Merge tag 'asoc-v3.13' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound into for-next

ASoC: Updates for v3.13

 - Further work on the dmaengine helpers, including support for
   configuring the parameters for DMA by reading the capabilities of the
   DMA controller which removes some guesswork and magic numbers fromm
   drivers.
 - A refresh of the documentation.
 - Conversions of many drivers to direct regmap API usage in order to
   allow the ASoC level register I/O code to be removed, this will
   hopefully be completed by v3.14.
 - Support for using async register I/O in DAPM, reducing the time taken
   to implement power transitions on systems that support it.

22 files changed, 589 insertions, 340 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 026771a9b097..394838f489eb 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -183,7 +183,7 @@ config MEMORY_HOTPLUG_SPARSE
 config MEMORY_HOTREMOVE
 	bool "Allow for memory hot remove"
 	select MEMORY_ISOLATION
-	select HAVE_BOOTMEM_INFO_NODE if X86_64
+	select HAVE_BOOTMEM_INFO_NODE if (X86_64 || PPC64)
 	depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE
 	depends on MIGRATION
 
diff --git a/mm/bounce.c b/mm/bounce.c
index c9f0a4339a7d..5a7d58fb883b 100644
--- a/mm/bounce.c
+++ b/mm/bounce.c
@@ -204,6 +204,8 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
 	struct bio_vec *to, *from;
 	unsigned i;
 
+	if (force)
+		goto bounce;
 	bio_for_each_segment(from, *bio_orig, i)
 		if (page_to_pfn(from->bv_page) > queue_bounce_pfn(q))
 			goto bounce;
diff --git a/mm/compaction.c b/mm/compaction.c
index c43789388cd8..b5326b141a25 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -677,6 +677,13 @@ static void isolate_freepages(struct zone *zone,
 					pfn -= pageblock_nr_pages) {
 		unsigned long isolated;
 
+		/*
+		 * This can iterate a massively long zone without finding any
+		 * suitable migration targets, so periodically check if we need
+		 * to schedule.
+		 */
+		cond_resched();
+
 		if (!pfn_valid(pfn))
 			continue;
 
diff --git a/mm/filemap.c b/mm/filemap.c
index 1e6aec4a2d2e..ae4846ff4849 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1616,7 +1616,6 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	struct inode *inode = mapping->host;
 	pgoff_t offset = vmf->pgoff;
 	struct page *page;
-	bool memcg_oom;
 	pgoff_t size;
 	int ret = 0;
 
@@ -1625,11 +1624,7 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		return VM_FAULT_SIGBUS;
 
 	/*
-	 * Do we have something in the page cache already?  Either
-	 * way, try readahead, but disable the memcg OOM killer for it
-	 * as readahead is optional and no errors are propagated up
-	 * the fault stack.  The OOM killer is enabled while trying to
-	 * instantiate the faulting page individually below.
+	 * Do we have something in the page cache already?
 	 */
 	page = find_get_page(mapping, offset);
 	if (likely(page) && !(vmf->flags & FAULT_FLAG_TRIED)) {
@@ -1637,14 +1632,10 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		 * We found the page, so try async readahead before
 		 * waiting for the lock.
 		 */
-		memcg_oom = mem_cgroup_toggle_oom(false);
 		do_async_mmap_readahead(vma, ra, file, page, offset);
-		mem_cgroup_toggle_oom(memcg_oom);
 	} else if (!page) {
 		/* No page in the page cache at all */
-		memcg_oom = mem_cgroup_toggle_oom(false);
 		do_sync_mmap_readahead(vma, ra, file, offset);
-		mem_cgroup_toggle_oom(memcg_oom);
 		count_vm_event(PGMAJFAULT);
 		mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
 		ret = VM_FAULT_MAJOR;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 7489884682d8..610e3df2768a 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2697,6 +2697,7 @@ void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address,
 
 	mmun_start = haddr;
 	mmun_end   = haddr + HPAGE_PMD_SIZE;
+again:
 	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 	spin_lock(&mm->page_table_lock);
 	if (unlikely(!pmd_trans_huge(*pmd))) {
@@ -2719,7 +2720,14 @@ void __split_huge_page_pmd(struct vm_area_struct *vma, unsigned long address,
 	split_huge_page(page);
 
 	put_page(page);
-	BUG_ON(pmd_trans_huge(*pmd));
+
+	/*
+	 * We don't always have down_write of mmap_sem here: a racing
+	 * do_huge_pmd_wp_page() might have copied-on-write to another
+	 * huge page before our split_huge_page() got the anon_vma lock.
+	 */
+	if (unlikely(pmd_trans_huge(*pmd)))
+		goto again;
 }
 
 void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address,
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index b49579c7f2a5..0b7656e804d1 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -653,6 +653,7 @@ static void free_huge_page(struct page *page)
 	BUG_ON(page_count(page));
 	BUG_ON(page_mapcount(page));
 	restore_reserve = PagePrivate(page);
+	ClearPagePrivate(page);
 
 	spin_lock(&hugetlb_lock);
 	hugetlb_cgroup_uncharge_page(hstate_index(h),
@@ -695,8 +696,22 @@ static void prep_compound_gigantic_page(struct page *page, unsigned long order)
 	/* we rely on prep_new_huge_page to set the destructor */
 	set_compound_order(page, order);
 	__SetPageHead(page);
+	__ClearPageReserved(page);
 	for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
 		__SetPageTail(p);
+		/*
+		 * For gigantic hugepages allocated through bootmem at
+		 * boot, it's safer to be consistent with the not-gigantic
+		 * hugepages and clear the PG_reserved bit from all tail pages
+		 * too.  Otherwse drivers using get_user_pages() to access tail
+		 * pages may get the reference counting wrong if they see
+		 * PG_reserved set on a tail page (despite the head page not
+		 * having PG_reserved set).  Enforcing this consistency between
+		 * head and tail pages allows drivers to optimize away a check
+		 * on the head page when they need know if put_page() is needed
+		 * after get_user_pages().
+		 */
+		__ClearPageReserved(p);
 		set_page_count(p, 0);
 		p->first_page = page;
 	}
@@ -1329,9 +1344,9 @@ static void __init gather_bootmem_prealloc(void)
 #else
 		page = virt_to_page(m);
 #endif
-		__ClearPageReserved(page);
 		WARN_ON(page_count(page) != 1);
 		prep_compound_huge_page(page, h->order);
+		WARN_ON(PageReserved(page));
 		prep_new_huge_page(h, page, page_to_nid(page));
 		/*
 		 * If we had gigantic hugepages allocated at boot time, we need
diff --git a/mm/hwpoison-inject.c b/mm/hwpoison-inject.c
index afc2daa91c60..4c84678371eb 100644
--- a/mm/hwpoison-inject.c
+++ b/mm/hwpoison-inject.c
@@ -20,8 +20,6 @@ static int hwpoison_inject(void *data, u64 val)
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	if (!hwpoison_filter_enable)
-		goto inject;
 	if (!pfn_valid(pfn))
 		return -ENXIO;
 
