> With these fixes, things *almost* worked, except something was freeing
> random pages, resulting in massive page cache corruption (2.3.11-[45] are
> DANGEROUS, and have resulted in some minor data trashing here). It turns
> out that __switch_to wasn't preserving prev in %eax -- fixed by returning
> prev from __switch_to. While I was at it, I made schedule_tail a FASTCALL
<sigh> that always happens: 10 minutes later I see the same telltale page
cache corruption chased all weekend: a source file is replaced by a cvs ,v
file. Well, maybe my brain dump will tickle another's ideas.
-ben (Zzzzzzz.)
-
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/