1 files changed, 142 insertions, 89 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index f5d2f63bae0..2913b3509d4 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -85,7 +85,6 @@ static void __exit_signal(struct task_struct *tsk)
 	struct tty_struct *uninitialized_var(tty);
 
 	sighand = rcu_dereference_check(tsk->sighand,
-					rcu_read_lock_held() ||
 					lockdep_tasklist_lock_is_held());
 	spin_lock(&sighand->siglock);
 
@@ -169,7 +168,6 @@ void release_task(struct task_struct * p)
 	struct task_struct *leader;
 	int zap_leader;
 repeat:
-	tracehook_prepare_release_task(p);
 	/* don't need to get the RCU readlock here - the process is dead and
 	 * can't be modifying its own credentials. But shut RCU-lockdep up */
 	rcu_read_lock();
@@ -179,7 +177,7 @@ repeat:
 	proc_flush_task(p);
 
 	write_lock_irq(&tasklist_lock);
-	tracehook_finish_release_task(p);
+	ptrace_release_task(p);
 	__exit_signal(p);
 
 	/*
@@ -190,22 +188,12 @@ repeat:
 	zap_leader = 0;
 	leader = p->group_leader;
 	if (leader != p && thread_group_empty(leader) && leader->exit_state == EXIT_ZOMBIE) {
-		BUG_ON(task_detached(leader));
-		do_notify_parent(leader, leader->exit_signal);
 		/*
 		 * If we were the last child thread and the leader has
 		 * exited already, and the leader's parent ignores SIGCHLD,
 		 * then we are the one who should release the leader.
-		 *
-		 * do_notify_parent() will have marked it self-reaping in
-		 * that case.
-		 */
-		zap_leader = task_detached(leader);
-
-		/*
-		 * This maintains the invariant that release_task()
-		 * only runs on a task in EXIT_DEAD, just for sanity.
 		 */
+		zap_leader = do_notify_parent(leader, leader->exit_signal);
 		if (zap_leader)
 			leader->exit_state = EXIT_DEAD;
 	}
@@ -277,18 +265,16 @@ int is_current_pgrp_orphaned(void)
 	return retval;
 }
 
-static int has_stopped_jobs(struct pid *pgrp)
+static bool has_stopped_jobs(struct pid *pgrp)
 {
-	int retval = 0;
 	struct task_struct *p;
 
 	do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
-		if (!task_is_stopped(p))
-			continue;
-		retval = 1;
-		break;
+		if (p->signal->flags & SIGNAL_STOP_STOPPED)
+			return true;
 	} while_each_pid_task(pgrp, PIDTYPE_PGID, p);
-	return retval;
+
+	return false;
 }
 
 /*
@@ -561,29 +547,28 @@ void exit_files(struct task_struct *tsk)
 
 #ifdef CONFIG_MM_OWNER
 /*
- * Task p is exiting and it owned mm, lets find a new owner for it
+ * A task is exiting.   If it owned this mm, find a new owner for the mm.
  */
-static inline int
-mm_need_new_owner(struct mm_struct *mm, struct task_struct *p)
-{
-	/*
-	 * If there are other users of the mm and the owner (us) is exiting
-	 * we need to find a new owner to take on the responsibility.
-	 */
-	if (atomic_read(&mm->mm_users) <= 1)
-		return 0;
-	if (mm->owner != p)
-		return 0;
-	return 1;
-}
-
 void mm_update_next_owner(struct mm_struct *mm)
 {
 	struct task_struct *c, *g, *p = current;
 
 retry:
-	if (!mm_need_new_owner(mm, p))
+	/*
+	 * If the exiting or execing task is not the owner, it's
+	 * someone else's problem.
+	 */
+	if (mm->owner != p)
 		return;
+	/*
+	 * The current owner is exiting/execing and there are no other
+	 * candidates.  Do not leave the mm pointing to a possibly
+	 * freed task structure.
+	 */
+	if (atomic_read(&mm->mm_users) <= 1) {
+		mm->owner = NULL;
+		return;
+	}
 
 	read_lock(&tasklist_lock);
 	/*
@@ -752,7 +737,7 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p,
 {
 	list_move_tail(&p->sibling, &p->real_parent->children);
 
