If loading a core PMU fails, legacy hardware/cache events may segv due
to there being no PMU. Create a placeholder empty PMU for this
case. This was discussed in:
https://lore.kernel.org/lkml/[email protected]/
Reported-by: Yang Jihong <[email protected]>
Signed-off-by: Ian Rogers <[email protected]>
---
tools/perf/util/pmu.c | 25 +++++++++++++++++++++++++
tools/perf/util/pmu.h | 1 +
tools/perf/util/pmus.c | 7 ++++++-
3 files changed, 32 insertions(+), 1 deletion(-)
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 8d5ecd4ff1a9..7f984a7f16ca 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -928,6 +928,31 @@ struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char
return NULL;
}
+/* Creates the PMU when sysfs scanning fails. */
+struct perf_pmu *perf_pmu__create_placeholder_core_pmu(struct list_head *core_pmus)
+{
+ struct perf_pmu *pmu = zalloc(sizeof(*pmu));
+
+ if (!pmu)
+ return NULL;
+
+ pmu->name = strdup("cpu");
+ if (!pmu->name) {
+ free(pmu);
+ return NULL;
+ }
+
+ pmu->is_core = true;
+ pmu->type = PERF_TYPE_RAW;
+ pmu->cpus = cpu_map__online();
+
+ INIT_LIST_HEAD(&pmu->format);
+ INIT_LIST_HEAD(&pmu->aliases);
+ INIT_LIST_HEAD(&pmu->caps);
+ list_add_tail(&pmu->list, core_pmus);
+ return pmu;
+}
+
void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu)
{
struct perf_pmu_format *format;
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 8807a624e918..203b92860e3c 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -286,6 +286,7 @@ int perf_pmu__event_source_devices_fd(void);
int perf_pmu__pathname_fd(int dirfd, const char *pmu_name, const char *filename, int flags);
struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char *lookup_name);
+struct perf_pmu *perf_pmu__create_placeholder_core_pmu(struct list_head *core_pmus);
void perf_pmu__delete(struct perf_pmu *pmu);
#endif /* __PMU_H */
diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c
index 0866dee3fc62..3cd9de42139e 100644
--- a/tools/perf/util/pmus.c
+++ b/tools/perf/util/pmus.c
@@ -153,7 +153,12 @@ static void pmu_read_sysfs(bool core_only)
closedir(dir);
if (core_only) {
- read_sysfs_core_pmus = true;
+ if (!list_empty(&core_pmus))
+ read_sysfs_core_pmus = true;
+ else {
+ if (perf_pmu__create_placeholder_core_pmu(&core_pmus))
+ read_sysfs_core_pmus = true;
+ }
} else {
read_sysfs_core_pmus = true;
read_sysfs_all_pmus = true;
--
2.41.0.162.gfafddb0af9-goog
Hello,
On 2023/6/28 2:28, Ian Rogers wrote:
> If loading a core PMU fails, legacy hardware/cache events may segv due
> to there being no PMU. Create a placeholder empty PMU for this
> case. This was discussed in:
> https://lore.kernel.org/lkml/[email protected]/
>
> Reported-by: Yang Jihong <[email protected]>
> Signed-off-by: Ian Rogers <[email protected]>
> ---
> tools/perf/util/pmu.c | 25 +++++++++++++++++++++++++
> tools/perf/util/pmu.h | 1 +
> tools/perf/util/pmus.c | 7 ++++++-
> 3 files changed, 32 insertions(+), 1 deletion(-)
>
> diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
> index 8d5ecd4ff1a9..7f984a7f16ca 100644
> --- a/tools/perf/util/pmu.c
> +++ b/tools/perf/util/pmu.c
> @@ -928,6 +928,31 @@ struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char
> return NULL;
> }
>
> +/* Creates the PMU when sysfs scanning fails. */
> +struct perf_pmu *perf_pmu__create_placeholder_core_pmu(struct list_head *core_pmus)
> +{
> + struct perf_pmu *pmu = zalloc(sizeof(*pmu));
> +
> + if (!pmu)
> + return NULL;
> +
> + pmu->name = strdup("cpu");
> + if (!pmu->name) {
> + free(pmu);
> + return NULL;
> + }
> +
> + pmu->is_core = true;
> + pmu->type = PERF_TYPE_RAW;
> + pmu->cpus = cpu_map__online();
> +
> + INIT_LIST_HEAD(&pmu->format);
> + INIT_LIST_HEAD(&pmu->aliases);
> + INIT_LIST_HEAD(&pmu->caps);
> + list_add_tail(&pmu->list, core_pmus);
> + return pmu;
> +}
> +
> void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu)
> {
> struct perf_pmu_format *format;
> diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
> index 8807a624e918..203b92860e3c 100644
> --- a/tools/perf/util/pmu.h
> +++ b/tools/perf/util/pmu.h
> @@ -286,6 +286,7 @@ int perf_pmu__event_source_devices_fd(void);
> int perf_pmu__pathname_fd(int dirfd, const char *pmu_name, const char *filename, int flags);
>
> struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char *lookup_name);
> +struct perf_pmu *perf_pmu__create_placeholder_core_pmu(struct list_head *core_pmus);
> void perf_pmu__delete(struct perf_pmu *pmu);
>
> #endif /* __PMU_H */
> diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c
> index 0866dee3fc62..3cd9de42139e 100644
> --- a/tools/perf/util/pmus.c
> +++ b/tools/perf/util/pmus.c
> @@ -153,7 +153,12 @@ static void pmu_read_sysfs(bool core_only)
>
> closedir(dir);
> if (core_only) {
> - read_sysfs_core_pmus = true;
> + if (!list_empty(&core_pmus))
> + read_sysfs_core_pmus = true;
> + else {
> + if (perf_pmu__create_placeholder_core_pmu(&core_pmus))
> + read_sysfs_core_pmus = true;
> + }
> } else {
> read_sysfs_core_pmus = true;
> read_sysfs_all_pmus = true;
>
Great. This patch solves the problem, the test results are shown in [1].
Tested-by: Yang Jihong <[email protected]>
[1]:
# perf --debug verbose=2 record true
<SNIP>
------------------------------------------------------------
perf_event_attr:
size 136
{ sample_period, sample_freq } 4000
sample_type IP|TID|TIME|PERIOD
read_format ID|LOST
disabled 1
inherit 1
mmap 1
comm 1
freq 1
enable_on_exec 1
task 1
precise_ip 3
sample_id_all 1
mmap2 1
comm_exec 1
ksymbol 1
bpf_event 1
------------------------------------------------------------
sys_perf_event_open: pid 703 cpu 0 group_fd -1 flags 0x8
sys_perf_event_open failed, error -2
decreasing precise_ip by one (2)
------------------------------------------------------------
perf_event_attr:
size 136
{ sample_period, sample_freq } 4000
sample_type IP|TID|TIME|PERIOD
read_format ID|LOST
disabled 1
inherit 1
mmap 1
comm 1
freq 1
enable_on_exec 1
task 1
precise_ip 2
sample_id_all 1
mmap2 1
comm_exec 1
ksymbol 1
bpf_event 1
------------------------------------------------------------
sys_perf_event_open: pid 703 cpu 0 group_fd -1 flags 0x8
sys_perf_event_open failed, error -2
decreasing precise_ip by one (1)
------------------------------------------------------------
perf_event_attr:
size 136
{ sample_period, sample_freq } 4000
sample_type IP|TID|TIME|PERIOD
read_format ID|LOST
disabled 1
inherit 1
mmap 1
comm 1
freq 1
enable_on_exec 1
task 1
precise_ip 1
sample_id_all 1
mmap2 1
comm_exec 1
ksymbol 1
bpf_event 1
------------------------------------------------------------
sys_perf_event_open: pid 703 cpu 0 group_fd -1 flags 0x8
sys_perf_event_open failed, error -2
decreasing precise_ip by one (0)
------------------------------------------------------------
perf_event_attr:
size 136
{ sample_period, sample_freq } 4000
sample_type IP|TID|TIME|PERIOD
read_format ID|LOST
disabled 1
inherit 1
mmap 1
comm 1
freq 1
enable_on_exec 1
task 1
sample_id_all 1
mmap2 1
comm_exec 1
ksymbol 1
bpf_event 1
------------------------------------------------------------
sys_perf_event_open: pid 703 cpu 0 group_fd -1 flags 0x8
sys_perf_event_open failed, error -2
Warning:
The cycles event is not supported, trying to fall back to cpu-clock-ticks
------------------------------------------------------------
perf_event_attr:
type 1
size 136
{ sample_period, sample_freq } 4000
sample_type IP|TID|TIME|PERIOD
read_format ID|LOST
disabled 1
inherit 1
mmap 1
comm 1
freq 1
enable_on_exec 1
