From: Kan Liang <[email protected]>
An earlier kernel patch allowed enabling PT and LBR at the same
time on Goldmont.
commit ccbebba4c6bf ("perf/x86/intel/pt: Bypass PT vs. LBR
exclusivity if the core supports it")
However, users still cannot use Intel PT and LBRs simultaneously.
$ sudo perf record -e cycles,intel_pt//u -b -- sleep 1
Error:
PMU Hardware doesn't support sampling/overflow-interrupts.
PT implicitly adds dummy event in perf tool. dummy event is
software event which doesn't support LBR.
Always setting branch_type=no for dummy event in Intel PT.
Signed-off-by: Kan Liang <[email protected]>
---
tools/perf/arch/x86/util/intel-pt.c | 19 +++++++++++++++++++
1 file changed, 19 insertions(+)
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index f630de0..651ab9e 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -544,6 +544,22 @@ static int intel_pt_validate_config(struct perf_pmu *intel_pt_pmu,
evsel->attr.config);
}
+static int add_no_lbr_config_term(struct list_head *config_terms)
+{
+ struct perf_evsel_config_term *lbr_term;
+
+ lbr_term = zalloc(sizeof(*lbr_term));
+ if (!lbr_term)
+ return -ENOMEM;
+
+ INIT_LIST_HEAD(&lbr_term->list);
+ lbr_term->type = PERF_EVSEL__CONFIG_TERM_BRANCH;
+ lbr_term->val.branch = strdup("no");
+ list_add_tail(&lbr_term->list, config_terms);
+
+ return 0;
+}
+
static int intel_pt_recording_options(struct auxtrace_record *itr,
struct perf_evlist *evlist,
struct record_opts *opts)
@@ -701,6 +717,8 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
perf_evsel__set_sample_bit(switch_evsel, TIME);
perf_evsel__set_sample_bit(switch_evsel, CPU);
+ add_no_lbr_config_term(&switch_evsel->config_terms);
+
opts->record_switch_events = false;
ptr->have_sched_switch = 3;
} else {
@@ -760,6 +778,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
/* And the CPU for switch events */
perf_evsel__set_sample_bit(tracking_evsel, CPU);
}
+ add_no_lbr_config_term(&tracking_evsel->config_terms);
}
/*
--
2.9.4
On Wed, Jun 28, 2017 at 10:31:53AM -0400, [email protected] wrote:
> From: Kan Liang <[email protected]>
>
> An earlier kernel patch allowed enabling PT and LBR at the same
> time on Goldmont.
> commit ccbebba4c6bf ("perf/x86/intel/pt: Bypass PT vs. LBR
> exclusivity if the core supports it")
> However, users still cannot use Intel PT and LBRs simultaneously.
> $ sudo perf record -e cycles,intel_pt//u -b -- sleep 1
> Error:
> PMU Hardware doesn't support sampling/overflow-interrupts.
>
> PT implicitly adds dummy event in perf tool. dummy event is
> software event which doesn't support LBR.
>
> Always setting branch_type=no for dummy event in Intel PT.
>
> Signed-off-by: Kan Liang <[email protected]>
> ---
> tools/perf/arch/x86/util/intel-pt.c | 19 +++++++++++++++++++
> 1 file changed, 19 insertions(+)
>
> diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
> index f630de0..651ab9e 100644
> --- a/tools/perf/arch/x86/util/intel-pt.c
> +++ b/tools/perf/arch/x86/util/intel-pt.c
> @@ -544,6 +544,22 @@ static int intel_pt_validate_config(struct perf_pmu *intel_pt_pmu,
> evsel->attr.config);
> }
>
> +static int add_no_lbr_config_term(struct list_head *config_terms)
> +{
> + struct perf_evsel_config_term *lbr_term;
> +
> + lbr_term = zalloc(sizeof(*lbr_term));
> + if (!lbr_term)
> + return -ENOMEM;
> +
> + INIT_LIST_HEAD(&lbr_term->list);
> + lbr_term->type = PERF_EVSEL__CONFIG_TERM_BRANCH;
> + lbr_term->val.branch = strdup("no");
> + list_add_tail(&lbr_term->list, config_terms);
> +
> + return 0;
> +}
> +
> static int intel_pt_recording_options(struct auxtrace_record *itr,
> struct perf_evlist *evlist,
> struct record_opts *opts)
> @@ -701,6 +717,8 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
> perf_evsel__set_sample_bit(switch_evsel, TIME);
> perf_evsel__set_sample_bit(switch_evsel, CPU);
>
> + add_no_lbr_config_term(&switch_evsel->config_terms);
> +
hum, why can't you change the sample bit directly? with:
perf_evsel__reset_sample_bit(switch_evsel, BRANCH_STACK);
jirka
> On Wed, Jun 28, 2017 at 10:31:53AM -0400, [email protected] wrote:
> > From: Kan Liang <[email protected]>
> >
> > An earlier kernel patch allowed enabling PT and LBR at the same time
> > on Goldmont.
> > commit ccbebba4c6bf ("perf/x86/intel/pt: Bypass PT vs. LBR exclusivity
> > if the core supports it") However, users still cannot use Intel PT and
> > LBRs simultaneously.
> > $ sudo perf record -e cycles,intel_pt//u -b -- sleep 1
> > Error:
> > PMU Hardware doesn't support sampling/overflow-interrupts.
> >
> > PT implicitly adds dummy event in perf tool. dummy event is software
> > event which doesn't support LBR.
> >
> > Always setting branch_type=no for dummy event in Intel PT.
> >
> > Signed-off-by: Kan Liang <[email protected]>
> > ---
> > tools/perf/arch/x86/util/intel-pt.c | 19 +++++++++++++++++++
> > 1 file changed, 19 insertions(+)
> >
> > diff --git a/tools/perf/arch/x86/util/intel-pt.c
> > b/tools/perf/arch/x86/util/intel-pt.c
> > index f630de0..651ab9e 100644
> > --- a/tools/perf/arch/x86/util/intel-pt.c
> > +++ b/tools/perf/arch/x86/util/intel-pt.c
> > @@ -544,6 +544,22 @@ static int intel_pt_validate_config(struct perf_pmu
> *intel_pt_pmu,
> > evsel->attr.config);
> > }
> >
> > +static int add_no_lbr_config_term(struct list_head *config_terms) {
> > + struct perf_evsel_config_term *lbr_term;
> > +
> > + lbr_term = zalloc(sizeof(*lbr_term));
> > + if (!lbr_term)
> > + return -ENOMEM;
> > +
> > + INIT_LIST_HEAD(&lbr_term->list);
> > + lbr_term->type = PERF_EVSEL__CONFIG_TERM_BRANCH;
> > + lbr_term->val.branch = strdup("no");
> > + list_add_tail(&lbr_term->list, config_terms);
> > +
> > + return 0;
> > +}
> > +
> > static int intel_pt_recording_options(struct auxtrace_record *itr,
> > struct perf_evlist *evlist,
> > struct record_opts *opts)
> > @@ -701,6 +717,8 @@ static int intel_pt_recording_options(struct
> auxtrace_record *itr,
> > perf_evsel__set_sample_bit(switch_evsel,
> TIME);
> > perf_evsel__set_sample_bit(switch_evsel,
> CPU);
> >
> > + add_no_lbr_config_term(&switch_evsel-
> >config_terms);
> > +
>
> hum, why can't you change the sample bit directly? with:
>
> perf_evsel__reset_sample_bit(switch_evsel,
> BRANCH_STACK);
It will be overwrite in perf_evsel__config.
Thanks,
Kan
On Thu, Jun 29, 2017 at 03:31:45PM +0000, Liang, Kan wrote:
SNIP
> > > static int intel_pt_recording_options(struct auxtrace_record *itr,
> > > struct perf_evlist *evlist,
> > > struct record_opts *opts)
> > > @@ -701,6 +717,8 @@ static int intel_pt_recording_options(struct
> > auxtrace_record *itr,
> > > perf_evsel__set_sample_bit(switch_evsel,
> > TIME);
> > > perf_evsel__set_sample_bit(switch_evsel,
> > CPU);
> > >
> > > + add_no_lbr_config_term(&switch_evsel-
> > >config_terms);
> > > +
> >
> > hum, why can't you change the sample bit directly? with:
> >
> > perf_evsel__reset_sample_bit(switch_evsel,
> > BRANCH_STACK);
>
> It will be overwrite in perf_evsel__config.
