All of lore.kernel.org
 help / color / mirror / Atom feed
From: Lina Iyer <lina.iyer@linaro.org>
To: ulf.hansson@linaro.org, khilman@kernel.org, rjw@rjwysocki.net,
	linux-pm@vger.kernel.org, linux-arm-kernel@lists.infradead.org
Cc: geert@linux-m68k.org, k.kozlowski@samsung.com,
	msivasub@codeaurora.org, agross@codeaurora.org,
	sboyd@codeaurora.org, linux-arm-msm@vger.kernel.org,
	lorenzo.pieralisi@arm.com, ahaslam@baylibre.com,
	mtitinger@baylibre.com, Lina Iyer <lina.iyer@linaro.org>
Subject: [RFC v2 07/12] PM / cpu_domains: Add PM Domain governor for CPUs
Date: Fri, 12 Feb 2016 13:50:33 -0700	[thread overview]
Message-ID: <1455310238-8963-8-git-send-email-lina.iyer@linaro.org> (raw)
In-Reply-To: <1455310238-8963-1-git-send-email-lina.iyer@linaro.org>

A PM domain comprising of CPUs may be powered off when all the CPUs in
the domain are powered down. Powering down a CPU domain is generally a
expensive operation and therefore the power performance trade offs
should be considered. The time between the last CPU powering down and
the first CPU powering up in a domain, is the time available for the
domain to sleep. Ideally, the sleep time of the domain should fulfill
the residency requirement of the domains' idle state.

To do this effectively, read the time before the wakeup of the cluster's
CPUs and ensure that the domain's idle state sleep time guarantees the
QoS requirements of each of the CPU, the PM QoS CPU_DMA_LATENCY and the
state's residency.

Signed-off-by: Lina Iyer <lina.iyer@linaro.org>
---
Changes since RFC v1 -
- bug fix

 drivers/base/power/cpu_domains.c | 75 +++++++++++++++++++++++++++++++++++++++-
 1 file changed, 74 insertions(+), 1 deletion(-)

diff --git a/drivers/base/power/cpu_domains.c b/drivers/base/power/cpu_domains.c
index c99710c..7069411 100644
--- a/drivers/base/power/cpu_domains.c
+++ b/drivers/base/power/cpu_domains.c
@@ -17,9 +17,12 @@
 #include <linux/list.h>
 #include <linux/of.h>
 #include <linux/pm_domain.h>
+#include <linux/pm_qos.h>
+#include <linux/pm_runtime.h>
 #include <linux/rculist.h>
 #include <linux/rcupdate.h>
 #include <linux/slab.h>
+#include <linux/tick.h>
 
 #define CPU_PD_NAME_MAX 36
 
@@ -52,6 +55,76 @@ struct cpu_pm_domain *to_cpu_pd(struct generic_pm_domain *d)
 	return res;
 }
 
+static bool cpu_pd_down_ok(struct dev_pm_domain *pd)
+{
+	struct generic_pm_domain *genpd = pd_to_genpd(pd);
+	struct cpu_pm_domain *cpu_pd = to_cpu_pd(genpd);
+	int qos = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
+	u64 sleep_ns;
+	ktime_t earliest, next_wakeup;
+	int cpu;
+	int i;
+
+	/* Reset the last set genpd state, default to index 0 */
+	genpd->state_idx = 0;
+
+	/* We dont want to power down, if QoS is 0 */
+	if (!qos)
+		return false;
+
+	/*
+	 * Find the sleep time for the cluster.
+	 * The time between now and the first wake up of any CPU that
+	 * are in this domain hierarchy is the time available for the
+	 * domain to be idle.
+	 */
+	earliest = ktime_set(KTIME_SEC_MAX, 0);
+	for_each_cpu_and(cpu, cpu_pd->cpus, cpu_online_mask) {
+		next_wakeup = tick_nohz_get_next_wakeup(cpu);
+		if (earliest.tv64 > next_wakeup.tv64)
+			earliest = next_wakeup;
+	}
+
+	sleep_ns = ktime_to_ns(ktime_sub(earliest, ktime_get()));
+	if (sleep_ns <= 0)
+		return false;
+
+	/*
+	 * Find the deepest sleep state that satisfies the residency
+	 * requirement and the QoS constraint
+	 */
+	for (i = genpd->state_count - 1; i >= 0; i--) {
+		u64 state_sleep_ns;
+
+		state_sleep_ns = genpd->states[i].power_off_latency_ns +
+			genpd->states[i].power_on_latency_ns +
+			genpd->states[i].residency_ns;
+
+		/*
+		 * If we cant sleep to save power in the state, move on
+		 * to the next lower idle state.
+		 */
+		if (state_sleep_ns > sleep_ns)
+			continue;
+
+		/*
+		 * We also dont want to sleep more than we should to
+		 * gaurantee QoS.
+		 */
+		if (state_sleep_ns < (qos * NSEC_PER_USEC))
+			break;
+	}
+
+	if (i >= 0)
+		genpd->state_idx = i;
+
+	return  (i >= 0) ? true : false;
+}
+
+static struct dev_power_governor cpu_pd_gov = {
+	.power_down_ok = cpu_pd_down_ok,
+};
+
 static int cpu_pd_attach_cpu(struct cpu_pm_domain *cpu_pd, int cpu)
 {
 	int ret;
@@ -143,7 +216,7 @@ static struct generic_pm_domain *of_init_cpu_pm_domain(struct device_node *dn,
 
 	/* Register the CPU genpd */
 	pr_debug("adding %s as CPU PM domain.\n", pd->genpd->name);
-	ret = of_pm_genpd_init(dn, pd->genpd, &simple_qos_governor, false);
+	ret = of_pm_genpd_init(dn, pd->genpd, &cpu_pd_gov, false);
 	if (ret) {
 		pr_err("Unable to initialize domain %s\n", dn->full_name);
 		goto fail;
-- 
2.1.4


WARNING: multiple messages have this Message-ID (diff)
From: lina.iyer@linaro.org (Lina Iyer)
To: linux-arm-kernel@lists.infradead.org
Subject: [RFC v2 07/12] PM / cpu_domains: Add PM Domain governor for CPUs
Date: Fri, 12 Feb 2016 13:50:33 -0700	[thread overview]
Message-ID: <1455310238-8963-8-git-send-email-lina.iyer@linaro.org> (raw)
In-Reply-To: <1455310238-8963-1-git-send-email-lina.iyer@linaro.org>

A PM domain comprising of CPUs may be powered off when all the CPUs in
the domain are powered down. Powering down a CPU domain is generally a
expensive operation and therefore the power performance trade offs
should be considered. The time between the last CPU powering down and
the first CPU powering up in a domain, is the time available for the
domain to sleep. Ideally, the sleep time of the domain should fulfill
the residency requirement of the domains' idle state.

To do this effectively, read the time before the wakeup of the cluster's
CPUs and ensure that the domain's idle state sleep time guarantees the
QoS requirements of each of the CPU, the PM QoS CPU_DMA_LATENCY and the
state's residency.

Signed-off-by: Lina Iyer <lina.iyer@linaro.org>
---
Changes since RFC v1 -
- bug fix

 drivers/base/power/cpu_domains.c | 75 +++++++++++++++++++++++++++++++++++++++-
 1 file changed, 74 insertions(+), 1 deletion(-)

diff --git a/drivers/base/power/cpu_domains.c b/drivers/base/power/cpu_domains.c
index c99710c..7069411 100644
--- a/drivers/base/power/cpu_domains.c
+++ b/drivers/base/power/cpu_domains.c
@@ -17,9 +17,12 @@
 #include <linux/list.h>
 #include <linux/of.h>
 #include <linux/pm_domain.h>
+#include <linux/pm_qos.h>
+#include <linux/pm_runtime.h>
 #include <linux/rculist.h>
 #include <linux/rcupdate.h>
 #include <linux/slab.h>
+#include <linux/tick.h>
 
 #define CPU_PD_NAME_MAX 36
 
@@ -52,6 +55,76 @@ struct cpu_pm_domain *to_cpu_pd(struct generic_pm_domain *d)
 	return res;
 }
 
