* [PATCH v2] perf evsel: Fix missing exclude_{host,guest} setting
@ 2021-10-26 4:33 Namhyung Kim
2021-10-26 18:31 ` Jiri Olsa
0 siblings, 1 reply; 4+ messages in thread
From: Namhyung Kim @ 2021-10-26 4:33 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, Jiri Olsa
Cc: Ingo Molnar, Peter Zijlstra, LKML, Andi Kleen, Ian Rogers,
Stephane Eranian
The current logic for the perf missing feature has a bug that it can
wrongly clear some modifiers like G or H. Actually some PMUs don't
support any filtering or exclusion while others do. But we check it
as a global feature.
For example, the cycles event can have 'G' modifier to enable it only
in the guest mode on x86. When you don't run any VMs it'll return 0.
# perf stat -a -e cycles:G sleep 1
Performance counter stats for 'system wide':
0 cycles:G
1.000721670 seconds time elapsed
But when it's used with other pmu events that don't support G modifier,
it'll be reset and return non-zero values.
# perf stat -a -e cycles:G,msr/tsc/ sleep 1
Performance counter stats for 'system wide':
538,029,960 cycles:G
16,924,010,738 msr/tsc/
1.001815327 seconds time elapsed
This is because of the missing feature detection logic being global.
Add a hashmap to set pmu-specific exclude_host/guest features.
Reported-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
v2 changes)
* change to enum perf_missing_pmu_features
* pass NULL to hashmap__find() to skip checking
* add a blank line after declaration
tools/perf/util/evsel.c | 47 +++++++++++++++++++++++++++++++++++------
tools/perf/util/evsel.h | 7 ++++++
2 files changed, 48 insertions(+), 6 deletions(-)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index dbfeceb2546c..f33801b4615d 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1434,6 +1434,10 @@ void evsel__delete(struct evsel *evsel)
{
evsel__exit(evsel);
free(evsel);
+
+ /* just free it for the first evsel */
+ hashmap__free(perf_missing_features.pmu);
+ perf_missing_features.pmu = NULL;
}
void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
@@ -1791,6 +1795,23 @@ static int __evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus,
return 0;
}
+#define PMU_HASH_BITS 4
+
+static size_t pmu_hash(const void *key, void *ctx __maybe_unused)
+{
+ const struct evsel *evsel = key;
+
+ return hash_bits(evsel->core.attr.type, PMU_HASH_BITS);
+}
+
+static bool pmu_equal(const void *key1, const void *key2, void *ctx __maybe_unused)
+{
+ const struct evsel *a = key1;
+ const struct evsel *b = key2;
+
+ return a->core.attr.type == b->core.attr.type;
+}
+
static void evsel__disable_missing_features(struct evsel *evsel)
{
if (perf_missing_features.weight_struct) {
@@ -1807,8 +1828,13 @@ static void evsel__disable_missing_features(struct evsel *evsel)
evsel->open_flags &= ~(unsigned long)PERF_FLAG_FD_CLOEXEC;
if (perf_missing_features.mmap2)
evsel->core.attr.mmap2 = 0;
- if (perf_missing_features.exclude_guest)
- evsel->core.attr.exclude_guest = evsel->core.attr.exclude_host = 0;
+ if (perf_missing_features.exclude_guest) {
+ /* we only have EXCLUDE_GUEST bit, let's skip checking */
+ if (hashmap__find(perf_missing_features.pmu, evsel, NULL)) {
+ evsel->core.attr.exclude_guest = 0;
+ evsel->core.attr.exclude_host = 0;
+ }
+ }
if (perf_missing_features.lbr_flags)
evsel->core.attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS |
PERF_SAMPLE_BRANCH_NO_CYCLES);
@@ -1840,6 +1866,9 @@ int evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus,
bool evsel__detect_missing_features(struct evsel *evsel)
{
+ if (perf_missing_features.pmu == NULL)
+ perf_missing_features.pmu = hashmap__new(pmu_hash, pmu_equal, NULL);
+
/*
* Must probe features in the order they were added to the
* perf_event_attr interface.
@@ -1900,10 +1929,16 @@ bool evsel__detect_missing_features(struct evsel *evsel)
perf_missing_features.mmap2 = true;
pr_debug2_peo("switching off mmap2\n");
return true;
- } else if (!perf_missing_features.exclude_guest &&
- (evsel->core.attr.exclude_guest || evsel->core.attr.exclude_host)) {
- perf_missing_features.exclude_guest = true;
- pr_debug2_peo("switching off exclude_guest, exclude_host\n");
+ } else if ((evsel->core.attr.exclude_guest || evsel->core.attr.exclude_host) &&
+ !hashmap__find(perf_missing_features.pmu, evsel, NULL)) {
+ uintptr_t pmu_features = PERF_MISSING_PMU_EXCLUDE_GUEST;
+
+ hashmap__add(perf_missing_features.pmu, evsel, (void *)pmu_features);
+
+ if (!perf_missing_features.exclude_guest) {
+ perf_missing_features.exclude_guest = true;
+ pr_debug2_peo("switching off exclude_guest, exclude_host\n");
+ }
return true;
} else if (!perf_missing_features.sample_id_all) {
perf_missing_features.sample_id_all = true;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 1f7edfa8568a..11b5ece19f0e 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -172,6 +172,13 @@ struct perf_missing_features {
bool data_page_size;
bool code_page_size;
bool weight_struct;
+
+ /* contains enum perf_missing_pmu_features below */
+ struct hashmap *pmu;
+};
+
+enum perf_missing_pmu_features {
+ PERF_MISSING_PMU_EXCLUDE_GUEST = 1UL << 0,
};
extern struct perf_missing_features perf_missing_features;
--
2.33.0.1079.g6e70778dc9-goog
^ permalink raw reply related [flat|nested] 4+ messages in thread
* Re: [PATCH v2] perf evsel: Fix missing exclude_{host,guest} setting
2021-10-26 4:33 [PATCH v2] perf evsel: Fix missing exclude_{host,guest} setting Namhyung Kim
@ 2021-10-26 18:31 ` Jiri Olsa
2021-10-26 19:30 ` Namhyung Kim
0 siblings, 1 reply; 4+ messages in thread
From: Jiri Olsa @ 2021-10-26 18:31 UTC (permalink / raw)
To: Namhyung Kim
Cc: Arnaldo Carvalho de Melo, Ingo Molnar, Peter Zijlstra, LKML,
Andi Kleen, Ian Rogers, Stephane Eranian
On Mon, Oct 25, 2021 at 09:33:51PM -0700, Namhyung Kim wrote:
> The current logic for the perf missing feature has a bug that it can
> wrongly clear some modifiers like G or H. Actually some PMUs don't
> support any filtering or exclusion while others do. But we check it
> as a global feature.
>
> For example, the cycles event can have 'G' modifier to enable it only
> in the guest mode on x86. When you don't run any VMs it'll return 0.
>
> # perf stat -a -e cycles:G sleep 1
>
> Performance counter stats for 'system wide':
>
> 0 cycles:G
>
> 1.000721670 seconds time elapsed
>
> But when it's used with other pmu events that don't support G modifier,
> it'll be reset and return non-zero values.
>
> # perf stat -a -e cycles:G,msr/tsc/ sleep 1
>
> Performance counter stats for 'system wide':
>
> 538,029,960 cycles:G
> 16,924,010,738 msr/tsc/
>
> 1.001815327 seconds time elapsed
>
> This is because of the missing feature detection logic being global.
> Add a hashmap to set pmu-specific exclude_host/guest features.
>
> Reported-by: Stephane Eranian <eranian@google.com>
> Signed-off-by: Namhyung Kim <namhyung@kernel.org>
> ---
> v2 changes)
> * change to enum perf_missing_pmu_features
> * pass NULL to hashmap__find() to skip checking
> * add a blank line after declaration
>
> tools/perf/util/evsel.c | 47 +++++++++++++++++++++++++++++++++++------
> tools/perf/util/evsel.h | 7 ++++++
> 2 files changed, 48 insertions(+), 6 deletions(-)
>
> diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> index dbfeceb2546c..f33801b4615d 100644
> --- a/tools/perf/util/evsel.c
> +++ b/tools/perf/util/evsel.c
> @@ -1434,6 +1434,10 @@ void evsel__delete(struct evsel *evsel)
> {
> evsel__exit(evsel);
> free(evsel);
> +
> + /* just free it for the first evsel */
> + hashmap__free(perf_missing_features.pmu);
> + perf_missing_features.pmu = NULL;
should this just remove evsel from perf_missing_features.pmu?
