Merge branch 'for-linus' of git://oss.sgi.com/xfs/xfs

* 'for-linus' of git://oss.sgi.com/xfs/xfs:
  xfs: cleanup xfs_file_aio_write
  xfs: always return with the iolock held from xfs_file_aio_write_checks
  xfs: remove the i_new_size field in struct xfs_inode
  xfs: remove the i_size field in struct xfs_inode
  xfs: replace i_pin_wait with a bit waitqueue
  xfs: replace i_flock with a sleeping bitlock
  xfs: make i_flags an unsigned long
  xfs: remove the if_ext_max field in struct xfs_ifork
  xfs: remove the unused dm_attrs structure
  xfs: cleanup xfs_iomap_eof_align_last_fsb
  xfs: remove xfs_itruncate_data

18 files changed, 374 insertions, 542 deletions

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 574d4ee9b625..74b9baf36ac3 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -111,8 +111,7 @@ xfs_ioend_new_eof(
 	xfs_fsize_t		bsize;
 
 	bsize = ioend->io_offset + ioend->io_size;
-	isize = MAX(ip->i_size, ip->i_new_size);
-	isize = MIN(isize, bsize);
+	isize = MIN(i_size_read(VFS_I(ip)), bsize);
 	return isize > ip->i_d.di_size ? isize : 0;
 }
 
@@ -126,11 +125,7 @@ static inline bool xfs_ioend_is_append(struct xfs_ioend *ioend)
 }
 
 /*
- * Update on-disk file size now that data has been written to disk.  The
- * current in-memory file size is i_size.  If a write is beyond eof i_new_size
- * will be the intended file size until i_size is updated.  If this write does
- * not extend all the way to the valid file size then restrict this update to
- * the end of the write.
+ * Update on-disk file size now that data has been written to disk.
  *
  * This function does not block as blocking on the inode lock in IO completion
  * can lead to IO completion order dependency deadlocks.. If it can't get the
@@ -1279,6 +1274,15 @@ xfs_end_io_direct_write(
 	struct xfs_ioend	*ioend = iocb->private;
 
 	/*
+	 * While the generic direct I/O code updates the inode size, it does
+	 * so only after the end_io handler is called, which means our
+	 * end_io handler thinks the on-disk size is outside the in-core
+	 * size.  To prevent this just update it a little bit earlier here.
+	 */
+	if (offset + size > i_size_read(ioend->io_inode))
+		i_size_write(ioend->io_inode, offset + size);
+
+	/*
 	 * blockdev_direct_IO can return an error even after the I/O
 	 * completion handler was called.  Thus we need to protect
 	 * against double-freeing.
@@ -1340,12 +1344,11 @@ xfs_vm_write_failed(
 
 	if (to > inode->i_size) {
 		/*
-		 * punch out the delalloc blocks we have already allocated. We
-		 * don't call xfs_setattr() to do this as we may be in the
-		 * middle of a multi-iovec write and so the vfs inode->i_size
-		 * will not match the xfs ip->i_size and so it will zero too
-		 * much. Hence we jus truncate the page cache to zero what is
-		 * necessary and punch the delalloc blocks directly.
+		 * Punch out the delalloc blocks we have already allocated.
+		 *
+		 * Don't bother with xfs_setattr given that nothing can have
+		 * made it to disk yet as the page is still locked at this
+		 * point.
 		 */
 		struct xfs_inode	*ip = XFS_I(inode);
 		xfs_fileoff_t		start_fsb;
diff --git a/fs/xfs/xfs_attr.c b/fs/xfs/xfs_attr.c
index 1e5d97f86ea8..08b9ac644c31 100644
--- a/fs/xfs/xfs_attr.c
+++ b/fs/xfs/xfs_attr.c
@@ -827,10 +827,6 @@ xfs_attr_inactive(xfs_inode_t *dp)
 	if (error)
 		goto out;
 
-	/*
-	 * Commit the last in the sequence of transactions.
-	 */
-	xfs_trans_log_inode(trans, dp, XFS_ILOG_CORE);
 	error = xfs_trans_commit(trans, XFS_TRANS_RELEASE_LOG_RES);
 	xfs_iunlock(dp, XFS_ILOCK_EXCL);
 
diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c
index c1b55e596551..d25eafd4d28d 100644
--- a/fs/xfs/xfs_attr_leaf.c
+++ b/fs/xfs/xfs_attr_leaf.c
@@ -271,10 +271,6 @@ xfs_attr_shortform_add(xfs_da_args_t *args, int forkoff)
 	dp = args->dp;
 	mp = dp->i_mount;
 	dp->i_d.di_forkoff = forkoff;
-	dp->i_df.if_ext_max =
-		XFS_IFORK_DSIZE(dp) / (uint)sizeof(xfs_bmbt_rec_t);
-	dp->i_afp->if_ext_max =
-		XFS_IFORK_ASIZE(dp) / (uint)sizeof(xfs_bmbt_rec_t);
 
 	ifp = dp->i_afp;
 	ASSERT(ifp->if_flags & XFS_IFINLINE);
@@ -326,7 +322,6 @@ xfs_attr_fork_reset(
 	ASSERT(ip->i_d.di_anextents == 0);
 	ASSERT(ip->i_afp == NULL);
 
