1 files changed, 108 insertions, 48 deletions

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index b7352bc4c815..46a861d55e48 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -766,6 +766,7 @@ xfs_inode_inherit_flags2(
  */
 static int
 xfs_init_new_inode(
+	struct user_namespace	*mnt_userns,
 	struct xfs_trans	*tp,
 	struct xfs_inode	*pip,
 	xfs_ino_t		ino,
@@ -775,6 +776,7 @@ xfs_init_new_inode(
 	prid_t			prid,
 	struct xfs_inode	**ipp)
 {
+	struct inode		*dir = pip ? VFS_I(pip) : NULL;
 	struct xfs_mount	*mp = tp->t_mountp;
 	struct xfs_inode	*ip;
 	unsigned int		flags;
@@ -804,18 +806,17 @@ xfs_init_new_inode(
 
 	ASSERT(ip != NULL);
 	inode = VFS_I(ip);
-	inode->i_mode = mode;
 	set_nlink(inode, nlink);
-	inode->i_uid = current_fsuid();
 	inode->i_rdev = rdev;
 	ip->i_d.di_projid = prid;
 
-	if (pip && XFS_INHERIT_GID(pip)) {
-		inode->i_gid = VFS_I(pip)->i_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 = fsuid_into_mnt(mnt_userns);
+		inode->i_gid = dir->i_gid;
+		inode->i_mode = mode;
 	} else {
-		inode->i_gid = current_fsgid();
+		inode_init_owner(mnt_userns, inode, dir, mode);
 	}
 
 	/*
@@ -824,7 +825,8 @@ xfs_init_new_inode(
 	 * (and only if the irix_sgid_inherit compatibility variable is set).
 	 */
 	if (irix_sgid_inherit &&
-	    (inode->i_mode & S_ISGID) && !in_group_p(inode->i_gid))
+	    (inode->i_mode & S_ISGID) &&
+	    !in_group_p(i_gid_into_mnt(mnt_userns, inode)))
 		inode->i_mode &= ~S_ISGID;
 
 	ip->i_d.di_size = 0;
@@ -901,6 +903,7 @@ xfs_init_new_inode(
  */
 int
 xfs_dir_ialloc(
+	struct user_namespace	*mnt_userns,
 	struct xfs_trans	**tpp,
 	struct xfs_inode	*dp,
 	umode_t			mode,
@@ -933,7 +936,8 @@ xfs_dir_ialloc(
 		return error;
 	ASSERT(ino != NULLFSINO);
 
-	return xfs_init_new_inode(*tpp, dp, ino, mode, nlink, rdev, prid, ipp);
+	return xfs_init_new_inode(mnt_userns, *tpp, dp, ino, mode, nlink, rdev,
+				  prid, ipp);
 }
 
 /*
@@ -973,6 +977,7 @@ xfs_bumplink(
 
 int
 xfs_create(
+	struct user_namespace	*mnt_userns,
 	xfs_inode_t		*dp,
 	struct xfs_name		*name,
 	umode_t			mode,
@@ -1022,23 +1027,22 @@ xfs_create(
 	 * the case we'll drop the one we have and get a more
 	 * appropriate transaction later.
 	 */
-	error = xfs_trans_alloc(mp, tres, resblks, 0, 0, &tp);
+	error = xfs_trans_alloc_icreate(mp, tres, udqp, gdqp, pdqp, resblks,
+			&tp);
 	if (error == -ENOSPC) {
 		/* flush outstanding delalloc blocks and retry */
 		xfs_flush_inodes(mp);
-		error = xfs_trans_alloc(mp, tres, resblks, 0, 0, &tp);
+		error = xfs_trans_alloc_icreate(mp, tres, udqp, gdqp, pdqp,
+				resblks, &tp);
 	}
 	if (error)
-		goto out_release_inode;
+		goto out_release_dquots;
 
 	xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT);
 	unlock_dp_on_error = true;
 
-	/*
-	 * Reserve disk quota and the inode.
-	 */
-	error = xfs_trans_reserve_quota(tp, mp, udqp, gdqp,
-						pdqp, resblks, 1, 0);
+	error = xfs_iext_count_may_overflow(dp, XFS_DATA_FORK,
+			XFS_IEXT_DIR_MANIP_CNT(mp));
 	if (error)
 		goto out_trans_cancel;
 
