Merge tag 'xfs-4.16-merge-4' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull xfs updates from Darrick Wong:
 "This merge cycle, we're again some substantive changes to XFS.

  Metadata verifiers have been restructured to provide more detail about
  which part of a metadata structure failed checks, and we've enhanced
  the new online fsck feature to cross-reference extent allocation
  information with the other metadata structures. With this pull, the
  metadata verification part of online fsck is more or less finished,
  though the feature is still experimental and still disabled by
  default.

  We're also preparing to remove the EXPERIMENTAL tag from a couple of
  features this cycle. This week we're committing a bunch of space
  accounting fixes for reflink and removing the EXPERIMENTAL tag from
  reflink; I anticipate that we'll be ready to do the same for the
  reverse mapping feature next week. (I don't have any pending fixes for
  rmap; however I wish to remove the tags one at a time.)

  This giant pile of patches has been run through a full xfstests run
  over the weekend and through a quick xfstests run against this
  morning's master, with no major failures reported. Let me know if
  there's any merge problems -- git merge reported that one of our
  patches touched the same function as the i_version series, but it
  resolved things cleanly.

  Summary:

   - Log faulting code locations when verifiers fail, for improved
     diagnosis of corrupt filesystems.

   - Implement metadata verifiers for local format inode fork data.

   - Online scrub now cross-references metadata records with other
     metadata.

   - Refactor the fs geometry ioctl generation functions.

   - Harden various metadata verifiers.

   - Fix various accounting problems.

   - Fix uncancelled transactions leaking when xattr functions fail.

   - Prevent the copy-on-write speculative preallocation garbage
     collector from racing with writeback.

   - Emit log reservation type information as trace data so that we can
     compare against xfsprogs.

   - Fix some erroneous asserts in the online scrub code.

   - Clean up the transaction reservation calculations.

   - Fix various minor bugs in online scrub.

   - Log complaints about mixed dio/buffered writes once per day and
     less noisily than before.

   - Refactor buffer log item lists to use list_head.

   - Break PNFS leases before reflinking blocks.

   - Reduce lock contention on reflink source files.

   - Fix some quota accounting problems with reflink.

   - Fix a serious corruption problem in the direct cow write code where
     we fed bad iomaps to the vfs iomap consumers.

   - Various other refactorings.

   - Remove EXPERIMENTAL tag from reflink!"

* tag 'xfs-4.16-merge-4' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (94 commits)
  xfs: remove experimental tag for reflinks
  xfs: don't screw up direct writes when freesp is fragmented
  xfs: check reflink allocation mappings
  iomap: warn on zero-length mappings
  xfs: treat CoW fork operations as delalloc for quota accounting
  xfs: only grab shared inode locks for source file during reflink
  xfs: allow xfs_lock_two_inodes to take different EXCL/SHARED modes
  xfs: reflink should break pnfs leases before sharing blocks
  xfs: don't clobber inobt/finobt cursors when xref with rmap
  xfs: skip CoW writes past EOF when writeback races with truncate
  xfs: preserve i_rdev when recycling a reclaimable inode
  xfs: refactor accounting updates out of xfs_bmap_btalloc
  xfs: refactor inode verifier corruption error printing
  xfs: make tracepoint inode number format consistent
  xfs: always zero di_flags2 when we free the inode
  xfs: call xfs_qm_dqattach before performing reflink operations
  xfs: bmap code cleanup
  Use list_head infra-structure for buffer's log items list
  Split buffer's b_fspriv field
  Get rid of xfs_buf_log_item_t typedef
  ...

