1 files changed, 160 insertions, 127 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 7acf43bf04a2..6c055929c8cc 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -59,6 +59,8 @@
 #include <trace/events/vmscan.h>
 
 struct cgroup_subsys mem_cgroup_subsys __read_mostly;
+EXPORT_SYMBOL(mem_cgroup_subsys);
+
 #define MEM_CGROUP_RECLAIM_RETRIES	5
 static struct mem_cgroup *root_mem_cgroup __read_mostly;
 
@@ -800,7 +802,7 @@ static unsigned long mem_cgroup_nr_lru_pages(struct mem_cgroup *memcg,
 	int nid;
 	u64 total = 0;
 
-	for_each_node_state(nid, N_HIGH_MEMORY)
+	for_each_node_state(nid, N_MEMORY)
 		total += mem_cgroup_node_nr_lru_pages(memcg, nid, lru_mask);
 	return total;
 }
@@ -1015,13 +1017,10 @@ 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)
+void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx)
 {
 	struct mem_cgroup *memcg;
 
-	if (!mm)
-		return;
-
 	rcu_read_lock();
 	memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
 	if (unlikely(!memcg))
@@ -1040,7 +1039,7 @@ void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx)
 out:
 	rcu_read_unlock();
 }
-EXPORT_SYMBOL(mem_cgroup_count_vm_event);
+EXPORT_SYMBOL(__mem_cgroup_count_vm_event);
 
 /**
  * mem_cgroup_zone_lruvec - get the lru list vector for a zone and memcg
@@ -1055,12 +1054,24 @@ struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone,
 				      struct mem_cgroup *memcg)
 {
 	struct mem_cgroup_per_zone *mz;
+	struct lruvec *lruvec;
 
-	if (mem_cgroup_disabled())
-		return &zone->lruvec;
+	if (mem_cgroup_disabled()) {
+		lruvec = &zone->lruvec;
+		goto out;
+	}
 
 	mz = mem_cgroup_zoneinfo(memcg, zone_to_nid(zone), zone_idx(zone));
-	return &mz->lruvec;
+	lruvec = &mz->lruvec;
+out:
+	/*
+	 * Since a node can be onlined after the mem_cgroup was created,
+	 * we have to be prepared to initialize lruvec->zone here;
+	 * and if offlined then reonlined, we need to reinitialize it.
+	 */
+	if (unlikely(lruvec->zone != zone))
+		lruvec->zone = zone;
+	return lruvec;
 }
 
 /*
@@ -1087,9 +1098,12 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone)
 	struct mem_cgroup_per_zone *mz;
 	struct mem_cgroup *memcg;
 	struct page_cgroup *pc;
+	struct lruvec *lruvec;
 
-	if (mem_cgroup_disabled())
-		return &zone->lruvec;
+	if (mem_cgroup_disabled()) {
+		lruvec = &zone->lruvec;
+		goto out;
+	}
 
 	pc = lookup_page_cgroup(page);
 	memcg = pc->mem_cgroup;
@@ -1107,7 +1121,16 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone)
 		pc->mem_cgroup = memcg = root_mem_cgroup;
 
 	mz = page_cgroup_zoneinfo(memcg, page);
-	return &mz->lruvec;
+	lruvec = &mz->lruvec;
+out:
+	/*
+	 * Since a node can be onlined after the mem_cgroup was created,
+	 * we have to be prepared to initialize lruvec->zone here;
+	 * and if offlined then reonlined, we need to reinitialize it.
+	 */
+	if (unlikely(lruvec->zone != zone))
+		lruvec->zone = zone;
+	return lruvec;
 }
 
 /**
@@ -1452,21 +1475,30 @@ static int mem_cgroup_count_children(struct mem_cgroup *memcg)
 static u64 mem_cgroup_get_limit(struct mem_cgroup *memcg)
 {
 	u64 limit;
-	u64 memsw;
 
 	limit = res_counter_read_u64(&memcg->res, RES_LIMIT);
-	limit += total_swap_pages << PAGE_SHIFT;
 
-	memsw = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
 	/*
-	 * If memsw is finite and limits the amount of swap space available
-	 * to this memcg, return that limit.
+	 * Do not consider swap space if we cannot swap due to swappiness
 	 */
-	return min(limit, memsw);
+	if (mem_cgroup_swappiness(memcg)) {
+		u64 memsw;
+
+		limit += total_swap_pages << PAGE_SHIFT;
+		memsw = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
+
+		/*
+		 * If memsw is finite and limits the amount of swap space
+		 * available to this memcg, return that limit.
+		 */
+		limit = min(limit, memsw);
+	}
+
+	return limit;
 }
 
