1 files changed, 133 insertions, 91 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 194721839cf5..eaa3accb01e7 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -302,6 +302,7 @@ struct mem_cgroup {
 
 	bool		oom_lock;
 	atomic_t	under_oom;
+	atomic_t	oom_wakeups;
 
 	atomic_t	refcnt;
 
@@ -379,7 +380,7 @@ struct mem_cgroup {
 static size_t memcg_size(void)
 {
 	return sizeof(struct mem_cgroup) +
-		nr_node_ids * sizeof(struct mem_cgroup_per_node);
+		nr_node_ids * sizeof(struct mem_cgroup_per_node *);
 }
 
 /* internal only representation about the status of kmem accounting. */
@@ -1220,7 +1221,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 			if (dead_count == iter->last_dead_count) {
 				smp_rmb();
 				last_visited = iter->last_visited;
-				if (last_visited &&
+				if (last_visited && last_visited != root &&
 				    !css_tryget(&last_visited->css))
 					last_visited = NULL;
 			}
@@ -1229,7 +1230,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 		memcg = __mem_cgroup_iter_next(root, last_visited);
 
 		if (reclaim) {
-			if (last_visited)
+			if (last_visited && last_visited != root)
 				css_put(&last_visited->css);
 
 			iter->last_visited = memcg;
@@ -2075,15 +2076,18 @@ static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
 	return total;
 }
 
+static DEFINE_SPINLOCK(memcg_oom_lock);
+
 /*
  * Check OOM-Killer is already running under our hierarchy.
  * If someone is running, return false.
- * Has to be called with memcg_oom_lock
  */
-static bool mem_cgroup_oom_lock(struct mem_cgroup *memcg)
+static bool mem_cgroup_oom_trylock(struct mem_cgroup *memcg)
 {
 	struct mem_cgroup *iter, *failed = NULL;
 
+	spin_lock(&memcg_oom_lock);
+
 	for_each_mem_cgroup_tree(iter, memcg) {
 		if (iter->oom_lock) {
 			/*
@@ -2097,33 +2101,33 @@ static bool mem_cgroup_oom_lock(struct mem_cgroup *memcg)
 			iter->oom_lock = true;
 	}
 
-	if (!failed)
-		return true;
-
-	/*
-	 * OK, we failed to lock the whole subtree so we have to clean up
-	 * what we set up to the failing subtree
-	 */
-	for_each_mem_cgroup_tree(iter, memcg) {
-		if (iter == failed) {
-			mem_cgroup_iter_break(memcg, iter);
-			break;
+	if (failed) {
+		/*
+		 * OK, we failed to lock the whole subtree so we have
+		 * to clean up what we set up to the failing subtree
+		 */
+		for_each_mem_cgroup_tree(iter, memcg) {
+			if (iter == failed) {
+				mem_cgroup_iter_break(memcg, iter);
+				break;
+			}
+			iter->oom_lock = false;
 		}
-		iter->oom_lock = false;
 	}
-	return false;
+
+	spin_unlock(&memcg_oom_lock);
+
+	return !failed;
 }
 
-/*
- * Has to be called with memcg_oom_lock
- */
-static int mem_cgroup_oom_unlock(struct mem_cgroup *memcg)
+static void mem_cgroup_oom_unlock(struct mem_cgroup *memcg)
 {
 	struct mem_cgroup *iter;
 
+	spin_lock(&memcg_oom_lock);
 	for_each_mem_cgroup_tree(iter, memcg)
 		iter->oom_lock = false;
-	return 0;
+	spin_unlock(&memcg_oom_lock);
 }
 
 static void mem_cgroup_mark_under_oom(struct mem_cgroup *memcg)
@@ -2147,7 +2151,6 @@ static void mem_cgroup_unmark_under_oom(struct mem_cgroup *memcg)
 		atomic_add_unless(&iter->under_oom, -1, 0);
 }
 
-static DEFINE_SPINLOCK(memcg_oom_lock);
 static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq);
 
 struct oom_wait_info {
@@ -2177,6 +2180,7 @@ static int memcg_oom_wake_function(wait_queue_t *wait,
 
 static void memcg_wakeup_oom(struct mem_cgroup *memcg)
 {
+	atomic_inc(&memcg->oom_wakeups);
 	/* for filtering, pass "memcg" as argument. */
 	__wake_up(&memcg_oom_waitq, TASK_NORMAL, 0, memcg);
 }
@@ -2187,57 +2191,97 @@ static void memcg_oom_recover(struct mem_cgroup *memcg)
 		memcg_wakeup_oom(memcg);
 }
 