@@ -33,6 +31,9 @@ static int hwpoison_inject(void *data, u64 val)
 	if (!get_page_unless_zero(hpage))
 		return 0;
 
+	if (!hwpoison_filter_enable)
+		goto inject;
+
 	if (!PageLRU(p) && !PageHuge(p))
 		shake_page(p, 0);
 	/*
diff --git a/mm/madvise.c b/mm/madvise.c
index 6975bc812542..539eeb96b323 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -343,10 +343,11 @@ static long madvise_remove(struct vm_area_struct *vma,
  */
 static int madvise_hwpoison(int bhv, unsigned long start, unsigned long end)
 {
+	struct page *p;
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
-	for (; start < end; start += PAGE_SIZE) {
-		struct page *p;
+	for (; start < end; start += PAGE_SIZE <<
+				compound_order(compound_head(p))) {
 		int ret;
 
 		ret = get_user_pages_fast(start, 1, 0, &p);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d5ff3ce13029..34d3ca9572d6 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -39,6 +39,7 @@
 #include <linux/limits.h>
 #include <linux/export.h>
 #include <linux/mutex.h>
+#include <linux/rbtree.h>
 #include <linux/slab.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
@@ -160,6 +161,10 @@ struct mem_cgroup_per_zone {
 
 	struct mem_cgroup_reclaim_iter reclaim_iter[DEF_PRIORITY + 1];
 
+	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	*memcg;		/* Back pointer, we cannot */
 						/* use container_of	   */
 };
@@ -168,6 +173,26 @@ struct mem_cgroup_per_node {
 	struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES];
 };
 
+/*
+ * 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;
+
 struct mem_cgroup_threshold {
 	struct eventfd_ctx *eventfd;
 	u64 threshold;
@@ -303,22 +328,6 @@ struct mem_cgroup {
 	atomic_t	numainfo_events;
 	atomic_t	numainfo_updating;
 #endif
-	/*
-	 * Protects soft_contributed transitions.
-	 * See mem_cgroup_update_soft_limit
-	 */
-	spinlock_t soft_lock;
-
-	/*
-	 * If true then this group has increased parents' children_in_excess
-	 * when it got over the soft limit.
-	 * When a group falls bellow the soft limit, parents' children_in_excess
-	 * is decreased and soft_contributed changed to false.
-	 */
-	bool soft_contributed;
-
-	/* Number of children that are in soft limit excess */
-	atomic_t children_in_excess;
 
 	struct mem_cgroup_per_node *nodeinfo[0];
 	/* WARNING: nodeinfo must be the last member here */
@@ -422,6 +431,7 @@ static bool move_file(void)
  * 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,
@@ -648,6 +658,164 @@ page_cgroup_zoneinfo(struct mem_cgroup *memcg, struct page *page)
 	return mem_cgroup_zoneinfo(memcg, 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 *memcg,
+				struct mem_cgroup_per_zone *mz,
+				struct mem_cgroup_tree_per_zone *mctz,
+				unsigned long long new_usage_in_excess)
+{
+	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 = new_usage_in_excess;
+	if (!mz->usage_in_excess)
+		return;
+	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 *memcg,
+				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_remove_exceeded(struct mem_cgroup *memcg,
+				struct mem_cgroup_per_zone *mz,
+				struct mem_cgroup_tree_per_zone *mctz)
+{
+	spin_lock(&mctz->lock);
+	__mem_cgroup_remove_exceeded(memcg, mz, mctz);
+	spin_unlock(&mctz->lock);
+}
+
+
+static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
+{
+	unsigned long long excess;
+	struct mem_cgroup_per_zone *mz;
+	struct mem_cgroup_tree_per_zone *mctz;
+	int nid = page_to_nid(page);
+	int zid = page_zonenum(page);
+	mctz = soft_limit_tree_from_page(page);
+
+	/*
+	 * Necessary to update all ancestors when hierarchy is used.
+	 * because their event counter is not touched.
+	 */
+	for (; memcg; memcg = parent_mem_cgroup(memcg)) {
+		mz = mem_cgroup_zoneinfo(memcg, nid, zid);
+		excess = res_counter_soft_limit_excess(&memcg->res);
+		/*
+		 * We have to update the tree if mz is on RB-tree or
+		 * mem is over its softlimit.
+		 */
+		if (excess || mz->on_tree) {
+			spin_lock(&mctz->lock);
+			/* if on-tree, remove it */
+			if (mz->on_tree)
+				__mem_cgroup_remove_exceeded(memcg, mz, mctz);
+			/*
+			 * Insert again. mz->usage_in_excess will be updated.
+			 * If excess is 0, no tree ops.
+			 */
+			__mem_cgroup_insert_exceeded(memcg, mz, mctz, excess);
+			spin_unlock(&mctz->lock);
+		}
+	}
+}
+
+static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg)
+{
+	int node, zone;
+	struct mem_cgroup_per_zone *mz;
+	struct mem_cgroup_tree_per_zone *mctz;
+
+	for_each_node(node) {
+		for (zone = 0; zone < MAX_NR_ZONES; zone++) {
+			mz = mem_cgroup_zoneinfo(memcg, node, zone);
+			mctz = soft_limit_tree_node_zone(node, zone);
+			mem_cgroup_remove_exceeded(memcg, mz, mctz);
+		}
+	}
+}
+
+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;
+
+retry:
+	mz = NULL;
+	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->memcg, mz, mctz);
+	if (!res_counter_soft_limit_excess(&mz->memcg->res) ||
+		!css_tryget(&mz->memcg->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;
+}
+
 /*
  * Implementation Note: reading percpu statistics for memcg.
  *
@@ -698,6 +866,7 @@ static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg,
 	unsigned long val = 0;
 	int cpu;
 
+	get_online_cpus();
 	for_each_online_cpu(cpu)
 		val += per_cpu(memcg->stat->events[idx], cpu);
 #ifdef CONFIG_HOTPLUG_CPU
@@ -705,6 +874,7 @@ static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg,
 	val += memcg->nocpu_base.events[idx];
 	spin_unlock(&memcg->pcp_counter_lock);
 #endif
+	put_online_cpus();
 	return val;
 }
 
@@ -822,48 +992,6 @@ static bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg,
 }
 
