mm: memcontrol: fix NR_WRITEBACK leak in memcg and system stats

After commit a983b5ebee57 ("mm: memcontrol: fix excessive complexity in
memory.stat reporting"), we observed slowly upward creeping NR_WRITEBACK
counts over the course of several days, both the per-memcg stats as well
as the system counter in e.g.  /proc/meminfo.

The conversion from full per-cpu stat counts to per-cpu cached atomic
stat counts introduced an irq-unsafe RMW operation into the updates.

Most stat updates come from process context, but one notable exception
is the NR_WRITEBACK counter.  While writebacks are issued from process
context, they are retired from (soft)irq context.

When writeback completions interrupt the RMW counter updates of new
writebacks being issued, the decs from the completions are lost.

Since the global updates are routed through the joint lruvec API, both
the memcg counters as well as the system counters are affected.

This patch makes the joint stat and event API irq safe.

Link: http://lkml.kernel.org/r/20180203082353.17284-1-hannes@cmpxchg.org
Fixes: a983b5ebee57 ("mm: memcontrol: fix excessive complexity in memory.stat reporting")
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Debugged-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Rik van Riel <riel@surriel.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Michal Hocko <mhocko@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 8820468635810a3d801a5dd52beca94a7a14b035..c46016bb25ebe2ba3919987876ae058dd0a7b01c 100644 (file)
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -523,9 +523,11 @@ static inline void __mod_memcg_state(struct mem_cgroup *memcg,
 static inline void mod_memcg_state(struct mem_cgroup *memcg,
                                   int idx, int val)
 {
-       preempt_disable();
+       unsigned long flags;
+
+       local_irq_save(flags);
        __mod_memcg_state(memcg, idx, val);
-       preempt_enable();
+       local_irq_restore(flags);
 }
 
 /**
@@ -606,9 +608,11 @@ static inline void __mod_lruvec_state(struct lruvec *lruvec,
 static inline void mod_lruvec_state(struct lruvec *lruvec,
                                    enum node_stat_item idx, int val)
 {
-       preempt_disable();
+       unsigned long flags;
+
+       local_irq_save(flags);
        __mod_lruvec_state(lruvec, idx, val);
-       preempt_enable();
+       local_irq_restore(flags);
 }
 
 static inline void __mod_lruvec_page_state(struct page *page,
@@ -630,9 +634,11 @@ static inline void __mod_lruvec_page_state(struct page *page,
 static inline void mod_lruvec_page_state(struct page *page,
                                         enum node_stat_item idx, int val)
 {
-       preempt_disable();
+       unsigned long flags;
+
+       local_irq_save(flags);
        __mod_lruvec_page_state(page, idx, val);
-       preempt_enable();
+       local_irq_restore(flags);
 }
 
 unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
@@ -659,9 +665,11 @@ static inline void __count_memcg_events(struct mem_cgroup *memcg,
 static inline void count_memcg_events(struct mem_cgroup *memcg,
                                      int idx, unsigned long count)
 {
-       preempt_disable();
+       unsigned long flags;
+
+       local_irq_save(flags);
        __count_memcg_events(memcg, idx, count);
-       preempt_enable();
+       local_irq_restore(flags);
 }
 
 /* idx can be of type enum memcg_event_item or vm_event_item */