Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Johannes Weiner <hannes@cmpxchg.org>
To:     Andrew Morton <akpm@linux-foundation.org>
Cc:     Leon Yang <lnyng@fb.com>, Chris Down <chris@chrisdown.name>,
        Roman Gushchin <guro@fb.com>, Michal Hocko <mhocko@suse.com>,
        linux-mm@kvack.org, cgroups@vger.kernel.org,
        linux-kernel@vger.kernel.org, kernel-team@fb.com
Subject: [PATCH] mm: memcontrol: fix occasional OOMs due to proportional memory.low reclaim
Date:   Tue, 17 Aug 2021 14:05:06 -0400
Message-Id: <20210817180506.220056-1-hannes@cmpxchg.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

We've noticed occasional OOM killing when memory.low settings are in
effect for cgroups. This is unexpected and undesirable as memory.low
is supposed to express non-OOMing memory priorities between cgroups.

The reason for this is proportional memory.low reclaim. When cgroups
are below their memory.low threshold, reclaim passes them over in the
first round, and then retries if it couldn't find pages anywhere else.
But when cgroups are slighly above their memory.low setting, page scan
force is scaled down and diminished in proportion to the overage, to
the point where it can cause reclaim to fail as well - only in that
case we currently don't retry, and instead trigger OOM.

To fix this, hook proportional reclaim into the same retry logic we
have in place for when cgroups are skipped entirely. This way if
reclaim fails and some cgroups were scanned with dimished pressure,
we'll try another full-force cycle before giving up and OOMing.

Reported-by: Leon Yang <lnyng@fb.com>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
---
 include/linux/memcontrol.h | 29 +++++++++++++++--------------
 mm/vmscan.c                | 27 +++++++++++++++++++--------
 2 files changed, 34 insertions(+), 22 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index bfe5c486f4ad..24797929d8a1 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -612,12 +612,15 @@ static inline bool mem_cgroup_disabled(void)
 	return !cgroup_subsys_enabled(memory_cgrp_subsys);
 }
 
-static inline unsigned long mem_cgroup_protection(struct mem_cgroup *root,
-						  struct mem_cgroup *memcg,
-						  bool in_low_reclaim)
+static inline void mem_cgroup_protection(struct mem_cgroup *root,
+					 struct mem_cgroup *memcg,
+					 unsigned long *min,
+					 unsigned long *low)
 {
+	*min = *low = 0;
+
 	if (mem_cgroup_disabled())
-		return 0;
+		return;
 
 	/*
 	 * There is no reclaim protection applied to a targeted reclaim.
@@ -653,13 +656,10 @@ static inline unsigned long mem_cgroup_protection(struct mem_cgroup *root,
 	 *
 	 */
 	if (root == memcg)
-		return 0;
-
-	if (in_low_reclaim)
-		return READ_ONCE(memcg->memory.emin);
+		return;
 
-	return max(READ_ONCE(memcg->memory.emin),
-		   READ_ONCE(memcg->memory.elow));
+	*min = READ_ONCE(memcg->memory.emin);
+	*low = READ_ONCE(memcg->memory.elow);
 }
 
 void mem_cgroup_calculate_protection(struct mem_cgroup *root,
@@ -1147,11 +1147,12 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm,
 {
 }
 
-static inline unsigned long mem_cgroup_protection(struct mem_cgroup *root,
-						  struct mem_cgroup *memcg,
-						  bool in_low_reclaim)
+static inline void mem_cgroup_protection(struct mem_cgroup *root,
+					 struct mem_cgroup *memcg,
+					 unsigned long *min,
+					 unsigned long *low)
 {
-	return 0;
+	*min = *low = 0;
 }
 
 static inline void mem_cgroup_calculate_protection(struct mem_cgroup *root,
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 4620df62f0ff..701106e1829c 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -100,9 +100,12 @@ struct scan_control {
 	unsigned int may_swap:1;
 
 	/*
-	 * Cgroups are not reclaimed below their configured memory.low,
-	 * unless we threaten to OOM. If any cgroups are skipped due to
-	 * memory.low and nothing was reclaimed, go back for memory.low.
+	 * Cgroup memory below memory.low is protected as long as we
+	 * don't threaten to OOM. If any cgroup is reclaimed at
+	 * reduced force or passed over entirely due to its memory.low
+	 * setting (memcg_low_skipped), and nothing is reclaimed as a
+	 * result, then go back back for one more cycle that reclaims
+	 * the protected memory (memcg_low_reclaim) to avert OOM.
 	 */
 	unsigned int memcg_low_reclaim:1;
 	unsigned int memcg_low_skipped:1;
@@ -2537,15 +2540,14 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
 	for_each_evictable_lru(lru) {
 		int file = is_file_lru(lru);
 		unsigned long lruvec_size;
+		unsigned long low, min;
 		unsigned long scan;
-		unsigned long protection;
 
 		lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx);
-		protection = mem_cgroup_protection(sc->target_mem_cgroup,
-						   memcg,
-						   sc->memcg_low_reclaim);
+		mem_cgroup_protection(sc->target_mem_cgroup, memcg,
+				      &min, &low);
 
-		if (protection) {
+		if (min || low) {
 			/*
 			 * Scale a cgroup's reclaim pressure by proportioning
 			 * its current usage to its memory.low or memory.min
@@ -2576,6 +2578,15 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
 			 * hard protection.
 			 */
 			unsigned long cgroup_size = mem_cgroup_size(memcg);
+			unsigned long protection;
+
+			/* memory.low scaling, make sure we retry before OOM */
+			if (!sc->memcg_low_reclaim && low > min) {
+				protection = low;
+				sc->memcg_low_skipped = 1;
+			} else {
+				protection = min;
+			}
 
 			/* Avoid TOCTOU with earlier protection check */
 			cgroup_size = max(cgroup_size, protection);
-- 
2.32.0