drm/amdkfd: Release an acquired process vm

For compute vm acquired from amdgpu, vm.pasid is managed
by kfd. Decouple pasid from such vm on process destroy
to avoid duplicate pasid release.

Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

9 files changed, 48 insertions, 1 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index ba0057e94d5e..2a1da3fe2b06 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -172,6 +172,7 @@ int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct kgd_dev *kgd,
 void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev,
 				struct amdgpu_vm *vm);
 void amdgpu_amdkfd_gpuvm_destroy_process_vm(struct kgd_dev *kgd, void *vm);
+void amdgpu_amdkfd_gpuvm_release_process_vm(struct kgd_dev *kgd, void *vm);
 uint32_t amdgpu_amdkfd_gpuvm_get_process_page_dir(void *vm);
 int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
 		struct kgd_dev *kgd, uint64_t va, uint64_t size,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
index ea3f698aef5e..6f0b5267addb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
@@ -205,6 +205,7 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.create_process_vm = amdgpu_amdkfd_gpuvm_create_process_vm,
 	.acquire_process_vm = amdgpu_amdkfd_gpuvm_acquire_process_vm,
 	.destroy_process_vm = amdgpu_amdkfd_gpuvm_destroy_process_vm,
+	.release_process_vm = amdgpu_amdkfd_gpuvm_release_process_vm,
 	.get_process_page_dir = amdgpu_amdkfd_gpuvm_get_process_page_dir,
 	.set_vm_context_page_table_base = set_vm_context_page_table_base,
 	.alloc_memory_of_gpu = amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
index f6e53e9352bd..ea7c18ce7754 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
@@ -164,6 +164,7 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.create_process_vm = amdgpu_amdkfd_gpuvm_create_process_vm,
 	.acquire_process_vm = amdgpu_amdkfd_gpuvm_acquire_process_vm,
 	.destroy_process_vm = amdgpu_amdkfd_gpuvm_destroy_process_vm,
+	.release_process_vm = amdgpu_amdkfd_gpuvm_release_process_vm,
 	.get_process_page_dir = amdgpu_amdkfd_gpuvm_get_process_page_dir,
 	.set_vm_context_page_table_base = set_vm_context_page_table_base,
 	.alloc_memory_of_gpu = amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
index 8efedfcb9dfc..3dc987cab0ea 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
@@ -201,6 +201,7 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.create_process_vm = amdgpu_amdkfd_gpuvm_create_process_vm,
 	.acquire_process_vm = amdgpu_amdkfd_gpuvm_acquire_process_vm,
 	.destroy_process_vm = amdgpu_amdkfd_gpuvm_destroy_process_vm,
+	.release_process_vm = amdgpu_amdkfd_gpuvm_release_process_vm,
 	.get_process_page_dir = amdgpu_amdkfd_gpuvm_get_process_page_dir,
 	.set_vm_context_page_table_base = set_vm_context_page_table_base,
 	.alloc_memory_of_gpu = amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 1cbdd9a7538e..e7ceae05d517 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1114,6 +1114,25 @@ void amdgpu_amdkfd_gpuvm_destroy_process_vm(struct kgd_dev *kgd, void *vm)
 	kfree(vm);
 }
 
+void amdgpu_amdkfd_gpuvm_release_process_vm(struct kgd_dev *kgd, void *vm)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+        struct amdgpu_vm *avm = (struct amdgpu_vm *)vm;
+
+	if (WARN_ON(!kgd || !vm))
+                return;
+
+        pr_debug("Releasing process vm %p\n", vm);
+
+        /* The original pasid of amdgpu vm has already been
+         * released during making a amdgpu vm to a compute vm
+         * The current pasid is managed by kfd and will be
+         * released on kfd process destroy. Set amdgpu pasid
+         * to 0 to avoid duplicate release.
+         */
+	amdgpu_vm_release_compute(adev, avm);
+}
+
 uint32_t amdgpu_amdkfd_gpuvm_get_process_page_dir(void *vm)
 {
 	struct amdgpu_vm *avm = (struct amdgpu_vm *)vm;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 272b7902a25c..23c78af850c6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -2824,6 +2824,26 @@ unreserve_bo:
 }
 
 /**
+ * amdgpu_vm_release_compute - release a compute vm
+ * @adev: amdgpu_device pointer
+ * @vm: a vm turned into compute vm by calling amdgpu_vm_make_compute
+ *
+ * This is a correspondant of amdgpu_vm_make_compute. It decouples compute
+ * pasid from vm. Compute should stop use of vm after this call.
+ */
+void amdgpu_vm_release_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm)
+{
+	if (vm->pasid) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&adev->vm_manager.pasid_lock, flags);
+		idr_remove(&adev->vm_manager.pasid_idr, vm->pasid);
+		spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, flags);
+	}
+	vm->pasid = 0;
+}
+
+/**
  * amdgpu_vm_free_levels - free PD/PT levels
  *
  * @adev: amdgpu device structure
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index 24b02c91ce0c..62116fa44718 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -298,6 +298,7 @@ void amdgpu_vm_manager_fini(struct amdgpu_device *adev);
 int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		   int vm_context, unsigned int pasid);
 int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm, unsigned int pasid);
+void amdgpu_vm_release_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm);
 void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm);
 bool amdgpu_vm_pasid_fault_credit(struct amdgpu_device *adev,
 				  unsigned int pasid);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index a246b8d76c86..0039e451d9af 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -322,8 +322,10 @@ static void kfd_process_destroy_pdds(struct kfd_process *p)
 		pr_debug("Releasing pdd (topology id %d) for process (pasid %d)\n",
 				pdd->dev->id, p->pasid);
 
-		if (pdd->drm_file)
+		if (pdd->drm_file) {
+			pdd->dev->kfd2kgd->release_process_vm(pdd->dev->kgd, pdd->vm);
 			fput(pdd->drm_file);
+		}
 		else if (pdd->vm)
 			pdd->dev->kfd2kgd->destroy_process_vm(
 				pdd->dev->kgd, pdd->vm);
diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
index 4b9981351bb3..814576f6ca1c 100644
--- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
@@ -378,6 +378,7 @@ struct kfd2kgd_calls {
 			unsigned int pasid, void **vm, void **process_info,
 			struct dma_fence **ef);
 	void (*destroy_process_vm)(struct kgd_dev *kgd, void *vm);
+	void (*release_process_vm)(struct kgd_dev *kgd, void *vm);
 	uint32_t (*get_process_page_dir)(void *vm);
 	void (*set_vm_context_page_table_base)(struct kgd_dev *kgd,
 			uint32_t vmid, uint32_t page_table_base);