From fd36f3dd79331b9610664b867ff205465bf9ce68 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 23 Dec 2015 02:06:58 +0900 Subject: [PATCH 01/59] perf hist: Pass struct sample to __hists__add_entry() This is a preparation to add more info into the hist_entry. Also it already passes too many argument, so passing sample directly will reduce the overhead of the function call. Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Cc: Andi Kleen Cc: David Ahern Cc: Frederic Weisbecker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Wang Nan Link: http://lkml.kernel.org/r/1450804030-29193-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-annotate.c | 7 +++++-- tools/perf/builtin-diff.c | 11 +++++------ tools/perf/tests/hists_link.c | 6 +++--- tools/perf/util/hist.c | 31 +++++++++++++++++-------------- tools/perf/util/hist.h | 4 ++-- 5 files changed, 32 insertions(+), 27 deletions(-) diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index e18f1b995ffd..b5b8db0b0338 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -47,7 +47,7 @@ struct perf_annotate { }; static int perf_evsel__add_sample(struct perf_evsel *evsel, - struct perf_sample *sample __maybe_unused, + struct perf_sample *sample, struct addr_location *al, struct perf_annotate *ann) { @@ -72,7 +72,10 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel, return 0; } - he = __hists__add_entry(hists, al, NULL, NULL, NULL, 1, 1, 0, true); + sample->period = 1; + sample->weight = 1; + + he = __hists__add_entry(hists, al, NULL, NULL, NULL, sample, true); if (he == NULL) return -ENOMEM; diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 0b180a885ba3..69f5b1feff39 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -311,11 +311,11 @@ static int formula_fprintf(struct hist_entry *he, struct hist_entry *pair, } static int hists__add_entry(struct hists *hists, - struct addr_location *al, u64 period, - u64 weight, u64 transaction) + struct addr_location *al, + struct perf_sample *sample) { - if (__hists__add_entry(hists, al, NULL, NULL, NULL, period, weight, - transaction, true) != NULL) + if (__hists__add_entry(hists, al, NULL, NULL, NULL, + sample, true) != NULL) return 0; return -ENOMEM; } @@ -336,8 +336,7 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused, return -1; } - if (hists__add_entry(hists, &al, sample->period, - sample->weight, sample->transaction)) { + if (hists__add_entry(hists, &al, sample)) { pr_warning("problem incrementing symbol period, skipping event\n"); goto out_put; } diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c index 6243e2b2a245..9eac98daecb8 100644 --- a/tools/perf/tests/hists_link.c +++ b/tools/perf/tests/hists_link.c @@ -64,7 +64,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) struct perf_evsel *evsel; struct addr_location al; struct hist_entry *he; - struct perf_sample sample = { .period = 1, }; + struct perf_sample sample = { .period = 1, .weight = 1, }; size_t i = 0, k; /* @@ -90,7 +90,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) goto out; he = __hists__add_entry(hists, &al, NULL, - NULL, NULL, 1, 1, 0, true); + NULL, NULL, &sample, true); if (he == NULL) { addr_location__put(&al); goto out; @@ -116,7 +116,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine) goto out; he = __hists__add_entry(hists, &al, NULL, - NULL, NULL, 1, 1, 0, true); + NULL, NULL, &sample, true); if (he == NULL) { addr_location__put(&al); goto out; diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 56e97f5af598..039bb91d0a92 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -461,7 +461,7 @@ struct hist_entry *__hists__add_entry(struct hists *hists, struct symbol *sym_parent, struct branch_info *bi, struct mem_info *mi, - u64 period, u64 weight, u64 transaction, + struct perf_sample *sample, bool sample_self) { struct hist_entry entry = { @@ -478,15 +478,15 @@ struct hist_entry *__hists__add_entry(struct hists *hists, .level = al->level, .stat = { .nr_events = 1, - .period = period, - .weight = weight, + .period = sample->period, + .weight = sample->weight, }, .parent = sym_parent, .filtered = symbol__parent_filter(sym_parent) | al->filtered, .hists = hists, .branch_info = bi, .mem_info = mi, - .transaction = transaction, + .transaction = sample->transaction, }; return hists__findnew_entry(hists, &entry, al, sample_self); @@ -526,12 +526,13 @@ iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al u64 cost; struct mem_info *mi = iter->priv; struct hists *hists = evsel__hists(iter->evsel); + struct perf_sample *sample = iter->sample; struct hist_entry *he; if (mi == NULL) return -EINVAL; - cost = iter->sample->weight; + cost = sample->weight; if (!cost) cost = 1; @@ -542,8 +543,10 @@ iter_add_single_mem_entry(struct hist_entry_iter *iter, struct addr_location *al * and this is indirectly achieved by passing period=weight here * and the he_stat__add_period() function. */ + sample->period = cost; + he = __hists__add_entry(hists, al, iter->parent, NULL, mi, - cost, cost, 0, true); + sample, true); if (!he) return -ENOMEM; @@ -630,6 +633,7 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a struct branch_info *bi; struct perf_evsel *evsel = iter->evsel; struct hists *hists = evsel__hists(evsel); + struct perf_sample *sample = iter->sample; struct hist_entry *he = NULL; int i = iter->curr; int err = 0; @@ -643,9 +647,11 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a * The report shows the percentage of total branches captured * and not events sampled. Thus we use a pseudo period of 1. */ + sample->period = 1; + sample->weight = bi->flags.cycles ? bi->flags.cycles : 1; + he = __hists__add_entry(hists, al, iter->parent, &bi[i], NULL, - 1, bi->flags.cycles ? bi->flags.cycles : 1, - 0, true); + sample, true); if (he == NULL) return -ENOMEM; @@ -682,8 +688,7 @@ iter_add_single_normal_entry(struct hist_entry_iter *iter, struct addr_location struct hist_entry *he; he = __hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL, - sample->period, sample->weight, - sample->transaction, true); + sample, true); if (he == NULL) return -ENOMEM; @@ -744,8 +749,7 @@ iter_add_single_cumulative_entry(struct hist_entry_iter *iter, int err = 0; he = __hists__add_entry(hists, al, iter->parent, NULL, NULL, - sample->period, sample->weight, - sample->transaction, true); + sample, true); if (he == NULL) return -ENOMEM; @@ -818,8 +822,7 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter, } he = __hists__add_entry(evsel__hists(evsel), al, iter->parent, NULL, NULL, - sample->period, sample->weight, - sample->transaction, false); + sample, false); if (he == NULL) return -ENOMEM; diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index a48a2078d288..36439bfad059 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -114,8 +114,8 @@ struct hist_entry *__hists__add_entry(struct hists *hists, struct addr_location *al, struct symbol *parent, struct branch_info *bi, - struct mem_info *mi, u64 period, - u64 weight, u64 transaction, + struct mem_info *mi, + struct perf_sample *sample, bool sample_self); int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al, int max_stack_depth, void *arg); From 723928340c9d28d92dcaff8b8fbc9100a1cf9429 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 24 Dec 2015 11:16:17 +0900 Subject: [PATCH 02/59] perf hist: Save raw_data/size for tracepoint events The raw_data and raw_size fields are to provide tracepoint specific information. They will be used by dynamic sort keys later. Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Cc: Andi Kleen Cc: David Ahern Cc: Frederic Weisbecker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Wang Nan Link: http://lkml.kernel.org/r/1450923377-18641-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/hist.c | 24 ++++++++++++++++++++++++ tools/perf/util/sort.h | 2 ++ 2 files changed, 26 insertions(+) diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 039bb91d0a92..2dcf38a78f08 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -369,6 +369,25 @@ static struct hist_entry *hist_entry__new(struct hist_entry *template, if (symbol_conf.use_callchain) callchain_init(he->callchain); + if (he->raw_data) { + he->raw_data = memdup(he->raw_data, he->raw_size); + + if (he->raw_data == NULL) { + map__put(he->ms.map); + if (he->branch_info) { + map__put(he->branch_info->from.map); + map__put(he->branch_info->to.map); + free(he->branch_info); + } + if (he->mem_info) { + map__put(he->mem_info->iaddr.map); + map__put(he->mem_info->daddr.map); + } + free(he->stat_acc); + free(he); + return NULL; + } + } INIT_LIST_HEAD(&he->pairs.node); thread__get(he->thread); } @@ -487,6 +506,8 @@ struct hist_entry *__hists__add_entry(struct hists *hists, .branch_info = bi, .mem_info = mi, .transaction = sample->transaction, + .raw_data = sample->raw_data, + .raw_size = sample->raw_size, }; return hists__findnew_entry(hists, &entry, al, sample_self); @@ -801,6 +822,8 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter, .sym = al->sym, }, .parent = iter->parent, + .raw_data = sample->raw_data, + .raw_size = sample->raw_size, }; int i; struct callchain_cursor cursor; @@ -974,6 +997,7 @@ void hist_entry__delete(struct hist_entry *he) if (he->srcfile && he->srcfile[0]) free(he->srcfile); free_callchain(he->callchain); + free(he->raw_data); free(he); } diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 86f05e7a5566..d29898708dbd 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -122,6 +122,8 @@ struct hist_entry { struct branch_info *branch_info; struct hists *hists; struct mem_info *mem_info; + void *raw_data; + u32 raw_size; struct callchain_root callchain[0]; /* must be last member */ }; From be45d40efec96558c489579bbf93465e90b10abe Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 23 Dec 2015 22:08:41 +0900 Subject: [PATCH 03/59] tools lib traceevent: Factor out and export print_event_field[s]() The print_event_field() and print_event_fields() functions print basic information of a given field or event without the print format. They'll be used by dynamic sort keys later. Committer note: Rename it to pevent_print_field[s]() to get proper namespacing, as discussed with Steven Rostedt. Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Acked-by: Steven Rostedt Cc: Andi Kleen Cc: David Ahern Cc: Frederic Weisbecker Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/r/1450876121-22494-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/traceevent/event-parse.c | 131 +++++++++++++++-------------- tools/lib/traceevent/event-parse.h | 4 + 2 files changed, 73 insertions(+), 62 deletions(-) diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index 68276f35e323..ea69ce35e902 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -4735,73 +4735,80 @@ static int is_printable_array(char *p, unsigned int len) return 1; } -static void print_event_fields(struct trace_seq *s, void *data, - int size __maybe_unused, - struct event_format *event) +void pevent_print_field(struct trace_seq *s, void *data, + struct format_field *field) { - struct format_field *field; unsigned long long val; unsigned int offset, len, i; + struct pevent *pevent = field->event->pevent; + + if (field->flags & FIELD_IS_ARRAY) { + offset = field->offset; + len = field->size; + if (field->flags & FIELD_IS_DYNAMIC) { + val = pevent_read_number(pevent, data + offset, len); + offset = val; + len = offset >> 16; + offset &= 0xffff; + } + if (field->flags & FIELD_IS_STRING && + is_printable_array(data + offset, len)) { + trace_seq_printf(s, "%s", (char *)data + offset); + } else { + trace_seq_puts(s, "ARRAY["); + for (i = 0; i < len; i++) { + if (i) + trace_seq_puts(s, ", "); + trace_seq_printf(s, "%02x", + *((unsigned char *)data + offset + i)); + } + trace_seq_putc(s, ']'); + field->flags &= ~FIELD_IS_STRING; + } + } else { + val = pevent_read_number(pevent, data + field->offset, + field->size); + if (field->flags & FIELD_IS_POINTER) { + trace_seq_printf(s, "0x%llx", val); + } else if (field->flags & FIELD_IS_SIGNED) { + switch (field->size) { + case 4: + /* + * If field is long then print it in hex. + * A long usually stores pointers. + */ + if (field->flags & FIELD_IS_LONG) + trace_seq_printf(s, "0x%x", (int)val); + else + trace_seq_printf(s, "%d", (int)val); + break; + case 2: + trace_seq_printf(s, "%2d", (short)val); + break; + case 1: + trace_seq_printf(s, "%1d", (char)val); + break; + default: + trace_seq_printf(s, "%lld", val); + } + } else { + if (field->flags & FIELD_IS_LONG) + trace_seq_printf(s, "0x%llx", val); + else + trace_seq_printf(s, "%llu", val); + } + } +} + +void pevent_print_fields(struct trace_seq *s, void *data, + int size __maybe_unused, struct event_format *event) +{ + struct format_field *field; field = event->format.fields; while (field) { trace_seq_printf(s, " %s=", field->name); - if (field->flags & FIELD_IS_ARRAY) { - offset = field->offset; - len = field->size; - if (field->flags & FIELD_IS_DYNAMIC) { - val = pevent_read_number(event->pevent, data + offset, len); - offset = val; - len = offset >> 16; - offset &= 0xffff; - } - if (field->flags & FIELD_IS_STRING && - is_printable_array(data + offset, len)) { - trace_seq_printf(s, "%s", (char *)data + offset); - } else { - trace_seq_puts(s, "ARRAY["); - for (i = 0; i < len; i++) { - if (i) - trace_seq_puts(s, ", "); - trace_seq_printf(s, "%02x", - *((unsigned char *)data + offset + i)); - } - trace_seq_putc(s, ']'); - field->flags &= ~FIELD_IS_STRING; - } - } else { - val = pevent_read_number(event->pevent, data + field->offset, - field->size); - if (field->flags & FIELD_IS_POINTER) { - trace_seq_printf(s, "0x%llx", val); - } else if (field->flags & FIELD_IS_SIGNED) { - switch (field->size) { - case 4: - /* - * If field is long then print it in hex. - * A long usually stores pointers. - */ - if (field->flags & FIELD_IS_LONG) - trace_seq_printf(s, "0x%x", (int)val); - else - trace_seq_printf(s, "%d", (int)val); - break; - case 2: - trace_seq_printf(s, "%2d", (short)val); - break; - case 1: - trace_seq_printf(s, "%1d", (char)val); - break; - default: - trace_seq_printf(s, "%lld", val); - } - } else { - if (field->flags & FIELD_IS_LONG) - trace_seq_printf(s, "0x%llx", val); - else - trace_seq_printf(s, "%llu", val); - } - } + pevent_print_field(s, data, field); field = field->next; } } @@ -4827,7 +4834,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event if (event->flags & EVENT_FL_FAILED) { trace_seq_printf(s, "[FAILED TO PARSE]"); - print_event_fields(s, data, size, event); + pevent_print_fields(s, data, size, event); return; } @@ -5301,7 +5308,7 @@ void pevent_event_info(struct trace_seq *s, struct event_format *event, int print_pretty = 1; if (event->pevent->print_raw || (event->flags & EVENT_FL_PRINTRAW)) - print_event_fields(s, record->data, record->size, event); + pevent_print_fields(s, record->data, record->size, event); else { if (event->handler && !(event->flags & EVENT_FL_NOHANDLE)) diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h index 6fc83c7edbe9..706d9bc24066 100644 --- a/tools/lib/traceevent/event-parse.h +++ b/tools/lib/traceevent/event-parse.h @@ -705,6 +705,10 @@ struct cmdline *pevent_data_pid_from_comm(struct pevent *pevent, const char *com struct cmdline *next); int pevent_cmdline_pid(struct pevent *pevent, struct cmdline *cmdline); +void pevent_print_field(struct trace_seq *s, void *data, + struct format_field *field); +void pevent_print_fields(struct trace_seq *s, void *data, + int size __maybe_unused, struct event_format *event); void pevent_event_info(struct trace_seq *s, struct event_format *event, struct pevent_record *record); int pevent_strerror(struct pevent *pevent, enum pevent_errno errnum, From 54f8f40384ab940e15585afde5c278c8e7726214 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 23 Dec 2015 02:07:01 +0900 Subject: [PATCH 04/59] perf top: Create the evlist sooner This is a preparation to support dynamic sort keys for tracepoint events. Dynamic sort keys can be created for specific fields in trace events so it needs the event information, so we need to pass the evlist to the sort routines, create it sooner so that the next patch can do that. Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Cc: Andi Kleen Cc: David Ahern Cc: Frederic Weisbecker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Wang Nan Link: http://lkml.kernel.org/r/1450804030-29193-5-git-send-email-namhyung@kernel.org [ Split from the patch passing the evlist to the sort routines ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-top.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 9ebd67a42ede..4e913d852518 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1231,6 +1231,12 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) if (argc) usage_with_options(top_usage, options); + if (!top.evlist->nr_entries && + perf_evlist__add_default(top.evlist) < 0) { + pr_err("Not enough memory for event selector list\n"); + goto out_delete_evlist; + } + sort__mode = SORT_MODE__TOP; /* display thread wants entries to be collapsed in a different tree */ sort__need_collapse = 1; @@ -1277,12 +1283,6 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) goto out_delete_evlist; } - if (!top.evlist->nr_entries && - perf_evlist__add_default(top.evlist) < 0) { - ui__error("Not enough memory for event selector list\n"); - goto out_delete_evlist; - } - symbol_conf.nr_events = top.evlist->nr_entries; if (top.delay_secs < 1) From 40184c46a3055a97e2efa69da6f17c05bff4b776 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 23 Dec 2015 02:07:01 +0900 Subject: [PATCH 05/59] perf tools: Pass evlist to setup_sorting() This is a preparation to support dynamic sort keys for tracepoint events. Dynamic sort keys can be created for specific fields in trace events so it needs the event information. Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Cc: Andi Kleen Cc: David Ahern Cc: Frederic Weisbecker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Wang Nan Link: http://lkml.kernel.org/r/1450804030-29193-5-git-send-email-namhyung@kernel.org [ Moving the evlist creation earlier in top was split to a previous patch ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-annotate.c | 2 +- tools/perf/builtin-diff.c | 2 +- tools/perf/builtin-report.c | 2 +- tools/perf/builtin-top.c | 2 +- tools/perf/tests/hists_cumulate.c | 8 ++++---- tools/perf/tests/hists_filter.c | 2 +- tools/perf/tests/hists_link.c | 2 +- tools/perf/tests/hists_output.c | 10 +++++----- tools/perf/util/sort.c | 15 +++++++++------ tools/perf/util/sort.h | 5 +++-- 10 files changed, 27 insertions(+), 23 deletions(-) diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c index b5b8db0b0338..cc5c1267c738 100644 --- a/tools/perf/builtin-annotate.c +++ b/tools/perf/builtin-annotate.c @@ -370,7 +370,7 @@ int cmd_annotate(int argc, const char **argv, const char *prefix __maybe_unused) if (ret < 0) goto out_delete; - if (setup_sorting() < 0) + if (setup_sorting(NULL) < 0) usage_with_options(annotate_usage, options); if (annotate.use_stdio) diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 69f5b1feff39..87063835d741 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -1279,7 +1279,7 @@ int cmd_diff(int argc, const char **argv, const char *prefix __maybe_unused) sort__mode = SORT_MODE__DIFF; - if (setup_sorting() < 0) + if (setup_sorting(NULL) < 0) usage_with_options(diff_usage, options); setup_pager(); diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 2a7330b99b82..ea53c816640a 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -897,7 +897,7 @@ repeat: symbol_conf.cumulate_callchain = false; } - if (setup_sorting() < 0) { + if (setup_sorting(session->evlist) < 0) { if (sort_order) parse_options_usage(report_usage, options, "s", 1); if (field_order) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 4e913d852518..005825942441 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1241,7 +1241,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) /* display thread wants entries to be collapsed in a different tree */ sort__need_collapse = 1; - if (setup_sorting() < 0) { + if (setup_sorting(top.evlist) < 0) { if (sort_order) parse_options_usage(top_usage, options, "s", 1); if (field_order) diff --git a/tools/perf/tests/hists_cumulate.c b/tools/perf/tests/hists_cumulate.c index 8292948bc5f9..e36089212061 100644 --- a/tools/perf/tests/hists_cumulate.c +++ b/tools/perf/tests/hists_cumulate.c @@ -281,7 +281,7 @@ static int test1(struct perf_evsel *evsel, struct machine *machine) symbol_conf.cumulate_callchain = false; perf_evsel__reset_sample_bit(evsel, CALLCHAIN); - setup_sorting(); + setup_sorting(NULL); callchain_register_param(&callchain_param); err = add_hist_entries(hists, machine); @@ -428,7 +428,7 @@ static int test2(struct perf_evsel *evsel, struct machine *machine) symbol_conf.cumulate_callchain = false; perf_evsel__set_sample_bit(evsel, CALLCHAIN); - setup_sorting(); + setup_sorting(NULL); callchain_register_param(&callchain_param); err = add_hist_entries(hists, machine); @@ -486,7 +486,7 @@ static int test3(struct perf_evsel *evsel, struct machine *machine) symbol_conf.cumulate_callchain = true; perf_evsel__reset_sample_bit(evsel, CALLCHAIN); - setup_sorting(); + setup_sorting(NULL); callchain_register_param(&callchain_param); err = add_hist_entries(hists, machine); @@ -670,7 +670,7 @@ static int test4(struct perf_evsel *evsel, struct machine *machine) symbol_conf.cumulate_callchain = true; perf_evsel__set_sample_bit(evsel, CALLCHAIN); - setup_sorting(); + setup_sorting(NULL); callchain_register_param(&callchain_param); err = add_hist_entries(hists, machine); diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c index ccb5b4921f25..2a784befd9ce 100644 --- a/tools/perf/tests/hists_filter.c +++ b/tools/perf/tests/hists_filter.c @@ -122,7 +122,7 @@ int test__hists_filter(int subtest __maybe_unused) goto out; /* default sort order (comm,dso,sym) will be used */ - if (setup_sorting() < 0) + if (setup_sorting(NULL) < 0) goto out; machines__init(&machines); diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c index 9eac98daecb8..c764d69ac6ef 100644 --- a/tools/perf/tests/hists_link.c +++ b/tools/perf/tests/hists_link.c @@ -294,7 +294,7 @@ int test__hists_link(int subtest __maybe_unused) goto out; /* default sort order (comm,dso,sym) will be used */ - if (setup_sorting() < 0) + if (setup_sorting(NULL) < 0) goto out; machines__init(&machines); diff --git a/tools/perf/tests/hists_output.c b/tools/perf/tests/hists_output.c index 248beec1d917..ebe6cd485b5d 100644 --- a/tools/perf/tests/hists_output.c +++ b/tools/perf/tests/hists_output.c @@ -134,7 +134,7 @@ static int test1(struct perf_evsel *evsel, struct machine *machine) field_order = NULL; sort_order = NULL; /* equivalent to sort_order = "comm,dso,sym" */ - setup_sorting(); + setup_sorting(NULL); /* * expected output: @@ -236,7 +236,7 @@ static int test2(struct perf_evsel *evsel, struct machine *machine) field_order = "overhead,cpu"; sort_order = "pid"; - setup_sorting(); + setup_sorting(NULL); /* * expected output: @@ -292,7 +292,7 @@ static int test3(struct perf_evsel *evsel, struct machine *machine) field_order = "comm,overhead,dso"; sort_order = NULL; - setup_sorting(); + setup_sorting(NULL); /* * expected output: @@ -366,7 +366,7 @@ static int test4(struct perf_evsel *evsel, struct machine *machine) field_order = "dso,sym,comm,overhead,dso"; sort_order = "sym"; - setup_sorting(); + setup_sorting(NULL); /* * expected output: @@ -468,7 +468,7 @@ static int test5(struct perf_evsel *evsel, struct machine *machine) field_order = "cpu,pid,comm,dso,sym"; sort_order = "dso,pid"; - setup_sorting(); + setup_sorting(NULL); /* * expected output: diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 2d8ccd4d9e1b..0c038a27fe5c 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -4,6 +4,8 @@ #include "comm.h" #include "symbol.h" #include "evsel.h" +#include "evlist.h" +#include regex_t parent_regex; const char default_parent_pattern[] = "^sys_|^do_page_fault"; @@ -1583,7 +1585,8 @@ int hpp_dimension__add_output(unsigned col) return __hpp_dimension__add_output(&hpp_sort_dimensions[col]); } -int sort_dimension__add(const char *tok) +static int sort_dimension__add(const char *tok, + struct perf_evlist *evlist __maybe_unused) { unsigned int i; @@ -1712,7 +1715,7 @@ static int setup_sort_order(void) return 0; } -static int __setup_sorting(void) +static int __setup_sorting(struct perf_evlist *evlist) { char *tmp, *tok, *str; const char *sort_keys; @@ -1743,7 +1746,7 @@ static int __setup_sorting(void) for (tok = strtok_r(str, ", ", &tmp); tok; tok = strtok_r(NULL, ", ", &tmp)) { - ret = sort_dimension__add(tok); + ret = sort_dimension__add(tok, evlist); if (ret == -EINVAL) { error("Invalid --sort key: `%s'", tok); break; @@ -1954,16 +1957,16 @@ out: return ret; } -int setup_sorting(void) +int setup_sorting(struct perf_evlist *evlist) { int err; - err = __setup_sorting(); + err = __setup_sorting(evlist); if (err < 0) return err; if (parent_pattern != default_parent_pattern) { - err = sort_dimension__add("parent"); + err = sort_dimension__add("parent", evlist); if (err < 0) return err; } diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index d29898708dbd..1a00f1eb9d21 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -226,10 +226,11 @@ struct sort_entry { extern struct sort_entry sort_thread; extern struct list_head hist_entry__sort_list; -int setup_sorting(void); +struct perf_evlist; +struct pevent; +int setup_sorting(struct perf_evlist *evlist); int setup_output_field(void); void reset_output_field(void); -extern int sort_dimension__add(const char *); void sort__setup_elide(FILE *fp); void perf_hpp__set_elide(int idx, bool elide); From c7c2a5e40f17ab3b14716d4f08d03792a9b683e7 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 23 Dec 2015 02:07:02 +0900 Subject: [PATCH 06/59] perf tools: Add dynamic sort key for tracepoint events The existing sort keys are less useful for tracepoint events in that they are always sampled at the same place, the function where the tracepoint is located. For example, a 'perf report' on sched:sched_switch event looks like the following: # Overhead Command Shared Object Symbol # ........ ............... ................ .............. # 47.22% swapper [kernel.vmlinux] [k] __schedule 21.67% transmission-gt [kernel.vmlinux] [k] __schedule 8.23% netctl-auto [kernel.vmlinux] [k] __schedule 5.53% kworker/0:1H [kernel.vmlinux] [k] __schedule 1.98% Xephyr [kernel.vmlinux] [k] __schedule 1.33% irq/33-iwlwifi [kernel.vmlinux] [k] __schedule 1.17% wpa_cli [kernel.vmlinux] [k] __schedule 1.13% rcu_preempt [kernel.vmlinux] [k] __schedule 0.85% ksoftirqd/0 [kernel.vmlinux] [k] __schedule 0.77% Timer [kernel.vmlinux] [k] __schedule In fact, tracepoints have meaningful information in their fields but there's no way to use in 'perf report' currently. The dynamic sort keys are introduced in this patc to overcome this limitation. The sched:sched_switch events have following fields: # sudo cat /sys/kernel/debug/tracing/events/sched/sched_switch/format name: sched_switch ID: 268 format: field:unsigned short common_type; offset:0; size:2; signed:0; field:unsigned char common_flags; offset:2; size:1; signed:0; field:unsigned char common_preempt_count; offset:3; size:1; signed:0; field:int common_pid; offset:4; size:4; signed:1; field:char prev_comm[16]; offset:8; size:16; signed:1; field:pid_t prev_pid; offset:24; size:4; signed:1; field:int prev_prio; offset:28; size:4; signed:1; field:long prev_state; offset:32; size:8; signed:1; field:char next_comm[16]; offset:40; size:16; signed:1; field:pid_t next_pid; offset:56; size:4; signed:1; field:int next_prio; offset:60; size:4; signed:1; print fmt: "prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s%s ==> next_comm=%s next_pid=%d next_prio=%d", REC->prev_comm, REC->prev_pid, REC->prev_prio, REC->prev_state & (2048-1) ? __print_flags(REC->prev_state & (2048-1), "|", { 1, "S"} , { 2, "D" }, { 4, "T" }, { 8, "t" }, { 16, "Z" }, { 32, "X" }, { 64, "x" }, { 128, "K"}, { 256, "W" }, { 512, "P" }, { 1024, "N" }) : "R", REC->prev_state & 2048 ? "+" : "", REC->next_comm, REC->next_pid, REC->next_prio With dynamic sort keys, you can use as a sort key. Those dynamic keys are checked and created on demand. For instance, below is to sort by next_pid field output on the same data file: $ perf report -s comm,sched:sched_switch.next_pid --stdio ... # Overhead Command next_pid # ........ ............... .......... # 21.23% transmission-gt 0 20.86% swapper 17773 6.62% netctl-auto 0 5.25% swapper 109 5.21% kworker/0:1H 0 1.98% Xephyr 0 1.98% swapper 6524 1.98% swapper 27478 1.37% swapper 27476 1.17% swapper 233 Multiple dynamic sort keys are also supported: $ perf report -s comm,sched:sched_switch.next_pid,sched:sched_switch.next_comm --stdio ... # Overhead Command next_pid next_comm # ........ ............... .......... ................ # 20.86% swapper 17773 transmission-gt 9.64% transmission-gt 0 swapper/0 9.16% transmission-gt 0 swapper/2 5.25% swapper 109 kworker/0:1H 5.21% kworker/0:1H 0 swapper/0 2.14% netctl-auto 0 swapper/2 1.98% netctl-auto 0 swapper/0 1.98% swapper 6524 Xephyr 1.98% swapper 27478 netctl-auto 1.78% transmission-gt 0 swapper/3 1.53% Xephyr 0 swapper/0 1.29% netctl-auto 0 swapper/1 1.29% swapper 27476 netctl-auto 1.21% netctl-auto 0 swapper/3 1.17% swapper 233 irq/33-iwlwifi Note that pid 0 exists for each cpu so have comm of 'swapper/N'. Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Andi Kleen Cc: David Ahern Cc: Frederic Weisbecker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Wang Nan Link: http://lkml.kernel.org/r/1450804030-29193-6-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/sort.c | 213 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 213 insertions(+) diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 0c038a27fe5c..cc659ba0e232 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1531,6 +1531,216 @@ static int __sort_dimension__add_hpp_output(struct sort_dimension *sd) return 0; } +struct hpp_dynamic_entry { + struct perf_hpp_fmt hpp; + struct perf_evsel *evsel; + struct format_field *field; + unsigned dynamic_len; +}; + +static int hde_width(struct hpp_dynamic_entry *hde) +{ + if (!hde->hpp.len) { + int len = hde->dynamic_len; + int namelen = strlen(hde->field->name); + int fieldlen = hde->field->size; + + if (namelen > len) + len = namelen; + + if (!(hde->field->flags & FIELD_IS_STRING)) { + /* length for print hex numbers */ + fieldlen = hde->field->size * 2 + 2; + } + if (fieldlen > len) + len = fieldlen; + + hde->hpp.len = len; + } + return hde->hpp.len; +} + +static int __sort__hde_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct perf_evsel *evsel __maybe_unused) +{ + struct hpp_dynamic_entry *hde; + size_t len = fmt->user_len; + + hde = container_of(fmt, struct hpp_dynamic_entry, hpp); + + if (!len) + len = hde_width(hde); + + return scnprintf(hpp->buf, hpp->size, "%*.*s", len, len, hde->field->name); +} + +static int __sort__hde_width(struct perf_hpp_fmt *fmt, + struct perf_hpp *hpp __maybe_unused, + struct perf_evsel *evsel __maybe_unused) +{ + struct hpp_dynamic_entry *hde; + size_t len = fmt->user_len; + + hde = container_of(fmt, struct hpp_dynamic_entry, hpp); + + if (!len) + len = hde_width(hde); + + return len; +} + +static int __sort__hde_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, + struct hist_entry *he) +{ + struct hpp_dynamic_entry *hde; + size_t len = fmt->user_len; + struct trace_seq seq; + int ret; + + hde = container_of(fmt, struct hpp_dynamic_entry, hpp); + + if (!len) + len = hde_width(hde); + + if (hists_to_evsel(he->hists) != hde->evsel) + return scnprintf(hpp->buf, hpp->size, "%*.*s", len, len, "N/A"); + + trace_seq_init(&seq); + pevent_print_field(&seq, he->raw_data, hde->field); + ret = scnprintf(hpp->buf, hpp->size, "%*.*s", len, len, seq.buffer); + trace_seq_destroy(&seq); + return ret; +} + +static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt, + struct hist_entry *a, struct hist_entry *b) +{ + struct hpp_dynamic_entry *hde; + struct format_field *field; + unsigned offset, size; + + hde = container_of(fmt, struct hpp_dynamic_entry, hpp); + + if (hists_to_evsel(a->hists) != hde->evsel) + return 0; + + field = hde->field; + if (field->flags & FIELD_IS_DYNAMIC) { + unsigned long long dyn; + + pevent_read_number_field(field, a->raw_data, &dyn); + offset = dyn & 0xffff; + size = (dyn >> 16) & 0xffff; + + /* record max width for output */ + if (size > hde->dynamic_len) + hde->dynamic_len = size; + } else { + offset = field->offset; + size = field->size; + } + + return memcmp(a->raw_data + offset, b->raw_data + offset, size); +} + +static struct hpp_dynamic_entry * +__alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field) +{ + struct hpp_dynamic_entry *hde; + + hde = malloc(sizeof(*hde)); + if (hde == NULL) { + pr_debug("Memory allocation failed\n"); + return NULL; + } + + hde->evsel = evsel; + hde->field = field; + hde->dynamic_len = 0; + + hde->hpp.name = field->name; + hde->hpp.header = __sort__hde_header; + hde->hpp.width = __sort__hde_width; + hde->hpp.entry = __sort__hde_entry; + hde->hpp.color = NULL; + + hde->hpp.cmp = __sort__hde_cmp; + hde->hpp.collapse = __sort__hde_cmp; + hde->hpp.sort = __sort__hde_cmp; + + INIT_LIST_HEAD(&hde->hpp.list); + INIT_LIST_HEAD(&hde->hpp.sort_list); + hde->hpp.elide = false; + hde->hpp.len = 0; + hde->hpp.user_len = 0; + + return hde; +} + +static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok) +{ + char *str, *event_name, *field_name; + struct perf_evsel *evsel, *pos; + struct format_field *field; + struct hpp_dynamic_entry *hde; + int ret = 0; + + if (evlist == NULL) + return -ENOENT; + + str = strdup(tok); + if (str == NULL) + return -ENOMEM; + + event_name = str; + field_name = strchr(str, '.'); + if (field_name == NULL) { + ret = -EINVAL; + goto out; + } + *field_name++ = '\0'; + + evsel = NULL; + evlist__for_each(evlist, pos) { + if (!strcmp(pos->name, event_name)) { + evsel = pos; + break; + } + } + + if (evsel == NULL) { + pr_debug("Cannot find event: %s\n", event_name); + ret = -ENOENT; + goto out; + } + + if (evsel->attr.type != PERF_TYPE_TRACEPOINT) { + pr_debug("%s is not a tracepoint event\n", event_name); + ret = -EINVAL; + goto out; + } + + field = pevent_find_any_field(evsel->tp_format, field_name); + if (field == NULL) { + pr_debug("Cannot find event field for %s.%s\n", + event_name, field_name); + ret = -ENOENT; + goto out; + } + + hde = __alloc_dynamic_entry(evsel, field); + if (hde == NULL) { + ret = -ENOMEM; + goto out; + } + + perf_hpp__register_sort_field(&hde->hpp); + +out: + free(str); + return ret; +} + static int __sort_dimension__add(struct sort_dimension *sd) { if (sd->taken) @@ -1667,6 +1877,9 @@ static int sort_dimension__add(const char *tok, return 0; } + if (!add_dynamic_entry(evlist, tok)) + return 0; + return -ESRCH; } From 60517d28fbd91629686dcf9a39aef4e068a3d5f6 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 23 Dec 2015 02:07:03 +0900 Subject: [PATCH 07/59] perf tools: Try to show pretty printed output for dynamic sort keys Each tracepoint event has format string for print to improve readability. Try to parse the output and match the field name. If it finds one, use that for the result. If not, fallbacks to the original output. For example, sort on kmem:kmalloc.gfp_flags looks like below: (Note: libtraceevent plugins are not installed on my system. They might affect the output below) Before: # Overhead Command gfp_flags # ........ ....... .......... # 99.89% perf 32848 0.06% sleep 208 0.03% perf 32976 0.01% perf 208 After: # Overhead Command gfp_flags # ........ ....... ................... # 99.89% perf GFP_NOFS|GFP_ZERO 0.06% sleep GFP_KERNEL 0.03% perf GFP_KERNEL|GFP_ZERO 0.01% perf GFP_KERNEL Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Andi Kleen Cc: David Ahern Cc: Frederic Weisbecker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Wang Nan Link: http://lkml.kernel.org/r/1450804030-29193-7-git-send-email-namhyung@kernel.org [ Fixed clash with earlier, updated patch in this patchkit ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/hist.c | 1 + tools/perf/util/sort.c | 105 +++++++++++++++++++++++++++++++++++++++-- tools/perf/util/sort.h | 1 + 3 files changed, 102 insertions(+), 5 deletions(-) diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 2dcf38a78f08..fdb97e16a8c3 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -997,6 +997,7 @@ void hist_entry__delete(struct hist_entry *he) if (he->srcfile && he->srcfile[0]) free(he->srcfile); free_callchain(he->callchain); + free(he->trace_output); free(he->raw_data); free(he); } diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index cc659ba0e232..22d28c7e0b01 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1560,6 +1560,62 @@ static int hde_width(struct hpp_dynamic_entry *hde) return hde->hpp.len; } +static char *get_trace_output(struct hist_entry *he) +{ + struct trace_seq seq; + struct perf_evsel *evsel; + struct pevent_record rec = { + .data = he->raw_data, + .size = he->raw_size, + }; + + evsel = hists_to_evsel(he->hists); + + trace_seq_init(&seq); + pevent_event_info(&seq, evsel->tp_format, &rec); + return seq.buffer; +} + +static void update_dynamic_len(struct hpp_dynamic_entry *hde, + struct hist_entry *he) +{ + char *str, *pos; + struct format_field *field = hde->field; + size_t namelen; + bool last = false; + + /* parse pretty print result and update max length */ + if (!he->trace_output) + he->trace_output = get_trace_output(he); + + namelen = strlen(field->name); + str = he->trace_output; + + while (str) { + pos = strchr(str, ' '); + if (pos == NULL) { + last = true; + pos = str + strlen(str); + } + + if (!strncmp(str, field->name, namelen)) { + size_t len; + + str += namelen + 1; + len = pos - str; + + if (len > hde->dynamic_len) + hde->dynamic_len = len; + break; + } + + if (last) + str = NULL; + else + str = pos + 1; + } +} + static int __sort__hde_header(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, struct perf_evsel *evsel __maybe_unused) { @@ -1594,7 +1650,10 @@ static int __sort__hde_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, { struct hpp_dynamic_entry *hde; size_t len = fmt->user_len; - struct trace_seq seq; + char *str, *pos; + struct format_field *field; + size_t namelen; + bool last = false; int ret; hde = container_of(fmt, struct hpp_dynamic_entry, hpp); @@ -1605,10 +1664,43 @@ static int __sort__hde_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, if (hists_to_evsel(he->hists) != hde->evsel) return scnprintf(hpp->buf, hpp->size, "%*.*s", len, len, "N/A"); - trace_seq_init(&seq); - pevent_print_field(&seq, he->raw_data, hde->field); - ret = scnprintf(hpp->buf, hpp->size, "%*.*s", len, len, seq.buffer); - trace_seq_destroy(&seq); + field = hde->field; + + namelen = strlen(field->name); + str = he->trace_output; + + while (str) { + pos = strchr(str, ' '); + if (pos == NULL) { + last = true; + pos = str + strlen(str); + } + + if (!strncmp(str, field->name, namelen)) { + str += namelen + 1; + str = strndup(str, pos - str); + + if (str == NULL) + return scnprintf(hpp->buf, hpp->size, + "%*.*s", len, len, "ERROR"); + break; + } + + if (last) + str = NULL; + else + str = pos + 1; + } + + if (str == NULL) { + struct trace_seq seq; + trace_seq_init(&seq); + pevent_print_field(&seq, he->raw_data, hde->field); + str = seq.buffer; + } + + ret = scnprintf(hpp->buf, hpp->size, "%*.*s", len, len, str); + free(str); return ret; } @@ -1638,6 +1730,9 @@ static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt, } else { offset = field->offset; size = field->size; + + update_dynamic_len(hde, a); + update_dynamic_len(hde, b); } return memcmp(a->raw_data + offset, b->raw_data + offset, size); diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 1a00f1eb9d21..f6d2a7e3e7f2 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -124,6 +124,7 @@ struct hist_entry { struct mem_info *mem_info; void *raw_data; u32 raw_size; + void *trace_output; struct callchain_root callchain[0]; /* must be last member */ }; From a34bb6a08d6020bde0475bc901793771858a1112 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 23 Dec 2015 02:07:04 +0900 Subject: [PATCH 08/59] perf tools: Add 'trace' sort key The 'trace' sort key is to show tracepoint event output using either print fmt or plugin. For example sched_switch event (using plugin) will show output like below: # perf record -e sched:sched_switch -a usleep 10 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.197 MB perf.data (69 samples) ] # $ perf report -s trace --stdio ... # Overhead Trace output # ........ ................................................... # 9.48% swapper/0:0 [120] R ==> transmission-gt:17773 [120] 9.48% transmission-gt:17773 [120] S ==> swapper/0:0 [120] 9.04% swapper/2:0 [120] R ==> transmission-gt:17773 [120] 8.92% transmission-gt:17773 [120] S ==> swapper/2:0 [120] 5.25% swapper/0:0 [120] R ==> kworker/0:1H:109 [100] 5.21% kworker/0:1H:109 [100] S ==> swapper/0:0 [120] 1.78% swapper/3:0 [120] R ==> transmission-gt:17773 [120] 1.78% transmission-gt:17773 [120] S ==> swapper/3:0 [120] 1.53% Xephyr:6524 [120] S ==> swapper/0:0 [120] 1.53% swapper/0:0 [120] R ==> Xephyr:6524 [120] 1.17% swapper/2:0 [120] R ==> irq/33-iwlwifi:233 [49] 1.13% irq/33-iwlwifi:233 [49] S ==> swapper/2:0 [120] Note that the 'trace' sort key works only for tracepoint events. If it's used to other type of events, just "N/A" will be printed. Suggested-and-acked-by: Jiri Olsa Signed-off-by: Namhyung Kim Tested-by: Arnaldo Carvalho de Melo Cc: Andi Kleen Cc: David Ahern Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Wang Nan Link: http://lkml.kernel.org/r/1450804030-29193-8-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/hist.h | 1 + tools/perf/util/sort.c | 76 +++++++++++++++++++++++++++++++++--------- tools/perf/util/sort.h | 1 + 3 files changed, 62 insertions(+), 16 deletions(-) diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 36439bfad059..15b22c563d30 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -52,6 +52,7 @@ enum hist_column { HISTC_MEM_IADDR_SYMBOL, HISTC_TRANSACTION, HISTC_CYCLES, + HISTC_TRACE, HISTC_NR_COLS, /* Last entry */ }; diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 22d28c7e0b01..db8476a9b103 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -445,6 +445,65 @@ struct sort_entry sort_socket = { .se_width_idx = HISTC_SOCKET, }; +/* --sort trace */ + +static char *get_trace_output(struct hist_entry *he) +{ + struct trace_seq seq; + struct perf_evsel *evsel; + struct pevent_record rec = { + .data = he->raw_data, + .size = he->raw_size, + }; + + evsel = hists_to_evsel(he->hists); + + trace_seq_init(&seq); + pevent_event_info(&seq, evsel->tp_format, &rec); + return seq.buffer; +} + +static int64_t +sort__trace_cmp(struct hist_entry *left, struct hist_entry *right) +{ + struct perf_evsel *evsel; + + evsel = hists_to_evsel(left->hists); + if (evsel->attr.type != PERF_TYPE_TRACEPOINT) + return 0; + + if (left->trace_output == NULL) + left->trace_output = get_trace_output(left); + if (right->trace_output == NULL) + right->trace_output = get_trace_output(right); + + hists__new_col_len(left->hists, HISTC_TRACE, strlen(left->trace_output)); + hists__new_col_len(right->hists, HISTC_TRACE, strlen(right->trace_output)); + + return strcmp(right->trace_output, left->trace_output); +} + +static int hist_entry__trace_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + struct perf_evsel *evsel; + + evsel = hists_to_evsel(he->hists); + if (evsel->attr.type != PERF_TYPE_TRACEPOINT) + return scnprintf(bf, size, "%-*.*s", width, width, "N/A"); + + if (he->trace_output == NULL) + he->trace_output = get_trace_output(he); + return repsep_snprintf(bf, size, "%-*.*s", width, width, he->trace_output); +} + +struct sort_entry sort_trace = { + .se_header = "Trace output", + .se_cmp = sort__trace_cmp, + .se_snprintf = hist_entry__trace_snprintf, + .se_width_idx = HISTC_TRACE, +}; + /* sort keys for branch stacks */ static int64_t @@ -1314,6 +1373,7 @@ static struct sort_dimension common_sort_dimensions[] = { DIM(SORT_LOCAL_WEIGHT, "local_weight", sort_local_weight), DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight), DIM(SORT_TRANSACTION, "transaction", sort_transaction), + DIM(SORT_TRACE, "trace", sort_trace), }; #undef DIM @@ -1560,22 +1620,6 @@ static int hde_width(struct hpp_dynamic_entry *hde) return hde->hpp.len; } -static char *get_trace_output(struct hist_entry *he) -{ - struct trace_seq seq; - struct perf_evsel *evsel; - struct pevent_record rec = { - .data = he->raw_data, - .size = he->raw_size, - }; - - evsel = hists_to_evsel(he->hists); - - trace_seq_init(&seq); - pevent_event_info(&seq, evsel->tp_format, &rec); - return seq.buffer; -} - static void update_dynamic_len(struct hpp_dynamic_entry *hde, struct hist_entry *he) { diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index f6d2a7e3e7f2..6b7590ade229 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -183,6 +183,7 @@ enum sort_type { SORT_LOCAL_WEIGHT, SORT_GLOBAL_WEIGHT, SORT_TRANSACTION, + SORT_TRACE, /* branch stack specific sort keys */ __SORT_BRANCH_STACK, From 053a3989e12fdf3be45c00ec1cb0ce09fba0ee4a Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 23 Dec 2015 02:07:05 +0900 Subject: [PATCH 09/59] perf report/top: Add --raw-trace option The --raw-trace option allows disabling pretty printing by the event's print_fmt or plugin. Besides that, each dynamic sort key now can receive a 'raw' suffix separated by '/' to ask for the raw trace of a specific field. $ perf report -s comm,kmem:kmalloc.gfp_flags ... # Overhead Command gfp_flags # ........ ....... ................... # 99.89% perf GFP_NOFS|GFP_ZERO 0.06% sleep GFP_KERNEL 0.03% perf GFP_KERNEL|GFP_ZERO 0.01% perf GFP_KERNEL Now $ perf report -s comm,kmem:kmalloc.gfp_flags --raw-trace or $ perf report -s comm,kmem:kmalloc.gfp_flags/raw ... # Overhead Command gfp_flags # ........ ....... .......... # 99.89% perf 32848 0.06% sleep 208 0.03% perf 32976 0.01% perf 208 Suggested-and-Acked-by: Jiri Olsa Signed-off-by: Namhyung Kim Tested-by: Arnaldo Carvalho de Melo Cc: Andi Kleen Cc: David Ahern Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Wang Nan Link: http://lkml.kernel.org/r/1450804030-29193-9-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-report.txt | 3 +++ tools/perf/Documentation/perf-top.txt | 3 +++ tools/perf/builtin-report.c | 2 ++ tools/perf/builtin-top.c | 2 ++ tools/perf/util/sort.c | 32 +++++++++++++++++++++--- tools/perf/util/symbol.h | 3 ++- 6 files changed, 41 insertions(+), 4 deletions(-) diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index dab99ed2b339..ae7cd91727f6 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -371,6 +371,9 @@ include::itrace.txt[] --socket-filter:: Only report the samples on the processor socket that match with this filter +--raw-trace:: + When displaying traceevent output, do not use print fmt or plugins. + include::callchain-overhead-calculation.txt[] SEE ALSO diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index 556cec09bf50..b0e60e17db38 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -230,6 +230,9 @@ Default is to monitor all CPUS. The various filters must be specified as a comma separated list: --branch-filter any_ret,u,k Note that this feature may not be available on all processors. +--raw-trace:: + When displaying traceevent output, do not use print fmt or plugins. + INTERACTIVE PROMPTING KEYS -------------------------- diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index ea53c816640a..f10c663af996 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -788,6 +788,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) "Show callgraph from reference event"), OPT_INTEGER(0, "socket-filter", &report.socket_filter, "only show processor socket that match with this filter"), + OPT_BOOLEAN(0, "raw-trace", &symbol_conf.raw_trace, + "Show raw trace event output (do not use print fmt or plugins)"), OPT_END() }; struct perf_data_file file = { diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 005825942441..bf01cbb0ef23 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1210,6 +1210,8 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused) OPT_CALLBACK('j', "branch-filter", &opts->branch_stack, "branch filter mask", "branch stack filter modes", parse_branch_stack), + OPT_BOOLEAN(0, "raw-trace", &symbol_conf.raw_trace, + "Show raw trace event output (do not use print fmt or plugins)"), OPT_END() }; const char * const top_usage[] = { diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index db8476a9b103..34776854626e 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -459,7 +459,12 @@ static char *get_trace_output(struct hist_entry *he) evsel = hists_to_evsel(he->hists); trace_seq_init(&seq); - pevent_event_info(&seq, evsel->tp_format, &rec); + if (symbol_conf.raw_trace) { + pevent_print_fields(&seq, he->raw_data, he->raw_size, + evsel->tp_format); + } else { + pevent_event_info(&seq, evsel->tp_format, &rec); + } return seq.buffer; } @@ -1596,6 +1601,7 @@ struct hpp_dynamic_entry { struct perf_evsel *evsel; struct format_field *field; unsigned dynamic_len; + bool raw_trace; }; static int hde_width(struct hpp_dynamic_entry *hde) @@ -1628,6 +1634,9 @@ static void update_dynamic_len(struct hpp_dynamic_entry *hde, size_t namelen; bool last = false; + if (hde->raw_trace) + return; + /* parse pretty print result and update max length */ if (!he->trace_output) he->trace_output = get_trace_output(he); @@ -1708,8 +1717,10 @@ static int __sort__hde_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, if (hists_to_evsel(he->hists) != hde->evsel) return scnprintf(hpp->buf, hpp->size, "%*.*s", len, len, "N/A"); - field = hde->field; + if (hde->raw_trace) + goto raw_field; + field = hde->field; namelen = strlen(field->name); str = he->trace_output; @@ -1738,6 +1749,7 @@ static int __sort__hde_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, if (str == NULL) { struct trace_seq seq; +raw_field: trace_seq_init(&seq); pevent_print_field(&seq, he->raw_data, hde->field); str = seq.buffer; @@ -1818,10 +1830,11 @@ __alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field) static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok) { - char *str, *event_name, *field_name; + char *str, *event_name, *field_name, *raw_opt; struct perf_evsel *evsel, *pos; struct format_field *field; struct hpp_dynamic_entry *hde; + bool raw_trace = symbol_conf.raw_trace; int ret = 0; if (evlist == NULL) @@ -1839,6 +1852,18 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok) } *field_name++ = '\0'; + raw_opt = strchr(field_name, '/'); + if (raw_opt) { + *raw_opt++ = '\0'; + + if (strcmp(raw_opt, "raw")) { + pr_err("Unsupported field option %s\n", raw_opt); + ret = -EINVAL; + goto out; + } + raw_trace = true; + } + evsel = NULL; evlist__for_each(evlist, pos) { if (!strcmp(pos->name, event_name)) { @@ -1872,6 +1897,7 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok) ret = -ENOMEM; goto out; } + hde->raw_trace = raw_trace; perf_hpp__register_sort_field(&hde->hpp); diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index 857f707ac12b..ccd1caa40e11 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -109,7 +109,8 @@ struct symbol_conf { branch_callstack, has_filter, show_ref_callgraph, - hide_unresolved; + hide_unresolved, + raw_trace; const char *vmlinux_name, *kallsyms_name, *source_prefix, From 5d0cff93bb7aa85349230d4e29902b2648640c53 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 23 Dec 2015 02:07:06 +0900 Subject: [PATCH 10/59] perf tools: Support shortcuts for events in dynamic sort keys The dynamic sort key requires event name but specifying full event name is rather inconvenient. This patch adds more ways to identify the event in a more compact way. 1. If session has just one event, event name can be omitted. 2. Events can be accessed by index preceded by a percent sign. 3. A part of the name can be used, if it's not ambiguous. The partial name should not contain ':' in it. 4. Full system + event name is still used, it should contain ':'. So in the below example all does same thing: $ perf record -e sched:sched_switch -a sleep 1 $ perf report -s next_pid,next_comm $ perf report -s %1.next_pid,%1.next_comm $ perf report -s switch.next_pid,switch.next_comm $ perf report -s sched:sched_switch.next_pid,sched:sched_switch.next_comm Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Andi Kleen Cc: David Ahern Cc: Frederic Weisbecker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Wang Nan Link: http://lkml.kernel.org/r/1450804030-29193-10-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/sort.c | 107 +++++++++++++++++++++++++++++++++-------- 1 file changed, 87 insertions(+), 20 deletions(-) diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 34776854626e..f3a98c25fb8d 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1828,10 +1828,90 @@ __alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field) return hde; } +static int parse_field_name(char *str, char **event, char **field, char **opt) +{ + char *event_name, *field_name, *opt_name; + + event_name = str; + field_name = strchr(str, '.'); + + if (field_name) { + *field_name++ = '\0'; + } else { + event_name = NULL; + field_name = str; + } + + opt_name = strchr(field_name, '/'); + if (opt_name) + *opt_name++ = '\0'; + + *event = event_name; + *field = field_name; + *opt = opt_name; + + return 0; +} + +/* find match evsel using a given event name. The event name can be: + * 1. NULL - only valid for single event session + * 2. '%' + event index (e.g. '%1' for first event) + * 3. full event name (e.g. sched:sched_switch) + * 4. partial event name (should not contain ':') + */ +static struct perf_evsel *find_evsel(struct perf_evlist *evlist, char *event_name) +{ + struct perf_evsel *evsel = NULL; + struct perf_evsel *pos; + bool full_name; + + /* case 1 */ + if (event_name == NULL) { + if (evlist->nr_entries != 1) { + pr_debug("event name should be given\n"); + return NULL; + } + + return perf_evlist__first(evlist); + } + + /* case 2 */ + if (event_name[0] == '%') { + int nr = strtol(event_name+1, NULL, 0); + + if (nr > evlist->nr_entries) + return NULL; + + evsel = perf_evlist__first(evlist); + while (--nr > 0) + evsel = perf_evsel__next(evsel); + + return evsel; + } + + full_name = !!strchr(event_name, ':'); + evlist__for_each(evlist, pos) { + /* case 3 */ + if (full_name && !strcmp(pos->name, event_name)) + return pos; + /* case 4 */ + if (!full_name && strstr(pos->name, event_name)) { + if (evsel) { + pr_debug("'%s' event is ambiguous: it can be %s or %s\n", + event_name, evsel->name, pos->name); + return NULL; + } + evsel = pos; + } + } + + return evsel; +} + static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok) { - char *str, *event_name, *field_name, *raw_opt; - struct perf_evsel *evsel, *pos; + char *str, *event_name, *field_name, *opt_name; + struct perf_evsel *evsel; struct format_field *field; struct hpp_dynamic_entry *hde; bool raw_trace = symbol_conf.raw_trace; @@ -1844,34 +1924,21 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok) if (str == NULL) return -ENOMEM; - event_name = str; - field_name = strchr(str, '.'); - if (field_name == NULL) { + if (parse_field_name(str, &event_name, &field_name, &opt_name) < 0) { ret = -EINVAL; goto out; } - *field_name++ = '\0'; - raw_opt = strchr(field_name, '/'); - if (raw_opt) { - *raw_opt++ = '\0'; - - if (strcmp(raw_opt, "raw")) { - pr_err("Unsupported field option %s\n", raw_opt); + if (opt_name) { + if (strcmp(opt_name, "raw")) { + pr_debug("unsupported field option %s\n", opt_name); ret = -EINVAL; goto out; } raw_trace = true; } - evsel = NULL; - evlist__for_each(evlist, pos) { - if (!strcmp(pos->name, event_name)) { - evsel = pos; - break; - } - } - + evsel = find_evsel(evlist, event_name); if (evsel == NULL) { pr_debug("Cannot find event: %s\n", event_name); ret = -ENOENT; From 3b099bf5898ac1bf44d822f0bc15a7517e6fa117 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 23 Dec 2015 02:07:07 +0900 Subject: [PATCH 11/59] perf tools: Support '.*' dynamic sort key Support '*' character for field name to add all (non-common) fields as sort keys easily. $ perf report -s 'switch.*' --stdio ... # Overhead prev_comm prev_pid prev_prio prev_state next_comm next_pid next_prio # ........ ........... ......... ......... .......... ............ ........ ......... # 3.82% swapper/0 0 120 0 netctl-auto 18711 120 3.75% netctl-auto 18711 120 1 swapper/0 0 120 2.24% swapper/1 0 120 0 netctl-auto 18709 120 2.24% netctl-auto 18709 120 1 swapper/1 0 120 1.80% swapper/2 0 120 0 rcu_preempt 7 120 1.80% swapper/2 0 120 0 netctl-auto 18711 120 1.80% rcu_preempt 7 120 1 swapper/2 0 120 1.80% netctl-auto 18711 120 1 swapper/2 0 120 ... Suggested-and-acked-by: Jiri Olsa Signed-off-by: Namhyung Kim Tested-by: Arnaldo Carvalho de Melo Cc: Andi Kleen Cc: David Ahern Cc: Frederic Weisbecker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Wang Nan Link: http://lkml.kernel.org/r/1450804030-29193-11-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/sort.c | 49 +++++++++++++++++++++++++++++------------- 1 file changed, 34 insertions(+), 15 deletions(-) diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index f3a98c25fb8d..f6aef15a651d 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1908,12 +1908,27 @@ static struct perf_evsel *find_evsel(struct perf_evlist *evlist, char *event_nam return evsel; } +static int __dynamic_dimension__add(struct perf_evsel *evsel, + struct format_field *field, + bool raw_trace) +{ + struct hpp_dynamic_entry *hde; + + hde = __alloc_dynamic_entry(evsel, field); + if (hde == NULL) + return -ENOMEM; + + hde->raw_trace = raw_trace; + + perf_hpp__register_sort_field(&hde->hpp); + return 0; +} + static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok) { char *str, *event_name, *field_name, *opt_name; struct perf_evsel *evsel; struct format_field *field; - struct hpp_dynamic_entry *hde; bool raw_trace = symbol_conf.raw_trace; int ret = 0; @@ -1951,22 +1966,26 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok) goto out; } - field = pevent_find_any_field(evsel->tp_format, field_name); - if (field == NULL) { - pr_debug("Cannot find event field for %s.%s\n", - event_name, field_name); - ret = -ENOENT; - goto out; - } + if (!strcmp(field_name, "*")) { + field = evsel->tp_format->format.fields; - hde = __alloc_dynamic_entry(evsel, field); - if (hde == NULL) { - ret = -ENOMEM; - goto out; - } - hde->raw_trace = raw_trace; + while (field) { + ret = __dynamic_dimension__add(evsel, field, raw_trace); + if (ret < 0) + goto out; - perf_hpp__register_sort_field(&hde->hpp); + field = field->next; + } + } else { + field = pevent_find_any_field(evsel->tp_format, field_name); + if (field == NULL) { + pr_debug("Cannot find event field for %s.%s\n", + event_name, field_name); + return -ENOENT; + } + + ret = __dynamic_dimension__add(evsel, field, raw_trace); + } out: free(str); From 361459f163fa1ec7ff4700ec876c3b7ff5f36cc6 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 23 Dec 2015 02:07:08 +0900 Subject: [PATCH 12/59] perf tools: Skip dynamic fields not defined for current event When there are multiple events, each dynamic sort key is defined just for one event. In this case other events will always show "N/A" for those fields. But they are meaningless and consume precious screen width. Let's skip those undefined dynamic fields. $ perf record -e kmem:kmalloc,kmem:kfree -a sleep 1 $ perf report -s 'comm,kmalloc.*' --stdio # To display the perf.data header info, please use --header/--header-only options. # # # Total Lost Samples: 0 # # Samples: 20K of event 'kmem:kmalloc' # Event count (approx.): 20533 # # Overhead Command call_site ptr bytes_req bytes_alloc gfp_flags # ........ ....... .................. .................. ......... ........... ................... # 99.89% perf ffffffffa01d4396 0xffff8803ffb79720 96 96 GFP_NOFS|GFP_ZERO 0.06% sleep ffffffff8114e1cd 0xffff8803d228a000 4096 4096 GFP_KERNEL 0.03% perf ffffffff811d6ae6 0xffff8803f7678f00 240 256 GFP_KERNEL|GFP_ZERO 0.00% perf ffffffff812263c1 0xffff880406172380 128 128 GFP_KERNEL 0.00% perf ffffffff812264b9 0xffff8803ffac1600 504 512 GFP_KERNEL 0.00% perf ffffffff81226634 0xffff880401dc5280 28 32 GFP_KERNEL 0.00% sleep ffffffff81226da9 0xffff8803ffac3a00 392 512 GFP_KERNEL # Samples: 20K of event 'kmem:kfree' # Event count (approx.): 20597 # # Overhead Command # ........ .............. # 99.63% perf 0.14% sleep 0.11% irq/36-iwlwifi 0.11% kworker/u16:0 0.01% Xorg 0.00% firefox Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Andi Kleen Cc: David Ahern Cc: Frederic Weisbecker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Wang Nan Link: http://lkml.kernel.org/r/1450804030-29193-12-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/ui/browsers/hists.c | 7 ++++--- tools/perf/ui/gtk/hists.c | 4 ++-- tools/perf/ui/hist.c | 2 +- tools/perf/ui/stdio/hist.c | 6 +++--- tools/perf/util/hist.c | 2 +- tools/perf/util/hist.h | 14 ++++++++++++-- tools/perf/util/sort.c | 20 ++++++++++++++------ 7 files changed, 37 insertions(+), 18 deletions(-) diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index ec331969b7d7..901d481e6cea 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -1041,7 +1041,8 @@ static int hist_browser__show_entry(struct hist_browser *browser, hist_browser__gotorc(browser, row, 0); perf_hpp__for_each_format(fmt) { - if (perf_hpp__should_skip(fmt) || column++ < browser->b.horiz_scroll) + if (perf_hpp__should_skip(fmt, entry->hists) || + column++ < browser->b.horiz_scroll) continue; if (current_entry && browser->b.navkeypressed) { @@ -1144,7 +1145,7 @@ static int hists_browser__scnprintf_headers(struct hist_browser *browser, char * } perf_hpp__for_each_format(fmt) { - if (perf_hpp__should_skip(fmt) || column++ < browser->b.horiz_scroll) + if (perf_hpp__should_skip(fmt, hists) || column++ < browser->b.horiz_scroll) continue; ret = fmt->header(fmt, &dummy_hpp, hists_to_evsel(hists)); @@ -1414,7 +1415,7 @@ static int hist_browser__fprintf_entry(struct hist_browser *browser, printed += fprintf(fp, "%c ", folded_sign); perf_hpp__for_each_format(fmt) { - if (perf_hpp__should_skip(fmt)) + if (perf_hpp__should_skip(fmt, he->hists)) continue; if (!first) { diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c index 467717276ab6..0f8dcfdfb10f 100644 --- a/tools/perf/ui/gtk/hists.c +++ b/tools/perf/ui/gtk/hists.c @@ -318,7 +318,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, col_idx = 0; perf_hpp__for_each_format(fmt) { - if (perf_hpp__should_skip(fmt)) + if (perf_hpp__should_skip(fmt, hists)) continue; /* @@ -368,7 +368,7 @@ static void perf_gtk__show_hists(GtkWidget *window, struct hists *hists, col_idx = 0; perf_hpp__for_each_format(fmt) { - if (perf_hpp__should_skip(fmt)) + if (perf_hpp__should_skip(fmt, h->hists)) continue; if (fmt->color) diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index 5029ba2b55af..8263c0eb9fb5 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -619,7 +619,7 @@ unsigned int hists__sort_list_width(struct hists *hists) struct perf_hpp dummy_hpp; perf_hpp__for_each_format(fmt) { - if (perf_hpp__should_skip(fmt)) + if (perf_hpp__should_skip(fmt, hists)) continue; if (first) diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c index 7ebc661be267..387110d50b00 100644 --- a/tools/perf/ui/stdio/hist.c +++ b/tools/perf/ui/stdio/hist.c @@ -385,7 +385,7 @@ static int hist_entry__snprintf(struct hist_entry *he, struct perf_hpp *hpp) return 0; perf_hpp__for_each_format(fmt) { - if (perf_hpp__should_skip(fmt)) + if (perf_hpp__should_skip(fmt, he->hists)) continue; /* @@ -464,7 +464,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, fprintf(fp, "# "); perf_hpp__for_each_format(fmt) { - if (perf_hpp__should_skip(fmt)) + if (perf_hpp__should_skip(fmt, hists)) continue; if (!first) @@ -490,7 +490,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows, perf_hpp__for_each_format(fmt) { unsigned int i; - if (perf_hpp__should_skip(fmt)) + if (perf_hpp__should_skip(fmt, hists)) continue; if (!first) diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index fdb97e16a8c3..afc9b8f1b36c 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -1112,7 +1112,7 @@ static int hist_entry__sort(struct hist_entry *a, struct hist_entry *b) int64_t cmp = 0; perf_hpp__for_each_sort_list(fmt) { - if (perf_hpp__should_skip(fmt)) + if (perf_hpp__should_skip(fmt, a->hists)) continue; cmp = fmt->sort(fmt, a, b); diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index 15b22c563d30..cb8f37349972 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -262,10 +262,20 @@ void perf_hpp__append_sort_keys(void); bool perf_hpp__is_sort_entry(struct perf_hpp_fmt *format); bool perf_hpp__same_sort_entry(struct perf_hpp_fmt *a, struct perf_hpp_fmt *b); +bool perf_hpp__is_dynamic_entry(struct perf_hpp_fmt *format); +bool perf_hpp__defined_dynamic_entry(struct perf_hpp_fmt *fmt, struct hists *hists); -static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format) +static inline bool perf_hpp__should_skip(struct perf_hpp_fmt *format, + struct hists *hists) { - return format->elide; + if (format->elide) + return true; + + if (perf_hpp__is_dynamic_entry(format) && + !perf_hpp__defined_dynamic_entry(format, hists)) + return true; + + return false; } void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists); diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index f6aef15a651d..fd56223793a8 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1698,6 +1698,15 @@ static int __sort__hde_width(struct perf_hpp_fmt *fmt, return len; } +bool perf_hpp__defined_dynamic_entry(struct perf_hpp_fmt *fmt, struct hists *hists) +{ + struct hpp_dynamic_entry *hde; + + hde = container_of(fmt, struct hpp_dynamic_entry, hpp); + + return hists_to_evsel(hists) == hde->evsel; +} + static int __sort__hde_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, struct hist_entry *he) { @@ -1714,9 +1723,6 @@ static int __sort__hde_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp, if (!len) len = hde_width(hde); - if (hists_to_evsel(he->hists) != hde->evsel) - return scnprintf(hpp->buf, hpp->size, "%*.*s", len, len, "N/A"); - if (hde->raw_trace) goto raw_field; @@ -1769,9 +1775,6 @@ static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt, hde = container_of(fmt, struct hpp_dynamic_entry, hpp); - if (hists_to_evsel(a->hists) != hde->evsel) - return 0; - field = hde->field; if (field->flags & FIELD_IS_DYNAMIC) { unsigned long long dyn; @@ -1794,6 +1797,11 @@ static int64_t __sort__hde_cmp(struct perf_hpp_fmt *fmt, return memcmp(a->raw_data + offset, b->raw_data + offset, size); } +bool perf_hpp__is_dynamic_entry(struct perf_hpp_fmt *fmt) +{ + return fmt->cmp == __sort__hde_cmp; +} + static struct hpp_dynamic_entry * __alloc_dynamic_entry(struct perf_evsel *evsel, struct format_field *field) { From 2e422fd1e4b0a1c0ca11d360be2147c87911dd1a Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 23 Dec 2015 02:07:09 +0900 Subject: [PATCH 13/59] perf tools: Add 'trace_fields' dynamic sort key The 'trace_fields' sort key is similar as 'trace' sort key, but it shows each fields separately. Each event will get different columns as their fields. $ perf report -s trace_fields --stdio # To display the perf.data header info, please use --header/--header-only options. # # # Total Lost Samples: 0 # # Samples: 20K of event 'kmem:kmalloc' # Event count (approx.): 20533 # # Overhead Command call_site ptr bytes_req bytes_alloc gfp_flags # ........ ....... .................. .................. ......... ........... ................... # 99.89% perf ffffffffa01d4396 0xffff8803ffb79720 96 96 GFP_NOFS|GFP_ZERO 0.06% sleep ffffffff8114e1cd 0xffff8803d228a000 4096 4096 GFP_KERNEL 0.03% perf ffffffff811d6ae6 0xffff8803f7678f00 240 256 GFP_KERNEL|GFP_ZERO 0.00% perf ffffffff812263c1 0xffff880406172380 128 128 GFP_KERNEL 0.00% perf ffffffff812264b9 0xffff8803ffac1600 504 512 GFP_KERNEL 0.00% perf ffffffff81226634 0xffff880401dc5280 28 32 GFP_KERNEL 0.00% sleep ffffffff81226da9 0xffff8803ffac3a00 392 512 GFP_KERNEL # Samples: 20K of event 'kmem:kfree' # Event count (approx.): 20597 # # Overhead call_site ptr # ........ .................. .................. # 99.58% ffffffffa01d85ad 0xffff8803ffb79720 0.07% ffffffff81443f5c 0xffff8803f7669400 0.02% ffffffff811d5753 0xffff8803f7678f00 0.01% ffffffff81443f5c 0xffff8803f766be00 0.01% ffffffff8114e359 0xffff8803d228a000 0.01% ffffffff81443f5c 0xffff8800d156dc00 0.01% ffffffff81443f5c 0xffff8803f7669400 0.01% ffffffff8114e359 0xffff8803d228a000 0.01% ffffffff8114e359 0xffff8803d228a000 0.01% ffffffff8114e359 0xffff8803d228a000 Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Andi Kleen Cc: David Ahern Cc: Frederic Weisbecker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Wang Nan Link: http://lkml.kernel.org/r/1450804030-29193-13-git-send-email-namhyung@kernel.org [ Combined with "perf tools: Fix segfault when using -s trace_fields" ] Link: http://lkml.kernel.org/r/1451991518-25673-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/sort.c | 47 ++++++++++++++++++++++++++++++++++-------- 1 file changed, 38 insertions(+), 9 deletions(-) diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index fd56223793a8..79aa71d26d9f 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1932,6 +1932,38 @@ static int __dynamic_dimension__add(struct perf_evsel *evsel, return 0; } +static int add_evsel_fields(struct perf_evsel *evsel, bool raw_trace) +{ + int ret; + struct format_field *field; + + field = evsel->tp_format->format.fields; + while (field) { + ret = __dynamic_dimension__add(evsel, field, raw_trace); + if (ret < 0) + return ret; + + field = field->next; + } + return 0; +} + +static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace) +{ + int ret; + struct perf_evsel *evsel; + + evlist__for_each(evlist, evsel) { + if (evsel->attr.type != PERF_TYPE_TRACEPOINT) + continue; + + ret = add_evsel_fields(evsel, raw_trace); + if (ret < 0) + return ret; + } + return 0; +} + static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok) { char *str, *event_name, *field_name, *opt_name; @@ -1961,6 +1993,11 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok) raw_trace = true; } + if (!strcmp(field_name, "trace_fields")) { + ret = add_all_dynamic_fields(evlist, raw_trace); + goto out; + } + evsel = find_evsel(evlist, event_name); if (evsel == NULL) { pr_debug("Cannot find event: %s\n", event_name); @@ -1975,15 +2012,7 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok) } if (!strcmp(field_name, "*")) { - field = evsel->tp_format->format.fields; - - while (field) { - ret = __dynamic_dimension__add(evsel, field, raw_trace); - if (ret < 0) - goto out; - - field = field->next; - } + ret = add_evsel_fields(evsel, raw_trace); } else { field = pevent_find_any_field(evsel->tp_format, field_name); if (field == NULL) { From d49dadea78624353d1df660efb49f187bd5c5971 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Wed, 23 Dec 2015 02:07:10 +0900 Subject: [PATCH 14/59] perf tools: Make 'trace' or 'trace_fields' sort key default for tracepoint events When an evlist contains tracepoint events only, use 'trace' sort key as default. If --raw-trace option was given, use 'trace_fields' instead. This will make users more convenient to see trace result. Suggested-and-Acked-by: Jiri Olsa Signed-off-by: Namhyung Kim Tested-by: Arnaldo Carvalho de Melo Cc: Andi Kleen Cc: David Ahern Cc: Frederic Weisbecker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Wang Nan Link: http://lkml.kernel.org/r/1450804030-29193-14-git-send-email-namhyung@kernel.org [ Check evlist in get_default_sort_order() fixing a segfault in 'perf test hists' reported by Jiri Olsa ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/sort.c | 30 +++++++++++++++++++++++++----- tools/perf/util/sort.h | 1 + 2 files changed, 26 insertions(+), 5 deletions(-) diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 79aa71d26d9f..4b4b1c5cccef 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -15,6 +15,7 @@ const char default_branch_sort_order[] = "comm,dso_from,symbol_from,symbol_to,cy const char default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked"; const char default_top_sort_order[] = "dso,symbol"; const char default_diff_sort_order[] = "dso,symbol"; +const char default_tracepoint_sort_order[] = "trace"; const char *sort_order; const char *field_order; regex_t ignore_callees_regex; @@ -2171,7 +2172,7 @@ static int sort_dimension__add(const char *tok, return -ESRCH; } -static const char *get_default_sort_order(void) +static const char *get_default_sort_order(struct perf_evlist *evlist) { const char *default_sort_orders[] = { default_sort_order, @@ -2179,14 +2180,33 @@ static const char *get_default_sort_order(void) default_mem_sort_order, default_top_sort_order, default_diff_sort_order, + default_tracepoint_sort_order, }; + bool use_trace = true; + struct perf_evsel *evsel; BUG_ON(sort__mode >= ARRAY_SIZE(default_sort_orders)); + if (evlist == NULL) + goto out_no_evlist; + + evlist__for_each(evlist, evsel) { + if (evsel->attr.type != PERF_TYPE_TRACEPOINT) { + use_trace = false; + break; + } + } + + if (use_trace) { + sort__mode = SORT_MODE__TRACEPOINT; + if (symbol_conf.raw_trace) + return "trace_fields"; + } +out_no_evlist: return default_sort_orders[sort__mode]; } -static int setup_sort_order(void) +static int setup_sort_order(struct perf_evlist *evlist) { char *new_sort_order; @@ -2207,7 +2227,7 @@ static int setup_sort_order(void) * because it's checked over the rest of the code. */ if (asprintf(&new_sort_order, "%s,%s", - get_default_sort_order(), sort_order + 1) < 0) { + get_default_sort_order(evlist), sort_order + 1) < 0) { error("Not enough memory to set up --sort"); return -ENOMEM; } @@ -2222,7 +2242,7 @@ static int __setup_sorting(struct perf_evlist *evlist) const char *sort_keys; int ret = 0; - ret = setup_sort_order(); + ret = setup_sort_order(evlist); if (ret) return ret; @@ -2236,7 +2256,7 @@ static int __setup_sorting(struct perf_evlist *evlist) return 0; } - sort_keys = get_default_sort_order(); + sort_keys = get_default_sort_order(evlist); } str = strdup(sort_keys); diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index 6b7590ade229..dec536b6ab3d 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -167,6 +167,7 @@ enum sort_mode { SORT_MODE__MEMORY, SORT_MODE__TOP, SORT_MODE__DIFF, + SORT_MODE__TRACEPOINT, }; enum sort_type { From d0018b495c0429af3efc1b54f16d291a9fa8b4be Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 23 Dec 2015 18:58:30 +0100 Subject: [PATCH 15/59] tools build feature: Fix feature_check_display_code typo This function is cursed.. ;-) Signed-off-by: Jiri Olsa Tested-by: Wang Nan Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Zefan Li Cc: pi3orama Link: http://lkml.kernel.org/r/1450893514-9158-2-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/build/Makefile.feature | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index 6c0519de765d..a8b4befdef7e 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -143,7 +143,7 @@ ifneq ("$(FEATURE_DUMP)","$(FEATURE_DUMP_FILE)") endif feature_display_check = $(eval $(feature_check_display_code)) -define feature_display_check_code +define feature_check_display_code ifneq ($(feature-$(1)), 1) feature_display := 1 endif From 76ee2ff342743e57cb6dc059d0aba90e0c4c9bfc Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 23 Dec 2015 18:58:31 +0100 Subject: [PATCH 16/59] tools build feature: Move dwarf post unwind choice output into perf We decide what dwarf unwind to choose way after the Makefile.feature makefile is included. The $(dwarf-post-unwind) is not even set at that time. For the same reason it was never included in FEATURE-DUMP file. Moving it into perf VF=1 verbose display. $ make VF=1 BUILD: Doing 'make -j4' parallel build Auto-detecting system features: ... dwarf: [ on ] ... ... LIBUNWIND_DIR: ... LIBDW_DIR: ... DWARF post unwind library: libunwind ... Signed-off-by: Jiri Olsa Tested-by: Wang Nan Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Zefan Li Cc: pi3orama Link: http://lkml.kernel.org/r/1450893514-9158-3-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/build/Makefile.feature | 9 --------- tools/perf/config/Makefile | 4 ++++ 2 files changed, 4 insertions(+), 9 deletions(-) diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index a8b4befdef7e..20753124c8f4 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -126,10 +126,6 @@ FEATURE_DUMP_FILENAME = $(OUTPUT)FEATURE-DUMP$(FEATURE_USER) FEATURE_DUMP := $(foreach feat,$(FEATURE_DISPLAY),feature-$(feat)($(feature-$(feat)))) FEATURE_DUMP_FILE := $(shell touch $(FEATURE_DUMP_FILENAME); cat $(FEATURE_DUMP_FILENAME)) -ifeq ($(dwarf-post-unwind),1) - FEATURE_DUMP += dwarf-post-unwind($(dwarf-post-unwind-text)) -endif - # The $(feature_display) controls the default detection message # output. It's set if: # - detected features differes from stored features from @@ -160,11 +156,6 @@ ifeq ($(feature_display),1) $(info ) $(info Auto-detecting system features:) $(foreach feat,$(FEATURE_DISPLAY),$(call feature_print_status,$(feat),)) - - ifeq ($(dwarf-post-unwind),1) - $(call feature_print_text,"DWARF post unwind library", $(dwarf-post-unwind-text)) - endif - ifneq ($(feature_verbose),1) $(info ) endif diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index a5524179d26e..18b2f96d0941 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -751,6 +751,10 @@ ifeq ($(VF),1) $(call print_var,sysconfdir) $(call print_var,LIBUNWIND_DIR) $(call print_var,LIBDW_DIR) + + ifeq ($(dwarf-post-unwind),1) + $(call feature_print_text,"DWARF post unwind library", $(dwarf-post-unwind-text)) + endif $(info ) endif From c6a5f88f335ec43d2850d62bc4924f719d265670 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 23 Dec 2015 18:58:32 +0100 Subject: [PATCH 17/59] tools build feature: Introduce feature_assign macro The feature_assign macro generates feature value assignment for name, like: $(call feature_assign,dwarf) == feature-dwarf=1 This will be used more in following patches. Signed-off-by: Jiri Olsa Tested-by: Wang Nan Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Zefan Li Cc: pi3orama Link: http://lkml.kernel.org/r/1450893514-9158-4-git-send-email-jolsa@kernel.org [ Rename it to feature_assign, the original shorter name was misleading, to say the least ;-) ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/build/Makefile.feature | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index 20753124c8f4..b1b262eb5bea 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -122,8 +122,14 @@ define feature_print_text_code MSG = $(shell printf '...%30s: %s' $(1) $(2)) endef +# +# generates feature value assignment for name, like: +# $(call feature_assign,dwarf) == feature-dwarf=1 +# +feature_assign = feature-$(1)=$(feature-$(1)) + FEATURE_DUMP_FILENAME = $(OUTPUT)FEATURE-DUMP$(FEATURE_USER) -FEATURE_DUMP := $(foreach feat,$(FEATURE_DISPLAY),feature-$(feat)($(feature-$(feat)))) +FEATURE_DUMP := $(foreach feat,$(FEATURE_DISPLAY),$(call feature_assign,$(feat))) FEATURE_DUMP_FILE := $(shell touch $(FEATURE_DUMP_FILENAME); cat $(FEATURE_DUMP_FILENAME)) # The $(feature_display) controls the default detection message From 936d120d5f6406377e622da3167cafc811d053ea Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 23 Dec 2015 18:58:33 +0100 Subject: [PATCH 18/59] tools build feature: Use value assignment form for FEATURE-DUMP file Changing the contents of the FEATURE-DUMP file, so it looks like: feature-backtrace=1 feature-dwarf=0 feature-fortify-source=1 feature-sync-compare-and-swap=0 This way it could get included in sub projects, so they won't be forced to redo features detection. Also now storing the complete set of features. Signed-off-by: Jiri Olsa Tested-by: Wang Nan Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Zefan Li Cc: pi3orama Link: http://lkml.kernel.org/r/1450893514-9158-5-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/build/Makefile.feature | 26 +++++++++++++++++++++----- 1 file changed, 21 insertions(+), 5 deletions(-) diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature index b1b262eb5bea..02db3cdff20f 100644 --- a/tools/build/Makefile.feature +++ b/tools/build/Makefile.feature @@ -129,8 +129,24 @@ endef feature_assign = feature-$(1)=$(feature-$(1)) FEATURE_DUMP_FILENAME = $(OUTPUT)FEATURE-DUMP$(FEATURE_USER) -FEATURE_DUMP := $(foreach feat,$(FEATURE_DISPLAY),$(call feature_assign,$(feat))) -FEATURE_DUMP_FILE := $(shell touch $(FEATURE_DUMP_FILENAME); cat $(FEATURE_DUMP_FILENAME)) +FEATURE_DUMP := $(shell touch $(FEATURE_DUMP_FILENAME); cat $(FEATURE_DUMP_FILENAME)) + +feature_dump_check = $(eval $(feature_dump_check_code)) +define feature_dump_check_code + ifeq ($(findstring $(1),$(FEATURE_DUMP)),) + $(2) := 1 + endif +endef + +# +# First check if any test from FEATURE_DISPLAY +# and set feature_display := 1 if it does +$(foreach feat,$(FEATURE_DISPLAY),$(call feature_dump_check,$(call feature_assign,$(feat)),feature_display)) + +# +# Now also check if any other test changed, +# so we force FEATURE-DUMP generation +$(foreach feat,$(FEATURE_TESTS),$(call feature_dump_check,$(call feature_assign,$(feat)),feature_dump_changed)) # The $(feature_display) controls the default detection message # output. It's set if: @@ -139,9 +155,9 @@ FEATURE_DUMP_FILE := $(shell touch $(FEATURE_DUMP_FILENAME); cat $(FEATURE_DUMP_ # - one of the $(FEATURE_DISPLAY) is not detected # - VF is enabled -ifneq ("$(FEATURE_DUMP)","$(FEATURE_DUMP_FILE)") - $(shell echo "$(FEATURE_DUMP)" > $(FEATURE_DUMP_FILENAME)) - feature_display := 1 +ifeq ($(feature_dump_changed),1) + $(shell rm -f $(FEATURE_DUMP_FILENAME)) + $(foreach feat,$(FEATURE_TESTS),$(shell echo "$(call feature_assign,$(feat))" >> $(FEATURE_DUMP_FILENAME))) endif feature_display_check = $(eval $(feature_check_display_code)) From 58683600dfe377c883eb8217b5a9bfcfe231b3ff Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 23 Dec 2015 18:58:34 +0100 Subject: [PATCH 19/59] perf build: Use FEATURE-DUMP in bpf subproject Using FEATURE-DUMP in bpf subproject for features detection in case bpf is built via perf. Keeping the current features detection otherwise. Signed-off-by: Jiri Olsa Tested-by: Wang Nan Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Zefan Li Cc: pi3orama Link: http://lkml.kernel.org/r/1450893514-9158-6-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/bpf/Makefile | 4 ++++ tools/perf/Makefile.perf | 2 +- 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 636e3ddb93a1..919b71780710 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -80,7 +80,11 @@ endif endif ifeq ($(check_feat),1) +ifeq ($(FEATURES_DUMP),) include $(srctree)/tools/build/Makefile.feature +else +include $(FEATURES_DUMP) +endif endif export prefix libdir src obj diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 569fcf022531..404e3b1c4e31 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -436,7 +436,7 @@ $(LIBAPI)-clean: $(Q)$(MAKE) -C $(LIB_DIR) O=$(OUTPUT) clean >/dev/null $(LIBBPF): fixdep FORCE - $(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) $(OUTPUT)libbpf.a + $(Q)$(MAKE) -C $(BPF_DIR) O=$(OUTPUT) $(OUTPUT)libbpf.a FEATURES_DUMP=$(realpath $(OUTPUT)FEATURE-DUMP) $(LIBBPF)-clean: $(call QUIET_CLEAN, libbpf) From 9735be24ec086fbccee321471cc21dedefa956a6 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 5 Jan 2016 19:58:35 +0900 Subject: [PATCH 20/59] perf tools: Add all matching dynamic sort keys for field name When a perf.data file has multiple events, it's likely to be similar (tracepoint) events. In that case, they might have same field name so add all of them to sort keys instead of bailing out. Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Cc: Andi Kleen Cc: David Ahern Cc: Frederic Weisbecker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Wang Nan Link: http://lkml.kernel.org/r/1451991518-25673-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/sort.c | 48 ++++++++++++++++++++++++++++-------------- 1 file changed, 32 insertions(+), 16 deletions(-) diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 4b4b1c5cccef..04e2a5cb19e3 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -1863,10 +1863,9 @@ static int parse_field_name(char *str, char **event, char **field, char **opt) } /* find match evsel using a given event name. The event name can be: - * 1. NULL - only valid for single event session - * 2. '%' + event index (e.g. '%1' for first event) - * 3. full event name (e.g. sched:sched_switch) - * 4. partial event name (should not contain ':') + * 1. '%' + event index (e.g. '%1' for first event) + * 2. full event name (e.g. sched:sched_switch) + * 3. partial event name (should not contain ':') */ static struct perf_evsel *find_evsel(struct perf_evlist *evlist, char *event_name) { @@ -1875,16 +1874,6 @@ static struct perf_evsel *find_evsel(struct perf_evlist *evlist, char *event_nam bool full_name; /* case 1 */ - if (event_name == NULL) { - if (evlist->nr_entries != 1) { - pr_debug("event name should be given\n"); - return NULL; - } - - return perf_evlist__first(evlist); - } - - /* case 2 */ if (event_name[0] == '%') { int nr = strtol(event_name+1, NULL, 0); @@ -1900,10 +1889,10 @@ static struct perf_evsel *find_evsel(struct perf_evlist *evlist, char *event_nam full_name = !!strchr(event_name, ':'); evlist__for_each(evlist, pos) { - /* case 3 */ + /* case 2 */ if (full_name && !strcmp(pos->name, event_name)) return pos; - /* case 4 */ + /* case 3 */ if (!full_name && strstr(pos->name, event_name)) { if (evsel) { pr_debug("'%s' event is ambiguous: it can be %s or %s\n", @@ -1965,6 +1954,28 @@ static int add_all_dynamic_fields(struct perf_evlist *evlist, bool raw_trace) return 0; } +static int add_all_matching_fields(struct perf_evlist *evlist, + char *field_name, bool raw_trace) +{ + int ret = -ESRCH; + struct perf_evsel *evsel; + struct format_field *field; + + evlist__for_each(evlist, evsel) { + if (evsel->attr.type != PERF_TYPE_TRACEPOINT) + continue; + + field = pevent_find_any_field(evsel->tp_format, field_name); + if (field == NULL) + continue; + + ret = __dynamic_dimension__add(evsel, field, raw_trace); + if (ret < 0) + break; + } + return ret; +} + static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok) { char *str, *event_name, *field_name, *opt_name; @@ -1999,6 +2010,11 @@ static int add_dynamic_entry(struct perf_evlist *evlist, const char *tok) goto out; } + if (event_name == NULL) { + ret = add_all_matching_fields(evlist, field_name, raw_trace); + goto out; + } + evsel = find_evsel(evlist, event_name); if (evsel == NULL) { pr_debug("Cannot find event: %s\n", event_name); From 4c96bee03247c6eab27287fa66457a231b9fab79 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 5 Jan 2016 19:58:36 +0900 Subject: [PATCH 21/59] perf report: Add documentation for dynamic sort keys Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Cc: Andi Kleen Cc: David Ahern Cc: Frederic Weisbecker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Wang Nan Link: http://lkml.kernel.org/r/1451991518-25673-3-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-report.txt | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+) diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index ae7cd91727f6..8a301f6afb37 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -117,6 +117,30 @@ OPTIONS And default sort keys are changed to comm, dso_from, symbol_from, dso_to and symbol_to, see '--branch-stack'. + If the data file has tracepoint event(s), following (dynamic) sort keys + are also available: + trace, trace_fields, [.][/raw] + + - trace: pretty printed trace output in a single column + - trace_fields: fields in tracepoints in separate columns + - : optional event and field name for a specific field + + The last form consists of event and field names. If event name is + omitted, it searches all events for matching field name. The matched + field will be shown only for the event has the field. The event name + supports substring match so user doesn't need to specify full subsystem + and event name everytime. For example, 'sched:sched_switch' event can + be shortened to 'switch' as long as it's not ambiguous. Also event can + be specified by its index (starting from 1) preceded by the '%'. + So '%1' is the first event, '%2' is the second, and so on. + + The field name can have '/raw' suffix which disables pretty printing + and shows raw field value like hex numbers. The --raw-trace option + has the same effect for all dynamic sort keys. + + The default sort keys are changed to 'trace' if all events in the data + file are tracepoint. + -F:: --fields=:: Specify output field - multiple keys can be specified in CSV format. From 6db1a5c190d6abe416ea36aa28a6c53e0b3bbd5e Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 5 Jan 2016 22:09:05 +0100 Subject: [PATCH 22/59] perf stat record: Keep sample_type 0 for pipe session For pipe sessions we need to keep sample_type zero, because script's perf_evsel__check_attr is triggered by sample_type != 0, and the check would fail on stat session. I was tempted to keep it zero unconditionally, but the pipe session is sufficient. In perf.data session we are guarded by HEADER_STAT feature. Signed-off-by: Jiri Olsa Cc: David Ahern Cc: Kan Liang Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1452028152-26762-2-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 9805e03ab163..7f568244662b 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -184,11 +184,18 @@ static int create_perf_stat_counter(struct perf_evsel *evsel) * like tracepoints. Clear it up for counting. */ attr->sample_period = 0; + /* * But set sample_type to PERF_SAMPLE_IDENTIFIER, which should be harmless * while avoiding that older tools show confusing messages. + * + * However for pipe sessions we need to keep it zero, + * because script's perf_evsel__check_attr is triggered + * by attr->sample_type != 0, and we can't run it on + * stat sessions. */ - attr->sample_type = PERF_SAMPLE_IDENTIFIER; + if (!