +888,7 @@ void __init finish_e820_parsing(void)
 			early_panic("Invalid user supplied memory map");
 		e820.nr_map = nr;
 
-		printk(KERN_INFO "user-defined physical RAM map:\n");
+		printk(KERN_INFO "e820: user-defined physical RAM map:\n");
 		e820_print_map("user");
 	}
 }
@@ -996,8 +996,9 @@ void __init e820_reserve_resources_late(void)
 			end = MAX_RESOURCE_SIZE;
 		if (start >= end)
 			continue;
-		printk(KERN_DEBUG "reserve RAM buffer: %016llx - %016llx ",
-			       start, end);
+		printk(KERN_DEBUG
+		       "e820: reserve RAM buffer [mem %#010llx-%#010llx]\n",
+		       start, end);
 		reserve_region_with_split(&iomem_resource, start, end,
 					  "RAM buffer");
 	}
@@ -1047,7 +1048,7 @@ void __init setup_memory_map(void)
 
 	who = x86_init.resources.memory_setup();
 	memcpy(&e820_saved, &e820, sizeof(struct e820map));
-	printk(KERN_INFO "BIOS-provided physical RAM map:\n");
+	printk(KERN_INFO "e820: BIOS-provided physical RAM map:\n");
 	e820_print_map(who);
 }
 
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index b02d4dd6b8a3..fbca2e6223bf 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -568,8 +568,8 @@ static int __init smp_scan_config(unsigned long base, unsigned long length)
 	struct mpf_intel *mpf;
 	unsigned long mem;
 
-	apic_printk(APIC_VERBOSE, "Scan SMP from %p for %ld bytes.\n",
-			bp, length);
+	apic_printk(APIC_VERBOSE, "Scan for SMP in [mem %#010lx-%#010lx]\n",
+		    base, base + length - 1);
 	BUILD_BUG_ON(sizeof(*mpf) != 16);
 
 	while (length > 0) {
@@ -584,8 +584,10 @@ static int __init smp_scan_config(unsigned long base, unsigned long length)
 #endif
 			mpf_found = mpf;
 
-			printk(KERN_INFO "found SMP MP-table at [%p] %llx\n",
-			       mpf, (u64)virt_to_phys(mpf));
+			printk(KERN_INFO "found SMP MP-table at [mem %#010llx-%#010llx] mapped at [%p]\n",
+			       (unsigned long long) virt_to_phys(mpf),
+			       (unsigned long long) virt_to_phys(mpf) +
+			       sizeof(*mpf) - 1, mpf);
 
 			mem = virt_to_phys(mpf);
 			memblock_reserve(mem, sizeof(*mpf));
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index f2afee6a19c1..982e44f960db 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -334,8 +334,8 @@ static void __init relocate_initrd(void)
 	memblock_reserve(ramdisk_here, area_size);
 	initrd_start = ramdisk_here + PAGE_OFFSET;
 	initrd_end   = initrd_start + ramdisk_size;
-	printk(KERN_INFO "Allocated new RAMDISK: %08llx - %08llx\n",
-			 ramdisk_here, ramdisk_here + ramdisk_size);
+	printk(KERN_INFO "Allocated new RAMDISK: [mem %#010llx-%#010llx]\n",
+			 ramdisk_here, ramdisk_here + ramdisk_size - 1);
 
 	q = (char *)initrd_start;
 
@@ -366,8 +366,8 @@ static void __init relocate_initrd(void)
 	/* high pages is not converted by early_res_to_bootmem */
 	ramdisk_image = boot_params.hdr.ramdisk_image;
 	ramdisk_size  = boot_params.hdr.ramdisk_size;
-	printk(KERN_INFO "Move RAMDISK from %016llx - %016llx to"
-		" %08llx - %08llx\n",
+	printk(KERN_INFO "Move RAMDISK from [mem %#010llx-%#010llx] to"
+		" [mem %#010llx-%#010llx]\n",
 		ramdisk_image, ramdisk_image + ramdisk_size - 1,
 		ramdisk_here, ramdisk_here + ramdisk_size - 1);
 }
@@ -392,8 +392,8 @@ static void __init reserve_initrd(void)
 		       ramdisk_size, end_of_lowmem>>1);
 	}
 
-	printk(KERN_INFO "RAMDISK: %08llx - %08llx\n", ramdisk_image,
-			ramdisk_end);
+	printk(KERN_INFO "RAMDISK: [mem %#010llx-%#010llx]\n", ramdisk_image,
+			ramdisk_end - 1);
 
 
 	if (ramdisk_end <= end_of_lowmem) {
@@ -906,8 +906,8 @@ void __init setup_arch(char **cmdline_p)
 	setup_bios_corruption_check();
 #endif
 
-	printk(KERN_DEBUG "initial memory mapped : 0 - %08lx\n",
-			max_pfn_mapped<<PAGE_SHIFT);
+	printk(KERN_DEBUG "initial memory mapped: [mem 0x00000000-%#010lx]\n",
+			(max_pfn_mapped<<PAGE_SHIFT) - 1);
 
 	setup_trampolines();
 
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 319b6f2fb8b9..97141c26a13a 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -84,8 +84,9 @@ static void __init find_early_table_space(struct map_range *mr, unsigned long en
 	pgt_buf_end = pgt_buf_start;
 	pgt_buf_top = pgt_buf_start + (tables >> PAGE_SHIFT);
 
-	printk(KERN_DEBUG "kernel direct mapping tables up to %lx @ %lx-%lx\n",
-		end, pgt_buf_start << PAGE_SHIFT, pgt_buf_top << PAGE_SHIFT);
+	printk(KERN_DEBUG "kernel direct mapping tables up to %#lx @ [mem %#010lx-%#010lx]\n",
+		end - 1, pgt_buf_start << PAGE_SHIFT,
+		(pgt_buf_top << PAGE_SHIFT) - 1);
 }
 
 void __init native_pagetable_reserve(u64 start, u64 end)
@@ -132,7 +133,8 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 	int nr_range, i;
 	int use_pse, use_gbpages;
 
-	printk(KERN_INFO "init_memory_mapping: %016lx-%016lx\n", start, end);
+	printk(KERN_INFO "init_memory_mapping: [mem %#010lx-%#010lx]\n",
+	       start, end - 1);
 
 #if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KMEMCHECK)
 	/*
@@ -251,8 +253,8 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 	}
 
 	for (i = 0; i < nr_range; i++)
-		printk(KERN_DEBUG " %010lx - %010lx page %s\n",
-				mr[i].start, mr[i].end,
+		printk(KERN_DEBUG " [mem %#010lx-%#010lx] page %s\n",
+				mr[i].start, mr[i].end - 1,
 			(mr[i].page_size_mask & (1<<PG_LEVEL_1G))?"1G":(
 			 (mr[i].page_size_mask & (1<<PG_LEVEL_2M))?"2M":"4k"));
 
@@ -350,8 +352,8 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
 	 * create a kernel page fault:
 	 */
 #ifdef CONFIG_DEBUG_PAGEALLOC
-	printk(KERN_INFO "debug: unmapping init memory %08lx..%08lx\n",
-		begin, end);
+	printk(KERN_INFO "debug: unmapping init [mem %#010lx-%#010lx]\n",
+		begin, end - 1);
 	set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
 #else
 	/*
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 19d3fa08b119..2d125be1bae9 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -141,8 +141,8 @@ static int __init numa_add_memblk_to(int nid, u64 start, u64 end,
 
 	/* whine about and ignore invalid blks */
 	if (start > end || nid < 0 || nid >= MAX_NUMNODES) {
-		pr_warning("NUMA: Warning: invalid memblk node %d (%Lx-%Lx)\n",
-			   nid, start, end);
+		pr_warning("NUMA: Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n",
+			   nid, start, end - 1);
 		return 0;
 	}
 
@@ -210,8 +210,8 @@ static void __init setup_node_data(int nid, u64 start, u64 end)
 
 	start = roundup(start, ZONE_ALIGN);
 
-	printk(KERN_INFO "Initmem setup node %d %016Lx-%016Lx\n",
-	       nid, start, end);
+	printk(KERN_INFO "Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
+	       nid, start, end - 1);
 
 	/*
 	 * Allocate node data.  Try remap allocator first, node-local
@@ -232,7 +232,7 @@ static void __init setup_node_data(int nid, u64 start, u64 end)
 	}
 
 	/* report and initialize */
-	printk(KERN_INFO "  NODE_DATA [%016Lx - %016Lx]%s\n",
+	printk(KERN_INFO "  NODE_DATA [mem %#010Lx-%#010Lx]%s\n",
 	       nd_pa, nd_pa + nd_size - 1, remapped ? " (remapped)" : "");
 	tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT);
 	if (!remapped && tnid != nid)
@@ -291,14 +291,14 @@ int __init numa_cleanup_meminfo(struct numa_meminfo *mi)
 			 */
 			if (bi->end > bj->start && bi->start < bj->end) {
 				if (bi->nid != bj->nid) {
-					pr_err("NUMA: node %d (%Lx-%Lx) overlaps with node %d (%Lx-%Lx)\n",
-					       bi->nid, bi->start, bi->end,
-					       bj->nid, bj->start, bj->end);
+					pr_err("NUMA: node %d [mem %#010Lx-%#010Lx] overlaps with node %d [mem %#010Lx-%#010Lx]\n",
+					       bi->nid, bi->start, bi->end - 1,
+					       bj->nid, bj->start, bj->end - 1);
 					return -EINVAL;
 				}
-				pr_warning("NUMA: Warning: node %d (%Lx-%Lx) overlaps with itself (%Lx-%Lx)\n",
-					   bi->nid, bi->start, bi->end,
-					   bj->start, bj->end);
+				pr_warning("NUMA: Warning: node %d [mem %#010Lx-%#010Lx] overlaps with itself [mem %#010Lx-%#010Lx]\n",
+					   bi->nid, bi->start, bi->end - 1,
+					   bj->start, bj->end - 1);
 			}
 
 			/*
@@ -320,9 +320,9 @@ int __init numa_cleanup_meminfo(struct numa_meminfo *mi)
 			}
 			if (k < mi->nr_blks)
 				continue;
-			printk(KERN_INFO "NUMA: Node %d [%Lx,%Lx) + [%Lx,%Lx) -> [%Lx,%Lx)\n",
-			       bi->nid, bi->start, bi->end, bj->start, bj->end,
-			       start, end);
+			printk(KERN_INFO "NUMA: Node %d [mem %#010Lx-%#010Lx] + [mem %#010Lx-%#010Lx] -> [mem %#010Lx-%#010Lx]\n",
+			       bi->nid, bi->start, bi->end - 1, bj->start,
+			       bj->end - 1, start, end - 1);
 			bi->start = start;
 			bi->end = end;
 			numa_remove_memblk_from(j--, mi);
@@ -616,8 +616,8 @@ static int __init dummy_numa_init(void)
 {
 	printk(KERN_INFO "%s\n",
 	       numa_off ? "NUMA turned off" : "No NUMA configuration found");
-	printk(KERN_INFO "Faking a node at %016Lx-%016Lx\n",
-	       0LLU, PFN_PHYS(max_pfn));
+	printk(KERN_INFO "Faking a node at [mem %#018Lx-%#018Lx]\n",
+	       0LLU, PFN_PHYS(max_pfn) - 1);
 
 	node_set(0, numa_nodes_parsed);
 	numa_add_memblk(0, 0, PFN_PHYS(max_pfn));
diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c
index 871dd8868170..dbbbb47260cc 100644
--- a/arch/x86/mm/numa_emulation.c
+++ b/arch/x86/mm/numa_emulation.c
@@ -68,8 +68,8 @@ static int __init emu_setup_memblk(struct numa_meminfo *ei,
 		numa_remove_memblk_from(phys_blk, pi);
 	}
 
-	printk(KERN_INFO "Faking node %d at %016Lx-%016Lx (%LuMB)\n", nid,
-	       eb->start, eb->end, (eb->end - eb->start) >> 20);
+	printk(KERN_INFO "Faking node %d at [mem %#018Lx-%#018Lx] (%LuMB)\n",
+	       nid, eb->start, eb->end - 1, (eb->end - eb->start) >> 20);
 	return 0;
 }
 
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index f6ff57b7efa5..f11729fd019c 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -209,9 +209,8 @@ static int reserve_ram_pages_type(u64 start, u64 end, unsigned long req_type,
 		page = pfn_to_page(pfn);
 		type = get_page_memtype(page);
 		if (type != -1) {
-			printk(KERN_INFO "reserve_ram_pages_type failed "
-				"0x%Lx-0x%Lx, track 0x%lx, req 0x%lx\n",
-				start, end, type, req_type);
+			printk(KERN_INFO "reserve_ram_pages_type failed [mem %#010Lx-%#010Lx], track 0x%lx, req 0x%lx\n",
+				start, end - 1, type, req_type);
 			if (new_type)
 				*new_type = type;
 
@@ -314,9 +313,9 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 
 	err = rbt_memtype_check_insert(new, new_type);
 	if (err) {
-		printk(KERN_INFO "reserve_memtype failed 0x%Lx-0x%Lx, "
-		       "track %s, req %s\n",
-		       start, end, cattr_name(new->type), cattr_name(req_type));
+		printk(KERN_INFO "reserve_memtype failed [mem %#010Lx-%#010Lx], track %s, req %s\n",
+		       start, end - 1,
+		       cattr_name(new->type), cattr_name(req_type));
 		kfree(new);
 		spin_unlock(&memtype_lock);
 
@@ -325,8 +324,8 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 
 	spin_unlock(&memtype_lock);
 
-	dprintk("reserve_memtype added 0x%Lx-0x%Lx, track %s, req %s, ret %s\n",
-		start, end, cattr_name(new->type), cattr_name(req_type),
+	dprintk("reserve_memtype added [mem %#010Lx-%#010Lx], track %s, req %s, ret %s\n",
+		start, end - 1, cattr_name(new->type), cattr_name(req_type),
 		new_type ? cattr_name(*new_type) : "-");
 
 	return err;
@@ -360,14 +359,14 @@ int free_memtype(u64 start, u64 end)
 	spin_unlock(&memtype_lock);
 
 	if (!entry) {
-		printk(KERN_INFO "%s:%d freeing invalid memtype %Lx-%Lx\n",
-			current->comm, current->pid, start, end);
+		printk(KERN_INFO "%s:%d freeing invalid memtype [mem %#010Lx-%#010Lx]\n",
+		       current->comm, current->pid, start, end - 1);
 		return -EINVAL;
 	}
 
 	kfree(entry);
 
-	dprintk("free_memtype request 0x%Lx-0x%Lx\n", start, end);
+	dprintk("free_memtype request [mem %#010Lx-%#010Lx]\n", start, end - 1);
 
 	return 0;
 }
@@ -491,9 +490,8 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size)
 
 	while (cursor < to) {
 		if (!devmem_is_allowed(pfn)) {
-			printk(KERN_INFO
-		"Program %s tried to access /dev/mem between %Lx->%Lx.\n",
-				current->comm, from, to);
+			printk(KERN_INFO "Program %s tried to access /dev/mem between [mem %#010Lx-%#010Lx]\n",
+				current->comm, from, to - 1);
 			return 0;
 		}
 		cursor += PAGE_SIZE;
@@ -554,12 +552,11 @@ int kernel_map_sync_memtype(u64 base, unsigned long size, unsigned long flags)
 				size;
 
 	if (ioremap_change_attr((unsigned long)__va(base), id_sz, flags) < 0) {
-		printk(KERN_INFO
-			"%s:%d ioremap_change_attr failed %s "
-			"for %Lx-%Lx\n",
+		printk(KERN_INFO "%s:%d ioremap_change_attr failed %s "
+			"for [mem %#010Lx-%#010Lx]\n",
 			current->comm, current->pid,
 			cattr_name(flags),
-			base, (unsigned long long)(base + size));
+			base, (unsigned long long)(base + size-1));
 		return -EINVAL;
 	}
 	return 0;
@@ -591,12 +588,11 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
 
 		flags = lookup_memtype(paddr);
 		if (want_flags != flags) {
-			printk(KERN_WARNING
-			"%s:%d map pfn RAM range req %s for %Lx-%Lx, got %s\n",
+			printk(KERN_WARNING "%s:%d map pfn RAM range req %s for [mem %#010Lx-%#010Lx], got %s\n",
 				current->comm, current->pid,
 				cattr_name(want_flags),
 				(unsigned long long)paddr,
-				(unsigned long long)(paddr + size),
+				(unsigned long long)(paddr + size - 1),
 				cattr_name(flags));
 			*vma_prot = __pgprot((pgprot_val(*vma_prot) &
 					      (~_PAGE_CACHE_MASK)) |
@@ -614,11 +610,11 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
 		    !is_new_memtype_allowed(paddr, size, want_flags, flags)) {
 			free_memtype(paddr, paddr + size);
 			printk(KERN_ERR "%s:%d map pfn expected mapping type %s"
-				" for %Lx-%Lx, got %s\n",
+				" for [mem %#010Lx-%#010Lx], got %s\n",
 				current->comm, current->pid,
 				cattr_name(want_flags),
 				(unsigned long long)paddr,
-				(unsigned long long)(paddr + size),
+				(unsigned long long)(paddr + size - 1),
 				cattr_name(flags));
 			return -EINVAL;
 		}
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index efb5b4b93711..732af3a96183 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -176,8 +176,9 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 		return;
 	}
 
-	printk(KERN_INFO "SRAT: Node %u PXM %u %Lx-%Lx\n", node, pxm,
-	       start, end);
+	printk(KERN_INFO "SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]\n",
+	       node, pxm,
+	       (unsigned long long) start, (unsigned long long) end - 1);
 }
 
 void __init acpi_numa_arch_fixup(void) {}
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 90aa2a11a933..af1a177216f1 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -592,11 +592,9 @@ static ssize_t print_nodes_state(enum node_states state, char *buf)
 {
 	int n;
 
-	n = nodelist_scnprintf(buf, PAGE_SIZE, node_states[state]);
-	if (n > 0 && PAGE_SIZE > n + 1) {
-		*(buf + n++) = '\n';
-		*(buf + n++) = '\0';
-	}
+	n = nodelist_scnprintf(buf, PAGE_SIZE-2, node_states[state]);
+	buf[n++] = '\n';
+	buf[n] = '\0';
 	return n;
 }
 
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index aa3642cb8209..0356099ae040 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -167,6 +167,14 @@ config GPIO_PXA
 	help
 	  Say yes here to support the PXA GPIO device
 
+config GPIO_STA2X11
+	bool "STA2x11/ConneXt GPIO support"
+	depends on MFD_STA2X11
+	select GENERIC_IRQ_CHIP
+	help
+	  Say yes here to support the STA2x11/ConneXt GPIO device.
+	  The GPIO module has 128 GPIO pins with alternate functions.
+
 config GPIO_XILINX
 	bool "Xilinx GPIO support"
 	depends on PPC_OF || MICROBLAZE
@@ -180,13 +188,13 @@ config GPIO_VR41XX
 	  Say yes here to support the NEC VR4100 series General-purpose I/O Uint
 
 config GPIO_SCH
-	tristate "Intel SCH/TunnelCreek GPIO"
+	tristate "Intel SCH/TunnelCreek/Centerton GPIO"
 	depends on PCI && X86
 	select MFD_CORE
 	select LPC_SCH
 	help
-	  Say yes here to support GPIO interface on Intel Poulsbo SCH
-	  or Intel Tunnel Creek processor.
+	  Say yes here to support GPIO interface on Intel Poulsbo SCH,
+	  Intel Tunnel Creek processor or Intel Centerton processor.
 	  The Intel SCH contains a total of 14 GPIO pins. Ten GPIOs are
 	  powered by the core power rail and are turned off during sleep
 	  modes (S3 and higher). The remaining four GPIOs are powered by
@@ -195,6 +203,22 @@ config GPIO_SCH
 	  system from the Suspend-to-RAM state.
 	  The Intel Tunnel Creek processor has 5 GPIOs powered by the
 	  core power rail and 9 from suspend power supply.
+	  The Intel Centerton processor has a total of 30 GPIO pins.
+	  Twenty-one are powered by the core power rail and 9 from the
+	  suspend power supply.
+
+config GPIO_ICH
+	tristate "Intel ICH GPIO"
+	depends on PCI && X86
+	select MFD_CORE
+	select LPC_ICH
+	help
+	  Say yes here to support the GPIO functionality of a number of Intel
+	  ICH-based chipsets.  Currently supported devices: ICH6, ICH7, ICH8
+	  ICH9, ICH10, Series 5/3400 (eg Ibex Peak), Series 6/C200 (eg
+	  Cougar Point), NM10 (Tiger Point), and 3100 (Whitmore Lake).
+
+	  If unsure, say N.
 
 config GPIO_VX855
 	tristate "VIA VX855/VX875 GPIO"
diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile
index 07a79e245407..fde36e5e3537 100644
--- a/drivers/gpio/Makefile
+++ b/drivers/gpio/Makefile
@@ -19,6 +19,7 @@ obj-$(CONFIG_ARCH_DAVINCI)	+= gpio-davinci.o
 obj-$(CONFIG_GPIO_EM)		+= gpio-em.o
 obj-$(CONFIG_GPIO_EP93XX)	+= gpio-ep93xx.o
 obj-$(CONFIG_GPIO_GE_FPGA)	+= gpio-ge.o
+obj-$(CONFIG_GPIO_ICH)		+= gpio-ich.o
 obj-$(CONFIG_GPIO_IT8761E)	+= gpio-it8761e.o
 obj-$(CONFIG_GPIO_JANZ_TTL)	+= gpio-janz-ttl.o
 obj-$(CONFIG_ARCH_KS8695)	+= gpio-ks8695.o
@@ -51,6 +52,7 @@ obj-$(CONFIG_PLAT_SAMSUNG)	+= gpio-samsung.o
 obj-$(CONFIG_ARCH_SA1100)	+= gpio-sa1100.o
 obj-$(CONFIG_GPIO_SCH)		+= gpio-sch.o
 obj-$(CONFIG_GPIO_SODAVILLE)	+= gpio-sodaville.o
+obj-$(CONFIG_GPIO_STA2X11)	+= gpio-sta2x11.o
 obj-$(CONFIG_GPIO_STMPE)	+= gpio-stmpe.o
 obj-$(CONFIG_GPIO_SX150X)	+= gpio-sx150x.o
 obj-$(CONFIG_GPIO_TC3589X)	+= gpio-tc3589x.o
diff --git a/drivers/gpio/gpio-ich.c b/drivers/gpio/gpio-ich.c
new file mode 100644
index 000000000000..b7c06517403d
--- /dev/null
+++ b/drivers/gpio/gpio-ich.c
@@ -0,0 +1,419 @@
+/*
+ * Intel ICH6-10, Series 5 and 6 GPIO driver
+ *
+ * Copyright (C) 2010 Extreme Engineering Solutions.
+ *
+ * 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., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/gpio.h>
+#include <linux/platform_device.h>
+#include <linux/mfd/lpc_ich.h>
+
+#define DRV_NAME "gpio_ich"
+
+/*
+ * GPIO register offsets in GPIO I/O space.
+ * Each chunk of 32 GPIOs is manipulated via its own USE_SELx, IO_SELx, and
+ * LVLx registers.  Logic in the read/write functions takes a register and
+ * an absolute bit number and determines the proper register offset and bit
+ * number in that register.  For example, to read the value of GPIO bit 50
+ * the code would access offset ichx_regs[2(=GPIO_LVL)][1(=50/32)],
+ * bit 18 (50%32).
+ */
+enum GPIO_REG {
+	GPIO_USE_SEL = 0,
+	GPIO_IO_SEL,
+	GPIO_LVL,
+};
+
+static const u8 ichx_regs[3][3] = {
+	{0x00, 0x30, 0x40},	/* USE_SEL[1-3] offsets */
+	{0x04, 0x34, 0x44},	/* IO_SEL[1-3] offsets */
+	{0x0c, 0x38, 0x48},	/* LVL[1-3] offsets */
+};
+
+#define ICHX_WRITE(val, reg, base_res)	outl(val, (reg) + (base_res)->start)
+#define ICHX_READ(reg, base_res)	inl((reg) + (base_res)->start)
+
+struct ichx_desc {
+	/* Max GPIO pins the chipset can have */
+	uint ngpio;
+
+	/* Whether the chipset has GPIO in GPE0_STS in the PM IO region */
+	bool uses_gpe0;
+
+	/* USE_SEL is bogus on some chipsets, eg 3100 */
+	u32 use_sel_ignore[3];
+
+	/* Some chipsets have quirks, let these use their own request/get */
+	int (*request)(struct gpio_chip *chip, unsigned offset);
+	int (*get)(struct gpio_chip *chip, unsigned offset);
+};
+
+static struct {
+	spinlock_t lock;
+	struct platform_device *dev;
+	struct gpio_chip chip;
+	struct resource *gpio_base;	/* GPIO IO base */
+	struct resource *pm_base;	/* Power Mangagment IO base */
+	struct ichx_desc *desc;	/* Pointer to chipset-specific description */
+	u32 orig_gpio_ctrl;	/* Orig CTRL value, used to restore on exit */
+} ichx_priv;
+
+static int modparam_gpiobase = -1;	/* dynamic */
+module_param_named(gpiobase, modparam_gpiobase, int, 0444);
+MODULE_PARM_DESC(gpiobase, "The GPIO number base. -1 means dynamic, "
+			   "which is the default.");
+
+static int ichx_write_bit(int reg, unsigned nr, int val, int verify)
+{
+	unsigned long flags;
+	u32 data, tmp;
+	int reg_nr = nr / 32;
+	int bit = nr & 0x1f;
+	int ret = 0;
+
+	spin_lock_irqsave(&ichx_priv.lock, flags);
+
+	data = ICHX_READ(ichx_regs[reg][reg_nr], ichx_priv.gpio_base);
+	if (val)
+		data |= 1 << bit;
+	else
+		data &= ~(1 << bit);
+	ICHX_WRITE(data, ichx_regs[reg][reg_nr], ichx_priv.gpio_base);
+	tmp = ICHX_READ(ichx_regs[reg][reg_nr], ichx_priv.gpio_base);
+	if (verify && data != tmp)
+		ret = -EPERM;
+
+	spin_unlock_irqrestore(&ichx_priv.lock, flags);
+
+	return ret;
+}
+
+static int ichx_read_bit(int reg, unsigned nr)
+{
+	unsigned long flags;
+	u32 data;
+	int reg_nr = nr / 32;
+	int bit = nr & 0x1f;
+
+	spin_lock_irqsave(&ichx_priv.lock, flags);
+
+	data = ICHX_READ(ichx_regs[reg][reg_nr], ichx_priv.gpio_base);
+
+	spin_unlock_irqrestore(&ichx_priv.lock, flags);
+
+	return data & (1 << bit) ? 1 : 0;
+}
+
+static int ichx_gpio_direction_input(struct gpio_chip *gpio, unsigned nr)
+{
+	/*
+	 * Try setting pin as an input and verify it worked since many pins
+	 * are output-only.
+	 */
+	if (ichx_write_bit(GPIO_IO_SEL, nr, 1, 1))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int ichx_gpio_direction_output(struct gpio_chip *gpio, unsigned nr,
+					int val)
+{
+	/* Set GPIO output value. */
+	ichx_write_bit(GPIO_LVL, nr, val, 0);
+
+	/*
+	 * Try setting pin as an output and verify it worked since many pins
+	 * are input-only.
+	 */
+	if (ichx_write_bit(GPIO_IO_SEL, nr, 0, 1))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int ichx_gpio_get(struct gpio_chip *chip, unsigned nr)
+{
+	return ichx_read_bit(GPIO_LVL, nr);
+}
+
+static int ich6_gpio_get(struct gpio_chip *chip, unsigned nr)
+{
+	unsigned long flags;
+	u32 data;
+
+	/*
+	 * GPI 0 - 15 need to be read from the power management registers on
+	 * a ICH6/3100 bridge.
+	 */
+	if (nr < 16) {
+		if (!ichx_priv.pm_base)
+			return -ENXIO;
+
+		spin_lock_irqsave(&ichx_priv.lock, flags);
+
+		/* GPI 0 - 15 are latched, write 1 to clear*/
+		ICHX_WRITE(1 << (16 + nr), 0, ichx_priv.pm_base);
+		data = ICHX_READ(0, ichx_priv.pm_base);
+
+		spin_unlock_irqrestore(&ichx_priv.lock, flags);
+
+		return (data >> 16) & (1 << nr) ? 1 : 0;
+	} else {
+		return ichx_gpio_get(chip, nr);
+	}
+}
+
+static int ichx_gpio_request(struct gpio_chip *chip, unsigned nr)
+{
+	/*
+	 * Note we assume the BIOS properly set a bridge's USE value.  Some
+	 * chips (eg Intel 3100) have bogus USE values though, so first see if
+	 * the chipset's USE value can be trusted for this specific bit.
+	 * If it can't be trusted, assume that the pin can be used as a GPIO.
+	 */
+	if (ichx_priv.desc->use_sel_ignore[nr / 32] & (1 << (nr & 0x1f)))
+		return 1;
+
+	return ichx_read_bit(GPIO_USE_SEL, nr) ? 0 : -ENODEV;
+}
+
+static int ich6_gpio_request(struct gpio_chip *chip, unsigned nr)
+{
+	/*
+	 * Fixups for bits 16 and 17 are necessary on the Intel ICH6/3100
+	 * bridge as they are controlled by USE register bits 0 and 1.  See
+	 * "Table 704 GPIO_USE_SEL1 register" in the i3100 datasheet for
+	 * additional info.
+	 */
+	if (nr == 16 || nr == 17)
+		nr -= 16;
+
+	return ichx_gpio_request(chip, nr);
+}
+
+static void ichx_gpio_set(struct gpio_chip *chip, unsigned nr, int val)
+{
+	ichx_write_bit(GPIO_LVL, nr, val, 0);
+}
+
+static void __devinit ichx_gpiolib_setup(struct gpio_chip *chip)
+{
+	chip->owner = THIS_MODULE;
+	chip->label = DRV_NAME;
+	chip->dev = &ichx_priv.dev->dev;
+
+	/* Allow chip-specific overrides of request()/get() */
+	chip->request = ichx_priv.desc->request ?
+		ichx_priv.desc->request : ichx_gpio_request;
+	chip->get = ichx_priv.desc->get ?
+		ichx_priv.desc->get : ichx_gpio_get;
+
+	chip->set = ichx_gpio_set;
+	chip->direction_input = ichx_gpio_direction_input;
+	chip->direction_output = ichx_gpio_direction_output;
+	chip->base = modparam_gpiobase;
+	chip->ngpio = ichx_priv.desc->ngpio;
+	chip->can_sleep = 0;
+	chip->dbg_show = NULL;
+}
+
+/* ICH6-based, 631xesb-based */
+static struct ichx_desc ich6_desc = {
+	/* Bridges using the ICH6 controller need fixups for GPIO 0 - 17 */
+	.request = ich6_gpio_request,
+	.get = ich6_gpio_get,
+
+	/* GPIO 0-15 are read in the GPE0_STS PM register */
+	.uses_gpe0 = true,
+
+	.ngpio = 50,
+};
+
+/* Intel 3100 */
+static struct ichx_desc i3100_desc = {
+	/*
+	 * Bits 16,17, 20 of USE_SEL and bit 16 of USE_SEL2 always read 0 on
+	 * the Intel 3100.  See "Table 712. GPIO Summary Table" of 3100
+	 * Datasheet for more info.
+	 */
+	.use_sel_ignore = {0x00130000, 0x00010000, 0x0},
+
+	/* The 3100 needs fixups for GPIO 0 - 17 */
+	.request = ich6_gpio_request,
+	.get = ich6_gpio_get,
+
+	/* GPIO 0-15 are read in the GPE0_STS PM register */
+	.uses_gpe0 = true,
+
+	.ngpio = 50,
+};
+
+/* ICH7 and ICH8-based */
+static struct ichx_desc ich7_desc = {
+	.ngpio = 50,
+};
+
+/* ICH9-based */
+static struct ichx_desc ich9_desc = {
+	.ngpio = 61,
+};
+
+/* ICH10-based - Consumer/corporate versions have different amount of GPIO */
+static struct ichx_desc ich10_cons_desc = {
+	.ngpio = 61,
+};
+static struct ichx_desc ich10_corp_desc = {
+	.ngpio = 72,
+};
+
+/* Intel 5 series, 6 series, 3400 series, and C200 series */
+static struct ichx_desc intel5_desc = {
+	.ngpio = 76,
+};
+
+static int __devinit ichx_gpio_probe(struct platform_device *pdev)
+{
+	struct resource *res_base, *res_pm;
+	int err;
+	struct lpc_ich_info *ich_info = pdev->dev.platform_data;
+
+	if (!ich_info)
+		return -ENODEV;
+
+	ichx_priv.dev = pdev;
+
+	switch (ich_info->gpio_version) {
+	case ICH_I3100_GPIO:
+		ichx_priv.desc = &i3100_desc;
+		break;
+	case ICH_V5_GPIO:
+		ichx_priv.desc = &intel5_desc;
+		break;
+	case ICH_V6_GPIO:
+		ichx_priv.desc = &ich6_desc;
+		break;
+	case ICH_V7_GPIO:
+		ichx_priv.desc = &ich7_desc;
+		break;
+	case ICH_V9_GPIO:
+		ichx_priv.desc = &ich9_desc;
+		break;
+	case ICH_V10CORP_GPIO:
+		ichx_priv.desc = &ich10_corp_desc;
+		break;
+	case ICH_V10CONS_GPIO:
+		ichx_priv.desc = &ich10_cons_desc;
+		break;
+	default:
+		return -ENODEV;
+	}
+
+	res_base = platform_get_resource(pdev, IORESOURCE_IO, ICH_RES_GPIO);
+	if (!res_base || !res_base->start || !res_base->end)
+		return -ENODEV;
+
+	if (!request_region(res_base->start, resource_size(res_base),
+				pdev->name))
+		return -EBUSY;
+
+	ichx_priv.gpio_base = res_base;
+
+	/*
+	 * If necessary, determine the I/O address of ACPI/power management
+	 * registers which are needed to read the the GPE0 register for GPI pins
+	 * 0 - 15 on some chipsets.
+	 */
+	if (!ichx_priv.desc->uses_gpe0)
+		goto init;
+
+	res_pm = platform_get_resource(pdev, IORESOURCE_IO, ICH_RES_GPE0);
+	if (!res_pm) {
+		pr_warn("ACPI BAR is unavailable, GPI 0 - 15 unavailable\n");
+		goto init;
+	}
+
+	if (!request_region(res_pm->start, resource_size(res_pm),
+			pdev->name)) {
+		pr_warn("ACPI BAR is busy, GPI 0 - 15 unavailable\n");
+		goto init;
+	}
+
+	ichx_priv.pm_base = res_pm;
+
+init:
+	ichx_gpiolib_setup(&ichx_priv.chip);
+	err = gpiochip_add(&ichx_priv.chip);
+	if (err) {
+		pr_err("Failed to register GPIOs\n");
+		goto add_err;
+	}
+
+	pr_info("GPIO from %d to %d on %s\n", ichx_priv.chip.base,
+	       ichx_priv.chip.base + ichx_priv.chip.ngpio - 1, DRV_NAME);
+
+	return 0;
+
+add_err:
+	release_region(ichx_priv.gpio_base->start,
+			resource_size(ichx_priv.gpio_base));
+	if (ichx_priv.pm_base)
+		release_region(ichx_priv.pm_base->start,
+				resource_size(ichx_priv.pm_base));
+	return err;
+}
+
+static int __devexit ichx_gpio_remove(struct platform_device *pdev)
+{
+	int err;
+
+	err = gpiochip_remove(&ichx_priv.chip);
+	if (err) {
+		dev_err(&pdev->dev, "%s failed, %d\n",
+				"gpiochip_remove()", err);
+		return err;
+	}
+
+	release_region(ichx_priv.gpio_base->start,
+				resource_size(ichx_priv.gpio_base));
+	if (ichx_priv.pm_base)
+		release_region(ichx_priv.pm_base->start,
+				resource_size(ichx_priv.pm_base));
+
+	return 0;
+}
+
+static struct platform_driver ichx_gpio_driver = {
+	.driver		= {
+		.owner	= THIS_MODULE,
+		.name	= DRV_NAME,
+	},
+	.probe		= ichx_gpio_probe,
+	.remove		= __devexit_p(ichx_gpio_remove),
+};
+
+module_platform_driver(ichx_gpio_driver);
+
+MODULE_AUTHOR("Peter Tyser <ptyser@xes-inc.com>");
+MODULE_DESCRIPTION("GPIO interface for Intel ICH series");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:"DRV_NAME);
diff --git a/drivers/gpio/gpio-sch.c b/drivers/gpio/gpio-sch.c
index 8cadf4d683a8..424dce8e3f30 100644
--- a/drivers/gpio/gpio-sch.c
+++ b/drivers/gpio/gpio-sch.c
@@ -232,6 +232,14 @@ static int __devinit sch_gpio_probe(struct platform_device *pdev)
 			sch_gpio_resume.ngpio = 9;
 			break;
 
+		case PCI_DEVICE_ID_INTEL_CENTERTON_ILB:
+			sch_gpio_core.base = 0;
+			sch_gpio_core.ngpio = 21;
+
+			sch_gpio_resume.base = 21;
+			sch_gpio_resume.ngpio = 9;
+			break;
+
 		default:
 			return -ENODEV;
 	}
diff --git a/drivers/gpio/gpio-sta2x11.c b/drivers/gpio/gpio-sta2x11.c
new file mode 100644
index 000000000000..38416be8ba11
--- /dev/null
+++ b/drivers/gpio/gpio-sta2x11.c
@@ -0,0 +1,435 @@
+/*
+ * STMicroelectronics ConneXt (STA2X11) GPIO driver
+ *
+ * Copyright 2012 ST Microelectronics (Alessandro Rubini)
+ * Based on gpio-ml-ioh.c, Copyright 2010 OKI Semiconductors Ltd.
+ * Also based on previous sta2x11 work, Copyright 2011 Wind River Systems, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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/module.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/gpio.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/mfd/sta2x11-mfd.h>
+
+struct gsta_regs {
+	u32 dat;		/* 0x00 */
+	u32 dats;
+	u32 datc;
+	u32 pdis;
+	u32 dir;		/* 0x10 */
+	u32 dirs;
+	u32 dirc;
+	u32 unused_1c;
+	u32 afsela;		/* 0x20 */
+	u32 unused_24[7];
+	u32 rimsc;		/* 0x40 */
+	u32 fimsc;
+	u32 is;
+	u32 ic;
+};
+
+struct gsta_gpio {
+	spinlock_t			lock;
+	struct device			*dev;
+	void __iomem			*reg_base;
+	struct gsta_regs __iomem	*regs[GSTA_NR_BLOCKS];
+	struct gpio_chip		gpio;
+	int				irq_base;
+	/* FIXME: save the whole config here (AF, ...) */
+	unsigned			irq_type[GSTA_NR_GPIO];
+};
+
+static inline struct gsta_regs __iomem *__regs(struct gsta_gpio *chip, int nr)
+{
+	return chip->regs[nr / GSTA_GPIO_PER_BLOCK];
+}
+
+static inline u32 __bit(int nr)
+{
+	return 1U << (nr % GSTA_GPIO_PER_BLOCK);
+}
+
+/*
+ * gpio methods
+ */
+
+static void gsta_gpio_set(struct gpio_chip *gpio, unsigned nr, int val)
+{
+	struct gsta_gpio *chip = container_of(gpio, struct gsta_gpio, gpio);
+	struct gsta_regs __iomem *regs = __regs(chip, nr);
+	u32 bit = __bit(nr);
+
+	if (val)
+		writel(bit, &regs->dats);
+	else
+		writel(bit, &regs->datc);
+}
+
+static int gsta_gpio_get(struct gpio_chip *gpio, unsigned nr)
+{
+	struct gsta_gpio *chip = container_of(gpio, struct gsta_gpio, gpio);
+	struct gsta_regs __iomem *regs = __regs(chip, nr);
+	u32 bit = __bit(nr);
+
+	return readl(&regs->dat) & bit;
+}
+
+static int gsta_gpio_direction_output(struct gpio_chip *gpio, unsigned nr,
+				      int val)
+{
+	struct gsta_gpio *chip = container_of(gpio, struct gsta_gpio, gpio);
+	struct gsta_regs __iomem *regs = __regs(chip, nr);
+	u32 bit = __bit(nr);
+
+	writel(bit, &regs->dirs);
+	/* Data register after direction, otherwise pullup/down is selected */
+	if (val)
+		writel(bit, &regs->dats);
+	else
+		writel(bit, &regs->datc);
+	return 0;
+}
+
+static int gsta_gpio_direction_input(struct gpio_chip *gpio, unsigned nr)
+{
+	struct gsta_gpio *chip = container_of(gpio, struct gsta_gpio, gpio);
+	struct gsta_regs __iomem *regs = __regs(chip, nr);
+	u32 bit = __bit(nr);
+
+	writel(bit, &regs->dirc);
+	return 0;
+}
+
+static int gsta_gpio_to_irq(struct gpio_chip *gpio, unsigned offset)
+{
+	struct gsta_gpio *chip = container_of(gpio, struct gsta_gpio, gpio);
+	return chip->irq_base + offset;
+}
+
+static void gsta_gpio_setup(struct gsta_gpio *chip) /* called from probe */
+{
+	struct gpio_chip *gpio = &chip->gpio;
+
+	/*
+	 * ARCH_NR_GPIOS is currently 256 and dynamic allocation starts
+	 * from the end. However, for compatibility, we need the first
+	 * ConneXt device to start from gpio 0: it's the main chipset
+	 * on most boards so documents and drivers assume gpio0..gpio127
+	 */
+	static int gpio_base;
+
+	gpio->label = dev_name(chip->dev);
+	gpio->owner = THIS_MODULE;
+	gpio->direction_input = gsta_gpio_direction_input;
+	gpio->get = gsta_gpio_get;
+	gpio->direction_output = gsta_gpio_direction_output;
+	gpio->set = gsta_gpio_set;
+	gpio->dbg_show = NULL;
+	gpio->base = gpio_base;
+	gpio->ngpio = GSTA_NR_GPIO;
+	gpio->can_sleep = 0;
+	gpio->to_irq = gsta_gpio_to_irq;
+
+	/*
+	 * After the first device, turn to dynamic gpio numbers.
+	 * For example, with ARCH_NR_GPIOS = 256 we can fit two cards
+	 */
+	if (!gpio_base)
+		gpio_base = -1;
+}
+
+/*
+ * Special method: alternate functions and pullup/pulldown. This is only
+ * invoked on startup to configure gpio's according to platform data.
+ * FIXME : this functionality shall be managed (and exported to other drivers)
+ * via the pin control subsystem.
+ */
+static void gsta_set_config(struct gsta_gpio *chip, int nr, unsigned cfg)
+{
+	struct gsta_regs __iomem *regs = __regs(chip, nr);
+	unsigned long flags;
+	u32 bit = __bit(nr);
+	u32 val;
+	int err = 0;
+
+	pr_info("%s: %p %i %i\n", __func__, chip, nr, cfg);
+
+	if (cfg == PINMUX_TYPE_NONE)
+		return;
+
+	/* Alternate function or not? */
+	spin_lock_irqsave(&chip->lock, flags);
+	val = readl(&regs->afsela);
+	if (cfg == PINMUX_TYPE_FUNCTION)
+		val |= bit;
+	else
+		val &= ~bit;
+	writel(val | bit, &regs->afsela);
+	if (cfg == PINMUX_TYPE_FUNCTION) {
+		spin_unlock_irqrestore(&chip->lock, flags);
+		return;
+	}
+
+	/* not alternate function: set details */
+	switch (cfg) {
+	case PINMUX_TYPE_OUTPUT_LOW:
+		writel(bit, &regs->dirs);
+		writel(bit, &regs->datc);
+		break;
+	case PINMUX_TYPE_OUTPUT_HIGH:
+		writel(bit, &regs->dirs);
+		writel(bit, &regs->dats);
+		break;
+	case PINMUX_TYPE_INPUT:
+		writel(bit, &regs->dirc);
+		val = readl(&regs->pdis) | bit;
+		writel(val, &regs->pdis);
+		break;
+	case PINMUX_TYPE_INPUT_PULLUP:
+		writel(bit, &regs->dirc);
+		val = readl(&regs->pdis) & ~bit;
+		writel(val, &regs->pdis);
+		writel(bit, &regs->dats);
+		break;
+	case PINMUX_TYPE_INPUT_PULLDOWN:
+		writel(bit, &regs->dirc);
+		val = readl(&regs->pdis) & ~bit;
+		writel(val, &regs->pdis);
+		writel(bit, &regs->datc);
+		break;
+	default:
+		err = 1;
+	}
+	spin_unlock_irqrestore(&chip->lock, flags);
+	if (err)
+		pr_err("%s: chip %p, pin %i, cfg %i is invalid\n",
+		       __func__, chip, nr, cfg);
+}
+
+/*
+ * Irq methods
+ */
+
+static void gsta_irq_disable(struct irq_data *data)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(data);
+	struct gsta_gpio *chip = gc->private;
+	int nr = data->irq - chip->irq_base;
+	struct gsta_regs __iomem *regs = __regs(chip, nr);
+	u32 bit = __bit(nr);
+	u32 val;
+	unsigned long flags;
+
+	spin_lock_irqsave(&chip->lock, flags);
+	if (chip->irq_type[nr] & IRQ_TYPE_EDGE_RISING) {
+		val = readl(&regs->rimsc) & ~bit;
+		writel(val, &regs->rimsc);
+	}
+	if (chip->irq_type[nr] & IRQ_TYPE_EDGE_FALLING) {
+		val = readl(&regs->fimsc) & ~bit;
+		writel(val, &regs->fimsc);
+	}
+	spin_unlock_irqrestore(&chip->lock, flags);
+	return;
+}
+
+static void gsta_irq_enable(struct irq_data *data)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(data);
+	struct gsta_gpio *chip = gc->private;
+	int nr = data->irq - chip->irq_base;
+	struct gsta_regs __iomem *regs = __regs(chip, nr);
+	u32 bit = __bit(nr);
+	u32 val;
+	int type;
+	unsigned long flags;
+
+	type = chip->irq_type[nr];
+
+	spin_lock_irqsave(&chip->lock, flags);
+	val = readl(&regs->rimsc);
+	if (type & IRQ_TYPE_EDGE_RISING)
+		writel(val | bit, &regs->rimsc);
+	else
+		writel(val & ~bit, &regs->rimsc);
+	val = readl(&regs->rimsc);
+	if (type & IRQ_TYPE_EDGE_FALLING)
+		writel(val | bit, &regs->fimsc);
+	else
+		writel(val & ~bit, &regs->fimsc);
+	spin_unlock_irqrestore(&chip->lock, flags);
+	return;
+}
+
+static int gsta_irq_type(struct irq_data *d, unsigned int type)
+{
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
+	struct gsta_gpio *chip = gc->private;
+	int nr = d->irq - chip->irq_base;
+
+	/* We only support edge interrupts */
+	if (!(type & (IRQ_TYPE_EDGE_RISING | IRQ_TYPE_EDGE_FALLING))) {
+		pr_debug("%s: unsupported type 0x%x\n", __func__, type);
+		return -EINVAL;
+	}
+
+	chip->irq_type[nr] = type; /* used for enable/disable */
+
+	gsta_irq_enable(d);
+	return 0;
+}
+
+static irqreturn_t gsta_gpio_handler(int irq, void *dev_id)
+{
+	struct gsta_gpio *chip = dev_id;
+	struct gsta_regs __iomem *regs;
+	u32 is;
+	int i, nr, base;
+	irqreturn_t ret = IRQ_NONE;
+
+	for (i = 0; i < GSTA_NR_BLOCKS; i++) {
+		regs = chip->regs[i];
+		base = chip->irq_base + i * GSTA_GPIO_PER_BLOCK;
+		while ((is = readl(&regs->is))) {
+			nr = __ffs(is);
+			irq = base + nr;
+			generic_handle_irq(irq);
+			writel(1 << nr, &regs->ic);
+			ret = IRQ_HANDLED;
+		}
+	}
+	return ret;
+}
+
+static __devinit void gsta_alloc_irq_chip(struct gsta_gpio *chip)
+{
+	struct irq_chip_generic *gc;
+	struct irq_chip_type *ct;
+
+	gc = irq_alloc_generic_chip(KBUILD_MODNAME, 1, chip->irq_base,
+				     chip->reg_base, handle_simple_irq);
+	gc->private = chip;
+	ct = gc->chip_types;
+
+	ct->chip.irq_set_type = gsta_irq_type;
+	ct->chip.irq_disable = gsta_irq_disable;
+	ct->chip.irq_enable = gsta_irq_enable;
+
+	/* FIXME: this makes at most 32 interrupts. Request 0 by now */
+	irq_setup_generic_chip(gc, 0 /* IRQ_MSK(GSTA_GPIO_PER_BLOCK) */, 0,
+			       IRQ_NOREQUEST | IRQ_NOPROBE, 0);
+
+	/* Set up all all 128 interrupts: code from setup_generic_chip */
+	{
+		struct irq_chip_type *ct = gc->chip_types;
+		int i, j;
+		for (j = 0; j < GSTA_NR_GPIO; j++) {
+			i = chip->irq_base + j;
+			irq_set_chip_and_handler(i, &ct->chip, ct->handler);
+			irq_set_chip_data(i, gc);
+			irq_modify_status(i, IRQ_NOREQUEST | IRQ_NOPROBE, 0);
+		}
+		gc->irq_cnt = i - gc->irq_base;
+	}
+}
+
+/* The platform device used here is instantiated by the MFD device */
+static int __devinit gsta_probe(struct platform_device *dev)
+{
+	int i, err;
+	struct pci_dev *pdev;
+	struct sta2x11_gpio_pdata *gpio_pdata;
+	struct gsta_gpio *chip;
+	struct resource *res;
+
+	pdev = *(struct pci_dev **)(dev->dev.platform_data);
+	gpio_pdata = dev_get_platdata(&pdev->dev);
+
+	if (gpio_pdata == NULL)
+		dev_err(&dev->dev, "no gpio config\n");
+	pr_debug("gpio config: %p\n", gpio_pdata);
+
+	res = platform_get_resource(dev, IORESOURCE_MEM, 0);
+
+	chip = devm_kzalloc(&dev->dev, sizeof(*chip), GFP_KERNEL);
+	chip->dev = &dev->dev;
+	chip->reg_base = devm_request_and_ioremap(&dev->dev, res);
+
+	for (i = 0; i < GSTA_NR_BLOCKS; i++) {
+		chip->regs[i] = chip->reg_base + i * 4096;
+		/* disable all irqs */
+		writel(0, &chip->regs[i]->rimsc);
+		writel(0, &chip->regs[i]->fimsc);
+		writel(~0, &chip->regs[i]->ic);
+	}
+	spin_lock_init(&chip->lock);
+	gsta_gpio_setup(chip);
+	for (i = 0; i < GSTA_NR_GPIO; i++)
+		gsta_set_config(chip, i, gpio_pdata->pinconfig[i]);
+
+	/* 384 was used in previous code: be compatible for other drivers */
+	err = irq_alloc_descs(-1, 384, GSTA_NR_GPIO, NUMA_NO_NODE);
+	if (err < 0) {
+		dev_warn(&dev->dev, "sta2x11 gpio: Can't get irq base (%i)\n",
+			 -err);
+		return err;
+	}
+	chip->irq_base = err;
+	gsta_alloc_irq_chip(chip);
+
+	err = request_irq(pdev->irq, gsta_gpio_handler,
+			     IRQF_SHARED, KBUILD_MODNAME, chip);
+	if (err < 0) {
+		dev_err(&dev->dev, "sta2x11 gpio: Can't request irq (%i)\n",
+			-err);
+		goto err_free_descs;
+	}
+
+	err = gpiochip_add(&chip->gpio);
+	if (err < 0) {
+		dev_err(&dev->dev, "sta2x11 gpio: Can't register (%i)\n",
+			-err);
+		goto err_free_irq;
+	}
+
+	platform_set_drvdata(dev, chip);
+	return 0;
+
+err_free_irq:
+	free_irq(pdev->irq, chip);
+err_free_descs:
+	irq_free_descs(chip->irq_base, GSTA_NR_GPIO);
+	return err;
+}
+
+static struct platform_driver sta2x11_gpio_platform_driver = {
+	.driver = {
+		.name	= "sta2x11-gpio",
+		.owner	= THIS_MODULE,
+	},
+	.probe = gsta_probe,
+};
+
+module_platform_driver(sta2x11_gpio_platform_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("sta2x11_gpio GPIO driver");
diff --git a/drivers/gpio/gpio-tps65910.c b/drivers/gpio/gpio-tps65910.c
index 7eef648a3351..c1ad2884f2ed 100644
--- a/drivers/gpio/gpio-tps65910.c
+++ b/drivers/gpio/gpio-tps65910.c
@@ -18,14 +18,27 @@
 #include <linux/errno.h>
 #include <linux/gpio.h>
 #include <linux/i2c.h>
+#include <linux/platform_device.h>
 #include <linux/mfd/tps65910.h>
+#include <linux/of_device.h>
+
+struct tps65910_gpio {
+	struct gpio_chip gpio_chip;
+	struct tps65910 *tps65910;
+};
+
+static inline struct tps65910_gpio *to_tps65910_gpio(struct gpio_chip *chip)
+{
+	return container_of(chip, struct tps65910_gpio, gpio_chip);
+}
 
 static int tps65910_gpio_get(struct gpio_chip *gc, unsigned offset)
 {
-	struct tps65910 *tps65910 = container_of(gc, struct tps65910, gpio);
-	uint8_t val;
+	struct tps65910_gpio *tps65910_gpio = to_tps65910_gpio(gc);
+	struct tps65910 *tps65910 = tps65910_gpio->tps65910;
+	unsigned int val;
 
-	tps65910->read(tps65910, TPS65910_GPIO0 + offset, 1, &val);
+	tps65910_reg_read(tps65910, TPS65910_GPIO0 + offset, &val);
 
 	if (val & GPIO_STS_MASK)
 		return 1;
@@ -36,83 +49,170 @@ static int tps65910_gpio_get(struct gpio_chip *gc, unsigned offset)
 static void tps65910_gpio_set(struct gpio_chip *gc, unsigned offset,
 			      int value)
 {
-	struct tps65910 *tps65910 = container_of(gc, struct tps65910, gpio);
+	struct tps65910_gpio *tps65910_gpio = to_tps65910_gpio(gc);
+	struct tps65910 *tps65910 = tps65910_gpio->tps65910;
 
 	if (value)
-		tps65910_set_bits(tps65910, TPS65910_GPIO0 + offset,
+		tps65910_reg_set_bits(tps65910, TPS65910_GPIO0 + offset,
 						GPIO_SET_MASK);
 	else
-		tps65910_clear_bits(tps65910, TPS65910_GPIO0 + offset,
+		tps65910_reg_clear_bits(tps65910, TPS65910_GPIO0 + offset,
 						GPIO_SET_MASK);
 }
 
 static int tps65910_gpio_output(struct gpio_chip *gc, unsigned offset,
 				int value)
 {
-	struct tps65910 *tps65910 = container_of(gc, struct tps65910, gpio);
+	struct tps65910_gpio *tps65910_gpio = to_tps65910_gpio(gc);
+	struct tps65910 *tps65910 = tps65910_gpio->tps65910;
 
 	/* Set the initial value */
 	tps65910_gpio_set(gc, offset, value);
 
-	return tps65910_set_bits(tps65910, TPS65910_GPIO0 + offset,
+	return tps65910_reg_set_bits(tps65910, TPS65910_GPIO0 + offset,
 						GPIO_CFG_MASK);
 }
 
 static int tps65910_gpio_input(struct gpio_chip *gc, unsigned offset)
 {
-	struct tps65910 *tps65910 = container_of(gc, struct tps65910, gpio);
+	struct tps65910_gpio *tps65910_gpio = to_tps65910_gpio(gc);
+	struct tps65910 *tps65910 = tps65910_gpio->tps65910;
 
-	return tps65910_clear_bits(tps65910, TPS65910_GPIO0 + offset,
+	return tps65910_reg_clear_bits(tps65910, TPS65910_GPIO0 + offset,
 						GPIO_CFG_MASK);
 }
 
-void tps65910_gpio_init(struct tps65910 *tps65910, int gpio_base)
+#ifdef CONFIG_OF
+static struct tps65910_board *tps65910_parse_dt_for_gpio(struct device *dev,
+		struct tps65910 *tps65910, int chip_ngpio)
 {
+	struct tps65910_board *tps65910_board = tps65910->of_plat_data;
+	unsigned int prop_array[TPS6591X_MAX_NUM_GPIO];
+	int ngpio = min(chip_ngpio, TPS6591X_MAX_NUM_GPIO);
 	int ret;
-	struct tps65910_board *board_data;
+	int idx;
+
+	tps65910_board->gpio_base = -1;
+	ret = of_property_read_u32_array(tps65910->dev->of_node,
+			"ti,en-gpio-sleep", prop_array, ngpio);
+	if (ret < 0) {
+		dev_dbg(dev, "ti,en-gpio-sleep not specified\n");
+		return tps65910_board;
+	}
 
-	if (!gpio_base)
-		return;
+	for (idx = 0; idx < ngpio; idx++)
+		tps65910_board->en_gpio_sleep[idx] = (prop_array[idx] != 0);
 
-	tps65910->gpio.owner		= THIS_MODULE;
-	tps65910->gpio.label		= tps65910->i2c_client->name;
-	tps65910->gpio.dev		= tps65910->dev;
-	tps65910->gpio.base		= gpio_base;
+	return tps65910_board;
+}
+#else
+static struct tps65910_board *tps65910_parse_dt_for_gpio(struct device *dev,
+		struct tps65910 *tps65910, int chip_ngpio)
+{
+	return NULL;
+}
+#endif
+
+static int __devinit tps65910_gpio_probe(struct platform_device *pdev)
+{
+	struct tps65910 *tps65910 = dev_get_drvdata(pdev->dev.parent);
+	struct tps65910_board *pdata = dev_get_platdata(tps65910->dev);
+	struct tps65910_gpio *tps65910_gpio;
+	int ret;
+	int i;
+
+	tps65910_gpio = devm_kzalloc(&pdev->dev,
+				sizeof(*tps65910_gpio), GFP_KERNEL);
+	if (!tps65910_gpio) {
+		dev_err(&pdev->dev, "Could not allocate tps65910_gpio\n");
+		return -ENOMEM;
+	}
+
+	tps65910_gpio->tps65910 = tps65910;
+
+	tps65910_gpio->gpio_chip.owner = THIS_MODULE;
+	tps65910_gpio->gpio_chip.label = tps65910->i2c_client->name;
 
 	switch(tps65910_chip_id(tps65910)) {
 	case TPS65910:
-		tps65910->gpio.ngpio	= TPS65910_NUM_GPIO;
+		tps65910_gpio->gpio_chip.ngpio = TPS65910_NUM_GPIO;
 		break;
 	case TPS65911:
-		tps65910->gpio.ngpio	= TPS65911_NUM_GPIO;
+		tps65910_gpio->gpio_chip.ngpio = TPS65911_NUM_GPIO;
 		break;
 	default:
-		return;
+		return -EINVAL;
+	}
+	tps65910_gpio->gpio_chip.can_sleep = 1;
+	tps65910_gpio->gpio_chip.direction_input = tps65910_gpio_input;
+	tps65910_gpio->gpio_chip.direction_output = tps65910_gpio_output;
+	tps65910_gpio->gpio_chip.set	= tps65910_gpio_set;
+	tps65910_gpio->gpio_chip.get	= tps65910_gpio_get;
+	tps65910_gpio->gpio_chip.dev = &pdev->dev;
+	if (pdata && pdata->gpio_base)
+		tps65910_gpio->gpio_chip.base = pdata->gpio_base;
+	else
+		tps65910_gpio->gpio_chip.base = -1;
+
+	if (!pdata && tps65910->dev->of_node)
+		pdata = tps65910_parse_dt_for_gpio(&pdev->dev, tps65910,
+			tps65910_gpio->gpio_chip.ngpio);
+
+	if (!pdata)
+		goto skip_init;
+
+	/* Configure sleep control for gpios if provided */
+	for (i = 0; i < tps65910_gpio->gpio_chip.ngpio; ++i) {
+		if (!pdata->en_gpio_sleep[i])
+			continue;
+
+		ret = tps65910_reg_set_bits(tps65910,
+			TPS65910_GPIO0 + i, GPIO_SLEEP_MASK);
+		if (ret < 0)
+			dev_warn(tps65910->dev,
+				"GPIO Sleep setting failed with err %d\n", ret);
 	}
-	tps65910->gpio.can_sleep	= 1;
-
-	tps65910->gpio.direction_input	= tps65910_gpio_input;
-	tps65910->gpio.direction_output	= tps65910_gpio_output;
-	tps65910->gpio.set		= tps65910_gpio_set;
-	tps65910->gpio.get		= tps65910_gpio_get;
-
-	/* Configure sleep control for gpios */
-	board_data = dev_get_platdata(tps65910->dev);
-	if (board_data) {
-		int i;
-		for (i = 0; i < tps65910->gpio.ngpio; ++i) {
-			if (board_data->en_gpio_sleep[i]) {
-				ret = tps65910_set_bits(tps65910,
-					TPS65910_GPIO0 + i, GPIO_SLEEP_MASK);
-				if (ret < 0)
-					dev_warn(tps65910->dev,
-						"GPIO Sleep setting failed\n");
-			}
-		}
+
+skip_init:
+	ret = gpiochip_add(&tps65910_gpio->gpio_chip);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Could not register gpiochip, %d\n", ret);
+		return ret;
 	}
 
-	ret = gpiochip_add(&tps65910->gpio);
+	platform_set_drvdata(pdev, tps65910_gpio);
+
+	return ret;
+}
+
+static int __devexit tps65910_gpio_remove(struct platform_device *pdev)
+{
+	struct tps65910_gpio *tps65910_gpio = platform_get_drvdata(pdev);
 
-	if (ret)
-		dev_warn(tps65910->dev, "GPIO registration failed: %d\n", ret);
+	return gpiochip_remove(&tps65910_gpio->gpio_chip);
 }
+
+static struct platform_driver tps65910_gpio_driver = {
+	.driver.name    = "tps65910-gpio",
+	.driver.owner   = THIS_MODULE,
+	.probe		= tps65910_gpio_probe,
+	.remove		= __devexit_p(tps65910_gpio_remove),
+};
+
+static int __init tps65910_gpio_init(void)
+{
+	return platform_driver_register(&tps65910_gpio_driver);
+}
+subsys_initcall(tps65910_gpio_init);
+
+static void __exit tps65910_gpio_exit(void)
+{
+	platform_driver_unregister(&tps65910_gpio_driver);
+}
+module_exit(tps65910_gpio_exit);
+
+MODULE_AUTHOR("Graeme Gregory <gg@slimlogic.co.uk>");
+MODULE_AUTHOR("Jorge Eduardo Candelaria jedu@slimlogic.co.uk>");
+MODULE_DESCRIPTION("GPIO interface for TPS65910/TPS6511 PMICs");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:tps65910-gpio");
diff --git a/drivers/gpio/gpio-wm831x.c b/drivers/gpio/gpio-wm831x.c
index deb949e75ec1..e56a2165641c 100644
--- a/drivers/gpio/gpio-wm831x.c
+++ b/drivers/gpio/gpio-wm831x.c
@@ -102,10 +102,8 @@ static int wm831x_gpio_to_irq(struct gpio_chip *chip, unsigned offset)
 	struct wm831x_gpio *wm831x_gpio = to_wm831x_gpio(chip);
 	struct wm831x *wm831x = wm831x_gpio->wm831x;
 
-	if (!wm831x->irq_base)
-		return -EINVAL;
-
-	return wm831x->irq_base + WM831X_IRQ_GPIO_1 + offset;
+	return irq_create_mapping(wm831x->irq_domain,
+				  WM831X_IRQ_GPIO_1 + offset);
 }
 
 static int wm831x_gpio_set_debounce(struct gpio_chip *chip, unsigned offset,
diff --git a/drivers/input/misc/wm831x-on.c b/drivers/input/misc/wm831x-on.c
index 47f18d6bce46..6790a812a1db 100644
--- a/drivers/input/misc/wm831x-on.c
+++ b/drivers/input/misc/wm831x-on.c
@@ -73,7 +73,7 @@ static int __devinit wm831x_on_probe(struct platform_device *pdev)
 {
 	struct wm831x *wm831x = dev_get_drvdata(pdev->dev.parent);
 	struct wm831x_on *wm831x_on;
-	int irq = platform_get_irq(pdev, 0);
+	int irq = wm831x_irq(wm831x, platform_get_irq(pdev, 0));
 	int ret;
 
 	wm831x_on = kzalloc(sizeof(struct wm831x_on), GFP_KERNEL);
diff --git a/drivers/input/touchscreen/wm831x-ts.c b/drivers/input/touchscreen/wm831x-ts.c
index 4bc851a9dc3d..e83410721e38 100644
--- a/drivers/input/touchscreen/wm831x-ts.c
+++ b/drivers/input/touchscreen/wm831x-ts.c
@@ -260,15 +260,16 @@ static __devinit int wm831x_ts_probe(struct platform_device *pdev)
 	 * If we have a direct IRQ use it, otherwise use the interrupt
 	 * from the WM831x IRQ controller.
 	 */
+	wm831x_ts->data_irq = wm831x_irq(wm831x,
+					 platform_get_irq_byname(pdev,
+								 "TCHDATA"));
 	if (pdata && pdata->data_irq)
 		wm831x_ts->data_irq = pdata->data_irq;
-	else
-		wm831x_ts->data_irq = platform_get_irq_byname(pdev, "TCHDATA");
 
+	wm831x_ts->pd_irq = wm831x_irq(wm831x,
+				       platform_get_irq_byname(pdev, "TCHPD"));
 	if (pdata && pdata->pd_irq)
 		wm831x_ts->pd_irq = pdata->pd_irq;
-	else
-		wm831x_ts->pd_irq = platform_get_irq_byname(pdev, "TCHPD");
 
 	if (pdata)
 		wm831x_ts->pressure = pdata->pressure;
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index f4b4dad77391..e129c820df7d 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -106,6 +106,19 @@ config UCB1400_CORE
 	  To compile this driver as a module, choose M here: the
 	  module will be called ucb1400_core.
 
+config MFD_LM3533
+	tristate "LM3533 Lighting Power chip"
+	depends on I2C
+	select MFD_CORE
+	select REGMAP_I2C
+	help
+	  Say yes here to enable support for National Semiconductor / TI
+	  LM3533 Lighting Power chips.
+
+	  This driver provides common support for accessing the device;
+	  additional drivers must be enabled in order to use the LED,
+	  backlight or ambient-light-sensor functionality of the device.
+
 config TPS6105X
 	tristate "TPS61050/61052 Boost Converters"
 	depends on I2C
@@ -177,8 +190,8 @@ config MFD_TPS65910
 	bool "TPS65910 Power Management chip"
 	depends on I2C=y && GPIOLIB
 	select MFD_CORE
-	select GPIO_TPS65910
 	select REGMAP_I2C
+	select IRQ_DOMAIN
 	help
 	  if you say yes here you get support for the TPS65910 series of
 	  Power Management chips.
@@ -409,6 +422,19 @@ config PMIC_ADP5520
 	  individual components like LCD backlight, LEDs, GPIOs and Kepad
 	  under the corresponding menus.
 
+config MFD_MAX77693
+	bool "Maxim Semiconductor MAX77693 PMIC Support"
+	depends on I2C=y && GENERIC_HARDIRQS
+	select MFD_CORE
+	select REGMAP_I2C
+	help
+	  Say yes here to support for Maxim Semiconductor MAX77693.
+	  This is a companion Power Management IC with Flash, Haptic, Charger,
+	  and MUIC(Micro USB Interface Controller) controls on chip.
+	  This driver provides common support for accessing the device;
+	  additional drivers must be enabled in order to use the functionality
+	  of the device.
+
 config MFD_MAX8925
 	bool "Maxim Semiconductor MAX8925 PMIC Support"
 	depends on I2C=y && GENERIC_HARDIRQS
@@ -454,9 +480,9 @@ config MFD_S5M_CORE
 	 of the device
 
 config MFD_WM8400
-	tristate "Support Wolfson Microelectronics WM8400"
+	bool "Support Wolfson Microelectronics WM8400"
 	select MFD_CORE
-	depends on I2C
+	depends on I2C=y
 	select REGMAP_I2C
 	help
 	  Support for the Wolfson Microelecronics WM8400 PMIC and audio
@@ -473,6 +499,7 @@ config MFD_WM831X_I2C
 	select MFD_CORE
 	select MFD_WM831X
 	select REGMAP_I2C
+	select IRQ_DOMAIN
 	depends on I2C=y && GENERIC_HARDIRQS
 	help
 	  Support for the Wolfson Microelecronics WM831x and WM832x PMICs
@@ -485,6 +512,7 @@ config MFD_WM831X_SPI
 	select MFD_CORE
 	select MFD_WM831X
 	select REGMAP_SPI
+	select IRQ_DOMAIN
 	depends on SPI_MASTER && GENERIC_HARDIRQS
 	help
 	  Support for the Wolfson Microelecronics WM831x and WM832x PMICs
@@ -597,17 +625,32 @@ config MFD_MC13783
 	tristate
 
 config MFD_MC13XXX
-	tristate "Support Freescale MC13783 and MC13892"
-	depends on SPI_MASTER
+	tristate
+	depends on SPI_MASTER || I2C
 	select MFD_CORE
 	select MFD_MC13783
 	help
-	  Support for the Freescale (Atlas) PMIC and audio CODECs
-	  MC13783 and MC13892.
-	  This driver provides common support for accessing  the device,
+	  Enable support for the Freescale MC13783 and MC13892 PMICs.
+	  This driver provides common support for accessing the device,
 	  additional drivers must be enabled in order to use the
 	  functionality of the device.
 
+config MFD_MC13XXX_SPI
+	tristate "Freescale MC13783 and MC13892 SPI interface"
+	depends on SPI_MASTER
+	select REGMAP_SPI
+	select MFD_MC13XXX
+	help
+	  Select this if your MC13xxx is connected via an SPI bus.
+
+config MFD_MC13XXX_I2C
+	tristate "Freescale MC13892 I2C interface"
+	depends on I2C
+	select REGMAP_I2C
+	select MFD_MC13XXX
+	help
+	  Select this if your MC13xxx is connected via an I2C bus.
+
 config ABX500_CORE
 	bool "ST-Ericsson ABX500 Mixed Signal Circuit register functions"
 	default y if ARCH_U300 || ARCH_U8500
@@ -651,7 +694,7 @@ config EZX_PCAP
 
 config AB8500_CORE
 	bool "ST-Ericsson AB8500 Mixed Signal Power Management chip"
-	depends on GENERIC_HARDIRQS && ABX500_CORE
+	depends on GENERIC_HARDIRQS && ABX500_CORE && MFD_DB8500_PRCMU
 	select MFD_CORE
 	help
 	  Select this option to enable access to AB8500 power management
@@ -722,6 +765,16 @@ config LPC_SCH
 	  LPC bridge function of the Intel SCH provides support for
 	  System Management Bus and General Purpose I/O.
 
+config LPC_ICH
+	tristate "Intel ICH LPC"
+	depends on PCI
+	select MFD_CORE
+	help
+	  The LPC bridge function of the Intel ICH provides support for
+	  many functional units. This driver provides needed support for
+	  other drivers to control these functions, currently GPIO and
+	  watchdog.
+
 config MFD_RDC321X
 	tristate "Support for RDC-R321x southbridge"
 	select MFD_CORE
@@ -854,6 +907,11 @@ config MFD_RC5T583
 	  Additional drivers must be enabled in order to use the
 	  different functionality of the device.
 
+config MFD_STA2X11
+	bool "STA2X11 multi function device support"
+	depends on STA2X11
+	select MFD_CORE
+
 config MFD_ANATOP
 	bool "Support for Freescale i.MX on-chip ANATOP controller"
 	depends on SOC_IMX6Q
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index 43672b87805a..75f6ed68a4b9 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -15,6 +15,7 @@ obj-$(CONFIG_MFD_DAVINCI_VOICECODEC)	+= davinci_voicecodec.o
 obj-$(CONFIG_MFD_DM355EVM_MSP)	+= dm355evm_msp.o
 obj-$(CONFIG_MFD_TI_SSP)	+= ti-ssp.o
 
+obj-$(CONFIG_MFD_STA2X11)	+= sta2x11-mfd.o
 obj-$(CONFIG_MFD_STMPE)		+= stmpe.o
 obj-$(CONFIG_STMPE_I2C)		+= stmpe-i2c.o
 obj-$(CONFIG_STMPE_SPI)		+= stmpe-spi.o
@@ -54,6 +55,8 @@ obj-$(CONFIG_TWL6030_PWM)	+= twl6030-pwm.o
 obj-$(CONFIG_TWL6040_CORE)	+= twl6040-core.o twl6040-irq.o
 
 obj-$(CONFIG_MFD_MC13XXX)	+= mc13xxx-core.o
+obj-$(CONFIG_MFD_MC13XXX_SPI)	+= mc13xxx-spi.o
+obj-$(CONFIG_MFD_MC13XXX_I2C)	+= mc13xxx-i2c.o
 
 obj-$(CONFIG_MFD_CORE)		+= mfd-core.o
 
@@ -75,6 +78,7 @@ obj-$(CONFIG_PMIC_DA9052)	+= da9052-core.o
 obj-$(CONFIG_MFD_DA9052_SPI)	+= da9052-spi.o
 obj-$(CONFIG_MFD_DA9052_I2C)	+= da9052-i2c.o
 
+obj-$(CONFIG_MFD_MAX77693)	+= max77693.o max77693-irq.o
 max8925-objs			:= max8925-core.o max8925-i2c.o
 obj-$(CONFIG_MFD_MAX8925)	+= max8925.o
 obj-$(CONFIG_MFD_MAX8997)	+= max8997.o max8997-irq.o
@@ -87,15 +91,15 @@ obj-$(CONFIG_PCF50633_GPIO)	+= pcf50633-gpio.o
 obj-$(CONFIG_ABX500_CORE)	+= abx500-core.o
 obj-$(CONFIG_AB3100_CORE)	+= ab3100-core.o
 obj-$(CONFIG_AB3100_OTP)	+= ab3100-otp.o
-obj-$(CONFIG_AB8500_CORE)	+= ab8500-core.o ab8500-sysctrl.o
 obj-$(CONFIG_AB8500_DEBUG)	+= ab8500-debugfs.o
 obj-$(CONFIG_AB8500_GPADC)	+= ab8500-gpadc.o
 obj-$(CONFIG_MFD_DB8500_PRCMU)	+= db8500-prcmu.o
-# ab8500-i2c need to come after db8500-prcmu (which provides the channel)
-obj-$(CONFIG_AB8500_I2C_CORE)	+= ab8500-i2c.o
+# ab8500-core need to come after db8500-prcmu (which provides the channel)
+obj-$(CONFIG_AB8500_CORE)	+= ab8500-core.o ab8500-sysctrl.o
 obj-$(CONFIG_MFD_TIMBERDALE)    += timberdale.o
 obj-$(CONFIG_PMIC_ADP5520)	+= adp5520.o
 obj-$(CONFIG_LPC_SCH)		+= lpc_sch.o
+obj-$(CONFIG_LPC_ICH)		+= lpc_ich.o
 obj-$(CONFIG_MFD_RDC321X)	+= rdc321x-southbridge.o
 obj-$(CONFIG_MFD_JANZ_CMODIO)	+= janz-cmodio.o
 obj-$(CONFIG_MFD_JZ4740_ADC)	+= jz4740-adc.o
diff --git a/drivers/mfd/ab8500-core.c b/drivers/mfd/ab8500-core.c
index 1f08704f7ae8..dac0e2998603 100644
--- a/drivers/mfd/ab8500-core.c
+++ b/drivers/mfd/ab8500-core.c
@@ -18,7 +18,10 @@
 #include <linux/mfd/core.h>
 #include <linux/mfd/abx500.h>
 #include <linux/mfd/abx500/ab8500.h>
+#include <linux/mfd/dbx500-prcmu.h>
 #include <linux/regulator/ab8500.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
 
 /*
  * Interrupt register offsets
@@ -91,12 +94,24 @@
 #define AB8500_IT_MASK23_REG		0x56
 #define AB8500_IT_MASK24_REG		0x57
 
+/*
+ * latch hierarchy registers
+ */
+#define AB8500_IT_LATCHHIER1_REG	0x60
+#define AB8500_IT_LATCHHIER2_REG	0x61
+#define AB8500_IT_LATCHHIER3_REG	0x62
+
+#define AB8500_IT_LATCHHIER_NUM		3
+
 #define AB8500_REV_REG			0x80
 #define AB8500_IC_NAME_REG		0x82
 #define AB8500_SWITCH_OFF_STATUS	0x00
 
 #define AB8500_TURN_ON_STATUS		0x00
 
+static bool no_bm; /* No battery management */
+module_param(no_bm, bool, S_IRUGO);
+
 #define AB9540_MODEM_CTRL2_REG			0x23
 #define AB9540_MODEM_CTRL2_SWDBBRSTN_BIT	BIT(2)
 
@@ -125,6 +140,41 @@ static const char ab8500_version_str[][7] = {
 	[AB8500_VERSION_AB8540] = "AB8540",
 };
 
+static int ab8500_i2c_write(struct ab8500 *ab8500, u16 addr, u8 data)
+{
+	int ret;
+
+	ret = prcmu_abb_write((u8)(addr >> 8), (u8)(addr & 0xFF), &data, 1);
+	if (ret < 0)
+		dev_err(ab8500->dev, "prcmu i2c error %d\n", ret);
+	return ret;
+}
+
+static int ab8500_i2c_write_masked(struct ab8500 *ab8500, u16 addr, u8 mask,
+	u8 data)
+{
+	int ret;
+
+	ret = prcmu_abb_write_masked((u8)(addr >> 8), (u8)(addr & 0xFF), &data,
+		&mask, 1);
+	if (ret < 0)
+		dev_err(ab8500->dev, "prcmu i2c error %d\n", ret);
+	return ret;
+}
+
+static int ab8500_i2c_read(struct ab8500 *ab8500, u16 addr)
+{
+	int ret;
+	u8 data;
+
+	ret = prcmu_abb_read((u8)(addr >> 8), (u8)(addr & 0xFF), &data, 1);
+	if (ret < 0) {
+		dev_err(ab8500->dev, "prcmu i2c error %d\n", ret);
+		return ret;
+	}
+	return (int)data;
+}
+
 static int ab8500_get_chip_id(struct device *dev)
 {
 	struct ab8500 *ab8500;
@@ -161,9 +211,13 @@ static int set_register_interruptible(struct ab8500 *ab8500, u8 bank,
 static int ab8500_set_register(struct device *dev, u8 bank,
 	u8 reg, u8 value)
 {
+	int ret;
 	struct ab8500 *ab8500 = dev_get_drvdata(dev->parent);
 
-	return set_register_interruptible(ab8500, bank, reg, value);
+	atomic_inc(&ab8500->transfer_ongoing);
+	ret = set_register_interruptible(ab8500, bank, reg, value);
+	atomic_dec(&ab8500->transfer_ongoing);
+	return ret;
 }
 
 static int get_register_interruptible(struct ab8500 *ab8500, u8 bank,
@@ -192,9 +246,13 @@ static int get_register_interruptible(struct ab8500 *ab8500, u8 bank,
 static int ab8500_get_register(struct device *dev, u8 bank,
 	u8 reg, u8 *value)
 {
+	int ret;
 	struct ab8500 *ab8500 = dev_get_drvdata(dev->parent);
 
-	return get_register_interruptible(ab8500, bank, reg, value);
+	atomic_inc(&ab8500->transfer_ongoing);
+	ret = get_register_interruptible(ab8500, bank, reg, value);
+	atomic_dec(&ab8500->transfer_ongoing);
+	return ret;
 }
 
 static int mask_and_set_register_interruptible(struct ab8500 *ab8500, u8 bank,
@@ -241,11 +299,14 @@ out:
 static int ab8500_mask_and_set_register(struct device *dev,
 	u8 bank, u8 reg, u8 bitmask, u8 bitvalues)
 {
+	int ret;
 	struct ab8500 *ab8500 = dev_get_drvdata(dev->parent);
 
-	return mask_and_set_register_interruptible(ab8500, bank, reg,
-		bitmask, bitvalues);
-
+	atomic_inc(&ab8500->transfer_ongoing);
+	ret= mask_and_set_register_interruptible(ab8500, bank, reg,
+						 bitmask, bitvalues);
+	atomic_dec(&ab8500->transfer_ongoing);
+	return ret;
 }
 
 static struct abx500_ops ab8500_ops = {
@@ -264,6 +325,7 @@ static void ab8500_irq_lock(struct irq_data *data)
 	struct ab8500 *ab8500 = irq_data_get_irq_chip_data(data);
 
 	mutex_lock(&ab8500->irq_lock);
+	atomic_inc(&ab8500->transfer_ongoing);
 }
 
 static void ab8500_irq_sync_unlock(struct irq_data *data)
@@ -292,7 +354,7 @@ static void ab8500_irq_sync_unlock(struct irq_data *data)
 		reg = AB8500_IT_MASK1_REG + ab8500->irq_reg_offset[i];
 		set_register_interruptible(ab8500, AB8500_INTERRUPT, reg, new);
 	}
-
+	atomic_dec(&ab8500->transfer_ongoing);
 	mutex_unlock(&ab8500->irq_lock);
 }
 
@@ -325,6 +387,90 @@ static struct irq_chip ab8500_irq_chip = {
 	.irq_unmask		= ab8500_irq_unmask,
 };
 
+static int ab8500_handle_hierarchical_line(struct ab8500 *ab8500,
+					int latch_offset, u8 latch_val)
+{
+	int int_bit = __ffs(latch_val);
+	int line, i;
+
+	do {
+		int_bit = __ffs(latch_val);
+
+		for (i = 0; i < ab8500->mask_size; i++)
+			if (ab8500->irq_reg_offset[i] == latch_offset)
+				break;
+
+		if (i >= ab8500->mask_size) {
+			dev_err(ab8500->dev, "Register offset 0x%2x not declared\n",
+					latch_offset);
+			return -ENXIO;
+		}
+
+		line = (i << 3) + int_bit;
+		latch_val &= ~(1 << int_bit);
+
+		handle_nested_irq(ab8500->irq_base + line);
+	} while (latch_val);
+
+	return 0;
+}
+
+static int ab8500_handle_hierarchical_latch(struct ab8500 *ab8500,
+					int hier_offset, u8 hier_val)
+{
+	int latch_bit, status;
+	u8 latch_offset, latch_val;
+
+	do {
+		latch_bit = __ffs(hier_val);
+		latch_offset = (hier_offset << 3) + latch_bit;
+
+		/* Fix inconsistent ITFromLatch25 bit mapping... */
+		if (unlikely(latch_offset == 17))
+			latch_offset = 24;
+
+		status = get_register_interruptible(ab8500,
+				AB8500_INTERRUPT,
+				AB8500_IT_LATCH1_REG + latch_offset,
+				&latch_val);
+		if (status < 0 || latch_val == 0)
+			goto discard;
+
+		status = ab8500_handle_hierarchical_line(ab8500,
+				latch_offset, latch_val);
+		if (status < 0)
+			return status;
+discard:
+		hier_val &= ~(1 << latch_bit);
+	} while (hier_val);
+
+	return 0;
+}
+
+static irqreturn_t ab8500_hierarchical_irq(int irq, void *dev)
+{
+	struct ab8500 *ab8500 = dev;
+	u8 i;
+
+	dev_vdbg(ab8500->dev, "interrupt\n");
+
+	/*  Hierarchical interrupt version */
+	for (i = 0; i < AB8500_IT_LATCHHIER_NUM; i++) {
+		int status;
+		u8 hier_val;
+
+		status = get_register_interruptible(ab8500, AB8500_INTERRUPT,
+			AB8500_IT_LATCHHIER1_REG + i, &hier_val);
+		if (status < 0 || hier_val == 0)
+			continue;
+
+		status = ab8500_handle_hierarchical_latch(ab8500, i, hier_val);
+		if (status < 0)
+			break;
+	}
+	return IRQ_HANDLED;
+}
+
 static irqreturn_t ab8500_irq(int irq, void *dev)
 {
 	struct ab8500 *ab8500 = dev;
@@ -332,6 +478,8 @@ static irqreturn_t ab8500_irq(int irq, void *dev)
 
 	dev_vdbg(ab8500->dev, "interrupt\n");
 
+	atomic_inc(&ab8500->transfer_ongoing);
+
 	for (i = 0; i < ab8500->mask_size; i++) {
 		int regoffset = ab8500->irq_reg_offset[i];
 		int status;
@@ -355,9 +503,10 @@ static irqreturn_t ab8500_irq(int irq, void *dev)
 
 			handle_nested_irq(ab8500->irq_base + line);
 			value &= ~(1 << bit);
+
 		} while (value);
 	}
-
+	atomic_dec(&ab8500->transfer_ongoing);
 	return IRQ_HANDLED;
 }
 
@@ -411,6 +560,14 @@ static void ab8500_irq_remove(struct ab8500 *ab8500)
 	}
 }
 
+int ab8500_suspend(struct ab8500 *ab8500)
+{
+	if (atomic_read(&ab8500->transfer_ongoing))
+		return -EINVAL;
+	else
+		return 0;
+}
+
 /* AB8500 GPIO Resources */
 static struct resource __devinitdata ab8500_gpio_resources[] = {
 	{
@@ -744,6 +901,39 @@ static struct resource __devinitdata ab8500_usb_resources[] = {
 	},
 };
 
+static struct resource __devinitdata ab8505_iddet_resources[] = {
+	{
+		.name  = "KeyDeglitch",
+		.start = AB8505_INT_KEYDEGLITCH,
+		.end   = AB8505_INT_KEYDEGLITCH,
+		.flags = IORESOURCE_IRQ,
+	},
+	{
+		.name  = "KP",
+		.start = AB8505_INT_KP,
+		.end   = AB8505_INT_KP,
+		.flags = IORESOURCE_IRQ,
+	},
+	{
+		.name  = "IKP",
+		.start = AB8505_INT_IKP,
+		.end   = AB8505_INT_IKP,
+		.flags = IORESOURCE_IRQ,
+	},
+	{
+		.name  = "IKR",
+		.start = AB8505_INT_IKR,
+		.end   = AB8505_INT_IKR,
+		.flags = IORESOURCE_IRQ,
+	},
+	{
+		.name  = "KeyStuck",
+		.start = AB8505_INT_KEYSTUCK,
+		.end   = AB8505_INT_KEYSTUCK,
+		.flags = IORESOURCE_IRQ,
+	},
+};
+
 static struct resource __devinitdata ab8500_temp_resources[] = {
 	{
 		.name  = "AB8500_TEMP_WARM",
@@ -778,35 +968,11 @@ static struct mfd_cell __devinitdata abx500_common_devs[] = {
 		.resources = ab8500_rtc_resources,
 	},
 	{
-		.name = "ab8500-charger",
-		.num_resources = ARRAY_SIZE(ab8500_charger_resources),
-		.resources = ab8500_charger_resources,
-	},
-	{
-		.name = "ab8500-btemp",
-		.num_resources = ARRAY_SIZE(ab8500_btemp_resources),
-		.resources = ab8500_btemp_resources,
-	},
-	{
-		.name = "ab8500-fg",
-		.num_resources = ARRAY_SIZE(ab8500_fg_resources),
-		.resources = ab8500_fg_resources,
-	},
-	{
-		.name = "ab8500-chargalg",
-		.num_resources = ARRAY_SIZE(ab8500_chargalg_resources),
-		.resources = ab8500_chargalg_resources,
-	},
-	{
 		.name = "ab8500-acc-det",
 		.num_resources = ARRAY_SIZE(ab8500_av_acc_detect_resources),
 		.resources = ab8500_av_acc_detect_resources,
 	},
 	{
-		.name = "ab8500-codec",
-	},
-
-	{
 		.name = "ab8500-poweron-key",
 		.num_resources = ARRAY_SIZE(ab8500_poweronkey_db_resources),
 		.resources = ab8500_poweronkey_db_resources,
@@ -834,6 +1000,29 @@ static struct mfd_cell __devinitdata abx500_common_devs[] = {
 	},
 };
 
+static struct mfd_cell __devinitdata ab8500_bm_devs[] = {
+	{
+		.name = "ab8500-charger",
+		.num_resources = ARRAY_SIZE(ab8500_charger_resources),
+		.resources = ab8500_charger_resources,
+	},
+	{
+		.name = "ab8500-btemp",
+		.num_resources = ARRAY_SIZE(ab8500_btemp_resources),
+		.resources = ab8500_btemp_resources,
+	},
+	{
+		.name = "ab8500-fg",
+		.num_resources = ARRAY_SIZE(ab8500_fg_resources),
+		.resources = ab8500_fg_resources,
+	},
+	{
+		.name = "ab8500-chargalg",
+		.num_resources = ARRAY_SIZE(ab8500_chargalg_resources),
+		.resources = ab8500_chargalg_resources,
+	},
+};
+
 static struct mfd_cell __devinitdata ab8500_devs[] = {
 	{
 		.name = "ab8500-gpio",
@@ -845,6 +1034,9 @@ static struct mfd_cell __devinitdata ab8500_devs[] = {
 		.num_resources = ARRAY_SIZE(ab8500_usb_resources),
 		.resources = ab8500_usb_resources,
 	},
+	{
+		.name = "ab8500-codec",
+	},
 };
 
 static struct mfd_cell __devinitdata ab9540_devs[] = {
@@ -858,6 +1050,18 @@ static struct mfd_cell __devinitdata ab9540_devs[] = {
 		.num_resources = ARRAY_SIZE(ab8500_usb_resources),
 		.resources = ab8500_usb_resources,
 	},
+	{
+		.name = "ab9540-codec",
+	},
+};
+
+/* Device list common to ab9540 and ab8505 */
+static struct mfd_cell __devinitdata ab9540_ab8505_devs[] = {
+	{
+		.name = "ab-iddet",
+		.num_resources = ARRAY_SIZE(ab8505_iddet_resources),
+		.resources = ab8505_iddet_resources,
+	},
 };
 
 static ssize_t show_chip_id(struct device *dev,
@@ -1003,18 +1207,66 @@ static struct attribute_group ab9540_attr_group = {
 	.attrs	= ab9540_sysfs_entries,
 };
 
-int __devinit ab8500_init(struct ab8500 *ab8500, enum ab8500_version version)
+static const struct of_device_id ab8500_match[] = {
+	{
+		.compatible = "stericsson,ab8500",
+		.data = (void *)AB8500_VERSION_AB8500,
+	},
+	{},
+};
+
+static int __devinit ab8500_probe(struct platform_device *pdev)
 {
-	struct ab8500_platform_data *plat = dev_get_platdata(ab8500->dev);
+	struct ab8500_platform_data *plat = dev_get_platdata(&pdev->dev);
+	const struct platform_device_id *platid = platform_get_device_id(pdev);
+	enum ab8500_version version = AB8500_VERSION_UNDEFINED;
+	struct device_node *np = pdev->dev.of_node;
+	struct ab8500 *ab8500;
+	struct resource *resource;
 	int ret;
 	int i;
 	u8 value;
 
+	ab8500 = kzalloc(sizeof *ab8500, GFP_KERNEL);
+	if (!ab8500)
+		return -ENOMEM;
+
 	if (plat)
 		ab8500->irq_base = plat->irq_base;
+	else if (np)
+		ret = of_property_read_u32(np, "stericsson,irq-base", &ab8500->irq_base);
+
+	if (!ab8500->irq_base) {
+		dev_info(&pdev->dev, "couldn't find irq-base\n");
+		ret = -EINVAL;
+		goto out_free_ab8500;
+	}
+
+	ab8500->dev = &pdev->dev;
+
+	resource = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
+	if (!resource) {
+		ret = -ENODEV;
+		goto out_free_ab8500;
+	}
+
+	ab8500->irq = resource->start;
+
+	ab8500->read = ab8500_i2c_read;
+	ab8500->write = ab8500_i2c_write;
+	ab8500->write_masked = ab8500_i2c_write_masked;
 
 	mutex_init(&ab8500->lock);
 	mutex_init(&ab8500->irq_lock);
+	atomic_set(&ab8500->transfer_ongoing, 0);
+
+	platform_set_drvdata(pdev, ab8500);
+
+	if (platid)
+		version = platid->driver_data;
+	else if (np)
+		version = (unsigned int)
+			of_match_device(ab8500_match, &pdev->dev)->data;
 
 	if (version != AB8500_VERSION_UNDEFINED)
 		ab8500->version = version;
@@ -1022,7 +1274,7 @@ int __devinit ab8500_init(struct ab8500 *ab8500, enum ab8500_version version)
 		ret = get_register_interruptible(ab8500, AB8500_MISC,
 			AB8500_IC_NAME_REG, &value);
 		if (ret < 0)
-			return ret;
+			goto out_free_ab8500;
 
 		ab8500->version = value;
 	}
@@ -1030,7 +1282,7 @@ int __devinit ab8500_init(struct ab8500 *ab8500, enum ab8500_version version)
 	ret = get_register_interruptible(ab8500, AB8500_MISC,
 		AB8500_REV_REG, &value);
 	if (ret < 0)
-		return ret;
+		goto out_free_ab8500;
 
 	ab8500->chip_id = value;
 
@@ -1105,30 +1357,57 @@ int __devinit ab8500_init(struct ab8500 *ab8500, enum ab8500_version version)
 		if (ret)
 			goto out_freeoldmask;
 
-		ret = request_threaded_irq(ab8500->irq, NULL, ab8500_irq,
-					   IRQF_ONESHOT | IRQF_NO_SUSPEND,
-					   "ab8500", ab8500);
+		/*  Activate this feature only in ab9540 */
+		/*  till tests are done on ab8500 1p2 or later*/
+		if (is_ab9540(ab8500))
+			ret = request_threaded_irq(ab8500->irq, NULL,
+					ab8500_hierarchical_irq,
+					IRQF_ONESHOT | IRQF_NO_SUSPEND,
+					"ab8500", ab8500);
+		else
+			ret = request_threaded_irq(ab8500->irq, NULL,
+					ab8500_irq,
+					IRQF_ONESHOT | IRQF_NO_SUSPEND,
+					"ab8500", ab8500);
 		if (ret)
 			goto out_removeirq;
 	}
 
-	ret = mfd_add_devices(ab8500->dev, 0, abx500_common_devs,
-			      ARRAY_SIZE(abx500_common_devs), NULL,
-			      ab8500->irq_base);
+	if (!np) {
+		ret = mfd_add_devices(ab8500->dev, 0, abx500_common_devs,
+				ARRAY_SIZE(abx500_common_devs), NULL,
+				ab8500->irq_base);
 
-	if (ret)
-		goto out_freeirq;
+		if (ret)
+			goto out_freeirq;
+
+		if (is_ab9540(ab8500))
+			ret = mfd_add_devices(ab8500->dev, 0, ab9540_devs,
+					ARRAY_SIZE(ab9540_devs), NULL,
+					ab8500->irq_base);
+		else
+			ret = mfd_add_devices(ab8500->dev, 0, ab8500_devs,
+					ARRAY_SIZE(ab8500_devs), NULL,
+					ab8500->irq_base);
+		if (ret)
+			goto out_freeirq;
 
-	if (is_ab9540(ab8500))
-		ret = mfd_add_devices(ab8500->dev, 0, ab9540_devs,
-			      ARRAY_SIZE(ab9540_devs), NULL,
-			      ab8500->irq_base);
-	else
-		ret = mfd_add_devices(ab8500->dev, 0, ab8500_devs,
-			      ARRAY_SIZE(ab9540_devs), NULL,
-			      ab8500->irq_base);
-	if (ret)
-		goto out_freeirq;
+		if (is_ab9540(ab8500) || is_ab8505(ab8500))
+			ret = mfd_add_devices(ab8500->dev, 0, ab9540_ab8505_devs,
+					ARRAY_SIZE(ab9540_ab8505_devs), NULL,
+					ab8500->irq_base);
+		if (ret)
+			goto out_freeirq;
+	}
+
+	if (!no_bm) {
+		/* Add battery management devices */
+		ret = mfd_add_devices(ab8500->dev, 0, ab8500_bm_devs,
+				      ARRAY_SIZE(ab8500_bm_devs), NULL,
+				      ab8500->irq_base);
+		if (ret)
+			dev_err(ab8500->dev, "error adding bm devices\n");
+	}
 
 	if (is_ab9540(ab8500))
 		ret = sysfs_create_group(&ab8500->dev->kobj,
@@ -1151,12 +1430,16 @@ out_freeoldmask:
 	kfree(ab8500->oldmask);
 out_freemask:
 	kfree(ab8500->mask);
+out_free_ab8500:
+	kfree(ab8500);
 
 	return ret;
 }
 
-int __devexit ab8500_exit(struct ab8500 *ab8500)
+static int __devexit ab8500_remove(struct platform_device *pdev)
 {
+	struct ab8500 *ab8500 = platform_get_drvdata(pdev);
+
 	if (is_ab9540(ab8500))
 		sysfs_remove_group(&ab8500->dev->kobj, &ab9540_attr_group);
 	else
@@ -1168,10 +1451,42 @@ int __devexit ab8500_exit(struct ab8500 *ab8500)
 	}
 	kfree(ab8500->oldmask);
 	kfree(ab8500->mask);
+	kfree(ab8500);
 
 	return 0;
 }
 
+static const struct platform_device_id ab8500_id[] = {
+	{ "ab8500-core", AB8500_VERSION_AB8500 },
+	{ "ab8505-i2c", AB8500_VERSION_AB8505 },
+	{ "ab9540-i2c", AB8500_VERSION_AB9540 },
+	{ "ab8540-i2c", AB8500_VERSION_AB8540 },
+	{ }
+};
+
+static struct platform_driver ab8500_core_driver = {
+	.driver = {
+		.name = "ab8500-core",
+		.owner = THIS_MODULE,
+		.of_match_table = ab8500_match,
+	},
+	.probe	= ab8500_probe,
+	.remove	= __devexit_p(ab8500_remove),
+	.id_table = ab8500_id,
+};
+
+static int __init ab8500_core_init(void)
+{
+	return platform_driver_register(&ab8500_core_driver);
+}
+
+static void __exit ab8500_core_exit(void)
+{
+	platform_driver_unregister(&ab8500_core_driver);
+}
+arch_initcall(ab8500_core_init);
+module_exit(ab8500_core_exit);
+
 MODULE_AUTHOR("Mattias Wallin, Srinidhi Kasagar, Rabin Vincent");
 MODULE_DESCRIPTION("AB8500 MFD core");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/mfd/ab8500-debugfs.c b/drivers/mfd/ab8500-debugfs.c
index 9a0211aa8897..50c4c89ab220 100644
--- a/drivers/mfd/ab8500-debugfs.c
+++ b/drivers/mfd/ab8500-debugfs.c
@@ -608,10 +608,16 @@ static int __devexit ab8500_debug_remove(struct platform_device *plf)
 	return 0;
 }
 
+static const struct of_device_id ab8500_debug_match[] = {
+        { .compatible = "stericsson,ab8500-debug", },
+        {}
+};
+
 static struct platform_driver ab8500_debug_driver = {
 	.driver = {
 		.name = "ab8500-debug",
 		.owner = THIS_MODULE,
+		.of_match_table = ab8500_debug_match,
 	},
 	.probe  = ab8500_debug_probe,
 	.remove = __devexit_p(ab8500_debug_remove)
diff --git a/drivers/mfd/ab8500-gpadc.c b/drivers/mfd/ab8500-gpadc.c
index c39fc716e1dc..b86fd8e1ec3f 100644
--- a/drivers/mfd/ab8500-gpadc.c
+++ b/drivers/mfd/ab8500-gpadc.c
@@ -584,7 +584,7 @@ static int __devinit ab8500_gpadc_probe(struct platform_device *pdev)
 
 	gpadc->irq = platform_get_irq_byname(pdev, "SW_CONV_END");
 	if (gpadc->irq < 0) {
-		dev_err(gpadc->dev, "failed to get platform irq-%d\n",
+		dev_err(&pdev->dev, "failed to get platform irq-%d\n",
 			gpadc->irq);
 		ret = gpadc->irq;
 		goto fail;
@@ -648,12 +648,18 @@ static int __devexit ab8500_gpadc_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct of_device_id ab8500_gpadc_match[] = {
+	{ .compatible = "stericsson,ab8500-gpadc", },
+	{}
+};
+
 static struct platform_driver ab8500_gpadc_driver = {
 	.probe = ab8500_gpadc_probe,
 	.remove = __devexit_p(ab8500_gpadc_remove),
 	.driver = {
 		.name = "ab8500-gpadc",
 		.owner = THIS_MODULE,
+		.of_match_table = ab8500_gpadc_match,
 	},
 };
 
diff --git a/drivers/mfd/ab8500-i2c.c b/drivers/mfd/ab8500-i2c.c
deleted file mode 100644
index b83045f102be..000000000000
--- a/drivers/mfd/ab8500-i2c.c
+++ /dev/null
@@ -1,128 +0,0 @@
-/*
- * Copyright (C) ST-Ericsson SA 2010
- * Author: Mattias Wallin <mattias.wallin@stericsson.com> for ST-Ericsson.
- * License Terms: GNU General Public License v2
- * This file was based on drivers/mfd/ab8500-spi.c
- */
-
-#include <linux/kernel.h>
-#include <linux/slab.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/platform_device.h>
-#include <linux/mfd/abx500/ab8500.h>
-#include <linux/mfd/dbx500-prcmu.h>
-
-static int ab8500_i2c_write(struct ab8500 *ab8500, u16 addr, u8 data)
-{
-	int ret;
-
-	ret = prcmu_abb_write((u8)(addr >> 8), (u8)(addr & 0xFF), &data, 1);
-	if (ret < 0)
-		dev_err(ab8500->dev, "prcmu i2c error %d\n", ret);
-	return ret;
-}
-
-static int ab8500_i2c_write_masked(struct ab8500 *ab8500, u16 addr, u8 mask,
-	u8 data)
-{
-	int ret;
-
-	ret = prcmu_abb_write_masked((u8)(addr >> 8), (u8)(addr & 0xFF), &data,
-		&mask, 1);
-	if (ret < 0)
-		dev_err(ab8500->dev, "prcmu i2c error %d\n", ret);
-	return ret;
-}
-
-static int ab8500_i2c_read(struct ab8500 *ab8500, u16 addr)
-{
-	int ret;
-	u8 data;
-
-	ret = prcmu_abb_read((u8)(addr >> 8), (u8)(addr & 0xFF), &data, 1);
-	if (ret < 0) {
-		dev_err(ab8500->dev, "prcmu i2c error %d\n", ret);
-		return ret;
-	}
-	return (int)data;
-}
-
-static int __devinit ab8500_i2c_probe(struct platform_device *plf)
-{
-	const struct platform_device_id *platid = platform_get_device_id(plf);
-	struct ab8500 *ab8500;
-	struct resource *resource;
-	int ret;
-
-	ab8500 = kzalloc(sizeof *ab8500, GFP_KERNEL);
-	if (!ab8500)
-		return -ENOMEM;
-
-	ab8500->dev = &plf->dev;
-
-	resource = platform_get_resource(plf, IORESOURCE_IRQ, 0);
-	if (!resource) {
-		kfree(ab8500);
-		return -ENODEV;
-	}
-
-	ab8500->irq = resource->start;
-
-	ab8500->read = ab8500_i2c_read;
-	ab8500->write = ab8500_i2c_write;
-	ab8500->write_masked = ab8500_i2c_write_masked;
-
-	platform_set_drvdata(plf, ab8500);
-
-	ret = ab8500_init(ab8500, platid->driver_data);
-	if (ret)
-		kfree(ab8500);
-
-
-	return ret;
-}
-
-static int __devexit ab8500_i2c_remove(struct platform_device *plf)
-{
-	struct ab8500 *ab8500 = platform_get_drvdata(plf);
-
-	ab8500_exit(ab8500);
-	kfree(ab8500);
-
-	return 0;
-}
-
-static const struct platform_device_id ab8500_id[] = {
-	{ "ab8500-i2c", AB8500_VERSION_AB8500 },
-	{ "ab8505-i2c", AB8500_VERSION_AB8505 },
-	{ "ab9540-i2c", AB8500_VERSION_AB9540 },
-	{ "ab8540-i2c", AB8500_VERSION_AB8540 },
-	{ }
-};
-
-static struct platform_driver ab8500_i2c_driver = {
-	.driver = {
-		.name = "ab8500-i2c",
-		.owner = THIS_MODULE,
-	},
-	.probe	= ab8500_i2c_probe,
-	.remove	= __devexit_p(ab8500_i2c_remove),
-	.id_table = ab8500_id,
-};
-
-static int __init ab8500_i2c_init(void)
-{
-	return platform_driver_register(&ab8500_i2c_driver);
-}
-
-static void __exit ab8500_i2c_exit(void)
-{
-	platform_driver_unregister(&ab8500_i2c_driver);
-}
-arch_initcall(ab8500_i2c_init);
-module_exit(ab8500_i2c_exit);
-
-MODULE_AUTHOR("Mattias WALLIN <mattias.wallin@stericsson.com");
-MODULE_DESCRIPTION("AB8500 Core access via PRCMU I2C");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/mfd/ab8500-sysctrl.c b/drivers/mfd/ab8500-sysctrl.c
index c28d4eb1eff0..5a3e51ccf258 100644
--- a/drivers/mfd/ab8500-sysctrl.c
+++ b/drivers/mfd/ab8500-sysctrl.c
@@ -61,10 +61,16 @@ static int __devexit ab8500_sysctrl_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct of_device_id ab8500_sysctrl_match[] = {
+	{ .compatible = "stericsson,ab8500-sysctrl", },
+	{}
+};
+
 static struct platform_driver ab8500_sysctrl_driver = {
 	.driver = {
 		.name = "ab8500-sysctrl",
 		.owner = THIS_MODULE,
+		.of_match_table = ab8500_sysctrl_match,
 	},
 	.probe = ab8500_sysctrl_probe,
 	.remove = __devexit_p(ab8500_sysctrl_remove),
diff --git a/drivers/mfd/anatop-mfd.c b/drivers/mfd/anatop-mfd.c
index 2af42480635e..6da06341f6c9 100644
--- a/drivers/mfd/anatop-mfd.c
+++ b/drivers/mfd/anatop-mfd.c
@@ -41,39 +41,26 @@
 #include <linux/of_address.h>
 #include <linux/mfd/anatop.h>
 
-u32 anatop_get_bits(struct anatop *adata, u32 addr, int bit_shift,
-		    int bit_width)
+u32 anatop_read_reg(struct anatop *adata, u32 addr)
 {
-	u32 val, mask;
-
-	if (bit_width == 32)
-		mask = ~0;
-	else
-		mask = (1 << bit_width) - 1;
-
-	val = readl(adata->ioreg + addr);
-	val = (val >> bit_shift) & mask;
-
-	return val;
+	return readl(adata->ioreg + addr);
 }
-EXPORT_SYMBOL_GPL(anatop_get_bits);
+EXPORT_SYMBOL_GPL(anatop_read_reg);
 
-void anatop_set_bits(struct anatop *adata, u32 addr, int bit_shift,
-		     int bit_width, u32 data)
+void anatop_write_reg(struct anatop *adata, u32 addr, u32 data, u32 mask)
 {
-	u32 val, mask;
+	u32 val;
 
-	if (bit_width == 32)
-		mask = ~0;
-	else
-		mask = (1 << bit_width) - 1;
+	data &= mask;
 
 	spin_lock(&adata->reglock);
-	val = readl(adata->ioreg + addr) & ~(mask << bit_shift);
-	writel((data << bit_shift) | val, adata->ioreg + addr);
+	val = readl(adata->ioreg + addr);
+	val &= ~mask;
+	val |= data;
+	writel(val, adata->ioreg + addr);
 	spin_unlock(&adata->reglock);
 }
-EXPORT_SYMBOL_GPL(anatop_set_bits);
+EXPORT_SYMBOL_GPL(anatop_write_reg);
 
 static const struct of_device_id of_anatop_match[] = {
 	{ .compatible = "fsl,imx6q-anatop", },
diff --git a/drivers/mfd/asic3.c b/drivers/mfd/asic3.c
index 1582c3d95257..383421bf5760 100644
--- a/drivers/mfd/asic3.c
+++ b/drivers/mfd/asic3.c
@@ -353,12 +353,28 @@ static int asic3_gpio_irq_type(struct irq_data *data, unsigned int type)
 	return 0;
 }
 
+static int asic3_gpio_irq_set_wake(struct irq_data *data, unsigned int on)
+{
+	struct asic3 *asic = irq_data_get_irq_chip_data(data);
+	u32 bank, index;
+	u16 bit;
+
+	bank = asic3_irq_to_bank(asic, data->irq);
+	index = asic3_irq_to_index(asic, data->irq);
+	bit = 1<<index;
+
+	asic3_set_register(asic, bank + ASIC3_GPIO_SLEEP_MASK, bit, !on);
+
+	return 0;
+}
+
 static struct irq_chip asic3_gpio_irq_chip = {
 	.name		= "ASIC3-GPIO",
 	.irq_ack	= asic3_mask_gpio_irq,
 	.irq_mask	= asic3_mask_gpio_irq,
 	.irq_unmask	= asic3_unmask_gpio_irq,
 	.irq_set_type	= asic3_gpio_irq_type,
+	.irq_set_wake	= asic3_gpio_irq_set_wake,
 };
 
 static struct irq_chip asic3_irq_chip = {
@@ -529,7 +545,7 @@ static int asic3_gpio_to_irq(struct gpio_chip *chip, unsigned offset)
 {
 	struct asic3 *asic = container_of(chip, struct asic3, gpio);
 
-	return (offset < ASIC3_NUM_GPIOS) ? asic->irq_base + offset : -ENXIO;
+	return asic->irq_base + offset;
 }
 
 static __init int asic3_gpio_probe(struct platform_device *pdev,
@@ -894,10 +910,13 @@ static int __init asic3_mfd_probe(struct platform_device *pdev,
 	asic3_mmc_resources[0].start >>= asic->bus_shift;
 	asic3_mmc_resources[0].end   >>= asic->bus_shift;
 
-	ret = mfd_add_devices(&pdev->dev, pdev->id,
+	if (pdata->clock_rate) {
+		ds1wm_pdata.clock_rate = pdata->clock_rate;
+		ret = mfd_add_devices(&pdev->dev, pdev->id,
 			&asic3_cell_ds1wm, 1, mem, asic->irq_base);
-	if (ret < 0)
-		goto out;
+		if (ret < 0)
+			goto out;
+	}
 
 	if (mem_sdio && (irq >= 0)) {
 		ret = mfd_add_devices(&pdev->dev, pdev->id,
@@ -1000,6 +1019,9 @@ static int __init asic3_probe(struct platform_device *pdev)
 
 	asic3_mfd_probe(pdev, pdata, mem);
 
+	asic3_set_register(asic, ASIC3_OFFSET(EXTCF, SELECT),
+		(ASIC3_EXTCF_CF0_BUF_EN|ASIC3_EXTCF_CF0_PWAIT_EN), 1);
+
 	dev_info(asic->dev, "ASIC3 Core driver\n");
 
 	return 0;
@@ -1021,6 +1043,9 @@ static int __devexit asic3_remove(struct platform_device *pdev)
 	int ret;
 	struct asic3 *asic = platform_get_drvdata(pdev);
 
+	asic3_set_register(asic, ASIC3_OFFSET(EXTCF, SELECT),
+		(ASIC3_EXTCF_CF0_BUF_EN|ASIC3_EXTCF_CF0_PWAIT_EN), 0);
+
 	asic3_mfd_remove(pdev);
 
 	ret = asic3_gpio_remove(pdev);
diff --git a/drivers/mfd/cs5535-mfd.c b/drivers/mfd/cs5535-mfd.c
index 315fef5d466a..3419e726de47 100644
--- a/drivers/mfd/cs5535-mfd.c
+++ b/drivers/mfd/cs5535-mfd.c
@@ -186,18 +186,7 @@ static struct pci_driver cs5535_mfd_driver = {
 	.remove = __devexit_p(cs5535_mfd_remove),
 };
 
-static int __init cs5535_mfd_init(void)
-{
-	return pci_register_driver(&cs5535_mfd_driver);
-}
-
-static void __exit cs5535_mfd_exit(void)
-{
-	pci_unregister_driver(&cs5535_mfd_driver);
-}
-
-module_init(cs5535_mfd_init);
-module_exit(cs5535_mfd_exit);
+module_pci_driver(cs5535_mfd_driver);
 
 MODULE_AUTHOR("Andres Salomon <dilinger@queued.net>");
 MODULE_DESCRIPTION("MFD driver for CS5535/CS5536 southbridge's ISA PCI device");
diff --git a/drivers/mfd/da9052-core.c b/drivers/mfd/da9052-core.c
index 7776aff46269..1f1313c90573 100644
--- a/drivers/mfd/da9052-core.c
+++ b/drivers/mfd/da9052-core.c
@@ -318,6 +318,135 @@ static bool da9052_reg_volatile(struct device *dev, unsigned int reg)
 	}
 }
 
+/*
+ * TBAT look-up table is computed from the R90 reg (8 bit register)
+ * reading as below. The battery temperature is in milliCentigrade
+ * TBAT = (1/(t1+1/298) - 273) * 1000 mC
+ * where t1 = (1/B)* ln(( ADCval * 2.5)/(R25*ITBAT*255))
+ * Default values are R25 = 10e3, B = 3380, ITBAT = 50e-6
+ * Example:
+ * R25=10E3, B=3380, ITBAT=50e-6, ADCVAL=62d calculates
+ * TBAT = 20015 mili degrees Centrigrade
+ *
+*/
+static const int32_t tbat_lookup[255] = {
+	183258, 144221, 124334, 111336, 101826, 94397, 88343, 83257,
+	78889, 75071, 71688, 68656, 65914, 63414, 61120, 59001,
+	570366, 55204, 53490, 51881, 50364, 48931, 47574, 46285,
+	45059, 43889, 42772, 41703, 40678, 39694, 38748, 37838,
+	36961, 36115, 35297, 34507, 33743, 33002, 32284, 31588,
+	30911, 30254, 29615, 28994, 28389, 27799, 27225, 26664,
+	26117, 25584, 25062, 24553, 24054, 23567, 23091, 22624,
+	22167, 21719, 21281, 20851, 20429, 20015, 19610, 19211,
+	18820, 18436, 18058, 17688, 17323, 16965, 16612, 16266,
+	15925, 15589, 15259, 14933, 14613, 14298, 13987, 13681,
+	13379, 13082, 12788, 12499, 12214, 11933, 11655, 11382,
+	11112, 10845, 10582, 10322, 10066, 9812, 9562, 9315,
+	9071, 8830, 8591, 8356, 8123, 7893, 7665, 7440,
+	7218, 6998, 6780, 6565, 6352, 6141, 5933, 5726,
+	5522, 5320, 5120, 4922, 4726, 4532, 4340, 4149,
+	3961, 3774, 3589, 3406, 3225, 3045, 2867, 2690,
+	2516, 2342, 2170, 2000, 1831, 1664, 1498, 1334,
+	1171, 1009, 849, 690, 532, 376, 221, 67,
+	-84, -236, -386, -535, -683, -830, -975, -1119,
+	-1263, -1405, -1546, -1686, -1825, -1964, -2101, -2237,
+	-2372, -2506, -2639, -2771, -2902, -3033, -3162, -3291,
+	-3418, -3545, -3671, -3796, -3920, -4044, -4166, -4288,
+	-4409, -4529, -4649, -4767, -4885, -5002, -5119, -5235,
+	-5349, -5464, -5577, -5690, -5802, -5913, -6024, -6134,
+	-6244, -6352, -6461, -6568, -6675, -6781, -6887, -6992,
+	-7096, -7200, -7303, -7406, -7508, -7609, -7710, -7810,
+	-7910, -8009, -8108, -8206, -8304, -8401, -8497, -8593,
+	-8689, -8784, -8878, -8972, -9066, -9159, -9251, -9343,
+	-9435, -9526, -9617, -9707, -9796, -9886, -9975, -10063,
+	-10151, -10238, -10325, -10412, -10839, -10923, -11007, -11090,
+	-11173, -11256, -11338, -11420, -11501, -11583, -11663, -11744,
+	-11823, -11903, -11982
+};
+
+static const u8 chan_mux[DA9052_ADC_VBBAT + 1] = {
+	[DA9052_ADC_VDDOUT]	= DA9052_ADC_MAN_MUXSEL_VDDOUT,
+	[DA9052_ADC_ICH]	= DA9052_ADC_MAN_MUXSEL_ICH,
+	[DA9052_ADC_TBAT]	= DA9052_ADC_MAN_MUXSEL_TBAT,
+	[DA9052_ADC_VBAT]	= DA9052_ADC_MAN_MUXSEL_VBAT,
+	[DA9052_ADC_IN4]	= DA9052_ADC_MAN_MUXSEL_AD4,
+	[DA9052_ADC_IN5]	= DA9052_ADC_MAN_MUXSEL_AD5,
+	[DA9052_ADC_IN6]	= DA9052_ADC_MAN_MUXSEL_AD6,
+	[DA9052_ADC_VBBAT]	= DA9052_ADC_MAN_MUXSEL_VBBAT
+};
+
+int da9052_adc_manual_read(struct da9052 *da9052, unsigned char channel)
+{
+	int ret;
+	unsigned short calc_data;
+	unsigned short data;
+	unsigned char mux_sel;
+
+	if (channel > DA9052_ADC_VBBAT)
+		return -EINVAL;
+
+	mutex_lock(&da9052->auxadc_lock);
+
+	/* Channel gets activated on enabling the Conversion bit */
+	mux_sel = chan_mux[channel] | DA9052_ADC_MAN_MAN_CONV;
+
+	ret = da9052_reg_write(da9052, DA9052_ADC_MAN_REG, mux_sel);
+	if (ret < 0)
+		goto err;
+
+	/* Wait for an interrupt */
+	if (!wait_for_completion_timeout(&da9052->done,
+					 msecs_to_jiffies(500))) {
+		dev_err(da9052->dev,
+			"timeout waiting for ADC conversion interrupt\n");
+		ret = -ETIMEDOUT;
+		goto err;
+	}
+
+	ret = da9052_reg_read(da9052, DA9052_ADC_RES_H_REG);
+	if (ret < 0)
+		goto err;
+
+	calc_data = (unsigned short)ret;
+	data = calc_data << 2;
+
+	ret = da9052_reg_read(da9052, DA9052_ADC_RES_L_REG);
+	if (ret < 0)
+		goto err;
+
+	calc_data = (unsigned short)(ret & DA9052_ADC_RES_LSB);
+	data |= calc_data;
+
+	ret = data;
+
+err:
+	mutex_unlock(&da9052->auxadc_lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(da9052_adc_manual_read);
+
+static irqreturn_t da9052_auxadc_irq(int irq, void *irq_data)
+{
+	struct da9052 *da9052 = irq_data;
+
+	complete(&da9052->done);
+
+	return IRQ_HANDLED;
+}
+
+int da9052_adc_read_temp(struct da9052 *da9052)
+{
+	int tbat;
+
+	tbat = da9052_reg_read(da9052, DA9052_TBAT_RES_REG);
+	if (tbat <= 0)
+		return tbat;
+
+	/* ARRAY_SIZE check is not needed since TBAT is a 8-bit register */
+	return tbat_lookup[tbat - 1];
+}
+EXPORT_SYMBOL_GPL(da9052_adc_read_temp);
+
 static struct resource da9052_rtc_resource = {
 	.name = "ALM",
 	.start = DA9052_IRQ_ALARM,
@@ -646,6 +775,9 @@ int __devinit da9052_device_init(struct da9052 *da9052, u8 chip_id)
 	struct irq_desc *desc;
 	int ret;
 
+	mutex_init(&da9052->auxadc_lock);
+	init_completion(&da9052->done);
+
 	if (pdata && pdata->init != NULL)
 		pdata->init(da9052);
 
@@ -665,6 +797,12 @@ int __devinit da9052_device_init(struct da9052 *da9052, u8 chip_id)
 
 	da9052->irq_base = regmap_irq_chip_get_base(da9052->irq_data);
 
+	ret = request_threaded_irq(DA9052_IRQ_ADC_EOM, NULL, da9052_auxadc_irq,
+				   IRQF_TRIGGER_LOW | IRQF_ONESHOT,
+				   "adc irq", da9052);
+	if (ret != 0)
+		dev_err(da9052->dev, "DA9052 ADC IRQ failed ret=%d\n", ret);
+
 	ret = mfd_add_devices(da9052->dev, -1, da9052_subdev_info,
 			      ARRAY_SIZE(da9052_subdev_info), NULL, 0);
 	if (ret)
@@ -673,6 +811,7 @@ int __devinit da9052_device_init(struct da9052 *da9052, u8 chip_id)
 	return 0;
 
 err:
+	free_irq(DA9052_IRQ_ADC_EOM, da9052);
 	mfd_remove_devices(da9052->dev);
 regmap_err:
 	return ret;
@@ -680,6 +819,7 @@ regmap_err:
 
 void da9052_device_exit(struct da9052 *da9052)
 {
+	free_irq(DA9052_IRQ_ADC_EOM, da9052);
 	regmap_del_irq_chip(da9052->chip_irq, da9052->irq_data);
 	mfd_remove_devices(da9052->dev);
 }
diff --git a/drivers/mfd/da9052-i2c.c b/drivers/mfd/da9052-i2c.c
index 36b88e395499..82c9d6450286 100644
--- a/drivers/mfd/da9052-i2c.c
+++ b/drivers/mfd/da9052-i2c.c
@@ -22,6 +22,11 @@
 #include <linux/mfd/da9052/da9052.h>
 #include <linux/mfd/da9052/reg.h>
 
+#ifdef CONFIG_OF
+#include <linux/of.h>
+#include <linux/of_device.h>
+#endif
+
 static int da9052_i2c_enable_multiwrite(struct da9052 *da9052)
 {
 	int reg_val, ret;
@@ -41,13 +46,31 @@ static int da9052_i2c_enable_multiwrite(struct da9052 *da9052)
 	return 0;
 }
 
+static struct i2c_device_id da9052_i2c_id[] = {
+	{"da9052", DA9052},
+	{"da9053-aa", DA9053_AA},
+	{"da9053-ba", DA9053_BA},
+	{"da9053-bb", DA9053_BB},
+	{}
+};
+
+#ifdef CONFIG_OF
+static const struct of_device_id dialog_dt_ids[] = {
+	{ .compatible = "dlg,da9052", .data = &da9052_i2c_id[0] },
+	{ .compatible = "dlg,da9053-aa", .data = &da9052_i2c_id[1] },
+	{ .compatible = "dlg,da9053-ab", .data = &da9052_i2c_id[2] },
+	{ .compatible = "dlg,da9053-bb", .data = &da9052_i2c_id[3] },
+	{ /* sentinel */ }
+};
+#endif
+
 static int __devinit da9052_i2c_probe(struct i2c_client *client,
 				       const struct i2c_device_id *id)
 {
 	struct da9052 *da9052;
 	int ret;
 
-	da9052 = kzalloc(sizeof(struct da9052), GFP_KERNEL);
+	da9052 = devm_kzalloc(&client->dev, sizeof(struct da9052), GFP_KERNEL);
 	if (!da9052)
 		return -ENOMEM;
 
@@ -55,8 +78,7 @@ static int __devinit da9052_i2c_probe(struct i2c_client *client,
 				     I2C_FUNC_SMBUS_BYTE_DATA)) {
 		dev_info(&client->dev, "Error in %s:i2c_check_functionality\n",
 			 __func__);
-		ret = -ENODEV;
-		goto err;
+		return  -ENODEV;
 	}
 
 	da9052->dev = &client->dev;
@@ -64,29 +86,39 @@ static int __devinit da9052_i2c_probe(struct i2c_client *client,
 
 	i2c_set_clientdata(client, da9052);
 
-	da9052->regmap = regmap_init_i2c(client, &da9052_regmap_config);
+	da9052->regmap = devm_regmap_init_i2c(client, &da9052_regmap_config);
 	if (IS_ERR(da9052->regmap)) {
 		ret = PTR_ERR(da9052->regmap);
 		dev_err(&client->dev, "Failed to allocate register map: %d\n",
 			ret);
-		goto err;
+		return ret;
 	}
 
 	ret = da9052_i2c_enable_multiwrite(da9052);
 	if (ret < 0)
-		goto err_regmap;
+		return ret;
+
+#ifdef CONFIG_OF
+	if (!id) {
+		struct device_node *np = client->dev.of_node;
+		const struct of_device_id *deviceid;
+
+		deviceid = of_match_node(dialog_dt_ids, np);
+		id = (const struct i2c_device_id *)deviceid->data;
+	}
+#endif
+
+	if (!id) {
+		ret = -ENODEV;
+		dev_err(&client->dev, "id is null.\n");
+		return ret;
+	}
 
 	ret = da9052_device_init(da9052, id->driver_data);
 	if (ret != 0)
-		goto err_regmap;
+		return ret;
 
 	return 0;
-
-err_regmap:
-	regmap_exit(da9052->regmap);
-err:
-	kfree(da9052);
-	return ret;
 }
 
 static int __devexit da9052_i2c_remove(struct i2c_client *client)
@@ -94,20 +126,9 @@ static int __devexit da9052_i2c_remove(struct i2c_client *client)
 	struct da9052 *da9052 = i2c_get_clientdata(client);
 
 	da9052_device_exit(da9052);
-	regmap_exit(da9052->regmap);
-	kfree(da9052);
-
 	return 0;
 }
 
-static struct i2c_device_id da9052_i2c_id[] = {
-	{"da9052", DA9052},
-	{"da9053-aa", DA9053_AA},
-	{"da9053-ba", DA9053_BA},
-	{"da9053-bb", DA9053_BB},
-	{}
-};
-
 static struct i2c_driver da9052_i2c_driver = {
 	.probe = da9052_i2c_probe,
 	.remove = __devexit_p(da9052_i2c_remove),
@@ -115,6 +136,9 @@ static struct i2c_driver da9052_i2c_driver = {
 	.driver = {
 		.name = "da9052",
 		.owner = THIS_MODULE,
+#ifdef CONFIG_OF
+		.of_match_table = dialog_dt_ids,
+#endif
 	},
 };
 
diff --git a/drivers/mfd/da9052-spi.c b/drivers/mfd/da9052-spi.c
index 6faf149e8d94..dbeadc5a6436 100644
--- a/drivers/mfd/da9052-spi.c
+++ b/drivers/mfd/da9052-spi.c
@@ -25,8 +25,9 @@ static int __devinit da9052_spi_probe(struct spi_device *spi)
 {
 	int ret;
 	const struct spi_device_id *id = spi_get_device_id(spi);
-	struct da9052 *da9052 = kzalloc(sizeof(struct da9052), GFP_KERNEL);
+	struct da9052 *da9052;
 
+	da9052 = devm_kzalloc(&spi->dev, sizeof(struct da9052), GFP_KERNEL);
 	if (!da9052)
 		return -ENOMEM;
 
@@ -42,25 +43,19 @@ static int __devinit da9052_spi_probe(struct spi_device *spi)
 	da9052_regmap_config.read_flag_mask = 1;
 	da9052_regmap_config.write_flag_mask = 0;
 
-	da9052->regmap = regmap_init_spi(spi, &da9052_regmap_config);
+	da9052->regmap = devm_regmap_init_spi(spi, &da9052_regmap_config);
 	if (IS_ERR(da9052->regmap)) {
 		ret = PTR_ERR(da9052->regmap);
 		dev_err(&spi->dev, "Failed to allocate register map: %d\n",
 			ret);
-		goto err;
+		return ret;
 	}
 
 	ret = da9052_device_init(da9052, id->driver_data);
 	if (ret != 0)
-		goto err_regmap;
+		return ret;
 
 	return 0;
-
-err_regmap:
-	regmap_exit(da9052->regmap);
-err:
-	kfree(da9052);
-	return ret;
 }
 
 static int __devexit da9052_spi_remove(struct spi_device *spi)
@@ -68,9 +63,6 @@ static int __devexit da9052_spi_remove(struct spi_device *spi)
 	struct da9052 *da9052 = dev_get_drvdata(&spi->dev);
 
 	da9052_device_exit(da9052);
-	regmap_exit(da9052->regmap);
-	kfree(da9052);
-
 	return 0;
 }
 
@@ -88,7 +80,6 @@ static struct spi_driver da9052_spi_driver = {
 	.id_table = da9052_spi_id,
 	.driver = {
 		.name = "da9052",
-		.bus = &spi_bus_type,
 		.owner = THIS_MODULE,
 	},
 };
diff --git a/drivers/mfd/db8500-prcmu.c b/drivers/mfd/db8500-prcmu.c
index 5be32489714f..671c8bc14bbc 100644
--- a/drivers/mfd/db8500-prcmu.c
+++ b/drivers/mfd/db8500-prcmu.c
@@ -2720,6 +2720,7 @@ static struct regulator_consumer_supply db8500_vape_consumers[] = {
 	REGULATOR_SUPPLY("v-i2c", "nmk-i2c.1"),
 	REGULATOR_SUPPLY("v-i2c", "nmk-i2c.2"),
 	REGULATOR_SUPPLY("v-i2c", "nmk-i2c.3"),
+	REGULATOR_SUPPLY("v-i2c", "nmk-i2c.4"),
 	/* "v-mmc" changed to "vcore" in the mainline kernel */
 	REGULATOR_SUPPLY("vcore", "sdi0"),
 	REGULATOR_SUPPLY("vcore", "sdi1"),
@@ -2958,9 +2959,10 @@ static struct mfd_cell db8500_prcmu_devs[] = {
  * prcmu_fw_init - arch init call for the Linux PRCMU fw init logic
  *
  */
-static int __init db8500_prcmu_probe(struct platform_device *pdev)
+static int __devinit db8500_prcmu_probe(struct platform_device *pdev)
 {
-	int err = 0;
+	struct device_node *np = pdev->dev.of_node;
+	int irq = 0, err = 0;
 
 	if (ux500_is_svp())
 		return -ENODEV;
@@ -2970,8 +2972,14 @@ static int __init db8500_prcmu_probe(struct platform_device *pdev)
 	/* Clean up the mailbox interrupts after pre-kernel code. */
 	writel(ALL_MBOX_BITS, PRCM_ARM_IT1_CLR);
 
-	err = request_threaded_irq(IRQ_DB8500_PRCMU1, prcmu_irq_handler,
-		prcmu_irq_thread_fn, IRQF_NO_SUSPEND, "prcmu", NULL);
+	if (np)
+		irq = platform_get_irq(pdev, 0);
+
+	if (!np || irq <= 0)
+		irq = IRQ_DB8500_PRCMU1;
+
+	err = request_threaded_irq(irq, prcmu_irq_handler,
+	        prcmu_irq_thread_fn, IRQF_NO_SUSPEND, "prcmu", NULL);
 	if (err < 0) {
 		pr_err("prcmu: Failed to allocate IRQ_DB8500_PRCMU1.\n");
 		err = -EBUSY;
@@ -2981,14 +2989,16 @@ static int __init db8500_prcmu_probe(struct platform_device *pdev)
 	if (cpu_is_u8500v20_or_later())
 		prcmu_config_esram0_deep_sleep(ESRAM0_DEEP_SLEEP_STATE_RET);
 
-	err = mfd_add_devices(&pdev->dev, 0, db8500_prcmu_devs,
-			      ARRAY_SIZE(db8500_prcmu_devs), NULL,
-			      0);
+	if (!np) {
+		err = mfd_add_devices(&pdev->dev, 0, db8500_prcmu_devs,
+				ARRAY_SIZE(db8500_prcmu_devs), NULL, 0);
+		if (err) {
+			pr_err("prcmu: Failed to add subdevices\n");
+			return err;
+		}
+	}
 
-	if (err)
-		pr_err("prcmu: Failed to add subdevices\n");
-	else
-		pr_info("DB8500 PRCMU initialized\n");
+	pr_info("DB8500 PRCMU initialized\n");
 
 no_irq_return:
 	return err;
@@ -2999,11 +3009,12 @@ static struct platform_driver db8500_prcmu_driver = {
 		.name = "db8500-prcmu",
 		.owner = THIS_MODULE,
 	},
+	.probe = db8500_prcmu_probe,
 };
 
 static int __init db8500_prcmu_init(void)
 {
-	return platform_driver_probe(&db8500_prcmu_driver, db8500_prcmu_probe);
+	return platform_driver_register(&db8500_prcmu_driver);
 }
 
 arch_initcall(db8500_prcmu_init);
diff --git a/drivers/mfd/intel_msic.c b/drivers/mfd/intel_msic.c
index b76657eb0c51..59df5584cb58 100644
--- a/drivers/mfd/intel_msic.c
+++ b/drivers/mfd/intel_msic.c
@@ -406,7 +406,7 @@ static int __devinit intel_msic_probe(struct platform_device *pdev)
 		return -ENXIO;
 	}
 
-	msic = kzalloc(sizeof(*msic), GFP_KERNEL);
+	msic = devm_kzalloc(&pdev->dev, sizeof(*msic), GFP_KERNEL);
 	if (!msic)
 		return -ENOMEM;
 
@@ -421,21 +421,13 @@ static int __devinit intel_msic_probe(struct platform_device *pdev)
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res) {
 		dev_err(&pdev->dev, "failed to get SRAM iomem resource\n");
-		ret = -ENODEV;
-		goto fail_free_msic;
+		return -ENODEV;
 	}
 
-	res = request_mem_region(res->start, resource_size(res), pdev->name);
-	if (!res) {
-		ret = -EBUSY;
-		goto fail_free_msic;
-	}
-
-	msic->irq_base = ioremap_nocache(res->start, resource_size(res));
+	msic->irq_base = devm_request_and_ioremap(&pdev->dev, res);
 	if (!msic->irq_base) {
 		dev_err(&pdev->dev, "failed to map SRAM memory\n");
-		ret = -ENOMEM;
-		goto fail_release_region;
+		return -ENOMEM;
 	}
 
 	platform_set_drvdata(pdev, msic);
@@ -443,7 +435,7 @@ static int __devinit intel_msic_probe(struct platform_device *pdev)
 	ret = intel_msic_init_devices(msic);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to initialize MSIC devices\n");
-		goto fail_unmap_mem;
+		return ret;
 	}
 
 	dev_info(&pdev->dev, "Intel MSIC version %c%d (vendor %#x)\n",
@@ -451,27 +443,14 @@ static int __devinit intel_msic_probe(struct platform_device *pdev)
 		 msic->vendor);
 
 	return 0;
-
-fail_unmap_mem:
-	iounmap(msic->irq_base);
-fail_release_region:
-	release_mem_region(res->start, resource_size(res));
-fail_free_msic:
-	kfree(msic);
-
-	return ret;
 }
 
 static int __devexit intel_msic_remove(struct platform_device *pdev)
 {
 	struct intel_msic *msic = platform_get_drvdata(pdev);
-	struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 
 	intel_msic_remove_devices(msic);
 	platform_set_drvdata(pdev, NULL);
-	iounmap(msic->irq_base);
-	release_mem_region(res->start, resource_size(res));
-	kfree(msic);
 
 	return 0;
 }
diff --git a/drivers/mfd/janz-cmodio.c b/drivers/mfd/janz-cmodio.c
index a9223ed1b7c5..2ea99989551a 100644
--- a/drivers/mfd/janz-cmodio.c
+++ b/drivers/mfd/janz-cmodio.c
@@ -283,23 +283,8 @@ static struct pci_driver cmodio_pci_driver = {
 	.remove   = __devexit_p(cmodio_pci_remove),
 };
 
-/*
- * Module Init / Exit
- */
-
-static int __init cmodio_init(void)
-{
-	return pci_register_driver(&cmodio_pci_driver);
-}
-
-static void __exit cmodio_exit(void)
-{
-	pci_unregister_driver(&cmodio_pci_driver);
-}
+module_pci_driver(cmodio_pci_driver);
 
