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
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
cgroups@vger.kernel.org, Qi Zheng <zhengqi.arch@bytedance.com>
Subject: [PATCH v3 28/30] mm: memcontrol: prepare for reparenting state_local
Date: Wed, 14 Jan 2026 19:32:55 +0800 [thread overview]
Message-ID: <b11a0bde9fe18673a61a79398f226ad7cb04a894.1768389889.git.zhengqi.arch@bytedance.com> (raw)
In-Reply-To: <cover.1768389889.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. The following counts are all non-hierarchical
and need to be reparented to prevent the counts of parent memcg overflow.
1. memcg->vmstats->state_local[i]
2. pn->lruvec_stats->state_local[i]
This commit implements the specific function, which will be used during
the reparenting process.
Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
---
include/linux/memcontrol.h | 4 +++
mm/memcontrol-v1.c | 16 +++++++++++
mm/memcontrol-v1.h | 3 ++
mm/memcontrol.c | 56 ++++++++++++++++++++++++++++++++++++++
4 files changed, 79 insertions(+)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 26c3c0e375f58..f84a23f13ffb4 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -963,12 +963,16 @@ static inline void mod_memcg_page_state(struct page *page,
unsigned long memcg_events(struct mem_cgroup *memcg, int event);
unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx);
+void reparent_memcg_state_local(struct mem_cgroup *memcg,
+ struct mem_cgroup *parent, int idx);
unsigned long memcg_page_state_output(struct mem_cgroup *memcg, int item);
bool memcg_stat_item_valid(int idx);
bool memcg_vm_event_item_valid(enum vm_event_item idx);
unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx);
unsigned long lruvec_page_state_local(struct lruvec *lruvec,
enum node_stat_item idx);
+void reparent_memcg_lruvec_state_local(struct mem_cgroup *memcg,
+ struct mem_cgroup *parent, int idx);
void mem_cgroup_flush_stats(struct mem_cgroup *memcg);
void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg);
diff --git a/mm/memcontrol-v1.c b/mm/memcontrol-v1.c
index f0ef650d2317b..800606135e7ba 100644
--- a/mm/memcontrol-v1.c
+++ b/mm/memcontrol-v1.c
@@ -1898,6 +1898,22 @@ 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 < ARRAY_SIZE(memcg1_stats); i++)
+ reparent_memcg_lruvec_state_local(memcg, parent, memcg1_stats[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 eb3c3c1056574..45528195d3578 100644
--- a/mm/memcontrol-v1.h
+++ b/mm/memcontrol-v1.h
@@ -41,6 +41,7 @@ static inline bool do_memsw_account(void)
unsigned long memcg_events_local(struct mem_cgroup *memcg, int event);
unsigned long memcg_page_state_local(struct mem_cgroup *memcg, int idx);
+void mod_memcg_page_state_local(struct mem_cgroup *memcg, int idx, unsigned long val);
unsigned long memcg_page_state_local_output(struct mem_cgroup *memcg, int item);
bool memcg1_alloc_events(struct mem_cgroup *memcg);
void memcg1_free_events(struct mem_cgroup *memcg);
@@ -73,6 +74,8 @@ 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 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 70583394f421f..7aa32b97c9f17 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -225,6 +225,28 @@ 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;
+
+ synchronize_rcu();
+
+ __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);
+}
+#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);
@@ -458,6 +480,28 @@ unsigned long lruvec_page_state_local(struct lruvec *lruvec,
return x;
}
+void reparent_memcg_lruvec_state_local(struct mem_cgroup *memcg,
+ struct mem_cgroup *parent, int idx)
+{
+ int i = memcg_stats_index(idx);
+ int nid;
+
+ if (WARN_ONCE(BAD_STAT_IDX(i), "%s: missing stat item %d\n", __func__, idx))
+ return;
+
+ 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));
+ struct mem_cgroup_per_node *parent_pn;
+ unsigned long value = lruvec_page_state_local(child_lruvec, idx);
+
+ parent_pn = container_of(parent_lruvec, struct mem_cgroup_per_node, lruvec);
+
+ WRITE_ONCE(parent_pn->lruvec_stats->state_local[i],
+ parent_pn->lruvec_stats->state_local[i] + value);
+ }
+}
+
/* Subset of vm_event_item to report for memcg event stats */
static const unsigned int memcg_vm_event_stat[] = {
#ifdef CONFIG_MEMCG_V1
@@ -757,6 +801,18 @@ 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)
+{
+ int i = memcg_stats_index(idx);
+ unsigned long value = memcg_page_state_local(memcg, idx);
+
+ if (WARN_ONCE(BAD_STAT_IDX(i), "%s: missing stat item %d\n", __func__, idx))
+ return;
+
+ WRITE_ONCE(parent->vmstats->state_local[i], parent->vmstats->state_local[i] + value);
+}
#endif
static void mod_memcg_lruvec_state(struct lruvec *lruvec,
--
2.20.1
next prev parent reply other threads:[~2026-01-14 11:36 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-01-14 11:26 [PATCH v3 00/30] Eliminate Dying Memory Cgroup Qi Zheng
2026-01-14 11:26 ` [PATCH v3 01/30] mm: memcontrol: remove dead code of checking parent memory cgroup Qi Zheng
2026-01-14 11:26 ` [PATCH v3 02/30] mm: workingset: use folio_lruvec() in workingset_refault() Qi Zheng
2026-01-14 11:26 ` [PATCH v3 03/30] mm: rename unlock_page_lruvec_irq and its variants Qi Zheng
2026-01-14 11:26 ` [PATCH v3 04/30] mm: vmscan: prepare for the refactoring the move_folios_to_lru() Qi Zheng
2026-01-14 11:26 ` [PATCH v3 05/30] mm: vmscan: refactor move_folios_to_lru() Qi Zheng
2026-01-14 11:26 ` [PATCH v3 06/30] mm: memcontrol: allocate object cgroup for non-kmem case Qi Zheng
2026-01-14 11:32 ` [PATCH v3 07/30] mm: memcontrol: return root object cgroup for root memory cgroup Qi Zheng
2026-01-14 11:32 ` [PATCH v3 08/30] mm: memcontrol: prevent memory cgroup release in get_mem_cgroup_from_folio() Qi Zheng
2026-01-14 11:32 ` [PATCH v3 09/30] buffer: prevent memory cgroup release in folio_alloc_buffers() Qi Zheng
2026-01-14 11:32 ` [PATCH v3 10/30] writeback: prevent memory cgroup release in writeback module Qi Zheng
2026-01-14 11:32 ` [PATCH v3 11/30] mm: memcontrol: prevent memory cgroup release in count_memcg_folio_events() Qi Zheng
2026-01-14 11:32 ` [PATCH v3 12/30] mm: page_io: prevent memory cgroup release in page_io module Qi Zheng
2026-01-14 11:32 ` [PATCH v3 13/30] mm: migrate: prevent memory cgroup release in folio_migrate_mapping() Qi Zheng
2026-01-14 11:32 ` [PATCH v3 14/30] mm: mglru: prevent memory cgroup release in mglru Qi Zheng
2026-01-14 11:32 ` [PATCH v3 15/30] mm: memcontrol: prevent memory cgroup release in mem_cgroup_swap_full() Qi Zheng
2026-01-14 11:32 ` [PATCH v3 16/30] mm: workingset: prevent memory cgroup release in lru_gen_eviction() Qi Zheng
2026-01-14 11:32 ` [PATCH v3 17/30] mm: thp: prevent memory cgroup release in folio_split_queue_lock{_irqsave}() Qi Zheng
2026-01-14 11:32 ` [PATCH v3 18/30] mm: zswap: prevent memory cgroup release in zswap_compress() Qi Zheng
2026-01-14 11:32 ` [PATCH v3 19/30] mm: workingset: prevent lruvec release in workingset_refault() Qi Zheng
2026-01-14 11:32 ` [PATCH v3 20/30] mm: zswap: prevent lruvec release in zswap_folio_swapin() Qi Zheng
2026-01-14 11:32 ` [PATCH v3 21/30] mm: swap: prevent lruvec release in lru_gen_clear_refs() Qi Zheng
2026-01-14 11:32 ` [PATCH v3 22/30] mm: workingset: prevent lruvec release in workingset_activation() Qi Zheng
2026-01-14 11:32 ` [PATCH v3 23/30] mm: do not open-code lruvec lock Qi Zheng
2026-01-14 11:32 ` [PATCH v3 24/30] mm: memcontrol: prepare for reparenting LRU pages for " Qi Zheng
2026-01-14 11:32 ` [PATCH v3 25/30] mm: vmscan: prepare for reparenting traditional LRU folios Qi Zheng
2026-01-14 11:32 ` [PATCH v3 26/30] mm: vmscan: prepare for reparenting MGLRU folios Qi Zheng
2026-01-14 11:32 ` [PATCH v3 27/30] mm: memcontrol: refactor memcg_reparent_objcgs() Qi Zheng
2026-01-14 11:32 ` Qi Zheng [this message]
2026-01-14 11:32 ` [PATCH v3 29/30] mm: memcontrol: eliminate the problem of dying memory cgroup for LRU folios Qi Zheng
2026-01-14 11:32 ` [PATCH v3 30/30] 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=b11a0bde9fe18673a61a79398f226ad7cb04a894.1768389889.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=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=weixugc@google.com \
--cc=yosry.ahmed@linux.dev \
--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