Patch "fs: Better permission checking for submounts" has been added to the 4.9-stable tree

@@ -202,7 +202,7 @@ static struct vfsmount *afs_mntpt_do_aut
 
 	/* try and do the mount */
 	_debug("--- attempting mount %s -o %s ---", devname, options);
-	mnt = vfs_kern_mount(&afs_fs_type, 0, devname, options);
+	mnt = vfs_submount(mntpt, &afs_fs_type, devname, options);
 	_debug("--- mount result %p ---", mnt);
 
 	free_page((unsigned long) devname);

@@ -431,8 +431,8 @@ int autofs4_wait(struct autofs_sb_info *
 		memcpy(&wq->name, &qstr, sizeof(struct qstr));
 		wq->dev = autofs4_get_dev(sbi);
 		wq->ino = autofs4_get_ino(sbi);
-		wq->uid = current_real_cred()->uid;
-		wq->gid = current_real_cred()->gid;
+		wq->uid = current_cred()->uid;
+		wq->gid = current_cred()->gid;
 		wq->pid = pid;
 		wq->tgid = tgid;
 		wq->status = -EINTR; /* Status return if interrupted */

@@ -245,7 +245,8 @@ compose_mount_options_err:
  * @fullpath:		full path in UNC format
  * @ref:		server's referral
  */
-static struct vfsmount *cifs_dfs_do_refmount(struct cifs_sb_info *cifs_sb,
+static struct vfsmount *cifs_dfs_do_refmount(struct dentry *mntpt,
+		struct cifs_sb_info *cifs_sb,
 		const char *fullpath, const struct dfs_info3_param *ref)
 {
 	struct vfsmount *mnt;

@@ -259,7 +260,7 @@ static struct vfsmount *cifs_dfs_do_refm
 	if (IS_ERR(mountdata))
 		return (struct vfsmount *)mountdata;
 
-	mnt = vfs_kern_mount(&cifs_fs_type, 0, devname, mountdata);
+	mnt = vfs_submount(mntpt, &cifs_fs_type, devname, mountdata);
 	kfree(mountdata);
 	kfree(devname);
 	return mnt;

@@ -334,7 +335,7 @@ static struct vfsmount *cifs_dfs_do_auto
 			mnt = ERR_PTR(-EINVAL);
 			break;
 		}
-		mnt = cifs_dfs_do_refmount(cifs_sb,
+		mnt = cifs_dfs_do_refmount(mntpt, cifs_sb,
 				full_path, referrals + i);
 		cifs_dbg(FYI, "%s: cifs_dfs_do_refmount:%s , mnt:%p\n",
 			 __func__, referrals[i].node_name, mnt);

@@ -187,9 +187,9 @@ static const struct super_operations deb
 
 static struct vfsmount *debugfs_automount(struct path *path)
 {
-	struct vfsmount *(*f)(void *);
-	f = (struct vfsmount *(*)(void *))path->dentry->d_fsdata;
-	return f(d_inode(path->dentry)->i_private);
+	debugfs_automount_t f;
+	f = (debugfs_automount_t)path->dentry->d_fsdata;
+	return f(path->dentry, d_inode(path->dentry)->i_private);
 }
 
 static const struct dentry_operations debugfs_dops = {

@@ -504,7 +504,7 @@ EXPORT_SYMBOL_GPL(debugfs_create_dir);
  */
 struct dentry *debugfs_create_automount(const char *name,
 					struct dentry *parent,
-					struct vfsmount *(*f)(void *),
+					debugfs_automount_t f,
 					void *data)
 {
 	struct dentry *dentry = start_creating(name, parent);

@@ -1100,7 +1100,6 @@ static int follow_automount(struct path
 			    bool *need_mntput)
 {
 	struct vfsmount *mnt;
-	const struct cred *old_cred;
 	int err;
 
 	if (!path->dentry->d_op || !path->dentry->d_op->d_automount)

@@ -1129,9 +1128,7 @@ static int follow_automount(struct path
 	if (nd->total_link_count >= 40)
 		return -ELOOP;
 
-	old_cred = override_creds(&init_cred);
 	mnt = path->dentry->d_op->d_automount(path);
-	revert_creds(old_cred);
 	if (IS_ERR(mnt)) {
 		/*
 		 * The filesystem is allowed to return -EISDIR here to indicate

@@ -995,6 +995,21 @@ vfs_kern_mount(struct file_system_type *
 }
 EXPORT_SYMBOL_GPL(vfs_kern_mount);
 
+struct vfsmount *
+vfs_submount(const struct dentry *mountpoint, struct file_system_type *type,
+	     const char *name, void *data)
+{
+	/* Until it is worked out how to pass the user namespace
+	 * through from the parent mount to the submount don't support
+	 * unprivileged mounts with submounts.
+	 */
+	if (mountpoint->d_sb->s_user_ns != &init_user_ns)
+		return ERR_PTR(-EPERM);
+
+	return vfs_kern_mount(type, MS_SUBMOUNT, name, data);
+}
+EXPORT_SYMBOL_GPL(vfs_submount);
+
 static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 					int flag)
 {