 MODULE_AUTHOR("Ira W. Snyder <iws@ovro.caltech.edu>");
 MODULE_DESCRIPTION("Janz CMOD-IO PCI MODULbus Carrier Board Driver");
 MODULE_LICENSE("GPL");
-
-module_init(cmodio_init);
-module_exit(cmodio_exit);
diff --git a/drivers/mfd/lm3533-core.c b/drivers/mfd/lm3533-core.c
new file mode 100644
index 000000000000..0b2879b87fd9
--- /dev/null
+++ b/drivers/mfd/lm3533-core.c
@@ -0,0 +1,667 @@
+/*
+ * lm3533-core.c -- LM3533 Core
+ *
+ * Copyright (C) 2011-2012 Texas Instruments
+ *
+ * Author: Johan Hovold <jhovold@gmail.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.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/err.h>
+#include <linux/gpio.h>
+#include <linux/i2c.h>
+#include <linux/mfd/core.h>
+#include <linux/regmap.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+
+#include <linux/mfd/lm3533.h>
+
+
+#define LM3533_BOOST_OVP_MASK		0x06
+#define LM3533_BOOST_OVP_SHIFT		1
+
+#define LM3533_BOOST_FREQ_MASK		0x01
+#define LM3533_BOOST_FREQ_SHIFT		0
+
+#define LM3533_BL_ID_MASK		1
+#define LM3533_LED_ID_MASK		3
+#define LM3533_BL_ID_MAX		1
+#define LM3533_LED_ID_MAX		3
+
+#define LM3533_HVLED_ID_MAX		2
+#define LM3533_LVLED_ID_MAX		5
+
+#define LM3533_REG_OUTPUT_CONF1		0x10
+#define LM3533_REG_OUTPUT_CONF2		0x11
+#define LM3533_REG_BOOST_PWM		0x2c
+
+#define LM3533_REG_MAX			0xb2
+
+
+static struct mfd_cell lm3533_als_devs[] = {
+	{
+		.name	= "lm3533-als",
+		.id	= -1,
+	},
+};
+
+static struct mfd_cell lm3533_bl_devs[] = {
+	{
+		.name	= "lm3533-backlight",
+		.id	= 0,
+	},
+	{
+		.name	= "lm3533-backlight",
+		.id	= 1,
+	},
+};
+
+static struct mfd_cell lm3533_led_devs[] = {
+	{
+		.name	= "lm3533-leds",
+		.id	= 0,
+	},
+	{
+		.name	= "lm3533-leds",
+		.id	= 1,
+	},
+	{
+		.name	= "lm3533-leds",
+		.id	= 2,
+	},
+	{
+		.name	= "lm3533-leds",
+		.id	= 3,
+	},
+};
+
+int lm3533_read(struct lm3533 *lm3533, u8 reg, u8 *val)
+{
+	int tmp;
+	int ret;
+
+	ret = regmap_read(lm3533->regmap, reg, &tmp);
+	if (ret < 0) {
+		dev_err(lm3533->dev, "failed to read register %02x: %d\n",
+								reg, ret);
+		return ret;
+	}
+
+	*val = tmp;
+
+	dev_dbg(lm3533->dev, "read [%02x]: %02x\n", reg, *val);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(lm3533_read);
+
+int lm3533_write(struct lm3533 *lm3533, u8 reg, u8 val)
+{
+	int ret;
+
+	dev_dbg(lm3533->dev, "write [%02x]: %02x\n", reg, val);
+
+	ret = regmap_write(lm3533->regmap, reg, val);
+	if (ret < 0) {
+		dev_err(lm3533->dev, "failed to write register %02x: %d\n",
+								reg, ret);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(lm3533_write);
+
+int lm3533_update(struct lm3533 *lm3533, u8 reg, u8 val, u8 mask)
+{
+	int ret;
+
+	dev_dbg(lm3533->dev, "update [%02x]: %02x/%02x\n", reg, val, mask);
+
+	ret = regmap_update_bits(lm3533->regmap, reg, mask, val);
+	if (ret < 0) {
+		dev_err(lm3533->dev, "failed to update register %02x: %d\n",
+								reg, ret);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(lm3533_update);
+
+static int lm3533_set_boost_freq(struct lm3533 *lm3533,
+						enum lm3533_boost_freq freq)
+{
+	int ret;
+
+	ret = lm3533_update(lm3533, LM3533_REG_BOOST_PWM,
+					freq << LM3533_BOOST_FREQ_SHIFT,
+					LM3533_BOOST_FREQ_MASK);
+	if (ret)
+		dev_err(lm3533->dev, "failed to set boost frequency\n");
+
+	return ret;
+}
+
+
+static int lm3533_set_boost_ovp(struct lm3533 *lm3533,
+						enum lm3533_boost_ovp ovp)
+{
+	int ret;
+
+	ret = lm3533_update(lm3533, LM3533_REG_BOOST_PWM,
+					ovp << LM3533_BOOST_OVP_SHIFT,
+					LM3533_BOOST_OVP_MASK);
+	if (ret)
+		dev_err(lm3533->dev, "failed to set boost ovp\n");
+
+	return ret;
+}
+
+/*
+ * HVLED output config -- output hvled controlled by backlight bl
+ */
+static int lm3533_set_hvled_config(struct lm3533 *lm3533, u8 hvled, u8 bl)
+{
+	u8 val;
+	u8 mask;
+	int shift;
+	int ret;
+
+	if (hvled == 0 || hvled > LM3533_HVLED_ID_MAX)
+		return -EINVAL;
+
+	if (bl > LM3533_BL_ID_MAX)
+		return -EINVAL;
+
+	shift = hvled - 1;
+	mask = LM3533_BL_ID_MASK << shift;
+	val = bl << shift;
+
+	ret = lm3533_update(lm3533, LM3533_REG_OUTPUT_CONF1, val, mask);
+	if (ret)
+		dev_err(lm3533->dev, "failed to set hvled config\n");
+
+	return ret;
+}
+
+/*
+ * LVLED output config -- output lvled controlled by LED led
+ */
+static int lm3533_set_lvled_config(struct lm3533 *lm3533, u8 lvled, u8 led)
+{
+	u8 reg;
+	u8 val;
+	u8 mask;
+	int shift;
+	int ret;
+
+	if (lvled == 0 || lvled > LM3533_LVLED_ID_MAX)
+		return -EINVAL;
+
+	if (led > LM3533_LED_ID_MAX)
+		return -EINVAL;
+
+	if (lvled < 4) {
+		reg = LM3533_REG_OUTPUT_CONF1;
+		shift = 2 * lvled;
+	} else {
+		reg = LM3533_REG_OUTPUT_CONF2;
+		shift = 2 * (lvled - 4);
+	}
+
+	mask = LM3533_LED_ID_MASK << shift;
+	val = led << shift;
+
+	ret = lm3533_update(lm3533, reg, val, mask);
+	if (ret)
+		dev_err(lm3533->dev, "failed to set lvled config\n");
+
+	return ret;
+}
+
+static void lm3533_enable(struct lm3533 *lm3533)
+{
+	if (gpio_is_valid(lm3533->gpio_hwen))
+		gpio_set_value(lm3533->gpio_hwen, 1);
+}
+
+static void lm3533_disable(struct lm3533 *lm3533)
+{
+	if (gpio_is_valid(lm3533->gpio_hwen))
+		gpio_set_value(lm3533->gpio_hwen, 0);
+}
+
+enum lm3533_attribute_type {
+	LM3533_ATTR_TYPE_BACKLIGHT,
+	LM3533_ATTR_TYPE_LED,
+};
+
+struct lm3533_device_attribute {
+	struct device_attribute dev_attr;
+	enum lm3533_attribute_type type;
+	union {
+		struct {
+			u8 id;
+		} output;
+	} u;
+};
+
+#define to_lm3533_dev_attr(_attr) \
+	container_of(_attr, struct lm3533_device_attribute, dev_attr)
+
+static ssize_t show_output(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct lm3533 *lm3533 = dev_get_drvdata(dev);
+	struct lm3533_device_attribute *lattr = to_lm3533_dev_attr(attr);
+	int id = lattr->u.output.id;
+	u8 reg;
+	u8 val;
+	u8 mask;
+	int shift;
+	int ret;
+
+	if (lattr->type == LM3533_ATTR_TYPE_BACKLIGHT) {
+		reg = LM3533_REG_OUTPUT_CONF1;
+		shift = id - 1;
+		mask = LM3533_BL_ID_MASK << shift;
+	} else {
+		if (id < 4) {
+			reg = LM3533_REG_OUTPUT_CONF1;
+			shift = 2 * id;
+		} else {
+			reg = LM3533_REG_OUTPUT_CONF2;
+			shift = 2 * (id - 4);
+		}
+		mask = LM3533_LED_ID_MASK << shift;
+	}
+
+	ret = lm3533_read(lm3533, reg, &val);
+	if (ret)
+		return ret;
+
+	val = (val & mask) >> shift;
+
+	return scnprintf(buf, PAGE_SIZE, "%u\n", val);
+}
+
+static ssize_t store_output(struct device *dev,
+					struct device_attribute *attr,
+					const char *buf, size_t len)
+{
+	struct lm3533 *lm3533 = dev_get_drvdata(dev);
+	struct lm3533_device_attribute *lattr = to_lm3533_dev_attr(attr);
+	int id = lattr->u.output.id;
+	u8 val;
+	int ret;
+
+	if (kstrtou8(buf, 0, &val))
+		return -EINVAL;
+
+	if (lattr->type == LM3533_ATTR_TYPE_BACKLIGHT)
+		ret = lm3533_set_hvled_config(lm3533, id, val);
+	else
+		ret = lm3533_set_lvled_config(lm3533, id, val);
+
+	if (ret)
+		return ret;
+
+	return len;
+}
+
+#define LM3533_OUTPUT_ATTR(_name, _mode, _show, _store, _type, _id) \
+	struct lm3533_device_attribute lm3533_dev_attr_##_name = \
+		{ .dev_attr	= __ATTR(_name, _mode, _show, _store), \
+		  .type		= _type, \
+		  .u.output	= { .id = _id }, }
+
+#define LM3533_OUTPUT_ATTR_RW(_name, _type, _id) \
+	LM3533_OUTPUT_ATTR(output_##_name, S_IRUGO | S_IWUSR, \
+					show_output, store_output, _type, _id)
+
+#define LM3533_OUTPUT_HVLED_ATTR_RW(_nr) \
+	LM3533_OUTPUT_ATTR_RW(hvled##_nr, LM3533_ATTR_TYPE_BACKLIGHT, _nr)
+#define LM3533_OUTPUT_LVLED_ATTR_RW(_nr) \
+	LM3533_OUTPUT_ATTR_RW(lvled##_nr, LM3533_ATTR_TYPE_LED, _nr)
+/*
+ * Output config:
+ *
+ * output_hvled<nr>	0-1
+ * output_lvled<nr>	0-3
+ */
+static LM3533_OUTPUT_HVLED_ATTR_RW(1);
+static LM3533_OUTPUT_HVLED_ATTR_RW(2);
+static LM3533_OUTPUT_LVLED_ATTR_RW(1);
+static LM3533_OUTPUT_LVLED_ATTR_RW(2);
+static LM3533_OUTPUT_LVLED_ATTR_RW(3);
+static LM3533_OUTPUT_LVLED_ATTR_RW(4);
+static LM3533_OUTPUT_LVLED_ATTR_RW(5);
+
+static struct attribute *lm3533_attributes[] = {
+	&lm3533_dev_attr_output_hvled1.dev_attr.attr,
+	&lm3533_dev_attr_output_hvled2.dev_attr.attr,
+	&lm3533_dev_attr_output_lvled1.dev_attr.attr,
+	&lm3533_dev_attr_output_lvled2.dev_attr.attr,
+	&lm3533_dev_attr_output_lvled3.dev_attr.attr,
+	&lm3533_dev_attr_output_lvled4.dev_attr.attr,
+	&lm3533_dev_attr_output_lvled5.dev_attr.attr,
+	NULL,
+};
+
+#define to_dev_attr(_attr) \
+	container_of(_attr, struct device_attribute, attr)
+
+static umode_t lm3533_attr_is_visible(struct kobject *kobj,
+					     struct attribute *attr, int n)
+{
+	struct device *dev = container_of(kobj, struct device, kobj);
+	struct lm3533 *lm3533 = dev_get_drvdata(dev);
+	struct device_attribute *dattr = to_dev_attr(attr);
+	struct lm3533_device_attribute *lattr = to_lm3533_dev_attr(dattr);
+	enum lm3533_attribute_type type = lattr->type;
+	umode_t mode = attr->mode;
+
+	if (!lm3533->have_backlights && type == LM3533_ATTR_TYPE_BACKLIGHT)
+		mode = 0;
+	else if (!lm3533->have_leds && type == LM3533_ATTR_TYPE_LED)
+		mode = 0;
+
+	return mode;
+};
+
+static struct attribute_group lm3533_attribute_group = {
+	.is_visible	= lm3533_attr_is_visible,
+	.attrs		= lm3533_attributes
+};
+
+static int __devinit lm3533_device_als_init(struct lm3533 *lm3533)
+{
+	struct lm3533_platform_data *pdata = lm3533->dev->platform_data;
+	int ret;
+
+	if (!pdata->als)
+		return 0;
+
+	lm3533_als_devs[0].platform_data = pdata->als;
+	lm3533_als_devs[0].pdata_size = sizeof(*pdata->als);
+
+	ret = mfd_add_devices(lm3533->dev, 0, lm3533_als_devs, 1, NULL, 0);
+	if (ret) {
+		dev_err(lm3533->dev, "failed to add ALS device\n");
+		return ret;
+	}
+
+	lm3533->have_als = 1;
+
+	return 0;
+}
+
+static int __devinit lm3533_device_bl_init(struct lm3533 *lm3533)
+{
+	struct lm3533_platform_data *pdata = lm3533->dev->platform_data;
+	int i;
+	int ret;
+
+	if (!pdata->backlights || pdata->num_backlights == 0)
+		return 0;
+
+	if (pdata->num_backlights > ARRAY_SIZE(lm3533_bl_devs))
+		pdata->num_backlights = ARRAY_SIZE(lm3533_bl_devs);
+
+	for (i = 0; i < pdata->num_backlights; ++i) {
+		lm3533_bl_devs[i].platform_data = &pdata->backlights[i];
+		lm3533_bl_devs[i].pdata_size = sizeof(pdata->backlights[i]);
+	}
+
+	ret = mfd_add_devices(lm3533->dev, 0, lm3533_bl_devs,
+					pdata->num_backlights, NULL, 0);
+	if (ret) {
+		dev_err(lm3533->dev, "failed to add backlight devices\n");
+		return ret;
+	}
+
+	lm3533->have_backlights = 1;
+
+	return 0;
+}
+
+static int __devinit lm3533_device_led_init(struct lm3533 *lm3533)
+{
+	struct lm3533_platform_data *pdata = lm3533->dev->platform_data;
+	int i;
+	int ret;
+
+	if (!pdata->leds || pdata->num_leds == 0)
+		return 0;
+
+	if (pdata->num_leds > ARRAY_SIZE(lm3533_led_devs))
+		pdata->num_leds = ARRAY_SIZE(lm3533_led_devs);
+
+	for (i = 0; i < pdata->num_leds; ++i) {
+		lm3533_led_devs[i].platform_data = &pdata->leds[i];
+		lm3533_led_devs[i].pdata_size = sizeof(pdata->leds[i]);
+	}
+
+	ret = mfd_add_devices(lm3533->dev, 0, lm3533_led_devs,
+						pdata->num_leds, NULL, 0);
+	if (ret) {
+		dev_err(lm3533->dev, "failed to add LED devices\n");
+		return ret;
+	}
+
+	lm3533->have_leds = 1;
+
+	return 0;
+}
+
+static int __devinit lm3533_device_setup(struct lm3533 *lm3533,
+					struct lm3533_platform_data *pdata)
+{
+	int ret;
+
+	ret = lm3533_set_boost_freq(lm3533, pdata->boost_freq);
+	if (ret)
+		return ret;
+
+	ret = lm3533_set_boost_ovp(lm3533, pdata->boost_ovp);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int __devinit lm3533_device_init(struct lm3533 *lm3533)
+{
+	struct lm3533_platform_data *pdata = lm3533->dev->platform_data;
+	int ret;
+
+	dev_dbg(lm3533->dev, "%s\n", __func__);
+
+	if (!pdata) {
+		dev_err(lm3533->dev, "no platform data\n");
+		return -EINVAL;
+	}
+
+	lm3533->gpio_hwen = pdata->gpio_hwen;
+
+	dev_set_drvdata(lm3533->dev, lm3533);
+
+	if (gpio_is_valid(lm3533->gpio_hwen)) {
+		ret = gpio_request_one(lm3533->gpio_hwen, GPIOF_OUT_INIT_LOW,
+								"lm3533-hwen");
+		if (ret < 0) {
+			dev_err(lm3533->dev,
+				"failed to request HWEN GPIO %d\n",
+				lm3533->gpio_hwen);
+			return ret;
+		}
+	}
+
+	lm3533_enable(lm3533);
+
+	ret = lm3533_device_setup(lm3533, pdata);
+	if (ret)
+		goto err_disable;
+
+	lm3533_device_als_init(lm3533);
+	lm3533_device_bl_init(lm3533);
+	lm3533_device_led_init(lm3533);
+
+	ret = sysfs_create_group(&lm3533->dev->kobj, &lm3533_attribute_group);
+	if (ret < 0) {
+		dev_err(lm3533->dev, "failed to create sysfs attributes\n");
+		goto err_unregister;
+	}
+
+	return 0;
+
+err_unregister:
+	mfd_remove_devices(lm3533->dev);
+err_disable:
+	lm3533_disable(lm3533);
+	if (gpio_is_valid(lm3533->gpio_hwen))
+		gpio_free(lm3533->gpio_hwen);
+
+	return ret;
+}
+
+static void __devexit lm3533_device_exit(struct lm3533 *lm3533)
+{
+	dev_dbg(lm3533->dev, "%s\n", __func__);
+
+	sysfs_remove_group(&lm3533->dev->kobj, &lm3533_attribute_group);
+
+	mfd_remove_devices(lm3533->dev);
+	lm3533_disable(lm3533);
+	if (gpio_is_valid(lm3533->gpio_hwen))
+		gpio_free(lm3533->gpio_hwen);
+}
+
+static bool lm3533_readable_register(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case 0x10 ... 0x2c:
+	case 0x30 ... 0x38:
+	case 0x40 ... 0x45:
+	case 0x50 ... 0x57:
+	case 0x60 ... 0x6e:
+	case 0x70 ... 0x75:
+	case 0x80 ... 0x85:
+	case 0x90 ... 0x95:
+	case 0xa0 ... 0xa5:
+	case 0xb0 ... 0xb2:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool lm3533_volatile_register(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case 0x34 ... 0x36:	/* zone */
+	case 0x37 ... 0x38:	/* adc */
+	case 0xb0 ... 0xb1:	/* fault */
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool lm3533_precious_register(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case 0x34:		/* zone */
+		return true;
+	default:
+		return false;
+	}
+}
+
+static struct regmap_config regmap_config = {
+	.reg_bits	= 8,
+	.val_bits	= 8,
+	.max_register	= LM3533_REG_MAX,
+	.readable_reg	= lm3533_readable_register,
+	.volatile_reg	= lm3533_volatile_register,
+	.precious_reg	= lm3533_precious_register,
+};
+
+static int __devinit lm3533_i2c_probe(struct i2c_client *i2c,
+					const struct i2c_device_id *id)
+{
+	struct lm3533 *lm3533;
+	int ret;
+
+	dev_dbg(&i2c->dev, "%s\n", __func__);
+
+	lm3533 = devm_kzalloc(&i2c->dev, sizeof(*lm3533), GFP_KERNEL);
+	if (!lm3533)
+		return -ENOMEM;
+
+	i2c_set_clientdata(i2c, lm3533);
+
+	lm3533->regmap = devm_regmap_init_i2c(i2c, &regmap_config);
+	if (IS_ERR(lm3533->regmap))
+		return PTR_ERR(lm3533->regmap);
+
+	lm3533->dev = &i2c->dev;
+	lm3533->irq = i2c->irq;
+
+	ret = lm3533_device_init(lm3533);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int __devexit lm3533_i2c_remove(struct i2c_client *i2c)
+{
+	struct lm3533 *lm3533 = i2c_get_clientdata(i2c);
+
+	dev_dbg(&i2c->dev, "%s\n", __func__);
+
+	lm3533_device_exit(lm3533);
+
+	return 0;
+}
+
+static const struct i2c_device_id lm3533_i2c_ids[] = {
+	{ "lm3533", 0 },
+	{ },
+};
+MODULE_DEVICE_TABLE(i2c, lm3533_i2c_ids);
+
+static struct i2c_driver lm3533_i2c_driver = {
+	.driver = {
+		   .name = "lm3533",
+		   .owner = THIS_MODULE,
+	},
+	.id_table	= lm3533_i2c_ids,
+	.probe		= lm3533_i2c_probe,
+	.remove		= __devexit_p(lm3533_i2c_remove),
+};
+
+static int __init lm3533_i2c_init(void)
+{
+	return i2c_add_driver(&lm3533_i2c_driver);
+}
+subsys_initcall(lm3533_i2c_init);
+
+static void __exit lm3533_i2c_exit(void)
+{
+	i2c_del_driver(&lm3533_i2c_driver);
+}
+module_exit(lm3533_i2c_exit);
+
+MODULE_AUTHOR("Johan Hovold <jhovold@gmail.com>");
+MODULE_DESCRIPTION("LM3533 Core");
+MODULE_LICENSE("GPL");
diff --git a/drivers/mfd/lm3533-ctrlbank.c b/drivers/mfd/lm3533-ctrlbank.c
new file mode 100644
index 000000000000..a4cb7a5220a7
--- /dev/null
+++ b/drivers/mfd/lm3533-ctrlbank.c
@@ -0,0 +1,148 @@
+/*
+ * lm3533-ctrlbank.c -- LM3533 Generic Control Bank interface
+ *
+ * Copyright (C) 2011-2012 Texas Instruments
+ *
+ * Author: Johan Hovold <jhovold@gmail.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.
+ */
+
+#include <linux/device.h>
+#include <linux/module.h>
+
+#include <linux/mfd/lm3533.h>
+
+
+#define LM3533_MAX_CURRENT_MIN		5000
+#define LM3533_MAX_CURRENT_MAX		29800
+#define LM3533_MAX_CURRENT_STEP		800
+
+#define LM3533_BRIGHTNESS_MAX		255
+#define LM3533_PWM_MAX			0x3f
+
+#define LM3533_REG_PWM_BASE		0x14
+#define LM3533_REG_MAX_CURRENT_BASE	0x1f
+#define LM3533_REG_CTRLBANK_ENABLE	0x27
+#define LM3533_REG_BRIGHTNESS_BASE	0x40
+
+
+static inline u8 lm3533_ctrlbank_get_reg(struct lm3533_ctrlbank *cb, u8 base)
+{
+	return base + cb->id;
+}
+
+int lm3533_ctrlbank_enable(struct lm3533_ctrlbank *cb)
+{
+	u8 mask;
+	int ret;
+
+	dev_dbg(cb->dev, "%s - %d\n", __func__, cb->id);
+
+	mask = 1 << cb->id;
+	ret = lm3533_update(cb->lm3533, LM3533_REG_CTRLBANK_ENABLE,
+								mask, mask);
+	if (ret)
+		dev_err(cb->dev, "failed to enable ctrlbank %d\n", cb->id);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(lm3533_ctrlbank_enable);
+
+int lm3533_ctrlbank_disable(struct lm3533_ctrlbank *cb)
+{
+	u8 mask;
+	int ret;
+
+	dev_dbg(cb->dev, "%s - %d\n", __func__, cb->id);
+
+	mask = 1 << cb->id;
+	ret = lm3533_update(cb->lm3533, LM3533_REG_CTRLBANK_ENABLE, 0, mask);
+	if (ret)
+		dev_err(cb->dev, "failed to disable ctrlbank %d\n", cb->id);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(lm3533_ctrlbank_disable);
+
+/*
+ * Full-scale current.
+ *
+ * imax		5000 - 29800 uA (800 uA step)
+ */
+int lm3533_ctrlbank_set_max_current(struct lm3533_ctrlbank *cb, u16 imax)
+{
+	u8 reg;
+	u8 val;
+	int ret;
+
+	if (imax < LM3533_MAX_CURRENT_MIN || imax > LM3533_MAX_CURRENT_MAX)
+		return -EINVAL;
+
+	val = (imax - LM3533_MAX_CURRENT_MIN) / LM3533_MAX_CURRENT_STEP;
+
+	reg = lm3533_ctrlbank_get_reg(cb, LM3533_REG_MAX_CURRENT_BASE);
+	ret = lm3533_write(cb->lm3533, reg, val);
+	if (ret)
+		dev_err(cb->dev, "failed to set max current\n");
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(lm3533_ctrlbank_set_max_current);
+
+#define lm3533_ctrlbank_set(_name, _NAME)				\
+int lm3533_ctrlbank_set_##_name(struct lm3533_ctrlbank *cb, u8 val)	\
+{									\
+	u8 reg;								\
+	int ret;							\
+									\
+	if (val > LM3533_##_NAME##_MAX)					\
+		return -EINVAL;						\
+									\
+	reg = lm3533_ctrlbank_get_reg(cb, LM3533_REG_##_NAME##_BASE);	\
+	ret = lm3533_write(cb->lm3533, reg, val);			\
+	if (ret)							\
+		dev_err(cb->dev, "failed to set " #_name "\n");		\
+									\
+	return ret;							\
+}									\
+EXPORT_SYMBOL_GPL(lm3533_ctrlbank_set_##_name);
+
+#define lm3533_ctrlbank_get(_name, _NAME)				\
+int lm3533_ctrlbank_get_##_name(struct lm3533_ctrlbank *cb, u8 *val)	\
+{									\
+	u8 reg;								\
+	int ret;							\
+									\
+	reg = lm3533_ctrlbank_get_reg(cb, LM3533_REG_##_NAME##_BASE);	\
+	ret = lm3533_read(cb->lm3533, reg, val);			\
+	if (ret)							\
+		dev_err(cb->dev, "failed to get " #_name "\n");		\
+									\
+	return ret;							\
+}									\
+EXPORT_SYMBOL_GPL(lm3533_ctrlbank_get_##_name);
+
+lm3533_ctrlbank_set(brightness, BRIGHTNESS);
+lm3533_ctrlbank_get(brightness, BRIGHTNESS);
+
+/*
+ * PWM-input control mask:
+ *
+ *   bit 5 - PWM-input enabled in Zone 4
+ *   bit 4 - PWM-input enabled in Zone 3
+ *   bit 3 - PWM-input enabled in Zone 2
+ *   bit 2 - PWM-input enabled in Zone 1
+ *   bit 1 - PWM-input enabled in Zone 0
+ *   bit 0 - PWM-input enabled
+ */
+lm3533_ctrlbank_set(pwm, PWM);
+lm3533_ctrlbank_get(pwm, PWM);
+
+
+MODULE_AUTHOR("Johan Hovold <jhovold@gmail.com>");
+MODULE_DESCRIPTION("LM3533 Control Bank interface");
+MODULE_LICENSE("GPL");
diff --git a/drivers/mfd/lpc_ich.c b/drivers/mfd/lpc_ich.c
new file mode 100644
index 000000000000..027cc8f86132
--- /dev/null
+++ b/drivers/mfd/lpc_ich.c
@@ -0,0 +1,888 @@
+/*
+ *  lpc_ich.c - LPC interface for Intel ICH
+ *
+ *  LPC bridge function of the Intel ICH contains many other
+ *  functional units, such as Interrupt controllers, Timers,
+ *  Power Management, System Management, GPIO, RTC, and LPC
+ *  Configuration Registers.
+ *
+ *  This driver is derived from lpc_sch.
+
+ *  Copyright (c) 2011 Extreme Engineering Solution, Inc.
+ *  Author: Aaron Sierra <asierra@xes-inc.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License 2 as published
+ *  by the Free Software Foundation.
+ *
+ *  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; see the file COPYING.  If not, write to
+ *  the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ *  This driver supports the following I/O Controller hubs:
+ *	(See the intel documentation on http://developer.intel.com.)
+ *	document number 290655-003, 290677-014: 82801AA (ICH), 82801AB (ICHO)
+ *	document number 290687-002, 298242-027: 82801BA (ICH2)
+ *	document number 290733-003, 290739-013: 82801CA (ICH3-S)
+ *	document number 290716-001, 290718-007: 82801CAM (ICH3-M)
+ *	document number 290744-001, 290745-025: 82801DB (ICH4)
+ *	document number 252337-001, 252663-008: 82801DBM (ICH4-M)
+ *	document number 273599-001, 273645-002: 82801E (C-ICH)
+ *	document number 252516-001, 252517-028: 82801EB (ICH5), 82801ER (ICH5R)
+ *	document number 300641-004, 300884-013: 6300ESB
+ *	document number 301473-002, 301474-026: 82801F (ICH6)
+ *	document number 313082-001, 313075-006: 631xESB, 632xESB
+ *	document number 307013-003, 307014-024: 82801G (ICH7)
+ *	document number 322896-001, 322897-001: NM10
+ *	document number 313056-003, 313057-017: 82801H (ICH8)
+ *	document number 316972-004, 316973-012: 82801I (ICH9)
+ *	document number 319973-002, 319974-002: 82801J (ICH10)
+ *	document number 322169-001, 322170-003: 5 Series, 3400 Series (PCH)
+ *	document number 320066-003, 320257-008: EP80597 (IICH)
+ *	document number 324645-001, 324646-001: Cougar Point (CPT)
+ *	document number TBD : Patsburg (PBG)
+ *	document number TBD : DH89xxCC
+ *	document number TBD : Panther Point
+ *	document number TBD : Lynx Point
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/acpi.h>
+#include <linux/pci.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/lpc_ich.h>
+
+#define ACPIBASE		0x40
+#define ACPIBASE_GPE_OFF	0x28
+#define ACPIBASE_GPE_END	0x2f
+#define ACPIBASE_SMI_OFF	0x30
+#define ACPIBASE_SMI_END	0x33
+#define ACPIBASE_TCO_OFF	0x60
+#define ACPIBASE_TCO_END	0x7f
+#define ACPICTRL		0x44
+
+#define ACPIBASE_GCS_OFF	0x3410
+#define ACPIBASE_GCS_END	0x3414
+
+#define GPIOBASE		0x48
+#define GPIOCTRL		0x4C
+
+#define RCBABASE		0xf0
+
+#define wdt_io_res(i) wdt_res(0, i)
+#define wdt_mem_res(i) wdt_res(ICH_RES_MEM_OFF, i)
+#define wdt_res(b, i) (&wdt_ich_res[(b) + (i)])
+
+static int lpc_ich_acpi_save = -1;
+static int lpc_ich_gpio_save = -1;
+
+static struct resource wdt_ich_res[] = {
+	/* ACPI - TCO */
+	{
+		.flags = IORESOURCE_IO,
+	},
+	/* ACPI - SMI */
+	{
+		.flags = IORESOURCE_IO,
+	},
+	/* GCS */
+	{
+		.flags = IORESOURCE_MEM,
+	},
+};
+
+static struct resource gpio_ich_res[] = {
+	/* GPIO */
+	{
+		.flags = IORESOURCE_IO,
+	},
+	/* ACPI - GPE0 */
+	{
+		.flags = IORESOURCE_IO,
+	},
+};
+
+enum lpc_cells {
+	LPC_WDT = 0,
+	LPC_GPIO,
+};
+
+static struct mfd_cell lpc_ich_cells[] = {
+	[LPC_WDT] = {
+		.name = "iTCO_wdt",
+		.num_resources = ARRAY_SIZE(wdt_ich_res),
+		.resources = wdt_ich_res,
+		.ignore_resource_conflicts = true,
+	},
+	[LPC_GPIO] = {
+		.name = "gpio_ich",
+		.num_resources = ARRAY_SIZE(gpio_ich_res),
+		.resources = gpio_ich_res,
+		.ignore_resource_conflicts = true,
+	},
+};
+
+/* chipset related info */
+enum lpc_chipsets {
+	LPC_ICH = 0,	/* ICH */
+	LPC_ICH0,	/* ICH0 */
+	LPC_ICH2,	/* ICH2 */
+	LPC_ICH2M,	/* ICH2-M */
+	LPC_ICH3,	/* ICH3-S */
+	LPC_ICH3M,	/* ICH3-M */
+	LPC_ICH4,	/* ICH4 */
+	LPC_ICH4M,	/* ICH4-M */
+	LPC_CICH,	/* C-ICH */
+	LPC_ICH5,	/* ICH5 & ICH5R */
+	LPC_6300ESB,	/* 6300ESB */
+	LPC_ICH6,	/* ICH6 & ICH6R */
+	LPC_ICH6M,	/* ICH6-M */
+	LPC_ICH6W,	/* ICH6W & ICH6RW */
+	LPC_631XESB,	/* 631xESB/632xESB */
+	LPC_ICH7,	/* ICH7 & ICH7R */
+	LPC_ICH7DH,	/* ICH7DH */
+	LPC_ICH7M,	/* ICH7-M & ICH7-U */
+	LPC_ICH7MDH,	/* ICH7-M DH */
+	LPC_NM10,	/* NM10 */
+	LPC_ICH8,	/* ICH8 & ICH8R */
+	LPC_ICH8DH,	/* ICH8DH */
+	LPC_ICH8DO,	/* ICH8DO */
+	LPC_ICH8M,	/* ICH8M */
+	LPC_ICH8ME,	/* ICH8M-E */
+	LPC_ICH9,	/* ICH9 */
+	LPC_ICH9R,	/* ICH9R */
+	LPC_ICH9DH,	/* ICH9DH */
+	LPC_ICH9DO,	/* ICH9DO */
+	LPC_ICH9M,	/* ICH9M */
+	LPC_ICH9ME,	/* ICH9M-E */
+	LPC_ICH10,	/* ICH10 */
+	LPC_ICH10R,	/* ICH10R */
+	LPC_ICH10D,	/* ICH10D */
+	LPC_ICH10DO,	/* ICH10DO */
+	LPC_PCH,	/* PCH Desktop Full Featured */
+	LPC_PCHM,	/* PCH Mobile Full Featured */
+	LPC_P55,	/* P55 */
+	LPC_PM55,	/* PM55 */
+	LPC_H55,	/* H55 */
+	LPC_QM57,	/* QM57 */
+	LPC_H57,	/* H57 */
+	LPC_HM55,	/* HM55 */
+	LPC_Q57,	/* Q57 */
+	LPC_HM57,	/* HM57 */
+	LPC_PCHMSFF,	/* PCH Mobile SFF Full Featured */
+	LPC_QS57,	/* QS57 */
+	LPC_3400,	/* 3400 */
+	LPC_3420,	/* 3420 */
+	LPC_3450,	/* 3450 */
+	LPC_EP80579,	/* EP80579 */
+	LPC_CPT,	/* Cougar Point */
+	LPC_CPTD,	/* Cougar Point Desktop */
+	LPC_CPTM,	/* Cougar Point Mobile */
+	LPC_PBG,	/* Patsburg */
+	LPC_DH89XXCC,	/* DH89xxCC */
+	LPC_PPT,	/* Panther Point */
+	LPC_LPT,	/* Lynx Point */
+};
+
+struct lpc_ich_info lpc_chipset_info[] __devinitdata = {
+	[LPC_ICH] = {
+		.name = "ICH",
+		.iTCO_version = 1,
+	},
+	[LPC_ICH0] = {
+		.name = "ICH0",
+		.iTCO_version = 1,
+	},
+	[LPC_ICH2] = {
+		.name = "ICH2",
+		.iTCO_version = 1,
+	},
+	[LPC_ICH2M] = {
+		.name = "ICH2-M",
+		.iTCO_version = 1,
+	},
+	[LPC_ICH3] = {
+		.name = "ICH3-S",
+		.iTCO_version = 1,
+	},
+	[LPC_ICH3M] = {
+		.name = "ICH3-M",
+		.iTCO_version = 1,
+	},
+	[LPC_ICH4] = {
+		.name = "ICH4",
+		.iTCO_version = 1,
+	},
+	[LPC_ICH4M] = {
+		.name = "ICH4-M",
+		.iTCO_version = 1,
+	},
+	[LPC_CICH] = {
+		.name = "C-ICH",
+		.iTCO_version = 1,
+	},
+	[LPC_ICH5] = {
+		.name = "ICH5 or ICH5R",
+		.iTCO_version = 1,
+	},
+	[LPC_6300ESB] = {
+		.name = "6300ESB",
+		.iTCO_version = 1,
+	},
+	[LPC_ICH6] = {
+		.name = "ICH6 or ICH6R",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V6_GPIO,
+	},
+	[LPC_ICH6M] = {
+		.name = "ICH6-M",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V6_GPIO,
+	},
+	[LPC_ICH6W] = {
+		.name = "ICH6W or ICH6RW",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V6_GPIO,
+	},
+	[LPC_631XESB] = {
+		.name = "631xESB/632xESB",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V6_GPIO,
+	},
+	[LPC_ICH7] = {
+		.name = "ICH7 or ICH7R",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V7_GPIO,
+	},
+	[LPC_ICH7DH] = {
+		.name = "ICH7DH",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V7_GPIO,
+	},
+	[LPC_ICH7M] = {
+		.name = "ICH7-M or ICH7-U",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V7_GPIO,
+	},
+	[LPC_ICH7MDH] = {
+		.name = "ICH7-M DH",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V7_GPIO,
+	},
+	[LPC_NM10] = {
+		.name = "NM10",
+		.iTCO_version = 2,
+	},
+	[LPC_ICH8] = {
+		.name = "ICH8 or ICH8R",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V7_GPIO,
+	},
+	[LPC_ICH8DH] = {
+		.name = "ICH8DH",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V7_GPIO,
+	},
+	[LPC_ICH8DO] = {
+		.name = "ICH8DO",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V7_GPIO,
+	},
+	[LPC_ICH8M] = {
+		.name = "ICH8M",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V7_GPIO,
+	},
+	[LPC_ICH8ME] = {
+		.name = "ICH8M-E",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V7_GPIO,
+	},
+	[LPC_ICH9] = {
+		.name = "ICH9",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V9_GPIO,
+	},
+	[LPC_ICH9R] = {
+		.name = "ICH9R",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V9_GPIO,
+	},
+	[LPC_ICH9DH] = {
+		.name = "ICH9DH",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V9_GPIO,
+	},
+	[LPC_ICH9DO] = {
+		.name = "ICH9DO",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V9_GPIO,
+	},
+	[LPC_ICH9M] = {
+		.name = "ICH9M",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V9_GPIO,
+	},
+	[LPC_ICH9ME] = {
+		.name = "ICH9M-E",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V9_GPIO,
+	},
+	[LPC_ICH10] = {
+		.name = "ICH10",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V10CONS_GPIO,
+	},
+	[LPC_ICH10R] = {
+		.name = "ICH10R",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V10CONS_GPIO,
+	},
+	[LPC_ICH10D] = {
+		.name = "ICH10D",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V10CORP_GPIO,
+	},
+	[LPC_ICH10DO] = {
+		.name = "ICH10DO",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V10CORP_GPIO,
+	},
+	[LPC_PCH] = {
+		.name = "PCH Desktop Full Featured",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V5_GPIO,
+	},
+	[LPC_PCHM] = {
+		.name = "PCH Mobile Full Featured",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V5_GPIO,
+	},
+	[LPC_P55] = {
+		.name = "P55",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V5_GPIO,
+	},
+	[LPC_PM55] = {
+		.name = "PM55",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V5_GPIO,
+	},
+	[LPC_H55] = {
+		.name = "H55",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V5_GPIO,
+	},
+	[LPC_QM57] = {
+		.name = "QM57",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V5_GPIO,
+	},
+	[LPC_H57] = {
+		.name = "H57",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V5_GPIO,
+	},
+	[LPC_HM55] = {
+		.name = "HM55",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V5_GPIO,
+	},
+	[LPC_Q57] = {
+		.name = "Q57",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V5_GPIO,
+	},
+	[LPC_HM57] = {
+		.name = "HM57",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V5_GPIO,
+	},
+	[LPC_PCHMSFF] = {
+		.name = "PCH Mobile SFF Full Featured",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V5_GPIO,
+	},
+	[LPC_QS57] = {
+		.name = "QS57",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V5_GPIO,
+	},
+	[LPC_3400] = {
+		.name = "3400",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V5_GPIO,
+	},
+	[LPC_3420] = {
+		.name = "3420",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V5_GPIO,
+	},
+	[LPC_3450] = {
+		.name = "3450",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V5_GPIO,
+	},
+	[LPC_EP80579] = {
+		.name = "EP80579",
+		.iTCO_version = 2,
+	},
+	[LPC_CPT] = {
+		.name = "Cougar Point",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V5_GPIO,
+	},
+	[LPC_CPTD] = {
+		.name = "Cougar Point Desktop",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V5_GPIO,
+	},
+	[LPC_CPTM] = {
+		.name = "Cougar Point Mobile",
+		.iTCO_version = 2,
+		.gpio_version = ICH_V5_GPIO,
+	},
+	[LPC_PBG] = {
+		.name = "Patsburg",
+		.iTCO_version = 2,
+	},
+	[LPC_DH89XXCC] = {
+		.name = "DH89xxCC",
+		.iTCO_version = 2,
+	},
+	[LPC_PPT] = {
+		.name = "Panther Point",
+		.iTCO_version = 2,
+	},
+	[LPC_LPT] = {
+		.name = "Lynx Point",
+		.iTCO_version = 2,
+	},
+};
+
+/*
+ * This data only exists for exporting the supported PCI ids
+ * via MODULE_DEVICE_TABLE.  We do not actually register a
+ * pci_driver, because the I/O Controller Hub has also other
+ * functions that probably will be registered by other drivers.
+ */
+static DEFINE_PCI_DEVICE_TABLE(lpc_ich_ids) = {
+	{ PCI_VDEVICE(INTEL, 0x2410), LPC_ICH},
+	{ PCI_VDEVICE(INTEL, 0x2420), LPC_ICH0},
+	{ PCI_VDEVICE(INTEL, 0x2440), LPC_ICH2},
+	{ PCI_VDEVICE(INTEL, 0x244c), LPC_ICH2M},
+	{ PCI_VDEVICE(INTEL, 0x2480), LPC_ICH3},
+	{ PCI_VDEVICE(INTEL, 0x248c), LPC_ICH3M},
+	{ PCI_VDEVICE(INTEL, 0x24c0), LPC_ICH4},
+	{ PCI_VDEVICE(INTEL, 0x24cc), LPC_ICH4M},
+	{ PCI_VDEVICE(INTEL, 0x2450), LPC_CICH},
+	{ PCI_VDEVICE(INTEL, 0x24d0), LPC_ICH5},
+	{ PCI_VDEVICE(INTEL, 0x25a1), LPC_6300ESB},
+	{ PCI_VDEVICE(INTEL, 0x2640), LPC_ICH6},
+	{ PCI_VDEVICE(INTEL, 0x2641), LPC_ICH6M},
+	{ PCI_VDEVICE(INTEL, 0x2642), LPC_ICH6W},
+	{ PCI_VDEVICE(INTEL, 0x2670), LPC_631XESB},
+	{ PCI_VDEVICE(INTEL, 0x2671), LPC_631XESB},
+	{ PCI_VDEVICE(INTEL, 0x2672), LPC_631XESB},
+	{ PCI_VDEVICE(INTEL, 0x2673), LPC_631XESB},
+	{ PCI_VDEVICE(INTEL, 0x2674), LPC_631XESB},
+	{ PCI_VDEVICE(INTEL, 0x2675), LPC_631XESB},
+	{ PCI_VDEVICE(INTEL, 0x2676), LPC_631XESB},
+	{ PCI_VDEVICE(INTEL, 0x2677), LPC_631XESB},
+	{ PCI_VDEVICE(INTEL, 0x2678), LPC_631XESB},
+	{ PCI_VDEVICE(INTEL, 0x2679), LPC_631XESB},
+	{ PCI_VDEVICE(INTEL, 0x267a), LPC_631XESB},
+	{ PCI_VDEVICE(INTEL, 0x267b), LPC_631XESB},
+	{ PCI_VDEVICE(INTEL, 0x267c), LPC_631XESB},
+	{ PCI_VDEVICE(INTEL, 0x267d), LPC_631XESB},
+	{ PCI_VDEVICE(INTEL, 0x267e), LPC_631XESB},
+	{ PCI_VDEVICE(INTEL, 0x267f), LPC_631XESB},
+	{ PCI_VDEVICE(INTEL, 0x27b8), LPC_ICH7},
+	{ PCI_VDEVICE(INTEL, 0x27b0), LPC_ICH7DH},
+	{ PCI_VDEVICE(INTEL, 0x27b9), LPC_ICH7M},
+	{ PCI_VDEVICE(INTEL, 0x27bd), LPC_ICH7MDH},
+	{ PCI_VDEVICE(INTEL, 0x27bc), LPC_NM10},
+	{ PCI_VDEVICE(INTEL, 0x2810), LPC_ICH8},
+	{ PCI_VDEVICE(INTEL, 0x2812), LPC_ICH8DH},
+	{ PCI_VDEVICE(INTEL, 0x2814), LPC_ICH8DO},
+	{ PCI_VDEVICE(INTEL, 0x2815), LPC_ICH8M},
+	{ PCI_VDEVICE(INTEL, 0x2811), LPC_ICH8ME},
+	{ PCI_VDEVICE(INTEL, 0x2918), LPC_ICH9},
+	{ PCI_VDEVICE(INTEL, 0x2916), LPC_ICH9R},
+	{ PCI_VDEVICE(INTEL, 0x2912), LPC_ICH9DH},
+	{ PCI_VDEVICE(INTEL, 0x2914), LPC_ICH9DO},
+	{ PCI_VDEVICE(INTEL, 0x2919), LPC_ICH9M},
+	{ PCI_VDEVICE(INTEL, 0x2917), LPC_ICH9ME},
+	{ PCI_VDEVICE(INTEL, 0x3a18), LPC_ICH10},
+	{ PCI_VDEVICE(INTEL, 0x3a16), LPC_ICH10R},
+	{ PCI_VDEVICE(INTEL, 0x3a1a), LPC_ICH10D},
+	{ PCI_VDEVICE(INTEL, 0x3a14), LPC_ICH10DO},
+	{ PCI_VDEVICE(INTEL, 0x3b00), LPC_PCH},
+	{ PCI_VDEVICE(INTEL, 0x3b01), LPC_PCHM},
+	{ PCI_VDEVICE(INTEL, 0x3b02), LPC_P55},
+	{ PCI_VDEVICE(INTEL, 0x3b03), LPC_PM55},
+	{ PCI_VDEVICE(INTEL, 0x3b06), LPC_H55},
+	{ PCI_VDEVICE(INTEL, 0x3b07), LPC_QM57},
+	{ PCI_VDEVICE(INTEL, 0x3b08), LPC_H57},
+	{ PCI_VDEVICE(INTEL, 0x3b09), LPC_HM55},
+	{ PCI_VDEVICE(INTEL, 0x3b0a), LPC_Q57},
+	{ PCI_VDEVICE(INTEL, 0x3b0b), LPC_HM57},
+	{ PCI_VDEVICE(INTEL, 0x3b0d), LPC_PCHMSFF},
+	{ PCI_VDEVICE(INTEL, 0x3b0f), LPC_QS57},
+	{ PCI_VDEVICE(INTEL, 0x3b12), LPC_3400},
+	{ PCI_VDEVICE(INTEL, 0x3b14), LPC_3420},
+	{ PCI_VDEVICE(INTEL, 0x3b16), LPC_3450},
+	{ PCI_VDEVICE(INTEL, 0x5031), LPC_EP80579},
+	{ PCI_VDEVICE(INTEL, 0x1c41), LPC_CPT},
+	{ PCI_VDEVICE(INTEL, 0x1c42), LPC_CPTD},
+	{ PCI_VDEVICE(INTEL, 0x1c43), LPC_CPTM},
+	{ PCI_VDEVICE(INTEL, 0x1c44), LPC_CPT},
+	{ PCI_VDEVICE(INTEL, 0x1c45), LPC_CPT},
+	{ PCI_VDEVICE(INTEL, 0x1c46), LPC_CPT},
+	{ PCI_VDEVICE(INTEL, 0x1c47), LPC_CPT},
+	{ PCI_VDEVICE(INTEL, 0x1c48), LPC_CPT},
+	{ PCI_VDEVICE(INTEL, 0x1c49), LPC_CPT},
+	{ PCI_VDEVICE(INTEL, 0x1c4a), LPC_CPT},
+	{ PCI_VDEVICE(INTEL, 0x1c4b), LPC_CPT},
+	{ PCI_VDEVICE(INTEL, 0x1c4c), LPC_CPT},
+	{ PCI_VDEVICE(INTEL, 0x1c4d), LPC_CPT},
+	{ PCI_VDEVICE(INTEL, 0x1c4e), LPC_CPT},
+	{ PCI_VDEVICE(INTEL, 0x1c4f), LPC_CPT},
+	{ PCI_VDEVICE(INTEL, 0x1c50), LPC_CPT},
+	{ PCI_VDEVICE(INTEL, 0x1c51), LPC_CPT},
+	{ PCI_VDEVICE(INTEL, 0x1c52), LPC_CPT},
+	{ PCI_VDEVICE(INTEL, 0x1c53), LPC_CPT},
+	{ PCI_VDEVICE(INTEL, 0x1c54), LPC_CPT},
+	{ PCI_VDEVICE(INTEL, 0x1c55), LPC_CPT},
+	{ PCI_VDEVICE(INTEL, 0x1c56), LPC_CPT},
+	{ PCI_VDEVICE(INTEL, 0x1c57), LPC_CPT},
+	{ PCI_VDEVICE(INTEL, 0x1c58), LPC_CPT},
+	{ PCI_VDEVICE(INTEL, 0x1c59), LPC_CPT},
+	{ PCI_VDEVICE(INTEL, 0x1c5a), LPC_CPT},
+	{ PCI_VDEVICE(INTEL, 0x1c5b), LPC_CPT},
+	{ PCI_VDEVICE(INTEL, 0x1c5c), LPC_CPT},
+	{ PCI_VDEVICE(INTEL, 0x1c5d), LPC_CPT},
+	{ PCI_VDEVICE(INTEL, 0x1c5e), LPC_CPT},
+	{ PCI_VDEVICE(INTEL, 0x1c5f), LPC_CPT},
+	{ PCI_VDEVICE(INTEL, 0x1d40), LPC_PBG},
+	{ PCI_VDEVICE(INTEL, 0x1d41), LPC_PBG},
+	{ PCI_VDEVICE(INTEL, 0x2310), LPC_DH89XXCC},
+	{ PCI_VDEVICE(INTEL, 0x1e40), LPC_PPT},
+	{ PCI_VDEVICE(INTEL, 0x1e41), LPC_PPT},
+	{ PCI_VDEVICE(INTEL, 0x1e42), LPC_PPT},
+	{ PCI_VDEVICE(INTEL, 0x1e43), LPC_PPT},
+	{ PCI_VDEVICE(INTEL, 0x1e44), LPC_PPT},
+	{ PCI_VDEVICE(INTEL, 0x1e45), LPC_PPT},
+	{ PCI_VDEVICE(INTEL, 0x1e46), LPC_PPT},
+	{ PCI_VDEVICE(INTEL, 0x1e47), LPC_PPT},
+	{ PCI_VDEVICE(INTEL, 0x1e48), LPC_PPT},
+	{ PCI_VDEVICE(INTEL, 0x1e49), LPC_PPT},
+	{ PCI_VDEVICE(INTEL, 0x1e4a), LPC_PPT},
+	{ PCI_VDEVICE(INTEL, 0x1e4b), LPC_PPT},
+	{ PCI_VDEVICE(INTEL, 0x1e4c), LPC_PPT},
+	{ PCI_VDEVICE(INTEL, 0x1e4d), LPC_PPT},
+	{ PCI_VDEVICE(INTEL, 0x1e4e), LPC_PPT},
+	{ PCI_VDEVICE(INTEL, 0x1e4f), LPC_PPT},
+	{ PCI_VDEVICE(INTEL, 0x1e50), LPC_PPT},
+	{ PCI_VDEVICE(INTEL, 0x1e51), LPC_PPT},
+	{ PCI_VDEVICE(INTEL, 0x1e52), LPC_PPT},
+	{ PCI_VDEVICE(INTEL, 0x1e53), LPC_PPT},
+	{ PCI_VDEVICE(INTEL, 0x1e54), LPC_PPT},
+	{ PCI_VDEVICE(INTEL, 0x1e55), LPC_PPT},
+	{ PCI_VDEVICE(INTEL, 0x1e56), LPC_PPT},
+	{ PCI_VDEVICE(INTEL, 0x1e57), LPC_PPT},
+	{ PCI_VDEVICE(INTEL, 0x1e58), LPC_PPT},
+	{ PCI_VDEVICE(INTEL, 0x1e59), LPC_PPT},
+	{ PCI_VDEVICE(INTEL, 0x1e5a), LPC_PPT},
+	{ PCI_VDEVICE(INTEL, 0x1e5b), LPC_PPT},
+	{ PCI_VDEVICE(INTEL, 0x1e5c), LPC_PPT},
+	{ PCI_VDEVICE(INTEL, 0x1e5d), LPC_PPT},
+	{ PCI_VDEVICE(INTEL, 0x1e5e), LPC_PPT},
+	{ PCI_VDEVICE(INTEL, 0x1e5f), LPC_PPT},
+	{ PCI_VDEVICE(INTEL, 0x8c40), LPC_LPT},
+	{ PCI_VDEVICE(INTEL, 0x8c41), LPC_LPT},
+	{ PCI_VDEVICE(INTEL, 0x8c42), LPC_LPT},
+	{ PCI_VDEVICE(INTEL, 0x8c43), LPC_LPT},
+	{ PCI_VDEVICE(INTEL, 0x8c44), LPC_LPT},
+	{ PCI_VDEVICE(INTEL, 0x8c45), LPC_LPT},
+	{ PCI_VDEVICE(INTEL, 0x8c46), LPC_LPT},
+	{ PCI_VDEVICE(INTEL, 0x8c47), LPC_LPT},
+	{ PCI_VDEVICE(INTEL, 0x8c48), LPC_LPT},
+	{ PCI_VDEVICE(INTEL, 0x8c49), LPC_LPT},
+	{ PCI_VDEVICE(INTEL, 0x8c4a), LPC_LPT},
+	{ PCI_VDEVICE(INTEL, 0x8c4b), LPC_LPT},
+	{ PCI_VDEVICE(INTEL, 0x8c4c), LPC_LPT},
+	{ PCI_VDEVICE(INTEL, 0x8c4d), LPC_LPT},
+	{ PCI_VDEVICE(INTEL, 0x8c4e), LPC_LPT},
+	{ PCI_VDEVICE(INTEL, 0x8c4f), LPC_LPT},
+	{ PCI_VDEVICE(INTEL, 0x8c50), LPC_LPT},
+	{ PCI_VDEVICE(INTEL, 0x8c51), LPC_LPT},
+	{ PCI_VDEVICE(INTEL, 0x8c52), LPC_LPT},
+	{ PCI_VDEVICE(INTEL, 0x8c53), LPC_LPT},
+	{ PCI_VDEVICE(INTEL, 0x8c54), LPC_LPT},
+	{ PCI_VDEVICE(INTEL, 0x8c55), LPC_LPT},
+	{ PCI_VDEVICE(INTEL, 0x8c56), LPC_LPT},
+	{ PCI_VDEVICE(INTEL, 0x8c57), LPC_LPT},
+	{ PCI_VDEVICE(INTEL, 0x8c58), LPC_LPT},
+	{ PCI_VDEVICE(INTEL, 0x8c59), LPC_LPT},
+	{ PCI_VDEVICE(INTEL, 0x8c5a), LPC_LPT},
+	{ PCI_VDEVICE(INTEL, 0x8c5b), LPC_LPT},
+	{ PCI_VDEVICE(INTEL, 0x8c5c), LPC_LPT},
+	{ PCI_VDEVICE(INTEL, 0x8c5d), LPC_LPT},
+	{ PCI_VDEVICE(INTEL, 0x8c5e), LPC_LPT},
+	{ PCI_VDEVICE(INTEL, 0x8c5f), LPC_LPT},
+	{ 0, },			/* End of list */
+};
+MODULE_DEVICE_TABLE(pci, lpc_ich_ids);
+
+static void lpc_ich_restore_config_space(struct pci_dev *dev)
+{
+	if (lpc_ich_acpi_save >= 0) {
+		pci_write_config_byte(dev, ACPICTRL, lpc_ich_acpi_save);
+		lpc_ich_acpi_save = -1;
+	}
+
+	if (lpc_ich_gpio_save >= 0) {
+		pci_write_config_byte(dev, GPIOCTRL, lpc_ich_gpio_save);
+		lpc_ich_gpio_save = -1;
+	}
+}
+
+static void __devinit lpc_ich_enable_acpi_space(struct pci_dev *dev)
+{
+	u8 reg_save;
+
+	pci_read_config_byte(dev, ACPICTRL, &reg_save);
+	pci_write_config_byte(dev, ACPICTRL, reg_save | 0x10);
+	lpc_ich_acpi_save = reg_save;
+}
+
+static void __devinit lpc_ich_enable_gpio_space(struct pci_dev *dev)
+{
+	u8 reg_save;
+
+	pci_read_config_byte(dev, GPIOCTRL, &reg_save);
+	pci_write_config_byte(dev, GPIOCTRL, reg_save | 0x10);
+	lpc_ich_gpio_save = reg_save;
+}
+
+static void __devinit lpc_ich_finalize_cell(struct mfd_cell *cell,
+					const struct pci_device_id *id)
+{
+	cell->platform_data = &lpc_chipset_info[id->driver_data];
+	cell->pdata_size = sizeof(struct lpc_ich_info);
+}
+
+static int __devinit lpc_ich_init_gpio(struct pci_dev *dev,
+				const struct pci_device_id *id)
+{
+	u32 base_addr_cfg;
+	u32 base_addr;
+	int ret;
+	bool acpi_conflict = false;
+	struct resource *res;
+
+	/* Setup power management base register */
+	pci_read_config_dword(dev, ACPIBASE, &base_addr_cfg);
+	base_addr = base_addr_cfg & 0x0000ff80;
+	if (!base_addr) {
+		dev_err(&dev->dev, "I/O space for ACPI uninitialized\n");
+		lpc_ich_cells[LPC_GPIO].num_resources--;
+		goto gpe0_done;
+	}
+
+	res = &gpio_ich_res[ICH_RES_GPE0];
+	res->start = base_addr + ACPIBASE_GPE_OFF;
+	res->end = base_addr + ACPIBASE_GPE_END;
+	ret = acpi_check_resource_conflict(res);
+	if (ret) {
+		/*
+		 * This isn't fatal for the GPIO, but we have to make sure that
+		 * the platform_device subsystem doesn't see this resource
+		 * or it will register an invalid region.
+		 */
+		lpc_ich_cells[LPC_GPIO].num_resources--;
+		acpi_conflict = true;
+	} else {
+		lpc_ich_enable_acpi_space(dev);
+	}
+
+gpe0_done:
+	/* Setup GPIO base register */
+	pci_read_config_dword(dev, GPIOBASE, &base_addr_cfg);
+	base_addr = base_addr_cfg & 0x0000ff80;
+	if (!base_addr) {
+		dev_err(&dev->dev, "I/O space for GPIO uninitialized\n");
+		ret = -ENODEV;
+		goto gpio_done;
+	}
+
+	/* Older devices provide fewer GPIO and have a smaller resource size. */
+	res = &gpio_ich_res[ICH_RES_GPIO];
+	res->start = base_addr;
+	switch (lpc_chipset_info[id->driver_data].gpio_version) {
+	case ICH_V5_GPIO:
+	case ICH_V10CORP_GPIO:
+		res->end = res->start + 128 - 1;
+		break;
+	default:
+		res->end = res->start + 64 - 1;
+		break;
+	}
+
+	ret = acpi_check_resource_conflict(res);
+	if (ret) {
+		/* this isn't necessarily fatal for the GPIO */
+		acpi_conflict = true;
+		goto gpio_done;
+	}
+	lpc_ich_enable_gpio_space(dev);
+
+	lpc_ich_finalize_cell(&lpc_ich_cells[LPC_GPIO], id);
+	ret = mfd_add_devices(&dev->dev, -1, &lpc_ich_cells[LPC_GPIO],
+				1, NULL, 0);
+
+gpio_done:
+	if (acpi_conflict)
+		pr_warn("Resource conflict(s) found affecting %s\n",
+				lpc_ich_cells[LPC_GPIO].name);
+	return ret;
+}
+
+static int __devinit lpc_ich_init_wdt(struct pci_dev *dev,
+				const struct pci_device_id *id)
+{
+	u32 base_addr_cfg;
+	u32 base_addr;
+	int ret;
+	bool acpi_conflict = false;
+	struct resource *res;
+
+	/* Setup power management base register */
+	pci_read_config_dword(dev, ACPIBASE, &base_addr_cfg);
+	base_addr = base_addr_cfg & 0x0000ff80;
+	if (!base_addr) {
+		dev_err(&dev->dev, "I/O space for ACPI uninitialized\n");
+		ret = -ENODEV;
+		goto wdt_done;
+	}
+
+	res = wdt_io_res(ICH_RES_IO_TCO);
+	res->start = base_addr + ACPIBASE_TCO_OFF;
+	res->end = base_addr + ACPIBASE_TCO_END;
+	ret = acpi_check_resource_conflict(res);
+	if (ret) {
+		acpi_conflict = true;
+		goto wdt_done;
+	}
+
+	res = wdt_io_res(ICH_RES_IO_SMI);
+	res->start = base_addr + ACPIBASE_SMI_OFF;
+	res->end = base_addr + ACPIBASE_SMI_END;
+	ret = acpi_check_resource_conflict(res);
+	if (ret) {
+		acpi_conflict = true;
+		goto wdt_done;
+	}
+	lpc_ich_enable_acpi_space(dev);
+
+	/*
+	 * Get the Memory-Mapped GCS register. To get access to it
+	 * we have to read RCBA from PCI Config space 0xf0 and use
+	 * it as base. GCS = RCBA + ICH6_GCS(0x3410).
+	 */
+	if (lpc_chipset_info[id->driver_data].iTCO_version == 2) {
+		pci_read_config_dword(dev, RCBABASE, &base_addr_cfg);
+		base_addr = base_addr_cfg & 0xffffc000;
+		if (!(base_addr_cfg & 1)) {
+			pr_err("RCBA is disabled by hardware/BIOS, "
+					"device disabled\n");
+			ret = -ENODEV;
+			goto wdt_done;
+		}
+		res = wdt_mem_res(ICH_RES_MEM_GCS);
+		res->start = base_addr + ACPIBASE_GCS_OFF;
+		res->end = base_addr + ACPIBASE_GCS_END;
+		ret = acpi_check_resource_conflict(res);
+		if (ret) {
+			acpi_conflict = true;
+			goto wdt_done;
+		}
+	}
+
+	lpc_ich_finalize_cell(&lpc_ich_cells[LPC_WDT], id);
+	ret = mfd_add_devices(&dev->dev, -1, &lpc_ich_cells[LPC_WDT],
+				1, NULL, 0);
+
+wdt_done:
+	if (acpi_conflict)
+		pr_warn("Resource conflict(s) found affecting %s\n",
+				lpc_ich_cells[LPC_WDT].name);
+	return ret;
+}
+
+static int __devinit lpc_ich_probe(struct pci_dev *dev,
+				const struct pci_device_id *id)
+{
+	int ret;
+	bool cell_added = false;
+
+	ret = lpc_ich_init_wdt(dev, id);
+	if (!ret)
+		cell_added = true;
+
+	ret = lpc_ich_init_gpio(dev, id);
+	if (!ret)
+		cell_added = true;
+
+	/*
+	 * We only care if at least one or none of the cells registered
+	 * successfully.
+	 */
+	if (!cell_added) {
+		lpc_ich_restore_config_space(dev);
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static void __devexit lpc_ich_remove(struct pci_dev *dev)
+{
+	mfd_remove_devices(&dev->dev);
+	lpc_ich_restore_config_space(dev);
+}
+
+static struct pci_driver lpc_ich_driver = {
+	.name		= "lpc_ich",
+	.id_table	= lpc_ich_ids,
+	.probe		= lpc_ich_probe,
+	.remove		= __devexit_p(lpc_ich_remove),
+};
+
+static int __init lpc_ich_init(void)
+{
+	return pci_register_driver(&lpc_ich_driver);
+}
+
+static void __exit lpc_ich_exit(void)
+{
+	pci_unregister_driver(&lpc_ich_driver);
+}
+
+module_init(lpc_ich_init);
+module_exit(lpc_ich_exit);
+
+MODULE_AUTHOR("Aaron Sierra <asierra@xes-inc.com>");
+MODULE_DESCRIPTION("LPC interface for Intel ICH");
+MODULE_LICENSE("GPL");
diff --git a/drivers/mfd/lpc_sch.c b/drivers/mfd/lpc_sch.c
index abc421364a45..9f20abc5e393 100644
--- a/drivers/mfd/lpc_sch.c
+++ b/drivers/mfd/lpc_sch.c
@@ -36,6 +36,7 @@
 
 #define GPIOBASE	0x44
 #define GPIO_IO_SIZE	64
+#define GPIO_IO_SIZE_CENTERTON	128
 
 #define WDTBASE		0x84
 #define WDT_IO_SIZE	64
@@ -68,7 +69,7 @@ static struct resource wdt_sch_resource = {
 
 static struct mfd_cell tunnelcreek_cells[] = {
 	{
-		.name = "tunnelcreek_wdt",
+		.name = "ie6xx_wdt",
 		.num_resources = 1,
 		.resources = &wdt_sch_resource,
 	},
@@ -77,6 +78,7 @@ static struct mfd_cell tunnelcreek_cells[] = {
 static DEFINE_PCI_DEVICE_TABLE(lpc_sch_ids) = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SCH_LPC) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ITC_LPC) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CENTERTON_ILB) },
 	{ 0, }
 };
 MODULE_DEVICE_TABLE(pci, lpc_sch_ids);
@@ -115,7 +117,11 @@ static int __devinit lpc_sch_probe(struct pci_dev *dev,
 	}
 
 	gpio_sch_resource.start = base_addr;
-	gpio_sch_resource.end = base_addr + GPIO_IO_SIZE - 1;
+
+	if (id->device == PCI_DEVICE_ID_INTEL_CENTERTON_ILB)
+		gpio_sch_resource.end = base_addr + GPIO_IO_SIZE_CENTERTON - 1;
+	else
+		gpio_sch_resource.end = base_addr + GPIO_IO_SIZE - 1;
 
 	for (i=0; i < ARRAY_SIZE(lpc_sch_cells); i++)
 		lpc_sch_cells[i].id = id->device;
@@ -125,7 +131,8 @@ static int __devinit lpc_sch_probe(struct pci_dev *dev,
 	if (ret)
 		goto out_dev;
 
-	if (id->device == PCI_DEVICE_ID_INTEL_ITC_LPC) {
+	if (id->device == PCI_DEVICE_ID_INTEL_ITC_LPC
+	 || id->device == PCI_DEVICE_ID_INTEL_CENTERTON_ILB) {
 		pci_read_config_dword(dev, WDTBASE, &base_addr_cfg);
 		if (!(base_addr_cfg & (1 << 31))) {
 			dev_err(&dev->dev, "Decode of the WDT I/O range disabled\n");
@@ -167,18 +174,7 @@ static struct pci_driver lpc_sch_driver = {
 	.remove		= __devexit_p(lpc_sch_remove),
 };
 
-static int __init lpc_sch_init(void)
-{
-	return pci_register_driver(&lpc_sch_driver);
-}
-
-static void __exit lpc_sch_exit(void)
-{
-	pci_unregister_driver(&lpc_sch_driver);
-}
-
-module_init(lpc_sch_init);
-module_exit(lpc_sch_exit);
+module_pci_driver(lpc_sch_driver);
 
 MODULE_AUTHOR("Denis Turischev <denis@compulab.co.il>");
 MODULE_DESCRIPTION("LPC interface for Intel Poulsbo SCH");
diff --git a/drivers/mfd/max77693-irq.c b/drivers/mfd/max77693-irq.c
new file mode 100644
index 000000000000..2b403569e0a6
--- /dev/null
+++ b/drivers/mfd/max77693-irq.c
@@ -0,0 +1,309 @@
+/*
+ * max77693-irq.c - Interrupt controller support for MAX77693
+ *
+ * Copyright (C) 2012 Samsung Electronics Co.Ltd
+ * SangYoung Son <hello.son@samsung.com>
+ *
+ * This program is not provided / owned by Maxim Integrated Products.
+ *
+ * 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
+ *
+ * This driver is based on max8997-irq.c
+ */
+
+#include <linux/err.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/irqdomain.h>
+#include <linux/mfd/max77693.h>
+#include <linux/mfd/max77693-private.h>
+
+static const u8 max77693_mask_reg[] = {
+	[LED_INT] = MAX77693_LED_REG_FLASH_INT_MASK,
+	[TOPSYS_INT] = MAX77693_PMIC_REG_TOPSYS_INT_MASK,
+	[CHG_INT] = MAX77693_CHG_REG_CHG_INT_MASK,
+	[MUIC_INT1] = MAX77693_MUIC_REG_INTMASK1,
+	[MUIC_INT2] = MAX77693_MUIC_REG_INTMASK2,
+	[MUIC_INT3] = MAX77693_MUIC_REG_INTMASK3,
+};
+
+static struct regmap *max77693_get_regmap(struct max77693_dev *max77693,
+				enum max77693_irq_source src)
+{
+	switch (src) {
+	case LED_INT ... CHG_INT:
+		return max77693->regmap;
+	case MUIC_INT1 ... MUIC_INT3:
+		return max77693->regmap_muic;
+	default:
+		return ERR_PTR(-EINVAL);
+	}
+}
+
+struct max77693_irq_data {
+	int mask;
+	enum max77693_irq_source group;
+};
+
+#define DECLARE_IRQ(idx, _group, _mask)		\
+	[(idx)] = { .group = (_group), .mask = (_mask) }
+static const struct max77693_irq_data max77693_irqs[] = {
+	DECLARE_IRQ(MAX77693_LED_IRQ_FLED2_OPEN,	LED_INT, 1 << 0),
+	DECLARE_IRQ(MAX77693_LED_IRQ_FLED2_SHORT,	LED_INT, 1 << 1),
+	DECLARE_IRQ(MAX77693_LED_IRQ_FLED1_OPEN,	LED_INT, 1 << 2),
+	DECLARE_IRQ(MAX77693_LED_IRQ_FLED1_SHORT,	LED_INT, 1 << 3),
+	DECLARE_IRQ(MAX77693_LED_IRQ_MAX_FLASH,		LED_INT, 1 << 4),
+
+	DECLARE_IRQ(MAX77693_TOPSYS_IRQ_T120C_INT,	TOPSYS_INT, 1 << 0),
+	DECLARE_IRQ(MAX77693_TOPSYS_IRQ_T140C_INT,	TOPSYS_INT, 1 << 1),
+	DECLARE_IRQ(MAX77693_TOPSYS_IRQ_LOWSYS_INT,	TOPSYS_INT, 1 << 3),
+
+	DECLARE_IRQ(MAX77693_CHG_IRQ_BYP_I,		CHG_INT, 1 << 0),
+	DECLARE_IRQ(MAX77693_CHG_IRQ_THM_I,		CHG_INT, 1 << 2),
+	DECLARE_IRQ(MAX77693_CHG_IRQ_BAT_I,		CHG_INT, 1 << 3),
+	DECLARE_IRQ(MAX77693_CHG_IRQ_CHG_I,		CHG_INT, 1 << 4),
+	DECLARE_IRQ(MAX77693_CHG_IRQ_CHGIN_I,		CHG_INT, 1 << 6),
+
+	DECLARE_IRQ(MAX77693_MUIC_IRQ_INT1_ADC,		MUIC_INT1, 1 << 0),
+	DECLARE_IRQ(MAX77693_MUIC_IRQ_INT1_ADC_LOW,	MUIC_INT1, 1 << 1),
+	DECLARE_IRQ(MAX77693_MUIC_IRQ_INT1_ADC_ERR,	MUIC_INT1, 1 << 2),
+	DECLARE_IRQ(MAX77693_MUIC_IRQ_INT1_ADC1K,	MUIC_INT1, 1 << 3),
+
+	DECLARE_IRQ(MAX77693_MUIC_IRQ_INT2_CHGTYP,	MUIC_INT2, 1 << 0),
+	DECLARE_IRQ(MAX77693_MUIC_IRQ_INT2_CHGDETREUN,	MUIC_INT2, 1 << 1),
+	DECLARE_IRQ(MAX77693_MUIC_IRQ_INT2_DCDTMR,	MUIC_INT2, 1 << 2),
+	DECLARE_IRQ(MAX77693_MUIC_IRQ_INT2_DXOVP,	MUIC_INT2, 1 << 3),
+	DECLARE_IRQ(MAX77693_MUIC_IRQ_INT2_VBVOLT,	MUIC_INT2, 1 << 4),
+	DECLARE_IRQ(MAX77693_MUIC_IRQ_INT2_VIDRM,	MUIC_INT2, 1 << 5),
+
+	DECLARE_IRQ(MAX77693_MUIC_IRQ_INT3_EOC,		MUIC_INT3, 1 << 0),
+	DECLARE_IRQ(MAX77693_MUIC_IRQ_INT3_CGMBC,	MUIC_INT3, 1 << 1),
+	DECLARE_IRQ(MAX77693_MUIC_IRQ_INT3_OVP,		MUIC_INT3, 1 << 2),
+	DECLARE_IRQ(MAX77693_MUIC_IRQ_INT3_MBCCHG_ERR,	MUIC_INT3, 1 << 3),
+	DECLARE_IRQ(MAX77693_MUIC_IRQ_INT3_CHG_ENABLED,	MUIC_INT3, 1 << 4),
+	DECLARE_IRQ(MAX77693_MUIC_IRQ_INT3_BAT_DET,	MUIC_INT3, 1 << 5),
+};
+
+static void max77693_irq_lock(struct irq_data *data)
+{
+	struct max77693_dev *max77693 = irq_get_chip_data(data->irq);
+
+	mutex_lock(&max77693->irqlock);
+}
+
+static void max77693_irq_sync_unlock(struct irq_data *data)
+{
+	struct max77693_dev *max77693 = irq_get_chip_data(data->irq);
+	int i;
+
+	for (i = 0; i < MAX77693_IRQ_GROUP_NR; i++) {
+		u8 mask_reg = max77693_mask_reg[i];
+		struct regmap *map = max77693_get_regmap(max77693, i);
+
+		if (mask_reg == MAX77693_REG_INVALID ||
+				IS_ERR_OR_NULL(map))
+			continue;
+		max77693->irq_masks_cache[i] = max77693->irq_masks_cur[i];
+
+		max77693_write_reg(map, max77693_mask_reg[i],
+				max77693->irq_masks_cur[i]);
+	}
+
+	mutex_unlock(&max77693->irqlock);
+}
+
+static const inline struct max77693_irq_data *
+irq_to_max77693_irq(struct max77693_dev *max77693, int irq)
+{
+	return &max77693_irqs[irq];
+}
+
+static void max77693_irq_mask(struct irq_data *data)
+{
+	struct max77693_dev *max77693 = irq_get_chip_data(data->irq);
+	const struct max77693_irq_data *irq_data =
+				irq_to_max77693_irq(max77693, data->irq);
+
+	if (irq_data->group >= MUIC_INT1 && irq_data->group <= MUIC_INT3)
+		max77693->irq_masks_cur[irq_data->group] &= ~irq_data->mask;
+	else
+		max77693->irq_masks_cur[irq_data->group] |= irq_data->mask;
+}
+
+static void max77693_irq_unmask(struct irq_data *data)
+{
+	struct max77693_dev *max77693 = irq_get_chip_data(data->irq);
+	const struct max77693_irq_data *irq_data =
+	    irq_to_max77693_irq(max77693, data->irq);
+
+	if (irq_data->group >= MUIC_INT1 && irq_data->group <= MUIC_INT3)
+		max77693->irq_masks_cur[irq_data->group] |= irq_data->mask;
+	else
+		max77693->irq_masks_cur[irq_data->group] &= ~irq_data->mask;
+}
+
+static struct irq_chip max77693_irq_chip = {
+	.name			= "max77693",
+	.irq_bus_lock		= max77693_irq_lock,
+	.irq_bus_sync_unlock	= max77693_irq_sync_unlock,
+	.irq_mask		= max77693_irq_mask,
+	.irq_unmask		= max77693_irq_unmask,
+};
+
+#define MAX77693_IRQSRC_CHG		(1 << 0)
+#define MAX77693_IRQSRC_TOP		(1 << 1)
+#define MAX77693_IRQSRC_FLASH		(1 << 2)
+#define MAX77693_IRQSRC_MUIC		(1 << 3)
+static irqreturn_t max77693_irq_thread(int irq, void *data)
+{
+	struct max77693_dev *max77693 = data;
+	u8 irq_reg[MAX77693_IRQ_GROUP_NR] = {};
+	u8 irq_src;
+	int ret;
+	int i, cur_irq;
+
+	ret = max77693_read_reg(max77693->regmap, MAX77693_PMIC_REG_INTSRC,
+				&irq_src);
+	if (ret < 0) {
+		dev_err(max77693->dev, "Failed to read interrupt source: %d\n",
+				ret);
+		return IRQ_NONE;
+	}
+
+	if (irq_src & MAX77693_IRQSRC_CHG)
+		/* CHG_INT */
+		ret = max77693_read_reg(max77693->regmap, MAX77693_CHG_REG_CHG_INT,
+				&irq_reg[CHG_INT]);
+
+	if (irq_src & MAX77693_IRQSRC_TOP)
+		/* TOPSYS_INT */
+		ret = max77693_read_reg(max77693->regmap,
+			MAX77693_PMIC_REG_TOPSYS_INT, &irq_reg[TOPSYS_INT]);
+
+	if (irq_src & MAX77693_IRQSRC_FLASH)
+		/* LED_INT */
+		ret = max77693_read_reg(max77693->regmap,
+			MAX77693_LED_REG_FLASH_INT, &irq_reg[LED_INT]);
+
+	if (irq_src & MAX77693_IRQSRC_MUIC)
+		/* MUIC INT1 ~ INT3 */
+		max77693_bulk_read(max77693->regmap, MAX77693_MUIC_REG_INT1,
+			MAX77693_NUM_IRQ_MUIC_REGS, &irq_reg[MUIC_INT1]);
+
+	/* Apply masking */
+	for (i = 0; i < MAX77693_IRQ_GROUP_NR; i++) {
+		if (i >= MUIC_INT1 && i <= MUIC_INT3)
+			irq_reg[i] &= max77693->irq_masks_cur[i];
+		else
+			irq_reg[i] &= ~max77693->irq_masks_cur[i];
+	}
+
+	/* Report */
+	for (i = 0; i < MAX77693_IRQ_NR; i++) {
+		if (irq_reg[max77693_irqs[i].group] & max77693_irqs[i].mask) {
+			cur_irq = irq_find_mapping(max77693->irq_domain, i);
+			if (cur_irq)
+				handle_nested_irq(cur_irq);
+		}
+	}
+
+	return IRQ_HANDLED;
+}
+
+int max77693_irq_resume(struct max77693_dev *max77693)
+{
+	if (max77693->irq)
+		max77693_irq_thread(0, max77693);
+
+	return 0;
+}
+
+static int max77693_irq_domain_map(struct irq_domain *d, unsigned int irq,
+				irq_hw_number_t hw)
+{
+	struct max77693_dev *max77693 = d->host_data;
+
+	irq_set_chip_data(irq, max77693);
+	irq_set_chip_and_handler(irq, &max77693_irq_chip, handle_edge_irq);
+	irq_set_nested_thread(irq, 1);
+#ifdef CONFIG_ARM
+	set_irq_flags(irq, IRQF_VALID);
+#else
+	irq_set_noprobe(irq);
+#endif
+	return 0;
+}
+
+static struct irq_domain_ops max77693_irq_domain_ops = {
+	.map = max77693_irq_domain_map,
+};
+
+int max77693_irq_init(struct max77693_dev *max77693)
+{
+	struct irq_domain *domain;
+	int i;
+	int ret;
+
+	mutex_init(&max77693->irqlock);
+
+	/* Mask individual interrupt sources */
+	for (i = 0; i < MAX77693_IRQ_GROUP_NR; i++) {
+		struct regmap *map;
+		/* MUIC IRQ  0:MASK 1:NOT MASK */
+		/* Other IRQ 1:MASK 0:NOT MASK */
+		if (i >= MUIC_INT1 && i <= MUIC_INT3) {
+			max77693->irq_masks_cur[i] = 0x00;
+			max77693->irq_masks_cache[i] = 0x00;
+		} else {
+			max77693->irq_masks_cur[i] = 0xff;
+			max77693->irq_masks_cache[i] = 0xff;
+		}
+		map = max77693_get_regmap(max77693, i);
+
+		if (IS_ERR_OR_NULL(map))
+			continue;
+		if (max77693_mask_reg[i] == MAX77693_REG_INVALID)
+			continue;
+		if (i >= MUIC_INT1 && i <= MUIC_INT3)
+			max77693_write_reg(map, max77693_mask_reg[i], 0x00);
+		else
+			max77693_write_reg(map, max77693_mask_reg[i], 0xff);
+	}
+
+	domain = irq_domain_add_linear(NULL, MAX77693_IRQ_NR,
+					&max77693_irq_domain_ops, max77693);
+	if (!domain) {
+		dev_err(max77693->dev, "could not create irq domain\n");
+		return -ENODEV;
+	}
+	max77693->irq_domain = domain;
+
+	ret = request_threaded_irq(max77693->irq, NULL, max77693_irq_thread,
+				   IRQF_TRIGGER_FALLING | IRQF_ONESHOT,
+				   "max77693-irq", max77693);
+
+	if (ret)
+		dev_err(max77693->dev, "Failed to request IRQ %d: %d\n",
+			max77693->irq, ret);
+
+	return 0;
+}
+
+void max77693_irq_exit(struct max77693_dev *max77693)
+{
+	if (max77693->irq)
+		free_irq(max77693->irq, max77693);
+}
diff --git a/drivers/mfd/max77693.c b/drivers/mfd/max77693.c
new file mode 100644
index 000000000000..e9e4278722f3
--- /dev/null
+++ b/drivers/mfd/max77693.c
@@ -0,0 +1,249 @@
+/*
+ * max77693.c - mfd core driver for the MAX 77693
+ *
+ * Copyright (C) 2012 Samsung Electronics
+ * SangYoung Son <hello.son@smasung.com>
+ *
+ * This program is not provided / owned by Maxim Integrated Products.
+ *
+ * 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
+ *
+ * This driver is based on max8997.c
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/i2c.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/pm_runtime.h>
+#include <linux/mutex.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/max77693.h>
+#include <linux/mfd/max77693-private.h>
+#include <linux/regulator/machine.h>
+#include <linux/regmap.h>
+
+#define I2C_ADDR_PMIC	(0xCC >> 1)	/* Charger, Flash LED */
+#define I2C_ADDR_MUIC	(0x4A >> 1)
+#define I2C_ADDR_HAPTIC	(0x90 >> 1)
+
+static struct mfd_cell max77693_devs[] = {
+	{ .name = "max77693-pmic", },
+	{ .name = "max77693-charger", },
+	{ .name = "max77693-flash", },
+	{ .name = "max77693-muic", },
+	{ .name = "max77693-haptic", },
+};
+
+int max77693_read_reg(struct regmap *map, u8 reg, u8 *dest)
+{
+	unsigned int val;
+	int ret;
+
+	ret = regmap_read(map, reg, &val);
+	*dest = val;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(max77693_read_reg);
+
+int max77693_bulk_read(struct regmap *map, u8 reg, int count, u8 *buf)
+{
+	int ret;
+
+	ret = regmap_bulk_read(map, reg, buf, count);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(max77693_bulk_read);
+
+int max77693_write_reg(struct regmap *map, u8 reg, u8 value)
+{
+	int ret;
+
+	ret = regmap_write(map, reg, value);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(max77693_write_reg);
+
+int max77693_bulk_write(struct regmap *map, u8 reg, int count, u8 *buf)
+{
+	int ret;
+
+	ret = regmap_bulk_write(map, reg, buf, count);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(max77693_bulk_write);
+
+int max77693_update_reg(struct regmap *map, u8 reg, u8 val, u8 mask)
+{
+	int ret;
+
+	ret = regmap_update_bits(map, reg, mask, val);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(max77693_update_reg);
+
+static const struct regmap_config max77693_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.max_register = MAX77693_PMIC_REG_END,
+};
+
+static int max77693_i2c_probe(struct i2c_client *i2c,
+			      const struct i2c_device_id *id)
+{
+	struct max77693_dev *max77693;
+	struct max77693_platform_data *pdata = i2c->dev.platform_data;
+	u8 reg_data;
+	int ret = 0;
+
+	max77693 = devm_kzalloc(&i2c->dev,
+			sizeof(struct max77693_dev), GFP_KERNEL);
+	if (max77693 == NULL)
+		return -ENOMEM;
+
+	max77693->regmap = devm_regmap_init_i2c(i2c, &max77693_regmap_config);
+	if (IS_ERR(max77693->regmap)) {
+		ret = PTR_ERR(max77693->regmap);
+		dev_err(max77693->dev,"failed to allocate register map: %d\n",
+				ret);
+		goto err_regmap;
+	}
+
+	i2c_set_clientdata(i2c, max77693);
+	max77693->dev = &i2c->dev;
+	max77693->i2c = i2c;
+	max77693->irq = i2c->irq;
+	max77693->type = id->driver_data;
+
+	if (!pdata)
+		goto err_regmap;
+
+	max77693->wakeup = pdata->wakeup;
+
+	mutex_init(&max77693->iolock);
+
+	if (max77693_read_reg(max77693->regmap,
+				MAX77693_PMIC_REG_PMIC_ID2, &reg_data) < 0) {
+		dev_err(max77693->dev, "device not found on this channel\n");
+		ret = -ENODEV;
+		goto err_regmap;
+	} else
+		dev_info(max77693->dev, "device ID: 0x%x\n", reg_data);
+
+	max77693->muic = i2c_new_dummy(i2c->adapter, I2C_ADDR_MUIC);
+	i2c_set_clientdata(max77693->muic, max77693);
+
+	max77693->haptic = i2c_new_dummy(i2c->adapter, I2C_ADDR_HAPTIC);
+	i2c_set_clientdata(max77693->haptic, max77693);
+
+	ret = max77693_irq_init(max77693);
+	if (ret < 0)
+		goto err_mfd;
+
+	pm_runtime_set_active(max77693->dev);
+
+	ret = mfd_add_devices(max77693->dev, -1, max77693_devs,
+			ARRAY_SIZE(max77693_devs), NULL, 0);
+	if (ret < 0)
+		goto err_mfd;
+
+	device_init_wakeup(max77693->dev, pdata->wakeup);
+
+	return ret;
+
+err_mfd:
+	i2c_unregister_device(max77693->muic);
+	i2c_unregister_device(max77693->haptic);
+err_regmap:
+	kfree(max77693);
+
+	return ret;
+}
+
+static int max77693_i2c_remove(struct i2c_client *i2c)
+{
+	struct max77693_dev *max77693 = i2c_get_clientdata(i2c);
+
+	mfd_remove_devices(max77693->dev);
+	i2c_unregister_device(max77693->muic);
+	i2c_unregister_device(max77693->haptic);
+
+	return 0;
+}
+
+static const struct i2c_device_id max77693_i2c_id[] = {
+	{ "max77693", TYPE_MAX77693 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, max77693_i2c_id);
+
+static int max77693_suspend(struct device *dev)
+{
+	struct i2c_client *i2c = container_of(dev, struct i2c_client, dev);
+	struct max77693_dev *max77693 = i2c_get_clientdata(i2c);
+
+	if (device_may_wakeup(dev))
+		irq_set_irq_wake(max77693->irq, 1);
+	return 0;
+}
+
+static int max77693_resume(struct device *dev)
+{
+	struct i2c_client *i2c = container_of(dev, struct i2c_client, dev);
+	struct max77693_dev *max77693 = i2c_get_clientdata(i2c);
+
+	if (device_may_wakeup(dev))
+		irq_set_irq_wake(max77693->irq, 0);
+	return max77693_irq_resume(max77693);
+}
+
+const struct dev_pm_ops max77693_pm = {
+	.suspend = max77693_suspend,
+	.resume = max77693_resume,
+};
+
+static struct i2c_driver max77693_i2c_driver = {
+	.driver = {
+		   .name = "max77693",
+		   .owner = THIS_MODULE,
+		   .pm = &max77693_pm,
+	},
+	.probe = max77693_i2c_probe,
+	.remove = max77693_i2c_remove,
+	.id_table = max77693_i2c_id,
+};
+
+static int __init max77693_i2c_init(void)
+{
+	return i2c_add_driver(&max77693_i2c_driver);
+}
+/* init early so consumer devices can complete system boot */
+subsys_initcall(max77693_i2c_init);
+
+static void __exit max77693_i2c_exit(void)
+{
+	i2c_del_driver(&max77693_i2c_driver);
+}
+module_exit(max77693_i2c_exit);
+
+MODULE_DESCRIPTION("MAXIM 77693 multi-function core driver");
+MODULE_AUTHOR("SangYoung, Son <hello.son@samsung.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/mfd/mc13xxx-core.c b/drivers/mfd/mc13xxx-core.c
index 738722cdecaa..f0ea3b8b3e4a 100644
--- a/drivers/mfd/mc13xxx-core.c
+++ b/drivers/mfd/mc13xxx-core.c
@@ -15,24 +15,13 @@
 #include <linux/platform_device.h>
 #include <linux/mutex.h>
 #include <linux/interrupt.h>
-#include <linux/spi/spi.h>
 #include <linux/mfd/core.h>
 #include <linux/mfd/mc13xxx.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/of_gpio.h>
 
-struct mc13xxx {
-	struct spi_device *spidev;
-	struct mutex lock;
-	int irq;
-	int flags;
-
-	irq_handler_t irqhandler[MC13XXX_NUM_IRQ];
-	void *irqdata[MC13XXX_NUM_IRQ];
-
-	int adcflags;
-};
+#include "mc13xxx.h"
 
 #define MC13XXX_IRQSTAT0	0
 #define MC13XXX_IRQSTAT0_ADCDONEI	(1 << 0)
@@ -139,34 +128,29 @@ struct mc13xxx {
 
 #define MC13XXX_ADC2		45
 
-#define MC13XXX_NUMREGS 0x3f
-
 void mc13xxx_lock(struct mc13xxx *mc13xxx)
 {
 	if (!mutex_trylock(&mc13xxx->lock)) {
-		dev_dbg(&mc13xxx->spidev->dev, "wait for %s from %pf\n",
+		dev_dbg(mc13xxx->dev, "wait for %s from %pf\n",
 				__func__, __builtin_return_address(0));
 
 		mutex_lock(&mc13xxx->lock);
 	}
-	dev_dbg(&mc13xxx->spidev->dev, "%s from %pf\n",
+	dev_dbg(mc13xxx->dev, "%s from %pf\n",
 			__func__, __builtin_return_address(0));
 }
 EXPORT_SYMBOL(mc13xxx_lock);
 
 void mc13xxx_unlock(struct mc13xxx *mc13xxx)
 {
-	dev_dbg(&mc13xxx->spidev->dev, "%s from %pf\n",
+	dev_dbg(mc13xxx->dev, "%s from %pf\n",
 			__func__, __builtin_return_address(0));
 	mutex_unlock(&mc13xxx->lock);
 }
 EXPORT_SYMBOL(mc13xxx_unlock);
 
-#define MC13XXX_REGOFFSET_SHIFT 25
 int mc13xxx_reg_read(struct mc13xxx *mc13xxx, unsigned int offset, u32 *val)
 {
-	struct spi_transfer t;
-	struct spi_message m;
 	int ret;
 
 	BUG_ON(!mutex_is_locked(&mc13xxx->lock));
@@ -174,84 +158,35 @@ int mc13xxx_reg_read(struct mc13xxx *mc13xxx, unsigned int offset, u32 *val)
 	if (offset > MC13XXX_NUMREGS)
 		return -EINVAL;
 
-	*val = offset << MC13XXX_REGOFFSET_SHIFT;
-
-	memset(&t, 0, sizeof(t));
-
-	t.tx_buf = val;
-	t.rx_buf = val;
-	t.len = sizeof(u32);
-
-	spi_message_init(&m);
-	spi_message_add_tail(&t, &m);
-
-	ret = spi_sync(mc13xxx->spidev, &m);
-
-	/* error in message.status implies error return from spi_sync */
-	BUG_ON(!ret && m.status);
+	ret = regmap_read(mc13xxx->regmap, offset, val);
+	dev_vdbg(mc13xxx->dev, "[0x%02x] -> 0x%06x\n", offset, *val);
 
-	if (ret)
-		return ret;
-
-	*val &= 0xffffff;
-
-	dev_vdbg(&mc13xxx->spidev->dev, "[0x%02x] -> 0x%06x\n", offset, *val);
-
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL(mc13xxx_reg_read);
 
 int mc13xxx_reg_write(struct mc13xxx *mc13xxx, unsigned int offset, u32 val)
 {
-	u32 buf;
-	struct spi_transfer t;
-	struct spi_message m;
-	int ret;
-
 	BUG_ON(!mutex_is_locked(&mc13xxx->lock));
 
-	dev_vdbg(&mc13xxx->spidev->dev, "[0x%02x] <- 0x%06x\n", offset, val);
+	dev_vdbg(mc13xxx->dev, "[0x%02x] <- 0x%06x\n", offset, val);
 
 	if (offset > MC13XXX_NUMREGS || val > 0xffffff)
 		return -EINVAL;
 
-	buf = 1 << 31 | offset << MC13XXX_REGOFFSET_SHIFT | val;
-
-	memset(&t, 0, sizeof(t));
-
-	t.tx_buf = &buf;
-	t.rx_buf = &buf;
-	t.len = sizeof(u32);
-
-	spi_message_init(&m);
-	spi_message_add_tail(&t, &m);
-
-	ret = spi_sync(mc13xxx->spidev, &m);
-
-	BUG_ON(!ret && m.status);
-
-	if (ret)
-		return ret;
-
-	return 0;
+	return regmap_write(mc13xxx->regmap, offset, val);
 }
 EXPORT_SYMBOL(mc13xxx_reg_write);
 
 int mc13xxx_reg_rmw(struct mc13xxx *mc13xxx, unsigned int offset,
 		u32 mask, u32 val)
 {
-	int ret;
-	u32 valread;
-
+	BUG_ON(!mutex_is_locked(&mc13xxx->lock));
 	BUG_ON(val & ~mask);
+	dev_vdbg(mc13xxx->dev, "[0x%02x] <- 0x%06x (mask: 0x%06x)\n",
+			offset, val, mask);
 
-	ret = mc13xxx_reg_read(mc13xxx, offset, &valread);
-	if (ret)
-		return ret;
-
-	valread = (valread & ~mask) | val;
-
-	return mc13xxx_reg_write(mc13xxx, offset, valread);
+	return regmap_update_bits(mc13xxx->regmap, offset, mask, val);
 }
 EXPORT_SYMBOL(mc13xxx_reg_rmw);
 
@@ -439,7 +374,7 @@ static int mc13xxx_irq_handle(struct mc13xxx *mc13xxx,
 			if (handled == IRQ_HANDLED)
 				num_handled++;
 		} else {
-			dev_err(&mc13xxx->spidev->dev,
+			dev_err(mc13xxx->dev,
 					"BUG: irq %u but no handler\n",
 					baseirq + irq);
 
@@ -475,25 +410,23 @@ static irqreturn_t mc13xxx_irq_thread(int irq, void *data)
 	return IRQ_RETVAL(handled);
 }
 
-enum mc13xxx_id {
-	MC13XXX_ID_MC13783,
-	MC13XXX_ID_MC13892,
-	MC13XXX_ID_INVALID,
-};
-
 static const char *mc13xxx_chipname[] = {
 	[MC13XXX_ID_MC13783] = "mc13783",
 	[MC13XXX_ID_MC13892] = "mc13892",
 };
 
 #define maskval(reg, mask)	(((reg) & (mask)) >> __ffs(mask))
-static int mc13xxx_identify(struct mc13xxx *mc13xxx, enum mc13xxx_id *id)
+static int mc13xxx_identify(struct mc13xxx *mc13xxx)
 {
 	u32 icid;
 	u32 revision;
-	const char *name;
 	int ret;
 
+	/*
+	 * Get the generation ID from register 46, as apparently some older
+	 * IC revisions only have this info at this location. Newer ICs seem to
+	 * have both.
+	 */
 	ret = mc13xxx_reg_read(mc13xxx, 46, &icid);
 	if (ret)
 		return ret;
@@ -502,26 +435,23 @@ static int mc13xxx_identify(struct mc13xxx *mc13xxx, enum mc13xxx_id *id)
 
 	switch (icid) {
 	case 2:
-		*id = MC13XXX_ID_MC13783;
-		name = "mc13783";
+		mc13xxx->ictype = MC13XXX_ID_MC13783;
 		break;
 	case 7:
-		*id = MC13XXX_ID_MC13892;
-		name = "mc13892";
+		mc13xxx->ictype = MC13XXX_ID_MC13892;
 		break;
 	default:
-		*id = MC13XXX_ID_INVALID;
+		mc13xxx->ictype = MC13XXX_ID_INVALID;
 		break;
 	}
 
-	if (*id == MC13XXX_ID_MC13783 || *id == MC13XXX_ID_MC13892) {
+	if (mc13xxx->ictype == MC13XXX_ID_MC13783 ||
+			mc13xxx->ictype == MC13XXX_ID_MC13892) {
 		ret = mc13xxx_reg_read(mc13xxx, MC13XXX_REVISION, &revision);
-		if (ret)
-			return ret;
 
-		dev_info(&mc13xxx->spidev->dev, "%s: rev: %d.%d, "
+		dev_info(mc13xxx->dev, "%s: rev: %d.%d, "
 				"fin: %d, fab: %d, icid: %d/%d\n",
-				mc13xxx_chipname[*id],
+				mc13xxx_chipname[mc13xxx->ictype],
 				maskval(revision, MC13XXX_REVISION_REVFULL),
 				maskval(revision, MC13XXX_REVISION_REVMETAL),
 				maskval(revision, MC13XXX_REVISION_FIN),
@@ -530,26 +460,12 @@ static int mc13xxx_identify(struct mc13xxx *mc13xxx, enum mc13xxx_id *id)
 				maskval(revision, MC13XXX_REVISION_ICIDCODE));
 	}
 
-	if (*id != MC13XXX_ID_INVALID) {
-		const struct spi_device_id *devid =
-			spi_get_device_id(mc13xxx->spidev);
-		if (!devid || devid->driver_data != *id)
-			dev_warn(&mc13xxx->spidev->dev, "device id doesn't "
-					"match auto detection!\n");
-	}
-
-	return 0;
+	return (mc13xxx->ictype == MC13XXX_ID_INVALID) ? -ENODEV : 0;
 }
 
 static const char *mc13xxx_get_chipname(struct mc13xxx *mc13xxx)
 {
-	const struct spi_device_id *devid =
-		spi_get_device_id(mc13xxx->spidev);
-
-	if (!devid)
-		return NULL;
-
-	return mc13xxx_chipname[devid->driver_data];
+	return mc13xxx_chipname[mc13xxx->ictype];
 }
 
 int mc13xxx_get_flags(struct mc13xxx *mc13xxx)
@@ -592,7 +508,7 @@ int mc13xxx_adc_do_conversion(struct mc13xxx *mc13xxx, unsigned int mode,
 	};
 	init_completion(&adcdone_data.done);
 
-	dev_dbg(&mc13xxx->spidev->dev, "%s\n", __func__);
+	dev_dbg(mc13xxx->dev, "%s\n", __func__);
 
 	mc13xxx_lock(mc13xxx);
 
@@ -637,7 +553,8 @@ int mc13xxx_adc_do_conversion(struct mc13xxx *mc13xxx, unsigned int mode,
 	adc1 |= ato << MC13783_ADC1_ATO_SHIFT;
 	if (atox)
 		adc1 |= MC13783_ADC1_ATOX;
-	dev_dbg(&mc13xxx->spidev->dev, "%s: request irq\n", __func__);
+
+	dev_dbg(mc13xxx->dev, "%s: request irq\n", __func__);
 	mc13xxx_irq_request(mc13xxx, MC13XXX_IRQ_ADCDONE,
 			mc13xxx_handler_adcdone, __func__, &adcdone_data);
 	mc13xxx_irq_ack(mc13xxx, MC13XXX_IRQ_ADCDONE);
@@ -695,7 +612,7 @@ static int mc13xxx_add_subdevice_pdata(struct mc13xxx *mc13xxx,
 	if (!cell.name)
 		return -ENOMEM;
 
-	return mfd_add_devices(&mc13xxx->spidev->dev, -1, &cell, 1, NULL, 0);
+	return mfd_add_devices(mc13xxx->dev, -1, &cell, 1, NULL, 0);
 }
 
 static int mc13xxx_add_subdevice(struct mc13xxx *mc13xxx, const char *format)
@@ -706,7 +623,7 @@ static int mc13xxx_add_subdevice(struct mc13xxx *mc13xxx, const char *format)
 #ifdef CONFIG_OF
 static int mc13xxx_probe_flags_dt(struct mc13xxx *mc13xxx)
 {
-	struct device_node *np = mc13xxx->spidev->dev.of_node;
+	struct device_node *np = mc13xxx->dev->of_node;
 
 	if (!np)
 		return -ENODEV;
@@ -732,55 +649,15 @@ static inline int mc13xxx_probe_flags_dt(struct mc13xxx *mc13xxx)
 }
 #endif
 
-static const struct spi_device_id mc13xxx_device_id[] = {
-	{
-		.name = "mc13783",
-		.driver_data = MC13XXX_ID_MC13783,
-	}, {
-		.name = "mc13892",
-		.driver_data = MC13XXX_ID_MC13892,
-	}, {
-		/* sentinel */
-	}
-};
-MODULE_DEVICE_TABLE(spi, mc13xxx_device_id);
-
-static const struct of_device_id mc13xxx_dt_ids[] = {
-	{ .compatible = "fsl,mc13783", .data = (void *) MC13XXX_ID_MC13783, },
-	{ .compatible = "fsl,mc13892", .data = (void *) MC13XXX_ID_MC13892, },
-	{ /* sentinel */ }
-};
-MODULE_DEVICE_TABLE(of, mc13xxx_dt_ids);
-
-static int mc13xxx_probe(struct spi_device *spi)
+int mc13xxx_common_init(struct mc13xxx *mc13xxx,
+		struct mc13xxx_platform_data *pdata, int irq)
 {
-	const struct of_device_id *of_id;
-	struct spi_driver *sdrv = to_spi_driver(spi->dev.driver);
-	struct mc13xxx *mc13xxx;
-	struct mc13xxx_platform_data *pdata = dev_get_platdata(&spi->dev);
-	enum mc13xxx_id id;
 	int ret;
 
-	of_id = of_match_device(mc13xxx_dt_ids, &spi->dev);
-	if (of_id)
-		sdrv->id_table = &mc13xxx_device_id[(enum mc13xxx_id) of_id->data];
-
-	mc13xxx = kzalloc(sizeof(*mc13xxx), GFP_KERNEL);
-	if (!mc13xxx)
-		return -ENOMEM;
-
-	dev_set_drvdata(&spi->dev, mc13xxx);
-	spi->mode = SPI_MODE_0 | SPI_CS_HIGH;
-	spi->bits_per_word = 32;
-	spi_setup(spi);
-
-	mc13xxx->spidev = spi;
-
-	mutex_init(&mc13xxx->lock);
 	mc13xxx_lock(mc13xxx);
 
-	ret = mc13xxx_identify(mc13xxx, &id);
-	if (ret || id == MC13XXX_ID_INVALID)
+	ret = mc13xxx_identify(mc13xxx);
+	if (ret)
 		goto err_revision;
 
 	/* mask all irqs */
@@ -792,18 +669,19 @@ static int mc13xxx_probe(struct spi_device *spi)
 	if (ret)
 		goto err_mask;
 
-	ret = request_threaded_irq(spi->irq, NULL, mc13xxx_irq_thread,
+	ret = request_threaded_irq(irq, NULL, mc13xxx_irq_thread,
 			IRQF_ONESHOT | IRQF_TRIGGER_HIGH, "mc13xxx", mc13xxx);
 
 	if (ret) {
 err_mask:
 err_revision:
 		mc13xxx_unlock(mc13xxx);
-		dev_set_drvdata(&spi->dev, NULL);
 		kfree(mc13xxx);
 		return ret;
 	}
 
+	mc13xxx->irq = irq;
+
 	mc13xxx_unlock(mc13xxx);
 
 	if (mc13xxx_probe_flags_dt(mc13xxx) < 0 && pdata)
@@ -838,42 +716,19 @@ err_revision:
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(mc13xxx_common_init);
 
-static int __devexit mc13xxx_remove(struct spi_device *spi)
+void mc13xxx_common_cleanup(struct mc13xxx *mc13xxx)
 {
-	struct mc13xxx *mc13xxx = dev_get_drvdata(&spi->dev);
+	free_irq(mc13xxx->irq, mc13xxx);
 
-	free_irq(mc13xxx->spidev->irq, mc13xxx);
+	mfd_remove_devices(mc13xxx->dev);
 
-	mfd_remove_devices(&spi->dev);
+	regmap_exit(mc13xxx->regmap);
 
 	kfree(mc13xxx);
-
-	return 0;
-}
-
-static struct spi_driver mc13xxx_driver = {
-	.id_table = mc13xxx_device_id,
-	.driver = {
-		.name = "mc13xxx",
-		.owner = THIS_MODULE,
-		.of_match_table = mc13xxx_dt_ids,
-	},
-	.probe = mc13xxx_probe,
-	.remove = __devexit_p(mc13xxx_remove),
-};
-
-static int __init mc13xxx_init(void)
-{
-	return spi_register_driver(&mc13xxx_driver);
-}
-subsys_initcall(mc13xxx_init);
-
-static void __exit mc13xxx_exit(void)
-{
-	spi_unregister_driver(&mc13xxx_driver);
 }
-module_exit(mc13xxx_exit);
+EXPORT_SYMBOL_GPL(mc13xxx_common_cleanup);
 
 MODULE_DESCRIPTION("Core driver for Freescale MC13XXX PMIC");
 MODULE_AUTHOR("Uwe Kleine-Koenig <u.kleine-koenig@pengutronix.de>");
diff --git a/drivers/mfd/mc13xxx-i2c.c b/drivers/mfd/mc13xxx-i2c.c
new file mode 100644
index 000000000000..d22501dad6a6
--- /dev/null
+++ b/drivers/mfd/mc13xxx-i2c.c
@@ -0,0 +1,128 @@
+/*
+ * Copyright 2009-2010 Creative Product Design
+ * Marc Reilly marc@cpdesign.com.au
+ *
+ * This program is free software; you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License version 2 as published by the
+ * Free Software Foundation.
+ */
+
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/mutex.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/mc13xxx.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_gpio.h>
+#include <linux/i2c.h>
+#include <linux/err.h>
+
+#include "mc13xxx.h"
+
+static const struct i2c_device_id mc13xxx_i2c_device_id[] = {
+	{
+		.name = "mc13892",
+		.driver_data = MC13XXX_ID_MC13892,
+	}, {
+		/* sentinel */
+	}
+};
+MODULE_DEVICE_TABLE(i2c, mc13xxx_i2c_device_id);
+
+static const struct of_device_id mc13xxx_dt_ids[] = {
+	{
+		.compatible = "fsl,mc13892",
+		.data = (void *) &mc13xxx_i2c_device_id[0],
+	}, {
+		/* sentinel */
+	}
+};
+MODULE_DEVICE_TABLE(of, mc13xxx_dt_ids);
+
+static struct regmap_config mc13xxx_regmap_i2c_config = {
+	.reg_bits = 8,
+	.val_bits = 24,
+
+	.max_register = MC13XXX_NUMREGS,
+
+	.cache_type = REGCACHE_NONE,
+};
+
+static int mc13xxx_i2c_probe(struct i2c_client *client,
+		const struct i2c_device_id *id)
+{
+	const struct of_device_id *of_id;
+	struct i2c_driver *idrv = to_i2c_driver(client->dev.driver);
+	struct mc13xxx *mc13xxx;
+	struct mc13xxx_platform_data *pdata = dev_get_platdata(&client->dev);
+	int ret;
+
+	of_id = of_match_device(mc13xxx_dt_ids, &client->dev);
+	if (of_id)
+		idrv->id_table = (const struct i2c_device_id*) of_id->data;
+
+	mc13xxx = kzalloc(sizeof(*mc13xxx), GFP_KERNEL);
+	if (!mc13xxx)
+		return -ENOMEM;
+
+	dev_set_drvdata(&client->dev, mc13xxx);
+
+	mc13xxx->dev = &client->dev;
+	mutex_init(&mc13xxx->lock);
+
+	mc13xxx->regmap = regmap_init_i2c(client, &mc13xxx_regmap_i2c_config);
+	if (IS_ERR(mc13xxx->regmap)) {
+		ret = PTR_ERR(mc13xxx->regmap);
+		dev_err(mc13xxx->dev, "Failed to initialize register map: %d\n",
+				ret);
+		dev_set_drvdata(&client->dev, NULL);
+		kfree(mc13xxx);
+		return ret;
+	}
+
+	ret = mc13xxx_common_init(mc13xxx, pdata, client->irq);
+
+	if (ret == 0 && (id->driver_data != mc13xxx->ictype))
+		dev_warn(mc13xxx->dev,
+				"device id doesn't match auto detection!\n");
+
+	return ret;
+}
+
+static int __devexit mc13xxx_i2c_remove(struct i2c_client *client)
+{
+	struct mc13xxx *mc13xxx = dev_get_drvdata(&client->dev);
+
+	mc13xxx_common_cleanup(mc13xxx);
+
+	return 0;
+}
+
+static struct i2c_driver mc13xxx_i2c_driver = {
+	.id_table = mc13xxx_i2c_device_id,
+	.driver = {
+		.owner = THIS_MODULE,
+		.name = "mc13xxx",
+		.of_match_table = mc13xxx_dt_ids,
+	},
+	.probe = mc13xxx_i2c_probe,
+	.remove = __devexit_p(mc13xxx_i2c_remove),
+};
+
+static int __init mc13xxx_i2c_init(void)
+{
+	return i2c_add_driver(&mc13xxx_i2c_driver);
+}
+subsys_initcall(mc13xxx_i2c_init);
+
+static void __exit mc13xxx_i2c_exit(void)
+{
+	i2c_del_driver(&mc13xxx_i2c_driver);
+}
+module_exit(mc13xxx_i2c_exit);
+
+MODULE_DESCRIPTION("i2c driver for Freescale MC13XXX PMIC");
+MODULE_AUTHOR("Marc Reilly <marc@cpdesign.com.au");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mfd/mc13xxx-spi.c b/drivers/mfd/mc13xxx-spi.c
new file mode 100644
index 000000000000..3fcdab3eb8eb
--- /dev/null
+++ b/drivers/mfd/mc13xxx-spi.c
@@ -0,0 +1,140 @@
+/*
+ * Copyright 2009-2010 Pengutronix
+ * Uwe Kleine-Koenig <u.kleine-koenig@pengutronix.de>
+ *
+ * loosely based on an earlier driver that has
+ * Copyright 2009 Pengutronix, Sascha Hauer <s.hauer@pengutronix.de>
+ *
+ * This program is free software; you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License version 2 as published by the
+ * Free Software Foundation.
+ */
+
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/mutex.h>
+#include <linux/interrupt.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/mc13xxx.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_gpio.h>
+#include <linux/err.h>
+#include <linux/spi/spi.h>
+
+#include "mc13xxx.h"
+
+static const struct spi_device_id mc13xxx_device_id[] = {
+	{
+		.name = "mc13783",
+		.driver_data = MC13XXX_ID_MC13783,
+	}, {
+		.name = "mc13892",
+		.driver_data = MC13XXX_ID_MC13892,
+	}, {
+		/* sentinel */
+	}
+};
+MODULE_DEVICE_TABLE(spi, mc13xxx_device_id);
+
+static const struct of_device_id mc13xxx_dt_ids[] = {
+	{ .compatible = "fsl,mc13783", .data = (void *) MC13XXX_ID_MC13783, },
+	{ .compatible = "fsl,mc13892", .data = (void *) MC13XXX_ID_MC13892, },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, mc13xxx_dt_ids);
+
+static struct regmap_config mc13xxx_regmap_spi_config = {
+	.reg_bits = 7,
+	.pad_bits = 1,
+	.val_bits = 24,
+
+	.max_register = MC13XXX_NUMREGS,
+
+	.cache_type = REGCACHE_NONE,
+};
+
+static int mc13xxx_spi_probe(struct spi_device *spi)
+{
+	const struct of_device_id *of_id;
+	struct spi_driver *sdrv = to_spi_driver(spi->dev.driver);
+	struct mc13xxx *mc13xxx;
+	struct mc13xxx_platform_data *pdata = dev_get_platdata(&spi->dev);
+	int ret;
+
+	of_id = of_match_device(mc13xxx_dt_ids, &spi->dev);
+	if (of_id)
+		sdrv->id_table = &mc13xxx_device_id[(enum mc13xxx_id) of_id->data];
+
+	mc13xxx = kzalloc(sizeof(*mc13xxx), GFP_KERNEL);
+	if (!mc13xxx)
+		return -ENOMEM;
+
+	dev_set_drvdata(&spi->dev, mc13xxx);
+	spi->mode = SPI_MODE_0 | SPI_CS_HIGH;
+	spi->bits_per_word = 32;
+
+	mc13xxx->dev = &spi->dev;
+	mutex_init(&mc13xxx->lock);
+
+	mc13xxx->regmap = regmap_init_spi(spi, &mc13xxx_regmap_spi_config);
+	if (IS_ERR(mc13xxx->regmap)) {
+		ret = PTR_ERR(mc13xxx->regmap);
+		dev_err(mc13xxx->dev, "Failed to initialize register map: %d\n",
+				ret);
+		dev_set_drvdata(&spi->dev, NULL);
+		kfree(mc13xxx);
+		return ret;
+	}
+
+	ret = mc13xxx_common_init(mc13xxx, pdata, spi->irq);
+
+	if (ret) {
+		dev_set_drvdata(&spi->dev, NULL);
+	} else {
+		const struct spi_device_id *devid =
+			spi_get_device_id(spi);
+		if (!devid || devid->driver_data != mc13xxx->ictype)
+			dev_warn(mc13xxx->dev,
+				"device id doesn't match auto detection!\n");
+	}
+
+	return ret;
+}
+
+static int __devexit mc13xxx_spi_remove(struct spi_device *spi)
+{
+	struct mc13xxx *mc13xxx = dev_get_drvdata(&spi->dev);
+
+	mc13xxx_common_cleanup(mc13xxx);
+
+	return 0;
+}
+
+static struct spi_driver mc13xxx_spi_driver = {
+	.id_table = mc13xxx_device_id,
+	.driver = {
+		.name = "mc13xxx",
+		.owner = THIS_MODULE,
+		.of_match_table = mc13xxx_dt_ids,
+	},
+	.probe = mc13xxx_spi_probe,
+	.remove = __devexit_p(mc13xxx_spi_remove),
+};
+
+static int __init mc13xxx_init(void)
+{
+	return spi_register_driver(&mc13xxx_spi_driver);
+}
+subsys_initcall(mc13xxx_init);
+
+static void __exit mc13xxx_exit(void)
+{
+	spi_unregister_driver(&mc13xxx_spi_driver);
+}
+module_exit(mc13xxx_exit);
+
+MODULE_DESCRIPTION("Core driver for Freescale MC13XXX PMIC");
+MODULE_AUTHOR("Uwe Kleine-Koenig <u.kleine-koenig@pengutronix.de>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mfd/mc13xxx.h b/drivers/mfd/mc13xxx.h
new file mode 100644
index 000000000000..bbba06feea06
--- /dev/null
+++ b/drivers/mfd/mc13xxx.h
@@ -0,0 +1,45 @@
+/*
+ * Copyright 2012 Creative Product Design
+ * Marc Reilly <marc@cpdesign.com.au>
+ *
+ * This program is free software; you can redistribute it and/or modify it under
+ * the terms of the GNU General Public License version 2 as published by the
+ * Free Software Foundation.
+ */
+#ifndef __DRIVERS_MFD_MC13XXX_H
+#define __DRIVERS_MFD_MC13XXX_H
+
+#include <linux/mutex.h>
+#include <linux/regmap.h>
+#include <linux/mfd/mc13xxx.h>
+
+enum mc13xxx_id {
+	MC13XXX_ID_MC13783,
+	MC13XXX_ID_MC13892,
+	MC13XXX_ID_INVALID,
+};
+
+#define MC13XXX_NUMREGS 0x3f
+
+struct mc13xxx {
+	struct regmap *regmap;
+
+	struct device *dev;
+	enum mc13xxx_id ictype;
+
+	struct mutex lock;
+	int irq;
+	int flags;
+
+	irq_handler_t irqhandler[MC13XXX_NUM_IRQ];
+	void *irqdata[MC13XXX_NUM_IRQ];
+
+	int adcflags;
+};
+
+int mc13xxx_common_init(struct mc13xxx *mc13xxx,
+		struct mc13xxx_platform_data *pdata, int irq);
+
+void mc13xxx_common_cleanup(struct mc13xxx *mc13xxx);
+
+#endif /* __DRIVERS_MFD_MC13XXX_H */
diff --git a/drivers/mfd/pcf50633-core.c b/drivers/mfd/pcf50633-core.c
index 189c2f07b83f..29c122bf28ea 100644
--- a/drivers/mfd/pcf50633-core.c
+++ b/drivers/mfd/pcf50633-core.c
@@ -204,7 +204,7 @@ static int __devinit pcf50633_probe(struct i2c_client *client,
 		return -ENOENT;
 	}
 
-	pcf = kzalloc(sizeof(*pcf), GFP_KERNEL);
+	pcf = devm_kzalloc(&client->dev, sizeof(*pcf), GFP_KERNEL);
 	if (!pcf)
 		return -ENOMEM;
 
@@ -212,12 +212,11 @@ static int __devinit pcf50633_probe(struct i2c_client *client,
 
 	mutex_init(&pcf->lock);
 
-	pcf->regmap = regmap_init_i2c(client, &pcf50633_regmap_config);
+	pcf->regmap = devm_regmap_init_i2c(client, &pcf50633_regmap_config);
 	if (IS_ERR(pcf->regmap)) {
 		ret = PTR_ERR(pcf->regmap);
-		dev_err(pcf->dev, "Failed to allocate register map: %d\n",
-			ret);
-		goto err_free;
+		dev_err(pcf->dev, "Failed to allocate register map: %d\n", ret);
+		return ret;
 	}
 
 	i2c_set_clientdata(client, pcf);
@@ -228,7 +227,7 @@ static int __devinit pcf50633_probe(struct i2c_client *client,
 	if (version < 0 || variant < 0) {
 		dev_err(pcf->dev, "Unable to probe pcf50633\n");
 		ret = -ENODEV;
-		goto err_regmap;
+		return ret;
 	}
 
 	dev_info(pcf->dev, "Probed device version %d variant %d\n",
@@ -237,16 +236,11 @@ static int __devinit pcf50633_probe(struct i2c_client *client,
 	pcf50633_irq_init(pcf, client->irq);
 
 	/* Create sub devices */
-	pcf50633_client_dev_register(pcf, "pcf50633-input",
-						&pcf->input_pdev);
-	pcf50633_client_dev_register(pcf, "pcf50633-rtc",
-						&pcf->rtc_pdev);
-	pcf50633_client_dev_register(pcf, "pcf50633-mbc",
-						&pcf->mbc_pdev);
-	pcf50633_client_dev_register(pcf, "pcf50633-adc",
-						&pcf->adc_pdev);
-	pcf50633_client_dev_register(pcf, "pcf50633-backlight",
-						&pcf->bl_pdev);
+	pcf50633_client_dev_register(pcf, "pcf50633-input", &pcf->input_pdev);
+	pcf50633_client_dev_register(pcf, "pcf50633-rtc", &pcf->rtc_pdev);
+	pcf50633_client_dev_register(pcf, "pcf50633-mbc", &pcf->mbc_pdev);
+	pcf50633_client_dev_register(pcf, "pcf50633-adc", &pcf->adc_pdev);
+	pcf50633_client_dev_register(pcf, "pcf50633-backlight", &pcf->bl_pdev);
 
 
 	for (i = 0; i < PCF50633_NUM_REGULATORS; i++) {
@@ -274,13 +268,6 @@ static int __devinit pcf50633_probe(struct i2c_client *client,
 		pdata->probe_done(pcf);
 
 	return 0;
-
-err_regmap:
-	regmap_exit(pcf->regmap);
-err_free:
-	kfree(pcf);
-
-	return ret;
 }
 
 static int __devexit pcf50633_remove(struct i2c_client *client)
@@ -300,9 +287,6 @@ static int __devexit pcf50633_remove(struct i2c_client *client)
 	for (i = 0; i < PCF50633_NUM_REGULATORS; i++)
 		platform_device_unregister(pcf->regulator_pdev[i]);
 
-	regmap_exit(pcf->regmap);
-	kfree(pcf);
-
 	return 0;
 }
 
diff --git a/drivers/mfd/rc5t583.c b/drivers/mfd/rc5t583.c
index 44afae0a69ce..cdc1df7fa0e9 100644
--- a/drivers/mfd/rc5t583.c
+++ b/drivers/mfd/rc5t583.c
@@ -75,6 +75,7 @@ static struct deepsleep_control_data deepsleep_data[] = {
 	(RC5T583_EXT_PWRREQ1_CONTROL | RC5T583_EXT_PWRREQ2_CONTROL)
 
 static struct mfd_cell rc5t583_subdevs[] = {
+	{.name = "rc5t583-gpio",},
 	{.name = "rc5t583-regulator",},
 	{.name = "rc5t583-rtc",      },
 	{.name = "rc5t583-key",      }
@@ -267,7 +268,7 @@ static int __devinit rc5t583_i2c_probe(struct i2c_client *i2c,
 	rc5t583->dev = &i2c->dev;
 	i2c_set_clientdata(i2c, rc5t583);
 
-	rc5t583->regmap = regmap_init_i2c(i2c, &rc5t583_regmap_config);
+	rc5t583->regmap = devm_regmap_init_i2c(i2c, &rc5t583_regmap_config);
 	if (IS_ERR(rc5t583->regmap)) {
 		ret = PTR_ERR(rc5t583->regmap);
 		dev_err(&i2c->dev, "regmap initialization failed: %d\n", ret);
@@ -276,7 +277,7 @@ static int __devinit rc5t583_i2c_probe(struct i2c_client *i2c,
 
 	ret = rc5t583_clear_ext_power_req(rc5t583, pdata);
 	if (ret < 0)
-		goto err_irq_init;
+		return ret;
 
 	if (i2c->irq) {
 		ret = rc5t583_irq_init(rc5t583, i2c->irq, pdata->irq_base);
@@ -299,8 +300,6 @@ static int __devinit rc5t583_i2c_probe(struct i2c_client *i2c,
 err_add_devs:
 	if (irq_init_success)
 		rc5t583_irq_exit(rc5t583);
-err_irq_init:
-	regmap_exit(rc5t583->regmap);
 	return ret;
 }
 
@@ -310,7 +309,6 @@ static int  __devexit rc5t583_i2c_remove(struct i2c_client *i2c)
 
 	mfd_remove_devices(rc5t583->dev);
 	rc5t583_irq_exit(rc5t583);
-	regmap_exit(rc5t583->regmap);
 	return 0;
 }
 
diff --git a/drivers/mfd/rdc321x-southbridge.c b/drivers/mfd/rdc321x-southbridge.c
index 809bd4a61089..685d61e431ad 100644
--- a/drivers/mfd/rdc321x-southbridge.c
+++ b/drivers/mfd/rdc321x-southbridge.c
@@ -108,18 +108,7 @@ static struct pci_driver rdc321x_sb_driver = {
 	.remove		= __devexit_p(rdc321x_sb_remove),
 };
 
-static int __init rdc321x_sb_init(void)
-{
-	return pci_register_driver(&rdc321x_sb_driver);
-}
-
-static void __exit rdc321x_sb_exit(void)
-{
-	pci_unregister_driver(&rdc321x_sb_driver);
-}
-
-module_init(rdc321x_sb_init);
-module_exit(rdc321x_sb_exit);
+module_pci_driver(rdc321x_sb_driver);
 
 MODULE_AUTHOR("Florian Fainelli <florian@openwrt.org>");
 MODULE_LICENSE("GPL");
diff --git a/drivers/mfd/s5m-core.c b/drivers/mfd/s5m-core.c
index 48949d998d10..dd170307e60e 100644
--- a/drivers/mfd/s5m-core.c
+++ b/drivers/mfd/s5m-core.c
@@ -114,12 +114,12 @@ static int s5m87xx_i2c_probe(struct i2c_client *i2c,
 		s5m87xx->wakeup = pdata->wakeup;
 	}
 
-	s5m87xx->regmap = regmap_init_i2c(i2c, &s5m_regmap_config);
+	s5m87xx->regmap = devm_regmap_init_i2c(i2c, &s5m_regmap_config);
 	if (IS_ERR(s5m87xx->regmap)) {
 		ret = PTR_ERR(s5m87xx->regmap);
 		dev_err(&i2c->dev, "Failed to allocate register map: %d\n",
 			ret);
-		goto err;
+		return ret;
 	}
 
 	s5m87xx->rtc = i2c_new_dummy(i2c->adapter, RTC_I2C_ADDR);
@@ -159,7 +159,6 @@ err:
 	mfd_remove_devices(s5m87xx->dev);
 	s5m_irq_exit(s5m87xx);
 	i2c_unregister_device(s5m87xx->rtc);
-	regmap_exit(s5m87xx->regmap);
 	return ret;
 }
 
@@ -170,7 +169,6 @@ static int s5m87xx_i2c_remove(struct i2c_client *i2c)
 	mfd_remove_devices(s5m87xx->dev);
 	s5m_irq_exit(s5m87xx);
 	i2c_unregister_device(s5m87xx->rtc);
-	regmap_exit(s5m87xx->regmap);
 	return 0;
 }
 
diff --git a/drivers/mfd/sta2x11-mfd.c b/drivers/mfd/sta2x11-mfd.c
new file mode 100644
index 000000000000..d31fed07aefb
--- /dev/null
+++ b/drivers/mfd/sta2x11-mfd.c
@@ -0,0 +1,467 @@
+/*
+ * Copyright (c) 2009-2011 Wind River Systems, Inc.
+ * Copyright (c) 2011 ST Microelectronics (Alessandro Rubini)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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/spinlock.h>
+#include <linux/errno.h>
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/list.h>
+#include <linux/io.h>
+#include <linux/ioport.h>
+#include <linux/pci.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/platform_device.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/sta2x11-mfd.h>
+
+#include <asm/sta2x11.h>
+
+/* This describes STA2X11 MFD chip for us, we may have several */
+struct sta2x11_mfd {
+	struct sta2x11_instance *instance;
+	spinlock_t lock;
+	struct list_head list;
+	void __iomem *sctl_regs;
+	void __iomem *apbreg_regs;
+};
+
+static LIST_HEAD(sta2x11_mfd_list);
+
+/* Three functions to act on the list */
+static struct sta2x11_mfd *sta2x11_mfd_find(struct pci_dev *pdev)
+{
+	struct sta2x11_instance *instance;
+	struct sta2x11_mfd *mfd;
+
+	if (!pdev && !list_empty(&sta2x11_mfd_list)) {
+		pr_warning("%s: Unspecified device, "
+			    "using first instance\n", __func__);
+		return list_entry(sta2x11_mfd_list.next,
+				  struct sta2x11_mfd, list);
+	}
+
+	instance = sta2x11_get_instance(pdev);
+	if (!instance)
+		return NULL;
+	list_for_each_entry(mfd, &sta2x11_mfd_list, list) {
+		if (mfd->instance == instance)
+			return mfd;
+	}
+	return NULL;
+}
+
+static int __devinit sta2x11_mfd_add(struct pci_dev *pdev, gfp_t flags)
+{
+	struct sta2x11_mfd *mfd = sta2x11_mfd_find(pdev);
+	struct sta2x11_instance *instance;
+
+	if (mfd)
+		return -EBUSY;
+	instance = sta2x11_get_instance(pdev);
+	if (!instance)
+		return -EINVAL;
+	mfd = kzalloc(sizeof(*mfd), flags);
+	if (!mfd)
+		return -ENOMEM;
+	INIT_LIST_HEAD(&mfd->list);
+	spin_lock_init(&mfd->lock);
+	mfd->instance = instance;
+	list_add(&mfd->list, &sta2x11_mfd_list);
+	return 0;
+}
+
+static int __devexit mfd_remove(struct pci_dev *pdev)
+{
+	struct sta2x11_mfd *mfd = sta2x11_mfd_find(pdev);
+
+	if (!mfd)
+		return -ENODEV;
+	list_del(&mfd->list);
+	kfree(mfd);
+	return 0;
+}
+
+/* These two functions are exported and are not expected to fail */
+u32 sta2x11_sctl_mask(struct pci_dev *pdev, u32 reg, u32 mask, u32 val)
+{
+	struct sta2x11_mfd *mfd = sta2x11_mfd_find(pdev);
+	u32 r;
+	unsigned long flags;
+
+	if (!mfd) {
+		dev_warn(&pdev->dev, ": can't access sctl regs\n");
+		return 0;
+	}
+	if (!mfd->sctl_regs) {
+		dev_warn(&pdev->dev, ": system ctl not initialized\n");
+		return 0;
+	}
+	spin_lock_irqsave(&mfd->lock, flags);
+	r = readl(mfd->sctl_regs + reg);
+	r &= ~mask;
+	r |= val;
+	if (mask)
+		writel(r, mfd->sctl_regs + reg);
+	spin_unlock_irqrestore(&mfd->lock, flags);
+	return r;
+}
+EXPORT_SYMBOL(sta2x11_sctl_mask);
+
+u32 sta2x11_apbreg_mask(struct pci_dev *pdev, u32 reg, u32 mask, u32 val)
+{
+	struct sta2x11_mfd *mfd = sta2x11_mfd_find(pdev);
+	u32 r;
+	unsigned long flags;
+
+	if (!mfd) {
+		dev_warn(&pdev->dev, ": can't access apb regs\n");
+		return 0;
+	}
+	if (!mfd->apbreg_regs) {
+		dev_warn(&pdev->dev, ": apb bridge not initialized\n");
+		return 0;
+	}
+	spin_lock_irqsave(&mfd->lock, flags);
+	r = readl(mfd->apbreg_regs + reg);
+	r &= ~mask;
+	r |= val;
+	if (mask)
+		writel(r, mfd->apbreg_regs + reg);
+	spin_unlock_irqrestore(&mfd->lock, flags);
+	return r;
+}
+EXPORT_SYMBOL(sta2x11_apbreg_mask);
+
+/* Two debugfs files, for our registers (FIXME: one instance only) */
+#define REG(regname) {.name = #regname, .offset = SCTL_ ## regname}
+static struct debugfs_reg32 sta2x11_sctl_regs[] = {
+	REG(SCCTL), REG(ARMCFG), REG(SCPLLCTL), REG(SCPLLFCTRL),
+	REG(SCRESFRACT), REG(SCRESCTRL1), REG(SCRESXTRL2), REG(SCPEREN0),
+	REG(SCPEREN1), REG(SCPEREN2), REG(SCGRST), REG(SCPCIPMCR1),
+	REG(SCPCIPMCR2), REG(SCPCIPMSR1), REG(SCPCIPMSR2), REG(SCPCIPMSR3),
+	REG(SCINTREN), REG(SCRISR), REG(SCCLKSTAT0), REG(SCCLKSTAT1),
+	REG(SCCLKSTAT2), REG(SCRSTSTA),
+};
+#undef REG
+
+static struct debugfs_regset32 sctl_regset = {
+	.regs = sta2x11_sctl_regs,
+	.nregs = ARRAY_SIZE(sta2x11_sctl_regs),
+};
+
+#define REG(regname) {.name = #regname, .offset = regname}
+static struct debugfs_reg32 sta2x11_apbreg_regs[] = {
+	REG(APBREG_BSR), REG(APBREG_PAER), REG(APBREG_PWAC), REG(APBREG_PRAC),
+	REG(APBREG_PCG), REG(APBREG_PUR), REG(APBREG_EMU_PCG),
+};
+#undef REG
+
+static struct debugfs_regset32 apbreg_regset = {
+	.regs = sta2x11_apbreg_regs,
+	.nregs = ARRAY_SIZE(sta2x11_apbreg_regs),
+};
+
+static struct dentry *sta2x11_sctl_debugfs;
+static struct dentry *sta2x11_apbreg_debugfs;
+
+/* Probe for the two platform devices */
+static int sta2x11_sctl_probe(struct platform_device *dev)
+{
+	struct pci_dev **pdev;
+	struct sta2x11_mfd *mfd;
+	struct resource *res;
+
+	pdev = dev->dev.platform_data;
+	mfd = sta2x11_mfd_find(*pdev);
+	if (!mfd)
+		return -ENODEV;
+
+	res = platform_get_resource(dev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -ENOMEM;
+
+	if (!request_mem_region(res->start, resource_size(res),
+				"sta2x11-sctl"))
+		return -EBUSY;
+
+	mfd->sctl_regs = ioremap(res->start, resource_size(res));
+	if (!mfd->sctl_regs) {
+		release_mem_region(res->start, resource_size(res));
+		return -ENOMEM;
+	}
+	sctl_regset.base = mfd->sctl_regs;
+	sta2x11_sctl_debugfs = debugfs_create_regset32("sta2x11-sctl",
+						  S_IFREG | S_IRUGO,
+						  NULL, &sctl_regset);
+	return 0;
+}
+
+static int sta2x11_apbreg_probe(struct platform_device *dev)
+{
+	struct pci_dev **pdev;
+	struct sta2x11_mfd *mfd;
+	struct resource *res;
+
+	pdev = dev->dev.platform_data;
+	dev_dbg(&dev->dev, "%s: pdata is %p\n", __func__, pdev);
+	dev_dbg(&dev->dev, "%s: *pdata is %p\n", __func__, *pdev);
+
+	mfd = sta2x11_mfd_find(*pdev);
+	if (!mfd)
+		return -ENODEV;
+
+	res = platform_get_resource(dev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -ENOMEM;
+
+	if (!request_mem_region(res->start, resource_size(res),
+				"sta2x11-apbreg"))
+		return -EBUSY;
+
+	mfd->apbreg_regs = ioremap(res->start, resource_size(res));
+	if (!mfd->apbreg_regs) {
+		release_mem_region(res->start, resource_size(res));
+		return -ENOMEM;
+	}
+	dev_dbg(&dev->dev, "%s: regbase %p\n", __func__, mfd->apbreg_regs);
+
+	apbreg_regset.base = mfd->apbreg_regs;
+	sta2x11_apbreg_debugfs = debugfs_create_regset32("sta2x11-apbreg",
+						  S_IFREG | S_IRUGO,
+						  NULL, &apbreg_regset);
+	return 0;
+}
+
+/* The two platform drivers */
+static struct platform_driver sta2x11_sctl_platform_driver = {
+	.driver = {
+		.name	= "sta2x11-sctl",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= sta2x11_sctl_probe,
+};
+
+static int __init sta2x11_sctl_init(void)
+{
+	pr_info("%s\n", __func__);
+	return platform_driver_register(&sta2x11_sctl_platform_driver);
+}
+
+static struct platform_driver sta2x11_platform_driver = {
+	.driver = {
+		.name	= "sta2x11-apbreg",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= sta2x11_apbreg_probe,
+};
+
+static int __init sta2x11_apbreg_init(void)
+{
+	pr_info("%s\n", __func__);
+	return platform_driver_register(&sta2x11_platform_driver);
+}
+
+/*
+ * What follows is the PCI device that hosts the above two pdevs.
+ * Each logic block is 4kB and they are all consecutive: we use this info.
+ */
+
+/* Bar 0 */
+enum bar0_cells {
+	STA2X11_GPIO_0 = 0,
+	STA2X11_GPIO_1,
+	STA2X11_GPIO_2,
+	STA2X11_GPIO_3,
+	STA2X11_SCTL,
+	STA2X11_SCR,
+	STA2X11_TIME,
+};
+/* Bar 1 */
+enum bar1_cells {
+	STA2X11_APBREG = 0,
+};
+#define CELL_4K(_name, _cell) { \
+		.name = _name, \
+		.start = _cell * 4096, .end = _cell * 4096 + 4095, \
+		.flags = IORESOURCE_MEM, \
+		}
+
+static const __devinitconst struct resource gpio_resources[] = {
+	{
+		.name = "sta2x11_gpio", /* 4 consecutive cells, 1 driver */
+		.start = 0,
+		.end = (4 * 4096) - 1,
+		.flags = IORESOURCE_MEM,
+	}
+};
+static const __devinitconst struct resource sctl_resources[] = {
+	CELL_4K("sta2x11-sctl", STA2X11_SCTL),
+};
+static const __devinitconst struct resource scr_resources[] = {
+	CELL_4K("sta2x11-scr", STA2X11_SCR),
+};
+static const __devinitconst struct resource time_resources[] = {
+	CELL_4K("sta2x11-time", STA2X11_TIME),
+};
+
+static const __devinitconst struct resource apbreg_resources[] = {
+	CELL_4K("sta2x11-apbreg", STA2X11_APBREG),
+};
+
+#define DEV(_name, _r) \
+	{ .name = _name, .num_resources = ARRAY_SIZE(_r), .resources = _r, }
+
+static __devinitdata struct mfd_cell sta2x11_mfd_bar0[] = {
+	DEV("sta2x11-gpio", gpio_resources), /* offset 0: we add pdata later */
+	DEV("sta2x11-sctl", sctl_resources),
+	DEV("sta2x11-scr", scr_resources),
+	DEV("sta2x11-time", time_resources),
+};
+
+static __devinitdata struct mfd_cell sta2x11_mfd_bar1[] = {
+	DEV("sta2x11-apbreg", apbreg_resources),
+};
+
+static int sta2x11_mfd_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+	pci_save_state(pdev);
+	pci_disable_device(pdev);
+	pci_set_power_state(pdev, pci_choose_state(pdev, state));
+
+	return 0;
+}
+
+static int sta2x11_mfd_resume(struct pci_dev *pdev)
+{
+	int err;
+
+	pci_set_power_state(pdev, 0);
+	err = pci_enable_device(pdev);
+	if (err)
+		return err;
+	pci_restore_state(pdev);
+
+	return 0;
+}
+
+static int __devinit sta2x11_mfd_probe(struct pci_dev *pdev,
+				       const struct pci_device_id *pci_id)
+{
+	int err, i;
+	struct sta2x11_gpio_pdata *gpio_data;
+
+	dev_info(&pdev->dev, "%s\n", __func__);
+
+	err = pci_enable_device(pdev);
+	if (err) {
+		dev_err(&pdev->dev, "Can't enable device.\n");
+		return err;
+	}
+
+	err = pci_enable_msi(pdev);
+	if (err)
+		dev_info(&pdev->dev, "Enable msi failed\n");
+
+	/* Read gpio config data as pci device's platform data */
+	gpio_data = dev_get_platdata(&pdev->dev);
+	if (!gpio_data)
+		dev_warn(&pdev->dev, "no gpio configuration\n");
+
+	dev_dbg(&pdev->dev, "%s, gpio_data = %p (%p)\n", __func__,
+		gpio_data, &gpio_data);
+	dev_dbg(&pdev->dev, "%s, pdev = %p (%p)\n", __func__,
+		pdev, &pdev);
+
+	/* platform data is the pci device for all of them */
+	for (i = 0; i < ARRAY_SIZE(sta2x11_mfd_bar0); i++) {
+		sta2x11_mfd_bar0[i].pdata_size = sizeof(pdev);
+		sta2x11_mfd_bar0[i].platform_data = &pdev;
+	}
+	sta2x11_mfd_bar1[0].pdata_size = sizeof(pdev);
+	sta2x11_mfd_bar1[0].platform_data = &pdev;
+
+	/* Record this pdev before mfd_add_devices: their probe looks for it */
+	sta2x11_mfd_add(pdev, GFP_ATOMIC);
+
+
+	err = mfd_add_devices(&pdev->dev, -1,
+			      sta2x11_mfd_bar0,
+			      ARRAY_SIZE(sta2x11_mfd_bar0),
+			      &pdev->resource[0],
+			      0);
+	if (err) {
+		dev_err(&pdev->dev, "mfd_add_devices[0] failed: %d\n", err);
+		goto err_disable;
+	}
+
+	err = mfd_add_devices(&pdev->dev, -1,
+			      sta2x11_mfd_bar1,
+			      ARRAY_SIZE(sta2x11_mfd_bar1),
+			      &pdev->resource[1],
+			      0);
+	if (err) {
+		dev_err(&pdev->dev, "mfd_add_devices[1] failed: %d\n", err);
+		goto err_disable;
+	}
+
+	return 0;
+
+err_disable:
+	mfd_remove_devices(&pdev->dev);
+	pci_disable_device(pdev);
+	pci_disable_msi(pdev);
+	return err;
+}
+
+static DEFINE_PCI_DEVICE_TABLE(sta2x11_mfd_tbl) = {
+	{PCI_DEVICE(PCI_VENDOR_ID_STMICRO, PCI_DEVICE_ID_STMICRO_GPIO)},
+	{0,},
+};
+
+static struct pci_driver sta2x11_mfd_driver = {
+	.name =		"sta2x11-mfd",
+	.id_table =	sta2x11_mfd_tbl,
+	.probe =	sta2x11_mfd_probe,
+	.suspend =	sta2x11_mfd_suspend,
+	.resume =	sta2x11_mfd_resume,
+};
+
+static int __init sta2x11_mfd_init(void)
+{
+	pr_info("%s\n", __func__);
+	return pci_register_driver(&sta2x11_mfd_driver);
+}
+
+/*
+ * All of this must be ready before "normal" devices like MMCI appear.
+ * But MFD (the pci device) can't be too early. The following choice
+ * prepares platform drivers very early and probe the PCI device later,
+ * but before other PCI devices.
+ */
+subsys_initcall(sta2x11_apbreg_init);
+subsys_initcall(sta2x11_sctl_init);
+rootfs_initcall(sta2x11_mfd_init);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Wind River");
+MODULE_DESCRIPTION("STA2x11 mfd for GPIO, SCTL and APBREG");
+MODULE_DEVICE_TABLE(pci, sta2x11_mfd_tbl);
diff --git a/drivers/mfd/stmpe-spi.c b/drivers/mfd/stmpe-spi.c
index b58c43c7ea93..afd459013ecb 100644
--- a/drivers/mfd/stmpe-spi.c
+++ b/drivers/mfd/stmpe-spi.c
@@ -122,7 +122,6 @@ MODULE_DEVICE_TABLE(spi, stmpe_id);
 static struct spi_driver stmpe_spi_driver = {
 	.driver = {
 		.name	= "stmpe-spi",
-		.bus	= &spi_bus_type,
 		.owner	= THIS_MODULE,
 #ifdef CONFIG_PM
 		.pm	= &stmpe_dev_pm_ops,
diff --git a/drivers/mfd/tps65090.c b/drivers/mfd/tps65090.c
index 47f802bf1848..396b9d1b6bd6 100644
--- a/drivers/mfd/tps65090.c
+++ b/drivers/mfd/tps65090.c
@@ -283,27 +283,24 @@ static int __devinit tps65090_i2c_probe(struct i2c_client *client,
 		}
 	}
 
-	tps65090->rmap = regmap_init_i2c(tps65090->client,
-		&tps65090_regmap_config);
+	tps65090->rmap = devm_regmap_init_i2c(tps65090->client,
+					      &tps65090_regmap_config);
 	if (IS_ERR(tps65090->rmap)) {
-		dev_err(&client->dev, "regmap_init failed with err: %ld\n",
-			PTR_ERR(tps65090->rmap));
+		ret = PTR_ERR(tps65090->rmap);
+		dev_err(&client->dev, "regmap_init failed with err: %d\n", ret);
 		goto err_irq_exit;
-	};
+	}
 
 	ret = mfd_add_devices(tps65090->dev, -1, tps65090s,
 		ARRAY_SIZE(tps65090s), NULL, 0);
 	if (ret) {
 		dev_err(&client->dev, "add mfd devices failed with err: %d\n",
 			ret);
-		goto err_regmap_exit;
+		goto err_irq_exit;
 	}
 
 	return 0;
 
-err_regmap_exit:
-	regmap_exit(tps65090->rmap);
-
 err_irq_exit:
 	if (client->irq)
 		free_irq(client->irq, tps65090);
@@ -316,29 +313,34 @@ static int __devexit tps65090_i2c_remove(struct i2c_client *client)
 	struct tps65090 *tps65090 = i2c_get_clientdata(client);
 
 	mfd_remove_devices(tps65090->dev);
-	regmap_exit(tps65090->rmap);
 	if (client->irq)
 		free_irq(client->irq, tps65090);
 
 	return 0;
 }
 
-#ifdef CONFIG_PM
-static int tps65090_i2c_suspend(struct i2c_client *client, pm_message_t state)
+#ifdef CONFIG_PM_SLEEP
+static int tps65090_suspend(struct device *dev)
 {
+	struct i2c_client *client = to_i2c_client(dev);
 	if (client->irq)
 		disable_irq(client->irq);
 	return 0;
 }
 
-static int tps65090_i2c_resume(struct i2c_client *client)
+static int tps65090_resume(struct device *dev)
 {
+	struct i2c_client *client = to_i2c_client(dev);
 	if (client->irq)
 		enable_irq(client->irq);
 	return 0;
 }
 #endif
 
+static const struct dev_pm_ops tps65090_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(tps65090_suspend, tps65090_resume)
+};
+
 static const struct i2c_device_id tps65090_id_table[] = {
 	{ "tps65090", 0 },
 	{ },
@@ -349,13 +351,10 @@ static struct i2c_driver tps65090_driver = {
 	.driver	= {
 		.name	= "tps65090",
 		.owner	= THIS_MODULE,
+		.pm	= &tps65090_pm_ops,
 	},
 	.probe		= tps65090_i2c_probe,
 	.remove		= __devexit_p(tps65090_i2c_remove),
-#ifdef CONFIG_PM
-	.suspend	= tps65090_i2c_suspend,
-	.resume		= tps65090_i2c_resume,
-#endif
 	.id_table	= tps65090_id_table,
 };
 
diff --git a/drivers/mfd/tps65217.c b/drivers/mfd/tps65217.c
index f7d854e4cc62..db194e433c08 100644
--- a/drivers/mfd/tps65217.c
+++ b/drivers/mfd/tps65217.c
@@ -96,7 +96,7 @@ EXPORT_SYMBOL_GPL(tps65217_reg_write);
  * @val: Value to write.
  * @level: Password protected level
  */
-int tps65217_update_bits(struct tps65217 *tps, unsigned int reg,
+static int tps65217_update_bits(struct tps65217 *tps, unsigned int reg,
 		unsigned int mask, unsigned int val, unsigned int level)
 {
 	int ret;
@@ -150,7 +150,7 @@ static int __devinit tps65217_probe(struct i2c_client *client,
 		return -ENOMEM;
 
 	tps->pdata = pdata;
-	tps->regmap = regmap_init_i2c(client, &tps65217_regmap_config);
+	tps->regmap = devm_regmap_init_i2c(client, &tps65217_regmap_config);
 	if (IS_ERR(tps->regmap)) {
 		ret = PTR_ERR(tps->regmap);
 		dev_err(tps->dev, "Failed to allocate register map: %d\n",
@@ -163,9 +163,9 @@ static int __devinit tps65217_probe(struct i2c_client *client,
 
 	ret = tps65217_reg_read(tps, TPS65217_REG_CHIPID, &version);
 	if (ret < 0) {
-		dev_err(tps->dev, "Failed to read revision"
-					" register: %d\n", ret);
-		goto err_regmap;
+		dev_err(tps->dev, "Failed to read revision register: %d\n",
+			ret);
+		return ret;
 	}
 
 	dev_info(tps->dev, "TPS65217 ID %#x version 1.%d\n",
@@ -190,11 +190,6 @@ static int __devinit tps65217_probe(struct i2c_client *client,
 	}
 
 	return 0;
-
-err_regmap:
-	regmap_exit(tps->regmap);
-
-	return ret;
 }
 
 static int __devexit tps65217_remove(struct i2c_client *client)
@@ -205,8 +200,6 @@ static int __devexit tps65217_remove(struct i2c_client *client)
 	for (i = 0; i < TPS65217_NUM_REGULATOR; i++)
 		platform_device_unregister(tps->regulator_pdev[i]);
 
-	regmap_exit(tps->regmap);
-
 	return 0;
 }
 
diff --git a/drivers/mfd/tps65910-irq.c b/drivers/mfd/tps65910-irq.c
index c9ed5c00a621..09aab3e4776d 100644
--- a/drivers/mfd/tps65910-irq.c
+++ b/drivers/mfd/tps65910-irq.c
@@ -20,15 +20,10 @@
 #include <linux/device.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
+#include <linux/irqdomain.h>
 #include <linux/gpio.h>
 #include <linux/mfd/tps65910.h>
 
-static inline int irq_to_tps65910_irq(struct tps65910 *tps65910,
-							int irq)
-{
-	return (irq - tps65910->irq_base);
-}
-
 /*
  * This is a threaded IRQ handler so can access I2C/SPI.  Since all
  * interrupts are clear on read the IRQ line will be reasserted and
@@ -41,28 +36,28 @@ static inline int irq_to_tps65910_irq(struct tps65910 *tps65910,
 static irqreturn_t tps65910_irq(int irq, void *irq_data)
 {
 	struct tps65910 *tps65910 = irq_data;
+	unsigned int reg;
 	u32 irq_sts;
 	u32 irq_mask;
-	u8 reg;
 	int i;
 
-	tps65910->read(tps65910, TPS65910_INT_STS, 1, &reg);
+	tps65910_reg_read(tps65910, TPS65910_INT_STS, &reg);
 	irq_sts = reg;
-	tps65910->read(tps65910, TPS65910_INT_STS2, 1, &reg);
+	tps65910_reg_read(tps65910, TPS65910_INT_STS2, &reg);
 	irq_sts |= reg << 8;
 	switch (tps65910_chip_id(tps65910)) {
 	case TPS65911:
-		tps65910->read(tps65910, TPS65910_INT_STS3, 1, &reg);
+		tps65910_reg_read(tps65910, TPS65910_INT_STS3, &reg);
 		irq_sts |= reg << 16;
 	}
 
-	tps65910->read(tps65910, TPS65910_INT_MSK, 1, &reg);
+	tps65910_reg_read(tps65910, TPS65910_INT_MSK, &reg);
 	irq_mask = reg;
-	tps65910->read(tps65910, TPS65910_INT_MSK2, 1, &reg);
+	tps65910_reg_read(tps65910, TPS65910_INT_MSK2, &reg);
 	irq_mask |= reg << 8;
 	switch (tps65910_chip_id(tps65910)) {
 	case TPS65911:
-		tps65910->read(tps65910, TPS65910_INT_MSK3, 1, &reg);
+		tps65910_reg_read(tps65910, TPS65910_INT_MSK3, &reg);
 		irq_mask |= reg << 16;
 	}
 
@@ -76,19 +71,19 @@ static irqreturn_t tps65910_irq(int irq, void *irq_data)
 		if (!(irq_sts & (1 << i)))
 			continue;
 
-		handle_nested_irq(tps65910->irq_base + i);
+		handle_nested_irq(irq_find_mapping(tps65910->domain, i));
 	}
 
 	/* Write the STS register back to clear IRQs we handled */
 	reg = irq_sts & 0xFF;
 	irq_sts >>= 8;
-	tps65910->write(tps65910, TPS65910_INT_STS, 1, &reg);
+	tps65910_reg_write(tps65910, TPS65910_INT_STS, reg);
 	reg = irq_sts & 0xFF;
-	tps65910->write(tps65910, TPS65910_INT_STS2, 1, &reg);
+	tps65910_reg_write(tps65910, TPS65910_INT_STS2, reg);
 	switch (tps65910_chip_id(tps65910)) {
 	case TPS65911:
 		reg = irq_sts >> 8;
-		tps65910->write(tps65910, TPS65910_INT_STS3, 1, &reg);
+		tps65910_reg_write(tps65910, TPS65910_INT_STS3, reg);
 	}
 
 	return IRQ_HANDLED;
@@ -105,27 +100,27 @@ static void tps65910_irq_sync_unlock(struct irq_data *data)
 {
 	struct tps65910 *tps65910 = irq_data_get_irq_chip_data(data);
 	u32 reg_mask;
-	u8 reg;
+	unsigned int reg;
 
-	tps65910->read(tps65910, TPS65910_INT_MSK, 1, &reg);
+	tps65910_reg_read(tps65910, TPS65910_INT_MSK, &reg);
 	reg_mask = reg;
-	tps65910->read(tps65910, TPS65910_INT_MSK2, 1, &reg);
+	tps65910_reg_read(tps65910, TPS65910_INT_MSK2, &reg);
 	reg_mask |= reg << 8;
 	switch (tps65910_chip_id(tps65910)) {
 	case TPS65911:
-		tps65910->read(tps65910, TPS65910_INT_MSK3, 1, &reg);
+		tps65910_reg_read(tps65910, TPS65910_INT_MSK3, &reg);
 		reg_mask |= reg << 16;
 	}
 
 	if (tps65910->irq_mask != reg_mask) {
 		reg = tps65910->irq_mask & 0xFF;
-		tps65910->write(tps65910, TPS65910_INT_MSK, 1, &reg);
+		tps65910_reg_write(tps65910, TPS65910_INT_MSK, reg);
 		reg = tps65910->irq_mask >> 8 & 0xFF;
-		tps65910->write(tps65910, TPS65910_INT_MSK2, 1, &reg);
+		tps65910_reg_write(tps65910, TPS65910_INT_MSK2, reg);
 		switch (tps65910_chip_id(tps65910)) {
 		case TPS65911:
 			reg = tps65910->irq_mask >> 16;
-			tps65910->write(tps65910, TPS65910_INT_MSK3, 1, &reg);
+			tps65910_reg_write(tps65910, TPS65910_INT_MSK3, reg);
 		}
 	}
 	mutex_unlock(&tps65910->irq_lock);
@@ -135,14 +130,14 @@ static void tps65910_irq_enable(struct irq_data *data)
 {
 	struct tps65910 *tps65910 = irq_data_get_irq_chip_data(data);
 
-	tps65910->irq_mask &= ~( 1 << irq_to_tps65910_irq(tps65910, data->irq));
+	tps65910->irq_mask &= ~(1 << data->hwirq);
 }
 
 static void tps65910_irq_disable(struct irq_data *data)
 {
 	struct tps65910 *tps65910 = irq_data_get_irq_chip_data(data);
 
-	tps65910->irq_mask |= ( 1 << irq_to_tps65910_irq(tps65910, data->irq));
+	tps65910->irq_mask |= (1 << data->hwirq);
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -164,10 +159,35 @@ static struct irq_chip tps65910_irq_chip = {
 	.irq_set_wake = tps65910_irq_set_wake,
 };
 
+static int tps65910_irq_map(struct irq_domain *h, unsigned int virq,
+				irq_hw_number_t hw)
+{
+	struct tps65910 *tps65910 = h->host_data;
+
+	irq_set_chip_data(virq, tps65910);
+	irq_set_chip_and_handler(virq, &tps65910_irq_chip, handle_edge_irq);
+	irq_set_nested_thread(virq, 1);
+
+	/* ARM needs us to explicitly flag the IRQ as valid
+	 * and will set them noprobe when we do so. */
+#ifdef CONFIG_ARM
+	set_irq_flags(virq, IRQF_VALID);
+#else
+	irq_set_noprobe(virq);
+#endif
+
+	return 0;
+}
+
+static struct irq_domain_ops tps65910_domain_ops = {
+	.map	= tps65910_irq_map,
+	.xlate	= irq_domain_xlate_twocell,
+};
+
 int tps65910_irq_init(struct tps65910 *tps65910, int irq,
 		    struct tps65910_platform_data *pdata)
 {
-	int ret, cur_irq;
+	int ret;
 	int flags = IRQF_ONESHOT;
 
 	if (!irq) {
@@ -175,17 +195,11 @@ int tps65910_irq_init(struct tps65910 *tps65910, int irq,
 		return -EINVAL;
 	}
 
-	if (!pdata || !pdata->irq_base) {
-		dev_warn(tps65910->dev, "No interrupt support, no IRQ base\n");
+	if (!pdata) {
+		dev_warn(tps65910->dev, "No interrupt support, no pdata\n");
 		return -EINVAL;
 	}
 
-	tps65910->irq_mask = 0xFFFFFF;
-
-	mutex_init(&tps65910->irq_lock);
-	tps65910->chip_irq = irq;
-	tps65910->irq_base = pdata->irq_base;
-
 	switch (tps65910_chip_id(tps65910)) {
 	case TPS65910:
 		tps65910->irq_num = TPS65910_NUM_IRQ;
@@ -195,22 +209,36 @@ int tps65910_irq_init(struct tps65910 *tps65910, int irq,
 		break;
 	}
 
