Merge tag 'for-linus-v3.8-rc1' of git://oss.sgi.com/xfs/xfs

Pull xfs update from Ben Myers:
 "There is plenty going on, including the cleanup of xfssyncd, metadata
  verifiers, CRC infrastructure for the log, tracking of inodes with
  speculative allocation, a cleanup of xfs_fs_subr.c, fixes for
  XFS_IOC_ZERO_RANGE, and important fix related to log replay (only
  update the last_sync_lsn when a transaction completes), a fix for
  deadlock on AGF buffers, documentation and comment updates, and a few
  more cleanups and fixes.

  Details:
   - remove the xfssyncd mess
   - only update the last_sync_lsn when a transaction completes
   - zero allocation_args on the kernel stack
   - fix AGF/alloc workqueue deadlock
   - silence uninitialised f.file warning
   - Update inode alloc comments
   - Update mount options documentation
   - report projid32bit feature in geometry call
   - speculative preallocation inode tracking
   - fix attr tree double split corruption
   - fix broken error handling in xfs_vm_writepage
   - drop buffer io reference when a bad bio is built
   - add more attribute tree trace points
   - growfs infrastructure changes for 3.8
   - fs/xfs/xfs_fs_subr.c die die die
   - add CRC infrastructure
   - add CRC checks to the log
   - Remove description of nodelaylog mount option from xfs.txt
   - inode allocation should use unmapped buffers
   - byte range granularity for XFS_IOC_ZERO_RANGE
   - fix direct IO nested transaction deadlock
   - fix stray dquot unlock when reclaiming dquots
   - fix sparse reported log CRC endian issue"

Fix up trivial conflict in fs/xfs/xfs_fsops.c due to the same patch
having been applied twice (commits eaef854335ce and 1375cb65e87b: "xfs:
growfs: don't read garbage for new secondary superblocks") with later
updates to the affected code in the XFS tree.

* tag 'for-linus-v3.8-rc1' of git://oss.sgi.com/xfs/xfs: (78 commits)
  xfs: fix sparse reported log CRC endian issue
  xfs: fix stray dquot unlock when reclaiming dquots
  xfs: fix direct IO nested transaction deadlock.
  xfs: byte range granularity for XFS_IOC_ZERO_RANGE
  xfs: inode allocation should use unmapped buffers.
  xfs: Remove the description of nodelaylog mount option from xfs.txt
  xfs: add CRC checks to the log
  xfs: add CRC infrastructure
  xfs: convert buffer verifiers to an ops structure.
  xfs: connect up write verifiers to new buffers
  xfs: add pre-write metadata buffer verifier callbacks
  xfs: add buffer pre-write callback
  xfs: Add verifiers to dir2 data readahead.
  xfs: add xfs_da_node verification
  xfs: factor and verify attr leaf reads
  xfs: factor dir2 leaf read
  xfs: factor out dir2 data block reading
  xfs: factor dir2 free block reading
  xfs: verify dir2 block format buffers
  xfs: factor dir2 block read operations
  ...

1 files changed, 113 insertions, 27 deletions

diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c
index 335206a9c69..393055fe3ae 100644
--- a/fs/xfs/xfs_alloc.c
+++ b/fs/xfs/xfs_alloc.c
@@ -430,6 +430,60 @@ xfs_alloc_fixup_trees(
 	return 0;
 }
 
+static void
+xfs_agfl_verify(
+	struct xfs_buf	*bp)
+{
+#ifdef WHEN_CRCS_COME_ALONG
+	/*
+	 * we cannot actually do any verification of the AGFL because mkfs does
+	 * not initialise the AGFL to zero or NULL. Hence the only valid part of
+	 * the AGFL is what the AGF says is active. We can't get to the AGF, so
+	 * we can't verify just those entries are valid.
+	 *
+	 * This problem goes away when the CRC format change comes along as that
+	 * requires the AGFL to be initialised by mkfs. At that point, we can
+	 * verify the blocks in the agfl -active or not- lie within the bounds
+	 * of the AG. Until then, just leave this check ifdef'd out.
+	 */
+	struct xfs_mount *mp = bp->b_target->bt_mount;
+	struct xfs_agfl	*agfl = XFS_BUF_TO_AGFL(bp);
+	int		agfl_ok = 1;
+
+	int		i;
+
+	for (i = 0; i < XFS_AGFL_SIZE(mp); i++) {
+		if (be32_to_cpu(agfl->agfl_bno[i]) == NULLAGBLOCK ||
+		    be32_to_cpu(agfl->agfl_bno[i]) >= mp->m_sb.sb_agblocks)
+			agfl_ok = 0;
+	}
+
+	if (!agfl_ok) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, agfl);
+		xfs_buf_ioerror(bp, EFSCORRUPTED);
+	}
+#endif
+}
+
+static void
+xfs_agfl_write_verify(
+	struct xfs_buf	*bp)
+{
+	xfs_agfl_verify(bp);
+}
+
+static void
+xfs_agfl_read_verify(
+	struct xfs_buf	*bp)
+{
+	xfs_agfl_verify(bp);
+}
+
+const struct xfs_buf_ops xfs_agfl_buf_ops = {
+	.verify_read = xfs_agfl_read_verify,
+	.verify_write = xfs_agfl_write_verify,
+};
+
 /*
  * Read in the allocation group free block array.
  */
@@ -447,7 +501,7 @@ xfs_alloc_read_agfl(
 	error = xfs_trans_read_buf(
 			mp, tp, mp->m_ddev_targp,
 			XFS_AG_DADDR(mp, agno, XFS_AGFL_DADDR(mp)),
-			XFS_FSS_TO_BB(mp, 1), 0, &bp);
+			XFS_FSS_TO_BB(mp, 1), 0, &bp, &xfs_agfl_buf_ops);
 	if (error)
 		return error;
 	ASSERT(!xfs_buf_geterror(bp));
@@ -2091,6 +2145,63 @@ xfs_alloc_put_freelist(
 	return 0;
 }
 
