Merge tag 'for-5.13-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:
 "First batch of various fixes, here's a list of notable ones:

   - fix unmountable seed device after fstrim

   - fix silent data loss in zoned mode due to ordered extent splitting

   - fix race leading to unpersisted data and metadata on fsync

   - fix deadlock when cloning inline extents and using qgroups"

* tag 'for-5.13-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: initialize return variable in cleanup_free_space_cache_v1
  btrfs: zoned: sanity check zone type
  btrfs: fix unmountable seed device after fstrim
  btrfs: fix deadlock when cloning inline extents and using qgroups
  btrfs: fix race leading to unpersisted data and metadata on fsync
  btrfs: do not consider send context as valid when trying to flush qgroups
  btrfs: zoned: fix silent data loss after failure splitting ordered extent

fs/btrfs/ctree.h

@@ -3127,7 +3127,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 			       struct btrfs_inode *inode, u64 new_size,
 			       u32 min_type);
 
-int btrfs_start_delalloc_snapshot(struct btrfs_root *root);
+int btrfs_start_delalloc_snapshot(struct btrfs_root *root, bool in_reclaim_context);
 int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, long nr,
 			       bool in_reclaim_context);
 int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end,

fs/btrfs/extent-tree.c

@@ -1340,12 +1340,16 @@ int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
 		stripe = bbio->stripes;
 		for (i = 0; i < bbio->num_stripes; i++, stripe++) {
 			u64 bytes;
+			struct btrfs_device *device = stripe->dev;
 
-			if (!stripe->dev->bdev) {
+			if (!device->bdev) {
 				ASSERT(btrfs_test_opt(fs_info, DEGRADED));
 				continue;
 			}
 
+			if (!test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state))
+				continue;
+
 			ret = do_discard_extent(stripe, &bytes);
 			if (!ret) {
 				discarded_bytes += bytes;

fs/btrfs/file.c

@@ -2067,6 +2067,30 @@ static int start_ordered_ops(struct inode *inode, loff_t start, loff_t end)
 	return ret;
 }
 
+static inline bool skip_inode_logging(const struct btrfs_log_ctx *ctx)
+{
+	struct btrfs_inode *inode = BTRFS_I(ctx->inode);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
+
+	if (btrfs_inode_in_log(inode, fs_info->generation) &&
+	    list_empty(&ctx->ordered_extents))
+		return true;
+
+	/*
+	 * If we are doing a fast fsync we can not bail out if the inode's
+	 * last_trans is <= then the last committed transaction, because we only
+	 * update the last_trans of the inode during ordered extent completion,
+	 * and for a fast fsync we don't wait for that, we only wait for the
+	 * writeback to complete.
+	 */
+	if (inode->last_trans <= fs_info->last_trans_committed &&
+	    (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags) ||
+	     list_empty(&ctx->ordered_extents)))
+		return true;
+
+	return false;
+}
+
 /*
  * fsync call for both files and directories.  This logs the inode into
  * the tree log instead of forcing full commits whenever possible.
@@ -2185,17 +2209,8 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 
 	atomic_inc(&root->log_batch);
 
-	/*
-	 * If we are doing a fast fsync we can not bail out if the inode's
-	 * last_trans is <= then the last committed transaction, because we only
-	 * update the last_trans of the inode during ordered extent completion,
-	 * and for a fast fsync we don't wait for that, we only wait for the
-	 * writeback to complete.
-	 */
 	smp_mb();
-	if (btrfs_inode_in_log(BTRFS_I(inode), fs_info->generation) ||
-	    (BTRFS_I(inode)->last_trans <= fs_info->last_trans_committed &&
-	     (full_sync || list_empty(&ctx.ordered_extents)))) {
+	if (skip_inode_logging(&ctx)) {
 		/*
 		 * We've had everything committed since the last time we were
 		 * modified so clear this flag in case it was set for whatever

fs/btrfs/free-space-cache.c

@@ -3949,7 +3949,7 @@ static int cleanup_free_space_cache_v1(struct btrfs_fs_info *fs_info,
 {
 	struct btrfs_block_group *block_group;
 	struct rb_node *node;
-	int ret;
+	int ret = 0;
 
 	btrfs_info(fs_info, "cleaning free space cache v1");
 

fs/btrfs/inode.c

@@ -9678,7 +9678,7 @@ static int start_delalloc_inodes(struct btrfs_root *root,
 	return ret;
 }
 