 /*
- * Called from rate-limited memcg_check_events when enough
- * MEM_CGROUP_TARGET_SOFTLIMIT events are accumulated and it makes sure
- * that all the parents up the hierarchy will be notified that this group
- * is in excess or that it is not in excess anymore. mmecg->soft_contributed
- * makes the transition a single action whenever the state flips from one to
- * the other.
- */
-static void mem_cgroup_update_soft_limit(struct mem_cgroup *memcg)
-{
-	unsigned long long excess = res_counter_soft_limit_excess(&memcg->res);
-	struct mem_cgroup *parent = memcg;
-	int delta = 0;
-
-	spin_lock(&memcg->soft_lock);
-	if (excess) {
-		if (!memcg->soft_contributed) {
-			delta = 1;
-			memcg->soft_contributed = true;
-		}
-	} else {
-		if (memcg->soft_contributed) {
-			delta = -1;
-			memcg->soft_contributed = false;
-		}
-	}
-
-	/*
-	 * Necessary to update all ancestors when hierarchy is used
-	 * because their event counter is not touched.
-	 * We track children even outside the hierarchy for the root
-	 * cgroup because tree walk starting at root should visit
-	 * all cgroups and we want to prevent from pointless tree
-	 * walk if no children is below the limit.
-	 */
-	while (delta && (parent = parent_mem_cgroup(parent)))
-		atomic_add(delta, &parent->children_in_excess);
-	if (memcg != root_mem_cgroup && !root_mem_cgroup->use_hierarchy)
-		atomic_add(delta, &root_mem_cgroup->children_in_excess);
-	spin_unlock(&memcg->soft_lock);
-}
-
-/*
  * Check events in order.
  *
  */
@@ -886,7 +1014,7 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page)
 
 		mem_cgroup_threshold(memcg);
 		if (unlikely(do_softlimit))
-			mem_cgroup_update_soft_limit(memcg);
+			mem_cgroup_update_tree(memcg, page);
 #if MAX_NUMNODES > 1
 		if (unlikely(do_numainfo))
 			atomic_inc(&memcg->numainfo_events);
@@ -929,15 +1057,6 @@ struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
 	return memcg;
 }
 
-static enum mem_cgroup_filter_t
-mem_cgroup_filter(struct mem_cgroup *memcg, struct mem_cgroup *root,
-		mem_cgroup_iter_filter cond)
-{
-	if (!cond)
-		return VISIT;
-	return cond(memcg, root);
-}
-
 /*
  * Returns a next (in a pre-order walk) alive memcg (with elevated css
  * ref. count) or NULL if the whole root's subtree has been visited.
@@ -945,7 +1064,7 @@ mem_cgroup_filter(struct mem_cgroup *memcg, struct mem_cgroup *root,
  * helper function to be used by mem_cgroup_iter
  */
 static struct mem_cgroup *__mem_cgroup_iter_next(struct mem_cgroup *root,
-		struct mem_cgroup *last_visited, mem_cgroup_iter_filter cond)
+		struct mem_cgroup *last_visited)
 {
 	struct cgroup_subsys_state *prev_css, *next_css;
 
@@ -963,31 +1082,11 @@ skip_node:
 	if (next_css) {
 		struct mem_cgroup *mem = mem_cgroup_from_css(next_css);
 
-		switch (mem_cgroup_filter(mem, root, cond)) {
-		case SKIP:
+		if (css_tryget(&mem->css))
+			return mem;
+		else {
 			prev_css = next_css;
 			goto skip_node;
-		case SKIP_TREE:
-			if (mem == root)
-				return NULL;
-			/*
-			 * css_rightmost_descendant is not an optimal way to
-			 * skip through a subtree (especially for imbalanced
-			 * trees leaning to right) but that's what we have right
-			 * now. More effective solution would be traversing
-			 * right-up for first non-NULL without calling
-			 * css_next_descendant_pre afterwards.
-			 */
-			prev_css = css_rightmost_descendant(next_css);
-			goto skip_node;
-		case VISIT:
-			if (css_tryget(&mem->css))
-				return mem;
-			else {
-				prev_css = next_css;
-				goto skip_node;
-			}
-			break;
 		}
 	}
 
@@ -1051,7 +1150,6 @@ static void mem_cgroup_iter_update(struct mem_cgroup_reclaim_iter *iter,
  * @root: hierarchy root
  * @prev: previously returned memcg, NULL on first invocation
  * @reclaim: cookie for shared reclaim walks, NULL for full walks
- * @cond: filter for visited nodes, NULL for no filter
  *
  * Returns references to children of the hierarchy below @root, or
  * @root itself, or %NULL after a full round-trip.
@@ -1064,18 +1162,15 @@ static void mem_cgroup_iter_update(struct mem_cgroup_reclaim_iter *iter,
  * divide up the memcgs in the hierarchy among all concurrent
  * reclaimers operating on the same zone and priority.
  */
-struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root,
+struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 				   struct mem_cgroup *prev,
-				   struct mem_cgroup_reclaim_cookie *reclaim,
-				   mem_cgroup_iter_filter cond)
+				   struct mem_cgroup_reclaim_cookie *reclaim)
 {
 	struct mem_cgroup *memcg = NULL;
 	struct mem_cgroup *last_visited = NULL;
 
-	if (mem_cgroup_disabled()) {
-		/* first call must return non-NULL, second return NULL */
-		return (struct mem_cgroup *)(unsigned long)!prev;
-	}
+	if (mem_cgroup_disabled())
+		return NULL;
 
 	if (!root)
 		root = root_mem_cgroup;
@@ -1086,9 +1181,7 @@ struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root,
 	if (!root->use_hierarchy && root != root_mem_cgroup) {
 		if (prev)
 			goto out_css_put;
-		if (mem_cgroup_filter(root, root, cond) == VISIT)
-			return root;
-		return NULL;
+		return root;
 	}
 
 	rcu_read_lock();
@@ -1111,7 +1204,7 @@ struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root,
 			last_visited = mem_cgroup_iter_load(iter, root, &seq);
 		}
 
-		memcg = __mem_cgroup_iter_next(root, last_visited, cond);
+		memcg = __mem_cgroup_iter_next(root, last_visited);
 
 		if (reclaim) {
 			mem_cgroup_iter_update(iter, last_visited, memcg, seq);
@@ -1122,11 +1215,7 @@ struct mem_cgroup *mem_cgroup_iter_cond(struct mem_cgroup *root,
 				reclaim->generation = iter->generation;
 		}
 
-		/*
-		 * We have finished the whole tree walk or no group has been
-		 * visited because filter told us to skip the root node.
-		 */
-		if (!memcg && (prev || (cond && !last_visited)))
+		if (prev && !memcg)
 			goto out_unlock;
 	}
 out_unlock:
@@ -1767,7 +1856,6 @@ static unsigned long mem_cgroup_reclaim(struct mem_cgroup *memcg,
 	return total;
 }
 
