Merge branch 'proc-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace

Pull proc updates from Eric Biederman:
 "This has four sets of changes:

   - modernize proc to support multiple private instances

   - ensure we see the exit of each process tid exactly

   - remove has_group_leader_pid

   - use pids not tasks in posix-cpu-timers lookup

  Alexey updated proc so each mount of proc uses a new superblock. This
  allows people to actually use mount options with proc with no fear of
  messing up another mount of proc. Given the kernel's internal mounts
  of proc for things like uml this was a real problem, and resulted in
  Android's hidepid mount options being ignored and introducing security
  issues.

  The rest of the changes are small cleanups and fixes that came out of
  my work to allow this change to proc. In essence it is swapping the
  pids in de_thread during exec which removes a special case the code
  had to handle. Then updating the code to stop handling that special
  case"

* 'proc-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
  proc: proc_pid_ns takes super_block as an argument
  remove the no longer needed pid_alive() check in __task_pid_nr_ns()
  posix-cpu-timers: Replace __get_task_for_clock with pid_for_clock
  posix-cpu-timers: Replace cpu_timer_pid_type with clock_pid_type
  posix-cpu-timers: Extend rcu_read_lock removing task_struct references
  signal: Remove has_group_leader_pid
  exec: Remove BUG_ON(has_group_leader_pid)
  posix-cpu-timer:  Unify the now redundant code in lookup_task
  posix-cpu-timer: Tidy up group_leader logic in lookup_task
  proc: Ensure we see the exit of each process tid exactly once
  rculist: Add hlists_swap_heads_rcu
  proc: Use PIDTYPE_TGID in next_tgid
  Use proc_pid_ns() to get pid_namespace from the proc superblock
  proc: use named enums for better readability
  proc: use human-readable values for hidepid
  docs: proc: add documentation for "hidepid=4" and "subset=pid" options and new mount behavior
  proc: add option to mount only a pids subset
  proc: instantiate only pids that we can ptrace on 'hidepid=4' mount option
  proc: allow to mount many instances of proc in one pid namespace
  proc: rename struct proc_fs_info to proc_fs_opts

1 files changed, 100 insertions, 31 deletions

diff --git a/fs/proc/root.c b/fs/proc/root.c
index cdbe9293ea55..ffebed1999e5 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -32,21 +32,86 @@
 struct proc_fs_context {
 	struct pid_namespace	*pid_ns;
 	unsigned int		mask;
-	int			hidepid;
+	enum proc_hidepid	hidepid;
 	int			gid;
+	enum proc_pidonly	pidonly;
 };
 
 enum proc_param {
 	Opt_gid,
 	Opt_hidepid,
+	Opt_subset,
 };
 
 static const struct fs_parameter_spec proc_fs_parameters[] = {
 	fsparam_u32("gid",	Opt_gid),
-	fsparam_u32("hidepid",	Opt_hidepid),
+	fsparam_string("hidepid",	Opt_hidepid),
+	fsparam_string("subset",	Opt_subset),
 	{}
 };
 
+static inline int valid_hidepid(unsigned int value)
+{
+	return (value == HIDEPID_OFF ||
+		value == HIDEPID_NO_ACCESS ||
+		value == HIDEPID_INVISIBLE ||
+		value == HIDEPID_NOT_PTRACEABLE);
+}
+
+static int proc_parse_hidepid_param(struct fs_context *fc, struct fs_parameter *param)
+{
+	struct proc_fs_context *ctx = fc->fs_private;
+	struct fs_parameter_spec hidepid_u32_spec = fsparam_u32("hidepid", Opt_hidepid);
+	struct fs_parse_result result;
+	int base = (unsigned long)hidepid_u32_spec.data;
+
+	if (param->type != fs_value_is_string)
+		return invalf(fc, "proc: unexpected type of hidepid value\n");
+
+	if (!kstrtouint(param->string, base, &result.uint_32)) {
+		if (!valid_hidepid(result.uint_32))
+			return invalf(fc, "proc: unknown value of hidepid - %s\n", param->string);
+		ctx->hidepid = result.uint_32;
+		return 0;
+	}
+
+	if (!strcmp(param->string, "off"))
+		ctx->hidepid = HIDEPID_OFF;
+	else if (!strcmp(param->string, "noaccess"))
+		ctx->hidepid = HIDEPID_NO_ACCESS;
+	else if (!strcmp(param->string, "invisible"))
+		ctx->hidepid = HIDEPID_INVISIBLE;
+	else if (!strcmp(param->string, "ptraceable"))
+		ctx->hidepid = HIDEPID_NOT_PTRACEABLE;
+	else
+		return invalf(fc, "proc: unknown value of hidepid - %s\n", param->string);
+
+	return 0;
+}
+
+static int proc_parse_subset_param(struct fs_context *fc, char *value)
+{
+	struct proc_fs_context *ctx = fc->fs_private;
+
+	while (value) {
+		char *ptr = strchr(value, ',');
+
+		if (ptr != NULL)
+			*ptr++ = '\0';
+
+		if (*value != '\0') {
+			if (!strcmp(value, "pid")) {
+				ctx->pidonly = PROC_PIDONLY_ON;
+			} else {
+				return invalf(fc, "proc: unsupported subset option - %s\n", value);
+			}
+		}
+		value = ptr;
+	}
+
+	return 0;
+}
+
 static int proc_parse_param(struct fs_context *fc, struct fs_parameter *param)
 {
 	struct proc_fs_context *ctx = fc->fs_private;
@@ -63,10 +128,13 @@ static int proc_parse_param(struct fs_context *fc, struct fs_parameter *param)
 		break;
 
