Merge tag 'xfs-5.20-merge-8' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull more xfs updates from Darrick Wong:
 "There's not a lot this time around, just the usual bug fixes and
  corrections for missing error returns.

   - Return error codes from block device flushes to userspace

   - Fix a deadlock between reclaim and mount time quotacheck

   - Fix an unnecessary ENOSPC return when doing COW on a filesystem
     with severe free space fragmentation

   - Fix a miscalculation in the transaction reservation computations
     for file removal operations"

* tag 'xfs-5.20-merge-8' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux:
  xfs: fix inode reservation space for removing transaction
  xfs: Fix false ENOSPC when performing direct write on a delalloc extent in cow fork
  xfs: fix intermittent hang during quotacheck
  xfs: check return codes when flushing block devices

fs/xfs/libxfs/xfs_trans_resv.c

@@ -515,7 +515,7 @@ xfs_calc_remove_reservation(
 {
 	return XFS_DQUOT_LOGRES(mp) +
 		xfs_calc_iunlink_add_reservation(mp) +
-		max((xfs_calc_inode_res(mp, 1) +
+		max((xfs_calc_inode_res(mp, 2) +
 		     xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp),
 				      XFS_FSB_TO_B(mp, 1))),
 		    (xfs_calc_buf_res(4, mp->m_sb.sb_sectsize) +

fs/xfs/xfs_file.c

@@ -143,7 +143,7 @@ xfs_file_fsync(
 {
 	struct xfs_inode	*ip = XFS_I(file->f_mapping->host);
 	struct xfs_mount	*mp = ip->i_mount;
-	int			error = 0;
+	int			error, err2;
 	int			log_flushed = 0;
 
 	trace_xfs_file_fsync(ip);
@@ -164,18 +164,21 @@ xfs_file_fsync(
 	 * inode size in case of an extending write.
 	 */
 	if (XFS_IS_REALTIME_INODE(ip))
-		blkdev_issue_flush(mp->m_rtdev_targp->bt_bdev);
+		error = blkdev_issue_flush(mp->m_rtdev_targp->bt_bdev);
 	else if (mp->m_logdev_targp != mp->m_ddev_targp)
-		blkdev_issue_flush(mp->m_ddev_targp->bt_bdev);
+		error = blkdev_issue_flush(mp->m_ddev_targp->bt_bdev);
 
 	/*
 	 * Any inode that has dirty modifications in the log is pinned.  The
-	 * racy check here for a pinned inode while not catch modifications
+	 * racy check here for a pinned inode will not catch modifications
 	 * that happen concurrently to the fsync call, but fsync semantics
 	 * only require to sync previously completed I/O.
 	 */
-	if (xfs_ipincount(ip))
-		error = xfs_fsync_flush_log(ip, datasync, &log_flushed);
+	if (xfs_ipincount(ip)) {
+		err2 = xfs_fsync_flush_log(ip, datasync, &log_flushed);
+		if (err2 && !error)
+			error = err2;
+	}
 
 	/*
 	 * If we only have a single device, and the log force about was
@@ -185,8 +188,11 @@ xfs_file_fsync(
 	 * commit.
 	 */
 	if (!log_flushed && !XFS_IS_REALTIME_INODE(ip) &&
-	    mp->m_logdev_targp == mp->m_ddev_targp)
-		blkdev_issue_flush(mp->m_ddev_targp->bt_bdev);
+	    mp->m_logdev_targp == mp->m_ddev_targp) {
+		err2 = blkdev_issue_flush(mp->m_ddev_targp->bt_bdev);
+		if (err2 && !error)
+			error = err2;
+	}
 
 	return error;
 }

fs/xfs/xfs_log.c

@@ -1925,9 +1925,17 @@ xlog_write_iclog(
 		 * device cache first to ensure all metadata writeback covered
 		 * by the LSN in this iclog is on stable storage. This is slow,
 		 * but it *must* complete before we issue the external log IO.
+		 *
+		 * If the flush fails, we cannot conclude that past metadata
+		 * writeback from the log succeeded.  Repeating the flush is
+		 * not possible, hence we must shut down with log IO error to
+		 * avoid shutdown re-entering this path and erroring out again.
 		 */
-		if (log->l_targ != log->l_mp->m_ddev_targp)
-			blkdev_issue_flush(log->l_mp->m_ddev_targp->bt_bdev);
+		if (log->l_targ != log->l_mp->m_ddev_targp &&
+		    blkdev_issue_flush(log->l_mp->m_ddev_targp->bt_bdev)) {
+			xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR);
+			return;
+		}
 	}
 	if (iclog->ic_flags & XLOG_ICL_NEED_FUA)
 		iclog->ic_bio.bi_opf |= REQ_FUA;

fs/xfs/xfs_qm.c

@@ -1235,6 +1235,11 @@ xfs_qm_flush_one(
 		if (error)
 			goto out_unlock;
 
