On Wed, Oct 17, 2012 at 10:32 AM, Anton Romanov <theli.ua@xxxxxxxxx> wrote: > Right. I see. > > PS. sorry to anyone who i accidentally directly messaged with copies of > kernel mails, Gmail reply button betrayed me :(. > no problem with that, but please don't top-post to these lists. > > On Wed, Oct 17, 2012 at 5:27 PM, Christoffer Dall > <c.dall@xxxxxxxxxxxxxxxxxxxxxx> wrote: >> >> On Wed, Oct 17, 2012 at 10:25 AM, Anton Romanov <theli.ua@xxxxxxxxx> >> wrote: >> > I'm not sure about the inkernel coding standards. >> > But why can't this be: >> > #if KVM_VTTBR > 255 >> > add r1, r1, #KVM_VTTBR >> > ldrd r2, r3, [r1] >> > #else >> > >> > ldrd r2, r3, [r1, #KVM_VTTBR] >> > #endif >> > ? >> > This way you wont add additional cycles if its not needed in particular >> > configuration. >> > >> that's way too cluttered for a single cycle imho. also, I'm not sure this will be a cycle in difference, the add takes place anyway, just as part of the other instruction, so my knowledge of the cpu internals comes to a short here. But it's really splitting hairs. > > > > _______________________________________________ > kvmarm mailing list > kvmarm@xxxxxxxxxxxxxxxxxxxxx > https://lists.cs.columbia.edu/cucslists/listinfo/kvmarm _______________________________________________ kvmarm mailing list kvmarm@xxxxxxxxxxxxxxxxxxxxx https://lists.cs.columbia.edu/cucslists/listinfo/kvmarm