I'm not sure when we should actually release this.. what's your rationale
for releasing it in here?
> }
>
> void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
> @@ -1791,6 +1795,23 @@ static int __evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus,
> return 0;
> }
>
> +#define PMU_HASH_BITS 4
> +
> +static size_t pmu_hash(const void *key, void *ctx __maybe_unused)
> +{
> + const struct evsel *evsel = key;
> +
> + return hash_bits(evsel->core.attr.type, PMU_HASH_BITS);
> +}
> +
> +static bool pmu_equal(const void *key1, const void *key2, void *ctx __maybe_unused)
> +{
> + const struct evsel *a = key1;
> + const struct evsel *b = key2;
> +
> + return a->core.attr.type == b->core.attr.type;
> +}
> +
> static void evsel__disable_missing_features(struct evsel *evsel)
> {
> if (perf_missing_features.weight_struct) {
> @@ -1807,8 +1828,13 @@ static void evsel__disable_missing_features(struct evsel *evsel)
> evsel->open_flags &= ~(unsigned long)PERF_FLAG_FD_CLOEXEC;
> if (perf_missing_features.mmap2)
> evsel->core.attr.mmap2 = 0;
> - if (perf_missing_features.exclude_guest)
> - evsel->core.attr.exclude_guest = evsel->core.attr.exclude_host = 0;
> + if (perf_missing_features.exclude_guest) {
> + /* we only have EXCLUDE_GUEST bit, let's skip checking */
> + if (hashmap__find(perf_missing_features.pmu, evsel, NULL)) {
> + evsel->core.attr.exclude_guest = 0;
> + evsel->core.attr.exclude_host = 0;
> + }
> + }
> if (perf_missing_features.lbr_flags)
> evsel->core.attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS |
> PERF_SAMPLE_BRANCH_NO_CYCLES);
> @@ -1840,6 +1866,9 @@ int evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus,
>
> bool evsel__detect_missing_features(struct evsel *evsel)
> {
> + if (perf_missing_features.pmu == NULL)
> + perf_missing_features.pmu = hashmap__new(pmu_hash, pmu_equal, NULL);
missing allocation fail check
thanks,
jirka
> +
> /*
> * Must probe features in the order they were added to the
> * perf_event_attr interface.
> @@ -1900,10 +1929,16 @@ bool evsel__detect_missing_features(struct evsel *evsel)
> perf_missing_features.mmap2 = true;
> pr_debug2_peo("switching off mmap2\n");
> return true;
> - } else if (!perf_missing_features.exclude_guest &&
> - (evsel->core.attr.exclude_guest || evsel->core.attr.exclude_host)) {
> - perf_missing_features.exclude_guest = true;
> - pr_debug2_peo("switching off exclude_guest, exclude_host\n");
> + } else if ((evsel->core.attr.exclude_guest || evsel->core.attr.exclude_host) &&
> + !hashmap__find(perf_missing_features.pmu, evsel, NULL)) {
> + uintptr_t pmu_features = PERF_MISSING_PMU_EXCLUDE_GUEST;
> +
> + hashmap__add(perf_missing_features.pmu, evsel, (void *)pmu_features);
> +
> + if (!perf_missing_features.exclude_guest) {
> + perf_missing_features.exclude_guest = true;
> + pr_debug2_peo("switching off exclude_guest, exclude_host\n");
> + }
> return true;
> } else if (!perf_missing_features.sample_id_all) {
> perf_missing_features.sample_id_all = true;
> diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
> index 1f7edfa8568a..11b5ece19f0e 100644
> --- a/tools/perf/util/evsel.h
> +++ b/tools/perf/util/evsel.h
> @@ -172,6 +172,13 @@ struct perf_missing_features {
> bool data_page_size;
> bool code_page_size;
> bool weight_struct;
> +
> + /* contains enum perf_missing_pmu_features below */
> + struct hashmap *pmu;
> +};
> +
> +enum perf_missing_pmu_features {
> + PERF_MISSING_PMU_EXCLUDE_GUEST = 1UL << 0,
> };
>
> extern struct perf_missing_features perf_missing_features;
> --
> 2.33.0.1079.g6e70778dc9-goog
>
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH v2] perf evsel: Fix missing exclude_{host,guest} setting
2021-10-26 18:31 ` Jiri Olsa
@ 2021-10-26 19:30 ` Namhyung Kim
2021-10-27 8:58 ` Jiri Olsa
0 siblings, 1 reply; 4+ messages in thread
From: Namhyung Kim @ 2021-10-26 19:30 UTC (permalink / raw)
To: Jiri Olsa
Cc: Arnaldo Carvalho de Melo, Ingo Molnar, Peter Zijlstra, LKML,
Andi Kleen, Ian Rogers, Stephane Eranian
Hi Jiri,
On Tue, Oct 26, 2021 at 11:32 AM Jiri Olsa <jolsa@redhat.com> wrote:
>
> On Mon, Oct 25, 2021 at 09:33:51PM -0700, Namhyung Kim wrote:
> > The current logic for the perf missing feature has a bug that it can
> > wrongly clear some modifiers like G or H. Actually some PMUs don't
> > support any filtering or exclusion while others do. But we check it
> > as a global feature.
