From 7f8d1ade1b19f684ed3a7c4fb1dc5d347127b438 Mon Sep 17 00:00:00 2001 From: Arnaldo Carvalho de Melo Date: Wed, 30 Sep 2015 17:49:49 -0300 Subject: [PATCH] perf tools: By default use the most precise "cycles" hw counter available If the user doesn't specify any event, try the most precise "cycles" available, i.e. start by "cycles:ppp" and go on removing "p" till it works. E.g. $ perf record usleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.017 MB perf.data (11 samples) ] $ perf evlist cycles:pp $ perf evlist -v cycles:pp: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, precise_ip: 2, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1 $ grep 'model name' /proc/cpuinfo | head -1 model name : Intel(R) Core(TM) i7-3667U CPU @ 2.00GHz $ When 'cycles' appears explicitely is specified this will not be tried, i.e. the user has full control of the level of precision to be used: $ perf record -e cycles usleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.016 MB perf.data (9 samples) ] $ perf evlist cycles $ perf evlist -v cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1 $ Cc: Adrian Hunter Cc: Borislav Petkov Cc: Chandler Carruth Cc: David Ahern Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Stephane Eranian Cc: Wang Nan Link: https://www.youtube.com/watch?v=nXaxk27zwlk Link: http://lkml.kernel.org/n/tip-b1ywebmt22pi78vjxau01wth@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/util/evlist.c | 22 +++++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-) diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 89546228b8ed..e7e195d867ea 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -205,6 +205,20 @@ void perf_evlist__set_leader(struct perf_evlist *evlist) } } +static void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr) +{ + attr->precise_ip = 3; + + while (attr->precise_ip != 0) { + int fd = sys_perf_event_open(attr, 0, -1, -1, 0); + if (fd != -1) { + close(fd); + break; + } + --attr->precise_ip; + } +} + int perf_evlist__add_default(struct perf_evlist *evlist) { struct perf_event_attr attr = { @@ -215,13 +229,15 @@ int perf_evlist__add_default(struct perf_evlist *evlist) event_attr_init(&attr); + perf_event_attr__set_max_precise_ip(&attr); + evsel = perf_evsel__new(&attr); if (evsel == NULL) goto error; - /* use strdup() because free(evsel) assumes name is allocated */ - evsel->name = strdup("cycles"); - if (!evsel->name) + /* use asprintf() because free(evsel) assumes name is allocated */ + if (asprintf(&evsel->name, "cycles%.*s", + attr.precise_ip ? attr.precise_ip + 1 : 0, ":ppp") < 0) goto error_free; perf_evlist__add(evlist, evsel); -- 2.11.0