-	/* Register with genirq */
-	for (cur_irq = tps65910->irq_base;
-	     cur_irq < tps65910->irq_num + tps65910->irq_base;
-	     cur_irq++) {
-		irq_set_chip_data(cur_irq, tps65910);
-		irq_set_chip_and_handler(cur_irq, &tps65910_irq_chip,
-					 handle_edge_irq);
-		irq_set_nested_thread(cur_irq, 1);
-
-		/* ARM needs us to explicitly flag the IRQ as valid
-		 * and will set them noprobe when we do so. */
-#ifdef CONFIG_ARM
-		set_irq_flags(cur_irq, IRQF_VALID);
-#else
-		irq_set_noprobe(cur_irq);
-#endif
+	if (pdata->irq_base > 0) {
+		pdata->irq_base = irq_alloc_descs(pdata->irq_base, 0,
+					tps65910->irq_num, -1);
+		if (pdata->irq_base < 0) {
+			dev_warn(tps65910->dev, "Failed to alloc IRQs: %d\n",
+					pdata->irq_base);
+			return pdata->irq_base;
+		}
+	}
+
+	tps65910->irq_mask = 0xFFFFFF;
+
+	mutex_init(&tps65910->irq_lock);
+	tps65910->chip_irq = irq;
+	tps65910->irq_base = pdata->irq_base;
+
+	if (pdata->irq_base > 0)
+		tps65910->domain = irq_domain_add_legacy(tps65910->dev->of_node,
+					tps65910->irq_num,
+					pdata->irq_base,
+					0,
+					&tps65910_domain_ops, tps65910);
+	else
+		tps65910->domain = irq_domain_add_linear(tps65910->dev->of_node,
+					tps65910->irq_num,
+					&tps65910_domain_ops, tps65910);
+
+	if (!tps65910->domain) {
+		dev_err(tps65910->dev, "Failed to create IRQ domain\n");
+		return -ENOMEM;
 	}
 
 	ret = request_threaded_irq(irq, NULL, tps65910_irq, flags,
diff --git a/drivers/mfd/tps65910.c b/drivers/mfd/tps65910.c
index bf2b25ebf2ca..be9e07b77325 100644
--- a/drivers/mfd/tps65910.c
+++ b/drivers/mfd/tps65910.c
@@ -19,13 +19,16 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/i2c.h>
-#include <linux/gpio.h>
 #include <linux/mfd/core.h>
 #include <linux/regmap.h>
 #include <linux/mfd/tps65910.h>
+#include <linux/of_device.h>
 
 static struct mfd_cell tps65910s[] = {
 	{
+		.name = "tps65910-gpio",
+	},
+	{
 		.name = "tps65910-pmic",
 	},
 	{
@@ -37,30 +40,6 @@ static struct mfd_cell tps65910s[] = {
 };
 
 
-static int tps65910_i2c_read(struct tps65910 *tps65910, u8 reg,
-				  int bytes, void *dest)
-{
-	return regmap_bulk_read(tps65910->regmap, reg, dest, bytes);
-}
-
-static int tps65910_i2c_write(struct tps65910 *tps65910, u8 reg,
-				  int bytes, void *src)
-{
-	return regmap_bulk_write(tps65910->regmap, reg, src, bytes);
-}
-
-int tps65910_set_bits(struct tps65910 *tps65910, u8 reg, u8 mask)
-{
-	return regmap_update_bits(tps65910->regmap, reg, mask, mask);
-}
-EXPORT_SYMBOL_GPL(tps65910_set_bits);
-
-int tps65910_clear_bits(struct tps65910 *tps65910, u8 reg, u8 mask)
-{
-	return regmap_update_bits(tps65910->regmap, reg, mask, 0);
-}
-EXPORT_SYMBOL_GPL(tps65910_clear_bits);
-
 static bool is_volatile_reg(struct device *dev, unsigned int reg)
 {
 	struct tps65910 *tps65910 = dev_get_drvdata(dev);
@@ -85,80 +64,197 @@ static const struct regmap_config tps65910_regmap_config = {
 	.reg_bits = 8,
 	.val_bits = 8,
 	.volatile_reg = is_volatile_reg,
-	.max_register = TPS65910_MAX_REGISTER,
-	.num_reg_defaults_raw = TPS65910_MAX_REGISTER,
+	.max_register = TPS65910_MAX_REGISTER - 1,
 	.cache_type = REGCACHE_RBTREE,
 };
 
-static int tps65910_i2c_probe(struct i2c_client *i2c,
-			    const struct i2c_device_id *id)
+static int __devinit tps65910_sleepinit(struct tps65910 *tps65910,
+		struct tps65910_board *pmic_pdata)
+{
+	struct device *dev = NULL;
+	int ret = 0;
+
+	dev = tps65910->dev;
+
+	if (!pmic_pdata->en_dev_slp)
+		return 0;
+
+	/* enabling SLEEP device state */
+	ret = tps65910_reg_set_bits(tps65910, TPS65910_DEVCTRL,
+				DEVCTRL_DEV_SLP_MASK);
+	if (ret < 0) {
+		dev_err(dev, "set dev_slp failed: %d\n", ret);
+		goto err_sleep_init;
+	}
+
+	/* Return if there is no sleep keepon data. */
+	if (!pmic_pdata->slp_keepon)
+		return 0;
+
+	if (pmic_pdata->slp_keepon->therm_keepon) {
+		ret = tps65910_reg_set_bits(tps65910,
+				TPS65910_SLEEP_KEEP_RES_ON,
+				SLEEP_KEEP_RES_ON_THERM_KEEPON_MASK);
+		if (ret < 0) {
+			dev_err(dev, "set therm_keepon failed: %d\n", ret);
+			goto disable_dev_slp;
+		}
+	}
+
+	if (pmic_pdata->slp_keepon->clkout32k_keepon) {
+		ret = tps65910_reg_set_bits(tps65910,
+				TPS65910_SLEEP_KEEP_RES_ON,
+				SLEEP_KEEP_RES_ON_CLKOUT32K_KEEPON_MASK);
+		if (ret < 0) {
+			dev_err(dev, "set clkout32k_keepon failed: %d\n", ret);
+			goto disable_dev_slp;
+		}
+	}
+
+	if (pmic_pdata->slp_keepon->i2chs_keepon) {
+		ret = tps65910_reg_set_bits(tps65910,
+				TPS65910_SLEEP_KEEP_RES_ON,
+				SLEEP_KEEP_RES_ON_I2CHS_KEEPON_MASK);
+		if (ret < 0) {
+			dev_err(dev, "set i2chs_keepon failed: %d\n", ret);
+			goto disable_dev_slp;
+		}
+	}
+
+	return 0;
+
+disable_dev_slp:
+	tps65910_reg_clear_bits(tps65910, TPS65910_DEVCTRL,
+				DEVCTRL_DEV_SLP_MASK);
+
+err_sleep_init:
+	return ret;
+}
+
+#ifdef CONFIG_OF
+static struct of_device_id tps65910_of_match[] = {
+	{ .compatible = "ti,tps65910", .data = (void *)TPS65910},
+	{ .compatible = "ti,tps65911", .data = (void *)TPS65911},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, tps65910_of_match);
+
+static struct tps65910_board *tps65910_parse_dt(struct i2c_client *client,
+						int *chip_id)
+{
+	struct device_node *np = client->dev.of_node;
+	struct tps65910_board *board_info;
+	unsigned int prop;
+	const struct of_device_id *match;
+	int ret = 0;
+
+	match = of_match_device(tps65910_of_match, &client->dev);
+	if (!match) {
+		dev_err(&client->dev, "Failed to find matching dt id\n");
+		return NULL;
+	}
+
+	*chip_id  = (int)match->data;
+
+	board_info = devm_kzalloc(&client->dev, sizeof(*board_info),
+			GFP_KERNEL);
+	if (!board_info) {
+		dev_err(&client->dev, "Failed to allocate pdata\n");
+		return NULL;
+	}
+
+	ret = of_property_read_u32(np, "ti,vmbch-threshold", &prop);
+	if (!ret)
+		board_info->vmbch_threshold = prop;
+	else if (*chip_id == TPS65911)
+		dev_warn(&client->dev, "VMBCH-Threshold not specified");
+
+	ret = of_property_read_u32(np, "ti,vmbch2-threshold", &prop);
+	if (!ret)
+		board_info->vmbch2_threshold = prop;
+	else if (*chip_id == TPS65911)
+		dev_warn(&client->dev, "VMBCH2-Threshold not specified");
+
+	board_info->irq = client->irq;
+	board_info->irq_base = -1;
+
+	return board_info;
+}
+#else
+static inline
+struct tps65910_board *tps65910_parse_dt(struct i2c_client *client,
+					 int *chip_id)
+{
+	return NULL;
+}
+#endif
+
+static __devinit int tps65910_i2c_probe(struct i2c_client *i2c,
+					const struct i2c_device_id *id)
 {
 	struct tps65910 *tps65910;
 	struct tps65910_board *pmic_plat_data;
+	struct tps65910_board *of_pmic_plat_data = NULL;
 	struct tps65910_platform_data *init_data;
 	int ret = 0;
+	int chip_id = id->driver_data;
 
 	pmic_plat_data = dev_get_platdata(&i2c->dev);
+
+	if (!pmic_plat_data && i2c->dev.of_node) {
+		pmic_plat_data = tps65910_parse_dt(i2c, &chip_id);
+		of_pmic_plat_data = pmic_plat_data;
+	}
+
 	if (!pmic_plat_data)
 		return -EINVAL;
 
-	init_data = kzalloc(sizeof(struct tps65910_platform_data), GFP_KERNEL);
+	init_data = devm_kzalloc(&i2c->dev, sizeof(*init_data), GFP_KERNEL);
 	if (init_data == NULL)
 		return -ENOMEM;
 
-	tps65910 = kzalloc(sizeof(struct tps65910), GFP_KERNEL);
-	if (tps65910 == NULL) {
-		kfree(init_data);
+	tps65910 = devm_kzalloc(&i2c->dev, sizeof(*tps65910), GFP_KERNEL);
+	if (tps65910 == NULL)
 		return -ENOMEM;
-	}
 
+	tps65910->of_plat_data = of_pmic_plat_data;
 	i2c_set_clientdata(i2c, tps65910);
 	tps65910->dev = &i2c->dev;
 	tps65910->i2c_client = i2c;
-	tps65910->id = id->driver_data;
-	tps65910->read = tps65910_i2c_read;
-	tps65910->write = tps65910_i2c_write;
+	tps65910->id = chip_id;
 	mutex_init(&tps65910->io_mutex);
 
-	tps65910->regmap = regmap_init_i2c(i2c, &tps65910_regmap_config);
+	tps65910->regmap = devm_regmap_init_i2c(i2c, &tps65910_regmap_config);
 	if (IS_ERR(tps65910->regmap)) {
 		ret = PTR_ERR(tps65910->regmap);
 		dev_err(&i2c->dev, "regmap initialization failed: %d\n", ret);
-		goto regmap_err;
+		return ret;
 	}
 
 	ret = mfd_add_devices(tps65910->dev, -1,
 			      tps65910s, ARRAY_SIZE(tps65910s),
 			      NULL, 0);
-	if (ret < 0)
-		goto err;
+	if (ret < 0) {
+		dev_err(&i2c->dev, "mfd_add_devices failed: %d\n", ret);
+		return ret;
+	}
 
 	init_data->irq = pmic_plat_data->irq;
 	init_data->irq_base = pmic_plat_data->irq_base;
 
-	tps65910_gpio_init(tps65910, pmic_plat_data->gpio_base);
-
 	tps65910_irq_init(tps65910, init_data->irq, init_data);
 
-	kfree(init_data);
-	return ret;
+	tps65910_sleepinit(tps65910, pmic_plat_data);
 
-err:
-	regmap_exit(tps65910->regmap);
-regmap_err:
-	kfree(tps65910);
-	kfree(init_data);
 	return ret;
 }
 
-static int tps65910_i2c_remove(struct i2c_client *i2c)
+static __devexit int tps65910_i2c_remove(struct i2c_client *i2c)
 {
 	struct tps65910 *tps65910 = i2c_get_clientdata(i2c);
 
 	tps65910_irq_exit(tps65910);
 	mfd_remove_devices(tps65910->dev);
-	regmap_exit(tps65910->regmap);
-	kfree(tps65910);
 
 	return 0;
 }
@@ -175,9 +271,10 @@ static struct i2c_driver tps65910_i2c_driver = {
 	.driver = {
 		   .name = "tps65910",
 		   .owner = THIS_MODULE,
+		   .of_match_table = of_match_ptr(tps65910_of_match),
 	},
 	.probe = tps65910_i2c_probe,
-	.remove = tps65910_i2c_remove,
+	.remove = __devexit_p(tps65910_i2c_remove),
 	.id_table = tps65910_i2c_id,
 };
 
diff --git a/drivers/mfd/twl4030-irq.c b/drivers/mfd/twl4030-irq.c
index 5d656e814358..ad733d76207a 100644
--- a/drivers/mfd/twl4030-irq.c
+++ b/drivers/mfd/twl4030-irq.c
@@ -757,6 +757,7 @@ int twl4030_init_irq(struct device *dev, int irq_num)
 		dev_err(dev, "could not claim irq%d: %d\n", irq_num, status);
 		goto fail_rqirq;
 	}
+	enable_irq_wake(irq_num);
 
 	return irq_base;
 fail_rqirq:
diff --git a/drivers/mfd/twl6040-core.c b/drivers/mfd/twl6040-core.c
index 2d6bedadca09..4ded9e7aa246 100644
--- a/drivers/mfd/twl6040-core.c
+++ b/drivers/mfd/twl6040-core.c
@@ -27,7 +27,12 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/kernel.h>
+#include <linux/err.h>
 #include <linux/platform_device.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/of_gpio.h>
+#include <linux/of_platform.h>
 #include <linux/gpio.h>
 #include <linux/delay.h>
 #include <linux/i2c.h>
@@ -35,8 +40,24 @@
 #include <linux/err.h>
 #include <linux/mfd/core.h>
 #include <linux/mfd/twl6040.h>
+#include <linux/regulator/consumer.h>
 
 #define VIBRACTRL_MEMBER(reg) ((reg == TWL6040_REG_VIBCTLL) ? 0 : 1)
+#define TWL6040_NUM_SUPPLIES	(2)
+
+static bool twl6040_has_vibra(struct twl6040_platform_data *pdata,
+			      struct device_node *node)
+{
+	if (pdata && pdata->vibra)
+		return true;
+
+#ifdef CONFIG_OF
+	if (of_find_node_by_name(node, "vibra"))
+		return true;
+#endif
+
+	return false;
+}
 
 int twl6040_reg_read(struct twl6040 *twl6040, unsigned int reg)
 {
@@ -502,17 +523,18 @@ static int __devinit twl6040_probe(struct i2c_client *client,
 				     const struct i2c_device_id *id)
 {
 	struct twl6040_platform_data *pdata = client->dev.platform_data;
+	struct device_node *node = client->dev.of_node;
 	struct twl6040 *twl6040;
 	struct mfd_cell *cell = NULL;
-	int ret, children = 0;
+	int irq, ret, children = 0;
 
-	if (!pdata) {
+	if (!pdata && !node) {
 		dev_err(&client->dev, "Platform data is missing\n");
 		return -EINVAL;
 	}
 
 	/* In order to operate correctly we need valid interrupt config */
-	if (!client->irq || !pdata->irq_base) {
+	if (!client->irq) {
 		dev_err(&client->dev, "Invalid IRQ configuration\n");
 		return -EINVAL;
 	}
@@ -524,7 +546,7 @@ static int __devinit twl6040_probe(struct i2c_client *client,
 		goto err;
 	}
 
-	twl6040->regmap = regmap_init_i2c(client, &twl6040_regmap_config);
+	twl6040->regmap = devm_regmap_init_i2c(client, &twl6040_regmap_config);
 	if (IS_ERR(twl6040->regmap)) {
 		ret = PTR_ERR(twl6040->regmap);
 		goto err;
@@ -532,9 +554,23 @@ static int __devinit twl6040_probe(struct i2c_client *client,
 
 	i2c_set_clientdata(client, twl6040);
 
+	twl6040->supplies[0].supply = "vio";
+	twl6040->supplies[1].supply = "v2v1";
+	ret = regulator_bulk_get(&client->dev, TWL6040_NUM_SUPPLIES,
+				 twl6040->supplies);
+	if (ret != 0) {
+		dev_err(&client->dev, "Failed to get supplies: %d\n", ret);
+		goto regulator_get_err;
+	}
+
+	ret = regulator_bulk_enable(TWL6040_NUM_SUPPLIES, twl6040->supplies);
+	if (ret != 0) {
+		dev_err(&client->dev, "Failed to enable supplies: %d\n", ret);
+		goto power_err;
+	}
+
 	twl6040->dev = &client->dev;
 	twl6040->irq = client->irq;
-	twl6040->irq_base = pdata->irq_base;
 
 	mutex_init(&twl6040->mutex);
 	mutex_init(&twl6040->io_mutex);
@@ -543,22 +579,26 @@ static int __devinit twl6040_probe(struct i2c_client *client,
 	twl6040->rev = twl6040_reg_read(twl6040, TWL6040_REG_ASICREV);
 
 	/* ERRATA: Automatic power-up is not possible in ES1.0 */
-	if (twl6040_get_revid(twl6040) > TWL6040_REV_ES1_0)
-		twl6040->audpwron = pdata->audpwron_gpio;
-	else
+	if (twl6040_get_revid(twl6040) > TWL6040_REV_ES1_0) {
+		if (pdata)
+			twl6040->audpwron = pdata->audpwron_gpio;
+		else
+			twl6040->audpwron = of_get_named_gpio(node,
+						"ti,audpwron-gpio", 0);
+	} else
 		twl6040->audpwron = -EINVAL;
 
 	if (gpio_is_valid(twl6040->audpwron)) {
 		ret = gpio_request_one(twl6040->audpwron, GPIOF_OUT_INIT_LOW,
 				       "audpwron");
 		if (ret)
-			goto gpio1_err;
+			goto gpio_err;
 	}
 
 	/* codec interrupt */
 	ret = twl6040_irq_init(twl6040);
 	if (ret)
-		goto gpio2_err;
+		goto irq_init_err;
 
 	ret = request_threaded_irq(twl6040->irq_base + TWL6040_IRQ_READY,
 				   NULL, twl6040_naudint_handler, 0,
@@ -572,22 +612,27 @@ static int __devinit twl6040_probe(struct i2c_client *client,
 	/* dual-access registers controlled by I2C only */
 	twl6040_set_bits(twl6040, TWL6040_REG_ACCCTL, TWL6040_I2CSEL);
 
-	if (pdata->codec) {
-		int irq = twl6040->irq_base + TWL6040_IRQ_PLUG;
-
-		cell = &twl6040->cells[children];
-		cell->name = "twl6040-codec";
-		twl6040_codec_rsrc[0].start = irq;
-		twl6040_codec_rsrc[0].end = irq;
-		cell->resources = twl6040_codec_rsrc;
-		cell->num_resources = ARRAY_SIZE(twl6040_codec_rsrc);
+	/*
+	 * The main functionality of twl6040 to provide audio on OMAP4+ systems.
+	 * We can add the ASoC codec child whenever this driver has been loaded.
+	 * The ASoC codec can work without pdata, pass the platform_data only if
+	 * it has been provided.
+	 */
+	irq = twl6040->irq_base + TWL6040_IRQ_PLUG;
+	cell = &twl6040->cells[children];
+	cell->name = "twl6040-codec";
+	twl6040_codec_rsrc[0].start = irq;
+	twl6040_codec_rsrc[0].end = irq;
+	cell->resources = twl6040_codec_rsrc;
+	cell->num_resources = ARRAY_SIZE(twl6040_codec_rsrc);
+	if (pdata && pdata->codec) {
 		cell->platform_data = pdata->codec;
 		cell->pdata_size = sizeof(*pdata->codec);
-		children++;
 	}
+	children++;
 
-	if (pdata->vibra) {
-		int irq = twl6040->irq_base + TWL6040_IRQ_VIB;
+	if (twl6040_has_vibra(pdata, node)) {
+		irq = twl6040->irq_base + TWL6040_IRQ_VIB;
 
 		cell = &twl6040->cells[children];
 		cell->name = "twl6040-vibra";
@@ -596,21 +641,17 @@ static int __devinit twl6040_probe(struct i2c_client *client,
 		cell->resources = twl6040_vibra_rsrc;
 		cell->num_resources = ARRAY_SIZE(twl6040_vibra_rsrc);
 
-		cell->platform_data = pdata->vibra;
-		cell->pdata_size = sizeof(*pdata->vibra);
+		if (pdata && pdata->vibra) {
+			cell->platform_data = pdata->vibra;
+			cell->pdata_size = sizeof(*pdata->vibra);
+		}
 		children++;
 	}
 
-	if (children) {
-		ret = mfd_add_devices(&client->dev, -1, twl6040->cells,
-				      children, NULL, 0);
-		if (ret)
-			goto mfd_err;
-	} else {
-		dev_err(&client->dev, "No platform data found for children\n");
-		ret = -ENODEV;
+	ret = mfd_add_devices(&client->dev, -1, twl6040->cells, children,
+			      NULL, 0);
+	if (ret)
 		goto mfd_err;
-	}
 
 	return 0;
 
@@ -618,12 +659,15 @@ mfd_err:
 	free_irq(twl6040->irq_base + TWL6040_IRQ_READY, twl6040);
 irq_err:
 	twl6040_irq_exit(twl6040);
-gpio2_err:
+irq_init_err:
 	if (gpio_is_valid(twl6040->audpwron))
 		gpio_free(twl6040->audpwron);
-gpio1_err:
+gpio_err:
+	regulator_bulk_disable(TWL6040_NUM_SUPPLIES, twl6040->supplies);
+power_err:
+	regulator_bulk_free(TWL6040_NUM_SUPPLIES, twl6040->supplies);
+regulator_get_err:
 	i2c_set_clientdata(client, NULL);
-	regmap_exit(twl6040->regmap);
 err:
 	return ret;
 }
@@ -643,7 +687,9 @@ static int __devexit twl6040_remove(struct i2c_client *client)
 
 	mfd_remove_devices(&client->dev);
 	i2c_set_clientdata(client, NULL);
-	regmap_exit(twl6040->regmap);
+
+	regulator_bulk_disable(TWL6040_NUM_SUPPLIES, twl6040->supplies);
+	regulator_bulk_free(TWL6040_NUM_SUPPLIES, twl6040->supplies);
 
 	return 0;
 }
diff --git a/drivers/mfd/twl6040-irq.c b/drivers/mfd/twl6040-irq.c
index b3f8ddaa28a8..4b42543da228 100644
--- a/drivers/mfd/twl6040-irq.c
+++ b/drivers/mfd/twl6040-irq.c
@@ -23,7 +23,10 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/err.h>
 #include <linux/irq.h>
+#include <linux/of.h>
+#include <linux/irqdomain.h>
 #include <linux/interrupt.h>
 #include <linux/mfd/core.h>
 #include <linux/mfd/twl6040.h>
@@ -138,7 +141,8 @@ static irqreturn_t twl6040_irq_thread(int irq, void *data)
 
 int twl6040_irq_init(struct twl6040 *twl6040)
 {
-	int cur_irq, ret;
+	struct device_node *node = twl6040->dev->of_node;
+	int i, nr_irqs, irq_base, ret;
 	u8 val;
 
 	mutex_init(&twl6040->irq_mutex);
@@ -148,21 +152,31 @@ int twl6040_irq_init(struct twl6040 *twl6040)
 	twl6040->irq_masks_cache = TWL6040_ALLINT_MSK;
 	twl6040_reg_write(twl6040, TWL6040_REG_INTMR, TWL6040_ALLINT_MSK);
 
+	nr_irqs = ARRAY_SIZE(twl6040_irqs);
+
+	irq_base = irq_alloc_descs(-1, 0, nr_irqs, 0);
+	if (IS_ERR_VALUE(irq_base)) {
+		dev_err(twl6040->dev, "Fail to allocate IRQ descs\n");
+		return irq_base;
+	}
+	twl6040->irq_base = irq_base;
+
+	irq_domain_add_legacy(node, ARRAY_SIZE(twl6040_irqs), irq_base, 0,
+			      &irq_domain_simple_ops, NULL);
+
 	/* Register them with genirq */
-	for (cur_irq = twl6040->irq_base;
-	     cur_irq < twl6040->irq_base + ARRAY_SIZE(twl6040_irqs);
-	     cur_irq++) {
-		irq_set_chip_data(cur_irq, twl6040);
-		irq_set_chip_and_handler(cur_irq, &twl6040_irq_chip,
+	for (i = irq_base; i < irq_base + nr_irqs; i++) {
+		irq_set_chip_data(i, twl6040);
+		irq_set_chip_and_handler(i, &twl6040_irq_chip,
 					 handle_level_irq);
-		irq_set_nested_thread(cur_irq, 1);
+		irq_set_nested_thread(i, 1);
 
 		/* ARM needs us to explicitly flag the IRQ as valid
 		 * and will set them noprobe when we do so. */
 #ifdef CONFIG_ARM
-		set_irq_flags(cur_irq, IRQF_VALID);
+		set_irq_flags(i, IRQF_VALID);
 #else
-		irq_set_noprobe(cur_irq);
+		irq_set_noprobe(i);
 #endif
 	}
 
diff --git a/drivers/mfd/vx855.c b/drivers/mfd/vx855.c
index b73cc15e0081..872aff21e4be 100644
--- a/drivers/mfd/vx855.c
+++ b/drivers/mfd/vx855.c
@@ -131,17 +131,7 @@ static struct pci_driver vx855_pci_driver = {
 	.remove		= __devexit_p(vx855_remove),
 };
 
-static int vx855_init(void)
-{
-	return pci_register_driver(&vx855_pci_driver);
-}
-module_init(vx855_init);
-
-static void vx855_exit(void)
-{
-	pci_unregister_driver(&vx855_pci_driver);
-}
-module_exit(vx855_exit);
+module_pci_driver(vx855_pci_driver);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Harald Welte <HaraldWelte@viatech.com>");
diff --git a/drivers/mfd/wm831x-auxadc.c b/drivers/mfd/wm831x-auxadc.c
index 87210954a066..6ee3018d8653 100644
--- a/drivers/mfd/wm831x-auxadc.c
+++ b/drivers/mfd/wm831x-auxadc.c
@@ -280,11 +280,11 @@ void wm831x_auxadc_init(struct wm831x *wm831x)
 	mutex_init(&wm831x->auxadc_lock);
 	INIT_LIST_HEAD(&wm831x->auxadc_pending);
 
-	if (wm831x->irq && wm831x->irq_base) {
+	if (wm831x->irq) {
 		wm831x->auxadc_read = wm831x_auxadc_read_irq;
 
-		ret = request_threaded_irq(wm831x->irq_base +
-					   WM831X_IRQ_AUXADC_DATA,
+		ret = request_threaded_irq(wm831x_irq(wm831x,
+						      WM831X_IRQ_AUXADC_DATA),
 					   NULL, wm831x_auxadc_irq, 0,
 					   "auxadc", wm831x);
 		if (ret < 0) {
diff --git a/drivers/mfd/wm831x-core.c b/drivers/mfd/wm831x-core.c
index 838056c3493a..946698fd2dc6 100644
--- a/drivers/mfd/wm831x-core.c
+++ b/drivers/mfd/wm831x-core.c
@@ -614,8 +614,15 @@ int wm831x_set_bits(struct wm831x *wm831x, unsigned short reg,
 }
 EXPORT_SYMBOL_GPL(wm831x_set_bits);
 
+static struct resource wm831x_io_parent = {
+	.start = 0,
+	.end   = 0xffffffff,
+	.flags = IORESOURCE_IO,
+};
+
 static struct resource wm831x_dcdc1_resources[] = {
 	{
+		.parent = &wm831x_io_parent,
 		.start = WM831X_DC1_CONTROL_1,
 		.end   = WM831X_DC1_DVS_CONTROL,
 		.flags = IORESOURCE_IO,
@@ -637,6 +644,7 @@ static struct resource wm831x_dcdc1_resources[] = {
 
 static struct resource wm831x_dcdc2_resources[] = {
 	{
+		.parent = &wm831x_io_parent,
 		.start = WM831X_DC2_CONTROL_1,
 		.end   = WM831X_DC2_DVS_CONTROL,
 		.flags = IORESOURCE_IO,
@@ -657,6 +665,7 @@ static struct resource wm831x_dcdc2_resources[] = {
 
 static struct resource wm831x_dcdc3_resources[] = {
 	{
+		.parent = &wm831x_io_parent,
 		.start = WM831X_DC3_CONTROL_1,
 		.end   = WM831X_DC3_SLEEP_CONTROL,
 		.flags = IORESOURCE_IO,
@@ -671,6 +680,7 @@ static struct resource wm831x_dcdc3_resources[] = {
 
 static struct resource wm831x_dcdc4_resources[] = {
 	{
+		.parent = &wm831x_io_parent,
 		.start = WM831X_DC4_CONTROL,
 		.end   = WM831X_DC4_SLEEP_CONTROL,
 		.flags = IORESOURCE_IO,
@@ -685,6 +695,7 @@ static struct resource wm831x_dcdc4_resources[] = {
 
 static struct resource wm8320_dcdc4_buck_resources[] = {
 	{
+		.parent = &wm831x_io_parent,
 		.start = WM831X_DC4_CONTROL,
 		.end   = WM832X_DC4_SLEEP_CONTROL,
 		.flags = IORESOURCE_IO,
@@ -707,6 +718,7 @@ static struct resource wm831x_gpio_resources[] = {
 
 static struct resource wm831x_isink1_resources[] = {
 	{
+		.parent = &wm831x_io_parent,
 		.start = WM831X_CURRENT_SINK_1,
 		.end   = WM831X_CURRENT_SINK_1,
 		.flags = IORESOURCE_IO,
@@ -720,6 +732,7 @@ static struct resource wm831x_isink1_resources[] = {
 
 static struct resource wm831x_isink2_resources[] = {
 	{
+		.parent = &wm831x_io_parent,
 		.start = WM831X_CURRENT_SINK_2,
 		.end   = WM831X_CURRENT_SINK_2,
 		.flags = IORESOURCE_IO,
@@ -733,6 +746,7 @@ static struct resource wm831x_isink2_resources[] = {
 
 static struct resource wm831x_ldo1_resources[] = {
 	{
+		.parent = &wm831x_io_parent,
 		.start = WM831X_LDO1_CONTROL,
 		.end   = WM831X_LDO1_SLEEP_CONTROL,
 		.flags = IORESOURCE_IO,
@@ -747,6 +761,7 @@ static struct resource wm831x_ldo1_resources[] = {
 
 static struct resource wm831x_ldo2_resources[] = {
 	{
+		.parent = &wm831x_io_parent,
 		.start = WM831X_LDO2_CONTROL,
 		.end   = WM831X_LDO2_SLEEP_CONTROL,
 		.flags = IORESOURCE_IO,
@@ -761,6 +776,7 @@ static struct resource wm831x_ldo2_resources[] = {
 
 static struct resource wm831x_ldo3_resources[] = {
 	{
+		.parent = &wm831x_io_parent,
 		.start = WM831X_LDO3_CONTROL,
 		.end   = WM831X_LDO3_SLEEP_CONTROL,
 		.flags = IORESOURCE_IO,
@@ -775,6 +791,7 @@ static struct resource wm831x_ldo3_resources[] = {
 
 static struct resource wm831x_ldo4_resources[] = {
 	{
+		.parent = &wm831x_io_parent,
 		.start = WM831X_LDO4_CONTROL,
 		.end   = WM831X_LDO4_SLEEP_CONTROL,
 		.flags = IORESOURCE_IO,
@@ -789,6 +806,7 @@ static struct resource wm831x_ldo4_resources[] = {
 
 static struct resource wm831x_ldo5_resources[] = {
 	{
+		.parent = &wm831x_io_parent,
 		.start = WM831X_LDO5_CONTROL,
 		.end   = WM831X_LDO5_SLEEP_CONTROL,
 		.flags = IORESOURCE_IO,
@@ -803,6 +821,7 @@ static struct resource wm831x_ldo5_resources[] = {
 
 static struct resource wm831x_ldo6_resources[] = {
 	{
+		.parent = &wm831x_io_parent,
 		.start = WM831X_LDO6_CONTROL,
 		.end   = WM831X_LDO6_SLEEP_CONTROL,
 		.flags = IORESOURCE_IO,
@@ -817,6 +836,7 @@ static struct resource wm831x_ldo6_resources[] = {
 
 static struct resource wm831x_ldo7_resources[] = {
 	{
+		.parent = &wm831x_io_parent,
 		.start = WM831X_LDO7_CONTROL,
 		.end   = WM831X_LDO7_SLEEP_CONTROL,
 		.flags = IORESOURCE_IO,
@@ -831,6 +851,7 @@ static struct resource wm831x_ldo7_resources[] = {
 
 static struct resource wm831x_ldo8_resources[] = {
 	{
+		.parent = &wm831x_io_parent,
 		.start = WM831X_LDO8_CONTROL,
 		.end   = WM831X_LDO8_SLEEP_CONTROL,
 		.flags = IORESOURCE_IO,
@@ -845,6 +866,7 @@ static struct resource wm831x_ldo8_resources[] = {
 
 static struct resource wm831x_ldo9_resources[] = {
 	{
+		.parent = &wm831x_io_parent,
 		.start = WM831X_LDO9_CONTROL,
 		.end   = WM831X_LDO9_SLEEP_CONTROL,
 		.flags = IORESOURCE_IO,
@@ -859,6 +881,7 @@ static struct resource wm831x_ldo9_resources[] = {
 
 static struct resource wm831x_ldo10_resources[] = {
 	{
+		.parent = &wm831x_io_parent,
 		.start = WM831X_LDO10_CONTROL,
 		.end   = WM831X_LDO10_SLEEP_CONTROL,
 		.flags = IORESOURCE_IO,
@@ -873,6 +896,7 @@ static struct resource wm831x_ldo10_resources[] = {
 
 static struct resource wm831x_ldo11_resources[] = {
 	{
+		.parent = &wm831x_io_parent,
 		.start = WM831X_LDO11_ON_CONTROL,
 		.end   = WM831X_LDO11_SLEEP_CONTROL,
 		.flags = IORESOURCE_IO,
@@ -974,6 +998,7 @@ static struct resource wm831x_rtc_resources[] = {
 
 static struct resource wm831x_status1_resources[] = {
 	{
+		.parent = &wm831x_io_parent,
 		.start = WM831X_STATUS_LED_1,
 		.end   = WM831X_STATUS_LED_1,
 		.flags = IORESOURCE_IO,
@@ -982,6 +1007,7 @@ static struct resource wm831x_status1_resources[] = {
 
 static struct resource wm831x_status2_resources[] = {
 	{
+		.parent = &wm831x_io_parent,
 		.start = WM831X_STATUS_LED_2,
 		.end   = WM831X_STATUS_LED_2,
 		.flags = IORESOURCE_IO,
@@ -1787,27 +1813,27 @@ int wm831x_device_init(struct wm831x *wm831x, unsigned long id, int irq)
 	case WM8310:
 		ret = mfd_add_devices(wm831x->dev, wm831x_num,
 				      wm8310_devs, ARRAY_SIZE(wm8310_devs),
-				      NULL, wm831x->irq_base);
+				      NULL, 0);
 		break;
 
 	case WM8311:
 		ret = mfd_add_devices(wm831x->dev, wm831x_num,
 				      wm8311_devs, ARRAY_SIZE(wm8311_devs),
-				      NULL, wm831x->irq_base);
+				      NULL, 0);
 		if (!pdata || !pdata->disable_touch)
 			mfd_add_devices(wm831x->dev, wm831x_num,
 					touch_devs, ARRAY_SIZE(touch_devs),
-					NULL, wm831x->irq_base);
+					NULL, 0);
 		break;
 
 	case WM8312:
 		ret = mfd_add_devices(wm831x->dev, wm831x_num,
 				      wm8312_devs, ARRAY_SIZE(wm8312_devs),
-				      NULL, wm831x->irq_base);
+				      NULL, 0);
 		if (!pdata || !pdata->disable_touch)
 			mfd_add_devices(wm831x->dev, wm831x_num,
 					touch_devs, ARRAY_SIZE(touch_devs),
-					NULL, wm831x->irq_base);
+					NULL, 0);
 		break;
 
 	case WM8320:
@@ -1816,7 +1842,7 @@ int wm831x_device_init(struct wm831x *wm831x, unsigned long id, int irq)
 	case WM8326:
 		ret = mfd_add_devices(wm831x->dev, wm831x_num,
 				      wm8320_devs, ARRAY_SIZE(wm8320_devs),
-				      NULL, wm831x->irq_base);
+				      NULL, 0);
 		break;
 
 	default:
@@ -1841,7 +1867,7 @@ int wm831x_device_init(struct wm831x *wm831x, unsigned long id, int irq)
 	if (ret & WM831X_XTAL_ENA) {
 		ret = mfd_add_devices(wm831x->dev, wm831x_num,
 				      rtc_devs, ARRAY_SIZE(rtc_devs),
-				      NULL, wm831x->irq_base);
+				      NULL, 0);
 		if (ret != 0) {
 			dev_err(wm831x->dev, "Failed to add RTC: %d\n", ret);
 			goto err_irq;
@@ -1854,7 +1880,7 @@ int wm831x_device_init(struct wm831x *wm831x, unsigned long id, int irq)
 		/* Treat errors as non-critical */
 		ret = mfd_add_devices(wm831x->dev, wm831x_num, backlight_devs,
 				      ARRAY_SIZE(backlight_devs), NULL,
-				      wm831x->irq_base);
+				      0);
 		if (ret < 0)
 			dev_err(wm831x->dev, "Failed to add backlight: %d\n",
 				ret);
@@ -1883,8 +1909,7 @@ void wm831x_device_exit(struct wm831x *wm831x)
 {
 	wm831x_otp_exit(wm831x);
 	mfd_remove_devices(wm831x->dev);
-	if (wm831x->irq_base)
-		free_irq(wm831x->irq_base + WM831X_IRQ_AUXADC_DATA, wm831x);
+	free_irq(wm831x_irq(wm831x, WM831X_IRQ_AUXADC_DATA), wm831x);
 	wm831x_irq_exit(wm831x);
 }
 
diff --git a/drivers/mfd/wm831x-irq.c b/drivers/mfd/wm831x-irq.c
index bec4d0539160..804e56ec99eb 100644
--- a/drivers/mfd/wm831x-irq.c
+++ b/drivers/mfd/wm831x-irq.c
@@ -18,6 +18,7 @@
 #include <linux/irq.h>
 #include <linux/mfd/core.h>
 #include <linux/interrupt.h>
+#include <linux/irqdomain.h>
 
 #include <linux/mfd/wm831x/core.h>
 #include <linux/mfd/wm831x/pdata.h>
@@ -328,7 +329,7 @@ static inline int irq_data_to_status_reg(struct wm831x_irq_data *irq_data)
 static inline struct wm831x_irq_data *irq_to_wm831x_irq(struct wm831x *wm831x,
 							int irq)
 {
-	return &wm831x_irqs[irq - wm831x->irq_base];
+	return &wm831x_irqs[irq];
 }
 
 static void wm831x_irq_lock(struct irq_data *data)
@@ -374,7 +375,7 @@ static void wm831x_irq_enable(struct irq_data *data)
 {
 	struct wm831x *wm831x = irq_data_get_irq_chip_data(data);
 	struct wm831x_irq_data *irq_data = irq_to_wm831x_irq(wm831x,
-							     data->irq);
+							     data->hwirq);
 
 	wm831x->irq_masks_cur[irq_data->reg - 1] &= ~irq_data->mask;
 }
@@ -383,7 +384,7 @@ static void wm831x_irq_disable(struct irq_data *data)
 {
 	struct wm831x *wm831x = irq_data_get_irq_chip_data(data);
 	struct wm831x_irq_data *irq_data = irq_to_wm831x_irq(wm831x,
-							     data->irq);
+							     data->hwirq);
 
 	wm831x->irq_masks_cur[irq_data->reg - 1] |= irq_data->mask;
 }
@@ -393,7 +394,7 @@ static int wm831x_irq_set_type(struct irq_data *data, unsigned int type)
 	struct wm831x *wm831x = irq_data_get_irq_chip_data(data);
 	int irq;
 
-	irq = data->irq - wm831x->irq_base;
+	irq = data->hwirq;
 
 	if (irq < WM831X_IRQ_GPIO_1 || irq > WM831X_IRQ_GPIO_11) {
 		/* Ignore internal-only IRQs */
@@ -412,22 +413,25 @@ static int wm831x_irq_set_type(struct irq_data *data, unsigned int type)
 	 * do the update here as we can be called with the bus lock
 	 * held.
 	 */
+	wm831x->gpio_level_low[irq] = false;
+	wm831x->gpio_level_high[irq] = false;
 	switch (type) {
 	case IRQ_TYPE_EDGE_BOTH:
 		wm831x->gpio_update[irq] = 0x10000 | WM831X_GPN_INT_MODE;
-		wm831x->gpio_level[irq] = false;
 		break;
 	case IRQ_TYPE_EDGE_RISING:
 		wm831x->gpio_update[irq] = 0x10000 | WM831X_GPN_POL;
-		wm831x->gpio_level[irq] = false;
 		break;
 	case IRQ_TYPE_EDGE_FALLING:
 		wm831x->gpio_update[irq] = 0x10000;
-		wm831x->gpio_level[irq] = false;
 		break;
 	case IRQ_TYPE_LEVEL_HIGH:
 		wm831x->gpio_update[irq] = 0x10000 | WM831X_GPN_POL;
-		wm831x->gpio_level[irq] = true;
+		wm831x->gpio_level_high[irq] = true;
+		break;
+	case IRQ_TYPE_LEVEL_LOW:
+		wm831x->gpio_update[irq] = 0x10000;
+		wm831x->gpio_level_low[irq] = true;
 		break;
 	default:
 		return -EINVAL;
@@ -469,9 +473,11 @@ static irqreturn_t wm831x_irq_thread(int irq, void *data)
 	 * descriptors.
 	 */
 	if (primary & WM831X_TCHPD_INT)
-		handle_nested_irq(wm831x->irq_base + WM831X_IRQ_TCHPD);
+		handle_nested_irq(irq_find_mapping(wm831x->irq_domain,
+						   WM831X_IRQ_TCHPD));
 	if (primary & WM831X_TCHDATA_INT)
-		handle_nested_irq(wm831x->irq_base + WM831X_IRQ_TCHDATA);
+		handle_nested_irq(irq_find_mapping(wm831x->irq_domain,
+						   WM831X_IRQ_TCHDATA));
 	primary &= ~(WM831X_TCHDATA_EINT | WM831X_TCHPD_EINT);
 
 	for (i = 0; i < ARRAY_SIZE(wm831x_irqs); i++) {
@@ -507,16 +513,29 @@ static irqreturn_t wm831x_irq_thread(int irq, void *data)
 		}
 
 		if (*status & wm831x_irqs[i].mask)
-			handle_nested_irq(wm831x->irq_base + i);
+			handle_nested_irq(irq_find_mapping(wm831x->irq_domain,
+							   i));
 
 		/* Simulate an edge triggered IRQ by polling the input
 		 * status.  This is sucky but improves interoperability.
 		 */
 		if (primary == WM831X_GP_INT &&
-		    wm831x->gpio_level[i - WM831X_IRQ_GPIO_1]) {
+		    wm831x->gpio_level_high[i - WM831X_IRQ_GPIO_1]) {
 			ret = wm831x_reg_read(wm831x, WM831X_GPIO_LEVEL);
 			while (ret & 1 << (i - WM831X_IRQ_GPIO_1)) {
-				handle_nested_irq(wm831x->irq_base + i);
+				handle_nested_irq(irq_find_mapping(wm831x->irq_domain,
+								   i));
+				ret = wm831x_reg_read(wm831x,
+						      WM831X_GPIO_LEVEL);
+			}
+		}
+
+		if (primary == WM831X_GP_INT &&
+		    wm831x->gpio_level_low[i - WM831X_IRQ_GPIO_1]) {
+			ret = wm831x_reg_read(wm831x, WM831X_GPIO_LEVEL);
+			while (!(ret & 1 << (i - WM831X_IRQ_GPIO_1))) {
+				handle_nested_irq(irq_find_mapping(wm831x->irq_domain,
+								   i));
 				ret = wm831x_reg_read(wm831x,
 						      WM831X_GPIO_LEVEL);
 			}
@@ -527,10 +546,34 @@ out:
 	return IRQ_HANDLED;
 }
 
+static int wm831x_irq_map(struct irq_domain *h, unsigned int virq,
+			  irq_hw_number_t hw)
+{
+	irq_set_chip_data(virq, h->host_data);
+	irq_set_chip_and_handler(virq, &wm831x_irq_chip, handle_edge_irq);
+	irq_set_nested_thread(virq, 1);
+
+	/* ARM needs us to explicitly flag the IRQ as valid
+	 * and will set them noprobe when we do so. */
+#ifdef CONFIG_ARM
+	set_irq_flags(virq, IRQF_VALID);
+#else
+	irq_set_noprobe(virq);
+#endif
+
+	return 0;
+}
+
+static struct irq_domain_ops wm831x_irq_domain_ops = {
+	.map	= wm831x_irq_map,
+	.xlate	= irq_domain_xlate_twocell,
+};
+
 int wm831x_irq_init(struct wm831x *wm831x, int irq)
 {
 	struct wm831x_pdata *pdata = wm831x->dev->platform_data;
-	int i, cur_irq, ret;
+	struct irq_domain *domain;
+	int i, ret, irq_base;
 
 	mutex_init(&wm831x->irq_lock);
 
@@ -543,18 +586,33 @@ int wm831x_irq_init(struct wm831x *wm831x, int irq)
 	}
 
 	/* Try to dynamically allocate IRQs if no base is specified */
-	if (!pdata || !pdata->irq_base)
-		wm831x->irq_base = -1;
+	if (pdata && pdata->irq_base) {
+		irq_base = irq_alloc_descs(pdata->irq_base, 0,
+					   WM831X_NUM_IRQS, 0);
+		if (irq_base < 0) {
+			dev_warn(wm831x->dev, "Failed to allocate IRQs: %d\n",
+				 irq_base);
+			irq_base = 0;
+		}
+	} else {
+		irq_base = 0;
+	}
+
+	if (irq_base)
+		domain = irq_domain_add_legacy(wm831x->dev->of_node,
+					       ARRAY_SIZE(wm831x_irqs),
+					       irq_base, 0,
+					       &wm831x_irq_domain_ops,
+					       wm831x);
 	else
-		wm831x->irq_base = pdata->irq_base;
+		domain = irq_domain_add_linear(wm831x->dev->of_node,
+					       ARRAY_SIZE(wm831x_irqs),
+					       &wm831x_irq_domain_ops,
+					       wm831x);
 
-	wm831x->irq_base = irq_alloc_descs(wm831x->irq_base, 0,
-					   WM831X_NUM_IRQS, 0);
-	if (wm831x->irq_base < 0) {
-		dev_warn(wm831x->dev, "Failed to allocate IRQs: %d\n",
-			 wm831x->irq_base);
-		wm831x->irq_base = 0;
-		return 0;
+	if (!domain) {
+		dev_warn(wm831x->dev, "Failed to allocate IRQ domain\n");
+		return -EINVAL;
 	}
 
 	if (pdata && pdata->irq_cmos)
@@ -565,38 +623,22 @@ int wm831x_irq_init(struct wm831x *wm831x, int irq)
 	wm831x_set_bits(wm831x, WM831X_IRQ_CONFIG,
 			WM831X_IRQ_OD, i);
 
-	/* Try to flag /IRQ as a wake source; there are a number of
-	 * unconditional wake sources in the PMIC so this isn't
-	 * conditional but we don't actually care *too* much if it
-	 * fails.
-	 */
-	ret = enable_irq_wake(irq);
-	if (ret != 0) {
-		dev_warn(wm831x->dev, "Can't enable IRQ as wake source: %d\n",
-			 ret);
-	}
-
 	wm831x->irq = irq;
-
-	/* Register them with genirq */
-	for (cur_irq = wm831x->irq_base;
-	     cur_irq < ARRAY_SIZE(wm831x_irqs) + wm831x->irq_base;
-	     cur_irq++) {
-		irq_set_chip_data(cur_irq, wm831x);
-		irq_set_chip_and_handler(cur_irq, &wm831x_irq_chip,
-					 handle_edge_irq);
-		irq_set_nested_thread(cur_irq, 1);
-
-		/* ARM needs us to explicitly flag the IRQ as valid
-		 * and will set them noprobe when we do so. */
-#ifdef CONFIG_ARM
-		set_irq_flags(cur_irq, IRQF_VALID);
-#else
-		irq_set_noprobe(cur_irq);
-#endif
-	}
+	wm831x->irq_domain = domain;
 
 	if (irq) {
+		/* Try to flag /IRQ as a wake source; there are a number of
+		 * unconditional wake sources in the PMIC so this isn't
+		 * conditional but we don't actually care *too* much if it
+		 * fails.
+		 */
+		ret = enable_irq_wake(irq);
+		if (ret != 0) {
+			dev_warn(wm831x->dev,
+				 "Can't enable IRQ as wake source: %d\n",
+				 ret);
+		}
+
 		ret = request_threaded_irq(irq, NULL, wm831x_irq_thread,
 					   IRQF_TRIGGER_LOW | IRQF_ONESHOT,
 					   "wm831x", wm831x);
diff --git a/drivers/mfd/wm8350-core.c b/drivers/mfd/wm8350-core.c
index dd1caaac55e4..8a9b11ca076a 100644
--- a/drivers/mfd/wm8350-core.c
+++ b/drivers/mfd/wm8350-core.c
@@ -20,6 +20,7 @@
 #include <linux/device.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
+#include <linux/regmap.h>
 #include <linux/workqueue.h>
 
 #include <linux/mfd/wm8350/core.h>
@@ -74,7 +75,7 @@ static int wm8350_phys_read(struct wm8350 *wm8350, u8 reg, int num_regs,
 	int bytes = num_regs * 2;
 
 	dev_dbg(wm8350->dev, "volatile read\n");
-	ret = wm8350->read_dev(wm8350, reg, bytes, (char *)dest);
+	ret = regmap_raw_read(wm8350->regmap, reg, dest, bytes);
 
 	for (i = reg; i < reg + num_regs; i++) {
 		/* Cache is CPU endian */
@@ -96,9 +97,6 @@ static int wm8350_read(struct wm8350 *wm8350, u8 reg, int num_regs, u16 *dest)
 	int ret = 0;
 	int bytes = num_regs * 2;
 
-	if (wm8350->read_dev == NULL)
-		return -ENODEV;
-
 	if ((reg + num_regs - 1) > WM8350_MAX_REGISTER) {
 		dev_err(wm8350->dev, "invalid reg %x\n",
 			reg + num_regs - 1);
@@ -149,9 +147,6 @@ static int wm8350_write(struct wm8350 *wm8350, u8 reg, int num_regs, u16 *src)
 	int end = reg + num_regs;
 	int bytes = num_regs * 2;
 
-	if (wm8350->write_dev == NULL)
-		return -ENODEV;
-
 	if ((reg + num_regs - 1) > WM8350_MAX_REGISTER) {
 		dev_err(wm8350->dev, "invalid reg %x\n",
 			reg + num_regs - 1);
@@ -182,7 +177,7 @@ static int wm8350_write(struct wm8350 *wm8350, u8 reg, int num_regs, u16 *src)
 	}
 
 	/* Actually write it out */
-	return wm8350->write_dev(wm8350, reg, bytes, (char *)src);
+	return regmap_raw_write(wm8350->regmap, reg, src, bytes);
 }
 
 /*
@@ -515,9 +510,8 @@ static int wm8350_create_cache(struct wm8350 *wm8350, int type, int mode)
 	 * a PMIC so the device many not be in a virgin state and we
 	 * can't rely on the silicon values.
 	 */
-	ret = wm8350->read_dev(wm8350, 0,
-			       sizeof(u16) * (WM8350_MAX_REGISTER + 1),
-			       wm8350->reg_cache);
+	ret = regmap_raw_read(wm8350->regmap, 0, wm8350->reg_cache,
+			      sizeof(u16) * (WM8350_MAX_REGISTER + 1));
 	if (ret < 0) {
 		dev_err(wm8350->dev,
 			"failed to read initial cache values\n");
@@ -570,35 +564,30 @@ int wm8350_device_init(struct wm8350 *wm8350, int irq,
 		       struct wm8350_platform_data *pdata)
 {
 	int ret;
-	u16 id1, id2, mask_rev;
-	u16 cust_id, mode, chip_rev;
+	unsigned int id1, id2, mask_rev;
+	unsigned int cust_id, mode, chip_rev;
 
 	dev_set_drvdata(wm8350->dev, wm8350);
 
 	/* get WM8350 revision and config mode */
-	ret = wm8350->read_dev(wm8350, WM8350_RESET_ID, sizeof(id1), &id1);
+	ret = regmap_read(wm8350->regmap, WM8350_RESET_ID, &id1);
 	if (ret != 0) {
 		dev_err(wm8350->dev, "Failed to read ID: %d\n", ret);
 		goto err;
 	}
 
-	ret = wm8350->read_dev(wm8350, WM8350_ID, sizeof(id2), &id2);
+	ret = regmap_read(wm8350->regmap, WM8350_ID, &id2);
 	if (ret != 0) {
 		dev_err(wm8350->dev, "Failed to read ID: %d\n", ret);
 		goto err;
 	}
 
-	ret = wm8350->read_dev(wm8350, WM8350_REVISION, sizeof(mask_rev),
-			       &mask_rev);
+	ret = regmap_read(wm8350->regmap, WM8350_REVISION, &mask_rev);
 	if (ret != 0) {
 		dev_err(wm8350->dev, "Failed to read revision: %d\n", ret);
 		goto err;
 	}
 
-	id1 = be16_to_cpu(id1);
-	id2 = be16_to_cpu(id2);
-	mask_rev = be16_to_cpu(mask_rev);
-
 	if (id1 != 0x6143) {
 		dev_err(wm8350->dev,
 			"Device with ID %x is not a WM8350\n", id1);
diff --git a/drivers/mfd/wm8350-i2c.c b/drivers/mfd/wm8350-i2c.c
index d955faaf27c4..a68aceb4e48c 100644
--- a/drivers/mfd/wm8350-i2c.c
+++ b/drivers/mfd/wm8350-i2c.c
@@ -15,47 +15,18 @@
 
 #include <linux/module.h>
 #include <linux/moduleparam.h>
+#include <linux/err.h>
 #include <linux/init.h>
 #include <linux/i2c.h>
 #include <linux/platform_device.h>
 #include <linux/mfd/wm8350/core.h>
+#include <linux/regmap.h>
 #include <linux/slab.h>
 
-static int wm8350_i2c_read_device(struct wm8350 *wm8350, char reg,
-				  int bytes, void *dest)
-{
-	int ret;
-
-	ret = i2c_master_send(wm8350->i2c_client, &reg, 1);
-	if (ret < 0)
-		return ret;
-	ret = i2c_master_recv(wm8350->i2c_client, dest, bytes);
-	if (ret < 0)
-		return ret;
-	if (ret != bytes)
-		return -EIO;
-	return 0;
-}
-
-static int wm8350_i2c_write_device(struct wm8350 *wm8350, char reg,
-				   int bytes, void *src)
-{
-	/* we add 1 byte for device register */
-	u8 msg[(WM8350_MAX_REGISTER << 1) + 1];
-	int ret;
-
-	if (bytes > ((WM8350_MAX_REGISTER << 1) + 1))
-		return -EINVAL;
-
-	msg[0] = reg;
-	memcpy(&msg[1], src, bytes);
-	ret = i2c_master_send(wm8350->i2c_client, msg, bytes + 1);
-	if (ret < 0)
-		return ret;
-	if (ret != bytes + 1)
-		return -EIO;
-	return 0;
-}
+static const struct regmap_config wm8350_regmap = {
+	.reg_bits = 8,
+	.val_bits = 16,
+};
 
 static int wm8350_i2c_probe(struct i2c_client *i2c,
 			    const struct i2c_device_id *id)
@@ -67,20 +38,18 @@ static int wm8350_i2c_probe(struct i2c_client *i2c,
 	if (wm8350 == NULL)
 		return -ENOMEM;
 
+	wm8350->regmap = devm_regmap_init_i2c(i2c, &wm8350_regmap);
+	if (IS_ERR(wm8350->regmap)) {
+		ret = PTR_ERR(wm8350->regmap);
+		dev_err(&i2c->dev, "Failed to allocate register map: %d\n",
+			ret);
+		return ret;
+	}
+
 	i2c_set_clientdata(i2c, wm8350);
 	wm8350->dev = &i2c->dev;
-	wm8350->i2c_client = i2c;
-	wm8350->read_dev = wm8350_i2c_read_device;
-	wm8350->write_dev = wm8350_i2c_write_device;
-
-	ret = wm8350_device_init(wm8350, i2c->irq, i2c->dev.platform_data);
-	if (ret < 0)
-		goto err;
-
-	return ret;
 
-err:
-	return ret;
+	return wm8350_device_init(wm8350, i2c->irq, i2c->dev.platform_data);
 }
 
 static int wm8350_i2c_remove(struct i2c_client *i2c)
diff --git a/drivers/mfd/wm8400-core.c b/drivers/mfd/wm8400-core.c
index 1189a17f0f25..4b7d378551d5 100644
--- a/drivers/mfd/wm8400-core.c
+++ b/drivers/mfd/wm8400-core.c
@@ -23,136 +23,16 @@
 #include <linux/regmap.h>
 #include <linux/slab.h>
 
-static struct {
-	u16  readable;    /* Mask of readable bits */
-	u16  writable;    /* Mask of writable bits */
-	u16  vol;         /* Mask of volatile bits */
-	int  is_codec;    /* Register controlled by codec reset */
-	u16  default_val; /* Value on reset */
-} reg_data[] = {
-	{ 0xFFFF, 0xFFFF, 0x0000, 0, 0x6172 }, /* R0 */
-	{ 0x7000, 0x0000, 0x8000, 0, 0x0000 }, /* R1 */
-	{ 0xFF17, 0xFF17, 0x0000, 0, 0x0000 }, /* R2 */
-	{ 0xEBF3, 0xEBF3, 0x0000, 1, 0x6000 }, /* R3 */
-	{ 0x3CF3, 0x3CF3, 0x0000, 1, 0x0000 }, /* R4  */
-	{ 0xF1F8, 0xF1F8, 0x0000, 1, 0x4050 }, /* R5  */
-	{ 0xFC1F, 0xFC1F, 0x0000, 1, 0x4000 }, /* R6  */
-	{ 0xDFDE, 0xDFDE, 0x0000, 1, 0x01C8 }, /* R7  */
-	{ 0xFCFC, 0xFCFC, 0x0000, 1, 0x0000 }, /* R8  */
-	{ 0xEFFF, 0xEFFF, 0x0000, 1, 0x0040 }, /* R9  */
-	{ 0xEFFF, 0xEFFF, 0x0000, 1, 0x0040 }, /* R10 */
-	{ 0x27F7, 0x27F7, 0x0000, 1, 0x0004 }, /* R11 */
-	{ 0x01FF, 0x01FF, 0x0000, 1, 0x00C0 }, /* R12 */
-	{ 0x01FF, 0x01FF, 0x0000, 1, 0x00C0 }, /* R13 */
-	{ 0x1FEF, 0x1FEF, 0x0000, 1, 0x0000 }, /* R14 */
-	{ 0x0163, 0x0163, 0x0000, 1, 0x0100 }, /* R15 */
-	{ 0x01FF, 0x01FF, 0x0000, 1, 0x00C0 }, /* R16 */
-	{ 0x01FF, 0x01FF, 0x0000, 1, 0x00C0 }, /* R17 */
-	{ 0x1FFF, 0x0FFF, 0x0000, 1, 0x0000 }, /* R18 */
-	{ 0xFFFF, 0xFFFF, 0x0000, 1, 0x1000 }, /* R19 */
-	{ 0xFFFF, 0xFFFF, 0x0000, 1, 0x1010 }, /* R20 */
-	{ 0xFFFF, 0xFFFF, 0x0000, 1, 0x1010 }, /* R21 */
-	{ 0x0FDD, 0x0FDD, 0x0000, 1, 0x8000 }, /* R22 */
-	{ 0x1FFF, 0x1FFF, 0x0000, 1, 0x0800 }, /* R23 */
-	{ 0x0000, 0x01DF, 0x0000, 1, 0x008B }, /* R24 */
-	{ 0x0000, 0x01DF, 0x0000, 1, 0x008B }, /* R25 */
-	{ 0x0000, 0x01DF, 0x0000, 1, 0x008B }, /* R26 */
-	{ 0x0000, 0x01DF, 0x0000, 1, 0x008B }, /* R27 */
-	{ 0x0000, 0x01FF, 0x0000, 1, 0x0000 }, /* R28 */
-	{ 0x0000, 0x01FF, 0x0000, 1, 0x0000 }, /* R29 */
-	{ 0x0000, 0x0077, 0x0000, 1, 0x0066 }, /* R30 */
-	{ 0x0000, 0x0033, 0x0000, 1, 0x0022 }, /* R31 */
-	{ 0x0000, 0x01FF, 0x0000, 1, 0x0079 }, /* R32 */
-	{ 0x0000, 0x01FF, 0x0000, 1, 0x0079 }, /* R33 */
-	{ 0x0000, 0x0003, 0x0000, 1, 0x0003 }, /* R34 */
-	{ 0x0000, 0x01FF, 0x0000, 1, 0x0003 }, /* R35 */
-	{ 0x0000, 0x0000, 0x0000, 0, 0x0000 }, /* R36 */
-	{ 0x0000, 0x003F, 0x0000, 1, 0x0100 }, /* R37 */
-	{ 0x0000, 0x0000, 0x0000, 0, 0x0000 }, /* R38 */
-	{ 0x0000, 0x000F, 0x0000, 0, 0x0000 }, /* R39 */
-	{ 0x0000, 0x00FF, 0x0000, 1, 0x0000 }, /* R40 */
-	{ 0x0000, 0x01B7, 0x0000, 1, 0x0000 }, /* R41 */
-	{ 0x0000, 0x01B7, 0x0000, 1, 0x0000 }, /* R42 */
-	{ 0x0000, 0x01FF, 0x0000, 1, 0x0000 }, /* R43 */
-	{ 0x0000, 0x01FF, 0x0000, 1, 0x0000 }, /* R44 */
-	{ 0x0000, 0x00FD, 0x0000, 1, 0x0000 }, /* R45 */
-	{ 0x0000, 0x00FD, 0x0000, 1, 0x0000 }, /* R46 */
-	{ 0x0000, 0x01FF, 0x0000, 1, 0x0000 }, /* R47 */
-	{ 0x0000, 0x01FF, 0x0000, 1, 0x0000 }, /* R48 */
-	{ 0x0000, 0x01FF, 0x0000, 1, 0x0000 }, /* R49 */
-	{ 0x0000, 0x01FF, 0x0000, 1, 0x0000 }, /* R50 */
-	{ 0x0000, 0x01B3, 0x0000, 1, 0x0180 }, /* R51 */
-	{ 0x0000, 0x0077, 0x0000, 1, 0x0000 }, /* R52 */
-	{ 0x0000, 0x0077, 0x0000, 1, 0x0000 }, /* R53 */
-	{ 0x0000, 0x00FF, 0x0000, 1, 0x0000 }, /* R54 */
-	{ 0x0000, 0x0001, 0x0000, 1, 0x0000 }, /* R55 */
-	{ 0x0000, 0x003F, 0x0000, 1, 0x0000 }, /* R56 */
-	{ 0x0000, 0x004F, 0x0000, 1, 0x0000 }, /* R57 */
-	{ 0x0000, 0x00FD, 0x0000, 1, 0x0000 }, /* R58 */
-	{ 0x0000, 0x0000, 0x0000, 0, 0x0000 }, /* R59 */
-	{ 0x1FFF, 0x1FFF, 0x0000, 1, 0x0000 }, /* R60 */
-	{ 0xFFFF, 0xFFFF, 0x0000, 1, 0x0000 }, /* R61 */
-	{ 0x03FF, 0x03FF, 0x0000, 1, 0x0000 }, /* R62 */
-	{ 0x007F, 0x007F, 0x0000, 1, 0x0000 }, /* R63 */
-	{ 0x0000, 0x0000, 0x0000, 0, 0x0000 }, /* R64 */
-	{ 0xDFFF, 0xDFFF, 0x0000, 0, 0x0000 }, /* R65 */
-	{ 0xDFFF, 0xDFFF, 0x0000, 0, 0x0000 }, /* R66 */
-	{ 0xDFFF, 0xDFFF, 0x0000, 0, 0x0000 }, /* R67 */
-	{ 0xDFFF, 0xDFFF, 0x0000, 0, 0x0000 }, /* R68 */
-	{ 0x0000, 0x0000, 0x0000, 0, 0x0000 }, /* R69 */
-	{ 0xFFFF, 0xFFFF, 0x0000, 0, 0x4400 }, /* R70 */
-	{ 0x23FF, 0x23FF, 0x0000, 0, 0x0000 }, /* R71 */
-	{ 0xFFFF, 0xFFFF, 0x0000, 0, 0x4400 }, /* R72 */
-	{ 0x23FF, 0x23FF, 0x0000, 0, 0x0000 }, /* R73 */
-	{ 0x0000, 0x0000, 0x0000, 0, 0x0000 }, /* R74 */
-	{ 0x000E, 0x000E, 0x0000, 0, 0x0008 }, /* R75 */
-	{ 0xE00F, 0xE00F, 0x0000, 0, 0x0000 }, /* R76 */
-	{ 0x0000, 0x0000, 0x0000, 0, 0x0000 }, /* R77 */
-	{ 0x03C0, 0x03C0, 0x0000, 0, 0x02C0 }, /* R78 */
-	{ 0xFFFF, 0x0000, 0xffff, 0, 0x0000 }, /* R79 */
-	{ 0xFFFF, 0xFFFF, 0x0000, 0, 0x0000 }, /* R80 */
-	{ 0xFFFF, 0x0000, 0xffff, 0, 0x0000 }, /* R81 */
-	{ 0x2BFF, 0x0000, 0xffff, 0, 0x0000 }, /* R82 */
-	{ 0x0000, 0x0000, 0x0000, 0, 0x0000 }, /* R83 */
-	{ 0x80FF, 0x80FF, 0x0000, 0, 0x00ff }, /* R84 */
-};
-
-static int wm8400_read(struct wm8400 *wm8400, u8 reg, int num_regs, u16 *dest)
+static bool wm8400_volatile(struct device *dev, unsigned int reg)
 {
-	int i, ret = 0;
-
-	BUG_ON(reg + num_regs > ARRAY_SIZE(wm8400->reg_cache));
-
-	/* If there are any volatile reads then read back the entire block */
-	for (i = reg; i < reg + num_regs; i++)
-		if (reg_data[i].vol) {
-			ret = regmap_bulk_read(wm8400->regmap, reg, dest,
-					       num_regs);
-			return ret;
-		}
-
-	/* Otherwise use the cache */
-	memcpy(dest, &wm8400->reg_cache[reg], num_regs * sizeof(u16));
-
-	return 0;
-}
-
-static int wm8400_write(struct wm8400 *wm8400, u8 reg, int num_regs,
-			u16 *src)
-{
-	int ret, i;
-
-	BUG_ON(reg + num_regs > ARRAY_SIZE(wm8400->reg_cache));
-
-	for (i = 0; i < num_regs; i++) {
-		BUG_ON(!reg_data[reg + i].writable);
-		wm8400->reg_cache[reg + i] = src[i];
-		ret = regmap_write(wm8400->regmap, reg, src[i]);
-		if (ret != 0)
-			return ret;
+	switch (reg) {
+	case WM8400_INTERRUPT_STATUS_1:
+	case WM8400_INTERRUPT_LEVELS:
+	case WM8400_SHUTDOWN_REASON:
+		return true;
+	default:
+		return false;
 	}
-
-	return 0;
 }
 
 /**
@@ -165,13 +45,12 @@ static int wm8400_write(struct wm8400 *wm8400, u8 reg, int num_regs,
  */
 u16 wm8400_reg_read(struct wm8400 *wm8400, u8 reg)
 {
-	u16 val;
-
-	mutex_lock(&wm8400->io_lock);
-
-	wm8400_read(wm8400, reg, 1, &val);
+	unsigned int val;
+	int ret;
 
-	mutex_unlock(&wm8400->io_lock);
+	ret = regmap_read(wm8400->regmap, reg, &val);
+	if (ret < 0)
+		return ret;
 
 	return val;
 }
@@ -179,63 +58,10 @@ EXPORT_SYMBOL_GPL(wm8400_reg_read);
 
 int wm8400_block_read(struct wm8400 *wm8400, u8 reg, int count, u16 *data)
 {
-	int ret;
-
-	mutex_lock(&wm8400->io_lock);
-
-	ret = wm8400_read(wm8400, reg, count, data);
-
-	mutex_unlock(&wm8400->io_lock);
-
-	return ret;
+	return regmap_bulk_read(wm8400->regmap, reg, data, count);
 }
 EXPORT_SYMBOL_GPL(wm8400_block_read);
 
-/**
- * wm8400_set_bits - Bitmask write
- *
- * @wm8400: Pointer to wm8400 control structure
- * @reg:    Register to access
- * @mask:   Mask of bits to change
- * @val:    Value to set for masked bits
- */
-int wm8400_set_bits(struct wm8400 *wm8400, u8 reg, u16 mask, u16 val)
-{
-	u16 tmp;
-	int ret;
-
-	mutex_lock(&wm8400->io_lock);
-
-	ret = wm8400_read(wm8400, reg, 1, &tmp);
-	tmp = (tmp & ~mask) | val;
-	if (ret == 0)
-		ret = wm8400_write(wm8400, reg, 1, &tmp);
-
-	mutex_unlock(&wm8400->io_lock);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(wm8400_set_bits);
-
-/**
- * wm8400_reset_codec_reg_cache - Reset cached codec registers to
- * their default values.
- */
-void wm8400_reset_codec_reg_cache(struct wm8400 *wm8400)
-{
-	int i;
-
-	mutex_lock(&wm8400->io_lock);
-
-	/* Reset all codec registers to their initial value */
-	for (i = 0; i < ARRAY_SIZE(wm8400->reg_cache); i++)
-		if (reg_data[i].is_codec)
-			wm8400->reg_cache[i] = reg_data[i].default_val;
-
-	mutex_unlock(&wm8400->io_lock);
-}
-EXPORT_SYMBOL_GPL(wm8400_reset_codec_reg_cache);
-
 static int wm8400_register_codec(struct wm8400 *wm8400)
 {
 	struct mfd_cell cell = {
@@ -257,44 +83,24 @@ static int wm8400_register_codec(struct wm8400 *wm8400)
 static int wm8400_init(struct wm8400 *wm8400,
 		       struct wm8400_platform_data *pdata)
 {
-	u16 reg;
-	int ret, i;
-
-	mutex_init(&wm8400->io_lock);
+	unsigned int reg;
+	int ret;
 
 	dev_set_drvdata(wm8400->dev, wm8400);
 
 	/* Check that this is actually a WM8400 */
-	ret = regmap_read(wm8400->regmap, WM8400_RESET_ID, &i);
+	ret = regmap_read(wm8400->regmap, WM8400_RESET_ID, &reg);
 	if (ret != 0) {
 		dev_err(wm8400->dev, "Chip ID register read failed\n");
 		return -EIO;
 	}
-	if (i != reg_data[WM8400_RESET_ID].default_val) {
-		dev_err(wm8400->dev, "Device is not a WM8400, ID is %x\n", i);
+	if (reg != 0x6172) {
+		dev_err(wm8400->dev, "Device is not a WM8400, ID is %x\n",
+			reg);
 		return -ENODEV;
 	}
 
-	/* We don't know what state the hardware is in and since this
-	 * is a PMIC we can't reset it safely so initialise the register
-	 * cache from the hardware.
-	 */
-	ret = regmap_raw_read(wm8400->regmap, 0, wm8400->reg_cache,
-			      ARRAY_SIZE(wm8400->reg_cache));
-	if (ret != 0) {
-		dev_err(wm8400->dev, "Register cache read failed\n");
-		return -EIO;
-	}
-	for (i = 0; i < ARRAY_SIZE(wm8400->reg_cache); i++)
-		wm8400->reg_cache[i] = be16_to_cpu(wm8400->reg_cache[i]);
-
-	/* If the codec is in reset use hard coded values */
-	if (!(wm8400->reg_cache[WM8400_POWER_MANAGEMENT_1] & WM8400_CODEC_ENA))
-		for (i = 0; i < ARRAY_SIZE(wm8400->reg_cache); i++)
-			if (reg_data[i].is_codec)
-				wm8400->reg_cache[i] = reg_data[i].default_val;
-
-	ret = wm8400_read(wm8400, WM8400_ID, 1, &reg);
+	ret = regmap_read(wm8400->regmap, WM8400_ID, &reg);
 	if (ret != 0) {
 		dev_err(wm8400->dev, "ID register read failed: %d\n", ret);
 		return ret;
@@ -334,8 +140,22 @@ static const struct regmap_config wm8400_regmap_config = {
 	.reg_bits = 8,
 	.val_bits = 16,
 	.max_register = WM8400_REGISTER_COUNT - 1,
+
+	.volatile_reg = wm8400_volatile,
+
+	.cache_type = REGCACHE_RBTREE,
 };
 
+/**
+ * wm8400_reset_codec_reg_cache - Reset cached codec registers to
+ * their default values.
+ */
+void wm8400_reset_codec_reg_cache(struct wm8400 *wm8400)
+{
+	regmap_reinit_cache(wm8400->regmap, &wm8400_regmap_config);
+}
+EXPORT_SYMBOL_GPL(wm8400_reset_codec_reg_cache);
+
 #if defined(CONFIG_I2C) || defined(CONFIG_I2C_MODULE)
 static int wm8400_i2c_probe(struct i2c_client *i2c,
 			    const struct i2c_device_id *id)
diff --git a/drivers/mfd/wm8994-core.c b/drivers/mfd/wm8994-core.c
index 9d7ca1e978fa..1e321d349777 100644
--- a/drivers/mfd/wm8994-core.c
+++ b/drivers/mfd/wm8994-core.c
@@ -500,7 +500,8 @@ static __devinit int wm8994_device_init(struct wm8994 *wm8994, int irq)
 			ret);
 		goto err_enable;
 	}
-	wm8994->revision = ret;
+	wm8994->revision = ret & WM8994_CHIP_REV_MASK;
+	wm8994->cust_id = (ret & WM8994_CUST_ID_MASK) >> WM8994_CUST_ID_SHIFT;
 
 	switch (wm8994->type) {
 	case WM8994:
@@ -553,8 +554,8 @@ static __devinit int wm8994_device_init(struct wm8994 *wm8994, int irq)
 		break;
 	}
 
-	dev_info(wm8994->dev, "%s revision %c\n", devname,
-		 'A' + wm8994->revision);
+	dev_info(wm8994->dev, "%s revision %c CUST_ID %02x\n", devname,
+		 'A' + wm8994->revision, wm8994->cust_id);
 
 	switch (wm8994->type) {
 	case WM1811:
@@ -732,23 +733,7 @@ static struct i2c_driver wm8994_i2c_driver = {
 	.id_table = wm8994_i2c_id,
 };
 
-static int __init wm8994_i2c_init(void)
-{
-	int ret;
-
-	ret = i2c_add_driver(&wm8994_i2c_driver);
-	if (ret != 0)
-		pr_err("Failed to register wm8994 I2C driver: %d\n", ret);
-
-	return ret;
-}
-module_init(wm8994_i2c_init);
-
-static void __exit wm8994_i2c_exit(void)
-{
-	i2c_del_driver(&wm8994_i2c_driver);
-}
-module_exit(wm8994_i2c_exit);
+module_i2c_driver(wm8994_i2c_driver);
 
 MODULE_DESCRIPTION("Core support for the WM8994 audio CODEC");
 MODULE_LICENSE("GPL");
diff --git a/drivers/mfd/wm8994-regmap.c b/drivers/mfd/wm8994-regmap.c
index bfd25af6ecb1..52e9e2944940 100644
--- a/drivers/mfd/wm8994-regmap.c
+++ b/drivers/mfd/wm8994-regmap.c
@@ -1122,7 +1122,6 @@ static bool wm8994_volatile_register(struct device *dev, unsigned int reg)
 	case WM8994_RATE_STATUS:
 	case WM8958_MIC_DETECT_3:
 	case WM8994_DC_SERVO_4E:
-	case WM8994_CHIP_REVISION:
 	case WM8994_INTERRUPT_STATUS_1:
 	case WM8994_INTERRUPT_STATUS_2:
 		return true;
diff --git a/drivers/misc/ab8500-pwm.c b/drivers/misc/ab8500-pwm.c
index d7a9aa14e5d5..042a8fe4efaa 100644
--- a/drivers/misc/ab8500-pwm.c
+++ b/drivers/misc/ab8500-pwm.c
@@ -142,10 +142,16 @@ static int __devexit ab8500_pwm_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct of_device_id ab8500_pwm_match[] = {
+	{ .compatible = "stericsson,ab8500-pwm", },
+	{}
+};
+
 static struct platform_driver ab8500_pwm_driver = {
 	.driver = {
 		.name = "ab8500-pwm",
 		.owner = THIS_MODULE,
+		.of_match_table = ab8500_pwm_match,
 	},
 	.probe = ab8500_pwm_probe,
 	.remove = __devexit_p(ab8500_pwm_remove),
diff --git a/drivers/power/wm831x_power.c b/drivers/power/wm831x_power.c
index 987332b71d8d..fc1ad9551182 100644
--- a/drivers/power/wm831x_power.c
+++ b/drivers/power/wm831x_power.c
@@ -565,7 +565,7 @@ static __devinit int wm831x_power_probe(struct platform_device *pdev)
 			    goto err_usb;
 	}
 
-	irq = platform_get_irq_byname(pdev, "SYSLO");
+	irq = wm831x_irq(wm831x, platform_get_irq_byname(pdev, "SYSLO"));
 	ret = request_threaded_irq(irq, NULL, wm831x_syslo_irq,
 				   IRQF_TRIGGER_RISING, "System power low",
 				   power);
@@ -575,7 +575,7 @@ static __devinit int wm831x_power_probe(struct platform_device *pdev)
 		goto err_battery;
 	}
 
-	irq = platform_get_irq_byname(pdev, "PWR SRC");
+	irq = wm831x_irq(wm831x, platform_get_irq_byname(pdev, "PWR SRC"));
 	ret = request_threaded_irq(irq, NULL, wm831x_pwr_src_irq,
 				   IRQF_TRIGGER_RISING, "Power source",
 				   power);
@@ -586,7 +586,9 @@ static __devinit int wm831x_power_probe(struct platform_device *pdev)
 	}
 
 	for (i = 0; i < ARRAY_SIZE(wm831x_bat_irqs); i++) {
-		irq = platform_get_irq_byname(pdev, wm831x_bat_irqs[i]);
+		irq = wm831x_irq(wm831x,
+				 platform_get_irq_byname(pdev,
+							 wm831x_bat_irqs[i]));
 		ret = request_threaded_irq(irq, NULL, wm831x_bat_irq,
 					   IRQF_TRIGGER_RISING,
 					   wm831x_bat_irqs[i],
@@ -606,10 +608,10 @@ err_bat_irq:
 		irq = platform_get_irq_byname(pdev, wm831x_bat_irqs[i]);
 		free_irq(irq, power);
 	}
-	irq = platform_get_irq_byname(pdev, "PWR SRC");
+	irq = wm831x_irq(wm831x, platform_get_irq_byname(pdev, "PWR SRC"));
 	free_irq(irq, power);
 err_syslo:
-	irq = platform_get_irq_byname(pdev, "SYSLO");
+	irq = wm831x_irq(wm831x, platform_get_irq_byname(pdev, "SYSLO"));
 	free_irq(irq, power);
 err_battery:
 	if (power->have_battery)
@@ -626,17 +628,20 @@ err_kmalloc:
 static __devexit int wm831x_power_remove(struct platform_device *pdev)
 {
 	struct wm831x_power *wm831x_power = platform_get_drvdata(pdev);
+	struct wm831x *wm831x = wm831x_power->wm831x;
 	int irq, i;
 
 	for (i = 0; i < ARRAY_SIZE(wm831x_bat_irqs); i++) {
-		irq = platform_get_irq_byname(pdev, wm831x_bat_irqs[i]);
+		irq = wm831x_irq(wm831x, 
+				 platform_get_irq_byname(pdev,
+							 wm831x_bat_irqs[i]));
 		free_irq(irq, wm831x_power);
 	}
 
-	irq = platform_get_irq_byname(pdev, "PWR SRC");
+	irq = wm831x_irq(wm831x, platform_get_irq_byname(pdev, "PWR SRC"));
 	free_irq(irq, wm831x_power);
 
-	irq = platform_get_irq_byname(pdev, "SYSLO");
+	irq = wm831x_irq(wm831x, platform_get_irq_byname(pdev, "SYSLO"));
 	free_irq(irq, wm831x_power);
 
 	if (wm831x_power->have_battery)
diff --git a/drivers/regulator/anatop-regulator.c b/drivers/regulator/anatop-regulator.c
index 49b2112b0486..3660bace123c 100644
--- a/drivers/regulator/anatop-regulator.c
+++ b/drivers/regulator/anatop-regulator.c
@@ -47,7 +47,7 @@ static int anatop_set_voltage(struct regulator_dev *reg, int min_uV,
 				  int max_uV, unsigned *selector)
 {
 	struct anatop_regulator *anatop_reg = rdev_get_drvdata(reg);
-	u32 val, sel;
+	u32 val, sel, mask;
 	int uv;
 
 	uv = min_uV;
@@ -71,11 +71,10 @@ static int anatop_set_voltage(struct regulator_dev *reg, int min_uV,
 	val = anatop_reg->min_bit_val + sel;
 	*selector = sel;
 	dev_dbg(&reg->dev, "%s: calculated val %d\n", __func__, val);
-	anatop_set_bits(anatop_reg->mfd,
-			anatop_reg->control_reg,
-			anatop_reg->vol_bit_shift,
-			anatop_reg->vol_bit_width,
-			val);
+	mask = ((1 << anatop_reg->vol_bit_width) - 1) <<
+		anatop_reg->vol_bit_shift;
+	val <<= anatop_reg->vol_bit_shift;
+	anatop_write_reg(anatop_reg->mfd, anatop_reg->control_reg, val, mask);
 
 	return 0;
 }
@@ -88,10 +87,9 @@ static int anatop_get_voltage_sel(struct regulator_dev *reg)
 	if (!anatop_reg->control_reg)
 		return -ENOTSUPP;
 
-	val = anatop_get_bits(anatop_reg->mfd,
-			      anatop_reg->control_reg,
-			      anatop_reg->vol_bit_shift,
-			      anatop_reg->vol_bit_width);
+	val = anatop_read_reg(anatop_reg->mfd, anatop_reg->control_reg);
+	val = (val & ((1 << anatop_reg->vol_bit_width) - 1)) >>
+		anatop_reg->vol_bit_shift;
 
 	return val - anatop_reg->min_bit_val;
 }
diff --git a/drivers/regulator/tps65910-regulator.c b/drivers/regulator/tps65910-regulator.c
index 4e01a423471b..6bf864b4bdf6 100644
--- a/drivers/regulator/tps65910-regulator.c
+++ b/drivers/regulator/tps65910-regulator.c
@@ -331,21 +331,16 @@ struct tps65910_reg {
 
 static inline int tps65910_read(struct tps65910_reg *pmic, u8 reg)
 {
-	u8 val;
+	unsigned int val;
 	int err;
 
-	err = pmic->mfd->read(pmic->mfd, reg, 1, &val);
+	err = tps65910_reg_read(pmic->mfd, reg, &val);
 	if (err)
 		return err;
 
 	return val;
 }
 
-static inline int tps65910_write(struct tps65910_reg *pmic, u8 reg, u8 val)
-{
-	return pmic->mfd->write(pmic->mfd, reg, 1, &val);
-}
-
 static int tps65910_modify_bits(struct tps65910_reg *pmic, u8 reg,
 					u8 set_mask, u8 clear_mask)
 {
@@ -362,7 +357,7 @@ static int tps65910_modify_bits(struct tps65910_reg *pmic, u8 reg,
 
 	data &= ~clear_mask;
 	data |= set_mask;
-	err = tps65910_write(pmic, reg, data);
+	err = tps65910_reg_write(pmic->mfd, reg, data);
 	if (err)
 		dev_err(pmic->mfd->dev, "Write for reg 0x%x failed\n", reg);
 
@@ -371,7 +366,7 @@ out:
 	return err;
 }
 
-static int tps65910_reg_read(struct tps65910_reg *pmic, u8 reg)
+static int tps65910_reg_read_locked(struct tps65910_reg *pmic, u8 reg)
 {
 	int data;
 
@@ -385,13 +380,13 @@ static int tps65910_reg_read(struct tps65910_reg *pmic, u8 reg)
 	return data;
 }
 
-static int tps65910_reg_write(struct tps65910_reg *pmic, u8 reg, u8 val)
+static int tps65910_reg_write_locked(struct tps65910_reg *pmic, u8 reg, u8 val)
 {
 	int err;
 
 	mutex_lock(&pmic->mutex);
 
-	err = tps65910_write(pmic, reg, val);
+	err = tps65910_reg_write(pmic->mfd, reg, val);
 	if (err < 0)
 		dev_err(pmic->mfd->dev, "Write for reg 0x%x failed\n", reg);
 
@@ -490,9 +485,9 @@ static int tps65910_set_mode(struct regulator_dev *dev, unsigned int mode)
 							LDO_ST_MODE_BIT);
 	case REGULATOR_MODE_IDLE:
 		value = LDO_ST_ON_BIT | LDO_ST_MODE_BIT;
-		return tps65910_set_bits(mfd, reg, value);
+		return tps65910_reg_set_bits(mfd, reg, value);
 	case REGULATOR_MODE_STANDBY:
-		return tps65910_clear_bits(mfd, reg, LDO_ST_ON_BIT);
+		return tps65910_reg_clear_bits(mfd, reg, LDO_ST_ON_BIT);
 	}
 
 	return -EINVAL;
@@ -507,7 +502,7 @@ static unsigned int tps65910_get_mode(struct regulator_dev *dev)
 	if (reg < 0)
 		return reg;
 
-	value = tps65910_reg_read(pmic, reg);
+	value = tps65910_reg_read_locked(pmic, reg);
 	if (value < 0)
 		return value;
 
@@ -527,28 +522,28 @@ static int tps65910_get_voltage_dcdc_sel(struct regulator_dev *dev)
 
 	switch (id) {
 	case TPS65910_REG_VDD1:
-		opvsel = tps65910_reg_read(pmic, TPS65910_VDD1_OP);
-		mult = tps65910_reg_read(pmic, TPS65910_VDD1);
+		opvsel = tps65910_reg_read_locked(pmic, TPS65910_VDD1_OP);
+		mult = tps65910_reg_read_locked(pmic, TPS65910_VDD1);
 		mult = (mult & VDD1_VGAIN_SEL_MASK) >> VDD1_VGAIN_SEL_SHIFT;
-		srvsel = tps65910_reg_read(pmic, TPS65910_VDD1_SR);
+		srvsel = tps65910_reg_read_locked(pmic, TPS65910_VDD1_SR);
 		sr = opvsel & VDD1_OP_CMD_MASK;
 		opvsel &= VDD1_OP_SEL_MASK;
 		srvsel &= VDD1_SR_SEL_MASK;
 		vselmax = 75;
 		break;
 	case TPS65910_REG_VDD2:
-		opvsel = tps65910_reg_read(pmic, TPS65910_VDD2_OP);
-		mult = tps65910_reg_read(pmic, TPS65910_VDD2);
+		opvsel = tps65910_reg_read_locked(pmic, TPS65910_VDD2_OP);
+		mult = tps65910_reg_read_locked(pmic, TPS65910_VDD2);
 		mult = (mult & VDD2_VGAIN_SEL_MASK) >> VDD2_VGAIN_SEL_SHIFT;
-		srvsel = tps65910_reg_read(pmic, TPS65910_VDD2_SR);
+		srvsel = tps65910_reg_read_locked(pmic, TPS65910_VDD2_SR);
 		sr = opvsel & VDD2_OP_CMD_MASK;
 		opvsel &= VDD2_OP_SEL_MASK;
 		srvsel &= VDD2_SR_SEL_MASK;
 		vselmax = 75;
 		break;
 	case TPS65911_REG_VDDCTRL:
-		opvsel = tps65910_reg_read(pmic, TPS65911_VDDCTRL_OP);
-		srvsel = tps65910_reg_read(pmic, TPS65911_VDDCTRL_SR);
+		opvsel = tps65910_reg_read_locked(pmic, TPS65911_VDDCTRL_OP);
+		srvsel = tps65910_reg_read_locked(pmic, TPS65911_VDDCTRL_SR);
 		sr = opvsel & VDDCTRL_OP_CMD_MASK;
 		opvsel &= VDDCTRL_OP_SEL_MASK;
 		srvsel &= VDDCTRL_SR_SEL_MASK;
@@ -588,7 +583,7 @@ static int tps65910_get_voltage_sel(struct regulator_dev *dev)
 	if (reg < 0)
 		return reg;
 
-	value = tps65910_reg_read(pmic, reg);
+	value = tps65910_reg_read_locked(pmic, reg);
 	if (value < 0)
 		return value;
 
@@ -625,7 +620,7 @@ static int tps65911_get_voltage_sel(struct regulator_dev *dev)
 
 	reg = pmic->get_ctrl_reg(id);
 
-	value = tps65910_reg_read(pmic, reg);
+	value = tps65910_reg_read_locked(pmic, reg);
 
 	switch (id) {
 	case TPS65911_REG_LDO1:
@@ -670,7 +665,7 @@ static int tps65910_set_voltage_dcdc_sel(struct regulator_dev *dev,
 		tps65910_modify_bits(pmic, TPS65910_VDD1,
 				(dcdc_mult << VDD1_VGAIN_SEL_SHIFT),
 						VDD1_VGAIN_SEL_MASK);
-		tps65910_reg_write(pmic, TPS65910_VDD1_OP, vsel);
+		tps65910_reg_write_locked(pmic, TPS65910_VDD1_OP, vsel);
 		break;
 	case TPS65910_REG_VDD2:
 		dcdc_mult = (selector / VDD1_2_NUM_VOLT_FINE) + 1;
@@ -681,11 +676,11 @@ static int tps65910_set_voltage_dcdc_sel(struct regulator_dev *dev,
 		tps65910_modify_bits(pmic, TPS65910_VDD2,
 				(dcdc_mult << VDD2_VGAIN_SEL_SHIFT),
 						VDD1_VGAIN_SEL_MASK);
-		tps65910_reg_write(pmic, TPS65910_VDD2_OP, vsel);
+		tps65910_reg_write_locked(pmic, TPS65910_VDD2_OP, vsel);
 		break;
 	case TPS65911_REG_VDDCTRL:
 		vsel = selector + 3;
-		tps65910_reg_write(pmic, TPS65911_VDDCTRL_OP, vsel);
+		tps65910_reg_write_locked(pmic, TPS65911_VDDCTRL_OP, vsel);
 	}
 
 	return 0;
@@ -936,10 +931,10 @@ static int tps65910_set_ext_sleep_config(struct tps65910_reg *pmic,
 
 	/* External EN1 control */
 	if (ext_sleep_config & TPS65910_SLEEP_CONTROL_EXT_INPUT_EN1)
-		ret = tps65910_set_bits(mfd,
+		ret = tps65910_reg_set_bits(mfd,
 				TPS65910_EN1_LDO_ASS + regoffs, bit_pos);
 	else
-		ret = tps65910_clear_bits(mfd,
+		ret = tps65910_reg_clear_bits(mfd,
 				TPS65910_EN1_LDO_ASS + regoffs, bit_pos);
 	if (ret < 0) {
 		dev_err(mfd->dev,
@@ -949,10 +944,10 @@ static int tps65910_set_ext_sleep_config(struct tps65910_reg *pmic,
 
 	/* External EN2 control */
 	if (ext_sleep_config & TPS65910_SLEEP_CONTROL_EXT_INPUT_EN2)
-		ret = tps65910_set_bits(mfd,
+		ret = tps65910_reg_set_bits(mfd,
 				TPS65910_EN2_LDO_ASS + regoffs, bit_pos);
 	else
-		ret = tps65910_clear_bits(mfd,
+		ret = tps65910_reg_clear_bits(mfd,
 				TPS65910_EN2_LDO_ASS + regoffs, bit_pos);
 	if (ret < 0) {
 		dev_err(mfd->dev,
@@ -964,10 +959,10 @@ static int tps65910_set_ext_sleep_config(struct tps65910_reg *pmic,
 	if ((tps65910_chip_id(mfd) == TPS65910) &&
 			(id >= TPS65910_REG_VDIG1)) {
 		if (ext_sleep_config & TPS65910_SLEEP_CONTROL_EXT_INPUT_EN3)
-			ret = tps65910_set_bits(mfd,
+			ret = tps65910_reg_set_bits(mfd,
 				TPS65910_EN3_LDO_ASS + regoffs, bit_pos);
 		else
-			ret = tps65910_clear_bits(mfd,
+			ret = tps65910_reg_clear_bits(mfd,
 				TPS65910_EN3_LDO_ASS + regoffs, bit_pos);
 		if (ret < 0) {
 			dev_err(mfd->dev,
@@ -979,10 +974,10 @@ static int tps65910_set_ext_sleep_config(struct tps65910_reg *pmic,
 	/* Return if no external control is selected */
 	if (!(ext_sleep_config & EXT_SLEEP_CONTROL)) {
 		/* Clear all sleep controls */
-		ret = tps65910_clear_bits(mfd,
+		ret = tps65910_reg_clear_bits(mfd,
 			TPS65910_SLEEP_KEEP_LDO_ON + regoffs, bit_pos);
 		if (!ret)
-			ret = tps65910_clear_bits(mfd,
+			ret = tps65910_reg_clear_bits(mfd,
 				TPS65910_SLEEP_SET_LDO_OFF + regoffs, bit_pos);
 		if (ret < 0)
 			dev_err(mfd->dev,
@@ -1001,32 +996,33 @@ static int tps65910_set_ext_sleep_config(struct tps65910_reg *pmic,
 				(tps65910_chip_id(mfd) == TPS65911))) {
 		int op_reg_add = pmic->get_ctrl_reg(id) + 1;
 		int sr_reg_add = pmic->get_ctrl_reg(id) + 2;
-		int opvsel = tps65910_reg_read(pmic, op_reg_add);
-		int srvsel = tps65910_reg_read(pmic, sr_reg_add);
+		int opvsel = tps65910_reg_read_locked(pmic, op_reg_add);
+		int srvsel = tps65910_reg_read_locked(pmic, sr_reg_add);
 		if (opvsel & VDD1_OP_CMD_MASK) {
 			u8 reg_val = srvsel & VDD1_OP_SEL_MASK;
-			ret = tps65910_reg_write(pmic, op_reg_add, reg_val);
+			ret = tps65910_reg_write_locked(pmic, op_reg_add,
+							reg_val);
 			if (ret < 0) {
 				dev_err(mfd->dev,
 					"Error in configuring op register\n");
 				return ret;
 			}
 		}
-		ret = tps65910_reg_write(pmic, sr_reg_add, 0);
+		ret = tps65910_reg_write_locked(pmic, sr_reg_add, 0);
 		if (ret < 0) {
 			dev_err(mfd->dev, "Error in settting sr register\n");
 			return ret;
 		}
 	}
 
-	ret = tps65910_clear_bits(mfd,
+	ret = tps65910_reg_clear_bits(mfd,
 			TPS65910_SLEEP_KEEP_LDO_ON + regoffs, bit_pos);
 	if (!ret) {
 		if (ext_sleep_config & TPS65911_SLEEP_CONTROL_EXT_INPUT_SLEEP)
-			ret = tps65910_set_bits(mfd,
+			ret = tps65910_reg_set_bits(mfd,
 				TPS65910_SLEEP_SET_LDO_OFF + regoffs, bit_pos);
 		else
-			ret = tps65910_clear_bits(mfd,
+			ret = tps65910_reg_clear_bits(mfd,
 				TPS65910_SLEEP_SET_LDO_OFF + regoffs, bit_pos);
 	}
 	if (ret < 0)
@@ -1177,7 +1173,7 @@ static __devinit int tps65910_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, pmic);
 
 	/* Give control of all register to control port */
-	tps65910_set_bits(pmic->mfd, TPS65910_DEVCTRL,
+	tps65910_reg_set_bits(pmic->mfd, TPS65910_DEVCTRL,
 				DEVCTRL_SR_CTL_I2C_SEL_MASK);
 
 	switch(tps65910_chip_id(tps65910)) {
diff --git a/drivers/regulator/wm831x-dcdc.c b/drivers/regulator/wm831x-dcdc.c
index a885911bb5fc..099da11e989f 100644
--- a/drivers/regulator/wm831x-dcdc.c
+++ b/drivers/regulator/wm831x-dcdc.c
@@ -535,7 +535,7 @@ static __devinit int wm831x_buckv_probe(struct platform_device *pdev)
 		goto err;
 	}
 
-	irq = platform_get_irq_byname(pdev, "UV");
+	irq = wm831x_irq(wm831x, platform_get_irq_byname(pdev, "UV"));
 	ret = request_threaded_irq(irq, NULL, wm831x_dcdc_uv_irq,
 				   IRQF_TRIGGER_RISING, dcdc->name, dcdc);
 	if (ret != 0) {
@@ -544,7 +544,7 @@ static __devinit int wm831x_buckv_probe(struct platform_device *pdev)
 		goto err_regulator;
 	}
 
-	irq = platform_get_irq_byname(pdev, "HC");
+	irq = wm831x_irq(wm831x, platform_get_irq_byname(pdev, "HC"));
 	ret = request_threaded_irq(irq, NULL, wm831x_dcdc_oc_irq,
 				   IRQF_TRIGGER_RISING, dcdc->name, dcdc);
 	if (ret != 0) {
@@ -558,7 +558,8 @@ static __devinit int wm831x_buckv_probe(struct platform_device *pdev)
 	return 0;
 
 err_uv:
-	free_irq(platform_get_irq_byname(pdev, "UV"), dcdc);
+	free_irq(wm831x_irq(wm831x, platform_get_irq_byname(pdev, "UV")),
+		 dcdc);
 err_regulator:
 	regulator_unregister(dcdc->regulator);
 err:
@@ -570,11 +571,14 @@ err:
 static __devexit int wm831x_buckv_remove(struct platform_device *pdev)
 {
 	struct wm831x_dcdc *dcdc = platform_get_drvdata(pdev);
+	struct wm831x *wm831x = dcdc->wm831x;
 
 	platform_set_drvdata(pdev, NULL);
 
-	free_irq(platform_get_irq_byname(pdev, "HC"), dcdc);
-	free_irq(platform_get_irq_byname(pdev, "UV"), dcdc);
+	free_irq(wm831x_irq(wm831x, platform_get_irq_byname(pdev, "HC")),
+			    dcdc);
+	free_irq(wm831x_irq(wm831x, platform_get_irq_byname(pdev, "UV")),
+			    dcdc);
 	regulator_unregister(dcdc->regulator);
 	if (dcdc->dvs_gpio)
 		gpio_free(dcdc->dvs_gpio);
@@ -726,7 +730,7 @@ static __devinit int wm831x_buckp_probe(struct platform_device *pdev)
 		goto err;
 	}
 
-	irq = platform_get_irq_byname(pdev, "UV");
+	irq = wm831x_irq(wm831x, platform_get_irq_byname(pdev, "UV"));
 	ret = request_threaded_irq(irq, NULL, wm831x_dcdc_uv_irq,
 				   IRQF_TRIGGER_RISING,	dcdc->name, dcdc);
 	if (ret != 0) {
@@ -751,7 +755,8 @@ static __devexit int wm831x_buckp_remove(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, NULL);
 
-	free_irq(platform_get_irq_byname(pdev, "UV"), dcdc);
+	free_irq(wm831x_irq(dcdc->wm831x, platform_get_irq_byname(pdev, "UV")),
+			    dcdc);
 	regulator_unregister(dcdc->regulator);
 
 	return 0;
@@ -859,7 +864,7 @@ static __devinit int wm831x_boostp_probe(struct platform_device *pdev)
 		goto err;
 	}
 
-	irq = platform_get_irq_byname(pdev, "UV");
+	irq = wm831x_irq(wm831x, platform_get_irq_byname(pdev, "UV"));
 	ret = request_threaded_irq(irq, NULL, wm831x_dcdc_uv_irq,
 				   IRQF_TRIGGER_RISING, dcdc->name,
 				   dcdc);
@@ -885,7 +890,8 @@ static __devexit int wm831x_boostp_remove(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, NULL);
 
-	free_irq(platform_get_irq_byname(pdev, "UV"), dcdc);
+	free_irq(wm831x_irq(dcdc->wm831x, platform_get_irq_byname(pdev, "UV")),
+		 dcdc);
 	regulator_unregister(dcdc->regulator);
 
 	return 0;
diff --git a/drivers/regulator/wm831x-isink.c b/drivers/regulator/wm831x-isink.c
index b50ab778b098..0d207c297714 100644
--- a/drivers/regulator/wm831x-isink.c
+++ b/drivers/regulator/wm831x-isink.c
@@ -202,7 +202,7 @@ static __devinit int wm831x_isink_probe(struct platform_device *pdev)
 		goto err;
 	}
 
-	irq = platform_get_irq(pdev, 0);
+	irq = wm831x_irq(wm831x, platform_get_irq(pdev, 0));
 	ret = request_threaded_irq(irq, NULL, wm831x_isink_irq,
 				   IRQF_TRIGGER_RISING, isink->name, isink);
 	if (ret != 0) {
@@ -227,7 +227,7 @@ static __devexit int wm831x_isink_remove(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, NULL);
 
-	free_irq(platform_get_irq(pdev, 0), isink);
+	free_irq(wm831x_irq(isink->wm831x, platform_get_irq(pdev, 0)), isink);
 
 	regulator_unregister(isink->regulator);
 
diff --git a/drivers/regulator/wm831x-ldo.c b/drivers/regulator/wm831x-ldo.c
index aa1f8b3fbe16..a9a28d8ac185 100644
--- a/drivers/regulator/wm831x-ldo.c
+++ b/drivers/regulator/wm831x-ldo.c
@@ -321,7 +321,7 @@ static __devinit int wm831x_gp_ldo_probe(struct platform_device *pdev)
 		goto err;
 	}
 
-	irq = platform_get_irq_byname(pdev, "UV");
+	irq = wm831x_irq(wm831x, platform_get_irq_byname(pdev, "UV"));
 	ret = request_threaded_irq(irq, NULL, wm831x_ldo_uv_irq,
 				   IRQF_TRIGGER_RISING, ldo->name,
 				   ldo);
@@ -347,7 +347,8 @@ static __devexit int wm831x_gp_ldo_remove(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, NULL);
 
-	free_irq(platform_get_irq_byname(pdev, "UV"), ldo);
+	free_irq(wm831x_irq(ldo->wm831x,
+			    platform_get_irq_byname(pdev, "UV")), ldo);
 	regulator_unregister(ldo->regulator);
 
 	return 0;
@@ -582,7 +583,7 @@ static __devinit int wm831x_aldo_probe(struct platform_device *pdev)
 		goto err;
 	}
 
-	irq = platform_get_irq_byname(pdev, "UV");
+	irq = wm831x_irq(wm831x, platform_get_irq_byname(pdev, "UV"));
 	ret = request_threaded_irq(irq, NULL, wm831x_ldo_uv_irq,
 				   IRQF_TRIGGER_RISING, ldo->name, ldo);
 	if (ret != 0) {
@@ -605,7 +606,8 @@ static __devexit int wm831x_aldo_remove(struct platform_device *pdev)
 {
 	struct wm831x_ldo *ldo = platform_get_drvdata(pdev);
 
-	free_irq(platform_get_irq_byname(pdev, "UV"), ldo);
+	free_irq(wm831x_irq(ldo->wm831x, platform_get_irq_byname(pdev, "UV")),
+		 ldo);
 	regulator_unregister(ldo->regulator);
 
 	return 0;
diff --git a/drivers/rtc/rtc-wm831x.c b/drivers/rtc/rtc-wm831x.c
index 3b6e6a67e765..59c6245e0421 100644
--- a/drivers/rtc/rtc-wm831x.c
+++ b/drivers/rtc/rtc-wm831x.c
@@ -396,7 +396,7 @@ static int wm831x_rtc_probe(struct platform_device *pdev)
 {
 	struct wm831x *wm831x = dev_get_drvdata(pdev->dev.parent);
 	struct wm831x_rtc *wm831x_rtc;
-	int alm_irq = platform_get_irq_byname(pdev, "ALM");
+	int alm_irq = wm831x_irq(wm831x, platform_get_irq_byname(pdev, "ALM"));
 	int ret = 0;
 
 	wm831x_rtc = devm_kzalloc(&pdev->dev, sizeof(*wm831x_rtc), GFP_KERNEL);
diff --git a/drivers/staging/android/ashmem.c b/drivers/staging/android/ashmem.c
index 4511420849bc..e84dbecd0991 100644
--- a/drivers/staging/android/ashmem.c
+++ b/drivers/staging/android/ashmem.c
@@ -19,6 +19,7 @@
 #include <linux/module.h>
 #include <linux/file.h>
 #include <linux/fs.h>
+#include <linux/falloc.h>
 #include <linux/miscdevice.h>
 #include <linux/security.h>
 #include <linux/mm.h>
@@ -363,11 +364,12 @@ static int ashmem_shrink(struct shrinker *s, struct shrink_control *sc)
 
 	mutex_lock(&ashmem_mutex);
 	list_for_each_entry_safe(range, next, &ashmem_lru_list, lru) {
-		struct inode *inode = range->asma->file->f_dentry->d_inode;
 		loff_t start = range->pgstart * PAGE_SIZE;
-		loff_t end = (range->pgend + 1) * PAGE_SIZE - 1;
+		loff_t end = (range->pgend + 1) * PAGE_SIZE;
 
-		vmtruncate_range(inode, start, end);
+		do_fallocate(range->asma->file,
+				FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
+				start, end - start);
 		range->purged = ASHMEM_WAS_PURGED;
 		lru_del(range);
 
diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c
index 59af3945ea85..65c7c62c7aae 100644
--- a/drivers/tty/pty.c
+++ b/drivers/tty/pty.c
@@ -633,7 +633,6 @@ static int ptmx_open(struct inode *inode, struct file *filp)
 	mutex_unlock(&devpts_mutex);
 
 	mutex_lock(&tty_mutex);
-	mutex_lock(&devpts_mutex);
 	tty = tty_init_dev(ptm_driver, index);
 
 	if (IS_ERR(tty)) {
@@ -643,7 +642,6 @@ static int ptmx_open(struct inode *inode, struct file *filp)
 
 	/* The tty returned here is locked so we can safely
 	   drop the mutex */
-	mutex_unlock(&devpts_mutex);
 	mutex_unlock(&tty_mutex);
 
 	set_bit(TTY_PTY_LOCK, &tty->flags); /* LOCK THE SLAVE */
diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c
index 173a9000a6cb..ba8be396a621 100644
--- a/drivers/tty/tty_ldisc.c
+++ b/drivers/tty/tty_ldisc.c
@@ -894,6 +894,23 @@ int tty_ldisc_setup(struct tty_struct *tty, struct tty_struct *o_tty)
 	tty_ldisc_enable(tty);
 	return 0;
 }
+
+static void tty_ldisc_kill(struct tty_struct *tty)
+{
+	mutex_lock(&tty->ldisc_mutex);
+	/*
+	 * Now kill off the ldisc
+	 */
+	tty_ldisc_close(tty, tty->ldisc);
+	tty_ldisc_put(tty->ldisc);
+	/* Force an oops if we mess this up */
+	tty->ldisc = NULL;
+
+	/* Ensure the next open requests the N_TTY ldisc */
+	tty_set_termios_ldisc(tty, N_TTY);
+	mutex_unlock(&tty->ldisc_mutex);
+}
+
 /**
  *	tty_ldisc_release		-	release line discipline
  *	@tty: tty being shut down
@@ -912,27 +929,19 @@ void tty_ldisc_release(struct tty_struct *tty, struct tty_struct *o_tty)
 	 * race with the set_ldisc code path.
 	 */
 
-	tty_unlock(tty);
+	tty_unlock_pair(tty, o_tty);
 	tty_ldisc_halt(tty);
 	tty_ldisc_flush_works(tty);
-	tty_lock(tty);
-
-	mutex_lock(&tty->ldisc_mutex);
-	/*
-	 * Now kill off the ldisc
-	 */
-	tty_ldisc_close(tty, tty->ldisc);
-	tty_ldisc_put(tty->ldisc);
-	/* Force an oops if we mess this up */
-	tty->ldisc = NULL;
+	if (o_tty) {
+		tty_ldisc_halt(o_tty);
+		tty_ldisc_flush_works(o_tty);
+	}
+	tty_lock_pair(tty, o_tty);
 
-	/* Ensure the next open requests the N_TTY ldisc */
-	tty_set_termios_ldisc(tty, N_TTY);
-	mutex_unlock(&tty->ldisc_mutex);
 
-	/* This will need doing differently if we need to lock */
+	tty_ldisc_kill(tty);
 	if (o_tty)
-		tty_ldisc_release(o_tty, NULL);
+		tty_ldisc_kill(o_tty);
 
 	/* And the memory resources remaining (buffers, termios) will be
 	   disposed of when the kref hits zero */
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index a18bf6358eb8..d92d7488be16 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -565,6 +565,7 @@ config INTEL_SCU_WATCHDOG
 config ITCO_WDT
 	tristate "Intel TCO Timer/Watchdog"
 	depends on (X86 || IA64) && PCI
+	select LPC_ICH
 	---help---
 	  Hardware driver for the intel TCO timer based watchdog devices.
 	  These drivers are included in the Intel 82801 I/O Controller
diff --git a/drivers/watchdog/iTCO_vendor.h b/drivers/watchdog/iTCO_vendor.h
index 9e27e6422f66..3c57b45537a2 100644
--- a/drivers/watchdog/iTCO_vendor.h
+++ b/drivers/watchdog/iTCO_vendor.h
@@ -1,8 +1,8 @@
 /* iTCO Vendor Specific Support hooks */
 #ifdef CONFIG_ITCO_VENDOR_SUPPORT
-extern void iTCO_vendor_pre_start(unsigned long, unsigned int);
-extern void iTCO_vendor_pre_stop(unsigned long);
-extern void iTCO_vendor_pre_keepalive(unsigned long, unsigned int);
+extern void iTCO_vendor_pre_start(struct resource *, unsigned int);
+extern void iTCO_vendor_pre_stop(struct resource *);
+extern void iTCO_vendor_pre_keepalive(struct resource *, unsigned int);
 extern void iTCO_vendor_pre_set_heartbeat(unsigned int);
 extern int iTCO_vendor_check_noreboot_on(void);
 #else
diff --git a/drivers/watchdog/iTCO_vendor_support.c b/drivers/watchdog/iTCO_vendor_support.c
index 2721d29ce243..b6b2f90b5d44 100644
--- a/drivers/watchdog/iTCO_vendor_support.c
+++ b/drivers/watchdog/iTCO_vendor_support.c
@@ -35,11 +35,6 @@
 
 #include "iTCO_vendor.h"
 
-/* iTCO defines */
-#define	SMI_EN		(acpibase + 0x30) /* SMI Control and Enable Register */
-#define	TCOBASE		(acpibase + 0x60) /* TCO base address */
-#define	TCO1_STS	(TCOBASE + 0x04)  /* TCO1 Status Register */
-
 /* List of vendor support modes */
 /* SuperMicro Pentium 3 Era 370SSE+-OEM1/P3TSSE */
 #define SUPERMICRO_OLD_BOARD	1
@@ -82,24 +77,24 @@ MODULE_PARM_DESC(vendorsupport, "iTCO vendor specific support mode, default="
  *	    20.6 seconds.
  */
 
-static void supermicro_old_pre_start(unsigned long acpibase)
+static void supermicro_old_pre_start(struct resource *smires)
 {
 	unsigned long val32;
 
 	/* Bit 13: TCO_EN -> 0 = Disables TCO logic generating an SMI# */
-	val32 = inl(SMI_EN);
+	val32 = inl(smires->start);
 	val32 &= 0xffffdfff;	/* Turn off SMI clearing watchdog */
-	outl(val32, SMI_EN);	/* Needed to activate watchdog */
+	outl(val32, smires->start);	/* Needed to activate watchdog */
 }
 
-static void supermicro_old_pre_stop(unsigned long acpibase)
+static void supermicro_old_pre_stop(struct resource *smires)
 {
 	unsigned long val32;
 
 	/* Bit 13: TCO_EN -> 1 = Enables the TCO logic to generate SMI# */
-	val32 = inl(SMI_EN);
+	val32 = inl(smires->start);
 	val32 |= 0x00002000;	/* Turn on SMI clearing watchdog */
-	outl(val32, SMI_EN);	/* Needed to deactivate watchdog */
+	outl(val32, smires->start);	/* Needed to deactivate watchdog */
 }
 
 /*
@@ -270,66 +265,66 @@ static void supermicro_new_pre_set_heartbeat(unsigned int heartbeat)
  *	Don't use this fix if you don't need to!!!
  */
 
-static void broken_bios_start(unsigned long acpibase)
+static void broken_bios_start(struct resource *smires)
 {
 	unsigned long val32;
 
-	val32 = inl(SMI_EN);
+	val32 = inl(smires->start);
 	/* Bit 13: TCO_EN     -> 0 = Disables TCO logic generating an SMI#
 	   Bit  0: GBL_SMI_EN -> 0 = No SMI# will be generated by ICH. */
 	val32 &= 0xffffdffe;
-	outl(val32, SMI_EN);
+	outl(val32, smires->start);
 }
 
-static void broken_bios_stop(unsigned long acpibase)
+static void broken_bios_stop(struct resource *smires)
 {
 	unsigned long val32;
 
-	val32 = inl(SMI_EN);
+	val32 = inl(smires->start);
 	/* Bit 13: TCO_EN     -> 1 = Enables TCO logic generating an SMI#
 	   Bit  0: GBL_SMI_EN -> 1 = Turn global SMI on again. */
 	val32 |= 0x00002001;
-	outl(val32, SMI_EN);
+	outl(val32, smires->start);
 }
 
 /*
  *	Generic Support Functions
  */
 
-void iTCO_vendor_pre_start(unsigned long acpibase,
+void iTCO_vendor_pre_start(struct resource *smires,
 			   unsigned int heartbeat)
 {
 	switch (vendorsupport) {
 	case SUPERMICRO_OLD_BOARD:
-		supermicro_old_pre_start(acpibase);
+		supermicro_old_pre_start(smires);
 		break;
 	case SUPERMICRO_NEW_BOARD:
 		supermicro_new_pre_start(heartbeat);
 		break;
 	case BROKEN_BIOS:
-		broken_bios_start(acpibase);
+		broken_bios_start(smires);
 		break;
 	}
 }
 EXPORT_SYMBOL(iTCO_vendor_pre_start);
 
-void iTCO_vendor_pre_stop(unsigned long acpibase)
+void iTCO_vendor_pre_stop(struct resource *smires)
 {
 	switch (vendorsupport) {
 	case SUPERMICRO_OLD_BOARD:
-		supermicro_old_pre_stop(acpibase);
+		supermicro_old_pre_stop(smires);
 		break;
 	case SUPERMICRO_NEW_BOARD:
 		supermicro_new_pre_stop();
 		break;
 	case BROKEN_BIOS:
-		broken_bios_stop(acpibase);
+		broken_bios_stop(smires);
 		break;
 	}
 }
 EXPORT_SYMBOL(iTCO_vendor_pre_stop);
 
-void iTCO_vendor_pre_keepalive(unsigned long acpibase, unsigned int heartbeat)
+void iTCO_vendor_pre_keepalive(struct resource *smires, unsigned int heartbeat)
 {
 	if (vendorsupport == SUPERMICRO_NEW_BOARD)
 		supermicro_new_pre_set_heartbeat(heartbeat);
diff --git a/drivers/watchdog/iTCO_wdt.c b/drivers/watchdog/iTCO_wdt.c
index 9fecb95645a3..741528b032e2 100644
--- a/drivers/watchdog/iTCO_wdt.c
+++ b/drivers/watchdog/iTCO_wdt.c
@@ -66,316 +66,16 @@
 #include <linux/spinlock.h>		/* For spin_lock/spin_unlock/... */
 #include <linux/uaccess.h>		/* For copy_to_user/put_user/... */
 #include <linux/io.h>			/* For inb/outb/... */
+#include <linux/mfd/core.h>
+#include <linux/mfd/lpc_ich.h>
 
 #include "iTCO_vendor.h"
 
-/* TCO related info */
-enum iTCO_chipsets {
-	TCO_ICH = 0,	/* ICH */
-	TCO_ICH0,	/* ICH0 */
-	TCO_ICH2,	/* ICH2 */
-	TCO_ICH2M,	/* ICH2-M */
-	TCO_ICH3,	/* ICH3-S */
-	TCO_ICH3M,	/* ICH3-M */
-	TCO_ICH4,	/* ICH4 */
-	TCO_ICH4M,	/* ICH4-M */
-	TCO_CICH,	/* C-ICH */
-	TCO_ICH5,	/* ICH5 & ICH5R */
-	TCO_6300ESB,	/* 6300ESB */
-	TCO_ICH6,	/* ICH6 & ICH6R */
-	TCO_ICH6M,	/* ICH6-M */
-	TCO_ICH6W,	/* ICH6W & ICH6RW */
-	TCO_631XESB,	/* 631xESB/632xESB */
-	TCO_ICH7,	/* ICH7 & ICH7R */
-	TCO_ICH7DH,	/* ICH7DH */
-	TCO_ICH7M,	/* ICH7-M & ICH7-U */
-	TCO_ICH7MDH,	/* ICH7-M DH */
-	TCO_NM10,	/* NM10 */
-	TCO_ICH8,	/* ICH8 & ICH8R */
-	TCO_ICH8DH,	/* ICH8DH */
-	TCO_ICH8DO,	/* ICH8DO */
-	TCO_ICH8M,	/* ICH8M */
-	TCO_ICH8ME,	/* ICH8M-E */
-	TCO_ICH9,	/* ICH9 */
-	TCO_ICH9R,	/* ICH9R */
-	TCO_ICH9DH,	/* ICH9DH */
-	TCO_ICH9DO,	/* ICH9DO */
-	TCO_ICH9M,	/* ICH9M */
-	TCO_ICH9ME,	/* ICH9M-E */
-	TCO_ICH10,	/* ICH10 */
-	TCO_ICH10R,	/* ICH10R */
-	TCO_ICH10D,	/* ICH10D */
-	TCO_ICH10DO,	/* ICH10DO */
-	TCO_PCH,	/* PCH Desktop Full Featured */
-	TCO_PCHM,	/* PCH Mobile Full Featured */
-	TCO_P55,	/* P55 */
-	TCO_PM55,	/* PM55 */
-	TCO_H55,	/* H55 */
-	TCO_QM57,	/* QM57 */
-	TCO_H57,	/* H57 */
-	TCO_HM55,	/* HM55 */
-	TCO_Q57,	/* Q57 */
-	TCO_HM57,	/* HM57 */
-	TCO_PCHMSFF,	/* PCH Mobile SFF Full Featured */
-	TCO_QS57,	/* QS57 */
-	TCO_3400,	/* 3400 */
-	TCO_3420,	/* 3420 */
-	TCO_3450,	/* 3450 */
-	TCO_EP80579,	/* EP80579 */
-	TCO_CPT,	/* Cougar Point */
-	TCO_CPTD,	/* Cougar Point Desktop */
-	TCO_CPTM,	/* Cougar Point Mobile */
-	TCO_PBG,	/* Patsburg */
-	TCO_DH89XXCC,	/* DH89xxCC */
-	TCO_PPT,	/* Panther Point */
-	TCO_LPT,	/* Lynx Point */
-};
-
-static struct {
-	char *name;
-	unsigned int iTCO_version;
-} iTCO_chipset_info[] __devinitdata = {
-	{"ICH", 1},
-	{"ICH0", 1},
-	{"ICH2", 1},
-	{"ICH2-M", 1},
-	{"ICH3-S", 1},
-	{"ICH3-M", 1},
-	{"ICH4", 1},
-	{"ICH4-M", 1},
-	{"C-ICH", 1},
-	{"ICH5 or ICH5R", 1},
-	{"6300ESB", 1},
-	{"ICH6 or ICH6R", 2},
-	{"ICH6-M", 2},
-	{"ICH6W or ICH6RW", 2},
-	{"631xESB/632xESB", 2},
-	{"ICH7 or ICH7R", 2},
-	{"ICH7DH", 2},
-	{"ICH7-M or ICH7-U", 2},
-	{"ICH7-M DH", 2},
-	{"NM10", 2},
-	{"ICH8 or ICH8R", 2},
-	{"ICH8DH", 2},
-	{"ICH8DO", 2},
-	{"ICH8M", 2},
-	{"ICH8M-E", 2},
-	{"ICH9", 2},
-	{"ICH9R", 2},
-	{"ICH9DH", 2},
-	{"ICH9DO", 2},
-	{"ICH9M", 2},
-	{"ICH9M-E", 2},
-	{"ICH10", 2},
-	{"ICH10R", 2},
-	{"ICH10D", 2},
-	{"ICH10DO", 2},
-	{"PCH Desktop Full Featured", 2},
-	{"PCH Mobile Full Featured", 2},
-	{"P55", 2},
-	{"PM55", 2},
-	{"H55", 2},
-	{"QM57", 2},
-	{"H57", 2},
-	{"HM55", 2},
-	{"Q57", 2},
-	{"HM57", 2},
-	{"PCH Mobile SFF Full Featured", 2},
-	{"QS57", 2},
-	{"3400", 2},
-	{"3420", 2},
-	{"3450", 2},
-	{"EP80579", 2},
-	{"Cougar Point", 2},
-	{"Cougar Point Desktop", 2},
-	{"Cougar Point Mobile", 2},
-	{"Patsburg", 2},
-	{"DH89xxCC", 2},
-	{"Panther Point", 2},
-	{"Lynx Point", 2},
-	{NULL, 0}
-};
-
-/*
- * This data only exists for exporting the supported PCI ids
- * via MODULE_DEVICE_TABLE.  We do not actually register a
- * pci_driver, because the I/O Controller Hub has also other
- * functions that probably will be registered by other drivers.
- */
-static DEFINE_PCI_DEVICE_TABLE(iTCO_wdt_pci_tbl) = {
-	{ PCI_VDEVICE(INTEL, 0x2410), TCO_ICH},
-	{ PCI_VDEVICE(INTEL, 0x2420), TCO_ICH0},
-	{ PCI_VDEVICE(INTEL, 0x2440), TCO_ICH2},
-	{ PCI_VDEVICE(INTEL, 0x244c), TCO_ICH2M},
-	{ PCI_VDEVICE(INTEL, 0x2480), TCO_ICH3},
-	{ PCI_VDEVICE(INTEL, 0x248c), TCO_ICH3M},
-	{ PCI_VDEVICE(INTEL, 0x24c0), TCO_ICH4},
-	{ PCI_VDEVICE(INTEL, 0x24cc), TCO_ICH4M},
-	{ PCI_VDEVICE(INTEL, 0x2450), TCO_CICH},
-	{ PCI_VDEVICE(INTEL, 0x24d0), TCO_ICH5},
-	{ PCI_VDEVICE(INTEL, 0x25a1), TCO_6300ESB},
-	{ PCI_VDEVICE(INTEL, 0x2640), TCO_ICH6},
-	{ PCI_VDEVICE(INTEL, 0x2641), TCO_ICH6M},
-	{ PCI_VDEVICE(INTEL, 0x2642), TCO_ICH6W},
-	{ PCI_VDEVICE(INTEL, 0x2670), TCO_631XESB},
-	{ PCI_VDEVICE(INTEL, 0x2671), TCO_631XESB},
-	{ PCI_VDEVICE(INTEL, 0x2672), TCO_631XESB},
-	{ PCI_VDEVICE(INTEL, 0x2673), TCO_631XESB},
-	{ PCI_VDEVICE(INTEL, 0x2674), TCO_631XESB},
-	{ PCI_VDEVICE(INTEL, 0x2675), TCO_631XESB},
-	{ PCI_VDEVICE(INTEL, 0x2676), TCO_631XESB},
-	{ PCI_VDEVICE(INTEL, 0x2677), TCO_631XESB},
-	{ PCI_VDEVICE(INTEL, 0x2678), TCO_631XESB},
-	{ PCI_VDEVICE(INTEL, 0x2679), TCO_631XESB},
-	{ PCI_VDEVICE(INTEL, 0x267a), TCO_631XESB},
-	{ PCI_VDEVICE(INTEL, 0x267b), TCO_631XESB},
-	{ PCI_VDEVICE(INTEL, 0x267c), TCO_631XESB},
-	{ PCI_VDEVICE(INTEL, 0x267d), TCO_631XESB},
-	{ PCI_VDEVICE(INTEL, 0x267e), TCO_631XESB},
-	{ PCI_VDEVICE(INTEL, 0x267f), TCO_631XESB},
-	{ PCI_VDEVICE(INTEL, 0x27b8), TCO_ICH7},
-	{ PCI_VDEVICE(INTEL, 0x27b0), TCO_ICH7DH},
-	{ PCI_VDEVICE(INTEL, 0x27b9), TCO_ICH7M},
-	{ PCI_VDEVICE(INTEL, 0x27bd), TCO_ICH7MDH},
-	{ PCI_VDEVICE(INTEL, 0x27bc), TCO_NM10},
-	{ PCI_VDEVICE(INTEL, 0x2810), TCO_ICH8},
-	{ PCI_VDEVICE(INTEL, 0x2812), TCO_ICH8DH},
-	{ PCI_VDEVICE(INTEL, 0x2814), TCO_ICH8DO},
-	{ PCI_VDEVICE(INTEL, 0x2815), TCO_ICH8M},
-	{ PCI_VDEVICE(INTEL, 0x2811), TCO_ICH8ME},
-	{ PCI_VDEVICE(INTEL, 0x2918), TCO_ICH9},
-	{ PCI_VDEVICE(INTEL, 0x2916), TCO_ICH9R},
-	{ PCI_VDEVICE(INTEL, 0x2912), TCO_ICH9DH},
-	{ PCI_VDEVICE(INTEL, 0x2914), TCO_ICH9DO},
-	{ PCI_VDEVICE(INTEL, 0x2919), TCO_ICH9M},
-	{ PCI_VDEVICE(INTEL, 0x2917), TCO_ICH9ME},
-	{ PCI_VDEVICE(INTEL, 0x3a18), TCO_ICH10},
-	{ PCI_VDEVICE(INTEL, 0x3a16), TCO_ICH10R},
-	{ PCI_VDEVICE(INTEL, 0x3a1a), TCO_ICH10D},
-	{ PCI_VDEVICE(INTEL, 0x3a14), TCO_ICH10DO},
-	{ PCI_VDEVICE(INTEL, 0x3b00), TCO_PCH},
-	{ PCI_VDEVICE(INTEL, 0x3b01), TCO_PCHM},
-	{ PCI_VDEVICE(INTEL, 0x3b02), TCO_P55},
-	{ PCI_VDEVICE(INTEL, 0x3b03), TCO_PM55},
-	{ PCI_VDEVICE(INTEL, 0x3b06), TCO_H55},
-	{ PCI_VDEVICE(INTEL, 0x3b07), TCO_QM57},
-	{ PCI_VDEVICE(INTEL, 0x3b08), TCO_H57},
-	{ PCI_VDEVICE(INTEL, 0x3b09), TCO_HM55},
-	{ PCI_VDEVICE(INTEL, 0x3b0a), TCO_Q57},
-	{ PCI_VDEVICE(INTEL, 0x3b0b), TCO_HM57},
-	{ PCI_VDEVICE(INTEL, 0x3b0d), TCO_PCHMSFF},
-	{ PCI_VDEVICE(INTEL, 0x3b0f), TCO_QS57},
-	{ PCI_VDEVICE(INTEL, 0x3b12), TCO_3400},
-	{ PCI_VDEVICE(INTEL, 0x3b14), TCO_3420},
-	{ PCI_VDEVICE(INTEL, 0x3b16), TCO_3450},
-	{ PCI_VDEVICE(INTEL, 0x5031), TCO_EP80579},
-	{ PCI_VDEVICE(INTEL, 0x1c41), TCO_CPT},
-	{ PCI_VDEVICE(INTEL, 0x1c42), TCO_CPTD},
-	{ PCI_VDEVICE(INTEL, 0x1c43), TCO_CPTM},
-	{ PCI_VDEVICE(INTEL, 0x1c44), TCO_CPT},
-	{ PCI_VDEVICE(INTEL, 0x1c45), TCO_CPT},
-	{ PCI_VDEVICE(INTEL, 0x1c46), TCO_CPT},
-	{ PCI_VDEVICE(INTEL, 0x1c47), TCO_CPT},
-	{ PCI_VDEVICE(INTEL, 0x1c48), TCO_CPT},
-	{ PCI_VDEVICE(INTEL, 0x1c49), TCO_CPT},
-	{ PCI_VDEVICE(INTEL, 0x1c4a), TCO_CPT},
-	{ PCI_VDEVICE(INTEL, 0x1c4b), TCO_CPT},
-	{ PCI_VDEVICE(INTEL, 0x1c4c), TCO_CPT},
-	{ PCI_VDEVICE(INTEL, 0x1c4d), TCO_CPT},
-	{ PCI_VDEVICE(INTEL, 0x1c4e), TCO_CPT},
-	{ PCI_VDEVICE(INTEL, 0x1c4f), TCO_CPT},
-	{ PCI_VDEVICE(INTEL, 0x1c50), TCO_CPT},
-	{ PCI_VDEVICE(INTEL, 0x1c51), TCO_CPT},
-	{ PCI_VDEVICE(INTEL, 0x1c52), TCO_CPT},
-	{ PCI_VDEVICE(INTEL, 0x1c53), TCO_CPT},
-	{ PCI_VDEVICE(INTEL, 0x1c54), TCO_CPT},
-	{ PCI_VDEVICE(INTEL, 0x1c55), TCO_CPT},
-	{ PCI_VDEVICE(INTEL, 0x1c56), TCO_CPT},
-	{ PCI_VDEVICE(INTEL, 0x1c57), TCO_CPT},
-	{ PCI_VDEVICE(INTEL, 0x1c58), TCO_CPT},
-	{ PCI_VDEVICE(INTEL, 0x1c59), TCO_CPT},
-	{ PCI_VDEVICE(INTEL, 0x1c5a), TCO_CPT},
-	{ PCI_VDEVICE(INTEL, 0x1c5b), TCO_CPT},
-	{ PCI_VDEVICE(INTEL, 0x1c5c), TCO_CPT},
-	{ PCI_VDEVICE(INTEL, 0x1c5d), TCO_CPT},
-	{ PCI_VDEVICE(INTEL, 0x1c5e), TCO_CPT},
-	{ PCI_VDEVICE(INTEL, 0x1c5f), TCO_CPT},
-	{ PCI_VDEVICE(INTEL, 0x1d40), TCO_PBG},
-	{ PCI_VDEVICE(INTEL, 0x1d41), TCO_PBG},
-	{ PCI_VDEVICE(INTEL, 0x2310), TCO_DH89XXCC},
-	{ PCI_VDEVICE(INTEL, 0x1e40), TCO_PPT},
-	{ PCI_VDEVICE(INTEL, 0x1e41), TCO_PPT},
-	{ PCI_VDEVICE(INTEL, 0x1e42), TCO_PPT},
-	{ PCI_VDEVICE(INTEL, 0x1e43), TCO_PPT},
-	{ PCI_VDEVICE(INTEL, 0x1e44), TCO_PPT},
-	{ PCI_VDEVICE(INTEL, 0x1e45), TCO_PPT},
-	{ PCI_VDEVICE(INTEL, 0x1e46), TCO_PPT},
-	{ PCI_VDEVICE(INTEL, 0x1e47), TCO_PPT},
-	{ PCI_VDEVICE(INTEL, 0x1e48), TCO_PPT},
-	{ PCI_VDEVICE(INTEL, 0x1e49), TCO_PPT},
-	{ PCI_VDEVICE(INTEL, 0x1e4a), TCO_PPT},
-	{ PCI_VDEVICE(INTEL, 0x1e4b), TCO_PPT},
-	{ PCI_VDEVICE(INTEL, 0x1e4c), TCO_PPT},
-	{ PCI_VDEVICE(INTEL, 0x1e4d), TCO_PPT},
-	{ PCI_VDEVICE(INTEL, 0x1e4e), TCO_PPT},
-	{ PCI_VDEVICE(INTEL, 0x1e4f), TCO_PPT},
-	{ PCI_VDEVICE(INTEL, 0x1e50), TCO_PPT},
-	{ PCI_VDEVICE(INTEL, 0x1e51), TCO_PPT},
-	{ PCI_VDEVICE(INTEL, 0x1e52), TCO_PPT},
-	{ PCI_VDEVICE(INTEL, 0x1e53), TCO_PPT},
-	{ PCI_VDEVICE(INTEL, 0x1e54), TCO_PPT},
-	{ PCI_VDEVICE(INTEL, 0x1e55), TCO_PPT},
-	{ PCI_VDEVICE(INTEL, 0x1e56), TCO_PPT},
-	{ PCI_VDEVICE(INTEL, 0x1e57), TCO_PPT},
-	{ PCI_VDEVICE(INTEL, 0x1e58), TCO_PPT},
-	{ PCI_VDEVICE(INTEL, 0x1e59), TCO_PPT},
-	{ PCI_VDEVICE(INTEL, 0x1e5a), TCO_PPT},
-	{ PCI_VDEVICE(INTEL, 0x1e5b), TCO_PPT},
-	{ PCI_VDEVICE(INTEL, 0x1e5c), TCO_PPT},
-	{ PCI_VDEVICE(INTEL, 0x1e5d), TCO_PPT},
-	{ PCI_VDEVICE(INTEL, 0x1e5e), TCO_PPT},
-	{ PCI_VDEVICE(INTEL, 0x1e5f), TCO_PPT},
-	{ PCI_VDEVICE(INTEL, 0x8c40), TCO_LPT},
-	{ PCI_VDEVICE(INTEL, 0x8c41), TCO_LPT},
-	{ PCI_VDEVICE(INTEL, 0x8c42), TCO_LPT},
-	{ PCI_VDEVICE(INTEL, 0x8c43), TCO_LPT},
-	{ PCI_VDEVICE(INTEL, 0x8c44), TCO_LPT},
-	{ PCI_VDEVICE(INTEL, 0x8c45), TCO_LPT},
-	{ PCI_VDEVICE(INTEL, 0x8c46), TCO_LPT},
-	{ PCI_VDEVICE(INTEL, 0x8c47), TCO_LPT},
-	{ PCI_VDEVICE(INTEL, 0x8c48), TCO_LPT},
-	{ PCI_VDEVICE(INTEL, 0x8c49), TCO_LPT},
-	{ PCI_VDEVICE(INTEL, 0x8c4a), TCO_LPT},
-	{ PCI_VDEVICE(INTEL, 0x8c4b), TCO_LPT},
-	{ PCI_VDEVICE(INTEL, 0x8c4c), TCO_LPT},
-	{ PCI_VDEVICE(INTEL, 0x8c4d), TCO_LPT},
-	{ PCI_VDEVICE(INTEL, 0x8c4e), TCO_LPT},
-	{ PCI_VDEVICE(INTEL, 0x8c4f), TCO_LPT},
-	{ PCI_VDEVICE(INTEL, 0x8c50), TCO_LPT},
-	{ PCI_VDEVICE(INTEL, 0x8c51), TCO_LPT},
-	{ PCI_VDEVICE(INTEL, 0x8c52), TCO_LPT},
-	{ PCI_VDEVICE(INTEL, 0x8c53), TCO_LPT},
-	{ PCI_VDEVICE(INTEL, 0x8c54), TCO_LPT},
-	{ PCI_VDEVICE(INTEL, 0x8c55), TCO_LPT},
-	{ PCI_VDEVICE(INTEL, 0x8c56), TCO_LPT},
-	{ PCI_VDEVICE(INTEL, 0x8c57), TCO_LPT},
-	{ PCI_VDEVICE(INTEL, 0x8c58), TCO_LPT},
-	{ PCI_VDEVICE(INTEL, 0x8c59), TCO_LPT},
-	{ PCI_VDEVICE(INTEL, 0x8c5a), TCO_LPT},
-	{ PCI_VDEVICE(INTEL, 0x8c5b), TCO_LPT},
-	{ PCI_VDEVICE(INTEL, 0x8c5c), TCO_LPT},
-	{ PCI_VDEVICE(INTEL, 0x8c5d), TCO_LPT},
-	{ PCI_VDEVICE(INTEL, 0x8c5e), TCO_LPT},
-	{ PCI_VDEVICE(INTEL, 0x8c5f), TCO_LPT},
-	{ 0, },			/* End of list */
-};
-MODULE_DEVICE_TABLE(pci, iTCO_wdt_pci_tbl);
-
 /* Address definitions for the TCO */
 /* TCO base address */
-#define TCOBASE		(iTCO_wdt_private.ACPIBASE + 0x60)
+#define TCOBASE		(iTCO_wdt_private.tco_res->start)
 /* SMI Control and Enable Register */
-#define SMI_EN		(iTCO_wdt_private.ACPIBASE + 0x30)
+#define SMI_EN		(iTCO_wdt_private.smi_res->start)
 
 #define TCO_RLD		(TCOBASE + 0x00) /* TCO Timer Reload and Curr. Value */
 #define TCOv1_TMR	(TCOBASE + 0x01) /* TCOv1 Timer Initial Value	*/
@@ -393,19 +93,18 @@ static char expect_release;
 static struct {		/* this is private data for the iTCO_wdt device */
 	/* TCO version/generation */
 	unsigned int iTCO_version;
-	/* The device's ACPIBASE address (TCOBASE = ACPIBASE+0x60) */
-	unsigned long ACPIBASE;
+	struct resource *tco_res;
+	struct resource *smi_res;
+	struct resource *gcs_res;
 	/* NO_REBOOT flag is Memory-Mapped GCS register bit 5 (TCO version 2)*/
 	unsigned long __iomem *gcs;
 	/* the lock for io operations */
 	spinlock_t io_lock;
+	struct platform_device *dev;
 	/* the PCI-device */
 	struct pci_dev *pdev;
 } iTCO_wdt_private;
 
-/* the watchdog platform device */
-static struct platform_device *iTCO_wdt_platform_device;
-
 /* module parameters */
 #define WATCHDOG_HEARTBEAT 30	/* 30 sec default heartbeat */
 static int heartbeat = WATCHDOG_HEARTBEAT;  /* in seconds */
@@ -485,7 +184,7 @@ static int iTCO_wdt_start(void)
 
 	spin_lock(&iTCO_wdt_private.io_lock);
 
-	iTCO_vendor_pre_start(iTCO_wdt_private.ACPIBASE, heartbeat);
+	iTCO_vendor_pre_start(iTCO_wdt_private.smi_res, heartbeat);
 
 	/* disable chipset's NO_REBOOT bit */
 	if (iTCO_wdt_unset_NO_REBOOT_bit()) {
@@ -519,7 +218,7 @@ static int iTCO_wdt_stop(void)
 
 	spin_lock(&iTCO_wdt_private.io_lock);
 
-	iTCO_vendor_pre_stop(iTCO_wdt_private.ACPIBASE);
+	iTCO_vendor_pre_stop(iTCO_wdt_private.smi_res);
 
 	/* Bit 11: TCO Timer Halt -> 1 = The TCO timer is disabled */
 	val = inw(TCO1_CNT);
@@ -541,7 +240,7 @@ static int iTCO_wdt_keepalive(void)
 {
 	spin_lock(&iTCO_wdt_private.io_lock);
 
-	iTCO_vendor_pre_keepalive(iTCO_wdt_private.ACPIBASE, heartbeat);
+	iTCO_vendor_pre_keepalive(iTCO_wdt_private.smi_res, heartbeat);
 
 	/* Reload the timer by writing to the TCO Timer Counter register */
 	if (iTCO_wdt_private.iTCO_version == 2)
@@ -786,83 +485,120 @@ static struct miscdevice iTCO_wdt_miscdev = {
  *	Init & exit routines
  */
 
-static int __devinit iTCO_wdt_init(struct pci_dev *pdev,
-		const struct pci_device_id *ent, struct platform_device *dev)
+static void __devexit iTCO_wdt_cleanup(void)
+{
+	/* Stop the timer before we leave */
+	if (!nowayout)
+		iTCO_wdt_stop();
+
+	/* Deregister */
+	misc_deregister(&iTCO_wdt_miscdev);
+
+	/* release resources */
+	release_region(iTCO_wdt_private.tco_res->start,
+			resource_size(iTCO_wdt_private.tco_res));
+	release_region(iTCO_wdt_private.smi_res->start,
+			resource_size(iTCO_wdt_private.smi_res));
+	if (iTCO_wdt_private.iTCO_version == 2) {
+		iounmap(iTCO_wdt_private.gcs);
+		release_mem_region(iTCO_wdt_private.gcs_res->start,
+				resource_size(iTCO_wdt_private.gcs_res));
+	}
+
+	iTCO_wdt_private.tco_res = NULL;
+	iTCO_wdt_private.smi_res = NULL;
+	iTCO_wdt_private.gcs_res = NULL;
+	iTCO_wdt_private.gcs = NULL;
+}
+
+static int __devinit iTCO_wdt_probe(struct platform_device *dev)
 {
-	int ret;
-	u32 base_address;
-	unsigned long RCBA;
+	int ret = -ENODEV;
 	unsigned long val32;
+	struct lpc_ich_info *ich_info = dev->dev.platform_data;
+
+	if (!ich_info)
+		goto out;
+
+	spin_lock_init(&iTCO_wdt_private.io_lock);
+
+	iTCO_wdt_private.tco_res =
+		platform_get_resource(dev, IORESOURCE_IO, ICH_RES_IO_TCO);
+	if (!iTCO_wdt_private.tco_res)
+		goto out;
+
+	iTCO_wdt_private.smi_res =
+		platform_get_resource(dev, IORESOURCE_IO, ICH_RES_IO_SMI);
+	if (!iTCO_wdt_private.smi_res)
+		goto out;
+
+	iTCO_wdt_private.iTCO_version = ich_info->iTCO_version;
+	iTCO_wdt_private.dev = dev;
+	iTCO_wdt_private.pdev = to_pci_dev(dev->dev.parent);
 
 	/*
-	 *      Find the ACPI/PM base I/O address which is the base
-	 *      for the TCO registers (TCOBASE=ACPIBASE + 0x60)
-	 *      ACPIBASE is bits [15:7] from 0x40-0x43
+	 * Get the Memory-Mapped GCS register, we need it for the
+	 * NO_REBOOT flag (TCO v2).
 	 */
-	pci_read_config_dword(pdev, 0x40, &base_address);
-	base_address &= 0x0000ff80;
-	if (base_address == 0x00000000) {
-		/* Something's wrong here, ACPIBASE has to be set */
-		pr_err("failed to get TCOBASE address, device disabled by hardware/BIOS\n");
-		return -ENODEV;
-	}
-	iTCO_wdt_private.iTCO_version =
-			iTCO_chipset_info[ent->driver_data].iTCO_version;
-	iTCO_wdt_private.ACPIBASE = base_address;
-	iTCO_wdt_private.pdev = pdev;
-
-	/* Get the Memory-Mapped GCS register, we need it for the
-	   NO_REBOOT flag (TCO v2). To get access to it you have to
-	   read RCBA from PCI Config space 0xf0 and use it as base.
-	   GCS = RCBA + ICH6_GCS(0x3410). */
 	if (iTCO_wdt_private.iTCO_version == 2) {
-		pci_read_config_dword(pdev, 0xf0, &base_address);
-		if ((base_address & 1) == 0) {
-			pr_err("RCBA is disabled by hardware/BIOS, device disabled\n");
-			ret = -ENODEV;
+		iTCO_wdt_private.gcs_res = platform_get_resource(dev,
+							IORESOURCE_MEM,
+							ICH_RES_MEM_GCS);
+
+		if (!iTCO_wdt_private.gcs_res)
+			goto out;
+
+		if (!request_mem_region(iTCO_wdt_private.gcs_res->start,
+			resource_size(iTCO_wdt_private.gcs_res), dev->name)) {
+			ret = -EBUSY;
 			goto out;
 		}
-		RCBA = base_address & 0xffffc000;
-		iTCO_wdt_private.gcs = ioremap((RCBA + 0x3410), 4);
+		iTCO_wdt_private.gcs = ioremap(iTCO_wdt_private.gcs_res->start,
+			resource_size(iTCO_wdt_private.gcs_res));
+		if (!iTCO_wdt_private.gcs) {
+			ret = -EIO;
+			goto unreg_gcs;
+		}
 	}
 
 	/* Check chipset's NO_REBOOT bit */
 	if (iTCO_wdt_unset_NO_REBOOT_bit() && iTCO_vendor_check_noreboot_on()) {
 		pr_info("unable to reset NO_REBOOT flag, device disabled by hardware/BIOS\n");
 		ret = -ENODEV;	/* Cannot reset NO_REBOOT bit */
-		goto out_unmap;
+		goto unmap_gcs;
 	}
 
 	/* Set the NO_REBOOT bit to prevent later reboots, just for sure */
 	iTCO_wdt_set_NO_REBOOT_bit();
 
 	/* The TCO logic uses the TCO_EN bit in the SMI_EN register */
-	if (!request_region(SMI_EN, 4, "iTCO_wdt")) {
-		pr_err("I/O address 0x%04lx already in use, device disabled\n",
+	if (!request_region(iTCO_wdt_private.smi_res->start,
+			resource_size(iTCO_wdt_private.smi_res), dev->name)) {
+		pr_err("I/O address 0x%04llx already in use, device disabled\n",
 		       SMI_EN);
-		ret = -EIO;
-		goto out_unmap;
+		ret = -EBUSY;
+		goto unmap_gcs;
 	}
 	if (turn_SMI_watchdog_clear_off >= iTCO_wdt_private.iTCO_version) {
-		/* Bit 13: TCO_EN -> 0 = Disables TCO logic generating an SMI# */
+		/*
+		 * Bit 13: TCO_EN -> 0
+		 * Disables TCO logic generating an SMI#
+		 */
 		val32 = inl(SMI_EN);
 		val32 &= 0xffffdfff;	/* Turn off SMI clearing watchdog */
 		outl(val32, SMI_EN);
 	}
 
-	/* The TCO I/O registers reside in a 32-byte range pointed to
-	   by the TCOBASE value */
-	if (!request_region(TCOBASE, 0x20, "iTCO_wdt")) {
-		pr_err("I/O address 0x%04lx already in use, device disabled\n",
+	if (!request_region(iTCO_wdt_private.tco_res->start,
+			resource_size(iTCO_wdt_private.tco_res), dev->name)) {
+		pr_err("I/O address 0x%04llx already in use, device disabled\n",
 		       TCOBASE);
-		ret = -EIO;
-		goto unreg_smi_en;
+		ret = -EBUSY;
+		goto unreg_smi;
 	}
 
-	pr_info("Found a %s TCO device (Version=%d, TCOBASE=0x%04lx)\n",
-		iTCO_chipset_info[ent->driver_data].name,
-		iTCO_chipset_info[ent->driver_data].iTCO_version,
-		TCOBASE);
+	pr_info("Found a %s TCO device (Version=%d, TCOBASE=0x%04llx)\n",
+		ich_info->name, ich_info->iTCO_version, TCOBASE);
 
 	/* Clear out the (probably old) status */
 	outw(0x0008, TCO1_STS);	/* Clear the Time Out Status bit */
@@ -883,7 +619,7 @@ static int __devinit iTCO_wdt_init(struct pci_dev *pdev,
 	if (ret != 0) {
 		pr_err("cannot register miscdev on minor=%d (err=%d)\n",
 		       WATCHDOG_MINOR, ret);
-		goto unreg_region;
+		goto unreg_tco;
 	}
 
 	pr_info("initialized. heartbeat=%d sec (nowayout=%d)\n",
@@ -891,62 +627,31 @@ static int __devinit iTCO_wdt_init(struct pci_dev *pdev,
 
 	return 0;
 
-unreg_region:
-	release_region(TCOBASE, 0x20);
-unreg_smi_en:
-	release_region(SMI_EN, 4);
-out_unmap:
+unreg_tco:
+	release_region(iTCO_wdt_private.tco_res->start,
+			resource_size(iTCO_wdt_private.tco_res));
+unreg_smi:
+	release_region(iTCO_wdt_private.smi_res->start,
+			resource_size(iTCO_wdt_private.smi_res));
+unmap_gcs:
 	if (iTCO_wdt_private.iTCO_version == 2)
 		iounmap(iTCO_wdt_private.gcs);
-out:
-	iTCO_wdt_private.ACPIBASE = 0;
-	return ret;
-}
-
-static void __devexit iTCO_wdt_cleanup(void)
-{
-	/* Stop the timer before we leave */
-	if (!nowayout)
-		iTCO_wdt_stop();
-
-	/* Deregister */
-	misc_deregister(&iTCO_wdt_miscdev);
-	release_region(TCOBASE, 0x20);
-	release_region(SMI_EN, 4);
+unreg_gcs:
 	if (iTCO_wdt_private.iTCO_version == 2)
-		iounmap(iTCO_wdt_private.gcs);
-	pci_dev_put(iTCO_wdt_private.pdev);
-	iTCO_wdt_private.ACPIBASE = 0;
-}
-
-static int __devinit iTCO_wdt_probe(struct platform_device *dev)
-{
-	int ret = -ENODEV;
-	int found = 0;
-	struct pci_dev *pdev = NULL;
-	const struct pci_device_id *ent;
-
-	spin_lock_init(&iTCO_wdt_private.io_lock);
-
-	for_each_pci_dev(pdev) {
-		ent = pci_match_id(iTCO_wdt_pci_tbl, pdev);
-		if (ent) {
-			found++;
-			ret = iTCO_wdt_init(pdev, ent, dev);
-			if (!ret)
-				break;
-		}
-	}
-
-	if (!found)
-		pr_info("No device detected\n");
+		release_mem_region(iTCO_wdt_private.gcs_res->start,
+				resource_size(iTCO_wdt_private.gcs_res));
+out:
+	iTCO_wdt_private.tco_res = NULL;
+	iTCO_wdt_private.smi_res = NULL;
+	iTCO_wdt_private.gcs_res = NULL;
+	iTCO_wdt_private.gcs = NULL;
 
 	return ret;
 }
 
 static int __devexit iTCO_wdt_remove(struct platform_device *dev)
 {
-	if (iTCO_wdt_private.ACPIBASE)
+	if (iTCO_wdt_private.tco_res || iTCO_wdt_private.smi_res)
 		iTCO_wdt_cleanup();
 
 	return 0;
@@ -977,23 +682,11 @@ static int __init iTCO_wdt_init_module(void)
 	if (err)
 		return err;
 
-	iTCO_wdt_platform_device = platform_device_register_simple(DRV_NAME,
-								-1, NULL, 0);
-	if (IS_ERR(iTCO_wdt_platform_device)) {
-		err = PTR_ERR(iTCO_wdt_platform_device);
-		goto unreg_platform_driver;
-	}
-
 	return 0;
-
-unreg_platform_driver:
-	platform_driver_unregister(&iTCO_wdt_driver);
-	return err;
 }
 
 static void __exit iTCO_wdt_cleanup_module(void)
 {
-	platform_device_unregister(iTCO_wdt_platform_device);
 	platform_driver_unregister(&iTCO_wdt_driver);
 	pr_info("Watchdog Module Unloaded\n");
 }
diff --git a/fs/bad_inode.c b/fs/bad_inode.c
index 37268c5bb98b..1b35d6bd06b0 100644
--- a/fs/bad_inode.c
+++ b/fs/bad_inode.c
@@ -292,7 +292,6 @@ static const struct inode_operations bad_inode_ops =
 	.getxattr	= bad_inode_getxattr,
 	.listxattr	= bad_inode_listxattr,
 	.removexattr	= bad_inode_removexattr,
-	/* truncate_range returns void */
 };
 
 
diff --git a/fs/exofs/Kbuild b/fs/exofs/Kbuild
index 352ba149d23e..389ba8312d5d 100644
--- a/fs/exofs/Kbuild
+++ b/fs/exofs/Kbuild
@@ -16,5 +16,5 @@
 libore-y := ore.o ore_raid.o
 obj-$(CONFIG_ORE) += libore.o
 
-exofs-y := inode.o file.o symlink.o namei.o dir.o super.o
+exofs-y := inode.o file.o symlink.o namei.o dir.o super.o sys.o
 obj-$(CONFIG_EXOFS_FS) += exofs.o
diff --git a/fs/exofs/exofs.h b/fs/exofs/exofs.h
index ca9d49665ef6..fffe86fd7a42 100644
--- a/fs/exofs/exofs.h
+++ b/fs/exofs/exofs.h
@@ -56,6 +56,9 @@
 struct exofs_dev {
 	struct ore_dev ored;
 	unsigned did;
+	unsigned urilen;
+	uint8_t *uri;
+	struct kobject ed_kobj;
 };
 /*
  * our extension to the in-memory superblock
@@ -73,6 +76,7 @@ struct exofs_sb_info {
 	struct ore_layout	layout;		/* Default files layout       */
 	struct ore_comp one_comp;		/* id & cred of partition id=0*/
 	struct ore_components oc;		/* comps for the partition    */
+	struct kobject	s_kobj;			/* holds per-sbi kobject      */
 };
 
 /*
@@ -176,6 +180,16 @@ void exofs_make_credential(u8 cred_a[OSD_CAP_LEN],
 			   const struct osd_obj_id *obj);
 int exofs_sbi_write_stats(struct exofs_sb_info *sbi);
 
+/* sys.c                 */
+int exofs_sysfs_init(void);
+void exofs_sysfs_uninit(void);
+int exofs_sysfs_sb_add(struct exofs_sb_info *sbi,
+		       struct exofs_dt_device_info *dt_dev);
+void exofs_sysfs_sb_del(struct exofs_sb_info *sbi);
+int exofs_sysfs_odev_add(struct exofs_dev *edev,
+			 struct exofs_sb_info *sbi);
+void exofs_sysfs_dbg_print(void);
+
 /*********************
  * operation vectors *
  *********************/
diff --git a/fs/exofs/super.c b/fs/exofs/super.c
index 735ca06430ac..433783624d10 100644
--- a/fs/exofs/super.c
+++ b/fs/exofs/super.c
@@ -472,6 +472,7 @@ static void exofs_put_super(struct super_block *sb)
 	_exofs_print_device("Unmounting", NULL, ore_comp_dev(&sbi->oc, 0),
 			    sbi->one_comp.obj.partition);
 
+	exofs_sysfs_sb_del(sbi);
 	bdi_destroy(&sbi->bdi);
 	exofs_free_sbi(sbi);
 	sb->s_fs_info = NULL;
@@ -632,6 +633,12 @@ static int exofs_read_lookup_dev_table(struct exofs_sb_info *sbi,
 	memcpy(&sbi->oc.ods[numdevs], &sbi->oc.ods[0],
 		(numdevs - 1) * sizeof(sbi->oc.ods[0]));
 
+	/* create sysfs subdir under which we put the device table
+	 * And cluster layout. A Superblock is identified by the string:
+	 *	"dev[0].osdname"_"pid"
+	 */
+	exofs_sysfs_sb_add(sbi, &dt->dt_dev_table[0]);
+
 	for (i = 0; i < numdevs; i++) {
 		struct exofs_fscb fscb;
 		struct osd_dev_info odi;
@@ -657,6 +664,7 @@ static int exofs_read_lookup_dev_table(struct exofs_sb_info *sbi,
 			eds[i].ored.od = fscb_od;
 			++sbi->oc.numdevs;
 			fscb_od = NULL;
+			exofs_sysfs_odev_add(&eds[i], sbi);
 			continue;
 		}
 
@@ -682,6 +690,7 @@ static int exofs_read_lookup_dev_table(struct exofs_sb_info *sbi,
 				  odi.osdname);
 			goto out;
 		}
+		exofs_sysfs_odev_add(&eds[i], sbi);
 
 		/* TODO: verify other information is correct and FS-uuid
 		 *	 matches. Benny what did you say about device table
@@ -745,7 +754,6 @@ static int exofs_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->one_comp.obj.partition = opts->pid;
 	sbi->one_comp.obj.id = 0;
 	exofs_make_credential(sbi->one_comp.cred, &sbi->one_comp.obj);
-	sbi->oc.numdevs = 1;
 	sbi->oc.single_comp = EC_SINGLE_COMP;
 	sbi->oc.comps = &sbi->one_comp;
 
@@ -804,6 +812,7 @@ static int exofs_fill_super(struct super_block *sb, void *data, int silent)
 			goto free_sbi;
 
 		ore_comp_set_dev(&sbi->oc, 0, od);
+		sbi->oc.numdevs = 1;
 	}
 
 	__sbi_read_stats(sbi);
@@ -844,6 +853,7 @@ static int exofs_fill_super(struct super_block *sb, void *data, int silent)
 		goto free_sbi;
 	}
 
+	exofs_sysfs_dbg_print();
 	_exofs_print_device("Mounting", opts->dev_name,
 			    ore_comp_dev(&sbi->oc, 0),
 			    sbi->one_comp.obj.partition);
@@ -1023,6 +1033,9 @@ static int __init init_exofs(void)
 	if (err)
 		goto out_d;
 
+	/* We don't fail if sysfs creation failed */
+	exofs_sysfs_init();
+
 	return 0;
 out_d:
 	destroy_inodecache();
@@ -1032,6 +1045,7 @@ out:
 
 static void __exit exit_exofs(void)
 {
+	exofs_sysfs_uninit();
 	unregister_filesystem(&exofs_type);
 	destroy_inodecache();
 }
diff --git a/fs/exofs/sys.c b/fs/exofs/sys.c
new file mode 100644
index 000000000000..e32bc919e4e3
--- /dev/null
+++ b/fs/exofs/sys.c
@@ -0,0 +1,200 @@
+/*
+ * Copyright (C) 2012
+ * Sachin Bhamare <sbhamare@panasas.com>
+ * Boaz Harrosh <bharrosh@panasas.com>
+ *
+ * This file is part of exofs.
+ *
+ * exofs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License 2 as published by
+ * the Free Software Foundation.
+ *
+ * exofs 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 exofs; if not, write to the:
+ *	Free Software Foundation <licensing@fsf.org>
+ */
+
+#include <linux/kobject.h>
+#include <linux/device.h>
+
+#include "exofs.h"
+
+struct odev_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct exofs_dev *, char *);
+	ssize_t (*store)(struct exofs_dev *, const char *, size_t);
+};
+
+static ssize_t odev_attr_show(struct kobject *kobj, struct attribute *attr,
+		char *buf)
+{
+	struct exofs_dev *edp = container_of(kobj, struct exofs_dev, ed_kobj);
+	struct odev_attr *a = container_of(attr, struct odev_attr, attr);
+
+	return a->show ? a->show(edp, buf) : 0;
+}
+
+static ssize_t odev_attr_store(struct kobject *kobj, struct attribute *attr,
+		const char *buf, size_t len)
+{
+	struct exofs_dev *edp = container_of(kobj, struct exofs_dev, ed_kobj);
+	struct odev_attr *a = container_of(attr, struct odev_attr, attr);
+
+	return a->store ? a->store(edp, buf, len) : len;
+}
+
+static const struct sysfs_ops odev_attr_ops = {
+	.show  = odev_attr_show,
+	.store = odev_attr_store,
+};
+
+
+static struct kset *exofs_kset;
+
+static ssize_t osdname_show(struct exofs_dev *edp, char *buf)
+{
+	struct osd_dev *odev = edp->ored.od;
+	const struct osd_dev_info *odi = osduld_device_info(odev);
+
+	return snprintf(buf, odi->osdname_len + 1, "%s", odi->osdname);
+}
+
+static ssize_t systemid_show(struct exofs_dev *edp, char *buf)
+{
+	struct osd_dev *odev = edp->ored.od;
+	const struct osd_dev_info *odi = osduld_device_info(odev);
+
+	memcpy(buf, odi->systemid, odi->systemid_len);
+	return odi->systemid_len;
+}
+
+static ssize_t uri_show(struct exofs_dev *edp, char *buf)
+{
+	return snprintf(buf, edp->urilen, "%s", edp->uri);
+}
+
+static ssize_t uri_store(struct exofs_dev *edp, const char *buf, size_t len)
+{
+	edp->urilen = strlen(buf) + 1;
+	edp->uri = krealloc(edp->uri, edp->urilen, GFP_KERNEL);
+	strncpy(edp->uri, buf, edp->urilen);
+	return edp->urilen;
+}
+
+#define OSD_ATTR(name, mode, show, store) \
+	static struct odev_attr odev_attr_##name = \
+					__ATTR(name, mode, show, store)
+
+OSD_ATTR(osdname, S_IRUGO, osdname_show, NULL);
+OSD_ATTR(systemid, S_IRUGO, systemid_show, NULL);
+OSD_ATTR(uri, S_IRWXU, uri_show, uri_store);
+
+static struct attribute *odev_attrs[] = {
+	&odev_attr_osdname.attr,
+	&odev_attr_systemid.attr,
+	&odev_attr_uri.attr,
+	NULL,
+};
+
+static struct kobj_type odev_ktype = {
+	.default_attrs	= odev_attrs,
+	.sysfs_ops	= &odev_attr_ops,
+};
+
+static struct kobj_type uuid_ktype = {
+};
+
+void exofs_sysfs_dbg_print()
+{
+#ifdef CONFIG_EXOFS_DEBUG
+	struct kobject *k_name, *k_tmp;
+
+	list_for_each_entry_safe(k_name, k_tmp, &exofs_kset->list, entry) {
+		printk(KERN_INFO "%s: name %s ref %d\n",
+			__func__, kobject_name(k_name),
+			(int)atomic_read(&k_name->kref.refcount));
+	}
+#endif
+}
+/*
+ * This function removes all kobjects under exofs_kset
+ * At the end of it, exofs_kset kobject will have a refcount
+ * of 1 which gets decremented only on exofs module unload
+ */
+void exofs_sysfs_sb_del(struct exofs_sb_info *sbi)
+{
+	struct kobject *k_name, *k_tmp;
+	struct kobject *s_kobj = &sbi->s_kobj;
+
+	list_for_each_entry_safe(k_name, k_tmp, &exofs_kset->list, entry) {
+		/* Remove all that are children of this SBI */
+		if (k_name->parent == s_kobj)
+			kobject_put(k_name);
+	}
+	kobject_put(s_kobj);
+}
+
+/*
+ * This function creates sysfs entries to hold the current exofs cluster
+ * instance (uniquely identified by osdname,pid tuple).
+ * This function gets called once per exofs mount instance.
+ */
+int exofs_sysfs_sb_add(struct exofs_sb_info *sbi,
+		       struct exofs_dt_device_info *dt_dev)
+{
+	struct kobject *s_kobj;
+	int retval = 0;
+	uint64_t pid = sbi->one_comp.obj.partition;
+
+	/* allocate new uuid dirent */
+	s_kobj = &sbi->s_kobj;
+	s_kobj->kset = exofs_kset;
+	retval = kobject_init_and_add(s_kobj, &uuid_ktype,
+			&exofs_kset->kobj,  "%s_%llx", dt_dev->osdname, pid);
+	if (retval) {
+		EXOFS_ERR("ERROR: Failed to create sysfs entry for "
+			  "uuid-%s_%llx => %d\n", dt_dev->osdname, pid, retval);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+int exofs_sysfs_odev_add(struct exofs_dev *edev, struct exofs_sb_info *sbi)
+{
+	struct kobject *d_kobj;
+	int retval = 0;
+
+	/* create osd device group which contains following attributes
+	 * osdname, systemid & uri
+	 */
+	d_kobj = &edev->ed_kobj;
+	d_kobj->kset = exofs_kset;
+	retval = kobject_init_and_add(d_kobj, &odev_ktype,
+			&sbi->s_kobj, "dev%u", edev->did);
+	if (retval) {
+		EXOFS_ERR("ERROR: Failed to create sysfs entry for "
+				"device dev%u\n", edev->did);
+		return retval;
+	}
+	return 0;
+}
+
+int exofs_sysfs_init(void)
+{
+	exofs_kset = kset_create_and_add("exofs", NULL, fs_kobj);
+	if (!exofs_kset) {
+		EXOFS_ERR("ERROR: kset_create_and_add exofs failed\n");
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+void exofs_sysfs_uninit(void)
+{
+	kset_unregister(exofs_kset);
+}
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index 2a0e6c599147..f90f4f5cd421 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -29,9 +29,20 @@ config NFS_FS
 
 	  If unsure, say N.
 
