Merge tag 'fs.idmapped.v6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/idmapping

Pull vfs idmapping updates from Christian Brauner:

 - Last cycle we introduced the dedicated struct mnt_idmap type for
   mount idmapping and the required infrastucture in 256c8aed2b42 ("fs:
   introduce dedicated idmap type for mounts"). As promised in last
   cycle's pull request message this converts everything to rely on
   struct mnt_idmap.

   Currently we still pass around the plain namespace that was attached
   to a mount. This is in general pretty convenient but it makes it easy
   to conflate namespaces that are relevant on the filesystem with
   namespaces that are relevant on the mount level. Especially for
   non-vfs developers without detailed knowledge in this area this was a
   potential source for bugs.

   This finishes the conversion. Instead of passing the plain namespace
   around this updates all places that currently take a pointer to a
   mnt_userns with a pointer to struct mnt_idmap.

   Now that the conversion is done all helpers down to the really
   low-level helpers only accept a struct mnt_idmap argument instead of
   two namespace arguments.

   Conflating mount and other idmappings will now cause the compiler to
   complain loudly thus eliminating the possibility of any bugs. This
   makes it impossible for filesystem developers to mix up mount and
   filesystem idmappings as they are two distinct types and require
   distinct helpers that cannot be used interchangeably.

   Everything associated with struct mnt_idmap is moved into a single
   separate file. With that change no code can poke around in struct
   mnt_idmap. It can only be interacted with through dedicated helpers.
   That means all filesystems are and all of the vfs is completely
   oblivious to the actual implementation of idmappings.

   We are now also able to extend struct mnt_idmap as we see fit. For
   example, we can decouple it completely from namespaces for users that
   don't require or don't want to use them at all. We can also extend
   the concept of idmappings so we can cover filesystem specific
   requirements.

   In combination with the vfs{g,u}id_t work we finished in v6.2 this
   makes this feature substantially more robust and thus difficult to
   implement wrong by a given filesystem and also protects the vfs.

 - Enable idmapped mounts for tmpfs and fulfill a longstanding request.

   A long-standing request from users had been to make it possible to
   create idmapped mounts for tmpfs. For example, to share the host's
   tmpfs mount between multiple sandboxes. This is a prerequisite for
   some advanced Kubernetes cases. Systemd also has a range of use-cases
   to increase service isolation. And there are more users of this.

   However, with all of the other work going on this was way down on the
   priority list but luckily someone other than ourselves picked this
   up.

   As usual the patch is tiny as all the infrastructure work had been
   done multiple kernel releases ago. In addition to all the tests that
   we already have I requested that Rodrigo add a dedicated tmpfs
   testsuite for idmapped mounts to xfstests. It is to be included into
   xfstests during the v6.3 development cycle. This should add a slew of
   additional tests.

* tag 'fs.idmapped.v6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/idmapping: (26 commits)
  shmem: support idmapped mounts for tmpfs
  fs: move mnt_idmap
  fs: port vfs{g,u}id helpers to mnt_idmap
  fs: port fs{g,u}id helpers to mnt_idmap
  fs: port i_{g,u}id_into_vfs{g,u}id() to mnt_idmap
  fs: port i_{g,u}id_{needs_}update() to mnt_idmap
  quota: port to mnt_idmap
  fs: port privilege checking helpers to mnt_idmap
  fs: port inode_owner_or_capable() to mnt_idmap
  fs: port inode_init_owner() to mnt_idmap
  fs: port acl to mnt_idmap
  fs: port xattr to mnt_idmap
  fs: port ->permission() to pass mnt_idmap
  fs: port ->fileattr_set() to pass mnt_idmap
  fs: port ->set_acl() to pass mnt_idmap
  fs: port ->get_acl() to pass mnt_idmap
  fs: port ->tmpfile() to pass mnt_idmap
  fs: port ->rename() to pass mnt_idmap
  fs: port ->mknod() to pass mnt_idmap
  fs: port ->mkdir() to pass mnt_idmap
  ...