-#if MAX_NUMNODES > 1
 /**
  * test_mem_cgroup_node_reclaimable
  * @memcg: the target memcg
@@ -1790,6 +1878,7 @@ static bool test_mem_cgroup_node_reclaimable(struct mem_cgroup *memcg,
 	return false;
 
 }
+#if MAX_NUMNODES > 1
 
 /*
  * Always updating the nodemask is not very good - even if we have an empty
@@ -1857,50 +1946,104 @@ int mem_cgroup_select_victim_node(struct mem_cgroup *memcg)
 	return node;
 }
 
+/*
+ * Check all nodes whether it contains reclaimable pages or not.
+ * For quick scan, we make use of scan_nodes. This will allow us to skip
+ * unused nodes. But scan_nodes is lazily updated and may not cotain
+ * enough new information. We need to do double check.
+ */
+static bool mem_cgroup_reclaimable(struct mem_cgroup *memcg, bool noswap)
+{
+	int nid;
+
+	/*
+	 * quick check...making use of scan_node.
+	 * We can skip unused nodes.
+	 */
+	if (!nodes_empty(memcg->scan_nodes)) {
+		for (nid = first_node(memcg->scan_nodes);
+		     nid < MAX_NUMNODES;
+		     nid = next_node(nid, memcg->scan_nodes)) {
+
+			if (test_mem_cgroup_node_reclaimable(memcg, nid, noswap))
+				return true;
+		}
+	}
+	/*
+	 * Check rest of nodes.
+	 */
+	for_each_node_state(nid, N_MEMORY) {
+		if (node_isset(nid, memcg->scan_nodes))
+			continue;
+		if (test_mem_cgroup_node_reclaimable(memcg, nid, noswap))
+			return true;
+	}
+	return false;
+}
+
 #else
 int mem_cgroup_select_victim_node(struct mem_cgroup *memcg)
 {
 	return 0;
 }
 
-#endif
-
-/*
- * A group is eligible for the soft limit reclaim under the given root
- * hierarchy if
- *	a) it is over its soft limit
- *	b) any parent up the hierarchy is over its soft limit
- *
- * If the given group doesn't have any children over the limit then it
- * doesn't make any sense to iterate its subtree.
- */
-enum mem_cgroup_filter_t
-mem_cgroup_soft_reclaim_eligible(struct mem_cgroup *memcg,
-		struct mem_cgroup *root)
+static bool mem_cgroup_reclaimable(struct mem_cgroup *memcg, bool noswap)
 {
-	struct mem_cgroup *parent;
-
-	if (!memcg)
-		memcg = root_mem_cgroup;
-	parent = memcg;
-
-	if (res_counter_soft_limit_excess(&memcg->res))
-		return VISIT;
+	return test_mem_cgroup_node_reclaimable(memcg, 0, noswap);
+}
+#endif
 
-	/*
-	 * If any parent up to the root in the hierarchy is over its soft limit
-	 * then we have to obey and reclaim from this group as well.
-	 */
-	while ((parent = parent_mem_cgroup(parent))) {
-		if (res_counter_soft_limit_excess(&parent->res))
-			return VISIT;
-		if (parent == root)
+static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
+				   struct zone *zone,
+				   gfp_t gfp_mask,
+				   unsigned long *total_scanned)
+{
+	struct mem_cgroup *victim = NULL;
+	int total = 0;
+	int loop = 0;
+	unsigned long excess;
+	unsigned long nr_scanned;
+	struct mem_cgroup_reclaim_cookie reclaim = {
+		.zone = zone,
+		.priority = 0,
+	};
+
+	excess = res_counter_soft_limit_excess(&root_memcg->res) >> PAGE_SHIFT;
+
+	while (1) {
+		victim = mem_cgroup_iter(root_memcg, victim, &reclaim);
+		if (!victim) {
+			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 (!total)
+					break;
+				/*
+				 * We want to do more targeted 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))
+					break;
+			}
+			continue;
+		}
+		if (!mem_cgroup_reclaimable(victim, false))
+			continue;
+		total += mem_cgroup_shrink_node_zone(victim, gfp_mask, false,
+						     zone, &nr_scanned);
+		*total_scanned += nr_scanned;
+		if (!res_counter_soft_limit_excess(&root_memcg->res))
 			break;
 	}
-
-	if (!atomic_read(&memcg->children_in_excess))
-		return SKIP_TREE;
-	return SKIP;
+	mem_cgroup_iter_break(root_memcg, victim);
+	return total;
 }
 
 static DEFINE_SPINLOCK(memcg_oom_lock);
@@ -2018,110 +2161,59 @@ static void memcg_oom_recover(struct mem_cgroup *memcg)
 		memcg_wakeup_oom(memcg);
 }
 
-/*
- * try to call OOM killer
- */
 static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
 {
-	bool locked;
-	int wakeups;
-
 	if (!current->memcg_oom.may_oom)
 		return;
-
-	current->memcg_oom.in_memcg_oom = 1;
-
 	/*
-	 * As with any blocking lock, a contender needs to start
-	 * listening for wakeups before attempting the trylock,
-	 * otherwise it can miss the wakeup from the unlock and sleep
-	 * indefinitely.  This is just open-coded because our locking
-	 * is so particular to memcg hierarchies.
+	 * We are in the middle of the charge context here, so we
+	 * don't want to block when potentially sitting on a callstack
+	 * that holds all kinds of filesystem and mm locks.
+	 *
+	 * Also, the caller may handle a failed allocation gracefully
+	 * (like optional page cache readahead) and so an OOM killer
+	 * invocation might not even be necessary.
+	 *
+	 * That's why we don't do anything here except remember the
+	 * OOM context and then deal with it at the end of the page
+	 * fault when the stack is unwound, the locks are released,
+	 * and when we know whether the fault was overall successful.
 	 */
-	wakeups = atomic_read(&memcg->oom_wakeups);
-	mem_cgroup_mark_under_oom(memcg);
-
-	locked = mem_cgroup_oom_trylock(memcg);
-
-	if (locked)
-		mem_cgroup_oom_notify(memcg);
-
-	if (locked && !memcg->oom_kill_disable) {
-		mem_cgroup_unmark_under_oom(memcg);
-		mem_cgroup_out_of_memory(memcg, mask, order);
-		mem_cgroup_oom_unlock(memcg);
-		/*
-		 * There is no guarantee that an OOM-lock contender
-		 * sees the wakeups triggered by the OOM kill
-		 * uncharges.  Wake any sleepers explicitely.
-		 */
-		memcg_oom_recover(memcg);
-	} else {
-		/*
-		 * A system call can just return -ENOMEM, but if this
-		 * is a page fault and somebody else is handling the
-		 * OOM already, we need to sleep on the OOM waitqueue
-		 * for this memcg until the situation is resolved.
-		 * Which can take some time because it might be
-		 * handled by a userspace task.
-		 *
-		 * However, this is the charge context, which means
-		 * that we may sit on a large call stack and hold
-		 * various filesystem locks, the mmap_sem etc. and we
-		 * don't want the OOM handler to deadlock on them
-		 * while we sit here and wait.  Store the current OOM
-		 * context in the task_struct, then return -ENOMEM.
-		 * At the end of the page fault handler, with the
-		 * stack unwound, pagefault_out_of_memory() will check
-		 * back with us by calling
-		 * mem_cgroup_oom_synchronize(), possibly putting the
-		 * task to sleep.
-		 */
-		current->memcg_oom.oom_locked = locked;
-		current->memcg_oom.wakeups = wakeups;
-		css_get(&memcg->css);
-		current->memcg_oom.wait_on_memcg = memcg;
-	}
+	css_get(&memcg->css);
+	current->memcg_oom.memcg = memcg;
+	current->memcg_oom.gfp_mask = mask;
+	current->memcg_oom.order = order;
 }
 
