/* gcc -W -Wall -O2 -o portime portime.c */

#include <stdlib.h>
#include <stdio.h>
#include <stdint.h>

#include <sys/io.h>

#define LOOPS 10000

inline uint64_t rdtsc(void)
{
	uint32_t hi, lo;

	asm ("rdtsc": "=d" (hi), "=a" (lo));

	return (uint64_t)hi << 32 | lo;
}

inline void serialize(void)
{
	asm ("cpuid": : : "eax", "ebx", "ecx", "edx");
}

int main(void)
{
	uint64_t tsc0, tsc1, tsc2, tsc3, tsc4;
	uint64_t out, in8, in6;
	int i;

	if (iopl(3) < 0) {
		perror("iopl");
		return EXIT_FAILURE;
	}

	asm ("cli");
	tsc0 = rdtsc();
	for (i = 0; i < LOOPS; i++) {
	 	serialize();	
		serialize();
	}
	tsc1 = rdtsc();
	for (i = 0; i < LOOPS; i++) {
		serialize();
		asm ("outb %al, $0x80");
		serialize();
	}
	tsc2 = rdtsc();
	for (i = 0; i < LOOPS; i++) {
		serialize();
		asm ("inb $0x80, %%al": : : "al");
		serialize();
	}
	tsc3 = rdtsc();
	for (i = 0; i < LOOPS; i++) {
		serialize();
		asm ("inb $0x61, %%al": : : "al");
		serialize();
	}
	tsc4 = rdtsc();
	asm ("sti");

	out = ((tsc2 - tsc1) - (tsc1 - tsc0)) / LOOPS;
	in8 = ((tsc3 - tsc2) - (tsc1 - tsc0)) / LOOPS;
	in6 = ((tsc4 - tsc3) - (tsc1 - tsc0)) / LOOPS;

	printf("out 0x80: %llu cycles\n", out);
	printf("in  0x80: %llu cycles\n", in8);
	printf("in  0x61: %llu cycles\n", in6);

	return EXIT_SUCCESS;
}