-void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
-			      int order)
+static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
+				     int order)
 {
 	struct mem_cgroup *iter;
 	unsigned long chosen_points = 0;
@@ -1611,9 +1643,9 @@ static void mem_cgroup_may_update_nodemask(struct mem_cgroup *memcg)
 		return;
 
 	/* make a nodemask where this memcg uses memory from */
-	memcg->scan_nodes = node_states[N_HIGH_MEMORY];
+	memcg->scan_nodes = node_states[N_MEMORY];
 
-	for_each_node_mask(nid, node_states[N_HIGH_MEMORY]) {
+	for_each_node_mask(nid, node_states[N_MEMORY]) {
 
 		if (!test_mem_cgroup_node_reclaimable(memcg, nid, false))
 			node_clear(nid, memcg->scan_nodes);
@@ -1684,7 +1716,7 @@ static bool mem_cgroup_reclaimable(struct mem_cgroup *memcg, bool noswap)
 	/*
 	 * Check rest of nodes.
 	 */
-	for_each_node_state(nid, N_HIGH_MEMORY) {
+	for_each_node_state(nid, N_MEMORY) {
 		if (node_isset(nid, memcg->scan_nodes))
 			continue;
 		if (test_mem_cgroup_node_reclaimable(memcg, nid, noswap))
@@ -2337,7 +2369,6 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
 again:
 	if (*ptr) { /* css should be a valid one */
 		memcg = *ptr;
-		VM_BUG_ON(css_is_removed(&memcg->css));
 		if (mem_cgroup_is_root(memcg))
 			goto done;
 		if (nr_pages == 1 && consume_stock(memcg))
@@ -2477,9 +2508,9 @@ static void __mem_cgroup_cancel_local_charge(struct mem_cgroup *memcg,
 
 /*
  * A helper function to get mem_cgroup from ID. must be called under
- * rcu_read_lock(). The caller must check css_is_removed() or some if
- * it's concern. (dropping refcnt from swap can be called against removed
- * memcg.)
+ * rcu_read_lock().  The caller is responsible for calling css_tryget if
+ * the mem_cgroup is used for charging. (dropping refcnt from swap can be
+ * called against removed memcg.)
  */
 static struct mem_cgroup *mem_cgroup_lookup(unsigned short id)
 {
@@ -2676,13 +2707,6 @@ static int mem_cgroup_move_account(struct page *page,
 	/* caller should have done css_get */
 	pc->mem_cgroup = to;
 	mem_cgroup_charge_statistics(to, anon, nr_pages);
-	/*
-	 * We charges against "to" which may not have any tasks. Then, "to"
-	 * can be under rmdir(). But in current implementation, caller of
-	 * this function is just force_empty() and move charge, so it's
-	 * guaranteed that "to" is never removed. So, we don't check rmdir
-	 * status here.
-	 */
 	move_unlock_mem_cgroup(from, &flags);
 	ret = 0;
 unlock:
@@ -2696,10 +2720,27 @@ out:
 	return ret;
 }
 
-/*
- * move charges to its parent.
+/**
+ * mem_cgroup_move_parent - moves page to the parent group
+ * @page: the page to move
+ * @pc: page_cgroup of the page
+ * @child: page's cgroup
+ *
+ * move charges to its parent or the root cgroup if the group has no
+ * parent (aka use_hierarchy==0).
+ * Although this might fail (get_page_unless_zero, isolate_lru_page or
+ * mem_cgroup_move_account fails) the failure is always temporary and
+ * it signals a race with a page removal/uncharge or migration. In the
+ * first case the page is on the way out and it will vanish from the LRU
+ * on the next attempt and the call should be retried later.
+ * Isolation from the LRU fails only if page has been isolated from
+ * the LRU since we looked at it and that usually means either global
+ * reclaim or migration going on. The page will either get back to the
+ * LRU or vanish.
+ * Finaly mem_cgroup_move_account fails only if the page got uncharged
+ * (!PageCgroupUsed) or moved to a different group. The page will
+ * disappear in the next attempt.
  */
-
 static int mem_cgroup_move_parent(struct page *page,
 				  struct page_cgroup *pc,
 				  struct mem_cgroup *child)
@@ -2709,9 +2750,7 @@ static int mem_cgroup_move_parent(struct page *page,
 	unsigned long uninitialized_var(flags);
 	int ret;
 