-	ip->i_df.if_ext_max = XFS_IFORK_DSIZE(ip) / sizeof(xfs_bmbt_rec_t);
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 }
 
@@ -389,10 +384,6 @@ xfs_attr_shortform_remove(xfs_da_args_t *args)
 				(args->op_flags & XFS_DA_OP_ADDNAME) ||
 				!(mp->m_flags & XFS_MOUNT_ATTR2) ||
 				dp->i_d.di_format == XFS_DINODE_FMT_BTREE);
-		dp->i_afp->if_ext_max =
-			XFS_IFORK_ASIZE(dp) / (uint)sizeof(xfs_bmbt_rec_t);
-		dp->i_df.if_ext_max =
-			XFS_IFORK_DSIZE(dp) / (uint)sizeof(xfs_bmbt_rec_t);
 		xfs_trans_log_inode(args->trans, dp,
 					XFS_ILOG_CORE | XFS_ILOG_ADATA);
 	}
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index d0ab78837057..188ef2fbd628 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -249,7 +249,27 @@ xfs_bmbt_lookup_ge(
 }
 
 /*
-* Update the record referred to by cur to the value given
+ * Check if the inode needs to be converted to btree format.
+ */
+static inline bool xfs_bmap_needs_btree(struct xfs_inode *ip, int whichfork)
+{
+	return XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS &&
+		XFS_IFORK_NEXTENTS(ip, whichfork) >
+			XFS_IFORK_MAXEXT(ip, whichfork);
+}
+
+/*
+ * Check if the inode should be converted to extent format.
+ */
+static inline bool xfs_bmap_wants_extents(struct xfs_inode *ip, int whichfork)
+{
+	return XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE &&
+		XFS_IFORK_NEXTENTS(ip, whichfork) <=
+			XFS_IFORK_MAXEXT(ip, whichfork);
+}
+
+/*
+ * Update the record referred to by cur to the value given
  * by [off, bno, len, state].
  * This either works (return 0) or gets an EFSCORRUPTED error.
  */
@@ -683,8 +703,8 @@ xfs_bmap_add_extent_delay_real(
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
 		}
-		if (bma->ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
-		    bma->ip->i_d.di_nextents > bma->ip->i_df.if_ext_max) {
+
+		if (xfs_bmap_needs_btree(bma->ip, XFS_DATA_FORK)) {
 			error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
 					bma->firstblock, bma->flist,
 					&bma->cur, 1, &tmp_rval, XFS_DATA_FORK);
@@ -767,8 +787,8 @@ xfs_bmap_add_extent_delay_real(
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
 		}
-		if (bma->ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
-		    bma->ip->i_d.di_nextents > bma->ip->i_df.if_ext_max) {
+
+		if (xfs_bmap_needs_btree(bma->ip, XFS_DATA_FORK)) {
 			error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
 				bma->firstblock, bma->flist, &bma->cur, 1,
 				&tmp_rval, XFS_DATA_FORK);
@@ -836,8 +856,8 @@ xfs_bmap_add_extent_delay_real(
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
 		}
-		if (bma->ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
-		    bma->ip->i_d.di_nextents > bma->ip->i_df.if_ext_max) {
+
+		if (xfs_bmap_needs_btree(bma->ip, XFS_DATA_FORK)) {
 			error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
 					bma->firstblock, bma->flist, &bma->cur,
 					1, &tmp_rval, XFS_DATA_FORK);
@@ -884,8 +904,7 @@ xfs_bmap_add_extent_delay_real(
 	}
 
 	/* convert to a btree if necessary */
-	if (XFS_IFORK_FORMAT(bma->ip, XFS_DATA_FORK) == XFS_DINODE_FMT_EXTENTS &&
-	    XFS_IFORK_NEXTENTS(bma->ip, XFS_DATA_FORK) > ifp->if_ext_max) {
+	if (xfs_bmap_needs_btree(bma->ip, XFS_DATA_FORK)) {
 		int	tmp_logflags;	/* partial log flag return val */
 
 		ASSERT(bma->cur == NULL);
@@ -1421,8 +1440,7 @@ xfs_bmap_add_extent_unwritten_real(
 	}
 
 	/* convert to a btree if necessary */
-	if (XFS_IFORK_FORMAT(ip, XFS_DATA_FORK) == XFS_DINODE_FMT_EXTENTS &&
-	    XFS_IFORK_NEXTENTS(ip, XFS_DATA_FORK) > ifp->if_ext_max) {
+	if (xfs_bmap_needs_btree(ip, XFS_DATA_FORK)) {
 		int	tmp_logflags;	/* partial log flag return val */
 
 		ASSERT(cur == NULL);
@@ -1812,8 +1830,7 @@ xfs_bmap_add_extent_hole_real(
 	}
 
 	/* convert to a btree if necessary */
-	if (XFS_IFORK_FORMAT(bma->ip, whichfork) == XFS_DINODE_FMT_EXTENTS &&
-	    XFS_IFORK_NEXTENTS(bma->ip, whichfork) > ifp->if_ext_max) {
+	if (xfs_bmap_needs_btree(bma->ip, whichfork)) {
 		int	tmp_logflags;	/* partial log flag return val */
 
