[PATCH v2 2/2] drm/amdkfd: heavy-weight flush TLB after unmap

[Philip Yang]

Need do a heavy-weight TLB flush to make sure we have no more dirty data
in the cache for the unmapped pages.

Define enum TLB_FLUSH_TYPE, add flush_type parameter to
amdgpu_amdkfd_flush_gpu_tlb_pasid.

Signed-off-by: Philip Yang <Philip.Yang at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 4 ++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h | 9 ++++++++-
 drivers/gpu/drm/amd/amdkfd/kfd_process.c   | 2 +-
 drivers/gpu/drm/amd/amdkfd/kfd_svm.c       | 4 ++--
 4 files changed, 13 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 5f6696a3c778..bfab2f9fdd17 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -670,10 +670,10 @@ int amdgpu_amdkfd_flush_gpu_tlb_vmid(struct kgd_dev *kgd, uint16_t vmid)
 	return 0;
 }
 
-int amdgpu_amdkfd_flush_gpu_tlb_pasid(struct kgd_dev *kgd, uint16_t pasid)
+int amdgpu_amdkfd_flush_gpu_tlb_pasid(struct kgd_dev *kgd, uint16_t pasid,
+				      enum TLB_FLUSH_TYPE flush_type)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
-	const uint32_t flush_type = 0;
 	bool all_hub = false;
 
 	if (adev->family == AMDGPU_FAMILY_AI)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 313ee49b9f17..f4de50de359b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -36,6 +36,12 @@
 
 extern uint64_t amdgpu_amdkfd_total_mem_size;
 
+enum TLB_FLUSH_TYPE {
+	TLB_FLUSH_LEGACY = 0,
+	TLB_FLUSH_LIGHTWEIGHT,
+	TLB_FLUSH_HEAVYWEIGHT
+};
+
 struct amdgpu_device;
 
 struct kfd_bo_va_list {
@@ -135,7 +141,8 @@ int amdgpu_amdkfd_submit_ib(struct kgd_dev *kgd, enum kgd_engine_type engine,
 void amdgpu_amdkfd_set_compute_idle(struct kgd_dev *kgd, bool idle);
 bool amdgpu_amdkfd_have_atomics_support(struct kgd_dev *kgd);
 int amdgpu_amdkfd_flush_gpu_tlb_vmid(struct kgd_dev *kgd, uint16_t vmid);
-int amdgpu_amdkfd_flush_gpu_tlb_pasid(struct kgd_dev *kgd, uint16_t pasid);
+int amdgpu_amdkfd_flush_gpu_tlb_pasid(struct kgd_dev *kgd, uint16_t pasid,
+				      enum TLB_FLUSH_TYPE flush_type);
 
 bool amdgpu_amdkfd_is_kfd_vmid(struct amdgpu_device *adev, u32 vmid);
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 9d4f527bda7c..5b6c5669c03d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -1853,7 +1853,7 @@ void kfd_flush_tlb(struct kfd_process_device *pdd)
 							pdd->qpd.vmid);
 	} else {
 		amdgpu_amdkfd_flush_gpu_tlb_pasid(dev->kgd,
-						pdd->process->pasid);
+					pdd->process->pasid, TLB_FLUSH_LEGACY);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index a52e4594785f..f2901e7a993e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -1127,7 +1127,7 @@ svm_range_unmap_from_gpus(struct svm_range *prange, unsigned long start,
 				break;
 		}
 		amdgpu_amdkfd_flush_gpu_tlb_pasid((struct kgd_dev *)adev,
-						  p->pasid);
+					p->pasid, TLB_FLUSH_HEAVYWEIGHT);
 	}
 
 	return r;
@@ -1183,7 +1183,7 @@ svm_range_map_to_gpu(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 
 		p = container_of(prange->svms, struct kfd_process, svms);
 		amdgpu_amdkfd_flush_gpu_tlb_pasid((struct kgd_dev *)adev,
-						  p->pasid);
+						p->pasid, TLB_FLUSH_LEGACY);
 	}
 out:
 	prange->mapping.bo_va = NULL;
-- 
2.17.1