1 files changed, 121 insertions, 29 deletions

diff --git a/fs/proc/root.c b/fs/proc/root.c
index 06a297a27ba3..99adddfeb4a4 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -38,12 +38,14 @@ enum proc_param {
 	Opt_gid,
 	Opt_hidepid,
 	Opt_subset,
+	Opt_pidns,
 };
 
 static const struct fs_parameter_spec proc_fs_parameters[] = {
-	fsparam_u32("gid",	Opt_gid),
+	fsparam_u32("gid",		Opt_gid),
 	fsparam_string("hidepid",	Opt_hidepid),
 	fsparam_string("subset",	Opt_subset),
+	fsparam_file_or_string("pidns",	Opt_pidns),
 	{}
 };
 
@@ -109,11 +111,66 @@ static int proc_parse_subset_param(struct fs_context *fc, char *value)
 	return 0;
 }
 
+#ifdef CONFIG_PID_NS
+static int proc_parse_pidns_param(struct fs_context *fc,
+				  struct fs_parameter *param,
+				  struct fs_parse_result *result)
+{
+	struct proc_fs_context *ctx = fc->fs_private;
+	struct pid_namespace *target, *active = task_active_pid_ns(current);
+	struct ns_common *ns;
+	struct file *ns_filp __free(fput) = NULL;
+
+	switch (param->type) {
+	case fs_value_is_file:
+		/* came through fsconfig, steal the file reference */
+		ns_filp = no_free_ptr(param->file);
+		break;
+	case fs_value_is_string:
+		ns_filp = filp_open(param->string, O_RDONLY, 0);
+		break;
+	default:
+		WARN_ON_ONCE(true);
+		break;
+	}
+	if (!ns_filp)
+		ns_filp = ERR_PTR(-EBADF);
+	if (IS_ERR(ns_filp)) {
+		errorfc(fc, "could not get file from pidns argument");
+		return PTR_ERR(ns_filp);
+	}
+
+	if (!proc_ns_file(ns_filp))
+		return invalfc(fc, "pidns argument is not an nsfs file");
+	ns = get_proc_ns(file_inode(ns_filp));
+	if (ns->ns_type != CLONE_NEWPID)
+		return invalfc(fc, "pidns argument is not a pidns file");
+	target = container_of(ns, struct pid_namespace, ns);
+
+	/*
+	 * pidns= is shorthand for joining the pidns to get a fsopen fd, so the
+	 * permission model should be the same as pidns_install().
+	 */
+	if (!ns_capable(target->user_ns, CAP_SYS_ADMIN)) {
+		errorfc(fc, "insufficient permissions to set pidns");
+		return -EPERM;
+	}
+	if (!pidns_is_ancestor(target, active))
+		return invalfc(fc, "cannot set pidns to non-descendant pidns");
+
+	put_pid_ns(ctx->pid_ns);
+	ctx->pid_ns = get_pid_ns(target);
+	put_user_ns(fc->user_ns);
+	fc->user_ns = get_user_ns(ctx->pid_ns->user_ns);
+	return 0;
+}
+#endif /* CONFIG_PID_NS */
+
 static int proc_parse_param(struct fs_context *fc, struct fs_parameter *param)
 {
 	struct proc_fs_context *ctx = fc->fs_private;
 	struct fs_parse_result result;
-	int opt;
+	int opt, err;
 
 	opt = fs_parse(fc, proc_fs_parameters, param, &result);
 	if (opt < 0)
@@ -125,15 +182,39 @@ static int proc_parse_param(struct fs_context *fc, struct fs_parameter *param)
 		break;
 
 	case Opt_hidepid:
-		if (proc_parse_hidepid_param(fc, param))
-			return -EINVAL;
+		err = proc_parse_hidepid_param(fc, param);
+		if (err)
+			return err;
 		break;
 
 	case Opt_subset:
-		if (proc_parse_subset_param(fc, param->string) < 0)
-			return -EINVAL;
+		err = proc_parse_subset_param(fc, param->string);
+		if (err)
+			return err;
 		break;
 
+	case Opt_pidns:
+#ifdef CONFIG_PID_NS
+		/*
+		 * We would have to RCU-protect every proc_pid_ns() or
+		 * proc_sb_info() access if we allowed this to be reconfigured
+		 * for an existing procfs instance. Luckily, procfs instances
+		 * are cheap to create, and mount-beneath would let you
+		 * atomically replace an instance even with overmounts.
+		 */
+		if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) {
+			errorfc(fc, "cannot reconfigure pidns for existing procfs");
+			return -EBUSY;
+		}
+		err = proc_parse_pidns_param(fc, param, &result);
+		if (err)
+			return err;
+		break;
+#else
+		errorfc(fc, "pidns mount flag not supported on this system");
+		return -EOPNOTSUPP;
+#endif
+
 	default:
 		return -EINVAL;
 	}
@@ -142,18 +223,29 @@ static int proc_parse_param(struct fs_context *fc, struct fs_parameter *param)
 	return 0;
 }
 
-static void proc_apply_options(struct proc_fs_info *fs_info,
+static int proc_apply_options(struct proc_fs_info *fs_info,
 			       struct fs_context *fc,
 			       struct user_namespace *user_ns)
 {
 	struct proc_fs_context *ctx = fc->fs_private;
 
+	if ((ctx->mask & (1 << Opt_subset)) &&
+	    fc->purpose == FS_CONTEXT_FOR_RECONFIGURE &&
+	    ctx->pidonly != fs_info->pidonly)
+		return invalf(fc, "proc: subset=pid cannot be changed\n");
+
 	if (ctx->mask & (1 << Opt_gid))
 		fs_info->pid_gid = make_kgid(user_ns, ctx->gid);
 	if (ctx->mask & (1 << Opt_hidepid))
 		fs_info->hide_pid = ctx->hidepid;
 	if (ctx->mask & (1 << Opt_subset))
 		fs_info->pidonly = ctx->pidonly;
+	if (ctx->mask & (1 << Opt_pidns) &&
+	    !WARN_ON_ONCE(fc->purpose == FS_CONTEXT_FOR_RECONFIGURE)) {
+		put_pid_ns(fs_info->pid_ns);
+		fs_info->pid_ns = get_pid_ns(ctx->pid_ns);
+	}
+	return 0;
 }
 
 static int proc_fill_super(struct super_block *s, struct fs_context *fc)
@@ -163,15 +255,18 @@ static int proc_fill_super(struct super_block *s, struct fs_context *fc)
 	struct proc_fs_info *fs_info;
 	int ret;
 
-	fs_info = kzalloc(sizeof(*fs_info), GFP_KERNEL);
+	fs_info = kzalloc_obj(*fs_info);
 	if (!fs_info)
 		return -ENOMEM;
 
 	fs_info->pid_ns = get_pid_ns(ctx->pid_ns);
-	proc_apply_options(fs_info, fc, current_user_ns());
+	fs_info->mounter_cred = get_cred(fc->cred);
+	ret = proc_apply_options(fs_info, fc, current_user_ns());
+	if (ret)
+		return ret;
 
 	/* User space would break if executables or devices appear on proc */
-	s->s_iflags |= SB_I_USERNS_VISIBLE | SB_I_NOEXEC | SB_I_NODEV;
+	s->s_iflags |= SB_I_NOEXEC | SB_I_NODEV;
 	s->s_flags |= SB_NODIRATIME | SB_NOSUID | SB_NOEXEC;
 	s->s_blocksize = 1024;
 	s->s_blocksize_bits = 10;
@@ -180,6 +275,9 @@ static int proc_fill_super(struct super_block *s, struct fs_context *fc)
 	s->s_time_gran = 1;
 	s->s_fs_info = fs_info;
 
+	if (fs_info->pidonly == PROC_PIDONLY_ON)
+		s->s_iflags |= SB_I_RESTRICTED_VARIANT;
+
 	/*
 	 * procfs isn't actually a stacking filesystem; however, there is
 	 * too much magic going on inside it to permit stacking things on
@@ -217,8 +315,7 @@ static int proc_reconfigure(struct fs_context *fc)
 
 	sync_filesystem(sb);
 
-	proc_apply_options(fs_info, fc, current_user_ns());
-	return 0;
+	return proc_apply_options(fs_info, fc, current_user_ns());
 }
 
 static int proc_get_tree(struct fs_context *fc)
@@ -245,7 +342,7 @@ static int proc_init_fs_context(struct fs_context *fc)
 {
 	struct proc_fs_context *ctx;
 
-	ctx = kzalloc(sizeof(struct proc_fs_context), GFP_KERNEL);
+	ctx = kzalloc_obj(struct proc_fs_context);
 	if (!ctx)
 		return -ENOMEM;
 
@@ -261,17 +358,12 @@ static void proc_kill_sb(struct super_block *sb)
 {
 	struct proc_fs_info *fs_info = proc_sb_info(sb);
 
-	if (!fs_info) {
-		kill_anon_super(sb);
-		return;
-	}
-
-	dput(fs_info->proc_self);
-	dput(fs_info->proc_thread_self);
-
 	kill_anon_super(sb);
-	put_pid_ns(fs_info->pid_ns);
-	kfree_rcu(fs_info, rcu);
+	if (fs_info) {
+		put_pid_ns(fs_info->pid_ns);
+		put_cred(fs_info->mounter_cred);
+		kfree_rcu(fs_info, rcu);
+	}
 }
 
 static struct file_system_type proc_fs_type = {
@@ -279,7 +371,7 @@ static struct file_system_type proc_fs_type = {
 	.init_fs_context	= proc_init_fs_context,
 	.parameters		= proc_fs_parameters,
 	.kill_sb		= proc_kill_sb,
-	.fs_flags		= FS_USERNS_MOUNT | FS_DISALLOW_NOTIFY_PERM,
+	.fs_flags		= FS_USERNS_MOUNT | FS_USERNS_MOUNT_RESTRICTED | FS_DISALLOW_NOTIFY_PERM,
 };
 
 void __init proc_root_init(void)
@@ -363,12 +455,12 @@ static const struct inode_operations proc_root_inode_operations = {
  * This is the root "inode" in the /proc tree..
  */
 struct proc_dir_entry proc_root = {
-	.low_ino	= PROC_ROOT_INO, 
-	.namelen	= 5, 
-	.mode		= S_IFDIR | S_IRUGO | S_IXUGO, 
-	.nlink		= 2, 
+	.low_ino	= PROCFS_ROOT_INO,
+	.namelen	= 5,
+	.mode		= S_IFDIR | S_IRUGO | S_IXUGO,
+	.nlink		= 2,
 	.refcnt		= REFCOUNT_INIT(1),
-	.proc_iops	= &proc_root_inode_operations, 
+	.proc_iops	= &proc_root_inode_operations,
 	.proc_dir_ops	= &proc_root_operations,
 	.parent		= &proc_root,
 	.subdir		= RB_ROOT,