From 6ca9a082b1908ff7f8adedf08166043b83b266f6 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 30 Aug 2018 08:32:28 +0200 Subject: perf stat: Pass a 'struct perf_stat_config' argument to global print functions Add 'struct perf_stat_config' argument to the global print functions, so that these functions can be used out of the 'perf stat' command code. Signed-off-by: Jiri Olsa Cc: Alexander Shishkin Cc: Andi Kleen Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20180830063252.23729-20-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index ba481d73f910..6176bae177c2 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1544,7 +1544,8 @@ struct metric_ctx { FILE *fp; }; -static void script_print_metric(void *ctx, const char *color, +static void script_print_metric(struct perf_stat_config *config __maybe_unused, + void *ctx, const char *color, const char *fmt, const char *unit, double val) { @@ -1562,7 +1563,8 @@ static void script_print_metric(void *ctx, const char *color, fprintf(mctx->fp, " %s\n", unit); } -static void script_new_line(void *ctx) +static void script_new_line(struct perf_stat_config *config __maybe_unused, + void *ctx) { struct metric_ctx *mctx = ctx; @@ -1608,7 +1610,7 @@ static void perf_sample__fprint_metric(struct perf_script *script, evsel_script(evsel)->val = val; if (evsel_script(evsel->leader)->gnum == evsel->leader->nr_members) { for_each_group_member (ev2, evsel->leader) { - perf_stat__print_shadow_stats(ev2, + perf_stat__print_shadow_stats(&stat_config, ev2, evsel_script(ev2)->val, sample->cpu, &ctx, -- cgit v1.2.2 From 89f1688a57a8f0b685fccd648e601a1f830fa744 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 13 Sep 2018 14:54:03 +0200 Subject: perf tools: Remove perf_tool from event_op2 Now that we keep a perf_tool pointer inside perf_session, there's no need to have a perf_tool argument in the event_op2 callback. Remove it. Signed-off-by: Jiri Olsa Cc: Alexander Shishkin Cc: Alexey Budankov Cc: Andi Kleen Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20180913125450.21342-2-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 38 ++++++++++++++++++-------------------- 1 file changed, 18 insertions(+), 20 deletions(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 6176bae177c2..765391b6c88c 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -2965,9 +2965,8 @@ static void script__setup_sample_type(struct perf_script *script) } } -static int process_stat_round_event(struct perf_tool *tool __maybe_unused, - union perf_event *event, - struct perf_session *session) +static int process_stat_round_event(struct perf_session *session, + union perf_event *event) { struct stat_round_event *round = &event->stat_round; struct perf_evsel *counter; @@ -2981,9 +2980,8 @@ static int process_stat_round_event(struct perf_tool *tool __maybe_unused, return 0; } -static int process_stat_config_event(struct perf_tool *tool __maybe_unused, - union perf_event *event, - struct perf_session *session __maybe_unused) +static int process_stat_config_event(struct perf_session *session __maybe_unused, + union perf_event *event) { perf_event__read_stat_config(&stat_config, &event->stat_config); return 0; @@ -3009,10 +3007,10 @@ static int set_maps(struct perf_script *script) } static -int process_thread_map_event(struct perf_tool *tool, - union perf_event *event, - struct perf_session *session __maybe_unused) +int process_thread_map_event(struct perf_session *session, + union perf_event *event) { + struct perf_tool *tool = session->tool; struct perf_script *script = container_of(tool, struct perf_script, tool); if (script->threads) { @@ -3028,10 +3026,10 @@ int process_thread_map_event(struct perf_tool *tool, } static -int process_cpu_map_event(struct perf_tool *tool __maybe_unused, - union perf_event *event, - struct perf_session *session __maybe_unused) +int process_cpu_map_event(struct perf_session *session, + union perf_event *event) { + struct perf_tool *tool = session->tool; struct perf_script *script = container_of(tool, struct perf_script, tool); if (script->cpus) { @@ -3046,21 +3044,21 @@ int process_cpu_map_event(struct perf_tool *tool __maybe_unused, return set_maps(script); } -static int process_feature_event(struct perf_tool *tool, - union perf_event *event, - struct perf_session *session) +static int process_feature_event(struct perf_session *session, + union perf_event *event) { if (event->feat.feat_id < HEADER_LAST_FEATURE) - return perf_event__process_feature(tool, event, session); + return perf_event__process_feature(session, event); return 0; } #ifdef HAVE_AUXTRACE_SUPPORT -static int perf_script__process_auxtrace_info(struct perf_tool *tool, - union perf_event *event, - struct perf_session *session) +static int perf_script__process_auxtrace_info(struct perf_session *session, + union perf_event *event) { - int ret = perf_event__process_auxtrace_info(tool, event, session); + struct perf_tool *tool = session->tool; + + int ret = perf_event__process_auxtrace_info(session, event); if (ret == 0) { struct perf_script *script = container_of(tool, struct perf_script, tool); -- cgit v1.2.2 From c12e039d1233f24ab2726945f883037f47b26f1d Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 13 Sep 2018 20:10:31 -0700 Subject: perf tools: Report itrace options in help I often forget all the options that --itrace accepts. Instead of burying them in the man page only report them in the normal command line help too to make them easier accessible. v2: Align Signed-off-by: Andi Kleen Cc: Jiri Olsa Cc: Kim Phillips Link: http://lkml.kernel.org/r/20180914031038.4160-2-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 765391b6c88c..66699dd351e0 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -3193,7 +3193,7 @@ int cmd_script(int argc, const char **argv) OPT_BOOLEAN(0, "ns", &nanosecs, "Use 9 decimal places when displaying time"), OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts", - "Instruction Tracing options", + "Instruction Tracing options\n" ITRACE_HELP, itrace_parse_synth_opts), OPT_BOOLEAN(0, "full-source-path", &srcline_full_filename, "Show full source file name path for source lines"), -- cgit v1.2.2 From 37fed3de555199733805a2d3e03aee7727c09ea4 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Tue, 18 Sep 2018 05:32:09 -0700 Subject: perf script: Allow sym and dso without ip, addr Currently sym and dso require printing ip and addr because the print function is tied to those outputs. With callindent it makes sense to print the symbol or dso without numerical IP or ADDR. So change the dependency check to only check the underlying attribute. Also the branch target output relies on the user_set flag to determine if the branch target should be implicitely printed. When modifying the fields with + or - also set user_set, so that ADDR can be removed. We also need to set wildcard_set to make the initial sanity check pass. This allows to remove a lot of noise in callindent output by dropping the numerical addresses, which are not all that useful. Before % perf script --itrace=cr -F +callindent swapper 0 [000] 156546.354971: 1 branches: pt_config 0 [unknown] ([unknown]) => ffffffff81010486 pt_config ([kernel.kallsyms]) swapper 0 [000] 156546.354971: 1 branches: pt_config ffffffff81010499 pt_config ([kernel.kallsyms]) => ffffffff8101063e pt_event_add ([kernel.kallsyms]) swapper 0 [000] 156546.354971: 1 branches: pt_event_add ffffffff81010635 pt_event_add ([kernel.kallsyms]) => ffffffff8115e687 event_sched_in.isra.107 ([kernel.kallsyms]) swapper 0 [000] 156546.354971: 1 branches: perf_pmu_enable ffffffff8115e726 event_sched_in.isra.107 ([kernel.kallsyms]) => ffffffff811579b0 perf_pmu_enable ([kernel.kallsyms]) swapper 0 [000] 156546.354971: 1 branches: perf_pmu_nop_void ffffffff81151730 perf_pmu_nop_void ([kernel.kallsyms]) => ffffffff8115e72b event_sched_in.isra.107 ([kernel.kallsyms]) swapper 0 [000] 156546.354971: 1 branches: event_sched_in.isra.107 ffffffff8115e737 event_sched_in.isra.107 ([kernel.kallsyms]) => ffffffff8115e7a5 group_sched_in ([kernel.kallsyms]) swapper 0 [000] 156546.354971: 1 branches: __x86_indirect_thunk_rax ffffffff8115e7f6 group_sched_in ([kernel.kallsyms]) => ffffffff81a03000 __x86_indirect_thunk_rax ([kernel.kallsyms]) After % perf script --itrace=cr -F +callindent,-ip,-sym,-symoff swapper 0 [000] 156546.354971: 1 branches: pt_config swapper 0 [000] 156546.354971: 1 branches: pt_config swapper 0 [000] 156546.354971: 1 branches: pt_event_add swapper 0 [000] 156546.354971: 1 branches: perf_pmu_enable swapper 0 [000] 156546.354971: 1 branches: perf_pmu_nop_void swapper 0 [000] 156546.354971: 1 branches: event_sched_in.isra.107 swapper 0 [000] 156546.354971: 1 branches: __x86_indirect_thunk_rax swapper 0 [000] 156546.354971: 1 branches: perf_pmu_nop_int swapper 0 [000] 156546.354971: 1 branches: group_sched_in swapper 0 [000] 156546.354971: 1 branches: event_filter_match swapper 0 [000] 156546.354971: 1 branches: event_filter_match swapper 0 [000] 156546.354971: 1 branches: group_sched_in Signed-off-by: Andi Kleen Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Jiri Olsa Cc: Kim Phillips Link: http://lkml.kernel.org/r/20180918123214.26728-5-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 66699dd351e0..7aa59696e97a 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -406,9 +406,10 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, PERF_OUTPUT_WEIGHT)) return -EINVAL; - if (PRINT_FIELD(SYM) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR)) { + if (PRINT_FIELD(SYM) && + !(evsel->attr.sample_type & (PERF_SAMPLE_IP|PERF_SAMPLE_ADDR))) { pr_err("Display of symbols requested but neither sample IP nor " - "sample address\nis selected. Hence, no addresses to convert " + "sample address\navailable. Hence, no addresses to convert " "to symbols.\n"); return -EINVAL; } @@ -417,10 +418,9 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, "selected.\n"); return -EINVAL; } - if (PRINT_FIELD(DSO) && !PRINT_FIELD(IP) && !PRINT_FIELD(ADDR) && - !PRINT_FIELD(BRSTACK) && !PRINT_FIELD(BRSTACKSYM) && !PRINT_FIELD(BRSTACKOFF)) { - pr_err("Display of DSO requested but no address to convert. Select\n" - "sample IP, sample address, brstack, brstacksym, or brstackoff.\n"); + if (PRINT_FIELD(DSO) && + !(evsel->attr.sample_type & (PERF_SAMPLE_IP|PERF_SAMPLE_ADDR))) { + pr_err("Display of DSO requested but no address to convert.\n"); return -EINVAL; } if (PRINT_FIELD(SRCLINE) && !PRINT_FIELD(IP)) { @@ -2491,6 +2491,8 @@ parse: output[j].fields &= ~all_output_options[i].field; else output[j].fields |= all_output_options[i].field; + output[j].user_set = true; + output[j].wildcard_set = true; } } } else { @@ -2501,7 +2503,8 @@ parse: rc = -EINVAL; goto out; } - output[type].fields |= all_output_options[i].field; + output[type].user_set = true; + output[type].wildcard_set = true; } } -- cgit v1.2.2 From a78cdee6fbb136694334ade4cedb331a9d0b4d5e Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Tue, 18 Sep 2018 05:32:10 -0700 Subject: perf script: Print DSO for callindent Now that we don't need to print the IP/ADDR for callindent the DSO is also not printed. It's useful for some cases, so add an own DSO printout for callindent for the case when IP/ADDR is not enabled. Before: % perf script --itrace=cr -F +callindent,-ip,-sym,-symoff,-addr swapper 0 [000] 3377.917072: 1 branches: pt_config swapper 0 [000] 3377.917072: 1 branches: pt_config swapper 0 [000] 3377.917072: 1 branches: pt_event_add swapper 0 [000] 3377.917072: 1 branches: perf_pmu_enable swapper 0 [000] 3377.917072: 1 branches: perf_pmu_nop_void swapper 0 [000] 3377.917072: 1 branches: event_sched_in.isra.107 swapper 0 [000] 3377.917072: 1 branches: __x86_indirect_thunk_rax swapper 0 [000] 3377.917072: 1 branches: perf_pmu_nop_int swapper 0 [000] 3377.917072: 1 branches: group_sched_in swapper 0 [000] 3377.917072: 1 branches: event_filter_match swapper 0 [000] 3377.917072: 1 branches: event_filter_match swapper 0 [000] 3377.917072: 1 branches: group_sched_in After: swapper 0 [000] 3377.917072: 1 branches: ([unknown]) pt_config swapper 0 [000] 3377.917072: 1 branches: ([kernel.kallsyms]) pt_config swapper 0 [000] 3377.917072: 1 branches: ([kernel.kallsyms]) pt_event_add swapper 0 [000] 3377.917072: 1 branches: ([kernel.kallsyms]) perf_pmu_enable swapper 0 [000] 3377.917072: 1 branches: ([kernel.kallsyms]) perf_pmu_nop_void swapper 0 [000] 3377.917072: 1 branches: ([kernel.kallsyms]) event_sched_in.isra.107 swapper 0 [000] 3377.917072: 1 branches: ([kernel.kallsyms]) __x86_indirect_thunk_rax swapper 0 [000] 3377.917072: 1 branches: ([kernel.kallsyms]) perf_pmu_nop_int swapper 0 [000] 3377.917072: 1 branches: ([kernel.kallsyms]) group_sched_in swapper 0 [000] 3377.917072: 1 branches: ([kernel.kallsyms]) event_filter_match swapper 0 [000] 3377.917072: 1 branches: ([kernel.kallsyms]) event_filter_match swapper 0 [000] 3377.917072: 1 branches: ([kernel.kallsyms]) group_sched_in swapper 0 [000] 3377.917072: 1 branches: ([kernel.kallsyms]) __x86_indirect_thunk_rax swapper 0 [000] 3377.917072: 1 branches: ([kernel.kallsyms]) perf_pmu_nop_txn swapper 0 [000] 3377.917072: 1 branches: ([kernel.kallsyms]) event_sched_in.isra.107 (in the kernel case of course it's not very useful, but it's important with user programs where symbols are not unique) Signed-off-by: Andi Kleen Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Jiri Olsa Cc: Kim Phillips Link: http://lkml.kernel.org/r/20180918123214.26728-6-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 7aa59696e97a..7732346bd9dd 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1115,6 +1115,7 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample, const char *name = NULL; static int spacing; int len = 0; + int dlen = 0; u64 ip = 0; /* @@ -1141,6 +1142,12 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample, ip = sample->ip; } + if (PRINT_FIELD(DSO) && !(PRINT_FIELD(IP) || PRINT_FIELD(ADDR))) { + dlen += fprintf(fp, "("); + dlen += map__fprintf_dsoname(al->map, fp); + dlen += fprintf(fp, ")\t"); + } + if (name) len = fprintf(fp, "%*s%s", (int)depth * 4, "", name); else if (ip) @@ -1159,7 +1166,7 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample, if (len < spacing) len += fprintf(fp, "%*s", spacing - len, ""); - return len; + return len + dlen; } static int perf_sample__fprintf_insn(struct perf_sample *sample, -- cgit v1.2.2 From 62cb1b8868a70c932b15959a98594df537df2ffc Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Thu, 20 Sep 2018 16:00:43 +0300 Subject: perf script: Enhance sample flags for trace begin / end Allow for different combinations of sample flags with "trace begin" or "trace end". Previously, the Intel PT decoder would indicate begin / end by a branch from / to zero. That hides useful information, in particular when a trace ends with a call. Before remedying that, prepare 'perf script' to display sample flags with more combinations that include trace begin / end. In those cases display 'tr start' and 'tr end' separately. Signed-off-by: Adrian Hunter Cc: Andi Kleen Cc: Jiri Olsa Link: http://lkml.kernel.org/r/20180920130048.31432-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 36 +++++++++++++++++++++++++++--------- 1 file changed, 27 insertions(+), 9 deletions(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 7732346bd9dd..4da5e32b9e03 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1262,6 +1262,18 @@ static struct { {0, NULL} }; +static const char *sample_flags_to_name(u32 flags) +{ + int i; + + for (i = 0; sample_flags[i].name ; i++) { + if (sample_flags[i].flags == flags) + return sample_flags[i].name; + } + + return NULL; +} + static int perf_sample__fprintf_flags(u32 flags, FILE *fp) { const char *chars = PERF_IP_FLAG_CHARS; @@ -1271,11 +1283,20 @@ static int perf_sample__fprintf_flags(u32 flags, FILE *fp) char str[33]; int i, pos = 0; - for (i = 0; sample_flags[i].name ; i++) { - if (sample_flags[i].flags == (flags & ~PERF_IP_FLAG_IN_TX)) { - name = sample_flags[i].name; - break; - } + name = sample_flags_to_name(flags & ~PERF_IP_FLAG_IN_TX); + if (name) + return fprintf(fp, " %-15s%4s ", name, in_tx ? "(x)" : ""); + + if (flags & PERF_IP_FLAG_TRACE_BEGIN) { + name = sample_flags_to_name(flags & ~(PERF_IP_FLAG_IN_TX | PERF_IP_FLAG_TRACE_BEGIN)); + if (name) + return fprintf(fp, " tr strt %-7s%4s ", name, in_tx ? "(x)" : ""); + } + + if (flags & PERF_IP_FLAG_TRACE_END) { + name = sample_flags_to_name(flags & ~(PERF_IP_FLAG_IN_TX | PERF_IP_FLAG_TRACE_END)); + if (name) + return fprintf(fp, " tr end %-7s%4s ", name, in_tx ? "(x)" : ""); } for (i = 0; i < n; i++, flags >>= 1) { @@ -1288,10 +1309,7 @@ static int perf_sample__fprintf_flags(u32 flags, FILE *fp) } str[pos] = 0; - if (name) - return fprintf(fp, " %-7s%4s ", name, in_tx ? "(x)" : ""); - - return fprintf(fp, " %-11s ", str); + return fprintf(fp, " %-19s ", str); } struct printer_data { -- cgit v1.2.2