From 78ec6f9df6642418411c534683da6133e0962ec7 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Wed, 24 Apr 2024 05:59:39 -0700 Subject: memcg: fix data-race KCSAN bug in rstats A data-race issue in memcg rstat occurs when two distinct code paths access the same 4-byte region concurrently. KCSAN detection triggers the following BUG as a result. BUG: KCSAN: data-race in __count_memcg_events / mem_cgroup_css_rstat_flush write to 0xffffe8ffff98e300 of 4 bytes by task 5274 on cpu 17: mem_cgroup_css_rstat_flush (mm/memcontrol.c:5850) cgroup_rstat_flush_locked (kernel/cgroup/rstat.c:243 (discriminator 7)) cgroup_rstat_flush (./include/linux/spinlock.h:401 kernel/cgroup/rstat.c:278) mem_cgroup_flush_stats.part.0 (mm/memcontrol.c:767) memory_numa_stat_show (mm/memcontrol.c:6911) read to 0xffffe8ffff98e300 of 4 bytes by task 410848 on cpu 27: __count_memcg_events (mm/memcontrol.c:725 mm/memcontrol.c:962) count_memcg_event_mm.part.0 (./include/linux/memcontrol.h:1097 ./include/linux/memcontrol.h:1120) handle_mm_fault (mm/memory.c:5483 mm/memory.c:5622) value changed: 0x00000029 -> 0x00000000 The race occurs because two code paths access the same "stats_updates" location. Although "stats_updates" is a per-CPU variable, it is remotely accessed by another CPU at cgroup_rstat_flush_locked()->mem_cgroup_css_rstat_flush(), leading to the data race mentioned. Considering that memcg_rstat_updated() is in the hot code path, adding a lock to protect it may not be desirable, especially since this variable pertains solely to statistics. Therefore, annotating accesses to stats_updates with READ/WRITE_ONCE() can prevent KCSAN splats and potential partial reads/writes. Link: https://lkml.kernel.org/r/20240424125940.2410718-1-leitao@debian.org Fixes: 9cee7e8ef3e3 ("mm: memcg: optimize parent iteration in memcg_rstat_updated()") Signed-off-by: Breno Leitao Suggested-by: Shakeel Butt Acked-by: Johannes Weiner Acked-by: Shakeel Butt Reviewed-by: Yosry Ahmed Cc: Michal Hocko Cc: Roman Gushchin Cc: Muchun Song Signed-off-by: Andrew Morton --- mm/memcontrol.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'mm/memcontrol.c') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 9095ab05d47a..a111e0d981ba 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -715,6 +715,7 @@ static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val) { struct memcg_vmstats_percpu *statc; int cpu = smp_processor_id(); + unsigned int stats_updates; if (!val) return; @@ -722,8 +723,9 @@ static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val) cgroup_rstat_updated(memcg->css.cgroup, cpu); statc = this_cpu_ptr(memcg->vmstats_percpu); for (; statc; statc = statc->parent) { - statc->stats_updates += abs(val); - if (statc->stats_updates < MEMCG_CHARGE_BATCH) + stats_updates = READ_ONCE(statc->stats_updates) + abs(val); + WRITE_ONCE(statc->stats_updates, stats_updates); + if (stats_updates < MEMCG_CHARGE_BATCH) continue; /* @@ -731,9 +733,9 @@ static inline void memcg_rstat_updated(struct mem_cgroup *memcg, int val) * redundant. Avoid the overhead of the atomic update. */ if (!memcg_vmstats_needs_flush(statc->vmstats)) - atomic64_add(statc->stats_updates, + atomic64_add(stats_updates, &statc->vmstats->stats_updates); - statc->stats_updates = 0; + WRITE_ONCE(statc->stats_updates, 0); } } @@ -5887,7 +5889,7 @@ static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu) } } } - statc->stats_updates = 0; + WRITE_ONCE(statc->stats_updates, 0); /* We are in a per-cpu loop here, only do the atomic write once */ if (atomic64_read(&memcg->vmstats->stats_updates)) atomic64_set(&memcg->vmstats->stats_updates, 0); -- cgit v1.2.3