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

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
@@ -1278,6 +1273,15 @@ 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
@@ -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;

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);
 

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);
 	}

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 @@ xfs_bunmapi(
 		}
 	}
 	*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 @@ xfs_bunmapi(
 	/*
 	 * 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 @@ xfs_bunmapi(
 	/*
 	 * 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;

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;
 }
@@ -348,16 +357,6 @@ xfs_swap_extents(
 	*ifp = *tifp;		/* struct copy */
 	*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
 	 */

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 @@ xfs_zero_eof(
 /*
  * 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 @@ xfs_file_aio_write_checks(
 	/*
 	 * 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 @@ xfs_file_buffered_aio_write(
 	 * 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;
 }
 

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;
 }

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 @@ xfs_iget(
 
 	*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
+__xfs_iflock(
+	struct xfs_inode	*ip)
+{
+	wait_queue_head_t *wq = bit_waitqueue(&ip->i_flags, __XFS_IFLOCK_BIT);
+	DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_IFLOCK_BIT);
+
+	do {
+		prepare_to_wait_exclusive(wq, &wait.wait, TASK_UNINTERRUPTIBLE);
+		if (xfs_isiflocked(ip))
+			io_schedule();
+	} while (!xfs_iflock_nowait(ip));
+
+	finish_wait(wq, &wait.wait);
+}

fs/xfs/xfs_inode.c

@@ -299,11 +299,8 @@ xfs_iformat(
 {
 	xfs_attr_shortform_t	*atp;
 	int			size;
-	int			error;
+	int			error = 0;
 	xfs_fsize_t             di_size;
-	ip->i_df.if_ext_max =
-		XFS_IFORK_DSIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t);
-	error = 0;
 
 	if (unlikely(be32_to_cpu(dip->di_nextents) +
 		     be16_to_cpu(dip->di_anextents) >
@@ -350,7 +347,6 @@ xfs_iformat(
 			return XFS_ERROR(EFSCORRUPTED);
 		}
 		ip->i_d.di_size = 0;
-		ip->i_size = 0;
 		ip->i_df.if_u2.if_rdev = xfs_dinode_get_rdev(dip);
 		break;
 
@@ -409,10 +405,10 @@ xfs_iformat(
 	}
 	if (!XFS_DFORK_Q(dip))
 		return 0;
+
 	ASSERT(ip->i_afp == NULL);
 	ip->i_afp = kmem_zone_zalloc(xfs_ifork_zone, KM_SLEEP | KM_NOFS);
-	ip->i_afp->if_ext_max =
-		XFS_IFORK_ASIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t);
+
 	switch (dip->di_aformat) {
 	case XFS_DINODE_FMT_LOCAL:
 		atp = (xfs_attr_shortform_t *)XFS_DFORK_APTR(dip);
@@ -604,10 +600,11 @@ xfs_iformat_btree(
 	 * or the number of extents is greater than the number of
 	 * blocks.
 	 */
-	if (unlikely(XFS_IFORK_NEXTENTS(ip, whichfork) <= ifp->if_ext_max
-	    || XFS_BMDR_SPACE_CALC(nrecs) >
-			XFS_DFORK_SIZE(dip, ip->i_mount, whichfork)
-	    || XFS_IFORK_NEXTENTS(ip, whichfork) > ip->i_d.di_nblocks)) {
+	if (unlikely(XFS_IFORK_NEXTENTS(ip, whichfork) <=
+			XFS_IFORK_MAXEXT(ip, whichfork) ||
+		     XFS_BMDR_SPACE_CALC(nrecs) >
+			XFS_DFORK_SIZE(dip, ip->i_mount, whichfork) ||
+		     XFS_IFORK_NEXTENTS(ip, whichfork) > ip->i_d.di_nblocks)) {
 		xfs_warn(ip->i_mount, "corrupt inode %Lu (btree).",
 			(unsigned long long) ip->i_ino);
 		XFS_CORRUPTION_ERROR("xfs_iformat_btree", XFS_ERRLEVEL_LOW,
@@ -835,12 +832,6 @@ xfs_iread(
 		 * with the uninitialized part of it.
 		 */
 		ip->i_d.di_mode = 0;
-		/*
-		 * Initialize the per-fork minima and maxima for a new
-		 * inode here.  xfs_iformat will do it for old inodes.
-		 */
-		ip->i_df.if_ext_max =
-			XFS_IFORK_DSIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t);
 	}
 
 	/*
@@ -861,7 +852,6 @@ xfs_iread(
 	}
 
 	ip->i_delayed_blks = 0;
-	ip->i_size = ip->i_d.di_size;
 
 	/*
 	 * Mark the buffer containing the inode as something to keep
@@ -1051,7 +1041,6 @@ xfs_ialloc(
 	}
 
 	ip->i_d.di_size = 0;
-	ip->i_size = 0;
 	ip->i_d.di_nextents = 0;
 	ASSERT(ip->i_d.di_nblocks == 0);
 
