From d809560b36a7ed31fbaf3719fdf79ddcbd30950b Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 7 Aug 2015 12:51:03 +0200 Subject: perf stat: Move perf_counts struct and functions into separate object Moving 'struct perf_counts' and associated functions into separate object, so we could remove stat.c object dependency from python build. It makes the python code to build properly, because it fails to load due to missing stat-shadow.c object dependency if some patches from Kan Liang are applied. So apply this one, then Kan's. Signed-off-by: Jiri Olsa Cc: Andi Kleen Cc: Jiri Olsa Cc: Kan Liang Cc: Namhyung Kim Link: http://lkml.kernel.org/r/20150807105103.GB8624@krava.brq.redhat.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 1 + tools/perf/util/Build | 1 + tools/perf/util/counts.c | 52 ++++++++++++++++++++++++++++++++++++++ tools/perf/util/counts.h | 37 +++++++++++++++++++++++++++ tools/perf/util/evsel.h | 2 +- tools/perf/util/python-ext-sources | 2 +- tools/perf/util/stat.c | 49 ----------------------------------- tools/perf/util/stat.h | 30 ---------------------- 8 files changed, 93 insertions(+), 81 deletions(-) create mode 100644 tools/perf/util/counts.c create mode 100644 tools/perf/util/counts.h diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index a054ddc0b2a0..7aa039bd379a 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -58,6 +58,7 @@ #include "util/cpumap.h" #include "util/thread.h" #include "util/thread_map.h" +#include "util/counts.h" #include #include diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 2ee81d74cf45..1ce0adc8b3cb 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -68,6 +68,7 @@ libperf-y += target.o libperf-y += rblist.o libperf-y += intlist.o libperf-y += vdso.o +libperf-y += counts.o libperf-y += stat.o libperf-y += stat-shadow.o libperf-y += record.o diff --git a/tools/perf/util/counts.c b/tools/perf/util/counts.c new file mode 100644 index 000000000000..e3fde313deb2 --- /dev/null +++ b/tools/perf/util/counts.c @@ -0,0 +1,52 @@ +#include +#include "evsel.h" +#include "counts.h" + +struct perf_counts *perf_counts__new(int ncpus, int nthreads) +{ + struct perf_counts *counts = zalloc(sizeof(*counts)); + + if (counts) { + struct xyarray *values; + + values = xyarray__new(ncpus, nthreads, sizeof(struct perf_counts_values)); + if (!values) { + free(counts); + return NULL; + } + + counts->values = values; + } + + return counts; +} + +void perf_counts__delete(struct perf_counts *counts) +{ + if (counts) { + xyarray__delete(counts->values); + free(counts); + } +} + +static void perf_counts__reset(struct perf_counts *counts) +{ + xyarray__reset(counts->values); +} + +void perf_evsel__reset_counts(struct perf_evsel *evsel) +{ + perf_counts__reset(evsel->counts); +} + +int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus, int nthreads) +{ + evsel->counts = perf_counts__new(ncpus, nthreads); + return evsel->counts != NULL ? 0 : -ENOMEM; +} + +void perf_evsel__free_counts(struct perf_evsel *evsel) +{ + perf_counts__delete(evsel->counts); + evsel->counts = NULL; +} diff --git a/tools/perf/util/counts.h b/tools/perf/util/counts.h new file mode 100644 index 000000000000..34d8baaf558a --- /dev/null +++ b/tools/perf/util/counts.h @@ -0,0 +1,37 @@ +#ifndef __PERF_COUNTS_H +#define __PERF_COUNTS_H + +#include "xyarray.h" + +struct perf_counts_values { + union { + struct { + u64 val; + u64 ena; + u64 run; + }; + u64 values[3]; + }; +}; + +struct perf_counts { + s8 scaled; + struct perf_counts_values aggr; + struct xyarray *values; +}; + + +static inline struct perf_counts_values* +perf_counts(struct perf_counts *counts, int cpu, int thread) +{ + return xyarray__entry(counts->values, cpu, thread); +} + +struct perf_counts *perf_counts__new(int ncpus, int nthreads); +void perf_counts__delete(struct perf_counts *counts); + +void perf_evsel__reset_counts(struct perf_evsel *evsel); +int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus, int nthreads); +void perf_evsel__free_counts(struct perf_evsel *evsel); + +#endif /* __PERF_COUNTS_H */ diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 