> >
> > For example, the cycles event can have 'G' modifier to enable it only
> > in the guest mode on x86. When you don't run any VMs it'll return 0.
> >
> > # perf stat -a -e cycles:G sleep 1
> >
> > Performance counter stats for 'system wide':
> >
> > 0 cycles:G
> >
> > 1.000721670 seconds time elapsed
> >
> > But when it's used with other pmu events that don't support G modifier,
> > it'll be reset and return non-zero values.
> >
> > # perf stat -a -e cycles:G,msr/tsc/ sleep 1
> >
> > Performance counter stats for 'system wide':
> >
> > 538,029,960 cycles:G
> > 16,924,010,738 msr/tsc/
> >
> > 1.001815327 seconds time elapsed
> >
> > This is because of the missing feature detection logic being global.
> > Add a hashmap to set pmu-specific exclude_host/guest features.
> >
> > Reported-by: Stephane Eranian <eranian@google.com>
> > Signed-off-by: Namhyung Kim <namhyung@kernel.org>
> > ---
> > v2 changes)
> > * change to enum perf_missing_pmu_features
> > * pass NULL to hashmap__find() to skip checking
> > * add a blank line after declaration
> >
> > tools/perf/util/evsel.c | 47 +++++++++++++++++++++++++++++++++++------
> > tools/perf/util/evsel.h | 7 ++++++
> > 2 files changed, 48 insertions(+), 6 deletions(-)
> >
> > diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> > index dbfeceb2546c..f33801b4615d 100644
> > --- a/tools/perf/util/evsel.c
> > +++ b/tools/perf/util/evsel.c
> > @@ -1434,6 +1434,10 @@ void evsel__delete(struct evsel *evsel)
> > {
> > evsel__exit(evsel);
> > free(evsel);
> > +
> > + /* just free it for the first evsel */
> > + hashmap__free(perf_missing_features.pmu);
> > + perf_missing_features.pmu = NULL;
>
> should this just remove evsel from perf_missing_features.pmu?
Nop, it'll release all the hash nodes (pmu). Each evsel can come
from a same PMU.
>
> I'm not sure when we should actually release this.. what's your rationale
> for releasing it in here?
Yeah, that's a problem when we should release it. Maybe we can
add a function and call it in the exit path but I didn't want to change
all the callsites just for this.
As evsel__delete() is called in the exit path, I thought it's a
place where we can free the hashmap. But I'm not very happy
with that either.. Do you have a better idea?
If another evsel is open after this function, I think it should
be fine since it will create a new hash map and check the
missing feature again.
>
> > }
> >
> > void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
> > @@ -1791,6 +1795,23 @@ static int __evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus,
> > return 0;
> > }
> >
> > +#define PMU_HASH_BITS 4
> > +
> > +static size_t pmu_hash(const void *key, void *ctx __maybe_unused)
> > +{
> > + const struct evsel *evsel = key;
> > +
> > + return hash_bits(evsel->core.attr.type, PMU_HASH_BITS);
> > +}
> > +
> > +static bool pmu_equal(const void *key1, const void *key2, void *ctx __maybe_unused)
> > +{
> > + const struct evsel *a = key1;
> > + const struct evsel *b = key2;
> > +
> > + return a->core.attr.type == b->core.attr.type;
> > +}
> > +
> > static void evsel__disable_missing_features(struct evsel *evsel)
> > {
> > if (perf_missing_features.weight_struct) {
> > @@ -1807,8 +1828,13 @@ static void evsel__disable_missing_features(struct evsel *evsel)
> > evsel->open_flags &= ~(unsigned long)PERF_FLAG_FD_CLOEXEC;
> > if (perf_missing_features.mmap2)
> > evsel->core.attr.mmap2 = 0;
> > - if (perf_missing_features.exclude_guest)
> > - evsel->core.attr.exclude_guest = evsel->core.attr.exclude_host = 0;
> > + if (perf_missing_features.exclude_guest) {
> > + /* we only have EXCLUDE_GUEST bit, let's skip checking */
> > + if (hashmap__find(perf_missing_features.pmu, evsel, NULL)) {
> > + evsel->core.attr.exclude_guest = 0;
> > + evsel->core.attr.exclude_host = 0;
> > + }
> > + }
> > if (perf_missing_features.lbr_flags)
> > evsel->core.attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS |
> > PERF_SAMPLE_BRANCH_NO_CYCLES);
> > @@ -1840,6 +1866,9 @@ int evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus,
> >
> > bool evsel__detect_missing_features(struct evsel *evsel)
> > {
> > + if (perf_missing_features.pmu == NULL)
> > + perf_missing_features.pmu = hashmap__new(pmu_hash, pmu_equal, NULL);
>
> missing allocation fail check
Ok, will change.
Thanks for your review,
Namhyung
>
> > +
> > /*
> > * Must probe features in the order they were added to the
> > * perf_event_attr interface.
> > @@ -1900,10 +1929,16 @@ bool evsel__detect_missing_features(struct evsel *evsel)
> > perf_missing_features.mmap2 = true;
> > pr_debug2_peo("switching off mmap2\n");
> > return true;
> > - } else if (!perf_missing_features.exclude_guest &&
> > - (evsel->core.attr.exclude_guest || evsel->core.attr.exclude_host)) {
> > - perf_missing_features.exclude_guest = true;
> > - pr_debug2_peo("switching off exclude_guest, exclude_host\n");
> > + } else if ((evsel->core.attr.exclude_guest || evsel->core.attr.exclude_host) &&
> > + !hashmap__find(perf_missing_features.pmu, evsel, NULL)) {
> > + uintptr_t pmu_features = PERF_MISSING_PMU_EXCLUDE_GUEST;
> > +
> > + hashmap__add(perf_missing_features.pmu, evsel, (void *)pmu_features);
> > +
> > + if (!perf_missing_features.exclude_guest) {
> > + perf_missing_features.exclude_guest = true;
> > + pr_debug2_peo("switching off exclude_guest, exclude_host\n");
> > + }
> > return true;
> > } else if (!perf_missing_features.sample_id_all) {
> > perf_missing_features.sample_id_all = true;
> > diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
> > index 1f7edfa8568a..11b5ece19f0e 100644
> > --- a/tools/perf/util/evsel.h
> > +++ b/tools/perf/util/evsel.h
> > @@ -172,6 +172,13 @@ struct perf_missing_features {
> > bool data_page_size;
> > bool code_page_size;
> > bool weight_struct;
> > +
> > + /* contains enum perf_missing_pmu_features below */
> > + struct hashmap *pmu;
> > +};
> > +
> > +enum perf_missing_pmu_features {
> > + PERF_MISSING_PMU_EXCLUDE_GUEST = 1UL << 0,
> > };
> >
> > extern struct perf_missing_features perf_missing_features;
> > --
> > 2.33.0.1079.g6e70778dc9-goog
> >
>
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH v2] perf evsel: Fix missing exclude_{host,guest} setting
2021-10-26 19:30 ` Namhyung Kim
@ 2021-10-27 8:58 ` Jiri Olsa
0 siblings, 0 replies; 4+ messages in thread
From: Jiri Olsa @ 2021-10-27 8:58 UTC (permalink / raw)
To: Namhyung Kim
Cc: Arnaldo Carvalho de Melo, Ingo Molnar, Peter Zijlstra, LKML,
Andi Kleen, Ian Rogers, Stephane Eranian
On Tue, Oct 26, 2021 at 12:30:42PM -0700, Namhyung Kim wrote:
> Hi Jiri,
>
> On Tue, Oct 26, 2021 at 11:32 AM Jiri Olsa <jolsa@redhat.com> wrote:
> >
> > On Mon, Oct 25, 2021 at 09:33:51PM -0700, Namhyung Kim wrote:
> > > The current logic for the perf missing feature has a bug that it can
> > > wrongly clear some modifiers like G or H. Actually some PMUs don't
> > > support any filtering or exclusion while others do. But we check it
> > > as a global feature.
> > >
> > > For example, the cycles event can have 'G' modifier to enable it only
> > > in the guest mode on x86. When you don't run any VMs it'll return 0.
> > >
> > > # perf stat -a -e cycles:G sleep 1
> > >
> > > Performance counter stats for 'system wide':
> > >
> > > 0 cycles:G
> > >
> > > 1.000721670 seconds time elapsed
> > >
> > > But when it's used with other pmu events that don't support G modifier,
> > > it'll be reset and return non-zero values.
> > >
> > > # perf stat -a -e cycles:G,msr/tsc/ sleep 1
> > >
> > > Performance counter stats for 'system wide':
> > >
> > > 538,029,960 cycles:G
> > > 16,924,010,738 msr/tsc/
> > >
> > > 1.001815327 seconds time elapsed
> > >
> > > This is because of the missing feature detection logic being global.
> > > Add a hashmap to set pmu-specific exclude_host/guest features.
> > >
> > > Reported-by: Stephane Eranian <eranian@google.com>
> > > Signed-off-by: Namhyung Kim <namhyung@kernel.org>
> > > ---
> > > v2 changes)
> > > * change to enum perf_missing_pmu_features
> > > * pass NULL to hashmap__find() to skip checking
> > > * add a blank line after declaration
> > >
> > > tools/perf/util/evsel.c | 47 +++++++++++++++++++++++++++++++++++------
> > > tools/perf/util/evsel.h | 7 ++++++
> > > 2 files changed, 48 insertions(+), 6 deletions(-)
> > >
> > > diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
> > > index dbfeceb2546c..f33801b4615d 100644
> > > --- a/tools/perf/util/evsel.c
> > > +++ b/tools/perf/util/evsel.c
> > > @@ -1434,6 +1434,10 @@ void evsel__delete(struct evsel *evsel)
> > > {
> > > evsel__exit(evsel);
> > > free(evsel);
> > > +
> > > + /* just free it for the first evsel */
> > > + hashmap__free(perf_missing_features.pmu);
> > > + perf_missing_features.pmu = NULL;
> >
> > should this just remove evsel from perf_missing_features.pmu?
>
> Nop, it'll release all the hash nodes (pmu). Each evsel can come
> from a same PMU.
>
> >
> > I'm not sure when we should actually release this.. what's your rationale
> > for releasing it in here?
>
> Yeah, that's a problem when we should release it. Maybe we can
> add a function and call it in the exit path but I didn't want to change
> all the callsites just for this.
yea, I think we probably need it in other places as well,
but that should be separate patchset I think
>
> As evsel__delete() is called in the exit path, I thought it's a
> place where we can free the hashmap. But I'm not very happy
> with that either.. Do you have a better idea?
nope ;-)
>
> If another evsel is open after this function, I think it should
> be fine since it will create a new hash map and check the
> missing feature again.