+static bool cpu_pd_down_ok(struct dev_pm_domain *pd)
+{
+	struct generic_pm_domain *genpd = pd_to_genpd(pd);
+	struct cpu_pm_domain *cpu_pd = to_cpu_pd(genpd);
+	int qos = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
+	u64 sleep_ns;
+	ktime_t earliest, next_wakeup;
+	int cpu;
+	int i;
+
+	/* Reset the last set genpd state, default to index 0 */
+	genpd->state_idx = 0;
+
+	/* We dont want to power down, if QoS is 0 */
+	if (!qos)
+		return false;
+
+	/*
+	 * Find the sleep time for the cluster.
+	 * The time between now and the first wake up of any CPU that
+	 * are in this domain hierarchy is the time available for the
+	 * domain to be idle.
+	 */
+	earliest = ktime_set(KTIME_SEC_MAX, 0);
+	for_each_cpu_and(cpu, cpu_pd->cpus, cpu_online_mask) {
+		next_wakeup = tick_nohz_get_next_wakeup(cpu);
+		if (earliest.tv64 > next_wakeup.tv64)
+			earliest = next_wakeup;
+	}
+
+	sleep_ns = ktime_to_ns(ktime_sub(earliest, ktime_get()));
+	if (sleep_ns <= 0)
+		return false;
+
+	/*
+	 * Find the deepest sleep state that satisfies the residency
+	 * requirement and the QoS constraint
+	 */
+	for (i = genpd->state_count - 1; i >= 0; i--) {
+		u64 state_sleep_ns;
+
+		state_sleep_ns = genpd->states[i].power_off_latency_ns +
+			genpd->states[i].power_on_latency_ns +
+			genpd->states[i].residency_ns;
+
+		/*
+		 * If we cant sleep to save power in the state, move on
+		 * to the next lower idle state.
+		 */
+		if (state_sleep_ns > sleep_ns)
+			continue;
+
+		/*
+		 * We also dont want to sleep more than we should to
+		 * gaurantee QoS.
+		 */
+		if (state_sleep_ns < (qos * NSEC_PER_USEC))
+			break;
+	}
+
+	if (i >= 0)
+		genpd->state_idx = i;
+
+	return  (i >= 0) ? true : false;
+}
+
+static struct dev_power_governor cpu_pd_gov = {
+	.power_down_ok = cpu_pd_down_ok,
+};
+
 static int cpu_pd_attach_cpu(struct cpu_pm_domain *cpu_pd, int cpu)
 {
 	int ret;
@@ -143,7 +216,7 @@ static struct generic_pm_domain *of_init_cpu_pm_domain(struct device_node *dn,
 
 	/* Register the CPU genpd */
 	pr_debug("adding %s as CPU PM domain.\n", pd->genpd->name);
-	ret = of_pm_genpd_init(dn, pd->genpd, &simple_qos_governor, false);
+	ret = of_pm_genpd_init(dn, pd->genpd, &cpu_pd_gov, false);
 	if (ret) {
 		pr_err("Unable to initialize domain %s\n", dn->full_name);
 		goto fail;
-- 
2.1.4

  parent reply	other threads:[~2016-02-12 20:50 UTC|newest]