@@ -1165,52 +1154,6 @@ xfs_ialloc(
 	return 0;
 }
 
-/*
- * Check to make sure that there are no blocks allocated to the
- * file beyond the size of the file.  We don't check this for
- * files with fixed size extents or real time extents, but we
- * at least do it for regular files.
- */
-#ifdef DEBUG
-STATIC void
-xfs_isize_check(
-	struct xfs_inode	*ip,
-	xfs_fsize_t		isize)
-{
-	struct xfs_mount	*mp = ip->i_mount;
-	xfs_fileoff_t		map_first;
-	int			nimaps;
-	xfs_bmbt_irec_t		imaps[2];
-	int			error;
-
-	if (!S_ISREG(ip->i_d.di_mode))
-		return;
-
-	if (XFS_IS_REALTIME_INODE(ip))
-		return;
-
-	if (ip->i_d.di_flags & XFS_DIFLAG_EXTSIZE)
-		return;
-
-	nimaps = 2;
-	map_first = XFS_B_TO_FSB(mp, (xfs_ufsize_t)isize);
-	/*
-	 * The filesystem could be shutting down, so bmapi may return
-	 * an error.
-	 */
-	error = xfs_bmapi_read(ip, map_first,
-			 (XFS_B_TO_FSB(mp,
-			       (xfs_ufsize_t)XFS_MAXIOFFSET(mp)) - map_first),
-			 imaps, &nimaps, XFS_BMAPI_ENTIRE);
-	if (error)
-		return;
-	ASSERT(nimaps == 1);
-	ASSERT(imaps[0].br_startblock == HOLESTARTBLOCK);
-}
-#else	/* DEBUG */
-#define xfs_isize_check(ip, isize)
-#endif	/* DEBUG */
-
 /*
  * Free up the underlying blocks past new_size.  The new size must be smaller
  * than the current size.  This routine can be used both for the attribute and
@@ -1252,12 +1195,14 @@ xfs_itruncate_extents(
 	int			done = 0;
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_IOLOCK_EXCL));
-	ASSERT(new_size <= ip->i_size);
+	ASSERT(new_size <= XFS_ISIZE(ip));
 	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
 	ASSERT(ip->i_itemp != NULL);
 	ASSERT(ip->i_itemp->ili_lock_flags == 0);
 	ASSERT(!XFS_NOT_DQATTACHED(mp, ip));
 
+	trace_xfs_itruncate_extents_start(ip, new_size);
+
 	/*
 	 * Since it is possible for space to become allocated beyond
 	 * the end of the file (in a crash where the space is allocated
@@ -1325,6 +1270,14 @@ xfs_itruncate_extents(
 			goto out;
 	}
 
+	/*
+	 * Always re-log the inode so that our permanent transaction can keep
+	 * on rolling it forward in the log.
+	 */
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+
+	trace_xfs_itruncate_extents_end(ip, new_size);
+
 out:
 	*tpp = tp;
 	return error;
@@ -1338,74 +1291,6 @@ xfs_itruncate_extents(
 	goto out;
 }
 
-int
-xfs_itruncate_data(
-	struct xfs_trans	**tpp,
-	struct xfs_inode	*ip,
-	xfs_fsize_t		new_size)
-{
-	int			error;
-
-	trace_xfs_itruncate_data_start(ip, new_size);
-
-	/*
-	 * The first thing we do is set the size to new_size permanently on
-	 * disk.  This way we don't have to worry about anyone ever being able
-	 * to look at the data being freed even in the face of a crash.
-	 * What we're getting around here is the case where we free a block, it
-	 * is allocated to another file, it is written to, and then we crash.
-	 * If the new data gets written to the file but the log buffers
-	 * containing the free and reallocation don't, then we'd end up with
-	 * garbage in the blocks being freed.  As long as we make the new_size
-	 * permanent before actually freeing any blocks it doesn't matter if
-	 * they get written to.
-	 */
-	if (ip->i_d.di_nextents > 0) {
-		/*
-		 * If we are not changing the file size then do not update
-		 * the on-disk file size - we may be called from
-		 * xfs_inactive_free_eofblocks().  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).
-		 */
-		if (ip->i_size != new_size) {
-			ip->i_d.di_size = new_size;
-			ip->i_size = new_size;
-			xfs_trans_log_inode(*tpp, ip, XFS_ILOG_CORE);
-		}
-	}
-
-	error = xfs_itruncate_extents(tpp, ip, XFS_DATA_FORK, new_size);
-	if (error)
-		return error;
-
-	/*
-	 * If we are not changing the file size then do not update the on-disk
-	 * file size - we may be called from xfs_inactive_free_eofblocks().
-	 * 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).
-	 */
-	xfs_isize_check(ip, new_size);
-	if (ip->i_size != new_size) {
-		ip->i_d.di_size = new_size;
-		ip->i_size = new_size;
-	}
-
-	ASSERT(new_size != 0 || ip->i_delayed_blks == 0);
-	ASSERT(new_size != 0 || ip->i_d.di_nextents == 0);
-
-	/*
-	 * Always re-log the inode so that our permanent transaction can keep
-	 * on rolling it forward in the log.
-	 */
-	xfs_trans_log_inode(*tpp, ip, XFS_ILOG_CORE);
-
-	trace_xfs_itruncate_data_end(ip, new_size);
-	return 0;
-}
-
 /*
  * This is called when the inode's link count goes to 0.
  * We place the on-disk inode on a list in the AGI.  It
@@ -1824,8 +1709,7 @@ xfs_ifree(
 	ASSERT(ip->i_d.di_nlink == 0);
 	ASSERT(ip->i_d.di_nextents == 0);
 	ASSERT(ip->i_d.di_anextents == 0);
-	ASSERT((ip->i_d.di_size == 0 && ip->i_size == 0) ||
-	       (!S_ISREG(ip->i_d.di_mode)));
+	ASSERT(ip->i_d.di_size == 0 || !S_ISREG(ip->i_d.di_mode));
 	ASSERT(ip->i_d.di_nblocks == 0);
 
 	/*
@@ -1844,8 +1728,6 @@ xfs_ifree(
 	ip->i_d.di_flags = 0;
 	ip->i_d.di_dmevmask = 0;
 	ip->i_d.di_forkoff = 0;		/* mark the attr fork not in use */
-	ip->i_df.if_ext_max =
-		XFS_IFORK_DSIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t);
 	ip->i_d.di_format = XFS_DINODE_FMT_EXTENTS;
 	ip->i_d.di_aformat = XFS_DINODE_FMT_EXTENTS;
 	/*
@@ -2151,7 +2033,7 @@ xfs_idestroy_fork(
  * once someone is waiting for it to be unpinned.
  */
 static void
-xfs_iunpin_nowait(
+xfs_iunpin(
 	struct xfs_inode	*ip)
 {
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
@@ -2163,14 +2045,29 @@ xfs_iunpin_nowait(
 
