* [PATCH v6 2/4] perf stat: add event unit and scale support
2013-11-08 19:45 [PATCH v6 0/4] perf/x86: add Intel RAPL PMU support Stephane Eranian
2013-11-08 19:46 ` [PATCH v6 1/4] perf: add active_entry list head to struct perf_event Stephane Eranian
@ 2013-11-08 19:46 ` Stephane Eranian
2013-11-08 19:46 ` [PATCH v6 3/4] perf,x86: add Intel RAPL PMU support Stephane Eranian
2013-11-08 19:46 ` [PATCH v6 4/4] perf,x86: add RAPL hrtimer support Stephane Eranian
3 siblings, 0 replies; 10+ messages in thread
From: Stephane Eranian @ 2013-11-08 19:46 UTC (permalink / raw)
To: linux-kernel
Cc: peterz, mingo, ak, acme, jolsa, zheng.z.yan, bp, maria.n.dimakopoulou
This patch adds perf stat support for handling event units and
scales as exported by the kernel.
The kernel can export PMU events actual unit and scaling factor
via sysfs:
$ ls -1 /sys/devices/power/events/energy-*
/sys/devices/power/events/energy-cores
/sys/devices/power/events/energy-cores.scale
/sys/devices/power/events/energy-cores.unit
/sys/devices/power/events/energy-pkg
/sys/devices/power/events/energy-pkg.scale
/sys/devices/power/events/energy-pkg.unit
$ cat /sys/devices/power/events/energy-cores.scale
2.3283064365386962890625e-10
$ cat cat /sys/devices/power/events/energy-cores.unit
Joules
This patch modifies the pmu event alias code to check
for the presence of the .unit and .scale files to load
the corresponding values. They are then used by perf stat
transparently:
# perf stat -a -e power/energy-pkg/,power/energy-cores/,cycles -I 1000 sleep 1000
# time counts unit events
1.000214717 3.07 Joules power/energy-pkg/ [100.00%]
1.000214717 0.53 Joules power/energy-cores/
1.000214717 12965028 cycles [100.00%]
2.000749289 3.01 Joules power/energy-pkg/
2.000749289 0.52 Joules power/energy-cores/
2.000749289 15817043 cycles
When the event does not have an explicit unit exported by
the kernel, nothing is printed. In csv output mode, there
will be an empty field.
Special thanks to Jiri for providing the supporting code
in the parser to trigger reading of the scale and unit files.
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
---
tools/perf/builtin-stat.c | 114 +++++++++++++++++++++++---------
tools/perf/util/evsel.c | 2 +
tools/perf/util/evsel.h | 3 +
tools/perf/util/parse-events.c | 28 +++++---
tools/perf/util/pmu.c | 139 ++++++++++++++++++++++++++++++++++++++--
tools/perf/util/pmu.h | 3 +-
6 files changed, 245 insertions(+), 44 deletions(-)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 0fc1c94..66d20c9 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -138,6 +138,7 @@ static const char *post_cmd = NULL;
static bool sync_run = false;
static unsigned int interval = 0;
static unsigned int initial_delay = 0;
+static unsigned int unit_width = 4; /* strlen("unit") */
static bool forever = false;
static struct timespec ref_time;
static struct cpu_map *aggr_map;
@@ -462,17 +463,17 @@ static void print_interval(void)
if (num_print_interval == 0 && !csv_output) {
switch (aggr_mode) {
case AGGR_SOCKET:
- fprintf(output, "# time socket cpus counts events\n");
+ fprintf(output, "# time socket cpus counts %*s events\n", unit_width, "unit");
break;
case AGGR_CORE:
- fprintf(output, "# time core cpus counts events\n");
+ fprintf(output, "# time core cpus counts %*s events\n", unit_width, "unit");
break;
case AGGR_NONE:
- fprintf(output, "# time CPU counts events\n");
+ fprintf(output, "# time CPU counts %*s events\n", unit_width, "unit");
break;
case AGGR_GLOBAL:
default:
- fprintf(output, "# time counts events\n");
+ fprintf(output, "# time counts %*s events\n", unit_width, "unit");
}
}
@@ -517,6 +518,7 @@ static int __run_perf_stat(int argc, const char **argv)
unsigned long long t0, t1;
struct perf_evsel *counter;
struct timespec ts;
+ size_t l;
int status = 0;
const bool forks = (argc > 0);
@@ -566,6 +568,10 @@ static int __run_perf_stat(int argc, const char **argv)
return -1;
}
counter->supported = true;
+
+ l = strlen(counter->unit);
+ if (l > unit_width)
+ unit_width = l;
}
if (perf_evlist__apply_filters(evsel_list)) {
@@ -705,14 +711,25 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
static void nsec_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
{
double msecs = avg / 1e6;
- const char *fmt = csv_output ? "%.6f%s%s" : "%18.6f%s%-25s";
+ const char *fmt_v, *fmt_n;
char name[25];
+ fmt_v = csv_output ? "%.6f%s" : "%18.6f%s";
+ fmt_n = csv_output ? "%s" : "%-25s";
+
aggr_printout(evsel, cpu, nr);
scnprintf(name, sizeof(name), "%s%s",
perf_evsel__name(evsel), csv_output ? "" : " (msec)");
- fprintf(output, fmt, msecs, csv_sep, name);
+
+ fprintf(output, fmt_v, msecs, csv_sep);
