1 files changed, 105 insertions, 13 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index fd90195667e1..84ae830234f8 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -211,6 +211,82 @@ repeat:
 }
 
 /*
+ * Note that if this function returns a valid task_struct pointer (!NULL)
+ * task->usage must remain >0 for the duration of the RCU critical section.
+ */
+struct task_struct *task_rcu_dereference(struct task_struct **ptask)
+{
+	struct sighand_struct *sighand;
+	struct task_struct *task;
+
+	/*
+	 * We need to verify that release_task() was not called and thus
+	 * delayed_put_task_struct() can't run and drop the last reference
+	 * before rcu_read_unlock(). We check task->sighand != NULL,
+	 * but we can read the already freed and reused memory.
+	 */
+retry:
+	task = rcu_dereference(*ptask);
+	if (!task)
+		return NULL;
+
+	probe_kernel_address(&task->sighand, sighand);
+
+	/*
+	 * Pairs with atomic_dec_and_test() in put_task_struct(). If this task
+	 * was already freed we can not miss the preceding update of this
+	 * pointer.
+	 */
+	smp_rmb();
+	if (unlikely(task != READ_ONCE(*ptask)))
+		goto retry;
+
+	/*
+	 * We've re-checked that "task == *ptask", now we have two different
+	 * cases:
+	 *
+	 * 1. This is actually the same task/task_struct. In this case
+	 *    sighand != NULL tells us it is still alive.
+	 *
+	 * 2. This is another task which got the same memory for task_struct.
+	 *    We can't know this of course, and we can not trust
+	 *    sighand != NULL.
+	 *
+	 *    In this case we actually return a random value, but this is
+	 *    correct.
+	 *
+	 *    If we return NULL - we can pretend that we actually noticed that
+	 *    *ptask was updated when the previous task has exited. Or pretend
+	 *    that probe_slab_address(&sighand) reads NULL.
+	 *
+	 *    If we return the new task (because sighand is not NULL for any
+	 *    reason) - this is fine too. This (new) task can't go away before
+	 *    another gp pass.
+	 *
+	 *    And note: We could even eliminate the false positive if re-read
+	 *    task->sighand once again to avoid the falsely NULL. But this case
+	 *    is very unlikely so we don't care.
+	 */
+	if (!sighand)
+		return NULL;
+
+	return task;
+}
+
+struct task_struct *try_get_task_struct(struct task_struct **ptask)
+{
+	struct task_struct *task;
+
+	rcu_read_lock();
+	task = task_rcu_dereference(ptask);
+	if (task)
+		get_task_struct(task);
+	rcu_read_unlock();
+
+	return task;
+}
+
+/*
  * Determine if a process group is "orphaned", according to the POSIX
  * definition in 2.2.2.52.  Orphaned process groups are not to be affected
  * by terminal-generated stop signals.  Newly orphaned process groups are
@@ -700,10 +776,14 @@ void do_exit(long code)
 
 	exit_signals(tsk);  /* sets PF_EXITING */
 	/*
-	 * tsk->flags are checked in the futex code to protect against
-	 * an exiting task cleaning up the robust pi futexes.
+	 * Ensure that all new tsk->pi_lock acquisitions must observe
+	 * PF_EXITING. Serializes against futex.c:attach_to_pi_owner().
 	 */
 	smp_mb();
+	/*
+	 * Ensure that we must observe the pi_state in exit_mm() ->
+	 * mm_release() -> exit_pi_state_list().
+	 */
 	raw_spin_unlock_wait(&tsk->pi_lock);
 
 	if (unlikely(in_atomic())) {
@@ -746,7 +826,7 @@ void do_exit(long code)
 		disassociate_ctty(1);
 	exit_task_namespaces(tsk);
 	exit_task_work(tsk);
-	exit_thread();
+	exit_thread(tsk);
 
 	/*
 	 * Flush inherited counters to the parent - before the parent
@@ -918,17 +998,28 @@ static int eligible_pid(struct wait_opts *wo, struct task_struct *p)
 		task_pid_type(p, wo->wo_type) == wo->wo_pid;
 }
 
-static int eligible_child(struct wait_opts *wo, struct task_struct *p)
+static int
+eligible_child(struct wait_opts *wo, bool ptrace, struct task_struct *p)
 {
 	if (!eligible_pid(wo, p))
 		return 0;
-	/* Wait for all children (clone and not) if __WALL is set;
-	 * otherwise, wait for clone children *only* if __WCLONE is
-	 * set; otherwise, wait for non-clone children *only*.  (Note:
-	 * A "clone" child here is one that reports to its parent
-	 * using a signal other than SIGCHLD.) */
-	if (((p->exit_signal != SIGCHLD) ^ !!(wo->wo_flags & __WCLONE))
-	    && !(wo->wo_flags & __WALL))
+
+	/*
+	 * Wait for all children (clone and not) if __WALL is set or
+	 * if it is traced by us.
+	 */
+	if (ptrace || (wo->wo_flags & __WALL))
+		return 1;
+
+	/*
+	 * Otherwise, wait for clone children *only* if __WCLONE is set;
+	 * otherwise, wait for non-clone children *only*.
+	 *
+	 * Note: a "clone" child here is one that reports to its parent
+	 * using a signal other than SIGCHLD, or a non-leader thread which
+	 * we can only see if it is traced by us.
+	 */
+	if ((p->exit_signal != SIGCHLD) ^ !!(wo->wo_flags & __WCLONE))
 		return 0;
 
 	return 1;
@@ -1300,7 +1391,7 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace,
 	if (unlikely(exit_state == EXIT_DEAD))
 		return 0;
 
-	ret = eligible_child(wo, p);
+	ret = eligible_child(wo, ptrace, p);
 	if (!ret)
 		return ret;
 
@@ -1524,7 +1615,8 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *,
 	enum pid_type type;
 	long ret;
 
-	if (options & ~(WNOHANG|WNOWAIT|WEXITED|WSTOPPED|WCONTINUED))
+	if (options & ~(WNOHANG|WNOWAIT|WEXITED|WSTOPPED|WCONTINUED|
+			__WNOTHREAD|__WCLONE|__WALL))
 		return -EINVAL;
 	if (!(options & (WEXITED|WSTOPPED|WCONTINUED)))
 		return -EINVAL;