Messages in this thread | | | Date | Sat, 24 Jul 1999 11:13:32 -0400 (EDT) | From | Alexander Viro <> | Subject | Re: bloat and debugging code |
| |
On Sat, 24 Jul 1999, Ingo Molnar wrote:
> > On Sat, 24 Jul 1999, Alexander Viro wrote: > > > BTW, for x86 gurus: what will happen if in ring 0 you change %cr3 > > (register, that is), leave the value in TSS unmodified and then return to > > ring 3? Is there any chance that processor will reload the old value > > (undefined/some processors are buggy and know to do that/it's documented > > behaviour/never happens on known processors)? > > the TSS is only ever consulted when we switch from ring3 into ring0, to > get esp and ss registers. (plus the io bitmaps if using ioperm()) It's not > supposed to reload %cr3 except when we do an explicit TSS switch.
Which excludes the "documented behaviour" variant. Could you try to modify activate_context() (add assignment to init_tss[smp_processor_id()].cr3) and see if it will change the behaviour on your processor? I can see how somebody might decide to reuse the microcode...
- 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/
| |