Merge tag 'vfs-7.3-rc1.ovl' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull overlayfs updates from Christian Brauner:
 "This lets the merged overlayfs mount itself be idmapped through
  mount_setattr(MOUNT_ATTR_IDMAP), in addition to the already supported
  idmapped lower and upper layers. The same overlay tree can then be
  exposed under a different ownership view.

  Overlayfs already normalizes every underlying id through the relevant
  layer idmap when ovl_copyattr() copies attributes into the overlay
  inode. So the overlay inode's i_uid and i_gid are overlay-final ids.

  The overlay mount idmap composes on top of that and is applied at the
  overlay-inode boundary only while the underlying layers keep being
  accessed with the mounter's credentials through their own (possibly
  idmapped) mounts.

  So this only changes how the caller sees the overlay inode and never
  widens the mounter's access to the layers. The second,
  mounter-credential check in ovl_permission() against the real inode
  stays on the layer idmap.

  Most paths need no change because the VFS applies the mount idmap to
  the overlay inode before overlayfs runs or after it returns at the
  syscall boundary. Overlayfs only has to change where it bypasses the
  generic path.

  This also included is a fix for a double end_creating() on the
  overlayfs casefold-mismatch path"

* tag 'vfs-7.3-rc1.ovl' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  ovl: fix double end_creating() on the casefold-mismatch path
  ovl: document security.capability idmapping on the xattr forward paths
  selftests/filesystems/overlayfs: test idmapped overlay mounts
  selftests/filesystems/overlayfs: fix set_layers_via_fds link error
  docs: document idmapped overlay mounts
  ovl: allow idmapping overlay mounts
  ovl: handle idmapped mounts in ovl_set_acl()
  ovl: handle idmapped mounts in ovl_getattr()
  ovl: handle idmapped mounts in ovl_setattr()
  ovl: handle idmapped mounts in ovl_permission()
  ovl: handle idmapped mounts in ovl_create_object() and ovl_tmpfile()

5 files changed, 32 insertions, 15 deletions

diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index 88bcf98d287d..7beb0af26498 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -188,7 +188,6 @@ struct dentry *ovl_create_real(struct ovl_fs *ofs, struct dentry *parent,
 			if (!err && ofs->casefold != ovl_dentry_casefolded(newdentry)) {
 				pr_warn_ratelimited("wrong inherited casefold (%pd2)\n",
 						    newdentry);
-				end_creating(newdentry);
 				err = -EINVAL;
 			}
 			break;
@@ -689,8 +688,8 @@ static int ovl_create_or_link(struct dentry *dentry, struct inode *inode,
 	return err;
 }
 
-static int ovl_create_object(struct dentry *dentry, int mode, dev_t rdev,
-			     const char *link)
+static int ovl_create_object(struct mnt_idmap *idmap, struct dentry *dentry,
+			     int mode, dev_t rdev, const char *link)
 {
 	int err;
 	struct inode *inode;
@@ -717,7 +716,7 @@ static int ovl_create_object(struct dentry *dentry, int mode, dev_t rdev,
 	inode_state_set(inode, I_CREATING);
 	spin_unlock(&inode->i_lock);
 
-	inode_init_owner(&nop_mnt_idmap, inode, dentry->d_parent->d_inode, mode);
+	inode_init_owner(idmap, inode, dentry->d_parent->d_inode, mode);
 	attr.mode = inode->i_mode;
 
 	err = ovl_create_or_link(dentry, inode, &attr, false);
@@ -734,13 +733,13 @@ out:
 static int ovl_create(struct mnt_idmap *idmap, struct inode *dir,
 		      struct dentry *dentry, umode_t mode)
 {
-	return ovl_create_object(dentry, (mode & 07777) | S_IFREG, 0, NULL);
+	return ovl_create_object(idmap, dentry, (mode & 07777) | S_IFREG, 0, NULL);
 }
 
 static struct dentry *ovl_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 				struct dentry *dentry, umode_t mode)
 {
-	return ERR_PTR(ovl_create_object(dentry, (mode & 07777) | S_IFDIR, 0, NULL));
+	return ERR_PTR(ovl_create_object(idmap, dentry, (mode & 07777) | S_IFDIR, 0, NULL));
 }
 
 static int ovl_mknod(struct mnt_idmap *idmap, struct inode *dir,
@@ -750,13 +749,13 @@ static int ovl_mknod(struct mnt_idmap *idmap, struct inode *dir,
 	if (S_ISCHR(mode) && rdev == WHITEOUT_DEV)
 		return -EPERM;
 
-	return ovl_create_object(dentry, mode, rdev, NULL);
+	return ovl_create_object(idmap, dentry, mode, rdev, NULL);
 }
 
 static int ovl_symlink(struct mnt_idmap *idmap, struct inode *dir,
 		       struct dentry *dentry, const char *link)
 {
-	return ovl_create_object(dentry, S_IFLNK, 0, link);
+	return ovl_create_object(idmap, dentry, S_IFLNK, 0, link);
 }
 
 static int ovl_set_link_redirect(struct dentry *dentry)
@@ -1444,7 +1443,7 @@ static int ovl_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
 	if (!inode)
 		goto drop_write;
 
-	inode_init_owner(&nop_mnt_idmap, inode, dir, mode);
+	inode_init_owner(idmap, inode, dir, mode);
 	err = ovl_create_tmpfile(file, dentry, inode, inode->i_mode);
 	if (err)
 		goto put_inode;
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index bc71231cad53..401cb8c75520 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -26,10 +26,18 @@ int ovl_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 	bool full_copy_up = false;
 	struct dentry *upperdentry;
 
-	err = setattr_prepare(&nop_mnt_idmap, dentry, attr);
+	err = setattr_prepare(idmap, dentry, attr);
 	if (err)
 		return err;
 
+	/* Rebase ownership from the mount idmap into overlay id space. */
+	if (attr->ia_valid & ATTR_UID)
+		attr->ia_vfsuid = VFSUIDT_INIT(from_vfsuid(idmap,
+				i_user_ns(d_inode(dentry)), attr->ia_vfsuid));
+	if (attr->ia_valid & ATTR_GID)
+		attr->ia_vfsgid = VFSGIDT_INIT(from_vfsgid(idmap,
+				i_user_ns(d_inode(dentry)), attr->ia_vfsgid));
+
 	if (attr->ia_valid & ATTR_SIZE) {
 		/* Truncate should trigger data copy up as well */
 		full_copy_up = true;
@@ -172,6 +180,8 @@ int ovl_getattr(struct mnt_idmap *idmap, const struct path *path,
 	int fsid = 0;
 	int err;
 	bool metacopy_blocks = false;
+	vfsuid_t vfsuid;
+	vfsgid_t vfsgid;
 
 	metacopy_blocks = ovl_is_metacopy_dentry(dentry);
 
@@ -284,6 +294,12 @@ int ovl_getattr(struct mnt_idmap *idmap, const struct path *path,
 	if (!is_dir && ovl_test_flag(OVL_INDEX, d_inode(dentry)))
 		stat->nlink = dentry->d_inode->i_nlink;
 
+	/* Map ownership of the real inode through the overlay mount idmap. */
+	vfsuid = make_vfsuid(idmap, i_user_ns(inode), stat->uid);
+	vfsgid = make_vfsgid(idmap, i_user_ns(inode), stat->gid);
+	stat->uid = vfsuid_into_kuid(vfsuid);
+	stat->gid = vfsgid_into_kgid(vfsgid);
+
 	return err;
 }
 
@@ -306,7 +322,7 @@ int ovl_permission(struct mnt_idmap *idmap,
 	 * Check overlay inode with the creds of task and underlying inode
 	 * with creds of mounter
 	 */
-	err = generic_permission(&nop_mnt_idmap, inode, mask);
+	err = generic_permission(idmap, inode, mask);
 	if (err)
 		return err;
 
@@ -534,7 +550,7 @@ int ovl_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
 		return -EOPNOTSUPP;
 	if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode))
 		return acl ? -EACCES : 0;
-	if (!inode_owner_or_capable(&nop_mnt_idmap, inode))
+	if (!inode_owner_or_capable(idmap, inode))
 		return -EPERM;
 
 	/*
@@ -542,8 +558,8 @@ int ovl_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
 	 * be done with mounter's capabilities and so that won't do it for us).
 	 */
 	if (unlikely(inode->i_mode & S_ISGID) && type == ACL_TYPE_ACCESS &&
-	    !in_group_p(inode->i_gid) &&
-	    !capable_wrt_inode_uidgid(&nop_mnt_idmap, inode, CAP_FSETID)) {
+	    !in_group_or_capable(idmap, inode,
+				 i_gid_into_vfsgid(idmap, inode))) {
 		struct iattr iattr = { .ia_valid = ATTR_KILL_SGID };
 
 		err = ovl_setattr(&nop_mnt_idmap, dentry, &iattr);
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index b75df37f70ac..e0d8c6152e9f 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -320,6 +320,7 @@ static inline int ovl_do_setxattr(struct ovl_fs *ofs, struct dentry *dentry,
 				  const char *name, const void *value,
 				  size_t size, int flags)
 {
+	/* Use vfs_setxattr(), not __vfs_setxattr(): it idmaps the security.capability rootid. */
 	int err = vfs_setxattr(ovl_upper_mnt_idmap(ofs), dentry, name,
 			       value, size, flags);
 
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 60b808b85fc4..e487597337e8 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -1574,7 +1574,7 @@ struct file_system_type ovl_fs_type = {
 	.name			= "overlay",
 	.init_fs_context	= ovl_init_fs_context,
 	.parameters		= ovl_parameter_spec,
-	.fs_flags		= FS_USERNS_MOUNT,
+	.fs_flags		= FS_USERNS_MOUNT | FS_ALLOW_IDMAP,
 	.kill_sb		= kill_anon_super,
 };
 MODULE_ALIAS_FS("overlay");
diff --git a/fs/overlayfs/xattrs.c b/fs/overlayfs/xattrs.c
index 859e80ae6f40..5ae44b9c8790 100644
--- a/fs/overlayfs/xattrs.c
+++ b/fs/overlayfs/xattrs.c
@@ -84,6 +84,7 @@ static int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char
 	struct path realpath;
 
 	ovl_i_path_real(inode, &realpath);
+	/* Use vfs_getxattr(), not __vfs_getxattr(): it idmaps the security.capability rootid. */
 	with_ovl_creds(dentry->d_sb)
 		return vfs_getxattr(mnt_idmap(realpath.mnt), realpath.dentry, name, value, size);
 }