1 files changed, 174 insertions, 219 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6ddaeba34e09..9acfb165eb52 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -62,6 +62,7 @@
 #include <linux/oom.h>
 #include <linux/lockdep.h>
 #include <linux/file.h>
+#include <linux/tracehook.h>
 #include "internal.h"
 #include <net/sock.h>
 #include <net/ip.h>
@@ -434,7 +435,7 @@ struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page)
 
 	memcg = page->mem_cgroup;
 
-	if (!memcg || !cgroup_on_dfl(memcg->css.cgroup))
+	if (!memcg || !cgroup_subsys_on_dfl(memory_cgrp_subsys))
 		memcg = root_mem_cgroup;
 
 	rcu_read_unlock();
@@ -644,12 +645,14 @@ mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
 }
 
 /*
+ * Return page count for single (non recursive) @memcg.
+ *
  * Implementation Note: reading percpu statistics for memcg.
  *
  * Both of vmstat[] and percpu_counter has threshold and do periodic
  * synchronization to implement "quick" read. There are trade-off between
  * reading cost and precision of value. Then, we may have a chance to implement
- * a periodic synchronizion of counter in memcg's counter.
+ * a periodic synchronization of counter in memcg's counter.
  *
  * But this _read() function is used for user interface now. The user accounts
  * memory usage by memory cgroup and he _always_ requires exact value because
@@ -659,17 +662,24 @@ mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
  *
  * If there are kernel internal actions which can make use of some not-exact
  * value, and reading all cpu value can be performance bottleneck in some
- * common workload, threashold and synchonization as vmstat[] should be
+ * common workload, threshold and synchronization as vmstat[] should be
  * implemented.
  */
-static long mem_cgroup_read_stat(struct mem_cgroup *memcg,
-				 enum mem_cgroup_stat_index idx)
+static unsigned long
+mem_cgroup_read_stat(struct mem_cgroup *memcg, enum mem_cgroup_stat_index idx)
 {
 	long val = 0;
 	int cpu;
 
+	/* Per-cpu values can be negative, use a signed accumulator */
 	for_each_possible_cpu(cpu)
 		val += per_cpu(memcg->stat->count[idx], cpu);
+	/*
+	 * Summing races with updates, so val may be negative.  Avoid exposing
+	 * transient negative values.
+	 */
+	if (val < 0)
+		val = 0;
 	return val;
 }
 
@@ -1254,7 +1264,7 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 		for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
 			if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
 				continue;
-			pr_cont(" %s:%ldKB", mem_cgroup_stat_names[i],
+			pr_cont(" %s:%luKB", mem_cgroup_stat_names[i],
 				K(mem_cgroup_read_stat(iter, i)));
 		}
 
@@ -1652,7 +1662,7 @@ static void memcg_oom_recover(struct mem_cgroup *memcg)
 
 static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
 {
-	if (!current->memcg_oom.may_oom)
+	if (!current->memcg_may_oom)
 		return;
 	/*
 	 * We are in the middle of the charge context here, so we
@@ -1669,9 +1679,9 @@ static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
 	 * and when we know whether the fault was overall successful.
 	 */
 	css_get(&memcg->css);
-	current->memcg_oom.memcg = memcg;
-	current->memcg_oom.gfp_mask = mask;
-	current->memcg_oom.order = order;
+	current->memcg_in_oom = memcg;
+	current->memcg_oom_gfp_mask = mask;
+	current->memcg_oom_order = order;
 }
 
 /**
@@ -1693,7 +1703,7 @@ static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
  */
 bool mem_cgroup_oom_synchronize(bool handle)
 {
-	struct mem_cgroup *memcg = current->memcg_oom.memcg;
+	struct mem_cgroup *memcg = current->memcg_in_oom;
 	struct oom_wait_info owait;
 	bool locked;
 
