summaryrefslogtreecommitdiffstats
path: root/kernel/cpuset.c
diff options
context:
space:
mode:
authorTejun Heo <tj@kernel.org>2010-06-08 21:40:36 +0200
committerTejun Heo <tj@kernel.org>2010-06-08 21:40:36 +0200
commit3a101d0548e925ab16ca6aaa8cf4f767d322ddb0 (patch)
treeb90d8c5f2efe30fcfa49a00fdea037567c6cd46f /kernel/cpuset.c
parent50a323b73069b169385a8ac65633dee837a7d13f (diff)
downloadtalos-obmc-linux-3a101d0548e925ab16ca6aaa8cf4f767d322ddb0.tar.gz
talos-obmc-linux-3a101d0548e925ab16ca6aaa8cf4f767d322ddb0.zip
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>
Diffstat (limited to 'kernel/cpuset.c')
-rw-r--r--kernel/cpuset.c21
1 files changed, 2 insertions, 19 deletions
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 02b9611eadde..05727dcaa80d 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");
OpenPOWER on IntegriCloud