Merge tag 'xfs-5.13-merge-3' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull xfs updates from Darrick Wong:
 "The notable user-visible addition this cycle is ability to remove
  space from the last AG in a filesystem. This is the first of many
  changes needed for full-fledged support for shrinking a filesystem.
  Still needed are (a) the ability to reorganize files and metadata away
  from the end of the fs; (b) the ability to remove entire allocation
  groups; (c) shrink support for realtime volumes; and (d) thorough
  testing of (a-c).

  There are a number of performance improvements in this code drop: Dave
  streamlined various parts of the buffer logging code and reduced the
  cost of various debugging checks, and added the ability to pre-create
  the xattr structures while creating files. Brian eliminated
  transaction reservations that were being held across writeback (thus
  reducing livelock potential.

  Other random pieces: Pavel fixed the repetitve warnings about
  deprecated mount options, I fixed online fsck to behave itself when a
  readonly remount comes in during scrub, and refactored various other
  parts of that code, Christoph contributed a lot of refactoring this
  cycle. The xfs_icdinode structure has been absorbed into the (incore)
  xfs_inode structure, and the format and flags handling around
  xfs_inode_fork structures has been simplified. Chandan provided a
  number of fixes for extent count overflow related problems that have
  been shaken out by debugging knobs added during 5.12.

  Summary:

   - Various minor fixes in online scrub.

   - Prevent metadata files from being automatically inactivated.

   - Validate btree heights by the computed per-btree limits.

   - Don't warn about remounting with deprecated mount options.

   - Initialize attr forks at create time if we suspect we're going to
     need to store them.

   - Reduce memory reallocation workouts in the logging code.

   - Fix some theoretical math calculation errors in logged buffers that
     span multiple discontig memory ranges but contiguous ondisk
     regions.

   - Speedups in dirty buffer bitmap handling.

   - Make type verifier functions more inline-happy to reduce overhead.

   - Reduce debug overhead in directory checking code.

   - Many many typo fixes.

   - Begin to handle the permanent loss of the very end of a filesystem.

   - Fold struct xfs_icdinode into xfs_inode.

   - Deprecate the long defunct BMV_IF_NO_DMAPI_READ from the bmapx
     ioctl.

   - Remove a broken directory block format check from online scrub.

   - Fix a bug where we could produce an unnecessarily tall data fork
     btree when creating an attr fork.

   - Fix scrub and readonly remounts racing.

   - Fix a writeback ioend log deadlock problem by dropping the behavior
     where we could preallocate a setfilesize transaction.

   - Fix some bugs in the new extent count checking code.

   - Fix some bugs in the attr fork preallocation code.

   - Refactor if_flags out of the incore inode fork data structure"

* tag 'xfs-5.13-merge-3' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (77 commits)
  xfs: remove xfs_quiesce_attr declaration
  xfs: remove XFS_IFEXTENTS
  xfs: remove XFS_IFINLINE
  xfs: remove XFS_IFBROOT
  xfs: only look at the fork format in xfs_idestroy_fork
  xfs: simplify xfs_attr_remove_args
  xfs: rename and simplify xfs_bmap_one_block
  xfs: move the XFS_IFEXTENTS check into xfs_iread_extents
  xfs: drop unnecessary setfilesize helper
  xfs: drop unused ioend private merge and setfilesize code
  xfs: open code ioend needs workqueue helper
  xfs: drop submit side trans alloc for append ioends
  xfs: fix return of uninitialized value in variable error
  xfs: get rid of the ip parameter to xchk_setup_*
  xfs: fix scrub and remount-ro protection when running scrub
  xfs: move the check for post-EOF mappings into xfs_can_free_eofblocks
  xfs: move the xfs_can_free_eofblocks call under the IOLOCK
  xfs: precalculate default inode attribute offset
  xfs: default attr fork size does not handle device inodes
  xfs: inode fork allocation depends on XFS_IFEXTENT flag
  ...

92 files changed, 1459 insertions, 1303 deletions

diff --git a/Documentation/admin-guide/xfs.rst b/Documentation/admin-guide/xfs.rst
index 5422407a96d7..8de008c0c5ad 100644
--- a/Documentation/admin-guide/xfs.rst
+++ b/Documentation/admin-guide/xfs.rst
@@ -522,7 +522,7 @@ and the short name of the data device.  They all can be found in:
 ================  ===========
   xfs_iwalk-$pid  Inode scans of the entire filesystem. Currently limited to
                   mount time quotacheck.
-  xfs-blockgc     Background garbage collection of disk space that have been
+  xfs-gc          Background garbage collection of disk space that have been
                   speculatively allocated beyond EOF or for staging copy on
                   write operations.
 ================  ===========
diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index 9331f3516afa..c68a36688474 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -22,6 +22,11 @@
 #include "xfs_ag.h"
 #include "xfs_ag_resv.h"
 #include "xfs_health.h"
+#include "xfs_error.h"
+#include "xfs_bmap.h"
+#include "xfs_defer.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
 
 static int
 xfs_get_aghdr_buf(
@@ -485,6 +490,116 @@ xfs_ag_init_headers(
 	return error;
 }
 
+int
+xfs_ag_shrink_space(
+	struct xfs_mount	*mp,
+	struct xfs_trans	**tpp,
+	xfs_agnumber_t		agno,
+	xfs_extlen_t		delta)
+{
+	struct xfs_alloc_arg	args = {
+		.tp	= *tpp,
+		.mp	= mp,
+		.type	= XFS_ALLOCTYPE_THIS_BNO,
+		.minlen = delta,
+		.maxlen = delta,
+		.oinfo	= XFS_RMAP_OINFO_SKIP_UPDATE,
+		.resv	= XFS_AG_RESV_NONE,
+		.prod	= 1
+	};
+	struct xfs_buf		*agibp, *agfbp;
+	struct xfs_agi		*agi;
+	struct xfs_agf		*agf;
+	int			error, err2;
+
+	ASSERT(agno == mp->m_sb.sb_agcount - 1);
+	error = xfs_ialloc_read_agi(mp, *tpp, agno, &agibp);
+	if (error)
+		return error;
+
+	agi = agibp->b_addr;
+
+	error = xfs_alloc_read_agf(mp, *tpp, agno, 0, &agfbp);
+	if (error)
+		return error;
+
+	agf = agfbp->b_addr;
+	/* some extra paranoid checks before we shrink the ag */
+	if (XFS_IS_CORRUPT(mp, agf->agf_length != agi->agi_length))
+		return -EFSCORRUPTED;
+	if (delta >= agi->agi_length)
+		return -EINVAL;
+
+	args.fsbno = XFS_AGB_TO_FSB(mp, agno,
+				    be32_to_cpu(agi->agi_length) - delta);
+
+	/*
+	 * Disable perag reservations so it doesn't cause the allocation request
+	 * to fail. We'll reestablish reservation before we return.
+	 */
+	error = xfs_ag_resv_free(agibp->b_pag);
+	if (error)
+		return error;
+
+	/* internal log shouldn't also show up in the free space btrees */
+	error = xfs_alloc_vextent(&args);
+	if (!error && args.agbno == NULLAGBLOCK)
+		error = -ENOSPC;
+
+	if (error) {
+		/*
+		 * if extent allocation fails, need to roll the transaction to
+		 * ensure that the AGFL fixup has been committed anyway.
+		 */
+		xfs_trans_bhold(*tpp, agfbp);
+		err2 = xfs_trans_roll(tpp);
+		if (err2)
+			return err2;
+		xfs_trans_bjoin(*tpp, agfbp);
+		goto resv_init_out;
+	}
+
+	/*
+	 * if successfully deleted from freespace btrees, need to confirm
+	 * per-AG reservation works as expected.
+	 */
+	be32_add_cpu(&agi->agi_length, -delta);
+	be32_add_cpu(&agf->agf_length, -delta);
+
+	err2 = xfs_ag_resv_init(agibp->b_pag, *tpp);
+	if (err2) {
+		be32_add_cpu(&agi->agi_length, delta);
+		be32_add_cpu(&agf->agf_length, delta);
+		if (err2 != -ENOSPC)
+			goto resv_err;
+
+		__xfs_bmap_add_free(*tpp, args.fsbno, delta, NULL, true);
+
+		/*
+		 * Roll the transaction before trying to re-init the per-ag
+		 * reservation. The new transaction is clean so it will cancel
+		 * without any side effects.
+		 */
+		error = xfs_defer_finish(tpp);
+		if (error)
+			return error;
+
+		error = -ENOSPC;
+		goto resv_init_out;
+	}
+	xfs_ialloc_log_agi(*tpp, agibp, XFS_AGI_LENGTH);
+	xfs_alloc_log_agf(*tpp, agfbp, XFS_AGF_LENGTH);
+	return 0;
+resv_init_out:
+	err2 = xfs_ag_resv_init(agibp->b_pag, *tpp);
+	if (!err2)
+		return error;
+resv_err:
+	xfs_warn(mp, "Error %d reserving per-AG metadata reserve pool.", err2);
+	xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
+	return err2;
+}
+
 /*
  * Extent the AG indicated by the @id by the length passed in
  */
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index 5166322807e7..4535de1d88ea 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -24,6 +24,8 @@ struct aghdr_init_data {
 };
 
 int xfs_ag_init_headers(struct xfs_mount *mp, struct aghdr_init_data *id);
+int xfs_ag_shrink_space(struct xfs_mount *mp, struct xfs_trans **tpp,
+			xfs_agnumber_t agno, xfs_extlen_t delta);
 int xfs_ag_extend_space(struct xfs_mount *mp, struct xfs_trans *tp,
 			struct aghdr_init_data *id, xfs_extlen_t len);
 int xfs_ag_get_geometry(struct xfs_mount *mp, xfs_agnumber_t agno,
diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c
index fdfe6dc0d307..6c5f8d10589c 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.c
+++ b/fs/xfs/libxfs/xfs_ag_resv.c
@@ -211,7 +211,11 @@ __xfs_ag_resv_init(
 		ASSERT(0);
 		return -EINVAL;
 	}
-	error = xfs_mod_fdblocks(mp, -(int64_t)hidden_space, true);
+
+	if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_AG_RESV_FAIL))
+		error = -ENOSPC;
+	else
+		error = xfs_mod_fdblocks(mp, -(int64_t)hidden_space, true);
 	if (error) {
 		trace_xfs_ag_resv_init_error(pag->pag_mount, pag->pag_agno,
 				error, _RET_IP_);
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 0c623d3c1036..aaa19101bb2a 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -2906,13 +2906,13 @@ xfs_agf_verify(
 
 	if (be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]) < 1 ||
 	    be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]) < 1 ||
-	    be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]) > XFS_BTREE_MAXLEVELS ||
-	    be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]) > XFS_BTREE_MAXLEVELS)
+	    be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]) > mp->m_ag_maxlevels ||
+	    be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]) > mp->m_ag_maxlevels)
 		return __this_address;
 
 	if (xfs_sb_version_hasrmapbt(&mp->m_sb) &&
 	    (be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) < 1 ||
-	     be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) > XFS_BTREE_MAXLEVELS))
+	     be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) > mp->m_rmap_maxlevels))
 		return __this_address;
 
 	if (xfs_sb_version_hasrmapbt(&mp->m_sb) &&
@@ -2939,7 +2939,7 @@ xfs_agf_verify(
 
 	if (xfs_sb_version_hasreflink(&mp->m_sb) &&
 	    (be32_to_cpu(agf->agf_refcount_level) < 1 ||
-	     be32_to_cpu(agf->agf_refcount_level) > XFS_BTREE_MAXLEVELS))
+	     be32_to_cpu(agf->agf_refcount_level) > mp->m_refc_maxlevels))
 		return __this_address;
 
 	return NULL;
diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index 472b3039eabb..96146f425e50 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -70,6 +70,26 @@ xfs_inode_hasattr(
 	return 1;
 }
 
+/*
+ * Returns true if the there is exactly only block in the attr fork, in which
+ * case the attribute fork consists of a single leaf block entry.
+ */
+bool
+xfs_attr_is_leaf(
+	struct xfs_inode	*ip)
+{
+	struct xfs_ifork	*ifp = ip->i_afp;
+	struct xfs_iext_cursor	icur;
+	struct xfs_bmbt_irec	imap;
+
+	if (ifp->if_nextents != 1 || ifp->if_format != XFS_DINODE_FMT_EXTENTS)
+		return false;
+
+	xfs_iext_first(ifp, &icur);
+	xfs_iext_get_extent(ifp, &icur, &imap);
+	return imap.br_startoff == 0 && imap.br_blockcount == 1;
+}
+
 /*========================================================================
  * Overall external interface routines.
  *========================================================================*/
@@ -89,7 +109,7 @@ xfs_attr_get_ilocked(
 
 	if (args->dp->i_afp->if_format == XFS_DINODE_FMT_LOCAL)
 		return xfs_attr_shortform_getvalue(args);
-	if (xfs_bmap_one_block(args->dp, XFS_ATTR_FORK))
+	if (xfs_attr_is_leaf(args->dp))
 		return xfs_attr_leaf_get(args);
 	return xfs_attr_node_get(args);
 }
@@ -293,7 +313,7 @@ xfs_attr_set_args(
 			return error;
 	}
 
-	if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) {
+	if (xfs_attr_is_leaf(dp)) {
 		error = xfs_attr_leaf_addname(args);
 		if (error != -ENOSPC)
 			return error;
@@ -342,12 +362,10 @@ xfs_has_attr(
 	if (!xfs_inode_hasattr(dp))
 		return -ENOATTR;
 
-	if (dp->i_afp->if_format == XFS_DINODE_FMT_LOCAL) {
-		ASSERT(dp->i_afp->if_flags & XFS_IFINLINE);
+	if (dp->i_afp->if_format == XFS_DINODE_FMT_LOCAL)
 		return xfs_attr_sf_findname(args, NULL, NULL);
-	}
 
-	if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) {
+	if (xfs_attr_is_leaf(dp)) {
 		error = xfs_attr_leaf_hasname(args, &bp);
 
 		if (bp)
@@ -366,21 +384,14 @@ 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_afp->if_format == 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);
-	}
+	if (!xfs_inode_hasattr(args->dp))
+		return -ENOATTR;
 
-	return error;
+	if (args->dp->i_afp->if_format == XFS_DINODE_FMT_LOCAL)
+		return xfs_attr_shortform_remove(args);
+	if (xfs_attr_is_leaf(args->dp))
+		return xfs_attr_leaf_removename(args);
+	return xfs_attr_node_removename(args);
 }
 
 /*
@@ -928,6 +939,7 @@ restart:
 	 * Search to see if name already exists, and get back a pointer
 	 * to where it should go.
 	 */
+	error = 0;
 	retval = xfs_attr_node_hasname(args, &state);
 	if (retval != -ENOATTR && retval != -EEXIST)
 		goto out;
@@ -1282,7 +1294,7 @@ xfs_attr_node_removename(
 	/*
 	 * If the result is small enough, push it all into the inode.
 	 */
-	if (xfs_bmap_one_block(dp, XFS_ATTR_FORK))
+	if (xfs_attr_is_leaf(dp))
 		error = xfs_attr_node_shrink(args, state);
 
 out:
diff --git a/fs/xfs/libxfs/xfs_attr.h b/fs/xfs/libxfs/xfs_attr.h
index 3e97a935e712..2b1f61987a9d 100644
--- a/fs/xfs/libxfs/xfs_attr.h
+++ b/fs/xfs/libxfs/xfs_attr.h
@@ -85,6 +85,7 @@ int xfs_attr_inactive(struct xfs_inode *dp);
 int xfs_attr_list_ilocked(struct xfs_attr_list_context *);
 int xfs_attr_list(struct xfs_attr_list_context *);
 int xfs_inode_hasattr(struct xfs_inode *ip);
+bool xfs_attr_is_leaf(struct xfs_inode *ip);
 int xfs_attr_get_ilocked(struct xfs_da_args *args);
 int xfs_attr_get(struct xfs_da_args *args);
 int xfs_attr_set(struct xfs_da_args *args);
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index d6ef69ab1c67..556184b63061 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -518,10 +518,10 @@ xfs_attr_copy_value(
  * Query whether the total requested number of attr fork bytes of extended
  * attribute space will be able to fit inline.
  *
- * Returns zero if not, else the di_forkoff fork offset to be used in the
+ * Returns zero if not, else the i_forkoff fork offset to be used in the
  * literal area for attribute data once the new bytes have been added.
  *
- * di_forkoff must be 8 byte aligned, hence is stored as a >>3 value;
+ * i_forkoff must be 8 byte aligned, hence is stored as a >>3 value;
  * special case for dev/uuid inodes, they have fixed size data forks.
  */
 int
@@ -560,7 +560,7 @@ xfs_attr_shortform_bytesfit(
 	 * literal area rebalancing.
 	 */
 	if (bytes <= XFS_IFORK_ASIZE(dp))
-		return dp->i_d.di_forkoff;
+		return dp->i_forkoff;
 
 	/*
 	 * For attr2 we can try to move the forkoff if there is space in the
@@ -581,7 +581,7 @@ xfs_attr_shortform_bytesfit(
 		 * minimum offset only needs to be the space required for
 		 * the btree root.
 		 */
-		if (!dp->i_d.di_forkoff && dp->i_df.if_bytes >
+		if (!dp->i_forkoff && dp->i_df.if_bytes >
 		    xfs_default_attroffset(dp))
 			dsize = XFS_BMDR_SPACE_CALC(MINDBTPTRS);
 		break;
@@ -592,10 +592,10 @@ xfs_attr_shortform_bytesfit(
 		 * minforkoff to where the btree root can finish so we have
 		 * plenty of room for attrs
 		 */
-		if (dp->i_d.di_forkoff) {
-			if (offset < dp->i_d.di_forkoff)
+		if (dp->i_forkoff) {
+			if (offset < dp->i_forkoff)
 				return 0;
-			return dp->i_d.di_forkoff;
+			return dp->i_forkoff;
 		}
 		dsize = XFS_BMAP_BROOT_SPACE(mp, dp->i_df.if_broot);
 		break;
@@ -651,13 +651,8 @@ xfs_attr_shortform_create(
 	trace_xfs_attr_sf_create(args);
 
 	ASSERT(ifp->if_bytes == 0);
-	if (ifp->if_format == XFS_DINODE_FMT_EXTENTS) {
-		ifp->if_flags &= ~XFS_IFEXTENTS;	/* just in case */
+	if (ifp->if_format == XFS_DINODE_FMT_EXTENTS)
 		ifp->if_format = XFS_DINODE_FMT_LOCAL;
-		ifp->if_flags |= XFS_IFINLINE;
-	} else {
-		ASSERT(ifp->if_flags & XFS_IFINLINE);
-	}
 	xfs_idata_realloc(dp, sizeof(*hdr), XFS_ATTR_FORK);
 	hdr = (struct xfs_attr_sf_hdr *)ifp->if_u1.if_data;
 	memset(hdr, 0, sizeof(*hdr));
@@ -730,10 +725,10 @@ xfs_attr_shortform_add(
 
 	dp = args->dp;
 	mp = dp->i_mount;
-	dp->i_d.di_forkoff = forkoff;
+	dp->i_forkoff = forkoff;
 
 	ifp = dp->i_afp;
-	ASSERT(ifp->if_flags & XFS_IFINLINE);
+	ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
 	sf = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
 	if (xfs_attr_sf_findname(args, &sfe, NULL) == -EEXIST)
 		ASSERT(0);
@@ -770,7 +765,7 @@ xfs_attr_fork_remove(
 	xfs_idestroy_fork(ip->i_afp);
 	kmem_cache_free(xfs_ifork_zone, ip->i_afp);
 	ip->i_afp = NULL;
-	ip->i_d.di_forkoff = 0;
+	ip->i_forkoff = 0;
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 }
 
@@ -821,8 +816,8 @@ xfs_attr_shortform_remove(
 		xfs_attr_fork_remove(dp, args->trans);
 	} else {
 		xfs_idata_realloc(dp, -size, XFS_ATTR_FORK);
-		dp->i_d.di_forkoff = xfs_attr_shortform_bytesfit(dp, totsize);
-		ASSERT(dp->i_d.di_forkoff);
+		dp->i_forkoff = xfs_attr_shortform_bytesfit(dp, totsize);
+		ASSERT(dp->i_forkoff);
 		ASSERT(totsize > sizeof(xfs_attr_sf_hdr_t) ||
 				(args->op_flags & XFS_DA_OP_ADDNAME) ||
 				!(mp->m_flags & XFS_MOUNT_ATTR2) ||
@@ -851,7 +846,7 @@ xfs_attr_shortform_lookup(xfs_da_args_t *args)
 	trace_xfs_attr_sf_lookup(args);
 
 	ifp = args->dp->i_afp;
-	ASSERT(ifp->if_flags & XFS_IFINLINE);
+	ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
 	sf = (struct xfs_attr_shortform *)ifp->if_u1.if_data;
 	sfe = &sf->list[0];
 	for (i = 0; i < sf->hdr.count;
@@ -878,7 +873,7 @@ xfs_attr_shortform_getvalue(
 	struct xfs_attr_sf_entry *sfe;
 	int			i;
 
-	ASSERT(args->dp->i_afp->if_flags == XFS_IFINLINE);
+	ASSERT(args->dp->i_afp->if_format == XFS_DINODE_FMT_LOCAL);
 	sf = (struct xfs_attr_shortform *)args->dp->i_afp->if_u1.if_data;
 	sfe = &sf->list[0];
 	for (i = 0; i < sf->hdr.count;
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index e0905ad171f0..7e3b9b01431e 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -66,13 +66,13 @@ xfs_bmap_compute_maxlevels(
 	 * either a signed 32-bit number for the data fork, or a signed 16-bit
 	 * number for the attr fork.
 	 *
-	 * Note that we can no longer assume that if we are in ATTR1 that
-	 * the fork offset of all the inodes will be
-	 * (xfs_default_attroffset(ip) >> 3) because we could have mounted
-	 * with ATTR2 and then mounted back with ATTR1, keeping the
-	 * di_forkoff's fixed but probably at various positions. Therefore,
-	 * for both ATTR1 and ATTR2 we have to assume the worst case scenario
-	 * of a minimum size available.
+	 * Note that we can no longer assume that if we are in ATTR1 that the
+	 * fork offset of all the inodes will be
+	 * (xfs_default_attroffset(ip) >> 3) because we could have mounted with
+	 * ATTR2 and then mounted back with ATTR1, keeping the i_forkoff's fixed
+	 * but probably at various positions. Therefore, for both ATTR1 and
+	 * ATTR2 we have to assume the worst case scenario of a minimum size
+	 * available.
 	 */
 	if (whichfork == XFS_DATA_FORK) {
 		maxleafents = MAXEXTNUM;
@@ -94,6 +94,15 @@ xfs_bmap_compute_maxlevels(
 	mp->m_bm_maxlevels[whichfork] = level;
 }
 
+unsigned int
+xfs_bmap_compute_attr_offset(
+	struct xfs_mount	*mp)
+{
+	if (mp->m_sb.sb_inodesize == 256)
+		return XFS_LITINO(mp) - XFS_BMDR_SPACE_CALC(MINABTPTRS);
+	return XFS_BMDR_SPACE_CALC(6 * MINABTPTRS);
+}
+
 STATIC int				/* error */
 xfs_bmbt_lookup_eq(
 	struct xfs_btree_cur	*cur,
@@ -192,22 +201,15 @@ uint
 xfs_default_attroffset(
 	struct xfs_inode	*ip)
 {
-	struct xfs_mount	*mp = ip->i_mount;
-	uint			offset;
-
-	if (mp->m_sb.sb_inodesize == 256)
-		offset = XFS_LITINO(mp) - XFS_BMDR_SPACE_CALC(MINABTPTRS);
-	else
-		offset = XFS_BMDR_SPACE_CALC(6 * MINABTPTRS);
-
-	ASSERT(offset < XFS_LITINO(mp));
-	return offset;
+	if (ip->i_df.if_format == XFS_DINODE_FMT_DEV)
+		return roundup(sizeof(xfs_dev_t), 8);
+	return M_IGEO(ip->i_mount)->attr_fork_offset;
 }
 
 /*
- * Helper routine to reset inode di_forkoff field when switching
- * attribute fork from local to extent format - we reset it where
- * possible to make space available for inline data fork extents.
+ * Helper routine to reset inode i_forkoff field when switching attribute fork
+ * from local to extent format - we reset it where possible to make space
+ * available for inline data fork extents.
  */
 STATIC void
 xfs_bmap_forkoff_reset(
@@ -219,8 +221,8 @@ xfs_bmap_forkoff_reset(
 	    ip->i_df.if_format != XFS_DINODE_FMT_BTREE) {
 		uint	dfl_forkoff = xfs_default_attroffset(ip) >> 3;
 
-		if (dfl_forkoff > ip->i_d.di_forkoff)
-			ip->i_d.di_forkoff = dfl_forkoff;
+		if (dfl_forkoff > ip->i_forkoff)
+			ip->i_forkoff = dfl_forkoff;
 	}
 }
 
@@ -603,7 +605,7 @@ xfs_bmap_btree_to_extents(
 
 	ASSERT(cur);
 	ASSERT(whichfork != XFS_COW_FORK);
-	ASSERT(ifp->if_flags & XFS_IFEXTENTS);
+	ASSERT(!xfs_need_iread_extents(ifp));
 	ASSERT(ifp->if_format == XFS_DINODE_FMT_BTREE);
 	ASSERT(be16_to_cpu(rblock->bb_level) == 1);
 	ASSERT(be16_to_cpu(rblock->bb_numrecs) == 1);
@@ -624,14 +626,13 @@ xfs_bmap_btree_to_extents(
 		return error;
 	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork);
 	xfs_bmap_add_free(cur->bc_tp, cbno, 1, &oinfo);
-	ip->i_d.di_nblocks--;
+	ip->i_nblocks--;
 	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);
 	xfs_trans_binval(tp, cbp);
 	if (cur->bc_bufs[0] == cbp)
 		cur->bc_bufs[0] = NULL;
 	xfs_iroot_realloc(ip, -1, whichfork);
 	ASSERT(ifp->if_broot == NULL);
-	ASSERT((ifp->if_flags & XFS_IFBROOT) == 0);
 	ifp->if_format = XFS_DINODE_FMT_EXTENTS;
 	*logflagsp |= XFS_ILOG_CORE | xfs_ilog_fext(whichfork);
 	return 0;
@@ -675,7 +676,6 @@ xfs_bmap_extents_to_btree(
 	 * to expand the root.
 	 */
 	xfs_iroot_realloc(ip, 1, whichfork);
-	ifp->if_flags |= XFS_IFBROOT;
 
 	/*
 	 * Fill in the root.
@@ -726,7 +726,7 @@ xfs_bmap_extents_to_btree(
 	       args.agno >= XFS_FSB_TO_AGNO(mp, tp->t_firstblock));
 	tp->t_firstblock = args.fsbno;
 	cur->bc_ino.allocated++;
-	ip->i_d.di_nblocks++;
+	ip->i_nblocks++;
 	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, 1L);
 	error = xfs_trans_get_buf(tp, mp->m_ddev_targp,
 			XFS_FSB_TO_DADDR(mp, args.fsbno),
@@ -805,8 +805,6 @@ xfs_bmap_local_to_extents_empty(
 	ASSERT(ifp->if_nextents == 0);
 
 	xfs_bmap_forkoff_reset(ip, whichfork);
-	ifp->if_flags &= ~XFS_IFINLINE;
-	ifp->if_flags |= XFS_IFEXTENTS;
 	ifp->if_u1.if_root = NULL;
 	ifp->if_height = 0;
 	ifp->if_format = XFS_DINODE_FMT_EXTENTS;
@@ -850,7 +848,6 @@ xfs_bmap_local_to_extents(
 
 	flags = 0;
 	error = 0;
-	ASSERT((ifp->if_flags & (XFS_IFINLINE|XFS_IFEXTENTS)) == XFS_IFINLINE);
 	memset(&args, 0, sizeof(args));
 	args.tp = tp;
 	args.mp = ip->i_mount;
@@ -908,7 +905,7 @@ xfs_bmap_local_to_extents(
 	xfs_iext_insert(ip, &icur, &rec, 0);
 
 	ifp->if_nextents = 1;
-	ip->i_d.di_nblocks = 1;
+	ip->i_nblocks = 1;
 	xfs_trans_mod_dquot_byino(tp, ip,
 		XFS_TRANS_DQ_BCOUNT, 1L);
 	flags |= xfs_ilog_fext(whichfork);
@@ -927,13 +924,15 @@ xfs_bmap_add_attrfork_btree(
 	xfs_inode_t		*ip,		/* incore inode pointer */
 	int			*flags)		/* inode logging flags */
 {
+	struct xfs_btree_block	*block = ip->i_df.if_broot;
 	xfs_btree_cur_t		*cur;		/* btree cursor */
 	int			error;		/* error return value */
 	xfs_mount_t		*mp;		/* file system mount struct */
 	int			stat;		/* newroot status */
 
 	mp = ip->i_mount;
-	if (ip->i_df.if_broot_bytes <= XFS_IFORK_DSIZE(ip))
+
+	if (XFS_BMAP_BMDR_SPACE(block) <= XFS_IFORK_DSIZE(ip))
 		*flags |= XFS_ILOG_DBROOT;
 	else {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, XFS_DATA_FORK);
@@ -1027,23 +1026,27 @@ xfs_bmap_add_attrfork_local(
 	return -EFSCORRUPTED;
 }
 
-/* Set an inode attr fork off based on the format */
+/*
+ * Set an inode attr fork offset based on the format of the data fork.
+ */
 int
 xfs_bmap_set_attrforkoff(
 	struct xfs_inode	*ip,
 	int			size,
 	int			*version)
 {
+	int			default_size = xfs_default_attroffset(ip) >> 3;
+
 	switch (ip->i_df.if_format) {
 	case XFS_DINODE_FMT_DEV:
-		ip->i_d.di_forkoff = roundup(sizeof(xfs_dev_t), 8) >> 3;
+		ip->i_forkoff = default_size;
 		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;
+		ip->i_forkoff = xfs_attr_shortform_bytesfit(ip, size);
+		if (!ip->i_forkoff)
+			ip->i_forkoff = default_size;
 		else if ((ip->i_mount->m_flags & XFS_MOUNT_ATTR2) && version)
 			*version = 2;
 		break;
@@ -1092,11 +1095,7 @@ xfs_bmap_add_attrfork(
 		goto trans_cancel;
 	ASSERT(ip->i_afp == NULL);
 
-	ip->i_afp = kmem_cache_zalloc(xfs_ifork_zone,
-				      GFP_KERNEL | __GFP_NOFAIL);
-
-	ip->i_afp->if_format = XFS_DINODE_FMT_EXTENTS;
-	ip->i_afp->if_flags = XFS_IFEXTENTS;
+	ip->i_afp = xfs_ifork_alloc(XFS_DINODE_FMT_EXTENTS, 0);
 	logflags = 0;
 	switch (ip->i_df.if_format) {
 	case XFS_DINODE_FMT_LOCAL:
@@ -1222,12 +1221,10 @@ xfs_iread_extents(
 	struct xfs_btree_cur	*cur;
 	int			error;
 
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+	if (!xfs_need_iread_extents(ifp))
+		return 0;
 
-	if (XFS_IS_CORRUPT(mp, ifp->if_format != XFS_DINODE_FMT_BTREE)) {
-		error = -EFSCORRUPTED;
-		goto out;
-	}
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 
 	ir.loaded = 0;
 	xfs_iext_first(ifp, &ir.icur);
@@ -1243,8 +1240,6 @@ xfs_iread_extents(
 		goto out;
 	}
 	ASSERT(ir.loaded == xfs_iext_count(ifp));
-
-	ifp->if_flags |= XFS_IFEXTENTS;
 	return 0;
 out:
 	xfs_iext_destroy(ifp);
@@ -1279,11 +1274,9 @@ xfs_bmap_first_unused(
 
 	ASSERT(xfs_ifork_has_extents(ifp));
 
-	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
-		error = xfs_iread_extents(tp, ip, whichfork);
-		if (error)
-			return error;
-	}
+	error = xfs_iread_extents(tp, ip, whichfork);
+	if (error)
+		return error;
 
 	lowest = max = *first_unused;
 	for_each_xfs_iext(ifp, &icur, &got) {
@@ -1331,11 +1324,9 @@ xfs_bmap_last_before(
 		return -EFSCORRUPTED;
 	}
 
-	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
-		error = xfs_iread_extents(tp, ip, whichfork);
-		if (error)
-			return error;
-	}
+	error = xfs_iread_extents(tp, ip, whichfork);
+	if (error)
+		return error;
 
 	if (!xfs_iext_lookup_extent_before(ip, ifp, last_block, &icur, &got))
 		*last_block = 0;
@@ -1354,11 +1345,9 @@ xfs_bmap_last_extent(
 	struct xfs_iext_cursor	icur;
 	int			error;
 
-	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
-		error = xfs_iread_extents(tp, ip, whichfork);
-		if (error)
-			return error;
-	}
+	error = xfs_iread_extents(tp, ip, whichfork);
+	if (error)
+		return error;
 
 	xfs_iext_last(ifp, &icur);
 	if (!xfs_iext_get_extent(ifp, &icur, rec))
@@ -1440,38 +1429,6 @@ xfs_bmap_last_offset(
 }
 
 /*
- * Returns whether the selected fork of the inode has exactly one
- * block or not.  For the data fork we check this matches di_size,
- * implying the file's range is 0..bsize-1.
- */
-int					/* 1=>1 block, 0=>otherwise */
-xfs_bmap_one_block(
-	struct xfs_inode	*ip,		/* incore inode */
-	int			whichfork)	/* data or attr fork */
-{
-	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, whichfork);
-	int			rval;		/* return value */
-	struct xfs_bmbt_irec	s;		/* internal version of extent */
-	struct xfs_iext_cursor icur;
-
-#ifndef DEBUG
-	if (whichfork == XFS_DATA_FORK)
-		return XFS_ISIZE(ip) == ip->i_mount->m_sb.sb_blocksize;
-#endif	/* !DEBUG */
-	if (ifp->if_nextents != 1)
-		return 0;
-	if (ifp->if_format != XFS_DINODE_FMT_EXTENTS)
-		return 0;
-	ASSERT(ifp->if_flags & XFS_IFEXTENTS);
-	xfs_iext_first(ifp, &icur);
-	xfs_iext_get_extent(ifp, &icur, &s);
-	rval = s.br_startoff == 0 && s.br_blockcount == 1;
-	if (rval && whichfork == XFS_DATA_FORK)
-		ASSERT(XFS_ISIZE(ip) == ip->i_mount->m_sb.sb_blocksize);
-	return rval;
-}
-
-/*
  * Extent tree manipulation functions used during allocation.
  */
 
@@ -2938,7 +2895,7 @@ done:
  */
 
 /*
- * Adjust the size of the new extent based on di_extsize and rt extsize.
+ * Adjust the size of the new extent based on i_extsize and rt extsize.
  */
 int
 xfs_bmap_extsize_align(
@@ -3444,7 +3401,7 @@ xfs_bmap_btalloc_accounting(
 	}
 
 	/* data/attr fork only */
-	ap->ip->i_d.di_nblocks += args->len;
+	ap->ip->i_nblocks += args->len;
 	xfs_trans_log_inode(ap->tp, ap->ip, XFS_ILOG_CORE);
 	if (ap->wasdel) {
 		ap->ip->i_delayed_blks -= args->len;
@@ -3586,7 +3543,8 @@ xfs_bmap_exact_minlen_extent_alloc(
 	args.fsbno = ap->blkno;
 	args.oinfo = XFS_RMAP_OINFO_SKIP_UPDATE;
 	args.type = XFS_ALLOCTYPE_FIRST_AG;
-	args.total = args.minlen = args.maxlen = ap->minlen;
+	args.minlen = args.maxlen = ap->minlen;
+	args.total = ap->total;
 
 	args.alignment = 1;
 	args.minalignslop = 0;
@@ -3985,11 +3943,9 @@ xfs_bmapi_read(
 
 	XFS_STATS_INC(mp, xs_blk_mapr);
 
-	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
-		error = xfs_iread_extents(NULL, ip, whichfork);
-		if (error)
-			return error;
-	}
+	error = xfs_iread_extents(NULL, ip, whichfork);
+	if (error)
+		return error;
 
 	if (!xfs_iext_lookup_extent(ip, ifp, bno, &icur, &got))
 		eof = true;
@@ -4227,7 +4183,7 @@ xfs_bmapi_allocate(
 			return error;
 	}
 
