Merge tag 'xfs-5.5-merge-16' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull XFS updates from Darrick Wong:
 "For this release, we changed quite a few things.

  Highlights:

   - Fixed some long tail latency problems in the block allocator

   - Removed some long deprecated (and for the past several years no-op)
     mount options and ioctls

   - Strengthened the extended attribute and directory verifiers

   - Audited and fixed all the places where we could return EFSCORRUPTED
     without logging anything

   - Refactored the old SGI space allocation ioctls to make the
     equivalent fallocate calls

   - Fixed a race between fallocate and directio

   - Fixed an integer overflow when files have more than a few
     billion(!) extents

   - Fixed a longstanding bug where quota accounting could be incorrect
     when performing unwritten extent conversion on a freshly mounted fs

   - Fixed various complaints in scrub about soft lockups and
     unresponsiveness to signals

   - De-vtable'd the directory handling code, which should make it
     faster

   - Converted to the new mount api, for better or for worse

   - Cleaned up some memory leaks

  and quite a lot of other smaller fixes and cleanups.

  A more detailed summary:

   - Fill out the build string

   - Prevent inode fork extent count overflows

   - Refactor the allocator to reduce long tail latency

   - Rework incore log locking a little to reduce spinning

   - Break up the xfs_iomap_begin functions into smaller more cohesive
     parts

   - Fix allocation alignment being dropped too early when the
     allocation request is for more blocks than an AG is large

   - Other small cleanups

   - Clean up file buftarg retrieval helpers

   - Hoist the resvsp and unresvsp ioctls to the vfs

   - Remove the undocumented biosize mount option, since it has never
     been mentioned as existing or supported on linux

   - Clean up some of the mount option printing and parsing

   - Enhance attr leaf verifier to check block structure

   - Check dirent and attr names for invalid characters before passing
     them to the vfs

   - Refactor open-coded bmbt walking

   - Fix a few places where we return EIO instead of EFSCORRUPTED after
     failing metadata sanity checks

   - Fix a synchronization problem between fallocate and aio dio
     corrupting the file length

   - Clean up various loose ends in the iomap and bmap code

   - Convert to the new mount api

   - Make sure we always log something when returning EFSCORRUPTED

   - Fix some problems where long running scrub loops could trigger soft
     lockup warnings and/or fail to exit due to fatal signals pending

   - Fix various Coverity complaints

   - Remove most of the function pointers from the directory code to
     reduce indirection penalties

   - Ensure that dquots are attached to the inode when performing
     unwritten extent conversion after io

   - Deuglify incore projid and crtime types

   - Fix another AGI/AGF locking order deadlock when renaming

   - Clean up some quota typedefs

   - Remove the FSSETDM ioctls which haven't done anything in 20 years

   - Fix some memory leaks when mounting the log fails

   - Fix an underflow when updating an xattr leaf freemap

   - Remove some trivial wrappers

   - Report metadata corruption as an error, not a (potentially) fatal
     assertion

   - Clean up the dir/attr buffer mapping code

   - Allow fatal signals to kill scrub during parent pointer checks"

* tag 'xfs-5.5-merge-16' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (198 commits)
  xfs: allow parent directory scans to be interrupted with fatal signals
  xfs: remove the mappedbno argument to xfs_da_get_buf
  xfs: remove the mappedbno argument to xfs_da_read_buf
  xfs: split xfs_da3_node_read
  xfs: remove the mappedbno argument to xfs_dir3_leafn_read
  xfs: remove the mappedbno argument to xfs_dir3_leaf_read
  xfs: remove the mappedbno argument to xfs_attr3_leaf_read
  xfs: remove the mappedbno argument to xfs_da_reada_buf
  xfs: improve the xfs_dabuf_map calling conventions
  xfs: refactor xfs_dabuf_map
  xfs: simplify mappedbno handling in xfs_da_{get,read}_buf
  xfs: report corruption only as a regular error
  xfs: Remove kmem_zone_free() wrapper
  xfs: Remove kmem_zone_destroy() wrapper
  xfs: Remove slab init wrappers
  xfs: fix attr leaf header freemap.size underflow
  xfs: fix some memory leaks in log recovery
  xfs: fix another missing include
  xfs: remove XFS_IOC_FSSETDM and XFS_IOC_FSSETDM_BY_HANDLE
  xfs: remove duplicated include from xfs_dir2_data.c
  ...

1 files changed, 41 insertions, 214 deletions

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 4f443703065e..2efd78a9719e 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -53,15 +53,16 @@ xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb)
  */
 int
 xfs_zero_extent(
-	struct xfs_inode *ip,
-	xfs_fsblock_t	start_fsb,
-	xfs_off_t	count_fsb)
+	struct xfs_inode	*ip,
+	xfs_fsblock_t		start_fsb,
+	xfs_off_t		count_fsb)
 {
-	struct xfs_mount *mp = ip->i_mount;
-	xfs_daddr_t	sector = xfs_fsb_to_db(ip, start_fsb);
-	sector_t	block = XFS_BB_TO_FSBT(mp, sector);
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_buftarg	*target = xfs_inode_buftarg(ip);
+	xfs_daddr_t		sector = xfs_fsb_to_db(ip, start_fsb);
+	sector_t		block = XFS_BB_TO_FSBT(mp, sector);
 
-	return blkdev_issue_zeroout(xfs_find_bdev_for_inode(VFS_I(ip)),
+	return blkdev_issue_zeroout(target->bt_bdev,
 		block << (mp->m_super->s_blocksize_bits - 9),
 		count_fsb << (mp->m_super->s_blocksize_bits - 9),
 		GFP_NOFS, 0);
@@ -164,13 +165,6 @@ xfs_bmap_rtalloc(
 		xfs_trans_mod_dquot_byino(ap->tp, ap->ip,
 			ap->wasdel ? XFS_TRANS_DQ_DELRTBCOUNT :
 					XFS_TRANS_DQ_RTBCOUNT, (long) ralen);
-
-		/* Zero the extent if we were asked to do so */
-		if (ap->datatype & XFS_ALLOC_USERDATA_ZERO) {
-			error = xfs_zero_extent(ap->ip, ap->blkno, ap->length);
-			if (error)
-				return error;
-		}
 	} else {
 		ap->length = 0;
 	}
@@ -179,29 +173,6 @@ xfs_bmap_rtalloc(
 #endif /* CONFIG_XFS_RT */
 
 /*
- * Check if the endoff is outside the last extent. If so the caller will grow
- * the allocation to a stripe unit boundary.  All offsets are considered outside
- * the end of file for an empty fork, so 1 is returned in *eof in that case.
- */
-int
-xfs_bmap_eof(
-	struct xfs_inode	*ip,
-	xfs_fileoff_t		endoff,
-	int			whichfork,
-	int			*eof)
-{
-	struct xfs_bmbt_irec	rec;
-	int			error;
-
-	error = xfs_bmap_last_extent(NULL, ip, whichfork, &rec, eof);
-	if (error || *eof)
-		return error;
-
-	*eof = endoff >= rec.br_startoff + rec.br_blockcount;
-	return 0;
-}
-
-/*
  * Extent tree block counting routines.
  */
 
@@ -229,106 +200,6 @@ xfs_bmap_count_leaves(
 }
 
 /*
- * Count leaf blocks given a range of extent records originally
- * in btree format.
- */
-STATIC void
-xfs_bmap_disk_count_leaves(
-	struct xfs_mount	*mp,
-	struct xfs_btree_block	*block,
-	int			numrecs,
-	xfs_filblks_t		*count)
-{
-	int		b;
-	xfs_bmbt_rec_t	*frp;
-
-	for (b = 1; b <= numrecs; b++) {
-		frp = XFS_BMBT_REC_ADDR(mp, block, b);
-		*count += xfs_bmbt_disk_get_blockcount(frp);
-	}
-}
-
-/*
- * Recursively walks each level of a btree
- * to count total fsblocks in use.
- */
-STATIC int
-xfs_bmap_count_tree(
-	struct xfs_mount	*mp,
-	struct xfs_trans	*tp,
-	struct xfs_ifork	*ifp,
-	xfs_fsblock_t		blockno,
-	int			levelin,
-	xfs_extnum_t		*nextents,
-	xfs_filblks_t		*count)
-{
-	int			error;
-	struct xfs_buf		*bp, *nbp;
-	int			level = levelin;
-	__be64			*pp;
-	xfs_fsblock_t           bno = blockno;
-	xfs_fsblock_t		nextbno;
-	struct xfs_btree_block	*block, *nextblock;
-	int			numrecs;
-
-	error = xfs_btree_read_bufl(mp, tp, bno, &bp, XFS_BMAP_BTREE_REF,
-						&xfs_bmbt_buf_ops);
-	if (error)
-		return error;
-	*count += 1;
-	block = XFS_BUF_TO_BLOCK(bp);
-
-	if (--level) {
-		/* Not at node above leaves, count this level of nodes */
-		nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib);
-		while (nextbno != NULLFSBLOCK) {
-			error = xfs_btree_read_bufl(mp, tp, nextbno, &nbp,
-						XFS_BMAP_BTREE_REF,
-						&xfs_bmbt_buf_ops);
-			if (error)
-				return error;
-			*count += 1;
-			nextblock = XFS_BUF_TO_BLOCK(nbp);
-			nextbno = be64_to_cpu(nextblock->bb_u.l.bb_rightsib);
-			xfs_trans_brelse(tp, nbp);
-		}
-
-		/* Dive to the next level */
-		pp = XFS_BMBT_PTR_ADDR(mp, block, 1, mp->m_bmap_dmxr[1]);
-		bno = be64_to_cpu(*pp);
-		error = xfs_bmap_count_tree(mp, tp, ifp, bno, level, nextents,
-				count);
-		if (error) {
-			xfs_trans_brelse(tp, bp);
-			XFS_ERROR_REPORT("xfs_bmap_count_tree(1)",
-					 XFS_ERRLEVEL_LOW, mp);
-			return -EFSCORRUPTED;
-		}
-		xfs_trans_brelse(tp, bp);
-	} else {
-		/* count all level 1 nodes and their leaves */
-		for (;;) {
-			nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib);
-			numrecs = be16_to_cpu(block->bb_numrecs);
-			(*nextents) += numrecs;
-			xfs_bmap_disk_count_leaves(mp, block, numrecs, count);
-			xfs_trans_brelse(tp, bp);
-			if (nextbno == NULLFSBLOCK)
-				break;
-			bno = nextbno;
-			error = xfs_btree_read_bufl(mp, tp, bno, &bp,
-						XFS_BMAP_BTREE_REF,
-						&xfs_bmbt_buf_ops);
-			if (error)
-				return error;
-			*count += 1;
-			block = XFS_BUF_TO_BLOCK(bp);
-		}
-	}
-	return 0;
-}
-
-/*
  * Count fsblocks of the given fork.  Delayed allocation extents are
  * not counted towards the totals.
  */
@@ -340,26 +211,19 @@ xfs_bmap_count_blocks(
 	xfs_extnum_t		*nextents,
 	xfs_filblks_t		*count)
 {
-	struct xfs_mount	*mp;	/* file system mount structure */
-	__be64			*pp;	/* pointer to block address */
-	struct xfs_btree_block	*block;	/* current btree block */
-	struct xfs_ifork	*ifp;	/* fork structure */
-	xfs_fsblock_t		bno;	/* block # of "block" */
-	int			level;	/* btree level, for checking */
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, whichfork);
+	struct xfs_btree_cur	*cur;
+	xfs_extlen_t		btblocks = 0;
 	int			error;
 
-	bno = NULLFSBLOCK;
-	mp = ip->i_mount;
 	*nextents = 0;
 	*count = 0;
-	ifp = XFS_IFORK_PTR(ip, whichfork);
+
 	if (!ifp)
 		return 0;
 
 	switch (XFS_IFORK_FORMAT(ip, whichfork)) {
-	case XFS_DINODE_FMT_EXTENTS:
-		*nextents = xfs_bmap_count_leaves(ifp, count);
-		return 0;
 	case XFS_DINODE_FMT_BTREE:
 		if (!(ifp->if_flags & XFS_IFEXTENTS)) {
 			error = xfs_iread_extents(tp, ip, whichfork);
@@ -367,26 +231,23 @@ xfs_bmap_count_blocks(
 				return error;
 		}
 
+		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
+		error = xfs_btree_count_blocks(cur, &btblocks);
+		xfs_btree_del_cursor(cur, error);
+		if (error)
+			return error;
+
 		/*
-		 * Root level must use BMAP_BROOT_PTR_ADDR macro to get ptr out.
+		 * xfs_btree_count_blocks includes the root block contained in
+		 * the inode fork in @btblocks, so subtract one because we're
+		 * only interested in allocated disk blocks.
 		 */
-		block = ifp->if_broot;
-		level = be16_to_cpu(block->bb_level);
-		ASSERT(level > 0);
-		pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes);
-		bno = be64_to_cpu(*pp);
-		ASSERT(bno != NULLFSBLOCK);
-		ASSERT(XFS_FSB_TO_AGNO(mp, bno) < mp->m_sb.sb_agcount);
-		ASSERT(XFS_FSB_TO_AGBNO(mp, bno) < mp->m_sb.sb_agblocks);
-
-		error = xfs_bmap_count_tree(mp, tp, ifp, bno, level,
-				nextents, count);
-		if (error) {
-			XFS_ERROR_REPORT("xfs_bmap_count_blocks(2)",
-					XFS_ERRLEVEL_LOW, mp);
-			return -EFSCORRUPTED;
-		}
-		return 0;
+		*count += btblocks - 1;
+
+		/* fall through */
+	case XFS_DINODE_FMT_EXTENTS:
+		*nextents = xfs_bmap_count_leaves(ifp, count);
+		break;
 	}
 
 	return 0;
@@ -964,8 +825,8 @@ xfs_alloc_file_space(
 		xfs_trans_ijoin(tp, ip, 0);
 
 		error = xfs_bmapi_write(tp, ip, startoffset_fsb,
-					allocatesize_fsb, alloc_type, resblks,
-					imapp, &nimaps);
+					allocatesize_fsb, alloc_type, 0, imapp,
+					&nimaps);
 		if (error)
 			goto error0;
 
@@ -1039,6 +900,7 @@ out_trans_cancel:
 	goto out_unlock;
 }
 
+/* Caller must first wait for the completion of any pending DIOs if required. */
 int
 xfs_flush_unmap_range(
 	struct xfs_inode	*ip,
@@ -1050,9 +912,6 @@ xfs_flush_unmap_range(
 	xfs_off_t		rounding, start, end;
 	int			error;
 
-	/* wait for the completion of any pending DIOs */
-	inode_dio_wait(inode);
-
 	rounding = max_t(xfs_off_t, 1 << mp->m_sb.sb_blocklog, PAGE_SIZE);
 	start = round_down(offset, rounding);
 	end = round_up(offset + len, rounding) - 1;
@@ -1084,10 +943,6 @@ xfs_free_file_space(
 	if (len <= 0)	/* if nothing being freed */
 		return 0;
 
-	error = xfs_flush_unmap_range(ip, offset, len);
-	if (error)
-		return error;
-
 	startoffset_fsb = XFS_B_TO_FSB(mp, offset);
 	endoffset_fsb = XFS_B_TO_FSBT(mp, offset + len);
 
@@ -1113,7 +968,8 @@ xfs_free_file_space(
 		return 0;
 	if (offset + len > XFS_ISIZE(ip))
 		len = XFS_ISIZE(ip) - offset;
-	error = iomap_zero_range(VFS_I(ip), offset, len, NULL, &xfs_iomap_ops);
+	error = iomap_zero_range(VFS_I(ip), offset, len, NULL,
+			&xfs_buffered_write_iomap_ops);
 	if (error)
 		return error;
 
@@ -1131,43 +987,6 @@ xfs_free_file_space(
 	return error;
 }
 
-/*
- * Preallocate and zero a range of a file. This mechanism has the allocation
- * semantics of fallocate and in addition converts data in the range to zeroes.
- */
-int
-xfs_zero_file_space(
-	struct xfs_inode	*ip,
-	xfs_off_t		offset,
-	xfs_off_t		len)
-{
-	struct xfs_mount	*mp = ip->i_mount;
-	uint			blksize;
-	int			error;
-
-	trace_xfs_zero_file_space(ip);
-
-	blksize = 1 << mp->m_sb.sb_blocklog;
-
-	/*
-	 * Punch a hole and prealloc the range. We use hole punch rather than
-	 * unwritten extent conversion for two reasons:
-	 *
-	 * 1.) Hole punch handles partial block zeroing for us.
-	 *
-	 * 2.) If prealloc returns ENOSPC, the file range is still zero-valued
-	 * by virtue of the hole punch.
-	 */
-	error = xfs_free_file_space(ip, offset, len);
-	if (error || xfs_is_always_cow_inode(ip))
-		return error;
-
-	return xfs_alloc_file_space(ip, round_down(offset, blksize),
-				     round_up(offset + len, blksize) -
-				     round_down(offset, blksize),
-				     XFS_BMAPI_PREALLOC);
-}
-
 static int
 xfs_prepare_shift(
 	struct xfs_inode	*ip,
@@ -1750,6 +1569,14 @@ xfs_swap_extents(
 		goto out_unlock;
 	}
 
+	error = xfs_qm_dqattach(ip);
+	if (error)
+		goto out_unlock;
+
+	error = xfs_qm_dqattach(tip);
+	if (error)
+		goto out_unlock;
+
 	error = xfs_swap_extent_flush(ip);
 	if (error)
 		goto out_unlock;