Messages in this thread | | | From | (Alan Cox) | Subject | Re: [patch] Katmai/PIII support for Linux pre-2.2.2-1 | Date | Wed, 3 Feb 1999 20:12:34 +0000 (GMT) |
| |
> > nor do we want to do boot-time dynamic linking. > > I think it would be better to do this. It would allow for a common kernel > that runs on all of Intel CPUs without opening a potential security hole > or having a serious performance impact, as not using the KNIs at all would > have.
Its not a "potential" security hole.
If KNI instructions don't fault in an environment where they are marked available but not saved then its an actual hole. If KNI instructions do fault its not a security hole
In case a) Ingo's code needs to panic at boot on a Xeon/PIII if its not using FXSAVE (clearly not acceptable) or dynamic link In case b) Ingo's patch is fine.
Ingo - I've yet to see any actual PIII docs - what _actually_ occurs in this situation
- 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/
| |