6a129081f3ad..b948f69d2558 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -9,7 +9,7 @@ #include "xyarray.h" #include "symbol.h" #include "cpumap.h" -#include "stat.h" +#include "counts.h" struct perf_evsel; diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index 0766d98c5da5..51be28b1bca2 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -16,7 +16,7 @@ util/util.c util/xyarray.c util/cgroup.c util/rblist.c -util/stat.c +util/counts.c util/strlist.c util/trace-event.c ../lib/rbtree.c diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index c5c709cdc3ce..415c359de465 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -97,55 +97,6 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel) } } -struct perf_counts *perf_counts__new(int ncpus, int nthreads) -{ - struct perf_counts *counts = zalloc(sizeof(*counts)); - - if (counts) { - struct xyarray *values; - - values = xyarray__new(ncpus, nthreads, sizeof(struct perf_counts_values)); - if (!values) { - free(counts); - return NULL; - } - - counts->values = values; - } - - return counts; -} - -void perf_counts__delete(struct perf_counts *counts) -{ - if (counts) { - xyarray__delete(counts->values); - free(counts); - } -} - -static void perf_counts__reset(struct perf_counts *counts) -{ - xyarray__reset(counts->values); -} - -void perf_evsel__reset_counts(struct perf_evsel *evsel) -{ - perf_counts__reset(evsel->counts); -} - -int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus, int nthreads) -{ - evsel->counts = perf_counts__new(ncpus, nthreads); - return evsel->counts != NULL ? 0 : -ENOMEM; -} - -void perf_evsel__free_counts(struct perf_evsel *evsel) -{ - perf_counts__delete(evsel->counts); - evsel->counts = NULL; -} - void perf_evsel__reset_stat_priv(struct perf_evsel *evsel) { int i; diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 0b897b083682..62448c8175d3 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -33,23 +33,6 @@ enum aggr_mode { AGGR_THREAD, }; -struct perf_counts_values { - union { - struct { - u64 val; - u64 ena; - u64 run; - }; - u64 values[3]; - }; -}; - -struct perf_counts { - s8 scaled; - struct perf_counts_values aggr; - struct xyarray *values; -}; - struct perf_stat_config { enum aggr_mode aggr_mode; bool scale; @@ -57,12 +40,6 @@ struct perf_stat_config { unsigned int interval; }; -static inline struct perf_counts_values* -perf_counts(struct perf_counts *counts, int cpu, int thread) -{ - return xyarray__entry(counts->values, cpu, thread); -} - void update_stats(struct stats *stats, u64 val); double avg_stats(struct stats *stats); double stddev_stats(struct stats *stats); @@ -96,13 +73,6 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count, void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel, double avg, int cpu, enum aggr_mode aggr); -struct perf_counts *perf_counts__new(int ncpus, int nthreads); -void perf_counts__delete(struct perf_counts *counts); - -void perf_evsel__reset_counts(struct perf_evsel *evsel); -int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus, int nthreads); -void perf_evsel__free_counts(struct perf_evsel *evsel); - void perf_evsel__reset_stat_priv(struct perf_evsel *evsel); int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel); void perf_evsel__free_stat_priv(struct perf_evsel *evsel); -- cgit v1.2.3 From 076a30c411ba2b91a18d44a5a01977035cdd7716 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Thu, 6 Aug 2015 15:44:52 -0400 Subject: perf callchain: Move option parsing code to util.c Move callchain option parse related code to util.c, to avoid dragging more object files into the python binding. Signed-off-by: Kan Liang Cc: Andi Kleen Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/1438890294-33409-1-git-send-email-kan.liang@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/callchain.c | 89 +------------------------------------------- tools/perf/util/callchain.h | 1 + tools/perf/util/util.c | 90 +++++++++++++++++++++++++++++++++++++++++++++ tools/perf/util/util.h | 2 + 4 files changed, 94 insertions(+), 88 deletions(-) diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index 