a650 supports expanded apriv support that allows us to map critical buffers
(ringbuffer and memstore) as as privileged to protect them from corruption.
Signed-off-by: Jordan Crouse
---
drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 6 +-
drivers/gpu/drm/msm/msm_gpu.c | 2 +-
Temporarily disable preemption on a5xx targets pending some improvements
to protect the RPTR shadow from being corrupted.
Signed-off-by: Jordan Crouse
---
drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git
The main a5xx preemption record can be marked as privileged to
protect it from user access but the counters storage needs to be
remain unprivileged. Split the buffers and mark the critical memory
as privileged.
Cc: sta...@vger.kernel.org
Signed-off-by: Jordan Crouse
---
Disable the RPTR shadow across all targets. It will be selectively
re-enabled later for targets that need it.
Signed-off-by: Jordan Crouse
---
drivers/gpu/drm/msm/adreno/a2xx_gpu.c | 5 +
drivers/gpu/drm/msm/adreno/a3xx_gpu.c | 10 +
drivers/gpu/drm/msm/adreno/a4xx_gpu.c |
On Adreno GPUs there is an option to shadow the RPTR register in GPU accessible
memory. The shadow memory allows the kernel driver to query the value of the
RPTR for each ringbuffer even if it is preempted out or if the GPU is turned off
during aggressive power management.
There are risks to
Since commit 9495b7e92f71 ("driver core: platform: Initialize dma_parms
for platform devices"), struct platform_device already provides a
dma_parms structure, so we can save allocating another one.
Also the DMA segment size is simply a size, not a bitmask.
Signed-off-by: Robin Murphy
---
(Including a bunch more emails in the To: that got missed the first time)
Hello everyone!
The X.org board is soliciting proposals to host XDC in 2021. Since
XDC2020 is being held virtually this year, we've decided to host in
either North America or Europe. However, the board is open to other
On Tue, Sep 1, 2020 at 8:41 AM Rob Clark wrote:
>
> From: Rob Clark
>
> This reduces the spam in dmesg when we start hitting the shrinker, and
> replaces it with something we can put on a timeline while profiling or
> debugging system issues.
That is a good solution,
Reviewed-by: Kristian H.