[PATCH -v4 0/2] mm: vmscan: fix node reclaim ignoring swappiness parameter

[PATCH -v4 0/2] mm: vmscan: fix node reclaim ignoring swappiness parameter

[Ridong]

From: Ridong Chen <chenridong@xiaomi.com>

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

Patch 1 moves mem_cgroup_swappiness() and vm_swappiness out of the public
include/linux/swap.h into the mm-private mm/swap.h, and makes the helper
handle both CONFIG_MEMCG and !CONFIG_MEMCG 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.

---

v3 -> v4:
 - READ_ONCE() was missed when reading memcg->swappiness, add it back.

v2 -> v3:
 - Simplify mem_cgroup_swappiness as suggested by Johannes.  
 - Rebase on the next-20260722

v1 -> v2:
 - Move mem_cgroup_swappiness() and vm_swappiness to mm/swap.h instead of
   include/linux/memcontrol.h. Suggested by Barry Song.
 - Correct fix tag for patch 2.

v1: https://lore.kernel.org/all/20260711091157.306070-1-ridong.chen@linux.dev/

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

 include/linux/memcontrol.h |  4 ++--
 include/linux/swap.h       | 19 -------------------
 mm/memcontrol.c            |  4 ++--
 mm/swap.h                  | 13 +++++++++++++
 mm/vmscan.c                | 19 +++++++------------
 5 files changed, 24 insertions(+), 35 deletions(-)

-- 
2.34.1

[PATCH -v4 1/2] memcg: move mem_cgroup_swappiness and vm_swappiness to mm/swap.h

[Ridong]

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.

Both mem_cgroup_swappiness() and vm_swappiness are only used within
mm/ (memcontrol.c, memcontrol-v1.c, vmscan.c), so move them out of the
public include/linux/swap.h into the mm-private mm/swap.h. This keeps
unrelated declarations out of include/linux/swap.h.

Guard memcg->swappiness with CONFIG_MEMCG_V1 as well, so v2-only
kernels drop the unused field.

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

Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Barry Song <baohua@kernel.org>
Reviewed-by: Song Hu <husong@kylinos.cn>
Signed-off-by: Ridong Chen <chenridong@xiaomi.com>
---
 include/linux/memcontrol.h |  4 ++--
 include/linux/swap.h       | 19 -------------------
 mm/memcontrol.c            |  4 ++--
 mm/swap.h                  | 13 +++++++++++++
 4 files changed, 17 insertions(+), 23 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 957260677678..e7a794dfb40e 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 +316,8 @@ 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[];
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 0544b2ec4c56..45f301d73e2a 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -309,7 +309,6 @@ static inline bool lru_cache_disabled(void)
 }
 
 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)
@@ -473,25 +472,7 @@ 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 *memcg)
-{
-	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 8319ad8c5c23..6864b76456fb 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -63,6 +63,7 @@
 #include <linux/sched/isolation.h>
 #include <linux/kmemleak.h>
 #include "internal.h"
+#include "swap.h"
 #include "swap_table.h"
 #include <net/sock.h>
 #include <net/ip.h>
@@ -4176,11 +4177,10 @@ 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);
diff --git a/mm/swap.h b/mm/swap.h
index abd26588abd2..d077e5893a42 100644
--- a/mm/swap.h
+++ b/mm/swap.h
@@ -4,6 +4,7 @@
 
 #include <linux/atomic.h> /* for atomic_long_t */
 #include <linux/mm.h> /* for PAGE_SHIFT */
+#include <linux/memcontrol.h> /* for mem_cgroup_swappiness() */
 
 struct mempolicy;
 struct swap_iocb;
@@ -99,6 +100,18 @@ struct swap_ops {
 	void (*submit_read)(struct swap_io_ctx *ctx);
 };
 
+extern int vm_swappiness;
+
+static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg)
+{
+#ifdef CONFIG_MEMCG_V1
+	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) &&
+	    !mem_cgroup_disabled() && !mem_cgroup_is_root(memcg))
+		return READ_ONCE(memcg->swappiness);
+#endif
+	return READ_ONCE(vm_swappiness);
+}
+
 #ifdef CONFIG_SWAP
 #include <linux/swapops.h> /* for swp_offset */
 #include <linux/blk_types.h> /* for bio_end_io_t */
-- 
2.34.1

[PATCH -v4 2/2] mm: vmscan: fix node reclaim ignoring swappiness parameter

[Ridong]

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

Cc: stable@vger.kernel.org # 6.17+
Fixes: b980077899ea ("mm: introduce per-node proactive reclaim interface")
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Barry Song <baohua@kernel.org>
Acked-by: Qi Zheng <qi.zheng@linux.dev>
Tested-by: Song Hu <husong@kylinos.cn>
Reviewed-by: Song Hu <husong@kylinos.cn>
Signed-off-by: Ridong Chen <chenridong@xiaomi.com>
---
 mm/vmscan.c | 19 +++++++------------
 1 file changed, 7 insertions(+), 12 deletions(-)

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 06e103f9781e..155167b3614b 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -199,6 +199,13 @@ 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. */
@@ -239,13 +246,6 @@ static bool writeback_throttling_sane(struct scan_control *sc)
 #endif
 	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)
 {
@@ -261,11 +261,6 @@ 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,
-- 
2.34.1