1 files changed, 122 insertions, 86 deletions

diff --git a/fs/xfs/libxfs/xfs_dir2_data.c b/fs/xfs/libxfs/xfs_dir2_data.c
index 8727a43115ef..920279485275 100644
--- a/fs/xfs/libxfs/xfs_dir2_data.c
+++ b/fs/xfs/libxfs/xfs_dir2_data.c
@@ -36,9 +36,9 @@
 /*
  * Check the consistency of the data block.
  * The input can also be a block-format directory.
- * Return 0 is the buffer is good, otherwise an error.
+ * Return NULL if the buffer is good, otherwise the address of the error.
  */
-int
+xfs_failaddr_t
 __xfs_dir3_data_check(
 	struct xfs_inode	*dp,		/* incore inode pointer */
 	struct xfs_buf		*bp)		/* data block's buffer */
@@ -73,6 +73,14 @@ __xfs_dir3_data_check(
 	 */
 	ops = xfs_dir_get_ops(mp, dp);
 
+	/*
+	 * If this isn't a directory, or we don't get handed the dir ops,
+	 * something is seriously wrong.  Bail out.
+	 */
+	if ((dp && !S_ISDIR(VFS_I(dp)->i_mode)) ||
+	    ops != xfs_dir_get_ops(mp, NULL))
+		return __this_address;
+
 	hdr = bp->b_addr;
 	p = (char *)ops->data_entry_p(hdr);
 
@@ -81,7 +89,6 @@ __xfs_dir3_data_check(
 	case cpu_to_be32(XFS_DIR2_BLOCK_MAGIC):
 		btp = xfs_dir2_block_tail_p(geo, hdr);
 		lep = xfs_dir2_block_leaf_p(btp);
-		endp = (char *)lep;
 
 		/*
 		 * The number of leaf entries is limited by the size of the
@@ -90,17 +97,19 @@ __xfs_dir3_data_check(
 		 * so just ensure that the count falls somewhere inside the
 		 * block right now.
 		 */
-		XFS_WANT_CORRUPTED_RETURN(mp, be32_to_cpu(btp->count) <
-			((char *)btp - p) / sizeof(struct xfs_dir2_leaf_entry));
+		if (be32_to_cpu(btp->count) >=
+		    ((char *)btp - p) / sizeof(struct xfs_dir2_leaf_entry))
+			return __this_address;
 		break;
 	case cpu_to_be32(XFS_DIR3_DATA_MAGIC):
 	case cpu_to_be32(XFS_DIR2_DATA_MAGIC):
-		endp = (char *)hdr + geo->blksize;
 		break;
 	default:
-		XFS_ERROR_REPORT("Bad Magic", XFS_ERRLEVEL_LOW, mp);
-		return -EFSCORRUPTED;
+		return __this_address;
 	}
+	endp = xfs_dir3_data_endp(geo, hdr);
+	if (!endp)
+		return __this_address;
 
 	/*
 	 * Account for zero bestfree entries.
@@ -108,22 +117,25 @@ __xfs_dir3_data_check(
 	bf = ops->data_bestfree_p(hdr);
 	count = lastfree = freeseen = 0;
 	if (!bf[0].length) {
-		XFS_WANT_CORRUPTED_RETURN(mp, !bf[0].offset);
+		if (bf[0].offset)
+			return __this_address;
 		freeseen |= 1 << 0;
 	}
 	if (!bf[1].length) {
-		XFS_WANT_CORRUPTED_RETURN(mp, !bf[1].offset);
+		if (bf[1].offset)
+			return __this_address;
 		freeseen |= 1 << 1;
 	}
 	if (!bf[2].length) {
-		XFS_WANT_CORRUPTED_RETURN(mp, !bf[2].offset);
+		if (bf[2].offset)
+			return __this_address;
 		freeseen |= 1 << 2;
 	}
 
