[PATCH v3] mm/memcg: clear folio memcg after changing per memcg stats
From: Bingfang Guo via B4 Relay
Date: Tue Sep 01 2026 - 22:07:07 EST
From: Bingfang Guo <bingfangguo@xxxxxxxxxxx>
I notice extremely high swapcached count in the per memcg level
memory.stat when running tests with cgroupv1 setup by swapping pages in
and out. It seems that the counter never gets decreased so the value is
rather useless and confusing to users reading it. So I think fixing it
so that the value can reflect the actual swapcache usage correctly could
be helpful.
__memcg1_swapout() transfers the memsw charge of a folio to its swap
entry and clears folio->memcg_data as part of that. In the vmscan
swapout path it runs before __swap_cache_del_folio(), which then
decrements the swapcache stats through lruvec_stat_mod_folio(). Since
folio->memcg_data has already been cleared, folio_memcg() returns NULL
and the NR_SWAPCACHE decrement only updates the node-level counter
instead of the memcg's lruvec, leaking the per-memcg swapcache count.
Move the __memcg1_swapout() call into __swap_cache_del_folio(), after
the NR_FILE_PAGES and NR_SWAPCACHE updates but before
__swap_cache_do_del_folio() removes the folio from the swap cache. This
keeps the stats attributed to the folio's memcg while still recording
the swap cgroup with a valid folio->swap. Add a swapout parameter so
the plain swap_cache_del_folio() path is left unchanged.
Fixes: b197d41462c20 ("mm/memcg, swap: store cgroup id in cluster table directly")
Signed-off-by: Bingfang Guo <bingfangguo@xxxxxxxxxxx>
---
The problem is reproducible using the following script and program:
```
#!/bin/bash
set -e
CG=/sys/fs/cgroup/memory/swapcache-leak-test
SIZE=$((256 * 1024 * 1024)) # 256 MiB of anon memory
[ "$(id -u)" -eq 0 ] || { echo "must run as root"; exit 1; }
grep -q . /proc/swaps <<<"$(tail -n +2 /proc/swaps)" || { echo "no swap active; run: swapon <dev>"; exit 1; }
cleanup() { rmdir "$CG" 2>/dev/null || true; }
trap cleanup EXIT
cc -O2 swapout.c -o swapout
mkdir -p "$CG"
echo "+memory" > /sys/fs/cgroup/cgroup.subtree_control 2>/dev/null || true
echo "== before reclaim =="
grep -E '^(swapcached|anon) ' "$CG/memory.stat"
# Put ourselves in the cgroup, allocate & touch anon memory, then wait to be reclaimed.
(
echo $BASHPID > "$CG/cgroup.procs"
# Allocate and dirty SIZE bytes of anonymous memory.
./swapout
) &
WORKER=$!
sleep 2
echo "== after reclaim (swap cache should drain to ~0) =="
grep -E '^(swapcached|anon) ' "$CG/memory.stat"
SWAPCACHED=$(awk '/^swapcached /{print $2}' "$CG/memory.stat")
echo
if [ "$SWAPCACHED" -gt $((1024 * 1024)) ]; then
echo "LEAK DETECTED: swapcached = $SWAPCACHED bytes (expected ~0) [BUGGY kernel]"
RC=1
else
echo "OK: swapcached = $SWAPCACHED bytes [FIXED kernel]"
RC=0
fi
kill "$WORKER" 2>/dev/null || true
wait "$WORKER" 2>/dev/null || true
exit $RC
```
swapout.c:
```
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <sys/mman.h>
int main(int argc, char **argv)
{
size_t mib = (argc > 1) ? strtoul(argv[1], NULL, 10) : 256;
size_t size = mib * 1024UL * 1024UL;
long page = sysconf(_SC_PAGESIZE);
char *buf;
size_t i;
buf = mmap(NULL, size, PROT_READ | PROT_WRITE,
MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
if (buf == MAP_FAILED) {
perror("mmap");
return 1;
}
/* Fault in and dirty every page so it becomes reclaimable anon. */
for (i = 0; i < size; i += page)
buf[i] = 1;
printf("allocated and dirtied %zu MiB, paging out...\n", mib);
/* Force the whole range out to swap. */
if (madvise(buf, size, MADV_PAGEOUT)) {
perror("madvise(MADV_PAGEOUT)");
return 1;
}
/* Give reclaim a moment, then stay alive so the cgroup can be inspected. */
printf("paged out; sleeping so memory.stat can be read. pid=%d\n", getpid());
sleep(30);
munmap(buf, size);
return 0;
}
```
Test result:
before:
```
== before reclaim ==
swapcached 0
allocated and dirtied 256 MiB, paging out...
paged out; sleeping so memory.stat can be read. pid=4778
== after reclaim (swap cache should drain to ~0) ==
swapcached 268435456
LEAK DETECTED: swapcached = 268435456 bytes (expected ~0) [BUGGY kernel]
```
after the patch:
```
== before reclaim ==
swapcached 0
allocated and dirtied 256 MiB, paging out...
paged out; sleeping so memory.stat can be read. pid=2601
== after reclaim (swap cache should drain to ~0) ==
swapcached 0
OK: swapcached = 0 bytes [FIXED kernel]
```
---
Changes in v3:
- Add doc for the new parameter.
