sched/numa: Fix use of spin_{un}lock_irq() when interrupts are disabled

As Peter Zijlstra told me, we have the following path:

do_exit()
  exit_itimers()
    itimer_delete()
      spin_lock_irqsave(&timer->it_lock, &flags);
      timer_delete_hook(timer);
        kc->timer_del(timer) := posix_cpu_timer_del()
          put_task_struct()
            __put_task_struct()
              task_numa_free()
                spin_lock(&grp->lock);

Which means that task_numa_free() can be called with interrupts
disabled, which means that we should not be using spin_lock_irq() but
spin_lock_irqsave() instead. Otherwise we are enabling interrupts while
holding an interrupt unsafe lock!

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner<tglx@linutronix.de>
Cc: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20140527182541.GH11096@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0fdb96de81a5b8a92c302961769cdefdb5cad915..b4768c0693927b1ce801502f79aa6e7fe9da1f80 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1707,18 +1707,19 @@ no_join:
 void task_numa_free(struct task_struct *p)
 {
        struct numa_group *grp = p->numa_group;
-       int i;
        void *numa_faults = p->numa_faults_memory;
+       unsigned long flags;
+       int i;
 
        if (grp) {
-               spin_lock_irq(&grp->lock);
+               spin_lock_irqsave(&grp->lock, flags);
                for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++)
                        grp->faults[i] -= p->numa_faults_memory[i];
                grp->total_faults -= p->total_numa_faults;
 
                list_del(&p->numa_entry);
                grp->nr_tasks--;
-               spin_unlock_irq(&grp->lock);
+               spin_unlock_irqrestore(&grp->lock, flags);
                rcu_assign_pointer(p->numa_group, NULL);
                put_numa_group(grp);
        }