[tip:perf/core] perf intel-pt: Add mispred-all config option to aid use with autofdo

[tip-bot for Adrian Hunter <tipbot@zytor.com>]

Commit-ID:  ba11ba65e02836c475427ae199adfc2d8cc4a900
Gitweb:     http://git.kernel.org/tip/ba11ba65e02836c475427ae199adfc2d8cc4a900
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Fri, 25 Sep 2015 16:15:56 +0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Mon, 28 Sep 2015 17:21:00 -0300

perf intel-pt: Add mispred-all config option to aid use with autofdo

autofdo incorrectly expects branch flags to include either mispred or
predicted.  In fact mispred = predicted = 0 is valid and means the flags
are not supported, which they aren't by Intel PT.

To make autofdo work, add a config option which will cause Intel PT
decoder to set the mispred flag on all branches.

Below is an example of using Intel PT with autofdo.  The example is
also added to the Intel PT documentation.  It requires autofdo
(https://github.com/google/autofdo) and gcc version 5.  The bubble
sort example is from the AutoFDO tutorial (https://gcc.gnu.org/wiki/AutoFDO/Tutorial)
amended to take the number of elements as a parameter.

	$ gcc-5 -O3 sort.c -o sort_optimized
	$ ./sort_optimized 30000
	Bubble sorting array of 30000 elements
	2254 ms

	$ cat ~/.perfconfig
	[intel-pt]
		mispred-all

	$ perf record -e intel_pt//u ./sort 3000
	Bubble sorting array of 3000 elements
	58 ms
	[ perf record: Woken up 2 times to write data ]
	[ perf record: Captured and wrote 3.939 MB perf.data ]
	$ perf inject -i perf.data -o inj --itrace=i100usle --strip
	$ ./create_gcov --binary=./sort --profile=inj --gcov=sort.gcov -gcov_version=1
	$ gcc-5 -O3 -fauto-profile=sort.gcov sort.c -o sort_autofdo
	$ ./sort_autofdo 30000
	Bubble sorting array of 30000 elements
	2155 ms

Note there is currently no advantage to using Intel PT instead of LBR,
but that may change in the future if greater use is made of the data.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/1443186956-18718-26-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/intel-pt.txt | 29 +++++++++++++++++++++++++++++
 tools/perf/util/intel-pt.c            | 14 ++++++++++++++
 2 files changed, 43 insertions(+)

diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt
index a0fbb5d..be764f9 100644
--- a/tools/perf/Documentation/intel-pt.txt
+++ b/tools/perf/Documentation/intel-pt.txt
@@ -764,3 +764,32 @@ perf inject also accepts the --itrace option in which case tracing data is
 removed and replaced with the synthesized events. e.g.
 
 	perf inject --itrace -i perf.data -o perf.data.new
+
+Below is an example of using Intel PT with autofdo.  It requires autofdo
+(https://github.com/google/autofdo) and gcc version 5.  The bubble
+sort example is from the AutoFDO tutorial (https://gcc.gnu.org/wiki/AutoFDO/Tutorial)
+amended to take the number of elements as a parameter.
+
+	$ gcc-5 -O3 sort.c -o sort_optimized
+	$ ./sort_optimized 30000
+	Bubble sorting array of 30000 elements
+	2254 ms
+
+	$ cat ~/.perfconfig
+	[intel-pt]
+		mispred-all
+
+	$ perf record -e intel_pt//u ./sort 3000
+	Bubble sorting array of 3000 elements
+	58 ms
+	[ perf record: Woken up 2 times to write data ]
+	[ perf record: Captured and wrote 3.939 MB perf.data ]
+	$ perf inject -i perf.data -o inj --itrace=i100usle --strip
+	$ ./create_gcov --binary=./sort --profile=inj --gcov=sort.gcov -gcov_version=1
+	$ gcc-5 -O3 -fauto-profile=sort.gcov sort.c -o sort_autofdo
+	$ ./sort_autofdo 30000
+	Bubble sorting array of 30000 elements
+	2155 ms
+
+Note there is currently no advantage to using Intel PT instead of LBR, but
+that may change in the future if greater use is made of the data.
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 05e8fcc51..03ff072 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -64,6 +64,7 @@ struct intel_pt {
 	bool data_queued;
 	bool est_tsc;
 	bool sync_switch;
+	bool mispred_all;
 	int have_sched_switch;
 	u32 pmu_type;
 	u64 kernel_start;
@@ -943,6 +944,7 @@ static void intel_pt_update_last_branch_rb(struct intel_pt_queue *ptq)
 	be->flags.abort = !!(state->flags & INTEL_PT_ABORT_TX);
 	be->flags.in_tx = !!(state->flags & INTEL_PT_IN_TX);
 	/* No support for mispredict */
+	be->flags.mispred = ptq->pt->mispred_all;
 
 	if (bs->nr < ptq->pt->synth_opts.last_branch_sz)
 		bs->nr += 1;
@@ -1967,6 +1969,16 @@ static bool intel_pt_find_switch(struct perf_evlist *evlist)
 	return false;
 }
 
+static int intel_pt_perf_config(const char *var, const char *value, void *data)
+{
+	struct intel_pt *pt = data;
+
+	if (!strcmp(var, "intel-pt.mispred-all"))
+		pt->mispred_all = perf_config_bool(var, value);
+
+	return 0;
+}
+
 static const char * const intel_pt_info_fmts[] = {
 	[INTEL_PT_PMU_TYPE]		= "  PMU Type            %"PRId64"\n",
 	[INTEL_PT_TIME_SHIFT]		= "  Time Shift          %"PRIu64"\n",
@@ -2011,6 +2023,8 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 	if (!pt)
 		return -ENOMEM;
 
+	perf_config(intel_pt_perf_config, pt);
+
 	err = auxtrace_queues__init(&pt->queues);
 	if (err)
 		goto err_free;