[PATCH 2/2] drm/amdgpu: Use offsets local to VCN in VF

[Lazar, Lijo]

On 3/5/2024 2:24 PM, Christian König wrote:
> 
> 
> Am 05.03.24 um 07:40 schrieb Lijo Lazar:
>> For VCN 4.0.3, use only the local addressing scheme while in VF
>> mode. This includes addressing scheme used for HUB offsets.
>>
>> Signed-off-by: Lijo Lazar <lijo.lazar at amd.com>
>> ---
>>   drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c | 20 +++++++++++++++++++-
>>   1 file changed, 19 insertions(+), 1 deletion(-)
>>
>> diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
>> b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
>> index 7b5ad13b618e..a27f3f260aab 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
>> +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
>> @@ -1381,6 +1381,24 @@ static uint64_t
>> vcn_v4_0_3_unified_ring_get_wptr(struct amdgpu_ring *ring)
>>                       regUVD_RB_WPTR);
>>   }
>>   +static void vcn_v4_0_3_enc_ring_emit_vm_flush(struct amdgpu_ring
>> *ring,
>> +                unsigned int vmid, uint64_t pd_addr)
>> +{
>> +    struct amdgpu_vmhub *hub;
>> +
>> +    /* For VF, only local offsets should be used */
>> +    if (amdgpu_sriov_vf(ring->adev))
>> +        ring->vm_hub = AMDGPU_MMHUB0(0);
> 
> That is clearly a no-go since the vm_hub must be statically and can't be
> changed here.
> 

After HUB allocation, the only usage of this hub pointer is to calculate
use the right offset. We still want VCN to use the right hub, only thing
is register offsets in MMHUB(0) are equal to 'local offsets'.

Thanks,
Lijo

> Regards,
> Christian.
> 
>> +    hub = &ring->adev->vmhub[ring->vm_hub];
>> +
>> +    pd_addr = amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
>> +
>> +    /* wait for reg writes */
>> +    vcn_v2_0_enc_ring_emit_reg_wait(ring, hub->ctx0_ptb_addr_lo32 +
>> +                    vmid * hub->ctx_addr_distance,
>> +                    lower_32_bits(pd_addr), 0xffffffff);
>> +}
>> +
>>   static void vcn_v4_0_3_ring_emit_hdp_flush(struct amdgpu_ring *ring)
>>   {
>>       /* VCN engine access for HDP flush doesn't work when RRMT is
>> enabled.
>> @@ -1443,7 +1461,7 @@ static const struct amdgpu_ring_funcs
>> vcn_v4_0_3_unified_ring_vm_funcs = {
>>       .emit_ib_size = 5, /* vcn_v2_0_enc_ring_emit_ib */
>>       .emit_ib = vcn_v2_0_enc_ring_emit_ib,
>>       .emit_fence = vcn_v2_0_enc_ring_emit_fence,
>> -    .emit_vm_flush = vcn_v2_0_enc_ring_emit_vm_flush,
>> +    .emit_vm_flush = vcn_v4_0_3_enc_ring_emit_vm_flush,
>>       .emit_hdp_flush = vcn_v4_0_3_ring_emit_hdp_flush,
>>       .test_ring = amdgpu_vcn_enc_ring_test_ring,
>>       .test_ib = amdgpu_vcn_unified_ring_test_ib,
>