 /**
  * mem_cgroup_oom_synchronize - complete memcg OOM handling
+ * @handle: actually kill/wait or just clean up the OOM state
  *
- * This has to be called at the end of a page fault if the the memcg
- * OOM handler was enabled and the fault is returning %VM_FAULT_OOM.
+ * This has to be called at the end of a page fault if the memcg OOM
+ * handler was enabled.
  *
- * Memcg supports userspace OOM handling, so failed allocations must
+ * Memcg supports userspace OOM handling where failed allocations must
  * sleep on a waitqueue until the userspace task resolves the
  * situation.  Sleeping directly in the charge context with all kinds
  * of locks held is not a good idea, instead we remember an OOM state
  * in the task and mem_cgroup_oom_synchronize() has to be called at
- * the end of the page fault to put the task to sleep and clean up the
- * OOM state.
+ * the end of the page fault to complete the OOM handling.
  *
  * Returns %true if an ongoing memcg OOM situation was detected and
- * finalized, %false otherwise.
+ * completed, %false otherwise.
  */
-bool mem_cgroup_oom_synchronize(void)
+bool mem_cgroup_oom_synchronize(bool handle)
 {
+	struct mem_cgroup *memcg = current->memcg_oom.memcg;
 	struct oom_wait_info owait;
-	struct mem_cgroup *memcg;
+	bool locked;
 
 	/* OOM is global, do not handle */
-	if (!current->memcg_oom.in_memcg_oom)
-		return false;
-
-	/*
-	 * We invoked the OOM killer but there is a chance that a kill
-	 * did not free up any charges.  Everybody else might already
-	 * be sleeping, so restart the fault and keep the rampage
-	 * going until some charges are released.
-	 */
-	memcg = current->memcg_oom.wait_on_memcg;
 	if (!memcg)
-		goto out;
+		return false;
 
-	if (test_thread_flag(TIF_MEMDIE) || fatal_signal_pending(current))
-		goto out_memcg;
+	if (!handle)
+		goto cleanup;
 
 	owait.memcg = memcg;
 	owait.wait.flags = 0;
@@ -2130,13 +2222,25 @@ bool mem_cgroup_oom_synchronize(void)
 	INIT_LIST_HEAD(&owait.wait.task_list);
 
 	prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE);
-	/* Only sleep if we didn't miss any wakeups since OOM */
-	if (atomic_read(&memcg->oom_wakeups) == current->memcg_oom.wakeups)
+	mem_cgroup_mark_under_oom(memcg);
+
+	locked = mem_cgroup_oom_trylock(memcg);
+
+	if (locked)
+		mem_cgroup_oom_notify(memcg);
+
+	if (locked && !memcg->oom_kill_disable) {
+		mem_cgroup_unmark_under_oom(memcg);
+		finish_wait(&memcg_oom_waitq, &owait.wait);
+		mem_cgroup_out_of_memory(memcg, current->memcg_oom.gfp_mask,
+					 current->memcg_oom.order);
+	} else {
 		schedule();
-	finish_wait(&memcg_oom_waitq, &owait.wait);
-out_memcg:
-	mem_cgroup_unmark_under_oom(memcg);
-	if (current->memcg_oom.oom_locked) {
+		mem_cgroup_unmark_under_oom(memcg);
+		finish_wait(&memcg_oom_waitq, &owait.wait);
+	}
+
+	if (locked) {
 		mem_cgroup_oom_unlock(memcg);
 		/*
 		 * There is no guarantee that an OOM-lock contender
@@ -2145,10 +2249,9 @@ out_memcg:
 		 */
 		memcg_oom_recover(memcg);
 	}
+cleanup:
+	current->memcg_oom.memcg = NULL;
 	css_put(&memcg->css);
-	current->memcg_oom.wait_on_memcg = NULL;
-out:
-	current->memcg_oom.in_memcg_oom = 0;
 	return true;
 }
 
@@ -2562,6 +2665,9 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
 		     || fatal_signal_pending(current)))
 		goto bypass;
 
+	if (unlikely(task_in_memcg_oom(current)))
+		goto bypass;
+
 	/*
 	 * We always charge the cgroup the mm_struct belongs to.
 	 * The mm_struct's mem_cgroup changes on task migration if the
@@ -2660,6 +2766,8 @@ done:
 	return 0;
 nomem:
 	*ptr = NULL;
+	if (gfp_mask & __GFP_NOFAIL)
+		return 0;
 	return -ENOMEM;
 bypass:
 	*ptr = root_mem_cgroup;
@@ -2812,7 +2920,9 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 	unlock_page_cgroup(pc);
 
