Merge tag 'for-6.5-rc6-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:

 - fix infinite loop in readdir(), could happen in a big directory when
   files get renamed during enumeration

 - fix extent map handling of skipped pinned ranges

 - fix a corner case when handling ordered extent length

 - fix a potential crash when balance cancel races with pause

 - verify correct uuid when starting scrub or device replace

* tag 'for-6.5-rc6-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: fix incorrect splitting in btrfs_drop_extent_map_range
  btrfs: fix BUG_ON condition in btrfs_cancel_balance
  btrfs: only subtract from len_to_oe_boundary when it is tracking an extent
  btrfs: fix replace/scrub failure with metadata_uuid
  btrfs: fix infinite directory reads

8 files changed, 113 insertions, 62 deletions

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index f2d2b313bde5..9419f4e37a58 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -443,6 +443,7 @@ struct btrfs_drop_extents_args {
 
 struct btrfs_file_private {
 	void *filldir_buf;
+	u64 last_index;
 	struct extent_state *llseek_cached_state;
 };
 
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 6b457b010cbc..6d51db066503 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1632,6 +1632,7 @@ int btrfs_inode_delayed_dir_index_count(struct btrfs_inode *inode)
 }
 
 bool btrfs_readdir_get_delayed_items(struct inode *inode,
+				     u64 last_index,
 				     struct list_head *ins_list,
 				     struct list_head *del_list)
 {
@@ -1651,14 +1652,14 @@ bool btrfs_readdir_get_delayed_items(struct inode *inode,
 
 	mutex_lock(&delayed_node->mutex);
 	item = __btrfs_first_delayed_insertion_item(delayed_node);
-	while (item) {
+	while (item && item->index <= last_index) {
 		refcount_inc(&item->refs);
 		list_add_tail(&item->readdir_list, ins_list);
 		item = __btrfs_next_delayed_item(item);
 	}
 
 	item = __btrfs_first_delayed_deletion_item(delayed_node);
-	while (item) {
+	while (item && item->index <= last_index) {
 		refcount_inc(&item->refs);
 		list_add_tail(&item->readdir_list, del_list);
 		item = __btrfs_next_delayed_item(item);
diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h
index 4f21daa3dbc7..dc1085b2a397 100644
--- a/fs/btrfs/delayed-inode.h
+++ b/fs/btrfs/delayed-inode.h
@@ -148,6 +148,7 @@ void btrfs_destroy_delayed_inodes(struct btrfs_fs_info *fs_info);
 
 /* Used for readdir() */
 bool btrfs_readdir_get_delayed_items(struct inode *inode,
+				     u64 last_index,
 				     struct list_head *ins_list,
 				     struct list_head *del_list);
 void btrfs_readdir_put_delayed_items(struct inode *inode,
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index ca765d62324f..90ad3006ef3a 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -902,7 +902,30 @@ static void submit_extent_page(struct btrfs_bio_ctrl *bio_ctrl,
 		size -= len;
 		pg_offset += len;
 		disk_bytenr += len;
-		bio_ctrl->len_to_oe_boundary -= len;
+
+		/*
+		 * len_to_oe_boundary defaults to U32_MAX, which isn't page or
+		 * sector aligned.  alloc_new_bio() then sets it to the end of
+		 * our ordered extent for writes into zoned devices.
+		 *
+		 * When len_to_oe_boundary is tracking an ordered extent, we
+		 * trust the ordered extent code to align things properly, and
+		 * the check above to cap our write to the ordered extent
+		 * boundary is correct.
+		 *
+		 * When len_to_oe_boundary is U32_MAX, the cap above would
+		 * result in a 4095 byte IO for the last page right before
+		 * we hit the bio limit of UINT_MAX.  bio_add_page() has all
+		 * the checks required to make sure we don't overflow the bio,
+		 * and we should just ignore len_to_oe_boundary completely
+		 * unless we're using it to track an ordered extent.
+		 *
+		 * It's pretty hard to make a bio sized U32_MAX, but it can
+		 * happen when the page cache is able to feed us contiguous
+		 * pages for large extents.
+		 */
+		if (bio_ctrl->len_to_oe_boundary != U32_MAX)
+			bio_ctrl->len_to_oe_boundary -= len;
 
