Merge branch 'akpm' (patches from Andrew)

Merge misc fixes from Andrew Morton:
 "10 patches.

  Subsystems affected by this patch series: MAINTAINERS and mm (shmem,
  pagealloc, tracing, memcg, memory-failure, vmscan, kfence, and
  hugetlb)"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  hugetlb: don't pass page cache pages to restore_reserve_on_error
  kfence: fix is_kfence_address() for addresses below KFENCE_POOL_SIZE
  mm: vmscan: fix missing psi annotation for node_reclaim()
  mm/hwpoison: retry with shake_page() for unhandlable pages
  mm: memcontrol: fix occasional OOMs due to proportional memory.low reclaim
  MAINTAINERS: update ClangBuiltLinux IRC chat
  mmflags.h: add missing __GFP_ZEROTAGS and __GFP_SKIP_KASAN_POISON names
  mm/page_alloc: don't corrupt pcppage_migratetype
  Revert "mm: swap: check if swap backing device is congested or not"
  Revert "mm/shmem: fix shmem_swapin() race with swapoff"

1 files changed, 22 insertions, 8 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 4620df62f0ff..eeae2f6bc532 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 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 @@ out:
 	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 @@ out:
 			 * 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);
@@ -4413,11 +4424,13 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
 		.may_swap = 1,
 		.reclaim_idx = gfp_zone(gfp_mask),
 	};
+	unsigned long pflags;
 
 	trace_mm_vmscan_node_reclaim_begin(pgdat->node_id, order,
 					   sc.gfp_mask);
 
 	cond_resched();
+	psi_memstall_enter(&pflags);
 	fs_reclaim_acquire(sc.gfp_mask);
 	/*
 	 * We need to be able to allocate from the reserves for RECLAIM_UNMAP
@@ -4442,6 +4455,7 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
 	current->flags &= ~PF_SWAPWRITE;
 	memalloc_noreclaim_restore(noreclaim_flag);
 	fs_reclaim_release(sc.gfp_mask);
+	psi_memstall_leave(&pflags);
 
 	trace_mm_vmscan_node_reclaim_end(sc.nr_reclaimed);