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/cpuset.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux/cpuset.h') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 457ed765a116..f20eb8f16025 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -20,6 +20,7 @@ extern int number_of_cpusets; /* How many cpusets are defined in system? */ extern int cpuset_init(void); extern void cpuset_init_smp(void); +extern void cpuset_update_active_cpus(void); extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask); extern int cpuset_cpus_allowed_fallback(struct task_struct *p); extern nodemask_t cpuset_mems_allowed(struct task_struct *p); @@ -132,6 +133,11 @@ static inline void set_mems_allowed(nodemask_t nodemask) static inline int cpuset_init(void) { return 0; } static inline void cpuset_init_smp(void) {} +static inline void cpuset_update_active_cpus(void) +{ + partition_sched_domains(1, NULL, NULL); +} + static inline void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask) { -- cgit