From: Peter Zijlstra <peterz@infradead.org>
To: Andrew Murray <andrew.murray@arm.com>
Cc: Ingo Molnar <mingo@redhat.com>,
Arnaldo Carvalho de Melo <acme@kernel.org>,
Shawn Guo <shawnguo@kernel.org>,
Sascha Hauer <s.hauer@pengutronix.de>,
Will Deacon <will.deacon@arm.com>,
Mark Rutland <mark.rutland@arm.com>,
Benjamin Herrenschmidt <benh@kernel.crashing.org>,
Thomas Gleixner <tglx@linutronix.de>,
Borislav Petkov <bp@alien8.de>,
x86@kernel.org, linux-alpha@vger.kernel.org,
linuxppc-dev@lists.ozlabs.org,
linux-arm-kernel@lists.infradead.org,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH 00/10] perf/core: Generalise event exclusion checking
Date: Mon, 19 Nov 2018 14:08:00 +0100 [thread overview]
Message-ID: <20181119130800.GE9761@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <1542363853-13849-1-git-send-email-andrew.murray@arm.com>
On Fri, Nov 16, 2018 at 10:24:03AM +0000, 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.
>
> However this approach requires that each time a new event modifier is
> added to perf, all the perf drivers need to be modified to indicate that
> they don't support the attribute. This results in additional boiler-plate
> code common to many drivers that needs to be maintained. An example of
> this is the addition of exclude_host and exclude_guest in 2011 yet many
> PMU drivers do not support this or indicate an error on events that make
> use of it.
>
> This patch generalises the test for exclusion and updates PMU drivers to
> use it. This is a functional change as some PMU drivers will now correctly
> report that they don't support certain events whereas they previously did.
Right, I like that idea, and yes, there's a lot of fail around there :/
> A longer term approach may instead be for PMU's to advertise their
> capabilities on registration.
This I think is the better approach. We already have the
PERF_PMU_CAP_flags that can be used to advertise various PMU
capabilities.
Something along these lines I suppose; then every PMU that actually
checks the flags, needs to set the flag, otherwise it'll fail.
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 53c500f0ca79..de15723ea52a 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 84530ab358c3..d76b724177b9 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -9772,6 +9772,14 @@ 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_exclude_flags(event)) {
+ event->destroy(event);
+ ret = -EINVAL;
+ }
+ }
+
if (ret)
module_put(pmu->module);
WARNING: multiple messages have this Message-ID (diff)
From: Peter Zijlstra <peterz@infradead.org>
To: Andrew Murray <andrew.murray@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>,
Sascha Hauer <s.hauer@pengutronix.de>,
x86@kernel.org, Will Deacon <will.deacon@arm.com>,
linuxppc-dev@lists.ozlabs.org,
Arnaldo Carvalho de Melo <acme@kernel.org>,
linux-kernel@vger.kernel.org, Ingo Molnar <mingo@redhat.com>,
Borislav Petkov <bp@alien8.de>,
linux-alpha@vger.kernel.org, Thomas Gleixner <tglx@linutronix.de>,
Shawn Guo <shawnguo@kernel.org>,
linux-arm-kernel@lists.infradead.org
Subject: Re: [PATCH 00/10] perf/core: Generalise event exclusion checking
Date: Mon, 19 Nov 2018 14:08:00 +0100 [thread overview]
Message-ID: <20181119130800.GE9761@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <1542363853-13849-1-git-send-email-andrew.murray@arm.com>
On Fri, Nov 16, 2018 at 10:24:03AM +0000, 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.
>
> However this approach requires that each time a new event modifier is
> added to perf, all the perf drivers need to be modified to indicate that
> they don't support the attribute. This results in additional boiler-plate
> code common to many drivers that needs to be maintained. An example of
> this is the addition of exclude_host and exclude_guest in 2011 yet many
> PMU drivers do not support this or indicate an error on events that make
> use of it.
>
> This patch generalises the test for exclusion and updates PMU drivers to
> use it. This is a functional change as some PMU drivers will now correctly
> report that they don't support certain events whereas they previously did.
Right, I like that idea, and yes, there's a lot of fail around there :/
> A longer term approach may instead be for PMU's to advertise their
> capabilities on registration.
This I think is the better approach. We already have the
PERF_PMU_CAP_flags that can be used to advertise various PMU
capabilities.
Something along these lines I suppose; then every PMU that actually
checks the flags, needs to set the flag, otherwise it'll fail.
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 53c500f0ca79..de15723ea52a 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 84530ab358c3..d76b724177b9 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -9772,6 +9772,14 @@ 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_exclude_flags(event)) {
+ event->destroy(event);
+ ret = -EINVAL;
+ }
+ }
+
if (ret)
module_put(pmu->module);
WARNING: multiple messages have this Message-ID (diff)
From: peterz@infradead.org (Peter Zijlstra)
To: linux-arm-kernel@lists.infradead.org
Subject: [PATCH 00/10] perf/core: Generalise event exclusion checking
Date: Mon, 19 Nov 2018 14:08:00 +0100 [thread overview]
Message-ID: <20181119130800.GE9761@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <1542363853-13849-1-git-send-email-andrew.murray@arm.com>
On Fri, Nov 16, 2018 at 10:24:03AM +0000, 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.
