aboutsummaryrefslogtreecommitdiff
path: root/drivers/md/dm-zone.c
blob: 6d82a34438c85a7b47b283e8ea61c19e97be3aff (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2021 Western Digital Corporation or its affiliates.
 */

#include <linux/blkdev.h>
#include <linux/mm.h>
#include <linux/sched/mm.h>
#include <linux/slab.h>

#include "dm-core.h"

#define DM_MSG_PREFIX "zone"

#define DM_ZONE_INVALID_WP_OFST		UINT_MAX

/*
 * For internal zone reports bypassing the top BIO submission path.
 */
static int dm_blk_do_report_zones(struct mapped_device *md, struct dm_table *t,
				  sector_t sector, unsigned int nr_zones,
				  report_zones_cb cb, void *data)
{
	struct gendisk *disk = md->disk;
	int ret;
	struct dm_report_zones_args args = {
		.next_sector = sector,
		.orig_data = data,
		.orig_cb = cb,
	};

	do {
		struct dm_target *tgt;

		tgt = dm_table_find_target(t, args.next_sector);
		if (WARN_ON_ONCE(!tgt->type->report_zones))
			return -EIO;

		args.tgt = tgt;
		ret = tgt->type->report_zones(tgt, &args,
					      nr_zones - args.zone_idx);
		if (ret < 0)
			return ret;
	} while (args.zone_idx < nr_zones &&
		 args.next_sector < get_capacity(disk));

	return args.zone_idx;
}

/*
 * User facing dm device block device report zone operation. This calls the
 * report_zones operation for each target of a device table. This operation is
 * generally implemented by targets using dm_report_zones().
 */
int dm_blk_report_zones(struct gendisk *disk, sector_t sector,
			unsigned int nr_zones, report_zones_cb cb, void *data)
{
	struct mapped_device *md = disk->private_data;
	struct dm_table *map;
	int srcu_idx, ret;

	if (dm_suspended_md(md))
		return -EAGAIN;

	map = dm_get_live_table(md, &srcu_idx);
	if (!map)
		return -EIO;

	ret = dm_blk_do_report_zones(md, map, sector, nr_zones, cb, data);

	dm_put_live_table(md, srcu_idx);

	return ret;
}

static int dm_report_zones_cb(struct blk_zone *zone, unsigned int idx,
			      void *data)
{
	struct dm_report_zones_args *args = data;
	sector_t sector_diff = args->tgt->begin - args->start;

	/*
	 * Ignore zones beyond the target range.
	 */
	if (zone->start >= args->start + args->tgt->len)
		return 0;

	/*
	 * Remap the start sector and write pointer position of the zone
	 * to match its position in the target range.
	 */
	zone->start += sector_diff;
	if (zone->type != BLK_ZONE_TYPE_CONVENTIONAL) {
		if (zone->cond == BLK_ZONE_COND_FULL)
			zone->wp = zone->start + zone->len;
		else if (zone->cond == BLK_ZONE_COND_EMPTY)
			zone->wp = zone->start;
		else
			zone->wp += sector_diff;
	}

	args->next_sector = zone->start + zone->len;
	return args->orig_cb(zone, args->zone_idx++, args->orig_data);
}

/*
 * Helper for drivers of zoned targets to implement struct target_type
 * report_zones operation.
 */
int dm_report_zones(struct block_device *bdev, sector_t start, sector_t sector,
		    struct dm_report_zones_args *args, unsigned int nr_zones)
{
	/*
	 * Set the target mapping start sector first so that
	 * dm_report_zones_cb() can correctly remap zone information.
	 */
	args->start = start;

	return blkdev_report_zones(bdev, sector, nr_zones,
				   dm_report_zones_cb, args);
}
EXPORT_SYMBOL_GPL(dm_report_zones);

bool dm_is_zone_write(struct mapped_device *md, struct bio *bio)
{
	struct request_queue *q = md->queue;

	if (!blk_queue_is_zoned(q))
		return false;

	switch (bio_op(bio)) {
	case REQ_OP_WRITE_ZEROES:
	case REQ_OP_WRITE_SAME:
	case REQ_OP_WRITE:
		return !op_is_flush(bio->bi_opf) && bio_sectors(bio);
	default:
		return false;
	}
}

void dm_cleanup_zoned_dev(struct mapped_device *md)
{
	struct request_queue *q = md->queue;

	if (q) {
		kfree(q->conv_zones_bitmap);
		q->conv_zones_bitmap = NULL;
		kfree(q->seq_zones_wlock);
		q->seq_zones_wlock = NULL;
	}

	kvfree(md->zwp_offset);
	md->zwp_offset = NULL;
	md->nr_zones = 0;
}

static unsigned int dm_get_zone_wp_offset(struct blk_zone *zone)
{
	switch (zone->cond) {
	case BLK_ZONE_COND_IMP_OPEN:
	case BLK_ZONE_COND_EXP_OPEN:
	case BLK_ZONE_COND_CLOSED:
		return zone->wp - zone->start;
	case BLK_ZONE_COND_FULL:
		return zone->len;
	case BLK_ZONE_COND_EMPTY:
	case BLK_ZONE_COND_NOT_WP:
	case BLK_ZONE_COND_OFFLINE:
	case BLK_ZONE_COND_READONLY:
	default:
		/*
		 * Conventional, offline and read-only zones do not have a valid
		 * write pointer. Use 0 as for an empty zone.
		 */
		return 0;
	}
}

static int dm_zone_revalidate_cb(struct blk_zone *zone, unsigned int idx,
				 void *data)
{
	struct mapped_device *md = data;
	struct request_queue *q = md->queue;

	switch (zone->type) {
	case BLK_ZONE_TYPE_CONVENTIONAL:
		if (!q->conv_zones_bitmap) {
			q->conv_zones_bitmap =
				kcalloc(BITS_TO_LONGS(q->nr_zones),
					sizeof(unsigned long), GFP_NOIO);
			if (!q->conv_zones_bitmap)
				return -ENOMEM;
		}
		set_bit(idx, q->conv_zones_bitmap);
		break;
	case BLK_ZONE_TYPE_SEQWRITE_REQ:
	case BLK_ZONE_TYPE_SEQWRITE_PREF:
		if (!q->seq_zones_wlock) {
			q->seq_zones_wlock =
				kcalloc(BITS_TO_LONGS(q->nr_zones),
					sizeof(unsigned long), GFP_NOIO);
			if (!q->seq_zones_wlock)
				return -ENOMEM;
		}
		if (!md->zwp_offset) {
			md->zwp_offset =
				kvcalloc(q->nr_zones, sizeof(unsigned int),
					 GFP_KERNEL);
			if (!md->zwp_offset)
				return -ENOMEM;
		}
		md->zwp_offset[idx] = dm_get_zone_wp_offset(zone);

		break;
	default:
		DMERR("Invalid zone type 0x%x at sectors %llu",
		      (int)zone->type, zone->start);
		return -ENODEV;
	}

	return 0;
}

/*
 * Revalidate the zones of a mapped device to initialize resource necessary
 * for zone append emulation. Note that we cannot simply use the block layer
 * blk_revalidate_disk_zones() function here as the mapped device is suspended
 * (this is called from __bind() context).
 */
static int dm_revalidate_zones(struct mapped_device *md, struct dm_table *t)
{
	struct request_queue *q = md->queue;
	unsigned int noio_flag;
	int ret;

	/*
	 * Check if something changed. If yes, cleanup the current resources
	 * and reallocate everything.
	 */
	if (!q->nr_zones || q->nr_zones != md->nr_zones)
		dm_cleanup_zoned_dev(md);
	if (md->nr_zones)
		return 0;

	/*
	 * Scan all zones to initialize everything. Ensure that all vmalloc
	 * operations in this context are done as if GFP_NOIO was specified.
	 */
	noio_flag = memalloc_noio_save();
	ret = dm_blk_do_report_zones(md, t, 0, q->nr_zones,
				     dm_zone_revalidate_cb, md);
	memalloc_noio_restore(noio_flag);
	if (ret < 0)
		goto err;
	if (ret != q->nr_zones) {
		ret = -EIO;
		goto err;
	}

	md->nr_zones = q->nr_zones;

	return 0;

err:
	DMERR("Revalidate zones failed %d", ret);
	dm_cleanup_zoned_dev(md);
	return ret;
}

static int device_not_zone_append_capable(struct dm_target *ti,
					  struct dm_dev *dev, sector_t start,
					  sector_t len, void *data)
{
	return !blk_queue_is_zoned(bdev_get_queue(dev->bdev));
}

static bool dm_table_supports_zone_append(struct dm_table *t)
{
	struct dm_target *ti;
	unsigned int i;

	for (i = 0; i < dm_table_get_num_targets(t); i++) {
		ti = dm_table_get_target(t, i);

		if (ti->emulate_zone_append)
			return false;

		if (!ti->type->iterate_devices ||
		    ti->type->iterate_devices(ti, device_not_zone_append_capable, NULL))
			return false;
	}

	return true;
}

int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q)
{
	struct mapped_device *md = t->md;

	/*
	 * For a zoned target, the number of zones should be updated for the
	 * correct value to be exposed in sysfs queue/nr_zones.
	 */
	WARN_ON_ONCE(queue_is_mq(q));
	q->nr_zones = blkdev_nr_zones(md->disk);

	/* Check if zone append is natively supported */
	if (dm_table_supports_zone_append(t)) {
		clear_bit(DMF_EMULATE_ZONE_APPEND, &md->flags);
		dm_cleanup_zoned_dev(md);
		return 0;
	}

	/*
	 * Mark the mapped device as needing zone append emulation and
	 * initialize the emulation resources once the capacity is set.
	 */
	set_bit(DMF_EMULATE_ZONE_APPEND, &md->flags);
	if (!get_capacity(md->disk))
		return 0;

	return dm_revalidate_zones(md, t);
}

static int dm_update_zone_wp_offset_cb(struct blk_zone *zone, unsigned int idx,
				       void *data)
{
	unsigned int *wp_offset = data;

	*wp_offset = dm_get_zone_wp_offset(zone);

	return 0;
}

static int dm_update_zone_wp_offset(struct mapped_device *md, unsigned int zno,
				    unsigned int *wp_ofst)
{
	sector_t sector = zno * blk_queue_zone_sectors(md->queue);
	unsigned int noio_flag;
	struct dm_table *t;
	int srcu_idx, ret;

	t = dm_get_live_table(md, &srcu_idx);
	if (!t)
		return -EIO;

	/*
	 * Ensure that all memory allocations in this context are done as if
	 * GFP_NOIO was specified.
	 */
	noio_flag = memalloc_noio_save();
	ret = dm_blk_do_report_zones(md, t, sector, 1,
				     dm_update_zone_wp_offset_cb, wp_ofst);
	memalloc_noio_restore(noio_flag);

	dm_put_live_table(md, srcu_idx);

	if (ret != 1)
		return -EIO;

	return 0;
}

/*
 * First phase of BIO mapping for targets with zone append emulation:
 * check all BIO that change a zone writer pointer and change zone
 * append operations into regular write operations.
 */
static bool dm_zone_map_bio_begin(struct mapped_device *md,
				  struct bio *orig_bio, struct bio *clone)
{
	sector_t zsectors = blk_queue_zone_sectors(md->queue);
	unsigned int zno = bio_zone_no(orig_bio);
	unsigned int zwp_offset = READ_ONCE(md->zwp_offset[zno]);

	/*
	 * If the target zone is in an error state, recover by inspecting the
	 * zone to get its current write pointer position. Note that since the
	 * target zone is already locked, a BIO issuing context should never
	 * see the zone write in the DM_ZONE_UPDATING_WP_OFST state.
	 */
	if (zwp_offset == DM_ZONE_INVALID_WP_OFST) {
		if (dm_update_zone_wp_offset(md, zno, &zwp_offset))
			return false;
		WRITE_ONCE(md->zwp_offset[zno], zwp_offset);
	}

	switch (bio_op(orig_bio)) {
	case REQ_OP_ZONE_RESET:
	case REQ_OP_ZONE_FINISH:
		return true;
	case REQ_OP_WRITE_ZEROES:
	case REQ_OP_WRITE_SAME:
	case REQ_OP_WRITE:
		/* Writes must be aligned to the zone write pointer */
		if ((clone->bi_iter.bi_sector & (zsectors - 1)) != zwp_offset)
			return false;
		break;
	case REQ_OP_ZONE_APPEND:
		/*
		 * Change zone append operations into a non-mergeable regular
		 * writes directed at the current write pointer position of the
		 * target zone.
		 */
		clone->bi_opf = REQ_OP_WRITE | REQ_NOMERGE |
			(orig_bio->bi_opf & (~REQ_OP_MASK));
		clone->bi_iter.bi_sector =
			orig_bio->bi_iter.bi_sector + zwp_offset;
		break;
	default:
		DMWARN_LIMIT("Invalid BIO operation");
		return false;
	}

	/* Cannot write to a full zone */
	if (zwp_offset >= zsectors)
		return false;

	return true;
}

/*
 * Second phase of BIO mapping for targets with zone append emulation:
 * update the zone write pointer offset array to account for the additional
 * data written to a zone. Note that at this point, the remapped clone BIO
 * may already have completed, so we do not touch it.
 */
static blk_status_t dm_zone_map_bio_end(struct mapped_device *md,
					struct bio *orig_bio,
					unsigned int nr_sectors)
{
	unsigned int zno = bio_zone_no(orig_bio);
	unsigned int zwp_offset = READ_ONCE(md->zwp_offset[zno]);

	/* The clone BIO may already have been completed and failed */
	if (zwp_offset == DM_ZONE_INVALID_WP_OFST)
		return BLK_STS_IOERR;

	/* Update the zone wp offset */
	switch (bio_op(orig_bio)) {
	case REQ_OP_ZONE_RESET:
		WRITE_ONCE(md->zwp_offset[zno], 0);
		return BLK_STS_OK;
	case REQ_OP_ZONE_FINISH:
		WRITE_ONCE(md->zwp_offset[zno],
			   blk_queue_zone_sectors(md->queue));
		return BLK_STS_OK;
	case REQ_OP_WRITE_ZEROES:
	case REQ_OP_WRITE_SAME:
	case REQ_OP_WRITE:
		WRITE_ONCE(md->zwp_offset[zno], zwp_offset + nr_sectors);
		return BLK_STS_OK;
	case REQ_OP_ZONE_APPEND:
		/*
		 * Check that the target did not truncate the write operation
		 * emulating a zone append.
		 */
		if (nr_sectors != bio_sectors(orig_bio)) {
			DMWARN_LIMIT("Truncated write for zone append");
			return BLK_STS_IOERR;
		}
		WRITE_ONCE(md->zwp_offset[zno], zwp_offset + nr_sectors);
		return BLK_STS_OK;
	default:
		DMWARN_LIMIT("Invalid BIO operation");
		return BLK_STS_IOERR;
	}
}

static inline void dm_zone_lock(struct request_queue *q,
				unsigned int zno, struct bio *clone)
{
	if (WARN_ON_ONCE(bio_flagged(clone, BIO_ZONE_WRITE_LOCKED)))
		return;

	wait_on_bit_lock_io(q->seq_zones_wlock, zno, TASK_UNINTERRUPTIBLE);
	bio_set_flag(clone, BIO_ZONE_WRITE_LOCKED);
}

static inline void dm_zone_unlock(struct request_queue *q,
				  unsigned int zno, struct bio *clone)
{
	if (!bio_flagged(clone, BIO_ZONE_WRITE_LOCKED))
		return;

	WARN_ON_ONCE(!test_bit(zno, q->seq_zones_wlock));
	clear_bit_unlock(zno, q->seq_zones_wlock);
	smp_mb__after_atomic();
	wake_up_bit(q->seq_zones_wlock, zno);

	bio_clear_flag(clone, BIO_ZONE_WRITE_LOCKED);
}

static bool dm_need_zone_wp_tracking(struct bio *orig_bio)
{
	/*
	 * Special processing is not needed for operations that do not need the
	 * zone write lock, that is, all operations that target conventional
	 * zones and all operations that do not modify directly a sequential
	 * zone write pointer.
	 */
	if (op_is_flush(orig_bio->bi_opf) && !bio_sectors(orig_bio))
		return false;
	switch (bio_op(orig_bio)) {
	case REQ_OP_WRITE_ZEROES:
	case REQ_OP_WRITE_SAME:
	case REQ_OP_WRITE:
	case REQ_OP_ZONE_RESET:
	case REQ_OP_ZONE_FINISH:
	case REQ_OP_ZONE_APPEND:
		return bio_zone_is_seq(orig_bio);
	default:
		return false;
	}
}

/*
 * Special IO mapping for targets needing zone append emulation.
 */
int dm_zone_map_bio(struct dm_target_io *tio)
{
	struct dm_io *io = tio->io;
	struct dm_target *ti = tio->ti;
	struct mapped_device *md = io->md;
	struct request_queue *q = md->queue;
	struct bio *orig_bio = io->orig_bio;
	struct bio *clone = &tio->clone;
	unsigned int zno;
	blk_status_t sts;
	int r;

	/*
	 * IOs that do not change a zone write pointer do not need
	 * any additional special processing.
	 */
	if (!dm_need_zone_wp_tracking(orig_bio))
		return ti->type->map(ti, clone);

	/* Lock the target zone */
	zno = bio_zone_no(orig_bio);
	dm_zone_lock(q, zno, clone);

	/*
	 * Check that the bio and the target zone write pointer offset are
	 * both valid, and if the bio is a zone append, remap it to a write.
	 */
	if (!dm_zone_map_bio_begin(md, orig_bio, clone)) {
		dm_zone_unlock(q, zno, clone);
		return DM_MAPIO_KILL;
	}

	/*
	 * The target map function may issue and complete the IO quickly.
	 * Take an extra reference on the IO to make sure it does disappear
	 * until we run dm_zone_map_bio_end().
	 */
	dm_io_inc_pending(io);

	/* Let the target do its work */
	r = ti->type->map(ti, clone);
	switch (r) {
	case DM_MAPIO_SUBMITTED:
		/*
		 * The target submitted the clone BIO. The target zone will
		 * be unlocked on completion of the clone.
		 */
		sts = dm_zone_map_bio_end(md, orig_bio, *tio->len_ptr);
		break;
	case DM_MAPIO_REMAPPED:
		/*
		 * The target only remapped the clone BIO. In case of error,
		 * unlock the target zone here as the clone will not be
		 * submitted.
		 */
		sts = dm_zone_map_bio_end(md, orig_bio, *tio->len_ptr);
		if (sts != BLK_STS_OK)
			dm_zone_unlock(q, zno, clone);
		break;
	case DM_MAPIO_REQUEUE:
	case DM_MAPIO_KILL:
	default:
		dm_zone_unlock(q, zno, clone);
		sts = BLK_STS_IOERR;
		break;
	}

	/* Drop the extra reference on the IO */
	dm_io_dec_pending(io, sts);

	if (sts != BLK_STS_OK)
		return DM_MAPIO_KILL;

	return r;
}

/*
 * IO completion callback called from clone_endio().
 */
void dm_zone_endio(struct dm_io *io, struct bio *clone)
{
	struct mapped_device *md = io->md;
	struct request_queue *q = md->queue;
	struct bio *orig_bio = io->orig_bio;
	unsigned int zwp_offset;
	unsigned int zno;

	/*
	 * For targets that do not emulate zone append, we only need to
	 * handle native zone-append bios.
	 */
	if (!dm_emulate_zone_append(md)) {
		/*
		 * Get the offset within the zone of the written sector
		 * and add that to the original bio sector position.
		 */
		if (clone->bi_status == BLK_STS_OK &&
		    bio_op(clone) == REQ_OP_ZONE_APPEND) {
			sector_t mask = (sector_t)blk_queue_zone_sectors(q) - 1;

			orig_bio->bi_iter.bi_sector +=
				clone->bi_iter.bi_sector & mask;
		}

		return;
	}

	/*
	 * For targets that do emulate zone append, if the clone BIO does not
	 * own the target zone write lock, we have nothing to do.
	 */
	if (!bio_flagged(clone, BIO_ZONE_WRITE_LOCKED))
		return;

	zno = bio_zone_no(orig_bio);

	if (clone->bi_status != BLK_STS_OK) {
		/*
		 * BIOs that modify a zone write pointer may leave the zone
		 * in an unknown state in case of failure (e.g. the write
		 * pointer was only partially advanced). In this case, set
		 * the target zone write pointer as invalid unless it is
		 * already being updated.
		 */
		WRITE_ONCE(md->zwp_offset[zno], DM_ZONE_INVALID_WP_OFST);
	} else if (bio_op(orig_bio) == REQ_OP_ZONE_APPEND) {
		/*
		 * Get the written sector for zone append operation that were
		 * emulated using regular write operations.
		 */
		zwp_offset = READ_ONCE(md->zwp_offset[zno]);
		if (WARN_ON_ONCE(zwp_offset < bio_sectors(orig_bio)))
			WRITE_ONCE(md->zwp_offset[zno],
				   DM_ZONE_INVALID_WP_OFST);
		else
			orig_bio->bi_iter.bi_sector +=
				zwp_offset - bio_sectors(orig_bio);
	}

	dm_zone_unlock(q, zno, clone);
}