 		ASSERT(bma->cur == NULL);
@@ -3037,8 +3054,7 @@ xfs_bmap_extents_to_btree(
 
 	ifp = XFS_IFORK_PTR(ip, whichfork);
 	ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS);
-	ASSERT(ifp->if_ext_max ==
-	       XFS_IFORK_SIZE(ip, whichfork) / (uint)sizeof(xfs_bmbt_rec_t));
+
 	/*
 	 * Make space in the inode incore.
 	 */
@@ -3184,13 +3200,8 @@ xfs_bmap_forkoff_reset(
 	    ip->i_d.di_format != XFS_DINODE_FMT_BTREE) {
 		uint	dfl_forkoff = xfs_default_attroffset(ip) >> 3;
 
-		if (dfl_forkoff > ip->i_d.di_forkoff) {
+		if (dfl_forkoff > ip->i_d.di_forkoff)
 			ip->i_d.di_forkoff = dfl_forkoff;
-			ip->i_df.if_ext_max =
-				XFS_IFORK_DSIZE(ip) / sizeof(xfs_bmbt_rec_t);
-			ip->i_afp->if_ext_max =
-				XFS_IFORK_ASIZE(ip) / sizeof(xfs_bmbt_rec_t);
-		}
 	}
 }
 
@@ -3430,8 +3441,6 @@ xfs_bmap_add_attrfork(
 	int			error;		/* error return value */
 
 	ASSERT(XFS_IFORK_Q(ip) == 0);
-	ASSERT(ip->i_df.if_ext_max ==
-	       XFS_IFORK_DSIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t));
 
 	mp = ip->i_mount;
 	ASSERT(!XFS_NOT_DQATTACHED(mp, ip));
@@ -3486,12 +3495,9 @@ xfs_bmap_add_attrfork(
 		error = XFS_ERROR(EINVAL);
 		goto error1;
 	}
-	ip->i_df.if_ext_max =
-		XFS_IFORK_DSIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t);
+
 	ASSERT(ip->i_afp == NULL);
 	ip->i_afp = kmem_zone_zalloc(xfs_ifork_zone, KM_SLEEP);
-	ip->i_afp->if_ext_max =
-		XFS_IFORK_ASIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t);
 	ip->i_afp->if_flags = XFS_IFEXTENTS;
 	logflags = 0;
 	xfs_bmap_init(&flist, &firstblock);
@@ -3535,20 +3541,17 @@ xfs_bmap_add_attrfork(
 		} else
 			spin_unlock(&mp->m_sb_lock);
 	}
-	if ((error = xfs_bmap_finish(&tp, &flist, &committed)))
+
+	error = xfs_bmap_finish(&tp, &flist, &committed);
+	if (error)
 		goto error2;
-	error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
-	ASSERT(ip->i_df.if_ext_max ==
-	       XFS_IFORK_DSIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t));
-	return error;
+	return xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
 error2:
 	xfs_bmap_cancel(&flist);
 error1:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 error0:
 	xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES|XFS_TRANS_ABORT);
-	ASSERT(ip->i_df.if_ext_max ==
-	       XFS_IFORK_DSIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t));
 	return error;
 }
 
@@ -3994,11 +3997,8 @@ xfs_bmap_one_block(
 	xfs_bmbt_irec_t	s;		/* internal version of extent */
 
 #ifndef DEBUG
-	if (whichfork == XFS_DATA_FORK) {
-		return S_ISREG(ip->i_d.di_mode) ?
-			(ip->i_size == ip->i_mount->m_sb.sb_blocksize) :
-			(ip->i_d.di_size == ip->i_mount->m_sb.sb_blocksize);
-	}
+	if (whichfork == XFS_DATA_FORK)
+		return XFS_ISIZE(ip) == ip->i_mount->m_sb.sb_blocksize;
 #endif	/* !DEBUG */
 	if (XFS_IFORK_NEXTENTS(ip, whichfork) != 1)
 		return 0;
@@ -4010,7 +4010,7 @@ xfs_bmap_one_block(
 	xfs_bmbt_get_all(ep, &s);
 	rval = s.br_startoff == 0 && s.br_blockcount == 1;
 	if (rval && whichfork == XFS_DATA_FORK)
-		ASSERT(ip->i_size == ip->i_mount->m_sb.sb_blocksize);
+		ASSERT(XFS_ISIZE(ip) == ip->i_mount->m_sb.sb_blocksize);
 	return rval;
 }
 
@@ -4379,8 +4379,6 @@ xfs_bmapi_read(
 	XFS_STATS_INC(xs_blk_mapr);
 
 	ifp = XFS_IFORK_PTR(ip, whichfork);
-	ASSERT(ifp->if_ext_max ==
-	       XFS_IFORK_SIZE(ip, whichfork) / (uint)sizeof(xfs_bmbt_rec_t));
 
 	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
 		error = xfs_iread_extents(NULL, ip, whichfork);
@@ -4871,8 +4869,6 @@ xfs_bmapi_write(
 		return XFS_ERROR(EIO);
 
 	ifp = XFS_IFORK_PTR(ip, whichfork);
-	ASSERT(ifp->if_ext_max ==
-	       XFS_IFORK_SIZE(ip, whichfork) / (uint)sizeof(xfs_bmbt_rec_t));
 
