Messages in this thread | | | Subject | Re: [PATCH] x86: static_cpu_has_safe: discard dynamic check after init | From | "H. Peter Anvin" <> | Date | Mon, 18 Jan 2016 15:13:00 -0800 |
| |
On January 18, 2016 3:05:54 PM PST, Borislav Petkov <bp@suse.de> wrote: >On Mon, Jan 18, 2016 at 11:45:18AM -0800, H. Peter Anvin wrote: >> I think the two-byte optimization is the real issue if there is one >at >> all. > >Well, we do optimize the jumps for a couple releases now, see >recompute_jump(). So we would always get the short JMP, if made >possible >by how gcc lays out the code so that the target is not far away. If the >JMP to the dynamic branch doesn't get nopped out anyway, that is. > >We have "debug-alternative" to dump exactly what happens during >patching. > >> I don't care about the inittext, and unless I'm misremembering >> completely altinstructions also get ejected. > >Ah yes, they do. > >> So I don't personally object to killing off the unsafe variant. > >Ok.
The optimization has always been there, the question is how often it actually kicks in. -- Sent from my Android device with K-9 Mail. Please excuse brevity and formatting.
| |