fix for account_group_exec_runtime(), make sure ->signal can't be freed under rq->lock

Impact: fix hang/crash on ia64 under high load

This is ugly, but the simplest patch by far.

Unlike other similar routines, account_group_exec_runtime() could be
called "implicitly" from within scheduler after exit_notify(). This
means we can race with the parent doing release_task(), we can't just
check ->signal != NULL.

Change __exit_signal() to do spin_unlock_wait(&task_rq(tsk)->lock)
before __cleanup_signal() to make sure ->signal can't be freed under
task_rq(tsk)->lock. Note that task_rq_unlock_wait() doesn't care
about the case when tsk changes cpu/rq under us, this should be OK.

Thanks to Ingo who nacked my previous buggy patch.

Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Reported-by: Doug Chapman <doug.chapman@hp.com>

3 files changed, 14 insertions, 0 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 295b7c756ca6..644ffbda17ca 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -247,6 +247,7 @@ extern void init_idle(struct task_struct *idle, int cpu);
 extern void init_idle_bootup_task(struct task_struct *idle);
 
 extern int runqueue_is_locked(void);
+extern void task_rq_unlock_wait(struct task_struct *p);
 
 extern cpumask_t nohz_cpu_mask;
 #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ)
diff --git a/kernel/exit.c b/kernel/exit.c
index 80137a5d9467..ae2b92be5fae 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -141,6 +141,11 @@ static void __exit_signal(struct task_struct *tsk)
         if (sig) {
                 flush_sigqueue(&sig->shared_pending);
                 taskstats_tgid_free(sig);
+                /*
+                 * Make sure ->signal can't go away under rq->lock,
+                 * see account_group_exec_runtime().
+                 */
+                task_rq_unlock_wait(tsk);
                 __cleanup_signal(sig);
         }
 }
diff --git a/kernel/sched.c b/kernel/sched.c
index f3149244e324..50a21f964679 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -969,6 +969,14 @@ static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
         }
 }
 
+void task_rq_unlock_wait(struct task_struct *p)
+{
+        struct rq *rq = task_rq(p);
+
+        smp_mb(); /* spin-unlock-wait is not a full memory barrier */
+        spin_unlock_wait(&rq->lock);
+}
+
 static void __task_rq_unlock(struct rq *rq)
         __releases(rq->lock)
 {