null_blk.c 14.6 KB
Newer Older
1
#include <linux/module.h>
2

3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34
#include <linux/moduleparam.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/blkdev.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/blk-mq.h>
#include <linux/hrtimer.h>

struct nullb_cmd {
	struct list_head list;
	struct llist_node ll_list;
	struct call_single_data csd;
	struct request *rq;
	struct bio *bio;
	unsigned int tag;
	struct nullb_queue *nq;
};

struct nullb_queue {
	unsigned long *tag_map;
	wait_queue_head_t wait;
	unsigned int queue_depth;

	struct nullb_cmd *cmds;
};

struct nullb {
	struct list_head list;
	unsigned int index;
	struct request_queue *q;
	struct gendisk *disk;
35
	struct blk_mq_tag_set tag_set;
36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63
	struct hrtimer timer;
	unsigned int queue_depth;
	spinlock_t lock;

	struct nullb_queue *queues;
	unsigned int nr_queues;
};

static LIST_HEAD(nullb_list);
static struct mutex lock;
static int null_major;
static int nullb_indexes;

struct completion_queue {
	struct llist_head list;
	struct hrtimer timer;
};

/*
 * These are per-cpu for now, they will need to be configured by the
 * complete_queues parameter and appropriately mapped.
 */
static DEFINE_PER_CPU(struct completion_queue, completion_queues);

enum {
	NULL_IRQ_NONE		= 0,
	NULL_IRQ_SOFTIRQ	= 1,
	NULL_IRQ_TIMER		= 2,
64
};
65

66
enum {
67 68 69 70 71
	NULL_Q_BIO		= 0,
	NULL_Q_RQ		= 1,
	NULL_Q_MQ		= 2,
};

72
static int submit_queues;
73 74 75 76 77 78 79 80
module_param(submit_queues, int, S_IRUGO);
MODULE_PARM_DESC(submit_queues, "Number of submission queues");

static int home_node = NUMA_NO_NODE;
module_param(home_node, int, S_IRUGO);
MODULE_PARM_DESC(home_node, "Home node for the device");

static int queue_mode = NULL_Q_MQ;
81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101

static int null_param_store_val(const char *str, int *val, int min, int max)
{
	int ret, new_val;

	ret = kstrtoint(str, 10, &new_val);
	if (ret)
		return -EINVAL;

	if (new_val < min || new_val > max)
		return -EINVAL;

	*val = new_val;
	return 0;
}

static int null_set_queue_mode(const char *str, const struct kernel_param *kp)
{
	return null_param_store_val(str, &queue_mode, NULL_Q_BIO, NULL_Q_MQ);
}

102
static const struct kernel_param_ops null_queue_mode_param_ops = {
103 104 105 106 107
	.set	= null_set_queue_mode,
	.get	= param_get_int,
};

device_param_cb(queue_mode, &null_queue_mode_param_ops, &queue_mode, S_IRUGO);
108
MODULE_PARM_DESC(queue_mode, "Block interface to use (0=bio,1=rq,2=multiqueue)");
109 110 111 112 113 114 115 116 117 118 119 120 121 122

static int gb = 250;
module_param(gb, int, S_IRUGO);
MODULE_PARM_DESC(gb, "Size in GB");

static int bs = 512;
module_param(bs, int, S_IRUGO);
MODULE_PARM_DESC(bs, "Block size (in bytes)");

static int nr_devices = 2;
module_param(nr_devices, int, S_IRUGO);
MODULE_PARM_DESC(nr_devices, "Number of devices to register");

static int irqmode = NULL_IRQ_SOFTIRQ;
123 124 125 126 127 128 129

static int null_set_irqmode(const char *str, const struct kernel_param *kp)
{
	return null_param_store_val(str, &irqmode, NULL_IRQ_NONE,
					NULL_IRQ_TIMER);
}

130
static const struct kernel_param_ops null_irqmode_param_ops = {
131 132 133 134 135
	.set	= null_set_irqmode,
	.get	= param_get_int,
};

device_param_cb(irqmode, &null_irqmode_param_ops, &irqmode, S_IRUGO);
136 137 138 139 140 141 142 143 144 145
MODULE_PARM_DESC(irqmode, "IRQ completion handler. 0-none, 1-softirq, 2-timer");

static int completion_nsec = 10000;
module_param(completion_nsec, int, S_IRUGO);
MODULE_PARM_DESC(completion_nsec, "Time in ns to complete a request in hardware. Default: 10,000ns");

static int hw_queue_depth = 64;
module_param(hw_queue_depth, int, S_IRUGO);
MODULE_PARM_DESC(hw_queue_depth, "Queue depth for each hardware queue. Default: 64");

