exit: Move preemption fixup up, move blocking operations down

With CONFIG_DEBUG_ATOMIC_SLEEP=y and CONFIG_CGROUPS=y, kernel oopses in
non-preemptible context look untidy; after the main oops, the kernel prints
a "sleeping function called from invalid context" report because
exit_signals() -> cgroup_threadgroup_change_begin() -> percpu_down_read()
can sleep, and that happens before the preempt_count_set(PREEMPT_ENABLED)
fixup.

It looks like the same thing applies to profile_task_exit() and
kcov_task_exit().

Fix it by moving the preemption fixup up and the calls to
profile_task_exit() and kcov_task_exit() down.

Fixes: 1dc0fffc48af ("sched/core: Robustify preemption leak checks")
Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200305220657.46800-1-jannh@google.com

1 files changed, 16 insertions, 9 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index ce2a75bc0ade..d56fe51bdf07 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -708,8 +708,12 @@ void __noreturn do_exit(long code)
 	struct task_struct *tsk = current;
 	int group_dead;
 
-	profile_task_exit(tsk);
-	kcov_task_exit(tsk);
+	/*
+	 * We can get here from a kernel oops, sometimes with preemption off.
+	 * Start by checking for critical errors.
+	 * Then fix up important state like USER_DS and preemption.
+	 * Then do everything else.
+	 */
 
 	WARN_ON(blk_needs_flush_plug(tsk));
 
@@ -727,6 +731,16 @@ void __noreturn do_exit(long code)
 	 */
 	set_fs(USER_DS);
 
+	if (unlikely(in_atomic())) {
+		pr_info("note: %s[%d] exited with preempt_count %d\n",
+			current->comm, task_pid_nr(current),
+			preempt_count());
+		preempt_count_set(PREEMPT_ENABLED);
+	}
+
+	profile_task_exit(tsk);
+	kcov_task_exit(tsk);
+
 	ptrace_event(PTRACE_EVENT_EXIT, code);
 
 	validate_creds_for_do_exit(tsk);
@@ -744,13 +758,6 @@ void __noreturn do_exit(long code)
 
 	exit_signals(tsk);  /* sets PF_EXITING */
 
-	if (unlikely(in_atomic())) {
-		pr_info("note: %s[%d] exited with preempt_count %d\n",
-			current->comm, task_pid_nr(current),
-			preempt_count());
-		preempt_count_set(PREEMPT_ENABLED);
-	}
-
 	/* sync mm's RSS info before statistics gathering */
 	if (tsk->mm)
 		sync_mm_rss(tsk->mm);