-	if (task_detached(p))
+	if (p->exit_state == EXIT_DEAD)
 		return;
 	/*
 	 * If this is a threaded reparent there is no need to
@@ -765,10 +750,9 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p,
 	p->exit_signal = SIGCHLD;
 
 	/* If it has exited notify the new parent about this child's death. */
-	if (!task_ptrace(p) &&
+	if (!p->ptrace &&
 	    p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) {
-		do_notify_parent(p, p->exit_signal);
-		if (task_detached(p)) {
+		if (do_notify_parent(p, p->exit_signal)) {
 			p->exit_state = EXIT_DEAD;
 			list_move_tail(&p->sibling, dead);
 		}
@@ -795,7 +779,7 @@ static void forget_original_parent(struct task_struct *father)
 		do {
 			t->real_parent = reaper;
 			if (t->parent == father) {
-				BUG_ON(task_ptrace(t));
+				BUG_ON(t->ptrace);
 				t->parent = t->real_parent;
 			}
 			if (t->pdeath_signal)
@@ -820,8 +804,7 @@ static void forget_original_parent(struct task_struct *father)
  */
 static void exit_notify(struct task_struct *tsk, int group_dead)
 {
-	int signal;
-	void *cookie;
+	bool autoreap;
 
 	/*
 	 * This does two things:
@@ -852,26 +835,33 @@ static void exit_notify(struct task_struct *tsk, int group_dead)
 	 * we have changed execution domain as these two values started
 	 * the same after a fork.
 	 */
-	if (tsk->exit_signal != SIGCHLD && !task_detached(tsk) &&
+	if (thread_group_leader(tsk) && tsk->exit_signal != SIGCHLD &&
 	    (tsk->parent_exec_id != tsk->real_parent->self_exec_id ||
 	     tsk->self_exec_id != tsk->parent_exec_id))
 		tsk->exit_signal = SIGCHLD;
 
-	signal = tracehook_notify_death(tsk, &cookie, group_dead);
-	if (signal >= 0)
-		signal = do_notify_parent(tsk, signal);
+	if (unlikely(tsk->ptrace)) {
+		int sig = thread_group_leader(tsk) &&
+				thread_group_empty(tsk) &&
+				!ptrace_reparented(tsk) ?
+			tsk->exit_signal : SIGCHLD;
+		autoreap = do_notify_parent(tsk, sig);
+	} else if (thread_group_leader(tsk)) {
+		autoreap = thread_group_empty(tsk) &&
+			do_notify_parent(tsk, tsk->exit_signal);
+	} else {
+		autoreap = true;
+	}
 
-	tsk->exit_state = signal == DEATH_REAP ? EXIT_DEAD : EXIT_ZOMBIE;
+	tsk->exit_state = autoreap ? EXIT_DEAD : EXIT_ZOMBIE;
 
 	/* mt-exec, de_thread() is waiting for group leader */
 	if (unlikely(tsk->signal->notify_count < 0))
 		wake_up_process(tsk->signal->group_exit_task);
 	write_unlock_irq(&tasklist_lock);
 
-	tracehook_report_death(tsk, signal, cookie, group_dead);
-
 	/* If the process is dead, release it - nobody will wait for it */
-	if (signal == DEATH_REAP)
+	if (autoreap)
 		release_task(tsk);
 }
 
@@ -907,7 +897,6 @@ NORET_TYPE void do_exit(long code)
 
 	profile_task_exit(tsk);
 
-	WARN_ON(atomic_read(&tsk->fs_excl));
 	WARN_ON(blk_needs_flush_plug(tsk));
 
 	if (unlikely(in_interrupt()))
@@ -924,7 +913,7 @@ NORET_TYPE void do_exit(long code)
 	 */
 	set_fs(USER_DS);
 