 	XFS_STATS_INC(xs_blk_mapw);
 
@@ -4981,8 +4977,7 @@ xfs_bmapi_write(
 	/*
 	 * Transform from btree to extents, give it cur.
 	 */
-	if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE &&
-	    XFS_IFORK_NEXTENTS(ip, whichfork) <= ifp->if_ext_max) {
+	if (xfs_bmap_wants_extents(ip, whichfork)) {
 		int		tmp_logflags = 0;
 
 		ASSERT(bma.cur);
@@ -4992,10 +4987,10 @@ xfs_bmapi_write(
 		if (error)
 			goto error0;
 	}
-	ASSERT(ifp->if_ext_max ==
-	       XFS_IFORK_SIZE(ip, whichfork) / (uint)sizeof(xfs_bmbt_rec_t));
+
 	ASSERT(XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE ||
-	       XFS_IFORK_NEXTENTS(ip, whichfork) > ifp->if_ext_max);
+	       XFS_IFORK_NEXTENTS(ip, whichfork) >
+		XFS_IFORK_MAXEXT(ip, whichfork));
 	error = 0;
 error0:
 	/*
@@ -5095,8 +5090,7 @@ xfs_bunmapi(
 
 	ASSERT(len > 0);
 	ASSERT(nexts >= 0);
-	ASSERT(ifp->if_ext_max ==
-	       XFS_IFORK_SIZE(ip, whichfork) / (uint)sizeof(xfs_bmbt_rec_t));
+
 	if (!(ifp->if_flags & XFS_IFEXTENTS) &&
 	    (error = xfs_iread_extents(tp, ip, whichfork)))
 		return error;
@@ -5322,7 +5316,8 @@ xfs_bunmapi(
 		 */
 		if (!wasdel && xfs_trans_get_block_res(tp) == 0 &&
 		    XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS &&
-		    XFS_IFORK_NEXTENTS(ip, whichfork) >= ifp->if_ext_max &&
+		    XFS_IFORK_NEXTENTS(ip, whichfork) >= /* Note the >= */
+			XFS_IFORK_MAXEXT(ip, whichfork) &&
 		    del.br_startoff > got.br_startoff &&
 		    del.br_startoff + del.br_blockcount <
 		    got.br_startoff + got.br_blockcount) {
@@ -5353,13 +5348,11 @@ nodelete:
 		}
 	}
 	*done = bno == (xfs_fileoff_t)-1 || bno < start || lastx < 0;
-	ASSERT(ifp->if_ext_max ==
-	       XFS_IFORK_SIZE(ip, whichfork) / (uint)sizeof(xfs_bmbt_rec_t));
+
 	/*
 	 * Convert to a btree if necessary.
 	 */
-	if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS &&
-	    XFS_IFORK_NEXTENTS(ip, whichfork) > ifp->if_ext_max) {
+	if (xfs_bmap_needs_btree(ip, whichfork)) {
 		ASSERT(cur == NULL);
 		error = xfs_bmap_extents_to_btree(tp, ip, firstblock, flist,
 			&cur, 0, &tmp_logflags, whichfork);
@@ -5370,8 +5363,7 @@ nodelete:
 	/*
 	 * transform from btree to extents, give it cur
 	 */
-	else if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE &&
-		 XFS_IFORK_NEXTENTS(ip, whichfork) <= ifp->if_ext_max) {
+	else if (xfs_bmap_wants_extents(ip, whichfork)) {
 		ASSERT(cur != NULL);
 		error = xfs_bmap_btree_to_extents(tp, ip, cur, &tmp_logflags,
 			whichfork);
@@ -5382,8 +5374,6 @@ nodelete:
 	/*
 	 * transform from extents to local?
 	 */
-	ASSERT(ifp->if_ext_max ==
-	       XFS_IFORK_SIZE(ip, whichfork) / (uint)sizeof(xfs_bmbt_rec_t));
 	error = 0;
 error0:
 	/*
@@ -5434,7 +5424,7 @@ xfs_getbmapx_fix_eof_hole(
 	if (startblock == HOLESTARTBLOCK) {
 		mp = ip->i_mount;
 		out->bmv_block = -1;
-		fixlen = XFS_FSB_TO_BB(mp, XFS_B_TO_FSB(mp, ip->i_size));
+		fixlen = XFS_FSB_TO_BB(mp, XFS_B_TO_FSB(mp, XFS_ISIZE(ip)));
 		fixlen -= out->bmv_offset;
 		if (prealloced && out->bmv_offset + out->bmv_length == end) {
 			/* Came to hole at EOF. Trim it. */
@@ -5522,7 +5512,7 @@ xfs_getbmap(
 			fixlen = XFS_MAXIOFFSET(mp);
 		} else {
 			prealloced = 0;
-			fixlen = ip->i_size;
+			fixlen = XFS_ISIZE(ip);
 		}
 	}
 
