[v2,03/20] perf/core: add PERF_PMU_CAP_EXCLUDE for exclusion capable PMUs
diff mbox series

Message ID 1543230756-15319-4-git-send-email-andrew.murray@arm.com
State Not Applicable
Headers show
Series
  • perf/core: Generalise event exclusion checking
Related show

Checks

Context Check Description
snowpatch_ozlabs/checkpatch warning total: 0 errors, 0 warnings, 1 checks, 22 lines checked
snowpatch_ozlabs/apply_patch success next/apply_patch Successfully applied

Commit Message

Andrew Murray Nov. 26, 2018, 11:12 a.m. UTC
Many PMU drivers do not have the capability to exclude counting events
that occur in specific contexts such as idle, kernel, guest, etc. These
drivers indicate this by returning an error in their event_init upon
testing the events attribute flags. This approach is error prone and
often inconsistent.

Let's instead allow PMU drivers to advertise their ability to exclude
based on context via a new capability: PERF_PMU_CAP_EXCLUDE. This
allows the perf core to reject requests for exclusion events where
there is no support in the PMU.

Signed-off-by: Andrew Murray <andrew.murray@arm.com>
---
 include/linux/perf_event.h | 1 +
 kernel/events/core.c       | 9 +++++++++
 2 files changed, 10 insertions(+)

Comments

Robin Murphy Nov. 26, 2018, 2:10 p.m. UTC | #1
Hi Andrew,

On 26/11/2018 11:12, Andrew Murray wrote:
> Many PMU drivers do not have the capability to exclude counting events
> that occur in specific contexts such as idle, kernel, guest, etc. These
> drivers indicate this by returning an error in their event_init upon
> testing the events attribute flags. This approach is error prone and
> often inconsistent.
> 
> Let's instead allow PMU drivers to advertise their ability to exclude
> based on context via a new capability: PERF_PMU_CAP_EXCLUDE. This
> allows the perf core to reject requests for exclusion events where
> there is no support in the PMU.
> 
> Signed-off-by: Andrew Murray <andrew.murray@arm.com>
> ---
>   include/linux/perf_event.h | 1 +
>   kernel/events/core.c       | 9 +++++++++
>   2 files changed, 10 insertions(+)
> 
> diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
> index b2e806f..69b3d65 100644
> --- a/include/linux/perf_event.h
> +++ b/include/linux/perf_event.h
> @@ -244,6 +244,7 @@ struct perf_event;
>   #define PERF_PMU_CAP_EXCLUSIVE			0x10
>   #define PERF_PMU_CAP_ITRACE			0x20
>   #define PERF_PMU_CAP_HETEROGENEOUS_CPUS		0x40
> +#define PERF_PMU_CAP_EXCLUDE			0x80
>   
>   /**
>    * struct pmu - generic performance monitoring unit
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index 5a97f34..9afb33c 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -9743,6 +9743,15 @@ static int perf_try_init_event(struct pmu *pmu, struct perf_event *event)
>   	if (ctx)
>   		perf_event_ctx_unlock(event->group_leader, ctx);
>   
> +	if (!ret) {
> +		if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUDE) &&
> +				event_has_any_exclude_flag(event)) {

Technically this is a bisection-breaker, since no driver has this 
capability yet - ideally, this patch should come after all the ones 
introducing it to the relevant drivers (with the removal of the 
now-redundant code from the other drivers at the end).

Alternatively, since we already have several other negative 
capabilities, unless there's a strong feeling against adding any more 
then it might work out simpler to flip it to PERF_PMU_CAP_NO_EXCLUDE, 
such that we only need to introduce the core check then directly replace 
the open-coded event checks with the capability in the appropriate 
drivers, and need not touch the exclusion-supporting ones at all.

Robin.

