namespace_devs.c 58.7 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14
/*
 * Copyright(c) 2013-2015 Intel Corporation. All rights reserved.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of version 2 of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * General Public License for more details.
 */
#include <linux/module.h>
#include <linux/device.h>
15
#include <linux/sort.h>
16
#include <linux/slab.h>
17
#include <linux/pmem.h>
18
#include <linux/list.h>
19
#include <linux/nd.h>
20
#include "nd-core.h"
21 22 23 24 25 26 27 28 29
#include "nd.h"

static void namespace_io_release(struct device *dev)
{
	struct nd_namespace_io *nsio = to_nd_namespace_io(dev);

	kfree(nsio);
}

30 31 32
static void namespace_pmem_release(struct device *dev)
{
	struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
33
	struct nd_region *nd_region = to_nd_region(dev->parent);
34

35 36
	if (nspm->id >= 0)
		ida_simple_remove(&nd_region->ns_ida, nspm->id);
37 38 39 40 41 42 43
	kfree(nspm->alt_name);
	kfree(nspm->uuid);
	kfree(nspm);
}

static void namespace_blk_release(struct device *dev)
{
44 45 46 47 48 49 50 51 52
	struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
	struct nd_region *nd_region = to_nd_region(dev->parent);

	if (nsblk->id >= 0)
		ida_simple_remove(&nd_region->ns_ida, nsblk->id);
	kfree(nsblk->alt_name);
	kfree(nsblk->uuid);
	kfree(nsblk->res);
	kfree(nsblk);
53 54
}

55
static const struct device_type namespace_io_device_type = {
56 57 58 59
	.name = "nd_namespace_io",
	.release = namespace_io_release,
};

60
static const struct device_type namespace_pmem_device_type = {
61 62 63 64
	.name = "nd_namespace_pmem",
	.release = namespace_pmem_release,
};

65
static const struct device_type namespace_blk_device_type = {
66 67 68 69
	.name = "nd_namespace_blk",
	.release = namespace_blk_release,
};

70
static bool is_namespace_pmem(const struct device *dev)
71 72 73 74
{
	return dev ? dev->type == &namespace_pmem_device_type : false;
}

75
static bool is_namespace_blk(const struct device *dev)
76 77 78 79
{
	return dev ? dev->type == &namespace_blk_device_type : false;
}

80
static bool is_namespace_io(const struct device *dev)
81 82 83 84
{
	return dev ? dev->type == &namespace_io_device_type : false;
}

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
static int is_uuid_busy(struct device *dev, void *data)
{
	u8 *uuid1 = data, *uuid2 = NULL;

	if (is_namespace_pmem(dev)) {
		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);

		uuid2 = nspm->uuid;
	} else if (is_namespace_blk(dev)) {
		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);

		uuid2 = nsblk->uuid;
	} else if (is_nd_btt(dev)) {
		struct nd_btt *nd_btt = to_nd_btt(dev);

		uuid2 = nd_btt->uuid;
	} else if (is_nd_pfn(dev)) {
		struct nd_pfn *nd_pfn = to_nd_pfn(dev);

		uuid2 = nd_pfn->uuid;
	}

	if (uuid2 && memcmp(uuid1, uuid2, NSLABEL_UUID_LEN) == 0)
		return -EBUSY;

	return 0;
}

static int is_namespace_uuid_busy(struct device *dev, void *data)
{
	if (is_nd_pmem(dev) || is_nd_blk(dev))
		return device_for_each_child(dev, data, is_uuid_busy);
	return 0;
}

/**
 * nd_is_uuid_unique - verify that no other namespace has @uuid
 * @dev: any device on a nvdimm_bus
 * @uuid: uuid to check
 */
bool nd_is_uuid_unique(struct device *dev, u8 *uuid)
{
	struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);

	if (!nvdimm_bus)
		return false;
	WARN_ON_ONCE(!is_nvdimm_bus_locked(&nvdimm_bus->dev));
	if (device_for_each_child(&nvdimm_bus->dev, uuid,
				is_namespace_uuid_busy) != 0)
		return false;
	return true;
}

138 139 140
bool pmem_should_map_pages(struct device *dev)
{
	struct nd_region *nd_region = to_nd_region(dev->parent);
141
	struct nd_namespace_io *nsio;
142 143 144 145 146 147 148 149 150 151

	if (!IS_ENABLED(CONFIG_ZONE_DEVICE))
		return false;

	if (!test_bit(ND_REGION_PAGEMAP, &nd_region->flags))
		return false;

	if (is_nd_pfn(dev) || is_nd_btt(dev))
		return false;

152 153 154 155 156 157
	nsio = to_nd_namespace_io(dev);
	if (region_intersects(nsio->res.start, resource_size(&nsio->res),
				IORESOURCE_SYSTEM_RAM,
				IORES_DESC_NONE) == REGION_MIXED)
		return false;

158 159 160 161 162 163 164 165
#ifdef ARCH_MEMREMAP_PMEM
	return ARCH_MEMREMAP_PMEM == MEMREMAP_WB;
#else
	return false;
#endif
}
EXPORT_SYMBOL(pmem_should_map_pages);

Vishal Verma's avatar
Vishal Verma committed
166 167 168 169
const char *nvdimm_namespace_disk_name(struct nd_namespace_common *ndns,
		char *name)
{
	struct nd_region *nd_region = to_nd_region(ndns->dev.parent);
170
	const char *suffix = NULL;
Vishal Verma's avatar
Vishal Verma committed
171

172 173
	if (ndns->claim && is_nd_btt(ndns->claim))
		suffix = "s";
Vishal Verma's avatar
Vishal Verma committed
174