- Link to v2: https://lore.kernel.org/r/20260901-memcg-swapcache-stats-fix-v2-1-9caad330459b@xxxxxxxxxxx
Changes in v2:
- Update the commit message to describe the problem in the beginnning.
- Change function declaration for !CONFIG_SWAP as well.
- Link to v1: https://lore.kernel.org/r/20260831-memcg-swapcache-stats-fix-v1-1-1c0819ebdb86@xxxxxxxxxxx
---
mm/swap.h | 6 ++++--
mm/swap_state.c | 11 ++++++++---
mm/vmscan.c | 3 +--
3 files changed, 13 insertions(+), 7 deletions(-)
diff --git a/mm/swap.h b/mm/swap.h
index 0b5d507739bcb..b3b54c28929a1 100644
--- a/mm/swap.h
+++ b/mm/swap.h
@@ -319,7 +319,8 @@ struct folio *swap_cache_alloc_folio(swp_entry_t target_entry, gfp_t gfp_mask,
void __swap_cache_add_folio(struct swap_cluster_info *ci,
struct folio *folio, swp_entry_t entry);
void __swap_cache_del_folio(struct swap_cluster_info *ci,
- struct folio *folio, swp_entry_t entry, void *shadow);
+ struct folio *folio, swp_entry_t entry, void *shadow,
+ bool swapout);
void __swap_cache_replace_folio(struct swap_cluster_info *ci,
struct folio *old, struct folio *new);
@@ -452,7 +453,8 @@ static inline void swap_cache_del_folio(struct folio *folio)
}
static inline void __swap_cache_del_folio(struct swap_cluster_info *ci,
- struct folio *folio, swp_entry_t entry, void *shadow)
+ struct folio *folio, swp_entry_t entry, void *shadow,
+ bool swapout)
{
}
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 305877e1f4d7b..99985208b529b 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -306,6 +306,7 @@ static void __swap_cache_do_del_folio(struct swap_cluster_info *ci,
* @folio: The folio.
* @entry: The first swap entry that the folio corresponds to.
* @shadow: shadow value to be filled in the swap cache.
+ * @swapout: whether this operation swaps out the folio.
*
* Removes a folio from the swap cache and fills a shadow in place.
* This won't put the folio's refcount. The caller has to do that.
@@ -314,13 +315,17 @@ static void __swap_cache_do_del_folio(struct swap_cluster_info *ci,
* using the index of @entry, and lock the cluster that holds the entries.
*/
void __swap_cache_del_folio(struct swap_cluster_info *ci, struct folio *folio,
- swp_entry_t entry, void *shadow)
+ swp_entry_t entry, void *shadow, bool swapout)
{
unsigned long nr_pages = folio_nr_pages(folio);
- __swap_cache_do_del_folio(ci, folio, entry, shadow);
node_stat_mod_folio(folio, NR_FILE_PAGES, -nr_pages);
lruvec_stat_mod_folio(folio, NR_SWAPCACHE, -nr_pages);
+
+ if (swapout)
+ __memcg1_swapout(folio, ci);
+
+ __swap_cache_do_del_folio(ci, folio, entry, shadow);
}
/**
@@ -339,7 +344,7 @@ void swap_cache_del_folio(struct folio *folio)
swp_entry_t entry = folio->swap;
ci = swap_cluster_lock(__swap_entry_to_info(entry), swp_offset(entry));
- __swap_cache_del_folio(ci, folio, entry, NULL);
+ __swap_cache_del_folio(ci, folio, entry, NULL, false);
swap_cluster_unlock(ci);
folio_ref_sub(folio, folio_nr_pages(folio));
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b4c9b8f3dfe99..af7dfa905cb50 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -735,8 +735,7 @@ static int __remove_mapping(struct address_space *mapping, struct folio *folio,
if (reclaimed && !mapping_exiting(mapping))
shadow = workingset_eviction(folio, target_memcg);
- __memcg1_swapout(folio, ci);
- __swap_cache_del_folio(ci, folio, swap, shadow);
+ __swap_cache_del_folio(ci, folio, swap, shadow, true);
swap_cluster_unlock_irq(ci);
} else {
void (*free_folio)(struct folio *);
---
base-commit: 88297631d4d42f6004cb39c0ba3da7d2d10a616f
change-id: 20260828-memcg-swapcache-stats-fix-1beef3dc3afb
Best regards,
--
Bingfang Guo <bingfangguo@xxxxxxxxxxx>