diff options
| author | Viresh Kumar | 2017-08-10 09:50:55 +0530 |
|---|---|---|
| committer | Rafael J. Wysocki | 2017-08-18 01:35:18 +0200 |
| commit | e2cabe48c20efb174ce0c01190f8b9c5f3ea1d13 (patch) | |
| tree | 00782649545658d4f962eb26207ddaa5cd274abe /kernel/sched | |
| parent | 209887e6b974c22328487b55d0f390522b014b03 (diff) | |
cpufreq: schedutil: Don't restrict kthread to related_cpus unnecessarily
Utilization update callbacks are now processed remotely, even on the
CPUs that don't share cpufreq policy with the target CPU (if
dvfs_possible_from_any_cpu flag is set).
But in non-fast switch paths, the frequency is changed only from one of
policy->related_cpus. This happens because the kthread which does the
actual update is bound to a subset of CPUs (i.e. related_cpus).
Allow frequency to be remotely updated as well (i.e. call
__cpufreq_driver_target()) if dvfs_possible_from_any_cpu flag is set.
Reported-by: Pavan Kondeti <pkondeti@codeaurora.org>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Diffstat (limited to 'kernel/sched')
| -rw-r--r-- | kernel/sched/cpufreq_schedutil.c | 6 |
1 files changed, 5 insertions, 1 deletions
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 2ba04bb3182a..69571ee6a175 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -487,7 +487,11 @@ static int sugov_kthread_create(struct sugov_policy *sg_policy) } sg_policy->thread = thread; - kthread_bind_mask(thread, policy->related_cpus); + + /* Kthread is bound to all CPUs by default */ + if (!policy->dvfs_possible_from_any_cpu) + kthread_bind_mask(thread, policy->related_cpus); + init_irq_work(&sg_policy->irq_work, sugov_irq_work); mutex_init(&sg_policy->work_lock); |