mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Kairui Song via B4 Relay <devnull+kasong.tencent.com@kernel.org>
To: linux-mm@kvack.org
Cc: Andrew Morton <akpm@linux-foundation.org>,
	 Johannes Weiner <hannes@cmpxchg.org>,
	Muchun Song <muchun.song@linux.dev>,
	 Qi Zheng <qi.zheng@linux.dev>,
	Ying Huang <ying.huang@linux.alibaba.com>,
	 Chris Li <chrisl@kernel.org>, Baoquan He <baoquan.he@linux.dev>,
	 Nico Pache <nico.pache@linux.dev>,
	Usama Arif <usama.arif@linux.dev>,
	 Michal Hocko <mhocko@kernel.org>,
	Roman Gushchin <roman.gushchin@linux.dev>,
	 Shakeel Butt <shakeel.butt@linux.dev>,
	David Hildenbrand <david@kernel.org>,
	 Lorenzo Stoakes <ljs@kernel.org>,
	"Liam R. Howlett" <liam@infradead.org>,
	 Barry Song <baohua@kernel.org>,
	Axel Rasmussen <axelrasmussen@google.com>,
	 Yuanchu Xie <yuanchu@google.com>, Wei Xu <weixugc@google.com>,
	 Vlastimil Babka <vbabka@kernel.org>,
	Suren Baghdasaryan <surenb@google.com>,
	 Nhat Pham <nphamcs@gmail.com>,
	Youngjun Park <youngjun.park@lge.com>,  Zi Yan <ziy@nvidia.com>,
	Gregory Price <gourry@gourry.net>,
	 "Matthew Wilcox (Oracle)" <willy@infradead.org>,
	 Baolin Wang <baolin.wang@linux.alibaba.com>,
	 Ryan Roberts <ryan.roberts@arm.com>, Dev Jain <dev.jain@arm.com>,
	 Lance Yang <lance.yang@linux.dev>,
	Hugh Dickins <hughd@google.com>,  SJ Park <sj@kernel.org>,
	David Rientjes <rientjes@google.com>,
	 Yu Zhao <yuzhao@google.com>, Vernon Yang <vernon2gm@gmail.com>,
	 Zicheng Wang <wangzicheng@honor.com>,
	Chen Ridong <chenridong@xiaomi.com>,
	 Tal Zussman <tz2294@columbia.edu>,
	Kairui Song <ryncsn@gmail.com>,
	 Xiang Liu <liuxiang.277@bytedance.com>,
	 Ehab Ababneh <ehab.ababneh@intel.com>,
	 Zhao Zhenzhuo <zhaozhengzhuo@uniontech.com>,
	 Lian Wang <lianux.mm@gmail.com>,
	Joanne Koong <joannelkoong@gmail.com>,
	 Kunwu Chan <kunwu.chan@gmail.com>, Hui Zhu <hui.zhu@linux.dev>,
	 linux-kernel@vger.kernel.org, cgroups@vger.kernel.org,
	 damon@lists.linux.dev, linux-doc@vger.kernel.org,
	 Kairui Song <kasong@tencent.com>
Subject: [PATCH v5 04/17] mm/memcg: add folio-based lruvec live helper
Date: Thu, 19 Nov 2026 05:03:36 +0800	[thread overview]
Message-ID: <20261119-mglru-fg-v5-4-9eee2fe97a2d@tencent.com> (raw)
In-Reply-To: <20261119-mglru-fg-v5-0-9eee2fe97a2d@tencent.com>

From: Kairui Song <kasong@tencent.com>

Add a helper that resolves a live lruvec for a folio under RCU
without taking the lruvec lock.  It takes a folio directly so the
lruvec lookup happens inside the RCU read-side critical section,
which a lruvec-based interface cannot guarantee.  The first user is
the lockless folio_inc_lru_refs() path later in the series.

Factor the ancestor walk out of lruvec_live_lock_irq() into
__lruvec_get_live(), so that both entry points share it, and spell
out why the walk is enough while only the RCU read lock is held:
reparenting of a memcg that starts dying waits for a grace period,
so it cannot race with the caller until the lock is released.

Move memcg_is_dying() up in memcontrol.h, next to the other memcg state
predicates, and use it for the walk rather than repeating the open coded
css_is_dying() test a few definitions away from where it is explained.

No functional change for existing callers.

Tested-by: Zhao Zhenzhuo <zhaozhengzhuo@uniontech.com>
Signed-off-by: Kairui Song <kasong@tencent.com>
---
 include/linux/memcontrol.h | 71 ++++++++++++++++++++++++++++++++++++----------
 1 file changed, 56 insertions(+), 15 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 980358bc6f49..441a5d57e723 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -571,6 +571,11 @@ static inline bool mem_cgroup_disabled(void)
 	return !cgroup_subsys_enabled(memory_cgrp_subsys);
 }
 
+static inline bool memcg_is_dying(struct mem_cgroup *memcg)
+{
+	return memcg ? css_is_dying(&memcg->css) : false;
+}
+
 static inline void mem_cgroup_protection(const struct mem_cgroup *root,
 					 const struct mem_cgroup *memcg,
 					 unsigned long *min,
@@ -1349,6 +1354,11 @@ static inline bool mem_cgroup_online(struct mem_cgroup *memcg)
 	return true;
 }
 
+static inline bool memcg_is_dying(struct mem_cgroup *memcg)
+{
+	return false;
+}
+
 static inline
 unsigned long mem_cgroup_get_zone_lru_size(const struct lruvec *lruvec,
 		enum lru_list lru, int zone_idx)
@@ -1510,28 +1520,41 @@ static inline void lruvec_lock_irq(struct lruvec *lruvec)
 	spin_lock_irq(&lruvec->lru_lock);
 }
 
-static inline struct lruvec *lruvec_live_lock_irq(struct lruvec *lruvec)
+/*
+ * Reparenting moves a dying memcg's LRU state to its parent at any time,
+ * so anything added to that LRU afterwards would be lost.  This helper
+ * walks up to the nearest live ancestor while the caller must hold the
+ * RCU read lock: reparenting of a memcg that starts dying waits for a
+ * grace period, so it cannot race with the caller until the lock is
+ * released.
+ */
+static inline struct lruvec *__lruvec_get_live(struct lruvec *lruvec)
 {
 #ifdef CONFIG_MEMCG
 	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
 	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
 
-	rcu_read_lock();
-
 	/*
 	 * The memcg can be NULL when the memory controller is disabled.
 	 * Otherwise, the caller keeps the memcg owning @lruvec alive.
 	 */
-	while (unlikely(memcg && css_is_dying(&memcg->css))) {
+	while (unlikely(memcg_is_dying(memcg))) {
 		memcg = parent_mem_cgroup(memcg);
 		lruvec = mem_cgroup_lruvec(memcg, pgdat);
 	}
+#endif
+	return lruvec;
+}
 
+static inline struct lruvec *lruvec_live_lock_irq(struct lruvec *lruvec)
+{
+#ifdef CONFIG_MEMCG
+	rcu_read_lock();
+	lruvec = __lruvec_get_live(lruvec);
 	spin_lock_irq(&lruvec->lru_lock);
 #else
 	lruvec_lock_irq(lruvec);
 #endif
-
 	return lruvec;
 }
 
@@ -1561,6 +1584,34 @@ static inline bool folio_matches_lruvec(const struct folio *folio,
 	       lruvec_memcg(lruvec) == folio_memcg(folio);
 }
 
+/**
+ * folio_lruvec_live_get - get a live lruvec for a folio under RCU
+ * @folio: the folio
+ *
+ * Same as folio_lruvec(), except that a folio whose memcg is dying is
+ * accounted to the nearest live ancestor, which is where reparenting
+ * would put it anyway.
+ *
+ * Return: the live lruvec, with rcu_read_lock() held.  Pair it with
+ * folio_lruvec_live_put().
+ */
+static inline struct lruvec *folio_lruvec_live_get(struct folio *folio)
+{
+#ifdef CONFIG_MEMCG
+	rcu_read_lock();
+	return __lruvec_get_live(folio_lruvec(folio));
+#else
+	return folio_lruvec(folio);
+#endif
+}
+
+static inline void folio_lruvec_live_put(struct lruvec *lruvec)
+{
+#ifdef CONFIG_MEMCG
+	rcu_read_unlock();
+#endif
+}
+
 /* Don't lock again iff page's lruvec locked */
 static inline struct lruvec *folio_lruvec_relock_irq(const struct folio *folio,
 		struct lruvec *locked_lruvec)
@@ -1826,11 +1877,6 @@ void mem_cgroup_node_filter_allowed(struct mem_cgroup *memcg, nodemask_t *mask);
 
 void mem_cgroup_show_protected_memory(struct mem_cgroup *memcg);
 
-static inline bool memcg_is_dying(struct mem_cgroup *memcg)
-{
-	return memcg ? css_is_dying(&memcg->css) : false;
-}
-
 #else
 static inline bool mem_cgroup_kmem_disabled(void)
 {
@@ -1901,11 +1947,6 @@ static inline void mem_cgroup_node_filter_allowed(struct mem_cgroup *memcg,
 static inline void mem_cgroup_show_protected_memory(struct mem_cgroup *memcg)
 {
 }
-
-static inline bool memcg_is_dying(struct mem_cgroup *memcg)
-{
-	return false;
-}
 #endif /* CONFIG_MEMCG */
 
 #if defined(CONFIG_MEMCG) && defined(CONFIG_LRU_GEN)

