lkml.org 
[lkml]   [2012]   [Jan]   [26]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [RFC][PATCH] tracing/module: Move tracepoint out of module.h

* Steven Rostedt <rostedt@goodmis.org> wrote:

> On Mon, 2012-01-23 at 09:29 +1030, Rusty Russell wrote:
> > > could just move the "if" part out.
> >
> > Agreed. Since GCC should be able to eliminate that branch in almost all
> > cases, since it's usually a literal NULL or address of a (non-weak)
> > symbol.
> >
> > Be interesting to see the before/after sizes with this out-of-line.
>
> Using my default test config I got:
>
> text data bss dec hex filename
> 7489488 2249584 9719808 19458880 128eb40 vmlinux-prepatch
> 7482458 2248048 9719808 19450314 128c9ca vmlinux-postpatch
>
> An 8k savings!

Lovely!

> @@ -445,8 +444,7 @@ static inline void __module_get(struct module *module)
> {
> if (module) {
> preempt_disable();
> - __this_cpu_inc(module->refptr->incs);
> - trace_module_get(module, _THIS_IP_);
> + inc_module(module, _THIS_IP_);
> preempt_enable();
> }
> }
> @@ -458,10 +456,9 @@ static inline int try_module_get(struct module *module)
> if (module) {
> preempt_disable();
>
> - if (likely(module_is_live(module))) {
> - __this_cpu_inc(module->refptr->incs);
> - trace_module_get(module, _THIS_IP_);
> - } else
> + if (likely(module_is_live(module)))
> + inc_module(module, _THIS_IP_);
> + else
> ret = 0;

How much more do we save if we move all of try_module_get() out
of line? It still seems a rather thick inline function with
preempt section and all. I'd *really* suggest that it should all
be uninlined.

Thanks,

Ingo


\
 
 \ /
  Last update: 2012-01-26 11:31    [from the cache]
©2003-2014 Jasper Spaans. Advertise on this site