>> This is still a rounding error but at a different site. I see we saved >> a division by doing a >> 10, but we added it right back by doing a /20 >> later in the platform code. > > While a >> 10 is done at every idle exit, div by 20 is done once during > boot, so this doesn't negate the previous optimization. >
Yes, fair point >> Shouldn't the rounding affect other >> platforms as well? Can't we fix it in cpuidle_enter_state(). > > This does affect all platforms, but I'm guessing no other place relied > on the precision of last_residency calculations. > Daniel can perhaps comment on this. > _______________________________________________ Linuxppc-dev mailing list Linuxppc-dev@lists.ozlabs.org https://lists.ozlabs.org/listinfo/linuxppc-dev