[PATCH RFC v4 1/2] mm: swap: introduce swapcache_prepare_nr and swapcache_clear_nr for large folios swap-in

[Barry Song <21cnbao@gmail.com>]

From: Barry Song <v-songbaohua@oppo.com>

Commit 13ddaf26be32 ("mm/swap: fix race when skipping swapcache") supports
one entry only, to support large folio swap-in, we need to handle multiple
swap entries.

Signed-off-by: Barry Song <v-songbaohua@oppo.com>
---
 include/linux/swap.h |   4 +-
 mm/swap.h            |   4 +-
 mm/swapfile.c        | 114 +++++++++++++++++++++++++------------------
 3 files changed, 70 insertions(+), 52 deletions(-)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index e473fe6cfb7a..c0f4f2073ca6 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -481,7 +481,7 @@ extern int get_swap_pages(int n, swp_entry_t swp_entries[], int order);
 extern int add_swap_count_continuation(swp_entry_t, gfp_t);
 extern void swap_shmem_alloc(swp_entry_t);
 extern int swap_duplicate(swp_entry_t);
-extern int swapcache_prepare(swp_entry_t);
+extern int swapcache_prepare_nr(swp_entry_t entry, int nr);
 extern void swap_free_nr(swp_entry_t entry, int nr_pages);
 extern void swapcache_free_entries(swp_entry_t *entries, int n);
 extern void free_swap_and_cache_nr(swp_entry_t entry, int nr);
@@ -555,7 +555,7 @@ static inline int swap_duplicate(swp_entry_t swp)
 	return 0;
 }
 
-static inline int swapcache_prepare(swp_entry_t swp)
+static inline int swapcache_prepare_nr(swp_entry_t swp, int nr)
 {
 	return 0;
 }
diff --git a/mm/swap.h b/mm/swap.h
index baa1fa946b34..b96b1157441f 100644
--- a/mm/swap.h
+++ b/mm/swap.h
@@ -59,7 +59,7 @@ void __delete_from_swap_cache(struct folio *folio,
 void delete_from_swap_cache(struct folio *folio);
 void clear_shadow_from_swap_cache(int type, unsigned long begin,
 				  unsigned long end);
-void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry);
+void swapcache_clear_nr(struct swap_info_struct *si, swp_entry_t entry, int nr);
 struct folio *swap_cache_get_folio(swp_entry_t entry,
 		struct vm_area_struct *vma, unsigned long addr);
 struct folio *filemap_get_incore_folio(struct address_space *mapping,
@@ -120,7 +120,7 @@ static inline int swap_writepage(struct page *p, struct writeback_control *wbc)
 	return 0;
 }
 
-static inline void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry)
+static inline void swapcache_clear_nr(struct swap_info_struct *si, swp_entry_t entry, int nr)
 {
 }
 
diff --git a/mm/swapfile.c b/mm/swapfile.c
index f7224bc1320c..8f60dd10fdef 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1352,7 +1352,8 @@ static void swap_entry_free(struct swap_info_struct *p, swp_entry_t entry)
 }
 
 static void cluster_swap_free_nr(struct swap_info_struct *sis,
-		unsigned long offset, int nr_pages)
+		unsigned long offset, int nr_pages,
+		unsigned char usage)
 {
 	struct swap_cluster_info *ci;
 	DECLARE_BITMAP(to_free, BITS_PER_LONG) = { 0 };
@@ -1362,7 +1363,7 @@ static void cluster_swap_free_nr(struct swap_info_struct *sis,
 	while (nr_pages) {
 		nr = min(BITS_PER_LONG, nr_pages);
 		for (i = 0; i < nr; i++) {
-			if (!__swap_entry_free_locked(sis, offset + i, 1))
+			if (!__swap_entry_free_locked(sis, offset + i, usage))
 				bitmap_set(to_free, i, 1);
 		}
 		if (!bitmap_empty(to_free, BITS_PER_LONG)) {
@@ -1396,7 +1397,7 @@ void swap_free_nr(swp_entry_t entry, int nr_pages)
 
 	while (nr_pages) {
 		nr = min_t(int, nr_pages, SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER);
-		cluster_swap_free_nr(sis, offset, nr);
+		cluster_swap_free_nr(sis, offset, nr, 1);
 		offset += nr;
 		nr_pages -= nr;
 	}
@@ -3382,7 +3383,7 @@ void si_swapinfo(struct sysinfo *val)
 }
 
 /*
- * Verify that a swap entry is valid and increment its swap map count.
+ * Verify that nr swap entries are valid and increment their swap map counts.
  *
  * Returns error code in following case.
  * - success -> 0
@@ -3392,66 +3393,88 @@ void si_swapinfo(struct sysinfo *val)
  * - swap-cache reference is requested but the entry is not used. -> ENOENT
  * - swap-mapped reference requested but needs continued swap count. -> ENOMEM
  */
-static int __swap_duplicate(swp_entry_t entry, unsigned char usage)
+static int __swap_duplicate_nr(swp_entry_t entry, unsigned char usage, int nr)
 {
 	struct swap_info_struct *p;
 	struct swap_cluster_info *ci;
 	unsigned long offset;
 	unsigned char count;
 	unsigned char has_cache;
-	int err;
+	int err, i;
 
 	p = swp_swap_info(entry);
 
 	offset = swp_offset(entry);
+	VM_WARN_ON(nr > SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER);
 	ci = lock_cluster_or_swap_info(p, offset);
 