 	case Opt_hidepid:
-		ctx->hidepid = result.uint_32;
-		if (ctx->hidepid < HIDEPID_OFF ||
-		    ctx->hidepid > HIDEPID_INVISIBLE)
-			return invalfc(fc, "hidepid value must be between 0 and 2.\n");
+		if (proc_parse_hidepid_param(fc, param))
+			return -EINVAL;
+		break;
+
+	case Opt_subset:
+		if (proc_parse_subset_param(fc, param->string) < 0)
+			return -EINVAL;
 		break;
 
 	default:
@@ -77,26 +145,33 @@ static int proc_parse_param(struct fs_context *fc, struct fs_parameter *param)
 	return 0;
 }
 
-static void proc_apply_options(struct super_block *s,
+static void proc_apply_options(struct proc_fs_info *fs_info,
 			       struct fs_context *fc,
-			       struct pid_namespace *pid_ns,
 			       struct user_namespace *user_ns)
 {
 	struct proc_fs_context *ctx = fc->fs_private;
 
 	if (ctx->mask & (1 << Opt_gid))
-		pid_ns->pid_gid = make_kgid(user_ns, ctx->gid);
+		fs_info->pid_gid = make_kgid(user_ns, ctx->gid);
 	if (ctx->mask & (1 << Opt_hidepid))
-		pid_ns->hide_pid = ctx->hidepid;
+		fs_info->hide_pid = ctx->hidepid;
+	if (ctx->mask & (1 << Opt_subset))
+		fs_info->pidonly = ctx->pidonly;
 }
 
 static int proc_fill_super(struct super_block *s, struct fs_context *fc)
 {
-	struct pid_namespace *pid_ns = get_pid_ns(s->s_fs_info);
+	struct proc_fs_context *ctx = fc->fs_private;
 	struct inode *root_inode;
+	struct proc_fs_info *fs_info;
 	int ret;
 
-	proc_apply_options(s, fc, pid_ns, current_user_ns());
+	fs_info = kzalloc(sizeof(*fs_info), GFP_KERNEL);
+	if (!fs_info)
+		return -ENOMEM;
+
+	fs_info->pid_ns = get_pid_ns(ctx->pid_ns);
+	proc_apply_options(fs_info, fc, current_user_ns());
 
 	/* User space would break if executables or devices appear on proc */
 	s->s_iflags |= SB_I_USERNS_VISIBLE | SB_I_NOEXEC | SB_I_NODEV;
@@ -106,6 +181,7 @@ static int proc_fill_super(struct super_block *s, struct fs_context *fc)
 	s->s_magic = PROC_SUPER_MAGIC;
 	s->s_op = &proc_sops;
 	s->s_time_gran = 1;
+	s->s_fs_info = fs_info;
 
 	/*
 	 * procfs isn't actually a stacking filesystem; however, there is
@@ -113,7 +189,7 @@ static int proc_fill_super(struct super_block *s, struct fs_context *fc)
 	 * top of it
 	 */
 	s->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH;
-	
+
 	/* procfs dentries and inodes don't require IO to create */
 	s->s_shrink.seeks = 0;
 
@@ -140,19 +216,17 @@ static int proc_fill_super(struct super_block *s, struct fs_context *fc)
 static int proc_reconfigure(struct fs_context *fc)
 {
 	struct super_block *sb = fc->root->d_sb;
-	struct pid_namespace *pid = sb->s_fs_info;
+	struct proc_fs_info *fs_info = proc_sb_info(sb);
 
 	sync_filesystem(sb);
 
-	proc_apply_options(sb, fc, pid, current_user_ns());
+	proc_apply_options(fs_info, fc, current_user_ns());
 	return 0;
 }
 
 static int proc_get_tree(struct fs_context *fc)
 {
-	struct proc_fs_context *ctx = fc->fs_private;
-
-	return get_tree_keyed(fc, proc_fill_super, ctx->pid_ns);
+	return get_tree_nodev(fc, proc_fill_super);
 }
 
 static void proc_fs_context_free(struct fs_context *fc)
@@ -188,22 +262,17 @@ static int proc_init_fs_context(struct fs_context *fc)
 
 static void proc_kill_sb(struct super_block *sb)
 {
-	struct pid_namespace *ns;
+	struct proc_fs_info *fs_info = proc_sb_info(sb);
 
-	ns = (struct pid_namespace *)sb->s_fs_info;
-	if (ns->proc_self)
-		dput(ns->proc_self);
-	if (ns->proc_thread_self)
-		dput(ns->proc_thread_self);
-	kill_anon_super(sb);
+	if (fs_info->proc_self)
+		dput(fs_info->proc_self);
 
-	/* Make the pid namespace safe for the next mount of proc */
-	ns->proc_self = NULL;
-	ns->proc_thread_self = NULL;
-	ns->pid_gid = GLOBAL_ROOT_GID;
-	ns->hide_pid = 0;
+	if (fs_info->proc_thread_self)
+		dput(fs_info->proc_thread_self);
 
-	put_pid_ns(ns);
+	kill_anon_super(sb);
+	put_pid_ns(fs_info->pid_ns);
+	kfree(fs_info);
 }
 
 static struct file_system_type proc_fs_type = {