workingset: memcg: sleep when flushing stats in workingset_refault()

In workingset_refault(), we call
mem_cgroup_flush_stats_atomic_ratelimited() to read accurate stats within
an RCU read section and with sleeping disallowed.  Move the call above the
RCU read section to make it non-atomic.

Flushing is an expensive operation that scales with the number of cpus and
the number of cgroups in the system, so avoid doing it atomically where
possible.

Since workingset_refault() is the only caller of
mem_cgroup_flush_stats_atomic_ratelimited(), just make it non-atomic, and
rename it to mem_cgroup_flush_stats_ratelimited().

Link: https://lkml.kernel.org/r/20230330191801.1967435-7-yosryahmed@google.com
Signed-off-by: Yosry Ahmed <yosryahmed@google.com>
Acked-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Josef Bacik <josef@toxicpanda.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Michal Koutný <mkoutny@suse.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vasily Averin <vasily.averin@linux.dev>
Cc: Zefan Li <lizefan.x@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 3db355e..222d737 100644 (file)
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1039,7 +1039,7 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
 
 void mem_cgroup_flush_stats(void);
 void mem_cgroup_flush_stats_atomic(void);
-void mem_cgroup_flush_stats_atomic_ratelimited(void);
+void mem_cgroup_flush_stats_ratelimited(void);
 
 void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
                              int val);
@@ -1541,7 +1541,7 @@ static inline void mem_cgroup_flush_stats_atomic(void)
 {
 }
 
-static inline void mem_cgroup_flush_stats_atomic_ratelimited(void)
+static inline void mem_cgroup_flush_stats_ratelimited(void)
 {
 }
 

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 06786de..e9e79ce 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -674,10 +674,10 @@ void mem_cgroup_flush_stats_atomic(void)
                do_flush_stats(true);
 }
 
-void mem_cgroup_flush_stats_atomic_ratelimited(void)
+void mem_cgroup_flush_stats_ratelimited(void)
 {
        if (time_after64(jiffies_64, READ_ONCE(flush_next_time)))
-               mem_cgroup_flush_stats_atomic();
+               mem_cgroup_flush_stats();
 }
 
 static void flush_memcg_stats_dwork(struct work_struct *w)

diff --git a/mm/workingset.c b/mm/workingset.c
index dab0c36..3025bee 100644 (file)
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -406,6 +406,9 @@ void workingset_refault(struct folio *folio, void *shadow)
        unpack_shadow(shadow, &memcgid, &pgdat, &eviction, &workingset);
        eviction <<= bucket_order;
 
+       /* Flush stats (and potentially sleep) before holding RCU read lock */
+       mem_cgroup_flush_stats_ratelimited();
+
        rcu_read_lock();
        /*
         * Look up the memcg associated with the stored ID. It might
@@ -461,8 +464,6 @@ void workingset_refault(struct folio *folio, void *shadow)
        lruvec = mem_cgroup_lruvec(memcg, pgdat);
 
        mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file, nr);
-
-       mem_cgroup_flush_stats_atomic_ratelimited();
        /*
         * Compare the distance to the existing workingset size. We
         * don't activate pages that couldn't stay resident even if