Merge branch 'akpm-current/current'

Conflicts:
	drivers/rtc/rtc-omap.c
	drivers/usb/storage/debug.c
	fs/ocfs2/inode.h
	lib/Kconfig

249 files changed, 6331 insertions, 4599 deletions

diff --git a/Documentation/cgroups/hugetlb.txt b/Documentation/cgroups/hugetlb.txt
index a9faaca1f029..106245c3aecc 100644
--- a/Documentation/cgroups/hugetlb.txt
+++ b/Documentation/cgroups/hugetlb.txt
@@ -29,7 +29,7 @@ Brief summary of control files
 
  hugetlb.<hugepagesize>.limit_in_bytes     # set/show limit of "hugepagesize" hugetlb usage
  hugetlb.<hugepagesize>.max_usage_in_bytes # show max "hugepagesize" hugetlb  usage recorded
- hugetlb.<hugepagesize>.usage_in_bytes     # show current res_counter usage for "hugepagesize" hugetlb
+ hugetlb.<hugepagesize>.usage_in_bytes     # show current usage for "hugepagesize" hugetlb
  hugetlb.<hugepagesize>.failcnt		   # show the number of allocation failure due to HugeTLB limit
 
 For a system supporting two hugepage size (16M and 16G) the control
diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index 02ab997a1ed2..46b2b5080317 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -1,5 +1,10 @@
 Memory Resource Controller
 
+NOTE: This document is hopelessly outdated and it asks for a complete
+      rewrite. It still contains a useful information so we are keeping it
+      here but make sure to check the current code if you need a deeper
+      understanding.
+
 NOTE: The Memory Resource Controller has generically been referred to as the
       memory controller in this document. Do not confuse memory controller
       used here with the memory controller that is used in hardware.
@@ -52,9 +57,9 @@ Brief summary of control files.
  tasks				 # attach a task(thread) and show list of threads
  cgroup.procs			 # show list of processes
  cgroup.event_control		 # an interface for event_fd()
- memory.usage_in_bytes		 # show current res_counter usage for memory
+ memory.usage_in_bytes		 # show current usage for memory
 				 (See 5.5 for details)
- memory.memsw.usage_in_bytes	 # show current res_counter usage for memory+Swap
+ memory.memsw.usage_in_bytes	 # show current usage for memory+Swap
 				 (See 5.5 for details)
  memory.limit_in_bytes		 # set/show limit of memory usage
  memory.memsw.limit_in_bytes	 # set/show limit of memory+Swap usage
@@ -116,16 +121,16 @@ The memory controller is the first controller developed.
 
 2.1. Design
 
-The core of the design is a counter called the res_counter. The res_counter
-tracks the current memory usage and limit of the group of processes associated
-with the controller. Each cgroup has a memory controller specific data
-structure (mem_cgroup) associated with it.
+The core of the design is a counter called the page_counter. The
+page_counter tracks the current memory usage and limit of the group of
+processes associated with the controller. Each cgroup has a memory controller
+specific data structure (mem_cgroup) associated with it.
 
 2.2. Accounting
 
 		+--------------------+
-		|  mem_cgroup     |
-		|  (res_counter)     |
+		|  mem_cgroup        |
+		|  (page_counter)    |
 		+--------------------+
 		 /            ^      \
 		/             |       \
@@ -352,9 +357,8 @@ set:
 0. Configuration
 
 a. Enable CONFIG_CGROUPS
-b. Enable CONFIG_RESOURCE_COUNTERS
-c. Enable CONFIG_MEMCG
-d. Enable CONFIG_MEMCG_SWAP (to use swap extension)
+b. Enable CONFIG_MEMCG
+c. Enable CONFIG_MEMCG_SWAP (to use swap extension)
 d. Enable CONFIG_MEMCG_KMEM (to use kmem extension)
 
 1. Prepare the cgroups (see cgroups.txt, Why are cgroups needed?)
diff --git a/Documentation/cgroups/resource_counter.txt b/Documentation/cgroups/resource_counter.txt
deleted file mode 100644
index 762ca54eb929..000000000000
--- a/Documentation/cgroups/resource_counter.txt
+++ /dev/null
@@ -1,197 +0,0 @@
-
-		The Resource Counter
-
-The resource counter, declared at include/linux/res_counter.h,
-is supposed to facilitate the resource management by controllers
-by providing common stuff for accounting.
-
-This "stuff" includes the res_counter structure and routines
-to work with it.
-
-
-
-1. Crucial parts of the res_counter structure
-
- a. unsigned long long usage
-
- 	The usage value shows the amount of a resource that is consumed
-	by a group at a given time. The units of measurement should be
-	determined by the controller that uses this counter. E.g. it can
-	be bytes, items or any other unit the controller operates on.
-
- b. unsigned long long max_usage
-
- 	The maximal value of the usage over time.
-
- 	This value is useful when gathering statistical information about
-	the particular group, as it shows the actual resource requirements
-	for a particular group, not just some usage snapshot.
-
- c. unsigned long long limit
-
- 	The maximal allowed amount of resource to consume by the group. In
-	case the group requests for more resources, so that the usage value
-	would exceed the limit, the resource allocation is rejected (see
-	the next section).
-
- d. unsigned long long failcnt
-
- 	The failcnt stands for "failures counter". This is the number of
-	resource allocation attempts that failed.
-
- c. spinlock_t lock
-
- 	Protects changes of the above values.
-
-
-
-2. Basic accounting routines
-
- a. void res_counter_init(struct res_counter *rc,
-				struct res_counter *rc_parent)
-
- 	Initializes the resource counter. As usual, should be the first
-	routine called for a new counter.
-
-	The struct res_counter *parent can be used to define a hierarchical
-	child -> parent relationship directly in the res_counter structure,
-	NULL can be used to define no relationship.
-
- c. int res_counter_charge(struct res_counter *rc, unsigned long val,
-				struct res_counter **limit_fail_at)
-
-	When a resource is about to be allocated it has to be accounted
-	with the appropriate resource counter (controller should determine
-	which one to use on its own). This operation is called "charging".
-
-	This is not very important which operation - resource allocation
-	or charging - is performed first, but
-	  * if the allocation is performed first, this may create a
-	    temporary resource over-usage by the time resource counter is
-	    charged;
-	  * if the charging is performed first, then it should be uncharged
-	    on error path (if the one is called).
-
-	If the charging fails and a hierarchical dependency exists, the
-	limit_fail_at parameter is set to the particular res_counter element
-	where the charging failed.
-
- d. u64 res_counter_uncharge(struct res_counter *rc, unsigned long val)
-
-	When a resource is released (freed) it should be de-accounted
-	from the resource counter it was accounted to.  This is called
-	"uncharging". The return value of this function indicate the amount
-	of charges still present in the counter.
-
-	The _locked routines imply that the res_counter->lock is taken.
-
- e. u64 res_counter_uncharge_until
-		(struct res_counter *rc, struct res_counter *top,
-		 unsigned long val)
-
-	Almost same as res_counter_uncharge() but propagation of uncharge
-	stops when rc == top. This is useful when kill a res_counter in
-	child cgroup.
-
- 2.1 Other accounting routines
-
-    There are more routines that may help you with common needs, like
-    checking whether the limit is reached or resetting the max_usage
-    value. They are all declared in include/linux/res_counter.h.
-
-
-
-3. Analyzing the resource counter registrations
-
- a. If the failcnt value constantly grows, this means that the counter's
-    limit is too tight. Either the group is misbehaving and consumes too
-    many resources, or the configuration is not suitable for the group
-    and the limit should be increased.
-
- b. The max_usage value can be used to quickly tune the group. One may
-    set the limits to maximal values and either load the container with
-    a common pattern or leave one for a while. After this the max_usage
-    value shows the amount of memory the container would require during
-    its common activity.
-
-    Setting the limit a bit above this value gives a pretty good
-    configuration that works in most of the cases.
-
- c. If the max_usage is much less than the limit, but the failcnt value
-    is growing, then the group tries to allocate a big chunk of resource
-    at once.
-
- d. If the max_usage is much less than the limit, but the failcnt value
-    is 0, then this group is given too high limit, that it does not
-    require. It is better to lower the limit a bit leaving more resource
-    for other groups.
-
-
-
-4. Communication with the control groups subsystem (cgroups)
-
-All the resource controllers that are using cgroups and resource counters
-should provide files (in the cgroup filesystem) to work with the resource
-counter fields. They are recommended to adhere to the following rules:
-
- a. File names
-
- 	Field name	File name
-	---------------------------------------------------
-	usage		usage_in_<unit_of_measurement>
-	max_usage	max_usage_in_<unit_of_measurement>
-	limit		limit_in_<unit_of_measurement>
-	failcnt		failcnt
-	lock		no file :)
-
- b. Reading from file should show the corresponding field value in the
-    appropriate format.
-
- c. Writing to file
-
- 	Field		Expected behavior
-	----------------------------------
-	usage		prohibited
-	max_usage	reset to usage
-	limit		set the limit
-	failcnt		reset to zero
-
-
-
-5. Usage example
-
- a. Declare a task group (take a look at cgroups subsystem for this) and
-    fold a res_counter into it
-
-	struct my_group {
-		struct res_counter res;
-
-		<other fields>
-	}
-
- b. Put hooks in resource allocation/release paths
-
- 	int alloc_something(...)
-	{
-		if (res_counter_charge(res_counter_ptr, amount) < 0)
-			return -ENOMEM;
-
-		<allocate the resource and return to the caller>
-	}
-
-	void release_something(...)
-	{
-		res_counter_uncharge(res_counter_ptr, amount);
-
-		<release the resource>
-	}
-
-    In order to keep the usage value self-consistent, both the
-    "res_counter_ptr" and the "amount" in release_something() should be
-    the same as they were in the alloc_something() when the releasing
-    resource was allocated.
-
- c. Provide the way to read res_counter values and set them (the cgroups
-    still can help with it).
-
- c. Compile and run :)
diff --git a/Documentation/devicetree/bindings/rtc/rtc-omap.txt b/Documentation/devicetree/bindings/rtc/rtc-omap.txt
index 5a0f02d34d95..750efd40c72e 100644
--- a/Documentation/devicetree/bindings/rtc/rtc-omap.txt
+++ b/Documentation/devicetree/bindings/rtc/rtc-omap.txt
@@ -5,11 +5,17 @@ Required properties:
 	- "ti,da830-rtc"  - for RTC IP used similar to that on DA8xx SoC family.
 	- "ti,am3352-rtc" - for RTC IP used similar to that on AM335x SoC family.
 			    This RTC IP has special WAKE-EN Register to enable
-			    Wakeup generation for event Alarm.
+			    Wakeup generation for event Alarm. It can also be
+			    used to control an external PMIC via the
+			    pmic_power_en pin.
 - reg: Address range of rtc register set
 - interrupts: rtc timer, alarm interrupts in order
 - interrupt-parent: phandle for the interrupt controller
 
+Optional properties:
+- ti,system-power-controller: whether the rtc is controlling the system power
+  through pmic_power_en
+
 Example:
 
 rtc@1c23000 {
@@ -18,4 +24,5 @@ rtc@1c23000 {
 	interrupts = <19
 		      19>;
 	interrupt-parent = <&intc>;
+	ti,system-power-controller;
 };
diff --git a/Documentation/filesystems/vfat.txt b/Documentation/filesystems/vfat.txt
index ce1126aceed8..223c32171dcc 100644
--- a/Documentation/filesystems/vfat.txt
+++ b/Documentation/filesystems/vfat.txt
@@ -180,6 +180,16 @@ dos1xfloppy  -- If set, use a fallback default BIOS Parameter Block
 
 <bool>: 0,1,yes,no,true,false
 
+LIMITATION
+---------------------------------------------------------------------
+* The fallocated region of file is discarded at umount/evict time
+  when using fallocate with FALLOC_FL_KEEP_SIZE.
+  So, User should assume that fallocated region can be discarded at
+  last close if there is memory pressure resulting in eviction of
+  the inode from the memory. As a result, for any dependency on
+  the fallocated region, user should make sure to recheck fallocate
+  after reopening the file.
+
 TODO
 ----------------------------------------------------------------------
 * Need to get rid of the raw scanning stuff.  Instead, always use
diff --git a/Documentation/kdump/kdump.txt b/Documentation/kdump/kdump.txt
index 6c0b9f27e465..bc4bd5a44b88 100644
--- a/Documentation/kdump/kdump.txt
+++ b/Documentation/kdump/kdump.txt
@@ -471,6 +471,13 @@ format. Crash is available on Dave Anderson's site at the following URL:
 
    http://people.redhat.com/~anderson/
 
+Trigger Kdump on WARN()
+=======================
+
+The kernel parameter, panic_on_warn, calls panic() in all WARN() paths.  This
+will cause a kdump to occur at the panic() call.  In cases where a user wants
+to specify this during runtime, /proc/sys/kernel/panic_on_warn can be set to 1
+to achieve the same behaviour.
 
 Contact
 =======
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index b5036bd9d6da..6087e083ea33 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2513,6 +2513,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			timeout < 0: reboot immediately
 			Format: <timeout>
 
+	panic_on_warn	panic() instead of WARN().  Useful to cause kdump
+			on a WARN().
+
 	crash_kexec_post_notifiers
 			Run kdump after running panic-notifiers and dumping
 			kmsg. This only for the users who doubt kdump always
diff --git a/Documentation/leds/leds-class.txt b/Documentation/leds/leds-class.txt
index 79699c200766..62261c04060a 100644
--- a/Documentation/leds/leds-class.txt
+++ b/Documentation/leds/leds-class.txt
@@ -2,9 +2,6 @@
 LED handling under Linux
 ========================
 
-If you're reading this and thinking about keyboard leds, these are
-handled by the input subsystem and the led class is *not* needed.
-
 In its simplest form, the LED class just allows control of LEDs from
 userspace. LEDs appear in /sys/class/leds/. The maximum brightness of the
 LED is defined in max_brightness file. The brightness file will set the brightness
diff --git a/Documentation/printk-formats.txt b/Documentation/printk-formats.txt
index 5a615c14f75d..8858db8f8805 100644
--- a/Documentation/printk-formats.txt
+++ b/Documentation/printk-formats.txt
@@ -216,6 +216,12 @@ dentry names:
 	equivalent of %s dentry->d_name.name we used to use, %pd<n> prints
 	n last components.  %pD does the same thing for struct file.
 
+task_struct comm name:
+
+        %pT
+
+        For printing task_struct->comm.
+
 struct va_format:
 
 	%pV
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index 57baff5bdb80..75511efefc64 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -54,8 +54,9 @@ show up in /proc/sys/kernel:
 - overflowuid
 - panic
 - panic_on_oops
-- panic_on_unrecovered_nmi
 - panic_on_stackoverflow
+- panic_on_unrecovered_nmi
+- panic_on_warn
 - pid_max
 - powersave-nap               [ PPC only ]
 - printk
@@ -115,10 +116,12 @@ set during run time.
 
 auto_msgmni:
 
-Enables/Disables automatic recomputing of msgmni upon memory add/remove
-or upon ipc namespace creation/removal (see the msgmni description
-above). Echoing "1" into this file enables msgmni automatic recomputing.
-Echoing "0" turns it off. auto_msgmni default value is 1.
+This variable has no effect and may be removed in future kernel
+releases. Reading it always returns 0.
+Up to Linux 3.17, it enabled/disabled automatic recomputing of msgmni
+upon memory add/remove or upon ipc namespace creation/removal.
+Echoing "1" into this file enabled msgmni automatic recomputing.
+Echoing "0" turned it off. auto_msgmni default value was 1.
 
 
 ==============================================================
@@ -527,19 +530,6 @@ the recommended setting is 60.
 
 ==============================================================
 
-panic_on_unrecovered_nmi:
-
-The default Linux behaviour on an NMI of either memory or unknown is
-to continue operation. For many environments such as scientific
-computing it is preferable that the box is taken out and the error
-dealt with than an uncorrected parity/ECC error get propagated.
-
-A small number of systems do generate NMI's for bizarre random reasons
-such as power management so the default is off. That sysctl works like
-the existing panic controls already in that directory.
-
-==============================================================
-
 panic_on_oops:
 
 Controls the kernel's behaviour when an oops or BUG is encountered.
@@ -563,6 +553,30 @@ This file shows up if CONFIG_DEBUG_STACKOVERFLOW is enabled.
 
 ==============================================================
 
+panic_on_unrecovered_nmi:
+
+The default Linux behaviour on an NMI of either memory or unknown is
+to continue operation. For many environments such as scientific
+computing it is preferable that the box is taken out and the error
+dealt with than an uncorrected parity/ECC error get propagated.
+
+A small number of systems do generate NMI's for bizarre random reasons
+such as power management so the default is off. That sysctl works like
+the existing panic controls already in that directory.
+
+==============================================================
+
+panic_on_warn:
+
+Calls panic() in the WARN() path when set to 1.  This is useful to avoid
+a kernel rebuild when attempting to kdump at the location of a WARN().
+
+0: only WARN(), default behaviour.
+
+1: call panic() after printing out WARN() location.
+
+==============================================================
+
 perf_cpu_time_max_percent:
 
 Hints to the kernel how much CPU time it should be allowed to
diff --git a/MAINTAINERS b/MAINTAINERS
index 59bc287d11de..4861577624b1 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2618,7 +2618,7 @@ L:	cgroups@vger.kernel.org
 L:	linux-mm@kvack.org
 S:	Maintained
 F:	mm/memcontrol.c
-F:	mm/page_cgroup.c
+F:	mm/swap_cgroup.c
 
 CORETEMP HARDWARE MONITORING DRIVER
 M:	Fenghua Yu <fenghua.yu@intel.com>
@@ -2735,7 +2735,7 @@ F:	drivers/net/wireless/cw1200/
 
 CX18 VIDEO4LINUX DRIVER
 M:	Andy Walls <awalls@md.metrocast.net>
-L:	ivtv-devel@ivtvdriver.org (moderated for non-subscribers)
+L:	ivtv-devel@ivtvdriver.org (subscribers-only)
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
 W:	http://linuxtv.org
@@ -5241,7 +5241,7 @@ F:	drivers/media/tuners/it913x*
 
 IVTV VIDEO4LINUX DRIVER
 M:	Andy Walls <awalls@md.metrocast.net>
-L:	ivtv-devel@ivtvdriver.org (moderated for non-subscribers)
+L:	ivtv-devel@ivtvdriver.org (subscribers-only)
 L:	linux-media@vger.kernel.org
 T:	git git://linuxtv.org/media_tree.git
 W:	http://www.ivtvdriver.org
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 2075ebdccf5d..9d580d0e89a9 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -5,6 +5,7 @@ config ARM
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAVE_CUSTOM_GPIO_H
+	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_USE_BUILTIN_BSWAP
diff --git a/arch/arm/boot/dts/am335x-boneblack.dts b/arch/arm/boot/dts/am335x-boneblack.dts
index 901739fcb85a..520b63605eb6 100644
--- a/arch/arm/boot/dts/am335x-boneblack.dts
+++ b/arch/arm/boot/dts/am335x-boneblack.dts
@@ -80,3 +80,7 @@
 		status = "okay";
 	};
 };
+
+&rtc {
+	ti,system-power-controller;
+};
diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi
index 831810583823..7ebbfe6992b7 100644
--- a/arch/arm/boot/dts/am33xx.dtsi
+++ b/arch/arm/boot/dts/am33xx.dtsi
@@ -419,7 +419,7 @@
 		};
 
 		rtc: rtc@44e3e000 {
-			compatible = "ti,da830-rtc";
+			compatible = "ti,am3352-rtc", "ti,da830-rtc";
 			reg = <0x44e3e000 0x1000>;
 			interrupts = <75
 				      76>;
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 1e0e4671dd25..58b657e41410 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -2,6 +2,7 @@ config ARM64
 	def_bool y
 	select ARCH_BINFMT_ELF_RANDOMIZE_PIE
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
+	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_SG_CHAIN
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_USE_CMPXCHG_LOCKREF
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 41a43bf26492..df22314f57cf 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -279,6 +279,7 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
 #endif /* CONFIG_HAVE_RCU_TABLE_FREE */
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
+#define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
 #define pmd_young(pmd)		pte_young(pmd_pte(pmd))
 #define pmd_wrprotect(pmd)	pte_pmd(pte_wrprotect(pmd_pte(pmd)))
 #define pmd_mksplitting(pmd)	pte_pmd(pte_mkspecial(pmd_pte(pmd)))
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index 5845ffea67c3..dc063fe6646a 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -2662,7 +2662,7 @@ pfm_context_create(pfm_context_t *ctx, void *arg, int count, struct pt_regs *reg
 
 	ret = -ENOMEM;
 
-	fd = get_unused_fd();
+	fd = get_unused_fd_flags(0);
 	if (fd < 0)
 		return fd;
 
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index a7736fa0580c..0bce820428fc 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -1,5 +1,6 @@
 config MICROBLAZE
 	def_bool y
+	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select ARCH_WANT_OPTIONAL_GPIOLIB
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 98e9c548bd75..daaee206d93b 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -128,6 +128,7 @@ config PPC
 	select HAVE_BPF_JIT if PPC64
 	select HAVE_ARCH_JUMP_LABEL
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
+	select ARCH_HAS_GCOV_PROFILE_ALL
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_CMOS_UPDATE
 	select GENERIC_TIME_VSYSCALL_OLD
diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index ae153c40ab7c..9b4b1904efae 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -467,6 +467,7 @@ static inline pte_t *pmdp_ptep(pmd_t *pmd)
 }
 
 #define pmd_pfn(pmd)		pte_pfn(pmd_pte(pmd))
+#define pmd_dirty(pmd)		pte_dirty(pmd_pte(pmd))
 #define pmd_young(pmd)		pte_young(pmd_pte(pmd))
 #define pmd_mkold(pmd)		pte_pmd(pte_mkold(pmd_pte(pmd)))
 #define pmd_wrprotect(pmd)	pte_pmd(pte_wrprotect(pmd_pte(pmd)))
diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index 65d633f20d37..1a3429e1ccb5 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -301,7 +301,7 @@ static int spufs_context_open(struct path *path)
 	int ret;
 	struct file *filp;
 
-	ret = get_unused_fd();
+	ret = get_unused_fd_flags(0);
 	if (ret < 0)
 		return ret;
 
@@ -518,7 +518,7 @@ static int spufs_gang_open(struct path *path)
 	int ret;
 	struct file *filp;
 
-	ret = get_unused_fd();
+	ret = get_unused_fd_flags(0);
 	if (ret < 0)
 		return ret;
 
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index f2cf1f90295b..68b68d755fdf 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -65,6 +65,7 @@ config S390
 	def_bool y
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
+	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_INLINE_READ_LOCK
 	select ARCH_INLINE_READ_LOCK_BH
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 244fb4c81e25..6db486ad7ca5 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -16,6 +16,7 @@ config SUPERH
 	select HAVE_DEBUG_BUGVERBOSE
 	select ARCH_HAVE_CUSTOM_GPIO_H
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG if (GUSA_RB || CPU_SH4A)
+	select ARCH_HAS_GCOV_PROFILE_ALL
 	select PERF_USE_VMALLOC
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_KERNEL_GZIP
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index bfeb626085ac..1ff9e7864168 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -667,6 +667,13 @@ static inline unsigned long pmd_pfn(pmd_t pmd)
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline unsigned long pmd_dirty(pmd_t pmd)
+{
+	pte_t pte = __pte(pmd_val(pmd));
+
+	return pte_dirty(pte);
+}
+
 static inline unsigned long pmd_young(pmd_t pmd)
 {
 	pte_t pte = __pte(pmd_val(pmd));
diff --git a/arch/tile/kernel/early_printk.c b/arch/tile/kernel/early_printk.c
index b608e00e7f6d..aefb2c086726 100644
--- a/arch/tile/kernel/early_printk.c
+++ b/arch/tile/kernel/early_printk.c
@@ -43,13 +43,20 @@ static struct console early_hv_console = {
 
 void early_panic(const char *fmt, ...)
 {
-	va_list ap;
+	struct va_format vaf;
+	va_list args;
+
 	arch_local_irq_disable_all();
-	va_start(ap, fmt);
-	early_printk("Kernel panic - not syncing: ");
-	early_vprintk(fmt, ap);
-	early_printk("\n");
-	va_end(ap);
+
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	early_printk("Kernel panic - not syncing: %pV", &vaf);
+
+	va_end(args);
+
 	dump_stack();
 	hv_halt();
 }
diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c
index f183f1c92b4f..864eea69556d 100644
--- a/arch/tile/kernel/setup.c
+++ b/arch/tile/kernel/setup.c
@@ -533,11 +533,10 @@ static void __init setup_memory(void)
 			}
 		}
 		physpages -= dropped_pages;
-		pr_warning("Only using %ldMB memory;"
-		       " ignoring %ldMB.\n",
-		       physpages >> (20 - PAGE_SHIFT),
-		       dropped_pages >> (20 - PAGE_SHIFT));
-		pr_warning("Consider using a larger page size.\n");
+		pr_warn("Only using %ldMB memory - ignoring %ldMB\n",
+			physpages >> (20 - PAGE_SHIFT),
+			dropped_pages >> (20 - PAGE_SHIFT));
+		pr_warn("Consider using a larger page size\n");
 	}
 #endif
 
@@ -564,9 +563,8 @@ static void __init setup_memory(void)
 
 #ifndef __tilegx__
 	if (node_end_pfn[0] > MAXMEM_PFN) {
-		pr_warning("Only using %ldMB LOWMEM.\n",
-		       MAXMEM>>20);
-		pr_warning("Use a HIGHMEM enabled kernel.\n");
+		pr_warn("Only using %ldMB LOWMEM\n", MAXMEM >> 20);
+		pr_warn("Use a HIGHMEM enabled kernel\n");
 		max_low_pfn = MAXMEM_PFN;
 		max_pfn = MAXMEM_PFN;
 		node_end_pfn[0] = MAXMEM_PFN;
@@ -1109,8 +1107,8 @@ static void __init load_hv_initrd(void)
 	fd = hv_fs_findfile((HV_VirtAddr) initramfs_file);
 	if (fd == HV_ENOENT) {
 		if (set_initramfs_file) {
-			pr_warning("No such hvfs initramfs file '%s'\n",
-				   initramfs_file);
+			pr_warn("No such hvfs initramfs file '%s'\n",
+				initramfs_file);
 			return;
 		} else {
 			/* Try old backwards-compatible name. */
@@ -1123,8 +1121,8 @@ static void __init load_hv_initrd(void)
 	stat = hv_fs_fstat(fd);
 	BUG_ON(stat.size < 0);
 	if (stat.flags & HV_FS_ISDIR) {
-		pr_warning("Ignoring hvfs file '%s': it's a directory.\n",
-			   initramfs_file);
+		pr_warn("Ignoring hvfs file '%s': it's a directory\n",
+			initramfs_file);
 		return;
 	}
 	initrd = alloc_bootmem_pages(stat.size);
@@ -1182,9 +1180,8 @@ static void __init validate_hv(void)
 	HV_Topology topology = hv_inquire_topology();
 	BUG_ON(topology.coord.x != 0 || topology.coord.y != 0);
 	if (topology.width != 1 || topology.height != 1) {
-		pr_warning("Warning: booting UP kernel on %dx%d grid;"
-			   " will ignore all but first tile.\n",
-			   topology.width, topology.height);
+		pr_warn("Warning: booting UP kernel on %dx%d grid; will ignore all but first tile\n",
+			topology.width, topology.height);
 	}
 #endif
 
@@ -1205,9 +1202,8 @@ static void __init validate_hv(void)
 	 * We use a struct cpumask for this, so it must be big enough.
 	 */
 	if ((smp_height * smp_width) > nr_cpu_ids)
-		early_panic("Hypervisor %d x %d grid too big for Linux"
-			    " NR_CPUS %d\n", smp_height, smp_width,
-			    nr_cpu_ids);
+		early_panic("Hypervisor %d x %d grid too big for Linux NR_CPUS %d\n",
+			    smp_height, smp_width, nr_cpu_ids);
 #endif
 
 	/*
@@ -1262,10 +1258,9 @@ static void __init validate_va(void)
 
 	/* Kernel PCs must have their high bit set; see intvec.S. */
 	if ((long)VMALLOC_START >= 0)
-		early_panic(
-			"Linux VMALLOC region below the 2GB line (%#lx)!\n"
-			"Reconfigure the kernel with smaller VMALLOC_RESERVE.\n",
-			VMALLOC_START);
+		early_panic("Linux VMALLOC region below the 2GB line (%#lx)!\n"
+			    "Reconfigure the kernel with smaller VMALLOC_RESERVE\n",
+			    VMALLOC_START);
 #endif
 }
 
@@ -1392,7 +1387,7 @@ static void __init setup_cpu_maps(void)
 
 static int __init dataplane(char *str)
 {
-	pr_warning("WARNING: dataplane support disabled in this kernel\n");
+	pr_warn("WARNING: dataplane support disabled in this kernel\n");
 	return 0;
 }
 
@@ -1410,8 +1405,8 @@ void __init setup_arch(char **cmdline_p)
 	len = hv_get_command_line((HV_VirtAddr) boot_command_line,
 				  COMMAND_LINE_SIZE);
 	if (boot_command_line[0])
-		pr_warning("WARNING: ignoring dynamic command line \"%s\"\n",
-			   boot_command_line);
+		pr_warn("WARNING: ignoring dynamic command line \"%s\"\n",
+			boot_command_line);
 	strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
 #else
 	char *hv_cmdline;
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 6d42b7e60c50..ec21dfdc27e5 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -24,6 +24,7 @@ config X86
 	select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI
 	select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS
 	select ARCH_HAS_FAST_MULTIPLIER
+	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select HAVE_AOUT if X86_32
diff --git a/arch/x86/ia32/audit.c b/arch/x86/ia32/audit.c
index 5d7b381da692..2eccc8932ae6 100644
--- a/arch/x86/ia32/audit.c
+++ b/arch/x86/ia32/audit.c
@@ -35,6 +35,7 @@ int ia32_classify_syscall(unsigned syscall)
 	case __NR_socketcall:
 		return 4;
 	case __NR_execve:
+	case __NR_execveat:
 		return 5;
 	default:
 		return 1;
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index ffe71228fc10..82e8a1d44658 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -480,6 +480,7 @@ GLOBAL(\label)
 	PTREGSCALL stub32_rt_sigreturn, sys32_rt_sigreturn
 	PTREGSCALL stub32_sigreturn, sys32_sigreturn
 	PTREGSCALL stub32_execve, compat_sys_execve
+	PTREGSCALL stub32_execveat, compat_sys_execveat
 	PTREGSCALL stub32_fork, sys_fork
 	PTREGSCALL stub32_vfork, sys_vfork
 
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index aa97a070f09f..081d6f45e006 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -99,6 +99,11 @@ static inline int pte_young(pte_t pte)
 	return pte_flags(pte) & _PAGE_ACCESSED;
 }
 
+static inline int pmd_dirty(pmd_t pmd)
+{
+	return pmd_flags(pmd) & _PAGE_DIRTY;
+}
+
 static inline int pmd_young(pmd_t pmd)
 {
 	return pmd_flags(pmd) & _PAGE_ACCESSED;
diff --git a/arch/x86/kernel/audit_64.c b/arch/x86/kernel/audit_64.c
index 06d3e5a14d9d..f3672508b249 100644
--- a/arch/x86/kernel/audit_64.c
+++ b/arch/x86/kernel/audit_64.c
@@ -50,6 +50,7 @@ int audit_classify_syscall(int abi, unsigned syscall)
 	case __NR_openat:
 		return 3;
 	case __NR_execve:
+	case __NR_execveat:
 		return 5;
 	default:
 		return 0;
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index b65be8bdd7d4..59384d5909fe 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -652,6 +652,20 @@ ENTRY(stub_execve)
 	CFI_ENDPROC
 END(stub_execve)
 
+ENTRY(stub_execveat)
+	CFI_STARTPROC
+	addq $8, %rsp
+	PARTIAL_FRAME 0
+	SAVE_REST
+	FIXUP_TOP_OF_STACK %r11
+	call sys_execveat
+	RESTORE_TOP_OF_STACK %r11
+	movq %rax,RAX(%rsp)
+	RESTORE_REST
+	jmp int_ret_from_sys_call
+	CFI_ENDPROC
+END(stub_execveat)
+
 /*
  * sigreturn is special because it needs to restore all registers on return.
  * This cannot be done with SYSRET, so use the IRET return path instead.
@@ -697,6 +711,20 @@ ENTRY(stub_x32_execve)
 	CFI_ENDPROC
 END(stub_x32_execve)
 
+ENTRY(stub_x32_execveat)
+	CFI_STARTPROC
+	addq $8, %rsp
+	PARTIAL_FRAME 0
+	SAVE_REST
+	FIXUP_TOP_OF_STACK %r11
+	call compat_sys_execveat
+	RESTORE_TOP_OF_STACK %r11
+	movq %rax,RAX(%rsp)
+	RESTORE_REST
+	jmp int_ret_from_sys_call
+	CFI_ENDPROC
+END(stub_x32_execveat)
+
 #endif
 
 /*
diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl
index 9fe1b5d002f0..b3560ece1c9f 100644
--- a/arch/x86/syscalls/syscall_32.tbl
+++ b/arch/x86/syscalls/syscall_32.tbl
@@ -364,3 +364,4 @@
 355	i386	getrandom		sys_getrandom
 356	i386	memfd_create		sys_memfd_create
 357	i386	bpf			sys_bpf
+358	i386	execveat		sys_execveat			stub32_execveat
diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl
index 281150b539a2..8d656fbb57aa 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/syscalls/syscall_64.tbl
@@ -328,6 +328,7 @@
 319	common	memfd_create		sys_memfd_create
 320	common	kexec_file_load		sys_kexec_file_load
 321	common	bpf			sys_bpf
+322	64	execveat		stub_execveat
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
@@ -366,3 +367,4 @@
 542	x32	getsockopt		compat_sys_getsockopt
 543	x32	io_setup		compat_sys_io_setup
 544	x32	io_submit		compat_sys_io_submit
+545	x32	execveat		stub_x32_execveat
diff --git a/arch/x86/um/sys_call_table_64.c b/arch/x86/um/sys_call_table_64.c
index f2f0723070ca..20c3649d0691 100644
--- a/arch/x86/um/sys_call_table_64.c
+++ b/arch/x86/um/sys_call_table_64.c
@@ -31,6 +31,7 @@
 #define stub_fork sys_fork
 #define stub_vfork sys_vfork
 #define stub_execve sys_execve
+#define stub_execveat sys_execveat
 #define stub_rt_sigreturn sys_rt_sigreturn
 
 #define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat)
diff --git a/block/bio.c b/block/bio.c
index 3e6e1986a5b2..96db147444a8 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -748,6 +748,7 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 				}
 			}
 
+			bio->bi_iter.bi_size += len;
 			goto done;
 		}
 
@@ -764,29 +765,32 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 		return 0;
 
 	/*
-	 * we might lose a segment or two here, but rather that than
-	 * make this too complex.
+	 * setup the new entry, we might clear it again later if we
+	 * cannot add the page
+	 */
+	bvec = &bio->bi_io_vec[bio->bi_vcnt];
+	bvec->bv_page = page;
+	bvec->bv_len = len;
+	bvec->bv_offset = offset;
+	bio->bi_vcnt++;
+	bio->bi_phys_segments++;
+	bio->bi_iter.bi_size += len;
+
+	/*
+	 * Perform a recount if the number of segments is greater
+	 * than queue_max_segments(q).
 	 */
 
-	while (bio->bi_phys_segments >= queue_max_segments(q)) {
+	while (bio->bi_phys_segments > queue_max_segments(q)) {
 
 		if (retried_segments)
-			return 0;
+			goto failed;
 
 		retried_segments = 1;
 		blk_recount_segments(q, bio);
 	}
 
 	/*
-	 * setup the new entry, we might clear it again later if we
-	 * cannot add the page
-	 */
-	bvec = &bio->bi_io_vec[bio->bi_vcnt];
-	bvec->bv_page = page;
-	bvec->bv_len = len;
-	bvec->bv_offset = offset;
-
-	/*
 	 * if queue has other restrictions (eg varying max sector size
 	 * depending on offset), it can specify a merge_bvec_fn in the
 	 * queue to get further control
@@ -795,7 +799,7 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 		struct bvec_merge_data bvm = {
 			.bi_bdev = bio->bi_bdev,
 			.bi_sector = bio->bi_iter.bi_sector,
-			.bi_size = bio->bi_iter.bi_size,
+			.bi_size = bio->bi_iter.bi_size - len,
 			.bi_rw = bio->bi_rw,
 		};
 
@@ -803,23 +807,25 @@ static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
 		 * merge_bvec_fn() returns number of bytes it can accept
 		 * at this offset
 		 */
-		if (q->merge_bvec_fn(q, &bvm, bvec) < bvec->bv_len) {
-			bvec->bv_page = NULL;
-			bvec->bv_len = 0;
-			bvec->bv_offset = 0;
-			return 0;
-		}
+		if (q->merge_bvec_fn(q, &bvm, bvec) < bvec->bv_len)
+			goto failed;
 	}
 
 	/* If we may be able to merge these biovecs, force a recount */
-	if (bio->bi_vcnt && (BIOVEC_PHYS_MERGEABLE(bvec-1, bvec)))
+	if (bio->bi_vcnt > 1 && (BIOVEC_PHYS_MERGEABLE(bvec-1, bvec)))
 		bio->bi_flags &= ~(1 << BIO_SEG_VALID);
 
-	bio->bi_vcnt++;
-	bio->bi_phys_segments++;
  done:
-	bio->bi_iter.bi_size += len;
 	return len;
+
+ failed:
+	bvec->bv_page = NULL;
+	bvec->bv_len = 0;
+	bvec->bv_offset = 0;
+	bio->bi_vcnt--;
+	bio->bi_iter.bi_size -= len;
+	blk_recount_segments(q, bio);
+	return 0;
 }
 
 /**
diff --git a/block/genhd.c b/block/genhd.c
index bd3060684ab2..8542ceb6044b 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -850,7 +850,7 @@ static int show_partition(struct seq_file *seqf, void *v)
 	char buf[BDEVNAME_SIZE];
 
 	/* Don't show non-partitionable removeable devices or empty devices */
-	if (!get_capacity(sgp) || (!disk_max_parts(sgp) &&
+	if (!get_capacity(sgp) || (!(disk_max_parts(sgp) > 1) &&
 				   (sgp->flags & GENHD_FL_REMOVABLE)))
 		return 0;
 	if (sgp->flags & GENHD_FL_SUPPRESS_PARTITION_INFO)
diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig
index df04227d00cf..98504ec99c7d 100644
--- a/drivers/base/Kconfig
+++ b/drivers/base/Kconfig
@@ -267,18 +267,24 @@ comment "Default contiguous memory area size:"
 config CMA_SIZE_MBYTES
 	int "Size in Mega Bytes"
 	depends on !CMA_SIZE_SEL_PERCENTAGE
+	default 0 if X86
 	default 16
 	help
 	  Defines the size (in MiB) of the default memory area for Contiguous
-	  Memory Allocator.
+	  Memory Allocator.  If the size of 0 is selected, CMA is disabled by
+	  default, but it can be enabled by passing cma=size[MG] to the kernel.
+
 
 config CMA_SIZE_PERCENTAGE
 	int "Percentage of total memory"
 	depends on !CMA_SIZE_SEL_MBYTES
+	default 0 if X86
 	default 10
 	help
 	  Defines the size of the default memory area for Contiguous Memory
 	  Allocator as a percentage of the total memory in the system.
+	  If 0 percent is selected, CMA is disabled by default, but it can be
+	  enabled by passing cma=size[MG] to the kernel.
 
 choice
 	prompt "Selected region size"
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 2ad0b5bce44b..4b4f4dbc3cfd 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -287,19 +287,18 @@ static inline int is_partial_io(struct bio_vec *bvec)
 /*
  * Check if request is within bounds and aligned on zram logical blocks.
  */
-static inline int valid_io_request(struct zram *zram, struct bio *bio)
+static inline int valid_io_request(struct zram *zram,
+		sector_t start, unsigned int size)
 {
-	u64 start, end, bound;
+	u64 end, bound;
 
 	/* unaligned request */
-	if (unlikely(bio->bi_iter.bi_sector &
-		     (ZRAM_SECTOR_PER_LOGICAL_BLOCK - 1)))
+	if (unlikely(start & (ZRAM_SECTOR_PER_LOGICAL_BLOCK - 1)))
 		return 0;
-	if (unlikely(bio->bi_iter.bi_size & (ZRAM_LOGICAL_BLOCK_SIZE - 1)))
+	if (unlikely(size & (ZRAM_LOGICAL_BLOCK_SIZE - 1)))
 		return 0;
 
-	start = bio->bi_iter.bi_sector;
-	end = start + (bio->bi_iter.bi_size >> SECTOR_SHIFT);
+	end = start + (size >> SECTOR_SHIFT);
 	bound = zram->disksize >> SECTOR_SHIFT;
 	/* out of range range */
 	if (unlikely(start >= bound || end > bound || start > end))
@@ -453,7 +452,7 @@ static int zram_decompress_page(struct zram *zram, char *mem, u32 index)
 }
 
 static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
-			  u32 index, int offset, struct bio *bio)
+			  u32 index, int offset)
 {
 	int ret;
 	struct page *page;
@@ -560,7 +559,8 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 	}
 
 	if (page_zero_filled(uncmem)) {
-		kunmap_atomic(user_mem);
+		if (user_mem)
+			kunmap_atomic(user_mem);
 		/* Free memory associated with this sector now. */
 		bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
 		zram_free_page(zram, index);
@@ -644,14 +644,13 @@ out:
 }
 
 static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
-			int offset, struct bio *bio)
+			int offset, int rw)
 {
 	int ret;
-	int rw = bio_data_dir(bio);
 
 	if (rw == READ) {
 		atomic64_inc(&zram->stats.num_reads);
-		ret = zram_bvec_read(zram, bvec, index, offset, bio);
+		ret = zram_bvec_read(zram, bvec, index, offset);
 	} else {
 		atomic64_inc(&zram->stats.num_writes);
 		ret = zram_bvec_write(zram, bvec, index, offset);
@@ -852,7 +851,7 @@ out:
 
 static void __zram_make_request(struct zram *zram, struct bio *bio)
 {
-	int offset;
+	int offset, rw;
 	u32 index;
 	struct bio_vec bvec;
 	struct bvec_iter iter;
@@ -867,6 +866,7 @@ static void __zram_make_request(struct zram *zram, struct bio *bio)
 		return;
 	}
 
+	rw = bio_data_dir(bio);
 	bio_for_each_segment(bvec, bio, iter) {
 		int max_transfer_size = PAGE_SIZE - offset;
 
@@ -881,15 +881,15 @@ static void __zram_make_request(struct zram *zram, struct bio *bio)
 			bv.bv_len = max_transfer_size;
 			bv.bv_offset = bvec.bv_offset;
 
-			if (zram_bvec_rw(zram, &bv, index, offset, bio) < 0)
+			if (zram_bvec_rw(zram, &bv, index, offset, rw) < 0)
 				goto out;
 
 			bv.bv_len = bvec.bv_len - max_transfer_size;
 			bv.bv_offset += max_transfer_size;
-			if (zram_bvec_rw(zram, &bv, index + 1, 0, bio) < 0)
+			if (zram_bvec_rw(zram, &bv, index + 1, 0, rw) < 0)
 				goto out;
 		} else
-			if (zram_bvec_rw(zram, &bvec, index, offset, bio) < 0)
+			if (zram_bvec_rw(zram, &bvec, index, offset, rw) < 0)
 				goto out;
 
 		update_position(&index, &offset, &bvec);
@@ -914,7 +914,8 @@ static void zram_make_request(struct request_queue *queue, struct bio *bio)
 	if (unlikely(!init_done(zram)))
 		goto error;
 
-	if (!valid_io_request(zram, bio)) {
+	if (!valid_io_request(zram, bio->bi_iter.bi_sector,
+					bio->bi_iter.bi_size)) {
 		atomic64_inc(&zram->stats.invalid_io);
 		goto error;
 	}
@@ -944,8 +945,51 @@ static void zram_slot_free_notify(struct block_device *bdev,
 	atomic64_inc(&zram->stats.notify_free);
 }
 
+static int zram_rw_page(struct block_device *bdev, sector_t sector,
+		       struct page *page, int rw)
+{
+	int offset, err;
+	u32 index;
+	struct zram *zram;
+	struct bio_vec bv;
+
+	zram = bdev->bd_disk->private_data;
+	if (!valid_io_request(zram, sector, PAGE_SIZE)) {
+		atomic64_inc(&zram->stats.invalid_io);
+		err = -EINVAL;
+		goto out;
+	}
+
+	down_read(&zram->init_lock);
+	if (unlikely(!init_done(zram))) {
+		err = -EIO;
+		goto out_unlock;
+	}
+
+	index = sector >> SECTORS_PER_PAGE_SHIFT;
+	offset = sector & (SECTORS_PER_PAGE - 1) << SECTOR_SHIFT;
+
+	bv.bv_page = page;
+	bv.bv_len = PAGE_SIZE;
+	bv.bv_offset = 0;
+
+	err = zram_bvec_rw(zram, &bv, index, offset, rw);
+
+out_unlock:
+	up_read(&zram->init_lock);
+out:
+	page_endio(page, rw, err);
+
+	/*
+	 * Return 0 prevents I/O fallback trial caused by rw_page fail
+	 * and upper layer can handle this IO error via page error.
+	 */
+	return 0;
+}
+
 static const struct block_device_operations zram_devops = {
 	.swap_slot_free_notify = zram_slot_free_notify,
+	.rw_page = zram_rw_page,
 	.owner = THIS_MODULE
 };
 
diff --git a/drivers/input/Kconfig b/drivers/input/Kconfig
index a11ff74a5127..9eac8de9e8b7 100644
--- a/drivers/input/Kconfig
+++ b/drivers/input/Kconfig
@@ -178,6 +178,15 @@ comment "Input Device Drivers"
 
 source "drivers/input/keyboard/Kconfig"
 
+config INPUT_LEDS
+	bool "LED Support"
+	depends on LEDS_CLASS = INPUT || LEDS_CLASS = y
+	select LEDS_TRIGGERS
+	default y
+	help
+	  This option enables support for LEDs on keyboards managed
+	  by the input layer.
+
 source "drivers/input/mouse/Kconfig"
 
 source "drivers/input/joystick/Kconfig"
diff --git a/drivers/input/Makefile b/drivers/input/Makefile
index 5ca3f631497f..2ab5f3336da5 100644
--- a/drivers/input/Makefile
+++ b/drivers/input/Makefile
@@ -6,6 +6,9 @@
 
 obj-$(CONFIG_INPUT)		+= input-core.o
 input-core-y := input.o input-compat.o input-mt.o ff-core.o
+ifeq ($(CONFIG_INPUT_LEDS),y)
+input-core-y += leds.o
+endif
 
 obj-$(CONFIG_INPUT_FF_MEMLESS)	+= ff-memless.o
 obj-$(CONFIG_INPUT_POLLDEV)	+= input-polldev.o
diff --git a/drivers/input/input.c b/drivers/input/input.c
index 0f175f55782b..0e01aeaf942a 100644
--- a/drivers/input/input.c
+++ b/drivers/input/input.c
@@ -711,6 +711,9 @@ static void input_disconnect_device(struct input_dev *dev)
 		handle->open = 0;
 
 	spin_unlock_irq(&dev->event_lock);
+
+	if (is_event_supported(EV_LED, dev->evbit, EV_MAX))
+		input_led_disconnect(dev);
 }
 
 /**
@@ -2137,6 +2140,9 @@ int input_register_device(struct input_dev *dev)
 
 	list_add_tail(&dev->node, &input_dev_list);
 
+	if (is_event_supported(EV_LED, dev->evbit, EV_MAX))
+		input_led_connect(dev);
+
 	list_for_each_entry(handler, &input_handler_list, node)
 		input_attach_handler(dev, handler);
 
@@ -2422,6 +2428,8 @@ static int __init input_init(void)
 		goto fail2;
 	}
 
+	input_led_init();
+
 	return 0;
 
  fail2:	input_proc_exit();
@@ -2431,6 +2439,7 @@ static int __init input_init(void)
 
 static void __exit input_exit(void)
 {
+	input_led_exit();
 	input_proc_exit();
 	unregister_chrdev_region(MKDEV(INPUT_MAJOR, 0),
 				 INPUT_MAX_CHAR_DEVICES);
diff --git a/drivers/input/leds.c b/drivers/input/leds.c
new file mode 100644
index 000000000000..193ee2425db1
--- /dev/null
+++ b/drivers/input/leds.c
@@ -0,0 +1,272 @@
+/*
+ * LED support for the input layer
+ *
+ * Copyright 2010-2014 Samuel Thibault <samuel.thibault@ens-lyon.org>
+ *
+ * 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/kernel.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/leds.h>
+#include <linux/input.h>
+
+/*
+ * Keyboard LEDs are propagated by default like the following example:
+ *
+ * VT keyboard numlock trigger
+ * -> vt::numl VT LED
+ * -> vt-numl VT trigger
+ * -> per-device inputX::numl LED
+ *
+ * Userland can however choose the trigger for the vt::numl LED, or
+ * independently choose the trigger for any inputx::numl LED.
+ *
+ *
+ * VT LED classes and triggers are registered on-demand according to
+ * existing LED devices
+ */
+
+/* Handler for VT LEDs, just triggers the corresponding VT trigger. */
+static void vt_led_set(struct led_classdev *cdev,
+			  enum led_brightness brightness);
+static struct led_classdev vt_leds[LED_CNT] = {
+#define DEFINE_INPUT_LED(vt_led, nam, deftrig) \
+	[vt_led] = { \
+		.name = "vt::"nam, \
+		.max_brightness = 1, \
+		.brightness_set = vt_led_set, \
+		.default_trigger = deftrig, \
+	}
+/* Default triggers for the VT LEDs just correspond to the legacy
+ * usage. */
+	DEFINE_INPUT_LED(LED_NUML, "numl", "kbd-numlock"),
+	DEFINE_INPUT_LED(LED_CAPSL, "capsl", "kbd-capslock"),
+	DEFINE_INPUT_LED(LED_SCROLLL, "scrolll", "kbd-scrollock"),
+	DEFINE_INPUT_LED(LED_COMPOSE, "compose", NULL),
+	DEFINE_INPUT_LED(LED_KANA, "kana", "kbd-kanalock"),
+	DEFINE_INPUT_LED(LED_SLEEP, "sleep", NULL),
+	DEFINE_INPUT_LED(LED_SUSPEND, "suspend", NULL),
+	DEFINE_INPUT_LED(LED_MUTE, "mute", NULL),
+	DEFINE_INPUT_LED(LED_MISC, "misc", NULL),
+	DEFINE_INPUT_LED(LED_MAIL, "mail", NULL),
+	DEFINE_INPUT_LED(LED_CHARGING, "charging", NULL),
+};
+static const char *const vt_led_names[LED_CNT] = {
+	[LED_NUML] = "numl",
+	[LED_CAPSL] = "capsl",
+	[LED_SCROLLL] = "scrolll",
+	[LED_COMPOSE] = "compose",
+	[LED_KANA] = "kana",
+	[LED_SLEEP] = "sleep",
+	[LED_SUSPEND] = "suspend",
+	[LED_MUTE] = "mute",
+	[LED_MISC] = "misc",
+	[LED_MAIL] = "mail",
+	[LED_CHARGING] = "charging",
+};
+/* Handler for hotplug initialization */
+static void vt_led_trigger_activate(struct led_classdev *cdev);
+/* VT triggers */
+static struct led_trigger vt_led_triggers[LED_CNT] = {
+#define DEFINE_INPUT_LED_TRIGGER(vt_led, nam) \
+	[vt_led] = { \
+		.name = "vt-"nam, \
+		.activate = vt_led_trigger_activate, \
+	}
+	DEFINE_INPUT_LED_TRIGGER(LED_NUML, "numl"),
+	DEFINE_INPUT_LED_TRIGGER(LED_CAPSL, "capsl"),
+	DEFINE_INPUT_LED_TRIGGER(LED_SCROLLL, "scrolll"),
+	DEFINE_INPUT_LED_TRIGGER(LED_COMPOSE, "compose"),
+	DEFINE_INPUT_LED_TRIGGER(LED_KANA, "kana"),
+	DEFINE_INPUT_LED_TRIGGER(LED_SLEEP, "sleep"),
+	DEFINE_INPUT_LED_TRIGGER(LED_SUSPEND, "suspend"),
+	DEFINE_INPUT_LED_TRIGGER(LED_MUTE, "mute"),
+	DEFINE_INPUT_LED_TRIGGER(LED_MISC, "misc"),
+	DEFINE_INPUT_LED_TRIGGER(LED_MAIL, "mail"),
+	DEFINE_INPUT_LED_TRIGGER(LED_CHARGING, "charging"),
+};
+
+/* Lock for registration coherency */
+static DEFINE_MUTEX(vt_led_registered_lock);
+
+/* Which VT LED classes and triggers are registered */
+static unsigned long vt_led_registered[BITS_TO_LONGS(LED_CNT)];
+
+/* Number of input devices having each LED */
+static int vt_led_references[LED_CNT];
+
+static int vt_led_state[LED_CNT];
+static struct work_struct vt_led_work[LED_CNT];
+
+static void vt_led_cb(struct work_struct *work)
+{
+	int led = work - vt_led_work;
+
+	led_trigger_event(&vt_led_triggers[led], vt_led_state[led]);
+}
+
+/* VT LED state change, tell the VT trigger.  */
+static void vt_led_set(struct led_classdev *cdev,
+			  enum led_brightness brightness)
+{
+	int led = cdev - vt_leds;
+
+	vt_led_state[led] = !!brightness;
+	schedule_work(&vt_led_work[led]);
+}
+
+/* LED state change for some keyboard, notify that keyboard.  */
+static void perdevice_input_led_set(struct led_classdev *cdev,
+			  enum led_brightness brightness)
+{
+	struct input_dev *dev;
+	struct led_classdev *leds;
+	int led;
+
+	dev = cdev->dev->platform_data;
+	if (!dev)
+		/* Still initializing */
+		return;
+	leds = dev->leds;
+	led = cdev - leds;
+
+	input_event(dev, EV_LED, led, !!brightness);
+	input_event(dev, EV_SYN, SYN_REPORT, 0);
+}
+
+/* Keyboard hotplug, initialize its LED status */
+static void vt_led_trigger_activate(struct led_classdev *cdev)
+{
+	struct led_trigger *trigger = cdev->trigger;
+	int led = trigger - vt_led_triggers;
+
+	if (cdev->brightness_set)
+		cdev->brightness_set(cdev, vt_leds[led].brightness);
+}
+
+/* Free led stuff from input device, used at abortion and disconnection.  */
+static void input_led_delete(struct input_dev *dev)
+{
+	if (dev) {
+		struct led_classdev *leds = dev->leds;
+		if (leds) {
+			int i;
+			for (i = 0; i < LED_CNT; i++)
+				kfree(leds[i].name);
+			kfree(leds);
+			dev->leds = NULL;
+		}
+	}
+}
+
+/* A new input device with potential LEDs to connect.  */
+int input_led_connect(struct input_dev *dev)
+{
+	int i, error = 0;
+	struct led_classdev *leds;
+
+	dev->leds = leds = kcalloc(LED_CNT, sizeof(*leds), GFP_KERNEL);
+	if (!dev->leds)
+		return -ENOMEM;
+
+	/* lazily register missing VT LEDs */
+	mutex_lock(&vt_led_registered_lock);
+	for (i = 0; i < LED_CNT; i++)
+		if (vt_leds[i].name && test_bit(i, dev->ledbit)) {
+			if (!vt_led_references[i]) {
+				led_trigger_register(&vt_led_triggers[i]);
+				/* This keyboard is first to have led i,
+				 * try to register it */
+				if (!led_classdev_register(NULL, &vt_leds[i]))
+					vt_led_references[i] = 1;
+				else
+					led_trigger_unregister(&vt_led_triggers[i]);
+			} else
+				vt_led_references[i]++;
+		}
+	mutex_unlock(&vt_led_registered_lock);
+
+	/* and register this device's LEDs */
+	for (i = 0; i < LED_CNT; i++)
+		if (vt_leds[i].name && test_bit(i, dev->ledbit)) {
+			leds[i].name = kasprintf(GFP_KERNEL, "%s::%s",
+						dev_name(&dev->dev),
+						vt_led_names[i]);
+			if (!leds[i].name) {
+				error = -ENOMEM;
+				goto err;
+			}
+			leds[i].max_brightness = 1;
+			leds[i].brightness_set = perdevice_input_led_set;
+			leds[i].default_trigger = vt_led_triggers[i].name;
+		}
+
+	/* No issue so far, we can register for real.  */
+	for (i = 0; i < LED_CNT; i++)
+		if (leds[i].name) {
+			led_classdev_register(&dev->dev, &leds[i]);
+			leds[i].dev->platform_data = dev;
+			perdevice_input_led_set(&leds[i],
+					vt_leds[i].brightness);
+		}
+
+	return 0;
+
+err:
+	input_led_delete(dev);
+	return error;
+}
+
+/*
+ * Disconnected input device. Clean it, and deregister now-useless VT LEDs
+ * and triggers.
+ */
+void input_led_disconnect(struct input_dev *dev)
+{
+	int i;
+	struct led_classdev *leds = dev->leds;
+
+	for (i = 0; i < LED_CNT; i++)
+		if (leds[i].name)
+			led_classdev_unregister(&leds[i]);
+
+	input_led_delete(dev);
+
+	mutex_lock(&vt_led_registered_lock);
+	for (i = 0; i < LED_CNT; i++) {
+		if (!vt_leds[i].name || !test_bit(i, dev->ledbit))
+			continue;
+
+		vt_led_references[i]--;
+		if (vt_led_references[i]) {
+			/* Still some devices needing it */
+			continue;
+		}
+
+		led_classdev_unregister(&vt_leds[i]);
+		led_trigger_unregister(&vt_led_triggers[i]);
+		clear_bit(i, vt_led_registered);
+	}
+	mutex_unlock(&vt_led_registered_lock);
+}
+
+void __init input_led_init(void)
+{
+	unsigned i;
+
+	for (i = 0; i < LED_CNT; i++)
+		INIT_WORK(&vt_led_work[i], vt_led_cb);
+}
+
+void __exit input_led_exit(void)
+{
+	unsigned i;
+
+	for (i = 0; i < LED_CNT; i++)
+		cancel_work_sync(&vt_led_work[i]);
+}
diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c
index 90d734bbf467..f724bdc50d25 100644
--- a/drivers/iommu/amd_iommu_v2.c
+++ b/drivers/iommu/amd_iommu_v2.c
@@ -92,13 +92,6 @@ static spinlock_t state_lock;
 
 static struct workqueue_struct *iommu_wq;
 
-/*
- * Empty page table - Used between
- * mmu_notifier_invalidate_range_start and
- * mmu_notifier_invalidate_range_end
- */
-static u64 *empty_page_table;
-
 static void free_pasid_states(struct device_state *dev_state);
 
 static u16 device_id(struct pci_dev *pdev)
@@ -418,46 +411,21 @@ static void mn_invalidate_page(struct mmu_notifier *mn,
 	__mn_flush_page(mn, address);
 }
 
-static void mn_invalidate_range_start(struct mmu_notifier *mn,
-				      struct mm_struct *mm,
-				      unsigned long start, unsigned long end)
-{
-	struct pasid_state *pasid_state;
-	struct device_state *dev_state;
-	unsigned long flags;
-
-	pasid_state = mn_to_state(mn);
-	dev_state   = pasid_state->device_state;
-
-	spin_lock_irqsave(&pasid_state->lock, flags);
-	if (pasid_state->mmu_notifier_count == 0) {
-		amd_iommu_domain_set_gcr3(dev_state->domain,
-					  pasid_state->pasid,
-					  __pa(empty_page_table));
-	}
-	pasid_state->mmu_notifier_count += 1;
-	spin_unlock_irqrestore(&pasid_state->lock, flags);
-}
-
-static void mn_invalidate_range_end(struct mmu_notifier *mn,
-				    struct mm_struct *mm,
-				    unsigned long start, unsigned long end)
+static void mn_invalidate_range(struct mmu_notifier *mn,
+				struct mm_struct *mm,
+				unsigned long start, unsigned long end)
 {
 	struct pasid_state *pasid_state;
 	struct device_state *dev_state;
-	unsigned long flags;
 
 	pasid_state = mn_to_state(mn);
 	dev_state   = pasid_state->device_state;
 
-	spin_lock_irqsave(&pasid_state->lock, flags);
-	pasid_state->mmu_notifier_count -= 1;
-	if (pasid_state->mmu_notifier_count == 0) {
-		amd_iommu_domain_set_gcr3(dev_state->domain,
-					  pasid_state->pasid,
-					  __pa(pasid_state->mm->pgd));
-	}
-	spin_unlock_irqrestore(&pasid_state->lock, flags);
+	if ((start ^ (end - 1)) < PAGE_SIZE)
+		amd_iommu_flush_page(dev_state->domain, pasid_state->pasid,
+				     start);
+	else
+		amd_iommu_flush_tlb(dev_state->domain, pasid_state->pasid);
 }
 
 static void mn_release(struct mmu_notifier *mn, struct mm_struct *mm)
@@ -482,8 +450,7 @@ static struct mmu_notifier_ops iommu_mn = {
 	.release		= mn_release,
 	.clear_flush_young      = mn_clear_flush_young,
 	.invalidate_page        = mn_invalidate_page,
-	.invalidate_range_start = mn_invalidate_range_start,
-	.invalidate_range_end   = mn_invalidate_range_end,
+	.invalidate_range       = mn_invalidate_range,
 };
 
 static void set_pri_tag_status(struct pasid_state *pasid_state,
@@ -954,18 +921,10 @@ static int __init amd_iommu_v2_init(void)
 	if (iommu_wq == NULL)
 		goto out;
 
-	ret = -ENOMEM;
-	empty_page_table = (u64 *)get_zeroed_page(GFP_KERNEL);
-	if (empty_page_table == NULL)
-		goto out_destroy_wq;
-
 	amd_iommu_register_ppr_notifier(&ppr_nb);
 
 	return 0;
 
-out_destroy_wq:
-	destroy_workqueue(iommu_wq);
-
 out:
 	return ret;
 }
@@ -999,8 +958,6 @@ static void __exit amd_iommu_v2_exit(void)
 	}
 
 	destroy_workqueue(iommu_wq);
-
-	free_page((unsigned long)empty_page_table);
 }
 
 module_init(amd_iommu_v2_init);
diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index a210338cfeb1..808095b452ab 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -11,9 +11,6 @@ menuconfig NEW_LEDS
 	  Say Y to enable Linux LED support.  This allows control of supported
 	  LEDs from both userspace and optionally, by kernel events (triggers).
 
-	  This is not related to standard keyboard LEDs which are controlled
-	  via the input system.
-
 if NEW_LEDS
 
 config LEDS_CLASS
diff --git a/drivers/misc/ti-st/st_core.c b/drivers/misc/ti-st/st_core.c
index 54be83d3efdd..374480cb69bf 100644
--- a/drivers/misc/ti-st/st_core.c
+++ b/drivers/misc/ti-st/st_core.c
@@ -343,7 +343,7 @@ void st_int_recv(void *disc_data,
 			/* Unknow packet? */
 		default:
 			type = *ptr;
-			if (st_gdata->list[type] == NULL) {
+			if (type >= ST_MAX_CHANNELS || st_gdata->list[type] == NULL) {
 				pr_err("chip/interface misbehavior dropping"
 					" frame starting with 0x%02x", type);
 				goto done;
diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c
index 5b2717f5dafa..818ea97f403c 100644
--- a/drivers/rtc/interface.c
+++ b/drivers/rtc/interface.c
@@ -30,6 +30,14 @@ static int __rtc_read_time(struct rtc_device *rtc, struct rtc_time *tm)
 	else {
 		memset(tm, 0, sizeof(struct rtc_time));
 		err = rtc->ops->read_time(rtc->dev.parent, tm);
+		if (err < 0) {
+			dev_err(&rtc->dev, "read_time: fail to read\n");
+			return err;
+		}
+
+		err = rtc_valid_tm(tm);
+		if (err < 0)
+			dev_err(&rtc->dev, "read_time: rtc_time isn't valid\n");
 	}
 	return err;
 }
diff --git a/drivers/rtc/rtc-omap.c b/drivers/rtc/rtc-omap.c
index ae444a8bd602..6755c14b7129 100644
--- a/drivers/rtc/rtc-omap.c
+++ b/drivers/rtc/rtc-omap.c
@@ -1,10 +1,11 @@
 /*
- * TI OMAP1 Real Time Clock interface for Linux
+ * TI OMAP Real Time Clock interface for Linux
  *
  * Copyright (C) 2003 MontaVista Software, Inc.
  * Author: George G. Davis <gdavis@mvista.com> or <source@mvista.com>
  *
  * Copyright (C) 2006 David Brownell (new RTC framework)
+ * Copyright (C) 2014 Johan Hovold <johan@kernel.org>
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
@@ -25,7 +26,8 @@
 #include <linux/pm_runtime.h>
 #include <linux/io.h>
 
-/* The OMAP1 RTC is a year/month/day/hours/minutes/seconds BCD clock
+/*
+ * The OMAP RTC is a year/month/day/hours/minutes/seconds BCD clock
  * with century-range alarm matching, driven by the 32kHz clock.
  *
  * The main user-visible ways it differs from PC RTCs are by omitting
@@ -39,10 +41,6 @@
  * the SoC). See the BOARD-SPECIFIC CUSTOMIZATION comment.
  */
 
-#define	DRIVER_NAME			"omap_rtc"
-
-#define OMAP_RTC_BASE			0xfffb4800
-
 /* RTC registers */
 #define OMAP_RTC_SECONDS_REG		0x00
 #define OMAP_RTC_MINUTES_REG		0x04
@@ -72,6 +70,15 @@
 
 #define OMAP_RTC_IRQWAKEEN		0x7c
 
+#define OMAP_RTC_ALARM2_SECONDS_REG	0x80
+#define OMAP_RTC_ALARM2_MINUTES_REG	0x84
+#define OMAP_RTC_ALARM2_HOURS_REG	0x88
+#define OMAP_RTC_ALARM2_DAYS_REG	0x8c
+#define OMAP_RTC_ALARM2_MONTHS_REG	0x90
+#define OMAP_RTC_ALARM2_YEARS_REG	0x94
+
+#define OMAP_RTC_PMIC_REG		0x98
+
 /* OMAP_RTC_CTRL_REG bit fields: */
 #define OMAP_RTC_CTRL_SPLIT		BIT(7)
 #define OMAP_RTC_CTRL_DISABLE		BIT(6)
@@ -84,6 +91,7 @@
 
 /* OMAP_RTC_STATUS_REG bit fields: */
 #define OMAP_RTC_STATUS_POWER_UP	BIT(7)
+#define OMAP_RTC_STATUS_ALARM2		BIT(7)
 #define OMAP_RTC_STATUS_ALARM		BIT(6)
 #define OMAP_RTC_STATUS_1D_EVENT	BIT(5)
 #define OMAP_RTC_STATUS_1H_EVENT	BIT(4)
@@ -93,6 +101,7 @@
 #define OMAP_RTC_STATUS_BUSY		BIT(0)
 
 /* OMAP_RTC_INTERRUPTS_REG bit fields: */
+#define OMAP_RTC_INTERRUPTS_IT_ALARM2	BIT(4)
 #define OMAP_RTC_INTERRUPTS_IT_ALARM	BIT(3)
 #define OMAP_RTC_INTERRUPTS_IT_TIMER	BIT(2)
 
@@ -102,61 +111,82 @@
 /* OMAP_RTC_IRQWAKEEN bit fields: */
 #define OMAP_RTC_IRQWAKEEN_ALARM_WAKEEN	BIT(1)
 
+/* OMAP_RTC_PMIC bit fields: */
+#define OMAP_RTC_PMIC_POWER_EN_EN	BIT(16)
+
 /* OMAP_RTC_KICKER values */
 #define	KICK0_VALUE			0x83e70b13
 #define	KICK1_VALUE			0x95a4f1e0
 
-#define	OMAP_RTC_HAS_KICKER		BIT(0)
-
-/*
- * Few RTC IP revisions has special WAKE-EN Register to enable Wakeup
- * generation for event Alarm.
- */
-#define	OMAP_RTC_HAS_IRQWAKEEN		BIT(1)
+struct omap_rtc_device_type {
+	bool has_32kclk_en;
+	bool has_kicker;
+	bool has_irqwakeen;
+	bool has_pmic_mode;
+	bool has_power_up_reset;
+};
 
-/*
- * Some RTC IP revisions (like those in AM335x and DRA7x) need
- * the 32KHz clock to be explicitly enabled.
- */
-#define OMAP_RTC_HAS_32KCLK_EN		BIT(2)
+struct omap_rtc {
+	struct rtc_device *rtc;
+	void __iomem *base;
+	int irq_alarm;
+	int irq_timer;
+	u8 interrupts_reg;
+	bool is_pmic_controller;
+	const struct omap_rtc_device_type *type;
+};
 
-static void __iomem	*rtc_base;
+static inline u8 rtc_read(struct omap_rtc *rtc, unsigned int reg)
+{
+	return readb(rtc->base + reg);
+}
 
-#define rtc_read(addr)		readb(rtc_base + (addr))
-#define rtc_write(val, addr)	writeb(val, rtc_base + (addr))
+static inline u32 rtc_readl(struct omap_rtc *rtc, unsigned int reg)
+{
+	return readl(rtc->base + reg);
+}
 
-#define rtc_writel(val, addr)	writel(val, rtc_base + (addr))
+static inline void rtc_write(struct omap_rtc *rtc, unsigned int reg, u8 val)
+{
+	writeb(val, rtc->base + reg);
+}
 
+static inline void rtc_writel(struct omap_rtc *rtc, unsigned int reg, u32 val)
+{
+	writel(val, rtc->base + reg);
+}
 
-/* we rely on the rtc framework to handle locking (rtc->ops_lock),
+/*
+ * We rely on the rtc framework to handle locking (rtc->ops_lock),
  * so the only other requirement is that register accesses which
  * require BUSY to be clear are made with IRQs locally disabled
  */
-static void rtc_wait_not_busy(void)
+static void rtc_wait_not_busy(struct omap_rtc *rtc)
 {
-	int	count = 0;
-	u8	status;
+	int count;
+	u8 status;
 
 	/* BUSY may stay active for 1/32768 second (~30 usec) */
 	for (count = 0; count < 50; count++) {
-		status = rtc_read(OMAP_RTC_STATUS_REG);
-		if ((status & (u8)OMAP_RTC_STATUS_BUSY) == 0)
+		status = rtc_read(rtc, OMAP_RTC_STATUS_REG);
+		if (!(status & OMAP_RTC_STATUS_BUSY))
 			break;
 		udelay(1);
 	}
 	/* now we have ~15 usec to read/write various registers */
 }
 
-static irqreturn_t rtc_irq(int irq, void *rtc)
+static irqreturn_t rtc_irq(int irq, void *dev_id)
 {
-	unsigned long		events = 0;
-	u8			irq_data;
+	struct omap_rtc	*rtc = dev_id;
+	unsigned long events = 0;
+	u8 irq_data;
 
-	irq_data = rtc_read(OMAP_RTC_STATUS_REG);
+	irq_data = rtc_read(rtc, OMAP_RTC_STATUS_REG);
 
 	/* alarm irq? */
 	if (irq_data & OMAP_RTC_STATUS_ALARM) {
-		rtc_write(OMAP_RTC_STATUS_ALARM, OMAP_RTC_STATUS_REG);
+		rtc_write(rtc, OMAP_RTC_STATUS_REG, OMAP_RTC_STATUS_ALARM);
 		events |= RTC_IRQF | RTC_AF;
 	}
 
@@ -164,23 +194,21 @@ static irqreturn_t rtc_irq(int irq, void *rtc)
 	if (irq_data & OMAP_RTC_STATUS_1S_EVENT)
 		events |= RTC_IRQF | RTC_UF;
 
-	rtc_update_irq(rtc, 1, events);
+	rtc_update_irq(rtc->rtc, 1, events);
 
 	return IRQ_HANDLED;
 }
 
 static int omap_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
 {
+	struct omap_rtc *rtc = dev_get_drvdata(dev);
 	u8 reg, irqwake_reg = 0;
-	struct platform_device *pdev = to_platform_device(dev);
-	const struct platform_device_id *id_entry =
-					platform_get_device_id(pdev);
 
 	local_irq_disable();
-	rtc_wait_not_busy();
-	reg = rtc_read(OMAP_RTC_INTERRUPTS_REG);
-	if (id_entry->driver_data & OMAP_RTC_HAS_IRQWAKEEN)
-		irqwake_reg = rtc_read(OMAP_RTC_IRQWAKEEN);
+	rtc_wait_not_busy(rtc);
+	reg = rtc_read(rtc, OMAP_RTC_INTERRUPTS_REG);
+	if (rtc->type->has_irqwakeen)
+		irqwake_reg = rtc_read(rtc, OMAP_RTC_IRQWAKEEN);
 
 	if (enabled) {
 		reg |= OMAP_RTC_INTERRUPTS_IT_ALARM;
@@ -189,10 +217,10 @@ static int omap_rtc_alarm_irq_enable(struct device *dev, unsigned int enabled)
 		reg &= ~OMAP_RTC_INTERRUPTS_IT_ALARM;
 		irqwake_reg &= ~OMAP_RTC_IRQWAKEEN_ALARM_WAKEEN;
 	}
-	rtc_wait_not_busy();
-	rtc_write(reg, OMAP_RTC_INTERRUPTS_REG);
-	if (id_entry->driver_data & OMAP_RTC_HAS_IRQWAKEEN)
-		rtc_write(irqwake_reg, OMAP_RTC_IRQWAKEEN);
+	rtc_wait_not_busy(rtc);
+	rtc_write(rtc, OMAP_RTC_INTERRUPTS_REG, reg);
+	if (rtc->type->has_irqwakeen)
+		rtc_write(rtc, OMAP_RTC_IRQWAKEEN, irqwake_reg);
 	local_irq_enable();
 
 	return 0;
@@ -230,39 +258,47 @@ static void bcd2tm(struct rtc_time *tm)
 	tm->tm_year = bcd2bin(tm->tm_year) + 100;
 }
 
+static void omap_rtc_read_time_raw(struct omap_rtc *rtc, struct rtc_time *tm)
+{
+	tm->tm_sec = rtc_read(rtc, OMAP_RTC_SECONDS_REG);
+	tm->tm_min = rtc_read(rtc, OMAP_RTC_MINUTES_REG);
+	tm->tm_hour = rtc_read(rtc, OMAP_RTC_HOURS_REG);
+	tm->tm_mday = rtc_read(rtc, OMAP_RTC_DAYS_REG);
+	tm->tm_mon = rtc_read(rtc, OMAP_RTC_MONTHS_REG);
+	tm->tm_year = rtc_read(rtc, OMAP_RTC_YEARS_REG);
+}
 
 static int omap_rtc_read_time(struct device *dev, struct rtc_time *tm)
 {
+	struct omap_rtc *rtc = dev_get_drvdata(dev);
+
 	/* we don't report wday/yday/isdst ... */
 	local_irq_disable();
-	rtc_wait_not_busy();
-
-	tm->tm_sec = rtc_read(OMAP_RTC_SECONDS_REG);
-	tm->tm_min = rtc_read(OMAP_RTC_MINUTES_REG);
-	tm->tm_hour = rtc_read(OMAP_RTC_HOURS_REG);
-	tm->tm_mday = rtc_read(OMAP_RTC_DAYS_REG);
-	tm->tm_mon = rtc_read(OMAP_RTC_MONTHS_REG);
-	tm->tm_year = rtc_read(OMAP_RTC_YEARS_REG);
-
+	rtc_wait_not_busy(rtc);
+	omap_rtc_read_time_raw(rtc, tm);
 	local_irq_enable();
 
 	bcd2tm(tm);
+
 	return 0;
 }
 
 static int omap_rtc_set_time(struct device *dev, struct rtc_time *tm)
 {
+	struct omap_rtc *rtc = dev_get_drvdata(dev);
+
 	if (tm2bcd(tm) < 0)
 		return -EINVAL;
+
 	local_irq_disable();
-	rtc_wait_not_busy();
+	rtc_wait_not_busy(rtc);
 
-	rtc_write(tm->tm_year, OMAP_RTC_YEARS_REG);
-	rtc_write(tm->tm_mon, OMAP_RTC_MONTHS_REG);
-	rtc_write(tm->tm_mday, OMAP_RTC_DAYS_REG);
-	rtc_write(tm->tm_hour, OMAP_RTC_HOURS_REG);
-	rtc_write(tm->tm_min, OMAP_RTC_MINUTES_REG);
-	rtc_write(tm->tm_sec, OMAP_RTC_SECONDS_REG);
+	rtc_write(rtc, OMAP_RTC_YEARS_REG, tm->tm_year);
+	rtc_write(rtc, OMAP_RTC_MONTHS_REG, tm->tm_mon);
+	rtc_write(rtc, OMAP_RTC_DAYS_REG, tm->tm_mday);
+	rtc_write(rtc, OMAP_RTC_HOURS_REG, tm->tm_hour);
+	rtc_write(rtc, OMAP_RTC_MINUTES_REG, tm->tm_min);
+	rtc_write(rtc, OMAP_RTC_SECONDS_REG, tm->tm_sec);
 
 	local_irq_enable();
 
@@ -271,48 +307,50 @@ static int omap_rtc_set_time(struct device *dev, struct rtc_time *tm)
 
 static int omap_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alm)
 {
+	struct omap_rtc *rtc = dev_get_drvdata(dev);
+	u8 interrupts;
+
 	local_irq_disable();
-	rtc_wait_not_busy();
+	rtc_wait_not_busy(rtc);
 
-	alm->time.tm_sec = rtc_read(OMAP_RTC_ALARM_SECONDS_REG);
-	alm->time.tm_min = rtc_read(OMAP_RTC_ALARM_MINUTES_REG);
-	alm->time.tm_hour = rtc_read(OMAP_RTC_ALARM_HOURS_REG);
-	alm->time.tm_mday = rtc_read(OMAP_RTC_ALARM_DAYS_REG);
-	alm->time.tm_mon = rtc_read(OMAP_RTC_ALARM_MONTHS_REG);
-	alm->time.tm_year = rtc_read(OMAP_RTC_ALARM_YEARS_REG);
+	alm->time.tm_sec = rtc_read(rtc, OMAP_RTC_ALARM_SECONDS_REG);
+	alm->time.tm_min = rtc_read(rtc, OMAP_RTC_ALARM_MINUTES_REG);
+	alm->time.tm_hour = rtc_read(rtc, OMAP_RTC_ALARM_HOURS_REG);
+	alm->time.tm_mday = rtc_read(rtc, OMAP_RTC_ALARM_DAYS_REG);
+	alm->time.tm_mon = rtc_read(rtc, OMAP_RTC_ALARM_MONTHS_REG);
+	alm->time.tm_year = rtc_read(rtc, OMAP_RTC_ALARM_YEARS_REG);
 
 	local_irq_enable();
 
 	bcd2tm(&alm->time);
-	alm->enabled = !!(rtc_read(OMAP_RTC_INTERRUPTS_REG)
-			& OMAP_RTC_INTERRUPTS_IT_ALARM);
+
+	interrupts = rtc_read(rtc, OMAP_RTC_INTERRUPTS_REG);
+	alm->enabled = !!(interrupts & OMAP_RTC_INTERRUPTS_IT_ALARM);
 
 	return 0;
 }
 
 static int omap_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alm)
 {
+	struct omap_rtc *rtc = dev_get_drvdata(dev);
 	u8 reg, irqwake_reg = 0;
-	struct platform_device *pdev = to_platform_device(dev);
-	const struct platform_device_id *id_entry =
-					platform_get_device_id(pdev);
 
 	if (tm2bcd(&alm->time) < 0)
 		return -EINVAL;
 
 	local_irq_disable();
-	rtc_wait_not_busy();
+	rtc_wait_not_busy(rtc);
 
-	rtc_write(alm->time.tm_year, OMAP_RTC_ALARM_YEARS_REG);
-	rtc_write(alm->time.tm_mon, OMAP_RTC_ALARM_MONTHS_REG);
-	rtc_write(alm->time.tm_mday, OMAP_RTC_ALARM_DAYS_REG);
-	rtc_write(alm->time.tm_hour, OMAP_RTC_ALARM_HOURS_REG);
-	rtc_write(alm->time.tm_min, OMAP_RTC_ALARM_MINUTES_REG);
-	rtc_write(alm->time.tm_sec, OMAP_RTC_ALARM_SECONDS_REG);
+	rtc_write(rtc, OMAP_RTC_ALARM_YEARS_REG, alm->time.tm_year);
+	rtc_write(rtc, OMAP_RTC_ALARM_MONTHS_REG, alm->time.tm_mon);
+	rtc_write(rtc, OMAP_RTC_ALARM_DAYS_REG, alm->time.tm_mday);
+	rtc_write(rtc, OMAP_RTC_ALARM_HOURS_REG, alm->time.tm_hour);
+	rtc_write(rtc, OMAP_RTC_ALARM_MINUTES_REG, alm->time.tm_min);
+	rtc_write(rtc, OMAP_RTC_ALARM_SECONDS_REG, alm->time.tm_sec);
 
-	reg = rtc_read(OMAP_RTC_INTERRUPTS_REG);
-	if (id_entry->driver_data & OMAP_RTC_HAS_IRQWAKEEN)
-		irqwake_reg = rtc_read(OMAP_RTC_IRQWAKEEN);
+	reg = rtc_read(rtc, OMAP_RTC_INTERRUPTS_REG);
+	if (rtc->type->has_irqwakeen)
+		irqwake_reg = rtc_read(rtc, OMAP_RTC_IRQWAKEEN);
 
 	if (alm->enabled) {
 		reg |= OMAP_RTC_INTERRUPTS_IT_ALARM;
@@ -321,15 +359,79 @@ static int omap_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alm)
 		reg &= ~OMAP_RTC_INTERRUPTS_IT_ALARM;
 		irqwake_reg &= ~OMAP_RTC_IRQWAKEEN_ALARM_WAKEEN;
 	}
-	rtc_write(reg, OMAP_RTC_INTERRUPTS_REG);
-	if (id_entry->driver_data & OMAP_RTC_HAS_IRQWAKEEN)
-		rtc_write(irqwake_reg, OMAP_RTC_IRQWAKEEN);
+	rtc_write(rtc, OMAP_RTC_INTERRUPTS_REG, reg);
+	if (rtc->type->has_irqwakeen)
+		rtc_write(rtc, OMAP_RTC_IRQWAKEEN, irqwake_reg);
 
 	local_irq_enable();
 
 	return 0;
 }
 
+static struct omap_rtc *omap_rtc_power_off_rtc;
+
+/*
+ * omap_rtc_poweroff: RTC-controlled power off
+ *
+ * The RTC can be used to control an external PMIC via the pmic_power_en pin,
+ * which can be configured to transition to OFF on ALARM2 events.
+ *
+ * Notes:
+ * The two-second alarm offset is the shortest offset possible as the alarm
+ * registers must be set before the next timer update and the offset
+ * calculation is too heavy for everything to be done within a single access
+ * period (~15 us).
+ *
+ * Called with local interrupts disabled.
+ */
+static void omap_rtc_power_off(void)
+{
+	struct omap_rtc *rtc = omap_rtc_power_off_rtc;
+	struct rtc_time tm;
+	unsigned long now;
+	u32 val;
+
+	/* enable pmic_power_en control */
+	val = rtc_readl(rtc, OMAP_RTC_PMIC_REG);
+	rtc_writel(rtc, OMAP_RTC_PMIC_REG, val | OMAP_RTC_PMIC_POWER_EN_EN);
+
+	/* set alarm two seconds from now */
+	omap_rtc_read_time_raw(rtc, &tm);
+	bcd2tm(&tm);
+	rtc_tm_to_time(&tm, &now);
+	rtc_time_to_tm(now + 2, &tm);
+
+	if (tm2bcd(&tm) < 0) {
+		dev_err(&rtc->rtc->dev, "power off failed\n");
+		return;
+	}
+
+	rtc_wait_not_busy(rtc);
+
+	rtc_write(rtc, OMAP_RTC_ALARM2_SECONDS_REG, tm.tm_sec);
+	rtc_write(rtc, OMAP_RTC_ALARM2_MINUTES_REG, tm.tm_min);
+	rtc_write(rtc, OMAP_RTC_ALARM2_HOURS_REG, tm.tm_hour);
+	rtc_write(rtc, OMAP_RTC_ALARM2_DAYS_REG, tm.tm_mday);
+	rtc_write(rtc, OMAP_RTC_ALARM2_MONTHS_REG, tm.tm_mon);
+	rtc_write(rtc, OMAP_RTC_ALARM2_YEARS_REG, tm.tm_year);
+
+	/*
+	 * enable ALARM2 interrupt
+	 *
+	 * NOTE: this fails on AM3352 if rtc_write (writeb) is used
+	 */
+	val = rtc_read(rtc, OMAP_RTC_INTERRUPTS_REG);
+	rtc_writel(rtc, OMAP_RTC_INTERRUPTS_REG,
+			val | OMAP_RTC_INTERRUPTS_IT_ALARM2);
+
+	/*
+	 * Wait for alarm to trigger (within two seconds) and external PMIC to
+	 * power off the system. Add a 500 ms margin for external latencies
+	 * (e.g. debounce circuits).
+	 */
+	mdelay(2500);
+}
+
 static struct rtc_class_ops omap_rtc_ops = {
 	.read_time	= omap_rtc_read_time,
 	.set_time	= omap_rtc_set_time,
@@ -338,137 +440,140 @@ static struct rtc_class_ops omap_rtc_ops = {
 	.alarm_irq_enable = omap_rtc_alarm_irq_enable,
 };
 
-static int omap_rtc_alarm;
-static int omap_rtc_timer;
+static const struct omap_rtc_device_type omap_rtc_default_type = {
+	.has_power_up_reset = true,
+};
 
-#define	OMAP_RTC_DATA_AM3352_IDX	1
-#define	OMAP_RTC_DATA_DA830_IDX		2
+static const struct omap_rtc_device_type omap_rtc_am3352_type = {
+	.has_32kclk_en	= true,
+	.has_kicker	= true,
+	.has_irqwakeen	= true,
+	.has_pmic_mode	= true,
+};
 
-static struct platform_device_id omap_rtc_devtype[] = {
+static const struct omap_rtc_device_type omap_rtc_da830_type = {
+	.has_kicker	= true,
+};
+
+static const struct platform_device_id omap_rtc_id_table[] = {
 	{
-		.name	= DRIVER_NAME,
-	},
-	[OMAP_RTC_DATA_AM3352_IDX] = {
+		.name	= "omap_rtc",
+		.driver_data = (kernel_ulong_t)&omap_rtc_default_type,
+	}, {
 		.name	= "am3352-rtc",
-		.driver_data = OMAP_RTC_HAS_KICKER | OMAP_RTC_HAS_IRQWAKEEN |
-			       OMAP_RTC_HAS_32KCLK_EN,
-	},
-	[OMAP_RTC_DATA_DA830_IDX] = {
+		.driver_data = (kernel_ulong_t)&omap_rtc_am3352_type,
+	}, {
 		.name	= "da830-rtc",
-		.driver_data = OMAP_RTC_HAS_KICKER,
-	},
-	{},
+		.driver_data = (kernel_ulong_t)&omap_rtc_da830_type,
+	}, {
+		/* sentinel */
+	}
 };
-MODULE_DEVICE_TABLE(platform, omap_rtc_devtype);
+MODULE_DEVICE_TABLE(platform, omap_rtc_id_table);
 
 static const struct of_device_id omap_rtc_of_match[] = {
-	{	.compatible	= "ti,da830-rtc",
-		.data		= &omap_rtc_devtype[OMAP_RTC_DATA_DA830_IDX],
-	},
-	{	.compatible	= "ti,am3352-rtc",
-		.data		= &omap_rtc_devtype[OMAP_RTC_DATA_AM3352_IDX],
-	},
-	{},
+	{
+		.compatible	= "ti,am3352-rtc",
+		.data		= &omap_rtc_am3352_type,
+	}, {
+		.compatible	= "ti,da830-rtc",
+		.data		= &omap_rtc_da830_type,
+	}, {
+		/* sentinel */
+	}
 };
 MODULE_DEVICE_TABLE(of, omap_rtc_of_match);
 
 static int __init omap_rtc_probe(struct platform_device *pdev)
 {
-	struct resource		*res;
-	struct rtc_device	*rtc;
-	u8			reg, new_ctrl;
+	struct omap_rtc	*rtc;
+	struct resource	*res;
+	u8 reg, mask, new_ctrl;
 	const struct platform_device_id *id_entry;
 	const struct of_device_id *of_id;
+	int ret;
 
-	of_id = of_match_device(omap_rtc_of_match, &pdev->dev);
-	if (of_id)
-		pdev->id_entry = of_id->data;
+	rtc = devm_kzalloc(&pdev->dev, sizeof(*rtc), GFP_KERNEL);
+	if (!rtc)
+		return -ENOMEM;
 
-	id_entry = platform_get_device_id(pdev);
-	if (!id_entry) {
-		dev_err(&pdev->dev, "no matching device entry\n");
-		return -ENODEV;
+	of_id = of_match_device(omap_rtc_of_match, &pdev->dev);
+	if (of_id) {
+		rtc->type = of_id->data;
+		rtc->is_pmic_controller = rtc->type->has_pmic_mode &&
+				of_property_read_bool(pdev->dev.of_node,
+						"ti,system-power-controller");
+	} else {
+		id_entry = platform_get_device_id(pdev);
+		rtc->type = (void *)id_entry->driver_data;
 	}
 
