Merge tag 'xfs-5.1-merge-4' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull xfs updates from Darrick Wong:
 "Here are a number of new features and bug fixes for 5.1

  They've undergone a week's worth of fstesting and merge cleanly with
  master as of this morning

  Most of the changes center on improving metadata validation and fixing
  problems with online fsck, though there's also a new cache to speed up
  unlinked inode handling and cleanup of the copy on write code in
  preparation for future features

  Changes for Linux 5.1:

   - Fix online fsck to handle inode btrees correctly on 64k block
     filesystems

   - Teach online fsck to check directory and attribute names for
     invalid characters

   - Miscellanous fixes for online fsck

   - Introduce a new panic mask so that we can halt immediately on
     metadata corruption (for debugging purposes)

   - Fix a block mapping race during writeback

   - Cache unlinked inode list backrefs in memory to speed up list
     processing

   - Separate the bnobt/cntbt and inobt/finobt buffer verifiers so that
     we can detect crosslinked btrees

   - Refactor magic number verification so that we can standardize it

   - Strengthen ondisk metadata structure offset build time verification

   - Fix a memory corruption problem in the listxattr code

   - Fix a shutdown problem during log recovery due to unreserved finobt
     expansion

   - Fix a referential integrity problem where O_TMPFILE inodes were put
     on the unlinked list with nlink > 0 which would cause asserts
     during log recovery if the system went down immediately

   - Refactor the delayed allocation allocator to be more clever about
     the possibility that its mapping might be stale

   - Various fixes to the copy on write mechanism

   - Make CoW preallocation suitable for use even with writes that
     wouldn't otherwise require it

   - Refactor an internal API

   - Fix some statx implementation bugs

   - Fix miscellaneous compiler and static checker complaints"

* tag 'xfs-5.1-merge-4' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (70 commits)
  xfs: fix reporting supported extra file attributes for statx()
  xfs: fix backwards endian conversion in scrub
  xfs: fix uninitialized error variables
  xfs: rework breaking of shared extents in xfs_file_iomap_begin
  xfs: don't pass iomap flags to xfs_reflink_allocate_cow
  xfs: fix uninitialized error variable
  xfs: introduce an always_cow mode
  xfs: report IOMAP_F_SHARED from xfs_file_iomap_begin_delay
  xfs: make COW fork unwritten extent conversions more robust
  xfs: merge COW handling into xfs_file_iomap_begin_delay
  xfs: also truncate holes covered by COW blocks
  xfs: don't use delalloc extents for COW on files with extsize hints
  xfs: fix SEEK_DATA for speculative COW fork preallocation
  xfs: make xfs_bmbt_to_iomap more useful
  xfs: fix xfs_buf magic number endian checks
  xfs: retry COW fork delalloc conversion when no extent was found
  xfs: remove the truncate short cut in xfs_map_blocks
  xfs: move xfs_iomap_write_allocate to xfs_aops.c
  xfs: move stat accounting to xfs_bmapi_convert_delalloc
  xfs: move transaction handling to xfs_bmapi_convert_delalloc
  ..

1 files changed, 63 insertions, 87 deletions

diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index c5b4fa004ca4..680ae7662a78 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -192,7 +192,7 @@ xfs_reflink_trim_around_shared(
 	int			error = 0;
 
 	/* Holes, unwritten, and delalloc extents cannot be shared */
-	if (!xfs_is_reflink_inode(ip) || !xfs_bmap_is_real_extent(irec)) {
+	if (!xfs_is_cow_inode(ip) || !xfs_bmap_is_real_extent(irec)) {
 		*shared = false;
 		return 0;
 	}
@@ -234,93 +234,59 @@ xfs_reflink_trim_around_shared(
 	}
 }
 
-/*
- * Trim the passed in imap to the next shared/unshared extent boundary, and
- * if imap->br_startoff points to a shared extent reserve space for it in the
- * COW fork.
- *
- * Note that imap will always contain the block numbers for the existing blocks
- * in the data fork, as the upper layers need them for read-modify-write
- * operations.
- */
-int
-xfs_reflink_reserve_cow(
+bool
+xfs_inode_need_cow(
 	struct xfs_inode	*ip,
-	struct xfs_bmbt_irec	*imap)
+	struct xfs_bmbt_irec	*imap,
+	bool			*shared)
 {
-	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
-	struct xfs_bmbt_irec	got;
-	int			error = 0;
-	bool			eof = false;
-	struct xfs_iext_cursor	icur;
-	bool			shared;
-
-	/*
-	 * Search the COW fork extent list first.  This serves two purposes:
-	 * first this implement the speculative preallocation using cowextisze,
-	 * so that we also unshared block adjacent to shared blocks instead
-	 * of just the shared blocks themselves.  Second the lookup in the
-	 * extent list is generally faster than going out to the shared extent
-	 * tree.
-	 */
-
-	if (!xfs_iext_lookup_extent(ip, ifp, imap->br_startoff, &icur, &got))
-		eof = true;
-	if (!eof && got.br_startoff <= imap->br_startoff) {
-		trace_xfs_reflink_cow_found(ip, imap);
-		xfs_trim_extent(imap, got.br_startoff, got.br_blockcount);
+	/* We can't update any real extents in always COW mode. */
+	if (xfs_is_always_cow_inode(ip) &&
+	    !isnullstartblock(imap->br_startblock)) {
+		*shared = true;
 		return 0;
 	}
 
 	/* Trim the mapping to the nearest shared extent boundary. */
-	error = xfs_reflink_trim_around_shared(ip, imap, &shared);
-	if (error)
-		return error;
-
-	/* Not shared?  Just report the (potentially capped) extent. */
-	if (!shared)
-		return 0;
-
-	/*
-	 * Fork all the shared blocks from our write offset until the end of
-	 * the extent.
-	 */
-	error = xfs_qm_dqattach_locked(ip, false);
-	if (error)
-		return error;
-
-	error = xfs_bmapi_reserve_delalloc(ip, XFS_COW_FORK, imap->br_startoff,
-			imap->br_blockcount, 0, &got, &icur, eof);
-	if (error == -ENOSPC || error == -EDQUOT)
-		trace_xfs_reflink_cow_enospc(ip, imap);
-	if (error)
-		return error;
-
-	xfs_trim_extent(imap, got.br_startoff, got.br_blockcount);
-	trace_xfs_reflink_cow_alloc(ip, &got);
-	return 0;
+	return xfs_reflink_trim_around_shared(ip, imap, shared);
 }
 
-/* Convert part of an unwritten CoW extent to a real one. */
-STATIC int
-xfs_reflink_convert_cow_extent(
-	struct xfs_inode		*ip,
-	struct xfs_bmbt_irec		*imap,
-	xfs_fileoff_t			offset_fsb,
-	xfs_filblks_t			count_fsb)
+static int
+xfs_reflink_convert_cow_locked(
+	struct xfs_inode	*ip,
+	xfs_fileoff_t		offset_fsb,
+	xfs_filblks_t		count_fsb)
 {
-	int				nimaps = 1;
+	struct xfs_iext_cursor	icur;
+	struct xfs_bmbt_irec	got;
+	struct xfs_btree_cur	*dummy_cur = NULL;
+	int			dummy_logflags;
+	int			error = 0;
 
-	if (imap->br_state == XFS_EXT_NORM)
+	if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &got))
 		return 0;
 
-	xfs_trim_extent(imap, offset_fsb, count_fsb);
-	trace_xfs_reflink_convert_cow(ip, imap);
-	if (imap->br_blockcount == 0)
-		return 0;
-	return xfs_bmapi_write(NULL, ip, imap->br_startoff, imap->br_blockcount,
-			XFS_BMAPI_COWFORK | XFS_BMAPI_CONVERT, 0, imap,
-			&nimaps);
+	do {
+		if (got.br_startoff >= offset_fsb + count_fsb)
+			break;
+		if (got.br_state == XFS_EXT_NORM)
+			continue;
+		if (WARN_ON_ONCE(isnullstartblock(got.br_startblock)))
+			return -EIO;
+
+		xfs_trim_extent(&got, offset_fsb, count_fsb);
+		if (!got.br_blockcount)
+			continue;
+
+		got.br_state = XFS_EXT_NORM;
+		error = xfs_bmap_add_extent_unwritten_real(NULL, ip,
+				XFS_COW_FORK, &icur, &dummy_cur, &got,
+				&dummy_logflags);
+		if (error)
+			return error;
+	} while (xfs_iext_next_extent(ip->i_cowfp, &icur, &got));
+
+	return error;
 }
 
 /* Convert all of the unwritten CoW extents in a file's range to real ones. */
@@ -334,15 +300,12 @@ xfs_reflink_convert_cow(
 	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset);
 	xfs_fileoff_t		end_fsb = XFS_B_TO_FSB(mp, offset + count);
 	xfs_filblks_t		count_fsb = end_fsb - offset_fsb;
-	struct xfs_bmbt_irec	imap;
-	int			nimaps = 1, error = 0;
+	int			error;
 
 	ASSERT(count != 0);
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	error = xfs_bmapi_write(NULL, ip, offset_fsb, count_fsb,
-			XFS_BMAPI_COWFORK | XFS_BMAPI_CONVERT |
-			XFS_BMAPI_CONVERT_ONLY, 0, &imap, &nimaps);
+	error = xfs_reflink_convert_cow_locked(ip, offset_fsb, count_fsb);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
 }
@@ -375,7 +338,7 @@ xfs_find_trim_cow_extent(
 	if (got.br_startoff > offset_fsb) {
 		xfs_trim_extent(imap, imap->br_startoff,
 				got.br_startoff - imap->br_startoff);
-		return xfs_reflink_trim_around_shared(ip, imap, shared);
+		return xfs_inode_need_cow(ip, imap, shared);
 	}
 
 	*shared = true;
@@ -397,7 +360,8 @@ xfs_reflink_allocate_cow(
 	struct xfs_inode	*ip,
 	struct xfs_bmbt_irec	*imap,
 	bool			*shared,
-	uint			*lockmode)
+	uint			*lockmode,
+	bool			convert_now)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	xfs_fileoff_t		offset_fsb = imap->br_startoff;
@@ -409,7 +373,10 @@ xfs_reflink_allocate_cow(
 	xfs_extlen_t		resblks = 0;
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
-	ASSERT(xfs_is_reflink_inode(ip));
+	if (!ip->i_cowfp) {
+		ASSERT(!xfs_is_reflink_inode(ip));
+		xfs_ifork_init_cow(ip);
+	}
 
 	error = xfs_find_trim_cow_extent(ip, imap, shared, &found);
 	if (error || !*shared)
@@ -471,7 +438,16 @@ xfs_reflink_allocate_cow(
 	if (nimaps == 0)
 		return -ENOSPC;
 convert:
-	return xfs_reflink_convert_cow_extent(ip, imap, offset_fsb, count_fsb);
+	xfs_trim_extent(imap, 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 || imap->br_state == XFS_EXT_NORM)
+		return 0;
+	trace_xfs_reflink_convert_cow(ip, imap);
+	return xfs_reflink_convert_cow_locked(ip, offset_fsb, count_fsb);
 
 out_unreserve:
 	xfs_trans_unreserve_quota_nblks(tp, ip, (long)resblks, 0,
@@ -586,7 +562,7 @@ xfs_reflink_cancel_cow_range(
 	int			error;
 
 	trace_xfs_reflink_cancel_cow_range(ip, offset, count);
-	ASSERT(xfs_is_reflink_inode(ip));
+	ASSERT(ip->i_cowfp);
 
 	offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
 	if (count == NULLFILEOFF)
@@ -1192,7 +1168,7 @@ xfs_reflink_remap_blocks(
 			break;
 		ASSERT(nimaps == 1);
 
-		trace_xfs_reflink_remap_imap(src, srcoff, len, XFS_IO_OVERWRITE,
+		trace_xfs_reflink_remap_imap(src, srcoff, len, XFS_DATA_FORK,
 				&imap);
 
 		/* Translate imap into the destination file. */