+		if (!(bp->b_flags & _XBF_DELWRI_Q)) {
+			error = -EAGAIN;
+			xfs_buf_relse(bp);
+			goto out_unlock;
+		}
 		xfs_buf_unlock(bp);
 
 		xfs_buf_delwri_pushbuf(bp, buffer_list);

fs/xfs/xfs_reflink.c

@@ -341,36 +341,55 @@ xfs_find_trim_cow_extent(
 	return 0;
 }
 
-/* Allocate all CoW reservations covering a range of blocks in a file. */
-int
-xfs_reflink_allocate_cow(
+static int
+xfs_reflink_convert_unwritten(
 	struct xfs_inode	*ip,
 	struct xfs_bmbt_irec	*imap,
 	struct xfs_bmbt_irec	*cmap,
-	bool			*shared,
-	uint			*lockmode,
 	bool			convert_now)
 {
-	struct xfs_mount	*mp = ip->i_mount;
 	xfs_fileoff_t		offset_fsb = imap->br_startoff;
 	xfs_filblks_t		count_fsb = imap->br_blockcount;
-	struct xfs_trans	*tp;
-	int			nimaps, error = 0;
-	bool			found;
-	xfs_filblks_t		resaligned;
-	xfs_extlen_t		resblks = 0;
+	int			error;
 
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
-	if (!ip->i_cowfp) {
-		ASSERT(!xfs_is_reflink_inode(ip));
-		xfs_ifork_init_cow(ip);
-	}
+	/*
+	 * cmap might larger than imap due to cowextsize hint.
+	 */
+	xfs_trim_extent(cmap, offset_fsb, count_fsb);
+
+	/*
+	 * COW fork extents are supposed to remain unwritten until we're ready
+	 * to initiate a disk write.  For direct I/O we are going to write the
+	 * data and need the conversion, but for buffered writes we're done.
+	 */
+	if (!convert_now || cmap->br_state == XFS_EXT_NORM)
+		return 0;
+
+	trace_xfs_reflink_convert_cow(ip, cmap);
+
+	error = xfs_reflink_convert_cow_locked(ip, offset_fsb, count_fsb);
+	if (!error)
+		cmap->br_state = XFS_EXT_NORM;
 
-	error = xfs_find_trim_cow_extent(ip, imap, cmap, shared, &found);
-	if (error || !*shared)
 	return error;
-	if (found)
-		goto convert;
+}
+
+static int
+xfs_reflink_fill_cow_hole(
+	struct xfs_inode	*ip,
+	struct xfs_bmbt_irec	*imap,
+	struct xfs_bmbt_irec	*cmap,
+	bool			*shared,
+	uint			*lockmode,
+	bool			convert_now)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_trans	*tp;
+	xfs_filblks_t		resaligned;
+	xfs_extlen_t		resblks;
+	int			nimaps;
+	int			error;
+	bool			found;
 
 	resaligned = xfs_aligned_fsb_count(imap->br_startoff,
 		imap->br_blockcount, xfs_get_cowextsz_hint(ip));
@@ -386,17 +405,17 @@ xfs_reflink_allocate_cow(
 
 	*lockmode = XFS_ILOCK_EXCL;
 
-	/*
-	 * Check for an overlapping extent again now that we dropped the ilock.
-	 */
 	error = xfs_find_trim_cow_extent(ip, imap, cmap, shared, &found);
 	if (error || !*shared)
 		goto out_trans_cancel;
+
 	if (found) {
 		xfs_trans_cancel(tp);
 		goto convert;
 	}
 