-	omap_rtc_timer = platform_get_irq(pdev, 0);
-	if (omap_rtc_timer <= 0) {
-		pr_debug("%s: no update irq?\n", pdev->name);
+	rtc->irq_timer = platform_get_irq(pdev, 0);
+	if (rtc->irq_timer <= 0)
 		return -ENOENT;
-	}
 
-	omap_rtc_alarm = platform_get_irq(pdev, 1);
-	if (omap_rtc_alarm <= 0) {
-		pr_debug("%s: no alarm irq?\n", pdev->name);
+	rtc->irq_alarm = platform_get_irq(pdev, 1);
+	if (rtc->irq_alarm <= 0)
 		return -ENOENT;
-	}
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	rtc_base = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(rtc_base))
-		return PTR_ERR(rtc_base);
+	rtc->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(rtc->base))
+		return PTR_ERR(rtc->base);
+
+	platform_set_drvdata(pdev, rtc);
 
 	/* Enable the clock/module so that we can access the registers */
 	pm_runtime_enable(&pdev->dev);
 	pm_runtime_get_sync(&pdev->dev);
 
-	if (id_entry->driver_data & OMAP_RTC_HAS_KICKER) {
-		rtc_writel(KICK0_VALUE, OMAP_RTC_KICK0_REG);
-		rtc_writel(KICK1_VALUE, OMAP_RTC_KICK1_REG);
-	}
-
-	rtc = devm_rtc_device_register(&pdev->dev, pdev->name,
-			&omap_rtc_ops, THIS_MODULE);
-	if (IS_ERR(rtc)) {
-		pr_debug("%s: can't register RTC device, err %ld\n",
-			pdev->name, PTR_ERR(rtc));
-		goto fail0;
+	if (rtc->type->has_kicker) {
+		rtc_writel(rtc, OMAP_RTC_KICK0_REG, KICK0_VALUE);
+		rtc_writel(rtc, OMAP_RTC_KICK1_REG, KICK1_VALUE);
 	}
-	platform_set_drvdata(pdev, rtc);
 
-	/* clear pending irqs, and set 1/second periodic,
-	 * which we'll use instead of update irqs
+	/*
+	 * disable interrupts
+	 *
+	 * NOTE: ALARM2 is not cleared on AM3352 if rtc_write (writeb) is used
 	 */
-	rtc_write(0, OMAP_RTC_INTERRUPTS_REG);
+	rtc_writel(rtc, OMAP_RTC_INTERRUPTS_REG, 0);
 
 	/* enable RTC functional clock */
-	if (id_entry->driver_data & OMAP_RTC_HAS_32KCLK_EN)
-		rtc_writel(OMAP_RTC_OSC_32KCLK_EN, OMAP_RTC_OSC_REG);
+	if (rtc->type->has_32kclk_en) {
+		reg = rtc_read(rtc, OMAP_RTC_OSC_REG);
+		rtc_writel(rtc, OMAP_RTC_OSC_REG,
+				reg | OMAP_RTC_OSC_32KCLK_EN);
+	}
 
 	/* clear old status */
-	reg = rtc_read(OMAP_RTC_STATUS_REG);
-	if (reg & (u8) OMAP_RTC_STATUS_POWER_UP) {
-		pr_info("%s: RTC power up reset detected\n",
-			pdev->name);
-		rtc_write(OMAP_RTC_STATUS_POWER_UP, OMAP_RTC_STATUS_REG);
-	}
-	if (reg & (u8) OMAP_RTC_STATUS_ALARM)
-		rtc_write(OMAP_RTC_STATUS_ALARM, OMAP_RTC_STATUS_REG);
+	reg = rtc_read(rtc, OMAP_RTC_STATUS_REG);
 
-	/* handle periodic and alarm irqs */
-	if (devm_request_irq(&pdev->dev, omap_rtc_timer, rtc_irq, 0,
-			dev_name(&rtc->dev), rtc)) {
-		pr_debug("%s: RTC timer interrupt IRQ%d already claimed\n",
-			pdev->name, omap_rtc_timer);
-		goto fail0;
-	}
-	if ((omap_rtc_timer != omap_rtc_alarm) &&
-		(devm_request_irq(&pdev->dev, omap_rtc_alarm, rtc_irq, 0,
-			dev_name(&rtc->dev), rtc))) {
-		pr_debug("%s: RTC alarm interrupt IRQ%d already claimed\n",
-			pdev->name, omap_rtc_alarm);
-		goto fail0;
+	mask = OMAP_RTC_STATUS_ALARM;
+
+	if (rtc->type->has_pmic_mode)
+		mask |= OMAP_RTC_STATUS_ALARM2;
+
+	if (rtc->type->has_power_up_reset) {
+		mask |= OMAP_RTC_STATUS_POWER_UP;
+		if (reg & OMAP_RTC_STATUS_POWER_UP)
+			dev_info(&pdev->dev, "RTC power up reset detected\n");
 	}
 
+	if (reg & mask)
+		rtc_write(rtc, OMAP_RTC_STATUS_REG, reg & mask);
+
 	/* On boards with split power, RTC_ON_NOFF won't reset the RTC */
-	reg = rtc_read(OMAP_RTC_CTRL_REG);
-	if (reg & (u8) OMAP_RTC_CTRL_STOP)
-		pr_info("%s: already running\n", pdev->name);
+	reg = rtc_read(rtc, OMAP_RTC_CTRL_REG);
+	if (reg & OMAP_RTC_CTRL_STOP)
+		dev_info(&pdev->dev, "already running\n");
 
 	/* force to 24 hour mode */
-	new_ctrl = reg & (OMAP_RTC_CTRL_SPLIT|OMAP_RTC_CTRL_AUTO_COMP);
+	new_ctrl = reg & (OMAP_RTC_CTRL_SPLIT | OMAP_RTC_CTRL_AUTO_COMP);
 	new_ctrl |= OMAP_RTC_CTRL_STOP;
 
-	/* BOARD-SPECIFIC CUSTOMIZATION CAN GO HERE:
+	/*
+	 * BOARD-SPECIFIC CUSTOMIZATION CAN GO HERE:
 	 *
 	 *  - Device wake-up capability setting should come through chip
 	 *    init logic. OMAP1 boards should initialize the "wakeup capable"
@@ -482,36 +587,70 @@ static int __init omap_rtc_probe(struct platform_device *pdev)
 	 *    is write-only, and always reads as zero...)
 	 */
 
+	if (new_ctrl & OMAP_RTC_CTRL_SPLIT)
+		dev_info(&pdev->dev, "split power mode\n");
+
+	if (reg != new_ctrl)
+		rtc_write(rtc, OMAP_RTC_CTRL_REG, new_ctrl);
+
 	device_init_wakeup(&pdev->dev, true);
 
-	if (new_ctrl & (u8) OMAP_RTC_CTRL_SPLIT)
-		pr_info("%s: split power mode\n", pdev->name);
+	rtc->rtc = devm_rtc_device_register(&pdev->dev, pdev->name,
+			&omap_rtc_ops, THIS_MODULE);
+	if (IS_ERR(rtc->rtc)) {
+		ret = PTR_ERR(rtc->rtc);
+		goto err;
+	}
 
-	if (reg != new_ctrl)
-		rtc_write(new_ctrl, OMAP_RTC_CTRL_REG);
+	/* handle periodic and alarm irqs */
+	ret = devm_request_irq(&pdev->dev, rtc->irq_timer, rtc_irq, 0,
+			dev_name(&rtc->rtc->dev), rtc);
+	if (ret)
+		goto err;
+
+	if (rtc->irq_timer != rtc->irq_alarm) {
+		ret = devm_request_irq(&pdev->dev, rtc->irq_alarm, rtc_irq, 0,
+				dev_name(&rtc->rtc->dev), rtc);
+		if (ret)
+			goto err;
+	}
+
+	if (rtc->is_pmic_controller) {
+		if (!pm_power_off) {
+			omap_rtc_power_off_rtc = rtc;
+			pm_power_off = omap_rtc_power_off;
+		}
+	}
 
 	return 0;
 
-fail0:
-	if (id_entry->driver_data & OMAP_RTC_HAS_KICKER)
-		rtc_writel(0, OMAP_RTC_KICK0_REG);
+err:
+	device_init_wakeup(&pdev->dev, false);
+	if (rtc->type->has_kicker)
+		rtc_writel(rtc, OMAP_RTC_KICK0_REG, 0);
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
-	return -EIO;
+
+	return ret;
 }
 
 static int __exit omap_rtc_remove(struct platform_device *pdev)
 {
-	const struct platform_device_id *id_entry =
-				platform_get_device_id(pdev);
+	struct omap_rtc *rtc = platform_get_drvdata(pdev);
+
+	if (pm_power_off == omap_rtc_power_off &&
+			omap_rtc_power_off_rtc == rtc) {
+		pm_power_off = NULL;
+		omap_rtc_power_off_rtc = NULL;
+	}
 
 	device_init_wakeup(&pdev->dev, 0);
 
 	/* leave rtc running, but disable irqs */
-	rtc_write(0, OMAP_RTC_INTERRUPTS_REG);
+	rtc_write(rtc, OMAP_RTC_INTERRUPTS_REG, 0);
 
-	if (id_entry->driver_data & OMAP_RTC_HAS_KICKER)
-		rtc_writel(0, OMAP_RTC_KICK0_REG);
+	if (rtc->type->has_kicker)
+		rtc_writel(rtc, OMAP_RTC_KICK0_REG, 0);
 
 	/* Disable the clock/module */
 	pm_runtime_put_sync(&pdev->dev);
@@ -521,20 +660,21 @@ static int __exit omap_rtc_remove(struct platform_device *pdev)
 }
 
 #ifdef CONFIG_PM_SLEEP
-static u8 irqstat;
-
 static int omap_rtc_suspend(struct device *dev)
 {
-	irqstat = rtc_read(OMAP_RTC_INTERRUPTS_REG);
+	struct omap_rtc *rtc = dev_get_drvdata(dev);
 
-	/* FIXME the RTC alarm is not currently acting as a wakeup event
+	rtc->interrupts_reg = rtc_read(rtc, OMAP_RTC_INTERRUPTS_REG);
+
+	/*
+	 * FIXME: the RTC alarm is not currently acting as a wakeup event
 	 * source on some platforms, and in fact this enable() call is just
 	 * saving a flag that's never used...
 	 */
 	if (device_may_wakeup(dev))
-		enable_irq_wake(omap_rtc_alarm);
+		enable_irq_wake(rtc->irq_alarm);
 	else
-		rtc_write(0, OMAP_RTC_INTERRUPTS_REG);
+		rtc_write(rtc, OMAP_RTC_INTERRUPTS_REG, 0);
 
 	/* Disable the clock/module */
 	pm_runtime_put_sync(dev);
@@ -544,13 +684,15 @@ static int omap_rtc_suspend(struct device *dev)
 
 static int omap_rtc_resume(struct device *dev)
 {
+	struct omap_rtc *rtc = dev_get_drvdata(dev);
+
 	/* Enable the clock/module so that we can access the registers */
 	pm_runtime_get_sync(dev);
 
 	if (device_may_wakeup(dev))
-		disable_irq_wake(omap_rtc_alarm);
+		disable_irq_wake(rtc->irq_alarm);
 	else
-		rtc_write(irqstat, OMAP_RTC_INTERRUPTS_REG);
+		rtc_write(rtc, OMAP_RTC_INTERRUPTS_REG, rtc->interrupts_reg);
 
 	return 0;
 }
@@ -560,22 +702,31 @@ static SIMPLE_DEV_PM_OPS(omap_rtc_pm_ops, omap_rtc_suspend, omap_rtc_resume);
 
 static void omap_rtc_shutdown(struct platform_device *pdev)
 {
-	rtc_write(0, OMAP_RTC_INTERRUPTS_REG);
+	struct omap_rtc *rtc = platform_get_drvdata(pdev);
+	u8 mask;
+
+	/*
+	 * Keep the ALARM interrupt enabled to allow the system to power up on
+	 * alarm events.
+	 */
+	mask = rtc_read(rtc, OMAP_RTC_INTERRUPTS_REG);
+	mask &= OMAP_RTC_INTERRUPTS_IT_ALARM;
+	rtc_write(rtc, OMAP_RTC_INTERRUPTS_REG, mask);
 }
 
-MODULE_ALIAS("platform:omap_rtc");
 static struct platform_driver omap_rtc_driver = {
 	.remove		= __exit_p(omap_rtc_remove),
 	.shutdown	= omap_rtc_shutdown,
 	.driver		= {
-		.name	= DRIVER_NAME,
+		.name	= "omap_rtc",
 		.pm	= &omap_rtc_pm_ops,
 		.of_match_table = omap_rtc_of_match,
 	},
-	.id_table	= omap_rtc_devtype,
+	.id_table	= omap_rtc_id_table,
 };
 
 module_platform_driver_probe(omap_rtc_driver, omap_rtc_probe);
 
+MODULE_ALIAS("platform:omap_rtc");
 MODULE_AUTHOR("George G. Davis (and others)");
 MODULE_LICENSE("GPL");
diff --git a/drivers/rtc/rtc-pcf8563.c b/drivers/rtc/rtc-pcf8563.c
index c2ef0a22ee94..96fb32e7d6f8 100644
--- a/drivers/rtc/rtc-pcf8563.c
+++ b/drivers/rtc/rtc-pcf8563.c
@@ -28,6 +28,7 @@
 #define PCF8563_REG_ST2		0x01
 #define PCF8563_BIT_AIE		(1 << 1)
 #define PCF8563_BIT_AF		(1 << 3)
+#define PCF8563_BITS_ST2_N	(7 << 5)
 
 #define PCF8563_REG_SC		0x02 /* datetime */
 #define PCF8563_REG_MN		0x03
@@ -41,6 +42,13 @@
 
 #define PCF8563_REG_CLKO	0x0D /* clock out */
 #define PCF8563_REG_TMRC	0x0E /* timer control */
+#define PCF8563_TMRC_ENABLE	BIT(7)
+#define PCF8563_TMRC_4096	0
+#define PCF8563_TMRC_64		1
+#define PCF8563_TMRC_1		2
+#define PCF8563_TMRC_1_60	3
+#define PCF8563_TMRC_MASK	3
+
 #define PCF8563_REG_TMR		0x0F /* timer */
 
 #define PCF8563_SC_LV		0x80 /* low voltage */
@@ -118,22 +126,21 @@ static int pcf8563_write_block_data(struct i2c_client *client,
 
 static int pcf8563_set_alarm_mode(struct i2c_client *client, bool on)
 {
-	unsigned char buf[2];
+	unsigned char buf;
 	int err;
 
-	err = pcf8563_read_block_data(client, PCF8563_REG_ST2, 1, buf + 1);
+	err = pcf8563_read_block_data(client, PCF8563_REG_ST2, 1, &buf);
 	if (err < 0)
 		return err;
 
 	if (on)
-		buf[1] |= PCF8563_BIT_AIE;
+		buf |= PCF8563_BIT_AIE;
 	else
-		buf[1] &= ~PCF8563_BIT_AIE;
+		buf &= ~PCF8563_BIT_AIE;
 
-	buf[1] &= ~PCF8563_BIT_AF;
-	buf[0] = PCF8563_REG_ST2;
+	buf &= ~(PCF8563_BIT_AF | PCF8563_BITS_ST2_N);
 
-	err = pcf8563_write_block_data(client, PCF8563_REG_ST2, 1, buf + 1);
+	err = pcf8563_write_block_data(client, PCF8563_REG_ST2, 1, &buf);
 	if (err < 0) {
 		dev_err(&client->dev, "%s: write error\n", __func__);
 		return -EIO;
@@ -336,8 +343,8 @@ static int pcf8563_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *tm)
 		__func__, buf[0], buf[1], buf[2], buf[3]);
 
 	tm->time.tm_min = bcd2bin(buf[0] & 0x7F);
-	tm->time.tm_hour = bcd2bin(buf[1] & 0x7F);
-	tm->time.tm_mday = bcd2bin(buf[2] & 0x1F);
+	tm->time.tm_hour = bcd2bin(buf[1] & 0x3F);
+	tm->time.tm_mday = bcd2bin(buf[2] & 0x3F);
 	tm->time.tm_wday = bcd2bin(buf[3] & 0x7);
 	tm->time.tm_mon = -1;
 	tm->time.tm_year = -1;
@@ -361,6 +368,14 @@ static int pcf8563_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *tm)
 	struct i2c_client *client = to_i2c_client(dev);
 	unsigned char buf[4];
 	int err;
+	unsigned long alarm_time;
+
+	/* The alarm has no seconds, round up to nearest minute */
+	if (tm->time.tm_sec) {
+		rtc_tm_to_time(&tm->time, &alarm_time);
+		alarm_time += 60-tm->time.tm_sec;
+		rtc_time_to_tm(alarm_time, &tm->time);
+	}
 
 	dev_dbg(dev, "%s, min=%d hour=%d wday=%d mday=%d "
 		"enabled=%d pending=%d\n", __func__,
@@ -381,6 +396,7 @@ static int pcf8563_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *tm)
 
 static int pcf8563_irq_enable(struct device *dev, unsigned int enabled)
 {
+	dev_dbg(dev, "%s: en=%d\n", __func__, enabled);
 	return pcf8563_set_alarm_mode(to_i2c_client(dev), !!enabled);
 }
 
@@ -398,6 +414,8 @@ static int pcf8563_probe(struct i2c_client *client,
 {
 	struct pcf8563 *pcf8563;
 	int err;
+	unsigned char buf;
+	unsigned char alm_pending;
 
 	dev_dbg(&client->dev, "%s\n", __func__);
 
@@ -415,6 +433,22 @@ static int pcf8563_probe(struct i2c_client *client,
 	pcf8563->client = client;
 	device_set_wakeup_capable(&client->dev, 1);
 
+	/* Set timer to lowest frequency to save power (ref Haoyu datasheet) */
+	buf = PCF8563_TMRC_1_60;
+	err = pcf8563_write_block_data(client, PCF8563_REG_TMRC, 1, &buf);
+	if (err < 0) {
+		dev_err(&client->dev, "%s: write error\n", __func__);
+		return err;
+	}
+
+	err = pcf8563_get_alarm_mode(client, NULL, &alm_pending);
+	if (err < 0) {
+		dev_err(&client->dev, "%s: read error\n", __func__);
+		return err;
+	}
+	if (alm_pending)
+		pcf8563_set_alarm_mode(client, 0);
+
 	pcf8563->rtc = devm_rtc_device_register(&client->dev,
 				pcf8563_driver.driver.name,
 				&pcf8563_rtc_ops, THIS_MODULE);
@@ -435,6 +469,9 @@ static int pcf8563_probe(struct i2c_client *client,
 
 	}
 
+	/* the pcf8563 alarm only supports a minute accuracy */
+	pcf8563->rtc->uie_unsupported = 1;
+
 	return 0;
 }
 
diff --git a/drivers/rtc/rtc-sirfsoc.c b/drivers/rtc/rtc-sirfsoc.c
index 52db89e25959..951f3e7ec64c 100644
--- a/drivers/rtc/rtc-sirfsoc.c
+++ b/drivers/rtc/rtc-sirfsoc.c
@@ -209,12 +209,37 @@ static int sirfsoc_rtc_ioctl(struct device *dev, unsigned int cmd,
 	}
 }
 
+static int sirfsoc_rtc_alarm_irq_enable(struct device *dev,
+		unsigned int enabled)
+{
+	unsigned long rtc_status_reg = 0x0;
+	struct sirfsoc_rtc_drv *rtcdrv;
+
+	rtcdrv = dev_get_drvdata(dev);
+
+	local_irq_disable();
+
+	rtc_status_reg = sirfsoc_rtc_iobrg_readl(
+				rtcdrv->rtc_base + RTC_STATUS);
+	if (enabled)
+		rtc_status_reg |= SIRFSOC_RTC_AL0E;
+	else
+		rtc_status_reg &= ~SIRFSOC_RTC_AL0E;
+
+	sirfsoc_rtc_iobrg_writel(rtc_status_reg, rtcdrv->rtc_base + RTC_STATUS);
+	local_irq_enable();
+
+	return 0;
+
+}
+
 static const struct rtc_class_ops sirfsoc_rtc_ops = {
 	.read_time = sirfsoc_rtc_read_time,
 	.set_time = sirfsoc_rtc_set_time,
 	.read_alarm = sirfsoc_rtc_read_alarm,
 	.set_alarm = sirfsoc_rtc_set_alarm,
-	.ioctl = sirfsoc_rtc_ioctl
+	.ioctl = sirfsoc_rtc_ioctl,
+	.alarm_irq_enable = sirfsoc_rtc_alarm_irq_enable
 };
 
 static irqreturn_t sirfsoc_rtc_irq_handler(int irq, void *pdata)
diff --git a/drivers/tty/Kconfig b/drivers/tty/Kconfig
index b24aa010f68c..65cd80bf9aec 100644
--- a/drivers/tty/Kconfig
+++ b/drivers/tty/Kconfig
@@ -13,6 +13,10 @@ config VT
 	bool "Virtual terminal" if EXPERT
 	depends on !S390 && !UML
 	select INPUT
+	select NEW_LEDS
+	select LEDS_CLASS
+	select LEDS_TRIGGERS
+	select INPUT_LEDS
 	default y
 	---help---
 	  If you say Y here, you will get support for terminal devices with
diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c
index c039cfea5b11..9d00088d3ecf 100644
--- a/drivers/tty/vt/keyboard.c
+++ b/drivers/tty/vt/keyboard.c
@@ -33,6 +33,7 @@
 #include <linux/string.h>
 #include <linux/init.h>
 #include <linux/slab.h>
+#include <linux/leds.h>
 
 #include <linux/kbd_kern.h>
 #include <linux/kbd_diacr.h>
@@ -130,6 +131,7 @@ static char rep;					/* flag telling character repeat */
 static int shift_state = 0;
 
 static unsigned char ledstate = 0xff;			/* undefined */
+static unsigned char lockstate = 0xff;			/* undefined */
 static unsigned char ledioctl;
 
 /*
@@ -961,6 +963,41 @@ static void k_brl(struct vc_data *vc, unsigned char value, char up_flag)
 	}
 }
 
+/* We route VT keyboard "leds" through triggers */
+static void kbd_ledstate_trigger_activate(struct led_classdev *cdev);
+
+static struct led_trigger ledtrig_ledstate[] = {
+#define DEFINE_LEDSTATE_TRIGGER(kbd_led, nam) \
+	[kbd_led] = { \
+		.name = nam, \
+		.activate = kbd_ledstate_trigger_activate, \
+	}
+	DEFINE_LEDSTATE_TRIGGER(VC_SCROLLOCK, "kbd-scrollock"),
+	DEFINE_LEDSTATE_TRIGGER(VC_NUMLOCK,   "kbd-numlock"),
+	DEFINE_LEDSTATE_TRIGGER(VC_CAPSLOCK,  "kbd-capslock"),
+	DEFINE_LEDSTATE_TRIGGER(VC_KANALOCK,  "kbd-kanalock"),
+#undef DEFINE_LEDSTATE_TRIGGER
+};
+
+static void kbd_lockstate_trigger_activate(struct led_classdev *cdev);
+
+static struct led_trigger ledtrig_lockstate[] = {
+#define DEFINE_LOCKSTATE_TRIGGER(kbd_led, nam) \
+	[kbd_led] = { \
+		.name = nam, \
+		.activate = kbd_lockstate_trigger_activate, \
+	}
+	DEFINE_LOCKSTATE_TRIGGER(VC_SHIFTLOCK,  "kbd-shiftlock"),
+	DEFINE_LOCKSTATE_TRIGGER(VC_ALTGRLOCK,  "kbd-altgrlock"),
+	DEFINE_LOCKSTATE_TRIGGER(VC_CTRLLOCK,   "kbd-ctrllock"),
+	DEFINE_LOCKSTATE_TRIGGER(VC_ALTLOCK,    "kbd-altlock"),
+	DEFINE_LOCKSTATE_TRIGGER(VC_SHIFTLLOCK, "kbd-shiftllock"),
+	DEFINE_LOCKSTATE_TRIGGER(VC_SHIFTRLOCK, "kbd-shiftrlock"),
+	DEFINE_LOCKSTATE_TRIGGER(VC_CTRLLLOCK,  "kbd-ctrlllock"),
+	DEFINE_LOCKSTATE_TRIGGER(VC_CTRLRLOCK,  "kbd-ctrlrlock"),
+#undef DEFINE_LOCKSTATE_TRIGGER
+};
+
 /*
  * The leds display either (i) the status of NumLock, CapsLock, ScrollLock,
  * or (ii) whatever pattern of lights people want to show using KDSETLED,
@@ -995,18 +1032,25 @@ static inline unsigned char getleds(void)
 	return kb->ledflagstate;
 }
 
-static int kbd_update_leds_helper(struct input_handle *handle, void *data)
+/* Called on trigger connection, to set initial state */
+static void kbd_ledstate_trigger_activate(struct led_classdev *cdev)
 {
-	unsigned char leds = *(unsigned char *)data;
+	struct led_trigger *trigger = cdev->trigger;
+	int led = trigger - ledtrig_ledstate;
 
-	if (test_bit(EV_LED, handle->dev->evbit)) {
-		input_inject_event(handle, EV_LED, LED_SCROLLL, !!(leds & 0x01));
-		input_inject_event(handle, EV_LED, LED_NUML,    !!(leds & 0x02));
-		input_inject_event(handle, EV_LED, LED_CAPSL,   !!(leds & 0x04));
-		input_inject_event(handle, EV_SYN, SYN_REPORT, 0);
-	}
+	tasklet_disable(&keyboard_tasklet);
+	led_trigger_event(trigger, ledstate & (1 << led) ? LED_FULL : LED_OFF);
+	tasklet_enable(&keyboard_tasklet);
+}
 
-	return 0;
+static void kbd_lockstate_trigger_activate(struct led_classdev *cdev)
+{
+	struct led_trigger *trigger = cdev->trigger;
+	int led = trigger - ledtrig_lockstate;
+
+	tasklet_disable(&keyboard_tasklet);
+	led_trigger_event(trigger, lockstate & (1 << led) ? LED_FULL : LED_OFF);
+	tasklet_enable(&keyboard_tasklet);
 }
 
 /**
@@ -1095,16 +1139,29 @@ static void kbd_bh(unsigned long dummy)
 {
 	unsigned char leds;
 	unsigned long flags;
-	
+	int i;
+
 	spin_lock_irqsave(&led_lock, flags);
 	leds = getleds();
 	spin_unlock_irqrestore(&led_lock, flags);
 
 	if (leds != ledstate) {
-		input_handler_for_each_handle(&kbd_handler, &leds,
-					      kbd_update_leds_helper);
+		for (i = 0; i < ARRAY_SIZE(ledtrig_ledstate); i++)
+			if ((leds ^ ledstate) & (1 << i))
+				led_trigger_event(&ledtrig_ledstate[i],
+						leds & (1 << i)
+						? LED_FULL : LED_OFF);
 		ledstate = leds;
 	}
+
+	if (kbd->lockstate != lockstate) {
+		for (i = 0; i < ARRAY_SIZE(ledtrig_lockstate); i++)
+			if ((kbd->lockstate ^ lockstate) & (1 << i))
+				led_trigger_event(&ledtrig_lockstate[i],
+						kbd->lockstate & (1 << i)
+						? LED_FULL : LED_OFF);
+		lockstate = kbd->lockstate;
+	}
 }
 
 DECLARE_TASKLET_DISABLED(keyboard_tasklet, kbd_bh, 0);
@@ -1442,20 +1499,6 @@ static void kbd_disconnect(struct input_handle *handle)
 	kfree(handle);
 }
 
-/*
- * Start keyboard handler on the new keyboard by refreshing LED state to
- * match the rest of the system.
- */
-static void kbd_start(struct input_handle *handle)
-{
-	tasklet_disable(&keyboard_tasklet);
-
-	if (ledstate != 0xff)
-		kbd_update_leds_helper(handle, &ledstate);
-
-	tasklet_enable(&keyboard_tasklet);
-}
-
 static const struct input_device_id kbd_ids[] = {
 	{
 		.flags = INPUT_DEVICE_ID_MATCH_EVBIT,
@@ -1477,7 +1520,6 @@ static struct input_handler kbd_handler = {
 	.match		= kbd_match,
 	.connect	= kbd_connect,
 	.disconnect	= kbd_disconnect,
-	.start		= kbd_start,
 	.name		= "kbd",
 	.id_table	= kbd_ids,
 };
@@ -1501,6 +1543,20 @@ int __init kbd_init(void)
 	if (error)
 		return error;
 
+	for (i = 0; i < ARRAY_SIZE(ledtrig_ledstate); i++) {
+		error = led_trigger_register(&ledtrig_ledstate[i]);
+		if (error)
+			pr_err("error %d while registering trigger %s\n",
+					error, ledtrig_ledstate[i].name);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(ledtrig_lockstate); i++) {
+		error = led_trigger_register(&ledtrig_lockstate[i]);
+		if (error)
+			pr_err("error %d while registering trigger %s\n",
+					error, ledtrig_lockstate[i].name);
+	}
+
 	tasklet_enable(&keyboard_tasklet);
 	tasklet_schedule(&keyboard_tasklet);
 
diff --git a/drivers/usb/storage/debug.c b/drivers/usb/storage/debug.c
index 7ec27201341a..57bf3ad41fb6 100644
--- a/drivers/usb/storage/debug.c
+++ b/drivers/usb/storage/debug.c
@@ -187,7 +187,7 @@ void usb_stor_dbg(const struct us_data *us, const char *fmt, ...)
 
 	va_start(args, fmt);
 
-	dev_vprintk_emit(7, &us->pusb_dev->dev, fmt, args);
+	dev_vprintk_emit(LOGLEVEL_DEBUG, &us->pusb_dev->dev, fmt, args);
 
 	va_end(args);
 }
diff --git a/drivers/video/backlight/backlight.c b/drivers/video/backlight/backlight.c
index bddc8b17a4d8..0ce8823952a8 100644
--- a/drivers/video/backlight/backlight.c
+++ b/drivers/video/backlight/backlight.c
@@ -190,8 +190,6 @@ static ssize_t brightness_store(struct device *dev,
 	}
 	mutex_unlock(&bd->ops_lock);
 
-	backlight_generate_event(bd, BACKLIGHT_UPDATE_SYSFS);
-
 	return rc;
 }
 static DEVICE_ATTR_RW(brightness);
diff --git a/fs/affs/affs.h b/fs/affs/affs.h
index 9bca88159725..ff44ff3ff015 100644
--- a/fs/affs/affs.h
+++ b/fs/affs/affs.h
@@ -135,8 +135,10 @@ extern void	affs_fix_checksum(struct super_block *sb, struct buffer_head *bh);
 extern void	secs_to_datestamp(time_t secs, struct affs_date *ds);
 extern umode_t	prot_to_mode(u32 prot);
 extern void	mode_to_prot(struct inode *inode);
+__printf(3, 4)
 extern void	affs_error(struct super_block *sb, const char *function,
 			   const char *fmt, ...);
+__printf(3, 4)
 extern void	affs_warning(struct super_block *sb, const char *function,
 			     const char *fmt, ...);
 extern bool	affs_nofilenametruncate(const struct dentry *dentry);
diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c
index 937ce8754b24..c852f2fa1710 100644
--- a/fs/affs/amigaffs.c
+++ b/fs/affs/amigaffs.c
@@ -10,8 +10,6 @@
 
 #include "affs.h"
 
-static char ErrorBuffer[256];
-
 /*
  * Functions for accessing Amiga-FFS structures.
  */
@@ -444,30 +442,30 @@ mode_to_prot(struct inode *inode)
 void
 affs_error(struct super_block *sb, const char *function, const char *fmt, ...)
 {
-	va_list	 args;
-
-	va_start(args,fmt);
-	vsnprintf(ErrorBuffer,sizeof(ErrorBuffer),fmt,args);
-	va_end(args);
+	struct va_format vaf;
+	va_list args;
 
-	pr_crit("error (device %s): %s(): %s\n", sb->s_id,
-		function,ErrorBuffer);
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+	pr_crit("error (device %s): %s(): %pV\n", sb->s_id, function, &vaf);
 	if (!(sb->s_flags & MS_RDONLY))
 		pr_warn("Remounting filesystem read-only\n");
 	sb->s_flags |= MS_RDONLY;
+	va_end(args);
 }
 
 void
 affs_warning(struct super_block *sb, const char *function, const char *fmt, ...)
 {
-	va_list	 args;
+	struct va_format vaf;
+	va_list args;
 
-	va_start(args,fmt);
-	vsnprintf(ErrorBuffer,sizeof(ErrorBuffer),fmt,args);
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+	pr_warn("(device %s): %s(): %pV\n", sb->s_id, function, &vaf);
 	va_end(args);
-
-	pr_warn("(device %s): %s(): %s\n", sb->s_id,
-		function,ErrorBuffer);
 }
 
 bool
diff --git a/fs/affs/file.c b/fs/affs/file.c
index 1ed590aafecf..05005bd2621a 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -12,35 +12,14 @@
  *  affs regular file handling primitives
  */
 
+#include <linux/aio.h>
 #include "affs.h"
 
 #if PAGE_SIZE < 4096
 #error PAGE_SIZE must be at least 4096
 #endif
 
-static int affs_grow_extcache(struct inode *inode, u32 lc_idx);
-static struct buffer_head *affs_alloc_extblock(struct inode *inode, struct buffer_head *bh, u32 ext);
-static inline struct buffer_head *affs_get_extblock(struct inode *inode, u32 ext);
 static struct buffer_head *affs_get_extblock_slow(struct inode *inode, u32 ext);
-static int affs_file_open(struct inode *inode, struct file *filp);
-static int affs_file_release(struct inode *inode, struct file *filp);
-
-const struct file_operations affs_file_operations = {
-	.llseek		= generic_file_llseek,
-	.read		= new_sync_read,
-	.read_iter	= generic_file_read_iter,
-	.write		= new_sync_write,
-	.write_iter	= generic_file_write_iter,
-	.mmap		= generic_file_mmap,
-	.open		= affs_file_open,
-	.release	= affs_file_release,
-	.fsync		= affs_file_fsync,
-	.splice_read	= generic_file_splice_read,
-};
-
-const struct inode_operations affs_file_inode_operations = {
-	.setattr	= affs_notify_change,
-};
 
 static int
 affs_file_open(struct inode *inode, struct file *filp)
@@ -355,7 +334,8 @@ affs_get_block(struct inode *inode, sector_t block, struct buffer_head *bh_resul
 
 		/* store new block */
 		if (bh_result->b_blocknr)
-			affs_warning(sb, "get_block", "block already set (%x)", bh_result->b_blocknr);
+			affs_warning(sb, "get_block", "block already set (%lx)",
+				     (unsigned long)bh_result->b_blocknr);
 		AFFS_BLOCK(sb, ext_bh, block) = cpu_to_be32(blocknr);
 		AFFS_HEAD(ext_bh)->block_count = cpu_to_be32(block + 1);
 		affs_adjust_checksum(ext_bh, blocknr - bh_result->b_blocknr + 1);
@@ -377,7 +357,8 @@ affs_get_block(struct inode *inode, sector_t block, struct buffer_head *bh_resul
 	return 0;
 
 err_big:
-	affs_error(inode->i_sb,"get_block","strange block request %d", block);
+	affs_error(inode->i_sb, "get_block", "strange block request %d",
+		   (int)block);
 	return -EIO;
 err_ext:
 	// unlock cache
@@ -412,6 +393,22 @@ static void affs_write_failed(struct address_space *mapping, loff_t to)
 	}
 }
 
+static ssize_t
+affs_direct_IO(int rw, struct kiocb *iocb, struct iov_iter *iter,
+	       loff_t offset)
+{
+	struct file *file = iocb->ki_filp;
+	struct address_space *mapping = file->f_mapping;
+	struct inode *inode = mapping->host;
+	size_t count = iov_iter_count(iter);
+	ssize_t ret;
+
+	ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, affs_get_block);
+	if (ret < 0 && (rw & WRITE))
+		affs_write_failed(mapping, offset + count);
+	return ret;
+}
+
 static int affs_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned flags,
 			struct page **pagep, void **fsdata)
@@ -438,6 +435,7 @@ const struct address_space_operations affs_aops = {
 	.writepage = affs_writepage,
 	.write_begin = affs_write_begin,
 	.write_end = generic_write_end,
+	.direct_IO = affs_direct_IO,
 	.bmap = _affs_bmap
 };
 
@@ -867,8 +865,9 @@ affs_truncate(struct inode *inode)
 	// lock cache
 	ext_bh = affs_get_extblock(inode, ext);
 	if (IS_ERR(ext_bh)) {
-		affs_warning(sb, "truncate", "unexpected read error for ext block %u (%d)",
-			     ext, PTR_ERR(ext_bh));
+		affs_warning(sb, "truncate",
+			     "unexpected read error for ext block %u (%ld)",
+			     (unsigned int)ext, PTR_ERR(ext_bh));
 		return;
 	}
 	if (AFFS_I(inode)->i_lc) {
@@ -914,8 +913,9 @@ affs_truncate(struct inode *inode)
 			struct buffer_head *bh = affs_bread_ino(inode, last_blk, 0);
 			u32 tmp;
 			if (IS_ERR(bh)) {
-				affs_warning(sb, "truncate", "unexpected read error for last block %u (%d)",
-					     ext, PTR_ERR(bh));
+				affs_warning(sb, "truncate",
+					     "unexpected read error for last block %u (%ld)",
+					     (unsigned int)ext, PTR_ERR(bh));
 				return;
 			}
 			tmp = be32_to_cpu(AFFS_DATA_HEAD(bh)->next);
@@ -961,3 +961,19 @@ int affs_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
 	mutex_unlock(&inode->i_mutex);
 	return ret;
 }
+const struct file_operations affs_file_operations = {
+	.llseek		= generic_file_llseek,
+	.read		= new_sync_read,
+	.read_iter	= generic_file_read_iter,
+	.write		= new_sync_write,
+	.write_iter	= generic_file_write_iter,
+	.mmap		= generic_file_mmap,
+	.open		= affs_file_open,
+	.release	= affs_file_release,
+	.fsync		= affs_file_fsync,
+	.splice_read	= generic_file_splice_read,
+};
+
+const struct inode_operations affs_file_inode_operations = {
+	.setattr	= affs_notify_change,
+};
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index b94d1cc9cd30..edf47774b03d 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -269,10 +269,6 @@ more:
 	}
 	ctx->pos++;
 	goto more;
-
-	befs_debug(sb, "<--- %s pos %lld", __func__, ctx->pos);
-
-	return 0;
 }
 
 static struct inode *
diff --git a/fs/binfmt_em86.c b/fs/binfmt_em86.c
index f37b08cea1f7..490538536cb4 100644
--- a/fs/binfmt_em86.c
+++ b/fs/binfmt_em86.c
@@ -42,6 +42,10 @@ static int load_em86(struct linux_binprm *bprm)
 			return -ENOEXEC;
 	}
 
+	/* Need to be able to load the file after exec */
+	if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE)
+		return -ENOENT;
+
 	allow_write_access(bprm->file);
 	fput(bprm->file);
 	bprm->file = NULL;
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index fd8beb9657a2..c04ef1d4f18a 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -1,21 +1,14 @@
 /*
- *  binfmt_misc.c
+ * binfmt_misc.c
  *
- *  Copyright (C) 1997 Richard Günther
+ * Copyright (C) 1997 Richard Günther
  *
- *  binfmt_misc detects binaries via a magic or filename extension and invokes
- *  a specified wrapper. This should obsolete binfmt_java, binfmt_em86 and
- *  binfmt_mz.
- *
- *  1997-04-25 first version
- *  [...]
- *  1997-05-19 cleanup
- *  1997-06-26 hpa: pass the real filename rather than argv[0]
- *  1997-06-30 minor cleanup
- *  1997-08-09 removed extension stripping, locking cleanup
- *  2001-02-28 AV: rewritten into something that resembles C. Original didn't.
+ * binfmt_misc detects binaries via a magic or filename extension and invokes
+ * a specified wrapper. See Documentation/binfmt_misc.txt for more details.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/sched.h>
@@ -30,8 +23,13 @@
 #include <linux/mount.h>
 #include <linux/syscalls.h>
 #include <linux/fs.h>
+#include <linux/uaccess.h>
 
-#include <asm/uaccess.h>
+#ifdef DEBUG
+# define USE_DEBUG 1
+#else
+# define USE_DEBUG 0
+#endif
 
 enum {
 	VERBOSE_STATUS = 1 /* make it zero to save 400 bytes kernel memory */
@@ -41,9 +39,9 @@ static LIST_HEAD(entries);
 static int enabled = 1;
 
 enum {Enabled, Magic};
-#define MISC_FMT_PRESERVE_ARGV0 (1<<31)
-#define MISC_FMT_OPEN_BINARY (1<<30)
-#define MISC_FMT_CREDENTIALS (1<<29)
+#define MISC_FMT_PRESERVE_ARGV0 (1 << 31)
+#define MISC_FMT_OPEN_BINARY (1 << 30)
+#define MISC_FMT_CREDENTIALS (1 << 29)
 
 typedef struct {
 	struct list_head list;
@@ -87,20 +85,24 @@ static Node *check_file(struct linux_binprm *bprm)
 	char *p = strrchr(bprm->interp, '.');
 	struct list_head *l;
 
+	/* Walk all the registered handlers. */
 	list_for_each(l, &entries) {
 		Node *e = list_entry(l, Node, list);
 		char *s;
 		int j;
 
+		/* Make sure this one is currently enabled. */
 		if (!test_bit(Enabled, &e->flags))
 			continue;
 
+		/* Do matching based on extension if applicable. */
 		if (!test_bit(Magic, &e->flags)) {
 			if (p && !strcmp(e->magic, p + 1))
 				return e;
 			continue;
 		}
 
+		/* Do matching based on magic & mask. */
 		s = bprm->buf + e->offset;
 		if (e->mask) {
 			for (j = 0; j < e->size; j++)
@@ -123,7 +125,7 @@ static Node *check_file(struct linux_binprm *bprm)
 static int load_misc_binary(struct linux_binprm *bprm)
 {
 	Node *fmt;
-	struct file * interp_file = NULL;
+	struct file *interp_file = NULL;
 	char iname[BINPRM_BUF_SIZE];
 	const char *iname_addr = iname;
 	int retval;
@@ -131,7 +133,7 @@ static int load_misc_binary(struct linux_binprm *bprm)
 
 	retval = -ENOEXEC;
 	if (!enabled)
-		goto _ret;
+		goto ret;
 
 	/* to keep locking time low, we copy the interpreter string */
 	read_lock(&entries_lock);
@@ -140,25 +142,30 @@ static int load_misc_binary(struct linux_binprm *bprm)
 		strlcpy(iname, fmt->interpreter, BINPRM_BUF_SIZE);
 	read_unlock(&entries_lock);
 	if (!fmt)
-		goto _ret;
+		goto ret;
+
+	/* Need to be able to load the file after exec */
+	if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE)
+		return -ENOENT;
 
 	if (!(fmt->flags & MISC_FMT_PRESERVE_ARGV0)) {
 		retval = remove_arg_zero(bprm);
 		if (retval)
-			goto _ret;
+			goto ret;
 	}
 
 	if (fmt->flags & MISC_FMT_OPEN_BINARY) {
 
 		/* if the binary should be opened on behalf of the
 		 * interpreter than keep it open and assign descriptor
-		 * to it */
- 		fd_binary = get_unused_fd();
- 		if (fd_binary < 0) {
- 			retval = fd_binary;
- 			goto _ret;
- 		}
- 		fd_install(fd_binary, bprm->file);
+		 * to it
+		 */
+		fd_binary = get_unused_fd_flags(0);
+		if (fd_binary < 0) {
+			retval = fd_binary;
+			goto ret;
+		}
+		fd_install(fd_binary, bprm->file);
 
 		/* if the binary is not readable than enforce mm->dumpable=0
 		   regardless of the interpreter's permissions */
@@ -171,32 +178,32 @@ static int load_misc_binary(struct linux_binprm *bprm)
 		bprm->interp_flags |= BINPRM_FLAGS_EXECFD;
 		bprm->interp_data = fd_binary;
 
- 	} else {
- 		allow_write_access(bprm->file);
- 		fput(bprm->file);
- 		bprm->file = NULL;
- 	}
+	} else {
+		allow_write_access(bprm->file);
+		fput(bprm->file);
+		bprm->file = NULL;
+	}
 	/* make argv[1] be the path to the binary */
-	retval = copy_strings_kernel (1, &bprm->interp, bprm);
+	retval = copy_strings_kernel(1, &bprm->interp, bprm);
 	if (retval < 0)
-		goto _error;
+		goto error;
 	bprm->argc++;
 
 	/* add the interp as argv[0] */
-	retval = copy_strings_kernel (1, &iname_addr, bprm);
+	retval = copy_strings_kernel(1, &iname_addr, bprm);
 	if (retval < 0)
-		goto _error;
-	bprm->argc ++;
+		goto error;
+	bprm->argc++;
 
 	/* Update interp in case binfmt_script needs it. */
 	retval = bprm_change_interp(iname, bprm);
 	if (retval < 0)
-		goto _error;
+		goto error;
 
-	interp_file = open_exec (iname);
-	retval = PTR_ERR (interp_file);
-	if (IS_ERR (interp_file))
-		goto _error;
+	interp_file = open_exec(iname);
+	retval = PTR_ERR(interp_file);
+	if (IS_ERR(interp_file))
+		goto error;
 
 	bprm->file = interp_file;
 	if (fmt->flags & MISC_FMT_CREDENTIALS) {
@@ -207,23 +214,23 @@ static int load_misc_binary(struct linux_binprm *bprm)
 		memset(bprm->buf, 0, BINPRM_BUF_SIZE);
 		retval = kernel_read(bprm->file, 0, bprm->buf, BINPRM_BUF_SIZE);
 	} else
-		retval = prepare_binprm (bprm);
+		retval = prepare_binprm(bprm);
 
 	if (retval < 0)
-		goto _error;
+		goto error;
 
 	retval = search_binary_handler(bprm);
 	if (retval < 0)
-		goto _error;
+		goto error;
 
-_ret:
+ret:
 	return retval;
-_error:
+error:
 	if (fd_binary > 0)
 		sys_close(fd_binary);
 	bprm->interp_flags = 0;
 	bprm->interp_data = 0;
-	goto _ret;
+	goto ret;
 }
 
 /* Command parsers */
@@ -250,36 +257,40 @@ static char *scanarg(char *s, char del)
 	return s;
 }
 
-static char * check_special_flags (char * sfs, Node * e)
+static char *check_special_flags(char *sfs, Node *e)
 {
-	char * p = sfs;
+	char *p = sfs;
 	int cont = 1;
 
 	/* special flags */
 	while (cont) {
 		switch (*p) {
-			case 'P':
-				p++;
-				e->flags |= MISC_FMT_PRESERVE_ARGV0;
-				break;
-			case 'O':
-				p++;
-				e->flags |= MISC_FMT_OPEN_BINARY;
-				break;
-			case 'C':
-				p++;
-				/* this flags also implies the
-				   open-binary flag */
-				e->flags |= (MISC_FMT_CREDENTIALS |
-						MISC_FMT_OPEN_BINARY);
-				break;
-			default:
-				cont = 0;
+		case 'P':
+			pr_debug("register: flag: P (preserve argv0)\n");
+			p++;
+			e->flags |= MISC_FMT_PRESERVE_ARGV0;
+			break;
+		case 'O':
+			pr_debug("register: flag: O (open binary)\n");
+			p++;
+			e->flags |= MISC_FMT_OPEN_BINARY;
+			break;
+		case 'C':
+			pr_debug("register: flag: C (preserve creds)\n");
+			p++;
+			/* this flags also implies the
+			   open-binary flag */
+			e->flags |= (MISC_FMT_CREDENTIALS |
+					MISC_FMT_OPEN_BINARY);
+			break;
+		default:
+			cont = 0;
 		}
 	}
 
 	return p;
 }
+
 /*
  * This registers a new binary format, it recognises the syntax
  * ':name:type:offset:magic:mask:interpreter:flags'
@@ -292,6 +303,8 @@ static Node *create_entry(const char __user *buffer, size_t count)
 	char *buf, *p;
 	char del;
 
+	pr_debug("register: received %zu bytes\n", count);
+
 	/* some sanity checks */
 	err = -EINVAL;
 	if ((count < 11) || (count > MAX_REGISTER_LENGTH))
@@ -299,7 +312,7 @@ static Node *create_entry(const char __user *buffer, size_t count)
 
 	err = -ENOMEM;
 	memsize = sizeof(Node) + count + 8;
-	e = kmalloc(memsize, GFP_USER);
+	e = kmalloc(memsize, GFP_KERNEL);
 	if (!e)
 		goto out;
 
@@ -307,98 +320,175 @@ static Node *create_entry(const char __user *buffer, size_t count)
 
 	memset(e, 0, sizeof(Node));
 	if (copy_from_user(buf, buffer, count))
-		goto Efault;
+		goto efault;
 
 	del = *p++;	/* delimeter */
 
-	memset(buf+count, del, 8);
+	pr_debug("register: delim: %#x {%c}\n", del, del);
+
+	/* Pad the buffer with the delim to simplify parsing below. */
+	memset(buf + count, del, 8);
 
+	/* Parse the 'name' field. */
 	e->name = p;
 	p = strchr(p, del);
 	if (!p)
-		goto Einval;
+		goto einval;
 	*p++ = '\0';
 	if (!e->name[0] ||
 	    !strcmp(e->name, ".") ||
 	    !strcmp(e->name, "..") ||
 	    strchr(e->name, '/'))
-		goto Einval;
+		goto einval;
+
+	pr_debug("register: name: {%s}\n", e->name);
+
+	/* Parse the 'type' field. */
 	switch (*p++) {
-		case 'E': e->flags = 1<<Enabled; break;
-		case 'M': e->flags = (1<<Enabled) | (1<<Magic); break;
-		default: goto Einval;
+	case 'E':
+		pr_debug("register: type: E (extension)\n");
+		e->flags = 1 << Enabled;
+		break;
+	case 'M':
+		pr_debug("register: type: M (magic)\n");
+		e->flags = (1 << Enabled) | (1 << Magic);
+		break;
+	default:
+		goto einval;
 	}
 	if (*p++ != del)
-		goto Einval;
+		goto einval;
+
 	if (test_bit(Magic, &e->flags)) {
-		char *s = strchr(p, del);
+		/* Handle the 'M' (magic) format. */
+		char *s;
+
+		/* Parse the 'offset' field. */
+		s = strchr(p, del);
 		if (!s)
-			goto Einval;
+			goto einval;
 		*s++ = '\0';
 		e->offset = simple_strtoul(p, &p, 10);
 		if (*p++)
-			goto Einval;
+			goto einval;
+		pr_debug("register: offset: %#x\n", e->offset);
+
+		/* Parse the 'magic' field. */
 		e->magic = p;
 		p = scanarg(p, del);
 		if (!p)
-			goto Einval;
+			goto einval;
 		p[-1] = '\0';
-		if (!e->magic[0])
-			goto Einval;
+		if (p == e->magic)
+			goto einval;
+		if (USE_DEBUG)
+			print_hex_dump_bytes(
+				KBUILD_MODNAME ": register: magic[raw]: ",
+				DUMP_PREFIX_NONE, e->magic, p - e->magic);
+
+		/* Parse the 'mask' field. */
 		e->mask = p;
 		p = scanarg(p, del);
 		if (!p)
-			goto Einval;
+			goto einval;
 		p[-1] = '\0';
-		if (!e->mask[0])
+		if (p == e->mask) {
 			e->mask = NULL;
+			pr_debug("register:  mask[raw]: none\n");
+		} else if (USE_DEBUG)
+			print_hex_dump_bytes(
+				KBUILD_MODNAME ": register:  mask[raw]: ",
+				DUMP_PREFIX_NONE, e->mask, p - e->mask);
+
+		/*
+		 * Decode the magic & mask fields.
+		 * Note: while we might have accepted embedded NUL bytes from
+		 * above, the unescape helpers here will stop at the first one
+		 * it encounters.
+		 */
 		e->size = string_unescape_inplace(e->magic, UNESCAPE_HEX);
 		if (e->mask &&
 		    string_unescape_inplace(e->mask, UNESCAPE_HEX) != e->size)
-			goto Einval;
+			goto einval;
 		if (e->size + e->offset > BINPRM_BUF_SIZE)
-			goto Einval;
+			goto einval;
+		pr_debug("register: magic/mask length: %i\n", e->size);
+		if (USE_DEBUG) {
+			print_hex_dump_bytes(
+				KBUILD_MODNAME ": register: magic[decoded]: ",
+				DUMP_PREFIX_NONE, e->magic, e->size);
+
+			if (e->mask) {
+				int i;
+				char *masked = kmalloc(e->size, GFP_KERNEL);
+
+				print_hex_dump_bytes(
+					KBUILD_MODNAME ": register:  mask[decoded]: ",
+					DUMP_PREFIX_NONE, e->mask, e->size);
+
+				if (masked) {
+					for (i = 0; i < e->size; ++i)
+						masked[i] = e->magic[i] & e->mask[i];
+					print_hex_dump_bytes(
+						KBUILD_MODNAME ": register:  magic[masked]: ",
+						DUMP_PREFIX_NONE, masked, e->size);
+
+					kfree(masked);
+				}
+			}
+		}
 	} else {
+		/* Handle the 'E' (extension) format. */
+
+		/* Skip the 'offset' field. */
 		p = strchr(p, del);
 		if (!p)
-			goto Einval;
+			goto einval;
 		*p++ = '\0';
+
+		/* Parse the 'magic' field. */
 		e->magic = p;
 		p = strchr(p, del);
 		if (!p)
-			goto Einval;
+			goto einval;
 		*p++ = '\0';
 		if (!e->magic[0] || strchr(e->magic, '/'))
-			goto Einval;
+			goto einval;
+		pr_debug("register: extension: {%s}\n", e->magic);
+
+		/* Skip the 'mask' field. */
 		p = strchr(p, del);
 		if (!p)
-			goto Einval;
+			goto einval;
 		*p++ = '\0';
 	}
+
+	/* Parse the 'interpreter' field. */
 	e->interpreter = p;
 	p = strchr(p, del);
 	if (!p)
-		goto Einval;
+		goto einval;
 	*p++ = '\0';
 	if (!e->interpreter[0])
-		goto Einval;
-
-
-	p = check_special_flags (p, e);
+		goto einval;
+	pr_debug("register: interpreter: {%s}\n", e->interpreter);
 
+	/* Parse the 'flags' field. */
+	p = check_special_flags(p, e);
 	if (*p == '\n')
 		p++;
 	if (p != buf + count)
-		goto Einval;
+		goto einval;
+
 	return e;
 
 out:
 	return ERR_PTR(err);
 
-Efault:
+efault:
 	kfree(e);
 	return ERR_PTR(-EFAULT);
-Einval:
+einval:
 	kfree(e);
 	return ERR_PTR(-EINVAL);
 }
@@ -417,7 +507,7 @@ static int parse_command(const char __user *buffer, size_t count)
 		return -EFAULT;
 	if (!count)
 		return 0;
-	if (s[count-1] == '\n')
+	if (s[count - 1] == '\n')
 		count--;
 	if (count == 1 && s[0] == '0')
 		return 1;
@@ -434,7 +524,7 @@ static void entry_status(Node *e, char *page)
 {
 	char *dp;
 	char *status = "disabled";
-	const char * flags = "flags: ";
+	const char *flags = "flags: ";
 
 	if (test_bit(Enabled, &e->flags))
 		status = "enabled";
@@ -448,19 +538,15 @@ static void entry_status(Node *e, char *page)
 	dp = page + strlen(page);
 
 	/* print the special flags */
-	sprintf (dp, "%s", flags);
-	dp += strlen (flags);
-	if (e->flags & MISC_FMT_PRESERVE_ARGV0) {
-		*dp ++ = 'P';
-	}
-	if (e->flags & MISC_FMT_OPEN_BINARY) {
-		*dp ++ = 'O';
-	}
-	if (e->flags & MISC_FMT_CREDENTIALS) {
-		*dp ++ = 'C';
-	}
-	*dp ++ = '\n';
-
+	sprintf(dp, "%s", flags);
+	dp += strlen(flags);
+	if (e->flags & MISC_FMT_PRESERVE_ARGV0)
+		*dp++ = 'P';
+	if (e->flags & MISC_FMT_OPEN_BINARY)
+		*dp++ = 'O';
+	if (e->flags & MISC_FMT_CREDENTIALS)
+		*dp++ = 'C';
+	*dp++ = '\n';
 
 	if (!test_bit(Magic, &e->flags)) {
 		sprintf(dp, "extension .%s\n", e->magic);
@@ -488,7 +574,7 @@ static void entry_status(Node *e, char *page)
 
 static struct inode *bm_get_inode(struct super_block *sb, int mode)
 {
-	struct inode * inode = new_inode(sb);
+	struct inode *inode = new_inode(sb);
 
 	if (inode) {
 		inode->i_ino = get_next_ino();
@@ -528,13 +614,14 @@ static void kill_node(Node *e)
 /* /<entry> */
 
 static ssize_t
-bm_entry_read(struct file * file, char __user * buf, size_t nbytes, loff_t *ppos)
+bm_entry_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
 {
 	Node *e = file_inode(file)->i_private;
 	ssize_t res;
 	char *page;
 
-	if (!(page = (char*) __get_free_page(GFP_KERNEL)))
+	page = (char *) __get_free_page(GFP_KERNEL);
+	if (!page)
 		return -ENOMEM;
 
 	entry_status(e, page);
@@ -553,20 +640,28 @@ static ssize_t bm_entry_write(struct file *file, const char __user *buffer,
 	int res = parse_command(buffer, count);
 
 	switch (res) {
-		case 1: clear_bit(Enabled, &e->flags);
-			break;
-		case 2: set_bit(Enabled, &e->flags);
-			break;
-		case 3: root = dget(file->f_path.dentry->d_sb->s_root);
-			mutex_lock(&root->d_inode->i_mutex);
-
-			kill_node(e);
-
-			mutex_unlock(&root->d_inode->i_mutex);
-			dput(root);
-			break;
-		default: return res;
+	case 1:
+		/* Disable this handler. */
+		clear_bit(Enabled, &e->flags);
+		break;
+	case 2:
+		/* Enable this handler. */
+		set_bit(Enabled, &e->flags);
+		break;
+	case 3:
+		/* Delete this handler. */
+		root = dget(file->f_path.dentry->d_sb->s_root);
+		mutex_lock(&root->d_inode->i_mutex);
+
+		kill_node(e);
+
+		mutex_unlock(&root->d_inode->i_mutex);
+		dput(root);
+		break;
+	default:
+		return res;
 	}
+
 	return count;
 }
 
@@ -654,26 +749,36 @@ bm_status_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
 	return simple_read_from_buffer(buf, nbytes, ppos, s, strlen(s));
 }
 
-static ssize_t bm_status_write(struct file * file, const char __user * buffer,
+static ssize_t bm_status_write(struct file *file, const char __user *buffer,
 		size_t count, loff_t *ppos)
 {
 	int res = parse_command(buffer, count);
 	struct dentry *root;
 
 	switch (res) {
-		case 1: enabled = 0; break;
-		case 2: enabled = 1; break;
-		case 3: root = dget(file->f_path.dentry->d_sb->s_root);
-			mutex_lock(&root->d_inode->i_mutex);
-
-			while (!list_empty(&entries))
-				kill_node(list_entry(entries.next, Node, list));
-
-			mutex_unlock(&root->d_inode->i_mutex);
-			dput(root);
-			break;
-		default: return res;
+	case 1:
+		/* Disable all handlers. */
+		enabled = 0;
+		break;
+	case 2:
+		/* Enable all handlers. */
+		enabled = 1;
+		break;
+	case 3:
+		/* Delete all handlers. */
+		root = dget(file->f_path.dentry->d_sb->s_root);
+		mutex_lock(&root->d_inode->i_mutex);
+
+		while (!list_empty(&entries))
+			kill_node(list_entry(entries.next, Node, list));
+
+		mutex_unlock(&root->d_inode->i_mutex);
+		dput(root);
+		break;
+	default:
+		return res;
 	}
+
 	return count;
 }
 
@@ -690,14 +795,16 @@ static const struct super_operations s_ops = {
 	.evict_inode	= bm_evict_inode,
 };
 
-static int bm_fill_super(struct super_block * sb, void * data, int silent)
+static int bm_fill_super(struct super_block *sb, void *data, int silent)
 {
+	int err;
 	static struct tree_descr bm_files[] = {
 		[2] = {"status", &bm_status_operations, S_IWUSR|S_IRUGO},
 		[3] = {"register", &bm_register_operations, S_IWUSR},
 		/* last one */ {""}
 	};
-	int err = simple_fill_super(sb, BINFMTFS_MAGIC, bm_files);
+
+	err = simple_fill_super(sb, BINFMTFS_MAGIC, bm_files);
 	if (!err)
 		sb->s_op = &s_ops;
 	return err;
diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c
index 5027a3e14922..afdf4e3cafc2 100644
--- a/fs/binfmt_script.c
+++ b/fs/binfmt_script.c
@@ -24,6 +24,16 @@ static int load_script(struct linux_binprm *bprm)
 
 	if ((bprm->buf[0] != '#') || (bprm->buf[1] != '!'))
 		return -ENOEXEC;
+
+	/*
+	 * If the script filename will be inaccessible after exec, typically
+	 * because it is a "/dev/fd/<fd>/.." path against an O_CLOEXEC fd, give
+	 * up now (on the assumption that the interpreter will want to load
+	 * this file).
+	 */
+	if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE)
+		return -ENOENT;
+
 	/*
 	 * This section does the #! interpretation.
 	 * Sorta complicated, but hopefully it will work.  -TYT
diff --git a/fs/char_dev.c b/fs/char_dev.c
index f77f7702fabe..67b2007f10fe 100644
--- a/fs/char_dev.c
+++ b/fs/char_dev.c
@@ -117,7 +117,6 @@ __register_chrdev_region(unsigned int major, unsigned int baseminor,
 			goto out;
 		}
 		major = i;
-		ret = major;
 	}
 
 	cd->major = major;
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 6d00c419cbae..1ea780bc6376 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -38,7 +38,7 @@ static const struct cifs_sid sid_everyone = {
 	1, 1, {0, 0, 0, 0, 0, 1}, {0} };
 /* security id for Authenticated Users system group */
 static const struct cifs_sid sid_authusers = {
-	1, 1, {0, 0, 0, 0, 0, 5}, {__constant_cpu_to_le32(11)} };
+	1, 1, {0, 0, 0, 0, 0, 5}, {cpu_to_le32(11)} };
 /* group users */
 static const struct cifs_sid sid_user = {1, 2 , {0, 0, 0, 0, 0, 5}, {} };
 
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 61d00a6e398f..fa13d5e79f64 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -2477,14 +2477,14 @@ CIFSSMBPosixLock(const unsigned int xid, struct cifs_tcon *tcon,
 		}
 		parm_data = (struct cifs_posix_lock *)
 			((char *)&pSMBr->hdr.Protocol + data_offset);
-		if (parm_data->lock_type == __constant_cpu_to_le16(CIFS_UNLCK))
+		if (parm_data->lock_type == cpu_to_le16(CIFS_UNLCK))
 			pLockData->fl_type = F_UNLCK;
 		else {
 			if (parm_data->lock_type ==
-					__constant_cpu_to_le16(CIFS_RDLCK))
+					cpu_to_le16(CIFS_RDLCK))
 				pLockData->fl_type = F_RDLCK;
 			else if (parm_data->lock_type ==
-					__constant_cpu_to_le16(CIFS_WRLCK))
+					cpu_to_le16(CIFS_WRLCK))
 				pLockData->fl_type = F_WRLCK;
 
 			pLockData->fl_start = le64_to_cpu(parm_data->start);
@@ -3276,25 +3276,25 @@ CIFSSMB_set_compression(const unsigned int xid, struct cifs_tcon *tcon,
 	pSMB->compression_state = cpu_to_le16(COMPRESSION_FORMAT_DEFAULT);
 
 	pSMB->TotalParameterCount = 0;
-	pSMB->TotalDataCount = __constant_cpu_to_le32(2);
+	pSMB->TotalDataCount = cpu_to_le32(2);
 	pSMB->MaxParameterCount = 0;
 	pSMB->MaxDataCount = 0;
 	pSMB->MaxSetupCount = 4;
 	pSMB->Reserved = 0;
 	pSMB->ParameterOffset = 0;
-	pSMB->DataCount = __constant_cpu_to_le32(2);
+	pSMB->DataCount = cpu_to_le32(2);
 	pSMB->DataOffset =
 		cpu_to_le32(offsetof(struct smb_com_transaction_compr_ioctl_req,
 				compression_state) - 4);  /* 84 */
 	pSMB->SetupCount = 4;
-	pSMB->SubCommand = __constant_cpu_to_le16(NT_TRANSACT_IOCTL);
+	pSMB->SubCommand = cpu_to_le16(NT_TRANSACT_IOCTL);
 	pSMB->ParameterCount = 0;
-	pSMB->FunctionCode = __constant_cpu_to_le32(FSCTL_SET_COMPRESSION);
+	pSMB->FunctionCode = cpu_to_le32(FSCTL_SET_COMPRESSION);
 	pSMB->IsFsctl = 1; /* FSCTL */
 	pSMB->IsRootFlag = 0;
 	pSMB->Fid = fid; /* file handle always le */
 	/* 3 byte pad, followed by 2 byte compress state */
-	pSMB->ByteCount = __constant_cpu_to_le16(5);
+	pSMB->ByteCount = cpu_to_le16(5);
 	inc_rfc1001_len(pSMB, 5);
 
 	rc = SendReceive(xid, tcon->ses, (struct smb_hdr *) pSMB,
@@ -3430,10 +3430,10 @@ static __u16 ACL_to_cifs_posix(char *parm_data, const char *pACL,
 	cifs_acl->version = cpu_to_le16(1);
 	if (acl_type == ACL_TYPE_ACCESS) {
 		cifs_acl->access_entry_count = cpu_to_le16(count);
-		cifs_acl->default_entry_count = __constant_cpu_to_le16(0xFFFF);
+		cifs_acl->default_entry_count = cpu_to_le16(0xFFFF);
 	} else if (acl_type == ACL_TYPE_DEFAULT) {
 		cifs_acl->default_entry_count = cpu_to_le16(count);
-		cifs_acl->access_entry_count = __constant_cpu_to_le16(0xFFFF);
+		cifs_acl->access_entry_count = cpu_to_le16(0xFFFF);
 	} else {
 		cifs_dbg(FYI, "unknown ACL type %d\n", acl_type);
 		return 0;
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index d535e168a9d3..96b7e9b7706d 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -1066,7 +1066,7 @@ cifs_push_mandatory_locks(struct cifsFileInfo *cfile)
 
 	max_num = (max_buf - sizeof(struct smb_hdr)) /
 						sizeof(LOCKING_ANDX_RANGE);
-	buf = kzalloc(max_num * sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL);
+	buf = kcalloc(max_num, sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL);
 	if (!buf) {
 		free_xid(xid);
 		return -ENOMEM;
@@ -1401,7 +1401,7 @@ cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock,
 
 	max_num = (max_buf - sizeof(struct smb_hdr)) /
 						sizeof(LOCKING_ANDX_RANGE);
-	buf = kzalloc(max_num * sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL);
+	buf = kcalloc(max_num, sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index 57db63ff88da..ab0fda6e8e58 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -46,7 +46,7 @@ static __u32 cifs_ssetup_hdr(struct cifs_ses *ses, SESSION_SETUP_ANDX *pSMB)
 					CIFSMaxBufSize + MAX_CIFS_HDR_SIZE - 4,
 					USHRT_MAX));
 	pSMB->req.MaxMpxCount = cpu_to_le16(ses->server->maxReq);
-	pSMB->req.VcNumber = __constant_cpu_to_le16(1);
+	pSMB->req.VcNumber = cpu_to_le16(1);
 
 	/* Now no need to set SMBFLG_CASELESS or obsolete CANONICAL PATH */
 
diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c
index 45992944e238..7198eac5dddd 100644
--- a/fs/cifs/smb2file.c
+++ b/fs/cifs/smb2file.c
@@ -111,7 +111,7 @@ smb2_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock,
 		return -EINVAL;
 
 	max_num = max_buf / sizeof(struct smb2_lock_element);
-	buf = kzalloc(max_num * sizeof(struct smb2_lock_element), GFP_KERNEL);
+	buf = kcalloc(max_num, sizeof(struct smb2_lock_element), GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
@@ -247,7 +247,7 @@ smb2_push_mandatory_locks(struct cifsFileInfo *cfile)
 	}
 
 	max_num = max_buf / sizeof(struct smb2_lock_element);
-	buf = kzalloc(max_num * sizeof(struct smb2_lock_element), GFP_KERNEL);
+	buf = kcalloc(max_num, sizeof(struct smb2_lock_element), GFP_KERNEL);
 	if (!buf) {
 		free_xid(xid);
 		return -ENOMEM;
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index 1a08a34838fc..f1cefc9763ed 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -67,27 +67,27 @@ check_smb2_hdr(struct smb2_hdr *hdr, __u64 mid)
  *  indexed by command in host byte order
  */
 static const __le16 smb2_rsp_struct_sizes[NUMBER_OF_SMB2_COMMANDS] = {
-	/* SMB2_NEGOTIATE */ __constant_cpu_to_le16(65),
-	/* SMB2_SESSION_SETUP */ __constant_cpu_to_le16(9),
-	/* SMB2_LOGOFF */ __constant_cpu_to_le16(4),
-	/* SMB2_TREE_CONNECT */ __constant_cpu_to_le16(16),
-	/* SMB2_TREE_DISCONNECT */ __constant_cpu_to_le16(4),
-	/* SMB2_CREATE */ __constant_cpu_to_le16(89),
-	/* SMB2_CLOSE */ __constant_cpu_to_le16(60),
-	/* SMB2_FLUSH */ __constant_cpu_to_le16(4),
-	/* SMB2_READ */ __constant_cpu_to_le16(17),
-	/* SMB2_WRITE */ __constant_cpu_to_le16(17),
-	/* SMB2_LOCK */ __constant_cpu_to_le16(4),
-	/* SMB2_IOCTL */ __constant_cpu_to_le16(49),
+	/* SMB2_NEGOTIATE */ cpu_to_le16(65),
+	/* SMB2_SESSION_SETUP */ cpu_to_le16(9),
+	/* SMB2_LOGOFF */ cpu_to_le16(4),
+	/* SMB2_TREE_CONNECT */ cpu_to_le16(16),
+	/* SMB2_TREE_DISCONNECT */ cpu_to_le16(4),
+	/* SMB2_CREATE */ cpu_to_le16(89),
+	/* SMB2_CLOSE */ cpu_to_le16(60),
+	/* SMB2_FLUSH */ cpu_to_le16(4),
+	/* SMB2_READ */ cpu_to_le16(17),
+	/* SMB2_WRITE */ cpu_to_le16(17),
+	/* SMB2_LOCK */ cpu_to_le16(4),
+	/* SMB2_IOCTL */ cpu_to_le16(49),
 	/* BB CHECK this ... not listed in documentation */
-	/* SMB2_CANCEL */ __constant_cpu_to_le16(0),
-	/* SMB2_ECHO */ __constant_cpu_to_le16(4),
-	/* SMB2_QUERY_DIRECTORY */ __constant_cpu_to_le16(9),
-	/* SMB2_CHANGE_NOTIFY */ __constant_cpu_to_le16(9),
-	/* SMB2_QUERY_INFO */ __constant_cpu_to_le16(9),
-	/* SMB2_SET_INFO */ __constant_cpu_to_le16(2),
+	/* SMB2_CANCEL */ cpu_to_le16(0),
+	/* SMB2_ECHO */ cpu_to_le16(4),
+	/* SMB2_QUERY_DIRECTORY */ cpu_to_le16(9),
+	/* SMB2_CHANGE_NOTIFY */ cpu_to_le16(9),
+	/* SMB2_QUERY_INFO */ cpu_to_le16(9),
+	/* SMB2_SET_INFO */ cpu_to_le16(2),
 	/* BB FIXME can also be 44 for lease break */
-	/* SMB2_OPLOCK_BREAK */ __constant_cpu_to_le16(24)
+	/* SMB2_OPLOCK_BREAK */ cpu_to_le16(24)
 };
 
 int
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 568f323665c8..93fd0586f9ec 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -600,7 +600,7 @@ smb2_clone_range(const unsigned int xid,
 		goto cchunk_out;
 
 	/* For now array only one chunk long, will make more flexible later */
-	pcchunk->ChunkCount = __constant_cpu_to_le32(1);
+	pcchunk->ChunkCount = cpu_to_le32(1);
 	pcchunk->Reserved = 0;
 	pcchunk->Reserved2 = 0;
 
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 0ca7f6364754..3417340bf89e 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -1358,7 +1358,7 @@ SMB2_set_compression(const unsigned int xid, struct cifs_tcon *tcon,
 	char *ret_data = NULL;
 
 	fsctl_input.CompressionState =
-			__constant_cpu_to_le16(COMPRESSION_FORMAT_DEFAULT);
+			cpu_to_le16(COMPRESSION_FORMAT_DEFAULT);
 
 	rc = SMB2_ioctl(xid, tcon, persistent_fid, volatile_fid,
 			FSCTL_SET_COMPRESSION, true /* is_fsctl */,
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index d84f46c5b2c5..ce858477002a 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -85,7 +85,7 @@
 /* BB FIXME - analyze following length BB */
 #define MAX_SMB2_HDR_SIZE 0x78 /* 4 len + 64 hdr + (2*24 wct) + 2 bct + 2 pad */
 
-#define SMB2_PROTO_NUMBER __constant_cpu_to_le32(0x424d53fe)
+#define SMB2_PROTO_NUMBER cpu_to_le32(0x424d53fe)
 
 /*
  * SMB2 Header Definition
@@ -96,7 +96,7 @@
  *
  */
 
-#define SMB2_HEADER_STRUCTURE_SIZE __constant_cpu_to_le16(64)
+#define SMB2_HEADER_STRUCTURE_SIZE cpu_to_le16(64)
 
 struct smb2_hdr {
 	__be32 smb2_buf_length;	/* big endian on wire */
@@ -137,16 +137,16 @@ struct smb2_transform_hdr {
 } __packed;
 
 /* Encryption Algorithms */
-#define SMB2_ENCRYPTION_AES128_CCM	__constant_cpu_to_le16(0x0001)
+#define SMB2_ENCRYPTION_AES128_CCM	cpu_to_le16(0x0001)
 
 /*
  *	SMB2 flag definitions
  */
-#define SMB2_FLAGS_SERVER_TO_REDIR	__constant_cpu_to_le32(0x00000001)
-#define SMB2_FLAGS_ASYNC_COMMAND	__constant_cpu_to_le32(0x00000002)
-#define SMB2_FLAGS_RELATED_OPERATIONS	__constant_cpu_to_le32(0x00000004)
-#define SMB2_FLAGS_SIGNED		__constant_cpu_to_le32(0x00000008)
-#define SMB2_FLAGS_DFS_OPERATIONS	__constant_cpu_to_le32(0x10000000)
+#define SMB2_FLAGS_SERVER_TO_REDIR	cpu_to_le32(0x00000001)
+#define SMB2_FLAGS_ASYNC_COMMAND	cpu_to_le32(0x00000002)
+#define SMB2_FLAGS_RELATED_OPERATIONS	cpu_to_le32(0x00000004)
+#define SMB2_FLAGS_SIGNED		cpu_to_le32(0x00000008)
+#define SMB2_FLAGS_DFS_OPERATIONS	cpu_to_le32(0x10000000)
 
 /*
  *	Definitions for SMB2 Protocol Data Units (network frames)
@@ -157,7 +157,7 @@ struct smb2_transform_hdr {
  *
  */
 
-#define SMB2_ERROR_STRUCTURE_SIZE2 __constant_cpu_to_le16(9)
+#define SMB2_ERROR_STRUCTURE_SIZE2 cpu_to_le16(9)
 
 struct smb2_err_rsp {
 	struct smb2_hdr hdr;
@@ -502,12 +502,12 @@ struct create_context {
 #define SMB2_LEASE_HANDLE_CACHING_HE	0x02
 #define SMB2_LEASE_WRITE_CACHING_HE	0x04
 
-#define SMB2_LEASE_NONE			__constant_cpu_to_le32(0x00)
-#define SMB2_LEASE_READ_CACHING		__constant_cpu_to_le32(0x01)
-#define SMB2_LEASE_HANDLE_CACHING	__constant_cpu_to_le32(0x02)
-#define SMB2_LEASE_WRITE_CACHING	__constant_cpu_to_le32(0x04)
+#define SMB2_LEASE_NONE			cpu_to_le32(0x00)
+#define SMB2_LEASE_READ_CACHING		cpu_to_le32(0x01)
+#define SMB2_LEASE_HANDLE_CACHING	cpu_to_le32(0x02)
+#define SMB2_LEASE_WRITE_CACHING	cpu_to_le32(0x04)
 
-#define SMB2_LEASE_FLAG_BREAK_IN_PROGRESS __constant_cpu_to_le32(0x02)
+#define SMB2_LEASE_FLAG_BREAK_IN_PROGRESS cpu_to_le32(0x02)
 
 #define SMB2_LEASE_KEY_SIZE 16
 
diff --git a/fs/exec.c b/fs/exec.c
index 7302b75a9820..3f86ffbdd06e 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -747,18 +747,25 @@ EXPORT_SYMBOL(setup_arg_pages);
 
 #endif /* CONFIG_MMU */
 
-static struct file *do_open_exec(struct filename *name)
+static struct file *do_open_execat(int fd, struct filename *name, int flags)
 {
 	struct file *file;
 	int err;
-	static const struct open_flags open_exec_flags = {
+	struct open_flags open_exec_flags = {
 		.open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC,
 		.acc_mode = MAY_EXEC | MAY_OPEN,
 		.intent = LOOKUP_OPEN,
 		.lookup_flags = LOOKUP_FOLLOW,
 	};
 
-	file = do_filp_open(AT_FDCWD, name, &open_exec_flags);
+	if ((flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0)
+		return ERR_PTR(-EINVAL);
+	if (flags & AT_SYMLINK_NOFOLLOW)
+		open_exec_flags.lookup_flags &= ~LOOKUP_FOLLOW;
+	if (flags & AT_EMPTY_PATH)
+		open_exec_flags.lookup_flags |= LOOKUP_EMPTY;
+
+	file = do_filp_open(fd, name, &open_exec_flags);
 	if (IS_ERR(file))
 		goto out;
 
@@ -769,12 +776,13 @@ static struct file *do_open_exec(struct filename *name)
 	if (file->f_path.mnt->mnt_flags & MNT_NOEXEC)
 		goto exit;
 
-	fsnotify_open(file);
-
 	err = deny_write_access(file);
 	if (err)
 		goto exit;
 
+	if (name->name[0] != '\0')
+		fsnotify_open(file);
+
 out:
 	return file;
 
@@ -786,7 +794,7 @@ exit:
 struct file *open_exec(const char *name)
 {
 	struct filename tmp = { .name = name };
-	return do_open_exec(&tmp);
+	return do_open_execat(AT_FDCWD, &tmp, 0);
 }
 EXPORT_SYMBOL(open_exec);
 
@@ -1427,10 +1435,12 @@ static int exec_binprm(struct linux_binprm *bprm)
 /*
  * sys_execve() executes a new program.
  */
-static int do_execve_common(struct filename *filename,
-				struct user_arg_ptr argv,
-				struct user_arg_ptr envp)
+static int do_execveat_common(int fd, struct filename *filename,
+			      struct user_arg_ptr argv,
+			      struct user_arg_ptr envp,
+			      int flags)
 {
+	char *pathbuf = NULL;
 	struct linux_binprm *bprm;
 	struct file *file;
 	struct files_struct *displaced;
@@ -1471,7 +1481,7 @@ static int do_execve_common(struct filename *filename,
 	check_unsafe_exec(bprm);
 	current->in_execve = 1;
 
-	file = do_open_exec(filename);
+	file = do_open_execat(fd, filename, flags);
 	retval = PTR_ERR(file);
 	if (IS_ERR(file))
 		goto out_unmark;
@@ -1479,7 +1489,28 @@ static int do_execve_common(struct filename *filename,
 	sched_exec();
 
 	bprm->file = file;
-	bprm->filename = bprm->interp = filename->name;
+	if (fd == AT_FDCWD || filename->name[0] == '/') {
+		bprm->filename = filename->name;
+	} else {
+		if (filename->name[0] == '\0')
+			pathbuf = kasprintf(GFP_TEMPORARY, "/dev/fd/%d", fd);
+		else
+			pathbuf = kasprintf(GFP_TEMPORARY, "/dev/fd/%d/%s",
+					    fd, filename->name);
+		if (!pathbuf) {
+			retval = -ENOMEM;
+			goto out_unmark;
+		}
+		/*
+		 * Record that a name derived from an O_CLOEXEC fd will be
+		 * inaccessible after exec. Relies on having exclusive access to
+		 * current->files (due to unshare_files above).
+		 */
+		if (close_on_exec(fd, current->files->fdt))
+			bprm->interp_flags |= BINPRM_FLAGS_PATH_INACCESSIBLE;
+		bprm->filename = pathbuf;
+	}
+	bprm->interp = bprm->filename;
 
 	retval = bprm_mm_init(bprm);
 	if (retval)
@@ -1537,6 +1568,7 @@ out_unmark:
 
 out_free:
 	free_bprm(bprm);
+	kfree(pathbuf);
 
 out_files:
 	if (displaced)
@@ -1552,7 +1584,18 @@ int do_execve(struct filename *filename,
 {
 	struct user_arg_ptr argv = { .ptr.native = __argv };
 	struct user_arg_ptr envp = { .ptr.native = __envp };
-	return do_execve_common(filename, argv, envp);
+	return do_execveat_common(AT_FDCWD, filename, argv, envp, 0);
+}
+
+int do_execveat(int fd, struct filename *filename,
+		const char __user *const __user *__argv,
+		const char __user *const __user *__envp,
+		int flags)
+{
+	struct user_arg_ptr argv = { .ptr.native = __argv };
+	struct user_arg_ptr envp = { .ptr.native = __envp };
+
+	return do_execveat_common(fd, filename, argv, envp, flags);
 }
 
 #ifdef CONFIG_COMPAT
@@ -1568,7 +1611,23 @@ static int compat_do_execve(struct filename *filename,
 		.is_compat = true,
 		.ptr.compat = __envp,
 	};
-	return do_execve_common(filename, argv, envp);
+	return do_execveat_common(AT_FDCWD, filename, argv, envp, 0);
+}
+
+static int compat_do_execveat(int fd, struct filename *filename,
+			      const compat_uptr_t __user *__argv,
+			      const compat_uptr_t __user *__envp,
+			      int flags)
+{
+	struct user_arg_ptr argv = {
+		.is_compat = true,
+		.ptr.compat = __argv,
+	};
+	struct user_arg_ptr envp = {
+		.is_compat = true,
+		.ptr.compat = __envp,
+	};
+	return do_execveat_common(fd, filename, argv, envp, flags);
 }
 #endif
 
@@ -1608,6 +1667,20 @@ SYSCALL_DEFINE3(execve,
 {
 	return do_execve(getname(filename), argv, envp);
 }
+
+SYSCALL_DEFINE5(execveat,
+		int, fd, const char __user *, filename,
+		const char __user *const __user *, argv,
+		const char __user *const __user *, envp,
+		int, flags)
+{
+	int lookup_flags = (flags & AT_EMPTY_PATH) ? LOOKUP_EMPTY : 0;
+
+	return do_execveat(fd,
+			   getname_flags(filename, lookup_flags, NULL),
+			   argv, envp, flags);
+}
+
 #ifdef CONFIG_COMPAT
 COMPAT_SYSCALL_DEFINE3(execve, const char __user *, filename,
 	const compat_uptr_t __user *, argv,
@@ -1615,4 +1688,17 @@ COMPAT_SYSCALL_DEFINE3(execve, const char __user *, filename,
 {
 	return compat_do_execve(getname(filename), argv, envp);
 }
+
+COMPAT_SYSCALL_DEFINE5(execveat, int, fd,
+		       const char __user *, filename,
+		       const compat_uptr_t __user *, argv,
+		       const compat_uptr_t __user *, envp,
+		       int,  flags)
+{
+	int lookup_flags = (flags & AT_EMPTY_PATH) ? LOOKUP_EMPTY : 0;
+
+	return compat_do_execveat(fd,
+				  getname_flags(filename, lookup_flags, NULL),
+				  argv, envp, flags);
+}
 #endif
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index a8bc47f75fa0..5b6e9f246233 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -107,7 +107,10 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	}
 
 	if (!journal) {
-		ret = generic_file_fsync(file, start, end, datasync);
+		if (test_opt(inode->i_sb, BARRIER))
+			ret = generic_file_fsync(file, start, end, datasync);
+		else
+			ret = __generic_file_fsync(file, start, end, datasync);
 		if (!ret && !hlist_empty(&inode->i_dentry))
 			ret = ext4_sync_parent(inode);
 		goto out;
diff --git a/fs/fat/cache.c b/fs/fat/cache.c
index 91ad9e1c9441..d3dd5baccdfa 100644
--- a/fs/fat/cache.c
+++ b/fs/fat/cache.c
@@ -303,6 +303,29 @@ static int fat_bmap_cluster(struct inode *inode, int cluster)
 	return dclus;
 }
 
+int fat_get_mapped_cluster(struct inode *inode, sector_t sector,
+			   sector_t last_block,
+			   unsigned long *mapped_blocks, sector_t *bmap)
+{
+	struct super_block *sb = inode->i_sb;
+	struct msdos_sb_info *sbi = MSDOS_SB(sb);
+	int cluster, offset;
+
+	cluster = sector >> (sbi->cluster_bits - sb->s_blocksize_bits);
+	offset  = sector & (sbi->sec_per_clus - 1);
+	cluster = fat_bmap_cluster(inode, cluster);
+	if (cluster < 0)
+		return cluster;
+	else if (cluster) {
+		*bmap = fat_clus_to_blknr(sbi, cluster) + offset;
+		*mapped_blocks = sbi->sec_per_clus - offset;
+		if (*mapped_blocks > last_block - sector)
+			*mapped_blocks = last_block - sector;
+	}
+
+	return 0;
+}
+
 int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys,
 	     unsigned long *mapped_blocks, int create)
 {
@@ -311,7 +334,6 @@ int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys,
 	const unsigned long blocksize = sb->s_blocksize;
 	const unsigned char blocksize_bits = sb->s_blocksize_bits;
 	sector_t last_block;
-	int cluster, offset;
 
 	*phys = 0;
 	*mapped_blocks = 0;
@@ -338,16 +360,6 @@ int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys,
 			return 0;
 	}
 
-	cluster = sector >> (sbi->cluster_bits - sb->s_blocksize_bits);
-	offset  = sector & (sbi->sec_per_clus - 1);
-	cluster = fat_bmap_cluster(inode, cluster);
-	if (cluster < 0)
-		return cluster;
-	else if (cluster) {
-		*phys = fat_clus_to_blknr(sbi, cluster) + offset;
-		*mapped_blocks = sbi->sec_per_clus - offset;
-		if (*mapped_blocks > last_block - sector)
-			*mapped_blocks = last_block - sector;
-	}
-	return 0;
+	return fat_get_mapped_cluster(inode, sector, last_block, mapped_blocks,
+				      phys);
 }
diff --git a/fs/fat/fat.h b/fs/fat/fat.h
index e0c4ba39a377..e59eb6ece9a5 100644
--- a/fs/fat/fat.h
+++ b/fs/fat/fat.h
@@ -288,6 +288,9 @@ static inline void fatwchar_to16(__u8 *dst, const wchar_t *src, size_t len)
 extern void fat_cache_inval_inode(struct inode *inode);
 extern int fat_get_cluster(struct inode *inode, int cluster,
 			   int *fclus, int *dclus);
+extern int fat_get_mapped_cluster(struct inode *inode, sector_t sector,
+				  sector_t last_block,
+				  unsigned long *mapped_blocks, sector_t *bmap);
 extern int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys,
 		    unsigned long *mapped_blocks, int create);
 
@@ -370,6 +373,7 @@ extern int fat_file_fsync(struct file *file, loff_t start, loff_t end,
 			  int datasync);
 
 /* fat/inode.c */
+extern int fat_block_truncate_page(struct inode *inode, loff_t from);
 extern void fat_attach(struct inode *inode, loff_t i_pos);
 extern void fat_detach(struct inode *inode);
 extern struct inode *fat_iget(struct super_block *sb, loff_t i_pos);
@@ -386,6 +390,7 @@ static inline unsigned long fat_dir_hash(int logstart)
 {
 	return hash_32(logstart, FAT_HASH_BITS);
 }
+extern int fat_add_cluster(struct inode *inode);
 
 /* fat/misc.c */
 extern __printf(3, 4) __cold
diff --git a/fs/fat/file.c b/fs/fat/file.c
index 85f79a89e747..12b16c375179 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -17,8 +17,12 @@
 #include <linux/blkdev.h>
 #include <linux/fsnotify.h>
 #include <linux/security.h>
+#include <linux/falloc.h>
 #include "fat.h"
 
