@@ -52,6 +52,8 @@
#define EXT_BITS 6
#define EXT_FRAC_BITS (EXT_BITS + FRAC_BITS)
+#define fp_ext_toint(X) ((X) >> EXT_FRAC_BITS)
+#define int_ext_tofp(X) ((int64_t)(X) << EXT_FRAC_BITS)
static inline int32_t mul_fp(int32_t x, int32_t y)
{
@@ -345,9 +347,9 @@ static struct perf_limits performance_limits = {
.no_turbo = 0,
.turbo_disabled = 0,
.max_perf_pct = 100,
- .max_perf = int_tofp(1),
+ .max_perf = int_ext_tofp(1),
.min_perf_pct = 100,
- .min_perf = int_tofp(1),
+ .min_perf = int_ext_tofp(1),
.max_policy_pct = 100,
.max_sysfs_pct = 100,
.min_policy_pct = 0,
@@ -358,7 +360,7 @@ static struct perf_limits powersave_limits = {
.no_turbo = 0,
.turbo_disabled = 0,
.max_perf_pct = 100,
- .max_perf = int_tofp(1),
+ .max_perf = int_ext_tofp(1),
.min_perf_pct = 0,
.min_perf = 0,
.max_policy_pct = 100,
@@ -770,7 +772,7 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b,
limits->max_perf_pct);
limits->max_perf_pct = max(limits->min_perf_pct,
limits->max_perf_pct);
- limits->max_perf = div_fp(limits->max_perf_pct, 100);
+ limits->max_perf = div_ext_fp(limits->max_perf_pct, 100);
mutex_unlock(&intel_pstate_limits_lock);
@@ -798,7 +800,7 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b,
limits->min_perf_pct);
limits->min_perf_pct = min(limits->max_perf_pct,
limits->min_perf_pct);
- limits->min_perf = div_fp(limits->min_perf_pct, 100);
+ limits->min_perf = div_ext_fp(limits->min_perf_pct, 100);
mutex_unlock(&intel_pstate_limits_lock);
@@ -1183,11 +1185,11 @@ static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max)
* policy, or by cpu specific default values determined through
* experimentation.
*/
- max_perf_adj = fp_toint(max_perf * perf_limits->max_perf);
+ max_perf_adj = fp_ext_toint(max_perf * perf_limits->max_perf);
*max = clamp_t(int, max_perf_adj,
cpu->pstate.min_pstate, cpu->pstate.turbo_pstate);
- min_perf = fp_toint(max_perf * perf_limits->min_perf);
+ min_perf = fp_ext_toint(max_perf * perf_limits->min_perf);
*min = clamp_t(int, min_perf, cpu->pstate.min_pstate, max_perf);
}
@@ -1547,9 +1549,9 @@ 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->max_perf = int_ext_tofp(1);
limits->min_perf_pct = 100;
- limits->min_perf = int_tofp(1);
+ limits->min_perf = int_ext_tofp(1);
limits->max_policy_pct = 100;
limits->max_sysfs_pct = 100;
limits->min_policy_pct = 0;
@@ -1588,10 +1590,10 @@ static void intel_pstate_update_perf_limits(struct cpufreq_policy *policy,
/* Make sure min_perf_pct <= max_perf_pct */
limits->min_perf_pct = min(limits->max_perf_pct, limits->min_perf_pct);
- limits->min_perf = div_fp(limits->min_perf_pct, 100);
- limits->max_perf = div_fp(limits->max_perf_pct, 100);
- limits->max_perf = round_up(limits->max_perf, FRAC_BITS);
- limits->min_perf = round_up(limits->min_perf, FRAC_BITS);
+ limits->min_perf = div_ext_fp(limits->min_perf_pct, 100);
+ limits->max_perf = div_ext_fp(limits->max_perf_pct, 100);
+ limits->max_perf = round_up(limits->max_perf, EXT_FRAC_BITS);
+ limits->min_perf = round_up(limits->min_perf, EXT_FRAC_BITS);
mutex_unlock(&intel_pstate_limits_lock);
Even with round up of limits->min_perf and limits->max_perf, in some cases resultant performance is 100 MHz less than the desired. For example when the maximum frequency is 3.50 GHz, setting scaling_min_frequency to 2.3 GHz always results in 2.2 GHz minimum. Currently the fixed floating point operation uses 8 bit precision for calculating limits->min_perf and limits->max_perf. For some operations in this driver the 14 bit precision is used. Using the 14 bit precision also for calculating limits->min_perf and limits->max_perf, addresses this issue. Introduced fp_ext_toint() equivalent to fp_toint() and int_ext_tofp() equivalent to int_tofp() with 14 bit precision. Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> --- drivers/cpufreq/intel_pstate.c | 28 +++++++++++++++------------- 1 file changed, 15 insertions(+), 13 deletions(-)