timers/core: Convert to hotplug state machine

When tearing down, call timers_dead_cpu() before notify_dead().
There is a hidden dependency between:

 - timers
 - block multiqueue
 - rcutree

If timers_dead_cpu() comes later than blk_mq_queue_reinit_notify()
that latter function causes a RCU stall.

Signed-off-by: Richard Cochran <rcochran@linutronix.de>
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: rt@linutronix.de
Link: http://lkml.kernel.org/r/20160713153337.566790058@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>

4 files changed, 14 insertions, 23 deletions

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 04ecc55009ed..15d46d2a1d16 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -16,6 +16,7 @@ enum cpuhp_state {
         CPUHP_X86_APB_DEAD,
         CPUHP_WORKQUEUE_PREP,
         CPUHP_HRTIMERS_PREPARE,
+        CPUHP_TIMERS_DEAD,
         CPUHP_NOTIFY_PREPARE,
         CPUHP_BRINGUP_CPU,
         CPUHP_AP_IDLE_DEAD,
diff --git a/include/linux/timer.h b/include/linux/timer.h
index 4419506b564e..51d601f192d4 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -273,4 +273,10 @@ unsigned long __round_jiffies_up_relative(unsigned long j, int cpu);
 unsigned long round_jiffies_up(unsigned long j);
 unsigned long round_jiffies_up_relative(unsigned long j);
 
+#ifdef CONFIG_HOTPLUG_CPU
+int timers_dead_cpu(unsigned int cpu);
+#else
+#define timers_dead_cpu NULL
+#endif
+
 #endif
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 85500e7fe238..e1017d92d308 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1195,6 +1195,11 @@ static struct cpuhp_step cpuhp_bp_states[] = {
                 .startup = hrtimers_prepare_cpu,
                 .teardown = hrtimers_dead_cpu,
         },
+        [CPUHP_TIMERS_DEAD] = {
+                .name = "timers dead",
+                .startup = NULL,
+                .teardown = timers_dead_cpu,
+        },
         /*
          * Preparatory and dead notifiers. Will be replaced once the notifiers
          * are converted to states.
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index cb9ab401e2d9..555670a5143c 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1804,7 +1804,7 @@ static void migrate_timer_list(struct timer_base *new_base, struct hlist_head *h
         }
 }
 
-static void migrate_timers(int cpu)
+int timers_dead_cpu(unsigned int cpu)
 {
         struct timer_base *old_base;
         struct timer_base *new_base;
@@ -1831,29 +1831,9 @@ static void migrate_timers(int cpu)
                 spin_unlock_irq(&new_base->lock);
                 put_cpu_ptr(&timer_bases);
         }
+        return 0;
 }
 
-static int timer_cpu_notify(struct notifier_block *self,
-                                unsigned long action, void *hcpu)
-{
-        switch (action) {
-        case CPU_DEAD:
-        case CPU_DEAD_FROZEN:
-                migrate_timers((long)hcpu);
-                break;
-        default:
-                break;
-        }
-
-        return NOTIFY_OK;
-}
-
-static inline void timer_register_cpu_notifier(void)
-{
-        cpu_notifier(timer_cpu_notify, 0);
-}
-#else
-static inline void timer_register_cpu_notifier(void) { }
 #endif /* CONFIG_HOTPLUG_CPU */
 
 static void __init init_timer_cpu(int cpu)
@@ -1881,7 +1861,6 @@ void __init init_timers(void)
 {
         init_timer_cpus();
         init_timer_stats();
-        timer_register_cpu_notifier();
         open_softirq(TIMER_SOFTIRQ, run_timer_softirq);
 }