From: Yosry Ahmed <yosry@kernel.org>
To: Qi Zheng <qi.zheng@linux.dev>
Cc: 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, linux-mm@kvack.org,
linux-kernel@vger.kernel.org, cgroups@vger.kernel.org,
Qi Zheng <zhengqi.arch@bytedance.com>
Subject: Re: [PATCH v5 update 29/32] mm: memcontrol: prepare for reparenting non-hierarchical stats
Date: Tue, 3 Mar 2026 14:56:54 +0000 [thread overview]
Message-ID: <46bgg2vwqvmex7wtk2fkvf454tqgaychb7l4odnnrx7svci5ha@vy4b4ophm763> (raw)
In-Reply-To: <de1476aa-20a3-420e-9cd7-9238efd3c85f@linux.dev>
On Tue, Mar 03, 2026 at 11:08:56AM +0800, Qi Zheng wrote:
> Hi Yosry,
[..]
> >
> > I don't think we should end up with two copies of
> > __mod_memcg_state/mod_memcg_state() and
> > __mod_memcg_lruvec_state/mod_memcg_lruvec_state(). I meant to refactor
> > mod_memcg_state() to call __mod_memcg_state(), where the latter does
> > not call get_non_dying_memcg_{start/end}(). Same for
> > mod_memcg_lruvec_state().
>
> Okay, like the following? But this would require modifications to
> [PATCH v5 31/32]. If there are no problems, I will send the updated
> patch to [PATCH v5 29/32] and [PATCH v5 31/32].
I cannot apply the diff, seems a bit corrupted.
But ideally, instead of a @reparent argument, we just have
__mod_memcg_lruvec_state() and __mod_memcg_state() do the work without
getting parent of dead memcgs, and then mod_memcg_lruvec_state() and
mod_memcg_state() just call them after get_non_dying_memcg_start().
What about this (untested), it should apply on top of 'mm: memcontrol:
eliminate the problem of dying memory cgroup for LRU folios' in mm-new,
so maybe it needs to be broken down across different patches:
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 753d76e96cc67..f0d55e1f9c49a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -527,7 +527,7 @@ unsigned long lruvec_page_state_local(struct lruvec *lruvec,
}
#ifdef CONFIG_MEMCG_V1
-static void __mod_memcg_lruvec_state(struct lruvec *lruvec,
+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,
@@ -536,16 +536,17 @@ void reparent_memcg_lruvec_state_local(struct mem_cgroup *memcg,
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));
unsigned long value = lruvec_page_state_local(child_lruvec, idx);
+ struct mem_cgroup_per_node *child_pn, *parent_pn;
- __mod_memcg_lruvec_state(child_lruvec, idx, -value);
- __mod_memcg_lruvec_state(parent_lruvec, idx, value);
+ 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
@@ -831,39 +832,42 @@ static inline void get_non_dying_memcg_end(void)
}
#endif
-/**
- * mod_memcg_state - update cgroup memory statistics
- * @memcg: the memory cgroup
- * @idx: the stat item - can be enum memcg_stat_item or enum node_stat_item
- * @val: delta to add to the counter, can be negative
- */
-void mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item idx,
- int val)
+static void __mod_memcg_state(struct mem_cgroup *memcg,
+ enum memcg_stat_item idx, int val)
{
int i = memcg_stats_index(idx);
int cpu;
- if (mem_cgroup_disabled())
- return;
-
if (WARN_ONCE(BAD_STAT_IDX(i), "%s: missing stat item %d\n", __func__, idx))
return;
cpu = get_cpu();
- memcg = get_non_dying_memcg_start(memcg);
-
this_cpu_add(memcg->vmstats_percpu->state[i], val);
val = memcg_state_val_in_pages(idx, val);
memcg_rstat_updated(memcg, val, cpu);
-
- get_non_dying_memcg_end();
-
trace_mod_memcg_state(memcg, idx, val);
put_cpu();
}
+/**
+ * mod_memcg_state - update cgroup memory statistics
+ * @memcg: the memory cgroup
+ * @idx: the stat item - can be enum memcg_stat_item or enum node_stat_item
+ * @val: delta to add to the counter, can be negative
+ */
+void mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item idx,
+ int val)
+{
+ if (mem_cgroup_disabled())
+ return;
+
+ memcg = get_non_dying_memcg_start(memcg);