175
	if (is_namespace_pmem(&ndns->dev) || is_namespace_io(&ndns->dev)) {
176 177 178 179 180 181 182 183 184 185 186 187 188 189 190
		int nsidx = 0;

		if (is_namespace_pmem(&ndns->dev)) {
			struct nd_namespace_pmem *nspm;

			nspm = to_nd_namespace_pmem(&ndns->dev);
			nsidx = nspm->id;
		}

		if (nsidx)
			sprintf(name, "pmem%d.%d%s", nd_region->id, nsidx,
					suffix ? suffix : "");
		else
			sprintf(name, "pmem%d%s", nd_region->id,
					suffix ? suffix : "");
191
	} else if (is_namespace_blk(&ndns->dev)) {
Vishal Verma's avatar
Vishal Verma committed
192 193 194
		struct nd_namespace_blk *nsblk;

		nsblk = to_nd_namespace_blk(&ndns->dev);
195 196
		sprintf(name, "ndblk%d.%d%s", nd_region->id, nsblk->id,
				suffix ? suffix : "");
Vishal Verma's avatar
Vishal Verma committed
197 198 199 200 201 202 203 204
	} else {
		return NULL;
	}

	return name;
}
EXPORT_SYMBOL(nvdimm_namespace_disk_name);

205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224
const u8 *nd_dev_to_uuid(struct device *dev)
{
	static const u8 null_uuid[16];

	if (!dev)
		return null_uuid;

	if (is_namespace_pmem(dev)) {
		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);

		return nspm->uuid;
	} else if (is_namespace_blk(dev)) {
		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);

		return nsblk->uuid;
	} else
		return null_uuid;
}
EXPORT_SYMBOL(nd_dev_to_uuid);

225 226 227 228 229 230 231 232 233
static ssize_t nstype_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_region *nd_region = to_nd_region(dev->parent);

	return sprintf(buf, "%d\n", nd_region_to_nstype(nd_region));
}
static DEVICE_ATTR_RO(nstype);

234 235 236 237 238 239 240 241 242 243 244
static ssize_t __alt_name_store(struct device *dev, const char *buf,
		const size_t len)
{
	char *input, *pos, *alt_name, **ns_altname;
	ssize_t rc;

	if (is_namespace_pmem(dev)) {
		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);

		ns_altname = &nspm->alt_name;
	} else if (is_namespace_blk(dev)) {
245 246 247
		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);

		ns_altname = &nsblk->alt_name;
248 249 250
	} else
		return -ENXIO;

251
	if (dev->driver || to_ndns(dev)->claim)
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
		return -EBUSY;

	input = kmemdup(buf, len + 1, GFP_KERNEL);
	if (!input)
		return -ENOMEM;

	input[len] = '\0';
	pos = strim(input);
	if (strlen(pos) + 1 > NSLABEL_NAME_LEN) {
		rc = -EINVAL;
		goto out;
	}

	alt_name = kzalloc(NSLABEL_NAME_LEN, GFP_KERNEL);
	if (!alt_name) {
		rc = -ENOMEM;
		goto out;
	}
	kfree(*ns_altname);
	*ns_altname = alt_name;
	sprintf(*ns_altname, "%s", pos);
	rc = len;

out:
	kfree(input);
	return rc;
}

280 281
static resource_size_t nd_namespace_blk_size(struct nd_namespace_blk *nsblk)
{
282
	struct nd_region *nd_region = to_nd_region(nsblk->common.dev.parent);
283 284 285 286 287 288 289 290 291 292 293 294 295 296 297
	struct nd_mapping *nd_mapping = &nd_region->mapping[0];
	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
	struct nd_label_id label_id;
	resource_size_t size = 0;
	struct resource *res;

	if (!nsblk->uuid)
		return 0;
	nd_label_gen_id(&label_id, nsblk->uuid, NSLABEL_FLAG_LOCAL);
	for_each_dpa_resource(ndd, res)
		if (strcmp(res->name, label_id.id) == 0)
			size += resource_size(res);
	return size;
}

298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315
static bool __nd_namespace_blk_validate(struct nd_namespace_blk *nsblk)
{
	struct nd_region *nd_region = to_nd_region(nsblk->common.dev.parent);
	struct nd_mapping *nd_mapping = &nd_region->mapping[0];
	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
	struct nd_label_id label_id;
	struct resource *res;
	int count, i;

	if (!nsblk->uuid || !nsblk->lbasize || !ndd)
		return false;

	count = 0;
	nd_label_gen_id(&label_id, nsblk->uuid, NSLABEL_FLAG_LOCAL);
	for_each_dpa_resource(ndd, res) {
		if (strcmp(res->name, label_id.id) != 0)
			continue;
		/*
316
		 * Resources with unacknowledged adjustments indicate a
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
		 * failure to update labels
		 */
		if (res->flags & DPA_RESOURCE_ADJUSTED)
			return false;
		count++;
	}

	/* These values match after a successful label update */
	if (count != nsblk->num_resources)
		return false;

	for (i = 0; i < nsblk->num_resources; i++) {
		struct resource *found = NULL;

		for_each_dpa_resource(ndd, res)
			if (res == nsblk->res[i]) {
				found = res;
				break;
			}
		/* stale resource */
		if (!found)
			return false;
	}

	return true;
}

resource_size_t nd_namespace_blk_validate(struct nd_namespace_blk *nsblk)
{
	resource_size_t size;

	nvdimm_bus_lock(&nsblk->common.dev);
	size = __nd_namespace_blk_validate(nsblk);
	nvdimm_bus_unlock(&nsblk->common.dev);

	return size;
}
EXPORT_SYMBOL(nd_namespace_blk_validate);


357 358 359
static int nd_namespace_label_update(struct nd_region *nd_region,
		struct device *dev)
{
360
	dev_WARN_ONCE(dev, dev->driver || to_ndns(dev)->claim,
361
			"namespace must be idle during label update\n");
362
	if (dev->driver || to_ndns(dev)->claim)
363 364 365 366 367 368 369 370
		return 0;

	/*
	 * Only allow label writes that will result in a valid namespace
	 * or deletion of an existing namespace.
	 */
	if (is_namespace_pmem(dev)) {
		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
371
		resource_size_t size = resource_size(&nspm->nsio.res);
372 373 374 375 376 377 378 379

		if (size == 0 && nspm->uuid)
			/* delete allocation */;
		else if (!nspm->uuid)
			return 0;

		return nd_pmem_namespace_label_update(nd_region, nspm, size);
	} else if (is_namespace_blk(dev)) {
380 381 382 383 384 385 386 387 388
		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
		resource_size_t size = nd_namespace_blk_size(nsblk);

		if (size == 0 && nsblk->uuid)
			/* delete allocation */;
		else if (!nsblk->uuid || !nsblk->lbasize)
			return 0;

		return nd_blk_namespace_label_update(nd_region, nsblk, size);
389 390 391 392
	} else
		return -ENXIO;
}

393 394 395
static ssize_t alt_name_store(struct device *dev,
		struct device_attribute *attr, const char *buf, size_t len)
{
396
	struct nd_region *nd_region = to_nd_region(dev->parent);
397 398 399 400 401 402
	ssize_t rc;

	device_lock(dev);
	nvdimm_bus_lock(dev);
	wait_nvdimm_bus_probe_idle(dev);
	rc = __alt_name_store(dev, buf, len);
403 404
	if (rc >= 0)
		rc = nd_namespace_label_update(nd_region, dev);
405 406 407 408
	dev_dbg(dev, "%s: %s(%zd)\n", __func__, rc < 0 ? "fail " : "", rc);
	nvdimm_bus_unlock(dev);
	device_unlock(dev);

409
	return rc < 0 ? rc : len;
410 411 412 413 414 415 416 417 418 419 420 421
}

static ssize_t alt_name_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	char *ns_altname;

	if (is_namespace_pmem(dev)) {
		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);

		ns_altname = nspm->alt_name;
	} else if (is_namespace_blk(dev)) {
422 423 424
		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);

		ns_altname = nsblk->alt_name;
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
	} else
		return -ENXIO;

	return sprintf(buf, "%s\n", ns_altname ? ns_altname : "");
}
static DEVICE_ATTR_RW(alt_name);

static int scan_free(struct nd_region *nd_region,
		struct nd_mapping *nd_mapping, struct nd_label_id *label_id,
		resource_size_t n)
{
	bool is_blk = strncmp(label_id->id, "blk", 3) == 0;
	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
	int rc = 0;

	while (n) {
		struct resource *res, *last;
		resource_size_t new_start;

		last = NULL;
		for_each_dpa_resource(ndd, res)
			if (strcmp(res->name, label_id->id) == 0)
				last = res;
		res = last;
		if (!res)
			return 0;

		if (n >= resource_size(res)) {
			n -= resource_size(res);
			nd_dbg_dpa(nd_region, ndd, res, "delete %d\n", rc);
			nvdimm_free_dpa(ndd, res);
			/* retry with last resource deleted */
			continue;
		}

		/*
		 * Keep BLK allocations relegated to high DPA as much as
		 * possible
		 */
		if (is_blk)
			new_start = res->start + n;
		else
			new_start = res->start;

		rc = adjust_resource(res, new_start, resource_size(res) - n);
470 471
		if (rc == 0)
			res->flags |= DPA_RESOURCE_ADJUSTED;
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
		nd_dbg_dpa(nd_region, ndd, res, "shrink %d\n", rc);
		break;
	}

	return rc;
}

/**
 * shrink_dpa_allocation - for each dimm in region free n bytes for label_id
 * @nd_region: the set of dimms to reclaim @n bytes from
 * @label_id: unique identifier for the namespace consuming this dpa range
 * @n: number of bytes per-dimm to release
 *
 * Assumes resources are ordered.  Starting from the end try to
 * adjust_resource() the allocation to @n, but if @n is larger than the
 * allocation delete it and find the 'new' last allocation in the label
 * set.
 */
static int shrink_dpa_allocation(struct nd_region *nd_region,
		struct nd_label_id *label_id, resource_size_t n)
{
	int i;

	for (i = 0; i < nd_region->ndr_mappings; i++) {
		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
		int rc;

		rc = scan_free(nd_region, nd_mapping, label_id, n);
		if (rc)
			return rc;
	}

	return 0;
}

static resource_size_t init_dpa_allocation(struct nd_label_id *label_id,
		struct nd_region *nd_region, struct nd_mapping *nd_mapping,
		resource_size_t n)
{
	bool is_blk = strncmp(label_id->id, "blk", 3) == 0;
	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
	resource_size_t first_dpa;
	struct resource *res;
	int rc = 0;

	/* allocate blk from highest dpa first */
	if (is_blk)
		first_dpa = nd_mapping->start + nd_mapping->size - n;
	else
		first_dpa = nd_mapping->start;

	/* first resource allocation for this label-id or dimm */
	res = nvdimm_allocate_dpa(ndd, label_id, first_dpa, n);
	if (!res)
		rc = -EBUSY;

	nd_dbg_dpa(nd_region, ndd, res, "init %d\n", rc);
	return rc ? n : 0;
}

532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552

/**
 * space_valid() - validate free dpa space against constraints
 * @nd_region: hosting region of the free space
 * @ndd: dimm device data for debug
 * @label_id: namespace id to allocate space
 * @prev: potential allocation that precedes free space
 * @next: allocation that follows the given free space range
 * @exist: first allocation with same id in the mapping
 * @n: range that must satisfied for pmem allocations
 * @valid: free space range to validate
 *
 * BLK-space is valid as long as it does not precede a PMEM
 * allocation in a given region. PMEM-space must be contiguous
 * and adjacent to an existing existing allocation (if one
 * exists).  If reserving PMEM any space is valid.
 */
static void space_valid(struct nd_region *nd_region, struct nvdimm_drvdata *ndd,
		struct nd_label_id *label_id, struct resource *prev,
		struct resource *next, struct resource *exist,
		resource_size_t n, struct resource *valid)
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
	bool is_reserve = strcmp(label_id->id, "pmem-reserve") == 0;
	bool is_pmem = strncmp(label_id->id, "pmem", 4) == 0;

	if (valid->start >= valid->end)
		goto invalid;

	if (is_reserve)
		return;

	if (!is_pmem) {
		struct nd_mapping *nd_mapping = &nd_region->mapping[0];
		struct nvdimm_bus *nvdimm_bus;
		struct blk_alloc_info info = {
			.nd_mapping = nd_mapping,
			.available = nd_mapping->size,
			.res = valid,
		};

		WARN_ON(!is_nd_blk(&nd_region->dev));
		nvdimm_bus = walk_to_nvdimm_bus(&nd_region->dev);
		device_for_each_child(&nvdimm_bus->dev, &info, alias_dpa_busy);
		return;
	}

	/* allocation needs to be contiguous, so this is all or nothing */
	if (resource_size(valid) < n)
		goto invalid;

	/* we've got all the space we need and no existing allocation */
	if (!exist)
		return;

	/* allocation needs to be contiguous with the existing namespace */
	if (valid->start == exist->end + 1
			|| valid->end == exist->start - 1)
		return;

 invalid:
	/* truncate @valid size to 0 */
	valid->end = valid->start - 1;
594 595 596 597 598 599 600 601 602 603 604 605 606
}

enum alloc_loc {
	ALLOC_ERR = 0, ALLOC_BEFORE, ALLOC_MID, ALLOC_AFTER,
};

static resource_size_t scan_allocate(struct nd_region *nd_region,
		struct nd_mapping *nd_mapping, struct nd_label_id *label_id,
		resource_size_t n)
{
	resource_size_t mapping_end = nd_mapping->start + nd_mapping->size - 1;
	bool is_pmem = strncmp(label_id->id, "pmem", 4) == 0;
	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
607
	struct resource *res, *exist = NULL, valid;
608 609 610
	const resource_size_t to_allocate = n;
	int first;

611 612 613 614 615 616 617
	for_each_dpa_resource(ndd, res)
		if (strcmp(label_id->id, res->name) == 0)
			exist = res;

	valid.start = nd_mapping->start;
	valid.end = mapping_end;
	valid.name = "free space";
618 619 620 621
 retry:
	first = 0;
	for_each_dpa_resource(ndd, res) {
		struct resource *next = res->sibling, *new_res = NULL;
622
		resource_size_t allocate, available = 0;
623 624 625 626 627 628 629 630 631 632 633 634
		enum alloc_loc loc = ALLOC_ERR;
		const char *action;
		int rc = 0;

		/* ignore resources outside this nd_mapping */
		if (res->start > mapping_end)
			continue;
		if (res->end < nd_mapping->start)
			continue;

		/* space at the beginning of the mapping */
		if (!first++ && res->start > nd_mapping->start) {
635 636 637 638 639 640
			valid.start = nd_mapping->start;
			valid.end = res->start - 1;
			space_valid(nd_region, ndd, label_id, NULL, next, exist,
					to_allocate, &valid);
			available = resource_size(&valid);
			if (available)
641 642 643 644 645
				loc = ALLOC_BEFORE;
		}

		/* space between allocations */
		if (!loc && next) {
646 647 648 649 650 651
			valid.start = res->start + resource_size(res);
			valid.end = min(mapping_end, next->start - 1);
			space_valid(nd_region, ndd, label_id, res, next, exist,
					to_allocate, &valid);
			available = resource_size(&valid);
			if (available)
652 653 654 655 656
				loc = ALLOC_MID;
		}

		/* space at the end of the mapping */
		if (!loc && !next) {
657 658 659 660 661 662
			valid.start = res->start + resource_size(res);
			valid.end = mapping_end;
			space_valid(nd_region, ndd, label_id, res, next, exist,
					to_allocate, &valid);
			available = resource_size(&valid);
			if (available)
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
				loc = ALLOC_AFTER;
		}

		if (!loc || !available)
			continue;
		allocate = min(available, n);
		switch (loc) {
		case ALLOC_BEFORE:
			if (strcmp(res->name, label_id->id) == 0) {
				/* adjust current resource up */
				rc = adjust_resource(res, res->start - allocate,
						resource_size(res) + allocate);
				action = "cur grow up";
			} else
				action = "allocate";
			break;
		case ALLOC_MID:
			if (strcmp(next->name, label_id->id) == 0) {
				/* adjust next resource up */
				rc = adjust_resource(next, next->start
						- allocate, resource_size(next)
						+ allocate);
				new_res = next;
				action = "next grow up";
			} else if (strcmp(res->name, label_id->id) == 0) {
				action = "grow down";
			} else
				action = "allocate";
			break;
		case ALLOC_AFTER:
			if (strcmp(res->name, label_id->id) == 0)
				action = "grow down";
			else
				action = "allocate";
			break;
		default:
			return n;
		}

