Teensy 2 - Serial1.write() - maybe bypass queue

Add same speedup from Arduino core, that on Serial1.write, check to see
if output queue is empty and data register empty, if so simply stuff the
character out in the output queue, without needing to use interrupt to
start transmission.  Helps speed up fast IO like 1MBS

Also, changed how UCSR1B is updated, to be like Arduino.  In particular
it turns on and off specific bit(s) instead of complete set of register.
Needed if you wish to emulate half duplex with this uart.

teensy/HardwareSerial.cpp

 #include <avr/interrupt.h>
 #include "core_pins.h"
 #include "HardwareSerial.h"
+#include "wiring_private.h" 
 
 #define RX_BUFFER_SIZE 64
 static volatile uint8_t rx_buffer[RX_BUFFER_SIZE];
 	if (tx_enable_pin < 255 && !transmitting) {
 		digitalWrite(tx_enable_pin, HIGH);
 	}
+	// If the buffer and the data register is empty, just write the byte
+	// to the data register and be done. This shortcut helps
+	// significantly improve the effective datarate at high (>
+	// 500kbit/s) bitrates, where interrupt overhead becomes a slowdown.
+	if (tx_buffer_head == tx_buffer_tail && bit_is_set(UCSR1A, UDRE1)) {
+		UDR1 = c;
+		transmitting = 1;
+		return 1;
+	}
+
 	i = tx_buffer_head + 1;
 	if (i >= TX_BUFFER_SIZE) i = 0;
 	while (tx_buffer_tail == i) ; // wait until space in buffer
 	tx_buffer[i] = c;
 	transmitting = 1;
 	tx_buffer_head = i;
-	UCSR1B = (1<<RXEN1) | (1<<TXCIE1) | (1<<TXEN1) | (1<<RXCIE1) | (1<<UDRIE1);
+	//UCSR1B = (1<<RXEN1) | (1<<TXCIE1) | (1<<TXEN1) | (1<<RXCIE1) | (1<<UDRIE1);
+	sbi(UCSR1B, UDRIE1);
+
 #if ARDUINO >= 100
 	return 1;
 #endif
 
 	if (tx_buffer_head == tx_buffer_tail) {
 		// buffer is empty, disable transmit interrupt
-		UCSR1B = (1<<RXEN1) | (1<<TXCIE1) | (1<<TXEN1) | (1<<RXCIE1);
+		//UCSR1B = (1<<RXEN1) | (1<<TXCIE1) | (1<<TXEN1) | (1<<RXCIE1);
+		cbi(UCSR1B, UDRIE1);
 	} else {
 		i = tx_buffer_tail + 1;
 		if (i >= TX_BUFFER_SIZE) i = 0;