dm-delay.c 8.0 KB
Newer Older
H
Heinz Mauelshagen 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15
/*
 * Copyright (C) 2005-2007 Red Hat GmbH
 *
 * A target that delays reads and/or writes and can send
 * them to different devices.
 *
 * This file is released under the GPL.
 */

#include <linux/module.h>
#include <linux/init.h>
#include <linux/blkdev.h>
#include <linux/bio.h>
#include <linux/slab.h>

16 17
#include <linux/device-mapper.h>

H
Heinz Mauelshagen 已提交
18 19 20 21
#define DM_MSG_PREFIX "delay"

struct delay_c {
	struct timer_list delay_timer;
A
Alasdair G Kergon 已提交
22
	struct mutex timer_lock;
H
Heinz Mauelshagen 已提交
23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38
	struct work_struct flush_expired_bios;
	struct list_head delayed_bios;
	atomic_t may_delay;
	mempool_t *delayed_pool;

	struct dm_dev *dev_read;
	sector_t start_read;
	unsigned read_delay;
	unsigned reads;

	struct dm_dev *dev_write;
	sector_t start_write;
	unsigned write_delay;
	unsigned writes;
};

A
Alasdair G Kergon 已提交
39
struct dm_delay_info {
H
Heinz Mauelshagen 已提交
40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59
	struct delay_c *context;
	struct list_head list;
	struct bio *bio;
	unsigned long expires;
};

static DEFINE_MUTEX(delayed_bios_lock);

static struct workqueue_struct *kdelayd_wq;
static struct kmem_cache *delayed_cache;

static void handle_delayed_timer(unsigned long data)
{
	struct delay_c *dc = (struct delay_c *)data;

	queue_work(kdelayd_wq, &dc->flush_expired_bios);
}

static void queue_timeout(struct delay_c *dc, unsigned long expires)
{
A
Alasdair G Kergon 已提交
60
	mutex_lock(&dc->timer_lock);
H
Heinz Mauelshagen 已提交
61 62 63 64

	if (!timer_pending(&dc->delay_timer) || expires < dc->delay_timer.expires)
		mod_timer(&dc->delay_timer, expires);

A
Alasdair G Kergon 已提交
65
	mutex_unlock(&dc->timer_lock);
H
Heinz Mauelshagen 已提交
66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81
}

static void flush_bios(struct bio *bio)
{
	struct bio *n;

	while (bio) {
		n = bio->bi_next;
		bio->bi_next = NULL;
		generic_make_request(bio);
		bio = n;
	}
}

static struct bio *flush_delayed_bios(struct delay_c *dc, int flush_all)
{
A
Alasdair G Kergon 已提交
82
	struct dm_delay_info *delayed, *next;
H
Heinz Mauelshagen 已提交
83 84
	unsigned long next_expires = 0;
	int start_timer = 0;
A
Alasdair G Kergon 已提交
85
	struct bio_list flush_bios = { };
H
Heinz Mauelshagen 已提交
86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164

	mutex_lock(&delayed_bios_lock);
	list_for_each_entry_safe(delayed, next, &dc->delayed_bios, list) {
		if (flush_all || time_after_eq(jiffies, delayed->expires)) {
			list_del(&delayed->list);
			bio_list_add(&flush_bios, delayed->bio);
			if ((bio_data_dir(delayed->bio) == WRITE))
				delayed->context->writes--;
			else
				delayed->context->reads--;
			mempool_free(delayed, dc->delayed_pool);
			continue;
		}

		if (!start_timer) {
			start_timer = 1;
			next_expires = delayed->expires;
		} else
			next_expires = min(next_expires, delayed->expires);
	}

	mutex_unlock(&delayed_bios_lock);

	if (start_timer)
		queue_timeout(dc, next_expires);

	return bio_list_get(&flush_bios);
}

static void flush_expired_bios(struct work_struct *work)
{
	struct delay_c *dc;

	dc = container_of(work, struct delay_c, flush_expired_bios);
	flush_bios(flush_delayed_bios(dc, 0));
}