@@ -1721,8 +1731,8 @@ bool mem_cgroup_oom_synchronize(bool handle)
 	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);
+		mem_cgroup_out_of_memory(memcg, current->memcg_oom_gfp_mask,
+					 current->memcg_oom_order);
 	} else {
 		schedule();
 		mem_cgroup_unmark_under_oom(memcg);
@@ -1739,7 +1749,7 @@ bool mem_cgroup_oom_synchronize(bool handle)
 		memcg_oom_recover(memcg);
 	}
 cleanup:
-	current->memcg_oom.memcg = NULL;
+	current->memcg_in_oom = NULL;
 	css_put(&memcg->css);
 	return true;
 }
@@ -1963,6 +1973,31 @@ static int memcg_cpu_hotplug_callback(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
+/*
+ * Scheduled by try_charge() to be executed from the userland return path
+ * and reclaims memory over the high limit.
+ */
+void mem_cgroup_handle_over_high(void)
+{
+	unsigned int nr_pages = current->memcg_nr_pages_over_high;
+	struct mem_cgroup *memcg, *pos;
+
+	if (likely(!nr_pages))
+		return;
+
+	pos = memcg = get_mem_cgroup_from_mm(current->mm);
+
+	do {
+		if (page_counter_read(&pos->memory) <= pos->high)
+			continue;
+		mem_cgroup_events(pos, MEMCG_HIGH, 1);
+		try_to_free_mem_cgroup_pages(pos, nr_pages, GFP_KERNEL, true);
+	} while ((pos = parent_mem_cgroup(pos)));
+
+	css_put(&memcg->css);
+	current->memcg_nr_pages_over_high = 0;
+}
+
 static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 		      unsigned int nr_pages)
 {
@@ -1973,17 +2008,16 @@ static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	unsigned long nr_reclaimed;
 	bool may_swap = true;
 	bool drained = false;
-	int ret = 0;
 
 	if (mem_cgroup_is_root(memcg))
-		goto done;
+		return 0;
 retry:
 	if (consume_stock(memcg, nr_pages))
-		goto done;
+		return 0;
 
 	if (!do_swap_account ||
-	    !page_counter_try_charge(&memcg->memsw, batch, &counter)) {
-		if (!page_counter_try_charge(&memcg->memory, batch, &counter))
+	    page_counter_try_charge(&memcg->memsw, batch, &counter)) {
+		if (page_counter_try_charge(&memcg->memory, batch, &counter))
 			goto done_restock;
 		if (do_swap_account)
 			page_counter_uncharge(&memcg->memsw, batch);
@@ -2007,12 +2041,12 @@ retry:
 	if (unlikely(test_thread_flag(TIF_MEMDIE) ||
 		     fatal_signal_pending(current) ||
 		     current->flags & PF_EXITING))
-		goto bypass;
+		goto force;
 
 	if (unlikely(task_in_memcg_oom(current)))
 		goto nomem;
 
-	if (!(gfp_mask & __GFP_WAIT))
+	if (!gfpflags_allow_blocking(gfp_mask))
 		goto nomem;
 
 	mem_cgroup_events(mem_over_limit, MEMCG_MAX, 1);
@@ -2053,38 +2087,54 @@ retry:
 		goto retry;
 
 	if (gfp_mask & __GFP_NOFAIL)
-		goto bypass;
+		goto force;
 
 	if (fatal_signal_pending(current))
-		goto bypass;
+		goto force;
 
 	mem_cgroup_events(mem_over_limit, MEMCG_OOM, 1);
 
-	mem_cgroup_oom(mem_over_limit, gfp_mask, get_order(nr_pages));
+	mem_cgroup_oom(mem_over_limit, gfp_mask,
+		       get_order(nr_pages * PAGE_SIZE));
 nomem:
 	if (!(gfp_mask & __GFP_NOFAIL))
 		return -ENOMEM;
-bypass:
-	return -EINTR;
+force:
+	/*
+	 * The allocation either can't fail or will lead to more memory
+	 * being freed very soon.  Allow memory usage go over the limit
+	 * temporarily by force charging it.
+	 */
+	page_counter_charge(&memcg->memory, nr_pages);
+	if (do_swap_account)
+		page_counter_charge(&memcg->memsw, nr_pages);
+	css_get_many(&memcg->css, nr_pages);
+
+	return 0;
 
