From 50a323b73069b169385a8ac65633dee837a7d13f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 8 Jun 2010 21:40:36 +0200 Subject: sched: define and use CPU_PRI_* enums for cpu notifier priorities Instead of hardcoding priority 10 and 20 in sched and perf, collect them into CPU_PRI_* enums. Signed-off-by: Tejun Heo Acked-by: Peter Zijlstra Cc: Rusty Russell Cc: Paul Mackerras Cc: Ingo Molnar Cc: Arnaldo Carvalho de Melo --- include/linux/cpu.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux/cpu.h') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index e287863ac053..2d9073883ea9 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -48,6 +48,15 @@ extern ssize_t arch_cpu_release(const char *, size_t); #endif struct notifier_block; +/* + * CPU notifier priorities. + */ +enum { + /* migration should happen before other stuff but after perf */ + CPU_PRI_PERF = 20, + CPU_PRI_MIGRATION = 10, +}; + #ifdef CONFIG_SMP /* Need to know about CPUs going up/down? */ #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE) -- cgit v1.2.3 From 3a101d0548e925ab16ca6aaa8cf4f767d322ddb0 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 8 Jun 2010 21:40:36 +0200 Subject: 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 Acked-by: Peter Zijlstra Cc: Rusty Russell Cc: Ingo Molnar Cc: Paul Menage --- include/linux/cpu.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux/cpu.h') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 2d9073883ea9..de6b1722cdca 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -52,6 +52,22 @@ struct notifier_block; * CPU notifier priorities. */ enum { + /* + * SCHED_ACTIVE marks a cpu which is coming up active during + * CPU_ONLINE and CPU_DOWN_FAILED and must be the first + * notifier. CPUSET_ACTIVE adjusts cpuset according to + * cpu_active mask right after SCHED_ACTIVE. During + * CPU_DOWN_PREPARE, SCHED_INACTIVE and CPUSET_INACTIVE are + * ordered in the similar way. + * + * This ordering guarantees consistent cpu_active mask and + * migration behavior to all cpu notifiers. + */ + CPU_PRI_SCHED_ACTIVE = INT_MAX, + CPU_PRI_CPUSET_ACTIVE = INT_MAX - 1, + CPU_PRI_SCHED_INACTIVE = INT_MIN + 1, + CPU_PRI_CPUSET_INACTIVE = INT_MIN, + /* migration should happen before other stuff but after perf */ CPU_PRI_PERF = 20, CPU_PRI_MIGRATION = 10, -- cgit v1.2.3 From db7bccf45cb87522096b8f43144e31ca605a9f24 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 29 Jun 2010 10:07:12 +0200 Subject: workqueue: reimplement CPU hotplugging support using trustee Reimplement CPU hotplugging support using trustee thread. On CPU down, a trustee thread is created and each step of CPU down is executed by the trustee and workqueue_cpu_callback() simply drives and waits for trustee state transitions. CPU down operation no longer waits for works to be drained but trustee sticks around till all pending works have been completed. If CPU is brought back up while works are still draining, workqueue_cpu_callback() tells trustee to step down and tell workers to rebind to the cpu. As it's difficult to tell whether cwqs are empty if it's freezing or frozen, trustee doesn't consider draining to be complete while a gcwq is freezing or frozen (tracked by new GCWQ_FREEZING flag). Also, workers which get unbound from their cpu are marked with WORKER_ROGUE. Trustee based implementation doesn't bring any new feature at this point but it will be used to manage worker pool when dynamic shared worker pool is implemented. Signed-off-by: Tejun Heo --- include/linux/cpu.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/cpu.h') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index de6b1722cdca..4823af64e9db 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -71,6 +71,8 @@ enum { /* migration should happen before other stuff but after perf */ CPU_PRI_PERF = 20, CPU_PRI_MIGRATION = 10, + /* prepare workqueues for other notifiers */ + CPU_PRI_WORKQUEUE = 5, }; #ifdef CONFIG_SMP -- cgit v1.2.3