From: Peter Zijlstra <a.p.zijlstra@chello.nl>
To: Paul Mackerras <paulus@samba.org>
Cc: mingo@elte.hu, rostedt@goodmis.org, linux-kernel@vger.kernel.org
Subject: Re: [RFC][PATCH 09/11] perf_counter: revamp syscall input ABI
Date: Thu, 19 Mar 2009 12:41:07 +0100 [thread overview]
Message-ID: <1237462867.7867.43.camel@twins> (raw)
In-Reply-To: <18881.29300.669876.820286@cargo.ozlabs.ibm.com>
On Thu, 2009-03-19 at 09:15 +1100, Paul Mackerras wrote:
> Peter Zijlstra writes:
>
> > Ah, I thought we should keep a pure 64 bit raw value. You never know
> > what hardware will do.
>
> Oh I see, you use hw_event->raw_event if hw_event->raw is set. I
> missed that before.
>
> Still, you're putting that into hwc->config along with other bits like
> ARCH_PERFMON_EVENTSEL_USR and ARCH_PERFMON_EVENTSEL_OS, so I would
> think we could spare two bits for the type, leaving 62 bits for the
> raw event code. And if that isn't enough, there's the
> hw_event.extra_config_len field, which allows userspace to pass in
> arbitrary amounts of extra PMU configuration data.
Good point, overflow interrupt, and usr/os/hv event filter and enable
bits are usually in the config word.
OK, how about the below? I didn't cut it to 2 bits, as that would
already exhaust the TYPE space -- then again, 60 does feel cramped a
bit..
Index: linux-2.6/include/linux/perf_counter.h
===================================================================
--- linux-2.6.orig/include/linux/perf_counter.h
+++ linux-2.6/include/linux/perf_counter.h
@@ -27,6 +27,12 @@ enum perf_event_types {
PERF_TYPE_HARDWARE = 0,
PERF_TYPE_SOFTWARE = 1,
PERF_TYPE_TRACEPOINT = 2,
+
+ /*
+ * available TYPE space, raw is the max value.
+ */
+
+ PERF_TYPE_RAW = 15,
};
/*
@@ -79,14 +85,8 @@ enum perf_counter_record_type {
* Hardware event to monitor via a performance monitoring counter:
*/
struct perf_counter_hw_event {
- union {
- __u64 raw_event;
- struct {
- __u64 event_id : 32,
- type : 8,
- __reserved_0 : 24;
- };
- };
+ __u64 event_id : 60,
+ type : 4;
__u64 irq_period;
__u64 record_type;
@@ -94,7 +94,6 @@ struct perf_counter_hw_event {
__u64 disabled : 1, /* off by default */
nmi : 1, /* NMI sampling */
- raw : 1, /* raw event type */
inherit : 1, /* children inherit it */
pinned : 1, /* must always be on PMU */
exclusive : 1, /* only group on PMU */
@@ -103,7 +102,7 @@ struct perf_counter_hw_event {
exclude_hv : 1, /* ditto hypervisor */
exclude_idle : 1, /* don't count when idle */
- __reserved_1 : 54;
+ __reserved_1 : 55;
__u32 extra_config_len;
__u32 __reserved_4;
next prev parent reply other threads:[~2009-03-19 11:41 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-03-17 21:56 [RFC][PATCH 00/11] tracepoint perf counter events and other stuff Peter Zijlstra
2009-03-17 21:56 ` [RFC][PATCH 01/11] perf_counter: fix uninitialized usage of event_list Peter Zijlstra
2009-03-17 21:56 ` [RFC][PATCH 02/11] perf_counter: generic context switch event Peter Zijlstra
2009-03-17 21:56 ` [RFC][PATCH 03/11] ftrace: fix memory leak Peter Zijlstra
2009-03-17 22:49 ` Steven Rostedt
2009-03-17 21:56 ` [RFC][PATCH 04/11] ftrace: provide an id file for each event Peter Zijlstra
2009-03-17 22:52 ` Steven Rostedt
2009-03-17 21:56 ` [RFC][PATCH 05/11] ftrace: ensure every event gets an id Peter Zijlstra
2009-03-17 22:54 ` Steven Rostedt
2009-03-17 21:56 ` [RFC][PATCH 06/11] ftrace: event profile hooks Peter Zijlstra
2009-03-17 21:56 ` [RFC][PATCH 07/11] perf_counter: fix up counter free paths Peter Zijlstra
2009-03-17 21:56 ` [RFC][PATCH 08/11] perf_counter: hook up the tracepoint events Peter Zijlstra
2009-03-17 21:56 ` [RFC][PATCH 09/11] perf_counter: revamp syscall input ABI Peter Zijlstra
2009-03-18 2:29 ` Paul Mackerras
2009-03-18 8:47 ` Peter Zijlstra
2009-03-18 22:15 ` Paul Mackerras
2009-03-19 11:41 ` Peter Zijlstra [this message]
2009-03-19 11:45 ` Peter Zijlstra
2009-03-18 4:31 ` Paul Mackerras
2009-03-18 8:55 ` Peter Zijlstra
2009-03-17 21:56 ` [RFC][PATCH 10/11] perfcounters: abstract wakeup flag setting in core to fix powerpc build Peter Zijlstra
2009-03-17 21:56 ` [RFC][PATCH 11/11] perf_counter: unify irq output code Peter Zijlstra
2009-03-18 2:37 ` Paul Mackerras
2009-03-18 5:28 ` Paul Mackerras
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=1237462867.7867.43.camel@twins \
--to=a.p.zijlstra@chello.nl \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=paulus@samba.org \
--cc=rostedt@goodmis.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox