5 files changed, 73 insertions, 1 deletions

diff --git a/fs/bcachefs/btree_locking.c b/fs/bcachefs/btree_locking.c
index c3e9b0cc7bbd..d66fff22109a 100644
--- a/fs/bcachefs/btree_locking.c
+++ b/fs/bcachefs/btree_locking.c
@@ -215,6 +215,7 @@ static noinline int break_cycle(struct lock_graph *g, struct printbuf *cycle)
 
 	if (unlikely(!best)) {
 		struct printbuf buf = PRINTBUF;
+		buf.atomic++;
 
 		prt_printf(&buf, bch2_fmt(g->g->trans->c, "cycle of nofail locks"));
 
diff --git a/fs/bcachefs/move.c b/fs/bcachefs/move.c
index 8171f947fac8..6e477fadaa2a 100644
--- a/fs/bcachefs/move.c
+++ b/fs/bcachefs/move.c
@@ -547,6 +547,7 @@ static int bch2_move_data_btree(struct moving_context *ctxt,
 		ctxt->stats->pos	= BBPOS(btree_id, start);
 	}
 
+	bch2_trans_begin(trans);
 	bch2_trans_iter_init(trans, &iter, btree_id, start,
 			     BTREE_ITER_prefetch|
 			     BTREE_ITER_all_snapshots);
@@ -920,7 +921,20 @@ static bool rereplicate_pred(struct bch_fs *c, void *arg,
 		? c->opts.metadata_replicas
 		: io_opts->data_replicas;
 
-	if (!nr_good || nr_good >= replicas)
+	rcu_read_lock();
+	struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k);
+	unsigned i = 0;
+	bkey_for_each_ptr(ptrs, ptr) {
+		struct bch_dev *ca = bch2_dev_rcu(c, ptr->dev);
+		if (!ptr->cached &&
+		    (!ca || !ca->mi.durability))
+			data_opts->kill_ptrs |= BIT(i);
+		i++;
+	}
+	rcu_read_unlock();
+
+	if (!data_opts->kill_ptrs &&
+	    (!nr_good || nr_good >= replicas))
 		return false;
 
 	data_opts->target		= 0;
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 91c994b569f3..6ed495ca7a31 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 e764ac3f22e2..d90138683a0a 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1885,6 +1885,7 @@ 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
@@ -1894,6 +1895,21 @@ 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 c5bdd674f55c..35a413ce935d 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -388,6 +388,37 @@ 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;