1 files changed, 87 insertions, 112 deletions

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index aa25fa335d3e..7823168c08a6 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -403,6 +403,7 @@ void btrfs_free_device(struct btrfs_device *device)
 static void free_fs_devices(struct btrfs_fs_devices *fs_devices)
 {
 	struct btrfs_device *device;
+
 	WARN_ON(fs_devices->opened);
 	while (!list_empty(&fs_devices->devices)) {
 		device = list_entry(fs_devices->devices.next,
@@ -727,7 +728,7 @@ static struct btrfs_fs_devices *find_fsid_reverted_metadata(
 	/*
 	 * Handle the case where the scanned device is part of an fs whose last
 	 * metadata UUID change reverted it to the original FSID. At the same
-	 * time * fs_devices was first created by another constitutent device
+	 * time fs_devices was first created by another constituent device
 	 * which didn't fully observe the operation. This results in an
 	 * btrfs_fs_devices created with metadata/fsid different AND
 	 * btrfs_fs_devices::fsid_change set AND the metadata_uuid of the
@@ -768,8 +769,11 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 					BTRFS_SUPER_FLAG_CHANGING_FSID_V2);
 
 	error = lookup_bdev(path, &path_devt);
-	if (error)
+	if (error) {
+		btrfs_err(NULL, "failed to lookup block device for path %s: %d",
+			  path, error);
 		return ERR_PTR(error);
+	}
 
 	if (fsid_change_in_progress) {
 		if (!has_metadata_uuid)
@@ -836,6 +840,9 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 		unsigned int nofs_flag;
 
 		if (fs_devices->opened) {
+			btrfs_err(NULL,
+		"device %s belongs to fsid %pU, and the fs is already mounted",
+				  path, fs_devices->fsid);
 			mutex_unlock(&fs_devices->device_list_mutex);
 			return ERR_PTR(-EBUSY);
 		}
@@ -905,6 +912,9 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 			 * generation are equal.
 			 */
 			mutex_unlock(&fs_devices->device_list_mutex);
+			btrfs_err(NULL,
+"device %s already registered with a higher generation, found %llu expect %llu",
+				  path, found_transid, device->generation);
 			return ERR_PTR(-EEXIST);
 		}
 
@@ -1172,9 +1182,22 @@ void btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
 
 	mutex_lock(&uuid_mutex);
 	close_fs_devices(fs_devices);
-	if (!fs_devices->opened)
+	if (!fs_devices->opened) {
 		list_splice_init(&fs_devices->seed_list, &list);
 
+		/*
+		 * If the struct btrfs_fs_devices is not assembled with any
+		 * other device, it can be re-initialized during the next mount
+		 * without the needing device-scan step. Therefore, it can be
+		 * fully freed.
+		 */
+		if (fs_devices->num_devices == 1) {
+			list_del(&fs_devices->fs_list);
+			free_fs_devices(fs_devices);
+		}
+	}
+
+
 	list_for_each_entry_safe(fs_devices, tmp, &list, seed_list) {
 		close_fs_devices(fs_devices);
 		list_del(&fs_devices->seed_list);
@@ -1591,7 +1614,7 @@ again:
 	if (ret < 0)
 		goto out;
 
-	while (1) {
+	while (search_start < search_end) {
 		l = path->nodes[0];
 		slot = path->slots[0];
 		if (slot >= btrfs_header_nritems(l)) {
@@ -1614,6 +1637,9 @@ again:
 		if (key.type != BTRFS_DEV_EXTENT_KEY)
 			goto next;
 
+		if (key.offset > search_end)
+			break;
+
 		if (key.offset > search_start) {
 			hole_size = key.offset - search_start;
 			dev_extent_hole_check(device, &search_start, &hole_size,
@@ -1674,6 +1700,7 @@ next:
 	else
 		ret = 0;
 
+	ASSERT(max_hole_start + max_hole_size <= search_end);
 out:
 	btrfs_free_path(path);
 	*start = max_hole_start;
@@ -2005,42 +2032,42 @@ static u64 btrfs_num_devices(struct btrfs_fs_info *fs_info)
 	return num_devices;
 }
 