+static long fat_fallocate(struct file *file, int mode,
+			  loff_t offset, loff_t len);
+
 static int fat_ioctl_get_attributes(struct inode *inode, u32 __user *user_attr)
 {
 	u32 attr;
@@ -182,6 +186,7 @@ const struct file_operations fat_file_operations = {
 #endif
 	.fsync		= fat_file_fsync,
 	.splice_read	= generic_file_splice_read,
+	.fallocate	= fat_fallocate,
 };
 
 static int fat_cont_expand(struct inode *inode, loff_t size)
@@ -220,6 +225,66 @@ out:
 	return err;
 }
 
+/*
+ * Preallocate space for a file. This implements fat's fallocate file
+ * operation, which gets called from sys_fallocate system call. User
+ * space requests len bytes at offset. If FALLOC_FL_KEEP_SIZE is set
+ * we just allocate clusters without zeroing them out. Otherwise we
+ * allocate and zero out clusters via an expanding truncate.
+ */
+static long fat_fallocate(struct file *file, int mode,
+			  loff_t offset, loff_t len)
+{
+	int nr_cluster; /* Number of clusters to be allocated */
+	loff_t mm_bytes; /* Number of bytes to be allocated for file */
+	loff_t ondisksize; /* block aligned on-disk size in bytes*/
+	struct inode *inode = file->f_mapping->host;
+	struct super_block *sb = inode->i_sb;
+	struct msdos_sb_info *sbi = MSDOS_SB(sb);
+	int err = 0;
+
+	/* No support for hole punch or other fallocate flags. */
+	if (mode & ~FALLOC_FL_KEEP_SIZE)
+		return -EOPNOTSUPP;
+
+	/* No support for dir */
+	if (!S_ISREG(inode->i_mode))
+		return -EOPNOTSUPP;
+
+	mutex_lock(&inode->i_mutex);
+	if (mode & FALLOC_FL_KEEP_SIZE) {
+		ondisksize = inode->i_blocks << 9;
+		if ((offset + len) <= ondisksize)
+			goto error;
+
+		/* First compute the number of clusters to be allocated */
+		mm_bytes = offset + len - ondisksize;
+		nr_cluster = (mm_bytes + (sbi->cluster_size - 1)) >>
+			sbi->cluster_bits;
+
+		/* Start the allocation.We are not zeroing out the clusters */
+		while (nr_cluster-- > 0) {
+			err = fat_add_cluster(inode);
+			if (err)
+				goto error;
+		}
+	} else {
+		if ((offset + len) <= MSDOS_I(inode)->mmu_private)
+			goto error;
+
+		err = inode_newsize_ok(inode, (len + offset));
+		if (err)
+			goto error;
+
+		/* This is just an expanding truncate */
+		err = fat_cont_expand(inode, (offset + len));
+	}
+
+error:
+	mutex_unlock(&inode->i_mutex);
+	return err;
+}
+
 /* Free all clusters after the skip'th cluster. */
 static int fat_free(struct inode *inode, int skip)
 {
@@ -443,6 +508,9 @@ int fat_setattr(struct dentry *dentry, struct iattr *attr)
 	}
 
 	if (attr->ia_valid & ATTR_SIZE) {
+		error = fat_block_truncate_page(inode, attr->ia_size);
+		if (error)
+			goto out;
 		down_write(&MSDOS_I(inode)->truncate_lock);
 		truncate_setsize(inode, attr->ia_size);
 		fat_truncate_blocks(inode, attr->ia_size);
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 756aead10d96..2c0a87f8e7e0 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -101,7 +101,7 @@ static struct fat_floppy_defaults {
 },
 };
 
-static int fat_add_cluster(struct inode *inode)
+int fat_add_cluster(struct inode *inode)
 {
 	int err, cluster;
 
@@ -144,7 +144,12 @@ static inline int __fat_get_block(struct inode *inode, sector_t iblock,
 	}
 
 	offset = (unsigned long)iblock & (sbi->sec_per_clus - 1);
-	if (!offset) {
+	/*
+	 * allocate a cluster according to the following.
+	 * 1) no more available blocks
+	 * 2) not part of fallocate region
+	 */
+	if (!offset && !(iblock < (sector_t)inode->i_blocks)) {
 		/* TODO: multiple cluster allocation would be desirable. */
 		err = fat_add_cluster(inode);
 		if (err)
@@ -282,18 +287,61 @@ static ssize_t fat_direct_IO(int rw, struct kiocb *iocb,
 	return ret;
 }
 
+static int fat_get_block_bmap(struct inode *inode, sector_t iblock,
+		struct buffer_head *bh_result, int create)
+{
+	struct super_block *sb = inode->i_sb;
+	unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits;
+	int err;
+	sector_t bmap, last_block;
+	unsigned long mapped_blocks;
+
+	BUG_ON(create != 0);
+
+	last_block = inode->i_blocks;
+
+	if (iblock >= last_block)
+		return 0;
+
+	err = fat_get_mapped_cluster(inode, iblock, last_block, &mapped_blocks,
+		&bmap);
+	if (err)
+		return err;
+
+	if (bmap) {
+		map_bh(bh_result, sb, bmap);
+		max_blocks = min(mapped_blocks, max_blocks);
+	}
+
+	bh_result->b_size = max_blocks << sb->s_blocksize_bits;
+
+	return 0;
+}
+
 static sector_t _fat_bmap(struct address_space *mapping, sector_t block)
 {
 	sector_t blocknr;
 
 	/* fat_get_cluster() assumes the requested blocknr isn't truncated. */
 	down_read(&MSDOS_I(mapping->host)->truncate_lock);
-	blocknr = generic_block_bmap(mapping, block, fat_get_block);
+	blocknr = generic_block_bmap(mapping, block, fat_get_block_bmap);
 	up_read(&MSDOS_I(mapping->host)->truncate_lock);
 
 	return blocknr;
 }
 
+/*
+ * fat_block_truncate_page() zeroes out a mapping from file offset `from'
+ * up to the end of the block which corresponds to `from'.
+ * This is required during truncate to physically zeroout the tail end
+ * of that block so it doesn't yield old data if the file is later grown.
+ * Also, avoid causing failure from fsx for cases of "data past EOF"
+ */
+int fat_block_truncate_page(struct inode *inode, loff_t from)
+{
+	return block_truncate_page(inode->i_mapping, from, fat_get_block);
+}
+
 static const struct address_space_operations fat_aops = {
 	.readpage	= fat_readpage,
 	.readpages	= fat_readpages,
@@ -550,12 +598,35 @@ out:
 
 EXPORT_SYMBOL_GPL(fat_build_inode);
 
+static int __fat_write_inode(struct inode *inode, int wait);
 static void fat_evict_inode(struct inode *inode)
 {
 	truncate_inode_pages_final(&inode->i_data);
 	if (!inode->i_nlink) {
 		inode->i_size = 0;
 		fat_truncate_blocks(inode, 0);
+	} else {
+		/* Release unwritten fallocated blocks on inode eviction. */
+		if ((inode->i_blocks << 9) >
+		    round_up(MSDOS_I(inode)->mmu_private,
+				inode->i_sb->s_blocksize)) {
+			int err;
+
+			fat_truncate_blocks(inode, MSDOS_I(inode)->mmu_private);
+			/* Fallocate results in updating the i_start/iogstart
+			 * for the zero byte file. So, make it return to
+			 * original state during evict and commit it to avoid
+			 * any corruption on the next access to the cluster
+			 * chain for the file.
+			 */
+			err = __fat_write_inode(inode, inode_needs_sync(inode));
+			if (err) {
+				fat_msg(inode->i_sb, KERN_WARNING, "Failed to "
+				"update on disk inode for unused fallocated "
+				"blocks, inode could be corrupted. Please run "
+				"fsck");
+			}
+		}
 	}
 	invalidate_inode_buffers(inode);
 	clear_inode(inode);
diff --git a/fs/file.c b/fs/file.c
index ab3eb6a88239..ee738ea028fa 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -869,7 +869,7 @@ SYSCALL_DEFINE1(dup, unsigned int, fildes)
 	struct file *file = fget_raw(fildes);
 
 	if (file) {
-		ret = get_unused_fd();
+		ret = get_unused_fd_flags(0);
 		if (ret >= 0)
 			fd_install(ret, file);
 		else
diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c
index 32602c667b4a..7892e6fddb66 100644
--- a/fs/hfsplus/catalog.c
+++ b/fs/hfsplus/catalog.c
@@ -38,21 +38,30 @@ int hfsplus_cat_bin_cmp_key(const hfsplus_btree_key *k1,
 	return hfsplus_strcmp(&k1->cat.name, &k2->cat.name);
 }
 
-void hfsplus_cat_build_key(struct super_block *sb, hfsplus_btree_key *key,
-			   u32 parent, struct qstr *str)
+/* Generates key for catalog file/folders record. */
+int hfsplus_cat_build_key(struct super_block *sb,
+		hfsplus_btree_key *key, u32 parent, struct qstr *str)
 {
-	int len;
+	int len, err;
 
 	key->cat.parent = cpu_to_be32(parent);
-	if (str) {
-		hfsplus_asc2uni(sb, &key->cat.name, HFSPLUS_MAX_STRLEN,
-					str->name, str->len);
-		len = be16_to_cpu(key->cat.name.length);
-	} else {
-		key->cat.name.length = 0;
-		len = 0;
-	}
+	err = hfsplus_asc2uni(sb, &key->cat.name, HFSPLUS_MAX_STRLEN,
+			str->name, str->len);
+	if (unlikely(err < 0))
+		return err;
+
+	len = be16_to_cpu(key->cat.name.length);
 	key->key_len = cpu_to_be16(6 + 2 * len);
+	return 0;
+}
+
+/* Generates key for catalog thread record. */
+void hfsplus_cat_build_key_with_cnid(struct super_block *sb,
+			hfsplus_btree_key *key, u32 parent)
+{
+	key->cat.parent = cpu_to_be32(parent);
+	key->cat.name.length = 0;
+	key->key_len = cpu_to_be16(6);
 }
 
 static void hfsplus_cat_build_key_uni(hfsplus_btree_key *key, u32 parent,
@@ -167,11 +176,16 @@ static int hfsplus_fill_cat_thread(struct super_block *sb,
 				   hfsplus_cat_entry *entry, int type,
 				   u32 parentid, struct qstr *str)
 {
+	int err;
+
 	entry->type = cpu_to_be16(type);
 	entry->thread.reserved = 0;
 	entry->thread.parentID = cpu_to_be32(parentid);
-	hfsplus_asc2uni(sb, &entry->thread.nodeName, HFSPLUS_MAX_STRLEN,
+	err = hfsplus_asc2uni(sb, &entry->thread.nodeName, HFSPLUS_MAX_STRLEN,
 				str->name, str->len);
+	if (unlikely(err < 0))
+		return err;
+
 	return 10 + be16_to_cpu(entry->thread.nodeName.length) * 2;
 }
 
@@ -183,7 +197,7 @@ int hfsplus_find_cat(struct super_block *sb, u32 cnid,
 	int err;
 	u16 type;
 
-	hfsplus_cat_build_key(sb, fd->search_key, cnid, NULL);
+	hfsplus_cat_build_key_with_cnid(sb, fd->search_key, cnid);
 	err = hfs_brec_read(fd, &tmp, sizeof(hfsplus_cat_entry));
 	if (err)
 		return err;
@@ -250,11 +264,16 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir,
 	if (err)
 		return err;
 
-	hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL);
+	hfsplus_cat_build_key_with_cnid(sb, fd.search_key, cnid);
 	entry_size = hfsplus_fill_cat_thread(sb, &entry,
 		S_ISDIR(inode->i_mode) ?
 			HFSPLUS_FOLDER_THREAD : HFSPLUS_FILE_THREAD,
 		dir->i_ino, str);
+	if (unlikely(entry_size < 0)) {
+		err = entry_size;
+		goto err2;
+	}
+
 	err = hfs_brec_find(&fd, hfs_find_rec_by_key);
 	if (err != -ENOENT) {
 		if (!err)
@@ -265,7 +284,10 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir,
 	if (err)
 		goto err2;
 
-	hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, str);
+	err = hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, str);
+	if (unlikely(err))
+		goto err1;
+
 	entry_size = hfsplus_cat_build_record(&entry, cnid, inode);
 	err = hfs_brec_find(&fd, hfs_find_rec_by_key);
 	if (err != -ENOENT) {
@@ -288,7 +310,7 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir,
 	return 0;
 
 err1:
-	hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL);
+	hfsplus_cat_build_key_with_cnid(sb, fd.search_key, cnid);
 	if (!hfs_brec_find(&fd, hfs_find_rec_by_key))
 		hfs_brec_remove(&fd);
 err2:
@@ -313,7 +335,7 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str)
 	if (!str) {
 		int len;
 
-		hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL);
+		hfsplus_cat_build_key_with_cnid(sb, fd.search_key, cnid);
 		err = hfs_brec_find(&fd, hfs_find_rec_by_key);
 		if (err)
 			goto out;
@@ -329,7 +351,9 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str)
 			off + 2, len);
 		fd.search_key->key_len = cpu_to_be16(6 + len);
 	} else
-		hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, str);
+		err = hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, str);
+		if (unlikely(err))
+			goto out;
 
 	err = hfs_brec_find(&fd, hfs_find_rec_by_key);
 	if (err)
@@ -360,7 +384,7 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, struct qstr *str)
 	if (err)
 		goto out;
 
-	hfsplus_cat_build_key(sb, fd.search_key, cnid, NULL);
+	hfsplus_cat_build_key_with_cnid(sb, fd.search_key, cnid);
 	err = hfs_brec_find(&fd, hfs_find_rec_by_key);
 	if (err)
 		goto out;
@@ -405,7 +429,11 @@ int hfsplus_rename_cat(u32 cnid,
 	dst_fd = src_fd;
 
 	/* find the old dir entry and read the data */
-	hfsplus_cat_build_key(sb, src_fd.search_key, src_dir->i_ino, src_name);
+	err = hfsplus_cat_build_key(sb, src_fd.search_key,
+			src_dir->i_ino, src_name);
+	if (unlikely(err))
+		goto out;
+
 	err = hfs_brec_find(&src_fd, hfs_find_rec_by_key);
 	if (err)
 		goto out;
@@ -419,7 +447,11 @@ int hfsplus_rename_cat(u32 cnid,
 	type = be16_to_cpu(entry.type);
 
 	/* create new dir entry with the data from the old entry */
-	hfsplus_cat_build_key(sb, dst_fd.search_key, dst_dir->i_ino, dst_name);
+	err = hfsplus_cat_build_key(sb, dst_fd.search_key,
+			dst_dir->i_ino, dst_name);
+	if (unlikely(err))
+		goto out;
+
 	err = hfs_brec_find(&dst_fd, hfs_find_rec_by_key);
 	if (err != -ENOENT) {
 		if (!err)
@@ -436,7 +468,11 @@ int hfsplus_rename_cat(u32 cnid,
 	dst_dir->i_mtime = dst_dir->i_ctime = CURRENT_TIME_SEC;
 
 	/* finally remove the old entry */
-	hfsplus_cat_build_key(sb, src_fd.search_key, src_dir->i_ino, src_name);
+	err = hfsplus_cat_build_key(sb, src_fd.search_key,
+			src_dir->i_ino, src_name);
+	if (unlikely(err))
+		goto out;
+
 	err = hfs_brec_find(&src_fd, hfs_find_rec_by_key);
 	if (err)
 		goto out;
@@ -449,7 +485,7 @@ int hfsplus_rename_cat(u32 cnid,
 	src_dir->i_mtime = src_dir->i_ctime = CURRENT_TIME_SEC;
 
 	/* remove old thread entry */
-	hfsplus_cat_build_key(sb, src_fd.search_key, cnid, NULL);
+	hfsplus_cat_build_key_with_cnid(sb, src_fd.search_key, cnid);
 	err = hfs_brec_find(&src_fd, hfs_find_rec_by_key);
 	if (err)
 		goto out;
@@ -459,9 +495,14 @@ int hfsplus_rename_cat(u32 cnid,
 		goto out;
 
 	/* create new thread entry */
-	hfsplus_cat_build_key(sb, dst_fd.search_key, cnid, NULL);
+	hfsplus_cat_build_key_with_cnid(sb, dst_fd.search_key, cnid);
 	entry_size = hfsplus_fill_cat_thread(sb, &entry, type,
 		dst_dir->i_ino, dst_name);
+	if (unlikely(entry_size < 0)) {
+		err = entry_size;
+		goto out;
+	}
+
 	err = hfs_brec_find(&dst_fd, hfs_find_rec_by_key);
 	if (err != -ENOENT) {
 		if (!err)
diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c
index 610a3260bef1..435bea231cc6 100644
--- a/fs/hfsplus/dir.c
+++ b/fs/hfsplus/dir.c
@@ -44,7 +44,10 @@ static struct dentry *hfsplus_lookup(struct inode *dir, struct dentry *dentry,
 	err = hfs_find_init(HFSPLUS_SB(sb)->cat_tree, &fd);
 	if (err)
 		return ERR_PTR(err);
-	hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino, &dentry->d_name);
+	err = hfsplus_cat_build_key(sb, fd.search_key, dir->i_ino,
+			&dentry->d_name);
+	if (unlikely(err < 0))
+		goto fail;
 again:
 	err = hfs_brec_read(&fd, &entry, sizeof(entry));
 	if (err) {
@@ -97,9 +100,11 @@ again:
 					be32_to_cpu(entry.file.permissions.dev);
 				str.len = sprintf(name, "iNode%d", linkid);
 				str.name = name;
-				hfsplus_cat_build_key(sb, fd.search_key,
+				err = hfsplus_cat_build_key(sb, fd.search_key,
 					HFSPLUS_SB(sb)->hidden_dir->i_ino,
 					&str);
+				if (unlikely(err < 0))
+					goto fail;
 				goto again;
 			}
 		} else if (!dentry->d_fsdata)
@@ -145,7 +150,7 @@ static int hfsplus_readdir(struct file *file, struct dir_context *ctx)
 		err = -ENOMEM;
 		goto out;
 	}
-	hfsplus_cat_build_key(sb, fd.search_key, inode->i_ino, NULL);
+	hfsplus_cat_build_key_with_cnid(sb, fd.search_key, inode->i_ino);
 	err = hfs_brec_find(&fd, hfs_find_rec_by_key);
 	if (err)
 		goto out;
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index eb5e059f481a..b0441d65fa54 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -443,8 +443,10 @@ int hfsplus_cat_case_cmp_key(const hfsplus_btree_key *k1,
 			     const hfsplus_btree_key *k2);
 int hfsplus_cat_bin_cmp_key(const hfsplus_btree_key *k1,
 			    const hfsplus_btree_key *k2);
-void hfsplus_cat_build_key(struct super_block *sb, hfsplus_btree_key *key,
+int hfsplus_cat_build_key(struct super_block *sb, hfsplus_btree_key *key,
 			   u32 parent, struct qstr *str);
+void hfsplus_cat_build_key_with_cnid(struct super_block *sb,
+				     hfsplus_btree_key *key, u32 parent);
 void hfsplus_cat_set_perms(struct inode *inode, struct hfsplus_perm *perms);
 int hfsplus_find_cat(struct super_block *sb, u32 cnid,
 		     struct hfs_find_data *fd);
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 4cf2024b87da..593af2fdcc2d 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -515,7 +515,9 @@ static int hfsplus_fill_super(struct super_block *sb, void *data, int silent)
 	err = hfs_find_init(sbi->cat_tree, &fd);
 	if (err)
 		goto out_put_root;
-	hfsplus_cat_build_key(sb, fd.search_key, HFSPLUS_ROOT_CNID, &str);
+	err = hfsplus_cat_build_key(sb, fd.search_key, HFSPLUS_ROOT_CNID, &str);
+	if (unlikely(err < 0))
+		goto out_put_root;
 	if (!hfs_brec_read(&fd, &entry, sizeof(entry))) {
 		hfs_find_exit(&fd);
 		if (entry.type != cpu_to_be16(HFSPLUS_FOLDER))
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 1e2872b25343..5eba47f593f8 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -412,10 +412,10 @@ static int hugetlb_vmtruncate(struct inode *inode, loff_t offset)
 	pgoff = offset >> PAGE_SHIFT;
 
 	i_size_write(inode, offset);
-	mutex_lock(&mapping->i_mmap_mutex);
+	i_mmap_lock_write(mapping);
 	if (!RB_EMPTY_ROOT(&mapping->i_mmap))
 		hugetlb_vmtruncate_list(&mapping->i_mmap, pgoff);
-	mutex_unlock(&mapping->i_mmap_mutex);
+	i_mmap_unlock_write(mapping);
 	truncate_hugepages(inode, offset);
 	return 0;
 }
@@ -472,12 +472,12 @@ static struct inode *hugetlbfs_get_root(struct super_block *sb,
 }
 
 /*
- * Hugetlbfs is not reclaimable; therefore its i_mmap_mutex will never
+ * Hugetlbfs is not reclaimable; therefore its i_mmap_rwsem will never
  * be taken from reclaim -- unlike regular filesystems. This needs an
  * annotation because huge_pmd_share() does an allocation under
- * i_mmap_mutex.
+ * i_mmap_rwsem.
  */
-static struct lock_class_key hugetlbfs_i_mmap_mutex_key;
+static struct lock_class_key hugetlbfs_i_mmap_rwsem_key;
 
 static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 					struct inode *dir,
@@ -495,8 +495,8 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 		struct hugetlbfs_inode_info *info;
 		inode->i_ino = get_next_ino();
 		inode_init_owner(inode, dir, mode);
-		lockdep_set_class(&inode->i_mapping->i_mmap_mutex,
-				&hugetlbfs_i_mmap_mutex_key);
+		lockdep_set_class(&inode->i_mapping->i_mmap_rwsem,
+				&hugetlbfs_i_mmap_rwsem_key);
 		inode->i_mapping->a_ops = &hugetlbfs_aops;
 		inode->i_mapping->backing_dev_info =&hugetlbfs_backing_dev_info;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
diff --git a/fs/inode.c b/fs/inode.c
index 2ed95f7caa4f..ad60555b4768 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -346,7 +346,7 @@ void address_space_init_once(struct address_space *mapping)
 	memset(mapping, 0, sizeof(*mapping));
 	INIT_RADIX_TREE(&mapping->page_tree, GFP_ATOMIC);
 	spin_lock_init(&mapping->tree_lock);
-	mutex_init(&mapping->i_mmap_mutex);
+	init_rwsem(&mapping->i_mmap_rwsem);
 	INIT_LIST_HEAD(&mapping->private_list);
 	spin_lock_init(&mapping->private_lock);
 	mapping->i_mmap = RB_ROOT;
diff --git a/fs/mpage.c b/fs/mpage.c
index 3e79220babac..587c7ed4185d 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -482,6 +482,7 @@ static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
 	struct buffer_head map_bh;
 	loff_t i_size = i_size_read(inode);
 	int ret = 0;
+	int wr = (wbc->sync_mode == WB_SYNC_ALL ?  WRITE_SYNC : WRITE);
 
 	if (page_has_buffers(page)) {
 		struct buffer_head *head = page_buffers(page);
@@ -590,7 +591,7 @@ page_is_mapped:
 	 * This page will go to BIO.  Do we need to send this BIO off first?
 	 */
 	if (bio && mpd->last_block_in_bio != blocks[0] - 1)
-		bio = mpage_bio_submit(WRITE, bio);
+		bio = mpage_bio_submit(wr, bio);
 
 alloc_new:
 	if (bio == NULL) {
@@ -614,7 +615,7 @@ alloc_new:
 	 */
 	length = first_unmapped << blkbits;
 	if (bio_add_page(bio, page, length, 0) < length) {
-		bio = mpage_bio_submit(WRITE, bio);
+		bio = mpage_bio_submit(wr, bio);
 		goto alloc_new;
 	}
 
@@ -624,7 +625,7 @@ alloc_new:
 	set_page_writeback(page);
 	unlock_page(page);
 	if (boundary || (first_unmapped != blocks_per_page)) {
-		bio = mpage_bio_submit(WRITE, bio);
+		bio = mpage_bio_submit(wr, bio);
 		if (boundary_block) {
 			write_boundary_block(boundary_bdev,
 					boundary_block, 1 << blkbits);
@@ -636,7 +637,7 @@ alloc_new:
 
 confused:
 	if (bio)
-		bio = mpage_bio_submit(WRITE, bio);
+		bio = mpage_bio_submit(wr, bio);
 
 	if (mpd->use_writepage) {
 		ret = mapping->a_ops->writepage(page, wbc);
@@ -692,8 +693,11 @@ mpage_writepages(struct address_space *mapping,
 		};
 
 		ret = write_cache_pages(mapping, wbc, __mpage_writepage, &mpd);
-		if (mpd.bio)
-			mpage_bio_submit(WRITE, mpd.bio);
+		if (mpd.bio) {
+			int wr = (wbc->sync_mode == WB_SYNC_ALL ?
+				  WRITE_SYNC : WRITE);
+			mpage_bio_submit(wr, mpd.bio);
+		}
 	}
 	blk_finish_plug(&plug);
 	return ret;
@@ -710,8 +714,11 @@ int mpage_writepage(struct page *page, get_block_t get_block,
 		.use_writepage = 0,
 	};
 	int ret = __mpage_writepage(page, wbc, &mpd);
-	if (mpd.bio)
-		mpage_bio_submit(WRITE, mpd.bio);
+	if (mpd.bio) {
+		int wr = (wbc->sync_mode == WB_SYNC_ALL ?
+			  WRITE_SYNC : WRITE);
+		mpage_bio_submit(wr, mpd.bio);
+	}
 	return ret;
 }
 EXPORT_SYMBOL(mpage_writepage);
diff --git a/fs/namei.c b/fs/namei.c
index db5fe86319e6..ca814165d84c 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -130,7 +130,7 @@ void final_putname(struct filename *name)
 
 #define EMBEDDED_NAME_MAX	(PATH_MAX - sizeof(struct filename))
 
-static struct filename *
+struct filename *
 getname_flags(const char __user *filename, int flags, int *empty)
 {
 	struct filename *result, *err;
diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c
index d5659d96ee7f..cf7e043a9447 100644
--- a/fs/ncpfs/ioctl.c
+++ b/fs/ncpfs/ioctl.c
@@ -447,7 +447,6 @@ static long __ncp_ioctl(struct inode *inode, unsigned int cmd, unsigned long arg
 						result = -EIO;
 					}
 				}
-				result = 0;
 			}
 			mutex_unlock(&server->root_setup_lock);
 
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index 700129940c6e..41e39102743a 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -229,8 +229,16 @@ int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is,
 					      &fsnotify_mark_srcu);
 	}
 
+	/*
+	 * We need to merge inode & vfsmount mark lists so that inode mark
+	 * ignore masks are properly reflected for mount mark notifications.
+	 * That's why this traversal is so complicated...
+	 */
 	while (inode_node || vfsmount_node) {
-		inode_group = vfsmount_group = NULL;
+		inode_group = NULL;
+		inode_mark = NULL;
+		vfsmount_group = NULL;
+		vfsmount_mark = NULL;
 
 		if (inode_node) {
 			inode_mark = hlist_entry(srcu_dereference(inode_node, &fsnotify_mark_srcu),
@@ -244,21 +252,19 @@ int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is,
 			vfsmount_group = vfsmount_mark->group;
 		}
 
-		if (inode_group > vfsmount_group) {
-			/* handle inode */
-			ret = send_to_group(to_tell, inode_mark, NULL, mask,
-					    data, data_is, cookie, file_name);
-			/* we didn't use the vfsmount_mark */
-			vfsmount_group = NULL;
-		} else if (vfsmount_group > inode_group) {
-			ret = send_to_group(to_tell, NULL, vfsmount_mark, mask,
-					    data, data_is, cookie, file_name);
-			inode_group = NULL;
-		} else {
-			ret = send_to_group(to_tell, inode_mark, vfsmount_mark,
-					    mask, data, data_is, cookie,
-					    file_name);
+		if (inode_group && vfsmount_group) {
+			int cmp = fsnotify_compare_groups(inode_group,
+							  vfsmount_group);
+			if (cmp > 0) {
+				inode_group = NULL;
+				inode_mark = NULL;
+			} else if (cmp < 0) {
+				vfsmount_group = NULL;
+				vfsmount_mark = NULL;
+			}
 		}
+		ret = send_to_group(to_tell, inode_mark, vfsmount_mark, mask,
+				    data, data_is, cookie, file_name);
 
 		if (ret && (mask & ALL_FSNOTIFY_PERM_EVENTS))
 			goto out;
diff --git a/fs/notify/fsnotify.h b/fs/notify/fsnotify.h
index 9c0898c4cfe1..3b68b0ae0a97 100644
--- a/fs/notify/fsnotify.h
+++ b/fs/notify/fsnotify.h
@@ -12,6 +12,10 @@ extern void fsnotify_flush_notify(struct fsnotify_group *group);
 /* protects reads of inode and vfsmount marks list */
 extern struct srcu_struct fsnotify_mark_srcu;
 
+/* compare two groups for sorting of marks lists */
+extern int fsnotify_compare_groups(struct fsnotify_group *a,
+				   struct fsnotify_group *b);
+
 extern void fsnotify_set_inode_mark_mask_locked(struct fsnotify_mark *fsn_mark,
 						__u32 mask);
 /* add a mark to an inode */
diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c
index e8497144b323..dfbf5447eea4 100644
--- a/fs/notify/inode_mark.c
+++ b/fs/notify/inode_mark.c
@@ -194,6 +194,7 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
 {
 	struct fsnotify_mark *lmark, *last = NULL;
 	int ret = 0;
+	int cmp;
 
 	mark->flags |= FSNOTIFY_MARK_FLAG_INODE;
 
@@ -219,11 +220,8 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
 			goto out;
 		}
 
-		if (mark->group->priority < lmark->group->priority)
-			continue;
-
-		if ((mark->group->priority == lmark->group->priority) &&
-		    (mark->group < lmark->group))
+		cmp = fsnotify_compare_groups(lmark->group, mark->group);
+		if (cmp < 0)
 			continue;
 
 		hlist_add_before_rcu(&mark->i.i_list, &lmark->i.i_list);
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index d90deaa08e78..34c38fabf514 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -210,6 +210,42 @@ void fsnotify_set_mark_ignored_mask_locked(struct fsnotify_mark *mark, __u32 mas
 }
 
 /*
+ * Sorting function for lists of fsnotify marks.
+ *
+ * Fanotify supports different notification classes (reflected as priority of
+ * notification group). Events shall be passed to notification groups in
+ * decreasing priority order. To achieve this marks in notification lists for
+ * inodes and vfsmounts are sorted so that priorities of corresponding groups
+ * are descending.
+ *
+ * Furthermore correct handling of the ignore mask requires processing inode
+ * and vfsmount marks of each group together. Using the group address as
+ * further sort criterion provides a unique sorting order and thus we can
+ * merge inode and vfsmount lists of marks in linear time and find groups
+ * present in both lists.
+ *
+ * A return value of 1 signifies that b has priority over a.
+ * A return value of 0 signifies that the two marks have to be handled together.
+ * A return value of -1 signifies that a has priority over b.
+ */
+int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b)
+{
+	if (a == b)
+		return 0;
+	if (!a)
+		return 1;
+	if (!b)
+		return -1;
+	if (a->priority < b->priority)
+		return 1;
+	if (a->priority > b->priority)
+		return -1;
+	if (a < b)
+		return 1;
+	return -1;
+}
+
+/*
  * Attach an initialized mark to a given group and fs object.
  * These marks may be used for the fsnotify backend to determine which
  * event types should be delivered to which group.
diff --git a/fs/notify/vfsmount_mark.c b/fs/notify/vfsmount_mark.c
index ac851e8376b1..faefa72a11eb 100644
--- a/fs/notify/vfsmount_mark.c
+++ b/fs/notify/vfsmount_mark.c
@@ -153,6 +153,7 @@ int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark,
 	struct mount *m = real_mount(mnt);
 	struct fsnotify_mark *lmark, *last = NULL;
 	int ret = 0;
+	int cmp;
 
 	mark->flags |= FSNOTIFY_MARK_FLAG_VFSMOUNT;
 
@@ -178,11 +179,8 @@ int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark,
 			goto out;
 		}
 
-		if (mark->group->priority < lmark->group->priority)
-			continue;
-
-		if ((mark->group->priority == lmark->group->priority) &&
-		    (mark->group < lmark->group))
+		cmp = fsnotify_compare_groups(lmark->group, mark->group);
+		if (cmp < 0)
 			continue;
 
 		hlist_add_before_rcu(&mark->m.m_list, &lmark->m.m_list);
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index a93bf9892256..fcae9ef1a328 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -5662,7 +5662,7 @@ int ocfs2_remove_btree_range(struct inode *inode,
 			     struct ocfs2_extent_tree *et,
 			     u32 cpos, u32 phys_cpos, u32 len, int flags,
 			     struct ocfs2_cached_dealloc_ctxt *dealloc,
-			     u64 refcount_loc)
+			     u64 refcount_loc, bool refcount_tree_locked)
 {
 	int ret, credits = 0, extra_blocks = 0;
 	u64 phys_blkno = ocfs2_clusters_to_blocks(inode->i_sb, phys_cpos);
@@ -5676,11 +5676,13 @@ int ocfs2_remove_btree_range(struct inode *inode,
 		BUG_ON(!(OCFS2_I(inode)->ip_dyn_features &
 			 OCFS2_HAS_REFCOUNT_FL));
 
-		ret = ocfs2_lock_refcount_tree(osb, refcount_loc, 1,
-					       &ref_tree, NULL);
-		if (ret) {
-			mlog_errno(ret);
-			goto bail;
+		if (!refcount_tree_locked) {
+			ret = ocfs2_lock_refcount_tree(osb, refcount_loc, 1,
+						       &ref_tree, NULL);
+			if (ret) {
+				mlog_errno(ret);
+				goto bail;
+			}
 		}
 
 		ret = ocfs2_prepare_refcount_change_for_del(inode,
@@ -7021,6 +7023,7 @@ int ocfs2_commit_truncate(struct ocfs2_super *osb,
 	u64 refcount_loc = le64_to_cpu(di->i_refcount_loc);
 	struct ocfs2_extent_tree et;
 	struct ocfs2_cached_dealloc_ctxt dealloc;
+	struct ocfs2_refcount_tree *ref_tree = NULL;
 
 	ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode), di_bh);
 	ocfs2_init_dealloc_ctxt(&dealloc);
@@ -7130,9 +7133,18 @@ start:
 
 	phys_cpos = ocfs2_blocks_to_clusters(inode->i_sb, blkno);
 
+	if ((flags & OCFS2_EXT_REFCOUNTED) && trunc_len && !ref_tree) {
+		status = ocfs2_lock_refcount_tree(osb, refcount_loc, 1,
+				&ref_tree, NULL);
+		if (status) {
+			mlog_errno(status);
+			goto bail;
+		}
+	}
+
 	status = ocfs2_remove_btree_range(inode, &et, trunc_cpos,
 					  phys_cpos, trunc_len, flags, &dealloc,
-					  refcount_loc);
+					  refcount_loc, true);
 	if (status < 0) {
 		mlog_errno(status);
 		goto bail;
@@ -7147,6 +7159,8 @@ start:
 	goto start;
 
 bail:
+	if (ref_tree)
+		ocfs2_unlock_refcount_tree(osb, ref_tree, 1);
 
 	ocfs2_schedule_truncate_log_flush(osb, 1);
 
diff --git a/fs/ocfs2/alloc.h b/fs/ocfs2/alloc.h
index ca381c584127..fb09b97db162 100644
--- a/fs/ocfs2/alloc.h
+++ b/fs/ocfs2/alloc.h
@@ -142,7 +142,7 @@ int ocfs2_remove_btree_range(struct inode *inode,
 			     struct ocfs2_extent_tree *et,
 			     u32 cpos, u32 phys_cpos, u32 len, int flags,
 			     struct ocfs2_cached_dealloc_ctxt *dealloc,
-			     u64 refcount_loc);
+			     u64 refcount_loc, bool refcount_tree_locked);
 
 int ocfs2_num_free_extents(struct ocfs2_super *osb,
 			   struct ocfs2_extent_tree *et);
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 1ef547e49373..dc9b301de6d4 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -28,6 +28,7 @@
 #include <linux/pipe_fs_i.h>
 #include <linux/mpage.h>
 #include <linux/quotaops.h>
+#include <linux/blkdev.h>
 
 #include <cluster/masklog.h>
 
@@ -47,6 +48,9 @@
 #include "ocfs2_trace.h"
 
 #include "buffer_head_io.h"
+#include "dir.h"
+#include "namei.h"
+#include "sysfile.h"
 
 static int ocfs2_symlink_get_block(struct inode *inode, sector_t iblock,
 				   struct buffer_head *bh_result, int create)
@@ -506,18 +510,21 @@ bail:
  *
  * called like this: dio->get_blocks(dio->inode, fs_startblk,
  * 					fs_count, map_bh, dio->rw == WRITE);
- *
- * Note that we never bother to allocate blocks here, and thus ignore the
- * create argument.
  */
 static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
 				     struct buffer_head *bh_result, int create)
 {
 	int ret;
+	u32 cpos = 0;
+	int alloc_locked = 0;
 	u64 p_blkno, inode_blocks, contig_blocks;
 	unsigned int ext_flags;
 	unsigned char blocksize_bits = inode->i_sb->s_blocksize_bits;
 	unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits;
+	unsigned long len = bh_result->b_size;
+	unsigned int clusters_to_alloc = 0;
+
+	cpos = ocfs2_blocks_to_clusters(inode->i_sb, iblock);
 
 	/* This function won't even be called if the request isn't all
 	 * nicely aligned and of the right size, so there's no need
@@ -539,6 +546,40 @@ static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
 	/* We should already CoW the refcounted extent in case of create. */
 	BUG_ON(create && (ext_flags & OCFS2_EXT_REFCOUNTED));
 
+	/* allocate blocks if no p_blkno is found, and create == 1 */
+	if (!p_blkno && create) {
+		ret = ocfs2_inode_lock(inode, NULL, 1);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto bail;
+		}
+
+		alloc_locked = 1;
+
+		/* fill hole, allocate blocks can't be larger than the size
+		 * of the hole */
+		clusters_to_alloc = ocfs2_clusters_for_bytes(inode->i_sb, len);
+		if (clusters_to_alloc > contig_blocks)
+			clusters_to_alloc = contig_blocks;
+
+		/* allocate extent and insert them into the extent tree */
+		ret = ocfs2_extend_allocation(inode, cpos,
+				clusters_to_alloc, 0);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto bail;
+		}
+
+		ret = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno,
+				&contig_blocks, &ext_flags);
+		if (ret < 0) {
+			mlog(ML_ERROR, "get_blocks() failed iblock=%llu\n",
+					(unsigned long long)iblock);
+			ret = -EIO;
+			goto bail;
+		}
+	}
+
 	/*
 	 * get_more_blocks() expects us to describe a hole by clearing
 	 * the mapped bit on bh_result().
@@ -556,6 +597,8 @@ static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
 		contig_blocks = max_blocks;
 	bh_result->b_size = contig_blocks << blocksize_bits;
 bail:
+	if (alloc_locked)
+		ocfs2_inode_unlock(inode, 1);
 	return ret;
 }
 
@@ -597,6 +640,179 @@ static int ocfs2_releasepage(struct page *page, gfp_t wait)
 	return try_to_free_buffers(page);
 }
 
+static int ocfs2_is_overwrite(struct ocfs2_super *osb,
+		struct inode *inode , loff_t offset)
+{
+	int ret = 0;
+	u32 v_cpos = 0;
+	u32 p_cpos = 0;
+	unsigned int num_clusters = 0;
+	unsigned int ext_flags = 0;
+
+	v_cpos = ocfs2_bytes_to_clusters(osb->sb, offset);
+	ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos,
+			&num_clusters, &ext_flags);
+	if (ret < 0) {
+		mlog_errno(ret);
+		return ret;
+	}
+
+	if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN))
+		return 1;
+
+	return 0;
+}
+
+static ssize_t ocfs2_direct_IO_write(struct kiocb *iocb,
+		struct iov_iter *iter,
+		loff_t offset)
+{
+	ssize_t ret = 0;
+	ssize_t written = 0;
+	bool orphaned = false;
+	int is_overwrite = 0;
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file)->i_mapping->host;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct buffer_head *di_bh = NULL;
+	size_t count = iter->count;
+	journal_t *journal = osb->journal->j_journal;
+	u32 zero_len;
+	int cluster_align;
+	loff_t final_size = offset + count;
+	int append_write = offset >= i_size_read(inode) ? 1 : 0;
+	unsigned int num_clusters = 0;
+	unsigned int ext_flags = 0;
+
+	{
+		u64 o = offset;
+
+		zero_len = do_div(o, 1 << osb->s_clustersize_bits);
+		cluster_align = !!zero_len;
+	}
+
+	/*
+	 * when final_size > inode->i_size, inode->i_size will be
+	 * updated after direct write, so add the inode to orphan
+	 * dir first.
+	 */
+	if (final_size > i_size_read(inode)) {
+		ret = ocfs2_add_inode_to_orphan(osb, inode);
+		if (ret < 0)
+			goto out;
+		orphaned = true;
+	}
+
+	if (append_write) {
+		ret = ocfs2_inode_lock(inode, &di_bh, 1);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto clean_orphan;
+		}
+
+		if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)))
+			ret = ocfs2_zero_extend(inode, di_bh, offset);
+		else
+			ret = ocfs2_extend_no_holes(inode, di_bh, offset, offset);
+		if (ret < 0) {
+			mlog_errno(ret);
+			ocfs2_inode_unlock(inode, 1);
+			brelse(di_bh);
+			goto clean_orphan;
+		}
+
+		is_overwrite = ocfs2_is_overwrite(osb, inode, offset);
+		if (is_overwrite < 0) {
+			mlog_errno(is_overwrite);
+			ocfs2_inode_unlock(inode, 1);
+			brelse(di_bh);
+			goto clean_orphan;
+		}
+
+		ocfs2_inode_unlock(inode, 1);
+		brelse(di_bh);
+	}
+
+	written = __blockdev_direct_IO(WRITE, iocb, inode, inode->i_sb->s_bdev,
+			iter, offset,
+			ocfs2_direct_IO_get_blocks,
+			ocfs2_dio_end_io, NULL, 0);
+	if (unlikely(written < 0)) {
+		loff_t i_size = i_size_read(inode);
+
+		if (offset + count > i_size) {
+			ret = ocfs2_inode_lock(inode, &di_bh, 1);
+			if (ret < 0) {
+				mlog_errno(ret);
+				goto clean_orphan;
+			}
+
+			if (i_size == i_size_read(inode)) {
+				ret = ocfs2_truncate_file(inode, di_bh,
+						i_size);
+				if (ret < 0) {
+					if (ret != -ENOSPC)
+						mlog_errno(ret);
+
+					ocfs2_inode_unlock(inode, 1);
+					brelse(di_bh);
+					goto clean_orphan;
+				}
+			}
+
+			ocfs2_inode_unlock(inode, 1);
+			brelse(di_bh);
+
+			ret = jbd2_journal_force_commit(journal);
+			if (ret < 0)
+				mlog_errno(ret);
+		}
+	} else if (append_write && !is_overwrite && !cluster_align) {
+		u32 p_cpos = 0;
+		u32 v_cpos = ocfs2_bytes_to_clusters(osb->sb, offset);
+
+		ret = ocfs2_get_clusters(inode, v_cpos, &p_cpos,
+				&num_clusters, &ext_flags);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto clean_orphan;
+		}
+
+		BUG_ON(!p_cpos || (ext_flags & OCFS2_EXT_UNWRITTEN));
+
+		ret = blkdev_issue_zeroout(osb->sb->s_bdev,
+				p_cpos << (osb->s_clustersize_bits - 9),
+				zero_len >> 9,
+				GFP_KERNEL);
+		if (ret < 0)
+			mlog_errno(ret);
+	}
+
+clean_orphan:
+	if (orphaned) {
+		int tmp_ret;
+		int update_isize = written > 0 ? 1 : 0;
+		loff_t end = update_isize ? offset + written : 0;
+		tmp_ret = ocfs2_del_inode_from_orphan(osb, inode,
+				update_isize, end);
+		if (tmp_ret < 0) {
+			ret = tmp_ret;
+			goto out;
+		}
+
+		tmp_ret = jbd2_journal_force_commit(journal);
+		if (tmp_ret < 0) {
+			ret = tmp_ret;
+			mlog_errno(tmp_ret);
+		}
+	}
+
+out:
+	if (ret >= 0)
+		ret = written;
+	return ret;
+}
+
 static ssize_t ocfs2_direct_IO(int rw,
 			       struct kiocb *iocb,
 			       struct iov_iter *iter,
@@ -604,6 +820,9 @@ static ssize_t ocfs2_direct_IO(int rw,
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file)->i_mapping->host;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	int full_coherency = !(osb->s_mount_opt &
+			OCFS2_MOUNT_COHERENCY_BUFFERED);
 
 	/*
 	 * Fallback to buffered I/O if we see an inode without
@@ -612,14 +831,19 @@ static ssize_t ocfs2_direct_IO(int rw,
 	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
 		return 0;
 
-	/* Fallback to buffered I/O if we are appending. */
-	if (i_size_read(inode) <= offset)
+	/* Fallback to buffered I/O if we are appending and
+	 * concurrent O_DIRECT writes are allowed.
+	 */
+	if (i_size_read(inode) <= offset && !full_coherency)
 		return 0;
 
-	return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev,
+	if (rw == READ)
+		return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev,
 				    iter, offset,
 				    ocfs2_direct_IO_get_blocks,
 				    ocfs2_dio_end_io, NULL, 0);
+	else
+		return ocfs2_direct_IO_write(iocb, iter, offset);
 }
 
 static void ocfs2_figure_cluster_boundaries(struct ocfs2_super *osb,
@@ -894,7 +1118,7 @@ void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages)
 	}
 }
 
-static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
+static void ocfs2_unlock_pages(struct ocfs2_write_ctxt *wc)
 {
 	int i;
 
@@ -915,7 +1139,11 @@ static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
 		page_cache_release(wc->w_target_page);
 	}
 	ocfs2_unlock_and_free_pages(wc->w_pages, wc->w_num_pages);
+}
 
+static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
+{
+	ocfs2_unlock_pages(wc);
 	brelse(wc->w_di_bh);
 	kfree(wc);
 }
@@ -1818,16 +2046,6 @@ try_again:
 		if (ret)
 			goto out_commit;
 	}
-	/*
-	 * We don't want this to fail in ocfs2_write_end(), so do it
-	 * here.
-	 */
-	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh,
-				      OCFS2_JOURNAL_ACCESS_WRITE);
-	if (ret) {
-		mlog_errno(ret);
-		goto out_quota;
-	}
 
 	/*
 	 * Fill our page array first. That way we've grabbed enough so
@@ -1978,7 +2196,7 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
 			   loff_t pos, unsigned len, unsigned copied,
 			   struct page *page, void *fsdata)
 {
-	int i;
+	int i, ret;
 	unsigned from, to, start = pos & (PAGE_CACHE_SIZE - 1);
 	struct inode *inode = mapping->host;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
@@ -2028,6 +2246,14 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
 		}
 	}
 
+	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh,
+				      OCFS2_JOURNAL_ACCESS_WRITE);
+	if (ret) {
+		copied = ret;
+		mlog_errno(ret);
+		goto out;
+	}
+
 out_write_size:
 	pos += copied;
 	if (pos > i_size_read(inode)) {
@@ -2042,11 +2268,20 @@ out_write_size:
 	ocfs2_update_inode_fsync_trans(handle, inode, 1);
 	ocfs2_journal_dirty(handle, wc->w_di_bh);
 
+out:
+	/* unlock pages before dealloc since it needs acquiring j_trans_barrier
+	 * lock, or it will cause a deadlock since journal commit threads holds
+	 * this lock and will ask for the page lock when flushing the data.
+	 * put it here to preserve the unlock order.
+	 */
+	ocfs2_unlock_pages(wc);
+
 	ocfs2_commit_trans(osb, handle);
 
 	ocfs2_run_deallocs(osb, &wc->w_dealloc);
 
-	ocfs2_free_write_ctxt(wc);
+	brelse(wc->w_di_bh);
+	kfree(wc);
 
 	return copied;
 }
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index eb9d48746ab4..16eff45727ee 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -1127,10 +1127,10 @@ static int o2hb_thread(void *data)
 		elapsed_msec = o2hb_elapsed_msecs(&before_hb, &after_hb);
 
 		mlog(ML_HEARTBEAT,
-		     "start = %lu.%lu, end = %lu.%lu, msec = %u\n",
+		     "start = %lu.%lu, end = %lu.%lu, msec = %u, ret = %d\n",
 		     before_hb.tv_sec, (unsigned long) before_hb.tv_usec,
 		     after_hb.tv_sec, (unsigned long) after_hb.tv_usec,
-		     elapsed_msec);
+		     elapsed_msec, ret);
 
 		if (!kthread_should_stop() &&
 		    elapsed_msec < reg->hr_timeout_ms) {
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index a96044004064..2e355e0f8335 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -1736,7 +1736,7 @@ static void o2net_connect_expired(struct work_struct *work)
 		     o2net_idle_timeout() / 1000,
 		     o2net_idle_timeout() % 1000);
 
-		o2net_set_nn_state(nn, NULL, 0, -ENOTCONN);
+		o2net_set_nn_state(nn, NULL, 0, 0);
 	}
 	spin_unlock(&nn->nn_lock);
 }
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index c43d9b4a1ec0..55cb2fca016b 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -4479,7 +4479,7 @@ int ocfs2_dx_dir_truncate(struct inode *dir, struct buffer_head *di_bh)
 		p_cpos = ocfs2_blocks_to_clusters(dir->i_sb, blkno);
 
 		ret = ocfs2_remove_btree_range(dir, &et, cpos, p_cpos, clen, 0,
-					       &dealloc, 0);
+					       &dealloc, 0, false);
 		if (ret) {
 			mlog_errno(ret);
 			goto out;
diff --git a/fs/ocfs2/dlm/dlmast.c b/fs/ocfs2/dlm/dlmast.c
index b46278f9ae44..fd6bbbbd7d78 100644
--- a/fs/ocfs2/dlm/dlmast.c
+++ b/fs/ocfs2/dlm/dlmast.c
@@ -385,8 +385,12 @@ int dlm_proxy_ast_handler(struct o2net_msg *msg, u32 len, void *data,
 		head = &res->granted;
 
 	list_for_each_entry(lock, head, list) {
-		if (lock->ml.cookie == cookie)
+		/* if lock is found but unlock is pending ignore the bast */
+		if (lock->ml.cookie == cookie) {
+			if (lock->unlock_pending)
+				break;
 			goto do_ast;
+		}
 	}
 
 	mlog(0, "Got %sast for unknown lock! cookie=%u:%llu, name=%.*s, "
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 215e41abf101..b26b476e1f06 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -498,16 +498,6 @@ static void dlm_lockres_release(struct kref *kref)
 	mlog(0, "destroying lockres %.*s\n", res->lockname.len,
 	     res->lockname.name);
 
-	spin_lock(&dlm->track_lock);
-	if (!list_empty(&res->tracking))
-		list_del_init(&res->tracking);
-	else {
-		mlog(ML_ERROR, "Resource %.*s not on the Tracking list\n",
-		     res->lockname.len, res->lockname.name);
-		dlm_print_one_lock_resource(res);
-	}
-	spin_unlock(&dlm->track_lock);
-
 	atomic_dec(&dlm->res_cur_count);
 
 	if (!hlist_unhashed(&res->hash_node) ||
@@ -695,14 +685,6 @@ void __dlm_lockres_grab_inflight_worker(struct dlm_ctxt *dlm,
 			res->inflight_assert_workers);
 }
 
-static void dlm_lockres_grab_inflight_worker(struct dlm_ctxt *dlm,
-		struct dlm_lock_resource *res)
-{
-	spin_lock(&res->spinlock);
-	__dlm_lockres_grab_inflight_worker(dlm, res);
-	spin_unlock(&res->spinlock);
-}
-
 static void __dlm_lockres_drop_inflight_worker(struct dlm_ctxt *dlm,
 		struct dlm_lock_resource *res)
 {
@@ -1460,6 +1442,18 @@ way_up_top:
 
 		/* take care of the easy cases up front */
 		spin_lock(&res->spinlock);
+
+		/*
+		 * Right after dlm spinlock was released, dlm_thread could have
+		 * purged the lockres. Check if lockres got unhashed. If so
+		 * start over.
+		 */
+		if (hlist_unhashed(&res->hash_node)) {
+			spin_unlock(&res->spinlock);
+			dlm_lockres_put(res);
+			goto way_up_top;
+		}
+
 		if (res->state & (DLM_LOCK_RES_RECOVERING|
 				  DLM_LOCK_RES_MIGRATING)) {
 			spin_unlock(&res->spinlock);
@@ -1634,6 +1628,7 @@ send_response:
 		}
 		mlog(0, "%u is the owner of %.*s, cleaning everyone else\n",
 			     dlm->node_num, res->lockname.len, res->lockname.name);
+		spin_lock(&res->spinlock);
 		ret = dlm_dispatch_assert_master(dlm, res, 0, request->node_idx,
 						 DLM_ASSERT_MASTER_MLE_CLEANUP);
 		if (ret < 0) {
@@ -1641,7 +1636,8 @@ send_response:
 			response = DLM_MASTER_RESP_ERROR;
 			dlm_lockres_put(res);
 		} else
-			dlm_lockres_grab_inflight_worker(dlm, res);
+			__dlm_lockres_grab_inflight_worker(dlm, res);
+		spin_unlock(&res->spinlock);
 	} else {
 		if (res)
 			dlm_lockres_put(res);
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 3365839d2971..79b5af5e6a7b 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -1656,14 +1656,18 @@ int dlm_do_master_requery(struct dlm_ctxt *dlm, struct dlm_lock_resource *res,
 	req.namelen = res->lockname.len;
 	memcpy(req.name, res->lockname.name, res->lockname.len);
 
+resend:
 	ret = o2net_send_message(DLM_MASTER_REQUERY_MSG, dlm->key,
 				 &req, sizeof(req), nodenum, &status);
-	/* XXX: negative status not handled properly here. */
 	if (ret < 0)
 		mlog(ML_ERROR, "Error %d when sending message %u (key "
 		     "0x%x) to node %u\n", ret, DLM_MASTER_REQUERY_MSG,
 		     dlm->key, nodenum);
-	else {
+	else if (status == -ENOMEM) {
+		mlog_errno(status);
+		msleep(50);
+		goto resend;
+	} else {
 		BUG_ON(status < 0);
 		BUG_ON(status > DLM_LOCK_RES_OWNER_UNKNOWN);
 		*real_master = (u8) (status & 0xff);
@@ -1705,9 +1709,13 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data,
 			int ret = dlm_dispatch_assert_master(dlm, res,
 							     0, 0, flags);
 			if (ret < 0) {
-				mlog_errno(-ENOMEM);
-				/* retry!? */
-				BUG();
+				mlog_errno(ret);
+				spin_unlock(&res->spinlock);
+				dlm_lockres_put(res);
+				spin_unlock(&dlm->spinlock);
+				dlm_put(dlm);
+				/* sender will take care of this and retry */
+				return ret;
 			} else
 				__dlm_lockres_grab_inflight_worker(dlm, res);
 			spin_unlock(&res->spinlock);
diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c
index 69aac6f088ad..2e5e6d5fffe8 100644
--- a/fs/ocfs2/dlm/dlmthread.c
+++ b/fs/ocfs2/dlm/dlmthread.c
@@ -211,6 +211,16 @@ static void dlm_purge_lockres(struct dlm_ctxt *dlm,
 
 	__dlm_unhash_lockres(dlm, res);
 
+	spin_lock(&dlm->track_lock);
+	if (!list_empty(&res->tracking))
+		list_del_init(&res->tracking);
+	else {
+		mlog(ML_ERROR, "Resource %.*s not on the Tracking list\n",
+				res->lockname.len, res->lockname.name);
+		__dlm_print_one_lock_resource(res);
+	}
+	spin_unlock(&dlm->track_lock);
+
 	/* lockres is not in the hash now.  drop the flag and wake up
 	 * any processes waiting in dlm_get_lock_resource. */
 	if (!master) {
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 37297c14f9a3..1c423af04c69 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -861,8 +861,13 @@ static inline void ocfs2_generic_handle_convert_action(struct ocfs2_lock_res *lo
 	 * We set the OCFS2_LOCK_UPCONVERT_FINISHING flag before clearing
 	 * the OCFS2_LOCK_BUSY flag to prevent the dc thread from
 	 * downconverting the lock before the upconvert has fully completed.
+	 * Do not prevent the dc thread from downconverting if NONBLOCK lock
+	 * had already returned.
 	 */
-	lockres_or_flags(lockres, OCFS2_LOCK_UPCONVERT_FINISHING);
+	if (!(lockres->l_flags & OCFS2_LOCK_NONBLOCK_FINISHED))
+		lockres_or_flags(lockres, OCFS2_LOCK_UPCONVERT_FINISHING);
+	else
+		lockres_clear_flags(lockres, OCFS2_LOCK_NONBLOCK_FINISHED);
 
 	lockres_clear_flags(lockres, OCFS2_LOCK_BUSY);
 }
@@ -1324,13 +1329,12 @@ static void lockres_add_mask_waiter(struct ocfs2_lock_res *lockres,
 
 /* returns 0 if the mw that was removed was already satisfied, -EBUSY
  * if the mask still hadn't reached its goal */
-static int lockres_remove_mask_waiter(struct ocfs2_lock_res *lockres,
+static int __lockres_remove_mask_waiter(struct ocfs2_lock_res *lockres,
 				      struct ocfs2_mask_waiter *mw)
 {
-	unsigned long flags;
 	int ret = 0;
 
-	spin_lock_irqsave(&lockres->l_lock, flags);
+	assert_spin_locked(&lockres->l_lock);
 	if (!list_empty(&mw->mw_item)) {
 		if ((lockres->l_flags & mw->mw_mask) != mw->mw_goal)
 			ret = -EBUSY;
@@ -1338,6 +1342,18 @@ static int lockres_remove_mask_waiter(struct ocfs2_lock_res *lockres,
 		list_del_init(&mw->mw_item);
 		init_completion(&mw->mw_complete);
 	}
+
+	return ret;
+}
+
+static int lockres_remove_mask_waiter(struct ocfs2_lock_res *lockres,
+				      struct ocfs2_mask_waiter *mw)
+{
+	unsigned long flags;
+	int ret = 0;
+
+	spin_lock_irqsave(&lockres->l_lock, flags);
+	ret = __lockres_remove_mask_waiter(lockres, mw);
 	spin_unlock_irqrestore(&lockres->l_lock, flags);
 
 	return ret;
@@ -1373,6 +1389,7 @@ static int __ocfs2_cluster_lock(struct ocfs2_super *osb,
 	unsigned long flags;
 	unsigned int gen;
 	int noqueue_attempted = 0;
+	int dlm_locked = 0;
 
 	ocfs2_init_mask_waiter(&mw);
 
@@ -1481,6 +1498,7 @@ again:
 			ocfs2_recover_from_dlm_error(lockres, 1);
 			goto out;
 		}
+		dlm_locked = 1;
 
 		mlog(0, "lock %s, successful return from ocfs2_dlm_lock\n",
 		     lockres->l_name);
@@ -1514,10 +1532,17 @@ out:
 	if (wait && arg_flags & OCFS2_LOCK_NONBLOCK &&
 	    mw.mw_mask & (OCFS2_LOCK_BUSY|OCFS2_LOCK_BLOCKED)) {
 		wait = 0;
-		if (lockres_remove_mask_waiter(lockres, &mw))
+		spin_lock_irqsave(&lockres->l_lock, flags);
+		if (__lockres_remove_mask_waiter(lockres, &mw)) {
+			if (dlm_locked)
+				lockres_or_flags(lockres,
+					OCFS2_LOCK_NONBLOCK_FINISHED);
+			spin_unlock_irqrestore(&lockres->l_lock, flags);
 			ret = -EAGAIN;
-		else
+		} else {
+			spin_unlock_irqrestore(&lockres->l_lock, flags);
 			goto again;
+		}
 	}
 	if (wait) {
 		ret = ocfs2_wait_for_mask(&mw);
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 324dc93ac896..38f3a562d771 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -295,7 +295,7 @@ out:
 	return ret;
 }
 
-static int ocfs2_set_inode_size(handle_t *handle,
+int ocfs2_set_inode_size(handle_t *handle,
 				struct inode *inode,
 				struct buffer_head *fe_bh,
 				u64 new_i_size)
@@ -441,7 +441,7 @@ out:
 	return status;
 }
 
-static int ocfs2_truncate_file(struct inode *inode,
+int ocfs2_truncate_file(struct inode *inode,
 			       struct buffer_head *di_bh,
 			       u64 new_i_size)
 {
@@ -709,6 +709,13 @@ leave:
 	return status;
 }
 
+int ocfs2_extend_allocation(struct inode *inode, u32 logical_start,
+		u32 clusters_to_add, int mark_unwritten)
+{
+	return __ocfs2_extend_allocation(inode, logical_start,
+			clusters_to_add, mark_unwritten);
+}
+
 /*
  * While a write will already be ordering the data, a truncate will not.
  * Thus, we need to explicitly order the zeroed pages.
@@ -1352,44 +1359,6 @@ out:
 	return ret;
 }
 
-/*
- * Will look for holes and unwritten extents in the range starting at
- * pos for count bytes (inclusive).
- */
-static int ocfs2_check_range_for_holes(struct inode *inode, loff_t pos,
-				       size_t count)
-{
-	int ret = 0;
-	unsigned int extent_flags;
-	u32 cpos, clusters, extent_len, phys_cpos;
-	struct super_block *sb = inode->i_sb;
-
-	cpos = pos >> OCFS2_SB(sb)->s_clustersize_bits;
-	clusters = ocfs2_clusters_for_bytes(sb, pos + count) - cpos;
-
-	while (clusters) {
-		ret = ocfs2_get_clusters(inode, cpos, &phys_cpos, &extent_len,
-					 &extent_flags);
-		if (ret < 0) {
-			mlog_errno(ret);
-			goto out;
-		}
-
-		if (phys_cpos == 0 || (extent_flags & OCFS2_EXT_UNWRITTEN)) {
-			ret = 1;
-			break;
-		}
-
-		if (extent_len > clusters)
-			extent_len = clusters;
-
-		clusters -= extent_len;
-		cpos += extent_len;
-	}
-out:
-	return ret;
-}
-
 static int ocfs2_write_remove_suid(struct inode *inode)
 {
 	int ret;
@@ -1803,7 +1772,7 @@ static int ocfs2_remove_inode_range(struct inode *inode,
 
 		ret = ocfs2_remove_btree_range(inode, &et, trunc_cpos,
 					       phys_cpos, trunc_len, flags,
-					       &dealloc, refcount_loc);
+					       &dealloc, refcount_loc, false);
 		if (ret < 0) {
 			mlog_errno(ret);
 			goto out;
@@ -2109,6 +2078,9 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
 	struct dentry *dentry = file->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
 	loff_t saved_pos = 0, end;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	int full_coherency = !(osb->s_mount_opt &
+		OCFS2_MOUNT_COHERENCY_BUFFERED);
 
 	/*
 	 * We start with a read level meta lock and only jump to an ex
@@ -2197,23 +2169,11 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
 		 * one node could wind up truncating another
 		 * nodes writes.
 		 */
-		if (end > i_size_read(inode)) {
+		if (end > i_size_read(inode) && !full_coherency) {
 			*direct_io = 0;
 			break;
 		}
 
-		/*
-		 * We don't fill holes during direct io, so
-		 * check for them here. If any are found, the
-		 * caller will have to retake some cluster
-		 * locks and initiate the io as buffered.
-		 */
-		ret = ocfs2_check_range_for_holes(inode, saved_pos, count);
-		if (ret == 1) {
-			*direct_io = 0;
-			ret = 0;
-		} else if (ret < 0)
-			mlog_errno(ret);
 		break;
 	}
 
@@ -2243,6 +2203,7 @@ static ssize_t ocfs2_file_write_iter(struct kiocb *iocb,
 	u32 old_clusters;
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
+	struct address_space *mapping = file->f_mapping;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	int full_coherency = !(osb->s_mount_opt &
 			       OCFS2_MOUNT_COHERENCY_BUFFERED);
@@ -2357,11 +2318,50 @@ relock:
 
 	iov_iter_truncate(from, count);
 	if (direct_io) {
+		loff_t endbyte;
+		ssize_t written_buffered;
 		written = generic_file_direct_write(iocb, from, *ppos);
-		if (written < 0) {
+		if (written < 0 || written == count) {
 			ret = written;
 			goto out_dio;
 		}
+
+		/*
+		 * direct-io write to a hole: fall through to buffered I/O
+		 * for completing the rest of the request.
+		 */
+		count -= written;
+		written_buffered = generic_perform_write(file, from, *ppos);
+		/*
+		 * If generic_file_buffered_write() returned a synchronous error
+		 * then we want to return the number of bytes which were
+		 * direct-written, or the error code if that was zero. Note
+		 * that this differs from normal direct-io semantics, which
+		 * will return -EFOO even if some bytes were written.
+		 */
+		if (written_buffered < 0) {
+			ret = written_buffered;
+			goto out;
+		}
+
+		/* We need to ensure that the page cache pages are written to
+		 * disk and invalidated to preserve the expected O_DIRECT
+		 * semantics.
+		 */
+		endbyte = *ppos + written_buffered - written - 1;
+		ret = filemap_write_and_wait_range(file->f_mapping, *ppos,
+				endbyte);
+		if (ret == 0) {
+			written = written_buffered;
+			invalidate_mapping_pages(mapping,
+					*ppos >> PAGE_CACHE_SHIFT,
+					endbyte >> PAGE_CACHE_SHIFT);
+		} else {
+			/*
+			 * We don't know how much we wrote, so just return
+			 * the number of bytes which were direct-written
+			 */
+		}
 	} else {
 		current->backing_dev_info = file->f_mapping->backing_dev_info;
 		written = generic_perform_write(file, from, *ppos);
@@ -2381,9 +2381,7 @@ out_dio:
 		if (ret < 0)
 			written = ret;
 
-		if (!ret && ((old_size != i_size_read(inode)) ||
-			     (old_clusters != OCFS2_I(inode)->ip_clusters) ||
-			     has_refcount)) {
+		if (!ret) {
 			ret = jbd2_journal_force_commit(osb->journal->j_journal);
 			if (ret < 0)
 				written = ret;
diff --git a/fs/ocfs2/file.h b/fs/ocfs2/file.h
index 97bf761c9e7c..e8c62f22215c 100644
--- a/fs/ocfs2/file.h
+++ b/fs/ocfs2/file.h
@@ -51,13 +51,22 @@ int ocfs2_add_inode_data(struct ocfs2_super *osb,
 			 struct ocfs2_alloc_context *data_ac,
 			 struct ocfs2_alloc_context *meta_ac,
 			 enum ocfs2_alloc_restarted *reason_ret);
+int ocfs2_set_inode_size(handle_t *handle,
+		struct inode *inode,
+		struct buffer_head *fe_bh,
+		u64 new_i_size);
 int ocfs2_simple_size_update(struct inode *inode,
 			     struct buffer_head *di_bh,
 			     u64 new_i_size);
+int ocfs2_truncate_file(struct inode *inode,
+		struct buffer_head *di_bh,
+		u64 new_i_size);
 int ocfs2_extend_no_holes(struct inode *inode, struct buffer_head *di_bh,
 			  u64 new_i_size, u64 zero_to);
 int ocfs2_zero_extend(struct inode *inode, struct buffer_head *di_bh,
 		      loff_t zero_to);
+int ocfs2_extend_allocation(struct inode *inode, u32 logical_start,
+		u32 clusters_to_add, int mark_unwritten);
 int ocfs2_setattr(struct dentry *dentry, struct iattr *attr);
 int ocfs2_getattr(struct vfsmount *mnt, struct dentry *dentry,
 		  struct kstat *stat);
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index 437de7f768c6..ae1a5e9f8f13 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -540,8 +540,7 @@ bail:
 	if (status < 0)
 		make_bad_inode(inode);
 
-	if (args && bh)
-		brelse(bh);
+	brelse(bh);
 
 	return status;
 }
@@ -1192,17 +1191,9 @@ void ocfs2_evict_inode(struct inode *inode)
 int ocfs2_drop_inode(struct inode *inode)
 {
 	struct ocfs2_inode_info *oi = OCFS2_I(inode);
-	int res;
-
 	trace_ocfs2_drop_inode((unsigned long long)oi->ip_blkno,
 				inode->i_nlink, oi->ip_flags);
-
-	if (oi->ip_flags & OCFS2_INODE_MAYBE_ORPHANED)
-		res = 1;
-	else
-		res = generic_drop_inode(inode);
-
-	return res;
+	return 1;
 }
 
 /*
diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h
index ca3431ee7f24..9314ab94cd23 100644
--- a/fs/ocfs2/inode.h
+++ b/fs/ocfs2/inode.h
@@ -82,6 +82,8 @@ struct ocfs2_inode_info
 	tid_t i_datasync_tid;
 
 	struct dquot *i_dquot[MAXQUOTAS];
+
+	wait_queue_head_t append_dio_wq;
 };
 
 /*
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 4f502382180f..e238bbc27a3c 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -50,6 +50,8 @@
 #include "sysfile.h"
 #include "uptodate.h"
 #include "quota.h"
+#include "file.h"
+#include "namei.h"
 
 #include "buffer_head_io.h"
 #include "ocfs2_trace.h"
@@ -69,13 +71,15 @@ static int ocfs2_journal_toggle_dirty(struct ocfs2_super *osb,
 static int ocfs2_trylock_journal(struct ocfs2_super *osb,
 				 int slot_num);
 static int ocfs2_recover_orphans(struct ocfs2_super *osb,
-				 int slot);
+				 int slot,
+				 enum ocfs2_orphan_reco_type orphan_reco_type);
 static int ocfs2_commit_thread(void *arg);
 static void ocfs2_queue_recovery_completion(struct ocfs2_journal *journal,
 					    int slot_num,
 					    struct ocfs2_dinode *la_dinode,
 					    struct ocfs2_dinode *tl_dinode,
-					    struct ocfs2_quota_recovery *qrec);
+					    struct ocfs2_quota_recovery *qrec,
+					    enum ocfs2_orphan_reco_type orphan_reco_type);
 
 static inline int ocfs2_wait_on_mount(struct ocfs2_super *osb)
 {
@@ -149,7 +153,8 @@ int ocfs2_compute_replay_slots(struct ocfs2_super *osb)
 	return 0;
 }
 
-void ocfs2_queue_replay_slots(struct ocfs2_super *osb)
+void ocfs2_queue_replay_slots(struct ocfs2_super *osb,
+		enum ocfs2_orphan_reco_type orphan_reco_type)
 {
 	struct ocfs2_replay_map *replay_map = osb->replay_map;
 	int i;
@@ -163,7 +168,8 @@ void ocfs2_queue_replay_slots(struct ocfs2_super *osb)
 	for (i = 0; i < replay_map->rm_slots; i++)
 		if (replay_map->rm_replay_slots[i])
 			ocfs2_queue_recovery_completion(osb->journal, i, NULL,
-							NULL, NULL);
+							NULL, NULL,
+							orphan_reco_type);
 	replay_map->rm_state = REPLAY_DONE;
 }
 
@@ -1174,6 +1180,7 @@ struct ocfs2_la_recovery_item {
 	struct ocfs2_dinode	*lri_la_dinode;
 	struct ocfs2_dinode	*lri_tl_dinode;
 	struct ocfs2_quota_recovery *lri_qrec;
+	enum ocfs2_orphan_reco_type  lri_orphan_reco_type;
 };
 
 /* Does the second half of the recovery process. By this point, the
@@ -1195,6 +1202,7 @@ void ocfs2_complete_recovery(struct work_struct *work)
 	struct ocfs2_dinode *la_dinode, *tl_dinode;
 	struct ocfs2_la_recovery_item *item, *n;
 	struct ocfs2_quota_recovery *qrec;
+	enum ocfs2_orphan_reco_type orphan_reco_type;
 	LIST_HEAD(tmp_la_list);
 
 	trace_ocfs2_complete_recovery(
@@ -1212,6 +1220,7 @@ void ocfs2_complete_recovery(struct work_struct *work)
 		la_dinode = item->lri_la_dinode;
 		tl_dinode = item->lri_tl_dinode;
 		qrec = item->lri_qrec;
+		orphan_reco_type = item->lri_orphan_reco_type;
 
 		trace_ocfs2_complete_recovery_slot(item->lri_slot,
 			la_dinode ? le64_to_cpu(la_dinode->i_blkno) : 0,
@@ -1236,7 +1245,8 @@ void ocfs2_complete_recovery(struct work_struct *work)
 			kfree(tl_dinode);
 		}
 
-		ret = ocfs2_recover_orphans(osb, item->lri_slot);
+		ret = ocfs2_recover_orphans(osb, item->lri_slot,
+				orphan_reco_type);
 		if (ret < 0)
 			mlog_errno(ret);
 
@@ -1261,7 +1271,8 @@ static void ocfs2_queue_recovery_completion(struct ocfs2_journal *journal,
 					    int slot_num,
 					    struct ocfs2_dinode *la_dinode,
 					    struct ocfs2_dinode *tl_dinode,
-					    struct ocfs2_quota_recovery *qrec)
+					    struct ocfs2_quota_recovery *qrec,
+					    enum ocfs2_orphan_reco_type orphan_reco_type)
 {
 	struct ocfs2_la_recovery_item *item;
 
@@ -1285,6 +1296,7 @@ static void ocfs2_queue_recovery_completion(struct ocfs2_journal *journal,
 	item->lri_slot = slot_num;
 	item->lri_tl_dinode = tl_dinode;
 	item->lri_qrec = qrec;
+	item->lri_orphan_reco_type = orphan_reco_type;
 
 	spin_lock(&journal->j_lock);
 	list_add_tail(&item->lri_list, &journal->j_la_cleanups);
@@ -1304,7 +1316,8 @@ void ocfs2_complete_mount_recovery(struct ocfs2_super *osb)
 	/* No need to queue up our truncate_log as regular cleanup will catch
 	 * that */
 	ocfs2_queue_recovery_completion(journal, osb->slot_num,
-					osb->local_alloc_copy, NULL, NULL);
+					osb->local_alloc_copy, NULL, NULL,
+					ORPHAN_NEED_TRUNCATE);
 	ocfs2_schedule_truncate_log_flush(osb, 0);
 
 	osb->local_alloc_copy = NULL;
@@ -1312,7 +1325,7 @@ void ocfs2_complete_mount_recovery(struct ocfs2_super *osb)
 
 	/* queue to recover orphan slots for all offline slots */
 	ocfs2_replay_map_set_state(osb, REPLAY_NEEDED);
-	ocfs2_queue_replay_slots(osb);
+	ocfs2_queue_replay_slots(osb, ORPHAN_NEED_TRUNCATE);
 	ocfs2_free_replay_slots(osb);
 }
 
@@ -1323,7 +1336,8 @@ void ocfs2_complete_quota_recovery(struct ocfs2_super *osb)
 						osb->slot_num,
 						NULL,
 						NULL,
-						osb->quota_rec);
+						osb->quota_rec,
+						ORPHAN_NEED_TRUNCATE);
 		osb->quota_rec = NULL;
 	}
 }
@@ -1360,7 +1374,7 @@ restart:
 
 	/* queue recovery for our own slot */
 	ocfs2_queue_recovery_completion(osb->journal, osb->slot_num, NULL,
-					NULL, NULL);
+					NULL, NULL, ORPHAN_NO_NEED_TRUNCATE);
 
 	spin_lock(&osb->osb_lock);
 	while (rm->rm_used) {
@@ -1419,13 +1433,14 @@ skip_recovery:
 			continue;
 		}
 		ocfs2_queue_recovery_completion(osb->journal, rm_quota[i],
-						NULL, NULL, qrec);
+						NULL, NULL, qrec,
+						ORPHAN_NEED_TRUNCATE);
 	}
 
 	ocfs2_super_unlock(osb, 1);
 
 	/* queue recovery for offline slots */
-	ocfs2_queue_replay_slots(osb);
+	ocfs2_queue_replay_slots(osb, ORPHAN_NEED_TRUNCATE);
 
 bail:
 	mutex_lock(&osb->recovery_lock);
@@ -1712,7 +1727,7 @@ static int ocfs2_recover_node(struct ocfs2_super *osb,
 
 	/* This will kfree the memory pointed to by la_copy and tl_copy */
 	ocfs2_queue_recovery_completion(osb->journal, slot_num, la_copy,
-					tl_copy, NULL);
+					tl_copy, NULL, ORPHAN_NEED_TRUNCATE);
 
 	status = 0;
 done:
@@ -1902,7 +1917,7 @@ void ocfs2_queue_orphan_scan(struct ocfs2_super *osb)
 
 	for (i = 0; i < osb->max_slots; i++)
 		ocfs2_queue_recovery_completion(osb->journal, i, NULL, NULL,
-						NULL);
+						NULL, ORPHAN_NO_NEED_TRUNCATE);
 	/*
 	 * We queued a recovery on orphan slots, increment the sequence
 	 * number and update LVB so other node will skip the scan for a while
@@ -2090,6 +2105,39 @@ static void ocfs2_clear_recovering_orphan_dir(struct ocfs2_super *osb,
 	ocfs2_node_map_clear_bit(osb, &osb->osb_recovering_orphan_dirs, slot);
 }
 
+static int ocfs2_truncate_file_locked(struct inode *inode)
+{
+	struct buffer_head *di_bh = NULL;
+	int ret;
+
+	ret = ocfs2_rw_lock(inode, 1);
+	if (ret < 0) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ret = ocfs2_inode_lock(inode, &di_bh, 1);
+	if (ret < 0) {
+		ocfs2_rw_unlock(inode, 1);
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ret = ocfs2_truncate_file(inode, di_bh, i_size_read(inode));
+	if (ret < 0) {
+		if (ret != -ENOSPC)
+			mlog_errno(ret);
+		ret = -ENOSPC;
+	}
+
+	ocfs2_inode_unlock(inode, 1);
+	ocfs2_rw_unlock(inode, 1);
+	brelse(di_bh);
+
+out:
+	return ret;
+}
+
 /*
  * Orphan recovery. Each mounted node has it's own orphan dir which we
  * must run during recovery. Our strategy here is to build a list of
@@ -2109,7 +2157,8 @@ static void ocfs2_clear_recovering_orphan_dir(struct ocfs2_super *osb,
  *   advertising our state to ocfs2_delete_inode().
  */
 static int ocfs2_recover_orphans(struct ocfs2_super *osb,
-				 int slot)
+				 int slot,
+				 enum ocfs2_orphan_reco_type orphan_reco_type)
 {
 	int ret = 0;
 	struct inode *inode = NULL;
@@ -2134,12 +2183,38 @@ static int ocfs2_recover_orphans(struct ocfs2_super *osb,
 
 		iter = oi->ip_next_orphan;
 
-		spin_lock(&oi->ip_lock);
-		/* Set the proper information to get us going into
-		 * ocfs2_delete_inode. */
-		oi->ip_flags |= OCFS2_INODE_MAYBE_ORPHANED;
-		spin_unlock(&oi->ip_lock);
+		/*
+		 * We need to take and drop the inode lock to
+		 * force read inode from disk.
+		 */
+		ret = ocfs2_inode_lock(inode, NULL, 0);
+		if (ret) {
+			mlog_errno(ret);
+			goto next;
+		}
+		ocfs2_inode_unlock(inode, 0);
+
+		if (inode->i_nlink == 0) {
+			spin_lock(&oi->ip_lock);
+			/* Set the proper information to get us going into
+			 * ocfs2_delete_inode. */
+			oi->ip_flags |= OCFS2_INODE_MAYBE_ORPHANED;
+			spin_unlock(&oi->ip_lock);
+		} else if (orphan_reco_type == ORPHAN_NEED_TRUNCATE) {
+			ret = ocfs2_truncate_file_locked(inode);
+			if (ret) {
+				mlog_errno(ret);
+				goto next;
+			}
+
+			ret = ocfs2_del_inode_from_orphan(osb, inode, 0, 0);
+			if (ret)
+				mlog_errno(ret);
+
+			wake_up(&OCFS2_I(inode)->append_dio_wq);
+		} /* else if ORPHAN_NO_NEED_TRUNCATE, do nothing */
 
+next:
 		iput(inode);
 
 		inode = iter;
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index 7f8cde94abfe..f4cd3c3e9fb7 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -472,6 +472,11 @@ static inline int ocfs2_unlink_credits(struct super_block *sb)
  * orphan dir index leaf */
 #define OCFS2_DELETE_INODE_CREDITS (3 * OCFS2_INODE_UPDATE_CREDITS + 4)
 
+/* dinode + orphan dir dinode + extent tree leaf block + orphan dir entry +
+ * orphan dir index root + orphan dir index leaf */
+#define OCFS2_INODE_ADD_TO_ORPHAN_CREDITS  (2 * OCFS2_INODE_UPDATE_CREDITS + 4)
+#define OCFS2_INODE_DEL_FROM_ORPHAN_CREDITS  OCFS2_INODE_ADD_TO_ORPHAN_CREDITS
+
 /* dinode update, old dir dinode update, new dir dinode update, old
  * dir dir entry, new dir dir entry, dir entry update for renaming
  * directory + target unlink + 3 x dir index leaves */
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index b931e04e3388..f15b560e1bbe 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -81,6 +81,12 @@ static int ocfs2_prepare_orphan_dir(struct ocfs2_super *osb,
 				    char *name,
 				    struct ocfs2_dir_lookup_result *lookup);
 
+static int ocfs2_dio_prepare_orphan_dir(struct ocfs2_super *osb,
+		struct inode **ret_orphan_dir,
+		u64 blkno,
+		char *name,
+		struct ocfs2_dir_lookup_result *lookup);
+
 static int ocfs2_orphan_add(struct ocfs2_super *osb,
 			    handle_t *handle,
 			    struct inode *inode,
@@ -89,6 +95,15 @@ static int ocfs2_orphan_add(struct ocfs2_super *osb,
 			    struct ocfs2_dir_lookup_result *lookup,
 			    struct inode *orphan_dir_inode);
 
+static int ocfs2_dio_orphan_add(struct ocfs2_super *osb,
+		handle_t *handle,
+		struct inode *inode,
+		struct buffer_head *fe_bh,
+		char *name,
+		struct ocfs2_dir_lookup_result *lookup,
+		struct inode *orphan_dir_inode,
+		bool orphaned);
+
 static int ocfs2_create_symlink_data(struct ocfs2_super *osb,
 				     handle_t *handle,
 				     struct inode *inode,
@@ -2137,6 +2152,51 @@ out:
 	return ret;
 }
 
+/**
+ * Copy from ocfs2_prepare_orphan_dir(). The difference:
+ * It will still lock orphan dir if entry exists.
+ * Caller must take care of -EEXIST and responsible for unlock.
+*/
+static int ocfs2_dio_prepare_orphan_dir(struct ocfs2_super *osb,
+				    struct inode **ret_orphan_dir,
+				    u64 blkno,
+				    char *name,
+				    struct ocfs2_dir_lookup_result *lookup)
+{
+	struct inode *orphan_dir_inode = NULL;
+	struct buffer_head *orphan_dir_bh = NULL;
+	int ret = 0;
+
+	ret = ocfs2_lookup_lock_orphan_dir(osb, &orphan_dir_inode,
+					   &orphan_dir_bh);
+	if (ret < 0) {
+		mlog_errno(ret);
+		return ret;
+	}
+
+	ret = __ocfs2_prepare_orphan_dir(orphan_dir_inode, orphan_dir_bh,
+					 blkno, name, lookup);
+	if (ret < 0 && ret != -EEXIST) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	*ret_orphan_dir = orphan_dir_inode;
+
+out:
+	brelse(orphan_dir_bh);
+
+	if (ret && ret != -EEXIST) {
+		ocfs2_inode_unlock(orphan_dir_inode, 1);
+		mutex_unlock(&orphan_dir_inode->i_mutex);
+		iput(orphan_dir_inode);
+	}
+
+	if (ret && ret != -EEXIST)
+		mlog_errno(ret);
+	return ret;
+}
+
 static int ocfs2_orphan_add(struct ocfs2_super *osb,
 			    handle_t *handle,
 			    struct inode *inode,
@@ -2226,6 +2286,100 @@ leave:
 	return status;
 }
 
+/**
+ * Copy from ocfs2_orphan_add, the difference:
+ * 1. Do not add entry if already added.
+ * 2. Update di flags OCFS2_DIO_ORPHANED_FL and record the
+ * orphan slot.
+*/
+static int ocfs2_dio_orphan_add(struct ocfs2_super *osb,
+			    handle_t *handle,
+			    struct inode *inode,
+			    struct buffer_head *fe_bh,
+			    char *name,
+			    struct ocfs2_dir_lookup_result *lookup,
+			    struct inode *orphan_dir_inode,
+			    bool orphaned)
+{
+	struct buffer_head *orphan_dir_bh = NULL;
+	int status = 0;
+	struct ocfs2_dinode *orphan_fe;
+	struct ocfs2_dinode *fe = (struct ocfs2_dinode *) fe_bh->b_data;
+
+	trace_ocfs2_dio_orphan_add_begin(
+				(unsigned long long)OCFS2_I(inode)->ip_blkno);
+
+	status = ocfs2_read_inode_block(orphan_dir_inode, &orphan_dir_bh);
+	if (status < 0) {
+		mlog_errno(status);
+		goto leave;
+	}
+
+	status = ocfs2_journal_access_di(handle,
+					 INODE_CACHE(orphan_dir_inode),
+					 orphan_dir_bh,
+					 OCFS2_JOURNAL_ACCESS_WRITE);
+	if (status < 0) {
+		mlog_errno(status);
+		goto leave;
+	}
+
+	/*
+	 * We're going to journal the change of i_flags and i_dio_orphaned_slot.
+	 * It's safe anyway, though some callers may duplicate the journaling.
+	 * Journaling within the func just make the logic look more
+	 * straightforward.
+	 */
+	status = ocfs2_journal_access_di(handle,
+					 INODE_CACHE(inode),
+					 fe_bh,
+					 OCFS2_JOURNAL_ACCESS_WRITE);
+	if (status < 0) {
+		mlog_errno(status);
+		goto leave;
+	}
+
+	/* we're a cluster, and nlink can change on disk from
+	 * underneath us... */
+	orphan_fe = (struct ocfs2_dinode *) orphan_dir_bh->b_data;
+	if (S_ISDIR(inode->i_mode))
+		ocfs2_add_links_count(orphan_fe, 1);
+	set_nlink(orphan_dir_inode, ocfs2_read_links_count(orphan_fe));
+	ocfs2_journal_dirty(handle, orphan_dir_bh);
+
+	/* It may already be orphaned by ocfs2_unlink/ocfs2_rename */
+	if (!orphaned) {
+		status = __ocfs2_add_entry(handle, orphan_dir_inode, name,
+				   OCFS2_ORPHAN_NAMELEN, inode,
+				   OCFS2_I(inode)->ip_blkno,
+				   orphan_dir_bh, lookup);
+		if (status < 0) {
+			mlog_errno(status);
+			goto rollback;
+		}
+	}
+
+	/* Update flag OCFS2_DIO_ORPHANED_FL and record the orphan slot */
+	fe->i_flags |= cpu_to_le32(OCFS2_DIO_ORPHANED_FL);
+	fe->i_dio_orphaned_slot = cpu_to_le16(osb->slot_num);
+
+	ocfs2_journal_dirty(handle, fe_bh);
+
+	trace_ocfs2_dio_orphan_add_end((unsigned long long)OCFS2_I(inode)->ip_blkno,
+				   osb->slot_num);
+
+rollback:
+	if (status < 0) {
+		if (S_ISDIR(inode->i_mode))
+			ocfs2_add_links_count(orphan_fe, -1);
+		set_nlink(orphan_dir_inode, ocfs2_read_links_count(orphan_fe));
+	}
+
+leave:
+	brelse(orphan_dir_bh);
+
+	return status;
+}
 /* unlike orphan_add, we expect the orphan dir to already be locked here. */
 int ocfs2_orphan_del(struct ocfs2_super *osb,
 		     handle_t *handle,
@@ -2500,6 +2654,200 @@ leave:
 	return status;
 }
 