(STAT_RECORD && perf_stat.file.is_pipe)) + attr->sample_type = PERF_SAMPLE_IDENTIFIER; /* * Disabling all counters initially, they will be enabled From cfc8874a485992491b865dde64965bb7c18c26b5 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 5 Jan 2016 22:09:06 +0100 Subject: [PATCH 23/59] perf script: Process cpu/threads maps Adding processing of cpu/threads maps. Configuring session's evlist with these maps. Signed-off-by: Jiri Olsa Tested-by: Kan Liang Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1452028152-26762-3-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 67 +++++++++++++++++++++++++++++++++++++ 1 file changed, 67 insertions(+) diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index bcc3542d9df5..aa6d7cf87dab 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -18,7 +18,11 @@ #include "util/sort.h" #include "util/data.h" #include "util/auxtrace.h" +#include "util/cpumap.h" +#include "util/thread_map.h" +#include "util/stat.h" #include +#include "asm/bug.h" static char const *script_name; static char const *generate_script_lang; @@ -606,6 +610,9 @@ struct perf_script { bool show_task_events; bool show_mmap_events; bool show_switch_events; + bool allocated; + struct cpu_map *cpus; + struct thread_map *threads; }; static void process_event(struct perf_script *script __maybe_unused, union perf_event *event, @@ -1682,6 +1689,63 @@ static void script__setup_sample_type(struct perf_script *script) } } +static int set_maps(struct perf_script *script) +{ + struct perf_evlist *evlist = script->session->evlist; + + if (!script->cpus || !script->threads) + return 0; + + if (WARN_ONCE(script->allocated, "stats double allocation\n")) + return -EINVAL; + + perf_evlist__set_maps(evlist, script->cpus, script->threads); + + if (perf_evlist__alloc_stats(evlist, true)) + return -ENOMEM; + + script->allocated = true; + return 0; +} + +static +int process_thread_map_event(struct perf_tool *tool, + union perf_event *event, + struct perf_session *session __maybe_unused) +{ + struct perf_script *script = container_of(tool, struct perf_script, tool); + + if (script->threads) { + pr_warning("Extra thread map event, ignoring.\n"); + return 0; + } + + script->threads = thread_map__new_event(&event->thread_map); + if (!script->threads) + return -ENOMEM; + + return set_maps(script); +} + +static +int process_cpu_map_event(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_session *session __maybe_unused) +{ + struct perf_script *script = container_of(tool, struct perf_script, tool); + + if (script->cpus) { + pr_warning("Extra cpu map event, ignoring.\n"); + return 0; + } + + script->cpus = cpu_map__new_data(&event->cpu_map.data); + if (!script->cpus) + return -ENOMEM; + + return set_maps(script); +} + int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) { bool show_full_info = false; @@ -1710,6 +1774,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) .auxtrace_info = perf_event__process_auxtrace_info, .auxtrace = perf_event__process_auxtrace, .auxtrace_error = perf_event__process_auxtrace_error, + .thread_map = process_thread_map_event, + .cpu_map = process_cpu_map_event, .ordered_events = true, .ordering_requires_timestamps = true, }, @@ -2063,6 +2129,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) flush_scripting(); out_delete: + perf_evlist__free_stats(session->evlist); perf_session__delete(session); if (script_started) From 91a2c3d54fd4b5be4e25acc1d8c1cc9a28319774 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 5 Jan 2016 22:09:07 +0100 Subject: [PATCH 24/59] perf script: Process stat config event Adding processing of stat config event and initialize stat_config object. Signed-off-by: Jiri Olsa Tested-by: Kan Liang Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1452028152-26762-4-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index aa6d7cf87dab..a90bc0b81e70 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -36,6 +36,7 @@ static bool print_flags; static bool nanosecs; static const char *cpu_list; static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); +static struct perf_stat_config stat_config; unsigned int scripting_max_stack = PERF_MAX_STACK_DEPTH; @@ -1689,6 +1690,14 @@ static void script__setup_sample_type(struct perf_script *script) } } +static int process_stat_config_event(struct perf_tool *tool __maybe_unused, + union perf_event *event, + struct perf_session *session __maybe_unused) +{ + perf_event__read_stat_config(&stat_config, &event->stat_config); + return 0; +} + static int set_maps(struct perf_script *script) { struct perf_evlist *evlist = script->session->evlist; @@ -1774,6 +1783,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) .auxtrace_info = perf_event__process_auxtrace_info, .auxtrace = perf_event__process_auxtrace, .auxtrace_error = perf_event__process_auxtrace_error, + .stat_config = process_stat_config_event, .thread_map = process_thread_map_event, .cpu_map = process_cpu_map_event, .ordered_events = true, From 8058a30ce174060a3c8156dc87b4d4ae39e8281b Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 5 Jan 2016 22:09:08 +0100 Subject: [PATCH 25/59] perf script: Add process_stat/process_stat_interval scripting interface Python and perl scripting code will define those callbacks and get stat data. Signed-off-by: Jiri Olsa Tested-by: Kan Liang Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1452028152-26762-5-git-send-email-jolsa@kernel.org [ Rename 'time' parameters to 'tstamp', to fix the build in older distros ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/trace-event.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h index b85ee55cca0c..bce5b1dac268 100644 --- a/tools/perf/util/trace-event.h +++ b/tools/perf/util/trace-event.h @@ -65,6 +65,7 @@ int tracing_data_put(struct tracing_data *tdata); struct addr_location; struct perf_session; +struct perf_stat_config; struct scripting_ops { const char *name; @@ -75,6 +76,9 @@ struct scripting_ops { struct perf_sample *sample, struct perf_evsel *evsel, struct addr_location *al); + void (*process_stat)(struct perf_stat_config *config, + struct perf_evsel *evsel, u64 tstamp); + void (*process_stat_interval)(u64 tstamp); int (*generate_script) (struct pevent *pevent, const char *outfile); }; From e099eba8c8df0f96e7cd6ddc5fc3151fe37be24e Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 5 Jan 2016 22:09:09 +0100 Subject: [PATCH 26/59] perf script: Add stat default handlers Implement struct scripting_ops::(process_stat|process_stat_interval) handlers - calling scripting handlers from stat events handlers. Signed-off-by: Jiri Olsa Tested-by: Kan Liang Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1452028152-26762-6-git-send-email-jolsa@kernel.org [ Rename 'time' parameters to 'tstamp', to fix the build in older distros ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+) diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index a90bc0b81e70..5e1865408aa5 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -221,6 +221,9 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, struct perf_event_attr *attr = &evsel->attr; bool allow_user_set; + if (perf_header__has_feat(&session->header, HEADER_STAT)) + return 0; + allow_user_set = perf_header__has_feat(&session->header, HEADER_AUXTRACE); @@ -674,6 +677,18 @@ static void process_event(struct perf_script *script __maybe_unused, union perf_ static struct scripting_ops *scripting_ops; +static void process_stat(struct perf_evsel *counter, u64 tstamp) +{ + if (scripting_ops && scripting_ops->process_stat) + scripting_ops->process_stat(&stat_config, counter, tstamp); +} + +static void process_stat_interval(u64 tstamp) +{ + if (scripting_ops && scripting_ops->process_stat_interval) + scripting_ops->process_stat_interval(tstamp); +} + static void setup_scripting(void) { setup_perl_scripting(); @@ -1690,6 +1705,22 @@ 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) +{ + struct stat_round_event *round = &event->stat_round; + struct perf_evsel *counter; + + evlist__for_each(session->evlist, counter) { + perf_stat_process_counter(&stat_config, counter); + process_stat(counter, round->time); + } + + process_stat_interval(round->time); + return 0; +} + static int process_stat_config_event(struct perf_tool *tool __maybe_unused, union perf_event *event, struct perf_session *session __maybe_unused) @@ -1783,6 +1814,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) .auxtrace_info = perf_event__process_auxtrace_info, .auxtrace = perf_event__process_auxtrace, .auxtrace_error = perf_event__process_auxtrace_error, + .stat = perf_event__process_stat_event, + .stat_round = process_stat_round_event, .stat_config = process_stat_config_event, .thread_map = process_thread_map_event, .cpu_map = process_cpu_map_event, From aef90263561a87ae6d9c6a0f4071d825ce636eef Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 5 Jan 2016 22:09:11 +0100 Subject: [PATCH 27/59] perf script: Add python support for stat events Add support to get stat events data in perf python scripts. The python script shall implement the following new interface to process stat data: def stat___[](cpu, thread, time, val, ena, run): - is called for every stat event for given counter, if user monitors 'cycles,instructions:u" following callbacks should be defined: def stat__cycles(cpu, thread, time, val, ena, run): def stat__instructions_u(cpu, thread, time, val, ena, run): def stat__interval(time): - is called for every interval with its time, in non interval mode it's called after last stat event with total measured time in ns The rest of the current interface stays untouched.. Please check example CPI metrics script in following patch with command line examples in changelogs. Signed-off-by: Jiri Olsa Tested-by: Kan Liang Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1452028152-26762-8-git-send-email-jolsa@kernel.org [ Rename 'time' parameters to 'tstamp', to fix the build in older distros ] Signed-off-by: Arnaldo Carvalho de Melo --- .../scripting-engines/trace-event-python.c | 115 +++++++++++++++++- 1 file changed, 109 insertions(+), 6 deletions(-) diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c index a8e825fca42a..d72fafc1c800 100644 --- a/tools/perf/util/scripting-engines/trace-event-python.c +++ b/tools/perf/util/scripting-engines/trace-event-python.c @@ -41,6 +41,9 @@ #include "../thread-stack.h" #include "../trace-event.h" #include "../machine.h" +#include "thread_map.h" +#include "cpumap.h" +#include "stat.h" PyMODINIT_FUNC initperf_trace_context(void); @@ -859,6 +862,104 @@ static void python_process_event(union perf_event *event, } } +static void get_handler_name(char *str, size_t size, + struct perf_evsel *evsel) +{ + char *p = str; + + scnprintf(str, size, "stat__%s", perf_evsel__name(evsel)); + + while ((p = strchr(p, ':'))) { + *p = '_'; + p++; + } +} + +static void +process_stat(struct perf_evsel *counter, int cpu, int thread, u64 tstamp, + struct perf_counts_values *count) +{ + PyObject *handler, *t; + static char handler_name[256]; + int n = 0; + + t = PyTuple_New(MAX_FIELDS); + if (!t) + Py_FatalError("couldn't create Python tuple"); + + get_handler_name(handler_name, sizeof(handler_name), + counter); + + handler = get_handler(handler_name); + if (!handler) { + pr_debug("can't find python handler %s\n", handler_name); + return; + } + + PyTuple_SetItem(t, n++, PyInt_FromLong(cpu)); + PyTuple_SetItem(t, n++, PyInt_FromLong(thread)); + + tuple_set_u64(t, n++, tstamp); + tuple_set_u64(t, n++, count->val); + tuple_set_u64(t, n++, count->ena); + tuple_set_u64(t, n++, count->run); + + if (_PyTuple_Resize(&t, n) == -1) + Py_FatalError("error resizing Python tuple"); + + call_object(handler, t, handler_name); + + Py_DECREF(t); +} + +static void python_process_stat(struct perf_stat_config *config, + struct perf_evsel *counter, u64 tstamp) +{ + struct thread_map *threads = counter->threads; + struct cpu_map *cpus = counter->cpus; + int cpu, thread; + + if (config->aggr_mode == AGGR_GLOBAL) { + process_stat(counter, -1, -1, tstamp, + &counter->counts->aggr); + return; + } + + for (thread = 0; thread < threads->nr; thread++) { + for (cpu = 0; cpu < cpus->nr; cpu++) { + process_stat(counter, cpus->map[cpu], + thread_map__pid(threads, thread), tstamp, + perf_counts(counter->counts, cpu, thread)); + } + } +} + +static void python_process_stat_interval(u64 tstamp) +{ + PyObject *handler, *t; + static const char handler_name[] = "stat__interval"; + int n = 0; + + t = PyTuple_New(MAX_FIELDS); + if (!t) + Py_FatalError("couldn't create Python tuple"); + + handler = get_handler(handler_name); + if (!handler) { + pr_debug("can't find python handler %s\n", handler_name); + return; + } + + tuple_set_u64(t, n++, tstamp); + + if (_PyTuple_Resize(&t, n) == -1) + Py_FatalError("error resizing Python tuple"); + + call_object(handler, t, handler_name); + + Py_DECREF(t); +} + static int run_start_sub(void) { main_module = PyImport_AddModule("__main__"); @@ -1201,10 +1302,12 @@ static int python_generate_script(struct pevent *pevent, const char *outfile) } struct scripting_ops python_scripting_ops = { - .name = "Python", - .start_script = python_start_script, - .flush_script = python_flush_script, - .stop_script = python_stop_script, - .process_event = python_process_event, - .generate_script = python_generate_script, + .name = "Python", + .start_script = python_start_script, + .flush_script = python_flush_script, + .stop_script = python_stop_script, + .process_event = python_process_event, + .process_stat = python_process_stat, + .process_stat_interval = python_process_stat_interval, + .generate_script = python_generate_script, }; From 15d2b9956b41ffb5961b897bf61cdc09f722dfbf Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 6 Jan 2016 11:49:55 +0100 Subject: [PATCH 28/59] perf cpumap: Fix cpu conversion in cpu_map__from_entries We can't convert u16 cpu_map_entries::cpu[x] value directly to int, because it could hold -1, which would be converted as 65535. Adding special treatment for -1, which is not real cpu number, to be converted to (int -1). Reported-by: Arnaldo Carvalho de Melo Signed-off-by: Jiri Olsa Cc: David Ahern Cc: Kan Liang Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1452077397-31958-2-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/cpumap.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index a0717b93d8f5..fa935093a599 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -188,8 +188,17 @@ static struct cpu_map *cpu_map__from_entries(struct cpu_map_entries *cpus) if (map) { unsigned i; - for (i = 0; i < cpus->nr; i++) - map->map[i] = (int)cpus->cpu[i]; + for (i = 0; i < cpus->nr; i++) { + /* + * Special treatment for -1, which is not real cpu number, + * and we need to use (int) -1 to initialize map[i], + * otherwise it would become 65535. + */ + if (cpus->cpu[i] == (u16) -1) + map->map[i] = -1; + else + map->map[i] = (int) cpus->cpu[i]; + } } return map; From 36e33c53f4b693d96fb8dd4529fe14306d4e3e76 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 6 Jan 2016 11:49:56 +0100 Subject: [PATCH 29/59] perf script: Display stat events by default If no script is specified for stat data, display stat events in raw form. $ perf stat record ls SNIP Performance counter stats for 'ls': 0.851585 task-clock (msec) # 0.717 CPUs utilized 0 context-switches # 0.000 K/sec 0 cpu-migrations # 0.000 K/sec 114 page-faults # 0.134 M/sec 2,620,918 cycles # 3.078 GHz stalled-cycles-frontend stalled-cycles-backend 2,714,111 instructions # 1.04 insns per cycle 542,434 branches # 636.970 M/sec 15,946 branch-misses # 2.94% of all branches 0.001186954 seconds time elapsed $ perf script CPU THREAD VAL ENA RUN TIME EVENT -1 26185 851585 851585 851585 1186954 task-clock -1 26185 0 851585 851585 1186954 context-switches -1 26185 0 851585 851585 1186954 cpu-migrations -1 26185 114 851585 851585 1186954 page-faults -1 26185 2620918 853340 853340 1186954 cycles -1 26185 0 0 0 1186954 stalled-cycles-frontend -1 26185 0 0 0 1186954 stalled-cycles-backend -1 26185 2714111 853340 853340 1186954 instructions -1 26185 542434 853340 853340 1186954 branches -1 26185 15946 853340 853340 1186954 branch-misses Signed-off-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Tested-by: Kan Liang Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1452077397-31958-3-git-send-email-jolsa@kernel.org [ Rename 'time' parameter to 'tstamp' to fix build on older distros ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 5e1865408aa5..5e2f9d20a296 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -677,10 +677,46 @@ static void process_event(struct perf_script *script __maybe_unused, union perf_ static struct scripting_ops *scripting_ops; +static void __process_stat(struct perf_evsel *counter, u64 tstamp) +{ + int nthreads = thread_map__nr(counter->threads); + int ncpus = perf_evsel__nr_cpus(counter); + int cpu, thread; + static int header_printed; + + if (counter->system_wide) + nthreads = 1; + + if (!header_printed) { + printf("%3s %8s %15s %15s %15s %15s %s\n", + "CPU", "THREAD", "VAL", "ENA", "RUN", "TIME", "EVENT"); + header_printed = 1; + } + + for (thread = 0; thread < nthreads; thread++) { + for (cpu = 0; cpu < ncpus; cpu++) { + struct perf_counts_values *counts; + + counts = perf_counts(counter->counts, cpu, thread); + + printf("%3d %8d %15" PRIu64 " %15" PRIu64 " %15" PRIu64 " %15" PRIu64 " %s\n", + counter->cpus->map[cpu], + thread_map__pid(counter->threads, thread), + counts->val, + counts->ena, + counts->run, + tstamp, + perf_evsel__name(counter)); + } + } +} + static void process_stat(struct perf_evsel *counter, u64 tstamp) { if (scripting_ops && scripting_ops->process_stat) scripting_ops->process_stat(&stat_config, counter, tstamp); + else + __process_stat(counter, tstamp); } static void process_stat_interval(u64 tstamp) From b8a1962d17b4e3cfdd7b7dc9ebd94affbcb4c1c5 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 6 Jan 2016 11:49:57 +0100 Subject: [PATCH 30/59] perf script: Add stat-cpi.py script Adding stat-cpi.py as an example of how to do stat scripting. It computes the CPI metrics from cycles and instructions events. The CPI is based performance metric showing the Cycles Per Instructions ratio, which helps to identify cycles-hungry code. Following stat record/report/script combinations could be used: - get CPI for given workload $ perf stat -e cycles,instructions record ls SNIP Performance counter stats for 'ls': 2,904,431 cycles 3,346,878 instructions # 1.15 insns per cycle 0.001782686 seconds time elapsed $ perf script -s ./scripts/python/stat-cpi.py 0.001783: cpu -1, thread -1 -> cpi 0.867803 (2904431/3346878) $ perf stat -e cycles,instructions record ls | perf script -s ./scripts/python/stat-cpi.py SNIP 0.001730: cpu -1, thread -1 -> cpi 0.869026 (2928292/3369627) - get CPI systemwide: $ perf stat -e cycles,instructions -a -I 1000 record sleep 3 # time counts unit events 1.000158618 594,274,711 cycles (100.00%) 1.000158618 441,898,250 instructions 2.000350973 567,649,705 cycles (100.00%) 2.000350973 432,669,206 instructions 3.000559210 561,940,430 cycles (100.00%) 3.000559210 420,403,465 instructions 3.000670798 780,105 cycles (100.00%) 3.000670798 326,516 instructions $ perf script -s ./scripts/python/stat-cpi.py 1.000159: cpu -1, thread -1 -> cpi 1.344823 (594274711/441898250) 2.000351: cpu -1, thread -1 -> cpi 1.311972 (567649705/432669206) 3.000559: cpu -1, thread -1 -> cpi 1.336669 (561940430/420403465) 3.000671: cpu -1, thread -1 -> cpi 2.389178 (780105/326516) $ perf stat -e cycles,instructions -a -I 1000 record sleep 3 | perf script -s ./scripts/python/stat-cpi.py 1.000202: cpu -1, thread -1 -> cpi 1.035091 (940778881/908885530) 2.000392: cpu -1, thread -1 -> cpi 1.442600 (627493992/434974455) 3.000545: cpu -1, thread -1 -> cpi 1.353612 (741463930/547766890) 3.000622: cpu -1, thread -1 -> cpi 2.642110 (784083/296764) Signed-off-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Tested-by: Kan Liang Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1452077397-31958-4-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/scripts/python/stat-cpi.py | 77 +++++++++++++++++++++++++++ 1 file changed, 77 insertions(+) create mode 100644 tools/perf/scripts/python/stat-cpi.py diff --git a/tools/perf/scripts/python/stat-cpi.py b/tools/perf/scripts/python/stat-cpi.py new file mode 100644 index 000000000000..8b60f343dd07 --- /dev/null +++ b/tools/perf/scripts/python/stat-cpi.py @@ -0,0 +1,77 @@ +#!