sched: adjust when cpu_active and cpuset configurations are updated during cpu on/offlining

Currently, when a cpu goes down, cpu_active is cleared before
CPU_DOWN_PREPARE starts and cpuset configuration is updated from a
default priority cpu notifier.  When a cpu is coming up, it's set
before CPU_ONLINE but cpuset configuration again is updated from the
same cpu notifier.

For cpu notifiers, this presents an inconsistent state.  Threads which
a CPU_DOWN_PREPARE notifier expects to be bound to the CPU can be
migrated to other cpus because the cpu is no more inactive.

Fix it by updating cpu_active in the highest priority cpu notifier and
cpuset configuration in the second highest when a cpu is coming up.
Down path is updated similarly.  This guarantees that all other cpu
notifiers see consistent cpu_active and cpuset configuration.

cpuset_track_online_cpus() notifier is converted to
cpuset_update_active_cpus() which just updates the configuration and
now called from cpuset_cpu_[in]active() notifiers registered from
sched_init_smp().  If cpuset is disabled, cpuset_update_active_cpus()
degenerates into partition_sched_domains() making separate notifier
for !CONFIG_CPUSETS unnecessary.

This problem is triggered by cmwq.  During CPU_DOWN_PREPARE, hotplug
callback creates a kthread and kthread_bind()s it to the target cpu,
and the thread is expected to run on that cpu.

* Ingo's test discovered __cpuinit/exit markups were incorrect.
  Fixed.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Paul Menage <menage@google.com>

3 files changed, 52 insertions, 42 deletions

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 97d1b42..f6e726f 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -235,11 +235,8 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 		return -EINVAL;
 
 	cpu_hotplug_begin();
-	set_cpu_active(cpu, false);
 	err = __cpu_notify(CPU_DOWN_PREPARE | mod, hcpu, -1, &nr_calls);
 	if (err) {
-		set_cpu_active(cpu, true);
-
 		nr_calls--;
 		__cpu_notify(CPU_DOWN_FAILED | mod, hcpu, nr_calls, NULL);
 		printk("%s: attempt to take down CPU %u failed\n",
@@ -249,7 +246,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 
 	err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
 	if (err) {
-		set_cpu_active(cpu, true);
 		/* CPU didn't die: tell everyone.  Can't complain. */
 		cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu);
 
@@ -321,8 +317,6 @@ static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen)
 		goto out_notify;
 	BUG_ON(!cpu_online(cpu));
 
-	set_cpu_active(cpu, true);
-
 	/* Now call notifier in preparation. */
 	cpu_notify(CPU_ONLINE | mod, hcpu);
 
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 02b9611..05727dc 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -2113,31 +2113,17 @@ static void scan_for_empty_cpusets(struct cpuset *root)
  * but making no active use of cpusets.
  *
  * This routine ensures that top_cpuset.cpus_allowed tracks
- * cpu_online_map on each CPU hotplug (cpuhp) event.
+ * cpu_active_mask on each CPU hotplug (cpuhp) event.
  *
  * Called within get_online_cpus().  Needs to call cgroup_lock()
  * before calling generate_sched_domains().
  */
-static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
-				unsigned long phase, void *unused_cpu)
+void __cpuexit cpuset_update_active_cpus(void)
 {
 	struct sched_domain_attr *attr;
 	cpumask_var_t *doms;
 	int ndoms;
 
-	switch (phase) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
-	case CPU_DOWN_FAILED:
-	case CPU_DOWN_FAILED_FROZEN:
-		break;
-
-	default:
-		return NOTIFY_DONE;
-	}
-
 	cgroup_lock();
 	mutex_lock(&callback_mutex);
 	cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask);
@@ -2148,8 +2134,6 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
 
 	/* Have scheduler rebuild the domains */
 	partition_sched_domains(ndoms, doms, attr);
-
-	return NOTIFY_OK;
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG
@@ -2203,7 +2187,6 @@ void __init cpuset_init_smp(void)
 	cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask);
 	top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
 