-	tracehook_report_exit(&code);
+	ptrace_event(PTRACE_EVENT_EXIT, code);
 
 	validate_creds_for_do_exit(tsk);
 
@@ -991,6 +980,7 @@ NORET_TYPE void do_exit(long code)
 	trace_sched_process_exit(tsk);
 
 	exit_sem(tsk);
+	exit_shm(tsk);
 	exit_files(tsk);
 	exit_fs(tsk);
 	check_stack_usage();
@@ -1016,7 +1006,7 @@ NORET_TYPE void do_exit(long code)
 	/*
 	 * FIXME: do that only when needed, using sched_exit tracepoint
 	 */
-	flush_ptrace_hw_breakpoint(tsk);
+	ptrace_put_breakpoints(tsk);
 
 	exit_notify(tsk, group_dead);
 #ifdef CONFIG_NUMA
@@ -1236,9 +1226,9 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 	traced = ptrace_reparented(p);
 	/*
 	 * It can be ptraced but not reparented, check
-	 * !task_detached() to filter out sub-threads.
+	 * thread_group_leader() to filter out sub-threads.
 	 */
-	if (likely(!traced) && likely(!task_detached(p))) {
+	if (likely(!traced) && thread_group_leader(p)) {
 		struct signal_struct *psig;
 		struct signal_struct *sig;
 		unsigned long maxrss;
@@ -1346,16 +1336,13 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 		/* We dropped tasklist, ptracer could die and untrace */
 		ptrace_unlink(p);
 		/*
-		 * If this is not a detached task, notify the parent.
-		 * If it's still not detached after that, don't release
-		 * it now.
+		 * If this is not a sub-thread, notify the parent.
+		 * If parent wants a zombie, don't release it now.
 		 */
-		if (!task_detached(p)) {
-			do_notify_parent(p, p->exit_signal);
-			if (!task_detached(p)) {
-				p->exit_state = EXIT_ZOMBIE;
-				p = NULL;
-			}
+		if (thread_group_leader(p) &&
+		    !do_notify_parent(p, p->exit_signal)) {
+			p->exit_state = EXIT_ZOMBIE;
+			p = NULL;
 		}
 		write_unlock_irq(&tasklist_lock);
 	}
@@ -1368,7 +1355,8 @@ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
 static int *task_stopped_code(struct task_struct *p, bool ptrace)
 {
 	if (ptrace) {
-		if (task_is_stopped_or_traced(p))
+		if (task_is_stopped_or_traced(p) &&
+		    !(p->jobctl & JOBCTL_LISTENING))
 			return &p->exit_code;
 	} else {
 		if (p->signal->flags & SIGNAL_STOP_STOPPED)
@@ -1377,11 +1365,23 @@ static int *task_stopped_code(struct task_struct *p, bool ptrace)
 	return NULL;
 }
 
-/*
- * Handle sys_wait4 work for one task in state TASK_STOPPED.  We hold
- * read_lock(&tasklist_lock) on entry.  If we return zero, we still hold
- * the lock and this task is uninteresting.  If we return nonzero, we have
- * released the lock and the system call should return.
+/**
+ * wait_task_stopped - Wait for %TASK_STOPPED or %TASK_TRACED
+ * @wo: wait options
+ * @ptrace: is the wait for ptrace
+ * @p: task to wait for
+ *
+ * Handle sys_wait4() work for %p in state %TASK_STOPPED or %TASK_TRACED.
+ *
+ * CONTEXT:
+ * read_lock(&tasklist_lock), which is released if return value is
+ * non-zero.  Also, grabs and releases @p->sighand->siglock.
+ *
+ * RETURNS:
+ * 0 if wait condition didn't exist and search for other wait conditions
+ * should continue.  Non-zero return, -errno on failure and @p's pid on
+ * success, implies that tasklist_lock is released and wait condition
+ * search should terminate.
  */
 static int wait_task_stopped(struct wait_opts *wo,
 				int ptrace, struct task_struct *p)
@@ -1397,6 +1397,9 @@ static int wait_task_stopped(struct wait_opts *wo,
 	if (!ptrace && !(wo->wo_flags & WUNTRACED))
 		return 0;
 
