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

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

[Felix Kuehling]

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@amd.com>
---
 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;
-- 
1.9.1

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

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

[Zhang, Jerry (Junwei)]

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@amd.com>

May be better to split it into 2 patches
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>

> ---
>   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;
>
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

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

[Christian König]

Am 28.03.2017 um 03:23 schrieb Zhang, Jerry (Junwei):
>
>
> 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@amd.com>
>
> May be better to split it into 2 patches

Yeah, would be nice to have. But should work this way as well and the 
hardware isn't even public.

> Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>

>
>> ---
>>   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;
>>
> _______________________________________________
> amd-gfx mailing list
> amd-gfx@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/amd-gfx


_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

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

[Felix Kuehling]

[-- Attachment #1: Type: text/plain, Size: 2445 bytes --]


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-5C7GfCeVMHo@public.gmane.org>
>
> May be better to split it into 2 patches
> Reviewed-by: Junwei Zhang <Jerry.Zhang-5C7GfCeVMHo@public.gmane.org>

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;
>>


[-- Attachment #2: 0001-drm-amdgpu-Register-UTCL2-as-a-source-of-VM-faults.patch --]
[-- Type: text/x-patch, Size: 926 bytes --]

>From 9690de839e9ee7f6fc31cd777ffde8770858edb0 Mon Sep 17 00:00:00 2001
From: Felix Kuehling <Felix.Kuehling-5C7GfCeVMHo@public.gmane.org>
Date: Tue, 28 Mar 2017 13:41:11 -0400
Subject: [PATCH 1/2] drm/amdgpu: Register UTCL2 as a source of VM faults

Signed-off-by: Felix Kuehling <Felix.Kuehling-5C7GfCeVMHo@public.gmane.org>
---
 drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 87bea71..981d3d9 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -556,6 +556,8 @@ 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;
-- 
1.9.1


[-- Attachment #3: 0002-drm-amdgpu-Clean-up-GFX-9-VM-fault-messages.patch --]
[-- Type: text/x-patch, Size: 2270 bytes --]

>From 9d47433ae1e799cacab2b002c75fcda41543beed Mon Sep 17 00:00:00 2001
From: Felix Kuehling <Felix.Kuehling-5C7GfCeVMHo@public.gmane.org>
Date: Tue, 28 Mar 2017 13:42:31 -0400
Subject: [PATCH 2/2] drm/amdgpu: Clean up GFX 9 VM fault messages

Clean up the VM fault message format and use rate-limiting similar
to other ASICs.

Signed-off-by: Felix Kuehling <Felix.Kuehling-5C7GfCeVMHo@public.gmane.org>
---
 drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 27 ++++++++++++++-------------
 1 file changed, 14 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 981d3d9..1e4734d 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -131,7 +131,7 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
 {
 	struct amdgpu_vmhub *gfxhub = &adev->vmhub[AMDGPU_GFXHUB];
 	struct amdgpu_vmhub *mmhub = &adev->vmhub[AMDGPU_MMHUB];
-	uint32_t status;
+	uint32_t status = 0;
 	u64 addr;
 
 	addr = (u64)entry->src_data[0] << 12;
@@ -145,19 +145,20 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
 			status = RREG32(gfxhub->vm_l2_pro_fault_status);
 			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);
-	} else {
-		DRM_ERROR("[%s]VMC page fault (src_id:%u ring:%u vm_id:%u pas_id:%u) "
-		  "at page 0x%016llx from %d\n",
-		  entry->vm_id_src ? "mmhub" : "gfxhub",
-		  entry->src_id, entry->ring_id, entry->vm_id, entry->pas_id,
-		  addr, entry->client_id);
+	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);
+		if (!amdgpu_sriov_vf(adev))
+			dev_err(adev->dev,
+				"VM_L2_PROTECTION_FAULT_STATUS:0x%08X\n",
+				status);
 	}
 
 	return 0;
-- 
1.9.1


[-- Attachment #4: Type: text/plain, Size: 154 bytes --]

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

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

[Deucher, Alexander]

> -----Original Message-----
> From: amd-gfx [mailto:amd-gfx-bounces@lists.freedesktop.org] On Behalf
> Of Felix Kuehling
> Sent: Tuesday, March 28, 2017 2:10 PM
> To: Zhang, Jerry; amd-gfx@lists.freedesktop.org
> Subject: Re: [PATCH] drm/amdgpu: Improve Vega10 VM fault handling
> 
> 
> 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@amd.com>
> >
> > May be better to split it into 2 patches
> > Reviewed-by: Junwei Zhang <Jerry.Zhang@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.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>

> 
> 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;
> >>

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

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

[Zhang, Jerry (Junwei)]

On 03/29/2017 02:37 AM, Deucher, Alexander wrote:
>> -----Original Message-----
>> From: amd-gfx [mailto:amd-gfx-bounces@lists.freedesktop.org] On Behalf
>> Of Felix Kuehling
>> Sent: Tuesday, March 28, 2017 2:10 PM
>> To: Zhang, Jerry; amd-gfx@lists.freedesktop.org
>> Subject: Re: [PATCH] drm/amdgpu: Improve Vega10 VM fault handling
>>
>>
>> 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@amd.com>
>> >
>> > May be better to split it into 2 patches
>> > Reviewed-by: Junwei Zhang <Jerry.Zhang@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.
>
> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>

Thanks.

Jerry
>
>>
>> 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;
>> >>
>
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

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

[Felix Kuehling]

Sorry, I pushed it already, just with Alex's R-B.

Thanks,
  Felix


On 17-03-28 09:28 PM, Zhang, Jerry (Junwei) wrote:
> On 03/29/2017 02:37 AM, Deucher, Alexander wrote:
>>> -----Original Message-----
>>> From: amd-gfx [mailto:amd-gfx-bounces@lists.freedesktop.org] On Behalf
>>> Of Felix Kuehling
>>> Sent: Tuesday, March 28, 2017 2:10 PM
>>> To: Zhang, Jerry; amd-gfx@lists.freedesktop.org
>>> Subject: Re: [PATCH] drm/amdgpu: Improve Vega10 VM fault handling
>>>
>>>
>>> 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@amd.com>
>>> >
>>> > May be better to split it into 2 patches
>>> > Reviewed-by: Junwei Zhang <Jerry.Zhang@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.
>>
>> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
> Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
>
> Thanks.
>
> Jerry
>>
>>>
>>> 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;
>>> >>
>>
> _______________________________________________
> amd-gfx mailing list
> amd-gfx@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/amd-gfx

_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

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

[Zhang, Jerry (Junwei)]

On 03/29/2017 09:37 AM, Felix Kuehling wrote:
> Sorry, I pushed it already, just with Alex's R-B.

That's fine.
Take it easy :)

Jerry

>
> Thanks,
>    Felix
>
>
> On 17-03-28 09:28 PM, Zhang, Jerry (Junwei) wrote:
>> On 03/29/2017 02:37 AM, Deucher, Alexander wrote:
>>>> -----Original Message-----
>>>> From: amd-gfx [mailto:amd-gfx-bounces@lists.freedesktop.org] On Behalf
>>>> Of Felix Kuehling
>>>> Sent: Tuesday, March 28, 2017 2:10 PM
>>>> To: Zhang, Jerry; amd-gfx@lists.freedesktop.org
>>>> Subject: Re: [PATCH] drm/amdgpu: Improve Vega10 VM fault handling
>>>>
>>>>
>>>> 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@amd.com>
>>>>>
>>>>> May be better to split it into 2 patches
>>>>> Reviewed-by: Junwei Zhang <Jerry.Zhang@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.
>>>
>>> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
>> Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
>>
>> Thanks.
>>
>> Jerry
>>>
>>>>
>>>> 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;
>>>>>>
>>>
>> _______________________________________________
>> amd-gfx mailing list
>> amd-gfx@lists.freedesktop.org
>> https://lists.freedesktop.org/mailman/listinfo/amd-gfx
>
> _______________________________________________
> amd-gfx mailing list
> amd-gfx@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/amd-gfx
>
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx

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

[Deucher, Alexander]

> -----Original Message-----
> From: amd-gfx [mailto:amd-gfx-bounces@lists.freedesktop.org] On Behalf
> Of Felix Kuehling
> Sent: Monday, March 27, 2017 6:25 PM
> To: amd-gfx@lists.freedesktop.org
> Cc: Kuehling, Felix
> Subject: [PATCH] drm/amdgpu: Improve Vega10 VM fault handling
> 
> 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@amd.com>

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>

> ---
>  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;
> --
> 1.9.1
> 
> _______________________________________________
> amd-gfx mailing list
> amd-gfx@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx