perf report: Add Instruction Tracing support

Add support for decoding an AUX area assuming it contains instruction
tracing data.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1429903807-20559-4-git-send-email-adrian.hunter@intel.com
[ Do not use -Z as an alternative to --itrace ]
[ Fixed initialization of itrace_synth_opts struct fields on older gcc versions ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 896672b..b66f6b4 100644 (file)
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -327,6 +327,33 @@ OPTIONS
 
 include::callchain-overhead-calculation.txt[]
 
+--itrace::
+       Options for decoding instruction tracing data. The options are:
+
+               i       synthesize instructions events
+               b       synthesize branches events
+               c       synthesize branches events (calls only)
+               r       synthesize branches events (returns only)
+               e       synthesize error events
+               d       create a debug log
+               g       synthesize a call chain for instructions events
+
+       The default is all events i.e. the same as --itrace=ibe
+
+       In addition, the period (default 100000) for instructions events
+       can be specified in units of:
+
+               i       instructions
+               t       ticks
+               ms      milliseconds
+               us      microseconds
+               ns      nanoseconds (default)
+
+       Also the call chain size (default 16, max. 1024) for instructions
+       events can be specified.
+
+       To disable decoding entirely, use --no-itrace.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-annotate[1]

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 476cdf7..18cb0ff 100644 (file)
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -36,6 +36,8 @@
 #include "util/data.h"
 #include "arch/common.h"
 
+#include "util/auxtrace.h"
+
 #include <dlfcn.h>
 #include <linux/bitmap.h>
 
@@ -585,6 +587,7 @@ parse_percent_limit(const struct option *opt, const char *str,
 int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 {
        struct perf_session *session;
+       struct itrace_synth_opts itrace_synth_opts = { .set = 0, };
        struct stat st;
        bool has_br_stack = false;
        int branch_mode = -1;
@@ -607,6 +610,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
                        .attr            = perf_event__process_attr,
                        .tracing_data    = perf_event__process_tracing_data,
                        .build_id        = perf_event__process_build_id,
+                       .id_index        = perf_event__process_id_index,
+                       .auxtrace_info   = perf_event__process_auxtrace_info,
+                       .auxtrace        = perf_event__process_auxtrace,
                        .ordered_events  = true,
                        .ordering_requires_timestamps = true,
                },
@@ -717,6 +723,9 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
                     "Don't show entries under that percent", parse_percent_limit),
        OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
                     "how to display percentage of filtered entries", parse_filter_percentage),
+       OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts",
+                           "Instruction Tracing options",
+                           itrace_parse_synth_opts),
        OPT_END()
        };
        struct perf_data_file file = {
@@ -761,6 +770,8 @@ repeat:
                                               report.queue_size);
        }
 
+       session->itrace_synth_opts = &itrace_synth_opts;
+
        report.session = session;
 
        has_br_stack = perf_header__has_feat(&session->header,