Merge tag 'xfs-4.20-merge-1' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pul xfs updates from Dave Chinner:
 "There's not a huge amount of change in this cycle - Darrick has been
  out of action for a couple of months (hence me sending the last few
  pull requests), so we decided a quiet cycle mainly focussed on bug
  fixes was a good idea. Darrick will take the helm again at the end of
  this merge window.

  FYI, I may be sending another update later in the cycle - there's a
  pending rework of the clone/dedupe_file_range code that fixes numerous
  bugs that is spread amongst the VFS, XFS and ocfs2 code. It has been
  reviewed and tested, Al and I just need to work out the details of the
  merge, so it may come from him rather than me.

  Summary:

   - only support filesystems with unwritten extents

   - add definition for statfs XFS magic number

   - remove unused parameters around reflink code

   - more debug for dangling delalloc extents

   - cancel COW extents on extent swap targets

   - fix quota stats output and clean up the code

   - refactor some of the attribute code in preparation for parent
     pointers

   - fix several buffer handling bugs"

* tag 'xfs-4.20-merge-1' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (21 commits)
  xfs: cancel COW blocks before swapext
  xfs: clear ail delwri queued bufs on unmount of shutdown fs
  xfs: use offsetof() in place of offset macros for __xfsstats
  xfs: Fix xqmstats offsets in /proc/fs/xfs/xqmstat
  xfs: fix use-after-free race in xfs_buf_rele
  xfs: Add attibute remove and helper functions
  xfs: Add attibute set and helper functions
  xfs: Add helper function xfs_attr_try_sf_addname
  xfs: Move fs/xfs/xfs_attr.h to fs/xfs/libxfs/xfs_attr.h
  xfs: issue log message on user force shutdown
  xfs: fix buffer state management in xrep_findroot_block
  xfs: always assign buffer verifiers when one is provided
  xfs: xrep_findroot_block should reject root blocks with siblings
  xfs: add a define for statfs magic to uapi
  xfs: print dangling delalloc extents
  xfs: fix fork selection in xfs_find_trim_cow_extent
  xfs: remove the unused trimmed argument from xfs_reflink_trim_around_shared
  xfs: remove the unused shared argument to xfs_reflink_reserve_cow
  xfs: handle zeroing in xfs_file_iomap_begin_delay
  xfs: remove suport for filesystems without unwritten extent flag
  ...

fs/xfs/libxfs/xfs_attr.c

@@ -191,6 +191,128 @@ xfs_attr_calc_size(
 	return nblks;
 }
 
+STATIC int
+xfs_attr_try_sf_addname(
+	struct xfs_inode	*dp,
+	struct xfs_da_args	*args)
+{
+
+	struct xfs_mount	*mp = dp->i_mount;
+	int			error, error2;
+
+	error = xfs_attr_shortform_addname(args);
+	if (error == -ENOSPC)
+		return error;
+
+	/*
+	 * Commit the shortform mods, and we're done.
+	 * NOTE: this is also the error path (EEXIST, etc).
+	 */
+	if (!error && (args->flags & ATTR_KERNOTIME) == 0)
+		xfs_trans_ichgtime(args->trans, dp, XFS_ICHGTIME_CHG);
+
+	if (mp->m_flags & XFS_MOUNT_WSYNC)
+		xfs_trans_set_sync(args->trans);
+
+	error2 = xfs_trans_commit(args->trans);
+	args->trans = NULL;
+	return error ? error : error2;
+}
+
+/*
+ * Set the attribute specified in @args.
+ */
+int
+xfs_attr_set_args(
+	struct xfs_da_args	*args,
+	struct xfs_buf          **leaf_bp)
+{
+	struct xfs_inode	*dp = args->dp;
+	int			error;
+
+	/*
+	 * If the attribute list is non-existent or a shortform list,
+	 * upgrade it to a single-leaf-block attribute list.
+	 */
+	if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL ||
+	    (dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS &&
+	     dp->i_d.di_anextents == 0)) {
+
+		/*
+		 * Build initial attribute list (if required).
+		 */
+		if (dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS)
+			xfs_attr_shortform_create(args);
+
+		/*
+		 * Try to add the attr to the attribute list in the inode.
+		 */
+		error = xfs_attr_try_sf_addname(dp, args);
+		if (error != -ENOSPC)
+			return error;
+
+		/*
+		 * It won't fit in the shortform, transform to a leaf block.
+		 * GROT: another possible req'mt for a double-split btree op.
+		 */
+		error = xfs_attr_shortform_to_leaf(args, leaf_bp);
+		if (error)
+			return error;
+
+		/*
+		 * Prevent the leaf buffer from being unlocked so that a
+		 * concurrent AIL push cannot grab the half-baked leaf
+		 * buffer and run into problems with the write verifier.
+		 */
+		xfs_trans_bhold(args->trans, *leaf_bp);
+
+		error = xfs_defer_finish(&args->trans);
+		if (error)
+			return error;
+
+		/*
+		 * Commit the leaf transformation.  We'll need another
+		 * (linked) transaction to add the new attribute to the
+		 * leaf.
+		 */
+		error = xfs_trans_roll_inode(&args->trans, dp);
+		if (error)
+			return error;
+		xfs_trans_bjoin(args->trans, *leaf_bp);
+		*leaf_bp = NULL;
+	}
+
+	if (xfs_bmap_one_block(dp, XFS_ATTR_FORK))
+		error = xfs_attr_leaf_addname(args);
+	else
+		error = xfs_attr_node_addname(args);
+	return error;
+}
+
+/*
+ * Remove the attribute specified in @args.
+ */
+int
+xfs_attr_remove_args(
+	struct xfs_da_args      *args)
+{
+	struct xfs_inode	*dp = args->dp;
+	int			error;
+
+	if (!xfs_inode_hasattr(dp)) {
+		error = -ENOATTR;
+	} else if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
+		ASSERT(dp->i_afp->if_flags & XFS_IFINLINE);
+		error = xfs_attr_shortform_remove(args);
+	} else if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) {
+		error = xfs_attr_leaf_removename(args);
+	} else {
+		error = xfs_attr_node_removename(args);
+	}
+
+	return error;
+}
+
 int
 xfs_attr_set(
 	struct xfs_inode	*dp,
@@ -204,7 +326,7 @@ xfs_attr_set(
 	struct xfs_da_args	args;
 	struct xfs_trans_res	tres;
 	int			rsvd = (flags & ATTR_ROOT) != 0;
-	int			error, err2, local;
+	int			error, local;
 
 	XFS_STATS_INC(mp, xs_attr_set);
 
@@ -255,94 +377,18 @@ xfs_attr_set(
 	error = xfs_trans_reserve_quota_nblks(args.trans, dp, args.total, 0,
 				rsvd ? XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_FORCE_RES :
 				       XFS_QMOPT_RES_REGBLKS);
-	if (error) {
-		xfs_iunlock(dp, XFS_ILOCK_EXCL);
-		xfs_trans_cancel(args.trans);
-		return error;
-	}
-
-	xfs_trans_ijoin(args.trans, dp, 0);
-
-	/*
-	 * If the attribute list is non-existent or a shortform list,
-	 * upgrade it to a single-leaf-block attribute list.
-	 */
-	if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL ||
-	    (dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS &&
-	     dp->i_d.di_anextents == 0)) {
-
-		/*
-		 * Build initial attribute list (if required).
-		 */
-		if (dp->i_d.di_aformat == XFS_DINODE_FMT_EXTENTS)
-			xfs_attr_shortform_create(&args);
-
-		/*
-		 * Try to add the attr to the attribute list in
-		 * the inode.
-		 */
-		error = xfs_attr_shortform_addname(&args);
-		if (error != -ENOSPC) {
-			/*
-			 * Commit the shortform mods, and we're done.
-			 * NOTE: this is also the error path (EEXIST, etc).
-			 */
-			ASSERT(args.trans != NULL);
-
-			/*
-			 * If this is a synchronous mount, make sure that
-			 * the transaction goes to disk before returning
-			 * to the user.
-			 */
-			if (mp->m_flags & XFS_MOUNT_WSYNC)
-				xfs_trans_set_sync(args.trans);
-
-			if (!error && (flags & ATTR_KERNOTIME) == 0) {
-				xfs_trans_ichgtime(args.trans, dp,
-							XFS_ICHGTIME_CHG);
-			}
-			err2 = xfs_trans_commit(args.trans);
-			xfs_iunlock(dp, XFS_ILOCK_EXCL);
-
-			return error ? error : err2;
-		}
-
-		/*
-		 * It won't fit in the shortform, transform to a leaf block.
-		 * GROT: another possible req'mt for a double-split btree op.
-		 */
-		error = xfs_attr_shortform_to_leaf(&args, &leaf_bp);
-		if (error)
-			goto out;
-		/*
-		 * Prevent the leaf buffer from being unlocked so that a
-		 * concurrent AIL push cannot grab the half-baked leaf
-		 * buffer and run into problems with the write verifier.
-		 */
-		xfs_trans_bhold(args.trans, leaf_bp);
-		error = xfs_defer_finish(&args.trans);
 	if (error)
-			goto out;
+		goto out_trans_cancel;
 
-		/*
-		 * Commit the leaf transformation.  We'll need another (linked)
-		 * transaction to add the new attribute to the leaf, which
-		 * means that we have to hold & join the leaf buffer here too.
-		 */
-		error = xfs_trans_roll_inode(&args.trans, dp);
+	xfs_trans_ijoin(args.trans, dp, 0);
+	error = xfs_attr_set_args(&args, &leaf_bp);
 	if (error)
-			goto out;
-		xfs_trans_bjoin(args.trans, leaf_bp);
-		leaf_bp = NULL;
+		goto out_release_leaf;
+	if (!args.trans) {
+		/* shortform attribute has already been committed */
+		goto out_unlock;
 	}
 
-	if (xfs_bmap_one_block(dp, XFS_ATTR_FORK))
-		error = xfs_attr_leaf_addname(&args);
-	else
-		error = xfs_attr_node_addname(&args);
-	if (error)
-		goto out;
-
 	/*
 	 * If this is a synchronous mount, make sure that the
 	 * transaction goes to disk before returning to the user.
@@ -358,17 +404,17 @@ xfs_attr_set(
 	 */
 	xfs_trans_log_inode(args.trans, dp, XFS_ILOG_CORE);
 	error = xfs_trans_commit(args.trans);
+out_unlock:
 	xfs_iunlock(dp, XFS_ILOCK_EXCL);
-
 	return error;
 
-out:
+out_release_leaf:
 	if (leaf_bp)
 		xfs_trans_brelse(args.trans, leaf_bp);
+out_trans_cancel:
 	if (args.trans)
 		xfs_trans_cancel(args.trans);
-	xfs_iunlock(dp, XFS_ILOCK_EXCL);
-	return error;
+	goto out_unlock;
 }
 
 /*
@@ -423,17 +469,7 @@ xfs_attr_remove(
 	 */
 	xfs_trans_ijoin(args.trans, dp, 0);
 
-	if (!xfs_inode_hasattr(dp)) {
-		error = -ENOATTR;
-	} else if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
-		ASSERT(dp->i_afp->if_flags & XFS_IFINLINE);
-		error = xfs_attr_shortform_remove(&args);
-	} else if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) {
-		error = xfs_attr_leaf_removename(&args);
-	} else {
-		error = xfs_attr_node_removename(&args);
-	}
-
+	error = xfs_attr_remove_args(&args);
 	if (error)
 		goto out;
 

fs/xfs/xfs_attr.h → fs/xfs/libxfs/xfs_attr.h

@@ -140,7 +140,9 @@ int xfs_attr_get(struct xfs_inode *ip, const unsigned char *name,
 		 unsigned char *value, int *valuelenp, int flags);
 int xfs_attr_set(struct xfs_inode *dp, const unsigned char *name,
 		 unsigned char *value, int valuelen, int flags);
+int xfs_attr_set_args(struct xfs_da_args *args, struct xfs_buf **leaf_bp);
 int xfs_attr_remove(struct xfs_inode *dp, const unsigned char *name, int flags);
+int xfs_attr_remove_args(struct xfs_da_args *args);
 int xfs_attr_list(struct xfs_inode *dp, char *buffer, int bufsize,
 		  int flags, struct attrlist_cursor_kern *cursor);
 

fs/xfs/libxfs/xfs_bmap.c

@@ -1019,6 +1019,34 @@ xfs_bmap_add_attrfork_local(
 	return -EFSCORRUPTED;
 }
 
+/* Set an inode attr fork off based on the format */
+int
+xfs_bmap_set_attrforkoff(
+	struct xfs_inode	*ip,
+	int			size,
+	int			*version)
+{
+	switch (ip->i_d.di_format) {
+	case XFS_DINODE_FMT_DEV:
+		ip->i_d.di_forkoff = roundup(sizeof(xfs_dev_t), 8) >> 3;
+		break;
+	case XFS_DINODE_FMT_LOCAL:
+	case XFS_DINODE_FMT_EXTENTS:
+	case XFS_DINODE_FMT_BTREE:
+		ip->i_d.di_forkoff = xfs_attr_shortform_bytesfit(ip, size);
+		if (!ip->i_d.di_forkoff)
+			ip->i_d.di_forkoff = xfs_default_attroffset(ip) >> 3;
+		else if ((ip->i_mount->m_flags & XFS_MOUNT_ATTR2) && version)
+			*version = 2;
+		break;
+	default:
+		ASSERT(0);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 /*
  * Convert inode from non-attributed to attributed.
  * Must not be in a transaction, ip must not be locked.
@@ -1070,26 +1098,9 @@ xfs_bmap_add_attrfork(
 
 	xfs_trans_ijoin(tp, ip, 0);
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-
-	switch (ip->i_d.di_format) {
-	case XFS_DINODE_FMT_DEV:
-		ip->i_d.di_forkoff = roundup(sizeof(xfs_dev_t), 8) >> 3;
-		break;
-	case XFS_DINODE_FMT_LOCAL:
-	case XFS_DINODE_FMT_EXTENTS:
-	case XFS_DINODE_FMT_BTREE:
-		ip->i_d.di_forkoff = xfs_attr_shortform_bytesfit(ip, size);
-		if (!ip->i_d.di_forkoff)
-			ip->i_d.di_forkoff = xfs_default_attroffset(ip) >> 3;
-		else if (mp->m_flags & XFS_MOUNT_ATTR2)
-			version = 2;
-		break;
-	default:
-		ASSERT(0);
-		error = -EINVAL;
+	error = xfs_bmap_set_attrforkoff(ip, size, &version);
+	if (error)
 		goto trans_cancel;
-	}
-
 	ASSERT(ip->i_afp == NULL);
 	ip->i_afp = kmem_zone_zalloc(xfs_ifork_zone, KM_SLEEP);
 	ip->i_afp->if_flags = XFS_IFEXTENTS;
@@ -4081,8 +4092,7 @@ xfs_bmapi_allocate(
 	 * extents to real extents when we're about to write the data.
 	 */
 	if ((!bma->wasdel || (bma->flags & XFS_BMAPI_COWFORK)) &&
-	    (bma->flags & XFS_BMAPI_PREALLOC) &&
-	    xfs_sb_version_hasextflgbit(&mp->m_sb))
+	    (bma->flags & XFS_BMAPI_PREALLOC))
 		bma->got.br_state = XFS_EXT_UNWRITTEN;
 
 	if (bma->wasdel)
@@ -5245,8 +5255,7 @@ __xfs_bunmapi(
 			 * unmapping part of it.  But we can't really
 			 * get rid of part of a realtime extent.
 			 */
-			if (del.br_state == XFS_EXT_UNWRITTEN ||
-			    !xfs_sb_version_hasextflgbit(&mp->m_sb)) {
+			if (del.br_state == XFS_EXT_UNWRITTEN) {
 				/*
 				 * This piece is unwritten, or we're not
 				 * using unwritten extents.  Skip over it.
@@ -5296,10 +5305,9 @@ __xfs_bunmapi(
 				del.br_blockcount -= mod;
 				del.br_startoff += mod;
 				del.br_startblock += mod;
-			} else if ((del.br_startoff == start &&
+			} else if (del.br_startoff == start &&
 				   (del.br_state == XFS_EXT_UNWRITTEN ||
-				     tp->t_blk_res == 0)) ||
-				   !xfs_sb_version_hasextflgbit(&mp->m_sb)) {
+				    tp->t_blk_res == 0)) {
 				/*
 				 * Can't make it unwritten.  There isn't
 				 * a full extent here so just skip it.
@@ -6114,11 +6122,7 @@ xfs_bmap_validate_extent(
 		    XFS_FSB_TO_AGNO(mp, endfsb))
 			return __this_address;
 	}
-	if (irec->br_state != XFS_EXT_NORM) {
-		if (whichfork != XFS_DATA_FORK)
+	if (irec->br_state != XFS_EXT_NORM && whichfork != XFS_DATA_FORK)
 		return __this_address;
-		if (!xfs_sb_version_hasextflgbit(&mp->m_sb))
-			return __this_address;
-	}
 	return NULL;
 }

fs/xfs/libxfs/xfs_bmap.h

@@ -183,6 +183,7 @@ void	xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno,
 		xfs_filblks_t len);
 void	xfs_trim_extent_eof(struct xfs_bmbt_irec *, struct xfs_inode *);
 int	xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd);
+int	xfs_bmap_set_attrforkoff(struct xfs_inode *ip, int size, int *version);
 void	xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork);
 void	__xfs_bmap_add_free(struct xfs_trans *tp, xfs_fsblock_t bno,
 		xfs_filblks_t len, struct xfs_owner_info *oinfo,

fs/xfs/libxfs/xfs_format.h

@@ -287,6 +287,8 @@ static inline bool xfs_sb_good_v4_features(struct xfs_sb *sbp)
 {
 	if (!(sbp->sb_versionnum & XFS_SB_VERSION_DIRV2BIT))
 		return false;
+	if (!(sbp->sb_versionnum & XFS_SB_VERSION_EXTFLGBIT))
+		return false;
 
