The patch titled
Subject: OOM, PM: OOM killed task cannot escape PM suspend
has been added to the -mm tree. Its filename is
oom-pm-oom-killed-task-cannot-escape-pm-suspend.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/oom-pm-oom-killed-task-cannot-escape-pm-suspend.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/oom-pm-oom-killed-task-cannot-escape-pm-suspend.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 ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Michal Hocko <mhocko@xxxxxxx>
Subject: OOM, PM: OOM killed task cannot escape PM suspend
PM freezer relies on having all tasks frozen by the time devices are
getting frozen so that no task will touch them while they are getting
frozen. But OOM killer is allowed to kill an already frozen task in order
to handle OOM situtation. In order to protect from late wake ups OOM
killer is disabled after all tasks are frozen. This, however, still keeps
a window open when a killed task didn't manage to die by the time
freeze_processes finishes.
Fix this race by checking all tasks after OOM killer has been disabled.
To prevent from useless check also introduce and check oom_kills count
which gets incremented when a task is killed by OOM killer. All the tasks
have to be checked only if the counter changes.
Fixes: f660daac474c6f (oom: thaw threads if oom killed thread is frozen before deferring)
Signed-off-by: Michal Hocko <mhocko@xxxxxxx>
Cc: Cong Wang <xiyou.wangcong@xxxxxxxxx>
Cc: Rafael J. Wysocki <rjw@xxxxxxxxxxxxx>
Cc: Tejun Heo <tj@xxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx> [3.2+]
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/oom.h | 2 ++
kernel/power/process.c | 31 ++++++++++++++++++++++++++++++-
mm/oom_kill.c | 14 ++++++++++++++
3 files changed, 46 insertions(+), 1 deletion(-)
diff -puN include/linux/oom.h~oom-pm-oom-killed-task-cannot-escape-pm-suspend include/linux/oom.h
--- a/include/linux/oom.h~oom-pm-oom-killed-task-cannot-escape-pm-suspend
+++ a/include/linux/oom.h
@@ -50,6 +50,8 @@ static inline bool oom_task_origin(const
extern unsigned long oom_badness(struct task_struct *p,
struct mem_cgroup *memcg, const nodemask_t *nodemask,
unsigned long totalpages);
+
+extern int oom_kills_count(void);
extern void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
unsigned int points, unsigned long totalpages,
struct mem_cgroup *memcg, nodemask_t *nodemask,
diff -puN kernel/power/process.c~oom-pm-oom-killed-task-cannot-escape-pm-suspend kernel/power/process.c
--- a/kernel/power/process.c~oom-pm-oom-killed-task-cannot-escape-pm-suspend
+++ a/kernel/power/process.c
@@ -118,6 +118,7 @@ static int try_to_freeze_tasks(bool user
int freeze_processes(void)
{
int error;
+ int oom_kills_saved;
error = __usermodehelper_disable(UMH_FREEZING);
if (error)
@@ -132,12 +133,40 @@ int freeze_processes(void)
pm_wakeup_clear();
printk("Freezing user space processes ... ");
pm_freezing = true;
+ oom_kills_saved = oom_kills_count();
error = try_to_freeze_tasks(true);
if (!error) {
- printk("done.");
__usermodehelper_set_disable_depth(UMH_DISABLED);
oom_killer_disable();
+
+ /*
+ * There was a OOM kill while we were freezing tasks
+ * and the killed task might be still on the way out
+ * so we have to double check for race.
+ */
+ if (oom_kills_count() != oom_kills_saved) {
+ struct task_struct *g, *p;
+
+ read_lock(&tasklist_lock);
+ do_each_thread(g, p) {
+ if (p == current || freezer_should_skip(p) ||
+ frozen(p))
+ continue;
+ error = -EBUSY;
+ break;
+ } while_each_thread(g, p);
+ read_unlock(&tasklist_lock);
+
+ if (error) {
+ __usermodehelper_set_disable_depth(UMH_ENABLED);
+ oom_killer_enable();
+ printk("OOM in progress. ");
+ goto done;
+ }
+ }
+ printk("done.");
}
+done:
printk("\n");
BUG_ON(in_atomic());
diff -puN mm/oom_kill.c~oom-pm-oom-killed-task-cannot-escape-pm-suspend mm/oom_kill.c
--- a/mm/oom_kill.c~oom-pm-oom-killed-task-cannot-escape-pm-suspend
+++ a/mm/oom_kill.c
@@ -402,6 +402,18 @@ static void dump_header(struct task_stru
dump_tasks(memcg, nodemask);
}
+/*
+ * Number of OOM killer invocations (including memcg OOM killer).
+ * Primarily used by PM freezer to check for potential races with
+ * OOM killed frozen task.
+ */
+static atomic_t oom_kills = ATOMIC_INIT(0);
+
+int oom_kills_count(void)
+{
+ return atomic_read(&oom_kills);
+}
+
#define K(x) ((x) << (PAGE_SHIFT-10))
/*
* Must be called while holding a reference to p, which will be released upon
@@ -504,11 +516,13 @@ void oom_kill_process(struct task_struct
pr_err("Kill process %d (%s) sharing same memory\n",
task_pid_nr(p), p->comm);
task_unlock(p);
+ atomic_inc(&oom_kills);
do_send_sig_info(SIGKILL, SEND_SIG_FORCED, p, true);
}
rcu_read_unlock();
set_tsk_thread_flag(victim, TIF_MEMDIE);
+ atomic_inc(&oom_kills);
do_send_sig_info(SIGKILL, SEND_SIG_FORCED, victim, true);
put_task_struct(victim);
}
_
Patches currently in -mm which might be from mhocko@xxxxxxx are
origin.patch
cgroup-kmemleak-add-kmemleak_free-for-cgroup-deallocations.patch
mm-memcontrol-lockless-page-counters.patch
mm-hugetlb_cgroup-convert-to-lockless-page-counters.patch
kernel-res_counter-remove-the-unused-api.patch
mm-memcontrol-convert-reclaim-iterator-to-simple-css-refcounting.patch
mm-memcontrol-take-a-css-reference-for-each-charged-page.patch
mm-memcontrol-remove-obsolete-kmemcg-pinning-tricks.patch
mm-memcontrol-continue-cache-reclaim-from-offlined-groups.patch
mm-memcontrol-remove-synchroneous-stock-draining-code.patch
freezer-check-oom-kill-while-being-frozen.patch
freezer-remove-obsolete-comments-in-__thaw_task.patch
oom-pm-oom-killed-task-cannot-escape-pm-suspend.patch
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html