From: Ridong Chen <chenridong@xiaomi.com>

The memory.peak / memory.swap.peak per-fd watermark tracking has two
issues. Each open fd is a watcher and reads back max(its own value, the
shared local_watermark); both bugs live in that scheme.

Worst case for both is the same and is userspace-visible: a reader of
memory.peak (or memory.swap.peak) gets a value lower than the true peak,
so a tool that sizes or bills a cgroup by its peak usage under-reports it.

Patch 1 (read side) fixes the race Sashiko pointed out in the v1 review
[1]: peak_show() inspects local_watermark and the per-fd values without
holding peaks_lock, so a reader that races an unrelated peak_write()
reset briefly observes the lowered value. Transient. It takes peaks_lock
in the show path.

Patch 2 (write side) fixes peak_write(): on a reset it stores the
current usage into the other watchers instead of the old watermark, so
once usage has dropped from a peak a reset on one fd drags every other
fd's peak down too, even fds that never reset.

---
Changes since v3:
- Switch to guard(spinlock) in the peak readers, suggested by Muchun.

Changes since v2:
- Spell out the worst-case userspace-visible effect, per Andrew's
  Go back to v1 [2].

Changes since v1:
 - New patch 1: hold peaks_lock in the peak readers (Sashiko).
 - Patch 2: floor the peers with max(usage, local_watermark), mirroring
   peak_show(), and skip the writing fd (Johannes Weiner).

[1] https://sashiko.dev/#/patchset/20260730115314.1069089-1-ridong.chen@linux.dev?part=1
[2] https://lore.kernel.org/all/20260730115314.1069089-1-ridong.chen@linux.dev/

Ridong Chen (2):
  memcg: acquire peaks_lock when reading memory.peak
  mm, memcg: fix memory.peak reset clobbering other fds' watermark

 mm/memcontrol.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

-- 
2.34.1

On 8/14/2026 11:30 AM, Ridong Chen wrote:
> From: Ridong Chen <chenridong@xiaomi.com>
> 
> The memory.peak / memory.swap.peak per-fd watermark tracking has two
> issues. Each open fd is a watcher and reads back max(its own value, the
> shared local_watermark); both bugs live in that scheme.
> 
> Worst case for both is the same and is userspace-visible: a reader of
> memory.peak (or memory.swap.peak) gets a value lower than the true peak,
> so a tool that sizes or bills a cgroup by its peak usage under-reports it.
> 
> Patch 1 (read side) fixes the race Sashiko pointed out in the v1 review
> [1]: peak_show() inspects local_watermark and the per-fd values without
> holding peaks_lock, so a reader that races an unrelated peak_write()
> reset briefly observes the lowered value. Transient. It takes peaks_lock
> in the show path.
> 
> Patch 2 (write side) fixes peak_write(): on a reset it stores the
> current usage into the other watchers instead of the old watermark, so
> once usage has dropped from a peak a reset on one fd drags every other
> fd's peak down too, even fds that never reset.
> 
> ---
> Changes since v3:
> - Switch to guard(spinlock) in the peak readers, suggested by Muchun.
> 
> Changes since v2:
> - Spell out the worst-case userspace-visible effect, per Andrew's
>    Go back to v1 [2].
> 
> Changes since v1:
>   - New patch 1: hold peaks_lock in the peak readers (Sashiko).
>   - Patch 2: floor the peers with max(usage, local_watermark), mirroring
>     peak_show(), and skip the writing fd (Johannes Weiner).
> 
> [1] https://sashiko.dev/#/patchset/20260730115314.1069089-1-ridong.chen@linux.dev?part=1
> [2] https://lore.kernel.org/all/20260730115314.1069089-1-ridong.chen@linux.dev/
> 
> Ridong Chen (2):
>    memcg: acquire peaks_lock when reading memory.peak
>    mm, memcg: fix memory.peak reset clobbering other fds' watermark
> 
>   mm/memcontrol.c | 9 ++++++---
>   1 file changed, 6 insertions(+), 3 deletions(-)
> 

Hi all,

Just a quick reminder on this series, could it be applied?
Sending this note in case it got buried.

-- 
Best regards
Ridong

On Thu, 20 Aug 2026 16:43:23 +0800 Ridong Chen <ridong.chen@linux.dev> wrote:

> 
> 
> > 
> > Ridong Chen (2):
> >    memcg: acquire peaks_lock when reading memory.peak
> >    mm, memcg: fix memory.peak reset clobbering other fds' watermark
> > 
> >   mm/memcontrol.c | 9 ++++++---
> >   1 file changed, 6 insertions(+), 3 deletions(-)
> > 
> 
> Hi all,
> 
> Just a quick reminder on this series, could it be applied?
> Sending this note in case it got buried.

New material doesn't get a lot of attention during late -rc and during
the merge window.  I've set this series aside for consideration late in the
merge window, but a resend at that time (or shortly after -rc1) would
be helpful.