 	/* check for unknown features in the fs */
 	if ((sbp->sb_versionnum & ~XFS_SB_VERSION_OKBITS) ||
@@ -357,12 +359,6 @@ static inline bool xfs_sb_version_haslogv2(struct xfs_sb *sbp)
 	       (sbp->sb_versionnum & XFS_SB_VERSION_LOGV2BIT);
 }
 
-static inline bool xfs_sb_version_hasextflgbit(struct xfs_sb *sbp)
-{
-	return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5 ||
-	       (sbp->sb_versionnum & XFS_SB_VERSION_EXTFLGBIT);
-}
-
 static inline bool xfs_sb_version_hassector(struct xfs_sb *sbp)
 {
 	return (sbp->sb_versionnum & XFS_SB_VERSION_SECTORBIT);

fs/xfs/libxfs/xfs_sb.c

@@ -1115,7 +1115,8 @@ xfs_fs_geometry(
 
 	geo->version = XFS_FSOP_GEOM_VERSION;
 	geo->flags = XFS_FSOP_GEOM_FLAGS_NLINK |
-		     XFS_FSOP_GEOM_FLAGS_DIRV2;
+		     XFS_FSOP_GEOM_FLAGS_DIRV2 |
+		     XFS_FSOP_GEOM_FLAGS_EXTFLG;
 	if (xfs_sb_version_hasattr(sbp))
 		geo->flags |= XFS_FSOP_GEOM_FLAGS_ATTR;
 	if (xfs_sb_version_hasquota(sbp))
@@ -1124,8 +1125,6 @@ xfs_fs_geometry(
 		geo->flags |= XFS_FSOP_GEOM_FLAGS_IALIGN;
 	if (xfs_sb_version_hasdalign(sbp))
 		geo->flags |= XFS_FSOP_GEOM_FLAGS_DALIGN;
-	if (xfs_sb_version_hasextflgbit(sbp))
-		geo->flags |= XFS_FSOP_GEOM_FLAGS_EXTFLG;
 	if (xfs_sb_version_hassector(sbp))
 		geo->flags |= XFS_FSOP_GEOM_FLAGS_SECTOR;
 	if (xfs_sb_version_hasasciici(sbp))

fs/xfs/scrub/repair.c

@@ -29,6 +29,8 @@
 #include "xfs_ag_resv.h"
 #include "xfs_trans_space.h"
 #include "xfs_quota.h"
+#include "xfs_attr.h"
+#include "xfs_reflink.h"
 #include "scrub/xfs_scrub.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
@@ -692,13 +694,14 @@ xrep_findroot_block(
 	struct xrep_find_ag_btree	*fab,
 	uint64_t			owner,
 	xfs_agblock_t			agbno,
-	bool				*found_it)
+	bool				*done_with_block)
 {
 	struct xfs_mount		*mp = ri->sc->mp;
 	struct xfs_buf			*bp;
 	struct xfs_btree_block		*btblock;
 	xfs_daddr_t			daddr;
-	int				error;
+	int				block_level;
+	int				error = 0;
 
 	daddr = XFS_AGB_TO_DADDR(mp, ri->sc->sa.agno, agbno);
 
@@ -717,36 +720,111 @@ xrep_findroot_block(
 			return error;
 	}
 
+	/*
+	 * Read the buffer into memory so that we can see if it's a match for
+	 * our btree type.  We have no clue if it is beforehand, and we want to
+	 * avoid xfs_trans_read_buf's behavior of dumping the DONE state (which
+	 * will cause needless disk reads in subsequent calls to this function)
+	 * and logging metadata verifier failures.
+	 *
+	 * Therefore, pass in NULL buffer ops.  If the buffer was already in
+	 * memory from some other caller it will already have b_ops assigned.
+	 * If it was in memory from a previous unsuccessful findroot_block
+	 * call, the buffer won't have b_ops but it should be clean and ready
+	 * for us to try to verify if the read call succeeds.  The same applies
+	 * if the buffer wasn't in memory at all.
+	 *
+	 * Note: If we never match a btree type with this buffer, it will be
+	 * left in memory with NULL b_ops.  This shouldn't be a problem unless
+	 * the buffer gets written.
+	 */
 	error = xfs_trans_read_buf(mp, ri->sc->tp, mp->m_ddev_targp, daddr,
 			mp->m_bsize, 0, &bp, NULL);
 	if (error)
 		return error;
 
-	/*
-	 * Does this look like a block matching our fs and higher than any
-	 * other block we've found so far?  If so, reattach buffer verifiers
-	 * so the AIL won't complain if the buffer is also dirty.
-	 */
+	/* Ensure the block magic matches the btree type we're looking for. */
 	btblock = XFS_BUF_TO_BLOCK(bp);
 	if (be32_to_cpu(btblock->bb_magic) != fab->magic)
 		goto out;
-	if (xfs_sb_version_hascrc(&mp->m_sb) &&
-	    !uuid_equal(&btblock->bb_u.s.bb_uuid, &mp->m_sb.sb_meta_uuid))
+
+	/*
+	 * If the buffer already has ops applied and they're not the ones for
+	 * this btree type, we know this block doesn't match the btree and we
+	 * can bail out.
+	 *
+	 * If the buffer ops match ours, someone else has already validated
+	 * the block for us, so we can move on to checking if this is a root
+	 * block candidate.
+	 *
+	 * If the buffer does not have ops, nobody has successfully validated
+	 * the contents and the buffer cannot be dirty.  If the magic, uuid,
+	 * and structure match this btree type then we'll move on to checking
+	 * if it's a root block candidate.  If there is no match, bail out.
+	 */
+	if (bp->b_ops) {
+		if (bp->b_ops != fab->buf_ops)
+			goto out;
+	} else {
+		ASSERT(!xfs_trans_buf_is_dirty(bp));
+		if (!uuid_equal(&btblock->bb_u.s.bb_uuid,
+				&mp->m_sb.sb_meta_uuid))
+			goto out;
+		fab->buf_ops->verify_read(bp);
+		if (bp->b_error) {
+			bp->b_error = 0;
 			goto out;
+		}
+
+		/*
+		 * Some read verifiers will (re)set b_ops, so we must be
+		 * careful not to blow away any such assignment.
+		 */
+		if (!bp->b_ops)
 			bp->b_ops = fab->buf_ops;
+	}
 
-	/* Ignore this block if it's lower in the tree than we've seen. */
-	if (fab->root != NULLAGBLOCK &&
-	    xfs_btree_get_level(btblock) < fab->height)
-		goto out;
+	/*
+	 * This block passes the magic/uuid and verifier tests for this btree
+	 * type.  We don't need the caller to try the other tree types.
+	 */
+	*done_with_block = true;
 
-	/* Make sure we pass the verifiers. */
-	bp->b_ops->verify_read(bp);
-	if (bp->b_error)
+	/*
+	 * Compare this btree block's level to the height of the current
+	 * candidate root block.
+	 *
+	 * If the level matches the root we found previously, throw away both
+	 * blocks because there can't be two candidate roots.
+	 *
+	 * If level is lower in the tree than the root we found previously,
+	 * ignore this block.
+	 */
+	block_level = xfs_btree_get_level(btblock);
+	if (block_level + 1 == fab->height) {
+		fab->root = NULLAGBLOCK;
+		goto out;
+	} else if (block_level < fab->height) {
 		goto out;
+	}
+
+	/*
+	 * This is the highest block in the tree that we've found so far.
+	 * Update the btree height to reflect what we've learned from this
+	 * block.
+	 */
+	fab->height = block_level + 1;
+
+	/*
+	 * If this block doesn't have sibling pointers, then it's the new root
+	 * block candidate.  Otherwise, the root will be found farther up the
+	 * tree.
+	 */
+	if (btblock->bb_u.s.bb_leftsib == cpu_to_be32(NULLAGBLOCK) &&
+	    btblock->bb_u.s.bb_rightsib == cpu_to_be32(NULLAGBLOCK))
 		fab->root = agbno;
-	fab->height = xfs_btree_get_level(btblock) + 1;
-	*found_it = true;
+	else
+		fab->root = NULLAGBLOCK;
 
 	trace_xrep_findroot_block(mp, ri->sc->sa.agno, agbno,
 			be32_to_cpu(btblock->bb_magic), fab->height - 1);
@@ -768,7 +846,7 @@ xrep_findroot_rmap(
 	struct xrep_findroot		*ri = priv;
 	struct xrep_find_ag_btree	*fab;
 	xfs_agblock_t			b;
-	bool				found_it;
+	bool				done;
 	int				error = 0;
 
 	/* Ignore anything that isn't AG metadata. */
@@ -777,16 +855,16 @@ xrep_findroot_rmap(
 
