Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

20 files changed, 1893 insertions, 300 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 71eb0b4cce8..24776072959 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -245,6 +245,20 @@ config DEFAULT_MMAP_MIN_ADDR
 	  /proc/sys/vm/mmap_min_addr tunable.
 
 
+config MEMORY_FAILURE
+	depends on MMU
+	depends on X86_MCE
+	bool "Enable recovery from hardware memory errors"
+	help
+	  Enables code to recover from some memory failures on systems
+	  with MCA recovery. This allows a system to continue running
+	  even when some of its memory has uncorrected errors. This requires
+	  special hardware support and typically ECC memory.
+
+config HWPOISON_INJECT
+	tristate "Poison pages injector"
+	depends on MEMORY_FAILURE && DEBUG_KERNEL
+
 config NOMMU_INITIAL_TRIM_EXCESS
 	int "Turn on mmap() excess space trimming before booting"
 	depends on !MMU
diff --git a/mm/Makefile b/mm/Makefile
index 88193d73cd1..ebf849042ed 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -5,14 +5,14 @@
 mmu-y			:= nommu.o
 mmu-$(CONFIG_MMU)	:= fremap.o highmem.o madvise.o memory.o mincore.o \
 			   mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \
-			   vmalloc.o
+			   vmalloc.o pagewalk.o
 
 obj-y			:= bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \
 			   maccess.o page_alloc.o page-writeback.o \
 			   readahead.o swap.o truncate.o vmscan.o shmem.o \
 			   prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \
 			   page_isolation.o mm_init.o mmu_context.o \
-			   pagewalk.o $(mmu-y)
+			   $(mmu-y)
 obj-y += init-mm.o
 
 obj-$(CONFIG_BOUNCE)	+= bounce.o
@@ -41,5 +41,7 @@ obj-$(CONFIG_SMP) += allocpercpu.o
 endif
 obj-$(CONFIG_QUICKLIST) += quicklist.o
 obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o page_cgroup.o
+obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o
+obj-$(CONFIG_HWPOISON_INJECT) += hwpoison-inject.o
 obj-$(CONFIG_DEBUG_KMEMLEAK) += kmemleak.o
 obj-$(CONFIG_DEBUG_KMEMLEAK_TEST) += kmemleak-test.o
diff --git a/mm/filemap.c b/mm/filemap.c
index bcc7372aebb..6c84e598b4a 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -58,7 +58,7 @@
 /*
  * Lock ordering:
  *
- *  ->i_mmap_lock		(vmtruncate)
+ *  ->i_mmap_lock		(truncate_pagecache)
  *    ->private_lock		(__free_pte->__set_page_dirty_buffers)
  *      ->swap_lock		(exclusive_swap_page, others)
  *        ->mapping->tree_lock
@@ -104,6 +104,10 @@
  *
  *  ->task->proc_lock
  *    ->dcache_lock		(proc_pid_lookup)
+ *
+ *  (code doesn't rely on that order, so you could switch it around)
+ *  ->tasklist_lock             (memory_failure, collect_procs_ao)
+ *    ->i_mmap_lock
  */
 
 /*
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 815dbd4a6dc..6f048fcc749 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1537,7 +1537,7 @@ static unsigned int cpuset_mems_nr(unsigned int *array)
 
 #ifdef CONFIG_SYSCTL
 int hugetlb_sysctl_handler(struct ctl_table *table, int write,
-			   struct file *file, void __user *buffer,
+			   void __user *buffer,
 			   size_t *length, loff_t *ppos)
 {
 	struct hstate *h = &default_hstate;
@@ -1548,7 +1548,7 @@ int hugetlb_sysctl_handler(struct ctl_table *table, int write,
 
 	table->data = &tmp;
 	table->maxlen = sizeof(unsigned long);
-	proc_doulongvec_minmax(table, write, file, buffer, length, ppos);
+	proc_doulongvec_minmax(table, write, buffer, length, ppos);
 
 	if (write)
 		h->max_huge_pages = set_max_huge_pages(h, tmp);
@@ -1557,10 +1557,10 @@ int hugetlb_sysctl_handler(struct ctl_table *table, int write,
 }
 
 int hugetlb_treat_movable_handler(struct ctl_table *table, int write,
-			struct file *file, void __user *buffer,
+			void __user *buffer,
 			size_t *length, loff_t *ppos)
 {
-	proc_dointvec(table, write, file, buffer, length, ppos);
+	proc_dointvec(table, write, buffer, length, ppos);
 	if (hugepages_treat_as_movable)
 		htlb_alloc_mask = GFP_HIGHUSER_MOVABLE;
 	else
@@ -1569,7 +1569,7 @@ int hugetlb_treat_movable_handler(struct ctl_table *table, int write,
 }
 
 int hugetlb_overcommit_handler(struct ctl_table *table, int write,
-			struct file *file, void __user *buffer,
+			void __user *buffer,
 			size_t *length, loff_t *ppos)
 {
 	struct hstate *h = &default_hstate;
@@ -1580,7 +1580,7 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write,
 
 	table->data = &tmp;
 	table->maxlen = sizeof(unsigned long);
-	proc_doulongvec_minmax(table, write, file, buffer, length, ppos);
+	proc_doulongvec_minmax(table, write, buffer, length, ppos);
 
 	if (write) {
 		spin_lock(&hugetlb_lock);
diff --git a/mm/hwpoison-inject.c b/mm/hwpoison-inject.c
new file mode 100644
index 00000000000..e1d85137f08
--- /dev/null
+++ b/mm/hwpoison-inject.c
@@ -0,0 +1,41 @@
+/* Inject a hwpoison memory failure on a arbitary pfn */
+#include <linux/module.h>
+#include <linux/debugfs.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+
+static struct dentry *hwpoison_dir, *corrupt_pfn;
+
+static int hwpoison_inject(void *data, u64 val)
+{
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	printk(KERN_INFO "Injecting memory failure at pfn %Lx\n", val);
+	return __memory_failure(val, 18, 0);
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(hwpoison_fops, NULL, hwpoison_inject, "%lli\n");
+
+static void pfn_inject_exit(void)
+{
+	if (hwpoison_dir)
+		debugfs_remove_recursive(hwpoison_dir);
+}
+
+static int pfn_inject_init(void)
+{
+	hwpoison_dir = debugfs_create_dir("hwpoison", NULL);
+	if (hwpoison_dir == NULL)
+		return -ENOMEM;
+	corrupt_pfn = debugfs_create_file("corrupt-pfn", 0600, hwpoison_dir,
+					  NULL, &hwpoison_fops);
+	if (corrupt_pfn == NULL) {
+		pfn_inject_exit();
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+module_init(pfn_inject_init);
+module_exit(pfn_inject_exit);
+MODULE_LICENSE("GPL");
diff --git a/mm/ksm.c b/mm/ksm.c
index 37cc3732509..f7edac356f4 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -30,6 +30,7 @@
 #include <linux/slab.h>
 #include <linux/rbtree.h>
 #include <linux/mmu_notifier.h>
+#include <linux/swap.h>
 #include <linux/ksm.h>
 
 #include <asm/tlbflush.h>
@@ -162,10 +163,10 @@ static unsigned long ksm_pages_unshared;
 static unsigned long ksm_rmap_items;
 
 /* Limit on the number of unswappable pages used */
-static unsigned long ksm_max_kernel_pages = 2000;
+static unsigned long ksm_max_kernel_pages;
 
 /* Number of pages ksmd should scan in one batch */
-static unsigned int ksm_thread_pages_to_scan = 200;
+static unsigned int ksm_thread_pages_to_scan = 100;
 
 /* Milliseconds ksmd should sleep between batches */
 static unsigned int ksm_thread_sleep_millisecs = 20;
@@ -173,7 +174,7 @@ static unsigned int ksm_thread_sleep_millisecs = 20;
 #define KSM_RUN_STOP	0
 #define KSM_RUN_MERGE	1
 #define KSM_RUN_UNMERGE	2
-static unsigned int ksm_run = KSM_RUN_MERGE;
+static unsigned int ksm_run = KSM_RUN_STOP;
 
 static DECLARE_WAIT_QUEUE_HEAD(ksm_thread_wait);
 static DEFINE_MUTEX(ksm_thread_mutex);
@@ -183,6 +184,11 @@ static DEFINE_SPINLOCK(ksm_mmlist_lock);
 		sizeof(struct __struct), __alignof__(struct __struct),\
 		(__flags), NULL)
 
+static void __init ksm_init_max_kernel_pages(void)
+{
+	ksm_max_kernel_pages = nr_free_buffer_pages() / 4;
+}
+
 static int __init ksm_slab_init(void)
 {
 	rmap_item_cache = KSM_KMEM_CACHE(rmap_item, 0);
@@ -1667,6 +1673,8 @@ static int __init ksm_init(void)
 	struct task_struct *ksm_thread;
 	int err;
 
+	ksm_init_max_kernel_pages();
+
 	err = ksm_slab_init();
 	if (err)
 		goto out;
diff --git a/mm/madvise.c b/mm/madvise.c
index d9ae2067952..35b1479b7c9 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -218,6 +218,32 @@ static long madvise_remove(struct vm_area_struct *vma,
 	return error;
 }
 
+#ifdef CONFIG_MEMORY_FAILURE
+/*
+ * Error injection support for memory error handling.
+ */
+static int madvise_hwpoison(unsigned long start, unsigned long end)
+{
+	int ret = 0;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	for (; start < end; start += PAGE_SIZE) {
+		struct page *p;
+		int ret = get_user_pages(current, current->mm, start, 1,
+						0, 0, &p, NULL);
+		if (ret != 1)
+			return ret;
+		printk(KERN_INFO "Injecting memory failure for page %lx at %lx\n",
+		       page_to_pfn(p), start);
+		/* Ignore return value for now */
+		__memory_failure(page_to_pfn(p), 0, 1);
+		put_page(p);
+	}
+	return ret;
+}
+#endif
+
 static long
 madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev,
 		unsigned long start, unsigned long end, int behavior)
@@ -308,6 +334,10 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
 	int write;
 	size_t len;
 
+#ifdef CONFIG_MEMORY_FAILURE
+	if (behavior == MADV_HWPOISON)
+		return madvise_hwpoison(start, start+len_in);
+#endif
 	if (!madvise_behavior_valid(behavior))
 		return error;
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 9b10d875378..e2b98a6875c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -29,6 +29,7 @@
 #include <linux/rcupdate.h>
 #include <linux/limits.h>
 #include <linux/mutex.h>
+#include <linux/rbtree.h>
 #include <linux/slab.h>
 #include <linux/swap.h>
 #include <linux/spinlock.h>
@@ -43,6 +44,7 @@
 
 struct cgroup_subsys mem_cgroup_subsys __read_mostly;
 #define MEM_CGROUP_RECLAIM_RETRIES	5
+struct mem_cgroup *root_mem_cgroup __read_mostly;
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
 /* Turned on only when memory cgroup is enabled && really_do_swap_account = 1 */
@@ -53,6 +55,7 @@ static int really_do_swap_account __initdata = 1; /* for remember boot option*/
 #endif
 
 static DEFINE_MUTEX(memcg_tasklist);	/* can be hold under cgroup_mutex */
+#define SOFTLIMIT_EVENTS_THRESH (1000)
 
 /*
  * Statistics for memory cgroup.
@@ -66,6 +69,8 @@ enum mem_cgroup_stat_index {
 	MEM_CGROUP_STAT_MAPPED_FILE,  /* # of pages charged as file rss */
 	MEM_CGROUP_STAT_PGPGIN_COUNT,	/* # of pages paged in */
 	MEM_CGROUP_STAT_PGPGOUT_COUNT,	/* # of pages paged out */
+	MEM_CGROUP_STAT_EVENTS,	/* sum of pagein + pageout for internal use */
+	MEM_CGROUP_STAT_SWAPOUT, /* # of pages, swapped out */
 
 	MEM_CGROUP_STAT_NSTATS,
 };
@@ -78,6 +83,20 @@ struct mem_cgroup_stat {
 	struct mem_cgroup_stat_cpu cpustat[0];
 };
 
+static inline void
+__mem_cgroup_stat_reset_safe(struct mem_cgroup_stat_cpu *stat,
+				enum mem_cgroup_stat_index idx)
+{
+	stat->count[idx] = 0;
+}
+
+static inline s64
+__mem_cgroup_stat_read_local(struct mem_cgroup_stat_cpu *stat,
+				enum mem_cgroup_stat_index idx)
+{
+	return stat->count[idx];
+}
+
 /*
  * For accounting under irq disable, no need for increment preempt count.
  */
@@ -117,6 +136,12 @@ struct mem_cgroup_per_zone {
 	unsigned long		count[NR_LRU_LISTS];
 
 	struct zone_reclaim_stat reclaim_stat;
+	struct rb_node		tree_node;	/* RB tree node */
+	unsigned long long	usage_in_excess;/* Set to the value by which */
+						/* the soft limit is exceeded*/
+	bool			on_tree;
+	struct mem_cgroup	*mem;		/* Back pointer, we cannot */
+						/* use container_of	   */
 };
 /* Macro for accessing counter */
 #define MEM_CGROUP_ZSTAT(mz, idx)	((mz)->count[(idx)])
@@ -130,6 +155,26 @@ struct mem_cgroup_lru_info {
 };
 
 /*
+ * Cgroups above their limits are maintained in a RB-Tree, independent of
+ * their hierarchy representation
+ */
+
+struct mem_cgroup_tree_per_zone {
+	struct rb_root rb_root;
+	spinlock_t lock;
+};
+
+struct mem_cgroup_tree_per_node {
+	struct mem_cgroup_tree_per_zone rb_tree_per_zone[MAX_NR_ZONES];
+};
+
+struct mem_cgroup_tree {
+	struct mem_cgroup_tree_per_node *rb_tree_per_node[MAX_NUMNODES];
+};
+
+static struct mem_cgroup_tree soft_limit_tree __read_mostly;
+
+/*
  * The memory controller data structure. The memory controller controls both
  * page cache and RSS per cgroup. We would eventually like to provide
  * statistics based on the statistics developed by Rik Van Riel for clock-pro,
@@ -186,6 +231,13 @@ struct mem_cgroup {
 	struct mem_cgroup_stat stat;
 };
 
+/*
+ * Maximum loops in mem_cgroup_hierarchical_reclaim(), used for soft
+ * limit reclaim to prevent infinite loops, if they ever occur.
+ */
+#define	MEM_CGROUP_MAX_RECLAIM_LOOPS		(100)
+#define	MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS	(2)
+
 enum charge_type {
 	MEM_CGROUP_CHARGE_TYPE_CACHE = 0,
 	MEM_CGROUP_CHARGE_TYPE_MAPPED,
@@ -200,13 +252,8 @@ enum charge_type {
 #define PCGF_CACHE	(1UL << PCG_CACHE)
 #define PCGF_USED	(1UL << PCG_USED)
 #define PCGF_LOCK	(1UL << PCG_LOCK)
-static const unsigned long
-pcg_default_flags[NR_CHARGE_TYPE] = {
-	PCGF_CACHE | PCGF_USED | PCGF_LOCK, /* File Cache */
-	PCGF_USED | PCGF_LOCK, /* Anon */
-	PCGF_CACHE | PCGF_USED | PCGF_LOCK, /* Shmem */
-	0, /* FORCE */
-};
+/* Not used, but added here for completeness */
+#define PCGF_ACCT	(1UL << PCG_ACCT)
 
 /* for encoding cft->private value on file */
 #define _MEM			(0)
@@ -215,15 +262,241 @@ pcg_default_flags[NR_CHARGE_TYPE] = {
 #define MEMFILE_TYPE(val)	(((val) >> 16) & 0xffff)
 #define MEMFILE_ATTR(val)	((val) & 0xffff)
 
