mm: re-enable kswapd when memory pressure subsides or demotion is toggled

If kswapd fails to reclaim pages from a node MAX_RECLAIM_RETRIES in a
row, kswapd on that node gets disabled. That is, the system won't wakeup
kswapd for that node until page reclamation is observed at least once.
That reclamation is mostly done by direct reclaim, which in turn enables
kswapd back.

However, on systems with CXL memory nodes, workloads with high anon page
usage can disable kswapd indefinitely, without triggering direct
reclaim. This can be reproduced with following steps:

   numa node 0   (32GB memory, 48 CPUs)
   numa node 2~5 (512GB CXL memory, 128GB each)
   (numa node 1 is disabled)
   swap space 8GB

   1) Set /sys/kernel/mm/demotion_enabled to 0.
   2) Set /proc/sys/kernel/numa_balancing to 0.
   3) Run a process that allocates and random accesses 500GB of anon
      pages.
   4) Let the process exit normally.

During 3), free memory on node 0 gets lower than low watermark, and
kswapd runs and depletes swap space. Then, kswapd fails consecutively
and gets disabled. Allocation afterwards happens on CXL memory, so node
0 never gains more memory pressure to trigger direct reclaim.

After 4), kswapd on node 0 remains disabled, and tasks running on that
node are unable to swap. If you turn on NUMA_BALANCING_MEMORY_TIERING
and demotion now, it won't work properly since kswapd is disabled.

To mitigate this problem, reset kswapd_failures to 0 on following
conditions:

   a) ZONE_BELOW_HIGH bit of a zone in hopeless node with a fallback
      memory node gets cleared.
   b) demotion_enabled is changed from false to true.

Rationale for a):
   ZONE_BELOW_HIGH bit being cleared might be a sign that the node may
   be reclaimable afterwards. This won't help much if the memory-hungry
   process keeps running without freeing anything, but at least the node
   will go back to reclaimable state when the process exits.

Rationale for b):
   When demotion_enabled is false, kswapd can only reclaim anon pages by
   swapping them out to swap space. If demotion_enabled is turned on,
   kswapd can demote anon pages to another node for reclaiming. So, the
   original failure count for determining reclaimability is no longer
   valid.

Since kswapd_failures resets may be missed by ++ operation, it is
changed from int to atomic_t.

[akpm@linux-foundation.org: tweak whitespace]
Link: https://lkml.kernel.org/r/aL6qGi69jWXfPc4D@pcw-MS-7D22
Signed-off-by: Chanwon Park <flyinrm@gmail.com>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

6 files changed, 45 insertions, 17 deletions

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 6c4eae96160d..7fb7331c5725 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1440,7 +1440,7 @@ typedef struct pglist_data {
 	int kswapd_order;
 	enum zone_type kswapd_highest_zoneidx;
 
-	int kswapd_failures;		/* Number of 'reclaimed == 0' runs */
+	atomic_t kswapd_failures;	/* Number of 'reclaimed == 0' runs */
 
 #ifdef CONFIG_COMPACTION
 	int kcompactd_max_order;
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
index 0382b6942b8b..0ea5c13f10a2 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -942,11 +942,23 @@ static ssize_t demotion_enabled_store(struct kobject *kobj,
 				      const char *buf, size_t count)
 {
 	ssize_t ret;
+	bool before = numa_demotion_enabled;
 
 	ret = kstrtobool(buf, &numa_demotion_enabled);
 	if (ret)
 		return ret;
 
+	/*
+	 * Reset kswapd_failures statistics. They may no longer be
+	 * valid since the policy for kswapd has changed.
+	 */
+	if (before == false && numa_demotion_enabled == true) {
+		struct pglist_data *pgdat;
+
+		for_each_online_pgdat(pgdat)
+			atomic_set(&pgdat->kswapd_failures, 0);
+	}
+
 	return count;
 }
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index df6df302d0c5..6ff9f17d5f4e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2860,14 +2860,29 @@ static void free_frozen_page_commit(struct zone *zone,
 		 */
 		return;
 	}
+
 	high = nr_pcp_high(pcp, zone, batch, free_high);
-	if (pcp->count >= high) {
-		free_pcppages_bulk(zone, nr_pcp_free(pcp, batch, high, free_high),
-				   pcp, pindex);
-		if (test_bit(ZONE_BELOW_HIGH, &zone->flags) &&
-		    zone_watermark_ok(zone, 0, high_wmark_pages(zone),
-				      ZONE_MOVABLE, 0))
-			clear_bit(ZONE_BELOW_HIGH, &zone->flags);
+	if (pcp->count < high)
+		return;
+
+	free_pcppages_bulk(zone, nr_pcp_free(pcp, batch, high, free_high),
+			   pcp, pindex);
+	if (test_bit(ZONE_BELOW_HIGH, &zone->flags) &&
+	    zone_watermark_ok(zone, 0, high_wmark_pages(zone),
+			      ZONE_MOVABLE, 0)) {
+		struct pglist_data *pgdat = zone->zone_pgdat;
+		clear_bit(ZONE_BELOW_HIGH, &zone->flags);
+
+		/*
+		 * Assume that memory pressure on this node is gone and may be
+		 * in a reclaimable state. If a memory fallback node exists,
+		 * direct reclaim may not have been triggered, causing a
+		 * 'hopeless node' to stay in that state for a while.  Let
+		 * kswapd work again by resetting kswapd_failures.
+		 */
+		if (atomic_read(&pgdat->kswapd_failures) >= MAX_RECLAIM_RETRIES &&
+		    next_memory_node(pgdat->node_id) < MAX_NUMNODES)
+			atomic_set(&pgdat->kswapd_failures, 0);
 	}
 }
 
