1 files changed, 86 insertions, 52 deletions

diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 1aa3abd67b36..813394c62849 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -162,7 +162,7 @@ xfs_iomap_write_direct(
 	xfs_fileoff_t	last_fsb;
 	xfs_filblks_t	count_fsb, resaligned;
 	xfs_fsblock_t	firstfsb;
-	xfs_extlen_t	extsz, temp;
+	xfs_extlen_t	extsz;
 	int		nimaps;
 	int		quota_flag;
 	int		rt;
@@ -203,14 +203,7 @@ xfs_iomap_write_direct(
 	}
 	count_fsb = last_fsb - offset_fsb;
 	ASSERT(count_fsb > 0);
-
-	resaligned = count_fsb;
-	if (unlikely(extsz)) {
-		if ((temp = do_mod(offset_fsb, extsz)))
-			resaligned += temp;
-		if ((temp = do_mod(resaligned, extsz)))
-			resaligned += extsz - temp;
-	}
+	resaligned = xfs_aligned_fsb_count(offset_fsb, count_fsb, extsz);
 
 	if (unlikely(rt)) {
 		resrtextents = qblocks = resaligned;
@@ -247,7 +240,7 @@ xfs_iomap_write_direct(
 	 */
 	if (IS_DAX(VFS_I(ip))) {
 		bmapi_flags = XFS_BMAPI_CONVERT | XFS_BMAPI_ZERO;
-		if (ISUNWRITTEN(imap)) {
+		if (imap->br_state == XFS_EXT_UNWRITTEN) {
 			tflags |= XFS_TRANS_RESERVE;
 			resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0) << 1;
 		}
@@ -550,7 +543,7 @@ xfs_file_iomap_begin_delay(
 	if (unlikely(XFS_TEST_ERROR(
 	    (XFS_IFORK_FORMAT(ip, XFS_DATA_FORK) != XFS_DINODE_FMT_EXTENTS &&
 	     XFS_IFORK_FORMAT(ip, XFS_DATA_FORK) != XFS_DINODE_FMT_BTREE),
-	     mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) {
+	     mp, XFS_ERRTAG_BMAPIFORMAT))) {
 		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp);
 		error = -EFSCORRUPTED;
 		goto out_unlock;
@@ -637,6 +630,11 @@ retry:
 		goto out_unlock;
 	}
 
+	/*
+	 * Flag newly allocated delalloc blocks with IOMAP_F_NEW so we punch
+	 * them out if the write happens to fail.
+	 */
+	iomap->flags = IOMAP_F_NEW;
 	trace_xfs_iomap_alloc(ip, offset, count, 0, &got);
 done:
 	if (isnullstartblock(got.br_startblock))
@@ -685,7 +683,7 @@ xfs_iomap_write_allocate(
 	int		nres;
 
 	if (whichfork == XFS_COW_FORK)
-		flags |= XFS_BMAPI_COWFORK;
+		flags |= XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC;
 
 	/*
 	 * Make sure that the dquots are there.
@@ -947,7 +945,7 @@ static inline bool imap_needs_alloc(struct inode *inode,
 	return !nimaps ||
 		imap->br_startblock == HOLESTARTBLOCK ||
 		imap->br_startblock == DELAYSTARTBLOCK ||
-		(IS_DAX(inode) && ISUNWRITTEN(imap));
+		(IS_DAX(inode) && imap->br_state == XFS_EXT_UNWRITTEN);
 }
 
 static inline bool need_excl_ilock(struct xfs_inode *ip, unsigned flags)
@@ -978,6 +976,7 @@ xfs_file_iomap_begin(
 	int			nimaps = 1, error = 0;
 	bool			shared = false, trimmed = false;
 	unsigned		lockmode;
+	struct block_device	*bdev;
 
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
@@ -996,53 +995,51 @@ xfs_file_iomap_begin(
 		lockmode = xfs_ilock_data_map_shared(ip);
 	}
 