+static void btrfs_scratch_superblock(struct btrfs_fs_info *fs_info,
+				     struct block_device *bdev, int copy_num)
+{
+	struct btrfs_super_block *disk_super;
+	const size_t len = sizeof(disk_super->magic);
+	const u64 bytenr = btrfs_sb_offset(copy_num);
+	int ret;
+
+	disk_super = btrfs_read_disk_super(bdev, bytenr, bytenr);
+	if (IS_ERR(disk_super))
+		return;
+
+	memset(&disk_super->magic, 0, len);
+	folio_mark_dirty(virt_to_folio(disk_super));
+	btrfs_release_disk_super(disk_super);
+
+	ret = sync_blockdev_range(bdev, bytenr, bytenr + len - 1);
+	if (ret)
+		btrfs_warn(fs_info, "error clearing superblock number %d (%d)",
+			copy_num, ret);
+}
+
 void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info,
 			       struct block_device *bdev,
 			       const char *device_path)
 {
-	struct btrfs_super_block *disk_super;
 	int copy_num;
 
 	if (!bdev)
 		return;
 
 	for (copy_num = 0; copy_num < BTRFS_SUPER_MIRROR_MAX; copy_num++) {
-		struct page *page;
-		int ret;
-
-		disk_super = btrfs_read_dev_one_super(bdev, copy_num, false);
-		if (IS_ERR(disk_super))
-			continue;
-
-		if (bdev_is_zoned(bdev)) {
+		if (bdev_is_zoned(bdev))
 			btrfs_reset_sb_log_zones(bdev, copy_num);
-			continue;
-		}
-
-		memset(&disk_super->magic, 0, sizeof(disk_super->magic));
-
-		page = virt_to_page(disk_super);
-		set_page_dirty(page);
-		lock_page(page);
-		/* write_on_page() unlocks the page */
-		ret = write_one_page(page);
-		if (ret)
-			btrfs_warn(fs_info,
-				"error clearing superblock number %d (%d)",
-				copy_num, ret);
-		btrfs_release_disk_super(disk_super);
-
+		else
+			btrfs_scratch_superblock(fs_info, bdev, copy_num);
 	}
 
 	/* Notify udev that device has changed */
@@ -6257,91 +6284,42 @@ static bool need_full_stripe(enum btrfs_map_op op)
 	return (op == BTRFS_MAP_WRITE || op == BTRFS_MAP_GET_READ_MIRRORS);
 }
 
-/*
- * Calculate the geometry of a particular (address, len) tuple. This
- * information is used to calculate how big a particular bio can get before it
- * straddles a stripe.
- *
- * @fs_info: the filesystem
- * @em:      mapping containing the logical extent
- * @op:      type of operation - write or read
- * @logical: address that we want to figure out the geometry of
- * @io_geom: pointer used to return values
- *
- * Returns < 0 in case a chunk for the given logical address cannot be found,
- * usually shouldn't happen unless @logical is corrupted, 0 otherwise.
- */
-int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, struct extent_map *em,
-			  enum btrfs_map_op op, u64 logical,
-			  struct btrfs_io_geometry *io_geom)
+static u64 btrfs_max_io_len(struct map_lookup *map, enum btrfs_map_op op,
+			    u64 offset, u64 *stripe_nr, u64 *stripe_offset,
+			    u64 *full_stripe_start)
 {
-	struct map_lookup *map;
-	u64 len;
-	u64 offset;
-	u64 stripe_offset;
-	u64 stripe_nr;
-	u32 stripe_len;
-	u64 raid56_full_stripe_start = (u64)-1;
-	int data_stripes;
+	u32 stripe_len = map->stripe_len;
 
 	ASSERT(op != BTRFS_MAP_DISCARD);
 
-	map = em->map_lookup;
-	/* Offset of this logical address in the chunk */
-	offset = logical - em->start;
-	/* Len of a stripe in a chunk */
-	stripe_len = map->stripe_len;
 	/*
-	 * Stripe_nr is where this block falls in
-	 * stripe_offset is the offset of this block in its stripe.
+	 * Stripe_nr is the stripe where this block falls.  stripe_offset is
+	 * the offset of this block in its stripe.
 	 */
-	stripe_nr = div64_u64_rem(offset, stripe_len, &stripe_offset);
-	ASSERT(stripe_offset < U32_MAX);
+	*stripe_nr = div64_u64_rem(offset, stripe_len, stripe_offset);
+	ASSERT(*stripe_offset < U32_MAX);
 
