public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Mathieu Desnoyers <compudj@krystal.dyndns.org>
To: Steven Rostedt <rostedt@goodmis.org>
Cc: Jason Baron <jbaron@redhat.com>,
	mingo@elte.hu, linux-kernel@vger.kernel.org,
	acme@ghostprotocols.net, fweisbec@gmail.com, fche@redhat.com,
	peterz@infradead.org
Subject: Re: [Patch 2/2] tracepoints for softirq entry/exit - tracepoints
Date: Mon, 16 Mar 2009 15:21:00 -0400	[thread overview]
Message-ID: <20090316192100.GA11878@Krystal> (raw)
In-Reply-To: <alpine.DEB.2.00.0903161514590.27978@gandalf.stny.rr.com>

* Steven Rostedt (rostedt@goodmis.org) wrote:
> 
> On Mon, 16 Mar 2009, Jason Baron wrote:
> 
> > hi,
> > 
> > ok, below is a re-spun patch 2/2 which converts to the TRACE_EVENT
> > format.
> 
> Thanks, some comments though.
> 
> > 
> > thanks,
> > 
> > -Jason
> > 
> > 
> > Signed-off-by: Jason Baron <jbaron@redhat.com>
> > 
> > ---
> > 
> >  include/trace/irq_event_types.h |   36 ++++++++++++++++++++++++++++++++++++
> >  kernel/softirq.c                |    7 ++++++-
> >  2 files changed, 42 insertions(+), 1 deletions(-)
> > 
> > 
> > diff --git a/include/trace/irq_event_types.h b/include/trace/irq_event_types.h
> > index 214bb92..de1f2a9 100644
> > --- a/include/trace/irq_event_types.h
> > +++ b/include/trace/irq_event_types.h
> > @@ -40,4 +40,40 @@ TRACE_EVENT(irq_handler_exit,
> >  		  __entry->irq, __entry->ret ? "handled" : "unhandled")
> >  );
> >  
> > +TRACE_EVENT(softirq_action_entry,
> > +
> > +	TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
> > +
> > +	TP_ARGS(h, vec),
> > +
> > +	TP_STRUCT__entry(
> > +		__array(	char,	softirq_name,	MAX_SOFTIRQ_NAME_LEN )
> > +	),
> > +
> > +	TP_fast_assign(
> > +		memcpy(__entry->softirq_name, softirq_to_name[h-vec],
> > +			MAX_SOFTIRQ_NAME_LEN);
> 
> memcpy isn't fast ;-)
> 

When given a constant size, memcpy is inlined by the compiler and turned
into a simple mov instruction. That shouldn't change a thing.

Mathieu

> What you want is this:
> 
> 	TP_STRUCT__entry(
> 		__field(	int,	vec	)
> 	),
> 
> 	TP_fast_assign(
> 		__entry->vec = h - vec;
> > +	),
> > +
> > +	TP_printk("softirq entry: %s", __entry->softirq_name)
> 
> 	TP_printk("softirq entry: %s", softirq_to_name[__entry->vec])
> 
> > +);
> > +
> > +TRACE_EVENT(softirq_action_exit,
> > +
> > +	TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
> > +
> > +	TP_ARGS(h, vec),
> > +
> > +	TP_STRUCT__entry(
> > +		__array(	char,	softirq_name,	MAX_SOFTIRQ_NAME_LEN )
> > +	),
> > +
> > +	TP_fast_assign(
> > +		memcpy(__entry->softirq_name, softirq_to_name[h-vec],
> > +			MAX_SOFTIRQ_NAME_LEN);
> > +	),
> > +
> > +	TP_printk("softirq exit: %s", __entry->softirq_name)
> 
> 
> And do the same here.
> 
> -- Steve
> 
> > +);
> > +
> >  #undef TRACE_SYSTEM
> > diff --git a/kernel/softirq.c b/kernel/softirq.c
> > index 8f3ae57..5e96c77 100644
> > --- a/kernel/softirq.c
> > +++ b/kernel/softirq.c
> > @@ -24,6 +24,7 @@
> >  #include <linux/ftrace.h>
> >  #include <linux/smp.h>
> >  #include <linux/tick.h>
> > +#include <trace/irq.h>
> >  
> >  #include <asm/irq.h>
> >  /*
> > @@ -185,6 +186,9 @@ EXPORT_SYMBOL(local_bh_enable_ip);
> >   */
> >  #define MAX_SOFTIRQ_RESTART 10
> >  
> > +DEFINE_TRACE(softirq_action_entry);
> > +DEFINE_TRACE(softirq_action_exit);
> > +
> >  asmlinkage void __do_softirq(void)
> >  {
> >  	struct softirq_action *h;
> > @@ -211,8 +215,9 @@ restart:
> >  		if (pending & 1) {
> >  			int prev_count = preempt_count();
> >  
> > +			trace_softirq_action_entry(h, softirq_vec);
> >  			h->action(h);
> > -
> > +			trace_softirq_action_exit(h, softirq_vec);
> >  			if (unlikely(prev_count != preempt_count())) {
> >  				printk(KERN_ERR "huh, entered softirq %td %s %p"
> >  				       "with preempt_count %08x,"
> > 
> 

-- 
Mathieu Desnoyers
OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F  BA06 3F25 A8FE 3BAE 9A68

  reply	other threads:[~2009-03-16 19:21 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-03-12 18:36 [Patch 2/2] tracepoints for softirq entry/exit - tracepoints Jason Baron
2009-03-12 19:02 ` Frederic Weisbecker
2009-03-12 23:49   ` Ingo Molnar
2009-03-13  4:03 ` [tip:tracing/ftrace] tracing: " Jason Baron
2009-03-14  2:57 ` [Patch 2/2] " Mathieu Desnoyers
2009-03-15  5:33   ` Ingo Molnar
2009-03-16 13:34   ` Steven Rostedt
2009-03-16 18:37     ` Mathieu Desnoyers
2009-03-16 18:45       ` Steven Rostedt
2009-03-16 18:51         ` Steven Rostedt
2009-03-16 19:28           ` Mathieu Desnoyers
2009-03-16 19:23         ` Mathieu Desnoyers
2009-03-16 19:00 ` Jason Baron
2009-03-16 19:17   ` Steven Rostedt
2009-03-16 19:21     ` Mathieu Desnoyers [this message]
2009-03-16 19:38     ` Jason Baron

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=20090316192100.GA11878@Krystal \
    --to=compudj@krystal.dyndns.org \
    --cc=acme@ghostprotocols.net \
    --cc=fche@redhat.com \
    --cc=fweisbec@gmail.com \
    --cc=jbaron@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --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