blk-zoned.c 8.7 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18
/*
 * 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/rbtree.h>
#include <linux/blkdev.h>

static inline sector_t blk_zone_start(struct request_queue *q,
				      sector_t sector)
{
19
	sector_t zone_mask = blk_queue_zone_sectors(q) - 1;
20 21 22 23

	return sector & ~zone_mask;
}

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
/*
 * 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->seq_zones_wlock)
		return false;

	if (blk_rq_is_passthrough(rq))
		return false;

	switch (req_op(rq)) {
	case REQ_OP_WRITE_ZEROES:
	case REQ_OP_WRITE_SAME:
	case REQ_OP_WRITE:
		return blk_rq_zone_is_seq(rq);
	default:
		return false;
	}
}
EXPORT_SYMBOL_GPL(blk_req_needs_zone_write_lock);

void __blk_req_zone_write_lock(struct request *rq)
{
	if (WARN_ON_ONCE(test_and_set_bit(blk_rq_zone_no(rq),
					  rq->q->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->seq_zones_wlock)
		WARN_ON_ONCE(!test_and_clear_bit(blk_rq_zone_no(rq),
						 rq->q->seq_zones_wlock));
}
EXPORT_SYMBOL_GPL(__blk_req_zone_write_unlock);

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
/*
 * Check that a zone report belongs to the partition.
 * If yes, fix its start sector and write pointer, copy it in the
 * zone information array and return true. Return false otherwise.
 */
static bool blkdev_report_zone(struct block_device *bdev,
			       struct blk_zone *rep,
			       struct blk_zone *zone)
{
	sector_t offset = get_start_sect(bdev);

	if (rep->start < offset)
		return false;

	rep->start -= offset;
	if (rep->start + rep->len > bdev->bd_part->nr_sects)
		return false;

	if (rep->type == BLK_ZONE_TYPE_CONVENTIONAL)
		rep->wp = rep->start + rep->len;
	else
		rep->wp -= offset;
	memcpy(zone, rep, sizeof(struct blk_zone));

	return true;
}

/**
 * blkdev_report_zones - Get zones information
 * @bdev:	Target block device
 * @sector:	Sector from which to report zones
 * @zones:	Array of zone structures where to return the zones information
 * @nr_zones:	Number of zone structures in the zone array
 * @gfp_mask:	Memory allocation flags (for bio_alloc)
 *
 * Description:
 *    Get zone information starting from the zone containing @sector.
 *    The number of zone information reported may be less than the number
 *    requested by @nr_zones. The number of zones actually reported is
 *    returned in @nr_zones.
 */
int blkdev_report_zones(struct block_device *bdev,
			sector_t sector,
			struct blk_zone *zones,
			unsigned int *nr_zones,
			gfp_t gfp_mask)
{
	struct request_queue *q = bdev_get_queue(bdev);
	struct blk_zone_report_hdr *hdr;
	unsigned int nrz = *nr_zones;
	struct page *page;
	unsigned int nr_rep;
	size_t rep_bytes;
	unsigned int nr_pages;
	struct bio *bio;
	struct bio_vec *bv;
	unsigned int i, n, nz;
	unsigned int ofst;
	void *addr;
125
	int ret;
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

	if (!q)
		return -ENXIO;

	if (!blk_queue_is_zoned(q))
		return -EOPNOTSUPP;

	if (!nrz)
		return 0;

	if (sector > bdev->bd_part->nr_sects) {
		*nr_zones = 0;
		return 0;
	}

	/*
	 * The zone report has a header. So make room for it in the
	 * payload. Also make sure that the report fits in a single BIO
	 * that will not be split down the stack.
	 */
	rep_bytes = sizeof(struct blk_zone_report_hdr) +
		sizeof(struct blk_zone) * nrz;
	rep_bytes = (rep_bytes + PAGE_SIZE - 1) & PAGE_MASK;
	if (rep_bytes > (queue_max_sectors(q) << 9))
		rep_bytes = queue_max_sectors(q) << 9;

	nr_pages = min_t(unsigned int, BIO_MAX_PAGES,
			 rep_bytes >> PAGE_SHIFT);
	nr_pages = min_t(unsigned int, nr_pages,
			 queue_max_segments(q));

	bio = bio_alloc(gfp_mask, nr_pages);
	if (!bio)
		return -ENOMEM;

161
	bio_set_dev(bio, bdev);
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
	bio->bi_iter.bi_sector = blk_zone_start(q, sector);
	bio_set_op_attrs(bio, REQ_OP_ZONE_REPORT, 0);

	for (i = 0; i < nr_pages; i++) {
		page = alloc_page(gfp_mask);
		if (!page) {
			ret = -ENOMEM;
			goto out;
		}
		if (!bio_add_page(bio, page, PAGE_SIZE, 0)) {
			__free_page(page);
			break;
		}
	}

	if (i == 0)
		ret = -ENOMEM;
	else
		ret = submit_bio_wait(bio);
	if (ret)
		goto out;

	/*
	 * Process the report result: skip the header and go through the
	 * reported zones to fixup and fixup the zone information for
	 * partitions. At the same time, return the zone information into
	 * the zone array.
	 */
	n = 0;
	nz = 0;
	nr_rep = 0;
	bio_for_each_segment_all(bv, bio, i) {

		if (!bv->bv_page)
			break;

		addr = kmap_atomic(bv->bv_page);

