Re: [PATCH] change name of rep_nop

[Peter Rival <frival@zk3.dec.com>]

Alan Cox wrote:

>>Here is a patch that addresses those three issues.  It adds an empty
>>definition of cpu_relax for all architectures except x86 (for x86 it
>>is defined to be rep_nop), and it changes smp_init to use a barrier
>>instead of making wait_init_idle be volatile.
>>
>>
> 
> Looks good to me


You also need to move the call to smp_boot_cpus() below the 
clear_bit(...) line in smp_init().  Without it, my Wildfire doesn't get 
past the while(wait_init_idle) loop - seems all of the CPUs have already 
done their work before the mask is set.  Besides, it's the right place 
for it anyway.  I'd generate a patch, but my system is bogged down in a 
benchmark for the next couple of hours.  If someone says so, I'll 
generate the patch after that...

  - Pete