Update Linux to v5.4.2

Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/kernel/exit.c b/kernel/exit.c
index 0e21e6d..d351fd0 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  linux/kernel/exit.c
  *
@@ -181,6 +182,11 @@
 	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)
 {
@@ -194,6 +200,7 @@
 	rcu_read_unlock();
 
 	proc_flush_task(p);
+	cgroup_release(p);
 
 	write_lock_irq(&tasklist_lock);
 	ptrace_release_task(p);
@@ -220,76 +227,13 @@
 
 	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;
@@ -307,12 +251,8 @@
 	 *        MB (A)	      MB (B)
 	 *    [L] cond		  [L] tsk
 	 */
-	smp_rmb(); /* (B) */
+	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);
@@ -421,7 +361,7 @@
 	 * freed task structure.
 	 */
 	if (atomic_read(&mm->mm_users) <= 1) {
-		mm->owner = NULL;
+		WRITE_ONCE(mm->owner, NULL);
 		return;
 	}
 
@@ -461,7 +401,7 @@
 	 * most likely racing with swapoff (try_to_unuse()) or /proc or
 	 * ptrace or page migration (get_task_mm()).  Mark owner as NULL.
 	 */
-	mm->owner = NULL;
+	WRITE_ONCE(mm->owner, NULL);
 	return;
 
 assign_new_owner:
@@ -482,7 +422,7 @@
 		put_task_struct(c);
 		goto retry;
 	}
-	mm->owner = c;
+	WRITE_ONCE(mm->owner, c);
 	task_unlock(c);
 	put_task_struct(c);
 }
@@ -497,7 +437,7 @@
 	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);
@@ -558,12 +498,14 @@
 	return NULL;
 }
 
-static struct task_struct *find_child_reaper(struct task_struct *father)
+static struct task_struct *find_child_reaper(struct task_struct *father,
+						struct list_head *dead)
 	__releases(&tasklist_lock)
 	__acquires(&tasklist_lock)
 {
 	struct pid_namespace *pid_ns = task_active_pid_ns(father);
 	struct task_struct *reaper = pid_ns->child_reaper;
+	struct task_struct *p, *n;
 
 	if (likely(reaper != father))
 		return reaper;
@@ -579,6 +521,12 @@
 		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);
+		release_task(p);
+	}
+
 	zap_pid_ns_processes(pid_ns);
 	write_lock_irq(&tasklist_lock);
 
@@ -668,7 +616,7 @@
 		exit_ptrace(father, dead);
 
 	/* Can drop and reacquire tasklist_lock */
-	reaper = find_child_reaper(father);
+	reaper = find_child_reaper(father, dead);
 	if (list_empty(&father->children))
 		return;
 
@@ -710,6 +658,7 @@
 	if (group_dead)
 		kill_orphaned_pgrp(tsk->group_leader, NULL);
 
+	tsk->exit_state = EXIT_ZOMBIE;
 	if (unlikely(tsk->ptrace)) {
 		int sig = thread_group_leader(tsk) &&
 				thread_group_empty(tsk) &&
@@ -723,9 +672,10 @@
 		autoreap = true;
 	}
 
-	tsk->exit_state = autoreap ? EXIT_DEAD : EXIT_ZOMBIE;
-	if (tsk->exit_state == EXIT_DEAD)
+	if (autoreap) {
+		tsk->exit_state = EXIT_DEAD;
 		list_add(&tsk->ptrace_entry, &dead);
+	}
 
 	/* mt-exec, de_thread() is waiting for group leader */
 	if (unlikely(tsk->signal->notify_count < 0))
@@ -796,32 +746,12 @@
 	 */
 	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",
@@ -866,6 +796,7 @@
 	exit_task_namespaces(tsk);
 	exit_task_work(tsk);
 	exit_thread(tsk);
+	exit_umh(tsk);
 
 	/*
 	 * Flush inherited counters to the parent - before the parent
@@ -895,12 +826,6 @@
 	 * 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);
@@ -1541,6 +1466,23 @@
 	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)
 {
@@ -1563,19 +1505,32 @@
 		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;
@@ -1604,10 +1559,9 @@
 	if (!infop)
 		return err;
 
-	if (!access_ok(VERIFY_WRITE, infop, sizeof(*infop)))
+	if (!user_access_begin(infop, sizeof(*infop)))
 		return -EFAULT;
 
-	user_access_begin();
 	unsafe_put_user(signo, &infop->si_signo, Efault);
 	unsafe_put_user(0, &infop->si_errno, Efault);
 	unsafe_put_user(info.cause, &infop->si_code, Efault);
@@ -1732,10 +1686,9 @@
 	if (!infop)
 		return err;
 
-	if (!access_ok(VERIFY_WRITE, infop, sizeof(*infop)))
+	if (!user_access_begin(infop, sizeof(*infop)))
 		return -EFAULT;
 
-	user_access_begin();
 	unsafe_put_user(signo, &infop->si_signo, Efault);
 	unsafe_put_user(0, &infop->si_errno, Efault);
 	unsafe_put_user(info.cause, &infop->si_code, Efault);