The patch titled
Subject: mm, oom: refactor dump_tasks for memcg OOMs
has been added to the -mm tree. Its filename is
mm-oom-refactor-dump_tasks-for-memcg-ooms.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-oom-refactor-dump_tasks-for-memcg-ooms.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-oom-refactor-dump_tasks-for-memcg-ooms.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/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Shakeel Butt <shakeelb@xxxxxxxxxx>
Subject: mm, oom: refactor dump_tasks for memcg OOMs
dump_tasks() currently goes through all the processes present on the
system even for memcg OOMs. Change dump_tasks() similar to
select_bad_process() and use mem_cgroup_scan_tasks() to selectively
traverse the processes of the memcgs during memcg OOM.
Link: http://lkml.kernel.org/r/20190617231207.160865-1-shakeelb@xxxxxxxxxx
Signed-off-by: Shakeel Butt <shakeelb@xxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Tetsuo Handa <penguin-kernel@xxxxxxxxxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Roman Gushchin <guro@xxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/oom_kill.c | 72 ++++++++++++++++++++++++++++--------------------
1 file changed, 42 insertions(+), 30 deletions(-)
--- a/mm/oom_kill.c~mm-oom-refactor-dump_tasks-for-memcg-ooms
+++ a/mm/oom_kill.c
@@ -385,10 +385,38 @@ static void select_bad_process(struct oo
oc->chosen_points = oc->chosen_points * 1000 / oc->totalpages;
}
+static int dump_task(struct task_struct *p, void *arg)
+{
+ struct oom_control *oc = arg;
+ struct task_struct *task;
+
+ if (oom_unkillable_task(p, NULL, oc->nodemask))
+ return 0;
+
+ task = find_lock_task_mm(p);
+ if (!task) {
+ /*
+ * This is a kthread or all of p's threads have already
+ * detached their mm's. There's no need to report
+ * them; they can't be oom killed anyway.
+ */
+ return 0;
+ }
+
+ pr_info("[%7d] %5d %5d %8lu %8lu %8ld %8lu %5hd %s\n",
+ task->pid, from_kuid(&init_user_ns, task_uid(task)),
+ task->tgid, task->mm->total_vm, get_mm_rss(task->mm),
+ mm_pgtables_bytes(task->mm),
+ get_mm_counter(task->mm, MM_SWAPENTS),
+ task->signal->oom_score_adj, task->comm);
+ task_unlock(task);
+
+ return 0;
+}
+
/**
* dump_tasks - dump current memory state of all system tasks
- * @memcg: current's memory controller, if constrained
- * @nodemask: nodemask passed to page allocator for mempolicy ooms
+ * @oc: pointer to struct oom_control
*
* Dumps the current memory state of all eligible tasks. Tasks not in the same
* memcg, not in the same cpuset, or bound to a disjoint set of mempolicy nodes
@@ -396,37 +424,21 @@ static void select_bad_process(struct oo
* State information includes task's pid, uid, tgid, vm size, rss,
* pgtables_bytes, swapents, oom_score_adj value, and name.
*/
-static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask)
+static void dump_tasks(struct oom_control *oc)
{
- struct task_struct *p;
- struct task_struct *task;
-
pr_info("Tasks state (memory values in pages):\n");
pr_info("[ pid ] uid tgid total_vm rss pgtables_bytes swapents oom_score_adj name\n");
- rcu_read_lock();
- for_each_process(p) {
- if (oom_unkillable_task(p, memcg, nodemask))
- continue;
-
- task = find_lock_task_mm(p);
- if (!task) {
- /*
- * This is a kthread or all of p's threads have already
- * detached their mm's. There's no need to report
- * them; they can't be oom killed anyway.
- */
- continue;
- }
-
- pr_info("[%7d] %5d %5d %8lu %8lu %8ld %8lu %5hd %s\n",
- task->pid, from_kuid(&init_user_ns, task_uid(task)),
- task->tgid, task->mm->total_vm, get_mm_rss(task->mm),
- mm_pgtables_bytes(task->mm),
- get_mm_counter(task->mm, MM_SWAPENTS),
- task->signal->oom_score_adj, task->comm);
- task_unlock(task);
+
+ if (is_memcg_oom(oc))
+ mem_cgroup_scan_tasks(oc->memcg, dump_task, oc);
+ else {
+ struct task_struct *p;
+
+ rcu_read_lock();
+ for_each_process(p)
+ dump_task(p, oc);
+ rcu_read_unlock();
}
- rcu_read_unlock();
}
static void dump_oom_summary(struct oom_control *oc, struct task_struct *victim)
@@ -458,7 +470,7 @@ static void dump_header(struct oom_contr
dump_unreclaimable_slab();
}
if (sysctl_oom_dump_tasks)
- dump_tasks(oc->memcg, oc->nodemask);
+ dump_tasks(oc);
if (p)
dump_oom_summary(oc, p);
}
_
Patches currently in -mm which might be from shakeelb@xxxxxxxxxx are
memcg-oom-no-oom-kill-for-__gfp_retry_mayfail.patch
memcg-fsnotify-no-oom-kill-for-remote-memcg-charging.patch
mm-memcg-introduce-memoryeventslocal.patch
mm-oom-refactor-dump_tasks-for-memcg-ooms.patch
mm-oom-fix-oom_unkillable_task-for-memcg-ooms.patch
