1 files changed, 149 insertions, 139 deletions

diff --git a/mm/swapfile.c b/mm/swapfile.c
index 2eff8b51a945..b4f3cc712580 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -52,9 +52,9 @@
 static bool swap_count_continued(struct swap_info_struct *, pgoff_t,
 				 unsigned char);
 static void free_swap_count_continuations(struct swap_info_struct *);
-static void swap_entry_range_free(struct swap_info_struct *si,
-				  struct swap_cluster_info *ci,
-				  swp_entry_t entry, unsigned int nr_pages);
+static void swap_entries_free(struct swap_info_struct *si,
+			      struct swap_cluster_info *ci,
+			      swp_entry_t entry, unsigned int nr_pages);
 static void swap_range_alloc(struct swap_info_struct *si,
 			     unsigned int nr_entries);
 static bool folio_swapcache_freeable(struct folio *folio);
@@ -192,7 +192,7 @@ 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)
+	if (swap_count(count) != 1 && swap_count(count) != SWAP_MAP_SHMEM)
 		return false;
 
 	while (++map < map_end) {
@@ -956,9 +956,8 @@ new_cluster:
 	}
 
 	/*
-	 * We don't have free cluster but have some clusters in
-	 * discarding, do discard now and reclaim them, then
-	 * reread cluster_next_cpu since we dropped si->lock
+	 * We don't have free cluster but have some clusters in discarding,
+	 * do discard now and reclaim them.
 	 */
 	if ((si->flags & SWP_PAGE_DISCARD) && swap_do_scheduled_discard(si))
 		goto new_cluster;
@@ -1115,6 +1114,7 @@ static void swap_range_alloc(struct swap_info_struct *si,
 		if (vm_swap_full())
 			schedule_work(&si->reclaim_work);
 	}
+	atomic_long_sub(nr_entries, &nr_swap_pages);
 }
 
 static void swap_range_free(struct swap_info_struct *si, unsigned long offset,
@@ -1272,13 +1272,22 @@ int folio_alloc_swap(struct folio *folio, gfp_t gfp)
 	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
 	VM_BUG_ON_FOLIO(!folio_test_uptodate(folio), folio);
 
-	/*
-	 * Should not even be attempting large allocations when huge
-	 * page swap is disabled. Warn and fail the allocation.
-	 */
-	if (order && (!IS_ENABLED(CONFIG_THP_SWAP) || size > SWAPFILE_CLUSTER)) {
-		VM_WARN_ON_ONCE(1);
-		return -EINVAL;
+	if (order) {
+		/*
+		 * Reject large allocation when THP_SWAP is disabled,
+		 * the caller should split the folio and try again.
+		 */
+		if (!IS_ENABLED(CONFIG_THP_SWAP))
+			return -EAGAIN;
+
+		/*
+		 * Allocation size should never exceed cluster size
+		 * (HPAGE_PMD_SIZE).
+		 */
+		if (size > SWAPFILE_CLUSTER) {
+			VM_WARN_ON_ONCE(1);
+			return -EINVAL;
+		}
 	}
 
 	local_lock(&percpu_swap_cluster.lock);
@@ -1304,7 +1313,6 @@ int folio_alloc_swap(struct folio *folio, gfp_t gfp)
 	if (add_to_swap_cache(folio, entry, gfp | __GFP_NOMEMALLOC, NULL))
 		goto out_free;
 
-	atomic_long_sub(size, &nr_swap_pages);
 	return 0;
 
 out_free:
@@ -1346,10 +1354,12 @@ out:
 	return NULL;
 }
 
-static unsigned char __swap_entry_free_locked(struct swap_info_struct *si,
-					      unsigned long offset,
-					      unsigned char usage)
+static unsigned char swap_entry_put_locked(struct swap_info_struct *si,
+					   struct swap_cluster_info *ci,
+					   swp_entry_t entry,
+					   unsigned char usage)
 {
+	unsigned long offset = swp_offset(entry);
 	unsigned char count;
 	unsigned char has_cache;
 
