[PATCH AUTOSEL 6.1 36/53] drm/amdkfd: Fix NULL pointer error for GC 11.0.1 on mGPU
From: Sasha Levin
Date: Mon Jan 16 2023 - 09:07:33 EST
From: Eric Huang <jinhuieric.huang@xxxxxxx>
[ Upstream commit a6941f89d7c6a6ba49316bbd7da2fb2f719119a7 ]
The point bo->kfd_bo is NULL for queue's write pointer BO
when creating queue on mGPU. To avoid using the pointer
fixes the error.
Signed-off-by: Eric Huang <jinhuieric.huang@xxxxxxx>
Reviewed-by: Felix Kuehling <Felix.Kuehling@xxxxxxx>
Signed-off-by: Alex Deucher <alexander.deucher@xxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 2 +-
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 29f045079a3e..404c839683b1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -2130,7 +2130,7 @@ int amdgpu_amdkfd_map_gtt_bo_to_gart(struct amdgpu_device *adev, struct amdgpu_b
}
amdgpu_amdkfd_remove_eviction_fence(
- bo, bo->kfd_bo->process_info->eviction_fence);
+ bo, bo->vm_bo->vm->process_info->eviction_fence);
amdgpu_bo_unreserve(bo);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index ecb4c3abc629..c06ada0844ba 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -200,7 +200,7 @@ static int add_queue_mes(struct device_queue_manager *dqm, struct queue *q,
queue_input.wptr_addr = (uint64_t)q->properties.write_ptr;
if (q->wptr_bo) {
- wptr_addr_off = (uint64_t)q->properties.write_ptr - (uint64_t)q->wptr_bo->kfd_bo->va;
+ wptr_addr_off = (uint64_t)q->properties.write_ptr & (PAGE_SIZE - 1);
queue_input.wptr_mc_addr = ((uint64_t)q->wptr_bo->tbo.resource->start << PAGE_SHIFT) + wptr_addr_off;
}
--
2.35.1