931cca8e6ae8..773fe13ce627 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -25,96 +25,9 @@ __thread struct callchain_cursor callchain_cursor; -#ifdef HAVE_DWARF_UNWIND_SUPPORT -static int get_stack_size(const char *str, unsigned long *_size) -{ - char *endptr; - unsigned long size; - unsigned long max_size = round_down(USHRT_MAX, sizeof(u64)); - - size = strtoul(str, &endptr, 0); - - do { - if (*endptr) - break; - - size = round_up(size, sizeof(u64)); - if (!size || size > max_size) - break; - - *_size = size; - return 0; - - } while (0); - - pr_err("callchain: Incorrect stack dump size (max %ld): %s\n", - max_size, str); - return -1; -} -#endif /* HAVE_DWARF_UNWIND_SUPPORT */ - int parse_callchain_record_opt(const char *arg, struct callchain_param *param) { - char *tok, *name, *saveptr = NULL; - char *buf; - int ret = -1; - - /* We need buffer that we know we can write to. */ - buf = malloc(strlen(arg) + 1); - if (!buf) - return -ENOMEM; - - strcpy(buf, arg); - - tok = strtok_r((char *)buf, ",", &saveptr); - name = tok ? : (char *)buf; - - do { - /* Framepointer style */ - if (!strncmp(name, "fp", sizeof("fp"))) { - if (!strtok_r(NULL, ",", &saveptr)) { - param->record_mode = CALLCHAIN_FP; - ret = 0; - } else - pr_err("callchain: No more arguments " - "needed for --call-graph fp\n"); - break; - -#ifdef HAVE_DWARF_UNWIND_SUPPORT - /* Dwarf style */ - } else if (!strncmp(name, "dwarf", sizeof("dwarf"))) { - const unsigned long default_stack_dump_size = 8192; - - ret = 0; - param->record_mode = CALLCHAIN_DWARF; - param->dump_size = default_stack_dump_size; - - tok = strtok_r(NULL, ",", &saveptr); - if (tok) { - unsigned long size = 0; - - ret = get_stack_size(tok, &size); - param->dump_size = size; - } -#endif /* HAVE_DWARF_UNWIND_SUPPORT */ - } else if (!strncmp(name, "lbr", sizeof("lbr"))) { - if (!strtok_r(NULL, ",", &saveptr)) { - param->record_mode = CALLCHAIN_LBR; - ret = 0; - } else - pr_err("callchain: No more arguments " - "needed for --call-graph lbr\n"); - break; - } else { - pr_err("callchain: Unknown --call-graph option " - "value: %s\n", arg); - break; - } - - } while (0); - - free(buf); - return ret; + return parse_callchain_record(arg, param); } static int parse_callchain_mode(const char *value) diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 68a32c2fe87a..acee2b3cd801 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -177,6 +177,7 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node * bool hide_unresolved); extern const char record_callchain_help[]; +extern int parse_callchain_record(const char *arg, struct callchain_param *param); int parse_callchain_record_opt(const char *arg, struct callchain_param *param); int parse_callchain_report_opt(const char *arg); int perf_callchain_config(const char *var, const char *value); diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index edc2d633b332..f7adf1203df1 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -566,6 +566,96 @@ unsigned long parse_tag_value(const char *str, struct parse_tag *tags) return (unsigned long) -1; } +int get_stack_size(const char *str, unsigned long *_size) +{ + char *endptr; + unsigned long size; + unsigned long max_size = round_down(USHRT_MAX, sizeof(u64)); + + size = strtoul(str, &endptr, 0); + + do { + if (*endptr) + break; + + size = round_up(size, sizeof(u64)); + if (!size || size > max_size) + break; + + *_size = size; + return 0; + + } while (0); + + pr_err("callchain: Incorrect stack dump size (max %ld): %s\n", + max_size, str); + return -1; +} + +int parse_callchain_record(const char *arg, struct callchain_param *param) +{ + char *tok, *name, *saveptr = NULL; + char *buf; + int ret = -1; + + /* We need buffer that we know we can write to. */ + buf = malloc(strlen(arg) + 1); + if (!buf) + return -ENOMEM; + + strcpy(buf, arg); + + tok = strtok_r((char *)buf, ",", &saveptr); + name = tok ? : (char *)buf; + + do { + /* Framepointer style */ + if (!strncmp(name, "fp", sizeof("fp"))) { + if (!strtok_r(NULL, ",", &saveptr)) { + param->record_mode = CALLCHAIN_FP; + ret = 0; + } else + pr_err("callchain: No more arguments " + "needed for --call-graph fp\n"); + break; + +#ifdef HAVE_DWARF_UNWIND_SUPPORT + /* Dwarf style */ + } else if (!strncmp(name, "dwarf", sizeof("dwarf"))) { + const unsigned long default_stack_dump_size = 8192; + + ret = 0; + param->record_mode = CALLCHAIN_DWARF; + param->dump_size = default_stack_dump_size; + + tok = strtok_r(NULL, ",", &saveptr); + if (tok) { + unsigned long size = 0; + + ret = get_stack_size(tok, &size); + param->dump_size = size; + } +#endif /* HAVE_DWARF_UNWIND_SUPPORT */ + } else if (!strncmp(name, "lbr", sizeof("lbr"))) { + if (!strtok_r(NULL, ",", &saveptr)) { + param->record_mode = CALLCHAIN_LBR; + ret = 0; + } else + pr_err("callchain: No more arguments " + "needed for --call-graph lbr\n"); + break; + } else { + pr_err("callchain: Unknown --call-graph option " + "value: %s\n", arg); + break; + } + + } while (0); + + free(buf); + return ret; +} + int filename__read_str(const char *filename, char **buf, size_t *sizep) { size_t size = 0, alloc_size = 0; diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 20d625a4cacf..81487037acf7 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -351,4 +351,6 @@ static inline char *asprintf_expr_not_in_ints(const char *var, size_t nints, int return asprintf_expr_inout_ints(var, false, nints, ints); } +int get_stack_size(const char *str, unsigned long *_size); + #endif /* GIT_COMPAT_UTIL_H */ -- cgit v1.2.3 From a9710ba091b0dcdace90f791706e9192313ffb7c Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Fri, 7 Aug 2015 15:24:05 -0700 Subject: perf tools: Support full source file paths for srcline For perf report/script srcline currently only the base file name of the source file is printed. This is a good default because it usually fits on the screen. But in some cases we want to know the full file name, for example to aggregate hits per file. In the later case we need more than the base file name to resolve file naming collisions: for example the kernel source has ~70 files named "core.c" It's also useful as input to post processing tools which want to point to the right file. Add a flag to allow full file name output. Add an option to perf report/script to enable this option. Signed-off-by: Andi Kleen Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/1438986245-15191-1-git-send-email-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-report.txt | 2 ++ tools/perf/Documentation/perf-script.txt | 3 +++ tools/perf/builtin-report.c | 2 ++ tools/perf/builtin-script.c | 2 ++ tools/perf/util/srcline.c | 6 +++++- tools/perf/util/util.h | 1 + 6 files changed, 15 insertions(+), 1 deletion(-) diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 960da203ec11..1a782ef02b68 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -354,6 +354,8 @@ OPTIONS To disable decoding entirely, use --no-itrace. +--full-source-path:: + Show the full path for source files for srcline output. include::callchain-overhead-calculation.txt[] diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index e2fec5fc21e7..8e9be1f9c1dd 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -260,6 +260,9 @@ OPTIONS To disable decoding entirely, use --no-itrace. +--full-source-path:: + Show the full path for source files for srcline output. + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-script-perl[1], diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 3a9d1b659fcd..f301e865001f 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -738,6 +738,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused) OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts", "Instruction Tracing options", itrace_parse_synth_opts), + OPT_BOOLEAN(0, "full-source-path", &srcline_full_filename, + "Show full source file name path for source lines"), OPT_END() }; struct perf_data_file file = { diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 7912feb9a024..7b376d215e94 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1653,6 +1653,8 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts", "Instruction Tracing options", itrace_parse_synth_opts), + OPT_BOOLEAN(0, "full-source-path", &srcline_full_filename, + "Show