3 files changed, 37 insertions, 0 deletions

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index a9466e346358..49d956b2cf30 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3866,6 +3866,7 @@ int btrfs_prealloc_file_range_trans(struct inode *inode,
                                     struct btrfs_trans_handle *trans, int mode,
                                     u64 start, u64 num_bytes, u64 min_size,
                                     loff_t actual_len, u64 *alloc_hint);
+int btrfs_inode_check_errors(struct inode *inode);
 extern const struct dentry_operations btrfs_dentry_operations;
 
 /* ioctl.c */
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index cb5978a4a277..a5374c2bb943 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -9464,6 +9464,21 @@ out_inode:
 
 }
 
+/* Inspired by filemap_check_errors() */
+int btrfs_inode_check_errors(struct inode *inode)
+{
+        int ret = 0;
+
+        if (test_bit(AS_ENOSPC, &inode->i_mapping->flags) &&
+            test_and_clear_bit(AS_ENOSPC, &inode->i_mapping->flags))
+                ret = -ENOSPC;
+        if (test_bit(AS_EIO, &inode->i_mapping->flags) &&
+            test_and_clear_bit(AS_EIO, &inode->i_mapping->flags))
+                ret = -EIO;
+
+        return ret;
+}
+
 static const struct inode_operations btrfs_dir_inode_operations = {
         .getattr        = btrfs_getattr,
         .lookup         = btrfs_lookup,
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 3883d0febd82..9a02da16f2be 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3635,6 +3635,12 @@ static int wait_ordered_extents(struct btrfs_trans_handle *trans,
                             test_bit(BTRFS_ORDERED_IOERR, &ordered->flags)));
 
                 if (test_bit(BTRFS_ORDERED_IOERR, &ordered->flags)) {
+                        /*
+                         * Clear the AS_EIO/AS_ENOSPC flags from the inode's
+                         * i_mapping flags, so that the next fsync won't get
+                         * an outdated io error too.
+                         */
+                        btrfs_inode_check_errors(inode);
                         *ordered_io_error = true;
                         break;
                 }
@@ -4098,6 +4104,21 @@ log_extents:
         btrfs_release_path(path);
         btrfs_release_path(dst_path);
         if (fast_search) {
+                /*
+                 * Some ordered extents started by fsync might have completed
+                 * before we collected the ordered extents in logged_list, which
+                 * means they're gone, not in our logged_list nor in the inode's
+                 * ordered tree. We want the application/user space to know an
+                 * error happened while attempting to persist file data so that
+                 * it can take proper action. If such error happened, we leave
+                 * without writing to the log tree and the fsync must report the
+                 * file data write error and not commit the current transaction.
+                 */
+                err = btrfs_inode_check_errors(inode);
+                if (err) {
+                        ctx->io_err = err;
+                        goto out_unlock;
+                }
                 ret = btrfs_log_changed_extents(trans, root, inode, dst_path,
                                                 &logged_list, ctx);
                 if (ret) {