+ __mod_memcg_state(memcg, idx, val);
+ get_non_dying_memcg_end();
+}
+
#ifdef CONFIG_MEMCG_V1
/* idx can be of type enum memcg_stat_item or node_stat_item. */
unsigned long memcg_page_state_local(struct mem_cgroup *memcg, int idx)
@@ -882,35 +886,26 @@ unsigned long memcg_page_state_local(struct mem_cgroup *memcg, int idx)
return x;
}
-static void __mod_memcg_state(struct mem_cgroup *memcg,
- enum memcg_stat_item idx, int val)
+void reparent_memcg_state_local(struct mem_cgroup *memcg,
+ struct mem_cgroup *parent, int idx)
{
int i = memcg_stats_index(idx);
- int cpu;
-
- if (mem_cgroup_disabled())
- return;
-
- cpu = get_cpu();
-
- this_cpu_add(memcg->vmstats_percpu->state[i], val);
- val = memcg_state_val_in_pages(idx, val);
- memcg_rstat_updated(memcg, val, cpu);
- trace_mod_memcg_state(memcg, idx, val);
+ unsigned long value = memcg_page_state_local(memcg, idx);
- put_cpu();
+ __mod_memcg_state(memcg, idx, -value);
+ __mod_memcg_state(parent, idx, value);
}
+#endif
-static void __mod_memcg_lruvec_state(struct lruvec *lruvec,
+static void __mod_memcg_lruvec_state(struct mem_cgroup_per_node *pn,
enum node_stat_item idx, int val)
{
- struct mem_cgroup_per_node *pn;
- struct mem_cgroup *memcg;
+ struct mem_cgroup *memcg = pn->memcg;
int i = memcg_stats_index(idx);
int cpu;
- pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
- memcg = pn->memcg;
+ if (WARN_ONCE(BAD_STAT_IDX(i), "%s: missing stat item %d\n", __func__, idx))
+ return;
cpu = get_cpu();
@@ -927,20 +922,6 @@ static void __mod_memcg_lruvec_state(struct lruvec *lruvec,
put_cpu();
}
-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;
-
- __mod_memcg_state(memcg, idx, -value);
- __mod_memcg_state(parent, idx, value);
-}
-#endif
-
static void mod_memcg_lruvec_state(struct lruvec *lruvec,
enum node_stat_item idx,
int val)
@@ -948,32 +929,13 @@ static void mod_memcg_lruvec_state(struct lruvec *lruvec,
struct pglist_data *pgdat = lruvec_pgdat(lruvec);
struct mem_cgroup_per_node *pn;
struct mem_cgroup *memcg;
- int i = memcg_stats_index(idx);
- int cpu;
-
- if (WARN_ONCE(BAD_STAT_IDX(i), "%s: missing stat item %d\n", __func__, idx))
- return;
pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
- memcg = pn->memcg;
-
- cpu = get_cpu();
-
- memcg = get_non_dying_memcg_start(memcg);
+ memcg = get_non_dying_memcg_start(pn->memcg);
pn = memcg->nodeinfo[pgdat->node_id];
-
- /* Update memcg */
- this_cpu_add(memcg->vmstats_percpu->state[i], val);
- /* Update lruvec */
- this_cpu_add(pn->lruvec_stats_percpu->state[i], val);
- val = memcg_state_val_in_pages(idx, val);
- memcg_rstat_updated(memcg, val, cpu);
-
+ __mod_memcg_lruvec_state(pn, idx, val);
get_non_dying_memcg_end();
- trace_mod_memcg_lruvec_state(memcg, idx, val);
-
- put_cpu();
}
/
next prev parent reply other threads:[~2026-03-03 14:57 UTC|newest]
Thread overview: 60+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-02-25 7:48 [PATCH v5 00/32] Eliminate Dying Memory Cgroup Qi Zheng
2026-02-25 7:48 ` [PATCH v5 01/32] mm: memcontrol: remove dead code of checking parent memory cgroup Qi Zheng
2026-02-25 7:48 ` [PATCH v5 02/32] mm: workingset: use folio_lruvec() in workingset_refault() Qi Zheng
2026-02-25 7:48 ` [PATCH v5 03/32] mm: rename unlock_page_lruvec_irq and its variants Qi Zheng
2026-02-25 7:48 ` [PATCH v5 04/32] mm: vmscan: prepare for the refactoring the move_folios_to_lru() Qi Zheng
2026-02-25 7:48 ` [PATCH v5 05/32] mm: vmscan: refactor move_folios_to_lru() Qi Zheng
2026-02-25 7:48 ` [PATCH v5 06/32] mm: memcontrol: allocate object cgroup for non-kmem case Qi Zheng
2026-02-25 7:48 ` [PATCH v5 07/32] mm: memcontrol: return root object cgroup for root memory cgroup Qi Zheng
2026-02-25 7:48 ` [PATCH v5 08/32] mm: memcontrol: prevent memory cgroup release in get_mem_cgroup_from_folio() Qi Zheng