1 files changed, 51 insertions, 53 deletions

diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index d2271431f344..fda167069617 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -112,7 +112,7 @@ void forget_all_cached_acls(struct inode *inode)
 }
 EXPORT_SYMBOL(forget_all_cached_acls);
 
-static struct posix_acl *__get_acl(struct user_namespace *mnt_userns,
+static struct posix_acl *__get_acl(struct mnt_idmap *idmap,
 				   struct dentry *dentry, struct inode *inode,
 				   int type)
 {
@@ -155,7 +155,7 @@ static struct posix_acl *__get_acl(struct user_namespace *mnt_userns,
 	 * we'll just create the negative cache entry.
 	 */
 	if (dentry && inode->i_op->get_acl) {
-		acl = inode->i_op->get_acl(mnt_userns, dentry, type);
+		acl = inode->i_op->get_acl(idmap, dentry, type);
 	} else if (inode->i_op->get_inode_acl) {
 		acl = inode->i_op->get_inode_acl(inode, type, false);
 	} else {
@@ -182,7 +182,7 @@ static struct posix_acl *__get_acl(struct user_namespace *mnt_userns,
 
 struct posix_acl *get_inode_acl(struct inode *inode, int type)
 {
-	return __get_acl(&init_user_ns, NULL, inode, type);
+	return __get_acl(&nop_mnt_idmap, NULL, inode, type);
 }
 EXPORT_SYMBOL(get_inode_acl);
 
@@ -373,7 +373,7 @@ EXPORT_SYMBOL(posix_acl_from_mode);
  * by the acl. Returns -E... otherwise.
  */
 int
-posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode,
+posix_acl_permission(struct mnt_idmap *idmap, struct inode *inode,
 		     const struct posix_acl *acl, int want)
 {
 	const struct posix_acl_entry *pa, *pe, *mask_obj;
@@ -388,18 +388,18 @@ posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode,
                 switch(pa->e_tag) {
                         case ACL_USER_OBJ:
 				/* (May have been checked already) */
-				vfsuid = i_uid_into_vfsuid(mnt_userns, inode);
+				vfsuid = i_uid_into_vfsuid(idmap, inode);
 				if (vfsuid_eq_kuid(vfsuid, current_fsuid()))
                                         goto check_perm;
                                 break;
                         case ACL_USER:
-				vfsuid = make_vfsuid(mnt_userns, fs_userns,
+				vfsuid = make_vfsuid(idmap, fs_userns,
 						     pa->e_uid);
 				if (vfsuid_eq_kuid(vfsuid, current_fsuid()))
                                         goto mask;
 				break;
                         case ACL_GROUP_OBJ:
-				vfsgid = i_gid_into_vfsgid(mnt_userns, inode);
+				vfsgid = i_gid_into_vfsgid(idmap, inode);
 				if (vfsgid_in_group_p(vfsgid)) {
 					found = 1;
 					if ((pa->e_perm & want) == want)
@@ -407,7 +407,7 @@ posix_acl_permission(struct user_namespace *mnt_userns, struct inode *inode,
                                 }
 				break;
                         case ACL_GROUP:
-				vfsgid = make_vfsgid(mnt_userns, fs_userns,
+				vfsgid = make_vfsgid(idmap, fs_userns,
 						     pa->e_gid);
 				if (vfsgid_in_group_p(vfsgid)) {
 					found = 1;
@@ -592,18 +592,18 @@ EXPORT_SYMBOL(__posix_acl_chmod);
 /**
  * posix_acl_chmod - chmod a posix acl
  *
- * @mnt_userns:	user namespace of the mount @inode was found from
+ * @idmap:	idmap of the mount @inode was found from
  * @dentry:	dentry to check permissions on
  * @mode:	the new mode of @inode
  *
- * If the dentry has been found through an idmapped mount the user namespace of
- * the vfsmount must be passed through @mnt_userns. This function will then
- * take care to map the inode according to @mnt_userns before checking
+ * If the dentry has been found through an idmapped mount the idmap of
+ * the vfsmount must be passed through @idmap. This function will then
+ * take care to map the inode according to @idmap before checking
  * permissions. On non-idmapped mounts or if permission checking is to be
- * performed on the raw inode simply passs init_user_ns.
+ * performed on the raw inode simply passs @nop_mnt_idmap.
  */
 int
- posix_acl_chmod(struct user_namespace *mnt_userns, struct dentry *dentry,
+ posix_acl_chmod(struct mnt_idmap *idmap, struct dentry *dentry,
 		    umode_t mode)
 {
 	struct inode *inode = d_inode(dentry);
@@ -625,7 +625,7 @@ int
 	ret = __posix_acl_chmod(&acl, GFP_KERNEL, mode);
 	if (ret)
 		return ret;
-	ret = inode->i_op->set_acl(mnt_userns, dentry, acl, ACL_TYPE_ACCESS);
+	ret = inode->i_op->set_acl(idmap, dentry, acl, ACL_TYPE_ACCESS);
 	posix_acl_release(acl);
 	return ret;
 }
@@ -684,7 +684,7 @@ EXPORT_SYMBOL_GPL(posix_acl_create);
 