146
static bool use_per_node_hctx = false;
147
module_param(use_per_node_hctx, bool, S_IRUGO);
148
MODULE_PARM_DESC(use_per_node_hctx, "Use per-node allocation for hardware context queues. Default: false");
149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215

static void put_tag(struct nullb_queue *nq, unsigned int tag)
{
	clear_bit_unlock(tag, nq->tag_map);

	if (waitqueue_active(&nq->wait))
		wake_up(&nq->wait);
}

static unsigned int get_tag(struct nullb_queue *nq)
{
	unsigned int tag;

	do {
		tag = find_first_zero_bit(nq->tag_map, nq->queue_depth);
		if (tag >= nq->queue_depth)
			return -1U;
	} while (test_and_set_bit_lock(tag, nq->tag_map));

	return tag;
}

static void free_cmd(struct nullb_cmd *cmd)
{
	put_tag(cmd->nq, cmd->tag);
}

static struct nullb_cmd *__alloc_cmd(struct nullb_queue *nq)
{
	struct nullb_cmd *cmd;
	unsigned int tag;

	tag = get_tag(nq);
	if (tag != -1U) {
		cmd = &nq->cmds[tag];
		cmd->tag = tag;
		cmd->nq = nq;
		return cmd;
	}

	return NULL;
}

static struct nullb_cmd *alloc_cmd(struct nullb_queue *nq, int can_wait)
{
	struct nullb_cmd *cmd;
	DEFINE_WAIT(wait);

	cmd = __alloc_cmd(nq);
	if (cmd || !can_wait)
		return cmd;

	do {
		prepare_to_wait(&nq->wait, &wait, TASK_UNINTERRUPTIBLE);
		cmd = __alloc_cmd(nq);
		if (cmd)
			break;

		io_schedule();
	} while (1);

	finish_wait(&nq->wait, &wait);
	return cmd;
}

static void end_cmd(struct nullb_cmd *cmd)
{
216 217
	switch (queue_mode)  {
	case NULL_Q_MQ:
218
		blk_mq_end_request(cmd->rq, 0);
219 220 221 222 223 224
		return;
	case NULL_Q_RQ:
		INIT_LIST_HEAD(&cmd->rq->queuelist);
		blk_end_request_all(cmd->rq, 0);
		break;
	case NULL_Q_BIO:
225
		bio_endio(cmd->bio);
226 227
		break;
	}
228

229
	free_cmd(cmd);
230 231 232 233 234 235 236 237 238 239 240
}

static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer)
{
	struct completion_queue *cq;
	struct llist_node *entry;
	struct nullb_cmd *cmd;

	cq = &per_cpu(completion_queues, smp_processor_id());

	while ((entry = llist_del_all(&cq->list)) != NULL) {
241
		entry = llist_reverse_order(entry);
242
		do {
243 244
			struct request_queue *q = NULL;

245 246
			cmd = container_of(entry, struct nullb_cmd, ll_list);
			entry = entry->next;
247 248
			if (cmd->rq)
				q = cmd->rq->q;
M
Ming Lei 已提交
249
			end_cmd(cmd);
250

251 252 253 254 255
			if (q && !q->mq_ops && blk_queue_stopped(q)) {
				spin_lock(q->queue_lock);
				if (blk_queue_stopped(q))
					blk_start_queue(q);
				spin_unlock(q->queue_lock);
256
			}
257 258 259 260 261 262 263 264 265 266 267 268 269 270
		} while (entry);
	}

	return HRTIMER_NORESTART;
}

static void null_cmd_end_timer(struct nullb_cmd *cmd)
{
	struct completion_queue *cq = &per_cpu(completion_queues, get_cpu());

	cmd->ll_list.next = NULL;
	if (llist_add(&cmd->ll_list, &cq->list)) {
		ktime_t kt = ktime_set(0, completion_nsec);

