Re: [PATCH stable v5.8] mm: memcg: fix memcg reclaim soft lockup
From: Greg KH
Date: Mon Sep 21 2020 - 12:11:48 EST
On Thu, Sep 17, 2020 at 06:19:13PM -0700, Julius Hemanth Pitti wrote:
> From: Xunlei Pang <xlpang@xxxxxxxxxxxxxxxxx>
> commit e3336cab2579012b1e72b5265adf98e2d6e244ad upstream.
> We've met softlockup with "CONFIG_PREEMPT_NONE=y", when the target memcg
> doesn't have any reclaimable memory.
> It can be easily reproduced as below:
> watchdog: BUG: soft lockup - CPU#0 stuck for 111s![memcg_test:2204]
> CPU: 0 PID: 2204 Comm: memcg_test Not tainted 5.9.0-rc2+ #12
> Call Trace:
> It only happens on our 1-vcpu instances, because there's no chance for
> oom reaper to run to reclaim the to-be-killed process.
> Add a cond_resched() at the upper shrink_node_memcgs() to solve this
> issue, this will mean that we will get a scheduling point for each memcg
> in the reclaimed hierarchy without any dependency on the reclaimable
> memory in that memcg thus making it more predictable.
> Suggested-by: Michal Hocko <mhocko@xxxxxxxx>
> Signed-off-by: Xunlei Pang <xlpang@xxxxxxxxxxxxxxxxx>
> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
> Acked-by: Chris Down <chris@xxxxxxxxxxxxxx>
> Acked-by: Michal Hocko <mhocko@xxxxxxxx>
> Acked-by: Johannes Weiner <hannes@xxxxxxxxxxx>
> Link: http://lkml.kernel.org/r/1598495549-67324-1-git-send-email-xlpang@xxxxxxxxxxxxxxxxx
> Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
> Fixes: b0dedc49a2da ("mm/vmscan.c: iterate only over charged shrinkers during memcg shrink_slab()")
> Cc: stable@xxxxxxxxxxxxxxx
> Signed-off-by: Julius Hemanth Pitti <jpitti@xxxxxxxxx>
> mm/vmscan.c | 8 ++++++++
> 1 file changed, 8 insertions(+)
The Fixes: tag you show here goes back to 4.19, can you provide a 4.19.y
and 5.4.y version of this as well?