+
+ if (csv_output)
+ fprintf(output, "%s%s", evsel->unit, csv_sep);
+ else
+ fprintf(output, "%-*s%s", unit_width, evsel->unit, csv_sep);
+
+ fprintf(output, fmt_n, name);
if (evsel->cgrp)
fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
@@ -909,21 +926,31 @@ static void print_ll_cache_misses(int cpu,
static void abs_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
{
double total, ratio = 0.0, total2;
+ double sc = evsel->scale;
const char *fmt;
- if (csv_output)
- fmt = "%.0f%s%s";
- else if (big_num)
- fmt = "%'18.0f%s%-25s";
- else
- fmt = "%18.0f%s%-25s";
+ if (csv_output) {
+ fmt = sc != 1.0 ? "%.2f%s" : "%.0f%s";
+ } else {
+ if (big_num)
+ fmt = sc != 1.0 ? "%'18.2f%s" : "%'18.0f%s";
+ else
+ fmt = sc != 1.0 ? "%18.2f%s" : "%18.0f%s";
+ }
aggr_printout(evsel, cpu, nr);
if (aggr_mode == AGGR_GLOBAL)
cpu = 0;
- fprintf(output, fmt, avg, csv_sep, perf_evsel__name(evsel));
+ fprintf(output, fmt, avg, csv_sep);
+
+ if (evsel->unit)
+ fprintf(output, "%-*s%s",
+ csv_output ? 0 : unit_width,
+ evsel->unit, csv_sep);
+
+ fprintf(output, "%-*s", csv_output ? 0 : 25, perf_evsel__name(evsel));
if (evsel->cgrp)
fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
@@ -942,7 +969,10 @@ static void abs_printout(int cpu, int nr, struct perf_evsel *evsel, double avg)
if (total && avg) {
ratio = total / avg;
- fprintf(output, "\n # %5.2f stalled cycles per insn", ratio);
+ fprintf(output, "\n");
+ if (aggr_mode == AGGR_NONE)
+ fprintf(output, " ");
+ fprintf(output, " # %5.2f stalled cycles per insn", ratio);
}
} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
@@ -1062,6 +1092,7 @@ static void print_aggr(char *prefix)
{
struct perf_evsel *counter;
int cpu, cpu2, s, s2, id, nr;
+ double uval;
u64 ena, run, val;
if (!(aggr_map || aggr_get_id))
@@ -1088,11 +1119,17 @@ static void print_aggr(char *prefix)
if (run == 0 || ena == 0) {
aggr_printout(counter, id, nr);
- fprintf(output, "%*s%s%*s",
+ fprintf(output, "%*s%s",
csv_output ? 0 : 18,
counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
- csv_sep,
- csv_output ? 0 : -24,
+ csv_sep);
+
+ fprintf(output, "%-*s%s",
+ csv_output ? 0 : unit_width,
+ counter->unit, csv_sep);
+
+ fprintf(output, "%*s",
+ csv_output ? 0 : -25,
perf_evsel__name(counter));
if (counter->cgrp)
@@ -1102,11 +1139,12 @@ static void print_aggr(char *prefix)
fputc('\n', output);
continue;
}
+ uval = val * counter->scale;
if (nsec_counter(counter))
- nsec_printout(id, nr, counter, val);
+ nsec_printout(id, nr, counter, uval);
else
- abs_printout(id, nr, counter, val);
+ abs_printout(id, nr, counter, uval);
if (!csv_output) {
print_noise(counter, 1.0);
@@ -1129,16 +1167,21 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
struct perf_stat *ps = counter->priv;
double avg = avg_stats(&ps->res_stats[0]);
int scaled = counter->counts->scaled;
+ double uval;
if (prefix)
fprintf(output, "%s", prefix);
if (scaled == -1) {
- fprintf(output, "%*s%s%*s",
+ fprintf(output, "%*s%s",
csv_output ? 0 : 18,
counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
- csv_sep,
- csv_output ? 0 : -24,
+ csv_sep);
+ fprintf(output, "%-*s%s",
+ csv_output ? 0 : unit_width,
+ counter->unit, csv_sep);
+ fprintf(output, "%*s",
+ csv_output ? 0 : -25,
perf_evsel__name(counter));
if (counter->cgrp)
@@ -1148,10 +1191,12 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
return;
}
+ uval = avg * counter->scale;
+
if (nsec_counter(counter))
- nsec_printout(-1, 0, counter, avg);
+ nsec_printout(-1, 0, counter, uval);
else
- abs_printout(-1, 0, counter, avg);
+ abs_printout(-1, 0, counter, uval);
print_noise(counter, avg);
@@ -1178,6 +1223,7 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
static void print_counter(struct perf_evsel *counter, char *prefix)
{
u64 ena, run, val;
+ double uval;
int cpu;
for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
@@ -1189,14 +1235,20 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
fprintf(output, "%s", prefix);
if (run == 0 || ena == 0) {
- fprintf(output, "CPU%*d%s%*s%s%*s",
+ fprintf(output, "CPU%*d%s%*s%s",
csv_output ? 0 : -4,
perf_evsel__cpus(counter)->map[cpu], csv_sep,
csv_output ? 0 : 18,
counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
- csv_sep,
- csv_output ? 0 : -24,
- perf_evsel__name(counter));
+ csv_sep);
+
+ fprintf(output, "%-*s%s",
+ csv_output ? 0 : unit_width,
+ counter->unit, csv_sep);
+
+ fprintf(output, "%*s",
+ csv_output ? 0 : -25,
+ perf_evsel__name(counter));
if (counter->cgrp)
fprintf(output, "%s%s",
@@ -1206,10 +1258,12 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
continue;
}
+ uval = val * counter->scale;
+
if (nsec_counter(counter))
- nsec_printout(cpu, 0, counter, val);
+ nsec_printout(cpu, 0, counter, uval);
else
- abs_printout(cpu, 0, counter, val);
+ abs_printout(cpu, 0, counter, uval);
if (!csv_output) {
print_noise(counter, 1.0);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 5280820..f1e3d02 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -162,6 +162,8 @@ void perf_evsel__init(struct perf_evsel *evsel,
evsel->idx = idx;
evsel->attr = *attr;
evsel->leader = evsel;
+ evsel->unit = "";
+ evsel->scale = 1.0;
INIT_LIST_HEAD(&evsel->node);
hists__init(&evsel->hists);
evsel->sample_size = __perf_evsel__sample_size(attr->sample_type);
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 64ec8e1..df2ea2b 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -68,6 +68,8 @@ struct perf_evsel {
u32 ids;
struct hists hists;
char *name;
+ double scale;
+ const char *unit;
struct event_format *tp_format;
union {
void *priv;
@@ -127,6 +129,7 @@ extern const char *perf_evsel__sw_names[PERF_COUNT_SW_MAX];
int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result,
char *bf, size_t size);
const char *perf_evsel__name(struct perf_evsel *evsel);
+
const char *perf_evsel__group_name(struct perf_evsel *evsel);
int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index c90e55c..90ae328 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -269,9 +269,10 @@ const char *event_type(int type)
-static int __add_event(struct list_head *list, int *idx,
- struct perf_event_attr *attr,
- char *name, struct cpu_map *cpus)
+static struct perf_evsel *
+__add_event(struct list_head *list, int *idx,
+ struct perf_event_attr *attr,
+ char *name, struct cpu_map *cpus)
{
struct perf_evsel *evsel;
@@ -279,19 +280,19 @@ static int __add_event(struct list_head *list, int *idx,
evsel = perf_evsel__new(attr, (*idx)++);
if (!evsel)
- return -ENOMEM;
+ return NULL;
evsel->cpus = cpus;
if (name)
evsel->name = strdup(name);
list_add_tail(&evsel->node, list);
- return 0;
+ return evsel;
}
static int add_event(struct list_head *list, int *idx,
struct perf_event_attr *attr, char *name)
{
- return __add_event(list, idx, attr, name, NULL);
+ return __add_event(list, idx, attr, name, NULL) ? 0 : -ENOMEM;
}
static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES], int size)
@@ -633,6 +634,9 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
{
struct perf_event_attr attr;
struct perf_pmu *pmu;
+ struct perf_evsel *evsel;
+ char *unit;
+ double scale;
pmu = perf_pmu__find(name);
if (!pmu)
@@ -640,7 +644,7 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
memset(&attr, 0, sizeof(attr));
- if (perf_pmu__check_alias(pmu, head_config))
+ if (perf_pmu__check_alias(pmu, head_config, &unit, &scale))
return -EINVAL;
/*
@@ -652,8 +656,14 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
if (perf_pmu__config(pmu, &attr, head_config))
return -EINVAL;
- return __add_event(list, idx, &attr, pmu_event_name(head_config),
- pmu->cpus);
+ evsel = __add_event(list, idx, &attr, pmu_event_name(head_config),
+ pmu->cpus);
+ if (evsel) {
+ evsel->unit = unit;
+ evsel->scale = scale;
+ }
+
+ return evsel ? 0 : -ENOMEM;
}
int parse_events__modifier_group(struct list_head *list,
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index c232d8d..03986fa 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1,19 +1,24 @@
#include <linux/list.h>
#include <sys/types.h>
-#include <sys/stat.h>
#include <unistd.h>
#include <stdio.h>
#include <dirent.h>
#include "fs.h"
+#include <locale.h>
+#include "sysfs.h"
#include "util.h"
#include "pmu.h"
#include "parse-events.h"
#include "cpumap.h"
+#define UNIT_MAX_LEN 31 /* max length for event unit name */
+
struct perf_pmu_alias {
char *name;
struct list_head terms;
struct list_head list;
+ char unit[UNIT_MAX_LEN+1];
+ double scale;
};
struct perf_pmu_format {
@@ -94,7 +99,80 @@ static int pmu_format(const char *name, struct list_head *format)
return 0;
}
-static int perf_pmu__new_alias(struct list_head *list, char *name, FILE *file)
+static int perf_pmu__parse_scale(struct perf_pmu_alias *alias, char *dir, char *name)
+{
+ struct stat st;
+ ssize_t sret;
+ char scale[128];
+ int fd, ret = -1;
+ char path[PATH_MAX];
+ char *lc;
+
+ snprintf(path, PATH_MAX, "%s/%s.scale", dir, name);
+
+ fd = open(path, O_RDONLY);
+ if (fd == -1)
+ return -1;
+
+ if (fstat(fd, &st) < 0)
+ goto error;
+
+ sret = read(fd, scale, sizeof(scale)-1);
+ if (sret < 0)
+ goto error;
+
+ scale[sret] = '\0';
+ /*
+ * save current locale
+ */
+ lc = setlocale(LC_NUMERIC, NULL);
+
+ /*
+ * force to C locale to ensure kernel
+ * scale string is converted correctly.
+ * kernel uses default C locale.
