1 files changed, 120 insertions, 88 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6728a7ae6f2d..26c6f4ec20f4 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -230,10 +230,30 @@ struct mem_cgroup {
 	 * the counter to account for memory usage
 	 */
 	struct res_counter res;
-	/*
-	 * the counter to account for mem+swap usage.
-	 */
-	struct res_counter memsw;
+
+	union {
+		/*
+		 * the counter to account for mem+swap usage.
+		 */
+		struct res_counter memsw;
+
+		/*
+		 * rcu_freeing is used only when freeing struct mem_cgroup,
+		 * so put it into a union to avoid wasting more memory.
+		 * It must be disjoint from the css field.  It could be
+		 * in a union with the res field, but res plays a much
+		 * larger part in mem_cgroup life than memsw, and might
+		 * be of interest, even at time of free, when debugging.
+		 * So share rcu_head with the less interesting memsw.
+		 */
+		struct rcu_head rcu_freeing;
+		/*
+		 * But when using vfree(), that cannot be done at
+		 * interrupt time, so we must then queue the work.
+		 */
+		struct work_struct work_freeing;
+	};
+
 	/*
 	 * Per cgroup active and inactive list, similar to the
 	 * per zone LRU lists.
@@ -1042,6 +1062,19 @@ struct lruvec *mem_cgroup_lru_add_list(struct zone *zone, struct page *page,
 
 	pc = lookup_page_cgroup(page);
 	memcg = pc->mem_cgroup;
+
+	/*
+	 * Surreptitiously switch any uncharged page to root:
+	 * an uncharged page off lru does nothing to secure
+	 * its former mem_cgroup from sudden removal.
+	 *
+	 * Our caller holds lru_lock, and PageCgroupUsed is updated
+	 * under page_cgroup lock: between them, they make all uses
+	 * of pc->mem_cgroup safe.
+	 */
+	if (!PageCgroupUsed(pc) && memcg != root_mem_cgroup)
+		pc->mem_cgroup = memcg = root_mem_cgroup;
+
 	mz = page_cgroup_zoneinfo(memcg, page);
 	/* compound_order() is stabilized through lru_lock */
 	MEM_CGROUP_ZSTAT(mz, lru) += 1 << compound_order(page);
@@ -2408,8 +2441,12 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 				       struct page *page,
 				       unsigned int nr_pages,
 				       struct page_cgroup *pc,
-				       enum charge_type ctype)
+				       enum charge_type ctype,
+				       bool lrucare)
 {
+	struct zone *uninitialized_var(zone);
+	bool was_on_lru = false;
+
 	lock_page_cgroup(pc);
 	if (unlikely(PageCgroupUsed(pc))) {
 		unlock_page_cgroup(pc);
@@ -2420,6 +2457,21 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 	 * we don't need page_cgroup_lock about tail pages, becase they are not
 	 * accessed by any other context at this point.
 	 */
+
+	/*
+	 * In some cases, SwapCache and FUSE(splice_buf->radixtree), the page
+	 * may already be on some other mem_cgroup's LRU.  Take care of it.
+	 */
+	if (lrucare) {
+		zone = page_zone(page);
+		spin_lock_irq(&zone->lru_lock);
+		if (PageLRU(page)) {
+			ClearPageLRU(page);
+			del_page_from_lru_list(zone, page, page_lru(page));
+			was_on_lru = true;
+		}
+	}
+
 	pc->mem_cgroup = memcg;
 	/*
 	 * We access a page_cgroup asynchronously without lock_page_cgroup().
@@ -2443,9 +2495,18 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 		break;
 	}
 
+	if (lrucare) {
+		if (was_on_lru) {
+			VM_BUG_ON(PageLRU(page));
+			SetPageLRU(page);
+			add_page_to_lru_list(zone, page, page_lru(page));
+		}
+		spin_unlock_irq(&zone->lru_lock);
+	}
+
 	mem_cgroup_charge_statistics(memcg, PageCgroupCache(pc), nr_pages);
 	unlock_page_cgroup(pc);
-	WARN_ON_ONCE(PageLRU(page));
+
 	/*
 	 * "charge_statistics" updated event counter. Then, check it.
 	 * Insert ancestor (and ancestor's ancestors), to softlimit RB-tree.
@@ -2643,7 +2704,7 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
 	ret = __mem_cgroup_try_charge(mm, gfp_mask, nr_pages, &memcg, oom);
 	if (ret == -ENOMEM)
 		return ret;
-	__mem_cgroup_commit_charge(memcg, page, nr_pages, pc, ctype);
+	__mem_cgroup_commit_charge(memcg, page, nr_pages, pc, ctype, false);
 	return 0;
 }
 
@@ -2663,35 +2724,6 @@ static void
 __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr,
 					enum charge_type ctype);
 
