Linux-libre 4.3.2-gnu

1 files changed, 109 insertions, 405 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 03a6f7506..c57c4423c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -111,56 +111,10 @@ static const char * const mem_cgroup_lru_names[] = {
 	"unevictable",
 };
 
-/*
- * Per memcg event counter is incremented at every pagein/pageout. With THP,
- * it will be incremated by the number of pages. This counter is used for
- * for trigger some periodic events. This is straightforward and better
- * than using jiffies etc. to handle periodic memcg event.
- */
-enum mem_cgroup_events_target {
-	MEM_CGROUP_TARGET_THRESH,
-	MEM_CGROUP_TARGET_SOFTLIMIT,
-	MEM_CGROUP_TARGET_NUMAINFO,
-	MEM_CGROUP_NTARGETS,
-};
 #define THRESHOLDS_EVENTS_TARGET 128
 #define SOFTLIMIT_EVENTS_TARGET 1024
 #define NUMAINFO_EVENTS_TARGET	1024
 
-struct mem_cgroup_stat_cpu {
-	long count[MEM_CGROUP_STAT_NSTATS];
-	unsigned long events[MEMCG_NR_EVENTS];
-	unsigned long nr_page_events;
-	unsigned long targets[MEM_CGROUP_NTARGETS];
-};
-
-struct reclaim_iter {
-	struct mem_cgroup *position;
-	/* scan generation, increased every round-trip */
-	unsigned int generation;
-};
-
-/*
- * per-zone information in memory controller.
- */
-struct mem_cgroup_per_zone {
-	struct lruvec		lruvec;
-	unsigned long		lru_size[NR_LRU_LISTS];
-
-	struct reclaim_iter	iter[DEF_PRIORITY + 1];
-
-	struct rb_node		tree_node;	/* RB tree node */
-	unsigned long		usage_in_excess;/* Set to the value by which */
-						/* the soft limit is exceeded*/
-	bool			on_tree;
-	struct mem_cgroup	*memcg;		/* Back pointer, we cannot */
-						/* use container_of	   */
-};
-
-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
@@ -181,32 +135,6 @@ struct mem_cgroup_tree {
 
 static struct mem_cgroup_tree soft_limit_tree __read_mostly;
 
-struct mem_cgroup_threshold {
-	struct eventfd_ctx *eventfd;
-	unsigned long threshold;
-};
-
-/* For threshold */
-struct mem_cgroup_threshold_ary {
-	/* An array index points to threshold just below or equal to usage. */
-	int current_threshold;
-	/* Size of entries[] */
-	unsigned int size;
-	/* Array of thresholds */
-	struct mem_cgroup_threshold entries[0];
-};
-
-struct mem_cgroup_thresholds {
-	/* Primary thresholds array */
-	struct mem_cgroup_threshold_ary *primary;
-	/*
-	 * Spare threshold array.
-	 * This is needed to make mem_cgroup_unregister_event() "never fail".
-	 * It must be able to store at least primary->size - 1 entries.
-	 */
-	struct mem_cgroup_threshold_ary *spare;
-};
-
 /* for OOM */
 struct mem_cgroup_eventfd_list {
 	struct list_head list;
@@ -256,113 +184,6 @@ struct mem_cgroup_event {
 static void mem_cgroup_threshold(struct mem_cgroup *memcg);
 static void mem_cgroup_oom_notify(struct mem_cgroup *memcg);
 