> +			if (event->destroy)
> +				event->destroy(event);
> +			ret = -EINVAL;
> +		}
> +	}
> +
>   	if (ret)
>   		module_put(pmu->module);
>   
>
Andrew Murray Nov. 26, 2018, 2:55 p.m. UTC | #2
On Mon, Nov 26, 2018 at 02:10:24PM +0000, Robin Murphy wrote:
> Hi Andrew,
> 
> On 26/11/2018 11:12, Andrew Murray wrote:
> > Many PMU drivers do not have the capability to exclude counting events
> > that occur in specific contexts such as idle, kernel, guest, etc. These
> > drivers indicate this by returning an error in their event_init upon
> > testing the events attribute flags. This approach is error prone and
> > often inconsistent.
> > 
> > Let's instead allow PMU drivers to advertise their ability to exclude
> > based on context via a new capability: PERF_PMU_CAP_EXCLUDE. This
> > allows the perf core to reject requests for exclusion events where
> > there is no support in the PMU.
> > 
> > Signed-off-by: Andrew Murray <andrew.murray@arm.com>
> > ---
> >   include/linux/perf_event.h | 1 +
> >   kernel/events/core.c       | 9 +++++++++
> >   2 files changed, 10 insertions(+)
> > 
> > diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
> > index b2e806f..69b3d65 100644
> > --- a/include/linux/perf_event.h
> > +++ b/include/linux/perf_event.h
> > @@ -244,6 +244,7 @@ struct perf_event;
> >   #define PERF_PMU_CAP_EXCLUSIVE			0x10
> >   #define PERF_PMU_CAP_ITRACE			0x20
> >   #define PERF_PMU_CAP_HETEROGENEOUS_CPUS		0x40
> > +#define PERF_PMU_CAP_EXCLUDE			0x80
> >   /**
> >    * struct pmu - generic performance monitoring unit
> > diff --git a/kernel/events/core.c b/kernel/events/core.c
> > index 5a97f34..9afb33c 100644
> > --- a/kernel/events/core.c
> > +++ b/kernel/events/core.c
> > @@ -9743,6 +9743,15 @@ static int perf_try_init_event(struct pmu *pmu, struct perf_event *event)
> >   	if (ctx)
> >   		perf_event_ctx_unlock(event->group_leader, ctx);
> > +	if (!ret) {
> > +		if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUDE) &&
> > +				event_has_any_exclude_flag(event)) {
> 
> Technically this is a bisection-breaker, since no driver has this capability
> yet - ideally, this patch should come after all the ones introducing it to
> the relevant drivers (with the removal of the now-redundant code from the
> other drivers at the end).

Indeed. Thought it is possible to first introduce the capability, update the
relevant drivers to advertise it, then add the change to core.c and finally
remove the unnecessary error checks as a result of using the new capability.
This approach could be bisection-proof.

> 
> Alternatively, since we already have several other negative capabilities,
> unless there's a strong feeling against adding any more then it might work
> out simpler to flip it to PERF_PMU_CAP_NO_EXCLUDE, such that we only need to
> introduce the core check then directly replace the open-coded event checks
> with the capability in the appropriate drivers, and need not touch the
> exclusion-supporting ones at all.

This would certaintly be less risky and invasive (e.g. compare the number of
files touched between this v2 and the previous v1).

I'm happy with either approach.

Thanks,

Andrew Murray

> 
> Robin.
> 
> > +			if (event->destroy)
> > +				event->destroy(event);
> > +			ret = -EINVAL;
> > +		}
> > +	}
> > +
> >   	if (ret)
> >   		module_put(pmu->module);
> >

Patch
diff mbox series

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index b2e806f..69b3d65 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -244,6 +244,7 @@  struct perf_event;
 #define PERF_PMU_CAP_EXCLUSIVE			0x10
 #define PERF_PMU_CAP_ITRACE			0x20
 #define PERF_PMU_CAP_HETEROGENEOUS_CPUS		0x40
+#define PERF_PMU_CAP_EXCLUDE			0x80
 
 /**
  * struct pmu - generic performance monitoring unit
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 5a97f34..9afb33c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -9743,6 +9743,15 @@  static int perf_try_init_event(struct pmu *pmu, struct perf_event *event)
 	if (ctx)
 		perf_event_ctx_unlock(event->group_leader, ctx);
 
+	if (!ret) {
+		if (!(pmu->capabilities & PERF_PMU_CAP_EXCLUDE) &&
+				event_has_any_exclude_flag(event)) {
+			if (event->destroy)
+				event->destroy(event);
+			ret = -EINVAL;
+		}
+	}
+
 	if (ret)
 		module_put(pmu->module);