diff --git a/kernel/events/core.c b/kernel/events/core.c
index f042d61019320fdf5e079bbec0b943403b44bd72..eb567b5c4dee676e37c5b9e590448f34619b1cfd 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6737,18 +6737,18 @@ void perf_event_wakeup(struct perf_event *event)
 static void perf_sigtrap(struct perf_event *event)
 {
 	/*
-	 * We'd expect this to only occur if the irq_work is delayed and either
-	 * ctx->task or current has changed in the meantime. This can be the
-	 * case on architectures that do not implement arch_irq_work_raise().
+	 * Both perf_pending_task() and perf_pending_irq() can race with the
+	 * task exiting.
 	 */
-	if (WARN_ON_ONCE(event->ctx->task != current))
+	if (current->flags & PF_EXITING)
 		return;
 
 	/*
-	 * Both perf_pending_task() and perf_pending_irq() can race with the
-	 * task exiting.
+	 * We'd expect this to only occur if the irq_work is delayed and either
+	 * ctx->task or current has changed in the meantime. This can be the
+	 * case on architectures that do not implement arch_irq_work_raise().
 	 */
-	if (current->flags & PF_EXITING)
+	if (WARN_ON_ONCE(event->ctx->task != current))
 		return;
 
 	send_sig_perf((void __user *)event->pending_addr,
@@ -6959,6 +6959,10 @@ perf_sample_ustack_size(u16 stack_size, u16 header_size,
 	if (!regs)
 		return 0;
 
+	/* No mm, no stack, no dump. */
+	if (!current->mm)
+		return 0;
+
 	/*
 	 * Check if we fit in with the requested stack size into the:
 	 * - TASK_SIZE
@@ -7664,6 +7668,9 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs)
 	const u32 max_stack = event->attr.sample_max_stack;
 	struct perf_callchain_entry *callchain;
 
+	if (!current->mm)
+		user = false;
+
 	if (!kernel && !user)
 		return &__empty_callchain;
 
diff --git a/kernel/exit.c b/kernel/exit.c
index f2b87b2a700984605bfc35224efeccf018562db1..4c7a08ad745610d8d3b94546c4cb8be96f8c9b67 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -855,6 +855,15 @@ void __noreturn do_exit(long code)
 	tsk->exit_code = code;
 	taskstats_exit(tsk, group_dead);
 
+	/*
+	 * Since sampling can touch ->mm, make sure to stop everything before we
+	 * tear it down.
+	 *
+	 * Also flushes inherited counters to the parent - before the parent
+	 * gets woken up by child-exit notifications.
+	 */
+	perf_event_exit_task(tsk);
+
 	exit_mm();
 
 	if (group_dead)
@@ -871,14 +880,6 @@ void __noreturn do_exit(long code)
 	exit_task_work(tsk);
 	exit_thread(tsk);
 
-	/*
-	 * Flush inherited counters to the parent - before the parent
-	 * gets woken up by child-exit notifications.
-	 *
-	 * because of cgroup mode, must be called before cgroup_exit()
-	 */
-	perf_event_exit_task(tsk);
-
 	sched_autogroup_exit_task(tsk);
 	cgroup_exit(tsk);