Messages in this thread | | | Date | Sat, 5 Dec 1998 14:29:00 +0100 (CET) | From | MOLNAR Ingo <> | Subject | Re: Problem with 1G RAM |
| |
On Fri, 4 Dec 1998, David S. Miller wrote:
> From: Perry Harrington <pedward@sun4.apsoft.com> > Date: Fri, 4 Dec 1998 14:58:51 -0800 (PST) > > Does any of this make sense? Or am I just off my rocker? I thought > of dynamicising PAGE_OFFSET for x86, but I figured that Linus, et > al, would have a fit over performance. > > Look at the BTFIXUP stuff we do on sparc32 to see another idea of how > to taper off most of the performance problems assosciated with a > dynamic PAGE_OFFSET. (TASK_UNMAPPED_BASE was a real killer before we > added the BTFIXUP stuff, it put a divide into a critical path).
the problem with this is that x86 CISC instructions are inherently more difficult to fix up runtime :(
-- mingo
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |