lkml.org 
[lkml]   [2009]   [Apr]   [28]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
SubjectRe: [PATCH] v3 RCU: the bloatwatch edition
Date
Paul E. McKenney <paulmck@linux.vnet.ibm.com> wrote:

> Your thought is that some of the functions could be moved to tinyrcu.h?
> Indeed, some of them would be smaller if inlined than even the call
> sequence. For example, rcu_needs_cpu() should remove code from the
> dynticks implementation given that it always returns zero.

tinyrcu.h is probably not a bad idea. Some of the functions are trivial, and
the code to do a function call is bigger than the body of the function itself.

rcu_exit_nohz(), rcu_nmi_enter/exit(), rcu_batches_completed[_bh](), for
example. Even call_rcu() and call_rcu_bh() might perhaps benefit from
inlining.

David


\
 
 \ /
  Last update: 2009-04-28 23:43    [W:0.142 / U:0.264 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site