Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1760646AbZCPTVZ (ORCPT ); Mon, 16 Mar 2009 15:21:25 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1755542AbZCPTVQ (ORCPT ); Mon, 16 Mar 2009 15:21:16 -0400 Received: from tomts16.bellnexxia.net ([209.226.175.4]:46487 "EHLO tomts16-srv.bellnexxia.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753425AbZCPTVQ (ORCPT ); Mon, 16 Mar 2009 15:21:16 -0400 X-IronPort-Anti-Spam-Filtered: true X-IronPort-Anti-Spam-Result: AtsEAFE9vklMQW1W/2dsb2JhbACBTtQog38G Date: Mon, 16 Mar 2009 15:21:00 -0400 From: Mathieu Desnoyers To: Steven Rostedt Cc: Jason Baron , 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 Message-ID: <20090316192100.GA11878@Krystal> References: <20090312183603.GC3352@redhat.com> <20090316190047.GB3111@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline In-Reply-To: X-Editor: vi X-Info: http://krystal.dyndns.org:8080 X-Operating-System: Linux/2.6.21.3-grsec (i686) X-Uptime: 15:20:03 up 16 days, 15:46, 3 users, load average: 0.23, 0.57, 0.64 User-Agent: Mutt/1.5.18 (2008-05-17) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 3558 Lines: 141 * 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 > > > > --- > > > > 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 > > #include > > #include > > +#include > > > > #include > > /* > > @@ -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 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/