-int btrfs_start_delalloc_snapshot(struct btrfs_root *root)
+int btrfs_start_delalloc_snapshot(struct btrfs_root *root, bool in_reclaim_context)
 {
 	struct writeback_control wbc = {
 		.nr_to_write = LONG_MAX,
@@ -9691,7 +9691,7 @@ int btrfs_start_delalloc_snapshot(struct btrfs_root *root)
 	if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
 		return -EROFS;
 
-	return start_delalloc_inodes(root, &wbc, true, false);
+	return start_delalloc_inodes(root, &wbc, true, in_reclaim_context);
 }
 
 int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, long nr,

fs/btrfs/ioctl.c

@@ -907,7 +907,7 @@ static noinline int btrfs_mksnapshot(const struct path *parent,
 	 */
 	btrfs_drew_read_lock(&root->snapshot_lock);
 
-	ret = btrfs_start_delalloc_snapshot(root);
+	ret = btrfs_start_delalloc_snapshot(root, false);
 	if (ret)
 		goto out;
 

fs/btrfs/ordered-data.c

@@ -984,7 +984,7 @@ int btrfs_split_ordered_extent(struct btrfs_ordered_extent *ordered, u64 pre,
 
 	if (pre)
 		ret = clone_ordered_extent(ordered, 0, pre);
-	if (post)
+	if (ret == 0 && post)
 		ret = clone_ordered_extent(ordered, pre + ordered->disk_num_bytes,
 					   post);
 

fs/btrfs/qgroup.c

@@ -3545,11 +3545,15 @@ static int try_flush_qgroup(struct btrfs_root *root)
 	struct btrfs_trans_handle *trans;
 	int ret;
 
-	/* Can't hold an open transaction or we run the risk of deadlocking */
-	ASSERT(current->journal_info == NULL ||
-	       current->journal_info == BTRFS_SEND_TRANS_STUB);
-	if (WARN_ON(current->journal_info &&
-		    current->journal_info != BTRFS_SEND_TRANS_STUB))
+	/*
+	 * Can't hold an open transaction or we run the risk of deadlocking,
+	 * and can't either be under the context of a send operation (where
+	 * current->journal_info is set to BTRFS_SEND_TRANS_STUB), as that
+	 * would result in a crash when starting a transaction and does not
+	 * make sense either (send is a read-only operation).
+	 */
+	ASSERT(current->journal_info == NULL);
+	if (WARN_ON(current->journal_info))
 		return 0;
 
 	/*
@@ -3562,7 +3566,7 @@ static int try_flush_qgroup(struct btrfs_root *root)
 		return 0;
 	}
 
-	ret = btrfs_start_delalloc_snapshot(root);
+	ret = btrfs_start_delalloc_snapshot(root, true);
 	if (ret < 0)
 		goto out;
 	btrfs_wait_ordered_extents(root, U64_MAX, 0, (u64)-1);

fs/btrfs/send.c

@@ -7170,7 +7170,7 @@ static int flush_delalloc_roots(struct send_ctx *sctx)
 	int i;
 
 	if (root) {
-		ret = btrfs_start_delalloc_snapshot(root);
+		ret = btrfs_start_delalloc_snapshot(root, false);
 		if (ret)
 			return ret;
 		btrfs_wait_ordered_extents(root, U64_MAX, 0, U64_MAX);
@@ -7178,7 +7178,7 @@ static int flush_delalloc_roots(struct send_ctx *sctx)
 
 	for (i = 0; i < sctx->clone_roots_cnt; i++) {
 		root = sctx->clone_roots[i].root;
-		ret = btrfs_start_delalloc_snapshot(root);
+		ret = btrfs_start_delalloc_snapshot(root, false);
 		if (ret)
 			return ret;
 		btrfs_wait_ordered_extents(root, U64_MAX, 0, U64_MAX);

fs/btrfs/tree-log.c

@@ -6061,7 +6061,8 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 	 * (since logging them is pointless, a link count of 0 means they
 	 * will never be accessible).
 	 */
-	if (btrfs_inode_in_log(inode, trans->transid) ||
+	if ((btrfs_inode_in_log(inode, trans->transid) &&
+	     list_empty(&ctx->ordered_extents)) ||
 	    inode->vfs_inode.i_nlink == 0) {
 		ret = BTRFS_NO_LOG_SYNC;
 		goto end_no_trans;

fs/btrfs/zoned.c

@@ -1126,6 +1126,11 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 			goto out;
 		}
 
+		if (zone.type == BLK_ZONE_TYPE_CONVENTIONAL) {
+			ret = -EIO;
+			goto out;
+		}
+
 		switch (zone.cond) {
 		case BLK_ZONE_COND_OFFLINE:
 		case BLK_ZONE_COND_READONLY: