Re: [PATCH v3 11/12] mm/memcg: remove no longer used swap cgroup array

[Chris Li]

On Tue, Apr 21, 2026 at 8:17 AM Kairui Song via B4 Relay
<devnull+kasong.tencent.com@xxxxxxxxxx> wrote:
>
> From: Kairui Song <kasong@xxxxxxxxxxx>
>
> Now all swap cgroup records are stored in the swap cluster directly,
> the static array is no longer needed.
>
> Signed-off-by: Kairui Song <kasong@xxxxxxxxxxx>
> ---
>  MAINTAINERS                 |   1 -
>  include/linux/swap_cgroup.h |  47 ------------
>  mm/Makefile                 |   3 -
>  mm/internal.h               |   1 -
>  mm/memcontrol-v1.c          |   1 -
>  mm/memcontrol.c             |   1 -
>  mm/swap_cgroup.c            | 172 --------------------------------------------

Nice patch stats.

Acked-by: Chris Li <chrisl@xxxxxxxxxx>

Chris

>  mm/swapfile.c               |   8 ---
>  8 files changed, 234 deletions(-)
>
> diff --git a/MAINTAINERS b/MAINTAINERS
> index 76d8291237be..217d98c89275 100644
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
> @@ -6565,7 +6565,6 @@ F:        mm/memcontrol.c
>  F:     mm/memcontrol-v1.c
>  F:     mm/memcontrol-v1.h
>  F:     mm/page_counter.c
> -F:     mm/swap_cgroup.c
>  F:     samples/cgroup/*
>  F:     tools/testing/selftests/cgroup/memcg_protection.m
>  F:     tools/testing/selftests/cgroup/test_hugetlb_memcg.c
> diff --git a/include/linux/swap_cgroup.h b/include/linux/swap_cgroup.h
> deleted file mode 100644
> index 91cdf12190a0..000000000000
> --- a/include/linux/swap_cgroup.h
> +++ /dev/null
> @@ -1,47 +0,0 @@
> -/* SPDX-License-Identifier: GPL-2.0 */
> -#ifndef __LINUX_SWAP_CGROUP_H
> -#define __LINUX_SWAP_CGROUP_H
> -
> -#include <linux/swap.h>
> -
> -#if defined(CONFIG_MEMCG) && defined(CONFIG_SWAP)
> -
> -extern void swap_cgroup_record(struct folio *folio, unsigned short id, swp_entry_t ent);
> -extern unsigned short swap_cgroup_clear(swp_entry_t ent, unsigned int nr_ents);
> -extern unsigned short lookup_swap_cgroup_id(swp_entry_t ent);
> -extern int swap_cgroup_swapon(int type, unsigned long max_pages);
> -extern void swap_cgroup_swapoff(int type);
> -
> -#else
> -
> -static inline
> -void swap_cgroup_record(struct folio *folio, unsigned short id, swp_entry_t ent)
> -{
> -}
> -
> -static inline
> -unsigned short swap_cgroup_clear(swp_entry_t ent, unsigned int nr_ents)
> -{
> -       return 0;
> -}
> -
> -static inline
> -unsigned short lookup_swap_cgroup_id(swp_entry_t ent)
> -{
> -       return 0;
> -}
> -
> -static inline int
> -swap_cgroup_swapon(int type, unsigned long max_pages)
> -{
> -       return 0;
> -}
> -
> -static inline void swap_cgroup_swapoff(int type)
> -{
> -       return;
> -}
> -
> -#endif
> -
> -#endif /* __LINUX_SWAP_CGROUP_H */
> diff --git a/mm/Makefile b/mm/Makefile
> index 8ad2ab08244e..eff9f9e7e061 100644
> --- a/mm/Makefile
> +++ b/mm/Makefile
> @@ -103,9 +103,6 @@ obj-$(CONFIG_PAGE_COUNTER) += page_counter.o
>  obj-$(CONFIG_LIVEUPDATE_MEMFD) += memfd_luo.o
>  obj-$(CONFIG_MEMCG_V1) += memcontrol-v1.o
>  obj-$(CONFIG_MEMCG) += memcontrol.o vmpressure.o
> -ifdef CONFIG_SWAP
> -obj-$(CONFIG_MEMCG) += swap_cgroup.o
> -endif
>  ifdef CONFIG_BPF_SYSCALL
>  obj-$(CONFIG_MEMCG) += bpf_memcontrol.o
>  endif
> diff --git a/mm/internal.h b/mm/internal.h
> index 9d2fec696bd6..7646ecb9d621 100644
> --- a/mm/internal.h
> +++ b/mm/internal.h
> @@ -17,7 +17,6 @@
>  #include <linux/rmap.h>
>  #include <linux/swap.h>
>  #include <linux/leafops.h>
> -#include <linux/swap_cgroup.h>
>  #include <linux/tracepoint-defs.h>
>
>  /* Internal core VMA manipulation functions. */
> diff --git a/mm/memcontrol-v1.c b/mm/memcontrol-v1.c
> index 494e7b9adc60..08be1a752c2e 100644
> --- a/mm/memcontrol-v1.c
> +++ b/mm/memcontrol-v1.c
> @@ -5,7 +5,6 @@
>  #include <linux/mm_inline.h>
>  #include <linux/pagewalk.h>
>  #include <linux/backing-dev.h>
> -#include <linux/swap_cgroup.h>
>  #include <linux/eventfd.h>
