lkml.org 
[lkml]   [2010]   [Aug]   [27]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH] lglock: make lg_lock_global() actually lock globally
On Thu, Aug 26, 2010 at 01:45:39PM +0200, Peter Zijlstra wrote:
> On Thu, 2010-08-26 at 21:38 +1000, Nick Piggin wrote:
> > I think for CPU plug, stop_machine is reasonable (especially
> > considering it is required in unload, which means any frequent
> > amount of cpu plug activity already will require stop_machine to
> > run anyway).
>
> How is it required?

Well, as is implemented.


> Its currently implemented as such, and its sure a lot easier to do that
> way, but I could imagine that unplugging a CPU could be done without it.

I would much prefer the rules to be simpler and easier for all
other kernel code, and keep complexity and overheads in cpu
plug/unplug.

I don't see what is so nice about stop_machine()less cpu plug/unplug
or module unload. Module load definitely is nice because you can
have a lot of modules and on demand loading from non-privileged
operations.



\
 
 \ /
  Last update: 2010-08-27 07:53    [W:0.050 / U:22.948 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site