On Wed, 2007-08-22 at 10:17 -0700, Jesse Barnes wrote:
quoted text
> On Wednesday, August 22, 2007 10:04:32 am James Bottomley wrote:
> > The spec isn't ambiguous ... it says if the device and bridge agree on
> > relaxed ordering, then it *may* be observed in the transaction.  If
> > there's a disagreement or neither wishes to support relaxed ordering
> > then the transaction *must* be strict.
> 
> Arg, don't make me dig out my spec, I don't have it handy...

Well ... I don't have one either.  However, Grant Grundler did a
presentation to OLS about relaxed ordering, and I went over it pretty
thoroughly with him a while ago.  The bottom line is that the default is
always strict unless both the bridge and the device agree otherwise.

quoted text
> > I really don't think a work around for a PCI spec violation belongs in
> > the generic DMA code, do you?  The correct fix for this should be to set
> > the device hints to strict ordering, which presumably altix respects?
> 
> Well, the Altix hw by itself won't honor device hints (I'm not even sure if 
> there are devices that honor order hints like you outline above).  However, 
> Altix could track per-device ordering as long as arch code was called from 
> such a hook.
> 
> > In which case, it sounds like what needs exposing are access to the PCI
> > device hints.  I believe both PCI-X and PCIe have these hints as
> > optional specifiers in the bridges, so it should be in a current Rev of
> > the PCI spec.  Or are you proposing adding an additional PCI API that
> > allows transaction flushes to be inserted into the stream for devices
> > and bridges that have already negotiated relaxed ordering? ... in which
> > case we need to take this to the PCI list.
> 
> I think it would have to be the latter, since otherwise it would be hard to 
> setup just completion queue requests to be ordered.

OK ... I think this is definitely a PCI specific API ... and probably a
generic one for requesting order flushes in devices that have negotiated
relaxed ordering.  Do you want to start a new thread on linux-pci and cc
me?

James


-
unsubscribe notice
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/