diff --git a/mm/show_mem.c b/mm/show_mem.c
index 90a9a37116e7..3a4b5207635d 100644
--- a/mm/show_mem.c
+++ b/mm/show_mem.c
@@ -278,7 +278,8 @@ static void show_free_areas(unsigned int filter, nodemask_t *nodemask, int max_z
 #endif
 			K(node_page_state(pgdat, NR_PAGETABLE)),
 			K(node_page_state(pgdat, NR_SECONDARY_PAGETABLE)),
-			str_yes_no(pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES),
+			str_yes_no(atomic_read(&pgdat->kswapd_failures) >=
+				   MAX_RECLAIM_RETRIES),
 			K(node_page_state(pgdat, NR_BALLOON_PAGES)));
 	}
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index e170c12e2065..b2fc8b626d3d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -518,7 +518,7 @@ static bool skip_throttle_noprogress(pg_data_t *pgdat)
 	 * If kswapd is disabled, reschedule if necessary but do not
 	 * throttle as the system is likely near OOM.
 	 */
-	if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
+	if (atomic_read(&pgdat->kswapd_failures) >= MAX_RECLAIM_RETRIES)
 		return true;
 
 	/*
@@ -5101,7 +5101,7 @@ static void lru_gen_shrink_node(struct pglist_data *pgdat, struct scan_control *
 	blk_finish_plug(&plug);
 done:
 	if (sc->nr_reclaimed > reclaimed)
-		pgdat->kswapd_failures = 0;
+		atomic_set(&pgdat->kswapd_failures, 0);
 }
 
 /******************************************************************************
@@ -6180,7 +6180,7 @@ again:
 	 * successful direct reclaim run will revive a dormant kswapd.
 	 */
 	if (reclaimable)
-		pgdat->kswapd_failures = 0;
+		atomic_set(&pgdat->kswapd_failures, 0);
 	else if (sc->cache_trim_mode)
 		sc->cache_trim_mode_failed = 1;
 }
@@ -6492,7 +6492,7 @@ static bool allow_direct_reclaim(pg_data_t *pgdat)
 	int i;
 	bool wmark_ok;
 
-	if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
+	if (atomic_read(&pgdat->kswapd_failures) >= MAX_RECLAIM_RETRIES)
 		return true;
 
 	for_each_managed_zone_pgdat(zone, pgdat, i, ZONE_NORMAL) {
@@ -6902,7 +6902,7 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order,
 		wake_up_all(&pgdat->pfmemalloc_wait);
 
 	/* Hopeless node, leave it to direct reclaim */
-	if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
+	if (atomic_read(&pgdat->kswapd_failures) >= MAX_RECLAIM_RETRIES)
 		return true;
 
 	if (pgdat_balanced(pgdat, order, highest_zoneidx)) {
@@ -7170,7 +7170,7 @@ restart:
 	}
 
 	if (!sc.nr_reclaimed)
-		pgdat->kswapd_failures++;
+		atomic_inc(&pgdat->kswapd_failures);
 
 out:
 	clear_reclaim_active(pgdat, highest_zoneidx);
@@ -7429,7 +7429,7 @@ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order,
 		return;
 
 	/* Hopeless node, leave it to direct reclaim if possible */
-	if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES ||
+	if (atomic_read(&pgdat->kswapd_failures) >= MAX_RECLAIM_RETRIES ||
 	    (pgdat_balanced(pgdat, order, highest_zoneidx) &&
 	     !pgdat_watermark_boosted(pgdat, highest_zoneidx))) {
 		/*
diff --git a/mm/vmstat.c b/mm/vmstat.c
index e522decf6a72..bb09c032eecf 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1848,7 +1848,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
 	seq_printf(m,
 		   "\n  node_unreclaimable:  %u"
 		   "\n  start_pfn:           %lu",
-		   pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES,
+		   atomic_read(&pgdat->kswapd_failures) >= MAX_RECLAIM_RETRIES,
 		   zone->zone_start_pfn);
 	seq_putc(m, '\n');
 }