[PATCH v4 7/8] tools, perf, script: Add --call-trace and --call-ret-trace

From: Andi Kleen
Date: Mon Sep 03 2018 - 12:23:31 EST


From: Andi Kleen <ak@xxxxxxxxxxxxxxx>

Add short cut options to print PT call trace and call-ret-trace,
for calls and call and returns. Roughly corresponds to ftrace
function tracer and function graph tracer.

Just makes these common use cases nicer to use.

% perf record -a -e intel_pt// sleep 1
% perf script --call-trace
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_pmu_enable
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) __x86_indirect_thunk_rax
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) event_filter_match
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) group_sched_in
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) __x86_indirect_thunk_rax
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) event_sched_in.isra.107
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_event_set_state.part.71
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_event_update_time
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_pmu_disable
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_log_itrace_start
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) __x86_indirect_thunk_rax
perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_event_update_userpage

% perf script --call-ret-trace
perf 900 [000] 194167.205652203: tr strt ([unknown]) pt_config
perf 900 [000] 194167.205652203: return ([kernel.kallsyms]) pt_config
perf 900 [000] 194167.205652203: return ([kernel.kallsyms]) pt_event_add
perf 900 [000] 194167.205652203: call ([kernel.kallsyms]) perf_pmu_enable
perf 900 [000] 194167.205652203: return ([kernel.kallsyms]) perf_pmu_nop_void
perf 900 [000] 194167.205652203: return ([kernel.kallsyms]) event_sched_in.isra.107
perf 900 [000] 194167.205652203: call ([kernel.kallsyms]) __x86_indirect_thunk_rax
perf 900 [000] 194167.205652203: return ([kernel.kallsyms]) perf_pmu_nop_int
perf 900 [000] 194167.205652203: return ([kernel.kallsyms]) group_sched_in
perf 900 [000] 194167.205652203: call ([kernel.kallsyms]) event_filter_match
perf 900 [000] 194167.205652203: return ([kernel.kallsyms]) event_filter_match
perf 900 [000] 194167.205652203: call ([kernel.kallsyms]) group_sched_in
perf 900 [000] 194167.205652203: call ([kernel.kallsyms]) __x86_indirect_thunk_rax
perf 900 [000] 194167.205652203: return ([kernel.kallsyms]) perf_pmu_nop_txn
perf 900 [000] 194167.205652203: call ([kernel.kallsyms]) event_sched_in.isra.107
perf 900 [000] 194167.205652203: call ([kernel.kallsyms]) perf_event_set_state.part.71

v2: Print errors, power, ptwrite too
Signed-off-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
---
tools/perf/Documentation/perf-script.txt | 7 +++++++
tools/perf/builtin-script.c | 24 ++++++++++++++++++++++++
2 files changed, 31 insertions(+)

diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 04a57e0fb3a6..29eb3c3eb93e 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -387,6 +387,13 @@ include::itrace.txt[]
Show instruction stream for intel_pt traces. Requires installing the
xed disassembler.

+--call-trace::
+ Show call stream for intel_pt traces. The CPUs are interleaved, but
+ can be filtered with -C.
+
+--call-ret-trace::
+ Show call and return stream for intel_pt traces.
+
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-script-perl[1],
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 99f69561e1f8..87ec7cc798ea 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -3094,6 +3094,26 @@ static int parse_insn_trace(const struct option *opt __maybe_unused,
return 0;
}

+static int parse_call_trace(const struct option *opt __maybe_unused,
+ const char *str __maybe_unused,
+ int unset __maybe_unused)
+{
+ parse_output_fields(NULL, "-ip,-addr,-event,-period,+callindent", 0);
+ itrace_parse_synth_opts(opt, "cewp", 0);
+ nanosecs = true;
+ return 0;
+}
+
+static int parse_callret_trace(const struct option *opt __maybe_unused,
+ const char *str __maybe_unused,
+ int unset __maybe_unused)
+{
+ parse_output_fields(NULL, "-ip,-addr,-event,-period,+callindent,+flags", 0);
+ itrace_parse_synth_opts(opt, "crewp", 0);
+ nanosecs = true;
+ return 0;
+}
+
int cmd_script(int argc, const char **argv)
{
bool show_full_info = false;
@@ -3183,6 +3203,10 @@ int cmd_script(int argc, const char **argv)
"only consider these symbols"),
OPT_CALLBACK_OPTARG(0, "insn-trace", &itrace_synth_opts, NULL, NULL,
"Decode instructions from itrace", parse_insn_trace),
+ OPT_CALLBACK_OPTARG(0, "call-trace", &itrace_synth_opts, NULL, NULL,
+ "Decode calls from from itrace", parse_call_trace),
+ OPT_CALLBACK_OPTARG(0, "call-ret-trace", &itrace_synth_opts, NULL, NULL,
+ "Decode calls and returns from itrace", parse_callret_trace),
OPT_STRING(0, "stop-bt", &symbol_conf.bt_stop_list_str, "symbol[,symbol...]",
"Stop display of callgraph at these symbols"),
OPT_STRING('C', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
--
2.17.1