@@ -2779,7 +2794,7 @@ long do_mount(const char *dev_name, cons
 
 	flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE | MS_BORN |
 		   MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT |
-		   MS_STRICTATIME | MS_NOREMOTELOCK);
+		   MS_STRICTATIME | MS_NOREMOTELOCK | MS_SUBMOUNT);
 
 	if (flags & MS_REMOUNT)
 		retval = do_remount(&path, flags & ~MS_REMOUNT, mnt_flags,

@@ -226,7 +226,7 @@ static struct vfsmount *nfs_do_clone_mou
 					   const char *devname,
 					   struct nfs_clone_mount *mountdata)
 {
-	return vfs_kern_mount(&nfs_xdev_fs_type, 0, devname, mountdata);
+	return vfs_submount(mountdata->dentry, &nfs_xdev_fs_type, devname, mountdata);
 }
 
 /**

@@ -279,7 +279,7 @@ static struct vfsmount *try_location(str
 				mountdata->hostname,
 				mountdata->mnt_path);
 
-		mnt = vfs_kern_mount(&nfs4_referral_fs_type, 0, page, mountdata);
+		mnt = vfs_submount(mountdata->dentry, &nfs4_referral_fs_type, page, mountdata);
 		if (!IS_ERR(mnt))
 			break;
 	}

@@ -470,7 +470,7 @@ struct super_block *sget_userns(struct f
 	struct super_block *old;
 	int err;
 
-	if (!(flags & MS_KERNMOUNT) &&
+	if (!(flags & (MS_KERNMOUNT|MS_SUBMOUNT)) &&
 	    !(type->fs_flags & FS_USERNS_MOUNT) &&
 	    !capable(CAP_SYS_ADMIN))
 		return ERR_PTR(-EPERM);

@@ -500,7 +500,7 @@ retry:
 	}
 	if (!s) {
 		spin_unlock(&sb_lock);
-		s = alloc_super(type, flags, user_ns);
+		s = alloc_super(type, (flags & ~MS_SUBMOUNT), user_ns);
 		if (!s)
 			return ERR_PTR(-ENOMEM);
 		goto retry;

@@ -541,8 +541,15 @@ struct super_block *sget(struct file_sys
 {
 	struct user_namespace *user_ns = current_user_ns();
 
+	/* We don't yet pass the user namespace of the parent
+	 * mount through to here so always use &init_user_ns
+	 * until that changes.
+	 */
+	if (flags & MS_SUBMOUNT)
+		user_ns = &init_user_ns;
+
 	/* Ensure the requestor has permissions over the target filesystem */
-	if (!(flags & MS_KERNMOUNT) && !ns_capable(user_ns, CAP_SYS_ADMIN))
+	if (!(flags & (MS_KERNMOUNT|MS_SUBMOUNT)) && !ns_capable(user_ns, CAP_SYS_ADMIN))
 		return ERR_PTR(-EPERM);
 
 	return sget_userns(type, test, set, flags, user_ns, data);

@@ -96,9 +96,10 @@ struct dentry *debugfs_create_dir(const
 struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent,
 				      const char *dest);
 
+typedef struct vfsmount *(*debugfs_automount_t)(struct dentry *, void *);
 struct dentry *debugfs_create_automount(const char *name,
 					struct dentry *parent,
-					struct vfsmount *(*f)(void *),
+					debugfs_automount_t f,
 					void *data);
 
 void debugfs_remove(struct dentry *dentry);

@@ -90,6 +90,9 @@ struct file_system_type;
 extern struct vfsmount *vfs_kern_mount(struct file_system_type *type,
 				      int flags, const char *name,
 				      void *data);
+extern struct vfsmount *vfs_submount(const struct dentry *mountpoint,
+				     struct file_system_type *type,
+				     const char *name, void *data);
 
 extern void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list);
 extern void mark_mounts_for_expiry(struct list_head *mounts);

@@ -132,6 +132,7 @@ struct inodes_stat_t {
 #define MS_LAZYTIME	(1<<25) /* Update the on-disk [acm]times lazily */
 
 /* These sb flags are internal to the kernel */
+#define MS_SUBMOUNT     (1<<26)
 #define MS_NOREMOTELOCK	(1<<27)
 #define MS_NOSEC	(1<<28)
 #define MS_BORN		(1<<29)

@@ -7241,7 +7241,7 @@ init_tracer_tracefs(struct trace_array *
 	ftrace_init_tracefs(tr, d_tracer);
 }
 
-static struct vfsmount *trace_automount(void *ingore)
+static struct vfsmount *trace_automount(struct dentry *mntpt, void *ingore)
 {
 	struct vfsmount *mnt;
 	struct file_system_type *type;

@@ -7254,7 +7254,7 @@ static struct vfsmount *trace_automount(
 	type = get_fs_type("tracefs");
 	if (!type)
 		return NULL;
-	mnt = vfs_kern_mount(type, 0, "tracefs", NULL);
+	mnt = vfs_submount(mntpt, type, "tracefs", NULL);
 	put_filesystem(type);
 	if (IS_ERR(mnt))
 		return NULL;