-	if ((ifp->if_flags & XFS_IFBROOT) && !bma->cur)
+	if (ifp->if_format == XFS_DINODE_FMT_BTREE && !bma->cur)
 		bma->cur = xfs_bmbt_init_cursor(mp, bma->tp, bma->ip, whichfork);
 	/*
 	 * Bump the number of extents we've allocated
@@ -4300,7 +4256,7 @@ xfs_bmapi_convert_unwritten(
 	 * Modify (by adding) the state flag, if writing.
 	 */
 	ASSERT(mval->br_blockcount <= len);
-	if ((ifp->if_flags & XFS_IFBROOT) && !bma->cur) {
+	if (ifp->if_format == XFS_DINODE_FMT_BTREE && !bma->cur) {
 		bma->cur = xfs_bmbt_init_cursor(bma->ip->i_mount, bma->tp,
 					bma->ip, whichfork);
 	}
@@ -4469,11 +4425,9 @@ xfs_bmapi_write(
 
 	XFS_STATS_INC(mp, xs_blk_mapw);
 
-	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
-		error = xfs_iread_extents(tp, ip, whichfork);
-		if (error)
-			goto error0;
-	}
+	error = xfs_iread_extents(tp, ip, whichfork);
+	if (error)
+		goto error0;
 
 	if (!xfs_iext_lookup_extent(ip, ifp, bno, &bma.icur, &bma.got))
 		eof = true;
@@ -4752,11 +4706,9 @@ xfs_bmapi_remap(
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
 
-	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
-		error = xfs_iread_extents(tp, ip, whichfork);
-		if (error)
-			return error;
-	}
+	error = xfs_iread_extents(tp, ip, whichfork);
+	if (error)
+		return error;
 
 	if (xfs_iext_lookup_extent(ip, ifp, bno, &icur, &got)) {
 		/* make sure we only reflink into a hole. */
@@ -4764,10 +4716,10 @@ xfs_bmapi_remap(
 		ASSERT(got.br_startoff - bno >= len);
 	}
 
-	ip->i_d.di_nblocks += len;
+	ip->i_nblocks += len;
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
-	if (ifp->if_flags & XFS_IFBROOT) {
+	if (ifp->if_format == XFS_DINODE_FMT_BTREE) {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
 		cur->bc_ino.flags = 0;
 	}
@@ -5355,7 +5307,7 @@ xfs_bmap_del_extent_real(
 	 * Adjust inode # blocks in the file.
 	 */
 	if (nblks)
-		ip->i_d.di_nblocks -= nblks;
+		ip->i_nblocks -= nblks;
 	/*
 	 * Adjust quota data.
 	 */
@@ -5427,9 +5379,10 @@ __xfs_bunmapi(
 	else
 		max_len = len;
 
-	if (!(ifp->if_flags & XFS_IFEXTENTS) &&
-	    (error = xfs_iread_extents(tp, ip, whichfork)))
+	error = xfs_iread_extents(tp, ip, whichfork);
+	if (error)
 		return error;
+
 	if (xfs_iext_count(ifp) == 0) {
 		*rlen = 0;
 		return 0;
@@ -5445,7 +5398,7 @@ __xfs_bunmapi(
 	end--;
 
 	logflags = 0;
-	if (ifp->if_flags & XFS_IFBROOT) {
+	if (ifp->if_format == XFS_DINODE_FMT_BTREE) {
 		ASSERT(ifp->if_format == XFS_DINODE_FMT_BTREE);
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
 		cur->bc_ino.flags = 0;
@@ -5915,13 +5868,11 @@ xfs_bmap_collapse_extents(
 
 	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL));
 
-	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
-		error = xfs_iread_extents(tp, ip, whichfork);
-		if (error)
-			return error;
-	}
+	error = xfs_iread_extents(tp, ip, whichfork);
+	if (error)
+		return error;
 
-	if (ifp->if_flags & XFS_IFBROOT) {
+	if (ifp->if_format == XFS_DINODE_FMT_BTREE) {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
 		cur->bc_ino.flags = 0;
 	}
@@ -6032,13 +5983,11 @@ xfs_bmap_insert_extents(
 
 	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL));
 
-	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
-		error = xfs_iread_extents(tp, ip, whichfork);
-		if (error)
-			return error;
-	}
+	error = xfs_iread_extents(tp, ip, whichfork);
+	if (error)
+		return error;
 
-	if (ifp->if_flags & XFS_IFBROOT) {
+	if (ifp->if_format == XFS_DINODE_FMT_BTREE) {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
 		cur->bc_ino.flags = 0;
 	}
@@ -6135,12 +6084,10 @@ xfs_bmap_split_extent(
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
 
-	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
-		/* Read in all the extents */
-		error = xfs_iread_extents(tp, ip, whichfork);
-		if (error)
-			return error;
-	}
+	/* Read in all the extents */
+	error = xfs_iread_extents(tp, ip, whichfork);
+	if (error)
+		return error;
 
 	/*
 	 * If there are not extents, or split_fsb lies in a hole we are done.
@@ -6155,7 +6102,7 @@ xfs_bmap_split_extent(
 	new.br_blockcount = got.br_blockcount - gotblkcnt;
 	new.br_state = got.br_state;
 
-	if (ifp->if_flags & XFS_IFBROOT) {
+	if (ifp->if_format == XFS_DINODE_FMT_BTREE) {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
 		cur->bc_ino.flags = 0;
 		error = xfs_bmbt_lookup_eq(cur, &got, &i);
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 6747e97a7949..f9a390ecfb1d 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -185,6 +185,7 @@ static inline bool xfs_bmap_is_written_extent(struct xfs_bmbt_irec *irec)
 
 void	xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno,
 		xfs_filblks_t len);
+unsigned int xfs_bmap_compute_attr_offset(struct xfs_mount *mp);
 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_trans *tp,
@@ -199,7 +200,6 @@ int	xfs_bmap_last_before(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t *last_block, int whichfork);
 int	xfs_bmap_last_offset(struct xfs_inode *ip, xfs_fileoff_t *unused,
 		int whichfork);
-int	xfs_bmap_one_block(struct xfs_inode *ip, int whichfork);
 int	xfs_bmapi_read(struct xfs_inode *ip, xfs_fileoff_t bno,
 		xfs_filblks_t len, struct xfs_bmbt_irec *mval,
 		int *nmap, int flags);
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index 976659190d27..1ceba020940e 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -183,7 +183,7 @@ xfs_bmbt_update_cursor(
 	struct xfs_btree_cur	*dst)
 {
 	ASSERT((dst->bc_tp->t_firstblock != NULLFSBLOCK) ||
-	       (dst->bc_ino.ip->i_d.di_flags & XFS_DIFLAG_REALTIME));
+	       (dst->bc_ino.ip->i_diflags & XFS_DIFLAG_REALTIME));
 
 	dst->bc_ino.allocated += src->bc_ino.allocated;
 	dst->bc_tp->t_firstblock = src->bc_tp->t_firstblock;
@@ -260,7 +260,7 @@ xfs_bmbt_alloc_block(
 	ASSERT(args.len == 1);
 	cur->bc_tp->t_firstblock = args.fsbno;
 	cur->bc_ino.allocated++;
-	cur->bc_ino.ip->i_d.di_nblocks++;
+	cur->bc_ino.ip->i_nblocks++;
 	xfs_trans_log_inode(args.tp, cur->bc_ino.ip, XFS_ILOG_CORE);
 	xfs_trans_mod_dquot_byino(args.tp, cur->bc_ino.ip,
 			XFS_TRANS_DQ_BCOUNT, 1L);
@@ -287,7 +287,7 @@ xfs_bmbt_free_block(
 
 	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_ino.whichfork);
 	xfs_bmap_add_free(cur->bc_tp, fsbno, 1, &oinfo);
-	ip->i_d.di_nblocks--;
+	ip->i_nblocks--;
 
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);
diff --git a/fs/xfs/libxfs/xfs_btree_staging.c b/fs/xfs/libxfs/xfs_btree_staging.c
index f464a7c7cf22..aa8dc9521c39 100644
--- a/fs/xfs/libxfs/xfs_btree_staging.c
+++ b/fs/xfs/libxfs/xfs_btree_staging.c
@@ -387,7 +387,6 @@ xfs_btree_bload_prep_block(
 		new_size = bbl->iroot_size(cur, nr_this_block, priv);
 		ifp->if_broot = kmem_zalloc(new_size, 0);
 		ifp->if_broot_bytes = (int)new_size;
-		ifp->if_flags |= XFS_IFBROOT;
 
 		/* Initialize it and send it out. */
 		xfs_btree_init_block_int(cur->bc_mp, ifp->if_broot,
diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index e46bc03365db..83ac9771bfb5 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -2145,7 +2145,7 @@ xfs_da_grow_inode_int(
 	struct xfs_trans	*tp = args->trans;
 	struct xfs_inode	*dp = args->dp;
 	int			w = args->whichfork;
-	xfs_rfsblock_t		nblks = dp->i_d.di_nblocks;
+	xfs_rfsblock_t		nblks = dp->i_nblocks;
 	struct xfs_bmbt_irec	map, *mapp;
 	int			nmap, error, got, i, mapi;
 
@@ -2211,7 +2211,7 @@ xfs_da_grow_inode_int(
 	}
 
 	/* account for newly allocated blocks in reserved blocks total */
-	args->total -= dp->i_d.di_nblocks - nblks;
+	args->total -= dp->i_nblocks - nblks;
 
 out_free_map:
 	if (mapp != &map)
diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c
index 612a9c5e41b1..050bdcc4fe73 100644
--- a/fs/xfs/libxfs/xfs_dir2.c
+++ b/fs/xfs/libxfs/xfs_dir2.c
@@ -179,9 +179,9 @@ xfs_dir_isempty(
 	xfs_dir2_sf_hdr_t	*sfp;
 
 	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
-	if (dp->i_d.di_size == 0)	/* might happen during shutdown. */
+	if (dp->i_disk_size == 0)	/* might happen during shutdown. */
 		return 1;
-	if (dp->i_d.di_size > XFS_IFORK_DSIZE(dp))
+	if (dp->i_disk_size > XFS_IFORK_DSIZE(dp))
 		return 0;
 	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
 	return !sfp->count;
@@ -584,8 +584,8 @@ xfs_dir2_grow_inode(
 		xfs_fsize_t	size;		/* directory file (data) size */
 
 		size = XFS_FSB_TO_B(mp, bno + count);
-		if (size > dp->i_d.di_size) {
-			dp->i_d.di_size = size;
+		if (size > dp->i_disk_size) {
+			dp->i_disk_size = size;
 			xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE);
 		}
 	}
@@ -608,7 +608,7 @@ xfs_dir2_isblock(
 	rval = XFS_FSB_TO_B(args->dp->i_mount, last) == args->geo->blksize;
 	if (XFS_IS_CORRUPT(args->dp->i_mount,
 			   rval != 0 &&
-			   args->dp->i_d.di_size != args->geo->blksize))
+			   args->dp->i_disk_size != args->geo->blksize))
 		return -EFSCORRUPTED;
 	*vp = rval;
 	return 0;
@@ -687,7 +687,7 @@ xfs_dir2_shrink_inode(
 	/*
 	 * If the block isn't the last one in the directory, we're done.
 	 */
-	if (dp->i_d.di_size > xfs_dir2_db_off_to_byte(args->geo, db + 1, 0))
+	if (dp->i_disk_size > xfs_dir2_db_off_to_byte(args->geo, db + 1, 0))
 		return 0;
 	bno = da;
 	if ((error = xfs_bmap_last_before(tp, dp, &bno, XFS_DATA_FORK))) {
@@ -703,7 +703,7 @@ xfs_dir2_shrink_inode(
 	/*
 	 * Set the size to the new last block.
 	 */
-	dp->i_d.di_size = XFS_FSB_TO_B(mp, bno);
+	dp->i_disk_size = XFS_FSB_TO_B(mp, bno);
 	xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
 	return 0;
 }
diff --git a/fs/xfs/libxfs/xfs_dir2_block.c b/fs/xfs/libxfs/xfs_dir2_block.c
index 5b59d3f7746b..75e1421f69c4 100644
--- a/fs/xfs/libxfs/xfs_dir2_block.c
+++ b/fs/xfs/libxfs/xfs_dir2_block.c
@@ -961,7 +961,7 @@ xfs_dir2_leaf_to_block(
 	 * been left behind during no-space-reservation operations.
 	 * These will show up in the leaf bests table.
 	 */
-	while (dp->i_d.di_size > args->geo->blksize) {
+	while (dp->i_disk_size > args->geo->blksize) {
 		int hdrsz;
 
 		hdrsz = args->geo->data_entry_offset;
@@ -1096,14 +1096,14 @@ xfs_dir2_sf_to_block(
 
 	trace_xfs_dir2_sf_to_block(args);
 
-	ASSERT(ifp->if_flags & XFS_IFINLINE);
-	ASSERT(dp->i_d.di_size >= offsetof(struct xfs_dir2_sf_hdr, parent));
+	ASSERT(ifp->if_format == XFS_DINODE_FMT_LOCAL);
+	ASSERT(dp->i_disk_size >= offsetof(struct xfs_dir2_sf_hdr, parent));
 
 	oldsfp = (xfs_dir2_sf_hdr_t *)ifp->if_u1.if_data;
 
-	ASSERT(ifp->if_bytes == dp->i_d.di_size);
+	ASSERT(ifp->if_bytes == dp->i_disk_size);
 	ASSERT(ifp->if_u1.if_data != NULL);
-	ASSERT(dp->i_d.di_size >= xfs_dir2_sf_hdr_size(oldsfp->i8count));
+	ASSERT(dp->i_disk_size >= xfs_dir2_sf_hdr_size(oldsfp->i8count));
 	ASSERT(dp->i_df.if_nextents == 0);
 
 	/*
@@ -1115,7 +1115,7 @@ xfs_dir2_sf_to_block(
 
 	xfs_idata_realloc(dp, -ifp->if_bytes, XFS_DATA_FORK);
 	xfs_bmap_local_to_extents_empty(tp, dp, XFS_DATA_FORK);
-	dp->i_d.di_size = 0;
+	dp->i_disk_size = 0;
 
 	/*
 	 * Add block 0 to the inode.
diff --git a/fs/xfs/libxfs/xfs_dir2_data.c b/fs/xfs/libxfs/xfs_dir2_data.c
index 375b3edb2ad2..e67fa086f2c1 100644
--- a/fs/xfs/libxfs/xfs_dir2_data.c
+++ b/fs/xfs/libxfs/xfs_dir2_data.c
@@ -218,7 +218,7 @@ __xfs_dir3_data_check(
 		 */
 		if (dep->namelen == 0)
 			return __this_address;
-		if (xfs_dir_ino_validate(mp, be64_to_cpu(dep->inumber)))
+		if (!xfs_verify_dir_ino(mp, be64_to_cpu(dep->inumber)))
 			return __this_address;
 		if (offset + xfs_dir2_data_entsize(mp, dep->namelen) > end)
 			return __this_address;
diff --git a/fs/xfs/libxfs/xfs_dir2_leaf.c b/fs/xfs/libxfs/xfs_dir2_leaf.c
index 95d2a3f92d75..5369d8bb2593 100644
--- a/fs/xfs/libxfs/xfs_dir2_leaf.c
+++ b/fs/xfs/libxfs/xfs_dir2_leaf.c
@@ -113,7 +113,7 @@ xfs_dir3_leaf1_check(
 	} else if (leafhdr.magic != XFS_DIR2_LEAF1_MAGIC)
 		return __this_address;
 
-	return xfs_dir3_leaf_check_int(dp->i_mount, &leafhdr, leaf);
+	return xfs_dir3_leaf_check_int(dp->i_mount, &leafhdr, leaf, false);
 }
 
 static inline void
@@ -139,7 +139,8 @@ xfs_failaddr_t
 xfs_dir3_leaf_check_int(
 	struct xfs_mount		*mp,
 	struct xfs_dir3_icleaf_hdr	*hdr,
-	struct xfs_dir2_leaf		*leaf)
+	struct xfs_dir2_leaf		*leaf,
+	bool				expensive_checking)
 {
 	struct xfs_da_geometry		*geo = mp->m_dir_geo;
 	xfs_dir2_leaf_tail_t		*ltp;
@@ -151,7 +152,7 @@ xfs_dir3_leaf_check_int(
 	/*
 	 * XXX (dgc): This value is not restrictive enough.
 	 * Should factor in the size of the bests table as well.
-	 * We can deduce a value for that from di_size.
+	 * We can deduce a value for that from i_disk_size.
 	 */
 	if (hdr->count > geo->leaf_max_ents)
 		return __this_address;
@@ -162,6 +163,9 @@ xfs_dir3_leaf_check_int(
 	    (char *)&hdr->ents[hdr->count] > (char *)xfs_dir2_leaf_bests_p(ltp))
 		return __this_address;
 
+	if (!expensive_checking)
+		return NULL;
+
 	/* Check hash value order, count stale entries.  */
 	for (i = stale = 0; i < hdr->count; i++) {
 		if (i + 1 < hdr->count) {
@@ -195,7 +199,7 @@ xfs_dir3_leaf_verify(
 		return fa;
 
 	xfs_dir2_leaf_hdr_from_disk(mp, &leafhdr, bp->b_addr);
-	return xfs_dir3_leaf_check_int(mp, &leafhdr, bp->b_addr);
+	return xfs_dir3_leaf_check_int(mp, &leafhdr, bp->b_addr, true);
 }
 
 static void
diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c
index 5d51265d29d6..d0520afb913a 100644
--- a/fs/xfs/libxfs/xfs_dir2_node.c
+++ b/fs/xfs/libxfs/xfs_dir2_node.c
@@ -73,7 +73,7 @@ xfs_dir3_leafn_check(
 	} else if (leafhdr.magic != XFS_DIR2_LEAFN_MAGIC)
 		return __this_address;
 
-	return xfs_dir3_leaf_check_int(dp->i_mount, &leafhdr, leaf);
+	return xfs_dir3_leaf_check_int(dp->i_mount, &leafhdr, leaf, false);
 }
 
 static inline void
@@ -441,7 +441,7 @@ xfs_dir2_leaf_to_node(
 	leaf = lbp->b_addr;
 	ltp = xfs_dir2_leaf_tail_p(args->geo, leaf);
 	if (be32_to_cpu(ltp->bestcount) >
-				(uint)dp->i_d.di_size / args->geo->blksize) {
+				(uint)dp->i_disk_size / args->geo->blksize) {
 		xfs_buf_mark_corrupt(lbp);
 		return -EFSCORRUPTED;
 	}
diff --git a/fs/xfs/libxfs/xfs_dir2_priv.h b/fs/xfs/libxfs/xfs_dir2_priv.h
index 44c6a77cba05..94943ce49cab 100644
--- a/fs/xfs/libxfs/xfs_dir2_priv.h
+++ b/fs/xfs/libxfs/xfs_dir2_priv.h
@@ -127,7 +127,8 @@ xfs_dir3_leaf_find_entry(struct xfs_dir3_icleaf_hdr *leafhdr,
 extern int xfs_dir2_node_to_leaf(struct xfs_da_state *state);
 
 extern xfs_failaddr_t xfs_dir3_leaf_check_int(struct xfs_mount *mp,
-		struct xfs_dir3_icleaf_hdr *hdr, struct xfs_dir2_leaf *leaf);
+		struct xfs_dir3_icleaf_hdr *hdr, struct xfs_dir2_leaf *leaf,
+		bool expensive_checks);
 
 /* xfs_dir2_node.c */
 void xfs_dir2_free_hdr_from_disk(struct xfs_mount *mp,
diff --git a/fs/xfs/libxfs/xfs_dir2_sf.c b/fs/xfs/libxfs/xfs_dir2_sf.c
index 8c4f76bba88b..46d18bf9d5e1 100644
--- a/fs/xfs/libxfs/xfs_dir2_sf.c
+++ b/fs/xfs/libxfs/xfs_dir2_sf.c
@@ -344,7 +344,7 @@ xfs_dir2_block_to_sf(
 	ASSERT(dp->i_df.if_bytes == 0);
 	xfs_init_local_fork(dp, XFS_DATA_FORK, sfp, size);
 	dp->i_df.if_format = XFS_DINODE_FMT_LOCAL;
-	dp->i_d.di_size = size;
+	dp->i_disk_size = size;
 
 	logflags |= XFS_ILOG_DDATA;
 	xfs_dir2_sf_check(args);
@@ -367,7 +367,7 @@ xfs_dir2_sf_addname(
 	xfs_inode_t		*dp;		/* incore directory inode */
 	int			error;		/* error return value */
 	int			incr_isize;	/* total change in size */
-	int			new_isize;	/* di_size after adding name */
+	int			new_isize;	/* size after adding name */
 	int			objchange;	/* changing to 8-byte inodes */
 	xfs_dir2_data_aoff_t	offset = 0;	/* offset for new entry */
 	int			pick;		/* which algorithm to use */
@@ -378,12 +378,12 @@ xfs_dir2_sf_addname(
 
 	ASSERT(xfs_dir2_sf_lookup(args) == -ENOENT);
 	dp = args->dp;
-	ASSERT(dp->i_df.if_flags & XFS_IFINLINE);
-	ASSERT(dp->i_d.di_size >= offsetof(struct xfs_dir2_sf_hdr, parent));
-	ASSERT(dp->i_df.if_bytes == dp->i_d.di_size);
+	ASSERT(dp->i_df.if_format == XFS_DINODE_FMT_LOCAL);
+	ASSERT(dp->i_disk_size >= offsetof(struct xfs_dir2_sf_hdr, parent));
+	ASSERT(dp->i_df.if_bytes == dp->i_disk_size);
 	ASSERT(dp->i_df.if_u1.if_data != NULL);
 	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
-	ASSERT(dp->i_d.di_size >= xfs_dir2_sf_hdr_size(sfp->i8count));
+	ASSERT(dp->i_disk_size >= xfs_dir2_sf_hdr_size(sfp->i8count));
 	/*
 	 * Compute entry (and change in) size.
 	 */
@@ -401,7 +401,7 @@ xfs_dir2_sf_addname(
 		objchange = 1;
 	}
 
-	new_isize = (int)dp->i_d.di_size + incr_isize;
+	new_isize = (int)dp->i_disk_size + incr_isize;
 	/*
 	 * Won't fit as shortform any more (due to size),
 	 * or the pick routine says it won't (due to offset values).
@@ -492,7 +492,7 @@ xfs_dir2_sf_addname_easy(
 	sfp->count++;
 	if (args->inumber > XFS_DIR2_MAX_SHORT_INUM)
 		sfp->i8count++;
-	dp->i_d.di_size = new_isize;
+	dp->i_disk_size = new_isize;
 	xfs_dir2_sf_check(args);
 }
 
@@ -519,7 +519,7 @@ xfs_dir2_sf_addname_hard(
 	int			nbytes;		/* temp for byte copies */
 	xfs_dir2_data_aoff_t	new_offset;	/* next offset value */
 	xfs_dir2_data_aoff_t	offset;		/* current offset value */
-	int			old_isize;	/* previous di_size */
+	int			old_isize;	/* previous size */
 	xfs_dir2_sf_entry_t	*oldsfep;	/* entry in original dir */
 	xfs_dir2_sf_hdr_t	*oldsfp;	/* original shortform dir */
 	xfs_dir2_sf_entry_t	*sfep;		/* entry in new dir */
@@ -529,7 +529,7 @@ xfs_dir2_sf_addname_hard(
 	 * Copy the old directory to the stack buffer.
 	 */
 	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
-	old_isize = (int)dp->i_d.di_size;
+	old_isize = (int)dp->i_disk_size;
 	buf = kmem_alloc(old_isize, 0);
 	oldsfp = (xfs_dir2_sf_hdr_t *)buf;
 	memcpy(oldsfp, sfp, old_isize);
@@ -586,7 +586,7 @@ xfs_dir2_sf_addname_hard(
 		memcpy(sfep, oldsfep, old_isize - nbytes);
 	}
 	kmem_free(buf);
-	dp->i_d.di_size = new_isize;
+	dp->i_disk_size = new_isize;
 	xfs_dir2_sf_check(args);
 }
 
@@ -697,7 +697,7 @@ xfs_dir2_sf_check(
 		ASSERT(xfs_dir2_sf_get_ftype(mp, sfep) < XFS_DIR3_FT_MAX);
 	}
 	ASSERT(i8count == sfp->i8count);
-	ASSERT((char *)sfep - (char *)sfp == dp->i_d.di_size);
+	ASSERT((char *)sfep - (char *)sfp == dp->i_disk_size);
 	ASSERT(offset +
 	       (sfp->count + 2) * (uint)sizeof(xfs_dir2_leaf_entry_t) +
 	       (uint)sizeof(xfs_dir2_block_tail_t) <= args->geo->blksize);
@@ -821,18 +821,16 @@ xfs_dir2_sf_create(
 	dp = args->dp;
 
 	ASSERT(dp != NULL);
-	ASSERT(dp->i_d.di_size == 0);
+	ASSERT(dp->i_disk_size == 0);
 	/*
 	 * If it's currently a zero-length extent file,
 	 * convert it to local format.
 	 */
 	if (dp->i_df.if_format == XFS_DINODE_FMT_EXTENTS) {
-		dp->i_df.if_flags &= ~XFS_IFEXTENTS;	/* just in case */
 		dp->i_df.if_format = XFS_DINODE_FMT_LOCAL;
 		xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE);
-		dp->i_df.if_flags |= XFS_IFINLINE;
 	}
-	ASSERT(dp->i_df.if_flags & XFS_IFINLINE);
+	ASSERT(dp->i_df.if_format == XFS_DINODE_FMT_LOCAL);
 	ASSERT(dp->i_df.if_bytes == 0);
 	i8count = pino > XFS_DIR2_MAX_SHORT_INUM;
 	size = xfs_dir2_sf_hdr_size(i8count);
@@ -850,7 +848,7 @@ xfs_dir2_sf_create(
 	 */
 	xfs_dir2_sf_put_parent_ino(sfp, pino);
 	sfp->count = 0;
-	dp->i_d.di_size = size;
+	dp->i_disk_size = size;
 	xfs_dir2_sf_check(args);
 	xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_DDATA);
 	return 0;
@@ -877,12 +875,12 @@ xfs_dir2_sf_lookup(
 
 	xfs_dir2_sf_check(args);
 
-	ASSERT(dp->i_df.if_flags & XFS_IFINLINE);
-	ASSERT(dp->i_d.di_size >= offsetof(struct xfs_dir2_sf_hdr, parent));
-	ASSERT(dp->i_df.if_bytes == dp->i_d.di_size);
+	ASSERT(dp->i_df.if_format == XFS_DINODE_FMT_LOCAL);
+	ASSERT(dp->i_disk_size >= offsetof(struct xfs_dir2_sf_hdr, parent));
+	ASSERT(dp->i_df.if_bytes == dp->i_disk_size);
 	ASSERT(dp->i_df.if_u1.if_data != NULL);
 	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
-	ASSERT(dp->i_d.di_size >= xfs_dir2_sf_hdr_size(sfp->i8count));
+	ASSERT(dp->i_disk_size >= xfs_dir2_sf_hdr_size(sfp->i8count));
 	/*
 	 * Special case for .
 	 */
@@ -954,8 +952,8 @@ xfs_dir2_sf_removename(
 
 	trace_xfs_dir2_sf_removename(args);
 
-	ASSERT(dp->i_df.if_flags & XFS_IFINLINE);
-	oldsize = (int)dp->i_d.di_size;
+	ASSERT(dp->i_df.if_format == XFS_DINODE_FMT_LOCAL);
+	oldsize = (int)dp->i_disk_size;
 	ASSERT(oldsize >= offsetof(struct xfs_dir2_sf_hdr, parent));
 	ASSERT(dp->i_df.if_bytes == oldsize);
 	ASSERT(dp->i_df.if_u1.if_data != NULL);
@@ -995,7 +993,7 @@ xfs_dir2_sf_removename(
 	 * Fix up the header and file size.
 	 */
 	sfp->count--;
-	dp->i_d.di_size = newsize;
+	dp->i_disk_size = newsize;
 	/*
 	 * Reallocate, making it smaller.
 	 */
@@ -1053,12 +1051,12 @@ xfs_dir2_sf_replace(
 
 	trace_xfs_dir2_sf_replace(args);
 
-	ASSERT(dp->i_df.if_flags & XFS_IFINLINE);
-	ASSERT(dp->i_d.di_size >= offsetof(struct xfs_dir2_sf_hdr, parent));
-	ASSERT(dp->i_df.if_bytes == dp->i_d.di_size);
+	ASSERT(dp->i_df.if_format == XFS_DINODE_FMT_LOCAL);
+	ASSERT(dp->i_disk_size >= offsetof(struct xfs_dir2_sf_hdr, parent));
+	ASSERT(dp->i_df.if_bytes == dp->i_disk_size);
 	ASSERT(dp->i_df.if_u1.if_data != NULL);
 	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
-	ASSERT(dp->i_d.di_size >= xfs_dir2_sf_hdr_size(sfp->i8count));
+	ASSERT(dp->i_disk_size >= xfs_dir2_sf_hdr_size(sfp->i8count));
 
 	/*
 	 * New inode number is large, and need to convert to 8-byte inodes.
@@ -1219,7 +1217,7 @@ xfs_dir2_sf_toino4(
 	 * Clean up the inode.
 	 */
 	kmem_free(buf);
-	dp->i_d.di_size = newsize;
+	dp->i_disk_size = newsize;
 	xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_DDATA);
 }
 
@@ -1292,6 +1290,6 @@ xfs_dir2_sf_toino8(
 	 * Clean up the inode.
 	 */
 	kmem_free(buf);
-	dp->i_d.di_size = newsize;
+	dp->i_disk_size = newsize;
 	xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE | XFS_ILOG_DDATA);
 }
diff --git a/fs/xfs/libxfs/xfs_errortag.h b/fs/xfs/libxfs/xfs_errortag.h
index 6ca9084b6934..a23a52e643ad 100644
--- a/fs/xfs/libxfs/xfs_errortag.h
+++ b/fs/xfs/libxfs/xfs_errortag.h
@@ -58,7 +58,8 @@
 #define XFS_ERRTAG_BUF_IOERROR				35
 #define XFS_ERRTAG_REDUCE_MAX_IEXTENTS			36
 #define XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT		37
-#define XFS_ERRTAG_MAX					38
+#define XFS_ERRTAG_AG_RESV_FAIL				38
+#define XFS_ERRTAG_MAX					39
 
 /*
  * Random factors for above tags, 1 means always, 2 means 1/2 time, etc.
@@ -101,5 +102,6 @@
 #define XFS_RANDOM_BUF_IOERROR				XFS_RANDOM_DEFAULT
 #define XFS_RANDOM_REDUCE_MAX_IEXTENTS			1
 #define XFS_RANDOM_BMAP_ALLOC_MINLEN_EXTENT		1
+#define XFS_RANDOM_AG_RESV_FAIL				1
 
 #endif /* __XFS_ERRORTAG_H_ */
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 630388b72dbe..76e2461b9e66 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -955,9 +955,8 @@ static inline time64_t xfs_bigtime_to_unix(uint64_t ondisk_seconds)
  * attribute use the XFS_DFORK_DPTR, XFS_DFORK_APTR, and XFS_DFORK_PTR macros
  * below.
  *
- * There is a very similar struct icdinode in xfs_inode which matches the
- * layout of the first 96 bytes of this structure, but is kept in native
- * format instead of big endian.
+ * There is a very similar struct xfs_log_dinode which matches the layout of
+ * this structure, but is kept in native format instead of big endian.
  *
  * Note: di_flushiter is only used by v1/2 inodes - it's effectively a zeroed
  * padding field for v3 inodes.
diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index 6bf7d8b7d743..a83bdd0c47a8 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -65,7 +65,7 @@ struct getbmapx {
 
 /*	bmv_iflags values - set by XFS_IOC_GETBMAPX caller.	*/
 #define BMV_IF_ATTRFORK		0x1	/* return attr fork rather than data */
-#define BMV_IF_NO_DMAPI_READ	0x2	/* Do not generate DMAPI read event  */
+#define BMV_IF_NO_DMAPI_READ	0x2	/* Deprecated */
 #define BMV_IF_PREALLOC		0x4	/* rtn status BMV_OF_PREALLOC if req */
 #define BMV_IF_DELALLOC		0x8	/* rtn status BMV_OF_DELALLOC if req */
 #define BMV_IF_NO_HOLES		0x10	/* Do not return holes */
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 69b228fce81a..eefdb518fe64 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -2535,12 +2535,12 @@ xfs_agi_verify(
 		return __this_address;
 
 	if (be32_to_cpu(agi->agi_level) < 1 ||
-	    be32_to_cpu(agi->agi_level) > XFS_BTREE_MAXLEVELS)
+	    be32_to_cpu(agi->agi_level) > M_IGEO(mp)->inobt_maxlevels)
 		return __this_address;
 
 	if (xfs_sb_version_hasfinobt(&mp->m_sb) &&
 	    (be32_to_cpu(agi->agi_free_level) < 1 ||
-	     be32_to_cpu(agi->agi_free_level) > XFS_BTREE_MAXLEVELS))
+	     be32_to_cpu(agi->agi_free_level) > M_IGEO(mp)->inobt_maxlevels))
 		return __this_address;
 
 	/*
diff --git a/fs/xfs/libxfs/xfs_iext_tree.c b/fs/xfs/libxfs/xfs_iext_tree.c
index b4164256993d..773cf4349428 100644
--- a/fs/xfs/libxfs/xfs_iext_tree.c
+++ b/fs/xfs/libxfs/xfs_iext_tree.c
@@ -8,9 +8,9 @@
 #include "xfs_format.h"
 #include "xfs_bit.h"
 #include "xfs_log_format.h"
-#include "xfs_inode.h"
 #include "xfs_trans_resv.h"
 #include "xfs_mount.h"
+#include "xfs_inode.h"
 #include "xfs_trace.h"
 
 /*
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 4d7410e49db4..5c9a7440d9e4 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -124,37 +124,18 @@ const struct xfs_buf_ops xfs_inode_buf_ra_ops = {
 /*
  * This routine is called to map an inode to the buffer containing the on-disk
  * version of the inode.  It returns a pointer to the buffer containing the
- * on-disk inode in the bpp parameter, and in the dipp parameter it returns a
- * pointer to the on-disk inode within that buffer.
- *
- * If a non-zero error is returned, then the contents of bpp and dipp are
- * undefined.
+ * on-disk inode in the bpp parameter.
  */
 int
 xfs_imap_to_bp(
 	struct xfs_mount	*mp,
 	struct xfs_trans	*tp,
 	struct xfs_imap		*imap,
-	struct xfs_dinode       **dipp,
-	struct xfs_buf		**bpp,
-	uint			buf_flags)
+	struct xfs_buf		**bpp)
 {
-	struct xfs_buf		*bp;
-	int			error;
-
-	buf_flags |= XBF_UNMAPPED;
-	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno,
-				   (int)imap->im_len, buf_flags, &bp,
+	return xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno,
+				   imap->im_len, XBF_UNMAPPED, bpp,
 				   &xfs_inode_buf_ops);
-	if (error) {
-		ASSERT(error != -EAGAIN || (buf_flags & XBF_TRYLOCK));
-		return error;
-	}
-
-	*bpp = bp;
-	if (dipp)
-		*dipp = xfs_buf_offset(bp, imap->im_boffset);
-	return 0;
 }
 
 static inline struct timespec64 xfs_inode_decode_bigtime(uint64_t ts)
@@ -192,7 +173,6 @@ xfs_inode_from_disk(
 	struct xfs_inode	*ip,
 	struct xfs_dinode	*from)
 {
-	struct xfs_icdinode	*to = &ip->i_d;
 	struct inode		*inode = VFS_I(ip);
 	int			error;
 	xfs_failaddr_t		fa;
@@ -212,7 +192,8 @@ xfs_inode_from_disk(
 	 * inode. If the inode is unused, mode is zero and we shouldn't mess
 	 * with the uninitialized part of it.
 	 */
-	to->di_flushiter = be16_to_cpu(from->di_flushiter);
+	if (!xfs_sb_version_has_v3inode(&ip->i_mount->m_sb))
+		ip->i_flushiter = be16_to_cpu(from->di_flushiter);
 	inode->i_generation = be32_to_cpu(from->di_gen);
 	inode->i_mode = be16_to_cpu(from->di_mode);
 	if (!inode->i_mode)
@@ -225,10 +206,10 @@ xfs_inode_from_disk(
 	 */
 	if (unlikely(from->di_version == 1)) {
 		set_nlink(inode, be16_to_cpu(from->di_onlink));
-		to->di_projid = 0;
+		ip->i_projid = 0;
 	} else {
 		set_nlink(inode, be32_to_cpu(from->di_nlink));
-		to->di_projid = (prid_t)be16_to_cpu(from->di_projid_hi) << 16 |
+		ip->i_projid = (prid_t)be16_to_cpu(from->di_projid_hi) << 16 |
 					be16_to_cpu(from->di_projid_lo);
 	}
 