+config NFS_V2
+	bool "NFS client support for NFS version 2"
+	depends on NFS_FS
+	default y
+	help
+	  This option enables support for version 2 of the NFS protocol
+	  (RFC 1094) in the kernel's NFS client.
+
+	  If unsure, say Y.
+
 config NFS_V3
 	bool "NFS client support for NFS version 3"
 	depends on NFS_FS
+	default y
 	help
 	  This option enables support for version 3 of the NFS protocol
 	  (RFC 1813) in the kernel's NFS client.
diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile
index b58613d0abb3..7ddd45d9f170 100644
--- a/fs/nfs/Makefile
+++ b/fs/nfs/Makefile
@@ -4,11 +4,12 @@
 
 obj-$(CONFIG_NFS_FS) += nfs.o
 
-nfs-y 			:= client.o dir.o file.o getroot.o inode.o super.o nfs2xdr.o \
-			   direct.o pagelist.o proc.o read.o symlink.o unlink.o \
+nfs-y 			:= client.o dir.o file.o getroot.o inode.o super.o \
+			   direct.o pagelist.o read.o symlink.o unlink.o \
 			   write.o namespace.o mount_clnt.o \
 			   dns_resolve.o cache_lib.o
 nfs-$(CONFIG_ROOT_NFS)	+= nfsroot.o
+nfs-$(CONFIG_NFS_V2)	+= proc.o nfs2xdr.o
 nfs-$(CONFIG_NFS_V3)	+= nfs3proc.o nfs3xdr.o
 nfs-$(CONFIG_NFS_V3_ACL)	+= nfs3acl.o
 nfs-$(CONFIG_NFS_V4)	+= nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o \
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 7f6a23f0244e..7ae8a608956f 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -187,7 +187,6 @@ static void bl_end_io_read(struct bio *bio, int err)
 	struct parallel_io *par = bio->bi_private;
 	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
-	struct nfs_read_data *rdata = (struct nfs_read_data *)par->data;
 
 	do {
 		struct page *page = bvec->bv_page;
@@ -198,9 +197,12 @@ static void bl_end_io_read(struct bio *bio, int err)
 			SetPageUptodate(page);
 	} while (bvec >= bio->bi_io_vec);
 	if (!uptodate) {
-		if (!rdata->pnfs_error)
-			rdata->pnfs_error = -EIO;
-		pnfs_set_lo_fail(rdata->lseg);
+		struct nfs_read_data *rdata = par->data;
+		struct nfs_pgio_header *header = rdata->header;
+
+		if (!header->pnfs_error)
+			header->pnfs_error = -EIO;
+		pnfs_set_lo_fail(header->lseg);
 	}
 	bio_put(bio);
 	put_parallel(par);
@@ -221,7 +223,7 @@ bl_end_par_io_read(void *data, int unused)
 {
 	struct nfs_read_data *rdata = data;
 
-	rdata->task.tk_status = rdata->pnfs_error;
+	rdata->task.tk_status = rdata->header->pnfs_error;
 	INIT_WORK(&rdata->task.u.tk_work, bl_read_cleanup);
 	schedule_work(&rdata->task.u.tk_work);
 }
@@ -229,6 +231,7 @@ bl_end_par_io_read(void *data, int unused)
 static enum pnfs_try_status
 bl_read_pagelist(struct nfs_read_data *rdata)
 {
+	struct nfs_pgio_header *header = rdata->header;
 	int i, hole;
 	struct bio *bio = NULL;
 	struct pnfs_block_extent *be = NULL, *cow_read = NULL;
@@ -239,7 +242,7 @@ bl_read_pagelist(struct nfs_read_data *rdata)
 	int pg_index = rdata->args.pgbase >> PAGE_CACHE_SHIFT;
 
 	dprintk("%s enter nr_pages %u offset %lld count %u\n", __func__,
-	       rdata->npages, f_offset, (unsigned int)rdata->args.count);
+	       rdata->pages.npages, f_offset, (unsigned int)rdata->args.count);
 
 	par = alloc_parallel(rdata);
 	if (!par)
@@ -249,17 +252,17 @@ bl_read_pagelist(struct nfs_read_data *rdata)
 
 	isect = (sector_t) (f_offset >> SECTOR_SHIFT);
 	/* Code assumes extents are page-aligned */
-	for (i = pg_index; i < rdata->npages; i++) {
+	for (i = pg_index; i < rdata->pages.npages; i++) {
 		if (!extent_length) {
 			/* We've used up the previous extent */
 			bl_put_extent(be);
 			bl_put_extent(cow_read);
 			bio = bl_submit_bio(READ, bio);
 			/* Get the next one */
-			be = bl_find_get_extent(BLK_LSEG2EXT(rdata->lseg),
+			be = bl_find_get_extent(BLK_LSEG2EXT(header->lseg),
 					     isect, &cow_read);
 			if (!be) {
-				rdata->pnfs_error = -EIO;
+				header->pnfs_error = -EIO;
 				goto out;
 			}
 			extent_length = be->be_length -
@@ -282,11 +285,12 @@ bl_read_pagelist(struct nfs_read_data *rdata)
 			struct pnfs_block_extent *be_read;
 
 			be_read = (hole && cow_read) ? cow_read : be;
-			bio = bl_add_page_to_bio(bio, rdata->npages - i, READ,
+			bio = bl_add_page_to_bio(bio, rdata->pages.npages - i,
+						 READ,
 						 isect, pages[i], be_read,
 						 bl_end_io_read, par);
 			if (IS_ERR(bio)) {
-				rdata->pnfs_error = PTR_ERR(bio);
+				header->pnfs_error = PTR_ERR(bio);
 				bio = NULL;
 				goto out;
 			}
@@ -294,9 +298,9 @@ bl_read_pagelist(struct nfs_read_data *rdata)
 		isect += PAGE_CACHE_SECTORS;
 		extent_length -= PAGE_CACHE_SECTORS;
 	}
-	if ((isect << SECTOR_SHIFT) >= rdata->inode->i_size) {
+	if ((isect << SECTOR_SHIFT) >= header->inode->i_size) {
 		rdata->res.eof = 1;
-		rdata->res.count = rdata->inode->i_size - f_offset;
+		rdata->res.count = header->inode->i_size - f_offset;
 	} else {
 		rdata->res.count = (isect << SECTOR_SHIFT) - f_offset;
 	}
@@ -345,7 +349,6 @@ static void bl_end_io_write_zero(struct bio *bio, int err)
 	struct parallel_io *par = bio->bi_private;
 	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
 	struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
-	struct nfs_write_data *wdata = (struct nfs_write_data *)par->data;
 
 	do {
 		struct page *page = bvec->bv_page;
@@ -358,9 +361,12 @@ static void bl_end_io_write_zero(struct bio *bio, int err)
 	} while (bvec >= bio->bi_io_vec);
 
 	if (unlikely(!uptodate)) {
-		if (!wdata->pnfs_error)
-			wdata->pnfs_error = -EIO;
-		pnfs_set_lo_fail(wdata->lseg);
+		struct nfs_write_data *data = par->data;
+		struct nfs_pgio_header *header = data->header;
+
+		if (!header->pnfs_error)
+			header->pnfs_error = -EIO;
+		pnfs_set_lo_fail(header->lseg);
 	}
 	bio_put(bio);
 	put_parallel(par);
@@ -370,12 +376,13 @@ static void bl_end_io_write(struct bio *bio, int err)
 {
 	struct parallel_io *par = bio->bi_private;
 	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
-	struct nfs_write_data *wdata = (struct nfs_write_data *)par->data;
+	struct nfs_write_data *data = par->data;
+	struct nfs_pgio_header *header = data->header;
 
 	if (!uptodate) {
-		if (!wdata->pnfs_error)
-			wdata->pnfs_error = -EIO;
-		pnfs_set_lo_fail(wdata->lseg);
+		if (!header->pnfs_error)
+			header->pnfs_error = -EIO;
+		pnfs_set_lo_fail(header->lseg);
 	}
 	bio_put(bio);
 	put_parallel(par);
@@ -391,9 +398,9 @@ static void bl_write_cleanup(struct work_struct *work)
 	dprintk("%s enter\n", __func__);
 	task = container_of(work, struct rpc_task, u.tk_work);
 	wdata = container_of(task, struct nfs_write_data, task);
-	if (likely(!wdata->pnfs_error)) {
+	if (likely(!wdata->header->pnfs_error)) {
 		/* Marks for LAYOUTCOMMIT */
-		mark_extents_written(BLK_LSEG2EXT(wdata->lseg),
+		mark_extents_written(BLK_LSEG2EXT(wdata->header->lseg),
 				     wdata->args.offset, wdata->args.count);
 	}
 	pnfs_ld_write_done(wdata);
@@ -404,12 +411,12 @@ static void bl_end_par_io_write(void *data, int num_se)
 {
 	struct nfs_write_data *wdata = data;
 
-	if (unlikely(wdata->pnfs_error)) {
-		bl_free_short_extents(&BLK_LSEG2EXT(wdata->lseg)->bl_inval,
+	if (unlikely(wdata->header->pnfs_error)) {
+		bl_free_short_extents(&BLK_LSEG2EXT(wdata->header->lseg)->bl_inval,
 					num_se);
 	}
 
-	wdata->task.tk_status = wdata->pnfs_error;
+	wdata->task.tk_status = wdata->header->pnfs_error;
 	wdata->verf.committed = NFS_FILE_SYNC;
 	INIT_WORK(&wdata->task.u.tk_work, bl_write_cleanup);
 	schedule_work(&wdata->task.u.tk_work);
@@ -540,6 +547,7 @@ check_page:
 static enum pnfs_try_status
 bl_write_pagelist(struct nfs_write_data *wdata, int sync)
 {
+	struct nfs_pgio_header *header = wdata->header;
 	int i, ret, npg_zero, pg_index, last = 0;
 	struct bio *bio = NULL;
 	struct pnfs_block_extent *be = NULL, *cow_read = NULL;
@@ -552,7 +560,7 @@ bl_write_pagelist(struct nfs_write_data *wdata, int sync)
 	pgoff_t index;
 	u64 temp;
 	int npg_per_block =
-	    NFS_SERVER(wdata->inode)->pnfs_blksize >> PAGE_CACHE_SHIFT;
+	    NFS_SERVER(header->inode)->pnfs_blksize >> PAGE_CACHE_SHIFT;
 
 	dprintk("%s enter, %Zu@%lld\n", __func__, count, offset);
 	/* At this point, wdata->pages is a (sequential) list of nfs_pages.
@@ -566,7 +574,7 @@ bl_write_pagelist(struct nfs_write_data *wdata, int sync)
 	/* At this point, have to be more careful with error handling */
 
 	isect = (sector_t) ((offset & (long)PAGE_CACHE_MASK) >> SECTOR_SHIFT);
-	be = bl_find_get_extent(BLK_LSEG2EXT(wdata->lseg), isect, &cow_read);
+	be = bl_find_get_extent(BLK_LSEG2EXT(header->lseg), isect, &cow_read);
 	if (!be || !is_writable(be, isect)) {
 		dprintk("%s no matching extents!\n", __func__);
 		goto out_mds;
@@ -597,10 +605,10 @@ fill_invalid_ext:
 			dprintk("%s zero %dth page: index %lu isect %llu\n",
 				__func__, npg_zero, index,
 				(unsigned long long)isect);
-			page = bl_find_get_zeroing_page(wdata->inode, index,
+			page = bl_find_get_zeroing_page(header->inode, index,
 							cow_read);
 			if (unlikely(IS_ERR(page))) {
-				wdata->pnfs_error = PTR_ERR(page);
+				header->pnfs_error = PTR_ERR(page);
 				goto out;
 			} else if (page == NULL)
 				goto next_page;
@@ -612,7 +620,7 @@ fill_invalid_ext:
 					__func__, ret);
 				end_page_writeback(page);
 				page_cache_release(page);
-				wdata->pnfs_error = ret;
+				header->pnfs_error = ret;
 				goto out;
 			}
 			if (likely(!bl_push_one_short_extent(be->be_inval)))
@@ -620,11 +628,11 @@ fill_invalid_ext:
 			else {
 				end_page_writeback(page);
 				page_cache_release(page);
-				wdata->pnfs_error = -ENOMEM;
+				header->pnfs_error = -ENOMEM;
 				goto out;
 			}
 			/* FIXME: This should be done in bi_end_io */
-			mark_extents_written(BLK_LSEG2EXT(wdata->lseg),
+			mark_extents_written(BLK_LSEG2EXT(header->lseg),
 					     page->index << PAGE_CACHE_SHIFT,
 					     PAGE_CACHE_SIZE);
 
@@ -632,7 +640,7 @@ fill_invalid_ext:
 						 isect, page, be,
 						 bl_end_io_write_zero, par);
 			if (IS_ERR(bio)) {
-				wdata->pnfs_error = PTR_ERR(bio);
+				header->pnfs_error = PTR_ERR(bio);
 				bio = NULL;
 				goto out;
 			}
@@ -647,16 +655,16 @@ next_page:
 
 	/* Middle pages */
 	pg_index = wdata->args.pgbase >> PAGE_CACHE_SHIFT;
-	for (i = pg_index; i < wdata->npages; i++) {
+	for (i = pg_index; i < wdata->pages.npages; i++) {
 		if (!extent_length) {
 			/* We've used up the previous extent */
 			bl_put_extent(be);
 			bio = bl_submit_bio(WRITE, bio);
 			/* Get the next one */
-			be = bl_find_get_extent(BLK_LSEG2EXT(wdata->lseg),
+			be = bl_find_get_extent(BLK_LSEG2EXT(header->lseg),
 					     isect, NULL);
 			if (!be || !is_writable(be, isect)) {
-				wdata->pnfs_error = -EINVAL;
+				header->pnfs_error = -EINVAL;
 				goto out;
 			}
 			if (be->be_state == PNFS_BLOCK_INVALID_DATA) {
@@ -664,7 +672,7 @@ next_page:
 								be->be_inval)))
 					par->bse_count++;
 				else {
-					wdata->pnfs_error = -ENOMEM;
+					header->pnfs_error = -ENOMEM;
 					goto out;
 				}
 			}
@@ -677,15 +685,15 @@ next_page:
 			if (unlikely(ret)) {
 				dprintk("%s bl_mark_sectors_init fail %d\n",
 					__func__, ret);
-				wdata->pnfs_error = ret;
+				header->pnfs_error = ret;
 				goto out;
 			}
 		}
-		bio = bl_add_page_to_bio(bio, wdata->npages - i, WRITE,
+		bio = bl_add_page_to_bio(bio, wdata->pages.npages - i, WRITE,
 					 isect, pages[i], be,
 					 bl_end_io_write, par);
 		if (IS_ERR(bio)) {
-			wdata->pnfs_error = PTR_ERR(bio);
+			header->pnfs_error = PTR_ERR(bio);
 			bio = NULL;
 			goto out;
 		}
diff --git a/fs/nfs/blocklayout/blocklayoutdev.c b/fs/nfs/blocklayout/blocklayoutdev.c
index a5c88a554d92..c96554245ccf 100644
--- a/fs/nfs/blocklayout/blocklayoutdev.c
+++ b/fs/nfs/blocklayout/blocklayoutdev.c
@@ -123,7 +123,7 @@ nfs4_blk_decode_device(struct nfs_server *server,
 	uint8_t *dataptr;
 	DECLARE_WAITQUEUE(wq, current);
 	int offset, len, i, rc;
-	struct net *net = server->nfs_client->net;
+	struct net *net = server->nfs_client->cl_net;
 	struct nfs_net *nn = net_generic(net, nfs_net_id);
 	struct bl_dev_msg *reply = &nn->bl_mount_reply;
 
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 60f7e4ec842c..7d108753af81 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -65,7 +65,7 @@ static DECLARE_WAIT_QUEUE_HEAD(nfs_client_active_wq);
 static int nfs_get_cb_ident_idr(struct nfs_client *clp, int minorversion)
 {
 	int ret = 0;
-	struct nfs_net *nn = net_generic(clp->net, nfs_net_id);
+	struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id);
 
 	if (clp->rpc_ops->version != 4 || minorversion != 0)
 		return ret;
@@ -90,7 +90,9 @@ static bool nfs4_disable_idmapping = true;
  * RPC cruft for NFS
  */
 static const struct rpc_version *nfs_version[5] = {
+#ifdef CONFIG_NFS_V2
 	[2]			= &nfs_version2,
+#endif
 #ifdef CONFIG_NFS_V3
 	[3]			= &nfs_version3,
 #endif
@@ -129,6 +131,7 @@ const struct rpc_program nfsacl_program = {
 #endif  /* CONFIG_NFS_V3_ACL */
 
 struct nfs_client_initdata {
+	unsigned long init_flags;
 	const char *hostname;
 	const struct sockaddr *addr;
 	size_t addrlen;
@@ -172,7 +175,7 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_
 	clp->cl_rpcclient = ERR_PTR(-EINVAL);
 
 	clp->cl_proto = cl_init->proto;
-	clp->net = get_net(cl_init->net);
+	clp->cl_net = get_net(cl_init->net);
 
 #ifdef CONFIG_NFS_V4
 	err = nfs_get_cb_ident_idr(clp, cl_init->minorversion);
@@ -182,7 +185,6 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_
 	spin_lock_init(&clp->cl_lock);
 	INIT_DELAYED_WORK(&clp->cl_renewd, nfs4_renew_state);
 	rpc_init_wait_queue(&clp->cl_rpcwaitq, "NFS client");
-	clp->cl_boot_time = CURRENT_TIME;
 	clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED;
 	clp->cl_minorversion = cl_init->minorversion;
 	clp->cl_mvops = nfs_v4_minor_ops[cl_init->minorversion];
@@ -207,6 +209,7 @@ static void nfs4_shutdown_session(struct nfs_client *clp)
 	if (nfs4_has_session(clp)) {
 		nfs4_deviceid_purge_client(clp);
 		nfs4_destroy_session(clp->cl_session);
+		nfs4_destroy_clientid(clp);
 	}
 
 }
@@ -235,6 +238,9 @@ static void nfs4_shutdown_client(struct nfs_client *clp)
 		nfs_idmap_delete(clp);
 
 	rpc_destroy_wait_queue(&clp->cl_rpcwaitq);
+	kfree(clp->cl_serverowner);
+	kfree(clp->cl_serverscope);
+	kfree(clp->cl_implid);
 }
 
 /* idr_remove_all is not needed as all id's are removed by nfs_put_client */
@@ -248,7 +254,7 @@ void nfs_cleanup_cb_ident_idr(struct net *net)
 /* nfs_client_lock held */
 static void nfs_cb_idr_remove_locked(struct nfs_client *clp)
 {
-	struct nfs_net *nn = net_generic(clp->net, nfs_net_id);
+	struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id);
 
 	if (clp->cl_cb_ident)
 		idr_remove(&nn->cb_ident_idr, clp->cl_cb_ident);
@@ -301,10 +307,8 @@ static void nfs_free_client(struct nfs_client *clp)
 	if (clp->cl_machine_cred != NULL)
 		put_rpccred(clp->cl_machine_cred);
 
-	put_net(clp->net);
+	put_net(clp->cl_net);
 	kfree(clp->cl_hostname);
-	kfree(clp->server_scope);
-	kfree(clp->impl_id);
 	kfree(clp);
 
 	dprintk("<-- nfs_free_client()\n");
@@ -321,7 +325,7 @@ void nfs_put_client(struct nfs_client *clp)
 		return;
 
 	dprintk("--> nfs_put_client({%d})\n", atomic_read(&clp->cl_count));
-	nn = net_generic(clp->net, nfs_net_id);
+	nn = net_generic(clp->cl_net, nfs_net_id);
 
 	if (atomic_dec_and_lock(&clp->cl_count, &nn->nfs_client_lock)) {
 		list_del(&clp->cl_share_link);
@@ -456,6 +460,8 @@ static bool nfs4_cb_match_client(const struct sockaddr *addr,
 	    clp->cl_cons_state == NFS_CS_SESSION_INITING))
 		return false;
 
+	smp_rmb();
+
 	/* Match the version and minorversion */
 	if (clp->rpc_ops->version != 4 ||
 	    clp->cl_minorversion != minorversion)
@@ -504,6 +510,47 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat
 	return NULL;
 }
 
+static bool nfs_client_init_is_complete(const struct nfs_client *clp)
+{
+	return clp->cl_cons_state != NFS_CS_INITING;
+}
+
+int nfs_wait_client_init_complete(const struct nfs_client *clp)
+{
+	return wait_event_killable(nfs_client_active_wq,
+			nfs_client_init_is_complete(clp));
+}
+
+/*
+ * Found an existing client.  Make sure it's ready before returning.
+ */
+static struct nfs_client *
+nfs_found_client(const struct nfs_client_initdata *cl_init,
+		 struct nfs_client *clp)
+{
+	int error;
+
+	error = nfs_wait_client_init_complete(clp);
+	if (error < 0) {
+		nfs_put_client(clp);
+		return ERR_PTR(-ERESTARTSYS);
+	}
+
+	if (clp->cl_cons_state < NFS_CS_READY) {
+		error = clp->cl_cons_state;
+		nfs_put_client(clp);
+		return ERR_PTR(error);
+	}
+
+	smp_rmb();
+
+	BUG_ON(clp->cl_cons_state != NFS_CS_READY);
+
+	dprintk("<-- %s found nfs_client %p for %s\n",
+		__func__, clp, cl_init->hostname ?: "");
+	return clp;
+}
+
 /*
  * Look up a client by IP address and protocol version
  * - creates a new record if one doesn't yet exist
@@ -512,11 +559,9 @@ static struct nfs_client *
 nfs_get_client(const struct nfs_client_initdata *cl_init,
 	       const struct rpc_timeout *timeparms,
 	       const char *ip_addr,
-	       rpc_authflavor_t authflavour,
-	       int noresvport)
+	       rpc_authflavor_t authflavour)
 {
 	struct nfs_client *clp, *new = NULL;
-	int error;
 	struct nfs_net *nn = net_generic(cl_init->net, nfs_net_id);
 
 	dprintk("--> nfs_get_client(%s,v%u)\n",
@@ -527,60 +572,29 @@ nfs_get_client(const struct nfs_client_initdata *cl_init,
 		spin_lock(&nn->nfs_client_lock);
 
 		clp = nfs_match_client(cl_init);
-		if (clp)
-			goto found_client;
-		if (new)
-			goto install_client;
+		if (clp) {
+			spin_unlock(&nn->nfs_client_lock);
+			if (new)
+				nfs_free_client(new);
+			return nfs_found_client(cl_init, clp);
+		}
+		if (new) {
+			list_add(&new->cl_share_link, &nn->nfs_client_list);
+			spin_unlock(&nn->nfs_client_lock);
+			new->cl_flags = cl_init->init_flags;
+			return cl_init->rpc_ops->init_client(new,
+						timeparms, ip_addr,
+						authflavour);
+		}
 
 		spin_unlock(&nn->nfs_client_lock);
 
 		new = nfs_alloc_client(cl_init);
 	} while (!IS_ERR(new));
 
-	dprintk("--> nfs_get_client() = %ld [failed]\n", PTR_ERR(new));
+	dprintk("<-- nfs_get_client() Failed to find %s (%ld)\n",
+		cl_init->hostname ?: "", PTR_ERR(new));
 	return new;
-
-	/* install a new client and return with it unready */
-install_client:
-	clp = new;
-	list_add(&clp->cl_share_link, &nn->nfs_client_list);
-	spin_unlock(&nn->nfs_client_lock);
-
-	error = cl_init->rpc_ops->init_client(clp, timeparms, ip_addr,
-					      authflavour, noresvport);
-	if (error < 0) {
-		nfs_put_client(clp);
-		return ERR_PTR(error);
-	}
-	dprintk("--> nfs_get_client() = %p [new]\n", clp);
-	return clp;
-
-	/* found an existing client
-	 * - make sure it's ready before returning
-	 */
-found_client:
-	spin_unlock(&nn->nfs_client_lock);
-
-	if (new)
-		nfs_free_client(new);
-
-	error = wait_event_killable(nfs_client_active_wq,
-				clp->cl_cons_state < NFS_CS_INITING);
-	if (error < 0) {
-		nfs_put_client(clp);
-		return ERR_PTR(-ERESTARTSYS);
-	}
-
-	if (clp->cl_cons_state < NFS_CS_READY) {
-		error = clp->cl_cons_state;
-		nfs_put_client(clp);
-		return ERR_PTR(error);
-	}
-
-	BUG_ON(clp->cl_cons_state != NFS_CS_READY);
-
-	dprintk("--> nfs_get_client() = %p [share]\n", clp);
-	return clp;
 }
 
 /*
@@ -588,27 +602,12 @@ found_client:
  */
 void nfs_mark_client_ready(struct nfs_client *clp, int state)
 {
+	smp_wmb();
 	clp->cl_cons_state = state;
 	wake_up_all(&nfs_client_active_wq);
 }
 
 /*
- * With sessions, the client is not marked ready until after a
- * successful EXCHANGE_ID and CREATE_SESSION.
- *
- * Map errors cl_cons_state errors to EPROTONOSUPPORT to indicate
- * other versions of NFS can be tried.
- */
-int nfs4_check_client_ready(struct nfs_client *clp)
-{
-	if (!nfs4_has_session(clp))
-		return 0;
-	if (clp->cl_cons_state < NFS_CS_READY)
-		return -EPROTONOSUPPORT;
-	return 0;
-}
-
-/*
  * Initialise the timeout values for a connection
  */
 static void nfs_init_timeout_values(struct rpc_timeout *to, int proto,
@@ -654,12 +653,11 @@ static void nfs_init_timeout_values(struct rpc_timeout *to, int proto,
  */
 static int nfs_create_rpc_client(struct nfs_client *clp,
 				 const struct rpc_timeout *timeparms,
-				 rpc_authflavor_t flavor,
-				 int discrtry, int noresvport)
+				 rpc_authflavor_t flavor)
 {
 	struct rpc_clnt		*clnt = NULL;
 	struct rpc_create_args args = {
-		.net		= clp->net,
+		.net		= clp->cl_net,
 		.protocol	= clp->cl_proto,
 		.address	= (struct sockaddr *)&clp->cl_addr,
 		.addrsize	= clp->cl_addrlen,
@@ -670,9 +668,9 @@ static int nfs_create_rpc_client(struct nfs_client *clp,
 		.authflavor	= flavor,
 	};
 
-	if (discrtry)
+	if (test_bit(NFS_CS_DISCRTRY, &clp->cl_flags))
 		args.flags |= RPC_CLNT_CREATE_DISCRTRY;
-	if (noresvport)
+	if (test_bit(NFS_CS_NORESVPORT, &clp->cl_flags))
 		args.flags |= RPC_CLNT_CREATE_NONPRIVPORT;
 
 	if (!IS_ERR(clp->cl_rpcclient))
@@ -713,7 +711,7 @@ static int nfs_start_lockd(struct nfs_server *server)
 		.nfs_version	= clp->rpc_ops->version,
 		.noresvport	= server->flags & NFS_MOUNT_NORESVPORT ?
 					1 : 0,
-		.net		= clp->net,
+		.net		= clp->cl_net,
 	};
 
 	if (nlm_init.nfs_version > 3)
@@ -805,36 +803,43 @@ static int nfs_init_server_rpcclient(struct nfs_server *server,
 	return 0;
 }
 
-/*
- * Initialise an NFS2 or NFS3 client
+/**
+ * nfs_init_client - Initialise an NFS2 or NFS3 client
+ *
+ * @clp: nfs_client to initialise
+ * @timeparms: timeout parameters for underlying RPC transport
+ * @ip_addr: IP presentation address (not used)
+ * @authflavor: authentication flavor for underlying RPC transport
+ *
+ * Returns pointer to an NFS client, or an ERR_PTR value.
  */
-int nfs_init_client(struct nfs_client *clp, const struct rpc_timeout *timeparms,
-		    const char *ip_addr, rpc_authflavor_t authflavour,
-		    int noresvport)
+struct nfs_client *nfs_init_client(struct nfs_client *clp,
+		    const struct rpc_timeout *timeparms,
+		    const char *ip_addr, rpc_authflavor_t authflavour)
 {
 	int error;
 
 	if (clp->cl_cons_state == NFS_CS_READY) {
 		/* the client is already initialised */
 		dprintk("<-- nfs_init_client() = 0 [already %p]\n", clp);
-		return 0;
+		return clp;
 	}
 
 	/*
 	 * Create a client RPC handle for doing FSSTAT with UNIX auth only
 	 * - RFC 2623, sec 2.3.2
 	 */
-	error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_UNIX,
-				      0, noresvport);
+	error = nfs_create_rpc_client(clp, timeparms, RPC_AUTH_UNIX);
 	if (error < 0)
 		goto error;
 	nfs_mark_client_ready(clp, NFS_CS_READY);
-	return 0;
+	return clp;
 
 error:
 	nfs_mark_client_ready(clp, error);
+	nfs_put_client(clp);
 	dprintk("<-- nfs_init_client() = xerror %d\n", error);
-	return error;
+	return ERR_PTR(error);
 }
 
 /*
@@ -847,7 +852,7 @@ static int nfs_init_server(struct nfs_server *server,
 		.hostname = data->nfs_server.hostname,
 		.addr = (const struct sockaddr *)&data->nfs_server.address,
 		.addrlen = data->nfs_server.addrlen,
-		.rpc_ops = &nfs_v2_clientops,
+		.rpc_ops = NULL,
 		.proto = data->nfs_server.protocol,
 		.net = data->net,
 	};
@@ -857,17 +862,28 @@ static int nfs_init_server(struct nfs_server *server,
 
 	dprintk("--> nfs_init_server()\n");
 
+	switch (data->version) {
+#ifdef CONFIG_NFS_V2
+	case 2:
+		cl_init.rpc_ops = &nfs_v2_clientops;
+		break;
+#endif
 #ifdef CONFIG_NFS_V3
-	if (data->version == 3)
+	case 3:
 		cl_init.rpc_ops = &nfs_v3_clientops;
+		break;
 #endif
+	default:
+		return -EPROTONOSUPPORT;
+	}
 
 	nfs_init_timeout_values(&timeparms, data->nfs_server.protocol,
 			data->timeo, data->retrans);
+	if (data->flags & NFS_MOUNT_NORESVPORT)
+		set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
 
 	/* Allocate or find a client reference we can use */
-	clp = nfs_get_client(&cl_init, &timeparms, NULL, RPC_AUTH_UNIX,
-			     data->flags & NFS_MOUNT_NORESVPORT);
+	clp = nfs_get_client(&cl_init, &timeparms, NULL, RPC_AUTH_UNIX);
 	if (IS_ERR(clp)) {
 		dprintk("<-- nfs_init_server() = error %ld\n", PTR_ERR(clp));
 		return PTR_ERR(clp);
@@ -880,7 +896,7 @@ static int nfs_init_server(struct nfs_server *server,
 	server->options = data->options;
 	server->caps |= NFS_CAP_HARDLINKS|NFS_CAP_SYMLINKS|NFS_CAP_FILEID|
 		NFS_CAP_MODE|NFS_CAP_NLINK|NFS_CAP_OWNER|NFS_CAP_OWNER_GROUP|
-		NFS_CAP_ATIME|NFS_CAP_CTIME|NFS_CAP_MTIME;
+		NFS_CAP_ATIME|NFS_CAP_CTIME|NFS_CAP_MTIME|NFS_CAP_CHANGE_ATTR;
 
 	if (data->rsize)
 		server->rsize = nfs_block_size(data->rsize, NULL);
@@ -1048,7 +1064,7 @@ static void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_serve
 static void nfs_server_insert_lists(struct nfs_server *server)
 {
 	struct nfs_client *clp = server->nfs_client;
-	struct nfs_net *nn = net_generic(clp->net, nfs_net_id);
+	struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id);
 
 	spin_lock(&nn->nfs_client_lock);
 	list_add_tail_rcu(&server->client_link, &clp->cl_superblocks);
@@ -1065,7 +1081,7 @@ static void nfs_server_remove_lists(struct nfs_server *server)
 
 	if (clp == NULL)
 		return;
-	nn = net_generic(clp->net, nfs_net_id);
+	nn = net_generic(clp->cl_net, nfs_net_id);
 	spin_lock(&nn->nfs_client_lock);
 	list_del_rcu(&server->client_link);
 	if (list_empty(&clp->cl_superblocks))
@@ -1333,21 +1349,27 @@ static int nfs4_init_client_minor_version(struct nfs_client *clp)
 		 * so that the client back channel can find the
 		 * nfs_client struct
 		 */
-		clp->cl_cons_state = NFS_CS_SESSION_INITING;
+		nfs_mark_client_ready(clp, NFS_CS_SESSION_INITING);
 	}
 #endif /* CONFIG_NFS_V4_1 */
 
 	return nfs4_init_callback(clp);
 }
 
-/*
- * Initialise an NFS4 client record
+/**
+ * nfs4_init_client - Initialise an NFS4 client record
+ *
+ * @clp: nfs_client to initialise
+ * @timeparms: timeout parameters for underlying RPC transport
+ * @ip_addr: callback IP address in presentation format
+ * @authflavor: authentication flavor for underlying RPC transport
+ *
+ * Returns pointer to an NFS client, or an ERR_PTR value.
  */
-int nfs4_init_client(struct nfs_client *clp,
-		     const struct rpc_timeout *timeparms,
-		     const char *ip_addr,
-		     rpc_authflavor_t authflavour,
-		     int noresvport)
+struct nfs_client *nfs4_init_client(struct nfs_client *clp,
+				    const struct rpc_timeout *timeparms,
+				    const char *ip_addr,
+				    rpc_authflavor_t authflavour)
 {
 	char buf[INET6_ADDRSTRLEN + 1];
 	int error;
@@ -1355,14 +1377,14 @@ int nfs4_init_client(struct nfs_client *clp,
 	if (clp->cl_cons_state == NFS_CS_READY) {
 		/* the client is initialised already */
 		dprintk("<-- nfs4_init_client() = 0 [already %p]\n", clp);
-		return 0;
+		return clp;
 	}
 
 	/* Check NFS protocol revision and initialize RPC op vector */
 	clp->rpc_ops = &nfs_v4_clientops;
 
-	error = nfs_create_rpc_client(clp, timeparms, authflavour,
-				      1, noresvport);
+	__set_bit(NFS_CS_DISCRTRY, &clp->cl_flags);
+	error = nfs_create_rpc_client(clp, timeparms, authflavour);
 	if (error < 0)
 		goto error;
 
@@ -1395,12 +1417,13 @@ int nfs4_init_client(struct nfs_client *clp,
 
 	if (!nfs4_has_session(clp))
 		nfs_mark_client_ready(clp, NFS_CS_READY);
-	return 0;
+	return clp;
 
 error:
 	nfs_mark_client_ready(clp, error);
+	nfs_put_client(clp);
 	dprintk("<-- nfs4_init_client() = xerror %d\n", error);
-	return error;
+	return ERR_PTR(error);
 }
 
 /*
@@ -1429,9 +1452,11 @@ static int nfs4_set_client(struct nfs_server *server,
 
 	dprintk("--> nfs4_set_client()\n");
 
+	if (server->flags & NFS_MOUNT_NORESVPORT)
+		set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
+
 	/* Allocate or find a client reference we can use */
-	clp = nfs_get_client(&cl_init, timeparms, ip_addr, authflavour,
-			     server->flags & NFS_MOUNT_NORESVPORT);
+	clp = nfs_get_client(&cl_init, timeparms, ip_addr, authflavour);
 	if (IS_ERR(clp)) {
 		error = PTR_ERR(clp);
 		goto error;
@@ -1465,8 +1490,8 @@ error:
  * the MDS.
  */
 struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
-		const struct sockaddr *ds_addr,
-		int ds_addrlen, int ds_proto)
+		const struct sockaddr *ds_addr, int ds_addrlen,
+		int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans)
 {
 	struct nfs_client_initdata cl_init = {
 		.addr = ds_addr,
@@ -1474,14 +1499,9 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
 		.rpc_ops = &nfs_v4_clientops,
 		.proto = ds_proto,
 		.minorversion = mds_clp->cl_minorversion,
-		.net = mds_clp->net,
-	};
-	struct rpc_timeout ds_timeout = {
-		.to_initval = 15 * HZ,
-		.to_maxval = 15 * HZ,
-		.to_retries = 1,
-		.to_exponential = 1,
+		.net = mds_clp->cl_net,
 	};
+	struct rpc_timeout ds_timeout;
 	struct nfs_client *clp;
 
 	/*
@@ -1489,8 +1509,9 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
 	 * cl_ipaddr so as to use the same EXCHANGE_ID co_ownerid as the MDS
 	 * (section 13.1 RFC 5661).
 	 */
+	nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans);
 	clp = nfs_get_client(&cl_init, &ds_timeout, mds_clp->cl_ipaddr,
-			     mds_clp->cl_rpcclient->cl_auth->au_flavor, 0);
+			     mds_clp->cl_rpcclient->cl_auth->au_flavor);
 
 	dprintk("<-- %s %p\n", __func__, clp);
 	return clp;
@@ -1701,7 +1722,7 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data,
 				rpc_protocol(parent_server->client),
 				parent_server->client->cl_timeout,
 				parent_client->cl_mvops->minor_version,
-				parent_client->net);
+				parent_client->cl_net);
 	if (error < 0)
 		goto error;
 
@@ -1805,6 +1826,7 @@ void nfs_clients_init(struct net *net)
 	idr_init(&nn->cb_ident_idr);
 #endif
 	spin_lock_init(&nn->nfs_client_lock);
+	nn->boot_time = CURRENT_TIME;
 }
 
 #ifdef CONFIG_PROC_FS
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 89af1d269274..bd3a9601d32d 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -316,6 +316,10 @@ out:
  * nfs_client_return_marked_delegations - return previously marked delegations
  * @clp: nfs_client to process
  *
+ * Note that this function is designed to be called by the state
+ * manager thread. For this reason, it cannot flush the dirty data,
+ * since that could deadlock in case of a state recovery error.
+ *
  * Returns zero on success, or a negative errno value.
  */
 int nfs_client_return_marked_delegations(struct nfs_client *clp)
@@ -340,11 +344,9 @@ restart:
 								server);
 			rcu_read_unlock();
 
-			if (delegation != NULL) {
-				filemap_flush(inode->i_mapping);
+			if (delegation != NULL)
 				err = __nfs_inode_return_delegation(inode,
 								delegation, 0);
-			}
 			iput(inode);
 			if (!err)
 				goto restart;
@@ -380,6 +382,10 @@ void nfs_inode_return_delegation_noreclaim(struct inode *inode)
  * nfs_inode_return_delegation - synchronously return a delegation
  * @inode: inode to process
  *
+ * This routine will always flush any dirty data to disk on the
+ * assumption that if we need to return the delegation, then
+ * we should stop caching.
+ *
  * Returns zero on success, or a negative errno value.
  */
 int nfs_inode_return_delegation(struct inode *inode)
@@ -389,10 +395,10 @@ int nfs_inode_return_delegation(struct inode *inode)
 	struct nfs_delegation *delegation;
 	int err = 0;
 
+	nfs_wb_all(inode);
 	if (rcu_access_pointer(nfsi->delegation) != NULL) {
 		delegation = nfs_detach_delegation(nfsi, server);
 		if (delegation != NULL) {
-			nfs_wb_all(inode);
 			err = __nfs_inode_return_delegation(inode, delegation, 1);
 		}
 	}
@@ -538,6 +544,8 @@ int nfs_async_inode_return_delegation(struct inode *inode,
 	struct nfs_client *clp = server->nfs_client;
 	struct nfs_delegation *delegation;
 
+	filemap_flush(inode->i_mapping);
+
 	rcu_read_lock();
 	delegation = rcu_dereference(NFS_I(inode)->delegation);
 
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index cd6a7a8dadae..72709c4193fa 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -66,6 +66,7 @@ static inline int nfs_have_delegation(struct inode *inode, fmode_t flags)
 
 static inline int nfs_inode_return_delegation(struct inode *inode)
 {
+	nfs_wb_all(inode);
 	return 0;
 }
 #endif
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index eedd24d0ad2e..0989a2099688 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -475,6 +475,29 @@ different:
 }
 
 static
+bool nfs_use_readdirplus(struct inode *dir, struct file *filp)
+{
+	if (!nfs_server_capable(dir, NFS_CAP_READDIRPLUS))
+		return false;
+	if (test_and_clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(dir)->flags))
+		return true;
+	if (filp->f_pos == 0)
+		return true;
+	return false;
+}
+
+/*
+ * This function is called by the lookup code to request the use of
+ * readdirplus to accelerate any future lookups in the same
+ * directory.
+ */
+static
+void nfs_advise_use_readdirplus(struct inode *dir)
+{
+	set_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(dir)->flags);
+}
+
+static
 void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
 {
 	struct qstr filename = QSTR_INIT(entry->name, entry->len);
@@ -871,7 +894,7 @@ static int nfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
 	desc->file = filp;
 	desc->dir_cookie = &dir_ctx->dir_cookie;
 	desc->decode = NFS_PROTO(inode)->decode_dirent;
-	desc->plus = NFS_USE_READDIRPLUS(inode);
+	desc->plus = nfs_use_readdirplus(inode, filp) ? 1 : 0;
 
 	nfs_block_sillyrename(dentry);
 	res = nfs_revalidate_mapping(inode, filp->f_mapping);
@@ -1111,7 +1134,7 @@ static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd)
 	if (!inode) {
 		if (nfs_neg_need_reval(dir, dentry, nd))
 			goto out_bad;
-		goto out_valid;
+		goto out_valid_noent;
 	}
 
 	if (is_bad_inode(inode)) {
@@ -1140,7 +1163,7 @@ static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd)
 	if (fhandle == NULL || fattr == NULL)
 		goto out_error;
 
-	error = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, &dentry->d_name, fhandle, fattr);
+	error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr);
 	if (error)
 		goto out_bad;
 	if (nfs_compare_fh(NFS_FH(inode), fhandle))
@@ -1153,6 +1176,9 @@ static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd)
 out_set_verifier:
 	nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
  out_valid:
+	/* Success: notify readdir to use READDIRPLUS */
+	nfs_advise_use_readdirplus(dir);
+ out_valid_noent:
 	dput(parent);
 	dfprintk(LOOKUPCACHE, "NFS: %s(%s/%s) is valid\n",
 			__func__, dentry->d_parent->d_name.name,
@@ -1296,7 +1322,7 @@ static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, stru
 	parent = dentry->d_parent;
 	/* Protect against concurrent sillydeletes */
 	nfs_block_sillyrename(parent);
-	error = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, &dentry->d_name, fhandle, fattr);
+	error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr);
 	if (error == -ENOENT)
 		goto no_entry;
 	if (error < 0) {
@@ -1308,6 +1334,9 @@ static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, stru
 	if (IS_ERR(res))
 		goto out_unblock_sillyrename;
 
+	/* Success: notify readdir to use READDIRPLUS */
+	nfs_advise_use_readdirplus(dir);
+
 no_entry:
 	res = d_materialise_unique(dentry, inode);
 	if (res != NULL) {
@@ -1643,7 +1672,7 @@ int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fhandle,
 	if (dentry->d_inode)
 		goto out;
 	if (fhandle->size == 0) {
-		error = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, &dentry->d_name, fhandle, fattr);
+		error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr);
 		if (error)
 			goto out_error;
 	}
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 481be7f7bdd3..23d170bc44f4 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -56,6 +56,7 @@
 
 #include "internal.h"
 #include "iostat.h"
+#include "pnfs.h"
 
 #define NFSDBG_FACILITY		NFSDBG_VFS
 
@@ -81,16 +82,19 @@ struct nfs_direct_req {
 	struct completion	completion;	/* wait for i/o completion */
 
 	/* commit state */
-	struct list_head	rewrite_list;	/* saved nfs_write_data structs */
-	struct nfs_write_data *	commit_data;	/* special write_data for commits */
+	struct nfs_mds_commit_info mds_cinfo;	/* Storage for cinfo */
+	struct pnfs_ds_commit_info ds_cinfo;	/* Storage for cinfo */
+	struct work_struct	work;
 	int			flags;
 #define NFS_ODIRECT_DO_COMMIT		(1)	/* an unstable reply was received */
 #define NFS_ODIRECT_RESCHED_WRITES	(2)	/* write verification failed */
 	struct nfs_writeverf	verf;		/* unstable write verifier */
 };
 
+static const struct nfs_pgio_completion_ops nfs_direct_write_completion_ops;
+static const struct nfs_commit_completion_ops nfs_direct_commit_completion_ops;
 static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode *inode);
-static const struct rpc_call_ops nfs_write_direct_ops;
+static void nfs_direct_write_schedule_work(struct work_struct *work);
 
 static inline void get_dreq(struct nfs_direct_req *dreq)
 {
@@ -124,22 +128,6 @@ ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_
 	return -EINVAL;
 }
 
-static void nfs_direct_dirty_pages(struct page **pages, unsigned int pgbase, size_t count)
-{
-	unsigned int npages;
-	unsigned int i;
-
-	if (count == 0)
-		return;
-	pages += (pgbase >> PAGE_SHIFT);
-	npages = (count + (pgbase & ~PAGE_MASK) + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	for (i = 0; i < npages; i++) {
-		struct page *page = pages[i];
-		if (!PageCompound(page))
-			set_page_dirty(page);
-	}
-}
-
 static void nfs_direct_release_pages(struct page **pages, unsigned int npages)
 {
 	unsigned int i;
@@ -147,26 +135,30 @@ static void nfs_direct_release_pages(struct page **pages, unsigned int npages)
 		page_cache_release(pages[i]);
 }
 
+void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo,
+			      struct nfs_direct_req *dreq)
+{
+	cinfo->lock = &dreq->lock;
+	cinfo->mds = &dreq->mds_cinfo;
+	cinfo->ds = &dreq->ds_cinfo;
+	cinfo->dreq = dreq;
+	cinfo->completion_ops = &nfs_direct_commit_completion_ops;
+}
+
 static inline struct nfs_direct_req *nfs_direct_req_alloc(void)
 {
 	struct nfs_direct_req *dreq;
 
-	dreq = kmem_cache_alloc(nfs_direct_cachep, GFP_KERNEL);
+	dreq = kmem_cache_zalloc(nfs_direct_cachep, GFP_KERNEL);
 	if (!dreq)
 		return NULL;
 
 	kref_init(&dreq->kref);
 	kref_get(&dreq->kref);
 	init_completion(&dreq->completion);
-	INIT_LIST_HEAD(&dreq->rewrite_list);
-	dreq->iocb = NULL;
-	dreq->ctx = NULL;
-	dreq->l_ctx = NULL;
+	INIT_LIST_HEAD(&dreq->mds_cinfo.list);
+	INIT_WORK(&dreq->work, nfs_direct_write_schedule_work);
 	spin_lock_init(&dreq->lock);
-	atomic_set(&dreq->io_count, 0);
-	dreq->count = 0;
-	dreq->error = 0;
-	dreq->flags = 0;
 
 	return dreq;
 }
@@ -226,47 +218,80 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq)
 	nfs_direct_req_release(dreq);
 }
 
-/*
- * We must hold a reference to all the pages in this direct read request
- * until the RPCs complete.  This could be long *after* we are woken up in
- * nfs_direct_wait (for instance, if someone hits ^C on a slow server).
- */
-static void nfs_direct_read_result(struct rpc_task *task, void *calldata)
+static void nfs_direct_readpage_release(struct nfs_page *req)
 {
-	struct nfs_read_data *data = calldata;
-
-	nfs_readpage_result(task, data);
+	dprintk("NFS: direct read done (%s/%lld %d@%lld)\n",
+		req->wb_context->dentry->d_inode->i_sb->s_id,
+		(long long)NFS_FILEID(req->wb_context->dentry->d_inode),
+		req->wb_bytes,
+		(long long)req_offset(req));
+	nfs_release_request(req);
 }
 
-static void nfs_direct_read_release(void *calldata)
+static void nfs_direct_read_completion(struct nfs_pgio_header *hdr)
 {
+	unsigned long bytes = 0;
+	struct nfs_direct_req *dreq = hdr->dreq;
 
-	struct nfs_read_data *data = calldata;
-	struct nfs_direct_req *dreq = (struct nfs_direct_req *) data->req;
-	int status = data->task.tk_status;
+	if (test_bit(NFS_IOHDR_REDO, &hdr->flags))
+		goto out_put;
 
 	spin_lock(&dreq->lock);
-	if (unlikely(status < 0)) {
-		dreq->error = status;
-		spin_unlock(&dreq->lock);
-	} else {
-		dreq->count += data->res.count;
-		spin_unlock(&dreq->lock);
-		nfs_direct_dirty_pages(data->pagevec,
-				data->args.pgbase,
-				data->res.count);
-	}
-	nfs_direct_release_pages(data->pagevec, data->npages);
+	if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && (hdr->good_bytes == 0))
+		dreq->error = hdr->error;
+	else
+		dreq->count += hdr->good_bytes;
+	spin_unlock(&dreq->lock);
 
+	while (!list_empty(&hdr->pages)) {
+		struct nfs_page *req = nfs_list_entry(hdr->pages.next);
+		struct page *page = req->wb_page;
+
+		if (test_bit(NFS_IOHDR_EOF, &hdr->flags)) {
+			if (bytes > hdr->good_bytes)
+				zero_user(page, 0, PAGE_SIZE);
+			else if (hdr->good_bytes - bytes < PAGE_SIZE)
+				zero_user_segment(page,
+					hdr->good_bytes & ~PAGE_MASK,
+					PAGE_SIZE);
+		}
+		if (!PageCompound(page)) {
+			if (test_bit(NFS_IOHDR_ERROR, &hdr->flags)) {
+				if (bytes < hdr->good_bytes)
+					set_page_dirty(page);
+			} else
+				set_page_dirty(page);
+		}
+		bytes += req->wb_bytes;
+		nfs_list_remove_request(req);
+		nfs_direct_readpage_release(req);
+	}
+out_put:
 	if (put_dreq(dreq))
 		nfs_direct_complete(dreq);
-	nfs_readdata_free(data);
+	hdr->release(hdr);
+}
+
+static void nfs_read_sync_pgio_error(struct list_head *head)
+{
+	struct nfs_page *req;
+
+	while (!list_empty(head)) {
+		req = nfs_list_entry(head->next);
+		nfs_list_remove_request(req);
+		nfs_release_request(req);
+	}
 }
 
-static const struct rpc_call_ops nfs_read_direct_ops = {
-	.rpc_call_prepare = nfs_read_prepare,
-	.rpc_call_done = nfs_direct_read_result,
-	.rpc_release = nfs_direct_read_release,
+static void nfs_direct_pgio_init(struct nfs_pgio_header *hdr)
+{
+	get_dreq(hdr->dreq);
+}
+
+static const struct nfs_pgio_completion_ops nfs_direct_read_completion_ops = {
+	.error_cleanup = nfs_read_sync_pgio_error,
+	.init_hdr = nfs_direct_pgio_init,
+	.completion = nfs_direct_read_completion,
 };
 
 /*
@@ -276,107 +301,82 @@ static const struct rpc_call_ops nfs_read_direct_ops = {
  * handled automatically by nfs_direct_read_result().  Otherwise, if
  * no requests have been sent, just return an error.
  */
-static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq,
+static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *desc,
 						const struct iovec *iov,
 						loff_t pos)
 {
+	struct nfs_direct_req *dreq = desc->pg_dreq;
 	struct nfs_open_context *ctx = dreq->ctx;
 	struct inode *inode = ctx->dentry->d_inode;
 	unsigned long user_addr = (unsigned long)iov->iov_base;
 	size_t count = iov->iov_len;
 	size_t rsize = NFS_SERVER(inode)->rsize;
-	struct rpc_task *task;
-	struct rpc_message msg = {
-		.rpc_cred = ctx->cred,
-	};
-	struct rpc_task_setup task_setup_data = {
-		.rpc_client = NFS_CLIENT(inode),
-		.rpc_message = &msg,
-		.callback_ops = &nfs_read_direct_ops,
-		.workqueue = nfsiod_workqueue,
-		.flags = RPC_TASK_ASYNC,
-	};
 	unsigned int pgbase;
 	int result;
 	ssize_t started = 0;
+	struct page **pagevec = NULL;
+	unsigned int npages;
 
 	do {
-		struct nfs_read_data *data;
 		size_t bytes;
+		int i;
 
 		pgbase = user_addr & ~PAGE_MASK;
-		bytes = min(rsize,count);
+		bytes = min(max_t(size_t, rsize, PAGE_SIZE), count);
 
 		result = -ENOMEM;
-		data = nfs_readdata_alloc(nfs_page_array_len(pgbase, bytes));
-		if (unlikely(!data))
+		npages = nfs_page_array_len(pgbase, bytes);
+		if (!pagevec)
+			pagevec = kmalloc(npages * sizeof(struct page *),
+					  GFP_KERNEL);
+		if (!pagevec)
 			break;
-
 		down_read(&current->mm->mmap_sem);
 		result = get_user_pages(current, current->mm, user_addr,
-					data->npages, 1, 0, data->pagevec, NULL);
+					npages, 1, 0, pagevec, NULL);
 		up_read(&current->mm->mmap_sem);
-		if (result < 0) {
-			nfs_readdata_free(data);
+		if (result < 0)
 			break;
-		}
-		if ((unsigned)result < data->npages) {
+		if ((unsigned)result < npages) {
 			bytes = result * PAGE_SIZE;
 			if (bytes <= pgbase) {
-				nfs_direct_release_pages(data->pagevec, result);
-				nfs_readdata_free(data);
+				nfs_direct_release_pages(pagevec, result);
 				break;
 			}
 			bytes -= pgbase;
-			data->npages = result;
+			npages = result;
 		}
 
-		get_dreq(dreq);
-
-		data->req = (struct nfs_page *) dreq;
-		data->inode = inode;
-		data->cred = msg.rpc_cred;
-		data->args.fh = NFS_FH(inode);
-		data->args.context = ctx;
-		data->args.lock_context = dreq->l_ctx;
-		data->args.offset = pos;
-		data->args.pgbase = pgbase;
-		data->args.pages = data->pagevec;
-		data->args.count = bytes;
-		data->res.fattr = &data->fattr;
-		data->res.eof = 0;
-		data->res.count = bytes;
-		nfs_fattr_init(&data->fattr);
-		msg.rpc_argp = &data->args;
-		msg.rpc_resp = &data->res;
-
-		task_setup_data.task = &data->task;
-		task_setup_data.callback_data = data;
-		NFS_PROTO(inode)->read_setup(data, &msg);
-
-		task = rpc_run_task(&task_setup_data);
-		if (IS_ERR(task))
-			break;
-		rpc_put_task(task);
-
-		dprintk("NFS: %5u initiated direct read call "
-			"(req %s/%Ld, %zu bytes @ offset %Lu)\n",
-				data->task.tk_pid,
-				inode->i_sb->s_id,
-				(long long)NFS_FILEID(inode),
-				bytes,
-				(unsigned long long)data->args.offset);
-
-		started += bytes;
-		user_addr += bytes;
-		pos += bytes;
-		/* FIXME: Remove this unnecessary math from final patch */
-		pgbase += bytes;
-		pgbase &= ~PAGE_MASK;
-		BUG_ON(pgbase != (user_addr & ~PAGE_MASK));
-
-		count -= bytes;
-	} while (count != 0);
+		for (i = 0; i < npages; i++) {
+			struct nfs_page *req;
+			unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase);
+			/* XXX do we need to do the eof zeroing found in async_filler? */
+			req = nfs_create_request(dreq->ctx, dreq->inode,
+						 pagevec[i],
+						 pgbase, req_len);
+			if (IS_ERR(req)) {
+				result = PTR_ERR(req);
+				break;
+			}
+			req->wb_index = pos >> PAGE_SHIFT;
+			req->wb_offset = pos & ~PAGE_MASK;
+			if (!nfs_pageio_add_request(desc, req)) {
+				result = desc->pg_error;
+				nfs_release_request(req);
+				break;
+			}
+			pgbase = 0;
+			bytes -= req_len;
+			started += req_len;
+			user_addr += req_len;
+			pos += req_len;
+			count -= req_len;
+		}
+		/* The nfs_page now hold references to these pages */
+		nfs_direct_release_pages(pagevec, npages);
+	} while (count != 0 && result >= 0);
+
+	kfree(pagevec);
 
 	if (started)
 		return started;
@@ -388,15 +388,19 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 					      unsigned long nr_segs,
 					      loff_t pos)
 {
+	struct nfs_pageio_descriptor desc;
 	ssize_t result = -EINVAL;
 	size_t requested_bytes = 0;
 	unsigned long seg;
 
+	nfs_pageio_init_read(&desc, dreq->inode,
+			     &nfs_direct_read_completion_ops);
 	get_dreq(dreq);
+	desc.pg_dreq = dreq;
 
 	for (seg = 0; seg < nr_segs; seg++) {
 		const struct iovec *vec = &iov[seg];
-		result = nfs_direct_read_schedule_segment(dreq, vec, pos);
+		result = nfs_direct_read_schedule_segment(&desc, vec, pos);
 		if (result < 0)
 			break;
 		requested_bytes += result;
@@ -405,6 +409,8 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 		pos += vec->iov_len;
 	}
 
+	nfs_pageio_complete(&desc);
+
 	/*
 	 * If no bytes were started, return the error, and let the
 	 * generic layer handle the completion.
@@ -441,104 +447,64 @@ static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov,
 	result = nfs_direct_read_schedule_iovec(dreq, iov, nr_segs, pos);
 	if (!result)
 		result = nfs_direct_wait(dreq);
+	NFS_I(inode)->read_io += result;
 out_release:
 	nfs_direct_req_release(dreq);
 out:
 	return result;
 }
 
-static void nfs_direct_free_writedata(struct nfs_direct_req *dreq)
-{
-	while (!list_empty(&dreq->rewrite_list)) {
-		struct nfs_write_data *data = list_entry(dreq->rewrite_list.next, struct nfs_write_data, pages);
-		list_del(&data->pages);
-		nfs_direct_release_pages(data->pagevec, data->npages);
-		nfs_writedata_free(data);
-	}
-}
-
 #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
 static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
 {
-	struct inode *inode = dreq->inode;
-	struct list_head *p;
-	struct nfs_write_data *data;
-	struct rpc_task *task;
-	struct rpc_message msg = {
-		.rpc_cred = dreq->ctx->cred,
-	};
-	struct rpc_task_setup task_setup_data = {
-		.rpc_client = NFS_CLIENT(inode),
-		.rpc_message = &msg,
-		.callback_ops = &nfs_write_direct_ops,
-		.workqueue = nfsiod_workqueue,
-		.flags = RPC_TASK_ASYNC,
-	};
+	struct nfs_pageio_descriptor desc;
+	struct nfs_page *req, *tmp;
+	LIST_HEAD(reqs);
+	struct nfs_commit_info cinfo;
+	LIST_HEAD(failed);
+
+	nfs_init_cinfo_from_dreq(&cinfo, dreq);
+	pnfs_recover_commit_reqs(dreq->inode, &reqs, &cinfo);
+	spin_lock(cinfo.lock);
+	nfs_scan_commit_list(&cinfo.mds->list, &reqs, &cinfo, 0);
+	spin_unlock(cinfo.lock);
 
 	dreq->count = 0;
 	get_dreq(dreq);
 
-	list_for_each(p, &dreq->rewrite_list) {
-		data = list_entry(p, struct nfs_write_data, pages);
-
-		get_dreq(dreq);
-
-		/* Use stable writes */
-		data->args.stable = NFS_FILE_SYNC;
-
-		/*
-		 * Reset data->res.
-		 */
-		nfs_fattr_init(&data->fattr);
-		data->res.count = data->args.count;
-		memset(&data->verf, 0, sizeof(data->verf));
-
-		/*
-		 * Reuse data->task; data->args should not have changed
-		 * since the original request was sent.
-		 */
-		task_setup_data.task = &data->task;
-		task_setup_data.callback_data = data;
-		msg.rpc_argp = &data->args;
-		msg.rpc_resp = &data->res;
-		NFS_PROTO(inode)->write_setup(data, &msg);
-
-		/*
-		 * We're called via an RPC callback, so BKL is already held.
-		 */
-		task = rpc_run_task(&task_setup_data);
-		if (!IS_ERR(task))
-			rpc_put_task(task);
-
-		dprintk("NFS: %5u rescheduled direct write call (req %s/%Ld, %u bytes @ offset %Lu)\n",
-				data->task.tk_pid,
-				inode->i_sb->s_id,
-				(long long)NFS_FILEID(inode),
-				data->args.count,
-				(unsigned long long)data->args.offset);
+	nfs_pageio_init_write(&desc, dreq->inode, FLUSH_STABLE,
+			      &nfs_direct_write_completion_ops);
+	desc.pg_dreq = dreq;
+
+	list_for_each_entry_safe(req, tmp, &reqs, wb_list) {
+		if (!nfs_pageio_add_request(&desc, req)) {
+			nfs_list_add_request(req, &failed);
+			spin_lock(cinfo.lock);
+			dreq->flags = 0;
+			dreq->error = -EIO;
+			spin_unlock(cinfo.lock);
+		}
 	}
+	nfs_pageio_complete(&desc);
 
-	if (put_dreq(dreq))
-		nfs_direct_write_complete(dreq, inode);
-}
-
-static void nfs_direct_commit_result(struct rpc_task *task, void *calldata)
-{
-	struct nfs_write_data *data = calldata;
+	while (!list_empty(&failed))
+		nfs_unlock_and_release_request(req);
 
-	/* Call the NFS version-specific code */
-	NFS_PROTO(data->inode)->commit_done(task, data);
+	if (put_dreq(dreq))
+		nfs_direct_write_complete(dreq, dreq->inode);
 }
 
-static void nfs_direct_commit_release(void *calldata)
+static void nfs_direct_commit_complete(struct nfs_commit_data *data)
 {
-	struct nfs_write_data *data = calldata;
-	struct nfs_direct_req *dreq = (struct nfs_direct_req *) data->req;
+	struct nfs_direct_req *dreq = data->dreq;
+	struct nfs_commit_info cinfo;
+	struct nfs_page *req;
 	int status = data->task.tk_status;
 
+	nfs_init_cinfo_from_dreq(&cinfo, dreq);
 	if (status < 0) {
 		dprintk("NFS: %5u commit failed with error %d.\n",
-				data->task.tk_pid, status);
+			data->task.tk_pid, status);
 		dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
 	} else if (memcmp(&dreq->verf, &data->verf, sizeof(data->verf))) {
 		dprintk("NFS: %5u commit verify failed\n", data->task.tk_pid);
@@ -546,62 +512,47 @@ static void nfs_direct_commit_release(void *calldata)
 	}
 
 	dprintk("NFS: %5u commit returned %d\n", data->task.tk_pid, status);
-	nfs_direct_write_complete(dreq, data->inode);
-	nfs_commit_free(data);
+	while (!list_empty(&data->pages)) {
+		req = nfs_list_entry(data->pages.next);
+		nfs_list_remove_request(req);
+		if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES) {
+			/* Note the rewrite will go through mds */
+			kref_get(&req->wb_kref);
+			nfs_mark_request_commit(req, NULL, &cinfo);
+		}
+		nfs_unlock_and_release_request(req);
+	}
+
+	if (atomic_dec_and_test(&cinfo.mds->rpcs_out))
+		nfs_direct_write_complete(dreq, data->inode);
+}
+
+static void nfs_direct_error_cleanup(struct nfs_inode *nfsi)
+{
+	/* There is no lock to clear */
 }
 
-static const struct rpc_call_ops nfs_commit_direct_ops = {
-	.rpc_call_prepare = nfs_write_prepare,
-	.rpc_call_done = nfs_direct_commit_result,
-	.rpc_release = nfs_direct_commit_release,
+static const struct nfs_commit_completion_ops nfs_direct_commit_completion_ops = {
+	.completion = nfs_direct_commit_complete,
+	.error_cleanup = nfs_direct_error_cleanup,
 };
 
 static void nfs_direct_commit_schedule(struct nfs_direct_req *dreq)
 {
-	struct nfs_write_data *data = dreq->commit_data;
-	struct rpc_task *task;
-	struct rpc_message msg = {
-		.rpc_argp = &data->args,
-		.rpc_resp = &data->res,
-		.rpc_cred = dreq->ctx->cred,
-	};
-	struct rpc_task_setup task_setup_data = {
-		.task = &data->task,
-		.rpc_client = NFS_CLIENT(dreq->inode),
-		.rpc_message = &msg,
-		.callback_ops = &nfs_commit_direct_ops,
-		.callback_data = data,
-		.workqueue = nfsiod_workqueue,
-		.flags = RPC_TASK_ASYNC,
-	};
-
-	data->inode = dreq->inode;
-	data->cred = msg.rpc_cred;
-
-	data->args.fh = NFS_FH(data->inode);
-	data->args.offset = 0;
-	data->args.count = 0;
-	data->args.context = dreq->ctx;
-	data->args.lock_context = dreq->l_ctx;
-	data->res.count = 0;
-	data->res.fattr = &data->fattr;
-	data->res.verf = &data->verf;
-	nfs_fattr_init(&data->fattr);
-
-	NFS_PROTO(data->inode)->commit_setup(data, &msg);
-
-	/* Note: task.tk_ops->rpc_release will free dreq->commit_data */
-	dreq->commit_data = NULL;
-
-	dprintk("NFS: %5u initiated commit call\n", data->task.tk_pid);
-
-	task = rpc_run_task(&task_setup_data);
-	if (!IS_ERR(task))
-		rpc_put_task(task);
+	int res;
+	struct nfs_commit_info cinfo;
+	LIST_HEAD(mds_list);
+
+	nfs_init_cinfo_from_dreq(&cinfo, dreq);
+	nfs_scan_commit(dreq->inode, &mds_list, &cinfo);
+	res = nfs_generic_commit_list(dreq->inode, &mds_list, 0, &cinfo);
+	if (res < 0) /* res == -ENOMEM */
+		nfs_direct_write_reschedule(dreq);
 }
 
-static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode *inode)
+static void nfs_direct_write_schedule_work(struct work_struct *work)
 {
+	struct nfs_direct_req *dreq = container_of(work, struct nfs_direct_req, work);
 	int flags = dreq->flags;
 
 	dreq->flags = 0;
@@ -613,89 +564,32 @@ static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode
 			nfs_direct_write_reschedule(dreq);
 			break;
 		default:
-			if (dreq->commit_data != NULL)
-				nfs_commit_free(dreq->commit_data);
-			nfs_direct_free_writedata(dreq);
-			nfs_zap_mapping(inode, inode->i_mapping);
+			nfs_zap_mapping(dreq->inode, dreq->inode->i_mapping);
 			nfs_direct_complete(dreq);
 	}
 }
 
-static void nfs_alloc_commit_data(struct nfs_direct_req *dreq)
+static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode *inode)
 {
-	dreq->commit_data = nfs_commitdata_alloc();
-	if (dreq->commit_data != NULL)
-		dreq->commit_data->req = (struct nfs_page *) dreq;
+	schedule_work(&dreq->work); /* Calls nfs_direct_write_schedule_work */
 }
+
 #else
-static inline void nfs_alloc_commit_data(struct nfs_direct_req *dreq)
+static void nfs_direct_write_schedule_work(struct work_struct *work)
 {
-	dreq->commit_data = NULL;
 }
 
 static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode *inode)
 {
-	nfs_direct_free_writedata(dreq);
 	nfs_zap_mapping(inode, inode->i_mapping);
 	nfs_direct_complete(dreq);
 }
 #endif
 
-static void nfs_direct_write_result(struct rpc_task *task, void *calldata)
-{
-	struct nfs_write_data *data = calldata;
-
-	nfs_writeback_done(task, data);
-}
-
 /*
  * NB: Return the value of the first error return code.  Subsequent
  *     errors after the first one are ignored.
  */
-static void nfs_direct_write_release(void *calldata)
-{
-	struct nfs_write_data *data = calldata;
-	struct nfs_direct_req *dreq = (struct nfs_direct_req *) data->req;
-	int status = data->task.tk_status;
-
-	spin_lock(&dreq->lock);
-
-	if (unlikely(status < 0)) {
-		/* An error has occurred, so we should not commit */
-		dreq->flags = 0;
-		dreq->error = status;
-	}
-	if (unlikely(dreq->error != 0))
-		goto out_unlock;
-
-	dreq->count += data->res.count;
-
-	if (data->res.verf->committed != NFS_FILE_SYNC) {
-		switch (dreq->flags) {
-			case 0:
-				memcpy(&dreq->verf, &data->verf, sizeof(dreq->verf));
-				dreq->flags = NFS_ODIRECT_DO_COMMIT;
-				break;
-			case NFS_ODIRECT_DO_COMMIT:
-				if (memcmp(&dreq->verf, &data->verf, sizeof(dreq->verf))) {
-					dprintk("NFS: %5u write verify failed\n", data->task.tk_pid);
-					dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
-				}
-		}
-	}
-out_unlock:
-	spin_unlock(&dreq->lock);
-
-	if (put_dreq(dreq))
-		nfs_direct_write_complete(dreq, data->inode);
-}
-
-static const struct rpc_call_ops nfs_write_direct_ops = {
-	.rpc_call_prepare = nfs_write_prepare,
-	.rpc_call_done = nfs_direct_write_result,
-	.rpc_release = nfs_direct_write_release,
-};
-
 /*
  * For each wsize'd chunk of the user's buffer, dispatch an NFS WRITE
  * operation.  If nfs_writedata_alloc() or get_user_pages() fails,
@@ -703,132 +597,187 @@ static const struct rpc_call_ops nfs_write_direct_ops = {
  * handled automatically by nfs_direct_write_result().  Otherwise, if
  * no requests have been sent, just return an error.
  */
-static ssize_t nfs_direct_write_schedule_segment(struct nfs_direct_req *dreq,
+static ssize_t nfs_direct_write_schedule_segment(struct nfs_pageio_descriptor *desc,
 						 const struct iovec *iov,
-						 loff_t pos, int sync)
+						 loff_t pos)
 {
+	struct nfs_direct_req *dreq = desc->pg_dreq;
 	struct nfs_open_context *ctx = dreq->ctx;
 	struct inode *inode = ctx->dentry->d_inode;
 	unsigned long user_addr = (unsigned long)iov->iov_base;
 	size_t count = iov->iov_len;
-	struct rpc_task *task;
-	struct rpc_message msg = {
-		.rpc_cred = ctx->cred,
-	};
-	struct rpc_task_setup task_setup_data = {
-		.rpc_client = NFS_CLIENT(inode),
-		.rpc_message = &msg,
-		.callback_ops = &nfs_write_direct_ops,
-		.workqueue = nfsiod_workqueue,
-		.flags = RPC_TASK_ASYNC,
-	};
 	size_t wsize = NFS_SERVER(inode)->wsize;
 	unsigned int pgbase;
 	int result;
 	ssize_t started = 0;
+	struct page **pagevec = NULL;
+	unsigned int npages;
 
 	do {
-		struct nfs_write_data *data;
 		size_t bytes;
+		int i;
 
 		pgbase = user_addr & ~PAGE_MASK;
-		bytes = min(wsize,count);
+		bytes = min(max_t(size_t, wsize, PAGE_SIZE), count);
 
 		result = -ENOMEM;
-		data = nfs_writedata_alloc(nfs_page_array_len(pgbase, bytes));
-		if (unlikely(!data))
+		npages = nfs_page_array_len(pgbase, bytes);
+		if (!pagevec)
+			pagevec = kmalloc(npages * sizeof(struct page *), GFP_KERNEL);
+		if (!pagevec)
 			break;
 
 		down_read(&current->mm->mmap_sem);
 		result = get_user_pages(current, current->mm, user_addr,
-					data->npages, 0, 0, data->pagevec, NULL);
+					npages, 0, 0, pagevec, NULL);
 		up_read(&current->mm->mmap_sem);
-		if (result < 0) {
-			nfs_writedata_free(data);
+		if (result < 0)
 			break;
-		}
-		if ((unsigned)result < data->npages) {
+
+		if ((unsigned)result < npages) {
 			bytes = result * PAGE_SIZE;
 			if (bytes <= pgbase) {
-				nfs_direct_release_pages(data->pagevec, result);
-				nfs_writedata_free(data);
+				nfs_direct_release_pages(pagevec, result);
 				break;
 			}
 			bytes -= pgbase;
-			data->npages = result;
+			npages = result;
 		}
 
-		get_dreq(dreq);
-
-		list_move_tail(&data->pages, &dreq->rewrite_list);
-
-		data->req = (struct nfs_page *) dreq;
-		data->inode = inode;
-		data->cred = msg.rpc_cred;
-		data->args.fh = NFS_FH(inode);
-		data->args.context = ctx;
-		data->args.lock_context = dreq->l_ctx;
-		data->args.offset = pos;
-		data->args.pgbase = pgbase;
-		data->args.pages = data->pagevec;
-		data->args.count = bytes;
-		data->args.stable = sync;
-		data->res.fattr = &data->fattr;
-		data->res.count = bytes;
-		data->res.verf = &data->verf;
-		nfs_fattr_init(&data->fattr);
-
-		task_setup_data.task = &data->task;
-		task_setup_data.callback_data = data;
-		msg.rpc_argp = &data->args;
-		msg.rpc_resp = &data->res;
-		NFS_PROTO(inode)->write_setup(data, &msg);
-
-		task = rpc_run_task(&task_setup_data);
-		if (IS_ERR(task))
-			break;
-		rpc_put_task(task);
-
-		dprintk("NFS: %5u initiated direct write call "
-			"(req %s/%Ld, %zu bytes @ offset %Lu)\n",
-				data->task.tk_pid,
-				inode->i_sb->s_id,
-				(long long)NFS_FILEID(inode),
-				bytes,
-				(unsigned long long)data->args.offset);
+		for (i = 0; i < npages; i++) {
+			struct nfs_page *req;
+			unsigned int req_len = min_t(size_t, bytes, PAGE_SIZE - pgbase);
 
-		started += bytes;
-		user_addr += bytes;
-		pos += bytes;
-
-		/* FIXME: Remove this useless math from the final patch */
-		pgbase += bytes;
-		pgbase &= ~PAGE_MASK;
-		BUG_ON(pgbase != (user_addr & ~PAGE_MASK));
+			req = nfs_create_request(dreq->ctx, dreq->inode,
+						 pagevec[i],
+						 pgbase, req_len);
+			if (IS_ERR(req)) {
+				result = PTR_ERR(req);
+				break;
+			}
+			nfs_lock_request(req);
+			req->wb_index = pos >> PAGE_SHIFT;
+			req->wb_offset = pos & ~PAGE_MASK;
+			if (!nfs_pageio_add_request(desc, req)) {
+				result = desc->pg_error;
+				nfs_unlock_and_release_request(req);
+				break;
+			}
+			pgbase = 0;
+			bytes -= req_len;
+			started += req_len;
+			user_addr += req_len;
+			pos += req_len;
+			count -= req_len;
+		}
+		/* The nfs_page now hold references to these pages */
+		nfs_direct_release_pages(pagevec, npages);
+	} while (count != 0 && result >= 0);
 
-		count -= bytes;
-	} while (count != 0);
+	kfree(pagevec);
 
 	if (started)
 		return started;
 	return result < 0 ? (ssize_t) result : -EFAULT;
 }
 
+static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
+{
+	struct nfs_direct_req *dreq = hdr->dreq;
+	struct nfs_commit_info cinfo;
+	int bit = -1;
+	struct nfs_page *req = nfs_list_entry(hdr->pages.next);
+
+	if (test_bit(NFS_IOHDR_REDO, &hdr->flags))
+		goto out_put;
+
+	nfs_init_cinfo_from_dreq(&cinfo, dreq);
+
+	spin_lock(&dreq->lock);
+
+	if (test_bit(NFS_IOHDR_ERROR, &hdr->flags)) {
+		dreq->flags = 0;
+		dreq->error = hdr->error;
+	}
+	if (dreq->error != 0)
+		bit = NFS_IOHDR_ERROR;
+	else {
+		dreq->count += hdr->good_bytes;
+		if (test_bit(NFS_IOHDR_NEED_RESCHED, &hdr->flags)) {
+			dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
+			bit = NFS_IOHDR_NEED_RESCHED;
+		} else if (test_bit(NFS_IOHDR_NEED_COMMIT, &hdr->flags)) {
+			if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES)
+				bit = NFS_IOHDR_NEED_RESCHED;
+			else if (dreq->flags == 0) {
+				memcpy(&dreq->verf, &req->wb_verf,
+				       sizeof(dreq->verf));
+				bit = NFS_IOHDR_NEED_COMMIT;
+				dreq->flags = NFS_ODIRECT_DO_COMMIT;
+			} else if (dreq->flags == NFS_ODIRECT_DO_COMMIT) {
+				if (memcmp(&dreq->verf, &req->wb_verf, sizeof(dreq->verf))) {
+					dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
+					bit = NFS_IOHDR_NEED_RESCHED;
+				} else
+					bit = NFS_IOHDR_NEED_COMMIT;
+			}
+		}
+	}
+	spin_unlock(&dreq->lock);
+
+	while (!list_empty(&hdr->pages)) {
+		req = nfs_list_entry(hdr->pages.next);
+		nfs_list_remove_request(req);
+		switch (bit) {
+		case NFS_IOHDR_NEED_RESCHED:
+		case NFS_IOHDR_NEED_COMMIT:
+			kref_get(&req->wb_kref);
+			nfs_mark_request_commit(req, hdr->lseg, &cinfo);
+		}
+		nfs_unlock_and_release_request(req);
+	}
+
+out_put:
+	if (put_dreq(dreq))
+		nfs_direct_write_complete(dreq, hdr->inode);
+	hdr->release(hdr);
+}
+
+static void nfs_write_sync_pgio_error(struct list_head *head)
+{
+	struct nfs_page *req;
+
+	while (!list_empty(head)) {
+		req = nfs_list_entry(head->next);
+		nfs_list_remove_request(req);
+		nfs_unlock_and_release_request(req);
+	}
+}
+
+static const struct nfs_pgio_completion_ops nfs_direct_write_completion_ops = {
+	.error_cleanup = nfs_write_sync_pgio_error,
+	.init_hdr = nfs_direct_pgio_init,
+	.completion = nfs_direct_write_completion,
+};
+
 static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 					       const struct iovec *iov,
 					       unsigned long nr_segs,
-					       loff_t pos, int sync)
+					       loff_t pos)
 {
+	struct nfs_pageio_descriptor desc;
 	ssize_t result = 0;
 	size_t requested_bytes = 0;
 	unsigned long seg;
 
+	nfs_pageio_init_write(&desc, dreq->inode, FLUSH_COND_STABLE,
+			      &nfs_direct_write_completion_ops);
+	desc.pg_dreq = dreq;
 	get_dreq(dreq);
 
 	for (seg = 0; seg < nr_segs; seg++) {
 		const struct iovec *vec = &iov[seg];
-		result = nfs_direct_write_schedule_segment(dreq, vec,
-							   pos, sync);
+		result = nfs_direct_write_schedule_segment(&desc, vec, pos);
 		if (result < 0)
 			break;
 		requested_bytes += result;
@@ -836,6 +785,8 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 			break;
 		pos += vec->iov_len;
 	}
+	nfs_pageio_complete(&desc);
+	NFS_I(dreq->inode)->write_io += desc.pg_bytes_written;
 
 	/*
 	 * If no bytes were started, return the error, and let the
@@ -858,16 +809,10 @@ static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov,
 	ssize_t result = -ENOMEM;
 	struct inode *inode = iocb->ki_filp->f_mapping->host;
 	struct nfs_direct_req *dreq;
-	size_t wsize = NFS_SERVER(inode)->wsize;
-	int sync = NFS_UNSTABLE;
 
 	dreq = nfs_direct_req_alloc();
 	if (!dreq)
 		goto out;
-	nfs_alloc_commit_data(dreq);
-
-	if (dreq->commit_data == NULL || count <= wsize)
-		sync = NFS_FILE_SYNC;
 
 	dreq->inode = inode;
 	dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
@@ -877,7 +822,7 @@ static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov,
 	if (!is_sync_kiocb(iocb))
 		dreq->iocb = iocb;
 
-	result = nfs_direct_write_schedule_iovec(dreq, iov, nr_segs, pos, sync);
+	result = nfs_direct_write_schedule_iovec(dreq, iov, nr_segs, pos);
 	if (!result)
 		result = nfs_direct_wait(dreq);
 out_release:
@@ -997,10 +942,15 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
 	task_io_account_write(count);
 
 	retval = nfs_direct_write(iocb, iov, nr_segs, pos, count);
+	if (retval > 0) {
+		struct inode *inode = mapping->host;
 
-	if (retval > 0)
 		iocb->ki_pos = pos + retval;
-
+		spin_lock(&inode->i_lock);
+		if (i_size_read(inode) < iocb->ki_pos)
+			i_size_write(inode, iocb->ki_pos);
+		spin_unlock(&inode->i_lock);
+	}
 out:
 	return retval;
 }
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index aa9b709fd328..56311ca5f9f8 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -174,6 +174,13 @@ nfs_file_flush(struct file *file, fl_owner_t id)
 	if ((file->f_mode & FMODE_WRITE) == 0)
 		return 0;
 
+	/*
+	 * If we're holding a write delegation, then just start the i/o
+	 * but don't wait for completion (or send a commit).
+	 */
+	if (nfs_have_delegation(inode, FMODE_WRITE))
+		return filemap_fdatawrite(file->f_mapping);
+
 	/* Flush writes to the server and return any errors */
 	return vfs_fsync(file, 0);
 }
@@ -417,6 +424,7 @@ static int nfs_write_end(struct file *file, struct address_space *mapping,
 
 	if (status < 0)
 		return status;
+	NFS_I(mapping->host)->write_io += copied;
 	return copied;
 }
 
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
index ae65c16b3670..c817787fbdb4 100644
--- a/fs/nfs/fscache.c
+++ b/fs/nfs/fscache.c
@@ -64,23 +64,12 @@ void nfs_fscache_release_client_cookie(struct nfs_client *clp)
  * either by the 'fsc=xxx' option to mount, or by inheriting it from the parent
  * superblock across an automount point of some nature.
  */
-void nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq,
-				  struct nfs_clone_mount *mntdata)
+void nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq, int ulen)
 {
 	struct nfs_fscache_key *key, *xkey;
 	struct nfs_server *nfss = NFS_SB(sb);
 	struct rb_node **p, *parent;
-	int diff, ulen;
-
-	if (uniq) {
-		ulen = strlen(uniq);
-	} else if (mntdata) {
-		struct nfs_server *mnt_s = NFS_SB(mntdata->sb);
-		if (mnt_s->fscache_key) {
-			uniq = mnt_s->fscache_key->key.uniquifier;
-			ulen = mnt_s->fscache_key->key.uniq_len;
-		}
-	}
+	int diff;
 
 	if (!uniq) {
 		uniq = "";
diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h
index b9c572d0679f..c5b11b53ff33 100644
--- a/fs/nfs/fscache.h
+++ b/fs/nfs/fscache.h
@@ -73,9 +73,7 @@ extern void nfs_fscache_unregister(void);
 extern void nfs_fscache_get_client_cookie(struct nfs_client *);
 extern void nfs_fscache_release_client_cookie(struct nfs_client *);
 
-extern void nfs_fscache_get_super_cookie(struct super_block *,
-					 const char *,
-					 struct nfs_clone_mount *);
+extern void nfs_fscache_get_super_cookie(struct super_block *, const char *, int);
 extern void nfs_fscache_release_super_cookie(struct super_block *);
 
 extern void nfs_fscache_init_inode_cookie(struct inode *);
@@ -172,12 +170,6 @@ static inline void nfs_fscache_unregister(void) {}
 static inline void nfs_fscache_get_client_cookie(struct nfs_client *clp) {}
 static inline void nfs_fscache_release_client_cookie(struct nfs_client *clp) {}
 
-static inline void nfs_fscache_get_super_cookie(
-	struct super_block *sb,
-	const char *uniq,
-	struct nfs_clone_mount *mntdata)
-{
-}
 static inline void nfs_fscache_release_super_cookie(struct super_block *sb) {}
 
 static inline void nfs_fscache_init_inode_cookie(struct inode *inode) {}
diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c
index 4ca6f5c8038e..8abfb19bd3aa 100644
--- a/fs/nfs/getroot.c
+++ b/fs/nfs/getroot.c
@@ -150,7 +150,7 @@ int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh)
 		goto out;
 
 	/* Start by getting the root filehandle from the server */
-	ret = server->nfs_client->rpc_ops->getroot(server, mntfh, &fsinfo);
+	ret = nfs4_proc_get_rootfh(server, mntfh, &fsinfo);
 	if (ret < 0) {
 		dprintk("nfs4_get_rootfh: getroot error = %d\n", -ret);
 		goto out;
@@ -178,87 +178,4 @@ out:
 	return ret;
 }
 
-/*
- * get an NFS4 root dentry from the root filehandle
- */
-struct dentry *nfs4_get_root(struct super_block *sb, struct nfs_fh *mntfh,
-			     const char *devname)
-{
-	struct nfs_server *server = NFS_SB(sb);
-	struct nfs_fattr *fattr = NULL;
-	struct dentry *ret;
-	struct inode *inode;
-	void *name = kstrdup(devname, GFP_KERNEL);
-	int error;
-
-	dprintk("--> nfs4_get_root()\n");
-
-	if (!name)
-		return ERR_PTR(-ENOMEM);
-
-	/* get the info about the server and filesystem */
-	error = nfs4_server_capabilities(server, mntfh);
-	if (error < 0) {
-		dprintk("nfs_get_root: getcaps error = %d\n",
-			-error);
-		kfree(name);
-		return ERR_PTR(error);
-	}
-
-	fattr = nfs_alloc_fattr();
-	if (fattr == NULL) {
-		kfree(name);
-		return ERR_PTR(-ENOMEM);
-	}
-
-	/* get the actual root for this mount */
-	error = server->nfs_client->rpc_ops->getattr(server, mntfh, fattr);
-	if (error < 0) {
-		dprintk("nfs_get_root: getattr error = %d\n", -error);
-		ret = ERR_PTR(error);
-		goto out;
-	}
-
-	if (fattr->valid & NFS_ATTR_FATTR_FSID &&
-	    !nfs_fsid_equal(&server->fsid, &fattr->fsid))
-		memcpy(&server->fsid, &fattr->fsid, sizeof(server->fsid));
-
-	inode = nfs_fhget(sb, mntfh, fattr);
-	if (IS_ERR(inode)) {
-		dprintk("nfs_get_root: get root inode failed\n");
-		ret = ERR_CAST(inode);
-		goto out;
-	}
-
-	error = nfs_superblock_set_dummy_root(sb, inode);
-	if (error != 0) {
-		ret = ERR_PTR(error);
-		goto out;
-	}
-
-	/* root dentries normally start off anonymous and get spliced in later
-	 * if the dentry tree reaches them; however if the dentry already
-	 * exists, we'll pick it up at this point and use it as the root
-	 */
-	ret = d_obtain_alias(inode);
-	if (IS_ERR(ret)) {
-		dprintk("nfs_get_root: get root dentry failed\n");
-		goto out;
-	}
-
-	security_d_instantiate(ret, inode);
-	spin_lock(&ret->d_lock);
-	if (IS_ROOT(ret) && !(ret->d_flags & DCACHE_NFSFS_RENAMED)) {
-		ret->d_fsdata = name;
-		name = NULL;
-	}
-	spin_unlock(&ret->d_lock);
-out:
-	if (name)
-		kfree(name);
-	nfs_free_fattr(fattr);
-	dprintk("<-- nfs4_get_root()\n");
-	return ret;
-}
-
 #endif /* CONFIG_NFS_V4 */
diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c
index ba3019f5934c..b5b86a05059c 100644
--- a/fs/nfs/idmap.c
+++ b/fs/nfs/idmap.c
@@ -415,7 +415,7 @@ static int __nfs_idmap_register(struct dentry *dir,
 static void nfs_idmap_unregister(struct nfs_client *clp,
 				      struct rpc_pipe *pipe)
 {
-	struct net *net = clp->net;
+	struct net *net = clp->cl_net;
 	struct super_block *pipefs_sb;
 
 	pipefs_sb = rpc_get_sb_net(net);
@@ -429,7 +429,7 @@ static int nfs_idmap_register(struct nfs_client *clp,
 				   struct idmap *idmap,
 				   struct rpc_pipe *pipe)
 {
-	struct net *net = clp->net;
+	struct net *net = clp->cl_net;
 	struct super_block *pipefs_sb;
 	int err = 0;
 
@@ -530,9 +530,25 @@ static struct nfs_client *nfs_get_client_for_event(struct net *net, int event)
 	struct nfs_net *nn = net_generic(net, nfs_net_id);
 	struct dentry *cl_dentry;
 	struct nfs_client *clp;
+	int err;
 
+restart:
 	spin_lock(&nn->nfs_client_lock);
 	list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) {
+		/* Wait for initialisation to finish */
+		if (clp->cl_cons_state == NFS_CS_INITING) {
+			atomic_inc(&clp->cl_count);
+			spin_unlock(&nn->nfs_client_lock);
+			err = nfs_wait_client_init_complete(clp);
+			nfs_put_client(clp);
+			if (err)
+				return NULL;
+			goto restart;
+		}
+		/* Skip nfs_clients that failed to initialise */
+		if (clp->cl_cons_state < 0)
+			continue;
+		smp_rmb();
 		if (clp->rpc_ops != &nfs_v4_clientops)
 			continue;
 		cl_dentry = clp->cl_idmap->idmap_pipe->dentry;
@@ -640,20 +656,16 @@ static int nfs_idmap_legacy_upcall(struct key_construction *cons,
 	struct idmap_msg *im;
 	struct idmap *idmap = (struct idmap *)aux;
 	struct key *key = cons->key;
-	int ret;
+	int ret = -ENOMEM;
 
 	/* msg and im are freed in idmap_pipe_destroy_msg */
 	msg = kmalloc(sizeof(*msg), GFP_KERNEL);
-	if (IS_ERR(msg)) {
-		ret = PTR_ERR(msg);
+	if (!msg)
 		goto out0;
-	}
 
 	im = kmalloc(sizeof(*im), GFP_KERNEL);
-	if (IS_ERR(im)) {
-		ret = PTR_ERR(im);
+	if (!im)
 		goto out1;
-	}
 
 	ret = nfs_idmap_prepare_message(key->description, im, msg);
 	if (ret < 0)
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index c6073139b402..2f6f78c4b42d 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -285,9 +285,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 		inode->i_mode = fattr->mode;
 		if ((fattr->valid & NFS_ATTR_FATTR_MODE) == 0
 				&& nfs_server_capable(inode, NFS_CAP_MODE))
-			nfsi->cache_validity |= NFS_INO_INVALID_ATTR
-				| NFS_INO_INVALID_ACCESS
-				| NFS_INO_INVALID_ACL;
+			nfsi->cache_validity |= NFS_INO_INVALID_ATTR;
 		/* Why so? Because we want revalidate for devices/FIFOs, and
 		 * that's precisely what we have in nfs_file_inode_operations.
 		 */
@@ -300,8 +298,6 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 			inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->dir_inode_ops;
 			inode->i_fop = &nfs_dir_operations;
 			inode->i_data.a_ops = &nfs_dir_aops;
-			if (nfs_server_capable(inode, NFS_CAP_READDIRPLUS))
-				set_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags);
 			/* Deal with crossing mountpoints */
 			if (fattr->valid & NFS_ATTR_FATTR_MOUNTPOINT ||
 					fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) {
@@ -327,6 +323,8 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 		inode->i_gid = -2;
 		inode->i_blocks = 0;
 		memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
+		nfsi->write_io = 0;
+		nfsi->read_io = 0;
 
 		nfsi->read_cache_jiffies = fattr->time_start;
 		nfsi->attr_gencount = fattr->gencount;
@@ -337,24 +335,19 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 		if (fattr->valid & NFS_ATTR_FATTR_MTIME)
 			inode->i_mtime = fattr->mtime;
 		else if (nfs_server_capable(inode, NFS_CAP_MTIME))
-			nfsi->cache_validity |= NFS_INO_INVALID_ATTR
-				| NFS_INO_INVALID_DATA;
+			nfsi->cache_validity |= NFS_INO_INVALID_ATTR;
 		if (fattr->valid & NFS_ATTR_FATTR_CTIME)
 			inode->i_ctime = fattr->ctime;
 		else if (nfs_server_capable(inode, NFS_CAP_CTIME))
-			nfsi->cache_validity |= NFS_INO_INVALID_ATTR
-				| NFS_INO_INVALID_ACCESS
-				| NFS_INO_INVALID_ACL;
+			nfsi->cache_validity |= NFS_INO_INVALID_ATTR;
 		if (fattr->valid & NFS_ATTR_FATTR_CHANGE)
 			inode->i_version = fattr->change_attr;
 		else if (nfs_server_capable(inode, NFS_CAP_CHANGE_ATTR))
-			nfsi->cache_validity |= NFS_INO_INVALID_ATTR
-				| NFS_INO_INVALID_DATA;
+			nfsi->cache_validity |= NFS_INO_INVALID_ATTR;
 		if (fattr->valid & NFS_ATTR_FATTR_SIZE)
 			inode->i_size = nfs_size_to_loff_t(fattr->size);
 		else
 			nfsi->cache_validity |= NFS_INO_INVALID_ATTR
-				| NFS_INO_INVALID_DATA
 				| NFS_INO_REVAL_PAGECACHE;
 		if (fattr->valid & NFS_ATTR_FATTR_NLINK)
 			set_nlink(inode, fattr->nlink);
@@ -363,15 +356,11 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 		if (fattr->valid & NFS_ATTR_FATTR_OWNER)
 			inode->i_uid = fattr->uid;
 		else if (nfs_server_capable(inode, NFS_CAP_OWNER))
-			nfsi->cache_validity |= NFS_INO_INVALID_ATTR
-				| NFS_INO_INVALID_ACCESS
-				| NFS_INO_INVALID_ACL;
+			nfsi->cache_validity |= NFS_INO_INVALID_ATTR;
 		if (fattr->valid & NFS_ATTR_FATTR_GROUP)
 			inode->i_gid = fattr->gid;
 		else if (nfs_server_capable(inode, NFS_CAP_OWNER_GROUP))
-			nfsi->cache_validity |= NFS_INO_INVALID_ATTR
-				| NFS_INO_INVALID_ACCESS
-				| NFS_INO_INVALID_ACL;
+			nfsi->cache_validity |= NFS_INO_INVALID_ATTR;
 		if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED)
 			inode->i_blocks = fattr->du.nfs2.blocks;
 		if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) {
@@ -654,6 +643,7 @@ struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, fmode_t f
 	nfs_init_lock_context(&ctx->lock_context);
 	ctx->lock_context.open_context = ctx;
 	INIT_LIST_HEAD(&ctx->list);
+	ctx->mdsthreshold = NULL;
 	return ctx;
 }
 
@@ -682,6 +672,7 @@ static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync)
 		put_rpccred(ctx->cred);
 	dput(ctx->dentry);
 	nfs_sb_deactive(sb);
+	kfree(ctx->mdsthreshold);
 	kfree(ctx);
 }
 
@@ -870,6 +861,15 @@ static int nfs_invalidate_mapping(struct inode *inode, struct address_space *map
 	return 0;
 }
 
+static bool nfs_mapping_need_revalidate_inode(struct inode *inode)
+{
+	if (nfs_have_delegated_attributes(inode))
+		return false;
+	return (NFS_I(inode)->cache_validity & NFS_INO_REVAL_PAGECACHE)
+		|| nfs_attribute_timeout(inode)
+		|| NFS_STALE(inode);
+}
+
 /**
  * nfs_revalidate_mapping - Revalidate the pagecache
  * @inode - pointer to host inode
@@ -880,9 +880,7 @@ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
 	struct nfs_inode *nfsi = NFS_I(inode);
 	int ret = 0;
 
-	if ((nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE)
-			|| nfs_attribute_cache_expired(inode)
-			|| NFS_STALE(inode)) {
+	if (nfs_mapping_need_revalidate_inode(inode)) {
 		ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
 		if (ret < 0)
 			goto out;
@@ -948,6 +946,8 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat
 	unsigned long invalid = 0;
 
 
+	if (nfs_have_delegated_attributes(inode))
+		return 0;
 	/* Has the inode gone and changed behind our back? */
 	if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid)
 		return -EIO;
@@ -960,7 +960,7 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat
 
 	/* Verify a few of the more important attributes */
 	if ((fattr->valid & NFS_ATTR_FATTR_MTIME) && !timespec_equal(&inode->i_mtime, &fattr->mtime))
-		invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
+		invalid |= NFS_INO_INVALID_ATTR;
 
 	if (fattr->valid & NFS_ATTR_FATTR_SIZE) {
 		cur_size = i_size_read(inode);
@@ -1279,14 +1279,26 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			nfs_display_fhandle_hash(NFS_FH(inode)),
 			atomic_read(&inode->i_count), fattr->valid);
 
-	if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid)
-		goto out_fileid;
+	if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid) {
+		printk(KERN_ERR "NFS: server %s error: fileid changed\n"
+			"fsid %s: expected fileid 0x%Lx, got 0x%Lx\n",
+			NFS_SERVER(inode)->nfs_client->cl_hostname,
+			inode->i_sb->s_id, (long long)nfsi->fileid,
+			(long long)fattr->fileid);
+		goto out_err;
+	}
 
 	/*
 	 * Make sure the inode's type hasn't changed.
 	 */
-	if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT))
-		goto out_changed;
+	if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT)) {
+		/*
+		* Big trouble! The inode has become a different object.
+		*/
+		printk(KERN_DEBUG "NFS: %s: inode %ld mode changed, %07o to %07o\n",
+				__func__, inode->i_ino, inode->i_mode, fattr->mode);
+		goto out_err;
+	}
 
 	server = NFS_SERVER(inode);
 	/* Update the fsid? */
@@ -1314,7 +1326,11 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 		if (inode->i_version != fattr->change_attr) {
 			dprintk("NFS: change_attr change on server for file %s/%ld\n",
 					inode->i_sb->s_id, inode->i_ino);
-			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
+			invalid |= NFS_INO_INVALID_ATTR
+				| NFS_INO_INVALID_DATA
+				| NFS_INO_INVALID_ACCESS
+				| NFS_INO_INVALID_ACL
+				| NFS_INO_REVAL_PAGECACHE;
 			if (S_ISDIR(inode->i_mode))
 				nfs_force_lookup_revalidate(inode);
 			inode->i_version = fattr->change_attr;
@@ -1323,38 +1339,15 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 		invalid |= save_cache_validity;
 
 	if (fattr->valid & NFS_ATTR_FATTR_MTIME) {
-		/* NFSv2/v3: Check if the mtime agrees */
-		if (!timespec_equal(&inode->i_mtime, &fattr->mtime)) {
-			dprintk("NFS: mtime change on server for file %s/%ld\n",
-					inode->i_sb->s_id, inode->i_ino);
-			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA;
-			if (S_ISDIR(inode->i_mode))
-				nfs_force_lookup_revalidate(inode);
-			memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
-		}
+		memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
 	} else if (server->caps & NFS_CAP_MTIME)
 		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
-				| NFS_INO_INVALID_DATA
-				| NFS_INO_REVAL_PAGECACHE
 				| NFS_INO_REVAL_FORCED);
 
 	if (fattr->valid & NFS_ATTR_FATTR_CTIME) {
-		/* If ctime has changed we should definitely clear access+acl caches */
-		if (!timespec_equal(&inode->i_ctime, &fattr->ctime)) {
-			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
-			/* and probably clear data for a directory too as utimes can cause
-			 * havoc with our cache.
-			 */
-			if (S_ISDIR(inode->i_mode)) {
-				invalid |= NFS_INO_INVALID_DATA;
-				nfs_force_lookup_revalidate(inode);
-			}
-			memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
-		}
+		memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
 	} else if (server->caps & NFS_CAP_CTIME)
 		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
-				| NFS_INO_INVALID_ACCESS
-				| NFS_INO_INVALID_ACL
 				| NFS_INO_REVAL_FORCED);
 
 	/* Check if our cached file size is stale */
@@ -1466,12 +1459,6 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 		nfsi->cache_validity |= invalid;
 
 	return 0;
- out_changed:
-	/*
-	 * Big trouble! The inode has become a different object.
-	 */
-	printk(KERN_DEBUG "NFS: %s: inode %ld mode changed, %07o to %07o\n",
-			__func__, inode->i_ino, inode->i_mode, fattr->mode);
  out_err:
 	/*
 	 * No need to worry about unhashing the dentry, as the
@@ -1480,13 +1467,6 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	 */
 	nfs_invalidate_inode(inode);
 	return -ESTALE;
-
- out_fileid:
-	printk(KERN_ERR "NFS: server %s error: fileid changed\n"
-		"fsid %s: expected fileid 0x%Lx, got 0x%Lx\n",
-		NFS_SERVER(inode)->nfs_client->cl_hostname, inode->i_sb->s_id,
-		(long long)nfsi->fileid, (long long)fattr->fileid);
-	goto out_err;
 }
 
 
@@ -1547,7 +1527,7 @@ static inline void nfs4_init_once(struct nfs_inode *nfsi)
 	nfsi->delegation_state = 0;
 	init_rwsem(&nfsi->rwsem);
 	nfsi->layout = NULL;
-	atomic_set(&nfsi->commits_outstanding, 0);
+	atomic_set(&nfsi->commit_info.rpcs_out, 0);
 #endif
 }
 
@@ -1559,9 +1539,9 @@ static void init_once(void *foo)
 	INIT_LIST_HEAD(&nfsi->open_files);
 	INIT_LIST_HEAD(&nfsi->access_cache_entry_lru);
 	INIT_LIST_HEAD(&nfsi->access_cache_inode_lru);
-	INIT_LIST_HEAD(&nfsi->commit_list);
+	INIT_LIST_HEAD(&nfsi->commit_info.list);
 	nfsi->npages = 0;
-	nfsi->ncommit = 0;
+	nfsi->commit_info.ncommit = 0;
 	atomic_set(&nfsi->silly_count, 1);
 	INIT_HLIST_HEAD(&nfsi->silly_list);
 	init_waitqueue_head(&nfsi->waitqueue);
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index b777bdaba4c5..1848a7275592 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -103,6 +103,7 @@ struct nfs_parsed_mount_data {
 	unsigned int		version;
 	unsigned int		minorversion;
 	char			*fscache_uniq;
+	bool			need_mount;
 
 	struct {
 		struct sockaddr_storage	address;
@@ -167,11 +168,13 @@ extern struct nfs_server *nfs_clone_server(struct nfs_server *,
 					   struct nfs_fh *,
 					   struct nfs_fattr *,
 					   rpc_authflavor_t);
+extern int nfs_wait_client_init_complete(const struct nfs_client *clp);
 extern void nfs_mark_client_ready(struct nfs_client *clp, int state);
-extern int nfs4_check_client_ready(struct nfs_client *clp);
 extern struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
 					     const struct sockaddr *ds_addr,
-					     int ds_addrlen, int ds_proto);
+					     int ds_addrlen, int ds_proto,
+					     unsigned int ds_timeo,
+					     unsigned int ds_retrans);
 #ifdef CONFIG_PROC_FS
 extern int __init nfs_fs_proc_init(void);
 extern void nfs_fs_proc_exit(void);
@@ -185,21 +188,11 @@ static inline void nfs_fs_proc_exit(void)
 }
 #endif
 
-/* nfs4namespace.c */
-#ifdef CONFIG_NFS_V4
-extern struct vfsmount *nfs_do_refmount(struct rpc_clnt *client, struct dentry *dentry);
-#else
-static inline
-struct vfsmount *nfs_do_refmount(struct rpc_clnt *client, struct dentry *dentry)
-{
-	return ERR_PTR(-ENOENT);
-}
-#endif
-
 /* callback_xdr.c */
 extern struct svc_version nfs4_callback_version1;
 extern struct svc_version nfs4_callback_version4;
 
+struct nfs_pageio_descriptor;
 /* pagelist.c */
 extern int __init nfs_init_nfspagecache(void);
 extern void nfs_destroy_nfspagecache(void);
@@ -210,9 +203,13 @@ extern void nfs_destroy_writepagecache(void);
 
 extern int __init nfs_init_directcache(void);
 extern void nfs_destroy_directcache(void);
+extern bool nfs_pgarray_set(struct nfs_page_array *p, unsigned int pagecount);
+extern void nfs_pgheader_init(struct nfs_pageio_descriptor *desc,
+			      struct nfs_pgio_header *hdr,
+			      void (*release)(struct nfs_pgio_header *hdr));
+void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos);
 
 /* nfs2xdr.c */
-extern int nfs_stat_to_errno(enum nfs_stat);
 extern struct rpc_procinfo nfs_procedures[];
 extern int nfs2_decode_dirent(struct xdr_stream *,
 				struct nfs_entry *, int);
@@ -237,14 +234,13 @@ extern const u32 nfs41_maxwrite_overhead;
 extern struct rpc_procinfo nfs4_procedures[];
 #endif
 
-extern int nfs4_init_ds_session(struct nfs_client *clp);
+extern int nfs4_init_ds_session(struct nfs_client *, unsigned long);
 
 /* proc.c */
 void nfs_close_context(struct nfs_open_context *ctx, int is_sync);
-extern int nfs_init_client(struct nfs_client *clp,
+extern struct nfs_client *nfs_init_client(struct nfs_client *clp,
 			   const struct rpc_timeout *timeparms,
-			   const char *ip_addr, rpc_authflavor_t authflavour,
-			   int noresvport);
+			   const char *ip_addr, rpc_authflavor_t authflavour);
 
 /* dir.c */
 extern int nfs_access_cache_shrinker(struct shrinker *shrink,
@@ -280,9 +276,10 @@ extern void nfs_sb_deactive(struct super_block *sb);
 extern char *nfs_path(char **p, struct dentry *dentry,
 		      char *buffer, ssize_t buflen);
 extern struct vfsmount *nfs_d_automount(struct path *path);
-#ifdef CONFIG_NFS_V4
-rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *);
-#endif
+struct vfsmount *nfs_submount(struct nfs_server *, struct dentry *,
+			      struct nfs_fh *, struct nfs_fattr *);
+struct vfsmount *nfs_do_submount(struct dentry *, struct nfs_fh *,
+				 struct nfs_fattr *, rpc_authflavor_t);
 
 /* getroot.c */
 extern struct dentry *nfs_get_root(struct super_block *, struct nfs_fh *,
@@ -294,46 +291,73 @@ extern struct dentry *nfs4_get_root(struct super_block *, struct nfs_fh *,
 extern int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh);
 #endif
 
-struct nfs_pageio_descriptor;
+struct nfs_pgio_completion_ops;
 /* read.c */
-extern int nfs_initiate_read(struct nfs_read_data *data, struct rpc_clnt *clnt,
-			     const struct rpc_call_ops *call_ops);
+extern struct nfs_read_header *nfs_readhdr_alloc(void);
+extern void nfs_readhdr_free(struct nfs_pgio_header *hdr);
+extern void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio,
+			struct inode *inode,
+			const struct nfs_pgio_completion_ops *compl_ops);
+extern int nfs_initiate_read(struct rpc_clnt *clnt,
+			     struct nfs_read_data *data,
+			     const struct rpc_call_ops *call_ops, int flags);
 extern void nfs_read_prepare(struct rpc_task *task, void *calldata);
 extern int nfs_generic_pagein(struct nfs_pageio_descriptor *desc,
-		struct list_head *head);
-
+			      struct nfs_pgio_header *hdr);
 extern void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio,
-		struct inode *inode);
+			struct inode *inode,
+			const struct nfs_pgio_completion_ops *compl_ops);
 extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio);
 extern void nfs_readdata_release(struct nfs_read_data *rdata);
 
 /* write.c */
+extern void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio,
+			struct inode *inode, int ioflags,
+			const struct nfs_pgio_completion_ops *compl_ops);
+extern struct nfs_write_header *nfs_writehdr_alloc(void);
+extern void nfs_writehdr_free(struct nfs_pgio_header *hdr);
 extern int nfs_generic_flush(struct nfs_pageio_descriptor *desc,
-		struct list_head *head);
+			     struct nfs_pgio_header *hdr);
 extern void nfs_pageio_init_write_mds(struct nfs_pageio_descriptor *pgio,
-				  struct inode *inode, int ioflags);
+			struct inode *inode, int ioflags,
+			const struct nfs_pgio_completion_ops *compl_ops);
 extern void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio);
 extern void nfs_writedata_release(struct nfs_write_data *wdata);
-extern void nfs_commit_free(struct nfs_write_data *p);
-extern int nfs_initiate_write(struct nfs_write_data *data,
-			      struct rpc_clnt *clnt,
+extern void nfs_commit_free(struct nfs_commit_data *p);
+extern int nfs_initiate_write(struct rpc_clnt *clnt,
+			      struct nfs_write_data *data,
 			      const struct rpc_call_ops *call_ops,
-			      int how);
+			      int how, int flags);
 extern void nfs_write_prepare(struct rpc_task *task, void *calldata);
-extern int nfs_initiate_commit(struct nfs_write_data *data,
-			       struct rpc_clnt *clnt,
+extern void nfs_commit_prepare(struct rpc_task *task, void *calldata);
+extern int nfs_initiate_commit(struct rpc_clnt *clnt,
+			       struct nfs_commit_data *data,
 			       const struct rpc_call_ops *call_ops,
-			       int how);
-extern void nfs_init_commit(struct nfs_write_data *data,
+			       int how, int flags);
+extern void nfs_init_commit(struct nfs_commit_data *data,
 			    struct list_head *head,
-			    struct pnfs_layout_segment *lseg);
+			    struct pnfs_layout_segment *lseg,
+			    struct nfs_commit_info *cinfo);
+int nfs_scan_commit_list(struct list_head *src, struct list_head *dst,
+			 struct nfs_commit_info *cinfo, int max);
+int nfs_scan_commit(struct inode *inode, struct list_head *dst,
+		    struct nfs_commit_info *cinfo);
+void nfs_mark_request_commit(struct nfs_page *req,
+			     struct pnfs_layout_segment *lseg,
+			     struct nfs_commit_info *cinfo);
+int nfs_generic_commit_list(struct inode *inode, struct list_head *head,
+			    int how, struct nfs_commit_info *cinfo);
 void nfs_retry_commit(struct list_head *page_list,
-		      struct pnfs_layout_segment *lseg);
-void nfs_commit_clear_lock(struct nfs_inode *nfsi);
-void nfs_commitdata_release(void *data);
-void nfs_commit_release_pages(struct nfs_write_data *data);
-void nfs_request_add_commit_list(struct nfs_page *req, struct list_head *head);
-void nfs_request_remove_commit_list(struct nfs_page *req);
+		      struct pnfs_layout_segment *lseg,
+		      struct nfs_commit_info *cinfo);
+void nfs_commitdata_release(struct nfs_commit_data *data);
+void nfs_request_add_commit_list(struct nfs_page *req, struct list_head *dst,
+				 struct nfs_commit_info *cinfo);
+void nfs_request_remove_commit_list(struct nfs_page *req,
+				    struct nfs_commit_info *cinfo);
+void nfs_init_cinfo(struct nfs_commit_info *cinfo,
+		    struct inode *inode,
+		    struct nfs_direct_req *dreq);
 
 #ifdef CONFIG_MIGRATION
 extern int nfs_migrate_page(struct address_space *,
@@ -342,15 +366,16 @@ extern int nfs_migrate_page(struct address_space *,
 #define nfs_migrate_page NULL
 #endif
 
+/* direct.c */
+void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo,
+			      struct nfs_direct_req *dreq);
+
 /* nfs4proc.c */
 extern void __nfs4_read_done_cb(struct nfs_read_data *);
-extern void nfs4_reset_read(struct rpc_task *task, struct nfs_read_data *data);
-extern int nfs4_init_client(struct nfs_client *clp,
+extern struct nfs_client *nfs4_init_client(struct nfs_client *clp,
 			    const struct rpc_timeout *timeparms,
 			    const char *ip_addr,
-			    rpc_authflavor_t authflavour,
-			    int noresvport);
-extern void nfs4_reset_write(struct rpc_task *task, struct nfs_write_data *data);
+			    rpc_authflavor_t authflavour);
 extern int _nfs4_call_sync(struct rpc_clnt *clnt,
 			   struct nfs_server *server,
 			   struct rpc_message *msg,
@@ -466,3 +491,15 @@ unsigned int nfs_page_array_len(unsigned int base, size_t len)
 		PAGE_SIZE - 1) >> PAGE_SHIFT;
 }
 
+/*
+ * Convert a struct timespec into a 64-bit change attribute
+ *
+ * This does approximately the same thing as timespec_to_ns(),
+ * but for calculation efficiency, we multiply the seconds by
+ * 1024*1024*1024.
+ */
+static inline
+u64 nfs_timespec_to_change_attr(const struct timespec *ts)
+{
+	return ((u64)ts->tv_sec << 30) + ts->tv_nsec;
+}
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index d51868e5683c..08b9c93675da 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -26,11 +26,6 @@ static LIST_HEAD(nfs_automount_list);
 static DECLARE_DELAYED_WORK(nfs_automount_task, nfs_expire_automounts);
 int nfs_mountpoint_expiry_timeout = 500 * HZ;
 
-static struct vfsmount *nfs_do_submount(struct dentry *dentry,
-					struct nfs_fh *fh,
-					struct nfs_fattr *fattr,
-					rpc_authflavor_t authflavor);
-
 /*
  * nfs_path - reconstruct the path given an arbitrary dentry
  * @base - used to return pointer to the end of devname part of path
@@ -118,64 +113,6 @@ Elong:
 	return ERR_PTR(-ENAMETOOLONG);
 }
 
-#ifdef CONFIG_NFS_V4
-rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *flavors)
-{
-	struct gss_api_mech *mech;
-	struct xdr_netobj oid;
-	int i;
-	rpc_authflavor_t pseudoflavor = RPC_AUTH_UNIX;
-
-	for (i = 0; i < flavors->num_flavors; i++) {
-		struct nfs4_secinfo_flavor *flavor;
-		flavor = &flavors->flavors[i];
-
-		if (flavor->flavor == RPC_AUTH_NULL || flavor->flavor == RPC_AUTH_UNIX) {
-			pseudoflavor = flavor->flavor;
-			break;
-		} else if (flavor->flavor == RPC_AUTH_GSS) {
-			oid.len  = flavor->gss.sec_oid4.len;
-			oid.data = flavor->gss.sec_oid4.data;
-			mech = gss_mech_get_by_OID(&oid);
-			if (!mech)
-				continue;
-			pseudoflavor = gss_svc_to_pseudoflavor(mech, flavor->gss.service);
-			gss_mech_put(mech);
-			break;
-		}
-	}
-
-	return pseudoflavor;
-}
-
-static struct rpc_clnt *nfs_lookup_mountpoint(struct inode *dir,
-					      struct qstr *name,
-					      struct nfs_fh *fh,
-					      struct nfs_fattr *fattr)
-{
-	int err;
-
-	if (NFS_PROTO(dir)->version == 4)
-		return nfs4_proc_lookup_mountpoint(dir, name, fh, fattr);
-
-	err = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, name, fh, fattr);
-	if (err)
-		return ERR_PTR(err);
-	return rpc_clone_client(NFS_SERVER(dir)->client);
-}
-#else /* CONFIG_NFS_V4 */
-static inline struct rpc_clnt *nfs_lookup_mountpoint(struct inode *dir,
-						     struct qstr *name,
-						     struct nfs_fh *fh,
-						     struct nfs_fattr *fattr)
-{
-	int err = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, name, fh, fattr);
-	if (err)
-		return ERR_PTR(err);
-	return rpc_clone_client(NFS_SERVER(dir)->client);
-}
-#endif /* CONFIG_NFS_V4 */
-
 /*
  * nfs_d_automount - Handle crossing a mountpoint on the server
  * @path - The mountpoint
@@ -191,10 +128,9 @@ static inline struct rpc_clnt *nfs_lookup_mountpoint(struct inode *dir,
 struct vfsmount *nfs_d_automount(struct path *path)
 {
 	struct vfsmount *mnt;
-	struct dentry *parent;
+	struct nfs_server *server = NFS_SERVER(path->dentry->d_inode);
 	struct nfs_fh *fh = NULL;
 	struct nfs_fattr *fattr = NULL;
-	struct rpc_clnt *client;
 
 	dprintk("--> nfs_d_automount()\n");
 
@@ -210,21 +146,7 @@ struct vfsmount *nfs_d_automount(struct path *path)
 
 	dprintk("%s: enter\n", __func__);
 
-	/* Look it up again to get its attributes */
-	parent = dget_parent(path->dentry);
-	client = nfs_lookup_mountpoint(parent->d_inode, &path->dentry->d_name, fh, fattr);
-	dput(parent);
-	if (IS_ERR(client)) {
-		mnt = ERR_CAST(client);
-		goto out;
-	}
-
-	if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL)
-		mnt = nfs_do_refmount(client, path->dentry);
-	else
-		mnt = nfs_do_submount(path->dentry, fh, fattr, client->cl_auth->au_flavor);
-	rpc_shutdown_client(client);
-
+	mnt = server->nfs_client->rpc_ops->submount(server, path->dentry, fh, fattr);
 	if (IS_ERR(mnt))
 		goto out;
 
@@ -297,10 +219,8 @@ static struct vfsmount *nfs_do_clone_mount(struct nfs_server *server,
  * @authflavor - security flavor to use when performing the mount
  *
  */
-static struct vfsmount *nfs_do_submount(struct dentry *dentry,
-					struct nfs_fh *fh,
-					struct nfs_fattr *fattr,
-					rpc_authflavor_t authflavor)
+struct vfsmount *nfs_do_submount(struct dentry *dentry, struct nfs_fh *fh,
+				 struct nfs_fattr *fattr, rpc_authflavor_t authflavor)
 {
 	struct nfs_clone_mount mountdata = {
 		.sb = dentry->d_sb,
@@ -333,3 +253,18 @@ out:
 	dprintk("<-- nfs_do_submount() = %p\n", mnt);
 	return mnt;
 }
+
+struct vfsmount *nfs_submount(struct nfs_server *server, struct dentry *dentry,
+			      struct nfs_fh *fh, struct nfs_fattr *fattr)
+{
+	int err;
+	struct dentry *parent = dget_parent(dentry);
+
+	/* Look it up again to get its attributes */
+	err = server->nfs_client->rpc_ops->lookup(parent->d_inode, &dentry->d_name, fh, fattr);
+	dput(parent);
+	if (err != 0)
+		return ERR_PTR(err);
+
+	return nfs_do_submount(dentry, fh, fattr, server->client->cl_auth->au_flavor);
+}
diff --git a/fs/nfs/netns.h b/fs/nfs/netns.h
index aa14ec303e94..8a6394edb8b0 100644
--- a/fs/nfs/netns.h
+++ b/fs/nfs/netns.h
@@ -1,3 +1,7 @@
+/*
+ * NFS-private data for each "struct net".  Accessed with net_generic().
+ */
+
 #ifndef __NFS_NETNS_H__
 #define __NFS_NETNS_H__
 
@@ -20,6 +24,7 @@ struct nfs_net {
 	struct idr cb_ident_idr; /* Protected by nfs_client_lock */
 #endif
 	spinlock_t nfs_client_lock;
+	struct timespec boot_time;
 };
 
 extern int nfs_net_id;
diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c
index 1f56000fabbd..baf759bccd05 100644
--- a/fs/nfs/nfs2xdr.c
+++ b/fs/nfs/nfs2xdr.c
@@ -61,6 +61,7 @@
 #define NFS_readdirres_sz	(1)
 #define NFS_statfsres_sz	(1+NFS_info_sz)
 
+static int nfs_stat_to_errno(enum nfs_stat);
 
 /*
  * While encoding arguments, set up the reply buffer in advance to
@@ -313,6 +314,8 @@ static int decode_fattr(struct xdr_stream *xdr, struct nfs_fattr *fattr)
 	p = xdr_decode_time(p, &fattr->atime);
 	p = xdr_decode_time(p, &fattr->mtime);
 	xdr_decode_time(p, &fattr->ctime);
+	fattr->change_attr = nfs_timespec_to_change_attr(&fattr->ctime);
+
 	return 0;
 out_overflow:
 	print_overflow_msg(__func__, xdr);
@@ -1109,7 +1112,7 @@ static const struct {
  * Returns a local errno value, or -EIO if the NFS status code is
  * not recognized.  This function is used jointly by NFSv2 and NFSv3.
  */
-int nfs_stat_to_errno(enum nfs_stat status)
+static int nfs_stat_to_errno(enum nfs_stat status)
 {
 	int i;
 
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 75c68299358e..2292a0fd2bff 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -142,7 +142,7 @@ nfs3_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
 }
 
 static int
-nfs3_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, struct qstr *name,
+nfs3_proc_lookup(struct inode *dir, struct qstr *name,
 		 struct nfs_fh *fhandle, struct nfs_fattr *fattr)
 {
 	struct nfs3_diropargs	arg = {
@@ -810,11 +810,13 @@ nfs3_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle,
 
 static int nfs3_read_done(struct rpc_task *task, struct nfs_read_data *data)
 {
-	if (nfs3_async_handle_jukebox(task, data->inode))
+	struct inode *inode = data->header->inode;
+
+	if (nfs3_async_handle_jukebox(task, inode))
 		return -EAGAIN;
 
-	nfs_invalidate_atime(data->inode);
-	nfs_refresh_inode(data->inode, &data->fattr);
+	nfs_invalidate_atime(inode);
+	nfs_refresh_inode(inode, &data->fattr);
 	return 0;
 }
 
@@ -830,10 +832,12 @@ static void nfs3_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_da
 
 static int nfs3_write_done(struct rpc_task *task, struct nfs_write_data *data)
 {
-	if (nfs3_async_handle_jukebox(task, data->inode))
+	struct inode *inode = data->header->inode;
+
+	if (nfs3_async_handle_jukebox(task, inode))
 		return -EAGAIN;
 	if (task->tk_status >= 0)
-		nfs_post_op_update_inode_force_wcc(data->inode, data->res.fattr);
+		nfs_post_op_update_inode_force_wcc(inode, data->res.fattr);
 	return 0;
 }
 
@@ -847,7 +851,12 @@ static void nfs3_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_
 	rpc_call_start(task);
 }
 
-static int nfs3_commit_done(struct rpc_task *task, struct nfs_write_data *data)
+static void nfs3_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data)
+{
+	rpc_call_start(task);
+}
+
+static int nfs3_commit_done(struct rpc_task *task, struct nfs_commit_data *data)
 {
 	if (nfs3_async_handle_jukebox(task, data->inode))
 		return -EAGAIN;
@@ -855,7 +864,7 @@ static int nfs3_commit_done(struct rpc_task *task, struct nfs_write_data *data)
 	return 0;
 }
 
-static void nfs3_proc_commit_setup(struct nfs_write_data *data, struct rpc_message *msg)
+static void nfs3_proc_commit_setup(struct nfs_commit_data *data, struct rpc_message *msg)
 {
 	msg->rpc_proc = &nfs3_procedures[NFS3PROC_COMMIT];
 }
@@ -875,6 +884,7 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
 	.file_inode_ops	= &nfs3_file_inode_operations,
 	.file_ops	= &nfs_file_operations,
 	.getroot	= nfs3_proc_get_root,
+	.submount	= nfs_submount,
 	.getattr	= nfs3_proc_getattr,
 	.setattr	= nfs3_proc_setattr,
 	.lookup		= nfs3_proc_lookup,
@@ -906,6 +916,7 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
 	.write_rpc_prepare = nfs3_proc_write_rpc_prepare,
 	.write_done	= nfs3_write_done,
 	.commit_setup	= nfs3_proc_commit_setup,
+	.commit_rpc_prepare = nfs3_proc_commit_rpc_prepare,
 	.commit_done	= nfs3_commit_done,
 	.lock		= nfs3_proc_lock,
 	.clear_acl_cache = nfs3_forget_cached_acls,
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index a77cc9a3ce55..902de489ec9b 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -86,6 +86,8 @@
 				XDR_QUADLEN(NFS_ACL_INLINE_BUFSIZE))
 #define ACL3_setaclres_sz	(1+NFS3_post_op_attr_sz)
 
+static int nfs3_stat_to_errno(enum nfs_stat);
+
 /*
  * Map file type to S_IFMT bits
  */
@@ -675,6 +677,7 @@ static int decode_fattr3(struct xdr_stream *xdr, struct nfs_fattr *fattr)
 	p = xdr_decode_nfstime3(p, &fattr->atime);
 	p = xdr_decode_nfstime3(p, &fattr->mtime);
 	xdr_decode_nfstime3(p, &fattr->ctime);
+	fattr->change_attr = nfs_timespec_to_change_attr(&fattr->ctime);
 
 	fattr->valid |= NFS_ATTR_FATTR_V3;
 	return 0;
@@ -725,12 +728,14 @@ static int decode_wcc_attr(struct xdr_stream *xdr, struct nfs_fattr *fattr)
 		goto out_overflow;
 
 	fattr->valid |= NFS_ATTR_FATTR_PRESIZE
+		| NFS_ATTR_FATTR_PRECHANGE
 		| NFS_ATTR_FATTR_PREMTIME
 		| NFS_ATTR_FATTR_PRECTIME;
 
 	p = xdr_decode_size3(p, &fattr->pre_size);
 	p = xdr_decode_nfstime3(p, &fattr->pre_mtime);
 	xdr_decode_nfstime3(p, &fattr->pre_ctime);
+	fattr->pre_change_attr = nfs_timespec_to_change_attr(&fattr->pre_ctime);
 
 	return 0;
 out_overflow:
@@ -1287,7 +1292,7 @@ static void nfs3_xdr_enc_readdirplus3args(struct rpc_rqst *req,
  *	};
  */
 static void encode_commit3args(struct xdr_stream *xdr,
-			       const struct nfs_writeargs *args)
+			       const struct nfs_commitargs *args)
 {
 	__be32 *p;
 
@@ -1300,7 +1305,7 @@ static void encode_commit3args(struct xdr_stream *xdr,
 
 static void nfs3_xdr_enc_commit3args(struct rpc_rqst *req,
 				     struct xdr_stream *xdr,
-				     const struct nfs_writeargs *args)
+				     const struct nfs_commitargs *args)
 {
 	encode_commit3args(xdr, args);
 }
@@ -1385,7 +1390,7 @@ static int nfs3_xdr_dec_getattr3res(struct rpc_rqst *req,
 out:
 	return error;
 out_default:
-	return nfs_stat_to_errno(status);
+	return nfs3_stat_to_errno(status);
 }
 
 /*
@@ -1424,7 +1429,7 @@ static int nfs3_xdr_dec_setattr3res(struct rpc_rqst *req,
 out:
 	return error;
 out_status:
-	return nfs_stat_to_errno(status);
+	return nfs3_stat_to_errno(status);
 }
 
 /*
@@ -1472,7 +1477,7 @@ out_default:
 	error = decode_post_op_attr(xdr, result->dir_attr);
 	if (unlikely(error))
 		goto out;
-	return nfs_stat_to_errno(status);
+	return nfs3_stat_to_errno(status);
 }
 
 /*
@@ -1513,7 +1518,7 @@ static int nfs3_xdr_dec_access3res(struct rpc_rqst *req,
 out:
 	return error;
 out_default:
-	return nfs_stat_to_errno(status);
+	return nfs3_stat_to_errno(status);
 }
 
 /*
@@ -1554,7 +1559,7 @@ static int nfs3_xdr_dec_readlink3res(struct rpc_rqst *req,
 out:
 	return error;
 out_default:
-	return nfs_stat_to_errno(status);
+	return nfs3_stat_to_errno(status);
 }
 
 /*
@@ -1636,7 +1641,7 @@ static int nfs3_xdr_dec_read3res(struct rpc_rqst *req, struct xdr_stream *xdr,
 out:
 	return error;
 out_status:
-	return nfs_stat_to_errno(status);
+	return nfs3_stat_to_errno(status);
 }
 
 /*
@@ -1706,7 +1711,7 @@ static int nfs3_xdr_dec_write3res(struct rpc_rqst *req, struct xdr_stream *xdr,
 out:
 	return error;
 out_status:
-	return nfs_stat_to_errno(status);
+	return nfs3_stat_to_errno(status);
 }
 
 /*
@@ -1770,7 +1775,7 @@ out_default:
 	error = decode_wcc_data(xdr, result->dir_attr);
 	if (unlikely(error))
 		goto out;
-	return nfs_stat_to_errno(status);
+	return nfs3_stat_to_errno(status);
 }
 