+static int ocfs2_dio_orphan_recovered(struct inode *inode)
+{
+	int ret;
+	struct buffer_head *di_bh = NULL;
+	struct ocfs2_dinode *di = NULL;
+
+	ret = ocfs2_inode_lock(inode, &di_bh, 1);
+	if (ret < 0) {
+		mlog_errno(ret);
+		return 0;
+	}
+
+	di = (struct ocfs2_dinode *) di_bh->b_data;
+	ret = !(di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL));
+	ocfs2_inode_unlock(inode, 1);
+	brelse(di_bh);
+
+	return ret;
+}
+
+int ocfs2_add_inode_to_orphan(struct ocfs2_super *osb,
+	struct inode *inode)
+{
+	char orphan_name[OCFS2_ORPHAN_NAMELEN + 1];
+	struct inode *orphan_dir_inode = NULL;
+	struct ocfs2_dir_lookup_result orphan_insert = { NULL, };
+	struct buffer_head *di_bh = NULL;
+	int status = 0;
+	handle_t *handle = NULL;
+	struct ocfs2_dinode *di = NULL;
+	bool orphaned = false;
+
+restart:
+	status = ocfs2_inode_lock(inode, &di_bh, 1);
+	if (status < 0) {
+		mlog_errno(status);
+		goto bail;
+	}
+
+	di = (struct ocfs2_dinode *) di_bh->b_data;
+	/*
+	 * Another append dio crashed?
+	 * If so, wait for recovery first.
+	 */
+	if (unlikely(di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL))) {
+		ocfs2_inode_unlock(inode, 1);
+		brelse(di_bh);
+		wait_event_interruptible(OCFS2_I(inode)->append_dio_wq,
+				ocfs2_dio_orphan_recovered(inode));
+		goto restart;
+	}
+
+	status = ocfs2_dio_prepare_orphan_dir(osb, &orphan_dir_inode,
+			OCFS2_I(inode)->ip_blkno,
+			orphan_name,
+			&orphan_insert);
+	if (status < 0 && status != -EEXIST) {
+		mlog_errno(status);
+		goto bail_unlock_inode;
+	} else if (status == -EEXIST) {
+		mlog(ML_NOTICE, "inode %llu already added to "
+				"orphan dir %llu.\n",
+				OCFS2_I(inode)->ip_blkno,
+				OCFS2_I(orphan_dir_inode)->ip_blkno);
+		if (!(di->i_flags & cpu_to_le32(OCFS2_ORPHANED_FL))) {
+			mlog_errno(status);
+			goto bail_unlock_orphan;
+		}
+		orphaned = true;
+	}
+
+	handle = ocfs2_start_trans(osb,
+			OCFS2_INODE_ADD_TO_ORPHAN_CREDITS);
+	if (IS_ERR(handle)) {
+		status = PTR_ERR(handle);
+		goto bail_unlock_orphan;
+	}
+
+	status = ocfs2_dio_orphan_add(osb, handle, inode, di_bh, orphan_name,
+			&orphan_insert, orphan_dir_inode, orphaned);
+	if (status)
+		mlog_errno(status);
+
+	ocfs2_commit_trans(osb, handle);
+
+bail_unlock_orphan:
+	ocfs2_inode_unlock(orphan_dir_inode, 1);
+	mutex_unlock(&orphan_dir_inode->i_mutex);
+	iput(orphan_dir_inode);
+
+	ocfs2_free_dir_lookup_result(&orphan_insert);
+
+bail_unlock_inode:
+	ocfs2_inode_unlock(inode, 1);
+	brelse(di_bh);
+
+bail:
+	return status;
+}
+
+int ocfs2_del_inode_from_orphan(struct ocfs2_super *osb,
+		struct inode *inode, int update_isize,
+		loff_t end)
+{
+	struct inode *orphan_dir_inode = NULL;
+	struct buffer_head *orphan_dir_bh = NULL;
+	struct buffer_head *di_bh = NULL;
+	struct ocfs2_dinode *di = NULL;
+	handle_t *handle = NULL;
+	int status = 0;
+
+	status = ocfs2_inode_lock(inode, &di_bh, 1);
+	if (status < 0) {
+		mlog_errno(status);
+		goto bail;
+	}
+	di = (struct ocfs2_dinode *) di_bh->b_data;
+
+	orphan_dir_inode = ocfs2_get_system_file_inode(osb,
+			ORPHAN_DIR_SYSTEM_INODE,
+			le16_to_cpu(di->i_dio_orphaned_slot));
+	if (!orphan_dir_inode) {
+		status = -EEXIST;
+		mlog_errno(status);
+		goto bail_unlock_inode;
+	}
+
+	mutex_lock(&orphan_dir_inode->i_mutex);
+	status = ocfs2_inode_lock(orphan_dir_inode, &orphan_dir_bh, 1);
+	if (status < 0) {
+		mutex_unlock(&orphan_dir_inode->i_mutex);
+		iput(orphan_dir_inode);
+		mlog_errno(status);
+		goto bail_unlock_inode;
+	}
+
+	handle = ocfs2_start_trans(osb,
+			OCFS2_INODE_DEL_FROM_ORPHAN_CREDITS);
+	if (IS_ERR(handle)) {
+		status = PTR_ERR(handle);
+		goto bail_unlock_orphan;
+	}
+
+	BUG_ON(!(di->i_flags & cpu_to_le32(OCFS2_DIO_ORPHANED_FL)));
+
+	/* Only delete entry if OCFS2_ORPHANED_FL not set, or
+	 * there are two entries added */
+	if (!(di->i_flags & cpu_to_le32(OCFS2_ORPHANED_FL)) ||
+			(di->i_flags & cpu_to_le32(OCFS2_ORPHANED_FL) &&
+			(di->i_orphaned_slot != di->i_dio_orphaned_slot))) {
+		status = ocfs2_orphan_del(osb, handle, orphan_dir_inode,
+				inode, orphan_dir_bh);
+		if (status < 0) {
+			mlog_errno(status);
+			goto bail_commit;
+		}
+	}
+
+	status = ocfs2_journal_access_di(handle,
+			INODE_CACHE(inode),
+			di_bh,
+			OCFS2_JOURNAL_ACCESS_WRITE);
+	if (status < 0) {
+		mlog_errno(status);
+		goto bail_commit;
+	}
+
+	di->i_flags &= ~cpu_to_le32(OCFS2_DIO_ORPHANED_FL);
+	di->i_dio_orphaned_slot = 0;
+
+	if (update_isize) {
+		status = ocfs2_set_inode_size(handle, inode, di_bh, end);
+		if (status)
+			mlog_errno(status);
+	} else
+		ocfs2_journal_dirty(handle, di_bh);
+
+bail_commit:
+	ocfs2_commit_trans(osb, handle);
+
+bail_unlock_orphan:
+	ocfs2_inode_unlock(orphan_dir_inode, 1);
+	mutex_unlock(&orphan_dir_inode->i_mutex);
+	brelse(orphan_dir_bh);
+	iput(orphan_dir_inode);
+
+bail_unlock_inode:
+	ocfs2_inode_unlock(inode, 1);
+	brelse(di_bh);
+
+bail:
+	return status;
+}
+
 int ocfs2_mv_orphaned_inode_to_new(struct inode *dir,
 				   struct inode *inode,
 				   struct dentry *dentry)
diff --git a/fs/ocfs2/namei.h b/fs/ocfs2/namei.h
index e5d059d4f115..562554026a60 100644
--- a/fs/ocfs2/namei.h
+++ b/fs/ocfs2/namei.h
@@ -38,6 +38,11 @@ int ocfs2_orphan_del(struct ocfs2_super *osb,
 int ocfs2_create_inode_in_orphan(struct inode *dir,
 				 int mode,
 				 struct inode **new_inode);
+int ocfs2_add_inode_to_orphan(struct ocfs2_super *osb,
+		struct inode *inode);
+int ocfs2_del_inode_from_orphan(struct ocfs2_super *osb,
+		struct inode *inode, int update_isize,
+		loff_t end);
 int ocfs2_mv_orphaned_inode_to_new(struct inode *dir,
 				   struct inode *new_inode,
 				   struct dentry *new_dentry);
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index bbec539230fd..131cc1cd8563 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -144,6 +144,12 @@ enum ocfs2_unlock_action {
 						     * before the upconvert
 						     * has completed */
 
+#define OCFS2_LOCK_NONBLOCK_FINISHED (0x00001000) /* NONBLOCK cluster
+						   * lock has already
+						   * returned, do not block
+						   * dc thread from
+						   * downconverting */
+
 struct ocfs2_lock_res_ops;
 
 typedef void (*ocfs2_lock_callback)(int status, unsigned long data);
@@ -203,6 +209,11 @@ struct ocfs2_lock_res {
 #endif
 };
 
+enum ocfs2_orphan_reco_type {
+	ORPHAN_NO_NEED_TRUNCATE = 0,
+	ORPHAN_NEED_TRUNCATE,
+};
+
 enum ocfs2_orphan_scan_state {
 	ORPHAN_SCAN_ACTIVE,
 	ORPHAN_SCAN_INACTIVE
@@ -718,6 +729,16 @@ static inline unsigned int ocfs2_clusters_for_bytes(struct super_block *sb,
 	return clusters;
 }
 
+static inline unsigned int ocfs2_bytes_to_clusters(struct super_block *sb,
+		u64 bytes)
+{
+	int cl_bits = OCFS2_SB(sb)->s_clustersize_bits;
+	unsigned int clusters;
+
+	clusters = (unsigned int)(bytes >> cl_bits);
+	return clusters;
+}
+
 static inline u64 ocfs2_blocks_for_bytes(struct super_block *sb,
 					 u64 bytes)
 {
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index 938387a10d5d..e933ea2e976e 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -229,6 +229,7 @@
 #define OCFS2_CHAIN_FL		(0x00000400)	/* Chain allocator */
 #define OCFS2_DEALLOC_FL	(0x00000800)	/* Truncate log */
 #define OCFS2_QUOTA_FL		(0x00001000)	/* Quota file */
+#define OCFS2_DIO_ORPHANED_FL	(0X00002000)	/* On the orphan list especially for dio */
 
 /*
  * Flags on ocfs2_dinode.i_dyn_features
@@ -729,7 +730,9 @@ struct ocfs2_dinode {
 					   inode belongs to.  Only valid
 					   if allocated from a
 					   discontiguous block group */
-/*A0*/	__le64 i_reserved2[3];
+/*A0*/	__le16 i_dio_orphaned_slot;	/* only used for append dio write */
+	__le16 i_reserved1[3];
+	__le64 i_reserved2[2];
 /*B8*/	union {
 		__le64 i_pad1;		/* Generic way to refer to this
 					   64bit union */
diff --git a/fs/ocfs2/ocfs2_trace.h b/fs/ocfs2/ocfs2_trace.h
index 6cb019b7c6a8..2d471cc879cb 100644
--- a/fs/ocfs2/ocfs2_trace.h
+++ b/fs/ocfs2/ocfs2_trace.h
@@ -2373,6 +2373,9 @@ DEFINE_OCFS2_ULL_EVENT(ocfs2_orphan_add_begin);
 
 DEFINE_OCFS2_ULL_UINT_EVENT(ocfs2_orphan_add_end);
 
+DEFINE_OCFS2_ULL_EVENT(ocfs2_dio_orphan_add_begin);
+DEFINE_OCFS2_ULL_UINT_EVENT(ocfs2_dio_orphan_add_end);
+
 TRACE_EVENT(ocfs2_orphan_del,
 	TP_PROTO(unsigned long long dir, const char *name, int namelen),
 	TP_ARGS(dir, name, namelen),
diff --git a/fs/ocfs2/slot_map.c b/fs/ocfs2/slot_map.c
index a88b2a4fcc85..d5493e361a38 100644
--- a/fs/ocfs2/slot_map.c
+++ b/fs/ocfs2/slot_map.c
@@ -306,7 +306,7 @@ int ocfs2_slot_to_node_num_locked(struct ocfs2_super *osb, int slot_num,
 	assert_spin_locked(&osb->osb_lock);
 
 	BUG_ON(slot_num < 0);
-	BUG_ON(slot_num > osb->max_slots);
+	BUG_ON(slot_num >= osb->max_slots);
 
 	if (!si->si_slots[slot_num].sl_valid)
 		return -ENOENT;
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 0945814ddb7b..04ee6d16cb37 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1629,8 +1629,9 @@ static int __init ocfs2_init(void)
 
 	ocfs2_debugfs_root = debugfs_create_dir("ocfs2", NULL);
 	if (!ocfs2_debugfs_root) {
-		status = -EFAULT;
+		status = -ENOMEM;
 		mlog(ML_ERROR, "Unable to create ocfs2 debugfs root.\n");
+		goto out4;
 	}
 
 	ocfs2_set_locking_protocol();
@@ -1767,6 +1768,8 @@ static void ocfs2_inode_init_once(void *data)
 	ocfs2_lock_res_init_once(&oi->ip_inode_lockres);
 	ocfs2_lock_res_init_once(&oi->ip_open_lockres);
 
+	init_waitqueue_head(&oi->append_dio_wq);
+
 	ocfs2_metadata_cache_init(INODE_CACHE(&oi->vfs_inode),
 				  &ocfs2_inode_caching_ops);
 
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index 016f01df3825..662f8dee149f 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -1284,7 +1284,7 @@ int ocfs2_xattr_get_nolock(struct inode *inode,
 		return -EOPNOTSUPP;
 
 	if (!(oi->ip_dyn_features & OCFS2_HAS_XATTR_FL))
-		ret = -ENODATA;
+		return -ENODATA;
 
 	xis.inode_bh = xbs.inode_bh = di_bh;
 	di = (struct ocfs2_dinode *)di_bh->b_data;
diff --git a/fs/proc/array.c b/fs/proc/array.c
index cd3653e4f35c..bd117d065b82 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -157,20 +157,29 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
 	struct user_namespace *user_ns = seq_user_ns(m);
 	struct group_info *group_info;
 	int g;
-	struct fdtable *fdt = NULL;
+	struct task_struct *tracer;
 	const struct cred *cred;
-	pid_t ppid, tpid;
+	pid_t ppid, tpid = 0, tgid, ngid;
+	unsigned int max_fds = 0;
 
 	rcu_read_lock();
 	ppid = pid_alive(p) ?
 		task_tgid_nr_ns(rcu_dereference(p->real_parent), ns) : 0;
-	tpid = 0;
-	if (pid_alive(p)) {
-		struct task_struct *tracer = ptrace_parent(p);
-		if (tracer)
-			tpid = task_pid_nr_ns(tracer, ns);
-	}
+
+	tracer = ptrace_parent(p);
+	if (tracer)
+		tpid = task_pid_nr_ns(tracer, ns);
+
+	tgid = task_tgid_nr_ns(p, ns);
+	ngid = task_numa_group_id(p);
 	cred = get_task_cred(p);
+
+	task_lock(p);
+	if (p->files)
+		max_fds = files_fdtable(p->files)->max_fds;
+	task_unlock(p);
+	rcu_read_unlock();
+
 	seq_printf(m,
 		"State:\t%s\n"
 		"Tgid:\t%d\n"
@@ -179,12 +188,10 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
 		"PPid:\t%d\n"
 		"TracerPid:\t%d\n"
 		"Uid:\t%d\t%d\t%d\t%d\n"
-		"Gid:\t%d\t%d\t%d\t%d\n",
+		"Gid:\t%d\t%d\t%d\t%d\n"
+		"FDSize:\t%d\nGroups:\t",
 		get_task_state(p),
-		task_tgid_nr_ns(p, ns),
-		task_numa_group_id(p),
-		pid_nr_ns(pid, ns),
-		ppid, tpid,
+		tgid, ngid, pid_nr_ns(pid, ns), ppid, tpid,
 		from_kuid_munged(user_ns, cred->uid),
 		from_kuid_munged(user_ns, cred->euid),
 		from_kuid_munged(user_ns, cred->suid),
@@ -192,20 +199,10 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
 		from_kgid_munged(user_ns, cred->gid),
 		from_kgid_munged(user_ns, cred->egid),
 		from_kgid_munged(user_ns, cred->sgid),
-		from_kgid_munged(user_ns, cred->fsgid));
-
-	task_lock(p);
-	if (p->files)
-		fdt = files_fdtable(p->files);
-	seq_printf(m,
-		"FDSize:\t%d\n"
-		"Groups:\t",
-		fdt ? fdt->max_fds : 0);
-	rcu_read_unlock();
+		from_kgid_munged(user_ns, cred->fsgid),
+		max_fds);
 
 	group_info = cred->group_info;
-	task_unlock(p);
-
 	for (g = 0; g < group_info->ngroups; g++)
 		seq_printf(m, "%d ",
 			   from_kgid_munged(user_ns, GROUP_AT(group_info, g)));
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 317b72641ebf..7fea13229f33 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -31,9 +31,73 @@ static DEFINE_SPINLOCK(proc_subdir_lock);
 
 static int proc_match(unsigned int len, const char *name, struct proc_dir_entry *de)
 {
-	if (de->namelen != len)
-		return 0;
-	return !memcmp(name, de->name, len);
+	if (len < de->namelen)
+		return -1;
+	if (len > de->namelen)
+		return 1;
+
+	return memcmp(name, de->name, len);
+}
+
+static struct proc_dir_entry *pde_subdir_first(struct proc_dir_entry *dir)
+{
+	return rb_entry_safe(rb_first(&dir->subdir), struct proc_dir_entry,
+			     subdir_node);
+}
+
+static struct proc_dir_entry *pde_subdir_next(struct proc_dir_entry *dir)
+{
+	return rb_entry_safe(rb_next(&dir->subdir_node), struct proc_dir_entry,
+			     subdir_node);
+}
+
+static struct proc_dir_entry *pde_subdir_find(struct proc_dir_entry *dir,
+					      const char *name,
+					      unsigned int len)
+{
+	struct rb_node *node = dir->subdir.rb_node;
+
+	while (node) {
+		struct proc_dir_entry *de = container_of(node,
+							 struct proc_dir_entry,
+							 subdir_node);
+		int result = proc_match(len, name, de);
+
+		if (result < 0)
+			node = node->rb_left;
+		else if (result > 0)
+			node = node->rb_right;
+		else
+			return de;
+	}
+	return NULL;
+}
+
+static bool pde_subdir_insert(struct proc_dir_entry *dir,
+			      struct proc_dir_entry *de)
+{
+	struct rb_root *root = &dir->subdir;
+	struct rb_node **new = &root->rb_node, *parent = NULL;
+
+	/* Figure out where to put new node */
+	while (*new) {
+		struct proc_dir_entry *this =
+			container_of(*new, struct proc_dir_entry, subdir_node);
+		int result = proc_match(de->namelen, de->name, this);
+
+		parent = *new;
+		if (result < 0)
+			new = &(*new)->rb_left;
+		else if (result > 0)
+			new = &(*new)->rb_right;
+		else
+			return false;
+	}
+
+	/* Add new node and rebalance tree. */
+	rb_link_node(&de->subdir_node, parent, new);
+	rb_insert_color(&de->subdir_node, root);
+	return true;
 }
 
 static int proc_notify_change(struct dentry *dentry, struct iattr *iattr)
@@ -92,10 +156,7 @@ static int __xlate_proc_name(const char *name, struct proc_dir_entry **ret,
 			break;
 
 		len = next - cp;
-		for (de = de->subdir; de ; de = de->next) {
-			if (proc_match(len, cp, de))
-				break;
-		}
+		de = pde_subdir_find(de, cp, len);
 		if (!de) {
 			WARN(1, "name '%s'\n", name);
 			return -ENOENT;
@@ -183,19 +244,16 @@ struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *dir,
 	struct inode *inode;
 
 	spin_lock(&proc_subdir_lock);
-	for (de = de->subdir; de ; de = de->next) {
-		if (de->namelen != dentry->d_name.len)
-			continue;
-		if (!memcmp(dentry->d_name.name, de->name, de->namelen)) {
-			pde_get(de);
-			spin_unlock(&proc_subdir_lock);
-			inode = proc_get_inode(dir->i_sb, de);
-			if (!inode)
-				return ERR_PTR(-ENOMEM);
-			d_set_d_op(dentry, &simple_dentry_operations);
-			d_add(dentry, inode);
-			return NULL;
-		}
+	de = pde_subdir_find(de, dentry->d_name.name, dentry->d_name.len);
+	if (de) {
+		pde_get(de);
+		spin_unlock(&proc_subdir_lock);
+		inode = proc_get_inode(dir->i_sb, de);
+		if (!inode)
+			return ERR_PTR(-ENOMEM);
+		d_set_d_op(dentry, &simple_dentry_operations);
+		d_add(dentry, inode);
+		return NULL;
 	}
 	spin_unlock(&proc_subdir_lock);
 	return ERR_PTR(-ENOENT);
@@ -225,7 +283,7 @@ int proc_readdir_de(struct proc_dir_entry *de, struct file *file,
 		return 0;
 
 	spin_lock(&proc_subdir_lock);
-	de = de->subdir;
+	de = pde_subdir_first(de);
 	i = ctx->pos - 2;
 	for (;;) {
 		if (!de) {
@@ -234,7 +292,7 @@ int proc_readdir_de(struct proc_dir_entry *de, struct file *file,
 		}
 		if (!i)
 			break;
-		de = de->next;
+		de = pde_subdir_next(de);
 		i--;
 	}
 
@@ -249,7 +307,7 @@ int proc_readdir_de(struct proc_dir_entry *de, struct file *file,
 		}
 		spin_lock(&proc_subdir_lock);
 		ctx->pos++;
-		next = de->next;
+		next = pde_subdir_next(de);
 		pde_put(de);
 		de = next;
 	} while (de);
@@ -286,9 +344,8 @@ static const struct inode_operations proc_dir_inode_operations = {
 
 static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp)
 {
-	struct proc_dir_entry *tmp;
 	int ret;
-	
+
 	ret = proc_alloc_inum(&dp->low_ino);
 	if (ret)
 		return ret;
@@ -304,21 +361,21 @@ static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp
 		dp->proc_iops = &proc_file_inode_operations;
 	} else {
 		WARN_ON(1);
+		proc_free_inum(dp->low_ino);
 		return -EINVAL;
 	}
 
 	spin_lock(&proc_subdir_lock);
-
-	for (tmp = dir->subdir; tmp; tmp = tmp->next)
-		if (strcmp(tmp->name, dp->name) == 0) {
-			WARN(1, "proc_dir_entry '%s/%s' already registered\n",
-				dir->name, dp->name);
-			break;
-		}
-
-	dp->next = dir->subdir;
 	dp->parent = dir;
-	dir->subdir = dp;
+	if (pde_subdir_insert(dir, dp) == false) {
+		WARN(1, "proc_dir_entry '%s/%s' already registered\n",
+		     dir->name, dp->name);
+		spin_unlock(&proc_subdir_lock);
+		if (S_ISDIR(dp->mode))
+			dir->nlink--;
+		proc_free_inum(dp->low_ino);
+		return -EEXIST;
+	}
 	spin_unlock(&proc_subdir_lock);
 
 	return 0;
@@ -354,6 +411,7 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
 	ent->namelen = qstr.len;
 	ent->mode = mode;
 	ent->nlink = nlink;
+	ent->subdir = RB_ROOT;
 	atomic_set(&ent->count, 1);
 	spin_lock_init(&ent->pde_unload_lock);
 	INIT_LIST_HEAD(&ent->pde_openers);
@@ -485,7 +543,6 @@ void pde_put(struct proc_dir_entry *pde)
  */
 void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
 {
-	struct proc_dir_entry **p;
 	struct proc_dir_entry *de = NULL;
 	const char *fn = name;
 	unsigned int len;
@@ -497,14 +554,9 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
 	}
 	len = strlen(fn);
 
-	for (p = &parent->subdir; *p; p=&(*p)->next ) {
-		if (proc_match(len, fn, *p)) {
-			de = *p;
-			*p = de->next;
-			de->next = NULL;
-			break;
-		}
-	}
+	de = pde_subdir_find(parent, fn, len);
+	if (de)
+		rb_erase(&de->subdir_node, &parent->subdir);
 	spin_unlock(&proc_subdir_lock);
 	if (!de) {
 		WARN(1, "name '%s'\n", name);
@@ -516,16 +568,15 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
 	if (S_ISDIR(de->mode))
 		parent->nlink--;
 	de->nlink = 0;
-	WARN(de->subdir, "%s: removing non-empty directory "
-			 "'%s/%s', leaking at least '%s'\n", __func__,
-			 de->parent->name, de->name, de->subdir->name);
+	WARN(pde_subdir_first(de),
+	     "%s: removing non-empty directory '%s/%s', leaking at least '%s'\n",
+	     __func__, de->parent->name, de->name, pde_subdir_first(de)->name);
 	pde_put(de);
 }
 EXPORT_SYMBOL(remove_proc_entry);
 
 int remove_proc_subtree(const char *name, struct proc_dir_entry *parent)
 {
-	struct proc_dir_entry **p;
 	struct proc_dir_entry *root = NULL, *de, *next;
 	const char *fn = name;
 	unsigned int len;
@@ -537,24 +588,18 @@ int remove_proc_subtree(const char *name, struct proc_dir_entry *parent)
 	}
 	len = strlen(fn);
 
-	for (p = &parent->subdir; *p; p=&(*p)->next ) {
-		if (proc_match(len, fn, *p)) {
-			root = *p;
-			*p = root->next;
-			root->next = NULL;
-			break;
-		}
-	}
+	root = pde_subdir_find(parent, fn, len);
 	if (!root) {
 		spin_unlock(&proc_subdir_lock);
 		return -ENOENT;
 	}
+	rb_erase(&root->subdir_node, &parent->subdir);
+
 	de = root;
 	while (1) {
-		next = de->subdir;
+		next = pde_subdir_first(de);
 		if (next) {
-			de->subdir = next->next;
-			next->next = NULL;
+			rb_erase(&next->subdir_node, &de->subdir);
 			de = next;
 			continue;
 		}
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index aa7a0ee182e1..7fb1a4869fd0 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -24,10 +24,9 @@ struct mempolicy;
  * tree) of these proc_dir_entries, so that we can dynamically
  * add new files to /proc.
  *
- * The "next" pointer creates a linked list of one /proc directory,
- * while parent/subdir create the directory structure (every
- * /proc file has a parent, but "subdir" is NULL for all
- * non-directory entries).
+ * parent/subdir are used for the directory structure (every /proc file has a
+ * parent, but "subdir" is empty for all non-directory entries).
+ * subdir_node is used to build the rb tree "subdir" of the parent.
  */
 struct proc_dir_entry {
 	unsigned int low_ino;
@@ -38,7 +37,9 @@ struct proc_dir_entry {
 	loff_t size;
 	const struct inode_operations *proc_iops;
 	const struct file_operations *proc_fops;
-	struct proc_dir_entry *next, *parent, *subdir;
+	struct proc_dir_entry *parent;
+	struct rb_root subdir;
+	struct rb_node subdir_node;
 	void *data;
 	atomic_t count;		/* use count */
 	atomic_t in_use;	/* number of callers into module in progress; */
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index a63af3e0a612..1bde894bc624 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -192,6 +192,7 @@ static __net_init int proc_net_ns_init(struct net *net)
 	if (!netd)
 		goto out;
 
+	netd->subdir = RB_ROOT;
 	netd->data = net;
 	netd->nlink = 2;
 	netd->namelen = 3;
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 094e44d4a6be..e74ac9f1a2c0 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -251,6 +251,7 @@ struct proc_dir_entry proc_root = {
 	.proc_iops	= &proc_root_inode_operations, 
 	.proc_fops	= &proc_root_operations,
 	.parent		= &proc_root,
+	.subdir		= RB_ROOT,
 	.name		= "/proc",
 };
 
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 4e0388cffe3d..2ab200d429be 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -447,58 +447,88 @@ struct mem_size_stats {
 	u64 pss;
 };
 
+static void smaps_account(struct mem_size_stats *mss, struct page *page,
+		unsigned long size, bool young, bool dirty)
+{
+	int mapcount;
+
+	if (PageAnon(page))
+		mss->anonymous += size;
 
-static void smaps_pte_entry(pte_t ptent, unsigned long addr,
-		unsigned long ptent_size, struct mm_walk *walk)
+	mss->resident += size;
+	/* Accumulate the size in pages that have been accessed. */
+	if (young || PageReferenced(page))
+		mss->referenced += size;
+	mapcount = page_mapcount(page);
+	if (mapcount >= 2) {
+		if (dirty || PageDirty(page))
+			mss->shared_dirty += size;
+		else
+			mss->shared_clean += size;
+		mss->pss += (size << PSS_SHIFT) / mapcount;
+	} else {
+		if (dirty || PageDirty(page))
+			mss->private_dirty += size;
+		else
+			mss->private_clean += size;
+		mss->pss += (size << PSS_SHIFT);
+	}
+}
+
+
+static void smaps_pte_entry(pte_t *pte, unsigned long addr,
+		struct mm_walk *walk)
 {
 	struct mem_size_stats *mss = walk->private;
 	struct vm_area_struct *vma = mss->vma;
 	pgoff_t pgoff = linear_page_index(vma, addr);
 	struct page *page = NULL;
-	int mapcount;
 
-	if (pte_present(ptent)) {
-		page = vm_normal_page(vma, addr, ptent);
-	} else if (is_swap_pte(ptent)) {
-		swp_entry_t swpent = pte_to_swp_entry(ptent);
+	if (pte_present(*pte)) {
+		page = vm_normal_page(vma, addr, *pte);
+	} else if (is_swap_pte(*pte)) {
+		swp_entry_t swpent = pte_to_swp_entry(*pte);
 
 		if (!non_swap_entry(swpent))
-			mss->swap += ptent_size;
+			mss->swap += PAGE_SIZE;
 		else if (is_migration_entry(swpent))
 			page = migration_entry_to_page(swpent);
-	} else if (pte_file(ptent)) {
-		if (pte_to_pgoff(ptent) != pgoff)
-			mss->nonlinear += ptent_size;
+	} else if (pte_file(*pte)) {
+		if (pte_to_pgoff(*pte) != pgoff)
+			mss->nonlinear += PAGE_SIZE;
 	}
 
 	if (!page)
 		return;
 
-	if (PageAnon(page))
-		mss->anonymous += ptent_size;
-
 	if (page->index != pgoff)
-		mss->nonlinear += ptent_size;
+		mss->nonlinear += PAGE_SIZE;
 
-	mss->resident += ptent_size;
-	/* Accumulate the size in pages that have been accessed. */
-	if (pte_young(ptent) || PageReferenced(page))
-		mss->referenced += ptent_size;
-	mapcount = page_mapcount(page);
-	if (mapcount >= 2) {
-		if (pte_dirty(ptent) || PageDirty(page))
-			mss->shared_dirty += ptent_size;
-		else
-			mss->shared_clean += ptent_size;
-		mss->pss += (ptent_size << PSS_SHIFT) / mapcount;
-	} else {
-		if (pte_dirty(ptent) || PageDirty(page))
-			mss->private_dirty += ptent_size;
-		else
-			mss->private_clean += ptent_size;
-		mss->pss += (ptent_size << PSS_SHIFT);
-	}
+	smaps_account(mss, page, PAGE_SIZE, pte_young(*pte), pte_dirty(*pte));
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
+		struct mm_walk *walk)
+{
+	struct mem_size_stats *mss = walk->private;
+	struct vm_area_struct *vma = mss->vma;
+	struct page *page;
+
+	/* FOLL_DUMP will return -EFAULT on huge zero page */
+	page = follow_trans_huge_pmd(vma, addr, pmd, FOLL_DUMP);
+	if (IS_ERR_OR_NULL(page))
+		return;
+	mss->anonymous_thp += HPAGE_PMD_SIZE;
+	smaps_account(mss, page, HPAGE_PMD_SIZE,
+			pmd_young(*pmd), pmd_dirty(*pmd));
 }
+#else
+static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
+		struct mm_walk *walk)
+{
+}
+#endif
 
 static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 			   struct mm_walk *walk)
@@ -509,9 +539,8 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	spinlock_t *ptl;
 
 	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
-		smaps_pte_entry(*(pte_t *)pmd, addr, HPAGE_PMD_SIZE, walk);
+		smaps_pmd_entry(pmd, addr, walk);
 		spin_unlock(ptl);
-		mss->anonymous_thp += HPAGE_PMD_SIZE;
 		return 0;
 	}
 
@@ -524,7 +553,7 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	 */
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	for (; addr != end; pte++, addr += PAGE_SIZE)
-		smaps_pte_entry(*pte, addr, PAGE_SIZE, walk);
+		smaps_pte_entry(pte, addr, walk);
 	pte_unmap_unlock(pte - 1, ptl);
 	cond_resched();
 	return 0;
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index 61f29e5ea840..576e4639ca60 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -53,6 +53,10 @@ struct linux_binprm {
 #define BINPRM_FLAGS_EXECFD_BIT 1
 #define BINPRM_FLAGS_EXECFD (1 << BINPRM_FLAGS_EXECFD_BIT)
 
+/* filename of the binary will be inaccessible after exec */
+#define BINPRM_FLAGS_PATH_INACCESSIBLE_BIT 2
+#define BINPRM_FLAGS_PATH_INACCESSIBLE (1 << BINPRM_FLAGS_PATH_INACCESSIBLE_BIT)
+
 /* Function parameter for binfmt->coredump */
 struct coredump_params {
 	const siginfo_t *siginfo;
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 9d5c3224a1e2..202e4034fe26 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -45,6 +45,7 @@
  * bitmap_set(dst, pos, nbits)			Set specified bit area
  * bitmap_clear(dst, pos, nbits)		Clear specified bit area
  * bitmap_find_next_zero_area(buf, len, pos, n, mask)	Find bit free area
+ * bitmap_find_next_zero_area_off(buf, len, pos, n, mask)	as above
  * bitmap_shift_right(dst, src, n, nbits)	*dst = *src >> n
  * bitmap_shift_left(dst, src, n, nbits)	*dst = *src << n
  * bitmap_remap(dst, src, old, new, nbits)	*dst = map(old, new)(src)
@@ -115,11 +116,36 @@ extern int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits);
 
 extern void bitmap_set(unsigned long *map, unsigned int start, int len);
 extern void bitmap_clear(unsigned long *map, unsigned int start, int len);
-extern unsigned long bitmap_find_next_zero_area(unsigned long *map,
-					 unsigned long size,
-					 unsigned long start,
-					 unsigned int nr,
-					 unsigned long align_mask);
+
+extern unsigned long bitmap_find_next_zero_area_off(unsigned long *map,
+						    unsigned long size,
+						    unsigned long start,
+						    unsigned int nr,
+						    unsigned long align_mask,
+						    unsigned long align_offset);
+
+/**
+ * bitmap_find_next_zero_area - find a contiguous aligned zero area
+ * @map: The address to base the search on
+ * @size: The bitmap size in bits
+ * @start: The bitnumber to start searching at
+ * @nr: The number of zeroed bits we're looking for
+ * @align_mask: Alignment mask for zero area
+ *
+ * The @align_mask should be one less than a power of 2; the effect is that
+ * the bit offset of all zero areas this function finds is multiples of that
+ * power of 2. A @align_mask of 0 means no alignment is required.
+ */
+static inline unsigned long
+bitmap_find_next_zero_area(unsigned long *map,
+			   unsigned long size,
+			   unsigned long start,
+			   unsigned int nr,
+			   unsigned long align_mask)
+{
+	return bitmap_find_next_zero_area_off(map, size, start, nr,
+					      align_mask, 0);
+}
 
 extern int bitmap_scnprintf(char *buf, unsigned int len,
 			const unsigned long *src, int nbits);
diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
index 4e2bd4c95b66..0995c2de8162 100644
--- a/include/linux/bootmem.h
+++ b/include/linux/bootmem.h
@@ -46,6 +46,7 @@ extern unsigned long init_bootmem_node(pg_data_t *pgdat,
 extern unsigned long init_bootmem(unsigned long addr, unsigned long memend);
 
 extern unsigned long free_all_bootmem(void);
+extern void reset_node_managed_pages(pg_data_t *pgdat);
 extern void reset_all_zones_managed_pages(void);
 
 extern void free_bootmem_node(pg_data_t *pgdat,
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 27b0c9105da5..641e56494a92 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -113,6 +113,19 @@ static inline void css_get(struct cgroup_subsys_state *css)
 }
 
 /**
+ * css_get_many - obtain references on the specified css
+ * @css: target css
+ * @n: number of references to get
+ *
+ * The caller must already have a reference.
+ */
+static inline void css_get_many(struct cgroup_subsys_state *css, unsigned int n)
+{
+	if (!(css->flags & CSS_NO_REF))
+		percpu_ref_get_many(&css->refcnt, n);
+}
+
+/**
  * css_tryget - try to obtain a reference on the specified css
  * @css: target css
  *
@@ -159,6 +172,19 @@ static inline void css_put(struct cgroup_subsys_state *css)
 		percpu_ref_put(&css->refcnt);
 }
 
+/**
+ * css_put_many - put css references
+ * @css: target css
+ * @n: number of references to put
+ *
+ * Put references obtained via css_get() and css_tryget_online().
+ */
+static inline void css_put_many(struct cgroup_subsys_state *css, unsigned int n)
+{
+	if (!(css->flags & CSS_NO_REF))
+		percpu_ref_put_many(&css->refcnt, n);
+}
+
 /* bits in struct cgroup flags field */
 enum {
 	/* Control Group requires release notifications to userspace */
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 60bdf8dc02a3..3238ffa33f68 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -33,10 +33,11 @@ extern int fragmentation_index(struct zone *zone, unsigned int order);
 extern unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *mask,
 			enum migrate_mode mode, int *contended,
-			struct zone **candidate_zone);
+			int alloc_flags, int classzone_idx);
 extern void compact_pgdat(pg_data_t *pgdat, int order);
 extern void reset_isolation_suitable(pg_data_t *pgdat);
-extern unsigned long compaction_suitable(struct zone *zone, int order);
+extern unsigned long compaction_suitable(struct zone *zone, int order,
+					int alloc_flags, int classzone_idx);
 
 /* Do not skip compaction more than 64 times */
 #define COMPACT_MAX_DEFER_SHIFT 6
@@ -103,7 +104,7 @@ static inline bool compaction_restarting(struct zone *zone, int order)
 static inline unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
 			enum migrate_mode mode, int *contended,
-			struct zone **candidate_zone)
+			int alloc_flags, int classzone_idx)
 {
 	return COMPACT_CONTINUE;
 }
@@ -116,7 +117,8 @@ static inline void reset_isolation_suitable(pg_data_t *pgdat)
 {
 }
 
-static inline unsigned long compaction_suitable(struct zone *zone, int order)
+static inline unsigned long compaction_suitable(struct zone *zone, int order,
+					int alloc_flags, int classzone_idx)
 {
 	return COMPACT_SKIPPED;
 }
diff --git a/include/linux/compat.h b/include/linux/compat.h
index e6494261eaff..7450ca2ac1fc 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -357,6 +357,9 @@ asmlinkage long compat_sys_lseek(unsigned int, compat_off_t, unsigned int);
 
 asmlinkage long compat_sys_execve(const char __user *filename, const compat_uptr_t __user *argv,
 		     const compat_uptr_t __user *envp);
+asmlinkage long compat_sys_execveat(int dfd, const char __user *filename,
+		     const compat_uptr_t __user *argv,
+		     const compat_uptr_t __user *envp, int flags);
 
 asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp,
 		compat_ulong_t __user *outp, compat_ulong_t __user *exp,
diff --git a/include/linux/crc64_ecma.h b/include/linux/crc64_ecma.h
new file mode 100644
index 000000000000..bba7a4d692b3
--- /dev/null
+++ b/include/linux/crc64_ecma.h
@@ -0,0 +1,56 @@
+/*
+ * Copyright 2013 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef __CRC64_ECMA_H_
+#define __CRC64_ECMA_H_
+
+#include <linux/types.h>
+
+
+#define CRC64_DEFAULT_INITVAL           0xFFFFFFFFFFFFFFFFULL
+
+
+/*
+ * crc64_ecma_seed - Initializes the CRC64 ECMA seed.
+ */
+u64 crc64_ecma_seed(void);
+
+/*
+ * crc64_ecma - Computes the 64 bit ECMA CRC.
+ *
+ * @pdata:	pointer to the data to compute checksum for.
+ * @nbytes:	number of bytes in data buffer.
+ * @seed:	CRC seed.
+ */
+u64 crc64_ecma(u8 const *pdata, u32 nbytes, u64 seed);
+
+#endif /* __CRC64_ECMA_H_ */
diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h
index c6f996f2abb6..798fad9e420d 100644
--- a/include/linux/fault-inject.h
+++ b/include/linux/fault-inject.h
@@ -5,6 +5,7 @@
 
 #include <linux/types.h>
 #include <linux/debugfs.h>
+#include <linux/ratelimit.h>
 #include <linux/atomic.h>
 
 /*
@@ -25,14 +26,18 @@ struct fault_attr {
 	unsigned long reject_end;
 
 	unsigned long count;
+	struct ratelimit_state ratelimit_state;
+	struct dentry *dname;
 };
 
-#define FAULT_ATTR_INITIALIZER {				\
-		.interval = 1,					\
-		.times = ATOMIC_INIT(1),			\
-		.require_end = ULONG_MAX,			\
-		.stacktrace_depth = 32,				\
-		.verbose = 2,					\
+#define FAULT_ATTR_INITIALIZER {					\
+		.interval = 1,						\
+		.times = ATOMIC_INIT(1),				\
+		.require_end = ULONG_MAX,				\
+		.stacktrace_depth = 32,					\
+		.ratelimit_state = RATELIMIT_STATE_INIT_DISABLED,	\
+		.verbose = 2,						\
+		.dname = NULL,						\
 	}
 
 #define DECLARE_FAULT_ATTR(name) struct fault_attr name = FAULT_ATTR_INITIALIZER
diff --git a/include/linux/file.h b/include/linux/file.h
index 4d69123377a2..f87d30882a24 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -66,7 +66,6 @@ extern void set_close_on_exec(unsigned int fd, int flag);
 extern bool get_close_on_exec(unsigned int fd);
 extern void put_filp(struct file *);
 extern int get_unused_fd_flags(unsigned flags);
-#define get_unused_fd() get_unused_fd_flags(0)
 extern void put_unused_fd(unsigned int fd);
 
 extern void fd_install(unsigned int fd, struct file *file);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 6fff03669e50..01df369d9eab 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -18,6 +18,7 @@
 #include <linux/pid.h>
 #include <linux/bug.h>
 #include <linux/mutex.h>
+#include <linux/rwsem.h>
 #include <linux/capability.h>
 #include <linux/semaphore.h>
 #include <linux/fiemap.h>
@@ -401,7 +402,7 @@ struct address_space {
 	atomic_t		i_mmap_writable;/* count VM_SHARED mappings */
 	struct rb_root		i_mmap;		/* tree of private and shared mappings */
 	struct list_head	i_mmap_nonlinear;/*list VM_NONLINEAR mappings */
-	struct mutex		i_mmap_mutex;	/* protect tree, count, list */
+	struct rw_semaphore	i_mmap_rwsem;	/* protect tree, count, list */
 	/* Protected by tree_lock together with the radix tree */
 	unsigned long		nrpages;	/* number of total pages */
 	unsigned long		nrshadows;	/* number of shadow entries */
@@ -467,6 +468,26 @@ struct block_device {
 
 int mapping_tagged(struct address_space *mapping, int tag);
 
+static inline void i_mmap_lock_write(struct address_space *mapping)
+{
+	down_write(&mapping->i_mmap_rwsem);
+}
+
+static inline void i_mmap_unlock_write(struct address_space *mapping)
+{
+	up_write(&mapping->i_mmap_rwsem);
+}
+
+static inline void i_mmap_lock_read(struct address_space *mapping)
+{
+	down_read(&mapping->i_mmap_rwsem);
+}
+
+static inline void i_mmap_unlock_read(struct address_space *mapping)
+{
+	up_read(&mapping->i_mmap_rwsem);
+}
+
 /*
  * Might pages of this file be mapped into userspace?
  */
@@ -2074,6 +2095,7 @@ extern int vfs_open(const struct path *, struct file *, const struct cred *);
 extern struct file * dentry_open(const struct path *, int, const struct cred *);
 extern int filp_close(struct file *, fl_owner_t id);
 
+extern struct filename *getname_flags(const char __user *, int, int *);
 extern struct filename *getname(const char __user *);
 extern struct filename *getname_kernel(const char *);
 
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 41b30fd4d041..07d2699cdb51 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -381,8 +381,8 @@ extern void free_kmem_pages(unsigned long addr, unsigned int order);
 
 void page_alloc_init(void);
 void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp);
-void drain_all_pages(void);
-void drain_local_pages(void *dummy);
+void drain_all_pages(struct zone *zone);
+void drain_local_pages(struct zone *zone);
 
 /*
  * gfp_allowed_mask is set to GFP_BOOT_MASK during early boot to restrict what
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 6e6d338641fe..cdd149ca5cc0 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -311,7 +311,8 @@ static inline struct hstate *hstate_sizelog(int page_size_log)
 {
 	if (!page_size_log)
 		return &default_hstate;
-	return size_to_hstate(1 << page_size_log);
+
+	return size_to_hstate(1UL << page_size_log);
 }
 
 static inline struct hstate *hstate_vma(struct vm_area_struct *vma)
diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h
index 0129f89cf98d..bcc853eccc85 100644
--- a/include/linux/hugetlb_cgroup.h
+++ b/include/linux/hugetlb_cgroup.h
@@ -16,7 +16,6 @@
 #define _LINUX_HUGETLB_CGROUP_H
 
 #include <linux/mmdebug.h>
-#include <linux/res_counter.h>
 
 struct hugetlb_cgroup;
 /*
diff --git a/include/linux/input.h b/include/linux/input.h
index 82ce323b9986..3b4c32f7312a 100644
--- a/include/linux/input.h
+++ b/include/linux/input.h
@@ -79,6 +79,7 @@ struct input_value {
  * @led: reflects current state of device's LEDs
  * @snd: reflects current state of sound effects
  * @sw: reflects current state of device's switches
+ * @leds: leds objects for the device's LEDs
  * @open: this method is called when the very first user calls
  *	input_open_device(). The driver must prepare the device
  *	to start generating events (start polling thread,
@@ -164,6 +165,8 @@ struct input_dev {
 	unsigned long snd[BITS_TO_LONGS(SND_CNT)];
 	unsigned long sw[BITS_TO_LONGS(SW_CNT)];
 
+	struct led_classdev *leds;
+
 	int (*open)(struct input_dev *dev);
 	void (*close)(struct input_dev *dev);
 	int (*flush)(struct input_dev *dev, struct file *file);
@@ -531,4 +534,29 @@ int input_ff_erase(struct input_dev *dev, int effect_id, struct file *file);
 int input_ff_create_memless(struct input_dev *dev, void *data,
 		int (*play_effect)(struct input_dev *, void *, struct ff_effect *));
 
+#ifdef CONFIG_INPUT_LEDS
+
+void input_led_init(void);
+void input_led_exit(void);
+
+int input_led_connect(struct input_dev *dev);
+void input_led_disconnect(struct input_dev *dev);
+
+#else
+
+static inline void input_led_init(void) { }
+
+static inline void input_led_exit(void) { }
+
+static inline int input_led_connect(struct input_dev *dev)
+{
+	return 0;
+}
+
+static inline void input_led_disconnect(struct input_dev *dev)
+{
+}
+
+#endif
+
 #endif
diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index 35e7eca4e33b..e365d5ec69cb 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -7,15 +7,6 @@
 #include <linux/notifier.h>
 #include <linux/nsproxy.h>
 
-/*
- * ipc namespace events
- */
-#define IPCNS_MEMCHANGED   0x00000001   /* Notify lowmem size changed */
-#define IPCNS_CREATED  0x00000002   /* Notify new ipc namespace created */
-#define IPCNS_REMOVED  0x00000003   /* Notify ipc namespace removed */
-
-#define IPCNS_CALLBACK_PRI 0
-
 struct user_namespace;
 
 struct ipc_ids {
@@ -38,7 +29,6 @@ struct ipc_namespace {
 	unsigned int	msg_ctlmni;
 	atomic_t	msg_bytes;
 	atomic_t	msg_hdrs;
-	int		auto_msgmni;
 
 	size_t		shm_ctlmax;
 	size_t		shm_ctlall;
@@ -77,18 +67,8 @@ extern atomic_t nr_ipc_ns;
 extern spinlock_t mq_lock;
 
 #ifdef CONFIG_SYSVIPC
-extern int register_ipcns_notifier(struct ipc_namespace *);
-extern int cond_register_ipcns_notifier(struct ipc_namespace *);
-extern void unregister_ipcns_notifier(struct ipc_namespace *);
-extern int ipcns_notify(unsigned long);
 extern void shm_destroy_orphaned(struct ipc_namespace *ns);
 #else /* CONFIG_SYSVIPC */
-static inline int register_ipcns_notifier(struct ipc_namespace *ns)
-{ return 0; }
-static inline int cond_register_ipcns_notifier(struct ipc_namespace *ns)
-{ return 0; }
-static inline void unregister_ipcns_notifier(struct ipc_namespace *ns) { }
-static inline int ipcns_notify(unsigned long l) { return 0; }
 static inline void shm_destroy_orphaned(struct ipc_namespace *ns) {}
 #endif /* CONFIG_SYSVIPC */
 
diff --git a/include/linux/kern_levels.h b/include/linux/kern_levels.h
index 866caaa9e2bb..c2ce155d83cc 100644
--- a/include/linux/kern_levels.h
+++ b/include/linux/kern_levels.h
@@ -22,4 +22,17 @@
  */
 #define KERN_CONT	""
 
+/* integer equivalents of KERN_<LEVEL> */
+#define LOGLEVEL_SCHED		-2	/* Deferred messages from sched code
+					 * are set to this special level */
+#define LOGLEVEL_DEFAULT	-1	/* default (or last) loglevel */
+#define LOGLEVEL_EMERG		0	/* system is unusable */
+#define LOGLEVEL_ALERT		1	/* action must be taken immediately */
+#define LOGLEVEL_CRIT		2	/* critical conditions */
+#define LOGLEVEL_ERR		3	/* error conditions */
+#define LOGLEVEL_WARNING	4	/* warning conditions */
+#define LOGLEVEL_NOTICE		5	/* normal but significant condition */
+#define LOGLEVEL_INFO		6	/* informational */
+#define LOGLEVEL_DEBUG		7	/* debug-level messages */
+
 #endif
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index f5a240e7557b..5449d2f4a1ef 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -424,6 +424,7 @@ extern int panic_timeout;
 extern int panic_on_oops;
 extern int panic_on_unrecovered_nmi;
 extern int panic_on_io_nmi;
+extern int panic_on_warn;
 extern int sysctl_panic_on_stackoverflow;
 /*
  * Only to be used by arch init code. If the user over-wrote the default
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 6b75640ef5ab..6ea9f919e888 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -25,7 +25,6 @@
 #include <linux/jump_label.h>
 
 struct mem_cgroup;
-struct page_cgroup;
 struct page;
 struct mm_struct;
 struct kmem_cache;
@@ -68,10 +67,9 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage,
 struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *);
 struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *);
 
-bool __mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg,
-				  struct mem_cgroup *memcg);
-bool task_in_mem_cgroup(struct task_struct *task,
-			const struct mem_cgroup *memcg);
+bool mem_cgroup_is_descendant(struct mem_cgroup *memcg,
+			      struct mem_cgroup *root);
+bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg);
 
 extern struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page);
 extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
@@ -79,15 +77,16 @@ extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
 extern struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg);
 extern struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css);
 
-static inline
-bool mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *memcg)
+static inline bool mm_match_cgroup(struct mm_struct *mm,
+				   struct mem_cgroup *memcg)
 {
 	struct mem_cgroup *task_memcg;
-	bool match;
+	bool match = false;
 
 	rcu_read_lock();
 	task_memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
-	match = __mem_cgroup_same_or_subtree(memcg, task_memcg);
+	if (task_memcg)
+		match = mem_cgroup_is_descendant(task_memcg, memcg);
 	rcu_read_unlock();
 	return match;
 }
@@ -141,8 +140,8 @@ static inline bool mem_cgroup_disabled(void)
 
 struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page, bool *locked,
 					      unsigned long *flags);
-void mem_cgroup_end_page_stat(struct mem_cgroup *memcg, bool locked,
-			      unsigned long flags);
+void mem_cgroup_end_page_stat(struct mem_cgroup *memcg, bool *locked,
+			      unsigned long *flags);
 void mem_cgroup_update_page_stat(struct mem_cgroup *memcg,
 				 enum mem_cgroup_stat_index idx, int val);
 
@@ -174,10 +173,6 @@ static inline void mem_cgroup_count_vm_event(struct mm_struct *mm,
 void mem_cgroup_split_huge_fixup(struct page *head);
 #endif
 
-#ifdef CONFIG_DEBUG_VM
-bool mem_cgroup_bad_page_check(struct page *page);
-void mem_cgroup_print_bad_page(struct page *page);
-#endif
 #else /* CONFIG_MEMCG */
 struct mem_cgroup;
 
@@ -297,7 +292,7 @@ static inline struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page,
 }
 
 static inline void mem_cgroup_end_page_stat(struct mem_cgroup *memcg,
-					bool locked, unsigned long flags)
+					bool *locked, unsigned long *flags)
 {
 }
 
@@ -347,19 +342,6 @@ void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx)
 }
 #endif /* CONFIG_MEMCG */
 
-#if !defined(CONFIG_MEMCG) || !defined(CONFIG_DEBUG_VM)
-static inline bool
-mem_cgroup_bad_page_check(struct page *page)
-{
-	return false;
-}
-
-static inline void
-mem_cgroup_print_bad_page(struct page *page)
-{
-}
-#endif
-
 enum {
 	UNDER_LIMIT,
 	SOFT_LIMIT,
@@ -447,9 +429,8 @@ memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order)
 	/*
 	 * __GFP_NOFAIL allocations will move on even if charging is not
 	 * possible. Therefore we don't even try, and have this allocation
-	 * unaccounted. We could in theory charge it with
-	 * res_counter_charge_nofail, but we hope those allocations are rare,
-	 * and won't be worth the trouble.
+	 * unaccounted. We could in theory charge it forcibly, but we hope
+	 * those allocations are rare, and won't be worth the trouble.
 	 */
 	if (gfp & __GFP_NOFAIL)
 		return true;
@@ -467,8 +448,6 @@ memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order)
  * memcg_kmem_uncharge_pages: uncharge pages from memcg
  * @page: pointer to struct page being freed
  * @order: allocation order.
- *
- * there is no need to specify memcg here, since it is embedded in page_cgroup
  */
 static inline void
 memcg_kmem_uncharge_pages(struct page *page, int order)
@@ -485,8 +464,7 @@ memcg_kmem_uncharge_pages(struct page *page, int order)
  *
  * Needs to be called after memcg_kmem_newpage_charge, regardless of success or
  * failure of the allocation. if @page is NULL, this function will revert the
- * charges. Otherwise, it will commit the memcg given by @memcg to the
- * corresponding page_cgroup.
+ * charges. Otherwise, it will commit @page to @memcg.
  */
 static inline void
 memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg, int order)
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 6e0b286649f1..33a8acf33848 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -22,6 +22,7 @@
 #define AT_VECTOR_SIZE (2*(AT_VECTOR_SIZE_ARCH + AT_VECTOR_SIZE_BASE + 1))
 
 struct address_space;
+struct mem_cgroup;
 
 #define USE_SPLIT_PTE_PTLOCKS	(NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS)
 #define USE_SPLIT_PMD_PTLOCKS	(USE_SPLIT_PTE_PTLOCKS && \
@@ -167,6 +168,10 @@ struct page {
 		struct page *first_page;	/* Compound tail pages */
 	};
 
+#ifdef CONFIG_MEMCG
+	struct mem_cgroup *mem_cgroup;
+#endif
+
 	/*
 	 * On machines where all RAM is mapped into kernel address space,
 	 * we can simply calculate the virtual address. On machines with
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index 88787bb4b3b9..95243d28a0ee 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -98,11 +98,11 @@ struct mmu_notifier_ops {
 	/*
 	 * invalidate_range_start() and invalidate_range_end() must be
 	 * paired and are called only when the mmap_sem and/or the
-	 * locks protecting the reverse maps are held. The subsystem
-	 * must guarantee that no additional references are taken to
-	 * the pages in the range established between the call to
-	 * invalidate_range_start() and the matching call to
-	 * invalidate_range_end().
+	 * locks protecting the reverse maps are held. If the subsystem
+	 * can't guarantee that no additional references are taken to
+	 * the pages in the range, it has to implement the
+	 * invalidate_range() notifier to remove any references taken
+	 * after invalidate_range_start().
 	 *
 	 * Invalidation of multiple concurrent ranges may be
 	 * optionally permitted by the driver. Either way the
@@ -144,6 +144,29 @@ struct mmu_notifier_ops {
 	void (*invalidate_range_end)(struct mmu_notifier *mn,
 				     struct mm_struct *mm,
 				     unsigned long start, unsigned long end);
+
+	/*
+	 * invalidate_range() is either called between
+	 * invalidate_range_start() and invalidate_range_end() when the
+	 * VM has to free pages that where unmapped, but before the
+	 * pages are actually freed, or outside of _start()/_end() when
+	 * a (remote) TLB is necessary.
+	 *
+	 * If invalidate_range() is used to manage a non-CPU TLB with
+	 * shared page-tables, it not necessary to implement the
+	 * invalidate_range_start()/end() notifiers, as
+	 * invalidate_range() alread catches the points in time when an
+	 * external TLB range needs to be flushed.
+	 *
+	 * The invalidate_range() function is called under the ptl
+	 * spin-lock and not allowed to sleep.
+	 *
+	 * Note that this function might be called with just a sub-range
+	 * of what was passed to invalidate_range_start()/end(), if
+	 * called between those functions.
+	 */
+	void (*invalidate_range)(struct mmu_notifier *mn, struct mm_struct *mm,
+				 unsigned long start, unsigned long end);
 };
 
 /*
@@ -154,7 +177,7 @@ struct mmu_notifier_ops {
  * Therefore notifier chains can only be traversed when either
  *
  * 1. mmap_sem is held.
- * 2. One of the reverse map locks is held (i_mmap_mutex or anon_vma->rwsem).
+ * 2. One of the reverse map locks is held (i_mmap_rwsem or anon_vma->rwsem).
  * 3. No other concurrent thread can access the list (release)
  */
 struct mmu_notifier {
@@ -190,6 +213,8 @@ extern void __mmu_notifier_invalidate_range_start(struct mm_struct *mm,
 				  unsigned long start, unsigned long end);
 extern void __mmu_notifier_invalidate_range_end(struct mm_struct *mm,
 				  unsigned long start, unsigned long end);
+extern void __mmu_notifier_invalidate_range(struct mm_struct *mm,
+				  unsigned long start, unsigned long end);
 
 static inline void mmu_notifier_release(struct mm_struct *mm)
 {
@@ -242,6 +267,13 @@ static inline void mmu_notifier_invalidate_range_end(struct mm_struct *mm,
 		__mmu_notifier_invalidate_range_end(mm, start, end);
 }
 
+static inline void mmu_notifier_invalidate_range(struct mm_struct *mm,
+				  unsigned long start, unsigned long end)
+{
+	if (mm_has_notifiers(mm))
+		__mmu_notifier_invalidate_range(mm, start, end);
+}
+
 static inline void mmu_notifier_mm_init(struct mm_struct *mm)
 {
 	mm->mmu_notifier_mm = NULL;
@@ -279,6 +311,44 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm)
 	__young;							\
 })
 
+#define	ptep_clear_flush_notify(__vma, __address, __ptep)		\
+({									\
+	unsigned long ___addr = __address & PAGE_MASK;			\
+	struct mm_struct *___mm = (__vma)->vm_mm;			\
+	pte_t ___pte;							\
+									\
+	___pte = ptep_clear_flush(__vma, __address, __ptep);		\
+	mmu_notifier_invalidate_range(___mm, ___addr,			\
+					___addr + PAGE_SIZE);		\
+									\
+	___pte;								\
+})
+
+#define pmdp_clear_flush_notify(__vma, __haddr, __pmd)			\
+({									\
+	unsigned long ___haddr = __haddr & HPAGE_PMD_MASK;		\
+	struct mm_struct *___mm = (__vma)->vm_mm;			\
+	pmd_t ___pmd;							\
+									\
+	___pmd = pmdp_clear_flush(__vma, __haddr, __pmd);		\
+	mmu_notifier_invalidate_range(___mm, ___haddr,			\
+				      ___haddr + HPAGE_PMD_SIZE);	\
+									\
+	___pmd;								\
+})
+
+#define pmdp_get_and_clear_notify(__mm, __haddr, __pmd)			\
+({									\
+	unsigned long ___haddr = __haddr & HPAGE_PMD_MASK;		\
+	pmd_t ___pmd;							\
+									\
+	___pmd = pmdp_get_and_clear(__mm, __haddr, __pmd);		\
+	mmu_notifier_invalidate_range(__mm, ___haddr,			\
+				      ___haddr + HPAGE_PMD_SIZE);	\
+									\
+	___pmd;								\
+})
+
 /*
  * set_pte_at_notify() sets the pte _after_ running the notifier.
  * This is safe to start by updating the secondary MMUs, because the primary MMU
@@ -342,6 +412,11 @@ static inline void mmu_notifier_invalidate_range_end(struct mm_struct *mm,
 {
 }
 
+static inline void mmu_notifier_invalidate_range(struct mm_struct *mm,
+				  unsigned long start, unsigned long end)
+{
+}
+
 static inline void mmu_notifier_mm_init(struct mm_struct *mm)
 {
 }
@@ -352,6 +427,9 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm)
 
 #define ptep_clear_flush_young_notify ptep_clear_flush_young
 #define pmdp_clear_flush_young_notify pmdp_clear_flush_young
+#define	ptep_clear_flush_notify ptep_clear_flush
+#define pmdp_clear_flush_notify pmdp_clear_flush
+#define pmdp_get_and_clear_notify pmdp_get_and_clear
 #define set_pte_at_notify set_pte_at
 
 #endif /* CONFIG_MMU_NOTIFIER */
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 48bf12ef6620..3879d7664dfc 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -431,6 +431,15 @@ struct zone {
 	 */
 	int			nr_migrate_reserve_block;
 
+#ifdef CONFIG_MEMORY_ISOLATION
+	/*
+	 * Number of isolated pageblock. It is used to solve incorrect
+	 * freepage counting problem due to racy retrieving migratetype
+	 * of pageblock. Protected by zone->lock.
+	 */
+	unsigned long		nr_isolate_pageblock;
+#endif
+
 #ifdef CONFIG_MEMORY_HOTPLUG
 	/* see spanned/present_pages for more description */
 	seqlock_t		span_seqlock;
@@ -713,9 +722,6 @@ typedef struct pglist_data {
 	int nr_zones;
 #ifdef CONFIG_FLAT_NODE_MEM_MAP	/* means !SPARSEMEM */
 	struct page *node_mem_map;
-#ifdef CONFIG_MEMCG
-	struct page_cgroup *node_page_cgroup;
-#endif
 #endif
 #ifndef CONFIG_NO_BOOTMEM
 	struct bootmem_data *bdata;
@@ -1069,7 +1075,6 @@ static inline unsigned long early_pfn_to_nid(unsigned long pfn)
 #define SECTION_ALIGN_DOWN(pfn)	((pfn) & PAGE_SECTION_MASK)
 
 struct page;
-struct page_cgroup;
 struct mem_section {
 	/*
 	 * This is, logically, a pointer to an array of struct
@@ -1087,14 +1092,6 @@ struct mem_section {
 
 	/* See declaration of similar field in struct zone */
 	unsigned long *pageblock_flags;
-#ifdef CONFIG_MEMCG
-	/*
-	 * If !SPARSEMEM, pgdat doesn't have page_cgroup pointer. We use
-	 * section. (see memcontrol.h/page_cgroup.h about this.)
-	 */
-	struct page_cgroup *page_cgroup;
-	unsigned long pad;
-#endif
 	/*
 	 * WARNING: mem_section must be a power-of-2 in size for the
 	 * calculation and use of SECTION_ROOT_MASK to make sense.
diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h
index 3fff8e774067..2dc1e1697b45 100644
--- a/include/linux/page-isolation.h
+++ b/include/linux/page-isolation.h
@@ -2,6 +2,10 @@
 #define __LINUX_PAGEISOLATION_H
 
 #ifdef CONFIG_MEMORY_ISOLATION
+static inline bool has_isolate_pageblock(struct zone *zone)
+{
+	return zone->nr_isolate_pageblock;
+}
 static inline bool is_migrate_isolate_page(struct page *page)
 {
 	return get_pageblock_migratetype(page) == MIGRATE_ISOLATE;
@@ -11,6 +15,10 @@ static inline bool is_migrate_isolate(int migratetype)
 	return migratetype == MIGRATE_ISOLATE;
 }
 #else
+static inline bool has_isolate_pageblock(struct zone *zone)
+{
+	return false;
+}
 static inline bool is_migrate_isolate_page(struct page *page)
 {
 	return false;
diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h
deleted file mode 100644
index 5c831f1eca79..000000000000
--- a/include/linux/page_cgroup.h
+++ /dev/null
@@ -1,105 +0,0 @@
-#ifndef __LINUX_PAGE_CGROUP_H
-#define __LINUX_PAGE_CGROUP_H
-
-enum {
-	/* flags for mem_cgroup */
-	PCG_USED = 0x01,	/* This page is charged to a memcg */
-	PCG_MEM = 0x02,		/* This page holds a memory charge */
-	PCG_MEMSW = 0x04,	/* This page holds a memory+swap charge */
-};
-
-struct pglist_data;
-
-#ifdef CONFIG_MEMCG
-struct mem_cgroup;
-
-/*
- * Page Cgroup can be considered as an extended mem_map.
- * A page_cgroup page is associated with every page descriptor. The
- * page_cgroup helps us identify information about the cgroup
- * All page cgroups are allocated at boot or memory hotplug event,
- * then the page cgroup for pfn always exists.
- */
-struct page_cgroup {
-	unsigned long flags;
-	struct mem_cgroup *mem_cgroup;
-};
-
-extern void pgdat_page_cgroup_init(struct pglist_data *pgdat);
-
-#ifdef CONFIG_SPARSEMEM
-static inline void page_cgroup_init_flatmem(void)
-{
-}
-extern void page_cgroup_init(void);
-#else
-extern void page_cgroup_init_flatmem(void);
-static inline void page_cgroup_init(void)
-{
-}
-#endif
-
-struct page_cgroup *lookup_page_cgroup(struct page *page);
-
-static inline int PageCgroupUsed(struct page_cgroup *pc)
-{
-	return !!(pc->flags & PCG_USED);
-}
-#else /* !CONFIG_MEMCG */
-struct page_cgroup;
-
-static inline void pgdat_page_cgroup_init(struct pglist_data *pgdat)
-{
-}
-
-static inline struct page_cgroup *lookup_page_cgroup(struct page *page)
-{
-	return NULL;
-}
-
-static inline void page_cgroup_init(void)
-{
-}
-
-static inline void page_cgroup_init_flatmem(void)
-{
-}
-#endif /* CONFIG_MEMCG */
-
-#include <linux/swap.h>
-
-#ifdef CONFIG_MEMCG_SWAP
-extern unsigned short swap_cgroup_cmpxchg(swp_entry_t ent,
-					unsigned short old, unsigned short new);
-extern unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id);
-extern unsigned short lookup_swap_cgroup_id(swp_entry_t ent);
-extern int swap_cgroup_swapon(int type, unsigned long max_pages);
-extern void swap_cgroup_swapoff(int type);
-#else
-
-static inline
-unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id)
-{
-	return 0;
-}
-
-static inline
-unsigned short lookup_swap_cgroup_id(swp_entry_t ent)
-{
-	return 0;
-}
-
-static inline int
-swap_cgroup_swapon(int type, unsigned long max_pages)
-{
-	return 0;
-}
-
-static inline void swap_cgroup_swapoff(int type)
-{
-	return;
-}
-
-#endif /* CONFIG_MEMCG_SWAP */
-
-#endif /* __LINUX_PAGE_CGROUP_H */
diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h
new file mode 100644
index 000000000000..955421575d16
--- /dev/null
+++ b/include/linux/page_counter.h
@@ -0,0 +1,51 @@
+#ifndef _LINUX_PAGE_COUNTER_H
+#define _LINUX_PAGE_COUNTER_H
+
+#include <linux/atomic.h>
+#include <linux/kernel.h>
+#include <asm/page.h>
+
+struct page_counter {
+	atomic_long_t count;
+	unsigned long limit;
+	struct page_counter *parent;
+
+	/* legacy */
+	unsigned long watermark;
+	unsigned long failcnt;
+};
+
+#if BITS_PER_LONG == 32
+#define PAGE_COUNTER_MAX LONG_MAX
+#else
+#define PAGE_COUNTER_MAX (LONG_MAX / PAGE_SIZE)
+#endif
+
+static inline void page_counter_init(struct page_counter *counter,
+				     struct page_counter *parent)
+{
+	atomic_long_set(&counter->count, 0);
+	counter->limit = PAGE_COUNTER_MAX;
+	counter->parent = parent;
+}
+
+static inline unsigned long page_counter_read(struct page_counter *counter)
+{
+	return atomic_long_read(&counter->count);
+}
+
+void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages);
+void page_counter_charge(struct page_counter *counter, unsigned long nr_pages);
+int page_counter_try_charge(struct page_counter *counter,
+			    unsigned long nr_pages,
+			    struct page_counter **fail);
+void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages);
+int page_counter_limit(struct page_counter *counter, unsigned long limit);
+int page_counter_memparse(const char *buf, unsigned long *nr_pages);
+
+static inline void page_counter_reset_watermark(struct page_counter *counter)
+{
+	counter->watermark = page_counter_read(counter);
+}
+
+#endif /* _LINUX_PAGE_COUNTER_H */
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index d5c89e0dd0e6..494ab0588b65 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -141,28 +141,42 @@ static inline bool __ref_is_percpu(struct percpu_ref *ref,
 }
 
 /**
- * percpu_ref_get - increment a percpu refcount
+ * percpu_ref_get_many - increment a percpu refcount
  * @ref: percpu_ref to get
+ * @nr: number of references to get
  *
- * Analagous to atomic_long_inc().
+ * Analogous to atomic_long_add().
  *
  * This function is safe to call as long as @ref is between init and exit.
  */
-static inline void percpu_ref_get(struct percpu_ref *ref)
+static inline void percpu_ref_get_many(struct percpu_ref *ref, unsigned long nr)
 {
 	unsigned long __percpu *percpu_count;
 
 	rcu_read_lock_sched();
 
 	if (__ref_is_percpu(ref, &percpu_count))
-		this_cpu_inc(*percpu_count);
+		this_cpu_add(*percpu_count, nr);
 	else
-		atomic_long_inc(&ref->count);
+		atomic_long_add(nr, &ref->count);
 
 	rcu_read_unlock_sched();
 }
 
 /**
+ * percpu_ref_get - increment a percpu refcount
+ * @ref: percpu_ref to get
+ *
+ * Analagous to atomic_long_inc().
+ *
+ * This function is safe to call as long as @ref is between init and exit.
+ */
+static inline void percpu_ref_get(struct percpu_ref *ref)
+{
+	percpu_ref_get_many(ref, 1);
+}
+
+/**
  * percpu_ref_tryget - try to increment a percpu refcount
  * @ref: percpu_ref to try-get
  *
@@ -225,29 +239,44 @@ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref)
 }
 
 /**
- * percpu_ref_put - decrement a percpu refcount
+ * percpu_ref_put_many - decrement a percpu refcount
  * @ref: percpu_ref to put
+ * @nr: number of references to put
  *
  * Decrement the refcount, and if 0, call the release function (which was passed
  * to percpu_ref_init())
  *
  * This function is safe to call as long as @ref is between init and exit.
  */
-static inline void percpu_ref_put(struct percpu_ref *ref)
+static inline void percpu_ref_put_many(struct percpu_ref *ref, unsigned long nr)
 {
 	unsigned long __percpu *percpu_count;
 
 	rcu_read_lock_sched();
 
 	if (__ref_is_percpu(ref, &percpu_count))
-		this_cpu_dec(*percpu_count);
-	else if (unlikely(atomic_long_dec_and_test(&ref->count)))
+		this_cpu_sub(*percpu_count, nr);
+	else if (unlikely(atomic_long_sub_and_test(nr, &ref->count)))
 		ref->release(ref);
 
 	rcu_read_unlock_sched();
 }
 
 /**
+ * percpu_ref_put - decrement a percpu refcount
+ * @ref: percpu_ref to put
+ *
+ * Decrement the refcount, and if 0, call the release function (which was passed
+ * to percpu_ref_init())
+ *
+ * This function is safe to call as long as @ref is between init and exit.
+ */
+static inline void percpu_ref_put(struct percpu_ref *ref)
+{
+	percpu_ref_put_many(ref, 1);
+}
+
+/**
  * percpu_ref_is_zero - test whether a percpu refcount reached zero
  * @ref: percpu_ref to test
  *
diff --git a/include/linux/printk.h b/include/linux/printk.h
index d78125f73ac4..3dd489f2dedc 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -118,7 +118,6 @@ int no_printk(const char *fmt, ...)
 #ifdef CONFIG_EARLY_PRINTK
 extern asmlinkage __printf(1, 2)
 void early_printk(const char *fmt, ...);
-void early_vprintk(const char *fmt, va_list ap);
 #else
 static inline __printf(1, 2) __cold
 void early_printk(const char *s, ...) { }
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index cc79eff4a1ad..987a73a40ef8 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -52,7 +52,7 @@ extern void ptrace_notify(int exit_code);
 extern void __ptrace_link(struct task_struct *child,
 			  struct task_struct *new_parent);
 extern void __ptrace_unlink(struct task_struct *child);
-extern void exit_ptrace(struct task_struct *tracer);
+extern void exit_ptrace(struct task_struct *tracer, struct list_head *dead);
 #define PTRACE_MODE_READ	0x01
 #define PTRACE_MODE_ATTACH	0x02
 #define PTRACE_MODE_NOAUDIT	0x04
diff --git a/include/linux/ratelimit.h b/include/linux/ratelimit.h
index 0a260d8a18bf..18102529254e 100644
--- a/include/linux/ratelimit.h
+++ b/include/linux/ratelimit.h
@@ -17,14 +17,20 @@ struct ratelimit_state {
 	unsigned long	begin;
 };
 
-#define DEFINE_RATELIMIT_STATE(name, interval_init, burst_init)		\
-									\
-	struct ratelimit_state name = {					\
+#define RATELIMIT_STATE_INIT(name, interval_init, burst_init) {		\
 		.lock		= __RAW_SPIN_LOCK_UNLOCKED(name.lock),	\
 		.interval	= interval_init,			\
 		.burst		= burst_init,				\
 	}
 
+#define RATELIMIT_STATE_INIT_DISABLED					\
+	RATELIMIT_STATE_INIT(ratelimit_state, 0, DEFAULT_RATELIMIT_BURST)
+
+#define DEFINE_RATELIMIT_STATE(name, interval_init, burst_init)		\
+									\
+	struct ratelimit_state name =					\
+		RATELIMIT_STATE_INIT(name, interval_init, burst_init)	\
+
 static inline void ratelimit_state_init(struct ratelimit_state *rs,
 					int interval, int burst)
 {
diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h
deleted file mode 100644
index 56b7bc32db4f..000000000000
--- a/include/linux/res_counter.h
+++ /dev/null
@@ -1,223 +0,0 @@
-#ifndef __RES_COUNTER_H__
-#define __RES_COUNTER_H__
-
-/*
- * Resource Counters
- * Contain common data types and routines for resource accounting
- *
- * Copyright 2007 OpenVZ SWsoft Inc
- *
- * Author: Pavel Emelianov <xemul@openvz.org>
- *
- * See Documentation/cgroups/resource_counter.txt for more
- * info about what this counter is.
- */
-
-#include <linux/spinlock.h>
-#include <linux/errno.h>
-
-/*
- * The core object. the cgroup that wishes to account for some
- * resource may include this counter into its structures and use
- * the helpers described beyond
- */
-
-struct res_counter {
-	/*
-	 * the current resource consumption level
-	 */
-	unsigned long long usage;
-	/*
-	 * the maximal value of the usage from the counter creation
-	 */
-	unsigned long long max_usage;
-	/*
-	 * the limit that usage cannot exceed
-	 */
-	unsigned long long limit;
-	/*
-	 * the limit that usage can be exceed
-	 */
-	unsigned long long soft_limit;
-	/*
-	 * the number of unsuccessful attempts to consume the resource
-	 */
-	unsigned long long failcnt;
-	/*
-	 * the lock to protect all of the above.
-	 * the routines below consider this to be IRQ-safe
-	 */
-	spinlock_t lock;
-	/*
-	 * Parent counter, used for hierarchial resource accounting
-	 */
-	struct res_counter *parent;
-};
-
-#define RES_COUNTER_MAX ULLONG_MAX
-
-/**
- * Helpers to interact with userspace
- * res_counter_read_u64() - returns the value of the specified member.
- * res_counter_read/_write - put/get the specified fields from the
- * res_counter struct to/from the user
- *
- * @counter:     the counter in question
- * @member:  the field to work with (see RES_xxx below)
- * @buf:     the buffer to opeate on,...
- * @nbytes:  its size...
- * @pos:     and the offset.
- */
-
-u64 res_counter_read_u64(struct res_counter *counter, int member);
-
-ssize_t res_counter_read(struct res_counter *counter, int member,
-		const char __user *buf, size_t nbytes, loff_t *pos,
-		int (*read_strategy)(unsigned long long val, char *s));
-
-int res_counter_memparse_write_strategy(const char *buf,
-					unsigned long long *res);
-
-/*
- * the field descriptors. one for each member of res_counter
- */
-
-enum {
-	RES_USAGE,
-	RES_MAX_USAGE,
-	RES_LIMIT,
-	RES_FAILCNT,
-	RES_SOFT_LIMIT,
-};
-
-/*
- * helpers for accounting
- */
-
-void res_counter_init(struct res_counter *counter, struct res_counter *parent);
-
-/*
- * charge - try to consume more resource.
- *
- * @counter: the counter
- * @val: the amount of the resource. each controller defines its own
- *       units, e.g. numbers, bytes, Kbytes, etc
- *
- * returns 0 on success and <0 if the counter->usage will exceed the
- * counter->limit
- *
- * charge_nofail works the same, except that it charges the resource
- * counter unconditionally, and returns < 0 if the after the current
- * charge we are over limit.
- */
-
-int __must_check res_counter_charge(struct res_counter *counter,
-		unsigned long val, struct res_counter **limit_fail_at);
-int res_counter_charge_nofail(struct res_counter *counter,
-		unsigned long val, struct res_counter **limit_fail_at);
-
-/*
- * uncharge - tell that some portion of the resource is released
- *
- * @counter: the counter
- * @val: the amount of the resource
- *
- * these calls check for usage underflow and show a warning on the console
- *
- * returns the total charges still present in @counter.
- */
-
-u64 res_counter_uncharge(struct res_counter *counter, unsigned long val);
-
-u64 res_counter_uncharge_until(struct res_counter *counter,
-			       struct res_counter *top,
-			       unsigned long val);
-/**
- * res_counter_margin - calculate chargeable space of a counter
- * @cnt: the counter
- *
- * Returns the difference between the hard limit and the current usage
- * of resource counter @cnt.
- */
-static inline unsigned long long res_counter_margin(struct res_counter *cnt)
-{
-	unsigned long long margin;
-	unsigned long flags;
-
-	spin_lock_irqsave(&cnt->lock, flags);
-	if (cnt->limit > cnt->usage)
-		margin = cnt->limit - cnt->usage;
-	else
-		margin = 0;
-	spin_unlock_irqrestore(&cnt->lock, flags);
-	return margin;
-}
-
-/**
- * Get the difference between the usage and the soft limit
- * @cnt: The counter
- *
- * Returns 0 if usage is less than or equal to soft limit
- * The difference between usage and soft limit, otherwise.
- */
-static inline unsigned long long
-res_counter_soft_limit_excess(struct res_counter *cnt)
-{
-	unsigned long long excess;
-	unsigned long flags;
-
-	spin_lock_irqsave(&cnt->lock, flags);
-	if (cnt->usage <= cnt->soft_limit)
-		excess = 0;
-	else
-		excess = cnt->usage - cnt->soft_limit;
-	spin_unlock_irqrestore(&cnt->lock, flags);
-	return excess;
-}
-
-static inline void res_counter_reset_max(struct res_counter *cnt)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&cnt->lock, flags);
-	cnt->max_usage = cnt->usage;
-	spin_unlock_irqrestore(&cnt->lock, flags);
-}
-
-static inline void res_counter_reset_failcnt(struct res_counter *cnt)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&cnt->lock, flags);
-	cnt->failcnt = 0;
-	spin_unlock_irqrestore(&cnt->lock, flags);
-}
-
-static inline int res_counter_set_limit(struct res_counter *cnt,
-		unsigned long long limit)
-{
-	unsigned long flags;
-	int ret = -EBUSY;
-
-	spin_lock_irqsave(&cnt->lock, flags);
-	if (cnt->usage <= limit) {
-		cnt->limit = limit;
-		ret = 0;
-	}
-	spin_unlock_irqrestore(&cnt->lock, flags);
-	return ret;
-}
-
-static inline int
-res_counter_set_soft_limit(struct res_counter *cnt,
-				unsigned long long soft_limit)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&cnt->lock, flags);
-	cnt->soft_limit = soft_limit;
-	spin_unlock_irqrestore(&cnt->lock, flags);
-	return 0;
-}
-
-#endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 55f5ee7cc3d3..ffd1444b087c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2482,6 +2482,10 @@ extern void do_group_exit(int);
 extern int do_execve(struct filename *,
 		     const char __user * const __user *,
 		     const char __user * const __user *);
+extern int do_execveat(int, struct filename *,
+		       const char __user * const __user *,
+		       const char __user * const __user *,
+		       int);
 extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *);
 struct task_struct *fork_idle(int);
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
diff --git a/include/linux/slab.h b/include/linux/slab.h
index c265bec6a57d..8a2457d42fc8 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -513,10 +513,6 @@ struct memcg_cache_params {
 
 int memcg_update_all_caches(int num_memcgs);
 
-struct seq_file;
-int cache_show(struct kmem_cache *s, struct seq_file *m);
-void print_slabinfo_header(struct seq_file *m);
-
 /**
  * kmalloc_array - allocate memory for an array.
  * @n: number of elements.
diff --git a/include/linux/string.h b/include/linux/string.h
index 2e22a2e58f3a..a0c6fd5fb5c5 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -117,6 +117,7 @@ void *memchr_inv(const void *s, int c, size_t n);
 
 extern char *kstrdup(const char *s, gfp_t gfp);
 extern char *kstrndup(const char *s, size_t len, gfp_t gfp);
+extern char *kstrimdup(const char *s, gfp_t gfp);
 extern void *kmemdup(const void *src, size_t len, gfp_t gfp);
 
 extern char **argv_split(gfp_t gfp, const char *str, int *argcp);
diff --git a/include/linux/swap_cgroup.h b/include/linux/swap_cgroup.h
new file mode 100644
index 000000000000..145306bdc92f
--- /dev/null
+++ b/include/linux/swap_cgroup.h
@@ -0,0 +1,42 @@
+#ifndef __LINUX_SWAP_CGROUP_H
+#define __LINUX_SWAP_CGROUP_H
+
+#include <linux/swap.h>
+
+#ifdef CONFIG_MEMCG_SWAP
+
+extern unsigned short swap_cgroup_cmpxchg(swp_entry_t ent,
+					unsigned short old, unsigned short new);
+extern unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id);
+extern unsigned short lookup_swap_cgroup_id(swp_entry_t ent);
+extern int swap_cgroup_swapon(int type, unsigned long max_pages);
+extern void swap_cgroup_swapoff(int type);
+
+#else
+
+static inline
+unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id)
+{
+	return 0;
+}
+
+static inline
+unsigned short lookup_swap_cgroup_id(swp_entry_t ent)
+{
+	return 0;
+}
+
+static inline int
+swap_cgroup_swapon(int type, unsigned long max_pages)
+{
+	return 0;
+}
+
+static inline void swap_cgroup_swapoff(int type)
+{
+	return;
+}
+
+#endif /* CONFIG_MEMCG_SWAP */
+
+#endif /* __LINUX_SWAP_CGROUP_H */
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index bda9b81357cc..83d956ef0b18 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -877,4 +877,8 @@ asmlinkage long sys_seccomp(unsigned int op, unsigned int flags,
 asmlinkage long sys_getrandom(char __user *buf, size_t count,
 			      unsigned int flags);
 asmlinkage long sys_bpf(int cmd, union bpf_attr *attr, unsigned int size);
+asmlinkage long sys_execveat(int dfd, const char __user *filename,
+			const char __user *const __user *argv,
+			const char __user *const __user *envp, int flags);
+
 #endif
diff --git a/include/net/sock.h b/include/net/sock.h
index db47833a8c80..9d269a7aca09 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -54,8 +54,8 @@
 #include <linux/security.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
+#include <linux/page_counter.h>
 #include <linux/memcontrol.h>
-#include <linux/res_counter.h>
 #include <linux/static_key.h>
 #include <linux/aio.h>
 #include <linux/sched.h>
@@ -1074,7 +1074,7 @@ enum cg_proto_flags {
 };
 
 struct cg_proto {
-	struct res_counter	memory_allocated;	/* Current allocated memory. */
+	struct page_counter	memory_allocated;	/* Current allocated memory. */
 	struct percpu_counter	sockets_allocated;	/* Current number of sockets. */
 	int			memory_pressure;
 	long			sysctl_mem[3];
@@ -1226,34 +1226,26 @@ static inline void memcg_memory_allocated_add(struct cg_proto *prot,
 					      unsigned long amt,
 					      int *parent_status)
 {
-	struct res_counter *fail;
-	int ret;
+	page_counter_charge(&prot->memory_allocated, amt);
 
-	ret = res_counter_charge_nofail(&prot->memory_allocated,
-					amt << PAGE_SHIFT, &fail);
-	if (ret < 0)
+	if (page_counter_read(&prot->memory_allocated) >
+	    prot->memory_allocated.limit)
 		*parent_status = OVER_LIMIT;
 }
 
 static inline void memcg_memory_allocated_sub(struct cg_proto *prot,
 					      unsigned long amt)
 {
-	res_counter_uncharge(&prot->memory_allocated, amt << PAGE_SHIFT);
-}
-
-static inline u64 memcg_memory_allocated_read(struct cg_proto *prot)
-{
-	u64 ret;
-	ret = res_counter_read_u64(&prot->memory_allocated, RES_USAGE);
-	return ret >> PAGE_SHIFT;
+	page_counter_uncharge(&prot->memory_allocated, amt);
 }
 
 static inline long
 sk_memory_allocated(const struct sock *sk)
 {
 	struct proto *prot = sk->sk_prot;
+
 	if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
-		return memcg_memory_allocated_read(sk->sk_cgrp);
+		return page_counter_read(&sk->sk_cgrp->memory_allocated);
 
 	return atomic_long_read(prot->memory_allocated);
 }
@@ -1267,7 +1259,7 @@ sk_memory_allocated_add(struct sock *sk, int amt, int *parent_status)
 		memcg_memory_allocated_add(sk->sk_cgrp, amt, parent_status);
 		/* update the root cgroup regardless */
 		atomic_long_add_return(amt, prot->memory_allocated);
-		return memcg_memory_allocated_read(sk->sk_cgrp);
+		return page_counter_read(&sk->sk_cgrp->memory_allocated);
 	}
 
 	return atomic_long_add_return(amt, prot->memory_allocated);
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 22749c134117..e016bd9b1a04 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -707,9 +707,11 @@ __SYSCALL(__NR_getrandom, sys_getrandom)
 __SYSCALL(__NR_memfd_create, sys_memfd_create)
 #define __NR_bpf 280
 __SYSCALL(__NR_bpf, sys_bpf)
+#define __NR_execveat 281
+__SC_COMP(__NR_execveat, sys_execveat, compat_sys_execveat)
 
 #undef __NR_syscalls
-#define __NR_syscalls 281
+#define __NR_syscalls 282
 
 /*
  * All syscalls below here should go away really,
diff --git a/include/uapi/linux/msg.h b/include/uapi/linux/msg.h
index a70375526578..f51c8001dbe5 100644
--- a/include/uapi/linux/msg.h
+++ b/include/uapi/linux/msg.h
@@ -51,16 +51,28 @@ struct msginfo {
 };
 
 /*
- * Scaling factor to compute msgmni:
- * the memory dedicated to msg queues (msgmni * msgmnb) should occupy
- * at most 1/MSG_MEM_SCALE of the lowmem (see the formula in ipc/msg.c):
- * up to 8MB       : msgmni = 16 (MSGMNI)
- * 4 GB            : msgmni = 8K
- * more than 16 GB : msgmni = 32K (IPCMNI)
+ * MSGMNI, MSGMAX and MSGMNB are default values which can be
+ * modified by sysctl.
+ *
+ * MSGMNI is the upper limit for the number of messages queues per
+ * namespace.
+ * It has been chosen to be as large possible without facilitating
+ * scenarios where userspace causes overflows when adjusting the limits via
+ * operations of the form retrieve current limit; add X; update limit".
+ *
+ * MSGMNB is the default size of a new message queue. Non-root tasks can
+ * decrease the size with msgctl(IPC_SET), root tasks
+ * (actually: CAP_SYS_RESOURCE) can both increase and decrease the queue
+ * size. The optimal value is application dependent.
+ * 16384 is used because it was always used (since 0.99.10)
+ *
+ * MAXMAX is the maximum size of an individual message, it's a global
+ * (per-namespace) limit that applies for all message queues.
+ * It's set to 1/2 of MSGMNB, to ensure that at least two messages fit into
+ * the queue. This is also an arbitrary choice (since 2.6.0).
  */
-#define MSG_MEM_SCALE 32
 
-#define MSGMNI    16   /* <= IPCMNI */     /* max # of msg queue identifiers */
+#define MSGMNI 32000   /* <= IPCMNI */     /* max # of msg queue identifiers */
 #define MSGMAX  8192   /* <= INT_MAX */   /* max size of message (bytes) */
 #define MSGMNB 16384   /* <= INT_MAX */   /* default max size of a message queue */
 
diff --git a/include/uapi/linux/sem.h b/include/uapi/linux/sem.h
index 541fce03b50c..dd73b908b2f3 100644
--- a/include/uapi/linux/sem.h
+++ b/include/uapi/linux/sem.h
@@ -63,10 +63,22 @@ struct  seminfo {
 	int semaem;
 };
 
-#define SEMMNI  128             /* <= IPCMNI  max # of semaphore identifiers */
-#define SEMMSL  250             /* <= 8 000 max num of semaphores per id */
+/*
+ * SEMMNI, SEMMSL and SEMMNS are default values which can be
+ * modified by sysctl.
+ * The values has been chosen to be larger than necessary for any
+ * known configuration.
+ *
+ * SEMOPM should not be increased beyond 1000, otherwise there is the
+ * risk that semop()/semtimedop() fails due to kernel memory fragmentation when
+ * allocating the sop array.
+ */
+
+
+#define SEMMNI  32000           /* <= IPCMNI  max # of semaphore identifiers */
+#define SEMMSL  32000           /* <= INT_MAX max num of semaphores per id */
 #define SEMMNS  (SEMMNI*SEMMSL) /* <= INT_MAX max # of semaphores in system */
-#define SEMOPM  32	        /* <= 1 000 max num of ops per semop call */
+#define SEMOPM  500	        /* <= 1 000 max num of ops per semop call */
 #define SEMVMX  32767           /* <= 32767 semaphore maximum value */
 #define SEMAEM  SEMVMX          /* adjust on exit max value */
 
diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h
index 43aaba1cc037..0956373b56db 100644
--- a/include/uapi/linux/sysctl.h
+++ b/include/uapi/linux/sysctl.h
@@ -153,6 +153,7 @@ enum
 	KERN_MAX_LOCK_DEPTH=74, /* int: rtmutex's maximum lock depth */
 	KERN_NMI_WATCHDOG=75, /* int: enable/disable nmi watchdog */
 	KERN_PANIC_ON_NMI=76, /* int: whether we will panic on an unrecovered */
+	KERN_PANIC_ON_WARN=77, /* int: call panic() in WARN() functions */
 };
 
 
diff --git a/init/Kconfig b/init/Kconfig
index ca183c222ff3..501ef0a35348 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -893,14 +893,6 @@ config ARCH_SUPPORTS_INT128
 config ARCH_WANT_NUMA_VARIABLE_LOCALITY
 	bool
 
-config NUMA_BALANCING_DEFAULT_ENABLED
-	bool "Automatically enable NUMA aware memory/task placement"
-	default y
-	depends on NUMA_BALANCING
-	help
-	  If set, automatic NUMA balancing will be enabled if running on a NUMA
-	  machine.
-
 config NUMA_BALANCING
 	bool "Memory placement aware NUMA scheduler"
 	depends on ARCH_SUPPORTS_NUMA_BALANCING
@@ -913,6 +905,14 @@ config NUMA_BALANCING
 
 	  This system will be inactive on UMA systems.
 
