[lkml]   [2008]   [Dec]   [23]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
SubjectRe: [PATCH 1/2] tracing/ftrace: don't trace on early stage of secondary cpu boot

On Wed, 24 Dec 2008, Fr?d?ric Weisbecker wrote:
> One other solution, would be to define raw_smp_processor_id() to
> stack_smp_processor_id() and current to
> cpu_pda(stack_smp_processor_id()) if function_tracer is configured.
> That would even let one to trace those cpu boot
> functions.
> But the other side effect with this is that perhaps "current" would be
> retrieved with one pointer more to dereference....

Nah, I think that is a bit too intrusive. We really do not want to call
the function tracer if it can not handle a simple smp_processor_id() call.
You never know what else might turn up in this area.

-- Steve

 \ /
  Last update: 2008-12-24 04:15    [W:0.035 / U:3.348 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site