Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1645422

[PATCH 37/37] perf intel-pt: Improve sample timestamp

Show all headers | View raw

The decoder uses its current timestamp in samples. Usually that is a
timestamp that has already passed, but in some cases it is a timestamp for
a branch that the decoder is walking towards, and consequently hasn't
reached. Improve that situation by using the pkt_state to determine when
to use the current or previous timestamp.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 .../perf/util/intel-pt-decoder/intel-pt-decoder.c  | 42 ++++++++++++++++++----
 1 file changed, 35 insertions(+), 7 deletions(-)

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 a6f41a0e1ae8..aa1593ce551d 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -64,6 +64,25 @@ enum intel_pt_pkt_state {
 	INTEL_PT_STATE_FUP_NO_TIP,
 };
 
+static inline bool intel_pt_sample_time(enum intel_pt_pkt_state pkt_state)
+{
+	switch (pkt_state) {
+	case INTEL_PT_STATE_NO_PSB:
+	case INTEL_PT_STATE_NO_IP:
+	case INTEL_PT_STATE_ERR_RESYNC:
+	case INTEL_PT_STATE_IN_SYNC:
+	case INTEL_PT_STATE_TNT:
+		return true;
+	case INTEL_PT_STATE_TIP:
+	case INTEL_PT_STATE_TIP_PGD:
+	case INTEL_PT_STATE_FUP:
+	case INTEL_PT_STATE_FUP_NO_TIP:
+		return false;
+	default:
+		return true;
+	};
+}
+
 #ifdef INTEL_PT_STRICT
 #define INTEL_PT_STATE_ERR1	INTEL_PT_STATE_NO_PSB
 #define INTEL_PT_STATE_ERR2	INTEL_PT_STATE_NO_PSB
@@ -101,6 +120,7 @@ struct intel_pt_decoder {
 	uint64_t timestamp;
 	uint64_t tsc_timestamp;
 	uint64_t ref_timestamp;
+	uint64_t sample_timestamp;
 	uint64_t ret_addr;
 	uint64_t ctc_timestamp;
 	uint64_t ctc_delta;
@@ -150,6 +170,7 @@ struct intel_pt_decoder {
 	uint64_t fup_pwre_payload;
 	uint64_t cbr_payload;
 	uint64_t timestamp_insn_cnt;
+	uint64_t sample_insn_cnt;
 	uint64_t stuck_ip;
 	int no_progress;
 	int stuck_ip_prd;
@@ -932,6 +953,7 @@ static int intel_pt_walk_insn(struct intel_pt_decoder *decoder,
 
 	decoder->tot_insn_cnt += insn_cnt;
 	decoder->timestamp_insn_cnt += insn_cnt;
+	decoder->sample_insn_cnt += insn_cnt;
 	decoder->period_insn_cnt += insn_cnt;
 
 	if (err) {
@@ -2279,7 +2301,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder)
 
 static uint64_t intel_pt_est_timestamp(struct intel_pt_decoder *decoder)
 {
-	uint64_t est = decoder->timestamp_insn_cnt << 1;
+	uint64_t est = decoder->sample_insn_cnt << 1;
 
 	if (!decoder->cbr || !decoder->max_non_turbo_ratio)
 		goto out;
@@ -2287,7 +2309,7 @@ static uint64_t intel_pt_est_timestamp(struct intel_pt_decoder *decoder)
 	est *= decoder->max_non_turbo_ratio;
 	est /= decoder->cbr;
 out:
-	return decoder->timestamp + est;
+	return decoder->sample_timestamp + est;
 }
 
 const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder)
@@ -2342,14 +2364,11 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder)
 		}
 	} while (err == -ENOLINK);
 
-	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.err = intel_pt_ext_err(err);
 		decoder->state.from_ip = decoder->ip;
+		decoder->sample_timestamp = decoder->timestamp;
+		decoder->sample_insn_cnt = decoder->timestamp_insn_cnt;
 	} else {
 		decoder->state.err = 0;
 		if (decoder->cbr != decoder->cbr_seen && decoder->state.type) {
@@ -2357,8 +2376,17 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder)
 			decoder->state.type |= INTEL_PT_CBR_CHG;
 			decoder->state.cbr_payload = decoder->cbr_payload;
 		}
+		if (intel_pt_sample_time(decoder->pkt_state)) {
+			decoder->sample_timestamp = decoder->timestamp;
+			decoder->sample_insn_cnt = decoder->timestamp_insn_cnt;
+		}
 	}
 
+	decoder->state.timestamp = decoder->sample_timestamp;
+	decoder->state.est_timestamp = intel_pt_est_timestamp(decoder);
+	decoder->state.cr3 = decoder->cr3;
+	decoder->state.tot_insn_cnt = decoder->tot_insn_cnt;
+
 	return &decoder->state;
 }
 
