/* gcc -m32 -O3 -Wall -fomit-frame-pointer -funroll-loops -g  -o time-segops time-segops.c -lrt */
#include <stdio.h>
#include <time.h>
#include <sys/time.h>
#include <errno.h>
#include <string.h>
#include <ctype.h>
#include <asm/unistd.h>

#define GTOD	0
#define SYNC	0
#define COUNT 50000000

/* different glibc's call this different things, so define our own */
struct desc {
	unsigned int  entry_number;
	unsigned long base_addr;
	unsigned int  limit;
	unsigned int  seg_32bit:1;
	unsigned int  contents:2;
	unsigned int  read_exec_only:1;
	unsigned int  limit_in_pages:1;
	unsigned int  seg_not_present:1;
	unsigned int  useable:1;
};

/* These don't seem to be consistently defined in glibc */
static int set_thread_area(struct desc *desc)
{
	int ret;
	asm("int $0x80"
	    : "=a" (ret)
	    : "0" (__NR_set_thread_area), "b" (desc)
	    : "memory");
	if (ret < 0) {
		errno = -ret;
		ret = -1;

	}
	return ret;
}
static int modify_ldt(int func, struct desc *desc, int size)
{
	int ret;
	asm("int $0x80"
	    : "=a" (ret)
	    : "0" (__NR_modify_ldt), "b" (func), "c" (desc), "d" (size)
	    : "memory");
	if (ret < 0) {
		errno = -ret;
		ret = -1;

	}
	return ret;
}

static inline unsigned long long now(void)
{
#if GTOD
	struct timeval tv;
	gettimeofday(&tv, NULL);
	return tv.tv_sec * 1000000000ull + tv.tv_usec * 1000ull;
#else
	struct timespec ts;
	clock_gettime(CLOCK_PROCESS_CPUTIME_ID, &ts);
	return ts.tv_sec * 1000000000ull + ts.tv_nsec;
#endif
}

/* Simulate an exception's effect on the pipeline? */
static inline void sync(void)
{
	if (0) {
		int a,b,c,d;
		asm volatile("cpuid"
			     : "=a" (a), "=b" (b), "=c" (c), "=d" (d)
			     : "0" (0), "2" (0)
			     : "memory");
	} else
		asm volatile("" : : : "memory");
}

static const char *test_none(int seg, int *offset)
{
	int i;

	for(i = 0; i < COUNT; i++) {
		sync();
	}

	return "<none>";
}

static const char *test_fs(int seg, int *offset)
{
	int i;

	for(i = 0; i < COUNT; i++) {
		asm volatile("push %%fs; mov %1, %%fs; addl $1, %%fs:%0; popl %%fs"
			     : "+m" (*offset): "r" (seg) : "memory");
		sync();
	}
	return "fs";
}

static const char *test_gs(int seg, int *offset)
{
	int i;

	for(i = 0; i < COUNT; i++) {
		asm volatile("push %%gs; mov %1, %%gs; addl $1, %%gs:%0; popl %%gs"
			     : "+m" (*offset): "r" (seg) : "memory");
		sync();
	}
	return "gs";
}

typedef const char *(*test_t)(int, int *);

static const test_t tests[] = {
	test_none,
	test_fs,
	test_gs,
	NULL,
};

static int segment[1];


static void test(int seg, int *offset, const char *segdesc)
{
	int i;

	for(i = 0; tests[i]; i++) {
		unsigned long long start, end;
		unsigned long long delta;
		const char *t;

		start = now();
		t = (*tests[i])(seg, offset);
		end = now();

		delta = (end - start);

		printf("   %s with %s selector: %lluns/iteration\n",
		       t, segdesc, delta / COUNT);
	}
}

struct cpu
{
	char modelname[100];
	int family, model, stepping;
	float speed;
};

static int cpu_details(struct cpu *cpu)
{
	FILE *fp = fopen("/proc/cpuinfo", "r");
	char buf[500];

	if (fp == NULL) {
		perror("open /proc/cpuinfo");
		return 0;
	}

	while(fgets(buf, sizeof(buf), fp) != NULL) {
		char *col = strchr(buf, ':');
		char *val;

		if (col == NULL)
			continue;

		val = col+1;
		while(*val == ' ')
			val++;

		col--;
		while(col > buf && isspace(*col))
			col--;
		col[1] = 0;

		col = strchr(val, '\n');
		if (col)
			*col = 0;

		//printf("name=%s val=%s\n", buf, val);

		if (strcmp(buf, "model name") == 0)
			strcpy(cpu->modelname, val);
		if (strcmp(buf, "cpu family") == 0)
			sscanf(val, "%d", &cpu->family);
		if (strcmp(buf, "model") == 0)
			sscanf(val, "%d", &cpu->model);
		if (strcmp(buf, "stepping") == 0)
			sscanf(val, "%d", &cpu->stepping);
		if (strcmp(buf, "cpu MHz") == 0)
			sscanf(val, "%f", &cpu->speed);

		if (strcmp(buf, "processor") == 0 && strcmp(val, "0") != 0)
			break;
	}
	fclose(fp);

	return 1;
}

int main()
{
	int ds, fs, gs;
	static struct desc desc = {
		.entry_number = 1,
		.base_addr = (unsigned long)segment,
		.limit = sizeof(segment)-1,
		.seg_32bit = 1,
		.contents = 0,
		.read_exec_only = 0,
		.limit_in_pages = 0,
		.seg_not_present = 0,
		.useable = 1,
	};
	int gdtseg, ldtseg;
	struct cpu cpu;
	float speed;

	if (!cpu_details(&cpu)) {
		printf("can't read CPU details");
		return 1;
	}
	speed = cpu.speed;


	if (modify_ldt(1, &desc, sizeof(desc)) == -1)
		perror("modify ldt");
	ldtseg = desc.entry_number * 8 | 4 | 3;

	desc.entry_number = -1;
	if (set_thread_area(&desc) == -1)
		perror("set_thread_area");
	gdtseg = desc.entry_number * 8 | 3;

	asm volatile("mov %%ds, %0; "
		     "mov %%fs, %1; "
		     "mov %%gs, %2"
		     : "=r" (ds), "=r" (fs), "=r" (gs) : : "memory");

	printf("\"%s\" @%gMhz (%d,%d,%d):\n",
	       cpu.modelname, cpu.speed, cpu.family, cpu.model, cpu.stepping);
	printf("ds=%x fs=%x gs=%x ldt=%x gdt=%x %s %s\n",
	       ds, fs, gs, ldtseg, gdtseg,
	       GTOD ? "GTOD" : "CPUTIME",
	       SYNC ? "SYNC" : "");

	test(ds, segment, "data");
	printf("\n");
	test(ldtseg, 0, "LDT");
	printf("\n");
	test(gdtseg, 0, "GDT");

	if (cpu_details(&cpu)) {
		if (speed != cpu.speed)
			printf("cpu speed changed %f->%f?! disable CPUFREQ\n",
			       speed, cpu.speed);
	}

	return 0;
}