+	if ((flags & IOMAP_NOWAIT) && !(ip->i_df.if_flags & XFS_IFEXTENTS)) {
+		error = -EAGAIN;
+		goto out_unlock;
+	}
+
 	ASSERT(offset <= mp->m_super->s_maxbytes);
 	if ((xfs_fsize_t)offset + length > mp->m_super->s_maxbytes)
 		length = mp->m_super->s_maxbytes - offset;
 	offset_fsb = XFS_B_TO_FSBT(mp, offset);
 	end_fsb = XFS_B_TO_FSB(mp, offset + length);
 
-	if (xfs_is_reflink_inode(ip) &&
-	    (flags & IOMAP_WRITE) && (flags & IOMAP_DIRECT)) {
-		shared = xfs_reflink_find_cow_mapping(ip, offset, &imap);
-		if (shared) {
-			xfs_iunlock(ip, lockmode);
-			goto alloc_done;
-		}
-		ASSERT(!isnullstartblock(imap.br_startblock));
-	}
-
 	error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap,
 			       &nimaps, 0);
 	if (error)
 		goto out_unlock;
 
-	if ((flags & IOMAP_REPORT) ||
-	    (xfs_is_reflink_inode(ip) &&
-	     (flags & IOMAP_WRITE) && (flags & IOMAP_DIRECT))) {
+	if (flags & IOMAP_REPORT) {
 		/* Trim the mapping to the nearest shared extent boundary. */
 		error = xfs_reflink_trim_around_shared(ip, &imap, &shared,
 				&trimmed);
 		if (error)
 			goto out_unlock;
-
-		/*
-		 * We're here because we're trying to do a directio write to a
-		 * region that isn't aligned to a filesystem block.  If the
-		 * extent is shared, fall back to buffered mode to handle the
-		 * RMW.
-		 */
-		if (!(flags & IOMAP_REPORT) && shared) {
-			trace_xfs_reflink_bounce_dio_write(ip, &imap);
-			error = -EREMCHG;
-			goto out_unlock;
-		}
 	}
 
 	if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) {
-		error = xfs_reflink_reserve_cow(ip, &imap, &shared);
-		if (error)
-			goto out_unlock;
+		if (flags & IOMAP_DIRECT) {
+			/*
+			 * A reflinked inode will result in CoW alloc.
+			 * FIXME: It could still overwrite on unshared extents
+			 * and not need allocation.
+			 */
+			if (flags & IOMAP_NOWAIT) {
+				error = -EAGAIN;
+				goto out_unlock;
+			}
+			/* may drop and re-acquire the ilock */
+			error = xfs_reflink_allocate_cow(ip, &imap, &shared,
+					&lockmode);
+			if (error)
+				goto out_unlock;
+		} else {
+			error = xfs_reflink_reserve_cow(ip, &imap, &shared);
+			if (error)
+				goto out_unlock;
+		}
 
 		end_fsb = imap.br_startoff + imap.br_blockcount;
 		length = XFS_FSB_TO_B(mp, end_fsb) - offset;
@@ -1050,6 +1047,14 @@ xfs_file_iomap_begin(
 
 	if ((flags & IOMAP_WRITE) && imap_needs_alloc(inode, &imap, nimaps)) {
 		/*
+		 * If nowait is set bail since we are going to make
+		 * allocations.
+		 */
+		if (flags & IOMAP_NOWAIT) {
+			error = -EAGAIN;
+			goto out_unlock;
+		}
+		/*
 		 * We cap the maximum length we map here to MAX_WRITEBACK_PAGES
 		 * pages to keep the chunks of work done where somewhat symmetric
 		 * with the work writeback does. This is a completely arbitrary
@@ -1071,7 +1076,6 @@ xfs_file_iomap_begin(
 		if (error)
 			return error;
 