-	data_stripes = nr_data_stripes(map);
+	if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
+		unsigned long full_stripe_len = stripe_len * nr_data_stripes(map);
 
-	/* Only stripe based profiles needs to check against stripe length. */
-	if (map->type & BTRFS_BLOCK_GROUP_STRIPE_MASK) {
-		u64 max_len = stripe_len - stripe_offset;
+		*full_stripe_start =
+			div64_u64(offset, full_stripe_len) * full_stripe_len;
 
 		/*
-		 * In case of raid56, we need to know the stripe aligned start
+		 * For writes to RAID56, allow to write a full stripe set, but
+		 * no straddling of stripe sets.
 		 */
-		if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
-			unsigned long full_stripe_len = stripe_len * data_stripes;
-			raid56_full_stripe_start = offset;
-
-			/*
-			 * Allow a write of a full stripe, but make sure we
-			 * don't allow straddling of stripes
-			 */
-			raid56_full_stripe_start = div64_u64(raid56_full_stripe_start,
-					full_stripe_len);
-			raid56_full_stripe_start *= full_stripe_len;
-
-			/*
-			 * For writes to RAID[56], allow a full stripeset across
-			 * all disks. For other RAID types and for RAID[56]
-			 * reads, just allow a single stripe (on a single disk).
-			 */
-			if (op == BTRFS_MAP_WRITE) {
-				max_len = stripe_len * data_stripes -
-					  (offset - raid56_full_stripe_start);
-			}
-		}
-		len = min_t(u64, em->len - offset, max_len);
-	} else {
-		len = em->len - offset;
+		if (op == BTRFS_MAP_WRITE)
+			return full_stripe_len - (offset - *full_stripe_start);
 	}
 
-	io_geom->len = len;
-	io_geom->offset = offset;
-	io_geom->stripe_len = stripe_len;
-	io_geom->stripe_nr = stripe_nr;
-	io_geom->stripe_offset = stripe_offset;
-	io_geom->raid56_stripe_offset = raid56_full_stripe_start;
-
-	return 0;
+	/*
+	 * For other RAID types and for RAID56 reads, allow a single stripe (on
+	 * a single disk).
+	 */
+	if (map->type & BTRFS_BLOCK_GROUP_STRIPE_MASK)
+		return stripe_len - *stripe_offset;
+	return U64_MAX;
 }
 
 static void set_io_stripe(struct btrfs_io_stripe *dst, const struct map_lookup *map,
@@ -6360,6 +6338,7 @@ int __btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 {
 	struct extent_map *em;
 	struct map_lookup *map;
+	u64 map_offset;
 	u64 stripe_offset;
 	u64 stripe_nr;
 	u64 stripe_len;
@@ -6378,7 +6357,7 @@ int __btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 	int patch_the_first_stripe_for_dev_replace = 0;
 	u64 physical_to_patch_in_first_stripe = 0;
 	u64 raid56_full_stripe_start = (u64)-1;
-	struct btrfs_io_geometry geom;
+	u64 max_len;
 
 	ASSERT(bioc_ret);
 	ASSERT(op != BTRFS_MAP_DISCARD);
@@ -6386,18 +6365,14 @@ int __btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 	em = btrfs_get_chunk_map(fs_info, logical, *length);
 	ASSERT(!IS_ERR(em));
 
-	ret = btrfs_get_io_geometry(fs_info, em, op, logical, &geom);
-	if (ret < 0)
-		return ret;
-
 	map = em->map_lookup;
-
-	*length = geom.len;
-	stripe_len = geom.stripe_len;
-	stripe_nr = geom.stripe_nr;
-	stripe_offset = geom.stripe_offset;
-	raid56_full_stripe_start = geom.raid56_stripe_offset;
 	data_stripes = nr_data_stripes(map);
+	stripe_len = map->stripe_len;
+
+	map_offset = logical - em->start;
+	max_len = btrfs_max_io_len(map, op, map_offset, &stripe_nr,
+				   &stripe_offset, &raid56_full_stripe_start);
+	*length = min_t(u64, em->len - map_offset, max_len);
 
 	down_read(&dev_replace->rwsem);
 	dev_replace_is_ongoing = btrfs_dev_replace_is_ongoing(dev_replace);