 }
 
+static void
+__xfs_iunpin_wait(
+	struct xfs_inode	*ip)
+{
+	wait_queue_head_t *wq = bit_waitqueue(&ip->i_flags, __XFS_IPINNED_BIT);
+	DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_IPINNED_BIT);
+
+	xfs_iunpin(ip);
+
+	do {
+		prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE);
+		if (xfs_ipincount(ip))
+			io_schedule();
+	} while (xfs_ipincount(ip));
+	finish_wait(wq, &wait.wait);
+}
+
 void
 xfs_iunpin_wait(
 	struct xfs_inode	*ip)
 {
-	if (xfs_ipincount(ip)) {
-		xfs_iunpin_nowait(ip);
-		wait_event(ip->i_ipin_wait, (xfs_ipincount(ip) == 0));
-	}
+	if (xfs_ipincount(ip))
+		__xfs_iunpin_wait(ip);
 }
 
 /*
@@ -2510,9 +2407,9 @@ xfs_iflush(
 	XFS_STATS_INC(xs_iflush_count);
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
-	ASSERT(!completion_done(&ip->i_flush));
+	ASSERT(xfs_isiflocked(ip));
 	ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE ||
-	       ip->i_d.di_nextents > ip->i_df.if_ext_max);
+	       ip->i_d.di_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK));
 
 	iip = ip->i_itemp;
 	mp = ip->i_mount;
@@ -2529,7 +2426,7 @@ xfs_iflush(
 	 * out for us if they occur after the log force completes.
 	 */
 	if (!(flags & SYNC_WAIT) && xfs_ipincount(ip)) {
-		xfs_iunpin_nowait(ip);
+		xfs_iunpin(ip);
 		xfs_ifunlock(ip);
 		return EAGAIN;
 	}
@@ -2626,9 +2523,9 @@ xfs_iflush_int(
 #endif
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
-	ASSERT(!completion_done(&ip->i_flush));
+	ASSERT(xfs_isiflocked(ip));
 	ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE ||
-	       ip->i_d.di_nextents > ip->i_df.if_ext_max);
+	       ip->i_d.di_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK));
 
 	iip = ip->i_itemp;
 	mp = ip->i_mount;

fs/xfs/xfs_inode.h

@@ -66,7 +66,6 @@ typedef struct xfs_ifork {
 	struct xfs_btree_block	*if_broot;	/* file's incore btree root */
 	short			if_broot_bytes;	/* bytes allocated for root */
 	unsigned char		if_flags;	/* per-fork flags */
-	unsigned char		if_ext_max;	/* max # of extent records */
 	union {
 		xfs_bmbt_rec_host_t *if_extents;/* linear map file exts */
 		xfs_ext_irec_t	*if_ext_irec;	/* irec map file exts */
@@ -206,12 +205,12 @@ typedef struct xfs_icdinode {
 	((w) == XFS_DATA_FORK ? \
 		((ip)->i_d.di_nextents = (n)) : \
 		((ip)->i_d.di_anextents = (n)))
-
+#define XFS_IFORK_MAXEXT(ip, w) \
+	(XFS_IFORK_SIZE(ip, w) / sizeof(xfs_bmbt_rec_t))
 
 
 #ifdef __KERNEL__
 
-struct bhv_desc;
 struct xfs_buf;
 struct xfs_bmap_free;
 struct xfs_bmbt_irec;
@@ -220,12 +219,6 @@ struct xfs_mount;
 struct xfs_trans;
 struct xfs_dquot;
 
-typedef struct dm_attrs_s {
-	__uint32_t	da_dmevmask;	/* DMIG event mask */
-	__uint16_t	da_dmstate;	/* DMIG state info */
-	__uint16_t	da_pad;		/* DMIG extra padding */
-} dm_attrs_t;
-
 typedef struct xfs_inode {
 	/* Inode linking and identification information. */
 	struct xfs_mount	*i_mount;	/* fs mount struct ptr */
@@ -244,27 +237,19 @@ typedef struct xfs_inode {
 	struct xfs_inode_log_item *i_itemp;	/* logging information */
 	mrlock_t		i_lock;		/* inode lock */
 	mrlock_t		i_iolock;	/* inode IO lock */
-	struct completion	i_flush;	/* inode flush completion q */
 	atomic_t		i_pincount;	/* inode pin count */
-	wait_queue_head_t	i_ipin_wait;	/* inode pinning wait queue */
 	spinlock_t		i_flags_lock;	/* inode i_flags lock */
 	/* Miscellaneous state. */
-	unsigned short		i_flags;	/* see defined flags below */
+	unsigned long		i_flags;	/* see defined flags below */
 	unsigned char		i_update_core;	/* timestamps/size is dirty */
 	unsigned int		i_delayed_blks;	/* count of delay alloc blks */
 
 	xfs_icdinode_t		i_d;		/* most of ondisk inode */
 
-	xfs_fsize_t		i_size;		/* in-memory size */
-	xfs_fsize_t		i_new_size;	/* size when write completes */
-
 	/* VFS inode */
 	struct inode		i_vnode;	/* embedded VFS inode */
 } xfs_inode_t;
 
-#define XFS_ISIZE(ip)	S_ISREG((ip)->i_d.di_mode) ? \
-				(ip)->i_size : (ip)->i_d.di_size;
-
 /* Convert from vfs inode to xfs inode */
 static inline struct xfs_inode *XFS_I(struct inode *inode)
 {
@@ -277,6 +262,18 @@ static inline struct inode *VFS_I(struct xfs_inode *ip)
 	return &ip->i_vnode;
 }
 
+/*
+ * For regular files we only update the on-disk filesize when actually
+ * writing data back to disk.  Until then only the copy in the VFS inode
+ * is uptodate.
+ */
+static inline xfs_fsize_t XFS_ISIZE(struct xfs_inode *ip)
+{
+	if (S_ISREG(ip->i_d.di_mode))
+		return i_size_read(VFS_I(ip));
+	return ip->i_d.di_size;
+}
+
 /*
  * i_flags helper functions
  */
@@ -331,6 +328,19 @@ xfs_iflags_test_and_clear(xfs_inode_t *ip, unsigned short flags)
 	return ret;
 }
 