/*
 * Mapping parameters:
 *    <device> <offset> <delay> [<write_device> <write_offset> <write_delay>]
 *
 * With separate write parameters, the first set is only used for reads.
 * Delays are specified in milliseconds.
 */
static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
{
	struct delay_c *dc;
	unsigned long long tmpll;

	if (argc != 3 && argc != 6) {
		ti->error = "requires exactly 3 or 6 arguments";
		return -EINVAL;
	}

	dc = kmalloc(sizeof(*dc), GFP_KERNEL);
	if (!dc) {
		ti->error = "Cannot allocate context";
		return -ENOMEM;
	}

	dc->reads = dc->writes = 0;

	if (sscanf(argv[1], "%llu", &tmpll) != 1) {
		ti->error = "Invalid device sector";
		goto bad;
	}
	dc->start_read = tmpll;

	if (sscanf(argv[2], "%u", &dc->read_delay) != 1) {
		ti->error = "Invalid delay";
		goto bad;
	}

	if (dm_get_device(ti, argv[0], dc->start_read, ti->len,
			  dm_table_get_mode(ti->table), &dc->dev_read)) {
		ti->error = "Device lookup failed";
		goto bad;
	}

D
Dmitry Monakhov 已提交
165 166
	dc->dev_write = NULL;
	if (argc == 3)
H
Heinz Mauelshagen 已提交
167 168 169 170
		goto out;

	if (sscanf(argv[4], "%llu", &tmpll) != 1) {
		ti->error = "Invalid write device sector";
D
Dmitry Monakhov 已提交
171
		goto bad_dev_read;
H
Heinz Mauelshagen 已提交
172 173 174 175 176
	}
	dc->start_write = tmpll;

	if (sscanf(argv[5], "%u", &dc->write_delay) != 1) {
		ti->error = "Invalid write delay";
D
Dmitry Monakhov 已提交
177
		goto bad_dev_read;
H
Heinz Mauelshagen 已提交
178 179 180 181 182
	}

	if (dm_get_device(ti, argv[3], dc->start_write, ti->len,
			  dm_table_get_mode(ti->table), &dc->dev_write)) {
		ti->error = "Write device lookup failed";
D
Dmitry Monakhov 已提交
183
		goto bad_dev_read;
H
Heinz Mauelshagen 已提交
184 185 186 187 188 189
	}

out:
	dc->delayed_pool = mempool_create_slab_pool(128, delayed_cache);
	if (!dc->delayed_pool) {
		DMERR("Couldn't create delayed bio pool.");
D
Dmitry Monakhov 已提交
190
		goto bad_dev_write;
H
Heinz Mauelshagen 已提交
191 192
	}

A
Alasdair G Kergon 已提交
193
	setup_timer(&dc->delay_timer, handle_delayed_timer, (unsigned long)dc);
H
Heinz Mauelshagen 已提交
194 195 196

	INIT_WORK(&dc->flush_expired_bios, flush_expired_bios);
	INIT_LIST_HEAD(&dc->delayed_bios);
A
Alasdair G Kergon 已提交
197
	mutex_init(&dc->timer_lock);
H
Heinz Mauelshagen 已提交
198 199
	atomic_set(&dc->may_delay, 1);

M
Mikulas Patocka 已提交
200
	ti->num_flush_requests = 1;
H
Heinz Mauelshagen 已提交
201 202 203
	ti->private = dc;
	return 0;

D
Dmitry Monakhov 已提交
204 205 206 207 208
bad_dev_write:
	if (dc->dev_write)
		dm_put_device(ti, dc->dev_write);
bad_dev_read:
	dm_put_device(ti, dc->dev_read);
H
Heinz Mauelshagen 已提交
209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230
bad:
	kfree(dc);
	return -EINVAL;
}

static void delay_dtr(struct dm_target *ti)
{
	struct delay_c *dc = ti->private;

	flush_workqueue(kdelayd_wq);

	dm_put_device(ti, dc->dev_read);

	if (dc->dev_write)
		dm_put_device(ti, dc->dev_write);

	mempool_destroy(dc->delayed_pool);
	kfree(dc);
}

static int delay_bio(struct delay_c *dc, int delay, struct bio *bio)
{
A
Alasdair G Kergon 已提交
231
	struct dm_delay_info *delayed;
H
Heinz Mauelshagen 已提交
232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281
	unsigned long expires = 0;

	if (!delay || !atomic_read(&dc->may_delay))
		return 1;

	delayed = mempool_alloc(dc->delayed_pool, GFP_NOIO);

