[Intel-gfx] [PATCH 2/3] drm/i915/perf: Add support for report sizes that are not power of 2

[Ashutosh Dixit]

On Sun, 15 Sep 2019 04:24:41 -0700, Lionel Landwerlin wrote:
>
> On 14/09/2019 02:06, Umesh Nerlige Ramappa wrote:
> > OA perf unit supports non-power of 2 report sizes. Enable support for
> > these sizes in the driver.
> >
> > Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa at intel.com>
> > ---
> >   drivers/gpu/drm/i915/i915_perf.c | 59 ++++++++++++--------------------
> >   1 file changed, 21 insertions(+), 38 deletions(-)
> >
> > diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
> > index 50b6d154fd46..482fca3da7de 100644
> > --- a/drivers/gpu/drm/i915/i915_perf.c
> > +++ b/drivers/gpu/drm/i915/i915_perf.c
> > @@ -450,7 +450,7 @@ static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream)
> >	u32 gtt_offset = i915_ggtt_offset(stream->oa_buffer.vma);
> >	int report_size = stream->oa_buffer.format_size;
> >	unsigned long flags;
> > -	u32 hw_tail;
> > +	u32 hw_tail, aging_tail;
> >	u64 now;
> >		/* We have to consider the (unlikely) possibility that read()
> > errors
> > @@ -459,16 +459,17 @@ static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream)
> >	 */
> >	spin_lock_irqsave(&stream->oa_buffer.ptr_lock, flags);
> >   -	hw_tail = dev_priv->perf.ops.oa_hw_tail_read(stream);
> > +	hw_tail = dev_priv->perf.ops.oa_hw_tail_read(stream) - gtt_offset;
> > +	aging_tail = stream->oa_buffer.aging_tail - gtt_offset;
> >		/* The tail pointer increases in 64 byte increments,
> >	 * not in report_size steps...
> >	 */
> > -	hw_tail &= ~(report_size - 1);
> > +	hw_tail = OA_TAKEN(hw_tail, (OA_TAKEN(hw_tail, aging_tail) % report_size));
>
>
> I'm struggling to parse this line above and I'm not 100% sure it's correct.
>
> Could add a comment to explain what is going on?

Also for efficiency perhaps the modulo (%) should be replaced by a
increment, compare and wraparound?

Thanks!
--
Ashutosh