kernel_samsung_a53x/drivers/gpu/drm/msm
Vladimir Lypak a5394161bf drm/msm/a5xx: disable preemption in submits by default
[ Upstream commit db9dec2db76146d65e1cfbb6afb2e2bd5dab67f8 ]

Fine grain preemption (switching from/to points within submits)
requires extra handling in command stream of those submits, especially
when rendering with tiling (using GMEM). However this handling is
missing at this point in mesa (and always was). For this reason we get
random GPU faults and hangs if more than one priority level is used
because local preemption is enabled prior to executing command stream
from submit.
With that said it was ahead of time to enable local preemption by
default considering the fact that even on downstream kernel it is only
enabled if requested via UAPI.

Fixes: a7a4c19c36de ("drm/msm/a5xx: fix setting of the CP_PREEMPT_ENABLE_LOCAL register")
Signed-off-by: Vladimir Lypak <vladimir.lypak@gmail.com>
Patchwork: https://patchwork.freedesktop.org/patch/612041/
Signed-off-by: Rob Clark <robdclark@chromium.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-11-23 23:21:21 +01:00
..
adreno drm/msm/a5xx: disable preemption in submits by default 2024-11-23 23:21:21 +01:00
disp drm/msm/dpu: don't play tricks with debug macros 2024-11-23 23:20:49 +01:00
dp drm/msm/dp: reset the link phy params before link training 2024-11-23 23:20:49 +01:00
dsi drm/msm/dsi: Enable runtime PM 2024-11-18 12:13:40 +01:00
edp
hdmi
Kconfig
Makefile
msm_atomic.c
msm_atomic_trace.h
msm_atomic_tracepoints.c
msm_debugfs.c
msm_debugfs.h
msm_drv.c
msm_drv.h
msm_fb.c
msm_fbdev.c
msm_fence.c
msm_fence.h
msm_gem.c
msm_gem.h
msm_gem_prime.c
msm_gem_shrinker.c
msm_gem_submit.c
msm_gem_vma.c
msm_gpu.c
msm_gpu.h
msm_gpu_trace.h
msm_gpu_tracepoints.c
msm_gpummu.c
msm_iommu.c
msm_kms.h
msm_mmu.h
msm_perf.c
msm_rd.c
msm_ringbuffer.c
msm_ringbuffer.h
msm_submitqueue.c
NOTES