| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <b11a0bde9fe18673a61a79398f226ad7cb04a894.1768389889.git.zhengqi.arch@bytedance.com>
Date: Wed, 14 Jan 2026 19:32:55 +0800
From: Qi Zheng <qi.zheng@...ux.dev>
To: hannes@...xchg.org,
hughd@...gle.com,
mhocko@...e.com,
roman.gushchin@...ux.dev,
shakeel.butt@...ux.dev,
muchun.song@...ux.dev,
david@...nel.org,
lorenzo.stoakes@...cle.com,
ziy@...dia.com,
harry.yoo@...cle.com,
yosry.ahmed@...ux.dev,
imran.f.khan@...cle.com,
kamalesh.babulal@...cle.com,
axelrasmussen@...gle.com,
yuanchu@...gle.com,
weixugc@...gle.com,
chenridong@...weicloud.com,
mkoutny@...e.com,
akpm@...ux-foundation.org,
hamzamahfooz@...ux.microsoft.com,
apais@...ux.microsoft.com,
lance.yang@...ux.dev
Cc: linux-mm@...ck.org,
linux-kernel@...r.kernel.org,
cgroups@...r.kernel.org,
Qi Zheng <zhengqi.arch@...edance.com>
Subject: [PATCH v3 28/30] mm: memcontrol: prepare for reparenting state_local
From: Qi Zheng <zhengqi.arch@...edance.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@...edance.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
Powered by blists - more mailing lists