-- 
1.9.1

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

[PATCH 00/37] perf intel-pt: Power events and PTWRITE Adrian Hunter <adrian.hunter@intel.com> - 2017-05-19 11:10 +0200
  [PATCH 30/37] perf intel-pt: Factor out intel_pt_set_event_name() Adrian Hunter <adrian.hunter@intel.com> - 2017-05-19 11:10 +0200
  [PATCH 14/37] perf intel-pt: Add decoder support for CBR events Adrian Hunter <adrian.hunter@intel.com> - 2017-05-19 11:10 +0200
  [PATCH 27/37] perf intel-pt: Join needlessly wrapped lines Adrian Hunter <adrian.hunter@intel.com> - 2017-05-19 11:10 +0200
  [PATCH 17/37] perf tools: Fix message because cpu list option is -C not -c Adrian Hunter <adrian.hunter@intel.com> - 2017-05-19 11:10 +0200
  [PATCH 07/37] perf intel-pt: Ensure never to set 'last_ip' when packet 'count' is zero Adrian Hunter <adrian.hunter@intel.com> - 2017-05-19 11:10 +0200
  [PATCH 37/37] perf intel-pt: Improve sample timestamp Adrian Hunter <adrian.hunter@intel.com> - 2017-05-19 11:10 +0200
    Re: [PATCH 37/37] perf intel-pt: Improve sample timestamp Andi Kleen <ak@linux.intel.com> - 2017-05-19 16:40 +0200
  [PATCH 09/37] perf intel-pt: Add missing __fallthrough Adrian Hunter <adrian.hunter@intel.com> - 2017-05-19 11:10 +0200
  [PATCH 19/37] perf script: Add 'synth' event type for synthesized events Adrian Hunter <adrian.hunter@intel.com> - 2017-05-19 11:10 +0200
  [PATCH 35/37] perf intel-pt: Do not use TSC packets for calculating CPU cycles to TSC Adrian Hunter <adrian.hunter@intel.com> - 2017-05-19 11:10 +0200
  [PATCH 05/37] perf intel-pt: Ensure IP is zero when state is INTEL_PT_STATE_NO_IP Adrian Hunter <adrian.hunter@intel.com> - 2017-05-19 11:10 +0200
  [PATCH 03/37] perf intel-pt: Add documentation for new config terms Adrian Hunter <adrian.hunter@intel.com> - 2017-05-19 11:10 +0200
  [PATCH 26/37] perf intel-pt: Remove unused instructions_sample_period Adrian Hunter <adrian.hunter@intel.com> - 2017-05-19 11:10 +0200
  [PATCH 11/37] perf intel-pt: Add decoder support for ptwrite and power event packets Adrian Hunter <adrian.hunter@intel.com> - 2017-05-19 11:10 +0200
  [PATCH 18/37] perf script: Fix message because field list option is -F not -f Adrian Hunter <adrian.hunter@intel.com> - 2017-05-19 11:10 +0200
  [PATCH 13/37] perf intel-pt: Move decoder error setting into one condition Adrian Hunter <adrian.hunter@intel.com> - 2017-05-19 11:10 +0200
  [PATCH 32/37] perf intel-pt: Synthesize new power and ptwrite events Adrian Hunter <adrian.hunter@intel.com> - 2017-05-19 11:10 +0200
  [PATCH 15/37] perf intel-pt: Remove redundant initial_skip checks Adrian Hunter <adrian.hunter@intel.com> - 2017-05-19 11:10 +0200
  [PATCH 24/37] perf script: Add synthesized Intel PT power and ptwrite events Adrian Hunter <adrian.hunter@intel.com> - 2017-05-19 11:10 +0200
  [PATCH 36/37] perf auxtrace: Add CPU filter support Adrian Hunter <adrian.hunter@intel.com> - 2017-05-19 11:10 +0200
  [PATCH 23/37] perf auxtrace: Add itrace option to output power events Adrian Hunter <adrian.hunter@intel.com> - 2017-05-19 11:10 +0200
  [PATCH 25/37] perf intel-pt: Factor out common code synthesizing event samples Adrian Hunter <adrian.hunter@intel.com> - 2017-05-19 11:10 +0200
  [PATCH 04/37] perf intel-pt: Fix missing stack clear Adrian Hunter <adrian.hunter@intel.com> - 2017-05-19 11:10 +0200
  [PATCH 20/37] perf script: Add 'synth' field for synthesized event payloads Adrian Hunter <adrian.hunter@intel.com> - 2017-05-19 11:10 +0200
  [PATCH 34/37] perf intel-pt: Update documentation to include new ptwrite and power events Adrian Hunter <adrian.hunter@intel.com> - 2017-05-19 11:10 +0200
  [PATCH 10/37] perf intel-pt: Clear FUP flag on error Adrian Hunter <adrian.hunter@intel.com> - 2017-05-19 11:10 +0200
  [PATCH 28/37] perf intel-pt: Tidy Intel PT evsel lookup into separate function Adrian Hunter <adrian.hunter@intel.com> - 2017-05-19 11:10 +0200
  [PATCH 16/37] perf intel-pt: Fix transactions_sample_type Adrian Hunter <adrian.hunter@intel.com> - 2017-05-19 11:10 +0200
  [PATCH 01/37] perf intel-pt: Allow decoding with branch tracing disabled Adrian Hunter <adrian.hunter@intel.com> - 2017-05-19 11:20 +0200
  [PATCH 02/37] perf intel-pt: Add default config for pass-through branch enable Adrian Hunter <adrian.hunter@intel.com> - 2017-05-19 11:20 +0200

csiph-web