-	count = p->swap_map[offset];
+	err = 0;
+	for (i = 0; i < nr; i++) {
+		count = p->swap_map[offset + i];
 
-	/*
-	 * swapin_readahead() doesn't check if a swap entry is valid, so the
-	 * swap entry could be SWAP_MAP_BAD. Check here with lock held.
-	 */
-	if (unlikely(swap_count(count) == SWAP_MAP_BAD)) {
-		err = -ENOENT;
-		goto unlock_out;
-	}
+		/*
+		 * swapin_readahead() doesn't check if a swap entry is valid, so the
+		 * swap entry could be SWAP_MAP_BAD. Check here with lock held.
+		 */
+		if (unlikely(swap_count(count) == SWAP_MAP_BAD)) {
+			err = -ENOENT;
+			goto unlock_out;
+		}
 
-	has_cache = count & SWAP_HAS_CACHE;
-	count &= ~SWAP_HAS_CACHE;
-	err = 0;
+		has_cache = count & SWAP_HAS_CACHE;
+		count &= ~SWAP_HAS_CACHE;
 
-	if (usage == SWAP_HAS_CACHE) {
+		if (usage == SWAP_HAS_CACHE) {
+			/* set SWAP_HAS_CACHE if there is no cache and entry is used */
+			if (!has_cache && count)
+				continue;
+			else if (has_cache)		/* someone else added cache */
+				err = -EEXIST;
+			else				/* no users remaining */
+				err = -ENOENT;
 
-		/* set SWAP_HAS_CACHE if there is no cache and entry is used */
-		if (!has_cache && count)
-			has_cache = SWAP_HAS_CACHE;
-		else if (has_cache)		/* someone else added cache */
-			err = -EEXIST;
-		else				/* no users remaining */
-			err = -ENOENT;
+		} else if (count || has_cache) {
 
-	} else if (count || has_cache) {
+			if ((count & ~COUNT_CONTINUED) < SWAP_MAP_MAX)
+				continue;
+			else if ((count & ~COUNT_CONTINUED) > SWAP_MAP_MAX)
+				err = -EINVAL;
+			else if (swap_count_continued(p, offset + i, count))
+				continue;
+			else
+				err = -ENOMEM;
+		} else
+			err = -ENOENT;			/* unused swap entry */
 
-		if ((count & ~COUNT_CONTINUED) < SWAP_MAP_MAX)
+		if (err)
+			goto unlock_out;
+	}
+
+	for (i = 0; i < nr; i++) {
+		count = p->swap_map[offset + i];
+		has_cache = count & SWAP_HAS_CACHE;
+		count &= ~SWAP_HAS_CACHE;
+
+		if (usage == SWAP_HAS_CACHE)
+			has_cache = SWAP_HAS_CACHE;
+		else if ((count & ~COUNT_CONTINUED) < SWAP_MAP_MAX)
 			count += usage;
-		else if ((count & ~COUNT_CONTINUED) > SWAP_MAP_MAX)
-			err = -EINVAL;
-		else if (swap_count_continued(p, offset, count))
-			count = COUNT_CONTINUED;
 		else
-			err = -ENOMEM;
-	} else
-		err = -ENOENT;			/* unused swap entry */
+			count = COUNT_CONTINUED;
 
-	if (!err)
-		WRITE_ONCE(p->swap_map[offset], count | has_cache);
+		WRITE_ONCE(p->swap_map[offset + i], count | has_cache);
+	}
 
 unlock_out:
 	unlock_cluster_or_swap_info(p, ci);
 	return err;
 }
 
+static int __swap_duplicate(swp_entry_t entry, unsigned char usage)
+{
+	return __swap_duplicate_nr(entry, usage, 1);
+}
+
 /*
  * Help swapoff by noting that swap entry belongs to shmem/tmpfs
  * (in which case its reference count is never incremented).
@@ -3485,22 +3508,17 @@ int swap_duplicate(swp_entry_t entry)
  * -EEXIST means there is a swap cache.
  * Note: return code is different from swap_duplicate().
  */
-int swapcache_prepare(swp_entry_t entry)
+int swapcache_prepare_nr(swp_entry_t entry, int nr)
 {
-	return __swap_duplicate(entry, SWAP_HAS_CACHE);
+	return __swap_duplicate_nr(entry, SWAP_HAS_CACHE, nr);
 }
 
-void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry)
+void swapcache_clear_nr(struct swap_info_struct *si, swp_entry_t entry, int nr)
 {
-	struct swap_cluster_info *ci;
-	unsigned long offset = swp_offset(entry);
-	unsigned char usage;
+	pgoff_t offset = swp_offset(entry);
 
-	ci = lock_cluster_or_swap_info(si, offset);
-	usage = __swap_entry_free_locked(si, offset, SWAP_HAS_CACHE);
-	unlock_cluster_or_swap_info(si, ci);
-	if (!usage)
-		free_swap_slot(entry);
+	VM_WARN_ON(nr > SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER);
+	cluster_swap_free_nr(si, offset, nr, SWAP_HAS_CACHE);
 }
 
 struct swap_info_struct *swp_swap_info(swp_entry_t entry)
-- 
2.34.1