+ */
+ setlocale(LC_NUMERIC, "C");
+
+ alias->scale = strtod(scale, NULL);
+
+ /* restore locale */
+ setlocale(LC_NUMERIC, lc);
+
+ ret = 0;
+error:
+ close(fd);
+ return ret;
+}
+
+static int perf_pmu__parse_unit(struct perf_pmu_alias *alias, char *dir, char *name)
+{
+ char path[PATH_MAX];
+ ssize_t sret;
+ int fd;
+
+ snprintf(path, PATH_MAX, "%s/%s.unit", dir, name);
+
+ fd = open(path, O_RDONLY);
+ if (fd == -1)
+ return -1;
+
+ sret = read(fd, alias->unit, UNIT_MAX_LEN);
+ if (sret < 0)
+ goto error;
+
+ close(fd);
+
+ alias->unit[sret] = '\0';
+
+ return 0;
+error:
+ close(fd);
+ alias->unit[0] = '\0';
+ return -1;
+}
+
+static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FILE *file)
{
struct perf_pmu_alias *alias;
char buf[256];
@@ -110,6 +188,9 @@ static int perf_pmu__new_alias(struct list_head *list, char *name, FILE *file)
return -ENOMEM;
INIT_LIST_HEAD(&alias->terms);
+ alias->scale = 1.0;
+ alias->unit[0] = '\0';
+
ret = parse_events_terms(&alias->terms, buf);
if (ret) {
free(alias);
@@ -117,7 +198,14 @@ static int perf_pmu__new_alias(struct list_head *list, char *name, FILE *file)
}
alias->name = strdup(name);
+ /*
+ * load unit name and scale if available
+ */
+ perf_pmu__parse_unit(alias, dir, name);
+ perf_pmu__parse_scale(alias, dir, name);
+
list_add_tail(&alias->list, list);
+
return 0;
}
@@ -129,6 +217,7 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
{
struct dirent *evt_ent;
DIR *event_dir;
+ size_t len;
int ret = 0;
event_dir = opendir(dir);
@@ -143,13 +232,24 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
if (!strcmp(name, ".") || !strcmp(name, ".."))
continue;
+ /*
+ * skip .unit and .scale info files
+ * parsed in perf_pmu__new_alias()
+ */
+ len = strlen(name);
+ if (len > 5 && !strcmp(name + len - 5, ".unit"))
+ continue;
+ if (len > 6 && !strcmp(name + len - 6, ".scale"))
+ continue;
+
snprintf(path, PATH_MAX, "%s/%s", dir, name);
ret = -EINVAL;
file = fopen(path, "r");
if (!file)
break;
- ret = perf_pmu__new_alias(head, name, file);
+
+ ret = perf_pmu__new_alias(head, dir, name, file);
fclose(file);
}
@@ -508,16 +608,42 @@ static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
return NULL;
}
+
+static int check_unit_scale(struct perf_pmu_alias *alias,
+ char **unit, double *scale)
+{
+ /*
+ * Only one term in event definition can
+ * define unit and scale, fail if there's
+ * more than one.
+ */
+ if ((*unit && alias->unit) ||
+ (*scale && alias->scale))
+ return -EINVAL;
+
+ if (alias->unit)
+ *unit = alias->unit;
+
+ if (alias->scale)
+ *scale = alias->scale;
+
+ return 0;
+}
+
/*
* Find alias in the terms list and replace it with the terms
* defined for the alias
*/
-int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms)
+int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
+ char **unit, double *scale)
{
struct parse_events_term *term, *h;
struct perf_pmu_alias *alias;
int ret;
+ *unit = NULL;
+ *scale = 0;
+
list_for_each_entry_safe(term, h, head_terms, list) {
alias = pmu_find_alias(pmu, term);
if (!alias)
@@ -525,6 +651,11 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms)
ret = pmu_alias_terms(alias, &term->list);
if (ret)
return ret;
+
+ ret = check_unit_scale(alias, unit, scale);
+ if (ret)
+ return ret;
+
list_del(&term->list);
free(term);
}
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 1179b26..9183380 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -28,7 +28,8 @@ int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
int perf_pmu__config_terms(struct list_head *formats,
struct perf_event_attr *attr,
struct list_head *head_terms);
-int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms);
+int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
+ char **unit, double *scale);
struct list_head *perf_pmu__alias(struct perf_pmu *pmu,
struct list_head *head_terms);
int perf_pmu_wrap(void);
--
1.7.9.5
^ permalink raw reply [flat|nested] 10+ messages in thread* [PATCH v6 3/4] perf,x86: add Intel RAPL PMU support
2013-11-08 19:45 [PATCH v6 0/4] perf/x86: add Intel RAPL PMU support Stephane Eranian
2013-11-08 19:46 ` [PATCH v6 1/4] perf: add active_entry list head to struct perf_event Stephane Eranian
2013-11-08 19:46 ` [PATCH v6 2/4] perf stat: add event unit and scale support Stephane Eranian
@ 2013-11-08 19:46 ` Stephane Eranian
2013-11-11 15:59 ` Peter Zijlstra
2013-11-08 19:46 ` [PATCH v6 4/4] perf,x86: add RAPL hrtimer support Stephane Eranian
3 siblings, 1 reply; 10+ messages in thread
From: Stephane Eranian @ 2013-11-08 19:46 UTC (permalink / raw)
To: linux-kernel
Cc: peterz, mingo, ak, acme, jolsa, zheng.z.yan, bp, maria.n.dimakopoulou
This patch adds a new uncore PMU to expose the Intel
RAPL energy consumption counters. Up to 3 counters,
each counting a particular RAPL event are exposed.
The RAPL counters are available on Intel SandyBridge,
IvyBridge, Haswell. The server skus add a 3rd counter.
The following events are available and exposed in sysfs:
- power/energy-cores: power consumption of all cores on socket
- power/energy-pkg: power consumption of all cores + LLc cache
- power/energy-dram: power consumption of DRAM (servers only)
For each event both the unit (Joules) and scale (2^-32 J)
is exposed in sysfs for use by perf stat and other tools.
Files are:
/sys/devices/power/events/energy-*.unit
/sys/devices/power/events/energy-*.scale
The RAPL PMU is uncore by nature and is implemented such
that it only works in system-wide mode. Measuring only
one CPU per socket is sufficient. The /sys/devices/power/cpumask
file can be used by tools to figure out which CPUs to monitor
by default. For instance, on a 2-socket system, 2 CPUs
(one on each socket) will be shown.
All the counters measure in the same unit (exposed via sysfs).
The perf_events API exposes all RAPL counters as 64-bit integers
counting in unit of 1/2^32 Joules (about 0.23 nJ). User level tools
must convert the counts by multiplying them by 2^-32 to obtain
Joules. The reason for this is that the kernel avoids
doing floating point math whenever possible because it is
expensive (user floating-point state must be saved). The method
used avoids kernel floating-point usage. There is no loss of
precision. Thanks to PeterZ for suggesting this approach.
To convert the raw count in Watt:
W = C * 2.3 / (1e10 * time)
or ldexp(C, -32).
RAPL PMU is a new standalone PMU which registers with the
perf_event core subsystem. The PMU type (attr->type) is
dynamically allocated and is available from /sys/device/power/type.
Sampling is not supported by the RAPL PMU. There is no
privilege level filtering either.
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Maria Dimakopoulou <maria.n.dimakopoulou@gmail.com>
---
arch/x86/kernel/cpu/Makefile | 2 +-
arch/x86/kernel/cpu/perf_event_intel_rapl.c | 607 +++++++++++++++++++++++++++
2 files changed, 608 insertions(+), 1 deletion(-)
create mode 100644 arch/x86/kernel/cpu/perf_event_intel_rapl.c
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 47b56a7..6359506 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -36,7 +36,7 @@ obj-$(CONFIG_CPU_SUP_AMD) += perf_event_amd_iommu.o
endif
obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_p6.o perf_event_knc.o perf_event_p4.o
obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o
-obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_uncore.o
+obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_uncore.o perf_event_intel_rapl.o
endif
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
new file mode 100644
index 0000000..8676c6d
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -0,0 +1,607 @@
+/*
+ * perf_event_intel_rapl.c: support Intel RAPL energy consumption counters
+ * Copyright (C) 2013 Google, Inc., Stephane Eranian
+ *
+ * Intel RAPL interface is specified in the IA-32 Manual Vol3b
+ * section 14.7.1 (September 2013)
+ *
+ * RAPL provides more controls than just reporting energy consumption
+ * however here we only expose the 3 energy consumption free running
+ * counters (pp0, pkg, dram).
+ *
+ * Each of those counters increments in a power unit defined by the
+ * RAPL_POWER_UNIT MSR. On SandyBridge, this unit is 1/(2^16) Joules
+ * but it can vary.
+ *
+ * Counter to rapl events mappings:
+ *
+ * pp0 counter: consumption of all physical cores (power plane 0)
+ * event: rapl_energy_cores
+ * perf code: 0x1
+ *
+ * pkg counter: consumption of the whole processor package
+ * event: rapl_energy_pkg
+ * perf code: 0x2
+ *
+ * dram counter: consumption of the dram domain (servers only)
+ * event: rapl_energy_dram
+ * perf code: 0x3
+ *
+ * We manage those counters as free running (read-only). They may be
+ * use simultaneously by other tools, such as turbostat.
+ *
+ * The events only support system-wide mode counting. There is no
+ * sampling support because it does not make sense and is not
+ * supported by the RAPL hardware.
+ *
+ * Because we want to avoid floating-point operations in the kernel,
+ * the events are all reported in fixed point arithmetic (32.32).
+ * Tools must adjust the counts to convert them to Watts using
+ * the duration of the measurement. Tools may use a function such as
+ * ldexp(raw_count, -32);
+ */
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/perf_event.h>
+#include <asm/cpu_device_id.h>
+#include "perf_event.h"
+
+/*
+ * RAPL energy status counters
+ */
+#define RAPL_IDX_PP0_NRG_STAT 0 /* all cores */
+#define INTEL_RAPL_PP0 0x1 /* pseudo-encoding */
+#define RAPL_IDX_PKG_NRG_STAT 1 /* entire package */
+#define INTEL_RAPL_PKG 0x2 /* pseudo-encoding */
+#define RAPL_IDX_RAM_NRG_STAT 2 /* DRAM */
+#define INTEL_RAPL_RAM 0x3 /* pseudo-encoding */
+
+/* Clients have PP0, PKG */
+#define RAPL_IDX_CLN (1<<RAPL_IDX_PP0_NRG_STAT|\
+ 1<<RAPL_IDX_PKG_NRG_STAT)
+
+/* Servers have PP0, PKG, RAM */
+#define RAPL_IDX_SRV (1<<RAPL_IDX_PP0_NRG_STAT|\
+ 1<<RAPL_IDX_PKG_NRG_STAT|\
+ 1<<RAPL_IDX_RAM_NRG_STAT)
+
+/*
+ * event code: LSB 8 bits, passed in attr->config
+ * any other bit is reserved
+ */
+#define RAPL_EVENT_MASK 0xFFULL
+
+#define DEFINE_RAPL_FORMAT_ATTR(_var, _name, _format) \
+static ssize_t __rapl_##_var##_show(struct kobject *kobj, \
+ struct kobj_attribute *attr, \
+ char *page) \
+{ \
+ BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \
+ return sprintf(page, _format "\n"); \
+} \
+static struct kobj_attribute format_attr_##_var = \
+ __ATTR(_name, 0444, __rapl_##_var##_show, NULL)
+
+#define RAPL_EVENT_DESC(_name, _config) \
+{ \
+ .attr = __ATTR(_name, 0444, rapl_event_show, NULL), \
+ .config = _config, \
+}
+
+#define RAPL_CNTR_WIDTH 32 /* 32-bit rapl counters */
+
+struct rapl_pmu {
+ spinlock_t lock;
+ int hw_unit; /* 1/2^hw_unit Joule */
+ int n_active; /* number of active events */
+ struct list_head active_list;
+ struct pmu *pmu; /* pointer to rapl_pmu_class */
+};
+
+static struct pmu rapl_pmu_class;
+static cpumask_t rapl_cpu_mask;
+static int rapl_cntr_mask;
+
+static DEFINE_PER_CPU(struct rapl_pmu *, rapl_pmu);
+static DEFINE_PER_CPU(struct rapl_pmu *, rapl_pmu_to_free);
+
+static DEFINE_SPINLOCK(rapl_hotplug_lock);
+
+static inline u64 rapl_read_counter(struct perf_event *event)
+{
+ u64 raw;
+ rdmsrl(event->hw.event_base, raw);
+ return raw;
+}
+
+static inline u64 rapl_scale(u64 v)
+{
+ /*
+ * scale delta to smallest unit (1/2^32)
+ * users must then scale back: count * 1/(1e9*2^32) to get Joules
+ * or use ldexp(count, -32).
