lkml.org 
[lkml]   [2011]   [Jul]   [8]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
SubjectRe: [tip:perf/core] perf: Remove the nmi parameter from the swevent and overflow interface
Hi Peter,

On Fri, Jul 01, 2011 at 04:21:25PM +0100, tip-bot for Peter Zijlstra wrote:
> Commit-ID: a8b0ca17b80e92faab46ee7179ba9e99ccb61233
> Gitweb: http://git.kernel.org/tip/a8b0ca17b80e92faab46ee7179ba9e99ccb61233
> Author: Peter Zijlstra <a.p.zijlstra@chello.nl>
> AuthorDate: Mon, 27 Jun 2011 14:41:57 +0200
> Committer: Ingo Molnar <mingo@elte.hu>
> CommitDate: Fri, 1 Jul 2011 11:06:35 +0200
>
> perf: Remove the nmi parameter from the swevent and overflow interface
>
> The nmi parameter indicated if we could do wakeups from the current
> context, if not, we would set some state and self-IPI and let the
> resulting interrupt do the wakeup.
>
> For the various event classes:
>
> - hardware: nmi=0; PMI is in fact an NMI or we run irq_work_run from
> the PMI-tail (ARM etc.)
> - tracepoint: nmi=0; since tracepoint could be from NMI context.
> - software: nmi=[0,1]; some, like the schedule thing cannot
> perform wakeups, and hence need 0.
>
> As one can see, there is very little nmi=1 usage, and the down-side of
> not using it is that on some platforms some software events can have a
> jiffy delay in wakeup (when arch_irq_work_raise isn't implemented).
>
> The up-side however is that we can remove the nmi parameter and save a
> bunch of conditionals in fast paths.
>
> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>

Whilst you updated the arch code in this series, you forgot to update the
oprofile perf backend. I think you want something as simple as:


diff --git a/drivers/oprofile/oprofile_perf.c b/drivers/oprofile/oprofile_perf.c
index 59acf9e..94796f3 100644
--- a/drivers/oprofile/oprofile_perf.c
+++ b/drivers/oprofile/oprofile_perf.c
@@ -31,7 +31,7 @@ static int num_counters;
/*
* Overflow callback for oprofile.
*/
-static void op_overflow_handler(struct perf_event *event, int unused,
+static void op_overflow_handler(struct perf_event *event,
struct perf_sample_data *data, struct pt_regs *regs)
{
int id;

although I haven't tried it.

Cheers,

Will


\
 
 \ /
  Last update: 2011-07-08 19:37    [W:0.075 / U:0.632 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site