diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 33bbad623e02..0b07ccc7e9bc 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -1237,6 +1237,25 @@ i915_request_await_execution(struct i915_request *rq,
 	return 0;
 }
 
+static int
+await_request_submit(struct i915_request *to, struct i915_request *from)
+{
+	/*
+	 * If we are waiting on a virtual engine, then it may be
+	 * constrained to execute on a single engine *prior* to submission.
+	 * When it is submitted, it will be first submitted to the virtual
+	 * engine and then passed to the physical engine. We cannot allow
+	 * the waiter to be submitted immediately to the physical engine
+	 * as it may then bypass the virtual request.
+	 */
+	if (to->engine == READ_ONCE(from->engine))
+		return i915_sw_fence_await_sw_fence_gfp(&to->submit,
+							&from->submit,
+							I915_FENCE_GFP);
+	else
+		return __i915_request_await_execution(to, from, NULL);
+}
+
 static int
 i915_request_await_request(struct i915_request *to, struct i915_request *from)
 {
@@ -1258,10 +1277,8 @@ i915_request_await_request(struct i915_request *to, struct i915_request *from)
 			return ret;
 	}
 
-	if (to->engine == READ_ONCE(from->engine))
-		ret = i915_sw_fence_await_sw_fence_gfp(&to->submit,
-						       &from->submit,
-						       I915_FENCE_GFP);
+	if (is_power_of_2(to->execution_mask | READ_ONCE(from->execution_mask)))
+		ret = await_request_submit(to, from);
 	else
 		ret = emit_semaphore_wait(to, from, I915_FENCE_GFP);
 	if (ret < 0)