[RFC PATCH 4/4] drm/amdgpu: Do bo_va ref counting for KFD BOs

[Felix Kuehling]

This is needed to correctly handle BOs imported into the GEM API, which
would otherwise get added twice to the same VM.

Signed-off-by: Felix Kuehling <felix.kuehl...@amd.com>
---
 .../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c  | 26 +++++++++++++++----
 1 file changed, 21 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c 
b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 6f90ff4b485d..bf90b2fa2738 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -371,8 +371,16 @@ static int amdgpu_amdkfd_bo_validate_and_fence(struct 
amdgpu_bo *bo,
                return ret;
 
        ret = amdgpu_amdkfd_bo_validate(bo, domain, true);
-       if (!ret)
-               amdgpu_bo_fence(bo, fence, true);
+       if (ret)
+               goto unreserve_out;
+
+       ret = dma_resv_reserve_shared(bo->tbo.base.resv, 1);
+       if (ret)
+               goto unreserve_out;
+
+       amdgpu_bo_fence(bo, fence, true);
+
+unreserve_out:
        amdgpu_bo_unreserve(bo);
 
        return ret;
@@ -716,6 +724,7 @@ 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;
        int i, ret;
 
        if (!va) {
@@ -779,7 +788,12 @@ 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;
@@ -803,7 +817,8 @@ 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);
                }
@@ -820,7 +835,8 @@ 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);
-- 
2.32.0