#include <stdio.h>
#include <stdlib.h>
#include <sys/mman.h>
#include <unistd.h>
#include <string.h>

typedef unsigned long long cycles_t;
typedef unsigned long long usecs_t;
typedef unsigned long long u64;

#ifdef __x86_64__
#define DECLARE_ARGS(val, low, high)    unsigned long low, high
#define EAX_EDX_VAL(val, low, high)     ((low) | ((u64)(high) << 32))
#define EAX_EDX_ARGS(val, low, high)    "a" (low), "d" (high)
#define EAX_EDX_RET(val, low, high)     "=a" (low), "=d" (high)
#else
#define DECLARE_ARGS(val, low, high)    unsigned long long val
#define EAX_EDX_VAL(val, low, high)     (val)
#define EAX_EDX_ARGS(val, low, high)    "A" (val)
#define EAX_EDX_RET(val, low, high)     "=A" (val)
#endif

static inline unsigned long long __rdtscll(void)
{
        DECLARE_ARGS(val, low, high);

        asm volatile("cpuid; rdtsc" : EAX_EDX_RET(val, low, high));

        return EAX_EDX_VAL(val, low, high);
}

#define rdtscll(val) do { (val) = __rdtscll(); } while (0)

#define NRSYSCALLS 30000
#define NRSLEEPS   100000

void main(int argc, char *argv[])
{
	unsigned long a, b, cycles;
	int i, syscall = 0;
	void *page = malloc(4096);

	if (mlock(page, 4096))
		perror("mlock");
	if (munlock(page, 4096))
		perror("munlock");

	if (argc != 2) {
		printf("usage: %s {idle,syscall}\n", argv[0]);
		exit(1);
	}

        rdtscll(a);

	if (strncmp("idle", argv[1], 4) == 0)
		syscall = 0;
	else if (strncmp("syscall", argv[1], 7) == 0)
		syscall = 1;
	else {
		printf("usage: %s {idle,syscall}\n", argv[0]);
		exit(1);
	}
	
	if (syscall == 1) {
        	for (i = 0; i < NRSYSCALLS; i++) {
			if (mlock(page, 4096))
				perror("mlock");
			if (munlock(page, 4096))
				perror("munlock");
		}
	} else {
        	for (i = 0; i < NRSLEEPS; i++)
		 	usleep(10);
	}

        rdtscll(b);

        cycles = b - a;

	if (syscall == 1)
        	printf("cycles per syscall: %d\n", (b-a)/(NRSYSCALLS*2));
	else
		printf("cycles per idle loop: %d\n", (b-a)/NRSLEEPS);
}