Dave Jones wrote:

2. 'The in-kernel AGPGART doesn't have all the features our driver requires'.

Newsflash: I take patches.

Sifting through the ATI mashed-up agpgart is quite painful, as there are
so many changes in there ifdef'd to hell and back that its hard to see
whats really needed and what isn't.  So, lets talk. Tell me what you need
from the kernel GART driver. If it makes sense, I'll merge patches in a
heartbeat.

(I'm about to show total ignorance of how agpgart works. Beware!)

One problem I've always had with AGP support on Linux is that when you have a 256MB aperture, that consumes 256MB of physical memory, whether it's being actively used or not. In the future, it would be nice if drivers that use AGP could do something more dynamic. At the very least, not having physical pages backing part of the aperture until needed would be great.

Ideally a driver could say, "I want this page to back this part of the aperture." That would make things like APPLE_client_storage or ARB_vertex_buffer_objects truly zero-copy. In fact, I think that's how it works on OS X. I seem to recall some discussions a few years ago about why this is difficult on x86, but I don't remember the reasons. I can still dream. :)

Finally, pushing all these little bits back upstream is going to make
*your* lives easier too. You'll no longer have to worry about this huge
chunk of code, and making it work everywhere. You'll gain further independance
against what kernel your driver is running against. Your users won't
have to worry about whether agpgart is built-in or modular.
(This is a real pain for Fedora/RHEL users, as we make it built-in
 so that things like the amd64 IOMMU, and framebuffers that use agp
 mappings work correctly).

Sounds like what I've been saying about libGL.so for years. :)


------------------------------------------------------- This SF.Net email is sponsored by BEA Weblogic Workshop FREE Java Enterprise J2EE developer tools! Get your free copy of BEA WebLogic Workshop 8.1 today. http://ads.osdn.com/?ad_id=5047&alloc_id=10808&op=click -- _______________________________________________ Dri-devel mailing list [EMAIL PROTECTED] https://lists.sourceforge.net/lists/listinfo/dri-devel

Reply via email to