linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Andrew Morton <akpm@linux-foundation.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,
	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 v6 00/33] Eliminate Dying Memory Cgroup
Date: Thu, 5 Mar 2026 16:51:18 -0800	[thread overview]
Message-ID: <20260305165118.33c0af5b7742e18f18b7231a@linux-foundation.org> (raw)
In-Reply-To: <cover.1772711148.git.zhengqi.arch@bytedance.com>

On Thu,  5 Mar 2026 19:52:18 +0800 Qi Zheng <qi.zheng@linux.dev> wrote:

>  - refactor mod_memcg_state() and mod_memcg_lruvec_state()
>    (suggested by Yosry Ahmed)
>  - use non-atomic method to reparent non-hierarchical stats
>    (suggested by Yosry Ahmed)
>  - remove the redundant declaration in  [PATCH v5 29/32]
>    (pointed by Shakeel Butt)
>  - collect Acked-bys

Updated, thanks.

Appended is how this update altered mm.git.

Hopefully we'll be able to move this into mm-unstable (and hance
linux-next) soon,

--- a/kernel/cgroup/cgroup.c~b
+++ a/kernel/cgroup/cgroup.c
@@ -6043,8 +6043,9 @@ out_unlock:
  */
 static void css_killed_work_fn(struct work_struct *work)
 {
-	struct cgroup_subsys_state *css = container_of(to_rcu_work(work),
-				struct cgroup_subsys_state, destroy_rwork);
+	struct cgroup_subsys_state *css;
+
+	css = container_of(to_rcu_work(work), struct cgroup_subsys_state, destroy_rwork);
 
 	cgroup_lock();
 
--- a/mm/memcontrol.c~b
+++ a/mm/memcontrol.c
@@ -526,25 +526,25 @@ unsigned long lruvec_page_state_local(st
 }
 
 #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,
 				       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));
 		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
@@ -830,39 +830,43 @@ static inline void get_non_dying_memcg_e
 }
 #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)
@@ -881,35 +885,25 @@ unsigned long memcg_page_state_local(str
 	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();
 
@@ -926,20 +920,6 @@ static void __mod_memcg_lruvec_state(str
 	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)
@@ -947,32 +927,14 @@ static void mod_memcg_lruvec_state(struc
 	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();
 }
 
 /**
_



      parent reply	other threads:[~2026-03-06  0:51 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-03-05 11:52 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 ` [PATCH v6 30/33] mm: memcontrol: prepare for reparenting non-hierarchical stats Qi Zheng
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
2026-03-06  0:51 ` Andrew Morton [this message]

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=20260305165118.33c0af5b7742e18f18b7231a@linux-foundation.org \
    --to=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