[tip:perf/core] perf intel-pt: Synthesize CBR events when last seen value changes

[tip-bot for Adrian Hunter]

Commit-ID:  5fe2cf7d19c48f2b53b57e6a5786972bc1b8d738
Gitweb:     https://git.kernel.org/tip/5fe2cf7d19c48f2b53b57e6a5786972bc1b8d738
Author:     Adrian Hunter <adrian.hunter@xxxxxxxxx>
AuthorDate: Sat, 22 Jun 2019 12:32:45 +0300
Committer:  Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
CommitDate: Tue, 25 Jun 2019 08:47:10 -0300

perf intel-pt: Synthesize CBR events when last seen value changes

The first core-to-bus ratio (CBR) event will not be shown if --itrace
's' option (skip initial number of events) is used, nor if time
intervals are specified that do not include the start of tracing. Change
the logic to record the last CBR value seen by the user, and synthesize
CBR events whenever that changes.

Signed-off-by: Adrian Hunter <adrian.hunter@xxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Link: http://lkml.kernel.org/r/20190622093248.581-5-adrian.hunter@xxxxxxxxx
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
---
 tools/perf/util/intel-pt.c | 65 +++++++++++++++++++++++++++++-----------------
 1 file changed, 41 insertions(+), 24 deletions(-)

diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 550db6e77968..470aaae9d930 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -171,6 +171,7 @@ struct intel_pt_queue {
 	u64 last_in_cyc_cnt;
 	u64 last_br_insn_cnt;
 	u64 last_br_cyc_cnt;
+	unsigned int cbr_seen;
 	char insn[INTEL_PT_INSN_BUF_SZ];
 };
 
@@ -1052,6 +1053,8 @@ static int intel_pt_setup_queue(struct intel_pt *pt,
 			ptq->cpu = queue->cpu;
 		ptq->tid = queue->tid;
 
+		ptq->cbr_seen = UINT_MAX;
+
 		if (pt->sampling_mode && !pt->snapshot_mode &&
 		    pt->timeless_decoding)
 			ptq->step_through_buffers = true;
@@ -1184,6 +1187,17 @@ static inline bool intel_pt_skip_event(struct intel_pt *pt)
 	       pt->num_events++ < pt->synth_opts.initial_skip;
 }
 
+/*
+ * Cannot count CBR as skipped because it won't go away until cbr == cbr_seen.
+ * Also ensure CBR is first non-skipped event by allowing for 4 more samples
+ * from this decoder state.
+ */
+static inline bool intel_pt_skip_cbr_event(struct intel_pt *pt)
+{
+	return pt->synth_opts.initial_skip &&
+	       pt->num_events + 4 < pt->synth_opts.initial_skip;
+}
+
 static void intel_pt_prep_a_sample(struct intel_pt_queue *ptq,
 				   union perf_event *event,
 				   struct perf_sample *sample)
@@ -1429,9 +1443,11 @@ static int intel_pt_synth_cbr_sample(struct intel_pt_queue *ptq)
 	struct perf_synth_intel_cbr raw;
 	u32 flags;
 
-	if (intel_pt_skip_event(pt))
+	if (intel_pt_skip_cbr_event(pt))
 		return 0;
 
+	ptq->cbr_seen = ptq->state->cbr;
+
 	intel_pt_prep_p_sample(pt, ptq, event, &sample);
 
 	sample.id = ptq->pt->cbr_id;
@@ -1868,8 +1884,7 @@ static inline bool intel_pt_is_switch_ip(struct intel_pt_queue *ptq, u64 ip)
 }
 
 #define INTEL_PT_PWR_EVT (INTEL_PT_MWAIT_OP | INTEL_PT_PWR_ENTRY | \
-			  INTEL_PT_EX_STOP | INTEL_PT_PWR_EXIT | \
-			  INTEL_PT_CBR_CHG)
+			  INTEL_PT_EX_STOP | INTEL_PT_PWR_EXIT)
 
 static int intel_pt_sample(struct intel_pt_queue *ptq)
 {
@@ -1901,31 +1916,33 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 			return err;
 	}
 
-	if (pt->sample_pwr_events && (state->type & INTEL_PT_PWR_EVT)) {
-		if (state->type & INTEL_PT_CBR_CHG) {
+	if (pt->sample_pwr_events) {
+		if (ptq->state->cbr != ptq->cbr_seen) {
 			err = intel_pt_synth_cbr_sample(ptq);
 			if (err)
 				return err;
 		}
-		if (state->type & INTEL_PT_MWAIT_OP) {
-			err = intel_pt_synth_mwait_sample(ptq);
-			if (err)
-				return err;
-		}
-		if (state->type & INTEL_PT_PWR_ENTRY) {
-			err = intel_pt_synth_pwre_sample(ptq);
-			if (err)
-				return err;
-		}
-		if (state->type & INTEL_PT_EX_STOP) {
-			err = intel_pt_synth_exstop_sample(ptq);
-			if (err)
-				return err;
-		}
-		if (state->type & INTEL_PT_PWR_EXIT) {
-			err = intel_pt_synth_pwrx_sample(ptq);
-			if (err)
-				return err;
+		if (state->type & INTEL_PT_PWR_EVT) {
+			if (state->type & INTEL_PT_MWAIT_OP) {
+				err = intel_pt_synth_mwait_sample(ptq);
+				if (err)
+					return err;
+			}
+			if (state->type & INTEL_PT_PWR_ENTRY) {
+				err = intel_pt_synth_pwre_sample(ptq);
+				if (err)
+					return err;
+			}
+			if (state->type & INTEL_PT_EX_STOP) {
+				err = intel_pt_synth_exstop_sample(ptq);
+				if (err)
+					return err;
+			}
+			if (state->type & INTEL_PT_PWR_EXIT) {
+				err = intel_pt_synth_pwrx_sample(ptq);
+				if (err)
+					return err;
+			}
 		}
 	}