The patch titled
memcg: oom wakeup filter
has been added to the -mm tree. Its filename is
memcg-oom-wakeup-filter.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: memcg: oom wakeup filter
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
memcg's oom waitqueue is a system-wide wait_queue (for handling
hierarchy.) So, it's better to add custom wake function and do filtering
in wake up path.
This patch adds a filtering feature for waking up oom-waiters. Hierarchy
is properly handled.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Reviewed-by: Daisuke Nishimura <nishimura@xxxxxxxxxxxxxxxxx>
Cc: Balbir Singh <balbir@xxxxxxxxxx>
Cc: Daisuke Nishimura <nishimura@xxxxxxxxxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/memcontrol.c | 61 +++++++++++++++++++++++++++++++++-------------
1 file changed, 44 insertions(+), 17 deletions(-)
diff -puN mm/memcontrol.c~memcg-oom-wakeup-filter mm/memcontrol.c
--- a/mm/memcontrol.c~memcg-oom-wakeup-filter
+++ a/mm/memcontrol.c
@@ -1293,14 +1293,54 @@ static void mem_cgroup_oom_unlock(struct
static DEFINE_MUTEX(memcg_oom_mutex);
static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq);
+struct oom_wait_info {
+ struct mem_cgroup *mem;
+ wait_queue_t wait;
+};
+
+static int memcg_oom_wake_function(wait_queue_t *wait,
+ unsigned mode, int sync, void *arg)
+{
+ struct mem_cgroup *wake_mem = (struct mem_cgroup *)arg;
+ struct oom_wait_info *oom_wait_info;
+
+ /* both of oom_wait_info->mem and wake_mem are stable under us */
+ oom_wait_info = container_of(wait, struct oom_wait_info, wait);
+
+ if (oom_wait_info->mem == wake_mem)
+ goto wakeup;
+ /* if no hierarchy, no match */
+ if (!oom_wait_info->mem->use_hierarchy || !wake_mem->use_hierarchy)
+ return 0;
+ /* check hierarchy */
+ if (!css_is_ancestor(&oom_wait_info->mem->css, &wake_mem->css) &&
+ !css_is_ancestor(&wake_mem->css, &oom_wait_info->mem->css))
+ return 0;
+
+wakeup:
+ return autoremove_wake_function(wait, mode, sync, arg);
+}
+
+static void memcg_wakeup_oom(struct mem_cgroup *mem)
+{
+ /* for filtering, pass "mem" as argument. */
+ __wake_up(&memcg_oom_waitq, TASK_NORMAL, 0, mem);
+}
+
/*
* try to call OOM killer. returns false if we should exit memory-reclaim loop.
*/
bool mem_cgroup_handle_oom(struct mem_cgroup *mem, gfp_t mask)
{
- DEFINE_WAIT(wait);
+ struct oom_wait_info owait;
bool locked;
+ owait.mem = mem;
+ owait.wait.flags = 0;
+ owait.wait.func = memcg_oom_wake_function;
+ owait.wait.private = current;
+ INIT_LIST_HEAD(&owait.wait.task_list);
+
/* At first, try to OOM lock hierarchy under mem.*/
mutex_lock(&memcg_oom_mutex);
locked = mem_cgroup_oom_lock(mem);
@@ -1310,31 +1350,18 @@ bool mem_cgroup_handle_oom(struct mem_cg
* under OOM is always welcomed, use TASK_KILLABLE here.
*/
if (!locked)
- prepare_to_wait(&memcg_oom_waitq, &wait, TASK_KILLABLE);
+ prepare_to_wait(&memcg_oom_waitq, &owait.wait, TASK_KILLABLE);
mutex_unlock(&memcg_oom_mutex);
if (locked)
mem_cgroup_out_of_memory(mem, mask);
else {
schedule();
- finish_wait(&memcg_oom_waitq, &wait);
+ finish_wait(&memcg_oom_waitq, &owait.wait);
}
mutex_lock(&memcg_oom_mutex);
mem_cgroup_oom_unlock(mem);
- /*
- * Here, we use global waitq .....more fine grained waitq ?
- * Assume following hierarchy.
- * A/
- * 01
- * 02
- * assume OOM happens both in A and 01 at the same time. Tthey are
- * mutually exclusive by lock. (kill in 01 helps A.)
- * When we use per memcg waitq, we have to wake up waiters on A and 02
- * in addtion to waiters on 01. We use global waitq for avoiding mess.
- * It will not be a big problem.
- * (And a task may be moved to other groups while it's waiting for OOM.)
- */
- wake_up_all(&memcg_oom_waitq);
+ memcg_wakeup_oom(mem);
mutex_unlock(&memcg_oom_mutex);
if (test_thread_flag(TIF_MEMDIE) || fatal_signal_pending(current))
_
Patches currently in -mm which might be from kamezawa.hiroyu@xxxxxxxxxxxxxx are
origin.patch
memcg-avoid-use-cmpxchg-in-swap-cgroup-maintainance.patch
memory-hotplug-allow-setting-of-phys_device.patch
memory-hotplug-s390-set-phys_device.patch
memcg-disable-move-charge-in-no-mmu-case.patch
memcontrol-fix-potential-null-deref.patch
linux-next.patch
cgroups-net_cls-as-module.patch
vfs-introduce-fmode_neg_offset-for-allowing-negative-f_pos.patch
memcg-oom-wakeup-filter.patch
memcg-oom-notifier.patch
memcg-oom-notifier-fix.patch
memcg-oom-kill-disable-and-oom-status.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
