Andrew Lukoshko
60fd7c7780
Add the RHEL 687.13.1 backports (1253-1269) from centos-stream-9 and upstream stable, on top of 687.12.1. RHEL now ships the smb cifs.spnego fix (CVE-2026-46243) too. Bump pkgrelease and specrelease to 687.13.1.
139 lines
5.2 KiB
Diff
139 lines
5.2 KiB
Diff
From a17c77996e1aa930c05901e213f1441f0db7a46a Mon Sep 17 00:00:00 2001
|
|
From: Nico Pache <npache@redhat.com>
|
|
Date: Sat, 4 Apr 2026 19:30:20 -0600
|
|
Subject: [PATCH] mm/page_alloc: simplify __alloc_pages_slowpath() flow
|
|
|
|
commit 2c4c3e29897d43c431b1cf9432fb66977f262ac2
|
|
Author: Vlastimil Babka <vbabka@suse.cz>
|
|
Date: Tue Jan 6 12:52:38 2026 +0100
|
|
|
|
mm/page_alloc: simplify __alloc_pages_slowpath() flow
|
|
|
|
The actions done before entering the main retry loop include waking up
|
|
kswapds and an allocation attempt with the precise alloc_flags. Then in
|
|
the loop we keep waking up kswapds, and we retry the allocation with flags
|
|
potentially further adjusted by being allowed to use reserves (due to e.g.
|
|
becoming an OOM killer victim).
|
|
|
|
We can adjust the retry loop to keep only one instance of waking up
|
|
kswapds and allocation attempt. Introduce the can_retry_reserves variable
|
|
for retrying once when we become eligible for reserves. It is still
|
|
useful not to evaluate reserve_flags immediately for the first allocation
|
|
attempt, because it's better to first try succeed in a non-preferred zone
|
|
above the min watermark before allocating immediately from the preferred
|
|
zone below min watermark.
|
|
|
|
Additionally move the cpuset update checks introduced by e05741fb10c3
|
|
("mm/page_alloc.c: avoid infinite retries caused by cpuset race") further
|
|
down the retry loop. It's enough to do the checks only before reaching
|
|
any potentially infinite 'goto retry;' loop.
|
|
|
|
There should be no meaningful functional changes. The change of exact
|
|
moments the retry for reserves and cpuset updates are checked should not
|
|
result in different outomes modulo races with concurrent allocator
|
|
activity.
|
|
|
|
Link: https://lkml.kernel.org/r/20260106-thp-thisnode-tweak-v3-3-f5d67c21a193@suse.cz
|
|
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
|
|
Acked-by: Michal Hocko <mhocko@suse.com>
|
|
Cc: Johannes Weiner <hannes@cmpxchg.org>
|
|
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
|
|
Cc: Brendan Jackman <jackmanb@google.com>
|
|
Cc: David Hildenbrand (Red Hat) <david@kernel.org>
|
|
Cc: David Rientjes <rientjes@google.com>
|
|
Cc: Liam Howlett <liam.howlett@oracle.com>
|
|
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
|
|
Cc: Mike Rapoport <rppt@kernel.org>
|
|
Cc: Pedro Falcato <pfalcato@suse.de>
|
|
Cc: Suren Baghdasaryan <surenb@google.com>
|
|
Cc: Zi Yan <ziy@nvidia.com>
|
|
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
|
|
|
|
JIRA: https://redhat.atlassian.net/browse/RHEL-148561
|
|
Signed-off-by: Nico Pache <npache@redhat.com>
|
|
|
|
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
|
|
index 277ed887ec7a..4c2b622a39cf 100644
|
|
--- a/mm/page_alloc.c
|
|
+++ b/mm/page_alloc.c
|
|
@@ -4069,6 +4069,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
|
|
unsigned int zonelist_iter_cookie;
|
|
int reserve_flags;
|
|
bool compact_first = false;
|
|
+ bool can_retry_reserves = true;
|
|
|
|
if (unlikely(nofail)) {
|
|
/*
|
|
@@ -4140,6 +4141,8 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
|
|
goto nopage;
|
|
}
|
|
|
|
+retry:
|
|
+ /* Ensure kswapd doesn't accidentally go to sleep as long as we loop */
|
|
if (alloc_flags & ALLOC_KSWAPD)
|
|
wake_all_kswapds(order, gfp_mask, ac);
|
|
|
|
@@ -4151,19 +4154,6 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
|
|
if (page)
|
|
goto got_pg;
|
|
|
|
-retry:
|
|
- /*
|
|
- * Deal with possible cpuset update races or zonelist updates to avoid
|
|
- * infinite retries.
|
|
- */
|
|
- if (check_retry_cpuset(cpuset_mems_cookie, ac) ||
|
|
- check_retry_zonelist(zonelist_iter_cookie))
|
|
- goto restart;
|
|
-
|
|
- /* Ensure kswapd doesn't accidentally go to sleep as long as we loop */
|
|
- if (alloc_flags & ALLOC_KSWAPD)
|
|
- wake_all_kswapds(order, gfp_mask, ac);
|
|
-
|
|
reserve_flags = __gfp_pfmemalloc_flags(gfp_mask);
|
|
if (reserve_flags)
|
|
alloc_flags = gfp_to_alloc_flags_cma(gfp_mask, reserve_flags) |
|
|
@@ -4178,12 +4168,18 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
|
|
ac->nodemask = NULL;
|
|
ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
|
|
ac->highest_zoneidx, ac->nodemask);
|
|
- }
|
|
|
|
- /* Attempt with potentially adjusted zonelist and alloc_flags */
|
|
- page = get_page_from_freelist(gfp_mask, order, alloc_flags, ac);
|
|
- if (page)
|
|
- goto got_pg;
|
|
+ /*
|
|
+ * The first time we adjust anything due to being allowed to
|
|
+ * ignore memory policies or watermarks, retry immediately. This
|
|
+ * allows us to keep the first allocation attempt optimistic so
|
|
+ * it can succeed in a zone that is still above watermarks.
|
|
+ */
|
|
+ if (can_retry_reserves) {
|
|
+ can_retry_reserves = false;
|
|
+ goto retry;
|
|
+ }
|
|
+ }
|
|
|
|
/* Caller is not willing to reclaim, we can't balance anything */
|
|
if (!can_direct_reclaim)
|
|
@@ -4246,6 +4242,15 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
|
|
!(gfp_mask & __GFP_RETRY_MAYFAIL)))
|
|
goto nopage;
|
|
|
|
+ /*
|
|
+ * Deal with possible cpuset update races or zonelist updates to avoid
|
|
+ * infinite retries. No "goto retry;" can be placed above this check
|
|
+ * unless it can execute just once.
|
|
+ */
|
|
+ if (check_retry_cpuset(cpuset_mems_cookie, ac) ||
|
|
+ check_retry_zonelist(zonelist_iter_cookie))
|
|
+ goto restart;
|
|
+
|
|
if (should_reclaim_retry(gfp_mask, order, ac, alloc_flags,
|
|
did_some_progress > 0, &no_progress_loops))
|
|
goto retry;
|
|
--
|
|
2.50.1 (Apple Git-155)
|
|
|