Merge tag 'xfs-fixes-for-linus-4.9-rc3' of...

Merge tag 'xfs-fixes-for-linus-4.9-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/dgc/linux-xfs

Pull xfs fixes from Dave Chinner:
 "This update contains fixes for most of the outstanding regressions
  introduced with the 4.9-rc1 XFS merge. There is also a fix for an
  iomap bug, too.

  This is a quite a bit larger than I'd prefer for a -rc3, but most of
  the change comes from cleaning up the new reflink copy on write code;
  it's much simpler and easier to understand now. These changes fixed
  several bugs in the new code, and it wasn't clear that there was an
  easier/simpler way to fix them. The rest of the fixes are the usual
  size you'd expect at this stage.

  I've left the commits to soak in linux-next for a some extra time
  because of the size before asking you to pull, no new problems with
  them have been reported so I think it's all OK.

  Summary:
   - iomap page offset masking fix for page faults
   - add IOMAP_REPORT to distinguish between read and fiemap map
     requests
   - cleanups to new shared data extent code
   - fix mount active status on failed log recovery
   - fix broken dquots in a buffer calculation
   - fix locking order issues and merge xfs_reflink_remap_range and
     xfs_file_share_range
   - rework unmapping of CoW extents and remove now unused functions
   - clean state when CoW is done"

* tag 'xfs-fixes-for-linus-4.9-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/dgc/linux-xfs: (25 commits)
  xfs: clear cowblocks tag when cow fork is emptied
  xfs: fix up inode cowblocks tracking tracepoints
  fs: Do to trim high file position bits in iomap_page_mkwrite_actor
  xfs: remove xfs_bunmapi_cow
  xfs: optimize xfs_reflink_end_cow
  xfs: optimize xfs_reflink_cancel_cow_blocks
  xfs: refactor xfs_bunmapi_cow
  xfs: optimize writes to reflink files
  xfs: don't bother looking at the refcount tree for reads
  xfs: handle "raw" delayed extents xfs_reflink_trim_around_shared
  xfs: add xfs_trim_extent
  iomap: add IOMAP_REPORT
  xfs: merge xfs_reflink_remap_range and xfs_file_share_range
  xfs: remove xfs_file_wait_for_io
  xfs: move inode locking from xfs_reflink_remap_range to xfs_file_share_range
  xfs: fix the same_inode check in xfs_file_share_range
  xfs: remove the same fs check from xfs_file_share_range
  libxfs: v3 inodes are only valid on crc-enabled filesystems
  libxfs: clean up _calc_dquots_per_chunk
  xfs: unset MS_ACTIVE if mount fails
  ...

fs/iomap.c

@@ -433,8 +433,7 @@ iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length,
 	struct page *page = data;
 	int ret;
 
-	ret = __block_write_begin_int(page, pos & ~PAGE_MASK, length,
-			NULL, iomap);
+	ret = __block_write_begin_int(page, pos, length, NULL, iomap);
 	if (ret)
 		return ret;
 
@@ -561,7 +560,7 @@ int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi,
 	}
 
 	while (len > 0) {
-		ret = iomap_apply(inode, start, len, 0, ops, &ctx,
+		ret = iomap_apply(inode, start, len, IOMAP_REPORT, ops, &ctx,
 				iomap_fiemap_actor);
 		/* inode with no (attribute) mapping will give ENOENT */
 		if (ret == -ENOENT)

fs/xfs/libxfs/xfs_bmap.h

@@ -190,6 +190,8 @@ void	xfs_bmap_trace_exlist(struct xfs_inode *ip, xfs_extnum_t cnt,
 #define	XFS_BMAP_TRACE_EXLIST(ip,c,w)
 #endif
 
+void	xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno,
+		xfs_filblks_t len);
 int	xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd);
 void	xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork);
 void	xfs_bmap_add_free(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
@@ -221,7 +223,11 @@ int	xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t bno, xfs_filblks_t len, int flags,
 		xfs_extnum_t nexts, xfs_fsblock_t *firstblock,
 		struct xfs_defer_ops *dfops, int *done);
-int	xfs_bunmapi_cow(struct xfs_inode *ip, struct xfs_bmbt_irec *del);
+int	xfs_bmap_del_extent_delay(struct xfs_inode *ip, int whichfork,
+		xfs_extnum_t *idx, struct xfs_bmbt_irec *got,
+		struct xfs_bmbt_irec *del);
+void	xfs_bmap_del_extent_cow(struct xfs_inode *ip, xfs_extnum_t *idx,
+		struct xfs_bmbt_irec *got, struct xfs_bmbt_irec *del);
 int	xfs_check_nostate_extents(struct xfs_ifork *ifp, xfs_extnum_t idx,
 		xfs_extnum_t num);
 uint	xfs_default_attroffset(struct xfs_inode *ip);

fs/xfs/libxfs/xfs_btree.c

@@ -4826,7 +4826,7 @@ xfs_btree_calc_size(
 	return rval;
 }
 
-int
+static int
 xfs_btree_count_blocks_helper(
 	struct xfs_btree_cur	*cur,
 	int			level,

fs/xfs/libxfs/xfs_dquot_buf.c

@@ -191,8 +191,7 @@ xfs_dquot_buf_verify_crc(
 	if (mp->m_quotainfo)
 		ndquots = mp->m_quotainfo->qi_dqperchunk;
 	else
-		ndquots = xfs_calc_dquots_per_chunk(
-					XFS_BB_TO_FSB(mp, bp->b_length));
+		ndquots = xfs_calc_dquots_per_chunk(bp->b_length);
 
 	for (i = 0; i < ndquots; i++, d++) {
 		if (!xfs_verify_cksum((char *)d, sizeof(struct xfs_dqblk),

fs/xfs/libxfs/xfs_format.h

@@ -865,7 +865,6 @@ typedef struct xfs_timestamp {
  * padding field for v3 inodes.
  */
 #define	XFS_DINODE_MAGIC		0x494e	/* 'IN' */
-#define XFS_DINODE_GOOD_VERSION(v)	((v) >= 1 && (v) <= 3)
 typedef struct xfs_dinode {
 	__be16		di_magic;	/* inode magic # = XFS_DINODE_MAGIC */
 	__be16		di_mode;	/* mode and type of file */

fs/xfs/libxfs/xfs_inode_buf.c

@@ -57,6 +57,17 @@ xfs_inobp_check(
 }
 #endif
 
+bool
+xfs_dinode_good_version(
+	struct xfs_mount *mp,
+	__u8		version)
+{
+	if (xfs_sb_version_hascrc(&mp->m_sb))
+		return version == 3;
+
+	return version == 1 || version == 2;
+}
+
 /*
  * If we are doing readahead on an inode buffer, we might be in log recovery
  * reading an inode allocation buffer that hasn't yet been replayed, and hence
@@ -91,7 +102,7 @@ xfs_inode_buf_verify(
 
 		dip = xfs_buf_offset(bp, (i << mp->m_sb.sb_inodelog));
 		di_ok = dip->di_magic == cpu_to_be16(XFS_DINODE_MAGIC) &&
-			    XFS_DINODE_GOOD_VERSION(dip->di_version);
+			xfs_dinode_good_version(mp, dip->di_version);
 		if (unlikely(XFS_TEST_ERROR(!di_ok, mp,
 						XFS_ERRTAG_ITOBP_INOTOBP,
 						XFS_RANDOM_ITOBP_INOTOBP))) {

fs/xfs/libxfs/xfs_inode_buf.h

@@ -74,6 +74,8 @@ void	xfs_inode_from_disk(struct xfs_inode *ip, struct xfs_dinode *from);
 void	xfs_log_dinode_to_disk(struct xfs_log_dinode *from,
 			       struct xfs_dinode *to);
 
+bool	xfs_dinode_good_version(struct xfs_mount *mp, __u8 version);
+
 #if defined(DEBUG)
 void	xfs_inobp_check(struct xfs_mount *, struct xfs_buf *);
 #else

fs/xfs/xfs_file.c

@@ -249,6 +249,7 @@ xfs_file_dio_aio_read(
 	struct xfs_inode	*ip = XFS_I(inode);
 	loff_t			isize = i_size_read(inode);
 	size_t			count = iov_iter_count(to);
+	loff_t			end = iocb->ki_pos + count - 1;
 	struct iov_iter		data;
 	struct xfs_buftarg	*target;
 	ssize_t			ret = 0;
@@ -272,50 +273,22 @@ xfs_file_dio_aio_read(
 
 	file_accessed(iocb->ki_filp);
 
-	/*
-	 * Locking is a bit tricky here. If we take an exclusive lock for direct
-	 * IO, we effectively serialise all new concurrent read IO to this file
-	 * and block it behind IO that is currently in progress because IO in
-	 * progress holds the IO lock shared. We only need to hold the lock
-	 * exclusive to blow away the page cache, so only take lock exclusively
-	 * if the page cache needs invalidation. This allows the normal direct
-	 * IO case of no page cache pages to proceeed concurrently without
-	 * serialisation.
-	 */
 	xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
 	if (mapping->nrpages) {
-		xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
-		xfs_rw_ilock(ip, XFS_IOLOCK_EXCL);
-
-		/*
-		 * The generic dio code only flushes the range of the particular
-		 * I/O. Because we take an exclusive lock here, this whole
-		 * sequence is considerably more expensive for us. This has a
-		 * noticeable performance impact for any file with cached pages,
-		 * even when outside of the range of the particular I/O.
-		 *
-		 * Hence, amortize the cost of the lock against a full file
-		 * flush and reduce the chances of repeated iolock cycles going
-		 * forward.
-		 */
-		if (mapping->nrpages) {
-			ret = filemap_write_and_wait(mapping);
-			if (ret) {
-				xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL);
-				return ret;
-			}
+		ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, end);
+		if (ret)
+			goto out_unlock;
 
 		/*
-			 * Invalidate whole pages. This can return an error if
-			 * we fail to invalidate a page, but this should never
-			 * happen on XFS. Warn if it does fail.
+		 * Invalidate whole pages. This can return an error if we fail
+		 * to invalidate a page, but this should never happen on XFS.
+		 * Warn if it does fail.
 		 */
-			ret = invalidate_inode_pages2(mapping);
+		ret = invalidate_inode_pages2_range(mapping,
+				iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT);
 		WARN_ON_ONCE(ret);
 		ret = 0;
 	}
-		xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
-	}
 
 	data = *to;
 	ret = __blockdev_direct_IO(iocb, inode, target->bt_bdev, &data,
@@ -324,8 +297,9 @@ xfs_file_dio_aio_read(
 		iocb->ki_pos += ret;
 		iov_iter_advance(to, ret);
 	}
-	xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
 
+out_unlock:
+	xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
 	return ret;
 }
 
@@ -570,34 +544,22 @@ xfs_file_dio_aio_write(
 	if ((iocb->ki_pos | count) & target->bt_logical_sectormask)
 		return -EINVAL;
 
-	/* "unaligned" here means not aligned to a filesystem block */
-	if ((iocb->ki_pos & mp->m_blockmask) ||
-	    ((iocb->ki_pos + count) & mp->m_blockmask))
-		unaligned_io = 1;
-
 	/*
-	 * We don't need to take an exclusive lock unless there page cache needs
-	 * to be invalidated or unaligned IO is being executed. We don't need to
-	 * consider the EOF extension case here because
-	 * xfs_file_aio_write_checks() will relock the inode as necessary for
-	 * EOF zeroing cases and fill out the new inode size as appropriate.
+	 * Don't take the exclusive iolock here unless the I/O is unaligned to
+	 * the file system block size.  We don't need to consider the EOF
+	 * extension case here because xfs_file_aio_write_checks() will relock
+	 * the inode as necessary for EOF zeroing cases and fill out the new
+	 * inode size as appropriate.
 	 */
-	if (unaligned_io || mapping->nrpages)
+	if ((iocb->ki_pos & mp->m_blockmask) ||
+	    ((iocb->ki_pos + count) & mp->m_blockmask)) {
+		unaligned_io = 1;
 		iolock = XFS_IOLOCK_EXCL;
-	else
+	} else {
 		iolock = XFS_IOLOCK_SHARED;
-	xfs_rw_ilock(ip, iolock);
+	}
 
-	/*
-	 * Recheck if there are cached pages that need invalidate after we got
-	 * the iolock to protect against other threads adding new pages while
-	 * we were waiting for the iolock.
-	 */
-	if (mapping->nrpages && iolock == XFS_IOLOCK_SHARED) {
-		xfs_rw_iunlock(ip, iolock);
-		iolock = XFS_IOLOCK_EXCL;
 	xfs_rw_ilock(ip, iolock);
-	}
 
 	ret = xfs_file_aio_write_checks(iocb, from, &iolock);
 	if (ret)
@@ -605,26 +567,26 @@ xfs_file_dio_aio_write(
 	count = iov_iter_count(from);
 	end = iocb->ki_pos + count - 1;
 