 	/*
-	 * "charge_statistics" updated event counter.
+	 * "charge_statistics" updated event counter. Then, check it.
+	 * Insert ancestor (and ancestor's ancestors), to softlimit RB-tree.
+	 * if they exceeds softlimit.
 	 */
 	memcg_check_events(memcg, page);
 }
@@ -4647,6 +4757,98 @@ 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,
+					    unsigned long *total_scanned)
+{
+	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;
+	unsigned long long excess;
+	unsigned long nr_scanned;
+
+	if (order > 0)
+		return 0;
+
+	mctz = soft_limit_tree_node_zone(zone_to_nid(zone), zone_idx(zone));
+	/*
+	 * 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;
+
+		nr_scanned = 0;
+		reclaimed = mem_cgroup_soft_reclaim(mz->memcg, zone,
+						    gfp_mask, &nr_scanned);
+		nr_reclaimed += reclaimed;
+		*total_scanned += nr_scanned;
+		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->memcg->css);
+				else /* next_mz == NULL or other memcg */
+					break;
+			} while (1);
+		}
+		__mem_cgroup_remove_exceeded(mz->memcg, mz, mctz);
+		excess = res_counter_soft_limit_excess(&mz->memcg->res);
+		/*
+		 * 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 excess == 0, no tree ops */
+		__mem_cgroup_insert_exceeded(mz->memcg, mz, mctz, excess);
+		spin_unlock(&mctz->lock);
+		css_put(&mz->memcg->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->memcg->css);
+	return nr_reclaimed;
+}
+
 /**
  * mem_cgroup_force_empty_list - clears LRU of a group
  * @memcg: group to clear
@@ -5911,6 +6113,8 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
 	for (zone = 0; zone < MAX_NR_ZONES; zone++) {
 		mz = &pn->zoneinfo[zone];
 		lruvec_init(&mz->lruvec);
+		mz->usage_in_excess = 0;
+		mz->on_tree = false;
 		mz->memcg = memcg;
 	}
 	memcg->nodeinfo[node] = pn;
@@ -5966,6 +6170,7 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
 	int node;
 	size_t size = memcg_size();
 
+	mem_cgroup_remove_from_trees(memcg);
 	free_css_id(&mem_cgroup_subsys, &memcg->css);
 
 	for_each_node(node)
@@ -6002,6 +6207,29 @@ struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
 }
 EXPORT_SYMBOL(parent_mem_cgroup);
 
+static void __init 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(node) {
+		tmp = node;
+		if (!node_state(node, N_NORMAL_MEMORY))
+			tmp = -1;
+		rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL, tmp);
+		BUG_ON(!rtpn);
+
+		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);
+		}
+	}
+}
+
 static struct cgroup_subsys_state * __ref
 mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 {
@@ -6031,7 +6259,6 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 	mutex_init(&memcg->thresholds_lock);
 	spin_lock_init(&memcg->move_lock);
 	vmpressure_init(&memcg->vmpressure);
-	spin_lock_init(&memcg->soft_lock);
 
 	return &memcg->css;
 
@@ -6109,13 +6336,6 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
 
 	mem_cgroup_invalidate_reclaim_iterators(memcg);
 	mem_cgroup_reparent_charges(memcg);
-	if (memcg->soft_contributed) {
-		while ((memcg = parent_mem_cgroup(memcg)))
-			atomic_dec(&memcg->children_in_excess);
-
-		if (memcg != root_mem_cgroup && !root_mem_cgroup->use_hierarchy)
-			atomic_dec(&root_mem_cgroup->children_in_excess);
-	}
 	mem_cgroup_destroy_all_caches(memcg);
 	vmpressure_cleanup(&memcg->vmpressure);
 }
@@ -6790,6 +7010,7 @@ static int __init mem_cgroup_init(void)
 {
 	hotcpu_notifier(memcg_cpu_hotplug_callback, 0);
 	enable_swap_cgroup();
+	mem_cgroup_soft_limit_tree_init();
 	memcg_stock_init();
 	return 0;
 }
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 947ed5413279..bf3351b5115e 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1114,8 +1114,10 @@ int memory_failure(unsigned long pfn, int trapno, int flags)
 			 * shake_page could have turned it free.
 			 */
 			if (is_free_buddy_page(p)) {
-				action_result(pfn, "free buddy, 2nd try",
-						DELAYED);
+				if (flags & MF_COUNT_INCREASED)
+					action_result(pfn, "free buddy", DELAYED);
+				else
+					action_result(pfn, "free buddy, 2nd try", DELAYED);
 				return 0;
 			}
 			action_result(pfn, "non LRU", IGNORED);
@@ -1349,7 +1351,7 @@ int unpoison_memory(unsigned long pfn)
 	 * worked by memory_failure() and the page lock is not held yet.
 	 * In such case, we yield to memory_failure() and make unpoison fail.
 	 */
-	if (PageTransHuge(page)) {
+	if (!PageHuge(page) && PageTransHuge(page)) {
 		pr_info("MCE: Memory failure is now running on %#lx\n", pfn);
 			return 0;
 	}
diff --git a/mm/memory.c b/mm/memory.c
index ca0003947115..1311f26497e6 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -837,6 +837,8 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 					 */
 					make_migration_entry_read(&entry);
 					pte = swp_entry_to_pte(entry);
+					if (pte_swp_soft_dirty(*src_pte))
+						pte = pte_swp_mksoft_dirty(pte);
 					set_pte_at(src_mm, addr, src_pte, pte);
 				}
 			}
@@ -3863,15 +3865,21 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * space.  Kernel faults are handled more gracefully.
 	 */
 	if (flags & FAULT_FLAG_USER)
-		mem_cgroup_enable_oom();
+		mem_cgroup_oom_enable();
 
 	ret = __handle_mm_fault(mm, vma, address, flags);
 
-	if (flags & FAULT_FLAG_USER)
-		mem_cgroup_disable_oom();
-
-	if (WARN_ON(task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM)))
-		mem_cgroup_oom_synchronize();
+	if (flags & FAULT_FLAG_USER) {
+		mem_cgroup_oom_disable();
+                /*
+                 * The task may have entered a memcg OOM situation but
+                 * if the allocation error was handled gracefully (no
+                 * VM_FAULT_OOM), there is no need to kill anything.
+                 * Just clean up the OOM state peacefully.
+                 */
+                if (task_in_memcg_oom(current) && !(ret & VM_FAULT_OOM))
+                        mem_cgroup_oom_synchronize(false);
+	}
 
 	return ret;
 }
diff --git a/mm/migrate.c b/mm/migrate.c
index 9c8d5f59d30b..7a7325ee1d08 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -107,7 +107,7 @@ void putback_movable_pages(struct list_head *l)
 		list_del(&page->lru);
 		dec_zone_page_state(page, NR_ISOLATED_ANON +
 				page_is_file_cache(page));
-		if (unlikely(balloon_page_movable(page)))
+		if (unlikely(isolated_balloon_page(page)))
 			balloon_page_putback(page);
 		else
 			putback_lru_page(page);
@@ -161,6 +161,8 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma,
 
 	get_page(new);
 	pte = pte_mkold(mk_pte(new, vma->vm_page_prot));
+	if (pte_swp_soft_dirty(*ptep))
+		pte = pte_mksoft_dirty(pte);
 	if (is_write_migration_entry(entry))
 		pte = pte_mkwrite(pte);
 #ifdef CONFIG_HUGETLB_PAGE
diff --git a/mm/mlock.c b/mm/mlock.c
index d63802663242..d480cd6fc475 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -379,10 +379,14 @@ static unsigned long __munlock_pagevec_fill(struct pagevec *pvec,
 
