[PATCH] drm/amdgpu: Unmap CSA under SR-IOV in KFD path

Trigger Huang Trigger.Huang at amd.com
Sun Apr 28 10:25:15 UTC 2019


In amdgpu open path, CSA will be mappened in VM, so when opening
KFD, calling mdgpu_vm_make_compute  will fail because it found this
VM is not a clean VM with some mappings, as a result, it will lead
to failed to create process VM object

The fix is try to unmap CSA, and actually CSA is not needed in
compute VF world switch

Signed-off-by: Trigger Huang <Trigger.Huang at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 10 ++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c          |  2 +-
 2 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 697b8ef..e0bc457 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -956,6 +956,16 @@ int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct kgd_dev *kgd,
 	if (avm->process_info)
 		return -EINVAL;
 
+	/* Delete CSA mapping to make sure this VM is a clean VM  before
+	 *  converting VM
+	 */
+	if (amdgpu_sriov_vf(adev) && drv_priv->csa_va) {
+		amdgpu_bo_reserve(adev->virt.csa_obj, true);
+		amdgpu_vm_bo_rmv(adev, drv_priv->csa_va);
+		drv_priv->csa_va = NULL;
+		amdgpu_bo_unreserve(adev->virt.csa_obj);
+	}
+
 	/* Convert VM into a compute VM */
 	ret = amdgpu_vm_make_compute(adev, avm, pasid);
 	if (ret)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index da7b4fe..361c2e5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -1069,7 +1069,7 @@ void amdgpu_driver_postclose_kms(struct drm_device *dev,
 
 	amdgpu_vm_bo_rmv(adev, fpriv->prt_va);
 
-	if (amdgpu_sriov_vf(adev)) {
+	if (amdgpu_sriov_vf(adev) && fpriv->csa_va) {
 		/* TODO: how to handle reserve failure */
 		BUG_ON(amdgpu_bo_reserve(adev->virt.csa_obj, true));
 		amdgpu_vm_bo_rmv(adev, fpriv->csa_va);
-- 
2.7.4



More information about the amd-gfx mailing list