I think let's keep it as it is for now and we'll see
thanks,
jirka
>
>
> >
> > > }
> > >
> > > void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
> > > @@ -1791,6 +1795,23 @@ static int __evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus,
> > > return 0;
> > > }
> > >
> > > +#define PMU_HASH_BITS 4
> > > +
> > > +static size_t pmu_hash(const void *key, void *ctx __maybe_unused)
> > > +{
> > > + const struct evsel *evsel = key;
> > > +
> > > + return hash_bits(evsel->core.attr.type, PMU_HASH_BITS);
> > > +}
> > > +
> > > +static bool pmu_equal(const void *key1, const void *key2, void *ctx __maybe_unused)
> > > +{
> > > + const struct evsel *a = key1;
> > > + const struct evsel *b = key2;
> > > +
> > > + return a->core.attr.type == b->core.attr.type;
> > > +}
> > > +
> > > static void evsel__disable_missing_features(struct evsel *evsel)
> > > {
> > > if (perf_missing_features.weight_struct) {
> > > @@ -1807,8 +1828,13 @@ static void evsel__disable_missing_features(struct evsel *evsel)
> > > evsel->open_flags &= ~(unsigned long)PERF_FLAG_FD_CLOEXEC;
> > > if (perf_missing_features.mmap2)
> > > evsel->core.attr.mmap2 = 0;
> > > - if (perf_missing_features.exclude_guest)
> > > - evsel->core.attr.exclude_guest = evsel->core.attr.exclude_host = 0;
> > > + if (perf_missing_features.exclude_guest) {
> > > + /* we only have EXCLUDE_GUEST bit, let's skip checking */
> > > + if (hashmap__find(perf_missing_features.pmu, evsel, NULL)) {
> > > + evsel->core.attr.exclude_guest = 0;
> > > + evsel->core.attr.exclude_host = 0;
> > > + }
> > > + }
> > > if (perf_missing_features.lbr_flags)
> > > evsel->core.attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS |
> > > PERF_SAMPLE_BRANCH_NO_CYCLES);
> > > @@ -1840,6 +1866,9 @@ int evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus,
> > >
> > > bool evsel__detect_missing_features(struct evsel *evsel)
> > > {
> > > + if (perf_missing_features.pmu == NULL)
> > > + perf_missing_features.pmu = hashmap__new(pmu_hash, pmu_equal, NULL);
> >
> > missing allocation fail check
>
> Ok, will change.
>
> Thanks for your review,
> Namhyung
>
>
> >
> > > +
> > > /*
> > > * Must probe features in the order they were added to the
> > > * perf_event_attr interface.
> > > @@ -1900,10 +1929,16 @@ bool evsel__detect_missing_features(struct evsel *evsel)
> > > perf_missing_features.mmap2 = true;
> > > pr_debug2_peo("switching off mmap2\n");
> > > return true;
> > > - } else if (!perf_missing_features.exclude_guest &&
> > > - (evsel->core.attr.exclude_guest || evsel->core.attr.exclude_host)) {
> > > - perf_missing_features.exclude_guest = true;
> > > - pr_debug2_peo("switching off exclude_guest, exclude_host\n");
> > > + } else if ((evsel->core.attr.exclude_guest || evsel->core.attr.exclude_host) &&
> > > + !hashmap__find(perf_missing_features.pmu, evsel, NULL)) {
> > > + uintptr_t pmu_features = PERF_MISSING_PMU_EXCLUDE_GUEST;
> > > +
> > > + hashmap__add(perf_missing_features.pmu, evsel, (void *)pmu_features);
> > > +
> > > + if (!perf_missing_features.exclude_guest) {
> > > + perf_missing_features.exclude_guest = true;
> > > + pr_debug2_peo("switching off exclude_guest, exclude_host\n");
> > > + }
> > > return true;
> > > } else if (!perf_missing_features.sample_id_all) {
> > > perf_missing_features.sample_id_all = true;
> > > diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
> > > index 1f7edfa8568a..11b5ece19f0e 100644
> > > --- a/tools/perf/util/evsel.h
> > > +++ b/tools/perf/util/evsel.h
> > > @@ -172,6 +172,13 @@ struct perf_missing_features {
> > > bool data_page_size;
> > > bool code_page_size;
> > > bool weight_struct;
> > > +
> > > + /* contains enum perf_missing_pmu_features below */
> > > + struct hashmap *pmu;
> > > +};
> > > +
> > > +enum perf_missing_pmu_features {
> > > + PERF_MISSING_PMU_EXCLUDE_GUEST = 1UL << 0,
> > > };
> > >
> > > extern struct perf_missing_features perf_missing_features;
> > > --
> > > 2.33.0.1079.g6e70778dc9-goog
> > >
> >
>
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2021-10-27 8:58 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-10-26 4:33 [PATCH v2] perf evsel: Fix missing exclude_{host,guest} setting Namhyung Kim
2021-10-26 18:31 ` Jiri Olsa
2021-10-26 19:30 ` Namhyung Kim
2021-10-27 8:58 ` Jiri Olsa
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.