 	/*
 	 * Initialize pte walk starting at the already pinned page where we
-	 * are sure that there is a pte.
+	 * are sure that there is a pte, as it was pinned under the same
+	 * mmap_sem write op.
 	 */
 	pte = get_locked_pte(vma->vm_mm, start,	&ptl);
-	end = min(end, pmd_addr_end(start, end));
+	/* Make sure we do not cross the page table boundary */
+	end = pgd_addr_end(start, end);
+	end = pud_addr_end(start, end);
+	end = pmd_addr_end(start, end);
 
 	/* The page next to the pinned page is the first we will try to get */
 	start += PAGE_SIZE;
@@ -736,6 +740,7 @@ static int do_mlockall(int flags)
 
 		/* Ignore errors */
 		mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags);
+		cond_resched();
 	}
 out:
 	return 0;
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 94722a4d6b43..a3af058f68e4 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -94,13 +94,16 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 			swp_entry_t entry = pte_to_swp_entry(oldpte);
 
 			if (is_write_migration_entry(entry)) {
+				pte_t newpte;
 				/*
 				 * A protection check is difficult so
 				 * just be safe and disable write
 				 */
 				make_migration_entry_read(&entry);
-				set_pte_at(mm, addr, pte,
-					swp_entry_to_pte(entry));
+				newpte = swp_entry_to_pte(entry);
+				if (pte_swp_soft_dirty(oldpte))
+					newpte = pte_swp_mksoft_dirty(newpte);
+				set_pte_at(mm, addr, pte, newpte);
 			}
 			pages++;
 		}
diff --git a/mm/mremap.c b/mm/mremap.c
index 91b13d6a16d4..0843feb66f3d 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -25,7 +25,6 @@
 #include <asm/uaccess.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
-#include <asm/pgalloc.h>
 
 #include "internal.h"
 
@@ -63,10 +62,8 @@ static pmd_t *alloc_new_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
 		return NULL;
 
 	pmd = pmd_alloc(mm, pud, addr);
-	if (!pmd) {
-		pud_free(mm, pud);
+	if (!pmd)
 		return NULL;
-	}
 
 	VM_BUG_ON(pmd_trans_huge(*pmd));
 
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 314e9d274381..6738c47f1f72 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -680,7 +680,7 @@ void pagefault_out_of_memory(void)
 {
 	struct zonelist *zonelist;
 
-	if (mem_cgroup_oom_synchronize())
+	if (mem_cgroup_oom_synchronize(true))
 		return;
 
 	zonelist = node_zonelist(first_online_node, GFP_KERNEL);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index f5236f804aa6..63807583d8e8 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1210,11 +1210,11 @@ static unsigned long dirty_poll_interval(unsigned long dirty,
 	return 1;
 }
 
-static long bdi_max_pause(struct backing_dev_info *bdi,
-			  unsigned long bdi_dirty)
+static unsigned long bdi_max_pause(struct backing_dev_info *bdi,
+				   unsigned long bdi_dirty)
 {
-	long bw = bdi->avg_write_bandwidth;
-	long t;
+	unsigned long bw = bdi->avg_write_bandwidth;
+	unsigned long t;
 
 	/*
 	 * Limit pause time for small memory systems. If sleeping for too long
@@ -1226,7 +1226,7 @@ static long bdi_max_pause(struct backing_dev_info *bdi,
 	t = bdi_dirty / (1 + bw / roundup_pow_of_two(1 + HZ / 8));
 	t++;
 
-	return min_t(long, t, MAX_PAUSE);
+	return min_t(unsigned long, t, MAX_PAUSE);
 }
 
 static long bdi_min_pause(struct backing_dev_info *bdi,
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 0ee638f76ebe..dd886fac451a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6366,10 +6366,6 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
 		list_del(&page->lru);
 		rmv_page_order(page);
 		zone->free_area[order].nr_free--;
-#ifdef CONFIG_HIGHMEM
-		if (PageHighMem(page))
-			totalhigh_pages -= 1 << order;
-#endif
 		for (i = 0; i < (1 << order); i++)
 			SetPageReserved((page+i));
 		pfn += (1 << order);
diff --git a/mm/slab_common.c b/mm/slab_common.c
index a3443278ce3a..e2e98af703ea 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -56,6 +56,7 @@ static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name,
 			continue;
 		}
 
+#if !defined(CONFIG_SLUB) || !defined(CONFIG_SLUB_DEBUG_ON)
 		/*
 		 * For simplicity, we won't check this in the list of memcg
 		 * caches. We have control over memcg naming, and if there
@@ -69,6 +70,7 @@ static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name,
 			s = NULL;
 			return -EINVAL;
 		}
+#endif
 	}
 
 	WARN_ON(strchr(name, ' '));	/* It confuses parsers */
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 3963fc24fcc1..de7c904e52e5 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1824,6 +1824,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	struct filename *pathname;
 	int i, type, prev;
 	int err;
+	unsigned int old_block_size;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -1914,6 +1915,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	}
 
 	swap_file = p->swap_file;
+	old_block_size = p->old_block_size;
 	p->swap_file = NULL;
 	p->max = 0;
 	swap_map = p->swap_map;
@@ -1938,7 +1940,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	inode = mapping->host;
 	if (S_ISBLK(inode->i_mode)) {
 		struct block_device *bdev = I_BDEV(inode);
-		set_blocksize(bdev, p->old_block_size);
+		set_blocksize(bdev, old_block_size);
 		blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);
 	} else {
 		mutex_lock(&inode->i_mutex);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 8ed1b775bdc9..eea668d9cff6 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -48,6 +48,7 @@
 #include <asm/div64.h>
 
 #include <linux/swapops.h>
+#include <linux/balloon_compaction.h>
 
 #include "internal.h"
 
@@ -139,23 +140,11 @@ static bool global_reclaim(struct scan_control *sc)
 {
 	return !sc->target_mem_cgroup;
 }
-
-static bool mem_cgroup_should_soft_reclaim(struct scan_control *sc)
-{
-	struct mem_cgroup *root = sc->target_mem_cgroup;
-	return !mem_cgroup_disabled() &&
-		mem_cgroup_soft_reclaim_eligible(root, root) != SKIP_TREE;
-}
 #else
 static bool global_reclaim(struct scan_control *sc)
 {
 	return true;
 }
-
-static bool mem_cgroup_should_soft_reclaim(struct scan_control *sc)
-{
-	return false;
-}
 #endif
 
 unsigned long zone_reclaimable_pages(struct zone *zone)
@@ -222,6 +211,7 @@ void unregister_shrinker(struct shrinker *shrinker)
 	down_write(&shrinker_rwsem);
 	list_del(&shrinker->list);
 	up_write(&shrinker_rwsem);
+	kfree(shrinker->nr_deferred);
 }
 EXPORT_SYMBOL(unregister_shrinker);
 