@@ -1381,7 +1391,7 @@ static unsigned char __swap_entry_free_locked(struct swap_info_struct *si,
 	if (usage)
 		WRITE_ONCE(si->swap_map[offset], usage);
 	else
-		WRITE_ONCE(si->swap_map[offset], SWAP_HAS_CACHE);
+		swap_entries_free(si, ci, entry, 1);
 
 	return usage;
 }
@@ -1452,71 +1462,104 @@ put_out:
 	return NULL;
 }
 
-static unsigned char __swap_entry_free(struct swap_info_struct *si,
-				       swp_entry_t entry)
+static void swap_entries_put_cache(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;
+	struct swap_cluster_info *ci;
 
 	ci = lock_cluster(si, offset);
-	usage = __swap_entry_free_locked(si, offset, 1);
-	if (!usage)
-		swap_entry_range_free(si, ci, swp_entry(si->type, offset), 1);
+	if (swap_only_has_cache(si, offset, nr))
+		swap_entries_free(si, ci, entry, nr);
+	else {
+		for (int i = 0; i < nr; i++, entry.val++)
+			swap_entry_put_locked(si, ci, entry, SWAP_HAS_CACHE);
+	}
 	unlock_cluster(ci);
-
-	return usage;
 }
 
-static bool __swap_entries_free(struct swap_info_struct *si,
-		swp_entry_t entry, int nr)
+static bool swap_entries_put_map(struct swap_info_struct *si,
+				 swp_entry_t entry, int nr)
 {
 	unsigned long offset = swp_offset(entry);
-	unsigned int type = swp_type(entry);
 	struct swap_cluster_info *ci;
 	bool has_cache = false;
 	unsigned char count;
 	int i;
 
-	if (nr <= 1 || swap_count(data_race(si->swap_map[offset])) != 1)
+	if (nr <= 1)
 		goto fallback;
-	/* cross into another cluster */
-	if (nr > SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER)
+	count = swap_count(data_race(si->swap_map[offset]));
+	if (count != 1 && count != SWAP_MAP_SHMEM)
 		goto fallback;
 
 	ci = lock_cluster(si, offset);
 	if (!swap_is_last_map(si, offset, nr, &has_cache)) {
-		unlock_cluster(ci);
-		goto fallback;
+		goto locked_fallback;
 	}
-	for (i = 0; i < nr; i++)
-		WRITE_ONCE(si->swap_map[offset + i], SWAP_HAS_CACHE);
 	if (!has_cache)
-		swap_entry_range_free(si, ci, entry, nr);
+		swap_entries_free(si, ci, entry, nr);
+	else
+		for (i = 0; i < nr; i++)
+			WRITE_ONCE(si->swap_map[offset + i], SWAP_HAS_CACHE);
 	unlock_cluster(ci);
 
 	return has_cache;
 
 fallback:
-	for (i = 0; i < nr; i++) {
-		if (data_race(si->swap_map[offset + i])) {
-			count = __swap_entry_free(si, swp_entry(type, offset + i));
-			if (count == SWAP_HAS_CACHE)
-				has_cache = true;
-		} else {
-			WARN_ON_ONCE(1);
-		}
+	ci = lock_cluster(si, offset);
+locked_fallback:
+	for (i = 0; i < nr; i++, entry.val++) {
+		count = swap_entry_put_locked(si, ci, entry, 1);
+		if (count == SWAP_HAS_CACHE)
+			has_cache = true;
 	}
+	unlock_cluster(ci);
 	return has_cache;
+
 }
 