 done_restock:
 	css_get_many(&memcg->css, batch);
 	if (batch > nr_pages)
 		refill_stock(memcg, batch - nr_pages);
-	if (!(gfp_mask & __GFP_WAIT))
-		goto done;
+
 	/*
-	 * If the hierarchy is above the normal consumption range,
-	 * make the charging task trim their excess contribution.
+	 * If the hierarchy is above the normal consumption range, schedule
+	 * reclaim on returning to userland.  We can perform reclaim here
+	 * if __GFP_RECLAIM but let's always punt for simplicity and so that
+	 * GFP_KERNEL can consistently be used during reclaim.  @memcg is
+	 * not recorded as it most likely matches current's and won't
+	 * change in the meantime.  As high limit is checked again before
+	 * reclaim, the cost of mismatch is negligible.
 	 */
 	do {
-		if (page_counter_read(&memcg->memory) <= memcg->high)
-			continue;
-		mem_cgroup_events(memcg, MEMCG_HIGH, 1);
-		try_to_free_mem_cgroup_pages(memcg, nr_pages, gfp_mask, true);
+		if (page_counter_read(&memcg->memory) > memcg->high) {
+			current->memcg_nr_pages_over_high += nr_pages;
+			set_notify_resume(current);
+			break;
+		}
 	} while ((memcg = parent_mem_cgroup(memcg)));
-done:
-	return ret;
+
+	return 0;
 }
 
 static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
@@ -2165,55 +2215,6 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg,
 }
 
 #ifdef CONFIG_MEMCG_KMEM
-int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp,
-		      unsigned long nr_pages)
-{
-	struct page_counter *counter;
-	int ret = 0;
-
-	ret = page_counter_try_charge(&memcg->kmem, nr_pages, &counter);
-	if (ret < 0)
-		return ret;
-
-	ret = try_charge(memcg, gfp, nr_pages);
-	if (ret == -EINTR)  {
-		/*
-		 * try_charge() chose to bypass to root due to OOM kill or
-		 * fatal signal.  Since our only options are to either fail
-		 * the allocation or charge it to this cgroup, do it as a
-		 * temporary condition. But we can't fail. From a kmem/slab
-		 * perspective, the cache has already been selected, by
-		 * mem_cgroup_kmem_get_cache(), so it is too late to change
-		 * our minds.
-		 *
-		 * This condition will only trigger if the task entered
-		 * memcg_charge_kmem in a sane state, but was OOM-killed
-		 * during try_charge() above. Tasks that were already dying
-		 * when the allocation triggers should have been already
-		 * directed to the root cgroup in memcontrol.h
-		 */
-		page_counter_charge(&memcg->memory, nr_pages);
-		if (do_swap_account)
-			page_counter_charge(&memcg->memsw, nr_pages);
-		css_get_many(&memcg->css, nr_pages);
-		ret = 0;
-	} else if (ret)
-		page_counter_uncharge(&memcg->kmem, nr_pages);
-
-	return ret;
-}
-
-void memcg_uncharge_kmem(struct mem_cgroup *memcg, unsigned long nr_pages)
-{
-	page_counter_uncharge(&memcg->memory, nr_pages);
-	if (do_swap_account)
-		page_counter_uncharge(&memcg->memsw, nr_pages);
-
-	page_counter_uncharge(&memcg->kmem, nr_pages);
-
-	css_put_many(&memcg->css, nr_pages);
-}
-
 static int memcg_alloc_cache_id(void)
 {
 	int id, size;
@@ -2375,85 +2376,58 @@ void __memcg_kmem_put_cache(struct kmem_cache *cachep)
 		css_put(&cachep->memcg_params.memcg->css);
 }
 
-/*
- * We need to verify if the allocation against current->mm->owner's memcg is
- * possible for the given order. But the page is not allocated yet, so we'll
- * need a further commit step to do the final arrangements.
- *
- * It is possible for the task to switch cgroups in this mean time, so at
- * commit time, we can't rely on task conversion any longer.  We'll then use
- * the handle argument to return to the caller which cgroup we should commit
- * against. We could also return the memcg directly and avoid the pointer
- * passing, but a boolean return value gives better semantics considering
- * the compiled-out case as well.
- *
- * Returning true means the allocation is possible.
- */
-bool
-__memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **_memcg, int order)
+int __memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order,
+			      struct mem_cgroup *memcg)
 {
-	struct mem_cgroup *memcg;
+	unsigned int nr_pages = 1 << order;
+	struct page_counter *counter;
 	int ret;
 
-	*_memcg = NULL;
+	if (!memcg_kmem_is_active(memcg))
+		return 0;
 
-	memcg = get_mem_cgroup_from_mm(current->mm);
+	if (!page_counter_try_charge(&memcg->kmem, nr_pages, &counter))
+		return -ENOMEM;
 
-	if (!memcg_kmem_is_active(memcg)) {
-		css_put(&memcg->css);
-		return true;
+	ret = try_charge(memcg, gfp, nr_pages);
+	if (ret) {
+		page_counter_uncharge(&memcg->kmem, nr_pages);
+		return ret;
 	}
 