 		/* Ordered extent boundary: move on to a new bio. */
 		if (bio_ctrl->len_to_oe_boundary == 0)
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 0cdb3e86f29b..a6d8368ed0ed 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -760,8 +760,6 @@ void btrfs_drop_extent_map_range(struct btrfs_inode *inode, u64 start, u64 end,
 
 		if (skip_pinned && test_bit(EXTENT_FLAG_PINNED, &em->flags)) {
 			start = em_end;
-			if (end != (u64)-1)
-				len = start + len - em_end;
 			goto next;
 		}
 
@@ -829,8 +827,8 @@ void btrfs_drop_extent_map_range(struct btrfs_inode *inode, u64 start, u64 end,
 				if (!split)
 					goto remove_em;
 			}
-			split->start = start + len;
-			split->len = em_end - (start + len);
+			split->start = end;
+			split->len = em_end - end;
 			split->block_start = em->block_start;
 			split->flags = flags;
 			split->compress_type = em->compress_type;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 9055e19b01ef..aa090b0b5d29 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -5873,6 +5873,74 @@ static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry,
 }
 
 /*
+ * Find the highest existing sequence number in a directory and then set the
+ * in-memory index_cnt variable to the first free sequence number.
+ */
+static int btrfs_set_inode_index_count(struct btrfs_inode *inode)
+{
+	struct btrfs_root *root = inode->root;
+	struct btrfs_key key, found_key;
+	struct btrfs_path *path;
+	struct extent_buffer *leaf;
+	int ret;
+
+	key.objectid = btrfs_ino(inode);
+	key.type = BTRFS_DIR_INDEX_KEY;
+	key.offset = (u64)-1;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+	if (ret < 0)
+		goto out;
+	/* FIXME: we should be able to handle this */
+	if (ret == 0)
+		goto out;
+	ret = 0;
+
+	if (path->slots[0] == 0) {
+		inode->index_cnt = BTRFS_DIR_START_INDEX;
+		goto out;
+	}
+
+	path->slots[0]--;
+
+	leaf = path->nodes[0];
+	btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
+
+	if (found_key.objectid != btrfs_ino(inode) ||
+	    found_key.type != BTRFS_DIR_INDEX_KEY) {
+		inode->index_cnt = BTRFS_DIR_START_INDEX;
+		goto out;
+	}
+
+	inode->index_cnt = found_key.offset + 1;
+out:
+	btrfs_free_path(path);
+	return ret;
+}
+
+static int btrfs_get_dir_last_index(struct btrfs_inode *dir, u64 *index)
+{
+	if (dir->index_cnt == (u64)-1) {
+		int ret;
+
+		ret = btrfs_inode_delayed_dir_index_count(dir);
+		if (ret) {
+			ret = btrfs_set_inode_index_count(dir);
+			if (ret)
+				return ret;
+		}
+	}
+
+	*index = dir->index_cnt;
+
+	return 0;
+}
+
+/*
  * All this infrastructure exists because dir_emit can fault, and we are holding
  * the tree lock when doing readdir.  For now just allocate a buffer and copy
  * our information into that, and then dir_emit from the buffer.  This is
@@ -5884,10 +5952,17 @@ static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry,
 static int btrfs_opendir(struct inode *inode, struct file *file)
 {
 	struct btrfs_file_private *private;
+	u64 last_index;
+	int ret;
+
+	ret = btrfs_get_dir_last_index(BTRFS_I(inode), &last_index);
+	if (ret)
+		return ret;
 