-	/*
-	 * See xfs_file_dio_aio_read() for why we do a full-file flush here.
-	 */
 	if (mapping->nrpages) {
-		ret = filemap_write_and_wait(VFS_I(ip)->i_mapping);
+		ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, end);
 		if (ret)
 			goto out;
+
 		/*
 		 * Invalidate whole pages. This can return an error if we fail
 		 * to invalidate a page, but this should never happen on XFS.
 		 * Warn if it does fail.
 		 */
-		ret = invalidate_inode_pages2(VFS_I(ip)->i_mapping);
+		ret = invalidate_inode_pages2_range(mapping,
+				iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT);
 		WARN_ON_ONCE(ret);
 		ret = 0;
 	}
 
 	/*
 	 * If we are doing unaligned IO, wait for all other IO to drain,
-	 * otherwise demote the lock if we had to flush cached pages
+	 * otherwise demote the lock if we had to take the exclusive lock
+	 * for other reasons in xfs_file_aio_write_checks.
 	 */
 	if (unaligned_io)
 		inode_dio_wait(inode);
@@ -947,134 +909,6 @@ xfs_file_fallocate(
 	return error;
 }
 
-/*
- * Flush all file writes out to disk.
- */
-static int
-xfs_file_wait_for_io(
-	struct inode	*inode,
-	loff_t		offset,
-	size_t		len)
-{
-	loff_t		rounding;
-	loff_t		ioffset;
-	loff_t		iendoffset;
-	loff_t		bs;
-	int		ret;
-
-	bs = inode->i_sb->s_blocksize;
-	inode_dio_wait(inode);
-
-	rounding = max_t(xfs_off_t, bs, PAGE_SIZE);
-	ioffset = round_down(offset, rounding);
-	iendoffset = round_up(offset + len, rounding) - 1;
-	ret = filemap_write_and_wait_range(inode->i_mapping, ioffset,
-					   iendoffset);
-	return ret;
-}
-
-/* Hook up to the VFS reflink function */
-STATIC int
-xfs_file_share_range(
-	struct file	*file_in,
-	loff_t		pos_in,
-	struct file	*file_out,
-	loff_t		pos_out,
-	u64		len,
-	bool		is_dedupe)
-{
-	struct inode	*inode_in;
-	struct inode	*inode_out;
-	ssize_t		ret;
-	loff_t		bs;
-	loff_t		isize;
-	int		same_inode;
-	loff_t		blen;
-	unsigned int	flags = 0;
-
-	inode_in = file_inode(file_in);
-	inode_out = file_inode(file_out);
-	bs = inode_out->i_sb->s_blocksize;
-
-	/* Don't touch certain kinds of inodes */
-	if (IS_IMMUTABLE(inode_out))
-		return -EPERM;
-	if (IS_SWAPFILE(inode_in) ||
-	    IS_SWAPFILE(inode_out))
-		return -ETXTBSY;
-
-	/* Reflink only works within this filesystem. */
-	if (inode_in->i_sb != inode_out->i_sb)
-		return -EXDEV;
-	same_inode = (inode_in->i_ino == inode_out->i_ino);
-
-	/* Don't reflink dirs, pipes, sockets... */
-	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
-		return -EISDIR;
-	if (S_ISFIFO(inode_in->i_mode) || S_ISFIFO(inode_out->i_mode))
-		return -EINVAL;
-	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
-		return -EINVAL;
-
-	/* Don't share DAX file data for now. */
-	if (IS_DAX(inode_in) || IS_DAX(inode_out))
-		return -EINVAL;
-
-	/* Are we going all the way to the end? */
-	isize = i_size_read(inode_in);
-	if (isize == 0)
-		return 0;
-	if (len == 0)
-		len = isize - pos_in;
-
-	/* Ensure offsets don't wrap and the input is inside i_size */
-	if (pos_in + len < pos_in || pos_out + len < pos_out ||
-	    pos_in + len > isize)
-		return -EINVAL;
-
-	/* Don't allow dedupe past EOF in the dest file */
-	if (is_dedupe) {
-		loff_t	disize;
-
-		disize = i_size_read(inode_out);
-		if (pos_out >= disize || pos_out + len > disize)
-			return -EINVAL;
-	}
-
-	/* If we're linking to EOF, continue to the block boundary. */
-	if (pos_in + len == isize)
-		blen = ALIGN(isize, bs) - pos_in;
-	else
-		blen = len;
-
-	/* Only reflink if we're aligned to block boundaries */
-	if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_in + blen, bs) ||
-	    !IS_ALIGNED(pos_out, bs) || !IS_ALIGNED(pos_out + blen, bs))
-		return -EINVAL;
-
-	/* Don't allow overlapped reflink within the same file */
-	if (same_inode && pos_out + blen > pos_in && pos_out < pos_in + blen)
-		return -EINVAL;
-
-	/* Wait for the completion of any pending IOs on srcfile */
-	ret = xfs_file_wait_for_io(inode_in, pos_in, len);
-	if (ret)
-		goto out;
-	ret = xfs_file_wait_for_io(inode_out, pos_out, len);
-	if (ret)
-		goto out;
-
-	if (is_dedupe)
-		flags |= XFS_REFLINK_DEDUPE;
-	ret = xfs_reflink_remap_range(XFS_I(inode_in), pos_in, XFS_I(inode_out),
-			pos_out, len, flags);
-	if (ret < 0)
-		goto out;
-
-out:
-	return ret;
-}
-
 STATIC ssize_t
 xfs_file_copy_range(
 	struct file	*file_in,
@@ -1086,7 +920,7 @@ xfs_file_copy_range(
 {
 	int		error;
 
-	error = xfs_file_share_range(file_in, pos_in, file_out, pos_out,
+	error = xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out,
 				     len, false);
 	if (error)
 		return error;
@@ -1101,7 +935,7 @@ xfs_file_clone_range(
 	loff_t		pos_out,
 	u64		len)
 {
-	return xfs_file_share_range(file_in, pos_in, file_out, pos_out,
+	return xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out,
 				     len, false);
 }
 
@@ -1124,7 +958,7 @@ xfs_file_dedupe_range(
 	if (len > XFS_MAX_DEDUPE_LEN)
 		len = XFS_MAX_DEDUPE_LEN;
 
-	error = xfs_file_share_range(src_file, loff, dst_file, dst_loff,
+	error = xfs_reflink_remap_range(src_file, loff, dst_file, dst_loff,
 				     len, true);
 	if (error)
 		return error;

fs/xfs/xfs_icache.c

@@ -1656,9 +1656,9 @@ void
 xfs_inode_set_cowblocks_tag(
 	xfs_inode_t	*ip)
 {
-	trace_xfs_inode_set_eofblocks_tag(ip);
+	trace_xfs_inode_set_cowblocks_tag(ip);
 	return __xfs_inode_set_eofblocks_tag(ip, xfs_queue_cowblocks,
-			trace_xfs_perag_set_eofblocks,
+			trace_xfs_perag_set_cowblocks,
 			XFS_ICI_COWBLOCKS_TAG);
 }
 
@@ -1666,7 +1666,7 @@ void
 xfs_inode_clear_cowblocks_tag(
 	xfs_inode_t	*ip)
 {
-	trace_xfs_inode_clear_eofblocks_tag(ip);
+	trace_xfs_inode_clear_cowblocks_tag(ip);
 	return __xfs_inode_clear_eofblocks_tag(ip,
-			trace_xfs_perag_clear_eofblocks, XFS_ICI_COWBLOCKS_TAG);
+			trace_xfs_perag_clear_cowblocks, XFS_ICI_COWBLOCKS_TAG);
 }

fs/xfs/xfs_iomap.c

@@ -566,6 +566,17 @@ xfs_file_iomap_begin_delay(
 	xfs_bmap_search_extents(ip, offset_fsb, XFS_DATA_FORK, &eof, &idx,
 			&got, &prev);
 	if (!eof && got.br_startoff <= offset_fsb) {
+		if (xfs_is_reflink_inode(ip)) {
+			bool		shared;
+
+			end_fsb = min(XFS_B_TO_FSB(mp, offset + count),
+					maxbytes_fsb);
+			xfs_trim_extent(&got, offset_fsb, end_fsb - offset_fsb);
+			error = xfs_reflink_reserve_cow(ip, &got, &shared);
+			if (error)
+				goto out_unlock;
+		}
+
 		trace_xfs_iomap_found(ip, offset, count, 0, &got);
 		goto done;
 	}
@@ -961,19 +972,13 @@ xfs_file_iomap_begin(
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_bmbt_irec	imap;
 	xfs_fileoff_t		offset_fsb, end_fsb;
-	bool			shared, trimmed;
 	int			nimaps = 1, error = 0;
+	bool			shared = false, trimmed = false;
 	unsigned		lockmode;
 
