El jue, 19-11-2026 a las 08:34 -0300, Maíra Canal escribió:
> Hi Iago,
> 
> On 19/11/26 05:17, Iago Toral wrote:
> > Looks good to me:
> > Reviewed-by: Iago Toral Quiroga <[email protected]>
> > 
> > I was not aware that hang checks were happening at second
> > boundaries,
> > regardless of the time at which the hangcheck was queued, it
> > doesn't
> > sound like a good idea, so I think it is good to change that.
> > 
> > On the other hand, now we rearm the hang check every 100ms instead
> > which is a much smaller window. I understand this reduces visible
> > impact of the workaround when the issue happens, but I am wondering
> > whether this alone has any visible performance impact for the 99%
> > of
> > the time we are not hitting the problem, I presume you haven't seen
> > any?
> > 
> 
> I benchmarked glmark2-wayland --off-screen (800x600, under labwc) and
> glmark2-es2-drm (1920x1080 fullscreen), which I believe are
> representative applications for RPi 3B+, and I observed no
> performance
> impact. I even tested 50 ms and I didn't observe a performance impact
> as
> well.
> 
> If you have other applications you would like to see the benchmark
> results, just let me know and I can test it.
> 

Thanks for checking, I think this is fine then.

Iago

> Best regards,
> - Maíra
> 
> > Iago
> > 
> > El mié, 18-11-2026 a las 18:47 -0300, Maíra Canal escribió:
> > > Mesa issue #16652 [1] reports GPU resets every few minutes on the
> > > Raspberry Pi 3. They happen when text labels are drawn over their
> > > shadows:
> > > two different threaded fragment shaders, plus untextured single-
> > > threaded
> > > ones, in the same tiles.
> > > 
> > > During a hang, the performance counters show four QPUs fetching
> > > instructions with 0 cache hits, ~6.5M misses per 100 ms, and 0
> > > valid
> > > instructions executed. This matches HW erratum GFXH-16: the QPUs
> > > of a
> > > slice share one instruction cache and can livelock, evicting each
> > > other's
> > > fills. Since shader code always starts at offset 0 of a page-
> > > aligned
> > > BO,
> > > every shader competes for the same cache sets.
> > > 
> > > This series works around it:
> > > 
> > >    - Patch 3 starts each shader's code at one of four offsets in
> > > its
> > > BO,
> > >      spreading shaders across cache sets.
> > > 
> > >    - Patch 4 clears the slice instruction and uniforms caches
> > > when the
> > >      hangcheck finds no progress, and resets the GPU only if the
> > > stall
> > >      persists. It is meant to recover from livelocks the offsets
> > > don't
> > >      prevent.
> > > 
> > > Patches 1 and 2 fix an off-by-one in the shader BO handle check
> > > and a
> > > NULL pointer dereference in validate_gl_shader_rec(), found while
> > > working
> > > on patch 3.
> > > 
> > > Tested on a Raspberry Pi 3B+ with the issue's reproducer, 4 x 15
> > > min
> > > runs:
> > > 
> > >    without the series:  29 GPU resets
> > >    with patches 1-3:     0 GPU resets
> > > 
> > > [1] https://gitlab.freedesktop.org/mesa/mesa/-/issues/16652
> > > 
> > > Best regards,
> > > - Maíra
> > > 
> > > ---
> > > Maíra Canal (4):
> > >        drm/vc4: Fix off-by-one in the shader record BO handle
> > > check
> > >        drm/vc4: Check for a validated shader before reading its
> > > thread
> > > mode
> > >        drm/vc4: Start shader code at varying offsets in its BO
> > >        drm/vc4: Clear the slice caches before resetting a stalled
> > > GPU
> > > 
> > >   drivers/gpu/drm/vc4/vc4_bo.c               | 43
> > > +++++++++++++++++++++++-------
> > >   drivers/gpu/drm/vc4/vc4_drv.h              | 15 ++++++++++-
> > >   drivers/gpu/drm/vc4/vc4_gem.c              | 20 ++++++++++++--
> > >   drivers/gpu/drm/vc4/vc4_validate.c         | 17 +++++++-----
> > >   drivers/gpu/drm/vc4/vc4_validate_shaders.c |  7 ++---
> > >   5 files changed, 79 insertions(+), 23 deletions(-)
> > > ---
> > > base-commit: 80ac6d197218c3399d66674167a4d7c9051a25e2
> > > change-id: 20261112-vc4-icache-workaround-d11b444bc7e8
> > > 
> > > 
> > 
> 
> 

Reply via email to