@@ -5551,7 +5541,7 @@ xfs_getbmap(
 
 	xfs_ilock(ip, XFS_IOLOCK_SHARED);
 	if (whichfork == XFS_DATA_FORK && !(iflags & BMV_IF_DELALLOC)) {
-		if (ip->i_delayed_blks || ip->i_size > ip->i_d.di_size) {
+		if (ip->i_delayed_blks || XFS_ISIZE(ip) > ip->i_d.di_size) {
 			error = xfs_flush_pages(ip, 0, -1, 0, FI_REMAPF);
 			if (error)
 				goto out_unlock_iolock;
diff --git a/fs/xfs/xfs_dfrag.c b/fs/xfs/xfs_dfrag.c
index 654dc6f05bac..dd974a55c77d 100644
--- a/fs/xfs/xfs_dfrag.c
+++ b/fs/xfs/xfs_dfrag.c
@@ -163,12 +163,14 @@ xfs_swap_extents_check_format(
 
 	/* Check temp in extent form to max in target */
 	if (tip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
-	    XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK) > ip->i_df.if_ext_max)
+	    XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK) >
+			XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK))
 		return EINVAL;
 
 	/* Check target in extent form to max in temp */
 	if (ip->i_d.di_format == XFS_DINODE_FMT_EXTENTS &&
-	    XFS_IFORK_NEXTENTS(ip, XFS_DATA_FORK) > tip->i_df.if_ext_max)
+	    XFS_IFORK_NEXTENTS(ip, XFS_DATA_FORK) >
+			XFS_IFORK_MAXEXT(tip, XFS_DATA_FORK))
 		return EINVAL;
 
 	/*
@@ -180,18 +182,25 @@ xfs_swap_extents_check_format(
 	 * (a common defrag case) which will occur when the temp inode is in
 	 * extent format...
 	 */
-	if (tip->i_d.di_format == XFS_DINODE_FMT_BTREE &&
-	    ((XFS_IFORK_BOFF(ip) &&
-	      tip->i_df.if_broot_bytes > XFS_IFORK_BOFF(ip)) ||
-	     XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK) <= ip->i_df.if_ext_max))
-		return EINVAL;
+	if (tip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
+		if (XFS_IFORK_BOFF(ip) &&
+		    tip->i_df.if_broot_bytes > XFS_IFORK_BOFF(ip))
+			return EINVAL;
+		if (XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK) <=
+		    XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK))
+			return EINVAL;
+	}
 
 	/* Reciprocal target->temp btree format checks */
-	if (ip->i_d.di_format == XFS_DINODE_FMT_BTREE &&
-	    ((XFS_IFORK_BOFF(tip) &&
-	      ip->i_df.if_broot_bytes > XFS_IFORK_BOFF(tip)) ||
-	     XFS_IFORK_NEXTENTS(ip, XFS_DATA_FORK) <= tip->i_df.if_ext_max))
-		return EINVAL;
+	if (ip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
+		if (XFS_IFORK_BOFF(tip) &&
+		    ip->i_df.if_broot_bytes > XFS_IFORK_BOFF(tip))
+			return EINVAL;
+
+		if (XFS_IFORK_NEXTENTS(ip, XFS_DATA_FORK) <=
+		    XFS_IFORK_MAXEXT(tip, XFS_DATA_FORK))
+			return EINVAL;
+	}
 
 	return 0;
 }
@@ -349,16 +358,6 @@ xfs_swap_extents(
 	*tifp = *tempifp;	/* struct copy */
 
 	/*
-	 * Fix the in-memory data fork values that are dependent on the fork
-	 * offset in the inode. We can't assume they remain the same as attr2
-	 * has dynamic fork offsets.
-	 */
-	ifp->if_ext_max = XFS_IFORK_SIZE(ip, XFS_DATA_FORK) /
-					(uint)sizeof(xfs_bmbt_rec_t);
-	tifp->if_ext_max = XFS_IFORK_SIZE(tip, XFS_DATA_FORK) /
-					(uint)sizeof(xfs_bmbt_rec_t);
-
-	/*
 	 * Fix the on-disk inode values
 	 */
 	tmp = (__uint64_t)ip->i_d.di_nblocks;
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index f675f3d9d7b3..7e5bc872f2b4 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -327,7 +327,7 @@ xfs_file_aio_read(
 				mp->m_rtdev_targp : mp->m_ddev_targp;
 		if ((iocb->ki_pos & target->bt_smask) ||
 		    (size & target->bt_smask)) {
-			if (iocb->ki_pos == ip->i_size)
+			if (iocb->ki_pos == i_size_read(inode))
 				return 0;
 			return -XFS_ERROR(EINVAL);
 		}
@@ -412,51 +412,6 @@ xfs_file_splice_read(
 	return ret;
 }
 