-/*
- * 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,
- * to help the administrator determine what knobs to tune.
- */
-struct mem_cgroup {
-	struct cgroup_subsys_state css;
-
-	/* Accounted resources */
-	struct page_counter memory;
-	struct page_counter memsw;
-	struct page_counter kmem;
-
-	/* Normal memory consumption range */
-	unsigned long low;
-	unsigned long high;
-
-	unsigned long soft_limit;
-
-	/* vmpressure notifications */
-	struct vmpressure vmpressure;
-
-	/* css_online() has been completed */
-	int initialized;
-
-	/*
-	 * Should the accounting and control be hierarchical, per subtree?
-	 */
-	bool use_hierarchy;
-
-	/* protected by memcg_oom_lock */
-	bool		oom_lock;
-	int		under_oom;
-
-	int	swappiness;
-	/* OOM-Killer disable */
-	int		oom_kill_disable;
-
-	/* protect arrays of thresholds */
-	struct mutex thresholds_lock;
-
-	/* thresholds for memory usage. RCU-protected */
-	struct mem_cgroup_thresholds thresholds;
-
-	/* thresholds for mem+swap usage. RCU-protected */
-	struct mem_cgroup_thresholds memsw_thresholds;
-
-	/* For oom notifier event fd */
-	struct list_head oom_notify;
-
-	/*
-	 * Should we move charges of a task when a task is moved into this
-	 * mem_cgroup ? And what type of charges should we move ?
-	 */
-	unsigned long move_charge_at_immigrate;
-	/*
-	 * set > 0 if pages under this cgroup are moving to other cgroup.
-	 */
-	atomic_t		moving_account;
-	/* taken only while moving_account > 0 */
-	spinlock_t		move_lock;
-	struct task_struct	*move_lock_task;
-	unsigned long		move_lock_flags;
-	/*
-	 * percpu counter.
-	 */
-	struct mem_cgroup_stat_cpu __percpu *stat;
-	spinlock_t pcp_counter_lock;
-
-#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET)
-	struct cg_proto tcp_mem;
-#endif
-#if defined(CONFIG_MEMCG_KMEM)
-        /* Index in the kmem_cache->memcg_params.memcg_caches array */
-	int kmemcg_id;
-	bool kmem_acct_activated;
-	bool kmem_acct_active;
-#endif
-
-	int last_scanned_node;
-#if MAX_NUMNODES > 1
-	nodemask_t	scan_nodes;
-	atomic_t	numainfo_events;
-	atomic_t	numainfo_updating;
-#endif
-
-#ifdef CONFIG_CGROUP_WRITEBACK
-	struct list_head cgwb_list;
-	struct wb_domain cgwb_domain;
-#endif
-
-	/* List of events which userspace want to receive */
-	struct list_head event_list;
-	spinlock_t event_list_lock;
-
-	struct mem_cgroup_per_node *nodeinfo[0];
-	/* WARNING: nodeinfo must be the last member here */
-};
-
-#ifdef CONFIG_MEMCG_KMEM
-bool memcg_kmem_is_active(struct mem_cgroup *memcg)
-{
-	return memcg->kmem_acct_active;
-}
-#endif
-
 /* Stuffs for move charges at task migration. */
 /*
  * Types of charges to be moved.
@@ -423,11 +244,6 @@ enum res_type {
  */
 static DEFINE_MUTEX(memcg_create_mutex);
 
-struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *s)
-{
-	return s ? container_of(s, struct mem_cgroup, css) : NULL;
-}
-
 /* Some nice accessors for the vmpressure. */
 struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg)
 {
@@ -499,8 +315,7 @@ void sock_update_memcg(struct sock *sk)
 		rcu_read_lock();
 		memcg = mem_cgroup_from_task(current);
 		cg_proto = sk->sk_prot->proto_cgroup(memcg);
-		if (!mem_cgroup_is_root(memcg) &&
-		    memcg_proto_active(cg_proto) &&
+		if (cg_proto && test_bit(MEMCG_SOCK_ACTIVE, &cg_proto->flags) &&
 		    css_tryget_online(&memcg->css)) {
 			sk->sk_cgrp = cg_proto;
 		}
@@ -593,11 +408,6 @@ mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone)
 	return &memcg->nodeinfo[nid]->zoneinfo[zid];
 }
 
-struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg)
-{
-	return &memcg->css;
-}
-
 /**
  * mem_cgroup_css_from_page - css of the memcg associated with a page
  * @page: page of interest
@@ -631,6 +441,34 @@ struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page)
 	return &memcg->css;
 }
 
+/**
+ * page_cgroup_ino - return inode number of the memcg a page is charged to
+ * @page: the page
+ *
+ * Look up the closest online ancestor of the memory cgroup @page is charged to
+ * and return its inode number or 0 if @page is not charged to any cgroup. It
+ * is safe to call this function without holding a reference to @page.
+ *
+ * Note, this function is inherently racy, because there is nothing to prevent
+ * the cgroup inode from getting torn down and potentially reallocated a moment
+ * after page_cgroup_ino() returns, so it only should be used by callers that
+ * do not care (such as procfs interfaces).
+ */
+ino_t page_cgroup_ino(struct page *page)
+{
+	struct mem_cgroup *memcg;
+	unsigned long ino = 0;
+
+	rcu_read_lock();
+	memcg = READ_ONCE(page->mem_cgroup);
+	while (memcg && !(memcg->css.flags & CSS_ONLINE))
+		memcg = parent_mem_cgroup(memcg);
+	if (memcg)
+		ino = cgroup_ino(memcg->css.cgroup);
+	rcu_read_unlock();
+	return ino;
+}
+
 static struct mem_cgroup_per_zone *
 mem_cgroup_page_zoneinfo(struct mem_cgroup *memcg, struct page *page)
 {
@@ -885,14 +723,6 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
 	__this_cpu_add(memcg->stat->nr_page_events, nr_pages);
 }
 
-unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru)
-{
-	struct mem_cgroup_per_zone *mz;
-
-	mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec);
-	return mz->lru_size[lru];
-}
-
 static unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
 						  int nid,
 						  unsigned int lru_mask)
@@ -995,6 +825,7 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
 
 	return mem_cgroup_from_css(task_css(p, memory_cgrp_id));
 }
+EXPORT_SYMBOL(mem_cgroup_from_task);
 
 static struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
 {
@@ -1040,7 +871,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 				   struct mem_cgroup *prev,
 				   struct mem_cgroup_reclaim_cookie *reclaim)
 {
-	struct reclaim_iter *uninitialized_var(iter);
+	struct mem_cgroup_reclaim_iter *uninitialized_var(iter);
 	struct cgroup_subsys_state *css = NULL;
 	struct mem_cgroup *memcg = NULL;
 	struct mem_cgroup *pos = NULL;
@@ -1182,30 +1013,6 @@ void mem_cgroup_iter_break(struct mem_cgroup *root,
 	     iter != NULL;				\
 	     iter = mem_cgroup_iter(NULL, iter, NULL))
 
-void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx)
-{
-	struct mem_cgroup *memcg;
-
-	rcu_read_lock();
-	memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
-	if (unlikely(!memcg))
-		goto out;
-
-	switch (idx) {
-	case PGFAULT:
-		this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGFAULT]);
-		break;
-	case PGMAJFAULT:
-		this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PGMAJFAULT]);
-		break;
-	default:
-		BUG();
-	}
-out:
-	rcu_read_unlock();
-}
-EXPORT_SYMBOL(__mem_cgroup_count_vm_event);
-
 /**
  * mem_cgroup_zone_lruvec - get the lru list vector for a zone and memcg
  * @zone: zone of the wanted lruvec
@@ -1304,15 +1111,6 @@ void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
 	VM_BUG_ON((long)(*lru_size) < 0);
 }
 
-bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, struct mem_cgroup *root)
-{
-	if (root == memcg)
-		return true;
-	if (!root->use_hierarchy)
-		return false;
-	return cgroup_is_descendant(memcg->css.cgroup, root->css.cgroup);
-}
-
 bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg)
 {
 	struct mem_cgroup *task_memcg;
@@ -1339,39 +1137,6 @@ bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg)
 	return ret;
 }
 
-int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec)
-{
-	unsigned long inactive_ratio;
-	unsigned long inactive;
-	unsigned long active;
-	unsigned long gb;
-
-	inactive = mem_cgroup_get_lru_size(lruvec, LRU_INACTIVE_ANON);
-	active = mem_cgroup_get_lru_size(lruvec, LRU_ACTIVE_ANON);
-
-	gb = (inactive + active) >> (30 - PAGE_SHIFT);
-	if (gb)
-		inactive_ratio = int_sqrt(10 * gb);
-	else
-		inactive_ratio = 1;
-
-	return inactive * inactive_ratio < active;
-}
-
-bool mem_cgroup_lruvec_online(struct lruvec *lruvec)
-{
-	struct mem_cgroup_per_zone *mz;
-	struct mem_cgroup *memcg;
-
-	if (mem_cgroup_disabled())
-		return true;
-
-	mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec);
-	memcg = mz->memcg;
-
-	return !!(memcg->css.flags & CSS_ONLINE);
-}
-
 #define mem_cgroup_from_counter(counter, member)	\
 	container_of(counter, struct mem_cgroup, member)
 
@@ -1403,15 +1168,6 @@ static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg)
 	return margin;
 }
 
