[PATCH] drm/amdgpu: Improve Vega10 VM fault handling

[Felix Kuehling]

On 17-03-27 09:23 PM, Zhang, Jerry (Junwei) wrote:
>
>
> On 03/28/2017 06:25 AM, Felix Kuehling wrote:
>> Register AMDGPU_IH_CLIENTID_UTCL2 as a source of VM faults. Clean
>> up the VM fault message format and use rate-limiting similar to
>> other ASICs.
>>
>> Signed-off-by: Felix Kuehling <Felix.Kuehling at amd.com>
>
> May be better to split it into 2 patches
> Reviewed-by: Junwei Zhang <Jerry.Zhang at amd.com>

I had to rebase my patch and had to resolve a conflict with an SRIOV
change that just landed. So I split it into two commits while I was at
it. Please review the attached patches.

Thanks,
  Felix


>
>> ---
>>   drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 19 +++++++++++++------
>>   1 file changed, 13 insertions(+), 6 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
>> b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
>> index 232c208..9831025 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
>> +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
>> @@ -145,12 +145,17 @@ static int gmc_v9_0_process_interrupt(struct
>> amdgpu_device *adev,
>>           WREG32_P(gfxhub->vm_l2_pro_fault_cntl, 1, ~1);
>>       }
>>
>> -    DRM_ERROR("[%s]VMC page fault (src_id:%u ring:%u vm_id:%u
>> pas_id:%u) "
>> -          "at page 0x%016llx from %d\n"
>> -          "VM_L2_PROTECTION_FAULT_STATUS:0x%08X\n",
>> -          entry->vm_id_src ? "mmhub" : "gfxhub",
>> -          entry->src_id, entry->ring_id, entry->vm_id, entry->pas_id,
>> -          addr, entry->client_id, status);
>> +    if (printk_ratelimit()) {
>> +        dev_err(adev->dev,
>> +            "[%s] VMC page fault (src_id:%u ring:%u vm_id:%u
>> pas_id:%u)\n",
>> +            entry->vm_id_src ? "mmhub" : "gfxhub",
>> +            entry->src_id, entry->ring_id, entry->vm_id,
>> +            entry->pas_id);
>> +        dev_err(adev->dev, "  at page 0x%016llx from %d\n",
>> +            addr, entry->client_id);
>> +        dev_err(adev->dev, "VM_L2_PROTECTION_FAULT_STATUS:0x%08X\n",
>> +            status);
>> +    }
>>
>>       return 0;
>>   }
>> @@ -539,6 +544,8 @@ static int gmc_v9_0_sw_init(void *handle)
>>       /* This interrupt is VMC page fault.*/
>>       r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_VMC, 0,
>>                   &adev->mc.vm_fault);
>> +    r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_UTCL2, 0,
>> +                &adev->mc.vm_fault);
>>
>>       if (r)
>>           return r;
>>

-------------- next part --------------
A non-text attachment was scrubbed...
Name: 0001-drm-amdgpu-Register-UTCL2-as-a-source-of-VM-faults.patch
Type: text/x-patch
Size: 884 bytes
Desc: not available
URL: <https://lists.freedesktop.org/archives/amd-gfx/attachments/20170328/a75270e2/attachment.bin>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: 0002-drm-amdgpu-Clean-up-GFX-9-VM-fault-messages.patch
Type: text/x-patch
Size: 2228 bytes
Desc: not available
URL: <https://lists.freedesktop.org/archives/amd-gfx/attachments/20170328/a75270e2/attachment-0001.bin>