-STATIC void
-xfs_aio_write_isize_update(
-	struct inode	*inode,
-	loff_t		*ppos,
-	ssize_t		bytes_written)
-{
-	struct xfs_inode	*ip = XFS_I(inode);
-	xfs_fsize_t		isize = i_size_read(inode);
-
-	if (bytes_written > 0)
-		XFS_STATS_ADD(xs_write_bytes, bytes_written);
-
-	if (unlikely(bytes_written < 0 && bytes_written != -EFAULT &&
-					*ppos > isize))
-		*ppos = isize;
-
-	if (*ppos > ip->i_size) {
-		xfs_rw_ilock(ip, XFS_ILOCK_EXCL);
-		if (*ppos > ip->i_size)
-			ip->i_size = *ppos;
-		xfs_rw_iunlock(ip, XFS_ILOCK_EXCL);
-	}
-}
-
-/*
- * If this was a direct or synchronous I/O that failed (such as ENOSPC) then
- * part of the I/O may have been written to disk before the error occurred.  In
- * this case the on-disk file size may have been adjusted beyond the in-memory
- * file size and now needs to be truncated back.
- */
-STATIC void
-xfs_aio_write_newsize_update(
-	struct xfs_inode	*ip,
-	xfs_fsize_t		new_size)
-{
-	if (new_size == ip->i_new_size) {
-		xfs_rw_ilock(ip, XFS_ILOCK_EXCL);
-		if (new_size == ip->i_new_size)
-			ip->i_new_size = 0;
-		if (ip->i_d.di_size > ip->i_size)
-			ip->i_d.di_size = ip->i_size;
-		xfs_rw_iunlock(ip, XFS_ILOCK_EXCL);
-	}
-}
-
 /*
  * xfs_file_splice_write() does not use xfs_rw_ilock() because
  * generic_file_splice_write() takes the i_mutex itself. This, in theory,
@@ -475,7 +430,6 @@ xfs_file_splice_write(
 {
 	struct inode		*inode = outfilp->f_mapping->host;
 	struct xfs_inode	*ip = XFS_I(inode);
-	xfs_fsize_t		new_size;
 	int			ioflags = 0;
 	ssize_t			ret;
 
@@ -489,19 +443,12 @@ xfs_file_splice_write(
 
 	xfs_ilock(ip, XFS_IOLOCK_EXCL);
 
-	new_size = *ppos + count;
-
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	if (new_size > ip->i_size)
-		ip->i_new_size = new_size;
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-
 	trace_xfs_file_splice_write(ip, count, *ppos, ioflags);
 
 	ret = generic_file_splice_write(pipe, outfilp, ppos, count, flags);
+	if (ret > 0)
+		XFS_STATS_ADD(xs_write_bytes, ret);
 
-	xfs_aio_write_isize_update(inode, ppos, ret);
-	xfs_aio_write_newsize_update(ip, new_size);
 	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
 	return ret;
 }
@@ -689,28 +636,26 @@ out_lock:
 /*
  * Common pre-write limit and setup checks.
  *
- * Returns with iolock held according to @iolock.
+ * Called with the iolocked held either shared and exclusive according to
+ * @iolock, and returns with it held.  Might upgrade the iolock to exclusive
+ * if called for a direct write beyond i_size.
  */
 STATIC ssize_t
 xfs_file_aio_write_checks(
 	struct file		*file,
 	loff_t			*pos,
 	size_t			*count,
-	xfs_fsize_t		*new_sizep,
 	int			*iolock)
 {
 	struct inode		*inode = file->f_mapping->host;
 	struct xfs_inode	*ip = XFS_I(inode);
-	xfs_fsize_t		new_size;
 	int			error = 0;
 
 	xfs_rw_ilock(ip, XFS_ILOCK_EXCL);
-	*new_sizep = 0;
 restart:
 	error = generic_write_checks(file, pos, count, S_ISBLK(inode->i_mode));
 	if (error) {
-		xfs_rw_iunlock(ip, XFS_ILOCK_EXCL | *iolock);
-		*iolock = 0;
+		xfs_rw_iunlock(ip, XFS_ILOCK_EXCL);
 		return error;
 	}
 
@@ -720,36 +665,21 @@ restart:
 	/*
 	 * If the offset is beyond the size of the file, we need to zero any
 	 * blocks that fall between the existing EOF and the start of this
-	 * write. There is no need to issue zeroing if another in-flght IO ends
-	 * at or before this one If zeronig is needed and we are currently
-	 * holding the iolock shared, we need to update it to exclusive which
-	 * involves dropping all locks and relocking to maintain correct locking
-	 * order. If we do this, restart the function to ensure all checks and
-	 * values are still valid.
+	 * write.  If zeroing is needed and we are currently holding the
+	 * iolock shared, we need to update it to exclusive which involves
+	 * dropping all locks and relocking to maintain correct locking order.
+	 * If we do this, restart the function to ensure all checks and values
+	 * are still valid.
 	 */
-	if ((ip->i_new_size && *pos > ip->i_new_size) ||
-	    (!ip->i_new_size && *pos > ip->i_size)) {
+	if (*pos > i_size_read(inode)) {
 		if (*iolock == XFS_IOLOCK_SHARED) {
 			xfs_rw_iunlock(ip, XFS_ILOCK_EXCL | *iolock);
 			*iolock = XFS_IOLOCK_EXCL;
 			xfs_rw_ilock(ip, XFS_ILOCK_EXCL | *iolock);
 			goto restart;
 		}
-		error = -xfs_zero_eof(ip, *pos, ip->i_size);
+		error = -xfs_zero_eof(ip, *pos, i_size_read(inode));
 	}
-
-	/*
-	 * If this IO extends beyond EOF, we may need to update ip->i_new_size.
-	 * We have already zeroed space beyond EOF (if necessary).  Only update
-	 * ip->i_new_size if this IO ends beyond any other in-flight writes.
-	 */
-	new_size = *pos + *count;
-	if (new_size > ip->i_size) {
-		if (new_size > ip->i_new_size)
-			ip->i_new_size = new_size;
-		*new_sizep = new_size;
-	}
-
 	xfs_rw_iunlock(ip, XFS_ILOCK_EXCL);
 	if (error)
 		return error;
@@ -794,9 +724,7 @@ xfs_file_dio_aio_write(
 	const struct iovec	*iovp,
 	unsigned long		nr_segs,
 	loff_t			pos,
-	size_t			ocount,
-	xfs_fsize_t		*new_size,
-	int			*iolock)
+	size_t			ocount)
 {
 	struct file		*file = iocb->ki_filp;
 	struct address_space	*mapping = file->f_mapping;
@@ -806,10 +734,10 @@ xfs_file_dio_aio_write(
 	ssize_t			ret = 0;
 	size_t			count = ocount;
 	int			unaligned_io = 0;
+	int			iolock;
 	struct xfs_buftarg	*target = XFS_IS_REALTIME_INODE(ip) ?
 					mp->m_rtdev_targp : mp->m_ddev_targp;
 