-	ret = memcg_charge_kmem(memcg, gfp, 1 << order);
-	if (!ret)
-		*_memcg = memcg;
+	page->mem_cgroup = memcg;
 
-	css_put(&memcg->css);
-	return (ret == 0);
+	return 0;
 }
 
-void __memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg,
-			      int order)
+int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order)
 {
-	VM_BUG_ON(mem_cgroup_is_root(memcg));
+	struct mem_cgroup *memcg;
+	int ret;
 
-	/* The page allocation failed. Revert */
-	if (!page) {
-		memcg_uncharge_kmem(memcg, 1 << order);
-		return;
-	}
-	page->mem_cgroup = memcg;
+	memcg = get_mem_cgroup_from_mm(current->mm);
+	ret = __memcg_kmem_charge_memcg(page, gfp, order, memcg);
+	css_put(&memcg->css);
+	return ret;
 }
 
-void __memcg_kmem_uncharge_pages(struct page *page, int order)
+void __memcg_kmem_uncharge(struct page *page, int order)
 {
 	struct mem_cgroup *memcg = page->mem_cgroup;
+	unsigned int nr_pages = 1 << order;
 
 	if (!memcg)
 		return;
 
 	VM_BUG_ON_PAGE(mem_cgroup_is_root(memcg), page);
 
-	memcg_uncharge_kmem(memcg, 1 << order);
-	page->mem_cgroup = NULL;
-}
-
-struct mem_cgroup *__mem_cgroup_from_kmem(void *ptr)
-{
-	struct mem_cgroup *memcg = NULL;
-	struct kmem_cache *cachep;
-	struct page *page;
-
-	page = virt_to_head_page(ptr);
-	if (PageSlab(page)) {
-		cachep = page->slab_cache;
-		if (!is_root_cache(cachep))
-			memcg = cachep->memcg_params.memcg;
-	} else
-		/* page allocated by alloc_kmem_pages */
-		memcg = page->mem_cgroup;
+	page_counter_uncharge(&memcg->kmem, nr_pages);
+	page_counter_uncharge(&memcg->memory, nr_pages);
+	if (do_swap_account)
+		page_counter_uncharge(&memcg->memsw, nr_pages);
 
-	return memcg;
+	page->mem_cgroup = NULL;
+	css_put_many(&memcg->css, nr_pages);
 }
 #endif /* CONFIG_MEMCG_KMEM */
 
@@ -2819,20 +2793,17 @@ static unsigned long tree_stat(struct mem_cgroup *memcg,
 			       enum mem_cgroup_stat_index idx)
 {
 	struct mem_cgroup *iter;
-	long val = 0;
+	unsigned long val = 0;
 
-	/* Per-cpu values can be negative, use a signed accumulator */
 	for_each_mem_cgroup_tree(iter, memcg)
 		val += mem_cgroup_read_stat(iter, idx);
 
-	if (val < 0) /* race ? */
-		val = 0;
 	return val;
 }
 
-static inline u64 mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
+static unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
 {
-	u64 val;
+	unsigned long val;
 
 	if (mem_cgroup_is_root(memcg)) {
 		val = tree_stat(memcg, MEM_CGROUP_STAT_CACHE);
@@ -2845,7 +2816,7 @@ static inline u64 mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
 		else
 			val = page_counter_read(&memcg->memsw);
 	}
-	return val << PAGE_SHIFT;
+	return val;
 }
 
 enum {
@@ -2879,9 +2850,9 @@ static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css,
 	switch (MEMFILE_ATTR(cft->private)) {
 	case RES_USAGE:
 		if (counter == &memcg->memory)
-			return mem_cgroup_usage(memcg, false);
+			return (u64)mem_cgroup_usage(memcg, false) * PAGE_SIZE;
 		if (counter == &memcg->memsw)
-			return mem_cgroup_usage(memcg, true);
+			return (u64)mem_cgroup_usage(memcg, true) * PAGE_SIZE;
 		return (u64)page_counter_read(counter) * PAGE_SIZE;
 	case RES_LIMIT:
 		return (u64)counter->limit * PAGE_SIZE;
@@ -2920,7 +2891,7 @@ static int memcg_activate_kmem(struct mem_cgroup *memcg,
 	 * of course permitted.
 	 */
 	mutex_lock(&memcg_create_mutex);
-	if (cgroup_has_tasks(memcg->css.cgroup) ||
+	if (cgroup_is_populated(memcg->css.cgroup) ||
 	    (memcg->use_hierarchy && memcg_has_children(memcg)))
 		err = -EBUSY;
 	mutex_unlock(&memcg_create_mutex);
@@ -3169,7 +3140,7 @@ static int memcg_stat_show(struct seq_file *m, void *v)
 	for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
 		if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
 			continue;
-		seq_printf(m, "%s %ld\n", mem_cgroup_stat_names[i],
+		seq_printf(m, "%s %lu\n", mem_cgroup_stat_names[i],
 			   mem_cgroup_read_stat(memcg, i) * PAGE_SIZE);
 	}
 
@@ -3194,13 +3165,13 @@ static int memcg_stat_show(struct seq_file *m, void *v)
 			   (u64)memsw * PAGE_SIZE);
 
 	for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
-		long long val = 0;
+		unsigned long long val = 0;
 
 		if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
 			continue;
 		for_each_mem_cgroup_tree(mi, memcg)
 			val += mem_cgroup_read_stat(mi, i) * PAGE_SIZE;
-		seq_printf(m, "total_%s %lld\n", mem_cgroup_stat_names[i], val);
+		seq_printf(m, "total_%s %llu\n", mem_cgroup_stat_names[i], val);
 	}
 
 	for (i = 0; i < MEM_CGROUP_EVENTS_NSTATS; i++) {
@@ -3734,44 +3705,43 @@ 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 */
@@ -4060,8 +4030,7 @@ static struct cftype mem_cgroup_legacy_files[] = {
 	{
 		.name = "cgroup.event_control",		/* XXX: for compat */
 		.write = memcg_write_event_control,
-		.flags = CFTYPE_NO_PREFIX,
-		.mode = S_IWUGO,
+		.flags = CFTYPE_NO_PREFIX | CFTYPE_WORLD_WRITABLE,
 	},
 	{
 		.name = "swappiness",
@@ -4179,7 +4148,6 @@ 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:
@@ -4396,28 +4364,16 @@ static int mem_cgroup_do_precharge(unsigned long count)
 {
 	int ret;
 
-	/* Try a single bulk charge without reclaim first */
-	ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_WAIT, count);
+	/* Try a single bulk charge without reclaim first, kswapd may wake */
+	ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_DIRECT_RECLAIM, count);
 	if (!ret) {
 		mc.precharge += count;
 		return ret;
 	}
-	if (ret == -EINTR) {
-		cancel_charge(root_mem_cgroup, count);
-		return ret;
-	}
 
 	/* Try charges one by one with reclaim */
 	while (count--) {
 		ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_NORETRY, 1);
-		/*
-		 * In case of failure, any residual charges against
-		 * mc.to will be dropped by mem_cgroup_clear_mc()
-		 * later on.  However, cancel any charges that are
-		 * bypassed to root right away or they'll be lost.
-		 */
-		if (ret == -EINTR)
-			cancel_charge(root_mem_cgroup, 1);
 		if (ret)
 			return ret;
 		mc.precharge++;
@@ -4572,9 +4528,8 @@ static int mem_cgroup_move_account(struct page *page,
 		goto out;
 
 	/*
-	 * Prevent mem_cgroup_migrate() from looking at page->mem_cgroup
-	 * of its source page while we change it: page migration takes
-	 * both pages off the LRU, but page cache replacement doesn't.
+	 * Prevent mem_cgroup_replace_page() from looking at
+	 * page->mem_cgroup of its source page while we change it.
 	 */
 	if (!trylock_page(page))
 		goto out;
@@ -4829,7 +4784,7 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 	struct mem_cgroup *from;
-	struct task_struct *p;
+	struct task_struct *leader, *p;
 	struct mm_struct *mm;
 	unsigned long move_flags;
 	int ret = 0;
@@ -4843,7 +4798,20 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
 	if (!move_flags)
 		return 0;
 
-	p = cgroup_taskset_first(tset);
+	/*
+	 * Multi-process migrations only happen on the default hierarchy
+	 * where charge immigration is not used.  Perform charge
+	 * immigration if @tset contains a leader and whine if there are
+	 * multiple.
+	 */
+	p = NULL;
+	cgroup_taskset_for_each_leader(leader, tset) {
+		WARN_ON_ONCE(p);
+		p = leader;
+	}
+	if (!p)
+		return 0;
+
 	from = mem_cgroup_from_task(p);
 