+static inline int
+xfs_iflags_test_and_set(xfs_inode_t *ip, unsigned short flags)
+{
+	int ret;
+
+	spin_lock(&ip->i_flags_lock);
+	ret = ip->i_flags & flags;
+	if (!ret)
+		ip->i_flags |= flags;
+	spin_unlock(&ip->i_flags_lock);
+	return ret;
+}
+
 /*
  * Project quota id helpers (previously projid was 16bit only
  * and using two 16bit values to hold new 32bit projid was chosen
@@ -350,36 +360,20 @@ xfs_set_projid(struct xfs_inode *ip,
 	ip->i_d.di_projid_lo = (__uint16_t) (projid & 0xffff);
 }
 
-/*
- * Manage the i_flush queue embedded in the inode.  This completion
- * queue synchronizes processes attempting to flush the in-core
- * inode back to disk.
- */
-static inline void xfs_iflock(xfs_inode_t *ip)
-{
-	wait_for_completion(&ip->i_flush);
-}
-
-static inline int xfs_iflock_nowait(xfs_inode_t *ip)
-{
-	return try_wait_for_completion(&ip->i_flush);
-}
-
-static inline void xfs_ifunlock(xfs_inode_t *ip)
-{
-	complete(&ip->i_flush);
-}
-
 /*
  * In-core inode flags.
  */
-#define XFS_IRECLAIM		0x0001  /* started reclaiming this inode */
-#define XFS_ISTALE		0x0002	/* inode has been staled */
-#define XFS_IRECLAIMABLE	0x0004	/* inode can be reclaimed */
-#define XFS_INEW		0x0008	/* inode has just been allocated */
-#define XFS_IFILESTREAM		0x0010	/* inode is in a filestream directory */
-#define XFS_ITRUNCATED		0x0020	/* truncated down so flush-on-close */
-#define XFS_IDIRTY_RELEASE	0x0040	/* dirty release already seen */
+#define XFS_IRECLAIM		(1 << 0) /* started reclaiming this inode */
+#define XFS_ISTALE		(1 << 1) /* inode has been staled */
+#define XFS_IRECLAIMABLE	(1 << 2) /* inode can be reclaimed */
+#define XFS_INEW		(1 << 3) /* inode has just been allocated */
+#define XFS_IFILESTREAM		(1 << 4) /* inode is in a filestream dir. */
+#define XFS_ITRUNCATED		(1 << 5) /* truncated down so flush-on-close */
+#define XFS_IDIRTY_RELEASE	(1 << 6) /* dirty release already seen */
+#define __XFS_IFLOCK_BIT	7	 /* inode is being flushed right now */
+#define XFS_IFLOCK		(1 << __XFS_IFLOCK_BIT)
+#define __XFS_IPINNED_BIT	8	 /* wakeup key for zero pin count */
+#define XFS_IPINNED		(1 << __XFS_IPINNED_BIT)
 
 /*
  * Per-lifetime flags need to be reset when re-using a reclaimable inode during
@@ -391,6 +385,34 @@ static inline void xfs_ifunlock(xfs_inode_t *ip)
 	 XFS_IDIRTY_RELEASE | XFS_ITRUNCATED | \
 	 XFS_IFILESTREAM);
 
+/*
+ * Synchronize processes attempting to flush the in-core inode back to disk.
+ */
+
+extern void __xfs_iflock(struct xfs_inode *ip);
+
+static inline int xfs_iflock_nowait(struct xfs_inode *ip)
+{
+	return !xfs_iflags_test_and_set(ip, XFS_IFLOCK);
+}
+
+static inline void xfs_iflock(struct xfs_inode *ip)
+{
+	if (!xfs_iflock_nowait(ip))
+		__xfs_iflock(ip);
+}
+
+static inline void xfs_ifunlock(struct xfs_inode *ip)
+{
+	xfs_iflags_clear(ip, XFS_IFLOCK);
+	wake_up_bit(&ip->i_flags, __XFS_IFLOCK_BIT);
+}
+
+static inline int xfs_isiflocked(struct xfs_inode *ip)
+{
+	return xfs_iflags_test(ip, XFS_IFLOCK);
+}
+
 /*
  * Flags for inode locking.
  * Bit ranges:	1<<1  - 1<<16-1 -- iolock/ilock modes (bitfield)
@@ -491,8 +513,6 @@ int		xfs_ifree(struct xfs_trans *, xfs_inode_t *,
 			   struct xfs_bmap_free *);
 int		xfs_itruncate_extents(struct xfs_trans **, struct xfs_inode *,
 				      int, xfs_fsize_t);
-int		xfs_itruncate_data(struct xfs_trans **, struct xfs_inode *,
-				   xfs_fsize_t);
 int		xfs_iunlink(struct xfs_trans *, xfs_inode_t *);
 
 void		xfs_iext_realloc(xfs_inode_t *, int, int);

fs/xfs/xfs_inode_item.c

@@ -79,8 +79,6 @@ xfs_inode_item_size(
 		break;
 
 	case XFS_DINODE_FMT_BTREE:
-		ASSERT(ip->i_df.if_ext_max ==
-		       XFS_IFORK_DSIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t));
 		iip->ili_format.ilf_fields &=
 			~(XFS_ILOG_DDATA | XFS_ILOG_DEXT |
 			  XFS_ILOG_DEV | XFS_ILOG_UUID);
@@ -557,7 +555,7 @@ xfs_inode_item_unpin(
 	trace_xfs_inode_unpin(ip, _RET_IP_);
 	ASSERT(atomic_read(&ip->i_pincount) > 0);
 	if (atomic_dec_and_test(&ip->i_pincount))
-		wake_up(&ip->i_ipin_wait);
+		wake_up_bit(&ip->i_flags, __XFS_IPINNED_BIT);
 }
 
 /*
@@ -719,7 +717,7 @@ xfs_inode_item_pushbuf(
 	 * If a flush is not in progress anymore, chances are that the
 	 * inode was taken off the AIL. So, just get out.
 	 */
-	if (completion_done(&ip->i_flush) ||
+	if (!xfs_isiflocked(ip) ||
 	    !(lip->li_flags & XFS_LI_IN_AIL)) {
 		xfs_iunlock(ip, XFS_ILOCK_SHARED);
 		return true;
@@ -752,7 +750,7 @@ xfs_inode_item_push(
 	struct xfs_inode	*ip = iip->ili_inode;
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED));
-	ASSERT(!completion_done(&ip->i_flush));
+	ASSERT(xfs_isiflocked(ip));
 
 	/*
 	 * Since we were able to lock the inode's flush lock and

fs/xfs/xfs_iomap.c

@@ -57,26 +57,26 @@ xfs_iomap_eof_align_last_fsb(
 	xfs_fileoff_t	*last_fsb)
 {
 	xfs_fileoff_t	new_last_fsb = 0;
-	xfs_extlen_t	align;
+	xfs_extlen_t	align = 0;
 	int		eof, error;
 
-	if (XFS_IS_REALTIME_INODE(ip))
-		;
-	/*
-	 * If mounted with the "-o swalloc" option, roundup the allocation
-	 * request to a stripe width boundary if the file size is >=
-	 * stripe width and we are allocating past the allocation eof.
-	 */
-	else if (mp->m_swidth && (mp->m_flags & XFS_MOUNT_SWALLOC) &&
-	        (ip->i_size >= XFS_FSB_TO_B(mp, mp->m_swidth)))
-		new_last_fsb = roundup_64(*last_fsb, mp->m_swidth);
-	/*
-	 * Roundup the allocation request to a stripe unit (m_dalign) boundary
-	 * if the file size is >= stripe unit size, and we are allocating past
-	 * the allocation eof.
-	 */
-	else if (mp->m_dalign && (ip->i_size >= XFS_FSB_TO_B(mp, mp->m_dalign)))
-		new_last_fsb = roundup_64(*last_fsb, mp->m_dalign);
+	if (!XFS_IS_REALTIME_INODE(ip)) {
+		/*
+		 * Round up the allocation request to a stripe unit
+		 * (m_dalign) boundary if the file size is >= stripe unit
+		 * size, and we are allocating past the allocation eof.
+		 *
+		 * If mounted with the "-o swalloc" option the alignment is
+		 * increased from the strip unit size to the stripe width.
+		 */
+		if (mp->m_swidth && (mp->m_flags & XFS_MOUNT_SWALLOC))
+			align = mp->m_swidth;
+		else if (mp->m_dalign)
+			align = mp->m_dalign;
+
+		if (align && XFS_ISIZE(ip) >= XFS_FSB_TO_B(mp, align))
+			new_last_fsb = roundup_64(*last_fsb, align);
+	}
 
 	/*
 	 * Always round up the allocation request to an extent boundary
@@ -154,7 +154,7 @@ xfs_iomap_write_direct(
 
 	offset_fsb = XFS_B_TO_FSBT(mp, offset);
 	last_fsb = XFS_B_TO_FSB(mp, ((xfs_ufsize_t)(offset + count)));
-	if ((offset + count) > ip->i_size) {
+	if ((offset + count) > XFS_ISIZE(ip)) {
 		error = xfs_iomap_eof_align_last_fsb(mp, ip, extsz, &last_fsb);
 		if (error)
 			goto error_out;
@@ -211,7 +211,7 @@ xfs_iomap_write_direct(
 	xfs_trans_ijoin(tp, ip, 0);
 
 	bmapi_flag = 0;
-	if (offset < ip->i_size || extsz)
+	if (offset < XFS_ISIZE(ip) || extsz)
 		bmapi_flag |= XFS_BMAPI_PREALLOC;
 
 	/*
@@ -286,7 +286,7 @@ xfs_iomap_eof_want_preallocate(
 	int		found_delalloc = 0;
 
 	*prealloc = 0;
-	if ((offset + count) <= ip->i_size)
+	if (offset + count <= XFS_ISIZE(ip))
 		return 0;
 
 	/*
@@ -340,7 +340,7 @@ xfs_iomap_prealloc_size(
 		 * if we pass in alloc_blocks = 0. Hence the "+ 1" to
 		 * ensure we always pass in a non-zero value.
 		 */
-		alloc_blocks = XFS_B_TO_FSB(mp, ip->i_size) + 1;
+		alloc_blocks = XFS_B_TO_FSB(mp, XFS_ISIZE(ip)) + 1;
 		alloc_blocks = XFS_FILEOFF_MIN(MAXEXTLEN,
 					rounddown_pow_of_two(alloc_blocks));
 
@@ -564,7 +564,7 @@ xfs_iomap_write_allocate(
 			 * back....
 			 */
 			nimaps = 1;
-			end_fsb = XFS_B_TO_FSB(mp, ip->i_size);
+			end_fsb = XFS_B_TO_FSB(mp, XFS_ISIZE(ip));
 			error = xfs_bmap_last_offset(NULL, ip, &last_block,
 							XFS_DATA_FORK);
 			if (error)

fs/xfs/xfs_iops.c

@@ -750,6 +750,7 @@ xfs_setattr_size(
 	struct xfs_mount	*mp = ip->i_mount;
 	struct inode		*inode = VFS_I(ip);
 	int			mask = iattr->ia_valid;
+	xfs_off_t		oldsize, newsize;
 	struct xfs_trans	*tp;
 	int			error;
 	uint			lock_flags;
@@ -777,11 +778,13 @@ xfs_setattr_size(
 		lock_flags |= XFS_IOLOCK_EXCL;
 	xfs_ilock(ip, lock_flags);
 
+	oldsize = inode->i_size;
+	newsize = iattr->ia_size;
+
 	/*
 	 * Short circuit the truncate case for zero length files.
 	 */
-	if (iattr->ia_size == 0 &&
-	    ip->i_size == 0 && ip->i_d.di_nextents == 0) {
+	if (newsize == 0 && oldsize == 0 && ip->i_d.di_nextents == 0) {
 		if (!(mask & (ATTR_CTIME|ATTR_MTIME)))
 			goto out_unlock;
 