-	*iolock = 0;
 	if ((pos & target->bt_smask) || (count & target->bt_smask))
 		return -XFS_ERROR(EINVAL);
 
@@ -824,31 +752,31 @@ xfs_file_dio_aio_write(
 	 * EOF zeroing cases and fill out the new inode size as appropriate.
 	 */
 	if (unaligned_io || mapping->nrpages)
-		*iolock = XFS_IOLOCK_EXCL;
+		iolock = XFS_IOLOCK_EXCL;
 	else
-		*iolock = XFS_IOLOCK_SHARED;
-	xfs_rw_ilock(ip, *iolock);
+		iolock = XFS_IOLOCK_SHARED;
+	xfs_rw_ilock(ip, iolock);
 
 	/*
 	 * Recheck if there are cached pages that need invalidate after we got
 	 * the iolock to protect against other threads adding new pages while
 	 * we were waiting for the iolock.
 	 */
-	if (mapping->nrpages && *iolock == XFS_IOLOCK_SHARED) {
-		xfs_rw_iunlock(ip, *iolock);
-		*iolock = XFS_IOLOCK_EXCL;
-		xfs_rw_ilock(ip, *iolock);
+	if (mapping->nrpages && iolock == XFS_IOLOCK_SHARED) {
+		xfs_rw_iunlock(ip, iolock);
+		iolock = XFS_IOLOCK_EXCL;
+		xfs_rw_ilock(ip, iolock);
 	}
 
-	ret = xfs_file_aio_write_checks(file, &pos, &count, new_size, iolock);
+	ret = xfs_file_aio_write_checks(file, &pos, &count, &iolock);
 	if (ret)
-		return ret;
+		goto out;
 
 	if (mapping->nrpages) {
 		ret = -xfs_flushinval_pages(ip, (pos & PAGE_CACHE_MASK), -1,
 							FI_REMAPF_LOCKED);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
 	/*
@@ -857,15 +785,18 @@ xfs_file_dio_aio_write(
 	 */
 	if (unaligned_io)
 		inode_dio_wait(inode);
-	else if (*iolock == XFS_IOLOCK_EXCL) {
+	else if (iolock == XFS_IOLOCK_EXCL) {
 		xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
-		*iolock = XFS_IOLOCK_SHARED;
+		iolock = XFS_IOLOCK_SHARED;
 	}
 
 	trace_xfs_file_direct_write(ip, count, iocb->ki_pos, 0);
 	ret = generic_file_direct_write(iocb, iovp,
 			&nr_segs, pos, &iocb->ki_pos, count, ocount);
 
+out:
+	xfs_rw_iunlock(ip, iolock);
+
 	/* No fallback to buffered IO on errors for XFS. */
 	ASSERT(ret < 0 || ret == count);
 	return ret;
@@ -877,9 +808,7 @@ xfs_file_buffered_aio_write(
 	const struct iovec	*iovp,
 	unsigned long		nr_segs,
 	loff_t			pos,
-	size_t			ocount,
-	xfs_fsize_t		*new_size,
-	int			*iolock)
+	size_t			ocount)
 {
 	struct file		*file = iocb->ki_filp;
 	struct address_space	*mapping = file->f_mapping;
@@ -887,14 +816,14 @@ xfs_file_buffered_aio_write(
 	struct xfs_inode	*ip = XFS_I(inode);
 	ssize_t			ret;
 	int			enospc = 0;
+	int			iolock = XFS_IOLOCK_EXCL;
 	size_t			count = ocount;
 
-	*iolock = XFS_IOLOCK_EXCL;
-	xfs_rw_ilock(ip, *iolock);
+	xfs_rw_ilock(ip, iolock);
 
-	ret = xfs_file_aio_write_checks(file, &pos, &count, new_size, iolock);
+	ret = xfs_file_aio_write_checks(file, &pos, &count, &iolock);
 	if (ret)
-		return ret;
+		goto out;
 
