提交 4799401f 编写于 作者: S Steven Rostedt 提交者: Linus Torvalds

memcg: Fix race condition in memcg_check_events() with this_cpu usage

Various code in memcontrol.c () calls this_cpu_read() on the calculations
to be done from two different percpu variables, or does an open-coded
read-modify-write on a single percpu variable.

Disable preemption throughout these operations so that the writes go to
the correct palces.

[hannes@cmpxchg.org: added this_cpu to __this_cpu conversion]
Signed-off-by: NJohannes Weiner <hannes@cmpxchg.org>
Signed-off-by: NSteven Rostedt <rostedt@goodmis.org>
Cc: Greg Thelen <gthelen@google.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Christoph Lameter <cl@linux.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
上级 a61ed3ce
...@@ -686,8 +686,8 @@ static bool __memcg_event_check(struct mem_cgroup *memcg, int target) ...@@ -686,8 +686,8 @@ static bool __memcg_event_check(struct mem_cgroup *memcg, int target)
{ {
unsigned long val, next; unsigned long val, next;
val = this_cpu_read(memcg->stat->events[MEM_CGROUP_EVENTS_COUNT]); val = __this_cpu_read(memcg->stat->events[MEM_CGROUP_EVENTS_COUNT]);
next = this_cpu_read(memcg->stat->targets[target]); next = __this_cpu_read(memcg->stat->targets[target]);
/* from time_after() in jiffies.h */ /* from time_after() in jiffies.h */
return ((long)next - (long)val < 0); return ((long)next - (long)val < 0);
} }
...@@ -696,7 +696,7 @@ static void __mem_cgroup_target_update(struct mem_cgroup *memcg, int target) ...@@ -696,7 +696,7 @@ static void __mem_cgroup_target_update(struct mem_cgroup *memcg, int target)
{ {
unsigned long val, next; unsigned long val, next;
val = this_cpu_read(memcg->stat->events[MEM_CGROUP_EVENTS_COUNT]); val = __this_cpu_read(memcg->stat->events[MEM_CGROUP_EVENTS_COUNT]);
switch (target) { switch (target) {
case MEM_CGROUP_TARGET_THRESH: case MEM_CGROUP_TARGET_THRESH:
...@@ -712,7 +712,7 @@ static void __mem_cgroup_target_update(struct mem_cgroup *memcg, int target) ...@@ -712,7 +712,7 @@ static void __mem_cgroup_target_update(struct mem_cgroup *memcg, int target)
return; return;
} }
this_cpu_write(memcg->stat->targets[target], next); __this_cpu_write(memcg->stat->targets[target], next);
} }
/* /*
...@@ -721,6 +721,7 @@ static void __mem_cgroup_target_update(struct mem_cgroup *memcg, int target) ...@@ -721,6 +721,7 @@ static void __mem_cgroup_target_update(struct mem_cgroup *memcg, int target)
*/ */
static void memcg_check_events(struct mem_cgroup *memcg, struct page *page) static void memcg_check_events(struct mem_cgroup *memcg, struct page *page)
{ {
preempt_disable();
/* threshold event is triggered in finer grain than soft limit */ /* threshold event is triggered in finer grain than soft limit */
if (unlikely(__memcg_event_check(memcg, MEM_CGROUP_TARGET_THRESH))) { if (unlikely(__memcg_event_check(memcg, MEM_CGROUP_TARGET_THRESH))) {
mem_cgroup_threshold(memcg); mem_cgroup_threshold(memcg);
...@@ -740,6 +741,7 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page) ...@@ -740,6 +741,7 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page)
} }
#endif #endif
} }
preempt_enable();
} }
static struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont) static struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册