		if (strcmp(action, "allocate") == 0) {
			/* BLK allocate bottom up */
			if (!is_pmem)
705
				valid.start += available - allocate;
706 707

			new_res = nvdimm_allocate_dpa(ndd, label_id,
708
					valid.start, allocate);
709 710 711 712 713 714
			if (!new_res)
				rc = -EBUSY;
		} else if (strcmp(action, "grow down") == 0) {
			/* adjust current resource down */
			rc = adjust_resource(res, res->start, resource_size(res)
					+ allocate);
715 716
			if (rc == 0)
				res->flags |= DPA_RESOURCE_ADJUSTED;
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
		}

		if (!new_res)
			new_res = res;

		nd_dbg_dpa(nd_region, ndd, new_res, "%s(%d) %d\n",
				action, loc, rc);

		if (rc)
			return n;

		n -= allocate;
		if (n) {
			/*
			 * Retry scan with newly inserted resources.
			 * For example, if we did an ALLOC_BEFORE
			 * insertion there may also have been space
			 * available for an ALLOC_AFTER insertion, so we
			 * need to check this same resource again
			 */
			goto retry;
		} else
			return 0;
	}

742 743 744 745 746 747
	/*
	 * If we allocated nothing in the BLK case it may be because we are in
	 * an initial "pmem-reserve pass".  Only do an initial BLK allocation
	 * when none of the DPA space is reserved.
	 */
	if ((is_pmem || !ndd->dpa.child) && n == to_allocate)
748 749 750 751
		return init_dpa_allocation(label_id, nd_region, nd_mapping, n);
	return n;
}

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
static int merge_dpa(struct nd_region *nd_region,
		struct nd_mapping *nd_mapping, struct nd_label_id *label_id)
{
	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
	struct resource *res;

	if (strncmp("pmem", label_id->id, 4) == 0)
		return 0;
 retry:
	for_each_dpa_resource(ndd, res) {
		int rc;
		struct resource *next = res->sibling;
		resource_size_t end = res->start + resource_size(res);

		if (!next || strcmp(res->name, label_id->id) != 0
				|| strcmp(next->name, label_id->id) != 0
				|| end != next->start)
			continue;
		end += resource_size(next);
		nvdimm_free_dpa(ndd, next);
		rc = adjust_resource(res, res->start, end - res->start);
		nd_dbg_dpa(nd_region, ndd, res, "merge %d\n", rc);
		if (rc)
			return rc;
		res->flags |= DPA_RESOURCE_ADJUSTED;
		goto retry;
	}

	return 0;
}

static int __reserve_free_pmem(struct device *dev, void *data)
{
	struct nvdimm *nvdimm = data;
	struct nd_region *nd_region;
	struct nd_label_id label_id;
	int i;

	if (!is_nd_pmem(dev))
		return 0;

	nd_region = to_nd_region(dev);
	if (nd_region->ndr_mappings == 0)
		return 0;

	memset(&label_id, 0, sizeof(label_id));
	strcat(label_id.id, "pmem-reserve");
	for (i = 0; i < nd_region->ndr_mappings; i++) {
		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
		resource_size_t n, rem = 0;

		if (nd_mapping->nvdimm != nvdimm)
			continue;

		n = nd_pmem_available_dpa(nd_region, nd_mapping, &rem);
		if (n == 0)
			return 0;
		rem = scan_allocate(nd_region, nd_mapping, &label_id, n);
		dev_WARN_ONCE(&nd_region->dev, rem,
				"pmem reserve underrun: %#llx of %#llx bytes\n",
				(unsigned long long) n - rem,
				(unsigned long long) n);
		return rem ? -ENXIO : 0;
	}

	return 0;
}

static void release_free_pmem(struct nvdimm_bus *nvdimm_bus,
		struct nd_mapping *nd_mapping)
{
	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
	struct resource *res, *_res;

	for_each_dpa_resource_safe(ndd, res, _res)
		if (strcmp(res->name, "pmem-reserve") == 0)
			nvdimm_free_dpa(ndd, res);
}

static int reserve_free_pmem(struct nvdimm_bus *nvdimm_bus,
		struct nd_mapping *nd_mapping)
{
	struct nvdimm *nvdimm = nd_mapping->nvdimm;
	int rc;

	rc = device_for_each_child(&nvdimm_bus->dev, nvdimm,
			__reserve_free_pmem);
	if (rc)
		release_free_pmem(nvdimm_bus, nd_mapping);
	return rc;
}

844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859
/**
 * grow_dpa_allocation - for each dimm allocate n bytes for @label_id
 * @nd_region: the set of dimms to allocate @n more bytes from
 * @label_id: unique identifier for the namespace consuming this dpa range
 * @n: number of bytes per-dimm to add to the existing allocation
 *
 * Assumes resources are ordered.  For BLK regions, first consume
 * BLK-only available DPA free space, then consume PMEM-aliased DPA
 * space starting at the highest DPA.  For PMEM regions start
 * allocations from the start of an interleave set and end at the first
 * BLK allocation or the end of the interleave set, whichever comes
 * first.
 */
static int grow_dpa_allocation(struct nd_region *nd_region,
		struct nd_label_id *label_id, resource_size_t n)
{
860 861
	struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(&nd_region->dev);
	bool is_pmem = strncmp(label_id->id, "pmem", 4) == 0;
862 863 864 865
	int i;

	for (i = 0; i < nd_region->ndr_mappings; i++) {
		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884
		resource_size_t rem = n;
		int rc, j;

		/*
		 * In the BLK case try once with all unallocated PMEM
		 * reserved, and once without
		 */
		for (j = is_pmem; j < 2; j++) {
			bool blk_only = j == 0;

			if (blk_only) {
				rc = reserve_free_pmem(nvdimm_bus, nd_mapping);
				if (rc)
					return rc;
			}
			rem = scan_allocate(nd_region, nd_mapping,
					label_id, rem);
			if (blk_only)
				release_free_pmem(nvdimm_bus, nd_mapping);
885

886 887 888 889 890 891 892 893 894 895 896 897 898
			/* try again and allow encroachments into PMEM */
			if (rem == 0)
				break;
		}

		dev_WARN_ONCE(&nd_region->dev, rem,
				"allocation underrun: %#llx of %#llx bytes\n",
				(unsigned long long) n - rem,
				(unsigned long long) n);
		if (rem)
			return -ENXIO;

		rc = merge_dpa(nd_region, nd_mapping, label_id);
899 900 901 902 903 904 905
		if (rc)
			return rc;
	}

	return 0;
}

906
static void nd_namespace_pmem_set_resource(struct nd_region *nd_region,
907 908 909
		struct nd_namespace_pmem *nspm, resource_size_t size)
{
	struct resource *res = &nspm->nsio.res;
910
	resource_size_t offset = 0;
911

912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944
	if (size && !nspm->uuid) {
		WARN_ON_ONCE(1);
		size = 0;
	}

	if (size && nspm->uuid) {
		struct nd_mapping *nd_mapping = &nd_region->mapping[0];
		struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
		struct nd_label_id label_id;
		struct resource *res;

		if (!ndd) {
			size = 0;
			goto out;
		}

		nd_label_gen_id(&label_id, nspm->uuid, 0);

		/* calculate a spa offset from the dpa allocation offset */
		for_each_dpa_resource(ndd, res)
			if (strcmp(res->name, label_id.id) == 0) {
				offset = (res->start - nd_mapping->start)
					* nd_region->ndr_mappings;
				goto out;
			}

		WARN_ON_ONCE(1);
		size = 0;
	}

 out:
	res->start = nd_region->ndr_start + offset;
	res->end = res->start + size - 1;
945 946
}

947 948 949 950 951 952 953 954 955
static bool uuid_not_set(const u8 *uuid, struct device *dev, const char *where)
{
	if (!uuid) {
		dev_dbg(dev, "%s: uuid not set\n", where);
		return true;
	}
	return false;
}

956 957 958 959
static ssize_t __size_store(struct device *dev, unsigned long long val)
{
	resource_size_t allocated = 0, available = 0;
	struct nd_region *nd_region = to_nd_region(dev->parent);
960
	struct nd_namespace_common *ndns = to_ndns(dev);
961 962 963 964
	struct nd_mapping *nd_mapping;
	struct nvdimm_drvdata *ndd;
	struct nd_label_id label_id;
	u32 flags = 0, remainder;
965
	int rc, i, id = -1;
966 967
	u8 *uuid = NULL;

968
	if (dev->driver || ndns->claim)
969 970 971 972 973 974
		return -EBUSY;

	if (is_namespace_pmem(dev)) {
		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);

		uuid = nspm->uuid;
975
		id = nspm->id;
976
	} else if (is_namespace_blk(dev)) {
977 978 979 980
		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);

		uuid = nsblk->uuid;
		flags = NSLABEL_FLAG_LOCAL;
981
		id = nsblk->id;
982 983 984 985 986 987
	}

	/*
	 * We need a uuid for the allocation-label and dimm(s) on which
	 * to store the label.
	 */
988
	if (uuid_not_set(uuid, dev, __func__))
989
		return -ENXIO;
990 991 992 993
	if (nd_region->ndr_mappings == 0) {
		dev_dbg(dev, "%s: not associated with dimm(s)\n", __func__);
		return -ENXIO;
	}
994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037

	div_u64_rem(val, SZ_4K * nd_region->ndr_mappings, &remainder);
	if (remainder) {
		dev_dbg(dev, "%llu is not %dK aligned\n", val,
				(SZ_4K * nd_region->ndr_mappings) / SZ_1K);
		return -EINVAL;
	}

	nd_label_gen_id(&label_id, uuid, flags);
	for (i = 0; i < nd_region->ndr_mappings; i++) {
		nd_mapping = &nd_region->mapping[i];
		ndd = to_ndd(nd_mapping);

		/*
		 * All dimms in an interleave set, or the base dimm for a blk
		 * region, need to be enabled for the size to be changed.
		 */
		if (!ndd)
			return -ENXIO;

		allocated += nvdimm_allocated_dpa(ndd, &label_id);
	}
	available = nd_region_available_dpa(nd_region);

	if (val > available + allocated)
		return -ENOSPC;

	if (val == allocated)
		return 0;

	val = div_u64(val, nd_region->ndr_mappings);
	allocated = div_u64(allocated, nd_region->ndr_mappings);
	if (val < allocated)
		rc = shrink_dpa_allocation(nd_region, &label_id,
				allocated - val);
	else
		rc = grow_dpa_allocation(nd_region, &label_id, val - allocated);

	if (rc)
		return rc;

	if (is_namespace_pmem(dev)) {
		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);

1038
		nd_namespace_pmem_set_resource(nd_region, nspm,
1039 1040 1041
				val * nd_region->ndr_mappings);
	}

1042 1043
	/*
	 * Try to delete the namespace if we deleted all of its
1044 1045 1046
	 * allocation, this is not the seed or 0th device for the
	 * region, and it is not actively claimed by a btt, pfn, or dax
	 * instance.
1047
	 */
1048
	if (val == 0 && id != 0 && nd_region->ns_seed != dev && !ndns->claim)
1049 1050
		nd_device_unregister(dev, ND_ASYNC);

