Messages in this thread | | | Date | Tue, 23 Dec 2008 22:11:54 -0500 (EST) | From | Steven Rostedt <> | Subject | Re: [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
| |