perf tools: Fix Intel PT 'instructions' sample period

The period on synthesized 'instructions' samples was being set to a
fixed value, whereas the correct value is the number of instructions
since the last sample, which is a value that the decoder can provide.
So do it that way.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/1437150840-31811-14-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index f8ac462..56790ea 100644 (file)
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -108,6 +108,7 @@ struct intel_pt_decoder {
        uint64_t sign_bits;
        uint64_t period;
        enum intel_pt_period_type period_type;
+       uint64_t tot_insn_cnt;
        uint64_t period_insn_cnt;
        uint64_t period_mask;
        uint64_t period_ticks;
@@ -559,6 +560,7 @@ static int intel_pt_walk_insn(struct intel_pt_decoder *decoder,
        err = decoder->walk_insn(intel_pt_insn, &insn_cnt, &decoder->ip, ip,
                                 max_insn_cnt, decoder->data);
 
+       decoder->tot_insn_cnt += insn_cnt;
        decoder->timestamp_insn_cnt += insn_cnt;
        decoder->period_insn_cnt += insn_cnt;
 
@@ -1529,6 +1531,7 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder)
        decoder->state.timestamp = decoder->timestamp;
        decoder->state.est_timestamp = intel_pt_est_timestamp(decoder);
        decoder->state.cr3 = decoder->cr3;
+       decoder->state.tot_insn_cnt = decoder->tot_insn_cnt;
 
        if (err)
                decoder->state.from_ip = decoder->ip;

diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
index 4c48802..cbf5704 100644 (file)
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
@@ -58,6 +58,7 @@ struct intel_pt_state {
        uint64_t from_ip;
        uint64_t to_ip;
        uint64_t cr3;
+       uint64_t tot_insn_cnt;
        uint64_t timestamp;
        uint64_t est_timestamp;
        uint64_t trace_nr;

diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index a5acd2f..3b34a64 100644 (file)
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -126,6 +126,7 @@ struct intel_pt_queue {
        u64 timestamp;
        u32 flags;
        u16 insn_len;
+       u64 last_insn_cnt;
 };
 
 static void intel_pt_dump(struct intel_pt *pt __maybe_unused,
@@ -920,11 +921,13 @@ static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq)
        sample.addr = ptq->state->to_ip;
        sample.id = ptq->pt->instructions_id;
        sample.stream_id = ptq->pt->instructions_id;
-       sample.period = ptq->pt->instructions_sample_period;
+       sample.period = ptq->state->tot_insn_cnt - ptq->last_insn_cnt;
        sample.cpu = ptq->cpu;
        sample.flags = ptq->flags;
        sample.insn_len = ptq->insn_len;
 
+       ptq->last_insn_cnt = ptq->state->tot_insn_cnt;
+
        if (pt->synth_opts.callchain) {
                thread_stack__sample(ptq->thread, ptq->chain,
                                     pt->synth_opts.callchain_sz, sample.ip);