sched: Fix ttwu() for __ARCH_WANT_INTERRUPTS_ON_CTXSW

Marc reported that e4a52bcb9 (sched: Remove rq->lock from the first
half of ttwu()) broke his ARM-SMP machine. Now ARM is one of the few
__ARCH_WANT_INTERRUPTS_ON_CTXSW users, so that exception in the ttwu()
code was suspect.

Yong found that the interrupt could hit after context_switch() changes
current but before it clears p->on_cpu, if that interrupt were to
attempt a wake-up of p we would indeed find ourselves spinning in IRQ
context.

Fix this by reverting to the old behaviour for this situation and
perform a full remote wake-up.

Cc: Frank Rowand <frank.rowand@am.sony.com>
Cc: Yong Zhang <yong.zhang0@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Reported-by: Marc Zyngier <Marc.Zyngier@arm.com>
Tested-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/kernel/sched.c b/kernel/sched.c
index 5e43e9dc65d1c197aa9b085a4ccf546551570177..a80ee911900e571d42cc80cb2c4afa7032dfe81d 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2573,7 +2573,26 @@ static void ttwu_queue_remote(struct task_struct *p, int cpu)
        if (!next)
                smp_send_reschedule(cpu);
 }
-#endif
+
+#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
+static int ttwu_activate_remote(struct task_struct *p, int wake_flags)
+{
+       struct rq *rq;
+       int ret = 0;
+
+       rq = __task_rq_lock(p);
+       if (p->on_cpu) {
+               ttwu_activate(rq, p, ENQUEUE_WAKEUP);
+               ttwu_do_wakeup(rq, p, wake_flags);
+               ret = 1;
+       }
+       __task_rq_unlock(rq);
+
+       return ret;
+
+}
+#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
+#endif /* CONFIG_SMP */
 
 static void ttwu_queue(struct task_struct *p, int cpu)
 {
@@ -2631,17 +2650,17 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
        while (p->on_cpu) {
 #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
                /*
-                * If called from interrupt context we could have landed in the
-                * middle of schedule(), in this case we should take care not
-                * to spin on ->on_cpu if p is current, since that would
-                * deadlock.
+                * In case the architecture enables interrupts in
+                * context_switch(), we cannot busy wait, since that
+                * would lead to deadlocks when an interrupt hits and
+                * tries to wake up @prev. So bail and do a complete
+                * remote wakeup.
                 */
-               if (p == current) {
-                       ttwu_queue(p, cpu);
+               if (ttwu_activate_remote(p, wake_flags))
                        goto stat;
-               }
-#endif
+#else
                cpu_relax();
+#endif
        }
        /*
         * Pairs with the smp_wmb() in finish_lock_switch().