 /*
@@ -1809,7 +1814,7 @@ static int nfs3_xdr_dec_remove3res(struct rpc_rqst *req,
 out:
 	return error;
 out_status:
-	return nfs_stat_to_errno(status);
+	return nfs3_stat_to_errno(status);
 }
 
 /*
@@ -1853,7 +1858,7 @@ static int nfs3_xdr_dec_rename3res(struct rpc_rqst *req,
 out:
 	return error;
 out_status:
-	return nfs_stat_to_errno(status);
+	return nfs3_stat_to_errno(status);
 }
 
 /*
@@ -1896,7 +1901,7 @@ static int nfs3_xdr_dec_link3res(struct rpc_rqst *req, struct xdr_stream *xdr,
 out:
 	return error;
 out_status:
-	return nfs_stat_to_errno(status);
+	return nfs3_stat_to_errno(status);
 }
 
 /**
@@ -2088,7 +2093,7 @@ out_default:
 	error = decode_post_op_attr(xdr, result->dir_attr);
 	if (unlikely(error))
 		goto out;
-	return nfs_stat_to_errno(status);
+	return nfs3_stat_to_errno(status);
 }
 
 /*
@@ -2156,7 +2161,7 @@ static int nfs3_xdr_dec_fsstat3res(struct rpc_rqst *req,
 out:
 	return error;
 out_status:
-	return nfs_stat_to_errno(status);
+	return nfs3_stat_to_errno(status);
 }
 
 /*
@@ -2232,7 +2237,7 @@ static int nfs3_xdr_dec_fsinfo3res(struct rpc_rqst *req,
 out:
 	return error;
 out_status:
-	return nfs_stat_to_errno(status);
+	return nfs3_stat_to_errno(status);
 }
 
 /*
@@ -2295,7 +2300,7 @@ static int nfs3_xdr_dec_pathconf3res(struct rpc_rqst *req,
 out:
 	return error;
 out_status:
-	return nfs_stat_to_errno(status);
+	return nfs3_stat_to_errno(status);
 }
 
 /*
@@ -2319,7 +2324,7 @@ out_status:
  */
 static int nfs3_xdr_dec_commit3res(struct rpc_rqst *req,
 				   struct xdr_stream *xdr,
-				   struct nfs_writeres *result)
+				   struct nfs_commitres *result)
 {
 	enum nfs_stat status;
 	int error;
@@ -2336,7 +2341,7 @@ static int nfs3_xdr_dec_commit3res(struct rpc_rqst *req,
 out:
 	return error;
 out_status:
-	return nfs_stat_to_errno(status);
+	return nfs3_stat_to_errno(status);
 }
 
 #ifdef CONFIG_NFS_V3_ACL
@@ -2401,7 +2406,7 @@ static int nfs3_xdr_dec_getacl3res(struct rpc_rqst *req,
 out:
 	return error;
 out_default:
-	return nfs_stat_to_errno(status);
+	return nfs3_stat_to_errno(status);
 }
 
 static int nfs3_xdr_dec_setacl3res(struct rpc_rqst *req,
@@ -2420,11 +2425,76 @@ static int nfs3_xdr_dec_setacl3res(struct rpc_rqst *req,
 out:
 	return error;
 out_default:
-	return nfs_stat_to_errno(status);
+	return nfs3_stat_to_errno(status);
 }
 
 #endif  /* CONFIG_NFS_V3_ACL */
 
+
+/*
+ * We need to translate between nfs status return values and
+ * the local errno values which may not be the same.
+ */
+static const struct {
+	int stat;
+	int errno;
+} nfs_errtbl[] = {
+	{ NFS_OK,		0		},
+	{ NFSERR_PERM,		-EPERM		},
+	{ NFSERR_NOENT,		-ENOENT		},
+	{ NFSERR_IO,		-errno_NFSERR_IO},
+	{ NFSERR_NXIO,		-ENXIO		},
+/*	{ NFSERR_EAGAIN,	-EAGAIN		}, */
+	{ NFSERR_ACCES,		-EACCES		},
+	{ NFSERR_EXIST,		-EEXIST		},
+	{ NFSERR_XDEV,		-EXDEV		},
+	{ NFSERR_NODEV,		-ENODEV		},
+	{ NFSERR_NOTDIR,	-ENOTDIR	},
+	{ NFSERR_ISDIR,		-EISDIR		},
+	{ NFSERR_INVAL,		-EINVAL		},
+	{ NFSERR_FBIG,		-EFBIG		},
+	{ NFSERR_NOSPC,		-ENOSPC		},
+	{ NFSERR_ROFS,		-EROFS		},
+	{ NFSERR_MLINK,		-EMLINK		},
+	{ NFSERR_NAMETOOLONG,	-ENAMETOOLONG	},
+	{ NFSERR_NOTEMPTY,	-ENOTEMPTY	},
+	{ NFSERR_DQUOT,		-EDQUOT		},
+	{ NFSERR_STALE,		-ESTALE		},
+	{ NFSERR_REMOTE,	-EREMOTE	},
+#ifdef EWFLUSH
+	{ NFSERR_WFLUSH,	-EWFLUSH	},
+#endif
+	{ NFSERR_BADHANDLE,	-EBADHANDLE	},
+	{ NFSERR_NOT_SYNC,	-ENOTSYNC	},
+	{ NFSERR_BAD_COOKIE,	-EBADCOOKIE	},
+	{ NFSERR_NOTSUPP,	-ENOTSUPP	},
+	{ NFSERR_TOOSMALL,	-ETOOSMALL	},
+	{ NFSERR_SERVERFAULT,	-EREMOTEIO	},
+	{ NFSERR_BADTYPE,	-EBADTYPE	},
+	{ NFSERR_JUKEBOX,	-EJUKEBOX	},
+	{ -1,			-EIO		}
+};
+
+/**
+ * nfs3_stat_to_errno - convert an NFS status code to a local errno
+ * @status: NFS status code to convert
+ *
+ * Returns a local errno value, or -EIO if the NFS status code is
+ * not recognized.  This function is used jointly by NFSv2 and NFSv3.
+ */
+static int nfs3_stat_to_errno(enum nfs_stat status)
+{
+	int i;
+
+	for (i = 0; nfs_errtbl[i].stat != -1; i++) {
+		if (nfs_errtbl[i].stat == (int)status)
+			return nfs_errtbl[i].errno;
+	}
+	dprintk("NFS: Unrecognized nfs status value: %u\n", status);
+	return nfs_errtbl[i].errno;
+}
+
+
 #define PROC(proc, argtype, restype, timer)				\
 [NFS3PROC_##proc] = {							\
 	.p_proc      = NFS3PROC_##proc,					\
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 8d75021020b3..c6827f93ab57 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -24,6 +24,8 @@ enum nfs4_client_state {
 	NFS4CLNT_RECALL_SLOT,
 	NFS4CLNT_LEASE_CONFIRM,
 	NFS4CLNT_SERVER_SCOPE_MISMATCH,
+	NFS4CLNT_PURGE_STATE,
+	NFS4CLNT_BIND_CONN_TO_SESSION,
 };
 
 enum nfs4_session_state {
@@ -52,11 +54,6 @@ struct nfs4_minor_version_ops {
 	const struct nfs4_state_maintenance_ops *state_renewal_ops;
 };
 
-struct nfs_unique_id {
-	struct rb_node rb_node;
-	__u64 id;
-};
-
 #define NFS_SEQID_CONFIRMED 1
 struct nfs_seqid_counter {
 	ktime_t create_time;
@@ -206,12 +203,18 @@ extern const struct dentry_operations nfs4_dentry_operations;
 extern const struct inode_operations nfs4_dir_inode_operations;
 
 /* nfs4namespace.c */
+rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *);
 struct rpc_clnt *nfs4_create_sec_client(struct rpc_clnt *, struct inode *, struct qstr *);
+struct vfsmount *nfs4_submount(struct nfs_server *, struct dentry *,
+			       struct nfs_fh *, struct nfs_fattr *);
 
 /* nfs4proc.c */
 extern int nfs4_proc_setclientid(struct nfs_client *, u32, unsigned short, struct rpc_cred *, struct nfs4_setclientid_res *);
 extern int nfs4_proc_setclientid_confirm(struct nfs_client *, struct nfs4_setclientid_res *arg, struct rpc_cred *);
+extern int nfs4_proc_get_rootfh(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *);
+extern int nfs4_proc_bind_conn_to_session(struct nfs_client *, struct rpc_cred *cred);
 extern int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred);
+extern int nfs4_destroy_clientid(struct nfs_client *clp);
 extern int nfs4_init_clientid(struct nfs_client *, struct rpc_cred *);
 extern int nfs41_init_clientid(struct nfs_client *, struct rpc_cred *);
 extern int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait, bool roc);
@@ -239,8 +242,8 @@ extern int nfs41_setup_sequence(struct nfs4_session *session,
 		struct rpc_task *task);
 extern void nfs4_destroy_session(struct nfs4_session *session);
 extern struct nfs4_session *nfs4_alloc_session(struct nfs_client *clp);
-extern int nfs4_proc_create_session(struct nfs_client *);
-extern int nfs4_proc_destroy_session(struct nfs4_session *);
+extern int nfs4_proc_create_session(struct nfs_client *, struct rpc_cred *);
+extern int nfs4_proc_destroy_session(struct nfs4_session *, struct rpc_cred *);
 extern int nfs4_init_session(struct nfs_server *server);
 extern int nfs4_proc_get_lease_time(struct nfs_client *clp,
 		struct nfs_fsinfo *fsinfo);
@@ -310,9 +313,9 @@ struct rpc_cred *nfs4_get_renew_cred_locked(struct nfs_client *clp);
 #if defined(CONFIG_NFS_V4_1)
 struct rpc_cred *nfs4_get_machine_cred_locked(struct nfs_client *clp);
 struct rpc_cred *nfs4_get_exchange_id_cred(struct nfs_client *clp);
-extern void nfs4_schedule_session_recovery(struct nfs4_session *);
+extern void nfs4_schedule_session_recovery(struct nfs4_session *, int);
 #else
-static inline void nfs4_schedule_session_recovery(struct nfs4_session *session)
+static inline void nfs4_schedule_session_recovery(struct nfs4_session *session, int err)
 {
 }
 #endif /* CONFIG_NFS_V4_1 */
@@ -334,7 +337,7 @@ extern void nfs4_schedule_stateid_recovery(const struct nfs_server *, struct nfs
 extern void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags);
 extern void nfs41_handle_recall_slot(struct nfs_client *clp);
 extern void nfs41_handle_server_scope(struct nfs_client *,
-				      struct server_scope **);
+				      struct nfs41_server_scope **);
 extern void nfs4_put_lock_state(struct nfs4_lock_state *lsp);
 extern int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl);
 extern void nfs4_select_rw_stateid(nfs4_stateid *, struct nfs4_state *,
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index 5acfd9ea8a31..e1340293872c 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -82,29 +82,76 @@ filelayout_get_dserver_offset(struct pnfs_layout_segment *lseg, loff_t offset)
 	BUG();
 }
 
+static void filelayout_reset_write(struct nfs_write_data *data)
+{
+	struct nfs_pgio_header *hdr = data->header;
+	struct rpc_task *task = &data->task;
+
+	if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
+		dprintk("%s Reset task %5u for i/o through MDS "
+			"(req %s/%lld, %u bytes @ offset %llu)\n", __func__,
+			data->task.tk_pid,
+			hdr->inode->i_sb->s_id,
+			(long long)NFS_FILEID(hdr->inode),
+			data->args.count,
+			(unsigned long long)data->args.offset);
+
+		task->tk_status = pnfs_write_done_resend_to_mds(hdr->inode,
+							&hdr->pages,
+							hdr->completion_ops);
+	}
+}
+
+static void filelayout_reset_read(struct nfs_read_data *data)
+{
+	struct nfs_pgio_header *hdr = data->header;
+	struct rpc_task *task = &data->task;
+
+	if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
+		dprintk("%s Reset task %5u for i/o through MDS "
+			"(req %s/%lld, %u bytes @ offset %llu)\n", __func__,
+			data->task.tk_pid,
+			hdr->inode->i_sb->s_id,
+			(long long)NFS_FILEID(hdr->inode),
+			data->args.count,
+			(unsigned long long)data->args.offset);
+
+		task->tk_status = pnfs_read_done_resend_to_mds(hdr->inode,
+							&hdr->pages,
+							hdr->completion_ops);
+	}
+}
+
 static int filelayout_async_handle_error(struct rpc_task *task,
 					 struct nfs4_state *state,
 					 struct nfs_client *clp,
-					 int *reset)
+					 struct pnfs_layout_segment *lseg)
 {
-	struct nfs_server *mds_server = NFS_SERVER(state->inode);
+	struct inode *inode = lseg->pls_layout->plh_inode;
+	struct nfs_server *mds_server = NFS_SERVER(inode);
+	struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg);
 	struct nfs_client *mds_client = mds_server->nfs_client;
+	struct nfs4_slot_table *tbl = &clp->cl_session->fc_slot_table;
 
 	if (task->tk_status >= 0)
 		return 0;
-	*reset = 0;
 
 	switch (task->tk_status) {
 	/* MDS state errors */
 	case -NFS4ERR_DELEG_REVOKED:
 	case -NFS4ERR_ADMIN_REVOKED:
 	case -NFS4ERR_BAD_STATEID:
+		if (state == NULL)
+			break;
 		nfs_remove_bad_delegation(state->inode);
 	case -NFS4ERR_OPENMODE:
+		if (state == NULL)
+			break;
 		nfs4_schedule_stateid_recovery(mds_server, state);
 		goto wait_on_recovery;
 	case -NFS4ERR_EXPIRED:
-		nfs4_schedule_stateid_recovery(mds_server, state);
+		if (state != NULL)
+			nfs4_schedule_stateid_recovery(mds_server, state);
 		nfs4_schedule_lease_recovery(mds_client);
 		goto wait_on_recovery;
 	/* DS session errors */
@@ -118,7 +165,7 @@ static int filelayout_async_handle_error(struct rpc_task *task,
 		dprintk("%s ERROR %d, Reset session. Exchangeid "
 			"flags 0x%x\n", __func__, task->tk_status,
 			clp->cl_exchange_flags);
-		nfs4_schedule_session_recovery(clp->cl_session);
+		nfs4_schedule_session_recovery(clp->cl_session, task->tk_status);
 		break;
 	case -NFS4ERR_DELAY:
 	case -NFS4ERR_GRACE:
@@ -127,11 +174,48 @@ static int filelayout_async_handle_error(struct rpc_task *task,
 		break;
 	case -NFS4ERR_RETRY_UNCACHED_REP:
 		break;
+	/* Invalidate Layout errors */
+	case -NFS4ERR_PNFS_NO_LAYOUT:
+	case -ESTALE:           /* mapped NFS4ERR_STALE */
+	case -EBADHANDLE:       /* mapped NFS4ERR_BADHANDLE */
+	case -EISDIR:           /* mapped NFS4ERR_ISDIR */
+	case -NFS4ERR_FHEXPIRED:
+	case -NFS4ERR_WRONG_TYPE:
+		dprintk("%s Invalid layout error %d\n", __func__,
+			task->tk_status);
+		/*
+		 * Destroy layout so new i/o will get a new layout.
+		 * Layout will not be destroyed until all current lseg
+		 * references are put. Mark layout as invalid to resend failed
+		 * i/o and all i/o waiting on the slot table to the MDS until
+		 * layout is destroyed and a new valid layout is obtained.
+		 */
+		set_bit(NFS_LAYOUT_INVALID,
+				&NFS_I(inode)->layout->plh_flags);
+		pnfs_destroy_layout(NFS_I(inode));
+		rpc_wake_up(&tbl->slot_tbl_waitq);
+		goto reset;
+	/* RPC connection errors */
+	case -ECONNREFUSED:
+	case -EHOSTDOWN:
+	case -EHOSTUNREACH:
+	case -ENETUNREACH:
+	case -EIO:
+	case -ETIMEDOUT:
+	case -EPIPE:
+		dprintk("%s DS connection error %d\n", __func__,
+			task->tk_status);
+		if (!filelayout_test_devid_invalid(devid))
+			_pnfs_return_layout(inode);
+		filelayout_mark_devid_invalid(devid);
+		rpc_wake_up(&tbl->slot_tbl_waitq);
+		nfs4_ds_disconnect(clp);
+		/* fall through */
 	default:
-		dprintk("%s DS error. Retry through MDS %d\n", __func__,
+reset:
+		dprintk("%s Retry through MDS. Error %d\n", __func__,
 			task->tk_status);
-		*reset = 1;
-		break;
+		return -NFS4ERR_RESET_TO_MDS;
 	}
 out:
 	task->tk_status = 0;
@@ -148,18 +232,17 @@ wait_on_recovery:
 static int filelayout_read_done_cb(struct rpc_task *task,
 				struct nfs_read_data *data)
 {
-	int reset = 0;
+	struct nfs_pgio_header *hdr = data->header;
+	int err;
 
-	dprintk("%s DS read\n", __func__);
+	err = filelayout_async_handle_error(task, data->args.context->state,
+					    data->ds_clp, hdr->lseg);
 
-	if (filelayout_async_handle_error(task, data->args.context->state,
-					  data->ds_clp, &reset) == -EAGAIN) {
-		dprintk("%s calling restart ds_clp %p ds_clp->cl_session %p\n",
-			__func__, data->ds_clp, data->ds_clp->cl_session);
-		if (reset) {
-			pnfs_set_lo_fail(data->lseg);
-			nfs4_reset_read(task, data);
-		}
+	switch (err) {
+	case -NFS4ERR_RESET_TO_MDS:
+		filelayout_reset_read(data);
+		return task->tk_status;
+	case -EAGAIN:
 		rpc_restart_call_prepare(task);
 		return -EAGAIN;
 	}
@@ -175,13 +258,15 @@ static int filelayout_read_done_cb(struct rpc_task *task,
 static void
 filelayout_set_layoutcommit(struct nfs_write_data *wdata)
 {
-	if (FILELAYOUT_LSEG(wdata->lseg)->commit_through_mds ||
+	struct nfs_pgio_header *hdr = wdata->header;
+
+	if (FILELAYOUT_LSEG(hdr->lseg)->commit_through_mds ||
 	    wdata->res.verf->committed == NFS_FILE_SYNC)
 		return;
 
 	pnfs_set_layoutcommit(wdata);
-	dprintk("%s ionde %lu pls_end_pos %lu\n", __func__, wdata->inode->i_ino,
-		(unsigned long) NFS_I(wdata->inode)->layout->plh_lwb);
+	dprintk("%s ionde %lu pls_end_pos %lu\n", __func__, hdr->inode->i_ino,
+		(unsigned long) NFS_I(hdr->inode)->layout->plh_lwb);
 }
 
 /*
@@ -191,8 +276,14 @@ filelayout_set_layoutcommit(struct nfs_write_data *wdata)
  */
 static void filelayout_read_prepare(struct rpc_task *task, void *data)
 {
-	struct nfs_read_data *rdata = (struct nfs_read_data *)data;
+	struct nfs_read_data *rdata = data;
 
+	if (filelayout_reset_to_mds(rdata->header->lseg)) {
+		dprintk("%s task %u reset io to MDS\n", __func__, task->tk_pid);
+		filelayout_reset_read(rdata);
+		rpc_exit(task, 0);
+		return;
+	}
 	rdata->read_done_cb = filelayout_read_done_cb;
 
 	if (nfs41_setup_sequence(rdata->ds_clp->cl_session,
@@ -205,42 +296,47 @@ static void filelayout_read_prepare(struct rpc_task *task, void *data)
 
 static void filelayout_read_call_done(struct rpc_task *task, void *data)
 {
-	struct nfs_read_data *rdata = (struct nfs_read_data *)data;
+	struct nfs_read_data *rdata = data;
 
 	dprintk("--> %s task->tk_status %d\n", __func__, task->tk_status);
 
+	if (test_bit(NFS_IOHDR_REDO, &rdata->header->flags) &&
+	    task->tk_status == 0)
+		return;
+
 	/* Note this may cause RPC to be resent */
-	rdata->mds_ops->rpc_call_done(task, data);
+	rdata->header->mds_ops->rpc_call_done(task, data);
 }
 
 static void filelayout_read_count_stats(struct rpc_task *task, void *data)
 {
-	struct nfs_read_data *rdata = (struct nfs_read_data *)data;
+	struct nfs_read_data *rdata = data;
 
-	rpc_count_iostats(task, NFS_SERVER(rdata->inode)->client->cl_metrics);
+	rpc_count_iostats(task, NFS_SERVER(rdata->header->inode)->client->cl_metrics);
 }
 
 static void filelayout_read_release(void *data)
 {
-	struct nfs_read_data *rdata = (struct nfs_read_data *)data;
+	struct nfs_read_data *rdata = data;
 
-	put_lseg(rdata->lseg);
-	rdata->mds_ops->rpc_release(data);
+	nfs_put_client(rdata->ds_clp);
+	rdata->header->mds_ops->rpc_release(data);
 }
 
 static int filelayout_write_done_cb(struct rpc_task *task,
 				struct nfs_write_data *data)
 {
-	int reset = 0;
-
-	if (filelayout_async_handle_error(task, data->args.context->state,
-					  data->ds_clp, &reset) == -EAGAIN) {
-		dprintk("%s calling restart ds_clp %p ds_clp->cl_session %p\n",
-			__func__, data->ds_clp, data->ds_clp->cl_session);
-		if (reset) {
-			pnfs_set_lo_fail(data->lseg);
-			nfs4_reset_write(task, data);
-		}
+	struct nfs_pgio_header *hdr = data->header;
+	int err;
+
+	err = filelayout_async_handle_error(task, data->args.context->state,
+					    data->ds_clp, hdr->lseg);
+
+	switch (err) {
+	case -NFS4ERR_RESET_TO_MDS:
+		filelayout_reset_write(data);
+		return task->tk_status;
+	case -EAGAIN:
 		rpc_restart_call_prepare(task);
 		return -EAGAIN;
 	}
@@ -250,7 +346,7 @@ static int filelayout_write_done_cb(struct rpc_task *task,
 }
 
 /* Fake up some data that will cause nfs_commit_release to retry the writes. */
-static void prepare_to_resend_writes(struct nfs_write_data *data)
+static void prepare_to_resend_writes(struct nfs_commit_data *data)
 {
 	struct nfs_page *first = nfs_list_entry(data->pages.next);
 
@@ -261,19 +357,19 @@ static void prepare_to_resend_writes(struct nfs_write_data *data)
 }
 
 static int filelayout_commit_done_cb(struct rpc_task *task,
-				     struct nfs_write_data *data)
+				     struct nfs_commit_data *data)
 {
-	int reset = 0;
-
-	if (filelayout_async_handle_error(task, data->args.context->state,
-					  data->ds_clp, &reset) == -EAGAIN) {
-		dprintk("%s calling restart ds_clp %p ds_clp->cl_session %p\n",
-			__func__, data->ds_clp, data->ds_clp->cl_session);
-		if (reset) {
-			prepare_to_resend_writes(data);
-			pnfs_set_lo_fail(data->lseg);
-		} else
-			rpc_restart_call_prepare(task);
+	int err;
+
+	err = filelayout_async_handle_error(task, NULL, data->ds_clp,
+					    data->lseg);
+
+	switch (err) {
+	case -NFS4ERR_RESET_TO_MDS:
+		prepare_to_resend_writes(data);
+		return -EAGAIN;
+	case -EAGAIN:
+		rpc_restart_call_prepare(task);
 		return -EAGAIN;
 	}
 
@@ -282,8 +378,14 @@ static int filelayout_commit_done_cb(struct rpc_task *task,
 
 static void filelayout_write_prepare(struct rpc_task *task, void *data)
 {
-	struct nfs_write_data *wdata = (struct nfs_write_data *)data;
+	struct nfs_write_data *wdata = data;
 
+	if (filelayout_reset_to_mds(wdata->header->lseg)) {
+		dprintk("%s task %u reset io to MDS\n", __func__, task->tk_pid);
+		filelayout_reset_write(wdata);
+		rpc_exit(task, 0);
+		return;
+	}
 	if (nfs41_setup_sequence(wdata->ds_clp->cl_session,
 				&wdata->args.seq_args, &wdata->res.seq_res,
 				task))
@@ -294,36 +396,66 @@ static void filelayout_write_prepare(struct rpc_task *task, void *data)
 
 static void filelayout_write_call_done(struct rpc_task *task, void *data)
 {
-	struct nfs_write_data *wdata = (struct nfs_write_data *)data;
+	struct nfs_write_data *wdata = data;
+
+	if (test_bit(NFS_IOHDR_REDO, &wdata->header->flags) &&
+	    task->tk_status == 0)
+		return;
 
 	/* Note this may cause RPC to be resent */
-	wdata->mds_ops->rpc_call_done(task, data);
+	wdata->header->mds_ops->rpc_call_done(task, data);
 }
 
 static void filelayout_write_count_stats(struct rpc_task *task, void *data)
 {
-	struct nfs_write_data *wdata = (struct nfs_write_data *)data;
+	struct nfs_write_data *wdata = data;
 
-	rpc_count_iostats(task, NFS_SERVER(wdata->inode)->client->cl_metrics);
+	rpc_count_iostats(task, NFS_SERVER(wdata->header->inode)->client->cl_metrics);
 }
 
 static void filelayout_write_release(void *data)
 {
-	struct nfs_write_data *wdata = (struct nfs_write_data *)data;
+	struct nfs_write_data *wdata = data;
+
+	nfs_put_client(wdata->ds_clp);
+	wdata->header->mds_ops->rpc_release(data);
+}
+
+static void filelayout_commit_prepare(struct rpc_task *task, void *data)
+{
+	struct nfs_commit_data *wdata = data;
 
-	put_lseg(wdata->lseg);
-	wdata->mds_ops->rpc_release(data);
+	if (nfs41_setup_sequence(wdata->ds_clp->cl_session,
+				&wdata->args.seq_args, &wdata->res.seq_res,
+				task))
+		return;
+
+	rpc_call_start(task);
+}
+
+static void filelayout_write_commit_done(struct rpc_task *task, void *data)
+{
+	struct nfs_commit_data *wdata = data;
+
+	/* Note this may cause RPC to be resent */
+	wdata->mds_ops->rpc_call_done(task, data);
+}
+
+static void filelayout_commit_count_stats(struct rpc_task *task, void *data)
+{
+	struct nfs_commit_data *cdata = data;
+
+	rpc_count_iostats(task, NFS_SERVER(cdata->inode)->client->cl_metrics);
 }
 
-static void filelayout_commit_release(void *data)
+static void filelayout_commit_release(void *calldata)
 {
-	struct nfs_write_data *wdata = (struct nfs_write_data *)data;
+	struct nfs_commit_data *data = calldata;
 
-	nfs_commit_release_pages(wdata);
-	if (atomic_dec_and_test(&NFS_I(wdata->inode)->commits_outstanding))
-		nfs_commit_clear_lock(NFS_I(wdata->inode));
-	put_lseg(wdata->lseg);
-	nfs_commitdata_release(wdata);
+	data->completion_ops->completion(data);
+	put_lseg(data->lseg);
+	nfs_put_client(data->ds_clp);
+	nfs_commitdata_release(data);
 }
 
 static const struct rpc_call_ops filelayout_read_call_ops = {
@@ -341,16 +473,17 @@ static const struct rpc_call_ops filelayout_write_call_ops = {
 };
 
 static const struct rpc_call_ops filelayout_commit_call_ops = {
-	.rpc_call_prepare = filelayout_write_prepare,
-	.rpc_call_done = filelayout_write_call_done,
-	.rpc_count_stats = filelayout_write_count_stats,
+	.rpc_call_prepare = filelayout_commit_prepare,
+	.rpc_call_done = filelayout_write_commit_done,
+	.rpc_count_stats = filelayout_commit_count_stats,
 	.rpc_release = filelayout_commit_release,
 };
 
 static enum pnfs_try_status
 filelayout_read_pagelist(struct nfs_read_data *data)
 {
-	struct pnfs_layout_segment *lseg = data->lseg;
+	struct nfs_pgio_header *hdr = data->header;
+	struct pnfs_layout_segment *lseg = hdr->lseg;
 	struct nfs4_pnfs_ds *ds;
 	loff_t offset = data->args.offset;
 	u32 j, idx;
@@ -358,25 +491,20 @@ filelayout_read_pagelist(struct nfs_read_data *data)
 	int status;
 
 	dprintk("--> %s ino %lu pgbase %u req %Zu@%llu\n",
-		__func__, data->inode->i_ino,
+		__func__, hdr->inode->i_ino,
 		data->args.pgbase, (size_t)data->args.count, offset);
 
-	if (test_bit(NFS_DEVICEID_INVALID, &FILELAYOUT_DEVID_NODE(lseg)->flags))
-		return PNFS_NOT_ATTEMPTED;
-
 	/* Retrieve the correct rpc_client for the byte range */
 	j = nfs4_fl_calc_j_index(lseg, offset);
 	idx = nfs4_fl_calc_ds_index(lseg, j);
 	ds = nfs4_fl_prepare_ds(lseg, idx);
-	if (!ds) {
-		/* Either layout fh index faulty, or ds connect failed */
-		set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags);
-		set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags);
+	if (!ds)
 		return PNFS_NOT_ATTEMPTED;
-	}
-	dprintk("%s USE DS: %s\n", __func__, ds->ds_remotestr);
+	dprintk("%s USE DS: %s cl_count %d\n", __func__,
+		ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count));
 
 	/* No multipath support. Use first DS */
+	atomic_inc(&ds->ds_clp->cl_count);
 	data->ds_clp = ds->ds_clp;
 	fh = nfs4_fl_select_ds_fh(lseg, j);
 	if (fh)
@@ -386,8 +514,8 @@ filelayout_read_pagelist(struct nfs_read_data *data)
 	data->mds_offset = offset;
 
 	/* Perform an asynchronous read to ds */
-	status = nfs_initiate_read(data, ds->ds_clp->cl_rpcclient,
-				   &filelayout_read_call_ops);
+	status = nfs_initiate_read(ds->ds_clp->cl_rpcclient, data,
+				  &filelayout_read_call_ops, RPC_TASK_SOFTCONN);
 	BUG_ON(status != 0);
 	return PNFS_ATTEMPTED;
 }
@@ -396,32 +524,26 @@ filelayout_read_pagelist(struct nfs_read_data *data)
 static enum pnfs_try_status
 filelayout_write_pagelist(struct nfs_write_data *data, int sync)
 {
-	struct pnfs_layout_segment *lseg = data->lseg;
+	struct nfs_pgio_header *hdr = data->header;
+	struct pnfs_layout_segment *lseg = hdr->lseg;
 	struct nfs4_pnfs_ds *ds;
 	loff_t offset = data->args.offset;
 	u32 j, idx;
 	struct nfs_fh *fh;
 	int status;
 
-	if (test_bit(NFS_DEVICEID_INVALID, &FILELAYOUT_DEVID_NODE(lseg)->flags))
-		return PNFS_NOT_ATTEMPTED;
-
 	/* Retrieve the correct rpc_client for the byte range */
 	j = nfs4_fl_calc_j_index(lseg, offset);
 	idx = nfs4_fl_calc_ds_index(lseg, j);
 	ds = nfs4_fl_prepare_ds(lseg, idx);
-	if (!ds) {
-		printk(KERN_ERR "NFS: %s: prepare_ds failed, use MDS\n",
-			__func__);
-		set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags);
-		set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags);
+	if (!ds)
 		return PNFS_NOT_ATTEMPTED;
-	}
-	dprintk("%s ino %lu sync %d req %Zu@%llu DS: %s\n", __func__,
-		data->inode->i_ino, sync, (size_t) data->args.count, offset,
-		ds->ds_remotestr);
+	dprintk("%s ino %lu sync %d req %Zu@%llu DS: %s cl_count %d\n",
+		__func__, hdr->inode->i_ino, sync, (size_t) data->args.count,
+		offset, ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count));
 
 	data->write_done_cb = filelayout_write_done_cb;
+	atomic_inc(&ds->ds_clp->cl_count);
 	data->ds_clp = ds->ds_clp;
 	fh = nfs4_fl_select_ds_fh(lseg, j);
 	if (fh)
@@ -433,8 +555,9 @@ filelayout_write_pagelist(struct nfs_write_data *data, int sync)
 	data->args.offset = filelayout_get_dserver_offset(lseg, offset);
 
 	/* Perform an asynchronous write */
-	status = nfs_initiate_write(data, ds->ds_clp->cl_rpcclient,
-				    &filelayout_write_call_ops, sync);
+	status = nfs_initiate_write(ds->ds_clp->cl_rpcclient, data,
+				    &filelayout_write_call_ops, sync,
+				    RPC_TASK_SOFTCONN);
 	BUG_ON(status != 0);
 	return PNFS_ATTEMPTED;
 }
@@ -650,10 +773,65 @@ filelayout_free_lseg(struct pnfs_layout_segment *lseg)
 
 	dprintk("--> %s\n", __func__);
 	nfs4_fl_put_deviceid(fl->dsaddr);
-	kfree(fl->commit_buckets);
+	/* This assumes a single RW lseg */
+	if (lseg->pls_range.iomode == IOMODE_RW) {
+		struct nfs4_filelayout *flo;
+
+		flo = FILELAYOUT_FROM_HDR(lseg->pls_layout);
+		flo->commit_info.nbuckets = 0;
+		kfree(flo->commit_info.buckets);
+		flo->commit_info.buckets = NULL;
+	}
 	_filelayout_free_lseg(fl);
 }
 
+static int
+filelayout_alloc_commit_info(struct pnfs_layout_segment *lseg,
+			     struct nfs_commit_info *cinfo,
+			     gfp_t gfp_flags)
+{
+	struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg);
+	struct pnfs_commit_bucket *buckets;
+	int size;
+
+	if (fl->commit_through_mds)
+		return 0;
+	if (cinfo->ds->nbuckets != 0) {
+		/* This assumes there is only one IOMODE_RW lseg.  What
+		 * we really want to do is have a layout_hdr level
+		 * dictionary of <multipath_list4, fh> keys, each
+		 * associated with a struct list_head, populated by calls
+		 * to filelayout_write_pagelist().
+		 * */
+		return 0;
+	}
+
+	size = (fl->stripe_type == STRIPE_SPARSE) ?
+		fl->dsaddr->ds_num : fl->dsaddr->stripe_count;
+
+	buckets = kcalloc(size, sizeof(struct pnfs_commit_bucket),
+			  gfp_flags);
+	if (!buckets)
+		return -ENOMEM;
+	else {
+		int i;
+
+		spin_lock(cinfo->lock);
+		if (cinfo->ds->nbuckets != 0)
+			kfree(buckets);
+		else {
+			cinfo->ds->buckets = buckets;
+			cinfo->ds->nbuckets = size;
+			for (i = 0; i < size; i++) {
+				INIT_LIST_HEAD(&buckets[i].written);
+				INIT_LIST_HEAD(&buckets[i].committing);
+			}
+		}
+		spin_unlock(cinfo->lock);
+		return 0;
+	}
+}
+
 static struct pnfs_layout_segment *
 filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid,
 		      struct nfs4_layoutget_res *lgr,
@@ -673,29 +851,6 @@ filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid,
 		_filelayout_free_lseg(fl);
 		return NULL;
 	}
-
-	/* This assumes there is only one IOMODE_RW lseg.  What
-	 * we really want to do is have a layout_hdr level
-	 * dictionary of <multipath_list4, fh> keys, each
-	 * associated with a struct list_head, populated by calls
-	 * to filelayout_write_pagelist().
-	 * */
-	if ((!fl->commit_through_mds) && (lgr->range.iomode == IOMODE_RW)) {
-		int i;
-		int size = (fl->stripe_type == STRIPE_SPARSE) ?
-			fl->dsaddr->ds_num : fl->dsaddr->stripe_count;
-
-		fl->commit_buckets = kcalloc(size, sizeof(struct nfs4_fl_commit_bucket), gfp_flags);
-		if (!fl->commit_buckets) {
-			filelayout_free_lseg(&fl->generic_hdr);
-			return NULL;
-		}
-		fl->number_of_buckets = size;
-		for (i = 0; i < size; i++) {
-			INIT_LIST_HEAD(&fl->commit_buckets[i].written);
-			INIT_LIST_HEAD(&fl->commit_buckets[i].committing);
-		}
-	}
 	return &fl->generic_hdr;
 }
 
@@ -716,8 +871,8 @@ filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
 	    !nfs_generic_pg_test(pgio, prev, req))
 		return false;
 
-	p_stripe = (u64)prev->wb_index << PAGE_CACHE_SHIFT;
-	r_stripe = (u64)req->wb_index << PAGE_CACHE_SHIFT;
+	p_stripe = (u64)req_offset(prev);
+	r_stripe = (u64)req_offset(req);
 	stripe_unit = FILELAYOUT_LSEG(pgio->pg_lseg)->stripe_unit;
 
 	do_div(p_stripe, stripe_unit);
@@ -732,6 +887,16 @@ filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio,
 {
 	BUG_ON(pgio->pg_lseg != NULL);
 
+	if (req->wb_offset != req->wb_pgbase) {
+		/*
+		 * Handling unaligned pages is difficult, because have to
+		 * somehow split a req in two in certain cases in the
+		 * pg.test code.  Avoid this by just not using pnfs
+		 * in this case.
+		 */
+		nfs_pageio_reset_read_mds(pgio);
+		return;
+	}
 	pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
 					   req->wb_context,
 					   0,
@@ -747,8 +912,13 @@ static void
 filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio,
 			 struct nfs_page *req)
 {
+	struct nfs_commit_info cinfo;
+	int status;
+
 	BUG_ON(pgio->pg_lseg != NULL);
 
+	if (req->wb_offset != req->wb_pgbase)
+		goto out_mds;
 	pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
 					   req->wb_context,
 					   0,
@@ -757,7 +927,17 @@ filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio,
 					   GFP_NOFS);
 	/* If no lseg, fall back to write through mds */
 	if (pgio->pg_lseg == NULL)
-		nfs_pageio_reset_write_mds(pgio);
+		goto out_mds;
+	nfs_init_cinfo(&cinfo, pgio->pg_inode, pgio->pg_dreq);
+	status = filelayout_alloc_commit_info(pgio->pg_lseg, &cinfo, GFP_NOFS);
+	if (status < 0) {
+		put_lseg(pgio->pg_lseg);
+		pgio->pg_lseg = NULL;
+		goto out_mds;
+	}
+	return;
+out_mds:
+	nfs_pageio_reset_write_mds(pgio);
 }
 
 static const struct nfs_pageio_ops filelayout_pg_read_ops = {
@@ -784,43 +964,42 @@ static u32 select_bucket_index(struct nfs4_filelayout_segment *fl, u32 j)
  * If this will make the bucket empty, it will need to put the lseg reference.
  */
 static void
-filelayout_clear_request_commit(struct nfs_page *req)
+filelayout_clear_request_commit(struct nfs_page *req,
+				struct nfs_commit_info *cinfo)
 {
 	struct pnfs_layout_segment *freeme = NULL;
-	struct inode *inode = req->wb_context->dentry->d_inode;
 
-	spin_lock(&inode->i_lock);
+	spin_lock(cinfo->lock);
 	if (!test_and_clear_bit(PG_COMMIT_TO_DS, &req->wb_flags))
 		goto out;
+	cinfo->ds->nwritten--;
 	if (list_is_singular(&req->wb_list)) {
-		struct pnfs_layout_segment *lseg;
+		struct pnfs_commit_bucket *bucket;
 
-		/* From here we can find the bucket, but for the moment,
-		 * since there is only one relevant lseg...
-		 */
-		list_for_each_entry(lseg, &NFS_I(inode)->layout->plh_segs, pls_list) {
-			if (lseg->pls_range.iomode == IOMODE_RW) {
-				freeme = lseg;
-				break;
-			}
-		}
+		bucket = list_first_entry(&req->wb_list,
+					  struct pnfs_commit_bucket,
+					  written);
+		freeme = bucket->wlseg;
+		bucket->wlseg = NULL;
 	}
 out:
-	nfs_request_remove_commit_list(req);
-	spin_unlock(&inode->i_lock);
+	nfs_request_remove_commit_list(req, cinfo);
+	spin_unlock(cinfo->lock);
 	put_lseg(freeme);
 }
 
 static struct list_head *
 filelayout_choose_commit_list(struct nfs_page *req,
-			      struct pnfs_layout_segment *lseg)
+			      struct pnfs_layout_segment *lseg,
+			      struct nfs_commit_info *cinfo)
 {
 	struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg);
 	u32 i, j;
 	struct list_head *list;
+	struct pnfs_commit_bucket *buckets;
 
 	if (fl->commit_through_mds)
-		return &NFS_I(req->wb_context->dentry->d_inode)->commit_list;
+		return &cinfo->mds->list;
 
 	/* Note that we are calling nfs4_fl_calc_j_index on each page
 	 * that ends up being committed to a data server.  An attractive
@@ -828,31 +1007,33 @@ filelayout_choose_commit_list(struct nfs_page *req,
 	 * to store the value calculated in filelayout_write_pagelist
 	 * and just use that here.
 	 */
-	j = nfs4_fl_calc_j_index(lseg,
-				 (loff_t)req->wb_index << PAGE_CACHE_SHIFT);
+	j = nfs4_fl_calc_j_index(lseg, req_offset(req));
 	i = select_bucket_index(fl, j);
-	list = &fl->commit_buckets[i].written;
+	buckets = cinfo->ds->buckets;
+	list = &buckets[i].written;
 	if (list_empty(list)) {
 		/* Non-empty buckets hold a reference on the lseg.  That ref
 		 * is normally transferred to the COMMIT call and released
 		 * there.  It could also be released if the last req is pulled
 		 * off due to a rewrite, in which case it will be done in
-		 * filelayout_remove_commit_req
+		 * filelayout_clear_request_commit
 		 */
-		get_lseg(lseg);
+		buckets[i].wlseg = get_lseg(lseg);
 	}
 	set_bit(PG_COMMIT_TO_DS, &req->wb_flags);
+	cinfo->ds->nwritten++;
 	return list;
 }
 
 static void
 filelayout_mark_request_commit(struct nfs_page *req,
-		struct pnfs_layout_segment *lseg)
+			       struct pnfs_layout_segment *lseg,
+			       struct nfs_commit_info *cinfo)
 {
 	struct list_head *list;
 
-	list = filelayout_choose_commit_list(req, lseg);
-	nfs_request_add_commit_list(req, list);
+	list = filelayout_choose_commit_list(req, lseg, cinfo);
+	nfs_request_add_commit_list(req, list, cinfo);
 }
 
 static u32 calc_ds_index_from_commit(struct pnfs_layout_segment *lseg, u32 i)
@@ -880,7 +1061,7 @@ select_ds_fh_from_commit(struct pnfs_layout_segment *lseg, u32 i)
 	return flseg->fh_array[i];
 }
 
-static int filelayout_initiate_commit(struct nfs_write_data *data, int how)
+static int filelayout_initiate_commit(struct nfs_commit_data *data, int how)
 {
 	struct pnfs_layout_segment *lseg = data->lseg;
 	struct nfs4_pnfs_ds *ds;
@@ -890,135 +1071,138 @@ static int filelayout_initiate_commit(struct nfs_write_data *data, int how)
 	idx = calc_ds_index_from_commit(lseg, data->ds_commit_index);
 	ds = nfs4_fl_prepare_ds(lseg, idx);
 	if (!ds) {
-		printk(KERN_ERR "NFS: %s: prepare_ds failed, use MDS\n",
-			__func__);
-		set_bit(lo_fail_bit(IOMODE_RW), &lseg->pls_layout->plh_flags);
-		set_bit(lo_fail_bit(IOMODE_READ), &lseg->pls_layout->plh_flags);
 		prepare_to_resend_writes(data);
 		filelayout_commit_release(data);
 		return -EAGAIN;
 	}
-	dprintk("%s ino %lu, how %d\n", __func__, data->inode->i_ino, how);
-	data->write_done_cb = filelayout_commit_done_cb;
+	dprintk("%s ino %lu, how %d cl_count %d\n", __func__,
+		data->inode->i_ino, how, atomic_read(&ds->ds_clp->cl_count));
+	data->commit_done_cb = filelayout_commit_done_cb;
+	atomic_inc(&ds->ds_clp->cl_count);
 	data->ds_clp = ds->ds_clp;
 	fh = select_ds_fh_from_commit(lseg, data->ds_commit_index);
 	if (fh)
 		data->args.fh = fh;
-	return nfs_initiate_commit(data, ds->ds_clp->cl_rpcclient,
-				   &filelayout_commit_call_ops, how);
-}
-
-/*
- * This is only useful while we are using whole file layouts.
- */
-static struct pnfs_layout_segment *
-find_only_write_lseg_locked(struct inode *inode)
-{
-	struct pnfs_layout_segment *lseg;
-
-	list_for_each_entry(lseg, &NFS_I(inode)->layout->plh_segs, pls_list)
-		if (lseg->pls_range.iomode == IOMODE_RW)
-			return lseg;
-	return NULL;
-}
-
-static struct pnfs_layout_segment *find_only_write_lseg(struct inode *inode)
-{
-	struct pnfs_layout_segment *rv;
-
-	spin_lock(&inode->i_lock);
-	rv = find_only_write_lseg_locked(inode);
-	if (rv)
-		get_lseg(rv);
-	spin_unlock(&inode->i_lock);
-	return rv;
+	return nfs_initiate_commit(ds->ds_clp->cl_rpcclient, data,
+				   &filelayout_commit_call_ops, how,
+				   RPC_TASK_SOFTCONN);
 }
 
 static int
-filelayout_scan_ds_commit_list(struct nfs4_fl_commit_bucket *bucket, int max,
-		spinlock_t *lock)
+transfer_commit_list(struct list_head *src, struct list_head *dst,
+		     struct nfs_commit_info *cinfo, int max)
 {
-	struct list_head *src = &bucket->written;
-	struct list_head *dst = &bucket->committing;
 	struct nfs_page *req, *tmp;
 	int ret = 0;
 
 	list_for_each_entry_safe(req, tmp, src, wb_list) {
 		if (!nfs_lock_request(req))
 			continue;
-		if (cond_resched_lock(lock))
+		kref_get(&req->wb_kref);
+		if (cond_resched_lock(cinfo->lock))
 			list_safe_reset_next(req, tmp, wb_list);
-		nfs_request_remove_commit_list(req);
+		nfs_request_remove_commit_list(req, cinfo);
 		clear_bit(PG_COMMIT_TO_DS, &req->wb_flags);
 		nfs_list_add_request(req, dst);
 		ret++;
-		if (ret == max)
+		if ((ret == max) && !cinfo->dreq)
 			break;
 	}
 	return ret;
 }
 
+static int
+filelayout_scan_ds_commit_list(struct pnfs_commit_bucket *bucket,
+			       struct nfs_commit_info *cinfo,
+			       int max)
+{
+	struct list_head *src = &bucket->written;
+	struct list_head *dst = &bucket->committing;
+	int ret;
+
+	ret = transfer_commit_list(src, dst, cinfo, max);
+	if (ret) {
+		cinfo->ds->nwritten -= ret;
+		cinfo->ds->ncommitting += ret;
+		bucket->clseg = bucket->wlseg;
+		if (list_empty(src))
+			bucket->wlseg = NULL;
+		else
+			get_lseg(bucket->clseg);
+	}
+	return ret;
+}
+
 /* Move reqs from written to committing lists, returning count of number moved.
- * Note called with i_lock held.
+ * Note called with cinfo->lock held.
  */
-static int filelayout_scan_commit_lists(struct inode *inode, int max,
-		spinlock_t *lock)
+static int filelayout_scan_commit_lists(struct nfs_commit_info *cinfo,
+					int max)
 {
-	struct pnfs_layout_segment *lseg;
-	struct nfs4_filelayout_segment *fl;
 	int i, rv = 0, cnt;
 
-	lseg = find_only_write_lseg_locked(inode);
-	if (!lseg)
-		goto out_done;
-	fl = FILELAYOUT_LSEG(lseg);
-	if (fl->commit_through_mds)
-		goto out_done;
-	for (i = 0; i < fl->number_of_buckets && max != 0; i++) {
-		cnt = filelayout_scan_ds_commit_list(&fl->commit_buckets[i],
-				max, lock);
+	for (i = 0; i < cinfo->ds->nbuckets && max != 0; i++) {
+		cnt = filelayout_scan_ds_commit_list(&cinfo->ds->buckets[i],
+						     cinfo, max);
 		max -= cnt;
 		rv += cnt;
 	}
-out_done:
 	return rv;
 }
 
+/* Pull everything off the committing lists and dump into @dst */
+static void filelayout_recover_commit_reqs(struct list_head *dst,
+					   struct nfs_commit_info *cinfo)
+{
+	struct pnfs_commit_bucket *b;
+	int i;
+
+	/* NOTE cinfo->lock is NOT held, relying on fact that this is
+	 * only called on single thread per dreq.
+	 * Can't take the lock because need to do put_lseg
+	 */
+	for (i = 0, b = cinfo->ds->buckets; i < cinfo->ds->nbuckets; i++, b++) {
+		if (transfer_commit_list(&b->written, dst, cinfo, 0)) {
+			BUG_ON(!list_empty(&b->written));
+			put_lseg(b->wlseg);
+			b->wlseg = NULL;
+		}
+	}
+	cinfo->ds->nwritten = 0;
+}
+
 static unsigned int
-alloc_ds_commits(struct inode *inode, struct list_head *list)
+alloc_ds_commits(struct nfs_commit_info *cinfo, struct list_head *list)
 {
-	struct pnfs_layout_segment *lseg;
-	struct nfs4_filelayout_segment *fl;
-	struct nfs_write_data *data;
+	struct pnfs_ds_commit_info *fl_cinfo;
+	struct pnfs_commit_bucket *bucket;
+	struct nfs_commit_data *data;
 	int i, j;
 	unsigned int nreq = 0;
 
-	/* Won't need this when non-whole file layout segments are supported
-	 * instead we will use a pnfs_layout_hdr structure */
-	lseg = find_only_write_lseg(inode);
-	if (!lseg)
-		return 0;
-	fl = FILELAYOUT_LSEG(lseg);
-	for (i = 0; i < fl->number_of_buckets; i++) {
-		if (list_empty(&fl->commit_buckets[i].committing))
+	fl_cinfo = cinfo->ds;
+	bucket = fl_cinfo->buckets;
+	for (i = 0; i < fl_cinfo->nbuckets; i++, bucket++) {
+		if (list_empty(&bucket->committing))
 			continue;
 		data = nfs_commitdata_alloc();
 		if (!data)
 			break;
 		data->ds_commit_index = i;
-		data->lseg = lseg;
+		data->lseg = bucket->clseg;
+		bucket->clseg = NULL;
 		list_add(&data->pages, list);
 		nreq++;
 	}
 
 	/* Clean up on error */
-	for (j = i; j < fl->number_of_buckets; j++) {
-		if (list_empty(&fl->commit_buckets[i].committing))
+	for (j = i; j < fl_cinfo->nbuckets; j++, bucket++) {
+		if (list_empty(&bucket->committing))
 			continue;
-		nfs_retry_commit(&fl->commit_buckets[i].committing, lseg);
-		put_lseg(lseg);  /* associated with emptying bucket */
+		nfs_retry_commit(&bucket->committing, bucket->clseg, cinfo);
+		put_lseg(bucket->clseg);
+		bucket->clseg = NULL;
 	}
-	put_lseg(lseg);
 	/* Caller will clean up entries put on list */
 	return nreq;
 }
@@ -1026,9 +1210,9 @@ alloc_ds_commits(struct inode *inode, struct list_head *list)
 /* This follows nfs_commit_list pretty closely */
 static int
 filelayout_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
-			   int how)
+			   int how, struct nfs_commit_info *cinfo)
 {
-	struct nfs_write_data	*data, *tmp;
+	struct nfs_commit_data *data, *tmp;
 	LIST_HEAD(list);
 	unsigned int nreq = 0;
 
@@ -1039,30 +1223,34 @@ filelayout_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
 			list_add(&data->pages, &list);
 			nreq++;
 		} else
-			nfs_retry_commit(mds_pages, NULL);
+			nfs_retry_commit(mds_pages, NULL, cinfo);
 	}
 
-	nreq += alloc_ds_commits(inode, &list);
+	nreq += alloc_ds_commits(cinfo, &list);
 
 	if (nreq == 0) {
-		nfs_commit_clear_lock(NFS_I(inode));
+		cinfo->completion_ops->error_cleanup(NFS_I(inode));
 		goto out;
 	}
 
-	atomic_add(nreq, &NFS_I(inode)->commits_outstanding);
+	atomic_add(nreq, &cinfo->mds->rpcs_out);
 
 	list_for_each_entry_safe(data, tmp, &list, pages) {
 		list_del_init(&data->pages);
 		if (!data->lseg) {
-			nfs_init_commit(data, mds_pages, NULL);
-			nfs_initiate_commit(data, NFS_CLIENT(inode),
-					    data->mds_ops, how);
+			nfs_init_commit(data, mds_pages, NULL, cinfo);
+			nfs_initiate_commit(NFS_CLIENT(inode), data,
+					    data->mds_ops, how, 0);
 		} else {
-			nfs_init_commit(data, &FILELAYOUT_LSEG(data->lseg)->commit_buckets[data->ds_commit_index].committing, data->lseg);
+			struct pnfs_commit_bucket *buckets;
+
+			buckets = cinfo->ds->buckets;
+			nfs_init_commit(data, &buckets[data->ds_commit_index].committing, data->lseg, cinfo);
 			filelayout_initiate_commit(data, how);
 		}
 	}
 out:
+	cinfo->ds->ncommitting = 0;
 	return PNFS_ATTEMPTED;
 }
 
@@ -1072,17 +1260,47 @@ filelayout_free_deveiceid_node(struct nfs4_deviceid_node *d)
 	nfs4_fl_free_deviceid(container_of(d, struct nfs4_file_layout_dsaddr, id_node));
 }
 
+static struct pnfs_layout_hdr *
+filelayout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags)
+{
+	struct nfs4_filelayout *flo;
+
+	flo = kzalloc(sizeof(*flo), gfp_flags);
+	return &flo->generic_hdr;
+}
+
+static void
+filelayout_free_layout_hdr(struct pnfs_layout_hdr *lo)
+{
+	kfree(FILELAYOUT_FROM_HDR(lo));
+}
+
+static struct pnfs_ds_commit_info *
+filelayout_get_ds_info(struct inode *inode)
+{
+	struct pnfs_layout_hdr *layout = NFS_I(inode)->layout;
+
+	if (layout == NULL)
+		return NULL;
+	else
+		return &FILELAYOUT_FROM_HDR(layout)->commit_info;
+}
+
 static struct pnfs_layoutdriver_type filelayout_type = {
 	.id			= LAYOUT_NFSV4_1_FILES,
 	.name			= "LAYOUT_NFSV4_1_FILES",
 	.owner			= THIS_MODULE,
+	.alloc_layout_hdr	= filelayout_alloc_layout_hdr,
+	.free_layout_hdr	= filelayout_free_layout_hdr,
 	.alloc_lseg		= filelayout_alloc_lseg,
 	.free_lseg		= filelayout_free_lseg,
 	.pg_read_ops		= &filelayout_pg_read_ops,
 	.pg_write_ops		= &filelayout_pg_write_ops,
+	.get_ds_info		= &filelayout_get_ds_info,
 	.mark_request_commit	= filelayout_mark_request_commit,
 	.clear_request_commit	= filelayout_clear_request_commit,
 	.scan_commit_lists	= filelayout_scan_commit_lists,
+	.recover_commit_reqs	= filelayout_recover_commit_reqs,
 	.commit_pagelist	= filelayout_commit_pagelist,
 	.read_pagelist		= filelayout_read_pagelist,
 	.write_pagelist		= filelayout_write_pagelist,
diff --git a/fs/nfs/nfs4filelayout.h b/fs/nfs/nfs4filelayout.h
index 21190bb1f5e3..43fe802dd678 100644
--- a/fs/nfs/nfs4filelayout.h
+++ b/fs/nfs/nfs4filelayout.h
@@ -33,6 +33,13 @@
 #include "pnfs.h"
 
 /*
+ * Default data server connection timeout and retrans vaules.
+ * Set by module paramters dataserver_timeo and dataserver_retrans.
+ */
+#define NFS4_DEF_DS_TIMEO   60
+#define NFS4_DEF_DS_RETRANS 5
+
+/*
  * Field testing shows we need to support up to 4096 stripe indices.
  * We store each index as a u8 (u32 on the wire) to keep the memory footprint
  * reasonable. This in turn means we support a maximum of 256
@@ -41,6 +48,9 @@
 #define NFS4_PNFS_MAX_STRIPE_CNT 4096
 #define NFS4_PNFS_MAX_MULTI_CNT  256 /* 256 fit into a u8 stripe_index */
 
+/* error codes for internal use */
+#define NFS4ERR_RESET_TO_MDS   12001
+
 enum stripetype4 {
 	STRIPE_SPARSE = 1,
 	STRIPE_DENSE = 2
@@ -62,23 +72,14 @@ struct nfs4_pnfs_ds {
 	atomic_t		ds_count;
 };
 
-/* nfs4_file_layout_dsaddr flags */
-#define NFS4_DEVICE_ID_NEG_ENTRY	0x00000001
-
 struct nfs4_file_layout_dsaddr {
 	struct nfs4_deviceid_node	id_node;
-	unsigned long			flags;
 	u32				stripe_count;
 	u8				*stripe_indices;
 	u32				ds_num;
 	struct nfs4_pnfs_ds		*ds_list[1];
 };
 
-struct nfs4_fl_commit_bucket {
-	struct list_head written;
-	struct list_head committing;
-};
-
 struct nfs4_filelayout_segment {
 	struct pnfs_layout_segment generic_hdr;
 	u32 stripe_type;
@@ -89,10 +90,19 @@ struct nfs4_filelayout_segment {
 	struct nfs4_file_layout_dsaddr *dsaddr; /* Point to GETDEVINFO data */
 	unsigned int num_fh;
 	struct nfs_fh **fh_array;
-	struct nfs4_fl_commit_bucket *commit_buckets; /* Sort commits to ds */
-	int number_of_buckets;
 };
 
+struct nfs4_filelayout {
+	struct pnfs_layout_hdr generic_hdr;
+	struct pnfs_ds_commit_info commit_info;
+};
+
+static inline struct nfs4_filelayout *
+FILELAYOUT_FROM_HDR(struct pnfs_layout_hdr *lo)
+{
+	return container_of(lo, struct nfs4_filelayout, generic_hdr);
+}
+
 static inline struct nfs4_filelayout_segment *
 FILELAYOUT_LSEG(struct pnfs_layout_segment *lseg)
 {
@@ -107,6 +117,36 @@ FILELAYOUT_DEVID_NODE(struct pnfs_layout_segment *lseg)
 	return &FILELAYOUT_LSEG(lseg)->dsaddr->id_node;
 }
 
+static inline void
+filelayout_mark_devid_invalid(struct nfs4_deviceid_node *node)
+{
+	u32 *p = (u32 *)&node->deviceid;
+
+	printk(KERN_WARNING "NFS: Deviceid [%x%x%x%x] marked out of use.\n",
+		p[0], p[1], p[2], p[3]);
+
+	set_bit(NFS_DEVICEID_INVALID, &node->flags);
+}
+
+static inline bool
+filelayout_test_layout_invalid(struct pnfs_layout_hdr *lo)
+{
+	return test_bit(NFS_LAYOUT_INVALID, &lo->plh_flags);
+}
+
+static inline bool
+filelayout_test_devid_invalid(struct nfs4_deviceid_node *node)
+{
+	return test_bit(NFS_DEVICEID_INVALID, &node->flags);
+}
+
+static inline bool
+filelayout_reset_to_mds(struct pnfs_layout_segment *lseg)
+{
+	return filelayout_test_devid_invalid(FILELAYOUT_DEVID_NODE(lseg)) ||
+		filelayout_test_layout_invalid(lseg->pls_layout);
+}
+
 extern struct nfs_fh *
 nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j);
 
@@ -119,5 +159,6 @@ extern void nfs4_fl_put_deviceid(struct nfs4_file_layout_dsaddr *dsaddr);
 extern void nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr);
 struct nfs4_file_layout_dsaddr *
 get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id, gfp_t gfp_flags);
+void nfs4_ds_disconnect(struct nfs_client *clp);
 
 #endif /* FS_NFS_NFS4FILELAYOUT_H */
diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c
index c9cff9adb2d3..a1fab8da7f03 100644
--- a/fs/nfs/nfs4filelayoutdev.c
+++ b/fs/nfs/nfs4filelayoutdev.c
@@ -30,12 +30,16 @@
 
 #include <linux/nfs_fs.h>
 #include <linux/vmalloc.h>
+#include <linux/module.h>
 
 #include "internal.h"
 #include "nfs4filelayout.h"
 
 #define NFSDBG_FACILITY		NFSDBG_PNFS_LD
 
+static unsigned int dataserver_timeo = NFS4_DEF_DS_TIMEO;
+static unsigned int dataserver_retrans = NFS4_DEF_DS_RETRANS;
+
 /*
  * Data server cache
  *
@@ -145,6 +149,28 @@ _data_server_lookup_locked(const struct list_head *dsaddrs)
 }
 
 /*
+ * Lookup DS by nfs_client pointer. Zero data server client pointer
+ */
+void nfs4_ds_disconnect(struct nfs_client *clp)
+{
+	struct nfs4_pnfs_ds *ds;
+	struct nfs_client *found = NULL;
+
+	dprintk("%s clp %p\n", __func__, clp);
+	spin_lock(&nfs4_ds_cache_lock);
+	list_for_each_entry(ds, &nfs4_data_server_cache, ds_node)
+		if (ds->ds_clp && ds->ds_clp == clp) {
+			found = ds->ds_clp;
+			ds->ds_clp = NULL;
+		}
+	spin_unlock(&nfs4_ds_cache_lock);
+	if (found) {
+		set_bit(NFS_CS_STOP_RENEW, &clp->cl_res_state);
+		nfs_put_client(clp);
+	}
+}
+
+/*
  * Create an rpc connection to the nfs4_pnfs_ds data server
  * Currently only supports IPv4 and IPv6 addresses
  */
@@ -165,8 +191,9 @@ nfs4_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds)
 			__func__, ds->ds_remotestr, da->da_remotestr);
 
 		clp = nfs4_set_ds_client(mds_srv->nfs_client,
-				 (struct sockaddr *)&da->da_addr,
-				 da->da_addrlen, IPPROTO_TCP);
+					(struct sockaddr *)&da->da_addr,
+					da->da_addrlen, IPPROTO_TCP,
+					dataserver_timeo, dataserver_retrans);
 		if (!IS_ERR(clp))
 			break;
 	}
@@ -176,28 +203,7 @@ nfs4_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds)
 		goto out;
 	}
 
-	if ((clp->cl_exchange_flags & EXCHGID4_FLAG_MASK_PNFS) != 0) {
-		if (!is_ds_client(clp)) {
-			status = -ENODEV;
-			goto out_put;
-		}
-		ds->ds_clp = clp;
-		dprintk("%s [existing] server=%s\n", __func__,
-			ds->ds_remotestr);
-		goto out;
-	}
-
-	/*
-	 * Do not set NFS_CS_CHECK_LEASE_TIME instead set the DS lease to
-	 * be equal to the MDS lease. Renewal is scheduled in create_session.
-	 */
-	spin_lock(&mds_srv->nfs_client->cl_lock);
-	clp->cl_lease_time = mds_srv->nfs_client->cl_lease_time;
-	spin_unlock(&mds_srv->nfs_client->cl_lock);
-	clp->cl_last_renewal = jiffies;
-
-	/* New nfs_client */
-	status = nfs4_init_ds_session(clp);
+	status = nfs4_init_ds_session(clp, mds_srv->nfs_client->cl_lease_time);
 	if (status)
 		goto out_put;
 
@@ -602,7 +608,7 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
 
 		mp_count = be32_to_cpup(p); /* multipath count */
 		for (j = 0; j < mp_count; j++) {
-			da = decode_ds_addr(NFS_SERVER(ino)->nfs_client->net,
+			da = decode_ds_addr(NFS_SERVER(ino)->nfs_client->cl_net,
 					    &stream, gfp_flags);
 			if (da)
 				list_add_tail(&da->da_node, &dsaddrs);
@@ -791,48 +797,42 @@ nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j)
 	return flseg->fh_array[i];
 }
 
-static void
-filelayout_mark_devid_negative(struct nfs4_file_layout_dsaddr *dsaddr,
-			       int err, const char *ds_remotestr)
-{
-	u32 *p = (u32 *)&dsaddr->id_node.deviceid;
-
-	printk(KERN_ERR "NFS: data server %s connection error %d."
-		" Deviceid [%x%x%x%x] marked out of use.\n",
-		ds_remotestr, err, p[0], p[1], p[2], p[3]);
-
-	spin_lock(&nfs4_ds_cache_lock);
-	dsaddr->flags |= NFS4_DEVICE_ID_NEG_ENTRY;
-	spin_unlock(&nfs4_ds_cache_lock);
-}
-
 struct nfs4_pnfs_ds *
 nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
 {
 	struct nfs4_file_layout_dsaddr *dsaddr = FILELAYOUT_LSEG(lseg)->dsaddr;
 	struct nfs4_pnfs_ds *ds = dsaddr->ds_list[ds_idx];
+	struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg);
+
+	if (filelayout_test_devid_invalid(devid))
+		return NULL;
 
 	if (ds == NULL) {
 		printk(KERN_ERR "NFS: %s: No data server for offset index %d\n",
 			__func__, ds_idx);
-		return NULL;
+		goto mark_dev_invalid;
 	}
 
 	if (!ds->ds_clp) {
 		struct nfs_server *s = NFS_SERVER(lseg->pls_layout->plh_inode);
 		int err;
 
-		if (dsaddr->flags & NFS4_DEVICE_ID_NEG_ENTRY) {
-			/* Already tried to connect, don't try again */
-			dprintk("%s Deviceid marked out of use\n", __func__);
-			return NULL;
-		}
 		err = nfs4_ds_connect(s, ds);
-		if (err) {
-			filelayout_mark_devid_negative(dsaddr, err,
-						       ds->ds_remotestr);
-			return NULL;
-		}
+		if (err)
+			goto mark_dev_invalid;
 	}
 	return ds;
+
+mark_dev_invalid:
+	filelayout_mark_devid_invalid(devid);
+	return NULL;
 }
+
+module_param(dataserver_retrans, uint, 0644);
+MODULE_PARM_DESC(dataserver_retrans, "The  number of times the NFSv4.1 client "
+			"retries a request before it attempts further "
+			" recovery  action.");
+module_param(dataserver_timeo, uint, 0644);
+MODULE_PARM_DESC(dataserver_timeo, "The time (in tenths of a second) the "
+			"NFSv4.1  client  waits for a response from a "
+			" data server before it retries an NFS request.");
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index a7f3dedc4ec7..017b4b01a69c 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -132,6 +132,35 @@ static size_t nfs_parse_server_name(char *string, size_t len,
 	return ret;
 }
 
+rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *flavors)
+{
+	struct gss_api_mech *mech;
+	struct xdr_netobj oid;
+	int i;
+	rpc_authflavor_t pseudoflavor = RPC_AUTH_UNIX;
+
+	for (i = 0; i < flavors->num_flavors; i++) {
+		struct nfs4_secinfo_flavor *flavor;
+		flavor = &flavors->flavors[i];
+
+		if (flavor->flavor == RPC_AUTH_NULL || flavor->flavor == RPC_AUTH_UNIX) {
+			pseudoflavor = flavor->flavor;
+			break;
+		} else if (flavor->flavor == RPC_AUTH_GSS) {
+			oid.len  = flavor->gss.sec_oid4.len;
+			oid.data = flavor->gss.sec_oid4.data;
+			mech = gss_mech_get_by_OID(&oid);
+			if (!mech)
+				continue;
+			pseudoflavor = gss_svc_to_pseudoflavor(mech, flavor->gss.service);
+			gss_mech_put(mech);
+			break;
+		}
+	}
+
+	return pseudoflavor;
+}
+
 static rpc_authflavor_t nfs4_negotiate_security(struct inode *inode, struct qstr *name)
 {
 	struct page *page;
@@ -168,7 +197,7 @@ struct rpc_clnt *nfs4_create_sec_client(struct rpc_clnt *clnt, struct inode *ino
 	rpc_authflavor_t flavor;
 
 	flavor = nfs4_negotiate_security(inode, name);
-	if (flavor < 0)
+	if ((int)flavor < 0)
 		return ERR_PTR(flavor);
 
 	clone = rpc_clone_client(clnt);
@@ -300,7 +329,7 @@ out:
  * @dentry - dentry of referral
  *
  */
-struct vfsmount *nfs_do_refmount(struct rpc_clnt *client, struct dentry *dentry)
+static struct vfsmount *nfs_do_refmount(struct rpc_clnt *client, struct dentry *dentry)
 {
 	struct vfsmount *mnt = ERR_PTR(-ENOMEM);
 	struct dentry *parent;
@@ -341,3 +370,25 @@ out:
 	dprintk("%s: done\n", __func__);
 	return mnt;
 }
+
+struct vfsmount *nfs4_submount(struct nfs_server *server, struct dentry *dentry,
+			       struct nfs_fh *fh, struct nfs_fattr *fattr)
+{
+	struct dentry *parent = dget_parent(dentry);
+	struct rpc_clnt *client;
+	struct vfsmount *mnt;
+
+	/* Look it up again to get its attributes and sec flavor */
+	client = nfs4_proc_lookup_mountpoint(parent->d_inode, &dentry->d_name, fh, fattr);
+	dput(parent);
+	if (IS_ERR(client))
+		return ERR_CAST(client);
+
+	if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL)
+		mnt = nfs_do_refmount(client, dentry);
+	else
+		mnt = nfs_do_submount(dentry, fh, fattr, client->cl_auth->au_flavor);
+
+	rpc_shutdown_client(client);
+	return mnt;
+}
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index ab985f6f0da8..d48dbefa0e71 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -64,6 +64,7 @@
 #include "iostat.h"
 #include "callback.h"
 #include "pnfs.h"
+#include "netns.h"
 
 #define NFSDBG_FACILITY		NFSDBG_PROC
 
@@ -80,6 +81,7 @@ static int _nfs4_recover_proc_open(struct nfs4_opendata *data);
 static int nfs4_do_fsinfo(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *);
 static int nfs4_async_handle_error(struct rpc_task *, const struct nfs_server *, struct nfs4_state *);
 static void nfs_fixup_referral_attributes(struct nfs_fattr *fattr);
+static int nfs4_proc_getattr(struct nfs_server *, struct nfs_fh *, struct nfs_fattr *);
 static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr);
 static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
 			    struct nfs_fattr *fattr, struct iattr *sattr,
@@ -101,6 +103,8 @@ static int nfs4_map_errors(int err)
 	case -NFS4ERR_BADOWNER:
 	case -NFS4ERR_BADNAME:
 		return -EINVAL;
+	case -NFS4ERR_SHARE_DENIED:
+		return -EACCES;
 	default:
 		dprintk("%s could not handle NFSv4 error %d\n",
 				__func__, -err);
@@ -304,7 +308,7 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc
 		case -NFS4ERR_SEQ_MISORDERED:
 			dprintk("%s ERROR: %d Reset session\n", __func__,
 				errorcode);
-			nfs4_schedule_session_recovery(clp->cl_session);
+			nfs4_schedule_session_recovery(clp->cl_session, errorcode);
 			exception->retry = 1;
 			break;
 #endif /* defined(CONFIG_NFS_V4_1) */
@@ -772,7 +776,7 @@ static void update_changeattr(struct inode *dir, struct nfs4_change_info *cinfo)
 	struct nfs_inode *nfsi = NFS_I(dir);
 
 	spin_lock(&dir->i_lock);
-	nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE|NFS_INO_INVALID_DATA;
+	nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA;
 	if (!cinfo->atomic || cinfo->before != dir->i_version)
 		nfs_force_lookup_revalidate(dir);
 	dir->i_version = cinfo->after;
@@ -788,7 +792,6 @@ struct nfs4_opendata {
 	struct nfs4_string owner_name;
 	struct nfs4_string group_name;
 	struct nfs_fattr f_attr;
-	struct nfs_fattr dir_attr;
 	struct dentry *dir;
 	struct dentry *dentry;
 	struct nfs4_state_owner *owner;
@@ -804,12 +807,10 @@ struct nfs4_opendata {
 static void nfs4_init_opendata_res(struct nfs4_opendata *p)
 {
 	p->o_res.f_attr = &p->f_attr;
-	p->o_res.dir_attr = &p->dir_attr;
 	p->o_res.seqid = p->o_arg.seqid;
 	p->c_res.seqid = p->c_arg.seqid;
 	p->o_res.server = p->o_arg.server;
 	nfs_fattr_init(&p->f_attr);
-	nfs_fattr_init(&p->dir_attr);
 	nfs_fattr_init_names(&p->f_attr, &p->owner_name, &p->group_name);
 }
 
@@ -843,7 +844,6 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry,
 	p->o_arg.name = &dentry->d_name;
 	p->o_arg.server = server;
 	p->o_arg.bitmask = server->attr_bitmask;
-	p->o_arg.dir_bitmask = server->cache_consistency_bitmask;
 	p->o_arg.claim = NFS4_OPEN_CLAIM_NULL;
 	if (attrs != NULL && attrs->ia_valid != 0) {
 		__be32 verf[2];
@@ -1332,7 +1332,7 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state
 			case -NFS4ERR_BAD_HIGH_SLOT:
 			case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
 			case -NFS4ERR_DEADSESSION:
-				nfs4_schedule_session_recovery(server->nfs_client->cl_session);
+				nfs4_schedule_session_recovery(server->nfs_client->cl_session, err);
 				goto out;
 			case -NFS4ERR_STALE_CLIENTID:
 			case -NFS4ERR_STALE_STATEID:
@@ -1611,8 +1611,6 @@ static int _nfs4_recover_proc_open(struct nfs4_opendata *data)
 
 	nfs_fattr_map_and_free_names(NFS_SERVER(dir), &data->f_attr);
 
-	nfs_refresh_inode(dir, o_res->dir_attr);
-
 	if (o_res->rflags & NFS4_OPEN_RESULT_CONFIRM) {
 		status = _nfs4_proc_open_confirm(data);
 		if (status != 0)
@@ -1645,11 +1643,8 @@ static int _nfs4_proc_open(struct nfs4_opendata *data)
 
 	nfs_fattr_map_and_free_names(server, &data->f_attr);
 
-	if (o_arg->open_flags & O_CREAT) {
+	if (o_arg->open_flags & O_CREAT)
 		update_changeattr(dir, &o_res->cinfo);
-		nfs_post_op_update_inode(dir, o_res->dir_attr);
-	} else
-		nfs_refresh_inode(dir, o_res->dir_attr);
 	if ((o_res->rflags & NFS4_OPEN_RESULT_LOCKTYPE_POSIX) == 0)
 		server->caps &= ~NFS_CAP_POSIX_LOCK;
 	if(o_res->rflags & NFS4_OPEN_RESULT_CONFIRM) {
@@ -1789,7 +1784,14 @@ static inline void nfs4_exclusive_attrset(struct nfs4_opendata *opendata, struct
 /*
  * Returns a referenced nfs4_state
  */
-static int _nfs4_do_open(struct inode *dir, struct dentry *dentry, fmode_t fmode, int flags, struct iattr *sattr, struct rpc_cred *cred, struct nfs4_state **res)
+static int _nfs4_do_open(struct inode *dir,
+			struct dentry *dentry,
+			fmode_t fmode,
+			int flags,
+			struct iattr *sattr,
+			struct rpc_cred *cred,
+			struct nfs4_state **res,
+			struct nfs4_threshold **ctx_th)
 {
 	struct nfs4_state_owner  *sp;
 	struct nfs4_state     *state = NULL;
@@ -1814,6 +1816,11 @@ static int _nfs4_do_open(struct inode *dir, struct dentry *dentry, fmode_t fmode
 	if (opendata == NULL)
 		goto err_put_state_owner;
 
+	if (ctx_th && server->attr_bitmask[2] & FATTR4_WORD2_MDSTHRESHOLD) {
+		opendata->f_attr.mdsthreshold = pnfs_mdsthreshold_alloc();
+		if (!opendata->f_attr.mdsthreshold)
+			goto err_opendata_put;
+	}
 	if (dentry->d_inode != NULL)
 		opendata->state = nfs4_get_open_state(dentry->d_inode, sp);
 
@@ -1839,11 +1846,19 @@ static int _nfs4_do_open(struct inode *dir, struct dentry *dentry, fmode_t fmode
 			nfs_setattr_update_inode(state->inode, sattr);
 		nfs_post_op_update_inode(state->inode, opendata->o_res.f_attr);
 	}
+
+	if (pnfs_use_threshold(ctx_th, opendata->f_attr.mdsthreshold, server))
+		*ctx_th = opendata->f_attr.mdsthreshold;
+	else
+		kfree(opendata->f_attr.mdsthreshold);
+	opendata->f_attr.mdsthreshold = NULL;
+
 	nfs4_opendata_put(opendata);
 	nfs4_put_state_owner(sp);
 	*res = state;
 	return 0;
 err_opendata_put:
+	kfree(opendata->f_attr.mdsthreshold);
 	nfs4_opendata_put(opendata);
 err_put_state_owner:
 	nfs4_put_state_owner(sp);
@@ -1853,14 +1868,21 @@ out_err:
 }
 
 
-static struct nfs4_state *nfs4_do_open(struct inode *dir, struct dentry *dentry, fmode_t fmode, int flags, struct iattr *sattr, struct rpc_cred *cred)
+static struct nfs4_state *nfs4_do_open(struct inode *dir,
+					struct dentry *dentry,
+					fmode_t fmode,
+					int flags,
+					struct iattr *sattr,
+					struct rpc_cred *cred,
+					struct nfs4_threshold **ctx_th)
 {
 	struct nfs4_exception exception = { };
 	struct nfs4_state *res;
 	int status;
 
 	do {
-		status = _nfs4_do_open(dir, dentry, fmode, flags, sattr, cred, &res);
+		status = _nfs4_do_open(dir, dentry, fmode, flags, sattr, cred,
+				       &res, ctx_th);
 		if (status == 0)
 			break;
 		/* NOTE: BAD_SEQID means the server and client disagree about the
@@ -2184,7 +2206,8 @@ nfs4_atomic_open(struct inode *dir, struct nfs_open_context *ctx, int open_flags
 	struct nfs4_state *state;
 
 	/* Protect against concurrent sillydeletes */
-	state = nfs4_do_open(dir, ctx->dentry, ctx->mode, open_flags, attr, ctx->cred);
+	state = nfs4_do_open(dir, ctx->dentry, ctx->mode, open_flags, attr,
+			     ctx->cred, &ctx->mdsthreshold);
 	if (IS_ERR(state))
 		return ERR_CAST(state);
 	ctx->state = state;
@@ -2354,8 +2377,8 @@ static int nfs4_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle,
 /*
  * get the file handle for the "/" directory on the server
  */
-static int nfs4_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle,
-			      struct nfs_fsinfo *info)
+int nfs4_proc_get_rootfh(struct nfs_server *server, struct nfs_fh *fhandle,
+			 struct nfs_fsinfo *info)
 {
 	int minor_version = server->nfs_client->cl_minorversion;
 	int status = nfs4_lookup_root(server, fhandle, info);
@@ -2372,6 +2395,31 @@ static int nfs4_proc_get_root(struct nfs_server *server, struct nfs_fh *fhandle,
 	return nfs4_map_errors(status);
 }
 
+static int nfs4_proc_get_root(struct nfs_server *server, struct nfs_fh *mntfh,
+			      struct nfs_fsinfo *info)
+{
+	int error;
+	struct nfs_fattr *fattr = info->fattr;
+
+	error = nfs4_server_capabilities(server, mntfh);
+	if (error < 0) {
+		dprintk("nfs4_get_root: getcaps error = %d\n", -error);
+		return error;
+	}
+
+	error = nfs4_proc_getattr(server, mntfh, fattr);
+	if (error < 0) {
+		dprintk("nfs4_get_root: getattr error = %d\n", -error);
+		return error;
+	}
+
+	if (fattr->valid & NFS_ATTR_FATTR_FSID &&
+	    !nfs_fsid_equal(&server->fsid, &fattr->fsid))
+		memcpy(&server->fsid, &fattr->fsid, sizeof(server->fsid));
+
+	return error;
+}
+
 /*
  * Get locations and (maybe) other attributes of a referral.
  * Note that we'll actually follow the referral later when
@@ -2578,7 +2626,7 @@ out:
 	return err;
 }
 
-static int nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, struct qstr *name,
+static int nfs4_proc_lookup(struct inode *dir, struct qstr *name,
 			    struct nfs_fh *fhandle, struct nfs_fattr *fattr)
 {
 	int status;
@@ -2761,7 +2809,7 @@ nfs4_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
 		fmode = ctx->mode;
 	}
 	sattr->ia_mode &= ~current_umask();
-	state = nfs4_do_open(dir, de, fmode, flags, sattr, cred);
+	state = nfs4_do_open(dir, de, fmode, flags, sattr, cred, NULL);
 	d_drop(dentry);
 	if (IS_ERR(state)) {
 		status = PTR_ERR(state);
@@ -2783,7 +2831,6 @@ static int _nfs4_proc_remove(struct inode *dir, struct qstr *name)
 	struct nfs_removeargs args = {
 		.fh = NFS_FH(dir),
 		.name = *name,
-		.bitmask = server->attr_bitmask,
 	};
 	struct nfs_removeres res = {
 		.server = server,
@@ -2793,19 +2840,11 @@ static int _nfs4_proc_remove(struct inode *dir, struct qstr *name)
 		.rpc_argp = &args,
 		.rpc_resp = &res,
 	};
-	int status = -ENOMEM;
-
-	res.dir_attr = nfs_alloc_fattr();
-	if (res.dir_attr == NULL)
-		goto out;
+	int status;
 
 	status = nfs4_call_sync(server->client, server, &msg, &args.seq_args, &res.seq_res, 1);
-	if (status == 0) {
+	if (status == 0)
 		update_changeattr(dir, &res.cinfo);
-		nfs_post_op_update_inode(dir, res.dir_attr);
-	}
-	nfs_free_fattr(res.dir_attr);
-out:
 	return status;
 }
 
@@ -2827,7 +2866,6 @@ static void nfs4_proc_unlink_setup(struct rpc_message *msg, struct inode *dir)
 	struct nfs_removeargs *args = msg->rpc_argp;
 	struct nfs_removeres *res = msg->rpc_resp;
 
-	args->bitmask = server->cache_consistency_bitmask;
 	res->server = server;
 	msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_REMOVE];
 	nfs41_init_sequence(&args->seq_args, &res->seq_res, 1);
@@ -2852,7 +2890,6 @@ static int nfs4_proc_unlink_done(struct rpc_task *task, struct inode *dir)
 	if (nfs4_async_handle_error(task, res->server, NULL) == -EAGAIN)
 		return 0;
 	update_changeattr(dir, &res->cinfo);
-	nfs_post_op_update_inode(dir, res->dir_attr);
 	return 1;
 }
 
@@ -2863,7 +2900,6 @@ static void nfs4_proc_rename_setup(struct rpc_message *msg, struct inode *dir)
 	struct nfs_renameres *res = msg->rpc_resp;
 
 	msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_RENAME];
-	arg->bitmask = server->attr_bitmask;
 	res->server = server;
 	nfs41_init_sequence(&arg->seq_args, &res->seq_res, 1);
 }
@@ -2889,9 +2925,7 @@ static int nfs4_proc_rename_done(struct rpc_task *task, struct inode *old_dir,
 		return 0;
 
 	update_changeattr(old_dir, &res->old_cinfo);
-	nfs_post_op_update_inode(old_dir, res->old_fattr);
 	update_changeattr(new_dir, &res->new_cinfo);
-	nfs_post_op_update_inode(new_dir, res->new_fattr);
 	return 1;
 }
 
@@ -2904,7 +2938,6 @@ static int _nfs4_proc_rename(struct inode *old_dir, struct qstr *old_name,
 		.new_dir = NFS_FH(new_dir),
 		.old_name = old_name,
 		.new_name = new_name,
-		.bitmask = server->attr_bitmask,
 	};
 	struct nfs_renameres res = {
 		.server = server,
@@ -2916,21 +2949,11 @@ static int _nfs4_proc_rename(struct inode *old_dir, struct qstr *old_name,
 	};
 	int status = -ENOMEM;
 	
-	res.old_fattr = nfs_alloc_fattr();
-	res.new_fattr = nfs_alloc_fattr();
-	if (res.old_fattr == NULL || res.new_fattr == NULL)
-		goto out;
-
 	status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1);
 	if (!status) {
 		update_changeattr(old_dir, &res.old_cinfo);
-		nfs_post_op_update_inode(old_dir, res.old_fattr);
 		update_changeattr(new_dir, &res.new_cinfo);
-		nfs_post_op_update_inode(new_dir, res.new_fattr);
 	}
-out:
-	nfs_free_fattr(res.new_fattr);
-	nfs_free_fattr(res.old_fattr);
 	return status;
 }
 
@@ -2968,18 +2991,15 @@ static int _nfs4_proc_link(struct inode *inode, struct inode *dir, struct qstr *
 	int status = -ENOMEM;
 
 	res.fattr = nfs_alloc_fattr();
-	res.dir_attr = nfs_alloc_fattr();
-	if (res.fattr == NULL || res.dir_attr == NULL)
+	if (res.fattr == NULL)
 		goto out;
 
 	status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1);
 	if (!status) {
 		update_changeattr(dir, &res.cinfo);
-		nfs_post_op_update_inode(dir, res.dir_attr);
 		nfs_post_op_update_inode(inode, res.fattr);
 	}
 out:
-	nfs_free_fattr(res.dir_attr);
 	nfs_free_fattr(res.fattr);
 	return status;
 }
@@ -3002,7 +3022,6 @@ struct nfs4_createdata {
 	struct nfs4_create_res res;
 	struct nfs_fh fh;
 	struct nfs_fattr fattr;
-	struct nfs_fattr dir_fattr;
 };
 
 static struct nfs4_createdata *nfs4_alloc_createdata(struct inode *dir,
@@ -3026,9 +3045,7 @@ static struct nfs4_createdata *nfs4_alloc_createdata(struct inode *dir,
 		data->res.server = server;
 		data->res.fh = &data->fh;
 		data->res.fattr = &data->fattr;
-		data->res.dir_fattr = &data->dir_fattr;
 		nfs_fattr_init(data->res.fattr);
-		nfs_fattr_init(data->res.dir_fattr);
 	}
 	return data;
 }
@@ -3039,7 +3056,6 @@ static int nfs4_do_create(struct inode *dir, struct dentry *dentry, struct nfs4_
 				    &data->arg.seq_args, &data->res.seq_res, 1);
 	if (status == 0) {
 		update_changeattr(dir, &data->res.dir_cinfo);
-		nfs_post_op_update_inode(dir, data->res.dir_fattr);
 		status = nfs_instantiate(dentry, data->res.fh, data->res.fattr);
 	}
 	return status;
@@ -3335,12 +3351,12 @@ static int nfs4_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle,
 
 void __nfs4_read_done_cb(struct nfs_read_data *data)
 {
-	nfs_invalidate_atime(data->inode);
+	nfs_invalidate_atime(data->header->inode);
 }
 
 static int nfs4_read_done_cb(struct rpc_task *task, struct nfs_read_data *data)
 {
-	struct nfs_server *server = NFS_SERVER(data->inode);
+	struct nfs_server *server = NFS_SERVER(data->header->inode);
 
 	if (nfs4_async_handle_error(task, server, data->args.context->state) == -EAGAIN) {
 		rpc_restart_call_prepare(task);
@@ -3375,7 +3391,7 @@ static void nfs4_proc_read_setup(struct nfs_read_data *data, struct rpc_message
 
 static void nfs4_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_data *data)
 {
-	if (nfs4_setup_sequence(NFS_SERVER(data->inode),
+	if (nfs4_setup_sequence(NFS_SERVER(data->header->inode),
 				&data->args.seq_args,
 				&data->res.seq_res,
 				task))
@@ -3383,25 +3399,9 @@ static void nfs4_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_da
 	rpc_call_start(task);
 }
 
-/* Reset the the nfs_read_data to send the read to the MDS. */
-void nfs4_reset_read(struct rpc_task *task, struct nfs_read_data *data)
-{
-	dprintk("%s Reset task for i/o through\n", __func__);
-	put_lseg(data->lseg);
-	data->lseg = NULL;
-	/* offsets will differ in the dense stripe case */
-	data->args.offset = data->mds_offset;
-	data->ds_clp = NULL;
-	data->args.fh     = NFS_FH(data->inode);
-	data->read_done_cb = nfs4_read_done_cb;
-	task->tk_ops = data->mds_ops;
-	rpc_task_reset_client(task, NFS_CLIENT(data->inode));
-}
-EXPORT_SYMBOL_GPL(nfs4_reset_read);
-
 static int nfs4_write_done_cb(struct rpc_task *task, struct nfs_write_data *data)
 {
-	struct inode *inode = data->inode;
+	struct inode *inode = data->header->inode;
 	
 	if (nfs4_async_handle_error(task, NFS_SERVER(inode), data->args.context->state) == -EAGAIN) {
 		rpc_restart_call_prepare(task);
@@ -3409,7 +3409,7 @@ static int nfs4_write_done_cb(struct rpc_task *task, struct nfs_write_data *data
 	}
 	if (task->tk_status >= 0) {
 		renew_lease(NFS_SERVER(inode), data->timestamp);
-		nfs_post_op_update_inode_force_wcc(inode, data->res.fattr);
+		nfs_post_op_update_inode_force_wcc(inode, &data->fattr);
 	}
 	return 0;
 }
@@ -3422,32 +3422,30 @@ static int nfs4_write_done(struct rpc_task *task, struct nfs_write_data *data)
 		nfs4_write_done_cb(task, data);
 }
 
-/* Reset the the nfs_write_data to send the write to the MDS. */
-void nfs4_reset_write(struct rpc_task *task, struct nfs_write_data *data)
+static
+bool nfs4_write_need_cache_consistency_data(const struct nfs_write_data *data)
 {
-	dprintk("%s Reset task for i/o through\n", __func__);
-	put_lseg(data->lseg);
-	data->lseg          = NULL;
-	data->ds_clp        = NULL;
-	data->write_done_cb = nfs4_write_done_cb;
-	data->args.fh       = NFS_FH(data->inode);
-	data->args.bitmask  = data->res.server->cache_consistency_bitmask;
-	data->args.offset   = data->mds_offset;
-	data->res.fattr     = &data->fattr;
-	task->tk_ops        = data->mds_ops;
-	rpc_task_reset_client(task, NFS_CLIENT(data->inode));
+	const struct nfs_pgio_header *hdr = data->header;
+
+	/* Don't request attributes for pNFS or O_DIRECT writes */
+	if (data->ds_clp != NULL || hdr->dreq != NULL)
+		return false;
+	/* Otherwise, request attributes if and only if we don't hold
+	 * a delegation
+	 */
+	return nfs_have_delegation(hdr->inode, FMODE_READ) == 0;
 }
-EXPORT_SYMBOL_GPL(nfs4_reset_write);
 
 static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_message *msg)
 {
-	struct nfs_server *server = NFS_SERVER(data->inode);
+	struct nfs_server *server = NFS_SERVER(data->header->inode);
 
-	if (data->lseg) {
+	if (!nfs4_write_need_cache_consistency_data(data)) {
 		data->args.bitmask = NULL;
 		data->res.fattr = NULL;
 	} else
 		data->args.bitmask = server->cache_consistency_bitmask;
+
 	if (!data->write_done_cb)
 		data->write_done_cb = nfs4_write_done_cb;
 	data->res.server = server;
@@ -3459,6 +3457,16 @@ static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_messag
 
 static void nfs4_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_data *data)
 {
+	if (nfs4_setup_sequence(NFS_SERVER(data->header->inode),
+				&data->args.seq_args,
+				&data->res.seq_res,
+				task))
+		return;
+	rpc_call_start(task);
+}
+
+static void nfs4_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data)
+{
 	if (nfs4_setup_sequence(NFS_SERVER(data->inode),
 				&data->args.seq_args,
 				&data->res.seq_res,
@@ -3467,7 +3475,7 @@ static void nfs4_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_
 	rpc_call_start(task);
 }
 
-static int nfs4_commit_done_cb(struct rpc_task *task, struct nfs_write_data *data)
+static int nfs4_commit_done_cb(struct rpc_task *task, struct nfs_commit_data *data)
 {
 	struct inode *inode = data->inode;
 
@@ -3475,28 +3483,22 @@ static int nfs4_commit_done_cb(struct rpc_task *task, struct nfs_write_data *dat
 		rpc_restart_call_prepare(task);
 		return -EAGAIN;
 	}
-	nfs_refresh_inode(inode, data->res.fattr);
 	return 0;
 }
 
-static int nfs4_commit_done(struct rpc_task *task, struct nfs_write_data *data)
+static int nfs4_commit_done(struct rpc_task *task, struct nfs_commit_data *data)
 {
 	if (!nfs4_sequence_done(task, &data->res.seq_res))
 		return -EAGAIN;
-	return data->write_done_cb(task, data);
+	return data->commit_done_cb(task, data);
 }
 
-static void nfs4_proc_commit_setup(struct nfs_write_data *data, struct rpc_message *msg)
+static void nfs4_proc_commit_setup(struct nfs_commit_data *data, struct rpc_message *msg)
 {
 	struct nfs_server *server = NFS_SERVER(data->inode);
 
-	if (data->lseg) {
-		data->args.bitmask = NULL;
-		data->res.fattr = NULL;
-	} else
-		data->args.bitmask = server->cache_consistency_bitmask;
-	if (!data->write_done_cb)
-		data->write_done_cb = nfs4_commit_done_cb;
+	if (data->commit_done_cb == NULL)
+		data->commit_done_cb = nfs4_commit_done_cb;
 	data->res.server = server;
 	msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COMMIT];
 	nfs41_init_sequence(&data->args.seq_args, &data->res.seq_res, 1);
@@ -3905,7 +3907,7 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
 		case -NFS4ERR_SEQ_MISORDERED:
 			dprintk("%s ERROR %d, Reset session\n", __func__,
 				task->tk_status);
-			nfs4_schedule_session_recovery(clp->cl_session);
+			nfs4_schedule_session_recovery(clp->cl_session, task->tk_status);
 			task->tk_status = 0;
 			return -EAGAIN;
 #endif /* CONFIG_NFS_V4_1 */
@@ -3931,13 +3933,21 @@ wait_on_recovery:
 	return -EAGAIN;
 }
 
-static void nfs4_construct_boot_verifier(struct nfs_client *clp,
-					 nfs4_verifier *bootverf)
+static void nfs4_init_boot_verifier(const struct nfs_client *clp,
+				    nfs4_verifier *bootverf)
 {
 	__be32 verf[2];
 
-	verf[0] = htonl((u32)clp->cl_boot_time.tv_sec);
-	verf[1] = htonl((u32)clp->cl_boot_time.tv_nsec);
+	if (test_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state)) {
+		/* An impossible timestamp guarantees this value
+		 * will never match a generated boot time. */
+		verf[0] = 0;
+		verf[1] = (__be32)(NSEC_PER_SEC + 1);
+	} else {
+		struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id);
+		verf[0] = (__be32)nn->boot_time.tv_sec;
+		verf[1] = (__be32)nn->boot_time.tv_nsec;
+	}
 	memcpy(bootverf->data, verf, sizeof(bootverf->data));
 }
 
@@ -3960,7 +3970,7 @@ int nfs4_proc_setclientid(struct nfs_client *clp, u32 program,
 	int loop = 0;
 	int status;
 
-	nfs4_construct_boot_verifier(clp, &sc_verifier);
+	nfs4_init_boot_verifier(clp, &sc_verifier);
 
 	for(;;) {
 		rcu_read_lock();
@@ -4104,7 +4114,7 @@ static int _nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, co
 	nfs41_init_sequence(&data->args.seq_args, &data->res.seq_res, 1);
 	data->args.fhandle = &data->fh;
 	data->args.stateid = &data->stateid;
-	data->args.bitmask = server->attr_bitmask;
+	data->args.bitmask = server->cache_consistency_bitmask;
 	nfs_copy_fh(&data->fh, NFS_FH(inode));
 	nfs4_stateid_copy(&data->stateid, stateid);
 	data->res.fattr = &data->fattr;
@@ -4125,9 +4135,10 @@ static int _nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, co
 	if (status != 0)
 		goto out;
 	status = data->rpc_status;
-	if (status != 0)
-		goto out;
-	nfs_refresh_inode(inode, &data->fattr);
+	if (status == 0)
+		nfs_post_op_update_inode_force_wcc(inode, &data->fattr);
+	else
+		nfs_refresh_inode(inode, &data->fattr);
 out:
 	rpc_put_task(task);
 	return status;
@@ -4837,7 +4848,7 @@ int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl)
 			case -NFS4ERR_BAD_HIGH_SLOT:
 			case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
 			case -NFS4ERR_DEADSESSION:
-				nfs4_schedule_session_recovery(server->nfs_client->cl_session);
+				nfs4_schedule_session_recovery(server->nfs_client->cl_session, err);
 				goto out;
 			case -ERESTARTSYS:
 				/*
@@ -5079,7 +5090,8 @@ out_inval:
 }
 
 static bool
-nfs41_same_server_scope(struct server_scope *a, struct server_scope *b)
+nfs41_same_server_scope(struct nfs41_server_scope *a,
+			struct nfs41_server_scope *b)
 {
 	if (a->server_scope_sz == b->server_scope_sz &&
 	    memcmp(a->server_scope, b->server_scope, a->server_scope_sz) == 0)
@@ -5089,6 +5101,61 @@ nfs41_same_server_scope(struct server_scope *a, struct server_scope *b)
 }
 
 /*
+ * nfs4_proc_bind_conn_to_session()
+ *
+ * The 4.1 client currently uses the same TCP connection for the
+ * fore and backchannel.
+ */
+int nfs4_proc_bind_conn_to_session(struct nfs_client *clp, struct rpc_cred *cred)
+{
+	int status;
+	struct nfs41_bind_conn_to_session_res res;
+	struct rpc_message msg = {
+		.rpc_proc =
+			&nfs4_procedures[NFSPROC4_CLNT_BIND_CONN_TO_SESSION],
+		.rpc_argp = clp,
+		.rpc_resp = &res,
+		.rpc_cred = cred,
+	};
+
+	dprintk("--> %s\n", __func__);
+	BUG_ON(clp == NULL);
+
+	res.session = kzalloc(sizeof(struct nfs4_session), GFP_NOFS);
+	if (unlikely(res.session == NULL)) {
+		status = -ENOMEM;
+		goto out;
+	}
+
+	status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
+	if (status == 0) {
+		if (memcmp(res.session->sess_id.data,
+		    clp->cl_session->sess_id.data, NFS4_MAX_SESSIONID_LEN)) {
+			dprintk("NFS: %s: Session ID mismatch\n", __func__);
+			status = -EIO;
+			goto out_session;
+		}
+		if (res.dir != NFS4_CDFS4_BOTH) {
+			dprintk("NFS: %s: Unexpected direction from server\n",
+				__func__);
+			status = -EIO;
+			goto out_session;
+		}
+		if (res.use_conn_in_rdma_mode) {
+			dprintk("NFS: %s: Server returned RDMA mode = true\n",
+				__func__);
+			status = -EIO;
+			goto out_session;
+		}
+	}
+out_session:
+	kfree(res.session);
+out:
+	dprintk("<-- %s status= %d\n", __func__, status);
+	return status;
+}
+
+/*
  * nfs4_proc_exchange_id()
  *
  * Since the clientid has expired, all compounds using sessions
@@ -5105,7 +5172,7 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred)
 		.flags = EXCHGID4_FLAG_SUPP_MOVED_REFER,
 	};
 	struct nfs41_exchange_id_res res = {
-		.client = clp,
+		0
 	};
 	int status;
 	struct rpc_message msg = {
@@ -5118,7 +5185,7 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred)
 	dprintk("--> %s\n", __func__);
 	BUG_ON(clp == NULL);
 
-	nfs4_construct_boot_verifier(clp, &verifier);
+	nfs4_init_boot_verifier(clp, &verifier);
 
 	args.id_len = scnprintf(args.id, sizeof(args.id),
 				"%s/%s/%u",
@@ -5126,59 +5193,135 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred)
 				clp->cl_rpcclient->cl_nodename,
 				clp->cl_rpcclient->cl_auth->au_flavor);
 
-	res.server_scope = kzalloc(sizeof(struct server_scope), GFP_KERNEL);
-	if (unlikely(!res.server_scope)) {
+	res.server_owner = kzalloc(sizeof(struct nfs41_server_owner),
+					GFP_NOFS);
+	if (unlikely(res.server_owner == NULL)) {
 		status = -ENOMEM;
 		goto out;
 	}
 
-	res.impl_id = kzalloc(sizeof(struct nfs41_impl_id), GFP_KERNEL);
-	if (unlikely(!res.impl_id)) {
+	res.server_scope = kzalloc(sizeof(struct nfs41_server_scope),
+					GFP_NOFS);
+	if (unlikely(res.server_scope == NULL)) {
+		status = -ENOMEM;
+		goto out_server_owner;
+	}
+
+	res.impl_id = kzalloc(sizeof(struct nfs41_impl_id), GFP_NOFS);
+	if (unlikely(res.impl_id == NULL)) {
 		status = -ENOMEM;
 		goto out_server_scope;
 	}
 
 	status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
-	if (!status)
-		status = nfs4_check_cl_exchange_flags(clp->cl_exchange_flags);
+	if (status == 0)
+		status = nfs4_check_cl_exchange_flags(res.flags);
+
+	if (status == 0) {
+		clp->cl_clientid = res.clientid;
+		clp->cl_exchange_flags = (res.flags & ~EXCHGID4_FLAG_CONFIRMED_R);
+		if (!(res.flags & EXCHGID4_FLAG_CONFIRMED_R))
+			clp->cl_seqid = res.seqid;
+
+		kfree(clp->cl_serverowner);
+		clp->cl_serverowner = res.server_owner;
+		res.server_owner = NULL;
 
-	if (!status) {
 		/* use the most recent implementation id */
-		kfree(clp->impl_id);
-		clp->impl_id = res.impl_id;
-	} else
-		kfree(res.impl_id);
+		kfree(clp->cl_implid);
+		clp->cl_implid = res.impl_id;
 
-	if (!status) {
-		if (clp->server_scope &&
-		    !nfs41_same_server_scope(clp->server_scope,
+		if (clp->cl_serverscope != NULL &&
+		    !nfs41_same_server_scope(clp->cl_serverscope,
 					     res.server_scope)) {
 			dprintk("%s: server_scope mismatch detected\n",
 				__func__);
 			set_bit(NFS4CLNT_SERVER_SCOPE_MISMATCH, &clp->cl_state);
-			kfree(clp->server_scope);
-			clp->server_scope = NULL;
+			kfree(clp->cl_serverscope);
+			clp->cl_serverscope = NULL;
 		}
 
-		if (!clp->server_scope) {
-			clp->server_scope = res.server_scope;
+		if (clp->cl_serverscope == NULL) {
+			clp->cl_serverscope = res.server_scope;
 			goto out;
 		}
-	}
+	} else
+		kfree(res.impl_id);
 
+out_server_owner:
+	kfree(res.server_owner);
 out_server_scope:
 	kfree(res.server_scope);
 out:
-	if (clp->impl_id)
+	if (clp->cl_implid != NULL)
 		dprintk("%s: Server Implementation ID: "
 			"domain: %s, name: %s, date: %llu,%u\n",
-			__func__, clp->impl_id->domain, clp->impl_id->name,
-			clp->impl_id->date.seconds,
-			clp->impl_id->date.nseconds);
+			__func__, clp->cl_implid->domain, clp->cl_implid->name,
+			clp->cl_implid->date.seconds,
+			clp->cl_implid->date.nseconds);
 	dprintk("<-- %s status= %d\n", __func__, status);
 	return status;
 }
 
+static int _nfs4_proc_destroy_clientid(struct nfs_client *clp,
+		struct rpc_cred *cred)
+{
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_DESTROY_CLIENTID],
+		.rpc_argp = clp,
+		.rpc_cred = cred,
+	};
+	int status;
+
+	status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
+	if (status)
+		pr_warn("NFS: Got error %d from the server %s on "
+			"DESTROY_CLIENTID.", status, clp->cl_hostname);
+	return status;
+}
+
+static int nfs4_proc_destroy_clientid(struct nfs_client *clp,
+		struct rpc_cred *cred)
+{
+	unsigned int loop;
+	int ret;
+
+	for (loop = NFS4_MAX_LOOP_ON_RECOVER; loop != 0; loop--) {
+		ret = _nfs4_proc_destroy_clientid(clp, cred);
+		switch (ret) {
+		case -NFS4ERR_DELAY:
+		case -NFS4ERR_CLIENTID_BUSY:
+			ssleep(1);
+			break;
+		default:
+			return ret;
+		}
+	}
+	return 0;
+}
+
+int nfs4_destroy_clientid(struct nfs_client *clp)
+{
+	struct rpc_cred *cred;
+	int ret = 0;
+
+	if (clp->cl_mvops->minor_version < 1)
+		goto out;
+	if (clp->cl_exchange_flags == 0)
+		goto out;
+	cred = nfs4_get_exchange_id_cred(clp);
+	ret = nfs4_proc_destroy_clientid(clp, cred);
+	if (cred)
+		put_rpccred(cred);
+	switch (ret) {
+	case 0:
+	case -NFS4ERR_STALE_CLIENTID:
+		clp->cl_exchange_flags = 0;
+	}
+out:
+	return ret;
+}
+
 struct nfs4_get_lease_time_data {
 	struct nfs4_get_lease_time_args *args;
 	struct nfs4_get_lease_time_res *res;
@@ -5399,8 +5542,12 @@ struct nfs4_session *nfs4_alloc_session(struct nfs_client *clp)
 void nfs4_destroy_session(struct nfs4_session *session)
 {
 	struct rpc_xprt *xprt;
+	struct rpc_cred *cred;
 
-	nfs4_proc_destroy_session(session);
+	cred = nfs4_get_exchange_id_cred(session->clp);
+	nfs4_proc_destroy_session(session, cred);
+	if (cred)
+		put_rpccred(cred);
 
 	rcu_read_lock();
 	xprt = rcu_dereference(session->clp->cl_rpcclient->cl_xprt);
@@ -5510,7 +5657,8 @@ static int nfs4_verify_channel_attrs(struct nfs41_create_session_args *args,
 	return nfs4_verify_back_channel_attrs(args, session);
 }
 
-static int _nfs4_proc_create_session(struct nfs_client *clp)
+static int _nfs4_proc_create_session(struct nfs_client *clp,
+		struct rpc_cred *cred)
 {
 	struct nfs4_session *session = clp->cl_session;
 	struct nfs41_create_session_args args = {
@@ -5524,6 +5672,7 @@ static int _nfs4_proc_create_session(struct nfs_client *clp)
 		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CREATE_SESSION],
 		.rpc_argp = &args,
 		.rpc_resp = &res,
+		.rpc_cred = cred,
 	};
 	int status;
 
@@ -5548,7 +5697,7 @@ static int _nfs4_proc_create_session(struct nfs_client *clp)
  * It is the responsibility of the caller to verify the session is
  * expired before calling this routine.
  */
-int nfs4_proc_create_session(struct nfs_client *clp)
+int nfs4_proc_create_session(struct nfs_client *clp, struct rpc_cred *cred)
 {
 	int status;
 	unsigned *ptr;
@@ -5556,7 +5705,7 @@ int nfs4_proc_create_session(struct nfs_client *clp)
 
 	dprintk("--> %s clp=%p session=%p\n", __func__, clp, session);
 
-	status = _nfs4_proc_create_session(clp);
+	status = _nfs4_proc_create_session(clp, cred);
 	if (status)
 		goto out;
 
@@ -5578,10 +5727,15 @@ out:
  * Issue the over-the-wire RPC DESTROY_SESSION.
  * The caller must serialize access to this routine.
  */
-int nfs4_proc_destroy_session(struct nfs4_session *session)
+int nfs4_proc_destroy_session(struct nfs4_session *session,
+		struct rpc_cred *cred)
 {
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_DESTROY_SESSION],
+		.rpc_argp = session,
+		.rpc_cred = cred,
+	};
 	int status = 0;
-	struct rpc_message msg;
 
 	dprintk("--> nfs4_proc_destroy_session\n");
 
@@ -5589,10 +5743,6 @@ int nfs4_proc_destroy_session(struct nfs4_session *session)
 	if (session->clp->cl_cons_state != NFS_CS_READY)
 		return status;
 
-	msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_DESTROY_SESSION];
-	msg.rpc_argp = session;
-	msg.rpc_resp = NULL;
-	msg.rpc_cred = NULL;
 	status = rpc_call_sync(session->clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
 
 	if (status)
@@ -5604,53 +5754,79 @@ int nfs4_proc_destroy_session(struct nfs4_session *session)
 	return status;
 }
 
+/*
+ * With sessions, the client is not marked ready until after a
+ * successful EXCHANGE_ID and CREATE_SESSION.
+ *
+ * Map errors cl_cons_state errors to EPROTONOSUPPORT to indicate
+ * other versions of NFS can be tried.
+ */
+static int nfs41_check_session_ready(struct nfs_client *clp)
+{
+	int ret;
+	
+	if (clp->cl_cons_state == NFS_CS_SESSION_INITING) {
+		ret = nfs4_client_recover_expired_lease(clp);
+		if (ret)
+			return ret;
+	}
+	if (clp->cl_cons_state < NFS_CS_READY)
+		return -EPROTONOSUPPORT;
+	smp_rmb();
+	return 0;
+}
+
 int nfs4_init_session(struct nfs_server *server)
 {
 	struct nfs_client *clp = server->nfs_client;
 	struct nfs4_session *session;
 	unsigned int rsize, wsize;
-	int ret;
 
 	if (!nfs4_has_session(clp))
 		return 0;
 
 	session = clp->cl_session;
-	if (!test_and_clear_bit(NFS4_SESSION_INITING, &session->session_state))
-		return 0;
+	spin_lock(&clp->cl_lock);
+	if (test_and_clear_bit(NFS4_SESSION_INITING, &session->session_state)) {
 
-	rsize = server->rsize;
-	if (rsize == 0)
-		rsize = NFS_MAX_FILE_IO_SIZE;
-	wsize = server->wsize;
-	if (wsize == 0)
-		wsize = NFS_MAX_FILE_IO_SIZE;
+		rsize = server->rsize;
+		if (rsize == 0)
+			rsize = NFS_MAX_FILE_IO_SIZE;
+		wsize = server->wsize;
+		if (wsize == 0)
+			wsize = NFS_MAX_FILE_IO_SIZE;
 
-	session->fc_attrs.max_rqst_sz = wsize + nfs41_maxwrite_overhead;
-	session->fc_attrs.max_resp_sz = rsize + nfs41_maxread_overhead;
+		session->fc_attrs.max_rqst_sz = wsize + nfs41_maxwrite_overhead;
+		session->fc_attrs.max_resp_sz = rsize + nfs41_maxread_overhead;
+	}
+	spin_unlock(&clp->cl_lock);
 
-	ret = nfs4_recover_expired_lease(server);
-	if (!ret)
-		ret = nfs4_check_client_ready(clp);
-	return ret;
+	return nfs41_check_session_ready(clp);
 }
 
-int nfs4_init_ds_session(struct nfs_client *clp)
+int nfs4_init_ds_session(struct nfs_client *clp, unsigned long lease_time)
 {
 	struct nfs4_session *session = clp->cl_session;
 	int ret;
 
-	if (!test_and_clear_bit(NFS4_SESSION_INITING, &session->session_state))
-		return 0;
-
-	ret = nfs4_client_recover_expired_lease(clp);
-	if (!ret)
-		/* Test for the DS role */
-		if (!is_ds_client(clp))
-			ret = -ENODEV;
-	if (!ret)
-		ret = nfs4_check_client_ready(clp);
-	return ret;
+	spin_lock(&clp->cl_lock);
+	if (test_and_clear_bit(NFS4_SESSION_INITING, &session->session_state)) {
+		/*
+		 * Do not set NFS_CS_CHECK_LEASE_TIME instead set the
+		 * DS lease to be equal to the MDS lease.
+		 */
+		clp->cl_lease_time = lease_time;
+		clp->cl_last_renewal = jiffies;
+	}
+	spin_unlock(&clp->cl_lock);
 
+	ret = nfs41_check_session_ready(clp);
+	if (ret)
+		return ret;
+	/* Test for the DS role */
+	if (!is_ds_client(clp))
+		return -ENODEV;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(nfs4_init_ds_session);
 
@@ -6557,6 +6733,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
 	.file_inode_ops	= &nfs4_file_inode_operations,
 	.file_ops	= &nfs4_file_operations,
 	.getroot	= nfs4_proc_get_root,
+	.submount	= nfs4_submount,
 	.getattr	= nfs4_proc_getattr,
 	.setattr	= nfs4_proc_setattr,
 	.lookup		= nfs4_proc_lookup,
@@ -6589,13 +6766,13 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
 	.write_rpc_prepare = nfs4_proc_write_rpc_prepare,
 	.write_done	= nfs4_write_done,
 	.commit_setup	= nfs4_proc_commit_setup,
+	.commit_rpc_prepare = nfs4_proc_commit_rpc_prepare,
 	.commit_done	= nfs4_commit_done,
 	.lock		= nfs4_proc_lock,
 	.clear_acl_cache = nfs4_zap_acl_attr,
 	.close_context  = nfs4_close_context,
 	.open_context	= nfs4_atomic_open,
 	.init_client	= nfs4_init_client,
-	.secinfo	= nfs4_proc_secinfo,
 };
 
 static const struct xattr_handler nfs4_xattr_nfs4_acl_handler = {
diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c
index dc484c0eae7f..6930bec91bca 100644
--- a/fs/nfs/nfs4renewd.c
+++ b/fs/nfs/nfs4renewd.c
@@ -49,7 +49,7 @@
 #include "nfs4_fs.h"
 #include "delegation.h"
 
-#define NFSDBG_FACILITY	NFSDBG_PROC
+#define NFSDBG_FACILITY		NFSDBG_STATE
 
 void
 nfs4_renew_state(struct work_struct *work)
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 7f0fcfc1fe9d..c679b9ecef63 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -57,6 +57,8 @@
 #include "internal.h"
 #include "pnfs.h"
 
+#define NFSDBG_FACILITY		NFSDBG_STATE
+
 #define OPENOWNER_POOL_SIZE	8
 
 const nfs4_stateid zero_stateid;
@@ -254,7 +256,7 @@ int nfs41_init_clientid(struct nfs_client *clp, struct rpc_cred *cred)
 		goto out;
 	set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
 do_confirm:
-	status = nfs4_proc_create_session(clp);
+	status = nfs4_proc_create_session(clp, cred);
 	if (status != 0)
 		goto out;
 	clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
@@ -1106,6 +1108,8 @@ void nfs4_schedule_lease_recovery(struct nfs_client *clp)
 		return;
 	if (!test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state))
 		set_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state);
+	dprintk("%s: scheduling lease recovery for server %s\n", __func__,
+			clp->cl_hostname);
 	nfs4_schedule_state_manager(clp);
 }
 EXPORT_SYMBOL_GPL(nfs4_schedule_lease_recovery);
@@ -1122,6 +1126,8 @@ static void nfs40_handle_cb_pathdown(struct nfs_client *clp)
 {
 	set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
 	nfs_expire_all_delegations(clp);
+	dprintk("%s: handling CB_PATHDOWN recovery for server %s\n", __func__,
+			clp->cl_hostname);
 }
 
 void nfs4_schedule_path_down_recovery(struct nfs_client *clp)
@@ -1158,6 +1164,8 @@ void nfs4_schedule_stateid_recovery(const struct nfs_server *server, struct nfs4
 	struct nfs_client *clp = server->nfs_client;
 
 	nfs4_state_mark_reclaim_nograce(clp, state);
+	dprintk("%s: scheduling stateid recovery for server %s\n", __func__,
+			clp->cl_hostname);
 	nfs4_schedule_state_manager(clp);
 }
 EXPORT_SYMBOL_GPL(nfs4_schedule_stateid_recovery);
@@ -1491,19 +1499,25 @@ static int nfs4_recovery_handle_error(struct nfs_client *clp, int error)
 		case -NFS4ERR_BADSLOT:
 		case -NFS4ERR_BAD_HIGH_SLOT:
 		case -NFS4ERR_DEADSESSION:
-		case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
 		case -NFS4ERR_SEQ_FALSE_RETRY:
 		case -NFS4ERR_SEQ_MISORDERED:
 			set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
 			/* Zero session reset errors */
 			break;
+		case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
+			set_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state);
+			break;
 		case -EKEYEXPIRED:
 			/* Nothing we can do */
 			nfs4_warn_keyexpired(clp->cl_hostname);
 			break;
 		default:
+			dprintk("%s: failed to handle error %d for server %s\n",
+					__func__, error, clp->cl_hostname);
 			return error;
 	}
+	dprintk("%s: handled error %d for server %s\n", __func__, error,
+			clp->cl_hostname);
 	return 0;
 }
 
@@ -1572,34 +1586,82 @@ out:
 	return nfs4_recovery_handle_error(clp, status);
 }
 
+/* Set NFS4CLNT_LEASE_EXPIRED for all v4.0 errors and for recoverable errors
+ * on EXCHANGE_ID for v4.1
+ */
+static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status)
+{
+	switch (status) {
+	case -NFS4ERR_SEQ_MISORDERED:
+		if (test_and_set_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state))
+			return -ESERVERFAULT;
+		/* Lease confirmation error: retry after purging the lease */
+		ssleep(1);
+	case -NFS4ERR_CLID_INUSE:
+	case -NFS4ERR_STALE_CLIENTID:
+		clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
+		break;
+	case -EACCES:
+		if (clp->cl_machine_cred == NULL)
+			return -EACCES;
+		/* Handle case where the user hasn't set up machine creds */
+		nfs4_clear_machine_cred(clp);
+	case -NFS4ERR_DELAY:
+	case -ETIMEDOUT:
+	case -EAGAIN:
+		ssleep(1);
+		break;
+
+	case -NFS4ERR_MINOR_VERS_MISMATCH:
+		if (clp->cl_cons_state == NFS_CS_SESSION_INITING)
+			nfs_mark_client_ready(clp, -EPROTONOSUPPORT);
+		dprintk("%s: exit with error %d for server %s\n",
+				__func__, -EPROTONOSUPPORT, clp->cl_hostname);
+		return -EPROTONOSUPPORT;
+	case -EKEYEXPIRED:
+		nfs4_warn_keyexpired(clp->cl_hostname);
+	case -NFS4ERR_NOT_SAME: /* FixMe: implement recovery
+				 * in nfs4_exchange_id */
+	default:
+		dprintk("%s: exit with error %d for server %s\n", __func__,
+				status, clp->cl_hostname);
+		return status;
+	}
+	set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
+	dprintk("%s: handled error %d for server %s\n", __func__, status,
+			clp->cl_hostname);
+	return 0;
+}
+
 static int nfs4_reclaim_lease(struct nfs_client *clp)
 {
 	struct rpc_cred *cred;
 	const struct nfs4_state_recovery_ops *ops =
 		clp->cl_mvops->reboot_recovery_ops;
-	int status = -ENOENT;
+	int status;
 
 	cred = ops->get_clid_cred(clp);
-	if (cred != NULL) {
-		status = ops->establish_clid(clp, cred);
-		put_rpccred(cred);
-		/* Handle case where the user hasn't set up machine creds */
-		if (status == -EACCES && cred == clp->cl_machine_cred) {
-			nfs4_clear_machine_cred(clp);
-			status = -EAGAIN;
-		}
-		if (status == -NFS4ERR_MINOR_VERS_MISMATCH)
-			status = -EPROTONOSUPPORT;
-	}
-	return status;
+	if (cred == NULL)
+		return -ENOENT;
+	status = ops->establish_clid(clp, cred);
+	put_rpccred(cred);
+	if (status != 0)
+		return nfs4_handle_reclaim_lease_error(clp, status);
+	return 0;
 }
 
 #ifdef CONFIG_NFS_V4_1
-void nfs4_schedule_session_recovery(struct nfs4_session *session)
+void nfs4_schedule_session_recovery(struct nfs4_session *session, int err)
 {
 	struct nfs_client *clp = session->clp;
 
-	set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
+	switch (err) {
+	default:
+		set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
+		break;
+	case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
+		set_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state);
+	}
 	nfs4_schedule_lease_recovery(clp);
 }
 EXPORT_SYMBOL_GPL(nfs4_schedule_session_recovery);
@@ -1607,14 +1669,19 @@ EXPORT_SYMBOL_GPL(nfs4_schedule_session_recovery);
 void nfs41_handle_recall_slot(struct nfs_client *clp)
 {
 	set_bit(NFS4CLNT_RECALL_SLOT, &clp->cl_state);
+	dprintk("%s: scheduling slot recall for server %s\n", __func__,
+			clp->cl_hostname);
 	nfs4_schedule_state_manager(clp);
 }
 
 static void nfs4_reset_all_state(struct nfs_client *clp)
 {
 	if (test_and_set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) == 0) {
-		clp->cl_boot_time = CURRENT_TIME;
+		set_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state);
+		clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
 		nfs4_state_start_reclaim_nograce(clp);
+		dprintk("%s: scheduling reset of all state for server %s!\n",
+				__func__, clp->cl_hostname);
 		nfs4_schedule_state_manager(clp);
 	}
 }
@@ -1623,33 +1690,50 @@ static void nfs41_handle_server_reboot(struct nfs_client *clp)
 {
 	if (test_and_set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) == 0) {
 		nfs4_state_start_reclaim_reboot(clp);
+		dprintk("%s: server %s rebooted!\n", __func__,
+				clp->cl_hostname);
 		nfs4_schedule_state_manager(clp);
 	}
 }
 
 static void nfs41_handle_state_revoked(struct nfs_client *clp)
 {
-	/* Temporary */
 	nfs4_reset_all_state(clp);
+	dprintk("%s: state revoked on server %s\n", __func__, clp->cl_hostname);
 }
 
 static void nfs41_handle_recallable_state_revoked(struct nfs_client *clp)
 {
 	/* This will need to handle layouts too */
 	nfs_expire_all_delegations(clp);
+	dprintk("%s: Recallable state revoked on server %s!\n", __func__,
+			clp->cl_hostname);
 }
 
-static void nfs41_handle_cb_path_down(struct nfs_client *clp)
+static void nfs41_handle_backchannel_fault(struct nfs_client *clp)
 {
 	nfs_expire_all_delegations(clp);
 	if (test_and_set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state) == 0)
 		nfs4_schedule_state_manager(clp);
+	dprintk("%s: server %s declared a backchannel fault\n", __func__,
+			clp->cl_hostname);
+}
+
+static void nfs41_handle_cb_path_down(struct nfs_client *clp)
+{
+	if (test_and_set_bit(NFS4CLNT_BIND_CONN_TO_SESSION,
+		&clp->cl_state) == 0)
+		nfs4_schedule_state_manager(clp);
 }
 
 void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags)
 {
 	if (!flags)
 		return;
+
+	dprintk("%s: \"%s\" (client ID %llx) flags=0x%08x\n",
+		__func__, clp->cl_hostname, clp->cl_clientid, flags);
+
 	if (flags & SEQ4_STATUS_RESTART_RECLAIM_NEEDED)
 		nfs41_handle_server_reboot(clp);
 	if (flags & (SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED |
@@ -1659,18 +1743,21 @@ void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags)
 		nfs41_handle_state_revoked(clp);
 	if (flags & SEQ4_STATUS_RECALLABLE_STATE_REVOKED)
 		nfs41_handle_recallable_state_revoked(clp);
-	if (flags & (SEQ4_STATUS_CB_PATH_DOWN |
-			    SEQ4_STATUS_BACKCHANNEL_FAULT |
-			    SEQ4_STATUS_CB_PATH_DOWN_SESSION))
+	if (flags & SEQ4_STATUS_BACKCHANNEL_FAULT)
+		nfs41_handle_backchannel_fault(clp);
+	else if (flags & (SEQ4_STATUS_CB_PATH_DOWN |
+				SEQ4_STATUS_CB_PATH_DOWN_SESSION))
 		nfs41_handle_cb_path_down(clp);
 }
 
 static int nfs4_reset_session(struct nfs_client *clp)
 {
+	struct rpc_cred *cred;
 	int status;
 
 	nfs4_begin_drain_session(clp);
-	status = nfs4_proc_destroy_session(clp->cl_session);
+	cred = nfs4_get_exchange_id_cred(clp);
+	status = nfs4_proc_destroy_session(clp->cl_session, cred);
 	if (status && status != -NFS4ERR_BADSESSION &&
 	    status != -NFS4ERR_DEADSESSION) {
 		status = nfs4_recovery_handle_error(clp, status);
@@ -1678,19 +1765,26 @@ static int nfs4_reset_session(struct nfs_client *clp)
 	}
 
 	memset(clp->cl_session->sess_id.data, 0, NFS4_MAX_SESSIONID_LEN);
-	status = nfs4_proc_create_session(clp);
+	status = nfs4_proc_create_session(clp, cred);
 	if (status) {
-		status = nfs4_recovery_handle_error(clp, status);
+		dprintk("%s: session reset failed with status %d for server %s!\n",
+			__func__, status, clp->cl_hostname);
+		status = nfs4_handle_reclaim_lease_error(clp, status);
 		goto out;
 	}
 	clear_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
 	/* create_session negotiated new slot table */
 	clear_bit(NFS4CLNT_RECALL_SLOT, &clp->cl_state);
+	clear_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state);
+	dprintk("%s: session reset was successful for server %s!\n",
+			__func__, clp->cl_hostname);
 
 	 /* Let the state manager reestablish state */
 	if (!test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state))
 		nfs41_setup_state_renewal(clp);
 out:
+	if (cred)
+		put_rpccred(cred);
 	return status;
 }
 
@@ -1722,37 +1816,41 @@ static int nfs4_recall_slot(struct nfs_client *clp)
 	return 0;
 }
 
-#else /* CONFIG_NFS_V4_1 */
-static int nfs4_reset_session(struct nfs_client *clp) { return 0; }
-static int nfs4_end_drain_session(struct nfs_client *clp) { return 0; }
-static int nfs4_recall_slot(struct nfs_client *clp) { return 0; }
-#endif /* CONFIG_NFS_V4_1 */
-
-/* Set NFS4CLNT_LEASE_EXPIRED for all v4.0 errors and for recoverable errors
- * on EXCHANGE_ID for v4.1
- */
-static void nfs4_set_lease_expired(struct nfs_client *clp, int status)
+static int nfs4_bind_conn_to_session(struct nfs_client *clp)
 {
-	switch (status) {
-	case -NFS4ERR_CLID_INUSE:
-	case -NFS4ERR_STALE_CLIENTID:
-		clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
+	struct rpc_cred *cred;
+	int ret;
+
+	nfs4_begin_drain_session(clp);
+	cred = nfs4_get_exchange_id_cred(clp);
+	ret = nfs4_proc_bind_conn_to_session(clp, cred);
+	if (cred)
+		put_rpccred(cred);
+	clear_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state);
+	switch (ret) {
+	case 0:
+		dprintk("%s: bind_conn_to_session was successful for server %s!\n",
+			__func__, clp->cl_hostname);
 		break;
 	case -NFS4ERR_DELAY:
-	case -ETIMEDOUT:
-	case -EAGAIN:
 		ssleep(1);
+		set_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state);
 		break;
-
-	case -EKEYEXPIRED:
-		nfs4_warn_keyexpired(clp->cl_hostname);
-	case -NFS4ERR_NOT_SAME: /* FixMe: implement recovery
-				 * in nfs4_exchange_id */
 	default:
-		return;
+		return nfs4_recovery_handle_error(clp, ret);
 	}
-	set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
+	return 0;
 }
+#else /* CONFIG_NFS_V4_1 */
+static int nfs4_reset_session(struct nfs_client *clp) { return 0; }
+static int nfs4_end_drain_session(struct nfs_client *clp) { return 0; }
+static int nfs4_recall_slot(struct nfs_client *clp) { return 0; }
+
+static int nfs4_bind_conn_to_session(struct nfs_client *clp)
+{
+	return 0;
+}
+#endif /* CONFIG_NFS_V4_1 */
 
 static void nfs4_state_manager(struct nfs_client *clp)
 {
@@ -1760,19 +1858,21 @@ static void nfs4_state_manager(struct nfs_client *clp)
 
 	/* Ensure exclusive access to NFSv4 state */
 	do {
+		if (test_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state)) {
+			status = nfs4_reclaim_lease(clp);
+			if (status < 0)
+				goto out_error;
+			clear_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state);
+			set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
+		}
+
 		if (test_and_clear_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state)) {
 			/* We're going to have to re-establish a clientid */
 			status = nfs4_reclaim_lease(clp);
-			if (status) {
-				nfs4_set_lease_expired(clp, status);
-				if (test_bit(NFS4CLNT_LEASE_EXPIRED,
-							&clp->cl_state))
-					continue;
-				if (clp->cl_cons_state ==
-							NFS_CS_SESSION_INITING)
-					nfs_mark_client_ready(clp, status);
+			if (status < 0)
 				goto out_error;
-			}
+			if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state))
+				continue;
 			clear_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state);
 
 			if (test_and_clear_bit(NFS4CLNT_SERVER_SCOPE_MISMATCH,
@@ -1803,6 +1903,15 @@ static void nfs4_state_manager(struct nfs_client *clp)
 				goto out_error;
 		}
 
+		/* Send BIND_CONN_TO_SESSION */
+		if (test_and_clear_bit(NFS4CLNT_BIND_CONN_TO_SESSION,
+				&clp->cl_state) && nfs4_has_session(clp)) {
+			status = nfs4_bind_conn_to_session(clp);
+			if (status < 0)
+				goto out_error;
+			continue;
+		}
+
 		/* First recover reboot state... */
 		if (test_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state)) {
 			status = nfs4_do_reclaim(clp,
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index c54aae364bee..ee4a74db95d0 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -53,9 +53,11 @@
 #include <linux/nfs4.h>
 #include <linux/nfs_fs.h>
 #include <linux/nfs_idmap.h>
+
 #include "nfs4_fs.h"
 #include "internal.h"
 #include "pnfs.h"
+#include "netns.h"
 
 #define NFSDBG_FACILITY		NFSDBG_XDR
 
@@ -99,9 +101,12 @@ static int nfs4_stat_to_errno(int);
 #define nfs4_path_maxsz		(1 + ((3 + NFS4_MAXPATHLEN) >> 2))
 #define nfs4_owner_maxsz	(1 + XDR_QUADLEN(IDMAP_NAMESZ))
 #define nfs4_group_maxsz	(1 + XDR_QUADLEN(IDMAP_NAMESZ))
+/* We support only one layout type per file system */
+#define decode_mdsthreshold_maxsz (1 + 1 + nfs4_fattr_bitmap_maxsz + 1 + 8)
 /* This is based on getfattr, which uses the most attributes: */
 #define nfs4_fattr_value_maxsz	(1 + (1 + 2 + 2 + 4 + 2 + 1 + 1 + 2 + 2 + \
-				3 + 3 + 3 + nfs4_owner_maxsz + nfs4_group_maxsz))
+				3 + 3 + 3 + nfs4_owner_maxsz + \
+				nfs4_group_maxsz + decode_mdsthreshold_maxsz))
 #define nfs4_fattr_maxsz	(nfs4_fattr_bitmap_maxsz + \
 				nfs4_fattr_value_maxsz)
 #define decode_getattr_maxsz    (op_decode_hdr_maxsz + nfs4_fattr_maxsz)
@@ -321,8 +326,20 @@ static int nfs4_stat_to_errno(int);
 				     1 /* csr_flags */ + \
 				     decode_channel_attrs_maxsz + \
 				     decode_channel_attrs_maxsz)
+#define encode_bind_conn_to_session_maxsz  (op_encode_hdr_maxsz + \
+				     /* bctsa_sessid */ \
+				     XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + \
+				     1 /* bctsa_dir */ + \
+				     1 /* bctsa_use_conn_in_rdma_mode */)
+#define decode_bind_conn_to_session_maxsz  (op_decode_hdr_maxsz +	\
+				     /* bctsr_sessid */ \
+				     XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + \
+				     1 /* bctsr_dir */ + \
+				     1 /* bctsr_use_conn_in_rdma_mode */)
 #define encode_destroy_session_maxsz    (op_encode_hdr_maxsz + 4)
 #define decode_destroy_session_maxsz    (op_decode_hdr_maxsz)
+#define encode_destroy_clientid_maxsz   (op_encode_hdr_maxsz + 2)
+#define decode_destroy_clientid_maxsz   (op_decode_hdr_maxsz)
 #define encode_sequence_maxsz	(op_encode_hdr_maxsz + \
 				XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + 4)
 #define decode_sequence_maxsz	(op_decode_hdr_maxsz + \
@@ -421,30 +438,22 @@ static int nfs4_stat_to_errno(int);
 #define NFS4_enc_commit_sz	(compound_encode_hdr_maxsz + \
 				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
-				encode_commit_maxsz + \
-				encode_getattr_maxsz)
+				encode_commit_maxsz)
 #define NFS4_dec_commit_sz	(compound_decode_hdr_maxsz + \
 				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
-				decode_commit_maxsz + \
-				decode_getattr_maxsz)
+				decode_commit_maxsz)
 #define NFS4_enc_open_sz        (compound_encode_hdr_maxsz + \
 				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
-				encode_savefh_maxsz + \
 				encode_open_maxsz + \
 				encode_getfh_maxsz + \
-				encode_getattr_maxsz + \
-				encode_restorefh_maxsz + \
 				encode_getattr_maxsz)
 #define NFS4_dec_open_sz        (compound_decode_hdr_maxsz + \
 				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
-				decode_savefh_maxsz + \
 				decode_open_maxsz + \
 				decode_getfh_maxsz + \
-				decode_getattr_maxsz + \
-				decode_restorefh_maxsz + \
 				decode_getattr_maxsz)
 #define NFS4_enc_open_confirm_sz \
 				(compound_encode_hdr_maxsz + \
@@ -595,47 +604,37 @@ static int nfs4_stat_to_errno(int);
 #define NFS4_enc_remove_sz	(compound_encode_hdr_maxsz + \
 				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
-				encode_remove_maxsz + \
-				encode_getattr_maxsz)
+				encode_remove_maxsz)
 #define NFS4_dec_remove_sz	(compound_decode_hdr_maxsz + \
 				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
-				decode_remove_maxsz + \
-				decode_getattr_maxsz)
+				decode_remove_maxsz)
 #define NFS4_enc_rename_sz	(compound_encode_hdr_maxsz + \
 				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
 				encode_savefh_maxsz + \
 				encode_putfh_maxsz + \
-				encode_rename_maxsz + \
-				encode_getattr_maxsz + \
-				encode_restorefh_maxsz + \
-				encode_getattr_maxsz)
+				encode_rename_maxsz)
 #define NFS4_dec_rename_sz	(compound_decode_hdr_maxsz + \
 				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
 				decode_savefh_maxsz + \
 				decode_putfh_maxsz + \
-				decode_rename_maxsz + \
-				decode_getattr_maxsz + \
-				decode_restorefh_maxsz + \
-				decode_getattr_maxsz)
+				decode_rename_maxsz)
 #define NFS4_enc_link_sz	(compound_encode_hdr_maxsz + \
 				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
 				encode_savefh_maxsz + \
 				encode_putfh_maxsz + \
 				encode_link_maxsz + \
-				decode_getattr_maxsz + \
 				encode_restorefh_maxsz + \
-				decode_getattr_maxsz)
+				encode_getattr_maxsz)
 #define NFS4_dec_link_sz	(compound_decode_hdr_maxsz + \
 				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
 				decode_savefh_maxsz + \
 				decode_putfh_maxsz + \
 				decode_link_maxsz + \
-				decode_getattr_maxsz + \
 				decode_restorefh_maxsz + \
 				decode_getattr_maxsz)
 #define NFS4_enc_symlink_sz	(compound_encode_hdr_maxsz + \
@@ -653,20 +652,14 @@ static int nfs4_stat_to_errno(int);
 #define NFS4_enc_create_sz	(compound_encode_hdr_maxsz + \
 				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
-				encode_savefh_maxsz + \
 				encode_create_maxsz + \
 				encode_getfh_maxsz + \
-				encode_getattr_maxsz + \
-				encode_restorefh_maxsz + \
 				encode_getattr_maxsz)
 #define NFS4_dec_create_sz	(compound_decode_hdr_maxsz + \
 				decode_sequence_maxsz + \
 				decode_putfh_maxsz + \
-				decode_savefh_maxsz + \
 				decode_create_maxsz + \
 				decode_getfh_maxsz + \
-				decode_getattr_maxsz + \
-				decode_restorefh_maxsz + \
 				decode_getattr_maxsz)
 #define NFS4_enc_pathconf_sz	(compound_encode_hdr_maxsz + \
 				encode_sequence_maxsz + \
@@ -738,6 +731,12 @@ static int nfs4_stat_to_errno(int);
 				decode_putfh_maxsz + \
 				decode_secinfo_maxsz)
 #if defined(CONFIG_NFS_V4_1)
+#define NFS4_enc_bind_conn_to_session_sz \
+				(compound_encode_hdr_maxsz + \
+				 encode_bind_conn_to_session_maxsz)
+#define NFS4_dec_bind_conn_to_session_sz \
+				(compound_decode_hdr_maxsz + \
+				 decode_bind_conn_to_session_maxsz)
 #define NFS4_enc_exchange_id_sz \
 				(compound_encode_hdr_maxsz + \
 				 encode_exchange_id_maxsz)
@@ -754,6 +753,10 @@ static int nfs4_stat_to_errno(int);
 					 encode_destroy_session_maxsz)
 #define NFS4_dec_destroy_session_sz	(compound_decode_hdr_maxsz + \
 					 decode_destroy_session_maxsz)
+#define NFS4_enc_destroy_clientid_sz	(compound_encode_hdr_maxsz + \
+					 encode_destroy_clientid_maxsz)
+#define NFS4_dec_destroy_clientid_sz	(compound_decode_hdr_maxsz + \
+					 decode_destroy_clientid_maxsz)
 #define NFS4_enc_sequence_sz \
 				(compound_decode_hdr_maxsz + \
 				 encode_sequence_maxsz)
@@ -1103,7 +1106,7 @@ static void encode_close(struct xdr_stream *xdr, const struct nfs_closeargs *arg
 	encode_nfs4_stateid(xdr, arg->stateid);
 }
 
-static void encode_commit(struct xdr_stream *xdr, const struct nfs_writeargs *args, struct compound_hdr *hdr)
+static void encode_commit(struct xdr_stream *xdr, const struct nfs_commitargs *args, struct compound_hdr *hdr)
 {
 	__be32 *p;
 
@@ -1194,6 +1197,16 @@ static void encode_getfattr(struct xdr_stream *xdr, const u32* bitmask, struct c
 			   bitmask[1] & nfs4_fattr_bitmap[1], hdr);
 }
 
+static void encode_getfattr_open(struct xdr_stream *xdr, const u32 *bitmask,
+				 struct compound_hdr *hdr)
+{
+	encode_getattr_three(xdr,
+			     bitmask[0] & nfs4_fattr_bitmap[0],
+			     bitmask[1] & nfs4_fattr_bitmap[1],
+			     bitmask[2] & FATTR4_WORD2_MDSTHRESHOLD,
+			     hdr);
+}
+
 static void encode_fsinfo(struct xdr_stream *xdr, const u32* bitmask, struct compound_hdr *hdr)
 {
 	encode_getattr_three(xdr,
@@ -1678,6 +1691,20 @@ static void encode_secinfo(struct xdr_stream *xdr, const struct qstr *name, stru
 
 #if defined(CONFIG_NFS_V4_1)
 /* NFSv4.1 operations */
+static void encode_bind_conn_to_session(struct xdr_stream *xdr,
+				   struct nfs4_session *session,
+				   struct compound_hdr *hdr)
+{
+	__be32 *p;
+
+	encode_op_hdr(xdr, OP_BIND_CONN_TO_SESSION,
+		decode_bind_conn_to_session_maxsz, hdr);
+	encode_opaque_fixed(xdr, session->sess_id.data, NFS4_MAX_SESSIONID_LEN);
+	p = xdr_reserve_space(xdr, 8);
+	*p++ = cpu_to_be32(NFS4_CDFC4_BACK_OR_BOTH);
+	*p = 0;	/* use_conn_in_rdma_mode = False */
+}
+
 static void encode_exchange_id(struct xdr_stream *xdr,
 			       struct nfs41_exchange_id_args *args,
 			       struct compound_hdr *hdr)
@@ -1726,6 +1753,7 @@ static void encode_create_session(struct xdr_stream *xdr,
 	char machine_name[NFS4_MAX_MACHINE_NAME_LEN];
 	uint32_t len;
 	struct nfs_client *clp = args->client;
+	struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id);
 	u32 max_resp_sz_cached;
 
 	/*
@@ -1767,7 +1795,7 @@ static void encode_create_session(struct xdr_stream *xdr,
 	*p++ = cpu_to_be32(RPC_AUTH_UNIX);			/* auth_sys */
 
 	/* authsys_parms rfc1831 */
-	*p++ = cpu_to_be32((u32)clp->cl_boot_time.tv_nsec);	/* stamp */
+	*p++ = (__be32)nn->boot_time.tv_nsec;		/* stamp */
 	p = xdr_encode_opaque(p, machine_name, len);
 	*p++ = cpu_to_be32(0);				/* UID */
 	*p++ = cpu_to_be32(0);				/* GID */
@@ -1782,6 +1810,14 @@ static void encode_destroy_session(struct xdr_stream *xdr,
 	encode_opaque_fixed(xdr, session->sess_id.data, NFS4_MAX_SESSIONID_LEN);
 }
 
+static void encode_destroy_clientid(struct xdr_stream *xdr,
+				   uint64_t clientid,
+				   struct compound_hdr *hdr)
+{
+	encode_op_hdr(xdr, OP_DESTROY_CLIENTID, decode_destroy_clientid_maxsz, hdr);
+	encode_uint64(xdr, clientid);
+}
+
 static void encode_reclaim_complete(struct xdr_stream *xdr,
 				    struct nfs41_reclaim_complete_args *args,
 				    struct compound_hdr *hdr)
@@ -2064,7 +2100,6 @@ static void nfs4_xdr_enc_remove(struct rpc_rqst *req, struct xdr_stream *xdr,
 	encode_sequence(xdr, &args->seq_args, &hdr);
 	encode_putfh(xdr, args->fh, &hdr);
 	encode_remove(xdr, &args->name, &hdr);
-	encode_getfattr(xdr, args->bitmask, &hdr);
 	encode_nops(&hdr);
 }
 
@@ -2084,9 +2119,6 @@ static void nfs4_xdr_enc_rename(struct rpc_rqst *req, struct xdr_stream *xdr,
 	encode_savefh(xdr, &hdr);
 	encode_putfh(xdr, args->new_dir, &hdr);
 	encode_rename(xdr, args->old_name, args->new_name, &hdr);
-	encode_getfattr(xdr, args->bitmask, &hdr);
-	encode_restorefh(xdr, &hdr);
-	encode_getfattr(xdr, args->bitmask, &hdr);
 	encode_nops(&hdr);
 }
 
@@ -2106,7 +2138,6 @@ static void nfs4_xdr_enc_link(struct rpc_rqst *req, struct xdr_stream *xdr,
 	encode_savefh(xdr, &hdr);
 	encode_putfh(xdr, args->dir_fh, &hdr);
 	encode_link(xdr, args->name, &hdr);
-	encode_getfattr(xdr, args->bitmask, &hdr);
 	encode_restorefh(xdr, &hdr);
 	encode_getfattr(xdr, args->bitmask, &hdr);
 	encode_nops(&hdr);
@@ -2125,12 +2156,9 @@ static void nfs4_xdr_enc_create(struct rpc_rqst *req, struct xdr_stream *xdr,
 	encode_compound_hdr(xdr, req, &hdr);
 	encode_sequence(xdr, &args->seq_args, &hdr);
 	encode_putfh(xdr, args->dir_fh, &hdr);
-	encode_savefh(xdr, &hdr);
 	encode_create(xdr, args, &hdr);
 	encode_getfh(xdr, &hdr);
 	encode_getfattr(xdr, args->bitmask, &hdr);
-	encode_restorefh(xdr, &hdr);
-	encode_getfattr(xdr, args->bitmask, &hdr);
 	encode_nops(&hdr);
 }
 
@@ -2191,12 +2219,9 @@ static void nfs4_xdr_enc_open(struct rpc_rqst *req, struct xdr_stream *xdr,
 	encode_compound_hdr(xdr, req, &hdr);
 	encode_sequence(xdr, &args->seq_args, &hdr);
 	encode_putfh(xdr, args->fh, &hdr);
-	encode_savefh(xdr, &hdr);
 	encode_open(xdr, args, &hdr);
 	encode_getfh(xdr, &hdr);
-	encode_getfattr(xdr, args->bitmask, &hdr);
-	encode_restorefh(xdr, &hdr);
-	encode_getfattr(xdr, args->dir_bitmask, &hdr);
+	encode_getfattr_open(xdr, args->bitmask, &hdr);
 	encode_nops(&hdr);
 }
 
@@ -2448,7 +2473,7 @@ static void nfs4_xdr_enc_write(struct rpc_rqst *req, struct xdr_stream *xdr,
  *  a COMMIT request
  */
 static void nfs4_xdr_enc_commit(struct rpc_rqst *req, struct xdr_stream *xdr,
-				struct nfs_writeargs *args)
+				struct nfs_commitargs *args)
 {
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
@@ -2458,8 +2483,6 @@ static void nfs4_xdr_enc_commit(struct rpc_rqst *req, struct xdr_stream *xdr,
 	encode_sequence(xdr, &args->seq_args, &hdr);
 	encode_putfh(xdr, args->fh, &hdr);
 	encode_commit(xdr, args, &hdr);
-	if (args->bitmask)
-		encode_getfattr(xdr, args->bitmask, &hdr);
 	encode_nops(&hdr);
 }
 
@@ -2602,8 +2625,8 @@ static void nfs4_xdr_enc_delegreturn(struct rpc_rqst *req,
 	encode_compound_hdr(xdr, req, &hdr);
 	encode_sequence(xdr, &args->seq_args, &hdr);
 	encode_putfh(xdr, args->fhandle, &hdr);
-	encode_delegreturn(xdr, args->stateid, &hdr);
 	encode_getfattr(xdr, args->bitmask, &hdr);
+	encode_delegreturn(xdr, args->stateid, &hdr);
 	encode_nops(&hdr);
 }
 