+/*
+ * Reclaim flags for mem_cgroup_hierarchical_reclaim
+ */
+#define MEM_CGROUP_RECLAIM_NOSWAP_BIT	0x0
+#define MEM_CGROUP_RECLAIM_NOSWAP	(1 << MEM_CGROUP_RECLAIM_NOSWAP_BIT)
+#define MEM_CGROUP_RECLAIM_SHRINK_BIT	0x1
+#define MEM_CGROUP_RECLAIM_SHRINK	(1 << MEM_CGROUP_RECLAIM_SHRINK_BIT)
+#define MEM_CGROUP_RECLAIM_SOFT_BIT	0x2
+#define MEM_CGROUP_RECLAIM_SOFT		(1 << MEM_CGROUP_RECLAIM_SOFT_BIT)
+
 static void mem_cgroup_get(struct mem_cgroup *mem);
 static void mem_cgroup_put(struct mem_cgroup *mem);
 static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *mem);
 
+static struct mem_cgroup_per_zone *
+mem_cgroup_zoneinfo(struct mem_cgroup *mem, int nid, int zid)
+{
+	return &mem->info.nodeinfo[nid]->zoneinfo[zid];
+}
+
+static struct mem_cgroup_per_zone *
+page_cgroup_zoneinfo(struct page_cgroup *pc)
+{
+	struct mem_cgroup *mem = pc->mem_cgroup;
+	int nid = page_cgroup_nid(pc);
+	int zid = page_cgroup_zid(pc);
+
+	if (!mem)
+		return NULL;
+
+	return mem_cgroup_zoneinfo(mem, nid, zid);
+}
+
+static struct mem_cgroup_tree_per_zone *
+soft_limit_tree_node_zone(int nid, int zid)
+{
+	return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid];
+}
+
+static struct mem_cgroup_tree_per_zone *
+soft_limit_tree_from_page(struct page *page)
+{
+	int nid = page_to_nid(page);
+	int zid = page_zonenum(page);
+
+	return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid];
+}
+
+static void
+__mem_cgroup_insert_exceeded(struct mem_cgroup *mem,
+				struct mem_cgroup_per_zone *mz,
+				struct mem_cgroup_tree_per_zone *mctz)
+{
+	struct rb_node **p = &mctz->rb_root.rb_node;
+	struct rb_node *parent = NULL;
+	struct mem_cgroup_per_zone *mz_node;
+
+	if (mz->on_tree)
+		return;
+
+	mz->usage_in_excess = res_counter_soft_limit_excess(&mem->res);
+	while (*p) {
+		parent = *p;
+		mz_node = rb_entry(parent, struct mem_cgroup_per_zone,
+					tree_node);
+		if (mz->usage_in_excess < mz_node->usage_in_excess)
+			p = &(*p)->rb_left;
+		/*
+		 * We can't avoid mem cgroups that are over their soft
+		 * limit by the same amount
+		 */
+		else if (mz->usage_in_excess >= mz_node->usage_in_excess)
+			p = &(*p)->rb_right;
+	}
+	rb_link_node(&mz->tree_node, parent, p);
+	rb_insert_color(&mz->tree_node, &mctz->rb_root);
+	mz->on_tree = true;
+}
+
+static void
+__mem_cgroup_remove_exceeded(struct mem_cgroup *mem,
+				struct mem_cgroup_per_zone *mz,
+				struct mem_cgroup_tree_per_zone *mctz)
+{
+	if (!mz->on_tree)
+		return;
+	rb_erase(&mz->tree_node, &mctz->rb_root);
+	mz->on_tree = false;
+}
+
+static void
+mem_cgroup_insert_exceeded(struct mem_cgroup *mem,
+				struct mem_cgroup_per_zone *mz,
+				struct mem_cgroup_tree_per_zone *mctz)
+{
+	spin_lock(&mctz->lock);
+	__mem_cgroup_insert_exceeded(mem, mz, mctz);
+	spin_unlock(&mctz->lock);
+}
+
+static void
+mem_cgroup_remove_exceeded(struct mem_cgroup *mem,
+				struct mem_cgroup_per_zone *mz,
+				struct mem_cgroup_tree_per_zone *mctz)
+{
+	spin_lock(&mctz->lock);
+	__mem_cgroup_remove_exceeded(mem, mz, mctz);
+	spin_unlock(&mctz->lock);
+}
+
+static bool mem_cgroup_soft_limit_check(struct mem_cgroup *mem)
+{
+	bool ret = false;
+	int cpu;
+	s64 val;
+	struct mem_cgroup_stat_cpu *cpustat;
+
+	cpu = get_cpu();
+	cpustat = &mem->stat.cpustat[cpu];
+	val = __mem_cgroup_stat_read_local(cpustat, MEM_CGROUP_STAT_EVENTS);
+	if (unlikely(val > SOFTLIMIT_EVENTS_THRESH)) {
+		__mem_cgroup_stat_reset_safe(cpustat, MEM_CGROUP_STAT_EVENTS);
+		ret = true;
+	}
+	put_cpu();
+	return ret;
+}
+
+static void mem_cgroup_update_tree(struct mem_cgroup *mem, struct page *page)
+{
+	unsigned long long prev_usage_in_excess, new_usage_in_excess;
+	bool updated_tree = false;
+	struct mem_cgroup_per_zone *mz;
+	struct mem_cgroup_tree_per_zone *mctz;
+
+	mz = mem_cgroup_zoneinfo(mem, page_to_nid(page), page_zonenum(page));
+	mctz = soft_limit_tree_from_page(page);
+
+	/*
+	 * We do updates in lazy mode, mem's are removed
+	 * lazily from the per-zone, per-node rb tree
+	 */
+	prev_usage_in_excess = mz->usage_in_excess;
+
+	new_usage_in_excess = res_counter_soft_limit_excess(&mem->res);
+	if (prev_usage_in_excess) {
+		mem_cgroup_remove_exceeded(mem, mz, mctz);
+		updated_tree = true;
+	}
+	if (!new_usage_in_excess)
+		goto done;
+	mem_cgroup_insert_exceeded(mem, mz, mctz);
+
+done:
+	if (updated_tree) {
+		spin_lock(&mctz->lock);
+		mz->usage_in_excess = new_usage_in_excess;
+		spin_unlock(&mctz->lock);
+	}
+}
+
+static void mem_cgroup_remove_from_trees(struct mem_cgroup *mem)
+{
+	int node, zone;
+	struct mem_cgroup_per_zone *mz;
+	struct mem_cgroup_tree_per_zone *mctz;
+
+	for_each_node_state(node, N_POSSIBLE) {
+		for (zone = 0; zone < MAX_NR_ZONES; zone++) {
+			mz = mem_cgroup_zoneinfo(mem, node, zone);
+			mctz = soft_limit_tree_node_zone(node, zone);
+			mem_cgroup_remove_exceeded(mem, mz, mctz);
+		}
+	}
+}
+
+static inline unsigned long mem_cgroup_get_excess(struct mem_cgroup *mem)
+{
+	return res_counter_soft_limit_excess(&mem->res) >> PAGE_SHIFT;
+}
+
+static struct mem_cgroup_per_zone *
+__mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
+{
+	struct rb_node *rightmost = NULL;
+	struct mem_cgroup_per_zone *mz = NULL;
+
+retry:
+	rightmost = rb_last(&mctz->rb_root);
+	if (!rightmost)
+		goto done;		/* Nothing to reclaim from */
+
+	mz = rb_entry(rightmost, struct mem_cgroup_per_zone, tree_node);
+	/*
+	 * Remove the node now but someone else can add it back,
+	 * we will to add it back at the end of reclaim to its correct
+	 * position in the tree.
+	 */
+	__mem_cgroup_remove_exceeded(mz->mem, mz, mctz);
+	if (!res_counter_soft_limit_excess(&mz->mem->res) ||
+		!css_tryget(&mz->mem->css))
+		goto retry;
+done:
+	return mz;
+}
+
+static struct mem_cgroup_per_zone *
+mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
+{
+	struct mem_cgroup_per_zone *mz;
+
+	spin_lock(&mctz->lock);
+	mz = __mem_cgroup_largest_soft_limit_node(mctz);
+	spin_unlock(&mctz->lock);
+	return mz;
+}
+
+static void mem_cgroup_swap_statistics(struct mem_cgroup *mem,
+					 bool charge)
+{
+	int val = (charge) ? 1 : -1;
+	struct mem_cgroup_stat *stat = &mem->stat;
+	struct mem_cgroup_stat_cpu *cpustat;
+	int cpu = get_cpu();
+
+	cpustat = &stat->cpustat[cpu];
+	__mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_SWAPOUT, val);
+	put_cpu();
+}
+
 static void mem_cgroup_charge_statistics(struct mem_cgroup *mem,
 					 struct page_cgroup *pc,
 					 bool charge)
 {
-	int val = (charge)? 1 : -1;
+	int val = (charge) ? 1 : -1;
 	struct mem_cgroup_stat *stat = &mem->stat;
 	struct mem_cgroup_stat_cpu *cpustat;
 	int cpu = get_cpu();
@@ -240,28 +513,10 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *mem,
 	else
 		__mem_cgroup_stat_add_safe(cpustat,
 				MEM_CGROUP_STAT_PGPGOUT_COUNT, 1);
+	__mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_EVENTS, 1);
 	put_cpu();
 }
 
-static struct mem_cgroup_per_zone *
-mem_cgroup_zoneinfo(struct mem_cgroup *mem, int nid, int zid)
-{
-	return &mem->info.nodeinfo[nid]->zoneinfo[zid];
-}
-
-static struct mem_cgroup_per_zone *
-page_cgroup_zoneinfo(struct page_cgroup *pc)
-{
-	struct mem_cgroup *mem = pc->mem_cgroup;
-	int nid = page_cgroup_nid(pc);
-	int zid = page_cgroup_zid(pc);
-
-	if (!mem)
-		return NULL;
-
-	return mem_cgroup_zoneinfo(mem, nid, zid);
-}
-
 static unsigned long mem_cgroup_get_local_zonestat(struct mem_cgroup *mem,
 					enum lru_list idx)
 {
@@ -354,6 +609,11 @@ static int mem_cgroup_walk_tree(struct mem_cgroup *root, void *data,
 	return ret;
 }
 
+static inline bool mem_cgroup_is_root(struct mem_cgroup *mem)
+{
+	return (mem == root_mem_cgroup);
+}
+
 /*
  * Following LRU functions are allowed to be used without PCG_LOCK.
  * Operations are called by routine of global LRU independently from memcg.
@@ -371,22 +631,24 @@ static int mem_cgroup_walk_tree(struct mem_cgroup *root, void *data,
 void mem_cgroup_del_lru_list(struct page *page, enum lru_list lru)
 {
 	struct page_cgroup *pc;
-	struct mem_cgroup *mem;
 	struct mem_cgroup_per_zone *mz;
 
 	if (mem_cgroup_disabled())
 		return;
 	pc = lookup_page_cgroup(page);
 	/* can happen while we handle swapcache. */
-	if (list_empty(&pc->lru) || !pc->mem_cgroup)
+	if (!TestClearPageCgroupAcctLRU(pc))
 		return;
+	VM_BUG_ON(!pc->mem_cgroup);
 	/*
 	 * We don't check PCG_USED bit. It's cleared when the "page" is finally
 	 * removed from global LRU.
 	 */
 	mz = page_cgroup_zoneinfo(pc);
-	mem = pc->mem_cgroup;
 	MEM_CGROUP_ZSTAT(mz, lru) -= 1;
+	if (mem_cgroup_is_root(pc->mem_cgroup))
+		return;
+	VM_BUG_ON(list_empty(&pc->lru));
 	list_del_init(&pc->lru);
 	return;
 }
@@ -410,8 +672,8 @@ void mem_cgroup_rotate_lru_list(struct page *page, enum lru_list lru)
 	 * For making pc->mem_cgroup visible, insert smp_rmb() here.
 	 */
 	smp_rmb();
-	/* unused page is not rotated. */
-	if (!PageCgroupUsed(pc))
+	/* unused or root page is not rotated. */
+	if (!PageCgroupUsed(pc) || mem_cgroup_is_root(pc->mem_cgroup))
 		return;
 	mz = page_cgroup_zoneinfo(pc);
 	list_move(&pc->lru, &mz->lists[lru]);
@@ -425,6 +687,7 @@ void mem_cgroup_add_lru_list(struct page *page, enum lru_list lru)
 	if (mem_cgroup_disabled())
 		return;
 	pc = lookup_page_cgroup(page);
+	VM_BUG_ON(PageCgroupAcctLRU(pc));
 	/*
 	 * Used bit is set without atomic ops but after smp_wmb().
 	 * For making pc->mem_cgroup visible, insert smp_rmb() here.
@@ -435,6 +698,9 @@ void mem_cgroup_add_lru_list(struct page *page, enum lru_list lru)
 
 	mz = page_cgroup_zoneinfo(pc);
 	MEM_CGROUP_ZSTAT(mz, lru) += 1;
+	SetPageCgroupAcctLRU(pc);
+	if (mem_cgroup_is_root(pc->mem_cgroup))
+		return;
 	list_add(&pc->lru, &mz->lists[lru]);
 }
 
@@ -469,7 +735,7 @@ static void mem_cgroup_lru_add_after_commit_swapcache(struct page *page)
 
 	spin_lock_irqsave(&zone->lru_lock, flags);
 	/* link when the page is linked to LRU but page_cgroup isn't */
-	if (PageLRU(page) && list_empty(&pc->lru))
+	if (PageLRU(page) && !PageCgroupAcctLRU(pc))
 		mem_cgroup_add_lru_list(page, page_lru(page));
 	spin_unlock_irqrestore(&zone->lru_lock, flags);
 }
@@ -855,28 +1121,62 @@ mem_cgroup_select_victim(struct mem_cgroup *root_mem)
  * If shrink==true, for avoiding to free too much, this returns immedieately.
  */
 static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
-				   gfp_t gfp_mask, bool noswap, bool shrink)
+						struct zone *zone,
+						gfp_t gfp_mask,
+						unsigned long reclaim_options)
 {
 	struct mem_cgroup *victim;
 	int ret, total = 0;
 	int loop = 0;
+	bool noswap = reclaim_options & MEM_CGROUP_RECLAIM_NOSWAP;
+	bool shrink = reclaim_options & MEM_CGROUP_RECLAIM_SHRINK;
+	bool check_soft = reclaim_options & MEM_CGROUP_RECLAIM_SOFT;
+	unsigned long excess = mem_cgroup_get_excess(root_mem);
 
 	/* If memsw_is_minimum==1, swap-out is of-no-use. */
 	if (root_mem->memsw_is_minimum)
 		noswap = true;
 