 /*
- * Drop the last HAS_CACHE flag of swap entries, caller have to
- * ensure all entries belong to the same cgroup.
+ * Only functions with "_nr" suffix are able to free entries spanning
+ * cross multi clusters, so ensure the range is within a single cluster
+ * when freeing entries with functions without "_nr" suffix.
  */
-static void swap_entry_range_free(struct swap_info_struct *si,
-				  struct swap_cluster_info *ci,
-				  swp_entry_t entry, unsigned int nr_pages)
+static bool swap_entries_put_map_nr(struct swap_info_struct *si,
+				    swp_entry_t entry, int nr)
+{
+	int cluster_nr, cluster_rest;
+	unsigned long offset = swp_offset(entry);
+	bool has_cache = false;
+
+	cluster_rest = SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER;
+	while (nr) {
+		cluster_nr = min(nr, cluster_rest);
+		has_cache |= swap_entries_put_map(si, entry, cluster_nr);
+		cluster_rest = SWAPFILE_CLUSTER;
+		nr -= cluster_nr;
+		entry.val += cluster_nr;
+	}
+
+	return has_cache;
+}
+
+/*
+ * Check if it's the last ref of swap entry in the freeing path.
+ * Qualified vlaue 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);
+}
+
+/*
+ * Drop the last ref of swap entries, caller have to ensure all entries
+ * belong to the same cgroup and cluster.
+ */
+static void swap_entries_free(struct swap_info_struct *si,
+			      struct swap_cluster_info *ci,
+			      swp_entry_t entry, unsigned int nr_pages)
 {
 	unsigned long offset = swp_offset(entry);
 	unsigned char *map = si->swap_map + offset;
@@ -1529,7 +1572,7 @@ static void swap_entry_range_free(struct swap_info_struct *si,
 
 	ci->count -= nr_pages;
 	do {
-		VM_BUG_ON(*map != SWAP_HAS_CACHE);
+		VM_BUG_ON(!swap_is_last_ref(*map));
 		*map = 0;
 	} while (++map < map_end);
 
@@ -1542,21 +1585,6 @@ static void swap_entry_range_free(struct swap_info_struct *si,
 		partial_free_cluster(si, ci);
 }
 
-static void cluster_swap_free_nr(struct swap_info_struct *si,
-		unsigned long offset, int nr_pages,
-		unsigned char usage)
-{
-	struct swap_cluster_info *ci;
-	unsigned long end = offset + nr_pages;
-
-	ci = lock_cluster(si, offset);
-	do {
-		if (!__swap_entry_free_locked(si, offset, usage))
-			swap_entry_range_free(si, ci, swp_entry(si->type, offset), 1);
-	} while (++offset < end);
-	unlock_cluster(ci);
-}
-
 /*
  * Caller has made sure that the swap device corresponding to entry
  * is still around or has not been recycled.
@@ -1573,7 +1601,7 @@ 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, 1);
+		swap_entries_put_map(sis, swp_entry(sis->type, offset), nr);
 		offset += nr;
 		nr_pages -= nr;
 	}
@@ -1584,8 +1612,6 @@ void swap_free_nr(swp_entry_t entry, int nr_pages)
  */
 void put_swap_folio(struct folio *folio, swp_entry_t entry)
 {
-	unsigned long offset = swp_offset(entry);
-	struct swap_cluster_info *ci;
 	struct swap_info_struct *si;
 	int size = 1 << swap_entry_order(folio_order(folio));
 
@@ -1593,16 +1619,7 @@ void put_swap_folio(struct folio *folio, swp_entry_t entry)
 	if (!si)
 		return;
 
-	ci = lock_cluster(si, offset);
-	if (swap_only_has_cache(si, offset, size))
-		swap_entry_range_free(si, ci, entry, size);
-	else {
-		for (int i = 0; i < size; i++, entry.val++) {
-			if (!__swap_entry_free_locked(si, offset + i, SWAP_HAS_CACHE))
-				swap_entry_range_free(si, ci, entry, 1);
-		}
-	}
-	unlock_cluster(ci);
+	swap_entries_put_cache(si, entry, size);
 }
 
 int __swap_count(swp_entry_t entry)
@@ -1797,7 +1814,7 @@ void free_swap_and_cache_nr(swp_entry_t entry, int nr)
 	/*
 	 * First free all entries in the range.
 	 */
-	any_only_cache = __swap_entries_free(si, entry, nr);
+	any_only_cache = swap_entries_put_map_nr(si, entry, nr);
 
