Re: PCI DMA to small buffers on cache-incoherent arch

From: Roland Dreier (roland@topspin.com)
Date: Sat Jun 08 2002 - 20:26:12 EST


>>>>> "David" == David S Miller <davem@redhat.com> writes:

    Roland> Or should we leave that usage unless it is observed
    Roland> causing problems (since we almost always get lucky and
    Roland> don't touch the rest of the cache line near the DMA)?
   
    David> I think passing in a 4 byte chunk and assuming the rest of
    David> the cacheline is unmodified is a valid expectation the more
    David> I think about it.

Just to make sure I'm reading this correctly, you're saying that as
long as a buffer is OK for DMA, it should be OK to use a
sub-cache-line chunk as a DMA buffer via pci_map_single(), and
accessing the rest of the cache line should be OK at any time before,
during and after the DMA.

    David> This means what MIPS is doing is wrong. For partial
    David> cacheline bits it can't do the invalidate thing.

If I understand you, this means non-cache-coherent PPC is wrong as
well -- pci_map_single() goes through consistent_sync() and turns
into:

        case PCI_DMA_FROMDEVICE: /* invalidate only */
                invalidate_dcache_range(start, end);
                break;

What alternate implementation are you proposing?

Thanks,
  Roland
-
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 : Sat Jun 15 2002 - 22:00:13 EST