On Thu, May 21, 2020 at 2:00 AM Naresh Kamboju
<naresh.kamboju@xxxxxxxxxx> wrote:
>
> On Wed, 20 May 2020 at 17:26, Naresh Kamboju <naresh.kamboju@xxxxxxxxxx> wrote:
> >
> >
> > This issue is specific on 32-bit architectures i386 and arm on linux-next tree.
> > As per the test results history this problem started happening from
> > Bad : next-20200430
> > Good : next-20200429
> >
> > steps to reproduce:
> > dd if=/dev/disk/by-id/ata-SanDisk_SSD_PLUS_120GB_190504A00573
> > of=/dev/null bs=1M count=2048
> > or
> > mkfs -t ext4 /dev/disk/by-id/ata-SanDisk_SSD_PLUS_120GB_190804A00BE5
> >
> >
> > Problem:
> > [ 38.802375] dd invoked oom-killer: gfp_mask=0x100cc0(GFP_USER),
> > order=0, oom_score_adj=0
>
> As a part of investigation on this issue LKFT teammate Anders Roxell
> git bisected the problem and found bad commit(s) which caused this problem.
>
> The following two patches have been reverted on next-20200519 and retested the
> reproducible steps and confirmed the test case mkfs -t ext4 got PASS.
> ( invoked oom-killer is gone now)
>
> Revert "mm, memcg: avoid stale protection values when cgroup is above
> protection"
> This reverts commit 23a53e1c02006120f89383270d46cbd040a70bc6.
>
> Revert "mm, memcg: decouple e{low,min} state mutations from protection
> checks"
> This reverts commit 7b88906ab7399b58bb088c28befe50bcce076d82.
>
My guess is that we made the same mistake in commit "mm, memcg:
decouple e{low,min} state mutations from protection
checks" that it read a stale memcg protection in
mem_cgroup_below_low() and mem_cgroup_below_min().
Bellow is a possble fix,
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 7a2c56fc..6591b71 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -391,20 +391,28 @@ static inline unsigned long
mem_cgroup_protection(struct mem_cgroup *root,
void mem_cgroup_calculate_protection(struct mem_cgroup *root,
struct mem_cgroup *memcg);
-static inline bool mem_cgroup_below_low(struct mem_cgroup *memcg)
+static inline bool mem_cgroup_below_low(struct mem_cgroup *root,
+ struct mem_cgroup *memcg)
{
if (mem_cgroup_disabled())
return false;
+ if (root == memcg)
+ return false;
+
return READ_ONCE(memcg->memory.elow) >=
page_counter_read(&memcg->memory);
}
-static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg)
+static inline bool mem_cgroup_below_min(struct mem_cgroup *root,
+ struct mem_cgroup *memcg)
{
if (mem_cgroup_disabled())
return false;
+ if (root == memcg)
+ return false;
+
return READ_ONCE(memcg->memory.emin) >=
page_counter_read(&memcg->memory);
}
@@ -896,12 +904,14 @@ static inline void
mem_cgroup_calculate_protection(struct mem_cgroup *root,
{
}
-static inline bool mem_cgroup_below_low(struct mem_cgroup *memcg)
+static inline bool mem_cgroup_below_low(struct mem_cgroup *root,
+ struct mem_cgroup *memcg)
{
return false;
}
-static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg)
+static inline bool mem_cgroup_below_min(struct mem_cgroup *root,
+ struct mem_cgroup *memcg)
{
return false;
}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index c71660e..fdcdd88 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2637,13 +2637,13 @@ static void shrink_node_memcgs(pg_data_t
*pgdat, struct scan_control *sc)
mem_cgroup_calculate_protection(target_memcg, memcg);
- if (mem_cgroup_below_min(memcg)) {
+ if (mem_cgroup_below_min(target_memcg, memcg)) {
/*
* Hard protection.
* If there is no reclaimable memory, OOM.
*/
continue;
- } else if (mem_cgroup_below_low(memcg)) {
+ } else if (mem_cgroup_below_low(target_memcg, memcg)) {
/*
* Soft protection.
* Respect the protection only as long as
> i386 test log shows mkfs -t ext4 pass
> https://lkft.validation.linaro.org/scheduler/job/1443405#L1200
>
> ref:
> https://lore.kernel.org/linux-mm/cover.1588092152.git.chris@xxxxxxxxxxxxxx/
> https://lore.kernel.org/linux-mm/CA+G9fYvzLm7n1BE7AJXd8_49fOgPgWWTiQ7sXkVre_zoERjQKg@xxxxxxxxxxxxxx/T/#t
>
> --
> Linaro LKFT
> https://lkft.linaro.org
--
Thanks
Yafang
