drm/amdkfd: Maintain svm_bo reference in page->zone_device_data

Each zone-device page holds a reference to the SVM BO that manages its
backing storage. This is necessary to correctly hold on to the BO in
case zone_device pages are shared with a child-process.

Signed-off-by: Alex Sierra <[email protected]>
Reviewed-by: Felix Kuehling <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

Author: alexsierrag

drivers/gpu/drm/amd/amdkfd/kfd_migrate.c

@@ -218,7 +218,8 @@ svm_migrate_get_vram_page(struct svm_range *prange, unsigned long pfn)
 	struct page *page;
 
 	page = pfn_to_page(pfn);
-	page->zone_device_data = prange;
+	svm_range_bo_ref(prange->svm_bo);
+	page->zone_device_data = prange->svm_bo;
 	get_page(page);
 	lock_page(page);
 }
@@ -502,7 +503,12 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc,
 
 static void svm_migrate_page_free(struct page *page)
 {
-	/* Keep this function to avoid warning */
+	struct svm_range_bo *svm_bo = page->zone_device_data;
+
+	if (svm_bo) {
+		pr_debug("svm_bo ref left: %d\n", kref_read(&svm_bo->kref));
+		svm_range_bo_unref(svm_bo);
+	}
 }
 
 static int

drivers/gpu/drm/amd/amdkfd/kfd_svm.c

@@ -312,14 +312,6 @@ static bool svm_bo_ref_unless_zero(struct svm_range_bo *svm_bo)
 	return true;
 }
 
-static struct svm_range_bo *svm_range_bo_ref(struct svm_range_bo *svm_bo)
-{
-	if (svm_bo)
-		kref_get(&svm_bo->kref);
-
-	return svm_bo;
-}
-
 static void svm_range_bo_release(struct kref *kref)
 {
 	struct svm_range_bo *svm_bo;
@@ -358,7 +350,7 @@ static void svm_range_bo_release(struct kref *kref)
 	kfree(svm_bo);
 }
 
-static void svm_range_bo_unref(struct svm_range_bo *svm_bo)
+void svm_range_bo_unref(struct svm_range_bo *svm_bo)
 {
 	if (!svm_bo)
 		return;

drivers/gpu/drm/amd/amdkfd/kfd_svm.h

@@ -150,6 +150,14 @@ static inline void svm_range_unlock(struct svm_range *prange)
 	mutex_unlock(&prange->lock);
 }
 
+static inline struct svm_range_bo *svm_range_bo_ref(struct svm_range_bo *svm_bo)
+{
+	if (svm_bo)
+		kref_get(&svm_bo->kref);
+
+	return svm_bo;
+}
+
 int svm_range_list_init(struct kfd_process *p);
 void svm_range_list_fini(struct kfd_process *p);
 int svm_ioctl(struct kfd_process *p, enum kfd_ioctl_svm_op op, uint64_t start,
@@ -186,6 +194,7 @@ svm_range_get_pdd_by_adev(struct svm_range *prange, struct amdgpu_device *adev);
  */
 #define KFD_IS_SVM_API_SUPPORTED(dev) ((dev)->pgmap.type != 0)
 
+void svm_range_bo_unref(struct svm_range_bo *svm_bo);
 #else
 
 struct kfd_process;