+config NUMA_BALANCING_DEFAULT_ENABLED
+	bool "Automatically enable NUMA aware memory/task placement"
+	default y
+	depends on NUMA_BALANCING
+	help
+	  If set, automatic NUMA balancing will be enabled if running on a NUMA
+	  machine.
+
 menuconfig CGROUPS
 	boolean "Control Group support"
 	select KERNFS
@@ -972,32 +972,17 @@ config CGROUP_CPUACCT
 	  Provides a simple Resource Controller for monitoring the
 	  total CPU consumed by the tasks in a cgroup.
 
-config RESOURCE_COUNTERS
-	bool "Resource counters"
-	help
-	  This option enables controller independent resource accounting
-	  infrastructure that works with cgroups.
+config PAGE_COUNTER
+       bool
 
 config MEMCG
 	bool "Memory Resource Controller for Control Groups"
-	depends on RESOURCE_COUNTERS
+	select PAGE_COUNTER
 	select EVENTFD
 	help
 	  Provides a memory resource controller that manages both anonymous
 	  memory and page cache. (See Documentation/cgroups/memory.txt)
 
-	  Note that setting this option increases fixed memory overhead
-	  associated with each page of memory in the system. By this,
-	  8(16)bytes/PAGE_SIZE on 32(64)bit system will be occupied by memory
-	  usage tracking struct at boot. Total amount of this is printed out
-	  at boot.
-
-	  Only enable when you're ok with these trade offs and really
-	  sure you need the memory resource controller. Even when you enable
-	  this, you can set "cgroup_disable=memory" at your boot option to
-	  disable memory resource controller and you can avoid overheads.
-	  (and lose benefits of memory resource controller)
-
 config MEMCG_SWAP
 	bool "Memory Resource Controller Swap Extension"
 	depends on MEMCG && SWAP
@@ -1048,7 +1033,8 @@ config MEMCG_KMEM
 
 config CGROUP_HUGETLB
 	bool "HugeTLB Resource Controller for Control Groups"
-	depends on RESOURCE_COUNTERS && HUGETLB_PAGE
+	depends on HUGETLB_PAGE
+	select PAGE_COUNTER
 	default n
 	help
 	  Provides a cgroup Resource Controller for HugeTLB pages.
diff --git a/init/main.c b/init/main.c
index 321d0ceb26d3..235aafbb2f2b 100644
--- a/init/main.c
+++ b/init/main.c
@@ -51,7 +51,6 @@
 #include <linux/mempolicy.h>
 #include <linux/key.h>
 #include <linux/buffer_head.h>
-#include <linux/page_cgroup.h>
 #include <linux/debug_locks.h>
 #include <linux/debugobjects.h>
 #include <linux/lockdep.h>
@@ -485,11 +484,6 @@ void __init __weak thread_info_cache_init(void)
  */
 static void __init mm_init(void)
 {
-	/*
-	 * page_cgroup requires contiguous pages,
-	 * bigger than MAX_ORDER unless SPARSEMEM.
-	 */
-	page_cgroup_init_flatmem();
 	mem_init();
 	kmem_cache_init();
 	percpu_init_late();
@@ -627,7 +621,6 @@ asmlinkage __visible void __init start_kernel(void)
 		initrd_start = 0;
 	}
 #endif
-	page_cgroup_init();
 	debug_objects_mem_init();
 	kmemleak_init();
 	setup_per_cpu_pageset();
@@ -959,8 +952,8 @@ static int __ref kernel_init(void *unused)
 		ret = run_init_process(execute_command);
 		if (!ret)
 			return 0;
-		pr_err("Failed to execute %s (error %d).  Attempting defaults...\n",
-			execute_command, ret);
+		panic("Requested init %s failed (error %d).",
+		      execute_command, ret);
 	}
 	if (!try_to_run_init_process("/sbin/init") ||
 	    !try_to_run_init_process("/etc/init") ||
diff --git a/ipc/Makefile b/ipc/Makefile
index 9075e172e52c..86c7300ecdf5 100644
--- a/ipc/Makefile
+++ b/ipc/Makefile
@@ -3,7 +3,7 @@
 #
 
 obj-$(CONFIG_SYSVIPC_COMPAT) += compat.o
-obj-$(CONFIG_SYSVIPC) += util.o msgutil.o msg.o sem.o shm.o ipcns_notifier.o syscall.o
+obj-$(CONFIG_SYSVIPC) += util.o msgutil.o msg.o sem.o shm.o syscall.o
 obj-$(CONFIG_SYSVIPC_SYSCTL) += ipc_sysctl.o
 obj_mq-$(CONFIG_COMPAT) += compat_mq.o
 obj-$(CONFIG_POSIX_MQUEUE) += mqueue.o msgutil.o $(obj_mq-y)
diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c
index e8075b247497..8ad93c29f511 100644
--- a/ipc/ipc_sysctl.c
+++ b/ipc/ipc_sysctl.c
@@ -62,29 +62,6 @@ static int proc_ipc_dointvec_minmax_orphans(struct ctl_table *table, int write,
 	return err;
 }
 
-static int proc_ipc_callback_dointvec_minmax(struct ctl_table *table, int write,
-	void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-	struct ctl_table ipc_table;
-	size_t lenp_bef = *lenp;
-	int rc;
-
-	memcpy(&ipc_table, table, sizeof(ipc_table));
-	ipc_table.data = get_ipc(table);
-
-	rc = proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
-
-	if (write && !rc && lenp_bef == *lenp)
-		/*
-		 * Tunable has successfully been changed by hand. Disable its
-		 * automatic adjustment. This simply requires unregistering
-		 * the notifiers that trigger recalculation.
-		 */
-		unregister_ipcns_notifier(current->nsproxy->ipc_ns);
-
-	return rc;
-}
-
 static int proc_ipc_doulongvec_minmax(struct ctl_table *table, int write,
 	void __user *buffer, size_t *lenp, loff_t *ppos)
 {
@@ -96,54 +73,19 @@ static int proc_ipc_doulongvec_minmax(struct ctl_table *table, int write,
 					lenp, ppos);
 }
 
-/*
- * Routine that is called when the file "auto_msgmni" has successfully been
- * written.
- * Two values are allowed:
- * 0: unregister msgmni's callback routine from the ipc namespace notifier
- *    chain. This means that msgmni won't be recomputed anymore upon memory
- *    add/remove or ipc namespace creation/removal.
- * 1: register back the callback routine.
- */
-static void ipc_auto_callback(int val)
-{
-	if (!val)
-		unregister_ipcns_notifier(current->nsproxy->ipc_ns);
-	else {
-		/*
-		 * Re-enable automatic recomputing only if not already
-		 * enabled.
-		 */
-		recompute_msgmni(current->nsproxy->ipc_ns);
-		cond_register_ipcns_notifier(current->nsproxy->ipc_ns);
-	}
-}
-
-static int proc_ipcauto_dointvec_minmax(struct ctl_table *table, int write,
+static int proc_ipc_auto_msgmni(struct ctl_table *table, int write,
 	void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table ipc_table;
-	int oldval;
-	int rc;
+	int dummy = 0;
 
 	memcpy(&ipc_table, table, sizeof(ipc_table));
-	ipc_table.data = get_ipc(table);
-	oldval = *((int *)(ipc_table.data));
+	ipc_table.data = &dummy;
 
-	rc = proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
+	if (write)
+		pr_info_once("writing to auto_msgmni has no effect");
 
-	if (write && !rc) {
-		int newval = *((int *)(ipc_table.data));
-		/*
-		 * The file "auto_msgmni" has correctly been set.
-		 * React by (un)registering the corresponding tunable, if the
-		 * value has changed.
-		 */
-		if (newval != oldval)
-			ipc_auto_callback(newval);
-	}
-
-	return rc;
+	return proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
 }
 
 #else
@@ -151,8 +93,7 @@ static int proc_ipcauto_dointvec_minmax(struct ctl_table *table, int write,
 #define proc_ipc_dointvec	   NULL
 #define proc_ipc_dointvec_minmax   NULL
 #define proc_ipc_dointvec_minmax_orphans   NULL
-#define proc_ipc_callback_dointvec_minmax  NULL
-#define proc_ipcauto_dointvec_minmax NULL
+#define proc_ipc_auto_msgmni	   NULL
 #endif
 
 static int zero;
@@ -204,11 +145,20 @@ static struct ctl_table ipc_kern_table[] = {
 		.data		= &init_ipc_ns.msg_ctlmni,
 		.maxlen		= sizeof(init_ipc_ns.msg_ctlmni),
 		.mode		= 0644,
-		.proc_handler	= proc_ipc_callback_dointvec_minmax,
+		.proc_handler	= proc_ipc_dointvec_minmax,
 		.extra1		= &zero,
 		.extra2		= &int_max,
 	},
 	{
+		.procname	= "auto_msgmni",
+		.data		= NULL,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_ipc_auto_msgmni,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
+	{
 		.procname	=  "msgmnb",
 		.data		= &init_ipc_ns.msg_ctlmnb,
 		.maxlen		= sizeof(init_ipc_ns.msg_ctlmnb),
@@ -224,15 +174,6 @@ static struct ctl_table ipc_kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_ipc_dointvec,
 	},
-	{
-		.procname	= "auto_msgmni",
-		.data		= &init_ipc_ns.auto_msgmni,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_ipcauto_dointvec_minmax,
-		.extra1		= &zero,
-		.extra2		= &one,
-	},
 #ifdef CONFIG_CHECKPOINT_RESTORE
 	{
 		.procname	= "sem_next_id",
diff --git a/ipc/ipcns_notifier.c b/ipc/ipcns_notifier.c
deleted file mode 100644
index b9b31a4f77e1..000000000000
--- a/ipc/ipcns_notifier.c
+++ /dev/null
@@ -1,92 +0,0 @@
-/*
- * linux/ipc/ipcns_notifier.c
- * Copyright (C) 2007 BULL SA. Nadia Derbey
- *
- * Notification mechanism for ipc namespaces:
- * The callback routine registered in the memory chain invokes the ipcns
- * notifier chain with the IPCNS_MEMCHANGED event.
- * Each callback routine registered in the ipcns namespace recomputes msgmni
- * for the owning namespace.
- */
-
-#include <linux/msg.h>
-#include <linux/rcupdate.h>
-#include <linux/notifier.h>
-#include <linux/nsproxy.h>
-#include <linux/ipc_namespace.h>
-
-#include "util.h"
-
-
-
-static BLOCKING_NOTIFIER_HEAD(ipcns_chain);
-
-
-static int ipcns_callback(struct notifier_block *self,
-				unsigned long action, void *arg)
-{
-	struct ipc_namespace *ns;
-
-	switch (action) {
-	case IPCNS_MEMCHANGED:   /* amount of lowmem has changed */
-	case IPCNS_CREATED:
-	case IPCNS_REMOVED:
-		/*
-		 * It's time to recompute msgmni
-		 */
-		ns = container_of(self, struct ipc_namespace, ipcns_nb);
-		/*
-		 * No need to get a reference on the ns: the 1st job of
-		 * free_ipc_ns() is to unregister the callback routine.
-		 * blocking_notifier_chain_unregister takes the wr lock to do
-		 * it.
-		 * When this callback routine is called the rd lock is held by
-		 * blocking_notifier_call_chain.
-		 * So the ipc ns cannot be freed while we are here.
-		 */
-		recompute_msgmni(ns);
-		break;
-	default:
-		break;
-	}
-
-	return NOTIFY_OK;
-}
-
-int register_ipcns_notifier(struct ipc_namespace *ns)
-{
-	int rc;
-
-	memset(&ns->ipcns_nb, 0, sizeof(ns->ipcns_nb));
-	ns->ipcns_nb.notifier_call = ipcns_callback;
-	ns->ipcns_nb.priority = IPCNS_CALLBACK_PRI;
-	rc = blocking_notifier_chain_register(&ipcns_chain, &ns->ipcns_nb);
-	if (!rc)
-		ns->auto_msgmni = 1;
-	return rc;
-}
-
-int cond_register_ipcns_notifier(struct ipc_namespace *ns)
-{
-	int rc;
-
-	memset(&ns->ipcns_nb, 0, sizeof(ns->ipcns_nb));
-	ns->ipcns_nb.notifier_call = ipcns_callback;
-	ns->ipcns_nb.priority = IPCNS_CALLBACK_PRI;
-	rc = blocking_notifier_chain_cond_register(&ipcns_chain,
-							&ns->ipcns_nb);
-	if (!rc)
-		ns->auto_msgmni = 1;
-	return rc;
-}
-
-void unregister_ipcns_notifier(struct ipc_namespace *ns)
-{
-	blocking_notifier_chain_unregister(&ipcns_chain, &ns->ipcns_nb);
-	ns->auto_msgmni = 0;
-}
-
-int ipcns_notify(unsigned long val)
-{
-	return blocking_notifier_call_chain(&ipcns_chain, val, NULL);
-}
diff --git a/ipc/msg.c b/ipc/msg.c
index c5d8e3749985..a7261d5cbc89 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -989,43 +989,12 @@ SYSCALL_DEFINE5(msgrcv, int, msqid, struct msgbuf __user *, msgp, size_t, msgsz,
 	return do_msgrcv(msqid, msgp, msgsz, msgtyp, msgflg, do_msg_fill);
 }
 
-/*
- * Scale msgmni with the available lowmem size: the memory dedicated to msg
- * queues should occupy at most 1/MSG_MEM_SCALE of lowmem.
- * Also take into account the number of nsproxies created so far.
- * This should be done staying within the (MSGMNI , IPCMNI/nr_ipc_ns) range.
- */
-void recompute_msgmni(struct ipc_namespace *ns)
-{
-	struct sysinfo i;
-	unsigned long allowed;
-	int nb_ns;
-
-	si_meminfo(&i);
-	allowed = (((i.totalram - i.totalhigh) / MSG_MEM_SCALE) * i.mem_unit)
-		/ MSGMNB;
-	nb_ns = atomic_read(&nr_ipc_ns);
-	allowed /= nb_ns;
-
-	if (allowed < MSGMNI) {
-		ns->msg_ctlmni = MSGMNI;
-		return;
-	}
-
-	if (allowed > IPCMNI / nb_ns) {
-		ns->msg_ctlmni = IPCMNI / nb_ns;
-		return;
-	}
-
-	ns->msg_ctlmni = allowed;
-}
 
 void msg_init_ns(struct ipc_namespace *ns)
 {
 	ns->msg_ctlmax = MSGMAX;
 	ns->msg_ctlmnb = MSGMNB;
-
-	recompute_msgmni(ns);
+	ns->msg_ctlmni = MSGMNI;
 
 	atomic_set(&ns->msg_bytes, 0);
 	atomic_set(&ns->msg_hdrs, 0);
@@ -1069,9 +1038,6 @@ void __init msg_init(void)
 {
 	msg_init_ns(&init_ipc_ns);
 
-	printk(KERN_INFO "msgmni has been set to %d\n",
-		init_ipc_ns.msg_ctlmni);
-
 	ipc_init_proc_interface("sysvipc/msg",
 				"       key      msqid perms      cbytes       qnum lspid lrpid   uid   gid  cuid  cgid      stime      rtime      ctime\n",
 				IPC_MSG_IDS, sysvipc_msg_proc_show);
diff --git a/ipc/namespace.c b/ipc/namespace.c
index b54468e48e32..1a3ffd40356e 100644
--- a/ipc/namespace.c
+++ b/ipc/namespace.c
@@ -45,14 +45,6 @@ static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns,
 	msg_init_ns(ns);
 	shm_init_ns(ns);
 
-	/*
-	 * msgmni has already been computed for the new ipc ns.
-	 * Thus, do the ipcns creation notification before registering that
-	 * new ipcns in the chain.
-	 */
-	ipcns_notify(IPCNS_CREATED);
-	register_ipcns_notifier(ns);
-
 	ns->user_ns = get_user_ns(user_ns);
 
 	return ns;
@@ -99,25 +91,11 @@ void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids,
 
 static void free_ipc_ns(struct ipc_namespace *ns)
 {
-	/*
-	 * Unregistering the hotplug notifier at the beginning guarantees
-	 * that the ipc namespace won't be freed while we are inside the
-	 * callback routine. Since the blocking_notifier_chain_XXX routines
-	 * hold a rw lock on the notifier list, unregister_ipcns_notifier()
-	 * won't take the rw lock before blocking_notifier_call_chain() has
-	 * released the rd lock.
-	 */
-	unregister_ipcns_notifier(ns);
 	sem_exit_ns(ns);
 	msg_exit_ns(ns);
 	shm_exit_ns(ns);
 	atomic_dec(&nr_ipc_ns);
 
-	/*
-	 * Do the ipcns removal notification after decrementing nr_ipc_ns in
-	 * order to have a correct value when recomputing msgmni.
-	 */
-	ipcns_notify(IPCNS_REMOVED);
 	put_user_ns(ns->user_ns);
 	proc_free_inum(ns->proc_inum);
 	kfree(ns);
diff --git a/ipc/sem.c b/ipc/sem.c
index 454f6c6020a8..b9dc34498b00 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -326,10 +326,17 @@ static inline int sem_lock(struct sem_array *sma, struct sembuf *sops,
 
 		/* Then check that the global lock is free */
 		if (!spin_is_locked(&sma->sem_perm.lock)) {
-			/* spin_is_locked() is not a memory barrier */
-			smp_mb();
+			/*
+			 * The ipc object lock check must be visible on all
+			 * cores before rechecking the complex count.  Otherwise
+			 * we can race with  another thread that does:
+			 *	complex_count++;
+			 *	spin_unlock(sem_perm.lock);
+			 */
+			smp_rmb();
 
-			/* Now repeat the test of complex_count:
+			/*
+			 * Now repeat the test of complex_count:
 			 * It can't change anymore until we drop sem->lock.
 			 * Thus: if is now 0, then it will stay 0.
 			 */
diff --git a/ipc/shm.c b/ipc/shm.c
index 01454796ba3c..e5dc7d246f05 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -1229,6 +1229,7 @@ SYSCALL_DEFINE1(shmdt, char __user *, shmaddr)
 	int retval = -EINVAL;
 #ifdef CONFIG_MMU
 	loff_t size = 0;
+	struct file *file;
 	struct vm_area_struct *next;
 #endif
 
@@ -1245,7 +1246,8 @@ SYSCALL_DEFINE1(shmdt, char __user *, shmaddr)
 	 *   started at address shmaddr. It records it's size and then unmaps
 	 *   it.
 	 * - Then it unmaps all shm vmas that started at shmaddr and that
-	 *   are within the initially determined size.
+	 *   are within the initially determined size and that are from the
+	 *   same shm segment from which we determined the size.
 	 * Errors from do_munmap are ignored: the function only fails if
 	 * it's called with invalid parameters or if it's called to unmap
 	 * a part of a vma. Both calls in this function are for full vmas,
@@ -1271,8 +1273,14 @@ SYSCALL_DEFINE1(shmdt, char __user *, shmaddr)
 		if ((vma->vm_ops == &shm_vm_ops) &&
 			(vma->vm_start - addr)/PAGE_SIZE == vma->vm_pgoff) {
 
-
-			size = file_inode(vma->vm_file)->i_size;
+			/*
+			 * Record the file of the shm segment being
+			 * unmapped.  With mremap(), someone could place
+			 * page from another segment but with equal offsets
+			 * in the range we are unmapping.
+			 */
+			file = vma->vm_file;
+			size = file_inode(file)->i_size;
 			do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start);
 			/*
 			 * We discovered the size of the shm segment, so
@@ -1298,8 +1306,8 @@ SYSCALL_DEFINE1(shmdt, char __user *, shmaddr)
 
 		/* finding a matching vma now does not alter retval */
 		if ((vma->vm_ops == &shm_vm_ops) &&
-			(vma->vm_start - addr)/PAGE_SIZE == vma->vm_pgoff)
-
+		    ((vma->vm_start - addr)/PAGE_SIZE == vma->vm_pgoff) &&
+		    (vma->vm_file == file))
 			do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start);
 		vma = next;
 	}
diff --git a/ipc/util.c b/ipc/util.c
index 88adc329888c..106bed0378ab 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -71,44 +71,6 @@ struct ipc_proc_iface {
 	int (*show)(struct seq_file *, void *);
 };
 
-static void ipc_memory_notifier(struct work_struct *work)
-{
-	ipcns_notify(IPCNS_MEMCHANGED);
-}
-
-static int ipc_memory_callback(struct notifier_block *self,
-				unsigned long action, void *arg)
-{
-	static DECLARE_WORK(ipc_memory_wq, ipc_memory_notifier);
-
-	switch (action) {
-	case MEM_ONLINE:    /* memory successfully brought online */
-	case MEM_OFFLINE:   /* or offline: it's time to recompute msgmni */
-		/*
-		 * This is done by invoking the ipcns notifier chain with the
-		 * IPC_MEMCHANGED event.
-		 * In order not to keep the lock on the hotplug memory chain
-		 * for too long, queue a work item that will, when waken up,
-		 * activate the ipcns notification chain.
-		 */
-		schedule_work(&ipc_memory_wq);
-		break;
-	case MEM_GOING_ONLINE:
-	case MEM_GOING_OFFLINE:
-	case MEM_CANCEL_ONLINE:
-	case MEM_CANCEL_OFFLINE:
-	default:
-		break;
-	}
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block ipc_memory_nb = {
-	.notifier_call = ipc_memory_callback,
-	.priority = IPC_CALLBACK_PRI,
-};
-
 /**
  * ipc_init - initialise ipc subsystem
  *
@@ -124,8 +86,6 @@ static int __init ipc_init(void)
 	sem_init();
 	msg_init();
 	shm_init();
-	register_hotmemory_notifier(&ipc_memory_nb);
-	register_ipcns_notifier(&init_ipc_ns);
 	return 0;
 }
 device_initcall(ipc_init);
diff --git a/kernel/Makefile b/kernel/Makefile
index 17ea6d4a9a24..a59481a3fa6c 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -57,7 +57,6 @@ obj-$(CONFIG_UTS_NS) += utsname.o
 obj-$(CONFIG_USER_NS) += user_namespace.o
 obj-$(CONFIG_PID_NS) += pid_namespace.o
 obj-$(CONFIG_IKCONFIG) += configs.o
-obj-$(CONFIG_RESOURCE_COUNTERS) += res_counter.o
 obj-$(CONFIG_SMP) += stop_machine.o
 obj-$(CONFIG_KPROBES_SANITY_TEST) += test_kprobes.o
 obj-$(CONFIG_AUDIT) += audit.o auditfilter.o
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 1d0af8a2c646..6158a64b2309 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -193,7 +193,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 	}
 
 	flush_cache_page(vma, addr, pte_pfn(*ptep));
-	ptep_clear_flush(vma, addr, ptep);
+	ptep_clear_flush_notify(vma, addr, ptep);
 	set_pte_at_notify(mm, addr, ptep, mk_pte(kpage, vma->vm_page_prot));
 
 	page_remove_rmap(page);
@@ -724,14 +724,14 @@ build_map_info(struct address_space *mapping, loff_t offset, bool is_register)
 	int more = 0;
 
  again:
-	mutex_lock(&mapping->i_mmap_mutex);
+	i_mmap_lock_read(mapping);
 	vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) {
 		if (!valid_vma(vma, is_register))
 			continue;
 
 		if (!prev && !more) {
 			/*
-			 * Needs GFP_NOWAIT to avoid i_mmap_mutex recursion through
+			 * Needs GFP_NOWAIT to avoid i_mmap_rwsem recursion through
 			 * reclaim. This is optimistic, no harm done if it fails.
 			 */
 			prev = kmalloc(sizeof(struct map_info),
@@ -755,7 +755,7 @@ build_map_info(struct address_space *mapping, loff_t offset, bool is_register)
 		info->mm = vma->vm_mm;
 		info->vaddr = offset_to_vaddr(vma, offset);
 	}
-	mutex_unlock(&mapping->i_mmap_mutex);
+	i_mmap_unlock_read(mapping);
 
 	if (!more)
 		goto out;
diff --git a/kernel/exit.c b/kernel/exit.c
index 6fc4ab353e02..619242257639 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -508,15 +508,7 @@ static struct task_struct *find_new_reaper(struct task_struct *father)
 static void reparent_leader(struct task_struct *father, struct task_struct *p,
 				struct list_head *dead)
 {
-	list_move_tail(&p->sibling, &p->real_parent->children);
-
-	if (p->exit_state == EXIT_DEAD)
-		return;
-	/*
-	 * If this is a threaded reparent there is no need to
-	 * notify anyone anything has happened.
-	 */
-	if (same_thread_group(p->real_parent, father))
+	if (unlikely(p->exit_state == EXIT_DEAD))
 		return;
 
 	/* We don't want people slaying init. */
@@ -527,7 +519,7 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p,
 	    p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) {
 		if (do_notify_parent(p, p->exit_signal)) {
 			p->exit_state = EXIT_DEAD;
-			list_move_tail(&p->sibling, dead);
+			list_add(&p->ptrace_entry, dead);
 		}
 	}
 
@@ -536,38 +528,37 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p,
 
 static void forget_original_parent(struct task_struct *father)
 {
-	struct task_struct *p, *n, *reaper;
+	struct task_struct *p, *t, *n, *reaper;
 	LIST_HEAD(dead_children);
 
 	write_lock_irq(&tasklist_lock);
-	/*
-	 * Note that exit_ptrace() and find_new_reaper() might
-	 * drop tasklist_lock and reacquire it.
-	 */
-	exit_ptrace(father);
-	reaper = find_new_reaper(father);
+	if (unlikely(!list_empty(&father->ptraced)))
+		exit_ptrace(father, &dead_children);
 
-	list_for_each_entry_safe(p, n, &father->children, sibling) {
-		struct task_struct *t = p;
-
-		do {
+	/* Can drop and reacquire tasklist_lock */
+	reaper = find_new_reaper(father);
+	list_for_each_entry(p, &father->children, sibling) {
+		for_each_thread(p, t) {
 			t->real_parent = reaper;
-			if (t->parent == father) {
-				BUG_ON(t->ptrace);
+			BUG_ON(!t->ptrace != (t->parent == father));
+			if (likely(!t->ptrace))
 				t->parent = t->real_parent;
-			}
 			if (t->pdeath_signal)
 				group_send_sig_info(t->pdeath_signal,
 						    SEND_SIG_NOINFO, t);
-		} while_each_thread(p, t);
-		reparent_leader(father, p, &dead_children);
+		}
+		/*
+		 * If this is a threaded reparent there is no need to
+		 * notify anyone anything has happened.
+		 */
+		if (!same_thread_group(reaper, father))
+			reparent_leader(father, p, &dead_children);
 	}
+	list_splice_tail_init(&father->children, &reaper->children);
 	write_unlock_irq(&tasklist_lock);
 
-	BUG_ON(!list_empty(&father->children));
-
-	list_for_each_entry_safe(p, n, &dead_children, sibling) {
-		list_del_init(&p->sibling);
+	list_for_each_entry_safe(p, n, &dead_children, ptrace_entry) {
+		list_del_init(&p->ptrace_entry);
 		release_task(p);
 	}
 }
diff --git a/kernel/fork.c b/kernel/fork.c
index 9ca84189cfc2..4dc2ddade9f1 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -433,7 +433,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 			get_file(file);
 			if (tmp->vm_flags & VM_DENYWRITE)
 				atomic_dec(&inode->i_writecount);
-			mutex_lock(&mapping->i_mmap_mutex);
+			i_mmap_lock_write(mapping);
 			if (tmp->vm_flags & VM_SHARED)
 				atomic_inc(&mapping->i_mmap_writable);
 			flush_dcache_mmap_lock(mapping);
@@ -445,7 +445,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 				vma_interval_tree_insert_after(tmp, mpnt,
 							&mapping->i_mmap);
 			flush_dcache_mmap_unlock(mapping);
-			mutex_unlock(&mapping->i_mmap_mutex);
+			i_mmap_unlock_write(mapping);
 		}
 
 		/*
diff --git a/kernel/gcov/Kconfig b/kernel/gcov/Kconfig
index de110438efee..6ca0b99e5f0a 100644
--- a/kernel/gcov/Kconfig
+++ b/kernel/gcov/Kconfig
@@ -32,10 +32,13 @@ config GCOV_KERNEL
 	Note that the debugfs filesystem has to be mounted to access
 	profiling data.
 
+config ARCH_HAS_GCOV_PROFILE_ALL
+	def_bool n
+
 config GCOV_PROFILE_ALL
 	bool "Profile entire Kernel"
 	depends on GCOV_KERNEL
-	depends on SUPERH || S390 || X86 || PPC || MICROBLAZE || ARM || ARM64
+	depends on ARCH_HAS_GCOV_PROFILE_ALL
 	default n
 	---help---
 	This options activates profiling for the entire kernel.
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 2abf9f6e9a61..9a8a01abbaed 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -600,7 +600,7 @@ kimage_file_alloc_init(struct kimage **rimage, int kernel_fd,
 	if (!kexec_on_panic) {
 		image->swap_page = kimage_alloc_control_pages(image, 0);
 		if (!image->swap_page) {
-			pr_err(KERN_ERR "Could not allocate swap buffer\n");
+			pr_err("Could not allocate swap buffer\n");
 			goto out_free_control_pages;
 		}
 	}
diff --git a/kernel/kmod.c b/kernel/kmod.c
index 80f7a6d00519..2777f40a9c7b 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -47,13 +47,6 @@ extern int max_threads;
 
 static struct workqueue_struct *khelper_wq;
 
-/*
- * kmod_thread_locker is used for deadlock avoidance.  There is no explicit
- * locking to protect this global - it is private to the singleton khelper
- * thread and should only ever be modified by that thread.
- */
-static const struct task_struct *kmod_thread_locker;
-
 #define CAP_BSET	(void *)1
 #define CAP_PI		(void *)2
 
@@ -223,7 +216,6 @@ static void umh_complete(struct subprocess_info *sub_info)
 static int ____call_usermodehelper(void *data)
 {
 	struct subprocess_info *sub_info = data;
-	int wait = sub_info->wait & ~UMH_KILLABLE;
 	struct cred *new;
 	int retval;
 
@@ -267,20 +259,13 @@ static int ____call_usermodehelper(void *data)
 out:
 	sub_info->retval = retval;
 	/* wait_for_helper() will call umh_complete if UHM_WAIT_PROC. */
-	if (wait != UMH_WAIT_PROC)
+	if (!(sub_info->wait & UMH_WAIT_PROC))
 		umh_complete(sub_info);
 	if (!retval)
 		return 0;
 	do_exit(0);
 }
 
-static int call_helper(void *data)
-{
-	/* Worker thread started blocking khelper thread. */
-	kmod_thread_locker = current;
-	return ____call_usermodehelper(data);
-}
-
 /* Keventd can't block, but this (a child) can. */
 static int wait_for_helper(void *data)
 {
@@ -323,21 +308,14 @@ static void __call_usermodehelper(struct work_struct *work)
 {
 	struct subprocess_info *sub_info =
 		container_of(work, struct subprocess_info, work);
-	int wait = sub_info->wait & ~UMH_KILLABLE;
 	pid_t pid;
 
-	/* CLONE_VFORK: wait until the usermode helper has execve'd
-	 * successfully We need the data structures to stay around
-	 * until that is done.  */
-	if (wait == UMH_WAIT_PROC)
+	if (sub_info->wait & UMH_WAIT_PROC)
 		pid = kernel_thread(wait_for_helper, sub_info,
 				    CLONE_FS | CLONE_FILES | SIGCHLD);
-	else {
-		pid = kernel_thread(call_helper, sub_info,
-				    CLONE_VFORK | SIGCHLD);
-		/* Worker thread stopped blocking khelper thread. */
-		kmod_thread_locker = NULL;
-	}
+	else
+		pid = kernel_thread(____call_usermodehelper, sub_info,
+				    SIGCHLD);
 
 	if (pid < 0) {
 		sub_info->retval = pid;
@@ -571,17 +549,6 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait)
 		goto out;
 	}
 	/*
-	 * Worker thread must not wait for khelper thread at below
-	 * wait_for_completion() if the thread was created with CLONE_VFORK
-	 * flag, for khelper thread is already waiting for the thread at
-	 * wait_for_completion() in do_fork().
-	 */
-	if (wait != UMH_NO_WAIT && current == kmod_thread_locker) {
-		retval = -EBUSY;
-		goto out;
-	}
-
-	/*
 	 * Set the completion pointer only if there is a waiter.
 	 * This makes it possible to use umh_complete to free
 	 * the data structure in case of UMH_NO_WAIT.
diff --git a/kernel/panic.c b/kernel/panic.c
index d09dc5c32c67..4d8d6f906dec 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -33,6 +33,7 @@ static int pause_on_oops;
 static int pause_on_oops_flag;
 static DEFINE_SPINLOCK(pause_on_oops_lock);
 static bool crash_kexec_post_notifiers;
+int panic_on_warn __read_mostly;
 
 int panic_timeout = CONFIG_PANIC_TIMEOUT;
 EXPORT_SYMBOL_GPL(panic_timeout);
@@ -244,6 +245,7 @@ static const struct tnt tnts[] = {
  *  'I' - Working around severe firmware bug.
  *  'O' - Out-of-tree module has been loaded.
  *  'E' - Unsigned module has been loaded.
+ *  'L' - A soft lockup has previously occurred.
  *
  *	The string is overwritten by the next call to print_tainted().
  */
@@ -427,6 +429,17 @@ static void warn_slowpath_common(const char *file, int line, void *caller,
 	if (args)
 		vprintk(args->fmt, args->args);
 
+	if (panic_on_warn) {
+		/*
+		 * This thread may hit another WARN() in the panic path.
+		 * Resetting this prevents additional WARN() from panicking the
+		 * system on this thread.  Other threads are blocked by the
+		 * panic_mutex in panic().
+		 */
+		panic_on_warn = 0;
+		panic("panic_on_warn set ...\n");
+	}
+
 	print_modules();
 	dump_stack();
 	print_oops_end_marker();
@@ -484,6 +497,7 @@ EXPORT_SYMBOL(__stack_chk_fail);
 
 core_param(panic, panic_timeout, int, 0644);
 core_param(pause_on_oops, pause_on_oops, int, 0644);
+core_param(panic_on_warn, panic_on_warn, int, 0644);
 
 static int __init setup_crash_kexec_post_notifiers(char *s)
 {
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index c8755e7e1dba..e7489716ad2c 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -62,9 +62,6 @@ int console_printk[4] = {
 	CONSOLE_LOGLEVEL_DEFAULT,	/* default_console_loglevel */
 };
 
-/* Deferred messaged from sched code are marked by this special level */
-#define SCHED_MESSAGE_LOGLEVEL -2
-
 /*
  * Low level drivers may need that to know if they can schedule in
  * their unblank() callback or not. So let's export it.
@@ -1259,7 +1256,7 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
 int do_syslog(int type, char __user *buf, int len, bool from_file)
 {
 	bool clear = false;
-	static int saved_console_loglevel = -1;
+	static int saved_console_loglevel = LOGLEVEL_DEFAULT;
 	int error;
 
 	error = check_syslog_permissions(type, from_file);
@@ -1316,15 +1313,15 @@ int do_syslog(int type, char __user *buf, int len, bool from_file)
 		break;
 	/* Disable logging to console */
 	case SYSLOG_ACTION_CONSOLE_OFF:
-		if (saved_console_loglevel == -1)
+		if (saved_console_loglevel == LOGLEVEL_DEFAULT)
 			saved_console_loglevel = console_loglevel;
 		console_loglevel = minimum_console_loglevel;
 		break;
 	/* Enable logging to console */
 	case SYSLOG_ACTION_CONSOLE_ON:
-		if (saved_console_loglevel != -1) {
+		if (saved_console_loglevel != LOGLEVEL_DEFAULT) {
 			console_loglevel = saved_console_loglevel;
-			saved_console_loglevel = -1;
+			saved_console_loglevel = LOGLEVEL_DEFAULT;
 		}
 		break;
 	/* Set level of messages printed to console */
@@ -1336,7 +1333,7 @@ int do_syslog(int type, char __user *buf, int len, bool from_file)
 			len = minimum_console_loglevel;
 		console_loglevel = len;
 		/* Implicitly re-enable logging to console */
-		saved_console_loglevel = -1;
+		saved_console_loglevel = LOGLEVEL_DEFAULT;
 		error = 0;
 		break;
 	/* Number of chars in the log buffer */
@@ -1629,8 +1626,8 @@ asmlinkage int vprintk_emit(int facility, int level,
 	/* cpu currently holding logbuf_lock in this function */
 	static volatile unsigned int logbuf_cpu = UINT_MAX;
 
-	if (level == SCHED_MESSAGE_LOGLEVEL) {
-		level = -1;
+	if (level == LOGLEVEL_SCHED) {
+		level = LOGLEVEL_DEFAULT;
 		in_sched = true;
 	}
 
@@ -1695,8 +1692,9 @@ asmlinkage int vprintk_emit(int facility, int level,
 			const char *end_of_header = printk_skip_level(text);
 			switch (kern_level) {
 			case '0' ... '7':
-				if (level == -1)
+				if (level == LOGLEVEL_DEFAULT)
 					level = kern_level - '0';
+				/* fallthrough */
 			case 'd':	/* KERN_DEFAULT */
 				lflags |= LOG_PREFIX;
 			}
@@ -1710,7 +1708,7 @@ asmlinkage int vprintk_emit(int facility, int level,
 		}
 	}
 
-	if (level == -1)
+	if (level == LOGLEVEL_DEFAULT)
 		level = default_message_loglevel;
 
 	if (dict)
@@ -1788,7 +1786,7 @@ EXPORT_SYMBOL(vprintk_emit);
 
 asmlinkage int vprintk(const char *fmt, va_list args)
 {
-	return vprintk_emit(0, -1, NULL, 0, fmt, args);
+	return vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, 0, fmt, args);
 }
 EXPORT_SYMBOL(vprintk);
 
@@ -1842,7 +1840,7 @@ asmlinkage __visible int printk(const char *fmt, ...)
 	}
 #endif
 	va_start(args, fmt);
-	r = vprintk_emit(0, -1, NULL, 0, fmt, args);
+	r = vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, 0, fmt, args);
 	va_end(args);
 
 	return r;
@@ -1881,23 +1879,20 @@ static size_t cont_print_text(char *text, size_t size) { return 0; }
 #ifdef CONFIG_EARLY_PRINTK
 struct console *early_console;
 
-void early_vprintk(const char *fmt, va_list ap)
-{
-	if (early_console) {
-		char buf[512];
-		int n = vscnprintf(buf, sizeof(buf), fmt, ap);
-
-		early_console->write(early_console, buf, n);
-	}
-}
-
 asmlinkage __visible void early_printk(const char *fmt, ...)
 {
 	va_list ap;
+	char buf[512];
+	int n;
+
+	if (!early_console)
+		return;
 
 	va_start(ap, fmt);
-	early_vprintk(fmt, ap);
+	n = vscnprintf(buf, sizeof(buf), fmt, ap);
 	va_end(ap);
+
+	early_console->write(early_console, buf, n);
 }
 #endif
 
@@ -2634,7 +2629,7 @@ int printk_deferred(const char *fmt, ...)
 
 	preempt_disable();
 	va_start(args, fmt);
-	r = vprintk_emit(0, SCHED_MESSAGE_LOGLEVEL, NULL, 0, fmt, args);
+	r = vprintk_emit(0, LOGLEVEL_SCHED, NULL, 0, fmt, args);
 	va_end(args);
 
 	__this_cpu_or(printk_pending, PRINTK_PENDING_OUTPUT);
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 54e75226c2c4..1eb9d90c3af9 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -485,36 +485,19 @@ static int ptrace_detach(struct task_struct *child, unsigned int data)
 
 /*
  * Detach all tasks we were using ptrace on. Called with tasklist held
- * for writing, and returns with it held too. But note it can release
- * and reacquire the lock.
+ * for writing.
  */
-void exit_ptrace(struct task_struct *tracer)
-	__releases(&tasklist_lock)
-	__acquires(&tasklist_lock)
+void exit_ptrace(struct task_struct *tracer, struct list_head *dead)
 {
 	struct task_struct *p, *n;
-	LIST_HEAD(ptrace_dead);
-
-	if (likely(list_empty(&tracer->ptraced)))
-		return;
 
 	list_for_each_entry_safe(p, n, &tracer->ptraced, ptrace_entry) {
 		if (unlikely(p->ptrace & PT_EXITKILL))
 			send_sig_info(SIGKILL, SEND_SIG_FORCED, p);
 
 		if (__ptrace_detach(tracer, p))
-			list_add(&p->ptrace_entry, &ptrace_dead);
-	}
-
-	write_unlock_irq(&tasklist_lock);
-	BUG_ON(!list_empty(&tracer->ptraced));
-
-	list_for_each_entry_safe(p, n, &ptrace_dead, ptrace_entry) {
-		list_del_init(&p->ptrace_entry);
-		release_task(p);
+			list_add(&p->ptrace_entry, dead);
 	}
-
-	write_lock_irq(&tasklist_lock);
 }
 
 int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len)
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
deleted file mode 100644
index e791130f85a7..000000000000
--- a/kernel/res_counter.c
+++ /dev/null
@@ -1,211 +0,0 @@
-/*
- * resource cgroups
- *
- * Copyright 2007 OpenVZ SWsoft Inc
- *
- * Author: Pavel Emelianov <xemul@openvz.org>
- *
- */
-
-#include <linux/types.h>
-#include <linux/parser.h>
-#include <linux/fs.h>
-#include <linux/res_counter.h>
-#include <linux/uaccess.h>
-#include <linux/mm.h>
-
-void res_counter_init(struct res_counter *counter, struct res_counter *parent)
-{
-	spin_lock_init(&counter->lock);
-	counter->limit = RES_COUNTER_MAX;
-	counter->soft_limit = RES_COUNTER_MAX;
-	counter->parent = parent;
-}
-
-static u64 res_counter_uncharge_locked(struct res_counter *counter,
-				       unsigned long val)
-{
-	if (WARN_ON(counter->usage < val))
-		val = counter->usage;
-
-	counter->usage -= val;
-	return counter->usage;
-}
-
-static int res_counter_charge_locked(struct res_counter *counter,
-				     unsigned long val, bool force)
-{
-	int ret = 0;
-
-	if (counter->usage + val > counter->limit) {
-		counter->failcnt++;
-		ret = -ENOMEM;
-		if (!force)
-			return ret;
-	}
-
-	counter->usage += val;
-	if (counter->usage > counter->max_usage)
-		counter->max_usage = counter->usage;
-	return ret;
-}
-
-static int __res_counter_charge(struct res_counter *counter, unsigned long val,
-				struct res_counter **limit_fail_at, bool force)
-{
-	int ret, r;
-	unsigned long flags;
-	struct res_counter *c, *u;
-
-	r = ret = 0;
-	*limit_fail_at = NULL;
-	local_irq_save(flags);
-	for (c = counter; c != NULL; c = c->parent) {
-		spin_lock(&c->lock);
-		r = res_counter_charge_locked(c, val, force);
-		spin_unlock(&c->lock);
-		if (r < 0 && !ret) {
-			ret = r;
-			*limit_fail_at = c;
-			if (!force)
-				break;
-		}
-	}
-
-	if (ret < 0 && !force) {
-		for (u = counter; u != c; u = u->parent) {
-			spin_lock(&u->lock);
-			res_counter_uncharge_locked(u, val);
-			spin_unlock(&u->lock);
-		}
-	}
-	local_irq_restore(flags);
-
-	return ret;
-}
-
-int res_counter_charge(struct res_counter *counter, unsigned long val,
-			struct res_counter **limit_fail_at)
-{
-	return __res_counter_charge(counter, val, limit_fail_at, false);
-}
-
-int res_counter_charge_nofail(struct res_counter *counter, unsigned long val,
-			      struct res_counter **limit_fail_at)
-{
-	return __res_counter_charge(counter, val, limit_fail_at, true);
-}
-
-u64 res_counter_uncharge_until(struct res_counter *counter,
-			       struct res_counter *top,
-			       unsigned long val)
-{
-	unsigned long flags;
-	struct res_counter *c;
-	u64 ret = 0;
-
-	local_irq_save(flags);
-	for (c = counter; c != top; c = c->parent) {
-		u64 r;
-		spin_lock(&c->lock);
-		r = res_counter_uncharge_locked(c, val);
-		if (c == counter)
-			ret = r;
-		spin_unlock(&c->lock);
-	}
-	local_irq_restore(flags);
-	return ret;
-}
-
-u64 res_counter_uncharge(struct res_counter *counter, unsigned long val)
-{
-	return res_counter_uncharge_until(counter, NULL, val);
-}
-
-static inline unsigned long long *
-res_counter_member(struct res_counter *counter, int member)
-{
-	switch (member) {
-	case RES_USAGE:
-		return &counter->usage;
-	case RES_MAX_USAGE:
-		return &counter->max_usage;
-	case RES_LIMIT:
-		return &counter->limit;
-	case RES_FAILCNT:
-		return &counter->failcnt;
-	case RES_SOFT_LIMIT:
-		return &counter->soft_limit;
-	};
-
-	BUG();
-	return NULL;
-}
-
-ssize_t res_counter_read(struct res_counter *counter, int member,
-		const char __user *userbuf, size_t nbytes, loff_t *pos,
-		int (*read_strategy)(unsigned long long val, char *st_buf))
-{
-	unsigned long long *val;
-	char buf[64], *s;
-
-	s = buf;
-	val = res_counter_member(counter, member);
-	if (read_strategy)
-		s += read_strategy(*val, s);
-	else
-		s += sprintf(s, "%llu\n", *val);
-	return simple_read_from_buffer((void __user *)userbuf, nbytes,
-			pos, buf, s - buf);
-}
-
-#if BITS_PER_LONG == 32
-u64 res_counter_read_u64(struct res_counter *counter, int member)
-{
-	unsigned long flags;
-	u64 ret;
-
-	spin_lock_irqsave(&counter->lock, flags);
-	ret = *res_counter_member(counter, member);
-	spin_unlock_irqrestore(&counter->lock, flags);
-
-	return ret;
-}
-#else
-u64 res_counter_read_u64(struct res_counter *counter, int member)
-{
-	return *res_counter_member(counter, member);
-}
-#endif
-
-int res_counter_memparse_write_strategy(const char *buf,
-					unsigned long long *resp)
-{
-	char *end;
-	unsigned long long res;
-
-	/* return RES_COUNTER_MAX(unlimited) if "-1" is specified */
-	if (*buf == '-') {
-		int rc = kstrtoull(buf + 1, 10, &res);
-
-		if (rc)
-			return rc;
-		if (res != 1)
-			return -EINVAL;
-		*resp = RES_COUNTER_MAX;
-		return 0;
-	}
-
-	res = memparse(buf, &end);
-	if (*end != '\0')
-		return -EINVAL;
-
-	if (PAGE_ALIGN(res) >= res)
-		res = PAGE_ALIGN(res);
-	else
-		res = RES_COUNTER_MAX;
-
-	*resp = res;
-
-	return 0;
-}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f44f108c930e..02084b56cbed 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4547,8 +4547,10 @@ void sched_show_task(struct task_struct *p)
 #ifdef CONFIG_DEBUG_STACK_USAGE
 	free = stack_not_used(p);
 #endif
+	ppid = 0;
 	rcu_read_lock();
-	ppid = task_pid_nr(rcu_dereference(p->real_parent));
+	if (pid_alive(p))
+		ppid = task_pid_nr(rcu_dereference(p->real_parent));
 	rcu_read_unlock();
 	printk(KERN_CONT "%5lu %5d %6d 0x%08lx\n", free,
 		task_pid_nr(p), ppid,
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index d2f5b00fed46..f68a74cd761d 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -235,3 +235,6 @@ cond_syscall(sys_seccomp);
 
 /* access BPF programs and maps */
 cond_syscall(sys_bpf);
+
+/* execveat */
+cond_syscall(sys_execveat);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 15f2511a1b7c..f57c5ae6de18 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1104,6 +1104,15 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 #endif
+	{
+		.procname	= "panic_on_warn",
+		.data		= &panic_on_warn,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
 	{ }
 };
 
@@ -1740,7 +1749,11 @@ static int _proc_do_string(char *data, int maxlen, int write,
 		while ((p - buffer) < *lenp && len < maxlen - 1) {
 			if (get_user(c, p++))
 				return -EFAULT;
-			if (c == 0 || c == '\n')
+			/*
+			 * \r terminates input to partially prevent attackers
+			 * from hiding info from sysadmins who use cat
+			 */
+			if (c == 0 || c == '\n' || c == '\r')
 				break;
 			data[len++] = c;
 		}
diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c
index 9a4f750a2963..7e7746a42a62 100644
--- a/kernel/sysctl_binary.c
+++ b/kernel/sysctl_binary.c
@@ -137,6 +137,7 @@ static const struct bin_table bin_kern_table[] = {
 	{ CTL_INT,	KERN_COMPAT_LOG,		"compat-log" },
 	{ CTL_INT,	KERN_MAX_LOCK_DEPTH,		"max_lock_depth" },
 	{ CTL_INT,	KERN_PANIC_ON_NMI,		"panic_on_unrecovered_nmi" },
+	{ CTL_INT,	KERN_PANIC_ON_WARN,		"panic_on_warn" },
 	{}
 };
 
diff --git a/lib/Kconfig b/lib/Kconfig
index b8c97f05140d..d625f6017ae6 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -186,6 +186,13 @@ config CRC8
 	  when they need to do cyclic redundancy check according CRC8
 	  algorithm. Module will be called crc8.
 
+config CRC64_ECMA
+	tristate "CRC64 ECMA function"
+	help
+	  This option provides CRC64 ECMA function. Drivers may select this
+	  when they need to do cyclic redundancy check according to the CRC64
+	  ECMA algorithm.
+
 config HALFMD4
 	bool
 
diff --git a/lib/Makefile b/lib/Makefile
index 336bb269ceb8..6cb07ec3eacd 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -75,6 +75,7 @@ obj-$(CONFIG_CRC32)	+= crc32.o
 obj-$(CONFIG_CRC7)	+= crc7.o
 obj-$(CONFIG_LIBCRC32C)	+= libcrc32c.o
 obj-$(CONFIG_CRC8)	+= crc8.o
+obj-$(CONFIG_CRC64_ECMA)	+= crc64_ecma.o
 obj-$(CONFIG_GENERIC_ALLOCATOR) += genalloc.o
 
 obj-$(CONFIG_ZLIB_INFLATE) += zlib_inflate/
diff --git a/lib/audit.c b/lib/audit.c
index 1d726a22565b..b8fb5ee81e26 100644
--- a/lib/audit.c
+++ b/lib/audit.c
@@ -54,6 +54,9 @@ int audit_classify_syscall(int abi, unsigned syscall)
 	case __NR_socketcall:
 		return 4;
 #endif
+#ifdef __NR_execveat
+	case __NR_execveat:
+#endif
 	case __NR_execve:
 		return 5;
 	default:
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 5bc7a1128fe8..324ea9eab8c1 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -328,30 +328,32 @@ void bitmap_clear(unsigned long *map, unsigned int start, int len)
 }
 EXPORT_SYMBOL(bitmap_clear);
 
-/*
- * bitmap_find_next_zero_area - find a contiguous aligned zero area
+/**
+ * bitmap_find_next_zero_area_off - find a contiguous aligned zero area
  * @map: The address to base the search on
  * @size: The bitmap size in bits
  * @start: The bitnumber to start searching at
  * @nr: The number of zeroed bits we're looking for
  * @align_mask: Alignment mask for zero area
+ * @align_offset: Alignment offset for zero area.
  *
  * The @align_mask should be one less than a power of 2; the effect is that
- * the bit offset of all zero areas this function finds is multiples of that
- * power of 2. A @align_mask of 0 means no alignment is required.
+ * the bit offset of all zero areas this function finds plus @align_offset
+ * is multiple of that power of 2.
  */
-unsigned long bitmap_find_next_zero_area(unsigned long *map,
-					 unsigned long size,
-					 unsigned long start,
-					 unsigned int nr,
-					 unsigned long align_mask)
+unsigned long bitmap_find_next_zero_area_off(unsigned long *map,
+					     unsigned long size,
+					     unsigned long start,
+					     unsigned int nr,
+					     unsigned long align_mask,
+					     unsigned long align_offset)
 {
 	unsigned long index, end, i;
 again:
 	index = find_next_zero_bit(map, size, start);
 
 	/* Align allocation */
-	index = __ALIGN_MASK(index, align_mask);
+	index = __ALIGN_MASK(index + align_offset, align_mask) - align_offset;
 
 	end = index + nr;
 	if (end > size)
@@ -363,7 +365,7 @@ again:
 	}
 	return index;
 }
-EXPORT_SYMBOL(bitmap_find_next_zero_area);
+EXPORT_SYMBOL(bitmap_find_next_zero_area_off);
 
 /*
  * Bitmap printing & parsing functions: first version by Nadia Yvette Chambers,
diff --git a/lib/crc64_ecma.c b/lib/crc64_ecma.c
new file mode 100644
index 000000000000..41629ea5a60c
--- /dev/null
+++ b/lib/crc64_ecma.c
@@ -0,0 +1,341 @@
+/*
+ * Copyright 2013 Freescale Semiconductor Inc.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/module.h>
+#include <linux/crc64_ecma.h>
+
+
+#define CRC64_BYTE_MASK			0xFF
+#define CRC64_TABLE_SIZE		256
+
+
+struct crc64_table {
+	u64 seed;
+	u64 table[CRC64_TABLE_SIZE];
+};
+
+
+static struct crc64_table CRC64_ECMA_182 = {
+	CRC64_DEFAULT_INITVAL,
+	{
+		0x0000000000000000ULL,
+		0xb32e4cbe03a75f6fULL,
+		0xf4843657a840a05bULL,
+		0x47aa7ae9abe7ff34ULL,
+		0x7bd0c384ff8f5e33ULL,
+		0xc8fe8f3afc28015cULL,
+		0x8f54f5d357cffe68ULL,
+		0x3c7ab96d5468a107ULL,
+		0xf7a18709ff1ebc66ULL,
+		0x448fcbb7fcb9e309ULL,
+		0x0325b15e575e1c3dULL,
+		0xb00bfde054f94352ULL,
+		0x8c71448d0091e255ULL,
+		0x3f5f08330336bd3aULL,
+		0x78f572daa8d1420eULL,
+		0xcbdb3e64ab761d61ULL,
+		0x7d9ba13851336649ULL,
+		0xceb5ed8652943926ULL,
+		0x891f976ff973c612ULL,
+		0x3a31dbd1fad4997dULL,
+		0x064b62bcaebc387aULL,
+		0xb5652e02ad1b6715ULL,
+		0xf2cf54eb06fc9821ULL,
+		0x41e11855055bc74eULL,
+		0x8a3a2631ae2dda2fULL,
+		0x39146a8fad8a8540ULL,
+		0x7ebe1066066d7a74ULL,
+		0xcd905cd805ca251bULL,
+		0xf1eae5b551a2841cULL,
+		0x42c4a90b5205db73ULL,
+		0x056ed3e2f9e22447ULL,
+		0xb6409f5cfa457b28ULL,
+		0xfb374270a266cc92ULL,
+		0x48190ecea1c193fdULL,
+		0x0fb374270a266cc9ULL,
+		0xbc9d3899098133a6ULL,
+		0x80e781f45de992a1ULL,
+		0x33c9cd4a5e4ecdceULL,
+		0x7463b7a3f5a932faULL,
+		0xc74dfb1df60e6d95ULL,
+		0x0c96c5795d7870f4ULL,
+		0xbfb889c75edf2f9bULL,
+		0xf812f32ef538d0afULL,
+		0x4b3cbf90f69f8fc0ULL,
+		0x774606fda2f72ec7ULL,
+		0xc4684a43a15071a8ULL,
+		0x83c230aa0ab78e9cULL,
+		0x30ec7c140910d1f3ULL,
+		0x86ace348f355aadbULL,
+		0x3582aff6f0f2f5b4ULL,
+		0x7228d51f5b150a80ULL,
+		0xc10699a158b255efULL,
+		0xfd7c20cc0cdaf4e8ULL,
+		0x4e526c720f7dab87ULL,
+		0x09f8169ba49a54b3ULL,
+		0xbad65a25a73d0bdcULL,
+		0x710d64410c4b16bdULL,
+		0xc22328ff0fec49d2ULL,
+		0x85895216a40bb6e6ULL,
+		0x36a71ea8a7ace989ULL,
+		0x0adda7c5f3c4488eULL,
+		0xb9f3eb7bf06317e1ULL,
+		0xfe5991925b84e8d5ULL,
+		0x4d77dd2c5823b7baULL,
+		0x64b62bcaebc387a1ULL,
+		0xd7986774e864d8ceULL,
+		0x90321d9d438327faULL,
+		0x231c512340247895ULL,
+		0x1f66e84e144cd992ULL,
+		0xac48a4f017eb86fdULL,
+		0xebe2de19bc0c79c9ULL,
+		0x58cc92a7bfab26a6ULL,
+		0x9317acc314dd3bc7ULL,
+		0x2039e07d177a64a8ULL,
+		0x67939a94bc9d9b9cULL,
+		0xd4bdd62abf3ac4f3ULL,
+		0xe8c76f47eb5265f4ULL,
+		0x5be923f9e8f53a9bULL,
+		0x1c4359104312c5afULL,
+		0xaf6d15ae40b59ac0ULL,
+		0x192d8af2baf0e1e8ULL,
+		0xaa03c64cb957be87ULL,
+		0xeda9bca512b041b3ULL,
+		0x5e87f01b11171edcULL,
+		0x62fd4976457fbfdbULL,
+		0xd1d305c846d8e0b4ULL,
+		0x96797f21ed3f1f80ULL,
+		0x2557339fee9840efULL,
+		0xee8c0dfb45ee5d8eULL,
+		0x5da24145464902e1ULL,
+		0x1a083bacedaefdd5ULL,
+		0xa9267712ee09a2baULL,
+		0x955cce7fba6103bdULL,
+		0x267282c1b9c65cd2ULL,
+		0x61d8f8281221a3e6ULL,
+		0xd2f6b4961186fc89ULL,
+		0x9f8169ba49a54b33ULL,
+		0x2caf25044a02145cULL,
+		0x6b055fede1e5eb68ULL,
+		0xd82b1353e242b407ULL,
+		0xe451aa3eb62a1500ULL,
+		0x577fe680b58d4a6fULL,
+		0x10d59c691e6ab55bULL,
+		0xa3fbd0d71dcdea34ULL,
+		0x6820eeb3b6bbf755ULL,
+		0xdb0ea20db51ca83aULL,
+		0x9ca4d8e41efb570eULL,
+		0x2f8a945a1d5c0861ULL,
+		0x13f02d374934a966ULL,
+		0xa0de61894a93f609ULL,
+		0xe7741b60e174093dULL,
+		0x545a57dee2d35652ULL,
+		0xe21ac88218962d7aULL,
+		0x5134843c1b317215ULL,
+		0x169efed5b0d68d21ULL,
+		0xa5b0b26bb371d24eULL,
+		0x99ca0b06e7197349ULL,
+		0x2ae447b8e4be2c26ULL,
+		0x6d4e3d514f59d312ULL,
+		0xde6071ef4cfe8c7dULL,
+		0x15bb4f8be788911cULL,
+		0xa6950335e42fce73ULL,
+		0xe13f79dc4fc83147ULL,
+		0x521135624c6f6e28ULL,
+		0x6e6b8c0f1807cf2fULL,
+		0xdd45c0b11ba09040ULL,
+		0x9aefba58b0476f74ULL,
+		0x29c1f6e6b3e0301bULL,
+		0xc96c5795d7870f42ULL,
+		0x7a421b2bd420502dULL,
+		0x3de861c27fc7af19ULL,
+		0x8ec62d7c7c60f076ULL,
+		0xb2bc941128085171ULL,
+		0x0192d8af2baf0e1eULL,
+		0x4638a2468048f12aULL,
+		0xf516eef883efae45ULL,
+		0x3ecdd09c2899b324ULL,
+		0x8de39c222b3eec4bULL,
+		0xca49e6cb80d9137fULL,
+		0x7967aa75837e4c10ULL,
+		0x451d1318d716ed17ULL,
+		0xf6335fa6d4b1b278ULL,
+		0xb199254f7f564d4cULL,
+		0x02b769f17cf11223ULL,
+		0xb4f7f6ad86b4690bULL,
+		0x07d9ba1385133664ULL,
+		0x4073c0fa2ef4c950ULL,
+		0xf35d8c442d53963fULL,
+		0xcf273529793b3738ULL,
+		0x7c0979977a9c6857ULL,
+		0x3ba3037ed17b9763ULL,
+		0x888d4fc0d2dcc80cULL,
+		0x435671a479aad56dULL,
+		0xf0783d1a7a0d8a02ULL,
+		0xb7d247f3d1ea7536ULL,
+		0x04fc0b4dd24d2a59ULL,
+		0x3886b22086258b5eULL,
+		0x8ba8fe9e8582d431ULL,
+		0xcc0284772e652b05ULL,
+		0x7f2cc8c92dc2746aULL,
+		0x325b15e575e1c3d0ULL,
+		0x8175595b76469cbfULL,
+		0xc6df23b2dda1638bULL,
+		0x75f16f0cde063ce4ULL,
+		0x498bd6618a6e9de3ULL,
+		0xfaa59adf89c9c28cULL,
+		0xbd0fe036222e3db8ULL,
+		0x0e21ac88218962d7ULL,
+		0xc5fa92ec8aff7fb6ULL,
+		0x76d4de52895820d9ULL,
+		0x317ea4bb22bfdfedULL,
+		0x8250e80521188082ULL,
+		0xbe2a516875702185ULL,
+		0x0d041dd676d77eeaULL,
+		0x4aae673fdd3081deULL,
+		0xf9802b81de97deb1ULL,
+		0x4fc0b4dd24d2a599ULL,
+		0xfceef8632775faf6ULL,
+		0xbb44828a8c9205c2ULL,
+		0x086ace348f355aadULL,
+		0x34107759db5dfbaaULL,
+		0x873e3be7d8faa4c5ULL,
+		0xc094410e731d5bf1ULL,
+		0x73ba0db070ba049eULL,
+		0xb86133d4dbcc19ffULL,
+		0x0b4f7f6ad86b4690ULL,
+		0x4ce50583738cb9a4ULL,
+		0xffcb493d702be6cbULL,
+		0xc3b1f050244347ccULL,
+		0x709fbcee27e418a3ULL,
+		0x3735c6078c03e797ULL,
+		0x841b8ab98fa4b8f8ULL,
+		0xadda7c5f3c4488e3ULL,
+		0x1ef430e13fe3d78cULL,
+		0x595e4a08940428b8ULL,
+		0xea7006b697a377d7ULL,
+		0xd60abfdbc3cbd6d0ULL,
+		0x6524f365c06c89bfULL,
+		0x228e898c6b8b768bULL,
+		0x91a0c532682c29e4ULL,
+		0x5a7bfb56c35a3485ULL,
+		0xe955b7e8c0fd6beaULL,
+		0xaeffcd016b1a94deULL,
+		0x1dd181bf68bdcbb1ULL,
+		0x21ab38d23cd56ab6ULL,
+		0x9285746c3f7235d9ULL,
+		0xd52f0e859495caedULL,
+		0x6601423b97329582ULL,
+		0xd041dd676d77eeaaULL,
+		0x636f91d96ed0b1c5ULL,
+		0x24c5eb30c5374ef1ULL,
+		0x97eba78ec690119eULL,
+		0xab911ee392f8b099ULL,
+		0x18bf525d915feff6ULL,
+		0x5f1528b43ab810c2ULL,
+		0xec3b640a391f4fadULL,
+		0x27e05a6e926952ccULL,
+		0x94ce16d091ce0da3ULL,
+		0xd3646c393a29f297ULL,
+		0x604a2087398eadf8ULL,
+		0x5c3099ea6de60cffULL,
+		0xef1ed5546e415390ULL,
+		0xa8b4afbdc5a6aca4ULL,
+		0x1b9ae303c601f3cbULL,
+		0x56ed3e2f9e224471ULL,
+		0xe5c372919d851b1eULL,
+		0xa26908783662e42aULL,
+		0x114744c635c5bb45ULL,
+		0x2d3dfdab61ad1a42ULL,
+		0x9e13b115620a452dULL,
+		0xd9b9cbfcc9edba19ULL,
+		0x6a978742ca4ae576ULL,
+		0xa14cb926613cf817ULL,
+		0x1262f598629ba778ULL,
+		0x55c88f71c97c584cULL,
+		0xe6e6c3cfcadb0723ULL,
+		0xda9c7aa29eb3a624ULL,
+		0x69b2361c9d14f94bULL,
+		0x2e184cf536f3067fULL,
+		0x9d36004b35545910ULL,
+		0x2b769f17cf112238ULL,
+		0x9858d3a9ccb67d57ULL,
+		0xdff2a94067518263ULL,
+		0x6cdce5fe64f6dd0cULL,
+		0x50a65c93309e7c0bULL,
+		0xe388102d33392364ULL,
+		0xa4226ac498dedc50ULL,
+		0x170c267a9b79833fULL,
+		0xdcd7181e300f9e5eULL,
+		0x6ff954a033a8c131ULL,
+		0x28532e49984f3e05ULL,
+		0x9b7d62f79be8616aULL,
+		0xa707db9acf80c06dULL,
+		0x14299724cc279f02ULL,
+		0x5383edcd67c06036ULL,
+		0xe0ada17364673f59ULL
+	}
+};
+
+
+/*
+ * crc64_ecma_seed - Initializes the CRC64 ECMA seed.
+ */
+u64 crc64_ecma_seed(void)
+{
+	return CRC64_ECMA_182.seed;
+}
+EXPORT_SYMBOL(crc64_ecma_seed);
+
+/*
+ * crc64_ecma - Computes the 64 bit ECMA CRC.
+ *
+ * pdata: pointer to the data to compute checksum for.
+ * nbytes: number of bytes in data buffer.
+ * seed: CRC seed.
+ */
+u64 crc64_ecma(u8 const *pdata, u32 nbytes, u64 seed)
+{
+	unsigned int i;
+	u64 crc = seed;
+
+	for (i = 0; i < nbytes; i++)
+		crc = CRC64_ECMA_182.table[(crc ^ pdata[i]) & CRC64_BYTE_MASK] ^
+			(crc >> 8);
+
+	return crc;
+}
+EXPORT_SYMBOL(crc64_ecma);
+
+MODULE_DESCRIPTION("CRC64 ECMA function");
+MODULE_AUTHOR("Freescale Semiconductor Inc.");
+MODULE_LICENSE("GPL");
diff --git a/lib/decompress.c b/lib/decompress.c
index 37f3c786348f..528ff932d8e4 100644
--- a/lib/decompress.c
+++ b/lib/decompress.c
@@ -44,8 +44,8 @@ struct compress_format {
 };
 
 static const struct compress_format compressed_formats[] __initconst = {
-	{ {037, 0213}, "gzip", gunzip },
-	{ {037, 0236}, "gzip", gunzip },
+	{ {0x1f, 0x8b}, "gzip", gunzip },
+	{ {0x1f, 0x9e}, "gzip", gunzip },
 	{ {0x42, 0x5a}, "bzip2", bunzip2 },
 	{ {0x5d, 0x00}, "lzma", unlzma },
 	{ {0xfd, 0x37}, "xz", unxz },
diff --git a/lib/decompress_bunzip2.c b/lib/decompress_bunzip2.c
index 8290e0bef7ea..6dd0335ea61b 100644
--- a/lib/decompress_bunzip2.c
+++ b/lib/decompress_bunzip2.c
@@ -184,7 +184,7 @@ static int INIT get_next_block(struct bunzip_data *bd)
 	if (get_bits(bd, 1))
 		return RETVAL_OBSOLETE_INPUT;
 	origPtr = get_bits(bd, 24);
-	if (origPtr > dbufSize)
+	if (origPtr >= dbufSize)
 		return RETVAL_DATA_ERROR;
 	/* mapping table: if some byte values are never used (encoding things
 	   like ascii text), the compression code removes the gaps to have fewer
diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c
index dfba05521748..527799d44476 100644
--- a/lib/dynamic_debug.c
+++ b/lib/dynamic_debug.c
@@ -576,7 +576,7 @@ void __dynamic_dev_dbg(struct _ddebug *descriptor,
 	} else {
 		char buf[PREFIX_SIZE];
 
-		dev_printk_emit(7, dev, "%s%s %s: %pV",
+		dev_printk_emit(LOGLEVEL_DEBUG, dev, "%s%s %s: %pV",
 				dynamic_emit_prefix(descriptor, buf),
 				dev_driver_string(dev), dev_name(dev),
 				&vaf);
@@ -605,7 +605,7 @@ void __dynamic_netdev_dbg(struct _ddebug *descriptor,
 	if (dev && dev->dev.parent) {
 		char buf[PREFIX_SIZE];
 
-		dev_printk_emit(7, dev->dev.parent,
+		dev_printk_emit(LOGLEVEL_DEBUG, dev->dev.parent,
 				"%s%s %s %s%s: %pV",
 				dynamic_emit_prefix(descriptor, buf),
 				dev_driver_string(dev->dev.parent),
diff --git a/lib/fault-inject.c b/lib/fault-inject.c
index d7d501ea856d..f1cdeb024d17 100644
--- a/lib/fault-inject.c
+++ b/lib/fault-inject.c
@@ -40,10 +40,16 @@ EXPORT_SYMBOL_GPL(setup_fault_attr);
 
 static void fail_dump(struct fault_attr *attr)
 {
-	if (attr->verbose > 0)
-		printk(KERN_NOTICE "FAULT_INJECTION: forcing a failure\n");
-	if (attr->verbose > 1)
-		dump_stack();
+	if (attr->verbose > 0 && __ratelimit(&attr->ratelimit_state)) {
+		printk(KERN_NOTICE "FAULT_INJECTION: forcing a failure.\n"
+		       "name %pd, interval %lu, probability %lu, "
+		       "space %d, times %d\n", attr->dname,
+		       attr->probability, attr->interval,
+		       atomic_read(&attr->space),
+		       atomic_read(&attr->times));
+		if (attr->verbose > 1)
+			dump_stack();
+	}
 }
 
 #define atomic_dec_not_zero(v)		atomic_add_unless((v), -1, 0)
@@ -202,6 +208,12 @@ struct dentry *fault_create_debugfs_attr(const char *name,
 		goto fail;
 	if (!debugfs_create_ul("verbose", mode, dir, &attr->verbose))
 		goto fail;
+	if (!debugfs_create_u32("verbose_ratelimit_interval_ms", mode, dir,
+				&attr->ratelimit_state.interval))
+		goto fail;
+	if (!debugfs_create_u32("verbose_ratelimit_burst", mode, dir,
+				&attr->ratelimit_state.burst))
+		goto fail;
 	if (!debugfs_create_bool("task-filter", mode, dir, &attr->task_filter))
 		goto fail;
 
@@ -222,6 +234,7 @@ struct dentry *fault_create_debugfs_attr(const char *name,
 
 #endif /* CONFIG_FAULT_INJECTION_STACKTRACE_FILTER */
 
+	attr->dname = dget(dir);
 	return dir;
 fail:
 	debugfs_remove_recursive(dir);
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index ec337f64f52d..d57551c031f4 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -1240,6 +1240,21 @@ char *address_val(char *buf, char *end, const void *addr,
 	return number(buf, end, num, spec);
 }
 
+static noinline_for_stack
+char *comm_name(char *buf, char *end, struct task_struct *tsk,
+		struct printf_spec spec, const char *fmt)
+{
+	char name[TASK_COMM_LEN];
+
+	/* Caller can pass NULL instead of current. */
+	if (!tsk)
+		tsk = current;
+	/* Not using get_task_comm() in case I'm in IRQ context. */
+	memcpy(name, tsk->comm, TASK_COMM_LEN);
+	name[sizeof(name) - 1] = '\0';
+	return string(buf, end, name, spec);
+}
+
 int kptr_restrict __read_mostly;
 
 /*
@@ -1318,6 +1333,7 @@ int kptr_restrict __read_mostly;
  *           (default assumed to be phys_addr_t, passed by reference)
  * - 'd[234]' For a dentry name (optionally 2-4 last components)
  * - 'D[234]' Same as 'd' but for a struct file
+ * - 'T' task_struct->comm
  *
  * Note: The difference between 'S' and 'F' is that on ia64 and ppc64
  * function pointers are really function descriptors, which contain a
@@ -1329,7 +1345,7 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 {
 	int default_width = 2 * sizeof(void *) + (spec.flags & SPECIAL ? 2 : 0);
 
-	if (!ptr && *fmt != 'K') {
+	if (!ptr && *fmt != 'K' && *fmt != 'T') {
 		/*
 		 * Print (null) with the same width as a pointer so it makes
 		 * tabular output look nice.
@@ -1459,6 +1475,8 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 		return dentry_name(buf, end,
 				   ((const struct file *)ptr)->f_path.dentry,
 				   spec, fmt);
+	case 'T':
+		return comm_name(buf, end, ptr, spec, fmt);
 	}
 	spec.flags |= SMALL;
 	if (spec.field_width == -1) {
diff --git a/mm/Makefile b/mm/Makefile
index 8405eb0023a9..b3c6ce932c64 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -55,7 +55,9 @@ obj-$(CONFIG_FS_XIP) += filemap_xip.o
 obj-$(CONFIG_MIGRATION) += migrate.o
 obj-$(CONFIG_QUICKLIST) += quicklist.o
 obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += huge_memory.o
-obj-$(CONFIG_MEMCG) += memcontrol.o page_cgroup.o vmpressure.o
+obj-$(CONFIG_PAGE_COUNTER) += page_counter.o
+obj-$(CONFIG_MEMCG) += memcontrol.o vmpressure.o
+obj-$(CONFIG_MEMCG_SWAP) += swap_cgroup.o
 obj-$(CONFIG_CGROUP_HUGETLB) += hugetlb_cgroup.o
 obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o
 obj-$(CONFIG_HWPOISON_INJECT) += hwpoison-inject.o
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 8a000cebb0d7..477be696511d 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -243,13 +243,10 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
 
 static int reset_managed_pages_done __initdata;
 
-static inline void __init reset_node_managed_pages(pg_data_t *pgdat)
+void reset_node_managed_pages(pg_data_t *pgdat)
 {
 	struct zone *z;
 
-	if (reset_managed_pages_done)
-		return;
-
 	for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++)
 		z->managed_pages = 0;
 }
@@ -258,8 +255,12 @@ void __init reset_all_zones_managed_pages(void)
 {
 	struct pglist_data *pgdat;
 
+	if (reset_managed_pages_done)
+		return;
+
 	for_each_online_pgdat(pgdat)
 		reset_node_managed_pages(pgdat);
+
 	reset_managed_pages_done = 1;
 }
 
diff --git a/mm/cma.c b/mm/cma.c
index fde706e1284f..081359926d03 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -63,6 +63,17 @@ static unsigned long cma_bitmap_aligned_mask(struct cma *cma, int align_order)
 	return (1UL << (align_order - cma->order_per_bit)) - 1;
 }
 
+static unsigned long cma_bitmap_aligned_offset(struct cma *cma, int align_order)
+{
+	unsigned int alignment;
+
+	if (align_order <= cma->order_per_bit)
+		return 0;
+	alignment = 1UL << (align_order - cma->order_per_bit);
+	return ALIGN(cma->base_pfn, alignment) -
+		(cma->base_pfn >> cma->order_per_bit);
+}
+
 static unsigned long cma_bitmap_maxno(struct cma *cma)
 {
 	return cma->count >> cma->order_per_bit;
@@ -328,7 +339,7 @@ err:
  */
 struct page *cma_alloc(struct cma *cma, int count, unsigned int align)
 {
-	unsigned long mask, pfn, start = 0;
+	unsigned long mask, offset, pfn, start = 0;
 	unsigned long bitmap_maxno, bitmap_no, bitmap_count;
 	struct page *page = NULL;
 	int ret;
@@ -343,13 +354,15 @@ struct page *cma_alloc(struct cma *cma, int count, unsigned int align)
 		return NULL;
 
 	mask = cma_bitmap_aligned_mask(cma, align);
+	offset = cma_bitmap_aligned_offset(cma, align);
 	bitmap_maxno = cma_bitmap_maxno(cma);
 	bitmap_count = cma_bitmap_pages_to_bits(cma, count);
 
 	for (;;) {
 		mutex_lock(&cma->lock);
-		bitmap_no = bitmap_find_next_zero_area(cma->bitmap,
-				bitmap_maxno, start, bitmap_count, mask);
+		bitmap_no = bitmap_find_next_zero_area_off(cma->bitmap,
+				bitmap_maxno, start, bitmap_count, mask,
+				offset);
 		if (bitmap_no >= bitmap_maxno) {
 			mutex_unlock(&cma->lock);
 			break;
diff --git a/mm/compaction.c b/mm/compaction.c
index ec74cf0123ef..552f58397a79 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -195,16 +195,12 @@ static void update_pageblock_skip(struct compact_control *cc,
 
 	/* Update where async and sync compaction should restart */
 	if (migrate_scanner) {
-		if (cc->finished_update_migrate)
-			return;
 		if (pfn > zone->compact_cached_migrate_pfn[0])
 			zone->compact_cached_migrate_pfn[0] = pfn;
 		if (cc->mode != MIGRATE_ASYNC &&
 		    pfn > zone->compact_cached_migrate_pfn[1])
 			zone->compact_cached_migrate_pfn[1] = pfn;
 	} else {
-		if (cc->finished_update_free)
-			return;
 		if (pfn < zone->compact_cached_free_pfn)
 			zone->compact_cached_free_pfn = pfn;
 	}
@@ -479,6 +475,16 @@ isolate_freepages_range(struct compact_control *cc,
 
 		block_end_pfn = min(block_end_pfn, end_pfn);
 
+		/*
+		 * pfn could pass the block_end_pfn if isolated freepage
+		 * is more than pageblock order. In this case, we adjust
+		 * scanning range to right one.
+		 */
+		if (pfn >= block_end_pfn) {
+			block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
+			block_end_pfn = min(block_end_pfn, end_pfn);
+		}
+
 		if (!pageblock_pfn_to_page(pfn, block_end_pfn, cc->zone))
 			break;
 
@@ -705,7 +711,6 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		del_page_from_lru_list(page, lruvec, page_lru(page));
 
 isolate_success:
-		cc->finished_update_migrate = true;
 		list_add(&page->lru, migratelist);
 		cc->nr_migratepages++;
 		nr_isolated++;
@@ -879,15 +884,6 @@ static void isolate_freepages(struct compact_control *cc)
 				block_start_pfn - pageblock_nr_pages;
 
 		/*
-		 * Set a flag that we successfully isolated in this pageblock.
-		 * In the next loop iteration, zone->compact_cached_free_pfn
-		 * will not be updated and thus it will effectively contain the
-		 * highest pageblock we isolated pages from.
-		 */
-		if (isolated)
-			cc->finished_update_free = true;
-
-		/*
 		 * isolate_freepages_block() might have aborted due to async
 		 * compaction being contended
 		 */
@@ -1029,8 +1025,12 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 	}
 
 	acct_isolated(zone, cc);
-	/* Record where migration scanner will be restarted */
-	cc->migrate_pfn = low_pfn;
+	/*
+	 * Record where migration scanner will be restarted. If we end up in
+	 * the same pageblock as the free scanner, make the scanners fully
+	 * meet so that compact_finished() terminates compaction.
+	 */
+	cc->migrate_pfn = (end_pfn <= cc->free_pfn) ? low_pfn : cc->free_pfn;
 
 	return cc->nr_migratepages ? ISOLATE_SUCCESS : ISOLATE_NONE;
 }
@@ -1072,9 +1072,9 @@ static int compact_finished(struct zone *zone, struct compact_control *cc,
 
 	/* Compaction run is not finished if the watermark is not met */
 	watermark = low_wmark_pages(zone);
-	watermark += (1 << cc->order);
 
-	if (!zone_watermark_ok(zone, cc->order, watermark, 0, 0))
+	if (!zone_watermark_ok(zone, cc->order, watermark, cc->classzone_idx,
+							cc->alloc_flags))
 		return COMPACT_CONTINUE;
 
 	/* Direct compactor: Is a suitable page free? */
@@ -1100,7 +1100,8 @@ static int compact_finished(struct zone *zone, struct compact_control *cc,
  *   COMPACT_PARTIAL  - If the allocation would succeed without compaction
  *   COMPACT_CONTINUE - If compaction should run now
  */
-unsigned long compaction_suitable(struct zone *zone, int order)
+unsigned long compaction_suitable(struct zone *zone, int order,
+					int alloc_flags, int classzone_idx)
 {
 	int fragindex;
 	unsigned long watermark;
@@ -1137,7 +1138,7 @@ unsigned long compaction_suitable(struct zone *zone, int order)
 		return COMPACT_SKIPPED;
 
 	if (fragindex == -1000 && zone_watermark_ok(zone, order, watermark,
-	    0, 0))
+	    classzone_idx, alloc_flags))
 		return COMPACT_PARTIAL;
 
 	return COMPACT_CONTINUE;
@@ -1151,7 +1152,8 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 	const int migratetype = gfpflags_to_migratetype(cc->gfp_mask);
 	const bool sync = cc->mode != MIGRATE_ASYNC;
 
-	ret = compaction_suitable(zone, cc->order);
+	ret = compaction_suitable(zone, cc->order, cc->alloc_flags,
+							cc->classzone_idx);
 	switch (ret) {
 	case COMPACT_PARTIAL:
 	case COMPACT_SKIPPED:
@@ -1194,6 +1196,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 	while ((ret = compact_finished(zone, cc, migratetype)) ==
 						COMPACT_CONTINUE) {
 		int err;
+		unsigned long last_migrated_pfn = 0;
 
 		switch (isolate_migratepages(zone, cc)) {
 		case ISOLATE_ABORT:
@@ -1202,7 +1205,12 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 			cc->nr_migratepages = 0;
 			goto out;
 		case ISOLATE_NONE:
-			continue;
+			/*
+			 * We haven't isolated and migrated anything, but
+			 * there might still be unflushed migrations from
+			 * previous cc->order aligned block.
+			 */
+			goto check_drain;
 		case ISOLATE_SUCCESS:
 			;
 		}
@@ -1227,6 +1235,39 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 				goto out;
 			}
 		}
+
+		/*
+		 * Record where we have freed pages by migration and not yet
+		 * flushed them to buddy allocator. Subtract 1, because often
+		 * we finish a pageblock and migrate_pfn points to the first
+		 * page* of the next one. In that case we want the drain below
+		 * to happen immediately.
+		 */
+		if (!last_migrated_pfn)
+			last_migrated_pfn = cc->migrate_pfn - 1;
+
+check_drain:
+		/*
+		 * Have we moved away from the previous cc->order aligned block
+		 * where we migrated from? If yes, flush the pages that were
+		 * freed, so that they can merge and compact_finished() can
+		 * detect immediately if allocation should succeed.
+		 */
+		if (cc->order > 0 && last_migrated_pfn) {
+			int cpu;
+			unsigned long current_block_start =
+				cc->migrate_pfn & ~((1UL << cc->order) - 1);
+
+			if (last_migrated_pfn < current_block_start) {
+				cpu = get_cpu();
+				lru_add_drain_cpu(cpu);
+				drain_local_pages(zone);
+				put_cpu();
+				/* No more flushing until we migrate again */
+				last_migrated_pfn = 0;
+			}
+		}
+
 	}
 
 out:
@@ -1240,7 +1281,8 @@ out:
 }
 
 static unsigned long compact_zone_order(struct zone *zone, int order,
-		gfp_t gfp_mask, enum migrate_mode mode, int *contended)
+		gfp_t gfp_mask, enum migrate_mode mode, int *contended,
+		int alloc_flags, int classzone_idx)
 {
 	unsigned long ret;
 	struct compact_control cc = {
@@ -1250,6 +1292,8 @@ static unsigned long compact_zone_order(struct zone *zone, int order,
 		.gfp_mask = gfp_mask,
 		.zone = zone,
 		.mode = mode,
+		.alloc_flags = alloc_flags,
+		.classzone_idx = classzone_idx,
 	};
 	INIT_LIST_HEAD(&cc.freepages);
 	INIT_LIST_HEAD(&cc.migratepages);
@@ -1274,14 +1318,13 @@ int sysctl_extfrag_threshold = 500;
  * @mode: The migration mode for async, sync light, or sync migration
  * @contended: Return value that determines if compaction was aborted due to
  *	       need_resched() or lock contention
- * @candidate_zone: Return the zone where we think allocation should succeed
  *
  * This is the main entry point for direct page compaction.
  */
 unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
 			enum migrate_mode mode, int *contended,
-			struct zone **candidate_zone)
+			int alloc_flags, int classzone_idx)
 {
 	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
 	int may_enter_fs = gfp_mask & __GFP_FS;
@@ -1289,7 +1332,6 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 	struct zoneref *z;
 	struct zone *zone;
 	int rc = COMPACT_DEFERRED;
-	int alloc_flags = 0;
 	int all_zones_contended = COMPACT_CONTENDED_LOCK; /* init for &= op */
 
 	*contended = COMPACT_CONTENDED_NONE;
@@ -1298,10 +1340,6 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 	if (!order || !may_enter_fs || !may_perform_io)
 		return COMPACT_SKIPPED;
 
-#ifdef CONFIG_CMA
-	if (gfpflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
-		alloc_flags |= ALLOC_CMA;
-#endif
 	/* Compact each zone in the list */
 	for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx,
 								nodemask) {
@@ -1312,7 +1350,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			continue;
 
 		status = compact_zone_order(zone, order, gfp_mask, mode,
-							&zone_contended);
+				&zone_contended, alloc_flags, classzone_idx);
 		rc = max(status, rc);
 		/*
 		 * It takes at least one zone that wasn't lock contended
@@ -1321,9 +1359,8 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 		all_zones_contended &= zone_contended;
 
 		/* If a normal allocation would succeed, stop compacting */
-		if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0,
-				      alloc_flags)) {
-			*candidate_zone = zone;
+		if (zone_watermark_ok(zone, order, low_wmark_pages(zone),
+					classzone_idx, alloc_flags)) {
 			/*
 			 * We think the allocation will succeed in this zone,
 			 * but it is not certain, hence the false. The caller
@@ -1345,7 +1382,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			goto break_loop;
 		}
 