-	/* Is ROOT ? */
-	if (mem_cgroup_is_root(child))
-		return -EINVAL;
+	VM_BUG_ON(mem_cgroup_is_root(child));
 
 	ret = -EBUSY;
 	if (!get_page_unless_zero(page))
@@ -2728,8 +2767,10 @@ static int mem_cgroup_move_parent(struct page *page,
 	if (!parent)
 		parent = root_mem_cgroup;
 
-	if (nr_pages > 1)
+	if (nr_pages > 1) {
+		VM_BUG_ON(!PageTransHuge(page));
 		flags = compound_lock_irqsave(page);
+	}
 
 	ret = mem_cgroup_move_account(page, nr_pages,
 				pc, child, parent);
@@ -2871,7 +2912,6 @@ __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *memcg,
 		return;
 	if (!memcg)
 		return;
-	cgroup_exclude_rmdir(&memcg->css);
 
 	__mem_cgroup_commit_charge(memcg, page, 1, ctype, true);
 	/*
@@ -2885,12 +2925,6 @@ __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *memcg,
 		swp_entry_t ent = {.val = page_private(page)};
 		mem_cgroup_uncharge_swap(ent);
 	}
-	/*
-	 * At swapin, we may charge account against cgroup which has no tasks.
-	 * So, rmdir()->pre_destroy() can be called while we do this charge.
-	 * In that case, we need to call pre_destroy() again. check it here.
-	 */
-	cgroup_release_and_wakeup_rmdir(&memcg->css);
 }
 
 void mem_cgroup_commit_charge_swapin(struct page *page,
@@ -3338,8 +3372,7 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg,
 
 	if (!memcg)
 		return;
-	/* blocks rmdir() */
-	cgroup_exclude_rmdir(&memcg->css);
+
 	if (!migration_ok) {
 		used = oldpage;
 		unused = newpage;
@@ -3373,13 +3406,6 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg,
 	 */
 	if (anon)
 		mem_cgroup_uncharge_page(used);
-	/*
-	 * At migration, we may charge account against cgroup which has no
-	 * tasks.
-	 * So, rmdir()->pre_destroy() can be called while we do this charge.
-	 * In that case, we need to call pre_destroy() again. check it here.
-	 */
-	cgroup_release_and_wakeup_rmdir(&memcg->css);
 }
 
 /*
@@ -3679,30 +3705,32 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 	return nr_reclaimed;
 }
 
-/*
+/**
+ * mem_cgroup_force_empty_list - clears LRU of a group
+ * @memcg: group to clear
+ * @node: NUMA node
+ * @zid: zone id
+ * @lru: lru to to clear
+ *
  * Traverse a specified page_cgroup list and try to drop them all.  This doesn't
- * reclaim the pages page themselves - it just removes the page_cgroups.
- * Returns true if some page_cgroups were not freed, indicating that the caller
- * must retry this operation.
+ * reclaim the pages page themselves - pages are moved to the parent (or root)
+ * group.
  */
-static bool mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
+static void mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
 				int node, int zid, enum lru_list lru)
 {
-	struct mem_cgroup_per_zone *mz;
-	unsigned long flags, loop;
+	struct lruvec *lruvec;
+	unsigned long flags;
 	struct list_head *list;
 	struct page *busy;
 	struct zone *zone;
 
 	zone = &NODE_DATA(node)->node_zones[zid];
-	mz = mem_cgroup_zoneinfo(memcg, node, zid);
-	list = &mz->lruvec.lists[lru];
+	lruvec = mem_cgroup_zone_lruvec(zone, memcg);
+	list = &lruvec->lists[lru];
 
-	loop = mz->lru_size[lru];
-	/* give some margin against EBUSY etc...*/
-	loop += 256;
 	busy = NULL;
-	while (loop--) {
+	do {
 		struct page_cgroup *pc;
 		struct page *page;
 
@@ -3728,76 +3756,72 @@ static bool mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
 			cond_resched();
 		} else
 			busy = NULL;
-	}
-	return !list_empty(list);
+	} while (!list_empty(list));
 }
 