@@ -245,20 +226,21 @@ xfs_inode_from_disk(
 	inode->i_mtime = xfs_inode_from_disk_ts(from, from->di_mtime);
 	inode->i_ctime = xfs_inode_from_disk_ts(from, from->di_ctime);
 
-	to->di_size = be64_to_cpu(from->di_size);
-	to->di_nblocks = be64_to_cpu(from->di_nblocks);
-	to->di_extsize = be32_to_cpu(from->di_extsize);
-	to->di_forkoff = from->di_forkoff;
-	to->di_dmevmask	= be32_to_cpu(from->di_dmevmask);
-	to->di_dmstate	= be16_to_cpu(from->di_dmstate);
-	to->di_flags	= be16_to_cpu(from->di_flags);
+	ip->i_disk_size = be64_to_cpu(from->di_size);
+	ip->i_nblocks = be64_to_cpu(from->di_nblocks);
+	ip->i_extsize = be32_to_cpu(from->di_extsize);
+	ip->i_forkoff = from->di_forkoff;
+	ip->i_diflags	= be16_to_cpu(from->di_flags);
+
+	if (from->di_dmevmask || from->di_dmstate)
+		xfs_iflags_set(ip, XFS_IPRESERVE_DM_FIELDS);
 
 	if (xfs_sb_version_has_v3inode(&ip->i_mount->m_sb)) {
 		inode_set_iversion_queried(inode,
 					   be64_to_cpu(from->di_changecount));
-		to->di_crtime = xfs_inode_from_disk_ts(from, from->di_crtime);
-		to->di_flags2 = be64_to_cpu(from->di_flags2);
-		to->di_cowextsize = be32_to_cpu(from->di_cowextsize);
+		ip->i_crtime = xfs_inode_from_disk_ts(from, from->di_crtime);
+		ip->i_diflags2 = be64_to_cpu(from->di_flags2);
+		ip->i_cowextsize = be32_to_cpu(from->di_cowextsize);
 	}
 
 	error = xfs_iformat_data_fork(ip, from);
@@ -303,7 +285,6 @@ xfs_inode_to_disk(
 	struct xfs_dinode	*to,
 	xfs_lsn_t		lsn)
 {
-	struct xfs_icdinode	*from = &ip->i_d;
 	struct inode		*inode = VFS_I(ip);
 
 	to->di_magic = cpu_to_be16(XFS_DINODE_MAGIC);
@@ -312,8 +293,8 @@ xfs_inode_to_disk(
 	to->di_format = xfs_ifork_format(&ip->i_df);
 	to->di_uid = cpu_to_be32(i_uid_read(inode));
 	to->di_gid = cpu_to_be32(i_gid_read(inode));
-	to->di_projid_lo = cpu_to_be16(from->di_projid & 0xffff);
-	to->di_projid_hi = cpu_to_be16(from->di_projid >> 16);
+	to->di_projid_lo = cpu_to_be16(ip->i_projid & 0xffff);
+	to->di_projid_hi = cpu_to_be16(ip->i_projid >> 16);
 
 	memset(to->di_pad, 0, sizeof(to->di_pad));
 	to->di_atime = xfs_inode_to_disk_ts(ip, inode->i_atime);
@@ -323,23 +304,21 @@ xfs_inode_to_disk(
 	to->di_gen = cpu_to_be32(inode->i_generation);
 	to->di_mode = cpu_to_be16(inode->i_mode);
 
-	to->di_size = cpu_to_be64(from->di_size);
-	to->di_nblocks = cpu_to_be64(from->di_nblocks);
-	to->di_extsize = cpu_to_be32(from->di_extsize);
+	to->di_size = cpu_to_be64(ip->i_disk_size);
+	to->di_nblocks = cpu_to_be64(ip->i_nblocks);
+	to->di_extsize = cpu_to_be32(ip->i_extsize);
 	to->di_nextents = cpu_to_be32(xfs_ifork_nextents(&ip->i_df));
 	to->di_anextents = cpu_to_be16(xfs_ifork_nextents(ip->i_afp));
-	to->di_forkoff = from->di_forkoff;
+	to->di_forkoff = ip->i_forkoff;
 	to->di_aformat = xfs_ifork_format(ip->i_afp);
-	to->di_dmevmask = cpu_to_be32(from->di_dmevmask);
-	to->di_dmstate = cpu_to_be16(from->di_dmstate);
-	to->di_flags = cpu_to_be16(from->di_flags);
+	to->di_flags = cpu_to_be16(ip->i_diflags);
 
 	if (xfs_sb_version_has_v3inode(&ip->i_mount->m_sb)) {
 		to->di_version = 3;
 		to->di_changecount = cpu_to_be64(inode_peek_iversion(inode));
-		to->di_crtime = xfs_inode_to_disk_ts(ip, from->di_crtime);
-		to->di_flags2 = cpu_to_be64(from->di_flags2);
-		to->di_cowextsize = cpu_to_be32(from->di_cowextsize);
+		to->di_crtime = xfs_inode_to_disk_ts(ip, ip->i_crtime);
+		to->di_flags2 = cpu_to_be64(ip->i_diflags2);
+		to->di_cowextsize = cpu_to_be32(ip->i_cowextsize);
 		to->di_ino = cpu_to_be64(ip->i_ino);
 		to->di_lsn = cpu_to_be64(lsn);
 		memset(to->di_pad2, 0, sizeof(to->di_pad2));
@@ -347,7 +326,7 @@ xfs_inode_to_disk(
 		to->di_flushiter = 0;
 	} else {
 		to->di_version = 2;
-		to->di_flushiter = cpu_to_be16(from->di_flushiter);
+		to->di_flushiter = cpu_to_be16(ip->i_flushiter);
 	}
 }
 
diff --git a/fs/xfs/libxfs/xfs_inode_buf.h b/fs/xfs/libxfs/xfs_inode_buf.h
index ef5eaf33d146..7f865bb4df84 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.h
+++ b/fs/xfs/libxfs/xfs_inode_buf.h
@@ -10,34 +10,6 @@ struct xfs_inode;
 struct xfs_dinode;
 
 /*
- * In memory representation of the XFS inode. This is held in the in-core struct
- * xfs_inode and represents the current on disk values but the structure is not
- * in on-disk format.  That is, this structure is always translated to on-disk
- * format specific structures at the appropriate time.
- */
-struct xfs_icdinode {
-	uint16_t	di_flushiter;	/* incremented on flush */
-	prid_t		di_projid;	/* owner's project id */
-	xfs_fsize_t	di_size;	/* number of bytes in file */
-	xfs_rfsblock_t	di_nblocks;	/* # of direct & btree blocks used */
-	xfs_extlen_t	di_extsize;	/* basic/minimum extent size for file */
-	uint8_t		di_forkoff;	/* attr fork offs, <<3 for 64b align */
-	uint32_t	di_dmevmask;	/* DMIG event mask */
-	uint16_t	di_dmstate;	/* DMIG state info */
-	uint16_t	di_flags;	/* random flags, XFS_DIFLAG_... */
-
-	uint64_t	di_flags2;	/* more random flags */
-	uint32_t	di_cowextsize;	/* basic cow extent size for file */
-
-	struct timespec64 di_crtime;	/* time created */
-};
-
-static inline bool xfs_icdinode_has_bigtime(const struct xfs_icdinode *icd)
-{
-	return icd->di_flags2 & XFS_DIFLAG2_BIGTIME;
-}
-
-/*
  * Inode location information.  Stored in the inode and passed to
  * xfs_imap_to_bp() to get a buffer and dinode for a given inode.
  */
@@ -47,9 +19,8 @@ struct xfs_imap {
 	unsigned short	im_boffset;	/* inode offset in block in bytes */
 };
 
-int	xfs_imap_to_bp(struct xfs_mount *, struct xfs_trans *,
-		       struct xfs_imap *, struct xfs_dinode **,
-		       struct xfs_buf **, uint);
+int	xfs_imap_to_bp(struct xfs_mount *mp, struct xfs_trans *tp,
+		       struct xfs_imap *imap, struct xfs_buf **bpp);
 void	xfs_dinode_calc_crc(struct xfs_mount *, struct xfs_dinode *);
 void	xfs_inode_to_disk(struct xfs_inode *ip, struct xfs_dinode *to,
 			  xfs_lsn_t lsn);
diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c
index e080d7e07643..1d174909f9bd 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.c
+++ b/fs/xfs/libxfs/xfs_inode_fork.c
@@ -60,8 +60,6 @@ xfs_init_local_fork(
 	}
 
 	ifp->if_bytes = size;
-	ifp->if_flags &= ~(XFS_IFEXTENTS | XFS_IFBROOT);
-	ifp->if_flags |= XFS_IFINLINE;
 }
 
 /*
@@ -151,7 +149,6 @@ xfs_iformat_extents(
 			xfs_iext_next(ifp, &icur);
 		}
 	}
-	ifp->if_flags |= XFS_IFEXTENTS;
 	return 0;
 }
 
@@ -194,8 +191,8 @@ xfs_iformat_btree(
 		     nrecs == 0 ||
 		     XFS_BMDR_SPACE_CALC(nrecs) >
 					XFS_DFORK_SIZE(dip, mp, whichfork) ||
-		     ifp->if_nextents > ip->i_d.di_nblocks) ||
-		     level == 0 || level > XFS_BTREE_MAXLEVELS) {
+		     ifp->if_nextents > ip->i_nblocks) ||
+		     level == 0 || level > XFS_BM_MAXLEVELS(mp, whichfork)) {
 		xfs_warn(mp, "corrupt inode %Lu (btree).",
 					(unsigned long long) ip->i_ino);
 		xfs_inode_verifier_error(ip, -EFSCORRUPTED,
@@ -213,8 +210,6 @@ xfs_iformat_btree(
 	 */
 	xfs_bmdr_to_bmbt(ip, dfp, XFS_DFORK_SIZE(dip, ip->i_mount, whichfork),
 			 ifp->if_broot, size);
-	ifp->if_flags &= ~XFS_IFEXTENTS;
-	ifp->if_flags |= XFS_IFBROOT;
 
 	ifp->if_bytes = 0;
 	ifp->if_u1.if_root = NULL;
@@ -242,7 +237,7 @@ xfs_iformat_data_fork(
 	case S_IFCHR:
 	case S_IFBLK:
 	case S_IFSOCK:
-		ip->i_d.di_size = 0;
+		ip->i_disk_size = 0;
 		inode->i_rdev = xfs_to_linux_dev_t(xfs_dinode_get_rdev(dip));
 		return 0;
 	case S_IFREG:
@@ -282,6 +277,19 @@ xfs_dfork_attr_shortform_size(
 	return be16_to_cpu(atp->hdr.totsize);
 }
 
+struct xfs_ifork *
+xfs_ifork_alloc(
+	enum xfs_dinode_fmt	format,
+	xfs_extnum_t		nextents)
+{
+	struct xfs_ifork	*ifp;
+
+	ifp = kmem_cache_zalloc(xfs_ifork_zone, GFP_NOFS | __GFP_NOFAIL);
+	ifp->if_format = format;
+	ifp->if_nextents = nextents;
+	return ifp;
+}
+
 int
 xfs_iformat_attr_fork(
 	struct xfs_inode	*ip,
@@ -293,11 +301,8 @@ xfs_iformat_attr_fork(
 	 * Initialize the extent count early, as the per-format routines may
 	 * depend on it.
 	 */
-	ip->i_afp = kmem_cache_zalloc(xfs_ifork_zone, GFP_NOFS | __GFP_NOFAIL);
-	ip->i_afp->if_format = dip->di_aformat;
-	if (unlikely(ip->i_afp->if_format == 0)) /* pre IRIX 6.2 file system */
-		ip->i_afp->if_format = XFS_DINODE_FMT_EXTENTS;
-	ip->i_afp->if_nextents = be16_to_cpu(dip->di_anextents);
+	ip->i_afp = xfs_ifork_alloc(dip->di_aformat,
+				be16_to_cpu(dip->di_anextents));
 
 	switch (ip->i_afp->if_format) {
 	case XFS_DINODE_FMT_LOCAL:
@@ -423,7 +428,6 @@ xfs_iroot_realloc(
 			XFS_BMBT_BLOCK_LEN(ip->i_mount));
 	} else {
 		new_broot = NULL;
-		ifp->if_flags &= ~XFS_IFBROOT;
 	}
 
 	/*
@@ -512,17 +516,16 @@ xfs_idestroy_fork(
 		ifp->if_broot = NULL;
 	}
 
-	/*
-	 * If the format is local, then we can't have an extents array so just
-	 * look for an inline data array.  If we're not local then we may or may
-	 * not have an extents list, so check and free it up if we do.
-	 */
-	if (ifp->if_format == XFS_DINODE_FMT_LOCAL) {
+	switch (ifp->if_format) {
+	case XFS_DINODE_FMT_LOCAL:
 		kmem_free(ifp->if_u1.if_data);
 		ifp->if_u1.if_data = NULL;
-	} else if (ifp->if_flags & XFS_IFEXTENTS) {
+		break;
+	case XFS_DINODE_FMT_EXTENTS:
+	case XFS_DINODE_FMT_BTREE:
 		if (ifp->if_height)
 			xfs_iext_destroy(ifp);
+		break;
 	}
 }
 
@@ -616,8 +619,6 @@ xfs_iflush_fork(
 		break;
 
 	case XFS_DINODE_FMT_EXTENTS:
-		ASSERT((ifp->if_flags & XFS_IFEXTENTS) ||
-		       !(iip->ili_fields & extflag[whichfork]));
 		if ((iip->ili_fields & extflag[whichfork]) &&
 		    (ifp->if_bytes > 0)) {
 			ASSERT(ifp->if_nextents > 0);
@@ -677,7 +678,6 @@ xfs_ifork_init_cow(
 
 	ip->i_cowfp = kmem_cache_zalloc(xfs_ifork_zone,
 				       GFP_NOFS | __GFP_NOFAIL);
-	ip->i_cowfp->if_flags = XFS_IFEXTENTS;
 	ip->i_cowfp->if_format = XFS_DINODE_FMT_EXTENTS;
 }
 
diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h
index 9e2137cd7372..a6f7897b6887 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.h
+++ b/fs/xfs/libxfs/xfs_inode_fork.h
@@ -22,19 +22,11 @@ struct xfs_ifork {
 		char		*if_data;	/* inline file data */
 	} if_u1;
 	short			if_broot_bytes;	/* bytes allocated for root */
-	unsigned char		if_flags;	/* per-fork flags */
 	int8_t			if_format;	/* format of this fork */
 	xfs_extnum_t		if_nextents;	/* # of extents in this fork */
 };
 
 /*
- * Per-fork incore inode flags.
- */
-#define	XFS_IFINLINE	0x01	/* Inline data is read in */
-#define	XFS_IFEXTENTS	0x02	/* All extent pointers are read in */
-#define	XFS_IFBROOT	0x04	/* i_broot points to the bmap b-tree root */
-
-/*
  * Worst-case increase in the fork extent count when we're adding a single
  * extent to a fork and there's no possibility of splitting an existing mapping.
  */
@@ -99,8 +91,8 @@ struct xfs_ifork {
  * Fork handling.
  */
 
-#define XFS_IFORK_Q(ip)			((ip)->i_d.di_forkoff != 0)
-#define XFS_IFORK_BOFF(ip)		((int)((ip)->i_d.di_forkoff << 3))
+#define XFS_IFORK_Q(ip)			((ip)->i_forkoff != 0)
+#define XFS_IFORK_BOFF(ip)		((int)((ip)->i_forkoff << 3))
 
 #define XFS_IFORK_PTR(ip,w)		\
 	((w) == XFS_DATA_FORK ? \
@@ -141,6 +133,8 @@ static inline int8_t xfs_ifork_format(struct xfs_ifork *ifp)
 	return ifp->if_format;
 }
 
+struct xfs_ifork *xfs_ifork_alloc(enum xfs_dinode_fmt format,
+				xfs_extnum_t nextents);
 struct xfs_ifork *xfs_iext_state_to_fork(struct xfs_inode *ip, int state);
 
 int		xfs_iformat_data_fork(struct xfs_inode *, struct xfs_dinode *);
@@ -236,4 +230,10 @@ int xfs_ifork_verify_local_attr(struct xfs_inode *ip);
 int xfs_iext_count_may_overflow(struct xfs_inode *ip, int whichfork,
 		int nr_to_add);
 
+/* returns true if the fork has extents but they are not read in yet. */
+static inline bool xfs_need_iread_extents(struct xfs_ifork *ifp)
+{
+	return ifp->if_format == XFS_DINODE_FMT_BTREE && ifp->if_height == 0;
+}
+
 #endif	/* __XFS_INODE_FORK_H__ */
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index fe3a49575ff3..483375c6a735 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -997,8 +997,8 @@ xfs_rtfree_extent(
 	 */
 	if (tp->t_frextents_delta + mp->m_sb.sb_frextents ==
 	    mp->m_sb.sb_rextents) {
-		if (!(mp->m_rbmip->i_d.di_flags & XFS_DIFLAG_NEWRTBM))
-			mp->m_rbmip->i_d.di_flags |= XFS_DIFLAG_NEWRTBM;
+		if (!(mp->m_rbmip->i_diflags & XFS_DIFLAG_NEWRTBM))
+			mp->m_rbmip->i_diflags |= XFS_DIFLAG_NEWRTBM;
 		*(uint64_t *)&VFS_I(mp->m_rbmip)->i_atime = 0;
 		xfs_trans_log_inode(tp, mp->m_rbmip, XFS_ILOG_CORE);
 	}
diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h
index 8c61a461bf7b..782fdd08f759 100644
--- a/fs/xfs/libxfs/xfs_shared.h
+++ b/fs/xfs/libxfs/xfs_shared.h
@@ -176,8 +176,12 @@ struct xfs_ino_geometry {
 
 	unsigned int	agino_log;	/* #bits for agino in inum */
 
+	/* precomputed default inode attribute fork offset */
+	unsigned int	attr_fork_offset;
+
 	/* precomputed value for di_flags2 */
 	uint64_t	new_diflags2;
+
 };
 
 #endif /* __XFS_SHARED_H__ */
diff --git a/fs/xfs/libxfs/xfs_trans_inode.c b/fs/xfs/libxfs/xfs_trans_inode.c
index 90f1d5645052..78324e043e25 100644
--- a/fs/xfs/libxfs/xfs_trans_inode.c
+++ b/fs/xfs/libxfs/xfs_trans_inode.c
@@ -70,7 +70,7 @@ xfs_trans_ichgtime(
 	if (flags & XFS_ICHGTIME_CHG)
 		inode->i_ctime = tv;
 	if (flags & XFS_ICHGTIME_CREATE)
-		ip->i_d.di_crtime = tv;
+		ip->i_crtime = tv;
 }
 
 /*
@@ -138,7 +138,7 @@ xfs_trans_log_inode(
 	if ((flags & (XFS_ILOG_CORE | XFS_ILOG_TIMESTAMP)) &&
 	    xfs_sb_version_hasbigtime(&ip->i_mount->m_sb) &&
 	    !xfs_inode_has_bigtime(ip)) {
-		ip->i_d.di_flags2 |= XFS_DIFLAG2_BIGTIME;
+		ip->i_diflags2 |= XFS_DIFLAG2_BIGTIME;
 		flags |= XFS_ILOG_CORE;
 	}
 
@@ -164,8 +164,7 @@ xfs_trans_log_inode(
 		 * here.
 		 */
 		spin_unlock(&iip->ili_lock);
-		error = xfs_imap_to_bp(ip->i_mount, tp, &ip->i_imap, NULL,
-					&bp, 0);
+		error = xfs_imap_to_bp(ip->i_mount, tp, &ip->i_imap, &bp);
 		if (error) {
 			xfs_force_shutdown(ip->i_mount, SHUTDOWN_META_IO_ERROR);
 			return;
diff --git a/fs/xfs/libxfs/xfs_types.c b/fs/xfs/libxfs/xfs_types.c
index b254fbeaaa50..04801362e1a7 100644
--- a/fs/xfs/libxfs/xfs_types.c
+++ b/fs/xfs/libxfs/xfs_types.c
@@ -13,7 +13,7 @@
 #include "xfs_mount.h"
 
 /* Find the size of the AG, in blocks. */
-xfs_agblock_t
+inline xfs_agblock_t
 xfs_ag_block_count(
 	struct xfs_mount	*mp,
 	xfs_agnumber_t		agno)
@@ -29,7 +29,7 @@ xfs_ag_block_count(
  * Verify that an AG block number pointer neither points outside the AG
  * nor points at static metadata.
  */
-bool
+inline bool
 xfs_verify_agbno(
 	struct xfs_mount	*mp,
 	xfs_agnumber_t		agno,
@@ -49,7 +49,7 @@ xfs_verify_agbno(
  * Verify that an FS block number pointer neither points outside the
  * filesystem nor points at static AG metadata.
  */
-bool
+inline bool
 xfs_verify_fsbno(
 	struct xfs_mount	*mp,
 	xfs_fsblock_t		fsbno)
@@ -85,7 +85,7 @@ xfs_verify_fsbext(
 }
 
 /* Calculate the first and last possible inode number in an AG. */
-void
+inline void
 xfs_agino_range(
 	struct xfs_mount	*mp,
 	xfs_agnumber_t		agno,
@@ -116,7 +116,7 @@ xfs_agino_range(
  * Verify that an AG inode number pointer neither points outside the AG
  * nor points at static metadata.
  */
-bool
+inline bool
 xfs_verify_agino(
 	struct xfs_mount	*mp,
 	xfs_agnumber_t		agno,
@@ -146,7 +146,7 @@ xfs_verify_agino_or_null(
  * Verify that an FS inode number pointer neither points outside the
  * filesystem nor points at static AG metadata.
  */
-bool
+inline bool
 xfs_verify_ino(
 	struct xfs_mount	*mp,
 	xfs_ino_t		ino)
@@ -162,7 +162,7 @@ xfs_verify_ino(
 }
 
 /* Is this an internal inode number? */
-bool
+inline bool
 xfs_internal_inum(
 	struct xfs_mount	*mp,
 	xfs_ino_t		ino)
@@ -190,7 +190,7 @@ xfs_verify_dir_ino(
  * Verify that an realtime block number pointer doesn't point off the
  * end of the realtime device.
  */
-bool
+inline bool
 xfs_verify_rtbno(
 	struct xfs_mount	*mp,
 	xfs_rtblock_t		rtbno)
@@ -215,7 +215,7 @@ xfs_verify_rtext(
 }
 
 /* Calculate the range of valid icount values. */
-void
+inline void
 xfs_icount_range(
 	struct xfs_mount	*mp,
 	unsigned long long	*min,
diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c
index ae8e2e0ac64a..749faa17f8e2 100644
--- a/fs/xfs/scrub/agheader.c
+++ b/fs/xfs/scrub/agheader.c
@@ -477,16 +477,13 @@ xchk_agf_xref(
 {
 	struct xfs_mount	*mp = sc->mp;
 	xfs_agblock_t		agbno;
-	int			error;
 
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
 
 	agbno = XFS_AGF_BLOCK(mp);
 
-	error = xchk_ag_btcur_init(sc, &sc->sa);
-	if (error)
-		return;
+	xchk_ag_btcur_init(sc, &sc->sa);
 
 	xchk_xref_is_used_space(sc, agbno, 1);
 	xchk_agf_xref_freeblks(sc);
@@ -508,7 +505,7 @@ xchk_agf(
 	struct xfs_mount	*mp = sc->mp;
 	struct xfs_agf		*agf;
 	struct xfs_perag	*pag;
-	xfs_agnumber_t		agno;
+	xfs_agnumber_t		agno = sc->sm->sm_agno;
 	xfs_agblock_t		agbno;
 	xfs_agblock_t		eoag;
 	xfs_agblock_t		agfl_first;
@@ -518,9 +515,7 @@ xchk_agf(
 	int			level;
 	int			error = 0;
 
-	agno = sc->sa.agno = sc->sm->sm_agno;
-	error = xchk_ag_read_headers(sc, agno, &sc->sa.agi_bp,
-			&sc->sa.agf_bp, &sc->sa.agfl_bp);
+	error = xchk_ag_read_headers(sc, agno, &sc->sa);
 	if (!xchk_process_error(sc, agno, XFS_AGF_BLOCK(sc->mp), &error))
 		goto out;
 	xchk_buffer_recheck(sc, sc->sa.agf_bp);
@@ -662,16 +657,13 @@ xchk_agfl_xref(
 {
 	struct xfs_mount	*mp = sc->mp;
 	xfs_agblock_t		agbno;
-	int			error;
 
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
 
 	agbno = XFS_AGFL_BLOCK(mp);
 
-	error = xchk_ag_btcur_init(sc, &sc->sa);
-	if (error)
-		return;
+	xchk_ag_btcur_init(sc, &sc->sa);
 
 	xchk_xref_is_used_space(sc, agbno, 1);
 	xchk_xref_is_not_inode_chunk(sc, agbno, 1);
@@ -691,14 +683,12 @@ xchk_agfl(
 {
 	struct xchk_agfl_info	sai;
 	struct xfs_agf		*agf;
-	xfs_agnumber_t		agno;
+	xfs_agnumber_t		agno = sc->sm->sm_agno;
 	unsigned int		agflcount;
 	unsigned int		i;
 	int			error;
 
-	agno = sc->sa.agno = sc->sm->sm_agno;
-	error = xchk_ag_read_headers(sc, agno, &sc->sa.agi_bp,
-			&sc->sa.agf_bp, &sc->sa.agfl_bp);
+	error = xchk_ag_read_headers(sc, agno, &sc->sa);
 	if (!xchk_process_error(sc, agno, XFS_AGFL_BLOCK(sc->mp), &error))
 		goto out;
 	if (!sc->sa.agf_bp)
@@ -817,16 +807,13 @@ xchk_agi_xref(
 {
 	struct xfs_mount	*mp = sc->mp;
 	xfs_agblock_t		agbno;
-	int			error;
 
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
 
 	agbno = XFS_AGI_BLOCK(mp);
 
-	error = xchk_ag_btcur_init(sc, &sc->sa);
-	if (error)
-		return;
+	xchk_ag_btcur_init(sc, &sc->sa);
 
 	xchk_xref_is_used_space(sc, agbno, 1);
 	xchk_xref_is_not_inode_chunk(sc, agbno, 1);
@@ -846,7 +833,7 @@ xchk_agi(
 	struct xfs_mount	*mp = sc->mp;
 	struct xfs_agi		*agi;
 	struct xfs_perag	*pag;
-	xfs_agnumber_t		agno;
+	xfs_agnumber_t		agno = sc->sm->sm_agno;
 	xfs_agblock_t		agbno;
 	xfs_agblock_t		eoag;
 	xfs_agino_t		agino;
@@ -857,9 +844,7 @@ xchk_agi(
 	int			level;
 	int			error = 0;
 
-	agno = sc->sa.agno = sc->sm->sm_agno;
-	error = xchk_ag_read_headers(sc, agno, &sc->sa.agi_bp,
-			&sc->sa.agf_bp, &sc->sa.agfl_bp);
+	error = xchk_ag_read_headers(sc, agno, &sc->sa);
 	if (!xchk_process_error(sc, agno, XFS_AGI_BLOCK(sc->mp), &error))
 		goto out;
 	xchk_buffer_recheck(sc, sc->sa.agi_bp);
diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c
index 73d924e47565..2720bd7fe53b 100644
--- a/fs/xfs/scrub/alloc.c
+++ b/fs/xfs/scrub/alloc.c
@@ -21,10 +21,9 @@
  */
 int
 xchk_setup_ag_allocbt(
-	struct xfs_scrub	*sc,
-	struct xfs_inode	*ip)
+	struct xfs_scrub	*sc)
 {
-	return xchk_setup_ag_btree(sc, ip, false);
+	return xchk_setup_ag_btree(sc, false);
 }
 
 /* Free space btree scrubber. */
diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c
index 9faddb334a2c..552af0cf8482 100644
--- a/fs/xfs/scrub/attr.c
+++ b/fs/xfs/scrub/attr.c
@@ -69,8 +69,7 @@ xchk_setup_xattr_buf(
 /* Set us up to scrub an inode's extended attributes. */
 int
 xchk_setup_xattr(
-	struct xfs_scrub	*sc,
-	struct xfs_inode	*ip)
+	struct xfs_scrub	*sc)
 {
 	int			error;
 
@@ -85,7 +84,7 @@ xchk_setup_xattr(
 			return error;
 	}
 
-	return xchk_setup_inode_contents(sc, ip, 0);
+	return xchk_setup_inode_contents(sc, 0);
 }
 
 /* Extended Attributes */
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index 33559c3a4bc3..b5ebf1d1b4db 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -26,12 +26,11 @@
 /* Set us up with an inode's bmap. */
 int
 xchk_setup_inode_bmap(
-	struct xfs_scrub	*sc,
-	struct xfs_inode	*ip)
+	struct xfs_scrub	*sc)
 {
 	int			error;
 
-	error = xchk_get_inode(sc, ip);
+	error = xchk_get_inode(sc);
 	if (error)
 		goto out;
 
@@ -448,12 +447,11 @@ xchk_bmap_btree(
 	int			error;
 
 	/* Load the incore bmap cache if it's not loaded. */
-	info->was_loaded = ifp->if_flags & XFS_IFEXTENTS;
-	if (!info->was_loaded) {
-		error = xfs_iread_extents(sc->tp, ip, whichfork);
-		if (!xchk_fblock_process_error(sc, whichfork, 0, &error))
-			goto out;
-	}
+	info->was_loaded = !xfs_need_iread_extents(ifp);
+
+	error = xfs_iread_extents(sc->tp, ip, whichfork);
+	if (!xchk_fblock_process_error(sc, whichfork, 0, &error))
+		goto out;
 
 	/* Check the btree structure. */
 	cur = xfs_bmbt_init_cursor(mp, sc->tp, ip, whichfork);
@@ -675,10 +673,6 @@ xchk_bmap(
 		/* No mappings to check. */
 		goto out;
 	case XFS_DINODE_FMT_EXTENTS:
-		if (!(ifp->if_flags & XFS_IFEXTENTS)) {
-			xchk_fblock_set_corrupt(sc, whichfork, 0);
-			goto out;
-		}
 		break;
 	case XFS_DINODE_FMT_BTREE:
 		if (whichfork == XFS_COW_FORK) {
diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c
index debf392e0515..a94bd8122c60 100644
--- a/fs/xfs/scrub/btree.c
+++ b/fs/xfs/scrub/btree.c
@@ -9,6 +9,7 @@
 #include "xfs_format.h"
 #include "xfs_trans_resv.h"
 #include "xfs_mount.h"
+#include "xfs_inode.h"
 #include "xfs_btree.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
@@ -442,6 +443,30 @@ xchk_btree_check_owner(
 	return xchk_btree_check_block_owner(bs, level, XFS_BUF_ADDR(bp));
 }
 
+/* Decide if we want to check minrecs of a btree block in the inode root. */
+static inline bool
+xchk_btree_check_iroot_minrecs(
+	struct xchk_btree	*bs)
+{
+	/*
+	 * xfs_bmap_add_attrfork_btree had an implementation bug wherein it
+	 * would miscalculate the space required for the data fork bmbt root
+	 * when adding an attr fork, and promote the iroot contents to an
+	 * external block unnecessarily.  This went unnoticed for many years
+	 * until scrub found filesystems in this state.  Inode rooted btrees are
+	 * not supposed to have immediate child blocks that are small enough
+	 * that the contents could fit in the inode root, but we can't fail
+	 * existing filesystems, so instead we disable the check for data fork
+	 * bmap btrees when there's an attr fork.
+	 */
+	if (bs->cur->bc_btnum == XFS_BTNUM_BMAP &&
+	    bs->cur->bc_ino.whichfork == XFS_DATA_FORK &&
+	    XFS_IFORK_Q(bs->sc->ip))
+		return false;
+
+	return true;
+}
+
 /*
  * Check that this btree block has at least minrecs records or is one of the
  * special blocks that don't require that.
@@ -475,8 +500,9 @@ xchk_btree_check_minrecs(
 
 		root_block = xfs_btree_get_block(cur, root_level, &root_bp);
 		root_maxrecs = cur->bc_ops->get_dmaxrecs(cur, root_level);
-		if (be16_to_cpu(root_block->bb_numrecs) != 1 ||
-		    numrecs <= root_maxrecs)
+		if (xchk_btree_check_iroot_minrecs(bs) &&
+		    (be16_to_cpu(root_block->bb_numrecs) != 1 ||
+		     numrecs <= root_maxrecs))
 			xchk_btree_set_corrupt(bs->sc, cur, level);
 		return;
 	}
diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index 53456f3de881..aa874607618a 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -402,22 +402,22 @@ int
 xchk_ag_read_headers(
 	struct xfs_scrub	*sc,
 	xfs_agnumber_t		agno,
-	struct xfs_buf		**agi,
-	struct xfs_buf		**agf,
-	struct xfs_buf		**agfl)
+	struct xchk_ag		*sa)
 {
 	struct xfs_mount	*mp = sc->mp;
 	int			error;
 
-	error = xfs_ialloc_read_agi(mp, sc->tp, agno, agi);
+	sa->agno = agno;
+
+	error = xfs_ialloc_read_agi(mp, sc->tp, agno, &sa->agi_bp);
 	if (error && want_ag_read_header_failure(sc, XFS_SCRUB_TYPE_AGI))
 		goto out;
 
-	error = xfs_alloc_read_agf(mp, sc->tp, agno, 0, agf);
+	error = xfs_alloc_read_agf(mp, sc->tp, agno, 0, &sa->agf_bp);
 	if (error && want_ag_read_header_failure(sc, XFS_SCRUB_TYPE_AGF))
 		goto out;
 
-	error = xfs_alloc_read_agfl(mp, sc->tp, agno, agfl);
+	error = xfs_alloc_read_agfl(mp, sc->tp, agno, &sa->agfl_bp);
 	if (error && want_ag_read_header_failure(sc, XFS_SCRUB_TYPE_AGFL))
 		goto out;
 	error = 0;
@@ -452,7 +452,7 @@ xchk_ag_btcur_free(
 }
 
 /* Initialize all the btree cursors for an AG. */
-int
+void
 xchk_ag_btcur_init(
 	struct xfs_scrub	*sc,
 	struct xchk_ag		*sa)
@@ -502,8 +502,6 @@ xchk_ag_btcur_init(
 		sa->refc_cur = xfs_refcountbt_init_cursor(mp, sc->tp,
 				sa->agf_bp, agno);
 	}
-
-	return 0;
 }
 
 /* Release the AG header context and btree cursors. */
@@ -547,13 +545,12 @@ xchk_ag_init(
 {
 	int			error;
 
-	sa->agno = agno;
-	error = xchk_ag_read_headers(sc, agno, &sa->agi_bp,
-			&sa->agf_bp, &sa->agfl_bp);
+	error = xchk_ag_read_headers(sc, agno, sa);
 	if (error)
 		return error;
 
-	return xchk_ag_btcur_init(sc, sa);
+	xchk_ag_btcur_init(sc, sa);
+	return 0;
 }
 
 /*
@@ -596,8 +593,7 @@ xchk_trans_alloc(
 /* Set us up with a transaction and an empty context. */
 int
 xchk_setup_fs(
-	struct xfs_scrub	*sc,
-	struct xfs_inode	*ip)
+	struct xfs_scrub	*sc)
 {
 	uint			resblks;
 
@@ -609,7 +605,6 @@ xchk_setup_fs(
 int
 xchk_setup_ag_btree(
 	struct xfs_scrub	*sc,
-	struct xfs_inode	*ip,
 	bool			force_log)
 {
 	struct xfs_mount	*mp = sc->mp;
@@ -627,7 +622,7 @@ xchk_setup_ag_btree(
 			return error;
 	}
 
