2 files changed, 32 insertions, 34 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 208812512..7fa5e70f1 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -380,14 +380,9 @@ static void svm_range_bo_release(struct kref *kref)
 		spin_lock(&svm_bo->list_lock);
 	}
 	spin_unlock(&svm_bo->list_lock);
-	if (!dma_fence_is_signaled(&svm_bo->eviction_fence->base)) {
-		/* We're not in the eviction worker.
-		 * Signal the fence and synchronize with any
-		 * pending eviction work.
-		 */
+	if (!dma_fence_is_signaled(&svm_bo->eviction_fence->base))
+		/* We're not in the eviction worker. Signal the fence. */
 		dma_fence_signal(&svm_bo->eviction_fence->base);
-		cancel_work_sync(&svm_bo->eviction_work);
-	}
 	dma_fence_put(&svm_bo->eviction_fence->base);
 	amdgpu_bo_unref(&svm_bo->bo);
 	kfree(svm_bo);
@@ -2246,8 +2241,10 @@ retry:
 		mutex_unlock(&svms->lock);
 		mmap_write_unlock(mm);
 
-		/* Pairs with mmget in svm_range_add_list_work */
-		mmput(mm);
+		/* Pairs with mmget in svm_range_add_list_work. If dropping the
+		 * last mm refcount, schedule release work to avoid circular locking
+		 */
+		mmput_async(mm);
 
 		spin_lock(&svms->deferred_list_lock);
 	}
@@ -2556,6 +2553,7 @@ svm_range_get_range_boundaries(struct kfd_process *p, int64_t addr,
 {
 	struct vm_area_struct *vma;
 	struct interval_tree_node *node;
+	struct rb_node *rb_node;
 	unsigned long start_limit, end_limit;
 
 	vma = find_vma(p->mm, addr << PAGE_SHIFT);
@@ -2578,16 +2576,15 @@ svm_range_get_range_boundaries(struct kfd_process *p, int64_t addr,
 	if (node) {
 		end_limit = min(end_limit, node->start);
 		/* Last range that ends before the fault address */
-		node = container_of(rb_prev(&node->rb),
-				    struct interval_tree_node, rb);
+		rb_node = rb_prev(&node->rb);
 	} else {
 		/* Last range must end before addr because
 		 * there was no range after addr
 		 */
-		node = container_of(rb_last(&p->svms.objects.rb_root),
-				    struct interval_tree_node, rb);
+		rb_node = rb_last(&p->svms.objects.rb_root);
 	}
-	if (node) {
+	if (rb_node) {
+		node = container_of(rb_node, struct interval_tree_node, rb);
 		if (node->last >= addr) {
 			WARN(1, "Overlap with prev node and page fault addr\n");
 			return -EFAULT;
@@ -3310,13 +3307,14 @@ svm_range_trigger_migration(struct mm_struct *mm, struct svm_range *prange,
 
 int svm_range_schedule_evict_svm_bo(struct amdgpu_amdkfd_fence *fence)
 {
-	if (!fence)
-		return -EINVAL;
-
-	if (dma_fence_is_signaled(&fence->base))
-		return 0;
-
-	if (fence->svm_bo) {
+	/* Dereferencing fence->svm_bo is safe here because the fence hasn't
+	 * signaled yet and we're under the protection of the fence->lock.
+	 * After the fence is signaled in svm_range_bo_release, we cannot get
+	 * here any more.
+	 *
+	 * Reference is dropped in svm_range_evict_svm_bo_worker.
+	 */
+	if (svm_bo_ref_unless_zero(fence->svm_bo)) {
 		WRITE_ONCE(fence->svm_bo->evicting, 1);
 		schedule_work(&fence->svm_bo->eviction_work);
 	}
@@ -3331,8 +3329,6 @@ static void svm_range_evict_svm_bo_worker(struct work_struct *work)
 	int r = 0;
 
 	svm_bo = container_of(work, struct svm_range_bo, eviction_work);
-	if (!svm_bo_ref_unless_zero(svm_bo))
-		return; /* svm_bo was freed while eviction was pending */
 
 	if (mmget_not_zero(svm_bo->eviction_fence->mm)) {
 		mm = svm_bo->eviction_fence->mm;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index 705d9e91b..029916971 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -1513,17 +1513,19 @@ static int kfd_add_peer_prop(struct kfd_topology_device *kdev,
 		/* CPU->CPU  link*/
 		cpu_dev = kfd_topology_device_by_proximity_domain(iolink1->node_to);
 		if (cpu_dev) {
-			list_for_each_entry(iolink3, &cpu_dev->io_link_props, list)
-				if (iolink3->node_to == iolink2->node_to)
-					break;
-
-			props->weight += iolink3->weight;
-			props->min_latency += iolink3->min_latency;
-			props->max_latency += iolink3->max_latency;
-			props->min_bandwidth = min(props->min_bandwidth,
-							iolink3->min_bandwidth);
-			props->max_bandwidth = min(props->max_bandwidth,
-							iolink3->max_bandwidth);
+			list_for_each_entry(iolink3, &cpu_dev->io_link_props, list) {
+				if (iolink3->node_to != iolink2->node_to)
+					continue;
+
+				props->weight += iolink3->weight;
+				props->min_latency += iolink3->min_latency;
+				props->max_latency += iolink3->max_latency;
+				props->min_bandwidth = min(props->min_bandwidth,
+							   iolink3->min_bandwidth);
+				props->max_bandwidth = min(props->max_bandwidth,
+							   iolink3->max_bandwidth);
+				break;
+			}
 		} else {
 			WARN(1, "CPU node not found");
 		}