 	/* Otherwise scan each block + btree type. */
 	for (b = 0; b < rec->rm_blockcount; b++) {
-		found_it = false;
+		done = false;
 		for (fab = ri->btree_info; fab->buf_ops; fab++) {
 			if (rec->rm_owner != fab->rmap_owner)
 				continue;
 			error = xrep_findroot_block(ri, fab,
 					rec->rm_owner, rec->rm_startblock + b,
-					&found_it);
+					&done);
 			if (error)
 				return error;
-			if (found_it)
+			if (done)
 				break;
 		}
 	}

fs/xfs/scrub/scrub.c

@@ -412,19 +412,6 @@ xchk_validate_inputs(
 		goto out;
 	}
 
-	error = -EOPNOTSUPP;
-	/*
-	 * We won't scrub any filesystem that doesn't have the ability
-	 * to record unwritten extents.  The option was made default in
-	 * 2003, removed from mkfs in 2007, and cannot be disabled in
-	 * v5, so if we find a filesystem without this flag it's either
-	 * really old or totally unsupported.  Avoid it either way.
-	 * We also don't support v1-v3 filesystems, which aren't
-	 * mountable.
-	 */
-	if (!xfs_sb_version_hasextflgbit(&mp->m_sb))
-		goto out;
-
 	/*
 	 * We only want to repair read-write v5+ filesystems.  Defer the check
 	 * for ops->repair until after our scrub confirms that we need to

fs/xfs/xfs_aops.c

@@ -917,7 +917,7 @@ xfs_vm_writepage(
 	struct writeback_control *wbc)
 {
 	struct xfs_writepage_ctx wpc = {
-		.io_type = XFS_IO_INVALID,
+		.io_type = XFS_IO_HOLE,
 	};
 	int			ret;
 
@@ -933,7 +933,7 @@ xfs_vm_writepages(
 	struct writeback_control *wbc)
 {
 	struct xfs_writepage_ctx wpc = {
-		.io_type = XFS_IO_INVALID,
+		.io_type = XFS_IO_HOLE,
 	};
 	int			ret;
 

fs/xfs/xfs_aops.h

@@ -12,21 +12,19 @@ extern struct bio_set xfs_ioend_bioset;
  * Types of I/O for bmap clustering and I/O completion tracking.
  */
 enum {
-	XFS_IO_INVALID,		/* initial state */
+	XFS_IO_HOLE,		/* covers region without any block allocation */
 	XFS_IO_DELALLOC,	/* covers delalloc region */
 	XFS_IO_UNWRITTEN,	/* covers allocated but uninitialized data */
 	XFS_IO_OVERWRITE,	/* covers already allocated extent */
 	XFS_IO_COW,		/* covers copy-on-write extent */
-	XFS_IO_HOLE,		/* covers region without any block allocation */
 };
 
 #define XFS_IO_TYPES \
-	{ XFS_IO_INVALID,		"invalid" }, \
+	{ XFS_IO_HOLE,			"hole" },	\
 	{ XFS_IO_DELALLOC,		"delalloc" },	\
 	{ XFS_IO_UNWRITTEN,		"unwritten" },	\
 	{ XFS_IO_OVERWRITE,		"overwrite" },	\
-	{ XFS_IO_COW,			"CoW" }, \
-	{ XFS_IO_HOLE,			"hole" }
+	{ XFS_IO_COW,			"CoW" }
 
 /*
  * Structure for buffered I/O completions.

fs/xfs/xfs_bmap_util.c

@@ -406,10 +406,10 @@ xfs_getbmap_report_one(
 	struct xfs_bmbt_irec	*got)
 {
 	struct kgetbmap		*p = out + bmv->bmv_entries;
-	bool			shared = false, trimmed = false;
+	bool			shared = false;
 	int			error;
 
-	error = xfs_reflink_trim_around_shared(ip, got, &shared, &trimmed);
+	error = xfs_reflink_trim_around_shared(ip, got, &shared);
 	if (error)
 		return error;
 
@@ -1042,44 +1042,6 @@ xfs_unmap_extent(
 	goto out_unlock;
 }
 
-static int
-xfs_adjust_extent_unmap_boundaries(
-	struct xfs_inode	*ip,
-	xfs_fileoff_t		*startoffset_fsb,
-	xfs_fileoff_t		*endoffset_fsb)
-{
-	struct xfs_mount	*mp = ip->i_mount;
-	struct xfs_bmbt_irec	imap;
-	int			nimap, error;
-	xfs_extlen_t		mod = 0;
-
-	nimap = 1;
-	error = xfs_bmapi_read(ip, *startoffset_fsb, 1, &imap, &nimap, 0);
-	if (error)
-		return error;
-
-	if (nimap && imap.br_startblock != HOLESTARTBLOCK) {
-		ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
-		div_u64_rem(imap.br_startblock, mp->m_sb.sb_rextsize, &mod);
-		if (mod)
-			*startoffset_fsb += mp->m_sb.sb_rextsize - mod;
-	}
-
-	nimap = 1;
-	error = xfs_bmapi_read(ip, *endoffset_fsb - 1, 1, &imap, &nimap, 0);
-	if (error)
-		return error;
-
-	if (nimap && imap.br_startblock != HOLESTARTBLOCK) {
-		ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
-		mod++;
-		if (mod && mod != mp->m_sb.sb_rextsize)
-			*endoffset_fsb -= mod;
-	}
-
-	return 0;
-}
-
 static int
 xfs_flush_unmap_range(
 	struct xfs_inode	*ip,
@@ -1133,19 +1095,8 @@ xfs_free_file_space(
 	endoffset_fsb = XFS_B_TO_FSBT(mp, offset + len);
 
 	/*
-	 * Need to zero the stuff we're not freeing, on disk.  If it's a RT file
-	 * and we can't use unwritten extents then we actually need to ensure
-	 * to zero the whole extent, otherwise we just need to take of block
-	 * boundaries, and xfs_bunmapi will handle the rest.
-	 */
-	if (XFS_IS_REALTIME_INODE(ip) &&
-	    !xfs_sb_version_hasextflgbit(&mp->m_sb)) {
-		error = xfs_adjust_extent_unmap_boundaries(ip, &startoffset_fsb,
-				&endoffset_fsb);
-		if (error)
-			return error;
-	}
-
+	 * Need to zero the stuff we're not freeing, on disk.
+	 */
 	if (endoffset_fsb > startoffset_fsb) {
 		while (!done) {
 			error = xfs_unmap_extent(ip, startoffset_fsb,
@@ -1824,6 +1775,12 @@ xfs_swap_extents(
 	if (error)
 		goto out_unlock;
 
+	if (xfs_inode_has_cow_data(tip)) {
+		error = xfs_reflink_cancel_cow_range(tip, 0, NULLFILEOFF, true);
+		if (error)
+			return error;
+	}
+
 	/*
 	 * Extent "swapping" with rmap requires a permanent reservation and
 	 * a block reservation because it's really just a remap operation

fs/xfs/xfs_buf.c

@@ -37,6 +37,32 @@ static kmem_zone_t *xfs_buf_zone;
 #define xb_to_gfp(flags) \
 	((((flags) & XBF_READ_AHEAD) ? __GFP_NORETRY : GFP_NOFS) | __GFP_NOWARN)
 
+/*
+ * Locking orders
+ *
+ * xfs_buf_ioacct_inc:
+ * xfs_buf_ioacct_dec:
+ *	b_sema (caller holds)
+ *	  b_lock
+ *
+ * xfs_buf_stale:
+ *	b_sema (caller holds)
+ *	  b_lock
+ *	    lru_lock
+ *
+ * xfs_buf_rele:
+ *	b_lock
+ *	  pag_buf_lock
+ *	    lru_lock
+ *
+ * xfs_buftarg_wait_rele
+ *	lru_lock
+ *	  b_lock (trylock due to inversion)
+ *
+ * xfs_buftarg_isolate
+ *	lru_lock
+ *	  b_lock (trylock due to inversion)
+ */
 
 static inline int
 xfs_buf_is_vmapped(
@@ -749,6 +775,30 @@ _xfs_buf_read(
 	return xfs_buf_submit(bp);
 }
 
+/*
+ * If the caller passed in an ops structure and the buffer doesn't have ops
+ * assigned, set the ops and use them to verify the contents.  If the contents
+ * cannot be verified, we'll clear XBF_DONE.  We assume the buffer has no
+ * recorded errors and is already in XBF_DONE state.
+ */
+int
+xfs_buf_ensure_ops(
+	struct xfs_buf		*bp,
+	const struct xfs_buf_ops *ops)
+{
+	ASSERT(bp->b_flags & XBF_DONE);
+	ASSERT(bp->b_error == 0);
+
+	if (!ops || bp->b_ops)
+		return 0;
+
+	bp->b_ops = ops;
+	bp->b_ops->verify_read(bp);
+	if (bp->b_error)
+		bp->b_flags &= ~XBF_DONE;
+	return bp->b_error;
+}
+
 xfs_buf_t *
 xfs_buf_read_map(
 	struct xfs_buftarg	*target,
@@ -762,26 +812,32 @@ xfs_buf_read_map(
 	flags |= XBF_READ;
 
 	bp = xfs_buf_get_map(target, map, nmaps, flags);
-	if (bp) {
+	if (!bp)
+		return NULL;
+
 	trace_xfs_buf_read(bp, flags, _RET_IP_);
 
 	if (!(bp->b_flags & XBF_DONE)) {
 		XFS_STATS_INC(target->bt_mount, xb_get_read);
 		bp->b_ops = ops;
 		_xfs_buf_read(bp, flags);
-		} else if (flags & XBF_ASYNC) {
+		return bp;
+	}
+
+	xfs_buf_ensure_ops(bp, ops);
+
+	if (flags & XBF_ASYNC) {
 		/*
 		 * Read ahead call which is already satisfied,
 		 * drop the buffer
 		 */
 		xfs_buf_relse(bp);
 		return NULL;
-		} else {
-			/* We do not want read in the flags */
-			bp->b_flags &= ~XBF_READ;
-		}
 	}
 
