1 files changed, 31 insertions, 22 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6b90d184e9c0..9a8e688724b1 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -996,7 +996,7 @@ static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg)
 	int nid, zid;
 	int i;
 
-	while ((memcg = parent_mem_cgroup(memcg))) {
+	for (; memcg; memcg = parent_mem_cgroup(memcg)) {
 		for_each_node(nid) {
 			for (zid = 0; zid < MAX_NR_ZONES; zid++) {
 				mz = &memcg->nodeinfo[nid]->zoneinfo[zid];
@@ -2055,6 +2055,15 @@ retry:
 		     current->flags & PF_EXITING))
 		goto force;
 
+	/*
+	 * Prevent unbounded recursion when reclaim operations need to
+	 * allocate memory. This might exceed the limits temporarily,
+	 * but we prefer facilitating memory reclaim and getting back
+	 * under the limit over triggering OOM kills in these cases.
+	 */
+	if (unlikely(current->flags & PF_MEMALLOC))
+		goto force;
+
 	if (unlikely(task_in_memcg_oom(current)))
 		goto nomem;
 
@@ -4141,24 +4150,6 @@ static void mem_cgroup_id_get_many(struct mem_cgroup *memcg, unsigned int n)
 	atomic_add(n, &memcg->id.ref);
 }
 
-static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg)
-{
-	while (!atomic_inc_not_zero(&memcg->id.ref)) {
-		/*
-		 * The root cgroup cannot be destroyed, so it's refcount must
-		 * always be >= 1.
-		 */
-		if (WARN_ON_ONCE(memcg == root_mem_cgroup)) {
-			VM_BUG_ON(1);
-			break;
-		}
-		memcg = parent_mem_cgroup(memcg);
-		if (!memcg)
-			memcg = root_mem_cgroup;
-	}
-	return memcg;
-}
-
 static void mem_cgroup_id_put_many(struct mem_cgroup *memcg, unsigned int n)
 {
 	if (atomic_sub_and_test(n, &memcg->id.ref)) {
@@ -4487,9 +4478,9 @@ static int mem_cgroup_do_precharge(unsigned long count)
 		return ret;
 	}
 
-	/* Try charges one by one with reclaim */
+	/* Try charges one by one with reclaim, but do not retry */
 	while (count--) {
-		ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_NORETRY, 1);
+		ret = try_charge(mc.to, GFP_KERNEL | __GFP_NORETRY, 1);
 		if (ret)
 			return ret;
 		mc.precharge++;
@@ -5585,7 +5576,7 @@ static void uncharge_list(struct list_head *page_list)
 		next = page->lru.next;
 
 		VM_BUG_ON_PAGE(PageLRU(page), page);
-		VM_BUG_ON_PAGE(page_count(page), page);
+		VM_BUG_ON_PAGE(!PageHWPoison(page) && page_count(page), page);
 
 		if (!page->mem_cgroup)
 			continue;
@@ -5742,6 +5733,24 @@ static int __init mem_cgroup_init(void)
 subsys_initcall(mem_cgroup_init);
 
 #ifdef CONFIG_MEMCG_SWAP
+static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg)
+{
+	while (!atomic_inc_not_zero(&memcg->id.ref)) {
+		/*
+		 * The root cgroup cannot be destroyed, so it's refcount must
+		 * always be >= 1.
+		 */
+		if (WARN_ON_ONCE(memcg == root_mem_cgroup)) {
+			VM_BUG_ON(1);
+			break;
+		}
+		memcg = parent_mem_cgroup(memcg);
+		if (!memcg)
+			memcg = root_mem_cgroup;
+	}
+	return memcg;
+}
+
 /**
  * mem_cgroup_swapout - transfer a memsw charge to swap
  * @page: page whose memsw charge to transfer