 /**
  * posix_acl_update_mode  -  update mode in set_acl
- * @mnt_userns:	user namespace of the mount @inode was found from
+ * @idmap:	idmap of the mount @inode was found from
  * @inode:	target inode
  * @mode_p:	mode (pointer) for update
  * @acl:	acl pointer
@@ -696,15 +696,15 @@ EXPORT_SYMBOL_GPL(posix_acl_create);
  * As with chmod, clear the setgid bit if the caller is not in the owning group
  * or capable of CAP_FSETID (see inode_change_ok).
  *
- * If the inode has been found through an idmapped mount the user namespace of
- * the vfsmount must be passed through @mnt_userns. This function will then
- * take care to map the inode according to @mnt_userns before checking
+ * If the inode has been found through an idmapped mount the idmap of
+ * the vfsmount must be passed through @idmap. This function will then
+ * take care to map the inode according to @idmap before checking
  * permissions. On non-idmapped mounts or if permission checking is to be
- * performed on the raw inode simply passs init_user_ns.
+ * performed on the raw inode simply passs @nop_mnt_idmap.
  *
  * Called from set_acl inode operations.
  */
-int posix_acl_update_mode(struct user_namespace *mnt_userns,
+int posix_acl_update_mode(struct mnt_idmap *idmap,
 			  struct inode *inode, umode_t *mode_p,
 			  struct posix_acl **acl)
 {
@@ -716,8 +716,8 @@ int posix_acl_update_mode(struct user_namespace *mnt_userns,
 		return error;
 	if (error == 0)
 		*acl = NULL;
-	if (!vfsgid_in_group_p(i_gid_into_vfsgid(mnt_userns, inode)) &&
-	    !capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FSETID))
+	if (!vfsgid_in_group_p(i_gid_into_vfsgid(idmap, inode)) &&
+	    !capable_wrt_inode_uidgid(idmap, inode, CAP_FSETID))
 		mode &= ~S_ISGID;
 	*mode_p = mode;
 	return 0;
@@ -894,7 +894,6 @@ static ssize_t vfs_posix_acl_to_xattr(struct mnt_idmap *idmap,
 	struct posix_acl_xattr_header *ext_acl = buffer;
 	struct posix_acl_xattr_entry *ext_entry;
 	struct user_namespace *fs_userns, *caller_userns;
-	struct user_namespace *mnt_userns;
 	ssize_t real_size, n;
 	vfsuid_t vfsuid;
 	vfsgid_t vfsgid;
@@ -910,19 +909,18 @@ static ssize_t vfs_posix_acl_to_xattr(struct mnt_idmap *idmap,
 
 	fs_userns = i_user_ns(inode);
 	caller_userns = current_user_ns();
-	mnt_userns = mnt_idmap_owner(idmap);
 	for (n=0; n < acl->a_count; n++, ext_entry++) {
 		const struct posix_acl_entry *acl_e = &acl->a_entries[n];
 		ext_entry->e_tag  = cpu_to_le16(acl_e->e_tag);
 		ext_entry->e_perm = cpu_to_le16(acl_e->e_perm);
 		switch(acl_e->e_tag) {
 		case ACL_USER:
-			vfsuid = make_vfsuid(mnt_userns, fs_userns, acl_e->e_uid);
+			vfsuid = make_vfsuid(idmap, fs_userns, acl_e->e_uid);
 			ext_entry->e_id = cpu_to_le32(from_kuid(
 				caller_userns, vfsuid_into_kuid(vfsuid)));
 			break;
 		case ACL_GROUP:
-			vfsgid = make_vfsgid(mnt_userns, fs_userns, acl_e->e_gid);
+			vfsgid = make_vfsgid(idmap, fs_userns, acl_e->e_gid);
 			ext_entry->e_id = cpu_to_le32(from_kgid(
 				caller_userns, vfsgid_into_kgid(vfsgid)));
 			break;
@@ -935,7 +933,7 @@ static ssize_t vfs_posix_acl_to_xattr(struct mnt_idmap *idmap,
 }
 
 int
-set_posix_acl(struct user_namespace *mnt_userns, struct dentry *dentry,
+set_posix_acl(struct mnt_idmap *idmap, struct dentry *dentry,
 	      int type, struct posix_acl *acl)
 {
 	struct inode *inode = d_inode(dentry);
@@ -947,7 +945,7 @@ set_posix_acl(struct user_namespace *mnt_userns, struct dentry *dentry,
 
 	if (type == ACL_TYPE_DEFAULT && !S_ISDIR(inode->i_mode))
 		return acl ? -EACCES : 0;
-	if (!inode_owner_or_capable(mnt_userns, inode))
+	if (!inode_owner_or_capable(idmap, inode))
 		return -EPERM;
 
 	if (acl) {
@@ -955,7 +953,7 @@ set_posix_acl(struct user_namespace *mnt_userns, struct dentry *dentry,
 		if (ret)
 			return ret;
 	}
-	return inode->i_op->set_acl(mnt_userns, dentry, acl, type);
+	return inode->i_op->set_acl(idmap, dentry, acl, type);
 }
 EXPORT_SYMBOL(set_posix_acl);
 
@@ -979,14 +977,14 @@ const struct xattr_handler posix_acl_default_xattr_handler = {
 };
 EXPORT_SYMBOL_GPL(posix_acl_default_xattr_handler);
 
-int simple_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry,
+int simple_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
 		   struct posix_acl *acl, int type)
 {
 	int error;
 	struct inode *inode = d_inode(dentry);
 
 	if (type == ACL_TYPE_ACCESS) {
-		error = posix_acl_update_mode(mnt_userns, inode,
+		error = posix_acl_update_mode(idmap, inode,
 				&inode->i_mode, &acl);
 		if (error)
 			return error;
@@ -1018,7 +1016,7 @@ int simple_acl_create(struct inode *dir, struct inode *inode)
 	return 0;
 }
 
-static int vfs_set_acl_idmapped_mnt(struct user_namespace *mnt_userns,
+static int vfs_set_acl_idmapped_mnt(struct mnt_idmap *idmap,
 				    struct user_namespace *fs_userns,
 				    struct posix_acl *acl)
 {
@@ -1027,11 +1025,11 @@ static int vfs_set_acl_idmapped_mnt(struct user_namespace *mnt_userns,
 
 		switch (acl_e->e_tag) {
 		case ACL_USER:
-			acl_e->e_uid = from_vfsuid(mnt_userns, fs_userns,
+			acl_e->e_uid = from_vfsuid(idmap, fs_userns,
 						   VFSUIDT_INIT(acl_e->e_uid));
 			break;
 		case ACL_GROUP:
-			acl_e->e_gid = from_vfsgid(mnt_userns, fs_userns,
+			acl_e->e_gid = from_vfsgid(idmap, fs_userns,
 						   VFSGIDT_INIT(acl_e->e_gid));
 			break;
 		}
@@ -1042,7 +1040,7 @@ static int vfs_set_acl_idmapped_mnt(struct user_namespace *mnt_userns,
 
 /**
  * vfs_set_acl - set posix acls
- * @mnt_userns: user namespace of the mount
+ * @idmap: idmap of the mount
  * @dentry: the dentry based on which to set the posix acls
  * @acl_name: the name of the posix acl
  * @kacl: the posix acls in the appropriate VFS format
@@ -1052,7 +1050,7 @@ static int vfs_set_acl_idmapped_mnt(struct user_namespace *mnt_userns,
  *
  * Return: On success 0, on error negative errno.
  */
-int vfs_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry,
+int vfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
 		const char *acl_name, struct posix_acl *kacl)
 {
 	int acl_type;
@@ -1072,7 +1070,7 @@ int vfs_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry,
 		 * if this is a filesystem with a backing store - ultimately
 		 * translate them to backing store values.
 		 */
-		error = vfs_set_acl_idmapped_mnt(mnt_userns, i_user_ns(inode), kacl);
+		error = vfs_set_acl_idmapped_mnt(idmap, i_user_ns(inode), kacl);
 		if (error)
 			return error;
 	}
@@ -1084,11 +1082,11 @@ retry_deleg:
 	 * We only care about restrictions the inode struct itself places upon
 	 * us otherwise POSIX ACLs aren't subject to any VFS restrictions.
 	 */
-	error = may_write_xattr(mnt_userns, inode);
+	error = may_write_xattr(idmap, inode);
 	if (error)
 		goto out_inode_unlock;
 
-	error = security_inode_set_acl(mnt_userns, dentry, acl_name, kacl);
+	error = security_inode_set_acl(idmap, dentry, acl_name, kacl);
 	if (error)
 		goto out_inode_unlock;
 
@@ -1097,7 +1095,7 @@ retry_deleg:
 		goto out_inode_unlock;
 
 	if (inode->i_opflags & IOP_XATTR)
-		error = set_posix_acl(mnt_userns, dentry, acl_type, kacl);
+		error = set_posix_acl(idmap, dentry, acl_type, kacl);
 	else if (unlikely(is_bad_inode(inode)))
 		error = -EIO;
 	else
@@ -1122,7 +1120,7 @@ EXPORT_SYMBOL_GPL(vfs_set_acl);
 