@@ -2651,6 +2674,22 @@ static void nfs4_xdr_enc_secinfo(struct rpc_rqst *req,
 
 #if defined(CONFIG_NFS_V4_1)
 /*
+ * BIND_CONN_TO_SESSION request
+ */
+static void nfs4_xdr_enc_bind_conn_to_session(struct rpc_rqst *req,
+				struct xdr_stream *xdr,
+				struct nfs_client *clp)
+{
+	struct compound_hdr hdr = {
+		.minorversion = clp->cl_mvops->minor_version,
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_bind_conn_to_session(xdr, clp->cl_session, &hdr);
+	encode_nops(&hdr);
+}
+
+/*
  * EXCHANGE_ID request
  */
 static void nfs4_xdr_enc_exchange_id(struct rpc_rqst *req,
@@ -2699,6 +2738,22 @@ static void nfs4_xdr_enc_destroy_session(struct rpc_rqst *req,
 }
 
 /*
+ * a DESTROY_CLIENTID request
+ */
+static void nfs4_xdr_enc_destroy_clientid(struct rpc_rqst *req,
+					 struct xdr_stream *xdr,
+					 struct nfs_client *clp)
+{
+	struct compound_hdr hdr = {
+		.minorversion = clp->cl_mvops->minor_version,
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_destroy_clientid(xdr, clp->cl_clientid, &hdr);
+	encode_nops(&hdr);
+}
+
+/*
  * a SEQUENCE request
  */
 static void nfs4_xdr_enc_sequence(struct rpc_rqst *req, struct xdr_stream *xdr,
@@ -4102,7 +4157,7 @@ static int decode_verifier(struct xdr_stream *xdr, void *verifier)
 	return decode_opaque_fixed(xdr, verifier, NFS4_VERIFIER_SIZE);
 }
 
-static int decode_commit(struct xdr_stream *xdr, struct nfs_writeres *res)
+static int decode_commit(struct xdr_stream *xdr, struct nfs_commitres *res)
 {
 	int status;
 
@@ -4220,6 +4275,110 @@ xdr_error:
 	return status;
 }
 
+static int decode_threshold_hint(struct xdr_stream *xdr,
+				  uint32_t *bitmap,
+				  uint64_t *res,
+				  uint32_t hint_bit)
+{
+	__be32 *p;
+
+	*res = 0;
+	if (likely(bitmap[0] & hint_bit)) {
+		p = xdr_inline_decode(xdr, 8);
+		if (unlikely(!p))
+			goto out_overflow;
+		xdr_decode_hyper(p, res);
+	}
+	return 0;
+out_overflow:
+	print_overflow_msg(__func__, xdr);
+	return -EIO;
+}
+
+static int decode_first_threshold_item4(struct xdr_stream *xdr,
+					struct nfs4_threshold *res)
+{
+	__be32 *p, *savep;
+	uint32_t bitmap[3] = {0,}, attrlen;
+	int status;
+
+	/* layout type */
+	p = xdr_inline_decode(xdr, 4);
+	if (unlikely(!p)) {
+		print_overflow_msg(__func__, xdr);
+		return -EIO;
+	}
+	res->l_type = be32_to_cpup(p);
+
+	/* thi_hintset bitmap */
+	status = decode_attr_bitmap(xdr, bitmap);
+	if (status < 0)
+		goto xdr_error;
+
+	/* thi_hintlist length */
+	status = decode_attr_length(xdr, &attrlen, &savep);
+	if (status < 0)
+		goto xdr_error;
+	/* thi_hintlist */
+	status = decode_threshold_hint(xdr, bitmap, &res->rd_sz, THRESHOLD_RD);
+	if (status < 0)
+		goto xdr_error;
+	status = decode_threshold_hint(xdr, bitmap, &res->wr_sz, THRESHOLD_WR);
+	if (status < 0)
+		goto xdr_error;
+	status = decode_threshold_hint(xdr, bitmap, &res->rd_io_sz,
+				       THRESHOLD_RD_IO);
+	if (status < 0)
+		goto xdr_error;
+	status = decode_threshold_hint(xdr, bitmap, &res->wr_io_sz,
+				       THRESHOLD_WR_IO);
+	if (status < 0)
+		goto xdr_error;
+
+	status = verify_attr_len(xdr, savep, attrlen);
+	res->bm = bitmap[0];
+
+	dprintk("%s bm=0x%x rd_sz=%llu wr_sz=%llu rd_io=%llu wr_io=%llu\n",
+		 __func__, res->bm, res->rd_sz, res->wr_sz, res->rd_io_sz,
+		res->wr_io_sz);
+xdr_error:
+	dprintk("%s ret=%d!\n", __func__, status);
+	return status;
+}
+
+/*
+ * Thresholds on pNFS direct I/O vrs MDS I/O
+ */
+static int decode_attr_mdsthreshold(struct xdr_stream *xdr,
+				    uint32_t *bitmap,
+				    struct nfs4_threshold *res)
+{
+	__be32 *p;
+	int status = 0;
+	uint32_t num;
+
+	if (unlikely(bitmap[2] & (FATTR4_WORD2_MDSTHRESHOLD - 1U)))
+		return -EIO;
+	if (likely(bitmap[2] & FATTR4_WORD2_MDSTHRESHOLD)) {
+		p = xdr_inline_decode(xdr, 4);
+		if (unlikely(!p))
+			goto out_overflow;
+		num = be32_to_cpup(p);
+		if (num == 0)
+			return 0;
+		if (num > 1)
+			printk(KERN_INFO "%s: Warning: Multiple pNFS layout "
+				"drivers per filesystem not supported\n",
+				__func__);
+
+		status = decode_first_threshold_item4(xdr, res);
+	}
+	return status;
+out_overflow:
+	print_overflow_msg(__func__, xdr);
+	return -EIO;
+}
+
 static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap,
 		struct nfs_fattr *fattr, struct nfs_fh *fh,
 		struct nfs4_fs_locations *fs_loc,
@@ -4326,6 +4485,10 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap,
 		goto xdr_error;
 	fattr->valid |= status;
 
+	status = decode_attr_mdsthreshold(xdr, bitmap, fattr->mdsthreshold);
+	if (status < 0)
+		goto xdr_error;
+
 xdr_error:
 	dprintk("%s: xdr returned %d\n", __func__, -status);
 	return status;
@@ -5156,7 +5319,6 @@ static int decode_exchange_id(struct xdr_stream *xdr,
 	uint32_t dummy;
 	char *dummy_str;
 	int status;
-	struct nfs_client *clp = res->client;
 	uint32_t impl_id_count;
 
 	status = decode_op_hdr(xdr, OP_EXCHANGE_ID);
@@ -5166,36 +5328,39 @@ static int decode_exchange_id(struct xdr_stream *xdr,
 	p = xdr_inline_decode(xdr, 8);
 	if (unlikely(!p))
 		goto out_overflow;
-	xdr_decode_hyper(p, &clp->cl_clientid);
+	xdr_decode_hyper(p, &res->clientid);
 	p = xdr_inline_decode(xdr, 12);
 	if (unlikely(!p))
 		goto out_overflow;
-	clp->cl_seqid = be32_to_cpup(p++);
-	clp->cl_exchange_flags = be32_to_cpup(p++);
+	res->seqid = be32_to_cpup(p++);
+	res->flags = be32_to_cpup(p++);
 
 	/* We ask for SP4_NONE */
 	dummy = be32_to_cpup(p);
 	if (dummy != SP4_NONE)
 		return -EIO;
 
-	/* Throw away minor_id */
+	/* server_owner4.so_minor_id */
 	p = xdr_inline_decode(xdr, 8);
 	if (unlikely(!p))
 		goto out_overflow;
+	p = xdr_decode_hyper(p, &res->server_owner->minor_id);
 
-	/* Throw away Major id */
+	/* server_owner4.so_major_id */
 	status = decode_opaque_inline(xdr, &dummy, &dummy_str);
 	if (unlikely(status))
 		return status;
+	if (unlikely(dummy > NFS4_OPAQUE_LIMIT))
+		return -EIO;
+	memcpy(res->server_owner->major_id, dummy_str, dummy);
+	res->server_owner->major_id_sz = dummy;
 
-	/* Save server_scope */
+	/* server_scope4 */
 	status = decode_opaque_inline(xdr, &dummy, &dummy_str);
 	if (unlikely(status))
 		return status;
-
 	if (unlikely(dummy > NFS4_OPAQUE_LIMIT))
 		return -EIO;
-
 	memcpy(res->server_scope->server_scope, dummy_str, dummy);
 	res->server_scope->server_scope_sz = dummy;
 
@@ -5276,6 +5441,37 @@ static int decode_sessionid(struct xdr_stream *xdr, struct nfs4_sessionid *sid)
 	return decode_opaque_fixed(xdr, sid->data, NFS4_MAX_SESSIONID_LEN);
 }
 
+static int decode_bind_conn_to_session(struct xdr_stream *xdr,
+				struct nfs41_bind_conn_to_session_res *res)
+{
+	__be32 *p;
+	int status;
+
+	status = decode_op_hdr(xdr, OP_BIND_CONN_TO_SESSION);
+	if (!status)
+		status = decode_sessionid(xdr, &res->session->sess_id);
+	if (unlikely(status))
+		return status;
+
+	/* dir flags, rdma mode bool */
+	p = xdr_inline_decode(xdr, 8);
+	if (unlikely(!p))
+		goto out_overflow;
+
+	res->dir = be32_to_cpup(p++);
+	if (res->dir == 0 || res->dir > NFS4_CDFS4_BOTH)
+		return -EIO;
+	if (be32_to_cpup(p) == 0)
+		res->use_conn_in_rdma_mode = false;
+	else
+		res->use_conn_in_rdma_mode = true;
+
+	return 0;
+out_overflow:
+	print_overflow_msg(__func__, xdr);
+	return -EIO;
+}
+
 static int decode_create_session(struct xdr_stream *xdr,
 				 struct nfs41_create_session_res *res)
 {
@@ -5312,6 +5508,11 @@ static int decode_destroy_session(struct xdr_stream *xdr, void *dummy)
 	return decode_op_hdr(xdr, OP_DESTROY_SESSION);
 }
 
+static int decode_destroy_clientid(struct xdr_stream *xdr, void *dummy)
+{
+	return decode_op_hdr(xdr, OP_DESTROY_CLIENTID);
+}
+
 static int decode_reclaim_complete(struct xdr_stream *xdr, void *dummy)
 {
 	return decode_op_hdr(xdr, OP_RECLAIM_COMPLETE);
@@ -5800,9 +6001,6 @@ static int nfs4_xdr_dec_remove(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	if (status)
 		goto out;
 	status = decode_remove(xdr, &res->cinfo);
-	if (status)
-		goto out;
-	decode_getfattr(xdr, res->dir_attr, res->server);
 out:
 	return status;
 }
@@ -5832,15 +6030,6 @@ static int nfs4_xdr_dec_rename(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	if (status)
 		goto out;
 	status = decode_rename(xdr, &res->old_cinfo, &res->new_cinfo);
-	if (status)
-		goto out;
-	/* Current FH is target directory */
-	if (decode_getfattr(xdr, res->new_fattr, res->server))
-		goto out;
-	status = decode_restorefh(xdr);
-	if (status)
-		goto out;
-	decode_getfattr(xdr, res->old_fattr, res->server);
 out:
 	return status;
 }
@@ -5876,8 +6065,6 @@ static int nfs4_xdr_dec_link(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	 * Note order: OP_LINK leaves the directory as the current
 	 *             filehandle.
 	 */
-	if (decode_getfattr(xdr, res->dir_attr, res->server))
-		goto out;
 	status = decode_restorefh(xdr);
 	if (status)
 		goto out;
@@ -5904,21 +6091,13 @@ static int nfs4_xdr_dec_create(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	status = decode_putfh(xdr);
 	if (status)
 		goto out;
-	status = decode_savefh(xdr);
-	if (status)
-		goto out;
 	status = decode_create(xdr, &res->dir_cinfo);
 	if (status)
 		goto out;
 	status = decode_getfh(xdr, res->fh);
 	if (status)
 		goto out;
-	if (decode_getfattr(xdr, res->fattr, res->server))
-		goto out;
-	status = decode_restorefh(xdr);
-	if (status)
-		goto out;
-	decode_getfattr(xdr, res->dir_fattr, res->server);
+	decode_getfattr(xdr, res->fattr, res->server);
 out:
 	return status;
 }
@@ -6075,19 +6254,12 @@ static int nfs4_xdr_dec_open(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	status = decode_putfh(xdr);
 	if (status)
 		goto out;
-	status = decode_savefh(xdr);
-	if (status)
-		goto out;
 	status = decode_open(xdr, res);
 	if (status)
 		goto out;
 	if (decode_getfh(xdr, &res->fh) != 0)
 		goto out;
-	if (decode_getfattr(xdr, res->f_attr, res->server) != 0)
-		goto out;
-	if (decode_restorefh(xdr) != 0)
-		goto out;
-	decode_getfattr(xdr, res->dir_attr, res->server);
+	decode_getfattr(xdr, res->f_attr, res->server);
 out:
 	return status;
 }
@@ -6353,7 +6525,7 @@ out:
  * Decode COMMIT response
  */
 static int nfs4_xdr_dec_commit(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
-			       struct nfs_writeres *res)
+			       struct nfs_commitres *res)
 {
 	struct compound_hdr hdr;
 	int status;
@@ -6368,10 +6540,6 @@ static int nfs4_xdr_dec_commit(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	if (status)
 		goto out;
 	status = decode_commit(xdr, res);
-	if (status)
-		goto out;
-	if (res->fattr)
-		decode_getfattr(xdr, res->fattr, res->server);
 out:
 	return status;
 }
@@ -6527,10 +6695,10 @@ static int nfs4_xdr_dec_delegreturn(struct rpc_rqst *rqstp,
 	status = decode_putfh(xdr);
 	if (status != 0)
 		goto out;
-	status = decode_delegreturn(xdr);
+	status = decode_getfattr(xdr, res->fattr, res->server);
 	if (status != 0)
 		goto out;
-	decode_getfattr(xdr, res->fattr, res->server);
+	status = decode_delegreturn(xdr);
 out:
 	return status;
 }
@@ -6591,6 +6759,22 @@ out:
 
 #if defined(CONFIG_NFS_V4_1)
 /*
+ * Decode BIND_CONN_TO_SESSION response
+ */
+static int nfs4_xdr_dec_bind_conn_to_session(struct rpc_rqst *rqstp,
+					struct xdr_stream *xdr,
+					void *res)
+{
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (!status)
+		status = decode_bind_conn_to_session(xdr, res);
+	return status;
+}
+
+/*
  * Decode EXCHANGE_ID response
  */
 static int nfs4_xdr_dec_exchange_id(struct rpc_rqst *rqstp,
@@ -6639,6 +6823,22 @@ static int nfs4_xdr_dec_destroy_session(struct rpc_rqst *rqstp,
 }
 
 /*
+ * Decode DESTROY_CLIENTID response
+ */
+static int nfs4_xdr_dec_destroy_clientid(struct rpc_rqst *rqstp,
+					struct xdr_stream *xdr,
+					void *res)
+{
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (!status)
+		status = decode_destroy_clientid(xdr, res);
+	return status;
+}
+
+/*
  * Decode SEQUENCE response
  */
 static int nfs4_xdr_dec_sequence(struct rpc_rqst *rqstp,
@@ -7085,6 +7285,9 @@ struct rpc_procinfo	nfs4_procedures[] = {
 	PROC(TEST_STATEID,	enc_test_stateid,	dec_test_stateid),
 	PROC(FREE_STATEID,	enc_free_stateid,	dec_free_stateid),
 	PROC(GETDEVICELIST,	enc_getdevicelist,	dec_getdevicelist),
+	PROC(BIND_CONN_TO_SESSION,
+			enc_bind_conn_to_session, dec_bind_conn_to_session),
+	PROC(DESTROY_CLIENTID,	enc_destroy_clientid,	dec_destroy_clientid),
 #endif /* CONFIG_NFS_V4_1 */
 };
 
diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c
index 4bff4a3dab46..b47277baebab 100644
--- a/fs/nfs/objlayout/objio_osd.c
+++ b/fs/nfs/objlayout/objio_osd.c
@@ -211,7 +211,7 @@ static void copy_single_comp(struct ore_components *oc, unsigned c,
 	memcpy(ocomp->cred, src_comp->oc_cap.cred, sizeof(ocomp->cred));
 }
 
-int __alloc_objio_seg(unsigned numdevs, gfp_t gfp_flags,
+static int __alloc_objio_seg(unsigned numdevs, gfp_t gfp_flags,
 		       struct objio_segment **pseg)
 {
 /*	This is the in memory structure of the objio_segment
@@ -440,11 +440,12 @@ static void _read_done(struct ore_io_state *ios, void *private)
 
 int objio_read_pagelist(struct nfs_read_data *rdata)
 {
+	struct nfs_pgio_header *hdr = rdata->header;
 	struct objio_state *objios;
 	int ret;
 
-	ret = objio_alloc_io_state(NFS_I(rdata->inode)->layout, true,
-			rdata->lseg, rdata->args.pages, rdata->args.pgbase,
+	ret = objio_alloc_io_state(NFS_I(hdr->inode)->layout, true,
+			hdr->lseg, rdata->args.pages, rdata->args.pgbase,
 			rdata->args.offset, rdata->args.count, rdata,
 			GFP_KERNEL, &objios);
 	if (unlikely(ret))
@@ -483,12 +484,12 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate)
 {
 	struct objio_state *objios = priv;
 	struct nfs_write_data *wdata = objios->oir.rpcdata;
+	struct address_space *mapping = wdata->header->inode->i_mapping;
 	pgoff_t index = offset / PAGE_SIZE;
-	struct page *page = find_get_page(wdata->inode->i_mapping, index);
+	struct page *page = find_get_page(mapping, index);
 
 	if (!page) {
-		page = find_or_create_page(wdata->inode->i_mapping,
-						index, GFP_NOFS);
+		page = find_or_create_page(mapping, index, GFP_NOFS);
 		if (unlikely(!page)) {
 			dprintk("%s: grab_cache_page Failed index=0x%lx\n",
 				__func__, index);
@@ -518,11 +519,12 @@ static const struct _ore_r4w_op _r4w_op = {
 
 int objio_write_pagelist(struct nfs_write_data *wdata, int how)
 {
+	struct nfs_pgio_header *hdr = wdata->header;
 	struct objio_state *objios;
 	int ret;
 
-	ret = objio_alloc_io_state(NFS_I(wdata->inode)->layout, false,
-			wdata->lseg, wdata->args.pages, wdata->args.pgbase,
+	ret = objio_alloc_io_state(NFS_I(hdr->inode)->layout, false,
+			hdr->lseg, wdata->args.pages, wdata->args.pgbase,
 			wdata->args.offset, wdata->args.count, wdata, GFP_NOFS,
 			&objios);
 	if (unlikely(ret))
diff --git a/fs/nfs/objlayout/objlayout.c b/fs/nfs/objlayout/objlayout.c
index 595c5fc21a19..874613545301 100644
--- a/fs/nfs/objlayout/objlayout.c
+++ b/fs/nfs/objlayout/objlayout.c
@@ -258,7 +258,7 @@ objlayout_read_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
 	if (status >= 0)
 		rdata->res.count = status;
 	else
-		rdata->pnfs_error = status;
+		rdata->header->pnfs_error = status;
 	objlayout_iodone(oir);
 	/* must not use oir after this point */
 
@@ -279,12 +279,14 @@ objlayout_read_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
 enum pnfs_try_status
 objlayout_read_pagelist(struct nfs_read_data *rdata)
 {
+	struct nfs_pgio_header *hdr = rdata->header;
+	struct inode *inode = hdr->inode;
 	loff_t offset = rdata->args.offset;
 	size_t count = rdata->args.count;
 	int err;
 	loff_t eof;
 
-	eof = i_size_read(rdata->inode);
+	eof = i_size_read(inode);
 	if (unlikely(offset + count > eof)) {
 		if (offset >= eof) {
 			err = 0;
@@ -297,17 +299,17 @@ objlayout_read_pagelist(struct nfs_read_data *rdata)
 	}
 
 	rdata->res.eof = (offset + count) >= eof;
-	_fix_verify_io_params(rdata->lseg, &rdata->args.pages,
+	_fix_verify_io_params(hdr->lseg, &rdata->args.pages,
 			      &rdata->args.pgbase,
 			      rdata->args.offset, rdata->args.count);
 
 	dprintk("%s: inode(%lx) offset 0x%llx count 0x%Zx eof=%d\n",
-		__func__, rdata->inode->i_ino, offset, count, rdata->res.eof);
+		__func__, inode->i_ino, offset, count, rdata->res.eof);
 
 	err = objio_read_pagelist(rdata);
  out:
 	if (unlikely(err)) {
-		rdata->pnfs_error = err;
+		hdr->pnfs_error = err;
 		dprintk("%s: Returned Error %d\n", __func__, err);
 		return PNFS_NOT_ATTEMPTED;
 	}
@@ -340,7 +342,7 @@ objlayout_write_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
 		wdata->res.count = status;
 		wdata->verf.committed = oir->committed;
 	} else {
-		wdata->pnfs_error = status;
+		wdata->header->pnfs_error = status;
 	}
 	objlayout_iodone(oir);
 	/* must not use oir after this point */
@@ -363,15 +365,16 @@ enum pnfs_try_status
 objlayout_write_pagelist(struct nfs_write_data *wdata,
 			 int how)
 {
+	struct nfs_pgio_header *hdr = wdata->header;
 	int err;
 
-	_fix_verify_io_params(wdata->lseg, &wdata->args.pages,
+	_fix_verify_io_params(hdr->lseg, &wdata->args.pages,
 			      &wdata->args.pgbase,
 			      wdata->args.offset, wdata->args.count);
 
 	err = objio_write_pagelist(wdata, how);
 	if (unlikely(err)) {
-		wdata->pnfs_error = err;
+		hdr->pnfs_error = err;
 		dprintk("%s: Returned Error %d\n", __func__, err);
 		return PNFS_NOT_ATTEMPTED;
 	}
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index d21fceaa9f62..aed913c833f4 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -26,6 +26,47 @@
 
 static struct kmem_cache *nfs_page_cachep;
 
+bool nfs_pgarray_set(struct nfs_page_array *p, unsigned int pagecount)
+{
+	p->npages = pagecount;
+	if (pagecount <= ARRAY_SIZE(p->page_array))
+		p->pagevec = p->page_array;
+	else {
+		p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_KERNEL);
+		if (!p->pagevec)
+			p->npages = 0;
+	}
+	return p->pagevec != NULL;
+}
+
+void nfs_pgheader_init(struct nfs_pageio_descriptor *desc,
+		       struct nfs_pgio_header *hdr,
+		       void (*release)(struct nfs_pgio_header *hdr))
+{
+	hdr->req = nfs_list_entry(desc->pg_list.next);
+	hdr->inode = desc->pg_inode;
+	hdr->cred = hdr->req->wb_context->cred;
+	hdr->io_start = req_offset(hdr->req);
+	hdr->good_bytes = desc->pg_count;
+	hdr->dreq = desc->pg_dreq;
+	hdr->release = release;
+	hdr->completion_ops = desc->pg_completion_ops;
+	if (hdr->completion_ops->init_hdr)
+		hdr->completion_ops->init_hdr(hdr);
+}
+
+void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos)
+{
+	spin_lock(&hdr->lock);
+	if (pos < hdr->io_start + hdr->good_bytes) {
+		set_bit(NFS_IOHDR_ERROR, &hdr->flags);
+		clear_bit(NFS_IOHDR_EOF, &hdr->flags);
+		hdr->good_bytes = pos - hdr->io_start;
+		hdr->error = error;
+	}
+	spin_unlock(&hdr->lock);
+}
+
 static inline struct nfs_page *
 nfs_page_alloc(void)
 {
@@ -76,12 +117,8 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode,
 	 * long write-back delay. This will be adjusted in
 	 * update_nfs_request below if the region is not locked. */
 	req->wb_page    = page;
-	atomic_set(&req->wb_complete, 0);
 	req->wb_index	= page->index;
 	page_cache_get(page);
-	BUG_ON(PagePrivate(page));
-	BUG_ON(!PageLocked(page));
-	BUG_ON(page->mapping->host != inode);
 	req->wb_offset  = offset;
 	req->wb_pgbase	= offset;
 	req->wb_bytes   = count;
@@ -104,6 +141,15 @@ void nfs_unlock_request(struct nfs_page *req)
 	clear_bit(PG_BUSY, &req->wb_flags);
 	smp_mb__after_clear_bit();
 	wake_up_bit(&req->wb_flags, PG_BUSY);
+}
+
+/**
+ * nfs_unlock_and_release_request - Unlock request and release the nfs_page
+ * @req:
+ */
+void nfs_unlock_and_release_request(struct nfs_page *req)
+{
+	nfs_unlock_request(req);
 	nfs_release_request(req);
 }
 
@@ -203,6 +249,7 @@ EXPORT_SYMBOL_GPL(nfs_generic_pg_test);
 void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
 		     struct inode *inode,
 		     const struct nfs_pageio_ops *pg_ops,
+		     const struct nfs_pgio_completion_ops *compl_ops,
 		     size_t bsize,
 		     int io_flags)
 {
@@ -215,9 +262,11 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
 	desc->pg_recoalesce = 0;
 	desc->pg_inode = inode;
 	desc->pg_ops = pg_ops;
+	desc->pg_completion_ops = compl_ops;
 	desc->pg_ioflags = io_flags;
 	desc->pg_error = 0;
 	desc->pg_lseg = NULL;
+	desc->pg_dreq = NULL;
 }
 
 /**
@@ -241,12 +290,12 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev,
 		return false;
 	if (req->wb_context->state != prev->wb_context->state)
 		return false;
-	if (req->wb_index != (prev->wb_index + 1))
-		return false;
 	if (req->wb_pgbase != 0)
 		return false;
 	if (prev->wb_pgbase + prev->wb_bytes != PAGE_CACHE_SIZE)
 		return false;
+	if (req_offset(req) != req_offset(prev) + prev->wb_bytes)
+		return false;
 	return pgio->pg_ops->pg_test(pgio, prev, req);
 }
 
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 38512bcd2e98..b8323aa7b543 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -395,6 +395,9 @@ mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
 	dprintk("%s:Begin lo %p\n", __func__, lo);
 
 	if (list_empty(&lo->plh_segs)) {
+		/* Reset MDS Threshold I/O counters */
+		NFS_I(lo->plh_inode)->write_io = 0;
+		NFS_I(lo->plh_inode)->read_io = 0;
 		if (!test_and_set_bit(NFS_LAYOUT_DESTROYED, &lo->plh_flags))
 			put_layout_hdr_locked(lo);
 		return 0;
@@ -455,6 +458,7 @@ pnfs_destroy_layout(struct nfs_inode *nfsi)
 	spin_unlock(&nfsi->vfs_inode.i_lock);
 	pnfs_free_lseg_list(&tmp_list);
 }
+EXPORT_SYMBOL_GPL(pnfs_destroy_layout);
 
 /*
  * Called by the state manger to remove all layouts established under an
@@ -692,6 +696,7 @@ out:
 	dprintk("<-- %s status: %d\n", __func__, status);
 	return status;
 }
+EXPORT_SYMBOL_GPL(_pnfs_return_layout);
 
 bool pnfs_roc(struct inode *ino)
 {
@@ -931,6 +936,81 @@ pnfs_find_lseg(struct pnfs_layout_hdr *lo,
 }
 
 /*
+ * Use mdsthreshold hints set at each OPEN to determine if I/O should go
+ * to the MDS or over pNFS
+ *
+ * The nfs_inode read_io and write_io fields are cumulative counters reset
+ * when there are no layout segments. Note that in pnfs_update_layout iomode
+ * is set to IOMODE_READ for a READ request, and set to IOMODE_RW for a
+ * WRITE request.
+ *
+ * A return of true means use MDS I/O.
+ *
+ * From rfc 5661:
+ * If a file's size is smaller than the file size threshold, data accesses
+ * SHOULD be sent to the metadata server.  If an I/O request has a length that
+ * is below the I/O size threshold, the I/O SHOULD be sent to the metadata
+ * server.  If both file size and I/O size are provided, the client SHOULD
+ * reach or exceed  both thresholds before sending its read or write
+ * requests to the data server.
+ */
+static bool pnfs_within_mdsthreshold(struct nfs_open_context *ctx,
+				     struct inode *ino, int iomode)
+{
+	struct nfs4_threshold *t = ctx->mdsthreshold;
+	struct nfs_inode *nfsi = NFS_I(ino);
+	loff_t fsize = i_size_read(ino);
+	bool size = false, size_set = false, io = false, io_set = false, ret = false;
+
+	if (t == NULL)
+		return ret;
+
+	dprintk("%s bm=0x%x rd_sz=%llu wr_sz=%llu rd_io=%llu wr_io=%llu\n",
+		__func__, t->bm, t->rd_sz, t->wr_sz, t->rd_io_sz, t->wr_io_sz);
+
+	switch (iomode) {
+	case IOMODE_READ:
+		if (t->bm & THRESHOLD_RD) {
+			dprintk("%s fsize %llu\n", __func__, fsize);
+			size_set = true;
+			if (fsize < t->rd_sz)
+				size = true;
+		}
+		if (t->bm & THRESHOLD_RD_IO) {
+			dprintk("%s nfsi->read_io %llu\n", __func__,
+				nfsi->read_io);
+			io_set = true;
+			if (nfsi->read_io < t->rd_io_sz)
+				io = true;
+		}
+		break;
+	case IOMODE_RW:
+		if (t->bm & THRESHOLD_WR) {
+			dprintk("%s fsize %llu\n", __func__, fsize);
+			size_set = true;
+			if (fsize < t->wr_sz)
+				size = true;
+		}
+		if (t->bm & THRESHOLD_WR_IO) {
+			dprintk("%s nfsi->write_io %llu\n", __func__,
+				nfsi->write_io);
+			io_set = true;
+			if (nfsi->write_io < t->wr_io_sz)
+				io = true;
+		}
+		break;
+	}
+	if (size_set && io_set) {
+		if (size && io)
+			ret = true;
+	} else if (size || io)
+		ret = true;
+
+	dprintk("<-- %s size %d io %d ret %d\n", __func__, size, io, ret);
+	return ret;
+}
+
+/*
  * Layout segment is retreived from the server if not cached.
  * The appropriate layout segment is referenced and returned to the caller.
  */
@@ -957,6 +1037,10 @@ pnfs_update_layout(struct inode *ino,
 
 	if (!pnfs_enabled_sb(NFS_SERVER(ino)))
 		return NULL;
+
+	if (pnfs_within_mdsthreshold(ctx, ino, iomode))
+		return NULL;
+
 	spin_lock(&ino->i_lock);
 	lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags);
 	if (lo == NULL) {
@@ -1082,6 +1166,10 @@ pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *r
 {
 	BUG_ON(pgio->pg_lseg != NULL);
 
+	if (req->wb_offset != req->wb_pgbase) {
+		nfs_pageio_reset_read_mds(pgio);
+		return;
+	}
 	pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
 					   req->wb_context,
 					   req_offset(req),
@@ -1100,6 +1188,10 @@ pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *
 {
 	BUG_ON(pgio->pg_lseg != NULL);
 
+	if (req->wb_offset != req->wb_pgbase) {
+		nfs_pageio_reset_write_mds(pgio);
+		return;
+	}
 	pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
 					   req->wb_context,
 					   req_offset(req),
@@ -1113,26 +1205,31 @@ pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *
 EXPORT_SYMBOL_GPL(pnfs_generic_pg_init_write);
 
 bool
-pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode)
+pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode,
+		      const struct nfs_pgio_completion_ops *compl_ops)
 {
 	struct nfs_server *server = NFS_SERVER(inode);
 	struct pnfs_layoutdriver_type *ld = server->pnfs_curr_ld;
 
 	if (ld == NULL)
 		return false;
-	nfs_pageio_init(pgio, inode, ld->pg_read_ops, server->rsize, 0);
+	nfs_pageio_init(pgio, inode, ld->pg_read_ops, compl_ops,
+			server->rsize, 0);
 	return true;
 }
 
 bool
-pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags)
+pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode,
+		       int ioflags,
+		       const struct nfs_pgio_completion_ops *compl_ops)
 {
 	struct nfs_server *server = NFS_SERVER(inode);
 	struct pnfs_layoutdriver_type *ld = server->pnfs_curr_ld;
 
 	if (ld == NULL)
 		return false;
-	nfs_pageio_init(pgio, inode, ld->pg_write_ops, server->wsize, ioflags);
+	nfs_pageio_init(pgio, inode, ld->pg_write_ops, compl_ops,
+			server->wsize, ioflags);
 	return true;
 }
 
@@ -1162,13 +1259,15 @@ pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
 }
 EXPORT_SYMBOL_GPL(pnfs_generic_pg_test);
 
-static int pnfs_write_done_resend_to_mds(struct inode *inode, struct list_head *head)
+int pnfs_write_done_resend_to_mds(struct inode *inode,
+				struct list_head *head,
+				const struct nfs_pgio_completion_ops *compl_ops)
 {
 	struct nfs_pageio_descriptor pgio;
 	LIST_HEAD(failed);
 
 	/* Resend all requests through the MDS */
-	nfs_pageio_init_write_mds(&pgio, inode, FLUSH_STABLE);
+	nfs_pageio_init_write_mds(&pgio, inode, FLUSH_STABLE, compl_ops);
 	while (!list_empty(head)) {
 		struct nfs_page *req = nfs_list_entry(head->next);
 
@@ -1188,30 +1287,37 @@ static int pnfs_write_done_resend_to_mds(struct inode *inode, struct list_head *
 	}
 	return 0;
 }
+EXPORT_SYMBOL_GPL(pnfs_write_done_resend_to_mds);
+
+static void pnfs_ld_handle_write_error(struct nfs_write_data *data)
+{
+	struct nfs_pgio_header *hdr = data->header;
+
+	dprintk("pnfs write error = %d\n", hdr->pnfs_error);
+	if (NFS_SERVER(hdr->inode)->pnfs_curr_ld->flags &
+	    PNFS_LAYOUTRET_ON_ERROR) {
+		clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(hdr->inode)->flags);
+		pnfs_return_layout(hdr->inode);
+	}
+	if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags))
+		data->task.tk_status = pnfs_write_done_resend_to_mds(hdr->inode,
+							&hdr->pages,
+							hdr->completion_ops);
+}
 
 /*
  * Called by non rpc-based layout drivers
  */
 void pnfs_ld_write_done(struct nfs_write_data *data)
 {
-	if (likely(!data->pnfs_error)) {
+	struct nfs_pgio_header *hdr = data->header;
+
+	if (!hdr->pnfs_error) {
 		pnfs_set_layoutcommit(data);
-		data->mds_ops->rpc_call_done(&data->task, data);
-	} else {
-		dprintk("pnfs write error = %d\n", data->pnfs_error);
-		if (NFS_SERVER(data->inode)->pnfs_curr_ld->flags &
-						PNFS_LAYOUTRET_ON_ERROR) {
-			/* Don't lo_commit on error, Server will needs to
-			 * preform a file recovery.
-			 */
-			clear_bit(NFS_INO_LAYOUTCOMMIT,
-				  &NFS_I(data->inode)->flags);
-			pnfs_return_layout(data->inode);
-		}
-		data->task.tk_status = pnfs_write_done_resend_to_mds(data->inode, &data->pages);
-	}
-	put_lseg(data->lseg);
-	data->mds_ops->rpc_release(data);
+		hdr->mds_ops->rpc_call_done(&data->task, data);
+	} else
+		pnfs_ld_handle_write_error(data);
+	hdr->mds_ops->rpc_release(data);
 }
 EXPORT_SYMBOL_GPL(pnfs_ld_write_done);
 
@@ -1219,12 +1325,13 @@ static void
 pnfs_write_through_mds(struct nfs_pageio_descriptor *desc,
 		struct nfs_write_data *data)
 {
-	list_splice_tail_init(&data->pages, &desc->pg_list);
-	if (data->req && list_empty(&data->req->wb_list))
-		nfs_list_add_request(data->req, &desc->pg_list);
-	nfs_pageio_reset_write_mds(desc);
-	desc->pg_recoalesce = 1;
-	put_lseg(data->lseg);
+	struct nfs_pgio_header *hdr = data->header;
+
+	if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
+		list_splice_tail_init(&hdr->pages, &desc->pg_list);
+		nfs_pageio_reset_write_mds(desc);
+		desc->pg_recoalesce = 1;
+	}
 	nfs_writedata_release(data);
 }
 
@@ -1234,23 +1341,18 @@ pnfs_try_to_write_data(struct nfs_write_data *wdata,
 			struct pnfs_layout_segment *lseg,
 			int how)
 {
-	struct inode *inode = wdata->inode;
+	struct nfs_pgio_header *hdr = wdata->header;
+	struct inode *inode = hdr->inode;
 	enum pnfs_try_status trypnfs;
 	struct nfs_server *nfss = NFS_SERVER(inode);
 
-	wdata->mds_ops = call_ops;
-	wdata->lseg = get_lseg(lseg);
+	hdr->mds_ops = call_ops;
 
 	dprintk("%s: Writing ino:%lu %u@%llu (how %d)\n", __func__,
 		inode->i_ino, wdata->args.count, wdata->args.offset, how);
-
 	trypnfs = nfss->pnfs_curr_ld->write_pagelist(wdata, how);
-	if (trypnfs == PNFS_NOT_ATTEMPTED) {
-		put_lseg(wdata->lseg);
-		wdata->lseg = NULL;
-	} else
+	if (trypnfs != PNFS_NOT_ATTEMPTED)
 		nfs_inc_stats(inode, NFSIOS_PNFS_WRITE);
-
 	dprintk("%s End (trypnfs:%d)\n", __func__, trypnfs);
 	return trypnfs;
 }
@@ -1266,7 +1368,7 @@ pnfs_do_multiple_writes(struct nfs_pageio_descriptor *desc, struct list_head *he
 	while (!list_empty(head)) {
 		enum pnfs_try_status trypnfs;
 
-		data = list_entry(head->next, struct nfs_write_data, list);
+		data = list_first_entry(head, struct nfs_write_data, list);
 		list_del_init(&data->list);
 
 		trypnfs = pnfs_try_to_write_data(data, call_ops, lseg, how);
@@ -1276,43 +1378,82 @@ pnfs_do_multiple_writes(struct nfs_pageio_descriptor *desc, struct list_head *he
 	put_lseg(lseg);
 }
 
+static void pnfs_writehdr_free(struct nfs_pgio_header *hdr)
+{
+	put_lseg(hdr->lseg);
+	nfs_writehdr_free(hdr);
+}
+
 int
 pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc)
 {
-	LIST_HEAD(head);
+	struct nfs_write_header *whdr;
+	struct nfs_pgio_header *hdr;
 	int ret;
 
-	ret = nfs_generic_flush(desc, &head);
-	if (ret != 0) {
+	whdr = nfs_writehdr_alloc();
+	if (!whdr) {
+		desc->pg_completion_ops->error_cleanup(&desc->pg_list);
 		put_lseg(desc->pg_lseg);
 		desc->pg_lseg = NULL;
-		return ret;
+		return -ENOMEM;
 	}
-	pnfs_do_multiple_writes(desc, &head, desc->pg_ioflags);
-	return 0;
+	hdr = &whdr->header;
+	nfs_pgheader_init(desc, hdr, pnfs_writehdr_free);
+	hdr->lseg = get_lseg(desc->pg_lseg);
+	atomic_inc(&hdr->refcnt);
+	ret = nfs_generic_flush(desc, hdr);
+	if (ret != 0) {
+		put_lseg(desc->pg_lseg);
+		desc->pg_lseg = NULL;
+	} else
+		pnfs_do_multiple_writes(desc, &hdr->rpc_list, desc->pg_ioflags);
+	if (atomic_dec_and_test(&hdr->refcnt))
+		hdr->completion_ops->completion(hdr);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(pnfs_generic_pg_writepages);
 
-static void pnfs_ld_handle_read_error(struct nfs_read_data *data)
+int pnfs_read_done_resend_to_mds(struct inode *inode,
+				struct list_head *head,
+				const struct nfs_pgio_completion_ops *compl_ops)
 {
 	struct nfs_pageio_descriptor pgio;
+	LIST_HEAD(failed);
 
-	put_lseg(data->lseg);
-	data->lseg = NULL;
-	dprintk("pnfs write error = %d\n", data->pnfs_error);
-	if (NFS_SERVER(data->inode)->pnfs_curr_ld->flags &
-						PNFS_LAYOUTRET_ON_ERROR)
-		pnfs_return_layout(data->inode);
-
-	nfs_pageio_init_read_mds(&pgio, data->inode);
-
-	while (!list_empty(&data->pages)) {
-		struct nfs_page *req = nfs_list_entry(data->pages.next);
+	/* Resend all requests through the MDS */
+	nfs_pageio_init_read_mds(&pgio, inode, compl_ops);
+	while (!list_empty(head)) {
+		struct nfs_page *req = nfs_list_entry(head->next);
 
 		nfs_list_remove_request(req);
-		nfs_pageio_add_request(&pgio, req);
+		if (!nfs_pageio_add_request(&pgio, req))
+			nfs_list_add_request(req, &failed);
 	}
 	nfs_pageio_complete(&pgio);
+
+	if (!list_empty(&failed)) {
+		list_move(&failed, head);
+		return -EIO;
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pnfs_read_done_resend_to_mds);
+
+static void pnfs_ld_handle_read_error(struct nfs_read_data *data)
+{
+	struct nfs_pgio_header *hdr = data->header;
+
+	dprintk("pnfs read error = %d\n", hdr->pnfs_error);
+	if (NFS_SERVER(hdr->inode)->pnfs_curr_ld->flags &
+	    PNFS_LAYOUTRET_ON_ERROR) {
+		clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(hdr->inode)->flags);
+		pnfs_return_layout(hdr->inode);
+	}
+	if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags))
+		data->task.tk_status = pnfs_read_done_resend_to_mds(hdr->inode,
+							&hdr->pages,
+							hdr->completion_ops);
 }
 
 /*
@@ -1320,13 +1461,14 @@ static void pnfs_ld_handle_read_error(struct nfs_read_data *data)
  */
 void pnfs_ld_read_done(struct nfs_read_data *data)
 {
-	if (likely(!data->pnfs_error)) {
+	struct nfs_pgio_header *hdr = data->header;
+
+	if (likely(!hdr->pnfs_error)) {
 		__nfs4_read_done_cb(data);
-		data->mds_ops->rpc_call_done(&data->task, data);
+		hdr->mds_ops->rpc_call_done(&data->task, data);
 	} else
 		pnfs_ld_handle_read_error(data);
-	put_lseg(data->lseg);
-	data->mds_ops->rpc_release(data);
+	hdr->mds_ops->rpc_release(data);
 }
 EXPORT_SYMBOL_GPL(pnfs_ld_read_done);
 
@@ -1334,11 +1476,13 @@ static void
 pnfs_read_through_mds(struct nfs_pageio_descriptor *desc,
 		struct nfs_read_data *data)
 {
-	list_splice_tail_init(&data->pages, &desc->pg_list);
-	if (data->req && list_empty(&data->req->wb_list))
-		nfs_list_add_request(data->req, &desc->pg_list);
-	nfs_pageio_reset_read_mds(desc);
-	desc->pg_recoalesce = 1;
+	struct nfs_pgio_header *hdr = data->header;
+
+	if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
+		list_splice_tail_init(&hdr->pages, &desc->pg_list);
+		nfs_pageio_reset_read_mds(desc);
+		desc->pg_recoalesce = 1;
+	}
 	nfs_readdata_release(data);
 }
 
@@ -1350,23 +1494,19 @@ pnfs_try_to_read_data(struct nfs_read_data *rdata,
 		       const struct rpc_call_ops *call_ops,
 		       struct pnfs_layout_segment *lseg)
 {
-	struct inode *inode = rdata->inode;
+	struct nfs_pgio_header *hdr = rdata->header;
+	struct inode *inode = hdr->inode;
 	struct nfs_server *nfss = NFS_SERVER(inode);
 	enum pnfs_try_status trypnfs;
 
-	rdata->mds_ops = call_ops;
-	rdata->lseg = get_lseg(lseg);
+	hdr->mds_ops = call_ops;
 
 	dprintk("%s: Reading ino:%lu %u@%llu\n",
 		__func__, inode->i_ino, rdata->args.count, rdata->args.offset);
 
 	trypnfs = nfss->pnfs_curr_ld->read_pagelist(rdata);
-	if (trypnfs == PNFS_NOT_ATTEMPTED) {
-		put_lseg(rdata->lseg);
-		rdata->lseg = NULL;
-	} else {
+	if (trypnfs != PNFS_NOT_ATTEMPTED)
 		nfs_inc_stats(inode, NFSIOS_PNFS_READ);
-	}
 	dprintk("%s End (trypnfs:%d)\n", __func__, trypnfs);
 	return trypnfs;
 }
@@ -1382,7 +1522,7 @@ pnfs_do_multiple_reads(struct nfs_pageio_descriptor *desc, struct list_head *hea
 	while (!list_empty(head)) {
 		enum pnfs_try_status trypnfs;
 
-		data = list_entry(head->next, struct nfs_read_data, list);
+		data = list_first_entry(head, struct nfs_read_data, list);
 		list_del_init(&data->list);
 
 		trypnfs = pnfs_try_to_read_data(data, call_ops, lseg);
@@ -1392,20 +1532,40 @@ pnfs_do_multiple_reads(struct nfs_pageio_descriptor *desc, struct list_head *hea
 	put_lseg(lseg);
 }
 
+static void pnfs_readhdr_free(struct nfs_pgio_header *hdr)
+{
+	put_lseg(hdr->lseg);
+	nfs_readhdr_free(hdr);
+}
+
 int
 pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc)
 {
-	LIST_HEAD(head);
+	struct nfs_read_header *rhdr;
+	struct nfs_pgio_header *hdr;
 	int ret;
 
-	ret = nfs_generic_pagein(desc, &head);
-	if (ret != 0) {
+	rhdr = nfs_readhdr_alloc();
+	if (!rhdr) {
+		desc->pg_completion_ops->error_cleanup(&desc->pg_list);
+		ret = -ENOMEM;
 		put_lseg(desc->pg_lseg);
 		desc->pg_lseg = NULL;
 		return ret;
 	}
-	pnfs_do_multiple_reads(desc, &head);
-	return 0;
+	hdr = &rhdr->header;
+	nfs_pgheader_init(desc, hdr, pnfs_readhdr_free);
+	hdr->lseg = get_lseg(desc->pg_lseg);
+	atomic_inc(&hdr->refcnt);
+	ret = nfs_generic_pagein(desc, hdr);
+	if (ret != 0) {
+		put_lseg(desc->pg_lseg);
+		desc->pg_lseg = NULL;
+	} else
+		pnfs_do_multiple_reads(desc, &hdr->rpc_list);
+	if (atomic_dec_and_test(&hdr->refcnt))
+		hdr->completion_ops->completion(hdr);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(pnfs_generic_pg_readpages);
 
@@ -1438,30 +1598,32 @@ EXPORT_SYMBOL_GPL(pnfs_set_lo_fail);
 void
 pnfs_set_layoutcommit(struct nfs_write_data *wdata)
 {
-	struct nfs_inode *nfsi = NFS_I(wdata->inode);
+	struct nfs_pgio_header *hdr = wdata->header;
+	struct inode *inode = hdr->inode;
+	struct nfs_inode *nfsi = NFS_I(inode);
 	loff_t end_pos = wdata->mds_offset + wdata->res.count;
 	bool mark_as_dirty = false;
 
-	spin_lock(&nfsi->vfs_inode.i_lock);
+	spin_lock(&inode->i_lock);
 	if (!test_and_set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) {
 		mark_as_dirty = true;
 		dprintk("%s: Set layoutcommit for inode %lu ",
-			__func__, wdata->inode->i_ino);
+			__func__, inode->i_ino);
 	}
-	if (!test_and_set_bit(NFS_LSEG_LAYOUTCOMMIT, &wdata->lseg->pls_flags)) {
+	if (!test_and_set_bit(NFS_LSEG_LAYOUTCOMMIT, &hdr->lseg->pls_flags)) {
 		/* references matched in nfs4_layoutcommit_release */
-		get_lseg(wdata->lseg);
+		get_lseg(hdr->lseg);
 	}
 	if (end_pos > nfsi->layout->plh_lwb)
 		nfsi->layout->plh_lwb = end_pos;
-	spin_unlock(&nfsi->vfs_inode.i_lock);
+	spin_unlock(&inode->i_lock);
 	dprintk("%s: lseg %p end_pos %llu\n",
-		__func__, wdata->lseg, nfsi->layout->plh_lwb);
+		__func__, hdr->lseg, nfsi->layout->plh_lwb);
 
 	/* if pnfs_layoutcommit_inode() runs between inode locks, the next one
 	 * will be a noop because NFS_INO_LAYOUTCOMMIT will not be set */
 	if (mark_as_dirty)
-		mark_inode_dirty_sync(wdata->inode);
+		mark_inode_dirty_sync(inode);
 }
 EXPORT_SYMBOL_GPL(pnfs_set_layoutcommit);
 
@@ -1550,3 +1712,15 @@ out_free:
 	kfree(data);
 	goto out;
 }
+
+struct nfs4_threshold *pnfs_mdsthreshold_alloc(void)
+{
+	struct nfs4_threshold *thp;
+
+	thp = kzalloc(sizeof(*thp), GFP_NOFS);
+	if (!thp) {
+		dprintk("%s mdsthreshold allocation failed\n", __func__);
+		return NULL;
+	}
+	return thp;
+}
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 442ebf68eeec..29fd23c0efdc 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -63,6 +63,7 @@ enum {
 	NFS_LAYOUT_BULK_RECALL,		/* bulk recall affecting layout */
 	NFS_LAYOUT_ROC,			/* some lseg had roc bit set */
 	NFS_LAYOUT_DESTROYED,		/* no new use of layout allowed */
+	NFS_LAYOUT_INVALID,		/* layout is being destroyed */
 };
 
 enum layoutdriver_policy_flags {
@@ -94,11 +95,20 @@ struct pnfs_layoutdriver_type {
 	const struct nfs_pageio_ops *pg_read_ops;
 	const struct nfs_pageio_ops *pg_write_ops;
 
+	struct pnfs_ds_commit_info *(*get_ds_info) (struct inode *inode);
 	void (*mark_request_commit) (struct nfs_page *req,
-					struct pnfs_layout_segment *lseg);
-	void (*clear_request_commit) (struct nfs_page *req);
-	int (*scan_commit_lists) (struct inode *inode, int max, spinlock_t *lock);
-	int (*commit_pagelist)(struct inode *inode, struct list_head *mds_pages, int how);
+				     struct pnfs_layout_segment *lseg,
+				     struct nfs_commit_info *cinfo);
+	void (*clear_request_commit) (struct nfs_page *req,
+				      struct nfs_commit_info *cinfo);
+	int (*scan_commit_lists) (struct nfs_commit_info *cinfo,
+				  int max);
+	void (*recover_commit_reqs) (struct list_head *list,
+				     struct nfs_commit_info *cinfo);
+	int (*commit_pagelist)(struct inode *inode,
+			       struct list_head *mds_pages,
+			       int how,
+			       struct nfs_commit_info *cinfo);
 
 	/*
 	 * Return PNFS_ATTEMPTED to indicate the layout code has attempted
@@ -168,8 +178,10 @@ extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp);
 void get_layout_hdr(struct pnfs_layout_hdr *lo);
 void put_lseg(struct pnfs_layout_segment *lseg);
 
-bool pnfs_pageio_init_read(struct nfs_pageio_descriptor *, struct inode *);
-bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *, struct inode *, int);
+bool pnfs_pageio_init_read(struct nfs_pageio_descriptor *, struct inode *,
+			   const struct nfs_pgio_completion_ops *);
+bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *, struct inode *,
+			    int, const struct nfs_pgio_completion_ops *);
 
 void set_pnfs_layoutdriver(struct nfs_server *, const struct nfs_fh *, u32);
 void unset_pnfs_layoutdriver(struct nfs_server *);
@@ -211,6 +223,11 @@ struct pnfs_layout_segment *pnfs_update_layout(struct inode *ino,
 					       gfp_t gfp_flags);
 
 void nfs4_deviceid_mark_client_invalid(struct nfs_client *clp);
+int pnfs_read_done_resend_to_mds(struct inode *inode, struct list_head *head,
+			const struct nfs_pgio_completion_ops *compl_ops);
+int pnfs_write_done_resend_to_mds(struct inode *inode, struct list_head *head,
+			const struct nfs_pgio_completion_ops *compl_ops);
+struct nfs4_threshold *pnfs_mdsthreshold_alloc(void);
 
 /* nfs4_deviceid_flags */
 enum {
@@ -261,49 +278,66 @@ static inline int pnfs_enabled_sb(struct nfs_server *nfss)
 }
 
 static inline int
-pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how)
+pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how,
+		 struct nfs_commit_info *cinfo)
 {
-	if (!test_and_clear_bit(NFS_INO_PNFS_COMMIT, &NFS_I(inode)->flags))
+	if (cinfo->ds == NULL || cinfo->ds->ncommitting == 0)
 		return PNFS_NOT_ATTEMPTED;
-	return NFS_SERVER(inode)->pnfs_curr_ld->commit_pagelist(inode, mds_pages, how);
+	return NFS_SERVER(inode)->pnfs_curr_ld->commit_pagelist(inode, mds_pages, how, cinfo);
+}
+
+static inline struct pnfs_ds_commit_info *
+pnfs_get_ds_info(struct inode *inode)
+{
+	struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
+
+	if (ld == NULL || ld->get_ds_info == NULL)
+		return NULL;
+	return ld->get_ds_info(inode);
 }
 
 static inline bool
-pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg)
+pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg,
+			 struct nfs_commit_info *cinfo)
 {
 	struct inode *inode = req->wb_context->dentry->d_inode;
 	struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
 
 	if (lseg == NULL || ld->mark_request_commit == NULL)
 		return false;
-	ld->mark_request_commit(req, lseg);
+	ld->mark_request_commit(req, lseg, cinfo);
 	return true;
 }
 
 static inline bool
-pnfs_clear_request_commit(struct nfs_page *req)
+pnfs_clear_request_commit(struct nfs_page *req, struct nfs_commit_info *cinfo)
 {
 	struct inode *inode = req->wb_context->dentry->d_inode;
 	struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
 
 	if (ld == NULL || ld->clear_request_commit == NULL)
 		return false;
-	ld->clear_request_commit(req);
+	ld->clear_request_commit(req, cinfo);
 	return true;
 }
 
 static inline int
-pnfs_scan_commit_lists(struct inode *inode, int max, spinlock_t *lock)
+pnfs_scan_commit_lists(struct inode *inode, struct nfs_commit_info *cinfo,
+		       int max)
 {
-	struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
-	int ret;
-
-	if (ld == NULL || ld->scan_commit_lists == NULL)
+	if (cinfo->ds == NULL || cinfo->ds->nwritten == 0)
 		return 0;
-	ret = ld->scan_commit_lists(inode, max, lock);
-	if (ret != 0)
-		set_bit(NFS_INO_PNFS_COMMIT, &NFS_I(inode)->flags);
-	return ret;
+	else
+		return NFS_SERVER(inode)->pnfs_curr_ld->scan_commit_lists(cinfo, max);
+}
+
+static inline void
+pnfs_recover_commit_reqs(struct inode *inode, struct list_head *list,
+			 struct nfs_commit_info *cinfo)
+{
+	if (cinfo->ds == NULL || cinfo->ds->nwritten == 0)
+		return;
+	NFS_SERVER(inode)->pnfs_curr_ld->recover_commit_reqs(list, cinfo);
 }
 
 /* Should the pNFS client commit and return the layout upon a setattr */
@@ -327,6 +361,14 @@ static inline int pnfs_return_layout(struct inode *ino)
 	return 0;
 }
 
+static inline bool
+pnfs_use_threshold(struct nfs4_threshold **dst, struct nfs4_threshold *src,
+		   struct nfs_server *nfss)
+{
+	return (dst && src && src->bm != 0 &&
+					nfss->pnfs_curr_ld->id == src->l_type);
+}
+
 #ifdef NFS_DEBUG
 void nfs4_print_deviceid(const struct nfs4_deviceid *dev_id);
 #else
@@ -396,45 +438,74 @@ static inline void unset_pnfs_layoutdriver(struct nfs_server *s)
 {
 }
 
-static inline bool pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode)
+static inline bool pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode,
+					 const struct nfs_pgio_completion_ops *compl_ops)
 {
 	return false;
 }
 
-static inline bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags)
+static inline bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags,
+					  const struct nfs_pgio_completion_ops *compl_ops)
 {
 	return false;
 }
 
 static inline int
-pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how)
+pnfs_commit_list(struct inode *inode, struct list_head *mds_pages, int how,
+		 struct nfs_commit_info *cinfo)
 {
 	return PNFS_NOT_ATTEMPTED;
 }
 
+static inline struct pnfs_ds_commit_info *
+pnfs_get_ds_info(struct inode *inode)
+{
+	return NULL;
+}
+
 static inline bool
-pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg)
+pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg,
+			 struct nfs_commit_info *cinfo)
 {
 	return false;
 }
 
 static inline bool
-pnfs_clear_request_commit(struct nfs_page *req)
+pnfs_clear_request_commit(struct nfs_page *req, struct nfs_commit_info *cinfo)
 {
 	return false;
 }
 
 static inline int
-pnfs_scan_commit_lists(struct inode *inode, int max, spinlock_t *lock)
+pnfs_scan_commit_lists(struct inode *inode, struct nfs_commit_info *cinfo,
+		       int max)
 {
 	return 0;
 }
 
+static inline void
+pnfs_recover_commit_reqs(struct inode *inode, struct list_head *list,
+			 struct nfs_commit_info *cinfo)
+{
+}
+
 static inline int pnfs_layoutcommit_inode(struct inode *inode, bool sync)
 {
 	return 0;
 }
 
+static inline bool
+pnfs_use_threshold(struct nfs4_threshold **dst, struct nfs4_threshold *src,
+		   struct nfs_server *nfss)
+{
+	return false;
+}
+
+static inline struct nfs4_threshold *pnfs_mdsthreshold_alloc(void)
+{
+	return NULL;
+}
+
 #endif /* CONFIG_NFS_V4_1 */
 
 #endif /* FS_NFS_PNFS_H */
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index d6408b6437de..a706b6bcc286 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -178,7 +178,7 @@ nfs_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
 }
 
 static int
-nfs_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, struct qstr *name,
+nfs_proc_lookup(struct inode *dir, struct qstr *name,
 		struct nfs_fh *fhandle, struct nfs_fattr *fattr)
 {
 	struct nfs_diropargs	arg = {
@@ -640,12 +640,14 @@ nfs_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle,
 
 static int nfs_read_done(struct rpc_task *task, struct nfs_read_data *data)
 {
+	struct inode *inode = data->header->inode;
+
 	if (nfs_async_handle_expired_key(task))
 		return -EAGAIN;
 
-	nfs_invalidate_atime(data->inode);
+	nfs_invalidate_atime(inode);
 	if (task->tk_status >= 0) {
-		nfs_refresh_inode(data->inode, data->res.fattr);
+		nfs_refresh_inode(inode, data->res.fattr);
 		/* Emulate the eof flag, which isn't normally needed in NFSv2
 		 * as it is guaranteed to always return the file attributes
 		 */
@@ -667,11 +669,13 @@ static void nfs_proc_read_rpc_prepare(struct rpc_task *task, struct nfs_read_dat
 
 static int nfs_write_done(struct rpc_task *task, struct nfs_write_data *data)
 {
+	struct inode *inode = data->header->inode;
+
 	if (nfs_async_handle_expired_key(task))
 		return -EAGAIN;
 
 	if (task->tk_status >= 0)
-		nfs_post_op_update_inode_force_wcc(data->inode, data->res.fattr);
+		nfs_post_op_update_inode_force_wcc(inode, data->res.fattr);
 	return 0;
 }
 
@@ -687,8 +691,13 @@ static void nfs_proc_write_rpc_prepare(struct rpc_task *task, struct nfs_write_d
 	rpc_call_start(task);
 }
 
+static void nfs_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data)
+{
+	BUG();
+}
+
 static void
-nfs_proc_commit_setup(struct nfs_write_data *data, struct rpc_message *msg)
+nfs_proc_commit_setup(struct nfs_commit_data *data, struct rpc_message *msg)
 {
 	BUG();
 }
@@ -732,6 +741,7 @@ const struct nfs_rpc_ops nfs_v2_clientops = {
 	.file_inode_ops	= &nfs_file_inode_operations,
 	.file_ops	= &nfs_file_operations,
 	.getroot	= nfs_proc_get_root,
+	.submount	= nfs_submount,
 	.getattr	= nfs_proc_getattr,
 	.setattr	= nfs_proc_setattr,
 	.lookup		= nfs_proc_lookup,
@@ -763,6 +773,7 @@ const struct nfs_rpc_ops nfs_v2_clientops = {
 	.write_rpc_prepare = nfs_proc_write_rpc_prepare,
 	.write_done	= nfs_write_done,
 	.commit_setup	= nfs_proc_commit_setup,
+	.commit_rpc_prepare = nfs_proc_commit_rpc_prepare,
 	.lock		= nfs_proc_lock,
 	.lock_check_bounds = nfs_lock_check_bounds,
 	.close_context	= nfs_close_context,
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 0a4be28c2ea3..86ced7836214 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -30,43 +30,73 @@
 #define NFSDBG_FACILITY		NFSDBG_PAGECACHE
 
 static const struct nfs_pageio_ops nfs_pageio_read_ops;
-static const struct rpc_call_ops nfs_read_partial_ops;
-static const struct rpc_call_ops nfs_read_full_ops;
+static const struct rpc_call_ops nfs_read_common_ops;
+static const struct nfs_pgio_completion_ops nfs_async_read_completion_ops;
 
 static struct kmem_cache *nfs_rdata_cachep;
 
-struct nfs_read_data *nfs_readdata_alloc(unsigned int pagecount)
+struct nfs_read_header *nfs_readhdr_alloc(void)
 {
-	struct nfs_read_data *p;
-
-	p = kmem_cache_zalloc(nfs_rdata_cachep, GFP_KERNEL);
-	if (p) {
-		INIT_LIST_HEAD(&p->pages);
-		p->npages = pagecount;
-		if (pagecount <= ARRAY_SIZE(p->page_array))
-			p->pagevec = p->page_array;
-		else {
-			p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_KERNEL);
-			if (!p->pagevec) {
-				kmem_cache_free(nfs_rdata_cachep, p);
-				p = NULL;
-			}
-		}
+	struct nfs_read_header *rhdr;
+
+	rhdr = kmem_cache_zalloc(nfs_rdata_cachep, GFP_KERNEL);
+	if (rhdr) {
+		struct nfs_pgio_header *hdr = &rhdr->header;
+
+		INIT_LIST_HEAD(&hdr->pages);
+		INIT_LIST_HEAD(&hdr->rpc_list);
+		spin_lock_init(&hdr->lock);
+		atomic_set(&hdr->refcnt, 0);
+	}
+	return rhdr;
+}
+
+static struct nfs_read_data *nfs_readdata_alloc(struct nfs_pgio_header *hdr,
+						unsigned int pagecount)
+{
+	struct nfs_read_data *data, *prealloc;
+
+	prealloc = &container_of(hdr, struct nfs_read_header, header)->rpc_data;
+	if (prealloc->header == NULL)
+		data = prealloc;
+	else
+		data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		goto out;
+
+	if (nfs_pgarray_set(&data->pages, pagecount)) {
+		data->header = hdr;
+		atomic_inc(&hdr->refcnt);
+	} else {
+		if (data != prealloc)
+			kfree(data);
+		data = NULL;
 	}
-	return p;
+out:
+	return data;
 }
 
-void nfs_readdata_free(struct nfs_read_data *p)
+void nfs_readhdr_free(struct nfs_pgio_header *hdr)
 {
-	if (p && (p->pagevec != &p->page_array[0]))
-		kfree(p->pagevec);
-	kmem_cache_free(nfs_rdata_cachep, p);
+	struct nfs_read_header *rhdr = container_of(hdr, struct nfs_read_header, header);
+
+	kmem_cache_free(nfs_rdata_cachep, rhdr);
 }
 
 void nfs_readdata_release(struct nfs_read_data *rdata)
 {
+	struct nfs_pgio_header *hdr = rdata->header;
+	struct nfs_read_header *read_header = container_of(hdr, struct nfs_read_header, header);
+
 	put_nfs_open_context(rdata->args.context);
-	nfs_readdata_free(rdata);
+	if (rdata->pages.pagevec != rdata->pages.page_array)
+		kfree(rdata->pages.pagevec);
+	if (rdata != &read_header->rpc_data)
+		kfree(rdata);
+	else
+		rdata->header = NULL;
+	if (atomic_dec_and_test(&hdr->refcnt))
+		hdr->completion_ops->completion(hdr);
 }
 
 static
@@ -78,39 +108,11 @@ int nfs_return_empty_page(struct page *page)
 	return 0;
 }
 
-static void nfs_readpage_truncate_uninitialised_page(struct nfs_read_data *data)
-{
-	unsigned int remainder = data->args.count - data->res.count;
-	unsigned int base = data->args.pgbase + data->res.count;
-	unsigned int pglen;
-	struct page **pages;
-
-	if (data->res.eof == 0 || remainder == 0)
-		return;
-	/*
-	 * Note: "remainder" can never be negative, since we check for
-	 * 	this in the XDR code.
-	 */
-	pages = &data->args.pages[base >> PAGE_CACHE_SHIFT];
-	base &= ~PAGE_CACHE_MASK;
-	pglen = PAGE_CACHE_SIZE - base;
-	for (;;) {
-		if (remainder <= pglen) {
-			zero_user(*pages, base, remainder);
-			break;
-		}
-		zero_user(*pages, base, pglen);
-		pages++;
-		remainder -= pglen;
-		pglen = PAGE_CACHE_SIZE;
-		base = 0;
-	}
-}
-
 void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio,
-		struct inode *inode)
+			      struct inode *inode,
+			      const struct nfs_pgio_completion_ops *compl_ops)
 {
-	nfs_pageio_init(pgio, inode, &nfs_pageio_read_ops,
+	nfs_pageio_init(pgio, inode, &nfs_pageio_read_ops, compl_ops,
 			NFS_SERVER(inode)->rsize, 0);
 }
 
@@ -121,11 +123,12 @@ void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio)
 }
 EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds);
 
-static void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio,
-		struct inode *inode)
+void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio,
+			  struct inode *inode,
+			  const struct nfs_pgio_completion_ops *compl_ops)
 {
-	if (!pnfs_pageio_init_read(pgio, inode))
-		nfs_pageio_init_read_mds(pgio, inode);
+	if (!pnfs_pageio_init_read(pgio, inode, compl_ops))
+		nfs_pageio_init_read_mds(pgio, inode, compl_ops);
 }
 
 int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
@@ -146,9 +149,10 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
 	if (len < PAGE_CACHE_SIZE)
 		zero_user_segment(page, len, PAGE_CACHE_SIZE);
 
-	nfs_pageio_init_read(&pgio, inode);
+	nfs_pageio_init_read(&pgio, inode, &nfs_async_read_completion_ops);
 	nfs_pageio_add_request(&pgio, new);
 	nfs_pageio_complete(&pgio);
+	NFS_I(inode)->read_io += pgio.pg_bytes_written;
 	return 0;
 }
 
@@ -169,16 +173,49 @@ static void nfs_readpage_release(struct nfs_page *req)
 	nfs_release_request(req);
 }
 
-int nfs_initiate_read(struct nfs_read_data *data, struct rpc_clnt *clnt,
-		      const struct rpc_call_ops *call_ops)
+/* Note io was page aligned */
+static void nfs_read_completion(struct nfs_pgio_header *hdr)
+{
+	unsigned long bytes = 0;
+
+	if (test_bit(NFS_IOHDR_REDO, &hdr->flags))
+		goto out;
+	while (!list_empty(&hdr->pages)) {
+		struct nfs_page *req = nfs_list_entry(hdr->pages.next);
+		struct page *page = req->wb_page;
+
+		if (test_bit(NFS_IOHDR_EOF, &hdr->flags)) {
+			if (bytes > hdr->good_bytes)
+				zero_user(page, 0, PAGE_SIZE);
+			else if (hdr->good_bytes - bytes < PAGE_SIZE)
+				zero_user_segment(page,
+					hdr->good_bytes & ~PAGE_MASK,
+					PAGE_SIZE);
+		}
+		bytes += req->wb_bytes;
+		if (test_bit(NFS_IOHDR_ERROR, &hdr->flags)) {
+			if (bytes <= hdr->good_bytes)
+				SetPageUptodate(page);
+		} else
+			SetPageUptodate(page);
+		nfs_list_remove_request(req);
+		nfs_readpage_release(req);
+	}
+out:
+	hdr->release(hdr);
+}
+
+int nfs_initiate_read(struct rpc_clnt *clnt,
+		      struct nfs_read_data *data,
+		      const struct rpc_call_ops *call_ops, int flags)
 {
-	struct inode *inode = data->inode;
+	struct inode *inode = data->header->inode;
 	int swap_flags = IS_SWAPFILE(inode) ? NFS_RPC_SWAPFLAGS : 0;
 	struct rpc_task *task;
 	struct rpc_message msg = {
 		.rpc_argp = &data->args,
 		.rpc_resp = &data->res,
-		.rpc_cred = data->cred,
+		.rpc_cred = data->header->cred,
 	};
 	struct rpc_task_setup task_setup_data = {
 		.task = &data->task,
@@ -187,7 +224,7 @@ int nfs_initiate_read(struct nfs_read_data *data, struct rpc_clnt *clnt,
 		.callback_ops = call_ops,
 		.callback_data = data,
 		.workqueue = nfsiod_workqueue,
-		.flags = RPC_TASK_ASYNC | swap_flags,
+		.flags = RPC_TASK_ASYNC | swap_flags | flags,
 	};
 
 	/* Set up the initial task struct. */
@@ -212,19 +249,15 @@ EXPORT_SYMBOL_GPL(nfs_initiate_read);
 /*
  * Set up the NFS read request struct
  */
-static void nfs_read_rpcsetup(struct nfs_page *req, struct nfs_read_data *data,
+static void nfs_read_rpcsetup(struct nfs_read_data *data,
 		unsigned int count, unsigned int offset)
 {
-	struct inode *inode = req->wb_context->dentry->d_inode;
-
-	data->req	  = req;
-	data->inode	  = inode;
-	data->cred	  = req->wb_context->cred;
+	struct nfs_page *req = data->header->req;
 
-	data->args.fh     = NFS_FH(inode);
+	data->args.fh     = NFS_FH(data->header->inode);
 	data->args.offset = req_offset(req) + offset;
 	data->args.pgbase = req->wb_pgbase + offset;
-	data->args.pages  = data->pagevec;
+	data->args.pages  = data->pages.pagevec;
 	data->args.count  = count;
 	data->args.context = get_nfs_open_context(req->wb_context);
 	data->args.lock_context = req->wb_lock_context;
@@ -238,9 +271,9 @@ static void nfs_read_rpcsetup(struct nfs_page *req, struct nfs_read_data *data,
 static int nfs_do_read(struct nfs_read_data *data,
 		const struct rpc_call_ops *call_ops)
 {
-	struct inode *inode = data->args.context->dentry->d_inode;
+	struct inode *inode = data->header->inode;
 
-	return nfs_initiate_read(data, NFS_CLIENT(inode), call_ops);
+	return nfs_initiate_read(NFS_CLIENT(inode), data, call_ops, 0);
 }
 
 static int
@@ -253,7 +286,7 @@ nfs_do_multiple_reads(struct list_head *head,
 	while (!list_empty(head)) {
 		int ret2;
 
-		data = list_entry(head->next, struct nfs_read_data, list);
+		data = list_first_entry(head, struct nfs_read_data, list);
 		list_del_init(&data->list);
 
 		ret2 = nfs_do_read(data, call_ops);
@@ -275,6 +308,24 @@ nfs_async_read_error(struct list_head *head)
 	}
 }
 
+static const struct nfs_pgio_completion_ops nfs_async_read_completion_ops = {
+	.error_cleanup = nfs_async_read_error,
+	.completion = nfs_read_completion,
+};
+
+static void nfs_pagein_error(struct nfs_pageio_descriptor *desc,
+		struct nfs_pgio_header *hdr)
+{
+	set_bit(NFS_IOHDR_REDO, &hdr->flags);
+	while (!list_empty(&hdr->rpc_list)) {
+		struct nfs_read_data *data = list_first_entry(&hdr->rpc_list,
+				struct nfs_read_data, list);
+		list_del(&data->list);
+		nfs_readdata_release(data);
+	}
+	desc->pg_completion_ops->error_cleanup(&desc->pg_list);
+}
+
 /*
  * Generate multiple requests to fill a single page.
  *
@@ -288,93 +339,95 @@ nfs_async_read_error(struct list_head *head)
  * won't see the new data until our attribute cache is updated.  This is more
  * or less conventional NFS client behavior.
  */
-static int nfs_pagein_multi(struct nfs_pageio_descriptor *desc, struct list_head *res)
+static int nfs_pagein_multi(struct nfs_pageio_descriptor *desc,
+			    struct nfs_pgio_header *hdr)
 {
-	struct nfs_page *req = nfs_list_entry(desc->pg_list.next);
+	struct nfs_page *req = hdr->req;
 	struct page *page = req->wb_page;
 	struct nfs_read_data *data;
 	size_t rsize = desc->pg_bsize, nbytes;
 	unsigned int offset;
-	int requests = 0;
-	int ret = 0;
-
-	nfs_list_remove_request(req);
 
 	offset = 0;
 	nbytes = desc->pg_count;
 	do {
 		size_t len = min(nbytes,rsize);
 
-		data = nfs_readdata_alloc(1);
-		if (!data)
-			goto out_bad;
-		data->pagevec[0] = page;
-		nfs_read_rpcsetup(req, data, len, offset);
-		list_add(&data->list, res);
-		requests++;
+		data = nfs_readdata_alloc(hdr, 1);
+		if (!data) {
+			nfs_pagein_error(desc, hdr);
+			return -ENOMEM;
+		}
+		data->pages.pagevec[0] = page;
+		nfs_read_rpcsetup(data, len, offset);
+		list_add(&data->list, &hdr->rpc_list);
 		nbytes -= len;
 		offset += len;
-	} while(nbytes != 0);
-	atomic_set(&req->wb_complete, requests);
-	desc->pg_rpc_callops = &nfs_read_partial_ops;
-	return ret;
-out_bad:
-	while (!list_empty(res)) {
-		data = list_entry(res->next, struct nfs_read_data, list);
-		list_del(&data->list);
-		nfs_readdata_release(data);
-	}
-	nfs_readpage_release(req);
-	return -ENOMEM;
+	} while (nbytes != 0);
+
+	nfs_list_remove_request(req);
+	nfs_list_add_request(req, &hdr->pages);
+	desc->pg_rpc_callops = &nfs_read_common_ops;
+	return 0;
 }
 
-static int nfs_pagein_one(struct nfs_pageio_descriptor *desc, struct list_head *res)
+static int nfs_pagein_one(struct nfs_pageio_descriptor *desc,
+			  struct nfs_pgio_header *hdr)
 {
 	struct nfs_page		*req;
 	struct page		**pages;
-	struct nfs_read_data	*data;
+	struct nfs_read_data    *data;
 	struct list_head *head = &desc->pg_list;
-	int ret = 0;
 
-	data = nfs_readdata_alloc(nfs_page_array_len(desc->pg_base,
-						     desc->pg_count));
+	data = nfs_readdata_alloc(hdr, nfs_page_array_len(desc->pg_base,
+							  desc->pg_count));
 	if (!data) {
-		nfs_async_read_error(head);
-		ret = -ENOMEM;
-		goto out;
+		nfs_pagein_error(desc, hdr);
+		return -ENOMEM;
 	}
 
-	pages = data->pagevec;
+	pages = data->pages.pagevec;
 	while (!list_empty(head)) {
 		req = nfs_list_entry(head->next);
 		nfs_list_remove_request(req);
-		nfs_list_add_request(req, &data->pages);
+		nfs_list_add_request(req, &hdr->pages);
 		*pages++ = req->wb_page;
 	}
-	req = nfs_list_entry(data->pages.next);
 
-	nfs_read_rpcsetup(req, data, desc->pg_count, 0);
-	list_add(&data->list, res);
-	desc->pg_rpc_callops = &nfs_read_full_ops;
-out:
-	return ret;
+	nfs_read_rpcsetup(data, desc->pg_count, 0);
+	list_add(&data->list, &hdr->rpc_list);
+	desc->pg_rpc_callops = &nfs_read_common_ops;
+	return 0;
 }
 
-int nfs_generic_pagein(struct nfs_pageio_descriptor *desc, struct list_head *head)
+int nfs_generic_pagein(struct nfs_pageio_descriptor *desc,
+		       struct nfs_pgio_header *hdr)
 {
 	if (desc->pg_bsize < PAGE_CACHE_SIZE)
-		return nfs_pagein_multi(desc, head);
-	return nfs_pagein_one(desc, head);
+		return nfs_pagein_multi(desc, hdr);
+	return nfs_pagein_one(desc, hdr);
 }
 
 static int nfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc)
 {
-	LIST_HEAD(head);
+	struct nfs_read_header *rhdr;
+	struct nfs_pgio_header *hdr;
 	int ret;
 
-	ret = nfs_generic_pagein(desc, &head);
+	rhdr = nfs_readhdr_alloc();
+	if (!rhdr) {
+		desc->pg_completion_ops->error_cleanup(&desc->pg_list);
+		return -ENOMEM;
+	}
+	hdr = &rhdr->header;
+	nfs_pgheader_init(desc, hdr, nfs_readhdr_free);
+	atomic_inc(&hdr->refcnt);
+	ret = nfs_generic_pagein(desc, hdr);
 	if (ret == 0)
-		ret = nfs_do_multiple_reads(&head, desc->pg_rpc_callops);
+		ret = nfs_do_multiple_reads(&hdr->rpc_list,
+					    desc->pg_rpc_callops);
+	if (atomic_dec_and_test(&hdr->refcnt))
+		hdr->completion_ops->completion(hdr);
 	return ret;
 }
 
@@ -389,20 +442,21 @@ static const struct nfs_pageio_ops nfs_pageio_read_ops = {
  */
 int nfs_readpage_result(struct rpc_task *task, struct nfs_read_data *data)
 {
+	struct inode *inode = data->header->inode;
 	int status;
 
 	dprintk("NFS: %s: %5u, (status %d)\n", __func__, task->tk_pid,
 			task->tk_status);
 
-	status = NFS_PROTO(data->inode)->read_done(task, data);
+	status = NFS_PROTO(inode)->read_done(task, data);
 	if (status != 0)
 		return status;
 
-	nfs_add_stats(data->inode, NFSIOS_SERVERREADBYTES, data->res.count);
+	nfs_add_stats(inode, NFSIOS_SERVERREADBYTES, data->res.count);
 
 	if (task->tk_status == -ESTALE) {
-		set_bit(NFS_INO_STALE, &NFS_I(data->inode)->flags);
-		nfs_mark_for_revalidate(data->inode);
+		set_bit(NFS_INO_STALE, &NFS_I(inode)->flags);
+		nfs_mark_for_revalidate(inode);
 	}
 	return 0;
 }
@@ -412,15 +466,13 @@ static void nfs_readpage_retry(struct rpc_task *task, struct nfs_read_data *data
 	struct nfs_readargs *argp = &data->args;
 	struct nfs_readres *resp = &data->res;
 
-	if (resp->eof || resp->count == argp->count)
-		return;
-
 	/* This is a short read! */
-	nfs_inc_stats(data->inode, NFSIOS_SHORTREAD);
+	nfs_inc_stats(data->header->inode, NFSIOS_SHORTREAD);
 	/* Has the server at least made some progress? */
-	if (resp->count == 0)
+	if (resp->count == 0) {
+		nfs_set_pgio_error(data->header, -EIO, argp->offset);
 		return;
-
+	}
 	/* Yes, so retry the read at the end of the data */
 	data->mds_offset += resp->count;
 	argp->offset += resp->count;
@@ -429,114 +481,46 @@ static void nfs_readpage_retry(struct rpc_task *task, struct nfs_read_data *data
 	rpc_restart_call_prepare(task);
 }
 
-/*
- * Handle a read reply that fills part of a page.
- */
-static void nfs_readpage_result_partial(struct rpc_task *task, void *calldata)
+static void nfs_readpage_result_common(struct rpc_task *task, void *calldata)
 {
 	struct nfs_read_data *data = calldata;
- 
+	struct nfs_pgio_header *hdr = data->header;
+
+	/* Note the only returns of nfs_readpage_result are 0 and -EAGAIN */
 	if (nfs_readpage_result(task, data) != 0)
 		return;
 	if (task->tk_status < 0)
-		return;
-
-	nfs_readpage_truncate_uninitialised_page(data);
-	nfs_readpage_retry(task, data);
+		nfs_set_pgio_error(hdr, task->tk_status, data->args.offset);
+	else if (data->res.eof) {
+		loff_t bound;
+
+		bound = data->args.offset + data->res.count;
+		spin_lock(&hdr->lock);
+		if (bound < hdr->io_start + hdr->good_bytes) {
+			set_bit(NFS_IOHDR_EOF, &hdr->flags);
+			clear_bit(NFS_IOHDR_ERROR, &hdr->flags);
+			hdr->good_bytes = bound - hdr->io_start;
+		}
+		spin_unlock(&hdr->lock);
+	} else if (data->res.count != data->args.count)
+		nfs_readpage_retry(task, data);
 }
 
-static void nfs_readpage_release_partial(void *calldata)
+static void nfs_readpage_release_common(void *calldata)
 {
-	struct nfs_read_data *data = calldata;
-	struct nfs_page *req = data->req;
-	struct page *page = req->wb_page;
-	int status = data->task.tk_status;
-
-	if (status < 0)
-		set_bit(PG_PARTIAL_READ_FAILED, &req->wb_flags);
-
-	if (atomic_dec_and_test(&req->wb_complete)) {
-		if (!test_bit(PG_PARTIAL_READ_FAILED, &req->wb_flags))
-			SetPageUptodate(page);
-		nfs_readpage_release(req);
-	}
 	nfs_readdata_release(calldata);
 }
 
 void nfs_read_prepare(struct rpc_task *task, void *calldata)
 {
 	struct nfs_read_data *data = calldata;
-	NFS_PROTO(data->inode)->read_rpc_prepare(task, data);
-}
-
-static const struct rpc_call_ops nfs_read_partial_ops = {
-	.rpc_call_prepare = nfs_read_prepare,
-	.rpc_call_done = nfs_readpage_result_partial,
-	.rpc_release = nfs_readpage_release_partial,
-};
-
-static void nfs_readpage_set_pages_uptodate(struct nfs_read_data *data)
-{
-	unsigned int count = data->res.count;
-	unsigned int base = data->args.pgbase;
-	struct page **pages;
-
-	if (data->res.eof)
-		count = data->args.count;
-	if (unlikely(count == 0))
-		return;
-	pages = &data->args.pages[base >> PAGE_CACHE_SHIFT];
-	base &= ~PAGE_CACHE_MASK;
-	count += base;
-	for (;count >= PAGE_CACHE_SIZE; count -= PAGE_CACHE_SIZE, pages++)
-		SetPageUptodate(*pages);
-	if (count == 0)
-		return;
-	/* Was this a short read? */
-	if (data->res.eof || data->res.count == data->args.count)
-		SetPageUptodate(*pages);
-}
-
-/*
- * This is the callback from RPC telling us whether a reply was
- * received or some error occurred (timeout or socket shutdown).
- */
-static void nfs_readpage_result_full(struct rpc_task *task, void *calldata)
-{
-	struct nfs_read_data *data = calldata;
-
-	if (nfs_readpage_result(task, data) != 0)
-		return;
-	if (task->tk_status < 0)
-		return;
-	/*
-	 * Note: nfs_readpage_retry may change the values of
-	 * data->args. In the multi-page case, we therefore need
-	 * to ensure that we call nfs_readpage_set_pages_uptodate()
-	 * first.
-	 */
-	nfs_readpage_truncate_uninitialised_page(data);
-	nfs_readpage_set_pages_uptodate(data);
-	nfs_readpage_retry(task, data);
-}
-
-static void nfs_readpage_release_full(void *calldata)
-{
-	struct nfs_read_data *data = calldata;
-
-	while (!list_empty(&data->pages)) {
-		struct nfs_page *req = nfs_list_entry(data->pages.next);
-
-		nfs_list_remove_request(req);
-		nfs_readpage_release(req);
-	}
-	nfs_readdata_release(calldata);
+	NFS_PROTO(data->header->inode)->read_rpc_prepare(task, data);
 }
 
-static const struct rpc_call_ops nfs_read_full_ops = {
+static const struct rpc_call_ops nfs_read_common_ops = {
 	.rpc_call_prepare = nfs_read_prepare,
-	.rpc_call_done = nfs_readpage_result_full,
-	.rpc_release = nfs_readpage_release_full,
+	.rpc_call_done = nfs_readpage_result_common,
+	.rpc_release = nfs_readpage_release_common,
 };
 
 /*
@@ -668,11 +652,12 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 	if (ret == 0)
 		goto read_complete; /* all pages were read */
 
-	nfs_pageio_init_read(&pgio, inode);
+	nfs_pageio_init_read(&pgio, inode, &nfs_async_read_completion_ops);
 
 	ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc);
 
 	nfs_pageio_complete(&pgio);
+	NFS_I(inode)->read_io += pgio.pg_bytes_written;
 	npages = (pgio.pg_bytes_written + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 	nfs_add_stats(inode, NFSIOS_READPAGES, npages);
 read_complete:
@@ -684,7 +669,7 @@ out:
 int __init nfs_init_readpagecache(void)
 {
 	nfs_rdata_cachep = kmem_cache_create("nfs_read_data",
-					     sizeof(struct nfs_read_data),
+					     sizeof(struct nfs_read_header),
 					     0, SLAB_HWCACHE_ALIGN,
 					     NULL);
 	if (nfs_rdata_cachep == NULL)
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 4ac7fca7e4bf..ff656c022684 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -66,6 +66,7 @@
 #include "pnfs.h"
 
 #define NFSDBG_FACILITY		NFSDBG_VFS
+#define NFS_TEXT_DATA		1
 
 #ifdef CONFIG_NFS_V3
 #define NFS_DEFAULT_VERSION 3
@@ -277,12 +278,22 @@ static match_table_t nfs_vers_tokens = {
 	{ Opt_vers_err, NULL }
 };
 
+struct nfs_mount_info {
+	void (*fill_super)(struct super_block *, struct nfs_mount_info *);
+	int (*set_security)(struct super_block *, struct dentry *, struct nfs_mount_info *);
+	struct nfs_parsed_mount_data *parsed;
+	struct nfs_clone_mount *cloned;
+	struct nfs_fh *mntfh;
+};
+
 static void nfs_umount_begin(struct super_block *);
 static int  nfs_statfs(struct dentry *, struct kstatfs *);
 static int  nfs_show_options(struct seq_file *, struct dentry *);
 static int  nfs_show_devname(struct seq_file *, struct dentry *);
 static int  nfs_show_path(struct seq_file *, struct dentry *);
 static int  nfs_show_stats(struct seq_file *, struct dentry *);
+static struct dentry *nfs_fs_mount_common(struct file_system_type *,
+		struct nfs_server *, int, const char *, struct nfs_mount_info *);
 static struct dentry *nfs_fs_mount(struct file_system_type *,
 		int, const char *, void *);
 static struct dentry *nfs_xdev_mount(struct file_system_type *fs_type,
@@ -323,12 +334,11 @@ static const struct super_operations nfs_sops = {
 };
 
 #ifdef CONFIG_NFS_V4
-static int nfs4_validate_text_mount_data(void *options,
+static void nfs4_validate_mount_flags(struct nfs_parsed_mount_data *);
+static int nfs4_validate_mount_data(void *options,
 	struct nfs_parsed_mount_data *args, const char *dev_name);
 static struct dentry *nfs4_try_mount(int flags, const char *dev_name,
-	struct nfs_parsed_mount_data *data);
-static struct dentry *nfs4_mount(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *raw_data);
+	struct nfs_mount_info *mount_info);
 static struct dentry *nfs4_remote_mount(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *raw_data);
 static struct dentry *nfs4_xdev_mount(struct file_system_type *fs_type,
@@ -342,7 +352,7 @@ static void nfs4_kill_super(struct super_block *sb);
 static struct file_system_type nfs4_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "nfs4",
-	.mount		= nfs4_mount,
+	.mount		= nfs_fs_mount,
 	.kill_sb	= nfs4_kill_super,
 	.fs_flags	= FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA,
 };
@@ -786,8 +796,8 @@ static void show_pnfs(struct seq_file *m, struct nfs_server *server)
 
 static void show_implementation_id(struct seq_file *m, struct nfs_server *nfss)
 {
-	if (nfss->nfs_client && nfss->nfs_client->impl_id) {
-		struct nfs41_impl_id *impl_id = nfss->nfs_client->impl_id;
+	if (nfss->nfs_client && nfss->nfs_client->cl_implid) {
+		struct nfs41_impl_id *impl_id = nfss->nfs_client->cl_implid;
 		seq_printf(m, "\n\timpl_id:\tname='%s',domain='%s',"
 			   "date='%llu,%u'",
 			   impl_id->name, impl_id->domain,
@@ -938,7 +948,7 @@ static void nfs_umount_begin(struct super_block *sb)
 		rpc_killall_tasks(rpc);
 }
 
-static struct nfs_parsed_mount_data *nfs_alloc_parsed_mount_data(unsigned int version)
+static struct nfs_parsed_mount_data *nfs_alloc_parsed_mount_data(void)
 {
 	struct nfs_parsed_mount_data *data;
 
@@ -953,8 +963,8 @@ static struct nfs_parsed_mount_data *nfs_alloc_parsed_mount_data(unsigned int ve
 		data->nfs_server.protocol = XPRT_TRANSPORT_TCP;
 		data->auth_flavors[0]	= RPC_AUTH_UNIX;
 		data->auth_flavor_len	= 1;
-		data->version		= version;
 		data->minorversion	= 0;
+		data->need_mount	= true;
 		data->net		= current->nsproxy->net_ns;
 		security_init_mnt_opts(&data->lsm_opts);
 	}
@@ -1674,8 +1684,8 @@ static int nfs_walk_authlist(struct nfs_parsed_mount_data *args,
  * Use the remote server's MOUNT service to request the NFS file handle
  * corresponding to the provided path.
  */
-static int nfs_try_mount(struct nfs_parsed_mount_data *args,
-			 struct nfs_fh *root_fh)
+static int nfs_request_mount(struct nfs_parsed_mount_data *args,
+			     struct nfs_fh *root_fh)
 {
 	rpc_authflavor_t server_authlist[NFS_MAX_SECFLAVORS];
 	unsigned int server_authlist_len = ARRAY_SIZE(server_authlist);
@@ -1738,6 +1748,26 @@ static int nfs_try_mount(struct nfs_parsed_mount_data *args,
 	return nfs_walk_authlist(args, &request);
 }
 
+static struct dentry *nfs_try_mount(int flags, const char *dev_name,
+				    struct nfs_mount_info *mount_info)
+{
+	int status;
+	struct nfs_server *server;
+
+	if (mount_info->parsed->need_mount) {
+		status = nfs_request_mount(mount_info->parsed, mount_info->mntfh);
+		if (status)
+			return ERR_PTR(status);
+	}
+
+	/* Get a volume representation */
+	server = nfs_create_server(mount_info->parsed, mount_info->mntfh);
+	if (IS_ERR(server))
+		return ERR_CAST(server);
+
+	return nfs_fs_mount_common(&nfs_fs_type, server, flags, dev_name, mount_info);
+}
+
 /*
  * Split "dev_name" into "hostname:export_path".
  *
@@ -1826,10 +1856,10 @@ out_path:
  * + breaking back: trying proto=udp after proto=tcp, v2 after v3,
  *   mountproto=tcp after mountproto=udp, and so on
  */
-static int nfs_validate_mount_data(void *options,
-				   struct nfs_parsed_mount_data *args,
-				   struct nfs_fh *mntfh,
-				   const char *dev_name)
+static int nfs23_validate_mount_data(void *options,
+				     struct nfs_parsed_mount_data *args,
+				     struct nfs_fh *mntfh,
+				     const char *dev_name)
 {
 	struct nfs_mount_data *data = (struct nfs_mount_data *)options;
 	struct sockaddr *sap = (struct sockaddr *)&args->nfs_server.address;
@@ -1883,6 +1913,7 @@ static int nfs_validate_mount_data(void *options,
 		args->acregmax		= data->acregmax;
 		args->acdirmin		= data->acdirmin;
 		args->acdirmax		= data->acdirmax;
+		args->need_mount	= false;
 
 		memcpy(sap, &data->addr, sizeof(data->addr));
 		args->nfs_server.addrlen = sizeof(data->addr);
@@ -1934,43 +1965,8 @@ static int nfs_validate_mount_data(void *options,
 		}
 
 		break;
-	default: {
-		int status;
-
-		if (nfs_parse_mount_options((char *)options, args) == 0)
-			return -EINVAL;
-
-		if (!nfs_verify_server_address(sap))
-			goto out_no_address;
-
-		if (args->version == 4)
-#ifdef CONFIG_NFS_V4
-			return nfs4_validate_text_mount_data(options,
-							     args, dev_name);
-#else
-			goto out_v4_not_compiled;
-#endif
-
-		nfs_set_port(sap, &args->nfs_server.port, 0);
-
-		nfs_set_mount_transport_protocol(args);
-
-		status = nfs_parse_devname(dev_name,
-					   &args->nfs_server.hostname,
-					   PAGE_SIZE,
-					   &args->nfs_server.export_path,
-					   NFS_MAXPATHLEN);
-		if (!status)
-			status = nfs_try_mount(args, mntfh);
-
-		kfree(args->nfs_server.export_path);
-		args->nfs_server.export_path = NULL;
-
-		if (status)
-			return status;
-
-		break;
-		}
+	default:
+		return NFS_TEXT_DATA;
 	}
 
 #ifndef CONFIG_NFS_V3
@@ -1999,12 +1995,6 @@ out_v3_not_compiled:
 	return -EPROTONOSUPPORT;
 #endif /* !CONFIG_NFS_V3 */
 
-#ifndef CONFIG_NFS_V4
-out_v4_not_compiled:
-	dfprintk(MOUNT, "NFS: NFSv4 is not compiled into kernel\n");
-	return -EPROTONOSUPPORT;
-#endif /* !CONFIG_NFS_V4 */
-
 out_nomem:
 	dfprintk(MOUNT, "NFS: not enough memory to handle mount options\n");
 	return -ENOMEM;
@@ -2018,6 +2008,82 @@ out_invalid_fh:
 	return -EINVAL;
 }
 
+#ifdef CONFIG_NFS_V4
+static int nfs_validate_mount_data(struct file_system_type *fs_type,
+				   void *options,
+				   struct nfs_parsed_mount_data *args,
+				   struct nfs_fh *mntfh,
+				   const char *dev_name)
+{
+	if (fs_type == &nfs_fs_type)
+		return nfs23_validate_mount_data(options, args, mntfh, dev_name);
+	return nfs4_validate_mount_data(options, args, dev_name);
+}
+#else
+static int nfs_validate_mount_data(struct file_system_type *fs_type,
+				   void *options,
+				   struct nfs_parsed_mount_data *args,
+				   struct nfs_fh *mntfh,
+				   const char *dev_name)
+{
+	return nfs23_validate_mount_data(options, args, mntfh, dev_name);
+}
+#endif
+
+static int nfs_validate_text_mount_data(void *options,
+					struct nfs_parsed_mount_data *args,
+					const char *dev_name)
+{
+	int port = 0;
+	int max_namelen = PAGE_SIZE;
+	int max_pathlen = NFS_MAXPATHLEN;
+	struct sockaddr *sap = (struct sockaddr *)&args->nfs_server.address;
+
+	if (nfs_parse_mount_options((char *)options, args) == 0)
+		return -EINVAL;
+
+	if (!nfs_verify_server_address(sap))
+		goto out_no_address;
+
+	if (args->version == 4) {
+#ifdef CONFIG_NFS_V4
+		port = NFS_PORT;
+		max_namelen = NFS4_MAXNAMLEN;
+		max_pathlen = NFS4_MAXPATHLEN;
+		nfs_validate_transport_protocol(args);
+		nfs4_validate_mount_flags(args);
+#else
+		goto out_v4_not_compiled;
+#endif /* CONFIG_NFS_V4 */
+	} else
+		nfs_set_mount_transport_protocol(args);
+
+	nfs_set_port(sap, &args->nfs_server.port, port);
+
+	if (args->auth_flavor_len > 1)
+		goto out_bad_auth;
+
+	return nfs_parse_devname(dev_name,
+				   &args->nfs_server.hostname,
+				   max_namelen,
+				   &args->nfs_server.export_path,
+				   max_pathlen);
+
+#ifndef CONFIG_NFS_V4
+out_v4_not_compiled:
+	dfprintk(MOUNT, "NFS: NFSv4 is not compiled into kernel\n");
+	return -EPROTONOSUPPORT;
+#endif /* !CONFIG_NFS_V4 */
+
+out_no_address:
+	dfprintk(MOUNT, "NFS: mount program didn't pass remote address\n");
+	return -EINVAL;
+
+out_bad_auth:
+	dfprintk(MOUNT, "NFS: Too many RPC auth flavours specified\n");
+	return -EINVAL;
+}
+
 static int
 nfs_compare_remount_data(struct nfs_server *nfss,
 			 struct nfs_parsed_mount_data *data)
@@ -2129,8 +2195,9 @@ static inline void nfs_initialise_sb(struct super_block *sb)
  * Finish setting up an NFS2/3 superblock
  */
 static void nfs_fill_super(struct super_block *sb,
-			   struct nfs_parsed_mount_data *data)
+			   struct nfs_mount_info *mount_info)
 {
+	struct nfs_parsed_mount_data *data = mount_info->parsed;
 	struct nfs_server *server = NFS_SB(sb);
 
 	sb->s_blocksize_bits = 0;
@@ -2154,8 +2221,9 @@ static void nfs_fill_super(struct super_block *sb,
  * Finish setting up a cloned NFS2/3 superblock
  */
 static void nfs_clone_super(struct super_block *sb,
-			    const struct super_block *old_sb)
+			    struct nfs_mount_info *mount_info)
 {
+	const struct super_block *old_sb = mount_info->cloned->sb;
 	struct nfs_server *server = NFS_SB(sb);
 
 	sb->s_blocksize_bits = old_sb->s_blocksize_bits;
@@ -2278,52 +2346,70 @@ static int nfs_compare_super(struct super_block *sb, void *data)
 	return nfs_compare_mount_options(sb, server, mntflags);
 }
 
+#ifdef CONFIG_NFS_FSCACHE
+static void nfs_get_cache_cookie(struct super_block *sb,
+				 struct nfs_parsed_mount_data *parsed,
+				 struct nfs_clone_mount *cloned)
+{
+	char *uniq = NULL;
+	int ulen = 0;
+
+	if (parsed && parsed->fscache_uniq) {
+		uniq = parsed->fscache_uniq;
+		ulen = strlen(parsed->fscache_uniq);
+	} else if (cloned) {
+		struct nfs_server *mnt_s = NFS_SB(cloned->sb);
+		if (mnt_s->fscache_key) {
+			uniq = mnt_s->fscache_key->key.uniquifier;
+			ulen = mnt_s->fscache_key->key.uniq_len;
+		};
+	}
+
+	nfs_fscache_get_super_cookie(sb, uniq, ulen);
+}
+#else
+static void nfs_get_cache_cookie(struct super_block *sb,
+				 struct nfs_parsed_mount_data *parsed,
+				 struct nfs_clone_mount *cloned)
+{
+}
+#endif
+
 static int nfs_bdi_register(struct nfs_server *server)
 {
 	return bdi_register_dev(&server->backing_dev_info, server->s_dev);
 }
 
-static struct dentry *nfs_fs_mount(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *raw_data)
+static int nfs_set_sb_security(struct super_block *s, struct dentry *mntroot,
+			       struct nfs_mount_info *mount_info)
+{
+	return security_sb_set_mnt_opts(s, &mount_info->parsed->lsm_opts);
+}
+
+static int nfs_clone_sb_security(struct super_block *s, struct dentry *mntroot,
+				 struct nfs_mount_info *mount_info)
+{
+	/* clone any lsm security options from the parent to the new sb */
+	security_sb_clone_mnt_opts(mount_info->cloned->sb, s);
+	if (mntroot->d_inode->i_op != NFS_SB(s)->nfs_client->rpc_ops->dir_inode_ops)
+		return -ESTALE;
+	return 0;
+}
+
+static struct dentry *nfs_fs_mount_common(struct file_system_type *fs_type,
+					  struct nfs_server *server,
+					  int flags, const char *dev_name,
+					  struct nfs_mount_info *mount_info)
 {
-	struct nfs_server *server = NULL;
 	struct super_block *s;
-	struct nfs_parsed_mount_data *data;
-	struct nfs_fh *mntfh;
 	struct dentry *mntroot = ERR_PTR(-ENOMEM);
 	int (*compare_super)(struct super_block *, void *) = nfs_compare_super;
 	struct nfs_sb_mountdata sb_mntdata = {
 		.mntflags = flags,
+		.server = server,
 	};
 	int error;
 
-	data = nfs_alloc_parsed_mount_data(NFS_DEFAULT_VERSION);
-	mntfh = nfs_alloc_fhandle();
-	if (data == NULL || mntfh == NULL)
-		goto out;
-
-	/* Validate the mount data */
-	error = nfs_validate_mount_data(raw_data, data, mntfh, dev_name);
-	if (error < 0) {
-		mntroot = ERR_PTR(error);
-		goto out;
-	}
-
-#ifdef CONFIG_NFS_V4
-	if (data->version == 4) {
-		mntroot = nfs4_try_mount(flags, dev_name, data);
-		goto out;
-	}
-#endif	/* CONFIG_NFS_V4 */
-
-	/* Get a volume representation */
-	server = nfs_create_server(data, mntfh);
-	if (IS_ERR(server)) {
-		mntroot = ERR_CAST(server);
-		goto out;
-	}
-	sb_mntdata.server = server;
-
 	if (server->flags & NFS_MOUNT_UNSHARED)
 		compare_super = NULL;
 
@@ -2351,23 +2437,21 @@ static struct dentry *nfs_fs_mount(struct file_system_type *fs_type,
 
 	if (!s->s_root) {
 		/* initial superblock/root creation */
-		nfs_fill_super(s, data);
-		nfs_fscache_get_super_cookie(s, data->fscache_uniq, NULL);
+		mount_info->fill_super(s, mount_info);
+		nfs_get_cache_cookie(s, mount_info->parsed, mount_info->cloned);
 	}
 
-	mntroot = nfs_get_root(s, mntfh, dev_name);
+	mntroot = nfs_get_root(s, mount_info->mntfh, dev_name);
 	if (IS_ERR(mntroot))
 		goto error_splat_super;
 
-	error = security_sb_set_mnt_opts(s, &data->lsm_opts);
+	error = mount_info->set_security(s, mntroot, mount_info);
 	if (error)
 		goto error_splat_root;
 
 	s->s_flags |= MS_ACTIVE;
 
 out:
-	nfs_free_parsed_mount_data(data);
-	nfs_free_fhandle(mntfh);
 	return mntroot;
 
 out_err_nosb:
@@ -2385,6 +2469,43 @@ error_splat_bdi:
 	goto out;
 }
 
+static struct dentry *nfs_fs_mount(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *raw_data)
+{
+	struct nfs_mount_info mount_info = {
+		.fill_super = nfs_fill_super,
+		.set_security = nfs_set_sb_security,
+	};
+	struct dentry *mntroot = ERR_PTR(-ENOMEM);
+	int error;
+
+	mount_info.parsed = nfs_alloc_parsed_mount_data();
+	mount_info.mntfh = nfs_alloc_fhandle();
+	if (mount_info.parsed == NULL || mount_info.mntfh == NULL)
+		goto out;
+
+	/* Validate the mount data */
+	error = nfs_validate_mount_data(fs_type, raw_data, mount_info.parsed, mount_info.mntfh, dev_name);
+	if (error == NFS_TEXT_DATA)
+		error = nfs_validate_text_mount_data(raw_data, mount_info.parsed, dev_name);
+	if (error < 0) {
+		mntroot = ERR_PTR(error);
+		goto out;
+	}
+
+#ifdef CONFIG_NFS_V4
+	if (mount_info.parsed->version == 4)
+		mntroot = nfs4_try_mount(flags, dev_name, &mount_info);
+	else
+#endif	/* CONFIG_NFS_V4 */
+		mntroot = nfs_try_mount(flags, dev_name, &mount_info);
+
+out:
+	nfs_free_parsed_mount_data(mount_info.parsed);
+	nfs_free_fhandle(mount_info.mntfh);
+	return mntroot;
+}
+
 /*
  * Ensure that we unregister the bdi before kill_anon_super
  * releases the device name
@@ -2409,93 +2530,51 @@ static void nfs_kill_super(struct super_block *s)
 }
 
 /*
- * Clone an NFS2/3 server record on xdev traversal (FSID-change)
+ * Clone an NFS2/3/4 server record on xdev traversal (FSID-change)
  */
 static struct dentry *
-nfs_xdev_mount(struct file_system_type *fs_type, int flags,
-		const char *dev_name, void *raw_data)
+nfs_xdev_mount_common(struct file_system_type *fs_type, int flags,
+		const char *dev_name, struct nfs_mount_info *mount_info)
 {
-	struct nfs_clone_mount *data = raw_data;
-	struct super_block *s;
+	struct nfs_clone_mount *data = mount_info->cloned;
 	struct nfs_server *server;
-	struct dentry *mntroot;
-	int (*compare_super)(struct super_block *, void *) = nfs_compare_super;
-	struct nfs_sb_mountdata sb_mntdata = {
-		.mntflags = flags,
-	};
+	struct dentry *mntroot = ERR_PTR(-ENOMEM);
 	int error;
 
-	dprintk("--> nfs_xdev_mount()\n");
+	dprintk("--> nfs_xdev_mount_common()\n");
+
+	mount_info->mntfh = data->fh;
 
 	/* create a new volume representation */
 	server = nfs_clone_server(NFS_SB(data->sb), data->fh, data->fattr, data->authflavor);
 	if (IS_ERR(server)) {
 		error = PTR_ERR(server);
-		goto out_err_noserver;
-	}
-	sb_mntdata.server = server;
-
-	if (server->flags & NFS_MOUNT_UNSHARED)
-		compare_super = NULL;
-
-	/* -o noac implies -o sync */
-	if (server->flags & NFS_MOUNT_NOAC)
-		sb_mntdata.mntflags |= MS_SYNCHRONOUS;
-
-	/* Get a superblock - note that we may end up sharing one that already exists */
-	s = sget(&nfs_fs_type, compare_super, nfs_set_super, &sb_mntdata);
-	if (IS_ERR(s)) {
-		error = PTR_ERR(s);
-		goto out_err_nosb;
-	}
-
-	if (s->s_fs_info != server) {
-		nfs_free_server(server);
-		server = NULL;
-	} else {
-		error = nfs_bdi_register(server);
-		if (error)
-			goto error_splat_bdi;
-	}
-
-	if (!s->s_root) {
-		/* initial superblock/root creation */
-		nfs_clone_super(s, data->sb);
-		nfs_fscache_get_super_cookie(s, NULL, data);
-	}
-
-	mntroot = nfs_get_root(s, data->fh, dev_name);
-	if (IS_ERR(mntroot)) {
-		error = PTR_ERR(mntroot);
-		goto error_splat_super;
-	}
-	if (mntroot->d_inode->i_op != NFS_SB(s)->nfs_client->rpc_ops->dir_inode_ops) {
-		dput(mntroot);
-		error = -ESTALE;
-		goto error_splat_super;
+		goto out_err;
 	}
 
-	s->s_flags |= MS_ACTIVE;
-
-	/* clone any lsm security options from the parent to the new sb */
-	security_sb_clone_mnt_opts(data->sb, s);
-
-	dprintk("<-- nfs_xdev_mount() = 0\n");
+	mntroot = nfs_fs_mount_common(fs_type, server, flags, dev_name, mount_info);
+	dprintk("<-- nfs_xdev_mount_common() = 0\n");
+out:
 	return mntroot;
 
-out_err_nosb:
-	nfs_free_server(server);
-out_err_noserver:
-	dprintk("<-- nfs_xdev_mount() = %d [error]\n", error);
-	return ERR_PTR(error);
+out_err:
+	dprintk("<-- nfs_xdev_mount_common() = %d [error]\n", error);
+	goto out;
+}
 
-error_splat_super:
-	if (server && !s->s_root)
-		bdi_unregister(&server->backing_dev_info);
-error_splat_bdi:
-	deactivate_locked_super(s);
-	dprintk("<-- nfs_xdev_mount() = %d [splat]\n", error);
-	return ERR_PTR(error);
+/*
+ * Clone an NFS2/3 server record on xdev traversal (FSID-change)
+ */
+static struct dentry *
+nfs_xdev_mount(struct file_system_type *fs_type, int flags,
+		const char *dev_name, void *raw_data)
+{
+	struct nfs_mount_info mount_info = {
+		.fill_super = nfs_clone_super,
+		.set_security = nfs_clone_sb_security,
+		.cloned   = raw_data,
+	};
+	return nfs_xdev_mount_common(&nfs_fs_type, flags, dev_name, &mount_info);
 }
 
 #ifdef CONFIG_NFS_V4
@@ -2504,8 +2583,9 @@ error_splat_bdi:
  * Finish setting up a cloned NFS4 superblock
  */
 static void nfs4_clone_super(struct super_block *sb,
-			    const struct super_block *old_sb)
+			     struct nfs_mount_info *mount_info)
 {
+	const struct super_block *old_sb = mount_info->cloned->sb;
 	sb->s_blocksize_bits = old_sb->s_blocksize_bits;
 	sb->s_blocksize = old_sb->s_blocksize;
 	sb->s_maxbytes = old_sb->s_maxbytes;
@@ -2523,7 +2603,8 @@ static void nfs4_clone_super(struct super_block *sb,
 /*
  * Set up an NFS4 superblock
  */
-static void nfs4_fill_super(struct super_block *sb)
+static void nfs4_fill_super(struct super_block *sb,
+			    struct nfs_mount_info *mount_info)
 {
 	sb->s_time_gran = 1;
 	sb->s_op = &nfs4_sops;
@@ -2542,37 +2623,6 @@ static void nfs4_validate_mount_flags(struct nfs_parsed_mount_data *args)
 			 NFS_MOUNT_LOCAL_FLOCK|NFS_MOUNT_LOCAL_FCNTL);
 }
 
-static int nfs4_validate_text_mount_data(void *options,
-					 struct nfs_parsed_mount_data *args,
-					 const char *dev_name)
-{
-	struct sockaddr *sap = (struct sockaddr *)&args->nfs_server.address;
-
-	nfs_set_port(sap, &args->nfs_server.port, NFS_PORT);
-
-	nfs_validate_transport_protocol(args);
-
-	nfs4_validate_mount_flags(args);
-
-	if (args->version != 4) {
-		dfprintk(MOUNT,
-			 "NFS4: Illegal mount version\n");
-		return -EINVAL;
-	}
-
-	if (args->auth_flavor_len > 1) {
-		dfprintk(MOUNT,
-			 "NFS4: Too many RPC auth flavours specified\n");
-		return -EINVAL;
-	}
-
-	return nfs_parse_devname(dev_name,
-				   &args->nfs_server.hostname,
-				   NFS4_MAXNAMLEN,
-				   &args->nfs_server.export_path,
-				   NFS4_MAXPATHLEN);
-}
-
 /*
  * Validate NFSv4 mount options
  */
@@ -2643,13 +2693,7 @@ static int nfs4_validate_mount_data(void *options,
 
 		break;
 	default:
-		if (nfs_parse_mount_options((char *)options, args) == 0)
-			return -EINVAL;
-
-		if (!nfs_verify_server_address(sap))
-			return -EINVAL;
-
-		return nfs4_validate_text_mount_data(options, args, dev_name);
+		return NFS_TEXT_DATA;
 	}
 
 	return 0;
@@ -2673,91 +2717,26 @@ out_no_address:
  */
 static struct dentry *
 nfs4_remote_mount(struct file_system_type *fs_type, int flags,
-		  const char *dev_name, void *raw_data)
+		  const char *dev_name, void *info)
 {
-	struct nfs_parsed_mount_data *data = raw_data;
-	struct super_block *s;
+	struct nfs_mount_info *mount_info = info;
 	struct nfs_server *server;
-	struct nfs_fh *mntfh;
-	struct dentry *mntroot;
-	int (*compare_super)(struct super_block *, void *) = nfs_compare_super;
-	struct nfs_sb_mountdata sb_mntdata = {
-		.mntflags = flags,
-	};
-	int error = -ENOMEM;
+	struct dentry *mntroot = ERR_PTR(-ENOMEM);
 
-	mntfh = nfs_alloc_fhandle();
-	if (data == NULL || mntfh == NULL)
-		goto out;
+	mount_info->fill_super = nfs4_fill_super;
+	mount_info->set_security = nfs_set_sb_security;
 
 	/* Get a volume representation */
-	server = nfs4_create_server(data, mntfh);
+	server = nfs4_create_server(mount_info->parsed, mount_info->mntfh);
 	if (IS_ERR(server)) {
-		error = PTR_ERR(server);
+		mntroot = ERR_CAST(server);
 		goto out;
 	}
-	sb_mntdata.server = server;
 
-	if (server->flags & NFS4_MOUNT_UNSHARED)
-		compare_super = NULL;
-
-	/* -o noac implies -o sync */
-	if (server->flags & NFS_MOUNT_NOAC)
-		sb_mntdata.mntflags |= MS_SYNCHRONOUS;
-
-	/* Get a superblock - note that we may end up sharing one that already exists */
-	s = sget(&nfs4_fs_type, compare_super, nfs_set_super, &sb_mntdata);
-	if (IS_ERR(s)) {
-		error = PTR_ERR(s);
-		goto out_free;
-	}
-
-	if (s->s_fs_info != server) {
-		nfs_free_server(server);
-		server = NULL;
-	} else {
-		error = nfs_bdi_register(server);
-		if (error)
-			goto error_splat_bdi;
-	}
-
-	if (!s->s_root) {
-		/* initial superblock/root creation */
-		nfs4_fill_super(s);
-		nfs_fscache_get_super_cookie(s, data->fscache_uniq, NULL);
-	}
-
-	mntroot = nfs4_get_root(s, mntfh, dev_name);
-	if (IS_ERR(mntroot)) {
-		error = PTR_ERR(mntroot);
-		goto error_splat_super;
-	}
-
-	error = security_sb_set_mnt_opts(s, &data->lsm_opts);
-	if (error)
-		goto error_splat_root;
-
-	s->s_flags |= MS_ACTIVE;
-
-	nfs_free_fhandle(mntfh);
-	return mntroot;
+	mntroot = nfs_fs_mount_common(fs_type, server, flags, dev_name, mount_info);
 
 out:
-	nfs_free_fhandle(mntfh);
-	return ERR_PTR(error);
-
-out_free:
-	nfs_free_server(server);
-	goto out;
-
-error_splat_root:
-	dput(mntroot);
-error_splat_super:
-	if (server && !s->s_root)
-		bdi_unregister(&server->backing_dev_info);
-error_splat_bdi:
-	deactivate_locked_super(s);
-	goto out;
+	return mntroot;
 }
 
 static struct vfsmount *nfs_do_root_mount(struct file_system_type *fs_type,
@@ -2869,17 +2848,18 @@ static struct dentry *nfs_follow_remote_path(struct vfsmount *root_mnt,
 }
 
 static struct dentry *nfs4_try_mount(int flags, const char *dev_name,
-			 struct nfs_parsed_mount_data *data)
+			 struct nfs_mount_info *mount_info)
 {
 	char *export_path;
 	struct vfsmount *root_mnt;
 	struct dentry *res;
+	struct nfs_parsed_mount_data *data = mount_info->parsed;
 
 	dfprintk(MOUNT, "--> nfs4_try_mount()\n");
 
 	export_path = data->nfs_server.export_path;
 	data->nfs_server.export_path = "/";
-	root_mnt = nfs_do_root_mount(&nfs4_remote_fs_type, flags, data,
+	root_mnt = nfs_do_root_mount(&nfs4_remote_fs_type, flags, mount_info,
 			data->nfs_server.hostname);
 	data->nfs_server.export_path = export_path;
 
@@ -2891,38 +2871,6 @@ static struct dentry *nfs4_try_mount(int flags, const char *dev_name,
 	return res;
 }
 
-/*
- * Get the superblock for an NFS4 mountpoint
- */
-static struct dentry *nfs4_mount(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *raw_data)
-{
-	struct nfs_parsed_mount_data *data;
-	int error = -ENOMEM;
-	struct dentry *res = ERR_PTR(-ENOMEM);
-
-	data = nfs_alloc_parsed_mount_data(4);
-	if (data == NULL)
-		goto out;
-
-	/* Validate the mount data */
-	error = nfs4_validate_mount_data(raw_data, data, dev_name);
-	if (error < 0) {
-		res = ERR_PTR(error);
-		goto out;
-	}
-
-	res = nfs4_try_mount(flags, dev_name, data);
-	if (IS_ERR(res))
-		error = PTR_ERR(res);
-
-out:
-	nfs_free_parsed_mount_data(data);
-	dprintk("<-- nfs4_mount() = %d%s\n", error,
-			error != 0 ? " [error]" : "");
-	return res;
-}
-
 static void nfs4_kill_super(struct super_block *sb)
 {
 	struct nfs_server *server = NFS_SB(sb);
@@ -2942,181 +2890,43 @@ static struct dentry *
 nfs4_xdev_mount(struct file_system_type *fs_type, int flags,
 		 const char *dev_name, void *raw_data)
 {
-	struct nfs_clone_mount *data = raw_data;
-	struct super_block *s;
-	struct nfs_server *server;
-	struct dentry *mntroot;
-	int (*compare_super)(struct super_block *, void *) = nfs_compare_super;
-	struct nfs_sb_mountdata sb_mntdata = {
-		.mntflags = flags,
+	struct nfs_mount_info mount_info = {
+		.fill_super = nfs4_clone_super,
+		.set_security = nfs_clone_sb_security,
+		.cloned = raw_data,
 	};
-	int error;
-
-	dprintk("--> nfs4_xdev_mount()\n");
-
-	/* create a new volume representation */
-	server = nfs_clone_server(NFS_SB(data->sb), data->fh, data->fattr, data->authflavor);
-	if (IS_ERR(server)) {
-		error = PTR_ERR(server);
-		goto out_err_noserver;
-	}
-	sb_mntdata.server = server;
-
-	if (server->flags & NFS4_MOUNT_UNSHARED)
-		compare_super = NULL;
-
-	/* -o noac implies -o sync */
-	if (server->flags & NFS_MOUNT_NOAC)
-		sb_mntdata.mntflags |= MS_SYNCHRONOUS;
-
-	/* Get a superblock - note that we may end up sharing one that already exists */
-	s = sget(&nfs4_fs_type, compare_super, nfs_set_super, &sb_mntdata);
-	if (IS_ERR(s)) {
-		error = PTR_ERR(s);
-		goto out_err_nosb;
-	}
-
-	if (s->s_fs_info != server) {
-		nfs_free_server(server);
-		server = NULL;
-	} else {
-		error = nfs_bdi_register(server);
-		if (error)
-			goto error_splat_bdi;
-	}
-
-	if (!s->s_root) {
-		/* initial superblock/root creation */
-		nfs4_clone_super(s, data->sb);
-		nfs_fscache_get_super_cookie(s, NULL, data);
-	}
-
-	mntroot = nfs4_get_root(s, data->fh, dev_name);
-	if (IS_ERR(mntroot)) {
-		error = PTR_ERR(mntroot);
-		goto error_splat_super;
-	}
-	if (mntroot->d_inode->i_op != NFS_SB(s)->nfs_client->rpc_ops->dir_inode_ops) {
-		dput(mntroot);
-		error = -ESTALE;
-		goto error_splat_super;
-	}
-
-	s->s_flags |= MS_ACTIVE;
-
-	security_sb_clone_mnt_opts(data->sb, s);
-
-	dprintk("<-- nfs4_xdev_mount() = 0\n");
-	return mntroot;
-
-out_err_nosb:
-	nfs_free_server(server);
-out_err_noserver:
-	dprintk("<-- nfs4_xdev_mount() = %d [error]\n", error);
-	return ERR_PTR(error);
-
-error_splat_super:
-	if (server && !s->s_root)
-		bdi_unregister(&server->backing_dev_info);
-error_splat_bdi:
-	deactivate_locked_super(s);
-	dprintk("<-- nfs4_xdev_mount() = %d [splat]\n", error);
-	return ERR_PTR(error);
+	return nfs_xdev_mount_common(&nfs4_fs_type, flags, dev_name, &mount_info);
 }
 
 static struct dentry *
 nfs4_remote_referral_mount(struct file_system_type *fs_type, int flags,
 			   const char *dev_name, void *raw_data)
 {
-	struct nfs_clone_mount *data = raw_data;
-	struct super_block *s;
-	struct nfs_server *server;
-	struct dentry *mntroot;
-	struct nfs_fh *mntfh;
-	int (*compare_super)(struct super_block *, void *) = nfs_compare_super;
-	struct nfs_sb_mountdata sb_mntdata = {
-		.mntflags = flags,
+	struct nfs_mount_info mount_info = {
+		.fill_super = nfs4_fill_super,
+		.set_security = nfs_clone_sb_security,
+		.cloned = raw_data,
 	};
-	int error = -ENOMEM;
+	struct nfs_server *server;
+	struct dentry *mntroot = ERR_PTR(-ENOMEM);
 
 	dprintk("--> nfs4_referral_get_sb()\n");
 
-	mntfh = nfs_alloc_fhandle();
-	if (mntfh == NULL)
-		goto out_err_nofh;
+	mount_info.mntfh = nfs_alloc_fhandle();
+	if (mount_info.cloned == NULL || mount_info.mntfh == NULL)
+		goto out;
 
 	/* create a new volume representation */
-	server = nfs4_create_referral_server(data, mntfh);
+	server = nfs4_create_referral_server(mount_info.cloned, mount_info.mntfh);
 	if (IS_ERR(server)) {
-		error = PTR_ERR(server);
-		goto out_err_noserver;
-	}
-	sb_mntdata.server = server;
-
-	if (server->flags & NFS4_MOUNT_UNSHARED)
-		compare_super = NULL;
-
-	/* -o noac implies -o sync */
-	if (server->flags & NFS_MOUNT_NOAC)
-		sb_mntdata.mntflags |= MS_SYNCHRONOUS;
-
-	/* Get a superblock - note that we may end up sharing one that already exists */
-	s = sget(&nfs4_fs_type, compare_super, nfs_set_super, &sb_mntdata);
-	if (IS_ERR(s)) {
-		error = PTR_ERR(s);
-		goto out_err_nosb;
-	}
-
-	if (s->s_fs_info != server) {
-		nfs_free_server(server);
-		server = NULL;
-	} else {
-		error = nfs_bdi_register(server);
-		if (error)
-			goto error_splat_bdi;
-	}
-
-	if (!s->s_root) {
-		/* initial superblock/root creation */
-		nfs4_fill_super(s);
-		nfs_fscache_get_super_cookie(s, NULL, data);
-	}
-
-	mntroot = nfs4_get_root(s, mntfh, dev_name);
-	if (IS_ERR(mntroot)) {
-		error = PTR_ERR(mntroot);
-		goto error_splat_super;
-	}
-	if (mntroot->d_inode->i_op != NFS_SB(s)->nfs_client->rpc_ops->dir_inode_ops) {
-		dput(mntroot);
-		error = -ESTALE;
-		goto error_splat_super;
+		mntroot = ERR_CAST(server);
+		goto out;
 	}
 
-	s->s_flags |= MS_ACTIVE;
-
-	security_sb_clone_mnt_opts(data->sb, s);
-
-	nfs_free_fhandle(mntfh);
-	dprintk("<-- nfs4_referral_get_sb() = 0\n");
+	mntroot = nfs_fs_mount_common(&nfs4_fs_type, server, flags, dev_name, &mount_info);
+out:
+	nfs_free_fhandle(mount_info.mntfh);
 	return mntroot;
-
-out_err_nosb:
-	nfs_free_server(server);
-out_err_noserver:
-	nfs_free_fhandle(mntfh);
-out_err_nofh:
-	dprintk("<-- nfs4_referral_get_sb() = %d [error]\n", error);
-	return ERR_PTR(error);
-
-error_splat_super:
-	if (server && !s->s_root)
-		bdi_unregister(&server->backing_dev_info);
-error_splat_bdi:
-	deactivate_locked_super(s);
-	nfs_free_fhandle(mntfh);
-	dprintk("<-- nfs4_referral_get_sb() = %d [splat]\n", error);
-	return ERR_PTR(error);
 }
 
 /*
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index c07462320f6b..e6fe3d69d14c 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -39,20 +39,20 @@
 /*
  * Local function declarations
  */
-static void nfs_pageio_init_write(struct nfs_pageio_descriptor *desc,
-				  struct inode *inode, int ioflags);
 static void nfs_redirty_request(struct nfs_page *req);
-static const struct rpc_call_ops nfs_write_partial_ops;
-static const struct rpc_call_ops nfs_write_full_ops;
+static const struct rpc_call_ops nfs_write_common_ops;
 static const struct rpc_call_ops nfs_commit_ops;
+static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops;
+static const struct nfs_commit_completion_ops nfs_commit_completion_ops;
 
 static struct kmem_cache *nfs_wdata_cachep;
 static mempool_t *nfs_wdata_mempool;
+static struct kmem_cache *nfs_cdata_cachep;
 static mempool_t *nfs_commit_mempool;
 
-struct nfs_write_data *nfs_commitdata_alloc(void)
+struct nfs_commit_data *nfs_commitdata_alloc(void)
 {
-	struct nfs_write_data *p = mempool_alloc(nfs_commit_mempool, GFP_NOFS);
+	struct nfs_commit_data *p = mempool_alloc(nfs_commit_mempool, GFP_NOFS);
 
 	if (p) {
 		memset(p, 0, sizeof(*p));
@@ -62,46 +62,73 @@ struct nfs_write_data *nfs_commitdata_alloc(void)
 }
 EXPORT_SYMBOL_GPL(nfs_commitdata_alloc);
 
-void nfs_commit_free(struct nfs_write_data *p)
+void nfs_commit_free(struct nfs_commit_data *p)
 {
-	if (p && (p->pagevec != &p->page_array[0]))
-		kfree(p->pagevec);
 	mempool_free(p, nfs_commit_mempool);
 }
 EXPORT_SYMBOL_GPL(nfs_commit_free);
 
-struct nfs_write_data *nfs_writedata_alloc(unsigned int pagecount)
+struct nfs_write_header *nfs_writehdr_alloc(void)
 {
-	struct nfs_write_data *p = mempool_alloc(nfs_wdata_mempool, GFP_NOFS);
+	struct nfs_write_header *p = mempool_alloc(nfs_wdata_mempool, GFP_NOFS);
 
 	if (p) {
+		struct nfs_pgio_header *hdr = &p->header;
+
 		memset(p, 0, sizeof(*p));
-		INIT_LIST_HEAD(&p->pages);
-		p->npages = pagecount;
-		if (pagecount <= ARRAY_SIZE(p->page_array))
-			p->pagevec = p->page_array;
-		else {
-			p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_NOFS);
-			if (!p->pagevec) {
-				mempool_free(p, nfs_wdata_mempool);
-				p = NULL;
-			}
-		}
+		INIT_LIST_HEAD(&hdr->pages);
+		INIT_LIST_HEAD(&hdr->rpc_list);
+		spin_lock_init(&hdr->lock);
+		atomic_set(&hdr->refcnt, 0);
 	}
 	return p;
 }
 
-void nfs_writedata_free(struct nfs_write_data *p)
+static struct nfs_write_data *nfs_writedata_alloc(struct nfs_pgio_header *hdr,
+						  unsigned int pagecount)
+{
+	struct nfs_write_data *data, *prealloc;
+
+	prealloc = &container_of(hdr, struct nfs_write_header, header)->rpc_data;
+	if (prealloc->header == NULL)
+		data = prealloc;
+	else
+		data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		goto out;
+
+	if (nfs_pgarray_set(&data->pages, pagecount)) {
+		data->header = hdr;
+		atomic_inc(&hdr->refcnt);
+	} else {
+		if (data != prealloc)
+			kfree(data);
+		data = NULL;
+	}
+out:
+	return data;
+}
+
+void nfs_writehdr_free(struct nfs_pgio_header *hdr)
 {
-	if (p && (p->pagevec != &p->page_array[0]))
-		kfree(p->pagevec);
-	mempool_free(p, nfs_wdata_mempool);
+	struct nfs_write_header *whdr = container_of(hdr, struct nfs_write_header, header);
+	mempool_free(whdr, nfs_wdata_mempool);
 }
 
 void nfs_writedata_release(struct nfs_write_data *wdata)
 {
+	struct nfs_pgio_header *hdr = wdata->header;
+	struct nfs_write_header *write_header = container_of(hdr, struct nfs_write_header, header);
+
 	put_nfs_open_context(wdata->args.context);
-	nfs_writedata_free(wdata);
+	if (wdata->pages.pagevec != wdata->pages.page_array)
+		kfree(wdata->pages.pagevec);
+	if (wdata != &write_header->rpc_data)
+		kfree(wdata);
+	else
+		wdata->header = NULL;
+	if (atomic_dec_and_test(&hdr->refcnt))
+		hdr->completion_ops->completion(hdr);
 }
 
 static void nfs_context_set_write_error(struct nfs_open_context *ctx, int error)
@@ -203,7 +230,6 @@ static int nfs_set_page_writeback(struct page *page)
 		struct inode *inode = page->mapping->host;
 		struct nfs_server *nfss = NFS_SERVER(inode);
 
-		page_cache_get(page);
 		if (atomic_long_inc_return(&nfss->writeback) >
 				NFS_CONGESTION_ON_THRESH) {
 			set_bdi_congested(&nfss->backing_dev_info,
@@ -219,7 +245,6 @@ static void nfs_end_page_writeback(struct page *page)
 	struct nfs_server *nfss = NFS_SERVER(inode);
 
 	end_page_writeback(page);
-	page_cache_release(page);
 	if (atomic_long_dec_return(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH)
 		clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC);
 }
@@ -235,10 +260,10 @@ static struct nfs_page *nfs_find_and_lock_request(struct page *page, bool nonblo
 		req = nfs_page_find_request_locked(page);
 		if (req == NULL)
 			break;
-		if (nfs_lock_request_dontget(req))
+		if (nfs_lock_request(req))
 			break;
 		/* Note: If we hold the page lock, as is the case in nfs_writepage,
-		 *	 then the call to nfs_lock_request_dontget() will always
+		 *	 then the call to nfs_lock_request() will always
 		 *	 succeed provided that someone hasn't already marked the
 		 *	 request as dirty (in which case we don't care).
 		 */
@@ -310,7 +335,8 @@ static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc
 	struct nfs_pageio_descriptor pgio;
 	int err;
 
-	nfs_pageio_init_write(&pgio, page->mapping->host, wb_priority(wbc));
+	nfs_pageio_init_write(&pgio, page->mapping->host, wb_priority(wbc),
+			      &nfs_async_write_completion_ops);
 	err = nfs_do_writepage(page, wbc, &pgio);
 	nfs_pageio_complete(&pgio);
 	if (err < 0)
@@ -353,7 +379,8 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
 
 	nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES);
 
-	nfs_pageio_init_write(&pgio, inode, wb_priority(wbc));
+	nfs_pageio_init_write(&pgio, inode, wb_priority(wbc),
+			      &nfs_async_write_completion_ops);
 	err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio);
 	nfs_pageio_complete(&pgio);
 
@@ -379,7 +406,7 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
 	struct nfs_inode *nfsi = NFS_I(inode);
 
 	/* Lock the request! */
-	nfs_lock_request_dontget(req);
+	nfs_lock_request(req);
 
 	spin_lock(&inode->i_lock);
 	if (!nfsi->npages && nfs_have_delegation(inode, FMODE_WRITE))
@@ -421,65 +448,88 @@ nfs_mark_request_dirty(struct nfs_page *req)
 /**
  * nfs_request_add_commit_list - add request to a commit list
  * @req: pointer to a struct nfs_page
- * @head: commit list head
+ * @dst: commit list head
+ * @cinfo: holds list lock and accounting info
  *
- * This sets the PG_CLEAN bit, updates the inode global count of
+ * This sets the PG_CLEAN bit, updates the cinfo count of
  * number of outstanding requests requiring a commit as well as
  * the MM page stats.
  *
- * The caller must _not_ hold the inode->i_lock, but must be
+ * The caller must _not_ hold the cinfo->lock, but must be
  * holding the nfs_page lock.
  */
 void
-nfs_request_add_commit_list(struct nfs_page *req, struct list_head *head)
+nfs_request_add_commit_list(struct nfs_page *req, struct list_head *dst,
+			    struct nfs_commit_info *cinfo)
 {
-	struct inode *inode = req->wb_context->dentry->d_inode;
-
 	set_bit(PG_CLEAN, &(req)->wb_flags);
-	spin_lock(&inode->i_lock);
-	nfs_list_add_request(req, head);
-	NFS_I(inode)->ncommit++;
-	spin_unlock(&inode->i_lock);
-	inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
-	inc_bdi_stat(req->wb_page->mapping->backing_dev_info, BDI_RECLAIMABLE);
-	__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
+	spin_lock(cinfo->lock);
+	nfs_list_add_request(req, dst);
+	cinfo->mds->ncommit++;
+	spin_unlock(cinfo->lock);
+	if (!cinfo->dreq) {
+		inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
+		inc_bdi_stat(req->wb_page->mapping->backing_dev_info,
+			     BDI_RECLAIMABLE);
+		__mark_inode_dirty(req->wb_context->dentry->d_inode,
+				   I_DIRTY_DATASYNC);
+	}
 }
 EXPORT_SYMBOL_GPL(nfs_request_add_commit_list);
 
 /**
  * nfs_request_remove_commit_list - Remove request from a commit list
  * @req: pointer to a nfs_page
+ * @cinfo: holds list lock and accounting info
  *
- * This clears the PG_CLEAN bit, and updates the inode global count of
+ * This clears the PG_CLEAN bit, and updates the cinfo's count of
  * number of outstanding requests requiring a commit
  * It does not update the MM page stats.
  *
- * The caller _must_ hold the inode->i_lock and the nfs_page lock.
+ * The caller _must_ hold the cinfo->lock and the nfs_page lock.
  */
 void
-nfs_request_remove_commit_list(struct nfs_page *req)
+nfs_request_remove_commit_list(struct nfs_page *req,
+			       struct nfs_commit_info *cinfo)
 {
-	struct inode *inode = req->wb_context->dentry->d_inode;
-
 	if (!test_and_clear_bit(PG_CLEAN, &(req)->wb_flags))
 		return;
 	nfs_list_remove_request(req);
-	NFS_I(inode)->ncommit--;
+	cinfo->mds->ncommit--;
 }
 EXPORT_SYMBOL_GPL(nfs_request_remove_commit_list);
 
+static void nfs_init_cinfo_from_inode(struct nfs_commit_info *cinfo,
+				      struct inode *inode)
+{
+	cinfo->lock = &inode->i_lock;
+	cinfo->mds = &NFS_I(inode)->commit_info;
+	cinfo->ds = pnfs_get_ds_info(inode);
+	cinfo->dreq = NULL;
+	cinfo->completion_ops = &nfs_commit_completion_ops;
+}
+
+void nfs_init_cinfo(struct nfs_commit_info *cinfo,
+		    struct inode *inode,
+		    struct nfs_direct_req *dreq)
+{
+	if (dreq)
+		nfs_init_cinfo_from_dreq(cinfo, dreq);
+	else
+		nfs_init_cinfo_from_inode(cinfo, inode);
+}
+EXPORT_SYMBOL_GPL(nfs_init_cinfo);
 
 /*
  * Add a request to the inode's commit list.
  */
-static void
-nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg)
+void
+nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg,
+			struct nfs_commit_info *cinfo)
 {
-	struct inode *inode = req->wb_context->dentry->d_inode;
-
-	if (pnfs_mark_request_commit(req, lseg))
+	if (pnfs_mark_request_commit(req, lseg, cinfo))
 		return;
-	nfs_request_add_commit_list(req, &NFS_I(inode)->commit_list);
+	nfs_request_add_commit_list(req, &cinfo->mds->list, cinfo);
 }
 
 static void
@@ -494,11 +544,13 @@ nfs_clear_request_commit(struct nfs_page *req)
 {
 	if (test_bit(PG_CLEAN, &req->wb_flags)) {
 		struct inode *inode = req->wb_context->dentry->d_inode;
+		struct nfs_commit_info cinfo;
 
-		if (!pnfs_clear_request_commit(req)) {
-			spin_lock(&inode->i_lock);
-			nfs_request_remove_commit_list(req);
-			spin_unlock(&inode->i_lock);
+		nfs_init_cinfo_from_inode(&cinfo, inode);
+		if (!pnfs_clear_request_commit(req, &cinfo)) {
+			spin_lock(cinfo.lock);
+			nfs_request_remove_commit_list(req, &cinfo);
+			spin_unlock(cinfo.lock);
 		}
 		nfs_clear_page_commit(req->wb_page);
 	}
@@ -508,28 +560,25 @@ static inline
 int nfs_write_need_commit(struct nfs_write_data *data)
 {
 	if (data->verf.committed == NFS_DATA_SYNC)
-		return data->lseg == NULL;
-	else
-		return data->verf.committed != NFS_FILE_SYNC;
+		return data->header->lseg == NULL;
+	return data->verf.committed != NFS_FILE_SYNC;
 }
 
-static inline
-int nfs_reschedule_unstable_write(struct nfs_page *req,
-				  struct nfs_write_data *data)
+#else
+static void nfs_init_cinfo_from_inode(struct nfs_commit_info *cinfo,
+				      struct inode *inode)
 {
-	if (test_and_clear_bit(PG_NEED_COMMIT, &req->wb_flags)) {
-		nfs_mark_request_commit(req, data->lseg);
-		return 1;
-	}
-	if (test_and_clear_bit(PG_NEED_RESCHED, &req->wb_flags)) {
-		nfs_mark_request_dirty(req);
-		return 1;
-	}
-	return 0;
 }
-#else
-static void
-nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg)
+
+void nfs_init_cinfo(struct nfs_commit_info *cinfo,
+		    struct inode *inode,
+		    struct nfs_direct_req *dreq)
+{
+}
+
+void
+nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg,
+			struct nfs_commit_info *cinfo)
 {
 }
 
@@ -544,25 +593,57 @@ int nfs_write_need_commit(struct nfs_write_data *data)
 	return 0;
 }
 
-static inline
-int nfs_reschedule_unstable_write(struct nfs_page *req,
-				  struct nfs_write_data *data)
+#endif
+
+static void nfs_write_completion(struct nfs_pgio_header *hdr)
 {
-	return 0;
+	struct nfs_commit_info cinfo;
+	unsigned long bytes = 0;
+
+	if (test_bit(NFS_IOHDR_REDO, &hdr->flags))
+		goto out;
+	nfs_init_cinfo_from_inode(&cinfo, hdr->inode);
+	while (!list_empty(&hdr->pages)) {
+		struct nfs_page *req = nfs_list_entry(hdr->pages.next);
+
+		bytes += req->wb_bytes;
+		nfs_list_remove_request(req);
+		if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) &&
+		    (hdr->good_bytes < bytes)) {
+			nfs_set_pageerror(req->wb_page);
+			nfs_context_set_write_error(req->wb_context, hdr->error);
+			goto remove_req;
+		}
+		if (test_bit(NFS_IOHDR_NEED_RESCHED, &hdr->flags)) {
+			nfs_mark_request_dirty(req);
+			goto next;
+		}
+		if (test_bit(NFS_IOHDR_NEED_COMMIT, &hdr->flags)) {
+			nfs_mark_request_commit(req, hdr->lseg, &cinfo);
+			goto next;
+		}
+remove_req:
+		nfs_inode_remove_request(req);
+next:
+		nfs_unlock_request(req);
+		nfs_end_page_writeback(req->wb_page);
+		nfs_release_request(req);
+	}
+out:
+	hdr->release(hdr);
 }
-#endif
 
 #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
-static int
-nfs_need_commit(struct nfs_inode *nfsi)
+static unsigned long
+nfs_reqs_to_commit(struct nfs_commit_info *cinfo)
 {
-	return nfsi->ncommit > 0;
+	return cinfo->mds->ncommit;
 }
 
-/* i_lock held by caller */
-static int
-nfs_scan_commit_list(struct list_head *src, struct list_head *dst, int max,
-		spinlock_t *lock)
+/* cinfo->lock held by caller */
+int
+nfs_scan_commit_list(struct list_head *src, struct list_head *dst,
+		     struct nfs_commit_info *cinfo, int max)
 {
 	struct nfs_page *req, *tmp;
 	int ret = 0;
@@ -570,12 +651,13 @@ nfs_scan_commit_list(struct list_head *src, struct list_head *dst, int max,
 	list_for_each_entry_safe(req, tmp, src, wb_list) {
 		if (!nfs_lock_request(req))
 			continue;
-		if (cond_resched_lock(lock))
+		kref_get(&req->wb_kref);
+		if (cond_resched_lock(cinfo->lock))
 			list_safe_reset_next(req, tmp, wb_list);
-		nfs_request_remove_commit_list(req);
+		nfs_request_remove_commit_list(req, cinfo);
 		nfs_list_add_request(req, dst);
 		ret++;
-		if (ret == max)
+		if ((ret == max) && !cinfo->dreq)
 			break;
 	}
 	return ret;
@@ -584,37 +666,38 @@ nfs_scan_commit_list(struct list_head *src, struct list_head *dst, int max,
 /*
  * nfs_scan_commit - Scan an inode for commit requests
  * @inode: NFS inode to scan
- * @dst: destination list
+ * @dst: mds destination list
+ * @cinfo: mds and ds lists of reqs ready to commit
  *
  * Moves requests from the inode's 'commit' request list.
  * The requests are *not* checked to ensure that they form a contiguous set.
  */
-static int
-nfs_scan_commit(struct inode *inode, struct list_head *dst)
+int
+nfs_scan_commit(struct inode *inode, struct list_head *dst,
+		struct nfs_commit_info *cinfo)
 {
-	struct nfs_inode *nfsi = NFS_I(inode);
 	int ret = 0;
 
-	spin_lock(&inode->i_lock);
-	if (nfsi->ncommit > 0) {
+	spin_lock(cinfo->lock);
+	if (cinfo->mds->ncommit > 0) {
 		const int max = INT_MAX;
 
-		ret = nfs_scan_commit_list(&nfsi->commit_list, dst, max,
-				&inode->i_lock);
-		ret += pnfs_scan_commit_lists(inode, max - ret,
-				&inode->i_lock);
+		ret = nfs_scan_commit_list(&cinfo->mds->list, dst,
+					   cinfo, max);
+		ret += pnfs_scan_commit_lists(inode, cinfo, max - ret);
 	}
-	spin_unlock(&inode->i_lock);
+	spin_unlock(cinfo->lock);
 	return ret;
 }
 
 #else
-static inline int nfs_need_commit(struct nfs_inode *nfsi)
+static unsigned long nfs_reqs_to_commit(struct nfs_commit_info *cinfo)
 {
 	return 0;
 }
 
-static inline int nfs_scan_commit(struct inode *inode, struct list_head *dst)
+int nfs_scan_commit(struct inode *inode, struct list_head *dst,
+		    struct nfs_commit_info *cinfo)
 {
 	return 0;
 }
@@ -659,7 +742,7 @@ static struct nfs_page *nfs_try_to_update_request(struct inode *inode,
 		    || end < req->wb_offset)
 			goto out_flushme;
 
-		if (nfs_lock_request_dontget(req))
+		if (nfs_lock_request(req))
 			break;
 
 		/* The request is locked, so wait and then retry */
@@ -729,7 +812,7 @@ static int nfs_writepage_setup(struct nfs_open_context *ctx, struct page *page,
 	nfs_grow_file(page, offset, count);
 	nfs_mark_uptodate(page, req->wb_pgbase, req->wb_bytes);
 	nfs_mark_request_dirty(req);
-	nfs_unlock_request(req);
+	nfs_unlock_and_release_request(req);
 	return 0;
 }
 
@@ -766,10 +849,14 @@ int nfs_flush_incompatible(struct file *file, struct page *page)
  * the PageUptodate() flag. In this case, we will need to turn off
  * write optimisations that depend on the page contents being correct.
  */
-static int nfs_write_pageuptodate(struct page *page, struct inode *inode)
+static bool nfs_write_pageuptodate(struct page *page, struct inode *inode)
 {
-	return PageUptodate(page) &&
-		!(NFS_I(inode)->cache_validity & (NFS_INO_REVAL_PAGECACHE|NFS_INO_INVALID_DATA));
+	if (nfs_have_delegated_attributes(inode))
+		goto out;
+	if (NFS_I(inode)->cache_validity & NFS_INO_REVAL_PAGECACHE)
+		return false;
+out:
+	return PageUptodate(page) != 0;
 }
 
 /*
@@ -815,17 +902,6 @@ int nfs_updatepage(struct file *file, struct page *page,
 	return status;
 }
 
-static void nfs_writepage_release(struct nfs_page *req,
-				  struct nfs_write_data *data)
-{
-	struct page *page = req->wb_page;
-
-	if (PageError(req->wb_page) || !nfs_reschedule_unstable_write(req, data))
-		nfs_inode_remove_request(req);
-	nfs_unlock_request(req);
-	nfs_end_page_writeback(page);
-}
-
 static int flush_task_priority(int how)
 {
 	switch (how & (FLUSH_HIGHPRI|FLUSH_LOWPRI)) {
@@ -837,18 +913,18 @@ static int flush_task_priority(int how)
 	return RPC_PRIORITY_NORMAL;
 }
 
