1 files changed, 52 insertions, 106 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index 5b4a5dcce8f8..2833ffb0c211 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -182,6 +182,11 @@ static void delayed_put_task_struct(struct rcu_head *rhp)
 	put_task_struct(tsk);
 }
 
+void put_task_struct_rcu_user(struct task_struct *task)
+{
+	if (refcount_dec_and_test(&task->rcu_users))
+		call_rcu(&task->rcu, delayed_put_task_struct);
+}
 
 void release_task(struct task_struct *p)
 {
@@ -222,76 +227,13 @@ repeat:
 
 	write_unlock_irq(&tasklist_lock);
 	release_thread(p);
-	call_rcu(&p->rcu, delayed_put_task_struct);
+	put_task_struct_rcu_user(p);
 
 	p = leader;
 	if (unlikely(zap_leader))
 		goto 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;
-}
-
 void rcuwait_wake_up(struct rcuwait *w)
 {
 	struct task_struct *task;
@@ -311,10 +253,6 @@ void rcuwait_wake_up(struct rcuwait *w)
 	 */
 	smp_mb(); /* (B) */
 
-	/*
-	 * Avoid using task_rcu_dereference() magic as long as we are careful,
-	 * see comment in rcuwait_wait_event() regarding ->exit_state.
-	 */
 	task = rcu_dereference(w->task);
 	if (task)
 		wake_up_process(task);
@@ -499,7 +437,7 @@ static void exit_mm(void)
 	struct mm_struct *mm = current->mm;
 	struct core_state *core_state;
 
-	mm_release(current, mm);
+	exit_mm_release(current, mm);
 	if (!mm)
 		return;
 	sync_mm_rss(mm);
@@ -579,10 +517,6 @@ static struct task_struct *find_child_reaper(struct task_struct *father,
 	}
 
 	write_unlock_irq(&tasklist_lock);
-	if (unlikely(pid_ns == &init_pid_ns)) {
-		panic("Attempted to kill init! exitcode=0x%08x\n",
-			father->signal->group_exit_code ?: father->exit_code);
-	}
 
 	list_for_each_entry_safe(p, n, dead, ptrace_entry) {
 		list_del_init(&p->ptrace_entry);
@@ -808,32 +742,12 @@ void __noreturn do_exit(long code)
 	 */
 	if (unlikely(tsk->flags & PF_EXITING)) {
 		pr_alert("Fixing recursive fault but reboot is needed!\n");
-		/*
-		 * We can do this unlocked here. The futex code uses
-		 * this flag just to verify whether the pi state
-		 * cleanup has been done or not. In the worst case it
-		 * loops once more. We pretend that the cleanup was
-		 * done as there is no way to return. Either the
-		 * OWNER_DIED bit is set by now or we push the blocked
-		 * task into the wait for ever nirwana as well.
-		 */
-		tsk->flags |= PF_EXITPIDONE;
+		futex_exit_recursive(tsk);
 		set_current_state(TASK_UNINTERRUPTIBLE);
 		schedule();
 	}
 
 	exit_signals(tsk);  /* sets PF_EXITING */
-	/*
-	 * 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_lock_irq(&tsk->pi_lock);
-	raw_spin_unlock_irq(&tsk->pi_lock);
 
 	if (unlikely(in_atomic())) {
 		pr_info("note: %s[%d] exited with preempt_count %d\n",
@@ -848,6 +762,14 @@ void __noreturn do_exit(long code)
 	acct_update_integrals(tsk);
 	group_dead = atomic_dec_and_test(&tsk->signal->live);
 	if (group_dead) {
+		/*
+		 * If the last thread of global init has exited, panic
+		 * immediately to get a useable coredump.
+		 */
+		if (unlikely(is_global_init(tsk)))
+			panic("Attempted to kill init! exitcode=0x%08x\n",
+				tsk->signal->group_exit_code ?: (int)code);
+
 #ifdef CONFIG_POSIX_TIMERS
 		hrtimer_cancel(&tsk->signal->real_timer);
 		exit_itimers(tsk->signal);
@@ -908,12 +830,6 @@ void __noreturn do_exit(long code)
 	 * Make sure we are holding no locks:
 	 */
 	debug_check_no_locks_held();
-	/*
-	 * We can do this unlocked here. The futex code uses this flag
-	 * just to verify whether the pi state cleanup has been done
-	 * or not. In the worst case it loops once more.
-	 */
-	tsk->flags |= PF_EXITPIDONE;
 
 	if (tsk->io_context)
 		exit_io_context(tsk);
@@ -1497,7 +1413,7 @@ static int child_wait_callback(wait_queue_entry_t *wait, unsigned mode,
 void __wake_up_parent(struct task_struct *p, struct task_struct *parent)
 {
 	__wake_up_sync_key(&parent->signal->wait_chldexit,
-				TASK_INTERRUPTIBLE, 1, p);
+			   TASK_INTERRUPTIBLE, p);
 }
 
 static long do_wait(struct wait_opts *wo)
@@ -1519,7 +1435,7 @@ repeat:
 	 */
 	wo->notask_error = -ECHILD;
 	if ((wo->wo_type < PIDTYPE_MAX) &&
-	   (!wo->wo_pid || hlist_empty(&wo->wo_pid->tasks[wo->wo_type])))
+	   (!wo->wo_pid || !pid_has_task(wo->wo_pid, wo->wo_type)))
 		goto notask;
 
 	set_current_state(TASK_INTERRUPTIBLE);
@@ -1554,6 +1470,23 @@ end:
 	return retval;
 }
 
+static struct pid *pidfd_get_pid(unsigned int fd)
+{
+	struct fd f;
+	struct pid *pid;
+
+	f = fdget(fd);
+	if (!f.file)
+		return ERR_PTR(-EBADF);
+
+	pid = pidfd_pid(f.file);
+	if (!IS_ERR(pid))
+		get_pid(pid);
+
+	fdput(f);
+	return pid;
+}
+
 static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop,
 			  int options, struct rusage *ru)
 {
@@ -1576,19 +1509,32 @@ static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop,
 		type = PIDTYPE_PID;
 		if (upid <= 0)
 			return -EINVAL;
+
+		pid = find_get_pid(upid);
 		break;
 	case P_PGID:
 		type = PIDTYPE_PGID;
-		if (upid <= 0)
+		if (upid < 0)
 			return -EINVAL;
+
+		if (upid)
+			pid = find_get_pid(upid);
+		else
+			pid = get_task_pid(current, PIDTYPE_PGID);
+		break;
+	case P_PIDFD:
+		type = PIDTYPE_PID;
+		if (upid < 0)
+			return -EINVAL;
+
+		pid = pidfd_get_pid(upid);
+		if (IS_ERR(pid))
+			return PTR_ERR(pid);
 		break;
 	default:
 		return -EINVAL;
 	}
 
-	if (type < PIDTYPE_MAX)
-		pid = find_get_pid(upid);
-
 	wo.wo_type	= type;
 	wo.wo_pid	= pid;
 	wo.wo_flags	= options;