-static void
-__mem_cgroup_commit_charge_lrucare(struct page *page, struct mem_cgroup *memcg,
-					enum charge_type ctype)
-{
-	struct page_cgroup *pc = lookup_page_cgroup(page);
-	struct zone *zone = page_zone(page);
-	unsigned long flags;
-	bool removed = false;
-
-	/*
-	 * In some case, SwapCache, FUSE(splice_buf->radixtree), the page
-	 * is already on LRU. It means the page may on some other page_cgroup's
-	 * LRU. Take care of it.
-	 */
-	spin_lock_irqsave(&zone->lru_lock, flags);
-	if (PageLRU(page)) {
-		del_page_from_lru_list(zone, page, page_lru(page));
-		ClearPageLRU(page);
-		removed = true;
-	}
-	__mem_cgroup_commit_charge(memcg, page, 1, pc, ctype);
-	if (removed) {
-		add_page_to_lru_list(zone, page, page_lru(page));
-		SetPageLRU(page);
-	}
-	spin_unlock_irqrestore(&zone->lru_lock, flags);
-	return;
-}
-
 int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
 				gfp_t gfp_mask)
 {
@@ -2769,13 +2801,16 @@ static void
 __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *memcg,
 					enum charge_type ctype)
 {
+	struct page_cgroup *pc;
+
 	if (mem_cgroup_disabled())
 		return;
 	if (!memcg)
 		return;
 	cgroup_exclude_rmdir(&memcg->css);
 
-	__mem_cgroup_commit_charge_lrucare(page, memcg, ctype);
+	pc = lookup_page_cgroup(page);
+	__mem_cgroup_commit_charge(memcg, page, 1, pc, ctype, true);
 	/*
 	 * Now swap is on-memory. This means this page may be
 	 * counted both as mem and swap....double count.
@@ -3027,23 +3062,6 @@ void mem_cgroup_uncharge_end(void)
 	batch->memcg = NULL;
 }
 
-/*
- * A function for resetting pc->mem_cgroup for newly allocated pages.
- * This function should be called if the newpage will be added to LRU
- * before start accounting.
- */
-void mem_cgroup_reset_owner(struct page *newpage)
-{
-	struct page_cgroup *pc;
-
-	if (mem_cgroup_disabled())
-		return;
-
-	pc = lookup_page_cgroup(newpage);
-	VM_BUG_ON(PageCgroupUsed(pc));
-	pc->mem_cgroup = root_mem_cgroup;
-}
-
 #ifdef CONFIG_SWAP
 /*
  * called after __delete_from_swap_cache() and drop "page" account.
@@ -3248,7 +3266,7 @@ int mem_cgroup_prepare_migration(struct page *page,
 		ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
 	else
 		ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM;
-	__mem_cgroup_commit_charge(memcg, newpage, 1, pc, ctype);
+	__mem_cgroup_commit_charge(memcg, newpage, 1, pc, ctype, false);
 	return ret;
 }
 
@@ -3332,7 +3350,7 @@ void mem_cgroup_replace_page_cache(struct page *oldpage,
 	 * the newpage may be on LRU(or pagevec for LRU) already. We lock
 	 * LRU while we overwrite pc->mem_cgroup.
 	 */
-	__mem_cgroup_commit_charge_lrucare(newpage, memcg, type);
+	__mem_cgroup_commit_charge(memcg, newpage, 1, pc, type, true);
 }
 
 #ifdef CONFIG_DEBUG_VM
@@ -4414,6 +4432,9 @@ static void mem_cgroup_usage_unregister_event(struct cgroup *cgrp,
 	 */
 	BUG_ON(!thresholds);
 
+	if (!thresholds->primary)
+		goto unlock;
+
 	usage = mem_cgroup_usage(memcg, type == _MEMSWAP);
 
 	/* Check if a threshold crossed before removing */
@@ -4462,7 +4483,7 @@ swap_buffers:
 
 	/* To be sure that nobody uses thresholds */
 	synchronize_rcu();
-
+unlock:
 	mutex_unlock(&memcg->thresholds_lock);
 }
 
@@ -4581,10 +4602,9 @@ static int register_kmem_files(struct cgroup *cont, struct cgroup_subsys *ss)
 	return mem_cgroup_sockets_init(cont, ss);
 };
 
-static void kmem_cgroup_destroy(struct cgroup_subsys *ss,
-				struct cgroup *cont)
+static void kmem_cgroup_destroy(struct cgroup *cont)
 {
-	mem_cgroup_sockets_destroy(cont, ss);
+	mem_cgroup_sockets_destroy(cont);
 }
 #else
 static int register_kmem_files(struct cgroup *cont, struct cgroup_subsys *ss)
@@ -4592,8 +4612,7 @@ static int register_kmem_files(struct cgroup *cont, struct cgroup_subsys *ss)
 	return 0;
 }
 
-static void kmem_cgroup_destroy(struct cgroup_subsys *ss,
-				struct cgroup *cont)
+static void kmem_cgroup_destroy(struct cgroup *cont)
 {
 }
 #endif
@@ -4779,6 +4798,27 @@ out_free:
 }
 
