[PATCH v4 2/2] mm/mglru: fix ineffective memory protection for non-kswapd reclaim

[Ridong Chen <ridong.chen@linux.dev>]

From: Ridong Chen <chenridong@xiaomi.com>

For MGLRU, memory.min/low is not honored during global proactive reclaim
(writing to the root memory.reclaim) and global direct reclaim, because
these paths shrink memcgs using stale protection (emin/elow).
It can be reproduced as follows:

  # echo 7 > /sys/kernel/mm/lru_gen/enabled
  # cd /sys/fs/cgroup
  # mkdir -p a/b
  # echo 100M > a/memory.min
  # echo +memory > a/cgroup.subtree_control
  # echo 100M > a/b/memory.min
  # echo $$ > a/b/cgroup.procs
  # dd if=/dev/zero of=/tmp/testfile bs=1M count=200
  # cat a/b/memory.current
  222650368
  # echo 500M > memory.reclaim
  -bash: echo: write error: Resource temporarily unavailable
  # cat a/b/memory.current
  6070272

memory.min is 100M, yet reclaim drops a/b down to 6M, breaking the
protection. The traditional LRU path is not affected because
shrink_node() calls mem_cgroup_calculate_protection() for each memcg it
visits during a top-down tree walk.

Commit 30d77b7eef01 ("mm/mglru: fix ineffective protection calculation")
moved the protection computation into lru_gen_age_node(), which only
runs for kswapd. Non-kswapd global reclaim reaches shrink_one() through
lru_gen_shrink_node() -> shrink_many() without any protection
computation, so emin/elow are whatever a previous kswapd run left behind
- or zero if kswapd never ran on this node. Relying on a prior kswapd
pass is not correct either: a memcg's emin/elow are derived from its
ancestors' memory.min/low settings and from children_min_usage, both of
which change over time, so emin/elow go stale even after kswapd has run
and must be recomputed at the point of reclaim.

Introduce mem_cgroup_calculate_protection_path() which computes emin/elow
along the root-to-target path only, by iterating through the cgroup
ancestors array top-down. This avoids the full tree traversal that would
be needed with mem_cgroup_calculate_protection(), limiting the cost to
O(depth) per memcg - typically 3-5 levels.

Call it from shrink_one() for the non-kswapd path so that each memcg
about to be shrunk has correct protection values.

Fixes: e4dde56cd208 ("mm: multi-gen LRU: per-node lru_gen_folio lists")
Cc: stable@vger.kernel.org
Assisted-by: Claude:claude-opus-4-8
Reviewed-by: Barry Song <baohua@kernel.org>
Reviewed-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Ridong Chen <chenridong@xiaomi.com>
---
 include/linux/memcontrol.h | 10 +++++++++
 mm/memcontrol.c            | 45 ++++++++++++++++++++++++++++++++++++++
 mm/vmscan.c                |  8 ++++++-
 3 files changed, 62 insertions(+), 1 deletion(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index f227348a3f24a..a65a516adc665 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1885,6 +1885,16 @@ static inline bool memcg_is_dying(struct mem_cgroup *memcg)
 }
 #endif /* CONFIG_MEMCG */
 
+#if defined(CONFIG_MEMCG) && defined(CONFIG_LRU_GEN)
+void mem_cgroup_calculate_protection_path(struct mem_cgroup *root,
+					  struct mem_cgroup *memcg);
+#else
+static inline void mem_cgroup_calculate_protection_path(struct mem_cgroup *root,
+							struct mem_cgroup *memcg)
+{
+}
+#endif
+
 #if defined(CONFIG_MEMCG) && defined(CONFIG_ZSWAP)
 bool obj_cgroup_may_zswap(struct obj_cgroup *objcg);
 void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 256b68ffca70e..ae568fc688130 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5214,6 +5214,51 @@ void mem_cgroup_calculate_protection(struct mem_cgroup *root,
 	page_counter_calculate_protection(&root->memory, &memcg->memory, recursive_protection);
 }
 
+#ifdef CONFIG_LRU_GEN
+/**
+ * mem_cgroup_calculate_protection_path - compute protection along a path
+ * @root: the top ancestor of the sub-tree being checked (NULL for root_mem_cgroup)
+ * @memcg: the target memory cgroup
+ *
+ * Walk the ancestor path from @root down to @memcg and compute the effective
+ * protection at each level.  This is safe for isolated queries because it
+ * ensures parents are computed before children.
+ */
+void mem_cgroup_calculate_protection_path(struct mem_cgroup *root,
+					  struct mem_cgroup *memcg)
+{
+	bool recursive_protection =
+		cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT;
+	struct cgroup *cg;
+	int root_level, i;
+
+	if (mem_cgroup_disabled())
+		return;
+
+	if (!root)
+		root = root_mem_cgroup;
+
+	if (memcg == root)
+		return;
+
+	root_level = root->css.cgroup->level;
+	cg = memcg->css.cgroup;
+
+	rcu_read_lock();
+	for (i = root_level + 1; i <= cg->level; i++) {
+		struct mem_cgroup *cur;
+
+		cur = mem_cgroup_from_css(cgroup_css(cg->ancestors[i],
+						     &memory_cgrp_subsys));
+		if (cur)
+			page_counter_calculate_protection(&root->memory,
+							  &cur->memory,
+							  recursive_protection);
+	}
+	rcu_read_unlock();
+}
+#endif /* CONFIG_LRU_GEN */
+
 static int charge_memcg(struct folio *folio, struct mem_cgroup *memcg,
 			gfp_t gfp)
 {
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b4c9b8f3dfe99..8409ea4bbf379 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -5111,7 +5111,13 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc)
 	struct mem_cgroup *memcg = lruvec_memcg(lruvec);
 	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
 
-	/* lru_gen_age_node() called mem_cgroup_calculate_protection() */
+	/*
+	 * For kswapd, mem_cgroup_calculate_protection() has already
+	 * been called during the top-down cgroup traversal.
+	 */
+	if (!current_is_kswapd())
+		mem_cgroup_calculate_protection_path(NULL, memcg);
+
 	if (mem_cgroup_below_min(NULL, memcg))
 		return MEMCG_LRU_YOUNG;
 
-- 
2.34.1