-		if (mode != MIGRATE_ASYNC) {
+		if (mode != MIGRATE_ASYNC && status == COMPACT_COMPLETE) {
 			/*
 			 * We think that allocation won't succeed in this zone
 			 * so we defer compaction there. If it ends up
diff --git a/mm/debug.c b/mm/debug.c
index 5ce45c9a29b5..0e58f3211f89 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -95,7 +95,10 @@ void dump_page_badflags(struct page *page, const char *reason,
 		dump_flags(page->flags & badflags,
 				pageflag_names, ARRAY_SIZE(pageflag_names));
 	}
-	mem_cgroup_print_bad_page(page);
+#ifdef CONFIG_MEMCG
+	if (page->mem_cgroup)
+		pr_alert("page->mem_cgroup:%p\n", page->mem_cgroup);
+#endif
 }
 
 void dump_page(struct page *page, const char *reason)
diff --git a/mm/filemap.c b/mm/filemap.c
index 14b4642279f1..e8905bc3cbd7 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -62,16 +62,16 @@
 /*
  * Lock ordering:
  *
- *  ->i_mmap_mutex		(truncate_pagecache)
+ *  ->i_mmap_rwsem		(truncate_pagecache)
  *    ->private_lock		(__free_pte->__set_page_dirty_buffers)
  *      ->swap_lock		(exclusive_swap_page, others)
  *        ->mapping->tree_lock
  *
  *  ->i_mutex
- *    ->i_mmap_mutex		(truncate->unmap_mapping_range)
+ *    ->i_mmap_rwsem		(truncate->unmap_mapping_range)
  *
  *  ->mmap_sem
- *    ->i_mmap_mutex
+ *    ->i_mmap_rwsem
  *      ->page_table_lock or pte_lock	(various, mainly in memory.c)
  *        ->mapping->tree_lock	(arch-dependent flush_dcache_mmap_lock)
  *
@@ -85,7 +85,7 @@
  *    sb_lock			(fs/fs-writeback.c)
  *    ->mapping->tree_lock	(__sync_single_inode)
  *
- *  ->i_mmap_mutex
+ *  ->i_mmap_rwsem
  *    ->anon_vma.lock		(vma_adjust)
  *
  *  ->anon_vma.lock
@@ -105,7 +105,7 @@
  *    ->inode->i_lock		(zap_pte_range->set_page_dirty)
  *    ->private_lock		(zap_pte_range->__set_page_dirty_buffers)
  *
- * ->i_mmap_mutex
+ * ->i_mmap_rwsem
  *   ->tasklist_lock            (memory_failure, collect_procs_ao)
  */
 
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
index d8d9fe3f685c..0d105aeff82f 100644
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -155,22 +155,14 @@ xip_file_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos)
 EXPORT_SYMBOL_GPL(xip_file_read);
 
 /*
- * __xip_unmap is invoked from xip_unmap and
- * xip_write
+ * __xip_unmap is invoked from xip_unmap and xip_write
  *
  * This function walks all vmas of the address_space and unmaps the
  * __xip_sparse_page when found at pgoff.
  */
-static void
-__xip_unmap (struct address_space * mapping,
-		     unsigned long pgoff)
+static void __xip_unmap(struct address_space * mapping, unsigned long pgoff)
 {
 	struct vm_area_struct *vma;
-	struct mm_struct *mm;
-	unsigned long address;
-	pte_t *pte;
-	pte_t pteval;
-	spinlock_t *ptl;
 	struct page *page;
 	unsigned count;
 	int locked = 0;
@@ -182,11 +174,14 @@ __xip_unmap (struct address_space * mapping,
 		return;
 
 retry:
-	mutex_lock(&mapping->i_mmap_mutex);
+	i_mmap_lock_read(mapping);
 	vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) {
-		mm = vma->vm_mm;
-		address = vma->vm_start +
+		pte_t *pte, pteval;
+		spinlock_t *ptl;
+		struct mm_struct *mm = vma->vm_mm;
+		unsigned long address = vma->vm_start +
 			((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
+
 		BUG_ON(address < vma->vm_start || address >= vma->vm_end);
 		pte = page_check_address(page, mm, address, &ptl, 1);
 		if (pte) {
@@ -202,7 +197,7 @@ retry:
 			page_cache_release(page);
 		}
 	}
-	mutex_unlock(&mapping->i_mmap_mutex);
+	i_mmap_unlock_read(mapping);
 
 	if (locked) {
 		mutex_unlock(&xip_sparse_mutex);
diff --git a/mm/fremap.c b/mm/fremap.c
index 72b8fa361433..2805d71cf476 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -37,7 +37,7 @@ static void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	if (pte_present(pte)) {
 		flush_cache_page(vma, addr, pte_pfn(pte));
-		pte = ptep_clear_flush(vma, addr, ptep);
+		pte = ptep_clear_flush_notify(vma, addr, ptep);
 		page = vm_normal_page(vma, addr, pte);
 		if (page) {
 			if (pte_dirty(pte))
@@ -238,13 +238,13 @@ get_write_lock:
 			}
 			goto out_freed;
 		}
-		mutex_lock(&mapping->i_mmap_mutex);
+		i_mmap_lock_write(mapping);
 		flush_dcache_mmap_lock(mapping);
 		vma->vm_flags |= VM_NONLINEAR;
 		vma_interval_tree_remove(vma, &mapping->i_mmap);
 		vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear);
 		flush_dcache_mmap_unlock(mapping);
-		mutex_unlock(&mapping->i_mmap_mutex);
+		i_mmap_unlock_write(mapping);
 	}
 
 	if (vma->vm_flags & VM_LOCKED) {
diff --git a/mm/frontswap.c b/mm/frontswap.c
index c30eec536f03..1b80c053cbaf 100644
--- a/mm/frontswap.c
+++ b/mm/frontswap.c
@@ -182,7 +182,7 @@ void __frontswap_init(unsigned type, unsigned long *map)
 	if (frontswap_ops)
 		frontswap_ops->init(type);
 	else {
-		BUG_ON(type > MAX_SWAPFILES);
+		BUG_ON(type >= MAX_SWAPFILES);
 		set_bit(type, need_init);
 	}
 }
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 46a1e4dbba81..817a875f2b8c 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -784,7 +784,6 @@ static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm,
 	if (!pmd_none(*pmd))
 		return false;
 	entry = mk_pmd(zero_page, vma->vm_page_prot);
-	entry = pmd_wrprotect(entry);
 	entry = pmd_mkhuge(entry);
 	pgtable_trans_huge_deposit(mm, pmd, pgtable);
 	set_pmd_at(mm, haddr, pmd, entry);
@@ -1036,7 +1035,7 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
 		goto out_free_pages;
 	VM_BUG_ON_PAGE(!PageHead(page), page);
 
-	pmdp_clear_flush(vma, haddr, pmd);
+	pmdp_clear_flush_notify(vma, haddr, pmd);
 	/* leave pmd empty until pte is filled */
 
 	pgtable = pgtable_trans_huge_withdraw(mm, pmd);
@@ -1179,7 +1178,7 @@ alloc:
 		pmd_t entry;
 		entry = mk_huge_pmd(new_page, vma->vm_page_prot);
 		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
-		pmdp_clear_flush(vma, haddr, pmd);
+		pmdp_clear_flush_notify(vma, haddr, pmd);
 		page_add_new_anon_rmap(new_page, vma, haddr);
 		mem_cgroup_commit_charge(new_page, memcg, false);
 		lru_cache_add_active_or_unevictable(new_page, vma);
@@ -1513,7 +1512,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 		pmd_t entry;
 		ret = 1;
 		if (!prot_numa) {
-			entry = pmdp_get_and_clear(mm, addr, pmd);
+			entry = pmdp_get_and_clear_notify(mm, addr, pmd);
 			if (pmd_numa(entry))
 				entry = pmd_mknonnuma(entry);
 			entry = pmd_modify(entry, newprot);
@@ -1645,6 +1644,7 @@ static int __split_huge_page_splitting(struct page *page,
 		 * serialize against split_huge_page*.
 		 */
 		pmdp_splitting_flush(vma, address, pmd);
+
 		ret = 1;
 		spin_unlock(ptl);
 	}
@@ -2835,7 +2835,7 @@ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
 	pmd_t _pmd;
 	int i;
 
-	pmdp_clear_flush(vma, haddr, pmd);
+	pmdp_clear_flush_notify(vma, haddr, pmd);
 	/* leave pmd empty until pte is filled */
 
 	pgtable = pgtable_trans_huge_withdraw(mm, pmd);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 82da930fa3f8..8654a52b1b01 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2598,8 +2598,11 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			}
 			set_huge_pte_at(dst, addr, dst_pte, entry);
 		} else {
-			if (cow)
+			if (cow) {
 				huge_ptep_set_wrprotect(src, addr, src_pte);
+				mmu_notifier_invalidate_range(src, mmun_start,
+								   mmun_end);
+			}
 			entry = huge_ptep_get(src_pte);
 			ptepage = pte_page(entry);
 			get_page(ptepage);
@@ -2638,8 +2641,9 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 
 	tlb_start_vma(tlb, vma);
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
+	address = start;
 again:
-	for (address = start; address < end; address += sz) {
+	for (; address < end; address += sz) {
 		ptep = huge_pte_offset(mm, address);
 		if (!ptep)
 			continue;
@@ -2686,6 +2690,7 @@ again:
 		page_remove_rmap(page);
 		force_flush = !__tlb_remove_page(tlb, page);
 		if (force_flush) {
+			address += sz;
 			spin_unlock(ptl);
 			break;
 		}
@@ -2724,9 +2729,9 @@ void __unmap_hugepage_range_final(struct mmu_gather *tlb,
 	 * on its way out.  We're lucky that the flag has such an appropriate
 	 * name, and can in fact be safely cleared here. We could clear it
 	 * before the __unmap_hugepage_range above, but all that's necessary
-	 * is to clear it before releasing the i_mmap_mutex. This works
+	 * is to clear it before releasing the i_mmap_rwsem. This works
 	 * because in the context this is called, the VMA is about to be
-	 * destroyed and the i_mmap_mutex is held.
+	 * destroyed and the i_mmap_rwsem is held.
 	 */
 	vma->vm_flags &= ~VM_MAYSHARE;
 }
@@ -2772,7 +2777,7 @@ static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * this mapping should be shared between all the VMAs,
 	 * __unmap_hugepage_range() is called as the lock is already held
 	 */
-	mutex_lock(&mapping->i_mmap_mutex);
+	i_mmap_lock_write(mapping);
 	vma_interval_tree_foreach(iter_vma, &mapping->i_mmap, pgoff, pgoff) {
 		/* Do not unmap the current VMA */
 		if (iter_vma == vma)
@@ -2789,7 +2794,7 @@ static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
 			unmap_hugepage_range(iter_vma, address,
 					     address + huge_page_size(h), page);
 	}
-	mutex_unlock(&mapping->i_mmap_mutex);
+	i_mmap_unlock_write(mapping);
 }
 
 /*
@@ -2899,6 +2904,7 @@ retry_avoidcopy:
 
 		/* Break COW */
 		huge_ptep_clear_flush(vma, address, ptep);
+		mmu_notifier_invalidate_range(mm, mmun_start, mmun_end);
 		set_huge_pte_at(mm, address, ptep,
 				make_huge_pte(vma, new_page, 1));
 		page_remove_rmap(old_page);
@@ -3346,7 +3352,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 	flush_cache_range(vma, address, end);
 
 	mmu_notifier_invalidate_range_start(mm, start, end);
-	mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex);
+	i_mmap_lock_write(vma->vm_file->f_mapping);
 	for (; address < end; address += huge_page_size(h)) {
 		spinlock_t *ptl;
 		ptep = huge_pte_offset(mm, address);
@@ -3368,13 +3374,14 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 		spin_unlock(ptl);
 	}
 	/*
-	 * Must flush TLB before releasing i_mmap_mutex: x86's huge_pmd_unshare
+	 * Must flush TLB before releasing i_mmap_rwsem: x86's huge_pmd_unshare
 	 * may have cleared our pud entry and done put_page on the page table:
-	 * once we release i_mmap_mutex, another task can do the final put_page
+	 * once we release i_mmap_rwsem, another task can do the final put_page
 	 * and that page table be reused and filled with junk.
 	 */
 	flush_tlb_range(vma, start, end);
-	mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
+	mmu_notifier_invalidate_range(mm, start, end);
+	i_mmap_unlock_write(vma->vm_file->f_mapping);
 	mmu_notifier_invalidate_range_end(mm, start, end);
 
 	return pages << h->order;
@@ -3523,7 +3530,7 @@ static int vma_shareable(struct vm_area_struct *vma, unsigned long addr)
  * and returns the corresponding pte. While this is not necessary for the
  * !shared pmd case because we can allocate the pmd later as well, it makes the
  * code much cleaner. pmd allocation is essential for the shared case because
- * pud has to be populated inside the same i_mmap_mutex section - otherwise
+ * pud has to be populated inside the same i_mmap_rwsem section - otherwise
  * racing tasks could either miss the sharing (see huge_pte_offset) or select a
  * bad pmd for sharing.
  */
@@ -3542,7 +3549,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 	if (!vma_shareable(vma, addr))
 		return (pte_t *)pmd_alloc(mm, pud, addr);
 
-	mutex_lock(&mapping->i_mmap_mutex);
+	i_mmap_lock_write(mapping);
 	vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) {
 		if (svma == vma)
 			continue;
@@ -3570,7 +3577,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
 	spin_unlock(ptl);
 out:
 	pte = (pte_t *)pmd_alloc(mm, pud, addr);
-	mutex_unlock(&mapping->i_mmap_mutex);
+	i_mmap_unlock_write(mapping);
 	return pte;
 }
 
diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c
index a67c26e0f360..037e1c00a5b7 100644
--- a/mm/hugetlb_cgroup.c
+++ b/mm/hugetlb_cgroup.c
@@ -14,6 +14,7 @@
  */
 
 #include <linux/cgroup.h>
+#include <linux/page_counter.h>
 #include <linux/slab.h>
 #include <linux/hugetlb.h>
 #include <linux/hugetlb_cgroup.h>
@@ -23,7 +24,7 @@ struct hugetlb_cgroup {
 	/*
 	 * the counter to account for hugepages from hugetlb.
 	 */
-	struct res_counter hugepage[HUGE_MAX_HSTATE];
+	struct page_counter hugepage[HUGE_MAX_HSTATE];
 };
 
 #define MEMFILE_PRIVATE(x, val)	(((x) << 16) | (val))
@@ -60,7 +61,7 @@ static inline bool hugetlb_cgroup_have_usage(struct hugetlb_cgroup *h_cg)
 	int idx;
 
 	for (idx = 0; idx < hugetlb_max_hstate; idx++) {
-		if ((res_counter_read_u64(&h_cg->hugepage[idx], RES_USAGE)) > 0)
+		if (page_counter_read(&h_cg->hugepage[idx]))
 			return true;
 	}
 	return false;
@@ -79,12 +80,12 @@ hugetlb_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 
 	if (parent_h_cgroup) {
 		for (idx = 0; idx < HUGE_MAX_HSTATE; idx++)
-			res_counter_init(&h_cgroup->hugepage[idx],
-					 &parent_h_cgroup->hugepage[idx]);
+			page_counter_init(&h_cgroup->hugepage[idx],
+					  &parent_h_cgroup->hugepage[idx]);
 	} else {
 		root_h_cgroup = h_cgroup;
 		for (idx = 0; idx < HUGE_MAX_HSTATE; idx++)
-			res_counter_init(&h_cgroup->hugepage[idx], NULL);
+			page_counter_init(&h_cgroup->hugepage[idx], NULL);
 	}
 	return &h_cgroup->css;
 }
@@ -108,9 +109,8 @@ static void hugetlb_cgroup_css_free(struct cgroup_subsys_state *css)
 static void hugetlb_cgroup_move_parent(int idx, struct hugetlb_cgroup *h_cg,
 				       struct page *page)
 {
-	int csize;
-	struct res_counter *counter;
-	struct res_counter *fail_res;
+	unsigned int nr_pages;
+	struct page_counter *counter;
 	struct hugetlb_cgroup *page_hcg;
 	struct hugetlb_cgroup *parent = parent_hugetlb_cgroup(h_cg);
 
@@ -123,15 +123,15 @@ static void hugetlb_cgroup_move_parent(int idx, struct hugetlb_cgroup *h_cg,
 	if (!page_hcg || page_hcg != h_cg)
 		goto out;
 
-	csize = PAGE_SIZE << compound_order(page);
+	nr_pages = 1 << compound_order(page);
 	if (!parent) {
 		parent = root_h_cgroup;
 		/* root has no limit */
-		res_counter_charge_nofail(&parent->hugepage[idx],
-					  csize, &fail_res);
+		page_counter_charge(&parent->hugepage[idx], nr_pages);
 	}
 	counter = &h_cg->hugepage[idx];
-	res_counter_uncharge_until(counter, counter->parent, csize);
+	/* Take the pages off the local counter */
+	page_counter_cancel(counter, nr_pages);
 
 	set_hugetlb_cgroup(page, parent);
 out:
@@ -166,9 +166,8 @@ int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
 				 struct hugetlb_cgroup **ptr)
 {
 	int ret = 0;
-	struct res_counter *fail_res;
+	struct page_counter *counter;
 	struct hugetlb_cgroup *h_cg = NULL;
-	unsigned long csize = nr_pages * PAGE_SIZE;
 
 	if (hugetlb_cgroup_disabled())
 		goto done;
@@ -187,7 +186,7 @@ again:
 	}
 	rcu_read_unlock();
 
-	ret = res_counter_charge(&h_cg->hugepage[idx], csize, &fail_res);
+	ret = page_counter_try_charge(&h_cg->hugepage[idx], nr_pages, &counter);
 	css_put(&h_cg->css);
 done:
 	*ptr = h_cg;
@@ -213,7 +212,6 @@ void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages,
 				  struct page *page)
 {
 	struct hugetlb_cgroup *h_cg;
-	unsigned long csize = nr_pages * PAGE_SIZE;
 
 	if (hugetlb_cgroup_disabled())
 		return;
@@ -222,61 +220,76 @@ void hugetlb_cgroup_uncharge_page(int idx, unsigned long nr_pages,
 	if (unlikely(!h_cg))
 		return;
 	set_hugetlb_cgroup(page, NULL);
-	res_counter_uncharge(&h_cg->hugepage[idx], csize);
+	page_counter_uncharge(&h_cg->hugepage[idx], nr_pages);
 	return;
 }
 
 void hugetlb_cgroup_uncharge_cgroup(int idx, unsigned long nr_pages,
 				    struct hugetlb_cgroup *h_cg)
 {
-	unsigned long csize = nr_pages * PAGE_SIZE;
-
 	if (hugetlb_cgroup_disabled() || !h_cg)
 		return;
 
 	if (huge_page_order(&hstates[idx]) < HUGETLB_CGROUP_MIN_ORDER)
 		return;
 
-	res_counter_uncharge(&h_cg->hugepage[idx], csize);
+	page_counter_uncharge(&h_cg->hugepage[idx], nr_pages);
 	return;
 }
 
+enum {
+	RES_USAGE,
+	RES_LIMIT,
+	RES_MAX_USAGE,
+	RES_FAILCNT,
+};
+
 static u64 hugetlb_cgroup_read_u64(struct cgroup_subsys_state *css,
 				   struct cftype *cft)
 {
-	int idx, name;
+	struct page_counter *counter;
 	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css);
 
-	idx = MEMFILE_IDX(cft->private);
-	name = MEMFILE_ATTR(cft->private);
+	counter = &h_cg->hugepage[MEMFILE_IDX(cft->private)];
 
-	return res_counter_read_u64(&h_cg->hugepage[idx], name);
+	switch (MEMFILE_ATTR(cft->private)) {
+	case RES_USAGE:
+		return (u64)page_counter_read(counter) * PAGE_SIZE;
+	case RES_LIMIT:
+		return (u64)counter->limit * PAGE_SIZE;
+	case RES_MAX_USAGE:
+		return (u64)counter->watermark * PAGE_SIZE;
+	case RES_FAILCNT:
+		return counter->failcnt;
+	default:
+		BUG();
+	}
 }
 
+static DEFINE_MUTEX(hugetlb_limit_mutex);
+
 static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of,
 				    char *buf, size_t nbytes, loff_t off)
 {
-	int idx, name, ret;
-	unsigned long long val;
+	int ret, idx;
+	unsigned long nr_pages;
 	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of));
 
+	if (hugetlb_cgroup_is_root(h_cg)) /* Can't set limit on root */
+		return -EINVAL;
+
 	buf = strstrip(buf);
+	ret = page_counter_memparse(buf, &nr_pages);
+	if (ret)
+		return ret;
+
 	idx = MEMFILE_IDX(of_cft(of)->private);
-	name = MEMFILE_ATTR(of_cft(of)->private);
 
-	switch (name) {
+	switch (MEMFILE_ATTR(of_cft(of)->private)) {
 	case RES_LIMIT:
-		if (hugetlb_cgroup_is_root(h_cg)) {
-			/* Can't set limit on root */
-			ret = -EINVAL;
-			break;
-		}
-		/* This function does all necessary parse...reuse it */
-		ret = res_counter_memparse_write_strategy(buf, &val);
-		if (ret)
-			break;
-		val = ALIGN(val, 1ULL << huge_page_shift(&hstates[idx]));
-		ret = res_counter_set_limit(&h_cg->hugepage[idx], val);
+		mutex_lock(&hugetlb_limit_mutex);
+		ret = page_counter_limit(&h_cg->hugepage[idx], nr_pages);
+		mutex_unlock(&hugetlb_limit_mutex);
 		break;
 	default:
 		ret = -EINVAL;
@@ -288,18 +301,18 @@ static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of,
 static ssize_t hugetlb_cgroup_reset(struct kernfs_open_file *of,
 				    char *buf, size_t nbytes, loff_t off)
 {
-	int idx, name, ret = 0;
+	int ret = 0;
+	struct page_counter *counter;
 	struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(of_css(of));
 
-	idx = MEMFILE_IDX(of_cft(of)->private);
-	name = MEMFILE_ATTR(of_cft(of)->private);
+	counter = &h_cg->hugepage[MEMFILE_IDX(of_cft(of)->private)];
 
-	switch (name) {
+	switch (MEMFILE_ATTR(of_cft(of)->private)) {
 	case RES_MAX_USAGE:
-		res_counter_reset_max(&h_cg->hugepage[idx]);
+		page_counter_reset_watermark(counter);
 		break;
 	case RES_FAILCNT:
-		res_counter_reset_failcnt(&h_cg->hugepage[idx]);
+		counter->failcnt = 0;
 		break;
 	default:
 		ret = -EINVAL;
diff --git a/mm/internal.h b/mm/internal.h
index 829304090b90..efad241f7014 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -108,6 +108,31 @@ extern pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address);
 /*
  * in mm/page_alloc.c
  */
+
+/*
+ * Locate the struct page for both the matching buddy in our
+ * pair (buddy1) and the combined O(n+1) page they form (page).
+ *
+ * 1) Any buddy B1 will have an order O twin B2 which satisfies
+ * the following equation:
+ *     B2 = B1 ^ (1 << O)
+ * For example, if the starting buddy (buddy2) is #8 its order
+ * 1 buddy is #10:
+ *     B2 = 8 ^ (1 << 1) = 8 ^ 2 = 10
+ *
+ * 2) Any buddy B will have an order O+1 parent P which
+ * satisfies the following equation:
+ *     P = B & ~(1 << O)
+ *
+ * Assumption: *_mem_map is contiguous at least up to MAX_ORDER
+ */
+static inline unsigned long
+__find_buddy_index(unsigned long page_idx, unsigned int order)
+{
+	return page_idx ^ (1 << order);
+}
+
+extern int __isolate_free_page(struct page *page, unsigned int order);
 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
@@ -136,13 +161,10 @@ struct compact_control {
 	unsigned long migrate_pfn;	/* isolate_migratepages search base */
 	enum migrate_mode mode;		/* Async or sync migration mode */
 	bool ignore_skip_hint;		/* Scan blocks even if marked skip */
-	bool finished_update_free;	/* True when the zone cached pfns are
-					 * no longer being updated
-					 */
-	bool finished_update_migrate;
-
 	int order;			/* order a direct compactor needs */
 	const gfp_t gfp_mask;		/* gfp mask of a direct compactor */
+	const int alloc_flags;		/* alloc flags of a direct compactor */
+	const int classzone_idx;	/* zone index of a direct compactor */
 	struct zone *zone;
 	int contended;			/* Signal need_sched() or lock
 					 * contention detected during
diff --git a/mm/ksm.c b/mm/ksm.c
index 6b2e337bc03c..d247efab5073 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -892,7 +892,7 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page,
 		 * this assure us that no O_DIRECT can happen after the check
 		 * or in the middle of the check.
 		 */
-		entry = ptep_clear_flush(vma, addr, ptep);
+		entry = ptep_clear_flush_notify(vma, addr, ptep);
 		/*
 		 * Check that no O_DIRECT or similar I/O is in progress on the
 		 * page
@@ -960,7 +960,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page,
 	page_add_anon_rmap(kpage, vma, addr);
 
 	flush_cache_page(vma, addr, pte_pfn(*ptep));
-	ptep_clear_flush(vma, addr, ptep);
+	ptep_clear_flush_notify(vma, addr, ptep);
 	set_pte_at_notify(mm, addr, ptep, mk_pte(kpage, vma->vm_page_prot));
 
 	page_remove_rmap(page);
diff --git a/mm/memblock.c b/mm/memblock.c
index 6ecb0d937fb5..252b77bdf65e 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -715,16 +715,13 @@ int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size)
 }
 
 /**
- * memblock_mark_hotplug - Mark hotpluggable memory with flag MEMBLOCK_HOTPLUG.
- * @base: the base phys addr of the region
- * @size: the size of the region
  *
- * This function isolates region [@base, @base + @size), and mark it with flag
- * MEMBLOCK_HOTPLUG.
+ * This function isolates region [@base, @base + @size), and sets/clears flag
  *
  * Return 0 on succees, -errno on failure.
  */
-int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size)
+static int __init_memblock memblock_setclr_flag(phys_addr_t base,
+				phys_addr_t size, int set, int flag)
 {
 	struct memblock_type *type = &memblock.memory;
 	int i, ret, start_rgn, end_rgn;
@@ -734,37 +731,37 @@ int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size)
 		return ret;
 
 	for (i = start_rgn; i < end_rgn; i++)
-		memblock_set_region_flags(&type->regions[i], MEMBLOCK_HOTPLUG);
+		if (set)
+			memblock_set_region_flags(&type->regions[i], flag);
+		else
+			memblock_clear_region_flags(&type->regions[i], flag);
 
 	memblock_merge_regions(type);
 	return 0;
 }
 
 /**
- * memblock_clear_hotplug - Clear flag MEMBLOCK_HOTPLUG for a specified region.
+ * memblock_mark_hotplug - Mark hotpluggable memory with flag MEMBLOCK_HOTPLUG.
  * @base: the base phys addr of the region
  * @size: the size of the region
  *
- * This function isolates region [@base, @base + @size), and clear flag
- * MEMBLOCK_HOTPLUG for the isolated regions.
+ * Return 0 on succees, -errno on failure.
+ */
+int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size)
+{
+	return memblock_setclr_flag(base, size, 1, MEMBLOCK_HOTPLUG);
+}
+
+/**
+ * memblock_clear_hotplug - Clear flag MEMBLOCK_HOTPLUG for a specified region.
+ * @base: the base phys addr of the region
+ * @size: the size of the region
  *
  * Return 0 on succees, -errno on failure.
  */
 int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size)
 {
-	struct memblock_type *type = &memblock.memory;
-	int i, ret, start_rgn, end_rgn;
-
-	ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn);
-	if (ret)
-		return ret;
-
-	for (i = start_rgn; i < end_rgn; i++)
-		memblock_clear_region_flags(&type->regions[i],
-					    MEMBLOCK_HOTPLUG);
-
-	memblock_merge_regions(type);
-	return 0;
+	return memblock_setclr_flag(base, size, 0, MEMBLOCK_HOTPLUG);
 }
 
 /**
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ee48428cf8e3..5a27e224d561 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -25,7 +25,7 @@
  * GNU General Public License for more details.
  */
 
-#include <linux/res_counter.h>
+#include <linux/page_counter.h>
 #include <linux/memcontrol.h>
 #include <linux/cgroup.h>
 #include <linux/mm.h>
@@ -51,7 +51,7 @@
 #include <linux/seq_file.h>
 #include <linux/vmpressure.h>
 #include <linux/mm_inline.h>
-#include <linux/page_cgroup.h>
+#include <linux/swap_cgroup.h>
 #include <linux/cpu.h>
 #include <linux/oom.h>
 #include <linux/lockdep.h>
@@ -143,14 +143,8 @@ struct mem_cgroup_stat_cpu {
 	unsigned long targets[MEM_CGROUP_NTARGETS];
 };
 
-struct mem_cgroup_reclaim_iter {
-	/*
-	 * last scanned hierarchy member. Valid only if last_dead_count
-	 * matches memcg->dead_count of the hierarchy root group.
-	 */
-	struct mem_cgroup *last_visited;
-	int last_dead_count;
-
+struct reclaim_iter {
+	struct mem_cgroup *position;
 	/* scan generation, increased every round-trip */
 	unsigned int generation;
 };
@@ -162,10 +156,10 @@ struct mem_cgroup_per_zone {
 	struct lruvec		lruvec;
 	unsigned long		lru_size[NR_LRU_LISTS];
 
-	struct mem_cgroup_reclaim_iter reclaim_iter[DEF_PRIORITY + 1];
+	struct reclaim_iter	iter[DEF_PRIORITY + 1];
 
 	struct rb_node		tree_node;	/* RB tree node */
-	unsigned long long	usage_in_excess;/* Set to the value by which */
+	unsigned long		usage_in_excess;/* Set to the value by which */
 						/* the soft limit is exceeded*/
 	bool			on_tree;
 	struct mem_cgroup	*memcg;		/* Back pointer, we cannot */
@@ -198,7 +192,7 @@ static struct mem_cgroup_tree soft_limit_tree __read_mostly;
 
 struct mem_cgroup_threshold {
 	struct eventfd_ctx *eventfd;
-	u64 threshold;
+	unsigned long threshold;
 };
 
 /* For threshold */
@@ -284,10 +278,13 @@ static void mem_cgroup_oom_notify(struct mem_cgroup *memcg);
  */
 struct mem_cgroup {
 	struct cgroup_subsys_state css;
-	/*
-	 * the counter to account for memory usage
-	 */
-	struct res_counter res;
+
+	/* Accounted resources */
+	struct page_counter memory;
+	struct page_counter memsw;
+	struct page_counter kmem;
+
+	unsigned long soft_limit;
 
 	/* vmpressure notifications */
 	struct vmpressure vmpressure;
@@ -296,15 +293,6 @@ struct mem_cgroup {
 	int initialized;
 
 	/*
-	 * the counter to account for mem+swap usage.
-	 */
-	struct res_counter memsw;
-
-	/*
-	 * the counter to account for kernel memory usage.
-	 */
-	struct res_counter kmem;
-	/*
 	 * Should the accounting and control be hierarchical, per subtree?
 	 */
 	bool use_hierarchy;
@@ -352,7 +340,6 @@ struct mem_cgroup {
 	struct mem_cgroup_stat_cpu nocpu_base;
 	spinlock_t pcp_counter_lock;
 
-	atomic_t	dead_count;
 #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET)
 	struct cg_proto tcp_mem;
 #endif
@@ -382,7 +369,6 @@ struct mem_cgroup {
 /* internal only representation about the status of kmem accounting. */
 enum {
 	KMEM_ACCOUNTED_ACTIVE, /* accounted by this cgroup itself */
-	KMEM_ACCOUNTED_DEAD, /* dead memcg with pending kmem charges */
 };
 
 #ifdef CONFIG_MEMCG_KMEM
@@ -396,22 +382,6 @@ static bool memcg_kmem_is_active(struct mem_cgroup *memcg)
 	return test_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags);
 }
 
-static void memcg_kmem_mark_dead(struct mem_cgroup *memcg)
-{
-	/*
-	 * Our caller must use css_get() first, because memcg_uncharge_kmem()
-	 * will call css_put() if it sees the memcg is dead.
-	 */
-	smp_wmb();
-	if (test_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags))
-		set_bit(KMEM_ACCOUNTED_DEAD, &memcg->kmem_account_flags);
-}
-
-static bool memcg_kmem_test_and_clear_dead(struct mem_cgroup *memcg)
-{
-	return test_and_clear_bit(KMEM_ACCOUNTED_DEAD,
-				  &memcg->kmem_account_flags);
-}
 #endif
 
 /* Stuffs for move charges at task migration. */
@@ -650,7 +620,7 @@ static void disarm_kmem_keys(struct mem_cgroup *memcg)
 	 * This check can't live in kmem destruction function,
 	 * since the charges will outlive the cgroup
 	 */
-	WARN_ON(res_counter_read_u64(&memcg->kmem, RES_USAGE) != 0);
+	WARN_ON(page_counter_read(&memcg->kmem));
 }
 #else
 static void disarm_kmem_keys(struct mem_cgroup *memcg)
@@ -664,8 +634,6 @@ static void disarm_static_keys(struct mem_cgroup *memcg)
 	disarm_kmem_keys(memcg);
 }
 
-static void drain_all_stock_async(struct mem_cgroup *memcg);
-
 static struct mem_cgroup_per_zone *
 mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone)
 {
@@ -706,7 +674,7 @@ soft_limit_tree_from_page(struct page *page)
 
 static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_zone *mz,
 					 struct mem_cgroup_tree_per_zone *mctz,
-					 unsigned long long new_usage_in_excess)
+					 unsigned long new_usage_in_excess)
 {
 	struct rb_node **p = &mctz->rb_root.rb_node;
 	struct rb_node *parent = NULL;
@@ -755,10 +723,21 @@ static void mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz,
 	spin_unlock_irqrestore(&mctz->lock, flags);
 }
 
+static unsigned long soft_limit_excess(struct mem_cgroup *memcg)
+{
+	unsigned long nr_pages = page_counter_read(&memcg->memory);
+	unsigned long soft_limit = ACCESS_ONCE(memcg->soft_limit);
+	unsigned long excess = 0;
+
+	if (nr_pages > soft_limit)
+		excess = nr_pages - soft_limit;
+
+	return excess;
+}
 
 static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
 {
-	unsigned long long excess;
+	unsigned long excess;
 	struct mem_cgroup_per_zone *mz;
 	struct mem_cgroup_tree_per_zone *mctz;
 
@@ -769,7 +748,7 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
 	 */
 	for (; memcg; memcg = parent_mem_cgroup(memcg)) {
 		mz = mem_cgroup_page_zoneinfo(memcg, page);
-		excess = res_counter_soft_limit_excess(&memcg->res);
+		excess = soft_limit_excess(memcg);
 		/*
 		 * We have to update the tree if mz is on RB-tree or
 		 * mem is over its softlimit.
@@ -825,7 +804,7 @@ retry:
 	 * position in the tree.
 	 */
 	__mem_cgroup_remove_exceeded(mz, mctz);
-	if (!res_counter_soft_limit_excess(&mz->memcg->res) ||
+	if (!soft_limit_excess(mz->memcg) ||
 	    !css_tryget_online(&mz->memcg->css))
 		goto retry;
 done:
@@ -1062,122 +1041,6 @@ static struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
 	return memcg;
 }
 
-/*
- * Returns a next (in a pre-order walk) alive memcg (with elevated css
- * ref. count) or NULL if the whole root's subtree has been visited.
- *
- * helper function to be used by mem_cgroup_iter
- */
-static struct mem_cgroup *__mem_cgroup_iter_next(struct mem_cgroup *root,
-		struct mem_cgroup *last_visited)
-{
-	struct cgroup_subsys_state *prev_css, *next_css;
-
-	prev_css = last_visited ? &last_visited->css : NULL;
-skip_node:
-	next_css = css_next_descendant_pre(prev_css, &root->css);
-
-	/*
-	 * Even if we found a group we have to make sure it is
-	 * alive. css && !memcg means that the groups should be
-	 * skipped and we should continue the tree walk.
-	 * last_visited css is safe to use because it is
-	 * protected by css_get and the tree walk is rcu safe.
-	 *
-	 * We do not take a reference on the root of the tree walk
-	 * because we might race with the root removal when it would
-	 * be the only node in the iterated hierarchy and mem_cgroup_iter
-	 * would end up in an endless loop because it expects that at
-	 * least one valid node will be returned. Root cannot disappear
-	 * because caller of the iterator should hold it already so
-	 * skipping css reference should be safe.
-	 */
-	if (next_css) {
-		struct mem_cgroup *memcg = mem_cgroup_from_css(next_css);
-
-		if (next_css == &root->css)
-			return memcg;
-
-		if (css_tryget_online(next_css)) {
-			/*
-			 * Make sure the memcg is initialized:
-			 * mem_cgroup_css_online() orders the the
-			 * initialization against setting the flag.
-			 */
-			if (smp_load_acquire(&memcg->initialized))
-				return memcg;
-			css_put(next_css);
-		}
-
-		prev_css = next_css;
-		goto skip_node;
-	}
-
-	return NULL;
-}
-
-static void mem_cgroup_iter_invalidate(struct mem_cgroup *root)
-{
-	/*
-	 * When a group in the hierarchy below root is destroyed, the
-	 * hierarchy iterator can no longer be trusted since it might
-	 * have pointed to the destroyed group.  Invalidate it.
-	 */
-	atomic_inc(&root->dead_count);
-}
-
-static struct mem_cgroup *
-mem_cgroup_iter_load(struct mem_cgroup_reclaim_iter *iter,
-		     struct mem_cgroup *root,
-		     int *sequence)
-{
-	struct mem_cgroup *position = NULL;
-	/*
-	 * A cgroup destruction happens in two stages: offlining and
-	 * release.  They are separated by a RCU grace period.
-	 *
-	 * If the iterator is valid, we may still race with an
-	 * offlining.  The RCU lock ensures the object won't be
-	 * released, tryget will fail if we lost the race.
-	 */
-	*sequence = atomic_read(&root->dead_count);
-	if (iter->last_dead_count == *sequence) {
-		smp_rmb();
-		position = iter->last_visited;
-
-		/*
-		 * We cannot take a reference to root because we might race
-		 * with root removal and returning NULL would end up in
-		 * an endless loop on the iterator user level when root
-		 * would be returned all the time.
-		 */
-		if (position && position != root &&
-		    !css_tryget_online(&position->css))
-			position = NULL;
-	}
-	return position;
-}
-
-static void mem_cgroup_iter_update(struct mem_cgroup_reclaim_iter *iter,
-				   struct mem_cgroup *last_visited,
-				   struct mem_cgroup *new_position,
-				   struct mem_cgroup *root,
-				   int sequence)
-{
-	/* root reference counting symmetric to mem_cgroup_iter_load */
-	if (last_visited && last_visited != root)
-		css_put(&last_visited->css);
-	/*
-	 * We store the sequence count from the time @last_visited was
-	 * loaded successfully instead of rereading it here so that we
-	 * don't lose destruction events in between.  We could have
-	 * raced with the destruction of @new_position after all.
-	 */
-	iter->last_visited = new_position;
-	smp_wmb();
-	iter->last_dead_count = sequence;
-}
-
 /**
  * mem_cgroup_iter - iterate over memory cgroup hierarchy
  * @root: hierarchy root
@@ -1199,8 +1062,10 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 				   struct mem_cgroup *prev,
 				   struct mem_cgroup_reclaim_cookie *reclaim)
 {
+	struct reclaim_iter *uninitialized_var(iter);
+	struct cgroup_subsys_state *css = NULL;
 	struct mem_cgroup *memcg = NULL;
-	struct mem_cgroup *last_visited = NULL;
+	struct mem_cgroup *pos = NULL;
 
 	if (mem_cgroup_disabled())
 		return NULL;
@@ -1209,50 +1074,101 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 		root = root_mem_cgroup;
 
 	if (prev && !reclaim)
-		last_visited = prev;
+		pos = prev;
 
 	if (!root->use_hierarchy && root != root_mem_cgroup) {
 		if (prev)
-			goto out_css_put;
+			goto out;
 		return root;
 	}
 
 	rcu_read_lock();
-	while (!memcg) {
-		struct mem_cgroup_reclaim_iter *uninitialized_var(iter);
-		int uninitialized_var(seq);
-
-		if (reclaim) {
-			struct mem_cgroup_per_zone *mz;
-
-			mz = mem_cgroup_zone_zoneinfo(root, reclaim->zone);
-			iter = &mz->reclaim_iter[reclaim->priority];
-			if (prev && reclaim->generation != iter->generation) {
-				iter->last_visited = NULL;
-				goto out_unlock;
-			}
 
-			last_visited = mem_cgroup_iter_load(iter, root, &seq);
+	if (reclaim) {
+		struct mem_cgroup_per_zone *mz;
+
+		mz = mem_cgroup_zone_zoneinfo(root, reclaim->zone);
+		iter = &mz->iter[reclaim->priority];
+
+		if (prev && reclaim->generation != iter->generation)
+			goto out_unlock;
+
+		do {
+			pos = ACCESS_ONCE(iter->position);
+			/*
+			 * A racing update may change the position and
+			 * put the last reference, hence css_tryget(),
+			 * or retry to see the updated position.
+			 */
+		} while (pos && !css_tryget(&pos->css));
+	}
+
+	if (pos)
+		css = &pos->css;
+
+	for (;;) {
+		css = css_next_descendant_pre(css, &root->css);
+		if (!css) {
+			/*
+			 * Reclaimers share the hierarchy walk, and a
+			 * new one might jump in right at the end of
+			 * the hierarchy - make sure they see at least
+			 * one group and restart from the beginning.
+			 */
+			if (!prev)
+				continue;
+			break;
 		}
 
-		memcg = __mem_cgroup_iter_next(root, last_visited);
+		/*
+		 * Verify the css and acquire a reference.  The root
+		 * is provided by the caller, so we know it's alive
+		 * and kicking, and don't take an extra reference.
+		 */
+		memcg = mem_cgroup_from_css(css);
+
+		if (css == &root->css)
+			break;
 
-		if (reclaim) {
-			mem_cgroup_iter_update(iter, last_visited, memcg, root,
-					seq);
+		if (css_tryget(css)) {
+			/*
+			 * Make sure the memcg is initialized:
+			 * mem_cgroup_css_online() orders the the
+			 * initialization against setting the flag.
+			 */
+			if (smp_load_acquire(&memcg->initialized))
+				break;
 
-			if (!memcg)
-				iter->generation++;
-			else if (!prev && memcg)
-				reclaim->generation = iter->generation;
+			css_put(css);
 		}
 
-		if (prev && !memcg)
-			goto out_unlock;
+		memcg = NULL;
 	}
+
+	if (reclaim) {
+		if (cmpxchg(&iter->position, pos, memcg) == pos) {
+			if (memcg)
+				css_get(&memcg->css);
+			if (pos)
+				css_put(&pos->css);
+		}
+
+		/*
+		 * pairs with css_tryget when dereferencing iter->position
+		 * above.
+		 */
+		if (pos)
+			css_put(&pos->css);
+
+		if (!memcg)
+			iter->generation++;
+		else if (!prev)
+			reclaim->generation = iter->generation;
+	}
+
 out_unlock:
 	rcu_read_unlock();
-out_css_put:
+out:
 	if (prev && prev != root)
 		css_put(&prev->css);
 
@@ -1346,15 +1262,18 @@ out:
 }
 
 /**
- * mem_cgroup_page_lruvec - return lruvec for adding an lru page
+ * mem_cgroup_page_lruvec - return lruvec for isolating/putting an LRU page
  * @page: the page
  * @zone: zone of the page
+ *
+ * This function is only safe when following the LRU page isolation
+ * and putback protocol: the LRU lock must be held, and the page must
+ * either be PageLRU() or the caller must have isolated/allocated it.
  */
 struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone)
 {
 	struct mem_cgroup_per_zone *mz;
 	struct mem_cgroup *memcg;
-	struct page_cgroup *pc;
 	struct lruvec *lruvec;
 
 	if (mem_cgroup_disabled()) {
@@ -1362,20 +1281,13 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone)
 		goto out;
 	}
 
-	pc = lookup_page_cgroup(page);
-	memcg = pc->mem_cgroup;
-
+	memcg = page->mem_cgroup;
 	/*
-	 * Surreptitiously switch any uncharged offlist page to root:
-	 * an uncharged page off lru does nothing to secure
-	 * its former mem_cgroup from sudden removal.
-	 *
-	 * Our caller holds lru_lock, and PageCgroupUsed is updated
-	 * under page_cgroup lock: between them, they make all uses
-	 * of pc->mem_cgroup safe.
+	 * Swapcache readahead pages are added to the LRU - and
+	 * possibly migrated - before they are charged.
 	 */
-	if (!PageLRU(page) && !PageCgroupUsed(pc) && memcg != root_mem_cgroup)
-		pc->mem_cgroup = memcg = root_mem_cgroup;
+	if (!memcg)
+		memcg = root_mem_cgroup;
 
 	mz = mem_cgroup_page_zoneinfo(memcg, page);
 	lruvec = &mz->lruvec;
@@ -1414,41 +1326,24 @@ void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
 	VM_BUG_ON((long)(*lru_size) < 0);
 }
 
-/*
- * 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)
+bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, struct mem_cgroup *root)
 {
-	if (root_memcg == memcg)
+	if (root == memcg)
 		return true;
-	if (!root_memcg->use_hierarchy || !memcg)
+	if (!root->use_hierarchy)
 		return false;
-	return cgroup_is_descendant(memcg->css.cgroup, root_memcg->css.cgroup);
+	return cgroup_is_descendant(memcg->css.cgroup, root->css.cgroup);
 }
 
-static bool mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg,
-				       struct mem_cgroup *memcg)
+bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg)
 {
-	bool ret;
-
-	rcu_read_lock();
-	ret = __mem_cgroup_same_or_subtree(root_memcg, memcg);
-	rcu_read_unlock();
-	return ret;
-}
-
-bool task_in_mem_cgroup(struct task_struct *task,
-			const struct mem_cgroup *memcg)
-{
-	struct mem_cgroup *curr = NULL;
+	struct mem_cgroup *task_memcg;
 	struct task_struct *p;
 	bool ret;
 
 	p = find_lock_task_mm(task);
 	if (p) {
-		curr = get_mem_cgroup_from_mm(p->mm);
+		task_memcg = get_mem_cgroup_from_mm(p->mm);
 		task_unlock(p);
 	} else {
 		/*
@@ -1457,19 +1352,12 @@ bool task_in_mem_cgroup(struct task_struct *task,
 		 * killed to prevent needlessly killing additional tasks.
 		 */
 		rcu_read_lock();
-		curr = mem_cgroup_from_task(task);
-		if (curr)
-			css_get(&curr->css);
+		task_memcg = mem_cgroup_from_task(task);
+		css_get(&task_memcg->css);
 		rcu_read_unlock();
 	}
-	/*
-	 * We should check use_hierarchy of "memcg" not "curr". Because checking
-	 * use_hierarchy of "curr" here make this function true if hierarchy is
-	 * enabled in "curr" and "curr" is a child of "memcg" in *cgroup*
-	 * hierarchy(even if use_hierarchy is disabled in "memcg").
-	 */
-	ret = mem_cgroup_same_or_subtree(memcg, curr);
-	css_put(&curr->css);
+	ret = mem_cgroup_is_descendant(task_memcg, memcg);
+	css_put(&task_memcg->css);
 	return ret;
 }
 
@@ -1492,7 +1380,7 @@ int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec)
 	return inactive * inactive_ratio < active;
 }
 
-#define mem_cgroup_from_res_counter(counter, member)	\
+#define mem_cgroup_from_counter(counter, member)	\
 	container_of(counter, struct mem_cgroup, member)
 
 /**
@@ -1504,12 +1392,23 @@ int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec)
  */
 static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg)
 {
-	unsigned long long margin;
+	unsigned long margin = 0;
+	unsigned long count;
+	unsigned long limit;
 
-	margin = res_counter_margin(&memcg->res);
-	if (do_swap_account)
-		margin = min(margin, res_counter_margin(&memcg->memsw));
-	return margin >> PAGE_SHIFT;
+	count = page_counter_read(&memcg->memory);
+	limit = ACCESS_ONCE(memcg->memory.limit);
+	if (count < limit)
+		margin = limit - count;
+
+	if (do_swap_account) {
+		count = page_counter_read(&memcg->memsw);
+		limit = ACCESS_ONCE(memcg->memsw.limit);
+		if (count <= limit)
+			margin = min(margin, limit - count);
+	}
+
+	return margin;
 }
 
 int mem_cgroup_swappiness(struct mem_cgroup *memcg)
@@ -1522,37 +1421,6 @@ int mem_cgroup_swappiness(struct mem_cgroup *memcg)
 }
 
 /*
- * memcg->moving_account is used for checking possibility that some thread is
- * calling move_account(). When a thread on CPU-A starts moving pages under
- * a memcg, other threads should check memcg->moving_account under
- * rcu_read_lock(), like this:
- *
- *         CPU-A                                    CPU-B
- *                                              rcu_read_lock()
- *         memcg->moving_account+1              if (memcg->mocing_account)
- *                                                   take heavy locks.
- *         synchronize_rcu()                    update something.
- *                                              rcu_read_unlock()
- *         start move here.
- */
-
-static void mem_cgroup_start_move(struct mem_cgroup *memcg)
-{
-	atomic_inc(&memcg->moving_account);
-	synchronize_rcu();
-}
-
-static void mem_cgroup_end_move(struct mem_cgroup *memcg)
-{
-	/*
-	 * Now, mem_cgroup_clear_mc() may call this function with NULL.
-	 * We check NULL in callee rather than caller.
-	 */
-	if (memcg)
-		atomic_dec(&memcg->moving_account);
-}
-
-/*
  * A routine for checking "mem" is under move_account() or not.
  *
  * Checking a cgroup is mc.from or mc.to or under hierarchy of
@@ -1574,8 +1442,8 @@ static bool mem_cgroup_under_move(struct mem_cgroup *memcg)
 	if (!from)
 		goto unlock;
 
-	ret = mem_cgroup_same_or_subtree(memcg, from)
-		|| mem_cgroup_same_or_subtree(memcg, to);
+	ret = mem_cgroup_is_descendant(from, memcg) ||
+		mem_cgroup_is_descendant(to, memcg);
 unlock:
 	spin_unlock(&mc.lock);
 	return ret;
@@ -1597,23 +1465,6 @@ static bool mem_cgroup_wait_acct_move(struct mem_cgroup *memcg)
 	return false;
 }
 
-/*
- * Take this lock when
- * - a code tries to modify page's memcg while it's USED.
- * - a code tries to modify page state accounting in a memcg.
- */
-static void move_lock_mem_cgroup(struct mem_cgroup *memcg,
-				  unsigned long *flags)
-{
-	spin_lock_irqsave(&memcg->move_lock, *flags);
-}
-
-static void move_unlock_mem_cgroup(struct mem_cgroup *memcg,
-				unsigned long *flags)
-{
-	spin_unlock_irqrestore(&memcg->move_lock, *flags);
-}
-
 #define K(x) ((x) << (PAGE_SHIFT-10))
 /**
  * mem_cgroup_print_oom_info: Print OOM information relevant to memory controller.
@@ -1644,18 +1495,15 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 
 	rcu_read_unlock();
 
-	pr_info("memory: usage %llukB, limit %llukB, failcnt %llu\n",
-		res_counter_read_u64(&memcg->res, RES_USAGE) >> 10,
-		res_counter_read_u64(&memcg->res, RES_LIMIT) >> 10,
-		res_counter_read_u64(&memcg->res, RES_FAILCNT));
-	pr_info("memory+swap: usage %llukB, limit %llukB, failcnt %llu\n",
-		res_counter_read_u64(&memcg->memsw, RES_USAGE) >> 10,
-		res_counter_read_u64(&memcg->memsw, RES_LIMIT) >> 10,
-		res_counter_read_u64(&memcg->memsw, RES_FAILCNT));
-	pr_info("kmem: usage %llukB, limit %llukB, failcnt %llu\n",
-		res_counter_read_u64(&memcg->kmem, RES_USAGE) >> 10,
-		res_counter_read_u64(&memcg->kmem, RES_LIMIT) >> 10,
-		res_counter_read_u64(&memcg->kmem, RES_FAILCNT));
+	pr_info("memory: usage %llukB, limit %llukB, failcnt %lu\n",
+		K((u64)page_counter_read(&memcg->memory)),
+		K((u64)memcg->memory.limit), memcg->memory.failcnt);
+	pr_info("memory+swap: usage %llukB, limit %llukB, failcnt %lu\n",
+		K((u64)page_counter_read(&memcg->memsw)),
+		K((u64)memcg->memsw.limit), memcg->memsw.failcnt);
+	pr_info("kmem: usage %llukB, limit %llukB, failcnt %lu\n",
+		K((u64)page_counter_read(&memcg->kmem)),
+		K((u64)memcg->kmem.limit), memcg->kmem.failcnt);
 
 	for_each_mem_cgroup_tree(iter, memcg) {
 		pr_info("Memory cgroup stats for ");
@@ -1695,28 +1543,17 @@ static int mem_cgroup_count_children(struct mem_cgroup *memcg)
 /*
  * Return the memory (and swap, if configured) limit for a memcg.
  */
-static u64 mem_cgroup_get_limit(struct mem_cgroup *memcg)
+static unsigned long mem_cgroup_get_limit(struct mem_cgroup *memcg)
 {
-	u64 limit;
-
-	limit = res_counter_read_u64(&memcg->res, RES_LIMIT);
+	unsigned long limit;
 
-	/*
-	 * Do not consider swap space if we cannot swap due to swappiness
-	 */
+	limit = memcg->memory.limit;
 	if (mem_cgroup_swappiness(memcg)) {
-		u64 memsw;
+		unsigned long memsw_limit;
 
-		limit += total_swap_pages << PAGE_SHIFT;
-		memsw = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
-
-		/*
-		 * If memsw is finite and limits the amount of swap space
-		 * available to this memcg, return that limit.
-		 */
-		limit = min(limit, memsw);
+		memsw_limit = memcg->memsw.limit;
+		limit = min(limit + total_swap_pages, memsw_limit);
 	}
-
 	return limit;
 }
 
@@ -1740,7 +1577,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	}
 
 	check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL);
-	totalpages = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT ? : 1;
+	totalpages = mem_cgroup_get_limit(memcg) ? : 1;
 	for_each_mem_cgroup_tree(iter, memcg) {
 		struct css_task_iter it;
 		struct task_struct *task;
@@ -1880,52 +1717,11 @@ int mem_cgroup_select_victim_node(struct mem_cgroup *memcg)
 	memcg->last_scanned_node = node;
 	return node;
 }
-
-/*
- * Check all nodes whether it contains reclaimable pages or not.
- * For quick scan, we make use of scan_nodes. This will allow us to skip
- * unused nodes. But scan_nodes is lazily updated and may not cotain
- * enough new information. We need to do double check.
- */
-static bool mem_cgroup_reclaimable(struct mem_cgroup *memcg, bool noswap)
-{
-	int nid;
-
-	/*
-	 * quick check...making use of scan_node.
-	 * We can skip unused nodes.
-	 */
-	if (!nodes_empty(memcg->scan_nodes)) {
-		for (nid = first_node(memcg->scan_nodes);
-		     nid < MAX_NUMNODES;
-		     nid = next_node(nid, memcg->scan_nodes)) {
-
-			if (test_mem_cgroup_node_reclaimable(memcg, nid, noswap))
-				return true;
-		}
-	}
-	/*
-	 * Check rest of nodes.
-	 */
-	for_each_node_state(nid, N_MEMORY) {
-		if (node_isset(nid, memcg->scan_nodes))
-			continue;
-		if (test_mem_cgroup_node_reclaimable(memcg, nid, noswap))
-			return true;
-	}
-	return false;
-}
-
 #else
 int mem_cgroup_select_victim_node(struct mem_cgroup *memcg)
 {
 	return 0;
 }
-
-static bool mem_cgroup_reclaimable(struct mem_cgroup *memcg, bool noswap)
-{
-	return test_mem_cgroup_node_reclaimable(memcg, 0, noswap);
-}
 #endif
 
 static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
@@ -1943,7 +1739,7 @@ static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
 		.priority = 0,
 	};
 
-	excess = res_counter_soft_limit_excess(&root_memcg->res) >> PAGE_SHIFT;
+	excess = soft_limit_excess(root_memcg);
 
 	while (1) {
 		victim = mem_cgroup_iter(root_memcg, victim, &reclaim);
@@ -1969,12 +1765,10 @@ static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
 			}
 			continue;
 		}
-		if (!mem_cgroup_reclaimable(victim, false))
-			continue;
 		total += mem_cgroup_shrink_node_zone(victim, gfp_mask, false,
 						     zone, &nr_scanned);
 		*total_scanned += nr_scanned;
-		if (!res_counter_soft_limit_excess(&root_memcg->res))
+		if (!soft_limit_excess(root_memcg))
 			break;
 	}
 	mem_cgroup_iter_break(root_memcg, victim);
@@ -2081,12 +1875,8 @@ static int memcg_oom_wake_function(wait_queue_t *wait,
 	oom_wait_info = container_of(wait, struct oom_wait_info, wait);
 	oom_wait_memcg = oom_wait_info->memcg;
 
-	/*
-	 * Both of oom_wait_info->memcg and wake_memcg are stable under us.
-	 * Then we can use css_is_ancestor without taking care of RCU.
-	 */
-	if (!mem_cgroup_same_or_subtree(oom_wait_memcg, wake_memcg)
-		&& !mem_cgroup_same_or_subtree(wake_memcg, oom_wait_memcg))
+	if (!mem_cgroup_is_descendant(wake_memcg, oom_wait_memcg) &&
+	    !mem_cgroup_is_descendant(oom_wait_memcg, wake_memcg))
 		return 0;
 	return autoremove_wake_function(wait, mode, sync, arg);
 }
@@ -2228,26 +2018,23 @@ struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page,
 					      unsigned long *flags)
 {
 	struct mem_cgroup *memcg;
-	struct page_cgroup *pc;
 
 	rcu_read_lock();
 
 	if (mem_cgroup_disabled())
 		return NULL;
-
-	pc = lookup_page_cgroup(page);
 again:
-	memcg = pc->mem_cgroup;
-	if (unlikely(!memcg || !PageCgroupUsed(pc)))
+	memcg = page->mem_cgroup;
+	if (unlikely(!memcg))
 		return NULL;
 
 	*locked = false;
 	if (atomic_read(&memcg->moving_account) <= 0)
 		return memcg;
 
-	move_lock_mem_cgroup(memcg, flags);
-	if (memcg != pc->mem_cgroup || !PageCgroupUsed(pc)) {
-		move_unlock_mem_cgroup(memcg, flags);
+	spin_lock_irqsave(&memcg->move_lock, *flags);
+	if (memcg != page->mem_cgroup) {
+		spin_unlock_irqrestore(&memcg->move_lock, *flags);
 		goto again;
 	}
 	*locked = true;
@@ -2261,11 +2048,11 @@ again:
  * @locked: value received from mem_cgroup_begin_page_stat()
  * @flags: value received from mem_cgroup_begin_page_stat()
  */
-void mem_cgroup_end_page_stat(struct mem_cgroup *memcg, bool locked,
-			      unsigned long flags)
+void mem_cgroup_end_page_stat(struct mem_cgroup *memcg, bool *locked,
+			      unsigned long *flags)
 {
-	if (memcg && locked)
-		move_unlock_mem_cgroup(memcg, &flags);
+	if (memcg && *locked)
+		spin_unlock_irqrestore(&memcg->move_lock, *flags);
 
 	rcu_read_unlock();
 }
@@ -2316,33 +2103,32 @@ static DEFINE_MUTEX(percpu_charge_mutex);
 static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 {
 	struct memcg_stock_pcp *stock;
-	bool ret = true;
+	bool ret = false;
 
 	if (nr_pages > CHARGE_BATCH)
-		return false;
+		return ret;
 
 	stock = &get_cpu_var(memcg_stock);
-	if (memcg == stock->cached && stock->nr_pages >= nr_pages)
+	if (memcg == stock->cached && stock->nr_pages >= nr_pages) {
 		stock->nr_pages -= nr_pages;
-	else /* need to call res_counter_charge */
-		ret = false;
+		ret = true;
+	}
 	put_cpu_var(memcg_stock);
 	return ret;
 }
 
 /*
- * Returns stocks cached in percpu to res_counter and reset cached information.
+ * Returns stocks cached in percpu and reset cached information.
  */
 static void drain_stock(struct memcg_stock_pcp *stock)
 {
 	struct mem_cgroup *old = stock->cached;
 
 	if (stock->nr_pages) {
-		unsigned long bytes = stock->nr_pages * PAGE_SIZE;
-
-		res_counter_uncharge(&old->res, bytes);
+		page_counter_uncharge(&old->memory, stock->nr_pages);
 		if (do_swap_account)
-			res_counter_uncharge(&old->memsw, bytes);
+			page_counter_uncharge(&old->memsw, stock->nr_pages);
+		css_put_many(&old->css, stock->nr_pages);
 		stock->nr_pages = 0;
 	}
 	stock->cached = NULL;
@@ -2371,7 +2157,7 @@ static void __init memcg_stock_init(void)
 }
 
 /*
- * Cache charges(val) which is from res_counter, to local per_cpu area.
+ * Cache charges(val) to local per_cpu area.
  * This will be consumed by consume_stock() function, later.
  */
 static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
@@ -2388,13 +2174,15 @@ static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 
 /*
  * Drains all per-CPU charge caches for given root_memcg resp. subtree
- * of the hierarchy under it. sync flag says whether we should block
- * until the work is done.
+ * of the hierarchy under it.
  */
-static void drain_all_stock(struct mem_cgroup *root_memcg, bool sync)
+static void drain_all_stock(struct mem_cgroup *root_memcg)
 {
 	int cpu, curcpu;
 
+	/* If someone's already draining, avoid adding running more workers. */
+	if (!mutex_trylock(&percpu_charge_mutex))
+		return;
 	/* Notify other cpus that system-wide "drain" is running */
 	get_online_cpus();
 	curcpu = get_cpu();
@@ -2405,7 +2193,7 @@ static void drain_all_stock(struct mem_cgroup *root_memcg, bool sync)
 		memcg = stock->cached;
 		if (!memcg || !stock->nr_pages)
 			continue;
-		if (!mem_cgroup_same_or_subtree(root_memcg, memcg))
+		if (!mem_cgroup_is_descendant(memcg, root_memcg))
 			continue;
 		if (!test_and_set_bit(FLUSHING_CACHED_CHARGE, &stock->flags)) {
 			if (cpu == curcpu)
@@ -2415,42 +2203,7 @@ static void drain_all_stock(struct mem_cgroup *root_memcg, bool sync)
 		}
 	}
 	put_cpu();
-
-	if (!sync)
-		goto out;
-
-	for_each_online_cpu(cpu) {
-		struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu);
-		if (test_bit(FLUSHING_CACHED_CHARGE, &stock->flags))
-			flush_work(&stock->work);
-	}
-out:
 	put_online_cpus();
-}
-
-/*
- * Tries to drain stocked charges in other cpus. This function is asynchronous
- * and just put a work per cpu for draining localy on each cpu. Caller can
- * expects some charges will be back to res_counter later but cannot wait for
- * it.
- */
-static void drain_all_stock_async(struct mem_cgroup *root_memcg)
-{
-	/*
-	 * If someone calls draining, avoid adding more kworker runs.
-	 */
-	if (!mutex_trylock(&percpu_charge_mutex))
-		return;
-	drain_all_stock(root_memcg, false);
-	mutex_unlock(&percpu_charge_mutex);
-}
-
-/* This is a synchronous drain interface. */
-static void drain_all_stock_sync(struct mem_cgroup *root_memcg)
-{
-	/* called when force_empty is called */
-	mutex_lock(&percpu_charge_mutex);
-	drain_all_stock(root_memcg, true);
 	mutex_unlock(&percpu_charge_mutex);
 }
 
@@ -2506,9 +2259,8 @@ static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	unsigned int batch = max(CHARGE_BATCH, nr_pages);
 	int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
 	struct mem_cgroup *mem_over_limit;
-	struct res_counter *fail_res;
+	struct page_counter *counter;
 	unsigned long nr_reclaimed;
-	unsigned long long size;
 	bool may_swap = true;
 	bool drained = false;
 	int ret = 0;
@@ -2519,16 +2271,15 @@ retry:
 	if (consume_stock(memcg, nr_pages))
 		goto done;
 
-	size = batch * PAGE_SIZE;
 	if (!do_swap_account ||
-	    !res_counter_charge(&memcg->memsw, size, &fail_res)) {
-		if (!res_counter_charge(&memcg->res, size, &fail_res))
+	    !page_counter_try_charge(&memcg->memsw, batch, &counter)) {
+		if (!page_counter_try_charge(&memcg->memory, batch, &counter))
 			goto done_restock;
 		if (do_swap_account)
-			res_counter_uncharge(&memcg->memsw, size);
-		mem_over_limit = mem_cgroup_from_res_counter(fail_res, res);
+			page_counter_uncharge(&memcg->memsw, batch);
+		mem_over_limit = mem_cgroup_from_counter(counter, memory);
 	} else {
-		mem_over_limit = mem_cgroup_from_res_counter(fail_res, memsw);
+		mem_over_limit = mem_cgroup_from_counter(counter, memsw);
 		may_swap = false;
 	}
 
@@ -2561,7 +2312,7 @@ retry:
 		goto retry;
 
 	if (!drained) {
-		drain_all_stock_async(mem_over_limit);
+		drain_all_stock(mem_over_limit);
 		drained = true;
 		goto retry;
 	}
@@ -2603,6 +2354,7 @@ bypass:
 	return -EINTR;
 
 done_restock:
+	css_get_many(&memcg->css, batch);
 	if (batch > nr_pages)
 		refill_stock(memcg, batch - nr_pages);
 done:
@@ -2611,32 +2363,14 @@ done:
 
 static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
 {
-	unsigned long bytes = nr_pages * PAGE_SIZE;
-
 	if (mem_cgroup_is_root(memcg))
 		return;
 
-	res_counter_uncharge(&memcg->res, bytes);
+	page_counter_uncharge(&memcg->memory, nr_pages);
 	if (do_swap_account)
-		res_counter_uncharge(&memcg->memsw, bytes);
-}
-
-/*
- * Cancel chrages in this cgroup....doesn't propagate to parent cgroup.
- * This is useful when moving usage to parent cgroup.
- */
-static void __mem_cgroup_cancel_local_charge(struct mem_cgroup *memcg,
-					unsigned int nr_pages)
-{
-	unsigned long bytes = nr_pages * PAGE_SIZE;
-
-	if (mem_cgroup_is_root(memcg))
-		return;
+		page_counter_uncharge(&memcg->memsw, nr_pages);
 
-	res_counter_uncharge_until(&memcg->res, memcg->res.parent, bytes);
-	if (do_swap_account)
-		res_counter_uncharge_until(&memcg->memsw,
-						memcg->memsw.parent, bytes);
+	css_put_many(&memcg->css, nr_pages);
 }
 
 /*
@@ -2665,17 +2399,15 @@ static struct mem_cgroup *mem_cgroup_lookup(unsigned short id)
  */
 struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
 {
-	struct mem_cgroup *memcg = NULL;
-	struct page_cgroup *pc;
+	struct mem_cgroup *memcg;
 	unsigned short id;
 	swp_entry_t ent;
 
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 
-	pc = lookup_page_cgroup(page);
-	if (PageCgroupUsed(pc)) {
-		memcg = pc->mem_cgroup;
-		if (memcg && !css_tryget_online(&memcg->css))
+	memcg = page->mem_cgroup;
+	if (memcg) {
+		if (!css_tryget_online(&memcg->css))
 			memcg = NULL;
 	} else if (PageSwapCache(page)) {
 		ent.val = page_private(page);
@@ -2723,14 +2455,9 @@ static void unlock_page_lru(struct page *page, int isolated)
 static void commit_charge(struct page *page, struct mem_cgroup *memcg,
 			  bool lrucare)
 {
-	struct page_cgroup *pc = lookup_page_cgroup(page);
 	int isolated;
 
-	VM_BUG_ON_PAGE(PageCgroupUsed(pc), page);
-	/*
-	 * we don't need page_cgroup_lock about tail pages, becase they are not
-	 * accessed by any other context at this point.
-	 */
+	VM_BUG_ON_PAGE(page->mem_cgroup, page);
 
 	/*
 	 * In some cases, SwapCache and FUSE(splice_buf->radixtree), the page
@@ -2741,7 +2468,7 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg,
 
 	/*
 	 * Nobody should be changing or seriously looking at
-	 * pc->mem_cgroup and pc->flags at this point:
+	 * page->mem_cgroup at this point:
 	 *
 	 * - the page is uncharged
 	 *
@@ -2753,15 +2480,12 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg,
 	 * - a page cache insertion, a swapin fault, or a migration
 	 *   have the page locked
 	 */
-	pc->mem_cgroup = memcg;
-	pc->flags = PCG_USED | PCG_MEM | (do_swap_account ? PCG_MEMSW : 0);
+	page->mem_cgroup = memcg;
 
 	if (lrucare)
 		unlock_page_lru(page, isolated);
 }
 
-static DEFINE_MUTEX(set_limit_mutex);
-
 #ifdef CONFIG_MEMCG_KMEM
 /*
  * The memcg_slab_mutex is held whenever a per memcg kmem cache is created or
@@ -2769,8 +2493,6 @@ static DEFINE_MUTEX(set_limit_mutex);
  */
 static DEFINE_MUTEX(memcg_slab_mutex);
 
-static DEFINE_MUTEX(activate_kmem_mutex);
-
 /*
  * This is a bit cumbersome, but it is rarely used and avoids a backpointer
  * in the memcg_cache_params struct.
@@ -2784,36 +2506,17 @@ static struct kmem_cache *memcg_params_to_cache(struct memcg_cache_params *p)
 	return cache_from_memcg_idx(cachep, memcg_cache_id(p->memcg));
 }
 
-#ifdef CONFIG_SLABINFO
-static int mem_cgroup_slabinfo_read(struct seq_file *m, void *v)
-{
-	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
-	struct memcg_cache_params *params;
-
-	if (!memcg_kmem_is_active(memcg))
-		return -EIO;
-
-	print_slabinfo_header(m);
-
-	mutex_lock(&memcg_slab_mutex);
-	list_for_each_entry(params, &memcg->memcg_slab_caches, list)
-		cache_show(memcg_params_to_cache(params), m);
-	mutex_unlock(&memcg_slab_mutex);
-
-	return 0;
-}
-#endif
-
-static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size)
+static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp,
+			     unsigned long nr_pages)
 {
-	struct res_counter *fail_res;
+	struct page_counter *counter;
 	int ret = 0;
 
-	ret = res_counter_charge(&memcg->kmem, size, &fail_res);
-	if (ret)
+	ret = page_counter_try_charge(&memcg->kmem, nr_pages, &counter);
+	if (ret < 0)
 		return ret;
 
-	ret = try_charge(memcg, gfp, size >> PAGE_SHIFT);
+	ret = try_charge(memcg, gfp, nr_pages);
 	if (ret == -EINTR)  {
 		/*
 		 * try_charge() chose to bypass to root due to OOM kill or
@@ -2830,37 +2533,27 @@ static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size)
 		 * when the allocation triggers should have been already
 		 * directed to the root cgroup in memcontrol.h
 		 */
-		res_counter_charge_nofail(&memcg->res, size, &fail_res);
+		page_counter_charge(&memcg->memory, nr_pages);
 		if (do_swap_account)
-			res_counter_charge_nofail(&memcg->memsw, size,
-						  &fail_res);
+			page_counter_charge(&memcg->memsw, nr_pages);
+		css_get_many(&memcg->css, nr_pages);
 		ret = 0;
 	} else if (ret)
-		res_counter_uncharge(&memcg->kmem, size);
+		page_counter_uncharge(&memcg->kmem, nr_pages);
 
 	return ret;
 }
 
-static void memcg_uncharge_kmem(struct mem_cgroup *memcg, u64 size)
+static void memcg_uncharge_kmem(struct mem_cgroup *memcg,
+				unsigned long nr_pages)
 {
-	res_counter_uncharge(&memcg->res, size);
+	page_counter_uncharge(&memcg->memory, nr_pages);
 	if (do_swap_account)
-		res_counter_uncharge(&memcg->memsw, size);
+		page_counter_uncharge(&memcg->memsw, nr_pages);
 
-	/* Not down to 0 */
-	if (res_counter_uncharge(&memcg->kmem, size))
-		return;
+	page_counter_uncharge(&memcg->kmem, nr_pages);
 
-	/*
-	 * Releases a reference taken in kmem_cgroup_css_offline in case
-	 * this last uncharge is racing with the offlining code or it is
-	 * outliving the memcg existence.
-	 *
-	 * The memory barrier imposed by test&clear is paired with the
-	 * explicit one in memcg_kmem_mark_dead().
-	 */
-	if (memcg_kmem_test_and_clear_dead(memcg))
-		css_put(&memcg->css);
+	css_put_many(&memcg->css, nr_pages);
 }
 
 /*
@@ -3124,19 +2817,21 @@ static void memcg_schedule_register_cache(struct mem_cgroup *memcg,
 
 int __memcg_charge_slab(struct kmem_cache *cachep, gfp_t gfp, int order)
 {
+	unsigned int nr_pages = 1 << order;
 	int res;
 
-	res = memcg_charge_kmem(cachep->memcg_params->memcg, gfp,
-				PAGE_SIZE << order);
+	res = memcg_charge_kmem(cachep->memcg_params->memcg, gfp, nr_pages);
 	if (!res)
-		atomic_add(1 << order, &cachep->memcg_params->nr_pages);
+		atomic_add(nr_pages, &cachep->memcg_params->nr_pages);
 	return res;
 }
 
 void __memcg_uncharge_slab(struct kmem_cache *cachep, int order)
 {
-	memcg_uncharge_kmem(cachep->memcg_params->memcg, PAGE_SIZE << order);
-	atomic_sub(1 << order, &cachep->memcg_params->nr_pages);
+	unsigned int nr_pages = 1 << order;
+
+	memcg_uncharge_kmem(cachep->memcg_params->memcg, nr_pages);
+	atomic_sub(nr_pages, &cachep->memcg_params->nr_pages);
 }
 
 /*
@@ -3161,7 +2856,7 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep,
 	VM_BUG_ON(!cachep->memcg_params);
 	VM_BUG_ON(!cachep->memcg_params->is_root_cache);
 
-	if (!current->mm || current->memcg_kmem_skip_account)
+	if (current->memcg_kmem_skip_account)
 		return cachep;
 
 	rcu_read_lock();
@@ -3247,7 +2942,7 @@ __memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **_memcg, int order)
 	 * allocations are extremely rare but can happen, for instance, for the
 	 * cache arrays. We bring this test here.
 	 */
-	if (!current->mm || current->memcg_kmem_skip_account)
+	if (current->memcg_kmem_skip_account)
 		return true;
 
 	memcg = get_mem_cgroup_from_mm(current->mm);
@@ -3257,7 +2952,7 @@ __memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **_memcg, int order)
 		return true;
 	}
 
-	ret = memcg_charge_kmem(memcg, gfp, PAGE_SIZE << order);
+	ret = memcg_charge_kmem(memcg, gfp, 1 << order);
 	if (!ret)
 		*_memcg = memcg;
 
@@ -3268,46 +2963,27 @@ __memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **_memcg, int order)
 void __memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg,
 			      int order)
 {
-	struct page_cgroup *pc;
-
 	VM_BUG_ON(mem_cgroup_is_root(memcg));
 
 	/* The page allocation failed. Revert */
 	if (!page) {
-		memcg_uncharge_kmem(memcg, PAGE_SIZE << order);
+		memcg_uncharge_kmem(memcg, 1 << order);
 		return;
 	}
-	/*
-	 * The page is freshly allocated and not visible to any
-	 * outside callers yet.  Set up pc non-atomically.
-	 */
-	pc = lookup_page_cgroup(page);
-	pc->mem_cgroup = memcg;
-	pc->flags = PCG_USED;
+	page->mem_cgroup = memcg;
 }
 
 void __memcg_kmem_uncharge_pages(struct page *page, int order)
 {
-	struct mem_cgroup *memcg = NULL;
-	struct page_cgroup *pc;
-
+	struct mem_cgroup *memcg = page->mem_cgroup;
 
-	pc = lookup_page_cgroup(page);
-	if (!PageCgroupUsed(pc))
-		return;
-
-	memcg = pc->mem_cgroup;
-	pc->flags = 0;
-
-	/*
-	 * We trust that only if there is a memcg associated with the page, it
-	 * is a valid allocation
-	 */
 	if (!memcg)
 		return;
 
 	VM_BUG_ON_PAGE(mem_cgroup_is_root(memcg), page);
-	memcg_uncharge_kmem(memcg, PAGE_SIZE << order);
+
+	memcg_uncharge_kmem(memcg, 1 << order);
+	page->mem_cgroup = NULL;
 }
 #else
 static inline void memcg_unregister_all_caches(struct mem_cgroup *memcg)
@@ -3325,21 +3001,15 @@ static inline void memcg_unregister_all_caches(struct mem_cgroup *memcg)
  */
 void mem_cgroup_split_huge_fixup(struct page *head)
 {
-	struct page_cgroup *head_pc = lookup_page_cgroup(head);
-	struct page_cgroup *pc;
-	struct mem_cgroup *memcg;
 	int i;
 
 	if (mem_cgroup_disabled())
 		return;
 
-	memcg = head_pc->mem_cgroup;
-	for (i = 1; i < HPAGE_PMD_NR; i++) {
-		pc = head_pc + i;
-		pc->mem_cgroup = memcg;
-		pc->flags = head_pc->flags;
-	}
-	__this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_RSS_HUGE],
+	for (i = 1; i < HPAGE_PMD_NR; i++)
+		head[i].mem_cgroup = head->mem_cgroup;
+
+	__this_cpu_sub(head->mem_cgroup->stat->count[MEM_CGROUP_STAT_RSS_HUGE],
 		       HPAGE_PMD_NR);
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
@@ -3348,7 +3018,6 @@ void mem_cgroup_split_huge_fixup(struct page *head)
  * mem_cgroup_move_account - move account of the page
  * @page: the page
  * @nr_pages: number of regular pages (>1 for huge pages)
- * @pc:	page_cgroup of the page.
  * @from: mem_cgroup which the page is moved from.
  * @to:	mem_cgroup which the page is moved to. @from != @to.
  *
@@ -3361,7 +3030,6 @@ void mem_cgroup_split_huge_fixup(struct page *head)
  */
 static int mem_cgroup_move_account(struct page *page,
 				   unsigned int nr_pages,
-				   struct page_cgroup *pc,
 				   struct mem_cgroup *from,
 				   struct mem_cgroup *to)
 {
@@ -3381,7 +3049,7 @@ static int mem_cgroup_move_account(struct page *page,
 		goto out;
 
 	/*
-	 * Prevent mem_cgroup_migrate() from looking at pc->mem_cgroup
+	 * Prevent mem_cgroup_migrate() from looking at page->mem_cgroup
 	 * of its source page while we change it: page migration takes
 	 * both pages off the LRU, but page cache replacement doesn't.
 	 */
@@ -3389,10 +3057,10 @@ static int mem_cgroup_move_account(struct page *page,
 		goto out;
 
 	ret = -EINVAL;
-	if (!PageCgroupUsed(pc) || pc->mem_cgroup != from)
+	if (page->mem_cgroup != from)
 		goto out_unlock;
 
-	move_lock_mem_cgroup(from, &flags);
+	spin_lock_irqsave(&from->move_lock, flags);
 
 	if (!PageAnon(page) && page_mapped(page)) {
 		__this_cpu_sub(from->stat->count[MEM_CGROUP_STAT_FILE_MAPPED],
@@ -3409,14 +3077,15 @@ static int mem_cgroup_move_account(struct page *page,
 	}
 
 	/*
-	 * It is safe to change pc->mem_cgroup here because the page
+	 * It is safe to change page->mem_cgroup here because the page
 	 * is referenced, charged, and isolated - we can't race with
 	 * uncharging, charging, migration, or LRU putback.
 	 */
 
 	/* caller should have done css_get */
-	pc->mem_cgroup = to;
-	move_unlock_mem_cgroup(from, &flags);
+	page->mem_cgroup = to;
+	spin_unlock_irqrestore(&from->move_lock, flags);
+
 	ret = 0;
 
 	local_irq_disable();
@@ -3431,72 +3100,6 @@ out:
 	return ret;
 }
 
-/**
- * mem_cgroup_move_parent - moves page to the parent group
- * @page: the page to move
- * @pc: page_cgroup of the page
- * @child: page's cgroup
- *
- * move charges to its parent or the root cgroup if the group has no
- * parent (aka use_hierarchy==0).
- * Although this might fail (get_page_unless_zero, isolate_lru_page or
- * mem_cgroup_move_account fails) the failure is always temporary and
- * it signals a race with a page removal/uncharge or migration. In the
- * first case the page is on the way out and it will vanish from the LRU
- * on the next attempt and the call should be retried later.
- * Isolation from the LRU fails only if page has been isolated from
- * the LRU since we looked at it and that usually means either global
- * reclaim or migration going on. The page will either get back to the
- * LRU or vanish.
- * Finaly mem_cgroup_move_account fails only if the page got uncharged
- * (!PageCgroupUsed) or moved to a different group. The page will
- * disappear in the next attempt.
- */
-static int mem_cgroup_move_parent(struct page *page,
-				  struct page_cgroup *pc,
-				  struct mem_cgroup *child)
-{
-	struct mem_cgroup *parent;
-	unsigned int nr_pages;
-	unsigned long uninitialized_var(flags);
-	int ret;
-
-	VM_BUG_ON(mem_cgroup_is_root(child));
-
-	ret = -EBUSY;
-	if (!get_page_unless_zero(page))
-		goto out;
-	if (isolate_lru_page(page))
-		goto put;
-
-	nr_pages = hpage_nr_pages(page);
-
-	parent = parent_mem_cgroup(child);
-	/*
-	 * If no parent, move charges to root cgroup.
-	 */
-	if (!parent)
-		parent = root_mem_cgroup;
-
-	if (nr_pages > 1) {
-		VM_BUG_ON_PAGE(!PageTransHuge(page), page);
-		flags = compound_lock_irqsave(page);
-	}
-
-	ret = mem_cgroup_move_account(page, nr_pages,
-				pc, child, parent);
-	if (!ret)
-		__mem_cgroup_cancel_local_charge(child, nr_pages);
-
-	if (nr_pages > 1)
-		compound_unlock_irqrestore(page, flags);
-	putback_lru_page(page);
-put:
-	put_page(page);
-out:
-	return ret;
-}
-
 #ifdef CONFIG_MEMCG_SWAP
 static void mem_cgroup_swap_statistics(struct mem_cgroup *memcg,
 					 bool charge)
@@ -3516,7 +3119,7 @@ static void mem_cgroup_swap_statistics(struct mem_cgroup *memcg,
  *
  * Returns 0 on success, -EINVAL on failure.
  *
- * The caller must have charged to @to, IOW, called res_counter_charge() about
+ * The caller must have charged to @to, IOW, called page_counter_charge() about
  * both res and memsw, and called css_get().
  */
 static int mem_cgroup_move_swap_account(swp_entry_t entry,
@@ -3532,7 +3135,7 @@ static int mem_cgroup_move_swap_account(swp_entry_t entry,
 		mem_cgroup_swap_statistics(to, true);
 		/*
 		 * This function is only called from task migration context now.
-		 * It postpones res_counter and refcount handling till the end
+		 * It postpones page_counter and refcount handling till the end
 		 * of task migration(mem_cgroup_clear_mc()) for performance
 		 * improvement. But we cannot postpone css_get(to)  because if
 		 * the process that has been moved to @to does swap-in, the
@@ -3554,96 +3157,57 @@ static inline int mem_cgroup_move_swap_account(swp_entry_t entry,
 }
 #endif
 
-#ifdef CONFIG_DEBUG_VM
-static struct page_cgroup *lookup_page_cgroup_used(struct page *page)
-{
-	struct page_cgroup *pc;
-
-	pc = lookup_page_cgroup(page);
-	/*
-	 * Can be NULL while feeding pages into the page allocator for
-	 * the first time, i.e. during boot or memory hotplug;
-	 * or when mem_cgroup_disabled().
-	 */
-	if (likely(pc) && PageCgroupUsed(pc))
-		return pc;
-	return NULL;
-}
-
-bool mem_cgroup_bad_page_check(struct page *page)
-{
-	if (mem_cgroup_disabled())
-		return false;
-
-	return lookup_page_cgroup_used(page) != NULL;
-}
-
-void mem_cgroup_print_bad_page(struct page *page)
-{
-	struct page_cgroup *pc;
-
-	pc = lookup_page_cgroup_used(page);
-	if (pc) {
-		pr_alert("pc:%p pc->flags:%lx pc->mem_cgroup:%p\n",
-			 pc, pc->flags, pc->mem_cgroup);
-	}
-}
-#endif
+static DEFINE_MUTEX(memcg_limit_mutex);
 
 static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
-				unsigned long long val)
+				   unsigned long limit)
 {
+	unsigned long curusage;
+	unsigned long oldusage;
+	bool enlarge = false;
 	int retry_count;
-	int ret = 0;
-	int children = mem_cgroup_count_children(memcg);
-	u64 curusage, oldusage;
-	int enlarge;
+	int ret;
 
 	/*
 	 * For keeping hierarchical_reclaim simple, how long we should retry
 	 * is depends on callers. We set our retry-count to be function
 	 * of # of children which we should visit in this loop.
 	 */
-	retry_count = MEM_CGROUP_RECLAIM_RETRIES * children;
+	retry_count = MEM_CGROUP_RECLAIM_RETRIES *
+		      mem_cgroup_count_children(memcg);
 
-	oldusage = res_counter_read_u64(&memcg->res, RES_USAGE);
+	oldusage = page_counter_read(&memcg->memory);
 
-	enlarge = 0;
-	while (retry_count) {
+	do {
 		if (signal_pending(current)) {
 			ret = -EINTR;
 			break;
 		}
-		/*
-		 * Rather than hide all in some function, I do this in
-		 * open coded manner. You see what this really does.
-		 * We have to guarantee memcg->res.limit <= memcg->memsw.limit.
-		 */
-		mutex_lock(&set_limit_mutex);
-		if (res_counter_read_u64(&memcg->memsw, RES_LIMIT) < val) {
+
+		mutex_lock(&memcg_limit_mutex);
+		if (limit > memcg->memsw.limit) {
+			mutex_unlock(&memcg_limit_mutex);
 			ret = -EINVAL;
-			mutex_unlock(&set_limit_mutex);
 			break;
 		}
-
-		if (res_counter_read_u64(&memcg->res, RES_LIMIT) < val)
-			enlarge = 1;
-
-		ret = res_counter_set_limit(&memcg->res, val);
-		mutex_unlock(&set_limit_mutex);
+		if (limit > memcg->memory.limit)
+			enlarge = true;
+		ret = page_counter_limit(&memcg->memory, limit);
+		mutex_unlock(&memcg_limit_mutex);
 
 		if (!ret)
 			break;
 
 		try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, true);
 
-		curusage = res_counter_read_u64(&memcg->res, RES_USAGE);
+		curusage = page_counter_read(&memcg->memory);
 		/* Usage is reduced ? */
 		if (curusage >= oldusage)
 			retry_count--;
 		else
 			oldusage = curusage;
-	}
+	} while (retry_count);
+
 	if (!ret && enlarge)
 		memcg_oom_recover(memcg);
 
@@ -3651,52 +3215,53 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
 }
 
 static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
-					unsigned long long val)
+					 unsigned long limit)
 {
+	unsigned long curusage;
+	unsigned long oldusage;
+	bool enlarge = false;
 	int retry_count;
-	u64 oldusage, curusage;
-	int children = mem_cgroup_count_children(memcg);
-	int ret = -EBUSY;
-	int enlarge = 0;
+	int ret;
 
 	/* see mem_cgroup_resize_res_limit */
-	retry_count = children * MEM_CGROUP_RECLAIM_RETRIES;
-	oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
-	while (retry_count) {
+	retry_count = MEM_CGROUP_RECLAIM_RETRIES *
+		      mem_cgroup_count_children(memcg);
+
+	oldusage = page_counter_read(&memcg->memsw);
+
+	do {
 		if (signal_pending(current)) {
 			ret = -EINTR;
 			break;
 		}
-		/*
-		 * Rather than hide all in some function, I do this in
-		 * open coded manner. You see what this really does.
-		 * We have to guarantee memcg->res.limit <= memcg->memsw.limit.
-		 */
-		mutex_lock(&set_limit_mutex);
-		if (res_counter_read_u64(&memcg->res, RES_LIMIT) > val) {
+
+		mutex_lock(&memcg_limit_mutex);
+		if (limit < memcg->memory.limit) {
+			mutex_unlock(&memcg_limit_mutex);
 			ret = -EINVAL;
-			mutex_unlock(&set_limit_mutex);
 			break;
 		}
-		if (res_counter_read_u64(&memcg->memsw, RES_LIMIT) < val)
-			enlarge = 1;
-		ret = res_counter_set_limit(&memcg->memsw, val);
-		mutex_unlock(&set_limit_mutex);
+		if (limit > memcg->memsw.limit)
+			enlarge = true;
+		ret = page_counter_limit(&memcg->memsw, limit);
+		mutex_unlock(&memcg_limit_mutex);
 
 		if (!ret)
 			break;
 
 		try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, false);
 
-		curusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
+		curusage = page_counter_read(&memcg->memsw);
 		/* Usage is reduced ? */
 		if (curusage >= oldusage)
 			retry_count--;
 		else
 			oldusage = curusage;
-	}
+	} while (retry_count);
+
 	if (!ret && enlarge)
 		memcg_oom_recover(memcg);
+
 	return ret;
 }
 
@@ -3709,7 +3274,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 	unsigned long reclaimed;
 	int loop = 0;
 	struct mem_cgroup_tree_per_zone *mctz;
-	unsigned long long excess;
+	unsigned long excess;
 	unsigned long nr_scanned;
 
 	if (order > 0)
@@ -3735,35 +3300,17 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 		nr_reclaimed += reclaimed;
 		*total_scanned += nr_scanned;
 		spin_lock_irq(&mctz->lock);
+		__mem_cgroup_remove_exceeded(mz, mctz);
 