 	/* We can write back this queue in page reclaim */
 	current->backing_dev_info = mapping->backing_dev_info;
@@ -908,13 +837,15 @@ write_retry:
 	 * page locks and retry *once*
 	 */
 	if (ret == -ENOSPC && !enospc) {
-		ret = -xfs_flush_pages(ip, 0, -1, 0, FI_NONE);
-		if (ret)
-			return ret;
 		enospc = 1;
-		goto write_retry;
+		ret = -xfs_flush_pages(ip, 0, -1, 0, FI_NONE);
+		if (!ret)
+			goto write_retry;
 	}
+
 	current->backing_dev_info = NULL;
+out:
+	xfs_rw_iunlock(ip, iolock);
 	return ret;
 }
 
@@ -930,9 +861,7 @@ xfs_file_aio_write(
 	struct inode		*inode = mapping->host;
 	struct xfs_inode	*ip = XFS_I(inode);
 	ssize_t			ret;
-	int			iolock;
 	size_t			ocount = 0;
-	xfs_fsize_t		new_size = 0;
 
 	XFS_STATS_INC(xs_write_calls);
 
@@ -951,33 +880,22 @@ xfs_file_aio_write(
 		return -EIO;
 
 	if (unlikely(file->f_flags & O_DIRECT))
-		ret = xfs_file_dio_aio_write(iocb, iovp, nr_segs, pos,
-						ocount, &new_size, &iolock);
+		ret = xfs_file_dio_aio_write(iocb, iovp, nr_segs, pos, ocount);
 	else
 		ret = xfs_file_buffered_aio_write(iocb, iovp, nr_segs, pos,
-						ocount, &new_size, &iolock);
-
-	xfs_aio_write_isize_update(inode, &iocb->ki_pos, ret);
+						  ocount);
 
-	if (ret <= 0)
-		goto out_unlock;
+	if (ret > 0) {
+		ssize_t err;
 
-	/* Handle various SYNC-type writes */
-	if ((file->f_flags & O_DSYNC) || IS_SYNC(inode)) {
-		loff_t end = pos + ret - 1;
-		int error;
+		XFS_STATS_ADD(xs_write_bytes, ret);
 
-		xfs_rw_iunlock(ip, iolock);
-		error = xfs_file_fsync(file, pos, end,
-				      (file->f_flags & __O_SYNC) ? 0 : 1);
-		xfs_rw_ilock(ip, iolock);
-		if (error)
-			ret = error;
+		/* Handle various SYNC-type writes */
+		err = generic_write_sync(file, pos, ret);
+		if (err < 0)
+			ret = err;
 	}
 
-out_unlock:
-	xfs_aio_write_newsize_update(ip, new_size);
-	xfs_rw_iunlock(ip, iolock);
 	return ret;
 }
 
diff --git a/fs/xfs/xfs_fs_subr.c b/fs/xfs/xfs_fs_subr.c
index ed88ed16811c..652b875a9d4c 100644
--- a/fs/xfs/xfs_fs_subr.c
+++ b/fs/xfs/xfs_fs_subr.c
@@ -90,7 +90,7 @@ xfs_wait_on_pages(
 
 	if (mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) {
 		return -filemap_fdatawait_range(mapping, first,
-					last == -1 ? ip->i_size - 1 : last);
+					last == -1 ? XFS_ISIZE(ip) - 1 : last);
 	}
 	return 0;
 }
diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c
index 3960a066d7ff..8c3e46394d48 100644
--- a/fs/xfs/xfs_iget.c
+++ b/fs/xfs/xfs_iget.c
@@ -77,7 +77,7 @@ xfs_inode_alloc(
 
 	ASSERT(atomic_read(&ip->i_pincount) == 0);
 	ASSERT(!spin_is_locked(&ip->i_flags_lock));
-	ASSERT(completion_done(&ip->i_flush));
+	ASSERT(!xfs_isiflocked(ip));
 	ASSERT(ip->i_ino == 0);
 
 	mrlock_init(&ip->i_iolock, MRLOCK_BARRIER, "xfsio", ip->i_ino);
@@ -94,8 +94,6 @@ xfs_inode_alloc(
 	ip->i_update_core = 0;
 	ip->i_delayed_blks = 0;
 	memset(&ip->i_d, 0, sizeof(xfs_icdinode_t));
-	ip->i_size = 0;
-	ip->i_new_size = 0;
 
 	return ip;
 }
@@ -150,7 +148,7 @@ xfs_inode_free(
 	/* asserts to verify all state is correct here */
 	ASSERT(atomic_read(&ip->i_pincount) == 0);
 	ASSERT(!spin_is_locked(&ip->i_flags_lock));
-	ASSERT(completion_done(&ip->i_flush));
+	ASSERT(!xfs_isiflocked(ip));
 
 	/*
 	 * Because we use RCU freeing we need to ensure the inode always
@@ -450,8 +448,6 @@ again:
 
 	*ipp = ip;
 
-	ASSERT(ip->i_df.if_ext_max ==
-	       XFS_IFORK_DSIZE(ip) / sizeof(xfs_bmbt_rec_t));
 	/*
 	 * If we have a real type for an on-disk inode, we can set ops(&unlock)
 	 * now.	 If it's a new inode being created, xfs_ialloc will handle it.
@@ -715,3 +711,19 @@ xfs_isilocked(
 	return 0;
 }
 #endif
+
+void