[REGRESSION][BISECTED] 58a261bfc967: choppy GPU performance

[Christopher Snowhill]

On Wed Oct 2, 2024 at 5:34 AM PDT, John Rowley wrote:
> If you're referring to the Freedesktop DRM issue then sinatosk a separate poster. I'm not involved in that thread. 🙂
> ----------------------------------------

Oh, sorry, my mistake. I thought you had popped over to the issue
tracker as well. Wasn't paying attention as much to the name of the user
reporting it there. Carry on.


> From: Christopher Snowhill <chris at kode54.net>
> To: John Rowley <lkml at johnrowley.me>; Mario Limonciello <mario.limonciello at amd.com>; Leo Li <sunpeng.li at amd.com>; Hamza Mahfooz <hamza.mahfooz at amd.com>
> CC: Harry Wentland <harry.wentland at amd.com>; Rodrigo Siqueira <Rodrigo.Siqueira at amd.com>; amd-gfx at lists.freedesktop.org; regressions at lists.linux.dev
> Date: 2 Oct 2024 11:57:12
> Subject: Re: [REGRESSION][BISECTED] 58a261bfc967: choppy GPU performance
>
> > On Tue Oct 1, 2024 at 2:32 PM PDT, John Rowley wrote:
> >> The attached patch seems to improve rendering performance a lot; animations and desktop performance are generally smoother again.
> >> 
> >> But it doesn't seem 100%, e.g. if I let the laptop idle for 10 secs before interacting with the touchpad, the desktop cursor seems to stick in-place for 100-200ms or so, before becoming responsive again.
> >> 
> >> This 'sticking' problem doesn't seem to occur with PSR disabled.
> >> 
> >> My testing isn't exactly scientifically sound I'm afraid, if there's a better test or benchmark I can run, please let me know.
> > 
> > May want to also tell the list that you mis-applied the patch on the
> > first go by misreading what it did and editing manually. I'm eager to
> > hear whether the actual patch worked out better.
> > 
> >> 
> >> On 01/10/2024 22:16, Mario Limonciello wrote:
> >>> On 10/1/2024 16:14, John Rowley wrote:
> >>>> Disabling PSR as per Leo's reply seems to have done the trick!
> >>>> 
> >>>> Stock 6.12-rc1 (without revert): BROKEN
> >>>> 
> >>>>      /sys/kernel/debug/dri/0000:c1:00.0/eDP-1/psr_state:
> >>>>      6
> >>>> 
> >>>>      /sys/kernel/debug/dri/0000:c1:00.0/eDP-1/psr_capability:
> >>>>      Sink support: yes [0x03]
> >>>>      Driver support: yes
> >>>> 
> >>>> With amdgpu.dcdebugmask=0x800: BROKEN
> >>>> 
> >>>> With amdgpu.dcdebugmask=0x10: FIXED! Performance is as it was on 6.11.
> >>>> 
> >>>>      /sys/kernel/debug/dri/0000:c1:00.0/eDP-1/psr_state:
> >>>>      0
> >>>> 
> >>>>      /sys/kernel/debug/dri/0000:c1:00.0/eDP-1/psr_capability:
> >>>>      Sink support: yes [0x03]
> >>>>      Driver support: no [0xffffffff]
> >>>> 
> >>>> I have the older Framework 13 panel (BOE 0x0BCA, 2256x1504 @ 59.999 Hz) so I assume PSR isn't supported according to Mario, yet psr_{state,capability} above seem to indicate otherwise?
> >>>> 
> >>> 
> >>> PSR and Replay are two different things.  But from your above analysis it does confirm it's a PSR issue.
> >>> 
> >>> There's a patch that Hamza attached to https://gitlab.freedesktop.org/drm/amd/-/issues/3658.
> >>> 
> >>> Can you try that?
> >>> 
> >>> Thanks,