+	/* We do not want read in the flags */
+	bp->b_flags &= ~XBF_READ;
+	ASSERT(bp->b_ops != NULL || ops == NULL);
 	return bp;
 }
 
@@ -1006,8 +1062,18 @@ xfs_buf_rele(
 
 	ASSERT(atomic_read(&bp->b_hold) > 0);
 
-	release = atomic_dec_and_lock(&bp->b_hold, &pag->pag_buf_lock);
+	/*
+	 * We grab the b_lock here first to serialise racing xfs_buf_rele()
+	 * calls. The pag_buf_lock being taken on the last reference only
+	 * serialises against racing lookups in xfs_buf_find(). IOWs, the second
+	 * to last reference we drop here is not serialised against the last
+	 * reference until we take bp->b_lock. Hence if we don't grab b_lock
+	 * first, the last "release" reference can win the race to the lock and
+	 * free the buffer before the second-to-last reference is processed,
+	 * leading to a use-after-free scenario.
+	 */
 	spin_lock(&bp->b_lock);
+	release = atomic_dec_and_lock(&bp->b_hold, &pag->pag_buf_lock);
 	if (!release) {
 		/*
 		 * Drop the in-flight state if the buffer is already on the LRU
@@ -1989,6 +2055,13 @@ xfs_buf_delwri_submit_buffers(
  * is only safely useable for callers that can track I/O completion by higher
  * level means, e.g. AIL pushing as the @buffer_list is consumed in this
  * function.
+ *
+ * Note: this function will skip buffers it would block on, and in doing so
+ * leaves them on @buffer_list so they can be retried on a later pass. As such,
+ * it is up to the caller to ensure that the buffer list is fully submitted or
+ * cancelled appropriately when they are finished with the list. Failure to
+ * cancel or resubmit the list until it is empty will result in leaked buffers
+ * at unmount time.
  */
 int
 xfs_buf_delwri_submit_nowait(

fs/xfs/xfs_buf.h

@@ -385,4 +385,6 @@ extern int xfs_setsize_buftarg(xfs_buftarg_t *, unsigned int);
 #define xfs_getsize_buftarg(buftarg)	block_size((buftarg)->bt_bdev)
 #define xfs_readonly_buftarg(buftarg)	bdev_read_only((buftarg)->bt_bdev)
 
+int xfs_buf_ensure_ops(struct xfs_buf *bp, const struct xfs_buf_ops *ops);
+
 #endif	/* __XFS_BUF_H__ */

fs/xfs/xfs_fsops.c

@@ -470,20 +470,13 @@ xfs_fs_goingdown(
  */
 void
 xfs_do_force_shutdown(
-	xfs_mount_t	*mp,
+	struct xfs_mount *mp,
 	int		flags,
 	char		*fname,
 	int		lnnum)
 {
-	int		logerror;
+	bool		logerror = flags & SHUTDOWN_LOG_IO_ERROR;
 
-	logerror = flags & SHUTDOWN_LOG_IO_ERROR;
-
-	if (!(flags & SHUTDOWN_FORCE_UMOUNT)) {
-		xfs_notice(mp,
-	"%s(0x%x) called from line %d of file %s.  Return address = "PTR_FMT,
-			__func__, flags, lnnum, fname, __return_address);
-	}
 	/*
 	 * No need to duplicate efforts.
 	 */
@@ -499,13 +492,22 @@ xfs_do_force_shutdown(
 	if (xfs_log_force_umount(mp, logerror))
 		return;
 
+	if (flags & SHUTDOWN_FORCE_UMOUNT) {
+		xfs_alert(mp,
+"User initiated shutdown received. Shutting down filesystem");
+		return;
+	}
+
+	xfs_notice(mp,
+"%s(0x%x) called from line %d of file %s. Return address = "PTR_FMT,
+		__func__, flags, lnnum, fname, __return_address);
+
 	if (flags & SHUTDOWN_CORRUPT_INCORE) {
 		xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_CORRUPT,
-    "Corruption of in-memory data detected.  Shutting down filesystem");
+"Corruption of in-memory data detected.  Shutting down filesystem");
 		if (XFS_ERRLEVEL_HIGH <= xfs_error_level)
 			xfs_stack_trace();
-	} else if (!(flags & SHUTDOWN_FORCE_UMOUNT)) {
-		if (logerror) {
+	} else if (logerror) {
 		xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_LOGERROR,
 			"Log I/O Error Detected. Shutting down filesystem");
 	} else if (flags & SHUTDOWN_DEVICE_REQ) {
@@ -515,11 +517,9 @@ xfs_do_force_shutdown(
 		xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_IOERROR,
 			"I/O Error Detected. Shutting down filesystem");
 	}
-	}
-	if (!(flags & SHUTDOWN_FORCE_UMOUNT)) {
+
 	xfs_alert(mp,
-	"Please umount the filesystem and rectify the problem(s)");
-	}
+		"Please unmount the filesystem and rectify the problem(s)");
 }
 
 /*

fs/xfs/xfs_ioctl.c

@@ -604,14 +604,6 @@ xfs_ioc_space(
 	uint			iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
 	int			error;
 
-	/*
-	 * Only allow the sys admin to reserve space unless
-	 * unwritten extents are enabled.
-	 */
-	if (!xfs_sb_version_hasextflgbit(&ip->i_mount->m_sb) &&
-	    !capable(CAP_SYS_ADMIN))
-		return -EPERM;
-
 	if (inode->i_flags & (S_IMMUTABLE|S_APPEND))
 		return -EPERM;
 

fs/xfs/xfs_iomap.c

@@ -62,6 +62,21 @@ xfs_bmbt_to_iomap(
 	iomap->dax_dev = xfs_find_daxdev_for_inode(VFS_I(ip));
 }
 
+static void
+xfs_hole_to_iomap(
+	struct xfs_inode	*ip,
+	struct iomap		*iomap,
+	xfs_fileoff_t		offset_fsb,
+	xfs_fileoff_t		end_fsb)
+{
+	iomap->addr = IOMAP_NULL_ADDR;
+	iomap->type = IOMAP_HOLE;
+	iomap->offset = XFS_FSB_TO_B(ip->i_mount, offset_fsb);
+	iomap->length = XFS_FSB_TO_B(ip->i_mount, end_fsb - offset_fsb);
+	iomap->bdev = xfs_find_bdev_for_inode(VFS_I(ip));
+	iomap->dax_dev = xfs_find_daxdev_for_inode(VFS_I(ip));
+}
+
 xfs_extlen_t
 xfs_eof_alignment(
 	struct xfs_inode	*ip,
@@ -502,6 +517,7 @@ xfs_file_iomap_begin_delay(
 	struct inode		*inode,
 	loff_t			offset,
 	loff_t			count,
+	unsigned		flags,
 	struct iomap		*iomap)
 {
 	struct xfs_inode	*ip = XFS_I(inode);
@@ -538,15 +554,23 @@ xfs_file_iomap_begin_delay(
 			goto out_unlock;
 	}
 
+	end_fsb = min(XFS_B_TO_FSB(mp, offset + count), maxbytes_fsb);
+
 	eof = !xfs_iext_lookup_extent(ip, ifp, offset_fsb, &icur, &got);
-	if (!eof && got.br_startoff <= offset_fsb) {
-		if (xfs_is_reflink_inode(ip)) {
-			bool		shared;
+	if (eof)
+		got.br_startoff = end_fsb; /* fake hole until the end */
 
-			end_fsb = min(XFS_B_TO_FSB(mp, offset + count),
-					maxbytes_fsb);
+	if (got.br_startoff <= offset_fsb) {
+		/*
+		 * For reflink files we may need a delalloc reservation when
+		 * overwriting shared extents.   This includes zeroing of
+		 * existing extents that contain data.
+		 */
+		if (xfs_is_reflink_inode(ip) &&
+		    ((flags & IOMAP_WRITE) ||
+		     got.br_state != XFS_EXT_UNWRITTEN)) {
 			xfs_trim_extent(&got, offset_fsb, end_fsb - offset_fsb);
-			error = xfs_reflink_reserve_cow(ip, &got, &shared);
+			error = xfs_reflink_reserve_cow(ip, &got);
 			if (error)
 				goto out_unlock;
 		}
@@ -555,6 +579,11 @@ xfs_file_iomap_begin_delay(
 		goto done;
 	}
 