271
		hrtimer_start(&cq->timer, kt, HRTIMER_MODE_REL_PINNED);
272 273 274 275 276 277 278
	}

	put_cpu();
}

static void null_softirq_done_fn(struct request *rq)
{
279 280 281 282
	if (queue_mode == NULL_Q_MQ)
		end_cmd(blk_mq_rq_to_pdu(rq));
	else
		end_cmd(rq->special);
283 284 285 286 287 288 289
}

static inline void null_handle_cmd(struct nullb_cmd *cmd)
{
	/* Complete IO by inline, softirq or timer */
	switch (irqmode) {
	case NULL_IRQ_SOFTIRQ:
290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305
		switch (queue_mode)  {
		case NULL_Q_MQ:
			blk_mq_complete_request(cmd->rq);
			break;
		case NULL_Q_RQ:
			blk_complete_request(cmd->rq);
			break;
		case NULL_Q_BIO:
			/*
			 * XXX: no proper submitting cpu information available.
			 */
			end_cmd(cmd);
			break;
		}
		break;
	case NULL_IRQ_NONE:
306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347
		end_cmd(cmd);
		break;
	case NULL_IRQ_TIMER:
		null_cmd_end_timer(cmd);
		break;
	}
}

static struct nullb_queue *nullb_to_queue(struct nullb *nullb)
{
	int index = 0;

	if (nullb->nr_queues != 1)
		index = raw_smp_processor_id() / ((nr_cpu_ids + nullb->nr_queues - 1) / nullb->nr_queues);

	return &nullb->queues[index];
}

static void null_queue_bio(struct request_queue *q, struct bio *bio)
{
	struct nullb *nullb = q->queuedata;
	struct nullb_queue *nq = nullb_to_queue(nullb);
	struct nullb_cmd *cmd;

	cmd = alloc_cmd(nq, 1);
	cmd->bio = bio;

	null_handle_cmd(cmd);
}

static int null_rq_prep_fn(struct request_queue *q, struct request *req)
{
	struct nullb *nullb = q->queuedata;
	struct nullb_queue *nq = nullb_to_queue(nullb);
	struct nullb_cmd *cmd;

	cmd = alloc_cmd(nq, 0);
	if (cmd) {
		cmd->rq = req;
		req->special = cmd;
		return BLKPREP_OK;
	}
348
	blk_stop_queue(q);
349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365

	return BLKPREP_DEFER;
}

static void null_request_fn(struct request_queue *q)
{
	struct request *rq;

	while ((rq = blk_fetch_request(q)) != NULL) {
		struct nullb_cmd *cmd = rq->special;

		spin_unlock_irq(q->queue_lock);
		null_handle_cmd(cmd);
		spin_lock_irq(q->queue_lock);
	}
}

366 367
static int null_queue_rq(struct blk_mq_hw_ctx *hctx,
			 const struct blk_mq_queue_data *bd)
368
{
369
	struct nullb_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
370

371
	cmd->rq = bd->rq;
372 373
	cmd->nq = hctx->driver_data;

374
	blk_mq_start_request(bd->rq);
375

376 377 378 379
	null_handle_cmd(cmd);
	return BLK_MQ_RQ_QUEUE_OK;
}

380 381 382 383 384 385 386 387 388
static void null_init_queue(struct nullb *nullb, struct nullb_queue *nq)
{
	BUG_ON(!nullb);
	BUG_ON(!nq);

	init_waitqueue_head(&nq->wait);
	nq->queue_depth = nullb->queue_depth;
}

389 390 391 392 393 394 395
static int null_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
			  unsigned int index)
{
	struct nullb *nullb = data;
	struct nullb_queue *nq = &nullb->queues[index];

	hctx->driver_data = nq;
396 397
	null_init_queue(nullb, nq);
	nullb->nr_queues++;
398 399 400 401 402 403 404 405

	return 0;
}

static struct blk_mq_ops null_mq_ops = {
	.queue_rq       = null_queue_rq,
	.map_queue      = blk_mq_map_queue,
	.init_hctx	= null_init_hctx,
406
	.complete	= null_softirq_done_fn,
407 408
};

