mm/vmscan: wake up flushers conditionally to avoid cgroup OOM

Commit 14aa8b2d5c2e ("mm/mglru: don't sync disk for each aging cycle")
removed the opportunity to wake up flushers during the MGLRU page
reclamation process can lead to an increased likelihood of triggering OOM
when encountering many dirty pages during reclamation on MGLRU.

This leads to premature OOM if there are too many dirty pages in cgroup:
Killed

dd invoked oom-killer: gfp_mask=0x101cca(GFP_HIGHUSER_MOVABLE|__GFP_WRITE),
order=0, oom_score_adj=0

Call Trace:
  <TASK>
  dump_stack_lvl+0x5f/0x80
  dump_stack+0x14/0x20
  dump_header+0x46/0x1b0
  oom_kill_process+0x104/0x220
  out_of_memory+0x112/0x5a0
  mem_cgroup_out_of_memory+0x13b/0x150
  try_charge_memcg+0x44f/0x5c0
  charge_memcg+0x34/0x50
  __mem_cgroup_charge+0x31/0x90
  filemap_add_folio+0x4b/0xf0
  __filemap_get_folio+0x1a4/0x5b0
  ? srso_return_thunk+0x5/0x5f
  ? __block_commit_write+0x82/0xb0
  ext4_da_write_begin+0xe5/0x270
  generic_perform_write+0x134/0x2b0
  ext4_buffered_write_iter+0x57/0xd0
  ext4_file_write_iter+0x76/0x7d0
  ? selinux_file_permission+0x119/0x150
  ? srso_return_thunk+0x5/0x5f
  ? srso_return_thunk+0x5/0x5f
  vfs_write+0x30c/0x440
  ksys_write+0x65/0xe0
  __x64_sys_write+0x1e/0x30
  x64_sys_call+0x11c2/0x1d50
  do_syscall_64+0x47/0x110
  entry_SYSCALL_64_after_hwframe+0x76/0x7e

 memory: usage 308224kB, limit 308224kB, failcnt 2589
 swap: usage 0kB, limit 9007199254740988kB, failcnt 0

  ...
  file_dirty 303247360
  file_writeback 0
  ...

oom-kill:constraint=CONSTRAINT_MEMCG,nodemask=(null),cpuset=test,
mems_allowed=0,oom_memcg=/test,task_memcg=/test,task=dd,pid=4404,uid=0
Memory cgroup out of memory: Killed process 4404 (dd) total-vm:10512kB,
anon-rss:1152kB, file-rss:1824kB, shmem-rss:0kB, UID:0 pgtables:76kB
oom_score_adj:0

The flusher wake up was removed to decrease SSD wearing, but if we are
seeing all dirty folios at the tail of an LRU, not waking up the flusher
could lead to thrashing easily.  So wake it up when a memcg is about to
OOM due to dirty caches.

I did run the build kernel test[1] on V6, with -j16 1G memcg on my local
branch:

Without the patch(10 times):
user 1449.394
system 368.78 372.58 363.03 362.31 360.84 372.70 368.72 364.94 373.51
366.58 (avg 367.399)
real 164.883

With the V6 patch(10 times):
user 1447.525
system 360.87 360.63 372.39 364.09 368.49 365.15 359.93 362.04 359.72
354.60 (avg 362.79)
real 164.514

Test results show that this patch has about 1% performance improvement,
which should be caused by noise.

Link: https://lkml.kernel.org/r/20241026115714.1437435-1-jingxiangzeng.cas@gmail.com
Link: https://lore.kernel.org/all/CACePvbV4L-gRN9UKKuUnksfVJjOTq_5Sti2-e=pb_w51kucLKQ@mail.gmail.com/ [1]
Fixes: 14aa8b2d5c2e ("mm/mglru: don't sync disk for each aging cycle")
Suggested-by: Wei Xu <weixugc@google.com>
Signed-off-by: Zeng Jingxiang <linuszeng@tencent.com>
Signed-off-by: Kairui Song <kasong@tencent.com>
Reviewed-by: Wei Xu <weixugc@google.com>
Tested-by: Chris Li <chrisl@kernel.org>
Cc: T.J. Mercier <tjmercier@google.com>
Cc: Yu Zhao <yuzhao@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 22 insertions, 3 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index caba8e811ec5..76378bc257e3 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4284,6 +4284,7 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c
 		       int tier_idx)
 {
 	bool success;
+	bool dirty, writeback;
 	int gen = folio_lru_gen(folio);
 	int type = folio_is_file_lru(folio);
 	int zone = folio_zonenum(folio);
@@ -4329,9 +4330,17 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c
 		return true;
 	}
 
+	dirty = folio_test_dirty(folio);
+	writeback = folio_test_writeback(folio);
+	if (type == LRU_GEN_FILE && dirty) {
+		sc->nr.file_taken += delta;
+		if (!writeback)
+			sc->nr.unqueued_dirty += delta;
+	}
+
 	/* waiting for writeback */
-	if (folio_test_locked(folio) || folio_test_writeback(folio) ||
-	    (type == LRU_GEN_FILE && folio_test_dirty(folio))) {
+	if (folio_test_locked(folio) || writeback ||
+	    (type == LRU_GEN_FILE && dirty)) {
 		gen = folio_inc_gen(lruvec, folio, true);
 		list_move(&folio->lru, &lrugen->folios[gen][type][zone]);
 		return true;
@@ -4447,7 +4456,8 @@ static int scan_folios(struct lruvec *lruvec, struct scan_control *sc,
 	trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, MAX_LRU_BATCH,
 				scanned, skipped, isolated,
 				type ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON);
-
+	if (type == LRU_GEN_FILE)
+		sc->nr.file_taken += isolated;
 	/*
 	 * There might not be eligible folios due to reclaim_idx. Check the
 	 * remaining to prevent livelock if it's not making progress.
@@ -4581,6 +4591,7 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap
 		return scanned;
 retry:
 	reclaimed = shrink_folio_list(&list, pgdat, sc, &stat, false);
+	sc->nr.unqueued_dirty += stat.nr_unqueued_dirty;
 	sc->nr_reclaimed += reclaimed;
 	trace_mm_vmscan_lru_shrink_inactive(pgdat->node_id,
 			scanned, reclaimed, &stat, sc->priority,
@@ -4789,6 +4800,13 @@ static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
 		cond_resched();
 	}
 
+	/*
+	 * If too many file cache in the coldest generation can't be evicted
+	 * due to being dirty, wake up the flusher.
+	 */
+	if (sc->nr.unqueued_dirty && sc->nr.unqueued_dirty == sc->nr.file_taken)
+		wakeup_flusher_threads(WB_REASON_VMSCAN);
+
 	/* whether this lruvec should be rotated */
 	return nr_to_scan < 0;
 }
@@ -5934,6 +5952,7 @@ static void shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 	bool reclaimable = false;
 
 	if (lru_gen_enabled() && root_reclaim(sc)) {
+		memset(&sc->nr, 0, sizeof(sc->nr));
 		lru_gen_shrink_node(pgdat, sc);
 		return;
 	}