 	VM_BUG_ON(from == memcg);
@@ -5059,7 +5027,7 @@ static void mem_cgroup_bind(struct cgroup_subsys_state *root_css)
 	 * guarantees that @root doesn't have any children, so turning it
 	 * on for the root memcg is enough.
 	 */
-	if (cgroup_on_dfl(root_css->cgroup))
+	if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
 		root_mem_cgroup->use_hierarchy = true;
 	else
 		root_mem_cgroup->use_hierarchy = false;
@@ -5068,7 +5036,9 @@ static void mem_cgroup_bind(struct cgroup_subsys_state *root_css)
 static u64 memory_current_read(struct cgroup_subsys_state *css,
 			       struct cftype *cft)
 {
-	return mem_cgroup_usage(mem_cgroup_from_css(css), false);
+	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+
+	return (u64)page_counter_read(&memcg->memory) * PAGE_SIZE;
 }
 
 static int memory_low_show(struct seq_file *m, void *v)
@@ -5180,6 +5150,7 @@ static int memory_events_show(struct seq_file *m, void *v)
 static struct cftype memory_files[] = {
 	{
 		.name = "current",
+		.flags = CFTYPE_NOT_ON_ROOT,
 		.read_u64 = memory_current_read,
 	},
 	{
@@ -5203,6 +5174,7 @@ static struct cftype memory_files[] = {
 	{
 		.name = "events",
 		.flags = CFTYPE_NOT_ON_ROOT,
+		.file_offset = offsetof(struct mem_cgroup, events_file),
 		.seq_show = memory_events_show,
 	},
 	{ }	/* terminate */
@@ -5322,11 +5294,6 @@ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
 	ret = try_charge(memcg, gfp_mask, nr_pages);
 
 	css_put(&memcg->css);
-
-	if (ret == -EINTR) {
-		memcg = root_mem_cgroup;
-		ret = 0;
-	}
 out:
 	*memcgp = memcg;
 	return ret;
@@ -5541,7 +5508,7 @@ void mem_cgroup_uncharge_list(struct list_head *page_list)
 }
 
 /**
- * mem_cgroup_migrate - migrate a charge to another page
+ * mem_cgroup_replace_page - migrate a charge to another page
  * @oldpage: currently charged page
  * @newpage: page to transfer the charge to
  * @lrucare: either or both pages might be on the LRU already
@@ -5550,16 +5517,13 @@ void mem_cgroup_uncharge_list(struct list_head *page_list)
  *
  * Both pages must be locked, @newpage->mapping must be set up.
  */
-void mem_cgroup_migrate(struct page *oldpage, struct page *newpage,
-			bool lrucare)
+void mem_cgroup_replace_page(struct page *oldpage, struct page *newpage)
 {
 	struct mem_cgroup *memcg;
 	int isolated;
 
 	VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage);
 	VM_BUG_ON_PAGE(!PageLocked(newpage), newpage);
-	VM_BUG_ON_PAGE(!lrucare && PageLRU(oldpage), oldpage);
-	VM_BUG_ON_PAGE(!lrucare && PageLRU(newpage), newpage);
 	VM_BUG_ON_PAGE(PageAnon(oldpage) != PageAnon(newpage), newpage);
 	VM_BUG_ON_PAGE(PageTransHuge(oldpage) != PageTransHuge(newpage),
 		       newpage);
@@ -5571,25 +5535,16 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage,
 	if (newpage->mem_cgroup)
 		return;
 
-	/*
-	 * Swapcache readahead pages can get migrated before being
-	 * charged, and migration from compaction can happen to an
-	 * uncharged page when the PFN walker finds a page that
-	 * reclaim just put back on the LRU but has not released yet.
-	 */
+	/* Swapcache readahead pages can get replaced before being charged */
 	memcg = oldpage->mem_cgroup;
 	if (!memcg)
 		return;
 
-	if (lrucare)
-		lock_page_lru(oldpage, &isolated);
-
+	lock_page_lru(oldpage, &isolated);
 	oldpage->mem_cgroup = NULL;
+	unlock_page_lru(oldpage, isolated);
 
-	if (lrucare)
-		unlock_page_lru(oldpage, isolated);
-
-	commit_charge(newpage, memcg, lrucare);
+	commit_charge(newpage, memcg, true);
 }
 
 /*