Re: [patch] x86: make delay_tsc() preemptible again

2007-11-16 Thread Ingo Molnar
* Peter Zijlstra <[EMAIL PROTECTED]> wrote: > > + prev_cpu = smp_processor_id(); > > rep_nop(); > > + preempt_enable(); > > Why not have the rep_nop() here between the enable, and disable ? yes, indeed - fixed. > > + /* > > +* If we preempt

Re: [patch] x86: make delay_tsc() preemptible again

2007-11-16 Thread Peter Zijlstra
On Fri, 2007-11-16 at 09:47 +0100, Ingo Molnar wrote: > * Ingo Molnar <[EMAIL PROTECTED]> wrote: > > > but that should not be needed in this case. Why doesnt the TSC using > > delay loop simply poll the CPU it is on and fix up the TSC? > > something like the patch below. > > Ingo > > --

[patch] x86: make delay_tsc() preemptible again

2007-11-16 Thread Ingo Molnar
* Ingo Molnar <[EMAIL PROTECTED]> wrote: > but that should not be needed in this case. Why doesnt the TSC using > delay loop simply poll the CPU it is on and fix up the TSC? something like the patch below. Ingo ---> Subject: x86: make delay_tsc() preemptible again From: In