-- 
2.56.1



  parent reply	other threads:[~2026-11-18 21:03 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-18 21:03 [PATCH v5 00/17] mm/mglru: frequency guided promotion (MGLRU-FG) and flag cleanup Kairui Song via B4 Relay
2026-11-18 21:03 ` [PATCH v5 01/17] mm/mglru: rename the generation offset in lru_gen_folio_seq() Kairui Song via B4 Relay
2026-11-18 21:03 ` [PATCH v5 02/17] mm/memcontrol: allow update of LRU statistic without holding LRU lock Kairui Song via B4 Relay
2026-11-18 21:03 ` [PATCH v5 03/17] mm/mglru: make generation page counters atomic Kairui Song via B4 Relay
2026-11-18 21:03 ` Kairui Song via B4 Relay [this message]
2026-11-18 21:03 ` [PATCH v5 05/17] mm/mglru: skip the flags cmpxchg when nothing changes Kairui Song via B4 Relay
2026-11-18 21:03 ` [PATCH v5 06/17] mm/mglru: frequency guided workingset promotion (MGLRU-FG) Kairui Song via B4 Relay
2026-11-18 21:03 ` [PATCH v5 07/17] mm/mglru: make folio lru referenced times count a generic API Kairui Song via B4 Relay
2026-11-18 21:03 ` [PATCH v5 08/17] mm/mglru: move add/del LRU size accounting out of lru_gen_update_size() Kairui Song via B4 Relay
2026-11-18 21:03 ` [PATCH v5 09/17] mm/mglru, gup: mark folios referenced via a fast helper Kairui Song via B4 Relay
2026-11-18 21:03 ` [PATCH v5 10/17] mm/mglru, smaps: convert to LRU refs based operations for MGLRU Kairui Song via B4 Relay
2026-11-18 21:03 ` [PATCH v5 11/17] mm/damon: " Kairui Song via B4 Relay
2026-11-18 21:03 ` [PATCH v5 12/17] mm/khugepaged: " Kairui Song via B4 Relay
2026-11-18 21:03 ` [PATCH v5 13/17] mm/madvise: adapt for " Kairui Song via B4 Relay
2026-11-18 21:03 ` [PATCH v5 14/17] mm/huge_memory: mark folio as accessed more accurately on split Kairui Song via B4 Relay
2026-11-18 21:03 ` [PATCH v5 15/17] mm/mglru: folio LRU refs based active/inactive number accounting Kairui Song via B4 Relay
2026-11-18 21:03 ` [PATCH v5 16/17] mm/mglru: make folio_inc_lru_refs lruvec lockless Kairui Song via B4 Relay
2026-11-18 21:03 ` [PATCH v5 17/17] mm/mglru: make folio_test_workingset() work based on folio LRU refs Kairui Song via B4 Relay

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=20261119-mglru-fg-v5-4-9eee2fe97a2d@tencent.com \
    --to=devnull+kasong.tencent.com@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=axelrasmussen@google.com \
    --cc=baohua@kernel.org \
    --cc=baolin.wang@linux.alibaba.com \
    --cc=baoquan.he@linux.dev \
    --cc=cgroups@vger.kernel.org \
    --cc=chenridong@xiaomi.com \
    --cc=chrisl@kernel.org \
    --cc=damon@lists.linux.dev \
    --cc=david@kernel.org \
    --cc=dev.jain@arm.com \
    --cc=ehab.ababneh@intel.com \
    --cc=gourry@gourry.net \
    --cc=hannes@cmpxchg.org \
    --cc=hughd@google.com \
    --cc=hui.zhu@linux.dev \
    --cc=joannelkoong@gmail.com \
    --cc=kasong@tencent.com \
    --cc=kunwu.chan@gmail.com \
    --cc=lance.yang@linux.dev \
    --cc=liam@infradead.org \
    --cc=lianux.mm@gmail.com \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=liuxiang.277@bytedance.com \
    --cc=ljs@kernel.org \
    --cc=mhocko@kernel.org \
    --cc=muchun.song@linux.dev \
    --cc=nico.pache@linux.dev \
    --cc=nphamcs@gmail.com \
    --cc=qi.zheng@linux.dev \
    --cc=rientjes@google.com \
    --cc=roman.gushchin@linux.dev \
    --cc=ryan.roberts@arm.com \
    --cc=ryncsn@gmail.com \
    --cc=shakeel.butt@linux.dev \
    --cc=sj@kernel.org \
    --cc=surenb@google.com \
    --cc=tz2294@columbia.edu \
    --cc=usama.arif@linux.dev \
    --cc=vbabka@kernel.org \
    --cc=vernon2gm@gmail.com \
    --cc=wangzicheng@honor.com \
    --cc=weixugc@google.com \
    --cc=willy@infradead.org \
    --cc=ying.huang@linux.alibaba.com \
    --cc=youngjun.park@lge.com \
    --cc=yuanchu@google.com \
    --cc=yuzhao@google.com \
    --cc=zhaozhengzhuo@uniontech.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

all inboxes | Powered by JetHome®