[PATCH 0/2] mm: fix node reclaim swappiness handling

[PATCH 0/2] mm: fix node reclaim swappiness handling

[Ridong Chen]

From: Ridong Chen <chenridong@xiaomi.com>

The per-node proactive reclaim interface
(/sys/devices/system/node/nodeX/reclaim) accepts a swappiness parameter,
but it was silently ignored when CONFIG_MEMCG is disabled. The root cause
is that sc_swappiness() had separate implementations for CONFIG_MEMCG and
!CONFIG_MEMCG, and the latter never checked proactive_swappiness.

Patch 1 moves mem_cgroup_swappiness() from swap.h to memcontrol.h and
makes it handle both CONFIG_MEMCG and !CONFIG_MEMCG cases in a single
inline function. This is a prerequisite for unifying sc_swappiness().

Patch 2 consolidates sc_swappiness() into a single definition that
works regardless of CONFIG_MEMCG, fixing the node reclaim swappiness
bug.

Ridong Chen (2):
  memcg: move mem_cgroup_swappiness to memcontrol.h
  mm: vmscan: fix node reclaim ignoring swappiness parameter

 include/linux/memcontrol.h | 25 +++++++++++++++++++++++--
 include/linux/swap.h       | 19 -------------------
 mm/memcontrol.c            |  3 +--
 mm/vmscan.c                | 17 +++++++----------
 4 files changed, 31 insertions(+), 33 deletions(-)

-- 
2.43.0

[PATCH 1/2] memcg: move mem_cgroup_swappiness to memcontrol.h

[Ridong Chen]

From: Ridong Chen <chenridong@xiaomi.com>

The per-memcg swappiness knob is v1-only; v2 always uses global
vm_swappiness and ignores the per-cgroup field.

Guard memcg->swappiness with CONFIG_MEMCG_V1, and move the helper
to memcontrol.h where it belongs.

No functional change for v1; v2-only kernels drop the unused field.

Signed-off-by: Ridong Chen <chenridong@xiaomi.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
---
 include/linux/memcontrol.h | 25 +++++++++++++++++++++++--
 include/linux/swap.h       | 19 -------------------
 mm/memcontrol.c            |  3 +--
 3 files changed, 24 insertions(+), 23 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index e1f46a0016fc..f59614956f96 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -239,8 +239,6 @@ struct mem_cgroup {
 	 */
 	bool oom_group;
 
-	int swappiness;
-
 	/* memory.events and memory.events.local */
 	struct cgroup_file events_file;
 	struct cgroup_file events_local_file;
@@ -318,6 +316,9 @@ struct mem_cgroup {
 	/* List of events which userspace want to receive */
 	struct list_head event_list;
 	spinlock_t event_list_lock;
+
+	int swappiness;
+
 #endif /* CONFIG_MEMCG_V1 */
 
 	struct mem_cgroup_per_node *nodeinfo[];
@@ -365,6 +366,9 @@ enum objext_flags {
 
 #define OBJEXTS_FLAGS_MASK (__NR_OBJEXTS_FLAGS - 1)
 
+/* Defined in mm/vmscan.c; used by mem_cgroup_swappiness(). */
+extern int vm_swappiness;
+
 #ifdef CONFIG_MEMCG
 /*
  * After the initialization objcg->memcg is always pointing at
@@ -1440,6 +1444,23 @@ static inline void mem_cgroup_flush_workqueue(void) { }
 static inline int mem_cgroup_init(void) { return 0; }
 #endif /* CONFIG_MEMCG */
 
+static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg)
+{
+#ifdef CONFIG_MEMCG_V1
+	/* Cgroup2 doesn't have per-cgroup swappiness */
+	if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
+		return READ_ONCE(vm_swappiness);
+
+	/* root ? */
+	if (mem_cgroup_disabled() || mem_cgroup_is_root(memcg))
+		return READ_ONCE(vm_swappiness);
+
+	return READ_ONCE(memcg->swappiness);
+#else
+	return READ_ONCE(vm_swappiness);
+#endif
+}
+
 /*
  * Extended information for slab objects stored as an array in page->memcg_data
  * if MEMCG_DATA_OBJEXTS is set.
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 8f0f68e245ba..2cfe364d66dc 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -372,7 +372,6 @@ extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem,
 						pg_data_t *pgdat,
 						unsigned long *nr_scanned);
 extern unsigned long shrink_all_memory(unsigned long nr_pages);
-extern int vm_swappiness;
 long remove_mapping(struct address_space *mapping, struct folio *folio);
 
 #if defined(CONFIG_SYSFS) && defined(CONFIG_NUMA)
@@ -537,25 +536,7 @@ static inline int add_swap_extent(struct swap_info_struct *sis,
 }
 #endif /* CONFIG_SWAP */
 #ifdef CONFIG_MEMCG
-static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg)
-{
-	/* Cgroup2 doesn't have per-cgroup swappiness */
-	if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
-		return READ_ONCE(vm_swappiness);
-
-	/* root ? */
-	if (mem_cgroup_disabled() || mem_cgroup_is_root(memcg))
-		return READ_ONCE(vm_swappiness);
-
-	return READ_ONCE(memcg->swappiness);
-}
-
 void lru_reparent_memcg(struct mem_cgroup *memcg, struct mem_cgroup *parent, int nid);
-#else
-static inline int mem_cgroup_swappiness(struct mem_cgroup *mem)
-{
-	return READ_ONCE(vm_swappiness);
-}
 #endif
 