 /*
+ * Helpers for freeing a vzalloc()ed mem_cgroup by RCU,
+ * but in process context.  The work_freeing structure is overlaid
+ * on the rcu_freeing structure, which itself is overlaid on memsw.
+ */
+static void vfree_work(struct work_struct *work)
+{
+	struct mem_cgroup *memcg;
+
+	memcg = container_of(work, struct mem_cgroup, work_freeing);
+	vfree(memcg);
+}
+static void vfree_rcu(struct rcu_head *rcu_head)
+{
+	struct mem_cgroup *memcg;
+
+	memcg = container_of(rcu_head, struct mem_cgroup, rcu_freeing);
+	INIT_WORK(&memcg->work_freeing, vfree_work);
+	schedule_work(&memcg->work_freeing);
+}
+
+/*
  * At destroying mem_cgroup, references from swap_cgroup can remain.
  * (scanning all at force_empty is too costly...)
  *
@@ -4801,9 +4841,9 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
 
 	free_percpu(memcg->stat);
 	if (sizeof(struct mem_cgroup) < PAGE_SIZE)
-		kfree(memcg);
+		kfree_rcu(memcg, rcu_freeing);
 	else
-		vfree(memcg);
+		call_rcu(&memcg->rcu_freeing, vfree_rcu);
 }
 
 static void mem_cgroup_get(struct mem_cgroup *memcg)
@@ -4885,7 +4925,7 @@ err_cleanup:
 }
 
 static struct cgroup_subsys_state * __ref
-mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
+mem_cgroup_create(struct cgroup *cont)
 {
 	struct mem_cgroup *memcg, *parent;
 	long error = -ENOMEM;
@@ -4947,20 +4987,18 @@ free_out:
 	return ERR_PTR(error);
 }
 
-static int mem_cgroup_pre_destroy(struct cgroup_subsys *ss,
-					struct cgroup *cont)
+static int mem_cgroup_pre_destroy(struct cgroup *cont)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
 
 	return mem_cgroup_force_empty(memcg, false);
 }
 
-static void mem_cgroup_destroy(struct cgroup_subsys *ss,
-				struct cgroup *cont)
+static void mem_cgroup_destroy(struct cgroup *cont)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
 
-	kmem_cgroup_destroy(ss, cont);
+	kmem_cgroup_destroy(cont);
 
 	mem_cgroup_put(memcg);
 }
@@ -5297,9 +5335,8 @@ static void mem_cgroup_clear_mc(void)
 	mem_cgroup_end_move(from);
 }
 
-static int mem_cgroup_can_attach(struct cgroup_subsys *ss,
-				struct cgroup *cgroup,
-				struct cgroup_taskset *tset)
+static int mem_cgroup_can_attach(struct cgroup *cgroup,
+				 struct cgroup_taskset *tset)
 {
 	struct task_struct *p = cgroup_taskset_first(tset);
 	int ret = 0;
@@ -5337,9 +5374,8 @@ static int mem_cgroup_can_attach(struct cgroup_subsys *ss,
 	return ret;
 }
 
-static void mem_cgroup_cancel_attach(struct cgroup_subsys *ss,
-				struct cgroup *cgroup,
-				struct cgroup_taskset *tset)
+static void mem_cgroup_cancel_attach(struct cgroup *cgroup,
+				     struct cgroup_taskset *tset)
 {
 	mem_cgroup_clear_mc();
 }
@@ -5454,9 +5490,8 @@ retry:
 	up_read(&mm->mmap_sem);
 }
 
-static void mem_cgroup_move_task(struct cgroup_subsys *ss,
-				struct cgroup *cont,
-				struct cgroup_taskset *tset)
+static void mem_cgroup_move_task(struct cgroup *cont,
+				 struct cgroup_taskset *tset)
 {
 	struct task_struct *p = cgroup_taskset_first(tset);
 	struct mm_struct *mm = get_task_mm(p);
@@ -5471,20 +5506,17 @@ static void mem_cgroup_move_task(struct cgroup_subsys *ss,
 		mem_cgroup_clear_mc();
 }
 #else	/* !CONFIG_MMU */
-static int mem_cgroup_can_attach(struct cgroup_subsys *ss,
-				struct cgroup *cgroup,
-				struct cgroup_taskset *tset)
+static int mem_cgroup_can_attach(struct cgroup *cgroup,
+				 struct cgroup_taskset *tset)
 {
 	return 0;
 }
-static void mem_cgroup_cancel_attach(struct cgroup_subsys *ss,
-				struct cgroup *cgroup,
-				struct cgroup_taskset *tset)
+static void mem_cgroup_cancel_attach(struct cgroup *cgroup,
+				     struct cgroup_taskset *tset)
 {
 }
-static void mem_cgroup_move_task(struct cgroup_subsys *ss,
-				struct cgroup *cont,
-				struct cgroup_taskset *tset)
+static void mem_cgroup_move_task(struct cgroup *cont,
+				 struct cgroup_taskset *tset)
 {
 }
 #endif