linux-kernel - [RFC][PATCH v5 14/14] cpuidle: set the current wake up latency

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <1382097147-30088-14-git-send-email-vincent.guittot@linaro.org>
Date:	Fri, 18 Oct 2013 13:52:27 +0200
From:	Vincent Guittot <vincent.guittot@...aro.org>
To:	linux-kernel@...r.kernel.org, peterz@...radead.org,
	mingo@...nel.org, pjt@...gle.com, Morten.Rasmussen@....com,
	cmetcalf@...era.com, tony.luck@...el.com, alex.shi@...el.com,
	preeti@...ux.vnet.ibm.com, linaro-kernel@...ts.linaro.org
Cc:	rjw@...k.pl, paulmck@...ux.vnet.ibm.com, corbet@....net,
	tglx@...utronix.de, len.brown@...el.com, arjan@...ux.intel.com,
	amit.kucheria@...aro.org, l.majewski@...sung.com,
	Vincent Guittot <vincent.guittot@...aro.org>
Subject: [RFC][PATCH v5 14/14] cpuidle: set the current wake up latency

Save the current wake up latency of a core. This latency is not always
the latency of a defined c-state but can also be an intermediate value
when a core is ready to shutdown (timer migration, cache flush ...) but
wait for the last core of the cluster to finalize the cluster power down.
This latter use case is not manage by the current version of the patch because
it implies that the cpuidle drivers set the wake up latency instead of the
cpuidle core.

Signed-off-by: Vincent Guittot <vincent.guittot@...aro.org>

Conflicts:

	drivers/cpuidle/cpuidle.c
---
 drivers/cpuidle/cpuidle.c |   11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index d75040d..7b6553b 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -19,6 +19,7 @@
 #include <linux/ktime.h>
 #include <linux/hrtimer.h>
 #include <linux/module.h>
+#include <linux/sched.h>
 #include <trace/events/power.h>
 
 #include "cpuidle.h"
@@ -42,6 +43,12 @@ void disable_cpuidle(void)
 	off = 1;
 }
 
+static void cpuidle_set_current_state(int cpu, int latency)
+{
+	struct sched_pm *stat = &per_cpu(sched_stat, cpu);
+
+	atomic_set(&(stat->wake_latency), latency);
+}
 /**
  * cpuidle_play_dead - cpu off-lining
  *
@@ -79,12 +86,16 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 	ktime_t time_start, time_end;
 	s64 diff;
 
+	cpuidle_set_current_state(dev->cpu, target_state->exit_latency);
+
 	time_start = ktime_get();
 
 	entered_state = target_state->enter(dev, drv, index);
 
 	time_end = ktime_get();
 
+	cpuidle_set_current_state(dev->cpu, 0);
+
 	local_irq_enable();
 
 	diff = ktime_to_us(ktime_sub(time_end, time_start));
-- 
1.7.9.5

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