summaryrefslogtreecommitdiffstats
path: root/block/blk-zoned.c
blob: da0f4b2a8fa09330bdc71bf545ed2dc688326392 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Zoned block device handling
 *
 * Copyright (c) 2015, Hannes Reinecke
 * Copyright (c) 2015, SUSE Linux GmbH
 *
 * Copyright (c) 2016, Damien Le Moal
 * Copyright (c) 2016, Western Digital
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/blkdev.h>
#include <linux/blk-mq.h>
#include <linux/mm.h>
#include <linux/vmalloc.h>
#include <linux/sched/mm.h>

#include "blk.h"

#define ZONE_COND_NAME(name) [BLK_ZONE_COND_##name] = #name
static const char *const zone_cond_name[] = {
	ZONE_COND_NAME(NOT_WP),
	ZONE_COND_NAME(EMPTY),
	ZONE_COND_NAME(IMP_OPEN),
	ZONE_COND_NAME(EXP_OPEN),
	ZONE_COND_NAME(CLOSED),
	ZONE_COND_NAME(READONLY),
	ZONE_COND_NAME(FULL),
	ZONE_COND_NAME(OFFLINE),
};
#undef ZONE_COND_NAME

/**
 * blk_zone_cond_str - Return string XXX in BLK_ZONE_COND_XXX.
 * @zone_cond: BLK_ZONE_COND_XXX.
 *
 * Description: Centralize block layer function to convert BLK_ZONE_COND_XXX
 * into string format. Useful in the debugging and tracing zone conditions. For
 * invalid BLK_ZONE_COND_XXX it returns string "UNKNOWN".
 */
const char *blk_zone_cond_str(enum blk_zone_cond zone_cond)
{
	static const char *zone_cond_str = "UNKNOWN";

	if (zone_cond < ARRAY_SIZE(zone_cond_name) && zone_cond_name[zone_cond])
		zone_cond_str = zone_cond_name[zone_cond];

	return zone_cond_str;
}
EXPORT_SYMBOL_GPL(blk_zone_cond_str);

/*
 * Return true if a request is a write requests that needs zone write locking.
 */
bool blk_req_needs_zone_write_lock(struct request *rq)
{
	if (!rq->q->disk->seq_zones_wlock)
		return false;

	return blk_rq_is_seq_zoned_write(rq);
}
EXPORT_SYMBOL_GPL(blk_req_needs_zone_write_lock);

bool blk_req_zone_write_trylock(struct request *rq)
{
	unsigned int zno = blk_rq_zone_no(rq);

	if (test_and_set_bit(zno, rq->q->disk->seq_zones_wlock))
		return false;

	WARN_ON_ONCE(rq->rq_flags & RQF_ZONE_WRITE_LOCKED);
	rq->rq_flags |= RQF_ZONE_WRITE_LOCKED;

	return true;
}
EXPORT_SYMBOL_GPL(blk_req_zone_write_trylock);

void __blk_req_zone_write_lock(struct request *rq)
{
	if (WARN_ON_ONCE(test_and_set_bit(blk_rq_zone_no(rq),
					  rq->q->disk->seq_zones_wlock)))
		return;

	WARN_ON_ONCE(rq->rq_flags & RQF_ZONE_WRITE_LOCKED);
	rq->rq_flags |= RQF_ZONE_WRITE_LOCKED;
}
EXPORT_SYMBOL_GPL(__blk_req_zone_write_lock);

void __blk_req_zone_write_unlock(struct request *rq)
{
	rq->rq_flags &= ~RQF_ZONE_WRITE_LOCKED;
	if (rq->q->disk->seq_zones_wlock)
		WARN_ON_ONCE(!test_and_clear_bit(blk_rq_zone_no(rq),
						 rq->q->disk->seq_zones_wlock));
}
EXPORT_SYMBOL_GPL(__blk_req_zone_write_unlock);

/**
 * bdev_nr_zones - Get number of zones
 * @bdev:	Target device
 *
 * Return the total number of zones of a zoned block device.  For a block
 * device without zone capabilities, the number of zones is always 0.
 */
unsigned int bdev_nr_zones(struct block_device *bdev)
{
	sector_t zone_sectors = bdev_zone_sectors(bdev);

	if (!bdev_is_zoned(bdev))
		return 0;
	return (bdev_nr_sectors(bdev) + zone_sectors - 1) >>
		ilog2(zone_sectors);
}
EXPORT_SYMBOL_GPL(bdev_nr_zones);