@@ -1047,7 +1051,8 @@ xfs_create(
 	 * entry pointing to them, but a directory also the "." entry
 	 * pointing to itself.
 	 */
-	error = xfs_dir_ialloc(&tp, dp, mode, is_dir ? 2 : 1, rdev, prid, &ip);
+	error = xfs_dir_ialloc(mnt_userns, &tp, dp, mode, is_dir ? 2 : 1, rdev,
+			       prid, &ip);
 	if (error)
 		goto out_trans_cancel;
 
@@ -1116,7 +1121,7 @@ xfs_create(
 		xfs_finish_inode_setup(ip);
 		xfs_irele(ip);
 	}
-
+ out_release_dquots:
 	xfs_qm_dqrele(udqp);
 	xfs_qm_dqrele(gdqp);
 	xfs_qm_dqrele(pdqp);
@@ -1128,6 +1133,7 @@ xfs_create(
 
 int
 xfs_create_tmpfile(
+	struct user_namespace	*mnt_userns,
 	struct xfs_inode	*dp,
 	umode_t			mode,
 	struct xfs_inode	**ipp)
@@ -1160,16 +1166,12 @@ xfs_create_tmpfile(
 	resblks = XFS_IALLOC_SPACE_RES(mp);
 	tres = &M_RES(mp)->tr_create_tmpfile;
 
-	error = xfs_trans_alloc(mp, tres, resblks, 0, 0, &tp);
-	if (error)
-		goto out_release_inode;
-
-	error = xfs_trans_reserve_quota(tp, mp, udqp, gdqp,
-						pdqp, resblks, 1, 0);
+	error = xfs_trans_alloc_icreate(mp, tres, udqp, gdqp, pdqp, resblks,
+			&tp);
 	if (error)
-		goto out_trans_cancel;
+		goto out_release_dquots;
 
-	error = xfs_dir_ialloc(&tp, dp, mode, 0, 0, prid, &ip);
+	error = xfs_dir_ialloc(mnt_userns, &tp, dp, mode, 0, 0, prid, &ip);
 	if (error)
 		goto out_trans_cancel;
 
@@ -1210,7 +1212,7 @@ xfs_create_tmpfile(
 		xfs_finish_inode_setup(ip);
 		xfs_irele(ip);
 	}
-
+ out_release_dquots:
 	xfs_qm_dqrele(udqp);
 	xfs_qm_dqrele(gdqp);
 	xfs_qm_dqrele(pdqp);
@@ -1258,6 +1260,11 @@ xfs_link(
 	xfs_trans_ijoin(tp, sip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, tdp, XFS_ILOCK_EXCL);
 
+	error = xfs_iext_count_may_overflow(tdp, XFS_DATA_FORK,
+			XFS_IEXT_DIR_MANIP_CNT(mp));
+	if (error)
+		goto error_return;
+
 	/*
 	 * If we are using project inheritance, we only allow hard link
 	 * creation in our tree when the project IDs are the same; else
@@ -2977,13 +2984,15 @@ out_trans_abort:
  */
 static int
 xfs_rename_alloc_whiteout(
+	struct user_namespace	*mnt_userns,
 	struct xfs_inode	*dp,
 	struct xfs_inode	**wip)
 {
 	struct xfs_inode	*tmpfile;
 	int			error;
 
-	error = xfs_create_tmpfile(dp, S_IFCHR | WHITEOUT_MODE, &tmpfile);
+	error = xfs_create_tmpfile(mnt_userns, dp, S_IFCHR | WHITEOUT_MODE,
+				   &tmpfile);
 	if (error)
 		return error;
 
@@ -3005,6 +3014,7 @@ xfs_rename_alloc_whiteout(
  */
 int
 xfs_rename(
+	struct user_namespace	*mnt_userns,
 	struct xfs_inode	*src_dp,
 	struct xfs_name		*src_name,
 	struct xfs_inode	*src_ip,
@@ -3017,7 +3027,7 @@ xfs_rename(
 	struct xfs_trans	*tp;
 	struct xfs_inode	*wip = NULL;		/* whiteout inode */
 	struct xfs_inode	*inodes[__XFS_SORT_INODES];
-	struct xfs_buf		*agibp;
+	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);
@@ -3036,7 +3046,7 @@ xfs_rename(
 	 */
 	if (flags & RENAME_WHITEOUT) {
 		ASSERT(!(flags & (RENAME_NOREPLACE | RENAME_EXCHANGE)));
-		error = xfs_rename_alloc_whiteout(target_dp, &wip);
+		error = xfs_rename_alloc_whiteout(mnt_userns, target_dp, &wip);
 		if (error)
 			return error;
 
@@ -3106,6 +3116,35 @@ xfs_rename(
 	/*
 	 * Check for expected errors before we dirty the transaction
 	 * so we can return an error without a transaction abort.
+	 *
+	 * Extent count overflow check:
+	 *
+	 * From the perspective of src_dp, a rename operation is essentially a
+	 * directory entry remove operation. Hence the only place where we check
+	 * for extent count overflow for src_dp is in
+	 * xfs_bmap_del_extent_real(). xfs_bmap_del_extent_real() returns
+	 * -ENOSPC when it detects a possible extent count overflow and in
+	 * response, the higher layers of directory handling code do the
+	 * following:
+	 * 1. Data/Free blocks: XFS lets these blocks linger until a
+	 *    future remove operation removes them.
+	 * 2. Dabtree blocks: XFS swaps the blocks with the last block in the
+	 *    Leaf space and unmaps the last block.
+	 *
+	 * For target_dp, there are two cases depending on whether the
+	 * destination directory entry exists or not.
+	 *
+	 * When destination directory entry does not exist (i.e. target_ip ==
+	 * NULL), extent count overflow check is performed only when transaction
+	 * has a non-zero sized space reservation associated with it.  With a
+	 * zero-sized space reservation, XFS allows a rename operation to
+	 * continue only when the directory has sufficient free space in its
+	 * data/leaf/free space blocks to hold the new entry.
+	 *
+	 * When destination directory entry exists (i.e. target_ip != NULL), all
+	 * we need to do is change the inode number associated with the already
+	 * existing entry. Hence there is no need to perform an extent count
+	 * overflow check.
 	 */
 	if (target_ip == NULL) {
 		/*
@@ -3116,6 +3155,12 @@ xfs_rename(
 			error = xfs_dir_canenter(tp, target_dp, target_name);
 			if (error)
 				goto out_trans_cancel;
+		} else {
+			error = xfs_iext_count_may_overflow(target_dp,
+					XFS_DATA_FORK,
+					XFS_IEXT_DIR_MANIP_CNT(mp));
+			if (error)
+				goto out_trans_cancel;
 		}
 	} else {
 		/*
@@ -3131,6 +3176,30 @@ 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
@@ -3182,22 +3251,6 @@ xfs_rename(
 		 * In case there is already an entry with the same
 		 * name at the destination directory, remove it first.
 		 */
-
-		/*
-		 * Check whether the replace operation will need to allocate
-		 * blocks.  This happens when the shortform directory lacks
-		 * space and we have to convert it to a block format directory.
-		 * When more blocks are necessary, we must lock the AGI first
-		 * to preserve locking order (AGI -> AGF).
-		 */
-		if (xfs_dir2_sf_replace_needblock(target_dp, src_ip->i_ino)) {
-			error = xfs_read_agi(mp, tp,
-					XFS_INO_TO_AGNO(mp, target_ip->i_ino),
-					&agibp);
-			if (error)
-				goto out_trans_cancel;
-		}
-
 		error = xfs_dir_replace(tp, target_dp, target_name,
 					src_ip->i_ino, spaceres);
 		if (error)
@@ -3273,9 +3326,16 @@ xfs_rename(
 	if (wip) {
 		error = xfs_dir_replace(tp, src_dp, src_name, wip->i_ino,
 					spaceres);
-	} else
+	} else {
+		/*
+		 * NOTE: We don't need to check for extent count overflow here
+		 * because the dir remove name code will leave the dir block in
+		 * place if the extent count would overflow.
+		 */
 		error = xfs_dir_removename(tp, src_dp, src_name, src_ip->i_ino,
 					   spaceres);
+	}
+
 	if (error)
 		goto out_trans_cancel;