-/*
- * try to call OOM killer. returns false if we should exit memory-reclaim loop.
+static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
+{
+	if (!current->memcg_oom.may_oom)
+		return;
+	/*
+	 * 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.
+	 */
+	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 memcg OOM
+ * handler was enabled.
+ *
+ * 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 complete the OOM handling.
+ *
+ * Returns %true if an ongoing memcg OOM situation was detected and
+ * completed, %false otherwise.
  */
-static bool mem_cgroup_handle_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 oom_wait_info owait;
-	bool locked, need_to_kill;
+	bool locked;
+
+	/* OOM is global, do not handle */
+	if (!memcg)
+		return false;
+
+	if (!handle)
+		goto cleanup;
 
 	owait.memcg = memcg;
 	owait.wait.flags = 0;
 	owait.wait.func = memcg_oom_wake_function;
 	owait.wait.private = current;
 	INIT_LIST_HEAD(&owait.wait.task_list);
-	need_to_kill = true;
-	mem_cgroup_mark_under_oom(memcg);
 
-	/* At first, try to OOM lock hierarchy under memcg.*/
-	spin_lock(&memcg_oom_lock);
-	locked = mem_cgroup_oom_lock(memcg);
-	/*
-	 * Even if signal_pending(), we can't quit charge() loop without
-	 * accounting. So, UNINTERRUPTIBLE is appropriate. But SIGKILL
-	 * under OOM is always welcomed, use TASK_KILLABLE here.
-	 */
 	prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE);
-	if (!locked || memcg->oom_kill_disable)
-		need_to_kill = false;
+	mem_cgroup_mark_under_oom(memcg);
+
+	locked = mem_cgroup_oom_trylock(memcg);
+
 	if (locked)
 		mem_cgroup_oom_notify(memcg);
-	spin_unlock(&memcg_oom_lock);
 
-	if (need_to_kill) {
+	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, mask, order);
+		mem_cgroup_out_of_memory(memcg, current->memcg_oom.gfp_mask,
+					 current->memcg_oom.order);
 	} else {
 		schedule();
+		mem_cgroup_unmark_under_oom(memcg);
 		finish_wait(&memcg_oom_waitq, &owait.wait);
 	}
-	spin_lock(&memcg_oom_lock);
-	if (locked)
-		mem_cgroup_oom_unlock(memcg);
-	memcg_wakeup_oom(memcg);
-	spin_unlock(&memcg_oom_lock);
 
-	mem_cgroup_unmark_under_oom(memcg);
-
-	if (test_thread_flag(TIF_MEMDIE) || fatal_signal_pending(current))
-		return false;
-	/* Give chance to dying process */
-	schedule_timeout_uninterruptible(1);
+	if (locked) {
+		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);
+	}
+cleanup:
+	current->memcg_oom.memcg = NULL;
+	css_put(&memcg->css);
 	return true;
 }
 
@@ -2550,12 +2594,11 @@ enum {
 	CHARGE_RETRY,		/* need to retry but retry is not bad */
 	CHARGE_NOMEM,		/* we can't do more. return -ENOMEM */
 	CHARGE_WOULDBLOCK,	/* GFP_WAIT wasn't set and no enough res. */
-	CHARGE_OOM_DIE,		/* the current is killed because of OOM */
 };
 
 static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 				unsigned int nr_pages, unsigned int min_pages,
-				bool oom_check)
+				bool invoke_oom)
 {
 	unsigned long csize = nr_pages * PAGE_SIZE;
 	struct mem_cgroup *mem_over_limit;
@@ -2612,14 +2655,10 @@ static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	if (mem_cgroup_wait_acct_move(mem_over_limit))
 		return CHARGE_RETRY;
 
-	/* If we don't need to call oom-killer at el, return immediately */
-	if (!oom_check)
-		return CHARGE_NOMEM;
-	/* check OOM */
-	if (!mem_cgroup_handle_oom(mem_over_limit, gfp_mask, get_order(csize)))
-		return CHARGE_OOM_DIE;
+	if (invoke_oom)
+		mem_cgroup_oom(mem_over_limit, gfp_mask, get_order(csize));
 
-	return CHARGE_RETRY;
+	return CHARGE_NOMEM;
 }
 
 /*
@@ -2663,6 +2702,9 @@ 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
@@ -2722,7 +2764,7 @@ again:
 	}
 
 	do {
-		bool oom_check;
+		bool invoke_oom = oom && !nr_oom_retries;
 
 		/* If killed, bypass charge */
 		if (fatal_signal_pending(current)) {
@@ -2730,14 +2772,8 @@ again:
 			goto bypass;
 		}
 
-		oom_check = false;
-		if (oom && !nr_oom_retries) {
-			oom_check = true;
-			nr_oom_retries = MEM_CGROUP_RECLAIM_RETRIES;
-		}
-
-		ret = mem_cgroup_do_charge(memcg, gfp_mask, batch, nr_pages,
-		    oom_check);
+		ret = mem_cgroup_do_charge(memcg, gfp_mask, batch,
+					   nr_pages, invoke_oom);
 		switch (ret) {
 		case CHARGE_OK:
 			break;
@@ -2750,16 +2786,12 @@ again:
 			css_put(&memcg->css);
 			goto nomem;
 		case CHARGE_NOMEM: /* OOM routine works */
-			if (!oom) {
+			if (!oom || invoke_oom) {
 				css_put(&memcg->css);
 				goto nomem;
 			}
-			/* If oom, we never return -ENOMEM */
 			nr_oom_retries--;
 			break;
-		case CHARGE_OOM_DIE: /* Killed by OOM Killer */
-			css_put(&memcg->css);
-			goto bypass;
 		}
 	} while (ret != CHARGE_OK);
 
@@ -3186,11 +3218,11 @@ int memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s,
 	if (!s->memcg_params)
 		return -ENOMEM;
 
-	INIT_WORK(&s->memcg_params->destroy,
-			kmem_cache_destroy_work_func);
 	if (memcg) {
 		s->memcg_params->memcg = memcg;
 		s->memcg_params->root_cache = root_cache;
+		INIT_WORK(&s->memcg_params->destroy,
+				kmem_cache_destroy_work_func);
 	} else
 		s->memcg_params->is_root_cache = true;
 
@@ -5584,7 +5616,13 @@ static int compare_thresholds(const void *a, const void *b)
 	const struct mem_cgroup_threshold *_a = a;
 	const struct mem_cgroup_threshold *_b = b;
 
-	return _a->threshold - _b->threshold;
+	if (_a->threshold > _b->threshold)
+		return 1;
+
+	if (_a->threshold < _b->threshold)
+		return -1;
+
+	return 0;
 }
 
 static int mem_cgroup_oom_notify_cb(struct mem_cgroup *memcg)
@@ -6296,16 +6334,6 @@ mem_cgroup_css_online(struct cgroup *cont)
 
 	error = memcg_init_kmem(memcg, &mem_cgroup_subsys);
 	mutex_unlock(&memcg_create_mutex);
-	if (error) {
-		/*
-		 * We call put now because our (and parent's) refcnts
-		 * are already in place. mem_cgroup_put() will internally
-		 * call __mem_cgroup_free, so return directly
-		 */
-		mem_cgroup_put(memcg);
-		if (parent->use_hierarchy)
-			mem_cgroup_put(parent);
-	}
 	return error;
 }
 
@@ -6330,9 +6358,23 @@ static void mem_cgroup_invalidate_reclaim_iterators(struct mem_cgroup *memcg)
 static void mem_cgroup_css_offline(struct cgroup *cont)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+	struct cgroup *iter;
 
 	mem_cgroup_invalidate_reclaim_iterators(memcg);
+
+	/*
+	 * This requires that offlining is serialized.  Right now that is
+	 * guaranteed because css_killed_work_fn() holds the cgroup_mutex.
+	 */
+	rcu_read_lock();
+	cgroup_for_each_descendant_post(iter, cont) {
+		rcu_read_unlock();
+		mem_cgroup_reparent_charges(mem_cgroup_from_cont(iter));
+		rcu_read_lock();
+	}
+	rcu_read_unlock();
 	mem_cgroup_reparent_charges(memcg);
+
 	mem_cgroup_destroy_all_caches(memcg);
 }