-int mem_cgroup_swappiness(struct mem_cgroup *memcg)
-{
-	/* root ? */
-	if (mem_cgroup_disabled() || !memcg->css.parent)
-		return vm_swappiness;
-
-	return memcg->swappiness;
-}
-
 /*
  * A routine for checking "mem" is under move_account() or not.
  *
@@ -1554,6 +1310,12 @@ static unsigned long mem_cgroup_get_limit(struct mem_cgroup *memcg)
 static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 				     int order)
 {
+	struct oom_control oc = {
+		.zonelist = NULL,
+		.nodemask = NULL,
+		.gfp_mask = gfp_mask,
+		.order = order,
+	};
 	struct mem_cgroup *iter;
 	unsigned long chosen_points = 0;
 	unsigned long totalpages;
@@ -1572,7 +1334,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 		goto unlock;
 	}
 
-	check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL, memcg);
+	check_panic_on_oom(&oc, CONSTRAINT_MEMCG, memcg);
 	totalpages = mem_cgroup_get_limit(memcg) ? : 1;
 	for_each_mem_cgroup_tree(iter, memcg) {
 		struct css_task_iter it;
@@ -1580,8 +1342,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 
 		css_task_iter_start(&iter->css, &it);
 		while ((task = css_task_iter_next(&it))) {
-			switch (oom_scan_process_thread(task, totalpages, NULL,
-							false)) {
+			switch (oom_scan_process_thread(&oc, task, totalpages)) {
 			case OOM_SCAN_SELECT:
 				if (chosen)
 					put_task_struct(chosen);
@@ -1619,8 +1380,8 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 
 	if (chosen) {
 		points = chosen_points * 1000 / totalpages;
-		oom_kill_process(chosen, gfp_mask, order, points, totalpages,
-				 memcg, NULL, "Memory cgroup out of memory");
+		oom_kill_process(&oc, chosen, points, totalpages, memcg,
+				 "Memory cgroup out of memory");
 	}
 unlock:
 	mutex_unlock(&oom_lock);
@@ -2071,23 +1832,6 @@ void mem_cgroup_end_page_stat(struct mem_cgroup *memcg)
 }
 EXPORT_SYMBOL(mem_cgroup_end_page_stat);
 
-/**
- * mem_cgroup_update_page_stat - update page state statistics
- * @memcg: memcg to account against
- * @idx: page state item to account
- * @val: number of pages (positive or negative)
- *
- * See mem_cgroup_begin_page_stat() for locking requirements.
- */
-void mem_cgroup_update_page_stat(struct mem_cgroup *memcg,
-				 enum mem_cgroup_stat_index idx, int val)
-{
-	VM_BUG_ON(!rcu_read_lock_held());
-
-	if (memcg)
-		this_cpu_add(memcg->stat->count[idx], val);
-}
-
 /*
  * size of first charge trial. "32" comes from vmscan.c's magic value.
  * TODO: maybe necessary to use big numbers in big irons.
@@ -2364,40 +2108,6 @@ static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
 	css_put_many(&memcg->css, nr_pages);
 }
 
-/*
- * try_get_mem_cgroup_from_page - look up page's memcg association
- * @page: the page
- *
- * Look up, get a css reference, and return the memcg that owns @page.
- *
- * The page must be locked to prevent racing with swap-in and page
- * cache charges.  If coming from an unlocked page table, the caller
- * must ensure the page is on the LRU or this can race with charging.
- */
-struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
-{
-	struct mem_cgroup *memcg;
-	unsigned short id;
-	swp_entry_t ent;
-
-	VM_BUG_ON_PAGE(!PageLocked(page), page);
-
-	memcg = page->mem_cgroup;
-	if (memcg) {
-		if (!css_tryget_online(&memcg->css))
-			memcg = NULL;
-	} else if (PageSwapCache(page)) {
-		ent.val = page_private(page);
-		id = lookup_swap_cgroup_id(ent);
-		rcu_read_lock();
-		memcg = mem_cgroup_from_id(id);
-		if (memcg && !css_tryget_online(&memcg->css))
-			memcg = NULL;
-		rcu_read_unlock();
-	}
-	return memcg;
-}
-
 static void lock_page_lru(struct page *page, int *isolated)
 {
 	struct zone *zone = page_zone(page);
@@ -2513,16 +2223,6 @@ void memcg_uncharge_kmem(struct mem_cgroup *memcg, unsigned long nr_pages)
 	css_put_many(&memcg->css, nr_pages);
 }
 