+	if (flags & IOMAP_ZERO) {
+		xfs_hole_to_iomap(ip, iomap, offset_fsb, got.br_startoff);
+		goto out_unlock;
+	}
+
 	error = xfs_qm_dqattach_locked(ip, false);
 	if (error)
 		goto out_unlock;
@@ -1003,16 +1032,17 @@ xfs_file_iomap_begin(
 	struct xfs_bmbt_irec	imap;
 	xfs_fileoff_t		offset_fsb, end_fsb;
 	int			nimaps = 1, error = 0;
-	bool			shared = false, trimmed = false;
+	bool			shared = false;
 	unsigned		lockmode;
 
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
 
-	if (((flags & (IOMAP_WRITE | IOMAP_DIRECT)) == IOMAP_WRITE) &&
+	if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && !(flags & IOMAP_DIRECT) &&
 			!IS_DAX(inode) && !xfs_get_extsz_hint(ip)) {
 		/* Reserve delalloc blocks for regular writeback. */
-		return xfs_file_iomap_begin_delay(inode, offset, length, iomap);
+		return xfs_file_iomap_begin_delay(inode, offset, length, flags,
+				iomap);
 	}
 
 	/*
@@ -1038,8 +1068,7 @@ xfs_file_iomap_begin(
 
 	if (flags & IOMAP_REPORT) {
 		/* Trim the mapping to the nearest shared extent boundary. */
-		error = xfs_reflink_trim_around_shared(ip, &imap, &shared,
-				&trimmed);
+		error = xfs_reflink_trim_around_shared(ip, &imap, &shared);
 		if (error)
 			goto out_unlock;
 	}
@@ -1065,7 +1094,7 @@ xfs_file_iomap_begin(
 			if (error)
 				goto out_unlock;
 		} else {
-			error = xfs_reflink_reserve_cow(ip, &imap, &shared);
+			error = xfs_reflink_reserve_cow(ip, &imap);
 			if (error)
 				goto out_unlock;
 		}

fs/xfs/xfs_reflink.c

@@ -182,8 +182,7 @@ int
 xfs_reflink_trim_around_shared(
 	struct xfs_inode	*ip,
 	struct xfs_bmbt_irec	*irec,
-	bool			*shared,
-	bool			*trimmed)
+	bool			*shared)
 {
 	xfs_agnumber_t		agno;
 	xfs_agblock_t		agbno;
@@ -209,7 +208,7 @@ xfs_reflink_trim_around_shared(
 	if (error)
 		return error;
 
-	*shared = *trimmed = false;
+	*shared = false;
 	if (fbno == NULLAGBLOCK) {
 		/* No shared blocks at all. */
 		return 0;
@@ -222,8 +221,6 @@ xfs_reflink_trim_around_shared(
 		 */
 		irec->br_blockcount = flen;
 		*shared = true;
-		if (flen != aglen)
-			*trimmed = true;
 		return 0;
 	} else {
 		/*
@@ -233,7 +230,6 @@ xfs_reflink_trim_around_shared(
 		 * start of the shared region.
 		 */
 		irec->br_blockcount = fbno - agbno;
-		*trimmed = true;
 		return 0;
 	}
 }
@@ -241,7 +237,7 @@ 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.  In this case *shared is set to true, else to false.
+ * 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
@@ -250,14 +246,14 @@ xfs_reflink_trim_around_shared(
 int
 xfs_reflink_reserve_cow(
 	struct xfs_inode	*ip,
-	struct xfs_bmbt_irec	*imap,
-	bool			*shared)
+	struct xfs_bmbt_irec	*imap)
 {
 	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
 	struct xfs_bmbt_irec	got;
 	int			error = 0;
-	bool			eof = false, trimmed;
+	bool			eof = false;
 	struct xfs_iext_cursor	icur;
+	bool			shared;
 
 	/*
 	 * Search the COW fork extent list first.  This serves two purposes:
@@ -273,18 +269,16 @@ xfs_reflink_reserve_cow(
 	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);
-
-		*shared = true;
 		return 0;
 	}
 
 	/* Trim the mapping to the nearest shared extent boundary. */
-	error = xfs_reflink_trim_around_shared(ip, imap, shared, &trimmed);
+	error = xfs_reflink_trim_around_shared(ip, imap, &shared);
 	if (error)
 		return error;
 
 	/* Not shared?  Just report the (potentially capped) extent. */
-	if (!*shared)
+	if (!shared)
 		return 0;
 
 	/*
@@ -368,7 +362,6 @@ xfs_find_trim_cow_extent(
 	xfs_filblks_t		count_fsb = imap->br_blockcount;
 	struct xfs_iext_cursor	icur;
 	struct xfs_bmbt_irec	got;
-	bool			trimmed;
 
 	*found = false;
 
@@ -376,9 +369,13 @@ xfs_find_trim_cow_extent(
 	 * If we don't find an overlapping extent, trim the range we need to
 	 * allocate to fit the hole we found.
 	 */
-	if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &got) ||
-	    got.br_startoff > offset_fsb)
-		return xfs_reflink_trim_around_shared(ip, imap, shared, &trimmed);
+	if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &got))
+		got.br_startoff = offset_fsb + count_fsb;
+	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);
+	}
 
 	*shared = true;
 	if (isnullstartblock(got.br_startblock)) {

fs/xfs/xfs_reflink.h

@@ -10,10 +10,10 @@ extern int xfs_reflink_find_shared(struct xfs_mount *mp, struct xfs_trans *tp,
 		xfs_agnumber_t agno, xfs_agblock_t agbno, xfs_extlen_t aglen,
 		xfs_agblock_t *fbno, xfs_extlen_t *flen, bool find_maximal);
 extern int xfs_reflink_trim_around_shared(struct xfs_inode *ip,
-		struct xfs_bmbt_irec *irec, bool *shared, bool *trimmed);
+		struct xfs_bmbt_irec *irec, bool *shared);
 
 extern int xfs_reflink_reserve_cow(struct xfs_inode *ip,
-		struct xfs_bmbt_irec *imap, bool *shared);
+		struct xfs_bmbt_irec *imap);
 extern int xfs_reflink_allocate_cow(struct xfs_inode *ip,
 		struct xfs_bmbt_irec *imap, bool *shared, uint *lockmode);
 extern int xfs_reflink_convert_cow(struct xfs_inode *ip, xfs_off_t offset,

fs/xfs/xfs_stats.c

@@ -29,30 +29,30 @@ int xfs_stats_format(struct xfsstats __percpu *stats, char *buf)
 		char	*desc;
 		int	endpoint;
 	} xstats[] = {
-		{ "extent_alloc",	XFSSTAT_END_EXTENT_ALLOC	},
-		{ "abt",		XFSSTAT_END_ALLOC_BTREE		},
-		{ "blk_map",		XFSSTAT_END_BLOCK_MAPPING	},
-		{ "bmbt",		XFSSTAT_END_BLOCK_MAP_BTREE	},
-		{ "dir",		XFSSTAT_END_DIRECTORY_OPS	},
-		{ "trans",		XFSSTAT_END_TRANSACTIONS	},
-		{ "ig",			XFSSTAT_END_INODE_OPS		},
-		{ "log",		XFSSTAT_END_LOG_OPS		},
-		{ "push_ail",		XFSSTAT_END_TAIL_PUSHING	},
-		{ "xstrat",		XFSSTAT_END_WRITE_CONVERT	},
-		{ "rw",			XFSSTAT_END_READ_WRITE_OPS	},
-		{ "attr",		XFSSTAT_END_ATTRIBUTE_OPS	},
-		{ "icluster",		XFSSTAT_END_INODE_CLUSTER	},
-		{ "vnodes",		XFSSTAT_END_VNODE_OPS		},
-		{ "buf",		XFSSTAT_END_BUF			},
-		{ "abtb2",		XFSSTAT_END_ABTB_V2		},
-		{ "abtc2",		XFSSTAT_END_ABTC_V2		},
-		{ "bmbt2",		XFSSTAT_END_BMBT_V2		},
-		{ "ibt2",		XFSSTAT_END_IBT_V2		},
-		{ "fibt2",		XFSSTAT_END_FIBT_V2		},
-		{ "rmapbt",		XFSSTAT_END_RMAP_V2		},
-		{ "refcntbt",		XFSSTAT_END_REFCOUNT		},
+		{ "extent_alloc",	xfsstats_offset(xs_abt_lookup)	},
+		{ "abt",		xfsstats_offset(xs_blk_mapr)	},
+		{ "blk_map",		xfsstats_offset(xs_bmbt_lookup)	},
+		{ "bmbt",		xfsstats_offset(xs_dir_lookup)	},
+		{ "dir",		xfsstats_offset(xs_trans_sync)	},
+		{ "trans",		xfsstats_offset(xs_ig_attempts)	},
+		{ "ig",			xfsstats_offset(xs_log_writes)	},
+		{ "log",		xfsstats_offset(xs_try_logspace)},
+		{ "push_ail",		xfsstats_offset(xs_xstrat_quick)},
+		{ "xstrat",		xfsstats_offset(xs_write_calls)	},
+		{ "rw",			xfsstats_offset(xs_attr_get)	},
+		{ "attr",		xfsstats_offset(xs_iflush_count)},
+		{ "icluster",		xfsstats_offset(vn_active)	},
+		{ "vnodes",		xfsstats_offset(xb_get)		},
+		{ "buf",		xfsstats_offset(xs_abtb_2)	},
+		{ "abtb2",		xfsstats_offset(xs_abtc_2)	},
+		{ "abtc2",		xfsstats_offset(xs_bmbt_2)	},
+		{ "bmbt2",		xfsstats_offset(xs_ibt_2)	},
+		{ "ibt2",		xfsstats_offset(xs_fibt_2)	},
+		{ "fibt2",		xfsstats_offset(xs_rmap_2)	},
+		{ "rmapbt",		xfsstats_offset(xs_refcbt_2)	},
+		{ "refcntbt",		xfsstats_offset(xs_qm_dqreclaims)},
 		/* we print both series of quota information together */
-		{ "qm",			XFSSTAT_END_QM			},
+		{ "qm",			xfsstats_offset(xs_xstrat_bytes)},
 	};
 
 	/* Loop over all stats groups */
@@ -104,6 +104,10 @@ void xfs_stats_clearall(struct xfsstats __percpu *stats)
 #ifdef CONFIG_PROC_FS
 /* legacy quota interfaces */
 #ifdef CONFIG_XFS_QUOTA
+
+#define XFSSTAT_START_XQMSTAT xfsstats_offset(xs_qm_dqreclaims)
+#define XFSSTAT_END_XQMSTAT xfsstats_offset(xs_qm_dquot)
+
 static int xqm_proc_show(struct seq_file *m, void *v)
 {
 	/* maximum; incore; ratio free to inuse; freelist */
@@ -119,7 +123,7 @@ static int xqmstat_proc_show(struct seq_file *m, void *v)
 	int j;
 
 	seq_printf(m, "qm");
-	for (j = XFSSTAT_END_IBT_V2; j < XFSSTAT_END_XQMSTAT; j++)
+	for (j = XFSSTAT_START_XQMSTAT; j < XFSSTAT_END_XQMSTAT; j++)
 		seq_printf(m, " %u", counter_val(xfsstats.xs_stats, j));
 	seq_putc(m, '\n');
 	return 0;

fs/xfs/xfs_stats.h

@@ -41,17 +41,14 @@ enum {
  * XFS global statistics
  */
 struct __xfsstats {
-# define XFSSTAT_END_EXTENT_ALLOC	4
 	uint32_t		xs_allocx;
 	uint32_t		xs_allocb;
 	uint32_t		xs_freex;
 	uint32_t		xs_freeb;
-# define XFSSTAT_END_ALLOC_BTREE	(XFSSTAT_END_EXTENT_ALLOC+4)
 	uint32_t		xs_abt_lookup;
 	uint32_t		xs_abt_compare;
 	uint32_t		xs_abt_insrec;
 	uint32_t		xs_abt_delrec;
-# define XFSSTAT_END_BLOCK_MAPPING	(XFSSTAT_END_ALLOC_BTREE+7)
 	uint32_t		xs_blk_mapr;
 	uint32_t		xs_blk_mapw;
 	uint32_t		xs_blk_unmap;
@@ -59,21 +56,17 @@ struct __xfsstats {
 	uint32_t		xs_del_exlist;
 	uint32_t		xs_look_exlist;
 	uint32_t		xs_cmp_exlist;
-# define XFSSTAT_END_BLOCK_MAP_BTREE	(XFSSTAT_END_BLOCK_MAPPING+4)
 	uint32_t		xs_bmbt_lookup;
 	uint32_t		xs_bmbt_compare;
 	uint32_t		xs_bmbt_insrec;
 	uint32_t		xs_bmbt_delrec;
-# define XFSSTAT_END_DIRECTORY_OPS	(XFSSTAT_END_BLOCK_MAP_BTREE+4)
 	uint32_t		xs_dir_lookup;
 	uint32_t		xs_dir_create;
 	uint32_t		xs_dir_remove;
 	uint32_t		xs_dir_getdents;
-# define XFSSTAT_END_TRANSACTIONS	(XFSSTAT_END_DIRECTORY_OPS+3)
 	uint32_t		xs_trans_sync;
 	uint32_t		xs_trans_async;
 	uint32_t		xs_trans_empty;
-# define XFSSTAT_END_INODE_OPS		(XFSSTAT_END_TRANSACTIONS+7)
 	uint32_t		xs_ig_attempts;
 	uint32_t		xs_ig_found;
 	uint32_t		xs_ig_frecycle;
@@ -81,13 +74,11 @@ struct __xfsstats {
 	uint32_t		xs_ig_dup;
 	uint32_t		xs_ig_reclaims;
 	uint32_t		xs_ig_attrchg;
-# define XFSSTAT_END_LOG_OPS		(XFSSTAT_END_INODE_OPS+5)
 	uint32_t		xs_log_writes;
 	uint32_t		xs_log_blocks;
 	uint32_t		xs_log_noiclogs;
 	uint32_t		xs_log_force;
 	uint32_t		xs_log_force_sleep;
-# define XFSSTAT_END_TAIL_PUSHING	(XFSSTAT_END_LOG_OPS+10)
 	uint32_t		xs_try_logspace;
 	uint32_t		xs_sleep_logspace;
 	uint32_t		xs_push_ail;
@@ -98,22 +89,17 @@ struct __xfsstats {
 	uint32_t		xs_push_ail_flushing;
 	uint32_t		xs_push_ail_restarts;
 	uint32_t		xs_push_ail_flush;
-# define XFSSTAT_END_WRITE_CONVERT	(XFSSTAT_END_TAIL_PUSHING+2)
 	uint32_t		xs_xstrat_quick;
 	uint32_t		xs_xstrat_split;
-# define XFSSTAT_END_READ_WRITE_OPS	(XFSSTAT_END_WRITE_CONVERT+2)
 	uint32_t		xs_write_calls;
 	uint32_t		xs_read_calls;
-# define XFSSTAT_END_ATTRIBUTE_OPS	(XFSSTAT_END_READ_WRITE_OPS+4)
 	uint32_t		xs_attr_get;
 	uint32_t		xs_attr_set;
 	uint32_t		xs_attr_remove;
 	uint32_t		xs_attr_list;
-# define XFSSTAT_END_INODE_CLUSTER	(XFSSTAT_END_ATTRIBUTE_OPS+3)
 	uint32_t		xs_iflush_count;
 	uint32_t		xs_icluster_flushcnt;
 	uint32_t		xs_icluster_flushinode;
-# define XFSSTAT_END_VNODE_OPS		(XFSSTAT_END_INODE_CLUSTER+8)
 	uint32_t		vn_active;	/* # vnodes not on free lists */
 	uint32_t		vn_alloc;	/* # times vn_alloc called */
 	uint32_t		vn_get;		/* # times vn_get called */
@@ -122,7 +108,6 @@ struct __xfsstats {
 	uint32_t		vn_reclaim;	/* # times vn_reclaim called */
 	uint32_t		vn_remove;	/* # times vn_remove called */
 	uint32_t		vn_free;	/* # times vn_free called */
-#define XFSSTAT_END_BUF			(XFSSTAT_END_VNODE_OPS+9)
 	uint32_t		xb_get;
 	uint32_t		xb_create;
 	uint32_t		xb_get_locked;
@@ -133,28 +118,19 @@ struct __xfsstats {
 	uint32_t		xb_page_found;
 	uint32_t		xb_get_read;
 /* Version 2 btree counters */
-#define XFSSTAT_END_ABTB_V2		(XFSSTAT_END_BUF + __XBTS_MAX)
 	uint32_t		xs_abtb_2[__XBTS_MAX];
-#define XFSSTAT_END_ABTC_V2		(XFSSTAT_END_ABTB_V2 + __XBTS_MAX)
 	uint32_t		xs_abtc_2[__XBTS_MAX];
-#define XFSSTAT_END_BMBT_V2		(XFSSTAT_END_ABTC_V2 + __XBTS_MAX)
 	uint32_t		xs_bmbt_2[__XBTS_MAX];
-#define XFSSTAT_END_IBT_V2		(XFSSTAT_END_BMBT_V2 + __XBTS_MAX)
 	uint32_t		xs_ibt_2[__XBTS_MAX];
-#define XFSSTAT_END_FIBT_V2		(XFSSTAT_END_IBT_V2 + __XBTS_MAX)
 	uint32_t		xs_fibt_2[__XBTS_MAX];
-#define XFSSTAT_END_RMAP_V2		(XFSSTAT_END_FIBT_V2 + __XBTS_MAX)
 	uint32_t		xs_rmap_2[__XBTS_MAX];
-#define XFSSTAT_END_REFCOUNT		(XFSSTAT_END_RMAP_V2 + __XBTS_MAX)
 	uint32_t		xs_refcbt_2[__XBTS_MAX];
-#define XFSSTAT_END_XQMSTAT		(XFSSTAT_END_REFCOUNT + 6)
 	uint32_t		xs_qm_dqreclaims;
 	uint32_t		xs_qm_dqreclaim_misses;
 	uint32_t		xs_qm_dquot_dups;
 	uint32_t		xs_qm_dqcachemisses;
 	uint32_t		xs_qm_dqcachehits;
 	uint32_t		xs_qm_dqwants;
-#define XFSSTAT_END_QM			(XFSSTAT_END_XQMSTAT+2)
 	uint32_t		xs_qm_dquot;
 	uint32_t		xs_qm_dquot_unused;
 /* Extra precision counters */
@@ -163,10 +139,12 @@ struct __xfsstats {
 	uint64_t		xs_read_bytes;
 };
 
