On 5/22/25 5:53 PM, Connor Abbott wrote:
> On Thu, May 22, 2025 at 11:46 AM Konrad Dybcio
> <konrad.dyb...@oss.qualcomm.com> wrote:
>>
>> On 5/21/25 12:28 AM, Connor Abbott wrote:
>>> Calling this packet is necessary when we switch contexts because there
>>> are various pieces of state used by userspace to synchronize between BR
>>> and BV that are persistent across submits and we need to make sure that
>>> they are in a "safe" state when switching contexts. Otherwise a
>>> userspace submission in one context could cause another context to
>>> function incorrectly and hang, effectively a denial of service (although
>>> without leaking data). This was missed during initial a7xx bringup.
>>>
>>> Fixes: af66706accdf ("drm/msm/a6xx: Add skeleton A7xx support")
>>> Signed-off-by: Connor Abbott <cwabbo...@gmail.com>
>>> ---
>>> drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 14 ++++++++++++++
>>> 1 file changed, 14 insertions(+)
>>>
>>> diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
>>> b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
>>> index
>>> 06465bc2d0b4b128cddfcfcaf1fe4252632b6777..f776e9ce43a7cdbb4ef769606ec851909b0c4cdd
>>> 100644
>>> --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
>>> +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
>>> @@ -130,6 +130,20 @@ static void a6xx_set_pagetable(struct a6xx_gpu
>>> *a6xx_gpu,
>>> OUT_RING(ring, lower_32_bits(rbmemptr(ring, fence)));
>>> OUT_RING(ring, upper_32_bits(rbmemptr(ring, fence)));
>>> OUT_RING(ring, submit->seqno - 1);
>>> +
>>> + OUT_PKT7(ring, CP_THREAD_CONTROL, 1);
>>> + OUT_RING(ring, CP_SET_THREAD_BOTH);
>>
>> Downstream does CP_SYNC_THREADS | CP_SET_THREAD_BOTH, fwiw
>>
>> Konrad
>
> Unfortunately the rest of the sequence downstream is slightly
> different so I had to adapt this somewhat. Downstream does this as the
> very first thing whereas we have a CP_SYNC_THREADS | CP_SET_THREAD_BR
> beforehand so the threads are already synced, and there were a few
> other minor differences iirc.
Seems you're right, thanks for confirming!
Konrad