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
 
-	if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) {
-		error = xfs_reflink_reserve_cow_range(ip, offset, length);
-		if (error < 0)
-			return error;
-	}
-
 	if ((flags & IOMAP_WRITE) && !IS_DAX(inode) &&
 		   !xfs_get_extsz_hint(ip)) {
 		/* Reserve delalloc blocks for regular writeback. */
@@ -981,7 +986,16 @@ xfs_file_iomap_begin(
 				iomap);
 	}
 
+	/*
+	 * COW writes will allocate delalloc space, so we need to make sure
+	 * to take the lock exclusively here.
+	 */
+	if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) {
+		lockmode = XFS_ILOCK_EXCL;
+		xfs_ilock(ip, XFS_ILOCK_EXCL);
+	} else {
 		lockmode = xfs_ilock_data_map_shared(ip);
+	}
 
 	ASSERT(offset <= mp->m_super->s_maxbytes);
 	if ((xfs_fsize_t)offset + length > mp->m_super->s_maxbytes)
@@ -991,16 +1005,24 @@ xfs_file_iomap_begin(
 
 	error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap,
 			       &nimaps, 0);
-	if (error) {
-		xfs_iunlock(ip, lockmode);
-		return error;
-	}
+	if (error)
+		goto out_unlock;
 
+	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) {
-		xfs_iunlock(ip, lockmode);
-		return error;
+		error = xfs_reflink_trim_around_shared(ip, &imap, &shared,
+				&trimmed);
+		if (error)
+			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;
+
+		end_fsb = imap.br_startoff + imap.br_blockcount;
+		length = XFS_FSB_TO_B(mp, end_fsb) - offset;
 	}
 
 	if ((flags & IOMAP_WRITE) && imap_needs_alloc(inode, &imap, nimaps)) {
@@ -1039,6 +1061,9 @@ xfs_file_iomap_begin(
 	if (shared)
 		iomap->flags |= IOMAP_F_SHARED;
 	return 0;
+out_unlock:
+	xfs_iunlock(ip, lockmode);
+	return error;
 }
 
 static int

fs/xfs/xfs_mount.c

@@ -1009,6 +1009,7 @@ xfs_mountfs(
  out_quota:
 	xfs_qm_unmount_quotas(mp);
  out_rtunmount:
+	mp->m_super->s_flags &= ~MS_ACTIVE;
 	xfs_rtunmount_inodes(mp);
  out_rele_rip:
 	IRELE(rip);

fs/xfs/xfs_reflink.h

@@ -26,8 +26,8 @@ extern int xfs_reflink_find_shared(struct xfs_mount *mp, xfs_agnumber_t agno,
 extern int xfs_reflink_trim_around_shared(struct xfs_inode *ip,
 		struct xfs_bmbt_irec *irec, bool *shared, bool *trimmed);
 
