linux-pm.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
To: rjw@rjwysocki.net, len.brown@intel.com, viresh.kumar@linaro.org
Cc: linux-pm@vger.kernel.org,
	Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Subject: [PATCH 4/4] cpufreq: intel_pstate: Add powersave policy support
Date: Fri,  4 Dec 2015 16:08:38 -0800	[thread overview]
Message-ID: <1449274118-15575-5-git-send-email-srinivas.pandruvada@linux.intel.com> (raw)
In-Reply-To: <1449274118-15575-1-git-send-email-srinivas.pandruvada@linux.intel.com>

Implement support for powersave policy. The powersave policy will limit
the max performance to P-State = Maximum Efficiency Ratio.

Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
---
 drivers/cpufreq/intel_pstate.c | 49 ++++++++++++++++++++++++++++++++++--------
 1 file changed, 40 insertions(+), 9 deletions(-)

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 61b7118..417d020 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -189,8 +189,23 @@ static struct perf_limits ondemand_limits = {
 	.min_sysfs_pct = 0,
 };
 
-#ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE
+static struct perf_limits powersave_limits = {
+	.no_turbo = 1,
+	.turbo_disabled = 1,
+	.max_perf_pct = 0,
+	.max_perf = int_tofp(1),
+	.min_perf_pct = 0,
+	.min_perf = int_tofp(1),
+	.max_policy_pct = 0,
+	.max_sysfs_pct = 0,
+	.min_policy_pct = 0,
+	.min_sysfs_pct = 0,
+};
+
+#if defined(CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE)
 static struct perf_limits *limits = &performance_limits;
+#elif defined(CONFIG_CPU_FREQ_DEFAULT_GOV_POWERSAVE)
+static struct perf_limits *limits = &powersave_limits;
 #else
 static struct perf_limits *limits = &ondemand_limits;
 #endif
@@ -1143,13 +1158,26 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 		return 0;
 	}
 
-	pr_debug("intel_pstate: set ondemand\n");
-	limits = &ondemand_limits;
-	limits->min_policy_pct = (policy->min * 100) / policy->cpuinfo.max_freq;
-	limits->min_policy_pct = clamp_t(int, limits->min_policy_pct, 0 , 100);
-	limits->max_policy_pct = DIV_ROUND_UP(policy->max * 100,
-					      policy->cpuinfo.max_freq);
-	limits->max_policy_pct = clamp_t(int, limits->max_policy_pct, 0 , 100);
+	if (policy->policy == CPUFREQ_POLICY_POWERSAVE) {
+		pr_debug("intel_pstate: set powersave\n");
+		limits = &powersave_limits;
+		limits->min_policy_pct = (policy->cpuinfo.min_freq * 100) /
+					  policy->cpuinfo.max_freq;
+		limits->min_policy_pct = clamp_t(int, limits->min_policy_pct,
+						 0, 100);
+		limits->max_policy_pct = limits->min_policy_pct;
+	} else {
+		pr_debug("intel_pstate: set ondemand\n");
+		limits = &ondemand_limits;
+		limits->min_policy_pct = (policy->min * 100) /
+					  policy->cpuinfo.max_freq;
+		limits->min_policy_pct = clamp_t(int, limits->min_policy_pct,
+						 0, 100);
+		limits->max_policy_pct = DIV_ROUND_UP(policy->max * 100,
+						policy->cpuinfo.max_freq);
+		limits->max_policy_pct = clamp_t(int, limits->max_policy_pct,
+						 0, 100);
+	}
 
 	/* Normalize user input to [min_policy_pct, max_policy_pct] */
 	limits->min_perf_pct = max(limits->min_policy_pct,
@@ -1181,7 +1209,8 @@ static int intel_pstate_verify_policy(struct cpufreq_policy *policy)
 	cpufreq_verify_within_cpu_limits(policy);
 
 	if (policy->policy != CPUFREQ_POLICY_ONDEMAND &&
-	    policy->policy != CPUFREQ_POLICY_PERFORMANCE)
+	    policy->policy != CPUFREQ_POLICY_PERFORMANCE &&
+	    policy->policy != CPUFREQ_POLICY_POWERSAVE)
 		return -EINVAL;
 
 	return 0;
@@ -1234,6 +1263,8 @@ static int intel_pstate_available_policies(u8 *mask)
 {
 
 	*mask = CPUFREQ_POLICY_PERFORMANCE | CPUFREQ_POLICY_ONDEMAND;
+	if (!hwp_active)
+		*mask |= CPUFREQ_POLICY_POWERSAVE;
 
 	return 0;
 }
-- 
2.4.3


  parent reply	other threads:[~2015-12-05  0:09 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-12-05  0:08 [PATCH 0/4] cpufreq governors and Intel P state driver compatibility Srinivas Pandruvada
2015-12-05  0:08 ` [PATCH 1/4] cpufreq: Add configurable generic policies Srinivas Pandruvada
2015-12-07  9:33   ` Viresh Kumar
2015-12-07 15:03     ` Srinivas Pandruvada
2015-12-05  0:08 ` [PATCH 2/4] cpufreq: Add ondemand as a generic policy Srinivas Pandruvada
2015-12-07  9:34   ` Viresh Kumar
2015-12-05  0:08 ` [PATCH 3/4] cpufreq: intel_pstate: Change powersave to ondemand policy Srinivas Pandruvada
2015-12-05  0:08 ` Srinivas Pandruvada [this message]
2015-12-08 14:35 ` [PATCH 0/4] cpufreq governors and Intel P state driver compatibility Thomas Renninger
2015-12-08 17:43   ` Srinivas Pandruvada
2015-12-09 15:02     ` Thomas Renninger
2015-12-09 16:12       ` Srinivas Pandruvada

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=1449274118-15575-5-git-send-email-srinivas.pandruvada@linux.intel.com \
    --to=srinivas.pandruvada@linux.intel.com \
    --cc=len.brown@intel.com \
    --cc=linux-pm@vger.kernel.org \
    --cc=rjw@rjwysocki.net \
    --cc=viresh.kumar@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 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).