+ * Watts = Joules/Time delta
+ */
+ return v << (32 - __get_cpu_var(rapl_pmu)->hw_unit);
+}
+
+static u64 rapl_event_update(struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ u64 prev_raw_count, new_raw_count;
+ s64 delta, sdelta;
+ int shift = RAPL_CNTR_WIDTH;
+
+again:
+ prev_raw_count = local64_read(&hwc->prev_count);
+ rdmsrl(event->hw.event_base, new_raw_count);
+
+ if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
+ new_raw_count) != prev_raw_count) {
+ cpu_relax();
+ goto again;
+ }
+
+ /*
+ * Now we have the new raw value and have updated the prev
+ * timestamp already. We can now calculate the elapsed delta
+ * (event-)time and add that to the generic event.
+ *
+ * Careful, not all hw sign-extends above the physical width
+ * of the count.
+ */
+ delta = (new_raw_count << shift) - (prev_raw_count << shift);
+ delta >>= shift;
+
+ sdelta = rapl_scale(delta);
+
+ local64_add(sdelta, &event->count);
+
+ return new_raw_count;
+}
+
+static void __rapl_pmu_event_start(struct rapl_pmu *pmu,
+ struct perf_event *event)
+{
+ if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
+ return;
+
+ event->hw.state = 0;
+
+ list_add_tail(&event->active_entry, &pmu->active_list);
+
+ local64_set(&event->hw.prev_count, rapl_read_counter(event));
+
+ pmu->n_active++;
+}
+
+static void rapl_pmu_event_start(struct perf_event *event, int mode)
+{
+ struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu);
+ unsigned long flags;
+
+ spin_lock_irqsave(&pmu->lock, flags);
+ __rapl_pmu_event_start(pmu, event);
+ spin_unlock_irqrestore(&pmu->lock, flags);
+}
+
+static void rapl_pmu_event_stop(struct perf_event *event, int mode)
+{
+ struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu);
+ struct hw_perf_event *hwc = &event->hw;
+ unsigned long flags;
+
+ spin_lock_irqsave(&pmu->lock, flags);
+
+ /* mark event as deactivated and stopped */
+ if (!(hwc->state & PERF_HES_STOPPED)) {
+ WARN_ON_ONCE(pmu->n_active <= 0);
+ pmu->n_active--;
+
+ list_del(&event->active_entry);
+
+ WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
+ hwc->state |= PERF_HES_STOPPED;
+ }
+
+ /* check if update of sw counter is necessary */
+ if ((mode & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
+ /*
+ * Drain the remaining delta count out of a event
+ * that we are disabling:
+ */
+ rapl_event_update(event);
+ hwc->state |= PERF_HES_UPTODATE;
+ }
+
+ spin_unlock_irqrestore(&pmu->lock, flags);
+}
+
+static int rapl_pmu_event_add(struct perf_event *event, int mode)
+{
+ struct rapl_pmu *pmu = __get_cpu_var(rapl_pmu);
+ struct hw_perf_event *hwc = &event->hw;
+ unsigned long flags;
+
+ spin_lock_irqsave(&pmu->lock, flags);
+
+ hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+
+ if (mode & PERF_EF_START)
+ __rapl_pmu_event_start(pmu, event);
+
+ spin_unlock_irqrestore(&pmu->lock, flags);
+
+ return 0;
+}
+
+static void rapl_pmu_event_del(struct perf_event *event, int flags)
+{
+ rapl_pmu_event_stop(event, PERF_EF_UPDATE);
+}
+
+static int rapl_pmu_event_init(struct perf_event *event)
+{
+ u64 cfg = event->attr.config & RAPL_EVENT_MASK;
+ int bit, msr, ret = 0;
+
+ /* only look at RAPL events */
+ if (event->attr.type != rapl_pmu_class.type)
+ return -ENOENT;
+
+ /* check only supported bits are set */
+ if (event->attr.config & ~RAPL_EVENT_MASK)
+ return -EINVAL;
+
+ /*
+ * check event is known (determines counter)
+ */
+ switch (cfg) {
+ case INTEL_RAPL_PP0:
+ bit = RAPL_IDX_PP0_NRG_STAT;
+ msr = MSR_PP0_ENERGY_STATUS;
+ break;
+ case INTEL_RAPL_PKG:
+ bit = RAPL_IDX_PKG_NRG_STAT;
+ msr = MSR_PKG_ENERGY_STATUS;
+ break;
+ case INTEL_RAPL_RAM:
+ bit = RAPL_IDX_RAM_NRG_STAT;
+ msr = MSR_DRAM_ENERGY_STATUS;
+ break;
+ default:
+ return -EINVAL;
+ }
+ /* check event supported */
+ if (!(rapl_cntr_mask & (1 << bit)))
+ return -EINVAL;
+
+ /* unsupported modes and filters */
+ if (event->attr.exclude_user ||
+ event->attr.exclude_kernel ||
+ event->attr.exclude_hv ||
+ event->attr.exclude_idle ||
+ event->attr.exclude_host ||
+ event->attr.exclude_guest ||
+ event->attr.sample_period) /* no sampling */
+ return -EINVAL;
+
+ /* must be done before validate_group */
+ event->hw.event_base = msr;
+ event->hw.config = cfg;
+ event->hw.idx = bit;
+
+ return ret;
+}
+
+static void rapl_pmu_event_read(struct perf_event *event)
+{
+ rapl_event_update(event);
+}
+
+static ssize_t rapl_get_attr_cpumask(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ int n = cpulist_scnprintf(buf, PAGE_SIZE - 2, &rapl_cpu_mask);
+
+ buf[n++] = '\n';
+ buf[n] = '\0';
+ return n;
+}
+
+static DEVICE_ATTR(cpumask, S_IRUGO, rapl_get_attr_cpumask, NULL);
+
+static struct attribute *rapl_pmu_attrs[] = {
+ &dev_attr_cpumask.attr,
+ NULL,
+};
+
+static struct attribute_group rapl_pmu_attr_group = {
+ .attrs = rapl_pmu_attrs,
+};
+
+EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01");
+EVENT_ATTR_STR(energy-pkg , rapl_pkg, "event=0x02");
+EVENT_ATTR_STR(energy-ram , rapl_ram, "event=0x03");
+
+EVENT_ATTR_STR(energy-cores.unit, rapl_cores_unit, "Joules");
+EVENT_ATTR_STR(energy-pkg.unit , rapl_pkg_unit, "Joules");
+EVENT_ATTR_STR(energy-ram.unit , rapl_ram_unit, "Joules");
+
+/*
+ * we compute in 0.23 nJ increments regardless of MSR
+ */
+EVENT_ATTR_STR(energy-cores.scale, rapl_cores_scale, "2.3283064365386962890625e-10");
+EVENT_ATTR_STR(energy-pkg.scale, rapl_pkg_scale, "2.3283064365386962890625e-10");
+EVENT_ATTR_STR(energy-ram.scale, rapl_ram_scale, "2.3283064365386962890625e-10");
+
+static struct attribute *rapl_events_srv_attr[] = {
+ EVENT_PTR(rapl_cores),
+ EVENT_PTR(rapl_pkg),
+ EVENT_PTR(rapl_ram),
+
+ EVENT_PTR(rapl_cores_unit),
+ EVENT_PTR(rapl_pkg_unit),
+ EVENT_PTR(rapl_ram_unit),
+
+ EVENT_PTR(rapl_cores_scale),
+ EVENT_PTR(rapl_pkg_scale),
+ EVENT_PTR(rapl_ram_scale),
+ NULL,
+};
+
+static struct attribute *rapl_events_cln_attr[] = {
+ EVENT_PTR(rapl_cores),
+ EVENT_PTR(rapl_pkg),
+
+ EVENT_PTR(rapl_cores_unit),
+ EVENT_PTR(rapl_pkg_unit),
+
+ EVENT_PTR(rapl_cores_scale),
+ EVENT_PTR(rapl_pkg_scale),
+ NULL,
+};
+
+static struct attribute_group rapl_pmu_events_group = {
+ .name = "events",
+ .attrs = NULL, /* patched at runtime */
+};
+
+DEFINE_RAPL_FORMAT_ATTR(event, event, "config:0-7");
+static struct attribute *rapl_formats_attr[] = {
+ &format_attr_event.attr,
+ NULL,
+};
+
+static struct attribute_group rapl_pmu_format_group = {
+ .name = "format",
+ .attrs = rapl_formats_attr,
+};
+
+const struct attribute_group *rapl_attr_groups[] = {
+ &rapl_pmu_attr_group,
+ &rapl_pmu_format_group,
+ &rapl_pmu_events_group,
+ NULL,
+};
+
+static struct pmu rapl_pmu_class = {
+ .attr_groups = rapl_attr_groups,
+ .task_ctx_nr = perf_invalid_context, /* system-wide only */
+ .event_init = rapl_pmu_event_init,
+ .add = rapl_pmu_event_add, /* must have */
+ .del = rapl_pmu_event_del, /* must have */
+ .start = rapl_pmu_event_start,
+ .stop = rapl_pmu_event_stop,
+ .read = rapl_pmu_event_read,
+};
+
+static void rapl_cpu_exit(int cpu)
+{
+ struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu);
+ int i, phys_id = topology_physical_package_id(cpu);
+ int target = -1;
+
+ spin_lock(&rapl_hotplug_lock);
+
+ /* find a new cpu on same package */
+ for_each_online_cpu(i) {
+ if (i == cpu)
+ continue;
+ if (phys_id == topology_physical_package_id(i)) {
+ target = i;
+ break;
+ }
+ }
+ /*
+ * clear cpu from cpumask
+ * if was set in cpumask and still some cpu on package,
+ * then move to new cpu
+ */
+ if (cpumask_test_and_clear_cpu(cpu, &rapl_cpu_mask) && target >= 0)
+ cpumask_set_cpu(target, &rapl_cpu_mask);
+
+ WARN_ON(cpumask_empty(&rapl_cpu_mask));
