SoftwareSerial.cpp diff with ArduinoCore-avr 1.8.3

--- /home/uaa/ArduinoCore-avr/libraries/SoftwareSerial/src/SoftwareSerial.cpp	Sun Jul 19 07:27:55 2020
+++ SoftwareSerial.cpp	Sat Jul 18 05:17:07 2020
@@ -42,8 +42,29 @@ http://arduiniana.org.
 #include <avr/pgmspace.h>
 #include <Arduino.h>
 #include <SoftwareSerial.h>
-#include <util/delay_basic.h>
+// #include <util/delay_basic.h>
+// replace modified _delay_loop_2() for LGT8F328P
+/*
+    Delay loop using a 16-bit counter \c __count, so up to 65536
+    iterations are possible.  (The value 65536 would have to be
+    passed as 0.)  The loop executes four CPU cycles per iteration,
+    not including the overhead the compiler requires to setup the
+    counter register pair.

+    Thus, at a CPU speed of 1 MHz, delays of up to about 262.1
+    milliseconds can be achieved.
+ */
+static void SoftwareSerial::_delay_loop_2(uint16_t __count)
+{
+	__asm__ volatile (
+		"1: sbiw %0,1" "\n\t"
+		"nop" "\n\t"	// LGT8F328P's SBIW takes 1 clock, adjust
+		"brne 1b"
+		: "=w" (__count)
+		: "0" (__count)
+	);
+}
+
 //
 // Statics
 //
@@ -301,6 +322,31 @@ uint16_t SoftwareSerial::subtract_cap(uint16_t num, ui
 // Public methods
 //

+void SoftwareSerial::begin(uint16_t rxcenter, uint16_t  rxintra, uint16_t  rxstop, uint16_t  tx)
+{
+  _rx_delay_centering = _rx_delay_intrabit = _rx_delay_stopbit = 0;
+  _tx_delay = tx;
+
+  // Only setup rx when we have a valid PCINT for this pin
+  if (digitalPinToPCICR((int8_t)_receivePin)) {
+    _rx_delay_centering = rxcenter;
+    _rx_delay_intrabit = rxintra;
+    _rx_delay_stopbit = rxstop;
+
+    *digitalPinToPCICR((int8_t)_receivePin) |= _BV(digitalPinToPCICRbit(_receivePin));
+    _pcint_maskreg = digitalPinToPCMSK(_receivePin);
+    _pcint_maskvalue = _BV(digitalPinToPCMSKbit(_receivePin));
+
+    tunedDelay(_tx_delay); // if we were low this establishes the end
+  }
+
+#if _DEBUG
+  pinMode(_DEBUG_PIN1, OUTPUT);
+  pinMode(_DEBUG_PIN2, OUTPUT);
+#endif
+
+  listen();
+}
 void SoftwareSerial::begin(long speed)
 {
   _rx_delay_centering = _rx_delay_intrabit = _rx_delay_stopbit = _tx_delay = 0;