drm/amdgpu: Correctly use bo_va->ref_count in compute VMs

This is needed to correctly handle BOs imported into compute VM from gfx.
Both kfd and gfx should use same bo_va and set bo_va->ref_count correctly
when map the Bos into same VM, otherwise we may trigger kernel general
protection when iterate mappings over bo_va's valids or invalids list.

Signed-off-by: Felix Kuehling <[email protected]>
Signed-off-by: Xiaogang Chen <[email protected]>
Acked-by: Christian König <[email protected]>
Reviewed-by: Ramesh Errabolu <[email protected]>
Tested-by: Xiaogang Chen <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

Author: xiaogang-chen-amd

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c

@@ -834,6 +834,7 @@ static int kfd_mem_attach(struct amdgpu_device *adev, struct kgd_mem *mem,
 	uint64_t va = mem->va;
 	struct kfd_mem_attachment *attachment[2] = {NULL, NULL};
 	struct amdgpu_bo *bo[2] = {NULL, NULL};
+	struct amdgpu_bo_va *bo_va;
 	bool same_hive = false;
 	int i, ret;
 
@@ -921,7 +922,12 @@ static int kfd_mem_attach(struct amdgpu_device *adev, struct kgd_mem *mem,
 			pr_debug("Unable to reserve BO during memory attach");
 			goto unwind;
 		}
-		attachment[i]->bo_va = amdgpu_vm_bo_add(adev, vm, bo[i]);
+		bo_va = amdgpu_vm_bo_find(vm, bo[i]);
+		if (!bo_va)
+			bo_va = amdgpu_vm_bo_add(adev, vm, bo[i]);
+		else
+			++bo_va->ref_count;
+		attachment[i]->bo_va = bo_va;
 		amdgpu_bo_unreserve(bo[i]);
 		if (unlikely(!attachment[i]->bo_va)) {
 			ret = -ENOMEM;
@@ -945,7 +951,8 @@ static int kfd_mem_attach(struct amdgpu_device *adev, struct kgd_mem *mem,
 			continue;
 		if (attachment[i]->bo_va) {
 			amdgpu_bo_reserve(bo[i], true);
-			amdgpu_vm_bo_del(adev, attachment[i]->bo_va);
+			if (--attachment[i]->bo_va->ref_count == 0)
+				amdgpu_vm_bo_del(adev, attachment[i]->bo_va);
 			amdgpu_bo_unreserve(bo[i]);
 			list_del(&attachment[i]->list);
 		}
@@ -962,7 +969,8 @@ static void kfd_mem_detach(struct kfd_mem_attachment *attachment)
 
 	pr_debug("\t remove VA 0x%llx in entry %p\n",
 			attachment->va, attachment);
-	amdgpu_vm_bo_del(attachment->adev, attachment->bo_va);
+	if (--attachment->bo_va->ref_count == 0)
+		amdgpu_vm_bo_del(attachment->adev, attachment->bo_va);
 	drm_gem_object_put(&bo->tbo.base);
 	list_del(&attachment->list);
 	kfree(attachment);