sched/hotplug: Move migration CPU_DYING to sched_cpu_dying()

Remove the hotplug notifier and make it an explicit state.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: rt@linutronix.de
Link: http://lkml.kernel.org/r/20160310120025.502222097@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index b22b000cf6ee1b12982d5b628cc2fa2ae2053b23..21597dcac0e2edcfdb4536adba9c2432e936f9a7 100644 (file)
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -59,9 +59,7 @@ struct notifier_block;
  * CPU notifier priorities.
  */
 enum {
-       /* migration should happen before other stuff but after perf */
        CPU_PRI_PERF            = 20,
-       CPU_PRI_MIGRATION       = 10,
 
        /* bring up workqueues before normal notifiers and down after */
        CPU_PRI_WORKQUEUE_UP    = 5,

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1e5f961b1a74893418d7de6e25d9d36384cc4e27..47835cf8aefab0768578e92803d1b77689141f74 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -376,6 +376,12 @@ extern int sched_cpu_starting(unsigned int cpu);
 extern int sched_cpu_activate(unsigned int cpu);
 extern int sched_cpu_deactivate(unsigned int cpu);
 
+#ifdef CONFIG_HOTPLUG_CPU
+extern int sched_cpu_dying(unsigned int cpu);
+#else
+# define sched_cpu_dying       NULL
+#endif
+
 extern void sched_show_task(struct task_struct *p);
 
 #ifdef CONFIG_LOCKUP_DETECTOR

diff --git a/kernel/cpu.c b/kernel/cpu.c
index c134a35374a18743ae98dd200b643fdcf1e343c2..d6eeb8c5ef88a6535fbb679c406eb8805689bb90 100644 (file)
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1223,7 +1223,7 @@ static struct cpuhp_step cpuhp_ap_states[] = {
        [CPUHP_AP_SCHED_STARTING] = {
                .name                   = "sched:starting",
                .startup                = sched_cpu_starting,
-               .teardown               = NULL,
+               .teardown               = sched_cpu_dying,
        },
        /*
         * Low level startup/teardown notifiers. Run with interrupts

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 8d8d9034edff16829d0f8417a8e422fd6f312d7e..a9a65ed772e384779c0e436ff6afb747a42eddda 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5411,51 +5411,6 @@ static void set_rq_offline(struct rq *rq)
        }
 }
 
-/*
- * migration_call - callback that gets triggered when a CPU is added.
- * Here we can start up the necessary migration thread for the new CPU.
- */
-static int
-migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
-{
-       int cpu = (long)hcpu;
-       unsigned long flags;
-       struct rq *rq = cpu_rq(cpu);
-
-       switch (action & ~CPU_TASKS_FROZEN) {
-
-#ifdef CONFIG_HOTPLUG_CPU
-       case CPU_DYING:
-               sched_ttwu_pending();
-               /* Update our root-domain */
-               raw_spin_lock_irqsave(&rq->lock, flags);
-               if (rq->rd) {
-                       BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
-                       set_rq_offline(rq);
-               }
-               migrate_tasks(rq);
-               BUG_ON(rq->nr_running != 1); /* the migration thread */
-               raw_spin_unlock_irqrestore(&rq->lock, flags);
-               calc_load_migrate(rq);
-               break;
-#endif
-       }
-
-       update_max_interval();
-
-       return NOTIFY_OK;
-}
-
-/*
- * Register at high priority so that task migration (migrate_all_tasks)
- * happens before everything else.  This has to be lower priority than
- * the notifier in the perf_event subsystem, though.
- */
-static struct notifier_block migration_notifier = {
-       .notifier_call = migration_call,
-       .priority = CPU_PRI_MIGRATION,
-};
-
 static void set_cpu_rq_start_time(unsigned int cpu)
 {
        struct rq *rq = cpu_rq(cpu);
@@ -7158,6 +7113,28 @@ int sched_cpu_starting(unsigned int cpu)
        return 0;
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
+int sched_cpu_dying(unsigned int cpu)
+{
+       struct rq *rq = cpu_rq(cpu);
+       unsigned long flags;
+
+       /* Handle pending wakeups and then migrate everything off */
+       sched_ttwu_pending();
+       raw_spin_lock_irqsave(&rq->lock, flags);
+       if (rq->rd) {
+               BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
+               set_rq_offline(rq);
+       }
+       migrate_tasks(rq);
+       BUG_ON(rq->nr_running != 1);
+       raw_spin_unlock_irqrestore(&rq->lock, flags);
+       calc_load_migrate(rq);
+       update_max_interval();
+       return 0;
+}
+#endif
+
 void __init sched_init_smp(void)
 {
        cpumask_var_t non_isolated_cpus;
@@ -7194,12 +7171,7 @@ void __init sched_init_smp(void)
 
 static int __init migration_init(void)
 {
-       void *cpu = (void *)(long)smp_processor_id();
-
        sched_rq_cpu_starting(smp_processor_id());
-       migration_call(&migration_notifier, CPU_ONLINE, cpu);
-       register_cpu_notifier(&migration_notifier);
-
        return 0;
 }
 early_initcall(migration_init);