mm/shmem, swap: remove SWAP_MAP_SHMEM

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).

Link: https://lkml.kernel.org/r/20251220-swap-table-p2-v5-8-8862a265a033@tencent.com
Signed-off-by: Kairui Song <kasong@tencent.com>
Signed-off-by: Nhat Pham <nphamcs@gmail.com>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Tested-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Chris Li <chrisl@kernel.org>
Cc: Rafael J. Wysocki (Intel) <rafael@kernel.org>
Cc: Yosry Ahmed <yosry.ahmed@linux.dev>
Cc: Deepanshu Kartikey <kartikey406@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kairui Song <ryncsn@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 38ca3df68716042946274c18a3a6695dda3b7b65..bf72b548a96d342787537ffd18e192f8dd77c857 100644 (file)
--- 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 c60392d054e26e037e179adbd88a4473a49fe28d..dd4951d6f891f30641f53205a3e15fe7b73cd105 100644 (file)
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1690,7 +1690,7 @@ try_split:
                        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 ea02d97951261eb38adfa1f22b586120f47333f7..eb394f30181a525f15a1f97f0d8687fb0415085c 100644 (file)
--- 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) {
@@ -1523,12 +1523,6 @@ 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))
@@ -1626,7 +1620,7 @@ 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);
@@ -1680,12 +1674,10 @@ 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 @@ unlock_out:
        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;
 }