full source file name path for source lines"), OPT_END() }; const char * const script_subcommands[] = { "record", "report", NULL }; diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c index c93fb0c5bd0b..fc08248f08ca 100644 --- a/tools/perf/util/srcline.c +++ b/tools/perf/util/srcline.c @@ -10,6 +10,8 @@ #include "symbol.h" +bool srcline_full_filename; + #ifdef HAVE_LIBBFD_SUPPORT /* @@ -277,7 +279,9 @@ char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym, if (!addr2line(dso_name, addr, &file, &line, dso)) goto out; - if (asprintf(&srcline, "%s:%u", basename(file), line) < 0) { + if (asprintf(&srcline, "%s:%u", + srcline_full_filename ? file : basename(file), + line) < 0) { free(file); goto out; } diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h index 81487037acf7..88a891562a47 100644 --- a/tools/perf/util/util.h +++ b/tools/perf/util/util.h @@ -318,6 +318,7 @@ static inline int path__join3(char *bf, size_t size, struct dso; struct symbol; +extern bool srcline_full_filename; char *get_srcline(struct dso *dso, u64 addr, struct symbol *sym, bool show_sym); void free_srcline(char *srcline); -- cgit v1.2.3 From ab35a7d0ee59a36c9c567defe43c1adb72e9240c Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Sat, 8 Aug 2015 19:12:10 +0200 Subject: perf tools: Unset perf_event_attr::freq when period term is set We need to unset 'perf_event_attr::freq' bit (default 1) when 'period' term is specified within event definition like: -e 'cpu/cpu-cycles,call-graph=fp,time,period=100000' otherwise it will handle the period value as frequency (and fail if it crossed the maximum allowed frequency value). Signed-off-by: Jiri Olsa Cc: Andi Kleen Cc: Kan Liang Cc: Namhyung Kim Link: http://lkml.kernel.org/r/20150808171210.GC17040@krava.brq.redhat.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index f572f469a30d..a59710f88d8a 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -598,6 +598,7 @@ static void apply_config_terms(struct perf_evsel *evsel) switch (term->type) { case PERF_EVSEL__CONFIG_TERM_PERIOD: attr->sample_period = term->val.period; + attr->freq = 0; break; case PERF_EVSEL__CONFIG_TERM_TIME: if (term->val.time) -- cgit v1.2.3 From 5cef897652f224442c013d9e9425536b38385351 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 10 Aug 2015 15:45:55 -0300 Subject: perf hists: hist_entry__cmp() may use he_tmp.hists, initialize it The iter_add_next_cumulative_entry() function calls hist_entry__cmp(), which may want to access the hists where this hist_entry is stored, initialize it to let that happen and avoid segfaults. Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-iqg98sfn4fvwcxp0pdvqauie@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/hist.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index a6e9ddd37913..2fe6ea39e257 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -761,6 +761,7 @@ iter_add_next_cumulative_entry(struct hist_entry_iter *iter, struct hist_entry **he_cache = iter->priv; struct hist_entry *he; struct hist_entry he_tmp = { + .hists = evsel__hists(evsel), .cpu = al->cpu, .thread = al->thread, .comm = thread__comm(al->thread), -- cgit v1.2.3 From e8e6d37e73e6b950c891c780745460b87f4755b6 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Mon, 10 Aug 2015 16:53:54 -0300 Subject: perf hists: Update the column width for the "srcline" sort key When we introduce a new sort key, we need to update the hists__calc_col_len() function accordingly, otherwise the width will be limited to strlen(header). We can't update it when obtaining a line value for a column (for instance, in sort__srcline_cmp()), because we reset it all when doing a resort (see hists__output_recalc_col_len()), so we need to, from what is in the hist_entry fields, set each of the column widths. Cc: Namhyung Kim Cc: Andi Kleen Cc: Jiri Olsa Fixes: 409a8be61560 ("perf tools: Add sort by src line/number") Link: http://lkml.kernel.org/n/tip-jgbe0yx8v1gs89cslr93pvz2@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/hist.