[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:0.020 / U:18.144 seconds]
    ©2003-2017 Jasper Spaans. hosted at Digital OceanAdvertise on this site