409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424
static void cleanup_queue(struct nullb_queue *nq)
{
	kfree(nq->tag_map);
	kfree(nq->cmds);
}

static void cleanup_queues(struct nullb *nullb)
{
	int i;

	for (i = 0; i < nullb->nr_queues; i++)
		cleanup_queue(&nullb->queues[i]);

	kfree(nullb->queues);
}

425 426 427 428 429
static void null_del_dev(struct nullb *nullb)
{
	list_del_init(&nullb->list);

	del_gendisk(nullb->disk);
430
	blk_cleanup_queue(nullb->q);
431 432
	if (queue_mode == NULL_Q_MQ)
		blk_mq_free_tag_set(&nullb->tag_set);
433
	put_disk(nullb->disk);
434
	cleanup_queues(nullb);
435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459
	kfree(nullb);
}

static int null_open(struct block_device *bdev, fmode_t mode)
{
	return 0;
}

static void null_release(struct gendisk *disk, fmode_t mode)
{
}

static const struct block_device_operations null_fops = {
	.owner =	THIS_MODULE,
	.open =		null_open,
	.release =	null_release,
};

static int setup_commands(struct nullb_queue *nq)
{
	struct nullb_cmd *cmd;
	int i, tag_size;

	nq->cmds = kzalloc(nq->queue_depth * sizeof(*cmd), GFP_KERNEL);
	if (!nq->cmds)
460
		return -ENOMEM;
461 462 463 464 465

	tag_size = ALIGN(nq->queue_depth, BITS_PER_LONG) / BITS_PER_LONG;
	nq->tag_map = kzalloc(tag_size * sizeof(unsigned long), GFP_KERNEL);
	if (!nq->tag_map) {
		kfree(nq->cmds);
466
		return -ENOMEM;
467 468 469 470 471 472 473 474 475 476 477 478 479 480
	}

	for (i = 0; i < nq->queue_depth; i++) {
		cmd = &nq->cmds[i];
		INIT_LIST_HEAD(&cmd->list);
		cmd->ll_list.next = NULL;
		cmd->tag = -1U;
	}

	return 0;
}

static int setup_queues(struct nullb *nullb)
{
481 482
	nullb->queues = kzalloc(submit_queues * sizeof(struct nullb_queue),
								GFP_KERNEL);
483
	if (!nullb->queues)
484
		return -ENOMEM;
485 486 487 488

	nullb->nr_queues = 0;
	nullb->queue_depth = hw_queue_depth;

489 490 491 492 493 494 495
	return 0;
}

static int init_driver_queues(struct nullb *nullb)
{
	struct nullb_queue *nq;
	int i, ret = 0;
496 497 498

	for (i = 0; i < submit_queues; i++) {
		nq = &nullb->queues[i];
499 500 501 502 503

		null_init_queue(nullb, nq);

		ret = setup_commands(nq);
		if (ret)
504
			return ret;
505 506
		nullb->nr_queues++;
	}
507
	return 0;
508 509 510 511 512 513 514
}

static int null_add_dev(void)
{
	struct gendisk *disk;
	struct nullb *nullb;
	sector_t size;
515
	int rv;
516 517

	nullb = kzalloc_node(sizeof(*nullb), GFP_KERNEL, home_node);
518 519
	if (!nullb) {
		rv = -ENOMEM;
520
		goto out;
521
	}
522 523 524

	spin_lock_init(&nullb->lock);

525 526 527
	if (queue_mode == NULL_Q_MQ && use_per_node_hctx)
		submit_queues = nr_online_nodes;

528 529
	rv = setup_queues(nullb);
	if (rv)
530
		goto out_free_nullb;
531 532

	if (queue_mode == NULL_Q_MQ) {
533
		nullb->tag_set.ops = &null_mq_ops;
534 535 536 537 538 539 540
		nullb->tag_set.nr_hw_queues = submit_queues;
		nullb->tag_set.queue_depth = hw_queue_depth;
		nullb->tag_set.numa_node = home_node;
		nullb->tag_set.cmd_size	= sizeof(struct nullb_cmd);
		nullb->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
		nullb->tag_set.driver_data = nullb;

541 542
		rv = blk_mq_alloc_tag_set(&nullb->tag_set);
		if (rv)
543 544 545
			goto out_cleanup_queues;

		nullb->q = blk_mq_init_queue(&nullb->tag_set);
546
		if (IS_ERR(nullb->q)) {
547
			rv = -ENOMEM;
548
			goto out_cleanup_tags;
549
		}
550 551
	} else if (queue_mode == NULL_Q_BIO) {
		nullb->q = blk_alloc_queue_node(GFP_KERNEL, home_node);
552 553
		if (!nullb->q) {
			rv = -ENOMEM;
554
			goto out_cleanup_queues;
555
		}
556
		blk_queue_make_request(nullb->q, null_queue_bio);
557 558 559
		rv = init_driver_queues(nullb);
		if (rv)
			goto out_cleanup_blk_queue;
560 561
	} else {
		nullb->q = blk_init_queue_node(null_request_fn, &nullb->lock, home_node);
562 563
		if (!nullb->q) {
			rv = -ENOMEM;
564
			goto out_cleanup_queues;
565
		}
566
		blk_queue_prep_rq(nullb->q, null_rq_prep_fn);
567
		blk_queue_softirq_done(nullb->q, null_softirq_done_fn);
568 569 570
		rv = init_driver_queues(nullb);
		if (rv)
			goto out_cleanup_blk_queue;
571 572 573 574
	}

