#define _XOPEN_SOURCE 500
#define _GNU_SOURCE
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <fcntl.h>
#include <string.h>
#include <errno.h>
#include <malloc.h>
#include <pthread.h>
#include <asm/unistd.h>

/*
 * A testcase for a race-condition in dm-snapshots.
 *
 * Change "VG" symbol to a volume group name that you are using.
 * The group should be on real disk with NCQ disabled.
 * No virtualization, no network disks, no ramdisk, no pagecache-backed loopback
 * (dm-loop is OK)
 * Use a CFQ disk scheduler on the physical device.
 *
 * You may tune the parameters with this #defines, if you have too fast disk,
 * try increasing number of threads.
 *
 * How does it work:
 *	It creates 10MB logical volume, fills it with a pattern and creates
 *	snapshot.
 *	Then, it spawns 10 threads, and synchronizes them so that the main
 *	thread simultaneously starts writing to the main volume and 10 helper
 *	threads start reading the snapshot.
 *	All the threads run in lockstep, operating on the same block
 *	simultaneously (note the unusual use of 3 rw-locks for maintaining the
 *	lockstep).
 *	The reader threads have much lower I/O priority than the main writing
 *	thread, so that their reads will be submitted, but will eventually wait
 *	until the main thread does its relocate and write. The readers will then
 *	read from the old overwritten area and signal an error.
 */

#define VG		"vg1"
#define LV		"test_lv"
#define LV_SNAP		"test_snap"
#define MEGABYTES	"10"
#define SNAP_MEGABYTES	"11"
#define THREADS		10
#define BS		4096
#define ORIG_PATTERN	'p'
#define NEW_PATTERN	'n'

enum {
	IOPRIO_CLASS_NONE,
	IOPRIO_CLASS_RT,
	IOPRIO_CLASS_BE,
	IOPRIO_CLASS_IDLE,
};

enum {
	IOPRIO_WHO_PROCESS = 1,
	IOPRIO_WHO_PGRP,
	IOPRIO_WHO_USER,
};

#define IOPRIO_CLASS_SHIFT	13

static inline int ioprio_set(int which, int who, int ioprio)
{
	return syscall(__NR_ioprio_set, which, who, ioprio);
}

static inline int ioprio_get(int which, int who)
{
	return syscall(__NR_ioprio_get, which, who);
}

#define PRIO_READER	((IOPRIO_CLASS_IDLE << IOPRIO_CLASS_SHIFT) | 0xff)
#define PRIO_WRITER	(IOPRIO_CLASS_RT << IOPRIO_CLASS_SHIFT)

static void do_cmd(char *cmd, int ign_err)
{
	int r;
	fprintf(stderr, "* %s\n", cmd);
	r = system(cmd);
	if (r) {
		if (r == -1) {
			perror("system");
		} else {
			if (ign_err) return;
			fprintf(stderr, "return code %x\n", r);
		}
		exit(1);
	}
}

static char pattern[BS];

static int h_orig, h_snap;
static int n;
static long long test_of;
static pthread_rwlock_t rw_lock_1;
static pthread_rwlock_t rw_lock_2;
static pthread_rwlock_t rw_lock_3;
static volatile int started = 0;

static void pthread_error(int r)
{
	fprintf(stderr, "pthread_error: %s\n", strerror(r));
	exit(1);
}

static void *test_read(void *of)
{
	int r;
	char *t = memalign(BS, BS);
	if (!t) perror("memalign"), exit(1);
	if ((r = pread(h_snap, t, BS, *(long long *)of)) != BS) {
		fprintf(stderr, "can't read (%d): %s\n", r, strerror(errno));
		exit(1);
	}
	if (memcmp(pattern, t, BS)) {
		int i;
		for (i = 0; i < BS; i++) if (t[i] != pattern[i]) break;
		fprintf(stderr, "!!!! SNAPSHOT VOLUME DAMAGE AT BLOCK OFFSET %llX, BYTE OFFSET %X: %02x != %02x\n", *(long long *)of, i, (unsigned char)t[i], (unsigned char)pattern[i]);
		exit(2);
	}
	free(t);
	return NULL;
}

