RE: [PATCH v5 6/7] cpufreq: amd-pstate: update pstate frequency transition delay time

[Yuan, Perry]

[AMD Official Use Only - General]

Hi Punit

> -----Original Message-----
> From: Punit Agrawal <punit.agrawal@xxxxxxxxxxxxx>
> Sent: Monday, August 15, 2022 11:06 PM
> To: Yuan, Perry <Perry.Yuan@xxxxxxx>
> Cc: rafael.j.wysocki@xxxxxxxxx; Huang, Ray <Ray.Huang@xxxxxxx>;
> viresh.kumar@xxxxxxxxxx; Sharma, Deepak <Deepak.Sharma@xxxxxxx>;
> Limonciello, Mario <Mario.Limonciello@xxxxxxx>; Fontenot, Nathan
> <Nathan.Fontenot@xxxxxxx>; Deucher, Alexander
> <Alexander.Deucher@xxxxxxx>; Su, Jinzhou (Joe) <Jinzhou.Su@xxxxxxx>;
> Huang, Shimmer <Shimmer.Huang@xxxxxxx>; Du, Xiaojian
> <Xiaojian.Du@xxxxxxx>; Meng, Li (Jassmine) <Li.Meng@xxxxxxx>; linux-
> pm@xxxxxxxxxxxxxxx; linux-kernel@xxxxxxxxxxxxxxx
> Subject: Re: [PATCH v5 6/7] cpufreq: amd-pstate: update pstate frequency
> transition delay time
> 
> [CAUTION: External Email]
> 
> Perry Yuan <Perry.Yuan@xxxxxxx> writes:
> 
> > Change the default transition latency to be 20ms that is more
> > reasonable transition delay for AMD processors in non-EPP driver mode.
> >
> > Update transition delay time to 1ms, in the AMD CPU autonomous mode
> > and non-autonomous mode, CPPC firmware will decide frequency at 1ms
> > timescale based on the workload utilization.
> >
> > Acked-by: Viresh Kumar <viresh.kumar@xxxxxxxxxx>
> > Signed-off-by: Perry Yuan <Perry.Yuan@xxxxxxx>
> > ---
> >  drivers/cpufreq/amd-pstate.c | 4 ++--
> >  1 file changed, 2 insertions(+), 2 deletions(-)
> >
> > diff --git a/drivers/cpufreq/amd-pstate.c
> > b/drivers/cpufreq/amd-pstate.c index e40177d14310..9cb051d61422 100644
> > --- a/drivers/cpufreq/amd-pstate.c
> > +++ b/drivers/cpufreq/amd-pstate.c
> > @@ -41,8 +41,8 @@
> >  #include <asm/msr.h>
> >  #include "amd-pstate-trace.h"
> >
> > -#define AMD_PSTATE_TRANSITION_LATENCY        0x20000
> > -#define AMD_PSTATE_TRANSITION_DELAY  500
> > +#define AMD_PSTATE_TRANSITION_LATENCY        20000
> > +#define AMD_PSTATE_TRANSITION_DELAY  1000
> 
> How were these values derived? If from documentation, it'll be good to add a
> link to the relevant documentation. And if they were derived from testing,
> please mention this in the commit log (along with some details of the tests used
> to determine the value).

The values are calculated from the CPU PM firmware and hardware design.
There are some latency and delay values defined  in the PM firmware, I have no documents about the detail for now. 

Perry.
> 
> >
> >  /*
> >   * TODO: We need more time to fine tune processors with shared memory
> > solution