Re: [RFC] Relaxed PIO read vs. DMA write ordering

[jbarnes@sgi.com (Jesse Barnes)]

On Wed, Jan 07, 2004 at 03:56:33PM -0800, Jesse Barnes wrote:
> On Wed, Jan 07, 2004 at 03:27:54PM -0800, Greg KH wrote:
> > On Wed, Jan 07, 2004 at 03:07:12PM -0800, Jesse Barnes wrote:
> > > 
> > >   1) add pcix_enable_relaxed() and read_relaxed() (read() would always be
> > >      ordered)
> > 
> > This probably preserves the current situation best, enabling driver
> > writers to be explicit in knowing what is happening.

This is also the easiest solution to implement for the sn2 platform.
Honestly, I haven't used any PCI-X chipsets (nor do I know of any) that
exploit this new relaxed ordering feature, so I'm only guessing at how
it might be usefully exported to the driver API.

The sn2 platform actually _always_ behaves as though relaxed ordering
were enabled, so all we really need to implement this correctly is a
read_relaxed(), which will be a read() but without the software
workaround we put in place to conform to the PCI PIO/DMA semantics.

Maybe we can just add read_relaxed() for now and deal with other
chipsets that allow relaxed ordering as they appear?

Thanks,
Jesse