lkml.org 
[lkml]   [2009]   [Apr]   [15]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: mmotm 2009-04-10-02-21 uploaded - forkbombed by work_for_cpu


On Wed, 15 Apr 2009, Andrew Morton wrote:
>
> <stares suspiciously at smp_call_function_many()>
>
> * smp_call_function_many(): Run a function on a set of other CPUs.
>
> "other". It refuses to call the function on *this* CPU. Tricky.

.. Argh. And totally different from all the other smp_call_function's. In
smp_call_function_single(), for example, we literally test

if (cpu == this_cpu) {
local_irq_save(flags);
func(info);
local_irq_restore(flags);
} else {
.. do the cross-call ..
so I think this is just smp_call_function_many() breakage.

In fact, right now the PPC flush_tlb_page() does that insane dance just
because of this issue. So yes, there are a few current users, and they
seem to dislike the bad semantics (the kvm code doesn't care).

Duh duh duh.

Linus


\
 
 \ /
  Last update: 2009-04-15 16:55    [from the cache]
©2003-2011 Jasper Spaans