>
where? you set the evsel->no_aux_samples
jirka
>
> On Thu, Jun 29, 2017 at 03:31:45PM +0000, Liang, Kan wrote:
>
> SNIP
>
> > > > static int intel_pt_recording_options(struct auxtrace_record *itr,
> > > > struct perf_evlist *evlist,
> > > > struct record_opts *opts) @@ -701,6
> +717,8 @@ static
> > > > int intel_pt_recording_options(struct
> > > auxtrace_record *itr,
> > > > perf_evsel__set_sample_bit(switch_evsel,
> > > TIME);
> > > > perf_evsel__set_sample_bit(switch_evsel,
> > > CPU);
> > > >
> > > > + add_no_lbr_config_term(&switch_evsel-
> > > >config_terms);
> > > > +
> > >
> > > hum, why can't you change the sample bit directly? with:
> > >
> > > perf_evsel__reset_sample_bit(switch_evsel,
> > > BRANCH_STACK);
> >
> > It will be overwrite in perf_evsel__config.
> >
>
> where? you set the evsel->no_aux_samples
Yes for switch_evsel, but no for tracking_evsel.
If it's only for switch_evsel, yes, we can change the sample bit directly.
But I think we should use the same method for both of them.
Thanks,
Kan
On Thu, Jun 29, 2017 at 03:50:29PM +0000, Liang, Kan wrote:
>
>
> >
> > On Thu, Jun 29, 2017 at 03:31:45PM +0000, Liang, Kan wrote:
> >
> > SNIP
> >
> > > > > static int intel_pt_recording_options(struct auxtrace_record *itr,
> > > > > struct perf_evlist *evlist,
> > > > > struct record_opts *opts) @@ -701,6
> > +717,8 @@ static
> > > > > int intel_pt_recording_options(struct
> > > > auxtrace_record *itr,
> > > > > perf_evsel__set_sample_bit(switch_evsel,
> > > > TIME);
> > > > > perf_evsel__set_sample_bit(switch_evsel,
> > > > CPU);
> > > > >
> > > > > + add_no_lbr_config_term(&switch_evsel-
> > > > >config_terms);
> > > > > +
> > > >
> > > > hum, why can't you change the sample bit directly? with:
> > > >
> > > > perf_evsel__reset_sample_bit(switch_evsel,
> > > > BRANCH_STACK);
> > >
> > > It will be overwrite in perf_evsel__config.
> > >
> >
> > where? you set the evsel->no_aux_samples
>
> Yes for switch_evsel, but no for tracking_evsel.
>
> If it's only for switch_evsel, yes, we can change the sample bit directly.
> But I think we should use the same method for both of them.
we could set the no_aux_samples for the tracking_evsel as well
jirka
> On Thu, Jun 29, 2017 at 03:50:29PM +0000, Liang, Kan wrote:
> >
> >
> > >
> > > On Thu, Jun 29, 2017 at 03:31:45PM +0000, Liang, Kan wrote:
> > >
> > > SNIP
> > >
> > > > > > static int intel_pt_recording_options(struct auxtrace_record *itr,
> > > > > > struct perf_evlist *evlist,
> > > > > > struct record_opts *opts) @@ -
> 701,6
> > > +717,8 @@ static
> > > > > > int intel_pt_recording_options(struct
> > > > > auxtrace_record *itr,
> > > > > >
> perf_evsel__set_sample_bit(switch_evsel,
> > > > > TIME);
> > > > > >
> perf_evsel__set_sample_bit(switch_evsel,
> > > > > CPU);
> > > > > >
> > > > > > +
> add_no_lbr_config_term(&switch_evsel-
> > > > > >config_terms);
> > > > > > +
> > > > >
> > > > > hum, why can't you change the sample bit directly? with:
> > > > >
> > > > > perf_evsel__reset_sample_bit(switch_evsel,
> > > > > BRANCH_STACK);
> > > >
> > > > It will be overwrite in perf_evsel__config.
> > > >
> > >
> > > where? you set the evsel->no_aux_samples
> >
> > Yes for switch_evsel, but no for tracking_evsel.
> >
> > If it's only for switch_evsel, yes, we can change the sample bit directly.
> > But I think we should use the same method for both of them.
>
>
> we could set the no_aux_samples for the tracking_evsel as well
>
Yes, I will do it in next version.
Thanks,
Kan