 /*
- * make mem_cgroup's charge to be 0 if there is no task.
+ * make mem_cgroup's charge to be 0 if there is no task by moving
+ * all the charges and pages to the parent.
  * This enables deleting this mem_cgroup.
+ *
+ * Caller is responsible for holding css reference on the memcg.
  */
-static int mem_cgroup_force_empty(struct mem_cgroup *memcg, bool free_all)
+static void mem_cgroup_reparent_charges(struct mem_cgroup *memcg)
 {
-	int ret;
-	int node, zid, shrink;
-	int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
-	struct cgroup *cgrp = memcg->css.cgroup;
+	int node, zid;
 
-	css_get(&memcg->css);
-
-	shrink = 0;
-	/* should free all ? */
-	if (free_all)
-		goto try_to_free;
-move_account:
 	do {
-		ret = -EBUSY;
-		if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children))
-			goto out;
 		/* This is for making all *used* pages to be on LRU. */
 		lru_add_drain_all();
 		drain_all_stock_sync(memcg);
-		ret = 0;
 		mem_cgroup_start_move(memcg);
-		for_each_node_state(node, N_HIGH_MEMORY) {
-			for (zid = 0; !ret && zid < MAX_NR_ZONES; zid++) {
+		for_each_node_state(node, N_MEMORY) {
+			for (zid = 0; zid < MAX_NR_ZONES; zid++) {
 				enum lru_list lru;
 				for_each_lru(lru) {
-					ret = mem_cgroup_force_empty_list(memcg,
+					mem_cgroup_force_empty_list(memcg,
 							node, zid, lru);
-					if (ret)
-						break;
 				}
 			}
-			if (ret)
-				break;
 		}
 		mem_cgroup_end_move(memcg);
 		memcg_oom_recover(memcg);
 		cond_resched();
-	/* "ret" should also be checked to ensure all lists are empty. */
-	} while (res_counter_read_u64(&memcg->res, RES_USAGE) > 0 || ret);
-out:
-	css_put(&memcg->css);
-	return ret;
 
-try_to_free:
+		/*
+		 * This is a safety check because mem_cgroup_force_empty_list
+		 * could have raced with mem_cgroup_replace_page_cache callers
+		 * so the lru seemed empty but the page could have been added
+		 * right after the check. RES_USAGE should be safe as we always
+		 * charge before adding to the LRU.
+		 */
+	} while (res_counter_read_u64(&memcg->res, RES_USAGE) > 0);
+}
+
+/*
+ * Reclaims as many pages from the given memcg as possible and moves
+ * the rest to the parent.
+ *
+ * Caller is responsible for holding css reference for memcg.
+ */
+static int mem_cgroup_force_empty(struct mem_cgroup *memcg)
+{
+	int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
+	struct cgroup *cgrp = memcg->css.cgroup;
+
 	/* returns EBUSY if there is a task or if we come here twice. */
-	if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children) || shrink) {
-		ret = -EBUSY;
-		goto out;
-	}
+	if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children))
+		return -EBUSY;
+
 	/* we call try-to-free pages for make this cgroup empty */
 	lru_add_drain_all();
 	/* try to free all pages in this cgroup */
-	shrink = 1;
 	while (nr_retries && res_counter_read_u64(&memcg->res, RES_USAGE) > 0) {
 		int progress;
 
-		if (signal_pending(current)) {
-			ret = -EINTR;
-			goto out;
-		}
+		if (signal_pending(current))
+			return -EINTR;
+
 		progress = try_to_free_mem_cgroup_pages(memcg, GFP_KERNEL,
 						false);
 		if (!progress) {
@@ -3808,13 +3832,23 @@ try_to_free:
 
 	}
 	lru_add_drain();
-	/* try move_account...there may be some *locked* pages. */
-	goto move_account;
+	mem_cgroup_reparent_charges(memcg);
+
+	return 0;
 }
 
 static int mem_cgroup_force_empty_write(struct cgroup *cont, unsigned int event)
 {
-	return mem_cgroup_force_empty(mem_cgroup_from_cont(cont), true);
+	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+	int ret;
+
+	if (mem_cgroup_is_root(memcg))
+		return -EINVAL;
+	css_get(&memcg->css);
+	ret = mem_cgroup_force_empty(memcg);
+	css_put(&memcg->css);
+
+	return ret;
 }
 
