1 files changed, 93 insertions, 60 deletions

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 7a9048c4c2f9..568a9332efd2 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -750,6 +750,7 @@ xfs_ialloc(
 	xfs_buf_t	**ialloc_context,
 	xfs_inode_t	**ipp)
 {
+	struct inode	*dir = pip ? VFS_I(pip) : NULL;
 	struct xfs_mount *mp = tp->t_mountp;
 	xfs_ino_t	ino;
 	xfs_inode_t	*ip;
@@ -795,26 +796,17 @@ xfs_ialloc(
 		return error;
 	ASSERT(ip != NULL);
 	inode = VFS_I(ip);
-
-	/*
-	 * We always convert v1 inodes to v2 now - we only support filesystems
-	 * with >= v2 inode capability, so there is no reason for ever leaving
-	 * an inode in v1 format.
-	 */
-	if (ip->i_d.di_version == 1)
-		ip->i_d.di_version = 2;
-
-	inode->i_mode = mode;
 	set_nlink(inode, nlink);
-	ip->i_d.di_uid = xfs_kuid_to_uid(current_fsuid());
-	ip->i_d.di_gid = xfs_kgid_to_gid(current_fsgid());
 	inode->i_rdev = rdev;
-	xfs_set_projid(ip, prid);
+	ip->i_d.di_projid = prid;
 
-	if (pip && XFS_INHERIT_GID(pip)) {
-		ip->i_d.di_gid = pip->i_d.di_gid;
-		if ((VFS_I(pip)->i_mode & S_ISGID) && S_ISDIR(mode))
-			inode->i_mode |= S_ISGID;
+	if (dir && !(dir->i_mode & S_ISGID) &&
+	    (mp->m_flags & XFS_MOUNT_GRPID)) {
+		inode->i_uid = current_fsuid();
+		inode->i_gid = dir->i_gid;
+		inode->i_mode = mode;
+	} else {
+		inode_init_owner(inode, dir, mode);
 	}
 
 	/*
@@ -822,9 +814,8 @@ xfs_ialloc(
 	 * ID or one of the supplementary group IDs, the S_ISGID bit is cleared
 	 * (and only if the irix_sgid_inherit compatibility variable is set).
 	 */
-	if ((irix_sgid_inherit) &&
-	    (inode->i_mode & S_ISGID) &&
-	    (!in_group_p(xfs_gid_to_kgid(ip->i_d.di_gid))))
+	if (irix_sgid_inherit &&
+	    (inode->i_mode & S_ISGID) && !in_group_p(inode->i_gid))
 		inode->i_mode &= ~S_ISGID;
 
 	ip->i_d.di_size = 0;
@@ -841,7 +832,7 @@ xfs_ialloc(
 	ip->i_d.di_dmstate = 0;
 	ip->i_d.di_flags = 0;
 
-	if (ip->i_d.di_version == 3) {
+	if (xfs_sb_version_has_v3inode(&mp->m_sb)) {
 		inode_set_iversion(inode, 1);
 		ip->i_d.di_flags2 = 0;
 		ip->i_d.di_cowextsize = 0;
@@ -849,7 +840,6 @@ xfs_ialloc(
 		ip->i_d.di_crtime.t_nsec = (int32_t)tv.tv_nsec;
 	}
 
-
 	flags = XFS_ILOG_CORE;
 	switch (mode & S_IFMT) {
 	case S_IFIFO:
@@ -902,20 +892,13 @@ xfs_ialloc(
 
 			ip->i_d.di_flags |= di_flags;
 		}
-		if (pip &&
-		    (pip->i_d.di_flags2 & XFS_DIFLAG2_ANY) &&
-		    pip->i_d.di_version == 3 &&
-		    ip->i_d.di_version == 3) {
-			uint64_t	di_flags2 = 0;
-
+		if (pip && (pip->i_d.di_flags2 & XFS_DIFLAG2_ANY)) {
 			if (pip->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) {
-				di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
+				ip->i_d.di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
 				ip->i_d.di_cowextsize = pip->i_d.di_cowextsize;
 			}
 			if (pip->i_d.di_flags2 & XFS_DIFLAG2_DAX)
-				di_flags2 |= XFS_DIFLAG2_DAX;
-
-			ip->i_d.di_flags2 |= di_flags2;
+				ip->i_d.di_flags2 |= XFS_DIFLAG2_DAX;
 		}
 		/* FALLTHROUGH */
 	case S_IFLNK:
@@ -1117,7 +1100,6 @@ xfs_bumplink(
 {
 	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
 
-	ASSERT(ip->i_d.di_version > 1);
 	inc_nlink(VFS_I(ip));
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 }
@@ -1153,8 +1135,7 @@ xfs_create(
 	/*
 	 * Make sure that we have allocated dquot(s) on disk.
 	 */
-	error = xfs_qm_vop_dqalloc(dp, xfs_kuid_to_uid(current_fsuid()),
-					xfs_kgid_to_gid(current_fsgid()), prid,
+	error = xfs_qm_vop_dqalloc(dp, current_fsuid(), current_fsgid(), prid,
 					XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
 					&udqp, &gdqp, &pdqp);
 	if (error)
@@ -1304,8 +1285,7 @@ xfs_create_tmpfile(
 	/*
 	 * Make sure that we have allocated dquot(s) on disk.
 	 */
-	error = xfs_qm_vop_dqalloc(dp, xfs_kuid_to_uid(current_fsuid()),
-				xfs_kgid_to_gid(current_fsgid()), prid,
+	error = xfs_qm_vop_dqalloc(dp, current_fsuid(), current_fsgid(), prid,
 				XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
 				&udqp, &gdqp, &pdqp);
 	if (error)
@@ -1418,7 +1398,7 @@ xfs_link(
 	 * the tree quota mechanism could be circumvented.
 	 */
 	if (unlikely((tdp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) &&
-		     (xfs_get_projid(tdp) != xfs_get_projid(sip)))) {
+		     tdp->i_d.di_projid != sip->i_d.di_projid)) {
 		error = -EXDEV;
 		goto error_return;
 	}
@@ -1513,10 +1493,8 @@ xfs_itruncate_extents_flags(
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp = *tpp;
 	xfs_fileoff_t		first_unmap_block;
-	xfs_fileoff_t		last_block;
 	xfs_filblks_t		unmap_len;
 	int			error = 0;
-	int			done = 0;
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 	ASSERT(!atomic_read(&VFS_I(ip)->i_count) ||
@@ -1536,21 +1514,22 @@ xfs_itruncate_extents_flags(
 	 * the end of the file (in a crash where the space is allocated
 	 * but the inode size is not yet updated), simply remove any
 	 * blocks which show up between the new EOF and the maximum
-	 * possible file size.  If the first block to be removed is
-	 * beyond the maximum file size (ie it is the same as last_block),
-	 * then there is nothing to do.
+	 * possible file size.
+	 *
+	 * We have to free all the blocks to the bmbt maximum offset, even if
+	 * the page cache can't scale that far.
 	 */
 	first_unmap_block = XFS_B_TO_FSB(mp, (xfs_ufsize_t)new_size);
-	last_block = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
-	if (first_unmap_block == last_block)
+	if (first_unmap_block >= XFS_MAX_FILEOFF) {
+		WARN_ON_ONCE(first_unmap_block > XFS_MAX_FILEOFF);
 		return 0;
+	}
 
-	ASSERT(first_unmap_block < last_block);
-	unmap_len = last_block - first_unmap_block + 1;
-	while (!done) {
+	unmap_len = XFS_MAX_FILEOFF - first_unmap_block + 1;
+	while (unmap_len > 0) {
 		ASSERT(tp->t_firstblock == NULLFSBLOCK);
-		error = xfs_bunmapi(tp, ip, first_unmap_block, unmap_len, flags,
-				    XFS_ITRUNC_MAX_EXTENTS, &done);
+		error = __xfs_bunmapi(tp, ip, first_unmap_block, &unmap_len,
+				flags, XFS_ITRUNC_MAX_EXTENTS);
 		if (error)
 			goto out;
 