-/*
- * helper for acessing a memcg's index. It will be used as an index in the
- * child cache array in kmem_cache, and also to derive its name. This function
- * will return -1 when this is not a kmem-limited memcg.
- */
-int memcg_cache_id(struct mem_cgroup *memcg)
-{
-	return memcg ? memcg->kmemcg_id : -1;
-}
-
 static int memcg_alloc_cache_id(void)
 {
 	int id, size;
@@ -4041,44 +3741,43 @@ struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb)
 /**
  * mem_cgroup_wb_stats - retrieve writeback related stats from its memcg
  * @wb: bdi_writeback in question
- * @pavail: out parameter for number of available pages
+ * @pfilepages: out parameter for number of file pages
+ * @pheadroom: out parameter for number of allocatable pages according to memcg
  * @pdirty: out parameter for number of dirty pages
  * @pwriteback: out parameter for number of pages under writeback
  *
- * Determine the numbers of available, dirty, and writeback pages in @wb's
- * memcg.  Dirty and writeback are self-explanatory.  Available is a bit
- * more involved.
+ * Determine the numbers of file, headroom, dirty, and writeback pages in
+ * @wb's memcg.  File, dirty and writeback are self-explanatory.  Headroom
+ * is a bit more involved.
  *
- * A memcg's headroom is "min(max, high) - used".  The available memory is
- * calculated as the lowest headroom of itself and the ancestors plus the
- * number of pages already being used for file pages.  Note that this
- * doesn't consider the actual amount of available memory in the system.
- * The caller should further cap *@pavail accordingly.
+ * A memcg's headroom is "min(max, high) - used".  In the hierarchy, the
+ * headroom is calculated as the lowest headroom of itself and the
+ * ancestors.  Note that this doesn't consider the actual amount of
+ * available memory in the system.  The caller should further cap
+ * *@pheadroom accordingly.
  */
-void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pavail,
-			 unsigned long *pdirty, unsigned long *pwriteback)
+void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
+			 unsigned long *pheadroom, unsigned long *pdirty,
+			 unsigned long *pwriteback)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css);
 	struct mem_cgroup *parent;
-	unsigned long head_room = PAGE_COUNTER_MAX;
-	unsigned long file_pages;
 
 	*pdirty = mem_cgroup_read_stat(memcg, MEM_CGROUP_STAT_DIRTY);
 
 	/* this should eventually include NR_UNSTABLE_NFS */
 	*pwriteback = mem_cgroup_read_stat(memcg, MEM_CGROUP_STAT_WRITEBACK);
+	*pfilepages = mem_cgroup_nr_lru_pages(memcg, (1 << LRU_INACTIVE_FILE) |
+						     (1 << LRU_ACTIVE_FILE));
+	*pheadroom = PAGE_COUNTER_MAX;
 
-	file_pages = mem_cgroup_nr_lru_pages(memcg, (1 << LRU_INACTIVE_FILE) |
-						    (1 << LRU_ACTIVE_FILE));
 	while ((parent = parent_mem_cgroup(memcg))) {
 		unsigned long ceiling = min(memcg->memory.limit, memcg->high);
 		unsigned long used = page_counter_read(&memcg->memory);
 
-		head_room = min(head_room, ceiling - min(ceiling, used));
+		*pheadroom = min(*pheadroom, ceiling - min(ceiling, used));
 		memcg = parent;
 	}
-
-	*pavail = file_pages + head_room;
 }
 
 #else	/* CONFIG_CGROUP_WRITEBACK */
@@ -4486,7 +4185,6 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 	if (memcg_wb_domain_init(memcg, GFP_KERNEL))
 		goto out_free_stat;
 
-	spin_lock_init(&memcg->pcp_counter_lock);
 	return memcg;
 
 out_free_stat:
@@ -5134,10 +4832,12 @@ static void mem_cgroup_clear_mc(void)
 static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
 				 struct cgroup_taskset *tset)
 {
-	struct task_struct *p = cgroup_taskset_first(tset);
-	int ret = 0;
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+	struct mem_cgroup *from;
+	struct task_struct *p;
+	struct mm_struct *mm;
 	unsigned long move_flags;
+	int ret = 0;
 
 	/*
 	 * We are now commited to this value whatever it is. Changes in this
@@ -5145,36 +4845,37 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
 	 * So we need to save it, and keep it going.
 	 */
 	move_flags = READ_ONCE(memcg->move_charge_at_immigrate);
-	if (move_flags) {
-		struct mm_struct *mm;
-		struct mem_cgroup *from = mem_cgroup_from_task(p);
+	if (!move_flags)
+		return 0;
 