@@ -807,14 +810,14 @@ xfs_setattr_size(
 	 * the inode to the transaction, because the inode cannot be unlocked
 	 * once it is a part of the transaction.
 	 */
-	if (iattr->ia_size > ip->i_size) {
+	if (newsize > oldsize) {
 		/*
 		 * Do the first part of growing a file: zero any data in the
 		 * last block that is beyond the old EOF.  We need to do this
 		 * before the inode is joined to the transaction to modify
 		 * i_size.
 		 */
-		error = xfs_zero_eof(ip, iattr->ia_size, ip->i_size);
+		error = xfs_zero_eof(ip, newsize, oldsize);
 		if (error)
 			goto out_unlock;
 	}
@@ -833,8 +836,8 @@ xfs_setattr_size(
 	 * here and prevents waiting for other data not within the range we
 	 * care about here.
 	 */
-	if (ip->i_size != ip->i_d.di_size && iattr->ia_size > ip->i_d.di_size) {
-		error = xfs_flush_pages(ip, ip->i_d.di_size, iattr->ia_size, 0,
+	if (oldsize != ip->i_d.di_size && newsize > ip->i_d.di_size) {
+		error = xfs_flush_pages(ip, ip->i_d.di_size, newsize, 0,
 					FI_NONE);
 		if (error)
 			goto out_unlock;
@@ -845,8 +848,7 @@ xfs_setattr_size(
 	 */
 	inode_dio_wait(inode);
 
-	error = -block_truncate_page(inode->i_mapping, iattr->ia_size,
-				     xfs_get_blocks);
+	error = -block_truncate_page(inode->i_mapping, newsize, xfs_get_blocks);
 	if (error)
 		goto out_unlock;
 
@@ -857,7 +859,7 @@ xfs_setattr_size(
 	if (error)
 		goto out_trans_cancel;
 
-	truncate_setsize(inode, iattr->ia_size);
+	truncate_setsize(inode, newsize);
 
 	commit_flags = XFS_TRANS_RELEASE_LOG_RES;
 	lock_flags |= XFS_ILOCK_EXCL;
@@ -876,19 +878,29 @@ xfs_setattr_size(
 	 * these flags set.  For all other operations the VFS set these flags
 	 * explicitly if it wants a timestamp update.
 	 */
-	if (iattr->ia_size != ip->i_size &&
-	    (!(mask & (ATTR_CTIME | ATTR_MTIME)))) {
+	if (newsize != oldsize && (!(mask & (ATTR_CTIME | ATTR_MTIME)))) {
 		iattr->ia_ctime = iattr->ia_mtime =
 			current_fs_time(inode->i_sb);
 		mask |= ATTR_CTIME | ATTR_MTIME;
 	}
 
-	if (iattr->ia_size > ip->i_size) {
-		ip->i_d.di_size = iattr->ia_size;
-		ip->i_size = iattr->ia_size;
-	} else if (iattr->ia_size <= ip->i_size ||
-		   (iattr->ia_size == 0 && ip->i_d.di_nextents)) {
-		error = xfs_itruncate_data(&tp, ip, iattr->ia_size);
+	/*
+	 * The first thing we do is set the size to new_size permanently on
+	 * disk.  This way we don't have to worry about anyone ever being able
+	 * to look at the data being freed even in the face of a crash.
+	 * What we're getting around here is the case where we free a block, it
+	 * is allocated to another file, it is written to, and then we crash.
+	 * If the new data gets written to the file but the log buffers
+	 * containing the free and reallocation don't, then we'd end up with
+	 * garbage in the blocks being freed.  As long as we make the new size
+	 * permanent before actually freeing any blocks it doesn't matter if
+	 * they get written to.
+	 */
+	ip->i_d.di_size = newsize;
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+
+	if (newsize <= oldsize) {
+		error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, newsize);
 		if (error)
 			goto out_trans_abort;
 

fs/xfs/xfs_qm_syscalls.c

@@ -31,6 +31,7 @@
 #include "xfs_mount.h"
 #include "xfs_bmap_btree.h"
 #include "xfs_inode.h"
+#include "xfs_inode_item.h"
 #include "xfs_itable.h"
 #include "xfs_bmap.h"
 #include "xfs_rtalloc.h"
@@ -263,13 +264,18 @@ xfs_qm_scall_trunc_qfile(
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, 0);
 
-	error = xfs_itruncate_data(&tp, ip, 0);
+	ip->i_d.di_size = 0;
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+
+	error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, 0);
 	if (error) {
 		xfs_trans_cancel(tp, XFS_TRANS_RELEASE_LOG_RES |
 				     XFS_TRANS_ABORT);
 		goto out_unlock;
 	}
 
+	ASSERT(ip->i_d.di_nextents == 0);
+
 	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
 	error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
 

fs/xfs/xfs_super.c

@@ -828,14 +828,6 @@ xfs_fs_inode_init_once(
 	/* xfs inode */
 	atomic_set(&ip->i_pincount, 0);
 	spin_lock_init(&ip->i_flags_lock);
-	init_waitqueue_head(&ip->i_ipin_wait);
-	/*
-	 * Because we want to use a counting completion, complete
-	 * the flush completion once to allow a single access to
-	 * the flush completion without blocking.
-	 */
-	init_completion(&ip->i_flush);
-	complete(&ip->i_flush);
 
 	mrlock_init(&ip->i_lock, MRLOCK_ALLOW_EQUAL_PRI|MRLOCK_BARRIER,
 		     "xfsino", ip->i_ino);

fs/xfs/xfs_sync.c

@@ -707,14 +707,13 @@ xfs_reclaim_inode_grab(
 		return 1;
 
 	/*
-	 * do some unlocked checks first to avoid unnecessary lock traffic.
-	 * The first is a flush lock check, the second is a already in reclaim
-	 * check. Only do these checks if we are not going to block on locks.
+	 * If we are asked for non-blocking operation, do unlocked checks to
+	 * see if the inode already is being flushed or in reclaim to avoid
+	 * lock traffic.
 	 */
 	if ((flags & SYNC_TRYLOCK) &&
-	    (!ip->i_flush.done || __xfs_iflags_test(ip, XFS_IRECLAIM))) {
+	    __xfs_iflags_test(ip, XFS_IFLOCK | XFS_IRECLAIM))
 		return 1;
-	}
 
 	/*
 	 * The radix tree lock here protects a thread in xfs_iget from racing

fs/xfs/xfs_trace.h

@@ -891,7 +891,6 @@ DECLARE_EVENT_CLASS(xfs_file_class,
 		__field(dev_t, dev)
 		__field(xfs_ino_t, ino)
 		__field(xfs_fsize_t, size)
-		__field(xfs_fsize_t, new_size)
 		__field(loff_t, offset)
 		__field(size_t, count)
 		__field(int, flags)
@@ -900,17 +899,15 @@ DECLARE_EVENT_CLASS(xfs_file_class,
 		__entry->dev = VFS_I(ip)->i_sb->s_dev;
 		__entry->ino = ip->i_ino;
 		__entry->size = ip->i_d.di_size;
-		__entry->new_size = ip->i_new_size;
 		__entry->offset = offset;
 		__entry->count = count;
 		__entry->flags = flags;
 	),
-	TP_printk("dev %d:%d ino 0x%llx size 0x%llx new_size 0x%llx "
+	TP_printk("dev %d:%d ino 0x%llx size 0x%llx "
 		  "offset 0x%llx count 0x%zx ioflags %s",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->ino,
 		  __entry->size,
-		  __entry->new_size,
 		  __entry->offset,
 		  __entry->count,
 		  __print_flags(__entry->flags, "|", XFS_IO_FLAGS))
@@ -978,7 +975,6 @@ DECLARE_EVENT_CLASS(xfs_imap_class,
 		__field(dev_t, dev)
 		__field(xfs_ino_t, ino)
 		__field(loff_t, size)
-		__field(loff_t, new_size)
 		__field(loff_t, offset)
 		__field(size_t, count)
 		__field(int, type)
@@ -990,7 +986,6 @@ DECLARE_EVENT_CLASS(xfs_imap_class,
 		__entry->dev = VFS_I(ip)->i_sb->s_dev;
 		__entry->ino = ip->i_ino;
 		__entry->size = ip->i_d.di_size;
-		__entry->new_size = ip->i_new_size;
 		__entry->offset = offset;
 		__entry->count = count;
 		__entry->type = type;
@@ -998,13 +993,11 @@ DECLARE_EVENT_CLASS(xfs_imap_class,
 		__entry->startblock = irec ? irec->br_startblock : 0;
 		__entry->blockcount = irec ? irec->br_blockcount : 0;
 	),
-	TP_printk("dev %d:%d ino 0x%llx size 0x%llx new_size 0x%llx "
-		  "offset 0x%llx count %zd type %s "
-		  "startoff 0x%llx startblock %lld blockcount 0x%llx",
+	TP_printk("dev %d:%d ino 0x%llx size 0x%llx offset 0x%llx count %zd "
+		  "type %s startoff 0x%llx startblock %lld blockcount 0x%llx",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->ino,
 		  __entry->size,
-		  __entry->new_size,
 		  __entry->offset,
 		  __entry->count,
 		  __print_symbolic(__entry->type, XFS_IO_TYPES),
@@ -1031,26 +1024,23 @@ DECLARE_EVENT_CLASS(xfs_simple_io_class,
 		__field(xfs_ino_t, ino)
 		__field(loff_t, isize)
 		__field(loff_t, disize)
-		__field(loff_t, new_size)
 		__field(loff_t, offset)
 		__field(size_t, count)
 	),
 	TP_fast_assign(
 		__entry->dev = VFS_I(ip)->i_sb->s_dev;
 		__entry->ino = ip->i_ino;
-		__entry->isize = ip->i_size;
+		__entry->isize = VFS_I(ip)->i_size;
 		__entry->disize = ip->i_d.di_size;
-		__entry->new_size = ip->i_new_size;
 		__entry->offset = offset;
 		__entry->count = count;
 	),
-	TP_printk("dev %d:%d ino 0x%llx isize 0x%llx disize 0x%llx new_size 0x%llx "
+	TP_printk("dev %d:%d ino 0x%llx isize 0x%llx disize 0x%llx "
 		  "offset 0x%llx count %zd",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->ino,
 		  __entry->isize,
 		  __entry->disize,
-		  __entry->new_size,
 		  __entry->offset,
 		  __entry->count)
 );
@@ -1090,8 +1080,8 @@ DECLARE_EVENT_CLASS(xfs_itrunc_class,
 DEFINE_EVENT(xfs_itrunc_class, name, \
 	TP_PROTO(struct xfs_inode *ip, xfs_fsize_t new_size), \
 	TP_ARGS(ip, new_size))
-DEFINE_ITRUNC_EVENT(xfs_itruncate_data_start);
-DEFINE_ITRUNC_EVENT(xfs_itruncate_data_end);
+DEFINE_ITRUNC_EVENT(xfs_itruncate_extents_start);
+DEFINE_ITRUNC_EVENT(xfs_itruncate_extents_end);
 