-extern int xfs_reflink_reserve_cow_range(struct xfs_inode *ip,
-		xfs_off_t offset, xfs_off_t count);
+extern int xfs_reflink_reserve_cow(struct xfs_inode *ip,
+		struct xfs_bmbt_irec *imap, bool *shared);
 extern int xfs_reflink_allocate_cow_range(struct xfs_inode *ip,
 		xfs_off_t offset, xfs_off_t count);
 extern bool xfs_reflink_find_cow_mapping(struct xfs_inode *ip, xfs_off_t offset,
@@ -43,11 +43,8 @@ extern int xfs_reflink_cancel_cow_range(struct xfs_inode *ip, xfs_off_t offset,
 extern int xfs_reflink_end_cow(struct xfs_inode *ip, xfs_off_t offset,
 		xfs_off_t count);
 extern int xfs_reflink_recover_cow(struct xfs_mount *mp);
-#define XFS_REFLINK_DEDUPE	1	/* only reflink if contents match */
-#define XFS_REFLINK_ALL		(XFS_REFLINK_DEDUPE)
-extern int xfs_reflink_remap_range(struct xfs_inode *src, xfs_off_t srcoff,
-		struct xfs_inode *dest, xfs_off_t destoff, xfs_off_t len,
-		unsigned int flags);
+extern int xfs_reflink_remap_range(struct file *file_in, loff_t pos_in,
+		struct file *file_out, loff_t pos_out, u64 len, bool is_dedupe);
 extern int xfs_reflink_clear_inode_flag(struct xfs_inode *ip,
 		struct xfs_trans **tpp);
 extern int xfs_reflink_unshare(struct xfs_inode *ip, xfs_off_t offset,

fs/xfs/xfs_sysfs.c

@@ -512,13 +512,13 @@ static struct attribute *xfs_error_attrs[] = {
 };
 
 
-struct kobj_type xfs_error_cfg_ktype = {
+static struct kobj_type xfs_error_cfg_ktype = {
 	.release = xfs_sysfs_release,
 	.sysfs_ops = &xfs_sysfs_ops,
 	.default_attrs = xfs_error_attrs,
 };
 
-struct kobj_type xfs_error_ktype = {
+static struct kobj_type xfs_error_ktype = {
 	.release = xfs_sysfs_release,
 	.sysfs_ops = &xfs_sysfs_ops,
 };

fs/xfs/xfs_trace.h

@@ -3346,7 +3346,7 @@ DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_alloc);
 DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_found);
 DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_enospc);
 
-DEFINE_RW_EVENT(xfs_reflink_reserve_cow_range);
+DEFINE_RW_EVENT(xfs_reflink_reserve_cow);
 DEFINE_RW_EVENT(xfs_reflink_allocate_cow_range);
 
 DEFINE_INODE_IREC_EVENT(xfs_reflink_bounce_dio_write);
@@ -3356,9 +3356,7 @@ DEFINE_INODE_IREC_EVENT(xfs_reflink_trim_irec);
 DEFINE_SIMPLE_IO_EVENT(xfs_reflink_cancel_cow_range);
 DEFINE_SIMPLE_IO_EVENT(xfs_reflink_end_cow);
 DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap);
-DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap_piece);
 
-DEFINE_INODE_ERROR_EVENT(xfs_reflink_reserve_cow_range_error);
 DEFINE_INODE_ERROR_EVENT(xfs_reflink_allocate_cow_range_error);
 DEFINE_INODE_ERROR_EVENT(xfs_reflink_cancel_cow_range_error);
 DEFINE_INODE_ERROR_EVENT(xfs_reflink_end_cow_error);

include/linux/iomap.h

@@ -19,11 +19,15 @@ struct vm_fault;
 #define IOMAP_UNWRITTEN	0x04	/* blocks allocated @blkno in unwritten state */
 
 /*
- * Flags for iomap mappings:
+ * Flags for all iomap mappings:
  */
-#define IOMAP_F_MERGED	0x01	/* contains multiple blocks/extents */
-#define IOMAP_F_SHARED	0x02	/* block shared with another file */
-#define IOMAP_F_NEW	0x04	/* blocks have been newly allocated */
+#define IOMAP_F_NEW	0x01	/* blocks have been newly allocated */
+
+/*
+ * Flags that only need to be reported for IOMAP_REPORT requests:
+ */
+#define IOMAP_F_MERGED	0x10	/* contains multiple blocks/extents */
+#define IOMAP_F_SHARED	0x20	/* block shared with another file */
 
 /*
  * Magic value for blkno:
@@ -42,8 +46,9 @@ struct iomap {
 /*
  * Flags for iomap_begin / iomap_end.  No flag implies a read.
  */
-#define IOMAP_WRITE		(1 << 0)
-#define IOMAP_ZERO		(1 << 1)
+#define IOMAP_WRITE		(1 << 0) /* writing, must allocate blocks */
+#define IOMAP_ZERO		(1 << 1) /* zeroing operation, may skip holes */
+#define IOMAP_REPORT		(1 << 2) /* report extent status, e.g. FIEMAP */
 
 struct iomap_ops {
 	/*