On Tue, 18 Jun 2002, Linus Torvalds wrote:
>
> So moving pages that way is definitely not cheap either. Hmm.
In fact, considering the cache and multi-CPU overhead, it's likely to be
faster to just memcpy() the damn thing from a regular cached mapping to an
existing AGP-mapped page. Which is pretty much what we do right now in
kernel space.
Playing VM games tends to be slow for normal mappings thanks to TLB
effects, and playing VM games with AGP stuff is taking that slowness to a
new level. In addition to the TLB effects you now have cache effects
and GART mapping updates. And cache effects are much worse than TLB
effects ever were, simply because caches are a damn lot bigger (not to
mention the fact that the x86 has very limited cache control).
So when it comes to mmap, I think you should either just map the AGP pages
uncached into user space in the first place (so that you don't have any
cache coherency problems at run-time) or you're better off doing the
existing memcpy(). Moving pages is too painful.
Linus
----------------------------------------------------------------------------
Bringing you mounds of caffeinated joy
>>> http://thinkgeek.com/sf <<<
_______________________________________________
Dri-devel mailing list
[EMAIL PROTECTED]
https://lists.sourceforge.net/lists/listinfo/dri-devel
