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
  ...

24 files changed, 607 insertions, 383 deletions

diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index c6299f82a6e4..844ed87b1900 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/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);
 
@@ -255,93 +377,17 @@ 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;
-	}
+	if (error)
+		goto out_trans_cancel;
 
 	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;
-
-		/*
-		 * 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);
-		if (error)
-			goto out;
-		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);
+	error = xfs_attr_set_args(&args, &leaf_bp);
 	if (error)
-		goto out;
+		goto out_release_leaf;
+	if (!args.trans) {
+		/* shortform attribute has already been committed */
+		goto out_unlock;
+	}
 
 	/*
 	 * If this is a synchronous mount, make sure that the
@@ -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;
 
diff --git a/fs/xfs/xfs_attr.h b/fs/xfs/libxfs/xfs_attr.h
index 033ff8c478e2..bdf52a333f3f 100644
--- a/fs/xfs/xfs_attr.h
+++ b/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);
 
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index a47670332326..74d7228e755b 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/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 &&
-				    (del.br_state == XFS_EXT_UNWRITTEN ||
-				     tp->t_blk_res == 0)) ||
-				   !xfs_sb_version_hasextflgbit(&mp->m_sb)) {
+			} else if (del.br_startoff == start &&
+				   (del.br_state == XFS_EXT_UNWRITTEN ||
+				    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)
-			return __this_address;
-		if (!xfs_sb_version_hasextflgbit(&mp->m_sb))
-			return __this_address;
-	}
+	if (irec->br_state != XFS_EXT_NORM && whichfork != XFS_DATA_FORK)
+		return __this_address;
 	return NULL;
 }
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index b6e9b639e731..488dc8860fd7 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/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,
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index afbe336600e1..9995d5ae380b 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/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);
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 081f46e30556..b5a82acd7dfe 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/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))
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 9f08dd9bf1d5..4fc0a5ea7673 100644
--- a/fs/xfs/scrub/repair.c
+++ b/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))
-		goto out;
-	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;
+	/*
+	 * 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;
+		}
 
-	/* Make sure we pass the verifiers. */
-	bp->b_ops->verify_read(bp);
-	if (bp->b_error)
+		/*
+		 * 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;
+	}
+
+	/*
+	 * 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;
+
+	/*
+	 * 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;
-	fab->root = agbno;
-	fab->height = xfs_btree_get_level(btblock) + 1;
-	*found_it = true;
+	} 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;
+	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;
 		}
 	}
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 4bfae1e61d30..1b2344d00525 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/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
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 49f5f5896a43..338b9d9984e0 100644
--- a/fs/xfs/xfs_aops.c
+++ b/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;
 
diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h
index 9af867951a10..494b4338446e 100644
--- a/fs/xfs/xfs_aops.h
+++ b/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_DELALLOC,		"delalloc" }, \
-	{ XFS_IO_UNWRITTEN,		"unwritten" }, \
-	{ XFS_IO_OVERWRITE,		"overwrite" }, \
-	{ XFS_IO_COW,			"CoW" }, \
-	{ XFS_IO_HOLE,			"hole" }
+	{ XFS_IO_HOLE,			"hole" },	\
+	{ XFS_IO_DELALLOC,		"delalloc" },	\
+	{ XFS_IO_UNWRITTEN,		"unwritten" },	\
+	{ XFS_IO_OVERWRITE,		"overwrite" },	\
+	{ XFS_IO_COW,			"CoW" }
 
 /*
  * Structure for buffered I/O completions.
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 6de8d90041ff..5d263dfdb3bc 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/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;
 
@@ -1043,44 +1043,6 @@ out_trans_cancel:
 }
 
 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,
 	xfs_off_t		offset,
@@ -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.
+	 * Need to zero the stuff we're not freeing, on disk.
 	 */
-	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;
-	}
-
 	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
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index e839907e8492..b21ea2ba768d 100644
--- a/fs/xfs/xfs_buf.c
+++ b/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