@@ -1570,7 +1549,7 @@ xfs_itruncate_extents_flags(
 	if (whichfork == XFS_DATA_FORK) {
 		/* Remove all pending CoW reservations. */
 		error = xfs_reflink_cancel_cow_blocks(ip, &tp,
-				first_unmap_block, last_block, true);
+				first_unmap_block, XFS_MAX_FILEOFF, true);
 		if (error)
 			goto out;
 
@@ -2149,8 +2128,10 @@ xfs_iunlink_update_bucket(
 	 * passed in because either we're adding or removing ourselves from the
 	 * head of the list.
 	 */
-	if (old_value == new_agino)
+	if (old_value == new_agino) {
+		xfs_buf_mark_corrupt(agibp);
 		return -EFSCORRUPTED;
+	}
 
 	agi->agi_unlinked[bucket_index] = cpu_to_be32(new_agino);
 	offset = offsetof(struct xfs_agi, agi_unlinked) +
@@ -2213,6 +2194,8 @@ xfs_iunlink_update_inode(
 	/* Make sure the old pointer isn't garbage. */
 	old_value = be32_to_cpu(dip->di_next_unlinked);
 	if (!xfs_verify_agino_or_null(mp, agno, old_value)) {
+		xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, dip,
+				sizeof(*dip), __this_address);
 		error = -EFSCORRUPTED;
 		goto out;
 	}
@@ -2224,8 +2207,11 @@ xfs_iunlink_update_inode(
 	 */
 	*old_next_agino = old_value;
 	if (old_value == next_agino) {
-		if (next_agino != NULLAGINO)
+		if (next_agino != NULLAGINO) {
+			xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__,
+					dip, sizeof(*dip), __this_address);
 			error = -EFSCORRUPTED;
+		}
 		goto out;
 	}
 
@@ -2276,8 +2262,10 @@ xfs_iunlink(
 	 */
 	next_agino = be32_to_cpu(agi->agi_unlinked[bucket_index]);
 	if (next_agino == agino ||
-	    !xfs_verify_agino_or_null(mp, agno, next_agino))
+	    !xfs_verify_agino_or_null(mp, agno, next_agino)) {
+		xfs_buf_mark_corrupt(agibp);
 		return -EFSCORRUPTED;
+	}
 
 	if (next_agino != NULLAGINO) {
 		struct xfs_perag	*pag;
@@ -2547,7 +2535,7 @@ xfs_ifree_cluster(
 	xfs_daddr_t		blkno;
 	xfs_buf_t		*bp;
 	xfs_inode_t		*ip;
-	xfs_inode_log_item_t	*iip;
+	struct xfs_inode_log_item *iip;
 	struct xfs_log_item	*lip;
 	struct xfs_perag	*pag;
 	struct xfs_ino_geometry	*igeo = M_IGEO(mp);
@@ -2584,8 +2572,10 @@ xfs_ifree_cluster(
 					mp->m_bsize * igeo->blocks_per_cluster,
 					XBF_UNMAPPED);
 
