From nobody Tue Sep 29 13:17:26 2026 Received: from out-179.mta1.migadu.com (out-179.mta1.migadu.com [95.215.58.179]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 5B9FE379C48 for ; Fri, 7 Aug 2026 09:01:27 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=95.215.58.179 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1786093289; cv=none; b=dmtv3pt4MFy5y5ccsOmhG0EDgoXIjzj/jmtiwsemRV+gftniHm5inGaOfnN4Z22NXxq0avyJpRcg34koN8U+O7DaB/n2z0FLShCHG3HoVeuy0KylGNfcHCO2cheKVOkJ27edk6bhUVqpsv1F2dAGYOeMLn8biOSpNddgq7ytxck= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1786093289; c=relaxed/simple; bh=XKGAvX4djssbQ2ukdaAM8mQE5S74yHPFPdp45LKcSrs=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=HZIkbD1HW3kLwSO+bXrt6Fvp7qXd8ZVH/LrFKT5Y0uxBNovYypQu25TZRP0suHe0Uc7fMHCP7b4ojbJevtZfLTfmEkhRp3GBAgSKWxPT9bJvm2OuvKENJEk1wPKdhgJ59TqtPXnRP+1nfs3xKt2nvSWGd/1Jp0WS0lQJ81bLbmk= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.dev; spf=pass smtp.mailfrom=linux.dev; dkim=pass (1024-bit key) header.d=linux.dev header.i=@linux.dev header.b=W4paKvFA; arc=none smtp.client-ip=95.215.58.179 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.dev Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.dev Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux.dev header.i=@linux.dev header.b="W4paKvFA" X-Report-Abuse: Please report any abuse attempt to abuse@migadu.com and include these headers. DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.dev; s=key1; t=1786093285; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=iG7BQOUNjluMUKJPYfIHD5r/Uah0YPlbWHQVgLWehtU=; b=W4paKvFA++v1+lPM1ytHVfF0PZgUR7OB0TF6XKLapSuMujihGcrfh1cnW4DDbj0JgZF4hM uzcLPRGnqw+YY1zkx6ns8pfJsv7N2hXW4gK6iqyVohSLE+pv95PdLIOdAdnstM5ayQxb/b I+VmA6gxITBSkq9zeH/4MNwnK4FYdSw= From: Ridong To: Johannes Weiner , Michal Hocko , Roman Gushchin , Shakeel Butt , Andrew Morton Cc: Muchun Song , Tejun Heo , =?UTF-8?q?Michal=20Koutn=C3=BD?= , cgroups@vger.kernel.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org, Ridong Chen , cui.tao@linux.dev, Ridong Chen Subject: [PATCH v2 1/2] memcg: acquire peaks_lock when reading memory.peak Date: Fri, 7 Aug 2026 16:59:59 +0800 Message-Id: <20260807090000.1532495-2-ridong.chen@linux.dev> In-Reply-To: <20260807090000.1532495-1-ridong.chen@linux.dev> References: <20260807090000.1532495-1-ridong.chen@linux.dev> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Migadu-Flow: FLOW_OUT Content-Type: text/plain; charset="utf-8" From: Ridong Chen Sashiko reported that a reader can transiently observe a lower peak within a race window [1]. peak_show() returns max(local_watermark, ofp->value), but peak_write() updates those two under peaks_lock while the reader takes no lock. The interleaving is: writer (reset on fd A) reader (fd B) ---------------------- ------------- usage =3D page_counter_read(pc) WRITE_ONCE(local_watermark, usage) // watermark lowered to usage lw =3D READ_ONCE(local_watermark) // sees the lowered usage val =3D READ_ONCE(ofp->value) // B's value not updated yet return max(lw, val) // both low -> low peak WRITE_ONCE(peer_ctx->value, usage) // B updated, but too late Fix it by acquiring peaks_lock when reading the peak, so the reader sees a consistent snapshot of local_watermark and the per-fd values. The same race applies to memory.swap.peak, which shares peaks_lock and the peak_write() path, so take the lock there as well. [1] https://sashiko.dev/#/patchset/20260730115314.1069089-1-ridong.chen@lin= ux.dev?part=3D1 Fixes: c6f53ed8f213 ("mm, memcg: cg2 memory{.swap,}.peak write handlers") Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Ridong Chen Acked-by: Johannes Weiner Acked-by: Shakeel Butt --- mm/memcontrol.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index dd6b1c298345..2da55b778ae3 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4711,8 +4711,13 @@ static int peak_show(struct seq_file *sf, void *v, s= truct page_counter *pc) static int memory_peak_show(struct seq_file *sf, void *v) { struct mem_cgroup *memcg =3D mem_cgroup_from_css(seq_css(sf)); + int ret; =20 - return peak_show(sf, v, &memcg->memory); + spin_lock(&memcg->peaks_lock); + ret =3D peak_show(sf, v, &memcg->memory); + spin_unlock(&memcg->peaks_lock); + + return ret; } =20 static int peak_open(struct kernfs_open_file *of) @@ -5790,8 +5795,13 @@ static u64 swap_current_read(struct cgroup_subsys_st= ate *css, static int swap_peak_show(struct seq_file *sf, void *v) { struct mem_cgroup *memcg =3D mem_cgroup_from_css(seq_css(sf)); + int ret; =20 - return peak_show(sf, v, &memcg->swap); + spin_lock(&memcg->peaks_lock); + ret =3D peak_show(sf, v, &memcg->swap); + spin_unlock(&memcg->peaks_lock); + + return ret; } =20 static ssize_t swap_peak_write(struct kernfs_open_file *of, char *buf, --=20 2.34.1 From nobody Tue Sep 29 13:17:26 2026 Received: from out-179.mta1.migadu.com (out-179.mta1.migadu.com [95.215.58.179]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 63A06456DFD for ; Fri, 7 Aug 2026 09:01:32 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=95.215.58.179 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1786093294; cv=none; b=abLvDrcWN6ihuFOWH0YkjfFSfQwvTg7/Fu3AvIo+eYfulvBSSQ1Kc6BsRrtL/bv9xUitIsjyDwFcnMUoLGUQLFzh3NaANIOkoKVixWm6H/Wx4F8xw7jNthkMVPlz15AbS0YHl1MqvFDmjZ7uKVI7wW7sY503zfJrIjZ25b8HVZM= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1786093294; c=relaxed/simple; bh=RX8z9I7OnvV2npprIz+JGsArP2imG52U22R46ndOGIs=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=Wd/uiv6VPM9jIMaRfXLfiVdSGDD5wA+C8LHO+IU163wqsTgZXtNldicPGiYpLAcIfX99H/EUHpOQd1qWmyjFR5aypwH+8DpDOnj+K2IsDbB1wgaGnZV6RAWO8Vw6Idv9M0C6i7Ady4fO550rAzSXc3fJcSV0l0jG5CJvqolC0WQ= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.dev; spf=pass smtp.mailfrom=linux.dev; dkim=pass (1024-bit key) header.d=linux.dev header.i=@linux.dev header.b=pO2RGrX0; arc=none smtp.client-ip=95.215.58.179 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.dev Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.dev Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux.dev header.i=@linux.dev header.b="pO2RGrX0" X-Report-Abuse: Please report any abuse attempt to abuse@migadu.com and include these headers. DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.dev; s=key1; t=1786093290; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=1NsqwCylIQfggUS/ZnqvTGsvf2SS7Ne6C41Isj65uBs=; b=pO2RGrX0w7v5HhK+rJrWAW+Dx1crB29AW4wfl5lJuRzAwJYJlA0kcUK6n9xu3fL0BYM7FW 6ek77di8TrigMxcEobIEXgXiLuF9HObGxVQh3o/13a8nPOAsz3YMpIajZL/ss8NnuV+EgB OEhNrrjonR05/Y6EVQL5Kzz1ALEwjAo= From: Ridong To: Johannes Weiner , Michal Hocko , Roman Gushchin , Shakeel Butt , Andrew Morton Cc: Muchun Song , Tejun Heo , =?UTF-8?q?Michal=20Koutn=C3=BD?= , cgroups@vger.kernel.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org, Ridong Chen , cui.tao@linux.dev, Ridong Chen Subject: [PATCH v2 2/2] mm, memcg: fix memory.peak reset clobbering other fds' watermark Date: Fri, 7 Aug 2026 17:00:00 +0800 Message-Id: <20260807090000.1532495-3-ridong.chen@linux.dev> In-Reply-To: <20260807090000.1532495-1-ridong.chen@linux.dev> References: <20260807090000.1532495-1-ridong.chen@linux.dev> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Migadu-Flow: FLOW_OUT Content-Type: text/plain; charset="utf-8" From: Ridong Chen Writing to memory.peak resets the peak for that fd only. Each fd is a watcher and reads back max(its own value, the shared local_watermark). peak_write() resets by lowering local_watermark to the current usage. To keep the other watchers' peaks it then walks the watcher list, but it stores the current usage into them instead of the old watermark. So once usage has dropped from a peak, a reset on one fd wrongly drags every other fd's peak down too, even fds that never reset. Reproduced on 7.2.0-rc5-next under QEMU, two fds A and B on one cgroup: B sees the peak (410624 KB), usage drops, then A resets -- and B's peak collapses to 1060 KB although B never reset. With this patch B keeps reading 410624 KB. Fix: save the old watermark before lowering it and use that to floor the other watchers, so a reset only affects the fd that issued it. Fixes: c6f53ed8f213 ("mm, memcg: cg2 memory{.swap,}.peak write handlers") Assisted-by: Claude:claude-opus-4-8 Signed-off-by: Ridong Chen Acked-by: Johannes Weiner --- mm/memcontrol.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 2da55b778ae3..28577beeb3d0 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4746,7 +4746,7 @@ static ssize_t peak_write(struct kernfs_open_file *of= , char *buf, size_t nbytes, loff_t off, struct page_counter *pc, struct list_head *watchers) { - unsigned long usage; + unsigned long usage, peer_watermark; struct cgroup_of_peak *peer_ctx; struct mem_cgroup *memcg =3D mem_cgroup_from_css(of_css(of)); struct cgroup_of_peak *ofp =3D of_peak(of); @@ -4754,11 +4754,12 @@ static ssize_t peak_write(struct kernfs_open_file *= of, char *buf, size_t nbytes, spin_lock(&memcg->peaks_lock); =20 usage =3D page_counter_read(pc); + peer_watermark =3D max(usage, READ_ONCE(pc->local_watermark)); WRITE_ONCE(pc->local_watermark, usage); =20 list_for_each_entry(peer_ctx, watchers, list) - if (usage > peer_ctx->value) - WRITE_ONCE(peer_ctx->value, usage); + if (peer_ctx !=3D ofp && peer_watermark > peer_ctx->value) + WRITE_ONCE(peer_ctx->value, peer_watermark); =20 /* initial write, register watcher */ if (ofp->value =3D=3D OFP_PEAK_UNSET) --=20 2.34.1