		/* Get header in the first page */
		ofst = 0;
		if (!nr_rep) {
			hdr = (struct blk_zone_report_hdr *) addr;
			nr_rep = hdr->nr_zones;
			ofst = sizeof(struct blk_zone_report_hdr);
		}

		/* Fixup and report zones */
		while (ofst < bv->bv_len &&
		       n < nr_rep && nz < nrz) {
			if (blkdev_report_zone(bdev, addr + ofst, &zones[nz]))
				nz++;
			ofst += sizeof(struct blk_zone);
			n++;
		}

		kunmap_atomic(addr);

		if (n >= nr_rep || nz >= nrz)
			break;

	}

224
	*nr_zones = nz;
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
out:
	bio_for_each_segment_all(bv, bio, i)
		__free_page(bv->bv_page);
	bio_put(bio);

	return ret;
}
EXPORT_SYMBOL_GPL(blkdev_report_zones);

/**
 * blkdev_reset_zones - Reset zones write pointer
 * @bdev:	Target block device
 * @sector:	Start sector of the first zone to reset
 * @nr_sectors:	Number of sectors, at least the length of one zone
 * @gfp_mask:	Memory allocation flags (for bio_alloc)
 *
 * Description:
 *    Reset the write pointer of the zones contained in the range
 *    @[email protected][email protected]_sectors. Specifying the entire disk sector range
 *    is valid, but the specified range should not contain conventional zones.
 */
int blkdev_reset_zones(struct block_device *bdev,
		       sector_t sector, sector_t nr_sectors,
		       gfp_t gfp_mask)
{
	struct request_queue *q = bdev_get_queue(bdev);
	sector_t zone_sectors;
	sector_t end_sector = sector + nr_sectors;
	struct bio *bio;
	int ret;

	if (!q)
		return -ENXIO;

	if (!blk_queue_is_zoned(q))
		return -EOPNOTSUPP;

	if (end_sector > bdev->bd_part->nr_sects)
		/* Out of range */
		return -EINVAL;

	/* Check alignment (handle eventual smaller last zone) */
267
	zone_sectors = blk_queue_zone_sectors(q);
268 269 270 271 272 273 274 275 276 277 278
	if (sector & (zone_sectors - 1))
		return -EINVAL;

	if ((nr_sectors & (zone_sectors - 1)) &&
	    end_sector != bdev->bd_part->nr_sects)
		return -EINVAL;

	while (sector < end_sector) {

		bio = bio_alloc(gfp_mask, 0);
		bio->bi_iter.bi_sector = sector;
279
		bio_set_dev(bio, bdev);
280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297
		bio_set_op_attrs(bio, REQ_OP_ZONE_RESET, 0);

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

		if (ret)
			return ret;

		sector += zone_sectors;

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

	}

	return 0;
}
EXPORT_SYMBOL_GPL(blkdev_reset_zones);
Shaun Tancheff's avatar
Shaun Tancheff committed
298

299
/*
Shaun Tancheff's avatar
Shaun Tancheff committed
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
 * BLKREPORTZONE ioctl processing.
 * Called from blkdev_ioctl.
 */
int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
			      unsigned int cmd, unsigned long arg)
{
	void __user *argp = (void __user *)arg;
	struct request_queue *q;
	struct blk_zone_report rep;
	struct blk_zone *zones;
	int ret;

	if (!argp)
		return -EINVAL;

	q = bdev_get_queue(bdev);
	if (!q)
		return -ENXIO;

	if (!blk_queue_is_zoned(q))
		return -ENOTTY;

	if (!capable(CAP_SYS_ADMIN))
		return -EACCES;

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

	if (!rep.nr_zones)
		return -EINVAL;

331 332 333 334 335
	if (rep.nr_zones > INT_MAX / sizeof(struct blk_zone))
		return -ERANGE;

	zones = kvmalloc(rep.nr_zones * sizeof(struct blk_zone),
			GFP_KERNEL | __GFP_ZERO);
Shaun Tancheff's avatar
Shaun Tancheff committed
336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356
	if (!zones)
		return -ENOMEM;

	ret = blkdev_report_zones(bdev, rep.sector,
				  zones, &rep.nr_zones,
				  GFP_KERNEL);
	if (ret)
		goto out;

	if (copy_to_user(argp, &rep, sizeof(struct blk_zone_report))) {
		ret = -EFAULT;
		goto out;
	}

	if (rep.nr_zones) {
		if (copy_to_user(argp + sizeof(struct blk_zone_report), zones,
				 sizeof(struct blk_zone) * rep.nr_zones))
			ret = -EFAULT;
	}

 out:
357
	kvfree(zones);
Shaun Tancheff's avatar
Shaun Tancheff committed
358 359 360 361

	return ret;
}

362
/*
Shaun Tancheff's avatar
Shaun Tancheff committed
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
 * BLKRESETZONE ioctl processing.
 * Called from blkdev_ioctl.
 */
int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode,
			     unsigned int cmd, unsigned long arg)
{
	void __user *argp = (void __user *)arg;
	struct request_queue *q;
	struct blk_zone_range zrange;

	if (!argp)
		return -EINVAL;

	q = bdev_get_queue(bdev);
	if (!q)
		return -ENXIO;

	if (!blk_queue_is_zoned(q))
		return -ENOTTY;

	if (!capable(CAP_SYS_ADMIN))
		return -EACCES;

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

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

	return blkdev_reset_zones(bdev, zrange.sector, zrange.nr_sectors,
				  GFP_KERNEL);
}