[tip:perf/core] perf intel-pt: Allow decoding with branch tracing disabled

From: tip-bot for Adrian Hunter
Date: Wed Jun 21 2017 - 14:26:15 EST


Commit-ID: 839598176b0554967238234e1e92c7d1e3f0d53d
Gitweb: http://git.kernel.org/tip/839598176b0554967238234e1e92c7d1e3f0d53d
Author: Adrian Hunter <adrian.hunter@xxxxxxxxx>
AuthorDate: Fri, 26 May 2017 11:17:11 +0300
Committer: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
CommitDate: Wed, 21 Jun 2017 11:35:48 -0300

perf intel-pt: Allow decoding with branch tracing disabled

The kernel now supports the disabling of branch tracing, however the
decoder assumes branch tracing is always enabled. Pass through a parameter
to indicate whether branch tracing is enabled and use it to avoid cases
when the decoder is expecting branch packets. There are 2 such cases.
First, FUP packets which can bind to an IP even when there is no branch
tracing. Secondly, the decoder will try to use branch packets to find an IP
to start decoding or to recover from errors.

Signed-off-by: Adrian Hunter <adrian.hunter@xxxxxxxxx>
Cc: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Link: http://lkml.kernel.org/r/1495786658-18063-11-git-send-email-adrian.hunter@xxxxxxxxx
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
---
tools/perf/util/intel-pt-decoder/intel-pt-decoder.c | 13 +++++++++++++
tools/perf/util/intel-pt-decoder/intel-pt-decoder.h | 1 +
tools/perf/util/intel-pt.c | 14 ++++++++++++++
3 files changed, 28 insertions(+)

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 cad40fe..dacb922 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -106,6 +106,7 @@ struct intel_pt_decoder {
const unsigned char *buf;
size_t len;
bool return_compression;
+ bool branch_enable;
bool mtc_insn;
bool pge;
bool have_tma;
@@ -214,6 +215,7 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params)
decoder->pgd_ip = params->pgd_ip;
decoder->data = params->data;
decoder->return_compression = params->return_compression;
+ decoder->branch_enable = params->branch_enable;

decoder->period = params->period;
decoder->period_type = params->period_type;
@@ -1650,6 +1652,10 @@ next:
break;
}
intel_pt_set_last_ip(decoder);
+ if (!decoder->branch_enable) {
+ decoder->ip = decoder->last_ip;
+ break;
+ }
err = intel_pt_walk_fup(decoder);
if (err != -EAGAIN) {
if (err)
@@ -1964,6 +1970,13 @@ static int intel_pt_sync_ip(struct intel_pt_decoder *decoder)

decoder->set_fup_tx_flags = false;

+ if (!decoder->branch_enable) {
+ decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
+ decoder->overflow = false;
+ decoder->state.type = 0; /* Do not have a sample */
+ return 0;
+ }
+
intel_pt_log("Scanning for full IP\n");
err = intel_pt_walk_to_ip(decoder);
if (err)
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 e90619a..add3bed 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
@@ -87,6 +87,7 @@ struct intel_pt_params {
bool (*pgd_ip)(uint64_t ip, void *data);
void *data;
bool return_compression;
+ bool branch_enable;
uint64_t period;
enum intel_pt_period_type period_type;
unsigned max_non_turbo_ratio;
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 4c7718f..5c59b8c 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -668,6 +668,19 @@ static bool intel_pt_return_compression(struct intel_pt *pt)
return true;
}

+static bool intel_pt_branch_enable(struct intel_pt *pt)
+{
+ struct perf_evsel *evsel;
+ u64 config;
+
+ evlist__for_each_entry(pt->session->evlist, evsel) {
+ if (intel_pt_get_config(pt, &evsel->attr, &config) &&
+ (config & 1) && !(config & 0x2000))
+ return false;
+ }
+ return true;
+}
+
static unsigned int intel_pt_mtc_period(struct intel_pt *pt)
{
struct perf_evsel *evsel;
@@ -799,6 +812,7 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
params.walk_insn = intel_pt_walk_next_insn;
params.data = ptq;
params.return_compression = intel_pt_return_compression(pt);
+ params.branch_enable = intel_pt_branch_enable(pt);
params.max_non_turbo_ratio = pt->max_non_turbo_ratio;
params.mtc_period = intel_pt_mtc_period(pt);
params.tsc_ctc_ratio_n = pt->tsc_ctc_ratio_n;