* [PATCH] drm/amdkfd: pages_addr offset must be 0 for system range
@ 2021-06-04 23:10 Philip Yang
2021-06-04 23:16 ` Felix Kuehling
2021-06-05 10:49 ` Christian König
0 siblings, 2 replies; 3+ messages in thread
From: Philip Yang @ 2021-06-04 23:10 UTC (permalink / raw)
To: amd-gfx, Felix.Kuehling; +Cc: Philip Yang
prange->offset is for VRAM range mm_nodes, if multiple ranges share same
mm_nodes, migrate range back to VRAM will reuse the VRAM at offset of
the same mm_nodes. For system memory pages_addr array, the offset is
always 0, otherwise, update GPU mapping will use incorrect system memory
page, and cause system memory corruption.
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
---
drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index f2901e7a993e..0f18bd0dc64e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -1153,7 +1153,7 @@ svm_range_map_to_gpu(struct amdgpu_device *adev, struct amdgpu_vm *vm,
prange->mapping.start = prange->start;
prange->mapping.last = prange->last;
- prange->mapping.offset = prange->offset;
+ prange->mapping.offset = prange->ttm_res ? prange->offset : 0;
pte_flags = svm_range_get_pte_flags(adev, prange);
r = amdgpu_vm_bo_update_mapping(adev, bo_adev, vm, false, false, NULL,
--
2.17.1
_______________________________________________
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/amdkfd: pages_addr offset must be 0 for system range
2021-06-04 23:10 [PATCH] drm/amdkfd: pages_addr offset must be 0 for system range Philip Yang
@ 2021-06-04 23:16 ` Felix Kuehling
2021-06-05 10:49 ` Christian König
1 sibling, 0 replies; 3+ messages in thread
From: Felix Kuehling @ 2021-06-04 23:16 UTC (permalink / raw)
To: Philip Yang, amd-gfx
Am 2021-06-04 um 7:10 p.m. schrieb Philip Yang:
> prange->offset is for VRAM range mm_nodes, if multiple ranges share same
> mm_nodes, migrate range back to VRAM will reuse the VRAM at offset of
> the same mm_nodes. For system memory pages_addr array, the offset is
> always 0, otherwise, update GPU mapping will use incorrect system memory
> page, and cause system memory corruption.
>
> Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
> ---
> drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
> index f2901e7a993e..0f18bd0dc64e 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
> @@ -1153,7 +1153,7 @@ svm_range_map_to_gpu(struct amdgpu_device *adev, struct amdgpu_vm *vm,
>
> prange->mapping.start = prange->start;
> prange->mapping.last = prange->last;
> - prange->mapping.offset = prange->offset;
> + prange->mapping.offset = prange->ttm_res ? prange->offset : 0;
> pte_flags = svm_range_get_pte_flags(adev, prange);
>
> r = amdgpu_vm_bo_update_mapping(adev, bo_adev, vm, false, false, NULL,
_______________________________________________
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/amdkfd: pages_addr offset must be 0 for system range
2021-06-04 23:10 [PATCH] drm/amdkfd: pages_addr offset must be 0 for system range Philip Yang
2021-06-04 23:16 ` Felix Kuehling
@ 2021-06-05 10:49 ` Christian König
1 sibling, 0 replies; 3+ messages in thread
From: Christian König @ 2021-06-05 10:49 UTC (permalink / raw)
To: Philip Yang, amd-gfx, Felix.Kuehling
Am 05.06.21 um 01:10 schrieb Philip Yang:
> prange->offset is for VRAM range mm_nodes, if multiple ranges share same
> mm_nodes, migrate range back to VRAM will reuse the VRAM at offset of
> the same mm_nodes. For system memory pages_addr array, the offset is
> always 0, otherwise, update GPU mapping will use incorrect system memory
> page, and cause system memory corruption.
Nirmoy and I also stumbled over a similar problem which we are going to
fix inside the VM code instead.
Christian.
>
> Signed-off-by: Philip Yang <Philip.Yang@amd.com>
> ---
> drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
> index f2901e7a993e..0f18bd0dc64e 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
> @@ -1153,7 +1153,7 @@ svm_range_map_to_gpu(struct amdgpu_device *adev, struct amdgpu_vm *vm,
>
> prange->mapping.start = prange->start;
> prange->mapping.last = prange->last;
> - prange->mapping.offset = prange->offset;
> + prange->mapping.offset = prange->ttm_res ? prange->offset : 0;
> pte_flags = svm_range_get_pte_flags(adev, prange);
>
> r = amdgpu_vm_bo_update_mapping(adev, bo_adev, vm, false, false, NULL,
_______________________________________________
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:[~2021-06-05 10:49 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-06-04 23:10 [PATCH] drm/amdkfd: pages_addr offset must be 0 for system range Philip Yang
2021-06-04 23:16 ` Felix Kuehling
2021-06-05 10:49 ` 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.