From d1b1552e15d41297abcaf3812378e3391d44fa6b Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 20 Sep 2018 11:05:38 -0700 Subject: [PATCH] tools script: Add --call-trace and --call-ret-trace 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 Signed-off-by: Andi Kleen Tested-by: Arnaldo Carvalho de Melo Tested-by: Leo Yan Acked-by: Jiri Olsa Cc: Kim Phillips Link: http://lkml.kernel.org/r/20180920180540.14039-4-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- 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 00c655ab4968..805baabd238e 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -390,6 +390,13 @@ include::itrace.txt[] --xed:: Run xed disassembler on output. 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 6099c722a679..566e1450898a 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -3122,6 +3122,26 @@ static int parse_xed(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; @@ -3213,6 +3233,10 @@ int cmd_script(int argc, const char **argv) "Decode instructions from itrace", parse_insn_trace), OPT_CALLBACK_OPTARG(0, "xed", NULL, NULL, NULL, "Run xed disassembler on output", parse_xed), + 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"),