linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
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 25/30] mm: vmscan: prepare for reparenting traditional LRU folios
Date: Wed, 14 Jan 2026 19:32:52 +0800	[thread overview]
Message-ID: <3adb367000706f9ef681b34d0a2b0eb34c494c84.1768389889.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. For traditional LRU list, each lruvec of every
memcg comprises four LRU lists. Due to the symmetry of the LRU lists, it
is feasible to transfer the LRU lists from a memcg to its parent memcg
during the reparenting process.

This commit implements the specific function, which will be used during
the reparenting process.

Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
---
 include/linux/mmzone.h |  4 ++++
 include/linux/swap.h   | 19 +++++++++++++++++++
 mm/swap.c              | 37 +++++++++++++++++++++++++++++++++++++
 mm/vmscan.c            | 19 -------------------
 4 files changed, 60 insertions(+), 19 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 6a7db0fee54a3..1014b5a93c09c 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -366,6 +366,10 @@ enum lruvec_flags {
 	LRUVEC_NODE_CONGESTED,
 };
 
+#ifdef CONFIG_MEMCG
+void lru_reparent_memcg(struct mem_cgroup *memcg, struct mem_cgroup *parent);
+#endif /* CONFIG_MEMCG */
+
 #endif /* !__GENERATING_BOUNDS_H */
 
 /*
diff --git a/include/linux/swap.h b/include/linux/swap.h
index e60f45b48e74d..4449d1f371a56 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -636,5 +636,24 @@ static inline bool mem_cgroup_swap_full(struct folio *folio)
 }
 #endif
 
+/* for_each_managed_zone_pgdat - helper macro to iterate over all managed zones in a pgdat up to
+ * and including the specified highidx
+ * @zone: The current zone in the iterator
+ * @pgdat: The pgdat which node_zones are being iterated
+ * @idx: The index variable
+ * @highidx: The index of the highest zone to return
+ *
+ * This macro iterates through all managed zones up to and including the specified highidx.
+ * The zone iterator enters an invalid state after macro call and must be reinitialized
+ * before it can be used again.
+ */
+#define for_each_managed_zone_pgdat(zone, pgdat, idx, highidx)	\
+	for ((idx) = 0, (zone) = (pgdat)->node_zones;		\
+	    (idx) <= (highidx);					\
+	    (idx)++, (zone)++)					\
+		if (!managed_zone(zone))			\
+			continue;				\
+		else
+
 #endif /* __KERNEL__*/
 #endif /* _LINUX_SWAP_H */
diff --git a/mm/swap.c b/mm/swap.c
index 7e53479ca1732..cb40e80da53cd 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -1090,6 +1090,43 @@ void folio_batch_remove_exceptionals(struct folio_batch *fbatch)
 	fbatch->nr = j;
 }
 
+#ifdef CONFIG_MEMCG
+static void lruvec_reparent_lru(struct lruvec *child_lruvec,
+				struct lruvec *parent_lruvec,
+				enum lru_list lru, int nid)
+{
+	int zid;
+	struct zone *zone;
+
+	if (lru != LRU_UNEVICTABLE)
+		list_splice_tail_init(&child_lruvec->lists[lru], &parent_lruvec->lists[lru]);
+
+	for_each_managed_zone_pgdat(zone, NODE_DATA(nid), zid, MAX_NR_ZONES - 1) {
+		unsigned long size = mem_cgroup_get_zone_lru_size(child_lruvec, lru, zid);
+
+		mem_cgroup_update_lru_size(parent_lruvec, lru, zid, size);
+	}
+}
+
+void lru_reparent_memcg(struct mem_cgroup *memcg, struct mem_cgroup *parent)
+{
+	int nid;
+
+	for_each_node(nid) {
+		enum lru_list lru;
+		struct lruvec *child_lruvec, *parent_lruvec;
+
+		child_lruvec = mem_cgroup_lruvec(memcg, NODE_DATA(nid));
+		parent_lruvec = mem_cgroup_lruvec(parent, NODE_DATA(nid));
+		parent_lruvec->anon_cost += child_lruvec->anon_cost;
+		parent_lruvec->file_cost += child_lruvec->file_cost;
+
+		for_each_lru(lru)
+			lruvec_reparent_lru(child_lruvec, parent_lruvec, lru, nid);
+	}
+}
+#endif
+
 static const struct ctl_table swap_sysctl_table[] = {
 	{
 		.procname	= "page-cluster",
diff --git a/mm/vmscan.c b/mm/vmscan.c
index c48ff6e05e004..e738082874878 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -270,25 +270,6 @@ static int sc_swappiness(struct scan_control *sc, struct mem_cgroup *memcg)
 }
 #endif
 
-/* for_each_managed_zone_pgdat - helper macro to iterate over all managed zones in a pgdat up to
- * and including the specified highidx
- * @zone: The current zone in the iterator
- * @pgdat: The pgdat which node_zones are being iterated
- * @idx: The index variable
- * @highidx: The index of the highest zone to return
- *
- * This macro iterates through all managed zones up to and including the specified highidx.
- * The zone iterator enters an invalid state after macro call and must be reinitialized
- * before it can be used again.
- */
-#define for_each_managed_zone_pgdat(zone, pgdat, idx, highidx)	\
-	for ((idx) = 0, (zone) = (pgdat)->node_zones;		\
-	    (idx) <= (highidx);					\
-	    (idx)++, (zone)++)					\
-		if (!managed_zone(zone))			\
-			continue;				\
-		else
-
 static void set_task_reclaim_state(struct task_struct *task,
 				   struct reclaim_state *rs)
 {
-- 
2.20.1



  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 ` Qi Zheng [this message]
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 ` [PATCH v3 28/30] mm: memcontrol: prepare for reparenting state_local Qi Zheng
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=3adb367000706f9ef681b34d0a2b0eb34c494c84.1768389889.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