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, 73 insertions, 31 deletions

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 9f424e0aef1f..604ee384a00a 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -547,23 +547,36 @@ again:
 
 /*
  * xfs_lock_two_inodes() can only be used to lock one type of lock at a time -
- * the iolock, the mmaplock or the ilock, but not more than one at a time. If we
- * lock more than one at a time, lockdep will report false positives saying we
- * have violated locking orders.
+ * the mmaplock or the ilock, but not more than one type at a time. If we lock
+ * more than one at a time, lockdep will report false positives saying we have
+ * violated locking orders.  The iolock must be double-locked separately since
+ * we use i_rwsem for that.  We now support taking one lock EXCL and the other
+ * SHARED.
  */
 void
 xfs_lock_two_inodes(
-	xfs_inode_t		*ip0,
-	xfs_inode_t		*ip1,
-	uint			lock_mode)
+	struct xfs_inode	*ip0,
+	uint			ip0_mode,
+	struct xfs_inode	*ip1,
+	uint			ip1_mode)
 {
-	xfs_inode_t		*temp;
+	struct xfs_inode	*temp;
+	uint			mode_temp;
 	int			attempts = 0;
 	xfs_log_item_t		*lp;
 
-	ASSERT(!(lock_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL)));
-	if (lock_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL))
-		ASSERT(!(lock_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)));
+	ASSERT(hweight32(ip0_mode) == 1);
+	ASSERT(hweight32(ip1_mode) == 1);
+	ASSERT(!(ip0_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL)));
+	ASSERT(!(ip1_mode & (XFS_IOLOCK_SHARED|XFS_IOLOCK_EXCL)));
+	ASSERT(!(ip0_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) ||
+	       !(ip0_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)));
+	ASSERT(!(ip1_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) ||
+	       !(ip1_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)));
+	ASSERT(!(ip1_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) ||
+	       !(ip0_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)));
+	ASSERT(!(ip0_mode & (XFS_MMAPLOCK_SHARED|XFS_MMAPLOCK_EXCL)) ||
+	       !(ip1_mode & (XFS_ILOCK_SHARED|XFS_ILOCK_EXCL)));
 
 	ASSERT(ip0->i_ino != ip1->i_ino);
 
@@ -571,10 +584,13 @@ xfs_lock_two_inodes(
 		temp = ip0;
 		ip0 = ip1;
 		ip1 = temp;
+		mode_temp = ip0_mode;
+		ip0_mode = ip1_mode;
+		ip1_mode = mode_temp;
 	}
 
  again:
-	xfs_ilock(ip0, xfs_lock_inumorder(lock_mode, 0));
+	xfs_ilock(ip0, xfs_lock_inumorder(ip0_mode, 0));
 
 	/*
 	 * If the first lock we have locked is in the AIL, we must TRY to get
@@ -583,18 +599,17 @@ xfs_lock_two_inodes(
 	 */
 	lp = (xfs_log_item_t *)ip0->i_itemp;
 	if (lp && (lp->li_flags & XFS_LI_IN_AIL)) {
-		if (!xfs_ilock_nowait(ip1, xfs_lock_inumorder(lock_mode, 1))) {
-			xfs_iunlock(ip0, lock_mode);
+		if (!xfs_ilock_nowait(ip1, xfs_lock_inumorder(ip1_mode, 1))) {
+			xfs_iunlock(ip0, ip0_mode);
 			if ((++attempts % 5) == 0)
 				delay(1); /* Don't just spin the CPU */
 			goto again;
 		}
 	} else {
-		xfs_ilock(ip1, xfs_lock_inumorder(lock_mode, 1));
+		xfs_ilock(ip1, xfs_lock_inumorder(ip1_mode, 1));
 	}
 }
 
-
 void
 __xfs_iflock(
 	struct xfs_inode	*ip)
@@ -1422,7 +1437,7 @@ xfs_link(
 	if (error)
 		goto std_return;
 
-	xfs_lock_two_inodes(sip, tdp, XFS_ILOCK_EXCL);
+	xfs_lock_two_inodes(sip, XFS_ILOCK_EXCL, tdp, XFS_ILOCK_EXCL);
 
 	xfs_trans_ijoin(tp, sip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, tdp, XFS_ILOCK_EXCL);
@@ -2215,7 +2230,7 @@ xfs_ifree_cluster(
 	xfs_buf_t		*bp;
 	xfs_inode_t		*ip;
 	xfs_inode_log_item_t	*iip;
-	xfs_log_item_t		*lip;
+	struct xfs_log_item	*lip;
 	struct xfs_perag	*pag;
 	xfs_ino_t		inum;
 
@@ -2273,8 +2288,7 @@ xfs_ifree_cluster(
 		 * stale first, we will not attempt to lock them in the loop
 		 * below as the XFS_ISTALE flag will be set.
 		 */
-		lip = bp->b_fspriv;
-		while (lip) {
+		list_for_each_entry(lip, &bp->b_li_list, li_bio_list) {
 			if (lip->li_type == XFS_LI_INODE) {
 				iip = (xfs_inode_log_item_t *)lip;
 				ASSERT(iip->ili_logged == 1);
@@ -2284,7 +2298,6 @@ xfs_ifree_cluster(
 							&iip->ili_item.li_lsn);
 				xfs_iflags_set(iip->ili_inode, XFS_ISTALE);
 			}
-			lip = lip->li_bio_list;
 		}
 
 
@@ -2452,6 +2465,7 @@ xfs_ifree(
 
 	VFS_I(ip)->i_mode = 0;		/* mark incore inode as free */
 	ip->i_d.di_flags = 0;
+	ip->i_d.di_flags2 = 0;
 	ip->i_d.di_dmevmask = 0;
 	ip->i_d.di_forkoff = 0;		/* mark the attr fork not in use */
 	ip->i_d.di_format = XFS_DINODE_FMT_EXTENTS;
@@ -2587,7 +2601,7 @@ xfs_remove(
 		goto std_return;
 	}
 
-	xfs_lock_two_inodes(dp, ip, XFS_ILOCK_EXCL);
+	xfs_lock_two_inodes(dp, XFS_ILOCK_EXCL, ip, XFS_ILOCK_EXCL);
 
 	xfs_trans_ijoin(tp, dp, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
@@ -3480,6 +3494,36 @@ abort_out:
 	return error;
 }
 
+/*
+ * If there are inline format data / attr forks attached to this inode,
+ * make sure they're not corrupt.
+ */
+bool
+xfs_inode_verify_forks(
+	struct xfs_inode	*ip)
+{
+	struct xfs_ifork	*ifp;
+	xfs_failaddr_t		fa;
+
+	fa = xfs_ifork_verify_data(ip, &xfs_default_ifork_ops);
+	if (fa) {
+		ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
+		xfs_inode_verifier_error(ip, -EFSCORRUPTED, "data fork",
+				ifp->if_u1.if_data, ifp->if_bytes, fa);
+		return false;
+	}
+
+	fa = xfs_ifork_verify_attr(ip, &xfs_default_ifork_ops);
+	if (fa) {
+		ifp = XFS_IFORK_PTR(ip, XFS_ATTR_FORK);
+		xfs_inode_verifier_error(ip, -EFSCORRUPTED, "attr fork",
+				ifp ? ifp->if_u1.if_data : NULL,
+				ifp ? ifp->if_bytes : 0, fa);
+		return false;
+	}
+	return true;
+}
+
 STATIC int
 xfs_iflush_int(
 	struct xfs_inode	*ip,
@@ -3502,7 +3546,7 @@ xfs_iflush_int(
 	if (XFS_TEST_ERROR(dip->di_magic != cpu_to_be16(XFS_DINODE_MAGIC),
 			       mp, XFS_ERRTAG_IFLUSH_1)) {
 		xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
-			"%s: Bad inode %Lu magic number 0x%x, ptr 0x%p",
+			"%s: Bad inode %Lu magic number 0x%x, ptr "PTR_FMT,
 			__func__, ip->i_ino, be16_to_cpu(dip->di_magic), dip);
 		goto corrupt_out;
 	}
@@ -3512,7 +3556,7 @@ xfs_iflush_int(
 		    (ip->i_d.di_format != XFS_DINODE_FMT_BTREE),
 		    mp, XFS_ERRTAG_IFLUSH_3)) {
 			xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
-				"%s: Bad regular inode %Lu, ptr 0x%p",
+				"%s: Bad regular inode %Lu, ptr "PTR_FMT,
 				__func__, ip->i_ino, ip);
 			goto corrupt_out;
 		}
@@ -3523,7 +3567,7 @@ xfs_iflush_int(
 		    (ip->i_d.di_format != XFS_DINODE_FMT_LOCAL),
 		    mp, XFS_ERRTAG_IFLUSH_4)) {
 			xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
-				"%s: Bad directory inode %Lu, ptr 0x%p",
+				"%s: Bad directory inode %Lu, ptr "PTR_FMT,
 				__func__, ip->i_ino, ip);
 			goto corrupt_out;
 		}
@@ -3532,7 +3576,7 @@ xfs_iflush_int(
 				ip->i_d.di_nblocks, mp, XFS_ERRTAG_IFLUSH_5)) {
 		xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
 			"%s: detected corrupt incore inode %Lu, "
-			"total extents = %d, nblocks = %Ld, ptr 0x%p",
+			"total extents = %d, nblocks = %Ld, ptr "PTR_FMT,
 			__func__, ip->i_ino,
 			ip->i_d.di_nextents + ip->i_d.di_anextents,
 			ip->i_d.di_nblocks, ip);
@@ -3541,7 +3585,7 @@ xfs_iflush_int(
 	if (XFS_TEST_ERROR(ip->i_d.di_forkoff > mp->m_sb.sb_inodesize,
 				mp, XFS_ERRTAG_IFLUSH_6)) {
 		xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
-			"%s: bad inode %Lu, forkoff 0x%x, ptr 0x%p",
+			"%s: bad inode %Lu, forkoff 0x%x, ptr "PTR_FMT,
 			__func__, ip->i_ino, ip->i_d.di_forkoff, ip);
 		goto corrupt_out;
 	}
@@ -3558,10 +3602,8 @@ xfs_iflush_int(
 	if (ip->i_d.di_version < 3)
 		ip->i_d.di_flushiter++;
 
-	/* Check the inline directory data. */
-	if (S_ISDIR(VFS_I(ip)->i_mode) &&
-	    ip->i_d.di_format == XFS_DINODE_FMT_LOCAL &&
-	    xfs_dir2_sf_verify(ip))
+	/* Check the inline fork data before we write out. */
+	if (!xfs_inode_verify_forks(ip))
 		goto corrupt_out;
 
 	/*
@@ -3624,7 +3666,7 @@ xfs_iflush_int(
 	/* generate the checksum. */
 	xfs_dinode_calc_crc(mp, dip);
 
-	ASSERT(bp->b_fspriv != NULL);
+	ASSERT(!list_empty(&bp->b_li_list));
 	ASSERT(bp->b_iodone != NULL);
 	return 0;