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, 41 insertions, 33 deletions

diff --git a/fs/proc/base.c b/fs/proc/base.c
index eb2255e95f62..b1d94d14ed5a 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -697,13 +697,21 @@ int proc_setattr(struct dentry *dentry, struct iattr *attr)
  * May current process learn task's sched/cmdline info (for hide_pid_min=1)
  * or euid/egid (for hide_pid_min=2)?
  */
-static bool has_pid_permissions(struct pid_namespace *pid,
+static bool has_pid_permissions(struct proc_fs_info *fs_info,
 				 struct task_struct *task,
-				 int hide_pid_min)
+				 enum proc_hidepid hide_pid_min)
 {
-	if (pid->hide_pid < hide_pid_min)
+	/*
+	 * If 'hidpid' mount option is set force a ptrace check,
+	 * we indicate that we are using a filesystem syscall
+	 * by passing PTRACE_MODE_READ_FSCREDS
+	 */
+	if (fs_info->hide_pid == HIDEPID_NOT_PTRACEABLE)
+		return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS);
+
+	if (fs_info->hide_pid < hide_pid_min)
 		return true;
-	if (in_group_p(pid->pid_gid))
+	if (in_group_p(fs_info->pid_gid))
 		return true;
 	return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS);
 }
@@ -711,18 +719,18 @@ static bool has_pid_permissions(struct pid_namespace *pid,
 
 static int proc_pid_permission(struct inode *inode, int mask)
 {
-	struct pid_namespace *pid = proc_pid_ns(inode);
+	struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb);
 	struct task_struct *task;
 	bool has_perms;
 
 	task = get_proc_task(inode);
 	if (!task)
 		return -ESRCH;
-	has_perms = has_pid_permissions(pid, task, HIDEPID_NO_ACCESS);
+	has_perms = has_pid_permissions(fs_info, task, HIDEPID_NO_ACCESS);
 	put_task_struct(task);
 
 	if (!has_perms) {
-		if (pid->hide_pid == HIDEPID_INVISIBLE) {
+		if (fs_info->hide_pid == HIDEPID_INVISIBLE) {
 			/*
 			 * Let's make getdents(), stat(), and open()
 			 * consistent with each other.  If a process
@@ -746,7 +754,7 @@ static const struct inode_operations proc_def_inode_operations = {
 static int proc_single_show(struct seq_file *m, void *v)
 {
 	struct inode *inode = m->private;
-	struct pid_namespace *ns = proc_pid_ns(inode);
+	struct pid_namespace *ns = proc_pid_ns(inode->i_sb);
 	struct pid *pid = proc_pid(inode);
 	struct task_struct *task;
 	int ret;
@@ -1415,7 +1423,7 @@ static const struct file_operations proc_fail_nth_operations = {
 static int sched_show(struct seq_file *m, void *v)
 {
 	struct inode *inode = m->private;
-	struct pid_namespace *ns = proc_pid_ns(inode);
+	struct pid_namespace *ns = proc_pid_ns(inode->i_sb);
 	struct task_struct *p;
 
 	p = get_proc_task(inode);
@@ -1909,7 +1917,7 @@ int pid_getattr(const struct path *path, struct kstat *stat,
 		u32 request_mask, unsigned int query_flags)
 {
 	struct inode *inode = d_inode(path->dentry);
-	struct pid_namespace *pid = proc_pid_ns(inode);
+	struct proc_fs_info *fs_info = proc_sb_info(inode->i_sb);
 	struct task_struct *task;
 
 	generic_fillattr(inode, stat);
@@ -1919,7 +1927,7 @@ int pid_getattr(const struct path *path, struct kstat *stat,
 	rcu_read_lock();
 	task = pid_task(proc_pid(inode), PIDTYPE_PID);
 	if (task) {
-		if (!has_pid_permissions(pid, task, HIDEPID_INVISIBLE)) {
+		if (!has_pid_permissions(fs_info, task, HIDEPID_INVISIBLE)) {
 			rcu_read_unlock();
 			/*
 			 * This doesn't prevent learning whether PID exists,
@@ -2470,7 +2478,7 @@ static int proc_timers_open(struct inode *inode, struct file *file)
 		return -ENOMEM;
 
 	tp->pid = proc_pid(inode);
-	tp->ns = proc_pid_ns(inode);
+	tp->ns = proc_pid_ns(inode->i_sb);
 	return 0;
 }
 
@@ -3312,6 +3320,7 @@ struct dentry *proc_pid_lookup(struct dentry *dentry, unsigned int flags)
 {
 	struct task_struct *task;
 	unsigned tgid;
+	struct proc_fs_info *fs_info;
 	struct pid_namespace *ns;
 	struct dentry *result = ERR_PTR(-ENOENT);
 
@@ -3319,7 +3328,8 @@ struct dentry *proc_pid_lookup(struct dentry *dentry, unsigned int flags)
 	if (tgid == ~0U)
 		goto out;
 
