Merging upstream version 6.9.11.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

6 files changed, 80 insertions, 14 deletions

diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 100020ca46..787ca2892d 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -89,6 +89,16 @@ enum {
 	BTRFS_INODE_FREE_SPACE_INODE,
 	/* Set when there are no capabilities in XATTs for the inode. */
 	BTRFS_INODE_NO_CAP_XATTR,
+	/*
+	 * Set if an error happened when doing a COW write before submitting a
+	 * bio or during writeback. Used for both buffered writes and direct IO
+	 * writes. This is to signal a fast fsync that it has to wait for
+	 * ordered extents to complete and therefore not log extent maps that
+	 * point to unwritten extents (when an ordered extent completes and it
+	 * has the BTRFS_ORDERED_IOERR flag set, it drops extent maps in its
+	 * range).
+	 */
+	BTRFS_INODE_COW_WRITE_ERROR,
 };
 
 /* in memory btrfs inode */
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index f9d7607239..97f6133b6e 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1875,6 +1875,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	 */
 	if (full_sync || btrfs_is_zoned(fs_info)) {
 		ret = btrfs_wait_ordered_range(inode, start, len);
+		clear_bit(BTRFS_INODE_COW_WRITE_ERROR, &BTRFS_I(inode)->runtime_flags);
 	} else {
 		/*
 		 * Get our ordered extents as soon as possible to avoid doing
@@ -1884,6 +1885,21 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 		btrfs_get_ordered_extents_for_logging(BTRFS_I(inode),
 						      &ctx.ordered_extents);
 		ret = filemap_fdatawait_range(inode->i_mapping, start, end);
+		if (ret)
+			goto out_release_extents;
+
+		/*
+		 * Check and clear the BTRFS_INODE_COW_WRITE_ERROR now after
+		 * starting and waiting for writeback, because for buffered IO
+		 * it may have been set during the end IO callback
+		 * (end_bbio_data_write() -> btrfs_finish_ordered_extent()) in
+		 * case an error happened and we need to wait for ordered
+		 * extents to complete so that any extent maps that point to
+		 * unwritten locations are dropped and we don't log them.
+		 */
+		if (test_and_clear_bit(BTRFS_INODE_COW_WRITE_ERROR,
+				       &BTRFS_I(inode)->runtime_flags))
+			ret = btrfs_wait_ordered_range(inode, start, len);
 	}
 
 	if (ret)
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index c2a42bcde9..7dbf4162c7 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -382,6 +382,37 @@ bool btrfs_finish_ordered_extent(struct btrfs_ordered_extent *ordered,
 	ret = can_finish_ordered_extent(ordered, page, file_offset, len, uptodate);
 	spin_unlock_irqrestore(&inode->ordered_tree_lock, flags);
 
+	/*
+	 * If this is a COW write it means we created new extent maps for the
+	 * range and they point to unwritten locations if we got an error either
+	 * before submitting a bio or during IO.
+	 *
+	 * We have marked the ordered extent with BTRFS_ORDERED_IOERR, and we
+	 * are queuing its completion below. During completion, at
+	 * btrfs_finish_one_ordered(), we will drop the extent maps for the
+	 * unwritten extents.
+	 *
+	 * However because completion runs in a work queue we can end up having
+	 * a fast fsync running before that. In the case of direct IO, once we
+	 * unlock the inode the fsync might start, and we queue the completion
+	 * before unlocking the inode. In the case of buffered IO when writeback
+	 * finishes (end_bbio_data_write()) we queue the completion, so if the
+	 * writeback was triggered by a fast fsync, the fsync might start
+	 * logging before ordered extent completion runs in the work queue.
+	 *
+	 * The fast fsync will log file extent items based on the extent maps it
+	 * finds, so if by the time it collects extent maps the ordered extent
+	 * completion didn't happen yet, it will log file extent items that
+	 * point to unwritten extents, resulting in a corruption if a crash
+	 * happens and the log tree is replayed. Note that a fast fsync does not
+	 * wait for completion of ordered extents in order to reduce latency.
+	 *
+	 * Set a flag in the inode so that the next fast fsync will wait for
+	 * ordered extents to complete before starting to log.
+	 */
+	if (!uptodate && !test_bit(BTRFS_ORDERED_NOCOW, &ordered->flags))
+		set_bit(BTRFS_INODE_COW_WRITE_ERROR, &inode->runtime_flags);
+
 	if (ret)
 		btrfs_queue_ordered_fn(ordered);
 	return ret;
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 4caa078d97..9af2afb417 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1351,7 +1351,7 @@ static int flush_reservations(struct btrfs_fs_info *fs_info)
 