task 1
precise_ip 3
sample_id_all 1
mmap2 1
comm_exec 1
ksymbol 1
bpf_event 1
------------------------------------------------------------
sys_perf_event_open: pid 703 cpu 0 group_fd -1 flags 0x8 = 5
sys_perf_event_open: pid 703 cpu 1 group_fd -1 flags 0x8 = 6
sys_perf_event_open: pid 703 cpu 2 group_fd -1 flags 0x8 = 7
sys_perf_event_open: pid 703 cpu 3 group_fd -1 flags 0x8 = 9
sys_perf_event_open: pid 703 cpu 4 group_fd -1 flags 0x8 = 10
sys_perf_event_open: pid 703 cpu 5 group_fd -1 flags 0x8 = 11
sys_perf_event_open: pid 703 cpu 6 group_fd -1 flags 0x8 = 12
sys_perf_event_open: pid 703 cpu 7 group_fd -1 flags 0x8 = 13
<SNIP>
[ perf record: Captured and wrote 0.006 MB perf.data (116 samples) ]
Thanks,
Yang
On Tue, Jun 27, 2023 at 8:01 PM Yang Jihong <[email protected]> wrote:
>
> Hello,
>
> On 2023/6/28 2:28, Ian Rogers wrote:
> > If loading a core PMU fails, legacy hardware/cache events may segv due
> > to there being no PMU. Create a placeholder empty PMU for this
> > case. This was discussed in:
> > https://lore.kernel.org/lkml/[email protected]/
> >
> > Reported-by: Yang Jihong <[email protected]>
> > Signed-off-by: Ian Rogers <[email protected]>
> > ---
> > tools/perf/util/pmu.c | 25 +++++++++++++++++++++++++
> > tools/perf/util/pmu.h | 1 +
> > tools/perf/util/pmus.c | 7 ++++++-
> > 3 files changed, 32 insertions(+), 1 deletion(-)
> >
> > diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
> > index 8d5ecd4ff1a9..7f984a7f16ca 100644
> > --- a/tools/perf/util/pmu.c
> > +++ b/tools/perf/util/pmu.c
> > @@ -928,6 +928,31 @@ struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char
> > return NULL;
> > }
> >
> > +/* Creates the PMU when sysfs scanning fails. */
> > +struct perf_pmu *perf_pmu__create_placeholder_core_pmu(struct list_head *core_pmus)
> > +{
> > + struct perf_pmu *pmu = zalloc(sizeof(*pmu));
> > +
> > + if (!pmu)
> > + return NULL;
> > +
> > + pmu->name = strdup("cpu");
> > + if (!pmu->name) {
> > + free(pmu);
> > + return NULL;
> > + }
> > +
> > + pmu->is_core = true;
> > + pmu->type = PERF_TYPE_RAW;
> > + pmu->cpus = cpu_map__online();
> > +
> > + INIT_LIST_HEAD(&pmu->format);
> > + INIT_LIST_HEAD(&pmu->aliases);
> > + INIT_LIST_HEAD(&pmu->caps);
> > + list_add_tail(&pmu->list, core_pmus);
> > + return pmu;
> > +}
> > +
> > void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu)
> > {
> > struct perf_pmu_format *format;
> > diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
> > index 8807a624e918..203b92860e3c 100644
> > --- a/tools/perf/util/pmu.h
> > +++ b/tools/perf/util/pmu.h
> > @@ -286,6 +286,7 @@ int perf_pmu__event_source_devices_fd(void);
> > int perf_pmu__pathname_fd(int dirfd, const char *pmu_name, const char *filename, int flags);
> >
> > struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char *lookup_name);
> > +struct perf_pmu *perf_pmu__create_placeholder_core_pmu(struct list_head *core_pmus);
> > void perf_pmu__delete(struct perf_pmu *pmu);
> >
> > #endif /* __PMU_H */
> > diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c
> > index 0866dee3fc62..3cd9de42139e 100644
> > --- a/tools/perf/util/pmus.c
> > +++ b/tools/perf/util/pmus.c
> > @@ -153,7 +153,12 @@ static void pmu_read_sysfs(bool core_only)
> >
> > closedir(dir);
> > if (core_only) {
> > - read_sysfs_core_pmus = true;
> > + if (!list_empty(&core_pmus))
> > + read_sysfs_core_pmus = true;
> > + else {
> > + if (perf_pmu__create_placeholder_core_pmu(&core_pmus))
> > + read_sysfs_core_pmus = true;
> > + }
> > } else {
> > read_sysfs_core_pmus = true;
> > read_sysfs_all_pmus = true;
> >
> Great. This patch solves the problem, the test results are shown in [1].
>
> Tested-by: Yang Jihong <[email protected]>
Applied to perf-tools-next, thanks!