 		/*
 		 * If we failed to reclaim anything from this memory cgroup
 		 * it is time to move on to the next cgroup
 		 */
 		next_mz = NULL;
-		if (!reclaimed) {
-			do {
-				/*
-				 * Loop until we find yet another one.
-				 *
-				 * By the time we get the soft_limit lock
-				 * again, someone might have aded the
-				 * group back on the RB tree. Iterate to
-				 * make sure we get a different mem.
-				 * mem_cgroup_largest_soft_limit_node returns
-				 * NULL if no other cgroup is present on
-				 * the tree
-				 */
-				next_mz =
-				__mem_cgroup_largest_soft_limit_node(mctz);
-				if (next_mz == mz)
-					css_put(&next_mz->memcg->css);
-				else /* next_mz == NULL or other memcg */
-					break;
-			} while (1);
-		}
-		__mem_cgroup_remove_exceeded(mz, mctz);
-		excess = res_counter_soft_limit_excess(&mz->memcg->res);
+		if (!reclaimed)
+			next_mz = __mem_cgroup_largest_soft_limit_node(mctz);
+
+		excess = soft_limit_excess(mz->memcg);
 		/*
 		 * One school of thought says that we should not add
 		 * back the node to the tree if reclaim returns 0.
@@ -3792,107 +3339,6 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 	return nr_reclaimed;
 }
 
-/**
- * mem_cgroup_force_empty_list - clears LRU of a group
- * @memcg: group to clear
- * @node: NUMA node
- * @zid: zone id
- * @lru: lru to to clear
- *
- * Traverse a specified page_cgroup list and try to drop them all.  This doesn't
- * reclaim the pages page themselves - pages are moved to the parent (or root)
- * group.
- */
-static void mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
-				int node, int zid, enum lru_list lru)
-{
-	struct lruvec *lruvec;
-	unsigned long flags;
-	struct list_head *list;
-	struct page *busy;
-	struct zone *zone;
-
-	zone = &NODE_DATA(node)->node_zones[zid];
-	lruvec = mem_cgroup_zone_lruvec(zone, memcg);
-	list = &lruvec->lists[lru];
-
-	busy = NULL;
-	do {
-		struct page_cgroup *pc;
-		struct page *page;
-
-		spin_lock_irqsave(&zone->lru_lock, flags);
-		if (list_empty(list)) {
-			spin_unlock_irqrestore(&zone->lru_lock, flags);
-			break;
-		}
-		page = list_entry(list->prev, struct page, lru);
-		if (busy == page) {
-			list_move(&page->lru, list);
-			busy = NULL;
-			spin_unlock_irqrestore(&zone->lru_lock, flags);
-			continue;
-		}
-		spin_unlock_irqrestore(&zone->lru_lock, flags);
-
-		pc = lookup_page_cgroup(page);
-
-		if (mem_cgroup_move_parent(page, pc, memcg)) {
-			/* found lock contention or "pc" is obsolete. */
-			busy = page;
-		} else
-			busy = NULL;
-		cond_resched();
-	} while (!list_empty(list));
-}
-
-/*
- * make mem_cgroup's charge to be 0 if there is no task by moving
- * all the charges and pages to the parent.
- * This enables deleting this mem_cgroup.
- *
- * Caller is responsible for holding css reference on the memcg.
- */
-static void mem_cgroup_reparent_charges(struct mem_cgroup *memcg)
-{
-	int node, zid;
-	u64 usage;
-
-	do {
-		/* This is for making all *used* pages to be on LRU. */
-		lru_add_drain_all();
-		drain_all_stock_sync(memcg);
-		mem_cgroup_start_move(memcg);
-		for_each_node_state(node, N_MEMORY) {
-			for (zid = 0; zid < MAX_NR_ZONES; zid++) {
-				enum lru_list lru;
-				for_each_lru(lru) {
-					mem_cgroup_force_empty_list(memcg,
-							node, zid, lru);
-				}
-			}
-		}
-		mem_cgroup_end_move(memcg);
-		memcg_oom_recover(memcg);
-		cond_resched();
-
-		/*
-		 * Kernel memory may not necessarily be trackable to a specific
-		 * process. So they are not migrated, and therefore we can't
-		 * expect their value to drop to 0 here.
-		 * Having res filled up with kmem only is enough.
-		 *
-		 * This is a safety check because mem_cgroup_force_empty_list
-		 * could have raced with mem_cgroup_replace_page_cache callers
-		 * so the lru seemed empty but the page could have been added
-		 * right after the check. RES_USAGE should be safe as we always
-		 * charge before adding to the LRU.
-		 */
-		usage = res_counter_read_u64(&memcg->res, RES_USAGE) -
-			res_counter_read_u64(&memcg->kmem, RES_USAGE);
-	} while (usage > 0);
-}
-
 /*
  * Test whether @memcg has children, dead or alive.  Note that this
  * function doesn't care whether @memcg has use_hierarchy enabled and
@@ -3930,7 +3376,7 @@ static int mem_cgroup_force_empty(struct mem_cgroup *memcg)
 	/* we call try-to-free pages for make this cgroup empty */
 	lru_add_drain_all();
 	/* try to free all pages in this cgroup */
-	while (nr_retries && res_counter_read_u64(&memcg->res, RES_USAGE) > 0) {
+	while (nr_retries && page_counter_read(&memcg->memory)) {
 		int progress;
 
 		if (signal_pending(current))
@@ -4001,8 +3447,8 @@ out:
 	return retval;
 }
 
-static unsigned long mem_cgroup_recursive_stat(struct mem_cgroup *memcg,
-					       enum mem_cgroup_stat_index idx)
+static unsigned long tree_stat(struct mem_cgroup *memcg,
+			       enum mem_cgroup_stat_index idx)
 {
 	struct mem_cgroup *iter;
 	long val = 0;
@@ -4020,55 +3466,71 @@ static inline u64 mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
 {
 	u64 val;
 
-	if (!mem_cgroup_is_root(memcg)) {
+	if (mem_cgroup_is_root(memcg)) {
+		val = tree_stat(memcg, MEM_CGROUP_STAT_CACHE);
+		val += tree_stat(memcg, MEM_CGROUP_STAT_RSS);
+		if (swap)
+			val += tree_stat(memcg, MEM_CGROUP_STAT_SWAP);
+	} else {
 		if (!swap)
-			return res_counter_read_u64(&memcg->res, RES_USAGE);
+			val = page_counter_read(&memcg->memory);
 		else
-			return res_counter_read_u64(&memcg->memsw, RES_USAGE);
+			val = page_counter_read(&memcg->memsw);
 	}
-
-	/*
-	 * Transparent hugepages are still accounted for in MEM_CGROUP_STAT_RSS
-	 * as well as in MEM_CGROUP_STAT_RSS_HUGE.
-	 */
-	val = mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_CACHE);
-	val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_RSS);
-
-	if (swap)
-		val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_SWAP);
-
 	return val << PAGE_SHIFT;
 }
 
+enum {
+	RES_USAGE,
+	RES_LIMIT,
+	RES_MAX_USAGE,
+	RES_FAILCNT,
+	RES_SOFT_LIMIT,
+};
 
 static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css,
 			       struct cftype *cft)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
-	enum res_type type = MEMFILE_TYPE(cft->private);
-	int name = MEMFILE_ATTR(cft->private);
+	struct page_counter *counter;
 
-	switch (type) {
+	switch (MEMFILE_TYPE(cft->private)) {
 	case _MEM:
-		if (name == RES_USAGE)
-			return mem_cgroup_usage(memcg, false);
-		return res_counter_read_u64(&memcg->res, name);
+		counter = &memcg->memory;
+		break;
 	case _MEMSWAP:
-		if (name == RES_USAGE)
-			return mem_cgroup_usage(memcg, true);
-		return res_counter_read_u64(&memcg->memsw, name);
+		counter = &memcg->memsw;
+		break;
 	case _KMEM:
-		return res_counter_read_u64(&memcg->kmem, name);
+		counter = &memcg->kmem;
 		break;
 	default:
 		BUG();
 	}
+
+	switch (MEMFILE_ATTR(cft->private)) {
+	case RES_USAGE:
+		if (counter == &memcg->memory)
+			return mem_cgroup_usage(memcg, false);
+		if (counter == &memcg->memsw)
+			return mem_cgroup_usage(memcg, true);
+		return (u64)page_counter_read(counter) * PAGE_SIZE;
+	case RES_LIMIT:
+		return (u64)counter->limit * PAGE_SIZE;
+	case RES_MAX_USAGE:
+		return (u64)counter->watermark * PAGE_SIZE;
+	case RES_FAILCNT:
+		return counter->failcnt;
+	case RES_SOFT_LIMIT:
+		return (u64)memcg->soft_limit * PAGE_SIZE;
+	default:
+		BUG();
+	}
 }
 
 #ifdef CONFIG_MEMCG_KMEM
-/* should be called with activate_kmem_mutex held */
-static int __memcg_activate_kmem(struct mem_cgroup *memcg,
-				 unsigned long long limit)
+static int memcg_activate_kmem(struct mem_cgroup *memcg,
+			       unsigned long nr_pages)
 {
 	int err = 0;
 	int memcg_id;
@@ -4077,12 +3539,6 @@ static int __memcg_activate_kmem(struct mem_cgroup *memcg,
 		return 0;
 
 	/*
-	 * We are going to allocate memory for data shared by all memory
-	 * cgroups so let's stop accounting here.
-	 */
-	memcg_stop_kmem_account();
-
-	/*
 	 * For simplicity, we won't allow this to be disabled.  It also can't
 	 * be changed if the cgroup has children already, or if tasks had
 	 * already joined.
@@ -4115,7 +3571,7 @@ static int __memcg_activate_kmem(struct mem_cgroup *memcg,
 	 * We couldn't have accounted to this cgroup, because it hasn't got the
 	 * active bit set yet, so this should succeed.
 	 */
-	err = res_counter_set_limit(&memcg->kmem, limit);
+	err = page_counter_limit(&memcg->kmem, nr_pages);
 	VM_BUG_ON(err);
 
 	static_key_slow_inc(&memcg_kmem_enabled_key);
@@ -4126,30 +3582,20 @@ static int __memcg_activate_kmem(struct mem_cgroup *memcg,
 	 */
 	memcg_kmem_set_active(memcg);
 out:
-	memcg_resume_kmem_account();
 	return err;
 }
 
-static int memcg_activate_kmem(struct mem_cgroup *memcg,
-			       unsigned long long limit)
-{
-	int ret;
-
-	mutex_lock(&activate_kmem_mutex);
-	ret = __memcg_activate_kmem(memcg, limit);
-	mutex_unlock(&activate_kmem_mutex);
-	return ret;
-}
-
 static int memcg_update_kmem_limit(struct mem_cgroup *memcg,
-				   unsigned long long val)
+				   unsigned long limit)
 {
 	int ret;
 
+	mutex_lock(&memcg_limit_mutex);
 	if (!memcg_kmem_is_active(memcg))
-		ret = memcg_activate_kmem(memcg, val);
+		ret = memcg_activate_kmem(memcg, limit);
 	else
-		ret = res_counter_set_limit(&memcg->kmem, val);
+		ret = page_counter_limit(&memcg->kmem, limit);
+	mutex_unlock(&memcg_limit_mutex);
 	return ret;
 }
 
@@ -4161,19 +3607,19 @@ static int memcg_propagate_kmem(struct mem_cgroup *memcg)
 	if (!parent)
 		return 0;
 
-	mutex_lock(&activate_kmem_mutex);
+	mutex_lock(&memcg_limit_mutex);
 	/*
 	 * If the parent cgroup is not kmem-active now, it cannot be activated
 	 * after this point, because it has at least one child already.
 	 */
 	if (memcg_kmem_is_active(parent))
-		ret = __memcg_activate_kmem(memcg, RES_COUNTER_MAX);
-	mutex_unlock(&activate_kmem_mutex);
+		ret = memcg_activate_kmem(memcg, PAGE_COUNTER_MAX);
+	mutex_unlock(&memcg_limit_mutex);
 	return ret;
 }
 #else
 static int memcg_update_kmem_limit(struct mem_cgroup *memcg,
-				   unsigned long long val)
+				   unsigned long limit)
 {
 	return -EINVAL;
 }
@@ -4187,110 +3633,69 @@ static ssize_t mem_cgroup_write(struct kernfs_open_file *of,
 				char *buf, size_t nbytes, loff_t off)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
-	enum res_type type;
-	int name;
-	unsigned long long val;
+	unsigned long nr_pages;
 	int ret;
 
 	buf = strstrip(buf);
-	type = MEMFILE_TYPE(of_cft(of)->private);
-	name = MEMFILE_ATTR(of_cft(of)->private);
+	ret = page_counter_memparse(buf, &nr_pages);
+	if (ret)
+		return ret;
 
-	switch (name) {
+	switch (MEMFILE_ATTR(of_cft(of)->private)) {
 	case RES_LIMIT:
 		if (mem_cgroup_is_root(memcg)) { /* Can't set limit on root */
 			ret = -EINVAL;
 			break;
 		}
-		/* This function does all necessary parse...reuse it */
-		ret = res_counter_memparse_write_strategy(buf, &val);
-		if (ret)
+		switch (MEMFILE_TYPE(of_cft(of)->private)) {
+		case _MEM:
+			ret = mem_cgroup_resize_limit(memcg, nr_pages);
 			break;
-		if (type == _MEM)
-			ret = mem_cgroup_resize_limit(memcg, val);
-		else if (type == _MEMSWAP)
-			ret = mem_cgroup_resize_memsw_limit(memcg, val);
-		else if (type == _KMEM)
-			ret = memcg_update_kmem_limit(memcg, val);
-		else
-			return -EINVAL;
-		break;
-	case RES_SOFT_LIMIT:
-		ret = res_counter_memparse_write_strategy(buf, &val);
-		if (ret)
+		case _MEMSWAP:
+			ret = mem_cgroup_resize_memsw_limit(memcg, nr_pages);
 			break;
-		/*
-		 * For memsw, soft limits are hard to implement in terms
-		 * of semantics, for now, we support soft limits for
-		 * control without swap
-		 */
-		if (type == _MEM)
-			ret = res_counter_set_soft_limit(&memcg->res, val);
-		else
-			ret = -EINVAL;
+		case _KMEM:
+			ret = memcg_update_kmem_limit(memcg, nr_pages);
+			break;
+		}
 		break;
-	default:
-		ret = -EINVAL; /* should be BUG() ? */
+	case RES_SOFT_LIMIT:
+		memcg->soft_limit = nr_pages;
+		ret = 0;
 		break;
 	}
 	return ret ?: nbytes;
 }
 
-static void memcg_get_hierarchical_limit(struct mem_cgroup *memcg,
-		unsigned long long *mem_limit, unsigned long long *memsw_limit)
-{
-	unsigned long long min_limit, min_memsw_limit, tmp;
-
-	min_limit = res_counter_read_u64(&memcg->res, RES_LIMIT);
-	min_memsw_limit = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
-	if (!memcg->use_hierarchy)
-		goto out;
-
-	while (memcg->css.parent) {
-		memcg = mem_cgroup_from_css(memcg->css.parent);
-		if (!memcg->use_hierarchy)
-			break;
-		tmp = res_counter_read_u64(&memcg->res, RES_LIMIT);
-		min_limit = min(min_limit, tmp);
-		tmp = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
-		min_memsw_limit = min(min_memsw_limit, tmp);
-	}
-out:
-	*mem_limit = min_limit;
-	*memsw_limit = min_memsw_limit;
-}
-
 static ssize_t mem_cgroup_reset(struct kernfs_open_file *of, char *buf,
 				size_t nbytes, loff_t off)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
-	int name;
-	enum res_type type;
+	struct page_counter *counter;
 
-	type = MEMFILE_TYPE(of_cft(of)->private);
-	name = MEMFILE_ATTR(of_cft(of)->private);
+	switch (MEMFILE_TYPE(of_cft(of)->private)) {
+	case _MEM:
+		counter = &memcg->memory;
+		break;
+	case _MEMSWAP:
+		counter = &memcg->memsw;
+		break;
+	case _KMEM:
+		counter = &memcg->kmem;
+		break;
+	default:
+		BUG();
+	}
 
-	switch (name) {
+	switch (MEMFILE_ATTR(of_cft(of)->private)) {
 	case RES_MAX_USAGE:
-		if (type == _MEM)
-			res_counter_reset_max(&memcg->res);
-		else if (type == _MEMSWAP)
-			res_counter_reset_max(&memcg->memsw);
-		else if (type == _KMEM)
-			res_counter_reset_max(&memcg->kmem);
-		else
-			return -EINVAL;
+		page_counter_reset_watermark(counter);
 		break;
 	case RES_FAILCNT:
-		if (type == _MEM)
-			res_counter_reset_failcnt(&memcg->res);
-		else if (type == _MEMSWAP)
-			res_counter_reset_failcnt(&memcg->memsw);
-		else if (type == _KMEM)
-			res_counter_reset_failcnt(&memcg->kmem);
-		else
-			return -EINVAL;
+		counter->failcnt = 0;
 		break;
+	default:
+		BUG();
 	}
 
 	return nbytes;
@@ -4387,6 +3792,7 @@ static inline void mem_cgroup_lru_names_not_uptodate(void)
 static int memcg_stat_show(struct seq_file *m, void *v)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+	unsigned long memory, memsw;
 	struct mem_cgroup *mi;
 	unsigned int i;
 
@@ -4406,14 +3812,16 @@ static int memcg_stat_show(struct seq_file *m, void *v)
 			   mem_cgroup_nr_lru_pages(memcg, BIT(i)) * PAGE_SIZE);
 
 	/* Hierarchical information */
-	{
-		unsigned long long limit, memsw_limit;
-		memcg_get_hierarchical_limit(memcg, &limit, &memsw_limit);
-		seq_printf(m, "hierarchical_memory_limit %llu\n", limit);
-		if (do_swap_account)
-			seq_printf(m, "hierarchical_memsw_limit %llu\n",
-				   memsw_limit);
+	memory = memsw = PAGE_COUNTER_MAX;
+	for (mi = memcg; mi; mi = parent_mem_cgroup(mi)) {
+		memory = min(memory, mi->memory.limit);
+		memsw = min(memsw, mi->memsw.limit);
 	}
+	seq_printf(m, "hierarchical_memory_limit %llu\n",
+		   (u64)memory * PAGE_SIZE);
+	if (do_swap_account)
+		seq_printf(m, "hierarchical_memsw_limit %llu\n",
+			   (u64)memsw * PAGE_SIZE);
 
 	for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
 		long long val = 0;
@@ -4497,7 +3905,7 @@ static int mem_cgroup_swappiness_write(struct cgroup_subsys_state *css,
 static void __mem_cgroup_threshold(struct mem_cgroup *memcg, bool swap)
 {
 	struct mem_cgroup_threshold_ary *t;
-	u64 usage;
+	unsigned long usage;
 	int i;
 
 	rcu_read_lock();
@@ -4596,10 +4004,11 @@ static int __mem_cgroup_usage_register_event(struct mem_cgroup *memcg,
 {
 	struct mem_cgroup_thresholds *thresholds;
 	struct mem_cgroup_threshold_ary *new;
-	u64 threshold, usage;
+	unsigned long threshold;
+	unsigned long usage;
 	int i, size, ret;
 
-	ret = res_counter_memparse_write_strategy(args, &threshold);
+	ret = page_counter_memparse(args, &threshold);
 	if (ret)
 		return ret;
 
@@ -4689,7 +4098,7 @@ static void __mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg,
 {
 	struct mem_cgroup_thresholds *thresholds;
 	struct mem_cgroup_threshold_ary *new;
-	u64 usage;
+	unsigned long usage;
 	int i, j, size;
 
 	mutex_lock(&memcg->thresholds_lock);
@@ -4855,40 +4264,6 @@ static void memcg_destroy_kmem(struct mem_cgroup *memcg)
 {
 	mem_cgroup_sockets_destroy(memcg);
 }
-
-static void kmem_cgroup_css_offline(struct mem_cgroup *memcg)
-{
-	if (!memcg_kmem_is_active(memcg))
-		return;
-
-	/*
-	 * kmem charges can outlive the cgroup. In the case of slab
-	 * pages, for instance, a page contain objects from various
-	 * processes. As we prevent from taking a reference for every
-	 * such allocation we have to be careful when doing uncharge
-	 * (see memcg_uncharge_kmem) and here during offlining.
-	 *
-	 * The idea is that that only the _last_ uncharge which sees
-	 * the dead memcg will drop the last reference. An additional
-	 * reference is taken here before the group is marked dead
-	 * which is then paired with css_put during uncharge resp. here.
-	 *
-	 * Although this might sound strange as this path is called from
-	 * css_offline() when the referencemight have dropped down to 0 and
-	 * shouldn't be incremented anymore (css_tryget_online() would
-	 * fail) we do not have other options because of the kmem
-	 * allocations lifetime.
-	 */
-	css_get(&memcg->css);
-
-	memcg_kmem_mark_dead(memcg);
-
-	if (res_counter_read_u64(&memcg->kmem, RES_USAGE) != 0)
-		return;
-
-	if (memcg_kmem_test_and_clear_dead(memcg))
-		css_put(&memcg->css);
-}
 #else
 static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 {
@@ -4898,10 +4273,6 @@ static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 static void memcg_destroy_kmem(struct mem_cgroup *memcg)
 {
 }
-
-static void kmem_cgroup_css_offline(struct mem_cgroup *memcg)
-{
-}
 #endif
 
 /*
@@ -5228,7 +4599,10 @@ static struct cftype mem_cgroup_files[] = {
 #ifdef CONFIG_SLABINFO
 	{
 		.name = "kmem.slabinfo",
-		.seq_show = mem_cgroup_slabinfo_read,
+		.seq_start = slab_start,
+		.seq_next = slab_next,
+		.seq_stop = slab_stop,
+		.seq_show = memcg_slab_show,
 	},
 #endif
 #endif
@@ -5343,17 +4717,6 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
 
 	free_percpu(memcg->stat);
 
-	/*
-	 * We need to make sure that (at least for now), the jump label
-	 * destruction code runs outside of the cgroup lock. This is because
-	 * get_online_cpus(), which is called from the static_branch update,
-	 * can't be called inside the cgroup_lock. cpusets are the ones
-	 * enforcing this dependency, so if they ever change, we might as well.
-	 *
-	 * schedule_work() will guarantee this happens. Be careful if you need
-	 * to move this code around, and make sure it is outside
-	 * the cgroup_lock.
-	 */
 	disarm_static_keys(memcg);
 	kfree(memcg);
 }
@@ -5363,9 +4726,9 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
  */
 struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
 {
-	if (!memcg->res.parent)
+	if (!memcg->memory.parent)
 		return NULL;
-	return mem_cgroup_from_res_counter(memcg->res.parent, res);
+	return mem_cgroup_from_counter(memcg->memory.parent, memory);
 }
 EXPORT_SYMBOL(parent_mem_cgroup);
 
@@ -5410,9 +4773,9 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 	/* root ? */
 	if (parent_css == NULL) {
 		root_mem_cgroup = memcg;
-		res_counter_init(&memcg->res, NULL);
-		res_counter_init(&memcg->memsw, NULL);
-		res_counter_init(&memcg->kmem, NULL);
+		page_counter_init(&memcg->memory, NULL);
+		page_counter_init(&memcg->memsw, NULL);
+		page_counter_init(&memcg->kmem, NULL);
 	}
 
 	memcg->last_scanned_node = MAX_NUMNODES;
@@ -5451,18 +4814,18 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css)
 	memcg->swappiness = mem_cgroup_swappiness(parent);
 
 	if (parent->use_hierarchy) {
-		res_counter_init(&memcg->res, &parent->res);
-		res_counter_init(&memcg->memsw, &parent->memsw);
-		res_counter_init(&memcg->kmem, &parent->kmem);
+		page_counter_init(&memcg->memory, &parent->memory);
+		page_counter_init(&memcg->memsw, &parent->memsw);
+		page_counter_init(&memcg->kmem, &parent->kmem);
 
 		/*
 		 * No need to take a reference to the parent because cgroup
 		 * core guarantees its existence.
 		 */
 	} else {
-		res_counter_init(&memcg->res, NULL);
-		res_counter_init(&memcg->memsw, NULL);
-		res_counter_init(&memcg->kmem, NULL);
+		page_counter_init(&memcg->memory, NULL);
+		page_counter_init(&memcg->memsw, NULL);
+		page_counter_init(&memcg->kmem, NULL);
 		/*
 		 * Deeper hierachy with use_hierarchy == false doesn't make
 		 * much sense so let cgroup subsystem know about this
@@ -5487,29 +4850,10 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css)
 	return 0;
 }
 
-/*
- * Announce all parents that a group from their hierarchy is gone.
- */
-static void mem_cgroup_invalidate_reclaim_iterators(struct mem_cgroup *memcg)
-{
-	struct mem_cgroup *parent = memcg;
-
-	while ((parent = parent_mem_cgroup(parent)))
-		mem_cgroup_iter_invalidate(parent);
-
-	/*
-	 * if the root memcg is not hierarchical we have to check it
-	 * explicitely.
-	 */
-	if (!root_mem_cgroup->use_hierarchy)
-		mem_cgroup_iter_invalidate(root_mem_cgroup);
-}
-
 static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 	struct mem_cgroup_event *event, *tmp;
-	struct cgroup_subsys_state *iter;
 
 	/*
 	 * Unregister events and notify userspace.
@@ -5523,17 +4867,6 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
 	}
 	spin_unlock(&memcg->event_list_lock);
 
-	kmem_cgroup_css_offline(memcg);
-
-	mem_cgroup_invalidate_reclaim_iterators(memcg);
-
-	/*
-	 * This requires that offlining is serialized.  Right now that is
-	 * guaranteed because css_killed_work_fn() holds the cgroup_mutex.
-	 */
-	css_for_each_descendant_post(iter, css)
-		mem_cgroup_reparent_charges(mem_cgroup_from_css(iter));
-
 	memcg_unregister_all_caches(memcg);
 	vmpressure_cleanup(&memcg->vmpressure);
 }
@@ -5541,42 +4874,6 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
 static void mem_cgroup_css_free(struct cgroup_subsys_state *css)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
-	/*
-	 * XXX: css_offline() would be where we should reparent all
-	 * memory to prepare the cgroup for destruction.  However,
-	 * memcg does not do css_tryget_online() and res_counter charging
-	 * under the same RCU lock region, which means that charging
-	 * could race with offlining.  Offlining only happens to
-	 * cgroups with no tasks in them but charges can show up
-	 * without any tasks from the swapin path when the target
-	 * memcg is looked up from the swapout record and not from the
-	 * current task as it usually is.  A race like this can leak
-	 * charges and put pages with stale cgroup pointers into
-	 * circulation:
-	 *
-	 * #0                        #1
-	 *                           lookup_swap_cgroup_id()
-	 *                           rcu_read_lock()
-	 *                           mem_cgroup_lookup()
-	 *                           css_tryget_online()
-	 *                           rcu_read_unlock()
-	 * disable css_tryget_online()
-	 * call_rcu()
-	 *   offline_css()
-	 *     reparent_charges()
-	 *                           res_counter_charge()
-	 *                           css_put()
-	 *                             css_free()
-	 *                           pc->mem_cgroup = dead memcg
-	 *                           add page to lru
-	 *
-	 * The bulk of the charges are still moved in offline_css() to
-	 * avoid pinning a lot of pages in case a long-term reference
-	 * like a swapout record is deferring the css_free() to long
-	 * after offlining.  But this makes sure we catch any charges
-	 * made after offlining:
-	 */
-	mem_cgroup_reparent_charges(memcg);
 
 	memcg_destroy_kmem(memcg);
 	__mem_cgroup_free(memcg);
@@ -5599,10 +4896,10 @@ static void mem_cgroup_css_reset(struct cgroup_subsys_state *css)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 
-	mem_cgroup_resize_limit(memcg, ULLONG_MAX);
-	mem_cgroup_resize_memsw_limit(memcg, ULLONG_MAX);
-	memcg_update_kmem_limit(memcg, ULLONG_MAX);
-	res_counter_set_soft_limit(&memcg->res, ULLONG_MAX);
+	mem_cgroup_resize_limit(memcg, PAGE_COUNTER_MAX);
+	mem_cgroup_resize_memsw_limit(memcg, PAGE_COUNTER_MAX);
+	memcg_update_kmem_limit(memcg, PAGE_COUNTER_MAX);
+	memcg->soft_limit = 0;
 }
 
 #ifdef CONFIG_MMU
@@ -5758,7 +5055,6 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma,
 		unsigned long addr, pte_t ptent, union mc_target *target)
 {
 	struct page *page = NULL;
-	struct page_cgroup *pc;
 	enum mc_target_type ret = MC_TARGET_NONE;
 	swp_entry_t ent = { .val = 0 };
 
@@ -5772,13 +5068,12 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma,
 	if (!page && !ent.val)
 		return ret;
 	if (page) {
-		pc = lookup_page_cgroup(page);
 		/*
 		 * Do only loose check w/o serialization.
-		 * mem_cgroup_move_account() checks the pc is valid or
+		 * mem_cgroup_move_account() checks the page is valid or
 		 * not under LRU exclusion.
 		 */
-		if (PageCgroupUsed(pc) && pc->mem_cgroup == mc.from) {
+		if (page->mem_cgroup == mc.from) {
 			ret = MC_TARGET_PAGE;
 			if (target)
 				target->page = page;
@@ -5806,15 +5101,13 @@ static enum mc_target_type get_mctgt_type_thp(struct vm_area_struct *vma,
 		unsigned long addr, pmd_t pmd, union mc_target *target)
 {
 	struct page *page = NULL;
-	struct page_cgroup *pc;
 	enum mc_target_type ret = MC_TARGET_NONE;
 
 	page = pmd_page(pmd);
 	VM_BUG_ON_PAGE(!page || !PageHead(page), page);
 	if (!move_anon())
 		return ret;
-	pc = lookup_page_cgroup(page);
-	if (PageCgroupUsed(pc) && pc->mem_cgroup == mc.from) {
+	if (page->mem_cgroup == mc.from) {
 		ret = MC_TARGET_PAGE;
 		if (target) {
 			get_page(page);
@@ -5897,7 +5190,6 @@ static void __mem_cgroup_clear_mc(void)
 {
 	struct mem_cgroup *from = mc.from;
 	struct mem_cgroup *to = mc.to;
-	int i;
 
 	/* we must uncharge all the leftover precharges from mc.to */
 	if (mc.precharge) {
@@ -5916,19 +5208,17 @@ static void __mem_cgroup_clear_mc(void)
 	if (mc.moved_swap) {
 		/* uncharge swap account from the old cgroup */
 		if (!mem_cgroup_is_root(mc.from))
-			res_counter_uncharge(&mc.from->memsw,
-					     PAGE_SIZE * mc.moved_swap);
-
-		for (i = 0; i < mc.moved_swap; i++)
-			css_put(&mc.from->css);
+			page_counter_uncharge(&mc.from->memsw, mc.moved_swap);
 
 		/*
-		 * we charged both to->res and to->memsw, so we should
-		 * uncharge to->res.
+		 * we charged both to->memory and to->memsw, so we
+		 * should uncharge to->memory.
 		 */
 		if (!mem_cgroup_is_root(mc.to))
-			res_counter_uncharge(&mc.to->res,
-					     PAGE_SIZE * mc.moved_swap);
+			page_counter_uncharge(&mc.to->memory, mc.moved_swap);
+
+		css_put_many(&mc.from->css, mc.moved_swap);
+
 		/* we've already done css_get(mc.to) */
 		mc.moved_swap = 0;
 	}
@@ -5939,8 +5229,6 @@ static void __mem_cgroup_clear_mc(void)
 
 static void mem_cgroup_clear_mc(void)
 {
-	struct mem_cgroup *from = mc.from;
-
 	/*
 	 * we must clear moving_task before waking up waiters at the end of
 	 * task migration.
@@ -5951,7 +5239,6 @@ static void mem_cgroup_clear_mc(void)
 	mc.from = NULL;
 	mc.to = NULL;
 	spin_unlock(&mc.lock);
-	mem_cgroup_end_move(from);
 }
 
 static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
@@ -5984,7 +5271,7 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
 			VM_BUG_ON(mc.precharge);
 			VM_BUG_ON(mc.moved_charge);
 			VM_BUG_ON(mc.moved_swap);
-			mem_cgroup_start_move(from);
+
 			spin_lock(&mc.lock);
 			mc.from = from;
 			mc.to = memcg;
@@ -6004,7 +5291,8 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
 static void mem_cgroup_cancel_attach(struct cgroup_subsys_state *css,
 				     struct cgroup_taskset *tset)
 {
-	mem_cgroup_clear_mc();
+	if (mc.to)
+		mem_cgroup_clear_mc();
 }
 
 static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
@@ -6018,7 +5306,6 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
 	enum mc_target_type target_type;
 	union mc_target target;
 	struct page *page;
-	struct page_cgroup *pc;
 
 	/*
 	 * We don't take compound_lock() here but no race with splitting thp
@@ -6039,9 +5326,8 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
 		if (target_type == MC_TARGET_PAGE) {
 			page = target.page;
 			if (!isolate_lru_page(page)) {
-				pc = lookup_page_cgroup(page);
 				if (!mem_cgroup_move_account(page, HPAGE_PMD_NR,
-							pc, mc.from, mc.to)) {
+							     mc.from, mc.to)) {
 					mc.precharge -= HPAGE_PMD_NR;
 					mc.moved_charge += HPAGE_PMD_NR;
 				}
@@ -6069,9 +5355,7 @@ retry:
 			page = target.page;
 			if (isolate_lru_page(page))
 				goto put;
-			pc = lookup_page_cgroup(page);
-			if (!mem_cgroup_move_account(page, 1, pc,
-						     mc.from, mc.to)) {
+			if (!mem_cgroup_move_account(page, 1, mc.from, mc.to)) {
 				mc.precharge--;
 				/* we uncharge from mc.from later. */
 				mc.moved_charge++;
@@ -6115,6 +5399,13 @@ static void mem_cgroup_move_charge(struct mm_struct *mm)
 	struct vm_area_struct *vma;
 
 	lru_add_drain_all();
+	/*
+	 * Signal mem_cgroup_begin_page_stat() to take the memcg's
+	 * move_lock while we're moving its pages to another memcg.
+	 * Then wait for already started RCU-only updates to finish.
+	 */
+	atomic_inc(&mc.from->moving_account);
+	synchronize_rcu();
 retry:
 	if (unlikely(!down_read_trylock(&mm->mmap_sem))) {
 		/*
@@ -6147,6 +5438,7 @@ retry:
 			break;
 	}
 	up_read(&mm->mmap_sem);
+	atomic_dec(&mc.from->moving_account);
 }
 
 static void mem_cgroup_move_task(struct cgroup_subsys_state *css,
@@ -6250,7 +5542,7 @@ static void __init enable_swap_cgroup(void)
  */
 void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
 {
-	struct page_cgroup *pc;
+	struct mem_cgroup *memcg;
 	unsigned short oldid;
 
 	VM_BUG_ON_PAGE(PageLRU(page), page);
@@ -6259,20 +5551,26 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
 	if (!do_swap_account)
 		return;
 
-	pc = lookup_page_cgroup(page);
+	memcg = page->mem_cgroup;
 
 	/* Readahead page, never charged */
-	if (!PageCgroupUsed(pc))
+	if (!memcg)
 		return;
 
-	VM_BUG_ON_PAGE(!(pc->flags & PCG_MEMSW), page);
-
-	oldid = swap_cgroup_record(entry, mem_cgroup_id(pc->mem_cgroup));
+	oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg));
 	VM_BUG_ON_PAGE(oldid, page);
+	mem_cgroup_swap_statistics(memcg, true);
+
+	page->mem_cgroup = NULL;
 
-	pc->flags &= ~PCG_MEMSW;
-	css_get(&pc->mem_cgroup->css);
-	mem_cgroup_swap_statistics(pc->mem_cgroup, true);
+	if (!mem_cgroup_is_root(memcg))
+		page_counter_uncharge(&memcg->memory, 1);
+
+	/* XXX: caller holds IRQ-safe mapping->tree_lock */
+	VM_BUG_ON(!irqs_disabled());
+
+	mem_cgroup_charge_statistics(memcg, page, -1);
+	memcg_check_events(memcg, page);
 }
 
 /**
@@ -6294,7 +5592,7 @@ void mem_cgroup_uncharge_swap(swp_entry_t entry)
 	memcg = mem_cgroup_lookup(id);
 	if (memcg) {
 		if (!mem_cgroup_is_root(memcg))
-			res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
+			page_counter_uncharge(&memcg->memsw, 1);
 		mem_cgroup_swap_statistics(memcg, false);
 		css_put(&memcg->css);
 	}
@@ -6330,7 +5628,6 @@ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
 		goto out;
 
 	if (PageSwapCache(page)) {
-		struct page_cgroup *pc = lookup_page_cgroup(page);
 		/*
 		 * Every swap fault against a single page tries to charge the
 		 * page, bail as early as possible.  shmem_unuse() encounters
@@ -6338,7 +5635,7 @@ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
 		 * the page lock, which serializes swap cache removal, which
 		 * in turn serializes uncharging.
 		 */
-		if (PageCgroupUsed(pc))
+		if (page->mem_cgroup)
 			goto out;
 	}
 
@@ -6452,19 +5749,16 @@ void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg)
 }
 
 static void uncharge_batch(struct mem_cgroup *memcg, unsigned long pgpgout,
-			   unsigned long nr_mem, unsigned long nr_memsw,
 			   unsigned long nr_anon, unsigned long nr_file,
 			   unsigned long nr_huge, struct page *dummy_page)
 {
+	unsigned long nr_pages = nr_anon + nr_file;
 	unsigned long flags;
 
 	if (!mem_cgroup_is_root(memcg)) {
-		if (nr_mem)
-			res_counter_uncharge(&memcg->res,
-					     nr_mem * PAGE_SIZE);
-		if (nr_memsw)
-			res_counter_uncharge(&memcg->memsw,
-					     nr_memsw * PAGE_SIZE);
+		page_counter_uncharge(&memcg->memory, nr_pages);
+		if (do_swap_account)
+			page_counter_uncharge(&memcg->memsw, nr_pages);
 		memcg_oom_recover(memcg);
 	}
 
@@ -6473,27 +5767,27 @@ static void uncharge_batch(struct mem_cgroup *memcg, unsigned long pgpgout,
 	__this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_CACHE], nr_file);
 	__this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_RSS_HUGE], nr_huge);
 	__this_cpu_add(memcg->stat->events[MEM_CGROUP_EVENTS_PGPGOUT], pgpgout);
-	__this_cpu_add(memcg->stat->nr_page_events, nr_anon + nr_file);
+	__this_cpu_add(memcg->stat->nr_page_events, nr_pages);
 	memcg_check_events(memcg, dummy_page);
 	local_irq_restore(flags);
+
+	if (!mem_cgroup_is_root(memcg))
+		css_put_many(&memcg->css, nr_pages);
 }
 
 static void uncharge_list(struct list_head *page_list)
 {
 	struct mem_cgroup *memcg = NULL;
-	unsigned long nr_memsw = 0;
 	unsigned long nr_anon = 0;
 	unsigned long nr_file = 0;
 	unsigned long nr_huge = 0;
 	unsigned long pgpgout = 0;
-	unsigned long nr_mem = 0;
 	struct list_head *next;
 	struct page *page;
 
 	next = page_list->next;
 	do {
 		unsigned int nr_pages = 1;
-		struct page_cgroup *pc;
 
 		page = list_entry(next, struct page, lru);
 		next = page->lru.next;
@@ -6501,24 +5795,22 @@ static void uncharge_list(struct list_head *page_list)
 		VM_BUG_ON_PAGE(PageLRU(page), page);
 		VM_BUG_ON_PAGE(page_count(page), page);
 
-		pc = lookup_page_cgroup(page);
-		if (!PageCgroupUsed(pc))
+		if (!page->mem_cgroup)
 			continue;
 
 		/*
 		 * Nobody should be changing or seriously looking at
-		 * pc->mem_cgroup and pc->flags at this point, we have
-		 * fully exclusive access to the page.
+		 * page->mem_cgroup at this point, we have fully
+		 * exclusive access to the page.
 		 */
 
-		if (memcg != pc->mem_cgroup) {
+		if (memcg != page->mem_cgroup) {
 			if (memcg) {
-				uncharge_batch(memcg, pgpgout, nr_mem, nr_memsw,
-					       nr_anon, nr_file, nr_huge, page);
-				pgpgout = nr_mem = nr_memsw = 0;
-				nr_anon = nr_file = nr_huge = 0;
+				uncharge_batch(memcg, pgpgout, nr_anon, nr_file,
+					       nr_huge, page);
+				pgpgout = nr_anon = nr_file = nr_huge = 0;
 			}
-			memcg = pc->mem_cgroup;
+			memcg = page->mem_cgroup;
 		}
 
 		if (PageTransHuge(page)) {
@@ -6532,18 +5824,14 @@ static void uncharge_list(struct list_head *page_list)
 		else
 			nr_file += nr_pages;
 
-		if (pc->flags & PCG_MEM)
-			nr_mem += nr_pages;
-		if (pc->flags & PCG_MEMSW)
-			nr_memsw += nr_pages;
-		pc->flags = 0;
+		page->mem_cgroup = NULL;
 
 		pgpgout++;
 	} while (next != page_list);
 
 	if (memcg)
-		uncharge_batch(memcg, pgpgout, nr_mem, nr_memsw,
-			       nr_anon, nr_file, nr_huge, page);
+		uncharge_batch(memcg, pgpgout, nr_anon, nr_file,
+			       nr_huge, page);
 }
 
 /**
@@ -6555,14 +5843,11 @@ static void uncharge_list(struct list_head *page_list)
  */
 void mem_cgroup_uncharge(struct page *page)
 {
-	struct page_cgroup *pc;
-
 	if (mem_cgroup_disabled())
 		return;
 
 	/* Don't touch page->lru of any random page, pre-check: */
-	pc = lookup_page_cgroup(page);
-	if (!PageCgroupUsed(pc))
+	if (!page->mem_cgroup)
 		return;
 
 	INIT_LIST_HEAD(&page->lru);
@@ -6598,7 +5883,7 @@ void mem_cgroup_uncharge_list(struct list_head *page_list)
 void mem_cgroup_migrate(struct page *oldpage, struct page *newpage,
 			bool lrucare)
 {
-	struct page_cgroup *pc;
+	struct mem_cgroup *memcg;
 	int isolated;
 
 	VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage);
@@ -6613,27 +5898,28 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage,
 		return;
 
 	/* Page cache replacement: new page already charged? */
-	pc = lookup_page_cgroup(newpage);
-	if (PageCgroupUsed(pc))
+	if (newpage->mem_cgroup)
 		return;
 
-	/* Re-entrant migration: old page already uncharged? */
-	pc = lookup_page_cgroup(oldpage);
-	if (!PageCgroupUsed(pc))
+	/*
+	 * Swapcache readahead pages can get migrated before being
+	 * charged, and migration from compaction can happen to an
+	 * uncharged page when the PFN walker finds a page that
+	 * reclaim just put back on the LRU but has not released yet.
+	 */
+	memcg = oldpage->mem_cgroup;
+	if (!memcg)
 		return;
 
-	VM_BUG_ON_PAGE(!(pc->flags & PCG_MEM), oldpage);
-	VM_BUG_ON_PAGE(do_swap_account && !(pc->flags & PCG_MEMSW), oldpage);
-
 	if (lrucare)
 		lock_page_lru(oldpage, &isolated);
 
-	pc->flags = 0;
+	oldpage->mem_cgroup = NULL;
 
 	if (lrucare)
 		unlock_page_lru(oldpage, isolated);
 
-	commit_charge(newpage, pc->mem_cgroup, lrucare);
+	commit_charge(newpage, memcg, lrucare);
 }
 
 /*
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index b852b10ec76d..6b94969d91c5 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -233,7 +233,7 @@ void shake_page(struct page *p, int access)
 		lru_add_drain_all();
 		if (PageLRU(p))
 			return;
-		drain_all_pages();
+		drain_all_pages(page_zone(p));
 		if (PageLRU(p) || is_free_buddy_page(p))
 			return;
 	}
@@ -466,7 +466,7 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 	struct task_struct *tsk;
 	struct address_space *mapping = page->mapping;
 
-	mutex_lock(&mapping->i_mmap_mutex);
+	i_mmap_lock_read(mapping);
 	read_lock(&tasklist_lock);
 	for_each_process(tsk) {
 		pgoff_t pgoff = page_to_pgoff(page);
@@ -488,7 +488,7 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 		}
 	}
 	read_unlock(&tasklist_lock);
-	mutex_unlock(&mapping->i_mmap_mutex);
+	i_mmap_unlock_read(mapping);
 }
 
 /*
@@ -1661,7 +1661,7 @@ static int __soft_offline_page(struct page *page, int flags)
 			if (!is_free_buddy_page(page))
 				lru_add_drain_all();
 			if (!is_free_buddy_page(page))
-				drain_all_pages();
+				drain_all_pages(page_zone(page));
 			SetPageHWPoison(page);
 			if (!is_free_buddy_page(page))
 				pr_info("soft offline: %#lx: page leaked\n",
diff --git a/mm/memory.c b/mm/memory.c
index 8ca218ba20bb..3ae93ce86b7d 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -238,6 +238,7 @@ static void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
 {
 	tlb->need_flush = 0;
 	tlb_flush(tlb);
+	mmu_notifier_invalidate_range(tlb->mm, tlb->start, tlb->end);
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
 	tlb_table_flush(tlb);
 #endif
@@ -1340,9 +1341,9 @@ static void unmap_single_vma(struct mmu_gather *tlb,
 			 * safe to do nothing in this case.
 			 */
 			if (vma->vm_file) {
-				mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex);
+				i_mmap_lock_write(vma->vm_file->f_mapping);
 				__unmap_hugepage_range_final(tlb, vma, start, end, NULL);
-				mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
+				i_mmap_unlock_write(vma->vm_file->f_mapping);
 			}
 		} else
 			unmap_page_range(tlb, vma, start, end, details);
@@ -2234,7 +2235,7 @@ gotten:
 		 * seen in the presence of one thread doing SMC and another
 		 * thread doing COW.
 		 */
-		ptep_clear_flush(vma, address, page_table);
+		ptep_clear_flush_notify(vma, address, page_table);
 		page_add_new_anon_rmap(new_page, vma, address);
 		mem_cgroup_commit_charge(new_page, memcg, false);
 		lru_cache_add_active_or_unevictable(new_page, vma);
@@ -2391,12 +2392,12 @@ void unmap_mapping_range(struct address_space *mapping,
 		details.last_index = ULONG_MAX;
 
 
-	mutex_lock(&mapping->i_mmap_mutex);
+	i_mmap_lock_read(mapping);
 	if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap)))
 		unmap_mapping_range_tree(&mapping->i_mmap, &details);
 	if (unlikely(!list_empty(&mapping->i_mmap_nonlinear)))
 		unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details);
-	mutex_unlock(&mapping->i_mmap_mutex);
+	i_mmap_unlock_read(mapping);
 }
 EXPORT_SYMBOL(unmap_mapping_range);
 
@@ -2979,6 +2980,8 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	int dirtied = 0;
 	int ret, tmp;
 
+	WARN_ON_ONCE(!rwsem_is_locked(&mm->mmap_sem));
+
 	ret = __do_fault(vma, address, pgoff, flags, &fault_page);
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY)))
 		return ret;
@@ -3009,6 +3012,12 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	if (set_page_dirty(fault_page))
 		dirtied = 1;
+	/*
+	 * Take a local copy of the address_space - page.mapping may be zeroed
+	 * by truncate after unlock_page().   The address_space itself remains
+	 * pinned by vma->vm_file's reference.  We rely on unlock_page()'s
+	 * release semantics to prevent the compiler from undoing this copying.
+	 */
 	mapping = fault_page->mapping;
 	unlock_page(fault_page);
 	if ((dirtied || vma->vm_ops->page_mkwrite) && mapping) {
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 252e1dbbed86..9fab10795bea 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -31,6 +31,7 @@
 #include <linux/stop_machine.h>
 #include <linux/hugetlb.h>
 #include <linux/memblock.h>
+#include <linux/bootmem.h>
 
 #include <asm/tlbflush.h>
 
@@ -1066,6 +1067,16 @@ out:
 }
 #endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */
 
+static void reset_node_present_pages(pg_data_t *pgdat)
+{
+	struct zone *z;
+
+	for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++)
+		z->present_pages = 0;
+
+	pgdat->node_present_pages = 0;
+}
+
 /* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */
 static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
 {
@@ -1096,6 +1107,21 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
 	build_all_zonelists(pgdat, NULL);
 	mutex_unlock(&zonelists_mutex);
 
+	/*
+	 * zone->managed_pages is set to an approximate value in
+	 * free_area_init_core(), which will cause
+	 * /sys/device/system/node/nodeX/meminfo has wrong data.
+	 * So reset it to 0 before any memory is onlined.
+	 */
+	reset_node_managed_pages(pgdat);
+
+	/*
+	 * When memory is hot-added, all the memory is in offline state. So
+	 * clear all zones' present_pages because they will be updated in
+	 * online_pages() and offline_pages().
+	 */
+	reset_node_present_pages(pgdat);
+
 	return pgdat;
 }
 
@@ -1699,7 +1725,7 @@ repeat:
 	if (drain) {
 		lru_add_drain_all();
 		cond_resched();
-		drain_all_pages();
+		drain_all_pages(zone);
 	}
 
 	pfn = scan_movable_pages(start_pfn, end_pfn);
@@ -1721,7 +1747,7 @@ repeat:
 	lru_add_drain_all();
 	yield();
 	/* drain pcp pages, this is synchronous. */
-	drain_all_pages();
+	drain_all_pages(zone);
 	/*
 	 * dissolve free hugepages in the memory block before doing offlining
 	 * actually in order to make hugetlbfs's object counting consistent.
diff --git a/mm/migrate.c b/mm/migrate.c
index 01439953abf5..41945cb0ca38 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1854,7 +1854,7 @@ fail_putback:
 	 */
 	flush_cache_range(vma, mmun_start, mmun_end);
 	page_add_anon_rmap(new_page, vma, mmun_start);
-	pmdp_clear_flush(vma, mmun_start, pmd);
+	pmdp_clear_flush_notify(vma, mmun_start, pmd);
 	set_pmd_at(mm, mmun_start, pmd, entry);
 	flush_tlb_range(vma, mmun_start, mmun_end);
 	update_mmu_cache_pmd(vma, address, &entry);
@@ -1862,6 +1862,7 @@ fail_putback:
 	if (page_count(page) != 2) {
 		set_pmd_at(mm, mmun_start, pmd, orig_entry);
 		flush_tlb_range(vma, mmun_start, mmun_end);
+		mmu_notifier_invalidate_range(mm, mmun_start, mmun_end);
 		update_mmu_cache_pmd(vma, address, &entry);
 		page_remove_rmap(new_page);
 		goto fail_putback;
diff --git a/mm/mmap.c b/mm/mmap.c
index 87e82b38453c..8f8590e04367 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -232,7 +232,7 @@ error:
 }
 
 /*
- * Requires inode->i_mapping->i_mmap_mutex
+ * Requires inode->i_mapping->i_mmap_rwsem
  */
 static void __remove_shared_vm_struct(struct vm_area_struct *vma,
 		struct file *file, struct address_space *mapping)
@@ -260,9 +260,9 @@ void unlink_file_vma(struct vm_area_struct *vma)
 
 	if (file) {
 		struct address_space *mapping = file->f_mapping;
-		mutex_lock(&mapping->i_mmap_mutex);
+		i_mmap_lock_write(mapping);
 		__remove_shared_vm_struct(vma, file, mapping);
-		mutex_unlock(&mapping->i_mmap_mutex);
+		i_mmap_unlock_write(mapping);
 	}
 }
 
@@ -674,14 +674,14 @@ static void vma_link(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	if (vma->vm_file) {
 		mapping = vma->vm_file->f_mapping;
-		mutex_lock(&mapping->i_mmap_mutex);
+		i_mmap_lock_write(mapping);
 	}
 
 	__vma_link(mm, vma, prev, rb_link, rb_parent);
 	__vma_link_file(vma);
 
 	if (mapping)
-		mutex_unlock(&mapping->i_mmap_mutex);
+		i_mmap_unlock_write(mapping);
 
 	mm->map_count++;
 	validate_mm(mm);
@@ -793,7 +793,7 @@ again:			remove_next = 1 + (end > next->vm_end);
 							next->vm_end);
 		}
 
-		mutex_lock(&mapping->i_mmap_mutex);
+		i_mmap_lock_write(mapping);
 		if (insert) {
 			/*
 			 * Put into interval tree now, so instantiated pages
@@ -880,7 +880,7 @@ again:			remove_next = 1 + (end > next->vm_end);
 		anon_vma_unlock_write(anon_vma);
 	}
 	if (mapping)
-		mutex_unlock(&mapping->i_mmap_mutex);
+		i_mmap_unlock_write(mapping);
 
 	if (root) {
 		uprobe_mmap(vma);
@@ -2785,7 +2785,7 @@ void exit_mmap(struct mm_struct *mm)
 
 /* Insert vm structure into process list sorted by address
  * and into the inode's i_mmap tree.  If vm_file is non-NULL
- * then i_mmap_mutex is taken here.
+ * then i_mmap_rwsem is taken here.
  */
 int insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma)
 {
@@ -3080,7 +3080,7 @@ static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping)
 		 */
 		if (test_and_set_bit(AS_MM_ALL_LOCKS, &mapping->flags))
 			BUG();
-		mutex_lock_nest_lock(&mapping->i_mmap_mutex, &mm->mmap_sem);
+		down_write_nest_lock(&mapping->i_mmap_rwsem, &mm->mmap_sem);
 	}
 }
 
@@ -3107,7 +3107,7 @@ static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping)
  * vma in this mm is backed by the same anon_vma or address_space.
  *
  * We can take all the locks in random order because the VM code
- * taking i_mmap_mutex or anon_vma->rwsem outside the mmap_sem never
+ * taking i_mmap_rwsem or anon_vma->rwsem outside the mmap_sem never
  * takes more than one of them in a row. Secondly we're protected
  * against a concurrent mm_take_all_locks() by the mm_all_locks_mutex.
  *
@@ -3176,7 +3176,7 @@ static void vm_unlock_mapping(struct address_space *mapping)
 		 * AS_MM_ALL_LOCKS can't change to 0 from under us
 		 * because we hold the mm_all_locks_mutex.
 		 */
-		mutex_unlock(&mapping->i_mmap_mutex);
+		i_mmap_unlock_write(mapping);
 		if (!test_and_clear_bit(AS_MM_ALL_LOCKS,
 					&mapping->flags))
 			BUG();
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index 2c8da9825fe3..3b9b3d0741b2 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -193,6 +193,16 @@ void __mmu_notifier_invalidate_range_end(struct mm_struct *mm,
 
 	id = srcu_read_lock(&srcu);
 	hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
+		/*
+		 * Call invalidate_range here too to avoid the need for the
+		 * subsystem of having to register an invalidate_range_end
+		 * call-back when there is invalidate_range already. Usually a
+		 * subsystem registers either invalidate_range_start()/end() or
+		 * invalidate_range(), so this will be no additional overhead
+		 * (besides the pointer check).
+		 */
+		if (mn->ops->invalidate_range)
+			mn->ops->invalidate_range(mn, mm, start, end);
 		if (mn->ops->invalidate_range_end)
 			mn->ops->invalidate_range_end(mn, mm, start, end);
 	}
@@ -200,6 +210,21 @@ void __mmu_notifier_invalidate_range_end(struct mm_struct *mm,
 }
 EXPORT_SYMBOL_GPL(__mmu_notifier_invalidate_range_end);
 
+void __mmu_notifier_invalidate_range(struct mm_struct *mm,
+				  unsigned long start, unsigned long end)
+{
+	struct mmu_notifier *mn;
+	int id;
+
+	id = srcu_read_lock(&srcu);
+	hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
+		if (mn->ops->invalidate_range)
+			mn->ops->invalidate_range(mn, mm, start, end);
+	}
+	srcu_read_unlock(&srcu, id);
+}
+EXPORT_SYMBOL_GPL(__mmu_notifier_invalidate_range);
+
 static int do_mmu_notifier_register(struct mmu_notifier *mn,
 				    struct mm_struct *mm,
 				    int take_mmap_sem)
diff --git a/mm/mremap.c b/mm/mremap.c
index c855922497a3..17fa018f5f39 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -99,7 +99,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 	spinlock_t *old_ptl, *new_ptl;
 
 	/*
-	 * When need_rmap_locks is true, we take the i_mmap_mutex and anon_vma
+	 * When need_rmap_locks is true, we take the i_mmap_rwsem and anon_vma
 	 * locks to ensure that rmap will always observe either the old or the
 	 * new ptes. This is the easiest way to avoid races with
 	 * truncate_pagecache(), page migration, etc...
@@ -119,7 +119,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 	if (need_rmap_locks) {
 		if (vma->vm_file) {
 			mapping = vma->vm_file->f_mapping;
-			mutex_lock(&mapping->i_mmap_mutex);
+			i_mmap_lock_write(mapping);
 		}
 		if (vma->anon_vma) {
 			anon_vma = vma->anon_vma;
@@ -156,7 +156,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 	if (anon_vma)
 		anon_vma_unlock_write(anon_vma);
 	if (mapping)
-		mutex_unlock(&mapping->i_mmap_mutex);
+		i_mmap_unlock_write(mapping);
 }
 
 #define LATENCY_LIMIT	(64 * PAGE_SIZE)
diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index 5d14c5d0a156..43078ad8cdda 100644
--- a/mm/nobootmem.c
+++ b/mm/nobootmem.c
@@ -145,12 +145,10 @@ static unsigned long __init free_low_memory_core_early(void)
 
 static int reset_managed_pages_done __initdata;
 
-static inline void __init reset_node_managed_pages(pg_data_t *pgdat)
+void reset_node_managed_pages(pg_data_t *pgdat)
 {
 	struct zone *z;
 
-	if (reset_managed_pages_done)
-		return;
 	for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++)
 		z->managed_pages = 0;
 }
@@ -159,8 +157,12 @@ void __init reset_all_zones_managed_pages(void)
 {
 	struct pglist_data *pgdat;
 
+	if (reset_managed_pages_done)
+		return;
+
 	for_each_online_pgdat(pgdat)
 		reset_node_managed_pages(pgdat);
+
 	reset_managed_pages_done = 1;
 }
 
diff --git a/mm/nommu.c b/mm/nommu.c
index bd1808e194a7..cd519e1cd8a7 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -722,11 +722,11 @@ static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma)
 	if (vma->vm_file) {
 		mapping = vma->vm_file->f_mapping;
 
-		mutex_lock(&mapping->i_mmap_mutex);
+		i_mmap_lock_write(mapping);
 		flush_dcache_mmap_lock(mapping);
 		vma_interval_tree_insert(vma, &mapping->i_mmap);
 		flush_dcache_mmap_unlock(mapping);
-		mutex_unlock(&mapping->i_mmap_mutex);
+		i_mmap_unlock_write(mapping);
 	}
 
 	/* add the VMA to the tree */
@@ -795,11 +795,11 @@ static void delete_vma_from_mm(struct vm_area_struct *vma)
 	if (vma->vm_file) {
 		mapping = vma->vm_file->f_mapping;
 
-		mutex_lock(&mapping->i_mmap_mutex);
+		i_mmap_lock_write(mapping);
 		flush_dcache_mmap_lock(mapping);
 		vma_interval_tree_remove(vma, &mapping->i_mmap);
 		flush_dcache_mmap_unlock(mapping);
-		mutex_unlock(&mapping->i_mmap_mutex);
+		i_mmap_unlock_write(mapping);
 	}
 
 	/* remove from the MM's tree and list */
@@ -2094,14 +2094,14 @@ int nommu_shrink_inode_mappings(struct inode *inode, size_t size,
 	high = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
 	down_write(&nommu_region_sem);
-	mutex_lock(&inode->i_mapping->i_mmap_mutex);
+	i_mmap_lock_read(inode->i_mapping);
 
 	/* search for VMAs that fall within the dead zone */
 	vma_interval_tree_foreach(vma, &inode->i_mapping->i_mmap, low, high) {
 		/* found one - only interested if it's shared out of the page
 		 * cache */
 		if (vma->vm_flags & VM_SHARED) {
-			mutex_unlock(&inode->i_mapping->i_mmap_mutex);
+			i_mmap_unlock_read(inode->i_mapping);
 			up_write(&nommu_region_sem);
 			return -ETXTBSY; /* not quite true, but near enough */
 		}
@@ -2113,8 +2113,7 @@ int nommu_shrink_inode_mappings(struct inode *inode, size_t size,
 	 * we don't check for any regions that start beyond the EOF as there
 	 * shouldn't be any
 	 */
-	vma_interval_tree_foreach(vma, &inode->i_mapping->i_mmap,
-				  0, ULONG_MAX) {
+	vma_interval_tree_foreach(vma, &inode->i_mapping->i_mmap, 0, ULONG_MAX) {
 		if (!(vma->vm_flags & VM_SHARED))
 			continue;
 
@@ -2129,7 +2128,7 @@ int nommu_shrink_inode_mappings(struct inode *inode, size_t size,
 		}
 	}
 
-	mutex_unlock(&inode->i_mapping->i_mmap_mutex);
+	i_mmap_unlock_read(inode->i_mapping);
 	up_write(&nommu_region_sem);
 	return 0;
 }
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 3348280eef89..864bba992735 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -119,7 +119,7 @@ found:
 
 /* return true if the task is not adequate as candidate victim task. */
 static bool oom_unkillable_task(struct task_struct *p,
-		const struct mem_cgroup *memcg, const nodemask_t *nodemask)
+		struct mem_cgroup *memcg, const nodemask_t *nodemask)
 {
 	if (is_global_init(p))
 		return true;
@@ -353,7 +353,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints,
  * State information includes task's pid, uid, tgid, vm size, rss, nr_ptes,
  * swapents, oom_score_adj value, and name.
  */
-static void dump_tasks(const struct mem_cgroup *memcg, const nodemask_t *nodemask)
+static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask)
 {
 	struct task_struct *p;
 	struct task_struct *task;
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 19ceae87522d..d5d81f5384d1 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2357,7 +2357,7 @@ int test_clear_page_writeback(struct page *page)
 		dec_zone_page_state(page, NR_WRITEBACK);
 		inc_zone_page_state(page, NR_WRITTEN);
 	}
-	mem_cgroup_end_page_stat(memcg, locked, memcg_flags);
+	mem_cgroup_end_page_stat(memcg, &locked, &memcg_flags);
 	return ret;
 }
 
@@ -2399,7 +2399,7 @@ int __test_set_page_writeback(struct page *page, bool keep_write)
 		mem_cgroup_inc_page_stat(memcg, MEM_CGROUP_STAT_WRITEBACK);
 		inc_zone_page_state(page, NR_WRITEBACK);
 	}
-	mem_cgroup_end_page_stat(memcg, locked, memcg_flags);
+	mem_cgroup_end_page_stat(memcg, &locked, &memcg_flags);
 	return ret;
 
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ab07b496672f..fbc091cdd0cf 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -48,7 +48,6 @@
 #include <linux/backing-dev.h>
 #include <linux/fault-inject.h>
 #include <linux/page-isolation.h>
-#include <linux/page_cgroup.h>
 #include <linux/debugobjects.h>
 #include <linux/kmemleak.h>
 #include <linux/compaction.h>
@@ -440,18 +439,29 @@ static int __init debug_guardpage_minorder_setup(char *buf)
 }
 __setup("debug_guardpage_minorder=", debug_guardpage_minorder_setup);
 
-static inline void set_page_guard_flag(struct page *page)
+static inline void set_page_guard(struct zone *zone, struct page *page,
+				unsigned int order, int migratetype)
 {
 	__set_bit(PAGE_DEBUG_FLAG_GUARD, &page->debug_flags);
+	INIT_LIST_HEAD(&page->lru);
+	set_page_private(page, order);
+	/* Guard pages are not available for any usage */
+	__mod_zone_freepage_state(zone, -(1 << order), migratetype);
 }
 
-static inline void clear_page_guard_flag(struct page *page)
+static inline void clear_page_guard(struct zone *zone, struct page *page,
+				unsigned int order, int migratetype)
 {
 	__clear_bit(PAGE_DEBUG_FLAG_GUARD, &page->debug_flags);
+	set_page_private(page, 0);
+	if (!is_migrate_isolate(migratetype))
+		__mod_zone_freepage_state(zone, (1 << order), migratetype);
 }
 #else
-static inline void set_page_guard_flag(struct page *page) { }
-static inline void clear_page_guard_flag(struct page *page) { }
+static inline void set_page_guard(struct zone *zone, struct page *page,
+				unsigned int order, int migratetype) {}
+static inline void clear_page_guard(struct zone *zone, struct page *page,
+				unsigned int order, int migratetype) {}
 #endif
 
 static inline void set_page_order(struct page *page, unsigned int order)
@@ -467,29 +477,6 @@ static inline void rmv_page_order(struct page *page)
 }
 
 /*
- * Locate the struct page for both the matching buddy in our
- * pair (buddy1) and the combined O(n+1) page they form (page).
- *
- * 1) Any buddy B1 will have an order O twin B2 which satisfies
- * the following equation:
- *     B2 = B1 ^ (1 << O)
- * For example, if the starting buddy (buddy2) is #8 its order
- * 1 buddy is #10:
- *     B2 = 8 ^ (1 << 1) = 8 ^ 2 = 10
- *
- * 2) Any buddy B will have an order O+1 parent P which
- * satisfies the following equation:
- *     P = B & ~(1 << O)
- *
- * Assumption: *_mem_map is contiguous at least up to MAX_ORDER
- */
-static inline unsigned long
-__find_buddy_index(unsigned long page_idx, unsigned int order)
-{
-	return page_idx ^ (1 << order);
-}
-
-/*
  * This function checks whether a page is free && is the buddy
  * we can do coalesce a page and its buddy if
  * (a) the buddy is not in a hole &&
@@ -569,6 +556,7 @@ static inline void __free_one_page(struct page *page,
 	unsigned long combined_idx;
 	unsigned long uninitialized_var(buddy_idx);
 	struct page *buddy;
+	int max_order = MAX_ORDER;
 
 	VM_BUG_ON(!zone_is_initialized(zone));
 
@@ -577,13 +565,24 @@ static inline void __free_one_page(struct page *page,
 			return;
 
 	VM_BUG_ON(migratetype == -1);
+	if (is_migrate_isolate(migratetype)) {
+		/*
+		 * We restrict max order of merging to prevent merge
+		 * between freepages on isolate pageblock and normal
+		 * pageblock. Without this, pageblock isolation
+		 * could cause incorrect freepage accounting.
+		 */
+		max_order = min(MAX_ORDER, pageblock_order + 1);
+	} else {
+		__mod_zone_freepage_state(zone, 1 << order, migratetype);
+	}
 
-	page_idx = pfn & ((1 << MAX_ORDER) - 1);
+	page_idx = pfn & ((1 << max_order) - 1);
 
 	VM_BUG_ON_PAGE(page_idx & ((1 << order) - 1), page);
 	VM_BUG_ON_PAGE(bad_range(zone, page), page);
 
-	while (order < MAX_ORDER-1) {
+	while (order < max_order - 1) {
 		buddy_idx = __find_buddy_index(page_idx, order);
 		buddy = page + (buddy_idx - page_idx);
 		if (!page_is_buddy(page, buddy, order))
@@ -593,10 +592,7 @@ static inline void __free_one_page(struct page *page,
 		 * merge with it and move up one order.
 		 */
 		if (page_is_guard(buddy)) {
-			clear_page_guard_flag(buddy);
-			set_page_private(page, 0);
-			__mod_zone_freepage_state(zone, 1 << order,
-						  migratetype);
+			clear_page_guard(zone, buddy, order, migratetype);
 		} else {
 			list_del(&buddy->lru);
 			zone->free_area[order].nr_free--;
@@ -650,8 +646,10 @@ static inline int free_pages_check(struct page *page)
 		bad_reason = "PAGE_FLAGS_CHECK_AT_FREE flag(s) set";
 		bad_flags = PAGE_FLAGS_CHECK_AT_FREE;
 	}
-	if (unlikely(mem_cgroup_bad_page_check(page)))
-		bad_reason = "cgroup check failed";
+#ifdef CONFIG_MEMCG
+	if (unlikely(page->mem_cgroup))
+		bad_reason = "page still charged to cgroup";
+#endif
 	if (unlikely(bad_reason)) {
 		bad_page(page, bad_reason, bad_flags);
 		return 1;
@@ -715,14 +713,12 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 			/* must delete as __free_one_page list manipulates */
 			list_del(&page->lru);
 			mt = get_freepage_migratetype(page);
+			if (unlikely(has_isolate_pageblock(zone)))
+				mt = get_pageblock_migratetype(page);
+
 			/* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */
 			__free_one_page(page, page_to_pfn(page), zone, 0, mt);
 			trace_mm_page_pcpu_drain(page, 0, mt);
-			if (likely(!is_migrate_isolate_page(page))) {
-				__mod_zone_page_state(zone, NR_FREE_PAGES, 1);
-				if (is_migrate_cma(mt))
-					__mod_zone_page_state(zone, NR_FREE_CMA_PAGES, 1);
-			}
 		} while (--to_free && --batch_free && !list_empty(list));
 	}
 	spin_unlock(&zone->lock);
@@ -739,9 +735,11 @@ static void free_one_page(struct zone *zone,
 	if (nr_scanned)
 		__mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned);
 
+	if (unlikely(has_isolate_pageblock(zone) ||
+		is_migrate_isolate(migratetype))) {
+		migratetype = get_pfnblock_migratetype(page, pfn);
+	}
 	__free_one_page(page, pfn, zone, order, migratetype);
-	if (unlikely(!is_migrate_isolate(migratetype)))
-		__mod_zone_freepage_state(zone, 1 << order, migratetype);
 	spin_unlock(&zone->lock);
 }
 
@@ -750,6 +748,9 @@ static bool free_pages_prepare(struct page *page, unsigned int order)
 	int i;
 	int bad = 0;
 
+	VM_BUG_ON_PAGE(PageTail(page), page);
+	VM_BUG_ON_PAGE(PageHead(page) && compound_order(page) != order, page);
+
 	trace_mm_page_free(page, order);
 	kmemcheck_free_shadow(page, order);
 
@@ -866,23 +867,17 @@ static inline void expand(struct zone *zone, struct page *page,
 		size >>= 1;
 		VM_BUG_ON_PAGE(bad_range(zone, &page[size]), &page[size]);
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
-		if (high < debug_guardpage_minorder()) {
+		if (IS_ENABLED(CONFIG_DEBUG_PAGEALLOC) &&
+			high < debug_guardpage_minorder()) {
 			/*
 			 * Mark as guard pages (or page), that will allow to
 			 * merge back to allocator when buddy will be freed.
 			 * Corresponding page table entries will not be touched,
 			 * pages will stay not present in virtual address space
 			 */
-			INIT_LIST_HEAD(&page[size].lru);
-			set_page_guard_flag(&page[size]);
-			set_page_private(&page[size], high);
-			/* Guard pages are not available for any usage */
-			__mod_zone_freepage_state(zone, -(1 << high),
-						  migratetype);
+			set_page_guard(zone, &page[size], high, migratetype);
 			continue;
 		}
-#endif
 		list_add(&page[size].lru, &area->free_list[migratetype]);
 		area->nr_free++;
 		set_page_order(&page[size], high);
@@ -907,8 +902,10 @@ static inline int check_new_page(struct page *page)
 		bad_reason = "PAGE_FLAGS_CHECK_AT_PREP flag set";
 		bad_flags = PAGE_FLAGS_CHECK_AT_PREP;
 	}
-	if (unlikely(mem_cgroup_bad_page_check(page)))
-		bad_reason = "cgroup check failed";
+#ifdef CONFIG_MEMCG
+	if (unlikely(page->mem_cgroup))
+		bad_reason = "page still charged to cgroup";
+#endif
 	if (unlikely(bad_reason)) {
 		bad_page(page, bad_reason, bad_flags);
 		return 1;
@@ -1276,55 +1273,75 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
 #endif
 
 /*
- * Drain pages of the indicated processor.
+ * Drain pcplists of the indicated processor and zone.
  *
  * The processor must either be the current processor and the
  * thread pinned to the current processor or a processor that
  * is not online.
  */
-static void drain_pages(unsigned int cpu)
+static void drain_pages_zone(unsigned int cpu, struct zone *zone)
 {
 	unsigned long flags;
-	struct zone *zone;
+	struct per_cpu_pageset *pset;
+	struct per_cpu_pages *pcp;
 
-	for_each_populated_zone(zone) {
-		struct per_cpu_pageset *pset;
-		struct per_cpu_pages *pcp;
+	local_irq_save(flags);
+	pset = per_cpu_ptr(zone->pageset, cpu);
 
-		local_irq_save(flags);
-		pset = per_cpu_ptr(zone->pageset, cpu);
+	pcp = &pset->pcp;
+	if (pcp->count) {
+		free_pcppages_bulk(zone, pcp->count, pcp);
+		pcp->count = 0;
+	}
+	local_irq_restore(flags);
+}
 
-		pcp = &pset->pcp;
-		if (pcp->count) {
-			free_pcppages_bulk(zone, pcp->count, pcp);
-			pcp->count = 0;
-		}
-		local_irq_restore(flags);
+/*
+ * Drain pcplists of all zones on the indicated processor.
+ *
+ * The processor must either be the current processor and the
+ * thread pinned to the current processor or a processor that
+ * is not online.
+ */
+static void drain_pages(unsigned int cpu)
+{
+	struct zone *zone;
+
+	for_each_populated_zone(zone) {
+		drain_pages_zone(cpu, zone);
 	}
 }
 
 /*
  * Spill all of this CPU's per-cpu pages back into the buddy allocator.
+ *
+ * The CPU has to be pinned. When zone parameter is non-NULL, spill just
+ * the single zone's pages.
  */
-void drain_local_pages(void *arg)
+void drain_local_pages(struct zone *zone)
 {
-	drain_pages(smp_processor_id());
+	int cpu = smp_processor_id();
+
+	if (zone)
+		drain_pages_zone(cpu, zone);
+	else
+		drain_pages(cpu);
 }
 
 /*
  * Spill all the per-cpu pages from all CPUs back into the buddy allocator.
  *
+ * When zone parameter is non-NULL, spill just the single zone's pages.
+ *
  * Note that this code is protected against sending an IPI to an offline
  * CPU but does not guarantee sending an IPI to newly hotplugged CPUs:
  * on_each_cpu_mask() blocks hotplug and won't talk to offlined CPUs but
  * nothing keeps CPUs from showing up after we populated the cpumask and
  * before the call to on_each_cpu_mask().
  */
-void drain_all_pages(void)
+void drain_all_pages(struct zone *zone)
 {
 	int cpu;
-	struct per_cpu_pageset *pcp;
-	struct zone *zone;
 
 	/*
 	 * Allocate in the BSS so we wont require allocation in
@@ -1339,20 +1356,31 @@ void drain_all_pages(void)
 	 * disables preemption as part of its processing
 	 */
 	for_each_online_cpu(cpu) {
+		struct per_cpu_pageset *pcp;
+		struct zone *z;
 		bool has_pcps = false;
-		for_each_populated_zone(zone) {
+
+		if (zone) {
 			pcp = per_cpu_ptr(zone->pageset, cpu);
-			if (pcp->pcp.count) {
+			if (pcp->pcp.count)
 				has_pcps = true;
-				break;
+		} else {
+			for_each_populated_zone(z) {
+				pcp = per_cpu_ptr(z->pageset, cpu);
+				if (pcp->pcp.count) {
+					has_pcps = true;
+					break;
+				}
 			}
 		}
+
 		if (has_pcps)
 			cpumask_set_cpu(cpu, &cpus_with_pcps);
 		else
 			cpumask_clear_cpu(cpu, &cpus_with_pcps);
 	}
-	on_each_cpu_mask(&cpus_with_pcps, drain_local_pages, NULL, 1);
+	on_each_cpu_mask(&cpus_with_pcps, (smp_call_func_t) drain_local_pages,
+								zone, 1);
 }
 
 #ifdef CONFIG_HIBERNATION
@@ -1484,7 +1512,7 @@ void split_page(struct page *page, unsigned int order)
 }
 EXPORT_SYMBOL_GPL(split_page);
 
-static int __isolate_free_page(struct page *page, unsigned int order)
+int __isolate_free_page(struct page *page, unsigned int order)
 {
 	unsigned long watermark;
 	struct zone *zone;
@@ -1714,7 +1742,7 @@ static bool __zone_watermark_ok(struct zone *z, unsigned int order,
 			unsigned long mark, int classzone_idx, int alloc_flags,
 			long free_pages)
 {
-	/* free_pages my go negative - that's OK */
+	/* free_pages may go negative - that's OK */
 	long min = mark;
 	int o;
 	long free_cma = 0;
@@ -2305,7 +2333,6 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	int classzone_idx, int migratetype, enum migrate_mode mode,
 	int *contended_compaction, bool *deferred_compaction)
 {
-	struct zone *last_compact_zone = NULL;
 	unsigned long compact_result;
 	struct page *page;
 
@@ -2316,7 +2343,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	compact_result = try_to_compact_pages(zonelist, order, gfp_mask,
 						nodemask, mode,
 						contended_compaction,
-						&last_compact_zone);
+						alloc_flags, classzone_idx);
 	current->flags &= ~PF_MEMALLOC;
 
 	switch (compact_result) {
@@ -2335,10 +2362,6 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	 */
 	count_vm_event(COMPACTSTALL);
 
-	/* Page migration frees to the PCP lists but we want merging */
-	drain_pages(get_cpu());
-	put_cpu();
-
 	page = get_page_from_freelist(gfp_mask, nodemask,
 			order, zonelist, high_zoneidx,
 			alloc_flags & ~ALLOC_NO_WATERMARKS,
@@ -2354,14 +2377,6 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	}
 
 	/*
-	 * last_compact_zone is where try_to_compact_pages thought allocation
-	 * should succeed, so it did not defer compaction. But here we know
-	 * that it didn't succeed, so we do the defer.
-	 */
-	if (last_compact_zone && mode != MIGRATE_ASYNC)
-		defer_compaction(last_compact_zone, order);
-
-	/*
 	 * It's bad if compaction run occurs and fails. The most likely reason
 	 * is that pages exist, but not enough to satisfy watermarks.
 	 */
@@ -2442,7 +2457,7 @@ retry:
 	 * pages are pinned on the per-cpu lists. Drain them and try again
 	 */
 	if (!page && !drained) {
-		drain_all_pages();
+		drain_all_pages(NULL);
 		drained = true;
 		goto retry;
 	}
@@ -2841,8 +2856,9 @@ retry_cpuset:
 		 * can deadlock because I/O on the device might not
 		 * complete.
 		 */
-		gfp_mask = memalloc_noio_flags(gfp_mask);
-		page = __alloc_pages_slowpath(gfp_mask, order,
+		gfp_t mask = memalloc_noio_flags(gfp_mask);
+
+		page = __alloc_pages_slowpath(mask, order,
 				zonelist, high_zoneidx, nodemask,
 				preferred_zone, classzone_idx, migratetype);
 	}
@@ -3902,14 +3918,14 @@ void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone)
 	else
 		page_group_by_mobility_disabled = 0;
 
-	printk("Built %i zonelists in %s order, mobility grouping %s.  "
+	pr_info("Built %i zonelists in %s order, mobility grouping %s.  "
 		"Total pages: %ld\n",
 			nr_online_nodes,
 			zonelist_order_name[current_zonelist_order],
 			page_group_by_mobility_disabled ? "off" : "on",
 			vm_total_pages);
 #ifdef CONFIG_NUMA
-	printk("Policy zone: %s\n", zone_names[policy_zone]);
+	pr_info("Policy zone: %s\n", zone_names[policy_zone]);
 #endif
 }
 
@@ -4841,7 +4857,6 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 #endif
 	init_waitqueue_head(&pgdat->kswapd_wait);
 	init_waitqueue_head(&pgdat->pfmemalloc_wait);
-	pgdat_page_cgroup_init(pgdat);
 
 	for (j = 0; j < MAX_NR_ZONES; j++) {
 		struct zone *zone = pgdat->node_zones + j;
@@ -5343,33 +5358,33 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 	find_zone_movable_pfns_for_nodes();
 
 	/* Print out the zone ranges */
-	printk("Zone ranges:\n");
+	pr_info("Zone ranges:\n");
 	for (i = 0; i < MAX_NR_ZONES; i++) {
 		if (i == ZONE_MOVABLE)
 			continue;
-		printk(KERN_CONT "  %-8s ", zone_names[i]);
+		pr_info("  %-8s ", zone_names[i]);
 		if (arch_zone_lowest_possible_pfn[i] ==
 				arch_zone_highest_possible_pfn[i])
-			printk(KERN_CONT "empty\n");
+			pr_cont("empty\n");
 		else
-			printk(KERN_CONT "[mem %0#10lx-%0#10lx]\n",
+			pr_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 for each node\n");
+	pr_info("Movable zone start for each node\n");
 	for (i = 0; i < MAX_NUMNODES; i++) {
 		if (zone_movable_pfn[i])
-			printk("  Node %d: %#010lx\n", i,
+			pr_info("  Node %d: %#010lx\n", i,
 			       zone_movable_pfn[i] << PAGE_SHIFT);
 	}
 
 	/* Print out the early node map */
-	printk("Early memory node ranges\n");
+	pr_info("Early memory node ranges\n");
 	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid)
-		printk("  node %3d: [mem %#010lx-%#010lx]\n", nid,
+		pr_info("  node %3d: [mem %#010lx-%#010lx]\n", nid,
 		       start_pfn << PAGE_SHIFT, (end_pfn << PAGE_SHIFT) - 1);
 
 	/* Initialise every node */
@@ -5505,7 +5520,7 @@ void __init mem_init_print_info(const char *str)
 
 #undef	adj_init_size
 
-	printk("Memory: %luK/%luK available "
+	pr_info("Memory: %luK/%luK available "
 	       "(%luK kernel code, %luK rwdata, %luK rodata, "
 	       "%luK init, %luK bss, %luK reserved"
 #ifdef	CONFIG_HIGHMEM
@@ -6394,7 +6409,7 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 	 */
 
 	lru_add_drain_all();
-	drain_all_pages();
+	drain_all_pages(cc.zone);
 
 	order = 0;
 	outer_start = start;
@@ -6408,13 +6423,12 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 
 	/* Make sure the range is really isolated. */
 	if (test_pages_isolated(outer_start, end, false)) {
-		pr_warn("alloc_contig_range test_pages_isolated(%lx, %lx) failed\n",
-		       outer_start, end);
+		pr_info("%s: [%lx, %lx) PFNs busy\n",
+			__func__, outer_start, end);
 		ret = -EBUSY;
 		goto done;
 	}
 
-
 	/* Grab isolated pages from freelists. */
 	outer_end = isolate_freepages_range(&cc, outer_start, end);
 	if (!outer_end) {
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
deleted file mode 100644
index 5331c2bd85a2..000000000000
--- a/mm/page_cgroup.c
+++ /dev/null
@@ -1,530 +0,0 @@
-#include <linux/mm.h>
-#include <linux/mmzone.h>
-#include <linux/bootmem.h>
-#include <linux/bit_spinlock.h>
-#include <linux/page_cgroup.h>
-#include <linux/hash.h>
-#include <linux/slab.h>
-#include <linux/memory.h>
-#include <linux/vmalloc.h>
-#include <linux/cgroup.h>
-#include <linux/swapops.h>
-#include <linux/kmemleak.h>
-
-static unsigned long total_usage;
-
-#if !defined(CONFIG_SPARSEMEM)
-
-
-void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
-{
-	pgdat->node_page_cgroup = NULL;
-}
-
-struct page_cgroup *lookup_page_cgroup(struct page *page)
-{
-	unsigned long pfn = page_to_pfn(page);
-	unsigned long offset;
-	struct page_cgroup *base;
-
-	base = NODE_DATA(page_to_nid(page))->node_page_cgroup;
-#ifdef CONFIG_DEBUG_VM
-	/*
-	 * The sanity checks the page allocator does upon freeing a
-	 * page can reach here before the page_cgroup arrays are
-	 * allocated when feeding a range of pages to the allocator
-	 * for the first time during bootup or memory hotplug.
-	 */
-	if (unlikely(!base))
-		return NULL;
-#endif
-	offset = pfn - NODE_DATA(page_to_nid(page))->node_start_pfn;
-	return base + offset;
-}
-
-static int __init alloc_node_page_cgroup(int nid)
-{
-	struct page_cgroup *base;
-	unsigned long table_size;
-	unsigned long nr_pages;
-
-	nr_pages = NODE_DATA(nid)->node_spanned_pages;
-	if (!nr_pages)
-		return 0;
-
-	table_size = sizeof(struct page_cgroup) * nr_pages;
-
-	base = memblock_virt_alloc_try_nid_nopanic(
-			table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS),
-			BOOTMEM_ALLOC_ACCESSIBLE, nid);
-	if (!base)
-		return -ENOMEM;
-	NODE_DATA(nid)->node_page_cgroup = base;
-	total_usage += table_size;
-	return 0;
-}
-
-void __init page_cgroup_init_flatmem(void)
-{
-
-	int nid, fail;
-
-	if (mem_cgroup_disabled())
-		return;
-
-	for_each_online_node(nid)  {
-		fail = alloc_node_page_cgroup(nid);
-		if (fail)
-			goto fail;
-	}
-	printk(KERN_INFO "allocated %ld bytes of page_cgroup\n", total_usage);
-	printk(KERN_INFO "please try 'cgroup_disable=memory' option if you"
-	" don't want memory cgroups\n");
-	return;
-fail:
-	printk(KERN_CRIT "allocation of page_cgroup failed.\n");
-	printk(KERN_CRIT "please try 'cgroup_disable=memory' boot option\n");
-	panic("Out of memory");
-}
-
-#else /* CONFIG_FLAT_NODE_MEM_MAP */
-
-struct page_cgroup *lookup_page_cgroup(struct page *page)
-{
-	unsigned long pfn = page_to_pfn(page);
-	struct mem_section *section = __pfn_to_section(pfn);
-#ifdef CONFIG_DEBUG_VM
-	/*
-	 * The sanity checks the page allocator does upon freeing a
-	 * page can reach here before the page_cgroup arrays are
-	 * allocated when feeding a range of pages to the allocator
-	 * for the first time during bootup or memory hotplug.
-	 */
-	if (!section->page_cgroup)
-		return NULL;
-#endif
-	return section->page_cgroup + pfn;
-}
-
-static void *__meminit alloc_page_cgroup(size_t size, int nid)
-{
-	gfp_t flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN;
-	void *addr = NULL;
-
-	addr = alloc_pages_exact_nid(nid, size, flags);
-	if (addr) {
-		kmemleak_alloc(addr, size, 1, flags);
-		return addr;
-	}
-
-	if (node_state(nid, N_HIGH_MEMORY))
-		addr = vzalloc_node(size, nid);
-	else
-		addr = vzalloc(size);
-
-	return addr;
-}
-
-static int __meminit init_section_page_cgroup(unsigned long pfn, int nid)
-{
-	struct mem_section *section;
-	struct page_cgroup *base;
-	unsigned long table_size;
-
-	section = __pfn_to_section(pfn);
-
-	if (section->page_cgroup)
-		return 0;
-
-	table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION;
-	base = alloc_page_cgroup(table_size, nid);
-
-	/*
-	 * The value stored in section->page_cgroup is (base - pfn)
-	 * and it does not point to the memory block allocated above,
-	 * causing kmemleak false positives.
-	 */
-	kmemleak_not_leak(base);
-
-	if (!base) {
-		printk(KERN_ERR "page cgroup allocation failure\n");
-		return -ENOMEM;
-	}
-
-	/*
-	 * The passed "pfn" may not be aligned to SECTION.  For the calculation
-	 * we need to apply a mask.
-	 */
-	pfn &= PAGE_SECTION_MASK;
-	section->page_cgroup = base - pfn;
-	total_usage += table_size;
-	return 0;
-}
-#ifdef CONFIG_MEMORY_HOTPLUG
-static void free_page_cgroup(void *addr)
-{
-	if (is_vmalloc_addr(addr)) {
-		vfree(addr);
-	} else {
-		struct page *page = virt_to_page(addr);
-		size_t table_size =
-			sizeof(struct page_cgroup) * PAGES_PER_SECTION;
-
-		BUG_ON(PageReserved(page));
-		kmemleak_free(addr);
-		free_pages_exact(addr, table_size);
-	}
-}
-
-static void __free_page_cgroup(unsigned long pfn)
-{
-	struct mem_section *ms;
-	struct page_cgroup *base;
-
-	ms = __pfn_to_section(pfn);
-	if (!ms || !ms->page_cgroup)
-		return;
-	base = ms->page_cgroup + pfn;
-	free_page_cgroup(base);
-	ms->page_cgroup = NULL;
-}
-
-static int __meminit online_page_cgroup(unsigned long start_pfn,
-				unsigned long nr_pages,
-				int nid)
-{
-	unsigned long start, end, pfn;
-	int fail = 0;
-
-	start = SECTION_ALIGN_DOWN(start_pfn);
-	end = SECTION_ALIGN_UP(start_pfn + nr_pages);
-
-	if (nid == -1) {
-		/*
-		 * In this case, "nid" already exists and contains valid memory.
-		 * "start_pfn" passed to us is a pfn which is an arg for
-		 * online__pages(), and start_pfn should exist.
-		 */
-		nid = pfn_to_nid(start_pfn);
-		VM_BUG_ON(!node_state(nid, N_ONLINE));
-	}
-
-	for (pfn = start; !fail && pfn < end; pfn += PAGES_PER_SECTION) {
-		if (!pfn_present(pfn))
-			continue;
-		fail = init_section_page_cgroup(pfn, nid);
-	}
-	if (!fail)
-		return 0;
-
-	/* rollback */
-	for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION)
-		__free_page_cgroup(pfn);
-
-	return -ENOMEM;
-}
-
-static int __meminit offline_page_cgroup(unsigned long start_pfn,
-				unsigned long nr_pages, int nid)
-{
-	unsigned long start, end, pfn;
-
-	start = SECTION_ALIGN_DOWN(start_pfn);
-	end = SECTION_ALIGN_UP(start_pfn + nr_pages);
-
-	for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION)
-		__free_page_cgroup(pfn);
-	return 0;
-
-}
-
-static int __meminit page_cgroup_callback(struct notifier_block *self,
-			       unsigned long action, void *arg)
-{
-	struct memory_notify *mn = arg;
-	int ret = 0;
-	switch (action) {
-	case MEM_GOING_ONLINE:
-		ret = online_page_cgroup(mn->start_pfn,
-				   mn->nr_pages, mn->status_change_nid);
-		break;
-	case MEM_OFFLINE:
-		offline_page_cgroup(mn->start_pfn,
-				mn->nr_pages, mn->status_change_nid);
-		break;
-	case MEM_CANCEL_ONLINE:
-		offline_page_cgroup(mn->start_pfn,
-				mn->nr_pages, mn->status_change_nid);
-		break;
-	case MEM_GOING_OFFLINE:
-		break;
-	case MEM_ONLINE:
-	case MEM_CANCEL_OFFLINE:
-		break;
-	}
-
-	return notifier_from_errno(ret);
-}
-
-#endif
-
-void __init page_cgroup_init(void)
-{
-	unsigned long pfn;
-	int nid;
-
-	if (mem_cgroup_disabled())
-		return;
-
-	for_each_node_state(nid, N_MEMORY) {
-		unsigned long start_pfn, end_pfn;
-
-		start_pfn = node_start_pfn(nid);
-		end_pfn = node_end_pfn(nid);
-		/*
-		 * start_pfn and end_pfn may not be aligned to SECTION and the
-		 * page->flags of out of node pages are not initialized.  So we
-		 * scan [start_pfn, the biggest section's pfn < end_pfn) here.
-		 */
-		for (pfn = start_pfn;
-		     pfn < end_pfn;
-                     pfn = ALIGN(pfn + 1, PAGES_PER_SECTION)) {
-
-			if (!pfn_valid(pfn))
-				continue;
-			/*
-			 * Nodes's pfns can be overlapping.
-			 * We know some arch can have a nodes layout such as
-			 * -------------pfn-------------->
-			 * N0 | N1 | N2 | N0 | N1 | N2|....
-			 */
-			if (pfn_to_nid(pfn) != nid)
-				continue;
-			if (init_section_page_cgroup(pfn, nid))
-				goto oom;
-		}
-	}
-	hotplug_memory_notifier(page_cgroup_callback, 0);
-	printk(KERN_INFO "allocated %ld bytes of page_cgroup\n", total_usage);
-	printk(KERN_INFO "please try 'cgroup_disable=memory' option if you "
-			 "don't want memory cgroups\n");
-	return;
-oom:
-	printk(KERN_CRIT "try 'cgroup_disable=memory' boot option\n");
-	panic("Out of memory");
-}
-
-void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
-{
-	return;
-}
-
-#endif
-
-
-#ifdef CONFIG_MEMCG_SWAP
-
-static DEFINE_MUTEX(swap_cgroup_mutex);
-struct swap_cgroup_ctrl {
-	struct page **map;
-	unsigned long length;
-	spinlock_t	lock;
-};
-
-static struct swap_cgroup_ctrl swap_cgroup_ctrl[MAX_SWAPFILES];
-
-struct swap_cgroup {
-	unsigned short		id;
-};
-#define SC_PER_PAGE	(PAGE_SIZE/sizeof(struct swap_cgroup))
-
-/*
- * SwapCgroup implements "lookup" and "exchange" operations.
- * In typical usage, this swap_cgroup is accessed via memcg's charge/uncharge
- * against SwapCache. At swap_free(), this is accessed directly from swap.
- *
- * This means,
- *  - we have no race in "exchange" when we're accessed via SwapCache because
- *    SwapCache(and its swp_entry) is under lock.
- *  - When called via swap_free(), there is no user of this entry and no race.
- * Then, we don't need lock around "exchange".
- *
- * TODO: we can push these buffers out to HIGHMEM.
- */
-
-/*
- * allocate buffer for swap_cgroup.
- */
-static int swap_cgroup_prepare(int type)
-{
-	struct page *page;
-	struct swap_cgroup_ctrl *ctrl;
-	unsigned long idx, max;
-
-	ctrl = &swap_cgroup_ctrl[type];
-
-	for (idx = 0; idx < ctrl->length; idx++) {
-		page = alloc_page(GFP_KERNEL | __GFP_ZERO);
-		if (!page)
-			goto not_enough_page;
-		ctrl->map[idx] = page;
-	}
-	return 0;
-not_enough_page:
-	max = idx;
-	for (idx = 0; idx < max; idx++)
-		__free_page(ctrl->map[idx]);
-
-	return -ENOMEM;
-}
-
-static struct swap_cgroup *lookup_swap_cgroup(swp_entry_t ent,
-					struct swap_cgroup_ctrl **ctrlp)
-{
-	pgoff_t offset = swp_offset(ent);
-	struct swap_cgroup_ctrl *ctrl;
-	struct page *mappage;
-	struct swap_cgroup *sc;
-
-	ctrl = &swap_cgroup_ctrl[swp_type(ent)];
-	if (ctrlp)
-		*ctrlp = ctrl;
-
-	mappage = ctrl->map[offset / SC_PER_PAGE];
-	sc = page_address(mappage);
-	return sc + offset % SC_PER_PAGE;
-}
-
-/**
- * swap_cgroup_cmpxchg - cmpxchg mem_cgroup's id for this swp_entry.
- * @ent: swap entry to be cmpxchged
- * @old: old id
- * @new: new id
- *
- * Returns old id at success, 0 at failure.
- * (There is no mem_cgroup using 0 as its id)
- */
-unsigned short swap_cgroup_cmpxchg(swp_entry_t ent,
-					unsigned short old, unsigned short new)
-{
-	struct swap_cgroup_ctrl *ctrl;
-	struct swap_cgroup *sc;
-	unsigned long flags;
-	unsigned short retval;
-
-	sc = lookup_swap_cgroup(ent, &ctrl);
-
-	spin_lock_irqsave(&ctrl->lock, flags);
-	retval = sc->id;
-	if (retval == old)
-		sc->id = new;
-	else
-		retval = 0;
-	spin_unlock_irqrestore(&ctrl->lock, flags);
-	return retval;
-}
-
-/**
- * swap_cgroup_record - record mem_cgroup for this swp_entry.
- * @ent: swap entry to be recorded into
- * @id: mem_cgroup to be recorded
- *
- * Returns old value at success, 0 at failure.
- * (Of course, old value can be 0.)
- */
-unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id)
-{
-	struct swap_cgroup_ctrl *ctrl;
-	struct swap_cgroup *sc;
-	unsigned short old;
-	unsigned long flags;
-
-	sc = lookup_swap_cgroup(ent, &ctrl);
-
-	spin_lock_irqsave(&ctrl->lock, flags);
-	old = sc->id;
-	sc->id = id;
-	spin_unlock_irqrestore(&ctrl->lock, flags);
-
-	return old;
-}
-
-/**
- * lookup_swap_cgroup_id - lookup mem_cgroup id tied to swap entry
- * @ent: swap entry to be looked up.
- *
- * Returns ID of mem_cgroup at success. 0 at failure. (0 is invalid ID)
- */
-unsigned short lookup_swap_cgroup_id(swp_entry_t ent)
-{
-	return lookup_swap_cgroup(ent, NULL)->id;
-}
-
-int swap_cgroup_swapon(int type, unsigned long max_pages)
-{
-	void *array;
-	unsigned long array_size;
-	unsigned long length;
-	struct swap_cgroup_ctrl *ctrl;
-
-	if (!do_swap_account)
-		return 0;
-
-	length = DIV_ROUND_UP(max_pages, SC_PER_PAGE);
-	array_size = length * sizeof(void *);
-
-	array = vzalloc(array_size);
-	if (!array)
-		goto nomem;
-
-	ctrl = &swap_cgroup_ctrl[type];
-	mutex_lock(&swap_cgroup_mutex);
-	ctrl->length = length;
-	ctrl->map = array;
-	spin_lock_init(&ctrl->lock);
-	if (swap_cgroup_prepare(type)) {
-		/* memory shortage */
-		ctrl->map = NULL;
-		ctrl->length = 0;
-		mutex_unlock(&swap_cgroup_mutex);
-		vfree(array);
-		goto nomem;
-	}
-	mutex_unlock(&swap_cgroup_mutex);
-
-	return 0;
-nomem:
-	printk(KERN_INFO "couldn't allocate enough memory for swap_cgroup.\n");
-	printk(KERN_INFO
-		"swap_cgroup can be disabled by swapaccount=0 boot option\n");
-	return -ENOMEM;
-}
-
-void swap_cgroup_swapoff(int type)
-{
-	struct page **map;
-	unsigned long i, length;
-	struct swap_cgroup_ctrl *ctrl;
-
-	if (!do_swap_account)
-		return;
-
-	mutex_lock(&swap_cgroup_mutex);
-	ctrl = &swap_cgroup_ctrl[type];
-	map = ctrl->map;
-	length = ctrl->length;
-	ctrl->map = NULL;
-	ctrl->length = 0;
-	mutex_unlock(&swap_cgroup_mutex);
-
-	if (map) {
-		for (i = 0; i < length; i++) {
-			struct page *page = map[i];
-			if (page)
-				__free_page(page);
-		}
-		vfree(map);
-	}
-}
-
-#endif
diff --git a/mm/page_counter.c b/mm/page_counter.c
new file mode 100644
index 000000000000..a009574fbba9
--- /dev/null
+++ b/mm/page_counter.c
@@ -0,0 +1,192 @@
+/*
+ * Lockless hierarchical page accounting & limiting
+ *
+ * Copyright (C) 2014 Red Hat, Inc., Johannes Weiner
+ */
+
+#include <linux/page_counter.h>
+#include <linux/atomic.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/sched.h>
+#include <linux/bug.h>
+#include <asm/page.h>
+
+/**
+ * page_counter_cancel - take pages out of the local counter
+ * @counter: counter
+ * @nr_pages: number of pages to cancel
+ */
+void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages)
+{
+	long new;
+
+	new = atomic_long_sub_return(nr_pages, &counter->count);
+	/* More uncharges than charges? */
+	WARN_ON_ONCE(new < 0);
+}
+
+/**
+ * page_counter_charge - hierarchically charge pages
+ * @counter: counter
+ * @nr_pages: number of pages to charge
+ *
+ * NOTE: This does not consider any configured counter limits.
+ */
+void page_counter_charge(struct page_counter *counter, unsigned long nr_pages)
+{
+	struct page_counter *c;
+
+	for (c = counter; c; c = c->parent) {
+		long new;
+
+		new = atomic_long_add_return(nr_pages, &c->count);
+		/*
+		 * This is indeed racy, but we can live with some
+		 * inaccuracy in the watermark.
+		 */
+		if (new > c->watermark)
+			c->watermark = new;
+	}
+}
+
+/**
+ * page_counter_try_charge - try to hierarchically charge pages
+ * @counter: counter
+ * @nr_pages: number of pages to charge
+ * @fail: points first counter to hit its limit, if any
+ *
+ * Returns 0 on success, or -ENOMEM and @fail if the counter or one of
+ * its ancestors has hit its configured limit.
+ */
+int page_counter_try_charge(struct page_counter *counter,
+			    unsigned long nr_pages,
+			    struct page_counter **fail)
+{
+	struct page_counter *c;
+
+	for (c = counter; c; c = c->parent) {
+		long new;
+		/*
+		 * Charge speculatively to avoid an expensive CAS.  If
+		 * a bigger charge fails, it might falsely lock out a
+		 * racing smaller charge and send it into reclaim
+		 * early, but the error is limited to the difference
+		 * between the two sizes, which is less than 2M/4M in
+		 * case of a THP locking out a regular page charge.
+		 *
+		 * The atomic_long_add_return() implies a full memory
+		 * barrier between incrementing the count and reading
+		 * the limit.  When racing with page_counter_limit(),
+		 * we either see the new limit or the setter sees the
+		 * counter has changed and retries.
+		 */
+		new = atomic_long_add_return(nr_pages, &c->count);
+		if (new > c->limit) {
+			atomic_long_sub(nr_pages, &c->count);
+			/*
+			 * This is racy, but we can live with some
+			 * inaccuracy in the failcnt.
+			 */
+			c->failcnt++;
+			*fail = c;
+			goto failed;
+		}
+		/*
+		 * Just like with failcnt, we can live with some
+		 * inaccuracy in the watermark.
+		 */
+		if (new > c->watermark)
+			c->watermark = new;
+	}
+	return 0;
+
+failed:
+	for (c = counter; c != *fail; c = c->parent)
+		page_counter_cancel(c, nr_pages);
+
+	return -ENOMEM;
+}
+
+/**
+ * page_counter_uncharge - hierarchically uncharge pages
+ * @counter: counter
+ * @nr_pages: number of pages to uncharge
+ */
+void page_counter_uncharge(struct page_counter *counter, unsigned long nr_pages)
+{
+	struct page_counter *c;
+
+	for (c = counter; c; c = c->parent)
+		page_counter_cancel(c, nr_pages);
+}
+
+/**
+ * page_counter_limit - limit the number of pages allowed
+ * @counter: counter
+ * @limit: limit to set
+ *
+ * Returns 0 on success, -EBUSY if the current number of pages on the
+ * counter already exceeds the specified limit.
+ *
+ * The caller must serialize invocations on the same counter.
+ */
+int page_counter_limit(struct page_counter *counter, unsigned long limit)
+{
+	for (;;) {
+		unsigned long old;
+		long count;
+
+		/*
+		 * Update the limit while making sure that it's not
+		 * below the concurrently-changing counter value.
+		 *
+		 * The xchg implies two full memory barriers before
+		 * and after, so the read-swap-read is ordered and
+		 * ensures coherency with page_counter_try_charge():
+		 * that function modifies the count before checking
+		 * the limit, so if it sees the old limit, we see the
+		 * modified counter and retry.
+		 */
+		count = atomic_long_read(&counter->count);
+
+		if (count > limit)
+			return -EBUSY;
+
+		old = xchg(&counter->limit, limit);
+
+		if (atomic_long_read(&counter->count) <= count)
+			return 0;
+
+		counter->limit = old;
+		cond_resched();
+	}
+}
+
+/**
+ * page_counter_memparse - memparse() for page counter limits
+ * @buf: string to parse
+ * @nr_pages: returns the result in number of pages
+ *
+ * Returns -EINVAL, or 0 and @nr_pages on success.  @nr_pages will be
+ * limited to %PAGE_COUNTER_MAX.
+ */
+int page_counter_memparse(const char *buf, unsigned long *nr_pages)
+{
+	char unlimited[] = "-1";
+	char *end;
+	u64 bytes;
+
+	if (!strncmp(buf, unlimited, sizeof(unlimited))) {
+		*nr_pages = PAGE_COUNTER_MAX;
+		return 0;
+	}
+
+	bytes = memparse(buf, &end);
+	if (*end != '\0')
+		return -EINVAL;
+
+	*nr_pages = min(bytes / PAGE_SIZE, (u64)PAGE_COUNTER_MAX);
+
+	return 0;
+}
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index d1473b2e9481..e5d9c5277966 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -60,6 +60,7 @@ out:
 		int migratetype = get_pageblock_migratetype(page);
 
 		set_pageblock_migratetype(page, MIGRATE_ISOLATE);
+		zone->nr_isolate_pageblock++;
 		nr_pages = move_freepages_block(zone, page, MIGRATE_ISOLATE);
 
 		__mod_zone_freepage_state(zone, -nr_pages, migratetype);
@@ -67,7 +68,7 @@ out:
 
 	spin_unlock_irqrestore(&zone->lock, flags);
 	if (!ret)
-		drain_all_pages();
+		drain_all_pages(zone);
 	return ret;
 }
 
@@ -75,16 +76,54 @@ void unset_migratetype_isolate(struct page *page, unsigned migratetype)
 {
 	struct zone *zone;
 	unsigned long flags, nr_pages;
+	struct page *isolated_page = NULL;
+	unsigned int order;
+	unsigned long page_idx, buddy_idx;
+	struct page *buddy;
 
 	zone = page_zone(page);
 	spin_lock_irqsave(&zone->lock, flags);
 	if (get_pageblock_migratetype(page) != MIGRATE_ISOLATE)
 		goto out;
-	nr_pages = move_freepages_block(zone, page, migratetype);
-	__mod_zone_freepage_state(zone, nr_pages, migratetype);
+
+	/*
+	 * Because freepage with more than pageblock_order on isolated
+	 * pageblock is restricted to merge due to freepage counting problem,
+	 * it is possible that there is free buddy page.
+	 * move_freepages_block() doesn't care of merge so we need other
+	 * approach in order to merge them. Isolation and free will make
+	 * these pages to be merged.
+	 */
+	if (PageBuddy(page)) {
+		order = page_order(page);
+		if (order >= pageblock_order) {
+			page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1);
+			buddy_idx = __find_buddy_index(page_idx, order);
+			buddy = page + (buddy_idx - page_idx);
+
+			if (!is_migrate_isolate_page(buddy)) {
+				__isolate_free_page(page, order);
+				set_page_refcounted(page);
+				isolated_page = page;
+			}
+		}
+	}
+
+	/*
+	 * If we isolate freepage with more than pageblock_order, there
+	 * should be no freepage in the range, so we could avoid costly
+	 * pageblock scanning for freepage moving.
+	 */
+	if (!isolated_page) {
+		nr_pages = move_freepages_block(zone, page, migratetype);
+		__mod_zone_freepage_state(zone, nr_pages, migratetype);
+	}
 	set_pageblock_migratetype(page, migratetype);
+	zone->nr_isolate_pageblock--;
 out:
 	spin_unlock_irqrestore(&zone->lock, flags);
+	if (isolated_page)
+		__free_pages(isolated_page, order);
 }
 
 static inline struct page *
@@ -137,8 +176,11 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 undo:
 	for (pfn = start_pfn;
 	     pfn < undo_pfn;
-	     pfn += pageblock_nr_pages)
-		unset_migratetype_isolate(pfn_to_page(pfn), migratetype);
+	     pfn += pageblock_nr_pages) {
+		page = __first_valid_page(pfn, pageblock_nr_pages);
+		if (page)
+			unset_migratetype_isolate(page, migratetype);
+	}
 
 	return -EBUSY;
 }
diff --git a/mm/rmap.c b/mm/rmap.c
index 19886fb2f13a..e3354b2c61d0 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -23,7 +23,7 @@
  * inode->i_mutex	(while writing or truncating, not reading or faulting)
  *   mm->mmap_sem
  *     page->flags PG_locked (lock_page)
- *       mapping->i_mmap_mutex
+ *       mapping->i_mmap_rwsem
  *         anon_vma->rwsem
  *           mm->page_table_lock or pte_lock
  *             zone->lru_lock (in mark_page_accessed, isolate_lru_page)
@@ -1051,7 +1051,7 @@ void page_add_file_rmap(struct page *page)
 		__inc_zone_page_state(page, NR_FILE_MAPPED);
 		mem_cgroup_inc_page_stat(memcg, MEM_CGROUP_STAT_FILE_MAPPED);
 	}
-	mem_cgroup_end_page_stat(memcg, locked, flags);
+	mem_cgroup_end_page_stat(memcg, &locked, &flags);
 }
 
 static void page_remove_file_rmap(struct page *page)
@@ -1081,7 +1081,7 @@ static void page_remove_file_rmap(struct page *page)
 	if (unlikely(PageMlocked(page)))
 		clear_page_mlock(page);
 out:
-	mem_cgroup_end_page_stat(memcg, locked, flags);
+	mem_cgroup_end_page_stat(memcg, &locked, &flags);
 }
 
 /**
@@ -1258,7 +1258,7 @@ out_mlock:
 	/*
 	 * We need mmap_sem locking, Otherwise VM_LOCKED check makes
 	 * unstable result and race. Plus, We can't wait here because
-	 * we now hold anon_vma->rwsem or mapping->i_mmap_mutex.
+	 * we now hold anon_vma->rwsem or mapping->i_mmap_rwsem.
 	 * if trylock failed, the page remain in evictable lru and later
 	 * vmscan could retry to move the page to unevictable lru if the
 	 * page is actually mlocked.
@@ -1378,7 +1378,7 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount,
 
 		/* Nuke the page table entry. */
 		flush_cache_page(vma, address, pte_pfn(*pte));
-		pteval = ptep_clear_flush(vma, address, pte);
+		pteval = ptep_clear_flush_notify(vma, address, pte);
 
 		/* If nonlinear, store the file page offset in the pte. */
 		if (page->index != linear_page_index(vma, address)) {
@@ -1633,7 +1633,7 @@ static struct anon_vma *rmap_walk_anon_lock(struct page *page,
 static int rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc)
 {
 	struct anon_vma *anon_vma;
-	pgoff_t pgoff = page_to_pgoff(page);
+	pgoff_t pgoff;
 	struct anon_vma_chain *avc;
 	int ret = SWAP_AGAIN;
 
@@ -1641,6 +1641,7 @@ static int rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc)
 	if (!anon_vma)
 		return ret;
 
+	pgoff = page_to_pgoff(page);
 	anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, pgoff) {
 		struct vm_area_struct *vma = avc->vma;
 		unsigned long address = vma_address(page, vma);
@@ -1674,7 +1675,7 @@ static int rmap_walk_anon(struct page *page, struct rmap_walk_control *rwc)
 static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc)
 {
 	struct address_space *mapping = page->mapping;
-	pgoff_t pgoff = page_to_pgoff(page);
+	pgoff_t pgoff;
 	struct vm_area_struct *vma;
 	int ret = SWAP_AGAIN;
 
@@ -1682,13 +1683,15 @@ static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc)
 	 * The page lock not only makes sure that page->mapping cannot
 	 * suddenly be NULLified by truncation, it makes sure that the
 	 * structure at mapping cannot be freed and reused yet,
-	 * so we can safely take mapping->i_mmap_mutex.
+	 * so we can safely take mapping->i_mmap_rwsem.
 	 */
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 
 	if (!mapping)
 		return ret;
-	mutex_lock(&mapping->i_mmap_mutex);
+
+	pgoff = page_to_pgoff(page);
+	i_mmap_lock_read(mapping);
 	vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) {
 		unsigned long address = vma_address(page, vma);
 
@@ -1709,9 +1712,8 @@ static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc)
 		goto done;
 
 	ret = rwc->file_nonlinear(page, mapping, rwc->arg);
-
 done:
-	mutex_unlock(&mapping->i_mmap_mutex);
+	i_mmap_unlock_read(mapping);
 	return ret;
 }
 
diff --git a/mm/slab.c b/mm/slab.c
index 063a91bc8826..a5cafe00e2b7 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -2590,7 +2590,10 @@ static int cache_grow(struct kmem_cache *cachep,
 	 * Be lazy and only check for valid flags here,  keeping it out of the
 	 * critical path in kmem_cache_alloc().
 	 */
-	BUG_ON(flags & GFP_SLAB_BUG_MASK);
+	if (unlikely(flags & GFP_SLAB_BUG_MASK)) {
+		pr_emerg("gfp: %u\n", flags & GFP_SLAB_BUG_MASK);
+		BUG();
+	}
 	local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK);
 
 	/* Take the node list lock to change the colour_next on this node */
@@ -3580,11 +3583,11 @@ static int alloc_kmem_cache_node(struct kmem_cache *cachep, gfp_t gfp)
 
 	for_each_online_node(node) {
 
-                if (use_alien_caches) {
-                        new_alien = alloc_alien_cache(node, cachep->limit, gfp);
-                        if (!new_alien)
-                                goto fail;
-                }
+		if (use_alien_caches) {
+			new_alien = alloc_alien_cache(node, cachep->limit, gfp);
+			if (!new_alien)
+				goto fail;
+		}
 
 		new_shared = NULL;
 		if (cachep->shared) {
@@ -4043,12 +4046,6 @@ ssize_t slabinfo_write(struct file *file, const char __user *buffer,
 
 #ifdef CONFIG_DEBUG_SLAB_LEAK
 
-static void *leaks_start(struct seq_file *m, loff_t *pos)
-{
-	mutex_lock(&slab_mutex);
-	return seq_list_start(&slab_caches, *pos);
-}
-
 static inline int add_caller(unsigned long *n, unsigned long v)
 {
 	unsigned long *p;
@@ -4170,7 +4167,7 @@ static int leaks_show(struct seq_file *m, void *p)
 }
 
 static const struct seq_operations slabstats_op = {
-	.start = leaks_start,
+	.start = slab_start,
 	.next = slab_next,
 	.stop = slab_stop,
 	.show = leaks_show,
diff --git a/mm/slab.h b/mm/slab.h
index ab019e63e3c2..3347fd77f7be 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -357,7 +357,9 @@ static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
 
 #endif
 
+void *slab_start(struct seq_file *m, loff_t *pos);
 void *slab_next(struct seq_file *m, void *p, loff_t *pos);
 void slab_stop(struct seq_file *m, void *p);
+int memcg_slab_show(struct seq_file *m, void *p);
 
 #endif /* MM_SLAB_H */
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 406944207b61..e03dd6f2a272 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -240,7 +240,7 @@ struct kmem_cache *find_mergeable(size_t size, size_t align,
 	size = ALIGN(size, align);
 	flags = kmem_cache_flags(size, flags, name, NULL);
 
-	list_for_each_entry(s, &slab_caches, list) {
+	list_for_each_entry_reverse(s, &slab_caches, list) {
 		if (slab_unmergeable(s))
 			continue;
 
@@ -259,6 +259,10 @@ struct kmem_cache *find_mergeable(size_t size, size_t align,
 		if (s->size - size >= sizeof(void *))
 			continue;
 
+		if (IS_ENABLED(CONFIG_SLAB) && align &&
+			(align > s->align || s->align % align))
+			continue;
+
 		return s;
 	}
 	return NULL;
@@ -807,7 +811,7 @@ EXPORT_SYMBOL(kmalloc_order_trace);
 #define SLABINFO_RIGHTS S_IRUSR
 #endif
 
-void print_slabinfo_header(struct seq_file *m)
+static void print_slabinfo_header(struct seq_file *m)
 {
 	/*
 	 * Output format version, so at least we can change it
@@ -830,14 +834,9 @@ void print_slabinfo_header(struct seq_file *m)
 	seq_putc(m, '\n');
 }
 
-static void *s_start(struct seq_file *m, loff_t *pos)
+void *slab_start(struct seq_file *m, loff_t *pos)
 {
-	loff_t n = *pos;
-
 	mutex_lock(&slab_mutex);
-	if (!n)
-		print_slabinfo_header(m);
-
 	return seq_list_start(&slab_caches, *pos);
 }
 
@@ -877,7 +876,7 @@ memcg_accumulate_slabinfo(struct kmem_cache *s, struct slabinfo *info)
 	}
 }
 
-int cache_show(struct kmem_cache *s, struct seq_file *m)
+static void cache_show(struct kmem_cache *s, struct seq_file *m)
 {
 	struct slabinfo sinfo;
 
@@ -896,17 +895,32 @@ int cache_show(struct kmem_cache *s, struct seq_file *m)
 		   sinfo.active_slabs, sinfo.num_slabs, sinfo.shared_avail);
 	slabinfo_show_stats(m, s);
 	seq_putc(m, '\n');
+}
+
+static int slab_show(struct seq_file *m, void *p)
+{
+	struct kmem_cache *s = list_entry(p, struct kmem_cache, list);
+
+	if (p == slab_caches.next)
+		print_slabinfo_header(m);
+	if (is_root_cache(s))
+		cache_show(s, m);
 	return 0;
 }
 
-static int s_show(struct seq_file *m, void *p)
+#ifdef CONFIG_MEMCG_KMEM
+int memcg_slab_show(struct seq_file *m, void *p)
 {
 	struct kmem_cache *s = list_entry(p, struct kmem_cache, list);
+	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
 
-	if (!is_root_cache(s))
-		return 0;
-	return cache_show(s, m);
+	if (p == slab_caches.next)
+		print_slabinfo_header(m);
+	if (!is_root_cache(s) && s->memcg_params->memcg == memcg)
+		cache_show(s, m);
+	return 0;
 }
+#endif
 
 /*
  * slabinfo_op - iterator that generates /proc/slabinfo
@@ -922,10 +936,10 @@ static int s_show(struct seq_file *m, void *p)
  * + further values on SMP and with statistics enabled
  */
 static const struct seq_operations slabinfo_op = {
-	.start = s_start,
+	.start = slab_start,
 	.next = slab_next,
 	.stop = slab_stop,
-	.show = s_show,
+	.show = slab_show,
 };
 
 static int slabinfo_open(struct inode *inode, struct file *file)
diff --git a/mm/slub.c b/mm/slub.c
index 7d12f51d9bac..765c5884d03d 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -849,12 +849,12 @@ static int check_slab(struct kmem_cache *s, struct page *page)
 	maxobj = order_objects(compound_order(page), s->size, s->reserved);
 	if (page->objects > maxobj) {
 		slab_err(s, page, "objects %u > max %u",
-			s->name, page->objects, maxobj);
+			page->objects, maxobj);
 		return 0;
 	}
 	if (page->inuse > page->objects) {
 		slab_err(s, page, "inuse %u > max %u",
-			s->name, page->inuse, page->objects);
+			page->inuse, page->objects);
 		return 0;
 	}
 	/* Slab_pad_check fixes things up after itself */
@@ -871,7 +871,7 @@ static int on_freelist(struct kmem_cache *s, struct page *page, void *search)
 	int nr = 0;
 	void *fp;
 	void *object = NULL;
-	unsigned long max_objects;
+	int max_objects;
 
 	fp = page->freelist;
 	while (fp && nr <= page->objects) {
@@ -1377,7 +1377,10 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
 	int order;
 	int idx;
 
-	BUG_ON(flags & GFP_SLAB_BUG_MASK);
+	if (unlikely(flags & GFP_SLAB_BUG_MASK)) {
+		pr_emerg("gfp: %u\n", flags & GFP_SLAB_BUG_MASK);
+		BUG();
+	}
 
 	page = allocate_slab(s,
 		flags & (GFP_RECLAIM_MASK | GFP_CONSTRAINT_MASK), node);
@@ -2555,7 +2558,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
 
 			} else { /* Needs to be taken off a list */
 
-	                        n = get_node(s, page_to_nid(page));
+				n = get_node(s, page_to_nid(page));
 				/*
 				 * Speculatively acquire the list_lock.
 				 * If the cmpxchg does not succeed then we may
@@ -2588,10 +2591,10 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
 		 * The list lock was not taken therefore no list
 		 * activity can be necessary.
 		 */
-                if (was_frozen)
-                        stat(s, FREE_FROZEN);
-                return;
-        }
+		if (was_frozen)
+			stat(s, FREE_FROZEN);
+		return;
+	}
 
 	if (unlikely(!new.inuse && n->nr_partial >= s->min_partial))
 		goto slab_empty;
diff --git a/mm/swap_cgroup.c b/mm/swap_cgroup.c
new file mode 100644
index 000000000000..b5f7f24b8dd1
--- /dev/null
+++ b/mm/swap_cgroup.c
@@ -0,0 +1,208 @@
+#include <linux/swap_cgroup.h>
+#include <linux/vmalloc.h>
+#include <linux/mm.h>
+
+#include <linux/swapops.h> /* depends on mm.h include */
+
+static DEFINE_MUTEX(swap_cgroup_mutex);
+struct swap_cgroup_ctrl {
+	struct page **map;
+	unsigned long length;
+	spinlock_t	lock;
+};
+
+static struct swap_cgroup_ctrl swap_cgroup_ctrl[MAX_SWAPFILES];
+
+struct swap_cgroup {
+	unsigned short		id;
+};
+#define SC_PER_PAGE	(PAGE_SIZE/sizeof(struct swap_cgroup))
+
+/*
+ * SwapCgroup implements "lookup" and "exchange" operations.
+ * In typical usage, this swap_cgroup is accessed via memcg's charge/uncharge
+ * against SwapCache. At swap_free(), this is accessed directly from swap.
+ *
+ * This means,
+ *  - we have no race in "exchange" when we're accessed via SwapCache because
+ *    SwapCache(and its swp_entry) is under lock.
+ *  - When called via swap_free(), there is no user of this entry and no race.
+ * Then, we don't need lock around "exchange".
+ *
+ * TODO: we can push these buffers out to HIGHMEM.
+ */
+
+/*
+ * allocate buffer for swap_cgroup.
+ */
+static int swap_cgroup_prepare(int type)
+{
+	struct page *page;
+	struct swap_cgroup_ctrl *ctrl;
+	unsigned long idx, max;
+
+	ctrl = &swap_cgroup_ctrl[type];
+
+	for (idx = 0; idx < ctrl->length; idx++) {
+		page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+		if (!page)
+			goto not_enough_page;
+		ctrl->map[idx] = page;
+	}
+	return 0;
+not_enough_page:
+	max = idx;
+	for (idx = 0; idx < max; idx++)
+		__free_page(ctrl->map[idx]);
+
+	return -ENOMEM;
+}
+
+static struct swap_cgroup *lookup_swap_cgroup(swp_entry_t ent,
+					struct swap_cgroup_ctrl **ctrlp)
+{
+	pgoff_t offset = swp_offset(ent);
+	struct swap_cgroup_ctrl *ctrl;
+	struct page *mappage;
+	struct swap_cgroup *sc;
+
+	ctrl = &swap_cgroup_ctrl[swp_type(ent)];
+	if (ctrlp)
+		*ctrlp = ctrl;
+
+	mappage = ctrl->map[offset / SC_PER_PAGE];
+	sc = page_address(mappage);
+	return sc + offset % SC_PER_PAGE;
+}
+
+/**
+ * swap_cgroup_cmpxchg - cmpxchg mem_cgroup's id for this swp_entry.
+ * @ent: swap entry to be cmpxchged
+ * @old: old id
+ * @new: new id
+ *
+ * Returns old id at success, 0 at failure.
+ * (There is no mem_cgroup using 0 as its id)
+ */
+unsigned short swap_cgroup_cmpxchg(swp_entry_t ent,
+					unsigned short old, unsigned short new)
+{
+	struct swap_cgroup_ctrl *ctrl;
+	struct swap_cgroup *sc;
+	unsigned long flags;
+	unsigned short retval;
+
+	sc = lookup_swap_cgroup(ent, &ctrl);
+
+	spin_lock_irqsave(&ctrl->lock, flags);
+	retval = sc->id;
+	if (retval == old)
+		sc->id = new;
+	else
+		retval = 0;
+	spin_unlock_irqrestore(&ctrl->lock, flags);
+	return retval;
+}
+
+/**
+ * swap_cgroup_record - record mem_cgroup for this swp_entry.
+ * @ent: swap entry to be recorded into
+ * @id: mem_cgroup to be recorded
+ *
+ * Returns old value at success, 0 at failure.
+ * (Of course, old value can be 0.)
+ */
+unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id)
+{
+	struct swap_cgroup_ctrl *ctrl;
+	struct swap_cgroup *sc;
+	unsigned short old;
+	unsigned long flags;
+
+	sc = lookup_swap_cgroup(ent, &ctrl);
+
+	spin_lock_irqsave(&ctrl->lock, flags);
+	old = sc->id;
+	sc->id = id;
+	spin_unlock_irqrestore(&ctrl->lock, flags);
+
+	return old;
+}
+
+/**
+ * lookup_swap_cgroup_id - lookup mem_cgroup id tied to swap entry
+ * @ent: swap entry to be looked up.
+ *
+ * Returns ID of mem_cgroup at success. 0 at failure. (0 is invalid ID)
+ */
+unsigned short lookup_swap_cgroup_id(swp_entry_t ent)
+{
+	return lookup_swap_cgroup(ent, NULL)->id;
+}
+
+int swap_cgroup_swapon(int type, unsigned long max_pages)
+{
+	void *array;
+	unsigned long array_size;
+	unsigned long length;
+	struct swap_cgroup_ctrl *ctrl;
+
+	if (!do_swap_account)
+		return 0;
+
+	length = DIV_ROUND_UP(max_pages, SC_PER_PAGE);
+	array_size = length * sizeof(void *);
+
+	array = vzalloc(array_size);
+	if (!array)
+		goto nomem;
+
+	ctrl = &swap_cgroup_ctrl[type];
+	mutex_lock(&swap_cgroup_mutex);
+	ctrl->length = length;
+	ctrl->map = array;
+	spin_lock_init(&ctrl->lock);
+	if (swap_cgroup_prepare(type)) {
+		/* memory shortage */
+		ctrl->map = NULL;
+		ctrl->length = 0;
+		mutex_unlock(&swap_cgroup_mutex);
+		vfree(array);
+		goto nomem;
+	}
+	mutex_unlock(&swap_cgroup_mutex);
+
+	return 0;
+nomem:
+	printk(KERN_INFO "couldn't allocate enough memory for swap_cgroup.\n");
+	printk(KERN_INFO
+		"swap_cgroup can be disabled by swapaccount=0 boot option\n");
+	return -ENOMEM;
+}
+
+void swap_cgroup_swapoff(int type)
+{
+	struct page **map;
+	unsigned long i, length;
+	struct swap_cgroup_ctrl *ctrl;
+
+	if (!do_swap_account)
+		return;
+
+	mutex_lock(&swap_cgroup_mutex);
+	ctrl = &swap_cgroup_ctrl[type];
+	map = ctrl->map;
+	length = ctrl->length;
+	ctrl->map = NULL;
+	ctrl->length = 0;
+	mutex_unlock(&swap_cgroup_mutex);
+
+	if (map) {
+		for (i = 0; i < length; i++) {
+			struct page *page = map[i];
+			if (page)
+				__free_page(page);
+		}
+		vfree(map);
+	}
+}
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 154444918685..9711342987a0 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -17,7 +17,6 @@
 #include <linux/blkdev.h>
 #include <linux/pagevec.h>
 #include <linux/migrate.h>
-#include <linux/page_cgroup.h>
 
 #include <asm/pgtable.h>
 
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 8798b2e0ac59..63f55ccb9b26 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -38,7 +38,7 @@
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <linux/swapops.h>
-#include <linux/page_cgroup.h>
+#include <linux/swap_cgroup.h>
 
 static bool swap_count_continued(struct swap_info_struct *, pgoff_t,
 				 unsigned char);
diff --git a/mm/util.c b/mm/util.c
index fec39d4509a9..d25558ba661c 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -3,6 +3,7 @@
 #include <linux/string.h>
 #include <linux/compiler.h>
 #include <linux/export.h>
+#include <linux/ctype.h>
 #include <linux/err.h>
 #include <linux/sched.h>
 #include <linux/security.h>
@@ -62,6 +63,35 @@ char *kstrndup(const char *s, size_t max, gfp_t gfp)
 EXPORT_SYMBOL(kstrndup);
 
 /**
+ * kstrimdup - Trim and copy a %NUL terminated string.
+ * @s: the string to trim and duplicate
+ * @gfp: the GFP mask used in the kmalloc() call when allocating memory
+ *
+ * Returns an address, which the caller must kfree, containing
+ * a duplicate of the passed string with leading and/or trailing
+ * whitespace (as defined by isspace) removed.
+ */
+char *kstrimdup(const char *s, gfp_t gfp)
+{
+	char *buf;
+	char *begin = skip_spaces(s);
+	size_t len = strlen(begin);
+
+	while (len && isspace(begin[len - 1]))
+		len--;
+
+	buf = kmalloc_track_caller(len + 1, gfp);
+	if (!buf)
+		return NULL;
+
+	memcpy(buf, begin, len);
+	buf[len] = '\0';
+
+	return buf;
+}
+EXPORT_SYMBOL(kstrimdup);
+
+/**
  * kmemdup - duplicate region of memory
  *
  * @src: memory region to duplicate
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 90520af7f186..8a18196fcdff 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -463,8 +463,7 @@ overflow:
 		goto retry;
 	}
 	if (printk_ratelimit())
-		printk(KERN_WARNING
-			"vmap allocation for size %lu failed: "
+		pr_warn("vmap allocation for size %lu failed: "
 			"use vmalloc=<size> to increase size.\n", size);
 	kfree(va);
 	return ERR_PTR(-EBUSY);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 38878b2ab1d0..a384339bf718 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -260,8 +260,7 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker,
 	do_div(delta, lru_pages + 1);
 	total_scan += delta;
 	if (total_scan < 0) {
-		printk(KERN_ERR
-		"shrink_slab: %pF negative objects to delete nr=%ld\n",
+		pr_err("shrink_slab: %pF negative objects to delete nr=%ld\n",
 		       shrinker->scan_objects, total_scan);
 		total_scan = freeable;
 	}
@@ -875,7 +874,8 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		 * end of the LRU a second time.
 		 */
 		mapping = page_mapping(page);
-		if ((mapping && bdi_write_congested(mapping->backing_dev_info)) ||
+		if (((dirty || writeback) && mapping &&
+		     bdi_write_congested(mapping->backing_dev_info)) ||
 		    (writeback && PageReclaim(page)))
 			nr_congested++;
 
@@ -2249,7 +2249,7 @@ static inline bool should_continue_reclaim(struct zone *zone,
 		return true;
 
 	/* If compaction would go ahead or the allocation would succeed, stop */
-	switch (compaction_suitable(zone, sc->order)) {
+	switch (compaction_suitable(zone, sc->order, 0, 0)) {
 	case COMPACT_PARTIAL:
 	case COMPACT_CONTINUE:
 		return false;
@@ -2346,7 +2346,7 @@ static inline bool compaction_ready(struct zone *zone, int order)
 	 * If compaction is not ready to start and allocation is not likely
 	 * to succeed without it, then keep reclaiming.
 	 */
-	if (compaction_suitable(zone, order) == COMPACT_SKIPPED)
+	if (compaction_suitable(zone, order, 0, 0) == COMPACT_SKIPPED)
 		return false;
 
 	return watermark_ok;
@@ -2825,8 +2825,8 @@ static bool zone_balanced(struct zone *zone, int order,
 				    balance_gap, classzone_idx, 0))
 		return false;
 
-	if (IS_ENABLED(CONFIG_COMPACTION) && order &&
-	    compaction_suitable(zone, order) == COMPACT_SKIPPED)
+	if (IS_ENABLED(CONFIG_COMPACTION) && order && compaction_suitable(zone,
+				order, 0, classzone_idx) == COMPACT_SKIPPED)
 		return false;
 
 	return true;
@@ -2953,8 +2953,8 @@ static bool kswapd_shrink_zone(struct zone *zone,
 	 * from memory. Do not reclaim more than needed for compaction.
 	 */
 	if (IS_ENABLED(CONFIG_COMPACTION) && sc->order &&
-			compaction_suitable(zone, sc->order) !=
-				COMPACT_SKIPPED)
+			compaction_suitable(zone, sc->order, 0, classzone_idx)
+							!= COMPACT_SKIPPED)
 		testorder = 0;
 
 	/*
diff --git a/mm/zbud.c b/mm/zbud.c
index ecf1dbef6983..db8de747bd5a 100644
--- a/mm/zbud.c
+++ b/mm/zbud.c
@@ -132,7 +132,7 @@ static struct zbud_ops zbud_zpool_ops = {
 
 static void *zbud_zpool_create(gfp_t gfp, struct zpool_ops *zpool_ops)
 {
-	return zbud_create_pool(gfp, &zbud_zpool_ops);
+	return zbud_create_pool(gfp, zpool_ops ? &zbud_zpool_ops : NULL);
 }
 
 static void zbud_zpool_destroy(void *pool)
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 839a48c3ca27..b3b57ef85830 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -214,7 +214,7 @@ struct link_free {
 };
 
 struct zs_pool {
-	struct size_class size_class[ZS_SIZE_CLASSES];
+	struct size_class *size_class[ZS_SIZE_CLASSES];
 
 	gfp_t flags;	/* allocation flags used when growing pool */
 	atomic_long_t pages_allocated;
@@ -468,7 +468,7 @@ static enum fullness_group fix_fullness_group(struct zs_pool *pool,
 	if (newfg == currfg)
 		goto out;
 
-	class = &pool->size_class[class_idx];
+	class = pool->size_class[class_idx];
 	remove_zspage(page, class, currfg);
 	insert_zspage(page, class, newfg);
 	set_zspage_mapping(page, class_idx, newfg);
@@ -925,6 +925,23 @@ fail:
 	return notifier_to_errno(ret);
 }
 
+static unsigned int get_maxobj_per_zspage(int size, int pages_per_zspage)
+{
+	return pages_per_zspage * PAGE_SIZE / size;
+}
+
+static bool can_merge(struct size_class *prev, int size, int pages_per_zspage)
+{
+	if (prev->pages_per_zspage != pages_per_zspage)
+		return false;
+
+	if (get_maxobj_per_zspage(prev->size, prev->pages_per_zspage)
+		!= get_maxobj_per_zspage(size, pages_per_zspage))
+		return false;
+
+	return true;
+}
+
 /**
  * zs_create_pool - Creates an allocation pool to work from.
  * @flags: allocation flags used to allocate pool metadata
@@ -945,25 +962,56 @@ struct zs_pool *zs_create_pool(gfp_t flags)
 	if (!pool)
 		return NULL;
 
-	for (i = 0; i < ZS_SIZE_CLASSES; i++) {
+	/*
+	 * Iterate reversly, because, size of size_class that we want to use
+	 * for merging should be larger or equal to current size.
+	 */
+	for (i = ZS_SIZE_CLASSES - 1; i >= 0; i--) {
 		int size;
+		int pages_per_zspage;
 		struct size_class *class;
+		struct size_class *prev_class;
 
 		size = ZS_MIN_ALLOC_SIZE + i * ZS_SIZE_CLASS_DELTA;
 		if (size > ZS_MAX_ALLOC_SIZE)
 			size = ZS_MAX_ALLOC_SIZE;
+		pages_per_zspage = get_pages_per_zspage(size);
+
+		/*
+		 * size_class is used for normal zsmalloc operation such
+		 * as alloc/free for that size. Although it is natural that we
+		 * have one size_class for each size, there is a chance that we
+		 * can get more memory utilization if we use one size_class for
+		 * many different sizes whose size_class have same
+		 * characteristics. So, we makes size_class point to
+		 * previous size_class if possible.
+		 */
+		if (i < ZS_SIZE_CLASSES - 1) {
+			prev_class = pool->size_class[i + 1];
+			if (can_merge(prev_class, size, pages_per_zspage)) {
+				pool->size_class[i] = prev_class;
+				continue;
+			}
+		}
+
+		class = kzalloc(sizeof(struct size_class), GFP_KERNEL);
+		if (!class)
+			goto err;
 
-		class = &pool->size_class[i];
 		class->size = size;
 		class->index = i;
+		class->pages_per_zspage = pages_per_zspage;
 		spin_lock_init(&class->lock);
-		class->pages_per_zspage = get_pages_per_zspage(size);
-
+		pool->size_class[i] = class;
 	}
 
 	pool->flags = flags;
 
 	return pool;
+
+err:
+	zs_destroy_pool(pool);
+	return NULL;
 }
 EXPORT_SYMBOL_GPL(zs_create_pool);
 
@@ -973,7 +1021,13 @@ void zs_destroy_pool(struct zs_pool *pool)
 
 	for (i = 0; i < ZS_SIZE_CLASSES; i++) {
 		int fg;
-		struct size_class *class = &pool->size_class[i];
+		struct size_class *class = pool->size_class[i];
+
+		if (!class)
+			continue;
+
+		if (class->index != i)
+			continue;
 
 		for (fg = 0; fg < _ZS_NR_FULLNESS_GROUPS; fg++) {
 			if (class->fullness_list[fg]) {
@@ -981,6 +1035,7 @@ void zs_destroy_pool(struct zs_pool *pool)
 					class->size, fg);
 			}
 		}
+		kfree(class);
 	}
 	kfree(pool);
 }
@@ -999,7 +1054,6 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size)
 {
 	unsigned long obj;
 	struct link_free *link;
-	int class_idx;
 	struct size_class *class;
 
 	struct page *first_page, *m_page;
@@ -1008,9 +1062,7 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size)
 	if (unlikely(!size || size > ZS_MAX_ALLOC_SIZE))
 		return 0;
 
-	class_idx = get_size_class_index(size);
-	class = &pool->size_class[class_idx];
-	BUG_ON(class_idx != class->index);
+	class = pool->size_class[get_size_class_index(size)];
 
 	spin_lock(&class->lock);
 	first_page = find_get_zspage(class);
@@ -1063,7 +1115,7 @@ void zs_free(struct zs_pool *pool, unsigned long obj)
 	first_page = get_first_page(f_page);
 
 	get_zspage_mapping(first_page, &class_idx, &fullness);
-	class = &pool->size_class[class_idx];
+	class = pool->size_class[class_idx];
 	f_offset = obj_idx_to_offset(f_page, f_objidx, class->size);
 
 	spin_lock(&class->lock);
@@ -1124,7 +1176,7 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle,
 
 	obj_handle_to_location(handle, &page, &obj_idx);
 	get_zspage_mapping(get_first_page(page), &class_idx, &fg);
-	class = &pool->size_class[class_idx];
+	class = pool->size_class[class_idx];
 	off = obj_idx_to_offset(page, obj_idx, class->size);
 
 	area = &get_cpu_var(zs_map_area);
@@ -1158,7 +1210,7 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle)
 
 	obj_handle_to_location(handle, &page, &obj_idx);
 	get_zspage_mapping(get_first_page(page), &class_idx, &fg);
-	class = &pool->size_class[class_idx];
+	class = pool->size_class[class_idx];
 	off = obj_idx_to_offset(page, obj_idx, class->size);
 
 	area = this_cpu_ptr(&zs_map_area);
diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c
index 1d191357bf88..272327134a1b 100644
--- a/net/ipv4/tcp_memcontrol.c
+++ b/net/ipv4/tcp_memcontrol.c
@@ -9,13 +9,13 @@
 int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 {
 	/*
-	 * The root cgroup does not use res_counters, but rather,
+	 * The root cgroup does not use page_counters, but rather,
 	 * rely on the data already collected by the network
 	 * subsystem
 	 */
-	struct res_counter *res_parent = NULL;
-	struct cg_proto *cg_proto, *parent_cg;
 	struct mem_cgroup *parent = parent_mem_cgroup(memcg);
+	struct page_counter *counter_parent = NULL;
+	struct cg_proto *cg_proto, *parent_cg;
 
 	cg_proto = tcp_prot.proto_cgroup(memcg);
 	if (!cg_proto)
@@ -29,9 +29,9 @@ int tcp_init_cgroup(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 
 	parent_cg = tcp_prot.proto_cgroup(parent);
 	if (parent_cg)
-		res_parent = &parent_cg->memory_allocated;
+		counter_parent = &parent_cg->memory_allocated;
 
-	res_counter_init(&cg_proto->memory_allocated, res_parent);
+	page_counter_init(&cg_proto->memory_allocated, counter_parent);
 	percpu_counter_init(&cg_proto->sockets_allocated, 0, GFP_KERNEL);
 
 	return 0;
@@ -50,7 +50,7 @@ void tcp_destroy_cgroup(struct mem_cgroup *memcg)
 }
 EXPORT_SYMBOL(tcp_destroy_cgroup);
 
-static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
+static int tcp_update_limit(struct mem_cgroup *memcg, unsigned long nr_pages)
 {
 	struct cg_proto *cg_proto;
 	int i;
@@ -60,20 +60,17 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
 	if (!cg_proto)
 		return -EINVAL;
 
-	if (val > RES_COUNTER_MAX)
-		val = RES_COUNTER_MAX;
-
-	ret = res_counter_set_limit(&cg_proto->memory_allocated, val);
+	ret = page_counter_limit(&cg_proto->memory_allocated, nr_pages);
 	if (ret)
 		return ret;
 
 	for (i = 0; i < 3; i++)
-		cg_proto->sysctl_mem[i] = min_t(long, val >> PAGE_SHIFT,
+		cg_proto->sysctl_mem[i] = min_t(long, nr_pages,
 						sysctl_tcp_mem[i]);
 
-	if (val == RES_COUNTER_MAX)
+	if (nr_pages == PAGE_COUNTER_MAX)
 		clear_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags);
-	else if (val != RES_COUNTER_MAX) {
+	else {
 		/*
 		 * The active bit needs to be written after the static_key
 		 * update. This is what guarantees that the socket activation
@@ -102,11 +99,20 @@ static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
 	return 0;
 }
 
+enum {
+	RES_USAGE,
+	RES_LIMIT,
+	RES_MAX_USAGE,
+	RES_FAILCNT,
+};
+
+static DEFINE_MUTEX(tcp_limit_mutex);
+
 static ssize_t tcp_cgroup_write(struct kernfs_open_file *of,
 				char *buf, size_t nbytes, loff_t off)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
-	unsigned long long val;
+	unsigned long nr_pages;
 	int ret = 0;
 
 	buf = strstrip(buf);
@@ -114,10 +120,12 @@ static ssize_t tcp_cgroup_write(struct kernfs_open_file *of,
 	switch (of_cft(of)->private) {
 	case RES_LIMIT:
 		/* see memcontrol.c */
-		ret = res_counter_memparse_write_strategy(buf, &val);
+		ret = page_counter_memparse(buf, &nr_pages);
 		if (ret)
 			break;
-		ret = tcp_update_limit(memcg, val);
+		mutex_lock(&tcp_limit_mutex);
+		ret = tcp_update_limit(memcg, nr_pages);
+		mutex_unlock(&tcp_limit_mutex);
 		break;
 	default:
 		ret = -EINVAL;
@@ -126,43 +134,36 @@ static ssize_t tcp_cgroup_write(struct kernfs_open_file *of,
 	return ret ?: nbytes;
 }
 
-static u64 tcp_read_stat(struct mem_cgroup *memcg, int type, u64 default_val)
-{
-	struct cg_proto *cg_proto;
-
-	cg_proto = tcp_prot.proto_cgroup(memcg);
-	if (!cg_proto)
-		return default_val;
-
-	return res_counter_read_u64(&cg_proto->memory_allocated, type);
-}
-
-static u64 tcp_read_usage(struct mem_cgroup *memcg)
-{
-	struct cg_proto *cg_proto;
-
-	cg_proto = tcp_prot.proto_cgroup(memcg);
-	if (!cg_proto)
-		return atomic_long_read(&tcp_memory_allocated) << PAGE_SHIFT;
-
-	return res_counter_read_u64(&cg_proto->memory_allocated, RES_USAGE);
-}
-
 static u64 tcp_cgroup_read(struct cgroup_subsys_state *css, struct cftype *cft)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+	struct cg_proto *cg_proto = tcp_prot.proto_cgroup(memcg);
 	u64 val;
 
 	switch (cft->private) {
 	case RES_LIMIT:
-		val = tcp_read_stat(memcg, RES_LIMIT, RES_COUNTER_MAX);
+		if (!cg_proto)
+			return PAGE_COUNTER_MAX;
+		val = cg_proto->memory_allocated.limit;
+		val *= PAGE_SIZE;
 		break;
 	case RES_USAGE:
-		val = tcp_read_usage(memcg);
+		if (!cg_proto)
+			val = atomic_long_read(&tcp_memory_allocated);
+		else
+			val = page_counter_read(&cg_proto->memory_allocated);
+		val *= PAGE_SIZE;
 		break;
 	case RES_FAILCNT:
+		if (!cg_proto)
+			return 0;
+		val = cg_proto->memory_allocated.failcnt;
+		break;
 	case RES_MAX_USAGE:
-		val = tcp_read_stat(memcg, cft->private, 0);
+		if (!cg_proto)
+			return 0;
+		val = cg_proto->memory_allocated.watermark;
+		val *= PAGE_SIZE;
 		break;
 	default:
 		BUG();
@@ -183,10 +184,10 @@ static ssize_t tcp_cgroup_reset(struct kernfs_open_file *of,
 
 	switch (of_cft(of)->private) {
 	case RES_MAX_USAGE:
-		res_counter_reset_max(&cg_proto->memory_allocated);
+		page_counter_reset_watermark(&cg_proto->memory_allocated);
 		break;
 	case RES_FAILCNT:
-		res_counter_reset_failcnt(&cg_proto->memory_allocated);
+		cg_proto->memory_allocated.failcnt = 0;
 		break;
 	}
 
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 374abf443636..5e63dce2e428 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -7,10 +7,11 @@
 
 use strict;
 use POSIX;
+use File::Basename;
+use Cwd 'abs_path';
 
 my $P = $0;
-$P =~ s@(.*)/@@g;
-my $D = $1;
+my $D = dirname(abs_path($P));
 
 my $V = '0.32';
 
@@ -438,26 +439,29 @@ our $allowed_asm_includes = qr{(?x:
 
 # Load common spelling mistakes and build regular expression list.
 my $misspellings;
-my @spelling_list;
 my %spelling_fix;
-open(my $spelling, '<', $spelling_file)
-    or die "$P: Can't open $spelling_file for reading: $!\n";
-while (<$spelling>) {
-	my $line = $_;
 
-	$line =~ s/\s*\n?$//g;
-	$line =~ s/^\s*//g;
+if (open(my $spelling, '<', $spelling_file)) {
+	my @spelling_list;
+	while (<$spelling>) {
+		my $line = $_;
+
+		$line =~ s/\s*\n?$//g;
+		$line =~ s/^\s*//g;
 
-	next if ($line =~ m/^\s*#/);
-	next if ($line =~ m/^\s*$/);
+		next if ($line =~ m/^\s*#/);
+		next if ($line =~ m/^\s*$/);
 
-	my ($suspect, $fix) = split(/\|\|/, $line);
+		my ($suspect, $fix) = split(/\|\|/, $line);
 
-	push(@spelling_list, $suspect);
-	$spelling_fix{$suspect} = $fix;
+		push(@spelling_list, $suspect);
+		$spelling_fix{$suspect} = $fix;
+	}
+	close($spelling);
+	$misspellings = join("|", @spelling_list);
+} else {
+	warn "No typos will be found - file '$spelling_file': $!\n";
 }
-close($spelling);
-$misspellings = join("|", @spelling_list);
 
 sub build_types {
 	my $mods = "(?x:  \n" . join("|\n  ", @modifierList) . "\n)";
@@ -2078,6 +2082,12 @@ sub process {
 			$in_commit_log = 0;
 		}
 
+# Check if MAINTAINERS is being updated.  If so, there's probably no need to
+# emit the "does MAINTAINERS need updating?" message on file add/move/delete
+		if ($line =~ /^\s*MAINTAINERS\s*\|/) {
+			$reported_maintainer_file = 1;
+		}
+
 # Check signature styles
 		if (!$in_header_lines &&
 		    $line =~ /^(\s*)([a-z0-9_-]+by:|$signature_tags)(\s*)(.*)/i) {
@@ -2246,7 +2256,7 @@ sub process {
 		}
 
 # Check for various typo / spelling mistakes
-		if ($in_commit_log || $line =~ /^\+/) {
+		if (defined($misspellings) && ($in_commit_log || $line =~ /^\+/)) {
 			while ($rawline =~ /(?:^|[^a-z@])($misspellings)(?:$|[^a-z@])/gi) {
 				my $typo = $1;
 				my $typo_fix = $spelling_fix{lc($typo)};
@@ -2515,7 +2525,8 @@ sub process {
 			}
 		}
 
-		if ($line =~ /^\+.*\(\s*$Type\s*\)[ \t]+(?!$Assignment|$Arithmetic|{)/) {
+		if ($line =~ /^\+.*(\w+\s*)?\(\s*$Type\s*\)[ \t]+(?!$Assignment|$Arithmetic|[,;\({\[\<\>])/ &&
+		    (!defined($1) || $1 !~ /sizeof\s*/)) {
 			if (CHK("SPACING",
 				"No space is necessary after a cast\n" . $herecurr) &&
 			    $fix) {
@@ -3563,14 +3574,33 @@ sub process {
 						}
 					}
 
-				# , must have a space on the right.
+				# , must not have a space before and must have a space on the right.
 				} elsif ($op eq ',') {
+					my $rtrim_before = 0;
+					my $space_after = 0;
+					if ($ctx =~ /Wx./) {
+						if (ERROR("SPACING",
+							  "space prohibited before that '$op' $at\n" . $hereptr)) {
+							$line_fixed = 1;
+							$rtrim_before = 1;
+						}
+					}
 					if ($ctx !~ /.x[WEC]/ && $cc !~ /^}/) {
 						if (ERROR("SPACING",
 							  "space required after that '$op' $at\n" . $hereptr)) {
-							$good = $fix_elements[$n] . trim($fix_elements[$n + 1]) . " ";
 							$line_fixed = 1;
 							$last_after = $n;
+							$space_after = 1;
+						}
+					}
+					if ($rtrim_before || $space_after) {
+						if ($rtrim_before) {
+							$good = rtrim($fix_elements[$n]) . trim($fix_elements[$n + 1]);
+						} else {
+							$good = $fix_elements[$n] . trim($fix_elements[$n + 1]);
+						}
+						if ($space_after) {
+							$good .= " ";
 						}
 					}
 
@@ -3814,9 +3844,27 @@ sub process {
 # ie: &(foo->bar) should be &foo->bar and *(foo->bar) should be *foo->bar
 
 		while ($line =~ /(?:[^&]&\s*|\*)\(\s*($Ident\s*(?:$Member\s*)+)\s*\)/g) {
-			CHK("UNNECESSARY_PARENTHESES",
-			    "Unnecessary parentheses around $1\n" . $herecurr);
-		    }
+			my $var = $1;
+			if (CHK("UNNECESSARY_PARENTHESES",
+				"Unnecessary parentheses around $var\n" . $herecurr) &&
+			    $fix) {
+				$fixed[$fixlinenr] =~ s/\(\s*\Q$var\E\s*\)/$var/;
+			}
+		}
+
+# check for unnecessary parentheses around function pointer uses
+# ie: (foo->bar)(); should be foo->bar();
+# but not "if (foo->bar) (" to avoid some false positives
+		if ($line =~ /(\bif\s*|)(\(\s*$Ident\s*(?:$Member\s*)+\))[ \t]*\(/ && $1 !~ /^if/) {
+			my $var = $2;
+			if (CHK("UNNECESSARY_PARENTHESES",
+				"Unnecessary parentheses around function pointer $var\n" . $herecurr) &&
+			    $fix) {
+				my $var2 = deparenthesize($var);
+				$var2 =~ s/\s//g;
+				$fixed[$fixlinenr] =~ s/\Q$var\E/$var2/;
+			}
+		}
 
 #goto labels aren't indented, allow a single space however
 		if ($line=~/^.\s+[A-Za-z\d_]+:(?![0-9]+)/ and
@@ -4056,7 +4104,9 @@ sub process {
 #Ignore Page<foo> variants
 			    $var !~ /^(?:Clear|Set|TestClear|TestSet|)Page[A-Z]/ &&
 #Ignore SI style variants like nS, mV and dB (ie: max_uV, regulator_min_uA_show)
-			    $var !~ /^(?:[a-z_]*?)_?[a-z][A-Z](?:_[a-z_]+)?$/) {
+			    $var !~ /^(?:[a-z_]*?)_?[a-z][A-Z](?:_[a-z_]+)?$/ &&
+#Ignore some three character SI units explicitly, like MiB and KHz
+			    $var !~ /^(?:[a-z_]*?)_?(?:[KMGT]iB|[KMGT]?Hz)(?:_[a-z_]+)?$/) {
 				while ($var =~ m{($Ident)}g) {
 					my $word = $1;
 					next if ($word !~ /[A-Z][a-z]|[a-z][A-Z]/);
@@ -4414,6 +4464,12 @@ sub process {
 			    "Concatenated strings should use spaces between elements\n" . $herecurr);
 		}
 
+# uncoalesced string fragments
+		if ($line =~ /"X*"\s*"/) {
+			WARN("STRING_FRAGMENTS",
+			     "Consecutive strings are generally better as a single string\n" . $herecurr);
+		}
+
 # warn about #if 0
 		if ($line =~ /^.\s*\#\s*if\s+0\b/) {
 			CHK("REDUNDANT_CODE",
@@ -4426,7 +4482,7 @@ sub process {
 			my $expr = '\s*\(\s*' . quotemeta($1) . '\s*\)\s*;';
 			if ($line =~ /\b(kfree|usb_free_urb|debugfs_remove(?:_recursive)?)$expr/) {
 				WARN('NEEDLESS_IF',
-				     "$1(NULL) is safe this check is probably not required\n" . $hereprev);
+				     "$1(NULL) is safe and this check is probably not required\n" . $hereprev);
 			}
 		}
 
@@ -4458,6 +4514,14 @@ sub process {
 			}
 		}
 
+# check for mask then right shift without a parentheses
+		if ($^V && $^V ge 5.10.0 &&
+		    $line =~ /$LvalOrFunc\s*\&\s*($LvalOrFunc)\s*>>/ &&
+		    $4 !~ /^\&/) { # $LvalOrFunc may be &foo, ignore if so
+			WARN("MASK_THEN_SHIFT",
+			     "Possible precedence defect with mask then right shift - may need parentheses\n" . $herecurr);
+		}
+
 # check for bad placement of section $InitAttribute (e.g.: __initdata)
 		if ($line =~ /(\b$InitAttribute\b)/) {
 			my $attr = $1;
@@ -4652,6 +4716,15 @@ sub process {
 			}
 		}
 
+# Check for __attribute__ weak, or __weak declarations (may have link issues)
+		if ($^V && $^V ge 5.10.0 &&
+		    $line =~ /(?:$Declare|$DeclareMisordered)\s*$Ident\s*$balanced_parens\s*(?:$Attribute)?\s*;/ &&
+		    ($line =~ /\b__attribute__\s*\(\s*\(.*\bweak\b/ ||
+		     $line =~ /\b__weak\b/)) {
+			ERROR("WEAK_DECLARATION",
+			      "Using weak declarations can have unintended link defects\n" . $herecurr);
+		}
+
 # check for sizeof(&)
 		if ($line =~ /\bsizeof\s*\(\s*\&/) {
 			WARN("SIZEOF_ADDRESS",
@@ -4908,6 +4981,17 @@ sub process {
 			}
 		}
 
+# check for #defines like: 1 << <digit> that could be BIT(digit)
+		if ($line =~ /#\s*define\s+\w+\s+\(?\s*1\s*([ulUL]*)\s*\<\<\s*(?:\d+|$Ident)\s*\)?/) {
+			my $ull = "";
+			$ull = "_ULL" if (defined($1) && $1 =~ /ll/i);
+			if (CHK("BIT_MACRO",
+				"Prefer using the BIT$ull macro\n" . $herecurr) &&
+			    $fix) {
+				$fixed[$fixlinenr] =~ s/\(?\s*1\s*[ulUL]*\s*<<\s*(\d+|$Ident)\s*\)?/BIT${ull}($1)/;
+			}
+		}
+
 # check for case / default statements not preceded by break/fallthrough/switch
 		if ($line =~ /^.\s*(?:case\s+(?:$Ident|$Constant)\s*|default):/) {
 			my $has_break = 0;
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index 433ae61e7f42..f1b17a476e12 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -53,6 +53,7 @@
 #define SMK_SENDING	2
 
 LIST_HEAD(smk_ipv6_port_list);
+static struct kmem_cache *smack_inode_cache;
 
 #ifdef CONFIG_SECURITY_SMACK_BRINGUP
 static void smk_bu_mode(int mode, char *s)
@@ -240,7 +241,7 @@ struct inode_smack *new_inode_smack(struct smack_known *skp)
 {
 	struct inode_smack *isp;
 
-	isp = kzalloc(sizeof(struct inode_smack), GFP_NOFS);
+	isp = kmem_cache_zalloc(smack_inode_cache, GFP_NOFS);
 	if (isp == NULL)
 		return NULL;
 
@@ -767,7 +768,7 @@ static int smack_inode_alloc_security(struct inode *inode)
  */
 static void smack_inode_free_security(struct inode *inode)
 {
-	kfree(inode->i_security);
+	kmem_cache_free(smack_inode_cache, inode->i_security);
 	inode->i_security = NULL;
 }
 
@@ -4264,10 +4265,16 @@ static __init int smack_init(void)
 	if (!security_module_enable(&smack_ops))
 		return 0;
 
+	smack_inode_cache = KMEM_CACHE(inode_smack, 0);
+	if (!smack_inode_cache)
+		return -ENOMEM;
+
 	tsp = new_task_smack(&smack_known_floor, &smack_known_floor,
 				GFP_KERNEL);
-	if (tsp == NULL)
+	if (tsp == NULL) {
+		kmem_cache_destroy(smack_inode_cache);
 		return -ENOMEM;
+	}
 
 	printk(KERN_INFO "Smack:  Initializing.\n");
 
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 45f145c6f843..a09a699e3ba9 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -1,6 +1,7 @@
 TARGETS = breakpoints
 TARGETS += cpu-hotplug
 TARGETS += efivarfs
+TARGETS += exec
 TARGETS += kcmp
 TARGETS += memfd
 TARGETS += memory-hotplug
diff --git a/tools/testing/selftests/exec/.gitignore b/tools/testing/selftests/exec/.gitignore
new file mode 100644
index 000000000000..64073e050c6a
--- /dev/null
+++ b/tools/testing/selftests/exec/.gitignore
@@ -0,0 +1,9 @@
+subdir*
+script*
+execveat
+execveat.symlink
+execveat.moved
+execveat.path.ephemeral
+execveat.ephemeral
+execveat.denatured
+xxxxxxxx*
\ No newline at end of file
diff --git a/tools/testing/selftests/exec/Makefile b/tools/testing/selftests/exec/Makefile
new file mode 100644
index 000000000000..66dfc2ce1788
--- /dev/null
+++ b/tools/testing/selftests/exec/Makefile
@@ -0,0 +1,25 @@
+CC = $(CROSS_COMPILE)gcc
+CFLAGS = -Wall
+BINARIES = execveat
+DEPS = execveat.symlink execveat.denatured script subdir
+all: $(BINARIES) $(DEPS)
+
+subdir:
+	mkdir -p $@
+script:
+	echo '#!/bin/sh' > $@
+	echo 'exit $$*' >> $@
+	chmod +x $@
+execveat.symlink: execveat
+	ln -s -f $< $@
+execveat.denatured: execveat
+	cp $< $@
+	chmod -x $@
+%: %.c
+	$(CC) $(CFLAGS) -o $@ $^
+
+run_tests: all
+	./execveat
+
+clean:
+	rm -rf $(BINARIES) $(DEPS) subdir.moved execveat.moved xxxxx*
diff --git a/tools/testing/selftests/exec/execveat.c b/tools/testing/selftests/exec/execveat.c
new file mode 100644
index 000000000000..33a5c06d95ca
--- /dev/null
+++ b/tools/testing/selftests/exec/execveat.c
@@ -0,0 +1,397 @@
+/*
+ * Copyright (c) 2014 Google, Inc.
+ *
+ * Licensed under the terms of the GNU GPL License version 2
+ *
+ * Selftests for execveat(2).
+ */
+
+#define _GNU_SOURCE  /* to get O_PATH, AT_EMPTY_PATH */
+#include <sys/sendfile.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+static char longpath[2 * PATH_MAX] = "";
+static char *envp[] = { "IN_TEST=yes", NULL, NULL };
+static char *argv[] = { "execveat", "99", NULL };
+
+static int execveat_(int fd, const char *path, char **argv, char **envp,
+		     int flags)
+{
+#ifdef __NR_execveat
+	return syscall(__NR_execveat, fd, path, argv, envp, flags);
+#else
+	errno = -ENOSYS;
+	return -1;
+#endif
+}
+
+#define check_execveat_fail(fd, path, flags, errno)	\
+	_check_execveat_fail(fd, path, flags, errno, #errno)
+static int _check_execveat_fail(int fd, const char *path, int flags,
+				int expected_errno, const char *errno_str)
+{
+	int rc;
+
+	errno = 0;
+	printf("Check failure of execveat(%d, '%s', %d) with %s... ",
+		fd, path?:"(null)", flags, errno_str);
+	rc = execveat_(fd, path, argv, envp, flags);
+
+	if (rc > 0) {
+		printf("[FAIL] (unexpected success from execveat(2))\n");
+		return 1;
+	}
+	if (errno != expected_errno) {
+		printf("[FAIL] (expected errno %d (%s) not %d (%s)\n",
+			expected_errno, strerror(expected_errno),
+			errno, strerror(errno));
+		return 1;
+	}
+	printf("[OK]\n");
+	return 0;
+}
+
+static int check_execveat_invoked_rc(int fd, const char *path, int flags,
+				     int expected_rc)
+{
+	int status;
+	int rc;
+	pid_t child;
+	int pathlen = path ? strlen(path) : 0;
+
+	if (pathlen > 40)
+		printf("Check success of execveat(%d, '%.20s...%s', %d)... ",
+			fd, path, (path + pathlen - 20), flags);
+	else
+		printf("Check success of execveat(%d, '%s', %d)... ",
+			fd, path?:"(null)", flags);
+	child = fork();
+	if (child < 0) {
+		printf("[FAIL] (fork() failed)\n");
+		return 1;
+	}
+	if (child == 0) {
+		/* Child: do execveat(). */
+		rc = execveat_(fd, path, argv, envp, flags);
+		printf("[FAIL]: execveat() failed, rc=%d errno=%d (%s)\n",
+			rc, errno, strerror(errno));
+		exit(1);  /* should not reach here */
+	}
+	/* Parent: wait for & check child's exit status. */
+	rc = waitpid(child, &status, 0);
+	if (rc != child) {
+		printf("[FAIL] (waitpid(%d,...) returned %d)\n", child, rc);
+		return 1;
+	}
+	if (!WIFEXITED(status)) {
+		printf("[FAIL] (child %d did not exit cleanly, status=%08x)\n",
+			child, status);
+		return 1;
+	}
+	if (WEXITSTATUS(status) != expected_rc) {
+		printf("[FAIL] (child %d exited with %d not %d)\n",
+			child, WEXITSTATUS(status), expected_rc);
+		return 1;
+	}
+	printf("[OK]\n");
+	return 0;
+}
+
+static int check_execveat(int fd, const char *path, int flags)
+{
+	return check_execveat_invoked_rc(fd, path, flags, 99);
+}
+
+static char *concat(const char *left, const char *right)
+{
+	char *result = malloc(strlen(left) + strlen(right) + 1);
+
+	strcpy(result, left);
+	strcat(result, right);
+	return result;
+}
+
+static int open_or_die(const char *filename, int flags)
+{
+	int fd = open(filename, flags);
+
+	if (fd < 0) {
+		printf("Failed to open '%s'; "
+			"check prerequisites are available\n", filename);
+		exit(1);
+	}
+	return fd;
+}
+
+static void exe_cp(const char *src, const char *dest)
+{
+	int in_fd = open_or_die(src, O_RDONLY);
+	int out_fd = open(dest, O_RDWR|O_CREAT|O_TRUNC, 0755);
+	struct stat info;
+
+	fstat(in_fd, &info);
+	sendfile(out_fd, in_fd, NULL, info.st_size);
+	close(in_fd);
+	close(out_fd);
+}
+
+#define XX_DIR_LEN 200
+static int check_execveat_pathmax(int dot_dfd, const char *src, int is_script)
+{
+	int fail = 0;
+	int ii, count, len;
+	char longname[XX_DIR_LEN + 1];
+	int fd;
+
+	if (*longpath == '\0') {
+		/* Create a filename close to PATH_MAX in length */
+		memset(longname, 'x', XX_DIR_LEN - 1);
+		longname[XX_DIR_LEN - 1] = '/';
+		longname[XX_DIR_LEN] = '\0';
+		count = (PATH_MAX - 3) / XX_DIR_LEN;
+		for (ii = 0; ii < count; ii++) {
+			strcat(longpath, longname);
+			mkdir(longpath, 0755);
+		}
+		len = (PATH_MAX - 3) - (count * XX_DIR_LEN);
+		if (len <= 0)
+			len = 1;
+		memset(longname, 'y', len);
+		longname[len] = '\0';
+		strcat(longpath, longname);
+	}
+	exe_cp(src, longpath);
+
+	/*
+	 * Execute as a pre-opened file descriptor, which works whether this is
+	 * a script or not (because the interpreter sees a filename like
+	 * "/dev/fd/20").
+	 */
+	fd = open(longpath, O_RDONLY);
+	if (fd > 0) {
+		printf("Invoke copy of '%s' via filename of length %lu:\n",
+			src, strlen(longpath));
+		fail += check_execveat(fd, "", AT_EMPTY_PATH);
+	} else {
+		printf("Failed to open length %lu filename, errno=%d (%s)\n",
+			strlen(longpath), errno, strerror(errno));
+		fail++;
+	}
+
+	/*
+	 * Execute as a long pathname relative to ".".  If this is a script,
+	 * the interpreter will launch but fail to open the script because its
+	 * name ("/dev/fd/5/xxx....") is bigger than PATH_MAX.
+	 */
+	if (is_script)
+		fail += check_execveat_invoked_rc(dot_dfd, longpath, 0, 127);
+	else
+		fail += check_execveat(dot_dfd, longpath, 0);
+
+	return fail;
+}
+
+static int run_tests(void)
+{
+	int fail = 0;
+	char *fullname = realpath("execveat", NULL);
+	char *fullname_script = realpath("script", NULL);
+	char *fullname_symlink = concat(fullname, ".symlink");
+	int subdir_dfd = open_or_die("subdir", O_DIRECTORY|O_RDONLY);
+	int subdir_dfd_ephemeral = open_or_die("subdir.ephemeral",
+					       O_DIRECTORY|O_RDONLY);
+	int dot_dfd = open_or_die(".", O_DIRECTORY|O_RDONLY);
+	int dot_dfd_path = open_or_die(".", O_DIRECTORY|O_RDONLY|O_PATH);
+	int dot_dfd_cloexec = open_or_die(".", O_DIRECTORY|O_RDONLY|O_CLOEXEC);
+	int fd = open_or_die("execveat", O_RDONLY);
+	int fd_path = open_or_die("execveat", O_RDONLY|O_PATH);
+	int fd_symlink = open_or_die("execveat.symlink", O_RDONLY);
+	int fd_denatured = open_or_die("execveat.denatured", O_RDONLY);
+	int fd_denatured_path = open_or_die("execveat.denatured",
+					    O_RDONLY|O_PATH);
+	int fd_script = open_or_die("script", O_RDONLY);
+	int fd_ephemeral = open_or_die("execveat.ephemeral", O_RDONLY);
+	int fd_ephemeral_path = open_or_die("execveat.path.ephemeral",
+					    O_RDONLY|O_PATH);
+	int fd_script_ephemeral = open_or_die("script.ephemeral", O_RDONLY);
+	int fd_cloexec = open_or_die("execveat", O_RDONLY|O_CLOEXEC);
+	int fd_script_cloexec = open_or_die("script", O_RDONLY|O_CLOEXEC);
+
+	/* Change file position to confirm it doesn't affect anything */
+	lseek(fd, 10, SEEK_SET);
+
+	/* Normal executable file: */
+	/*   dfd + path */
+	fail += check_execveat(subdir_dfd, "../execveat", 0);
+	fail += check_execveat(dot_dfd, "execveat", 0);
+	fail += check_execveat(dot_dfd_path, "execveat", 0);
+	/*   absolute path */
+	fail += check_execveat(AT_FDCWD, fullname, 0);
+	/*   absolute path with nonsense dfd */
+	fail += check_execveat(99, fullname, 0);
+	/*   fd + no path */
+	fail += check_execveat(fd, "", AT_EMPTY_PATH);
+	/*   O_CLOEXEC fd + no path */
+	fail += check_execveat(fd_cloexec, "", AT_EMPTY_PATH);
+	/*   O_PATH fd */
+	fail += check_execveat(fd_path, "", AT_EMPTY_PATH);
+
+	/* Mess with executable file that's already open: */
+	/*   fd + no path to a file that's been renamed */
+	rename("execveat.ephemeral", "execveat.moved");
+	fail += check_execveat(fd_ephemeral, "", AT_EMPTY_PATH);
+	/*   fd + no path to a file that's been deleted */
+	unlink("execveat.moved"); /* remove the file now fd open */
+	fail += check_execveat(fd_ephemeral, "", AT_EMPTY_PATH);
+
+	/* Mess with executable file that's already open with O_PATH */
+	/*   fd + no path to a file that's been deleted */
+	unlink("execveat.path.ephemeral");
+	fail += check_execveat(fd_ephemeral_path, "", AT_EMPTY_PATH);
+
+	/* Invalid argument failures */
+	fail += check_execveat_fail(fd, "", 0, ENOENT);
+	fail += check_execveat_fail(fd, NULL, AT_EMPTY_PATH, EFAULT);
+
+	/* Symlink to executable file: */
+	/*   dfd + path */
+	fail += check_execveat(dot_dfd, "execveat.symlink", 0);
+	fail += check_execveat(dot_dfd_path, "execveat.symlink", 0);
+	/*   absolute path */
+	fail += check_execveat(AT_FDCWD, fullname_symlink, 0);
+	/*   fd + no path, even with AT_SYMLINK_NOFOLLOW (already followed) */
+	fail += check_execveat(fd_symlink, "", AT_EMPTY_PATH);
+	fail += check_execveat(fd_symlink, "",
+			       AT_EMPTY_PATH|AT_SYMLINK_NOFOLLOW);
+
+	/* Symlink fails when AT_SYMLINK_NOFOLLOW set: */
+	/*   dfd + path */
+	fail += check_execveat_fail(dot_dfd, "execveat.symlink",
+				    AT_SYMLINK_NOFOLLOW, ELOOP);
+	fail += check_execveat_fail(dot_dfd_path, "execveat.symlink",
+				    AT_SYMLINK_NOFOLLOW, ELOOP);
+	/*   absolute path */
+	fail += check_execveat_fail(AT_FDCWD, fullname_symlink,
+				    AT_SYMLINK_NOFOLLOW, ELOOP);
+
+	/* Shell script wrapping executable file: */
+	/*   dfd + path */
+	fail += check_execveat(subdir_dfd, "../script", 0);
+	fail += check_execveat(dot_dfd, "script", 0);
+	fail += check_execveat(dot_dfd_path, "script", 0);
+	/*   absolute path */
+	fail += check_execveat(AT_FDCWD, fullname_script, 0);
+	/*   fd + no path */
+	fail += check_execveat(fd_script, "", AT_EMPTY_PATH);
+	fail += check_execveat(fd_script, "",
+			       AT_EMPTY_PATH|AT_SYMLINK_NOFOLLOW);
+	/*   O_CLOEXEC fd fails for a script (as script file inaccessible) */
+	fail += check_execveat_fail(fd_script_cloexec, "", AT_EMPTY_PATH,
+				    ENOENT);
+	fail += check_execveat_fail(dot_dfd_cloexec, "script", 0, ENOENT);
+
+	/* Mess with script file that's already open: */
+	/*   fd + no path to a file that's been renamed */
+	rename("script.ephemeral", "script.moved");
+	fail += check_execveat(fd_script_ephemeral, "", AT_EMPTY_PATH);
+	/*   fd + no path to a file that's been deleted */
+	unlink("script.moved"); /* remove the file while fd open */
+	fail += check_execveat(fd_script_ephemeral, "", AT_EMPTY_PATH);
+
+	/* Rename a subdirectory in the path: */
+	rename("subdir.ephemeral", "subdir.moved");
+	fail += check_execveat(subdir_dfd_ephemeral, "../script", 0);
+	fail += check_execveat(subdir_dfd_ephemeral, "script", 0);
+	/* Remove the subdir and its contents */
+	unlink("subdir.moved/script");
+	unlink("subdir.moved");
+	/* Shell loads via deleted subdir OK because name starts with .. */
+	fail += check_execveat(subdir_dfd_ephemeral, "../script", 0);
+	fail += check_execveat_fail(subdir_dfd_ephemeral, "script", 0, ENOENT);
+
+	/* Flag values other than AT_SYMLINK_NOFOLLOW => EINVAL */
+	fail += check_execveat_fail(dot_dfd, "execveat", 0xFFFF, EINVAL);
+	/* Invalid path => ENOENT */
+	fail += check_execveat_fail(dot_dfd, "no-such-file", 0, ENOENT);
+	fail += check_execveat_fail(dot_dfd_path, "no-such-file", 0, ENOENT);
+	fail += check_execveat_fail(AT_FDCWD, "no-such-file", 0, ENOENT);
+	/* Attempt to execute directory => EACCES */
+	fail += check_execveat_fail(dot_dfd, "", AT_EMPTY_PATH, EACCES);
+	/* Attempt to execute non-executable => EACCES */
+	fail += check_execveat_fail(dot_dfd, "Makefile", 0, EACCES);
+	fail += check_execveat_fail(fd_denatured, "", AT_EMPTY_PATH, EACCES);
+	fail += check_execveat_fail(fd_denatured_path, "", AT_EMPTY_PATH,
+				    EACCES);
+	/* Attempt to execute nonsense FD => EBADF */
+	fail += check_execveat_fail(99, "", AT_EMPTY_PATH, EBADF);
+	fail += check_execveat_fail(99, "execveat", 0, EBADF);
+	/* Attempt to execute relative to non-directory => ENOTDIR */
+	fail += check_execveat_fail(fd, "execveat", 0, ENOTDIR);
+
+	fail += check_execveat_pathmax(dot_dfd, "execveat", 0);
+	fail += check_execveat_pathmax(dot_dfd, "script", 1);
+	return fail;
+}
+
+static void prerequisites(void)
+{
+	int fd;
+	const char *script = "#!/bin/sh\nexit $*\n";
+
+	/* Create ephemeral copies of files */
+	exe_cp("execveat", "execveat.ephemeral");
+	exe_cp("execveat", "execveat.path.ephemeral");
+	exe_cp("script", "script.ephemeral");
+	mkdir("subdir.ephemeral", 0755);
+
+	fd = open("subdir.ephemeral/script", O_RDWR|O_CREAT|O_TRUNC, 0755);
+	write(fd, script, strlen(script));
+	close(fd);
+}
+
+int main(int argc, char **argv)
+{
+	int ii;
+	int rc;
+	const char *verbose = getenv("VERBOSE");
+
+	if (argc >= 2) {
+		/* If we are invoked with an argument, don't run tests. */
+		const char *in_test = getenv("IN_TEST");
+
+		if (verbose) {
+			printf("  invoked with:");
+			for (ii = 0; ii < argc; ii++)
+				printf(" [%d]='%s'", ii, argv[ii]);
+			printf("\n");
+		}
+
+		/* Check expected environment transferred. */
+		if (!in_test || strcmp(in_test, "yes") != 0) {
+			printf("[FAIL] (no IN_TEST=yes in env)\n");
+			return 1;
+		}
+
+		/* Use the final argument as an exit code. */
+		rc = atoi(argv[argc - 1]);
+		fflush(stdout);
+	} else {
+		prerequisites();
+		if (verbose)
+			envp[1] = "VERBOSE=1";
+		rc = run_tests();
+		if (rc > 0)
+			printf("%d tests failed\n", rc);
+	}
+	return rc;
+}
diff --git a/usr/Kconfig b/usr/Kconfig
index 2d4c77eecf2e..572dcf7b6a44 100644
--- a/usr/Kconfig
+++ b/usr/Kconfig
@@ -46,17 +46,17 @@ config INITRAMFS_ROOT_GID
 	  If you are not sure, leave it set to "0".
 
 config RD_GZIP
-	bool "Support initial ramdisks compressed using gzip" if EXPERT
-	default y
+	bool "Support initial ramdisks compressed using gzip"
 	depends on BLK_DEV_INITRD
+	default y
 	select DECOMPRESS_GZIP
 	help
 	  Support loading of a gzip encoded initial ramdisk or cpio buffer.
 	  If unsure, say Y.
 
 config RD_BZIP2
-	bool "Support initial ramdisks compressed using bzip2" if EXPERT
-	default !EXPERT
+	bool "Support initial ramdisks compressed using bzip2"
+	default y
 	depends on BLK_DEV_INITRD
 	select DECOMPRESS_BZIP2
 	help
@@ -64,8 +64,8 @@ config RD_BZIP2
 	  If unsure, say N.
 
 config RD_LZMA
-	bool "Support initial ramdisks compressed using LZMA" if EXPERT
-	default !EXPERT
+	bool "Support initial ramdisks compressed using LZMA"
+	default y
 	depends on BLK_DEV_INITRD
 	select DECOMPRESS_LZMA
 	help
@@ -73,17 +73,17 @@ config RD_LZMA
 	  If unsure, say N.
 
 config RD_XZ
-	bool "Support initial ramdisks compressed using XZ" if EXPERT
-	default !EXPERT
+	bool "Support initial ramdisks compressed using XZ"
 	depends on BLK_DEV_INITRD
+	default y
 	select DECOMPRESS_XZ
 	help
 	  Support loading of a XZ encoded initial ramdisk or cpio buffer.
 	  If unsure, say N.
 
 config RD_LZO
-	bool "Support initial ramdisks compressed using LZO" if EXPERT
-	default !EXPERT
+	bool "Support initial ramdisks compressed using LZO"
+	default y
 	depends on BLK_DEV_INITRD
 	select DECOMPRESS_LZO
 	help
@@ -91,8 +91,8 @@ config RD_LZO
 	  If unsure, say N.
 
 config RD_LZ4
-	bool "Support initial ramdisks compressed using LZ4" if EXPERT
-	default !EXPERT
+	bool "Support initial ramdisks compressed using LZ4"
+	default y
 	depends on BLK_DEV_INITRD
 	select DECOMPRESS_LZ4
 	help