cpufreq: intel_pstate: fix inconsistency in setting policy limits

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 causes the performance limits variable to be used always when
the policy is performance.

Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 9ae159631f52af00eb84160f38159bf38d1d182a..c6c169a1b2fc742a29d4774ff4bb5dac86ff9fcb 100644 (file)
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -1141,6 +1141,20 @@ 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)
@@ -1148,15 +1162,18 @@ 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,