Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932654Ab2KENyp (ORCPT ); Mon, 5 Nov 2012 08:54:45 -0500 Received: from mail-wg0-f42.google.com ([74.125.82.42]:40949 "EHLO mail-wg0-f42.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932570Ab2KENxd (ORCPT ); Mon, 5 Nov 2012 08:53:33 -0500 From: Stephane Eranian To: linux-kernel@vger.kernel.org Cc: peterz@infradead.org, mingo@elte.hu, ak@linux.intel.com, acme@redhat.com, jolsa@redhat.com, namhyung.kim@lge.com Subject: [PATCH v2 12/16] perf report: add support for mem access profiling Date: Mon, 5 Nov 2012 14:50:59 +0100 Message-Id: <1352123463-7346-13-git-send-email-eranian@google.com> X-Mailer: git-send-email 1.7.9.5 In-Reply-To: <1352123463-7346-1-git-send-email-eranian@google.com> References: <1352123463-7346-1-git-send-email-eranian@google.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 7702 Lines: 223 This patch adds the --mem-mode option to perf report. This mode requires a perf.data file created with memory access samples. Signed-off-by: Stephane Eranian --- tools/perf/builtin-report.c | 131 +++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 127 insertions(+), 4 deletions(-) diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index f07eae7..14cb7c1 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -46,6 +46,7 @@ struct perf_report { bool show_full_info; bool show_threads; bool inverted_callchain; + bool mem_mode; struct perf_read_values show_threads_values; const char *pretty_printing_style; symbol_filter_t annotate_init; @@ -54,6 +55,96 @@ struct perf_report { DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS); }; +static int perf_report__add_mem_hist_entry(struct perf_tool *tool, + struct addr_location *al, + struct perf_sample *sample, + struct perf_evsel *evsel, + struct machine *machine, + union perf_event *event) +{ + struct perf_report *rep = container_of(tool, struct perf_report, tool); + struct symbol *parent = NULL; + u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; + int err = 0; + struct hist_entry *he; + struct mem_info *mi, *mx; + uint64_t cost; + + if ((sort__has_parent || symbol_conf.use_callchain) + && sample->callchain) { + err = machine__resolve_callchain(machine, evsel, al->thread, + sample, &parent); + if (err) + return err; + } + + mi = machine__resolve_mem(machine, al->thread, sample, cpumode); + if (!mi) + return -ENOMEM; + + if (rep->hide_unresolved && !al->sym) + return 0; + + cost = mi->cost; + if (!cost) + cost = 1; + + /* + * The report shows the percentage of total branches captured + * and not events sampled. Thus we use a pseudo period of 1. + * Only in the newt browser we are doing integrated annotation, + * so we don't allocated the extra space needed because the stdio + * code will not use it. + */ + he = __hists__add_mem_entry(&evsel->hists, al, parent, mi, + cost); + if (!he) + return -ENOMEM; + + if (sort__has_sym && he->ms.sym && use_browser > 0) { + struct annotation *notes = symbol__annotation(he->ms.sym); + + assert(evsel != NULL); + + if (notes->src == NULL && symbol__alloc_hist(he->ms.sym) < 0) + goto out; + + err = hist_entry__inc_addr_samples(he, evsel->idx, al->addr); + if (err) + goto out; + } + + if (sort__has_sym && he->mem_info->daddr.sym && use_browser > 0) { + struct annotation *notes; + + mx = he->mem_info; + + notes = symbol__annotation(mx->daddr.sym); + if (!notes->src + && symbol__alloc_hist(mx->daddr.sym) < 0) + goto out; + + err = symbol__inc_addr_samples(mx->daddr.sym, + mx->daddr.map, + evsel->idx, + mx->daddr.al_addr); + if (err) + goto out; + } + + evsel->hists.stats.total_period += sample->period; + hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE); + err = 0; + + if (symbol_conf.use_callchain) { + err = callchain_append(he->callchain, + &callchain_cursor, + sample->period); + } +out: + return err; +} + static int perf_report__add_branch_hist_entry(struct perf_tool *tool, struct addr_location *al, struct perf_sample *sample, @@ -209,6 +300,12 @@ static int process_sample_event(struct perf_tool *tool, pr_debug("problem adding lbr entry, skipping event\n"); return -1; } + } else if (rep->mem_mode == 1) { + if (perf_report__add_mem_hist_entry(tool, &al, sample, + evsel, machine, event)) { + pr_debug("problem adding mem entry, skipping event\n"); + return -1; + } } else { if (al.map != NULL) al.map->dso->hit = 1; @@ -292,7 +389,8 @@ static void sig_handler(int sig __maybe_unused) session_done = 1; } -static size_t hists__fprintf_nr_sample_events(struct hists *self, +static size_t hists__fprintf_nr_sample_events(struct perf_report *rep, + struct hists *self, const char *evname, FILE *fp) { size_t ret; @@ -305,7 +403,11 @@ static size_t hists__fprintf_nr_sample_events(struct hists *self, if (evname != NULL) ret += fprintf(fp, " of event '%s'", evname); - ret += fprintf(fp, "\n# Event count (approx.): %" PRIu64, nr_events); + if (rep->mem_mode) { + ret += fprintf(fp, "\n# Total cost : %" PRIu64, nr_events); + ret += fprintf(fp, "\n# Sort order : %s", sort_order); + } else + ret += fprintf(fp, "\n# Event count (approx.): %" PRIu64, nr_events); return ret + fprintf(fp, "\n#\n"); } @@ -319,7 +421,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist, struct hists *hists = &pos->hists; const char *evname = perf_evsel__name(pos); - hists__fprintf_nr_sample_events(hists, evname, stdout); + hists__fprintf_nr_sample_events(rep, hists, evname, stdout); hists__fprintf(hists, true, 0, 0, stdout); fprintf(stdout, "\n\n"); } @@ -595,7 +697,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) "Use the stdio interface"), OPT_STRING('s', "sort", &sort_order, "key[,key2...]", "sort by key(s): pid, comm, dso, symbol, parent, dso_to," - " dso_from, symbol_to, symbol_from, mispredict"), + " dso_from, symbol_to, symbol_from, mispredict, mem, cost, symbol_daddr, dso_daddr, tlb, snoop, locked"), OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization, "Show sample percentage for different cpu modes"), OPT_STRING('p', "parent", &parent_pattern, "regex", @@ -641,6 +743,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) "use branch records for histogram filling", parse_branch_mode), OPT_STRING(0, "objdump", &objdump_path, "path", "objdump binary to use for disassembly and annotations"), + OPT_BOOLEAN(0, "mem-mode", &report.mem_mode, "mem access profile"), OPT_END() }; @@ -692,6 +795,18 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) "dso_to,symbol_to"; } + if (report.mem_mode) { + if (sort__branch_mode == 1) { + fprintf(stderr, "branch and mem mode incompatible\n"); + goto error; + } + /* + * if no sort_order is provided, then specify + * branch-mode specific order + */ + if (sort_order == default_sort_order) + sort_order = "cost,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked"; + } if (strcmp(input_name, "-") != 0) setup_browser(true); @@ -763,6 +878,14 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) sort_entry__setup_elide(&sort_sym_from, symbol_conf.sym_from_list, "sym_from", stdout); sort_entry__setup_elide(&sort_sym_to, symbol_conf.sym_to_list, "sym_to", stdout); } else { + if (report.mem_mode) { + sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "symbol_daddr", stdout); + sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso_daddr", stdout); + sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "mem", stdout); + sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "cost", stdout); + sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "tlb", stdout); + sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "snoop", stdout); + } sort_entry__setup_elide(&sort_dso, symbol_conf.dso_list, "dso", stdout); sort_entry__setup_elide(&sort_sym, symbol_conf.sym_list, "symbol", stdout); } -- 1.7.9.5 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/