/**
 * blkdev_report_zones - Get zones information
 * @bdev:	Target block device
 * @sector:	Sector from which to report zones
 * @nr_zones:	Maximum number of zones to report
 * @cb:		Callback function called for each reported zone
 * @data:	Private data for the callback
 *
 * Description:
 *    Get zone information starting from the zone containing @sector for at most
 *    @nr_zones, and call @cb for each zone reported by the device.
 *    To report all zones in a device starting from @sector, the BLK_ALL_ZONES
 *    constant can be passed to @nr_zones.
 *    Returns the number of zones reported by the device, or a negative errno
 *    value in case of failure.
 *
 *    Note: The caller must use memalloc_noXX_save/restore() calls to control
 *    memory allocations done within this function.
 */
int blkdev_report_zones(struct block_device *bdev, sector_t sector,
			unsigned int nr_zones, report_zones_cb cb, void *data)
{
	struct gendisk *disk = bdev->bd_disk;
	sector_t capacity = get_capacity(disk);

	if (!bdev_is_zoned(bdev) || WARN_ON_ONCE(!disk->fops->report_zones))
		return -EOPNOTSUPP;

	if (!nr_zones || sector >= capacity)
		return 0;

	return disk->fops->report_zones(disk, sector, nr_zones, cb, data);
}
EXPORT_SYMBOL_GPL(blkdev_report_zones);

static inline unsigned long *blk_alloc_zone_bitmap(int node,
						   unsigned int nr_zones)
{
	return kcalloc_node(BITS_TO_LONGS(nr_zones), sizeof(unsigned long),
			    GFP_NOIO, node);
}

static int blk_zone_need_reset_cb(struct blk_zone *zone, unsigned int idx,
				  void *data)
{
	/*
	 * For an all-zones reset, ignore conventional, empty, read-only
	 * and offline zones.
	 */
	switch (zone->cond) {
	case BLK_ZONE_COND_NOT_WP:
	case BLK_ZONE_COND_EMPTY:
	case BLK_ZONE_COND_READONLY:
	case BLK_ZONE_COND_OFFLINE:
		return 0;
	default:
		set_bit(idx, (unsigned long *)data);
		return 0;
	}
}

static int blkdev_zone_reset_all_emulated(struct block_device *bdev)
{
	struct gendisk *disk = bdev->bd_disk;
	sector_t capacity = bdev_nr_sectors(bdev);
	sector_t zone_sectors = bdev_zone_sectors(bdev);
	unsigned long *need_reset;
	struct bio *bio = NULL;
	sector_t sector = 0;
	int ret;

	need_reset = blk_alloc_zone_bitmap(disk->queue->node, disk->nr_zones);
	if (!need_reset)
		return -ENOMEM;

	ret = disk->fops->report_zones(disk, 0, disk->nr_zones,
				       blk_zone_need_reset_cb, need_reset);
	if (ret < 0)
		goto out_free_need_reset;

	ret = 0;
	while (sector < capacity) {
		if (!test_bit(disk_zone_no(disk, sector), need_reset)) {
			sector += zone_sectors;
			continue;
		}

		bio = blk_next_bio(bio, bdev, 0, REQ_OP_ZONE_RESET | REQ_SYNC,
				   GFP_KERNEL);
		bio->bi_iter.bi_sector = sector;
		sector += zone_sectors;

		/* This may take a while, so be nice to others */
		cond_resched();
	}

	if (bio) {
		ret = submit_bio_wait(bio);
		bio_put(bio);
	}

out_free_need_reset:
	kfree(need_reset);
	return ret;
}

static int blkdev_zone_reset_all(struct block_device *bdev)
{
	struct bio bio;

	bio_init(&bio, bdev, NULL, 0, REQ_OP_ZONE_RESET_ALL | REQ_SYNC);
	return submit_bio_wait(&bio);
}

/**
 * blkdev_zone_mgmt - Execute a zone management operation on a range of zones
 * @bdev:	Target block device
 * @op:		Operation to be performed on the zones
 * @sector:	Start sector of the first zone to operate on
 * @nr_sectors:	Number of sectors, should be at least the length of one zone and
 *		must be zone size aligned.
 *
 * Description:
 *    Perform the specified operation on the range of zones specified by
 *    @sector..@sector+@nr_sectors. Specifying the entire disk sector range
 *    is valid, but the specified range should not contain conventional zones.
 *    The operation to execute on each zone can be a zone reset, open, close
 *    or finish request.
 */
int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
		     sector_t sector, sector_t nr_sectors)
{
	struct request_queue *q = bdev_get_queue(bdev);
	sector_t zone_sectors = bdev_zone_sectors(bdev);
	sector_t capacity = bdev_nr_sectors(bdev);
	sector_t end_sector = sector + nr_sectors;
	struct bio *bio = NULL;
	int ret = 0;

	if (!bdev_is_zoned(bdev))
		return -EOPNOTSUPP;

	if (bdev_read_only(bdev))
		return -EPERM;

	if (!op_is_zone_mgmt(op))
		return -EOPNOTSUPP;

	if (end_sector <= sector || end_sector > capacity)
		/* Out of range */
		return -EINVAL;

	/* Check alignment (handle eventual smaller last zone) */
	if (!bdev_is_zone_start(bdev, sector))
		return -EINVAL;

	if (!bdev_is_zone_start(bdev, nr_sectors) && end_sector != capacity)
		return -EINVAL;

	/*
	 * In the case of a zone reset operation over all zones,
	 * REQ_OP_ZONE_RESET_ALL can be used with devices supporting this
	 * command. For other devices, we emulate this command behavior by
	 * identifying the zones needing a reset.
	 */
	if (op == REQ_OP_ZONE_RESET && sector == 0 && nr_sectors == capacity) {
		if (!blk_queue_zone_resetall(q))
			return blkdev_zone_reset_all_emulated(bdev);
		return blkdev_zone_reset_all(bdev);
	}

	while (sector < end_sector) {
		bio = blk_next_bio(bio, bdev, 0, op | REQ_SYNC, GFP_KERNEL);
		bio->bi_iter.bi_sector = sector;
		sector += zone_sectors;

		/* This may take a while, so be nice to others */
		cond_resched();
	}

	ret = submit_bio_wait(bio);
	bio_put(bio);

	return ret;
}
EXPORT_SYMBOL_GPL(blkdev_zone_mgmt);

struct zone_report_args {
	struct blk_zone __user *zones;
};

static int blkdev_copy_zone_to_user(struct blk_zone *zone, unsigned int idx,
				    void *data)
{
	struct zone_report_args *args = data;

	if (copy_to_user(&args->zones[idx], zone, sizeof(struct blk_zone)))
		return -EFAULT;
	return 0;
}

/*
 * BLKREPORTZONE ioctl processing.
 * Called from blkdev_ioctl.
 */
int blkdev_report_zones_ioctl(struct block_device *bdev, unsigned int cmd,
		unsigned long arg)
{
	void __user *argp = (void __user *)arg;
	struct zone_report_args args;
	struct blk_zone_report rep;
	int ret;

	if (!argp)
		return -EINVAL;

	if (!bdev_is_zoned(bdev))
		return -ENOTTY;

	if (copy_from_user(&rep, argp, sizeof(struct blk_zone_report)))
		return -EFAULT;

	if (!rep.nr_zones)
		return -EINVAL;

	args.zones = argp + sizeof(struct blk_zone_report);
	ret = blkdev_report_zones(bdev, rep.sector, rep.nr_zones,
				  blkdev_copy_zone_to_user, &args);
	if (ret < 0)
		return ret;

	rep.nr_zones = ret;
	rep.flags = BLK_ZONE_REP_CAPACITY;
	if (copy_to_user(argp, &rep, sizeof(struct blk_zone_report)))
		return -EFAULT;
	return 0;
}

static int blkdev_truncate_zone_range(struct block_device *bdev,
		blk_mode_t mode, const struct blk_zone_range *zrange)
{
	loff_t start, end;

	if (zrange->sector + zrange->nr_sectors <= zrange->sector ||
	    zrange->sector + zrange->nr_sectors > get_capacity(bdev->bd_disk))
		/* Out of range */
		return -EINVAL;

	start = zrange->sector << SECTOR_SHIFT;
	end = ((zrange->sector + zrange->nr_sectors) << SECTOR_SHIFT) - 1;

	return truncate_bdev_range(bdev, mode, start, end);
}

/*
 * BLKRESETZONE, BLKOPENZONE, BLKCLOSEZONE and BLKFINISHZONE ioctl processing.
 * Called from blkdev_ioctl.
 */
int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode,
			   unsigned int cmd, unsigned long arg)
{
	void __user *argp = (void __user *)arg;
	struct blk_zone_range zrange;
	enum req_op op;
	int ret;

	if (!argp)
		return -EINVAL;

	if (!bdev_is_zoned(bdev))
		return -ENOTTY;

	if (!(mode & BLK_OPEN_WRITE))
		return -EBADF;

	if (copy_from_user(&zrange, argp, sizeof(struct blk_zone_range)))
		return -EFAULT;

	switch (cmd) {
	case BLKRESETZONE:
		op = REQ_OP_ZONE_RESET;

		/* Invalidate the page cache, including dirty pages. */
		filemap_invalidate_lock(bdev->bd_inode->i_mapping);
		ret = blkdev_truncate_zone_range(bdev, mode, &zrange);
		if (ret)
			goto fail;
		break;
	case BLKOPENZONE:
		op = REQ_OP_ZONE_OPEN;
		break;
	case BLKCLOSEZONE:
		op = REQ_OP_ZONE_CLOSE;
		break;
	case BLKFINISHZONE:
		op = REQ_OP_ZONE_FINISH;
		break;
	default:
		return -ENOTTY;
	}

	ret = blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors);

fail:
	if (cmd == BLKRESETZONE)
		filemap_invalidate_unlock(bdev->bd_inode->i_mapping);

	return ret;
}

void disk_free_zone_bitmaps(struct gendisk *disk)
{
	kfree(disk->conv_zones_bitmap);
	disk->conv_zones_bitmap = NULL;
	kfree(disk->seq_zones_wlock);
	disk->seq_zones_wlock = NULL;
}

struct blk_revalidate_zone_args {
	struct gendisk	*disk;
	unsigned long	*conv_zones_bitmap;
	unsigned long	*seq_zones_wlock;
	unsigned int	nr_zones;
	sector_t	sector;
};

/*
 * Helper function to check the validity of zones of a zoned block device.
 */
static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx,
				  void *data)
{
	struct blk_revalidate_zone_args *args = data;
	struct gendisk *disk = args->disk;
	struct request_queue *q = disk->queue;
	sector_t capacity = get_capacity(disk);
	sector_t zone_sectors = q->limits.chunk_sectors;

	/* Check for bad zones and holes in the zone report */
	if (zone->start != args->sector) {
		pr_warn("%s: Zone gap at sectors %llu..%llu\n",
			disk->disk_name, args->sector, zone->start);
		return -ENODEV;
	}

	if (zone->start >= capacity || !zone->len) {
		pr_warn("%s: Invalid zone start %llu, length %llu\n",
			disk->disk_name, zone->start, zone->len);
		return -ENODEV;
	}

	/*
	 * All zones must have the same size, with the exception on an eventual
	 * smaller last zone.
	 */
	if (zone->start + zone->len < capacity) {
		if (zone->len != zone_sectors) {
			pr_warn("%s: Invalid zoned device with non constant zone size\n",
				disk->disk_name);
			return -ENODEV;
		}
	} else if (zone->len > zone_sectors) {
		pr_warn("%s: Invalid zoned device with larger last zone size\n",
			disk->disk_name);
		return -ENODEV;
	}

	/* Check zone type */
	switch (zone->type) {
	case BLK_ZONE_TYPE_CONVENTIONAL:
		if (!args->conv_zones_bitmap) {
			args->conv_zones_bitmap =
				blk_alloc_zone_bitmap(q->node, args->nr_zones);
			if (!args->conv_zones_bitmap)
				return -ENOMEM;
		}
		set_bit(idx, args->conv_zones_bitmap);
		break;
	case BLK_ZONE_TYPE_SEQWRITE_REQ:
		if (!args->seq_zones_wlock) {
			args->seq_zones_wlock =
				blk_alloc_zone_bitmap(q->node, args->nr_zones);
			if (!args->seq_zones_wlock)
				return -ENOMEM;
		}
		break;
	case BLK_ZONE_TYPE_SEQWRITE_PREF:
	default:
		pr_warn("%s: Invalid zone type 0x%x at sectors %llu\n",
			disk->disk_name, (int)zone->type, zone->start);
		return -ENODEV;
	}

	args->sector += zone->len;
	return 0;
}

/**
 * blk_revalidate_disk_zones - (re)allocate and initialize zone bitmaps
 * @disk:	Target disk
 * @update_driver_data:	Callback to update driver data on the frozen disk
 *
 * Helper function for low-level device drivers to check and (re) allocate and
 * initialize a disk request queue zone bitmaps. This functions should normally
 * be called within the disk ->revalidate method for blk-mq based drivers.
 * Before calling this function, the device driver must already have set the
 * device zone size (chunk_sector limit) and the max zone append limit.
 * For BIO based drivers, this function cannot be used. BIO based device drivers
 * only need to set disk->nr_zones so that the sysfs exposed value is correct.
 * If the @update_driver_data callback function is not NULL, the callback is
 * executed with the device request queue frozen after all zones have been
 * checked.
 */
int blk_revalidate_disk_zones(struct gendisk *disk,
			      void (*update_driver_data)(struct gendisk *disk))
{
	struct request_queue *q = disk->queue;
	sector_t zone_sectors = q->limits.chunk_sectors;
	sector_t capacity = get_capacity(disk);
	struct blk_revalidate_zone_args args = { };
	unsigned int noio_flag;
	int ret;

	if (WARN_ON_ONCE(!blk_queue_is_zoned(q)))
		return -EIO;
	if (WARN_ON_ONCE(!queue_is_mq(q)))
		return -EIO;

	if (!capacity)
		return -ENODEV;

	/*
	 * Checks that the device driver indicated a valid zone size and that
	 * the max zone append limit is set.
	 */
	if (!zone_sectors || !is_power_of_2(zone_sectors)) {
		pr_warn("%s: Invalid non power of two zone size (%llu)\n",
			disk->disk_name, zone_sectors);
		return -ENODEV;
	}

	if (!q->limits.max_zone_append_sectors) {
		pr_warn("%s: Invalid 0 maximum zone append limit\n",
			disk->disk_name);
		return -ENODEV;
	}

	/*
	 * Ensure that all memory allocations in this context are done as if
	 * GFP_NOIO was specified.
	 */
	args.disk = disk;
	args.nr_zones = (capacity + zone_sectors - 1) >> ilog2(zone_sectors);
	noio_flag = memalloc_noio_save();
	ret = disk->fops->report_zones(disk, 0, UINT_MAX,
				       blk_revalidate_zone_cb, &args);
	if (!ret) {
		pr_warn("%s: No zones reported\n", disk->disk_name);
		ret = -ENODEV;
	}
	memalloc_noio_restore(noio_flag);

	/*
	 * If zones where reported, make sure that the entire disk capacity
	 * has been checked.
	 */
	if (ret > 0 && args.sector != capacity) {
		pr_warn("%s: Missing zones from sector %llu\n",
			disk->disk_name, args.sector);
		ret = -ENODEV;
	}

	/*
	 * Install the new bitmaps and update nr_zones only once the queue is
	 * stopped and all I/Os are completed (i.e. a scheduler is not
	 * referencing the bitmaps).
	 */
	blk_mq_freeze_queue(q);
	if (ret > 0) {
		disk->nr_zones = args.nr_zones;
		swap(disk->seq_zones_wlock, args.seq_zones_wlock);
		swap(disk->conv_zones_bitmap, args.conv_zones_bitmap);
		if (update_driver_data)
			update_driver_data(disk);
		ret = 0;
	} else {
		pr_warn("%s: failed to revalidate zones\n", disk->disk_name);
		disk_free_zone_bitmaps(disk);
	}
	blk_mq_unfreeze_queue(q);

	kfree(args.seq_zones_wlock);
	kfree(args.conv_zones_bitmap);
	return ret;
}
EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones);