[PATCH 10/16] perf intel-pt: Add support for recording the max non-turbo ratio

From: Adrian Hunter
Date: Fri Sep 23 2016 - 10:45:17 EST


Previously the maximum non-turbo ratio was calculated from TSC assuming a
100 MHz multiplier which is correct for current hardware supporting
Intel PT. However more recent kernels also now export the value, so use
that in preference to the calculated value.

Signed-off-by: Adrian Hunter <adrian.hunter@xxxxxxxxx>
---
tools/perf/arch/x86/util/intel-pt.c | 6 ++++++
tools/perf/util/intel-pt.c | 14 +++++++++++++-
tools/perf/util/intel-pt.h | 1 +
3 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index a2412e9d883b..18b21514c153 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -302,6 +302,7 @@ static int intel_pt_info_fill(struct auxtrace_record *itr,
bool cap_user_time_zero = false, per_cpu_mmaps;
u64 tsc_bit, mtc_bit, mtc_freq_bits, cyc_bit, noretcomp_bit;
u32 tsc_ctc_ratio_n, tsc_ctc_ratio_d;
+ unsigned long max_non_turbo_ratio;
int err;

if (priv_size != INTEL_PT_AUXTRACE_PRIV_SIZE)
@@ -317,6 +318,10 @@ static int intel_pt_info_fill(struct auxtrace_record *itr,

intel_pt_tsc_ctc_ratio(&tsc_ctc_ratio_n, &tsc_ctc_ratio_d);

+ if (perf_pmu__scan_file(intel_pt_pmu, "max_nonturbo_ratio",
+ "%lu", &max_non_turbo_ratio) != 1)
+ max_non_turbo_ratio = 0;
+
if (!session->evlist->nr_mmaps)
return -EINVAL;

@@ -351,6 +356,7 @@ static int intel_pt_info_fill(struct auxtrace_record *itr,
auxtrace_info->priv[INTEL_PT_TSC_CTC_N] = tsc_ctc_ratio_n;
auxtrace_info->priv[INTEL_PT_TSC_CTC_D] = tsc_ctc_ratio_d;
auxtrace_info->priv[INTEL_PT_CYC_BIT] = cyc_bit;
+ auxtrace_info->priv[INTEL_PT_MAX_NONTURBO_RATIO] = max_non_turbo_ratio;

return 0;
}
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index b744ea812a2e..77fbf02c8e41 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -2023,6 +2023,7 @@ static const char * const intel_pt_info_fmts[] = {
[INTEL_PT_TSC_CTC_N] = " TSC:CTC numerator %"PRIu64"\n",
[INTEL_PT_TSC_CTC_D] = " TSC:CTC denominator %"PRIu64"\n",
[INTEL_PT_CYC_BIT] = " CYC bit %#"PRIx64"\n",
+ [INTEL_PT_MAX_NONTURBO_RATIO] = " Max non-turbo ratio %"PRIu64"\n",
};

static void intel_pt_print_info(u64 *arr, int start, int finish)
@@ -2087,6 +2088,15 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
INTEL_PT_CYC_BIT);
}

+ if (auxtrace_info->header.size >= sizeof(struct auxtrace_info_event) +
+ (sizeof(u64) * INTEL_PT_MAX_NONTURBO_RATIO)) {
+ pt->max_non_turbo_ratio =
+ auxtrace_info->priv[INTEL_PT_MAX_NONTURBO_RATIO];
+ intel_pt_print_info(&auxtrace_info->priv[0],
+ INTEL_PT_MAX_NONTURBO_RATIO,
+ INTEL_PT_MAX_NONTURBO_RATIO);
+ }
+
pt->timeless_decoding = intel_pt_timeless_decoding(pt);
pt->have_tsc = intel_pt_have_tsc(pt);
pt->sampling_mode = false;
@@ -2156,7 +2166,9 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
if (pt->tc.time_mult) {
u64 tsc_freq = intel_pt_ns_to_ticks(pt, 1000000000);

- pt->max_non_turbo_ratio = (tsc_freq + 50000000) / 100000000;
+ if (!pt->max_non_turbo_ratio)
+ pt->max_non_turbo_ratio =
+ (tsc_freq + 50000000) / 100000000;
intel_pt_log("TSC frequency %"PRIu64"\n", tsc_freq);
intel_pt_log("Maximum non-turbo ratio %u\n",
pt->max_non_turbo_ratio);
diff --git a/tools/perf/util/intel-pt.h b/tools/perf/util/intel-pt.h
index 0065949df693..8b8356233e6a 100644
--- a/tools/perf/util/intel-pt.h
+++ b/tools/perf/util/intel-pt.h
@@ -34,6 +34,7 @@ enum {
INTEL_PT_TSC_CTC_N,
INTEL_PT_TSC_CTC_D,
INTEL_PT_CYC_BIT,
+ INTEL_PT_MAX_NONTURBO_RATIO,
INTEL_PT_AUXTRACE_PRIV_MAX,
};

--
1.9.1