	nullb->q->queuedata = nullb;
	queue_flag_set_unlocked(QUEUE_FLAG_NONROT, nullb->q);
575
	queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, nullb->q);
576 577

	disk = nullb->disk = alloc_disk_node(1, home_node);
578 579
	if (!disk) {
		rv = -ENOMEM;
580
		goto out_cleanup_blk_queue;
581
	}
582 583 584 585 586 587 588 589 590 591 592 593 594

	mutex_lock(&lock);
	list_add_tail(&nullb->list, &nullb_list);
	nullb->index = nullb_indexes++;
	mutex_unlock(&lock);

	blk_queue_logical_block_size(nullb->q, bs);
	blk_queue_physical_block_size(nullb->q, bs);

	size = gb * 1024 * 1024 * 1024ULL;
	sector_div(size, bs);
	set_capacity(disk, size);

595
	disk->flags |= GENHD_FL_EXT_DEVT | GENHD_FL_SUPPRESS_PARTITION_INFO;
596 597 598 599 600 601 602 603
	disk->major		= null_major;
	disk->first_minor	= nullb->index;
	disk->fops		= &null_fops;
	disk->private_data	= nullb;
	disk->queue		= nullb->q;
	sprintf(disk->disk_name, "nullb%d", nullb->index);
	add_disk(disk);
	return 0;
604 605 606 607 608 609 610 611 612 613 614

out_cleanup_blk_queue:
	blk_cleanup_queue(nullb->q);
out_cleanup_tags:
	if (queue_mode == NULL_Q_MQ)
		blk_mq_free_tag_set(&nullb->tag_set);
out_cleanup_queues:
	cleanup_queues(nullb);
out_free_nullb:
	kfree(nullb);
out:
615
	return rv;
616 617 618 619 620 621
}

static int __init null_init(void)
{
	unsigned int i;

622 623 624 625 626
	if (bs > PAGE_SIZE) {
		pr_warn("null_blk: invalid block size\n");
		pr_warn("null_blk: defaults block size to %lu\n", PAGE_SIZE);
		bs = PAGE_SIZE;
	}
627

628
	if (queue_mode == NULL_Q_MQ && use_per_node_hctx) {
629
		if (submit_queues < nr_online_nodes) {
630 631
			pr_warn("null_blk: submit_queues param is set to %u.",
							nr_online_nodes);
632 633
			submit_queues = nr_online_nodes;
		}
634
	} else if (submit_queues > nr_cpu_ids)
635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687
		submit_queues = nr_cpu_ids;
	else if (!submit_queues)
		submit_queues = 1;

	mutex_init(&lock);

	/* Initialize a separate list for each CPU for issuing softirqs */
	for_each_possible_cpu(i) {
		struct completion_queue *cq = &per_cpu(completion_queues, i);

		init_llist_head(&cq->list);

		if (irqmode != NULL_IRQ_TIMER)
			continue;

		hrtimer_init(&cq->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
		cq->timer.function = null_cmd_timer_expired;
	}

	null_major = register_blkdev(0, "nullb");
	if (null_major < 0)
		return null_major;

	for (i = 0; i < nr_devices; i++) {
		if (null_add_dev()) {
			unregister_blkdev(null_major, "nullb");
			return -EINVAL;
		}
	}

	pr_info("null: module loaded\n");
	return 0;
}

static void __exit null_exit(void)
{
	struct nullb *nullb;

	unregister_blkdev(null_major, "nullb");

	mutex_lock(&lock);
	while (!list_empty(&nullb_list)) {
		nullb = list_entry(nullb_list.next, struct nullb, list);
		null_del_dev(nullb);
	}
	mutex_unlock(&lock);
}

module_init(null_init);
module_exit(null_exit);

MODULE_AUTHOR("Jens Axboe <jaxboe@fusionio.com>");
MODULE_LICENSE("GPL");