 TRACE_EVENT(xfs_pagecache_inval,
 	TP_PROTO(struct xfs_inode *ip, xfs_off_t start, xfs_off_t finish),
@@ -1568,7 +1558,6 @@ DECLARE_EVENT_CLASS(xfs_swap_extent_class,
 		__field(xfs_ino_t, ino)
 		__field(int, format)
 		__field(int, nex)
-		__field(int, max_nex)
 		__field(int, broot_size)
 		__field(int, fork_off)
 	),
@@ -1578,18 +1567,16 @@ DECLARE_EVENT_CLASS(xfs_swap_extent_class,
 		__entry->ino = ip->i_ino;
 		__entry->format = ip->i_d.di_format;
 		__entry->nex = ip->i_d.di_nextents;
-		__entry->max_nex = ip->i_df.if_ext_max;
 		__entry->broot_size = ip->i_df.if_broot_bytes;
 		__entry->fork_off = XFS_IFORK_BOFF(ip);
 	),
 	TP_printk("dev %d:%d ino 0x%llx (%s), %s format, num_extents %d, "
-		  "Max in-fork extents %d, broot size %d, fork offset %d",
+		  "broot size %d, fork offset %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->ino,
 		  __print_symbolic(__entry->which, XFS_SWAPEXT_INODES),
 		  __print_symbolic(__entry->format, XFS_INODE_FORMAT_STR),
 		  __entry->nex,
-		  __entry->max_nex,
 		  __entry->broot_size,
 		  __entry->fork_off)
 )

fs/xfs/xfs_vnodeops.c

@@ -175,7 +175,7 @@ xfs_free_eofblocks(
 	 * 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)ip->i_size));
+	end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_ISIZE(ip));
 	last_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_MAXIOFFSET(mp));
 	if (last_fsb <= end_fsb)
 		return 0;
@@ -226,7 +226,14 @@ xfs_free_eofblocks(
 		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		xfs_trans_ijoin(tp, ip, 0);
 
-		error = xfs_itruncate_data(&tp, ip, ip->i_size);
+		/*
+		 * 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(&tp, ip, XFS_DATA_FORK,
+					      XFS_ISIZE(ip));
 		if (error) {
 			/*
 			 * If we get an error at this point we simply don't
@@ -540,8 +547,8 @@ xfs_release(
 		return 0;
 
 	if ((S_ISREG(ip->i_d.di_mode) &&
-	     ((ip->i_size > 0) || (VN_CACHED(VFS_I(ip)) > 0 ||
-	       ip->i_delayed_blks > 0)) &&
+	     (VFS_I(ip)->i_size > 0 ||
+	      (VN_CACHED(VFS_I(ip)) > 0 || ip->i_delayed_blks > 0)) &&
 	     (ip->i_df.if_flags & XFS_IFEXTENTS))  &&
 	    (!(ip->i_d.di_flags & (XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND)))) {
 
@@ -618,7 +625,7 @@ xfs_inactive(
 	 * only one with a reference to the inode.
 	 */
 	truncate = ((ip->i_d.di_nlink == 0) &&
-	    ((ip->i_d.di_size != 0) || (ip->i_size != 0) ||
+	    ((ip->i_d.di_size != 0) || XFS_ISIZE(ip) != 0 ||
 	     (ip->i_d.di_nextents > 0) || (ip->i_delayed_blks > 0)) &&
 	    S_ISREG(ip->i_d.di_mode));
 
@@ -632,12 +639,12 @@ xfs_inactive(
 
 	if (ip->i_d.di_nlink != 0) {
 		if ((S_ISREG(ip->i_d.di_mode) &&
-                     ((ip->i_size > 0) || (VN_CACHED(VFS_I(ip)) > 0 ||
-                       ip->i_delayed_blks > 0)) &&
-		      (ip->i_df.if_flags & XFS_IFEXTENTS) &&
-		     (!(ip->i_d.di_flags &
+		    (VFS_I(ip)->i_size > 0 ||
+		     (VN_CACHED(VFS_I(ip)) > 0 || ip->i_delayed_blks > 0)) &&
+		    (ip->i_df.if_flags & XFS_IFEXTENTS) &&
+		    (!(ip->i_d.di_flags &
 				(XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND)) ||
-		      (ip->i_delayed_blks != 0)))) {
+		     ip->i_delayed_blks != 0))) {
 			error = xfs_free_eofblocks(mp, ip, 0);
 			if (error)
 				return VN_INACTIVE_CACHE;
@@ -670,13 +677,18 @@ xfs_inactive(
 		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		xfs_trans_ijoin(tp, ip, 0);
 
-		error = xfs_itruncate_data(&tp, ip, 0);
+		ip->i_d.di_size = 0;
+		xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+
+		error = xfs_itruncate_extents(&tp, ip, XFS_DATA_FORK, 0);
 		if (error) {
 			xfs_trans_cancel(tp,
 				XFS_TRANS_RELEASE_LOG_RES | XFS_TRANS_ABORT);
 			xfs_iunlock(ip, XFS_IOLOCK_EXCL | XFS_ILOCK_EXCL);
 			return VN_INACTIVE_CACHE;
 		}
+
+		ASSERT(ip->i_d.di_nextents == 0);
 	} else if (S_ISLNK(ip->i_d.di_mode)) {
 
 		/*
@@ -1961,11 +1973,11 @@ xfs_zero_remaining_bytes(
 	 * since nothing can read beyond eof.  The space will
 	 * be zeroed when the file is extended anyway.
 	 */
-	if (startoff >= ip->i_size)
+	if (startoff >= XFS_ISIZE(ip))
 		return 0;
 
-	if (endoff > ip->i_size)
-		endoff = ip->i_size;
+	if (endoff > XFS_ISIZE(ip))
+		endoff = XFS_ISIZE(ip);
 
 	bp = xfs_buf_get_uncached(XFS_IS_REALTIME_INODE(ip) ?
 					mp->m_rtdev_targp : mp->m_ddev_targp,
@@ -2260,7 +2272,7 @@ xfs_change_file_space(
 		bf->l_start += offset;
 		break;
 	case 2: /*SEEK_END*/
-		bf->l_start += ip->i_size;
+		bf->l_start += XFS_ISIZE(ip);
 		break;
 	default:
 		return XFS_ERROR(EINVAL);
@@ -2277,7 +2289,7 @@ xfs_change_file_space(
 	bf->l_whence = 0;
 
 	startoffset = bf->l_start;
-	fsize = ip->i_size;
+	fsize = XFS_ISIZE(ip);
 
 	/*
 	 * XFS_IOC_RESVSP and XFS_IOC_UNRESVSP will reserve or unreserve