[PATCH v2 2/3] drm/amdgpu: convert code name to ip version for noretry set

Christian König ckoenig.leichtzumerken at gmail.com
Wed Mar 2 07:46:21 UTC 2022


Am 01.03.22 um 16:24 schrieb Paul Menzel:
> Dear Yifan,
>
>
> Thank you for your patch.
>
> Am 01.03.22 um 16:01 schrieb Yifan Zhang:
>> Use IP version rather than codename for noretry set.
>
> Why?

Why not?

>
>> Signed-off-by: Yifan Zhang <yifan1.zhang at amd.com>
>> ---
>>   drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c | 17 ++++++++---------
>>   1 file changed, 8 insertions(+), 9 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c 
>> b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
>> index ab75e189bc0b..fbc22b7b6315 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
>> @@ -559,14 +559,14 @@ void amdgpu_gmc_noretry_set(struct 
>> amdgpu_device *adev)
>>   {
>>       struct amdgpu_gmc *gmc = &adev->gmc;
>>   -    switch (adev->asic_type) {
>> -    case CHIP_VEGA10:
>> -    case CHIP_VEGA20:
>> -    case CHIP_ARCTURUS:
>> -    case CHIP_ALDEBARAN:
>> -    case CHIP_BEIGE_GOBY:
>> -    case CHIP_YELLOW_CARP:
>> -    case CHIP_RENOIR:
>> +    switch (adev->ip_versions[GC_HWIP][0]) {
>> +    case IP_VERSION(9, 0, 1):
>> +    case IP_VERSION(9, 4, 0):
>> +    case IP_VERSION(9, 4, 1):
>> +    case IP_VERSION(9, 4, 2):
>> +    case IP_VERSION(10, 3, 5):
>> +    case IP_VERSION(10, 3, 3):
>> +    case IP_VERSION(9, 3, 0):
>
> I think, sorting these entries might be useful.
>
> Should the names be added as comments for those not having them 
> memorized?
>
>>           /*
>>            * noretry = 0 will cause kfd page fault tests fail
>>            * for some ASICs, so set default to 1 for these ASICs.
>> @@ -576,7 +576,6 @@ void amdgpu_gmc_noretry_set(struct amdgpu_device 
>> *adev)
>>           else
>>               gmc->noretry = amdgpu_noretry;
>>           break;
>> -    case CHIP_RAVEN:
>
> Why remove this?
>
>>       default:
>>           /* Raven currently has issues with noretry
>>            * regardless of what we decide for other
>
>
> Kind regards,
>
> Paul



More information about the amd-gfx mailing list