[PATCH 1/2] mm: vmscan: restore high-cpu watermark safety in kswapd

[Johannes Weiner <hannes@cmpxchg.org>]

Vlastimil points out that commit a211c6550efc ("mm: page_alloc:
defrag_mode kswapd/kcompactd watermarks") switched kswapd from
zone_watermark_ok_safe() to the standard, percpu-cached version of
reading free pages, thus dropping the watermark safety precautions for
systems with high CPU counts (e.g. >212 cpus on 64G). Restore them.

Since zone_watermark_ok_safe() is no longer the right interface, and
this was the last caller of the function anyway, open-code the
zone_page_state_snapshot() conditional and delete the function.

Reported-by: Vlastimil Babka <vbabka@suse.cz>
Fixes: a211c6550efc ("mm: page_alloc: defrag_mode kswapd/kcompactd watermarks")
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
---
 include/linux/mmzone.h |  2 --
 mm/page_alloc.c        | 12 ------------
 mm/vmscan.c            | 21 +++++++++++++++++++--
 3 files changed, 19 insertions(+), 16 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 4c95fcc9e9df..6ccec1bf2896 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1502,8 +1502,6 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
 bool zone_watermark_ok(struct zone *z, unsigned int order,
 		unsigned long mark, int highest_zoneidx,
 		unsigned int alloc_flags);
-bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
-		unsigned long mark, int highest_zoneidx);
 /*
  * Memory initialization context, use to differentiate memory added by
  * the platform statically or via memory hotplug interface.
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d7cfcfa2b077..928a81f67326 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3470,18 +3470,6 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
 	return false;
 }
 
-bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
-			unsigned long mark, int highest_zoneidx)
-{
-	long free_pages = zone_page_state(z, NR_FREE_PAGES);
-
-	if (z->percpu_drift_mark && free_pages < z->percpu_drift_mark)
-		free_pages = zone_page_state_snapshot(z, NR_FREE_PAGES);
-
-	return __zone_watermark_ok(z, order, mark, highest_zoneidx, 0,
-								free_pages);
-}
-
 #ifdef CONFIG_NUMA
 int __read_mostly node_reclaim_distance = RECLAIM_DISTANCE;
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b620d74b0f66..cc422ad830d6 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -6736,6 +6736,7 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx)
 	 * meet watermarks.
 	 */
 	for_each_managed_zone_pgdat(zone, pgdat, i, highest_zoneidx) {
+		enum zone_stat_item item;
 		unsigned long free_pages;
 
 		if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING)
@@ -6748,9 +6749,25 @@ static bool pgdat_balanced(pg_data_t *pgdat, int order, int highest_zoneidx)
 		 * blocks to avoid polluting allocator fallbacks.
 		 */
 		if (defrag_mode)
-			free_pages = zone_page_state(zone, NR_FREE_PAGES_BLOCKS);
+			item = NR_FREE_PAGES_BLOCKS;
 		else
-			free_pages = zone_page_state(zone, NR_FREE_PAGES);
+			item = NR_FREE_PAGES;
+
+		/*
+		 * When there is a high number of CPUs in the system,
+		 * the cumulative error from the vmstat per-cpu cache
+		 * can blur the line between the watermarks. In that
+		 * case, be safe and get an accurate snapshot.
+		 *
+		 * TODO: NR_FREE_PAGES_BLOCKS moves in steps of
+		 * pageblock_nr_pages, while the vmstat pcp threshold
+		 * is limited to 125. On many configurations that
+		 * counter won't actually be per-cpu cached. But keep
+		 * things simple for now; revisit when somebody cares.
+		 */
+		free_pages = zone_page_state(zone, item);
+		if (zone->percpu_drift_mark && free_pages < zone->percpu_drift_mark)
+			free_pages = zone_page_state_snapshot(zone, item);
 
 		if (__zone_watermark_ok(zone, order, mark, highest_zoneidx,
 					0, free_pages))
-- 
2.49.0