linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
To: rostedt <rostedt@goodmis.org>
Cc: linux-kernel <linux-kernel@vger.kernel.org>,
	Ingo Molnar <mingo@kernel.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Peter Zijlstra <peterz@infradead.org>
Subject: Re: [PATCH] tracepoints: Do not punish non static call users
Date: Thu, 4 Feb 2021 14:52:51 -0500 (EST)	[thread overview]
Message-ID: <238902062.7677.1612468371566.JavaMail.zimbra@efficios.com> (raw)
In-Reply-To: <20210204141742.46739ed2@gandalf.local.home>

----- On Feb 4, 2021, at 2:17 PM, rostedt rostedt@goodmis.org wrote:

> With static calls, a tracepoint can call the callback directly if there is
> only one callback registered to that tracepoint. When there is more than
> one, the static call will call the tracepoint's "iterator" function, which
> needs to reload the tracepoint's "funcs" array again, as it could have
> changed since the first time it was loaded.
> 
> But an arch without static calls is punished by having to load the
> tracepoint's "funcs" array twice. Once in the DO_TRACE macro, and once
> again in the iterator macro.

In addition to loading it, it needs to test it against NULL twice.

> 
> For archs without static calls, there's no reason to load the array macro
> in the first place, since the iterator function will do it anyway.
> 
> Change the __DO_TRACE_CALL() macro to do the double call only for

Do you mean "double call" or "double load and NULL check" ?

> architectures with static calls, and just call the iterator function
> directly for architectures without static calls.
> 
> [ Tested only on architectures with static calls, will test on those
>  without later ]
> 
> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
> ---
> diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
> index dc1d4c612cc3..966bfa6a861c 100644
> --- a/include/linux/tracepoint.h
> +++ b/include/linux/tracepoint.h
> @@ -152,9 +152,18 @@ static inline struct tracepoint
> *tracepoint_ptr_deref(tracepoint_ptr_t *p)
> #ifdef TRACEPOINTS_ENABLED
> 
> #ifdef CONFIG_HAVE_STATIC_CALL
> -#define __DO_TRACE_CALL(name)	static_call(tp_func_##name)
> +#define __DO_TRACE_CALL(name, args)					\
> +	do {								\
> +		struct tracepoint_func *it_func_ptr;			\
> +		it_func_ptr =						\
> +			rcu_dereference_raw((&__tracepoint_##name)->funcs); \
> +		if (it_func_ptr) {					\
> +			__data = (it_func_ptr)->data;			\
> +			static_call(tp_func_##name)(args);		\
> +		}							\
> +	} while (0)
> #else
> -#define __DO_TRACE_CALL(name)	__traceiter_##name
> +#define __DO_TRACE_CALL(name, args)	__traceiter_##name(args)

Also, we may want to comment or annotate the "void *data" argument of
__traceiter_##_name() to state that it is unused.

Thanks,

Mathieu

> #endif /* CONFIG_HAVE_STATIC_CALL */
> 
> /*
> @@ -168,7 +177,6 @@ static inline struct tracepoint
> *tracepoint_ptr_deref(tracepoint_ptr_t *p)
>  */
> #define __DO_TRACE(name, proto, args, cond, rcuidle)			\
> 	do {								\
> -		struct tracepoint_func *it_func_ptr;			\
> 		int __maybe_unused __idx = 0;				\
> 		void *__data;						\
> 									\
> @@ -190,12 +198,7 @@ static inline struct tracepoint
> *tracepoint_ptr_deref(tracepoint_ptr_t *p)
> 			rcu_irq_enter_irqson();				\
> 		}							\
> 									\
> -		it_func_ptr =						\
> -			rcu_dereference_raw((&__tracepoint_##name)->funcs); \
> -		if (it_func_ptr) {					\
> -			__data = (it_func_ptr)->data;			\
> -			__DO_TRACE_CALL(name)(args);			\
> -		}							\
> +		__DO_TRACE_CALL(name, TP_ARGS(args));			\
> 									\
> 		if (rcuidle) {						\
>  			rcu_irq_exit_irqson();				\

-- 
Mathieu Desnoyers
EfficiOS Inc.
http://www.efficios.com

  reply	other threads:[~2021-02-04 19:59 UTC|newest]

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-02-04 19:17 [PATCH] tracepoints: Do not punish non static call users Steven Rostedt
2021-02-04 19:52 ` Mathieu Desnoyers [this message]
2021-02-04 20:09   ` Steven Rostedt
2021-02-05 15:57 ` kernel test robot
2021-02-05 21:35 ` kernel test robot

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=238902062.7677.1612468371566.JavaMail.zimbra@efficios.com \
    --to=mathieu.desnoyers@efficios.com \
    --cc=akpm@linux-foundation.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.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).