linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Rafael J. Wysocki" <rjw@rjwysocki.net>
To: Peter Zijlstra <peterz@infradead.org>,
	Linux PM <linux-pm@vger.kernel.org>,
	Frederic Weisbecker <fweisbec@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>,
	Paul McKenney <paulmck@linux.vnet.ibm.com>,
	Thomas Ilsche <thomas.ilsche@tu-dresden.de>,
	Doug Smythies <dsmythies@telus.net>,
	Rik van Riel <riel@surriel.com>,
	Aubrey Li <aubrey.li@linux.intel.com>,
	Mike Galbraith <mgalbraith@suse.de>,
	LKML <linux-kernel@vger.kernel.org>
Subject: [RFC/RFT][PATCH v3 6/6] cpuidle: menu: Refine idle state selection for running tick
Date: Fri, 09 Mar 2018 10:49:11 +0100	[thread overview]
Message-ID: <2427176.MrJbnUnnmj@aspire.rjw.lan> (raw)
In-Reply-To: <2450532.XN8DODrtDf@aspire.rjw.lan>

From: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

If the tick isn't stopped, the target residency of the state selected
by the menu governor may be greater than the actual time to the next
tick and that means lost energy.

To avoid that, make tick_nohz_get_sleep_length() return the current
time the the next event (before stopping the tick) in addition to
the estimated one via an extra pointer argument and make
menu_select() use that value to refine the state selection
when necessary.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpuidle/governors/menu.c |   21 ++++++++++++++++++---
 include/linux/tick.h             |    2 +-
 kernel/time/tick-sched.c         |    7 +++++--
 3 files changed, 24 insertions(+), 6 deletions(-)

Index: linux-pm/include/linux/tick.h
===================================================================
--- linux-pm.orig/include/linux/tick.h
+++ linux-pm/include/linux/tick.h
@@ -119,7 +119,7 @@ extern void tick_nohz_idle_retain_tick(v
 extern void tick_nohz_idle_enter(void);
 extern void tick_nohz_idle_exit(void);
 extern void tick_nohz_irq_exit(void);
-extern ktime_t tick_nohz_get_sleep_length(void);
+extern ktime_t tick_nohz_get_sleep_length(ktime_t *cur_ret);
 extern unsigned long tick_nohz_get_idle_calls(void);
 extern unsigned long tick_nohz_get_idle_calls_cpu(int cpu);
 extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time);
Index: linux-pm/kernel/time/tick-sched.c
===================================================================
--- linux-pm.orig/kernel/time/tick-sched.c
+++ linux-pm/kernel/time/tick-sched.c
@@ -1024,10 +1024,11 @@ void tick_nohz_irq_exit(void)
 
 /**
  * tick_nohz_get_sleep_length - return the expected length of the current sleep
+ * @cur_ret: pointer for returning the current time to the next event
  *
  * Called from power state control code with interrupts disabled
  */
-ktime_t tick_nohz_get_sleep_length(void)
+ktime_t tick_nohz_get_sleep_length(ktime_t *cur_ret)
 {
 	struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
 	struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
@@ -1038,6 +1039,8 @@ ktime_t tick_nohz_get_sleep_length(void)
 	 */
 	ktime_t now = ts->idle_entrytime;
 
+	*cur_ret = ktime_sub(dev->next_event, now);
+
 	if (can_stop_idle_tick(cpu, ts)) {
 		ktime_t next_event = __tick_nohz_next_event(ts, cpu);
 
@@ -1045,7 +1048,7 @@ ktime_t tick_nohz_get_sleep_length(void)
 			return ktime_sub(next_event, now);
 	}
 
-	return ktime_sub(dev->next_event, now);
+	return *cur_ret;
 }
 
 /**
Index: linux-pm/drivers/cpuidle/governors/menu.c
===================================================================
--- linux-pm.orig/drivers/cpuidle/governors/menu.c
+++ linux-pm/drivers/cpuidle/governors/menu.c
@@ -296,6 +296,7 @@ static int menu_select(struct cpuidle_dr
 	unsigned int expected_interval;
 	unsigned long nr_iowaiters, cpu_load;
 	int resume_latency = dev_pm_qos_raw_read_value(device);
+	ktime_t tick_time;
 
 	if (data->needs_update) {
 		menu_update(drv, dev);
@@ -313,7 +314,7 @@ static int menu_select(struct cpuidle_dr
 	}
 
 	/* determine the expected residency time, round up */
-	data->next_timer_us = ktime_to_us(tick_nohz_get_sleep_length());
+	data->next_timer_us = ktime_to_us(tick_nohz_get_sleep_length(&tick_time));
 
 	get_iowait_load(&nr_iowaiters, &cpu_load);
 	data->bucket = which_bucket(data->next_timer_us, nr_iowaiters);
@@ -400,8 +401,22 @@ static int menu_select(struct cpuidle_dr
 		 * within the tick period range that could be used if longer
 		 * idle duration was predicted.
 		 */
-		*nohz_ret = !(first_idx > idx &&
-			      drv->states[first_idx].target_residency < TICK_USEC_HZ);
+		if (first_idx > idx &&
+		    drv->states[first_idx].target_residency < TICK_USEC_HZ) {
+			unsigned int tick_us = ktime_to_us(tick_time);
+
+			/*
+			 * Find a state with target residency less than the
+			 * time to the next timer event including the tick.
+			 */
+			while (idx > 0 &&
+			    (drv->states[idx].target_residency > tick_us ||
+			     drv->states[idx].disabled ||
+			     dev->states_usage[idx].disable))
+				idx--;
+
+			*nohz_ret = false;
+		}
 	}
 
 	data->last_state_idx = idx;

  parent reply	other threads:[~2018-03-09  9:48 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-03-09  9:34 [RFC/RFT][PATCH v3 0/6] sched/cpuidle: Idle loop rework Rafael J. Wysocki
2018-03-09  9:36 ` [RFC/RFT][PATCH v3 1/6] time: tick-sched: Reorganize idle tick management code Rafael J. Wysocki
2018-03-09  9:38 ` [RFC/RFT][PATCH v3 2/6] sched: idle: Do not stop the tick upfront in the idle loop Rafael J. Wysocki
2018-03-09  9:39 ` [RFC/RFT][PATCH v3 3/6] sched: idle: Do not stop the tick before cpuidle_idle_call() Rafael J. Wysocki
2018-03-09  9:41 ` [RFC/RFT][PATCH v3 4/6] cpuidle: Return nohz hint from cpuidle_select() Rafael J. Wysocki
2018-03-09  9:46 ` [RFC/RFT][PATCH v3 5/6] sched: idle: Select idle state before stopping the tick Rafael J. Wysocki
2018-03-11  1:44   ` Frederic Weisbecker
2018-03-11 10:31     ` Rafael J. Wysocki
2018-03-09  9:49 ` Rafael J. Wysocki [this message]
2018-03-09 15:19 ` [RFC/RFT][PATCH v3 0/6] sched/cpuidle: Idle loop rework Rik van Riel
2018-03-10  5:01 ` Mike Galbraith
2018-03-10  9:09   ` Rafael J. Wysocki
2018-03-10  7:41 ` Doug Smythies
2018-03-10  9:00   ` Rafael J. Wysocki
2018-03-10 16:07   ` Doug Smythies
2018-03-10 23:55     ` Rafael J. Wysocki
2018-03-11  7:43     ` Doug Smythies
2018-03-11 10:21       ` Rafael J. Wysocki
2018-03-11 10:34         ` Rafael J. Wysocki
2018-03-11 15:52       ` Doug Smythies
2018-03-11 23:02       ` Doug Smythies
2018-03-12  9:28         ` Rafael J. Wysocki

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=2427176.MrJbnUnnmj@aspire.rjw.lan \
    --to=rjw@rjwysocki.net \
    --cc=aubrey.li@linux.intel.com \
    --cc=dsmythies@telus.net \
    --cc=fweisbec@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pm@vger.kernel.org \
    --cc=mgalbraith@suse.de \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=peterz@infradead.org \
    --cc=riel@surriel.com \
    --cc=tglx@linutronix.de \
    --cc=thomas.ilsche@tu-dresden.de \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).