On Sat, 2009-04-04 at 10:25 -0700, Eric Anholt wrote:
> Before, I was figuring it was better to have easy code than memory
> optimal code in my infrequently-tested workaround. Since recent notes
> about kmalloc limits, I'll switch to using bitmap.h.
Yeah, a single page of bits will cover 32k of
On Fri, 2009-04-03 at 18:08 -0700, Keith Packard wrote:
> On Fri, 2009-04-03 at 17:03 -0700, Eric Anholt wrote:
>
> > + obj_priv->bit_17 = kmalloc(page_count, GFP_KERNEL);
>
> seems like you could save a bit of memory here by using 1 bit per page
> instead of a byte.
Before, I was figu
On Fri, 03 Apr 2009 18:08:14 -0700
Keith Packard wrote:
> On Fri, 2009-04-03 at 17:03 -0700, Eric Anholt wrote:
>
> > + obj_priv->bit_17 = kmalloc(page_count, GFP_KERNEL);
>
> seems like you could save a bit of memory here by using 1 bit per page
> instead of a byte.
>
If you choose
On Fri, 2009-04-03 at 17:03 -0700, Eric Anholt wrote:
> + obj_priv->bit_17 = kmalloc(page_count, GFP_KERNEL);
seems like you could save a bit of memory here by using 1 bit per page
instead of a byte.
--
keith.pack...@intel.com
signature.asc
Description: This is a digitally signed
Save the bit 17 state of the pages when freeing the page list, and
reswizzle them if necessary when rebinding the pages. This exposes two new
swizzle enums to userland, which would have to be respected for correct
operation of software fallbacks on these objects. Given that users
complain that 3D