2026-02-25 7:48 ` [PATCH v5 09/32] buffer: prevent memory cgroup release in folio_alloc_buffers() Qi Zheng
2026-02-25 7:48 ` [PATCH v5 10/32] writeback: prevent memory cgroup release in writeback module Qi Zheng
2026-02-25 7:48 ` [PATCH v5 11/32] mm: memcontrol: prevent memory cgroup release in count_memcg_folio_events() Qi Zheng
2026-02-25 7:48 ` [PATCH v5 12/32] mm: page_io: prevent memory cgroup release in page_io module Qi Zheng
2026-02-25 7:52 ` [PATCH v5 13/32] mm: migrate: prevent memory cgroup release in folio_migrate_mapping() Qi Zheng
2026-02-25 7:52 ` [PATCH v5 14/32] mm: mglru: prevent memory cgroup release in mglru Qi Zheng
2026-02-25 7:52 ` [PATCH v5 15/32] mm: memcontrol: prevent memory cgroup release in mem_cgroup_swap_full() Qi Zheng
2026-02-25 7:52 ` [PATCH v5 16/32] mm: workingset: prevent memory cgroup release in lru_gen_eviction() Qi Zheng
2026-02-25 7:53 ` [PATCH v5 17/32] mm: thp: prevent memory cgroup release in folio_split_queue_lock{_irqsave}() Qi Zheng
2026-02-25 7:53 ` [PATCH v5 18/32] mm: zswap: prevent memory cgroup release in zswap_compress() Qi Zheng
2026-02-25 7:53 ` [PATCH v5 19/32] mm: workingset: prevent lruvec release in workingset_refault() Qi Zheng
2026-02-25 7:53 ` [PATCH v5 20/32] mm: zswap: prevent lruvec release in zswap_folio_swapin() Qi Zheng
2026-02-25 7:53 ` [PATCH v5 21/32] mm: swap: prevent lruvec release in lru_gen_clear_refs() Qi Zheng
2026-02-25 7:53 ` [PATCH v5 22/32] mm: workingset: prevent lruvec release in workingset_activation() Qi Zheng
2026-02-25 7:53 ` [PATCH v5 23/32] mm: do not open-code lruvec lock Qi Zheng
2026-02-25 7:53 ` [PATCH v5 24/32] mm: memcontrol: prepare for reparenting LRU pages for " Qi Zheng
2026-02-25 7:53 ` [PATCH v5 25/32] mm: vmscan: prepare for reparenting traditional LRU folios Qi Zheng
2026-02-25 7:53 ` [PATCH v5 26/32] mm: vmscan: prepare for reparenting MGLRU folios Qi Zheng
2026-02-25 7:53 ` [PATCH v5 27/32] mm: memcontrol: refactor memcg_reparent_objcgs() Qi Zheng
2026-02-25 7:53 ` [PATCH v5 28/32] mm: workingset: use lruvec_lru_size() to get the number of lru pages Qi Zheng
2026-02-25 7:53 ` [PATCH v5 29/32] mm: memcontrol: prepare for reparenting non-hierarchical stats Qi Zheng
2026-02-25 14:58 ` Yosry Ahmed
2026-02-26 0:25 ` Shakeel Butt
2026-02-26 6:42 ` Qi Zheng
2026-02-26 15:16 ` Yosry Ahmed
2026-02-26 17:02 ` Shakeel Butt
2026-02-26 17:13 ` Yosry Ahmed
2026-02-27 3:11 ` Qi Zheng
2026-02-27 6:05 ` Qi Zheng
2026-02-27 18:18 ` Yosry Ahmed
2026-02-28 3:40 ` Qi Zheng
2026-02-26 6:41 ` Qi Zheng
2026-02-26 1:41 ` Shakeel Butt
2026-02-26 6:45 ` Qi Zheng
2026-02-28 7:25 ` [PATCH v5 update " Qi Zheng
2026-02-28 19:08 ` Andrew Morton
2026-03-02 2:30 ` Qi Zheng
2026-03-02 15:53 ` Yosry Ahmed
2026-03-03 3:08 ` Qi Zheng
2026-03-03 14:56 ` Yosry Ahmed [this message]
2026-02-25 7:53 ` [PATCH v5 30/32] mm: memcontrol: convert objcg to be per-memcg per-node type Qi Zheng
2026-02-25 9:44 ` [PATCH v5 update " Qi Zheng
2026-02-26 2:27 ` Shakeel Butt
2026-02-26 6:47 ` Qi Zheng
2026-02-26 20:05 ` Shakeel Butt
2026-02-27 6:34 ` Qi Zheng
2026-02-25 7:53 ` [PATCH v5 31/32] mm: memcontrol: eliminate the problem of dying memory cgroup for LRU folios Qi Zheng
2026-02-26 2:40 ` Shakeel Butt
2026-02-25 7:53 ` [PATCH v5 32/32] mm: lru: add VM_WARN_ON_ONCE_FOLIO to lru maintenance helpers Qi Zheng
2026-02-25 21:57 ` [PATCH v5 00/32] Eliminate Dying Memory Cgroup Andrew Morton
2026-02-27 0:24 ` SeongJae Park
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=46bgg2vwqvmex7wtk2fkvf454tqgaychb7l4odnnrx7svci5ha@vy4b4ophm763 \
--to=yosry@kernel.org \
--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=qi.zheng@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=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