+ /*
+ * migrate events and context to new cpu
+ */
+ if (target >= 0)
+ perf_pmu_migrate_context(pmu->pmu, cpu, target);
+
+ spin_unlock(&rapl_hotplug_lock);
+}
+
+static void rapl_cpu_init(int cpu)
+{
+ int i, phys_id = topology_physical_package_id(cpu);
+
+ spin_lock(&rapl_hotplug_lock);
+
+ /* check if phys_is is already covered */
+ for_each_cpu(i, &rapl_cpu_mask) {
+ if (phys_id == topology_physical_package_id(i))
+ goto skip;
+ }
+ /* was not found, so add it */
+ cpumask_set_cpu(cpu, &rapl_cpu_mask);
+skip:
+ spin_unlock(&rapl_hotplug_lock);
+}
+
+static int rapl_cpu_prepare(int cpu)
+{
+ struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu);
+ int phys_id = topology_physical_package_id(cpu);
+
+ if (pmu)
+ return 0;
+
+ if (phys_id < 0)
+ return -1;
+
+ pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
+ if (!pmu)
+ return -1;
+
+ spin_lock_init(&pmu->lock);
+
+ INIT_LIST_HEAD(&pmu->active_list);
+
+ /*
+ * grab power unit as: 1/2^unit Joules
+ *
+ * we cache in local PMU instance
+ */
+ rdmsrl(MSR_RAPL_POWER_UNIT, pmu->hw_unit);
+ pmu->hw_unit = (pmu->hw_unit >> 8) & 0x1FULL;
+ pmu->pmu = &rapl_pmu_class;
+
+ /* set RAPL pmu for this cpu for now */
+ per_cpu(rapl_pmu, cpu) = pmu;
+ per_cpu(rapl_pmu_to_free, cpu) = NULL;
+
+ return 0;
+}
+
+static void rapl_cpu_kfree(int cpu)
+{
+ struct rapl_pmu *pmu = per_cpu(rapl_pmu_to_free, cpu);
+
+ kfree(pmu);
+
+ per_cpu(rapl_pmu_to_free, cpu) = NULL;
+}
+
+static int rapl_cpu_dying(int cpu)
+{
+ struct rapl_pmu *pmu = per_cpu(rapl_pmu, cpu);
+
+ if (!pmu)
+ return 0;
+
+ spin_lock(&rapl_hotplug_lock);
+
+ per_cpu(rapl_pmu, cpu) = NULL;
+
+ per_cpu(rapl_pmu_to_free, cpu) = pmu;
+
+ spin_unlock(&rapl_hotplug_lock);
+
+ return 0;
+}
+
+static int rapl_cpu_notifier(struct notifier_block *self,
+ unsigned long action, void *hcpu)
+{
+ unsigned int cpu = (long)hcpu;
+
+ switch (action & ~CPU_TASKS_FROZEN) {
+ case CPU_UP_PREPARE:
+ rapl_cpu_prepare(cpu);
+ break;
+ case CPU_STARTING:
+ spin_lock(&rapl_hotplug_lock);
+ rapl_cpu_init(cpu);
+ spin_unlock(&rapl_hotplug_lock);
+ break;
+ case CPU_UP_CANCELED:
+ case CPU_DYING:
+ rapl_cpu_dying(cpu);
+ break;
+ case CPU_ONLINE:
+ case CPU_DEAD:
+ rapl_cpu_kfree(cpu);
+ break;
+ case CPU_DOWN_PREPARE:
+ rapl_cpu_exit(cpu);
+ break;
+ default:
+ break;
+ }
+
+ return NOTIFY_OK;
+}
+
+static const struct x86_cpu_id rapl_cpu_match[] = {
+ [0] = { .vendor = X86_VENDOR_INTEL, .family = 6 },
+ [1] = {},
+};
+
+static int __init rapl_pmu_init(void)
+{
+ struct rapl_pmu *pmu;
+ int cpu, ret;
+
+ /*
+ * check for Intel processor family 6
+ */
+ if (!x86_match_cpu(rapl_cpu_match))
+ return 0;
+
+ /* check supported CPU */
+ switch (boot_cpu_data.x86_model) {
+ case 42: /* Sandy Bridge */
+ case 58: /* Ivy Bridge */
+ case 60: /* Haswell */
+ rapl_cntr_mask = RAPL_IDX_CLN;
+ rapl_pmu_events_group.attrs = rapl_events_cln_attr;
+ break;
+ case 45: /* Sandy Bridge-EP */
+ case 62: /* IvyTown */
+ rapl_cntr_mask = RAPL_IDX_SRV;
+ rapl_pmu_events_group.attrs = rapl_events_srv_attr;
+ break;
+
+ default:
+ /* unsupported */
+ return 0;
+ }
+ get_online_cpus();
+
+ for_each_online_cpu(cpu) {
+ rapl_cpu_prepare(cpu);
+ rapl_cpu_init(cpu);
+ }
+
+ perf_cpu_notifier(rapl_cpu_notifier);
+
+ ret = perf_pmu_register(&rapl_pmu_class, "power", -1);
+ if (WARN_ON(ret)) {
+ pr_info("RAPL PMU detected, registration failed (%d), RAPL PMU disabled\n", ret);
+ put_online_cpus();
+ return -1;
+ }
+
+ pmu = __get_cpu_var(rapl_pmu);
+
+ pr_info("RAPL PMU detected, hw unit 2^-%d Joules,"
+ " API unit is 2^-32 Joules,"
+ " %d fixed counters\n",
+ pmu->hw_unit,
+ hweight32(rapl_cntr_mask));
+
+ put_online_cpus();
+
+ return 0;
+}
+device_initcall(rapl_pmu_init);
--
1.7.9.5
^ permalink raw reply [flat|nested] 10+ messages in thread