@@ -1125,7 +1115,8 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
 	LIST_HEAD(clean_pages);
 
 	list_for_each_entry_safe(page, next, page_list, lru) {
-		if (page_is_file_cache(page) && !PageDirty(page)) {
+		if (page_is_file_cache(page) && !PageDirty(page) &&
+		    !isolated_balloon_page(page)) {
 			ClearPageActive(page);
 			list_move(&page->lru, &clean_pages);
 		}
@@ -2176,11 +2167,9 @@ static inline bool should_continue_reclaim(struct zone *zone,
 	}
 }
 
-static int
-__shrink_zone(struct zone *zone, struct scan_control *sc, bool soft_reclaim)
+static void shrink_zone(struct zone *zone, struct scan_control *sc)
 {
 	unsigned long nr_reclaimed, nr_scanned;
-	int groups_scanned = 0;
 
 	do {
 		struct mem_cgroup *root = sc->target_mem_cgroup;
@@ -2188,17 +2177,15 @@ __shrink_zone(struct zone *zone, struct scan_control *sc, bool soft_reclaim)
 			.zone = zone,
 			.priority = sc->priority,
 		};
-		struct mem_cgroup *memcg = NULL;
-		mem_cgroup_iter_filter filter = (soft_reclaim) ?
-			mem_cgroup_soft_reclaim_eligible : NULL;
+		struct mem_cgroup *memcg;
 
 		nr_reclaimed = sc->nr_reclaimed;
 		nr_scanned = sc->nr_scanned;
 
-		while ((memcg = mem_cgroup_iter_cond(root, memcg, &reclaim, filter))) {
+		memcg = mem_cgroup_iter(root, NULL, &reclaim);
+		do {
 			struct lruvec *lruvec;
 
-			groups_scanned++;
 			lruvec = mem_cgroup_zone_lruvec(zone, memcg);
 
 			shrink_lruvec(lruvec, sc);
@@ -2218,7 +2205,8 @@ __shrink_zone(struct zone *zone, struct scan_control *sc, bool soft_reclaim)
 				mem_cgroup_iter_break(root, memcg);
 				break;
 			}
-		}
+			memcg = mem_cgroup_iter(root, memcg, &reclaim);
+		} while (memcg);
 
 		vmpressure(sc->gfp_mask, sc->target_mem_cgroup,
 			   sc->nr_scanned - nr_scanned,
@@ -2226,37 +2214,6 @@ __shrink_zone(struct zone *zone, struct scan_control *sc, bool soft_reclaim)
 
 	} while (should_continue_reclaim(zone, sc->nr_reclaimed - nr_reclaimed,
 					 sc->nr_scanned - nr_scanned, sc));
-
-	return groups_scanned;
-}
-
-
-static void shrink_zone(struct zone *zone, struct scan_control *sc)
-{
-	bool do_soft_reclaim = mem_cgroup_should_soft_reclaim(sc);
-	unsigned long nr_scanned = sc->nr_scanned;
-	int scanned_groups;
-
-	scanned_groups = __shrink_zone(zone, sc, do_soft_reclaim);
-	/*
-	 * memcg iterator might race with other reclaimer or start from
-	 * a incomplete tree walk so the tree walk in __shrink_zone
-	 * might have missed groups that are above the soft limit. Try
-	 * another loop to catch up with others. Do it just once to
-	 * prevent from reclaim latencies when other reclaimers always
-	 * preempt this one.
-	 */
-	if (do_soft_reclaim && !scanned_groups)
-		__shrink_zone(zone, sc, do_soft_reclaim);
-
-	/*
-	 * No group is over the soft limit or those that are do not have
-	 * pages in the zone we are reclaiming so we have to reclaim everybody
-	 */
-	if (do_soft_reclaim && (sc->nr_scanned == nr_scanned)) {
-		__shrink_zone(zone, sc, false);
-		return;
-	}
 }
 
 /* Returns true if compaction should go ahead for a high-order request */
@@ -2320,6 +2277,8 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 {
 	struct zoneref *z;
 	struct zone *zone;
+	unsigned long nr_soft_reclaimed;
+	unsigned long nr_soft_scanned;
 	bool aborted_reclaim = false;
 
 	/*
@@ -2359,6 +2318,18 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 					continue;
 				}
 			}
+			/*
+			 * This steals pages from memory cgroups over softlimit
+			 * and returns the number of reclaimed pages and
+			 * scanned pages. This works for global memory pressure
+			 * and balancing, not for a memcg's limit.
+			 */
+			nr_soft_scanned = 0;
+			nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone,
+						sc->order, sc->gfp_mask,
+						&nr_soft_scanned);
+			sc->nr_reclaimed += nr_soft_reclaimed;
+			sc->nr_scanned += nr_soft_scanned;
 			/* need some check for avoid more shrink_zone() */
 		}
 
@@ -2952,6 +2923,8 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
 {
 	int i;
 	int end_zone = 0;	/* Inclusive.  0 = ZONE_DMA */
+	unsigned long nr_soft_reclaimed;
+	unsigned long nr_soft_scanned;
 	struct scan_control sc = {
 		.gfp_mask = GFP_KERNEL,
 		.priority = DEF_PRIORITY,
@@ -3066,6 +3039,15 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
 
 			sc.nr_scanned = 0;
 
+			nr_soft_scanned = 0;
+			/*
+			 * Call soft limit reclaim before calling shrink_zone.
+			 */
+			nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone,
+							order, sc.gfp_mask,
+							&nr_soft_scanned);
+			sc.nr_reclaimed += nr_soft_reclaimed;
+
 			/*
 			 * There should be no need to raise the scanning
 			 * priority if enough pages are already being scanned
diff --git a/mm/zswap.c b/mm/zswap.c
index 841e35f1db22..d93510c6aa2d 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -804,6 +804,10 @@ static void zswap_frontswap_invalidate_area(unsigned type)
 	}
 	tree->rbroot = RB_ROOT;
 	spin_unlock(&tree->lock);
+
+	zbud_destroy_pool(tree->pool);
+	kfree(tree);
+	zswap_trees[type] = NULL;
 }
 
 static struct zbud_ops zswap_zbud_ops = {