[PATCH 23/70] cpufreq: interactive: pin timers to associated CPU

[BÃlint Czobor]

From: Todd Poynor <toddpoynor@xxxxxxxxxx>

Helps avoid waking up other CPUs to react to activity on the local CPU.

Change-Id: Ife272aaa7916894a437705d44521b1a1693fbe8e
Signed-off-by: Todd Poynor <toddpoynor@xxxxxxxxxx>
Signed-off-by: BÃlint Czobor <czoborbalint@xxxxxxxxx>
---
 drivers/cpufreq/cpufreq_interactive.c |  106 +++++++++------------------------
 1 file changed, 27 insertions(+), 79 deletions(-)

diff --git a/drivers/cpufreq/cpufreq_interactive.c b/drivers/cpufreq/cpufreq_interactive.c
index 16bd23b..e53eae2 100644
--- a/drivers/cpufreq/cpufreq_interactive.c
+++ b/drivers/cpufreq/cpufreq_interactive.c
@@ -42,8 +42,6 @@ struct cpufreq_interactive_cpuinfo {
 	int timer_idlecancel;
 	u64 time_in_idle;
 	u64 idle_exit_time;
-	u64 timer_run_time;
-	int idling;
 	u64 target_set_time;
 	u64 target_set_time_in_idle;
 	struct cpufreq_policy *policy;
@@ -109,6 +107,7 @@ struct cpufreq_governor cpufreq_gov_interactive = {
 
 static void cpufreq_interactive_timer(unsigned long data)
 {
+	u64 now;
 	unsigned int delta_idle;
 	unsigned int delta_time;
 	int cpu_load;
@@ -127,26 +126,11 @@ static void cpufreq_interactive_timer(unsigned long data)
 	if (!pcpu->governor_enabled)
 		goto exit;
 
-	/*
-	 * Once pcpu->timer_run_time is updated to >= pcpu->idle_exit_time,
-	 * this lets idle exit know the current idle time sample has
-	 * been processed, and idle exit can generate a new sample and
-	 * re-arm the timer.  This prevents a concurrent idle
-	 * exit on that CPU from writing a new set of info at the same time
-	 * the timer function runs (the timer function can't use that info
-	 * until more time passes).
-	 */
 	time_in_idle = pcpu->time_in_idle;
 	idle_exit_time = pcpu->idle_exit_time;
-	now_idle = get_cpu_idle_time_us(data, &pcpu->timer_run_time);
-	smp_wmb();
-
-	/* If we raced with cancelling a timer, skip. */
-	if (!idle_exit_time)
-		goto exit;
-
+	now_idle = get_cpu_idle_time_us(data, &now);
 	delta_idle = (unsigned int)(now_idle - time_in_idle);
-	delta_time = (unsigned int)(pcpu->timer_run_time - idle_exit_time);
+	delta_time = (unsigned int)(now - idle_exit_time);
 
 	/*
 	 * If timer ran less than 1ms after short-term sample started, retry.
@@ -160,8 +144,7 @@ static void cpufreq_interactive_timer(unsigned long data)
 		cpu_load = 100 * (delta_time - delta_idle) / delta_time;
 
 	delta_idle = (unsigned int)(now_idle - pcpu->target_set_time_in_idle);
-	delta_time = (unsigned int)(pcpu->timer_run_time -
-				    pcpu->target_set_time);
+	delta_time = (unsigned int)(now - pcpu->target_set_time);
 
 	if ((delta_time == 0) || (delta_idle > delta_time))
 		load_since_change = 0;
@@ -189,7 +172,7 @@ static void cpufreq_interactive_timer(unsigned long data)
 
 			if (pcpu->target_freq == hispeed_freq &&
 			    new_freq > hispeed_freq &&
-			    pcpu->timer_run_time - pcpu->hispeed_validate_time
+			    now - pcpu->hispeed_validate_time
 			    < above_hispeed_delay_val) {
 				trace_cpufreq_interactive_notyet(data, cpu_load,
 								 pcpu->target_freq,
@@ -202,7 +185,7 @@ static void cpufreq_interactive_timer(unsigned long data)
 	}
 
 	if (new_freq <= hispeed_freq)
-		pcpu->hispeed_validate_time = pcpu->timer_run_time;
+		pcpu->hispeed_validate_time = now;
 
 	if (cpufreq_frequency_table_target(pcpu->policy, pcpu->freq_table,
 					   new_freq, CPUFREQ_RELATION_H,
@@ -219,8 +202,7 @@ static void cpufreq_interactive_timer(unsigned long data)
 	 * floor frequency for the minimum sample time since last validated.
 	 */
 	if (new_freq < pcpu->floor_freq) {
-		if (pcpu->timer_run_time - pcpu->floor_validate_time
-		    < min_sample_time) {
+		if (now - pcpu->floor_validate_time < min_sample_time) {
 			trace_cpufreq_interactive_notyet(data, cpu_load,
 					 pcpu->target_freq, new_freq);
 			goto rearm;
@@ -228,7 +210,7 @@ static void cpufreq_interactive_timer(unsigned long data)
 	}
 
 	pcpu->floor_freq = new_freq;
-	pcpu->floor_validate_time = pcpu->timer_run_time;
+	pcpu->floor_validate_time = now;
 
 	if (pcpu->target_freq == new_freq) {
 		trace_cpufreq_interactive_already(data, cpu_load,
@@ -239,7 +221,7 @@ static void cpufreq_interactive_timer(unsigned long data)
 	trace_cpufreq_interactive_target(data, cpu_load, pcpu->target_freq,
 					 new_freq);
 	pcpu->target_set_time_in_idle = now_idle;
-	pcpu->target_set_time = pcpu->timer_run_time;
+	pcpu->target_set_time = now;
 
 	pcpu->target_freq = new_freq;
 	spin_lock_irqsave(&speedchange_cpumask_lock, flags);
@@ -258,23 +240,16 @@ rearm_if_notmax:
 rearm:
 	if (!timer_pending(&pcpu->cpu_timer)) {
 		/*
-		 * If already at min: if that CPU is idle, don't set timer.
-		 * Else cancel the timer if that CPU goes idle.  We don't
-		 * need to re-evaluate speed until the next idle exit.
+		 * If already at min, cancel the timer if that CPU goes idle.
+		 * We don't need to re-evaluate speed until the next idle exit.
 		 */
-		if (pcpu->target_freq == pcpu->policy->min) {
-			smp_rmb();
-
-			if (pcpu->idling)
-				goto exit;
-
+		if (pcpu->target_freq == pcpu->policy->min)
 			pcpu->timer_idlecancel = 1;
-		}
 
 		pcpu->time_in_idle = get_cpu_idle_time_us(
 			data, &pcpu->idle_exit_time);
-		mod_timer(&pcpu->cpu_timer,
-			  jiffies + usecs_to_jiffies(timer_rate));
+		mod_timer_pinned(&pcpu->cpu_timer,
+				 jiffies + usecs_to_jiffies(timer_rate));
 	}
 
 exit:
@@ -290,8 +265,6 @@ static void cpufreq_interactive_idle_start(void)
 	if (!pcpu->governor_enabled)
 		return;
 