1051 1052 1053 1054 1055 1056
	return rc;
}

static ssize_t size_store(struct device *dev,
		struct device_attribute *attr, const char *buf, size_t len)
{
1057
	struct nd_region *nd_region = to_nd_region(dev->parent);
1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069
	unsigned long long val;
	u8 **uuid = NULL;
	int rc;

	rc = kstrtoull(buf, 0, &val);
	if (rc)
		return rc;

	device_lock(dev);
	nvdimm_bus_lock(dev);
	wait_nvdimm_bus_probe_idle(dev);
	rc = __size_store(dev, val);
1070 1071
	if (rc >= 0)
		rc = nd_namespace_label_update(nd_region, dev);
1072 1073 1074 1075 1076 1077

	if (is_namespace_pmem(dev)) {
		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);

		uuid = &nspm->uuid;
	} else if (is_namespace_blk(dev)) {
1078 1079 1080
		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);

		uuid = &nsblk->uuid;
1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094
	}

	if (rc == 0 && val == 0 && uuid) {
		/* setting size zero == 'delete namespace' */
		kfree(*uuid);
		*uuid = NULL;
	}

	dev_dbg(dev, "%s: %llx %s (%d)\n", __func__, val, rc < 0
			? "fail" : "success", rc);

	nvdimm_bus_unlock(dev);
	device_unlock(dev);

1095
	return rc < 0 ? rc : len;
1096 1097
}

1098
resource_size_t __nvdimm_namespace_capacity(struct nd_namespace_common *ndns)
1099
{
1100
	struct device *dev = &ndns->dev;
1101

1102 1103 1104
	if (is_namespace_pmem(dev)) {
		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);

1105
		return resource_size(&nspm->nsio.res);
1106
	} else if (is_namespace_blk(dev)) {
1107
		return nd_namespace_blk_size(to_nd_namespace_blk(dev));
1108 1109 1110
	} else if (is_namespace_io(dev)) {
		struct nd_namespace_io *nsio = to_nd_namespace_io(dev);

1111 1112 1113 1114 1115 1116 1117 1118 1119
		return resource_size(&nsio->res);
	} else
		WARN_ONCE(1, "unknown namespace type\n");
	return 0;
}

resource_size_t nvdimm_namespace_capacity(struct nd_namespace_common *ndns)
{
	resource_size_t size;
1120

1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133
	nvdimm_bus_lock(&ndns->dev);
	size = __nvdimm_namespace_capacity(ndns);
	nvdimm_bus_unlock(&ndns->dev);

	return size;
}
EXPORT_SYMBOL(nvdimm_namespace_capacity);

static ssize_t size_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	return sprintf(buf, "%llu\n", (unsigned long long)
			nvdimm_namespace_capacity(to_ndns(dev)));
1134
}
1135
static DEVICE_ATTR(size, 0444, size_show, size_store);
1136

1137
static u8 *namespace_to_uuid(struct device *dev)
1138 1139 1140 1141
{
	if (is_namespace_pmem(dev)) {
		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);

1142
		return nspm->uuid;
1143
	} else if (is_namespace_blk(dev)) {
1144 1145
		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);

1146
		return nsblk->uuid;
1147
	} else
1148 1149 1150 1151 1152 1153 1154
		return ERR_PTR(-ENXIO);
}

static ssize_t uuid_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	u8 *uuid = namespace_to_uuid(dev);
1155

1156 1157
	if (IS_ERR(uuid))
		return PTR_ERR(uuid);
1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175
	if (uuid)
		return sprintf(buf, "%pUb\n", uuid);
	return sprintf(buf, "\n");
}

/**
 * namespace_update_uuid - check for a unique uuid and whether we're "renaming"
 * @nd_region: parent region so we can updates all dimms in the set
 * @dev: namespace type for generating label_id
 * @new_uuid: incoming uuid
 * @old_uuid: reference to the uuid storage location in the namespace object
 */
static int namespace_update_uuid(struct nd_region *nd_region,
		struct device *dev, u8 *new_uuid, u8 **old_uuid)
{
	u32 flags = is_namespace_blk(dev) ? NSLABEL_FLAG_LOCAL : 0;
	struct nd_label_id old_label_id;
	struct nd_label_id new_label_id;
1176
	int i;
1177

1178 1179
	if (!nd_is_uuid_unique(dev, new_uuid))
		return -EINVAL;
1180 1181 1182 1183

	if (*old_uuid == NULL)
		goto out;

1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199
	/*
	 * If we've already written a label with this uuid, then it's
	 * too late to rename because we can't reliably update the uuid
	 * without losing the old namespace.  Userspace must delete this
	 * namespace to abandon the old uuid.
	 */
	for (i = 0; i < nd_region->ndr_mappings; i++) {
		struct nd_mapping *nd_mapping = &nd_region->mapping[i];

		/*
		 * This check by itself is sufficient because old_uuid
		 * would be NULL above if this uuid did not exist in the
		 * currently written set.
		 *
		 * FIXME: can we delete uuid with zero dpa allocated?
		 */
1200
		if (list_empty(&nd_mapping->labels))
1201 1202 1203
			return -EBUSY;
	}