-int nfs_initiate_write(struct nfs_write_data *data,
-		       struct rpc_clnt *clnt,
+int nfs_initiate_write(struct rpc_clnt *clnt,
+		       struct nfs_write_data *data,
 		       const struct rpc_call_ops *call_ops,
-		       int how)
+		       int how, int flags)
 {
-	struct inode *inode = data->inode;
+	struct inode *inode = data->header->inode;
 	int priority = flush_task_priority(how);
 	struct rpc_task *task;
 	struct rpc_message msg = {
 		.rpc_argp = &data->args,
 		.rpc_resp = &data->res,
-		.rpc_cred = data->cred,
+		.rpc_cred = data->header->cred,
 	};
 	struct rpc_task_setup task_setup_data = {
 		.rpc_client = clnt,
@@ -857,7 +933,7 @@ int nfs_initiate_write(struct nfs_write_data *data,
 		.callback_ops = call_ops,
 		.callback_data = data,
 		.workqueue = nfsiod_workqueue,
-		.flags = RPC_TASK_ASYNC,
+		.flags = RPC_TASK_ASYNC | flags,
 		.priority = priority,
 	};
 	int ret = 0;
@@ -892,26 +968,21 @@ EXPORT_SYMBOL_GPL(nfs_initiate_write);
 /*
  * Set up the argument/result storage required for the RPC call.
  */
-static void nfs_write_rpcsetup(struct nfs_page *req,
-		struct nfs_write_data *data,
+static void nfs_write_rpcsetup(struct nfs_write_data *data,
 		unsigned int count, unsigned int offset,
-		int how)
+		int how, struct nfs_commit_info *cinfo)
 {
-	struct inode *inode = req->wb_context->dentry->d_inode;
+	struct nfs_page *req = data->header->req;
 
 	/* Set up the RPC argument and reply structs
 	 * NB: take care not to mess about with data->commit et al. */
 
-	data->req = req;
-	data->inode = inode = req->wb_context->dentry->d_inode;
-	data->cred = req->wb_context->cred;
-
-	data->args.fh     = NFS_FH(inode);
+	data->args.fh     = NFS_FH(data->header->inode);
 	data->args.offset = req_offset(req) + offset;
 	/* pnfs_set_layoutcommit needs this */
 	data->mds_offset = data->args.offset;
 	data->args.pgbase = req->wb_pgbase + offset;
-	data->args.pages  = data->pagevec;
+	data->args.pages  = data->pages.pagevec;
 	data->args.count  = count;
 	data->args.context = get_nfs_open_context(req->wb_context);
 	data->args.lock_context = req->wb_lock_context;
@@ -920,7 +991,7 @@ static void nfs_write_rpcsetup(struct nfs_page *req,
 	case 0:
 		break;
 	case FLUSH_COND_STABLE:
-		if (nfs_need_commit(NFS_I(inode)))
+		if (nfs_reqs_to_commit(cinfo))
 			break;
 	default:
 		data->args.stable = NFS_FILE_SYNC;
@@ -936,9 +1007,9 @@ static int nfs_do_write(struct nfs_write_data *data,
 		const struct rpc_call_ops *call_ops,
 		int how)
 {
-	struct inode *inode = data->args.context->dentry->d_inode;
+	struct inode *inode = data->header->inode;
 
-	return nfs_initiate_write(data, NFS_CLIENT(inode), call_ops, how);
+	return nfs_initiate_write(NFS_CLIENT(inode), data, call_ops, how, 0);
 }
 
 static int nfs_do_multiple_writes(struct list_head *head,
@@ -951,7 +1022,7 @@ static int nfs_do_multiple_writes(struct list_head *head,
 	while (!list_empty(head)) {
 		int ret2;
 
-		data = list_entry(head->next, struct nfs_write_data, list);
+		data = list_first_entry(head, struct nfs_write_data, list);
 		list_del_init(&data->list);
 		
 		ret2 = nfs_do_write(data, call_ops, how);
@@ -967,31 +1038,60 @@ static int nfs_do_multiple_writes(struct list_head *head,
  */
 static void nfs_redirty_request(struct nfs_page *req)
 {
-	struct page *page = req->wb_page;
-
 	nfs_mark_request_dirty(req);
 	nfs_unlock_request(req);
-	nfs_end_page_writeback(page);
+	nfs_end_page_writeback(req->wb_page);
+	nfs_release_request(req);
+}
+
+static void nfs_async_write_error(struct list_head *head)
+{
+	struct nfs_page	*req;
+
+	while (!list_empty(head)) {
+		req = nfs_list_entry(head->next);
+		nfs_list_remove_request(req);
+		nfs_redirty_request(req);
+	}
+}
+
+static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops = {
+	.error_cleanup = nfs_async_write_error,
+	.completion = nfs_write_completion,
+};
+
+static void nfs_flush_error(struct nfs_pageio_descriptor *desc,
+		struct nfs_pgio_header *hdr)
+{
+	set_bit(NFS_IOHDR_REDO, &hdr->flags);
+	while (!list_empty(&hdr->rpc_list)) {
+		struct nfs_write_data *data = list_first_entry(&hdr->rpc_list,
+				struct nfs_write_data, list);
+		list_del(&data->list);
+		nfs_writedata_release(data);
+	}
+	desc->pg_completion_ops->error_cleanup(&desc->pg_list);
 }
 
 /*
  * Generate multiple small requests to write out a single
  * contiguous dirty area on one page.
  */
-static int nfs_flush_multi(struct nfs_pageio_descriptor *desc, struct list_head *res)
+static int nfs_flush_multi(struct nfs_pageio_descriptor *desc,
+			   struct nfs_pgio_header *hdr)
 {
-	struct nfs_page *req = nfs_list_entry(desc->pg_list.next);
+	struct nfs_page *req = hdr->req;
 	struct page *page = req->wb_page;
 	struct nfs_write_data *data;
 	size_t wsize = desc->pg_bsize, nbytes;
 	unsigned int offset;
 	int requests = 0;
-	int ret = 0;
+	struct nfs_commit_info cinfo;
 
-	nfs_list_remove_request(req);
+	nfs_init_cinfo(&cinfo, desc->pg_inode, desc->pg_dreq);
 
 	if ((desc->pg_ioflags & FLUSH_COND_STABLE) &&
-	    (desc->pg_moreio || NFS_I(desc->pg_inode)->ncommit ||
+	    (desc->pg_moreio || nfs_reqs_to_commit(&cinfo) ||
 	     desc->pg_count > wsize))
 		desc->pg_ioflags &= ~FLUSH_COND_STABLE;
 
@@ -1001,28 +1101,22 @@ static int nfs_flush_multi(struct nfs_pageio_descriptor *desc, struct list_head
 	do {
 		size_t len = min(nbytes, wsize);
 
-		data = nfs_writedata_alloc(1);
-		if (!data)
-			goto out_bad;
-		data->pagevec[0] = page;
-		nfs_write_rpcsetup(req, data, len, offset, desc->pg_ioflags);
-		list_add(&data->list, res);
+		data = nfs_writedata_alloc(hdr, 1);
+		if (!data) {
+			nfs_flush_error(desc, hdr);
+			return -ENOMEM;
+		}
+		data->pages.pagevec[0] = page;
+		nfs_write_rpcsetup(data, len, offset, desc->pg_ioflags, &cinfo);
+		list_add(&data->list, &hdr->rpc_list);
 		requests++;
 		nbytes -= len;
 		offset += len;
 	} while (nbytes != 0);
-	atomic_set(&req->wb_complete, requests);
-	desc->pg_rpc_callops = &nfs_write_partial_ops;
-	return ret;
-
-out_bad:
-	while (!list_empty(res)) {
-		data = list_entry(res->next, struct nfs_write_data, list);
-		list_del(&data->list);
-		nfs_writedata_release(data);
-	}
-	nfs_redirty_request(req);
-	return -ENOMEM;
+	nfs_list_remove_request(req);
+	nfs_list_add_request(req, &hdr->pages);
+	desc->pg_rpc_callops = &nfs_write_common_ops;
+	return 0;
 }
 
 /*
@@ -1033,62 +1127,71 @@ out_bad:
  * This is the case if nfs_updatepage detects a conflicting request
  * that has been written but not committed.
  */
-static int nfs_flush_one(struct nfs_pageio_descriptor *desc, struct list_head *res)
+static int nfs_flush_one(struct nfs_pageio_descriptor *desc,
+			 struct nfs_pgio_header *hdr)
 {
 	struct nfs_page		*req;
 	struct page		**pages;
 	struct nfs_write_data	*data;
 	struct list_head *head = &desc->pg_list;
-	int ret = 0;
+	struct nfs_commit_info cinfo;
 
-	data = nfs_writedata_alloc(nfs_page_array_len(desc->pg_base,
-						      desc->pg_count));
+	data = nfs_writedata_alloc(hdr, nfs_page_array_len(desc->pg_base,
+							   desc->pg_count));
 	if (!data) {
-		while (!list_empty(head)) {
-			req = nfs_list_entry(head->next);
-			nfs_list_remove_request(req);
-			nfs_redirty_request(req);
-		}
-		ret = -ENOMEM;
-		goto out;
+		nfs_flush_error(desc, hdr);
+		return -ENOMEM;
 	}
-	pages = data->pagevec;
+
+	nfs_init_cinfo(&cinfo, desc->pg_inode, desc->pg_dreq);
+	pages = data->pages.pagevec;
 	while (!list_empty(head)) {
 		req = nfs_list_entry(head->next);
 		nfs_list_remove_request(req);
-		nfs_list_add_request(req, &data->pages);
+		nfs_list_add_request(req, &hdr->pages);
 		*pages++ = req->wb_page;
 	}
-	req = nfs_list_entry(data->pages.next);
 
 	if ((desc->pg_ioflags & FLUSH_COND_STABLE) &&
-	    (desc->pg_moreio || NFS_I(desc->pg_inode)->ncommit))
+	    (desc->pg_moreio || nfs_reqs_to_commit(&cinfo)))
 		desc->pg_ioflags &= ~FLUSH_COND_STABLE;
 
 	/* Set up the argument struct */
-	nfs_write_rpcsetup(req, data, desc->pg_count, 0, desc->pg_ioflags);
-	list_add(&data->list, res);
-	desc->pg_rpc_callops = &nfs_write_full_ops;
-out:
-	return ret;
+	nfs_write_rpcsetup(data, desc->pg_count, 0, desc->pg_ioflags, &cinfo);
+	list_add(&data->list, &hdr->rpc_list);
+	desc->pg_rpc_callops = &nfs_write_common_ops;
+	return 0;
 }
 
-int nfs_generic_flush(struct nfs_pageio_descriptor *desc, struct list_head *head)
+int nfs_generic_flush(struct nfs_pageio_descriptor *desc,
+		      struct nfs_pgio_header *hdr)
 {
 	if (desc->pg_bsize < PAGE_CACHE_SIZE)
-		return nfs_flush_multi(desc, head);
-	return nfs_flush_one(desc, head);
+		return nfs_flush_multi(desc, hdr);
+	return nfs_flush_one(desc, hdr);
 }
 
 static int nfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc)
 {
-	LIST_HEAD(head);
+	struct nfs_write_header *whdr;
+	struct nfs_pgio_header *hdr;
 	int ret;
 
-	ret = nfs_generic_flush(desc, &head);
+	whdr = nfs_writehdr_alloc();
+	if (!whdr) {
+		desc->pg_completion_ops->error_cleanup(&desc->pg_list);
+		return -ENOMEM;
+	}
+	hdr = &whdr->header;
+	nfs_pgheader_init(desc, hdr, nfs_writehdr_free);
+	atomic_inc(&hdr->refcnt);
+	ret = nfs_generic_flush(desc, hdr);
 	if (ret == 0)
-		ret = nfs_do_multiple_writes(&head, desc->pg_rpc_callops,
-				desc->pg_ioflags);
+		ret = nfs_do_multiple_writes(&hdr->rpc_list,
+					     desc->pg_rpc_callops,
+					     desc->pg_ioflags);
+	if (atomic_dec_and_test(&hdr->refcnt))
+		hdr->completion_ops->completion(hdr);
 	return ret;
 }
 
@@ -1098,9 +1201,10 @@ static const struct nfs_pageio_ops nfs_pageio_write_ops = {
 };
 
 void nfs_pageio_init_write_mds(struct nfs_pageio_descriptor *pgio,
-				  struct inode *inode, int ioflags)
+			       struct inode *inode, int ioflags,
+			       const struct nfs_pgio_completion_ops *compl_ops)
 {
-	nfs_pageio_init(pgio, inode, &nfs_pageio_write_ops,
+	nfs_pageio_init(pgio, inode, &nfs_pageio_write_ops, compl_ops,
 				NFS_SERVER(inode)->wsize, ioflags);
 }
 
@@ -1111,80 +1215,27 @@ void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio)
 }
 EXPORT_SYMBOL_GPL(nfs_pageio_reset_write_mds);
 
-static void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio,
-				  struct inode *inode, int ioflags)
+void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio,
+			   struct inode *inode, int ioflags,
+			   const struct nfs_pgio_completion_ops *compl_ops)
 {
-	if (!pnfs_pageio_init_write(pgio, inode, ioflags))
-		nfs_pageio_init_write_mds(pgio, inode, ioflags);
+	if (!pnfs_pageio_init_write(pgio, inode, ioflags, compl_ops))
+		nfs_pageio_init_write_mds(pgio, inode, ioflags, compl_ops);
 }
 
-/*
- * Handle a write reply that flushed part of a page.
- */
-static void nfs_writeback_done_partial(struct rpc_task *task, void *calldata)
+void nfs_write_prepare(struct rpc_task *task, void *calldata)
 {
-	struct nfs_write_data	*data = calldata;
-
-	dprintk("NFS: %5u write(%s/%lld %d@%lld)",
-		task->tk_pid,
-		data->req->wb_context->dentry->d_inode->i_sb->s_id,
-		(long long)
-		  NFS_FILEID(data->req->wb_context->dentry->d_inode),
-		data->req->wb_bytes, (long long)req_offset(data->req));
-
-	nfs_writeback_done(task, data);
+	struct nfs_write_data *data = calldata;
+	NFS_PROTO(data->header->inode)->write_rpc_prepare(task, data);
 }
 
-static void nfs_writeback_release_partial(void *calldata)
+void nfs_commit_prepare(struct rpc_task *task, void *calldata)
 {
-	struct nfs_write_data	*data = calldata;
-	struct nfs_page		*req = data->req;
-	struct page		*page = req->wb_page;
-	int status = data->task.tk_status;
+	struct nfs_commit_data *data = calldata;
 
-	if (status < 0) {
-		nfs_set_pageerror(page);
-		nfs_context_set_write_error(req->wb_context, status);
-		dprintk(", error = %d\n", status);
-		goto out;
-	}
-
-	if (nfs_write_need_commit(data)) {
-		struct inode *inode = page->mapping->host;
-
-		spin_lock(&inode->i_lock);
-		if (test_bit(PG_NEED_RESCHED, &req->wb_flags)) {
-			/* Do nothing we need to resend the writes */
-		} else if (!test_and_set_bit(PG_NEED_COMMIT, &req->wb_flags)) {
-			memcpy(&req->wb_verf, &data->verf, sizeof(req->wb_verf));
-			dprintk(" defer commit\n");
-		} else if (memcmp(&req->wb_verf, &data->verf, sizeof(req->wb_verf))) {
-			set_bit(PG_NEED_RESCHED, &req->wb_flags);
-			clear_bit(PG_NEED_COMMIT, &req->wb_flags);
-			dprintk(" server reboot detected\n");
-		}
-		spin_unlock(&inode->i_lock);
-	} else
-		dprintk(" OK\n");
-
-out:
-	if (atomic_dec_and_test(&req->wb_complete))
-		nfs_writepage_release(req, data);
-	nfs_writedata_release(calldata);
+	NFS_PROTO(data->inode)->commit_rpc_prepare(task, data);
 }
 
-void nfs_write_prepare(struct rpc_task *task, void *calldata)
-{
-	struct nfs_write_data *data = calldata;
-	NFS_PROTO(data->inode)->write_rpc_prepare(task, data);
-}
-
-static const struct rpc_call_ops nfs_write_partial_ops = {
-	.rpc_call_prepare = nfs_write_prepare,
-	.rpc_call_done = nfs_writeback_done_partial,
-	.rpc_release = nfs_writeback_release_partial,
-};
-
 /*
  * Handle a write reply that flushes a whole page.
  *
@@ -1192,59 +1243,37 @@ static const struct rpc_call_ops nfs_write_partial_ops = {
  *	  writebacks since the page->count is kept > 1 for as long
  *	  as the page has a write request pending.
  */
-static void nfs_writeback_done_full(struct rpc_task *task, void *calldata)
+static void nfs_writeback_done_common(struct rpc_task *task, void *calldata)
 {
 	struct nfs_write_data	*data = calldata;
 
 	nfs_writeback_done(task, data);
 }
 
-static void nfs_writeback_release_full(void *calldata)
+static void nfs_writeback_release_common(void *calldata)
 {
 	struct nfs_write_data	*data = calldata;
+	struct nfs_pgio_header *hdr = data->header;
 	int status = data->task.tk_status;
+	struct nfs_page *req = hdr->req;
 
-	/* Update attributes as result of writeback. */
-	while (!list_empty(&data->pages)) {
-		struct nfs_page *req = nfs_list_entry(data->pages.next);
-		struct page *page = req->wb_page;
-
-		nfs_list_remove_request(req);
-
-		dprintk("NFS: %5u write (%s/%lld %d@%lld)",
-			data->task.tk_pid,
-			req->wb_context->dentry->d_inode->i_sb->s_id,
-			(long long)NFS_FILEID(req->wb_context->dentry->d_inode),
-			req->wb_bytes,
-			(long long)req_offset(req));
-
-		if (status < 0) {
-			nfs_set_pageerror(page);
-			nfs_context_set_write_error(req->wb_context, status);
-			dprintk(", error = %d\n", status);
-			goto remove_request;
-		}
-
-		if (nfs_write_need_commit(data)) {
+	if ((status >= 0) && nfs_write_need_commit(data)) {
+		spin_lock(&hdr->lock);
+		if (test_bit(NFS_IOHDR_NEED_RESCHED, &hdr->flags))
+			; /* Do nothing */
+		else if (!test_and_set_bit(NFS_IOHDR_NEED_COMMIT, &hdr->flags))
 			memcpy(&req->wb_verf, &data->verf, sizeof(req->wb_verf));
-			nfs_mark_request_commit(req, data->lseg);
-			dprintk(" marked for commit\n");
-			goto next;
-		}
-		dprintk(" OK\n");
-remove_request:
-		nfs_inode_remove_request(req);
-	next:
-		nfs_unlock_request(req);
-		nfs_end_page_writeback(page);
+		else if (memcmp(&req->wb_verf, &data->verf, sizeof(req->wb_verf)))
+			set_bit(NFS_IOHDR_NEED_RESCHED, &hdr->flags);
+		spin_unlock(&hdr->lock);
 	}
-	nfs_writedata_release(calldata);
+	nfs_writedata_release(data);
 }
 
-static const struct rpc_call_ops nfs_write_full_ops = {
+static const struct rpc_call_ops nfs_write_common_ops = {
 	.rpc_call_prepare = nfs_write_prepare,
-	.rpc_call_done = nfs_writeback_done_full,
-	.rpc_release = nfs_writeback_release_full,
+	.rpc_call_done = nfs_writeback_done_common,
+	.rpc_release = nfs_writeback_release_common,
 };
 
 
@@ -1255,6 +1284,7 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data)
 {
 	struct nfs_writeargs	*argp = &data->args;
 	struct nfs_writeres	*resp = &data->res;
+	struct inode		*inode = data->header->inode;
 	int status;
 
 	dprintk("NFS: %5u nfs_writeback_done (status %d)\n",
@@ -1267,10 +1297,10 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data)
 	 * another writer had changed the file, but some applications
 	 * depend on tighter cache coherency when writing.
 	 */
-	status = NFS_PROTO(data->inode)->write_done(task, data);
+	status = NFS_PROTO(inode)->write_done(task, data);
 	if (status != 0)
 		return;
-	nfs_add_stats(data->inode, NFSIOS_SERVERWRITTENBYTES, resp->count);
+	nfs_add_stats(inode, NFSIOS_SERVERWRITTENBYTES, resp->count);
 
 #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
 	if (resp->verf->committed < argp->stable && task->tk_status >= 0) {
@@ -1288,46 +1318,47 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data)
 		if (time_before(complain, jiffies)) {
 			dprintk("NFS:       faulty NFS server %s:"
 				" (committed = %d) != (stable = %d)\n",
-				NFS_SERVER(data->inode)->nfs_client->cl_hostname,
+				NFS_SERVER(inode)->nfs_client->cl_hostname,
 				resp->verf->committed, argp->stable);
 			complain = jiffies + 300 * HZ;
 		}
 	}
 #endif
-	/* Is this a short write? */
-	if (task->tk_status >= 0 && resp->count < argp->count) {
+	if (task->tk_status < 0)
+		nfs_set_pgio_error(data->header, task->tk_status, argp->offset);
+	else if (resp->count < argp->count) {
 		static unsigned long    complain;
 
-		nfs_inc_stats(data->inode, NFSIOS_SHORTWRITE);
+		/* This a short write! */
+		nfs_inc_stats(inode, NFSIOS_SHORTWRITE);
 
 		/* Has the server at least made some progress? */
-		if (resp->count != 0) {
-			/* Was this an NFSv2 write or an NFSv3 stable write? */
-			if (resp->verf->committed != NFS_UNSTABLE) {
-				/* Resend from where the server left off */
-				data->mds_offset += resp->count;
-				argp->offset += resp->count;
-				argp->pgbase += resp->count;
-				argp->count -= resp->count;
-			} else {
-				/* Resend as a stable write in order to avoid
-				 * headaches in the case of a server crash.
-				 */
-				argp->stable = NFS_FILE_SYNC;
+		if (resp->count == 0) {
+			if (time_before(complain, jiffies)) {
+				printk(KERN_WARNING
+				       "NFS: Server wrote zero bytes, expected %u.\n",
+				       argp->count);
+				complain = jiffies + 300 * HZ;
 			}
-			rpc_restart_call_prepare(task);
+			nfs_set_pgio_error(data->header, -EIO, argp->offset);
+			task->tk_status = -EIO;
 			return;
 		}
-		if (time_before(complain, jiffies)) {
-			printk(KERN_WARNING
-			       "NFS: Server wrote zero bytes, expected %u.\n",
-					argp->count);
-			complain = jiffies + 300 * HZ;
+		/* Was this an NFSv2 write or an NFSv3 stable write? */
+		if (resp->verf->committed != NFS_UNSTABLE) {
+			/* Resend from where the server left off */
+			data->mds_offset += resp->count;
+			argp->offset += resp->count;
+			argp->pgbase += resp->count;
+			argp->count -= resp->count;
+		} else {
+			/* Resend as a stable write in order to avoid
+			 * headaches in the case of a server crash.
+			 */
+			argp->stable = NFS_FILE_SYNC;
 		}
-		/* Can't do anything about it except throw an error. */
-		task->tk_status = -EIO;
+		rpc_restart_call_prepare(task);
 	}
-	return;
 }
 
 
@@ -1347,26 +1378,23 @@ static int nfs_commit_set_lock(struct nfs_inode *nfsi, int may_wait)
 	return (ret < 0) ? ret : 1;
 }
 
-void nfs_commit_clear_lock(struct nfs_inode *nfsi)
+static void nfs_commit_clear_lock(struct nfs_inode *nfsi)
 {
 	clear_bit(NFS_INO_COMMIT, &nfsi->flags);
 	smp_mb__after_clear_bit();
 	wake_up_bit(&nfsi->flags, NFS_INO_COMMIT);
 }
-EXPORT_SYMBOL_GPL(nfs_commit_clear_lock);
 
-void nfs_commitdata_release(void *data)
+void nfs_commitdata_release(struct nfs_commit_data *data)
 {
-	struct nfs_write_data *wdata = data;
-
-	put_nfs_open_context(wdata->args.context);
-	nfs_commit_free(wdata);
+	put_nfs_open_context(data->context);
+	nfs_commit_free(data);
 }
 EXPORT_SYMBOL_GPL(nfs_commitdata_release);
 
-int nfs_initiate_commit(struct nfs_write_data *data, struct rpc_clnt *clnt,
+int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data,
 			const struct rpc_call_ops *call_ops,
-			int how)
+			int how, int flags)
 {
 	struct rpc_task *task;
 	int priority = flush_task_priority(how);
@@ -1382,7 +1410,7 @@ int nfs_initiate_commit(struct nfs_write_data *data, struct rpc_clnt *clnt,
 		.callback_ops = call_ops,
 		.callback_data = data,
 		.workqueue = nfsiod_workqueue,
-		.flags = RPC_TASK_ASYNC,
+		.flags = RPC_TASK_ASYNC | flags,
 		.priority = priority,
 	};
 	/* Set up the initial task struct.  */
@@ -1403,9 +1431,10 @@ EXPORT_SYMBOL_GPL(nfs_initiate_commit);
 /*
  * Set up the argument/result storage required for the RPC call.
  */
-void nfs_init_commit(struct nfs_write_data *data,
-			    struct list_head *head,
-			    struct pnfs_layout_segment *lseg)
+void nfs_init_commit(struct nfs_commit_data *data,
+		     struct list_head *head,
+		     struct pnfs_layout_segment *lseg,
+		     struct nfs_commit_info *cinfo)
 {
 	struct nfs_page *first = nfs_list_entry(head->next);
 	struct inode *inode = first->wb_context->dentry->d_inode;
@@ -1419,13 +1448,14 @@ void nfs_init_commit(struct nfs_write_data *data,
 	data->cred	  = first->wb_context->cred;
 	data->lseg	  = lseg; /* reference transferred */
 	data->mds_ops     = &nfs_commit_ops;
+	data->completion_ops = cinfo->completion_ops;
+	data->dreq	  = cinfo->dreq;
 
 	data->args.fh     = NFS_FH(data->inode);
 	/* Note: we always request a commit of the entire inode */
 	data->args.offset = 0;
 	data->args.count  = 0;
-	data->args.context = get_nfs_open_context(first->wb_context);
-	data->res.count   = 0;
+	data->context     = get_nfs_open_context(first->wb_context);
 	data->res.fattr   = &data->fattr;
 	data->res.verf    = &data->verf;
 	nfs_fattr_init(&data->fattr);
@@ -1433,18 +1463,21 @@ void nfs_init_commit(struct nfs_write_data *data,
 EXPORT_SYMBOL_GPL(nfs_init_commit);
 
 void nfs_retry_commit(struct list_head *page_list,
-		      struct pnfs_layout_segment *lseg)
+		      struct pnfs_layout_segment *lseg,
+		      struct nfs_commit_info *cinfo)
 {
 	struct nfs_page *req;
 
 	while (!list_empty(page_list)) {
 		req = nfs_list_entry(page_list->next);
 		nfs_list_remove_request(req);
-		nfs_mark_request_commit(req, lseg);
-		dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
-		dec_bdi_stat(req->wb_page->mapping->backing_dev_info,
-			     BDI_RECLAIMABLE);
-		nfs_unlock_request(req);
+		nfs_mark_request_commit(req, lseg, cinfo);
+		if (!cinfo->dreq) {
+			dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
+			dec_bdi_stat(req->wb_page->mapping->backing_dev_info,
+				     BDI_RECLAIMABLE);
+		}
+		nfs_unlock_and_release_request(req);
 	}
 }
 EXPORT_SYMBOL_GPL(nfs_retry_commit);
@@ -1453,9 +1486,10 @@ EXPORT_SYMBOL_GPL(nfs_retry_commit);
  * Commit dirty pages
  */
 static int
-nfs_commit_list(struct inode *inode, struct list_head *head, int how)
+nfs_commit_list(struct inode *inode, struct list_head *head, int how,
+		struct nfs_commit_info *cinfo)
 {
-	struct nfs_write_data	*data;
+	struct nfs_commit_data	*data;
 
 	data = nfs_commitdata_alloc();
 
@@ -1463,11 +1497,13 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how)
 		goto out_bad;
 
 	/* Set up the argument struct */
-	nfs_init_commit(data, head, NULL);
-	return nfs_initiate_commit(data, NFS_CLIENT(inode), data->mds_ops, how);
+	nfs_init_commit(data, head, NULL, cinfo);
+	atomic_inc(&cinfo->mds->rpcs_out);
+	return nfs_initiate_commit(NFS_CLIENT(inode), data, data->mds_ops,
+				   how, 0);
  out_bad:
-	nfs_retry_commit(head, NULL);
-	nfs_commit_clear_lock(NFS_I(inode));
+	nfs_retry_commit(head, NULL, cinfo);
+	cinfo->completion_ops->error_cleanup(NFS_I(inode));
 	return -ENOMEM;
 }
 
@@ -1476,7 +1512,7 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how)
  */
 static void nfs_commit_done(struct rpc_task *task, void *calldata)
 {
-	struct nfs_write_data	*data = calldata;
+	struct nfs_commit_data	*data = calldata;
 
         dprintk("NFS: %5u nfs_commit_done (status %d)\n",
                                 task->tk_pid, task->tk_status);
@@ -1485,10 +1521,11 @@ static void nfs_commit_done(struct rpc_task *task, void *calldata)
 	NFS_PROTO(data->inode)->commit_done(task, data);
 }
 
-void nfs_commit_release_pages(struct nfs_write_data *data)
+static void nfs_commit_release_pages(struct nfs_commit_data *data)
 {
 	struct nfs_page	*req;
 	int status = data->task.tk_status;
+	struct nfs_commit_info cinfo;
 
 	while (!list_empty(&data->pages)) {
 		req = nfs_list_entry(data->pages.next);
@@ -1519,42 +1556,59 @@ void nfs_commit_release_pages(struct nfs_write_data *data)
 		dprintk(" mismatch\n");
 		nfs_mark_request_dirty(req);
 	next:
-		nfs_unlock_request(req);
+		nfs_unlock_and_release_request(req);
 	}
+	nfs_init_cinfo(&cinfo, data->inode, data->dreq);
+	if (atomic_dec_and_test(&cinfo.mds->rpcs_out))
+		nfs_commit_clear_lock(NFS_I(data->inode));
 }
-EXPORT_SYMBOL_GPL(nfs_commit_release_pages);
 
 static void nfs_commit_release(void *calldata)
 {
-	struct nfs_write_data *data = calldata;
+	struct nfs_commit_data *data = calldata;
 
-	nfs_commit_release_pages(data);
-	nfs_commit_clear_lock(NFS_I(data->inode));
+	data->completion_ops->completion(data);
 	nfs_commitdata_release(calldata);
 }
 
 static const struct rpc_call_ops nfs_commit_ops = {
-	.rpc_call_prepare = nfs_write_prepare,
+	.rpc_call_prepare = nfs_commit_prepare,
 	.rpc_call_done = nfs_commit_done,
 	.rpc_release = nfs_commit_release,
 };
 
+static const struct nfs_commit_completion_ops nfs_commit_completion_ops = {
+	.completion = nfs_commit_release_pages,
+	.error_cleanup = nfs_commit_clear_lock,
+};
+
+int nfs_generic_commit_list(struct inode *inode, struct list_head *head,
+			    int how, struct nfs_commit_info *cinfo)
+{
+	int status;
+
+	status = pnfs_commit_list(inode, head, how, cinfo);
+	if (status == PNFS_NOT_ATTEMPTED)
+		status = nfs_commit_list(inode, head, how, cinfo);
+	return status;
+}
+
 int nfs_commit_inode(struct inode *inode, int how)
 {
 	LIST_HEAD(head);
+	struct nfs_commit_info cinfo;
 	int may_wait = how & FLUSH_SYNC;
 	int res;
 
 	res = nfs_commit_set_lock(NFS_I(inode), may_wait);
 	if (res <= 0)
 		goto out_mark_dirty;
-	res = nfs_scan_commit(inode, &head);
+	nfs_init_cinfo_from_inode(&cinfo, inode);
+	res = nfs_scan_commit(inode, &head, &cinfo);
 	if (res) {
 		int error;
 
-		error = pnfs_commit_list(inode, &head, how);
-		if (error == PNFS_NOT_ATTEMPTED)
-			error = nfs_commit_list(inode, &head, how);
+		error = nfs_generic_commit_list(inode, &head, how, &cinfo);
 		if (error < 0)
 			return error;
 		if (!may_wait)
@@ -1585,14 +1639,14 @@ static int nfs_commit_unstable_pages(struct inode *inode, struct writeback_contr
 	int ret = 0;
 
 	/* no commits means nothing needs to be done */
-	if (!nfsi->ncommit)
+	if (!nfsi->commit_info.ncommit)
 		return ret;
 
 	if (wbc->sync_mode == WB_SYNC_NONE) {
 		/* Don't commit yet if this is a non-blocking flush and there
 		 * are a lot of outstanding writes for this mapping.
 		 */
-		if (nfsi->ncommit <= (nfsi->npages >> 1))
+		if (nfsi->commit_info.ncommit <= (nfsi->npages >> 1))
 			goto out_mark_dirty;
 
 		/* don't wait for the COMMIT response */
@@ -1665,7 +1719,7 @@ int nfs_wb_page_cancel(struct inode *inode, struct page *page)
 		req = nfs_page_find_request(page);
 		if (req == NULL)
 			break;
-		if (nfs_lock_request_dontget(req)) {
+		if (nfs_lock_request(req)) {
 			nfs_clear_request_commit(req);
 			nfs_inode_remove_request(req);
 			/*
@@ -1673,7 +1727,7 @@ int nfs_wb_page_cancel(struct inode *inode, struct page *page)
 			 * page as being dirty
 			 */
 			cancel_dirty_page(page, PAGE_CACHE_SIZE);
-			nfs_unlock_request(req);
+			nfs_unlock_and_release_request(req);
 			break;
 		}
 		ret = nfs_wait_on_request(req);
@@ -1742,7 +1796,7 @@ int nfs_migrate_page(struct address_space *mapping, struct page *newpage,
 int __init nfs_init_writepagecache(void)
 {
 	nfs_wdata_cachep = kmem_cache_create("nfs_write_data",
-					     sizeof(struct nfs_write_data),
+					     sizeof(struct nfs_write_header),
 					     0, SLAB_HWCACHE_ALIGN,
 					     NULL);
 	if (nfs_wdata_cachep == NULL)
@@ -1753,6 +1807,13 @@ int __init nfs_init_writepagecache(void)
 	if (nfs_wdata_mempool == NULL)
 		return -ENOMEM;
 
+	nfs_cdata_cachep = kmem_cache_create("nfs_commit_data",
+					     sizeof(struct nfs_commit_data),
+					     0, SLAB_HWCACHE_ALIGN,
+					     NULL);
+	if (nfs_cdata_cachep == NULL)
+		return -ENOMEM;
+
 	nfs_commit_mempool = mempool_create_slab_pool(MIN_POOL_COMMIT,
 						      nfs_wdata_cachep);
 	if (nfs_commit_mempool == NULL)
diff --git a/fs/proc/base.c b/fs/proc/base.c
index d2d3108a611c..d7d711876b6a 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -411,12 +411,13 @@ static const struct file_operations proc_lstats_operations = {
 
 static int proc_oom_score(struct task_struct *task, char *buffer)
 {
+	unsigned long totalpages = totalram_pages + total_swap_pages;
 	unsigned long points = 0;
 
 	read_lock(&tasklist_lock);
 	if (pid_alive(task))
-		points = oom_badness(task, NULL, NULL,
-					totalram_pages + total_swap_pages);
+		points = oom_badness(task, NULL, NULL, totalpages) *
+						1000 / totalpages;
 	read_unlock(&tasklist_lock);
 	return sprintf(buffer, "%lu\n", points);
 }
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 1030a716d155..7faaf2acc570 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -784,7 +784,7 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 
 	/* find the first VMA at or above 'addr' */
 	vma = find_vma(walk->mm, addr);
-	if (pmd_trans_huge_lock(pmd, vma) == 1) {
+	if (vma && pmd_trans_huge_lock(pmd, vma) == 1) {
 		for (; addr != end; addr += PAGE_SIZE) {
 			unsigned long offset;
 
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index e2768f188f55..6f2b45a9b6bc 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -445,6 +445,18 @@ static inline int pmd_write(pmd_t pmd)
 #endif /* __HAVE_ARCH_PMD_WRITE */
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
+#ifndef pmd_read_atomic
+static inline pmd_t pmd_read_atomic(pmd_t *pmdp)
+{
+	/*
+	 * Depend on compiler for an atomic pmd read. NOTE: this is
+	 * only going to work, if the pmdval_t isn't larger than
+	 * an unsigned long.
+	 */
+	return *pmdp;
+}
+#endif
+
 /*
  * This function is meant to be used by sites walking pagetables with
  * the mmap_sem hold in read mode to protect against MADV_DONTNEED and
@@ -458,11 +470,17 @@ static inline int pmd_write(pmd_t pmd)
  * undefined so behaving like if the pmd was none is safe (because it
  * can return none anyway). The compiler level barrier() is critically
  * important to compute the two checks atomically on the same pmdval.
+ *
+ * For 32bit kernels with a 64bit large pmd_t this automatically takes
+ * care of reading the pmd atomically to avoid SMP race conditions
+ * against pmd_populate() when the mmap_sem is hold for reading by the
+ * caller (a special atomic read not done by "gcc" as in the generic
+ * version above, is also needed when THP is disabled because the page
+ * fault can populate the pmd from under us).
  */
 static inline int pmd_none_or_trans_huge_or_clear_bad(pmd_t *pmd)
 {
-	/* depend on compiler for an atomic pmd read */
-	pmd_t pmdval = *pmd;
+	pmd_t pmdval = pmd_read_atomic(pmd);
 	/*
 	 * The barrier will stabilize the pmdval in a register or on
 	 * the stack so that it will stop changing under the code.
diff --git a/include/linux/Kbuild b/include/linux/Kbuild
index 4cd59b95858f..7185b8f15ced 100644
--- a/include/linux/Kbuild
+++ b/include/linux/Kbuild
@@ -225,6 +225,7 @@ header-y += kd.h
 header-y += kdev_t.h
 header-y += kernel.h
 header-y += kernelcapi.h
+header-y += kernel-page-flags.h
 header-y += keyboard.h
 header-y += keyctl.h
 header-y += l2tp.h
diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
index 1a0cd270bb7a..324fe08ea3b1 100644
--- a/include/linux/bootmem.h
+++ b/include/linux/bootmem.h
@@ -135,9 +135,6 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat,
 extern int reserve_bootmem_generic(unsigned long addr, unsigned long size,
 				   int flags);
 
-extern void *alloc_bootmem_section(unsigned long size,
-				   unsigned long section_nr);
-
 #ifdef CONFIG_HAVE_ARCH_ALLOC_REMAP
 extern void *alloc_remap(int nid, unsigned long size);
 #else
diff --git a/include/linux/bug.h b/include/linux/bug.h
index 72961c39576a..aaac4bba6f5c 100644
--- a/include/linux/bug.h
+++ b/include/linux/bug.h
@@ -30,6 +30,13 @@ struct pt_regs;
 #define BUILD_BUG_ON_ZERO(e) (sizeof(struct { int:-!!(e); }))
 #define BUILD_BUG_ON_NULL(e) ((void *)sizeof(struct { int:-!!(e); }))
 
+/*
+ * BUILD_BUG_ON_INVALID() permits the compiler to check the validity of the
+ * expression but avoids the generation of any code, even if that expression
+ * has side-effects.
+ */
+#define BUILD_BUG_ON_INVALID(e) ((void)(sizeof((__force long)(e))))
+
 /**
  * BUILD_BUG_ON - break compile if a condition is true.
  * @condition: the condition which the compiler should know is false.
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 51a90b7f2d60..e988037abd2a 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -1,6 +1,8 @@
 #ifndef _LINUX_COMPACTION_H
 #define _LINUX_COMPACTION_H
 
+#include <linux/node.h>
+
 /* Return values for compact_zone() and try_to_compact_pages() */
 /* compaction didn't start as it was not possible or direct reclaim was more suitable */
 #define COMPACT_SKIPPED		0
@@ -11,6 +13,23 @@
 /* The full zone was compacted */
 #define COMPACT_COMPLETE	3
 
+/*
+ * compaction supports three modes
+ *
+ * COMPACT_ASYNC_MOVABLE uses asynchronous migration and only scans
+ *    MIGRATE_MOVABLE pageblocks as migration sources and targets.
+ * COMPACT_ASYNC_UNMOVABLE uses asynchronous migration and only scans
+ *    MIGRATE_MOVABLE pageblocks as migration sources.
+ *    MIGRATE_UNMOVABLE pageblocks are scanned as potential migration
+ *    targets and convers them to MIGRATE_MOVABLE if possible
+ * COMPACT_SYNC uses synchronous migration and scans all pageblocks
+ */
+enum compact_mode {
+	COMPACT_ASYNC_MOVABLE,
+	COMPACT_ASYNC_UNMOVABLE,
+	COMPACT_SYNC,
+};
+
 #ifdef CONFIG_COMPACTION
 extern int sysctl_compact_memory;
 extern int sysctl_compaction_handler(struct ctl_table *table, int write,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index cdc1a9630948..038076b27ea4 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1681,7 +1681,6 @@ struct inode_operations {
 	ssize_t (*getxattr) (struct dentry *, const char *, void *, size_t);
 	ssize_t (*listxattr) (struct dentry *, char *, size_t);
 	int (*removexattr) (struct dentry *, const char *);
-	void (*truncate_range)(struct inode *, loff_t, loff_t);
 	int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
 		      u64 len);
 } ____cacheline_aligned;
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index c8af7a2efb52..4c59b1131187 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -59,6 +59,8 @@ extern pmd_t *page_check_address_pmd(struct page *page,
 #define HPAGE_PMD_MASK HPAGE_MASK
 #define HPAGE_PMD_SIZE HPAGE_SIZE
 
+extern bool is_vma_temporary_stack(struct vm_area_struct *vma);
+
 #define transparent_hugepage_enabled(__vma)				\
 	((transparent_hugepage_flags &					\
 	  (1<<TRANSPARENT_HUGEPAGE_FLAG) ||				\
diff --git a/include/linux/kernel-page-flags.h b/include/linux/kernel-page-flags.h
index 26a65711676f..a1bdf6966357 100644
--- a/include/linux/kernel-page-flags.h
+++ b/include/linux/kernel-page-flags.h
@@ -32,6 +32,8 @@
 #define KPF_KSM			21
 #define KPF_THP			22
 
+#ifdef __KERNEL__
+
 /* kernel hacking assistances
  * WARNING: subject to change, never rely on them!
  */
@@ -44,4 +46,6 @@
 #define KPF_ARCH		38
 #define KPF_UNCACHED		39
 
+#endif /* __KERNEL__ */
+
 #endif /* LINUX_KERNEL_PAGE_FLAGS_H */
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index f94efd2f6c27..cfe9050ad8da 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -79,6 +79,8 @@ extern void mem_cgroup_uncharge_cache_page(struct page *page);
 
 extern void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 				     int order);
+bool __mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg,
+				  struct mem_cgroup *memcg);
 int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *memcg);
 
 extern struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page);
@@ -92,10 +94,13 @@ static inline
 int mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *cgroup)
 {
 	struct mem_cgroup *memcg;
+	int match;
+
 	rcu_read_lock();
 	memcg = mem_cgroup_from_task(rcu_dereference((mm)->owner));
+	match = __mem_cgroup_same_or_subtree(cgroup, memcg);
 	rcu_read_unlock();
-	return cgroup == memcg;
+	return match;
 }
 
 extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg);
@@ -121,8 +126,6 @@ int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg,
 int mem_cgroup_select_victim_node(struct mem_cgroup *memcg);
 unsigned long mem_cgroup_zone_nr_lru_pages(struct mem_cgroup *memcg,
 					int nid, int zid, unsigned int lrumask);
-struct zone_reclaim_stat *mem_cgroup_get_reclaim_stat(struct mem_cgroup *memcg,
-						      struct zone *zone);
 struct zone_reclaim_stat*
 mem_cgroup_get_reclaim_stat_from_page(struct page *page);
 extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
@@ -351,13 +354,6 @@ mem_cgroup_zone_nr_lru_pages(struct mem_cgroup *memcg, int nid, int zid,
 	return 0;
 }
 
-
-static inline struct zone_reclaim_stat*
-mem_cgroup_get_reclaim_stat(struct mem_cgroup *memcg, struct zone *zone)
-{
-	return NULL;
-}
-
 static inline struct zone_reclaim_stat*
 mem_cgroup_get_reclaim_stat_from_page(struct page *page)
 {
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 7c727a90d70d..4aa42732e47f 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -225,8 +225,8 @@ static inline void check_highest_zone(enum zone_type k)
 		policy_zone = k;
 }
 
-int do_migrate_pages(struct mm_struct *mm,
-	const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags);
+int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
+		     const nodemask_t *to, int flags);
 
 
 #ifdef CONFIG_TMPFS
@@ -354,9 +354,8 @@ static inline bool mempolicy_nodemask_intersects(struct task_struct *tsk,
 	return false;
 }
 
-static inline int do_migrate_pages(struct mm_struct *mm,
-			const nodemask_t *from_nodes,
-			const nodemask_t *to_nodes, int flags)
+static inline int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
+				   const nodemask_t *to, int flags)
 {
 	return 0;
 }
diff --git a/include/linux/mfd/abx500/ab8500.h b/include/linux/mfd/abx500/ab8500.h
index fccc3002f271..91dd3ef63e99 100644
--- a/include/linux/mfd/abx500/ab8500.h
+++ b/include/linux/mfd/abx500/ab8500.h
@@ -7,6 +7,7 @@
 #ifndef MFD_AB8500_H
 #define MFD_AB8500_H
 
+#include <linux/atomic.h>
 #include <linux/mutex.h>
 
 struct device;
@@ -194,6 +195,14 @@ enum ab8500_version {
 #define AB9540_INT_GPIO52F		123
 #define AB9540_INT_GPIO53F		124
 #define AB9540_INT_GPIO54F		125 /* not 8505 */
+/* ab8500_irq_regoffset[16] -> IT[Source|Latch|Mask]25 */
+#define AB8505_INT_KEYSTUCK		128
+#define AB8505_INT_IKR			129
+#define AB8505_INT_IKP			130
+#define AB8505_INT_KP			131
+#define AB8505_INT_KEYDEGLITCH		132
+#define AB8505_INT_MODPWRSTATUSF	134
+#define AB8505_INT_MODPWRSTATUSR	135
 
 /*
  * AB8500_AB9540_NR_IRQS is used when configuring the IRQ numbers for the
@@ -203,8 +212,8 @@ enum ab8500_version {
  * which is larger.
  */
 #define AB8500_NR_IRQS			112
-#define AB8505_NR_IRQS			128
-#define AB9540_NR_IRQS			128
+#define AB8505_NR_IRQS			136
+#define AB9540_NR_IRQS			136
 /* This is set to the roof of any AB8500 chip variant IRQ counts */
 #define AB8500_MAX_NR_IRQS		AB9540_NR_IRQS
 
@@ -216,6 +225,7 @@ enum ab8500_version {
  * @dev: parent device
  * @lock: read/write operations lock
  * @irq_lock: genirq bus lock
+ * @transfer_ongoing: 0 if no transfer ongoing
  * @irq: irq line
  * @version: chip version id (e.g. ab8500 or ab9540)
  * @chip_id: chip revision id
@@ -234,7 +244,7 @@ struct ab8500 {
 	struct device	*dev;
 	struct mutex	lock;
 	struct mutex	irq_lock;
-
+	atomic_t	transfer_ongoing;
 	int		irq_base;
 	int		irq;
 	enum ab8500_version version;
@@ -280,6 +290,8 @@ extern int __devinit ab8500_init(struct ab8500 *ab8500,
 				 enum ab8500_version version);
 extern int __devexit ab8500_exit(struct ab8500 *ab8500);
 
+extern int ab8500_suspend(struct ab8500 *ab8500);
+
 static inline int is_ab8500(struct ab8500 *ab)
 {
 	return ab->version == AB8500_VERSION_AB8500;
diff --git a/include/linux/mfd/anatop.h b/include/linux/mfd/anatop.h
index 22c1007d3ec5..7f92acf03d9e 100644
--- a/include/linux/mfd/anatop.h
+++ b/include/linux/mfd/anatop.h
@@ -34,7 +34,7 @@ struct anatop {
 	spinlock_t reglock;
 };
 
-extern u32 anatop_get_bits(struct anatop *, u32, int, int);
-extern void anatop_set_bits(struct anatop *, u32, int, int, u32);
+extern u32 anatop_read_reg(struct anatop *, u32);
+extern void anatop_write_reg(struct anatop *, u32, u32, u32);
 
 #endif /*  __LINUX_MFD_ANATOP_H */
diff --git a/include/linux/mfd/asic3.h b/include/linux/mfd/asic3.h
index ef6faa5cee46..e1148d037e7b 100644
--- a/include/linux/mfd/asic3.h
+++ b/include/linux/mfd/asic3.h
@@ -31,6 +31,8 @@ struct asic3_platform_data {
 
 	unsigned int gpio_base;
 
+	unsigned int clock_rate;
+
 	struct asic3_led *leds;
 };
 
diff --git a/include/linux/mfd/da9052/da9052.h b/include/linux/mfd/da9052/da9052.h
index 8313cd9658e3..0507c4c21a7d 100644
--- a/include/linux/mfd/da9052/da9052.h
+++ b/include/linux/mfd/da9052/da9052.h
@@ -33,6 +33,18 @@
 
 #include <linux/mfd/da9052/reg.h>
 
+/* Common - HWMON Channel Definations */
+#define DA9052_ADC_VDDOUT	0
+#define DA9052_ADC_ICH		1
+#define DA9052_ADC_TBAT	2
+#define DA9052_ADC_VBAT	3
+#define DA9052_ADC_IN4		4
+#define DA9052_ADC_IN5		5
+#define DA9052_ADC_IN6		6
+#define DA9052_ADC_TSI		7
+#define DA9052_ADC_TJUNC	8
+#define DA9052_ADC_VBBAT	9
+
 #define DA9052_IRQ_DCIN	0
 #define DA9052_IRQ_VBUS	1
 #define DA9052_IRQ_DCINREM	2
@@ -79,6 +91,9 @@ struct da9052 {
 	struct device *dev;
 	struct regmap *regmap;
 
+	struct mutex auxadc_lock;
+	struct completion done;
+
 	int irq_base;
 	struct regmap_irq_chip_data *irq_data;
 	u8 chip_id;
@@ -86,6 +101,10 @@ struct da9052 {
 	int chip_irq;
 };
 
+/* ADC API */
+int da9052_adc_manual_read(struct da9052 *da9052, unsigned char channel);
+int da9052_adc_read_temp(struct da9052 *da9052);
+
 /* Device I/O API */
 static inline int da9052_reg_read(struct da9052 *da9052, unsigned char reg)
 {
diff --git a/include/linux/mfd/lm3533.h b/include/linux/mfd/lm3533.h
new file mode 100644
index 000000000000..594bc591f256
--- /dev/null
+++ b/include/linux/mfd/lm3533.h
@@ -0,0 +1,104 @@
+/*
+ * lm3533.h -- LM3533 interface
+ *
+ * Copyright (C) 2011-2012 Texas Instruments
+ *
+ * Author: Johan Hovold <jhovold@gmail.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.
+ */
+
+#ifndef __LINUX_MFD_LM3533_H
+#define __LINUX_MFD_LM3533_H
+
+#define LM3533_ATTR_RO(_name) \
+	DEVICE_ATTR(_name, S_IRUGO, show_##_name, NULL)
+#define LM3533_ATTR_RW(_name) \
+	DEVICE_ATTR(_name, S_IRUGO | S_IWUSR , show_##_name, store_##_name)
+
+struct device;
+struct regmap;
+
+struct lm3533 {
+	struct device *dev;
+
+	struct regmap *regmap;
+
+	int gpio_hwen;
+	int irq;
+
+	unsigned have_als:1;
+	unsigned have_backlights:1;
+	unsigned have_leds:1;
+};
+
+struct lm3533_ctrlbank {
+	struct lm3533 *lm3533;
+	struct device *dev;
+	int id;
+};
+
+struct lm3533_als_platform_data {
+	unsigned pwm_mode:1;		/* PWM input mode (default analog) */
+	u8 r_select;			/* 1 - 127 (ignored in PWM-mode) */
+};
+
+struct lm3533_bl_platform_data {
+	char *name;
+	u16 max_current;		/* 5000 - 29800 uA (800 uA step) */
+	u8 default_brightness;		/* 0 - 255 */
+	u8 pwm;				/* 0 - 0x3f */
+};
+
+struct lm3533_led_platform_data {
+	char *name;
+	const char *default_trigger;
+	u16 max_current;		/* 5000 - 29800 uA (800 uA step) */
+	u8 pwm;				/* 0 - 0x3f */
+};
+
+enum lm3533_boost_freq {
+	LM3533_BOOST_FREQ_500KHZ,
+	LM3533_BOOST_FREQ_1000KHZ,
+};
+
+enum lm3533_boost_ovp {
+	LM3533_BOOST_OVP_16V,
+	LM3533_BOOST_OVP_24V,
+	LM3533_BOOST_OVP_32V,
+	LM3533_BOOST_OVP_40V,
+};
+
+struct lm3533_platform_data {
+	int gpio_hwen;
+
+	enum lm3533_boost_ovp boost_ovp;
+	enum lm3533_boost_freq boost_freq;
+
+	struct lm3533_als_platform_data *als;
+
+	struct lm3533_bl_platform_data *backlights;
+	int num_backlights;
+
+	struct lm3533_led_platform_data *leds;
+	int num_leds;
+};
+
+extern int lm3533_ctrlbank_enable(struct lm3533_ctrlbank *cb);
+extern int lm3533_ctrlbank_disable(struct lm3533_ctrlbank *cb);
+
+extern int lm3533_ctrlbank_set_brightness(struct lm3533_ctrlbank *cb, u8 val);
+extern int lm3533_ctrlbank_get_brightness(struct lm3533_ctrlbank *cb, u8 *val);
+extern int lm3533_ctrlbank_set_max_current(struct lm3533_ctrlbank *cb,
+								u16 imax);
+extern int lm3533_ctrlbank_set_pwm(struct lm3533_ctrlbank *cb, u8 val);
+extern int lm3533_ctrlbank_get_pwm(struct lm3533_ctrlbank *cb, u8 *val);
+
+extern int lm3533_read(struct lm3533 *lm3533, u8 reg, u8 *val);
+extern int lm3533_write(struct lm3533 *lm3533, u8 reg, u8 val);
+extern int lm3533_update(struct lm3533 *lm3533, u8 reg, u8 val, u8 mask);
+
+#endif	/* __LINUX_MFD_LM3533_H */
diff --git a/include/linux/mfd/lpc_ich.h b/include/linux/mfd/lpc_ich.h
new file mode 100644
index 000000000000..fec5256c3f5d
--- /dev/null
+++ b/include/linux/mfd/lpc_ich.h
@@ -0,0 +1,48 @@
+/*
+ *  linux/drivers/mfd/lpc_ich.h
+ *
+ *  Copyright (c) 2012 Extreme Engineering Solution, Inc.
+ *  Author: Aaron Sierra <asierra@xes-inc.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License 2 as published
+ *  by the Free Software Foundation.
+ *
+ *  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; see the file COPYING.  If not, write to
+ *  the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+#ifndef LPC_ICH_H
+#define LPC_ICH_H
+
+/* Watchdog resources */
+#define ICH_RES_IO_TCO	0
+#define ICH_RES_IO_SMI	1
+#define ICH_RES_MEM_OFF	2
+#define ICH_RES_MEM_GCS	0
+
+/* GPIO resources */
+#define ICH_RES_GPIO	0
+#define ICH_RES_GPE0	1
+
+/* GPIO compatibility */
+#define ICH_I3100_GPIO		0x401
+#define ICH_V5_GPIO		0x501
+#define ICH_V6_GPIO		0x601
+#define ICH_V7_GPIO		0x701
+#define ICH_V9_GPIO		0x801
+#define ICH_V10CORP_GPIO	0xa01
+#define ICH_V10CONS_GPIO	0xa11
+
+struct lpc_ich_info {
+	char name[32];
+	unsigned int iTCO_version;
+	unsigned int gpio_version;
+};
+
+#endif
diff --git a/include/linux/mfd/max77693-private.h b/include/linux/mfd/max77693-private.h
new file mode 100644
index 000000000000..68263c5fa53c
--- /dev/null
+++ b/include/linux/mfd/max77693-private.h
@@ -0,0 +1,227 @@
+/*
+ * max77693-private.h - Voltage regulator driver for the Maxim 77693
+ *
+ *  Copyright (C) 2012 Samsung Electrnoics
+ *  SangYoung Son <hello.son@samsung.com>
+ *
+ * This program is not provided / owned by Maxim Integrated Products.
+ *
+ * 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
+ */
+
+#ifndef __LINUX_MFD_MAX77693_PRIV_H
+#define __LINUX_MFD_MAX77693_PRIV_H
+
+#include <linux/i2c.h>
+
+#define MAX77693_NUM_IRQ_MUIC_REGS	3
+#define MAX77693_REG_INVALID		(0xff)
+
+/* Slave addr = 0xCC: PMIC, Charger, Flash LED */
+enum max77693_pmic_reg {
+	MAX77693_LED_REG_IFLASH1			= 0x00,
+	MAX77693_LED_REG_IFLASH2			= 0x01,
+	MAX77693_LED_REG_ITORCH				= 0x02,
+	MAX77693_LED_REG_ITORCHTIMER			= 0x03,
+	MAX77693_LED_REG_FLASH_TIMER			= 0x04,
+	MAX77693_LED_REG_FLASH_EN			= 0x05,
+	MAX77693_LED_REG_MAX_FLASH1			= 0x06,
+	MAX77693_LED_REG_MAX_FLASH2			= 0x07,
+	MAX77693_LED_REG_MAX_FLASH3			= 0x08,
+	MAX77693_LED_REG_MAX_FLASH4			= 0x09,
+	MAX77693_LED_REG_VOUT_CNTL			= 0x0A,
+	MAX77693_LED_REG_VOUT_FLASH1			= 0x0B,
+	MAX77693_LED_REG_VOUT_FLASH2			= 0x0C,
+	MAX77693_LED_REG_FLASH_INT			= 0x0E,
+	MAX77693_LED_REG_FLASH_INT_MASK			= 0x0F,
+	MAX77693_LED_REG_FLASH_INT_STATUS		= 0x10,
+
+	MAX77693_PMIC_REG_PMIC_ID1			= 0x20,
+	MAX77693_PMIC_REG_PMIC_ID2			= 0x21,
+	MAX77693_PMIC_REG_INTSRC			= 0x22,
+	MAX77693_PMIC_REG_INTSRC_MASK			= 0x23,
+	MAX77693_PMIC_REG_TOPSYS_INT			= 0x24,
+	MAX77693_PMIC_REG_TOPSYS_INT_MASK		= 0x26,
+	MAX77693_PMIC_REG_TOPSYS_STAT			= 0x28,
+	MAX77693_PMIC_REG_MAINCTRL1			= 0x2A,
+	MAX77693_PMIC_REG_LSCNFG			= 0x2B,
+
+	MAX77693_CHG_REG_CHG_INT			= 0xB0,
+	MAX77693_CHG_REG_CHG_INT_MASK			= 0xB1,
+	MAX77693_CHG_REG_CHG_INT_OK			= 0xB2,
+	MAX77693_CHG_REG_CHG_DETAILS_00			= 0xB3,
+	MAX77693_CHG_REG_CHG_DETAILS_01			= 0xB4,
+	MAX77693_CHG_REG_CHG_DETAILS_02			= 0xB5,
+	MAX77693_CHG_REG_CHG_DETAILS_03			= 0xB6,
+	MAX77693_CHG_REG_CHG_CNFG_00			= 0xB7,
+	MAX77693_CHG_REG_CHG_CNFG_01			= 0xB8,
+	MAX77693_CHG_REG_CHG_CNFG_02			= 0xB9,
+	MAX77693_CHG_REG_CHG_CNFG_03			= 0xBA,
+	MAX77693_CHG_REG_CHG_CNFG_04			= 0xBB,
+	MAX77693_CHG_REG_CHG_CNFG_05			= 0xBC,
+	MAX77693_CHG_REG_CHG_CNFG_06			= 0xBD,
+	MAX77693_CHG_REG_CHG_CNFG_07			= 0xBE,
+	MAX77693_CHG_REG_CHG_CNFG_08			= 0xBF,
+	MAX77693_CHG_REG_CHG_CNFG_09			= 0xC0,
+	MAX77693_CHG_REG_CHG_CNFG_10			= 0xC1,
+	MAX77693_CHG_REG_CHG_CNFG_11			= 0xC2,
+	MAX77693_CHG_REG_CHG_CNFG_12			= 0xC3,
+	MAX77693_CHG_REG_CHG_CNFG_13			= 0xC4,
+	MAX77693_CHG_REG_CHG_CNFG_14			= 0xC5,
+	MAX77693_CHG_REG_SAFEOUT_CTRL			= 0xC6,
+
+	MAX77693_PMIC_REG_END,
+};
+
+/* Slave addr = 0x4A: MUIC */
+enum max77693_muic_reg {
+	MAX77693_MUIC_REG_ID		= 0x00,
+	MAX77693_MUIC_REG_INT1		= 0x01,
+	MAX77693_MUIC_REG_INT2		= 0x02,
+	MAX77693_MUIC_REG_INT3		= 0x03,
+	MAX77693_MUIC_REG_STATUS1	= 0x04,
+	MAX77693_MUIC_REG_STATUS2	= 0x05,
+	MAX77693_MUIC_REG_STATUS3	= 0x06,
+	MAX77693_MUIC_REG_INTMASK1	= 0x07,
+	MAX77693_MUIC_REG_INTMASK2	= 0x08,
+	MAX77693_MUIC_REG_INTMASK3	= 0x09,
+	MAX77693_MUIC_REG_CDETCTRL1	= 0x0A,
+	MAX77693_MUIC_REG_CDETCTRL2	= 0x0B,
+	MAX77693_MUIC_REG_CTRL1		= 0x0C,
+	MAX77693_MUIC_REG_CTRL2		= 0x0D,
+	MAX77693_MUIC_REG_CTRL3		= 0x0E,
+
+	MAX77693_MUIC_REG_END,
+};
+
+/* Slave addr = 0x90: Haptic */
+enum max77693_haptic_reg {
+	MAX77693_HAPTIC_REG_STATUS		= 0x00,
+	MAX77693_HAPTIC_REG_CONFIG1		= 0x01,
+	MAX77693_HAPTIC_REG_CONFIG2		= 0x02,
+	MAX77693_HAPTIC_REG_CONFIG_CHNL		= 0x03,
+	MAX77693_HAPTIC_REG_CONFG_CYC1		= 0x04,
+	MAX77693_HAPTIC_REG_CONFG_CYC2		= 0x05,
+	MAX77693_HAPTIC_REG_CONFIG_PER1		= 0x06,
+	MAX77693_HAPTIC_REG_CONFIG_PER2		= 0x07,
+	MAX77693_HAPTIC_REG_CONFIG_PER3		= 0x08,
+	MAX77693_HAPTIC_REG_CONFIG_PER4		= 0x09,
+	MAX77693_HAPTIC_REG_CONFIG_DUTY1	= 0x0A,
+	MAX77693_HAPTIC_REG_CONFIG_DUTY2	= 0x0B,
+	MAX77693_HAPTIC_REG_CONFIG_PWM1		= 0x0C,
+	MAX77693_HAPTIC_REG_CONFIG_PWM2		= 0x0D,
+	MAX77693_HAPTIC_REG_CONFIG_PWM3		= 0x0E,
+	MAX77693_HAPTIC_REG_CONFIG_PWM4		= 0x0F,
+	MAX77693_HAPTIC_REG_REV			= 0x10,
+
+	MAX77693_HAPTIC_REG_END,
+};
+
+enum max77693_irq_source {
+	LED_INT = 0,
+	TOPSYS_INT,
+	CHG_INT,
+	MUIC_INT1,
+	MUIC_INT2,
+	MUIC_INT3,
+
+	MAX77693_IRQ_GROUP_NR,
+};
+
+enum max77693_irq {
+	/* PMIC - FLASH */
+	MAX77693_LED_IRQ_FLED2_OPEN,
+	MAX77693_LED_IRQ_FLED2_SHORT,
+	MAX77693_LED_IRQ_FLED1_OPEN,
+	MAX77693_LED_IRQ_FLED1_SHORT,
+	MAX77693_LED_IRQ_MAX_FLASH,
+
+	/* PMIC - TOPSYS */
+	MAX77693_TOPSYS_IRQ_T120C_INT,
+	MAX77693_TOPSYS_IRQ_T140C_INT,
+	MAX77693_TOPSYS_IRQ_LOWSYS_INT,
+
+	/* PMIC - Charger */
+	MAX77693_CHG_IRQ_BYP_I,
+	MAX77693_CHG_IRQ_THM_I,
+	MAX77693_CHG_IRQ_BAT_I,
+	MAX77693_CHG_IRQ_CHG_I,
+	MAX77693_CHG_IRQ_CHGIN_I,
+
+	/* MUIC INT1 */
+	MAX77693_MUIC_IRQ_INT1_ADC,
+	MAX77693_MUIC_IRQ_INT1_ADC_LOW,
+	MAX77693_MUIC_IRQ_INT1_ADC_ERR,
+	MAX77693_MUIC_IRQ_INT1_ADC1K,
+
+	/* MUIC INT2 */
+	MAX77693_MUIC_IRQ_INT2_CHGTYP,
+	MAX77693_MUIC_IRQ_INT2_CHGDETREUN,
+	MAX77693_MUIC_IRQ_INT2_DCDTMR,
+	MAX77693_MUIC_IRQ_INT2_DXOVP,
+	MAX77693_MUIC_IRQ_INT2_VBVOLT,
+	MAX77693_MUIC_IRQ_INT2_VIDRM,
+
+	/* MUIC INT3 */
+	MAX77693_MUIC_IRQ_INT3_EOC,
+	MAX77693_MUIC_IRQ_INT3_CGMBC,
+	MAX77693_MUIC_IRQ_INT3_OVP,
+	MAX77693_MUIC_IRQ_INT3_MBCCHG_ERR,
+	MAX77693_MUIC_IRQ_INT3_CHG_ENABLED,
+	MAX77693_MUIC_IRQ_INT3_BAT_DET,
+
+	MAX77693_IRQ_NR,
+};
+
+struct max77693_dev {
+	struct device *dev;
+	struct i2c_client *i2c;		/* 0xCC , PMIC, Charger, Flash LED */
+	struct i2c_client *muic;	/* 0x4A , MUIC */
+	struct i2c_client *haptic;	/* 0x90 , Haptic */
+	struct mutex iolock;
+
+	int type;
+
+	struct regmap *regmap;
+	struct regmap *regmap_muic;
+	struct regmap *regmap_haptic;
+
+	struct irq_domain *irq_domain;
+
+	int irq;
+	int irq_gpio;
+	bool wakeup;
+	struct mutex irqlock;
+	int irq_masks_cur[MAX77693_IRQ_GROUP_NR];
+	int irq_masks_cache[MAX77693_IRQ_GROUP_NR];
+};
+
+enum max77693_types {
+	TYPE_MAX77693,
+};
+
+extern int max77693_read_reg(struct regmap *map, u8 reg, u8 *dest);
+extern int max77693_bulk_read(struct regmap *map, u8 reg, int count,
+				u8 *buf);
+extern int max77693_write_reg(struct regmap *map, u8 reg, u8 value);
+extern int max77693_bulk_write(struct regmap *map, u8 reg, int count,
+				u8 *buf);
+extern int max77693_update_reg(struct regmap *map, u8 reg, u8 val, u8 mask);
+
+extern int max77693_irq_init(struct max77693_dev *max77686);
+extern void max77693_irq_exit(struct max77693_dev *max77686);
+extern int max77693_irq_resume(struct max77693_dev *max77686);
+
+#endif /*  __LINUX_MFD_MAX77693_PRIV_H */
diff --git a/include/linux/mfd/max77693.h b/include/linux/mfd/max77693.h
new file mode 100644
index 000000000000..1d28ae90384e
--- /dev/null
+++ b/include/linux/mfd/max77693.h
@@ -0,0 +1,36 @@
+/*
+ * max77693.h - Driver for the Maxim 77693
+ *
+ *  Copyright (C) 2012 Samsung Electrnoics
+ *  SangYoung Son <hello.son@samsung.com>
+ *
+ * This program is not provided / owned by Maxim Integrated Products.
+ *
+ * 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
+ *
+ * This driver is based on max8997.h
+ *
+ * MAX77693 has PMIC, Charger, Flash LED, Haptic, MUIC devices.
+ * The devices share the same I2C bus and included in
+ * this mfd driver.
+ */
+
+#ifndef __LINUX_MFD_MAX77693_H
+#define __LINUX_MFD_MAX77693_H
+
+struct max77693_platform_data {
+	int wakeup;
+};
+#endif	/* __LINUX_MFD_MAX77693_H */
diff --git a/include/linux/mfd/sta2x11-mfd.h b/include/linux/mfd/sta2x11-mfd.h
new file mode 100644
index 000000000000..d179227e866f
--- /dev/null
+++ b/include/linux/mfd/sta2x11-mfd.h
@@ -0,0 +1,324 @@
+/*
+ * Copyright (c) 2009-2011 Wind River Systems, Inc.
+ * Copyright (c) 2011 ST Microelectronics (Alessandro Rubini)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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
+ *
+ * The STMicroelectronics ConneXt (STA2X11) chip has several unrelated
+ * functions in one PCI endpoint functions. This driver simply
+ * registers the platform devices in this iomemregion and exports a few
+ * functions to access common registers
+ */
+
+#ifndef __STA2X11_MFD_H
+#define __STA2X11_MFD_H
+#include <linux/types.h>
+#include <linux/pci.h>
+
+/*
+ * The MFD PCI block includes the GPIO peripherals and other register blocks.
+ * For GPIO, we have 32*4 bits (I use "gsta" for "gpio sta2x11".)
+ */
+#define GSTA_GPIO_PER_BLOCK	32
+#define GSTA_NR_BLOCKS		4
+#define GSTA_NR_GPIO		(GSTA_GPIO_PER_BLOCK * GSTA_NR_BLOCKS)
+
+/* Pinconfig is set by the board definition: altfunc, pull-up, pull-down */
+struct sta2x11_gpio_pdata {
+	unsigned pinconfig[GSTA_NR_GPIO];
+};
+
+/* Macros below lifted from sh_pfc.h, with minor differences */
+#define PINMUX_TYPE_NONE		0
+#define PINMUX_TYPE_FUNCTION		1
+#define PINMUX_TYPE_OUTPUT_LOW		2
+#define PINMUX_TYPE_OUTPUT_HIGH		3
+#define PINMUX_TYPE_INPUT		4
+#define PINMUX_TYPE_INPUT_PULLUP	5
+#define PINMUX_TYPE_INPUT_PULLDOWN	6
+
+/* Give names to GPIO pins, like PXA does, taken from the manual */
+#define STA2X11_GPIO0			0
+#define STA2X11_GPIO1			1
+#define STA2X11_GPIO2			2
+#define STA2X11_GPIO3			3
+#define STA2X11_GPIO4			4
+#define STA2X11_GPIO5			5
+#define STA2X11_GPIO6			6
+#define STA2X11_GPIO7			7
+#define STA2X11_GPIO8_RGBOUT_RED7	8
+#define STA2X11_GPIO9_RGBOUT_RED6	9
+#define STA2X11_GPIO10_RGBOUT_RED5	10
+#define STA2X11_GPIO11_RGBOUT_RED4	11
+#define STA2X11_GPIO12_RGBOUT_RED3	12
+#define STA2X11_GPIO13_RGBOUT_RED2	13
+#define STA2X11_GPIO14_RGBOUT_RED1	14
+#define STA2X11_GPIO15_RGBOUT_RED0	15
+#define STA2X11_GPIO16_RGBOUT_GREEN7	16
+#define STA2X11_GPIO17_RGBOUT_GREEN6	17
+#define STA2X11_GPIO18_RGBOUT_GREEN5	18
+#define STA2X11_GPIO19_RGBOUT_GREEN4	19
+#define STA2X11_GPIO20_RGBOUT_GREEN3	20
+#define STA2X11_GPIO21_RGBOUT_GREEN2	21
+#define STA2X11_GPIO22_RGBOUT_GREEN1	22
+#define STA2X11_GPIO23_RGBOUT_GREEN0	23
+#define STA2X11_GPIO24_RGBOUT_BLUE7	24
+#define STA2X11_GPIO25_RGBOUT_BLUE6	25
+#define STA2X11_GPIO26_RGBOUT_BLUE5	26
+#define STA2X11_GPIO27_RGBOUT_BLUE4	27
+#define STA2X11_GPIO28_RGBOUT_BLUE3	28
+#define STA2X11_GPIO29_RGBOUT_BLUE2	29
+#define STA2X11_GPIO30_RGBOUT_BLUE1	30
+#define STA2X11_GPIO31_RGBOUT_BLUE0	31
+#define STA2X11_GPIO32_RGBOUT_VSYNCH	32
+#define STA2X11_GPIO33_RGBOUT_HSYNCH	33
+#define STA2X11_GPIO34_RGBOUT_DEN	34
+#define STA2X11_GPIO35_ETH_CRS_DV	35
+#define STA2X11_GPIO36_ETH_TXD1		36
+#define STA2X11_GPIO37_ETH_TXD0		37
+#define STA2X11_GPIO38_ETH_TX_EN	38
+#define STA2X11_GPIO39_MDIO		39
+#define STA2X11_GPIO40_ETH_REF_CLK	40
+#define STA2X11_GPIO41_ETH_RXD1		41
+#define STA2X11_GPIO42_ETH_RXD0		42
+#define STA2X11_GPIO43_MDC		43
+#define STA2X11_GPIO44_CAN_TX		44
+#define STA2X11_GPIO45_CAN_RX		45
+#define STA2X11_GPIO46_MLB_DAT		46
+#define STA2X11_GPIO47_MLB_SIG		47
+#define STA2X11_GPIO48_SPI0_CLK		48
+#define STA2X11_GPIO49_SPI0_TXD		49
+#define STA2X11_GPIO50_SPI0_RXD		50
+#define STA2X11_GPIO51_SPI0_FRM		51
+#define STA2X11_GPIO52_SPI1_CLK		52
+#define STA2X11_GPIO53_SPI1_TXD		53
+#define STA2X11_GPIO54_SPI1_RXD		54
+#define STA2X11_GPIO55_SPI1_FRM		55
+#define STA2X11_GPIO56_SPI2_CLK		56
+#define STA2X11_GPIO57_SPI2_TXD		57
+#define STA2X11_GPIO58_SPI2_RXD		58
+#define STA2X11_GPIO59_SPI2_FRM		59
+#define STA2X11_GPIO60_I2C0_SCL		60
+#define STA2X11_GPIO61_I2C0_SDA		61
+#define STA2X11_GPIO62_I2C1_SCL		62
+#define STA2X11_GPIO63_I2C1_SDA		63
+#define STA2X11_GPIO64_I2C2_SCL		64
+#define STA2X11_GPIO65_I2C2_SDA		65
+#define STA2X11_GPIO66_I2C3_SCL		66
+#define STA2X11_GPIO67_I2C3_SDA		67
+#define STA2X11_GPIO68_MSP0_RCK		68
+#define STA2X11_GPIO69_MSP0_RXD		69
+#define STA2X11_GPIO70_MSP0_RFS		70
+#define STA2X11_GPIO71_MSP0_TCK		71
+#define STA2X11_GPIO72_MSP0_TXD		72
+#define STA2X11_GPIO73_MSP0_TFS		73
+#define STA2X11_GPIO74_MSP0_SCK		74
+#define STA2X11_GPIO75_MSP1_CK		75
+#define STA2X11_GPIO76_MSP1_RXD		76
+#define STA2X11_GPIO77_MSP1_FS		77
+#define STA2X11_GPIO78_MSP1_TXD		78
+#define STA2X11_GPIO79_MSP2_CK		79
+#define STA2X11_GPIO80_MSP2_RXD		80
+#define STA2X11_GPIO81_MSP2_FS		81
+#define STA2X11_GPIO82_MSP2_TXD		82
+#define STA2X11_GPIO83_MSP3_CK		83
+#define STA2X11_GPIO84_MSP3_RXD		84
+#define STA2X11_GPIO85_MSP3_FS		85
+#define STA2X11_GPIO86_MSP3_TXD		86
+#define STA2X11_GPIO87_MSP4_CK		87
+#define STA2X11_GPIO88_MSP4_RXD		88
+#define STA2X11_GPIO89_MSP4_FS		89
+#define STA2X11_GPIO90_MSP4_TXD		90
+#define STA2X11_GPIO91_MSP5_CK		91
+#define STA2X11_GPIO92_MSP5_RXD		92
+#define STA2X11_GPIO93_MSP5_FS		93
+#define STA2X11_GPIO94_MSP5_TXD		94
+#define STA2X11_GPIO95_SDIO3_DAT3	95
+#define STA2X11_GPIO96_SDIO3_DAT2	96
+#define STA2X11_GPIO97_SDIO3_DAT1	97
+#define STA2X11_GPIO98_SDIO3_DAT0	98
+#define STA2X11_GPIO99_SDIO3_CLK	99
+#define STA2X11_GPIO100_SDIO3_CMD	100
+#define STA2X11_GPIO101			101
+#define STA2X11_GPIO102			102
+#define STA2X11_GPIO103			103
+#define STA2X11_GPIO104			104
+#define STA2X11_GPIO105_SDIO2_DAT3	105
+#define STA2X11_GPIO106_SDIO2_DAT2	106
+#define STA2X11_GPIO107_SDIO2_DAT1	107
+#define STA2X11_GPIO108_SDIO2_DAT0	108
+#define STA2X11_GPIO109_SDIO2_CLK	109
+#define STA2X11_GPIO110_SDIO2_CMD	110
+#define STA2X11_GPIO111			111
+#define STA2X11_GPIO112			112
+#define STA2X11_GPIO113			113
+#define STA2X11_GPIO114			114
+#define STA2X11_GPIO115_SDIO1_DAT3	115
+#define STA2X11_GPIO116_SDIO1_DAT2	116
+#define STA2X11_GPIO117_SDIO1_DAT1	117
+#define STA2X11_GPIO118_SDIO1_DAT0	118
+#define STA2X11_GPIO119_SDIO1_CLK	119
+#define STA2X11_GPIO120_SDIO1_CMD	120
+#define STA2X11_GPIO121			121
+#define STA2X11_GPIO122			122
+#define STA2X11_GPIO123			123
+#define STA2X11_GPIO124			124
+#define STA2X11_GPIO125_UART2_TXD	125
+#define STA2X11_GPIO126_UART2_RXD	126
+#define STA2X11_GPIO127_UART3_TXD	127
+
+/*
+ * The APB bridge has its own registers, needed by our users as well.
+ * They are accessed with the following read/mask/write function.
+ */
+u32 sta2x11_apbreg_mask(struct pci_dev *pdev, u32 reg, u32 mask, u32 val);
+
+/* CAN and MLB */
+#define APBREG_BSR	0x00	/* Bridge Status Reg */
+#define APBREG_PAER	0x08	/* Peripherals Address Error Reg */
+#define APBREG_PWAC	0x20	/* Peripheral Write Access Control reg */
+#define APBREG_PRAC	0x40	/* Peripheral Read Access Control reg */
+#define APBREG_PCG	0x60	/* Peripheral Clock Gating Reg */
+#define APBREG_PUR	0x80	/* Peripheral Under Reset Reg */
+#define APBREG_EMU_PCG	0xA0	/* Emulator Peripheral Clock Gating Reg */
+
+#define APBREG_CAN	(1 << 1)
+#define APBREG_MLB	(1 << 3)
+
+/* SARAC */
+#define APBREG_BSR_SARAC     0x100 /* Bridge Status Reg */
+#define APBREG_PAER_SARAC    0x108 /* Peripherals Address Error Reg */
+#define APBREG_PWAC_SARAC    0x120 /* Peripheral Write Access Control reg */
+#define APBREG_PRAC_SARAC    0x140 /* Peripheral Read Access Control reg */
+#define APBREG_PCG_SARAC     0x160 /* Peripheral Clock Gating Reg */
+#define APBREG_PUR_SARAC     0x180 /* Peripheral Under Reset Reg */
+#define APBREG_EMU_PCG_SARAC 0x1A0 /* Emulator Peripheral Clock Gating Reg */
+
+#define APBREG_SARAC	(1 << 2)
+
+/*
+ * The system controller has its own registers. Some of these are accessed
+ * by out users as well, using the following read/mask/write/function
+ */
+u32 sta2x11_sctl_mask(struct pci_dev *pdev, u32 reg, u32 mask, u32 val);
+
+#define SCTL_SCCTL		0x00	/* System controller control register */
+#define SCTL_ARMCFG		0x04	/* ARM configuration register */
+#define SCTL_SCPLLCTL		0x08	/* PLL control status register */
+#define SCTL_SCPLLFCTRL		0x0c	/* PLL frequency control register */
+#define SCTL_SCRESFRACT		0x10	/* PLL fractional input register */
+#define SCTL_SCRESCTRL1		0x14	/* Peripheral reset control 1 */
+#define SCTL_SCRESXTRL2		0x18	/* Peripheral reset control 2 */
+#define SCTL_SCPEREN0		0x1c	/* Peripheral clock enable register 0 */
+#define SCTL_SCPEREN1		0x20	/* Peripheral clock enable register 1 */
+#define SCTL_SCPEREN2		0x24	/* Peripheral clock enable register 2 */
+#define SCTL_SCGRST		0x28	/* Peripheral global reset */
+#define SCTL_SCPCIPMCR1		0x30	/* PCI power management control 1 */
+#define SCTL_SCPCIPMCR2		0x34	/* PCI power management control 2 */
+#define SCTL_SCPCIPMSR1		0x38	/* PCI power management status 1 */
+#define SCTL_SCPCIPMSR2		0x3c	/* PCI power management status 2 */
+#define SCTL_SCPCIPMSR3		0x40	/* PCI power management status 3 */
+#define SCTL_SCINTREN		0x44	/* Interrupt enable */
+#define SCTL_SCRISR		0x48	/* RAW interrupt status */
+#define SCTL_SCCLKSTAT0		0x4c	/* Peripheral clocks status 0 */
+#define SCTL_SCCLKSTAT1		0x50	/* Peripheral clocks status 1 */
+#define SCTL_SCCLKSTAT2		0x54	/* Peripheral clocks status 2 */
+#define SCTL_SCRSTSTA		0x58	/* Reset status register */
+
+#define SCTL_SCRESCTRL1_USB_PHY_POR	(1 << 0)
+#define SCTL_SCRESCTRL1_USB_OTG	(1 << 1)
+#define SCTL_SCRESCTRL1_USB_HRST	(1 << 2)
+#define SCTL_SCRESCTRL1_USB_PHY_HOST	(1 << 3)
+#define SCTL_SCRESCTRL1_SATAII	(1 << 4)
+#define SCTL_SCRESCTRL1_VIP		(1 << 5)
+#define SCTL_SCRESCTRL1_PER_MMC0	(1 << 6)
+#define SCTL_SCRESCTRL1_PER_MMC1	(1 << 7)
+#define SCTL_SCRESCTRL1_PER_GPIO0	(1 << 8)
+#define SCTL_SCRESCTRL1_PER_GPIO1	(1 << 9)
+#define SCTL_SCRESCTRL1_PER_GPIO2	(1 << 10)
+#define SCTL_SCRESCTRL1_PER_GPIO3	(1 << 11)
+#define SCTL_SCRESCTRL1_PER_MTU0	(1 << 12)
+#define SCTL_SCRESCTRL1_KER_SPI0	(1 << 13)
+#define SCTL_SCRESCTRL1_KER_SPI1	(1 << 14)
+#define SCTL_SCRESCTRL1_KER_SPI2	(1 << 15)
+#define SCTL_SCRESCTRL1_KER_MCI0	(1 << 16)
+#define SCTL_SCRESCTRL1_KER_MCI1	(1 << 17)
+#define SCTL_SCRESCTRL1_PRE_HSI2C0	(1 << 18)
+#define SCTL_SCRESCTRL1_PER_HSI2C1	(1 << 19)
+#define SCTL_SCRESCTRL1_PER_HSI2C2	(1 << 20)
+#define SCTL_SCRESCTRL1_PER_HSI2C3	(1 << 21)
+#define SCTL_SCRESCTRL1_PER_MSP0	(1 << 22)
+#define SCTL_SCRESCTRL1_PER_MSP1	(1 << 23)
+#define SCTL_SCRESCTRL1_PER_MSP2	(1 << 24)
+#define SCTL_SCRESCTRL1_PER_MSP3	(1 << 25)
+#define SCTL_SCRESCTRL1_PER_MSP4	(1 << 26)
+#define SCTL_SCRESCTRL1_PER_MSP5	(1 << 27)
+#define SCTL_SCRESCTRL1_PER_MMC	(1 << 28)
+#define SCTL_SCRESCTRL1_KER_MSP0	(1 << 29)
+#define SCTL_SCRESCTRL1_KER_MSP1	(1 << 30)
+#define SCTL_SCRESCTRL1_KER_MSP2	(1 << 31)
+
+#define SCTL_SCPEREN0_UART0		(1 << 0)
+#define SCTL_SCPEREN0_UART1		(1 << 1)
+#define SCTL_SCPEREN0_UART2		(1 << 2)
+#define SCTL_SCPEREN0_UART3		(1 << 3)
+#define SCTL_SCPEREN0_MSP0		(1 << 4)
+#define SCTL_SCPEREN0_MSP1		(1 << 5)
+#define SCTL_SCPEREN0_MSP2		(1 << 6)
+#define SCTL_SCPEREN0_MSP3		(1 << 7)
+#define SCTL_SCPEREN0_MSP4		(1 << 8)
+#define SCTL_SCPEREN0_MSP5		(1 << 9)
+#define SCTL_SCPEREN0_SPI0		(1 << 10)
+#define SCTL_SCPEREN0_SPI1		(1 << 11)
+#define SCTL_SCPEREN0_SPI2		(1 << 12)
+#define SCTL_SCPEREN0_I2C0		(1 << 13)
+#define SCTL_SCPEREN0_I2C1		(1 << 14)
+#define SCTL_SCPEREN0_I2C2		(1 << 15)
+#define SCTL_SCPEREN0_I2C3		(1 << 16)
+#define SCTL_SCPEREN0_SVDO_LVDS		(1 << 17)
+#define SCTL_SCPEREN0_USB_HOST		(1 << 18)
+#define SCTL_SCPEREN0_USB_OTG		(1 << 19)
+#define SCTL_SCPEREN0_MCI0		(1 << 20)
+#define SCTL_SCPEREN0_MCI1		(1 << 21)
+#define SCTL_SCPEREN0_MCI2		(1 << 22)
+#define SCTL_SCPEREN0_MCI3		(1 << 23)
+#define SCTL_SCPEREN0_SATA		(1 << 24)
+#define SCTL_SCPEREN0_ETHERNET		(1 << 25)
+#define SCTL_SCPEREN0_VIC		(1 << 26)
+#define SCTL_SCPEREN0_DMA_AUDIO		(1 << 27)
+#define SCTL_SCPEREN0_DMA_SOC		(1 << 28)
+#define SCTL_SCPEREN0_RAM		(1 << 29)
+#define SCTL_SCPEREN0_VIP		(1 << 30)
+#define SCTL_SCPEREN0_ARM		(1 << 31)
+
+#define SCTL_SCPEREN1_UART0		(1 << 0)
+#define SCTL_SCPEREN1_UART1		(1 << 1)
+#define SCTL_SCPEREN1_UART2		(1 << 2)
+#define SCTL_SCPEREN1_UART3		(1 << 3)
+#define SCTL_SCPEREN1_MSP0		(1 << 4)
+#define SCTL_SCPEREN1_MSP1		(1 << 5)
+#define SCTL_SCPEREN1_MSP2		(1 << 6)
+#define SCTL_SCPEREN1_MSP3		(1 << 7)
+#define SCTL_SCPEREN1_MSP4		(1 << 8)
+#define SCTL_SCPEREN1_MSP5		(1 << 9)
+#define SCTL_SCPEREN1_SPI0		(1 << 10)
+#define SCTL_SCPEREN1_SPI1		(1 << 11)
+#define SCTL_SCPEREN1_SPI2		(1 << 12)
+#define SCTL_SCPEREN1_I2C0		(1 << 13)
+#define SCTL_SCPEREN1_I2C1		(1 << 14)
+#define SCTL_SCPEREN1_I2C2		(1 << 15)
+#define SCTL_SCPEREN1_I2C3		(1 << 16)
+#define SCTL_SCPEREN1_USB_PHY		(1 << 17)
+
+#endif /* __STA2X11_MFD_H */
diff --git a/include/linux/mfd/stmpe.h b/include/linux/mfd/stmpe.h
index 8516fd1eaabc..f8d5b4d5843f 100644
--- a/include/linux/mfd/stmpe.h
+++ b/include/linux/mfd/stmpe.h
@@ -117,7 +117,7 @@ struct matrix_keymap_data;
  * @no_autorepeat: disable key autorepeat
  */
 struct stmpe_keypad_platform_data {
-	struct matrix_keymap_data *keymap_data;
+	const struct matrix_keymap_data *keymap_data;
 	unsigned int debounce_ms;
 	unsigned int scan_count;
 	bool no_autorepeat;
diff --git a/include/linux/mfd/tps65910.h b/include/linux/mfd/tps65910.h
index 1c6c2860d1a6..dd8dc0a6c462 100644
--- a/include/linux/mfd/tps65910.h
+++ b/include/linux/mfd/tps65910.h
@@ -18,6 +18,7 @@
 #define __LINUX_MFD_TPS65910_H
 
 #include <linux/gpio.h>
+#include <linux/regmap.h>
 
 /* TPS chip id list */
 #define TPS65910			0
@@ -783,6 +784,18 @@
 #define TPS65910_SLEEP_CONTROL_EXT_INPUT_EN3		0x4
 #define TPS65911_SLEEP_CONTROL_EXT_INPUT_SLEEP		0x8
 
+/*
+ * Sleep keepon data: Maintains the state in sleep mode
+ * @therm_keepon: Keep on the thermal monitoring in sleep state.
+ * @clkout32k_keepon: Keep on the 32KHz clock output in sleep state.
+ * @i2chs_keepon: Keep on high speed internal clock in sleep state.
+ */
+struct tps65910_sleep_keepon_data {
+	unsigned therm_keepon:1;
+	unsigned clkout32k_keepon:1;
+	unsigned i2chs_keepon:1;
+};
+
 /**
  * struct tps65910_board
  * Board platform data may be used to initialize regulators.
@@ -794,6 +807,8 @@ struct tps65910_board {
 	int irq_base;
 	int vmbch_threshold;
 	int vmbch2_threshold;
+	bool en_dev_slp;
+	struct tps65910_sleep_keepon_data *slp_keepon;
 	bool en_gpio_sleep[TPS6591X_MAX_NUM_GPIO];
 	unsigned long regulator_ext_sleep_control[TPS65910_NUM_REGS];
 	struct regulator_init_data *tps65910_pmic_init_data[TPS65910_NUM_REGS];
@@ -809,16 +824,14 @@ struct tps65910 {
 	struct regmap *regmap;
 	struct mutex io_mutex;
 	unsigned int id;
-	int (*read)(struct tps65910 *tps65910, u8 reg, int size, void *dest);
-	int (*write)(struct tps65910 *tps65910, u8 reg, int size, void *src);
 
 	/* Client devices */
 	struct tps65910_pmic *pmic;
 	struct tps65910_rtc *rtc;
 	struct tps65910_power *power;
 
-	/* GPIO Handling */
-	struct gpio_chip gpio;
+	/* Device node parsed board data */
+	struct tps65910_board *of_plat_data;
 
 	/* IRQ Handling */
 	struct mutex irq_lock;
@@ -826,6 +839,7 @@ struct tps65910 {
 	int irq_base;
 	int irq_num;
 	u32 irq_mask;
+	struct irq_domain *domain;
 };
 
 struct tps65910_platform_data {
@@ -833,9 +847,6 @@ struct tps65910_platform_data {
 	int irq_base;
 };
 
-int tps65910_set_bits(struct tps65910 *tps65910, u8 reg, u8 mask);
-int tps65910_clear_bits(struct tps65910 *tps65910, u8 reg, u8 mask);
-void tps65910_gpio_init(struct tps65910 *tps65910, int gpio_base);
 int tps65910_irq_init(struct tps65910 *tps65910, int irq,
 		struct tps65910_platform_data *pdata);
 int tps65910_irq_exit(struct tps65910 *tps65910);
@@ -845,4 +856,28 @@ static inline int tps65910_chip_id(struct tps65910 *tps65910)
 	return tps65910->id;
 }
 
+static inline int tps65910_reg_read(struct tps65910 *tps65910, u8 reg,
+		unsigned int *val)
+{
+	return regmap_read(tps65910->regmap, reg, val);
+}
+
+static inline int tps65910_reg_write(struct tps65910 *tps65910, u8 reg,
+		unsigned int val)
+{
+	return regmap_write(tps65910->regmap, reg, val);
+}
+
+static inline int tps65910_reg_set_bits(struct tps65910 *tps65910, u8 reg,
+		u8 mask)
+{
+	return regmap_update_bits(tps65910->regmap, reg, mask, mask);
+}
+
+static inline int tps65910_reg_clear_bits(struct tps65910 *tps65910, u8 reg,
+		u8 mask)
+{
+	return regmap_update_bits(tps65910->regmap, reg, mask, 0);
+}
+
 #endif /*  __LINUX_MFD_TPS65910_H */
diff --git a/include/linux/mfd/twl6040.h b/include/linux/mfd/twl6040.h
index b15b5f03f5c4..6659487c31e7 100644
--- a/include/linux/mfd/twl6040.h
+++ b/include/linux/mfd/twl6040.h
@@ -27,6 +27,7 @@
 
 #include <linux/interrupt.h>
 #include <linux/mfd/core.h>
+#include <linux/regulator/consumer.h>
 
 #define TWL6040_REG_ASICID		0x01
 #define TWL6040_REG_ASICREV		0x02
@@ -203,6 +204,7 @@ struct regmap;
 struct twl6040 {
 	struct device *dev;
 	struct regmap *regmap;
+	struct regulator_bulk_data supplies[2]; /* supplies for vio, v2v1 */
 	struct mutex mutex;
 	struct mutex io_mutex;
 	struct mutex irq_mutex;
diff --git a/include/linux/mfd/wm831x/core.h b/include/linux/mfd/wm831x/core.h
index 4b1211859f74..4a3b83a77614 100644
--- a/include/linux/mfd/wm831x/core.h
+++ b/include/linux/mfd/wm831x/core.h
@@ -17,6 +17,7 @@
 
 #include <linux/completion.h>
 #include <linux/interrupt.h>
+#include <linux/irqdomain.h>
 #include <linux/list.h>
 #include <linux/regmap.h>
 
@@ -338,6 +339,7 @@
 #define WM831X_FLL_CLK_SRC_WIDTH                     2  /* FLL_CLK_SRC - [1:0] */
 
 struct regulator_dev;
+struct irq_domain;
 
 #define WM831X_NUM_IRQ_REGS 5
 #define WM831X_NUM_GPIO_REGS 16
@@ -367,7 +369,7 @@ struct wm831x {
 
 	int irq;  /* Our chip IRQ */
 	struct mutex irq_lock;
-	int irq_base;
+	struct irq_domain *irq_domain;
 	int irq_masks_cur[WM831X_NUM_IRQ_REGS];   /* Currently active value */
 	int irq_masks_cache[WM831X_NUM_IRQ_REGS]; /* Cached hardware value */
 
@@ -382,7 +384,8 @@ struct wm831x {
 
 	/* Used by the interrupt controller code to post writes */
 	int gpio_update[WM831X_NUM_GPIO_REGS];
-	bool gpio_level[WM831X_NUM_GPIO_REGS];
+	bool gpio_level_high[WM831X_NUM_GPIO_REGS];
+	bool gpio_level_low[WM831X_NUM_GPIO_REGS];
 
 	struct mutex auxadc_lock;
 	struct list_head auxadc_pending;
@@ -417,6 +420,11 @@ int wm831x_irq_init(struct wm831x *wm831x, int irq);
 void wm831x_irq_exit(struct wm831x *wm831x);
 void wm831x_auxadc_init(struct wm831x *wm831x);
 
+static inline int wm831x_irq(struct wm831x *wm831x, int irq)
+{
+	return irq_create_mapping(wm831x->irq_domain, irq);
+}
+
 extern struct regmap_config wm831x_regmap_config;
 
 #endif
diff --git a/include/linux/mfd/wm8350/core.h b/include/linux/mfd/wm8350/core.h
index 98fcc977e82b..9192b6404a73 100644
--- a/include/linux/mfd/wm8350/core.h
+++ b/include/linux/mfd/wm8350/core.h
@@ -602,6 +602,7 @@ extern const u16 wm8352_mode2_defaults[];
 extern const u16 wm8352_mode3_defaults[];
 
 struct wm8350;
+struct regmap;
 
 struct wm8350_hwmon {
 	struct platform_device *pdev;
@@ -612,13 +613,7 @@ struct wm8350 {
 	struct device *dev;
 
 	/* device IO */
-	union {
-		struct i2c_client *i2c_client;
-		struct spi_device *spi_device;
-	};
-	int (*read_dev)(struct wm8350 *wm8350, char reg, int size, void *dest);
-	int (*write_dev)(struct wm8350 *wm8350, char reg, int size,
-			 void *src);
+	struct regmap *regmap;
 	u16 *reg_cache;
 
 	struct mutex auxadc_mutex;
diff --git a/include/linux/mfd/wm8400-private.h b/include/linux/mfd/wm8400-private.h
index 0147b6968510..2de565b94d0c 100644
--- a/include/linux/mfd/wm8400-private.h
+++ b/include/linux/mfd/wm8400-private.h
@@ -24,19 +24,14 @@
 #include <linux/mfd/wm8400.h>
 #include <linux/mutex.h>
 #include <linux/platform_device.h>
-
-struct regmap;
+#include <linux/regmap.h>
 
 #define WM8400_REGISTER_COUNT 0x55
 
 struct wm8400 {
 	struct device *dev;
-
-	struct mutex io_lock;
 	struct regmap *regmap;
 
-	u16 reg_cache[WM8400_REGISTER_COUNT];
-
 	struct platform_device regulators[6];
 };
 
@@ -930,6 +925,11 @@ struct wm8400 {
 
 u16 wm8400_reg_read(struct wm8400 *wm8400, u8 reg);
 int wm8400_block_read(struct wm8400 *wm8400, u8 reg, int count, u16 *data);
-int wm8400_set_bits(struct wm8400 *wm8400, u8 reg, u16 mask, u16 val);
+
+static inline int wm8400_set_bits(struct wm8400 *wm8400, u8 reg,
+				  u16 mask, u16 val)
+{
+	return regmap_update_bits(wm8400->regmap, reg, mask, val);
+}
 
 #endif
diff --git a/include/linux/mfd/wm8994/core.h b/include/linux/mfd/wm8994/core.h
index 6695c3ec4518..1f173306bf05 100644
--- a/include/linux/mfd/wm8994/core.h
+++ b/include/linux/mfd/wm8994/core.h
@@ -57,6 +57,7 @@ struct wm8994 {
 
 	enum wm8994_type type;
 	int revision;
+	int cust_id;
 
 	struct device *dev;
 	struct regmap *regmap;
diff --git a/include/linux/mfd/wm8994/registers.h b/include/linux/mfd/wm8994/registers.h
index 86e6a032a078..053548961c15 100644
--- a/include/linux/mfd/wm8994/registers.h
+++ b/include/linux/mfd/wm8994/registers.h
@@ -2212,6 +2212,9 @@
 /*
  * R256 (0x100) - Chip Revision
  */
+#define WM8994_CUST_ID_MASK                     0xFF00  /* CUST_ID - [15:8] */
+#define WM8994_CUST_ID_SHIFT                         8  /* CUST_ID - [15:8] */
+#define WM8994_CUST_ID_WIDTH                         8  /* CUST_ID - [15:8] */
 #define WM8994_CHIP_REV_MASK                    0x000F  /* CHIP_REV - [3:0] */
 #define WM8994_CHIP_REV_SHIFT                        0  /* CHIP_REV - [3:0] */
 #define WM8994_CHIP_REV_WIDTH                        4  /* CHIP_REV - [3:0] */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 7d5c37f24c63..ce26716238c3 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -321,6 +321,7 @@ static inline int is_vmalloc_or_module_addr(const void *x)
 static inline void compound_lock(struct page *page)
 {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	VM_BUG_ON(PageSlab(page));
 	bit_spin_lock(PG_compound_lock, &page->flags);
 #endif
 }
@@ -328,6 +329,7 @@ static inline void compound_lock(struct page *page)
 static inline void compound_unlock(struct page *page)
 {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	VM_BUG_ON(PageSlab(page));
 	bit_spin_unlock(PG_compound_lock, &page->flags);
 #endif
 }
@@ -871,8 +873,6 @@ extern void pagefault_out_of_memory(void);
 extern void show_free_areas(unsigned int flags);
 extern bool skip_free_areas_node(unsigned int flags, int nid);
 
-int shmem_lock(struct file *file, int lock, struct user_struct *user);
-struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags);
 int shmem_zero_setup(struct vm_area_struct *);
 
 extern int can_do_mlock(void);
@@ -951,11 +951,9 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping,
 extern void truncate_pagecache(struct inode *inode, loff_t old, loff_t new);
 extern void truncate_setsize(struct inode *inode, loff_t newsize);
 extern int vmtruncate(struct inode *inode, loff_t offset);
-extern int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end);
 void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end);
 int truncate_inode_page(struct address_space *mapping, struct page *page);
 int generic_error_remove_page(struct address_space *mapping, struct page *page);
-
 int invalidate_inode_page(struct page *page);
 
 #ifdef CONFIG_MMU
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 26574c726121..dad95bdd06d7 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -345,17 +345,6 @@ struct mm_struct {
 	/* Architecture-specific MM context */
 	mm_context_t context;
 
-	/* Swap token stuff */
-	/*
-	 * Last value of global fault stamp as seen by this process.
-	 * In other words, this value gives an indication of how long
-	 * it has been since this task got the token.
-	 * Look at mm/thrash.c
-	 */
-	unsigned int faultstamp;
-	unsigned int token_priority;
-	unsigned int last_interval;
-
 	unsigned long flags; /* Must use atomic bitops to access the bits */
 
 	struct core_state *core_state; /* coredumping support */
diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h
index c04ecfe03f7f..580bd587d916 100644
--- a/include/linux/mmdebug.h
+++ b/include/linux/mmdebug.h
@@ -4,7 +4,7 @@
 #ifdef CONFIG_DEBUG_VM
 #define VM_BUG_ON(cond) BUG_ON(cond)
 #else
-#define VM_BUG_ON(cond) do { (void)(cond); } while (0)
+#define VM_BUG_ON(cond) BUILD_BUG_ON_INVALID(cond)
 #endif
 
 #ifdef CONFIG_DEBUG_VIRTUAL
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 54631776dff2..588c5cb2851d 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -185,8 +185,22 @@ static inline int is_unevictable_lru(enum lru_list lru)
 	return (lru == LRU_UNEVICTABLE);
 }
 
+struct zone_reclaim_stat {
+	/*
+	 * The pageout code in vmscan.c keeps track of how many of the
+	 * mem/swap backed and file backed pages are referenced.
+	 * The higher the rotated/scanned ratio, the more valuable
+	 * that cache is.
+	 *
+	 * The anon LRU stats live in [0], file LRU stats in [1]
+	 */
+	unsigned long		recent_rotated[2];
+	unsigned long		recent_scanned[2];
+};
+
 struct lruvec {
 	struct list_head lists[NR_LRU_LISTS];
+	struct zone_reclaim_stat reclaim_stat;
 };
 
 /* Mask used at gathering information at once (see memcontrol.c) */
@@ -313,19 +327,6 @@ enum zone_type {
 #error ZONES_SHIFT -- too many zones configured adjust calculation
 #endif
 
-struct zone_reclaim_stat {
-	/*
-	 * The pageout code in vmscan.c keeps track of how many of the
-	 * mem/swap backed and file backed pages are referenced.
-	 * The higher the rotated/scanned ratio, the more valuable
-	 * that cache is.
-	 *
-	 * The anon LRU stats live in [0], file LRU stats in [1]
-	 */
-	unsigned long		recent_rotated[2];
-	unsigned long		recent_scanned[2];
-};
-
 struct zone {
 	/* Fields commonly accessed by the page allocator */
 
@@ -407,8 +408,6 @@ struct zone {
 	spinlock_t		lru_lock;
 	struct lruvec		lruvec;
 
-	struct zone_reclaim_stat reclaim_stat;
-
 	unsigned long		pages_scanned;	   /* since last reclaim */
 	unsigned long		flags;		   /* zone flags, see below */
 
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 0987146b0637..af2d2fa30eee 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -69,6 +69,10 @@
 #define NFS4_CDFC4_FORE_OR_BOTH 0x3
 #define NFS4_CDFC4_BACK_OR_BOTH 0x7
 
+#define NFS4_CDFS4_FORE 0x1
+#define NFS4_CDFS4_BACK 0x2
+#define NFS4_CDFS4_BOTH 0x3
+
 #define NFS4_SET_TO_SERVER_TIME	0
 #define NFS4_SET_TO_CLIENT_TIME	1
 
@@ -526,6 +530,13 @@ enum lock_type4 {
 #define FATTR4_WORD1_MOUNTED_ON_FILEID  (1UL << 23)
 #define FATTR4_WORD1_FS_LAYOUT_TYPES    (1UL << 30)
 #define FATTR4_WORD2_LAYOUT_BLKSIZE     (1UL << 1)
+#define FATTR4_WORD2_MDSTHRESHOLD       (1UL << 4)
+
+/* MDS threshold bitmap bits */
+#define THRESHOLD_RD                    (1UL << 0)
+#define THRESHOLD_WR                    (1UL << 1)
+#define THRESHOLD_RD_IO                 (1UL << 2)
+#define THRESHOLD_WR_IO                 (1UL << 3)
 
 #define NFSPROC4_NULL 0
 #define NFSPROC4_COMPOUND 1
@@ -596,6 +607,8 @@ enum {
 	NFSPROC4_CLNT_TEST_STATEID,
 	NFSPROC4_CLNT_FREE_STATEID,
 	NFSPROC4_CLNT_GETDEVICELIST,
+	NFSPROC4_CLNT_BIND_CONN_TO_SESSION,
+	NFSPROC4_CLNT_DESTROY_CLIENTID,
 };
 
 /* nfs41 types */
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 52a1bdb4ee2b..b23cfc120edb 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -102,6 +102,7 @@ struct nfs_open_context {
 	int error;
 
 	struct list_head list;
+	struct nfs4_threshold	*mdsthreshold;
 };
 
 struct nfs_open_dir_context {
@@ -179,8 +180,7 @@ struct nfs_inode {
 	__be32			cookieverf[2];
 
 	unsigned long		npages;
-	unsigned long		ncommit;
-	struct list_head	commit_list;
+	struct nfs_mds_commit_info commit_info;
 
 	/* Open contexts for shared mmap writes */
 	struct list_head	open_files;
@@ -201,8 +201,10 @@ struct nfs_inode {
 
 	/* pNFS layout information */
 	struct pnfs_layout_hdr *layout;
-	atomic_t		commits_outstanding;
 #endif /* CONFIG_NFS_V4*/
+	/* how many bytes have been written/read and how many bytes queued up */
+	__u64 write_io;
+	__u64 read_io;
 #ifdef CONFIG_NFS_FSCACHE
 	struct fscache_cookie	*fscache;
 #endif
@@ -230,7 +232,6 @@ struct nfs_inode {
 #define NFS_INO_FSCACHE		(5)		/* inode can be cached by FS-Cache */
 #define NFS_INO_FSCACHE_LOCK	(6)		/* FS-Cache cookie management lock */
 #define NFS_INO_COMMIT		(7)		/* inode is committing unstable writes */
-#define NFS_INO_PNFS_COMMIT	(8)		/* use pnfs code for commit */
 #define NFS_INO_LAYOUTCOMMIT	(9)		/* layoutcommit required */
 #define NFS_INO_LAYOUTCOMMITTING (10)		/* layoutcommit inflight */
 
@@ -317,11 +318,6 @@ static inline int nfs_server_capable(struct inode *inode, int cap)
 	return NFS_SERVER(inode)->caps & cap;
 }
 
-static inline int NFS_USE_READDIRPLUS(struct inode *inode)
-{
-	return test_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags);
-}
-
 static inline void nfs_set_verifier(struct dentry * dentry, unsigned long verf)
 {
 	dentry->d_time = verf;
@@ -552,8 +548,8 @@ extern int nfs_wb_page(struct inode *inode, struct page* page);
 extern int nfs_wb_page_cancel(struct inode *inode, struct page* page);
 #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
 extern int  nfs_commit_inode(struct inode *, int);
-extern struct nfs_write_data *nfs_commitdata_alloc(void);
-extern void nfs_commit_free(struct nfs_write_data *wdata);
+extern struct nfs_commit_data *nfs_commitdata_alloc(void);
+extern void nfs_commit_free(struct nfs_commit_data *data);
 #else
 static inline int
 nfs_commit_inode(struct inode *inode, int how)
@@ -569,12 +565,6 @@ nfs_have_writebacks(struct inode *inode)
 }
 
 /*
- * Allocate nfs_write_data structures
- */
-extern struct nfs_write_data *nfs_writedata_alloc(unsigned int npages);
-extern void nfs_writedata_free(struct nfs_write_data *);
-
-/*
  * linux/fs/nfs/read.c
  */
 extern int  nfs_readpage(struct file *, struct page *);
@@ -585,12 +575,6 @@ extern int  nfs_readpage_async(struct nfs_open_context *, struct inode *,
 			       struct page *);
 
 /*
- * Allocate nfs_read_data structures
- */
-extern struct nfs_read_data *nfs_readdata_alloc(unsigned int npages);
-extern void nfs_readdata_free(struct nfs_read_data *);
-
-/*
  * linux/fs/nfs3proc.c
  */
 #ifdef CONFIG_NFS_V3_ACL
@@ -654,6 +638,7 @@ nfs_fileid_to_ino_t(u64 fileid)
 #define NFSDBG_FSCACHE		0x0800
 #define NFSDBG_PNFS		0x1000
 #define NFSDBG_PNFS_LD		0x2000
+#define NFSDBG_STATE		0x4000
 #define NFSDBG_ALL		0xFFFF
 
 #ifdef __KERNEL__
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 7073fc74481c..fbb78fb09bd2 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -17,7 +17,7 @@ struct nfs4_sequence_args;
 struct nfs4_sequence_res;
 struct nfs_server;
 struct nfs4_minor_version_ops;
-struct server_scope;
+struct nfs41_server_scope;
 struct nfs41_impl_id;
 
 /*
@@ -35,6 +35,9 @@ struct nfs_client {
 #define NFS_CS_RENEWD		3		/* - renewd started */
 #define NFS_CS_STOP_RENEW	4		/* no more state to renew */
 #define NFS_CS_CHECK_LEASE_TIME	5		/* need to check lease time */
+	unsigned long		cl_flags;	/* behavior switches */
+#define NFS_CS_NORESVPORT	0		/* - use ephemeral src port */
+#define NFS_CS_DISCRTRY		1		/* - disconnect on RPC retry */
 	struct sockaddr_storage	cl_addr;	/* server identifier */
 	size_t			cl_addrlen;
 	char *			cl_hostname;	/* hostname of server */
@@ -61,9 +64,6 @@ struct nfs_client {
 
 	struct rpc_wait_queue	cl_rpcwaitq;
 
-	/* used for the setclientid verifier */
-	struct timespec		cl_boot_time;
-
 	/* idmapper */
 	struct idmap *		cl_idmap;
 
@@ -79,16 +79,17 @@ struct nfs_client {
 	u32			cl_seqid;
 	/* The flags used for obtaining the clientid during EXCHANGE_ID */
 	u32			cl_exchange_flags;
-	struct nfs4_session	*cl_session; 	/* sharred session */
+	struct nfs4_session	*cl_session;	/* shared session */
+	struct nfs41_server_owner *cl_serverowner;
+	struct nfs41_server_scope *cl_serverscope;
+	struct nfs41_impl_id	*cl_implid;
 #endif /* CONFIG_NFS_V4 */
 
 #ifdef CONFIG_NFS_FSCACHE
 	struct fscache_cookie	*fscache;	/* client index cache cookie */
 #endif
 
-	struct server_scope	*server_scope;	/* from exchange_id */
-	struct nfs41_impl_id	*impl_id;	/* from exchange_id */
-	struct net		*net;
+	struct net		*cl_net;
 };
 
 /*
diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h
index eac30d6bec17..88d166b555e8 100644
--- a/include/linux/nfs_page.h
+++ b/include/linux/nfs_page.h
@@ -27,7 +27,6 @@ enum {
 	PG_CLEAN,
 	PG_NEED_COMMIT,
 	PG_NEED_RESCHED,
-	PG_PARTIAL_READ_FAILED,
 	PG_COMMIT_TO_DS,
 };
 
@@ -37,7 +36,6 @@ struct nfs_page {
 	struct page		*wb_page;	/* page to read in/write out */
 	struct nfs_open_context	*wb_context;	/* File state context info */
 	struct nfs_lock_context	*wb_lock_context;	/* lock context info */
-	atomic_t		wb_complete;	/* i/os we're waiting for */
 	pgoff_t			wb_index;	/* Offset >> PAGE_CACHE_SHIFT */
 	unsigned int		wb_offset,	/* Offset & ~PAGE_CACHE_MASK */
 				wb_pgbase,	/* Start of page data */
@@ -68,7 +66,9 @@ struct nfs_pageio_descriptor {
 	int 			pg_ioflags;
 	int			pg_error;
 	const struct rpc_call_ops *pg_rpc_callops;
+	const struct nfs_pgio_completion_ops *pg_completion_ops;
 	struct pnfs_layout_segment *pg_lseg;
+	struct nfs_direct_req	*pg_dreq;
 };
 
 #define NFS_WBACK_BUSY(req)	(test_bit(PG_BUSY,&(req)->wb_flags))
@@ -84,6 +84,7 @@ extern	void nfs_release_request(struct nfs_page *req);
 extern	void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
 			     struct inode *inode,
 			     const struct nfs_pageio_ops *pg_ops,
+			     const struct nfs_pgio_completion_ops *compl_ops,
 			     size_t bsize,
 			     int how);
 extern	int nfs_pageio_add_request(struct nfs_pageio_descriptor *,
@@ -95,26 +96,17 @@ extern bool nfs_generic_pg_test(struct nfs_pageio_descriptor *desc,
 				struct nfs_page *req);
 extern  int nfs_wait_on_request(struct nfs_page *);
 extern	void nfs_unlock_request(struct nfs_page *req);
+extern	void nfs_unlock_and_release_request(struct nfs_page *req);
 
 /*
- * Lock the page of an asynchronous request without getting a new reference
+ * Lock the page of an asynchronous request
  */
 static inline int
-nfs_lock_request_dontget(struct nfs_page *req)
-{
-	return !test_and_set_bit(PG_BUSY, &req->wb_flags);
-}
-
-static inline int
 nfs_lock_request(struct nfs_page *req)
 {
-	if (test_and_set_bit(PG_BUSY, &req->wb_flags))
-		return 0;
-	kref_get(&req->wb_kref);
-	return 1;
+	return !test_and_set_bit(PG_BUSY, &req->wb_flags);
 }
 
-
 /**
  * nfs_list_add_request - Insert a request into a list
  * @req: request
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 7ba3551a0414..d1a7bf51c326 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -35,6 +35,15 @@ static inline int nfs_fsid_equal(const struct nfs_fsid *a, const struct nfs_fsid
 	return a->major == b->major && a->minor == b->minor;
 }
 
+struct nfs4_threshold {
+	__u32	bm;
+	__u32	l_type;
+	__u64	rd_sz;
+	__u64	wr_sz;
+	__u64	rd_io_sz;
+	__u64	wr_io_sz;
+};
+
 struct nfs_fattr {
 	unsigned int		valid;		/* which fields are valid */
 	umode_t			mode;
@@ -67,6 +76,7 @@ struct nfs_fattr {
 	unsigned long		gencount;
 	struct nfs4_string	*owner_name;
 	struct nfs4_string	*group_name;
+	struct nfs4_threshold	*mdsthreshold;	/* pNFS threshold hints */
 };
 
 #define NFS_ATTR_FATTR_TYPE		(1U << 0)
@@ -106,14 +116,14 @@ struct nfs_fattr {
 		| NFS_ATTR_FATTR_FILEID \
 		| NFS_ATTR_FATTR_ATIME \
 		| NFS_ATTR_FATTR_MTIME \
-		| NFS_ATTR_FATTR_CTIME)
+		| NFS_ATTR_FATTR_CTIME \
+		| NFS_ATTR_FATTR_CHANGE)
 #define NFS_ATTR_FATTR_V2 (NFS_ATTR_FATTR \
 		| NFS_ATTR_FATTR_BLOCKS_USED)
 #define NFS_ATTR_FATTR_V3 (NFS_ATTR_FATTR \
 		| NFS_ATTR_FATTR_SPACE_USED)
 #define NFS_ATTR_FATTR_V4 (NFS_ATTR_FATTR \
-		| NFS_ATTR_FATTR_SPACE_USED \
-		| NFS_ATTR_FATTR_CHANGE)
+		| NFS_ATTR_FATTR_SPACE_USED)
 
 /*
  * Info on the file system
@@ -338,7 +348,6 @@ struct nfs_openargs {
 	const struct qstr *	name;
 	const struct nfs_server *server;	 /* Needed for ID mapping */
 	const u32 *		bitmask;
-	const u32 *		dir_bitmask;
 	__u32			claim;
 	struct nfs4_sequence_args	seq_args;
 };
@@ -349,7 +358,6 @@ struct nfs_openres {
 	struct nfs4_change_info	cinfo;
 	__u32                   rflags;
 	struct nfs_fattr *      f_attr;
-	struct nfs_fattr *      dir_attr;
 	struct nfs_seqid *	seqid;
 	const struct nfs_server *server;
 	fmode_t			delegation_type;
@@ -519,12 +527,29 @@ struct nfs_writeres {
 };
 
 /*
+ * Arguments to the commit call.
+ */
+struct nfs_commitargs {
+	struct nfs_fh		*fh;
+	__u64			offset;
+	__u32			count;
+	const u32		*bitmask;
+	struct nfs4_sequence_args	seq_args;
+};
+
+struct nfs_commitres {
+	struct nfs_fattr	*fattr;
+	struct nfs_writeverf	*verf;
+	const struct nfs_server *server;
+	struct nfs4_sequence_res	seq_res;
+};
+
+/*
  * Common arguments to the unlink call
  */
 struct nfs_removeargs {
 	const struct nfs_fh	*fh;
 	struct qstr		name;
-	const u32 *		bitmask;
 	struct nfs4_sequence_args	seq_args;
 };
 
@@ -543,7 +568,6 @@ struct nfs_renameargs {
 	const struct nfs_fh		*new_dir;
 	const struct qstr		*old_name;
 	const struct qstr		*new_name;
-	const u32			*bitmask;
 	struct nfs4_sequence_args	seq_args;
 };
 
@@ -839,7 +863,6 @@ struct nfs4_create_res {
 	struct nfs_fh *			fh;
 	struct nfs_fattr *		fattr;
 	struct nfs4_change_info		dir_cinfo;
-	struct nfs_fattr *		dir_fattr;
 	struct nfs4_sequence_res	seq_res;
 };
 
@@ -1061,6 +1084,21 @@ struct nfstime4 {
 };
 
 #ifdef CONFIG_NFS_V4_1
+
+struct pnfs_commit_bucket {
+	struct list_head written;
+	struct list_head committing;
+	struct pnfs_layout_segment *wlseg;
+	struct pnfs_layout_segment *clseg;
+};
+
+struct pnfs_ds_commit_info {
+	int nwritten;
+	int ncommitting;
+	int nbuckets;
+	struct pnfs_commit_bucket *buckets;
+};
+
 #define NFS4_EXCHANGE_ID_LEN	(48)
 struct nfs41_exchange_id_args {
 	struct nfs_client		*client;
@@ -1070,13 +1108,13 @@ struct nfs41_exchange_id_args {
 	u32				flags;
 };
 
-struct server_owner {
+struct nfs41_server_owner {
 	uint64_t			minor_id;
 	uint32_t			major_id_sz;
 	char				major_id[NFS4_OPAQUE_LIMIT];
 };
 
-struct server_scope {
+struct nfs41_server_scope {
 	uint32_t			server_scope_sz;
 	char 				server_scope[NFS4_OPAQUE_LIMIT];
 };
@@ -1087,10 +1125,18 @@ struct nfs41_impl_id {
 	struct nfstime4			date;
 };
 
+struct nfs41_bind_conn_to_session_res {
+	struct nfs4_session		*session;
+	u32				dir;
+	bool				use_conn_in_rdma_mode;
+};
+
 struct nfs41_exchange_id_res {
-	struct nfs_client		*client;
+	u64				clientid;
+	u32				seqid;
 	u32				flags;
-	struct server_scope		*server_scope;
+	struct nfs41_server_owner	*server_owner;
+	struct nfs41_server_scope	*server_scope;
 	struct nfs41_impl_id		*impl_id;
 };
 
@@ -1143,35 +1189,114 @@ struct nfs41_free_stateid_res {
 	struct nfs4_sequence_res	seq_res;
 };
 
+#else
+
+struct pnfs_ds_commit_info {
+};
+
 #endif /* CONFIG_NFS_V4_1 */
 
 struct nfs_page;
 
 #define NFS_PAGEVEC_SIZE	(8U)
 
+struct nfs_page_array {
+	struct page		**pagevec;
+	unsigned int		npages;		/* Max length of pagevec */
+	struct page		*page_array[NFS_PAGEVEC_SIZE];
+};
+
 struct nfs_read_data {
+	struct nfs_pgio_header	*header;
+	struct list_head	list;
 	struct rpc_task		task;
-	struct inode		*inode;
-	struct rpc_cred		*cred;
 	struct nfs_fattr	fattr;	/* fattr storage */
-	struct list_head	pages;	/* Coalesced read requests */
-	struct list_head	list;	/* lists of struct nfs_read_data */
-	struct nfs_page		*req;	/* multi ops per nfs_page */
-	struct page		**pagevec;
-	unsigned int		npages;	/* Max length of pagevec */
 	struct nfs_readargs args;
 	struct nfs_readres  res;
 	unsigned long		timestamp;	/* For lease renewal */
-	struct pnfs_layout_segment *lseg;
-	struct nfs_client	*ds_clp;	/* pNFS data server */
-	const struct rpc_call_ops *mds_ops;
 	int (*read_done_cb) (struct rpc_task *task, struct nfs_read_data *data);
 	__u64			mds_offset;
+	struct nfs_page_array	pages;
+	struct nfs_client	*ds_clp;	/* pNFS data server */
+};
+
+/* used as flag bits in nfs_pgio_header */
+enum {
+	NFS_IOHDR_ERROR = 0,
+	NFS_IOHDR_EOF,
+	NFS_IOHDR_REDO,
+	NFS_IOHDR_NEED_COMMIT,
+	NFS_IOHDR_NEED_RESCHED,
+};
+
+struct nfs_pgio_header {
+	struct inode		*inode;
+	struct rpc_cred		*cred;
+	struct list_head	pages;
+	struct list_head	rpc_list;
+	atomic_t		refcnt;
+	struct nfs_page		*req;
+	struct pnfs_layout_segment *lseg;
+	loff_t			io_start;
+	const struct rpc_call_ops *mds_ops;
+	void (*release) (struct nfs_pgio_header *hdr);
+	const struct nfs_pgio_completion_ops *completion_ops;
+	struct nfs_direct_req	*dreq;
+	spinlock_t		lock;
+	/* fields protected by lock */
 	int			pnfs_error;
-	struct page		*page_array[NFS_PAGEVEC_SIZE];
+	int			error;		/* merge with pnfs_error */
+	unsigned long		good_bytes;	/* boundary of good data */
+	unsigned long		flags;
+};
+
+struct nfs_read_header {
+	struct nfs_pgio_header	header;
+	struct nfs_read_data	rpc_data;
 };
 
 struct nfs_write_data {
+	struct nfs_pgio_header	*header;
+	struct list_head	list;
+	struct rpc_task		task;
+	struct nfs_fattr	fattr;
+	struct nfs_writeverf	verf;
+	struct nfs_writeargs	args;		/* argument struct */
+	struct nfs_writeres	res;		/* result struct */
+	unsigned long		timestamp;	/* For lease renewal */
+	int (*write_done_cb) (struct rpc_task *task, struct nfs_write_data *data);
+	__u64			mds_offset;	/* Filelayout dense stripe */
+	struct nfs_page_array	pages;
+	struct nfs_client	*ds_clp;	/* pNFS data server */
+};
+
+struct nfs_write_header {
+	struct nfs_pgio_header	header;
+	struct nfs_write_data	rpc_data;
+};
+
+struct nfs_mds_commit_info {
+	atomic_t rpcs_out;
+	unsigned long		ncommit;
+	struct list_head	list;
+};
+
+struct nfs_commit_data;
+struct nfs_inode;
+struct nfs_commit_completion_ops {
+	void (*error_cleanup) (struct nfs_inode *nfsi);
+	void (*completion) (struct nfs_commit_data *data);
+};
+
+struct nfs_commit_info {
+	spinlock_t			*lock;
+	struct nfs_mds_commit_info	*mds;
+	struct pnfs_ds_commit_info	*ds;
+	struct nfs_direct_req		*dreq;	/* O_DIRECT request */
+	const struct nfs_commit_completion_ops *completion_ops;
+};
+
+struct nfs_commit_data {
 	struct rpc_task		task;
 	struct inode		*inode;
 	struct rpc_cred		*cred;
@@ -1179,22 +1304,22 @@ struct nfs_write_data {
 	struct nfs_writeverf	verf;
 	struct list_head	pages;		/* Coalesced requests we wish to flush */
 	struct list_head	list;		/* lists of struct nfs_write_data */
-	struct nfs_page		*req;		/* multi ops per nfs_page */
-	struct page		**pagevec;
-	unsigned int		npages;		/* Max length of pagevec */
-	struct nfs_writeargs	args;		/* argument struct */
-	struct nfs_writeres	res;		/* result struct */
+	struct nfs_direct_req	*dreq;		/* O_DIRECT request */
+	struct nfs_commitargs	args;		/* argument struct */
+	struct nfs_commitres	res;		/* result struct */
+	struct nfs_open_context *context;
 	struct pnfs_layout_segment *lseg;
 	struct nfs_client	*ds_clp;	/* pNFS data server */
 	int			ds_commit_index;
 	const struct rpc_call_ops *mds_ops;
-	int (*write_done_cb) (struct rpc_task *task, struct nfs_write_data *data);
-#ifdef CONFIG_NFS_V4
-	unsigned long		timestamp;	/* For lease renewal */
-#endif
-	__u64			mds_offset;	/* Filelayout dense stripe */
-	int			pnfs_error;
-	struct page		*page_array[NFS_PAGEVEC_SIZE];
+	const struct nfs_commit_completion_ops *completion_ops;
+	int (*commit_done_cb) (struct rpc_task *task, struct nfs_commit_data *data);
+};
+
+struct nfs_pgio_completion_ops {
+	void	(*error_cleanup)(struct list_head *head);
+	void	(*init_hdr)(struct nfs_pgio_header *hdr);
+	void	(*completion)(struct nfs_pgio_header *hdr);
 };
 
 struct nfs_unlinkdata {
@@ -1234,11 +1359,13 @@ struct nfs_rpc_ops {
 
 	int	(*getroot) (struct nfs_server *, struct nfs_fh *,
 			    struct nfs_fsinfo *);
+	struct vfsmount *(*submount) (struct nfs_server *, struct dentry *,
+				      struct nfs_fh *, struct nfs_fattr *);
 	int	(*getattr) (struct nfs_server *, struct nfs_fh *,
 			    struct nfs_fattr *);
 	int	(*setattr) (struct dentry *, struct nfs_fattr *,
 			    struct iattr *);
-	int	(*lookup)  (struct rpc_clnt *clnt, struct inode *, struct qstr *,
+	int	(*lookup)  (struct inode *, struct qstr *,
 			    struct nfs_fh *, struct nfs_fattr *);
 	int	(*access)  (struct inode *, struct nfs_access_entry *);
 	int	(*readlink)(struct inode *, struct page *, unsigned int,
@@ -1277,8 +1404,9 @@ struct nfs_rpc_ops {
 	void	(*write_setup)  (struct nfs_write_data *, struct rpc_message *);
 	void	(*write_rpc_prepare)(struct rpc_task *, struct nfs_write_data *);
 	int	(*write_done)  (struct rpc_task *, struct nfs_write_data *);
-	void	(*commit_setup) (struct nfs_write_data *, struct rpc_message *);
-	int	(*commit_done) (struct rpc_task *, struct nfs_write_data *);
+	void	(*commit_setup) (struct nfs_commit_data *, struct rpc_message *);
+	void	(*commit_rpc_prepare)(struct rpc_task *, struct nfs_commit_data *);
+	int	(*commit_done) (struct rpc_task *, struct nfs_commit_data *);
 	int	(*lock)(struct file *, int, struct file_lock *);
 	int	(*lock_check_bounds)(const struct file_lock *);
 	void	(*clear_acl_cache)(struct inode *);
@@ -1287,9 +1415,9 @@ struct nfs_rpc_ops {
 				struct nfs_open_context *ctx,
 				int open_flags,
 				struct iattr *iattr);
-	int	(*init_client) (struct nfs_client *, const struct rpc_timeout *,
-				const char *, rpc_authflavor_t, int);
-	int	(*secinfo)(struct inode *, const struct qstr *, struct nfs4_secinfo_flavors *);
+	struct nfs_client *
+		(*init_client) (struct nfs_client *, const struct rpc_timeout *,
+				const char *, rpc_authflavor_t);
 };
 
 /*
diff --git a/include/linux/oom.h b/include/linux/oom.h
index 3d7647536b03..e4c29bc72e70 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -43,8 +43,9 @@ enum oom_constraint {
 extern void compare_swap_oom_score_adj(int old_val, int new_val);
 extern int test_set_oom_score_adj(int new_val);
 
-extern unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
-			const nodemask_t *nodemask, unsigned long totalpages);
+extern unsigned long oom_badness(struct task_struct *p,
+		struct mem_cgroup *memcg, const nodemask_t *nodemask,
+		unsigned long totalpages);
 extern int try_set_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags);
 extern void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags);
 
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index efa26b4da8d2..7cfad3bbb0cc 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -460,11 +460,11 @@ static inline int fault_in_pages_readable(const char __user *uaddr, int size)
  */
 static inline int fault_in_multipages_writeable(char __user *uaddr, int size)
 {
-	int ret;
+	int ret = 0;
 	char __user *end = uaddr + size - 1;
 
 	if (unlikely(size == 0))
-		return 0;
+		return ret;
 
 	/*
 	 * Writing zeroes into userspace here is OK, because we know that if
@@ -489,11 +489,11 @@ static inline int fault_in_multipages_readable(const char __user *uaddr,
 					       int size)
 {
 	volatile char c;
-	int ret;
+	int ret = 0;
 	const char __user *end = uaddr + size - 1;
 
 	if (unlikely(size == 0))
-		return 0;
+		return ret;
 
 	while (uaddr <= end) {
 		ret = __get_user(c, uaddr);
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 3329965ed63f..ab741b0d0074 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2506,6 +2506,7 @@
 #define PCI_DEVICE_ID_INTEL_MRST_SD2	0x084F
 #define PCI_DEVICE_ID_INTEL_I960	0x0960
 #define PCI_DEVICE_ID_INTEL_I960RM	0x0962
+#define PCI_DEVICE_ID_INTEL_CENTERTON_ILB	0x0c60
 #define PCI_DEVICE_ID_INTEL_8257X_SOL	0x1062
 #define PCI_DEVICE_ID_INTEL_82573E_SOL	0x1085
 #define PCI_DEVICE_ID_INTEL_82573L_SOL	0x108F
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index fd07c4542cee..3fce545df394 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -173,8 +173,6 @@ enum ttu_flags {
 };
 #define TTU_ACTION(x) ((x) & TTU_ACTION_MASK)
 
-bool is_vma_temporary_stack(struct vm_area_struct *vma);
-
 int try_to_unmap(struct page *, enum ttu_flags flags);
 int try_to_unmap_one(struct page *, struct vm_area_struct *,
 			unsigned long address, enum ttu_flags flags);
diff --git a/include/linux/swap.h b/include/linux/swap.h
index b1fd5c7925fe..49c0fa9ef5cf 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -351,31 +351,14 @@ extern int swap_type_of(dev_t, sector_t, struct block_device **);
 extern unsigned int count_swap_pages(int, int);
 extern sector_t map_swap_page(struct page *, struct block_device **);
 extern sector_t swapdev_block(int, pgoff_t);
+extern int page_swapcount(struct page *);
 extern int reuse_swap_page(struct page *);
 extern int try_to_free_swap(struct page *);
 struct backing_dev_info;
 
-/* linux/mm/thrash.c */
-extern struct mm_struct *swap_token_mm;
-extern void grab_swap_token(struct mm_struct *);
-extern void __put_swap_token(struct mm_struct *);
-extern void disable_swap_token(struct mem_cgroup *memcg);
-
-static inline int has_swap_token(struct mm_struct *mm)
-{
-	return (mm == swap_token_mm);
-}
-
-static inline void put_swap_token(struct mm_struct *mm)
-{
-	if (has_swap_token(mm))
-		__put_swap_token(mm);
-}
-
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR
 extern void
 mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout);
-extern int mem_cgroup_count_swap_user(swp_entry_t ent, struct page **pagep);
 #else
 static inline void
 mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout)
@@ -462,6 +445,11 @@ static inline void delete_from_swap_cache(struct page *page)
 {
 }
 
+static inline int page_swapcount(struct page *page)
+{
+	return 0;
+}
+
 #define reuse_swap_page(page)	(page_mapcount(page) == 1)
 
 static inline int try_to_free_swap(struct page *page)
@@ -476,37 +464,11 @@ static inline swp_entry_t get_swap_page(void)
 	return entry;
 }
 
-/* linux/mm/thrash.c */
-static inline void put_swap_token(struct mm_struct *mm)
-{
-}
-
-static inline void grab_swap_token(struct mm_struct *mm)
-{
-}
-
-static inline int has_swap_token(struct mm_struct *mm)
-{
-	return 0;
-}
-
-static inline void disable_swap_token(struct mem_cgroup *memcg)
-{
-}
-
 static inline void
 mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent)
 {
 }
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
-static inline int
-mem_cgroup_count_swap_user(swp_entry_t ent, struct page **pagep)
-{
-	return 0;
-}
-#endif
-
 #endif /* CONFIG_SWAP */
 #endif /* __KERNEL__*/
 #endif /* _LINUX_SWAP_H */
diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index f64560e204bc..bab3b87e4064 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -13,7 +13,7 @@
 #define RECLAIM_WB_ANON		0x0001u
 #define RECLAIM_WB_FILE		0x0002u
 #define RECLAIM_WB_MIXED	0x0010u
-#define RECLAIM_WB_SYNC		0x0004u
+#define RECLAIM_WB_SYNC		0x0004u /* Unused, all reclaim async */
 #define RECLAIM_WB_ASYNC	0x0008u
 
 #define show_reclaim_flags(flags)				\
@@ -25,15 +25,15 @@
 		{RECLAIM_WB_ASYNC,	"RECLAIM_WB_ASYNC"}	\
 		) : "RECLAIM_WB_NONE"
 
-#define trace_reclaim_flags(page, sync) ( \
+#define trace_reclaim_flags(page) ( \
 	(page_is_file_cache(page) ? RECLAIM_WB_FILE : RECLAIM_WB_ANON) | \
-	(sync & RECLAIM_MODE_SYNC ? RECLAIM_WB_SYNC : RECLAIM_WB_ASYNC)   \
+	(RECLAIM_WB_ASYNC) \
 	)
 
-#define trace_shrink_flags(file, sync) ( \
-	(sync & RECLAIM_MODE_SYNC ? RECLAIM_WB_MIXED : \
-			(file ? RECLAIM_WB_FILE : RECLAIM_WB_ANON)) |  \
-	(sync & RECLAIM_MODE_SYNC ? RECLAIM_WB_SYNC : RECLAIM_WB_ASYNC) \
+#define trace_shrink_flags(file) \
+	( \
+		(file ? RECLAIM_WB_FILE : RECLAIM_WB_ANON) | \
+		(RECLAIM_WB_ASYNC) \
 	)
 
 TRACE_EVENT(mm_vmscan_kswapd_sleep,
@@ -263,22 +263,16 @@ DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template,
 		unsigned long nr_requested,
 		unsigned long nr_scanned,
 		unsigned long nr_taken,
-		unsigned long nr_lumpy_taken,
-		unsigned long nr_lumpy_dirty,
-		unsigned long nr_lumpy_failed,
 		isolate_mode_t isolate_mode,
 		int file),
 
-	TP_ARGS(order, nr_requested, nr_scanned, nr_taken, nr_lumpy_taken, nr_lumpy_dirty, nr_lumpy_failed, isolate_mode, file),
+	TP_ARGS(order, nr_requested, nr_scanned, nr_taken, isolate_mode, file),
 
 	TP_STRUCT__entry(
 		__field(int, order)
 		__field(unsigned long, nr_requested)
 		__field(unsigned long, nr_scanned)
 		__field(unsigned long, nr_taken)
-		__field(unsigned long, nr_lumpy_taken)
-		__field(unsigned long, nr_lumpy_dirty)
-		__field(unsigned long, nr_lumpy_failed)
 		__field(isolate_mode_t, isolate_mode)
 		__field(int, file)
 	),
@@ -288,22 +282,16 @@ DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template,
 		__entry->nr_requested = nr_requested;
 		__entry->nr_scanned = nr_scanned;
 		__entry->nr_taken = nr_taken;
-		__entry->nr_lumpy_taken = nr_lumpy_taken;
-		__entry->nr_lumpy_dirty = nr_lumpy_dirty;
-		__entry->nr_lumpy_failed = nr_lumpy_failed;
 		__entry->isolate_mode = isolate_mode;
 		__entry->file = file;
 	),
 
-	TP_printk("isolate_mode=%d order=%d nr_requested=%lu nr_scanned=%lu nr_taken=%lu contig_taken=%lu contig_dirty=%lu contig_failed=%lu file=%d",
+	TP_printk("isolate_mode=%d order=%d nr_requested=%lu nr_scanned=%lu nr_taken=%lu file=%d",
 		__entry->isolate_mode,
 		__entry->order,
 		__entry->nr_requested,
 		__entry->nr_scanned,
 		__entry->nr_taken,
-		__entry->nr_lumpy_taken,
-		__entry->nr_lumpy_dirty,
-		__entry->nr_lumpy_failed,
 		__entry->file)
 );
 
@@ -313,13 +301,10 @@ DEFINE_EVENT(mm_vmscan_lru_isolate_template, mm_vmscan_lru_isolate,
 		unsigned long nr_requested,
 		unsigned long nr_scanned,
 		unsigned long nr_taken,
-		unsigned long nr_lumpy_taken,
-		unsigned long nr_lumpy_dirty,
-		unsigned long nr_lumpy_failed,
 		isolate_mode_t isolate_mode,
 		int file),
 
-	TP_ARGS(order, nr_requested, nr_scanned, nr_taken, nr_lumpy_taken, nr_lumpy_dirty, nr_lumpy_failed, isolate_mode, file)
+	TP_ARGS(order, nr_requested, nr_scanned, nr_taken, isolate_mode, file)
 
 );
 
@@ -329,13 +314,10 @@ DEFINE_EVENT(mm_vmscan_lru_isolate_template, mm_vmscan_memcg_isolate,
 		unsigned long nr_requested,
 		unsigned long nr_scanned,
 		unsigned long nr_taken,
-		unsigned long nr_lumpy_taken,
-		unsigned long nr_lumpy_dirty,
-		unsigned long nr_lumpy_failed,
 		isolate_mode_t isolate_mode,
 		int file),
 
-	TP_ARGS(order, nr_requested, nr_scanned, nr_taken, nr_lumpy_taken, nr_lumpy_dirty, nr_lumpy_failed, isolate_mode, file)
+	TP_ARGS(order, nr_requested, nr_scanned, nr_taken, isolate_mode, file)
 
 );
 
@@ -395,88 +377,6 @@ TRACE_EVENT(mm_vmscan_lru_shrink_inactive,
 		show_reclaim_flags(__entry->reclaim_flags))
 );
 
-TRACE_EVENT(replace_swap_token,
-	TP_PROTO(struct mm_struct *old_mm,
-		 struct mm_struct *new_mm),
-
-	TP_ARGS(old_mm, new_mm),
-
-	TP_STRUCT__entry(
-		__field(struct mm_struct*,	old_mm)
-		__field(unsigned int,		old_prio)
-		__field(struct mm_struct*,	new_mm)
-		__field(unsigned int,		new_prio)
-	),
-
-	TP_fast_assign(
-		__entry->old_mm   = old_mm;
-		__entry->old_prio = old_mm ? old_mm->token_priority : 0;
-		__entry->new_mm   = new_mm;
-		__entry->new_prio = new_mm->token_priority;
-	),
-
-	TP_printk("old_token_mm=%p old_prio=%u new_token_mm=%p new_prio=%u",
-		  __entry->old_mm, __entry->old_prio,
-		  __entry->new_mm, __entry->new_prio)
-);
-
-DECLARE_EVENT_CLASS(put_swap_token_template,
-	TP_PROTO(struct mm_struct *swap_token_mm),
-
-	TP_ARGS(swap_token_mm),
-
-	TP_STRUCT__entry(
-		__field(struct mm_struct*, swap_token_mm)
-	),
-
-	TP_fast_assign(
-		__entry->swap_token_mm = swap_token_mm;
-	),
-
-	TP_printk("token_mm=%p", __entry->swap_token_mm)
-);
-
-DEFINE_EVENT(put_swap_token_template, put_swap_token,
-	TP_PROTO(struct mm_struct *swap_token_mm),
-	TP_ARGS(swap_token_mm)
-);
-
-DEFINE_EVENT_CONDITION(put_swap_token_template, disable_swap_token,
-	TP_PROTO(struct mm_struct *swap_token_mm),
-	TP_ARGS(swap_token_mm),
-	TP_CONDITION(swap_token_mm != NULL)
-);
-
-TRACE_EVENT_CONDITION(update_swap_token_priority,
-	TP_PROTO(struct mm_struct *mm,
-		 unsigned int old_prio,
-		 struct mm_struct *swap_token_mm),
-
-	TP_ARGS(mm, old_prio, swap_token_mm),
-
-	TP_CONDITION(mm->token_priority != old_prio),
-
-	TP_STRUCT__entry(
-		__field(struct mm_struct*, mm)
-		__field(unsigned int, old_prio)
-		__field(unsigned int, new_prio)
-		__field(struct mm_struct*, swap_token_mm)
-		__field(unsigned int, swap_token_prio)
-	),
-
-	TP_fast_assign(
-		__entry->mm		= mm;
-		__entry->old_prio	= old_prio;
-		__entry->new_prio	= mm->token_priority;
-		__entry->swap_token_mm	= swap_token_mm;
-		__entry->swap_token_prio = swap_token_mm ? swap_token_mm->token_priority : 0;
-	),
-
-	TP_printk("mm=%p old_prio=%u new_prio=%u swap_token_mm=%p token_prio=%u",
-		  __entry->mm, __entry->old_prio, __entry->new_prio,
-		  __entry->swap_token_mm, __entry->swap_token_prio)
-);
-
 #endif /* _TRACE_VMSCAN_H */
 
 /* This part must be outside protection */
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index a0c6af34d500..0f3527d6184a 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -5132,7 +5132,7 @@ EXPORT_SYMBOL_GPL(css_depth);
  * @root: the css supporsed to be an ancestor of the child.
  *
  * Returns true if "root" is an ancestor of "child" in its hierarchy. Because
- * this function reads css->id, this use rcu_dereference() and rcu_read_lock().
+ * this function reads css->id, the caller must hold rcu_read_lock().
  * But, considering usual usage, the csses should be valid objects after test.
  * Assuming that the caller will do some action to the child if this returns
  * returns true, the caller must take "child";s reference count.
@@ -5144,18 +5144,18 @@ bool css_is_ancestor(struct cgroup_subsys_state *child,
 {
 	struct css_id *child_id;
 	struct css_id *root_id;
-	bool ret = true;
 
-	rcu_read_lock();
 	child_id  = rcu_dereference(child->id);
+	if (!child_id)
+		return false;
 	root_id = rcu_dereference(root->id);
-	if (!child_id
-	    || !root_id
-	    || (child_id->depth < root_id->depth)
-	    || (child_id->stack[root_id->depth] != root_id->id))
-		ret = false;
-	rcu_read_unlock();
-	return ret;
+	if (!root_id)
+		return false;
+	if (child_id->depth < root_id->depth)
+		return false;
+	if (child_id->stack[root_id->depth] != root_id->id)
+		return false;
+	return true;
 }
 
 void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css)
diff --git a/kernel/fork.c b/kernel/fork.c
index 47b4e4f379f9..017fb23d5983 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -386,7 +386,8 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 		}
 		charge = 0;
 		if (mpnt->vm_flags & VM_ACCOUNT) {
-			unsigned int len = (mpnt->vm_end - mpnt->vm_start) >> PAGE_SHIFT;
+			unsigned long len;
+			len = (mpnt->vm_end - mpnt->vm_start) >> PAGE_SHIFT;
 			if (security_vm_enough_memory_mm(oldmm, len)) /* sic */
 				goto fail_nomem;
 			charge = len;
@@ -614,7 +615,6 @@ void mmput(struct mm_struct *mm)
 			list_del(&mm->mmlist);
 			spin_unlock(&mmlist_lock);
 		}
-		put_swap_token(mm);
 		if (mm->binfmt)
 			module_put(mm->binfmt->module);
 		mmdrop(mm);
@@ -831,10 +831,6 @@ struct mm_struct *dup_mm(struct task_struct *tsk)
 	memcpy(mm, oldmm, sizeof(*mm));
 	mm_init_cpumask(mm);
 
-	/* Initializing for Swap token stuff */
-	mm->token_priority = 0;
-	mm->last_interval = 0;
-
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	mm->pmd_huge_pte = NULL;
 #endif
@@ -913,10 +909,6 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk)
 		goto fail_nomem;
 
 good_mm:
-	/* Initializing for Swap token stuff */
-	mm->token_priority = 0;
-	mm->last_interval = 0;
-
 	tsk->mm = mm;
 	tsk->active_mm = mm;
 	return 0;
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 414f46ed1dcd..45bc1f83a5ad 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -130,11 +130,9 @@ void swiotlb_print_info(void)
 	pstart = virt_to_phys(io_tlb_start);
 	pend = virt_to_phys(io_tlb_end);
 
