Re: [PATCH] drm/i915: Fix conversion between clock ticks and nanoseconds

[Rodrigo Vivi <rodrigo.vivi@intel.com>]

On Thu, Oct 16, 2025 at 04:36:23PM -0700, Umesh Nerlige Ramappa wrote:
> On Thu, Oct 16, 2025 at 01:07:17PM -0700, Dixit, Ashutosh wrote:
> > On Wed, 15 Oct 2025 17:03:51 -0700, Umesh Nerlige Ramappa wrote:
> > > 
> > > When tick values are large, the multiplication by NSEC_PER_SEC is larger
> > > than 64 bits and results in bad conversions.
> > > 
> > > The issue is seen in PMU busyness counters that look like they have
> > > wrapped around due to bad conversion. i915 PMU implementation returns
> > > monotonically increasing counters. If a count is lesser than previous
> > > one, it will only return the larger value until the smaller value
> > > catches up. The user will see this as zero delta between two
> > > measurements even though the engines are busy.
> > > 
> > > Fix it by using mul_u64_u32_div()
> > 
> > Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
> 
> Thanks, Pushed it.
> 
> @Lucas, @Rodrigo
> 
> fyi,
> 
> I was working on drm-intel-gt-next and did a dim ub at some point and it
> automatically switched to drm-xe-next. Instead of pushing drm-intel-gt-next,
> I accidentally pushed drm-xe-next without any changes. Hope that does not
> cause any issues.

I'm kind of confused here.... I was going to force-push this out of
drm-xe-next. But it is not there.

Unless Lucas was faster than me...

In any case, please go to your drm-xe-next repository and run
git fetch drm-xe && git reset --hard drm-xe/drm-xe-next

just in case it is only applied but not pushed yet, so you don't
end up really pushing it on your next dim push.

> 
> I later pushed the right branch.

yeap, this one in the drm-intel-gt-next I can see.

> 
> Regards,
> Umesh
> > 
> > > Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/14955
> > > Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
> > > ---
> > > v2:
> > > - Fix divide by zero for Gen11 (Andi)
> > > - Update commit message
> > > 
> > > v3:
> > > - Drop GCD and use mul_u64_u32_div() instead (Ashutosh)
> > > ---
> > >  drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c | 4 ++--
> > >  1 file changed, 2 insertions(+), 2 deletions(-)
> > > 
> > > diff --git a/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c b/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c
> > > index 88b147fa5cb1..c90b35881a26 100644
> > > --- a/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c
> > > +++ b/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c
> > > @@ -205,7 +205,7 @@ static u64 div_u64_roundup(u64 nom, u32 den)
> > > 
> > >  u64 intel_gt_clock_interval_to_ns(const struct intel_gt *gt, u64 count)
> > >  {
> > > -	return div_u64_roundup(count * NSEC_PER_SEC, gt->clock_frequency);
> > > +	return mul_u64_u32_div(count, NSEC_PER_SEC, gt->clock_frequency);
> > >  }
> > > 
> > >  u64 intel_gt_pm_interval_to_ns(const struct intel_gt *gt, u64 count)
> > > @@ -215,7 +215,7 @@ u64 intel_gt_pm_interval_to_ns(const struct intel_gt *gt, u64 count)
> > > 
> > >  u64 intel_gt_ns_to_clock_interval(const struct intel_gt *gt, u64 ns)
> > >  {
> > > -	return div_u64_roundup(gt->clock_frequency * ns, NSEC_PER_SEC);
> > > +	return mul_u64_u32_div(ns, gt->clock_frequency, NSEC_PER_SEC);
> > >  }
> > > 
> > >  u64 intel_gt_ns_to_pm_interval(const struct intel_gt *gt, u64 ns)
> > > --
> > > 2.43.0
> > >