>  #include <linux/poll.h>
>  #include <linux/sort.h>
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 193c8eb73be7..12165fd32529 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -54,7 +54,6 @@
>  #include <linux/vmpressure.h>
>  #include <linux/memremap.h>
>  #include <linux/mm_inline.h>
> -#include <linux/swap_cgroup.h>
>  #include <linux/cpu.h>
>  #include <linux/oom.h>
>  #include <linux/lockdep.h>
> diff --git a/mm/swap_cgroup.c b/mm/swap_cgroup.c
> deleted file mode 100644
> index de779fed8c21..000000000000
> --- a/mm/swap_cgroup.c
> +++ /dev/null
> @@ -1,172 +0,0 @@
> -// SPDX-License-Identifier: GPL-2.0
> -#include <linux/swap_cgroup.h>
> -#include <linux/vmalloc.h>
> -#include <linux/mm.h>
> -
> -#include <linux/swapops.h> /* depends on mm.h include */
> -
> -static DEFINE_MUTEX(swap_cgroup_mutex);
> -
> -/* Pack two cgroup id (short) of two entries in one swap_cgroup (atomic_t) */
> -#define ID_PER_SC (sizeof(struct swap_cgroup) / sizeof(unsigned short))
> -#define ID_SHIFT (BITS_PER_TYPE(unsigned short))
> -#define ID_MASK (BIT(ID_SHIFT) - 1)
> -struct swap_cgroup {
> -       atomic_t ids;
> -};
> -
> -struct swap_cgroup_ctrl {
> -       struct swap_cgroup *map;
> -};
> -
> -static struct swap_cgroup_ctrl swap_cgroup_ctrl[MAX_SWAPFILES];
> -
> -static unsigned short __swap_cgroup_id_lookup(struct swap_cgroup *map,
> -                                             pgoff_t offset)
> -{
> -       unsigned int shift = (offset % ID_PER_SC) * ID_SHIFT;
> -       unsigned int old_ids = atomic_read(&map[offset / ID_PER_SC].ids);
> -
> -       BUILD_BUG_ON(!is_power_of_2(ID_PER_SC));
> -       BUILD_BUG_ON(sizeof(struct swap_cgroup) != sizeof(atomic_t));
> -
> -       return (old_ids >> shift) & ID_MASK;
> -}
> -
> -static unsigned short __swap_cgroup_id_xchg(struct swap_cgroup *map,
> -                                           pgoff_t offset,
> -                                           unsigned short new_id)
> -{
> -       unsigned short old_id;
> -       struct swap_cgroup *sc = &map[offset / ID_PER_SC];
> -       unsigned int shift = (offset % ID_PER_SC) * ID_SHIFT;
> -       unsigned int new_ids, old_ids = atomic_read(&sc->ids);
> -
> -       do {
> -               old_id = (old_ids >> shift) & ID_MASK;
> -               new_ids = (old_ids & ~(ID_MASK << shift));
> -               new_ids |= ((unsigned int)new_id) << shift;
> -       } while (!atomic_try_cmpxchg(&sc->ids, &old_ids, new_ids));
> -
> -       return old_id;
> -}
> -
> -/**
> - * swap_cgroup_record - record mem_cgroup for a set of swap entries.
> - * These entries must belong to one single folio, and that folio
> - * must be being charged for swap space (swap out), and these
> - * entries must not have been charged
> - *
> - * @folio: the folio that the swap entry belongs to
> - * @id: mem_cgroup ID to be recorded
> - * @ent: the first swap entry to be recorded
> - */
> -void swap_cgroup_record(struct folio *folio, unsigned short id,
> -                       swp_entry_t ent)
> -{
> -       unsigned int nr_ents = folio_nr_pages(folio);
> -       struct swap_cgroup *map;
> -       pgoff_t offset, end;
> -       unsigned short old;
> -
> -       offset = swp_offset(ent);
> -       end = offset + nr_ents;
> -       map = swap_cgroup_ctrl[swp_type(ent)].map;
> -
> -       do {
> -               old = __swap_cgroup_id_xchg(map, offset, id);
> -               VM_BUG_ON(old);
> -       } while (++offset != end);
> -}
> -
> -/**
> - * swap_cgroup_clear - clear mem_cgroup for a set of swap entries.
> - * These entries must be being uncharged from swap. They either
> - * belongs to one single folio in the swap cache (swap in for
> - * cgroup v1), or no longer have any users (slot freeing).
> - *
> - * @ent: the first swap entry to be recorded into
> - * @nr_ents: number of swap entries to be recorded
> - *
> - * Returns the existing old value.
> - */
> -unsigned short swap_cgroup_clear(swp_entry_t ent, unsigned int nr_ents)
> -{
> -       pgoff_t offset, end;
> -       struct swap_cgroup *map;
> -       unsigned short old, iter = 0;
> -
> -       offset = swp_offset(ent);
> -       end = offset + nr_ents;
> -       map = swap_cgroup_ctrl[swp_type(ent)].map;
> -
> -       do {
> -               old = __swap_cgroup_id_xchg(map, offset, 0);
> -               if (!iter)
> -                       iter = old;
> -               VM_BUG_ON(iter != old);
> -       } while (++offset != end);
> -
> -       return old;
> -}
> -
> -/**
> - * lookup_swap_cgroup_id - lookup mem_cgroup id tied to swap entry
> - * @ent: swap entry to be looked up.
> - *
> - * Returns ID of mem_cgroup at success. 0 at failure. (0 is invalid ID)
> - */
> -unsigned short lookup_swap_cgroup_id(swp_entry_t ent)
> -{
> -       struct swap_cgroup_ctrl *ctrl;
> -
> -       if (mem_cgroup_disabled())
> -               return 0;
> -
> -       ctrl = &swap_cgroup_ctrl[swp_type(ent)];
> -       return __swap_cgroup_id_lookup(ctrl->map, swp_offset(ent));
> -}
> -
> -int swap_cgroup_swapon(int type, unsigned long max_pages)
> -{
> -       struct swap_cgroup *map;
> -       struct swap_cgroup_ctrl *ctrl;
> -
> -       if (mem_cgroup_disabled())
> -               return 0;
> -
> -       BUILD_BUG_ON(sizeof(unsigned short) * ID_PER_SC !=
> -                    sizeof(struct swap_cgroup));
> -       map = vzalloc(DIV_ROUND_UP(max_pages, ID_PER_SC) *
> -                     sizeof(struct swap_cgroup));
> -       if (!map)
> -               goto nomem;
> -
> -       ctrl = &swap_cgroup_ctrl[type];
> -       mutex_lock(&swap_cgroup_mutex);
> -       ctrl->map = map;
> -       mutex_unlock(&swap_cgroup_mutex);
> -
> -       return 0;
> -nomem:
> -       pr_info("couldn't allocate enough memory for swap_cgroup\n");
> -       pr_info("swap_cgroup can be disabled by swapaccount=0 boot option\n");
> -       return -ENOMEM;
> -}
> -
> -void swap_cgroup_swapoff(int type)
> -{
> -       struct swap_cgroup *map;
> -       struct swap_cgroup_ctrl *ctrl;
> -
> -       if (mem_cgroup_disabled())
> -               return;
> -
> -       mutex_lock(&swap_cgroup_mutex);
> -       ctrl = &swap_cgroup_ctrl[type];
> -       map = ctrl->map;
> -       ctrl->map = NULL;
> -       mutex_unlock(&swap_cgroup_mutex);
> -
> -       vfree(map);
> -}
> diff --git a/mm/swapfile.c b/mm/swapfile.c
> index edf4cb36728e..2172920e68d1 100644
> --- a/mm/swapfile.c
> +++ b/mm/swapfile.c
> @@ -45,7 +45,6 @@
>
>  #include <asm/tlbflush.h>
>  #include <linux/leafops.h>
> -#include <linux/swap_cgroup.h>
>  #include "swap_table.h"
>  #include "internal.h"
>  #include "swap.h"
> @@ -3136,8 +3135,6 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
>         p->global_cluster = NULL;
>         kvfree(zeromap);
>         free_swap_cluster_info(cluster_info, maxpages);
> -       /* Destroy swap account information */
> -       swap_cgroup_swapoff(p->type);
>
>         inode = mapping->host;
>
> @@ -3668,10 +3665,6 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
>         if (error)
>                 goto bad_swap_unlock_inode;
>
> -       error = swap_cgroup_swapon(si->type, maxpages);
> -       if (error)
> -               goto bad_swap_unlock_inode;
> -
>         /*
>          * Use kvmalloc_array instead of bitmap_zalloc as the allocation order might
>          * be above MAX_PAGE_ORDER incase of a large swap file.
> @@ -3782,7 +3775,6 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
>         si->global_cluster = NULL;
>         inode = NULL;
>         destroy_swap_extents(si, swap_file);
> -       swap_cgroup_swapoff(si->type);
>         free_swap_cluster_info(si->cluster_info, si->max);
>         si->cluster_info = NULL;
>         kvfree(si->zeromap);
>
> --
> 2.53.0
>
>
>