 	private = kzalloc(sizeof(struct btrfs_file_private), GFP_KERNEL);
 	if (!private)
 		return -ENOMEM;
+	private->last_index = last_index;
 	private->filldir_buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
 	if (!private->filldir_buf) {
 		kfree(private);
@@ -5954,7 +6029,8 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 
 	INIT_LIST_HEAD(&ins_list);
 	INIT_LIST_HEAD(&del_list);
-	put = btrfs_readdir_get_delayed_items(inode, &ins_list, &del_list);
+	put = btrfs_readdir_get_delayed_items(inode, private->last_index,
+					      &ins_list, &del_list);
 
 again:
 	key.type = BTRFS_DIR_INDEX_KEY;
@@ -5972,6 +6048,8 @@ again:
 			break;
 		if (found_key.offset < ctx->pos)
 			continue;
+		if (found_key.offset > private->last_index)
+			break;
 		if (btrfs_should_delete_dir_index(&del_list, found_key.offset))
 			continue;
 		di = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dir_item);
@@ -6108,57 +6186,6 @@ static int btrfs_update_time(struct inode *inode, struct timespec64 *now,
 }
 
 /*
- * find the highest existing sequence number in a directory
- * and then set the in-memory index_cnt variable to reflect
- * free sequence numbers
- */
-static int btrfs_set_inode_index_count(struct btrfs_inode *inode)
-{
-	struct btrfs_root *root = inode->root;
-	struct btrfs_key key, found_key;
-	struct btrfs_path *path;
-	struct extent_buffer *leaf;
-	int ret;
-
-	key.objectid = btrfs_ino(inode);
-	key.type = BTRFS_DIR_INDEX_KEY;
-	key.offset = (u64)-1;
-
-	path = btrfs_alloc_path();
-	if (!path)
-		return -ENOMEM;
-
-	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
-	if (ret < 0)
-		goto out;
-	/* FIXME: we should be able to handle this */
-	if (ret == 0)
-		goto out;
-	ret = 0;
-
-	if (path->slots[0] == 0) {
-		inode->index_cnt = BTRFS_DIR_START_INDEX;
-		goto out;
-	}
-
-	path->slots[0]--;
-
-	leaf = path->nodes[0];
-	btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
-
-	if (found_key.objectid != btrfs_ino(inode) ||
-	    found_key.type != BTRFS_DIR_INDEX_KEY) {
-		inode->index_cnt = BTRFS_DIR_START_INDEX;
-		goto out;
-	}
-
-	inode->index_cnt = found_key.offset + 1;
-out:
-	btrfs_free_path(path);
-	return ret;
-}
-
-/*
  * helper to find a free sequence number in a given directory.  This current
  * code is very simple, later versions will do smarter things in the btree
  */
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 4cae41bd6de0..7289f5bff397 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -605,7 +605,8 @@ static void scrub_verify_one_metadata(struct scrub_stripe *stripe, int sector_nr
 			      btrfs_stack_header_bytenr(header), logical);
 		return;
 	}
-	if (memcmp(header->fsid, fs_info->fs_devices->fsid, BTRFS_FSID_SIZE) != 0) {
+	if (memcmp(header->fsid, fs_info->fs_devices->metadata_uuid,
+		   BTRFS_FSID_SIZE) != 0) {
 		bitmap_set(&stripe->meta_error_bitmap, sector_nr, sectors_per_tree);
 		bitmap_set(&stripe->error_bitmap, sector_nr, sectors_per_tree);
 		btrfs_warn_rl(fs_info,
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 2ecb76cf3d91..6aa9bf3661ac 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -4638,8 +4638,7 @@ int btrfs_cancel_balance(struct btrfs_fs_info *fs_info)
 		}
 	}
 
-	BUG_ON(fs_info->balance_ctl ||
-		test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags));
+	ASSERT(!test_bit(BTRFS_FS_BALANCE_RUNNING, &fs_info->flags));
 	atomic_dec(&fs_info->balance_cancel_req);
 	mutex_unlock(&fs_info->balance_mutex);
 	return 0;