/usr/bin/env python + +data = {} +times = [] +threads = [] +cpus = [] + +def get_key(time, event, cpu, thread): + return "%d-%s-%d-%d" % (time, event, cpu, thread) + +def store_key(time, cpu, thread): + if (time not in times): + times.append(time) + + if (cpu not in cpus): + cpus.append(cpu) + + if (thread not in threads): + threads.append(thread) + +def store(time, event, cpu, thread, val, ena, run): + #print "event %s cpu %d, thread %d, time %d, val %d, ena %d, run %d" % \ + # (event, cpu, thread, time, val, ena, run) + + store_key(time, cpu, thread) + key = get_key(time, event, cpu, thread) + data[key] = [ val, ena, run] + +def get(time, event, cpu, thread): + key = get_key(time, event, cpu, thread) + return data[key][0] + +def stat__cycles_k(cpu, thread, time, val, ena, run): + store(time, "cycles", cpu, thread, val, ena, run); + +def stat__instructions_k(cpu, thread, time, val, ena, run): + store(time, "instructions", cpu, thread, val, ena, run); + +def stat__cycles_u(cpu, thread, time, val, ena, run): + store(time, "cycles", cpu, thread, val, ena, run); + +def stat__instructions_u(cpu, thread, time, val, ena, run): + store(time, "instructions", cpu, thread, val, ena, run); + +def stat__cycles(cpu, thread, time, val, ena, run): + store(time, "cycles", cpu, thread, val, ena, run); + +def stat__instructions(cpu, thread, time, val, ena, run): + store(time, "instructions", cpu, thread, val, ena, run); + +def stat__interval(time): + for cpu in cpus: + for thread in threads: + cyc = get(time, "cycles", cpu, thread) + ins = get(time, "instructions", cpu, thread) + cpi = 0 + + if ins != 0: + cpi = cyc/float(ins) + + print "%15f: cpu %d, thread %d -> cpi %f (%d/%d)" % (time/(float(1000000000)), cpu, thread, cpi, cyc, ins) + +def trace_end(): + pass +# XXX trace_end callback could be used as an alternative place +# to compute same values as in the script above: +# +# for time in times: +# for cpu in cpus: +# for thread in threads: +# cyc = get(time, "cycles", cpu, thread) +# ins = get(time, "instructions", cpu, thread) +# +# if ins != 0: +# cpi = cyc/float(ins) +# +# print "time %.9f, cpu %d, thread %d -> cpi %f" % (time/(float(1000000000)), cpu, thread, cpi) From 84530920de3c6ccb92c6661da784f6cdb66d3304 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Wed, 6 Jan 2016 19:50:01 +0100 Subject: [PATCH 31/59] perf pmu: fix alias->snapshot missing initialization bug This patch fixes a bug in __perf_pmu__new_alias() whereby the alias->snapshot field was not initialized to false. This led to random alias->snapshot value for an alias and was breaking some measurements such as: $ perf stat -a -e uncore_imc/data_reads/ -I 1000 sleep 100 Because the event ended up being treated as snapshot mode, when it is not. Signed-off-by: Stephane Eranian Cc: Andi Kleen Cc: Jiri Olsa Cc: Kan Liang Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1452106201-13073-1-git-send-email-eranian@google.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/pmu.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index e4b173dec4b9..b597bcc8fc78 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -220,6 +220,7 @@ static int __perf_pmu__new_alias(struct list_head *list, char *dir, char *name, alias->scale = 1.0; alias->unit[0] = '\0'; alias->per_pkg = false; + alias->snapshot = false; ret = parse_events_terms(&alias->terms, val); if (ret) { From 4f4ba0e6afac4b181471f5f12bd87294bd8807f6 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 7 Jan 2016 09:54:56 -0300 Subject: [PATCH 32/59] perf tests: No need to set attr.sample_freq in the perf time to TSC test We were asking for a 4kHz sample_freq, making the test fail needlessly when the system reduced /proc/sys/kernel/perf_event_max_sample_rate below that. In this test we only look at the PERF_SAMPLE_TIME fields in PERF_RECORD_ meta events, no need to set sample_freq. Thanks to Namhyung for suggesting that max_sample_rate could be the reason for the test failure, seeing the 'perf test -vv' output I sent. Before: # echo 1000 > /proc/sys/kernel/perf_event_max_sample_rate # perf test TSC 45: Test converting perf time to TSC : FAILED! After: # perf test TSC 45: Test converting perf time to TSC : Ok # cat /proc/sys/kernel/perf_event_max_sample_rate 1000 Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-lcob05qhawkuvsyuu9g1fld5@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/x86/tests/perf-time-to-tsc.c | 1 - 1 file changed, 1 deletion(-) diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/arch/x86/tests/perf-time-to-tsc.c index a289aa8a083a..9d29ee283ac5 100644 --- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c +++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c @@ -41,7 +41,6 @@ int test__perf_time_to_tsc(int subtest __maybe_unused) .mmap_pages = UINT_MAX, .user_freq = UINT_MAX, .user_interval = ULLONG_MAX, - .freq = 4000, .target = { .uses_mmap = true, }, From 5bae0250237f7a5ec4355f9920701de247b8db91 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 7 Jan 2016 13:14:56 -0300 Subject: [PATCH 33/59] perf evlist: Introduce perf_evlist__new_dummy constructor For case where all we need is an evlist with just an "dummy" evsel, like in some 'perf test' entries. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-q52le0pblm2k3ncvyilelr9z@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evlist.c | 28 ++++++++++++++++++++++++++++ tools/perf/util/evlist.h | 3 +++ 2 files changed, 31 insertions(+) diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index b9eac0daa0b9..fa6dbf0ea0d6 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -68,6 +68,18 @@ struct perf_evlist *perf_evlist__new_default(void) return evlist; } +struct perf_evlist *perf_evlist__new_dummy(void) +{ + struct perf_evlist *evlist = perf_evlist__new(); + + if (evlist && perf_evlist__add_dummy(evlist)) { + perf_evlist__delete(evlist); + evlist = NULL; + } + + return evlist; +} + /** * perf_evlist__set_id_pos - set the positions of event ids. * @evlist: selected event list @@ -248,6 +260,22 @@ error: return -ENOMEM; } +int perf_evlist__add_dummy(struct perf_evlist *evlist) +{ + struct perf_event_attr attr = { + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_DUMMY, + .size = sizeof(attr), /* to capture ABI version */ + }; + struct perf_evsel *evsel = perf_evsel__new(&attr); + + if (evsel == NULL) + return -ENOMEM; + + perf_evlist__add(evlist, evsel); + return 0; +} + static int perf_evlist__add_attrs(struct perf_evlist *evlist, struct perf_event_attr *attrs, size_t nr_attrs) { diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 139a50038097..3b7e1e2f1a86 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -67,6 +67,7 @@ struct perf_evsel_str_handler { struct perf_evlist *perf_evlist__new(void); struct perf_evlist *perf_evlist__new_default(void); +struct perf_evlist *perf_evlist__new_dummy(void); void perf_evlist__init(struct perf_evlist *evlist, struct cpu_map *cpus, struct thread_map *threads); void perf_evlist__exit(struct perf_evlist *evlist); @@ -81,6 +82,8 @@ int __perf_evlist__add_default_attrs(struct perf_evlist *evlist, #define perf_evlist__add_default_attrs(evlist, array) \ __perf_evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array)) +int perf_evlist__add_dummy(struct perf_evlist *evlist); + int perf_evlist__add_newtp(struct perf_evlist *evlist, const char *sys, const char *name, void *handler); From 69ef8f475586974d3921c4799bfa75b8fef877a8 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 7 Jan 2016 13:17:00 -0300 Subject: [PATCH 34/59] perf test: Use "dummy" events in the PERF_RECORD_ test As we're test just the !PERF_RECORD_SAMPLE records. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-qp8radcz3il4q9wbnseh337d@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/perf-record.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c index 9d5f0b57c4c1..8dc0baba8798 100644 --- a/tools/perf/tests/perf-record.c +++ b/tools/perf/tests/perf-record.c @@ -45,7 +45,7 @@ int test__PERF_RECORD(int subtest __maybe_unused) }; cpu_set_t cpu_mask; size_t cpu_mask_size = sizeof(cpu_mask); - struct perf_evlist *evlist = perf_evlist__new_default(); + struct perf_evlist *evlist = perf_evlist__new_dummy(); struct perf_evsel *evsel; struct perf_sample sample; const char *cmd = "sleep"; @@ -61,6 +61,9 @@ int test__PERF_RECORD(int subtest __maybe_unused) int total_events = 0, nr_events[PERF_RECORD_MAX] = { 0, }; char sbuf[STRERR_BUFSIZE]; + if (evlist == NULL) /* Fallback for kernels lacking PERF_COUNT_SW_DUMMY */ + evlist = perf_evlist__new_default(); + if (evlist == NULL || argv == NULL) { pr_debug("Not enough memory to create evlist\n"); goto out; From 2e4f81ee90e801017115afb7397198f65e512031 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 7 Jan 2016 13:20:22 -0300 Subject: [PATCH 35/59] perf test: No need for setting attr.sample_freq on the RECORD test We're not looking at PERF_RECORD_SAMPLE entries and now by default we use PERF_COUNT_SW_DUMMY, so just remove that setting. Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-cly7cnotktv5rqao13pkorem@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/perf-record.c | 1 - 1 file changed, 1 deletion(-) diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c index 8dc0baba8798..1cc78cefe399 100644 --- a/tools/perf/tests/perf-record.c +++ b/tools/perf/tests/perf-record.c @@ -40,7 +40,6 @@ int test__PERF_RECORD(int subtest __maybe_unused) .uses_mmap = true, }, .no_buffering = true, - .freq = 10, .mmap_pages = 256, }; cpu_set_t cpu_mask; From 372b212263998ae8e3b2f80ce52af3168d749158 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 7 Jan 2016 16:47:11 -0300 Subject: [PATCH 36/59] perf python: Add missing files to binding link list Fixing this problem, introduced recently: $ perf test python 16: Try 'import perf' in python, checking link problems : FAILED! In verbose mode we find out what is missing: $ perf test -v python 16: Try 'import perf' in python, checking link problems : --- start --- test child forked, pid 24894 Traceback (most recent call last): File "", line 1, in ImportError: /tmp/build/perf/python/perf.so: undefined symbol: find_next_bit test child finished with -1 ---- end ---- Try 'import perf' in python, checking link problems: FAILED! $ Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Fixes: f77b57ad4fc4 ("perf cpu_map: Add cpu_map__new_event function") Link: http://lkml.kernel.org/n/tip-rajx0zkz6czdrnvvwf0jp76p@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/python-ext-sources | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index 51be28b1bca2..38a0b63ebe8b 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -10,6 +10,8 @@ util/ctype.c util/evlist.c util/evsel.c util/cpumap.c +util/bitmap.c +../lib/util/find_next_bit.c ../lib/hweight.c util/thread_map.c util/util.c From 239849dde350c9f7356974ca4f62171f50a2c86e Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 7 Jan 2016 16:51:58 -0300 Subject: [PATCH 37/59] perf tests: No need to set attr.sample_freq for tracking !PERF_RECORD_SAMPLE We were asking for a 4kHz sample_freq, making the test fail needlessly when the system reduced /proc/sys/kernel/perf_event_max_sample_rate below that. Before: # perf test -vv dummy 23: Test using a dummy software event to keep tracking : --- start --- test child forked, pid 32421 ------------------------------------------------------------ perf_event_attr: type 1 size 112 config 0x9 { sample_period, sample_freq } 4000 sample_type IP|TID|ID|PERIOD sys_perf_event_open failed, error -22 Unable to open dummy and cycles event test child finished with -2 ---- end ---- Test using a dummy software event to keep tracking: Skip # [root@zoo ~]# cat /proc/sys/kernel/perf_event_max_sample_rate 1000 After: [root@zoo ~]# perf test dummy 23: Test using a dummy software event to keep tracking : Ok Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-487iquegrs2379e5n0pi0tcp@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/tests/keep-tracking.c | 1 - 1 file changed, 1 deletion(-) diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c index a337a6da1f39..615813278334 100644 --- a/tools/perf/tests/keep-tracking.c +++ b/tools/perf/tests/keep-tracking.c @@ -55,7 +55,6 @@ int test__keep_tracking(int subtest __maybe_unused) .mmap_pages = UINT_MAX, .user_freq = UINT_MAX, .user_interval = ULLONG_MAX, - .freq = 4000, .target = { .uses_mmap = true, }, From a831e67913e356be63d5bb0509fc1af3c4e6ceb4 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Thu, 7 Jan 2016 16:59:27 -0300 Subject: [PATCH 38/59] perf tests: Give a bit more information on the CQM test failure path Before: $ perf test -v cqm 48: Test intel cqm nmi context read : --- start --- test child forked, pid 1681 parse_events failed test child finished with -2 ---- end ---- Test intel cqm nmi context read: Skip $ After: $ perf test -v cqm 48: Test intel cqm nmi context read : --- start --- test child forked, pid 1681 parse_events failed, is "intel_cqm/llc_occupancy/" available? test child finished with -2 ---- end ---- Test intel cqm nmi context read: Skip $ Cc: Adrian Hunter Cc: David Ahern Cc: Jiri Olsa Cc: Matt Fleming Cc: Namhyung Kim Cc: Wang Nan Link: http://lkml.kernel.org/n/tip-eidpiv5x4nkbsx37xwikbnir@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/x86/tests/intel-cqm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/arch/x86/tests/intel-cqm.c b/tools/perf/arch/x86/tests/intel-cqm.c index 94e0cb7462f9..3e89ba825f6b 100644 --- a/tools/perf/arch/x86/tests/intel-cqm.c +++ b/tools/perf/arch/x86/tests/intel-cqm.c @@ -54,7 +54,7 @@ int test__intel_cqm_count_nmi_context(int subtest __maybe_unused) ret = parse_events(evlist, "intel_cqm/llc_occupancy/", NULL); if (ret) { - pr_debug("parse_events failed\n"); + pr_debug("parse_events failed, is \"intel_cqm/llc_occupancy/\" available?\n"); err = TEST_SKIP; goto out; } From 552eb975b83756e3d95aeb5edaeb5c3c032b0021 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 8 Jan 2016 10:46:52 -0300 Subject: [PATCH 39/59] tools lib: Move find_next_bit.c to tools/lib/ The commit that introduced it should've moved it to the same place, plus the 'tools/' prefix, but instead moved it to a bogus tools/lib/util/ directory, being the only file there. Move it to tools/lib/find_bit.c, picking the name for the file where these routines live since: 8f6f19dd5143 ("lib: move find_last_bit to lib/find_next_bit.c") Next step is to make tools/lib/find_bit.c to differ from lib/find_bit.c just in removing what is not used by tools/. Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: George Spelvin Cc: Namhyung Kim Cc: Rasmus Villemoes Cc: Wang Nan Cc: Yury Norov Link: http://lkml.kernel.org/n/tip-p391cex5mqvahp4pwrton87n@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/{util/find_next_bit.c => find_bit.c} | 2 +- tools/perf/MANIFEST | 2 +- tools/perf/util/Build | 6 +++--- tools/perf/util/python-ext-sources | 2 +- 4 files changed, 6 insertions(+), 6 deletions(-) rename tools/lib/{util/find_next_bit.c => find_bit.c} (97%) diff --git a/tools/lib/util/find_next_bit.c b/tools/lib/find_bit.c similarity index 97% rename from tools/lib/util/find_next_bit.c rename to tools/lib/find_bit.c index 41b44f65a79e..732d8c38d2c3 100644 --- a/tools/lib/util/find_next_bit.c +++ b/tools/lib/find_bit.c @@ -1,6 +1,6 @@ /* find_next_bit.c: fallback find next bit implementation * - * Copied from lib/find_next_bit.c to tools/lib/next_bit.c + * Copied from lib/find_next_bit.c to tools/lib/find_bit.c * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index ce3932ee4893..b3db8dfebbf2 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -26,7 +26,7 @@ tools/lib/rbtree.c tools/lib/string.c tools/lib/symbol/kallsyms.c tools/lib/symbol/kallsyms.h -tools/lib/util/find_next_bit.c +tools/lib/find_bit.c tools/include/asm/atomic.h tools/include/asm/barrier.h tools/include/asm/bug.h diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 94b1099f2c22..e8bc10b41b66 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -9,7 +9,7 @@ libperf-y += env.o libperf-y += event.o libperf-y += evlist.o libperf-y += evsel.o -libperf-y += find_next_bit.o +libperf-y += find_bit.o libperf-y += kallsyms.o libperf-y += levenshtein.o libperf-y += llvm-utils.o @@ -132,7 +132,7 @@ CFLAGS_pmu-bison.o += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w $(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c $(OUTPUT)util/pmu.o: $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c -CFLAGS_find_next_bit.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" +CFLAGS_find_bit.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" CFLAGS_rbtree.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" CFLAGS_libstring.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" CFLAGS_hweight.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" @@ -142,7 +142,7 @@ $(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c FORCE $(call rule_mkdir) $(call if_changed_dep,cc_o_c) -$(OUTPUT)util/find_next_bit.o: ../lib/util/find_next_bit.c FORCE +$(OUTPUT)util/find_bit.o: ../lib/find_bit.c FORCE $(call rule_mkdir) $(call if_changed_dep,cc_o_c) diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index 38a0b63ebe8b..f15d14fb35eb 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -11,7 +11,7 @@ util/evlist.c util/evsel.c util/cpumap.c util/bitmap.c -../lib/util/find_next_bit.c +../lib/find_bit.c ../lib/hweight.c util/thread_map.c util/util.c From 64af4e0da419ef9e9db0d34a3b5836adbf90a5e8 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 8 Jan 2016 11:26:43 -0300 Subject: [PATCH 40/59] tools lib: Sync tools/lib/find_bit.c with the kernel Need to move the bitmap.[ch] things from tools/perf/ to tools/lib, will be done in the next patches. Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: George Spelvin Cc: Namhyung Kim Cc: Rasmus Villemoes Cc: Wang Nan Cc: Yury Norov Link: http://lkml.kernel.org/n/tip-5fys65wkd7gu8j7a7xgukc5t@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/lib/find_bit.c | 103 ++++++++++++------------- tools/perf/util/include/linux/bitmap.h | 2 + 2 files changed, 51 insertions(+), 54 deletions(-) diff --git a/tools/lib/find_bit.c b/tools/lib/find_bit.c index 732d8c38d2c3..9122a9e80046 100644 --- a/tools/lib/find_bit.c +++ b/tools/lib/find_bit.c @@ -1,10 +1,17 @@ -/* find_next_bit.c: fallback find next bit implementation +/* bit search implementation * - * Copied from lib/find_next_bit.c to tools/lib/find_bit.c + * Copied from lib/find_bit.c to tools/lib/find_bit.c * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * + * Copyright (C) 2008 IBM Corporation + * 'find_last_bit' is written by Rusty Russell + * (Inspired by David Howell's find_next_bit implementation) + * + * Rewritten by Yury Norov to decrease + * size and improve performance, 2015. + * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version @@ -12,10 +19,41 @@ */ #include -#include -#include +#include +#include -#define BITOP_WORD(nr) ((nr) / BITS_PER_LONG) +#if !defined(find_next_bit) + +/* + * This is a common helper function for find_next_bit and + * find_next_zero_bit. The difference is the "invert" argument, which + * is XORed with each fetched word before searching it for one bits. + */ +static unsigned long _find_next_bit(const unsigned long *addr, + unsigned long nbits, unsigned long start, unsigned long invert) +{ + unsigned long tmp; + + if (!nbits || start >= nbits) + return nbits; + + tmp = addr[start / BITS_PER_LONG] ^ invert; + + /* Handle 1st word. */ + tmp &= BITMAP_FIRST_WORD_MASK(start); + start = round_down(start, BITS_PER_LONG); + + while (!tmp) { + start += BITS_PER_LONG; + if (start >= nbits) + return nbits; + + tmp = addr[start / BITS_PER_LONG] ^ invert; + } + + return min(start + __ffs(tmp), nbits); +} +#endif #ifndef find_next_bit /* @@ -24,40 +62,7 @@ unsigned long find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { - const unsigned long *p = addr + BITOP_WORD(offset); - unsigned long result = offset & ~(BITS_PER_LONG-1); - unsigned long tmp; - - if (offset >= size) - return size; - size -= result; - offset %= BITS_PER_LONG; - if (offset) { - tmp = *(p++); - tmp &= (~0UL << offset); - if (size < BITS_PER_LONG) - goto found_first; - if (tmp) - goto found_middle; - size -= BITS_PER_LONG; - result += BITS_PER_LONG; - } - while (size & ~(BITS_PER_LONG-1)) { - if ((tmp = *(p++))) - goto found_middle; - result += BITS_PER_LONG; - size -= BITS_PER_LONG; - } - if (!size) - return result; - tmp = *p; - -found_first: - tmp &= (~0UL >> (BITS_PER_LONG - size)); - if (tmp == 0UL) /* Are any bits set? */ - return result + size; /* Nope. */ -found_middle: - return result + __ffs(tmp); + return _find_next_bit(addr, size, offset, 0UL); } #endif @@ -67,23 +72,13 @@ found_middle: */ unsigned long find_first_bit(const unsigned long *addr, unsigned long size) { - const unsigned long *p = addr; - unsigned long result = 0; - unsigned long tmp; + unsigned long idx; - while (size & ~(BITS_PER_LONG-1)) { - if ((tmp = *(p++))) - goto found; - result += BITS_PER_LONG; - size -= BITS_PER_LONG; + for (idx = 0; idx * BITS_PER_LONG < size; idx++) { + if (addr[idx]) + return min(idx * BITS_PER_LONG + __ffs(addr[idx]), size); } - if (!size) - return result; - tmp = (*p) & (~0UL >> (BITS_PER_LONG - size)); - if (tmp == 0UL) /* Are any bits set? */ - return result + size; /* Nope. */ -found: - return result + __ffs(tmp); + return size; } #endif diff --git a/tools/perf/util/include/linux/bitmap.h b/tools/perf/util/include/linux/bitmap.h index 40bd21488032..28f5493da491 100644 --- a/tools/perf/util/include/linux/bitmap.h +++ b/tools/perf/util/include/linux/bitmap.h @@ -11,6 +11,8 @@ int __bitmap_weight(const unsigned long *bitmap, int bits); void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, int bits); +#define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1))) + #define BITMAP_LAST_WORD_MASK(nbits) \ ( \ ((nbits) % BITS_PER_LONG) ? \ From 915b0882c3108a21e9b3b5e176d3151ad522242d Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Fri, 8 Jan 2016 12:33:37 -0300 Subject: [PATCH 41/59] tools lib: Move bitmap.[ch] from tools/perf/ to tools/{lib,include}/ So that lib/find_bit.c doesn't requires anything inside tools/perf/ Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: George Spelvin Cc: Namhyung Kim Cc: Rasmus Villemoes Cc: Wang Nan Cc: Yury Norov Link: http://lkml.kernel.org/n/tip-7lxe7jgohaac5faodndhdmvk@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/{perf/util => }/include/linux/bitmap.h | 0 tools/{perf/util => lib}/bitmap.c | 0 tools/perf/util/Build | 5 +++++ tools/perf/util/python-ext-sources | 2 +- 4 files changed, 6 insertions(+), 1 deletion(-) rename tools/{perf/util => }/include/linux/bitmap.h (100%) rename tools/{perf/util => lib}/bitmap.c (100%) diff --git a/tools/perf/util/include/linux/bitmap.h b/tools/include/linux/bitmap.h similarity index 100% rename from tools/perf/util/include/linux/bitmap.h rename to tools/include/linux/bitmap.h diff --git a/tools/perf/util/bitmap.c b/tools/lib/bitmap.c similarity index 100% rename from tools/perf/util/bitmap.c rename to tools/lib/bitmap.c diff --git a/tools/perf/util/Build b/tools/perf/util/Build index e8bc10b41b66..5eec53a3f4ac 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -132,6 +132,7 @@ CFLAGS_pmu-bison.o += -DYYENABLE_NLS=0 -DYYLTYPE_IS_TRIVIAL=0 -w $(OUTPUT)util/parse-events.o: $(OUTPUT)util/parse-events-flex.c $(OUTPUT)util/parse-events-bison.c $(OUTPUT)util/pmu.o: $(OUTPUT)util/pmu-flex.c $(OUTPUT)util/pmu-bison.c +CFLAGS_bitmap.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" CFLAGS_find_bit.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" CFLAGS_rbtree.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" CFLAGS_libstring.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PERFCONFIG_SQ))" @@ -142,6 +143,10 @@ $(OUTPUT)util/kallsyms.o: ../lib/symbol/kallsyms.c FORCE $(call rule_mkdir) $(call if_changed_dep,cc_o_c) +$(OUTPUT)util/bitmap.o: ../lib/bitmap.c FORCE + $(call rule_mkdir) + $(call if_changed_dep,cc_o_c) + $(OUTPUT)util/find_bit.o: ../lib/find_bit.c FORCE $(call rule_mkdir) $(call if_changed_dep,cc_o_c) diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index f15d14fb35eb..8162ba0e2e57 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -10,7 +10,7 @@ util/ctype.c util/evlist.c util/evsel.c util/cpumap.c -util/bitmap.c +../lib/bitmap.c ../lib/find_bit.c ../lib/hweight.c util/thread_map.c From 42b276a2351517409d55b1202a1fa8b05c0cdc99 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Tue, 5 Jan 2016 12:06:00 +0900 Subject: [PATCH 42/59] perf top: Decay periods in callchains It missed to decay periods in callchains when decaying hist entries. This resulted in more than 100 percent overhead in callchains in the fractal style output. Reported-by: Arnaldo Carvalho de Melo Signed-off-by: Namhyung Kim Cc: Andi Kleen Cc: David Ahern Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1451963160-17196-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/callchain.c | 28 ++++++++++++++++++++++++++++ tools/perf/util/callchain.h | 1 + tools/perf/util/hist.c | 1 + 3 files changed, 30 insertions(+) diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 564377d2bebf..53c43eb9489e 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -925,6 +925,34 @@ void free_callchain(struct callchain_root *root) free_callchain_node(&root->node); } +static u64 decay_callchain_node(struct callchain_node *node) +{ + struct callchain_node *child; + struct rb_node *n; + u64 child_hits = 0; + + n = rb_first(&node->rb_root_in); + while (n) { + child = container_of(n, struct callchain_node, rb_node_in); + + child_hits += decay_callchain_node(child); + n = rb_next(n); + } + + node->hit = (node->hit * 7) / 8; + node->children_hit = child_hits; + + return node->hit; +} + +void decay_callchain(struct callchain_root *root) +{ + if (!symbol_conf.use_callchain) + return; + + decay_callchain_node(&root->node); +} + int callchain_node__make_parent_list(struct callchain_node *node) { struct callchain_node *parent = node->parent; diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 8ac8f043004c..18dd22269764 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -253,6 +253,7 @@ int callchain_node__fprintf_value(struct callchain_node *node, FILE *fp, u64 total); void free_callchain(struct callchain_root *root); +void decay_callchain(struct callchain_root *root); int callchain_node__make_parent_list(struct callchain_node *node); #endif /* __PERF_CALLCHAIN_H */ diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index afc9b8f1b36c..888776b43cb0 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -254,6 +254,7 @@ static bool hists__decay_entry(struct hists *hists, struct hist_entry *he) he_stat__decay(&he->stat); if (symbol_conf.cumulate_callchain) he_stat__decay(he->stat_acc); + decay_callchain(he->callchain); diff = prev_period - he->stat.period; From 1e9abf8b03c8f9352f54171647296c41317679a4 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Sun, 29 Nov 2015 23:24:17 +0900 Subject: [PATCH 43/59] perf report: Change default to use event group view The event group view feature is to see related events together. To use the group view, events should be recorded as a group with a dedicated syntax of surrounding events by braces (-e '{ evt1, evt2, ... }'). Also 'perf report' also requires the --group option to enable it. However it's almost always beneficial to use the group view to see the group events as it's more expressive. And I think it's more natural to see events together if they are recorded as a group. Thus this patch changes the default value to enable it. If users don't want to see like it and keep the original behavior, they can set the report.group config variable to false and/or use --no-group option in the 'perf report' command line. Requested-by: Ingo Molnar Signed-off-by: Namhyung Kim Cc: David Ahern Cc: Jiri Olsa Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Taeung Song Link: http://lkml.kernel.org/r/1448807057-3506-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/symbol.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index d51abd2e7865..3b2de6eb3376 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -39,6 +39,7 @@ struct symbol_conf symbol_conf = { .cumulate_callchain = true, .show_hist_headers = true, .symfs = "", + .event_group = true, }; static enum dso_binary_type binary_type_symtab[] = { From cbd08b7335c9d559f424dcef7bea333605597490 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 7 Jan 2016 10:14:04 +0100 Subject: [PATCH 44/59] perf tools: Do not show trace command if it's not compiled in The trace command still appears in help message when you run simple 'perf' command. It's because the generate-cmdlist.sh does not care about the HAVE_LIBAUDIT_SUPPORT dependency of trace command and puts it into generated common_cmds array. Wrapping trace command under HAVE_LIBAUDIT_SUPPORT dependency, which will exclude it from common_cmds array if HAVE_LIBAUDIT_SUPPORT is not set. Signed-off-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: David Ahern Cc: Namhyung Kim Cc: Noel Grandin Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1452158050-28061-8-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/command-list.txt | 2 +- tools/perf/util/generate-cmdlist.sh | 15 +++++++++++++++ 2 files changed, 16 insertions(+), 1 deletion(-) diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt index acc3ea7d90b7..ab5cbaa170d0 100644 --- a/tools/perf/command-list.txt +++ b/tools/perf/command-list.txt @@ -26,4 +26,4 @@ perf-stat mainporcelain common perf-test mainporcelain common perf-timechart mainporcelain common perf-top mainporcelain common -perf-trace mainporcelain common +perf-trace mainporcelain audit diff --git a/tools/perf/util/generate-cmdlist.sh b/tools/perf/util/generate-cmdlist.sh index 36a885d2cd22..0ac2037c970c 100755 --- a/tools/perf/util/generate-cmdlist.sh +++ b/tools/perf/util/generate-cmdlist.sh @@ -36,4 +36,19 @@ do }' "Documentation/perf-$cmd.txt" done echo "#endif /* HAVE_LIBELF_SUPPORT */" + +echo "#ifdef HAVE_LIBAUDIT_SUPPORT" +sed -n -e 's/^perf-\([^ ]*\)[ ].* audit*/\1/p' command-list.txt | +sort | +while read cmd +do + sed -n ' + /^NAME/,/perf-'"$cmd"'/H + ${ + x + s/.*perf-'"$cmd"' - \(.*\)/ {"'"$cmd"'", "\1"},/ + p + }' "Documentation/perf-$cmd.txt" +done +echo "#endif /* HAVE_LIBELF_SUPPORT */" echo "};" From 2d7c03e6b0c604decae33b0ce03e69b79b2a39a1 Mon Sep 17 00:00:00 2001 From: Wang Nan Date: Fri, 8 Jan 2016 14:23:57 +0000 Subject: [PATCH 45/59] perf tools: Add missing headers in perf's MANIFEST These lost headers are found in arm64 cross buildings, failing to build perf using tarballs generated using: $ make perf-targz-src-pkg Signed-off-by: Wang Nan Cc: Jiri Olsa Cc: Namhyung Kim Cc: Zefan Li Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1452263041-225488-3-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/MANIFEST | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST index b3db8dfebbf2..ddf922f93aa1 100644 --- a/tools/perf/MANIFEST +++ b/tools/perf/MANIFEST @@ -1,6 +1,7 @@ tools/perf tools/arch/alpha/include/asm/barrier.h tools/arch/arm/include/asm/barrier.h +tools/arch/arm64/include/asm/barrier.h tools/arch/ia64/include/asm/barrier.h tools/arch/mips/include/asm/barrier.h tools/arch/powerpc/include/asm/barrier.h @@ -30,6 +31,7 @@ tools/lib/find_bit.c tools/include/asm/atomic.h tools/include/asm/barrier.h tools/include/asm/bug.h +tools/include/asm-generic/atomic-gcc.h tools/include/asm-generic/barrier.h tools/include/asm-generic/bitops/arch_hweight.h tools/include/asm-generic/bitops/atomic.h From 9cdbc409626b29ab30f06a6393db6763f040f753 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 7 Jan 2016 10:14:05 +0100 Subject: [PATCH 46/59] perf script: Align event name properly Adding code to align event names, so we get aligned output in case of multiple events with different names. Before: $ perf script :13757 13757 163918.230829: cpu/mem-snp-none/P: ffff88085f20d010 :13757 13757 163918.230832: cpu/mem-loads,ldlat=30/P: 7f5a5f719f00 :13757 13757 163918.230835: cpu/mem-loads,ldlat=30/P: 7f5a5f719f00 :13758 13758 163918.230838: cpu/mem-snp-none/P: ffff88085f4ad810 :13758 13758 163918.154093: cpu/mem-stores/P: ffff88085bb53f28 :13757 13757 163918.155264: cpu/mem-snp-hitm/P: 601080 ... After: $ perf script :13757 13757 163918.228831: cpu/mem-snp-none/P: ffffffff81a841c0 :13757 13757 163918.228834: cpu/mem-loads,ldlat=30/P: 7f5a5f719f08 :13757 13757 163918.228837: cpu/mem-loads,ldlat=30/P: 7f5a5f719f08 :13758 13758 163918.228837: cpu/mem-snp-none/P: ffff88085f4ad800 :13758 13758 163918.154093: cpu/mem-stores/P: ffff88085bb53f28 :13757 13757 163918.155264: cpu/mem-snp-hitm/P: 601080 ... Signed-off-by: Jiri Olsa Acked-by: David Ahern Cc: Adrian Hunter Cc: Namhyung Kim Cc: Noel Grandin Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1452158050-28061-9-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 24 ++++++++++++++++++++++-- 1 file changed, 22 insertions(+), 2 deletions(-) diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 5e2f9d20a296..c691214d820f 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -617,9 +617,24 @@ struct perf_script { bool allocated; struct cpu_map *cpus; struct thread_map *threads; + int name_width; }; -static void process_event(struct perf_script *script __maybe_unused, union perf_event *event, +static int perf_evlist__max_name_len(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + int max = 0; + + evlist__for_each(evlist, evsel) { + int len = strlen(perf_evsel__name(evsel)); + + max = MAX(len, max); + } + + return max; +} + +static void process_event(struct perf_script *script, union perf_event *event, struct perf_sample *sample, struct perf_evsel *evsel, struct addr_location *al) { @@ -636,7 +651,12 @@ static void process_event(struct perf_script *script __maybe_unused, union perf_ if (PRINT_FIELD(EVNAME)) { const char *evname = perf_evsel__name(evsel); - printf("%s: ", evname ? evname : "[unknown]"); + + if (!script->name_width) + script->name_width = perf_evlist__max_name_len(script->session->evlist); + + printf("%*s: ", script->name_width, + evname ? evname : "[unknown]"); } if (print_flags) From 685c84154cef61dd7d961f36ab92f13c3ef5d354 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 7 Jan 2016 10:14:06 +0100 Subject: [PATCH 47/59] perf tools: Include all tools/lib directory for tags/cscope/TAGS targets Besides lockdep we use all the 'tools/lib' code in perf, so include it completely in tags. Signed-off-by: Jiri Olsa Cc: Adrian Hunter Cc: David Ahern Cc: Namhyung Kim Cc: Noel Grandin Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1452158050-28061-10-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Makefile.perf | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 404e3b1c4e31..1025ea79b90b 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -488,7 +488,7 @@ INSTALL_DOC_TARGETS += quick-install-doc quick-install-man quick-install-html $(DOC_TARGETS): $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) $(@:doc=all) -TAG_FOLDERS= . ../lib/traceevent ../lib/api ../lib/symbol ../include ../lib/bpf +TAG_FOLDERS= . ../lib ../include TAG_FILES= ../../include/uapi/linux/perf_event.h TAGS: From bb4ced29f5d5ff1d4d51b602dad34a0d15495a67 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 7 Jan 2016 10:14:07 +0100 Subject: [PATCH 48/59] perf tools: Remove list entry from struct sort_entry It's no longer needed. Signed-off-by: Jiri Olsa Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: David Ahern Cc: Noel Grandin Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1452158050-28061-11-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/sort.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index dec536b6ab3d..687bbb124428 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -214,8 +214,6 @@ enum sort_type { */ struct sort_entry { - struct list_head list; - const char *se_header; int64_t (*se_cmp)(struct hist_entry *, struct hist_entry *); From b97511c5bc94ef12613f485ab82f989df04088da Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 7 Jan 2016 10:14:08 +0100 Subject: [PATCH 49/59] perf tools: Add overhead/overhead_children keys defaults via string We currently set 'overhead' and 'overhead_children' as default sort keys within perf_hpp__init function by directly adding into the sort list. This patch adds 'overhead' and 'overhead_children' in text form into sort_keys and let them be added by standard sort dimension interface. We need to eliminate dirrect sort_list additions to be able to add support for hists specific sort keys. Signed-off-by: Jiri Olsa Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: David Ahern Cc: Noel Grandin Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1452158050-28061-12-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/ui/hist.c | 12 ------------ tools/perf/util/sort.c | 39 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 39 insertions(+), 12 deletions(-) diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c index 8263c0eb9fb5..bf2a66e254ea 100644 --- a/tools/perf/ui/hist.c +++ b/tools/perf/ui/hist.c @@ -443,7 +443,6 @@ LIST_HEAD(perf_hpp__sort_list); void perf_hpp__init(void) { - struct list_head *list; int i; for (i = 0; i < PERF_HPP__MAX_INDEX; i++) { @@ -484,17 +483,6 @@ void perf_hpp__init(void) if (symbol_conf.show_total_period) hpp_dimension__add_output(PERF_HPP__PERIOD); - - /* prepend overhead field for backward compatiblity. */ - list = &perf_hpp__format[PERF_HPP__OVERHEAD].sort_list; - if (list_empty(list)) - list_add(list, &perf_hpp__sort_list); - - if (symbol_conf.cumulate_callchain) { - list = &perf_hpp__format[PERF_HPP__OVERHEAD_ACC].sort_list; - if (list_empty(list)) - list_add(list, &perf_hpp__sort_list); - } } void perf_hpp__column_register(struct perf_hpp_fmt *format) diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 04e2a5cb19e3..ec722346e6ff 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -2252,6 +2252,34 @@ static int setup_sort_order(struct perf_evlist *evlist) return 0; } +/* + * Adds 'pre,' prefix into 'str' is 'pre' is + * not already part of 'str'. + */ +static char *prefix_if_not_in(const char *pre, char *str) +{ + char *n; + + if (!str || strstr(str, pre)) + return str; + + if (asprintf(&n, "%s,%s", pre, str) < 0) + return NULL; + + free(str); + return n; +} + +static char *setup_overhead(char *keys) +{ + keys = prefix_if_not_in("overhead", keys); + + if (symbol_conf.cumulate_callchain) + keys = prefix_if_not_in("overhead_children", keys); + + return keys; +} + static int __setup_sorting(struct perf_evlist *evlist) { char *tmp, *tok, *str; @@ -2281,6 +2309,17 @@ static int __setup_sorting(struct perf_evlist *evlist) return -ENOMEM; } + /* + * Prepend overhead fields for backward compatibility. + */ + if (!is_strict_order(field_order)) { + str = setup_overhead(str); + if (str == NULL) { + error("Not enough memory to setup overhead keys"); + return -ENOMEM; + } + } + for (tok = strtok_r(str, ", ", &tmp); tok; tok = strtok_r(NULL, ", ", &tmp)) { ret = sort_dimension__add(tok, evlist); From 21e6d8428664293f203be3004dcd8d70f68ebdb9 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 7 Jan 2016 10:14:09 +0100 Subject: [PATCH 50/59] perf diff: Use perf_hpp__register_sort_field interface Using perf_hpp__register_sort_field interface instead of directly adding the entry. Signed-off-by: Jiri Olsa Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: David Ahern Cc: Noel Grandin Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1452158050-28061-13-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-diff.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c index 87063835d741..36ccc2b8827f 100644 --- a/tools/perf/builtin-diff.c +++ b/tools/perf/builtin-diff.c @@ -1207,7 +1207,7 @@ static int ui_init(void) BUG_ON(1); } - list_add(&fmt->sort_list, &perf_hpp__sort_list); + perf_hpp__register_sort_field(fmt); return 0; } From fc284be9d88528dd2a28d5471e40a6acde6c3036 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 7 Jan 2016 10:14:10 +0100 Subject: [PATCH 51/59] perf hists: Export a couple of hist functions These are necessary for multi threaded sample processing: - hists__get__get_rotate_entries_in() - hists__collapse_insert_entry() - __hists__init() Signed-off-by: Namhyung Kim Cc: Adrian Hunter Cc: David Ahern Cc: Noel Grandin Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1452158050-28061-14-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/hist.c | 19 ++++++++++++------- tools/perf/util/hist.h | 5 +++++ 2 files changed, 17 insertions(+), 7 deletions(-) diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 888776b43cb0..c226303e3da0 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -1007,9 +1007,8 @@ void hist_entry__delete(struct hist_entry *he) * collapse the histogram */ -static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused, - struct rb_root *root, - struct hist_entry *he) +bool hists__collapse_insert_entry(struct hists *hists __maybe_unused, + struct rb_root *root, struct hist_entry *he) { struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; @@ -1049,7 +1048,7 @@ static bool hists__collapse_insert_entry(struct hists *hists __maybe_unused, return true; } -static struct rb_root *hists__get_rotate_entries_in(struct hists *hists) +struct rb_root *hists__get_rotate_entries_in(struct hists *hists) { struct rb_root *root; @@ -1584,10 +1583,8 @@ int perf_hist_config(const char *var, const char *value) return 0; } -static int hists_evsel__init(struct perf_evsel *evsel) +int __hists__init(struct hists *hists) { - struct hists *hists = evsel__hists(evsel); - memset(hists, 0, sizeof(*hists)); hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT; hists->entries_in = &hists->entries_in_array[0]; @@ -1627,6 +1624,14 @@ static void hists_evsel__exit(struct perf_evsel *evsel) hists__delete_all_entries(hists); } +static int hists_evsel__init(struct perf_evsel *evsel) +{ + struct hists *hists = evsel__hists(evsel); + + __hists__init(hists); + return 0; +} + /* * XXX We probably need a hists_evsel__exit() to free the hist_entries * stored in the rbtree... diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index cb8f37349972..d4ec4822a103 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -185,6 +185,11 @@ static inline struct hists *evsel__hists(struct perf_evsel *evsel) } int hists__init(void); +int __hists__init(struct hists *hists); + +struct rb_root *hists__get_rotate_entries_in(struct hists *hists); +bool hists__collapse_insert_entry(struct hists *hists __maybe_unused, + struct rb_root *root, struct hist_entry *he); struct perf_hpp { char *buf; From 14cbfbeb76540cc0c53fbb0ba34b3a4900ebe40f Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 7 Jan 2016 20:41:53 +0900 Subject: [PATCH 52/59] perf report: Show random usage tip on the help line Currently perf report only shows a help message "For a higher level overview, try: perf report --sort comm,dso" unconditionally (even if the sort keys were used). Add more help tips and show randomly. Load tips from ${prefix}/share/doc/perf-tip/tips.txt file. $ perf report | tail 0.10% swapper [kernel.vmlinux] [k] irq_exit 0.09% swapper [kernel.vmlinux] [k] flush_smp_call_function_queue 0.08% swapper [kernel.vmlinux] [k] native_write_msr_safe 0.03% swapper [kernel.vmlinux] [k] group_sched_in 0.01% perf [kernel.vmlinux] [k] native_write_msr_safe # # (Tip: Search options using a keyword: perf report -h ) # Signed-off-by: Namhyung Kim Acked-by: Ingo Molnar Cc: Andi Kleen Cc: David Ahern Cc: Jiri Olsa Cc: Masami Hiramatsu Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Wang Nan Link: http://lkml.kernel.org/r/1452166913-27046-1-git-send-email-namhyung@kernel.org [ Renamed it to perf_tip() and the parameter dirname to dirpath to fix the build on older distros ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Build | 1 + tools/perf/Documentation/tips.txt | 14 ++++++++++++++ tools/perf/Makefile.perf | 3 +++ tools/perf/builtin-report.c | 2 +- tools/perf/config/Makefile | 6 ++++++ tools/perf/perf.c | 4 ++++ tools/perf/util/util.c | 27 +++++++++++++++++++++++++++ tools/perf/util/util.h | 2 ++ 8 files changed, 58 insertions(+), 1 deletion(-) create mode 100644 tools/perf/Documentation/tips.txt diff --git a/tools/perf/Build b/tools/perf/Build index 00c4b8c3d8ca..6b67e6f4179f 100644 --- a/tools/perf/Build +++ b/tools/perf/Build @@ -41,6 +41,7 @@ CFLAGS_perf.o += -DPERF_HTML_PATH="BUILD_STR($(htmldir_SQ))" \ -DPREFIX="BUILD_STR($(prefix_SQ))" \ -include $(OUTPUT)PERF-VERSION-FILE CFLAGS_builtin-trace.o += -DSTRACE_GROUPS_DIR="BUILD_STR($(STRACE_GROUPS_DIR_SQ))" +CFLAGS_builtin-report.o += -DTIPDIR="BUILD_STR($(tipdir_SQ))" libperf-y += util/ libperf-y += arch/ diff --git a/tools/perf/Documentation/tips.txt b/tools/perf/Documentation/tips.txt new file mode 100644 index 000000000000..a1c10e360db5 --- /dev/null +++ b/tools/perf/Documentation/tips.txt @@ -0,0 +1,14 @@ +For a higher level overview, try: perf report --sort comm,dso +Sample related events with: perf