-	error = xchk_setup_fs(sc, ip);
+	error = xchk_setup_fs(sc);
 	if (error)
 		return error;
 
@@ -655,11 +650,11 @@ xchk_checkpoint_log(
  */
 int
 xchk_get_inode(
-	struct xfs_scrub	*sc,
-	struct xfs_inode	*ip_in)
+	struct xfs_scrub	*sc)
 {
 	struct xfs_imap		imap;
 	struct xfs_mount	*mp = sc->mp;
+	struct xfs_inode	*ip_in = XFS_I(file_inode(sc->file));
 	struct xfs_inode	*ip = NULL;
 	int			error;
 
@@ -720,12 +715,11 @@ xchk_get_inode(
 int
 xchk_setup_inode_contents(
 	struct xfs_scrub	*sc,
-	struct xfs_inode	*ip,
 	unsigned int		resblks)
 {
 	int			error;
 
-	error = xchk_get_inode(sc, ip);
+	error = xchk_get_inode(sc);
 	if (error)
 		return error;
 
@@ -821,7 +815,7 @@ xchk_metadata_inode_forks(
 		return 0;
 
 	/* Metadata inodes don't live on the rt device. */
-	if (sc->ip->i_d.di_flags & XFS_DIFLAG_REALTIME) {
+	if (sc->ip->i_diflags & XFS_DIFLAG_REALTIME) {
 		xchk_ino_set_corrupt(sc, sc->ip->i_ino);
 		return 0;
 	}
diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h
index 2e50d146105d..0410faf7d735 100644
--- a/fs/xfs/scrub/common.h
+++ b/fs/xfs/scrub/common.h
@@ -72,66 +72,52 @@ bool xchk_should_check_xref(struct xfs_scrub *sc, int *error,
 			   struct xfs_btree_cur **curpp);
 
 /* Setup functions */
-int xchk_setup_fs(struct xfs_scrub *sc, struct xfs_inode *ip);
-int xchk_setup_ag_allocbt(struct xfs_scrub *sc,
-			       struct xfs_inode *ip);
-int xchk_setup_ag_iallocbt(struct xfs_scrub *sc,
-				struct xfs_inode *ip);
-int xchk_setup_ag_rmapbt(struct xfs_scrub *sc,
-			      struct xfs_inode *ip);
-int xchk_setup_ag_refcountbt(struct xfs_scrub *sc,
-				  struct xfs_inode *ip);
-int xchk_setup_inode(struct xfs_scrub *sc,
-			  struct xfs_inode *ip);
-int xchk_setup_inode_bmap(struct xfs_scrub *sc,
-			       struct xfs_inode *ip);
-int xchk_setup_inode_bmap_data(struct xfs_scrub *sc,
-				    struct xfs_inode *ip);
-int xchk_setup_directory(struct xfs_scrub *sc,
-			      struct xfs_inode *ip);
-int xchk_setup_xattr(struct xfs_scrub *sc,
-			  struct xfs_inode *ip);
-int xchk_setup_symlink(struct xfs_scrub *sc,
-			    struct xfs_inode *ip);
-int xchk_setup_parent(struct xfs_scrub *sc,
-			   struct xfs_inode *ip);
+int xchk_setup_fs(struct xfs_scrub *sc);
+int xchk_setup_ag_allocbt(struct xfs_scrub *sc);
+int xchk_setup_ag_iallocbt(struct xfs_scrub *sc);
+int xchk_setup_ag_rmapbt(struct xfs_scrub *sc);
+int xchk_setup_ag_refcountbt(struct xfs_scrub *sc);
+int xchk_setup_inode(struct xfs_scrub *sc);
+int xchk_setup_inode_bmap(struct xfs_scrub *sc);
+int xchk_setup_inode_bmap_data(struct xfs_scrub *sc);
+int xchk_setup_directory(struct xfs_scrub *sc);
+int xchk_setup_xattr(struct xfs_scrub *sc);
+int xchk_setup_symlink(struct xfs_scrub *sc);
+int xchk_setup_parent(struct xfs_scrub *sc);
 #ifdef CONFIG_XFS_RT
-int xchk_setup_rt(struct xfs_scrub *sc, struct xfs_inode *ip);
+int xchk_setup_rt(struct xfs_scrub *sc);
 #else
 static inline int
-xchk_setup_rt(struct xfs_scrub *sc, struct xfs_inode *ip)
+xchk_setup_rt(struct xfs_scrub *sc)
 {
 	return -ENOENT;
 }
 #endif
 #ifdef CONFIG_XFS_QUOTA
-int xchk_setup_quota(struct xfs_scrub *sc, struct xfs_inode *ip);
+int xchk_setup_quota(struct xfs_scrub *sc);
 #else
 static inline int
-xchk_setup_quota(struct xfs_scrub *sc, struct xfs_inode *ip)
+xchk_setup_quota(struct xfs_scrub *sc)
 {
 	return -ENOENT;
 }
 #endif
-int xchk_setup_fscounters(struct xfs_scrub *sc, struct xfs_inode *ip);
+int xchk_setup_fscounters(struct xfs_scrub *sc);
 
 void xchk_ag_free(struct xfs_scrub *sc, struct xchk_ag *sa);
 int xchk_ag_init(struct xfs_scrub *sc, xfs_agnumber_t agno,
 		struct xchk_ag *sa);
 void xchk_perag_get(struct xfs_mount *mp, struct xchk_ag *sa);
 int xchk_ag_read_headers(struct xfs_scrub *sc, xfs_agnumber_t agno,
-		struct xfs_buf **agi, struct xfs_buf **agf,
-		struct xfs_buf **agfl);
+		struct xchk_ag *sa);
 void xchk_ag_btcur_free(struct xchk_ag *sa);
-int xchk_ag_btcur_init(struct xfs_scrub *sc, struct xchk_ag *sa);
+void xchk_ag_btcur_init(struct xfs_scrub *sc, struct xchk_ag *sa);
 int xchk_count_rmap_ownedby_ag(struct xfs_scrub *sc, struct xfs_btree_cur *cur,
 		const struct xfs_owner_info *oinfo, xfs_filblks_t *blocks);
 
-int xchk_setup_ag_btree(struct xfs_scrub *sc, struct xfs_inode *ip,
-		bool force_log);
-int xchk_get_inode(struct xfs_scrub *sc, struct xfs_inode *ip_in);
-int xchk_setup_inode_contents(struct xfs_scrub *sc, struct xfs_inode *ip,
-		unsigned int resblks);
+int xchk_setup_ag_btree(struct xfs_scrub *sc, bool force_log);
+int xchk_get_inode(struct xfs_scrub *sc);
+int xchk_setup_inode_contents(struct xfs_scrub *sc, unsigned int resblks);
 void xchk_buffer_recheck(struct xfs_scrub *sc, struct xfs_buf *bp);
 
 /*
diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c
index 178b3455a170..28dda391d5df 100644
--- a/fs/xfs/scrub/dir.c
+++ b/fs/xfs/scrub/dir.c
@@ -22,10 +22,9 @@
 /* Set us up to scrub directories. */
 int
 xchk_setup_directory(
-	struct xfs_scrub	*sc,
-	struct xfs_inode	*ip)
+	struct xfs_scrub	*sc)
 {
-	return xchk_setup_inode_contents(sc, ip, 0);
+	return xchk_setup_inode_contents(sc, 0);
 }
 
 /* Directories */
@@ -538,7 +537,7 @@ xchk_directory_leaf1_bestfree(
 	 * There should be as many bestfree slots as there are dir data
 	 * blocks that can fit under i_size.
 	 */
-	if (bestcount != xfs_dir2_byte_to_db(geo, sc->ip->i_d.di_size)) {
+	if (bestcount != xfs_dir2_byte_to_db(geo, sc->ip->i_disk_size)) {
 		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 		goto out;
 	}
@@ -694,15 +693,6 @@ xchk_directory_blocks(
 	/* Iterate all the data extents in the directory... */
 	found = xfs_iext_lookup_extent(sc->ip, ifp, lblk, &icur, &got);
 	while (found && !(sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) {
-		/* Block directories only have a single block at offset 0. */
-		if (is_block &&
-		    (got.br_startoff > 0 ||
-		     got.br_blockcount != args.geo->fsbcount)) {
-			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK,
-					got.br_startoff);
-			break;
-		}
-
 		/* No more data blocks... */
 		if (got.br_startoff >= leaf_lblk)
 			break;
@@ -817,7 +807,7 @@ xchk_directory(
 		return -ENOENT;
 
 	/* Plausible size? */
-	if (sc->ip->i_d.di_size < xfs_dir2_sf_hdr_size(0)) {
+	if (sc->ip->i_disk_size < xfs_dir2_sf_hdr_size(0)) {
 		xchk_ino_set_corrupt(sc, sc->ip->i_ino);
 		goto out;
 	}
@@ -843,7 +833,7 @@ xchk_directory(
 	 * Userspace usually asks for a 32k buffer, so we will too.
 	 */
 	bufsize = (size_t)min_t(loff_t, XFS_READDIR_BUFSIZE,
-			sc->ip->i_d.di_size);
+			sc->ip->i_disk_size);
 
 	/*
 	 * Look up every name in this directory by hash.
diff --git a/fs/xfs/scrub/fscounters.c b/fs/xfs/scrub/fscounters.c
index ec2064ed3c30..7b4386c78fbf 100644
--- a/fs/xfs/scrub/fscounters.c
+++ b/fs/xfs/scrub/fscounters.c
@@ -116,8 +116,7 @@ next_loop_perag:
 
 int
 xchk_setup_fscounters(
-	struct xfs_scrub	*sc,
-	struct xfs_inode	*ip)
+	struct xfs_scrub	*sc)
 {
 	struct xchk_fscounters	*fsc;
 	int			error;
diff --git a/fs/xfs/scrub/health.c b/fs/xfs/scrub/health.c
index 83d27cdf579b..3de59b5c2ce6 100644
--- a/fs/xfs/scrub/health.c
+++ b/fs/xfs/scrub/health.c
@@ -133,7 +133,8 @@ xchk_update_health(
 	if (!sc->sick_mask)
 		return;
 
-	bad = (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT);
+	bad = (sc->sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT |
+				   XFS_SCRUB_OFLAG_XCORRUPT));
 	switch (type_to_health_flag[sc->sm->sm_type].group) {
 	case XHG_AG:
 		pag = xfs_perag_get(sc->mp, sc->sm->sm_agno);
diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c
index 6517d67e8d51..8d9f3fb0cd22 100644
--- a/fs/xfs/scrub/ialloc.c
+++ b/fs/xfs/scrub/ialloc.c
@@ -29,10 +29,9 @@
  */
 int
 xchk_setup_ag_iallocbt(
-	struct xfs_scrub	*sc,
-	struct xfs_inode	*ip)
+	struct xfs_scrub	*sc)
 {
-	return xchk_setup_ag_btree(sc, ip, sc->flags & XCHK_TRY_HARDER);
+	return xchk_setup_ag_btree(sc, sc->flags & XCHK_TRY_HARDER);
 }
 
 /* Inode btree scrubber. */
@@ -212,7 +211,6 @@ xchk_iallocbt_check_cluster(
 {
 	struct xfs_imap			imap;
 	struct xfs_mount		*mp = bs->cur->bc_mp;
-	struct xfs_dinode		*dip;
 	struct xfs_buf			*cluster_bp;
 	unsigned int			nr_inodes;
 	xfs_agnumber_t			agno = bs->cur->bc_ag.agno;
@@ -278,7 +276,7 @@ xchk_iallocbt_check_cluster(
 			&XFS_RMAP_OINFO_INODES);
 
 	/* Grab the inode cluster buffer. */
-	error = xfs_imap_to_bp(mp, bs->cur->bc_tp, &imap, &dip, &cluster_bp, 0);
+	error = xfs_imap_to_bp(mp, bs->cur->bc_tp, &imap, &cluster_bp);
 	if (!xchk_btree_xref_process_error(bs->sc, bs->cur, 0, &error))
 		return error;
 
diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index faf65eb5bd31..61f90b2c9430 100644
--- a/fs/xfs/scrub/inode.c
+++ b/fs/xfs/scrub/inode.c
@@ -28,8 +28,7 @@
  */
 int
 xchk_setup_inode(
-	struct xfs_scrub	*sc,
-	struct xfs_inode	*ip)
+	struct xfs_scrub	*sc)
 {
 	int			error;
 
@@ -37,7 +36,7 @@ xchk_setup_inode(
 	 * Try to get the inode.  If the verifiers fail, we try again
 	 * in raw mode.
 	 */
-	error = xchk_get_inode(sc, ip);
+	error = xchk_get_inode(sc);
 	switch (error) {
 	case 0:
 		break;
diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c
index 66c35f6dfc24..ab182a5cd0c0 100644
--- a/fs/xfs/scrub/parent.c
+++ b/fs/xfs/scrub/parent.c
@@ -20,10 +20,9 @@
 /* Set us up to scrub parents. */
 int
 xchk_setup_parent(
-	struct xfs_scrub	*sc,
-	struct xfs_inode	*ip)
+	struct xfs_scrub	*sc)
 {
-	return xchk_setup_inode_contents(sc, ip, 0);
+	return xchk_setup_inode_contents(sc, 0);
 }
 
 /* Parent pointers */
@@ -102,7 +101,7 @@ xchk_parent_count_parent_dentries(
 	 * scanned.
 	 */
 	bufsize = (size_t)min_t(loff_t, XFS_READDIR_BUFSIZE,
-			parent->i_d.di_size);
+			parent->i_disk_size);
 	oldpos = 0;
 	while (true) {
 		error = xfs_readdir(sc->tp, parent, &spc.dc, bufsize);
diff --git a/fs/xfs/scrub/quota.c b/fs/xfs/scrub/quota.c
index e34ca20ae8e4..acbb9839d42f 100644
--- a/fs/xfs/scrub/quota.c
+++ b/fs/xfs/scrub/quota.c
@@ -37,8 +37,7 @@ xchk_quota_to_dqtype(
 /* Set us up to scrub a quota. */
 int
 xchk_setup_quota(
-	struct xfs_scrub	*sc,
-	struct xfs_inode	*ip)
+	struct xfs_scrub	*sc)
 {
 	xfs_dqtype_t		dqtype;
 	int			error;
@@ -53,7 +52,7 @@ xchk_setup_quota(
 	mutex_lock(&sc->mp->m_quotainfo->qi_quotaofflock);
 	if (!xfs_this_quota_on(sc->mp, dqtype))
 		return -ENOENT;
-	error = xchk_setup_fs(sc, ip);
+	error = xchk_setup_fs(sc);
 	if (error)
 		return error;
 	sc->ip = xfs_quota_inode(sc->mp, dqtype);
@@ -85,7 +84,7 @@ xchk_quota_item(
 	int			error = 0;
 
 	if (xchk_should_terminate(sc, &error))
-		return error;
+		return -ECANCELED;
 
 	/*
 	 * Except for the root dquot, the actual dquot we got must either have
@@ -162,7 +161,7 @@ xchk_quota_item(
 
 out:
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
-		return -EFSCORRUPTED;
+		return -ECANCELED;
 
 	return 0;
 }
@@ -238,6 +237,8 @@ xchk_quota(
 	error = xfs_qm_dqiterate(mp, dqtype, xchk_quota_item, &sqi);
 	sc->ilock_flags = XFS_ILOCK_EXCL;
 	xfs_ilock(sc->ip, sc->ilock_flags);
+	if (error == -ECANCELED)
+		error = 0;
 	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK,
 			sqi.last_id * qi->qi_dqperchunk, &error))
 		goto out;
diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c
index dd672e6bbc75..744530a66c0c 100644
--- a/fs/xfs/scrub/refcount.c
+++ b/fs/xfs/scrub/refcount.c
@@ -19,10 +19,9 @@
  */
 int
 xchk_setup_ag_refcountbt(
-	struct xfs_scrub	*sc,
-	struct xfs_inode	*ip)
+	struct xfs_scrub	*sc)
 {
-	return xchk_setup_ag_btree(sc, ip, false);
+	return xchk_setup_ag_btree(sc, false);
 }
 
 /* Reference count btree scrubber. */
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 25e86c71e7b9..c2857d854c83 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -37,19 +37,18 @@
  */
 int
 xrep_attempt(
-	struct xfs_inode	*ip,
 	struct xfs_scrub	*sc)
 {
 	int			error = 0;
 
-	trace_xrep_attempt(ip, sc->sm, error);
+	trace_xrep_attempt(XFS_I(file_inode(sc->file)), sc->sm, error);
 
 	xchk_ag_btcur_free(&sc->sa);
 
 	/* Repair whatever's broken. */
 	ASSERT(sc->ops->repair);
 	error = sc->ops->repair(sc);
-	trace_xrep_done(ip, sc->sm, error);
+	trace_xrep_done(XFS_I(file_inode(sc->file)), sc->sm, error);
 	switch (error) {
 	case 0:
 		/*
@@ -207,7 +206,11 @@ xrep_calc_ag_resblks(
 
 	/* Now grab the block counters from the AGF. */
 	error = xfs_alloc_read_agf(mp, NULL, sm->sm_agno, 0, &bp);
-	if (!error) {
+	if (error) {
+		aglen = xfs_ag_block_count(mp, sm->sm_agno);
+		freelen = aglen;
+		usedlen = aglen;
+	} else {
 		struct xfs_agf	*agf = bp->b_addr;
 
 		aglen = be32_to_cpu(agf->agf_length);
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index fe77de01abe0..3bb152d52a07 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -17,7 +17,7 @@ static inline int xrep_notsupported(struct xfs_scrub *sc)
 
 /* Repair helpers */
 
-int xrep_attempt(struct xfs_inode *ip, struct xfs_scrub *sc);
+int xrep_attempt(struct xfs_scrub *sc);
 void xrep_failure(struct xfs_mount *mp);
 int xrep_roll_ag_trans(struct xfs_scrub *sc);
 bool xrep_ag_has_space(struct xfs_perag *pag, xfs_extlen_t nr_blocks,
@@ -64,8 +64,8 @@ int xrep_agi(struct xfs_scrub *sc);
 
 #else
 
-static inline int xrep_attempt(
-	struct xfs_inode	*ip,
+static inline int
+xrep_attempt(
 	struct xfs_scrub	*sc)
 {
 	return -EOPNOTSUPP;
diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c
index f4fcb4719f41..a4f17477c5d1 100644
--- a/fs/xfs/scrub/rmap.c
+++ b/fs/xfs/scrub/rmap.c
@@ -21,10 +21,9 @@
  */
 int
 xchk_setup_ag_rmapbt(
-	struct xfs_scrub	*sc,
-	struct xfs_inode	*ip)
+	struct xfs_scrub	*sc)
 {
-	return xchk_setup_ag_btree(sc, ip, false);
+	return xchk_setup_ag_btree(sc, false);
 }
 
 /* Reverse-mapping scrubber. */
diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c
index d409ca592178..37c0e2266c85 100644
--- a/fs/xfs/scrub/rtbitmap.c
+++ b/fs/xfs/scrub/rtbitmap.c
@@ -20,12 +20,11 @@
 /* Set us up with the realtime metadata locked. */
 int
 xchk_setup_rt(
-	struct xfs_scrub	*sc,
-	struct xfs_inode	*ip)
+	struct xfs_scrub	*sc)
 {
 	int			error;
 
-	error = xchk_setup_fs(sc, ip);
+	error = xchk_setup_fs(sc);
 	if (error)
 		return error;
 
@@ -100,7 +99,7 @@ xchk_rtbitmap(
 	int			error;
 
 	/* Is the size of the rtbitmap correct? */
-	if (sc->mp->m_rbmip->i_d.di_size !=
+	if (sc->mp->m_rbmip->i_disk_size !=
 	    XFS_FSB_TO_B(sc->mp, sc->mp->m_sb.sb_rbmblocks)) {
 		xchk_ino_set_corrupt(sc, sc->mp->m_rbmip->i_ino);
 		return 0;
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 8ebf35b115ce..0e542636227c 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -149,9 +149,10 @@ xchk_probe(
 STATIC int
 xchk_teardown(
 	struct xfs_scrub	*sc,
-	struct xfs_inode	*ip_in,
 	int			error)
 {
+	struct xfs_inode	*ip_in = XFS_I(file_inode(sc->file));
+
 	xchk_ag_free(sc, &sc->sa);
 	if (sc->tp) {
 		if (error == 0 && (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR))
@@ -168,7 +169,8 @@ xchk_teardown(
 			xfs_irele(sc->ip);
 		sc->ip = NULL;
 	}
-	sb_end_write(sc->mp->m_super);
+	if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR)
+		mnt_drop_write_file(sc->file);
 	if (sc->flags & XCHK_REAPING_DISABLED)
 		xchk_start_reaping(sc);
 	if (sc->flags & XCHK_HAS_QUOTAOFFLOCK) {
@@ -456,23 +458,25 @@ static inline void xchk_postmortem(struct xfs_scrub *sc)
 /* Dispatch metadata scrubbing. */
 int
 xfs_scrub_metadata(
-	struct xfs_inode		*ip,
+	struct file			*file,
 	struct xfs_scrub_metadata	*sm)
 {
 	struct xfs_scrub		sc = {
-		.mp			= ip->i_mount,
+		.file			= file,
 		.sm			= sm,
 		.sa			= {
 			.agno		= NULLAGNUMBER,
 		},
 	};
-	struct xfs_mount		*mp = ip->i_mount;
+	struct xfs_mount		*mp = XFS_I(file_inode(file))->i_mount;
 	int				error = 0;
 
+	sc.mp = mp;
+
 	BUILD_BUG_ON(sizeof(meta_scrub_ops) !=
 		(sizeof(struct xchk_meta_ops) * XFS_SCRUB_TYPE_NR));
 
-	trace_xchk_start(ip, sm, error);
+	trace_xchk_start(XFS_I(file_inode(file)), sm, error);
 
 	/* Forbidden if we are shut down or mounted norecovery. */
 	error = -ESHUTDOWN;
@@ -492,15 +496,17 @@ xfs_scrub_metadata(
 	sc.sick_mask = xchk_health_mask_for_scrub_type(sm->sm_type);
 retry_op:
 	/*
-	 * If freeze runs concurrently with a scrub, the freeze can be delayed
-	 * indefinitely as we walk the filesystem and iterate over metadata
-	 * buffers.  Freeze quiesces the log (which waits for the buffer LRU to
-	 * be emptied) and that won't happen while checking is running.
+	 * When repairs are allowed, prevent freezing or readonly remount while
+	 * scrub is running with a real transaction.
 	 */
-	sb_start_write(mp->m_super);
+	if (sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) {
+		error = mnt_want_write_file(sc.file);
+		if (error)
+			goto out;
+	}
 
 	/* Set up for the operation. */
-	error = sc.ops->setup(&sc, ip);
+	error = sc.ops->setup(&sc);
 	if (error)
 		goto out_teardown;
 
@@ -512,12 +518,12 @@ retry_op:
 		 * Tear down everything we hold, then set up again with
 		 * preparation for worst-case scenarios.
 		 */
-		error = xchk_teardown(&sc, ip, 0);
+		error = xchk_teardown(&sc, 0);
 		if (error)
 			goto out;
 		sc.flags |= XCHK_TRY_HARDER;
 		goto retry_op;
-	} else if (error)
+	} else if (error || (sm->sm_flags & XFS_SCRUB_OFLAG_INCOMPLETE))
 		goto out_teardown;
 
 	xchk_update_health(&sc);
@@ -546,14 +552,14 @@ retry_op:
 		 * If it's broken, userspace wants us to fix it, and we haven't
 		 * already tried to fix it, then attempt a repair.
 		 */
-		error = xrep_attempt(ip, &sc);
+		error = xrep_attempt(&sc);
 		if (error == -EAGAIN) {
 			/*
 			 * Either the repair function succeeded or it couldn't
 			 * get all the resources it needs; either way, we go
 			 * back to the beginning and call the scrub function.
 			 */
-			error = xchk_teardown(&sc, ip, 0);
+			error = xchk_teardown(&sc, 0);
 			if (error) {
 				xrep_failure(mp);
 				goto out;
@@ -565,9 +571,9 @@ retry_op:
 out_nofix:
 	xchk_postmortem(&sc);
 out_teardown:
-	error = xchk_teardown(&sc, ip, error);
+	error = xchk_teardown(&sc, error);
 out:
-	trace_xchk_done(ip, sm, error);
+	trace_xchk_done(XFS_I(file_inode(file)), sm, error);
 	if (error == -EFSCORRUPTED || error == -EFSBADCRC) {
 		sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
 		error = 0;
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index ad1ceb44a628..08a483cb46e2 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -18,8 +18,7 @@ enum xchk_type {
 
 struct xchk_meta_ops {
 	/* Acquire whatever resources are needed for the operation. */
-	int		(*setup)(struct xfs_scrub *,
-				 struct xfs_inode *);
+	int		(*setup)(struct xfs_scrub *sc);
 
 	/* Examine metadata for errors. */
 	int		(*scrub)(struct xfs_scrub *);
@@ -59,7 +58,18 @@ struct xfs_scrub {
 	struct xfs_scrub_metadata	*sm;
 	const struct xchk_meta_ops	*ops;
 	struct xfs_trans		*tp;
+
+	/* File that scrub was called with. */
+	struct file			*file;
+
+	/*
+	 * File that is undergoing the scrub operation.  This can differ from
+	 * the file that scrub was called with if we're checking file-based fs
+	 * metadata (e.g. rt bitmaps) or if we're doing a scrub-by-handle for
+	 * something that can't be opened directly (e.g. symlinks).
+	 */
 	struct xfs_inode		*ip;
+
 	void				*buf;
 	uint				ilock_flags;
 
diff --git a/fs/xfs/scrub/symlink.c b/fs/xfs/scrub/symlink.c
index c08be5ede066..599ee277bba2 100644
--- a/fs/xfs/scrub/symlink.c
+++ b/fs/xfs/scrub/symlink.c
@@ -18,15 +18,14 @@
 /* Set us up to scrub a symbolic link. */
 int
 xchk_setup_symlink(
-	struct xfs_scrub	*sc,
-	struct xfs_inode	*ip)
+	struct xfs_scrub	*sc)
 {
 	/* Allocate the buffer without the inode lock held. */
 	sc->buf = kvzalloc(XFS_SYMLINK_MAXLEN + 1, GFP_KERNEL);
 	if (!sc->buf)
 		return -ENOMEM;
 
-	return xchk_setup_inode_contents(sc, ip, 0);
+	return xchk_setup_inode_contents(sc, 0);
 }
 
 /* Symbolic links. */
@@ -43,7 +42,7 @@ xchk_symlink(
 	if (!S_ISLNK(VFS_I(ip)->i_mode))
 		return -ENOENT;
 	ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
-	len = ip->i_d.di_size;
+	len = ip->i_disk_size;
 
 	/* Plausible size? */
 	if (len > XFS_SYMLINK_MAXLEN || len <= 0) {
@@ -52,7 +51,7 @@ xchk_symlink(
 	}
 
 	/* Inline symlink? */
-	if (ifp->if_flags & XFS_IFINLINE) {
+	if (ifp->if_format == XFS_DINODE_FMT_LOCAL) {
 		if (len > XFS_IFORK_DSIZE(ip) ||
 		    len > strnlen(ifp->if_u1.if_data, XFS_IFORK_DSIZE(ip)))
 			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
diff --git a/fs/xfs/scrub/xfs_scrub.h b/fs/xfs/scrub/xfs_scrub.h
index 2897ba3a17e6..2ceae614ade8 100644
--- a/fs/xfs/scrub/xfs_scrub.h
+++ b/fs/xfs/scrub/xfs_scrub.h
@@ -7,9 +7,9 @@
 #define __XFS_SCRUB_H__
 
 #ifndef CONFIG_XFS_ONLINE_SCRUB
-# define xfs_scrub_metadata(ip, sm)	(-ENOTTY)
+# define xfs_scrub_metadata(file, sm)	(-ENOTTY)
 #else
-int xfs_scrub_metadata(struct xfs_inode *ip, struct xfs_scrub_metadata *sm);
+int xfs_scrub_metadata(struct file *file, struct xfs_scrub_metadata *sm);
 #endif /* CONFIG_XFS_ONLINE_SCRUB */
 
 #endif	/* __XFS_SCRUB_H__ */
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index b4186d666157..9b08db45ce85 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -36,47 +36,26 @@ XFS_WPC(struct iomap_writepage_ctx *ctx)
 static inline bool xfs_ioend_is_append(struct iomap_ioend *ioend)
 {
 	return ioend->io_offset + ioend->io_size >
-		XFS_I(ioend->io_inode)->i_d.di_size;
-}
-
-STATIC int
-xfs_setfilesize_trans_alloc(
-	struct iomap_ioend	*ioend)
-{
-	struct xfs_mount	*mp = XFS_I(ioend->io_inode)->i_mount;
-	struct xfs_trans	*tp;
-	int			error;
-
-	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_fsyncts, 0, 0, 0, &tp);
-	if (error)
-		return error;
-
-	ioend->io_private = tp;
-
-	/*
-	 * We may pass freeze protection with a transaction.  So tell lockdep
-	 * we released it.
-	 */
-	__sb_writers_release(ioend->io_inode->i_sb, SB_FREEZE_FS);
-	/*
-	 * We hand off the transaction to the completion thread now, so
-	 * clear the flag here.
-	 */
-	xfs_trans_clear_context(tp);
-	return 0;
+		XFS_I(ioend->io_inode)->i_disk_size;
 }
 
 /*
  * Update on-disk file size now that data has been written to disk.
  */
-STATIC int
-__xfs_setfilesize(
+int
+xfs_setfilesize(
 	struct xfs_inode	*ip,
-	struct xfs_trans	*tp,
 	xfs_off_t		offset,
 	size_t			size)
 {
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_trans	*tp;
 	xfs_fsize_t		isize;
+	int			error;
+
+	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_fsyncts, 0, 0, 0, &tp);
+	if (error)
+		return error;
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	isize = xfs_new_eof(ip, offset + size);
@@ -88,55 +67,13 @@ __xfs_setfilesize(
 
 	trace_xfs_setfilesize(ip, offset, size);
 
-	ip->i_d.di_size = isize;
+	ip->i_disk_size = isize;
 	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
 	return xfs_trans_commit(tp);
 }
 
-int
-xfs_setfilesize(
-	struct xfs_inode	*ip,
-	xfs_off_t		offset,
-	size_t			size)
-{
-	struct xfs_mount	*mp = ip->i_mount;
-	struct xfs_trans	*tp;
-	int			error;
-
-	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_fsyncts, 0, 0, 0, &tp);
-	if (error)
-		return error;
-
-	return __xfs_setfilesize(ip, tp, offset, size);
-}
-
-STATIC int
-xfs_setfilesize_ioend(
-	struct iomap_ioend	*ioend,
-	int			error)
-{
-	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
-	struct xfs_trans	*tp = ioend->io_private;
-
-	/*
-	 * The transaction may have been allocated in the I/O submission thread,
-	 * thus we need to mark ourselves as being in a transaction manually.
-	 * Similarly for freeze protection.
-	 */
-	xfs_trans_set_context(tp);
-	__sb_writers_acquired(VFS_I(ip)->i_sb, SB_FREEZE_FS);
-
-	/* we abort the update if there was an IO error */
-	if (error) {
-		xfs_trans_cancel(tp);
-		return error;
-	}
-
-	return __xfs_setfilesize(ip, tp, ioend->io_offset, ioend->io_size);
-}
-
 /*
  * IO write completion.
  */
@@ -158,7 +95,7 @@ xfs_end_ioend(
 	nofs_flag = memalloc_nofs_save();
 
 	/*
-	 * Just clean up the in-memory strutures if the fs has been shut down.
+	 * Just clean up the in-memory structures if the fs has been shut down.
 	 */
 	if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
 		error = -EIO;
@@ -182,35 +119,14 @@ xfs_end_ioend(
 		error = xfs_reflink_end_cow(ip, offset, size);
 	else if (ioend->io_type == IOMAP_UNWRITTEN)
 		error = xfs_iomap_write_unwritten(ip, offset, size, false);
-	else
-		ASSERT(!xfs_ioend_is_append(ioend) || ioend->io_private);
 
+	if (!error && xfs_ioend_is_append(ioend))
+		error = xfs_setfilesize(ip, ioend->io_offset, ioend->io_size);
 done:
-	if (ioend->io_private)
-		error = xfs_setfilesize_ioend(ioend, error);
 	iomap_finish_ioends(ioend, error);
 	memalloc_nofs_restore(nofs_flag);
 }
 
-/*
- * If the to be merged ioend has a preallocated transaction for file
- * size updates we need to ensure the ioend it is merged into also
- * has one.  If it already has one we can simply cancel the transaction
- * as it is guaranteed to be clean.
- */
-static void
-xfs_ioend_merge_private(
-	struct iomap_ioend	*ioend,
-	struct iomap_ioend	*next)
-{
-	if (!ioend->io_private) {
-		ioend->io_private = next->io_private;
-		next->io_private = NULL;
-	} else {
-		xfs_setfilesize_ioend(next, -ECANCELED);
-	}
-}
-
 /* Finish all pending io completions. */
 void
 xfs_end_io(
@@ -230,18 +146,11 @@ xfs_end_io(
 	while ((ioend = list_first_entry_or_null(&tmp, struct iomap_ioend,
 			io_list))) {
 		list_del_init(&ioend->io_list);
-		iomap_ioend_try_merge(ioend, &tmp, xfs_ioend_merge_private);
+		iomap_ioend_try_merge(ioend, &tmp, NULL);
 		xfs_end_ioend(ioend);
 	}
 }
 
-static inline bool xfs_ioend_needs_workqueue(struct iomap_ioend *ioend)
-{
-	return ioend->io_private ||
-		ioend->io_type == IOMAP_UNWRITTEN ||
-		(ioend->io_flags & IOMAP_F_SHARED);
-}
-
 STATIC void
 xfs_end_bio(
 	struct bio		*bio)
@@ -250,8 +159,6 @@ xfs_end_bio(
 	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
 	unsigned long		flags;
 
-	ASSERT(xfs_ioend_needs_workqueue(ioend));
-
 	spin_lock_irqsave(&ip->i_ioend_lock, flags);
 	if (list_empty(&ip->i_ioend_list))
 		WARN_ON_ONCE(!queue_work(ip->i_mount->m_unwritten_workqueue,
@@ -384,8 +291,7 @@ retry:
 	cow_fsb = NULLFILEOFF;
 	whichfork = XFS_DATA_FORK;
 	xfs_ilock(ip, XFS_ILOCK_SHARED);
-	ASSERT(ip->i_df.if_format != XFS_DINODE_FMT_BTREE ||
-	       (ip->i_df.if_flags & XFS_IFEXTENTS));
+	ASSERT(!xfs_need_iread_extents(&ip->i_df));
 
 	/*
 	 * Check if this is offset is covered by a COW extents, and if yes use
@@ -501,17 +407,11 @@ xfs_prepare_ioend(
 				ioend->io_offset, ioend->io_size);
 	}
 
-	/* Reserve log space if we might write beyond the on-disk inode size. */
-	if (!status &&
-	    ((ioend->io_flags & IOMAP_F_SHARED) ||
-	     ioend->io_type != IOMAP_UNWRITTEN) &&
-	    xfs_ioend_is_append(ioend) &&
-	    !ioend->io_private)
-		status = xfs_setfilesize_trans_alloc(ioend);
-
 	memalloc_nofs_restore(nofs_flag);
 
-	if (xfs_ioend_needs_workqueue(ioend))
+	/* send ioends that might require a transaction to the completion wq */
+	if (xfs_ioend_is_append(ioend) || ioend->io_type == IOMAP_UNWRITTEN ||
+	    (ioend->io_flags & IOMAP_F_SHARED))
 		ioend->io_bio->bi_end_io = xfs_end_bio;
 	return status;
 }
diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c
index 8f8837fe21cf..25dcc98d50e6 100644
--- a/fs/xfs/xfs_attr_list.c
+++ b/fs/xfs/xfs_attr_list.c
@@ -514,7 +514,7 @@ xfs_attr_list_ilocked(
 		return 0;
 	if (dp->i_afp->if_format == XFS_DINODE_FMT_LOCAL)
 		return xfs_attr_shortform_list(context);
-	if (xfs_bmap_one_block(dp, XFS_ATTR_FORK))
+	if (xfs_attr_is_leaf(dp))
 		return xfs_attr_leaf_list(context);
 	return xfs_attr_node_list(context);
 }
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index e7d68318e6a5..a5e9d7d34023 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -154,7 +154,7 @@ xfs_bmap_rtalloc(
 		ap->blkno *= mp->m_sb.sb_rextsize;
 		ralen *= mp->m_sb.sb_rextsize;
 		ap->length = ralen;
-		ap->ip->i_d.di_nblocks += ralen;
+		ap->ip->i_nblocks += ralen;
 		xfs_trans_log_inode(ap->tp, ap->ip, XFS_ILOG_CORE);
 		if (ap->wasdel)
 			ap->ip->i_delayed_blks -= ralen;
@@ -225,11 +225,9 @@ xfs_bmap_count_blocks(
 
 	switch (ifp->if_format) {
 	case XFS_DINODE_FMT_BTREE:
-		if (!(ifp->if_flags & XFS_IFEXTENTS)) {
-			error = xfs_iread_extents(tp, ip, whichfork);
-			if (error)
-				return error;
-		}
+		error = xfs_iread_extents(tp, ip, whichfork);
+		if (error)
+			return error;
 
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
 		error = xfs_btree_count_blocks(cur, &btblocks);
@@ -423,7 +421,7 @@ xfs_getbmap(
 		break;
 	case XFS_DATA_FORK:
 		if (!(iflags & BMV_IF_DELALLOC) &&
-		    (ip->i_delayed_blks || XFS_ISIZE(ip) > ip->i_d.di_size)) {
+		    (ip->i_delayed_blks || XFS_ISIZE(ip) > ip->i_disk_size)) {
 			error = filemap_write_and_wait(VFS_I(ip)->i_mapping);
 			if (error)
 				goto out_unlock_iolock;
@@ -439,7 +437,7 @@ xfs_getbmap(
 		}
 
 		if (xfs_get_extsz_hint(ip) ||
-		    (ip->i_d.di_flags &
+		    (ip->i_diflags &
 		     (XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND)))
 			max_len = mp->m_super->s_maxbytes;
 		else
@@ -471,11 +469,9 @@ xfs_getbmap(
 	first_bno = bno = XFS_BB_TO_FSBT(mp, bmv->bmv_offset);
 	len = XFS_BB_TO_FSB(mp, bmv->bmv_length);
 
-	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
-		error = xfs_iread_extents(NULL, ip, whichfork);
-		if (error)
-			goto out_unlock_ilock;
-	}
+	error = xfs_iread_extents(NULL, ip, whichfork);
+	if (error)
+		goto out_unlock_ilock;
 
 	if (!xfs_iext_lookup_extent(ip, ifp, bno, &icur, &got)) {
 		/*
@@ -558,7 +554,7 @@ xfs_bmap_punch_delalloc_range(
 	struct xfs_iext_cursor	icur;
 	int			error = 0;
 
-	ASSERT(ifp->if_flags & XFS_IFEXTENTS);
+	ASSERT(!xfs_need_iread_extents(ifp));
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	if (!xfs_iext_lookup_extent_before(ip, ifp, &end_fsb, &icur, &got))
@@ -597,8 +593,24 @@ out_unlock:
  * regular files that are marked preallocated or append-only.
  */
 bool
-xfs_can_free_eofblocks(struct xfs_inode *ip, bool force)
+xfs_can_free_eofblocks(
+	struct xfs_inode	*ip,
+	bool			force)
 {
+	struct xfs_bmbt_irec	imap;
+	struct xfs_mount	*mp = ip->i_mount;
+	xfs_fileoff_t		end_fsb;
+	xfs_fileoff_t		last_fsb;
+	int			nimaps = 1;
+	int			error;
+
+	/*
+	 * Caller must either hold the exclusive io lock; or be inactivating
+	 * the inode, which guarantees there are no other users of the inode.
+	 */
+	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL) ||
+	       (VFS_I(ip)->i_state & I_FREEING));
+
 	/* prealloc/delalloc exists only on regular files */
 	if (!S_ISREG(VFS_I(ip)->i_mode))
 		return false;
@@ -613,18 +625,43 @@ xfs_can_free_eofblocks(struct xfs_inode *ip, bool force)
 		return false;
 
 	/* If we haven't read in the extent list, then don't do it now. */
-	if (!(ip->i_df.if_flags & XFS_IFEXTENTS))
+	if (xfs_need_iread_extents(&ip->i_df))
 		return false;
 
 	/*
 	 * Do not free real preallocated or append-only files unless the file
 	 * has delalloc blocks and we are forced to remove them.
 	 */
-	if (ip->i_d.di_flags & (XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND))
+	if (ip->i_diflags & (XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND))
 		if (!force || ip->i_delayed_blks == 0)
 			return false;
 
-	return true;
+	/*
+	 * Do not try to free post-EOF blocks if EOF is beyond the end of the
+	 * range supported by the page cache, because the truncation will loop
+	 * forever.
+	 */
+	end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_ISIZE(ip));
+	last_fsb = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
+	if (last_fsb <= end_fsb)
+		return false;
+
+	/*
+	 * Look up the mapping for the first block past EOF.  If we can't find
+	 * it, there's nothing to free.
+	 */
+	xfs_ilock(ip, XFS_ILOCK_SHARED);
+	error = xfs_bmapi_read(ip, end_fsb, last_fsb - end_fsb, &imap, &nimaps,
+			0);
+	xfs_iunlock(ip, XFS_ILOCK_SHARED);
+	if (error || nimaps == 0)
+		return false;
+
+	/*
+	 * If there's a real mapping there or there are delayed allocation
+	 * reservations, then we have post-EOF blocks to try to free.
+	 */
+	return imap.br_startblock != HOLESTARTBLOCK || ip->i_delayed_blks;
 }
 
 /*
@@ -637,78 +674,52 @@ xfs_free_eofblocks(
 	struct xfs_inode	*ip)
 {
 	struct xfs_trans	*tp;
-	int			error;
-	xfs_fileoff_t		end_fsb;
-	xfs_fileoff_t		last_fsb;
-	xfs_filblks_t		map_len;
-	int			nimaps;
-	struct xfs_bmbt_irec	imap;
 	struct xfs_mount	*mp = ip->i_mount;
+	int			error;
 
-	/*
-	 * Figure out if there are any blocks beyond the end
-	 * of the file.  If not, then there is nothing to do.
-	 */
-	end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_ISIZE(ip));
-	last_fsb = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
-	if (last_fsb <= end_fsb)
-		return 0;
-	map_len = last_fsb - end_fsb;
+	/* Attach the dquots to the inode up front. */
+	error = xfs_qm_dqattach(ip);
+	if (error)
+		return error;
 
-	nimaps = 1;
-	xfs_ilock(ip, XFS_ILOCK_SHARED);
-	error = xfs_bmapi_read(ip, end_fsb, map_len, &imap, &nimaps, 0);
-	xfs_iunlock(ip, XFS_ILOCK_SHARED);
+	/* Wait on dio to ensure i_size has settled. */
+	inode_dio_wait(VFS_I(ip));
 
-	/*
-	 * If there are blocks after the end of file, truncate the file to its
-	 * current size to free them up.
-	 */
-	if (!error && (nimaps != 0) &&
-	    (imap.br_startblock != HOLESTARTBLOCK ||
-	     ip->i_delayed_blks)) {
-		/*
-		 * Attach the dquots to the inode up front.
-		 */
-		error = xfs_qm_dqattach(ip);
-		if (error)
-			return error;
+	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
+	if (error) {
+		ASSERT(XFS_FORCED_SHUTDOWN(mp));
+		return error;
+	}
 
-		/* wait on dio to ensure i_size has settled */
-		inode_dio_wait(VFS_I(ip));
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(tp, ip, 0);
 
-		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0,
-				&tp);
-		if (error) {
-			ASSERT(XFS_FORCED_SHUTDOWN(mp));
-			return error;
-		}
+	/*
+	 * Do not update the on-disk file size.  If we update the on-disk file
+	 * size and then the system crashes before the contents of the file are
+	 * flushed to disk then the files may be full of holes (ie NULL files
+	 * bug).
+	 */
+	error = xfs_itruncate_extents_flags(&tp, ip, XFS_DATA_FORK,
+				XFS_ISIZE(ip), XFS_BMAPI_NODISCARD);
+	if (error)
+		goto err_cancel;
 
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
-		xfs_trans_ijoin(tp, ip, 0);
+	error = xfs_trans_commit(tp);
+	if (error)
+		goto out_unlock;
 
-		/*
-		 * Do not update the on-disk file size.  If we update the
-		 * on-disk file size and then the system crashes before the
-		 * contents of the file are flushed to disk then the files
-		 * may be full of holes (ie NULL files bug).
-		 */
-		error = xfs_itruncate_extents_flags(&tp, ip, XFS_DATA_FORK,
-					XFS_ISIZE(ip), XFS_BMAPI_NODISCARD);
-		if (error) {
-			/*
-			 * If we get an error at this point we simply don't
-			 * bother truncating the file.
-			 */
-			xfs_trans_cancel(tp);
-		} else {
-			error = xfs_trans_commit(tp);
-			if (!error)
-				xfs_inode_clear_eofblocks_tag(ip);
-		}
+	xfs_inode_clear_eofblocks_tag(ip);
+	goto out_unlock;
 
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	}
+err_cancel:
+	/*
+	 * If we get an error at this point we simply don't
+	 * bother truncating the file.
+	 */
+	xfs_trans_cancel(tp);
+out_unlock:
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
 }
 
@@ -1208,7 +1219,7 @@ xfs_swap_extents_check_format(
 	if (XFS_IS_QUOTA_ON(ip->i_mount) &&
 	    (!uid_eq(VFS_I(ip)->i_uid, VFS_I(tip)->i_uid) ||
 	     !gid_eq(VFS_I(ip)->i_gid, VFS_I(tip)->i_gid) ||
-	     ip->i_d.di_projid != tip->i_d.di_projid))
+	     ip->i_projid != tip->i_projid))
 		return -EINVAL;
 
 	/* Should never get a local format */
@@ -1323,9 +1334,9 @@ xfs_swap_extent_rmap(
 	 * rmap functions when we go to fix up the rmaps.  The flags
 	 * will be switch for reals later.
 	 */
-	tip_flags2 = tip->i_d.di_flags2;
-	if (ip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK)
-		tip->i_d.di_flags2 |= XFS_DIFLAG2_REFLINK;
+	tip_flags2 = tip->i_diflags2;
+	if (ip->i_diflags2 & XFS_DIFLAG2_REFLINK)
+		tip->i_diflags2 |= XFS_DIFLAG2_REFLINK;
 
 	offset_fsb = 0;
 	end_fsb = XFS_B_TO_FSB(ip->i_mount, i_size_read(VFS_I(ip)));
@@ -1412,12 +1423,12 @@ xfs_swap_extent_rmap(
 		offset_fsb += ilen;
 	}
 
-	tip->i_d.di_flags2 = tip_flags2;
+	tip->i_diflags2 = tip_flags2;
 	return 0;
 
 out:
 	trace_xfs_swap_extent_rmap_error(ip, error, _RET_IP_);
-	tip->i_d.di_flags2 = tip_flags2;
+	tip->i_diflags2 = tip_flags2;
 	return error;
 }
 
@@ -1476,9 +1487,9 @@ xfs_swap_extent_forks(
 	/*
 	 * Fix the on-disk inode values
 	 */
-	tmp = (uint64_t)ip->i_d.di_nblocks;
-	ip->i_d.di_nblocks = tip->i_d.di_nblocks - taforkblks + aforkblks;
-	tip->i_d.di_nblocks = tmp + taforkblks - aforkblks;
+	tmp = (uint64_t)ip->i_nblocks;
+	ip->i_nblocks = tip->i_nblocks - taforkblks + aforkblks;
+	tip->i_nblocks = tmp + taforkblks - aforkblks;
 
 	/*
 	 * The extents in the source inode could still contain speculative
@@ -1663,8 +1674,8 @@ xfs_swap_extents(
 
 	/* Verify all data are being swapped */
 	if (sxp->sx_offset != 0 ||
-	    sxp->sx_length != ip->i_d.di_size ||
-	    sxp->sx_length != tip->i_d.di_size) {
+	    sxp->sx_length != ip->i_disk_size ||
+	    sxp->sx_length != tip->i_disk_size) {
 		error = -EFAULT;
 		goto out_trans_cancel;
 	}
@@ -1715,13 +1726,13 @@ xfs_swap_extents(
 		goto out_trans_cancel;
 
 	/* Do we have to swap reflink flags? */
-	if ((ip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK) ^
-	    (tip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK)) {
-		f = ip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK;
-		ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
-		ip->i_d.di_flags2 |= tip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK;
-		tip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
-		tip->i_d.di_flags2 |= f & XFS_DIFLAG2_REFLINK;
+	if ((ip->i_diflags2 & XFS_DIFLAG2_REFLINK) ^
+	    (tip->i_diflags2 & XFS_DIFLAG2_REFLINK)) {
+		f = ip->i_diflags2 & XFS_DIFLAG2_REFLINK;
+		ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
+		ip->i_diflags2 |= tip->i_diflags2 & XFS_DIFLAG2_REFLINK;
+		tip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
+		tip->i_diflags2 |= f & XFS_DIFLAG2_REFLINK;
 	}
 
 	/* Swap the cow forks. */
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index dc0be2a639cc..fb69879e4b2b 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -55,6 +55,24 @@ xfs_buf_log_format_size(
 			(blfp->blf_map_size * sizeof(blfp->blf_data_map[0]));
 }
 
+static inline bool
+xfs_buf_item_straddle(
+	struct xfs_buf		*bp,
+	uint			offset,
+	int			first_bit,
+	int			nbits)
+{
+	void			*first, *last;
+
+	first = xfs_buf_offset(bp, offset + (first_bit << XFS_BLF_SHIFT));
+	last = xfs_buf_offset(bp,
+			offset + ((first_bit + nbits) << XFS_BLF_SHIFT));
+
+	if (last - first != nbits * XFS_BLF_CHUNK)
+		return true;
+	return false;
+}
+
 /*
  * This returns the number of log iovecs needed to log the
  * given buf log item.
@@ -69,24 +87,56 @@ STATIC void
 xfs_buf_item_size_segment(
 	struct xfs_buf_log_item		*bip,
 	struct xfs_buf_log_format	*blfp,
+	uint				offset,
 	int				*nvecs,
 	int				*nbytes)
 {
 	struct xfs_buf			*bp = bip->bli_buf;
+	int				first_bit;
+	int				nbits;
 	int				next_bit;
 	int				last_bit;
 
-	last_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size, 0);
-	if (last_bit == -1)
+	first_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size, 0);
+	if (first_bit == -1)
 		return;
 
-	/*
-	 * initial count for a dirty buffer is 2 vectors - the format structure
-	 * and the first dirty region.
-	 */
-	*nvecs += 2;
-	*nbytes += xfs_buf_log_format_size(blfp) + XFS_BLF_CHUNK;
+	(*nvecs)++;
+	*nbytes += xfs_buf_log_format_size(blfp);
+
+	do {
+		nbits = xfs_contig_bits(blfp->blf_data_map,
+					blfp->blf_map_size, first_bit);
+		ASSERT(nbits > 0);
 
+		/*
+		 * Straddling a page is rare because we don't log contiguous
+		 * chunks of unmapped buffers anywhere.
+		 */
+		if (nbits > 1 &&
+		    xfs_buf_item_straddle(bp, offset, first_bit, nbits))
+			goto slow_scan;
+
+		(*nvecs)++;
+		*nbytes += nbits * XFS_BLF_CHUNK;
+
+		/*
+		 * This takes the bit number to start looking from and
+		 * returns the next set bit from there.  It returns -1
+		 * if there are no more bits set or the start bit is
+		 * beyond the end of the bitmap.
+		 */
+		first_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size,
+					(uint)first_bit + nbits + 1);
+	} while (first_bit != -1);
+
+	return;
+
+slow_scan:
+	/* Count the first bit we jumped out of the above loop from */
+	(*nvecs)++;
+	*nbytes += XFS_BLF_CHUNK;
+	last_bit = first_bit;
 	while (last_bit != -1) {
 		/*
 		 * This takes the bit number to start looking from and
@@ -103,16 +153,15 @@ xfs_buf_item_size_segment(
 		 */
 		if (next_bit == -1) {
 			break;
-		} else if (next_bit != last_bit + 1) {
-			last_bit = next_bit;
-			(*nvecs)++;
-		} else if (xfs_buf_offset(bp, next_bit * XFS_BLF_CHUNK) !=
-			   (xfs_buf_offset(bp, last_bit * XFS_BLF_CHUNK) +
-			    XFS_BLF_CHUNK)) {
+		} else if (next_bit != last_bit + 1 ||
+		           xfs_buf_item_straddle(bp, offset, first_bit, nbits)) {
 			last_bit = next_bit;
+			first_bit = next_bit;
 			(*nvecs)++;
+			nbits = 1;
 		} else {
 			last_bit++;
+			nbits++;
 		}
 		*nbytes += XFS_BLF_CHUNK;
 	}
@@ -142,7 +191,10 @@ xfs_buf_item_size(
 	int			*nbytes)
 {
 	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
+	struct xfs_buf		*bp = bip->bli_buf;
 	int			i;
+	int			bytes;
+	uint			offset = 0;
 
 	ASSERT(atomic_read(&bip->bli_refcount) > 0);
 	if (bip->bli_flags & XFS_BLI_STALE) {
@@ -174,7 +226,7 @@ xfs_buf_item_size(
 	}
 
 	/*
-	 * the vector count is based on the number of buffer vectors we have
+	 * The vector count is based on the number of buffer vectors we have
 	 * dirty bits in. This will only be greater than one when we have a
 	 * compound buffer with more than one segment dirty. Hence for compound
 	 * buffers we need to track which segment the dirty bits correspond to,
@@ -182,10 +234,19 @@ xfs_buf_item_size(
 	 * count for the extra buf log format structure that will need to be
 	 * written.
 	 */
+	bytes = 0;
 	for (i = 0; i < bip->bli_format_count; i++) {
-		xfs_buf_item_size_segment(bip, &bip->bli_formats[i],
-					  nvecs, nbytes);
+		xfs_buf_item_size_segment(bip, &bip->bli_formats[i], offset,
+					  nvecs, &bytes);
+		offset += BBTOB(bp->b_maps[i].bm_len);
 	}
+
+	/*
+	 * Round up the buffer size required to minimise the number of memory
+	 * allocations that need to be done as this item grows when relogged by
+	 * repeated modifications.
+	 */
+	*nbytes = round_up(bytes, 512);
 	trace_xfs_buf_item_size(bip);
 }
 
@@ -204,18 +265,6 @@ xfs_buf_item_copy_iovec(
 			nbits * XFS_BLF_CHUNK);
 }
 
-static inline bool
-xfs_buf_item_straddle(
-	struct xfs_buf		*bp,
-	uint			offset,
-	int			next_bit,
-	int			last_bit)
-{
-	return xfs_buf_offset(bp, offset + (next_bit << XFS_BLF_SHIFT)) !=
-		(xfs_buf_offset(bp, offset + (last_bit << XFS_BLF_SHIFT)) +
-		 XFS_BLF_CHUNK);
-}
-
 static void
 xfs_buf_item_format_segment(
 	struct xfs_buf_log_item	*bip,
@@ -268,6 +317,38 @@ xfs_buf_item_format_segment(
 	/*
 	 * Fill in an iovec for each set of contiguous chunks.
 	 */
+	do {
+		ASSERT(first_bit >= 0);
+		nbits = xfs_contig_bits(blfp->blf_data_map,
+					blfp->blf_map_size, first_bit);
+		ASSERT(nbits > 0);
+
+		/*
+		 * Straddling a page is rare because we don't log contiguous
+		 * chunks of unmapped buffers anywhere.
+		 */
+		if (nbits > 1 &&
+		    xfs_buf_item_straddle(bp, offset, first_bit, nbits))
+			goto slow_scan;
+
+		xfs_buf_item_copy_iovec(lv, vecp, bp, offset,
+					first_bit, nbits);
+		blfp->blf_size++;
+
+		/*
+		 * This takes the bit number to start looking from and
+		 * returns the next set bit from there.  It returns -1
+		 * if there are no more bits set or the start bit is
+		 * beyond the end of the bitmap.
+		 */
+		first_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size,
+					(uint)first_bit + nbits + 1);
+	} while (first_bit != -1);
+
+	return;
+
+slow_scan:
+	ASSERT(bp->b_addr == NULL);
 	last_bit = first_bit;
 	nbits = 1;
 	for (;;) {
@@ -292,7 +373,7 @@ xfs_buf_item_format_segment(
 			blfp->blf_size++;
 			break;
 		} else if (next_bit != last_bit + 1 ||
-		           xfs_buf_item_straddle(bp, offset, next_bit, last_bit)) {
+		           xfs_buf_item_straddle(bp, offset, first_bit, nbits)) {
 			xfs_buf_item_copy_iovec(lv, vecp, bp, offset,
 						first_bit, nbits);
 			blfp->blf_size++;
diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c
index 66deddd5e296..da1cc683560c 100644
--- a/fs/xfs/xfs_dir2_readdir.c
+++ b/fs/xfs/xfs_dir2_readdir.c
@@ -57,8 +57,8 @@ xfs_dir2_sf_getdents(
 	xfs_ino_t		ino;
 	struct xfs_da_geometry	*geo = args->geo;
 
-	ASSERT(dp->i_df.if_flags & XFS_IFINLINE);
-	ASSERT(dp->i_df.if_bytes == dp->i_d.di_size);
+	ASSERT(dp->i_df.if_format == XFS_DINODE_FMT_LOCAL);
+	ASSERT(dp->i_df.if_bytes == dp->i_disk_size);
 	ASSERT(dp->i_df.if_u1.if_data != NULL);
 
 	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
@@ -258,11 +258,9 @@ xfs_dir2_leaf_readbuf(
 	int			ra_want;
 	int			error = 0;
 
-	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
-		error = xfs_iread_extents(args->trans, dp, XFS_DATA_FORK);
-		if (error)
-			goto out;
-	}
+	error = xfs_iread_extents(args->trans, dp, XFS_DATA_FORK);
+	if (error)
+		goto out;
 
 	/*
 	 * Look for mapped directory blocks at or above the current offset.
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index bd8379b98374..ecd5059d6928 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -748,11 +748,9 @@ xfs_dq_get_next_id(
 	start = (xfs_fsblock_t)next_id / mp->m_quotainfo->qi_dqperchunk;
 
 	lock_flags = xfs_ilock_data_map_shared(quotip);
-	if (!(quotip->i_df.if_flags & XFS_IFEXTENTS)) {
-		error = xfs_iread_extents(NULL, quotip, XFS_DATA_FORK);
-		if (error)
-			return error;
-	}
+	error = xfs_iread_extents(NULL, quotip, XFS_DATA_FORK);
+	if (error)
+		return error;
 
 	if (xfs_iext_lookup_extent(quotip, &quotip->i_df, start, &cur, &got)) {
 		/* contiguous chunk, bump startoff for the id calculation */
@@ -953,7 +951,7 @@ xfs_qm_id_for_quotatype(
 	case XFS_DQTYPE_GROUP:
 		return i_gid_read(VFS_I(ip));
 	case XFS_DQTYPE_PROJ:
-		return ip->i_d.di_projid;
+		return ip->i_projid;
 	}
 	ASSERT(0);
 	return 0;
diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c
index 185b4915b7bf..ce3bc1b291a1 100644
--- a/fs/xfs/xfs_error.c
+++ b/fs/xfs/xfs_error.c
@@ -56,6 +56,7 @@ static unsigned int xfs_errortag_random_default[] = {
 	XFS_RANDOM_BUF_IOERROR,
 	XFS_RANDOM_REDUCE_MAX_IEXTENTS,
 	XFS_RANDOM_BMAP_ALLOC_MINLEN_EXTENT,
+	XFS_RANDOM_AG_RESV_FAIL,
 };
 
 struct xfs_errortag_attr {
@@ -168,6 +169,7 @@ XFS_ERRORTAG_ATTR_RW(iunlink_fallback,	XFS_ERRTAG_IUNLINK_FALLBACK);
 XFS_ERRORTAG_ATTR_RW(buf_ioerror,	XFS_ERRTAG_BUF_IOERROR);
 XFS_ERRORTAG_ATTR_RW(reduce_max_iextents,	XFS_ERRTAG_REDUCE_MAX_IEXTENTS);
 XFS_ERRORTAG_ATTR_RW(bmap_alloc_minlen_extent,	XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT);
+XFS_ERRORTAG_ATTR_RW(ag_resv_fail, XFS_ERRTAG_AG_RESV_FAIL);
 
 static struct attribute *xfs_errortag_attrs[] = {
 	XFS_ERRORTAG_ATTR_LIST(noerror),
@@ -208,6 +210,7 @@ static struct attribute *xfs_errortag_attrs[] = {
 	XFS_ERRORTAG_ATTR_LIST(buf_ioerror),
 	XFS_ERRORTAG_ATTR_LIST(reduce_max_iextents),
 	XFS_ERRORTAG_ATTR_LIST(bmap_alloc_minlen_extent),
+	XFS_ERRORTAG_ATTR_LIST(ag_resv_fail),
 	NULL,
 };
 
@@ -299,6 +302,8 @@ xfs_errortag_add(
 	struct xfs_mount	*mp,
 	unsigned int		error_tag)
 {
+	BUILD_BUG_ON(ARRAY_SIZE(xfs_errortag_random_default) != XFS_ERRTAG_MAX);
+
 	if (error_tag >= XFS_ERRTAG_MAX)
 		return -EINVAL;
 
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index a007ca0711d9..396ef36dcd0a 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -90,9 +90,9 @@ xfs_update_prealloc_flags(
 	}
 
 	if (flags & XFS_PREALLOC_SET)
-		ip->i_d.di_flags |= XFS_DIFLAG_PREALLOC;
+		ip->i_diflags |= XFS_DIFLAG_PREALLOC;
 	if (flags & XFS_PREALLOC_CLEAR)
-		ip->i_d.di_flags &= ~XFS_DIFLAG_PREALLOC;
+		ip->i_diflags &= ~XFS_DIFLAG_PREALLOC;
 
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 	if (flags & XFS_PREALLOC_SYNC)
@@ -1159,10 +1159,10 @@ xfs_file_remap_range(
 	 */
 	cowextsize = 0;
 	if (pos_in == 0 && len == i_size_read(inode_in) &&
-	    (src->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) &&
+	    (src->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) &&
 	    pos_out == 0 && len >= i_size_read(inode_out) &&
-	    !(dest->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE))
-		cowextsize = src->i_d.di_cowextsize;
+	    !(dest->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE))
+		cowextsize = src->i_cowextsize;
 
 	ret = xfs_reflink_update_dest(dest, pos_out + len, cowextsize,
 			remap_flags);
@@ -1244,7 +1244,7 @@ xfs_file_readdir(
 	 * point we can change the ->readdir prototype to include the
 	 * buffer size.  For now we use the current glibc buffer size.
 	 */
-	bufsize = (size_t)min_t(loff_t, XFS_READDIR_BUFSIZE, ip->i_d.di_size);
+	bufsize = (size_t)min_t(loff_t, XFS_READDIR_BUFSIZE, ip->i_disk_size);
 
 	return xfs_readdir(NULL, ip, ctx, bufsize);
 }
diff --git a/fs/xfs/xfs_filestream.h b/fs/xfs/xfs_filestream.h
index 5cc7665e93c9..3af963743e4d 100644
--- a/fs/xfs/xfs_filestream.h
+++ b/fs/xfs/xfs_filestream.h
@@ -22,7 +22,7 @@ xfs_inode_is_filestream(
 	struct xfs_inode	*ip)
 {
 	return (ip->i_mount->m_flags & XFS_MOUNT_FILESTREAMS) ||
-		(ip->i_d.di_flags & XFS_DIFLAG_FILESTREAM);
+		(ip->i_diflags & XFS_DIFLAG_FILESTREAM);
 }
 
 #endif /* __XFS_FILESTREAM_H__ */
diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index 9ce5e7d5bf8f..34f2b971ce43 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -904,14 +904,6 @@ xfs_getfsmap(
 	info.fsmap_recs = fsmap_recs;
 	info.head = head;
 
-	/*
-	 * If fsmap runs concurrently with a scrub, the freeze can be delayed
-	 * indefinitely as we walk the rmapbt and iterate over metadata
-	 * buffers.  Freeze quiesces the log (which waits for the buffer LRU to
-	 * be emptied) and that won't happen while we're reading buffers.
-	 */
-	sb_start_write(mp->m_super);
-
 	/* For each device we support... */
 	for (i = 0; i < XFS_GETFSMAP_DEVS; i++) {
 		/* Is this device within the range the user asked for? */
@@ -934,6 +926,11 @@ xfs_getfsmap(
 		if (handlers[i].dev > head->fmh_keys[0].fmr_device)
 			memset(&dkeys[0], 0, sizeof(struct xfs_fsmap));
 
+		/*
+		 * Grab an empty transaction so that we can use its recursive
+		 * buffer locking abilities to detect cycles in the rmapbt
+		 * without deadlocking.
+		 */
 		error = xfs_trans_alloc_empty(mp, &tp);
 		if (error)
 			break;
@@ -951,7 +948,6 @@ xfs_getfsmap(
 
 	if (tp)
 		xfs_trans_cancel(tp);
-	sb_end_write(mp->m_super);
 	head->fmh_oflags = FMH_OF_DEV_T;
 	return error;
 }
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index a2a407039227..b33c894b6cf3 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -21,6 +21,64 @@
 #include "xfs_ag_resv.h"
 
 /*
+ * Write new AG headers to disk. Non-transactional, but need to be
+ * written and completed prior to the growfs transaction being logged.
+ * To do this, we use a delayed write buffer list and wait for
+ * submission and IO completion of the list as a whole. This allows the
+ * IO subsystem to merge all the AG headers in a single AG into a single
+ * IO and hide most of the latency of the IO from us.
+ *
+ * This also means that if we get an error whilst building the buffer
+ * list to write, we can cancel the entire list without having written
+ * anything.
+ */
+static int
+xfs_resizefs_init_new_ags(
+	struct xfs_trans	*tp,
+	struct aghdr_init_data	*id,
+	xfs_agnumber_t		oagcount,
+	xfs_agnumber_t		nagcount,
+	xfs_rfsblock_t		delta,
+	bool			*lastag_extended)
+{
+	struct xfs_mount	*mp = tp->t_mountp;
+	xfs_rfsblock_t		nb = mp->m_sb.sb_dblocks + delta;
+	int			error;
+
+	*lastag_extended = false;
+
+	INIT_LIST_HEAD(&id->buffer_list);
+	for (id->agno = nagcount - 1;
+	     id->agno >= oagcount;
+	     id->agno--, delta -= id->agsize) {
+
+		if (id->agno == nagcount - 1)
+			id->agsize = nb - (id->agno *
+					(xfs_rfsblock_t)mp->m_sb.sb_agblocks);
+		else
+			id->agsize = mp->m_sb.sb_agblocks;
+
+		error = xfs_ag_init_headers(mp, id);
+		if (error) {
+			xfs_buf_delwri_cancel(&id->buffer_list);
+			return error;
+		}
+	}
+
+	error = xfs_buf_delwri_submit(&id->buffer_list);
+	if (error)
+		return error;
+
+	xfs_trans_agblocks_delta(tp, id->nfree);
+
+	if (delta) {
+		*lastag_extended = true;
+		error = xfs_ag_extend_space(mp, tp, id, delta);
+	}
+	return error;
+}
+
+/*
  * growfs operations
  */
 static int
@@ -33,22 +91,25 @@ xfs_growfs_data_private(
 	xfs_agnumber_t		nagcount;
 	xfs_agnumber_t		nagimax = 0;
 	xfs_rfsblock_t		nb, nb_div, nb_mod;
-	xfs_rfsblock_t		delta;
+	int64_t			delta;
+	bool			lastag_extended;
 	xfs_agnumber_t		oagcount;
 	struct xfs_trans	*tp;
 	struct aghdr_init_data	id = {};
 
 	nb = in->newblocks;
-	if (nb < mp->m_sb.sb_dblocks)
-		return -EINVAL;
-	if ((error = xfs_sb_validate_fsb_count(&mp->m_sb, nb)))
+	error = xfs_sb_validate_fsb_count(&mp->m_sb, nb);
+	if (error)
 		return error;
-	error = xfs_buf_read_uncached(mp->m_ddev_targp,
+
+	if (nb > mp->m_sb.sb_dblocks) {
+		error = xfs_buf_read_uncached(mp->m_ddev_targp,
 				XFS_FSB_TO_BB(mp, nb) - XFS_FSS_TO_BB(mp, 1),
 				XFS_FSS_TO_BB(mp, 1), 0, &bp, NULL);
-	if (error)
-		return error;
-	xfs_buf_relse(bp);
+		if (error)
+			return error;
+		xfs_buf_relse(bp);
+	}
 
 	nb_div = nb;
 	nb_mod = do_div(nb_div, mp->m_sb.sb_agblocks);
@@ -56,10 +117,16 @@ xfs_growfs_data_private(
 	if (nb_mod && nb_mod < XFS_MIN_AG_BLOCKS) {
 		nagcount--;
 		nb = (xfs_rfsblock_t)nagcount * mp->m_sb.sb_agblocks;
-		if (nb < mp->m_sb.sb_dblocks)
-			return -EINVAL;
 	}
 	delta = nb - mp->m_sb.sb_dblocks;
+	/*
+	 * Reject filesystems with a single AG because they are not
+	 * supported, and reject a shrink operation that would cause a
+	 * filesystem to become unsupported.
+	 */
+	if (delta < 0 && nagcount < 2)
+		return -EINVAL;
+
 	oagcount = mp->m_sb.sb_agcount;
 
 	/* allocate the new per-ag structures */
@@ -67,55 +134,34 @@ xfs_growfs_data_private(
 		error = xfs_initialize_perag(mp, nagcount, &nagimax);
 		if (error)
 			return error;
+	} else if (nagcount < oagcount) {
+		/* TODO: shrinking the entire AGs hasn't yet completed */
+		return -EINVAL;
 	}
 
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_growdata,
-			XFS_GROWFS_SPACE_RES(mp), 0, XFS_TRANS_RESERVE, &tp);
+			(delta > 0 ? XFS_GROWFS_SPACE_RES(mp) : -delta), 0,
+			XFS_TRANS_RESERVE, &tp);
 	if (error)
 		return error;
 
-	/*
-	 * Write new AG headers to disk. Non-transactional, but need to be
-	 * written and completed prior to the growfs transaction being logged.
-	 * To do this, we use a delayed write buffer list and wait for
-	 * submission and IO completion of the list as a whole. This allows the
-	 * IO subsystem to merge all the AG headers in a single AG into a single
-	 * IO and hide most of the latency of the IO from us.
-	 *
-	 * This also means that if we get an error whilst building the buffer
-	 * list to write, we can cancel the entire list without having written
-	 * anything.
-	 */
-	INIT_LIST_HEAD(&id.buffer_list);
-	for (id.agno = nagcount - 1;
-	     id.agno >= oagcount;
-	     id.agno--, delta -= id.agsize) {
-
-		if (id.agno == nagcount - 1)
-			id.agsize = nb -
-				(id.agno * (xfs_rfsblock_t)mp->m_sb.sb_agblocks);
-		else
-			id.agsize = mp->m_sb.sb_agblocks;
+	if (delta > 0) {
+		error = xfs_resizefs_init_new_ags(tp, &id, oagcount, nagcount,
+						  delta, &lastag_extended);
+	} else {
+		static struct ratelimit_state shrink_warning = \
+			RATELIMIT_STATE_INIT("shrink_warning", 86400 * HZ, 1);
+		ratelimit_set_flags(&shrink_warning, RATELIMIT_MSG_ON_RELEASE);
 
-		error = xfs_ag_init_headers(mp, &id);
-		if (error) {
-			xfs_buf_delwri_cancel(&id.buffer_list);
-			goto out_trans_cancel;
-		}
+		if (__ratelimit(&shrink_warning))
+			xfs_alert(mp,
+	"EXPERIMENTAL online shrink feature in use. Use at your own risk!");
+
+		error = xfs_ag_shrink_space(mp, &tp, nagcount - 1, -delta);
 	}
-	error = xfs_buf_delwri_submit(&id.buffer_list);
 	if (error)
 		goto out_trans_cancel;
 
