Re: [PATCH 4/4] drm/amdgpu/nv: add navi GPU reset handler

["Sharma, Shashank" <shashank.sharma@amd.com>]

Hey Andrey,
That seems like a good idea, may I know if there is a trigger for STB 
dump ? or is it just the infrastructure which one can use when they feel 
a need to dump info ? Also, how reliable is the STB infra during a reset ?

Regards
Shashank
On 1/24/2022 5:32 PM, Andrey Grodzovsky wrote:
> You probably can add the STB dump we worked on a while ago to your info 
> dump - a reminder
> on the feature is here https://www.spinics.net/lists/amd-gfx/msg70751.html
> 
> Andrey
> 
> On 2022-01-21 15:34, Sharma, Shashank wrote:
>> From 899ec6060eb7d8a3d4d56ab439e4e6cdd74190a4 Mon Sep 17 00:00:00 2001
>> From: Somalapuram Amaranath <Amaranath.Somalapuram@amd.com>
>> Date: Fri, 21 Jan 2022 14:19:42 +0530
>> Subject: [PATCH 4/4] drm/amdgpu/nv: add navi GPU reset handler
>>
>> This patch adds a GPU reset handler for Navi ASIC family, which
>> typically dumps some of the registersand sends a trace event.
>>
>> V2: Accomodated call to work function to send uevent
>>
>> Signed-off-by: Somalapuram Amaranath <Amaranath.Somalapuram@amd.com>
>> Signed-off-by: Shashank Sharma <shashank.sharma@amd.com>
>> ---
>>  drivers/gpu/drm/amd/amdgpu/nv.c | 28 ++++++++++++++++++++++++++++
>>  1 file changed, 28 insertions(+)
>>
>> diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c 
>> b/drivers/gpu/drm/amd/amdgpu/nv.c
>> index 01efda4398e5..ada35d4c5245 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/nv.c
>> +++ b/drivers/gpu/drm/amd/amdgpu/nv.c
>> @@ -528,10 +528,38 @@ nv_asic_reset_method(struct amdgpu_device *adev)
>>      }
>>  }
>>
>> +static void amdgpu_reset_dumps(struct amdgpu_device *adev)
>> +{
>> +    int r = 0, i;
>> +
>> +    /* original raven doesn't have full asic reset */
>> +    if ((adev->apu_flags & AMD_APU_IS_RAVEN) &&
>> +        !(adev->apu_flags & AMD_APU_IS_RAVEN2))
>> +        return;
>> +    for (i = 0; i < adev->num_ip_blocks; i++) {
>> +        if (!adev->ip_blocks[i].status.valid)
>> +            continue;
>> +        if (!adev->ip_blocks[i].version->funcs->reset_reg_dumps)
>> +            continue;
>> +        r = adev->ip_blocks[i].version->funcs->reset_reg_dumps(adev);
>> +
>> +        if (r)
>> +            DRM_ERROR("reset_reg_dumps of IP block <%s> failed %d\n",
>> + adev->ip_blocks[i].version->funcs->name, r);
>> +    }
>> +
>> +    /* Schedule work to send uevent */
>> +    if (!queue_work(system_unbound_wq, &adev->gpu_reset_work))
>> +        DRM_ERROR("failed to add GPU reset work\n");
>> +
>> +    dump_stack();
>> +}
>> +
>>  static int nv_asic_reset(struct amdgpu_device *adev)
>>  {
>>      int ret = 0;
>>
>> +    amdgpu_reset_dumps(adev);
>>      switch (nv_asic_reset_method(adev)) {
>>      case AMD_RESET_METHOD_PCI:
>>          dev_info(adev->dev, "PCI reset\n");