[PATCH] mm: vmscan: do not skip CMA while LRU is full of CMA folios

[liuhailong]

From: liuhailong <liuhailong@xxxxxxxx>

If the allocation flag isn't movable, commit 5da226dbfce3 ("mm:
skip CMA pages when they are not available") skips CMA during direct
reclamation. This generally speeds up the reclamation of non-movable
folios. However, in scenarios with limited system memory and a majority
of reclaimable folios in LRU being from CMA, this can result in prolonged
idle loops where the system reclaims nothing but consumes CPU.

I traced the process of a thread entering direct reclamation,
and printed the relevant information of the sc(scan_control).
__alloc_pages_direct_reclaim start
sc->priority:9 sc->nr_skipped_cma:32208  sc->nr_scanned:36  sc->nr_reclaimed:3
sc->priority:8 sc->nr_skipped_cma:32199  sc->nr_scanned:69  sc->nr_reclaimed:3
sc->priority:7 sc->nr_skipped_cma:198405 sc->nr_scanned:121 sc->nr_reclaimed:3
sc->priority:6 sc->nr_skipped_cma:236713 sc->nr_scanned:147 sc->nr_reclaimed:3
sc->priority:5 sc->nr_skipped_cma:708209 sc->nr_scanned:379 sc->nr_reclaimed:3
sc->priority:4 sc->nr_skipped_cma:785537 sc->nr_scanned:646 sc->nr_reclaimed:3
__alloc_pages_direct_reclaim end duration 3356ms

Continuously skipping CMA even when the LRU is filled with CMA
folios can also result in lmkd failing to terminate processes. The
duration of psi_memstall (measured from the exit to the entry of
__alloc_pages_direct_reclaim) becomes excessively long, lasting for
example a couple of seconds. Consequently, lmkd fails to awaken and
terminate processes promptly.

This patch introduces no_skip_cma and sets it to true when the number of
skipped CMA folios is excessively high. It offers two benefits: Rather
than wasting time in idle loops, it's better to assist other threads in
reclaiming some folios; This shortens the duration of psi_memstall and
ensures timely activation of lmkd within a few milliseconds.

Signed-off-by: liuhailong <liuhailong@xxxxxxxx>
---
 mm/vmscan.c | 23 ++++++++++++++++++++++-
 1 file changed, 22 insertions(+), 1 deletion(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index fa321c125099..2c74c1c94d88 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -114,6 +114,9 @@ struct scan_control {
 	/* Proactive reclaim invoked by userspace through memory.reclaim */
 	unsigned int proactive:1;

+	/* Can reclaim skip cma pages */
+	unsigned int no_skip_cma:1;
+
 	/*
 	 * Cgroup memory below memory.low is protected as long as we
 	 * don't threaten to OOM. If any cgroup is reclaimed at
@@ -157,6 +160,9 @@ struct scan_control {
 	/* Number of pages freed so far during a call to shrink_zones() */
 	unsigned long nr_reclaimed;

+	/* Number of cma-pages skipped so far during a call to shrink_zones() */
+	unsigned long nr_skipped_cma;
+
 	struct {
 		unsigned int dirty;
 		unsigned int unqueued_dirty;
@@ -1572,9 +1578,13 @@ static __always_inline void update_lru_sizes(struct lruvec *lruvec,
  */
 static bool skip_cma(struct folio *folio, struct scan_control *sc)
 {
-	return !current_is_kswapd() &&
+	bool ret = !current_is_kswapd() && !sc->no_skip_cma &&
 			gfp_migratetype(sc->gfp_mask) != MIGRATE_MOVABLE &&
 			folio_migratetype(folio) == MIGRATE_CMA;
+
+	if (ret)
+		sc->nr_skipped_cma += folio_nr_pages(folio);
+	return ret;
 }
 #else
 static bool skip_cma(struct folio *folio, struct scan_control *sc)
@@ -6188,6 +6198,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 			vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup,
 					sc->priority);
 		sc->nr_scanned = 0;
+		sc->nr_skipped_cma = 0;
 		shrink_zones(zonelist, sc);

 		if (sc->nr_reclaimed >= sc->nr_to_reclaim)
@@ -6202,6 +6213,16 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 		 */
 		if (sc->priority < DEF_PRIORITY - 2)
 			sc->may_writepage = 1;
+
+		/*
+		 * If we're getting trouble reclaiming non-cma pages and
+		 * currently a substantial number of CMA pages on LRU,
+		 * start reclaiming cma pages to alleviate other threads
+		 * and decrease lru size.
+		 */
+		if (sc->priority < DEF_PRIORITY - 2 &&
+		    sc->nr_scanned < (sc->nr_skipped_cma >> 3))
+			sc->no_skip_cma = 1;
 	} while (--sc->priority >= 0);

 	last_pgdat = NULL;
--
2.36.1