linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Frederic Weisbecker <fweisbec@gmail.com>
To: Ingo Molnar <mingo@elte.hu>
Cc: LKML <linux-kernel@vger.kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Arnaldo Carvalho de Melo <acme@redhat.com>,
	Steven Rostedt <rostedt@goodmis.org>,
	Paul Mackerras <paulus@samba.org>,
	Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>,
	Li Zefan <lizf@cn.fujitsu.com>,
	Lai Jiangshan <laijs@cn.fujitsu.com>,
	Masami Hiramatsu <mhiramat@redhat.com>,
	Jens Axboe <jens.axboe@oracle.com>
Subject: Re: [PATCH 05/11] perf: New PERF_EVENT_IOC_INJECT ioctl
Date: Wed, 3 Feb 2010 10:19:58 +0100	[thread overview]
Message-ID: <20100203091955.GA18638@nowhere> (raw)
In-Reply-To: <1265188475-23509-6-git-send-regression-fweisbec@gmail.com>

On Wed, Feb 03, 2010 at 10:14:29AM +0100, Frederic Weisbecker wrote:
> The PERF_EVENT_IOC_INJECT perf event ioctl can be used to inject
> events, if the corresponding pmu and event supports it.
> 
> On trace events, it will call the inject callback, usually reserved
> for events that need to catch up with the user.
> 
> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
> Cc: Peter Zijlstra <peterz@infradead.org>
> Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
> Cc: Steven Rostedt <rostedt@goodmis.org>
> Cc: Paul Mackerras <paulus@samba.org>
> Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
> Cc: Li Zefan <lizf@cn.fujitsu.com>
> Cc: Lai Jiangshan <laijs@cn.fujitsu.com>
> Cc: Masami Hiramatsu <mhiramat@redhat.com>
> Cc: Jens Axboe <jens.axboe@oracle.com>
> ---
>  include/linux/perf_event.h |    2 ++
>  kernel/perf_event.c        |   23 +++++++++++++++++++++++
>  2 files changed, 25 insertions(+), 0 deletions(-)
> 
> diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
> index 556b0f4..d2e83f0 100644
> --- a/include/linux/perf_event.h
> +++ b/include/linux/perf_event.h
> @@ -228,6 +228,7 @@ struct perf_event_attr {
>  #define PERF_EVENT_IOC_PERIOD		_IOW('$', 4, __u64)
>  #define PERF_EVENT_IOC_SET_OUTPUT	_IO ('$', 5)
>  #define PERF_EVENT_IOC_SET_FILTER	_IOW('$', 6, char *)
> +#define PERF_EVENT_IOC_INJECT		_IO ('$', 7)
>  
>  enum perf_event_ioc_flags {
>  	PERF_IOC_FLAG_GROUP		= 1U << 0,
> @@ -513,6 +514,7 @@ struct pmu {
>  	void (*disable)			(struct perf_event *event);
>  	void (*read)			(struct perf_event *event);
>  	void (*unthrottle)		(struct perf_event *event);
> +	void (*inject)			(struct perf_event *event);
>  };
>  
>  /**
> diff --git a/kernel/perf_event.c b/kernel/perf_event.c
> index 40f8b07..e4dfd12 100644
> --- a/kernel/perf_event.c
> +++ b/kernel/perf_event.c
> @@ -2151,6 +2151,26 @@ unlock:
>  	return ret;
>  }
>  
> +static void __perf_event_inject(void *info)
> +{
> +	struct perf_event *event = info;
> +
> +	event->pmu->inject(event);
> +}
> +
> +static int perf_event_inject(struct perf_event *event)
> +{
> +	struct perf_event_context *ctx = event->ctx;
> +	struct task_struct *task = ctx->task;
> +
> +	if (!event->pmu->inject || task)
> +		return -EINVAL;
> +
> +	smp_call_function_single(event->cpu, __perf_event_inject, event, 1);
> +



Ah, I forgot to say. Injection is only supported on cpu
bound events (non-task bound). Because if it is task-bound,
we can't ensure we can inject while the event is scheduled,
not sure how to fix this.


  reply	other threads:[~2010-02-03  9:20 UTC|newest]

Thread overview: 55+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-02-03  9:14 [RFC GIT PULL] perf/trace/lock optimization/scalability improvements Frederic Weisbecker
2010-02-03  9:14 ` [PATCH 01/11] tracing: Add lock_class_init event Frederic Weisbecker
2010-02-03  9:14 ` [PATCH 02/11] tracing: Introduce TRACE_EVENT_INJECT Frederic Weisbecker
2010-02-05 14:08   ` Steven Rostedt
2010-02-05 14:47   ` Steven Rostedt
2010-02-05 14:53     ` Peter Zijlstra
2010-02-05 15:07       ` Steven Rostedt
2010-02-06 12:20         ` Frederic Weisbecker
2010-02-06 13:19           ` Steven Rostedt
2010-02-10 10:04             ` Frederic Weisbecker
2010-02-10 14:05               ` Steven Rostedt
2010-02-11 18:57                 ` Frederic Weisbecker
2010-02-11 19:23                   ` Steven Rostedt
2010-02-03  9:14 ` [PATCH 03/11] tracing: Inject lock_class_init events on registration Frederic Weisbecker
2010-02-05 14:13   ` Steven Rostedt
2010-02-05 14:30     ` Peter Zijlstra
2010-02-05 14:44       ` Steven Rostedt
2010-02-03  9:14 ` [PATCH 04/11] tracing: Add lock class id in lock_acquire event Frederic Weisbecker
2010-02-03  9:14 ` [PATCH 05/11] perf: New PERF_EVENT_IOC_INJECT ioctl Frederic Weisbecker
2010-02-03  9:19   ` Frederic Weisbecker [this message]
2010-02-03  9:14 ` [PATCH 06/11] perf: Handle injection ioctl with trace events Frederic Weisbecker
2010-02-03  9:14 ` [PATCH 07/11] perf: Handle injection iotcl for tracepoints from perf record Frederic Weisbecker
2010-02-03  9:14 ` [PATCH 08/11] perf/lock: Add support for lock_class_init events Frederic Weisbecker
2010-02-03  9:14 ` [PATCH 09/11] tracing: Remove the lock name from most lock events Frederic Weisbecker
2010-02-03  9:14 ` [PATCH 10/11] tracing/perf: Fix lock events recursions in the fast path Frederic Weisbecker
2010-02-04 15:47   ` Paul E. McKenney
2010-02-05  2:38     ` Lai Jiangshan
2010-02-05  9:45       ` Peter Zijlstra
2010-02-05  9:50         ` Peter Zijlstra
2010-02-05 10:49           ` Ingo Molnar
2010-02-05 12:10             ` Peter Zijlstra
2010-02-05 12:12               ` Peter Zijlstra
2010-02-05 13:01                 ` Peter Zijlstra
2010-02-06 11:12                   ` Frederic Weisbecker
2010-02-06 11:24                     ` Peter Zijlstra
2010-02-06 11:40                       ` Frederic Weisbecker
2010-02-06 14:17                         ` Peter Zijlstra
2010-02-06 16:10                           ` Frederic Weisbecker
2010-02-07  9:45                             ` Peter Zijlstra
2010-02-10 10:17                               ` Frederic Weisbecker
2010-02-28 22:24                   ` Frederic Weisbecker
2010-02-03  9:14 ` [PATCH 11/11] perf lock: Drop the buffers multiplexing dependency Frederic Weisbecker
2010-02-03 10:25 ` [RFC GIT PULL] perf/trace/lock optimization/scalability improvements Jens Axboe
2010-02-03 20:50   ` Frederic Weisbecker
2010-02-03 21:21     ` Jens Axboe
2010-02-03 22:13       ` Frederic Weisbecker
2010-02-04 19:40     ` Jens Axboe
2010-02-06 10:37       ` Frederic Weisbecker
2010-02-03 10:26 ` Ingo Molnar
2010-02-03 21:26   ` Frederic Weisbecker
2010-02-03 10:33 ` Peter Zijlstra
2010-02-03 22:07   ` Frederic Weisbecker
2010-02-04  6:33     ` Ingo Molnar
2010-02-07 17:10     ` Peter Zijlstra
2010-02-10 10:49       ` Frederic Weisbecker

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=20100203091955.GA18638@nowhere \
    --to=fweisbec@gmail.com \
    --cc=acme@redhat.com \
    --cc=jens.axboe@oracle.com \
    --cc=laijs@cn.fujitsu.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=lizf@cn.fujitsu.com \
    --cc=mhiramat@redhat.com \
    --cc=mingo@elte.hu \
    --cc=mitake@dcl.info.waseda.ac.jp \
    --cc=paulus@samba.org \
    --cc=peterz@infradead.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;
as well as URLs for NNTP newsgroup(s).