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 2fe6ea39e257..608c0a7fd0f4 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -151,6 +151,9 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) hists__new_col_len(hists, HISTC_LOCAL_WEIGHT, 12); hists__new_col_len(hists, HISTC_GLOBAL_WEIGHT, 12); + if (h->srcline) + hists__new_col_len(hists, HISTC_SRCLINE, strlen(h->srcline)); + if (h->transaction) hists__new_col_len(hists, HISTC_TRANSACTION, hist_entry__transaction_len()); -- cgit v1.2.3 From 31191a85fb875cf123cea56bbfd34f4b941f3c79 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Fri, 7 Aug 2015 15:54:24 -0700 Subject: perf report: Add support for srcfile sort key In some cases it's useful to characterize samples by file. This is useful to get a higher level categorization, for example to map cost to subsystems. Add a srcfile sort key to perf report. It builds on top of the existing srcline support. Commiter notes: E.g.: # perf record -F 10000 usleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.016 MB perf.data (13 samples) ] [root@zoo ~]# perf report -s srcfile --stdio # Total Lost Samples: 0 # # Samples: 13 of event 'cycles' # Event count (approx.): 869878 # # Overhead Source File # ........ ........... 60.99% . 20.62% paravirt.h 14.23% rmap.c 4.04% signal.c 0.11% msr.h # The first line is collecting all the files for which srcfiles couldn't somehow get resolved to: # perf report -s srcfile,dso --stdio # Total Lost Samples: 0 # # Samples: 13 of event 'cycles' # Event count (approx.): 869878 # # Overhead Source File Shared Object # ........ ........... ................ 40.97% . ld-2.20.so 20.62% paravirt.h [kernel.vmlinux] 20.02% . libc-2.20.so 14.23% rmap.c [kernel.vmlinux] 4.04% signal.c [kernel.vmlinux] 0.11% msr.h [kernel.vmlinux] # XXX: Investigate why that is not resolving on Fedora 21, Andi says he hasn't seen this on Fedora 22. Signed-off-by: Andi Kleen Tested-by: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Namhyung Kim Link: http://lkml.kernel.org/r/1438988064-21834-1-git-send-email-andi@firstfloor.org [ Added column length update, from 0e65bdb3f90f ('perf hists: Update the column width for the "srcline" sort key') ] Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-report.txt | 2 ++ tools/perf/util/hist.c | 5 +++ tools/perf/util/hist.h | 1 + tools/perf/util/sort.c | 52 ++++++++++++++++++++++++++++++++ tools/perf/util/sort.h | 2 ++ 5 files changed, 62 insertions(+) diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 1a782ef02b68..7b07d19e2d54 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -81,6 +81,8 @@ OPTIONS - cpu: cpu number the task ran at the time of sample - srcline: filename and line number executed at the time of sample. The DWARF debugging info must be provided. + - srcfile: file name of the source file of the same. Requires dwarf + information. - weight: Event specific weight, e.g. memory latency or transaction abort cost. This is the global weight. - local_weight: Local weight version of the weight above. diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 608c0a7fd0f4..6bccfae334b1 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -154,6 +154,9 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h) if (h->srcline) hists__new_col_len(hists, HISTC_SRCLINE, strlen(h->srcline)); + if (h->srcfile) + hists__new_col_len(hists, HISTC_SRCFILE, strlen(h->srcfile)); + if (h->transaction) hists__new_col_len(hists, HISTC_TRANSACTION, hist_entry__transaction_len()); @@ -949,6 +952,8 @@ void hist_entry__delete(struct hist_entry *he) zfree(&he->stat_acc); free_srcline(he->srcline); + if (he->srcfile && he->srcfile[0]) + free(he->srcfile); free_callchain(he->callchain); free(he); } diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h index e2f712f85d2e..bc528d54e457 100644 --- a/tools/perf/util/hist.h +++ b/tools/perf/util/hist.h @@ -30,6 +30,7 @@ enum hist_column { HISTC_PARENT, HISTC_CPU, HISTC_SRCLINE, + HISTC_SRCFILE, HISTC_MISPREDICT, HISTC_IN_TX, HISTC_ABORT, diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 5177088a71d3..c0c32b050e45 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -319,6 +319,57 @@ struct sort_entry sort_srcline = { .se_width_idx = HISTC_SRCLINE, }; +/* --sort srcfile */ + +static char no_srcfile[1]; + +static char *get_srcfile(struct hist_entry *e) +{ + char *sf, *p; + struct map *map = e->ms.map; + + sf = get_srcline(map->dso, map__rip_2objdump(map, e->ip), + e->ms.sym, true); + p = strchr(sf, ':'); + if (p && *sf) { + *p = 0; + return sf; + } + free(sf); + return no_srcfile; +} + +static int64_t +sort__srcfile_cmp(struct hist_entry *left, struct hist_entry *right) +{ + if (!left->srcfile) { + if (!left->ms.map) + left->srcfile = no_srcfile; + else + left->srcfile = get_srcfile(left); + } + if (!right->srcfile) { + if (!right->ms.map) + right->srcfile = no_srcfile; + else + right->srcfile = get_srcfile(right); + } + return strcmp(right->srcfile, left->srcfile); +} + +static int hist_entry__srcfile_snprintf(struct hist_entry *he, char *bf, + size_t size, unsigned int width) +{ + return repsep_snprintf(bf, size, "%-*.*s", width, width, he->srcfile); +} + +struct sort_entry sort_srcfile = { + .se_header = "Source File", + .se_cmp = sort__srcfile_cmp, + .se_snprintf = hist_entry__srcfile_snprintf, + .se_width_idx = HISTC_SRCFILE, +}; + /* --sort parent */ static int64_t @@ -1196,6 +1247,7 @@ static struct sort_dimension common_sort_dimensions[] = { DIM(SORT_PARENT, "parent", sort_parent), DIM(SORT_CPU, "cpu", sort_cpu), DIM(SORT_SRCLINE, "srcline", sort_srcline), + DIM(SORT_SRCFILE, "srcfile", sort_srcfile), DIM(SORT_LOCAL_WEIGHT, "local_weight", sort_local_weight), DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight), DIM(SORT_TRANSACTION, "transaction", sort_transaction), diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h index bc6c87a76d16..3c2a399f8f5b 100644 --- a/tools/perf/util/sort.h +++ b/tools/perf/util/sort.h @@ -114,6 +114,7 @@ struct hist_entry { }; }; char *srcline; + char *srcfile; struct symbol *parent; struct rb_root sorted_chain; struct branch_info *branch_info; @@ -172,6 +173,7 @@ enum sort_type { SORT_PARENT, SORT_CPU, SORT_SRCLINE, + SORT_SRCFILE, SORT_LOCAL_WEIGHT, SORT_GLOBAL_WEIGHT, SORT_TRANSACTION, -- cgit v1.2.3 From 09af2a553577a6e53e40011a910be0f27ce56f3e Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Sun, 9 Aug 2015 15:45:23 +0900 Subject: perf record: Support per-event freq term Now perf can set per-event value of time and (sampling) period. But I guess most users like me just want to set frequency rather than period. So add the 'freq' term in the event parser. Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Cc: David Ahern Cc: Kan Liang Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1439102724-14079-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-record.txt | 1 + tools/perf/util/evsel.c | 4 ++++ tools/perf/util/evsel.h | 2 ++ tools/perf/util/parse-events.c | 6 ++++++ tools/perf/util/parse-events.h | 1 + tools/perf/util/parse-events.l | 1 + tools/perf/util/pmu.c | 2 +- 7 files changed, 16 insertions(+), 1 deletion(-) diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 0d852d1bc90f..afbe45ef7e3e 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -49,6 +49,7 @@ OPTIONS These params can be used to overload default config values per event. Here is a list of the params. - 'period': Set event sampling period + - 'freq': Set event sampling frequency - 'time': Disable/enable time stamping. Acceptable values are 1 for enabling time stamping. 0 for disabling time stamping. The default is 1. diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index a59710f88d8a..f664a22b5fea 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -600,6 +600,10 @@ static void apply_config_terms(struct perf_evsel *evsel) attr->sample_period = term->val.period; attr->freq = 0; break; + case PERF_EVSEL__CONFIG_TERM_FREQ: + attr->sample_freq = term->val.freq; + attr->freq = 1; + break; case PERF_EVSEL__CONFIG_TERM_TIME: if (term->val.time) perf_evsel__set_sample_bit(evsel, TIME); diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index b948f69d2558..fdf2674ab339 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -39,6 +39,7 @@ struct cgroup_sel; */ enum { PERF_EVSEL__CONFIG_TERM_PERIOD, + PERF_EVSEL__CONFIG_TERM_FREQ, PERF_EVSEL__CONFIG_TERM_TIME, PERF_EVSEL__CONFIG_TERM_MAX, }; @@ -48,6 +49,7 @@ struct perf_evsel_config_term { int type; union { u64 period; + u64 freq; bool time; } val; }; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 828936dc3f1e..dbf315df4220 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -597,6 +597,9 @@ do { \ case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD: CHECK_TYPE_VAL(NUM); break; + case PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ: + CHECK_TYPE_VAL(NUM); + break; case PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE: /* * TODO uncomment when the field is available @@ -659,6 +662,9 @@ do { \ case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD: ADD_CONFIG_TERM(PERIOD, period, term->val.num); break; + case PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ: + ADD_CONFIG_TERM(FREQ, freq, term->val.num); + break; case PARSE_EVENTS__TERM_TYPE_TIME: ADD_CONFIG_TERM(TIME, time, term->val.num); break; diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index e6f9aacc1cce..ce2d13a16226 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -62,6 +62,7 @@ enum { PARSE_EVENTS__TERM_TYPE_CONFIG2, PARSE_EVENTS__TERM_TYPE_NAME, PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD, + PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE, PARSE_EVENTS__TERM_TYPE_TIME, }; diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index f5427505ae77..4306f5ad75c7 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -182,6 +182,7 @@ config1 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG1); } config2 { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_CONFIG2); } name { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NAME); } period { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD); } +freq { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_SAMPLE_FREQ); } branch_type { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE); } time { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_TIME); } , { return ','; } diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index d4b0e6454bc6..d85f11b8cacf 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -634,7 +634,7 @@ static char *formats_error_string(struct list_head *formats) { struct perf_pmu_format *format; char *err, *str; - static const char *static_terms = "config,config1,config2,name,period,branch_type,time\n"; + static const char *static_terms = "config,config1,config2,name,period,freq,branch_type,time\n"; unsigned i = 0; if (!asprintf(&str, "valid terms:")) -- cgit v1.2.3 From 4605bb55b91449a1a953a51f0334d3bc02351adb Mon Sep 17 00:00:00 2001 From: Namhyung Kim Date: Sun, 9 Aug 2015 15:45:24 +0900 Subject: perf evlist: Be more specific on -F/--freq Currently perf evlist -F shows the number as if it's always sampling frequency. But we now support per-event freq/period settings. So it'd better to show more detailed info whether it's freq or period. $ perf record -e 'cpu/config=1/,cpu/config=2,period=300000/' sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.017 MB perf.data ] $ perf evlist -F cpu/config=1/: sample_freq=4000 cpu/config=2,period=300000/: sample_period=300000 Signed-off-by: Namhyung Kim Acked-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: David Ahern Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1439102724-14079-2-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evsel.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index f664a22b5fea..04fddddc6b6f 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -2158,8 +2158,13 @@ int perf_evsel__fprintf(struct perf_evsel *evsel, printed += perf_event_attr__fprintf(fp, &evsel->attr, __print_attr__fprintf, &first); } else if (details->freq) { - printed += comma_fprintf(fp, &first, " sample_freq=%" PRIu64, - (u64)evsel->attr.sample_freq); + const char *term = "sample_freq"; + + if (!evsel->attr.freq) + term = "sample_period"; + + printed += comma_fprintf(fp, &first, " %s=%" PRIu64, + term, (u64)evsel->attr.sample_freq); } out: fputc('\n', fp); -- cgit v1.2.3