From: Jann Horn <jannh@xxxxxxxxxx>
[ Upstream commit 586b58cac8b4683eb58a1446fbc399de18974e40 ]
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@xxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Link: https://lkml.kernel.org/r/20200305220657.46800-1-jannh@xxxxxxxxxx
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
kernel/exit.c | 25 ++++++++++++++++---------
1 file changed, 16 insertions(+), 9 deletions(-)
diff --git a/kernel/exit.c b/kernel/exit.c
index 894fca56a38c..eeaafd4064c9 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -772,8 +772,12 @@ 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));
@@ -791,6 +795,16 @@ 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);
@@ -828,13 +842,6 @@ void __noreturn do_exit(long code)
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",
- 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);
--
2.25.1
