From: Srinivas Pandruvada Date: Tue, 25 Oct 2016 20:20:41 +0000 (-0700) Subject: cpufreq: intel_pstate: Reduce impact due to rounding error X-Git-Url: https://git.karo-electronics.de/?a=commitdiff_plain;h=5879f877398a2a5e5006c6e16a4288e9d4c308a1;p=linux-beck.git cpufreq: intel_pstate: Reduce impact due to rounding error When policy->max and policy->min are same, in some cases they don't result in the same frequency cap. The max_policy_pct is rounded up but not min_perf_pct. So even when they are same, results in different percentage or maximum and minimum. Since minimum is a conservative value for power, a lower value without rounding is better in most of the cases, unless user wants policy->max = policy->min. This change uses use the same policy percentage when policy->max and policy->min are same. Signed-off-by: Srinivas Pandruvada Signed-off-by: Rafael J. Wysocki --- diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index b6e9b49bf151..8e7390bb2175 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -1543,11 +1543,17 @@ static void intel_pstate_set_performance_limits(struct perf_limits *limits) static void intel_pstate_update_perf_limits(struct cpufreq_policy *policy, struct perf_limits *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->max == policy->min) { + limits->min_policy_pct = limits->max_policy_pct; + } else { + limits->min_policy_pct = (policy->min * 100) / + policy->cpuinfo.max_freq; + limits->min_policy_pct = clamp_t(int, limits->min_policy_pct, + 0, 100); + } /* Normalize user input to [min_policy_pct, max_policy_pct] */ limits->min_perf_pct = max(limits->min_policy_pct,