static void *test_thread(void *_)
{
	int r;
	//fprintf(stderr, "start\n");
	if ((r = ioprio_set(IOPRIO_WHO_PROCESS, 0, PRIO_READER))) perror("ioprio_set"), exit(1);
	if ((r = pthread_rwlock_rdlock(&rw_lock_2))) pthread_error(r);
	started = 1;
	if ((r = ioprio_get(IOPRIO_WHO_PROCESS, 0)) != PRIO_READER) {
		if (r == -1) perror("ioprio_get");
		else fprintf(stderr, "reader priority not set: %x\n", r);
		exit(1);
	}
	again:
	if ((r = pthread_rwlock_rdlock(&rw_lock_1))) pthread_error(r);
	if ((r = pthread_rwlock_unlock(&rw_lock_2))) pthread_error(r);
	if (test_of == -1) {
		if ((r = pthread_rwlock_unlock(&rw_lock_1))) pthread_error(r);
		//fprintf(stderr, "return\n");
		return NULL;
	}
	//fprintf(stderr, "test(%lld)\n", test_of);
	test_read(&test_of);
	if ((r = pthread_rwlock_rdlock(&rw_lock_3))) pthread_error(r);
	if ((r = pthread_rwlock_unlock(&rw_lock_1))) pthread_error(r);
	if ((r = pthread_rwlock_rdlock(&rw_lock_2))) pthread_error(r);
	if ((r = pthread_rwlock_unlock(&rw_lock_3))) pthread_error(r);
	goto again;
}

int main(void)
{
	int i, j, r;
	char *np;
	pthread_t thr[THREADS];

	memset(pattern, ORIG_PATTERN, sizeof pattern);

	do_cmd("lvremove -f "VG"/"LV_SNAP"", 1);
	do_cmd("lvremove -f "VG"/"LV"", 1);
	do_cmd("lvcreate -L "MEGABYTES" -n "LV" "VG"", 0);

	h_orig = open("/dev/mapper/"VG"-"LV"", O_RDWR);
	if (h_orig < 0) perror("open orig"), exit(1);
	n = 0;
	while (write(h_orig, pattern, BS) == BS) {
		n++;
		fprintf(stderr, "creating %llx...\r", (long long)n * BS);
	}
	if (fsync(h_orig)) perror("fsync"), exit(1);
	fprintf(stderr,"\n");
	lseek(h_orig, 0, SEEK_SET);
	close(h_orig);

	do_cmd("lvcreate -L "SNAP_MEGABYTES" -n "LV_SNAP" -s "VG"/"LV"", 0);

	h_orig = open("/dev/mapper/"VG"-"LV"", O_RDWR | O_DIRECT);
	if (h_orig < 0) perror("open orig"), exit(1);

	h_snap = open("/dev/mapper/"VG"-"LV_SNAP"", O_RDONLY | O_DIRECT);
	if (h_snap < 0) perror("open snap"), exit(1);

	if ((r = pthread_rwlock_init(&rw_lock_1, NULL))) pthread_error(r);
	if ((r = pthread_rwlock_init(&rw_lock_2, NULL))) pthread_error(r);
	if ((r = pthread_rwlock_init(&rw_lock_3, NULL))) pthread_error(r);
	if ((r = pthread_rwlock_wrlock(&rw_lock_1))) pthread_error(r);
	if ((r = pthread_rwlock_wrlock(&rw_lock_3))) pthread_error(r);

	if ((r = ioprio_set(IOPRIO_WHO_PROCESS, 0, PRIO_WRITER))) perror("ioprio_set"), exit(1);

	for (j = 0; j < THREADS; j++) {
		if ((r = pthread_create(&thr[j], NULL, test_thread, NULL))) pthread_error(r);
	}
	while (!started) usleep(1000);

	if ((r = ioprio_get(IOPRIO_WHO_PROCESS, 0)) != PRIO_WRITER) {
		if (r == -1) perror("ioprio_get");
		else fprintf(stderr, "writer priority not set: %x\n", r);
		exit(1);
	}

	np = memalign(BS, BS);
	if (!np) perror("memalign"), exit(1);
	memset(np, NEW_PATTERN, BS);
	for (i = 0; i < n; i++) {
		test_of = (off_t)i * BS;
		fprintf(stderr, "testing %llx...\r", test_of);
		if ((r = pthread_rwlock_unlock(&rw_lock_1))) pthread_error(r);
		if (pwrite(h_orig, np, BS, test_of) != BS) {
			fprintf(stderr, "can't write (%d): %s\n", r, strerror(errno));
			exit(1);
		}
		if ((r = pthread_rwlock_wrlock(&rw_lock_2))) pthread_error(r);
		if ((r = pthread_rwlock_unlock(&rw_lock_3))) pthread_error(r);
		if ((r = pthread_rwlock_wrlock(&rw_lock_1))) pthread_error(r);
		if ((r = pthread_rwlock_unlock(&rw_lock_2))) pthread_error(r);
		if ((r = pthread_rwlock_wrlock(&rw_lock_3))) pthread_error(r);
	}
	fprintf(stderr,"\n");

	test_of = -1;
	if ((r = pthread_rwlock_unlock(&rw_lock_1))) pthread_error(r);

	for (j = 0; j < THREADS; j++) {
		if ((r = pthread_join(thr[j], NULL))) pthread_error(r);
	}

	fprintf(stderr, "TEST PASSED OK.\n");

	return 0;
}