* [PATCH] drm/amdgpu: disable system memory page tables for now
@ 2019-01-07 13:45 Christian König
[not found] ` <20190107134502.2247-1-christian.koenig-5C7GfCeVMHo@public.gmane.org>
0 siblings, 1 reply; 3+ messages in thread
From: Christian König @ 2019-01-07 13:45 UTC (permalink / raw)
To: amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW
We hit a problem with IOMMU with that. Disable until we have time to
debug further.
Signed-off-by: Christian König <christian.koenig@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 3 ---
1 file changed, 3 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 4cc0d1079935..ccffcadfd73b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -847,9 +847,6 @@ static void amdgpu_vm_bo_param(struct amdgpu_device *adev, struct amdgpu_vm *vm,
bp->size = amdgpu_vm_bo_size(adev, level);
bp->byte_align = AMDGPU_GPU_PAGE_SIZE;
bp->domain = AMDGPU_GEM_DOMAIN_VRAM;
- if (bp->size <= PAGE_SIZE && adev->asic_type >= CHIP_VEGA10 &&
- adev->flags & AMD_IS_APU)
- bp->domain |= AMDGPU_GEM_DOMAIN_GTT;
bp->domain = amdgpu_bo_get_preferred_pin_domain(adev, bp->domain);
bp->flags = AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS |
AMDGPU_GEM_CREATE_CPU_GTT_USWC;
--
2.14.1
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply related [flat|nested] 3+ messages in thread
* Re: [PATCH] drm/amdgpu: disable system memory page tables for now
[not found] ` <20190107134502.2247-1-christian.koenig-5C7GfCeVMHo@public.gmane.org>
@ 2019-01-07 15:03 ` Michel Dänzer
[not found] ` <1c139c39-43b2-5fd9-459c-c2d463629845-otUistvHUpPR7s880joybQ@public.gmane.org>
0 siblings, 1 reply; 3+ messages in thread
From: Michel Dänzer @ 2019-01-07 15:03 UTC (permalink / raw)
To: Christian König; +Cc: amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW
On 2019-01-07 2:45 p.m., Christian König wrote:
> We hit a problem with IOMMU with that. Disable until we have time to
> debug further.
>
> Signed-off-by: Christian König <christian.koenig@amd.com>
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 3 ---
> 1 file changed, 3 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> index 4cc0d1079935..ccffcadfd73b 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> @@ -847,9 +847,6 @@ static void amdgpu_vm_bo_param(struct amdgpu_device *adev, struct amdgpu_vm *vm,
> bp->size = amdgpu_vm_bo_size(adev, level);
> bp->byte_align = AMDGPU_GPU_PAGE_SIZE;
> bp->domain = AMDGPU_GEM_DOMAIN_VRAM;
> - if (bp->size <= PAGE_SIZE && adev->asic_type >= CHIP_VEGA10 &&
> - adev->flags & AMD_IS_APU)
> - bp->domain |= AMDGPU_GEM_DOMAIN_GTT;
> bp->domain = amdgpu_bo_get_preferred_pin_domain(adev, bp->domain);
> bp->flags = AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS |
> AMDGPU_GEM_CREATE_CPU_GTT_USWC;
>
Thanks for taking care of this Christian. Maybe add a reference to at
least one of the bug reports about this, but either way:
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
--
Earthling Michel Dänzer | http://www.amd.com
Libre software enthusiast | Mesa and X developer
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [PATCH] drm/amdgpu: disable system memory page tables for now
[not found] ` <1c139c39-43b2-5fd9-459c-c2d463629845-otUistvHUpPR7s880joybQ@public.gmane.org>
@ 2019-01-07 15:06 ` Christian König
0 siblings, 0 replies; 3+ messages in thread
From: Christian König @ 2019-01-07 15:06 UTC (permalink / raw)
To: Michel Dänzer; +Cc: amd-gfx-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW
Am 07.01.19 um 16:03 schrieb Michel Dänzer:
> On 2019-01-07 2:45 p.m., Christian König wrote:
>> We hit a problem with IOMMU with that. Disable until we have time to
>> debug further.
>>
>> Signed-off-by: Christian König <christian.koenig@amd.com>
>> ---
>> drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 3 ---
>> 1 file changed, 3 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
>> index 4cc0d1079935..ccffcadfd73b 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
>> @@ -847,9 +847,6 @@ static void amdgpu_vm_bo_param(struct amdgpu_device *adev, struct amdgpu_vm *vm,
>> bp->size = amdgpu_vm_bo_size(adev, level);
>> bp->byte_align = AMDGPU_GPU_PAGE_SIZE;
>> bp->domain = AMDGPU_GEM_DOMAIN_VRAM;
>> - if (bp->size <= PAGE_SIZE && adev->asic_type >= CHIP_VEGA10 &&
>> - adev->flags & AMD_IS_APU)
>> - bp->domain |= AMDGPU_GEM_DOMAIN_GTT;
>> bp->domain = amdgpu_bo_get_preferred_pin_domain(adev, bp->domain);
>> bp->flags = AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS |
>> AMDGPU_GEM_CREATE_CPU_GTT_USWC;
>>
> Thanks for taking care of this Christian.
Actually I'm not that happy about this because it seems to point out
either a hardware problem or a software problem in the IOMMU driver.
I just don't have time to investigate further, so disabling it is the
least I can do.
> Maybe add a reference to at
> least one of the bug reports about this, but either way:
>
> Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Thanks,
Christian.
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2019-01-07 15:06 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2019-01-07 13:45 [PATCH] drm/amdgpu: disable system memory page tables for now Christian König
[not found] ` <20190107134502.2247-1-christian.koenig-5C7GfCeVMHo@public.gmane.org>
2019-01-07 15:03 ` Michel Dänzer
[not found] ` <1c139c39-43b2-5fd9-459c-c2d463629845-otUistvHUpPR7s880joybQ@public.gmane.org>
2019-01-07 15:06 ` Christian König
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.