From: Shengming Hu <hu.shengming@zte.com.cn>
Date: Thu, 29 Jan 2026 14:38:14 +0000 (+0800)
Subject: mm/page_alloc: avoid overcounting bulk alloc in watermark check
X-Git-Url: http://git.ipfire.org/gitweb.cgi?a=commitdiff_plain;h=7e74dd031620549174eb287649aa12970ef56589;p=thirdparty%2Fkernel%2Fstable.git

mm/page_alloc: avoid overcounting bulk alloc in watermark check

alloc_pages_bulk_noprof() only fills NULL slots and already tracks how
many entries are pre-populated via nr_populated.

The fast watermark check was adding nr_pages unconditionally, which can
overestimate the demand.  Use (nr_pages - nr_populated) instead, as an
upper bound on the remaining pages this call can still allocate without
scanning the whole array.

Link: https://lkml.kernel.org/r/tencent_F36C5B5FB4DED98C79D9BDEE1210CD338C06@qq.com
Signed-off-by: Shengming Hu <hu.shengming@zte.com.cn>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 2d4b6f1a554e..d88c8c67ac0b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5136,7 +5136,7 @@ unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid,
 
 		cond_accept_memory(zone, 0, alloc_flags);
 retry_this_zone:
-		mark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK) + nr_pages;
+		mark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK) + nr_pages - nr_populated;
 		if (zone_watermark_fast(zone, 0,  mark,
 				zonelist_zone_idx(ac.preferred_zoneref),
 				alloc_flags, gfp)) {