-	while (loop < 2) {
+	while (1) {
 		victim = mem_cgroup_select_victim(root_mem);
-		if (victim == root_mem)
+		if (victim == root_mem) {
 			loop++;
+			if (loop >= 2) {
+				/*
+				 * If we have not been able to reclaim
+				 * anything, it might because there are
+				 * no reclaimable pages under this hierarchy
+				 */
+				if (!check_soft || !total) {
+					css_put(&victim->css);
+					break;
+				}
+				/*
+				 * We want to do more targetted reclaim.
+				 * excess >> 2 is not to excessive so as to
+				 * reclaim too much, nor too less that we keep
+				 * coming back to reclaim from this cgroup
+				 */
+				if (total >= (excess >> 2) ||
+					(loop > MEM_CGROUP_MAX_RECLAIM_LOOPS)) {
+					css_put(&victim->css);
+					break;
+				}
+			}
+		}
 		if (!mem_cgroup_local_usage(&victim->stat)) {
 			/* this cgroup's local usage == 0 */
 			css_put(&victim->css);
 			continue;
 		}
 		/* we use swappiness of local cgroup */
-		ret = try_to_free_mem_cgroup_pages(victim, gfp_mask, noswap,
-						   get_swappiness(victim));
+		if (check_soft)
+			ret = mem_cgroup_shrink_node_zone(victim, gfp_mask,
+				noswap, get_swappiness(victim), zone,
+				zone->zone_pgdat->node_id);
+		else
+			ret = try_to_free_mem_cgroup_pages(victim, gfp_mask,
+						noswap, get_swappiness(victim));
 		css_put(&victim->css);
 		/*
 		 * At shrinking usage, we can't check we should stop here or
@@ -886,7 +1186,10 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
 		if (shrink)
 			return ret;
 		total += ret;
-		if (mem_cgroup_check_under_limit(root_mem))
+		if (check_soft) {
+			if (res_counter_check_under_soft_limit(&root_mem->res))
+				return total;
+		} else if (mem_cgroup_check_under_limit(root_mem))
 			return 1 + total;
 	}
 	return total;
@@ -965,11 +1268,11 @@ done:
  */
 static int __mem_cgroup_try_charge(struct mm_struct *mm,
 			gfp_t gfp_mask, struct mem_cgroup **memcg,
-			bool oom)
+			bool oom, struct page *page)
 {
-	struct mem_cgroup *mem, *mem_over_limit;
+	struct mem_cgroup *mem, *mem_over_limit, *mem_over_soft_limit;
 	int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
-	struct res_counter *fail_res;
+	struct res_counter *fail_res, *soft_fail_res = NULL;
 
 	if (unlikely(test_thread_flag(TIF_MEMDIE))) {
 		/* Don't account this! */
@@ -996,20 +1299,23 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
 	VM_BUG_ON(css_is_removed(&mem->css));
 
 	while (1) {
-		int ret;
-		bool noswap = false;
+		int ret = 0;
+		unsigned long flags = 0;
 
-		ret = res_counter_charge(&mem->res, PAGE_SIZE, &fail_res);
+		if (mem_cgroup_is_root(mem))
+			goto done;
+		ret = res_counter_charge(&mem->res, PAGE_SIZE, &fail_res,
+						&soft_fail_res);
 		if (likely(!ret)) {
 			if (!do_swap_account)
 				break;
 			ret = res_counter_charge(&mem->memsw, PAGE_SIZE,
-							&fail_res);
+							&fail_res, NULL);
 			if (likely(!ret))
 				break;
 			/* mem+swap counter fails */
-			res_counter_uncharge(&mem->res, PAGE_SIZE);
-			noswap = true;
+			res_counter_uncharge(&mem->res, PAGE_SIZE, NULL);
+			flags |= MEM_CGROUP_RECLAIM_NOSWAP;
 			mem_over_limit = mem_cgroup_from_res_counter(fail_res,
 									memsw);
 		} else
@@ -1020,8 +1326,8 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
 		if (!(gfp_mask & __GFP_WAIT))
 			goto nomem;
 
-		ret = mem_cgroup_hierarchical_reclaim(mem_over_limit, gfp_mask,
-							noswap, false);
+		ret = mem_cgroup_hierarchical_reclaim(mem_over_limit, NULL,
+						gfp_mask, flags);
 		if (ret)
 			continue;
 
@@ -1046,13 +1352,24 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
 			goto nomem;
 		}
 	}
+	/*
+	 * Insert just the ancestor, we should trickle down to the correct
+	 * cgroup for reclaim, since the other nodes will be below their
+	 * soft limit
+	 */
+	if (soft_fail_res) {
+		mem_over_soft_limit =
+			mem_cgroup_from_res_counter(soft_fail_res, res);
+		if (mem_cgroup_soft_limit_check(mem_over_soft_limit))
+			mem_cgroup_update_tree(mem_over_soft_limit, page);
+	}
+done:
 	return 0;
 nomem:
 	css_put(&mem->css);
 	return -ENOMEM;
 }
 
-
 /*
  * A helper function to get mem_cgroup from ID. must be called under
  * rcu_read_lock(). The caller must check css_is_removed() or some if
@@ -1119,15 +1436,38 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *mem,
 	lock_page_cgroup(pc);
 	if (unlikely(PageCgroupUsed(pc))) {
 		unlock_page_cgroup(pc);
-		res_counter_uncharge(&mem->res, PAGE_SIZE);
-		if (do_swap_account)
-			res_counter_uncharge(&mem->memsw, PAGE_SIZE);
+		if (!mem_cgroup_is_root(mem)) {
+			res_counter_uncharge(&mem->res, PAGE_SIZE, NULL);
+			if (do_swap_account)
+				res_counter_uncharge(&mem->memsw, PAGE_SIZE,
+							NULL);
+		}
 		css_put(&mem->css);
 		return;
 	}
+
 	pc->mem_cgroup = mem;
+	/*
+	 * We access a page_cgroup asynchronously without lock_page_cgroup().
+	 * Especially when a page_cgroup is taken from a page, pc->mem_cgroup
+	 * is accessed after testing USED bit. To make pc->mem_cgroup visible
+	 * before USED bit, we need memory barrier here.
+	 * See mem_cgroup_add_lru_list(), etc.
+ 	 */
 	smp_wmb();
-	pc->flags = pcg_default_flags[ctype];
+	switch (ctype) {
+	case MEM_CGROUP_CHARGE_TYPE_CACHE:
+	case MEM_CGROUP_CHARGE_TYPE_SHMEM:
+		SetPageCgroupCache(pc);
+		SetPageCgroupUsed(pc);
+		break;
+	case MEM_CGROUP_CHARGE_TYPE_MAPPED:
+		ClearPageCgroupCache(pc);
+		SetPageCgroupUsed(pc);
+		break;
+	default:
+		break;
+	}
 
 	mem_cgroup_charge_statistics(mem, pc, true);
 
@@ -1178,7 +1518,8 @@ static int mem_cgroup_move_account(struct page_cgroup *pc,
 	if (pc->mem_cgroup != from)
 		goto out;
 
-	res_counter_uncharge(&from->res, PAGE_SIZE);
+	if (!mem_cgroup_is_root(from))
+		res_counter_uncharge(&from->res, PAGE_SIZE, NULL);
 	mem_cgroup_charge_statistics(from, pc, false);
 
 	page = pc->page;
@@ -1197,8 +1538,8 @@ static int mem_cgroup_move_account(struct page_cgroup *pc,
 						1);
 	}
 
-	if (do_swap_account)
-		res_counter_uncharge(&from->memsw, PAGE_SIZE);
+	if (do_swap_account && !mem_cgroup_is_root(from))
+		res_counter_uncharge(&from->memsw, PAGE_SIZE, NULL);
 	css_put(&from->css);
 
 	css_get(&to->css);
@@ -1238,7 +1579,7 @@ static int mem_cgroup_move_parent(struct page_cgroup *pc,
 	parent = mem_cgroup_from_cont(pcg);
 
 
-	ret = __mem_cgroup_try_charge(NULL, gfp_mask, &parent, false);
+	ret = __mem_cgroup_try_charge(NULL, gfp_mask, &parent, false, page);
 	if (ret || !parent)
 		return ret;
 
@@ -1268,9 +1609,11 @@ uncharge:
 	/* drop extra refcnt by try_charge() */
 	css_put(&parent->css);
 	/* uncharge if move fails */
-	res_counter_uncharge(&parent->res, PAGE_SIZE);
-	if (do_swap_account)
-		res_counter_uncharge(&parent->memsw, PAGE_SIZE);
+	if (!mem_cgroup_is_root(parent)) {
+		res_counter_uncharge(&parent->res, PAGE_SIZE, NULL);
+		if (do_swap_account)
+			res_counter_uncharge(&parent->memsw, PAGE_SIZE, NULL);
+	}
 	return ret;
 }
 
@@ -1295,7 +1638,7 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
 	prefetchw(pc);
 
 	mem = memcg;
-	ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, true);
+	ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, true, page);
 	if (ret || !mem)
 		return ret;
 
@@ -1414,14 +1757,14 @@ int mem_cgroup_try_charge_swapin(struct mm_struct *mm,
 	if (!mem)
 		goto charge_cur_mm;
 	*ptr = mem;
-	ret = __mem_cgroup_try_charge(NULL, mask, ptr, true);
+	ret = __mem_cgroup_try_charge(NULL, mask, ptr, true, page);
 	/* drop extra refcnt from tryget */
 	css_put(&mem->css);
 	return ret;
 charge_cur_mm:
 	if (unlikely(!mm))
 		mm = &init_mm;
-	return __mem_cgroup_try_charge(mm, mask, ptr, true);
+	return __mem_cgroup_try_charge(mm, mask, ptr, true, page);
 }
 
 static void
@@ -1459,7 +1802,10 @@ __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr,
 			 * This recorded memcg can be obsolete one. So, avoid
 			 * calling css_tryget
 			 */
-			res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
+			if (!mem_cgroup_is_root(memcg))
+				res_counter_uncharge(&memcg->memsw, PAGE_SIZE,
+							NULL);
+			mem_cgroup_swap_statistics(memcg, false);
 			mem_cgroup_put(memcg);
 		}
 		rcu_read_unlock();
@@ -1484,9 +1830,11 @@ void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *mem)
 		return;
 	if (!mem)
 		return;
-	res_counter_uncharge(&mem->res, PAGE_SIZE);
-	if (do_swap_account)
-		res_counter_uncharge(&mem->memsw, PAGE_SIZE);
+	if (!mem_cgroup_is_root(mem)) {
+		res_counter_uncharge(&mem->res, PAGE_SIZE, NULL);
+		if (do_swap_account)
+			res_counter_uncharge(&mem->memsw, PAGE_SIZE, NULL);
+	}
 	css_put(&mem->css);
 }
 
@@ -1500,6 +1848,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 	struct page_cgroup *pc;
 	struct mem_cgroup *mem = NULL;
 	struct mem_cgroup_per_zone *mz;
+	bool soft_limit_excess = false;
 
 	if (mem_cgroup_disabled())
 		return NULL;
@@ -1538,9 +1887,14 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 		break;
 	}
 
-	res_counter_uncharge(&mem->res, PAGE_SIZE);
-	if (do_swap_account && (ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT))
-		res_counter_uncharge(&mem->memsw, PAGE_SIZE);
+	if (!mem_cgroup_is_root(mem)) {
+		res_counter_uncharge(&mem->res, PAGE_SIZE, &soft_limit_excess);
+		if (do_swap_account &&
+				(ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT))
+			res_counter_uncharge(&mem->memsw, PAGE_SIZE, NULL);
+	}
+	if (ctype == MEM_CGROUP_CHARGE_TYPE_SWAPOUT)
+		mem_cgroup_swap_statistics(mem, true);
 	mem_cgroup_charge_statistics(mem, pc, false);
 
 	ClearPageCgroupUsed(pc);
@@ -1554,6 +1908,8 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 	mz = page_cgroup_zoneinfo(pc);
 	unlock_page_cgroup(pc);
 
+	if (soft_limit_excess && mem_cgroup_soft_limit_check(mem))
+		mem_cgroup_update_tree(mem, page);
 	/* at swapout, this memcg will be accessed to record to swap */
 	if (ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT)
 		css_put(&mem->css);
@@ -1629,7 +1985,9 @@ void mem_cgroup_uncharge_swap(swp_entry_t ent)
 		 * We uncharge this because swap is freed.
 		 * This memcg can be obsolete one. We avoid calling css_tryget
 		 */
-		res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
+		if (!mem_cgroup_is_root(memcg))
+			res_counter_uncharge(&memcg->memsw, PAGE_SIZE, NULL);
+		mem_cgroup_swap_statistics(memcg, false);
 		mem_cgroup_put(memcg);
 	}
 	rcu_read_unlock();
@@ -1658,7 +2016,8 @@ int mem_cgroup_prepare_migration(struct page *page, struct mem_cgroup **ptr)
 	unlock_page_cgroup(pc);
 
 	if (mem) {
-		ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, &mem, false);
+		ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, &mem, false,
+						page);
 		css_put(&mem->css);
 	}
 	*ptr = mem;
@@ -1798,8 +2157,9 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
 		if (!ret)
 			break;
 
-		progress = mem_cgroup_hierarchical_reclaim(memcg, GFP_KERNEL,
-						   false, true);
+		progress = mem_cgroup_hierarchical_reclaim(memcg, NULL,
+						GFP_KERNEL,
+						MEM_CGROUP_RECLAIM_SHRINK);
 		curusage = res_counter_read_u64(&memcg->res, RES_USAGE);
 		/* Usage is reduced ? */
   		if (curusage >= oldusage)
@@ -1851,7 +2211,9 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
 		if (!ret)
 			break;
 
-		mem_cgroup_hierarchical_reclaim(memcg, GFP_KERNEL, true, true);
+		mem_cgroup_hierarchical_reclaim(memcg, NULL, GFP_KERNEL,
+						MEM_CGROUP_RECLAIM_NOSWAP |
+						MEM_CGROUP_RECLAIM_SHRINK);
 		curusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
 		/* Usage is reduced ? */
 		if (curusage >= oldusage)
@@ -1862,6 +2224,97 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
 	return ret;
 }
 
+unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
+						gfp_t gfp_mask, int nid,
+						int zid)
+{
+	unsigned long nr_reclaimed = 0;
+	struct mem_cgroup_per_zone *mz, *next_mz = NULL;
+	unsigned long reclaimed;
+	int loop = 0;
+	struct mem_cgroup_tree_per_zone *mctz;
+
+	if (order > 0)
+		return 0;
+
+	mctz = soft_limit_tree_node_zone(nid, zid);
+	/*
+	 * This loop can run a while, specially if mem_cgroup's continuously
+	 * keep exceeding their soft limit and putting the system under
+	 * pressure
+	 */
+	do {
+		if (next_mz)
+			mz = next_mz;
+		else
+			mz = mem_cgroup_largest_soft_limit_node(mctz);
+		if (!mz)
+			break;
+
+		reclaimed = mem_cgroup_hierarchical_reclaim(mz->mem, zone,
+						gfp_mask,
+						MEM_CGROUP_RECLAIM_SOFT);
+		nr_reclaimed += reclaimed;
+		spin_lock(&mctz->lock);
+
+		/*
+		 * 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->mem->css);
+					next_mz = NULL;
+				} else /* next_mz == NULL or other memcg */
+					break;
+			} while (1);
+		}
+		mz->usage_in_excess =
+			res_counter_soft_limit_excess(&mz->mem->res);
+		__mem_cgroup_remove_exceeded(mz->mem, mz, mctz);
+		/*
+		 * One school of thought says that we should not add
+		 * back the node to the tree if reclaim returns 0.
+		 * But our reclaim could return 0, simply because due
+		 * to priority we are exposing a smaller subset of
+		 * memory to reclaim from. Consider this as a longer
+		 * term TODO.
+		 */
+		if (mz->usage_in_excess)
+			__mem_cgroup_insert_exceeded(mz->mem, mz, mctz);
+		spin_unlock(&mctz->lock);
+		css_put(&mz->mem->css);
+		loop++;
+		/*
+		 * Could not reclaim anything and there are no more
+		 * mem cgroups to try or we seem to be looping without
+		 * reclaiming anything.
+		 */
+		if (!nr_reclaimed &&
+			(next_mz == NULL ||
+			loop > MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS))
+			break;
+	} while (!nr_reclaimed);
+	if (next_mz)
+		css_put(&next_mz->mem->css);
+	return nr_reclaimed;
+}
+
 /*
  * This routine traverse page_cgroup in given list and drop them all.
  * *And* this routine doesn't reclaim page itself, just removes page_cgroup.
@@ -2046,20 +2499,64 @@ static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft,
 	return retval;
 }
 
