cpufreq: schedutil: Don't skip freq update when limits change

commit 600f5badb78c316146d062cfd7af4a2cfb655baa upstream.

To avoid reducing the frequency of a CPU prematurely, we skip reducing
the frequency if the CPU had been busy recently.

This should not be done when the limits of the policy are changed, for
example due to thermal throttling. We should always get the frequency
within the new limits as soon as possible.

Trying to fix this by using only one flag, i.e. need_freq_update, can
lead to a race condition where the flag gets cleared without forcing us
to change the frequency at least once. And so this patch introduces
another flag to avoid that race condition.

Fixes: ecd28842 ("cpufreq: schedutil: Don't set next_freq to UINT_MAX")
Cc: v4.18+ <stable@vger.kernel.org> # v4.18+
Reported-by: NDoug Smythies <dsmythies@telus.net>
Tested-by: NDoug Smythies <dsmythies@telus.net>
Signed-off-by: NViresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

kernel/sched/cpufreq_schedutil.c

@@ -40,6 +40,7 @@ struct sugov_policy {
 	struct task_struct	*thread;
 	bool			work_in_progress;
 
+	bool			limits_changed;
 	bool			need_freq_update;
 };
 
@@ -90,8 +91,11 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
 	    !cpufreq_this_cpu_can_update(sg_policy->policy))
 		return false;
 
-	if (unlikely(sg_policy->need_freq_update))
+	if (unlikely(sg_policy->limits_changed)) {
+		sg_policy->limits_changed = false;
+		sg_policy->need_freq_update = true;
 		return true;
+	}
 
 	delta_ns = time - sg_policy->last_freq_update_time;
 
@@ -405,7 +409,7 @@ static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; }
 static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu, struct sugov_policy *sg_policy)
 {
 	if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_dl)
-		sg_policy->need_freq_update = true;
+		sg_policy->limits_changed = true;
 }
 
 static void sugov_update_single(struct update_util_data *hook, u64 time,
@@ -425,7 +429,8 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
 	if (!sugov_should_update_freq(sg_policy, time))
 		return;
 
-	busy = sugov_cpu_is_busy(sg_cpu);
+	/* Limits may have changed, don't skip frequency update */
+	busy = !sg_policy->need_freq_update && sugov_cpu_is_busy(sg_cpu);
 
 	util = sugov_get_util(sg_cpu);
 	max = sg_cpu->max;
@@ -798,6 +803,7 @@ static int sugov_start(struct cpufreq_policy *policy)
 	sg_policy->last_freq_update_time	= 0;
 	sg_policy->next_freq			= 0;
 	sg_policy->work_in_progress		= false;
+	sg_policy->limits_changed		= false;
 	sg_policy->need_freq_update		= false;
 	sg_policy->cached_raw_freq		= 0;
 
@@ -849,7 +855,7 @@ static void sugov_limits(struct cpufreq_policy *policy)
 		mutex_unlock(&sg_policy->work_lock);
 	}
 
-	sg_policy->need_freq_update = true;
+	sg_policy->limits_changed = true;
 }
 
 static struct cpufreq_governor schedutil_gov = {