-	pcpu->idling = 1;
-	smp_wmb();
 	pending = timer_pending(&pcpu->cpu_timer);
 
 	if (pcpu->target_freq != pcpu->policy->min) {
@@ -308,8 +281,9 @@ static void cpufreq_interactive_idle_start(void)
 			pcpu->time_in_idle = get_cpu_idle_time_us(
 				smp_processor_id(), &pcpu->idle_exit_time);
 			pcpu->timer_idlecancel = 0;
-			mod_timer(&pcpu->cpu_timer,
-				  jiffies + usecs_to_jiffies(timer_rate));
+			mod_timer_pinned(
+				&pcpu->cpu_timer,
+				jiffies + usecs_to_jiffies(timer_rate));
 		}
 #endif
 	} else {
@@ -321,12 +295,6 @@ static void cpufreq_interactive_idle_start(void)
 		 */
 		if (pending && pcpu->timer_idlecancel) {
 			del_timer(&pcpu->cpu_timer);
-			/*
-			 * Ensure last timer run time is after current idle
-			 * sample start time, so next idle exit will always
-			 * start a new idle sampling period.
-			 */
-			pcpu->idle_exit_time = 0;
 			pcpu->timer_idlecancel = 0;
 		}
 	}
@@ -341,29 +309,15 @@ static void cpufreq_interactive_idle_end(void)
 	if (!pcpu->governor_enabled)
 		return;
 
-	pcpu->idling = 0;
-	smp_wmb();
-
-	/*
-	 * Arm the timer for 1-2 ticks later if not already, and if the timer
-	 * function has already processed the previous load sampling
-	 * interval.  (If the timer is not pending but has not processed
-	 * the previous interval, it is probably racing with us on another
-	 * CPU.  Let it compute load based on the previous sample and then
-	 * re-arm the timer for another interval when it's done, rather
-	 * than updating the interval start time to be "now", which doesn't
-	 * give the timer function enough time to make a decision on this
-	 * run.)
-	 */
-	if (timer_pending(&pcpu->cpu_timer) == 0 &&
-	    pcpu->timer_run_time >= pcpu->idle_exit_time &&
-	    pcpu->governor_enabled) {
+	/* Arm the timer for 1-2 ticks later if not already. */
+	if (!timer_pending(&pcpu->cpu_timer)) {
 		pcpu->time_in_idle =
 			get_cpu_idle_time_us(smp_processor_id(),
 					     &pcpu->idle_exit_time);
 		pcpu->timer_idlecancel = 0;
-		mod_timer(&pcpu->cpu_timer,
-			  jiffies + usecs_to_jiffies(timer_rate));
+		mod_timer_pinned(
+			&pcpu->cpu_timer,
+			jiffies + usecs_to_jiffies(timer_rate));
 	}
 
 }
@@ -673,6 +627,8 @@ static int cpufreq_governor_interactive(struct cpufreq_policy *policy,
 
 		freq_table =
 			cpufreq_frequency_get_table(policy->cpu);
+		if (!hispeed_freq)
+			hispeed_freq = policy->max;
 
 		for_each_cpu(j, policy->cpus) {
 			pcpu = &per_cpu(cpuinfo, j);
@@ -689,11 +645,11 @@ static int cpufreq_governor_interactive(struct cpufreq_policy *policy,
 				pcpu->target_set_time;
 			pcpu->governor_enabled = 1;
 			smp_wmb();
+			pcpu->cpu_timer.expires =
+				jiffies + usecs_to_jiffies(timer_rate);
+			add_timer_on(&pcpu->cpu_timer, j);
 		}
 
-		if (!hispeed_freq)
-			hispeed_freq = policy->max;
-
 		/*
 		 * Do not register the idle hook and create sysfs
 		 * entries if we have already done so.
@@ -715,14 +671,6 @@ static int cpufreq_governor_interactive(struct cpufreq_policy *policy,
 			pcpu->governor_enabled = 0;
 			smp_wmb();
 			del_timer_sync(&pcpu->cpu_timer);
-
-			/*
-			 * Reset idle exit time since we may cancel the timer
-			 * before it can run after the last idle exit time,
-			 * to avoid tripping the check in idle exit for a timer
-			 * that is trying to run.
-			 */
-			pcpu->idle_exit_time = 0;
 		}
 
 		if (atomic_dec_return(&active_count) > 0)
-- 
1.7.9.5

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/