Home Home > GIT Browse > stable-xen
summaryrefslogtreecommitdiff
blob: 85c24cace9732fa62b67afd81c827437a04adfb9 (plain)
1
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
35
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
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
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
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
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
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
282
283
284
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
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
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
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
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
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
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
#include <linux/module.h>

#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>
#include <linux/lightnvm.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 hrtimer timer;
};

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;
	struct nvm_dev *ndev;
	struct blk_mq_tag_set *tag_set;
	struct blk_mq_tag_set __tag_set;
	struct hrtimer timer;
	unsigned int queue_depth;
	spinlock_t lock;

	struct nullb_queue *queues;
	unsigned int nr_queues;
	char disk_name[DISK_NAME_LEN];
};

static LIST_HEAD(nullb_list);
static struct mutex lock;
static int null_major;
static int nullb_indexes;
static struct kmem_cache *ppa_cache;
static struct blk_mq_tag_set tag_set;

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

enum {
	NULL_Q_BIO		= 0,
	NULL_Q_RQ		= 1,
	NULL_Q_MQ		= 2,
};

static int submit_queues;
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;

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);
}

static const struct kernel_param_ops null_queue_mode_param_ops = {
	.set	= null_set_queue_mode,
	.get	= param_get_int,
};

device_param_cb(queue_mode, &null_queue_mode_param_ops, &queue_mode, S_IRUGO);
MODULE_PARM_DESC(queue_mode, "Block interface to use (0=bio,1=rq,2=multiqueue)");

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 = 1;
module_param(nr_devices, int, S_IRUGO);
MODULE_PARM_DESC(nr_devices, "Number of devices to register");

static bool use_lightnvm;
module_param(use_lightnvm, bool, S_IRUGO);
MODULE_PARM_DESC(use_lightnvm, "Register as a LightNVM device");

static bool blocking;
module_param(blocking, bool, S_IRUGO);
MODULE_PARM_DESC(blocking, "Register as a blocking blk-mq driver device");

static bool shared_tags;
module_param(shared_tags, bool, S_IRUGO);
MODULE_PARM_DESC(shared_tags, "Share tag set between devices for blk-mq");

static int irqmode = NULL_IRQ_SOFTIRQ;

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);
}

static const struct kernel_param_ops null_irqmode_param_ops = {
	.set	= null_set_irqmode,
	.get	= param_get_int,
};

device_param_cb(irqmode, &null_irqmode_param_ops, &irqmode, S_IRUGO);
MODULE_PARM_DESC(irqmode, "IRQ completion handler. 0-none, 1-softirq, 2-timer");

static unsigned long completion_nsec = 10000;
module_param(completion_nsec, ulong, 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");

static bool use_per_node_hctx = false;
module_param(use_per_node_hctx, bool, S_IRUGO);
MODULE_PARM_DESC(use_per_node_hctx, "Use per-node allocation for hardware context queues. Default: false");

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 enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer);

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;
		if (irqmode == NULL_IRQ_TIMER) {
			hrtimer_init(&cmd->timer, CLOCK_MONOTONIC,
				     HRTIMER_MODE_REL);
			cmd->timer.function = null_cmd_timer_expired;
		}
		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)
{
	struct request_queue *q = NULL;

	if (cmd->rq)
		q = cmd->rq->q;

	switch (queue_mode)  {
	case NULL_Q_MQ:
		blk_mq_end_request(cmd->rq, BLK_STS_OK);
		return;
	case NULL_Q_RQ:
		INIT_LIST_HEAD(&cmd->rq->queuelist);
		blk_end_request_all(cmd->rq, BLK_STS_OK);
		break;
	case NULL_Q_BIO:
		bio_endio(cmd->bio);
		break;
	}

	free_cmd(cmd);

	/* Restart queue if needed, as we are freeing a tag */
	if (queue_mode == NULL_Q_RQ && blk_queue_stopped(q)) {
		unsigned long flags;

		spin_lock_irqsave(q->queue_lock, flags);
		blk_start_queue_async(q);
		spin_unlock_irqrestore(q->queue_lock, flags);
	}
}

static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer)
{
	end_cmd(container_of(timer, struct nullb_cmd, timer));

	return HRTIMER_NORESTART;
}

static void null_cmd_end_timer(struct nullb_cmd *cmd)
{
	ktime_t kt = completion_nsec;

	hrtimer_start(&cmd->timer, kt, HRTIMER_MODE_REL);
}

static void null_softirq_done_fn(struct request *rq)
{
	if (queue_mode == NULL_Q_MQ)
		end_cmd(blk_mq_rq_to_pdu(rq));
	else
		end_cmd(rq->special);
}

static inline void null_handle_cmd(struct nullb_cmd *cmd)
{
	/* Complete IO by inline, softirq or timer */
	switch (irqmode) {
	case NULL_IRQ_SOFTIRQ:
		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:
		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 blk_qc_t 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);
	return BLK_QC_T_NONE;
}

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;
	}
	blk_stop_queue(q);

	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);
	}
}

static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
			 const struct blk_mq_queue_data *bd)
{
	struct nullb_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);

	might_sleep_if(hctx->flags & BLK_MQ_F_BLOCKING);

	if (irqmode == NULL_IRQ_TIMER) {
		hrtimer_init(&cmd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
		cmd->timer.function = null_cmd_timer_expired;
	}
	cmd->rq = bd->rq;
	cmd->nq = hctx->driver_data;

	blk_mq_start_request(bd->rq);

	null_handle_cmd(cmd);
	return BLK_STS_OK;
}

static const struct blk_mq_ops null_mq_ops = {
	.queue_rq       = null_queue_rq,
	.complete	= null_softirq_done_fn,
};

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);
}

#ifdef CONFIG_NVM

static void null_lnvm_end_io(struct request *rq, blk_status_t status)
{
	struct nvm_rq *rqd = rq->end_io_data;

	/* XXX: lighnvm core seems to expect NVM_RSP_* values here.. */
	rqd->error = status ? -EIO : 0;
	nvm_end_io(rqd);

	blk_put_request(rq);
}

static int null_lnvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd)
{
	struct request_queue *q = dev->q;
	struct request *rq;
	struct bio *bio = rqd->bio;

	rq = blk_mq_alloc_request(q,
		op_is_write(bio_op(bio)) ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
	if (IS_ERR(rq))
		return -ENOMEM;

	blk_init_request_from_bio(rq, bio);

	rq->end_io_data = rqd;

	blk_execute_rq_nowait(q, NULL, rq, 0, null_lnvm_end_io);

	return 0;
}

static int null_lnvm_id(struct nvm_dev *dev, struct nvm_id *id)
{
	sector_t size = gb * 1024 * 1024 * 1024ULL;
	sector_t blksize;
	struct nvm_id_group *grp;

	id->ver_id = 0x1;
	id->vmnt = 0;
	id->cap = 0x2;
	id->dom = 0x1;

	id->ppaf.blk_offset = 0;
	id->ppaf.blk_len = 16;
	id->ppaf.pg_offset = 16;
	id->ppaf.pg_len = 16;
	id->ppaf.sect_offset = 32;
	id->ppaf.sect_len = 8;
	id->ppaf.pln_offset = 40;
	id->ppaf.pln_len = 8;
	id->ppaf.lun_offset = 48;
	id->ppaf.lun_len = 8;
	id->ppaf.ch_offset = 56;
	id->ppaf.ch_len = 8;

	sector_div(size, bs); /* convert size to pages */
	size >>= 8; /* concert size to pgs pr blk */
	grp = &id->grp;
	grp->mtype = 0;
	grp->fmtype = 0;
	grp->num_ch = 1;
	grp->num_pg = 256;
	blksize = size;
	size >>= 16;
	grp->num_lun = size + 1;
	sector_div(blksize, grp->num_lun);
	grp->num_blk = blksize;
	grp->num_pln = 1;

	grp->fpg_sz = bs;
	grp->csecs = bs;
	grp->trdt = 25000;
	grp->trdm = 25000;
	grp->tprt = 500000;
	grp->tprm = 500000;
	grp->tbet = 1500000;
	grp->tbem = 1500000;
	grp->mpos = 0x010101; /* single plane rwe */
	grp->cpar = hw_queue_depth;

	return 0;
}

static void *null_lnvm_create_dma_pool(struct nvm_dev *dev, char *name)
{
	mempool_t *virtmem_pool;

	virtmem_pool = mempool_create_slab_pool(64, ppa_cache);
	if (!virtmem_pool) {
		pr_err("null_blk: Unable to create virtual memory pool\n");
		return NULL;
	}

	return virtmem_pool;
}

static void null_lnvm_destroy_dma_pool(void *pool)
{
	mempool_destroy(pool);
}

static void *null_lnvm_dev_dma_alloc(struct nvm_dev *dev, void *pool,
				gfp_t mem_flags, dma_addr_t *dma_handler)
{
	return mempool_alloc(pool, mem_flags);
}

static void null_lnvm_dev_dma_free(void *pool, void *entry,
							dma_addr_t dma_handler)
{
	mempool_free(entry, pool);
}

static struct nvm_dev_ops null_lnvm_dev_ops = {
	.identity		= null_lnvm_id,
	.submit_io		= null_lnvm_submit_io,

	.create_dma_pool	= null_lnvm_create_dma_pool,
	.destroy_dma_pool	= null_lnvm_destroy_dma_pool,
	.dev_dma_alloc		= null_lnvm_dev_dma_alloc,
	.dev_dma_free		= null_lnvm_dev_dma_free,

	/* Simulate nvme protocol restriction */
	.max_phys_sect		= 64,
};

static int null_nvm_register(struct nullb *nullb)
{
	struct nvm_dev *dev;
	int rv;

	dev = nvm_alloc_dev(0);
	if (!dev)
		return -ENOMEM;

	dev->q = nullb->q;
	memcpy(dev->name, nullb->disk_name, DISK_NAME_LEN);
	dev->ops = &null_lnvm_dev_ops;

	rv = nvm_register(dev);
	if (rv) {
		kfree(dev);
		return rv;
	}
	nullb->ndev = dev;
	return 0;
}

static void null_nvm_unregister(struct nullb *nullb)
{
	nvm_unregister(nullb->ndev);
}
#else
static int null_nvm_register(struct nullb *nullb)
{
	pr_err("null_blk: CONFIG_NVM needs to be enabled for LightNVM\n");
	return -EINVAL;
}
static void null_nvm_unregister(struct nullb *nullb) {}
#endif /* CONFIG_NVM */

static void null_del_dev(struct nullb *nullb)
{
	list_del_init(&nullb->list);

	if (use_lightnvm)
		null_nvm_unregister(nullb);
	else
		del_gendisk(nullb->disk);
	blk_cleanup_queue(nullb->q);
	if (queue_mode == NULL_Q_MQ && nullb->tag_set == &nullb->__tag_set)
		blk_mq_free_tag_set(nullb->tag_set);
	if (!use_lightnvm)
		put_disk(nullb->disk);
	cleanup_queues(nullb);
	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 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;
}

static void null_init_queues(struct nullb *nullb)
{
	struct request_queue *q = nullb->q;
	struct blk_mq_hw_ctx *hctx;
	struct nullb_queue *nq;
	int i;

	queue_for_each_hw_ctx(q, hctx, i) {
		if (!hctx->nr_ctx || !hctx->tags)
			continue;
		nq = &nullb->queues[i];
		hctx->driver_data = nq;
		null_init_queue(nullb, nq);
		nullb->nr_queues++;
	}
}

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)
		return -ENOMEM;

	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);
		return -ENOMEM;
	}

	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)
{
	nullb->queues = kzalloc(submit_queues * sizeof(struct nullb_queue),
								GFP_KERNEL);
	if (!nullb->queues)
		return -ENOMEM;

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

	return 0;
}

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

	for (i = 0; i < submit_queues; i++) {
		nq = &nullb->queues[i];

		null_init_queue(nullb, nq);

		ret = setup_commands(nq);
		if (ret)
			return ret;
		nullb->nr_queues++;
	}
	return 0;
}

static int null_gendisk_register(struct nullb *nullb)
{
	struct gendisk *disk;
	sector_t size;

	disk = nullb->disk = alloc_disk_node(1, home_node);
	if (!disk)
		return -ENOMEM;
	size = gb * 1024 * 1024 * 1024ULL;
	set_capacity(disk, size >> 9);

	disk->flags |= GENHD_FL_EXT_DEVT | GENHD_FL_SUPPRESS_PARTITION_INFO;
	disk->major		= null_major;
	disk->first_minor	= nullb->index;
	disk->fops		= &null_fops;
	disk->private_data	= nullb;
	disk->queue		= nullb->q;
	strncpy(disk->disk_name, nullb->disk_name, DISK_NAME_LEN);

	add_disk(disk);
	return 0;
}

static int null_init_tag_set(struct blk_mq_tag_set *set)
{
	set->ops = &null_mq_ops;
	set->nr_hw_queues = submit_queues;
	set->queue_depth = hw_queue_depth;
	set->numa_node = home_node;
	set->cmd_size	= sizeof(struct nullb_cmd);
	set->flags = BLK_MQ_F_SHOULD_MERGE;
	set->driver_data = NULL;

	if (blocking)
		set->flags |= BLK_MQ_F_BLOCKING;

	return blk_mq_alloc_tag_set(set);
}

static int null_add_dev(void)
{
	struct nullb *nullb;
	int rv;

	nullb = kzalloc_node(sizeof(*nullb), GFP_KERNEL, home_node);
	if (!nullb) {
		rv = -ENOMEM;
		goto out;
	}

	spin_lock_init(&nullb->lock);

	if (queue_mode == NULL_Q_MQ && use_per_node_hctx)
		submit_queues = nr_online_nodes;

	rv = setup_queues(nullb);
	if (rv)
		goto out_free_nullb;

	if (queue_mode == NULL_Q_MQ) {
		if (shared_tags) {
			nullb->tag_set = &tag_set;
			rv = 0;
		} else {
			nullb->tag_set = &nullb->__tag_set;
			rv = null_init_tag_set(nullb->tag_set);
		}

