While you're testing patches, can you try this version too?

        Py_UCS4 c = 0, minc = 0x20;
        for (next = end; next < len; next++) {
            c = PyUnicode_READ(kind, buf, next);
            if (c == '"' || c == '\\') {
                break;
            }
            minc = c < minc ? c : minc;
        }
        if (strict && minc <= 0x1f) {
            raise_errmsg("Invalid control character at", pystr, next);
            goto bail;
        }

When we tried this, the conditional expression became a "cmovl" operator which removed 3-4 branches from within the loop entirely, and it was 18% better than the baseline (which has now moved...)