	delayed->context = dc;
	delayed->bio = bio;
	delayed->expires = expires = jiffies + (delay * HZ / 1000);

	mutex_lock(&delayed_bios_lock);

	if (bio_data_dir(bio) == WRITE)
		dc->writes++;
	else
		dc->reads++;

	list_add_tail(&delayed->list, &dc->delayed_bios);

	mutex_unlock(&delayed_bios_lock);

	queue_timeout(dc, expires);

	return 0;
}

static void delay_presuspend(struct dm_target *ti)
{
	struct delay_c *dc = ti->private;

	atomic_set(&dc->may_delay, 0);
	del_timer_sync(&dc->delay_timer);
	flush_bios(flush_delayed_bios(dc, 1));
}

static void delay_resume(struct dm_target *ti)
{
	struct delay_c *dc = ti->private;

	atomic_set(&dc->may_delay, 1);
}

static int delay_map(struct dm_target *ti, struct bio *bio,
		     union map_info *map_context)
{
	struct delay_c *dc = ti->private;

	if ((bio_data_dir(bio) == WRITE) && (dc->dev_write)) {
		bio->bi_bdev = dc->dev_write->bdev;
M
Mikulas Patocka 已提交
282 283 284
		if (bio_sectors(bio))
			bio->bi_sector = dc->start_write +
					 (bio->bi_sector - ti->begin);
H
Heinz Mauelshagen 已提交
285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311

		return delay_bio(dc, dc->write_delay, bio);
	}

	bio->bi_bdev = dc->dev_read->bdev;
	bio->bi_sector = dc->start_read +
			 (bio->bi_sector - ti->begin);

	return delay_bio(dc, dc->read_delay, bio);
}

static int delay_status(struct dm_target *ti, status_type_t type,
			char *result, unsigned maxlen)
{
	struct delay_c *dc = ti->private;
	int sz = 0;

	switch (type) {
	case STATUSTYPE_INFO:
		DMEMIT("%u %u", dc->reads, dc->writes);
		break;

	case STATUSTYPE_TABLE:
		DMEMIT("%s %llu %u", dc->dev_read->name,
		       (unsigned long long) dc->start_read,
		       dc->read_delay);
		if (dc->dev_write)
M
Milan Broz 已提交
312
			DMEMIT(" %s %llu %u", dc->dev_write->name,
H
Heinz Mauelshagen 已提交
313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342
			       (unsigned long long) dc->start_write,
			       dc->write_delay);
		break;
	}

	return 0;
}

static struct target_type delay_target = {
	.name	     = "delay",
	.version     = {1, 0, 2},
	.module      = THIS_MODULE,
	.ctr	     = delay_ctr,
	.dtr	     = delay_dtr,
	.map	     = delay_map,
	.presuspend  = delay_presuspend,
	.resume	     = delay_resume,
	.status	     = delay_status,
};

static int __init dm_delay_init(void)
{
	int r = -ENOMEM;

	kdelayd_wq = create_workqueue("kdelayd");
	if (!kdelayd_wq) {
		DMERR("Couldn't start kdelayd");
		goto bad_queue;
	}

A
Alasdair G Kergon 已提交
343
	delayed_cache = KMEM_CACHE(dm_delay_info, 0);
H
Heinz Mauelshagen 已提交
344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366
	if (!delayed_cache) {
		DMERR("Couldn't create delayed bio cache.");
		goto bad_memcache;
	}

	r = dm_register_target(&delay_target);
	if (r < 0) {
		DMERR("register failed %d", r);
		goto bad_register;
	}

	return 0;

bad_register:
	kmem_cache_destroy(delayed_cache);
bad_memcache:
	destroy_workqueue(kdelayd_wq);
bad_queue:
	return r;
}

static void __exit dm_delay_exit(void)
{
367
	dm_unregister_target(&delay_target);
H
Heinz Mauelshagen 已提交
368 369 370 371 372 373 374 375 376 377 378
	kmem_cache_destroy(delayed_cache);
	destroy_workqueue(kdelayd_wq);
}

/* Module hooks */
module_init(dm_delay_init);
module_exit(dm_delay_exit);

MODULE_DESCRIPTION(DM_NAME " delay target");
MODULE_AUTHOR("Heinz Mauelshagen <mauelshagen@redhat.com>");
MODULE_LICENSE("GPL");