Messages in this thread | | | Date | Fri, 24 Mar 2006 05:23:39 +0200 | From | Muli Ben-Yehuda <> | Subject | Re: [PATCH 3/3] x86-64: Calgary IOMMU - hook it in |
| |
On Thu, Mar 23, 2006 at 05:36:43PM +0100, Andi Kleen wrote:
> > +static int __init pci_iommu_init(void) > > +{ > > + int rc = 0; > > + > > +#ifdef CONFIG_GART_IOMMU > > + rc = gart_iommu_init(); > > + if (!rc) /* success? */ > > + return 0; > > +#endif > > +#ifdef CONFIG_CALGARY_IOMMU > > + rc = calgary_iommu_init(); > > +#endif > > This is weird. Normally I would expect you to detect the calgary thing first > and only then run the gart_iommu detection if not found. Why this > order?
Seniority? :-) these are mutually exclusive, really, so we didn't consider it important which runs "first".
> Fixing that would also not require adding the additional hacks to gart iommu > you added.
We'll still need it at least to stop swiotlb from kicking in in pci_swiotlb_init if we detected either gart or Calgary.
Cheers, Muli -- Muli Ben-Yehuda http://www.mulix.org | http://mulix.livejournal.com/
- 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/
| |