 /**
  * vfs_get_acl - get posix acls
- * @mnt_userns: user namespace of the mount
+ * @idmap: idmap of the mount
  * @dentry: the dentry based on which to retrieve the posix acls
  * @acl_name: the name of the posix acl
  *
@@ -1131,7 +1129,7 @@ EXPORT_SYMBOL_GPL(vfs_set_acl);
  *
  * Return: On success POSIX ACLs in VFS format, on error negative errno.
  */
-struct posix_acl *vfs_get_acl(struct user_namespace *mnt_userns,
+struct posix_acl *vfs_get_acl(struct mnt_idmap *idmap,
 			      struct dentry *dentry, const char *acl_name)
 {
 	struct inode *inode = d_inode(dentry);
@@ -1146,7 +1144,7 @@ struct posix_acl *vfs_get_acl(struct user_namespace *mnt_userns,
 	 * The VFS has no restrictions on reading POSIX ACLs so calling
 	 * something like xattr_permission() isn't needed. Only LSMs get a say.
 	 */
-	error = security_inode_get_acl(mnt_userns, dentry, acl_name);
+	error = security_inode_get_acl(idmap, dentry, acl_name);
 	if (error)
 		return ERR_PTR(error);
 
@@ -1155,7 +1153,7 @@ struct posix_acl *vfs_get_acl(struct user_namespace *mnt_userns,
 	if (S_ISLNK(inode->i_mode))
 		return ERR_PTR(-EOPNOTSUPP);
 
-	acl = __get_acl(mnt_userns, dentry, inode, acl_type);
+	acl = __get_acl(idmap, dentry, inode, acl_type);
 	if (IS_ERR(acl))
 		return acl;
 	if (!acl)
@@ -1167,7 +1165,7 @@ EXPORT_SYMBOL_GPL(vfs_get_acl);
 
 /**
  * vfs_remove_acl - remove posix acls
- * @mnt_userns: user namespace of the mount
+ * @idmap: idmap of the mount
  * @dentry: the dentry based on which to retrieve the posix acls
  * @acl_name: the name of the posix acl
  *
@@ -1175,7 +1173,7 @@ EXPORT_SYMBOL_GPL(vfs_get_acl);
  *
  * Return: On success 0, on error negative errno.
  */
-int vfs_remove_acl(struct user_namespace *mnt_userns, struct dentry *dentry,
+int vfs_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry,
 		   const char *acl_name)
 {
 	int acl_type;
@@ -1194,11 +1192,11 @@ retry_deleg:
 	 * We only care about restrictions the inode struct itself places upon
 	 * us otherwise POSIX ACLs aren't subject to any VFS restrictions.
 	 */
-	error = may_write_xattr(mnt_userns, inode);
+	error = may_write_xattr(idmap, inode);
 	if (error)
 		goto out_inode_unlock;
 
-	error = security_inode_remove_acl(mnt_userns, dentry, acl_name);
+	error = security_inode_remove_acl(idmap, dentry, acl_name);
 	if (error)
 		goto out_inode_unlock;
 
@@ -1207,14 +1205,14 @@ retry_deleg:
 		goto out_inode_unlock;
 
 	if (inode->i_opflags & IOP_XATTR)
-		error = set_posix_acl(mnt_userns, dentry, acl_type, NULL);
+		error = set_posix_acl(idmap, dentry, acl_type, NULL);
 	else if (unlikely(is_bad_inode(inode)))
 		error = -EIO;
 	else
 		error = -EOPNOTSUPP;
 	if (!error) {
 		fsnotify_xattr(dentry);
-		evm_inode_post_remove_acl(mnt_userns, dentry, acl_name);
+		evm_inode_post_remove_acl(idmap, dentry, acl_name);
 	}
 
 out_inode_unlock:
@@ -1246,7 +1244,7 @@ int do_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
 			return PTR_ERR(acl);
 	}
 
-	error = vfs_set_acl(mnt_idmap_owner(idmap), dentry, acl_name, acl);
+	error = vfs_set_acl(idmap, dentry, acl_name, acl);
 	posix_acl_release(acl);
 	return error;
 }
@@ -1257,7 +1255,7 @@ ssize_t do_get_acl(struct mnt_idmap *idmap, struct dentry *dentry,
 	ssize_t error;
 	struct posix_acl *acl;
 
-	acl = vfs_get_acl(mnt_idmap_owner(idmap), dentry, acl_name);
+	acl = vfs_get_acl(idmap, dentry, acl_name);
 	if (IS_ERR(acl))
 		return PTR_ERR(acl);