schedutil: Allow cpufreq requests to be made even when kthread kicked

Currently there is a chance of a schedutil cpufreq update request to be
dropped if there is a pending update request. This pending request can
be delayed if there is a scheduling delay of the irq_work and the wake
up of the schedutil governor kthread.

A very bad scenario is when a schedutil request was already just made,
such as to reduce the CPU frequency, then a newer request to increase
CPU frequency (even sched deadline urgent frequency increase requests)
can be dropped, even though the rate limits suggest that its Ok to
process a request. This is because of the way the work_in_progress flag
is used.

This patch improves the situation by allowing new requests to happen
even though the old one is still being processed. Note that in this
approach, if an irq_work was already issued, we just update next_freq
and don't bother to queue another request so there's no extra work being
done to make this happen.

Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Acked-by: Juri Lelli <juri.lelli@redhat.com>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index caf435c14a52c2222209e4161701ffda644607b3..178946e3639348260fa6b42ddbc47fd384327f1c 100644 (file)
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -92,9 +92,6 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
            !cpufreq_this_cpu_can_update(sg_policy->policy))
                return false;
 
-       if (sg_policy->work_in_progress)
-               return false;
-
        if (unlikely(sg_policy->need_freq_update))
                return true;
 
@@ -121,7 +118,7 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time,
 
                policy->cur = next_freq;
                trace_cpu_frequency(next_freq, smp_processor_id());
-       } else {
+       } else if (!sg_policy->work_in_progress) {
                sg_policy->work_in_progress = true;
                irq_work_queue(&sg_policy->irq_work);
        }
@@ -366,6 +363,13 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
 
        ignore_dl_rate_limit(sg_cpu, sg_policy);
 
+       /*
+        * For slow-switch systems, single policy requests can't run at the
+        * moment if update is in progress, unless we acquire update_lock.
+        */
+       if (sg_policy->work_in_progress)
+               return;
+
        if (!sugov_should_update_freq(sg_policy, time))
                return;
 
@@ -440,13 +444,27 @@ sugov_update_shared(struct update_util_data *hook, u64 time, unsigned int flags)
 static void sugov_work(struct kthread_work *work)
 {
        struct sugov_policy *sg_policy = container_of(work, struct sugov_policy, work);
+       unsigned int freq;
+       unsigned long flags;
+
+       /*
+        * Hold sg_policy->update_lock shortly to handle the case where:
+        * incase sg_policy->next_freq is read here, and then updated by
+        * sugov_update_shared just before work_in_progress is set to false
+        * here, we may miss queueing the new update.
+        *
+        * Note: If a work was queued after the update_lock is released,
+        * sugov_work will just be called again by kthread_work code; and the
+        * request will be proceed before the sugov thread sleeps.
+        */
+       raw_spin_lock_irqsave(&sg_policy->update_lock, flags);
+       freq = sg_policy->next_freq;
+       sg_policy->work_in_progress = false;
+       raw_spin_unlock_irqrestore(&sg_policy->update_lock, flags);
 
        mutex_lock(&sg_policy->work_lock);
-       __cpufreq_driver_target(sg_policy->policy, sg_policy->next_freq,
-                               CPUFREQ_RELATION_L);
+       __cpufreq_driver_target(sg_policy->policy, freq, CPUFREQ_RELATION_L);
        mutex_unlock(&sg_policy->work_lock);
-
-       sg_policy->work_in_progress = false;
 }
 
 static void sugov_irq_work(struct irq_work *irq_work)