+struct mem_cgroup_idx_data {
+	s64 val;
+	enum mem_cgroup_stat_index idx;
+};
+
+static int
+mem_cgroup_get_idx_stat(struct mem_cgroup *mem, void *data)
+{
+	struct mem_cgroup_idx_data *d = data;
+	d->val += mem_cgroup_read_stat(&mem->stat, d->idx);
+	return 0;
+}
+
+static void
+mem_cgroup_get_recursive_idx_stat(struct mem_cgroup *mem,
+				enum mem_cgroup_stat_index idx, s64 *val)
+{
+	struct mem_cgroup_idx_data d;
+	d.idx = idx;
+	d.val = 0;
+	mem_cgroup_walk_tree(mem, &d, mem_cgroup_get_idx_stat);
+	*val = d.val;
+}
+
 static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft)
 {
 	struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
-	u64 val = 0;
+	u64 idx_val, val;
 	int type, name;
 
 	type = MEMFILE_TYPE(cft->private);
 	name = MEMFILE_ATTR(cft->private);
 	switch (type) {
 	case _MEM:
-		val = res_counter_read_u64(&mem->res, name);
+		if (name == RES_USAGE && mem_cgroup_is_root(mem)) {
+			mem_cgroup_get_recursive_idx_stat(mem,
+				MEM_CGROUP_STAT_CACHE, &idx_val);
+			val = idx_val;
+			mem_cgroup_get_recursive_idx_stat(mem,
+				MEM_CGROUP_STAT_RSS, &idx_val);
+			val += idx_val;
+			val <<= PAGE_SHIFT;
+		} else
+			val = res_counter_read_u64(&mem->res, name);
 		break;
 	case _MEMSWAP:
-		val = res_counter_read_u64(&mem->memsw, name);
+		if (name == RES_USAGE && mem_cgroup_is_root(mem)) {
+			mem_cgroup_get_recursive_idx_stat(mem,
+				MEM_CGROUP_STAT_CACHE, &idx_val);
+			val = idx_val;
+			mem_cgroup_get_recursive_idx_stat(mem,
+				MEM_CGROUP_STAT_RSS, &idx_val);
+			val += idx_val;
+			mem_cgroup_get_recursive_idx_stat(mem,
+				MEM_CGROUP_STAT_SWAPOUT, &idx_val);
+			val <<= PAGE_SHIFT;
+		} else
+			val = res_counter_read_u64(&mem->memsw, name);
 		break;
 	default:
 		BUG();
@@ -2083,6 +2580,10 @@ static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
 	name = MEMFILE_ATTR(cft->private);
 	switch (name) {
 	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(buffer, &val);
 		if (ret)
@@ -2092,6 +2593,20 @@ static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
 		else
 			ret = mem_cgroup_resize_memsw_limit(memcg, val);
 		break;
+	case RES_SOFT_LIMIT:
+		ret = res_counter_memparse_write_strategy(buffer, &val);
+		if (ret)
+			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;
+		break;
 	default:
 		ret = -EINVAL; /* should be BUG() ? */
 		break;
@@ -2149,6 +2664,7 @@ static int mem_cgroup_reset(struct cgroup *cont, unsigned int event)
 			res_counter_reset_failcnt(&mem->memsw);
 		break;
 	}
+
 	return 0;
 }
 
@@ -2160,6 +2676,7 @@ enum {
 	MCS_MAPPED_FILE,
 	MCS_PGPGIN,
 	MCS_PGPGOUT,
+	MCS_SWAP,
 	MCS_INACTIVE_ANON,
 	MCS_ACTIVE_ANON,
 	MCS_INACTIVE_FILE,
@@ -2181,6 +2698,7 @@ struct {
 	{"mapped_file", "total_mapped_file"},
 	{"pgpgin", "total_pgpgin"},
 	{"pgpgout", "total_pgpgout"},
+	{"swap", "total_swap"},
 	{"inactive_anon", "total_inactive_anon"},
 	{"active_anon", "total_active_anon"},
 	{"inactive_file", "total_inactive_file"},
@@ -2205,6 +2723,10 @@ static int mem_cgroup_get_local_stat(struct mem_cgroup *mem, void *data)
 	s->stat[MCS_PGPGIN] += val;
 	val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_PGPGOUT_COUNT);
 	s->stat[MCS_PGPGOUT] += val;
+	if (do_swap_account) {
+		val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_SWAPOUT);
+		s->stat[MCS_SWAP] += val * PAGE_SIZE;
+	}
 
 	/* per zone stat */
 	val = mem_cgroup_get_local_zonestat(mem, LRU_INACTIVE_ANON);
@@ -2236,8 +2758,11 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
 	memset(&mystat, 0, sizeof(mystat));
 	mem_cgroup_get_local_stat(mem_cont, &mystat);
 
-	for (i = 0; i < NR_MCS_STAT; i++)
+	for (i = 0; i < NR_MCS_STAT; i++) {
+		if (i == MCS_SWAP && !do_swap_account)
+			continue;
 		cb->fill(cb, memcg_stat_strings[i].local_name, mystat.stat[i]);
+	}
 
 	/* Hierarchical information */
 	{
@@ -2250,9 +2775,11 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
 
 	memset(&mystat, 0, sizeof(mystat));
 	mem_cgroup_get_total_stat(mem_cont, &mystat);
-	for (i = 0; i < NR_MCS_STAT; i++)
+	for (i = 0; i < NR_MCS_STAT; i++) {
+		if (i == MCS_SWAP && !do_swap_account)
+			continue;
 		cb->fill(cb, memcg_stat_strings[i].total_name, mystat.stat[i]);
-
+	}
 
 #ifdef CONFIG_DEBUG_VM
 	cb->fill(cb, "inactive_ratio", calc_inactive_ratio(mem_cont, NULL));
@@ -2345,6 +2872,12 @@ static struct cftype mem_cgroup_files[] = {
 		.read_u64 = mem_cgroup_read,
 	},
 	{
+		.name = "soft_limit_in_bytes",
+		.private = MEMFILE_PRIVATE(_MEM, RES_SOFT_LIMIT),
+		.write_string = mem_cgroup_write,
+		.read_u64 = mem_cgroup_read,
+	},
+	{
 		.name = "failcnt",
 		.private = MEMFILE_PRIVATE(_MEM, RES_FAILCNT),
 		.trigger = mem_cgroup_reset,
@@ -2438,6 +2971,9 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node)
 		mz = &pn->zoneinfo[zone];
 		for_each_lru(l)
 			INIT_LIST_HEAD(&mz->lists[l]);
+		mz->usage_in_excess = 0;
+		mz->on_tree = false;
+		mz->mem = mem;
 	}
 	return 0;
 }
@@ -2483,6 +3019,7 @@ static void __mem_cgroup_free(struct mem_cgroup *mem)
 {
 	int node;
 
+	mem_cgroup_remove_from_trees(mem);
 	free_css_id(&mem_cgroup_subsys, &mem->css);
 
 	for_each_node_state(node, N_POSSIBLE)
@@ -2531,6 +3068,31 @@ static void __init enable_swap_cgroup(void)
 }
 #endif
 
+static int mem_cgroup_soft_limit_tree_init(void)
+{
+	struct mem_cgroup_tree_per_node *rtpn;
+	struct mem_cgroup_tree_per_zone *rtpz;
+	int tmp, node, zone;
+
+	for_each_node_state(node, N_POSSIBLE) {
+		tmp = node;
+		if (!node_state(node, N_NORMAL_MEMORY))
+			tmp = -1;
+		rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL, tmp);
+		if (!rtpn)
+			return 1;
+
+		soft_limit_tree.rb_tree_per_node[node] = rtpn;
+
+		for (zone = 0; zone < MAX_NR_ZONES; zone++) {
+			rtpz = &rtpn->rb_tree_per_zone[zone];
+			rtpz->rb_root = RB_ROOT;
+			spin_lock_init(&rtpz->lock);
+		}
+	}
+	return 0;
+}
+
 static struct cgroup_subsys_state * __ref
 mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 {
@@ -2545,10 +3107,15 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 	for_each_node_state(node, N_POSSIBLE)
 		if (alloc_mem_cgroup_per_zone_info(mem, node))
 			goto free_out;
+
 	/* root ? */
 	if (cont->parent == NULL) {
 		enable_swap_cgroup();
 		parent = NULL;
+		root_mem_cgroup = mem;
+		if (mem_cgroup_soft_limit_tree_init())
+			goto free_out;
+
 	} else {
 		parent = mem_cgroup_from_cont(cont->parent);
 		mem->use_hierarchy = parent->use_hierarchy;
@@ -2577,6 +3144,7 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 	return &mem->css;
 free_out:
 	__mem_cgroup_free(mem);
+	root_mem_cgroup = NULL;
 	return ERR_PTR(error);
 }
 
@@ -2612,7 +3180,8 @@ static int mem_cgroup_populate(struct cgroup_subsys *ss,
 static void mem_cgroup_move_task(struct cgroup_subsys *ss,
 				struct cgroup *cont,
 				struct cgroup *old_cont,
-				struct task_struct *p)
+				struct task_struct *p,
+				bool threadgroup)
 {
 	mutex_lock(&memcg_tasklist);
 	/*
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
new file mode 100644
index 00000000000..729d4b15b64
--- /dev/null
+++ b/mm/memory-failure.c
@@ -0,0 +1,832 @@
+/*
+ * Copyright (C) 2008, 2009 Intel Corporation
+ * Authors: Andi Kleen, Fengguang Wu
+ *
+ * This software may be redistributed and/or modified under the terms of
+ * the GNU General Public License ("GPL") version 2 only as published by the
+ * Free Software Foundation.
+ *
+ * High level machine check handler. Handles pages reported by the
+ * hardware as being corrupted usually due to a 2bit ECC memory or cache
+ * failure.
+ *
+ * Handles page cache pages in various states.	The tricky part
+ * here is that we can access any page asynchronous to other VM
+ * users, because memory failures could happen anytime and anywhere,
+ * possibly violating some of their assumptions. This is why this code
+ * has to be extremely careful. Generally it tries to use normal locking
+ * rules, as in get the standard locks, even if that means the
+ * error handling takes potentially a long time.
+ *
+ * The operation to map back from RMAP chains to processes has to walk
+ * the complete process list and has non linear complexity with the number
+ * mappings. In short it can be quite slow. But since memory corruptions
+ * are rare we hope to get away with this.
+ */
+
+/*
+ * Notebook:
+ * - hugetlb needs more code
+ * - kcore/oldmem/vmcore/mem/kmem check for hwpoison pages
+ * - pass bad pages to kdump next kernel
+ */
+#define DEBUG 1		/* remove me in 2.6.34 */
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/page-flags.h>
+#include <linux/sched.h>
+#include <linux/rmap.h>
+#include <linux/pagemap.h>
+#include <linux/swap.h>
+#include <linux/backing-dev.h>
+#include "internal.h"
+
+int sysctl_memory_failure_early_kill __read_mostly = 0;
+
+int sysctl_memory_failure_recovery __read_mostly = 1;
+
+atomic_long_t mce_bad_pages __read_mostly = ATOMIC_LONG_INIT(0);
+
+/*
+ * Send all the processes who have the page mapped an ``action optional''
+ * signal.
+ */
+static int kill_proc_ao(struct task_struct *t, unsigned long addr, int trapno,
+			unsigned long pfn)
+{
+	struct siginfo si;
+	int ret;
+
+	printk(KERN_ERR
+		"MCE %#lx: Killing %s:%d early due to hardware memory corruption\n",
+		pfn, t->comm, t->pid);
+	si.si_signo = SIGBUS;
+	si.si_errno = 0;
+	si.si_code = BUS_MCEERR_AO;
+	si.si_addr = (void *)addr;
+#ifdef __ARCH_SI_TRAPNO
+	si.si_trapno = trapno;
+#endif
+	si.si_addr_lsb = PAGE_SHIFT;
+	/*
+	 * Don't use force here, it's convenient if the signal
+	 * can be temporarily blocked.
+	 * This could cause a loop when the user sets SIGBUS
+	 * to SIG_IGN, but hopefully noone will do that?
+	 */
+	ret = send_sig_info(SIGBUS, &si, t);  /* synchronous? */
+	if (ret < 0)
+		printk(KERN_INFO "MCE: Error sending signal to %s:%d: %d\n",
+		       t->comm, t->pid, ret);
+	return ret;
+}
+
+/*
+ * Kill all processes that have a poisoned page mapped and then isolate
+ * the page.
+ *
+ * General strategy:
+ * Find all processes having the page mapped and kill them.
+ * But we keep a page reference around so that the page is not
+ * actually freed yet.
+ * Then stash the page away
+ *
+ * There's no convenient way to get back to mapped processes
+ * from the VMAs. So do a brute-force search over all
+ * running processes.
+ *
+ * Remember that machine checks are not common (or rather
+ * if they are common you have other problems), so this shouldn't
+ * be a performance issue.
+ *
+ * Also there are some races possible while we get from the
+ * error detection to actually handle it.
+ */
+
+struct to_kill {
+	struct list_head nd;
+	struct task_struct *tsk;
+	unsigned long addr;
+	unsigned addr_valid:1;
+};
+
+/*
+ * Failure handling: if we can't find or can't kill a process there's
+ * not much we can do.	We just print a message and ignore otherwise.
+ */
+
+/*
+ * Schedule a process for later kill.
+ * Uses GFP_ATOMIC allocations to avoid potential recursions in the VM.
+ * TBD would GFP_NOIO be enough?
+ */
+static void add_to_kill(struct task_struct *tsk, struct page *p,
+		       struct vm_area_struct *vma,
+		       struct list_head *to_kill,
+		       struct to_kill **tkc)
+{
+	struct to_kill *tk;
+
+	if (*tkc) {
+		tk = *tkc;
+		*tkc = NULL;
+	} else {
+		tk = kmalloc(sizeof(struct to_kill), GFP_ATOMIC);
+		if (!tk) {
+			printk(KERN_ERR
+		"MCE: Out of memory while machine check handling\n");
+			return;
+		}
+	}
+	tk->addr = page_address_in_vma(p, vma);
+	tk->addr_valid = 1;
+
+	/*
+	 * In theory we don't have to kill when the page was
+	 * munmaped. But it could be also a mremap. Since that's
+	 * likely very rare kill anyways just out of paranoia, but use
+	 * a SIGKILL because the error is not contained anymore.
+	 */
+	if (tk->addr == -EFAULT) {
+		pr_debug("MCE: Unable to find user space address %lx in %s\n",
+			page_to_pfn(p), tsk->comm);
+		tk->addr_valid = 0;
+	}
+	get_task_struct(tsk);
+	tk->tsk = tsk;
+	list_add_tail(&tk->nd, to_kill);
+}
+
+/*
+ * Kill the processes that have been collected earlier.
+ *
+ * Only do anything when DOIT is set, otherwise just free the list
+ * (this is used for clean pages which do not need killing)
+ * Also when FAIL is set do a force kill because something went
+ * wrong earlier.
+ */
+static void kill_procs_ao(struct list_head *to_kill, int doit, int trapno,
+			  int fail, unsigned long pfn)
+{
+	struct to_kill *tk, *next;
+
+	list_for_each_entry_safe (tk, next, to_kill, nd) {
+		if (doit) {
+			/*
+			 * In case something went wrong with munmaping
+			 * make sure the process doesn't catch the
+			 * signal and then access the memory. Just kill it.
+			 * the signal handlers
+			 */
+			if (fail || tk->addr_valid == 0) {
+				printk(KERN_ERR
+		"MCE %#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n",
+					pfn, tk->tsk->comm, tk->tsk->pid);
+				force_sig(SIGKILL, tk->tsk);
+			}
+
+			/*
+			 * In theory the process could have mapped
+			 * something else on the address in-between. We could
+			 * check for that, but we need to tell the
+			 * process anyways.
+			 */
+			else if (kill_proc_ao(tk->tsk, tk->addr, trapno,
+					      pfn) < 0)
+				printk(KERN_ERR
+		"MCE %#lx: Cannot send advisory machine check signal to %s:%d\n",
+					pfn, tk->tsk->comm, tk->tsk->pid);
+		}
+		put_task_struct(tk->tsk);
+		kfree(tk);
+	}
+}
+
+static int task_early_kill(struct task_struct *tsk)
+{
+	if (!tsk->mm)
+		return 0;
+	if (tsk->flags & PF_MCE_PROCESS)
+		return !!(tsk->flags & PF_MCE_EARLY);
+	return sysctl_memory_failure_early_kill;
+}
+
+/*
+ * Collect processes when the error hit an anonymous page.
+ */
+static void collect_procs_anon(struct page *page, struct list_head *to_kill,
+			      struct to_kill **tkc)
+{
+	struct vm_area_struct *vma;
+	struct task_struct *tsk;
+	struct anon_vma *av;
+
+	read_lock(&tasklist_lock);
+	av = page_lock_anon_vma(page);
+	if (av == NULL)	/* Not actually mapped anymore */
+		goto out;
+	for_each_process (tsk) {
+		if (!task_early_kill(tsk))
+			continue;
+		list_for_each_entry (vma, &av->head, anon_vma_node) {
+			if (!page_mapped_in_vma(page, vma))
+				continue;
+			if (vma->vm_mm == tsk->mm)
+				add_to_kill(tsk, page, vma, to_kill, tkc);
+		}
+	}
+	page_unlock_anon_vma(av);
+out:
+	read_unlock(&tasklist_lock);
+}
+
+/*
+ * Collect processes when the error hit a file mapped page.
+ */
+static void collect_procs_file(struct page *page, struct list_head *to_kill,
+			      struct to_kill **tkc)
+{
+	struct vm_area_struct *vma;
+	struct task_struct *tsk;
+	struct prio_tree_iter iter;
+	struct address_space *mapping = page->mapping;
+
+	/*
+	 * A note on the locking order between the two locks.
+	 * We don't rely on this particular order.
+	 * If you have some other code that needs a different order
+	 * feel free to switch them around. Or add a reverse link
+	 * from mm_struct to task_struct, then this could be all
+	 * done without taking tasklist_lock and looping over all tasks.
+	 */
+
+	read_lock(&tasklist_lock);
+	spin_lock(&mapping->i_mmap_lock);
+	for_each_process(tsk) {
+		pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+
+		if (!task_early_kill(tsk))
+			continue;
+
+		vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff,
+				      pgoff) {
+			/*
+			 * Send early kill signal to tasks where a vma covers
+			 * the page but the corrupted page is not necessarily
+			 * mapped it in its pte.
+			 * Assume applications who requested early kill want
+			 * to be informed of all such data corruptions.
+			 */
+			if (vma->vm_mm == tsk->mm)
+				add_to_kill(tsk, page, vma, to_kill, tkc);
+		}
+	}
+	spin_unlock(&mapping->i_mmap_lock);
+	read_unlock(&tasklist_lock);
+}
+
+/*
+ * Collect the processes who have the corrupted page mapped to kill.
+ * This is done in two steps for locking reasons.
+ * First preallocate one tokill structure outside the spin locks,
+ * so that we can kill at least one process reasonably reliable.
+ */
+static void collect_procs(struct page *page, struct list_head *tokill)
+{
+	struct to_kill *tk;
+
+	if (!page->mapping)
+		return;
+
+	tk = kmalloc(sizeof(struct to_kill), GFP_NOIO);
+	if (!tk)
+		return;
+	if (PageAnon(page))
+		collect_procs_anon(page, tokill, &tk);
+	else
+		collect_procs_file(page, tokill, &tk);
+	kfree(tk);
+}
+
+/*
+ * Error handlers for various types of pages.
+ */
+
+enum outcome {
+	FAILED,		/* Error handling failed */
+	DELAYED,	/* Will be handled later */
+	IGNORED,	/* Error safely ignored */
+	RECOVERED,	/* Successfully recovered */
+};
+
+static const char *action_name[] = {
+	[FAILED] = "Failed",
+	[DELAYED] = "Delayed",
+	[IGNORED] = "Ignored",
+	[RECOVERED] = "Recovered",
+};
+
+/*
+ * Error hit kernel page.
+ * Do nothing, try to be lucky and not touch this instead. For a few cases we
+ * could be more sophisticated.
+ */
+static int me_kernel(struct page *p, unsigned long pfn)
+{
+	return DELAYED;
+}
+
+/*
+ * Already poisoned page.
+ */
+static int me_ignore(struct page *p, unsigned long pfn)
+{
+	return IGNORED;
+}
+
+/*
+ * Page in unknown state. Do nothing.
+ */
+static int me_unknown(struct page *p, unsigned long pfn)
+{
+	printk(KERN_ERR "MCE %#lx: Unknown page state\n", pfn);
+	return FAILED;
+}
+
+/*
+ * Free memory
+ */
+static int me_free(struct page *p, unsigned long pfn)
+{
+	return DELAYED;
+}
+
+/*
+ * Clean (or cleaned) page cache page.
+ */
+static int me_pagecache_clean(struct page *p, unsigned long pfn)
+{
+	int err;
+	int ret = FAILED;
+	struct address_space *mapping;
+
+	if (!isolate_lru_page(p))
+		page_cache_release(p);
+
+	/*
+	 * For anonymous pages we're done the only reference left
+	 * should be the one m_f() holds.
+	 */
+	if (PageAnon(p))
+		return RECOVERED;
+
+	/*
+	 * Now truncate the page in the page cache. This is really
+	 * more like a "temporary hole punch"
+	 * Don't do this for block devices when someone else
+	 * has a reference, because it could be file system metadata
+	 * and that's not safe to truncate.
+	 */
+	mapping = page_mapping(p);
+	if (!mapping) {
+		/*
+		 * Page has been teared down in the meanwhile
+		 */
+		return FAILED;
+	}
+
+	/*
+	 * Truncation is a bit tricky. Enable it per file system for now.
+	 *
+	 * Open: to take i_mutex or not for this? Right now we don't.
+	 */
+	if (mapping->a_ops->error_remove_page) {
+		err = mapping->a_ops->error_remove_page(mapping, p);
+		if (err != 0) {
+			printk(KERN_INFO "MCE %#lx: Failed to punch page: %d\n",
+					pfn, err);
+		} else if (page_has_private(p) &&
+				!try_to_release_page(p, GFP_NOIO)) {
+			pr_debug("MCE %#lx: failed to release buffers\n", pfn);
+		} else {
+			ret = RECOVERED;
+		}
+	} else {
+		/*
+		 * If the file system doesn't support it just invalidate
+		 * This fails on dirty or anything with private pages
+		 */
+		if (invalidate_inode_page(p))
+			ret = RECOVERED;
+		else
+			printk(KERN_INFO "MCE %#lx: Failed to invalidate\n",
+				pfn);
+	}
+	return ret;
+}
+
+/*
+ * Dirty cache page page
+ * Issues: when the error hit a hole page the error is not properly
+ * propagated.
+ */
+static int me_pagecache_dirty(struct page *p, unsigned long pfn)
+{
+	struct address_space *mapping = page_mapping(p);
+
+	SetPageError(p);
+	/* TBD: print more information about the file. */
+	if (mapping) {
+		/*
+		 * IO error will be reported by write(), fsync(), etc.
+		 * who check the mapping.
+		 * This way the application knows that something went
+		 * wrong with its dirty file data.
+		 *
+		 * There's one open issue:
+		 *
+		 * The EIO will be only reported on the next IO
+		 * operation and then cleared through the IO map.
+		 * Normally Linux has two mechanisms to pass IO error
+		 * first through the AS_EIO flag in the address space
+		 * and then through the PageError flag in the page.
+		 * Since we drop pages on memory failure handling the
+		 * only mechanism open to use is through AS_AIO.
+		 *
+		 * This has the disadvantage that it gets cleared on
+		 * the first operation that returns an error, while
+		 * the PageError bit is more sticky and only cleared
+		 * when the page is reread or dropped.  If an
+		 * application assumes it will always get error on
+		 * fsync, but does other operations on the fd before
+		 * and the page is dropped inbetween then the error
+		 * will not be properly reported.
+		 *
+		 * This can already happen even without hwpoisoned
+		 * pages: first on metadata IO errors (which only
+		 * report through AS_EIO) or when the page is dropped
+		 * at the wrong time.
+		 *
+		 * So right now we assume that the application DTRT on
+		 * the first EIO, but we're not worse than other parts
+		 * of the kernel.
+		 */
+		mapping_set_error(mapping, EIO);
+	}
+
+	return me_pagecache_clean(p, pfn);
+}
+
+/*
+ * Clean and dirty swap cache.
+ *
+ * Dirty swap cache page is tricky to handle. The page could live both in page
+ * cache and swap cache(ie. page is freshly swapped in). So it could be
+ * referenced concurrently by 2 types of PTEs:
+ * normal PTEs and swap PTEs. We try to handle them consistently by calling
+ * try_to_unmap(TTU_IGNORE_HWPOISON) to convert the normal PTEs to swap PTEs,
+ * and then
+ *      - clear dirty bit to prevent IO
+ *      - remove from LRU
+ *      - but keep in the swap cache, so that when we return to it on
+ *        a later page fault, we know the application is accessing
+ *        corrupted data and shall be killed (we installed simple
+ *        interception code in do_swap_page to catch it).
+ *
+ * Clean swap cache pages can be directly isolated. A later page fault will
+ * bring in the known good data from disk.
+ */
+static int me_swapcache_dirty(struct page *p, unsigned long pfn)
+{
+	int ret = FAILED;
+
+	ClearPageDirty(p);
+	/* Trigger EIO in shmem: */
+	ClearPageUptodate(p);
+
+	if (!isolate_lru_page(p)) {
+		page_cache_release(p);
+		ret = DELAYED;
+	}
+
+	return ret;
+}
+
+static int me_swapcache_clean(struct page *p, unsigned long pfn)
+{
+	int ret = FAILED;
+
+	if (!isolate_lru_page(p)) {
+		page_cache_release(p);
+		ret = RECOVERED;
+	}
+	delete_from_swap_cache(p);
+	return ret;
+}
+
+/*
+ * Huge pages. Needs work.
+ * Issues:
+ * No rmap support so we cannot find the original mapper. In theory could walk
+ * all MMs and look for the mappings, but that would be non atomic and racy.
+ * Need rmap for hugepages for this. Alternatively we could employ a heuristic,
+ * like just walking the current process and hoping it has it mapped (that
+ * should be usually true for the common "shared database cache" case)
+ * Should handle free huge pages and dequeue them too, but this needs to
+ * handle huge page accounting correctly.
+ */
+static int me_huge_page(struct page *p, unsigned long pfn)
+{
+	return FAILED;
+}
+
+/*
+ * Various page states we can handle.
+ *
+ * A page state is defined by its current page->flags bits.
+ * The table matches them in order and calls the right handler.
+ *
+ * This is quite tricky because we can access page at any time
+ * in its live cycle, so all accesses have to be extremly careful.
+ *
+ * This is not complete. More states could be added.
+ * For any missing state don't attempt recovery.
+ */
+
+#define dirty		(1UL << PG_dirty)
+#define sc		(1UL << PG_swapcache)
+#define unevict		(1UL << PG_unevictable)
+#define mlock		(1UL << PG_mlocked)
+#define writeback	(1UL << PG_writeback)
+#define lru		(1UL << PG_lru)
+#define swapbacked	(1UL << PG_swapbacked)
+#define head		(1UL << PG_head)
+#define tail		(1UL << PG_tail)
+#define compound	(1UL << PG_compound)
+#define slab		(1UL << PG_slab)
+#define buddy		(1UL << PG_buddy)
+#define reserved	(1UL << PG_reserved)
+
+static struct page_state {
+	unsigned long mask;
+	unsigned long res;
+	char *msg;
+	int (*action)(struct page *p, unsigned long pfn);
+} error_states[] = {
+	{ reserved,	reserved,	"reserved kernel",	me_ignore },
+	{ buddy,	buddy,		"free kernel",	me_free },
+
+	/*
+	 * Could in theory check if slab page is free or if we can drop
+	 * currently unused objects without touching them. But just
+	 * treat it as standard kernel for now.
+	 */
+	{ slab,		slab,		"kernel slab",	me_kernel },
+
+#ifdef CONFIG_PAGEFLAGS_EXTENDED
+	{ head,		head,		"huge",		me_huge_page },
+	{ tail,		tail,		"huge",		me_huge_page },
+#else
+	{ compound,	compound,	"huge",		me_huge_page },
+#endif
+
+	{ sc|dirty,	sc|dirty,	"swapcache",	me_swapcache_dirty },
+	{ sc|dirty,	sc,		"swapcache",	me_swapcache_clean },
+
+	{ unevict|dirty, unevict|dirty,	"unevictable LRU", me_pagecache_dirty},
+	{ unevict,	unevict,	"unevictable LRU", me_pagecache_clean},
+
+#ifdef CONFIG_HAVE_MLOCKED_PAGE_BIT
+	{ mlock|dirty,	mlock|dirty,	"mlocked LRU",	me_pagecache_dirty },
+	{ mlock,	mlock,		"mlocked LRU",	me_pagecache_clean },
+#endif
+
+	{ lru|dirty,	lru|dirty,	"LRU",		me_pagecache_dirty },
+	{ lru|dirty,	lru,		"clean LRU",	me_pagecache_clean },
+	{ swapbacked,	swapbacked,	"anonymous",	me_pagecache_clean },
+
+	/*
+	 * Catchall entry: must be at end.
+	 */
+	{ 0,		0,		"unknown page state",	me_unknown },
+};
+
+#undef lru
+
+static void action_result(unsigned long pfn, char *msg, int result)
+{
+	struct page *page = NULL;
+	if (pfn_valid(pfn))
+		page = pfn_to_page(pfn);
+
+	printk(KERN_ERR "MCE %#lx: %s%s page recovery: %s\n",
+		pfn,
+		page && PageDirty(page) ? "dirty " : "",
+		msg, action_name[result]);
+}
+
+static int page_action(struct page_state *ps, struct page *p,
+			unsigned long pfn, int ref)
+{
+	int result;
+
+	result = ps->action(p, pfn);
+	action_result(pfn, ps->msg, result);
+	if (page_count(p) != 1 + ref)
+		printk(KERN_ERR
+		       "MCE %#lx: %s page still referenced by %d users\n",
+		       pfn, ps->msg, page_count(p) - 1);
+
+	/* Could do more checks here if page looks ok */
+	/*
+	 * Could adjust zone counters here to correct for the missing page.
+	 */
+
+	return result == RECOVERED ? 0 : -EBUSY;
+}
+
+#define N_UNMAP_TRIES 5
+
+/*
+ * Do all that is necessary to remove user space mappings. Unmap
+ * the pages and send SIGBUS to the processes if the data was dirty.
+ */
+static void hwpoison_user_mappings(struct page *p, unsigned long pfn,
+				  int trapno)
+{
+	enum ttu_flags ttu = TTU_UNMAP | TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS;
+	struct address_space *mapping;
+	LIST_HEAD(tokill);
+	int ret;
+	int i;
+	int kill = 1;
+
+	if (PageReserved(p) || PageCompound(p) || PageSlab(p))
+		return;
+
+	if (!PageLRU(p))
+		lru_add_drain_all();
+
+	/*
+	 * This check implies we don't kill processes if their pages
+	 * are in the swap cache early. Those are always late kills.
+	 */
+	if (!page_mapped(p))
+		return;
+
+	if (PageSwapCache(p)) {
+		printk(KERN_ERR
+		       "MCE %#lx: keeping poisoned page in swap cache\n", pfn);
+		ttu |= TTU_IGNORE_HWPOISON;
+	}
+
+	/*
+	 * Propagate the dirty bit from PTEs to struct page first, because we
+	 * need this to decide if we should kill or just drop the page.
+	 */
+	mapping = page_mapping(p);
+	if (!PageDirty(p) && mapping && mapping_cap_writeback_dirty(mapping)) {
+		if (page_mkclean(p)) {
+			SetPageDirty(p);
+		} else {
+			kill = 0;
+			ttu |= TTU_IGNORE_HWPOISON;
+			printk(KERN_INFO
+	"MCE %#lx: corrupted page was clean: dropped without side effects\n",
+				pfn);
+		}
+	}
+
+	/*
+	 * First collect all the processes that have the page
+	 * mapped in dirty form.  This has to be done before try_to_unmap,
+	 * because ttu takes the rmap data structures down.
+	 *
+	 * Error handling: We ignore errors here because
+	 * there's nothing that can be done.
+	 */
+	if (kill)
+		collect_procs(p, &tokill);
+
+	/*
+	 * try_to_unmap can fail temporarily due to races.
+	 * Try a few times (RED-PEN better strategy?)
+	 */
+	for (i = 0; i < N_UNMAP_TRIES; i++) {
+		ret = try_to_unmap(p, ttu);
+		if (ret == SWAP_SUCCESS)
+			break;
+		pr_debug("MCE %#lx: try_to_unmap retry needed %d\n", pfn,  ret);
+	}
+
+	if (ret != SWAP_SUCCESS)
+		printk(KERN_ERR "MCE %#lx: failed to unmap page (mapcount=%d)\n",
+				pfn, page_mapcount(p));
+
+	/*
+	 * Now that the dirty bit has been propagated to the
+	 * struct page and all unmaps done we can decide if
+	 * killing is needed or not.  Only kill when the page
+	 * was dirty, otherwise the tokill list is merely
+	 * freed.  When there was a problem unmapping earlier
+	 * use a more force-full uncatchable kill to prevent
+	 * any accesses to the poisoned memory.
+	 */
+	kill_procs_ao(&tokill, !!PageDirty(p), trapno,
+		      ret != SWAP_SUCCESS, pfn);
+}
+
+int __memory_failure(unsigned long pfn, int trapno, int ref)
+{
+	struct page_state *ps;
+	struct page *p;
+	int res;
+
+	if (!sysctl_memory_failure_recovery)
+		panic("Memory failure from trap %d on page %lx", trapno, pfn);
+
+	if (!pfn_valid(pfn)) {
+		action_result(pfn, "memory outside kernel control", IGNORED);
+		return -EIO;
+	}
+
+	p = pfn_to_page(pfn);
+	if (TestSetPageHWPoison(p)) {
+		action_result(pfn, "already hardware poisoned", IGNORED);
+		return 0;
+	}
+
+	atomic_long_add(1, &mce_bad_pages);
+
+	/*
+	 * We need/can do nothing about count=0 pages.
+	 * 1) it's a free page, and therefore in safe hand:
+	 *    prep_new_page() will be the gate keeper.
+	 * 2) it's part of a non-compound high order page.
+	 *    Implies some kernel user: cannot stop them from
+	 *    R/W the page; let's pray that the page has been
+	 *    used and will be freed some time later.
+	 * In fact it's dangerous to directly bump up page count from 0,
+	 * that may make page_freeze_refs()/page_unfreeze_refs() mismatch.
+	 */
+	if (!get_page_unless_zero(compound_head(p))) {
+		action_result(pfn, "free or high order kernel", IGNORED);
+		return PageBuddy(compound_head(p)) ? 0 : -EBUSY;
+	}
+
+	/*
+	 * Lock the page and wait for writeback to finish.
+	 * It's very difficult to mess with pages currently under IO
+	 * and in many cases impossible, so we just avoid it here.
+	 */
+	lock_page_nosync(p);
+	wait_on_page_writeback(p);
+
+	/*
+	 * Now take care of user space mappings.
+	 */
+	hwpoison_user_mappings(p, pfn, trapno);
+
+	/*
+	 * Torn down by someone else?
+	 */
+	if (PageLRU(p) && !PageSwapCache(p) && p->mapping == NULL) {
+		action_result(pfn, "already truncated LRU", IGNORED);
+		res = 0;
+		goto out;
+	}
+
+	res = -EBUSY;
+	for (ps = error_states;; ps++) {
+		if ((p->flags & ps->mask) == ps->res) {
+			res = page_action(ps, p, pfn, ref);
+			break;
+		}
+	}
+out:
+	unlock_page(p);
+	return res;
+}
+EXPORT_SYMBOL_GPL(__memory_failure);
+
+/**
+ * memory_failure - Handle memory failure of a page.
+ * @pfn: Page Number of the corrupted page
+ * @trapno: Trap number reported in the signal to user space.
+ *
+ * This function is called by the low level machine check code
+ * of an architecture when it detects hardware memory corruption
+ * of a page. It tries its best to recover, which includes
+ * dropping pages, killing processes etc.
+ *
+ * The function is primarily of use for corruptions that
+ * happen outside the current execution context (e.g. when
+ * detected by a background scrubber)
+ *
+ * Must run in process context (e.g. a work queue) with interrupts
+ * enabled and no spinlocks hold.
+ */
+void memory_failure(unsigned long pfn, int trapno)
+{
+	__memory_failure(pfn, trapno, 0);
+}
diff --git a/mm/memory.c b/mm/memory.c
index b1443ac07c0..7e91b5f9f69 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -297,7 +297,8 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		unsigned long addr = vma->vm_start;
 