Thread overview: 68+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-02-12 20:50 [RFC v2 00/12] PM: SoC idle support using PM domains Lina Iyer
2016-02-12 20:50 ` Lina Iyer
2016-02-12 20:50 ` [RFC v2 01/12] PM / Domains: Abstract genpd locking Lina Iyer
2016-02-12 20:50   ` Lina Iyer
2016-02-26 18:08   ` Stephen Boyd
2016-02-26 18:08     ` Stephen Boyd
2016-03-01 16:55     ` Lina Iyer
2016-03-01 16:55       ` Lina Iyer
2016-02-12 20:50 ` [RFC v2 02/12] PM / Domains: Support IRQ safe PM domains Lina Iyer
2016-02-12 20:50   ` Lina Iyer
2016-02-26 18:17   ` Stephen Boyd
2016-02-26 18:17     ` Stephen Boyd
2016-03-01 17:44     ` Lina Iyer
2016-03-01 17:44       ` Lina Iyer
2016-02-12 20:50 ` [RFC v2 03/12] PM / cpu_domains: Setup PM domains for CPUs/clusters Lina Iyer
2016-02-12 20:50   ` Lina Iyer
2016-02-17 23:38   ` Lina Iyer
2016-02-17 23:38     ` Lina Iyer
2016-02-18 17:29   ` [BUG FIX] PM / cpu_domains: Check for NULL callbacks Lina Iyer
2016-02-18 17:29     ` Lina Iyer
2016-02-18 17:46     ` Rafael J. Wysocki
2016-02-18 17:46       ` Rafael J. Wysocki
2016-02-18 22:51       ` Lina Iyer
2016-02-18 22:51         ` Lina Iyer
2016-02-26 19:10   ` [RFC v2 03/12] PM / cpu_domains: Setup PM domains for CPUs/clusters Stephen Boyd
2016-02-26 19:10     ` Stephen Boyd
2016-03-01 18:00     ` Lina Iyer
2016-03-01 18:00       ` Lina Iyer
2016-02-12 20:50 ` [RFC v2 04/12] ARM: cpuidle: Add runtime PM support for CPUs Lina Iyer
2016-02-12 20:50   ` Lina Iyer
2016-02-26 18:24   ` Stephen Boyd
2016-02-26 18:24     ` Stephen Boyd
2016-03-01 18:36     ` Lina Iyer
2016-03-01 18:36       ` Lina Iyer
2016-02-12 20:50 ` [RFC v2 05/12] timer: Export next wake up of a CPU Lina Iyer
2016-02-12 20:50   ` Lina Iyer
2016-02-12 20:50 ` [RFC v2 06/12] PM / cpu_domains: Record CPUs that are part of the domain Lina Iyer
2016-02-12 20:50   ` Lina Iyer
2016-02-26 19:20   ` Stephen Boyd
2016-02-26 19:20     ` Stephen Boyd
2016-03-01 19:24     ` Lina Iyer
2016-03-01 19:24       ` Lina Iyer
2016-02-12 20:50 ` Lina Iyer [this message]
2016-02-12 20:50   ` [RFC v2 07/12] PM / cpu_domains: Add PM Domain governor for CPUs Lina Iyer
2016-02-26 19:33   ` Stephen Boyd
2016-02-26 19:33     ` Stephen Boyd
2016-03-01 19:32     ` Lina Iyer
2016-03-01 19:32       ` Lina Iyer
2016-03-01 19:35       ` Stephen Boyd
2016-03-01 19:35         ` Stephen Boyd
2016-02-12 20:50 ` [RFC v2 08/12] Documentation / cpu_domains: Describe CPU PM domains setup and governor Lina Iyer
2016-02-12 20:50   ` Lina Iyer
2016-02-26 19:43   ` Stephen Boyd
2016-02-26 19:43     ` Stephen Boyd
2016-03-01 19:36     ` Lina Iyer
2016-03-01 19:36       ` Lina Iyer
2016-02-12 20:50 ` [RFC v2 09/12] drivers: firmware: psci: Allow OS Initiated suspend mode Lina Iyer
2016-02-12 20:50   ` Lina Iyer
2016-02-12 20:50 ` [RFC v2 10/12] ARM64: psci: Support cluster idle states for OS-Initiated Lina Iyer
2016-02-12 20:50   ` Lina Iyer
2016-02-12 20:50 ` [RFC v2 11/12] ARM64: dts: Add PSCI cpuidle support for MSM8916 Lina Iyer
2016-02-12 20:50   ` Lina Iyer
2016-02-12 20:50 ` [RFC v2 12/12] ARM64: dts: Define CPU power domain " Lina Iyer
2016-02-12 20:50   ` Lina Iyer
2016-02-26 19:50   ` Stephen Boyd
2016-02-26 19:50     ` Stephen Boyd
2016-03-01 19:41     ` Lina Iyer
2016-03-01 19:41       ` Lina Iyer

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=1455310238-8963-8-git-send-email-lina.iyer@linaro.org \
    --to=lina.iyer@linaro.org \
    --cc=agross@codeaurora.org \
    --cc=ahaslam@baylibre.com \
    --cc=geert@linux-m68k.org \
    --cc=k.kozlowski@samsung.com \
    --cc=khilman@kernel.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-arm-msm@vger.kernel.org \
    --cc=linux-pm@vger.kernel.org \
    --cc=lorenzo.pieralisi@arm.com \
    --cc=msivasub@codeaurora.org \
    --cc=mtitinger@baylibre.com \
    --cc=rjw@rjwysocki.net \
    --cc=sboyd@codeaurora.org \
    --cc=ulf.hansson@linaro.org \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.