+#define	xfsstats_offset(f)	(offsetof(struct __xfsstats, f)/sizeof(uint32_t))
+
 struct xfsstats {
 	union {
 		struct __xfsstats	s;
-		uint32_t		a[XFSSTAT_END_XQMSTAT];
+		uint32_t		a[xfsstats_offset(xs_qm_dquot)];
 	};
 };
 

fs/xfs/xfs_super.c

@@ -43,6 +43,7 @@
 #include <linux/dax.h>
 #include <linux/init.h>
 #include <linux/slab.h>
+#include <linux/magic.h>
 #include <linux/mount.h>
 #include <linux/mempool.h>
 #include <linux/writeback.h>
@@ -933,6 +934,32 @@ xfs_fs_alloc_inode(
 	return NULL;
 }
 
+#ifdef DEBUG
+static void
+xfs_check_delalloc(
+	struct xfs_inode	*ip,
+	int			whichfork)
+{
+	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, whichfork);
+	struct xfs_bmbt_irec	got;
+	struct xfs_iext_cursor	icur;
+
+	if (!ifp || !xfs_iext_lookup_extent(ip, ifp, 0, &icur, &got))
+		return;
+	do {
+		if (isnullstartblock(got.br_startblock)) {
+			xfs_warn(ip->i_mount,
+	"ino %llx %s fork has delalloc extent at [0x%llx:0x%llx]",
+				ip->i_ino,
+				whichfork == XFS_DATA_FORK ? "data" : "cow",
+				got.br_startoff, got.br_blockcount);
+		}
+	} while (xfs_iext_next_extent(ifp, &icur, &got));
+}
+#else
+#define xfs_check_delalloc(ip, whichfork)	do { } while (0)
+#endif
+
 /*
  * Now that the generic code is guaranteed not to be accessing
  * the linux inode, we can inactivate and reclaim the inode.
@@ -951,7 +978,12 @@ xfs_fs_destroy_inode(
 
 	xfs_inactive(ip);
 
-	ASSERT(XFS_FORCED_SHUTDOWN(ip->i_mount) || ip->i_delayed_blks == 0);
+	if (!XFS_FORCED_SHUTDOWN(ip->i_mount) && ip->i_delayed_blks) {
+		xfs_check_delalloc(ip, XFS_DATA_FORK);
+		xfs_check_delalloc(ip, XFS_COW_FORK);
+		ASSERT(0);
+	}
+
 	XFS_STATS_INC(ip->i_mount, vn_reclaim);
 
 	/*
@@ -1097,7 +1129,7 @@ xfs_fs_statfs(
 	xfs_extlen_t		lsize;
 	int64_t			ffree;
 
-	statp->f_type = XFS_SB_MAGIC;
+	statp->f_type = XFS_SUPER_MAGIC;
 	statp->f_namelen = MAXNAMELEN - 1;
 
 	id = huge_encode_dev(mp->m_ddev_targp->bt_dev);
@@ -1650,7 +1682,7 @@ xfs_fs_fill_super(
 	 * we must configure the block size in the superblock before we run the
 	 * full mount process as the mount process can lookup and cache inodes.
 	 */
-	sb->s_magic = XFS_SB_MAGIC;
+	sb->s_magic = XFS_SUPER_MAGIC;
 	sb->s_blocksize = mp->m_sb.sb_blocksize;
 	sb->s_blocksize_bits = ffs(sb->s_blocksize) - 1;
 	sb->s_maxbytes = xfs_max_file_offset(sb->s_blocksize_bits);

fs/xfs/xfs_trans.h

@@ -220,6 +220,7 @@ void		xfs_trans_ijoin(struct xfs_trans *, struct xfs_inode *, uint);
 void		xfs_trans_log_buf(struct xfs_trans *, struct xfs_buf *, uint,
 				  uint);
 void		xfs_trans_dirty_buf(struct xfs_trans *, struct xfs_buf *);
+bool		xfs_trans_buf_is_dirty(struct xfs_buf *bp);
 void		xfs_trans_log_inode(xfs_trans_t *, struct xfs_inode *, uint);
 
 void		xfs_extent_free_init_defer_op(void);

fs/xfs/xfs_trans_ail.c

@@ -531,17 +531,33 @@ xfsaild(
 			set_current_state(TASK_INTERRUPTIBLE);
 
 		/*
-		 * Check kthread_should_stop() after we set the task state
-		 * to guarantee that we either see the stop bit and exit or
-		 * the task state is reset to runnable such that it's not
-		 * scheduled out indefinitely and detects the stop bit at
-		 * next iteration.
-		 *
+		 * Check kthread_should_stop() after we set the task state to
+		 * guarantee that we either see the stop bit and exit or the
+		 * task state is reset to runnable such that it's not scheduled
+		 * out indefinitely and detects the stop bit at next iteration.
 		 * A memory barrier is included in above task state set to
 		 * serialize again kthread_stop().
 		 */
 		if (kthread_should_stop()) {
 			__set_current_state(TASK_RUNNING);
+
+			/*
+			 * The caller forces out the AIL before stopping the
+			 * thread in the common case, which means the delwri
+			 * queue is drained. In the shutdown case, the queue may
+			 * still hold relogged buffers that haven't been
+			 * submitted because they were pinned since added to the
+			 * queue.
+			 *
+			 * Log I/O error processing stales the underlying buffer
+			 * and clears the delwri state, expecting the buf to be
+			 * removed on the next submission attempt. That won't
+			 * happen if we're shutting down, so this is the last
+			 * opportunity to release such buffers from the queue.
+			 */
+			ASSERT(list_empty(&ailp->ail_buf_list) ||
+			       XFS_FORCED_SHUTDOWN(ailp->ail_mount));
+			xfs_buf_delwri_cancel(&ailp->ail_buf_list);
 			break;
 		}
 

fs/xfs/xfs_trans_buf.c

@@ -264,11 +264,39 @@ xfs_trans_read_buf_map(
 			return -EIO;
 		}
 
+		/*
+		 * Check if the caller is trying to read a buffer that is
+		 * already attached to the transaction yet has no buffer ops
+		 * assigned.  Ops are usually attached when the buffer is
+		 * attached to the transaction, or by the read caller if
+		 * special circumstances.  That didn't happen, which is not
+		 * how this is supposed to go.
+		 *
+		 * If the buffer passes verification we'll let this go, but if
+		 * not we have to shut down.  Let the transaction cleanup code
+		 * release this buffer when it kills the tranaction.
+		 */
+		ASSERT(bp->b_ops != NULL);
+		error = xfs_buf_ensure_ops(bp, ops);
+		if (error) {
+			xfs_buf_ioerror_alert(bp, __func__);
+
+			if (tp->t_flags & XFS_TRANS_DIRTY)
+				xfs_force_shutdown(tp->t_mountp,
+						SHUTDOWN_META_IO_ERROR);
+
+			/* bad CRC means corrupted metadata */
+			if (error == -EFSBADCRC)
+				error = -EFSCORRUPTED;
+			return error;
+		}
+
 		bip = bp->b_log_item;
 		bip->bli_recur++;
 
 		ASSERT(atomic_read(&bip->bli_refcount) > 0);
 		trace_xfs_trans_read_buf_recur(bip);
+		ASSERT(bp->b_ops != NULL || ops == NULL);
 		*bpp = bp;
 		return 0;
 	}
@@ -316,11 +344,25 @@ xfs_trans_read_buf_map(
 		_xfs_trans_bjoin(tp, bp, 1);
 		trace_xfs_trans_read_buf(bp->b_log_item);
 	}
+	ASSERT(bp->b_ops != NULL || ops == NULL);
 	*bpp = bp;
 	return 0;
 
 }
 
+/* Has this buffer been dirtied by anyone? */
+bool
+xfs_trans_buf_is_dirty(
+	struct xfs_buf		*bp)
+{
+	struct xfs_buf_log_item	*bip = bp->b_log_item;
+
+	if (!bip)
+		return false;
+	ASSERT(bip->bli_item.li_type == XFS_LI_BUF);
+	return test_bit(XFS_LI_DIRTY, &bip->bli_item.li_flags);
+}
+
 /*
  * Release a buffer previously joined to the transaction. If the buffer is
  * modified within this transaction, decrement the recursion count but do not

include/uapi/linux/magic.h

@@ -29,6 +29,7 @@
 #define HPFS_SUPER_MAGIC	0xf995e849
 #define ISOFS_SUPER_MAGIC	0x9660
 #define JFFS2_SUPER_MAGIC	0x72b6
+#define XFS_SUPER_MAGIC		0x58465342	/* "XFSB" */
 #define PSTOREFS_MAGIC		0x6165676C
 #define EFIVARFS_MAGIC		0xde5e81e4
 #define HOSTFS_SUPER_MAGIC	0x00c0ffee