On Fri, May 19, 2017 at 4:17 AM, Linus Walleij <linus.wall...@linaro.org> wrote: > This merges the Moxa Art timer driver into the Faraday FTTMR010 > driver and replaces all Kconfig symbols to use the Faraday > driver instead. We are now so similar that the drivers can > be merged by just adding a few lines to the Faraday timer. > > Differences: > > - The Faraday driver explicitly sets the counter to count > upwards for the clocksource, removing the need for the > clocksource core to invert the value. > > - The Faraday driver also handles sched_clock() > > On the Aspeed, the counter can only count downwards, so support > the timers in downward-counting mode as well, and flag the > Aspeed to use this mode. This mode was tested on the Gemini so > I have high hopes that it'll work fine on the Aspeed as well. > > After this we have one driver for all three SoCs and a generic > Faraday FTTMR010 timer driver, which is nice. > > Cc: Joel Stanley <j...@jms.id.au> > Cc: Jonas Jensen <jonas.jen...@gmail.com> > Signed-off-by: Linus Walleij <linus.wall...@linaro.org> > --- > ChangeLog v1->v2: > - As it appears that the Aspeed timers can only count downwards, > augment the code to deal with downward counting clockevent, > clock source and sched_clock(), and flag the Aspeed for this > mode. > > ARM SoC folks: please ACK this so it can be merged with in the > clocksource subsystem once it works. > > Joel: it would be super if you can test this. If you have some > vendor tree or similar that actually indicates where the > up/down counter bits are it's even better, but I'm hoping that > this half-assed guesswork will JustWork(TM) (yeah, famous > last words, sorry...)
I gave it a spin on the ast2500-evb and it worked for me. I also gave it a read through and it looks good. I'd lowercase the shouty FTTMR010-TIMER message that pops up during boot, but it's no biggie. Reviewed-by: Joel Stanley <j...@jms.id.au> Tested-by: Joel Stanley <j...@jms.id.au> Cheers, Joel