-	hotcpu_notifier(cpuset_track_online_cpus, 0);
 	hotplug_memory_notifier(cpuset_track_online_nodes, 10);
 
 	cpuset_wq = create_singlethread_workqueue("cpuset");
diff --git a/kernel/sched.c b/kernel/sched.c
index 552faf8..2b942e4 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -5804,17 +5804,46 @@ static struct notifier_block __cpuinitdata migration_notifier = {
 	.priority = CPU_PRI_MIGRATION,
 };
 
+static int __cpuinit sched_cpu_active(struct notifier_block *nfb,
+				      unsigned long action, void *hcpu)
+{
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_ONLINE:
+	case CPU_DOWN_FAILED:
+		set_cpu_active((long)hcpu, true);
+		return NOTIFY_OK;
+	default:
+		return NOTIFY_DONE;
+	}
+}
+
+static int __cpuinit sched_cpu_inactive(struct notifier_block *nfb,
+					unsigned long action, void *hcpu)
+{
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_DOWN_PREPARE:
+		set_cpu_active((long)hcpu, false);
+		return NOTIFY_OK;
+	default:
+		return NOTIFY_DONE;
+	}
+}
+
 static int __init migration_init(void)
 {
 	void *cpu = (void *)(long)smp_processor_id();
 	int err;
 
-	/* Start one for the boot CPU: */
+	/* Initialize migration for the boot CPU */
 	err = migration_call(&migration_notifier, CPU_UP_PREPARE, cpu);
 	BUG_ON(err == NOTIFY_BAD);
 	migration_call(&migration_notifier, CPU_ONLINE, cpu);
 	register_cpu_notifier(&migration_notifier);
 
+	/* Register cpu active notifiers */
+	cpu_notifier(sched_cpu_active, CPU_PRI_SCHED_ACTIVE);
+	cpu_notifier(sched_cpu_inactive, CPU_PRI_SCHED_INACTIVE);
+
 	return 0;
 }
 early_initcall(migration_init);
@@ -7273,29 +7302,35 @@ int __init sched_create_sysfs_power_savings_entries(struct sysdev_class *cls)
 }
 #endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
 
-#ifndef CONFIG_CPUSETS
 /*
- * Add online and remove offline CPUs from the scheduler domains.
- * When cpusets are enabled they take over this function.
+ * Update cpusets according to cpu_active mask.  If cpusets are
+ * disabled, cpuset_update_active_cpus() becomes a simple wrapper
+ * around partition_sched_domains().
  */
-static int update_sched_domains(struct notifier_block *nfb,
-				unsigned long action, void *hcpu)
+static int __cpuexit cpuset_cpu_active(struct notifier_block *nfb,
+				       unsigned long action, void *hcpu)
 {
-	switch (action) {
+	switch (action & ~CPU_TASKS_FROZEN) {
 	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
 	case CPU_DOWN_FAILED:
-	case CPU_DOWN_FAILED_FROZEN:
-		partition_sched_domains(1, NULL, NULL);
+		cpuset_update_active_cpus();
 		return NOTIFY_OK;
+	default:
+		return NOTIFY_DONE;
+	}
+}
 
+static int __cpuexit cpuset_cpu_inactive(struct notifier_block *nfb,
+					 unsigned long action, void *hcpu)
+{
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_DOWN_PREPARE:
+		cpuset_update_active_cpus();
+		return NOTIFY_OK;
 	default:
 		return NOTIFY_DONE;
 	}
 }
-#endif
 
 static int update_runtime(struct notifier_block *nfb,
 				unsigned long action, void *hcpu)
@@ -7341,10 +7376,8 @@ void __init sched_init_smp(void)
 	mutex_unlock(&sched_domains_mutex);
 	put_online_cpus();
 
-#ifndef CONFIG_CPUSETS
-	/* XXX: Theoretical race here - CPU may be hotplugged now */
-	hotcpu_notifier(update_sched_domains, 0);
-#endif
+	hotcpu_notifier(cpuset_cpu_active, CPU_PRI_CPUSET_ACTIVE);
+	hotcpu_notifier(cpuset_cpu_inactive, CPU_PRI_CPUSET_INACTIVE);
 
 	/* RT runtime code needs to handle some hotplug events */
 	hotcpu_notifier(update_runtime, 0);