drm/amdkfd: support concurrent userptr update for HMM

Userptr restore may have concurrent userptr invalidation after
hmm_vma_fault adds the range to the hmm->ranges list, needs call
hmm_vma_range_done to remove the range from hmm->ranges list first,
then reschedule the restore worker. Otherwise hmm_vma_fault will add
same range to the list, this will cause loop in the list because
range->next point to range itself.

Add function untrack_invalid_user_pages to reduce code duplication.

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

1 files changed, 19 insertions, 6 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 9142a355da28..e1cae4a37113 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1737,6 +1737,23 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info,
 	return 0;
 }
 
+/* Remove invalid userptr BOs from hmm track list
+ *
+ * Stop HMM track the userptr update
+ */
+static void untrack_invalid_user_pages(struct amdkfd_process_info *process_info)
+{
+	struct kgd_mem *mem, *tmp_mem;
+	struct amdgpu_bo *bo;
+
+	list_for_each_entry_safe(mem, tmp_mem,
+				 &process_info->userptr_inval_list,
+				 validate_list.head) {
+		bo = mem->bo;
+		amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm);
+	}
+}
+
 /* Validate invalid userptr BOs
  *
  * Validates BOs on the userptr_inval_list, and moves them back to the
@@ -1854,12 +1871,6 @@ unreserve_out:
 out_free:
 	kfree(pd_bo_list_entries);
 out_no_mem:
-	list_for_each_entry_safe(mem, tmp_mem,
-				 &process_info->userptr_inval_list,
-				 validate_list.head) {
-		bo = mem->bo;
-		amdgpu_ttm_tt_get_user_pages_done(bo->tbo.ttm);
-	}
 
 	return ret;
 }
@@ -1924,7 +1935,9 @@ static void amdgpu_amdkfd_restore_userptr_worker(struct work_struct *work)
 		 * hanging. No point trying again.
 		 */
 	}
+
 unlock_out:
+	untrack_invalid_user_pages(process_info);
 	mutex_unlock(&process_info->lock);
 	mmput(mm);
 	put_task_struct(usertask);