From 1b7c8fe294a6bf913832e998f519029cad47dbcb Mon Sep 17 00:00:00 2001 From: Ridong Chen Date: Thu, 23 Jul 2026 11:24:33 +0800 Subject: [PATCH] memcg: move mem_cgroup_swappiness and vm_swappiness to mm/swap.h Patch series "mm: vmscan: fix node reclaim ignoring swappiness parameter", v4. 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. This patch (of 2): 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. Link: https://lore.kernel.org/20260723032434.2016749-1-ridong.chen@linux.dev Link: https://lore.kernel.org/20260723032434.2016749-2-ridong.chen@linux.dev Signed-off-by: Ridong Chen Acked-by: Johannes Weiner Reviewed-by: Barry Song Reviewed-by: Song Hu Acked-by: Shakeel Butt Cc: Axel Rasmussen Cc: Baoquan He Cc: Chris Li Cc: David Hildenbrand Cc: Davidlohr Bueso Cc: Kairui Song Cc: Kemeng Shi Cc: Lorenzo Stoakes Cc: Michal Hocko Cc: Muchun Song Cc: Nhat Pham Cc: Roman Gushchin Cc: Wei Xu Cc: Yuanchu Xie Cc: Qi Zheng Signed-off-by: Andrew Morton --- include/linux/memcontrol.h | 4 ++-- include/linux/swap.h | 19 ------------------- mm/memcontrol.c | 4 ++-- mm/swap.h | 14 ++++++++++++++ 4 files changed, 18 insertions(+), 23 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 8170bb8066a2..f619e24fc3bb 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 696ed01709c2..330a420fd6de 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) @@ -468,25 +467,7 @@ 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 69b37f63a307..ec92cb40156d 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -63,6 +63,7 @@ #include #include #include "internal.h" +#include "swap.h" #include "swap_table.h" #include #include @@ -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; memcg->memsw.track_failcnt = !memcg_on_dfl; WRITE_ONCE(memcg->oom_kill_disable, READ_ONCE(parent->oom_kill_disable)); diff --git a/mm/swap.h b/mm/swap.h index b51ad3071a73..2ccf8cf7f6c1 100644 --- a/mm/swap.h +++ b/mm/swap.h @@ -4,6 +4,8 @@ #include /* for atomic_long_t */ #include /* for PAGE_SHIFT */ +#include /* for mem_cgroup_swappiness() */ + struct mempolicy; struct swap_iocb; struct swap_memcg_table; @@ -76,6 +78,18 @@ enum swap_cluster_flags { CLUSTER_FLAG_MAX, }; +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 /* for swp_offset */ #include /* for bio_end_io_t */