 int btrfs_quota_disable(struct btrfs_fs_info *fs_info)
 {
-	struct btrfs_root *quota_root;
+	struct btrfs_root *quota_root = NULL;
 	struct btrfs_trans_handle *trans = NULL;
 	int ret = 0;
 
@@ -1449,9 +1449,9 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info)
 	btrfs_free_tree_block(trans, btrfs_root_id(quota_root),
 			      quota_root->node, 0, 1);
 
-	btrfs_put_root(quota_root);
 
 out:
+	btrfs_put_root(quota_root);
 	mutex_unlock(&fs_info->qgroup_ioctl_lock);
 	if (ret && trans)
 		btrfs_end_transaction(trans);
diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c
index 8c4fc98ca9..aa7ddc09c5 100644
--- a/fs/btrfs/ref-verify.c
+++ b/fs/btrfs/ref-verify.c
@@ -441,7 +441,8 @@ static int process_extent_item(struct btrfs_fs_info *fs_info,
 	u32 item_size = btrfs_item_size(leaf, slot);
 	unsigned long end, ptr;
 	u64 offset, flags, count;
-	int type, ret;
+	int type;
+	int ret = 0;
 
 	ei = btrfs_item_ptr(leaf, slot, struct btrfs_extent_item);
 	flags = btrfs_extent_flags(leaf, ei);
@@ -486,7 +487,11 @@ static int process_extent_item(struct btrfs_fs_info *fs_info,
 						  key->objectid, key->offset);
 			break;
 		case BTRFS_EXTENT_OWNER_REF_KEY:
-			WARN_ON(!btrfs_fs_incompat(fs_info, SIMPLE_QUOTA));
+			if (!btrfs_fs_incompat(fs_info, SIMPLE_QUOTA)) {
+				btrfs_err(fs_info,
+			  "found extent owner ref without simple quotas enabled");
+				ret = -EINVAL;
+			}
 			break;
 		default:
 			btrfs_err(fs_info, "invalid key type in iref");
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index afd6932f5e..d7caa3732f 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1688,20 +1688,24 @@ static void scrub_submit_extent_sector_read(struct scrub_ctx *sctx,
 					    (i << fs_info->sectorsize_bits);
 			int err;
 
-			bbio = btrfs_bio_alloc(stripe->nr_sectors, REQ_OP_READ,
-					       fs_info, scrub_read_endio, stripe);
-			bbio->bio.bi_iter.bi_sector = logical >> SECTOR_SHIFT;
-
 			io_stripe.is_scrub = true;
+			stripe_len = (nr_sectors - i) << fs_info->sectorsize_bits;
+			/*
+			 * For RST cases, we need to manually split the bbio to
+			 * follow the RST boundary.
+			 */
 			err = btrfs_map_block(fs_info, BTRFS_MAP_READ, logical,
-					      &stripe_len, &bioc, &io_stripe,
-					      &mirror);
+					      &stripe_len, &bioc, &io_stripe, &mirror);
 			btrfs_put_bioc(bioc);
-			if (err) {
-				btrfs_bio_end_io(bbio,
-						 errno_to_blk_status(err));
-				return;
+			if (err < 0) {
+				set_bit(i, &stripe->io_error_bitmap);
+				set_bit(i, &stripe->error_bitmap);
+				continue;
 			}
+
+			bbio = btrfs_bio_alloc(stripe->nr_sectors, REQ_OP_READ,
+					       fs_info, scrub_read_endio, stripe);
+			bbio->bio.bi_iter.bi_sector = logical >> SECTOR_SHIFT;
 		}
 
 		__bio_add_page(&bbio->bio, page, fs_info->sectorsize, pgoff);