-	XFS_WANT_CORRUPTED_RETURN(mp, be16_to_cpu(bf[0].length) >=
-						be16_to_cpu(bf[1].length));
-	XFS_WANT_CORRUPTED_RETURN(mp, be16_to_cpu(bf[1].length) >=
-						be16_to_cpu(bf[2].length));
+	if (be16_to_cpu(bf[0].length) < be16_to_cpu(bf[1].length))
+		return __this_address;
+	if (be16_to_cpu(bf[1].length) < be16_to_cpu(bf[2].length))
+		return __this_address;
 	/*
 	 * Loop over the data/unused entries.
 	 */
@@ -135,22 +147,23 @@ __xfs_dir3_data_check(
 		 * doesn't need to be there.
 		 */
 		if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) {
-			XFS_WANT_CORRUPTED_RETURN(mp, lastfree == 0);
-			XFS_WANT_CORRUPTED_RETURN(mp, endp >=
-					p + be16_to_cpu(dup->length));
-			XFS_WANT_CORRUPTED_RETURN(mp,
-				be16_to_cpu(*xfs_dir2_data_unused_tag_p(dup)) ==
-					       (char *)dup - (char *)hdr);
+			if (lastfree != 0)
+				return __this_address;
+			if (endp < p + be16_to_cpu(dup->length))
+				return __this_address;
+			if (be16_to_cpu(*xfs_dir2_data_unused_tag_p(dup)) !=
+			    (char *)dup - (char *)hdr)
+				return __this_address;
 			dfp = xfs_dir2_data_freefind(hdr, bf, dup);
 			if (dfp) {
 				i = (int)(dfp - bf);
-				XFS_WANT_CORRUPTED_RETURN(mp,
-					(freeseen & (1 << i)) == 0);
+				if ((freeseen & (1 << i)) != 0)
+					return __this_address;
 				freeseen |= 1 << i;
 			} else {
-				XFS_WANT_CORRUPTED_RETURN(mp,
-					be16_to_cpu(dup->length) <=
-						be16_to_cpu(bf[2].length));
+				if (be16_to_cpu(dup->length) >
+				    be16_to_cpu(bf[2].length))
+					return __this_address;
 			}
 			p += be16_to_cpu(dup->length);
 			lastfree = 1;
@@ -163,16 +176,17 @@ __xfs_dir3_data_check(
 		 * The linear search is crude but this is DEBUG code.
 		 */
 		dep = (xfs_dir2_data_entry_t *)p;
-		XFS_WANT_CORRUPTED_RETURN(mp, dep->namelen != 0);
-		XFS_WANT_CORRUPTED_RETURN(mp,
-			!xfs_dir_ino_validate(mp, be64_to_cpu(dep->inumber)));
-		XFS_WANT_CORRUPTED_RETURN(mp, endp >=
-				p + ops->data_entsize(dep->namelen));
-		XFS_WANT_CORRUPTED_RETURN(mp,
-			be16_to_cpu(*ops->data_entry_tag_p(dep)) ==
-					       (char *)dep - (char *)hdr);
-		XFS_WANT_CORRUPTED_RETURN(mp,
-				ops->data_get_ftype(dep) < XFS_DIR3_FT_MAX);
+		if (dep->namelen == 0)
+			return __this_address;
+		if (xfs_dir_ino_validate(mp, be64_to_cpu(dep->inumber)))
+			return __this_address;
+		if (endp < p + ops->data_entsize(dep->namelen))
+			return __this_address;
+		if (be16_to_cpu(*ops->data_entry_tag_p(dep)) !=
+		    (char *)dep - (char *)hdr)
+			return __this_address;
+		if (ops->data_get_ftype(dep) >= XFS_DIR3_FT_MAX)
+			return __this_address;
 		count++;
 		lastfree = 0;
 		if (hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
@@ -188,34 +202,52 @@ __xfs_dir3_data_check(
 				    be32_to_cpu(lep[i].hashval) == hash)
 					break;
 			}
-			XFS_WANT_CORRUPTED_RETURN(mp,
-						  i < be32_to_cpu(btp->count));
+			if (i >= be32_to_cpu(btp->count))
+				return __this_address;
 		}
 		p += ops->data_entsize(dep->namelen);
 	}
 	/*
 	 * Need to have seen all the entries and all the bestfree slots.
 	 */
-	XFS_WANT_CORRUPTED_RETURN(mp, freeseen == 7);
+	if (freeseen != 7)
+		return __this_address;
 	if (hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
 	    hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC)) {
 		for (i = stale = 0; i < be32_to_cpu(btp->count); i++) {
 			if (lep[i].address ==
 			    cpu_to_be32(XFS_DIR2_NULL_DATAPTR))
 				stale++;
-			if (i > 0)
-				XFS_WANT_CORRUPTED_RETURN(mp,
-					be32_to_cpu(lep[i].hashval) >=
-						be32_to_cpu(lep[i - 1].hashval));
+			if (i > 0 && be32_to_cpu(lep[i].hashval) <
+				     be32_to_cpu(lep[i - 1].hashval))
+				return __this_address;
 		}
-		XFS_WANT_CORRUPTED_RETURN(mp, count ==
-			be32_to_cpu(btp->count) - be32_to_cpu(btp->stale));
-		XFS_WANT_CORRUPTED_RETURN(mp, stale == be32_to_cpu(btp->stale));
+		if (count != be32_to_cpu(btp->count) - be32_to_cpu(btp->stale))
+			return __this_address;
+		if (stale != be32_to_cpu(btp->stale))
+			return __this_address;
 	}
-	return 0;
+	return NULL;
+}
+
+#ifdef DEBUG
+void
+xfs_dir3_data_check(
+	struct xfs_inode	*dp,
+	struct xfs_buf		*bp)
+{
+	xfs_failaddr_t		fa;
+
+	fa = __xfs_dir3_data_check(dp, bp);
+	if (!fa)
+		return;
+	xfs_corruption_error(__func__, XFS_ERRLEVEL_LOW, dp->i_mount,
+			bp->b_addr, __FILE__, __LINE__, fa);
+	ASSERT(0);
 }
+#endif
 