-	printk(KERN_INFO "Placing %luMB software IO TLB between %p - %p\n",
-	       bytes >> 20, io_tlb_start, io_tlb_end);
-	printk(KERN_INFO "software IO TLB at phys %#llx - %#llx\n",
-	       (unsigned long long)pstart,
-	       (unsigned long long)pend);
+	printk(KERN_INFO "software IO TLB [mem %#010llx-%#010llx] (%luMB) mapped at [%p-%p]\n",
+	       (unsigned long long)pstart, (unsigned long long)pend - 1,
+	       bytes >> 20, io_tlb_start, io_tlb_end - 1);
 }
 
 void __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
diff --git a/mm/Kconfig b/mm/Kconfig
index 39220026c797..b2176374b98e 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -349,6 +349,16 @@ choice
 	  benefit.
 endchoice
 
+config CROSS_MEMORY_ATTACH
+	bool "Cross Memory Support"
+	depends on MMU
+	default y
+	help
+	  Enabling this option adds the system calls process_vm_readv and
+	  process_vm_writev which allow a process with the correct privileges
+	  to directly read from or write to to another process's address space.
+	  See the man page for more details.
+
 #
 # UP and nommu archs use km based percpu allocator
 #
diff --git a/mm/Makefile b/mm/Makefile
index 8aada89efbbb..a156285ce88d 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -5,8 +5,11 @@
 mmu-y			:= nommu.o
 mmu-$(CONFIG_MMU)	:= fremap.o highmem.o madvise.o memory.o mincore.o \
 			   mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \
-			   vmalloc.o pagewalk.o pgtable-generic.o \
-			   process_vm_access.o
+			   vmalloc.o pagewalk.o pgtable-generic.o
+
+ifdef CONFIG_CROSS_MEMORY_ATTACH
+mmu-$(CONFIG_MMU)	+= process_vm_access.o
+endif
 
 obj-y			:= filemap.o mempool.o oom_kill.o fadvise.o \
 			   maccess.o page_alloc.o page-writeback.o \
@@ -25,7 +28,7 @@ endif
 obj-$(CONFIG_HAVE_MEMBLOCK) += memblock.o
 
 obj-$(CONFIG_BOUNCE)	+= bounce.o
-obj-$(CONFIG_SWAP)	+= page_io.o swap_state.o swapfile.o thrash.o
+obj-$(CONFIG_SWAP)	+= page_io.o swap_state.o swapfile.o
 obj-$(CONFIG_HAS_DMA)	+= dmapool.o
 obj-$(CONFIG_HUGETLBFS)	+= hugetlb.o
 obj-$(CONFIG_NUMA) 	+= mempolicy.o
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 0131170c9d54..ec4fcb7a56c8 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -77,16 +77,16 @@ unsigned long __init bootmem_bootmap_pages(unsigned long pages)
  */
 static void __init link_bootmem(bootmem_data_t *bdata)
 {
-	struct list_head *iter;
+	bootmem_data_t *ent;
 
-	list_for_each(iter, &bdata_list) {
-		bootmem_data_t *ent;
-
-		ent = list_entry(iter, bootmem_data_t, list);
-		if (bdata->node_min_pfn < ent->node_min_pfn)
-			break;
+	list_for_each_entry(ent, &bdata_list, list) {
+		if (bdata->node_min_pfn < ent->node_min_pfn) {
+			list_add_tail(&bdata->list, &ent->list);
+			return;
+		}
 	}
-	list_add_tail(&bdata->list, iter);
+
+	list_add_tail(&bdata->list, &bdata_list);
 }
 
 /*
@@ -203,7 +203,8 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 		} else {
 			unsigned long off = 0;
 
-			while (vec && off < BITS_PER_LONG) {
+			vec >>= start & (BITS_PER_LONG - 1);
+			while (vec) {
 				if (vec & 1) {
 					page = pfn_to_page(start + off);
 					__free_pages_bootmem(page, 0);
@@ -467,7 +468,7 @@ static unsigned long __init align_off(struct bootmem_data *bdata,
 	return ALIGN(base + off, align) - base;
 }
 
-static void * __init alloc_bootmem_core(struct bootmem_data *bdata,
+static void * __init alloc_bootmem_bdata(struct bootmem_data *bdata,
 					unsigned long size, unsigned long align,
 					unsigned long goal, unsigned long limit)
 {
@@ -588,14 +589,14 @@ static void * __init alloc_arch_preferred_bootmem(bootmem_data_t *bdata,
 		p_bdata = bootmem_arch_preferred_node(bdata, size, align,
 							goal, limit);
 		if (p_bdata)
-			return alloc_bootmem_core(p_bdata, size, align,
+			return alloc_bootmem_bdata(p_bdata, size, align,
 							goal, limit);
 	}
 #endif
 	return NULL;
 }
 
-static void * __init ___alloc_bootmem_nopanic(unsigned long size,
+static void * __init alloc_bootmem_core(unsigned long size,
 					unsigned long align,
 					unsigned long goal,
 					unsigned long limit)
@@ -603,7 +604,6 @@ static void * __init ___alloc_bootmem_nopanic(unsigned long size,
 	bootmem_data_t *bdata;
 	void *region;
 
-restart:
 	region = alloc_arch_preferred_bootmem(NULL, size, align, goal, limit);
 	if (region)
 		return region;
@@ -614,11 +614,25 @@ restart:
 		if (limit && bdata->node_min_pfn >= PFN_DOWN(limit))
 			break;
 
-		region = alloc_bootmem_core(bdata, size, align, goal, limit);
+		region = alloc_bootmem_bdata(bdata, size, align, goal, limit);
 		if (region)
 			return region;
 	}
 
+	return NULL;
+}
+
+static void * __init ___alloc_bootmem_nopanic(unsigned long size,
+					      unsigned long align,
+					      unsigned long goal,
+					      unsigned long limit)
+{
+	void *ptr;
+
+restart:
+	ptr = alloc_bootmem_core(size, align, goal, limit);
+	if (ptr)
+		return ptr;
 	if (goal) {
 		goal = 0;
 		goto restart;
@@ -684,21 +698,56 @@ void * __init __alloc_bootmem(unsigned long size, unsigned long align,
 	return ___alloc_bootmem(size, align, goal, limit);
 }
 
-static void * __init ___alloc_bootmem_node(bootmem_data_t *bdata,
+static void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat,
 				unsigned long size, unsigned long align,
 				unsigned long goal, unsigned long limit)
 {
 	void *ptr;
 
-	ptr = alloc_arch_preferred_bootmem(bdata, size, align, goal, limit);
+again:
+	ptr = alloc_arch_preferred_bootmem(pgdat->bdata, size,
+					   align, goal, limit);
 	if (ptr)
 		return ptr;
 
-	ptr = alloc_bootmem_core(bdata, size, align, goal, limit);
+	ptr = alloc_bootmem_bdata(pgdat->bdata, size, align, goal, limit);
 	if (ptr)
 		return ptr;
 
-	return ___alloc_bootmem(size, align, goal, limit);
+	ptr = alloc_bootmem_core(size, align, goal, limit);
+	if (ptr)
+		return ptr;
+
+	if (goal) {
+		goal = 0;
+		goto again;
+	}
+
+	return NULL;
+}
+
+void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size,
+				   unsigned long align, unsigned long goal)
+{
+	if (WARN_ON_ONCE(slab_is_available()))
+		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
+
+	return ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, 0);
+}
+
+void * __init ___alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
+				    unsigned long align, unsigned long goal,
+				    unsigned long limit)
+{
+	void *ptr;
+
+	ptr = ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, 0);
+	if (ptr)
+		return ptr;
+
+	printk(KERN_ALERT "bootmem alloc of %lu bytes failed!\n", size);
+	panic("Out of memory");
+	return NULL;
 }
 
 /**
@@ -722,7 +771,7 @@ void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
 	if (WARN_ON_ONCE(slab_is_available()))
 		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
 
-	return  ___alloc_bootmem_node(pgdat->bdata, size, align, goal, 0);
+	return  ___alloc_bootmem_node(pgdat, size, align, goal, 0);
 }
 
 void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
@@ -743,7 +792,7 @@ void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
 		unsigned long new_goal;
 
 		new_goal = MAX_DMA32_PFN << PAGE_SHIFT;
-		ptr = alloc_bootmem_core(pgdat->bdata, size, align,
+		ptr = alloc_bootmem_bdata(pgdat->bdata, size, align,
 						 new_goal, 0);
 		if (ptr)
 			return ptr;
@@ -754,47 +803,6 @@ void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
 
 }
 
-#ifdef CONFIG_SPARSEMEM
-/**
- * alloc_bootmem_section - allocate boot memory from a specific section
- * @size: size of the request in bytes
- * @section_nr: sparse map section to allocate from
- *
- * Return NULL on failure.
- */
-void * __init alloc_bootmem_section(unsigned long size,
-				    unsigned long section_nr)
-{
-	bootmem_data_t *bdata;
-	unsigned long pfn, goal;
-
-	pfn = section_nr_to_pfn(section_nr);
-	goal = pfn << PAGE_SHIFT;
-	bdata = &bootmem_node_data[early_pfn_to_nid(pfn)];
-
-	return alloc_bootmem_core(bdata, size, SMP_CACHE_BYTES, goal, 0);
-}
-#endif
-
-void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size,
-				   unsigned long align, unsigned long goal)
-{
-	void *ptr;
-
-	if (WARN_ON_ONCE(slab_is_available()))
-		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
-
-	ptr = alloc_arch_preferred_bootmem(pgdat->bdata, size, align, goal, 0);
-	if (ptr)
-		return ptr;
-
-	ptr = alloc_bootmem_core(pgdat->bdata, size, align, goal, 0);
-	if (ptr)
-		return ptr;
-
-	return __alloc_bootmem_nopanic(size, align, goal);
-}
-
 #ifndef ARCH_LOW_ADDRESS_LIMIT
 #define ARCH_LOW_ADDRESS_LIMIT	0xffffffffUL
 #endif
@@ -839,6 +847,6 @@ void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size,
 	if (WARN_ON_ONCE(slab_is_available()))
 		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
 
-	return ___alloc_bootmem_node(pgdat->bdata, size, align,
-				goal, ARCH_LOW_ADDRESS_LIMIT);
+	return ___alloc_bootmem_node(pgdat, size, align,
+				     goal, ARCH_LOW_ADDRESS_LIMIT);
 }
diff --git a/mm/compaction.c b/mm/compaction.c
index da7d35ea5103..840ee288e296 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -235,7 +235,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 	 */
 	while (unlikely(too_many_isolated(zone))) {
 		/* async migration should just abort */
-		if (!cc->sync)
+		if (cc->mode != COMPACT_SYNC)
 			return 0;
 
 		congestion_wait(BLK_RW_ASYNC, HZ/10);
@@ -303,7 +303,8 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 		 * satisfies the allocation
 		 */
 		pageblock_nr = low_pfn >> pageblock_order;
-		if (!cc->sync && last_pageblock_nr != pageblock_nr &&
+		if (cc->mode != COMPACT_SYNC &&
+		    last_pageblock_nr != pageblock_nr &&
 		    !migrate_async_suitable(get_pageblock_migratetype(page))) {
 			low_pfn += pageblock_nr_pages;
 			low_pfn = ALIGN(low_pfn, pageblock_nr_pages) - 1;
@@ -324,7 +325,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 			continue;
 		}
 
-		if (!cc->sync)
+		if (cc->mode != COMPACT_SYNC)
 			mode |= ISOLATE_ASYNC_MIGRATE;
 
 		/* Try isolate the page */
@@ -357,27 +358,90 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 
 #endif /* CONFIG_COMPACTION || CONFIG_CMA */
 #ifdef CONFIG_COMPACTION
+/*
+ * Returns true if MIGRATE_UNMOVABLE pageblock was successfully
+ * converted to MIGRATE_MOVABLE type, false otherwise.
+ */
+static bool rescue_unmovable_pageblock(struct page *page)
+{
+	unsigned long pfn, start_pfn, end_pfn;
+	struct page *start_page, *end_page;
+
+	pfn = page_to_pfn(page);
+	start_pfn = pfn & ~(pageblock_nr_pages - 1);
+	end_pfn = start_pfn + pageblock_nr_pages;
+
+	start_page = pfn_to_page(start_pfn);
+	end_page = pfn_to_page(end_pfn);
+
+	/* Do not deal with pageblocks that overlap zones */
+	if (page_zone(start_page) != page_zone(end_page))
+		return false;
+
+	for (page = start_page, pfn = start_pfn; page < end_page; pfn++,
+								  page++) {
+		if (!pfn_valid_within(pfn))
+			continue;
+
+		if (PageBuddy(page)) {
+			int order = page_order(page);
+
+			pfn += (1 << order) - 1;
+			page += (1 << order) - 1;
+
+			continue;
+		} else if (page_count(page) == 0 || PageLRU(page))
+			continue;
+
+		return false;
+	}
+
+	set_pageblock_migratetype(page, MIGRATE_MOVABLE);
+	move_freepages_block(page_zone(page), page, MIGRATE_MOVABLE);
+	return true;
+}
 
-/* Returns true if the page is within a block suitable for migration to */
-static bool suitable_migration_target(struct page *page)
+enum smt_result {
+	GOOD_AS_MIGRATION_TARGET,
+	FAIL_UNMOVABLE_TARGET,
+	FAIL_BAD_TARGET,
+};
+
+/*
+ * Returns GOOD_AS_MIGRATION_TARGET if the page is within a block
+ * suitable for migration to, FAIL_UNMOVABLE_TARGET if the page
+ * is within a MIGRATE_UNMOVABLE block, FAIL_BAD_TARGET otherwise.
+ */
+static enum smt_result suitable_migration_target(struct page *page,
+				      struct compact_control *cc)
 {
 
 	int migratetype = get_pageblock_migratetype(page);
 
 	/* Don't interfere with memory hot-remove or the min_free_kbytes blocks */
 	if (migratetype == MIGRATE_ISOLATE || migratetype == MIGRATE_RESERVE)
-		return false;
+		return FAIL_BAD_TARGET;
 
 	/* If the page is a large free page, then allow migration */
 	if (PageBuddy(page) && page_order(page) >= pageblock_order)
-		return true;
+		return GOOD_AS_MIGRATION_TARGET;
 
 	/* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */
-	if (migrate_async_suitable(migratetype))
-		return true;
+	if (cc->mode != COMPACT_ASYNC_UNMOVABLE &&
+	    migrate_async_suitable(migratetype))
+		return GOOD_AS_MIGRATION_TARGET;
+
+	if (cc->mode == COMPACT_ASYNC_MOVABLE &&
+	    migratetype == MIGRATE_UNMOVABLE)
+		return FAIL_UNMOVABLE_TARGET;
+
+	if (cc->mode != COMPACT_ASYNC_MOVABLE &&
+	    migratetype == MIGRATE_UNMOVABLE &&
+	    rescue_unmovable_pageblock(page))
+		return GOOD_AS_MIGRATION_TARGET;
 
 	/* Otherwise skip the block */
-	return false;
+	return FAIL_BAD_TARGET;
 }
 
 /*
@@ -411,6 +475,13 @@ static void isolate_freepages(struct zone *zone,
 	zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages;
 
 	/*
+	 * isolate_freepages() may be called more than once during
+	 * compact_zone_order() run and we want only the most recent
+	 * count.
+	 */
+	cc->nr_pageblocks_skipped = 0;
+
+	/*
 	 * Isolate free pages until enough are available to migrate the
 	 * pages on cc->migratepages. We stop searching if the migrate
 	 * and free page scanners meet or enough free pages are isolated.
@@ -418,6 +489,7 @@ static void isolate_freepages(struct zone *zone,
 	for (; pfn > low_pfn && cc->nr_migratepages > nr_freepages;
 					pfn -= pageblock_nr_pages) {
 		unsigned long isolated;
+		enum smt_result ret;
 
 		if (!pfn_valid(pfn))
 			continue;
@@ -434,9 +506,12 @@ static void isolate_freepages(struct zone *zone,
 			continue;
 
 		/* Check the block is suitable for migration */
-		if (!suitable_migration_target(page))
+		ret = suitable_migration_target(page, cc);
+		if (ret != GOOD_AS_MIGRATION_TARGET) {
+			if (ret == FAIL_UNMOVABLE_TARGET)
+				cc->nr_pageblocks_skipped++;
 			continue;
-
+		}
 		/*
 		 * Found a block suitable for isolating free pages from. Now
 		 * we disabled interrupts, double check things are ok and
@@ -445,12 +520,14 @@ static void isolate_freepages(struct zone *zone,
 		 */
 		isolated = 0;
 		spin_lock_irqsave(&zone->lock, flags);
-		if (suitable_migration_target(page)) {
+		ret = suitable_migration_target(page, cc);
+		if (ret == GOOD_AS_MIGRATION_TARGET) {
 			end_pfn = min(pfn + pageblock_nr_pages, zone_end_pfn);
 			isolated = isolate_freepages_block(pfn, end_pfn,
 							   freelist, false);
 			nr_freepages += isolated;
-		}
+		} else if (ret == FAIL_UNMOVABLE_TARGET)
+			cc->nr_pageblocks_skipped++;
 		spin_unlock_irqrestore(&zone->lock, flags);
 
 		/*
@@ -682,8 +759,9 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 
 		nr_migrate = cc->nr_migratepages;
 		err = migrate_pages(&cc->migratepages, compaction_alloc,
-				(unsigned long)cc, false,
-				cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC);
+			(unsigned long)&cc->freepages, false,
+			(cc->mode == COMPACT_SYNC) ? MIGRATE_SYNC_LIGHT
+						      : MIGRATE_ASYNC);
 		update_nr_listpages(cc);
 		nr_remaining = cc->nr_migratepages;
 
@@ -712,7 +790,8 @@ out:
 
 static unsigned long compact_zone_order(struct zone *zone,
 				 int order, gfp_t gfp_mask,
-				 bool sync)
+				 enum compact_mode mode,
+				 unsigned long *nr_pageblocks_skipped)
 {
 	struct compact_control cc = {
 		.nr_freepages = 0,
@@ -720,12 +799,17 @@ static unsigned long compact_zone_order(struct zone *zone,
 		.order = order,
 		.migratetype = allocflags_to_migratetype(gfp_mask),
 		.zone = zone,
-		.sync = sync,
+		.mode = mode,
 	};
+	unsigned long rc;
+
 	INIT_LIST_HEAD(&cc.freepages);
 	INIT_LIST_HEAD(&cc.migratepages);
 
-	return compact_zone(zone, &cc);
+	rc = compact_zone(zone, &cc);
+	*nr_pageblocks_skipped = cc.nr_pageblocks_skipped;
+
+	return rc;
 }
 
 int sysctl_extfrag_threshold = 500;
@@ -750,6 +834,8 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 	struct zoneref *z;
 	struct zone *zone;
 	int rc = COMPACT_SKIPPED;
+	unsigned long nr_pageblocks_skipped;
+	enum compact_mode mode;
 
 	/*
 	 * Check whether it is worth even starting compaction. The order check is
@@ -766,12 +852,22 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 								nodemask) {
 		int status;
 
-		status = compact_zone_order(zone, order, gfp_mask, sync);
+		mode = sync ? COMPACT_SYNC : COMPACT_ASYNC_MOVABLE;
+retry:
+		status = compact_zone_order(zone, order, gfp_mask, mode,
+						&nr_pageblocks_skipped);
 		rc = max(status, rc);
 
 		/* If a normal allocation would succeed, stop compacting */
 		if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0, 0))
 			break;
+
+		if (rc == COMPACT_COMPLETE && mode == COMPACT_ASYNC_MOVABLE) {
+			if (nr_pageblocks_skipped) {
+				mode = COMPACT_ASYNC_UNMOVABLE;
+				goto retry;
+			}
+		}
 	}
 
 	return rc;
@@ -805,7 +901,7 @@ static int __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc)
 			if (ok && cc->order > zone->compact_order_failed)
 				zone->compact_order_failed = cc->order + 1;
 			/* Currently async compaction is never deferred. */
-			else if (!ok && cc->sync)
+			else if (!ok && cc->mode == COMPACT_SYNC)
 				defer_compaction(zone, cc->order);
 		}
 
@@ -820,7 +916,7 @@ int compact_pgdat(pg_data_t *pgdat, int order)
 {
 	struct compact_control cc = {
 		.order = order,
-		.sync = false,
+		.mode = COMPACT_ASYNC_MOVABLE,
 	};
 
 	return __compact_pgdat(pgdat, &cc);
@@ -830,7 +926,7 @@ static int compact_node(int nid)
 {
 	struct compact_control cc = {
 		.order = -1,
-		.sync = true,
+		.mode = COMPACT_SYNC,
 	};
 
 	return __compact_pgdat(NODE_DATA(nid), &cc);
diff --git a/mm/filemap.c b/mm/filemap.c
index 79c4b2b0b14e..64b48f934b89 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -29,7 +29,6 @@
 #include <linux/pagevec.h>
 #include <linux/blkdev.h>
 #include <linux/security.h>
-#include <linux/syscalls.h>
 #include <linux/cpuset.h>
 #include <linux/hardirq.h> /* for BUG_ON(!in_atomic()) only */
 #include <linux/memcontrol.h>
@@ -1478,44 +1477,6 @@ out:
 }
 EXPORT_SYMBOL(generic_file_aio_read);
 
-static ssize_t
-do_readahead(struct address_space *mapping, struct file *filp,
-	     pgoff_t index, unsigned long nr)
-{
-	if (!mapping || !mapping->a_ops || !mapping->a_ops->readpage)
-		return -EINVAL;
-
-	force_page_cache_readahead(mapping, filp, index, nr);
-	return 0;
-}
-
-SYSCALL_DEFINE(readahead)(int fd, loff_t offset, size_t count)
-{
-	ssize_t ret;
-	struct file *file;
-
-	ret = -EBADF;
-	file = fget(fd);
-	if (file) {
-		if (file->f_mode & FMODE_READ) {
-			struct address_space *mapping = file->f_mapping;
-			pgoff_t start = offset >> PAGE_CACHE_SHIFT;
-			pgoff_t end = (offset + count - 1) >> PAGE_CACHE_SHIFT;
-			unsigned long len = end - start + 1;
-			ret = do_readahead(mapping, file, start, len);
-		}
-		fput(file);
-	}
-	return ret;
-}
-#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
-asmlinkage long SyS_readahead(long fd, loff_t offset, long count)
-{
-	return SYSC_readahead((int) fd, offset, (size_t) count);
-}
-SYSCALL_ALIAS(sys_readahead, SyS_readahead);
-#endif
-
 #ifdef CONFIG_MMU
 /**
  * page_cache_read - adds requested page to the page cache if not already there
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index f0e5306eeb55..d0def42c121b 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -636,16 +636,12 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 					unsigned long haddr, pmd_t *pmd,
 					struct page *page)
 {
-	int ret = 0;
 	pgtable_t pgtable;
 
 	VM_BUG_ON(!PageCompound(page));
 	pgtable = pte_alloc_one(mm, haddr);
-	if (unlikely(!pgtable)) {
-		mem_cgroup_uncharge_page(page);
-		put_page(page);
+	if (unlikely(!pgtable))
 		return VM_FAULT_OOM;
-	}
 
 	clear_huge_page(page, haddr, HPAGE_PMD_NR);
 	__SetPageUptodate(page);
@@ -675,7 +671,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 		spin_unlock(&mm->page_table_lock);
 	}
 
-	return ret;
+	return 0;
 }
 
 static inline gfp_t alloc_hugepage_gfpmask(int defrag, gfp_t extra_gfp)
@@ -724,8 +720,14 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			put_page(page);
 			goto out;
 		}
+		if (unlikely(__do_huge_pmd_anonymous_page(mm, vma, haddr, pmd,
+							  page))) {
+			mem_cgroup_uncharge_page(page);
+			put_page(page);
+			goto out;
+		}
 
-		return __do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, page);
+		return 0;
 	}
 out:
 	/*
@@ -950,6 +952,8 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		count_vm_event(THP_FAULT_FALLBACK);
 		ret = do_huge_pmd_wp_page_fallback(mm, vma, address,
 						   pmd, orig_pmd, page, haddr);
+		if (ret & VM_FAULT_OOM)
+			split_huge_page(page);
 		put_page(page);
 		goto out;
 	}
@@ -957,6 +961,7 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) {
 		put_page(new_page);
+		split_huge_page(page);
 		put_page(page);
 		ret |= VM_FAULT_OOM;
 		goto out;
@@ -968,8 +973,10 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	spin_lock(&mm->page_table_lock);
 	put_page(page);
 	if (unlikely(!pmd_same(*pmd, orig_pmd))) {
+		spin_unlock(&mm->page_table_lock);
 		mem_cgroup_uncharge_page(new_page);
 		put_page(new_page);
+		goto out;
 	} else {
 		pmd_t entry;
 		VM_BUG_ON(!PageHead(page));
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 4e28416c47fb..285a81e87ec8 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -273,8 +273,8 @@ static long region_count(struct list_head *head, long f, long t)
 
 	/* Locate each segment we overlap with, and count that overlap. */
 	list_for_each_entry(rg, head, link) {
-		int seg_from;
-		int seg_to;
+		long seg_from;
+		long seg_to;
 
 		if (rg->to <= f)
 			continue;
@@ -2157,6 +2157,15 @@ static void hugetlb_vm_op_open(struct vm_area_struct *vma)
 		kref_get(&reservations->refs);
 }
 
+static void resv_map_put(struct vm_area_struct *vma)
+{
+	struct resv_map *reservations = vma_resv_map(vma);
+
+	if (!reservations)
+		return;
+	kref_put(&reservations->refs, resv_map_release);
+}
+
 static void hugetlb_vm_op_close(struct vm_area_struct *vma)
 {
 	struct hstate *h = hstate_vma(vma);
@@ -2173,7 +2182,7 @@ static void hugetlb_vm_op_close(struct vm_area_struct *vma)
 		reserve = (end - start) -
 			region_count(&reservations->regions, start, end);
 
-		kref_put(&reservations->refs, resv_map_release);
+		resv_map_put(vma);
 
 		if (reserve) {
 			hugetlb_acct_memory(h, -reserve);
@@ -2991,12 +3000,16 @@ int hugetlb_reserve_pages(struct inode *inode,
 		set_vma_resv_flags(vma, HPAGE_RESV_OWNER);
 	}
 
-	if (chg < 0)
-		return chg;
+	if (chg < 0) {
+		ret = chg;
+		goto out_err;
+	}
 
 	/* There must be enough pages in the subpool for the mapping */
-	if (hugepage_subpool_get_pages(spool, chg))
-		return -ENOSPC;
+	if (hugepage_subpool_get_pages(spool, chg)) {
+		ret = -ENOSPC;
+		goto out_err;
+	}
 
 	/*
 	 * Check enough hugepages are available for the reservation.
@@ -3005,7 +3018,7 @@ int hugetlb_reserve_pages(struct inode *inode,
 	ret = hugetlb_acct_memory(h, chg);
 	if (ret < 0) {
 		hugepage_subpool_put_pages(spool, chg);
-		return ret;
+		goto out_err;
 	}
 
 	/*
@@ -3022,6 +3035,9 @@ int hugetlb_reserve_pages(struct inode *inode,
 	if (!vma || vma->vm_flags & VM_MAYSHARE)
 		region_add(&inode->i_mapping->private_list, from, to);
 	return 0;
+out_err:
+	resv_map_put(vma);
+	return ret;
 }
 
 void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
diff --git a/mm/internal.h b/mm/internal.h
index aee4761cf9a9..4194ab9dc19b 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -94,6 +94,9 @@ extern void putback_lru_page(struct page *page);
 /*
  * in mm/page_alloc.c
  */
+extern void set_pageblock_migratetype(struct page *page, int migratetype);
+extern int move_freepages_block(struct zone *zone, struct page *page,
+				int migratetype);
 extern void __free_pages_bootmem(struct page *page, unsigned int order);
 extern void prep_compound_page(struct page *page, unsigned long order);
 #ifdef CONFIG_MEMORY_FAILURE
@@ -101,6 +104,7 @@ extern bool is_free_buddy_page(struct page *page);
 #endif
 
 #if defined CONFIG_COMPACTION || defined CONFIG_CMA
+#include <linux/compaction.h>
 
 /*
  * in mm/compaction.c
@@ -119,11 +123,14 @@ struct compact_control {
 	unsigned long nr_migratepages;	/* Number of pages to migrate */
 	unsigned long free_pfn;		/* isolate_freepages search base */
 	unsigned long migrate_pfn;	/* isolate_migratepages search base */
-	bool sync;			/* Synchronous migration */
+	enum compact_mode mode;		/* Compaction mode */
 
 	int order;			/* order a direct compactor needs */
 	int migratetype;		/* MOVABLE, RECLAIMABLE etc */
 	struct zone *zone;
+
+	/* Number of UNMOVABLE destination pageblocks skipped during scan */
+	unsigned long nr_pageblocks_skipped;
 };
 
 unsigned long
@@ -164,7 +171,8 @@ static inline void munlock_vma_pages_all(struct vm_area_struct *vma)
  * to determine if it's being mapped into a LOCKED vma.
  * If so, mark page as mlocked.
  */
-static inline int is_mlocked_vma(struct vm_area_struct *vma, struct page *page)
+static inline int mlocked_vma_newpage(struct vm_area_struct *vma,
+				    struct page *page)
 {
 	VM_BUG_ON(PageLRU(page));
 
@@ -222,7 +230,7 @@ extern unsigned long vma_address(struct page *page,
 				 struct vm_area_struct *vma);
 #endif
 #else /* !CONFIG_MMU */
-static inline int is_mlocked_vma(struct vm_area_struct *v, struct page *p)
+static inline int mlocked_vma_newpage(struct vm_area_struct *v, struct page *p)
 {
 	return 0;
 }
diff --git a/mm/madvise.c b/mm/madvise.c
index 1ccbba5b6674..deff1b64a08c 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -11,8 +11,10 @@
 #include <linux/mempolicy.h>
 #include <linux/page-isolation.h>
 #include <linux/hugetlb.h>
+#include <linux/falloc.h>
 #include <linux/sched.h>
 #include <linux/ksm.h>
+#include <linux/fs.h>
 
 /*
  * Any behaviour which results in changes to the vma->vm_flags needs to
@@ -200,8 +202,7 @@ static long madvise_remove(struct vm_area_struct *vma,
 				struct vm_area_struct **prev,
 				unsigned long start, unsigned long end)
 {
-	struct address_space *mapping;
-	loff_t offset, endoff;
+	loff_t offset;
 	int error;
 
 	*prev = NULL;	/* tell sys_madvise we drop mmap_sem */
@@ -217,16 +218,14 @@ static long madvise_remove(struct vm_area_struct *vma,
 	if ((vma->vm_flags & (VM_SHARED|VM_WRITE)) != (VM_SHARED|VM_WRITE))
 		return -EACCES;
 
-	mapping = vma->vm_file->f_mapping;
-
 	offset = (loff_t)(start - vma->vm_start)
 			+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
-	endoff = (loff_t)(end - vma->vm_start - 1)
-			+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
 
-	/* vmtruncate_range needs to take i_mutex */
+	/* filesystem's fallocate may need to take i_mutex */
 	up_read(&current->mm->mmap_sem);
-	error = vmtruncate_range(mapping->host, offset, endoff);
+	error = do_fallocate(vma->vm_file,
+				FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
+				offset, end - start);
 	down_read(&current->mm->mmap_sem);
 	return error;
 }
diff --git a/mm/memblock.c b/mm/memblock.c
index a44eab3157f8..952123eba433 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -37,6 +37,8 @@ struct memblock memblock __initdata_memblock = {
 
 int memblock_debug __initdata_memblock;
 static int memblock_can_resize __initdata_memblock;
+static int memblock_memory_in_slab __initdata_memblock = 0;
+static int memblock_reserved_in_slab __initdata_memblock = 0;
 
 /* inline so we don't get a warning when pr_debug is compiled out */
 static inline const char *memblock_type_name(struct memblock_type *type)
@@ -187,6 +189,7 @@ static int __init_memblock memblock_double_array(struct memblock_type *type)
 	struct memblock_region *new_array, *old_array;
 	phys_addr_t old_size, new_size, addr;
 	int use_slab = slab_is_available();
+	int *in_slab;
 
 	/* We don't allow resizing until we know about the reserved regions
 	 * of memory that aren't suitable for allocation
@@ -198,6 +201,12 @@ static int __init_memblock memblock_double_array(struct memblock_type *type)
 	old_size = type->max * sizeof(struct memblock_region);
 	new_size = old_size << 1;
 
+	/* Retrieve the slab flag */
+	if (type == &memblock.memory)
+		in_slab = &memblock_memory_in_slab;
+	else
+		in_slab = &memblock_reserved_in_slab;
+
 	/* Try to find some space for it.
 	 *
 	 * WARNING: We assume that either slab_is_available() and we use it or
@@ -212,14 +221,15 @@ static int __init_memblock memblock_double_array(struct memblock_type *type)
 	if (use_slab) {
 		new_array = kmalloc(new_size, GFP_KERNEL);
 		addr = new_array ? __pa(new_array) : 0;
-	} else
+	} else {
 		addr = memblock_find_in_range(0, MEMBLOCK_ALLOC_ACCESSIBLE, new_size, sizeof(phys_addr_t));
+		new_array = addr ? __va(addr) : 0;
+	}
 	if (!addr) {
 		pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n",
 		       memblock_type_name(type), type->max, type->max * 2);
 		return -1;
 	}
-	new_array = __va(addr);
 
 	memblock_dbg("memblock: %s array is doubled to %ld at [%#010llx-%#010llx]",
 		 memblock_type_name(type), type->max * 2, (u64)addr, (u64)addr + new_size - 1);
@@ -234,22 +244,24 @@ static int __init_memblock memblock_double_array(struct memblock_type *type)
 	type->regions = new_array;
 	type->max <<= 1;
 
-	/* If we use SLAB that's it, we are done */
-	if (use_slab)
-		return 0;
-
-	/* Add the new reserved region now. Should not fail ! */
-	BUG_ON(memblock_reserve(addr, new_size));
-
-	/* If the array wasn't our static init one, then free it. We only do
-	 * that before SLAB is available as later on, we don't know whether
-	 * to use kfree or free_bootmem_pages(). Shouldn't be a big deal
-	 * anyways
+	/* Free old array. We needn't free it if the array is the
+	 * static one
 	 */
-	if (old_array != memblock_memory_init_regions &&
-	    old_array != memblock_reserved_init_regions)
+	if (*in_slab)
+		kfree(old_array);
+	else if (old_array != memblock_memory_init_regions &&
+		 old_array != memblock_reserved_init_regions)
 		memblock_free(__pa(old_array), old_size);
 
+	/* Reserve the new array if that comes from the memblock.
+	 * Otherwise, we needn't do it
+	 */
+	if (!use_slab)
+		BUG_ON(memblock_reserve(addr, new_size));
+
+	/* Update slab flag */
+	*in_slab = use_slab;
+
 	return 0;
 }
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index f342778a0c0a..00c8898dbb81 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -138,7 +138,6 @@ struct mem_cgroup_per_zone {
 
 	struct mem_cgroup_reclaim_iter reclaim_iter[DEF_PRIORITY + 1];
 
-	struct zone_reclaim_stat reclaim_stat;
 	struct rb_node		tree_node;	/* RB tree node */
 	unsigned long long	usage_in_excess;/* Set to the value by which */
 						/* the soft limit is exceeded*/
@@ -1149,15 +1148,25 @@ struct lruvec *mem_cgroup_lru_move_lists(struct zone *zone,
  * Checks whether given mem is same or in the root_mem_cgroup's
  * hierarchy subtree
  */
+bool __mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg,
+				  struct mem_cgroup *memcg)
+{
+	if (root_memcg == memcg)
+		return true;
+	if (!root_memcg->use_hierarchy)
+		return false;
+	return css_is_ancestor(&memcg->css, &root_memcg->css);
+}
+
 static bool mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg,
-		struct mem_cgroup *memcg)
+				       struct mem_cgroup *memcg)
 {
-	if (root_memcg != memcg) {
-		return (root_memcg->use_hierarchy &&
-			css_is_ancestor(&memcg->css, &root_memcg->css));
-	}
+	bool ret;
 
-	return true;
+	rcu_read_lock();
+	ret = __mem_cgroup_same_or_subtree(root_memcg, memcg);
+	rcu_read_unlock();
+	return ret;
 }
 
 int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *memcg)
@@ -1233,16 +1242,6 @@ int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg, struct zone *zone)
 	return (active > inactive);
 }
 
-struct zone_reclaim_stat *mem_cgroup_get_reclaim_stat(struct mem_cgroup *memcg,
-						      struct zone *zone)
-{
-	int nid = zone_to_nid(zone);
-	int zid = zone_idx(zone);
-	struct mem_cgroup_per_zone *mz = mem_cgroup_zoneinfo(memcg, nid, zid);
-
-	return &mz->reclaim_stat;
-}
-
 struct zone_reclaim_stat *
 mem_cgroup_get_reclaim_stat_from_page(struct page *page)
 {
@@ -1258,7 +1257,7 @@ mem_cgroup_get_reclaim_stat_from_page(struct page *page)
 	/* Ensure pc->mem_cgroup is visible after reading PCG_USED. */
 	smp_rmb();
 	mz = page_cgroup_zoneinfo(pc->mem_cgroup, page);
-	return &mz->reclaim_stat;
+	return &mz->lruvec.reclaim_stat;
 }
 
 #define mem_cgroup_from_res_counter(counter, member)	\
@@ -2845,24 +2844,7 @@ __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *memcg,
 	 */
 	if (do_swap_account && PageSwapCache(page)) {
 		swp_entry_t ent = {.val = page_private(page)};
-		struct mem_cgroup *swap_memcg;
-		unsigned short id;
-
-		id = swap_cgroup_record(ent, 0);
-		rcu_read_lock();
-		swap_memcg = mem_cgroup_lookup(id);
-		if (swap_memcg) {
-			/*
-			 * This recorded memcg can be obsolete one. So, avoid
-			 * calling css_tryget
-			 */
-			if (!mem_cgroup_is_root(swap_memcg))
-				res_counter_uncharge(&swap_memcg->memsw,
-						     PAGE_SIZE);
-			mem_cgroup_swap_statistics(swap_memcg, false);
-			mem_cgroup_put(swap_memcg);
-		}
-		rcu_read_unlock();
+		mem_cgroup_uncharge_swap(ent);
 	}
 	/*
 	 * At swapin, we may charge account against cgroup which has no tasks.
@@ -3155,7 +3137,6 @@ void mem_cgroup_uncharge_swap(swp_entry_t ent)
  * @entry: swap entry to be moved
  * @from:  mem_cgroup which the entry is moved from
  * @to:  mem_cgroup which the entry is moved to
- * @need_fixup: whether we should fixup res_counters and refcounts.
  *
  * It succeeds only when the swap_cgroup's record for this entry is the same
  * as the mem_cgroup's id of @from.
@@ -3166,7 +3147,7 @@ void mem_cgroup_uncharge_swap(swp_entry_t ent)
  * both res and memsw, and called css_get().
  */
 static int mem_cgroup_move_swap_account(swp_entry_t entry,
-		struct mem_cgroup *from, struct mem_cgroup *to, bool need_fixup)
+				struct mem_cgroup *from, struct mem_cgroup *to)
 {
 	unsigned short old_id, new_id;
 
@@ -3185,24 +3166,13 @@ static int mem_cgroup_move_swap_account(swp_entry_t entry,
 		 * swap-in, the refcount of @to might be decreased to 0.
 		 */
 		mem_cgroup_get(to);
-		if (need_fixup) {
-			if (!mem_cgroup_is_root(from))
-				res_counter_uncharge(&from->memsw, PAGE_SIZE);
-			mem_cgroup_put(from);
-			/*
-			 * we charged both to->res and to->memsw, so we should
-			 * uncharge to->res.
-			 */
-			if (!mem_cgroup_is_root(to))
-				res_counter_uncharge(&to->res, PAGE_SIZE);
-		}
 		return 0;
 	}
 	return -EINVAL;
 }
 #else
 static inline int mem_cgroup_move_swap_account(swp_entry_t entry,
-		struct mem_cgroup *from, struct mem_cgroup *to, bool need_fixup)
+				struct mem_cgroup *from, struct mem_cgroup *to)
 {
 	return -EINVAL;
 }
@@ -3363,7 +3333,7 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg,
 void mem_cgroup_replace_page_cache(struct page *oldpage,
 				  struct page *newpage)
 {
-	struct mem_cgroup *memcg;
+	struct mem_cgroup *memcg = NULL;
 	struct page_cgroup *pc;
 	enum charge_type type = MEM_CGROUP_CHARGE_TYPE_CACHE;
 
@@ -3373,11 +3343,20 @@ void mem_cgroup_replace_page_cache(struct page *oldpage,
 	pc = lookup_page_cgroup(oldpage);
 	/* fix accounting on old pages */
 	lock_page_cgroup(pc);
-	memcg = pc->mem_cgroup;
-	mem_cgroup_charge_statistics(memcg, false, -1);
-	ClearPageCgroupUsed(pc);
+	if (PageCgroupUsed(pc)) {
+		memcg = pc->mem_cgroup;
+		mem_cgroup_charge_statistics(memcg, false, -1);
+		ClearPageCgroupUsed(pc);
+	}
 	unlock_page_cgroup(pc);
 
+	/*
+	 * When called from shmem_replace_page(), in some cases the
+	 * oldpage has already been charged, and in some cases not.
+	 */
+	if (!memcg)
+		return;
+
 	if (PageSwapBacked(oldpage))
 		type = MEM_CGROUP_CHARGE_TYPE_SHMEM;
 
@@ -4226,21 +4205,19 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
 	{
 		int nid, zid;
 		struct mem_cgroup_per_zone *mz;
+		struct zone_reclaim_stat *rstat;
 		unsigned long recent_rotated[2] = {0, 0};
 		unsigned long recent_scanned[2] = {0, 0};
 
 		for_each_online_node(nid)
 			for (zid = 0; zid < MAX_NR_ZONES; zid++) {
 				mz = mem_cgroup_zoneinfo(memcg, nid, zid);
+				rstat = &mz->lruvec.reclaim_stat;
 
-				recent_rotated[0] +=
-					mz->reclaim_stat.recent_rotated[0];
-				recent_rotated[1] +=
-					mz->reclaim_stat.recent_rotated[1];
-				recent_scanned[0] +=
-					mz->reclaim_stat.recent_scanned[0];
-				recent_scanned[1] +=
-					mz->reclaim_stat.recent_scanned[1];
+				recent_rotated[0] += rstat->recent_rotated[0];
+				recent_rotated[1] += rstat->recent_rotated[1];
+				recent_scanned[0] += rstat->recent_scanned[0];
+				recent_scanned[1] += rstat->recent_scanned[1];
 			}
 		cb->fill(cb, "recent_rotated_anon", recent_rotated[0]);
 		cb->fill(cb, "recent_rotated_file", recent_rotated[1]);
@@ -5135,7 +5112,7 @@ static struct page *mc_handle_present_pte(struct vm_area_struct *vma,
 		return NULL;
 	if (PageAnon(page)) {
 		/* we don't move shared anon */
-		if (!move_anon() || page_mapcount(page) > 2)
+		if (!move_anon())
 			return NULL;
 	} else if (!move_file())
 		/* we ignore mapcount for file pages */
@@ -5146,26 +5123,32 @@ static struct page *mc_handle_present_pte(struct vm_area_struct *vma,
 	return page;
 }
 
+#ifdef CONFIG_SWAP
 static struct page *mc_handle_swap_pte(struct vm_area_struct *vma,
 			unsigned long addr, pte_t ptent, swp_entry_t *entry)
 {
-	int usage_count;
 	struct page *page = NULL;
 	swp_entry_t ent = pte_to_swp_entry(ptent);
 
 	if (!move_anon() || non_swap_entry(ent))
 		return NULL;
-	usage_count = mem_cgroup_count_swap_user(ent, &page);
-	if (usage_count > 1) { /* we don't move shared anon */
-		if (page)
-			put_page(page);
-		return NULL;
-	}
+	/*
+	 * Because lookup_swap_cache() updates some statistics counter,
+	 * we call find_get_page() with swapper_space directly.
+	 */
+	page = find_get_page(&swapper_space, ent.val);
 	if (do_swap_account)
 		entry->val = ent.val;
 
 	return page;
 }
+#else
+static struct page *mc_handle_swap_pte(struct vm_area_struct *vma,
+			unsigned long addr, pte_t ptent, swp_entry_t *entry)
+{
+	return NULL;
+}
+#endif
 
 static struct page *mc_handle_file_pte(struct vm_area_struct *vma,
 			unsigned long addr, pte_t ptent, swp_entry_t *entry)
@@ -5521,8 +5504,7 @@ put:			/* get_mctgt_type() gets the page */
 			break;
 		case MC_TARGET_SWAP:
 			ent = target.ent;
-			if (!mem_cgroup_move_swap_account(ent,
-						mc.from, mc.to, false)) {
+			if (!mem_cgroup_move_swap_account(ent, mc.from, mc.to)) {
 				mc.precharge--;
 				/* we fixup refcnts and charges later. */
 				mc.moved_swap++;
@@ -5598,7 +5580,6 @@ static void mem_cgroup_move_task(struct cgroup *cont,
 	if (mm) {
 		if (mc.to)
 			mem_cgroup_move_charge(mm);
-		put_swap_token(mm);
 		mmput(mm);
 	}
 	if (mc.to)
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index c99ad4e6b88c..ab1e7145e290 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1388,16 +1388,16 @@ static int get_any_page(struct page *p, unsigned long pfn, int flags)
 	 */
 	if (!get_page_unless_zero(compound_head(p))) {
 		if (PageHuge(p)) {
-			pr_info("get_any_page: %#lx free huge page\n", pfn);
+			pr_info("%s: %#lx free huge page\n", __func__, pfn);
 			ret = dequeue_hwpoisoned_huge_page(compound_head(p));
 		} else if (is_free_buddy_page(p)) {
-			pr_info("get_any_page: %#lx free buddy page\n", pfn);
+			pr_info("%s: %#lx free buddy page\n", __func__, pfn);
 			/* Set hwpoison bit while page is still isolated */
 			SetPageHWPoison(p);
 			ret = 0;
 		} else {
-			pr_info("get_any_page: %#lx: unknown zero refcount page type %lx\n",
-				pfn, p->flags);
+			pr_info("%s: %#lx: unknown zero refcount page type %lx\n",
+				__func__, pfn, p->flags);
 			ret = -EIO;
 		}
 	} else {
diff --git a/mm/memory.c b/mm/memory.c
index e40f6759ba98..1b7dc662bf9f 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2908,7 +2908,6 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	delayacct_set_flag(DELAYACCT_PF_SWAPIN);
 	page = lookup_swap_cache(entry);
 	if (!page) {
-		grab_swap_token(mm); /* Contend for token _before_ read-in */
 		page = swapin_readahead(entry,
 					GFP_HIGHUSER_MOVABLE, vma, address);
 		if (!page) {
@@ -2938,6 +2937,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	}
 
 	locked = lock_page_or_retry(page, mm, flags);
+
 	delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
 	if (!locked) {
 		ret |= VM_FAULT_RETRY;
@@ -3486,6 +3486,7 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (unlikely(is_vm_hugetlb_page(vma)))
 		return hugetlb_fault(mm, vma, address, flags);
 
+retry:
 	pgd = pgd_offset(mm, address);
 	pud = pud_alloc(mm, pgd, address);
 	if (!pud)
@@ -3499,13 +3500,24 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 							  pmd, flags);
 	} else {
 		pmd_t orig_pmd = *pmd;
+		int ret;
+
 		barrier();
 		if (pmd_trans_huge(orig_pmd)) {
 			if (flags & FAULT_FLAG_WRITE &&
 			    !pmd_write(orig_pmd) &&
-			    !pmd_trans_splitting(orig_pmd))
-				return do_huge_pmd_wp_page(mm, vma, address,
-							   pmd, orig_pmd);
+			    !pmd_trans_splitting(orig_pmd)) {
+				ret = do_huge_pmd_wp_page(mm, vma, address, pmd,
+							  orig_pmd);
+				/*
+				 * If COW results in an oom, the huge pmd will
+				 * have been split, so retry the fault on the
+				 * pte for a smaller charge.
+				 */
+				if (unlikely(ret & VM_FAULT_OOM))
+					goto retry;
+				return ret;
+			}
 			return 0;
 		}
 	}
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index fc898cb4fe8f..0d7e3ec8e0f3 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -74,8 +74,7 @@ static struct resource *register_memory_resource(u64 start, u64 size)
 	res->end = start + size - 1;
 	res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
 	if (request_resource(&iomem_resource, res) < 0) {
-		printk("System RAM resource %llx - %llx cannot be added\n",
-		(unsigned long long)res->start, (unsigned long long)res->end);
+		printk("System RAM resource %pR cannot be added\n", res);
 		kfree(res);
 		res = NULL;
 	}
@@ -502,8 +501,10 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages)
 		online_pages_range);
 	if (ret) {
 		mutex_unlock(&zonelists_mutex);
-		printk(KERN_DEBUG "online_pages %lx at %lx failed\n",
-			nr_pages, pfn);
+		printk(KERN_DEBUG "online_pages [mem %#010llx-%#010llx] failed\n",
+		       (unsigned long long) pfn << PAGE_SHIFT,
+		       (((unsigned long long) pfn + nr_pages)
+			    << PAGE_SHIFT) - 1);
 		memory_notify(MEM_CANCEL_ONLINE, &arg);
 		unlock_memory_hotplug();
 		return ret;
@@ -977,8 +978,9 @@ repeat:
 	return 0;
 
 failed_removal:
-	printk(KERN_INFO "memory offlining %lx to %lx failed\n",
-		start_pfn, end_pfn);
+	printk(KERN_INFO "memory offlining [mem %#010llx-%#010llx] failed\n",
+	       (unsigned long long) start_pfn << PAGE_SHIFT,
+	       ((unsigned long long) end_pfn << PAGE_SHIFT) - 1);
 	memory_notify(MEM_CANCEL_OFFLINE, &arg);
 	/* pushback to free area */
 	undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 88f9422b92e7..f15c1b24ca18 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -390,7 +390,7 @@ static void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask,
 {
 	if (!pol)
 		return;
-	if (!mpol_store_user_nodemask(pol) && step == 0 &&
+	if (!mpol_store_user_nodemask(pol) && step == MPOL_REBIND_ONCE &&
 	    nodes_equal(pol->w.cpuset_mems_allowed, *newmask))
 		return;
 
@@ -950,8 +950,8 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest,
  *
  * Returns the number of page that could not be moved.
  */
-int do_migrate_pages(struct mm_struct *mm,
-	const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags)
+int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
+		     const nodemask_t *to, int flags)
 {
 	int busy = 0;
 	int err;
@@ -963,7 +963,7 @@ int do_migrate_pages(struct mm_struct *mm,
 
 	down_read(&mm->mmap_sem);
 
-	err = migrate_vmas(mm, from_nodes, to_nodes, flags);
+	err = migrate_vmas(mm, from, to, flags);
 	if (err)
 		goto out;
 
@@ -998,14 +998,34 @@ int do_migrate_pages(struct mm_struct *mm,
 	 * moved to an empty node, then there is nothing left worth migrating.
 	 */
 
-	tmp = *from_nodes;
+	tmp = *from;
 	while (!nodes_empty(tmp)) {
 		int s,d;
 		int source = -1;
 		int dest = 0;
 
 		for_each_node_mask(s, tmp) {
-			d = node_remap(s, *from_nodes, *to_nodes);
+
+			/*
+			 * do_migrate_pages() tries to maintain the relative
+			 * node relationship of the pages established between
+			 * threads and memory areas.
+                         *
+			 * However if the number of source nodes is not equal to
+			 * the number of destination nodes we can not preserve
+			 * this node relative relationship.  In that case, skip
+			 * copying memory from a node that is in the destination
+			 * mask.
+			 *
+			 * Example: [2,3,4] -> [3,4,5] moves everything.
+			 *          [0-7] - > [3,4,5] moves only 0,1,2,6,7.
+			 */
+
+			if ((nodes_weight(*from) != nodes_weight(*to)) &&
+						(node_isset(s, *to)))
+				continue;
+
+			d = node_remap(s, *from, *to);
 			if (s == d)
 				continue;
 
@@ -1065,8 +1085,8 @@ static void migrate_page_add(struct page *page, struct list_head *pagelist,
 {
 }
 
-int do_migrate_pages(struct mm_struct *mm,
-	const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags)
+int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
+		     const nodemask_t *to, int flags)
 {
 	return -ENOSYS;
 }
diff --git a/mm/mmap.c b/mm/mmap.c
index e8dcfc7de866..4a9c2a391e28 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1639,33 +1639,34 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
 {
 	struct vm_area_struct *vma = NULL;
 
-	if (mm) {
-		/* Check the cache first. */
-		/* (Cache hit rate is typically around 35%.) */
-		vma = mm->mmap_cache;
-		if (!(vma && vma->vm_end > addr && vma->vm_start <= addr)) {
-			struct rb_node * rb_node;
-
-			rb_node = mm->mm_rb.rb_node;
-			vma = NULL;
-
-			while (rb_node) {
-				struct vm_area_struct * vma_tmp;
-
-				vma_tmp = rb_entry(rb_node,
-						struct vm_area_struct, vm_rb);
-
-				if (vma_tmp->vm_end > addr) {
-					vma = vma_tmp;
-					if (vma_tmp->vm_start <= addr)
-						break;
-					rb_node = rb_node->rb_left;
-				} else
-					rb_node = rb_node->rb_right;
-			}
-			if (vma)
-				mm->mmap_cache = vma;
+	if (WARN_ON_ONCE(!mm))		/* Remove this in linux-3.6 */
+		return NULL;
+
+	/* Check the cache first. */
+	/* (Cache hit rate is typically around 35%.) */
+	vma = mm->mmap_cache;
+	if (!(vma && vma->vm_end > addr && vma->vm_start <= addr)) {
+		struct rb_node *rb_node;
+
+		rb_node = mm->mm_rb.rb_node;
+		vma = NULL;
+
+		while (rb_node) {
+			struct vm_area_struct *vma_tmp;
+
+			vma_tmp = rb_entry(rb_node,
+					   struct vm_area_struct, vm_rb);
+
+			if (vma_tmp->vm_end > addr) {
+				vma = vma_tmp;
+				if (vma_tmp->vm_start <= addr)
+					break;
+				rb_node = rb_node->rb_left;
+			} else
+				rb_node = rb_node->rb_right;
 		}
+		if (vma)
+			mm->mmap_cache = vma;
 	}
 	return vma;
 }
diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index 1983fb1c7026..d23415c001bc 100644
--- a/mm/nobootmem.c
+++ b/mm/nobootmem.c
@@ -274,86 +274,85 @@ void * __init __alloc_bootmem(unsigned long size, unsigned long align,
 	return ___alloc_bootmem(size, align, goal, limit);
 }
 
-/**
- * __alloc_bootmem_node - allocate boot memory from a specific node
- * @pgdat: node to allocate from
- * @size: size of the request in bytes
- * @align: alignment of the region
- * @goal: preferred starting address of the region
- *
- * The goal is dropped if it can not be satisfied and the allocation will
- * fall back to memory below @goal.
- *
- * Allocation may fall back to any node in the system if the specified node
- * can not hold the requested memory.
- *
- * The function panics if the request can not be satisfied.
- */
-void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
-				   unsigned long align, unsigned long goal)
+static void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat,
+						   unsigned long size,
+						   unsigned long align,
+						   unsigned long goal,
+						   unsigned long limit)
 {
 	void *ptr;
 
-	if (WARN_ON_ONCE(slab_is_available()))
-		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
-
 again:
 	ptr = __alloc_memory_core_early(pgdat->node_id, size, align,
-					 goal, -1ULL);
+					goal, limit);
 	if (ptr)
 		return ptr;
 
 	ptr = __alloc_memory_core_early(MAX_NUMNODES, size, align,
-					goal, -1ULL);
-	if (!ptr && goal) {
+					goal, limit);
+	if (ptr)
+		return ptr;
+
+	if (goal) {
 		goal = 0;
 		goto again;
 	}
-	return ptr;
+
+	return NULL;
 }
 
-void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
+void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size,
 				   unsigned long align, unsigned long goal)
 {
-	return __alloc_bootmem_node(pgdat, size, align, goal);
+	if (WARN_ON_ONCE(slab_is_available()))
+		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
+
+	return ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, 0);
 }
 
-#ifdef CONFIG_SPARSEMEM
-/**
- * alloc_bootmem_section - allocate boot memory from a specific section
- * @size: size of the request in bytes
- * @section_nr: sparse map section to allocate from
- *
- * Return NULL on failure.
- */
-void * __init alloc_bootmem_section(unsigned long size,
-				    unsigned long section_nr)
+void * __init ___alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
+				    unsigned long align, unsigned long goal,
+				    unsigned long limit)
 {
-	unsigned long pfn, goal, limit;
+	void *ptr;
 
-	pfn = section_nr_to_pfn(section_nr);
-	goal = pfn << PAGE_SHIFT;
-	limit = section_nr_to_pfn(section_nr + 1) << PAGE_SHIFT;
+	ptr = ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, limit);
+	if (ptr)
+		return ptr;
 
-	return __alloc_memory_core_early(early_pfn_to_nid(pfn), size,
-					 SMP_CACHE_BYTES, goal, limit);
+	printk(KERN_ALERT "bootmem alloc of %lu bytes failed!\n", size);
+	panic("Out of memory");
+	return NULL;
 }
-#endif
 
-void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size,
+/**
+ * __alloc_bootmem_node - allocate boot memory from a specific node
+ * @pgdat: node to allocate from
+ * @size: size of the request in bytes
+ * @align: alignment of the region
+ * @goal: preferred starting address of the region
+ *
+ * The goal is dropped if it can not be satisfied and the allocation will
+ * fall back to memory below @goal.
+ *
+ * Allocation may fall back to any node in the system if the specified node
+ * can not hold the requested memory.
+ *
+ * The function panics if the request can not be satisfied.
+ */
+void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
 				   unsigned long align, unsigned long goal)
 {
-	void *ptr;
-
 	if (WARN_ON_ONCE(slab_is_available()))
 		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
 
-	ptr =  __alloc_memory_core_early(pgdat->node_id, size, align,
-						 goal, -1ULL);
-	if (ptr)
-		return ptr;
+	return ___alloc_bootmem_node(pgdat, size, align, goal, 0);
+}
 
-	return __alloc_bootmem_nopanic(size, align, goal);
+void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
+				   unsigned long align, unsigned long goal)
+{
+	return __alloc_bootmem_node(pgdat, size, align, goal);
 }
 
 #ifndef ARCH_LOW_ADDRESS_LIMIT
@@ -397,16 +396,9 @@ void * __init __alloc_bootmem_low(unsigned long size, unsigned long align,
 void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size,
 				       unsigned long align, unsigned long goal)
 {
-	void *ptr;
-
 	if (WARN_ON_ONCE(slab_is_available()))
 		return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
 
-	ptr = __alloc_memory_core_early(pgdat->node_id, size, align,
-				goal, ARCH_LOW_ADDRESS_LIMIT);
-	if (ptr)
-		return ptr;
-
-	return  __alloc_memory_core_early(MAX_NUMNODES, size, align,
-				goal, ARCH_LOW_ADDRESS_LIMIT);
+	return ___alloc_bootmem_node(pgdat, size, align, goal,
+				     ARCH_LOW_ADDRESS_LIMIT);
 }
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 9f09a1fde9f9..ed0e19677360 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -180,10 +180,10 @@ static bool oom_unkillable_task(struct task_struct *p,
  * predictable as possible.  The goal is to return the highest value for the
  * task consuming the most memory to avoid subsequent oom failures.
  */
-unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
-		      const nodemask_t *nodemask, unsigned long totalpages)
+unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
+			  const nodemask_t *nodemask, unsigned long totalpages)
 {
-	long points;
+	unsigned long points;
 
 	if (oom_unkillable_task(p, memcg, nodemask))
 		return 0;
@@ -198,21 +198,11 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
 	}
 
 	/*
-	 * The memory controller may have a limit of 0 bytes, so avoid a divide
-	 * by zero, if necessary.
-	 */
-	if (!totalpages)
-		totalpages = 1;
-
-	/*
 	 * The baseline for the badness score is the proportion of RAM that each
 	 * task's rss, pagetable and swap space use.
 	 */
-	points = get_mm_rss(p->mm) + p->mm->nr_ptes;
-	points += get_mm_counter(p->mm, MM_SWAPENTS);
-
-	points *= 1000;
-	points /= totalpages;
+	points = get_mm_rss(p->mm) + p->mm->nr_ptes +
+		 get_mm_counter(p->mm, MM_SWAPENTS);
 	task_unlock(p);
 
 	/*
@@ -220,23 +210,20 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
 	 * implementation used by LSMs.
 	 */
 	if (has_capability_noaudit(p, CAP_SYS_ADMIN))
-		points -= 30;
+		points -= 30 * totalpages / 1000;
 
 	/*
 	 * /proc/pid/oom_score_adj ranges from -1000 to +1000 such that it may
 	 * either completely disable oom killing or always prefer a certain
 	 * task.
 	 */
-	points += p->signal->oom_score_adj;
+	points += p->signal->oom_score_adj * totalpages / 1000;
 
 	/*
-	 * Never return 0 for an eligible task that may be killed since it's
-	 * possible that no single user task uses more than 0.1% of memory and
-	 * no single admin tasks uses more than 3.0%.
+	 * Never return 0 for an eligible task regardless of the root bonus and
+	 * oom_score_adj (oom_score_adj can't be OOM_SCORE_ADJ_MIN here).
 	 */
-	if (points <= 0)
-		return 1;
-	return (points < 1000) ? points : 1000;
+	return points ? points : 1;
 }
 
 /*
@@ -314,7 +301,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
 {
 	struct task_struct *g, *p;
 	struct task_struct *chosen = NULL;
-	*ppoints = 0;
+	unsigned long chosen_points = 0;
 
 	do_each_thread(g, p) {
 		unsigned int points;
@@ -354,7 +341,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
 			 */
 			if (p == current) {
 				chosen = p;
-				*ppoints = 1000;
+				chosen_points = ULONG_MAX;
 			} else if (!force_kill) {
 				/*
 				 * If this task is not being ptraced on exit,
@@ -367,12 +354,13 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
 		}
 
 		points = oom_badness(p, memcg, nodemask, totalpages);
-		if (points > *ppoints) {
+		if (points > chosen_points) {
 			chosen = p;
-			*ppoints = points;
+			chosen_points = points;
 		}
 	} while_each_thread(g, p);
 
+	*ppoints = chosen_points * 1000 / totalpages;
 	return chosen;
 }
 
@@ -572,7 +560,7 @@ void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	}
 
 	check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL);
-	limit = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT;
+	limit = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT ? : 1;
 	read_lock(&tasklist_lock);
 	p = select_bad_process(&points, limit, memcg, NULL, false);
 	if (p && PTR_ERR(p) != -1UL)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index bab8e3bc4202..8cbfc38e68ac 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -219,7 +219,7 @@ EXPORT_SYMBOL(nr_online_nodes);
 
 int page_group_by_mobility_disabled __read_mostly;
 
-static void set_pageblock_migratetype(struct page *page, int migratetype)
+void set_pageblock_migratetype(struct page *page, int migratetype)
 {
 
 	if (unlikely(page_group_by_mobility_disabled))
@@ -954,8 +954,8 @@ static int move_freepages(struct zone *zone,
 	return pages_moved;
 }
 
-static int move_freepages_block(struct zone *zone, struct page *page,
-				int migratetype)
+int move_freepages_block(struct zone *zone, struct page *page,
+			 int migratetype)
 {
 	unsigned long start_pfn, end_pfn;
 	struct page *start_page, *end_page;
@@ -4300,25 +4300,24 @@ static inline void setup_usemap(struct pglist_data *pgdat,
 
 #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
 
-/* Return a sensible default order for the pageblock size. */
-static inline int pageblock_default_order(void)
-{
-	if (HPAGE_SHIFT > PAGE_SHIFT)
-		return HUGETLB_PAGE_ORDER;
-
-	return MAX_ORDER-1;
-}
-
 /* Initialise the number of pages represented by NR_PAGEBLOCK_BITS */
-static inline void __init set_pageblock_order(unsigned int order)
+static inline void __init set_pageblock_order(void)
 {
+	unsigned int order;
+
 	/* Check that pageblock_nr_pages has not already been setup */
 	if (pageblock_order)
 		return;
 
+	if (HPAGE_SHIFT > PAGE_SHIFT)
+		order = HUGETLB_PAGE_ORDER;
+	else
+		order = MAX_ORDER - 1;
+
 	/*
 	 * Assume the largest contiguous order of interest is a huge page.
-	 * This value may be variable depending on boot parameters on IA64
+	 * This value may be variable depending on boot parameters on IA64 and
+	 * powerpc.
 	 */
 	pageblock_order = order;
 }
@@ -4326,15 +4325,13 @@ static inline void __init set_pageblock_order(unsigned int order)
 
 /*
  * When CONFIG_HUGETLB_PAGE_SIZE_VARIABLE is not set, set_pageblock_order()
- * and pageblock_default_order() are unused as pageblock_order is set
- * at compile-time. See include/linux/pageblock-flags.h for the values of
- * pageblock_order based on the kernel config
+ * is unused as pageblock_order is set at compile-time. See
+ * include/linux/pageblock-flags.h for the values of pageblock_order based on
+ * the kernel config
  */
-static inline int pageblock_default_order(unsigned int order)
+static inline void set_pageblock_order(void)
 {
-	return MAX_ORDER-1;
 }
-#define set_pageblock_order(x)	do {} while (0)
 
 #endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
 
@@ -4413,16 +4410,16 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 		zone_pcp_init(zone);
 		for_each_lru(lru)
 			INIT_LIST_HEAD(&zone->lruvec.lists[lru]);
-		zone->reclaim_stat.recent_rotated[0] = 0;
-		zone->reclaim_stat.recent_rotated[1] = 0;
-		zone->reclaim_stat.recent_scanned[0] = 0;
-		zone->reclaim_stat.recent_scanned[1] = 0;
+		zone->lruvec.reclaim_stat.recent_rotated[0] = 0;
+		zone->lruvec.reclaim_stat.recent_rotated[1] = 0;
+		zone->lruvec.reclaim_stat.recent_scanned[0] = 0;
+		zone->lruvec.reclaim_stat.recent_scanned[1] = 0;
 		zap_zone_vm_stats(zone);
 		zone->flags = 0;
 		if (!size)
 			continue;
 
-		set_pageblock_order(pageblock_default_order());
+		set_pageblock_order();
 		setup_usemap(pgdat, zone, size);
 		ret = init_currently_empty_zone(zone, zone_start_pfn,
 						size, MEMMAP_EARLY);
@@ -4815,7 +4812,7 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 	find_zone_movable_pfns_for_nodes();
 
 	/* Print out the zone ranges */
-	printk("Zone PFN ranges:\n");
+	printk("Zone ranges:\n");
 	for (i = 0; i < MAX_NR_ZONES; i++) {
 		if (i == ZONE_MOVABLE)
 			continue;
@@ -4824,22 +4821,25 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 				arch_zone_highest_possible_pfn[i])
 			printk(KERN_CONT "empty\n");
 		else
-			printk(KERN_CONT "%0#10lx -> %0#10lx\n",
-				arch_zone_lowest_possible_pfn[i],
-				arch_zone_highest_possible_pfn[i]);
+			printk(KERN_CONT "[mem %0#10lx-%0#10lx]\n",
+				arch_zone_lowest_possible_pfn[i] << PAGE_SHIFT,
+				(arch_zone_highest_possible_pfn[i]
+					<< PAGE_SHIFT) - 1);
 	}
 
 	/* Print out the PFNs ZONE_MOVABLE begins at in each node */
-	printk("Movable zone start PFN for each node\n");
+	printk("Movable zone start for each node\n");
 	for (i = 0; i < MAX_NUMNODES; i++) {
 		if (zone_movable_pfn[i])
-			printk("  Node %d: %lu\n", i, zone_movable_pfn[i]);
+			printk("  Node %d: %#010lx\n", i,
+			       zone_movable_pfn[i] << PAGE_SHIFT);
 	}
 
 	/* Print out the early_node_map[] */
-	printk("Early memory PFN ranges\n");
+	printk("Early memory node ranges\n");
 	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid)
-		printk("  %3d: %0#10lx -> %0#10lx\n", nid, start_pfn, end_pfn);
+		printk("  node %3d: [mem %#010lx-%#010lx]\n", nid,
+		       start_pfn << PAGE_SHIFT, (end_pfn << PAGE_SHIFT) - 1);
 
 	/* Initialise every node */
 	mminit_verify_pageflags_layout();
@@ -5657,7 +5657,7 @@ static int __alloc_contig_migrate_range(unsigned long start, unsigned long end)
 		.nr_migratepages = 0,
 		.order = -1,
 		.zone = page_zone(pfn_to_page(start)),
-		.sync = true,
+		.mode = COMPACT_SYNC,
 	};
 	INIT_LIST_HEAD(&cc.migratepages);
 
@@ -5938,7 +5938,7 @@ bool is_free_buddy_page(struct page *page)
 }
 #endif
 
-static struct trace_print_flags pageflag_names[] = {
+static const struct trace_print_flags pageflag_names[] = {
 	{1UL << PG_locked,		"locked"	},
 	{1UL << PG_error,		"error"		},
 	{1UL << PG_referenced,		"referenced"	},
@@ -5973,7 +5973,9 @@ static struct trace_print_flags pageflag_names[] = {
 #ifdef CONFIG_MEMORY_FAILURE
 	{1UL << PG_hwpoison,		"hwpoison"	},
 #endif
-	{-1UL,				NULL		},
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	{1UL << PG_compound_lock,	"compound_lock"	},
+#endif
 };
 
 static void dump_page_flags(unsigned long flags)
@@ -5982,12 +5984,14 @@ static void dump_page_flags(unsigned long flags)
 	unsigned long mask;
 	int i;
 
+	BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS);
+
 	printk(KERN_ALERT "page flags: %#lx(", flags);
 
 	/* remove zone id */
 	flags &= (1UL << NR_PAGEFLAGS) - 1;
 
-	for (i = 0; pageflag_names[i].name && flags; i++) {
+	for (i = 0; i < ARRAY_SIZE(pageflag_names) && flags; i++) {
 
 		mask = pageflag_names[i].mask;
 		if ((flags & mask) != mask)
diff --git a/mm/readahead.c b/mm/readahead.c
index cbcbb02f3e28..ea8f8fa21649 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -17,6 +17,8 @@
 #include <linux/task_io_accounting_ops.h>
 #include <linux/pagevec.h>
 #include <linux/pagemap.h>
+#include <linux/syscalls.h>
+#include <linux/file.h>
 
 /*
  * Initialise a struct file's readahead state.  Assumes that the caller has
@@ -562,3 +564,41 @@ page_cache_async_readahead(struct address_space *mapping,
 	ondemand_readahead(mapping, ra, filp, true, offset, req_size);
 }
 EXPORT_SYMBOL_GPL(page_cache_async_readahead);
+
+static ssize_t
+do_readahead(struct address_space *mapping, struct file *filp,
+	     pgoff_t index, unsigned long nr)
+{
+	if (!mapping || !mapping->a_ops || !mapping->a_ops->readpage)
+		return -EINVAL;
+
+	force_page_cache_readahead(mapping, filp, index, nr);
+	return 0;
+}
+
+SYSCALL_DEFINE(readahead)(int fd, loff_t offset, size_t count)
+{
+	ssize_t ret;
+	struct file *file;
+
+	ret = -EBADF;
+	file = fget(fd);
+	if (file) {
+		if (file->f_mode & FMODE_READ) {
+			struct address_space *mapping = file->f_mapping;
+			pgoff_t start = offset >> PAGE_CACHE_SHIFT;
+			pgoff_t end = (offset + count - 1) >> PAGE_CACHE_SHIFT;
+			unsigned long len = end - start + 1;
+			ret = do_readahead(mapping, file, start, len);
+		}
+		fput(file);
+	}
+	return ret;
+}
+#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
+asmlinkage long SyS_readahead(long fd, loff_t offset, long count)
+{
+	return SYSC_readahead((int) fd, offset, (size_t) count);
+}
+SYSCALL_ALIAS(sys_readahead, SyS_readahead);
+#endif
diff --git a/mm/rmap.c b/mm/rmap.c
index 5b5ad584ffb7..0f3b7cda2a24 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -755,12 +755,6 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma,
 		pte_unmap_unlock(pte, ptl);
 	}
 
-	/* Pretend the page is referenced if the task has the
-	   swap token and is in the middle of a page fault. */
-	if (mm != current->mm && has_swap_token(mm) &&
-			rwsem_is_locked(&mm->mmap_sem))
-		referenced++;
-
 	(*mapcount)--;
 
 	if (referenced)
diff --git a/mm/shmem.c b/mm/shmem.c
index be5af34a070d..d576b84d913c 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -53,6 +53,7 @@ static struct vfsmount *shm_mnt;
 #include <linux/blkdev.h>
 #include <linux/pagevec.h>
 #include <linux/percpu_counter.h>
+#include <linux/falloc.h>
 #include <linux/splice.h>
 #include <linux/security.h>
 #include <linux/swapops.h>
@@ -83,12 +84,25 @@ struct shmem_xattr {
 	char value[0];
 };
 
+/*
+ * shmem_fallocate and shmem_writepage communicate via inode->i_private
+ * (with i_mutex making sure that it has only one user at a time):
+ * we would prefer not to enlarge the shmem inode just for that.
+ */
+struct shmem_falloc {
+	pgoff_t start;		/* start of range currently being fallocated */
+	pgoff_t next;		/* the next page offset to be fallocated */
+	pgoff_t nr_falloced;	/* how many new pages have been fallocated */
+	pgoff_t nr_unswapped;	/* how often writepage refused to swap out */
+};
+
 /* Flag allocation requirements to shmem_getpage */
 enum sgp_type {
 	SGP_READ,	/* don't exceed i_size, don't allocate page */
 	SGP_CACHE,	/* don't exceed i_size, may allocate page */
 	SGP_DIRTY,	/* like SGP_CACHE, but set new page dirty */
-	SGP_WRITE,	/* may exceed i_size, may allocate page */
+	SGP_WRITE,	/* may exceed i_size, may allocate !Uptodate page */
+	SGP_FALLOC,	/* like SGP_WRITE, but make existing page Uptodate */
 };
 
 #ifdef CONFIG_TMPFS
@@ -103,6 +117,9 @@ static unsigned long shmem_default_max_inodes(void)
 }
 #endif
 
+static bool shmem_should_replace_page(struct page *page, gfp_t gfp);
+static int shmem_replace_page(struct page **pagep, gfp_t gfp,
+				struct shmem_inode_info *info, pgoff_t index);
 static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 	struct page **pagep, enum sgp_type sgp, gfp_t gfp, int *fault_type);
 
@@ -423,27 +440,31 @@ void shmem_unlock_mapping(struct address_space *mapping)
 
 /*
  * Remove range of pages and swap entries from radix tree, and free them.
+ * If !unfalloc, truncate or punch hole; if unfalloc, undo failed fallocate.
  */
-void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
+static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
+								 bool unfalloc)
 {
 	struct address_space *mapping = inode->i_mapping;
 	struct shmem_inode_info *info = SHMEM_I(inode);
 	pgoff_t start = (lstart + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
-	unsigned partial = lstart & (PAGE_CACHE_SIZE - 1);
-	pgoff_t end = (lend >> PAGE_CACHE_SHIFT);
+	pgoff_t end = (lend + 1) >> PAGE_CACHE_SHIFT;
+	unsigned int partial_start = lstart & (PAGE_CACHE_SIZE - 1);
+	unsigned int partial_end = (lend + 1) & (PAGE_CACHE_SIZE - 1);
 	struct pagevec pvec;
 	pgoff_t indices[PAGEVEC_SIZE];
 	long nr_swaps_freed = 0;
 	pgoff_t index;
 	int i;
 
-	BUG_ON((lend & (PAGE_CACHE_SIZE - 1)) != (PAGE_CACHE_SIZE - 1));
+	if (lend == -1)
+		end = -1;	/* unsigned, so actually very big */
 
 	pagevec_init(&pvec, 0);
 	index = start;
-	while (index <= end) {
+	while (index < end) {
 		pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
-			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1,
+				min(end - index, (pgoff_t)PAGEVEC_SIZE),
 							pvec.pages, indices);
 		if (!pvec.nr)
 			break;
@@ -452,10 +473,12 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
 			struct page *page = pvec.pages[i];
 
 			index = indices[i];
-			if (index > end)
+			if (index >= end)
 				break;
 
 			if (radix_tree_exceptional_entry(page)) {
+				if (unfalloc)
+					continue;
 				nr_swaps_freed += !shmem_free_swap(mapping,
 								index, page);
 				continue;
@@ -463,9 +486,11 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
 
 			if (!trylock_page(page))
 				continue;
-			if (page->mapping == mapping) {
-				VM_BUG_ON(PageWriteback(page));
-				truncate_inode_page(mapping, page);
+			if (!unfalloc || !PageUptodate(page)) {
+				if (page->mapping == mapping) {
+					VM_BUG_ON(PageWriteback(page));
+					truncate_inode_page(mapping, page);
+				}
 			}
 			unlock_page(page);
 		}
@@ -476,30 +501,47 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
 		index++;
 	}
 
-	if (partial) {
+	if (partial_start) {
 		struct page *page = NULL;
 		shmem_getpage(inode, start - 1, &page, SGP_READ, NULL);
 		if (page) {
-			zero_user_segment(page, partial, PAGE_CACHE_SIZE);
+			unsigned int top = PAGE_CACHE_SIZE;
+			if (start > end) {
+				top = partial_end;
+				partial_end = 0;
+			}
+			zero_user_segment(page, partial_start, top);
+			set_page_dirty(page);
+			unlock_page(page);
+			page_cache_release(page);
+		}
+	}
+	if (partial_end) {
+		struct page *page = NULL;
+		shmem_getpage(inode, end, &page, SGP_READ, NULL);
+		if (page) {
+			zero_user_segment(page, 0, partial_end);
 			set_page_dirty(page);
 			unlock_page(page);
 			page_cache_release(page);
 		}
 	}
+	if (start >= end)
+		return;
 
 	index = start;
 	for ( ; ; ) {
 		cond_resched();
 		pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
-			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1,
+				min(end - index, (pgoff_t)PAGEVEC_SIZE),
 							pvec.pages, indices);
 		if (!pvec.nr) {
-			if (index == start)
+			if (index == start || unfalloc)
 				break;
 			index = start;
 			continue;
 		}
-		if (index == start && indices[0] > end) {
+		if ((index == start || unfalloc) && indices[0] >= end) {
 			shmem_deswap_pagevec(&pvec);
 			pagevec_release(&pvec);
 			break;
@@ -509,19 +551,23 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
 			struct page *page = pvec.pages[i];
 
 			index = indices[i];
-			if (index > end)
+			if (index >= end)
 				break;
 
 			if (radix_tree_exceptional_entry(page)) {
+				if (unfalloc)
+					continue;
 				nr_swaps_freed += !shmem_free_swap(mapping,
 								index, page);
 				continue;
 			}
 
 			lock_page(page);
-			if (page->mapping == mapping) {
-				VM_BUG_ON(PageWriteback(page));
-				truncate_inode_page(mapping, page);
+			if (!unfalloc || !PageUptodate(page)) {
+				if (page->mapping == mapping) {
+					VM_BUG_ON(PageWriteback(page));
+					truncate_inode_page(mapping, page);
+				}
 			}
 			unlock_page(page);
 		}
@@ -535,7 +581,11 @@ void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
 	info->swapped -= nr_swaps_freed;
 	shmem_recalc_inode(inode);
 	spin_unlock(&info->lock);
+}
 
+void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
+{
+	shmem_undo_range(inode, lstart, lend, false);
 	inode->i_ctime = inode->i_mtime = CURRENT_TIME;
 }
 EXPORT_SYMBOL_GPL(shmem_truncate_range);
@@ -604,12 +654,13 @@ static void shmem_evict_inode(struct inode *inode)
  * If swap found in inode, free it and move page from swapcache to filecache.
  */
 static int shmem_unuse_inode(struct shmem_inode_info *info,
-			     swp_entry_t swap, struct page *page)
+			     swp_entry_t swap, struct page **pagep)
 {
 	struct address_space *mapping = info->vfs_inode.i_mapping;
 	void *radswap;
 	pgoff_t index;
-	int error;
+	gfp_t gfp;
+	int error = 0;
 
 	radswap = swp_to_radix_entry(swap);
 	index = radix_tree_locate_item(&mapping->page_tree, radswap);
@@ -625,22 +676,37 @@ static int shmem_unuse_inode(struct shmem_inode_info *info,
 	if (shmem_swaplist.next != &info->swaplist)
 		list_move_tail(&shmem_swaplist, &info->swaplist);
 
+	gfp = mapping_gfp_mask(mapping);
+	if (shmem_should_replace_page(*pagep, gfp)) {
+		mutex_unlock(&shmem_swaplist_mutex);
+		error = shmem_replace_page(pagep, gfp, info, index);
+		mutex_lock(&shmem_swaplist_mutex);
+		/*
+		 * We needed to drop mutex to make that restrictive page
+		 * allocation; but the inode might already be freed by now,
+		 * and we cannot refer to inode or mapping or info to check.
+		 * However, we do hold page lock on the PageSwapCache page,
+		 * so can check if that still has our reference remaining.
+		 */
+		if (!page_swapcount(*pagep))
+			error = -ENOENT;
+	}
+
 	/*
 	 * We rely on shmem_swaplist_mutex, not only to protect the swaplist,
 	 * but also to hold up shmem_evict_inode(): so inode cannot be freed
 	 * beneath us (pagelock doesn't help until the page is in pagecache).
 	 */
-	error = shmem_add_to_page_cache(page, mapping, index,
+	if (!error)
+		error = shmem_add_to_page_cache(*pagep, mapping, index,
 						GFP_NOWAIT, radswap);
-	/* which does mem_cgroup_uncharge_cache_page on error */
-
 	if (error != -ENOMEM) {
 		/*
 		 * Truncation and eviction use free_swap_and_cache(), which
 		 * only does trylock page: if we raced, best clean up here.
 		 */
-		delete_from_swap_cache(page);
-		set_page_dirty(page);
+		delete_from_swap_cache(*pagep);
+		set_page_dirty(*pagep);
 		if (!error) {
 			spin_lock(&info->lock);
 			info->swapped--;
@@ -660,7 +726,14 @@ int shmem_unuse(swp_entry_t swap, struct page *page)
 	struct list_head *this, *next;
 	struct shmem_inode_info *info;
 	int found = 0;
-	int error;
+	int error = 0;
+
+	/*
+	 * There's a faint possibility that swap page was replaced before
+	 * caller locked it: it will come back later with the right page.
+	 */
+	if (unlikely(!PageSwapCache(page)))
+		goto out;
 
 	/*
 	 * Charge page using GFP_KERNEL while we can wait, before taking
@@ -676,7 +749,7 @@ int shmem_unuse(swp_entry_t swap, struct page *page)
 	list_for_each_safe(this, next, &shmem_swaplist) {
 		info = list_entry(this, struct shmem_inode_info, swaplist);
 		if (info->swapped)
-			found = shmem_unuse_inode(info, swap, page);
+			found = shmem_unuse_inode(info, swap, &page);
 		else
 			list_del_init(&info->swaplist);
 		cond_resched();
@@ -685,8 +758,6 @@ int shmem_unuse(swp_entry_t swap, struct page *page)
 	}
 	mutex_unlock(&shmem_swaplist_mutex);
 
-	if (!found)
-		mem_cgroup_uncharge_cache_page(page);
 	if (found < 0)
 		error = found;
 out:
@@ -727,6 +798,38 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 		WARN_ON_ONCE(1);	/* Still happens? Tell us about it! */
 		goto redirty;
 	}
+
+	/*
+	 * This is somewhat ridiculous, but without plumbing a SWAP_MAP_FALLOC
+	 * value into swapfile.c, the only way we can correctly account for a
+	 * fallocated page arriving here is now to initialize it and write it.
+	 *
+	 * That's okay for a page already fallocated earlier, but if we have
+	 * not yet completed the fallocation, then (a) we want to keep track
+	 * of this page in case we have to undo it, and (b) it may not be a
+	 * good idea to continue anyway, once we're pushing into swap.  So
+	 * reactivate the page, and let shmem_fallocate() quit when too many.
+	 */
+	if (!PageUptodate(page)) {
+		if (inode->i_private) {
+			struct shmem_falloc *shmem_falloc;
+			spin_lock(&inode->i_lock);
+			shmem_falloc = inode->i_private;
+			if (shmem_falloc &&
+			    index >= shmem_falloc->start &&
+			    index < shmem_falloc->next)
+				shmem_falloc->nr_unswapped++;
+			else
+				shmem_falloc = NULL;
+			spin_unlock(&inode->i_lock);
+			if (shmem_falloc)
+				goto redirty;
+		}
+		clear_highpage(page);
+		flush_dcache_page(page);
+		SetPageUptodate(page);
+	}
+
 	swap = get_swap_page();
 	if (!swap.val)
 		goto redirty;
@@ -856,6 +959,84 @@ static inline struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo)
 #endif
 
 /*
+ * When a page is moved from swapcache to shmem filecache (either by the
+ * usual swapin of shmem_getpage_gfp(), or by the less common swapoff of
+ * shmem_unuse_inode()), it may have been read in earlier from swap, in
+ * ignorance of the mapping it belongs to.  If that mapping has special
+ * constraints (like the gma500 GEM driver, which requires RAM below 4GB),
+ * we may need to copy to a suitable page before moving to filecache.
+ *
+ * In a future release, this may well be extended to respect cpuset and
+ * NUMA mempolicy, and applied also to anonymous pages in do_swap_page();
+ * but for now it is a simple matter of zone.
+ */
+static bool shmem_should_replace_page(struct page *page, gfp_t gfp)
+{
+	return page_zonenum(page) > gfp_zone(gfp);
+}
+
+static int shmem_replace_page(struct page **pagep, gfp_t gfp,
+				struct shmem_inode_info *info, pgoff_t index)
+{
+	struct page *oldpage, *newpage;
+	struct address_space *swap_mapping;
+	pgoff_t swap_index;
+	int error;
+
+	oldpage = *pagep;
+	swap_index = page_private(oldpage);
+	swap_mapping = page_mapping(oldpage);
+
+	/*
+	 * We have arrived here because our zones are constrained, so don't
+	 * limit chance of success by further cpuset and node constraints.
+	 */
+	gfp &= ~GFP_CONSTRAINT_MASK;
+	newpage = shmem_alloc_page(gfp, info, index);
+	if (!newpage)
+		return -ENOMEM;
+	VM_BUG_ON(shmem_should_replace_page(newpage, gfp));
+
+	*pagep = newpage;
+	page_cache_get(newpage);
+	copy_highpage(newpage, oldpage);
+
+	VM_BUG_ON(!PageLocked(oldpage));
+	__set_page_locked(newpage);
+	VM_BUG_ON(!PageUptodate(oldpage));
+	SetPageUptodate(newpage);
+	VM_BUG_ON(!PageSwapBacked(oldpage));
+	SetPageSwapBacked(newpage);
+	VM_BUG_ON(!swap_index);
+	set_page_private(newpage, swap_index);
+	VM_BUG_ON(!PageSwapCache(oldpage));
+	SetPageSwapCache(newpage);
+
+	/*
+	 * Our caller will very soon move newpage out of swapcache, but it's
+	 * a nice clean interface for us to replace oldpage by newpage there.
+	 */
+	spin_lock_irq(&swap_mapping->tree_lock);
+	error = shmem_radix_tree_replace(swap_mapping, swap_index, oldpage,
+								   newpage);
+	__inc_zone_page_state(newpage, NR_FILE_PAGES);
+	__dec_zone_page_state(oldpage, NR_FILE_PAGES);
+	spin_unlock_irq(&swap_mapping->tree_lock);
+	BUG_ON(error);
+
+	mem_cgroup_replace_page_cache(oldpage, newpage);
+	lru_cache_add_anon(newpage);
+
+	ClearPageSwapCache(oldpage);
+	set_page_private(oldpage, 0);
+
+	unlock_page(oldpage);
+	page_cache_release(oldpage);
+	page_cache_release(oldpage);
+	return 0;
+}
+
+/*
  * shmem_getpage_gfp - find page in cache, or get from swap, or allocate
  *
  * If we allocate a new one we do not mark it dirty. That's up to the
@@ -872,6 +1053,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
 	swp_entry_t swap;
 	int error;
 	int once = 0;
+	int alloced = 0;
 
 	if (index > (MAX_LFS_FILESIZE >> PAGE_CACHE_SHIFT))
 		return -EFBIG;
@@ -883,19 +1065,21 @@ repeat:
 		page = NULL;
 	}
 
-	if (sgp != SGP_WRITE &&
+	if (sgp != SGP_WRITE && sgp != SGP_FALLOC &&
 	    ((loff_t)index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) {
 		error = -EINVAL;
 		goto failed;
 	}
 
+	/* fallocated page? */
+	if (page && !PageUptodate(page)) {
+		if (sgp != SGP_READ)
+			goto clear;
+		unlock_page(page);
+		page_cache_release(page);
+		page = NULL;
+	}
 	if (page || (sgp == SGP_READ && !swap.val)) {
-		/*
-		 * Once we can get the page lock, it must be uptodate:
-		 * if there were an error in reading back from swap,
-		 * the page would not be inserted into the filecache.
-		 */
-		BUG_ON(page && !PageUptodate(page));
 		*pagep = page;
 		return 0;
 	}
@@ -923,19 +1107,20 @@ repeat:
 
 		/* We have to do this with page locked to prevent races */
 		lock_page(page);
+		if (!PageSwapCache(page) || page->mapping) {
+			error = -EEXIST;	/* try again */
+			goto failed;
+		}
 		if (!PageUptodate(page)) {
 			error = -EIO;
 			goto failed;
 		}
 		wait_on_page_writeback(page);
 
-		/* Someone may have already done it for us */
-		if (page->mapping) {
-			if (page->mapping == mapping &&
-			    page->index == index)
-				goto done;
-			error = -EEXIST;
-			goto failed;
+		if (shmem_should_replace_page(page, gfp)) {
+			error = shmem_replace_page(&page, gfp, info, index);
+			if (error)
+				goto failed;
 		}
 
 		error = mem_cgroup_cache_charge(page, current->mm,
@@ -991,19 +1176,36 @@ repeat:
 		inode->i_blocks += BLOCKS_PER_PAGE;
 		shmem_recalc_inode(inode);
 		spin_unlock(&info->lock);
+		alloced = true;
 
-		clear_highpage(page);
-		flush_dcache_page(page);
-		SetPageUptodate(page);
+		/*
+		 * Let SGP_FALLOC use the SGP_WRITE optimization on a new page.
+		 */
+		if (sgp == SGP_FALLOC)
+			sgp = SGP_WRITE;
+clear:
+		/*
+		 * Let SGP_WRITE caller clear ends if write does not fill page;
+		 * but SGP_FALLOC on a page fallocated earlier must initialize
+		 * it now, lest undo on failure cancel our earlier guarantee.
+		 */
+		if (sgp != SGP_WRITE) {
+			clear_highpage(page);
+			flush_dcache_page(page);
+			SetPageUptodate(page);
+		}
 		if (sgp == SGP_DIRTY)
 			set_page_dirty(page);
 	}
-done:
+
 	/* Perhaps the file has been truncated since we checked */
-	if (sgp != SGP_WRITE &&
+	if (sgp != SGP_WRITE && sgp != SGP_FALLOC &&
 	    ((loff_t)index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) {
 		error = -EINVAL;
-		goto trunc;
+		if (alloced)
+			goto trunc;
+		else
+			goto failed;
 	}
 	*pagep = page;
 	return 0;
@@ -1012,6 +1214,7 @@ done:
 	 * Error recovery.
 	 */
 trunc:
+	info = SHMEM_I(inode);
 	ClearPageDirty(page);
 	delete_from_page_cache(page);
 	spin_lock(&info->lock);
@@ -1019,6 +1222,7 @@ trunc:
 	inode->i_blocks -= BLOCKS_PER_PAGE;
 	spin_unlock(&info->lock);
 decused:
+	sbinfo = SHMEM_SB(inode->i_sb);
 	if (sbinfo->max_blocks)
 		percpu_counter_add(&sbinfo->used_blocks, -1);
 unacct:
@@ -1204,6 +1408,14 @@ shmem_write_end(struct file *file, struct address_space *mapping,
 	if (pos + copied > inode->i_size)
 		i_size_write(inode, pos + copied);
 
+	if (!PageUptodate(page)) {
+		if (copied < PAGE_CACHE_SIZE) {
+			unsigned from = pos & (PAGE_CACHE_SIZE - 1);
+			zero_user_segments(page, 0, from,
+					from + copied, PAGE_CACHE_SIZE);
+		}
+		SetPageUptodate(page);
+	}
 	set_page_dirty(page);
 	unlock_page(page);
 	page_cache_release(page);
@@ -1462,6 +1674,199 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
 	return error;
 }
 
+/*
+ * llseek SEEK_DATA or SEEK_HOLE through the radix_tree.
+ */
+static pgoff_t shmem_seek_hole_data(struct address_space *mapping,
+				    pgoff_t index, pgoff_t end, int origin)
+{
+	struct page *page;
+	struct pagevec pvec;
+	pgoff_t indices[PAGEVEC_SIZE];
+	bool done = false;
+	int i;
+
+	pagevec_init(&pvec, 0);
+	pvec.nr = 1;		/* start small: we may be there already */
+	while (!done) {
+		pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
+					pvec.nr, pvec.pages, indices);
+		if (!pvec.nr) {
+			if (origin == SEEK_DATA)
+				index = end;
+			break;
+		}
+		for (i = 0; i < pvec.nr; i++, index++) {
+			if (index < indices[i]) {
+				if (origin == SEEK_HOLE) {
+					done = true;
+					break;
+				}
+				index = indices[i];
+			}
+			page = pvec.pages[i];
+			if (page && !radix_tree_exceptional_entry(page)) {
+				if (!PageUptodate(page))
+					page = NULL;
+			}
+			if (index >= end ||
+			    (page && origin == SEEK_DATA) ||
+			    (!page && origin == SEEK_HOLE)) {
+				done = true;
+				break;
+			}
+		}
+		shmem_deswap_pagevec(&pvec);
+		pagevec_release(&pvec);
+		pvec.nr = PAGEVEC_SIZE;
+		cond_resched();
+	}
+	return index;
+}
+
+static loff_t shmem_file_llseek(struct file *file, loff_t offset, int origin)
+{
+	struct address_space *mapping;
+	struct inode *inode;
+	pgoff_t start, end;
+	loff_t new_offset;
+
+	if (origin != SEEK_DATA && origin != SEEK_HOLE)
+		return generic_file_llseek_size(file, offset, origin,
+							MAX_LFS_FILESIZE);
+	mapping = file->f_mapping;
+	inode = mapping->host;
+	mutex_lock(&inode->i_mutex);
+	/* We're holding i_mutex so we can access i_size directly */
+
+	if (offset < 0)
+		offset = -EINVAL;
+	else if (offset >= inode->i_size)
+		offset = -ENXIO;
+	else {
+		start = offset >> PAGE_CACHE_SHIFT;
+		end = (inode->i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+		new_offset = shmem_seek_hole_data(mapping, start, end, origin);
+		new_offset <<= PAGE_CACHE_SHIFT;
+		if (new_offset > offset) {
+			if (new_offset < inode->i_size)
+				offset = new_offset;
+			else if (origin == SEEK_DATA)
+				offset = -ENXIO;
+			else
+				offset = inode->i_size;
+		}
+	}
+
+	if (offset >= 0 && offset != file->f_pos) {
+		file->f_pos = offset;
+		file->f_version = 0;
+	}
+	mutex_unlock(&inode->i_mutex);
+	return offset;
+}
+
+static long shmem_fallocate(struct file *file, int mode, loff_t offset,
+							 loff_t len)
+{
+	struct inode *inode = file->f_path.dentry->d_inode;
+	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
+	struct shmem_falloc shmem_falloc;
+	pgoff_t start, index, end;
+	int error;
+
+	mutex_lock(&inode->i_mutex);
+
+	if (mode & FALLOC_FL_PUNCH_HOLE) {
+		struct address_space *mapping = file->f_mapping;
+		loff_t unmap_start = round_up(offset, PAGE_SIZE);
+		loff_t unmap_end = round_down(offset + len, PAGE_SIZE) - 1;
+
+		if ((u64)unmap_end > (u64)unmap_start)
+			unmap_mapping_range(mapping, unmap_start,
+					    1 + unmap_end - unmap_start, 0);
+		shmem_truncate_range(inode, offset, offset + len - 1);
+		/* No need to unmap again: hole-punching leaves COWed pages */
+		error = 0;
+		goto out;
+	}
+
+	/* We need to check rlimit even when FALLOC_FL_KEEP_SIZE */
+	error = inode_newsize_ok(inode, offset + len);
+	if (error)
+		goto out;
+
+	start = offset >> PAGE_CACHE_SHIFT;
+	end = (offset + len + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	/* Try to avoid a swapstorm if len is impossible to satisfy */
+	if (sbinfo->max_blocks && end - start > sbinfo->max_blocks) {
+		error = -ENOSPC;
+		goto out;
+	}
+
+	shmem_falloc.start = start;
+	shmem_falloc.next  = start;
+	shmem_falloc.nr_falloced = 0;
+	shmem_falloc.nr_unswapped = 0;
+	spin_lock(&inode->i_lock);
+	inode->i_private = &shmem_falloc;
+	spin_unlock(&inode->i_lock);
+
+	for (index = start; index < end; index++) {
+		struct page *page;
+
+		/*
+		 * Good, the fallocate(2) manpage permits EINTR: we may have
+		 * been interrupted because we are using up too much memory.
+		 */
+		if (signal_pending(current))
+			error = -EINTR;
+		else if (shmem_falloc.nr_unswapped > shmem_falloc.nr_falloced)
+			error = -ENOMEM;
+		else
+			error = shmem_getpage(inode, index, &page, SGP_FALLOC,
+									NULL);
+		if (error) {
+			/* Remove the !PageUptodate pages we added */
+			shmem_undo_range(inode,
+				(loff_t)start << PAGE_CACHE_SHIFT,
+				(loff_t)index << PAGE_CACHE_SHIFT, true);
+			goto undone;
+		}
+
+		/*
+		 * Inform shmem_writepage() how far we have reached.
+		 * No need for lock or barrier: we have the page lock.
+		 */
+		shmem_falloc.next++;
+		if (!PageUptodate(page))
+			shmem_falloc.nr_falloced++;
+
+		/*
+		 * If !PageUptodate, leave it that way so that freeable pages
+		 * can be recognized if we need to rollback on error later.
+		 * But set_page_dirty so that memory pressure will swap rather
+		 * than free the pages we are allocating (and SGP_CACHE pages
+		 * might still be clean: we now need to mark those dirty too).
+		 */
+		set_page_dirty(page);
+		unlock_page(page);
+		page_cache_release(page);
+		cond_resched();
+	}
+
+	if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size)
+		i_size_write(inode, offset + len);
+	inode->i_ctime = CURRENT_TIME;
+undone:
+	spin_lock(&inode->i_lock);
+	inode->i_private = NULL;
+	spin_unlock(&inode->i_lock);
+out:
+	mutex_unlock(&inode->i_mutex);
+	return error;
+}
+
 static int shmem_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct shmem_sb_info *sbinfo = SHMEM_SB(dentry->d_sb);
@@ -1665,6 +2070,7 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s
 		kaddr = kmap_atomic(page);
 		memcpy(kaddr, symname, len);
 		kunmap_atomic(kaddr);
+		SetPageUptodate(page);
 		set_page_dirty(page);
 		unlock_page(page);
 		page_cache_release(page);
@@ -2270,6 +2676,7 @@ int shmem_fill_super(struct super_block *sb, void *data, int silent)
 		}
 	}
 	sb->s_export_op = &shmem_export_ops;
+	sb->s_flags |= MS_NOSEC;
 #else
 	sb->s_flags |= MS_NOUSER;
 #endif
@@ -2364,7 +2771,7 @@ static const struct address_space_operations shmem_aops = {
 static const struct file_operations shmem_file_operations = {
 	.mmap		= shmem_mmap,
 #ifdef CONFIG_TMPFS
-	.llseek		= generic_file_llseek,
+	.llseek		= shmem_file_llseek,
 	.read		= do_sync_read,
 	.write		= do_sync_write,
 	.aio_read	= shmem_file_aio_read,
@@ -2372,12 +2779,12 @@ static const struct file_operations shmem_file_operations = {
 	.fsync		= noop_fsync,
 	.splice_read	= shmem_file_splice_read,
 	.splice_write	= generic_file_splice_write,
+	.fallocate	= shmem_fallocate,
 #endif
 };
 
 static const struct inode_operations shmem_inode_operations = {
 	.setattr	= shmem_setattr,
-	.truncate_range	= shmem_truncate_range,
 #ifdef CONFIG_TMPFS_XATTR
 	.setxattr	= shmem_setxattr,
 	.getxattr	= shmem_getxattr,
diff --git a/mm/sparse.c b/mm/sparse.c
index a8bc7d364deb..6a4bf9160e85 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -273,10 +273,10 @@ static unsigned long *__kmalloc_section_usemap(void)
 #ifdef CONFIG_MEMORY_HOTREMOVE
 static unsigned long * __init
 sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
-					 unsigned long count)
+					 unsigned long size)
 {
-	unsigned long section_nr;
-
+	pg_data_t *host_pgdat;
+	unsigned long goal;
 	/*
 	 * A page may contain usemaps for other sections preventing the
 	 * page being freed and making a section unremovable while
@@ -287,8 +287,10 @@ sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
 	 * from the same section as the pgdat where possible to avoid
 	 * this problem.
 	 */
-	section_nr = pfn_to_section_nr(__pa(pgdat) >> PAGE_SHIFT);
-	return alloc_bootmem_section(usemap_size() * count, section_nr);
+	goal = __pa(pgdat) & PAGE_SECTION_MASK;
+	host_pgdat = NODE_DATA(early_pfn_to_nid(goal >> PAGE_SHIFT));
+	return __alloc_bootmem_node_nopanic(host_pgdat, size,
+					    SMP_CACHE_BYTES, goal);
 }
 
 static void __init check_usemap_section_nr(int nid, unsigned long *usemap)
@@ -332,9 +334,9 @@ static void __init check_usemap_section_nr(int nid, unsigned long *usemap)
 #else
 static unsigned long * __init
 sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
-					 unsigned long count)
+					 unsigned long size)
 {
-	return NULL;
+	return alloc_bootmem_node_nopanic(pgdat, size);
 }
 
 static void __init check_usemap_section_nr(int nid, unsigned long *usemap)
@@ -352,13 +354,10 @@ static void __init sparse_early_usemaps_alloc_node(unsigned long**usemap_map,
 	int size = usemap_size();
 
 	usemap = sparse_early_usemaps_alloc_pgdat_section(NODE_DATA(nodeid),
-								 usemap_count);
+							  size * usemap_count);
 	if (!usemap) {
-		usemap = alloc_bootmem_node(NODE_DATA(nodeid), size * usemap_count);
-		if (!usemap) {
-			printk(KERN_WARNING "%s: allocation failed\n", __func__);
-			return;
-		}
+		printk(KERN_WARNING "%s: allocation failed\n", __func__);
+		return;
 	}
 
 	for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
diff --git a/mm/swap.c b/mm/swap.c
index 5c13f1338972..0503ad705e7c 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -82,6 +82,25 @@ static void put_compound_page(struct page *page)
 		if (likely(page != page_head &&
 			   get_page_unless_zero(page_head))) {
 			unsigned long flags;
+
+			/*
+			 * THP can not break up slab pages so avoid taking
+			 * compound_lock().  Slab performs non-atomic bit ops
+			 * on page->flags for better performance.  In particular
+			 * slab_unlock() in slub used to be a hot path.  It is
+			 * still hot on arches that do not support
+			 * this_cpu_cmpxchg_double().
+			 */
+			if (PageSlab(page_head)) {
+				if (PageTail(page)) {
+					if (put_page_testzero(page_head))
+						VM_BUG_ON(1);
+
+					atomic_dec(&page->_mapcount);
+					goto skip_lock_tail;
+				} else
+					goto skip_lock;
+			}
 			/*
 			 * page_head wasn't a dangling pointer but it
 			 * may not be a head page anymore by the time
@@ -92,10 +111,10 @@ static void put_compound_page(struct page *page)
 			if (unlikely(!PageTail(page))) {
 				/* __split_huge_page_refcount run before us */
 				compound_unlock_irqrestore(page_head, flags);
-				VM_BUG_ON(PageHead(page_head));
+skip_lock:
 				if (put_page_testzero(page_head))
 					__put_single_page(page_head);
-			out_put_single:
+out_put_single:
 				if (put_page_testzero(page))
 					__put_single_page(page);
 				return;
@@ -115,6 +134,8 @@ static void put_compound_page(struct page *page)
 			VM_BUG_ON(atomic_read(&page_head->_count) <= 0);
 			VM_BUG_ON(atomic_read(&page->_count) != 0);
 			compound_unlock_irqrestore(page_head, flags);
+
+skip_lock_tail:
 			if (put_page_testzero(page_head)) {
 				if (PageHead(page_head))
 					__put_compound_page(page_head);
@@ -162,6 +183,18 @@ bool __get_page_tail(struct page *page)
 	struct page *page_head = compound_trans_head(page);
 
 	if (likely(page != page_head && get_page_unless_zero(page_head))) {
+
+		/* Ref to put_compound_page() comment. */
+		if (PageSlab(page_head)) {
+			if (likely(PageTail(page))) {
+				__get_page_tail_foll(page, false);
+				return true;
+			} else {
+				put_page(page_head);
+				return false;
+			}
+		}
+
 		/*
 		 * page_head wasn't a dangling pointer but it
 		 * may not be a head page anymore by the time
@@ -279,21 +312,15 @@ void rotate_reclaimable_page(struct page *page)
 static void update_page_reclaim_stat(struct zone *zone, struct page *page,
 				     int file, int rotated)
 {
-	struct zone_reclaim_stat *reclaim_stat = &zone->reclaim_stat;
-	struct zone_reclaim_stat *memcg_reclaim_stat;
+	struct zone_reclaim_stat *reclaim_stat;
 
-	memcg_reclaim_stat = mem_cgroup_get_reclaim_stat_from_page(page);
+	reclaim_stat = mem_cgroup_get_reclaim_stat_from_page(page);
+	if (!reclaim_stat)
+		reclaim_stat = &zone->lruvec.reclaim_stat;
 
 	reclaim_stat->recent_scanned[file]++;
 	if (rotated)
 		reclaim_stat->recent_rotated[file]++;
-
-	if (!memcg_reclaim_stat)
-		return;
-
-	memcg_reclaim_stat->recent_scanned[file]++;
-	if (rotated)
-		memcg_reclaim_stat->recent_rotated[file]++;
 }
 
 static void __activate_page(struct page *page, void *arg)
diff --git a/mm/swapfile.c b/mm/swapfile.c
index fafc26d1b1dc..457b10baef59 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -601,7 +601,7 @@ void swapcache_free(swp_entry_t entry, struct page *page)
  * This does not give an exact answer when swap count is continued,
  * but does include the high COUNT_CONTINUED flag to allow for that.
  */
-static inline int page_swapcount(struct page *page)
+int page_swapcount(struct page *page)
 {
 	int count = 0;
 	struct swap_info_struct *p;
@@ -717,37 +717,6 @@ int free_swap_and_cache(swp_entry_t entry)
 	return p != NULL;
 }
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
-/**
- * mem_cgroup_count_swap_user - count the user of a swap entry
- * @ent: the swap entry to be checked
- * @pagep: the pointer for the swap cache page of the entry to be stored
- *
- * Returns the number of the user of the swap entry. The number is valid only
- * for swaps of anonymous pages.
- * If the entry is found on swap cache, the page is stored to pagep with
- * refcount of it being incremented.
- */
-int mem_cgroup_count_swap_user(swp_entry_t ent, struct page **pagep)
-{
-	struct page *page;
-	struct swap_info_struct *p;
-	int count = 0;
-
-	page = find_get_page(&swapper_space, ent.val);
-	if (page)
-		count += page_mapcount(page);
-	p = swap_info_get(ent);
-	if (p) {
-		count += swap_count(p->swap_map[swp_offset(ent)]);
-		spin_unlock(&swap_lock);
-	}
-
-	*pagep = page;
-	return count;
-}
-#endif
-
 #ifdef CONFIG_HIBERNATION
 /*
  * Find the swap type that corresponds to given device (if any).
diff --git a/mm/thrash.c b/mm/thrash.c
deleted file mode 100644
index 57ad495dbd54..000000000000
--- a/mm/thrash.c
+++ /dev/null
@@ -1,155 +0,0 @@
-/*
- * mm/thrash.c
- *
- * Copyright (C) 2004, Red Hat, Inc.
- * Copyright (C) 2004, Rik van Riel <riel@redhat.com>
- * Released under the GPL, see the file COPYING for details.
- *
- * Simple token based thrashing protection, using the algorithm
- * described in: http://www.cse.ohio-state.edu/hpcs/WWW/HTML/publications/abs05-1.html
- *
- * Sep 2006, Ashwin Chaugule <ashwin.chaugule@celunite.com>
- * Improved algorithm to pass token:
- * Each task has a priority which is incremented if it contended
- * for the token in an interval less than its previous attempt.
- * If the token is acquired, that task's priority is boosted to prevent
- * the token from bouncing around too often and to let the task make
- * some progress in its execution.
- */
-
-#include <linux/jiffies.h>
-#include <linux/mm.h>
-#include <linux/sched.h>
-#include <linux/swap.h>
-#include <linux/memcontrol.h>
-
-#include <trace/events/vmscan.h>
-
-#define TOKEN_AGING_INTERVAL	(0xFF)
-
-static DEFINE_SPINLOCK(swap_token_lock);
-struct mm_struct *swap_token_mm;
-static struct mem_cgroup *swap_token_memcg;
-
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
-static struct mem_cgroup *swap_token_memcg_from_mm(struct mm_struct *mm)
-{
-	struct mem_cgroup *memcg;
-
-	memcg = try_get_mem_cgroup_from_mm(mm);
-	if (memcg)
-		css_put(mem_cgroup_css(memcg));
-
-	return memcg;
-}
-#else
-static struct mem_cgroup *swap_token_memcg_from_mm(struct mm_struct *mm)
-{
-	return NULL;
-}
-#endif
-
-void grab_swap_token(struct mm_struct *mm)
-{
-	int current_interval;
-	unsigned int old_prio = mm->token_priority;
-	static unsigned int global_faults;
-	static unsigned int last_aging;
-
-	global_faults++;
-
-	current_interval = global_faults - mm->faultstamp;
-
-	if (!spin_trylock(&swap_token_lock))
-		return;
-
-	/* First come first served */
-	if (!swap_token_mm)
-		goto replace_token;
-
-	/*
-	 * Usually, we don't need priority aging because long interval faults
-	 * makes priority decrease quickly. But there is one exception. If the
-	 * token owner task is sleeping, it never make long interval faults.
-	 * Thus, we need a priority aging mechanism instead. The requirements
-	 * of priority aging are
-	 *  1) An aging interval is reasonable enough long. Too short aging
-	 *     interval makes quick swap token lost and decrease performance.
-	 *  2) The swap token owner task have to get priority aging even if
-	 *     it's under sleep.
-	 */
-	if ((global_faults - last_aging) > TOKEN_AGING_INTERVAL) {
-		swap_token_mm->token_priority /= 2;
-		last_aging = global_faults;
-	}
-
-	if (mm == swap_token_mm) {
-		mm->token_priority += 2;
-		goto update_priority;
-	}
-
-	if (current_interval < mm->last_interval)
-		mm->token_priority++;
-	else {
-		if (likely(mm->token_priority > 0))
-			mm->token_priority--;
-	}
-
-	/* Check if we deserve the token */
-	if (mm->token_priority > swap_token_mm->token_priority)
-		goto replace_token;
-
-update_priority:
-	trace_update_swap_token_priority(mm, old_prio, swap_token_mm);
-
-out:
-	mm->faultstamp = global_faults;
-	mm->last_interval = current_interval;
-	spin_unlock(&swap_token_lock);
-	return;
-
-replace_token:
-	mm->token_priority += 2;
-	trace_replace_swap_token(swap_token_mm, mm);
-	swap_token_mm = mm;
-	swap_token_memcg = swap_token_memcg_from_mm(mm);
-	last_aging = global_faults;
-	goto out;
-}
-
-/* Called on process exit. */
-void __put_swap_token(struct mm_struct *mm)
-{
-	spin_lock(&swap_token_lock);
-	if (likely(mm == swap_token_mm)) {
-		trace_put_swap_token(swap_token_mm);
-		swap_token_mm = NULL;
-		swap_token_memcg = NULL;
-	}
-	spin_unlock(&swap_token_lock);
-}
-
-static bool match_memcg(struct mem_cgroup *a, struct mem_cgroup *b)
-{
-	if (!a)
-		return true;
-	if (!b)
-		return true;
-	if (a == b)
-		return true;
-	return false;
-}
-
-void disable_swap_token(struct mem_cgroup *memcg)
-{
-	/* memcg reclaim don't disable unrelated mm token. */
-	if (match_memcg(memcg, swap_token_memcg)) {
-		spin_lock(&swap_token_lock);
-		if (match_memcg(memcg, swap_token_memcg)) {
-			trace_disable_swap_token(swap_token_mm);
-			swap_token_mm = NULL;
-			swap_token_memcg = NULL;
-		}
-		spin_unlock(&swap_token_lock);
-	}
-}
diff --git a/mm/truncate.c b/mm/truncate.c
index 61a183b89df6..75801acdaac7 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -602,31 +602,6 @@ int vmtruncate(struct inode *inode, loff_t newsize)
 }
 EXPORT_SYMBOL(vmtruncate);
 
-int vmtruncate_range(struct inode *inode, loff_t lstart, loff_t lend)
-{
-	struct address_space *mapping = inode->i_mapping;
-	loff_t holebegin = round_up(lstart, PAGE_SIZE);
-	loff_t holelen = 1 + lend - holebegin;
-
-	/*
-	 * If the underlying filesystem is not going to provide
-	 * a way to truncate a range of blocks (punch a hole) -
-	 * we should return failure right now.
-	 */
-	if (!inode->i_op->truncate_range)
-		return -ENOSYS;
-
-	mutex_lock(&inode->i_mutex);
-	inode_dio_wait(inode);
-	unmap_mapping_range(mapping, holebegin, holelen, 1);
-	inode->i_op->truncate_range(inode, lstart, lend);
-	/* unmap again to remove racily COWed private pages */
-	unmap_mapping_range(mapping, holebegin, holelen, 1);
-	mutex_unlock(&inode->i_mutex);
-
-	return 0;
-}
-
 /**
  * truncate_pagecache_range - unmap and remove pagecache that is hole-punched
  * @inode: inode
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 94dff883b449..2aad49981b57 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1185,9 +1185,10 @@ void __init vmalloc_init(void)
 	/* Import existing vmlist entries. */
 	for (tmp = vmlist; tmp; tmp = tmp->next) {
 		va = kzalloc(sizeof(struct vmap_area), GFP_NOWAIT);
-		va->flags = tmp->flags | VM_VM_AREA;
+		va->flags = VM_VM_AREA;
 		va->va_start = (unsigned long)tmp->addr;
 		va->va_end = va->va_start + tmp->size;
+		va->vm = tmp;
 		__insert_vmap_area(va);
 	}
 
@@ -2375,8 +2376,8 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets,
 		return NULL;
 	}
 
-	vms = kzalloc(sizeof(vms[0]) * nr_vms, GFP_KERNEL);
-	vas = kzalloc(sizeof(vas[0]) * nr_vms, GFP_KERNEL);
+	vms = kcalloc(nr_vms, sizeof(vms[0]), GFP_KERNEL);
+	vas = kcalloc(nr_vms, sizeof(vas[0]), GFP_KERNEL);
 	if (!vas || !vms)
 		goto err_free2;
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 3d1365c17868..8deb5f4da4d9 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -53,24 +53,6 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/vmscan.h>
 
-/*
- * reclaim_mode determines how the inactive list is shrunk
- * RECLAIM_MODE_SINGLE: Reclaim only order-0 pages
- * RECLAIM_MODE_ASYNC:  Do not block
- * RECLAIM_MODE_SYNC:   Allow blocking e.g. call wait_on_page_writeback
- * RECLAIM_MODE_LUMPYRECLAIM: For high-order allocations, take a reference
- *			page from the LRU and reclaim all pages within a
- *			naturally aligned range
- * RECLAIM_MODE_COMPACTION: For high-order allocations, reclaim a number of
- *			order-0 pages and then compact the zone
- */
-typedef unsigned __bitwise__ reclaim_mode_t;
-#define RECLAIM_MODE_SINGLE		((__force reclaim_mode_t)0x01u)
-#define RECLAIM_MODE_ASYNC		((__force reclaim_mode_t)0x02u)
-#define RECLAIM_MODE_SYNC		((__force reclaim_mode_t)0x04u)
-#define RECLAIM_MODE_LUMPYRECLAIM	((__force reclaim_mode_t)0x08u)
-#define RECLAIM_MODE_COMPACTION		((__force reclaim_mode_t)0x10u)
-
 struct scan_control {
 	/* Incremented by the number of inactive pages that were scanned */
 	unsigned long nr_scanned;
@@ -97,12 +79,6 @@ struct scan_control {
 	int order;
 
 	/*
-	 * Intend to reclaim enough continuous memory rather than reclaim
-	 * enough amount of memory. i.e, mode for high order allocation.
-	 */
-	reclaim_mode_t reclaim_mode;
-
-	/*
 	 * The memory cgroup that hit its limit and as a result is the
 	 * primary target of this reclaim invocation.
 	 */
@@ -164,35 +140,22 @@ static bool global_reclaim(struct scan_control *sc)
 {
 	return !sc->target_mem_cgroup;
 }
-
-static bool scanning_global_lru(struct mem_cgroup_zone *mz)
-{
-	return !mz->mem_cgroup;
-}
 #else
 static bool global_reclaim(struct scan_control *sc)
 {
 	return true;
 }
-
-static bool scanning_global_lru(struct mem_cgroup_zone *mz)
-{
-	return true;
-}
 #endif
 
 static struct zone_reclaim_stat *get_reclaim_stat(struct mem_cgroup_zone *mz)
 {
-	if (!scanning_global_lru(mz))
-		return mem_cgroup_get_reclaim_stat(mz->mem_cgroup, mz->zone);
-
-	return &mz->zone->reclaim_stat;
+	return &mem_cgroup_zone_lruvec(mz->zone, mz->mem_cgroup)->reclaim_stat;
 }
 
 static unsigned long zone_nr_lru_pages(struct mem_cgroup_zone *mz,
 				       enum lru_list lru)
 {
-	if (!scanning_global_lru(mz))
+	if (!mem_cgroup_disabled())
 		return mem_cgroup_zone_nr_lru_pages(mz->mem_cgroup,
 						    zone_to_nid(mz->zone),
 						    zone_idx(mz->zone),
@@ -364,39 +327,6 @@ out:
 	return ret;
 }
 
-static void set_reclaim_mode(int priority, struct scan_control *sc,
-				   bool sync)
-{
-	reclaim_mode_t syncmode = sync ? RECLAIM_MODE_SYNC : RECLAIM_MODE_ASYNC;
-
-	/*
-	 * Initially assume we are entering either lumpy reclaim or
-	 * reclaim/compaction.Depending on the order, we will either set the
-	 * sync mode or just reclaim order-0 pages later.
-	 */
-	if (COMPACTION_BUILD)
-		sc->reclaim_mode = RECLAIM_MODE_COMPACTION;
-	else
-		sc->reclaim_mode = RECLAIM_MODE_LUMPYRECLAIM;
-
-	/*
-	 * Avoid using lumpy reclaim or reclaim/compaction if possible by
-	 * restricting when its set to either costly allocations or when
-	 * under memory pressure
-	 */
-	if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
-		sc->reclaim_mode |= syncmode;
-	else if (sc->order && priority < DEF_PRIORITY - 2)
-		sc->reclaim_mode |= syncmode;
-	else
-		sc->reclaim_mode = RECLAIM_MODE_SINGLE | RECLAIM_MODE_ASYNC;
-}
-
-static void reset_reclaim_mode(struct scan_control *sc)
-{
-	sc->reclaim_mode = RECLAIM_MODE_SINGLE | RECLAIM_MODE_ASYNC;
-}
-
 static inline int is_page_cache_freeable(struct page *page)
 {
 	/*
@@ -416,10 +346,6 @@ static int may_write_to_queue(struct backing_dev_info *bdi,
 		return 1;
 	if (bdi == current->backing_dev_info)
 		return 1;
-
-	/* lumpy reclaim for hugepage often need a lot of write */
-	if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
-		return 1;
 	return 0;
 }
 
@@ -523,8 +449,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping,
 			/* synchronous write or broken a_ops? */
 			ClearPageReclaim(page);
 		}
-		trace_mm_vmscan_writepage(page,
-			trace_reclaim_flags(page, sc->reclaim_mode));
+		trace_mm_vmscan_writepage(page, trace_reclaim_flags(page));
 		inc_zone_page_state(page, NR_VMSCAN_WRITE);
 		return PAGE_SUCCESS;
 	}
@@ -707,13 +632,10 @@ static enum page_references page_check_references(struct page *page,
 	int referenced_ptes, referenced_page;
 	unsigned long vm_flags;
 
-	referenced_ptes = page_referenced(page, 1, mz->mem_cgroup, &vm_flags);
+	referenced_ptes = page_referenced(page, 1, sc->target_mem_cgroup,
+					  &vm_flags);
 	referenced_page = TestClearPageReferenced(page);
 
-	/* Lumpy reclaim - ignore references */
-	if (sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM)
-		return PAGEREF_RECLAIM;
-
 	/*
 	 * Mlock lost the isolation race with us.  Let try_to_unmap()
 	 * move the page to the unevictable list.
@@ -722,7 +644,7 @@ static enum page_references page_check_references(struct page *page,
 		return PAGEREF_RECLAIM;
 
 	if (referenced_ptes) {
-		if (PageAnon(page))
+		if (PageSwapBacked(page))
 			return PAGEREF_ACTIVATE;
 		/*
 		 * All mapped pages start out with page table
@@ -813,19 +735,8 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 
 		if (PageWriteback(page)) {
 			nr_writeback++;
-			/*
-			 * Synchronous reclaim cannot queue pages for
-			 * writeback due to the possibility of stack overflow
-			 * but if it encounters a page under writeback, wait
-			 * for the IO to complete.
-			 */
-			if ((sc->reclaim_mode & RECLAIM_MODE_SYNC) &&
-			    may_enter_fs)
-				wait_on_page_writeback(page);
-			else {
-				unlock_page(page);
-				goto keep_lumpy;
-			}
+			unlock_page(page);
+			goto keep;
 		}
 
 		references = page_check_references(page, mz, sc);
@@ -908,7 +819,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 				goto activate_locked;
 			case PAGE_SUCCESS:
 				if (PageWriteback(page))
-					goto keep_lumpy;
+					goto keep;
 				if (PageDirty(page))
 					goto keep;
 
@@ -994,7 +905,6 @@ cull_mlocked:
 			try_to_free_swap(page);
 		unlock_page(page);
 		putback_lru_page(page);
-		reset_reclaim_mode(sc);
 		continue;
 
 activate_locked:
@@ -1007,8 +917,6 @@ activate_locked:
 keep_locked:
 		unlock_page(page);
 keep:
-		reset_reclaim_mode(sc);
-keep_lumpy:
 		list_add(&page->lru, &ret_pages);
 		VM_BUG_ON(PageLRU(page) || PageUnevictable(page));
 	}
@@ -1064,11 +972,7 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode, int file)
 	if (!all_lru_mode && !!page_is_file_cache(page) != file)
 		return ret;
 
-	/*
-	 * When this function is being called for lumpy reclaim, we
-	 * initially look into all LRU pages, active, inactive and
-	 * unevictable; only give shrink_page_list evictable pages.
-	 */
+	/* Do not give back unevictable pages for compaction */
 	if (PageUnevictable(page))
 		return ret;
 
@@ -1153,9 +1057,6 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 	struct lruvec *lruvec;
 	struct list_head *src;
 	unsigned long nr_taken = 0;
-	unsigned long nr_lumpy_taken = 0;
-	unsigned long nr_lumpy_dirty = 0;
-	unsigned long nr_lumpy_failed = 0;
 	unsigned long scan;
 	int lru = LRU_BASE;
 
@@ -1168,10 +1069,6 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 
 	for (scan = 0; scan < nr_to_scan && !list_empty(src); scan++) {
 		struct page *page;
-		unsigned long pfn;
-		unsigned long end_pfn;
-		unsigned long page_pfn;
-		int zone_id;
 
 		page = lru_to_page(src);
 		prefetchw_prev_lru_page(page, src, flags);
@@ -1193,84 +1090,6 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		default:
 			BUG();
 		}
-
-		if (!sc->order || !(sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM))
-			continue;
-
-		/*
-		 * Attempt to take all pages in the order aligned region
-		 * surrounding the tag page.  Only take those pages of
-		 * the same active state as that tag page.  We may safely
-		 * round the target page pfn down to the requested order
-		 * as the mem_map is guaranteed valid out to MAX_ORDER,
-		 * where that page is in a different zone we will detect
-		 * it from its zone id and abort this block scan.
-		 */
-		zone_id = page_zone_id(page);
-		page_pfn = page_to_pfn(page);
-		pfn = page_pfn & ~((1 << sc->order) - 1);
-		end_pfn = pfn + (1 << sc->order);
-		for (; pfn < end_pfn; pfn++) {
-			struct page *cursor_page;
-
-			/* The target page is in the block, ignore it. */
-			if (unlikely(pfn == page_pfn))
-				continue;
-
-			/* Avoid holes within the zone. */
-			if (unlikely(!pfn_valid_within(pfn)))
-				break;
-
-			cursor_page = pfn_to_page(pfn);
-
-			/* Check that we have not crossed a zone boundary. */
-			if (unlikely(page_zone_id(cursor_page) != zone_id))
-				break;
-
-			/*
-			 * If we don't have enough swap space, reclaiming of
-			 * anon page which don't already have a swap slot is
-			 * pointless.
-			 */
-			if (nr_swap_pages <= 0 && PageSwapBacked(cursor_page) &&
-			    !PageSwapCache(cursor_page))
-				break;
-
-			if (__isolate_lru_page(cursor_page, mode, file) == 0) {
-				unsigned int isolated_pages;
-
-				mem_cgroup_lru_del(cursor_page);
-				list_move(&cursor_page->lru, dst);
-				isolated_pages = hpage_nr_pages(cursor_page);
-				nr_taken += isolated_pages;
-				nr_lumpy_taken += isolated_pages;
-				if (PageDirty(cursor_page))
-					nr_lumpy_dirty += isolated_pages;
-				scan++;
-				pfn += isolated_pages - 1;
-			} else {
-				/*
-				 * Check if the page is freed already.
-				 *
-				 * We can't use page_count() as that
-				 * requires compound_head and we don't
-				 * have a pin on the page here. If a
-				 * page is tail, we may or may not
-				 * have isolated the head, so assume
-				 * it's not free, it'd be tricky to
-				 * track the head status without a
-				 * page pin.
-				 */
-				if (!PageTail(cursor_page) &&
-				    !atomic_read(&cursor_page->_count))
-					continue;
-				break;
-			}
-		}
-
-		/* If we break out of the loop above, lumpy reclaim failed */
-		if (pfn < end_pfn)
-			nr_lumpy_failed++;
 	}
 
 	*nr_scanned = scan;
@@ -1278,7 +1097,6 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 	trace_mm_vmscan_lru_isolate(sc->order,
 			nr_to_scan, scan,
 			nr_taken,
-			nr_lumpy_taken, nr_lumpy_dirty, nr_lumpy_failed,
 			mode, file);
 	return nr_taken;
 }
@@ -1454,47 +1272,6 @@ update_isolated_counts(struct mem_cgroup_zone *mz,
 }
 
 /*
- * Returns true if a direct reclaim should wait on pages under writeback.
- *
- * If we are direct reclaiming for contiguous pages and we do not reclaim
- * everything in the list, try again and wait for writeback IO to complete.
- * This will stall high-order allocations noticeably. Only do that when really
- * need to free the pages under high memory pressure.
- */
-static inline bool should_reclaim_stall(unsigned long nr_taken,
-					unsigned long nr_freed,
-					int priority,
-					struct scan_control *sc)
-{
-	int lumpy_stall_priority;
-
-	/* kswapd should not stall on sync IO */
-	if (current_is_kswapd())
-		return false;
-
-	/* Only stall on lumpy reclaim */
-	if (sc->reclaim_mode & RECLAIM_MODE_SINGLE)
-		return false;
-
-	/* If we have reclaimed everything on the isolated list, no stall */
-	if (nr_freed == nr_taken)
-		return false;
-
-	/*
-	 * For high-order allocations, there are two stall thresholds.
-	 * High-cost allocations stall immediately where as lower
-	 * order allocations such as stacks require the scanning
-	 * priority to be much higher before stalling.
-	 */
-	if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
-		lumpy_stall_priority = DEF_PRIORITY;
-	else
-		lumpy_stall_priority = DEF_PRIORITY / 3;
-
-	return priority <= lumpy_stall_priority;
-}
-
-/*
  * shrink_inactive_list() is a helper for shrink_zone().  It returns the number
  * of reclaimed pages
  */
@@ -1522,10 +1299,6 @@ shrink_inactive_list(unsigned long nr_to_scan, struct mem_cgroup_zone *mz,
 			return SWAP_CLUSTER_MAX;
 	}
 
-	set_reclaim_mode(priority, sc, false);
-	if (sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM)
-		isolate_mode |= ISOLATE_ACTIVE;
-
 	lru_add_drain();
 
 	if (!sc->may_unmap)
@@ -1556,13 +1329,6 @@ shrink_inactive_list(unsigned long nr_to_scan, struct mem_cgroup_zone *mz,
 	nr_reclaimed = shrink_page_list(&page_list, mz, sc, priority,
 						&nr_dirty, &nr_writeback);
 
-	/* Check if we should syncronously wait for writeback */
-	if (should_reclaim_stall(nr_taken, nr_reclaimed, priority, sc)) {
-		set_reclaim_mode(priority, sc, true);
-		nr_reclaimed += shrink_page_list(&page_list, mz, sc,
-					priority, &nr_dirty, &nr_writeback);
-	}
-
 	spin_lock_irq(&zone->lru_lock);
 
 	reclaim_stat->recent_scanned[0] += nr_anon;
@@ -1616,7 +1382,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct mem_cgroup_zone *mz,
 		zone_idx(zone),
 		nr_scanned, nr_reclaimed,
 		priority,
-		trace_shrink_flags(file, sc->reclaim_mode));
+		trace_shrink_flags(file));
 	return nr_reclaimed;
 }
 
@@ -1695,8 +1461,6 @@ static void shrink_active_list(unsigned long nr_to_scan,
 
 	lru_add_drain();
 
-	reset_reclaim_mode(sc);
-
 	if (!sc->may_unmap)
 		isolate_mode |= ISOLATE_UNMAPPED;
 	if (!sc->may_writepage)
@@ -1737,7 +1501,8 @@ static void shrink_active_list(unsigned long nr_to_scan,
 			}
 		}
 
-		if (page_referenced(page, 0, mz->mem_cgroup, &vm_flags)) {
+		if (page_referenced(page, 0, sc->target_mem_cgroup,
+				    &vm_flags)) {
 			nr_rotated += hpage_nr_pages(page);
 			/*
 			 * Identify referenced, file-backed active pages and
@@ -1811,7 +1576,7 @@ static int inactive_anon_is_low(struct mem_cgroup_zone *mz)
 	if (!total_swap_pages)
 		return 0;
 
-	if (!scanning_global_lru(mz))
+	if (!mem_cgroup_disabled())
 		return mem_cgroup_inactive_anon_is_low(mz->mem_cgroup,
 						       mz->zone);
 
@@ -1850,7 +1615,7 @@ static int inactive_file_is_low_global(struct zone *zone)
  */
 static int inactive_file_is_low(struct mem_cgroup_zone *mz)
 {
-	if (!scanning_global_lru(mz))
+	if (!mem_cgroup_disabled())
 		return mem_cgroup_inactive_file_is_low(mz->mem_cgroup,
 						       mz->zone);
 
@@ -1984,10 +1749,10 @@ static void get_scan_count(struct mem_cgroup_zone *mz, struct scan_control *sc,
 	 * proportional to the fraction of recently scanned pages on
 	 * each list that were recently referenced and in active use.
 	 */
-	ap = (anon_prio + 1) * (reclaim_stat->recent_scanned[0] + 1);
+	ap = anon_prio * (reclaim_stat->recent_scanned[0] + 1);
 	ap /= reclaim_stat->recent_rotated[0] + 1;
 
-	fp = (file_prio + 1) * (reclaim_stat->recent_scanned[1] + 1);
+	fp = file_prio * (reclaim_stat->recent_scanned[1] + 1);
 	fp /= reclaim_stat->recent_rotated[1] + 1;
 	spin_unlock_irq(&mz->zone->lru_lock);
 
@@ -2000,7 +1765,7 @@ out:
 		unsigned long scan;
 
 		scan = zone_nr_lru_pages(mz, lru);
-		if (priority || noswap) {
+		if (priority || noswap || !vmscan_swappiness(mz, sc)) {
 			scan >>= priority;
 			if (!scan && force_scan)
 				scan = SWAP_CLUSTER_MAX;
@@ -2010,23 +1775,35 @@ out:
 	}
 }
 
+/* Use reclaim/compaction for costly allocs or under memory pressure */
+static bool in_reclaim_compaction(int priority, struct scan_control *sc)
+{
+	if (COMPACTION_BUILD && sc->order &&
+			(sc->order > PAGE_ALLOC_COSTLY_ORDER ||
+			 priority < DEF_PRIORITY - 2))
+		return true;
+
+	return false;
+}
+
 /*
- * Reclaim/compaction depends on a number of pages being freed. To avoid
- * disruption to the system, a small number of order-0 pages continue to be
- * rotated and reclaimed in the normal fashion. However, by the time we get
- * back to the allocator and call try_to_compact_zone(), we ensure that
- * there are enough free pages for it to be likely successful
+ * Reclaim/compaction is used for high-order allocation requests. It reclaims
+ * order-0 pages before compacting the zone. should_continue_reclaim() returns
+ * true if more pages should be reclaimed such that when the page allocator
+ * calls try_to_compact_zone() that it will have enough free pages to succeed.
+ * It will give up earlier than that if there is difficulty reclaiming pages.
  */
 static inline bool should_continue_reclaim(struct mem_cgroup_zone *mz,
 					unsigned long nr_reclaimed,
 					unsigned long nr_scanned,
+					int priority,
 					struct scan_control *sc)
 {
 	unsigned long pages_for_compaction;
 	unsigned long inactive_lru_pages;
 
 	/* If not in reclaim/compaction mode, stop */
-	if (!(sc->reclaim_mode & RECLAIM_MODE_COMPACTION))
+	if (!in_reclaim_compaction(priority, sc))
 		return false;
 
 	/* Consider stopping depending on scan and reclaim activity */
@@ -2128,7 +1905,8 @@ restart:
 
 	/* reclaim/compaction might need reclaim to continue */
 	if (should_continue_reclaim(mz, nr_reclaimed,
-					sc->nr_scanned - nr_scanned, sc))
+					sc->nr_scanned - nr_scanned,
+					priority, sc))
 		goto restart;
 
 	throttle_vm_writeout(sc->gfp_mask);
@@ -2353,8 +2131,6 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 
 	for (priority = DEF_PRIORITY; priority >= 0; priority--) {
 		sc->nr_scanned = 0;
-		if (!priority)
-			disable_swap_token(sc->target_mem_cgroup);
 		aborted_reclaim = shrink_zones(priority, zonelist, sc);
 
 		/*
@@ -2705,10 +2481,6 @@ loop_again:
 		unsigned long lru_pages = 0;
 		int has_under_min_watermark_zone = 0;
 
-		/* The swap token gets in the way of swapout... */
-		if (!priority)
-			disable_swap_token(NULL);
-
 		all_zones_ok = 1;
 		balanced = 0;
 
@@ -3537,7 +3309,7 @@ int page_evictable(struct page *page, struct vm_area_struct *vma)
 	if (mapping_unevictable(page_mapping(page)))
 		return 0;
 
-	if (PageMlocked(page) || (vma && is_mlocked_vma(vma, page)))
+	if (PageMlocked(page) || (vma && mlocked_vma_newpage(vma, page)))
 		return 0;
 
 	return 1;
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 0dad31dc1618..1bbbbd9776ad 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1223,7 +1223,6 @@ module_init(setup_vmstat)
 #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_COMPACTION)
 #include <linux/debugfs.h>
 
-static struct dentry *extfrag_debug_root;
 
 /*
  * Return an index indicating how much of the available free memory is
@@ -1361,19 +1360,24 @@ static const struct file_operations extfrag_file_ops = {
 
 static int __init extfrag_debug_init(void)
 {
+	struct dentry *extfrag_debug_root;
+
 	extfrag_debug_root = debugfs_create_dir("extfrag", NULL);
 	if (!extfrag_debug_root)
 		return -ENOMEM;
 
 	if (!debugfs_create_file("unusable_index", 0444,
 			extfrag_debug_root, NULL, &unusable_file_ops))
-		return -ENOMEM;
+		goto fail;
 
 	if (!debugfs_create_file("extfrag_index", 0444,
 			extfrag_debug_root, NULL, &extfrag_file_ops))
-		return -ENOMEM;
+		goto fail;
 
 	return 0;
+fail:
+	debugfs_remove_recursive(extfrag_debug_root);
+	return -ENOMEM;
 }
 
 module_init(extfrag_debug_init);
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 7fee13b331d1..f56f045778ae 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1286,6 +1286,8 @@ call_reserveresult(struct rpc_task *task)
 	}
 
 	switch (status) {
+	case -ENOMEM:
+		rpc_delay(task, HZ >> 2);
 	case -EAGAIN:	/* woken up; retry */
 		task->tk_action = call_reserve;
 		return;
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index fd2423991c2d..04040476082e 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -120,7 +120,7 @@ EXPORT_SYMBOL_GPL(rpc_pipe_generic_upcall);
 
 /**
  * rpc_queue_upcall - queue an upcall message to userspace
- * @inode: inode of upcall pipe on which to queue given message
+ * @pipe: upcall pipe on which to queue given message
  * @msg: message to queue
  *
  * Call with an @inode created by rpc_mkpipe() to queue an upcall.
@@ -819,9 +819,7 @@ static int rpc_rmdir_depopulate(struct dentry *dentry,
  * @parent: dentry of directory to create new "pipe" in
  * @name: name of pipe
  * @private: private data to associate with the pipe, for the caller's use
- * @ops: operations defining the behavior of the pipe: upcall, downcall,
- *	release_pipe, open_pipe, and destroy_msg.
- * @flags: rpc_pipe flags
+ * @pipe: &rpc_pipe containing input parameters
  *
  * Data is made available for userspace to read by calls to
  * rpc_queue_upcall().  The actual reads will result in calls to
@@ -943,7 +941,7 @@ struct dentry *rpc_create_client_dir(struct dentry *dentry,
 
 /**
  * rpc_remove_client_dir - Remove a directory created with rpc_create_client_dir()
- * @clnt: rpc client
+ * @dentry: dentry for the pipe
  */
 int rpc_remove_client_dir(struct dentry *dentry)
 {
@@ -1115,7 +1113,7 @@ rpc_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_op = &s_ops;
 	sb->s_time_gran = 1;
 
-	inode = rpc_get_inode(sb, S_IFDIR | 0755);
+	inode = rpc_get_inode(sb, S_IFDIR | S_IRUGO | S_IXUGO);
 	sb->s_root = root = d_make_root(inode);
 	if (!root)
 		return -ENOMEM;
diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c
index 78ac39fd9fe7..3c0653439f3d 100644
--- a/net/sunrpc/rpcb_clnt.c
+++ b/net/sunrpc/rpcb_clnt.c
@@ -394,6 +394,7 @@ static int rpcb_register_call(struct rpc_clnt *clnt, struct rpc_message *msg)
 
 /**
  * rpcb_register - set or unset a port registration with the local rpcbind svc
+ * @net: target network namespace
  * @prog: RPC program number to bind
  * @vers: RPC version number to bind
  * @prot: transport protocol to register
@@ -521,6 +522,7 @@ static int rpcb_unregister_all_protofamilies(struct sunrpc_net *sn,
 
 /**
  * rpcb_v4_register - set or unset a port registration with the local rpcbind
+ * @net: target network namespace
  * @program: RPC program number of service to (un)register
  * @version: RPC version number of service to (un)register
  * @address: address family, IP address, and port to (un)register
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 6fe2dcead150..3c83035cdaa9 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -979,20 +979,21 @@ static void xprt_alloc_slot(struct rpc_task *task)
 		list_del(&req->rq_list);
 		goto out_init_req;
 	}
-	req = xprt_dynamic_alloc_slot(xprt, GFP_NOWAIT);
+	req = xprt_dynamic_alloc_slot(xprt, GFP_NOWAIT|__GFP_NOWARN);
 	if (!IS_ERR(req))
 		goto out_init_req;
 	switch (PTR_ERR(req)) {
 	case -ENOMEM:
-		rpc_delay(task, HZ >> 2);
 		dprintk("RPC:       dynamic allocation of request slot "
 				"failed! Retrying\n");
+		task->tk_status = -ENOMEM;
 		break;
 	case -EAGAIN:
 		rpc_sleep_on(&xprt->backlog, task, NULL);
 		dprintk("RPC:       waiting for request slot\n");
+	default:
+		task->tk_status = -EAGAIN;
 	}
-	task->tk_status = -EAGAIN;
 	return;
 out_init_req:
 	task->tk_status = 0;
diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c
index 7dab7b25b5c6..f576971f6556 100644
--- a/tools/vm/page-types.c
+++ b/tools/vm/page-types.c
@@ -35,6 +35,7 @@
 #include <sys/mount.h>
 #include <sys/statfs.h>
 #include "../../include/linux/magic.h"
+#include "../../include/linux/kernel-page-flags.h"
 
 
 #ifndef MAX_PATH
@@ -73,33 +74,6 @@
 #define KPF_BYTES		8
 #define PROC_KPAGEFLAGS		"/proc/kpageflags"
 
-/* copied from kpageflags_read() */
-#define KPF_LOCKED		0
-#define KPF_ERROR		1
-#define KPF_REFERENCED		2
-#define KPF_UPTODATE		3
-#define KPF_DIRTY		4
-#define KPF_LRU			5
-#define KPF_ACTIVE		6
-#define KPF_SLAB		7
-#define KPF_WRITEBACK		8
-#define KPF_RECLAIM		9
-#define KPF_BUDDY		10
-
-/* [11-20] new additions in 2.6.31 */
-#define KPF_MMAP		11
-#define KPF_ANON		12
-#define KPF_SWAPCACHE		13
-#define KPF_SWAPBACKED		14
-#define KPF_COMPOUND_HEAD	15
-#define KPF_COMPOUND_TAIL	16
-#define KPF_HUGE		17
-#define KPF_UNEVICTABLE		18
-#define KPF_HWPOISON		19
-#define KPF_NOPAGE		20
-#define KPF_KSM			21
-#define KPF_THP			22
-
 /* [32-] kernel hacking assistances */
 #define KPF_RESERVED		32
 #define KPF_MLOCKED		33
@@ -326,7 +300,7 @@ static char *page_flag_name(uint64_t flags)
 {
 	static char buf[65];
 	int present;
-	int i, j;
+	size_t i, j;
 
 	for (i = 0, j = 0; i < ARRAY_SIZE(page_flag_names); i++) {
 		present = (flags >> i) & 1;
@@ -344,7 +318,7 @@ static char *page_flag_name(uint64_t flags)
 static char *page_flag_longname(uint64_t flags)
 {
 	static char buf[1024];
-	int i, n;
+	size_t i, n;
 
 	for (i = 0, n = 0; i < ARRAY_SIZE(page_flag_names); i++) {
 		if (!page_flag_names[i])
@@ -402,7 +376,7 @@ static void show_page(unsigned long voffset,
 
 static void show_summary(void)
 {
-	int i;
+	size_t i;
 
 	printf("             flags\tpage-count       MB"
 		"  symbolic-flags\t\t\tlong-symbolic-flags\n");
@@ -500,7 +474,7 @@ static int debugfs_valid_mountpoint(const char *debugfs)
 /* find the path to the mounted debugfs */
 static const char *debugfs_find_mountpoint(void)
 {
-	const char **ptr;
+	const char *const *ptr;
 	char type[100];
 	FILE *fp;
 
@@ -537,7 +511,7 @@ static const char *debugfs_find_mountpoint(void)
 
 static void debugfs_mount(void)
 {
-	const char **ptr;
+	const char *const *ptr;
 
 	/* see if it's already mounted */
 	if (debugfs_find_mountpoint())
@@ -614,10 +588,10 @@ static int unpoison_page(unsigned long offset)
  * page frame walker
  */
 
-static int hash_slot(uint64_t flags)
+static size_t hash_slot(uint64_t flags)
 {
-	int k = HASH_KEY(flags);
-	int i;
+	size_t k = HASH_KEY(flags);
+	size_t i;
 
 	/* Explicitly reserve slot 0 for flags 0: the following logic
 	 * cannot distinguish an unoccupied slot from slot (flags==0).
@@ -670,7 +644,7 @@ static void walk_pfn(unsigned long voffset,
 {
 	uint64_t buf[KPAGEFLAGS_BATCH];
 	unsigned long batch;
-	long pages;
+	unsigned long pages;
 	unsigned long i;
 
 	while (count) {
@@ -779,7 +753,7 @@ static const char *page_flag_type(uint64_t flag)
 
 static void usage(void)
 {
-	int i, j;
+	size_t i, j;
 
 	printf(
 "page-types [options]\n"
@@ -938,7 +912,7 @@ static void add_bits_filter(uint64_t mask, uint64_t bits)
 
 static uint64_t parse_flag_name(const char *str, int len)
 {
-	int i;
+	size_t i;
 
 	if (!*str || !len)
 		return 0;