+	ASSERT(cmap->br_startoff > imap->br_startoff);
+
 	/* Allocate the entire reservation as unwritten blocks. */
 	nimaps = 1;
 	error = xfs_bmapi_write(tp, ip, imap->br_startoff, imap->br_blockcount,
@@ -416,26 +435,135 @@ xfs_reflink_allocate_cow(
 	 */
 	if (nimaps == 0)
 		return -ENOSPC;
+
 convert:
-	xfs_trim_extent(cmap, offset_fsb, count_fsb);
+	return xfs_reflink_convert_unwritten(ip, imap, cmap, convert_now);
+
+out_trans_cancel:
+	xfs_trans_cancel(tp);
+	return error;
+}
+
+static int
+xfs_reflink_fill_delalloc(
+	struct xfs_inode	*ip,
+	struct xfs_bmbt_irec	*imap,
+	struct xfs_bmbt_irec	*cmap,
+	bool			*shared,
+	uint			*lockmode,
+	bool			convert_now)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_trans	*tp;
+	int			nimaps;
+	int			error;
+	bool			found;
+
+	do {
+		xfs_iunlock(ip, *lockmode);
+		*lockmode = 0;
+
+		error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, 0, 0,
+				false, &tp);
+		if (error)
+			return error;
+
+		*lockmode = XFS_ILOCK_EXCL;
+
+		error = xfs_find_trim_cow_extent(ip, imap, cmap, shared,
+				&found);
+		if (error || !*shared)
+			goto out_trans_cancel;
+
+		if (found) {
+			xfs_trans_cancel(tp);
+			break;
+		}
+
+		ASSERT(isnullstartblock(cmap->br_startblock) ||
+		       cmap->br_startblock == DELAYSTARTBLOCK);
+
 		/*
-	 * COW fork extents are supposed to remain unwritten until we're ready
-	 * to initiate a disk write.  For direct I/O we are going to write the
-	 * data and need the conversion, but for buffered writes we're done.
+		 * Replace delalloc reservation with an unwritten extent.
 		 */
-	if (!convert_now || cmap->br_state == XFS_EXT_NORM)
-		return 0;
-	trace_xfs_reflink_convert_cow(ip, cmap);
-	error = xfs_reflink_convert_cow_locked(ip, offset_fsb, count_fsb);
-	if (!error)
-		cmap->br_state = XFS_EXT_NORM;
+		nimaps = 1;
+		error = xfs_bmapi_write(tp, ip, cmap->br_startoff,
+				cmap->br_blockcount,
+				XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC, 0,
+				cmap, &nimaps);
+		if (error)
+			goto out_trans_cancel;
+
+		xfs_inode_set_cowblocks_tag(ip);
+		error = xfs_trans_commit(tp);
+		if (error)
 			return error;
 
+		/*
+		 * Allocation succeeded but the requested range was not even
+		 * partially satisfied?  Bail out!
+		 */
+		if (nimaps == 0)
+			return -ENOSPC;
+	} while (cmap->br_startoff + cmap->br_blockcount <= imap->br_startoff);
+
+	return xfs_reflink_convert_unwritten(ip, imap, cmap, convert_now);
+
 out_trans_cancel:
 	xfs_trans_cancel(tp);
 	return error;
 }
 
+/* Allocate all CoW reservations covering a range of blocks in a file. */
+int
+xfs_reflink_allocate_cow(
+	struct xfs_inode	*ip,
+	struct xfs_bmbt_irec	*imap,
+	struct xfs_bmbt_irec	*cmap,
+	bool			*shared,
+	uint			*lockmode,
+	bool			convert_now)
+{
+	int			error;
+	bool			found;
+
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+	if (!ip->i_cowfp) {
+		ASSERT(!xfs_is_reflink_inode(ip));
+		xfs_ifork_init_cow(ip);
+	}
+
+	error = xfs_find_trim_cow_extent(ip, imap, cmap, shared, &found);
+	if (error || !*shared)
+		return error;
+
+	/* CoW fork has a real extent */
+	if (found)
+		return xfs_reflink_convert_unwritten(ip, imap, cmap,
+				convert_now);
+
+	/*
+	 * CoW fork does not have an extent and data extent is shared.
+	 * Allocate a real extent in the CoW fork.
+	 */
+	if (cmap->br_startoff > imap->br_startoff)
+		return xfs_reflink_fill_cow_hole(ip, imap, cmap, shared,
+				lockmode, convert_now);
+
+	/*
+	 * CoW fork has a delalloc reservation. Replace it with a real extent.
+	 * There may or may not be a data fork mapping.
+	 */
+	if (isnullstartblock(cmap->br_startblock) ||
+	    cmap->br_startblock == DELAYSTARTBLOCK)
+		return xfs_reflink_fill_delalloc(ip, imap, cmap, shared,
+				lockmode, convert_now);
+
+	/* Shouldn't get here. */
+	ASSERT(0);
+	return -EFSCORRUPTED;
+}
+
 /*
  * Cancel CoW reservations for some block range of an inode.
  *