		if (rv)
			goto out_cleanup_queues;

		nullb->q = blk_mq_init_queue(nullb->tag_set);
		if (IS_ERR(nullb->q)) {
			rv = -ENOMEM;
			goto out_cleanup_tags;
		}
		null_init_queues(nullb);
	} else if (queue_mode == NULL_Q_BIO) {
		nullb->q = blk_alloc_queue_node(GFP_KERNEL, home_node);
		if (!nullb->q) {
			rv = -ENOMEM;
			goto out_cleanup_queues;
		}
		blk_queue_make_request(nullb->q, null_queue_bio);
		rv = init_driver_queues(nullb);
		if (rv)
			goto out_cleanup_blk_queue;
	} else {
		nullb->q = blk_init_queue_node(null_request_fn, &nullb->lock, home_node);
		if (!nullb->q) {
			rv = -ENOMEM;
			goto out_cleanup_queues;
		}
		blk_queue_prep_rq(nullb->q, null_rq_prep_fn);
		blk_queue_softirq_done(nullb->q, null_softirq_done_fn);
		rv = init_driver_queues(nullb);
		if (rv)
			goto out_cleanup_blk_queue;
	}

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

	mutex_lock(&lock);
	nullb->index = nullb_indexes++;
	mutex_unlock(&lock);

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

	sprintf(nullb->disk_name, "nullb%d", nullb->index);

	if (use_lightnvm)
		rv = null_nvm_register(nullb);
	else
		rv = null_gendisk_register(nullb);

	if (rv)
		goto out_cleanup_blk_queue;

	mutex_lock(&lock);
	list_add_tail(&nullb->list, &nullb_list);
	mutex_unlock(&lock);

	return 0;
out_cleanup_blk_queue:
	blk_cleanup_queue(nullb->q);
out_cleanup_tags:
	if (queue_mode == NULL_Q_MQ && nullb->tag_set == &nullb->__tag_set)
		blk_mq_free_tag_set(nullb->tag_set);
out_cleanup_queues:
	cleanup_queues(nullb);
out_free_nullb:
	kfree(nullb);
out:
	return rv;
}

static int __init null_init(void)
{
	int ret = 0;
	unsigned int i;
	struct nullb *nullb;

	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;
	}

	if (use_lightnvm && bs != 4096) {
		pr_warn("null_blk: LightNVM only supports 4k block size\n");
		pr_warn("null_blk: defaults block size to 4k\n");
		bs = 4096;
	}

	if (use_lightnvm && queue_mode != NULL_Q_MQ) {
		pr_warn("null_blk: LightNVM only supported for blk-mq\n");
		pr_warn("null_blk: defaults queue mode to blk-mq\n");
		queue_mode = NULL_Q_MQ;
	}

	if (queue_mode == NULL_Q_MQ && use_per_node_hctx) {
		if (submit_queues < nr_online_nodes) {
			pr_warn("null_blk: submit_queues param is set to %u.",
							nr_online_nodes);
			submit_queues = nr_online_nodes;
		}
	} else if (submit_queues > nr_cpu_ids)
		submit_queues = nr_cpu_ids;
	else if (!submit_queues)
		submit_queues = 1;

	if (queue_mode == NULL_Q_MQ && shared_tags) {
		ret = null_init_tag_set(&tag_set);
		if (ret)
			return ret;
	}

	mutex_init(&lock);

	null_major = register_blkdev(0, "nullb");
	if (null_major < 0) {
		ret = null_major;
		goto err_tagset;
	}

	if (use_lightnvm) {
		ppa_cache = kmem_cache_create("ppa_cache", 64 * sizeof(u64),
								0, 0, NULL);
		if (!ppa_cache) {
			pr_err("null_blk: unable to create ppa cache\n");
			ret = -ENOMEM;
			goto err_ppa;
		}
	}

	for (i = 0; i < nr_devices; i++) {
		ret = null_add_dev();
		if (ret)
			goto err_dev;
	}

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

err_dev:
	while (!list_empty(&nullb_list)) {
		nullb = list_entry(nullb_list.next, struct nullb, list);
		null_del_dev(nullb);
	}
	kmem_cache_destroy(ppa_cache);
err_ppa:
	unregister_blkdev(null_major, "nullb");
err_tagset:
	if (queue_mode == NULL_Q_MQ && shared_tags)
		blk_mq_free_tag_set(&tag_set);
	return ret;
}

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);

	if (queue_mode == NULL_Q_MQ && shared_tags)
		blk_mq_free_tag_set(&tag_set);

	kmem_cache_destroy(ppa_cache);
}

module_init(null_init);
module_exit(null_exit);

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