Messages in this thread | | | Date | Fri, 10 Jan 2014 08:11:24 -0800 | From | "H. Peter Anvin" <> | Subject | Re: Sanitize CPU-state when switching tasks (was sanitize CPU-state when switching from virtual-8086 mode to other task) |
| |
On 01/10/2014 03:16 AM, Linus Torvalds wrote: > On Fri, Jan 10, 2014 at 6:06 PM, Borislav Petkov <bp@alien8.de> wrote: >> >> Tested-by: Borislav Petkov <bp@suse.de> > > Ok, good. > > Peter, do you want to take it (feel free to add my sign-off), or > should I just commit it? > > Also, is there a way to have a "likely not true" version of that > "static_cpu_has()"? There seems to be no way to make the non-K7/K8 > case the fallthrough code.. Not that this is likely that > performance-critical, but.. >
I'll take it.
We don't have a "likely not true" version of static_cpu_has() at this point... it would mean we couldn't do short jumps unfortunately (and they would still take the false path until alternatives run.)
-hpa
| |