Re: [PATCH] drm/amdkfd: Fix NULL pointer error for GC 11.0.1 on mGPU

[Eric Huang]

Ping.

On 2023-01-05 14:28, Eric Huang wrote:

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.hu...@amd.com>
---
  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 9885735f1a30..d4c29e9edf34 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -2179,7 +2179,7 @@ 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 6013f498ea1e..55c2dc48e567 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -231,7 +231,7 @@ 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;
        }