Re: [PATCH 5/5] powerpc/powernv: TCE invalidation for PHB3

[Gavin Shan <shangw@linux.vnet.ibm.com>]

On Wed, Apr 24, 2013 at 01:25:08AM +1000, Benjamin Herrenschmidt wrote:
>On Tue, 2013-04-23 at 19:03 +0800, Gavin Shan wrote:
>>          * of flags if that becomes the case
>>          */
>>         if (tbl->it_type & TCE_PCI_SWINV_CREATE)
>> -               pnv_tce_invalidate(tbl, tces, tcep - 1);
>> +               phb->dma_tce_invalidate(tbl, tces, tcep - 1);
>>  
>>         return 0;
>>  }
>
>TCE invalidate is very performance sensitive, we might be better off
>doing the if (ioda_type == PNV_PHB_IODA1) ... else ... here (which
>the CPU can generally predict) rather than a function pointer call
>which can be more tricky.
>

Ok. I'll change it in next version ;-)

Thanks,
Gavin