 #if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6dc4888a90f3..b61def56c41a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4174,11 +4174,10 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 #endif
 	page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX);
 	if (parent) {
-		WRITE_ONCE(memcg->swappiness, mem_cgroup_swappiness(parent));
-
 		page_counter_init(&memcg->memory, &parent->memory, memcg_on_dfl);
 		page_counter_init(&memcg->swap, &parent->swap, false);
 #ifdef CONFIG_MEMCG_V1
+		WRITE_ONCE(memcg->swappiness, mem_cgroup_swappiness(parent));
 		memcg->memory.track_failcnt = !memcg_on_dfl;
 		WRITE_ONCE(memcg->oom_kill_disable, READ_ONCE(parent->oom_kill_disable));
 		page_counter_init(&memcg->kmem, &parent->kmem, false);
-- 
2.43.0

[PATCH 2/2] mm: vmscan: fix node reclaim ignoring swappiness parameter

[Ridong Chen]

From: Ridong Chen <chenridong@xiaomi.com>

sc_swappiness() had two separate definitions depending on
CONFIG_MEMCG. The !CONFIG_MEMCG variant simply returned
vm_swappiness, ignoring the proactive_swappiness value passed
through scan_control. This caused the swappiness parameter
written to /sys/devices/system/node/nodeX/reclaim to have no
effect when CONFIG_MEMCG is disabled.

Fix this by consolidating sc_swappiness() into a single definition
that checks sc->proactive_swappiness first, then falls back to
mem_cgroup_swappiness() which already handles both CONFIG_MEMCG
and !CONFIG_MEMCG.

Before fix (swappiness=max ignored, mostly file pages reclaimed):

    # cat /proc/sys/vm/swappiness
    60
    # cat /proc/vmstat | grep pgsteal
    pgsteal_kswapd 0
    pgsteal_direct 0
    pgsteal_khugepaged 0
    pgsteal_proactive 1840
    pgsteal_anon 25
    pgsteal_file 1815
    # echo "64M swappiness=max" > /sys/devices/system/node/node0/reclaim
    # cat /proc/vmstat | grep pgsteal
    pgsteal_kswapd 0
    pgsteal_direct 0
    pgsteal_khugepaged 0
    pgsteal_proactive 18013
    pgsteal_anon 337
    pgsteal_file 17676

After fix (swappiness=max honored, anon pages reclaimed as expected):

    # cat /proc/vmstat | grep pgsteal
    pgsteal_kswapd 0
    pgsteal_direct 0
    pgsteal_khugepaged 0
    pgsteal_proactive 0
    pgsteal_anon 0
    pgsteal_file 0
    # echo "64M swappiness=max" > /sys/devices/system/node/node0/reclaim
    # cat /proc/vmstat | grep pgsteal
    pgsteal_kswapd 0
    pgsteal_direct 0
    pgsteal_khugepaged 0
    pgsteal_proactive 16283
    pgsteal_anon 16283
    pgsteal_file 0

Fixes: 68cd9050d871 ("mm: add swappiness= arg to memory.reclaim")
Signed-off-by: Ridong Chen <chenridong@xiaomi.com>
---
 mm/vmscan.c | 17 +++++++----------
 1 file changed, 7 insertions(+), 10 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 35c3bb15ae96..5271bd023c1d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -198,6 +198,13 @@ struct scan_control {
  */
 int vm_swappiness = 60;
 
+static int sc_swappiness(struct scan_control *sc, struct mem_cgroup *memcg)
+{
+	if (sc->proactive && sc->proactive_swappiness)
+		return *sc->proactive_swappiness;
+	return mem_cgroup_swappiness(memcg);
+}
+
 #ifdef CONFIG_MEMCG
 
 /* Returns true for reclaim through cgroup limits or cgroup interfaces. */
@@ -239,12 +246,6 @@ static bool writeback_throttling_sane(struct scan_control *sc)
 	return false;
 }
 
-static int sc_swappiness(struct scan_control *sc, struct mem_cgroup *memcg)
-{
-	if (sc->proactive && sc->proactive_swappiness)
-		return *sc->proactive_swappiness;
-	return mem_cgroup_swappiness(memcg);
-}
 #else
 static bool cgroup_reclaim(struct scan_control *sc)
 {
@@ -261,10 +262,6 @@ static bool writeback_throttling_sane(struct scan_control *sc)
 	return true;
 }
 
-static int sc_swappiness(struct scan_control *sc, struct mem_cgroup *memcg)
-{
-	return READ_ONCE(vm_swappiness);
-}
 #endif
 
 static void set_task_reclaim_state(struct task_struct *task,
-- 
2.43.0