record -e '{cycles,instructions}:S' +Compare performance results with: perf diff [ ] +Boolean options have negative forms, e.g.: perf report --no-children +Customize output of perf script with: perf script -F event,ip,sym +Generate a script for your data: perf script -g +Save output of perf stat using: perf stat record +Create an archive with symtabs to analyse on other machine: perf archive +Search options using a keyword: perf report -h +Use parent filter to see specific call path: perf report -p +List events using substring match: perf list +To see list of saved events and attributes: perf evlist -v +Use --symfs if your symbol files are in non-standard locations +To see callchains in a more compact form: perf report -g folded diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 1025ea79b90b..0a22407e1d7d 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -567,6 +567,9 @@ endif $(call QUIET_INSTALL, perf_completion-script) \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d'; \ $(INSTALL) perf-completion.sh '$(DESTDIR_SQ)$(sysconfdir_SQ)/bash_completion.d/perf' + $(call QUIET_INSTALL, perf-tip) \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(tip_instdir_SQ)'; \ + $(INSTALL) Documentation/tips.txt -t '$(DESTDIR_SQ)$(tip_instdir_SQ)' install-tests: all install-gtk $(call QUIET_INSTALL, tests) \ diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index f10c663af996..d5a42ee12529 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -433,7 +433,7 @@ static int report__browse_hists(struct report *rep) int ret; struct perf_session *session = rep->session; struct perf_evlist *evlist = session->evlist; - const char *help = "For a higher level overview, try: perf report --sort comm,dso"; + const char *help = perf_tip(TIPDIR); switch (use_browser) { case 1: diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile index 18b2f96d0941..254d06e39bea 100644 --- a/tools/perf/config/Makefile +++ b/tools/perf/config/Makefile @@ -691,6 +691,7 @@ sharedir = $(prefix)/share template_dir = share/perf-core/templates STRACE_GROUPS_DIR = share/perf-core/strace/groups htmldir = share/doc/perf-doc +tipdir = share/doc/perf-tip ifeq ($(prefix),/usr) sysconfdir = /etc ETC_PERFCONFIG = $(sysconfdir)/perfconfig @@ -717,6 +718,7 @@ infodir_SQ = $(subst ','\'',$(infodir)) perfexecdir_SQ = $(subst ','\'',$(perfexecdir)) template_dir_SQ = $(subst ','\'',$(template_dir)) htmldir_SQ = $(subst ','\'',$(htmldir)) +tipdir_SQ = $(subst ','\'',$(tipdir)) prefix_SQ = $(subst ','\'',$(prefix)) sysconfdir_SQ = $(subst ','\'',$(sysconfdir)) libdir_SQ = $(subst ','\'',$(libdir)) @@ -724,12 +726,15 @@ libdir_SQ = $(subst ','\'',$(libdir)) ifneq ($(filter /%,$(firstword $(perfexecdir))),) perfexec_instdir = $(perfexecdir) STRACE_GROUPS_INSTDIR = $(STRACE_GROUPS_DIR) +tip_instdir = $(tipdir) else perfexec_instdir = $(prefix)/$(perfexecdir) STRACE_GROUPS_INSTDIR = $(prefix)/$(STRACE_GROUPS_DIR) +tip_instdir = $(prefix)/$(tipdir) endif perfexec_instdir_SQ = $(subst ','\'',$(perfexec_instdir)) STRACE_GROUPS_INSTDIR_SQ = $(subst ','\'',$(STRACE_GROUPS_INSTDIR)) +tip_instdir_SQ = $(subst ','\'',$(tip_instdir)) # If we install to $(HOME) we keep the traceevent default: # $(HOME)/.traceevent/plugins @@ -770,6 +775,7 @@ $(call detected_var,ETC_PERFCONFIG_SQ) $(call detected_var,STRACE_GROUPS_DIR_SQ) $(call detected_var,prefix_SQ) $(call detected_var,perfexecdir_SQ) +$(call detected_var,tipdir_SQ) $(call detected_var,LIBDIR) $(call detected_var,GTK_CFLAGS) $(call detected_var,PERL_EMBED_CCOPTS) diff --git a/tools/perf/perf.c b/tools/perf/perf.c index cb1d2499c45c..a929618b8eb6 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -19,6 +19,8 @@ #include "util/debug.h" #include #include +#include +#include const char perf_usage_string[] = "perf [--version] [--help] [OPTIONS] COMMAND [ARGS]"; @@ -542,6 +544,8 @@ int main(int argc, const char **argv) if (!cmd) cmd = "perf-help"; + srandom(time(NULL)); + /* get debugfs/tracefs mount point from /proc/mounts */ tracing_path_mount(); diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index aff0cfd83662..88b8f8d21f58 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -16,6 +16,8 @@ #include #include #include "callchain.h" +#include "strlist.h" +#include struct callchain_param callchain_param = { .mode = CHAIN_GRAPH_ABS, @@ -663,3 +665,28 @@ fetch_kernel_version(unsigned int *puint, char *str, *puint = (version << 16) + (patchlevel << 8) + sublevel; return 0; } + +const char *perf_tip(const char *dirpath) +{ + struct strlist *tips; + struct str_node *node; + char *tip = NULL; + struct strlist_config conf = { + .dirname = system_path(dirpath) , + }; + + tips = strlist__new("tips.txt", &conf); + if (tips == NULL || strlist__nr_entries(tips) == 1) { + tip = (char *)"Cannot find tips.txt file"; + goto out; + } + + node = strlist__entry(tips, random() % strlist__nr_entries(tips)); + if (asprintf(&tip, "Tip: %s", node->s) < 0) + tip = (char *)"Tip: get more memory! ;-)"; + +out: + strlist__delete(tips); + + return tip; +} diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 4b519c59bdc3..fe915e616f9b 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -342,4 +342,6 @@ int fetch_kernel_version(unsigned int *puint, #define KVER_FMT "%d.%d.%d" #define KVER_PARAM(x) KVER_VERSION(x), KVER_PATCHLEVEL(x), KVER_SUBLEVEL(x) +const char *perf_tip(const char *dirpath); + #endif /* GIT_COMPAT_UTIL_H */ From 23df7f798435796aff07d641456326b81cb34a77 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Thu, 7 Jan 2016 10:13:59 +0100 Subject: [PATCH 53/59] perf evlist: Make perf_evlist__open() open evsels with their cpus and threads (like perf record does) 'perf record' uses perf_evsel__open() to open events and passes the evsel->cpus and evsel->threads. Many tests and some tools instead use perf_evlist__open() which passes instead evlist->cpus and evlist->threads. Make perf_evlist__open() follow the 'perf record' behaviour so that a consistent approach is taken. Signed-off-by: Adrian Hunter Cc: David Ahern Cc: Namhyung Kim Cc: Noel Grandin Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1452158050-28061-3-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evlist.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index fa6dbf0ea0d6..29e085b2e168 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -1498,7 +1498,7 @@ int perf_evlist__open(struct perf_evlist *evlist) perf_evlist__update_id_pos(evlist); evlist__for_each(evlist, evsel) { - err = perf_evsel__open(evsel, evlist->cpus, evlist->threads); + err = perf_evsel__open(evsel, evsel->cpus, evsel->threads); if (err < 0) goto out_err; } From d2190a8091124f832c8862ace3a3d7d70a2506a5 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 7 Jan 2016 10:13:58 +0100 Subject: [PATCH 54/59] perf evlist: Remove perf_evlist__(enable|disable)_event functions Replacing them with perf_evsel__(enable|disable). Signed-off-by: Jiri Olsa Cc: Adrian Hunter Cc: David Ahern Cc: Namhyung Kim Cc: Noel Grandin Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1452158050-28061-2-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/arch/x86/util/intel-bts.c | 4 +-- tools/perf/arch/x86/util/intel-pt.c | 4 +-- tools/perf/tests/keep-tracking.c | 2 +- tools/perf/tests/switch-tracking.c | 6 ++-- tools/perf/util/evlist.c | 42 ---------------------------- tools/perf/util/evlist.h | 4 --- 6 files changed, 8 insertions(+), 54 deletions(-) diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c index 9b94ce520917..8d8150f1cf9b 100644 --- a/tools/perf/arch/x86/util/intel-bts.c +++ b/tools/perf/arch/x86/util/intel-bts.c @@ -327,7 +327,7 @@ static int intel_bts_snapshot_start(struct auxtrace_record *itr) evlist__for_each(btsr->evlist, evsel) { if (evsel->attr.type == btsr->intel_bts_pmu->type) - return perf_evlist__disable_event(btsr->evlist, evsel); + return perf_evsel__disable(evsel); } return -EINVAL; } @@ -340,7 +340,7 @@ static int intel_bts_snapshot_finish(struct auxtrace_record *itr) evlist__for_each(btsr->evlist, evsel) { if (evsel->attr.type == btsr->intel_bts_pmu->type) - return perf_evlist__enable_event(btsr->evlist, evsel); + return perf_evsel__enable(evsel); } return -EINVAL; } diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index b64d46285ebb..f05daacc9e78 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -725,7 +725,7 @@ static int intel_pt_snapshot_start(struct auxtrace_record *itr) evlist__for_each(ptr->evlist, evsel) { if (evsel->attr.type == ptr->intel_pt_pmu->type) - return perf_evlist__disable_event(ptr->evlist, evsel); + return perf_evsel__disable(evsel); } return -EINVAL; } @@ -738,7 +738,7 @@ static int intel_pt_snapshot_finish(struct auxtrace_record *itr) evlist__for_each(ptr->evlist, evsel) { if (evsel->attr.type == ptr->intel_pt_pmu->type) - return perf_evlist__enable_event(ptr->evlist, evsel); + return perf_evsel__enable(evsel); } return -EINVAL; } diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c index 615813278334..ddb78fae064a 100644 --- a/tools/perf/tests/keep-tracking.c +++ b/tools/perf/tests/keep-tracking.c @@ -123,7 +123,7 @@ int test__keep_tracking(int subtest __maybe_unused) evsel = perf_evlist__last(evlist); - CHECK__(perf_evlist__disable_event(evlist, evsel)); + CHECK__(perf_evsel__disable(evsel)); comm = "Test COMM 2"; CHECK__(prctl(PR_SET_NAME, (unsigned long)comm, 0, 0, 0)); diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c index dfbd8d69ce89..ebd80168d51e 100644 --- a/tools/perf/tests/switch-tracking.c +++ b/tools/perf/tests/switch-tracking.c @@ -455,7 +455,7 @@ int test__switch_tracking(int subtest __maybe_unused) perf_evlist__enable(evlist); - err = perf_evlist__disable_event(evlist, cpu_clocks_evsel); + err = perf_evsel__disable(cpu_clocks_evsel); if (err) { pr_debug("perf_evlist__disable_event failed!\n"); goto out_err; @@ -474,7 +474,7 @@ int test__switch_tracking(int subtest __maybe_unused) goto out_err; } - err = perf_evlist__disable_event(evlist, cycles_evsel); + err = perf_evsel__disable(cycles_evsel); if (err) { pr_debug("perf_evlist__disable_event failed!\n"); goto out_err; @@ -500,7 +500,7 @@ int test__switch_tracking(int subtest __maybe_unused) goto out_err; } - err = perf_evlist__enable_event(evlist, cycles_evsel); + err = perf_evsel__enable(cycles_evsel); if (err) { pr_debug("perf_evlist__disable_event failed!\n"); goto out_err; diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 29e085b2e168..d81f13de2476 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -393,48 +393,6 @@ void perf_evlist__toggle_enable(struct perf_evlist *evlist) (evlist->enabled ? perf_evlist__disable : perf_evlist__enable)(evlist); } -int perf_evlist__disable_event(struct perf_evlist *evlist, - struct perf_evsel *evsel) -{ - int cpu, thread, err; - int nr_cpus = cpu_map__nr(evlist->cpus); - int nr_threads = perf_evlist__nr_threads(evlist, evsel); - - if (!evsel->fd) - return 0; - - for (cpu = 0; cpu < nr_cpus; cpu++) { - for (thread = 0; thread < nr_threads; thread++) { - err = ioctl(FD(evsel, cpu, thread), - PERF_EVENT_IOC_DISABLE, 0); - if (err) - return err; - } - } - return 0; -} - -int perf_evlist__enable_event(struct perf_evlist *evlist, - struct perf_evsel *evsel) -{ - int cpu, thread, err; - int nr_cpus = cpu_map__nr(evlist->cpus); - int nr_threads = perf_evlist__nr_threads(evlist, evsel); - - if (!evsel->fd) - return -EINVAL; - - for (cpu = 0; cpu < nr_cpus; cpu++) { - for (thread = 0; thread < nr_threads; thread++) { - err = ioctl(FD(evsel, cpu, thread), - PERF_EVENT_IOC_ENABLE, 0); - if (err) - return err; - } - } - return 0; -} - static int perf_evlist__enable_event_cpu(struct perf_evlist *evlist, struct perf_evsel *evsel, int cpu) { diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 3b7e1e2f1a86..7c4d9a206776 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -155,10 +155,6 @@ void perf_evlist__disable(struct perf_evlist *evlist); void perf_evlist__enable(struct perf_evlist *evlist); void perf_evlist__toggle_enable(struct perf_evlist *evlist); -int perf_evlist__disable_event(struct perf_evlist *evlist, - struct perf_evsel *evsel); -int perf_evlist__enable_event(struct perf_evlist *evlist, - struct perf_evsel *evsel); int perf_evlist__enable_event_idx(struct perf_evlist *evlist, struct perf_evsel *evsel, int idx); From f22ed827a8d5ff5a85e7c8e865baaaaf71a8d0cc Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 7 Jan 2016 10:14:00 +0100 Subject: [PATCH 55/59] perf unwind: Use find_map function in access_dso_mem The find_map helper is already there, so let's use it. Also we're going to introduce wider search in following patch, so it'll be easier to make this change on single place. Signed-off-by: Jiri Olsa Tested-by: Noel Grandin Cc: Adrian Hunter Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1452158050-28061-4-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/unwind-libunwind.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index 3c258a0e4092..f37859c04317 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -416,20 +416,19 @@ get_proc_name(unw_addr_space_t __maybe_unused as, static int access_dso_mem(struct unwind_info *ui, unw_word_t addr, unw_word_t *data) { - struct addr_location al; + struct map *map; ssize_t size; - thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER, - MAP__FUNCTION, addr, &al); - if (!al.map) { + map = find_map(addr, ui); + if (!map) { pr_debug("unwind: no map for %lx\n", (unsigned long)addr); return -1; } - if (!al.map->dso) + if (!map->dso) return -1; - size = dso__data_read_addr(al.map->dso, al.map, ui->machine, + size = dso__data_read_addr(map->dso, map, ui->machine, addr, (u8 *) data, sizeof(*data)); return !(size == sizeof(*data)); From 0ddf5246f70ecc04e1bb4c4dc2be65977d1c03a7 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 7 Jan 2016 10:14:01 +0100 Subject: [PATCH 56/59] perf unwind: Check for mmaps also in MAP__VARIABLE tree We've seen cases (softice) where DWARF unwinder went through non executable mmaps, which we need to lookup in MAP__VARIABLE tree. Reported-and-Tested-by: Noel Grandin Signed-off-by: Jiri Olsa Cc: Adrian Hunter Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1452158050-28061-5-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/unwind-libunwind.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index f37859c04317..ee7e372297e5 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -319,6 +319,15 @@ static struct map *find_map(unw_word_t ip, struct unwind_info *ui) thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER, MAP__FUNCTION, ip, &al); + if (!al.map) { + /* + * We've seen cases (softice) where DWARF unwinder went + * through non executable mmaps, which we need to lookup + * in MAP__VARIABLE tree. + */ + thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER, + MAP__VARIABLE, ip, &al); + } return al.map; } From 0ba98149f8c8b6b2ba36be9938afb731fa719004 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 7 Jan 2016 10:14:02 +0100 Subject: [PATCH 57/59] perf libdw: Check for mmaps also in MAP__VARIABLE tree We've seen cases (softice) where DWARF unwinder went through non executable mmaps, which we need to lookup in MAP__VARIABLE tree. Reported-and-Tested-by: Noel Grandin Signed-off-by: Jiri Olsa Cc: Adrian Hunter Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1452158050-28061-6-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/unwind-libdw.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index db8142ba7cb9..cf5e250bc78e 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -95,6 +95,16 @@ static int access_dso_mem(struct unwind_info *ui, Dwarf_Addr addr, thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER, MAP__FUNCTION, addr, &al); + if (!al.map) { + /* + * We've seen cases (softice) where DWARF unwinder went + * through non executable mmaps, which we need to lookup + * in MAP__VARIABLE tree. + */ + thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER, + MAP__VARIABLE, addr, &al); + } + if (!al.map) { pr_debug("unwind: no map for %lx\n", (unsigned long)addr); return -1; From 5c0cf22477eaa890beeb4bc3554e5bebbea4b007 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Thu, 7 Jan 2016 14:30:22 +0100 Subject: [PATCH 58/59] perf record: Store data mmaps for dwarf unwind Currently we don't synthesize data mmap by default. It depends on -d option, that enables data address sampling. But we've seen cases (softice) where DWARF unwinder went through non executable mmaps, which we need to lookup in MAP__VARIABLE tree. Making data mmaps to be synthesized for dwarf unwind as well. Reported-by: Noel Grandin Signed-off-by: Jiri Olsa Cc: Adrian Hunter Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20160107133022.GA32115@krava.brq.redhat.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-record.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 9c5cdc2c4471..dc4e0adf5c5b 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -815,8 +815,12 @@ int record_parse_callchain_opt(const struct option *opt, } ret = parse_callchain_record_opt(arg, &callchain_param); - if (!ret) + if (!ret) { + /* Enable data address sampling for DWARF unwind. */ + if (callchain_param.record_mode == CALLCHAIN_DWARF) + record->sample_address = true; callchain_debug(); + } return ret; } From 775d8a1b0d75211cc6123915c6b5b688f2002478 Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Thu, 7 Jan 2016 09:12:29 +0900 Subject: [PATCH 59/59] perf evlist: Add --trace-fields option to show trace fields To use dynamic sort keys, it might be good to add an option to see the list of field names. $ perf evlist -i perf.data.sched sched:sched_switch sched:sched_stat_wait sched:sched_stat_sleep sched:sched_stat_iowait sched:sched_stat_runtime sched:sched_process_fork sched:sched_wakeup sched:sched_wakeup_new sched:sched_migrate_task # Tip: use 'perf evlist --trace-fields' to show fields for tracepoint events $ perf evlist -i perf.data.sched --trace-fields sched:sched_switch: trace_fields: prev_comm,prev_pid,prev_prio,prev_state,next_comm,next_pid,next_prio sched:sched_stat_wait: trace_fields: comm,pid,delay sched:sched_stat_sleep: trace_fields: comm,pid,delay sched:sched_stat_iowait: trace_fields: comm,pid,delay sched:sched_stat_runtime: trace_fields: comm,pid,runtime,vruntime sched:sched_process_fork: trace_fields: parent_comm,parent_pid,child_comm,child_pid sched:sched_wakeup: trace_fields: comm,pid,prio,success,target_cpu sched:sched_wakeup_new: trace_fields: comm,pid,prio,success,target_cpu sched:sched_migrate_task: trace_fields: comm,pid,prio,orig_cpu,dest_cpu Committer notes: For another file, in verbose mode: # perf evlist -v --trace-fields sched:sched_switch: type: 2, size: 112, config: 0x10b, { sample_period, sample_freq }: 1, sample_type: IP|TID|TIME|CPU|PERIOD|RAW, disabled: 1, inherit: 1, mmap: 1, comm: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, trace_fields: prev_comm,prev_pid,prev_prio,prev_state,next_comm,next_pid,next_prio # Signed-off-by: Namhyung Kim Cc: Andi Kleen Cc: David Ahern Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Wang Nan Link: http://lkml.kernel.org/r/1452125549-1511-5-git-send-email-namhyung@kernel.org [ Replaced 'trace_fields=' with 'trace_fields: ' to make the output consistent in -v mode ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-evlist.txt | 3 +++ tools/perf/builtin-evlist.c | 11 ++++++++++- tools/perf/util/evsel.c | 23 +++++++++++++++++++++++ tools/perf/util/evsel.h | 1 + 4 files changed, 37 insertions(+), 1 deletion(-) diff --git a/tools/perf/Documentation/perf-evlist.txt b/tools/perf/Documentation/perf-evlist.txt index 1ceb3700ffbb..6f7200fb85cf 100644 --- a/tools/perf/Documentation/perf-evlist.txt +++ b/tools/perf/Documentation/perf-evlist.txt @@ -32,6 +32,9 @@ OPTIONS --group:: Show event group information. +--trace-fields:: + Show tracepoint field names. + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-list[1], diff --git a/tools/perf/builtin-evlist.c b/tools/perf/builtin-evlist.c index 08a7d36a2cf8..8a31f511e1a0 100644 --- a/tools/perf/builtin-evlist.c +++ b/tools/perf/builtin-evlist.c @@ -26,14 +26,22 @@ static int __cmd_evlist(const char *file_name, struct perf_attr_details *details .mode = PERF_DATA_MODE_READ, .force = details->force, }; + bool has_tracepoint = false; session = perf_session__new(&file, 0, NULL); if (session == NULL) return -1; - evlist__for_each(session->evlist, pos) + evlist__for_each(session->evlist, pos) { perf_evsel__fprintf(pos, details, stdout); + if (pos->attr.type == PERF_TYPE_TRACEPOINT) + has_tracepoint = true; + } + + if (has_tracepoint && !details->trace_fields) + printf("# Tip: use 'perf evlist --trace-fields' to show fields for tracepoint events\n"); + perf_session__delete(session); return 0; } @@ -49,6 +57,7 @@ int cmd_evlist(int argc, const char **argv, const char *prefix __maybe_unused) OPT_BOOLEAN('g', "group", &details.event_group, "Show event group information"), OPT_BOOLEAN('f', "force", &details.force, "don't complain, do it"), + OPT_BOOLEAN(0, "trace-fields", &details.trace_fields, "Show tracepoint fields"), OPT_END() }; const char * const evlist_usage[] = { diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 544e4400de13..cdbaf9b51e42 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -2298,6 +2298,29 @@ int perf_evsel__fprintf(struct perf_evsel *evsel, printed += comma_fprintf(fp, &first, " %s=%" PRIu64, term, (u64)evsel->attr.sample_freq); } + + if (details->trace_fields) { + struct format_field *field; + + if (evsel->attr.type != PERF_TYPE_TRACEPOINT) { + printed += comma_fprintf(fp, &first, " (not a tracepoint)"); + goto out; + } + + field = evsel->tp_format->format.fields; + if (field == NULL) { + printed += comma_fprintf(fp, &first, " (no trace field)"); + goto out; + } + + printed += comma_fprintf(fp, &first, " trace_fields: %s", field->name); + + field = field->next; + while (field) { + printed += comma_fprintf(fp, &first, "%s", field->name); + field = field->next; + } + } out: fputc('\n', fp); return ++printed; diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 5ded1fc0341e..8e75434bd01c 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -369,6 +369,7 @@ struct perf_attr_details { bool verbose; bool event_group; bool force; + bool trace_fields; }; int perf_evsel__fprintf(struct perf_evsel *evsel,