 
@@ -4087,7 +4121,7 @@ static int memcg_numa_stat_show(struct cgroup *cont, struct cftype *cft,
 
 	total_nr = mem_cgroup_nr_lru_pages(memcg, LRU_ALL);
 	seq_printf(m, "total=%lu", total_nr);
-	for_each_node_state(nid, N_HIGH_MEMORY) {
+	for_each_node_state(nid, N_MEMORY) {
 		node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid, LRU_ALL);
 		seq_printf(m, " N%d=%lu", nid, node_nr);
 	}
@@ -4095,7 +4129,7 @@ static int memcg_numa_stat_show(struct cgroup *cont, struct cftype *cft,
 
 	file_nr = mem_cgroup_nr_lru_pages(memcg, LRU_ALL_FILE);
 	seq_printf(m, "file=%lu", file_nr);
-	for_each_node_state(nid, N_HIGH_MEMORY) {
+	for_each_node_state(nid, N_MEMORY) {
 		node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid,
 				LRU_ALL_FILE);
 		seq_printf(m, " N%d=%lu", nid, node_nr);
@@ -4104,7 +4138,7 @@ static int memcg_numa_stat_show(struct cgroup *cont, struct cftype *cft,
 
 	anon_nr = mem_cgroup_nr_lru_pages(memcg, LRU_ALL_ANON);
 	seq_printf(m, "anon=%lu", anon_nr);
-	for_each_node_state(nid, N_HIGH_MEMORY) {
+	for_each_node_state(nid, N_MEMORY) {
 		node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid,
 				LRU_ALL_ANON);
 		seq_printf(m, " N%d=%lu", nid, node_nr);
@@ -4113,7 +4147,7 @@ static int memcg_numa_stat_show(struct cgroup *cont, struct cftype *cft,
 
 	unevictable_nr = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_UNEVICTABLE));
 	seq_printf(m, "unevictable=%lu", unevictable_nr);
-	for_each_node_state(nid, N_HIGH_MEMORY) {
+	for_each_node_state(nid, N_MEMORY) {
 		node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid,
 				BIT(LRU_UNEVICTABLE));
 		seq_printf(m, " N%d=%lu", nid, node_nr);
@@ -4736,7 +4770,7 @@ 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, &NODE_DATA(node)->node_zones[zone]);
+		lruvec_init(&mz->lruvec);
 		mz->usage_in_excess = 0;
 		mz->on_tree = false;
 		mz->memcg = memcg;
@@ -4920,7 +4954,7 @@ err_cleanup:
 }
 
 static struct cgroup_subsys_state * __ref
-mem_cgroup_create(struct cgroup *cont)
+mem_cgroup_css_alloc(struct cgroup *cont)
 {
 	struct mem_cgroup *memcg, *parent;
 	long error = -ENOMEM;
@@ -5001,14 +5035,14 @@ free_out:
 	return ERR_PTR(error);
 }
 
-static int mem_cgroup_pre_destroy(struct cgroup *cont)
+static void mem_cgroup_css_offline(struct cgroup *cont)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
 
-	return mem_cgroup_force_empty(memcg, false);
+	mem_cgroup_reparent_charges(memcg);
 }
 
-static void mem_cgroup_destroy(struct cgroup *cont)
+static void mem_cgroup_css_free(struct cgroup *cont)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
 
@@ -5598,16 +5632,15 @@ static void mem_cgroup_move_task(struct cgroup *cont,
 struct cgroup_subsys mem_cgroup_subsys = {
 	.name = "memory",
 	.subsys_id = mem_cgroup_subsys_id,
-	.create = mem_cgroup_create,
-	.pre_destroy = mem_cgroup_pre_destroy,
-	.destroy = mem_cgroup_destroy,
+	.css_alloc = mem_cgroup_css_alloc,
+	.css_offline = mem_cgroup_css_offline,
+	.css_free = mem_cgroup_css_free,
 	.can_attach = mem_cgroup_can_attach,
 	.cancel_attach = mem_cgroup_cancel_attach,
 	.attach = mem_cgroup_move_task,
 	.base_cftypes = mem_cgroup_files,
 	.early_init = 0,
 	.use_id = 1,
-	.__DEPRECATED_clear_css_refs = true,
 };
 
 #ifdef CONFIG_MEMCG_SWAP