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
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Sun Oct 07 2001 - 21:00:38 EST