| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20251117-swap-table-p2-v2-8-37730e6ea6d5@tencent.com>
Date: Mon, 17 Nov 2025 02:11:49 +0800
From: Kairui Song <ryncsn@...il.com>
To: linux-mm@...ck.org
Cc: Andrew Morton <akpm@...ux-foundation.org>, Baoquan He <bhe@...hat.com>,
Barry Song <baohua@...nel.org>, Chris Li <chrisl@...nel.org>,
Nhat Pham <nphamcs@...il.com>, Yosry Ahmed <yosry.ahmed@...ux.dev>,
David Hildenbrand <david@...nel.org>, Johannes Weiner <hannes@...xchg.org>,
Youngjun Park <youngjun.park@....com>, Hugh Dickins <hughd@...gle.com>,
Baolin Wang <baolin.wang@...ux.alibaba.com>,
Ying Huang <ying.huang@...ux.alibaba.com>,
Kemeng Shi <shikemeng@...weicloud.com>,
Lorenzo Stoakes <lorenzo.stoakes@...cle.com>,
"Matthew Wilcox (Oracle)" <willy@...radead.org>,
linux-kernel@...r.kernel.org, Kairui Song <kasong@...cent.com>
Subject: [PATCH v2 08/19] mm/shmem, swap: remove SWAP_MAP_SHMEM
From: Nhat Pham <nphamcs@...il.com>
The SWAP_MAP_SHMEM state was introduced in the commit aaa468653b4a
("swap_info: note SWAP_MAP_SHMEM"), to quickly determine if a swap entry
belongs to shmem during swapoff.
However, swapoff has since been rewritten in the commit b56a2d8af914
("mm: rid swapoff of quadratic complexity"). Now having swap count ==
SWAP_MAP_SHMEM value is basically the same as having swap count == 1,
and swap_shmem_alloc() behaves analogously to swap_duplicate(). The only
difference of note is that swap_shmem_alloc() does not check for
-ENOMEM returned from __swap_duplicate(), but it is OK because shmem
never re-duplicates any swap entry it owns. This will stil be safe if we
use (batched) swap_duplicate() instead.
This commit adds swap_duplicate_nr(), the batched variant of
swap_duplicate(), and removes the SWAP_MAP_SHMEM state and the
associated swap_shmem_alloc() helper to simplify the state machine (both
mentally and in terms of actual code). We will also have an extra
state/special value that can be repurposed (for swap entries that never
gets re-duplicated).
Signed-off-by: Nhat Pham <nphamcs@...il.com>
Signed-off-by: Kairui Song <kasong@...cent.com>
---
include/linux/swap.h | 15 +++++++--------
mm/shmem.c | 2 +-
mm/swapfile.c | 42 +++++++++++++++++-------------------------
3 files changed, 25 insertions(+), 34 deletions(-)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 38ca3df68716..bf72b548a96d 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -230,7 +230,6 @@ enum {
/* Special value in first swap_map */
#define SWAP_MAP_MAX 0x3e /* Max count */
#define SWAP_MAP_BAD 0x3f /* Note page is bad */
-#define SWAP_MAP_SHMEM 0xbf /* Owned by shmem/tmpfs */
/* Special value in each swap_map continuation */
#define SWAP_CONT_MAX 0x7f /* Max count */
@@ -458,8 +457,7 @@ bool folio_free_swap(struct folio *folio);
void put_swap_folio(struct folio *folio, swp_entry_t entry);
extern swp_entry_t get_swap_page_of_type(int);
extern int add_swap_count_continuation(swp_entry_t, gfp_t);
-extern void swap_shmem_alloc(swp_entry_t, int);
-extern int swap_duplicate(swp_entry_t);
+extern int swap_duplicate_nr(swp_entry_t entry, int nr);
extern int swapcache_prepare(swp_entry_t entry, int nr);
extern void swap_free_nr(swp_entry_t entry, int nr_pages);
extern void free_swap_and_cache_nr(swp_entry_t entry, int nr);
@@ -514,11 +512,7 @@ static inline int add_swap_count_continuation(swp_entry_t swp, gfp_t gfp_mask)
return 0;
}
-static inline void swap_shmem_alloc(swp_entry_t swp, int nr)
-{
-}
-
-static inline int swap_duplicate(swp_entry_t swp)
+static inline int swap_duplicate_nr(swp_entry_t swp, int nr_pages)
{
return 0;
}
@@ -569,6 +563,11 @@ static inline int add_swap_extent(struct swap_info_struct *sis,
}
#endif /* CONFIG_SWAP */
+static inline int swap_duplicate(swp_entry_t entry)
+{
+ return swap_duplicate_nr(entry, 1);
+}
+
static inline void free_swap_and_cache(swp_entry_t entry)
{
free_swap_and_cache_nr(entry, 1);
diff --git a/mm/shmem.c b/mm/shmem.c
index 8b711b8bcdba..0b0af71ce5e8 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1654,7 +1654,7 @@ int shmem_writeout(struct folio *folio, struct swap_iocb **plug,
spin_unlock(&shmem_swaplist_lock);
}
- swap_shmem_alloc(folio->swap, nr_pages);
+ swap_duplicate_nr(folio->swap, nr_pages);
shmem_delete_from_page_cache(folio, swp_to_radix_entry(folio->swap));
BUG_ON(folio_mapped(folio));
diff --git a/mm/swapfile.c b/mm/swapfile.c
index a433445e9225..580adf9d93bd 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -201,7 +201,7 @@ static bool swap_is_last_map(struct swap_info_struct *si,
unsigned char *map_end = map + nr_pages;
unsigned char count = *map;
- if (swap_count(count) != 1 && swap_count(count) != SWAP_MAP_SHMEM)
+ if (swap_count(count) != 1)
return false;
while (++map < map_end) {
@@ -1522,12 +1522,6 @@ static unsigned char swap_entry_put_locked(struct swap_info_struct *si,
if (usage == SWAP_HAS_CACHE) {
VM_BUG_ON(!has_cache);
has_cache = 0;
- } else if (count == SWAP_MAP_SHMEM) {
- /*
- * Or we could insist on shmem.c using a special
- * swap_shmem_free() and free_shmem_swap_and_cache()...
- */
- count = 0;
} else if ((count & ~COUNT_CONTINUED) <= SWAP_MAP_MAX) {
if (count == COUNT_CONTINUED) {
if (swap_count_continued(si, offset, count))
@@ -1625,7 +1619,7 @@ static bool swap_entries_put_map(struct swap_info_struct *si,
if (nr <= 1)
goto fallback;
count = swap_count(data_race(si->swap_map[offset]));
- if (count != 1 && count != SWAP_MAP_SHMEM)
+ if (count != 1)
goto fallback;
ci = swap_cluster_lock(si, offset);
@@ -1679,12 +1673,10 @@ static bool swap_entries_put_map_nr(struct swap_info_struct *si,
/*
* Check if it's the last ref of swap entry in the freeing path.
- * Qualified value includes 1, SWAP_HAS_CACHE or SWAP_MAP_SHMEM.
*/
static inline bool __maybe_unused swap_is_last_ref(unsigned char count)
{
- return (count == SWAP_HAS_CACHE) || (count == 1) ||
- (count == SWAP_MAP_SHMEM);
+ return (count == SWAP_HAS_CACHE) || (count == 1);
}
/*
@@ -3678,7 +3670,6 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage, int nr)
offset = swp_offset(entry);
VM_WARN_ON(nr > SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER);
- VM_WARN_ON(usage == 1 && nr > 1);
ci = swap_cluster_lock(si, offset);
err = 0;
@@ -3738,27 +3729,28 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage, int nr)
return err;
}
-/*
- * Help swapoff by noting that swap entry belongs to shmem/tmpfs
- * (in which case its reference count is never incremented).
- */
-void swap_shmem_alloc(swp_entry_t entry, int nr)
-{
- __swap_duplicate(entry, SWAP_MAP_SHMEM, nr);
-}
-
-/*
- * Increase reference count of swap entry by 1.
+/**
+ * swap_duplicate_nr() - Increase reference count of nr contiguous swap entries
+ * by 1.
+ *
+ * @entry: first swap entry from which we want to increase the refcount.
+ * @nr: Number of entries in range.
+ *
* Returns 0 for success, or -ENOMEM if a swap_count_continuation is required
* but could not be atomically allocated. Returns 0, just as if it succeeded,
* if __swap_duplicate() fails for another reason (-EINVAL or -ENOENT), which
* might occur if a page table entry has got corrupted.
+ *
+ * Note that we are currently not handling the case where nr > 1 and we need to
+ * add swap count continuation. This is OK, because no such user exists - shmem
+ * is the only user that can pass nr > 1, and it never re-duplicates any swap
+ * entry it owns.
*/
-int swap_duplicate(swp_entry_t entry)
+int swap_duplicate_nr(swp_entry_t entry, int nr)
{
int err = 0;
- while (!err && __swap_duplicate(entry, 1, 1) == -ENOMEM)
+ while (!err && __swap_duplicate(entry, 1, nr) == -ENOMEM)
err = add_swap_count_continuation(entry, GFP_ATOMIC);
return err;
}
--
2.51.2
Powered by blists - more mailing lists