-	xfs_trans_agblocks_delta(tp, id.nfree);
-
-	/* If there are new blocks in the old last AG, extend it. */
-	if (delta) {
-		error = xfs_ag_extend_space(mp, tp, &id, delta);
-		if (error)
-			goto out_trans_cancel;
-	}
-
 	/*
 	 * Update changed superblock fields transactionally. These are not
 	 * seen by the rest of the world until the transaction commit applies
@@ -123,11 +169,19 @@ xfs_growfs_data_private(
 	 */
 	if (nagcount > oagcount)
 		xfs_trans_mod_sb(tp, XFS_TRANS_SB_AGCOUNT, nagcount - oagcount);
-	if (nb > mp->m_sb.sb_dblocks)
-		xfs_trans_mod_sb(tp, XFS_TRANS_SB_DBLOCKS,
-				 nb - mp->m_sb.sb_dblocks);
+	if (delta)
+		xfs_trans_mod_sb(tp, XFS_TRANS_SB_DBLOCKS, delta);
 	if (id.nfree)
 		xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, id.nfree);
+
+	/*
+	 * Sync sb counters now to reflect the updated values. This is
+	 * particularly important for shrink because the write verifier
+	 * will fail if sb_fdblocks is ever larger than sb_dblocks.
+	 */
+	if (xfs_sb_version_haslazysbcount(&mp->m_sb))
+		xfs_log_sb(tp);
+
 	xfs_trans_set_sync(tp);
 	error = xfs_trans_commit(tp);
 	if (error)
@@ -139,28 +193,29 @@ xfs_growfs_data_private(
 	xfs_set_low_space_thresholds(mp);
 	mp->m_alloc_set_aside = xfs_alloc_set_aside(mp);
 
-	/*
-	 * If we expanded the last AG, free the per-AG reservation
-	 * so we can reinitialize it with the new size.
-	 */
-	if (delta) {
-		struct xfs_perag	*pag;
-
-		pag = xfs_perag_get(mp, id.agno);
-		error = xfs_ag_resv_free(pag);
-		xfs_perag_put(pag);
-		if (error)
-			return error;
+	if (delta > 0) {
+		/*
+		 * If we expanded the last AG, free the per-AG reservation
+		 * so we can reinitialize it with the new size.
+		 */
+		if (lastag_extended) {
+			struct xfs_perag	*pag;
+
+			pag = xfs_perag_get(mp, id.agno);
+			error = xfs_ag_resv_free(pag);
+			xfs_perag_put(pag);
+			if (error)
+				return error;
+		}
+		/*
+		 * Reserve AG metadata blocks. ENOSPC here does not mean there
+		 * was a growfs failure, just that there still isn't space for
+		 * new user data after the grow has been run.
+		 */
+		error = xfs_fs_reserve_ag_blocks(mp);
+		if (error == -ENOSPC)
+			error = 0;
 	}
-
-	/*
-	 * Reserve AG metadata blocks. ENOSPC here does not mean there was a
-	 * growfs failure, just that there still isn't space for new user data
-	 * after the grow has been run.
-	 */
-	error = xfs_fs_reserve_ag_blocks(mp);
-	if (error == -ENOSPC)
-		error = 0;
 	return error;
 
 out_trans_cancel:
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 1d7720a0c068..3c81daca0e9a 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -63,7 +63,9 @@ xfs_inode_alloc(
 	memset(&ip->i_df, 0, sizeof(ip->i_df));
 	ip->i_flags = 0;
 	ip->i_delayed_blks = 0;
-	memset(&ip->i_d, 0, sizeof(ip->i_d));
+	ip->i_diflags2 = mp->m_ino_geo.new_diflags2;
+	ip->i_nblocks = 0;
+	ip->i_forkoff = 0;
 	ip->i_sick = 0;
 	ip->i_checked = 0;
 	INIT_WORK(&ip->i_ioend_work, xfs_end_io);
@@ -307,7 +309,7 @@ xfs_iget_check_free_state(
 			return -EFSCORRUPTED;
 		}
 
-		if (ip->i_d.di_nblocks != 0) {
+		if (ip->i_nblocks != 0) {
 			xfs_warn(ip->i_mount,
 "Corruption detected! Free inode 0x%llx has blocks allocated!",
 				ip->i_ino);
@@ -497,7 +499,7 @@ xfs_iget_cache_miss(
 	 * simply build the new inode core with a random generation number.
 	 *
 	 * For version 4 (and older) superblocks, log recovery is dependent on
-	 * the di_flushiter field being initialised from the current on-disk
+	 * the i_flushiter field being initialised from the current on-disk
 	 * value and hence we must also read the inode off disk even when
 	 * initializing new inodes.
 	 */
@@ -505,14 +507,14 @@ xfs_iget_cache_miss(
 	    (flags & XFS_IGET_CREATE) && !(mp->m_flags & XFS_MOUNT_IKEEP)) {
 		VFS_I(ip)->i_generation = prandom_u32();
 	} else {
-		struct xfs_dinode	*dip;
 		struct xfs_buf		*bp;
 
-		error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &dip, &bp, 0);
+		error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &bp);
 		if (error)
 			goto out_destroy;
 
-		error = xfs_inode_from_disk(ip, dip);
+		error = xfs_inode_from_disk(ip,
+				xfs_buf_offset(bp, ip->i_imap.im_boffset));
 		if (!error)
 			xfs_buf_set_ref(bp, XFS_INO_REF);
 		xfs_trans_brelse(tp, bp);
@@ -1202,7 +1204,7 @@ xfs_inode_match_id(
 		return false;
 
 	if ((eofb->eof_flags & XFS_EOF_FLAGS_PRID) &&
-	    ip->i_d.di_projid != eofb->eof_prid)
+	    ip->i_projid != eofb->eof_prid)
 		return false;
 
 	return true;
@@ -1226,7 +1228,7 @@ xfs_inode_match_id_union(
 		return true;
 
 	if ((eofb->eof_flags & XFS_EOF_FLAGS_PRID) &&
-	    ip->i_d.di_projid == eofb->eof_prid)
+	    ip->i_projid == eofb->eof_prid)
 		return true;
 
 	return false;
@@ -1294,13 +1296,6 @@ xfs_inode_free_eofblocks(
 	if (!xfs_iflags_test(ip, XFS_IEOFBLOCKS))
 		return 0;
 
-	if (!xfs_can_free_eofblocks(ip, false)) {
-		/* inode could be preallocated or append-only */
-		trace_xfs_inode_free_eofblocks_invalid(ip);
-		xfs_inode_clear_eofblocks_tag(ip);
-		return 0;
-	}
-
 	/*
 	 * If the mapping is dirty the operation can block and wait for some
 	 * time. Unless we are waiting, skip it.
@@ -1322,7 +1317,13 @@ xfs_inode_free_eofblocks(
 	}
 	*lockflags |= XFS_IOLOCK_EXCL;
 
-	return xfs_free_eofblocks(ip);
+	if (xfs_can_free_eofblocks(ip, false))
+		return xfs_free_eofblocks(ip);
+
+	/* inode could be preallocated or append-only */
+	trace_xfs_inode_free_eofblocks_invalid(ip);
+	xfs_inode_clear_eofblocks_tag(ip);
+	return 0;
 }
 
 /*
@@ -1335,7 +1336,7 @@ xfs_blockgc_queue(
 {
 	rcu_read_lock();
 	if (radix_tree_tagged(&pag->pag_ici_root, XFS_ICI_BLOCKGC_TAG))
-		queue_delayed_work(pag->pag_mount->m_blockgc_workqueue,
+		queue_delayed_work(pag->pag_mount->m_gc_workqueue,
 				   &pag->pag_blockgc_work,
 				   msecs_to_jiffies(xfs_blockgc_secs * 1000));
 	rcu_read_unlock();
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 2a8bdf33e6c4..0369eb22c1bb 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -60,8 +60,8 @@ xfs_get_extsz_hint(
 	 */
 	if (xfs_is_always_cow_inode(ip))
 		return 0;
-	if ((ip->i_d.di_flags & XFS_DIFLAG_EXTSIZE) && ip->i_d.di_extsize)
-		return ip->i_d.di_extsize;
+	if ((ip->i_diflags & XFS_DIFLAG_EXTSIZE) && ip->i_extsize)
+		return ip->i_extsize;
 	if (XFS_IS_REALTIME_INODE(ip))
 		return ip->i_mount->m_sb.sb_rextsize;
 	return 0;
@@ -80,8 +80,8 @@ xfs_get_cowextsz_hint(
 	xfs_extlen_t		a, b;
 
 	a = 0;
-	if (ip->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE)
-		a = ip->i_d.di_cowextsize;
+	if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE)
+		a = ip->i_cowextsize;
 	b = xfs_get_extsz_hint(ip);
 
 	a = max(a, b);
@@ -111,8 +111,7 @@ xfs_ilock_data_map_shared(
 {
 	uint			lock_mode = XFS_ILOCK_SHARED;
 
-	if (ip->i_df.if_format == XFS_DINODE_FMT_BTREE &&
-	    (ip->i_df.if_flags & XFS_IFEXTENTS) == 0)
+	if (xfs_need_iread_extents(&ip->i_df))
 		lock_mode = XFS_ILOCK_EXCL;
 	xfs_ilock(ip, lock_mode);
 	return lock_mode;
@@ -124,9 +123,7 @@ xfs_ilock_attr_map_shared(
 {
 	uint			lock_mode = XFS_ILOCK_SHARED;
 
-	if (ip->i_afp &&
-	    ip->i_afp->if_format == XFS_DINODE_FMT_BTREE &&
-	    (ip->i_afp->if_flags & XFS_IFEXTENTS) == 0)
+	if (ip->i_afp && xfs_need_iread_extents(ip->i_afp))
 		lock_mode = XFS_ILOCK_EXCL;
 	xfs_ilock(ip, lock_mode);
 	return lock_mode;
@@ -598,67 +595,55 @@ xfs_lock_two_inodes(
 	}
 }
 
-STATIC uint
-_xfs_dic2xflags(
-	uint16_t		di_flags,
-	uint64_t		di_flags2,
-	bool			has_attr)
+uint
+xfs_ip2xflags(
+	struct xfs_inode	*ip)
 {
 	uint			flags = 0;
 
-	if (di_flags & XFS_DIFLAG_ANY) {
-		if (di_flags & XFS_DIFLAG_REALTIME)
+	if (ip->i_diflags & XFS_DIFLAG_ANY) {
+		if (ip->i_diflags & XFS_DIFLAG_REALTIME)
 			flags |= FS_XFLAG_REALTIME;
-		if (di_flags & XFS_DIFLAG_PREALLOC)
+		if (ip->i_diflags & XFS_DIFLAG_PREALLOC)
 			flags |= FS_XFLAG_PREALLOC;
-		if (di_flags & XFS_DIFLAG_IMMUTABLE)
+		if (ip->i_diflags & XFS_DIFLAG_IMMUTABLE)
 			flags |= FS_XFLAG_IMMUTABLE;
-		if (di_flags & XFS_DIFLAG_APPEND)
+		if (ip->i_diflags & XFS_DIFLAG_APPEND)
 			flags |= FS_XFLAG_APPEND;
-		if (di_flags & XFS_DIFLAG_SYNC)
+		if (ip->i_diflags & XFS_DIFLAG_SYNC)
 			flags |= FS_XFLAG_SYNC;
-		if (di_flags & XFS_DIFLAG_NOATIME)
+		if (ip->i_diflags & XFS_DIFLAG_NOATIME)
 			flags |= FS_XFLAG_NOATIME;
-		if (di_flags & XFS_DIFLAG_NODUMP)
+		if (ip->i_diflags & XFS_DIFLAG_NODUMP)
 			flags |= FS_XFLAG_NODUMP;
-		if (di_flags & XFS_DIFLAG_RTINHERIT)
+		if (ip->i_diflags & XFS_DIFLAG_RTINHERIT)
 			flags |= FS_XFLAG_RTINHERIT;
-		if (di_flags & XFS_DIFLAG_PROJINHERIT)
+		if (ip->i_diflags & XFS_DIFLAG_PROJINHERIT)
 			flags |= FS_XFLAG_PROJINHERIT;
-		if (di_flags & XFS_DIFLAG_NOSYMLINKS)
+		if (ip->i_diflags & XFS_DIFLAG_NOSYMLINKS)
 			flags |= FS_XFLAG_NOSYMLINKS;
-		if (di_flags & XFS_DIFLAG_EXTSIZE)
+		if (ip->i_diflags & XFS_DIFLAG_EXTSIZE)
 			flags |= FS_XFLAG_EXTSIZE;
-		if (di_flags & XFS_DIFLAG_EXTSZINHERIT)
+		if (ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT)
 			flags |= FS_XFLAG_EXTSZINHERIT;
-		if (di_flags & XFS_DIFLAG_NODEFRAG)
+		if (ip->i_diflags & XFS_DIFLAG_NODEFRAG)
 			flags |= FS_XFLAG_NODEFRAG;
-		if (di_flags & XFS_DIFLAG_FILESTREAM)
+		if (ip->i_diflags & XFS_DIFLAG_FILESTREAM)
 			flags |= FS_XFLAG_FILESTREAM;
 	}
 
-	if (di_flags2 & XFS_DIFLAG2_ANY) {
-		if (di_flags2 & XFS_DIFLAG2_DAX)
+	if (ip->i_diflags2 & XFS_DIFLAG2_ANY) {
+		if (ip->i_diflags2 & XFS_DIFLAG2_DAX)
 			flags |= FS_XFLAG_DAX;
-		if (di_flags2 & XFS_DIFLAG2_COWEXTSIZE)
+		if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE)
 			flags |= FS_XFLAG_COWEXTSIZE;
 	}
 
-	if (has_attr)
+	if (XFS_IFORK_Q(ip))
 		flags |= FS_XFLAG_HASATTR;
-
 	return flags;
 }
 
-uint
-xfs_ip2xflags(
-	struct xfs_inode	*ip)
-{
-	struct xfs_icdinode	*dic = &ip->i_d;
-
-	return _xfs_dic2xflags(dic->di_flags, dic->di_flags2, XFS_IFORK_Q(ip));
-}
-
 /*
  * Lookups up an inode from "name". If ci_name is not NULL, then a CI match
  * is allowed, otherwise it has to be an exact match. If a CI match is found,
@@ -708,42 +693,42 @@ xfs_inode_inherit_flags(
 	umode_t			mode = VFS_I(ip)->i_mode;
 
 	if (S_ISDIR(mode)) {
-		if (pip->i_d.di_flags & XFS_DIFLAG_RTINHERIT)
+		if (pip->i_diflags & XFS_DIFLAG_RTINHERIT)
 			di_flags |= XFS_DIFLAG_RTINHERIT;
-		if (pip->i_d.di_flags & XFS_DIFLAG_EXTSZINHERIT) {
+		if (pip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) {
 			di_flags |= XFS_DIFLAG_EXTSZINHERIT;
-			ip->i_d.di_extsize = pip->i_d.di_extsize;
+			ip->i_extsize = pip->i_extsize;
 		}
-		if (pip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)
+		if (pip->i_diflags & XFS_DIFLAG_PROJINHERIT)
 			di_flags |= XFS_DIFLAG_PROJINHERIT;
 	} else if (S_ISREG(mode)) {
-		if ((pip->i_d.di_flags & XFS_DIFLAG_RTINHERIT) &&
+		if ((pip->i_diflags & XFS_DIFLAG_RTINHERIT) &&
 		    xfs_sb_version_hasrealtime(&ip->i_mount->m_sb))
 			di_flags |= XFS_DIFLAG_REALTIME;
-		if (pip->i_d.di_flags & XFS_DIFLAG_EXTSZINHERIT) {
+		if (pip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) {
 			di_flags |= XFS_DIFLAG_EXTSIZE;
-			ip->i_d.di_extsize = pip->i_d.di_extsize;
+			ip->i_extsize = pip->i_extsize;
 		}
 	}
-	if ((pip->i_d.di_flags & XFS_DIFLAG_NOATIME) &&
+	if ((pip->i_diflags & XFS_DIFLAG_NOATIME) &&
 	    xfs_inherit_noatime)
 		di_flags |= XFS_DIFLAG_NOATIME;
-	if ((pip->i_d.di_flags & XFS_DIFLAG_NODUMP) &&
+	if ((pip->i_diflags & XFS_DIFLAG_NODUMP) &&
 	    xfs_inherit_nodump)
 		di_flags |= XFS_DIFLAG_NODUMP;
-	if ((pip->i_d.di_flags & XFS_DIFLAG_SYNC) &&
+	if ((pip->i_diflags & XFS_DIFLAG_SYNC) &&
 	    xfs_inherit_sync)
 		di_flags |= XFS_DIFLAG_SYNC;
-	if ((pip->i_d.di_flags & XFS_DIFLAG_NOSYMLINKS) &&
+	if ((pip->i_diflags & XFS_DIFLAG_NOSYMLINKS) &&
 	    xfs_inherit_nosymlinks)
 		di_flags |= XFS_DIFLAG_NOSYMLINKS;
-	if ((pip->i_d.di_flags & XFS_DIFLAG_NODEFRAG) &&
+	if ((pip->i_diflags & XFS_DIFLAG_NODEFRAG) &&
 	    xfs_inherit_nodefrag)
 		di_flags |= XFS_DIFLAG_NODEFRAG;
-	if (pip->i_d.di_flags & XFS_DIFLAG_FILESTREAM)
+	if (pip->i_diflags & XFS_DIFLAG_FILESTREAM)
 		di_flags |= XFS_DIFLAG_FILESTREAM;
 
-	ip->i_d.di_flags |= di_flags;
+	ip->i_diflags |= di_flags;
 }
 
 /* Propagate di_flags2 from a parent inode to a child inode. */
@@ -752,12 +737,12 @@ xfs_inode_inherit_flags2(
 	struct xfs_inode	*ip,
 	const struct xfs_inode	*pip)
 {
-	if (pip->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) {
-		ip->i_d.di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
-		ip->i_d.di_cowextsize = pip->i_d.di_cowextsize;
+	if (pip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) {
+		ip->i_diflags2 |= XFS_DIFLAG2_COWEXTSIZE;
+		ip->i_cowextsize = pip->i_cowextsize;
 	}
-	if (pip->i_d.di_flags2 & XFS_DIFLAG2_DAX)
-		ip->i_d.di_flags2 |= XFS_DIFLAG2_DAX;
+	if (pip->i_diflags2 & XFS_DIFLAG2_DAX)
+		ip->i_diflags2 |= XFS_DIFLAG2_DAX;
 }
 
 /*
@@ -774,6 +759,7 @@ xfs_init_new_inode(
 	xfs_nlink_t		nlink,
 	dev_t			rdev,
 	prid_t			prid,
+	bool			init_xattrs,
 	struct xfs_inode	**ipp)
 {
 	struct inode		*dir = pip ? VFS_I(pip) : NULL;
@@ -808,7 +794,7 @@ xfs_init_new_inode(
 	inode = VFS_I(ip);
 	set_nlink(inode, nlink);
 	inode->i_rdev = rdev;
-	ip->i_d.di_projid = prid;
+	ip->i_projid = prid;
 
 	if (dir && !(dir->i_mode & S_ISGID) &&
 	    (mp->m_flags & XFS_MOUNT_GRPID)) {
@@ -829,25 +815,22 @@ xfs_init_new_inode(
 	    !in_group_p(i_gid_into_mnt(mnt_userns, inode)))
 		inode->i_mode &= ~S_ISGID;
 
-	ip->i_d.di_size = 0;
+	ip->i_disk_size = 0;
 	ip->i_df.if_nextents = 0;
-	ASSERT(ip->i_d.di_nblocks == 0);
+	ASSERT(ip->i_nblocks == 0);
 
 	tv = current_time(inode);
 	inode->i_mtime = tv;
 	inode->i_atime = tv;
 	inode->i_ctime = tv;
 
-	ip->i_d.di_extsize = 0;
-	ip->i_d.di_dmevmask = 0;
-	ip->i_d.di_dmstate = 0;
-	ip->i_d.di_flags = 0;
+	ip->i_extsize = 0;
+	ip->i_diflags = 0;
 
 	if (xfs_sb_version_has_v3inode(&mp->m_sb)) {
 		inode_set_iversion(inode, 1);
-		ip->i_d.di_flags2 = mp->m_ino_geo.new_diflags2;
-		ip->i_d.di_cowextsize = 0;
-		ip->i_d.di_crtime = tv;
+		ip->i_cowextsize = 0;
+		ip->i_crtime = tv;
 	}
 
 	flags = XFS_ILOG_CORE;
@@ -857,19 +840,17 @@ xfs_init_new_inode(
 	case S_IFBLK:
 	case S_IFSOCK:
 		ip->i_df.if_format = XFS_DINODE_FMT_DEV;
-		ip->i_df.if_flags = 0;
 		flags |= XFS_ILOG_DEV;
 		break;
 	case S_IFREG:
 	case S_IFDIR:
-		if (pip && (pip->i_d.di_flags & XFS_DIFLAG_ANY))
+		if (pip && (pip->i_diflags & XFS_DIFLAG_ANY))
 			xfs_inode_inherit_flags(ip, pip);
-		if (pip && (pip->i_d.di_flags2 & XFS_DIFLAG2_ANY))
+		if (pip && (pip->i_diflags2 & XFS_DIFLAG2_ANY))
 			xfs_inode_inherit_flags2(ip, pip);
 		/* FALLTHROUGH */
 	case S_IFLNK:
 		ip->i_df.if_format = XFS_DINODE_FMT_EXTENTS;
-		ip->i_df.if_flags = XFS_IFEXTENTS;
 		ip->i_df.if_bytes = 0;
 		ip->i_df.if_u1.if_root = NULL;
 		break;
@@ -878,6 +859,20 @@ xfs_init_new_inode(
 	}
 
 	/*
+	 * If we need to create attributes immediately after allocating the
+	 * inode, initialise an empty attribute fork right now. We use the
+	 * default fork offset for attributes here as we don't know exactly what
+	 * size or how many attributes we might be adding. We can do this
+	 * safely here because we know the data fork is completely empty and
+	 * this saves us from needing to run a separate transaction to set the
+	 * fork offset in the immediate future.
+	 */
+	if (init_xattrs && xfs_sb_version_hasattr(&mp->m_sb)) {
+		ip->i_forkoff = xfs_default_attroffset(ip) >> 3;
+		ip->i_afp = xfs_ifork_alloc(XFS_DINODE_FMT_EXTENTS, 0);
+	}
+
+	/*
 	 * Log the new values stuffed into the inode.
 	 */
 	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
@@ -910,6 +905,7 @@ xfs_dir_ialloc(
 	xfs_nlink_t		nlink,
 	dev_t			rdev,
 	prid_t			prid,
+	bool			init_xattrs,
 	struct xfs_inode	**ipp)
 {
 	struct xfs_buf		*agibp;
@@ -937,7 +933,7 @@ xfs_dir_ialloc(
 	ASSERT(ino != NULLFSINO);
 
 	return xfs_init_new_inode(mnt_userns, *tpp, dp, ino, mode, nlink, rdev,
-				  prid, ipp);
+				  prid, init_xattrs, ipp);
 }
 
 /*
@@ -982,6 +978,7 @@ xfs_create(
 	struct xfs_name		*name,
 	umode_t			mode,
 	dev_t			rdev,
+	bool			init_xattrs,
 	xfs_inode_t		**ipp)
 {
 	int			is_dir = S_ISDIR(mode);
@@ -1053,7 +1050,7 @@ xfs_create(
 	 * pointing to itself.
 	 */
 	error = xfs_dir_ialloc(mnt_userns, &tp, dp, mode, is_dir ? 2 : 1, rdev,
-			       prid, &ip);
+			       prid, init_xattrs, &ip);
 	if (error)
 		goto out_trans_cancel;
 
@@ -1173,7 +1170,8 @@ xfs_create_tmpfile(
 	if (error)
 		goto out_release_dquots;
 
-	error = xfs_dir_ialloc(mnt_userns, &tp, dp, mode, 0, 0, prid, &ip);
+	error = xfs_dir_ialloc(mnt_userns, &tp, dp, mode, 0, 0, prid,
+				false, &ip);
 	if (error)
 		goto out_trans_cancel;
 
@@ -1272,8 +1270,8 @@ xfs_link(
 	 * creation in our tree when the project IDs are the same; else
 	 * the tree quota mechanism could be circumvented.
 	 */
-	if (unlikely((tdp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) &&
-		     tdp->i_d.di_projid != sip->i_d.di_projid)) {
+	if (unlikely((tdp->i_diflags & XFS_DIFLAG_PROJINHERIT) &&
+		     tdp->i_projid != sip->i_projid)) {
 		error = -EXDEV;
 		goto error_return;
 	}
@@ -1331,7 +1329,7 @@ xfs_itruncate_clear_reflink_flags(
 	dfork = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
 	cfork = XFS_IFORK_PTR(ip, XFS_COW_FORK);
 	if (dfork->if_bytes == 0 && cfork->if_bytes == 0)
-		ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
+		ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
 	if (cfork->if_bytes == 0)
 		xfs_inode_clear_cowblocks_tag(ip);
 }
@@ -1442,7 +1440,7 @@ xfs_release(
 	xfs_inode_t	*ip)
 {
 	xfs_mount_t	*mp = ip->i_mount;
-	int		error;
+	int		error = 0;
 
 	if (!S_ISREG(VFS_I(ip)->i_mode) || (VFS_I(ip)->i_mode == 0))
 		return 0;
@@ -1478,8 +1476,16 @@ xfs_release(
 	if (VFS_I(ip)->i_nlink == 0)
 		return 0;
 
-	if (xfs_can_free_eofblocks(ip, false)) {
+	/*
+	 * If we can't get the iolock just skip truncating the blocks past EOF
+	 * because we could deadlock with the mmap_lock otherwise. We'll get
+	 * another chance to drop them once the last reference to the inode is
+	 * dropped, so we'll never leak blocks permanently.
+	 */
+	if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL))
+		return 0;
 
+	if (xfs_can_free_eofblocks(ip, false)) {
 		/*
 		 * Check if the inode is being opened, written and closed
 		 * frequently and we have delayed allocation blocks outstanding
@@ -1495,26 +1501,20 @@ xfs_release(
 		 * place.
 		 */
 		if (xfs_iflags_test(ip, XFS_IDIRTY_RELEASE))
-			return 0;
-		/*
-		 * If we can't get the iolock just skip truncating the blocks
-		 * past EOF because we could deadlock with the mmap_lock
-		 * otherwise. We'll get another chance to drop them once the
-		 * last reference to the inode is dropped, so we'll never leak
-		 * blocks permanently.
-		 */
-		if (xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) {
-			error = xfs_free_eofblocks(ip);
-			xfs_iunlock(ip, XFS_IOLOCK_EXCL);
-			if (error)
-				return error;
-		}
+			goto out_unlock;
+
+		error = xfs_free_eofblocks(ip);
+		if (error)
+			goto out_unlock;
 
 		/* delalloc blocks after truncation means it really is dirty */
 		if (ip->i_delayed_blks)
 			xfs_iflags_set(ip, XFS_IDIRTY_RELEASE);
 	}
-	return 0;
+
+out_unlock:
+	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+	return error;
 }
 
 /*
@@ -1543,7 +1543,7 @@ xfs_inactive_truncate(
 	 * of a system crash before the truncate completes. See the related
 	 * comment in xfs_vn_setattr_size() for details.
 	 */
-	ip->i_d.di_size = 0;
+	ip->i_disk_size = 0;
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
 	error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, 0);
@@ -1697,6 +1697,10 @@ xfs_inactive(
 	if (mp->m_flags & XFS_MOUNT_RDONLY)
 		return;
 
+	/* Metadata inodes require explicit resource cleanup. */
+	if (xfs_is_metadata_inode(ip))
+		return;
+
 	/* Try to clean out the cow blocks if there are any. */
 	if (xfs_inode_has_cow_data(ip))
 		xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, true);
@@ -1718,7 +1722,7 @@ xfs_inactive(
 	}
 
 	if (S_ISREG(VFS_I(ip)->i_mode) &&
-	    (ip->i_d.di_size != 0 || XFS_ISIZE(ip) != 0 ||
+	    (ip->i_disk_size != 0 || XFS_ISIZE(ip) != 0 ||
 	     ip->i_df.if_nextents > 0 || ip->i_delayed_blks > 0))
 		truncate = 1;
 
@@ -1745,7 +1749,7 @@ xfs_inactive(
 	}
 
 	ASSERT(!ip->i_afp);
-	ASSERT(ip->i_d.di_forkoff == 0);
+	ASSERT(ip->i_forkoff == 0);
 
 	/*
 	 * Free the inode.
@@ -2053,9 +2057,10 @@ xfs_iunlink_update_inode(
 
 	ASSERT(xfs_verify_agino_or_null(mp, agno, next_agino));
 
-	error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &dip, &ibp, 0);
+	error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &ibp);
 	if (error)
 		return error;
+	dip = xfs_buf_offset(ibp, ip->i_imap.im_boffset);
 
 	/* Make sure the old pointer isn't garbage. */
 	old_value = be32_to_cpu(dip->di_next_unlinked);
@@ -2180,13 +2185,14 @@ xfs_iunlink_map_ino(
 		return error;
 	}
 
-	error = xfs_imap_to_bp(mp, tp, imap, dipp, bpp, 0);
+	error = xfs_imap_to_bp(mp, tp, imap, bpp);
 	if (error) {
 		xfs_warn(mp, "%s: xfs_imap_to_bp returned error %d.",
 				__func__, error);
 		return error;
 	}
 
+	*dipp = xfs_buf_offset(*bpp, imap->im_boffset);
 	return 0;
 }
 
@@ -2564,8 +2570,8 @@ xfs_ifree(
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 	ASSERT(VFS_I(ip)->i_nlink == 0);
 	ASSERT(ip->i_df.if_nextents == 0);
-	ASSERT(ip->i_d.di_size == 0 || !S_ISREG(VFS_I(ip)->i_mode));
-	ASSERT(ip->i_d.di_nblocks == 0);
+	ASSERT(ip->i_disk_size == 0 || !S_ISREG(VFS_I(ip)->i_mode));
+	ASSERT(ip->i_nblocks == 0);
 
 	/*
 	 * Pull the on-disk inode from the AGI unlinked list.
@@ -2590,11 +2596,12 @@ xfs_ifree(
 	}
 
 	VFS_I(ip)->i_mode = 0;		/* mark incore inode as free */
-	ip->i_d.di_flags = 0;
-	ip->i_d.di_flags2 = ip->i_mount->m_ino_geo.new_diflags2;
-	ip->i_d.di_dmevmask = 0;
-	ip->i_d.di_forkoff = 0;		/* mark the attr fork not in use */
+	ip->i_diflags = 0;
+	ip->i_diflags2 = ip->i_mount->m_ino_geo.new_diflags2;
+	ip->i_forkoff = 0;		/* mark the attr fork not in use */
 	ip->i_df.if_format = XFS_DINODE_FMT_EXTENTS;
+	if (xfs_iflags_test(ip, XFS_IPRESERVE_DM_FIELDS))
+		xfs_iflags_clear(ip, XFS_IPRESERVE_DM_FIELDS);
 
 	/* Don't attempt to replay owner changes for a deleted inode */
 	spin_lock(&iip->ili_lock);
@@ -2870,7 +2877,7 @@ xfs_finish_rename(
 /*
  * xfs_cross_rename()
  *
- * responsible for handling RENAME_EXCHANGE flag in renameat2() sytemcall
+ * responsible for handling RENAME_EXCHANGE flag in renameat2() syscall
  */
 STATIC int
 xfs_cross_rename(
@@ -3103,8 +3110,8 @@ xfs_rename(
 	 * into our tree when the project IDs are the same; else the
 	 * tree quota mechanism would be circumvented.
 	 */
-	if (unlikely((target_dp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) &&
-		     target_dp->i_d.di_projid != src_ip->i_d.di_projid)) {
+	if (unlikely((target_dp->i_diflags & XFS_DIFLAG_PROJINHERIT) &&
+		     target_dp->i_projid != src_ip->i_projid)) {
 		error = -EXDEV;
 		goto out_trans_cancel;
 	}
@@ -3414,34 +3421,33 @@ xfs_iflush(
 		}
 	}
 	if (XFS_TEST_ERROR(ip->i_df.if_nextents + xfs_ifork_nextents(ip->i_afp) >
-				ip->i_d.di_nblocks, mp, XFS_ERRTAG_IFLUSH_5)) {
+				ip->i_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 "PTR_FMT,
 			__func__, ip->i_ino,
 			ip->i_df.if_nextents + xfs_ifork_nextents(ip->i_afp),
-			ip->i_d.di_nblocks, ip);
+			ip->i_nblocks, ip);
 		goto flush_out;
 	}
-	if (XFS_TEST_ERROR(ip->i_d.di_forkoff > mp->m_sb.sb_inodesize,
+	if (XFS_TEST_ERROR(ip->i_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 "PTR_FMT,
-			__func__, ip->i_ino, ip->i_d.di_forkoff, ip);
+			__func__, ip->i_ino, ip->i_forkoff, ip);
 		goto flush_out;
 	}
 
 	/*
-	 * Inode item log recovery for v2 inodes are dependent on the
-	 * di_flushiter count for correct sequencing. We bump the flush
-	 * iteration count so we can detect flushes which postdate a log record
-	 * during recovery. This is redundant as we now log every change and
-	 * hence this can't happen but we need to still do it to ensure
-	 * backwards compatibility with old kernels that predate logging all
-	 * inode changes.
+	 * Inode item log recovery for v2 inodes are dependent on the flushiter
+	 * count for correct sequencing.  We bump the flush iteration count so
+	 * we can detect flushes which postdate a log record during recovery.
+	 * This is redundant as we now log every change and hence this can't
+	 * happen but we need to still do it to ensure backwards compatibility
+	 * with old kernels that predate logging all inode changes.
 	 */
 	if (!xfs_sb_version_has_v3inode(&mp->m_sb))
-		ip->i_d.di_flushiter++;
+		ip->i_flushiter++;
 
 	/*
 	 * If there are inline format data / attr forks attached to this inode,
@@ -3462,8 +3468,10 @@ xfs_iflush(
 	xfs_inode_to_disk(ip, dip, iip->ili_item.li_lsn);
 
 	/* Wrap, we never let the log put out DI_MAX_FLUSH */
-	if (ip->i_d.di_flushiter == DI_MAX_FLUSH)
-		ip->i_d.di_flushiter = 0;
+	if (!xfs_sb_version_has_v3inode(&mp->m_sb)) {
+		if (ip->i_flushiter == DI_MAX_FLUSH)
+			ip->i_flushiter = 0;
+	}
 
 	xfs_iflush_fork(ip, dip, iip, XFS_DATA_FORK);
 	if (XFS_IFORK_Q(ip))
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 88ee4c3930ae..ca826cfba91c 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -54,8 +54,19 @@ typedef struct xfs_inode {
 	/* Miscellaneous state. */
 	unsigned long		i_flags;	/* see defined flags below */
 	uint64_t		i_delayed_blks;	/* count of delay alloc blks */
-
-	struct xfs_icdinode	i_d;		/* most of ondisk inode */
+	xfs_fsize_t		i_disk_size;	/* number of bytes in file */
+	xfs_rfsblock_t		i_nblocks;	/* # of direct & btree blocks */
+	prid_t			i_projid;	/* owner's project id */
+	xfs_extlen_t		i_extsize;	/* basic/minimum extent size */
+	/* cowextsize is only used for v3 inodes, flushiter for v1/2 */
+	union {
+		xfs_extlen_t	i_cowextsize;	/* basic cow extent size */
+		uint16_t	i_flushiter;	/* incremented on flush */
+	};
+	uint8_t			i_forkoff;	/* attr fork offset >> 3 */
+	uint16_t		i_diflags;	/* XFS_DIFLAG_... */
+	uint64_t		i_diflags2;	/* XFS_DIFLAG2_... */
+	struct timespec64	i_crtime;	/* time created */
 
 	/* VFS inode */
 	struct inode		i_vnode;	/* embedded VFS inode */
@@ -87,7 +98,7 @@ static inline xfs_fsize_t XFS_ISIZE(struct xfs_inode *ip)
 {
 	if (S_ISREG(VFS_I(ip)->i_mode))
 		return i_size_read(VFS_I(ip));
-	return ip->i_d.di_size;
+	return ip->i_disk_size;
 }
 
 /*
@@ -101,7 +112,7 @@ xfs_new_eof(struct xfs_inode *ip, xfs_fsize_t new_size)
 
 	if (new_size > i_size || new_size < 0)
 		new_size = i_size;
-	return new_size > ip->i_d.di_size ? new_size : 0;
+	return new_size > ip->i_disk_size ? new_size : 0;
 }
 
 /*
@@ -174,15 +185,23 @@ xfs_iflags_test_and_set(xfs_inode_t *ip, unsigned short flags)
 static inline prid_t
 xfs_get_initial_prid(struct xfs_inode *dp)
 {
-	if (dp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)
-		return dp->i_d.di_projid;
+	if (dp->i_diflags & XFS_DIFLAG_PROJINHERIT)
+		return dp->i_projid;
 
 	return XFS_PROJID_DEFAULT;
 }
 
 static inline bool xfs_is_reflink_inode(struct xfs_inode *ip)
 {
-	return ip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK;
+	return ip->i_diflags2 & XFS_DIFLAG2_REFLINK;
+}
+
+static inline bool xfs_is_metadata_inode(struct xfs_inode *ip)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+
+	return ip == mp->m_rbmip || ip == mp->m_rsumip ||
+		xfs_is_quota_inode(&mp->m_sb, ip->i_ino);
 }
 
 /*
@@ -196,7 +215,7 @@ static inline bool xfs_inode_has_cow_data(struct xfs_inode *ip)
 
 static inline bool xfs_inode_has_bigtime(struct xfs_inode *ip)
 {
-	return ip->i_d.di_flags2 & XFS_DIFLAG2_BIGTIME;
+	return ip->i_diflags2 & XFS_DIFLAG2_BIGTIME;
 }
 
 /*
@@ -214,6 +233,7 @@ static inline bool xfs_inode_has_bigtime(struct xfs_inode *ip)
 #define XFS_IRECLAIMABLE	(1 << 2) /* inode can be reclaimed */
 #define __XFS_INEW_BIT		3	 /* inode has just been allocated */
 #define XFS_INEW		(1 << __XFS_INEW_BIT)
+#define XFS_IPRESERVE_DM_FIELDS	(1 << 4) /* has legacy DMAPI fields set */
 #define XFS_ITRUNCATED		(1 << 5) /* truncated down so flush-on-close */
 #define XFS_IDIRTY_RELEASE	(1 << 6) /* dirty release already seen */
 #define XFS_IFLUSHING		(1 << 7) /* inode is being flushed */
@@ -371,7 +391,8 @@ int		xfs_lookup(struct xfs_inode *dp, struct xfs_name *name,
 			   struct xfs_inode **ipp, struct xfs_name *ci_name);
 int		xfs_create(struct user_namespace *mnt_userns,
 			   struct xfs_inode *dp, struct xfs_name *name,
-			   umode_t mode, dev_t rdev, struct xfs_inode **ipp);
+			   umode_t mode, dev_t rdev, bool need_xattr,
+			   struct xfs_inode **ipp);
 int		xfs_create_tmpfile(struct user_namespace *mnt_userns,
 			   struct xfs_inode *dp, umode_t mode,
 			   struct xfs_inode **ipp);
@@ -413,7 +434,8 @@ xfs_extlen_t	xfs_get_cowextsz_hint(struct xfs_inode *ip);
 int		xfs_dir_ialloc(struct user_namespace *mnt_userns,
 			       struct xfs_trans **tpp, struct xfs_inode *dp,
 			       umode_t mode, xfs_nlink_t nlink, dev_t dev,
-			       prid_t prid, struct xfs_inode **ipp);
+			       prid_t prid, bool need_xattr,
+			       struct xfs_inode **ipp);
 
 static inline int
 xfs_itruncate_extents(
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index 17e20a6d8b4e..c1b32680f71c 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -196,7 +196,7 @@ xfs_inode_item_format_data_fork(
 			 */
 			data_bytes = roundup(ip->i_df.if_bytes, 4);
 			ASSERT(ip->i_df.if_u1.if_data != NULL);
-			ASSERT(ip->i_d.di_size > 0);
+			ASSERT(ip->i_disk_size > 0);
 			xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_ILOCAL,
 					ip->i_df.if_u1.if_data, data_bytes);
 			ilf->ilf_dsize = (unsigned)data_bytes;
@@ -317,21 +317,47 @@ xfs_inode_to_log_dinode_ts(
 	return its;
 }
 
+/*
+ * The legacy DMAPI fields are only present in the on-disk and in-log inodes,
+ * but not in the in-memory one.  But we are guaranteed to have an inode buffer
+ * in memory when logging an inode, so we can just copy it from the on-disk
+ * inode to the in-log inode here so that recovery of file system with these
+ * fields set to non-zero values doesn't lose them.  For all other cases we zero
+ * the fields.
+ */
+static void
+xfs_copy_dm_fields_to_log_dinode(
+	struct xfs_inode	*ip,
+	struct xfs_log_dinode	*to)
+{
+	struct xfs_dinode	*dip;
+
+	dip = xfs_buf_offset(ip->i_itemp->ili_item.li_buf,
+			     ip->i_imap.im_boffset);
+
+	if (xfs_iflags_test(ip, XFS_IPRESERVE_DM_FIELDS)) {
+		to->di_dmevmask = be32_to_cpu(dip->di_dmevmask);
+		to->di_dmstate = be16_to_cpu(dip->di_dmstate);
+	} else {
+		to->di_dmevmask = 0;
+		to->di_dmstate = 0;
+	}
+}
+
 static void
 xfs_inode_to_log_dinode(
 	struct xfs_inode	*ip,
 	struct xfs_log_dinode	*to,
 	xfs_lsn_t		lsn)
 {
-	struct xfs_icdinode	*from = &ip->i_d;
 	struct inode		*inode = VFS_I(ip);
 
 	to->di_magic = XFS_DINODE_MAGIC;
 	to->di_format = xfs_ifork_format(&ip->i_df);
 	to->di_uid = i_uid_read(inode);
 	to->di_gid = i_gid_read(inode);
-	to->di_projid_lo = from->di_projid & 0xffff;
-	to->di_projid_hi = from->di_projid >> 16;
+	to->di_projid_lo = ip->i_projid & 0xffff;
+	to->di_projid_hi = ip->i_projid >> 16;
 
 	memset(to->di_pad, 0, sizeof(to->di_pad));
 	memset(to->di_pad3, 0, sizeof(to->di_pad3));
@@ -342,16 +368,16 @@ xfs_inode_to_log_dinode(
 	to->di_gen = inode->i_generation;
 	to->di_mode = inode->i_mode;
 
-	to->di_size = from->di_size;
-	to->di_nblocks = from->di_nblocks;
-	to->di_extsize = from->di_extsize;
+	to->di_size = ip->i_disk_size;
+	to->di_nblocks = ip->i_nblocks;
+	to->di_extsize = ip->i_extsize;
 	to->di_nextents = xfs_ifork_nextents(&ip->i_df);
 	to->di_anextents = xfs_ifork_nextents(ip->i_afp);
-	to->di_forkoff = from->di_forkoff;
+	to->di_forkoff = ip->i_forkoff;
 	to->di_aformat = xfs_ifork_format(ip->i_afp);
-	to->di_dmevmask = from->di_dmevmask;
-	to->di_dmstate = from->di_dmstate;
-	to->di_flags = from->di_flags;
+	to->di_flags = ip->i_diflags;
+
+	xfs_copy_dm_fields_to_log_dinode(ip, to);
 
 	/* log a dummy value to ensure log structure is fully initialised */
 	to->di_next_unlinked = NULLAGINO;
@@ -359,9 +385,9 @@ xfs_inode_to_log_dinode(
 	if (xfs_sb_version_has_v3inode(&ip->i_mount->m_sb)) {
 		to->di_version = 3;
 		to->di_changecount = inode_peek_iversion(inode);
-		to->di_crtime = xfs_inode_to_log_dinode_ts(ip, from->di_crtime);
-		to->di_flags2 = from->di_flags2;
-		to->di_cowextsize = from->di_cowextsize;
+		to->di_crtime = xfs_inode_to_log_dinode_ts(ip, ip->i_crtime);
+		to->di_flags2 = ip->i_diflags2;
+		to->di_cowextsize = ip->i_cowextsize;
 		to->di_ino = ip->i_ino;
 		to->di_lsn = lsn;
 		memset(to->di_pad2, 0, sizeof(to->di_pad2));
@@ -369,7 +395,7 @@ xfs_inode_to_log_dinode(
 		to->di_flushiter = 0;
 	} else {
 		to->di_version = 2;
-		to->di_flushiter = from->di_flushiter;
+		to->di_flushiter = ip->i_flushiter;
 	}
 }
 
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index bbda105a2ce5..3925bfcb2365 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -1060,14 +1060,16 @@ xfs_fill_fsxattr(
 	int			whichfork,
 	struct fileattr		*fa)
 {
+	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, whichfork);
 
 	fileattr_fill_xflags(fa, xfs_ip2xflags(ip));
-	fa->fsx_extsize = ip->i_d.di_extsize << ip->i_mount->m_sb.sb_blocklog;
-	fa->fsx_cowextsize = ip->i_d.di_cowextsize <<
-			ip->i_mount->m_sb.sb_blocklog;
-	fa->fsx_projid = ip->i_d.di_projid;
-	if (ifp && (ifp->if_flags & XFS_IFEXTENTS))
+
+	fa->fsx_extsize = XFS_FSB_TO_B(mp, ip->i_extsize);
+	if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE)
+		fa->fsx_cowextsize = XFS_FSB_TO_B(mp, ip->i_cowextsize);
+	fa->fsx_projid = ip->i_projid;
+	if (ifp && !xfs_need_iread_extents(ifp))
 		fa->fsx_nextents = xfs_iext_count(ifp);
 	else
 		fa->fsx_nextents = xfs_ifork_nextents(ifp);
@@ -1111,7 +1113,7 @@ xfs_flags2diflags(
 {
 	/* can't set PREALLOC this way, just preserve it */
 	uint16_t		di_flags =
-		(ip->i_d.di_flags & XFS_DIFLAG_PREALLOC);
+		(ip->i_diflags & XFS_DIFLAG_PREALLOC);
 
 	if (xflags & FS_XFLAG_IMMUTABLE)
 		di_flags |= XFS_DIFLAG_IMMUTABLE;
@@ -1152,8 +1154,8 @@ xfs_flags2diflags2(
 	unsigned int		xflags)
 {
 	uint64_t		di_flags2 =
-		(ip->i_d.di_flags2 & (XFS_DIFLAG2_REFLINK |
-				      XFS_DIFLAG2_BIGTIME));
+		(ip->i_diflags2 & (XFS_DIFLAG2_REFLINK |
+				   XFS_DIFLAG2_BIGTIME));
 
 	if (xflags & FS_XFLAG_DAX)
 		di_flags2 |= XFS_DIFLAG2_DAX;
@@ -1170,7 +1172,7 @@ xfs_ioctl_setattr_xflags(
 	struct fileattr		*fa)
 {
 	struct xfs_mount	*mp = ip->i_mount;
-	uint64_t		di_flags2;
+	uint64_t		i_flags2;
 
 	/* Can't change realtime flag if any extents are allocated. */
 	if ((ip->i_df.if_nextents || ip->i_delayed_blks) &&
@@ -1180,25 +1182,25 @@ xfs_ioctl_setattr_xflags(
 	/* If realtime flag is set then must have realtime device */
 	if (fa->fsx_xflags & FS_XFLAG_REALTIME) {
 		if (mp->m_sb.sb_rblocks == 0 || mp->m_sb.sb_rextsize == 0 ||
-		    (ip->i_d.di_extsize % mp->m_sb.sb_rextsize))
+		    (ip->i_extsize % mp->m_sb.sb_rextsize))
 			return -EINVAL;
 	}
 
 	/* Clear reflink if we are actually able to set the rt flag. */
 	if ((fa->fsx_xflags & FS_XFLAG_REALTIME) && xfs_is_reflink_inode(ip))
-		ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
+		ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
 
 	/* Don't allow us to set DAX mode for a reflinked file for now. */
 	if ((fa->fsx_xflags & FS_XFLAG_DAX) && xfs_is_reflink_inode(ip))
 		return -EINVAL;
 
 	/* diflags2 only valid for v3 inodes. */
-	di_flags2 = xfs_flags2diflags2(ip, fa->fsx_xflags);
-	if (di_flags2 && !xfs_sb_version_has_v3inode(&mp->m_sb))
+	i_flags2 = xfs_flags2diflags2(ip, fa->fsx_xflags);
+	if (i_flags2 && !xfs_sb_version_has_v3inode(&mp->m_sb))
 		return -EINVAL;
 
-	ip->i_d.di_flags = xfs_flags2diflags(ip, fa->fsx_xflags);
-	ip->i_d.di_flags2 = di_flags2;
+	ip->i_diflags = xfs_flags2diflags(ip, fa->fsx_xflags);
+	ip->i_diflags2 = i_flags2;
 
 	xfs_diflags_to_iflags(ip, false);
 	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
@@ -1223,9 +1225,9 @@ xfs_ioctl_setattr_prepare_dax(
 		return;
 
 	if (((fa->fsx_xflags & FS_XFLAG_DAX) &&
-	    !(ip->i_d.di_flags2 & XFS_DIFLAG2_DAX)) ||
+	    !(ip->i_diflags2 & XFS_DIFLAG2_DAX)) ||
 	    (!(fa->fsx_xflags & FS_XFLAG_DAX) &&
-	     (ip->i_d.di_flags2 & XFS_DIFLAG2_DAX)))
+	     (ip->i_diflags2 & XFS_DIFLAG2_DAX)))
 		d_mark_dontcache(inode);
 }
 
@@ -1293,7 +1295,7 @@ xfs_ioctl_setattr_check_extsize(
 		return 0;
 
 	if (S_ISREG(VFS_I(ip)->i_mode) && ip->i_df.if_nextents &&
-	    ((ip->i_d.di_extsize << mp->m_sb.sb_blocklog) != fa->fsx_extsize))
+	    ((ip->i_extsize << mp->m_sb.sb_blocklog) != fa->fsx_extsize))
 		return -EINVAL;
 
 	if (fa->fsx_extsize == 0)
@@ -1463,12 +1465,12 @@ xfs_fileattr_set(
 		VFS_I(ip)->i_mode &= ~(S_ISUID|S_ISGID);
 
 	/* Change the ownerships and register project quota modifications */
-	if (ip->i_d.di_projid != fa->fsx_projid) {
+	if (ip->i_projid != fa->fsx_projid) {
 		if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_PQUOTA_ON(mp)) {
 			olddquot = xfs_qm_vop_chown(tp, ip,
 						&ip->i_pdquot, pdqp);
 		}
-		ip->i_d.di_projid = fa->fsx_projid;
+		ip->i_projid = fa->fsx_projid;
 	}
 
 	/*
@@ -1476,16 +1478,17 @@ xfs_fileattr_set(
 	 * extent size hint should be set on the inode. If no extent size flags
 	 * are set on the inode then unconditionally clear the extent size hint.
 	 */
-	if (ip->i_d.di_flags & (XFS_DIFLAG_EXTSIZE | XFS_DIFLAG_EXTSZINHERIT))
-		ip->i_d.di_extsize = fa->fsx_extsize >> mp->m_sb.sb_blocklog;
-	else
-		ip->i_d.di_extsize = 0;
-	if (xfs_sb_version_has_v3inode(&mp->m_sb) &&
-	    (ip->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE))
-		ip->i_d.di_cowextsize = fa->fsx_cowextsize >>
-				mp->m_sb.sb_blocklog;
+	if (ip->i_diflags & (XFS_DIFLAG_EXTSIZE | XFS_DIFLAG_EXTSZINHERIT))
+		ip->i_extsize = XFS_B_TO_FSB(mp, fa->fsx_extsize);
 	else
-		ip->i_d.di_cowextsize = 0;
+		ip->i_extsize = 0;
+
+	if (xfs_sb_version_has_v3inode(&mp->m_sb)) {
+		if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE)
+			ip->i_cowextsize = XFS_B_TO_FSB(mp, fa->fsx_cowextsize);
+		else
+			ip->i_cowextsize = 0;
+	}
 
 skip_xattr:
 	error = xfs_trans_commit(tp);
@@ -1543,8 +1546,6 @@ xfs_ioc_getbmap(
 		bmx.bmv_iflags = BMV_IF_ATTRFORK;
 		/*FALLTHRU*/
 	case XFS_IOC_GETBMAP:
-		if (file->f_mode & FMODE_NOCMTIME)
-			bmx.bmv_iflags |= BMV_IF_NO_DMAPI_READ;
 		/* struct getbmap is a strict subset of struct getbmapx. */
 		recsize = sizeof(struct getbmap);
 		break;
@@ -1720,7 +1721,7 @@ out_free:
 
 STATIC int
 xfs_ioc_scrub_metadata(
-	struct xfs_inode		*ip,
+	struct file			*file,
 	void				__user *arg)
 {
 	struct xfs_scrub_metadata	scrub;
@@ -1732,7 +1733,7 @@ xfs_ioc_scrub_metadata(
 	if (copy_from_user(&scrub, arg, sizeof(scrub)))
 		return -EFAULT;
 
-	error = xfs_scrub_metadata(ip, &scrub);
+	error = xfs_scrub_metadata(file, &scrub);
 	if (error)
 		return error;
 
@@ -2023,7 +2024,7 @@ xfs_file_ioctl(
 		return xfs_ioc_getfsmap(ip, arg);
 
 	case XFS_IOC_SCRUB_METADATA:
-		return xfs_ioc_scrub_metadata(ip, arg);
+		return xfs_ioc_scrub_metadata(filp, arg);
 
 	case XFS_IOC_FD_TO_HANDLE:
 	case XFS_IOC_PATH_TO_HANDLE:
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index e17ab7f42928..d154f42e2dc6 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -159,7 +159,7 @@ xfs_iomap_eof_align_last_fsb(
 	struct xfs_bmbt_irec	irec;
 	struct xfs_iext_cursor	icur;
 
-	ASSERT(ifp->if_flags & XFS_IFEXTENTS);
+	ASSERT(!xfs_need_iread_extents(ifp));
 
 	/*
 	 * Always round up the allocation request to the extent hint boundary.
@@ -198,6 +198,7 @@ xfs_iomap_write_direct(
 	bool			force = false;
 	int			error;
 	int			bmapi_flags = XFS_BMAPI_PREALLOC;
+	int			nr_exts = XFS_IEXT_ADD_NOSPLIT_CNT;
 
 	ASSERT(count_fsb > 0);
 
@@ -232,6 +233,7 @@ xfs_iomap_write_direct(
 		bmapi_flags = XFS_BMAPI_CONVERT | XFS_BMAPI_ZERO;
 		if (imap->br_state == XFS_EXT_UNWRITTEN) {
 			force = true;
+			nr_exts = XFS_IEXT_WRITE_UNWRITTEN_CNT;
 			dblocks = XFS_DIOSTRAT_SPACE_RES(mp, 0) << 1;
 		}
 	}
@@ -241,8 +243,7 @@ xfs_iomap_write_direct(
 	if (error)
 		return error;
 
-	error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK,
-			XFS_IEXT_ADD_NOSPLIT_CNT);
+	error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK, nr_exts);
 	if (error)
 		goto out_trans_cancel;
 
@@ -572,7 +573,7 @@ xfs_iomap_write_unwritten(
 			i_size_write(inode, i_size);
 		i_size = xfs_new_eof(ip, i_size);
 		if (i_size) {
-			ip->i_d.di_size = i_size;
+			ip->i_disk_size = i_size;
 			xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 		}
 
@@ -666,7 +667,7 @@ xfs_ilock_for_iomap(
 	 * is an opencoded xfs_ilock_data_map_shared() call but with
 	 * non-blocking behaviour.
 	 */
-	if (!(ip->i_df.if_flags & XFS_IFEXTENTS)) {
+	if (xfs_need_iread_extents(&ip->i_df)) {
 		if (flags & IOMAP_NOWAIT)
 			return -EAGAIN;
 		mode = XFS_ILOCK_EXCL;
@@ -893,11 +894,9 @@ xfs_buffered_write_iomap_begin(
 
 	XFS_STATS_INC(mp, xs_blk_mapw);
 
-	if (!(ip->i_df.if_flags & XFS_IFEXTENTS)) {
-		error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK);
-		if (error)
-			goto out_unlock;
-	}
+	error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK);
+	if (error)
+		goto out_unlock;
 
 	/*
 	 * Search the data fork first to look up our source mapping.  We
@@ -1208,11 +1207,9 @@ xfs_seek_iomap_begin(
 		return -EIO;
 
 	lockmode = xfs_ilock_data_map_shared(ip);
-	if (!(ip->i_df.if_flags & XFS_IFEXTENTS)) {
-		error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK);
-		if (error)
-			goto out_unlock;
-	}
+	error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK);
+	if (error)
+		goto out_unlock;
 
 	if (xfs_iext_lookup_extent(ip, &ip->i_df, offset_fsb, &icur, &imap)) {
 		/*
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index e1f749b711f8..dfe24b7f26e5 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -127,6 +127,37 @@ xfs_cleanup_inode(
 	xfs_remove(XFS_I(dir), &teardown, XFS_I(inode));
 }
 
+/*
+ * Check to see if we are likely to need an extended attribute to be added to
+ * the inode we are about to allocate. This allows the attribute fork to be
+ * created during the inode allocation, reducing the number of transactions we
+ * need to do in this fast path.
+ *
+ * The security checks are optimistic, but not guaranteed. The two LSMs that
+ * require xattrs to be added here (selinux and smack) are also the only two
+ * LSMs that add a sb->s_security structure to the superblock. Hence if security
+ * is enabled and sb->s_security is set, we have a pretty good idea that we are
+ * going to be asked to add a security xattr immediately after allocating the
+ * xfs inode and instantiating the VFS inode.
+ */
+static inline bool
+xfs_create_need_xattr(
+	struct inode	*dir,
+	struct posix_acl *default_acl,
+	struct posix_acl *acl)
+{
+	if (acl)
+		return true;
+	if (default_acl)
+		return true;
+#if IS_ENABLED(CONFIG_SECURITY)
+	if (dir->i_sb->s_security)
+		return true;
+#endif
+	return false;
+}
+
+
 STATIC int
 xfs_generic_create(
 	struct user_namespace	*mnt_userns,
@@ -164,7 +195,8 @@ xfs_generic_create(
 
 	if (!tmpfile) {
 		error = xfs_create(mnt_userns, XFS_I(dir), &name, mode, rdev,
-				   &ip);
+				xfs_create_need_xattr(dir, default_acl, acl),
+				&ip);
 	} else {
 		error = xfs_create_tmpfile(mnt_userns, XFS_I(dir), mode, &ip);
 	}
@@ -488,7 +520,7 @@ xfs_vn_get_link_inline(
 	struct xfs_inode	*ip = XFS_I(inode);
 	char			*link;
 
-	ASSERT(ip->i_df.if_flags & XFS_IFINLINE);
+	ASSERT(ip->i_df.if_format == XFS_DINODE_FMT_LOCAL);
 
 	/*
 	 * The VFS crashes on a NULL pointer, so return -EFSCORRUPTED if
@@ -563,13 +595,12 @@ xfs_vn_getattr(
 	stat->atime = inode->i_atime;
 	stat->mtime = inode->i_mtime;
 	stat->ctime = inode->i_ctime;
-	stat->blocks =
-		XFS_FSB_TO_BB(mp, ip->i_d.di_nblocks + ip->i_delayed_blks);
+	stat->blocks = XFS_FSB_TO_BB(mp, ip->i_nblocks + ip->i_delayed_blks);
 
 	if (xfs_sb_version_has_v3inode(&mp->m_sb)) {
 		if (request_mask & STATX_BTIME) {
 			stat->result_mask |= STATX_BTIME;
-			stat->btime = ip->i_d.di_crtime;
+			stat->btime = ip->i_crtime;
 		}
 	}
 
@@ -577,11 +608,11 @@ xfs_vn_getattr(
 	 * Note: If you add another clause to set an attribute flag, please
 	 * update attributes_mask below.
 	 */
-	if (ip->i_d.di_flags & XFS_DIFLAG_IMMUTABLE)
+	if (ip->i_diflags & XFS_DIFLAG_IMMUTABLE)
 		stat->attributes |= STATX_ATTR_IMMUTABLE;
-	if (ip->i_d.di_flags & XFS_DIFLAG_APPEND)
+	if (ip->i_diflags & XFS_DIFLAG_APPEND)
 		stat->attributes |= STATX_ATTR_APPEND;
-	if (ip->i_d.di_flags & XFS_DIFLAG_NODUMP)
+	if (ip->i_diflags & XFS_DIFLAG_NODUMP)
 		stat->attributes |= STATX_ATTR_NODUMP;
 
 	stat->attributes_mask |= (STATX_ATTR_IMMUTABLE |
@@ -706,7 +737,7 @@ xfs_setattr_nonsize(
 		 */
 		ASSERT(udqp == NULL);
 		ASSERT(gdqp == NULL);
-		error = xfs_qm_vop_dqalloc(ip, uid, gid, ip->i_d.di_projid,
+		error = xfs_qm_vop_dqalloc(ip, uid, gid, ip->i_projid,
 					   qflags, &udqp, &gdqp, NULL);
 		if (error)
 			return error;
@@ -918,8 +949,8 @@ xfs_setattr_size(
 	 * operation.
 	 *
 	 * And we update in-core i_size and truncate page cache beyond newsize
-	 * before writeback the [di_size, newsize] range, so we're guaranteed
-	 * not to write stale data past the new EOF on truncate down.
+	 * before writeback the [i_disk_size, newsize] range, so we're
+	 * guaranteed not to write stale data past the new EOF on truncate down.
 	 */
 	truncate_setsize(inode, newsize);
 
@@ -932,9 +963,9 @@ xfs_setattr_size(
 	 * otherwise those blocks may not be zeroed after a crash.
 	 */
 	if (did_zeroing ||
-	    (newsize > ip->i_d.di_size && oldsize != ip->i_d.di_size)) {
+	    (newsize > ip->i_disk_size && oldsize != ip->i_disk_size)) {
 		error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
-						ip->i_d.di_size, newsize - 1);
+						ip->i_disk_size, newsize - 1);
 		if (error)
 			return error;
 	}
@@ -976,7 +1007,7 @@ xfs_setattr_size(
 	 * permanent before actually freeing any blocks it doesn't matter if
 	 * they get written to.
 	 */
-	ip->i_d.di_size = newsize;
+	ip->i_disk_size = newsize;
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
 	if (newsize <= oldsize) {
@@ -1262,7 +1293,7 @@ xfs_inode_should_enable_dax(
 		return false;
 	if (ip->i_mount->m_flags & XFS_MOUNT_DAX_ALWAYS)
 		return true;
-	if (ip->i_d.di_flags2 & XFS_DIFLAG2_DAX)
+	if (ip->i_diflags2 & XFS_DIFLAG2_DAX)
 		return true;
 	return false;
 }
@@ -1319,7 +1350,7 @@ xfs_setup_inode(
 	/* make the inode look hashed for the writeback code */
 	inode_fake_hash(inode);
 
-	i_size_write(inode, ip->i_d.di_size);
+	i_size_write(inode, ip->i_disk_size);
 	xfs_diflags_to_iflags(ip, true);
 
 	if (S_ISDIR(inode->i_mode)) {
@@ -1377,7 +1408,7 @@ xfs_setup_iops(
 		inode->i_fop = &xfs_dir_file_operations;
 		break;
 	case S_IFLNK:
-		if (ip->i_df.if_flags & XFS_IFINLINE)
+		if (ip->i_df.if_format == XFS_DINODE_FMT_LOCAL)
 			inode->i_op = &xfs_inline_symlink_inode_operations;
 		else
 			inode->i_op = &xfs_symlink_inode_operations;
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index 3498b97fb06d..f331975a16de 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -60,7 +60,6 @@ xfs_bulkstat_one_int(
 	struct xfs_bstat_chunk	*bc)
 {
 	struct user_namespace	*sb_userns = mp->m_super->s_user_ns;
-	struct xfs_icdinode	*dic;		/* dinode core info pointer */
 	struct xfs_inode	*ip;		/* incore inode pointer */
 	struct inode		*inode;
 	struct xfs_bulkstat	*buf = bc->buf;
@@ -81,16 +80,14 @@ xfs_bulkstat_one_int(
 	ASSERT(ip->i_imap.im_blkno != 0);
 	inode = VFS_I(ip);
 
-	dic = &ip->i_d;
-
 	/* xfs_iget returns the following without needing
 	 * further change.
 	 */
-	buf->bs_projectid = ip->i_d.di_projid;
+	buf->bs_projectid = ip->i_projid;
 	buf->bs_ino = ino;
 	buf->bs_uid = from_kuid(sb_userns, i_uid_into_mnt(mnt_userns, inode));
 	buf->bs_gid = from_kgid(sb_userns, i_gid_into_mnt(mnt_userns, inode));
-	buf->bs_size = dic->di_size;
+	buf->bs_size = ip->i_disk_size;
 
 	buf->bs_nlink = inode->i_nlink;
 	buf->bs_atime = inode->i_atime.tv_sec;
@@ -99,13 +96,11 @@ xfs_bulkstat_one_int(
 	buf->bs_mtime_nsec = inode->i_mtime.tv_nsec;
 	buf->bs_ctime = inode->i_ctime.tv_sec;
 	buf->bs_ctime_nsec = inode->i_ctime.tv_nsec;
-	buf->bs_btime = dic->di_crtime.tv_sec;
-	buf->bs_btime_nsec = dic->di_crtime.tv_nsec;
 	buf->bs_gen = inode->i_generation;
 	buf->bs_mode = inode->i_mode;
 
 	buf->bs_xflags = xfs_ip2xflags(ip);
-	buf->bs_extsize_blks = dic->di_extsize;
+	buf->bs_extsize_blks = ip->i_extsize;
 	buf->bs_extents = xfs_ifork_nextents(&ip->i_df);
 	xfs_bulkstat_health(ip, buf);
 	buf->bs_aextents = xfs_ifork_nextents(ip->i_afp);
@@ -113,8 +108,10 @@ xfs_bulkstat_one_int(
 	buf->bs_version = XFS_BULKSTAT_VERSION_V5;
 
 	if (xfs_sb_version_has_v3inode(&mp->m_sb)) {
-		if (dic->di_flags2 & XFS_DIFLAG2_COWEXTSIZE)
-			buf->bs_cowextsize_blks = dic->di_cowextsize;
+		buf->bs_btime = ip->i_crtime.tv_sec;
+		buf->bs_btime_nsec = ip->i_crtime.tv_nsec;
+		if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE)
+			buf->bs_cowextsize_blks = ip->i_cowextsize;
 	}
 
 	switch (ip->i_df.if_format) {
@@ -132,7 +129,7 @@ xfs_bulkstat_one_int(
 	case XFS_DINODE_FMT_BTREE:
 		buf->bs_rdev = 0;
 		buf->bs_blksize = mp->m_sb.sb_blocksize;
-		buf->bs_blocks = dic->di_nblocks + ip->i_delayed_blks;
+		buf->bs_blocks = ip->i_nblocks + ip->i_delayed_blks;
 		break;
 	}
 	xfs_iunlock(ip, XFS_ILOCK_SHARED);
diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h
index af6be9b9ccdf..7688663b9773 100644
--- a/fs/xfs/xfs_linux.h
+++ b/fs/xfs/xfs_linux.h
@@ -233,7 +233,7 @@ int xfs_rw_bdev(struct block_device *bdev, sector_t sector, unsigned int count,
  * configured realtime device.
  */
 #define XFS_IS_REALTIME_INODE(ip)			\
-	(((ip)->i_d.di_flags & XFS_DIFLAG_REALTIME) &&	\
+	(((ip)->i_diflags & XFS_DIFLAG_REALTIME) &&	\
 	 (ip)->i_mount->m_rtdev_targp)
 #define XFS_IS_REALTIME_MOUNT(mp) ((mp)->m_rtdev_targp ? 1 : 0)
 #else
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 97f31308de03..e5dd1c0c2f03 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -2683,9 +2683,10 @@ xlog_recover_process_one_iunlink(
 	/*
 	 * Get the on disk inode to find the next inode in the bucket.
 	 */
-	error = xfs_imap_to_bp(mp, NULL, &ip->i_imap, &dip, &ibp, 0);
+	error = xfs_imap_to_bp(mp, NULL, &ip->i_imap, &ibp);
 	if (error)
 		goto fail_iput;
+	dip = xfs_buf_offset(ibp, ip->i_imap.im_boffset);
 
 	xfs_iflags_clear(ip, XFS_IRECOVERY);
 	ASSERT(VFS_I(ip)->i_nlink == 0);
@@ -2695,12 +2696,6 @@ xlog_recover_process_one_iunlink(
 	agino = be32_to_cpu(dip->di_next_unlinked);
 	xfs_buf_relse(ibp);
 
-	/*
-	 * Prevent any DMAPI event from being sent when the reference on
-	 * the inode is dropped.
-	 */
-	ip->i_d.di_dmevmask = 0;
-
 	xfs_irele(ip);
 	return agino;
 
@@ -2736,7 +2731,7 @@ xlog_recover_process_one_iunlink(
  * of log space.
  *
  * This behaviour is bad for latency on single CPU and non-preemptible kernels,
- * and can prevent other filesytem work (such as CIL pushes) from running. This
+ * and can prevent other filesystem work (such as CIL pushes) from running. This
  * can lead to deadlocks if the recovery process runs out of log reservation
  * space. Hence we need to yield the CPU when there is other kernel work
  * scheduled on this CPU to ensure other scheduled work can run without undue
@@ -3404,7 +3399,7 @@ xlog_recover(
 
 		/*
 		 * Delay log recovery if the debug hook is set. This is debug
-		 * instrumention to coordinate simulation of I/O failures with
+		 * instrumentation to coordinate simulation of I/O failures with
 		 * log recovery.
 		 */
 		if (xfs_globals.log_recovery_delay) {
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 1c97b155a8ee..cb1e2c4702c3 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -675,6 +675,18 @@ xfs_unmount_flush_inodes(
 	xfs_health_unmount(mp);
 }
 
+static void
+xfs_mount_setup_inode_geom(
+	struct xfs_mount	*mp)
+{
+	struct xfs_ino_geometry *igeo = M_IGEO(mp);
+
+	igeo->attr_fork_offset = xfs_bmap_compute_attr_offset(mp);
+	ASSERT(igeo->attr_fork_offset < XFS_LITINO(mp));
+
+	xfs_ialloc_setup_geometry(mp);
+}
+
 /*
  * This function does the following on an initial mount of a file system:
  *	- reads the superblock from disk and init the mount struct
@@ -758,7 +770,7 @@ xfs_mountfs(
 	xfs_alloc_compute_maxlevels(mp);
 	xfs_bmap_compute_maxlevels(mp, XFS_DATA_FORK);
 	xfs_bmap_compute_maxlevels(mp, XFS_ATTR_FORK);
-	xfs_ialloc_setup_geometry(mp);
+	xfs_mount_setup_inode_geom(mp);
 	xfs_rmapbt_compute_maxlevels(mp);
 	xfs_refcountbt_compute_maxlevels(mp);
 
