From: Qi Zheng <qi.zheng@linux.dev>
To: hannes@cmpxchg.org, hughd@google.com, mhocko@suse.com,
roman.gushchin@linux.dev, shakeel.butt@linux.dev,
muchun.song@linux.dev, david@kernel.org,
lorenzo.stoakes@oracle.com, ziy@nvidia.com, harry.yoo@oracle.com,
yosry.ahmed@linux.dev, imran.f.khan@oracle.com,
kamalesh.babulal@oracle.com, axelrasmussen@google.com,
yuanchu@google.com, weixugc@google.com,
chenridong@huaweicloud.com, mkoutny@suse.com,
akpm@linux-foundation.org, hamzamahfooz@linux.microsoft.com,
apais@linux.microsoft.com, lance.yang@linux.dev, bhe@redhat.com,
usamaarif642@gmail.com
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
cgroups@vger.kernel.org, Qi Zheng <zhengqi.arch@bytedance.com>,
Yosry Ahmed <yosry@kernel.org>
Subject: [PATCH v6 30/33] mm: memcontrol: prepare for reparenting non-hierarchical stats
Date: Thu, 5 Mar 2026 19:52:48 +0800 [thread overview]
Message-ID: <e862995c45a7101a541284b6ebee5e5c32c89066.1772711148.git.zhengqi.arch@bytedance.com> (raw)
In-Reply-To: <cover.1772711148.git.zhengqi.arch@bytedance.com>
From: Qi Zheng <zhengqi.arch@bytedance.com>
To resolve the dying memcg issue, we need to reparent LRU folios of child
memcg to its parent memcg. This could cause problems for non-hierarchical
stats.
As Yosry Ahmed pointed out:
```
In short, if memory is charged to a dying cgroup at the time of
reparenting, when the memory gets uncharged the stats updates will occur
at the parent. This will update both hierarchical and non-hierarchical
stats of the parent, which would corrupt the parent's non-hierarchical
stats (because those counters were never incremented when the memory was
charged).
```
Now we have the following two types of non-hierarchical stats, and they
are only used in CONFIG_MEMCG_V1:
a. memcg->vmstats->state_local[i]
b. pn->lruvec_stats->state_local[i]
To ensure that these non-hierarchical stats work properly, we need to
reparent these non-hierarchical stats after reparenting LRU folios. To
this end, this commit makes the following preparations:
1. implement reparent_state_local() to reparent non-hierarchical stats
2. make css_killed_work_fn() to be called in rcu work, and implement
get_non_dying_memcg_start() and get_non_dying_memcg_end() to avoid race
between mod_memcg_state()/mod_memcg_lruvec_state()
and reparent_state_local()
Co-developed-by: Yosry Ahmed <yosry@kernel.org>
Signed-off-by: Yosry Ahmed <yosry@kernel.org>
Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
Acked-by: Shakeel Butt <shakeel.butt@linux.dev>
---
kernel/cgroup/cgroup.c | 9 ++--
mm/memcontrol-v1.c | 16 +++++++
mm/memcontrol-v1.h | 7 +++
mm/memcontrol.c | 97 ++++++++++++++++++++++++++++++++++++++++++
4 files changed, 125 insertions(+), 4 deletions(-)
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index be1d71dda3179..a9007f8aa029e 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -6044,8 +6044,9 @@ int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode)
*/
static void css_killed_work_fn(struct work_struct *work)
{
- struct cgroup_subsys_state *css =
- container_of(work, struct cgroup_subsys_state, destroy_work);
+ struct cgroup_subsys_state *css;
+
+ css = container_of(to_rcu_work(work), struct cgroup_subsys_state, destroy_rwork);
cgroup_lock();
@@ -6066,8 +6067,8 @@ static void css_killed_ref_fn(struct percpu_ref *ref)
container_of(ref, struct cgroup_subsys_state, refcnt);
if (atomic_dec_and_test(&css->online_cnt)) {
- INIT_WORK(&css->destroy_work, css_killed_work_fn);
- queue_work(cgroup_offline_wq, &css->destroy_work);
+ INIT_RCU_WORK(&css->destroy_rwork, css_killed_work_fn);
+ queue_rcu_work(cgroup_offline_wq, &css->destroy_rwork);
}
}
diff --git a/mm/memcontrol-v1.c b/mm/memcontrol-v1.c
index fe42ef664f1e1..51fb4406f45cf 100644
--- a/mm/memcontrol-v1.c
+++ b/mm/memcontrol-v1.c
@@ -1897,6 +1897,22 @@ static const unsigned int memcg1_events[] = {
PGMAJFAULT,
};
+void reparent_memcg1_state_local(struct mem_cgroup *memcg, struct mem_cgroup *parent)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++)
+ reparent_memcg_state_local(memcg, parent, memcg1_stats[i]);
+}
+
+void reparent_memcg1_lruvec_state_local(struct mem_cgroup *memcg, struct mem_cgroup *parent)
+{
+ int i;
+
+ for (i = 0; i < NR_LRU_LISTS; i++)
+ reparent_memcg_lruvec_state_local(memcg, parent, i);
+}
+
void memcg1_stat_format(struct mem_cgroup *memcg, struct seq_buf *s)
{
unsigned long memory, memsw;
diff --git a/mm/memcontrol-v1.h b/mm/memcontrol-v1.h
index 4041b5027a94b..05e6ff40f7556 100644
--- a/mm/memcontrol-v1.h
+++ b/mm/memcontrol-v1.h
@@ -77,6 +77,13 @@ void memcg1_uncharge_batch(struct mem_cgroup *memcg, unsigned long pgpgout,
unsigned long nr_memory, int nid);
void memcg1_stat_format(struct mem_cgroup *memcg, struct seq_buf *s);
+void reparent_memcg1_state_local(struct mem_cgroup *memcg, struct mem_cgroup *parent);
+void reparent_memcg1_lruvec_state_local(struct mem_cgroup *memcg, struct mem_cgroup *parent);
+
+void reparent_memcg_state_local(struct mem_cgroup *memcg,
+ struct mem_cgroup *parent, int idx);
+void reparent_memcg_lruvec_state_local(struct mem_cgroup *memcg,
+ struct mem_cgroup *parent, int idx);
void memcg1_account_kmem(struct mem_cgroup *memcg, int nr_pages);
static inline bool memcg1_tcpmem_active(struct mem_cgroup *memcg)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 23b70bd80ddc9..b0519a16f5684 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -226,6 +226,34 @@ static inline struct obj_cgroup *__memcg_reparent_objcgs(struct mem_cgroup *memc
return objcg;
}
+#ifdef CONFIG_MEMCG_V1
+static void __mem_cgroup_flush_stats(struct mem_cgroup *memcg, bool force);
+
+static inline void reparent_state_local(struct mem_cgroup *memcg, struct mem_cgroup *parent)
+{
+ if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
+ return;
+
+ /*
+ * Reparent stats exposed non-hierarchically. Flush @memcg's stats first
+ * to read its stats accurately , and conservatively flush @parent's
+ * stats after reparenting to avoid hiding a potentially large stat
+ * update (e.g. from callers of mem_cgroup_flush_stats_ratelimited()).
+ */
+ __mem_cgroup_flush_stats(memcg, true);
+
+ /* The following counts are all non-hierarchical and need to be reparented. */
+ reparent_memcg1_state_local(memcg, parent);
+ reparent_memcg1_lruvec_state_local(memcg, parent);
+
+ __mem_cgroup_flush_stats(parent, true);
+}
+#else
+static inline void reparent_state_local(struct mem_cgroup *memcg, struct mem_cgroup *parent)
+{
+}
+#endif
+
static inline void reparent_locks(struct mem_cgroup *memcg, struct mem_cgroup *parent)
{
spin_lock_irq(&objcg_lock);
@@ -473,6 +501,30 @@ unsigned long lruvec_page_state_local(struct lruvec *lruvec,
return x;
}
+#ifdef CONFIG_MEMCG_V1
+static void __mod_memcg_lruvec_state(struct mem_cgroup_per_node *pn,
+ enum node_stat_item idx, int val);
+
+void reparent_memcg_lruvec_state_local(struct mem_cgroup *memcg,
+ struct mem_cgroup *parent, int idx)
+{
+ int nid;
+
+ for_each_node(nid) {
+ struct lruvec *child_lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(nid));
+ struct lruvec *parent_lruvec = mem_cgroup_lruvec(parent, NODE_DATA(nid));
+ unsigned long value = lruvec_page_state_local(child_lruvec, idx);
+ struct mem_cgroup_per_node *child_pn, *parent_pn;
+
+ child_pn = container_of(child_lruvec, struct mem_cgroup_per_node, lruvec);
+ parent_pn = container_of(parent_lruvec, struct mem_cgroup_per_node, lruvec);
+
+ __mod_memcg_lruvec_state(child_pn, idx, -value);
+ __mod_memcg_lruvec_state(parent_pn, idx, value);
+ }
+}
+#endif
+
/* Subset of vm_event_item to report for memcg event stats */
static const unsigned int memcg_vm_event_stat[] = {
#ifdef CONFIG_MEMCG_V1
@@ -718,6 +770,42 @@ static int memcg_state_val_in_pages(int idx, int val)
return max(val * unit / PAGE_SIZE, 1UL);
}
+#ifdef CONFIG_MEMCG_V1
+/*
+ * Used in mod_memcg_state() and mod_memcg_lruvec_state() to avoid race with
+ * reparenting of non-hierarchical state_locals.
+ */
+static inline struct mem_cgroup *get_non_dying_memcg_start(struct mem_cgroup *memcg)
+{
+ if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
+ return memcg;
+
+ rcu_read_lock();
+
+ while (memcg_is_dying(memcg))
+ memcg = parent_mem_cgroup(memcg);
+
+ return memcg;
+}
+
+static inline void get_non_dying_memcg_end(void)
+{
+ if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
+ return;
+
+ rcu_read_unlock();
+}
+#else
+static inline struct mem_cgroup *get_non_dying_memcg_start(struct mem_cgroup *memcg)
+{
+ return memcg;
+}
+
+static inline void get_non_dying_memcg_end(void)
+{
+}
+#endif
+
static void __mod_memcg_state(struct mem_cgroup *memcg,
enum memcg_stat_item idx, int val)
{
@@ -769,6 +857,15 @@ unsigned long memcg_page_state_local(struct mem_cgroup *memcg, int idx)
#endif
return x;
}
+
+void reparent_memcg_state_local(struct mem_cgroup *memcg,
+ struct mem_cgroup *parent, int idx)
+{
+ unsigned long value = memcg_page_state_local(memcg, idx);
+
+ __mod_memcg_state(memcg, idx, -value);
+ __mod_memcg_state(parent, idx, value);
+}
#endif
static void __mod_memcg_lruvec_state(struct mem_cgroup_per_node *pn,
--
2.20.1
next prev parent reply other threads:[~2026-03-05 11:59 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-03-05 11:52 [PATCH v6 00/33] Eliminate Dying Memory Cgroup Qi Zheng
2026-03-05 11:52 ` [PATCH v6 01/33] mm: memcontrol: remove dead code of checking parent memory cgroup Qi Zheng
2026-03-05 11:52 ` [PATCH v6 02/33] mm: workingset: use folio_lruvec() in workingset_refault() Qi Zheng
2026-03-05 11:52 ` [PATCH v6 03/33] mm: rename unlock_page_lruvec_irq and its variants Qi Zheng
2026-03-05 11:52 ` [PATCH v6 04/33] mm: vmscan: prepare for the refactoring the move_folios_to_lru() Qi Zheng
2026-03-05 11:52 ` [PATCH v6 05/33] mm: vmscan: refactor move_folios_to_lru() Qi Zheng
2026-03-05 11:52 ` [PATCH v6 06/33] mm: memcontrol: allocate object cgroup for non-kmem case Qi Zheng
2026-03-05 11:52 ` [PATCH v6 07/33] mm: memcontrol: return root object cgroup for root memory cgroup Qi Zheng
2026-03-05 11:52 ` [PATCH v6 08/33] mm: memcontrol: prevent memory cgroup release in get_mem_cgroup_from_folio() Qi Zheng
2026-03-05 11:52 ` [PATCH v6 09/33] buffer: prevent memory cgroup release in folio_alloc_buffers() Qi Zheng
2026-03-05 11:52 ` [PATCH v6 10/33] writeback: prevent memory cgroup release in writeback module Qi Zheng
2026-03-05 11:52 ` [PATCH v6 11/33] mm: memcontrol: prevent memory cgroup release in count_memcg_folio_events() Qi Zheng
2026-03-05 11:52 ` [PATCH v6 12/33] mm: page_io: prevent memory cgroup release in page_io module Qi Zheng
2026-03-05 11:52 ` [PATCH v6 13/33] mm: migrate: prevent memory cgroup release in folio_migrate_mapping() Qi Zheng
2026-03-05 11:52 ` [PATCH v6 14/33] mm: mglru: prevent memory cgroup release in mglru Qi Zheng
2026-03-05 11:52 ` [PATCH v6 15/33] mm: memcontrol: prevent memory cgroup release in mem_cgroup_swap_full() Qi Zheng
2026-03-05 11:52 ` [PATCH v6 16/33] mm: workingset: prevent memory cgroup release in lru_gen_eviction() Qi Zheng
2026-03-05 11:52 ` [PATCH v6 17/33] mm: thp: prevent memory cgroup release in folio_split_queue_lock{_irqsave}() Qi Zheng
2026-03-05 11:52 ` [PATCH v6 18/33] mm: zswap: prevent memory cgroup release in zswap_compress() Qi Zheng
2026-03-05 11:52 ` [PATCH v6 19/33] mm: workingset: prevent lruvec release in workingset_refault() Qi Zheng
2026-03-05 11:52 ` [PATCH v6 20/33] mm: zswap: prevent lruvec release in zswap_folio_swapin() Qi Zheng
2026-03-05 11:52 ` [PATCH v6 21/33] mm: swap: prevent lruvec release in lru_gen_clear_refs() Qi Zheng
2026-03-05 11:52 ` [PATCH v6 22/33] mm: workingset: prevent lruvec release in workingset_activation() Qi Zheng
2026-03-05 11:52 ` [PATCH v6 23/33] mm: do not open-code lruvec lock Qi Zheng
2026-03-05 11:52 ` [PATCH v6 24/33] mm: memcontrol: prepare for reparenting LRU pages for " Qi Zheng
2026-03-05 11:52 ` [PATCH v6 25/33] mm: vmscan: prepare for reparenting traditional LRU folios Qi Zheng
2026-03-05 11:52 ` [PATCH v6 26/33] mm: vmscan: prepare for reparenting MGLRU folios Qi Zheng
2026-03-05 11:52 ` [PATCH v6 27/33] mm: memcontrol: refactor memcg_reparent_objcgs() Qi Zheng
2026-03-05 11:52 ` [PATCH v6 28/33] mm: workingset: use lruvec_lru_size() to get the number of lru pages Qi Zheng
2026-03-05 11:52 ` [PATCH v6 29/33] mm: memcontrol: refactor mod_memcg_state() and mod_memcg_lruvec_state() Qi Zheng
2026-03-05 11:52 ` Qi Zheng [this message]
2026-03-05 11:52 ` [PATCH v6 31/33] mm: memcontrol: convert objcg to be per-memcg per-node type Qi Zheng
2026-03-05 11:52 ` [PATCH v6 32/33] mm: memcontrol: eliminate the problem of dying memory cgroup for LRU folios Qi Zheng
2026-03-05 11:52 ` [PATCH v6 33/33] mm: lru: add VM_WARN_ON_ONCE_FOLIO to lru maintenance helpers Qi Zheng
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=e862995c45a7101a541284b6ebee5e5c32c89066.1772711148.git.zhengqi.arch@bytedance.com \
--to=qi.zheng@linux.dev \
--cc=akpm@linux-foundation.org \
--cc=apais@linux.microsoft.com \
--cc=axelrasmussen@google.com \
--cc=bhe@redhat.com \
--cc=cgroups@vger.kernel.org \
--cc=chenridong@huaweicloud.com \
--cc=david@kernel.org \
--cc=hamzamahfooz@linux.microsoft.com \
--cc=hannes@cmpxchg.org \
--cc=harry.yoo@oracle.com \
--cc=hughd@google.com \
--cc=imran.f.khan@oracle.com \
--cc=kamalesh.babulal@oracle.com \
--cc=lance.yang@linux.dev \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lorenzo.stoakes@oracle.com \
--cc=mhocko@suse.com \
--cc=mkoutny@suse.com \
--cc=muchun.song@linux.dev \
--cc=roman.gushchin@linux.dev \
--cc=shakeel.butt@linux.dev \
--cc=usamaarif642@gmail.com \
--cc=weixugc@google.com \
--cc=yosry.ahmed@linux.dev \
--cc=yosry@kernel.org \
--cc=yuanchu@google.com \
--cc=zhengqi.arch@bytedance.com \
--cc=ziy@nvidia.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox