linux-kernel - [PATCH mm-unstable v4 4/5] mm: restart if multiple traversals raced

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20240905003058.1859929-5-kinseyho@google.com>
Date: Thu,  5 Sep 2024 00:30:53 +0000
From: Kinsey Ho <kinseyho@...gle.com>
To: Andrew Morton <akpm@...ux-foundation.org>
Cc: linux-mm@...ck.org, linux-kernel@...r.kernel.org, cgroups@...r.kernel.org, 
	Yosry Ahmed <yosryahmed@...gle.com>, Roman Gushchin <roman.gushchin@...ux.dev>, 
	Johannes Weiner <hannes@...xchg.org>, Michal Hocko <mhocko@...nel.org>, 
	Shakeel Butt <shakeel.butt@...ux.dev>, Muchun Song <muchun.song@...ux.dev>, 
	Tejun Heo <tj@...nel.org>, Zefan Li <lizefan.x@...edance.com>, mkoutny@...e.com, 
	"T . J . Mercier" <tjmercier@...gle.com>, Hugh Dickins <hughd@...gle.com>, Kinsey Ho <kinseyho@...gle.com>, 
	syzbot+e099d407346c45275ce9@...kaller.appspotmail.com
Subject: [PATCH mm-unstable v4 4/5] mm: restart if multiple traversals raced

Currently, if multiple reclaimers raced on the same position, the
reclaimers which detect the race will still reclaim from the same memcg.
Instead, the reclaimers which detect the race should move on to the next
memcg in the hierarchy.

So, in the case where multiple traversals race, jump back to the start
of the mem_cgroup_iter() function to find the next memcg in the
hierarchy to reclaim from.

Reported-by: syzbot+e099d407346c45275ce9@...kaller.appspotmail.com
Closes: https://lore.kernel.org/000000000000817cf10620e20d33@google.com/
Signed-off-by: Kinsey Ho <kinseyho@...gle.com>
Reviewed-by: T.J. Mercier <tjmercier@...gle.com>
Cc: Johannes Weiner <hannes@...xchg.org>
Cc: Michal Hocko <mhocko@...nel.org>
Cc: Michal Koutný <mkoutny@...e.com>
Cc: Muchun Song <muchun.song@...ux.dev>
Cc: Roman Gushchin <roman.gushchin@...ux.dev>
Cc: Shakeel Butt <shakeel.butt@...ux.dev>
Cc: Tejun Heo <tj@...nel.org>
Cc: Yosry Ahmed <yosryahmed@...gle.com>
Cc: Zefan Li <lizefan.x@...edance.com>
Cc: Hugh Dickins <hughd@...gle.com>
---
 include/linux/memcontrol.h |  4 ++--
 mm/memcontrol.c            | 26 +++++++++++++++++---------
 2 files changed, 19 insertions(+), 11 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index fe05fdb92779..2ef94c74847d 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -57,7 +57,7 @@ enum memcg_memory_event {
 
 struct mem_cgroup_reclaim_cookie {
 	pg_data_t *pgdat;
-	unsigned int generation;
+	int generation;
 };
 
 #ifdef CONFIG_MEMCG
@@ -78,7 +78,7 @@ struct lruvec_stats;
 struct mem_cgroup_reclaim_iter {
 	struct mem_cgroup *position;
 	/* scan generation, increased every round-trip */
-	unsigned int generation;
+	atomic_t generation;
 };
 
 /*
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c24ef6a106e0..ce5d066393c9 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -988,8 +988,8 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 				   struct mem_cgroup_reclaim_cookie *reclaim)
 {
 	struct mem_cgroup_reclaim_iter *iter;
-	struct cgroup_subsys_state *css = NULL;
-	struct mem_cgroup *memcg = NULL;
+	struct cgroup_subsys_state *css;
+	struct mem_cgroup *memcg;
 	struct mem_cgroup *pos = NULL;
 
 	if (mem_cgroup_disabled())
@@ -1000,19 +1000,23 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 
 	rcu_read_lock();
 restart:
+	memcg = NULL;
+
 	if (reclaim) {
+		int gen;
 		struct mem_cgroup_per_node *mz;
 
 		mz = root->nodeinfo[reclaim->pgdat->node_id];
 		iter = &mz->iter;
+		gen = atomic_read(&iter->generation);
 
 		/*
 		 * On start, join the current reclaim iteration cycle.
 		 * Exit when a concurrent walker completes it.
 		 */
 		if (!prev)
-			reclaim->generation = iter->generation;
-		else if (reclaim->generation != iter->generation)
+			reclaim->generation = gen;
+		else if (reclaim->generation != gen)
 			goto out_unlock;
 
 		pos = READ_ONCE(iter->position);
@@ -1020,8 +1024,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 		pos = prev;
 	}
 
-	if (pos)
-		css = &pos->css;
+	css = pos ? &pos->css : NULL;
 
 	for (;;) {
 		css = css_next_descendant_pre(css, &root->css);
@@ -1035,21 +1038,26 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 		 * and kicking, and don't take an extra reference.
 		 */
 		if (css == &root->css || css_tryget(css)) {
-			memcg = mem_cgroup_from_css(css);
 			break;
 		}
 	}
 
+	memcg = mem_cgroup_from_css(css);
+
 	if (reclaim) {
 		/*
 		 * The position could have already been updated by a competing
 		 * thread, so check that the value hasn't changed since we read
 		 * it to avoid reclaiming from the same cgroup twice.
 		 */
-		(void)cmpxchg(&iter->position, pos, memcg);
+		if (cmpxchg(&iter->position, pos, memcg) != pos) {
+			if (css && css != &root->css)
+				css_put(css);
+			goto restart;
+		}
 
 		if (!memcg) {
-			iter->generation++;
+			atomic_inc(&iter->generation);
 
 			/*
 			 * Reclaimers share the hierarchy walk, and a
-- 
2.46.0.469.g59c65b2a67-goog