[v2] cpufreq: intel_pstate: fix inconsistency in setting policy limits

Commit Message

srinivas pandruvada April 4, 2016, 2:42 a.m. UTC

When user sets performance policy using cpufreq interface, it is possible
that because of policy->max limits, the actual performance is still
limited. But the current implementation will silently switch the
policy to powersave and start using powersave limits. If user modifies
any limits using intel_pstate sysfs, this is actually changing powersave
limits.

The current implementation tracks limits under powersave and performance
policy using two different variables. When policy->max is less than
policy->cpuinfo.max_freq, only powersave limit variable is used.

This fix involves uses performance limits variable always when policy
is performance.

Signed-off-by: Srinivas Pandruvada <[e-mail]>
---
v2:
Rebased on top of 
https://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm.git
branch: linux-next


 drivers/cpufreq/intel_pstate.c | 29 +++++++++++++++++++++++------
 1 file changed, 23 insertions(+), 6 deletions(-)

Comments

Rafael J. Wysocki April 6, 2016, 11:35 p.m. UTC | #1

On Sunday, April 03, 2016 07:42:11 PM Srinivas Pandruvada wrote:
> When user sets performance policy using cpufreq interface, it is possible
> that because of policy->max limits, the actual performance is still
> limited. But the current implementation will silently switch the
> policy to powersave and start using powersave limits. If user modifies
> any limits using intel_pstate sysfs, this is actually changing powersave
> limits.
> 
> The current implementation tracks limits under powersave and performance
> policy using two different variables. When policy->max is less than
> policy->cpuinfo.max_freq, only powersave limit variable is used.
> 
> This fix involves uses performance limits variable always when policy
> is performance.
> 
> Signed-off-by: Srinivas Pandruvada <[e-mail]>

Applied, thanks!

--
To unsubscribe from this list: send the line "unsubscribe linux-pm" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Patch

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index a382195..4674804 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -1140,6 +1140,20 @@  static void intel_pstate_clear_update_util_hook(unsigned int cpu)
 	synchronize_sched();
 }
 
+static void intel_pstate_set_performance_limits(struct perf_limits *limits)
+{
+	limits->no_turbo = 0;
+	limits->turbo_disabled = 0;
+	limits->max_perf_pct = 100;
+	limits->max_perf = int_tofp(1);
+	limits->min_perf_pct = 100;
+	limits->min_perf = int_tofp(1);
+	limits->max_policy_pct = 100;
+	limits->max_sysfs_pct = 100;
+	limits->min_policy_pct = 0;
+	limits->min_sysfs_pct = 0;
+}
+
 static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 {
 	if (!policy->cpuinfo.max_freq)
@@ -1147,15 +1161,18 @@  static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 
 	intel_pstate_clear_update_util_hook(policy->cpu);
 
-	if (policy->policy == CPUFREQ_POLICY_PERFORMANCE &&
-	    policy->max >= policy->cpuinfo.max_freq) {
-		pr_debug("intel_pstate: set performance\n");
+	if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) {
 		limits = &performance_limits;
-		goto out;
+		if (policy->max >= policy->cpuinfo.max_freq) {
+			pr_debug("intel_pstate: set performance\n");
+			intel_pstate_set_performance_limits(limits);
+			goto out;
+		}
+	} else {
+		pr_debug("intel_pstate: set powersave\n");
+		limits = &powersave_limits;
 	}
 
-	pr_debug("intel_pstate: set powersave\n");
-	limits = &powersave_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,