[Intel-gfx] [PATCH] drm/mm: Support 4 GiB and larger ranges

Russell King - ARM Linux linux at arm.linux.org.uk
Tue Jan 27 13:26:27 PST 2015


On Tue, Jan 27, 2015 at 09:31:26AM +0100, Thomas Hellstrom wrote:
> On 01/27/2015 09:15 AM, Thierry Reding wrote:
> > Are you referring to the 4 GiB - 1 comment? The point I was trying to
> > make is not that the granularity of the IOVA space needs to be 1 byte
> > but rather that using an unsigned long for a size on a 32-bit machine
> > will give you 4 GiB - 1 addresses. The IOMMU page size is still 4 KiB
> > for Tegra.
> 
> I was rather referring to that if the range manager (drm_mm) is set up
> to manage pages instead of bytes
> (like, for example, the TTM VM address space), you'd get 4G - 1 pages,
> which, I believe, is sufficient on most 32 bit systems?

It'd probably also be more efficient on 32-bit systems rather than
shifting them over to using 64-bit quantities.

If the allocation granularity were to move to pages, would it be worth
moving to a pfn-based addressing system too, rather than sticking with
a byte address there too?

-- 
FTTC broadband for 0.8mile line: currently at 10.5Mbps down 400kbps up
according to speedtest.net.


More information about the Intel-gfx mailing list