 		/*
-		 * Hide vma from rmap and vmtruncate before freeing pgtables
+		 * Hide vma from rmap and truncate_pagecache before freeing
+		 * pgtables
 		 */
 		anon_vma_unlink(vma);
 		unlink_file_vma(vma);
@@ -1325,7 +1326,8 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 				if (ret & VM_FAULT_ERROR) {
 					if (ret & VM_FAULT_OOM)
 						return i ? i : -ENOMEM;
-					else if (ret & VM_FAULT_SIGBUS)
+					if (ret &
+					    (VM_FAULT_HWPOISON|VM_FAULT_SIGBUS))
 						return i ? i : -EFAULT;
 					BUG();
 				}
@@ -2407,7 +2409,7 @@ restart:
  * @mapping: the address space containing mmaps to be unmapped.
  * @holebegin: byte in first page to unmap, relative to the start of
  * the underlying file.  This will be rounded down to a PAGE_SIZE
- * boundary.  Note that this is different from vmtruncate(), which
+ * boundary.  Note that this is different from truncate_pagecache(), which
  * must keep the partial page.  In contrast, we must get rid of
  * partial pages.
  * @holelen: size of prospective hole in bytes.  This will be rounded
@@ -2458,63 +2460,6 @@ void unmap_mapping_range(struct address_space *mapping,
 }
 EXPORT_SYMBOL(unmap_mapping_range);
 
-/**
- * vmtruncate - unmap mappings "freed" by truncate() syscall
- * @inode: inode of the file used
- * @offset: file offset to start truncating
- *
- * NOTE! We have to be ready to update the memory sharing
- * between the file and the memory map for a potential last
- * incomplete page.  Ugly, but necessary.
- */
-int vmtruncate(struct inode * inode, loff_t offset)
-{
-	if (inode->i_size < offset) {
-		unsigned long limit;
-
-		limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
-		if (limit != RLIM_INFINITY && offset > limit)
-			goto out_sig;
-		if (offset > inode->i_sb->s_maxbytes)
-			goto out_big;
-		i_size_write(inode, offset);
-	} else {
-		struct address_space *mapping = inode->i_mapping;
-
-		/*
-		 * truncation of in-use swapfiles is disallowed - it would
-		 * cause subsequent swapout to scribble on the now-freed
-		 * blocks.
-		 */
-		if (IS_SWAPFILE(inode))
-			return -ETXTBSY;
-		i_size_write(inode, offset);
-
-		/*
-		 * unmap_mapping_range is called twice, first simply for
-		 * efficiency so that truncate_inode_pages does fewer
-		 * single-page unmaps.  However after this first call, and
-		 * before truncate_inode_pages finishes, it is possible for
-		 * private pages to be COWed, which remain after
-		 * truncate_inode_pages finishes, hence the second
-		 * unmap_mapping_range call must be made for correctness.
-		 */
-		unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
-		truncate_inode_pages(mapping, offset);
-		unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
-	}
-
-	if (inode->i_op->truncate)
-		inode->i_op->truncate(inode);
-	return 0;
-
-out_sig:
-	send_sig(SIGXFSZ, current, 0);
-out_big:
-	return -EFBIG;
-}
-EXPORT_SYMBOL(vmtruncate);
-
 int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end)
 {
 	struct address_space *mapping = inode->i_mapping;
@@ -2559,8 +2504,15 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto out;
 
 	entry = pte_to_swp_entry(orig_pte);
-	if (is_migration_entry(entry)) {
-		migration_entry_wait(mm, pmd, address);
+	if (unlikely(non_swap_entry(entry))) {
+		if (is_migration_entry(entry)) {
+			migration_entry_wait(mm, pmd, address);
+		} else if (is_hwpoison_entry(entry)) {
+			ret = VM_FAULT_HWPOISON;
+		} else {
+			print_bad_pte(vma, address, orig_pte, NULL);
+			ret = VM_FAULT_OOM;
+		}
 		goto out;
 	}
 	delayacct_set_flag(DELAYACCT_PF_SWAPIN);
@@ -2584,6 +2536,10 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		/* Had to read the page from swap area: Major fault */
 		ret = VM_FAULT_MAJOR;
 		count_vm_event(PGMAJFAULT);
+	} else if (PageHWPoison(page)) {
+		ret = VM_FAULT_HWPOISON;
+		delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
+		goto out;
 	}
 
 	lock_page(page);
@@ -2760,6 +2716,12 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))
 		return ret;
 
+	if (unlikely(PageHWPoison(vmf.page))) {
+		if (ret & VM_FAULT_LOCKED)
+			unlock_page(vmf.page);
+		return VM_FAULT_HWPOISON;
+	}
+
 	/*
 	 * For consistency in subsequent calls, make the faulted page always
 	 * locked.
diff --git a/mm/migrate.c b/mm/migrate.c
index 16052e80aaa..1a4bf481378 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -675,7 +675,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
 	}
 
 	/* Establish migration ptes or remove ptes */
-	try_to_unmap(page, 1);
+	try_to_unmap(page, TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS);
 
 skip_unmap:
 	if (!page_mapped(page))
diff --git a/mm/mremap.c b/mm/mremap.c
index 20a07dba6be..97bff254771 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -86,8 +86,8 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 	if (vma->vm_file) {
 		/*
 		 * Subtle point from Rajesh Venkatasubramanian: before
-		 * moving file-based ptes, we must lock vmtruncate out,
-		 * since it might clean the dst vma before the src vma,
+		 * moving file-based ptes, we must lock truncate_pagecache
+		 * out, since it might clean the dst vma before the src vma,
 		 * and we propagate stale pages into the dst afterward.
 		 */
 		mapping = vma->vm_file->f_mapping;
diff --git a/mm/nommu.c b/mm/nommu.c
index 8d484241d03..c73aa4753d7 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -83,46 +83,6 @@ struct vm_operations_struct generic_file_vm_ops = {
 };
 
 /*
- * Handle all mappings that got truncated by a "truncate()"
- * system call.
- *
- * NOTE! We have to be ready to update the memory sharing
- * between the file and the memory map for a potential last
- * incomplete page.  Ugly, but necessary.
- */
-int vmtruncate(struct inode *inode, loff_t offset)
-{
-	struct address_space *mapping = inode->i_mapping;
-	unsigned long limit;
-
-	if (inode->i_size < offset)
-		goto do_expand;
-	i_size_write(inode, offset);
-
-	truncate_inode_pages(mapping, offset);
-	goto out_truncate;
-
-do_expand:
-	limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
-	if (limit != RLIM_INFINITY && offset > limit)
-		goto out_sig;
-	if (offset > inode->i_sb->s_maxbytes)
-		goto out;
-	i_size_write(inode, offset);
-
-out_truncate:
-	if (inode->i_op->truncate)
-		inode->i_op->truncate(inode);
-	return 0;
-out_sig:
-	send_sig(SIGXFSZ, current, 0);
-out:
-	return -EFBIG;
-}
-
-EXPORT_SYMBOL(vmtruncate);
-
-/*
  * Return the total memory allocated for this pointer, not
  * just what the caller asked for.
  *
@@ -866,7 +826,7 @@ static int validate_mmap_request(struct file *file,
 	int ret;
 
 	/* do the simple checks first */
-	if (flags & MAP_FIXED || addr) {
+	if (flags & MAP_FIXED) {
 		printk(KERN_DEBUG
 		       "%d: Can't do fixed-address/overlay mmap of RAM\n",
 		       current->pid);
@@ -1074,7 +1034,7 @@ static int do_mmap_shared_file(struct vm_area_struct *vma)
 	ret = vma->vm_file->f_op->mmap(vma->vm_file, vma);
 	if (ret == 0) {
 		vma->vm_region->vm_top = vma->vm_region->vm_end;
-		return ret;
+		return 0;
 	}
 	if (ret != -ENOSYS)
 		return ret;
@@ -1091,7 +1051,8 @@ static int do_mmap_shared_file(struct vm_area_struct *vma)
  */
 static int do_mmap_private(struct vm_area_struct *vma,
 			   struct vm_region *region,
-			   unsigned long len)
+			   unsigned long len,
+			   unsigned long capabilities)
 {
 	struct page *pages;
 	unsigned long total, point, n, rlen;
@@ -1102,13 +1063,13 @@ static int do_mmap_private(struct vm_area_struct *vma,
 	 * shared mappings on devices or memory
 	 * - VM_MAYSHARE will be set if it may attempt to share
 	 */
-	if (vma->vm_file) {
+	if (capabilities & BDI_CAP_MAP_DIRECT) {
 		ret = vma->vm_file->f_op->mmap(vma->vm_file, vma);
 		if (ret == 0) {
 			/* shouldn't return success if we're not sharing */
 			BUG_ON(!(vma->vm_flags & VM_MAYSHARE));
 			vma->vm_region->vm_top = vma->vm_region->vm_end;
-			return ret;
+			return 0;
 		}
 		if (ret != -ENOSYS)
 			return ret;
@@ -1221,9 +1182,6 @@ unsigned long do_mmap_pgoff(struct file *file,
 
 	kenter(",%lx,%lx,%lx,%lx,%lx", addr, len, prot, flags, pgoff);
 
-	if (!(flags & MAP_FIXED))
-		addr = round_hint_to_min(addr);
-
 	/* decide whether we should attempt the mapping, and if so what sort of
 	 * mapping */
 	ret = validate_mmap_request(file, addr, len, prot, flags, pgoff,
@@ -1233,6 +1191,9 @@ unsigned long do_mmap_pgoff(struct file *file,
 		return ret;
 	}
 
+	/* we ignore the address hint */
+	addr = 0;
+
 	/* we've determined that we can make the mapping, now translate what we
 	 * now know into VMA flags */
 	vm_flags = determine_vm_flags(file, prot, flags, capabilities);
@@ -1346,7 +1307,7 @@ unsigned long do_mmap_pgoff(struct file *file,
 		 * - this is the hook for quasi-memory character devices to
 		 *   tell us the location of a shared mapping
 		 */
-		if (file && file->f_op->get_unmapped_area) {
+		if (capabilities & BDI_CAP_MAP_DIRECT) {
 			addr = file->f_op->get_unmapped_area(file, addr, len,
 							     pgoff, flags);
 			if (IS_ERR((void *) addr)) {
@@ -1370,15 +1331,17 @@ unsigned long do_mmap_pgoff(struct file *file,
 	}
 
 	vma->vm_region = region;
-	add_nommu_region(region);
 
-	/* set up the mapping */
+	/* set up the mapping
+	 * - the region is filled in if BDI_CAP_MAP_DIRECT is still set
+	 */
 	if (file && vma->vm_flags & VM_SHARED)
 		ret = do_mmap_shared_file(vma);
 	else
-		ret = do_mmap_private(vma, region, len);
+		ret = do_mmap_private(vma, region, len, capabilities);
 	if (ret < 0)
-		goto error_put_region;
+		goto error_just_free;
+	add_nommu_region(region);
 
 	/* okay... we have a mapping; now we have to register it */
 	result = vma->vm_start;
@@ -1396,19 +1359,6 @@ share:
 	kleave(" = %lx", result);
 	return result;
 
-error_put_region:
-	__put_nommu_region(region);
-	if (vma) {
-		if (vma->vm_file) {
-			fput(vma->vm_file);
-			if (vma->vm_flags & VM_EXECUTABLE)
-				removed_exe_file_vma(vma->vm_mm);
-		}
-		kmem_cache_free(vm_area_cachep, vma);
-	}
-	kleave(" = %d [pr]", ret);
-	return ret;
-
 error_just_free:
 	up_write(&nommu_region_sem);
 error:
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 5f378dd5880..d99664e8607 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -155,37 +155,37 @@ static void update_completion_period(void)
 }
 
 int dirty_background_ratio_handler(struct ctl_table *table, int write,
-		struct file *filp, void __user *buffer, size_t *lenp,
+		void __user *buffer, size_t *lenp,
 		loff_t *ppos)
 {
 	int ret;
 
-	ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	if (ret == 0 && write)
 		dirty_background_bytes = 0;
 	return ret;
 }
 
 int dirty_background_bytes_handler(struct ctl_table *table, int write,
-		struct file *filp, void __user *buffer, size_t *lenp,
+		void __user *buffer, size_t *lenp,
 		loff_t *ppos)
 {
 	int ret;
 
-	ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos);
+	ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
 	if (ret == 0 && write)
 		dirty_background_ratio = 0;
 	return ret;
 }
 
 int dirty_ratio_handler(struct ctl_table *table, int write,
-		struct file *filp, void __user *buffer, size_t *lenp,
+		void __user *buffer, size_t *lenp,
 		loff_t *ppos)
 {
 	int old_ratio = vm_dirty_ratio;
 	int ret;
 
-	ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	if (ret == 0 && write && vm_dirty_ratio != old_ratio) {
 		update_completion_period();
 		vm_dirty_bytes = 0;
@@ -195,13 +195,13 @@ int dirty_ratio_handler(struct ctl_table *table, int write,
 
 
 int dirty_bytes_handler(struct ctl_table *table, int write,
-		struct file *filp, void __user *buffer, size_t *lenp,
+		void __user *buffer, size_t *lenp,
 		loff_t *ppos)
 {
 	unsigned long old_bytes = vm_dirty_bytes;
 	int ret;
 
-	ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos);
+	ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
 	if (ret == 0 && write && vm_dirty_bytes != old_bytes) {
 		update_completion_period();
 		vm_dirty_ratio = 0;
@@ -686,9 +686,9 @@ static DEFINE_TIMER(laptop_mode_wb_timer, laptop_timer_fn, 0, 0);
  * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs
  */
 int dirty_writeback_centisecs_handler(ctl_table *table, int write,
-	struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+	void __user *buffer, size_t *length, loff_t *ppos)
 {
-	proc_dointvec(table, write, file, buffer, length, ppos);
+	proc_dointvec(table, write, buffer, length, ppos);
 	return 0;
 }
 
@@ -1149,6 +1149,13 @@ int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page)
 EXPORT_SYMBOL(redirty_page_for_writepage);
 
 /*
+ * Dirty a page.
+ *
+ * For pages with a mapping this should be done under the page lock
+ * for the benefit of asynchronous memory errors who prefer a consistent
+ * dirty state. This rule can be broken in some special cases,
+ * but should be better not to.
+ *
  * If the mapping doesn't provide a set_page_dirty a_op, then
  * just fall through and assume that it wants buffer_heads.
  */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 5717f27a070..bf720550b44 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -234,6 +234,12 @@ static void bad_page(struct page *page)
 	static unsigned long nr_shown;
 	static unsigned long nr_unshown;
 
+	/* Don't complain about poisoned pages */
+	if (PageHWPoison(page)) {
+		__ClearPageBuddy(page);
+		return;
+	}
+
 	/*
 	 * Allow a burst of 60 reports, then keep quiet for that minute;
 	 * or allow a steady drip of one report per second.
@@ -666,7 +672,7 @@ static inline void expand(struct zone *zone, struct page *page,
 /*
  * This page is about to be returned from the page allocator
  */
-static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
+static inline int check_new_page(struct page *page)
 {
 	if (unlikely(page_mapcount(page) |
 		(page->mapping != NULL)  |
@@ -675,6 +681,18 @@ static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
 		bad_page(page);
 		return 1;
 	}
+	return 0;
+}
+
+static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
+{
+	int i;
+
+	for (i = 0; i < (1 << order); i++) {
+		struct page *p = page + i;
+		if (unlikely(check_new_page(p)))
+			return 1;
+	}
 
 	set_page_private(page, 0);
 	set_page_refcounted(page);
@@ -2373,7 +2391,7 @@ early_param("numa_zonelist_order", setup_numa_zonelist_order);
  * sysctl handler for numa_zonelist_order
  */
 int numa_zonelist_order_handler(ctl_table *table, int write,
-		struct file *file, void __user *buffer, size_t *length,
+		void __user *buffer, size_t *length,
 		loff_t *ppos)
 {
 	char saved_string[NUMA_ZONELIST_ORDER_LEN];
@@ -2382,7 +2400,7 @@ int numa_zonelist_order_handler(ctl_table *table, int write,
 	if (write)
 		strncpy(saved_string, (char*)table->data,
 			NUMA_ZONELIST_ORDER_LEN);
-	ret = proc_dostring(table, write, file, buffer, length, ppos);
+	ret = proc_dostring(table, write, buffer, length, ppos);
 	if (ret)
 		return ret;
 	if (write) {
@@ -4706,9 +4724,9 @@ module_init(init_per_zone_wmark_min)
  *	changes.
  */
 int min_free_kbytes_sysctl_handler(ctl_table *table, int write, 
-	struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+	void __user *buffer, size_t *length, loff_t *ppos)
 {
-	proc_dointvec(table, write, file, buffer, length, ppos);
+	proc_dointvec(table, write, buffer, length, ppos);
 	if (write)
 		setup_per_zone_wmarks();
 	return 0;
@@ -4716,12 +4734,12 @@ int min_free_kbytes_sysctl_handler(ctl_table *table, int write,
 
 #ifdef CONFIG_NUMA
 int sysctl_min_unmapped_ratio_sysctl_handler(ctl_table *table, int write,
-	struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+	void __user *buffer, size_t *length, loff_t *ppos)
 {
 	struct zone *zone;
 	int rc;
 
-	rc = proc_dointvec_minmax(table, write, file, buffer, length, ppos);
+	rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
 	if (rc)
 		return rc;
 
@@ -4732,12 +4750,12 @@ int sysctl_min_unmapped_ratio_sysctl_handler(ctl_table *table, int write,
 }
 
 int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write,
-	struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+	void __user *buffer, size_t *length, loff_t *ppos)
 {
 	struct zone *zone;
 	int rc;
 
-	rc = proc_dointvec_minmax(table, write, file, buffer, length, ppos);
+	rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
 	if (rc)
 		return rc;
 
@@ -4758,9 +4776,9 @@ int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write,
  * if in function of the boot time zone sizes.
  */
 int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write,
-	struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+	void __user *buffer, size_t *length, loff_t *ppos)
 {
-	proc_dointvec_minmax(table, write, file, buffer, length, ppos);
+	proc_dointvec_minmax(table, write, buffer, length, ppos);
 	setup_per_zone_lowmem_reserve();
 	return 0;
 }
@@ -4772,13 +4790,13 @@ int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write,
  */
 
 int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write,
-	struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+	void __user *buffer, size_t *length, loff_t *ppos)
 {
 	struct zone *zone;
 	unsigned int cpu;
 	int ret;
 
-	ret = proc_dointvec_minmax(table, write, file, buffer, length, ppos);
+	ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
 	if (!write || (ret == -EINVAL))
 		return ret;
 	for_each_populated_zone(zone) {
diff --git a/mm/rmap.c b/mm/rmap.c
index 720fc03a7bc..28aafe2b530 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -36,6 +36,11 @@
  *                 mapping->tree_lock (widely used, in set_page_dirty,
  *                           in arch-dependent flush_dcache_mmap_lock,
  *                           within inode_lock in __sync_single_inode)
+ *
+ * (code doesn't rely on that order so it could be switched around)
+ * ->tasklist_lock
+ *   anon_vma->lock      (memory_failure, collect_procs_anon)
+ *     pte map lock
  */
 
 #include <linux/mm.h>
@@ -191,7 +196,7 @@ void __init anon_vma_init(void)
  * Getting a lock on a stable anon_vma from a page off the LRU is
  * tricky: page_lock_anon_vma rely on RCU to guard against the races.
  */
-static struct anon_vma *page_lock_anon_vma(struct page *page)
+struct anon_vma *page_lock_anon_vma(struct page *page)
 {
 	struct anon_vma *anon_vma;
 	unsigned long anon_mapping;
@@ -211,7 +216,7 @@ out:
 	return NULL;
 }
 
-static void page_unlock_anon_vma(struct anon_vma *anon_vma)
+void page_unlock_anon_vma(struct anon_vma *anon_vma)
 {
 	spin_unlock(&anon_vma->lock);
 	rcu_read_unlock();
@@ -311,7 +316,7 @@ pte_t *page_check_address(struct page *page, struct mm_struct *mm,
  * if the page is not mapped into the page tables of this VMA.  Only
  * valid for normal file or anonymous VMAs.
  */
-static int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma)
+int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma)
 {
 	unsigned long address;
 	pte_t *pte;
@@ -756,7 +761,7 @@ void page_remove_rmap(struct page *page)
  * repeatedly from either try_to_unmap_anon or try_to_unmap_file.
  */
 static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
-				int migration)
+				enum ttu_flags flags)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long address;
@@ -778,11 +783,13 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 	 * If it's recently referenced (perhaps page_referenced
 	 * skipped over this mm) then we should reactivate it.
 	 */
-	if (!migration) {
+	if (!(flags & TTU_IGNORE_MLOCK)) {
 		if (vma->vm_flags & VM_LOCKED) {
 			ret = SWAP_MLOCK;
 			goto out_unmap;
 		}
+	}
+	if (!(flags & TTU_IGNORE_ACCESS)) {
 		if (ptep_clear_flush_young_notify(vma, address, pte)) {
 			ret = SWAP_FAIL;
 			goto out_unmap;
@@ -800,7 +807,14 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 	/* Update high watermark before we lower rss */
 	update_hiwater_rss(mm);
 
-	if (PageAnon(page)) {
+	if (PageHWPoison(page) && !(flags & TTU_IGNORE_HWPOISON)) {
+		if (PageAnon(page))
+			dec_mm_counter(mm, anon_rss);
+		else
+			dec_mm_counter(mm, file_rss);
+		set_pte_at(mm, address, pte,
+				swp_entry_to_pte(make_hwpoison_entry(page)));
+	} else if (PageAnon(page)) {
 		swp_entry_t entry = { .val = page_private(page) };
 
 		if (PageSwapCache(page)) {
@@ -822,12 +836,12 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			 * pte. do_swap_page() will wait until the migration
 			 * pte is removed and then restart fault handling.
 			 */
-			BUG_ON(!migration);
+			BUG_ON(TTU_ACTION(flags) != TTU_MIGRATION);
 			entry = make_migration_entry(page, pte_write(pteval));
 		}
 		set_pte_at(mm, address, pte, swp_entry_to_pte(entry));
 		BUG_ON(pte_file(*pte));
-	} else if (PAGE_MIGRATION && migration) {
+	} else if (PAGE_MIGRATION && (TTU_ACTION(flags) == TTU_MIGRATION)) {
 		/* Establish migration entry for a file page */
 		swp_entry_t entry;
 		entry = make_migration_entry(page, pte_write(pteval));
@@ -996,12 +1010,13 @@ static int try_to_mlock_page(struct page *page, struct vm_area_struct *vma)
  * vm_flags for that VMA.  That should be OK, because that vma shouldn't be
  * 'LOCKED.
  */
-static int try_to_unmap_anon(struct page *page, int unlock, int migration)
+static int try_to_unmap_anon(struct page *page, enum ttu_flags flags)
 {
 	struct anon_vma *anon_vma;
 	struct vm_area_struct *vma;
 	unsigned int mlocked = 0;
 	int ret = SWAP_AGAIN;
+	int unlock = TTU_ACTION(flags) == TTU_MUNLOCK;
 
 	if (MLOCK_PAGES && unlikely(unlock))
 		ret = SWAP_SUCCESS;	/* default for try_to_munlock() */
@@ -1017,7 +1032,7 @@ static int try_to_unmap_anon(struct page *page, int unlock, int migration)
 				continue;  /* must visit all unlocked vmas */
 			ret = SWAP_MLOCK;  /* saw at least one mlocked vma */
 		} else {
-			ret = try_to_unmap_one(page, vma, migration);
+			ret = try_to_unmap_one(page, vma, flags);
 			if (ret == SWAP_FAIL || !page_mapped(page))
 				break;
 		}
@@ -1041,8 +1056,7 @@ static int try_to_unmap_anon(struct page *page, int unlock, int migration)
 /**
  * try_to_unmap_file - unmap/unlock file page using the object-based rmap method
  * @page: the page to unmap/unlock
- * @unlock:  request for unlock rather than unmap [unlikely]
- * @migration:  unmapping for migration - ignored if @unlock
+ * @flags: action and flags
  *
  * Find all the mappings of a page using the mapping pointer and the vma chains
  * contained in the address_space struct it points to.
@@ -1054,7 +1068,7 @@ static int try_to_unmap_anon(struct page *page, int unlock, int migration)
  * vm_flags for that VMA.  That should be OK, because that vma shouldn't be
  * 'LOCKED.
  */
-static int try_to_unmap_file(struct page *page, int unlock, int migration)
+static int try_to_unmap_file(struct page *page, enum ttu_flags flags)
 {
 	struct address_space *mapping = page->mapping;
 	pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
@@ -1066,6 +1080,7 @@ static int try_to_unmap_file(struct page *page, int unlock, int migration)
 	unsigned long max_nl_size = 0;
 	unsigned int mapcount;
 	unsigned int mlocked = 0;
+	int unlock = TTU_ACTION(flags) == TTU_MUNLOCK;
 
 	if (MLOCK_PAGES && unlikely(unlock))
 		ret = SWAP_SUCCESS;	/* default for try_to_munlock() */
@@ -1078,7 +1093,7 @@ static int try_to_unmap_file(struct page *page, int unlock, int migration)
 				continue;	/* must visit all vmas */
 			ret = SWAP_MLOCK;
 		} else {
-			ret = try_to_unmap_one(page, vma, migration);
+			ret = try_to_unmap_one(page, vma, flags);
 			if (ret == SWAP_FAIL || !page_mapped(page))
 				goto out;
 		}
@@ -1103,7 +1118,8 @@ static int try_to_unmap_file(struct page *page, int unlock, int migration)
 			ret = SWAP_MLOCK;	/* leave mlocked == 0 */
 			goto out;		/* no need to look further */
 		}
-		if (!MLOCK_PAGES && !migration && (vma->vm_flags & VM_LOCKED))
+		if (!MLOCK_PAGES && !(flags & TTU_IGNORE_MLOCK) &&
+			(vma->vm_flags & VM_LOCKED))
 			continue;
 		cursor = (unsigned long) vma->vm_private_data;
 		if (cursor > max_nl_cursor)
@@ -1137,7 +1153,7 @@ static int try_to_unmap_file(struct page *page, int unlock, int migration)
 	do {
 		list_for_each_entry(vma, &mapping->i_mmap_nonlinear,
 						shared.vm_set.list) {
-			if (!MLOCK_PAGES && !migration &&
+			if (!MLOCK_PAGES && !(flags & TTU_IGNORE_MLOCK) &&
 			    (vma->vm_flags & VM_LOCKED))
 				continue;
 			cursor = (unsigned long) vma->vm_private_data;
@@ -1177,7 +1193,7 @@ out:
 /**
  * try_to_unmap - try to remove all page table mappings to a page
  * @page: the page to get unmapped
- * @migration: migration flag
+ * @flags: action and flags
  *
  * Tries to remove all the page table entries which are mapping this
  * page, used in the pageout path.  Caller must hold the page lock.
@@ -1188,16 +1204,16 @@ out:
  * SWAP_FAIL	- the page is unswappable
  * SWAP_MLOCK	- page is mlocked.
  */
-int try_to_unmap(struct page *page, int migration)
+int try_to_unmap(struct page *page, enum ttu_flags flags)
 {
 	int ret;
 
 	BUG_ON(!PageLocked(page));
 
 	if (PageAnon(page))
-		ret = try_to_unmap_anon(page, 0, migration);
+		ret = try_to_unmap_anon(page, flags);
 	else
-		ret = try_to_unmap_file(page, 0, migration);
+		ret = try_to_unmap_file(page, flags);
 	if (ret != SWAP_MLOCK && !page_mapped(page))
 		ret = SWAP_SUCCESS;
 	return ret;
@@ -1222,8 +1238,8 @@ int try_to_munlock(struct page *page)
 	VM_BUG_ON(!PageLocked(page) || PageLRU(page));
 
 	if (PageAnon(page))
-		return try_to_unmap_anon(page, 1, 0);
+		return try_to_unmap_anon(page, TTU_MUNLOCK);
 	else
-		return try_to_unmap_file(page, 1, 0);
+		return try_to_unmap_file(page, TTU_MUNLOCK);
 }
 
diff --git a/mm/shmem.c b/mm/shmem.c
index b206a7a32e2..98631c26c20 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1633,8 +1633,8 @@ shmem_write_end(struct file *file, struct address_space *mapping,
 	if (pos + copied > inode->i_size)
 		i_size_write(inode, pos + copied);
 
-	unlock_page(page);
 	set_page_dirty(page);
+	unlock_page(page);
 	page_cache_release(page);
 
 	return copied;
@@ -1971,13 +1971,13 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s
 			iput(inode);
 			return error;
 		}
-		unlock_page(page);
 		inode->i_mapping->a_ops = &shmem_aops;
 		inode->i_op = &shmem_symlink_inode_operations;
 		kaddr = kmap_atomic(page, KM_USER0);
 		memcpy(kaddr, symname, len);
 		kunmap_atomic(kaddr, KM_USER0);
 		set_page_dirty(page);
+		unlock_page(page);
 		page_cache_release(page);
 	}
 	if (dir->i_mode & S_ISGID)
@@ -2420,6 +2420,7 @@ static const struct address_space_operations shmem_aops = {
 	.write_end	= shmem_write_end,
 #endif
 	.migratepage	= migrate_page,
+	.error_remove_page = generic_error_remove_page,
 };
 
 static const struct file_operations shmem_file_operations = {
diff --git a/mm/swapfile.c b/mm/swapfile.c
index f1bf19daadc..4de7f02f820 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -699,7 +699,7 @@ int free_swap_and_cache(swp_entry_t entry)
 	struct swap_info_struct *p;
 	struct page *page = NULL;
 
-	if (is_migration_entry(entry))
+	if (non_swap_entry(entry))
 		return 1;
 
 	p = swap_info_get(entry);
@@ -2085,7 +2085,7 @@ static int __swap_duplicate(swp_entry_t entry, bool cache)
 	int count;
 	bool has_cache;
 
-	if (is_migration_entry(entry))
+	if (non_swap_entry(entry))
 		return -EINVAL;
 
 	type = swp_type(entry);
diff --git a/mm/truncate.c b/mm/truncate.c
index ccc3ecf7cb9..450cebdabfc 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -93,11 +93,11 @@ EXPORT_SYMBOL(cancel_dirty_page);
  * its lock, b) when a concurrent invalidate_mapping_pages got there first and
  * c) when tmpfs swizzles a page between a tmpfs inode and swapper_space.
  */
-static void
+static int
 truncate_complete_page(struct address_space *mapping, struct page *page)
 {
 	if (page->mapping != mapping)
-		return;
+		return -EIO;
 
 	if (page_has_private(page))
 		do_invalidatepage(page, 0);
@@ -108,6 +108,7 @@ truncate_complete_page(struct address_space *mapping, struct page *page)
 	remove_from_page_cache(page);
 	ClearPageMappedToDisk(page);
 	page_cache_release(page);	/* pagecache ref */
+	return 0;
 }
 
 /*
@@ -135,6 +136,51 @@ invalidate_complete_page(struct address_space *mapping, struct page *page)
 	return ret;
 }
 
+int truncate_inode_page(struct address_space *mapping, struct page *page)
+{
+	if (page_mapped(page)) {
+		unmap_mapping_range(mapping,
+				   (loff_t)page->index << PAGE_CACHE_SHIFT,
+				   PAGE_CACHE_SIZE, 0);
+	}
+	return truncate_complete_page(mapping, page);
+}
+
+/*
+ * Used to get rid of pages on hardware memory corruption.
+ */
+int generic_error_remove_page(struct address_space *mapping, struct page *page)
+{
+	if (!mapping)
+		return -EINVAL;
+	/*
+	 * Only punch for normal data pages for now.
+	 * Handling other types like directories would need more auditing.
+	 */
+	if (!S_ISREG(mapping->host->i_mode))
+		return -EIO;
+	return truncate_inode_page(mapping, page);
+}
+EXPORT_SYMBOL(generic_error_remove_page);
+
+/*
+ * Safely invalidate one page from its pagecache mapping.
+ * It only drops clean, unused pages. The page must be locked.
+ *
+ * Returns 1 if the page is successfully invalidated, otherwise 0.
+ */
+int invalidate_inode_page(struct page *page)
+{
+	struct address_space *mapping = page_mapping(page);
+	if (!mapping)
+		return 0;
+	if (PageDirty(page) || PageWriteback(page))
+		return 0;
+	if (page_mapped(page))
+		return 0;
+	return invalidate_complete_page(mapping, page);
+}
+
 /**
  * truncate_inode_pages - truncate range of pages specified by start & end byte offsets
  * @mapping: mapping to truncate
@@ -196,12 +242,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
 				unlock_page(page);
 				continue;
 			}
-			if (page_mapped(page)) {
-				unmap_mapping_range(mapping,
-				  (loff_t)page_index<<PAGE_CACHE_SHIFT,
-				  PAGE_CACHE_SIZE, 0);
-			}
-			truncate_complete_page(mapping, page);
+			truncate_inode_page(mapping, page);
 			unlock_page(page);
 		}
 		pagevec_release(&pvec);
@@ -238,15 +279,10 @@ void truncate_inode_pages_range(struct address_space *mapping,
 				break;
 			lock_page(page);
 			wait_on_page_writeback(page);
-			if (page_mapped(page)) {
-				unmap_mapping_range(mapping,
-				  (loff_t)page->index<<PAGE_CACHE_SHIFT,
-				  PAGE_CACHE_SIZE, 0);
-			}
+			truncate_inode_page(mapping, page);
 			if (page->index > next)
 				next = page->index;
 			next++;
-			truncate_complete_page(mapping, page);
 			unlock_page(page);
 		}
 		pagevec_release(&pvec);
@@ -311,12 +347,8 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
 			if (lock_failed)
 				continue;
 
-			if (PageDirty(page) || PageWriteback(page))
-				goto unlock;
-			if (page_mapped(page))
-				goto unlock;
-			ret += invalidate_complete_page(mapping, page);
-unlock:
+			ret += invalidate_inode_page(page);
+
 			unlock_page(page);
 			if (next > end)
 				break;
@@ -465,3 +497,67 @@ int invalidate_inode_pages2(struct address_space *mapping)
 	return invalidate_inode_pages2_range(mapping, 0, -1);
 }
 EXPORT_SYMBOL_GPL(invalidate_inode_pages2);
+
+/**
+ * truncate_pagecache - unmap and remove pagecache that has been truncated
+ * @inode: inode
+ * @old: old file offset
+ * @new: new file offset
+ *
+ * inode's new i_size must already be written before truncate_pagecache
+ * is called.
+ *
+ * This function should typically be called before the filesystem
+ * releases resources associated with the freed range (eg. deallocates
+ * blocks). This way, pagecache will always stay logically coherent
+ * with on-disk format, and the filesystem would not have to deal with
+ * situations such as writepage being called for a page that has already
+ * had its underlying blocks deallocated.
+ */
+void truncate_pagecache(struct inode *inode, loff_t old, loff_t new)
+{
+	if (new < old) {
+		struct address_space *mapping = inode->i_mapping;
+
+		/*
+		 * unmap_mapping_range is called twice, first simply for
+		 * efficiency so that truncate_inode_pages does fewer
+		 * single-page unmaps.  However after this first call, and
+		 * before truncate_inode_pages finishes, it is possible for
+		 * private pages to be COWed, which remain after
+		 * truncate_inode_pages finishes, hence the second
+		 * unmap_mapping_range call must be made for correctness.
+		 */
+		unmap_mapping_range(mapping, new + PAGE_SIZE - 1, 0, 1);
+		truncate_inode_pages(mapping, new);
+		unmap_mapping_range(mapping, new + PAGE_SIZE - 1, 0, 1);
+	}
+}
+EXPORT_SYMBOL(truncate_pagecache);
+
+/**
+ * vmtruncate - unmap mappings "freed" by truncate() syscall
+ * @inode: inode of the file used
+ * @offset: file offset to start truncating
+ *
+ * NOTE! We have to be ready to update the memory sharing
+ * between the file and the memory map for a potential last
+ * incomplete page.  Ugly, but necessary.
+ */
+int vmtruncate(struct inode *inode, loff_t offset)
+{
+	loff_t oldsize;
+	int error;
+
+	error = inode_newsize_ok(inode, offset);
+	if (error)
+		return error;
+	oldsize = inode->i_size;
+	i_size_write(inode, offset);
+	truncate_pagecache(inode, oldsize, offset);
+	if (inode->i_op->truncate)
+		inode->i_op->truncate(inode);
+
+	return error;
+}
+EXPORT_SYMBOL(vmtruncate);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 613e89f471d..1219ceb8a9b 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -663,7 +663,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		 * processes. Try to unmap it here.
 		 */
 		if (page_mapped(page) && mapping) {
-			switch (try_to_unmap(page, 0)) {
+			switch (try_to_unmap(page, TTU_UNMAP)) {
 			case SWAP_FAIL:
 				goto activate_locked;
 			case SWAP_AGAIN:
@@ -1836,11 +1836,45 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR
 
+unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
+						gfp_t gfp_mask, bool noswap,
+						unsigned int swappiness,
+						struct zone *zone, int nid)
+{
+	struct scan_control sc = {
+		.may_writepage = !laptop_mode,
+		.may_unmap = 1,
+		.may_swap = !noswap,
+		.swap_cluster_max = SWAP_CLUSTER_MAX,
+		.swappiness = swappiness,
+		.order = 0,
+		.mem_cgroup = mem,
+		.isolate_pages = mem_cgroup_isolate_pages,
+	};
+	nodemask_t nm  = nodemask_of_node(nid);
+
+	sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
+			(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
+	sc.nodemask = &nm;
+	sc.nr_reclaimed = 0;
+	sc.nr_scanned = 0;
+	/*
+	 * NOTE: Although we can get the priority field, using it
+	 * here is not a good idea, since it limits the pages we can scan.
+	 * if we don't reclaim here, the shrink_zone from balance_pgdat
+	 * will pick up pages from other mem cgroup's as well. We hack
+	 * the priority and make it zero.
+	 */
+	shrink_zone(0, zone, &sc);
+	return sc.nr_reclaimed;
+}
+
 unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 					   gfp_t gfp_mask,
 					   bool noswap,
 					   unsigned int swappiness)
 {
+	struct zonelist *zonelist;
 	struct scan_control sc = {
 		.may_writepage = !laptop_mode,
 		.may_unmap = 1,
@@ -1852,7 +1886,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 		.isolate_pages = mem_cgroup_isolate_pages,
 		.nodemask = NULL, /* we don't care the placement */
 	};
-	struct zonelist *zonelist;
 
 	sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
 			(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
@@ -1974,6 +2007,7 @@ loop_again:
 		for (i = 0; i <= end_zone; i++) {
 			struct zone *zone = pgdat->node_zones + i;
 			int nr_slab;
+			int nid, zid;
 
 			if (!populated_zone(zone))
 				continue;
@@ -1988,6 +2022,15 @@ loop_again:
 			temp_priority[i] = priority;
 			sc.nr_scanned = 0;
 			note_zone_scanning_priority(zone, priority);
+
+			nid = pgdat->node_id;
+			zid = zone_idx(zone);
+			/*
+			 * Call soft limit reclaim before calling shrink_zone.
+			 * For now we ignore the return value
+			 */
+			mem_cgroup_soft_limit_reclaim(zone, order, sc.gfp_mask,
+							nid, zid);
 			/*
 			 * We put equal pressure on every zone, unless one
 			 * zone has way too many pages free already.
@@ -2801,10 +2844,10 @@ static void scan_all_zones_unevictable_pages(void)
 unsigned long scan_unevictable_pages;
 
 int scan_unevictable_handler(struct ctl_table *table, int write,
-			   struct file *file, void __user *buffer,
+			   void __user *buffer,
 			   size_t *length, loff_t *ppos)
 {
-	proc_doulongvec_minmax(table, write, file, buffer, length, ppos);
+	proc_doulongvec_minmax(table, write, buffer, length, ppos);
 
 	if (write && *(unsigned long *)table->data)
 		scan_all_zones_unevictable_pages();