-		VM_BUG_ON(from == memcg);
+	p = cgroup_taskset_first(tset);
+	from = mem_cgroup_from_task(p);
 
-		mm = get_task_mm(p);
-		if (!mm)
-			return 0;
-		/* We move charges only when we move a owner of the mm */
-		if (mm->owner == p) {
-			VM_BUG_ON(mc.from);
-			VM_BUG_ON(mc.to);
-			VM_BUG_ON(mc.precharge);
-			VM_BUG_ON(mc.moved_charge);
-			VM_BUG_ON(mc.moved_swap);
-
-			spin_lock(&mc.lock);
-			mc.from = from;
-			mc.to = memcg;
-			mc.flags = move_flags;
-			spin_unlock(&mc.lock);
-			/* We set mc.moving_task later */
-
-			ret = mem_cgroup_precharge_mc(mm);
-			if (ret)
-				mem_cgroup_clear_mc();
-		}
-		mmput(mm);
+	VM_BUG_ON(from == memcg);
+
+	mm = get_task_mm(p);
+	if (!mm)
+		return 0;
+	/* We move charges only when we move a owner of the mm */
+	if (mm->owner == p) {
+		VM_BUG_ON(mc.from);
+		VM_BUG_ON(mc.to);
+		VM_BUG_ON(mc.precharge);
+		VM_BUG_ON(mc.moved_charge);
+		VM_BUG_ON(mc.moved_swap);
+
+		spin_lock(&mc.lock);
+		mc.from = from;
+		mc.to = memcg;
+		mc.flags = move_flags;
+		spin_unlock(&mc.lock);
+		/* We set mc.moving_task later */
+
+		ret = mem_cgroup_precharge_mc(mm);
+		if (ret)
+			mem_cgroup_clear_mc();
 	}
+	mmput(mm);
 	return ret;
 }
 
@@ -5528,19 +5229,6 @@ struct cgroup_subsys memory_cgrp_subsys = {
 };
 
 /**
- * mem_cgroup_events - count memory events against a cgroup
- * @memcg: the memory cgroup
- * @idx: the event index
- * @nr: the number of events to account for
- */
-void mem_cgroup_events(struct mem_cgroup *memcg,
-		       enum mem_cgroup_events_index idx,
-		       unsigned int nr)
-{
-	this_cpu_add(memcg->stat->events[idx], nr);
-}
-
-/**
  * mem_cgroup_low - check if memory consumption is below the normal range
  * @root: the highest ancestor to consider
  * @memcg: the memory cgroup to check
@@ -5612,8 +5300,20 @@ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
 		 * the page lock, which serializes swap cache removal, which
 		 * in turn serializes uncharging.
 		 */
+		VM_BUG_ON_PAGE(!PageLocked(page), page);
 		if (page->mem_cgroup)
 			goto out;
+
+		if (do_swap_account) {
+			swp_entry_t ent = { .val = page_private(page), };
+			unsigned short id = lookup_swap_cgroup_id(ent);
+
+			rcu_read_lock();
+			memcg = mem_cgroup_from_id(id);
+			if (memcg && !css_tryget_online(&memcg->css))
+				memcg = NULL;
+			rcu_read_unlock();
+		}
 	}
 
 	if (PageTransHuge(page)) {
@@ -5621,8 +5321,6 @@ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
 		VM_BUG_ON_PAGE(!PageTransHuge(page), page);
 	}
 
-	if (do_swap_account && PageSwapCache(page))
-		memcg = try_get_mem_cgroup_from_page(page);
 	if (!memcg)
 		memcg = get_mem_cgroup_from_mm(mm);
 
@@ -5972,7 +5670,13 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
 	if (!mem_cgroup_is_root(memcg))
 		page_counter_uncharge(&memcg->memory, 1);
 
-	/* Caller disabled preemption with mapping->tree_lock */
+	/*
+	 * Interrupts should be disabled here because the caller holds the
+	 * mapping->tree_lock lock which is taken with interrupts-off. It is
+	 * important here to have the interrupts disabled because it is the
+	 * only synchronisation we have for udpating the per-CPU variables.
+	 */
+	VM_BUG_ON(!irqs_disabled());
 	mem_cgroup_charge_statistics(memcg, page, -1);
 	memcg_check_events(memcg, page);
 }