[PATCH] pids: make task_tgid_nr_ns() safe

[Oleg Nesterov]

This was reported many times, and this was even mentioned in commit
52ee2dfdd4f5 "pids: refactor vnr/nr_ns helpers to make them safe" but
somehow nobody bothered to fix the obvious problem: task_tgid_nr_ns()
is not safe because task->group_leader points to nowhere after the
exiting task passes exit_notify(), rcu_read_lock() can not help.

We really need to change __unhash_process() to nullify group_leader,
parent, and real_parent, but this needs some cleanups. Until then we
can turn task_tgid_nr_ns() into another user of __task_pid_nr_ns() and
fix the problem.

Reported-by: Troy Kensinger <tkensinger@xxxxxxxxxx>
Signed-off-by: Oleg Nesterov <oleg@xxxxxxxxxx>
---
 include/linux/pid.h   |  4 +++-
 include/linux/sched.h | 51 +++++++++++++++++++++++++++------------------------
 kernel/pid.c          | 11 ++++-------
 3 files changed, 34 insertions(+), 32 deletions(-)

diff --git a/include/linux/pid.h b/include/linux/pid.h
index 4d17931..7195827 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -8,7 +8,9 @@ enum pid_type
 	PIDTYPE_PID,
 	PIDTYPE_PGID,
 	PIDTYPE_SID,
-	PIDTYPE_MAX
+	PIDTYPE_MAX,
+	/* only valid to __task_pid_nr_ns() */
+	__PIDTYPE_TGID
 };
 
 /*
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8337e2d..c05ac5f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1163,13 +1163,6 @@ static inline pid_t task_tgid_nr(struct task_struct *tsk)
 	return tsk->tgid;
 }
 
-extern pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns);
-
-static inline pid_t task_tgid_vnr(struct task_struct *tsk)
-{
-	return pid_vnr(task_tgid(tsk));
-}
-
 /**
  * pid_alive - check that a task structure is not stale
  * @p: Task structure to be checked.
@@ -1185,23 +1178,6 @@ static inline int pid_alive(const struct task_struct *p)
 	return p->pids[PIDTYPE_PID].pid != NULL;
 }
 
-static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns)
-{
-	pid_t pid = 0;
-
-	rcu_read_lock();
-	if (pid_alive(tsk))
-		pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns);
-	rcu_read_unlock();
-
-	return pid;
-}
-
-static inline pid_t task_ppid_nr(const struct task_struct *tsk)
-{
-	return task_ppid_nr_ns(tsk, &init_pid_ns);
-}
-
 static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
 {
 	return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns);
@@ -1223,6 +1199,33 @@ static inline pid_t task_session_vnr(struct task_struct *tsk)
 	return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL);
 }
 
+static inline pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
+{
+	return __task_pid_nr_ns(tsk, __PIDTYPE_TGID, ns);
+}
+
+static inline pid_t task_tgid_vnr(struct task_struct *tsk)
+{
+	return __task_pid_nr_ns(tsk, __PIDTYPE_TGID, NULL);
+}
+
+static inline pid_t task_ppid_nr_ns(const struct task_struct *tsk, struct pid_namespace *ns)
+{
+	pid_t pid = 0;
+
+	rcu_read_lock();
+	if (pid_alive(tsk))
+		pid = task_tgid_nr_ns(rcu_dereference(tsk->real_parent), ns);
+	rcu_read_unlock();
+
+	return pid;
+}
+
+static inline pid_t task_ppid_nr(const struct task_struct *tsk)
+{
+	return task_ppid_nr_ns(tsk, &init_pid_ns);
+}
+
 /* Obsolete, do not use: */
 static inline pid_t task_pgrp_nr(struct task_struct *tsk)
 {
diff --git a/kernel/pid.c b/kernel/pid.c
index c69c30d..020dedb 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -527,8 +527,11 @@ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
 	if (!ns)
 		ns = task_active_pid_ns(current);
 	if (likely(pid_alive(task))) {
-		if (type != PIDTYPE_PID)
+		if (type != PIDTYPE_PID) {
+			if (type == __PIDTYPE_TGID)
+				type = PIDTYPE_PID;
 			task = task->group_leader;
+		}
 		nr = pid_nr_ns(rcu_dereference(task->pids[type].pid), ns);
 	}
 	rcu_read_unlock();
@@ -537,12 +540,6 @@ pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
 }
 EXPORT_SYMBOL(__task_pid_nr_ns);
 
-pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
-{
-	return pid_nr_ns(task_tgid(tsk), ns);
-}
-EXPORT_SYMBOL(task_tgid_nr_ns);
-
 struct pid_namespace *task_active_pid_ns(struct task_struct *tsk)
 {
 	return ns_of_pid(task_pid(tsk));
-- 
2.5.0