Uncore events require a CPU i.e. it cannot be -1.
The evsel system_wide flag is intended for events that should be on every
CPU, which does not make sense for uncore events because uncore events do
not map one-to-one with CPUs.
These 2 requirements are not exactly the same, so introduce a new flag
'requires_cpu' the uncore case.
Signed-off-by: Adrian Hunter <[email protected]>
---
tools/lib/perf/evlist.c | 4 +++-
tools/lib/perf/include/internal/evsel.h | 1 +
tools/perf/builtin-stat.c | 5 +----
tools/perf/util/evsel.c | 1 +
tools/perf/util/parse-events.c | 2 +-
5 files changed, 7 insertions(+), 6 deletions(-)
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index 37dfa9d936a7..9fbcca3fc836 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -42,7 +42,9 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
if (!evsel->own_cpus || evlist->has_user_cpus) {
perf_cpu_map__put(evsel->cpus);
evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus);
- } else if (!evsel->system_wide && perf_cpu_map__empty(evlist->user_requested_cpus)) {
+ } else if (!evsel->system_wide &&
+ !evsel->requires_cpu &&
+ perf_cpu_map__empty(evlist->user_requested_cpus)) {
perf_cpu_map__put(evsel->cpus);
evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus);
} else if (evsel->cpus != evsel->own_cpus) {
diff --git a/tools/lib/perf/include/internal/evsel.h b/tools/lib/perf/include/internal/evsel.h
index cfc9ebd7968e..77fbb8b97e5c 100644
--- a/tools/lib/perf/include/internal/evsel.h
+++ b/tools/lib/perf/include/internal/evsel.h
@@ -50,6 +50,7 @@ struct perf_evsel {
/* parse modifier helper */
int nr_members;
bool system_wide;
+ bool requires_cpu;
int idx;
};
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index a96f106dc93a..8972ae546cfe 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -364,9 +364,6 @@ static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu_
if (!counter->supported)
return -ENOENT;
- if (counter->core.system_wide)
- nthreads = 1;
-
for (thread = 0; thread < nthreads; thread++) {
struct perf_counts_values *count;
@@ -2224,7 +2221,7 @@ static void setup_system_wide(int forks)
struct evsel *counter;
evlist__for_each_entry(evsel_list, counter) {
- if (!counter->core.system_wide &&
+ if (!counter->core.requires_cpu &&
strcmp(counter->name, "duration_time")) {
return;
}
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 2a1729e7aee4..81bbddb6fbc0 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -382,6 +382,7 @@ struct evsel *evsel__clone(struct evsel *orig)
evsel->core.threads = perf_thread_map__get(orig->core.threads);
evsel->core.nr_members = orig->core.nr_members;
evsel->core.system_wide = orig->core.system_wide;
+ evsel->core.requires_cpu = orig->core.requires_cpu;
if (orig->name) {
evsel->name = strdup(orig->name);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index dd84fed698a3..783359017548 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -350,7 +350,7 @@ __add_event(struct list_head *list, int *idx,
(*idx)++;
evsel->core.cpus = cpus;
evsel->core.own_cpus = perf_cpu_map__get(cpus);
- evsel->core.system_wide = pmu ? pmu->is_uncore : false;
+ evsel->core.requires_cpu = pmu ? pmu->is_uncore : false;
evsel->auto_merge_stats = auto_merge_stats;
if (name)
--
2.25.1
On Fri, Apr 29, 2022 at 3:58 PM Namhyung Kim <[email protected]> wrote:
>
> On Fri, Apr 22, 2022 at 9:25 AM Adrian Hunter <[email protected]> wrote:
> >
> > Uncore events require a CPU i.e. it cannot be -1.
> >
> > The evsel system_wide flag is intended for events that should be on every
> > CPU, which does not make sense for uncore events because uncore events do
> > not map one-to-one with CPUs.
> >
> > These 2 requirements are not exactly the same, so introduce a new flag
> > 'requires_cpu' the uncore case.
>
> Yeah, I like this change! I was often confused by the two different things.
>
> Thanks,
> Namhyung
>
> >
> > Signed-off-by: Adrian Hunter <[email protected]>
> > ---
> > tools/lib/perf/evlist.c | 4 +++-
> > tools/lib/perf/include/internal/evsel.h | 1 +
> > tools/perf/builtin-stat.c | 5 +----
> > tools/perf/util/evsel.c | 1 +
> > tools/perf/util/parse-events.c | 2 +-
> > 5 files changed, 7 insertions(+), 6 deletions(-)
> >
> > diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
> > index 37dfa9d936a7..9fbcca3fc836 100644
> > --- a/tools/lib/perf/evlist.c
> > +++ b/tools/lib/perf/evlist.c
> > @@ -42,7 +42,9 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
> > if (!evsel->own_cpus || evlist->has_user_cpus) {
> > perf_cpu_map__put(evsel->cpus);
> > evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus);
> > - } else if (!evsel->system_wide && perf_cpu_map__empty(evlist->user_requested_cpus)) {
> > + } else if (!evsel->system_wide &&
> > + !evsel->requires_cpu &&
> > + perf_cpu_map__empty(evlist->user_requested_cpus)) {
> > perf_cpu_map__put(evsel->cpus);
> > evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus);
> > } else if (evsel->cpus != evsel->own_cpus) {
> > diff --git a/tools/lib/perf/include/internal/evsel.h b/tools/lib/perf/include/internal/evsel.h
> > index cfc9ebd7968e..77fbb8b97e5c 100644
> > --- a/tools/lib/perf/include/internal/evsel.h
> > +++ b/tools/lib/perf/include/internal/evsel.h
> > @@ -50,6 +50,7 @@ struct perf_evsel {
> > /* parse modifier helper */
> > int nr_members;
> > bool system_wide;
Nice cleanup! Could we add some comments here as to what the booleans
mean/imply?
Thanks,
Ian
> > + bool requires_cpu;
> > int idx;
> > };
> >
> > diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
> > index a96f106dc93a..8972ae546cfe 100644
> > --- a/tools/perf/builtin-stat.c
> > +++ b/tools/perf/builtin-stat.c
> > @@ -364,9 +364,6 @@ static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu_
> > if (!counter->supported)
> > return -ENOENT;
> >
> > - if (counter->core.system_wide)
> > - nthreads = 1;
> > -
> > for (thread = 0; thread < nthreads; thread++) {
> > struct perf_counts_values *count;
> >
> > @@ -2224,7 +2221,7 @@ static void setup_system_wide(int forks)
> > struct evsel *counter;
> >
> > evlist__for_each_entry(evsel_list, counter) {
> > - if (!counter->core.system_wide &&
> > + if (!counter->core.requires_cpu &&
> > strcmp(counter->name, "duration_time")) {
> > return;
> > }
> > diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> > index 2a1729e7aee4..81bbddb6fbc0 100644
> > --- a/tools/perf/util/evsel.c
> > +++ b/tools/perf/util/evsel.c
> > @@ -382,6 +382,7 @@ struct evsel *evsel__clone(struct evsel *orig)
> > evsel->core.threads = perf_thread_map__get(orig->core.threads);
> > evsel->core.nr_members = orig->core.nr_members;
> > evsel->core.system_wide = orig->core.system_wide;
> > + evsel->core.requires_cpu = orig->core.requires_cpu;
> >
> > if (orig->name) {
> > evsel->name = strdup(orig->name);
> > diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
> > index dd84fed698a3..783359017548 100644
> > --- a/tools/perf/util/parse-events.c
> > +++ b/tools/perf/util/parse-events.c
> > @@ -350,7 +350,7 @@ __add_event(struct list_head *list, int *idx,
> > (*idx)++;
> > evsel->core.cpus = cpus;
> > evsel->core.own_cpus = perf_cpu_map__get(cpus);
> > - evsel->core.system_wide = pmu ? pmu->is_uncore : false;
> > + evsel->core.requires_cpu = pmu ? pmu->is_uncore : false;
> > evsel->auto_merge_stats = auto_merge_stats;
> >
> > if (name)
> > --
> > 2.25.1
> >
On Fri, Apr 22, 2022 at 9:25 AM Adrian Hunter <[email protected]> wrote:
>
> Uncore events require a CPU i.e. it cannot be -1.
>
> The evsel system_wide flag is intended for events that should be on every
> CPU, which does not make sense for uncore events because uncore events do
> not map one-to-one with CPUs.
>
> These 2 requirements are not exactly the same, so introduce a new flag
> 'requires_cpu' the uncore case.
Yeah, I like this change! I was often confused by the two different things.
Thanks,
Namhyung
>
> Signed-off-by: Adrian Hunter <[email protected]>
> ---
> tools/lib/perf/evlist.c | 4 +++-
> tools/lib/perf/include/internal/evsel.h | 1 +
> tools/perf/builtin-stat.c | 5 +----
> tools/perf/util/evsel.c | 1 +
> tools/perf/util/parse-events.c | 2 +-
> 5 files changed, 7 insertions(+), 6 deletions(-)
>
> diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
> index 37dfa9d936a7..9fbcca3fc836 100644
> --- a/tools/lib/perf/evlist.c
> +++ b/tools/lib/perf/evlist.c
> @@ -42,7 +42,9 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
> if (!evsel->own_cpus || evlist->has_user_cpus) {
> perf_cpu_map__put(evsel->cpus);
> evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus);
> - } else if (!evsel->system_wide && perf_cpu_map__empty(evlist->user_requested_cpus)) {
> + } else if (!evsel->system_wide &&
> + !evsel->requires_cpu &&
> + perf_cpu_map__empty(evlist->user_requested_cpus)) {
> perf_cpu_map__put(evsel->cpus);
> evsel->cpus = perf_cpu_map__get(evlist->user_requested_cpus);
> } else if (evsel->cpus != evsel->own_cpus) {
> diff --git a/tools/lib/perf/include/internal/evsel.h b/tools/lib/perf/include/internal/evsel.h
> index cfc9ebd7968e..77fbb8b97e5c 100644
> --- a/tools/lib/perf/include/internal/evsel.h
> +++ b/tools/lib/perf/include/internal/evsel.h
> @@ -50,6 +50,7 @@ struct perf_evsel {
> /* parse modifier helper */
> int nr_members;
> bool system_wide;
> + bool requires_cpu;
> int idx;
> };
>
> diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
> index a96f106dc93a..8972ae546cfe 100644
> --- a/tools/perf/builtin-stat.c
> +++ b/tools/perf/builtin-stat.c
> @@ -364,9 +364,6 @@ static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu_
> if (!counter->supported)
> return -ENOENT;
>
> - if (counter->core.system_wide)
> - nthreads = 1;
> -
> for (thread = 0; thread < nthreads; thread++) {
> struct perf_counts_values *count;
>
> @@ -2224,7 +2221,7 @@ static void setup_system_wide(int forks)
> struct evsel *counter;
>
> evlist__for_each_entry(evsel_list, counter) {
> - if (!counter->core.system_wide &&
> + if (!counter->core.requires_cpu &&
> strcmp(counter->name, "duration_time")) {
> return;
> }
> diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> index 2a1729e7aee4..81bbddb6fbc0 100644
> --- a/tools/perf/util/evsel.c
> +++ b/tools/perf/util/evsel.c
> @@ -382,6 +382,7 @@ struct evsel *evsel__clone(struct evsel *orig)
> evsel->core.threads = perf_thread_map__get(orig->core.threads);
> evsel->core.nr_members = orig->core.nr_members;
> evsel->core.system_wide = orig->core.system_wide;
> + evsel->core.requires_cpu = orig->core.requires_cpu;
>
> if (orig->name) {
> evsel->name = strdup(orig->name);
> diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
> index dd84fed698a3..783359017548 100644
> --- a/tools/perf/util/parse-events.c
> +++ b/tools/perf/util/parse-events.c
> @@ -350,7 +350,7 @@ __add_event(struct list_head *list, int *idx,
> (*idx)++;
> evsel->core.cpus = cpus;
> evsel->core.own_cpus = perf_cpu_map__get(cpus);
> - evsel->core.system_wide = pmu ? pmu->is_uncore : false;
> + evsel->core.requires_cpu = pmu ? pmu->is_uncore : false;
> evsel->auto_merge_stats = auto_merge_stats;
>
> if (name)
> --
> 2.25.1
>