Hi all, I am a moron, I missed:
+skip: + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) + goto disable; It uses a different path... Regards, NIck On Mon, Jan 8, 2018 at 11:27 AM, Nick Lowe <nick.l...@gmail.com> wrote: > Hi Kevin, > > I am not following :-) For AMD, there should not be a tradeoff as > there is no need for the page table isolation. > > Regards, > > Nick > > On Mon, Jan 8, 2018 at 11:21 AM, Kevin Darbyshire-Bryant > <ke...@darbyshire-bryant.me.uk> wrote: >> >> >>> On 8 Jan 2018, at 11:12, Nick Lowe <nick.l...@gmail.com> wrote: >>> >>> Agreed. So this will seemingly regress something like an APU2 and >>> therefore probably should not be merged to LEDE as-is? >> >> I’ll let an adult decide the performance/security tradeoff. _______________________________________________ Lede-dev mailing list Lede-dev@lists.infradead.org http://lists.infradead.org/mailman/listinfo/lede-dev