 	/*
 	 * Short-circuit the below loop if none of the entries had their
@@ -1807,13 +1824,7 @@ void free_swap_and_cache_nr(swp_entry_t entry, int nr)
 		goto out;
 
 	/*
-	 * Now go back over the range trying to reclaim the swap cache. This is
-	 * more efficient for large folios because we will only try to reclaim
-	 * the swap once per folio in the common case. If we do
-	 * __swap_entry_free() and __try_to_reclaim_swap() in the same loop, the
-	 * latter will get a reference and lock the folio for every individual
-	 * page but will only succeed once the swap slot for every subpage is
-	 * zero.
+	 * Now go back over the range trying to reclaim the swap cache.
 	 */
 	for (offset = start_offset; offset < end_offset; offset += nr) {
 		nr = 1;
@@ -2359,7 +2370,7 @@ retry:
 	 * Limit the number of retries? No: when mmget_not_zero()
 	 * above fails, that mm is likely to be freeing swap from
 	 * exit_mmap(), which proceeds at its own independent pace;
-	 * and even shmem_writepage() could have been preempted after
+	 * and even shmem_writeout() could have been preempted after
 	 * folio_alloc_swap(), temporarily hiding that swap.  It's easy
 	 * and robust (though cpu-intensive) just to keep retrying.
 	 */
@@ -3129,43 +3140,30 @@ static unsigned long read_swap_header(struct swap_info_struct *si,
 	return maxpages;
 }
 
-static int setup_swap_map_and_extents(struct swap_info_struct *si,
-					union swap_header *swap_header,
-					unsigned char *swap_map,
-					unsigned long maxpages,
-					sector_t *span)
+static int setup_swap_map(struct swap_info_struct *si,
+			  union swap_header *swap_header,
+			  unsigned char *swap_map,
+			  unsigned long maxpages)
 {
-	unsigned int nr_good_pages;
 	unsigned long i;
-	int nr_extents;
-
-	nr_good_pages = maxpages - 1;	/* omit header page */
 
+	swap_map[0] = SWAP_MAP_BAD; /* omit header page */
 	for (i = 0; i < swap_header->info.nr_badpages; i++) {
 		unsigned int page_nr = swap_header->info.badpages[i];
 		if (page_nr == 0 || page_nr > swap_header->info.last_page)
 			return -EINVAL;
 		if (page_nr < maxpages) {
 			swap_map[page_nr] = SWAP_MAP_BAD;
-			nr_good_pages--;
+			si->pages--;
 		}
 	}
 
-	if (nr_good_pages) {
-		swap_map[0] = SWAP_MAP_BAD;
-		si->max = maxpages;
-		si->pages = nr_good_pages;
-		nr_extents = setup_swap_extents(si, span);
-		if (nr_extents < 0)
-			return nr_extents;
-		nr_good_pages = si->pages;
-	}
-	if (!nr_good_pages) {
+	if (!si->pages) {
 		pr_warn("Empty swap-file\n");
 		return -EINVAL;
 	}
 
-	return nr_extents;
+	return 0;
 }
 
 #define SWAP_CLUSTER_INFO_COLS						\
@@ -3205,13 +3203,17 @@ static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si,
 	 * Mark unusable pages as unavailable. The clusters aren't
 	 * marked free yet, so no list operations are involved yet.
 	 *
-	 * See setup_swap_map_and_extents(): header page, bad pages,
+	 * See setup_swap_map(): header page, bad pages,
 	 * and the EOF part of the last cluster.
 	 */
 	inc_cluster_info_page(si, cluster_info, 0);
-	for (i = 0; i < swap_header->info.nr_badpages; i++)
-		inc_cluster_info_page(si, cluster_info,
-				      swap_header->info.badpages[i]);
+	for (i = 0; i < swap_header->info.nr_badpages; i++) {
+		unsigned int page_nr = swap_header->info.badpages[i];
+
+		if (page_nr >= maxpages)
+			continue;
+		inc_cluster_info_page(si, cluster_info, page_nr);
+	}
 	for (i = maxpages; i < round_up(maxpages, SWAPFILE_CLUSTER); i++)
 		inc_cluster_info_page(si, cluster_info, i);
 
@@ -3323,6 +3325,15 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	}
 
 	/*
+	 * The swap subsystem needs a major overhaul to support this.
+	 * It doesn't work yet so just disable it for now.
+	 */
+	if (mapping_min_folio_order(mapping) > 0) {
+		error = -EINVAL;
+		goto bad_swap_unlock_inode;
+	}
+
+	/*
 	 * Read the swap header.
 	 */
 	if (!mapping->a_ops->read_folio) {
@@ -3342,6 +3353,21 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 		goto bad_swap_unlock_inode;
 	}
 
+	si->max = maxpages;
+	si->pages = maxpages - 1;
+	nr_extents = setup_swap_extents(si, &span);
+	if (nr_extents < 0) {
+		error = nr_extents;
+		goto bad_swap_unlock_inode;
+	}
+	if (si->pages != si->max - 1) {
+		pr_err("swap:%u != (max:%u - 1)\n", si->pages, si->max);
+		error = -EINVAL;
+		goto bad_swap_unlock_inode;
+	}
+
+	maxpages = si->max;
+
 	/* OK, set up the swap map and apply the bad block list */
 	swap_map = vzalloc(maxpages);
 	if (!swap_map) {
@@ -3353,12 +3379,9 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	if (error)
 		goto bad_swap_unlock_inode;
 
-	nr_extents = setup_swap_map_and_extents(si, swap_header, swap_map,
-						maxpages, &span);
-	if (unlikely(nr_extents < 0)) {
-		error = nr_extents;
+	error = setup_swap_map(si, swap_header, swap_map, maxpages);
+	if (error)
 		goto bad_swap_unlock_inode;
-	}
 
 	/*
 	 * Use kvmalloc_array instead of bitmap_zalloc as the allocation order might
@@ -3636,11 +3659,13 @@ int swapcache_prepare(swp_entry_t entry, int nr)
 	return __swap_duplicate(entry, SWAP_HAS_CACHE, nr);
 }
 
+/*
+ * Caller should ensure entries belong to the same folio so
+ * the entries won't span cross cluster boundary.
+ */
 void swapcache_clear(struct swap_info_struct *si, swp_entry_t entry, int nr)
 {
-	unsigned long offset = swp_offset(entry);
-
-	cluster_swap_free_nr(si, offset, nr, SWAP_HAS_CACHE);
+	swap_entries_put_cache(si, entry, nr);
 }
 
 struct swap_info_struct *swp_swap_info(swp_entry_t entry)
@@ -3649,21 +3674,6 @@ struct swap_info_struct *swp_swap_info(swp_entry_t entry)
 }
 
 /*
- * out-of-line methods to avoid include hell.
- */
-struct address_space *swapcache_mapping(struct folio *folio)
-{
-	return swp_swap_info(folio->swap)->swap_file->f_mapping;
-}
-EXPORT_SYMBOL_GPL(swapcache_mapping);
-
-pgoff_t __folio_swap_cache_index(struct folio *folio)
-{
-	return swap_cache_index(folio->swap);
-}
-EXPORT_SYMBOL_GPL(__folio_swap_cache_index);
-
-/*
  * add_swap_count_continuation - called when a swap count is duplicated
  * beyond SWAP_MAP_MAX, it allocates a new page and links that to the entry's
  * page of the original vmalloc'ed swap_map, to hold the continuation count
@@ -3780,7 +3790,7 @@ outer:
  * into, carry if so, or else fail until a new continuation page is allocated;
  * when the original swap_map count is decremented from 0 with continuation,
  * borrow from the continuation and report whether it still holds more.
- * Called while __swap_duplicate() or caller of __swap_entry_free_locked()
+ * Called while __swap_duplicate() or caller of swap_entry_put_locked()
  * holds cluster lock.
  */
 static bool swap_count_continued(struct swap_info_struct *si,