Mark Lord wrote: > Tejun Heo wrote: >> Alan Cox wrote: > .. >> Because we can't use DMA uniformly, I went the other way and tried to >> use PIO uniformly. Another important point is that the other OS which >> is probably the only platform most ATAPI device vendors test against use >> PIO for these commands. >> >>> - Control over the DMA/PIO strategy belongs with the driver. If we mess >>> that up it will cost us dearly later. >> >> And I don't get what we'll lose. Care to deliberate? > .. > > Mmmm.. so what happens with the various controllers that can do PIO > using host-DMA and host-queuing ? Dropping to *real* PIO mode can > be quite expensive on those, especially when the channel is shared > with a hard disk. They continue to do PIO the way they used to do. No reason to drop to *real* PIO mode. Also, as now DMA / DMA-PIO buffers have trailing drain buffer for misc ATAPI commands, it should behave the same way as real PIO mode to the attached drive. -- tejun - To unsubscribe from this list: send the line "unsubscribe linux-ide" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
