[PATCH 4.4 16/83] perf intel-pt: Improve sample timestamp

[Greg Kroah-Hartman <gregkh@linuxfoundation.org>]

4.4-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Adrian Hunter <adrian.hunter@intel.com>

commit 3f04d98e972b59706bd43d6cc75efac91f8fba50 upstream.

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>
Cc: Andi Kleen <ak@linux.intel.com>
Link: http://lkml.kernel.org/r/1495786658-18063-3-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

---
 tools/perf/util/intel-pt-decoder/intel-pt-decoder.c |   34 ++++++++++++++++++--
 1 file changed, 31 insertions(+), 3 deletions(-)

--- 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
@@ -98,6 +117,7 @@ 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;
@@ -140,6 +160,7 @@ struct intel_pt_decoder {
 	unsigned int fup_tx_flags;
 	unsigned int tx_flags;
 	uint64_t timestamp_insn_cnt;
+	uint64_t sample_insn_cnt;
 	uint64_t stuck_ip;
 	int no_progress;
 	int stuck_ip_prd;
@@ -896,6 +917,7 @@ static int intel_pt_walk_insn(struct int
 
 	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) {
@@ -2035,7 +2057,7 @@ static int intel_pt_sync(struct intel_pt
 
 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;
@@ -2043,7 +2065,7 @@ static uint64_t intel_pt_est_timestamp(s
 	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)
@@ -2099,11 +2121,17 @@ const struct intel_pt_state *intel_pt_de
 	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 (intel_pt_sample_time(decoder->pkt_state)) {
+			decoder->sample_timestamp = decoder->timestamp;
+			decoder->sample_insn_cnt = decoder->timestamp_insn_cnt;
+		}
 	}
 
-	decoder->state.timestamp = decoder->timestamp;
+	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;