>
> However this approach requires that each time a new event modifier is
> added to perf, all the perf drivers need to be modified to indicate that
> they don't support the attribute. This results in additional boiler-plate
> code common to many drivers that needs to be maintained. An example of
> this is the addition of exclude_host and exclude_guest in 2011 yet many
> PMU drivers do not support this or indicate an error on events that make
> use of it.
>
> This patch generalises the test for exclusion and updates PMU drivers to
> use it. This is a functional change as some PMU drivers will now correctly
> report that they don't support certain events whereas they previously did.
Right, I like that idea, and yes, there's a lot of fail around there :/
> A longer term approach may instead be for PMU's to advertise their
> capabilities on registration.
This I think is the better approach. We already have the
PERF_PMU_CAP_flags that can be used to advertise various PMU
capabilities.
Something along these lines I suppose; then every PMU that actually
checks the flags, needs to set the flag, otherwise it'll fail.
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 53c500f0ca79..de15723ea52a 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 84530ab358c3..d76b724177b9 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -9772,6 +9772,14 @@ 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_exclude_flags(event)) {
+ event->destroy(event);
+ ret = -EINVAL;
+ }
+ }
+
if (ret)
module_put(pmu->module);
WARNING: multiple messages have this Message-ID (diff)
From: Peter Zijlstra <peterz@infradead.org>
To: Andrew Murray <andrew.murray@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>,
Benjamin Herrenschmidt <benh@kernel.crashing.org>,
Sascha Hauer <s.hauer@pengutronix.de>,
x86@kernel.org, Will Deacon <will.deacon@arm.com>,
linuxppc-dev@lists.ozlabs.org,
Arnaldo Carvalho de Melo <acme@kernel.org>,
linux-kernel@vger.kernel.org, Ingo Molnar <mingo@redhat.com>,
Borislav Petkov <bp@alien8.de>,
linux-alpha@vger.kernel.org, Thomas Gleixner <tglx@linutronix.de>,
Shawn Guo <shawnguo@kernel.org>,
linux-arm-kernel@lists.infradead.org
Subject: Re: [PATCH 00/10] perf/core: Generalise event exclusion checking
Date: Mon, 19 Nov 2018 14:08:00 +0100 [thread overview]
Message-ID: <20181119130800.GE9761@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <1542363853-13849-1-git-send-email-andrew.murray@arm.com>
On Fri, Nov 16, 2018 at 10:24:03AM +0000, 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.
>
> However this approach requires that each time a new event modifier is
> added to perf, all the perf drivers need to be modified to indicate that
> they don't support the attribute. This results in additional boiler-plate
> code common to many drivers that needs to be maintained. An example of
> this is the addition of exclude_host and exclude_guest in 2011 yet many
> PMU drivers do not support this or indicate an error on events that make
> use of it.
>
> This patch generalises the test for exclusion and updates PMU drivers to
> use it. This is a functional change as some PMU drivers will now correctly
> report that they don't support certain events whereas they previously did.
Right, I like that idea, and yes, there's a lot of fail around there :/
> A longer term approach may instead be for PMU's to advertise their
> capabilities on registration.
This I think is the better approach. We already have the
PERF_PMU_CAP_flags that can be used to advertise various PMU
capabilities.
Something along these lines I suppose; then every PMU that actually
checks the flags, needs to set the flag, otherwise it'll fail.
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 53c500f0ca79..de15723ea52a 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 84530ab358c3..d76b724177b9 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -9772,6 +9772,14 @@ 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_exclude_flags(event)) {
+ event->destroy(event);
+ ret = -EINVAL;
+ }
+ }
+
if (ret)
module_put(pmu->module);
next prev parent reply other threads:[~2018-11-19 13:08 UTC|newest]
Thread overview: 92+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-11-16 10:24 [PATCH 00/10] perf/core: Generalise event exclusion checking Andrew Murray
2018-11-16 10:24 ` Andrew Murray
2018-11-16 10:24 ` Andrew Murray
2018-11-16 10:24 ` [PATCH 01/10] perf/core: Add macro to test for event exclusion flags Andrew Murray
2018-11-16 10:24 ` Andrew Murray
2018-11-16 10:24 ` Andrew Murray
2018-11-19 12:58 ` Peter Zijlstra
2018-11-19 12:58 ` Peter Zijlstra
2018-11-19 12:58 ` Peter Zijlstra
2018-11-19 12:58 ` Peter Zijlstra
2018-11-19 16:01 ` Mark Rutland
2018-11-19 16:01 ` Mark Rutland
2018-11-19 16:01 ` Mark Rutland
2018-11-20 11:28 ` Michael Ellerman
2018-11-20 11:28 ` Michael Ellerman
2018-11-20 11:28 ` Michael Ellerman
2018-11-23 14:32 ` Andrew Murray
2018-11-23 14:32 ` Andrew Murray
2018-11-23 14:32 ` Andrew Murray
2018-11-16 10:24 ` [PATCH 02/10] arm: perf/core: generalise event exclusion checking with perf macro Andrew Murray
2018-11-16 10:24 ` Andrew Murray
2018-11-16 10:24 ` Andrew Murray
2018-11-16 10:24 ` [PATCH 03/10] arm: perf: add additional validation to set_event_filter Andrew Murray
2018-11-16 10:24 ` Andrew Murray
2018-11-16 10:24 ` Andrew Murray
2018-11-16 10:24 ` [PATCH 04/10] powerpc: perf/core: generalise event exclusion checking with perf macro Andrew Murray
2018-11-16 10:24 ` Andrew Murray
2018-11-16 10:24 ` Andrew Murray
2018-11-20 11:21 ` Michael Ellerman
2018-11-20 11:21 ` Michael Ellerman
2018-11-20 11:21 ` Michael Ellerman
2018-11-16 10:24 ` [PATCH 05/10] powerpc/pmu/fsl: add additional validation to event_init Andrew Murray
2018-11-16 10:24 ` Andrew Murray
2018-11-16 10:24 ` Andrew Murray
2018-11-16 10:24 ` [PATCH 06/10] alpha: perf/core: generalise event exclusion checking with perf macro Andrew Murray
2018-11-16 10:24 ` Andrew Murray
2018-11-16 10:24 ` Andrew Murray
2018-11-16 10:24 ` [PATCH 07/10] x86: " Andrew Murray
2018-11-16 10:24 ` Andrew Murray
2018-11-16 10:24 ` Andrew Murray
2018-11-16 10:24 ` [PATCH 08/10] perf/core: Remove unused perf_flags Andrew Murray
2018-11-16 10:24 ` Andrew Murray
2018-11-16 10:24 ` Andrew Murray
2018-11-16 10:24 ` [PATCH 09/10] drivers/perf: perf/core: generalise event exclusion checking with perf macro Andrew Murray
2018-11-16 10:24 ` Andrew Murray
2018-11-16 10:24 ` Andrew Murray
2018-11-19 16:03 ` Mark Rutland
2018-11-19 16:03 ` Mark Rutland
2018-11-19 16:03 ` Mark Rutland
2018-11-23 14:31 ` Andrew Murray
2018-11-23 14:31 ` Andrew Murray
2018-11-23 14:31 ` Andrew Murray
2018-11-16 10:24 ` [PATCH 10/10] perf/doc: update design.txt for exclude_{host|guest} flags Andrew Murray
2018-11-16 10:24 ` Andrew Murray
2018-11-16 10:24 ` Andrew Murray
2018-11-20 11:31 ` Michael Ellerman
2018-11-20 11:31 ` Michael Ellerman
2018-11-20 11:31 ` Michael Ellerman
2018-11-20 13:32 ` Andrew Murray
2018-11-20 13:32 ` Andrew Murray
2018-11-20 13:32 ` Andrew Murray
2018-12-11 11:06 ` Michael Ellerman
2018-12-11 11:06 ` Michael Ellerman
2018-12-11 11:06 ` Michael Ellerman
2018-12-11 11:06 ` Michael Ellerman
2018-12-11 13:59 ` Andrew Murray
2018-12-11 13:59 ` Andrew Murray
2018-12-11 13:59 ` Andrew Murray
2018-12-12 4:48 ` Michael Ellerman
2018-12-12 4:48 ` Michael Ellerman
2018-12-12 4:48 ` Michael Ellerman
2018-12-12 4:48 ` Michael Ellerman
2018-12-12 8:07 ` Christoffer Dall
2018-12-12 8:07 ` Christoffer Dall
2018-12-12 8:07 ` Christoffer Dall
2018-12-12 17:08 ` Andrew Murray
2018-12-12 17:08 ` Andrew Murray
2018-12-12 17:08 ` Andrew Murray
2018-11-19 13:08 ` Peter Zijlstra [this message]
2018-11-19 13:08 ` [PATCH 00/10] perf/core: Generalise event exclusion checking Peter Zijlstra
2018-11-19 13:08 ` Peter Zijlstra
2018-11-19 13:08 ` Peter Zijlstra
2018-11-22 12:21 ` Andrew Murray
2018-11-22 12:21 ` Andrew Murray
2018-11-22 12:21 ` Andrew Murray
2018-11-22 12:26 ` Peter Zijlstra
2018-11-22 12:26 ` Peter Zijlstra
2018-11-22 12:26 ` Peter Zijlstra
2018-11-22 12:26 ` Peter Zijlstra
2018-11-22 12:59 ` Andrew Murray
2018-11-22 12:59 ` Andrew Murray
2018-11-22 12:59 ` Andrew Murray
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20181119130800.GE9761@hirez.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=acme@kernel.org \
--cc=andrew.murray@arm.com \
--cc=benh@kernel.crashing.org \
--cc=bp@alien8.de \
--cc=linux-alpha@vger.kernel.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=mark.rutland@arm.com \
--cc=mingo@redhat.com \
--cc=s.hauer@pengutronix.de \
--cc=shawnguo@kernel.org \
--cc=tglx@linutronix.de \
--cc=will.deacon@arm.com \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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.