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 v1.2.3 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 v1.2.3 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 v1.2.3 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 v1.2.3 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 v1.2.3 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 v1.2.3 From c1c9b9695cc8868048f45c7e2559f65bc0be7382 Mon Sep 17 00:00:00 2001 From: Milian Wolff Date: Sun, 21 Oct 2018 21:14:23 +0200 Subject: perf script: Allow extended console debug output The script tool isn't using a browser, yet use_browser wasn't set explicitly to zero. This in turn lead to confusing output such as: ``` $ perf script -vvv ... ... overlapping maps in /home/milian/foobar (disable tui for more info) ... ``` Explicitly set use_browser to 0 now, which gives us the extended debug information now in perf script as expected. Signed-off-by: Milian Wolff Acked-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Link: http://lkml.kernel.org/r/20181021191424.16183-1-milian.wolff@kdab.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 4 +++- 1 file changed, 3 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 4da5e32b9e03..bd468b90801b 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -3417,8 +3417,10 @@ int cmd_script(int argc, const char **argv) exit(-1); } - if (!script_name) + if (!script_name) { setup_pager(); + use_browser = 0; + } session = perf_session__new(&data, false, &script.tool); if (session == NULL) -- cgit v1.2.3 From 7ee40678af935fb489b0c6cf0f75808175214cd7 Mon Sep 17 00:00:00 2001 From: Milian Wolff Date: Sun, 21 Oct 2018 21:14:24 +0200 Subject: perf script: Flush output stream after events in verbose mode When the perf script output is written to a terminal stream, the normal output of `perf script` would get buffered, but its debug output would be written directly. This made it quite hard to figure out where a given debug output is coming from. We can improve on this by flushing the output buffer after processing an event. To see the value, compare the following output for a `perf script -v` run: Before this patch: ``` unwind: reg 16, val 7faf7dfdc000 unwind: reg 7, val 7ffc80811e30 unwind: find_proc_info dso /usr/lib/ld-2.28.so unwind: reg 6, val 0 unwind: _start:ip = 0x7faf7dfdc000 (0x2000) unwind: reg 16, val 7faf7dfdc000 unwind: reg 7, val 7ffc80811e30 unwind: find_proc_info dso /usr/lib/ld-2.28.so unwind: reg 6, val 0 unwind: _start:ip = 0x7faf7dfdc000 (0x2000) unwind: reg 16, val 7faf7dfdc000 unwind: reg 7, val 7ffc80811e30 unwind: find_proc_info dso /usr/lib/ld-2.28.so unwind: reg 6, val 0 unwind: _start:ip = 0x7faf7dfdc000 (0x2000) unwind: reg 16, val 7faf7dfdc000 unwind: reg 7, val 7ffc80811e30 ... lots and lots of verbose debug output cpp-inlining 24617 90229.122036534: 1 cycles:uppp: 7faf7dfdc000 _start+0x0 (/usr/lib/ld-2.28.so) cpp-inlining 24617 90229.122043974: 1 cycles:uppp: 7faf7dfdc000 _start+0x0 (/usr/lib/ld-2.28.so) ... ``` After this patch: ``` ... unwind: reg 16, val 7faf7dfdc000 unwind: reg 7, val 7ffc80811e30 unwind: find_proc_info dso /usr/lib/ld-2.28.so unwind: reg 6, val 0 unwind: _start:ip = 0x7faf7dfdc000 (0x2000) cpp-inlining 24617 90229.122036534: 1 cycles:uppp: 7faf7dfdc000 _start+0x0 (/usr/lib/ld-2.28.so) unwind: reg 16, val 7faf7dfdc000 unwind: reg 7, val 7ffc80811e30 unwind: find_proc_info dso /usr/lib/ld-2.28.so unwind: reg 6, val 0 unwind: _start:ip = 0x7faf7dfdc000 (0x2000) cpp-inlining 24617 90229.122043974: 1 cycles:uppp: 7faf7dfdc000 _start+0x0 (/usr/lib/ld-2.28.so) ... ``` This new output format makes it much easier to use perf script output for debugging purposes, e.g. to investigate broken dwarf unwinding. Signed-off-by: Milian Wolff Acked-by: Jiri Olsa Link: http://lkml.kernel.org/r/20181021191424.16183-2-milian.wolff@kdab.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index bd468b90801b..ca09b7d2adb7 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1737,6 +1737,9 @@ static void process_event(struct perf_script *script, if (PRINT_FIELD(METRIC)) perf_sample__fprint_metric(script, thread, evsel, sample, fp); + + if (verbose) + fflush(fp); } static struct scripting_ops *scripting_ops; -- cgit v1.2.3 From b585ebdb5912cf1438d4822f79aaebe36a2d123a Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 20 Sep 2018 11:05:36 -0700 Subject: perf script: Add --insn-trace for instruction decoding Add a --insn-trace short hand option for decoding and disassembling instruction streams for intel_pt. This automatically pipes the output into the xed disassembler to generate disassembled instructions. This just makes this use model much nicer to use. Before % perf record -e intel_pt// ... % perf script --itrace=i0ns --ns -F +insn,-event,-period | xed -F insn: -A -64 swapper 0 [000] 17276.429606186: ffffffff81010486 pt_config ([kernel.kallsyms]) nopl %eax, (%rax,%rax,1) swapper 0 [000] 17276.429606186: ffffffff8101048b pt_config ([kernel.kallsyms]) add $0x10, %rsp swapper 0 [000] 17276.429606186: ffffffff8101048f pt_config ([kernel.kallsyms]) popq %rbx swapper 0 [000] 17276.429606186: ffffffff81010490 pt_config ([kernel.kallsyms]) popq %rbp swapper 0 [000] 17276.429606186: ffffffff81010491 pt_config ([kernel.kallsyms]) popq %r12 swapper 0 [000] 17276.429606186: ffffffff81010493 pt_config ([kernel.kallsyms]) popq %r13 swapper 0 [000] 17276.429606186: ffffffff81010495 pt_config ([kernel.kallsyms]) popq %r14 swapper 0 [000] 17276.429606186: ffffffff81010497 pt_config ([kernel.kallsyms]) popq %r15 swapper 0 [000] 17276.429606186: ffffffff81010499 pt_config ([kernel.kallsyms]) retq swapper 0 [000] 17276.429606186: ffffffff8101063e pt_event_add ([kernel.kallsyms]) cmpl $0x1, 0x1b0(%rbx) swapper 0 [000] 17276.429606186: ffffffff81010645 pt_event_add ([kernel.kallsyms]) mov $0xffffffea, %eax swapper 0 [000] 17276.429606186: ffffffff8101064a pt_event_add ([kernel.kallsyms]) mov $0x0, %edx swapper 0 [000] 17276.429606186: ffffffff8101064f pt_event_add ([kernel.kallsyms]) popq %rbx swapper 0 [000] 17276.429606186: ffffffff81010650 pt_event_add ([kernel.kallsyms]) cmovnz %edx, %eax swapper 0 [000] 17276.429606186: ffffffff81010653 pt_event_add ([kernel.kallsyms]) jmp 0xffffffff81010635 swapper 0 [000] 17276.429606186: ffffffff81010635 pt_event_add ([kernel.kallsyms]) retq swapper 0 [000] 17276.429606186: ffffffff8115e687 event_sched_in.isra.107 ([kernel.kallsyms]) test %eax, %eax Now: % perf record -e intel_pt// ... % perf script --insn-trace --xed ... same output ... XED needs to be installed with: $ git clone https://github.com/intelxed/mbuild.git mbuild $ git clone https://github.com/intelxed/xed $ cd xed $ ./mfile.py $ ./mfile.py examples $ sudo ./mfile.py --prefix=/usr/local install $ sudo cp obj/examples/xed /usr/local/bin $ xed | head -3 ERROR: required argument(s) were missing Copyright (C) 2017, Intel Corporation. All rights reserved. XED version: [v10.0-328-g7d62c8c49b7b] $ Signed-off-by: Andi Kleen Tested-by: Arnaldo Carvalho de Melo Acked-by: Jiri Olsa Link: http://lkml.kernel.org/r/20180920180540.14039-2-andi@firstfloor.org [ Fixed up whitespace damage, added the 'mfile.py examples + cp obj/examples/xed ... ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index ca09b7d2adb7..411ea175bcaf 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -44,6 +44,7 @@ #include #include #include +#include #include "sane_ctype.h" @@ -3103,6 +3104,24 @@ static int perf_script__process_auxtrace_info(struct perf_session *session, #define perf_script__process_auxtrace_info 0 #endif +static int parse_insn_trace(const struct option *opt __maybe_unused, + const char *str __maybe_unused, + int unset __maybe_unused) +{ + parse_output_fields(NULL, "+insn,-event,-period", 0); + itrace_parse_synth_opts(opt, "i0ns", 0); + nanosecs = true; + return 0; +} + +static int parse_xed(const struct option *opt __maybe_unused, + const char *str __maybe_unused, + int unset __maybe_unused) +{ + force_pager("xed -F insn: -A -64 | less"); + return 0; +} + int cmd_script(int argc, const char **argv) { bool show_full_info = false; @@ -3187,6 +3206,10 @@ int cmd_script(int argc, const char **argv) "system-wide collection from all CPUs"), OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]", "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, "xed", NULL, NULL, NULL, + "Run xed disassembler on output", parse_xed), 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"), -- cgit v1.2.3 From 4eb068157121939f4bc16256a37bcd88f5554123 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 20 Sep 2018 11:05:37 -0700 Subject: perf script: Make itrace script default to all calls By default 'perf script' for itrace outputs sampled instructions or branches. In my experience this is confusing to users because it's hard to correlate with real program behavior. The sampling makes sense for tools like 'perf report' that actually sample to reduce the run time, but run time is normally not a problem for 'perf script'. It's better to give an accurate representation of the program flow. Default 'perf script' to output all calls for itrace. That's a much saner default. The old behavior can be still requested with 'perf script' --itrace=ibxwpe100000 v2: Fix ETM build failure v3: Really fix ETM build failure (Kim Phillips) Signed-off-by: Andi Kleen Acked-by: Jiri Olsa Cc: Kim Phillips Cc: Leo Yan Link: http://lkml.kernel.org/r/20180920180540.14039-3-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 5 ++++- 1 file changed, 4 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 411ea175bcaf..6099c722a679 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -3131,7 +3131,10 @@ int cmd_script(int argc, const char **argv) char *rec_script_path = NULL; char *rep_script_path = NULL; struct perf_session *session; - struct itrace_synth_opts itrace_synth_opts = { .set = false, }; + struct itrace_synth_opts itrace_synth_opts = { + .set = false, + .default_no_sample = true, + }; char *script_path = NULL; const char **__argv; int i, j, err = 0; -- cgit v1.2.3 From d1b1552e15d41297abcaf3812378e3391d44fa6b Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 20 Sep 2018 11:05:38 -0700 Subject: 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/builtin-script.c | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) (limited to 'tools/perf/builtin-script.c') 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"), -- cgit v1.2.3 From 99f753f048b3f02f31a56951781672021af6cd0d Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 20 Sep 2018 11:05:39 -0700 Subject: perf script: Implement --graph-function Add a ftrace style --graph-function argument to 'perf script' that allows to print itrace function calls only below a given function. This makes it easier to find the code of interest in a large trace. % perf record -e intel_pt//k -a sleep 1 % perf script --graph-function group_sched_in --call-trace 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 900 [000] 194167.205652203: ([kernel.kallsyms]) calc_timer_values perf 900 [000] 194167.205652203: ([kernel.kallsyms]) sched_clock_cpu perf 900 [000] 194167.205652203: ([kernel.kallsyms]) __x86_indirect_thunk_rax perf 900 [000] 194167.205652203: ([kernel.kallsyms]) arch_perf_update_userpage perf 900 [000] 194167.205652203: ([kernel.kallsyms]) __fentry__ perf 900 [000] 194167.205652203: ([kernel.kallsyms]) using_native_sched_clock perf 900 [000] 194167.205652203: ([kernel.kallsyms]) sched_clock_stable perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_pmu_enable perf 900 [000] 194167.205652203: ([kernel.kallsyms]) __x86_indirect_thunk_rax swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) group_sched_in swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) __x86_indirect_thunk_rax swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) event_sched_in.isra.107 swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) perf_event_set_state.part.71 swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) perf_event_update_time swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) perf_pmu_disable swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) perf_log_itrace_start swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) __x86_indirect_thunk_rax swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) perf_event_update_userpage swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) calc_timer_values swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) sched_clock_cpu swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) __x86_indirect_thunk_rax swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) arch_perf_update_userpage swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) __fentry__ swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) using_native_sched_clock swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) sched_clock_stable 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/20180920180540.14039-5-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 96 ++++++++++++++++++++++++++++++++++++--------- 1 file changed, 78 insertions(+), 18 deletions(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 566e1450898a..9d2249ea75e3 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1105,6 +1105,35 @@ out: return printed; } +static const char *resolve_branch_sym(struct perf_sample *sample, + struct perf_evsel *evsel, + struct thread *thread, + struct addr_location *al, + u64 *ip) +{ + struct addr_location addr_al; + struct perf_event_attr *attr = &evsel->attr; + const char *name = NULL; + + if (sample->flags & (PERF_IP_FLAG_CALL | PERF_IP_FLAG_TRACE_BEGIN)) { + if (sample_addr_correlates_sym(attr)) { + thread__resolve(thread, &addr_al, sample); + if (addr_al.sym) + name = addr_al.sym->name; + else + *ip = sample->addr; + } else { + *ip = sample->addr; + } + } else if (sample->flags & (PERF_IP_FLAG_RETURN | PERF_IP_FLAG_TRACE_END)) { + if (al->sym) + name = al->sym->name; + else + *ip = sample->ip; + } + return name; +} + static int perf_sample__fprintf_callindent(struct perf_sample *sample, struct perf_evsel *evsel, struct thread *thread, @@ -1112,7 +1141,6 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample, { struct perf_event_attr *attr = &evsel->attr; size_t depth = thread_stack__depth(thread); - struct addr_location addr_al; const char *name = NULL; static int spacing; int len = 0; @@ -1126,22 +1154,7 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample, if (thread->ts && sample->flags & PERF_IP_FLAG_RETURN) depth += 1; - if (sample->flags & (PERF_IP_FLAG_CALL | PERF_IP_FLAG_TRACE_BEGIN)) { - if (sample_addr_correlates_sym(attr)) { - thread__resolve(thread, &addr_al, sample); - if (addr_al.sym) - name = addr_al.sym->name; - else - ip = sample->addr; - } else { - ip = sample->addr; - } - } else if (sample->flags & (PERF_IP_FLAG_RETURN | PERF_IP_FLAG_TRACE_END)) { - if (al->sym) - name = al->sym->name; - else - ip = sample->ip; - } + name = resolve_branch_sym(sample, evsel, thread, al, &ip); if (PRINT_FIELD(DSO) && !(PRINT_FIELD(IP) || PRINT_FIELD(ADDR))) { dlen += fprintf(fp, "("); @@ -1647,6 +1660,47 @@ static void perf_sample__fprint_metric(struct perf_script *script, } } +static bool show_event(struct perf_sample *sample, + struct perf_evsel *evsel, + struct thread *thread, + struct addr_location *al) +{ + int depth = thread_stack__depth(thread); + + if (!symbol_conf.graph_function) + return true; + + if (thread->filter) { + if (depth <= thread->filter_entry_depth) { + thread->filter = false; + return false; + } + return true; + } else { + const char *s = symbol_conf.graph_function; + u64 ip; + const char *name = resolve_branch_sym(sample, evsel, thread, al, + &ip); + unsigned nlen; + + if (!name) + return false; + nlen = strlen(name); + while (*s) { + unsigned len = strcspn(s, ","); + if (nlen == len && !strncmp(name, s, len)) { + thread->filter = true; + thread->filter_entry_depth = depth; + return true; + } + s += len; + if (*s == ',') + s++; + } + return false; + } +} + static void process_event(struct perf_script *script, struct perf_sample *sample, struct perf_evsel *evsel, struct addr_location *al, @@ -1661,6 +1715,9 @@ static void process_event(struct perf_script *script, if (output[type].fields == 0) return; + if (!show_event(sample, evsel, thread, al)) + return; + ++es->samples; perf_sample__fprintf_start(sample, thread, evsel, @@ -3237,6 +3294,8 @@ int cmd_script(int argc, const char **argv) "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, "graph-function", &symbol_conf.graph_function, "symbol[,symbol...]", + "Only print symbols and callees with --call-trace/--call-ret-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"), @@ -3494,7 +3553,8 @@ int cmd_script(int argc, const char **argv) script.session = session; script__setup_sample_type(&script); - if (output[PERF_TYPE_HARDWARE].fields & PERF_OUTPUT_CALLINDENT) + if ((output[PERF_TYPE_HARDWARE].fields & PERF_OUTPUT_CALLINDENT) || + symbol_conf.graph_function) itrace_synth_opts.thread_stack = true; session->itrace_synth_opts = &itrace_synth_opts; -- cgit v1.2.3 From fe57120e18a1f9124ca758c89cc54f91333d1847 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Mon, 24 Sep 2018 10:07:32 -0700 Subject: perf script: Support total cycles count For 'perf script' brstackinsn also print a running cycles count. This makes it easier to calculate cycle deltas for code sections measured with LBRs. % perf record -b -a sleep 1 % perf script -F +brstackinsn ... 00007f73ecc41083 insn: 74 06 # PRED 9 cycles [17] 1.11 IPC 00007f73ecc4108b insn: a8 10 00007f73ecc4108d insn: 74 71 # PRED 1 cycles [18] 1.00 IPC 00007f73ecc41100 insn: 48 8b 46 10 00007f73ecc41104 insn: 4c 8b 38 00007f73ecc41107 insn: 4d 85 ff 00007f73ecc4110a insn: 0f 84 b0 00 00 00 00007f73ecc41110 insn: 83 43 58 01 00007f73ecc41114 insn: 48 89 df 00007f73ecc41117 insn: e8 94 73 04 00 # PRED 6 cycles [24] 1.00 IPC Signed-off-by: Andi Kleen Acked-by: Jiri Olsa Cc: Andi Kleen Link: http://lkml.kernel.org/r/20180924170732.GA28040@tassilo.jf.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 9d2249ea75e3..b5bc85bd0bbe 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -913,7 +913,7 @@ static int grab_bb(u8 *buffer, u64 start, u64 end, static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en, struct perf_insn *x, u8 *inbuf, int len, - int insn, FILE *fp) + int insn, FILE *fp, int *total_cycles) { int printed = fprintf(fp, "\t%016" PRIx64 "\t%-30s\t#%s%s%s%s", ip, dump_insn(x, ip, inbuf, len, NULL), @@ -922,7 +922,8 @@ static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en, en->flags.in_tx ? " INTX" : "", en->flags.abort ? " ABORT" : ""); if (en->flags.cycles) { - printed += fprintf(fp, " %d cycles", en->flags.cycles); + *total_cycles += en->flags.cycles; + printed += fprintf(fp, " %d cycles [%d]", en->flags.cycles, *total_cycles); if (insn) printed += fprintf(fp, " %.2f IPC", (float)insn / en->flags.cycles); } @@ -979,6 +980,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, u8 buffer[MAXBB]; unsigned off; struct symbol *lastsym = NULL; + int total_cycles = 0; if (!(br && br->nr)) return 0; @@ -999,7 +1001,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, printed += ip__fprintf_sym(br->entries[nr - 1].from, thread, x.cpumode, x.cpu, &lastsym, attr, fp); printed += ip__fprintf_jump(br->entries[nr - 1].from, &br->entries[nr - 1], - &x, buffer, len, 0, fp); + &x, buffer, len, 0, fp, &total_cycles); } /* Print all blocks */ @@ -1027,7 +1029,8 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample, printed += ip__fprintf_sym(ip, thread, x.cpumode, x.cpu, &lastsym, attr, fp); if (ip == end) { - printed += ip__fprintf_jump(ip, &br->entries[i], &x, buffer + off, len - off, insn, fp); + printed += ip__fprintf_jump(ip, &br->entries[i], &x, buffer + off, len - off, insn, fp, + &total_cycles); break; } else { printed += fprintf(fp, "\t%016" PRIx64 "\t%s\n", ip, -- cgit v1.2.3