-		if (!bp)
+		if (!bp) {
+			xfs_perag_put(pag);
 			return -ENOMEM;
+		}
 
 		/*
 		 * This buffer may not have been correctly initialised as we
@@ -2607,7 +2597,7 @@ xfs_ifree_cluster(
 		 */
 		list_for_each_entry(lip, &bp->b_li_list, li_bio_list) {
 			if (lip->li_type == XFS_LI_INODE) {
-				iip = (xfs_inode_log_item_t *)lip;
+				iip = (struct xfs_inode_log_item *)lip;
 				ASSERT(iip->ili_logged == 1);
 				lip->li_cb = xfs_istale_done;
 				xfs_trans_ail_copy_lsn(mp->m_ail,
@@ -3215,6 +3205,7 @@ xfs_rename(
 	struct xfs_trans	*tp;
 	struct xfs_inode	*wip = NULL;		/* whiteout inode */
 	struct xfs_inode	*inodes[__XFS_SORT_INODES];
+	int			i;
 	int			num_inodes = __XFS_SORT_INODES;
 	bool			new_parent = (src_dp != target_dp);
 	bool			src_is_directory = S_ISDIR(VFS_I(src_ip)->i_mode);
@@ -3288,7 +3279,7 @@ xfs_rename(
 	 * tree quota mechanism would be circumvented.
 	 */
 	if (unlikely((target_dp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) &&
-		     (xfs_get_projid(target_dp) != xfs_get_projid(src_ip)))) {
+		     target_dp->i_d.di_projid != src_ip->i_d.di_projid)) {
 		error = -EXDEV;
 		goto out_trans_cancel;
 	}
@@ -3327,6 +3318,30 @@ xfs_rename(
 	}
 
 	/*
+	 * Lock the AGI buffers we need to handle bumping the nlink of the
+	 * whiteout inode off the unlinked list and to handle dropping the
+	 * nlink of the target inode.  Per locking order rules, do this in
+	 * increasing AG order and before directory block allocation tries to
+	 * grab AGFs because we grab AGIs before AGFs.
+	 *
+	 * The (vfs) caller must ensure that if src is a directory then
+	 * target_ip is either null or an empty directory.
+	 */
+	for (i = 0; i < num_inodes && inodes[i] != NULL; i++) {
+		if (inodes[i] == wip ||
+		    (inodes[i] == target_ip &&
+		     (VFS_I(target_ip)->i_nlink == 1 || src_is_directory))) {
+			struct xfs_buf	*bp;
+			xfs_agnumber_t	agno;
+
+			agno = XFS_INO_TO_AGNO(mp, inodes[i]->i_ino);
+			error = xfs_read_agi(mp, tp, agno, &bp);
+			if (error)
+				goto out_trans_cancel;
+		}
+	}
+
+	/*
 	 * Directory entry creation below may acquire the AGF. Remove
 	 * the whiteout from the unlinked list first to preserve correct
 	 * AGI/AGF locking order. This dirties the transaction so failures
@@ -3796,7 +3811,6 @@ xfs_iflush_int(
 	ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE ||
 	       ip->i_d.di_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK));
 	ASSERT(iip != NULL && iip->ili_fields != 0);
-	ASSERT(ip->i_d.di_version > 1);
 
 	/* set *dip = inode's place in the buffer */
 	dip = xfs_buf_offset(bp, ip->i_imap.im_boffset);
@@ -3857,7 +3871,7 @@ xfs_iflush_int(
 	 * backwards compatibility with old kernels that predate logging all
 	 * inode changes.
 	 */
-	if (ip->i_d.di_version < 3)
+	if (!xfs_sb_version_has_v3inode(&mp->m_sb))
 		ip->i_d.di_flushiter++;
 
 	/* Check the inline fork data before we write out. */
@@ -3940,3 +3954,22 @@ xfs_irele(
 	trace_xfs_irele(ip, _RET_IP_);
 	iput(VFS_I(ip));
 }
+
+/*
+ * Ensure all commited transactions touching the inode are written to the log.
+ */
+int
+xfs_log_force_inode(
+	struct xfs_inode	*ip)
+{
+	xfs_lsn_t		lsn = 0;
+
+	xfs_ilock(ip, XFS_ILOCK_SHARED);
+	if (xfs_ipincount(ip))
+		lsn = ip->i_itemp->ili_last_lsn;
+	xfs_iunlock(ip, XFS_ILOCK_SHARED);
+
+	if (!lsn)
+		return 0;
+	return xfs_log_force_lsn(ip->i_mount, lsn, XFS_LOG_SYNC, NULL);
+}