+static void
+xfs_agf_verify(
+	struct xfs_buf	*bp)
+ {
+	struct xfs_mount *mp = bp->b_target->bt_mount;
+	struct xfs_agf	*agf;
+	int		agf_ok;
+
+	agf = XFS_BUF_TO_AGF(bp);
+
+	agf_ok = agf->agf_magicnum == cpu_to_be32(XFS_AGF_MAGIC) &&
+		XFS_AGF_GOOD_VERSION(be32_to_cpu(agf->agf_versionnum)) &&
+		be32_to_cpu(agf->agf_freeblks) <= be32_to_cpu(agf->agf_length) &&
+		be32_to_cpu(agf->agf_flfirst) < XFS_AGFL_SIZE(mp) &&
+		be32_to_cpu(agf->agf_fllast) < XFS_AGFL_SIZE(mp) &&
+		be32_to_cpu(agf->agf_flcount) <= XFS_AGFL_SIZE(mp);
+
+	/*
+	 * during growfs operations, the perag is not fully initialised,
+	 * so we can't use it for any useful checking. growfs ensures we can't
+	 * use it by using uncached buffers that don't have the perag attached
+	 * so we can detect and avoid this problem.
+	 */
+	if (bp->b_pag)
+		agf_ok = agf_ok && be32_to_cpu(agf->agf_seqno) ==
+						bp->b_pag->pag_agno;
+
+	if (xfs_sb_version_haslazysbcount(&mp->m_sb))
+		agf_ok = agf_ok && be32_to_cpu(agf->agf_btreeblks) <=
+						be32_to_cpu(agf->agf_length);
+
+	if (unlikely(XFS_TEST_ERROR(!agf_ok, mp, XFS_ERRTAG_ALLOC_READ_AGF,
+			XFS_RANDOM_ALLOC_READ_AGF))) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, agf);
+		xfs_buf_ioerror(bp, EFSCORRUPTED);
+	}
+}
+
+static void
+xfs_agf_read_verify(
+	struct xfs_buf	*bp)
+{
+	xfs_agf_verify(bp);
+}
+
+static void
+xfs_agf_write_verify(
+	struct xfs_buf	*bp)
+{
+	xfs_agf_verify(bp);
+}
+
+const struct xfs_buf_ops xfs_agf_buf_ops = {
+	.verify_read = xfs_agf_read_verify,
+	.verify_write = xfs_agf_write_verify,
+};
+
 /*
  * Read in the allocation group header (free/alloc section).
  */
@@ -2102,44 +2213,19 @@ xfs_read_agf(
 	int			flags,	/* XFS_BUF_ */
 	struct xfs_buf		**bpp)	/* buffer for the ag freelist header */
 {
-	struct xfs_agf	*agf;		/* ag freelist header */
-	int		agf_ok;		/* set if agf is consistent */
 	int		error;
 
 	ASSERT(agno != NULLAGNUMBER);
 	error = xfs_trans_read_buf(
 			mp, tp, mp->m_ddev_targp,
 			XFS_AG_DADDR(mp, agno, XFS_AGF_DADDR(mp)),
-			XFS_FSS_TO_BB(mp, 1), flags, bpp);
+			XFS_FSS_TO_BB(mp, 1), flags, bpp, &xfs_agf_buf_ops);
 	if (error)
 		return error;
 	if (!*bpp)
 		return 0;
 
 	ASSERT(!(*bpp)->b_error);
-	agf = XFS_BUF_TO_AGF(*bpp);
-
-	/*
-	 * Validate the magic number of the agf block.
-	 */
-	agf_ok =
-		agf->agf_magicnum == cpu_to_be32(XFS_AGF_MAGIC) &&
-		XFS_AGF_GOOD_VERSION(be32_to_cpu(agf->agf_versionnum)) &&
-		be32_to_cpu(agf->agf_freeblks) <= be32_to_cpu(agf->agf_length) &&
-		be32_to_cpu(agf->agf_flfirst) < XFS_AGFL_SIZE(mp) &&
-		be32_to_cpu(agf->agf_fllast) < XFS_AGFL_SIZE(mp) &&
-		be32_to_cpu(agf->agf_flcount) <= XFS_AGFL_SIZE(mp) &&
-		be32_to_cpu(agf->agf_seqno) == agno;
-	if (xfs_sb_version_haslazysbcount(&mp->m_sb))
-		agf_ok = agf_ok && be32_to_cpu(agf->agf_btreeblks) <=
-						be32_to_cpu(agf->agf_length);
-	if (unlikely(XFS_TEST_ERROR(!agf_ok, mp, XFS_ERRTAG_ALLOC_READ_AGF,
-			XFS_RANDOM_ALLOC_READ_AGF))) {
-		XFS_CORRUPTION_ERROR("xfs_alloc_read_agf",
-				     XFS_ERRLEVEL_LOW, mp, agf);
-		xfs_trans_brelse(tp, *bpp);
-		return XFS_ERROR(EFSCORRUPTED);
-	}
 	xfs_buf_set_ref(*bpp, XFS_AGF_REF);
 	return 0;
 }