+	if (!task_stopped_code(p, ptrace))
+		return 0;
+
 	exit_code = 0;
 	spin_lock_irq(&p->sighand->siglock);
 
@@ -1538,33 +1541,83 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace,
 		return 0;
 	}
 
-	if (likely(!ptrace) && unlikely(task_ptrace(p))) {
+	/* dead body doesn't have much to contribute */
+	if (p->exit_state == EXIT_DEAD)
+		return 0;
+
+	/* slay zombie? */
+	if (p->exit_state == EXIT_ZOMBIE) {
+		/*
+		 * A zombie ptracee is only visible to its ptracer.
+		 * Notification and reaping will be cascaded to the real
+		 * parent when the ptracer detaches.
+		 */
+		if (likely(!ptrace) && unlikely(p->ptrace)) {
+			/* it will become visible, clear notask_error */
+			wo->notask_error = 0;
+			return 0;
+		}
+
+		/* we don't reap group leaders with subthreads */
+		if (!delay_group_leader(p))
+			return wait_task_zombie(wo, p);
+
+		/*
+		 * Allow access to stopped/continued state via zombie by
+		 * falling through.  Clearing of notask_error is complex.
+		 *
+		 * When !@ptrace:
+		 *
+		 * If WEXITED is set, notask_error should naturally be
+		 * cleared.  If not, subset of WSTOPPED|WCONTINUED is set,
+		 * so, if there are live subthreads, there are events to
+		 * wait for.  If all subthreads are dead, it's still safe
+		 * to clear - this function will be called again in finite
+		 * amount time once all the subthreads are released and
+		 * will then return without clearing.
+		 *
+		 * When @ptrace:
+		 *
+		 * Stopped state is per-task and thus can't change once the
+		 * target task dies.  Only continued and exited can happen.
+		 * Clear notask_error if WCONTINUED | WEXITED.
+		 */
+		if (likely(!ptrace) || (wo->wo_flags & (WCONTINUED | WEXITED)))
+			wo->notask_error = 0;
+	} else {
+		/*
+		 * If @p is ptraced by a task in its real parent's group,
+		 * hide group stop/continued state when looking at @p as
+		 * the real parent; otherwise, a single stop can be
+		 * reported twice as group and ptrace stops.
+		 *
+		 * If a ptracer wants to distinguish the two events for its
+		 * own children, it should create a separate process which
+		 * takes the role of real parent.
+		 */
+		if (likely(!ptrace) && p->ptrace && !ptrace_reparented(p))
+			return 0;
+
 		/*
-		 * This child is hidden by ptrace.
-		 * We aren't allowed to see it now, but eventually we will.
+		 * @p is alive and it's gonna stop, continue or exit, so
+		 * there always is something to wait for.
 		 */
 		wo->notask_error = 0;
-		return 0;
 	}
 
-	if (p->exit_state == EXIT_DEAD)
-		return 0;
-
 	/*
-	 * We don't reap group leaders with subthreads.
+	 * Wait for stopped.  Depending on @ptrace, different stopped state
+	 * is used and the two don't interact with each other.
 	 */
-	if (p->exit_state == EXIT_ZOMBIE && !delay_group_leader(p))
-		return wait_task_zombie(wo, p);
+	ret = wait_task_stopped(wo, ptrace, p);
+	if (ret)
+		return ret;
 
 	/*
-	 * It's stopped or running now, so it might
-	 * later continue, exit, or stop again.
+	 * Wait for continued.  There's only one continued state and the
+	 * ptracer can consume it which can confuse the real parent.  Don't
+	 * use WCONTINUED from ptracer.  You don't need or want it.
 	 */
-	wo->notask_error = 0;
-
-	if (task_stopped_code(p, ptrace))
-		return wait_task_stopped(wo, ptrace, p);
-
 	return wait_task_continued(wo, p);
 }