-static bool
+static xfs_failaddr_t
 xfs_dir3_data_verify(
 	struct xfs_buf		*bp)
 {
@@ -224,20 +256,18 @@ xfs_dir3_data_verify(
 
 	if (xfs_sb_version_hascrc(&mp->m_sb)) {
 		if (hdr3->magic != cpu_to_be32(XFS_DIR3_DATA_MAGIC))
-			return false;
+			return __this_address;
 		if (!uuid_equal(&hdr3->uuid, &mp->m_sb.sb_meta_uuid))
-			return false;
+			return __this_address;
 		if (be64_to_cpu(hdr3->blkno) != bp->b_bn)
-			return false;
+			return __this_address;
 		if (!xfs_log_check_lsn(mp, be64_to_cpu(hdr3->lsn)))
-			return false;
+			return __this_address;
 	} else {
 		if (hdr3->magic != cpu_to_be32(XFS_DIR2_DATA_MAGIC))
-			return false;
+			return __this_address;
 	}
-	if (__xfs_dir3_data_check(NULL, bp))
-		return false;
-	return true;
+	return __xfs_dir3_data_check(NULL, bp);
 }
 
 /*
@@ -263,8 +293,7 @@ xfs_dir3_data_reada_verify(
 		bp->b_ops->verify_read(bp);
 		return;
 	default:
-		xfs_buf_ioerror(bp, -EFSCORRUPTED);
-		xfs_verifier_error(bp);
+		xfs_verifier_error(bp, -EFSCORRUPTED, __this_address);
 		break;
 	}
 }
@@ -274,15 +303,16 @@ xfs_dir3_data_read_verify(
 	struct xfs_buf	*bp)
 {
 	struct xfs_mount	*mp = bp->b_target->bt_mount;
+	xfs_failaddr_t		fa;
 
 	if (xfs_sb_version_hascrc(&mp->m_sb) &&
-	     !xfs_buf_verify_cksum(bp, XFS_DIR3_DATA_CRC_OFF))
-		 xfs_buf_ioerror(bp, -EFSBADCRC);
-	else if (!xfs_dir3_data_verify(bp))
-		xfs_buf_ioerror(bp, -EFSCORRUPTED);
-
-	if (bp->b_error)
-		xfs_verifier_error(bp);
+	    !xfs_buf_verify_cksum(bp, XFS_DIR3_DATA_CRC_OFF))
+		xfs_verifier_error(bp, -EFSBADCRC, __this_address);
+	else {
+		fa = xfs_dir3_data_verify(bp);
+		if (fa)
+			xfs_verifier_error(bp, -EFSCORRUPTED, fa);
+	}
 }
 
 static void
@@ -290,12 +320,13 @@ xfs_dir3_data_write_verify(
 	struct xfs_buf	*bp)
 {
 	struct xfs_mount	*mp = bp->b_target->bt_mount;
-	struct xfs_buf_log_item	*bip = bp->b_fspriv;
+	struct xfs_buf_log_item	*bip = bp->b_log_item;
 	struct xfs_dir3_blk_hdr	*hdr3 = bp->b_addr;
+	xfs_failaddr_t		fa;
 
-	if (!xfs_dir3_data_verify(bp)) {
-		xfs_buf_ioerror(bp, -EFSCORRUPTED);
-		xfs_verifier_error(bp);
+	fa = xfs_dir3_data_verify(bp);
+	if (fa) {
+		xfs_verifier_error(bp, -EFSCORRUPTED, fa);
 		return;
 	}
 
@@ -312,6 +343,7 @@ const struct xfs_buf_ops xfs_dir3_data_buf_ops = {
 	.name = "xfs_dir3_data",
 	.verify_read = xfs_dir3_data_read_verify,
 	.verify_write = xfs_dir3_data_write_verify,
+	.verify_struct = xfs_dir3_data_verify,
 };
 
 static const struct xfs_buf_ops xfs_dir3_data_reada_buf_ops = {
@@ -515,7 +547,6 @@ xfs_dir2_data_freescan_int(
 	struct xfs_dir2_data_hdr *hdr,
 	int			*loghead)
 {
-	xfs_dir2_block_tail_t	*btp;		/* block tail */
 	xfs_dir2_data_entry_t	*dep;		/* active data entry */
 	xfs_dir2_data_unused_t	*dup;		/* unused data entry */
 	struct xfs_dir2_data_free *bf;
@@ -537,12 +568,7 @@ xfs_dir2_data_freescan_int(
 	 * Set up pointers.
 	 */
 	p = (char *)ops->data_entry_p(hdr);
-	if (hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
-	    hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC)) {
-		btp = xfs_dir2_block_tail_p(geo, hdr);
-		endp = (char *)xfs_dir2_block_leaf_p(btp);
-	} else
-		endp = (char *)hdr + geo->blksize;
+	endp = xfs_dir3_data_endp(geo, hdr);
 	/*
 	 * Loop over the block's entries.
 	 */
@@ -755,17 +781,9 @@ xfs_dir2_data_make_free(
 	/*
 	 * Figure out where the end of the data area is.
 	 */
-	if (hdr->magic == cpu_to_be32(XFS_DIR2_DATA_MAGIC) ||
-	    hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC))
-		endptr = (char *)hdr + args->geo->blksize;
-	else {
-		xfs_dir2_block_tail_t	*btp;	/* block tail */
+	endptr = xfs_dir3_data_endp(args->geo, hdr);
+	ASSERT(endptr != NULL);
 
-		ASSERT(hdr->magic == cpu_to_be32(XFS_DIR2_BLOCK_MAGIC) ||
-			hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC));
-		btp = xfs_dir2_block_tail_p(args->geo, hdr);
-		endptr = (char *)xfs_dir2_block_leaf_p(btp);
-	}
 	/*
 	 * If this isn't the start of the block, then back up to
 	 * the previous entry and see if it's free.
@@ -1067,3 +1085,21 @@ xfs_dir2_data_use_free(
 	}
 	*needscanp = needscan;
 }
+
+/* Find the end of the entry data in a data/block format dir block. */
+void *
+xfs_dir3_data_endp(
+	struct xfs_da_geometry		*geo,
+	struct xfs_dir2_data_hdr	*hdr)
+{
+	switch (hdr->magic) {
+	case cpu_to_be32(XFS_DIR3_BLOCK_MAGIC):
+	case cpu_to_be32(XFS_DIR2_BLOCK_MAGIC):
+		return xfs_dir2_block_leaf_p(xfs_dir2_block_tail_p(geo, hdr));
+	case cpu_to_be32(XFS_DIR3_DATA_MAGIC):
+	case cpu_to_be32(XFS_DIR2_DATA_MAGIC):
+		return (char *)hdr + geo->blksize;
+	default:
+		return NULL;
+	}
+}