-	ns = dentry->d_sb->s_fs_info;
+	fs_info = proc_sb_info(dentry->d_sb);
+	ns = fs_info->pid_ns;
 	rcu_read_lock();
 	task = find_task_by_pid_ns(tgid, ns);
 	if (task)
@@ -3328,7 +3338,14 @@ struct dentry *proc_pid_lookup(struct dentry *dentry, unsigned int flags)
 	if (!task)
 		goto out;
 
+	/* Limit procfs to only ptraceable tasks */
+	if (fs_info->hide_pid == HIDEPID_NOT_PTRACEABLE) {
+		if (!has_pid_permissions(fs_info, task, HIDEPID_NO_ACCESS))
+			goto out_put_task;
+	}
+
 	result = proc_pid_instantiate(dentry, task, NULL);
+out_put_task:
 	put_task_struct(task);
 out:
 	return result;
@@ -3354,20 +3371,8 @@ retry:
 	pid = find_ge_pid(iter.tgid, ns);
 	if (pid) {
 		iter.tgid = pid_nr_ns(pid, ns);
-		iter.task = pid_task(pid, PIDTYPE_PID);
-		/* What we to know is if the pid we have find is the
-		 * pid of a thread_group_leader.  Testing for task
-		 * being a thread_group_leader is the obvious thing
-		 * todo but there is a window when it fails, due to
-		 * the pid transfer logic in de_thread.
-		 *
-		 * So we perform the straight forward test of seeing
-		 * if the pid we have found is the pid of a thread
-		 * group leader, and don't worry if the task we have
-		 * found doesn't happen to be a thread group leader.
-		 * As we don't care in the case of readdir.
-		 */
-		if (!iter.task || !has_group_leader_pid(iter.task)) {
+		iter.task = pid_task(pid, PIDTYPE_TGID);
+		if (!iter.task) {
 			iter.tgid += 1;
 			goto retry;
 		}
@@ -3383,20 +3388,21 @@ retry:
 int proc_pid_readdir(struct file *file, struct dir_context *ctx)
 {
 	struct tgid_iter iter;
-	struct pid_namespace *ns = proc_pid_ns(file_inode(file));
+	struct proc_fs_info *fs_info = proc_sb_info(file_inode(file)->i_sb);
+	struct pid_namespace *ns = proc_pid_ns(file_inode(file)->i_sb);
 	loff_t pos = ctx->pos;
 
 	if (pos >= PID_MAX_LIMIT + TGID_OFFSET)
 		return 0;
 
 	if (pos == TGID_OFFSET - 2) {
-		struct inode *inode = d_inode(ns->proc_self);
+		struct inode *inode = d_inode(fs_info->proc_self);
 		if (!dir_emit(ctx, "self", 4, inode->i_ino, DT_LNK))
 			return 0;
 		ctx->pos = pos = pos + 1;
 	}
 	if (pos == TGID_OFFSET - 1) {
-		struct inode *inode = d_inode(ns->proc_thread_self);
+		struct inode *inode = d_inode(fs_info->proc_thread_self);
 		if (!dir_emit(ctx, "thread-self", 11, inode->i_ino, DT_LNK))
 			return 0;
 		ctx->pos = pos = pos + 1;
@@ -3410,7 +3416,7 @@ int proc_pid_readdir(struct file *file, struct dir_context *ctx)
 		unsigned int len;
 
 		cond_resched();
-		if (!has_pid_permissions(ns, iter.task, HIDEPID_INVISIBLE))
+		if (!has_pid_permissions(fs_info, iter.task, HIDEPID_INVISIBLE))
 			continue;
 
 		len = snprintf(name, sizeof(name), "%u", iter.tgid);
@@ -3610,6 +3616,7 @@ static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry
 	struct task_struct *task;
 	struct task_struct *leader = get_proc_task(dir);
 	unsigned tid;
+	struct proc_fs_info *fs_info;
 	struct pid_namespace *ns;
 	struct dentry *result = ERR_PTR(-ENOENT);
 
@@ -3620,7 +3627,8 @@ static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry
 	if (tid == ~0U)
 		goto out;
 
-	ns = dentry->d_sb->s_fs_info;
+	fs_info = proc_sb_info(dentry->d_sb);
+	ns = fs_info->pid_ns;
 	rcu_read_lock();
 	task = find_task_by_pid_ns(tid, ns);
 	if (task)
@@ -3734,7 +3742,7 @@ static int proc_task_readdir(struct file *file, struct dir_context *ctx)
 	/* f_version caches the tgid value that the last readdir call couldn't
 	 * return. lseek aka telldir automagically resets f_version to 0.
 	 */
-	ns = proc_pid_ns(inode);
+	ns = proc_pid_ns(inode->i_sb);
 	tid = (int)file->f_version;
 	file->f_version = 0;
 	for (task = first_tid(proc_pid(inode), tid, ctx->pos - 2, ns);