mm: memcontrol: make per-cpu charge cache IRQ-safe for socket accounting

During cgroup2 rollout into production, we started encountering css
refcount underflows and css access crashes in the memory controller.
Splitting the heavily shared css reference counter into logical users
narrowed the imbalance down to the cgroup2 socket memory accounting.

The problem turns out to be the per-cpu charge cache.  Cgroup1 had a
separate socket counter, but the new cgroup2 socket accounting goes
through the common charge path that uses a shared per-cpu cache for all
memory that is being tracked.  Those caches are safe against scheduling
preemption, but not against interrupts - such as the newly added packet
receive path.  When cache draining is interrupted by network RX taking
pages out of the cache, the resuming drain operation will put references
of in-use pages, thus causing the imbalance.

Disable IRQs during all per-cpu charge cache operations.

Fixes: f7e1cb6ec51b ("mm: memcontrol: account socket memory in unified hierarchy memory controller")
Link: http://lkml.kernel.org/r/20160914194846.11153-1-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Tejun Heo <tj@kernel.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Vladimir Davydov <vdavydov@virtuozzo.com>
Cc: <stable@vger.kernel.org>	[4.5+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 9a6a51a7c416074ccd5d974ac9f17a54c85d14db..4be518d4e68ab437549693161c189c7caefe87ae 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1740,17 +1740,22 @@ static DEFINE_MUTEX(percpu_charge_mutex);
 static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 {
        struct memcg_stock_pcp *stock;
+       unsigned long flags;
        bool ret = false;
 
        if (nr_pages > CHARGE_BATCH)
                return ret;
 
-       stock = &get_cpu_var(memcg_stock);
+       local_irq_save(flags);
+
+       stock = this_cpu_ptr(&memcg_stock);
        if (memcg == stock->cached && stock->nr_pages >= nr_pages) {
                stock->nr_pages -= nr_pages;
                ret = true;
        }
-       put_cpu_var(memcg_stock);
+
+       local_irq_restore(flags);
+
        return ret;
 }
 
@@ -1771,15 +1776,18 @@ static void drain_stock(struct memcg_stock_pcp *stock)
        stock->cached = NULL;
 }
 
-/*
- * This must be called under preempt disabled or must be called by
- * a thread which is pinned to local cpu.
- */
 static void drain_local_stock(struct work_struct *dummy)
 {
-       struct memcg_stock_pcp *stock = this_cpu_ptr(&memcg_stock);
+       struct memcg_stock_pcp *stock;
+       unsigned long flags;
+
+       local_irq_save(flags);
+
+       stock = this_cpu_ptr(&memcg_stock);
        drain_stock(stock);
        clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags);
+
+       local_irq_restore(flags);
 }
 
 /*
@@ -1788,14 +1796,19 @@ static void drain_local_stock(struct work_struct *dummy)
  */
 static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 {
-       struct memcg_stock_pcp *stock = &get_cpu_var(memcg_stock);
+       struct memcg_stock_pcp *stock;
+       unsigned long flags;
+
+       local_irq_save(flags);
 
+       stock = this_cpu_ptr(&memcg_stock);
        if (stock->cached != memcg) { /* reset if necessary */
                drain_stock(stock);
                stock->cached = memcg;
        }
        stock->nr_pages += nr_pages;
-       put_cpu_var(memcg_stock);
+
+       local_irq_restore(flags);
 }
 
 /*