aboutsummaryrefslogtreecommitdiffstats
path: root/mm
diff options
authorKairui Song <kasong@tencent.com>2026-05-17 23:39:50 +0800
committerAndrew Morton <akpm@linux-foundation.org>2026-05-28 21:31:09 -0700
commite5424e22f89515a107e85ea18859eb36a0c9ab22 (patch)
treebdd3c853c2ff4162ce9b32ac15003a7ff462f8cb /mm
parent3efa15243a5f7aa5d002642efc819f6219d1c66e (diff)
downloadlinux-next-history-e5424e22f89515a107e85ea18859eb36a0c9ab22.tar.gz
mm/memcg: remove no longer used swap cgroup array
Now all swap cgroup records are stored in the swap cluster directly, the static array is no longer needed. Link: https://lore.kernel.org/20260517-swap-table-p4-v5-11-88ae43e064c7@tencent.com Signed-off-by: Kairui Song <kasong@tencent.com> Acked-by: Chris Li <chrisl@kernel.org> Cc: Baolin Wang <baolin.wang@linux.alibaba.com> Cc: Baoquan He <bhe@redhat.com> Cc: Barry Song <baohua@kernel.org> Cc: Chengming Zhou <chengming.zhou@linux.dev> Cc: David Hildenbrand <david@kernel.org> Cc: Hugh Dickins <hughd@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kemeng Shi <shikemeng@huaweicloud.com> Cc: Lorenzo Stoakes <ljs@kernel.org> Cc: Muchun Song <muchun.song@linux.dev> Cc: Nhat Pham <nphamcs@gmail.com> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Shakeel Butt <shakeel.butt@linux.dev> Cc: Youngjun Park <youngjun.park@lge.com> Cc: Zi Yan <ziy@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/Makefile3
-rw-r--r--mm/internal.h1
-rw-r--r--mm/memcontrol-v1.c1
-rw-r--r--mm/memcontrol.c1
-rw-r--r--mm/swap_cgroup.c174
-rw-r--r--mm/swapfile.c8
6 files changed, 0 insertions, 188 deletions
diff --git a/mm/Makefile b/mm/Makefile
index 8ad2ab08244eb..eff9f9e7e061c 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 9dbd8e3c991f3..5602393054f3e 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 517b21236672b..7650692115678 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 beecfc6f376dc..92269740eef13 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 95c38e54dd587..0000000000000
--- a/mm/swap_cgroup.c
+++ /dev/null
@@ -1,174 +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)];
- if (unlikely(!ctrl->map))
- return 0;
- 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 bd141eb9ef10a..992e77b7105df 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"
@@ -3058,8 +3057,6 @@ 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;
@@ -3590,10 +3587,6 @@ 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.
@@ -3704,7 +3697,6 @@ bad_swap:
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);