-alloc_done:
 		iomap->flags = IOMAP_F_NEW;
 		trace_xfs_iomap_alloc(ip, offset, length, 0, &imap);
 	} else {
@@ -1082,6 +1086,14 @@ alloc_done:
 	}
 
 	xfs_bmbt_to_iomap(ip, iomap, &imap);
+
+	/* optionally associate a dax device with the iomap bdev */
+	bdev = iomap->bdev;
+	if (blk_queue_dax(bdev->bd_queue))
+		iomap->dax_dev = fs_dax_get_by_host(bdev->bd_disk->disk_name);
+	else
+		iomap->dax_dev = NULL;
+
 	if (shared)
 		iomap->flags |= IOMAP_F_SHARED;
 	return 0;
@@ -1095,25 +1107,46 @@ xfs_file_iomap_end_delalloc(
 	struct xfs_inode	*ip,
 	loff_t			offset,
 	loff_t			length,
-	ssize_t			written)
+	ssize_t			written,
+	struct iomap		*iomap)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	xfs_fileoff_t		start_fsb;
 	xfs_fileoff_t		end_fsb;
 	int			error = 0;
 
-	start_fsb = XFS_B_TO_FSB(mp, offset + written);
+	/*
+	 * Behave as if the write failed if drop writes is enabled. Set the NEW
+	 * flag to force delalloc cleanup.
+	 */
+	if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_DROP_WRITES)) {
+		iomap->flags |= IOMAP_F_NEW;
+		written = 0;
+	}
+
+	/*
+	 * start_fsb refers to the first unused block after a short write. If
+	 * nothing was written, round offset down to point at the first block in
+	 * the range.
+	 */
+	if (unlikely(!written))
+		start_fsb = XFS_B_TO_FSBT(mp, offset);
+	else
+		start_fsb = XFS_B_TO_FSB(mp, offset + written);
 	end_fsb = XFS_B_TO_FSB(mp, offset + length);
 
 	/*
-	 * Trim back delalloc blocks if we didn't manage to write the whole
-	 * range reserved.
+	 * Trim delalloc blocks if they were allocated by this write and we
+	 * didn't manage to write the whole range.
 	 *
 	 * We don't need to care about racing delalloc as we hold i_mutex
 	 * across the reserve/allocate/unreserve calls. If there are delalloc
 	 * blocks in the range, they are ours.
 	 */
-	if (start_fsb < end_fsb) {
+	if ((iomap->flags & IOMAP_F_NEW) && start_fsb < end_fsb) {
+		truncate_pagecache_range(VFS_I(ip), XFS_FSB_TO_B(mp, start_fsb),
+					 XFS_FSB_TO_B(mp, end_fsb) - 1);
+
 		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		error = xfs_bmap_punch_delalloc_range(ip, start_fsb,
 					       end_fsb - start_fsb);
@@ -1138,13 +1171,14 @@ xfs_file_iomap_end(
 	unsigned		flags,
 	struct iomap		*iomap)
 {
+	fs_put_dax(iomap->dax_dev);
 	if ((flags & IOMAP_WRITE) && iomap->type == IOMAP_DELALLOC)
 		return xfs_file_iomap_end_delalloc(XFS_I(inode), offset,
-				length, written);
+				length, written, iomap);
 	return 0;
 }
 
-struct iomap_ops xfs_iomap_ops = {
+const struct iomap_ops xfs_iomap_ops = {
 	.iomap_begin		= xfs_file_iomap_begin,
 	.iomap_end		= xfs_file_iomap_end,
 };
@@ -1168,10 +1202,10 @@ xfs_xattr_iomap_begin(
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
 
-	lockmode = xfs_ilock_data_map_shared(ip);
+	lockmode = xfs_ilock_attr_map_shared(ip);
 
 	/* if there are no attribute fork or extents, return ENOENT */
-	if (XFS_IFORK_Q(ip) || !ip->i_d.di_anextents) {
+	if (!XFS_IFORK_Q(ip) || !ip->i_d.di_anextents) {
 		error = -ENOENT;
 		goto out_unlock;
 	}
@@ -1190,6 +1224,6 @@ out_unlock:
 	return error;
 }
 
-struct iomap_ops xfs_xattr_iomap_ops = {
+const struct iomap_ops xfs_xattr_iomap_ops = {
 	.iomap_begin		= xfs_xattr_iomap_begin,
 };