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 659ad95fe3e0..81829d19596e 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -93,7 +93,7 @@ typedef struct xfs_mount {
 	struct workqueue_struct	*m_unwritten_workqueue;
 	struct workqueue_struct	*m_cil_workqueue;
 	struct workqueue_struct	*m_reclaim_workqueue;
-	struct workqueue_struct *m_blockgc_workqueue;
+	struct workqueue_struct *m_gc_workqueue;
 	struct workqueue_struct	*m_sync_workqueue;
 
 	int			m_bsize;	/* fs logical block size */
diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c
index f3082a957d5e..956cca24e67f 100644
--- a/fs/xfs/xfs_pnfs.c
+++ b/fs/xfs/xfs_pnfs.c
@@ -286,7 +286,7 @@ xfs_fs_commit_blocks(
 	xfs_setattr_time(ip, iattr);
 	if (update_isize) {
 		i_size_write(inode, iattr->ia_size);
-		ip->i_d.di_size = iattr->ia_size;
+		ip->i_disk_size = iattr->ia_size;
 	}
 
 	xfs_trans_set_sync(tp);
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index bfa4164990b1..4bf949a89d0d 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -788,7 +788,7 @@ xfs_qm_qino_alloc(
 
 	if (need_alloc) {
 		error = xfs_dir_ialloc(&init_user_ns, &tp, NULL, S_IFREG, 1, 0,
-				       0, ipp);
+				       0, false, ipp);
 		if (error) {
 			xfs_trans_cancel(tp);
 			return error;
@@ -992,7 +992,7 @@ xfs_qm_reset_dqcounts_buf(
 	 * trans_reserve. But, this gets called during quotacheck, and that
 	 * happens only at mount time which is single threaded.
 	 */
-	if (qip->i_d.di_nblocks == 0)
+	if (qip->i_nblocks == 0)
 		return 0;
 
 	map = kmem_alloc(XFS_DQITER_MAP_SIZE * sizeof(*map), 0);
@@ -1165,16 +1165,14 @@ xfs_qm_dqusage_adjust(
 	if (XFS_IS_REALTIME_INODE(ip)) {
 		struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
 
-		if (!(ifp->if_flags & XFS_IFEXTENTS)) {
-			error = xfs_iread_extents(tp, ip, XFS_DATA_FORK);
-			if (error)
-				goto error0;
-		}
+		error = xfs_iread_extents(tp, ip, XFS_DATA_FORK);
+		if (error)
+			goto error0;
 
 		xfs_bmap_count_leaves(ifp, &rtblks);
 	}
 
-	nblks = (xfs_qcnt_t)ip->i_d.di_nblocks - rtblks;
+	nblks = (xfs_qcnt_t)ip->i_nblocks - rtblks;
 
 	/*
 	 * Add the (disk blocks and inode) resources occupied by this
@@ -1716,7 +1714,7 @@ xfs_qm_vop_dqalloc(
 	}
 	if ((flags & XFS_QMOPT_PQUOTA) && XFS_IS_PQUOTA_ON(mp)) {
 		ASSERT(O_pdqpp);
-		if (ip->i_d.di_projid != prid) {
+		if (ip->i_projid != prid) {
 			xfs_iunlock(ip, lockflags);
 			error = xfs_qm_dqget(mp, prid,
 					XFS_DQTYPE_PROJ, true, &pq);
@@ -1779,11 +1777,11 @@ xfs_qm_vop_chown(
 	ASSERT(prevdq);
 	ASSERT(prevdq != newdq);
 
-	xfs_trans_mod_dquot(tp, prevdq, bfield, -(ip->i_d.di_nblocks));
+	xfs_trans_mod_dquot(tp, prevdq, bfield, -(ip->i_nblocks));
 	xfs_trans_mod_dquot(tp, prevdq, XFS_TRANS_DQ_ICOUNT, -1);
 
 	/* the sparkling new dquot */
-	xfs_trans_mod_dquot(tp, newdq, bfield, ip->i_d.di_nblocks);
+	xfs_trans_mod_dquot(tp, newdq, bfield, ip->i_nblocks);
 	xfs_trans_mod_dquot(tp, newdq, XFS_TRANS_DQ_ICOUNT, 1);
 
 	/*
@@ -1877,7 +1875,7 @@ xfs_qm_vop_create_dqattach(
 	}
 	if (pdqp && XFS_IS_PQUOTA_ON(mp)) {
 		ASSERT(ip->i_pdquot == NULL);
-		ASSERT(ip->i_d.di_projid == pdqp->q_id);
+		ASSERT(ip->i_projid == pdqp->q_id);
 
 		ip->i_pdquot = xfs_qm_dqhold(pdqp);
 		xfs_trans_mod_dquot(tp, pdqp, XFS_TRANS_DQ_ICOUNT, 1);
diff --git a/fs/xfs/xfs_qm_bhv.c b/fs/xfs/xfs_qm_bhv.c
index 639398091ad6..df00dfbf5c9d 100644
--- a/fs/xfs/xfs_qm_bhv.c
+++ b/fs/xfs/xfs_qm_bhv.c
@@ -60,7 +60,7 @@ xfs_qm_statvfs(
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_dquot	*dqp;
 
-	if (!xfs_qm_dqget(mp, ip->i_d.di_projid, XFS_DQTYPE_PROJ, false, &dqp)) {
+	if (!xfs_qm_dqget(mp, ip->i_projid, XFS_DQTYPE_PROJ, false, &dqp)) {
 		xfs_fill_statvfs_from_dquot(statp, dqp);
 		xfs_qm_dqput(dqp);
 	}
diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c
index ca1b57d291dc..11f1e2fbf22f 100644
--- a/fs/xfs/xfs_qm_syscalls.c
+++ b/fs/xfs/xfs_qm_syscalls.c
@@ -293,7 +293,7 @@ xfs_qm_scall_trunc_qfile(
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, 0);
 
-	ip->i_d.di_size = 0;
+	ip->i_disk_size = 0;
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
 	error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, 0);
diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c
index d27c0e852c0b..88d70c236a54 100644
--- a/fs/xfs/xfs_quotaops.c
+++ b/fs/xfs/xfs_quotaops.c
@@ -35,7 +35,7 @@ xfs_qm_fill_state(
 		tempqip = true;
 	}
 	tstate->flags |= QCI_SYSFILE;
-	tstate->blocks = ip->i_d.di_nblocks;
+	tstate->blocks = ip->i_nblocks;
 	tstate->nextents = ip->i_df.if_nextents;
 	tstate->spc_timelimit = (u32)defq->blk.time;
 	tstate->ino_timelimit = (u32)defq->ino.time;
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 725c7d8e4438..4dd4af6ac2ef 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -874,7 +874,7 @@ xfs_reflink_set_inode_flag(
 	if (!xfs_is_reflink_inode(src)) {
 		trace_xfs_reflink_set_inode_flag(src);
 		xfs_trans_ijoin(tp, src, XFS_ILOCK_EXCL);
-		src->i_d.di_flags2 |= XFS_DIFLAG2_REFLINK;
+		src->i_diflags2 |= XFS_DIFLAG2_REFLINK;
 		xfs_trans_log_inode(tp, src, XFS_ILOG_CORE);
 		xfs_ifork_init_cow(src);
 	} else
@@ -886,7 +886,7 @@ xfs_reflink_set_inode_flag(
 	if (!xfs_is_reflink_inode(dest)) {
 		trace_xfs_reflink_set_inode_flag(dest);
 		xfs_trans_ijoin(tp, dest, XFS_ILOCK_EXCL);
-		dest->i_d.di_flags2 |= XFS_DIFLAG2_REFLINK;
+		dest->i_diflags2 |= XFS_DIFLAG2_REFLINK;
 		xfs_trans_log_inode(tp, dest, XFS_ILOG_CORE);
 		xfs_ifork_init_cow(dest);
 	} else
@@ -930,12 +930,12 @@ xfs_reflink_update_dest(
 	if (newlen > i_size_read(VFS_I(dest))) {
 		trace_xfs_reflink_update_inode_size(dest, newlen);
 		i_size_write(VFS_I(dest), newlen);
-		dest->i_d.di_size = newlen;
+		dest->i_disk_size = newlen;
 	}
 
 	if (cowextsize) {
-		dest->i_d.di_cowextsize = cowextsize;
-		dest->i_d.di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
+		dest->i_cowextsize = cowextsize;
+		dest->i_diflags2 |= XFS_DIFLAG2_COWEXTSIZE;
 	}
 
 	xfs_trans_log_inode(tp, dest, XFS_ILOG_CORE);
@@ -1156,7 +1156,7 @@ xfs_reflink_remap_extent(
 	if (newlen > i_size_read(VFS_I(ip))) {
 		trace_xfs_reflink_update_inode_size(ip, newlen);
 		i_size_write(VFS_I(ip), newlen);
-		ip->i_d.di_size = newlen;
+		ip->i_disk_size = newlen;
 		xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 	}
 
@@ -1392,11 +1392,9 @@ xfs_reflink_inode_has_shared_extents(
 	int				error;
 
 	ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
-	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
-		error = xfs_iread_extents(tp, ip, XFS_DATA_FORK);
-		if (error)
-			return error;
-	}
+	error = xfs_iread_extents(tp, ip, XFS_DATA_FORK);
+	if (error)
+		return error;
 
 	*has_shared = false;
 	found = xfs_iext_lookup_extent(ip, ifp, 0, &icur, &got);
@@ -1455,7 +1453,7 @@ xfs_reflink_clear_inode_flag(
 
 	/* Clear the inode flag. */
 	trace_xfs_reflink_unset_inode_flag(ip);
-	ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
+	ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK;
 	xfs_inode_clear_cowblocks_tag(ip);
 	xfs_trans_log_inode(*tpp, ip, XFS_ILOG_CORE);
 
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 161b0e8992ba..4e7be6b4ca8e 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -966,8 +966,8 @@ xfs_growfs_rt(
 	 * Get the old block counts for bitmap and summary inodes.
 	 * These can't change since other growfs callers are locked out.
 	 */
-	rbmblocks = XFS_B_TO_FSB(mp, mp->m_rbmip->i_d.di_size);
-	rsumblocks = XFS_B_TO_FSB(mp, mp->m_rsumip->i_d.di_size);
+	rbmblocks = XFS_B_TO_FSB(mp, mp->m_rbmip->i_disk_size);
+	rsumblocks = XFS_B_TO_FSB(mp, mp->m_rsumip->i_disk_size);
 	/*
 	 * Allocate space to the bitmap and summary files, as necessary.
 	 */
@@ -1036,9 +1036,9 @@ xfs_growfs_rt(
 		 * to update the incore size so that inode inactivation won't
 		 * punch what it thinks are "posteof" blocks.
 		 */
-		mp->m_rbmip->i_d.di_size =
+		mp->m_rbmip->i_disk_size =
 			nsbp->sb_rbmblocks * nsbp->sb_blocksize;
-		i_size_write(VFS_I(mp->m_rbmip), mp->m_rbmip->i_d.di_size);
+		i_size_write(VFS_I(mp->m_rbmip), mp->m_rbmip->i_disk_size);
 		xfs_trans_log_inode(tp, mp->m_rbmip, XFS_ILOG_CORE);
 		/*
 		 * Get the summary inode into the transaction.
@@ -1050,8 +1050,8 @@ xfs_growfs_rt(
 		 * incore size so that inode inactivation won't punch what it
 		 * thinks are "posteof" blocks.
 		 */
-		mp->m_rsumip->i_d.di_size = nmp->m_rsumsize;
-		i_size_write(VFS_I(mp->m_rsumip), mp->m_rsumip->i_d.di_size);
+		mp->m_rsumip->i_disk_size = nmp->m_rsumsize;
+		i_size_write(VFS_I(mp->m_rsumip), mp->m_rsumip->i_disk_size);
 		xfs_trans_log_inode(tp, mp->m_rsumip, XFS_ILOG_CORE);
 		/*
 		 * Copy summary data from old to new sizes.
@@ -1318,8 +1318,8 @@ xfs_rtpick_extent(
 	ASSERT(xfs_isilocked(mp->m_rbmip, XFS_ILOCK_EXCL));
 
 	seqp = (uint64_t *)&VFS_I(mp->m_rbmip)->i_atime;
-	if (!(mp->m_rbmip->i_d.di_flags & XFS_DIFLAG_NEWRTBM)) {
-		mp->m_rbmip->i_d.di_flags |= XFS_DIFLAG_NEWRTBM;
+	if (!(mp->m_rbmip->i_diflags & XFS_DIFLAG_NEWRTBM)) {
+		mp->m_rbmip->i_diflags |= XFS_DIFLAG_NEWRTBM;
 		*seqp = 0;
 	}
 	seq = *seqp;
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index e5e0713bebcd..a2dab05332ac 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -519,10 +519,10 @@ xfs_init_mount_workqueues(
 	if (!mp->m_reclaim_workqueue)
 		goto out_destroy_cil;
 
-	mp->m_blockgc_workqueue = alloc_workqueue("xfs-blockgc/%s",
+	mp->m_gc_workqueue = alloc_workqueue("xfs-gc/%s",
 			WQ_SYSFS | WQ_UNBOUND | WQ_FREEZABLE | WQ_MEM_RECLAIM,
 			0, mp->m_super->s_id);
-	if (!mp->m_blockgc_workqueue)
+	if (!mp->m_gc_workqueue)
 		goto out_destroy_reclaim;
 
 	mp->m_sync_workqueue = alloc_workqueue("xfs-sync/%s",
@@ -533,7 +533,7 @@ xfs_init_mount_workqueues(
 	return 0;
 
 out_destroy_eofb:
-	destroy_workqueue(mp->m_blockgc_workqueue);
+	destroy_workqueue(mp->m_gc_workqueue);
 out_destroy_reclaim:
 	destroy_workqueue(mp->m_reclaim_workqueue);
 out_destroy_cil:
@@ -551,7 +551,7 @@ xfs_destroy_mount_workqueues(
 	struct xfs_mount	*mp)
 {
 	destroy_workqueue(mp->m_sync_workqueue);
-	destroy_workqueue(mp->m_blockgc_workqueue);
+	destroy_workqueue(mp->m_gc_workqueue);
 	destroy_workqueue(mp->m_reclaim_workqueue);
 	destroy_workqueue(mp->m_cil_workqueue);
 	destroy_workqueue(mp->m_unwritten_workqueue);
@@ -834,13 +834,13 @@ xfs_fs_statfs(
 	statp->f_ffree = max_t(int64_t, ffree, 0);
 
 
-	if ((ip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) &&
+	if ((ip->i_diflags & XFS_DIFLAG_PROJINHERIT) &&
 	    ((mp->m_qflags & (XFS_PQUOTA_ACCT|XFS_PQUOTA_ENFD))) ==
 			      (XFS_PQUOTA_ACCT|XFS_PQUOTA_ENFD))
 		xfs_qm_statvfs(ip, statp);
 
 	if (XFS_IS_REALTIME_MOUNT(mp) &&
-	    (ip->i_d.di_flags & (XFS_DIFLAG_RTINHERIT | XFS_DIFLAG_REALTIME))) {
+	    (ip->i_diflags & (XFS_DIFLAG_RTINHERIT | XFS_DIFLAG_REALTIME))) {
 		statp->f_blocks = sbp->sb_rblocks;
 		statp->f_bavail = statp->f_bfree =
 			sbp->sb_frextents * sbp->sb_rextsize;
@@ -1126,6 +1126,22 @@ suffix_kstrtoint(
 	return ret;
 }
 
+static inline void
+xfs_fs_warn_deprecated(
+	struct fs_context	*fc,
+	struct fs_parameter	*param,
+	uint64_t		flag,
+	bool			value)
+{
+	/* Don't print the warning if reconfiguring and current mount point
+	 * already had the flag set
+	 */
+	if ((fc->purpose & FS_CONTEXT_FOR_RECONFIGURE) &&
+			!!(XFS_M(fc->root->d_sb)->m_flags & flag) == value)
+		return;
+	xfs_warn(fc->s_fs_info, "%s mount option is deprecated.", param->key);
+}
+
 /*
  * Set mount state from a mount option.
  *
@@ -1136,7 +1152,7 @@ xfs_fs_parse_param(
 	struct fs_context	*fc,
 	struct fs_parameter	*param)
 {
-	struct xfs_mount	*mp = fc->s_fs_info;
+	struct xfs_mount	*parsing_mp = fc->s_fs_info;
 	struct fs_parse_result	result;
 	int			size = 0;
 	int			opt;
@@ -1147,142 +1163,142 @@ xfs_fs_parse_param(
 
 	switch (opt) {
 	case Opt_logbufs:
-		mp->m_logbufs = result.uint_32;
+		parsing_mp->m_logbufs = result.uint_32;
 		return 0;
 	case Opt_logbsize:
-		if (suffix_kstrtoint(param->string, 10, &mp->m_logbsize))
+		if (suffix_kstrtoint(param->string, 10, &parsing_mp->m_logbsize))
 			return -EINVAL;
 		return 0;
 	case Opt_logdev:
-		kfree(mp->m_logname);
-		mp->m_logname = kstrdup(param->string, GFP_KERNEL);
-		if (!mp->m_logname)
+		kfree(parsing_mp->m_logname);
+		parsing_mp->m_logname = kstrdup(param->string, GFP_KERNEL);
+		if (!parsing_mp->m_logname)
 			return -ENOMEM;
 		return 0;
 	case Opt_rtdev:
-		kfree(mp->m_rtname);
-		mp->m_rtname = kstrdup(param->string, GFP_KERNEL);
-		if (!mp->m_rtname)
+		kfree(parsing_mp->m_rtname);
+		parsing_mp->m_rtname = kstrdup(param->string, GFP_KERNEL);
+		if (!parsing_mp->m_rtname)
 			return -ENOMEM;
 		return 0;
 	case Opt_allocsize:
 		if (suffix_kstrtoint(param->string, 10, &size))
 			return -EINVAL;
-		mp->m_allocsize_log = ffs(size) - 1;
-		mp->m_flags |= XFS_MOUNT_ALLOCSIZE;
+		parsing_mp->m_allocsize_log = ffs(size) - 1;
+		parsing_mp->m_flags |= XFS_MOUNT_ALLOCSIZE;
 		return 0;
 	case Opt_grpid:
 	case Opt_bsdgroups:
-		mp->m_flags |= XFS_MOUNT_GRPID;
+		parsing_mp->m_flags |= XFS_MOUNT_GRPID;
 		return 0;
 	case Opt_nogrpid:
 	case Opt_sysvgroups:
-		mp->m_flags &= ~XFS_MOUNT_GRPID;
+		parsing_mp->m_flags &= ~XFS_MOUNT_GRPID;
 		return 0;
 	case Opt_wsync:
-		mp->m_flags |= XFS_MOUNT_WSYNC;
+		parsing_mp->m_flags |= XFS_MOUNT_WSYNC;
 		return 0;
 	case Opt_norecovery:
-		mp->m_flags |= XFS_MOUNT_NORECOVERY;
+		parsing_mp->m_flags |= XFS_MOUNT_NORECOVERY;
 		return 0;
 	case Opt_noalign:
-		mp->m_flags |= XFS_MOUNT_NOALIGN;
+		parsing_mp->m_flags |= XFS_MOUNT_NOALIGN;
 		return 0;
 	case Opt_swalloc:
-		mp->m_flags |= XFS_MOUNT_SWALLOC;
+		parsing_mp->m_flags |= XFS_MOUNT_SWALLOC;
 		return 0;
 	case Opt_sunit:
-		mp->m_dalign = result.uint_32;
+		parsing_mp->m_dalign = result.uint_32;
 		return 0;
 	case Opt_swidth:
-		mp->m_swidth = result.uint_32;
+		parsing_mp->m_swidth = result.uint_32;
 		return 0;
 	case Opt_inode32:
-		mp->m_flags |= XFS_MOUNT_SMALL_INUMS;
+		parsing_mp->m_flags |= XFS_MOUNT_SMALL_INUMS;
 		return 0;
 	case Opt_inode64:
-		mp->m_flags &= ~XFS_MOUNT_SMALL_INUMS;
+		parsing_mp->m_flags &= ~XFS_MOUNT_SMALL_INUMS;
 		return 0;
 	case Opt_nouuid:
-		mp->m_flags |= XFS_MOUNT_NOUUID;
+		parsing_mp->m_flags |= XFS_MOUNT_NOUUID;
 		return 0;
 	case Opt_largeio:
-		mp->m_flags |= XFS_MOUNT_LARGEIO;
+		parsing_mp->m_flags |= XFS_MOUNT_LARGEIO;
 		return 0;
 	case Opt_nolargeio:
-		mp->m_flags &= ~XFS_MOUNT_LARGEIO;
+		parsing_mp->m_flags &= ~XFS_MOUNT_LARGEIO;
 		return 0;
 	case Opt_filestreams:
-		mp->m_flags |= XFS_MOUNT_FILESTREAMS;
+		parsing_mp->m_flags |= XFS_MOUNT_FILESTREAMS;
 		return 0;
 	case Opt_noquota:
-		mp->m_qflags &= ~XFS_ALL_QUOTA_ACCT;
-		mp->m_qflags &= ~XFS_ALL_QUOTA_ENFD;
-		mp->m_qflags &= ~XFS_ALL_QUOTA_ACTIVE;
+		parsing_mp->m_qflags &= ~XFS_ALL_QUOTA_ACCT;
+		parsing_mp->m_qflags &= ~XFS_ALL_QUOTA_ENFD;
+		parsing_mp->m_qflags &= ~XFS_ALL_QUOTA_ACTIVE;
 		return 0;
 	case Opt_quota:
 	case Opt_uquota:
 	case Opt_usrquota:
-		mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE |
+		parsing_mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE |
 				 XFS_UQUOTA_ENFD);
 		return 0;
 	case Opt_qnoenforce:
 	case Opt_uqnoenforce:
-		mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE);
-		mp->m_qflags &= ~XFS_UQUOTA_ENFD;
+		parsing_mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE);
+		parsing_mp->m_qflags &= ~XFS_UQUOTA_ENFD;
 		return 0;
 	case Opt_pquota:
 	case Opt_prjquota:
-		mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE |
+		parsing_mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE |
 				 XFS_PQUOTA_ENFD);
 		return 0;
 	case Opt_pqnoenforce:
-		mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE);
-		mp->m_qflags &= ~XFS_PQUOTA_ENFD;
+		parsing_mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE);
+		parsing_mp->m_qflags &= ~XFS_PQUOTA_ENFD;
 		return 0;
 	case Opt_gquota:
 	case Opt_grpquota:
-		mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE |
+		parsing_mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE |
 				 XFS_GQUOTA_ENFD);
 		return 0;
 	case Opt_gqnoenforce:
-		mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE);
-		mp->m_qflags &= ~XFS_GQUOTA_ENFD;
+		parsing_mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE);
+		parsing_mp->m_qflags &= ~XFS_GQUOTA_ENFD;
 		return 0;
 	case Opt_discard:
-		mp->m_flags |= XFS_MOUNT_DISCARD;
+		parsing_mp->m_flags |= XFS_MOUNT_DISCARD;
 		return 0;
 	case Opt_nodiscard:
-		mp->m_flags &= ~XFS_MOUNT_DISCARD;
+		parsing_mp->m_flags &= ~XFS_MOUNT_DISCARD;
 		return 0;
 #ifdef CONFIG_FS_DAX
 	case Opt_dax:
-		xfs_mount_set_dax_mode(mp, XFS_DAX_ALWAYS);
+		xfs_mount_set_dax_mode(parsing_mp, XFS_DAX_ALWAYS);
 		return 0;
 	case Opt_dax_enum:
-		xfs_mount_set_dax_mode(mp, result.uint_32);
+		xfs_mount_set_dax_mode(parsing_mp, result.uint_32);
 		return 0;
 #endif
 	/* Following mount options will be removed in September 2025 */
 	case Opt_ikeep:
-		xfs_warn(mp, "%s mount option is deprecated.", param->key);
-		mp->m_flags |= XFS_MOUNT_IKEEP;
+		xfs_fs_warn_deprecated(fc, param, XFS_MOUNT_IKEEP, true);
+		parsing_mp->m_flags |= XFS_MOUNT_IKEEP;
 		return 0;
 	case Opt_noikeep:
-		xfs_warn(mp, "%s mount option is deprecated.", param->key);
-		mp->m_flags &= ~XFS_MOUNT_IKEEP;
+		xfs_fs_warn_deprecated(fc, param, XFS_MOUNT_IKEEP, false);
+		parsing_mp->m_flags &= ~XFS_MOUNT_IKEEP;
 		return 0;
 	case Opt_attr2:
-		xfs_warn(mp, "%s mount option is deprecated.", param->key);
-		mp->m_flags |= XFS_MOUNT_ATTR2;
+		xfs_fs_warn_deprecated(fc, param, XFS_MOUNT_ATTR2, true);
+		parsing_mp->m_flags |= XFS_MOUNT_ATTR2;
 		return 0;
 	case Opt_noattr2:
-		xfs_warn(mp, "%s mount option is deprecated.", param->key);
-		mp->m_flags &= ~XFS_MOUNT_ATTR2;
-		mp->m_flags |= XFS_MOUNT_NOATTR2;
+		xfs_fs_warn_deprecated(fc, param, XFS_MOUNT_NOATTR2, true);
+		parsing_mp->m_flags &= ~XFS_MOUNT_ATTR2;
+		parsing_mp->m_flags |= XFS_MOUNT_NOATTR2;
 		return 0;
 	default:
-		xfs_warn(mp, "unknown mount option [%s].", param->key);
+		xfs_warn(parsing_mp, "unknown mount option [%s].", param->key);
 		return -EINVAL;
 	}
 
@@ -1918,7 +1934,7 @@ xfs_init_zones(void)
 	if (!xfs_ifork_zone)
 		goto out_destroy_da_state_zone;
 
-	xfs_trans_zone = kmem_cache_create("xf_trans",
+	xfs_trans_zone = kmem_cache_create("xfs_trans",
 					   sizeof(struct xfs_trans),
 					   0, 0, NULL);
 	if (!xfs_trans_zone)
diff --git a/fs/xfs/xfs_super.h b/fs/xfs/xfs_super.h
index 1ca484b8357f..d2b40dc60dfc 100644
--- a/fs/xfs/xfs_super.h
+++ b/fs/xfs/xfs_super.h
@@ -86,7 +86,6 @@ struct xfs_mount;
 struct xfs_buftarg;
 struct block_device;
 
-extern void xfs_quiesce_attr(struct xfs_mount *mp);
 extern void xfs_flush_inodes(struct xfs_mount *mp);
 extern void xfs_blkdev_issue_flush(struct xfs_buftarg *);
 extern xfs_agnumber_t xfs_set_inode_alloc(struct xfs_mount *,
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 63edb4dbed4a..99fbec32c10a 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -33,7 +33,7 @@ xfs_readlink_bmap_ilocked(
 	struct xfs_buf		*bp;
 	xfs_daddr_t		d;
 	char			*cur_chunk;
-	int			pathlen = ip->i_d.di_size;
+	int			pathlen = ip->i_disk_size;
 	int			nmaps = XFS_SYMLINK_MAPS;
 	int			byte_cnt;
 	int			n;
@@ -86,7 +86,7 @@ xfs_readlink_bmap_ilocked(
 	}
 	ASSERT(pathlen == 0);
 
-	link[ip->i_d.di_size] = '\0';
+	link[ip->i_disk_size] = '\0';
 	error = 0;
 
  out:
@@ -104,14 +104,14 @@ xfs_readlink(
 
 	trace_xfs_readlink(ip);
 
-	ASSERT(!(ip->i_df.if_flags & XFS_IFINLINE));
+	ASSERT(ip->i_df.if_format != XFS_DINODE_FMT_LOCAL);
 
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
 
 	xfs_ilock(ip, XFS_ILOCK_SHARED);
 
-	pathlen = ip->i_d.di_size;
+	pathlen = ip->i_disk_size;
 	if (!pathlen)
 		goto out;
 
@@ -210,7 +210,7 @@ xfs_symlink(
 	/*
 	 * Check whether the directory allows new symlinks or not.
 	 */
-	if (dp->i_d.di_flags & XFS_DIFLAG_NOSYMLINKS) {
+	if (dp->i_diflags & XFS_DIFLAG_NOSYMLINKS) {
 		error = -EPERM;
 		goto out_trans_cancel;
 	}
@@ -224,7 +224,7 @@ xfs_symlink(
 	 * Allocate an inode for the symlink.
 	 */
 	error = xfs_dir_ialloc(mnt_userns, &tp, dp, S_IFLNK | (mode & ~S_IFMT),
-			       1, 0, prid, &ip);
+			       1, 0, prid, false, &ip);
 	if (error)
 		goto out_trans_cancel;
 
@@ -250,7 +250,7 @@ xfs_symlink(
 	if (pathlen <= XFS_IFORK_DSIZE(ip)) {
 		xfs_init_local_fork(ip, XFS_DATA_FORK, target_path, pathlen);
 
-		ip->i_d.di_size = pathlen;
+		ip->i_disk_size = pathlen;
 		ip->i_df.if_format = XFS_DINODE_FMT_LOCAL;
 		xfs_trans_log_inode(tp, ip, XFS_ILOG_DDATA | XFS_ILOG_CORE);
 	} else {
@@ -265,7 +265,7 @@ xfs_symlink(
 			goto out_trans_cancel;
 
 		resblks -= fs_blocks;
-		ip->i_d.di_size = pathlen;
+		ip->i_disk_size = pathlen;
 		xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
 		cur_chunk = target_path;
@@ -300,7 +300,7 @@ xfs_symlink(
 		}
 		ASSERT(pathlen == 0);
 	}
-	i_size_write(VFS_I(ip), ip->i_d.di_size);
+	i_size_write(VFS_I(ip), ip->i_disk_size);
 
 	/*
 	 * Create the directory entry for the symlink.
@@ -377,7 +377,7 @@ xfs_inactive_symlink_rmt(
 	xfs_trans_t	*tp;
 
 	mp = ip->i_mount;
-	ASSERT(ip->i_df.if_flags & XFS_IFEXTENTS);
+	ASSERT(!xfs_need_iread_extents(&ip->i_df));
 	/*
 	 * We're freeing a symlink that has some
 	 * blocks allocated to it.  Free the
@@ -400,8 +400,8 @@ xfs_inactive_symlink_rmt(
 	 * locked for the second transaction.  In the error paths we need it
 	 * held so the cancel won't rele it, see below.
 	 */
-	size = (int)ip->i_d.di_size;
-	ip->i_d.di_size = 0;
+	size = (int)ip->i_disk_size;
+	ip->i_disk_size = 0;
 	VFS_I(ip)->i_mode = (VFS_I(ip)->i_mode & ~S_IFMT) | S_IFREG;
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 	/*
@@ -477,7 +477,7 @@ xfs_inactive_symlink(
 		return -EIO;
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	pathlen = (int)ip->i_d.di_size;
+	pathlen = (int)ip->i_disk_size;
 	ASSERT(pathlen);
 
 	if (pathlen <= 0 || pathlen > XFS_SYMLINK_MAXLEN) {
@@ -492,7 +492,7 @@ xfs_inactive_symlink(
 	 * Inline fork state gets removed by xfs_difree() so we have nothing to
 	 * do here in that case.
 	 */
-	if (ip->i_df.if_flags & XFS_IFINLINE) {
+	if (ip->i_df.if_format == XFS_DINODE_FMT_LOCAL) {
 		xfs_iunlock(ip, XFS_ILOCK_EXCL);
 		return 0;
 	}
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index e74bbb648f83..808ae337b222 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -1298,7 +1298,7 @@ DECLARE_EVENT_CLASS(xfs_file_class,
 	TP_fast_assign(
 		__entry->dev = file_inode(iocb->ki_filp)->i_sb->s_dev;
 		__entry->ino = XFS_I(file_inode(iocb->ki_filp))->i_ino;
-		__entry->size = XFS_I(file_inode(iocb->ki_filp))->i_d.di_size;
+		__entry->size = XFS_I(file_inode(iocb->ki_filp))->i_disk_size;
 		__entry->offset = iocb->ki_pos;
 		__entry->count = iov_iter_count(iter);
 	),
@@ -1341,7 +1341,7 @@ DECLARE_EVENT_CLASS(xfs_imap_class,
 	TP_fast_assign(
 		__entry->dev = VFS_I(ip)->i_sb->s_dev;
 		__entry->ino = ip->i_ino;
-		__entry->size = ip->i_d.di_size;
+		__entry->size = ip->i_disk_size;
 		__entry->offset = offset;
 		__entry->count = count;
 		__entry->whichfork = whichfork;
@@ -1387,7 +1387,7 @@ DECLARE_EVENT_CLASS(xfs_simple_io_class,
 		__entry->dev = VFS_I(ip)->i_sb->s_dev;
 		__entry->ino = ip->i_ino;
 		__entry->isize = VFS_I(ip)->i_size;
-		__entry->disize = ip->i_d.di_size;
+		__entry->disize = ip->i_disk_size;
 		__entry->offset = offset;
 		__entry->count = count;
 	),
@@ -1425,7 +1425,7 @@ DECLARE_EVENT_CLASS(xfs_itrunc_class,
 	TP_fast_assign(
 		__entry->dev = VFS_I(ip)->i_sb->s_dev;
 		__entry->ino = ip->i_ino;
-		__entry->size = ip->i_d.di_size;
+		__entry->size = ip->i_disk_size;
 		__entry->new_size = new_size;
 	),
 	TP_printk("dev %d:%d ino 0x%llx size 0x%llx new_size 0x%llx",
@@ -1455,7 +1455,7 @@ TRACE_EVENT(xfs_pagecache_inval,
 	TP_fast_assign(
 		__entry->dev = VFS_I(ip)->i_sb->s_dev;
 		__entry->ino = ip->i_ino;
-		__entry->size = ip->i_d.di_size;
+		__entry->size = ip->i_disk_size;
 		__entry->start = start;
 		__entry->finish = finish;
 	),
@@ -1483,7 +1483,7 @@ TRACE_EVENT(xfs_bunmap,
 	TP_fast_assign(
 		__entry->dev = VFS_I(ip)->i_sb->s_dev;
 		__entry->ino = ip->i_ino;
-		__entry->size = ip->i_d.di_size;
+		__entry->size = ip->i_disk_size;
 		__entry->bno = bno;
 		__entry->len = len;
 		__entry->caller_ip = caller_ip;
@@ -3145,12 +3145,12 @@ DECLARE_EVENT_CLASS(xfs_double_io_class,
 		__entry->dev = VFS_I(src)->i_sb->s_dev;
 		__entry->src_ino = src->i_ino;
 		__entry->src_isize = VFS_I(src)->i_size;
-		__entry->src_disize = src->i_d.di_size;
+		__entry->src_disize = src->i_disk_size;
 		__entry->src_offset = soffset;
 		__entry->len = len;
 		__entry->dest_ino = dest->i_ino;
 		__entry->dest_isize = VFS_I(dest)->i_size;
-		__entry->dest_disize = dest->i_d.di_size;
+		__entry->dest_disize = dest->i_disk_size;
 		__entry->dest_offset = doffset;
 	),
 	TP_printk("dev %d:%d count %zd "
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index b22a09e9daee..bcc978011869 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -436,7 +436,6 @@ xfs_trans_mod_sb(
 		tp->t_res_frextents_delta += delta;
 		break;
 	case XFS_TRANS_SB_DBLOCKS:
-		ASSERT(delta > 0);
 		tp->t_dblocks_delta += delta;
 		break;
 	case XFS_TRANS_SB_AGCOUNT:
@@ -618,19 +617,12 @@ xfs_trans_unreserve_and_mod_sb(
 		ASSERT(!error);
 	}
 
-	if (idelta) {
+	if (idelta)
 		percpu_counter_add_batch(&mp->m_icount, idelta,
 					 XFS_ICOUNT_BATCH);
-		if (idelta < 0)
-			ASSERT(__percpu_counter_compare(&mp->m_icount, 0,
-							XFS_ICOUNT_BATCH) >= 0);
-	}
 
-	if (ifreedelta) {
+	if (ifreedelta)
 		percpu_counter_add(&mp->m_ifree, ifreedelta);
-		if (ifreedelta < 0)
-			ASSERT(percpu_counter_compare(&mp->m_ifree, 0) >= 0);
-	}
 
 	if (rtxdelta == 0 && !(tp->t_flags & XFS_TRANS_SB_DIRTY))
 		return;
@@ -1197,7 +1189,7 @@ retry:
 		 * though that part is only semi-transactional.
 		 */
 		error = xfs_trans_reserve_quota_bydquots(tp, mp, udqp, gdqp,
-				pdqp, ip->i_d.di_nblocks + ip->i_delayed_blks,
+				pdqp, ip->i_nblocks + ip->i_delayed_blks,
 				1, qflags);
 		if ((error == -EDQUOT || error == -ENOSPC) && !retried) {
 			xfs_trans_cancel(tp);
diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c
index 12be32f66dc1..0d050f8829ef 100644
--- a/fs/xfs/xfs_xattr.c
+++ b/fs/xfs/xfs_xattr.c
@@ -9,6 +9,8 @@
 #include "xfs_format.h"
 #include "xfs_log_format.h"
 #include "xfs_da_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
 #include "xfs_inode.h"
 #include "xfs_attr.h"
 #include "xfs_acl.h"