tools/power turbostat: simplify Bzy_MHz calculation

    Bzy_MHz = TSC_delta*tsc_tweak/APERF_delta/MPERF_delta/measurement_interval

becomes

    Bzy_MHz = base_mhz/APERF_delta/MPERF_delta

on systems which support MSR_NHM_PLATFORM_INFO.

base_mhz is calculated directly from the base_ratio
reported in MSR_NHM_PLATFORM_INFO * bclk,
and bclk is discovered via MSR or cpuid.

This reduces the dependency of Bzy_MHz calculation on the TSC.
Previously, there were 4 TSC readings required in each caculation,
the raw TSC delta combined with the measurement_interval.
This also removes the "tsc_tweak" correction factor used when
TSC runs on a different base clock from the CPU's bclk.

After this change, tsc_tweak is used only for %Busy.

The end-result should be a Bzy_MHz result slightly less prone to jitter.

Signed-off-by: Len Brown <len.brown@intel.com>

diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index bde0ef1a63df4876d5149c85f4083eb92561dbb4..84ec4e4599758357121263dcbc1cd0cf16b970b6 100644 (file)
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -75,6 +75,7 @@ unsigned int aperf_mperf_multiplier = 1;
 int do_smi;
 double bclk;
 double base_hz;
+unsigned int has_base_hz;
 double tsc_tweak = 1.0;
 unsigned int show_pkg;
 unsigned int show_core;
@@ -96,6 +97,7 @@ unsigned int do_ring_perf_limit_reasons;
 unsigned int crystal_hz;
 unsigned long long tsc_hz;
 int base_cpu;
+double discover_bclk(unsigned int family, unsigned int model);
 
 #define RAPL_PKG               (1 << 0)
                                        /* 0x610 MSR_PKG_POWER_LIMIT */
@@ -511,9 +513,13 @@ int format_counters(struct thread_data *t, struct core_data *c,
        }
 
        /* Bzy_MHz */
-       if (has_aperf)
-               outp += sprintf(outp, "%8.0f",
-                       1.0 * t->tsc * tsc_tweak / units * t->aperf / t->mperf / interval_float);
+       if (has_aperf) {
+               if (has_base_hz)
+                       outp += sprintf(outp, "%8.0f", base_hz / units * t->aperf / t->mperf);
+               else
+                       outp += sprintf(outp, "%8.0f",
+                               1.0 * t->tsc / units * t->aperf / t->mperf / interval_float);
+       }
 
        /* TSC_MHz */
        outp += sprintf(outp, "%8.0f", 1.0 * t->tsc/units/interval_float);
@@ -1158,12 +1164,6 @@ int phi_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV,
 static void
 calculate_tsc_tweak()
 {
-       unsigned long long msr;
-       unsigned int base_ratio;
-
-       get_msr(base_cpu, MSR_NHM_PLATFORM_INFO, &msr);
-       base_ratio = (msr >> 8) & 0xFF;
-       base_hz = base_ratio * bclk * 1000000;
        tsc_tweak = base_hz / tsc_hz;
 }
 
@@ -1821,6 +1821,7 @@ void check_permissions()
 int probe_nhm_msrs(unsigned int family, unsigned int model)
 {
        unsigned long long msr;
+       unsigned int base_ratio;
        int *pkg_cstate_limits;
 
        if (!genuine_intel)
@@ -1829,6 +1830,8 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
        if (family != 6)
                return 0;
 
+       bclk = discover_bclk(family, model);
+
        switch (model) {
        case 0x1A:      /* Core i7, Xeon 5500 series - Bloomfield, Gainstown NHM-EP */
        case 0x1E:      /* Core i7 and i5 Processor - Clarksfield, Lynnfield, Jasper Forest */
@@ -1871,9 +1874,13 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
                return 0;
        }
        get_msr(base_cpu, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr);
-
        pkg_cstate_limit = pkg_cstate_limits[msr & 0xF];
 
+       get_msr(base_cpu, MSR_NHM_PLATFORM_INFO, &msr);
+       base_ratio = (msr >> 8) & 0xFF;
+
+       base_hz = base_ratio * bclk * 1000000;
+       has_base_hz = 1;
        return 1;
 }
 int has_nhm_turbo_ratio_limit(unsigned int family, unsigned int model)
@@ -2780,7 +2787,6 @@ void process_cpuid()
        do_skl_residency = has_skl_msrs(family, model);
        do_slm_cstates = is_slm(family, model);
        do_knl_cstates  = is_knl(family, model);
-       bclk = discover_bclk(family, model);
 
        rapl_probe(family, model);
        perf_limit_reasons_probe(family, model);