1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226
	nd_label_gen_id(&old_label_id, *old_uuid, flags);
	nd_label_gen_id(&new_label_id, new_uuid, flags);
	for (i = 0; i < nd_region->ndr_mappings; i++) {
		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
		struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
		struct resource *res;

		for_each_dpa_resource(ndd, res)
			if (strcmp(res->name, old_label_id.id) == 0)
				sprintf((void *) res->name, "%s",
						new_label_id.id);
	}
	kfree(*old_uuid);
 out:
	*old_uuid = new_uuid;
	return 0;
}

static ssize_t uuid_store(struct device *dev,
		struct device_attribute *attr, const char *buf, size_t len)
{
	struct nd_region *nd_region = to_nd_region(dev->parent);
	u8 *uuid = NULL;
1227
	ssize_t rc = 0;
1228 1229 1230 1231 1232 1233 1234
	u8 **ns_uuid;

	if (is_namespace_pmem(dev)) {
		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);

		ns_uuid = &nspm->uuid;
	} else if (is_namespace_blk(dev)) {
1235 1236 1237
		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);

		ns_uuid = &nsblk->uuid;
1238 1239 1240 1241 1242 1243
	} else
		return -ENXIO;

	device_lock(dev);
	nvdimm_bus_lock(dev);
	wait_nvdimm_bus_probe_idle(dev);
1244 1245 1246 1247
	if (to_ndns(dev)->claim)
		rc = -EBUSY;
	if (rc >= 0)
		rc = nd_uuid_store(dev, &uuid, buf, len);
1248 1249
	if (rc >= 0)
		rc = namespace_update_uuid(nd_region, dev, uuid, ns_uuid);
1250 1251 1252 1253
	if (rc >= 0)
		rc = nd_namespace_label_update(nd_region, dev);
	else
		kfree(uuid);
1254 1255 1256 1257 1258
	dev_dbg(dev, "%s: result: %zd wrote: %s%s", __func__,
			rc, buf, buf[len - 1] == '\n' ? "" : "\n");
	nvdimm_bus_unlock(dev);
	device_unlock(dev);

1259
	return rc < 0 ? rc : len;
1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285
}
static DEVICE_ATTR_RW(uuid);

static ssize_t resource_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct resource *res;

	if (is_namespace_pmem(dev)) {
		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);

		res = &nspm->nsio.res;
	} else if (is_namespace_io(dev)) {
		struct nd_namespace_io *nsio = to_nd_namespace_io(dev);

		res = &nsio->res;
	} else
		return -ENXIO;

	/* no address to convey if the namespace has no allocation */
	if (resource_size(res) == 0)
		return -ENXIO;
	return sprintf(buf, "%#llx\n", (unsigned long long) res->start);
}
static DEVICE_ATTR_RO(resource);

1286 1287
static const unsigned long ns_lbasize_supported[] = { 512, 520, 528,
	4096, 4104, 4160, 4224, 0 };
1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303

static ssize_t sector_size_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);

	if (!is_namespace_blk(dev))
		return -ENXIO;

	return nd_sector_size_show(nsblk->lbasize, ns_lbasize_supported, buf);
}

static ssize_t sector_size_store(struct device *dev,
		struct device_attribute *attr, const char *buf, size_t len)
{
	struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
1304
	struct nd_region *nd_region = to_nd_region(dev->parent);
1305
	ssize_t rc = 0;
1306 1307 1308 1309 1310 1311

	if (!is_namespace_blk(dev))
		return -ENXIO;

	device_lock(dev);
	nvdimm_bus_lock(dev);
1312 1313 1314 1315 1316
	if (to_ndns(dev)->claim)
		rc = -EBUSY;
	if (rc >= 0)
		rc = nd_sector_size_store(dev, buf, &nsblk->lbasize,
				ns_lbasize_supported);
1317 1318 1319 1320 1321
	if (rc >= 0)
		rc = nd_namespace_label_update(nd_region, dev);
	dev_dbg(dev, "%s: result: %zd %s: %s%s", __func__,
			rc, rc < 0 ? "tried" : "wrote", buf,
			buf[len - 1] == '\n' ? "" : "\n");
1322 1323 1324 1325 1326 1327 1328
	nvdimm_bus_unlock(dev);
	device_unlock(dev);

	return rc ? rc : len;
}
static DEVICE_ATTR_RW(sector_size);

1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370
static ssize_t dpa_extents_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_region *nd_region = to_nd_region(dev->parent);
	struct nd_label_id label_id;
	int count = 0, i;
	u8 *uuid = NULL;
	u32 flags = 0;

	nvdimm_bus_lock(dev);
	if (is_namespace_pmem(dev)) {
		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);

		uuid = nspm->uuid;
		flags = 0;
	} else if (is_namespace_blk(dev)) {
		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);

		uuid = nsblk->uuid;
		flags = NSLABEL_FLAG_LOCAL;
	}

	if (!uuid)
		goto out;

	nd_label_gen_id(&label_id, uuid, flags);
	for (i = 0; i < nd_region->ndr_mappings; i++) {
		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
		struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
		struct resource *res;

		for_each_dpa_resource(ndd, res)
			if (strcmp(res->name, label_id.id) == 0)
				count++;
	}
 out:
	nvdimm_bus_unlock(dev);

	return sprintf(buf, "%d\n", count);
}
static DEVICE_ATTR_RO(dpa_extents);

1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384
static ssize_t holder_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_namespace_common *ndns = to_ndns(dev);
	ssize_t rc;

	device_lock(dev);
	rc = sprintf(buf, "%s\n", ndns->claim ? dev_name(ndns->claim) : "");
	device_unlock(dev);

	return rc;
}
static DEVICE_ATTR_RO(holder);

1385 1386 1387 1388 1389 1390 1391 1392 1393 1394
static ssize_t mode_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_namespace_common *ndns = to_ndns(dev);
	struct device *claim;
	char *mode;
	ssize_t rc;

	device_lock(dev);
	claim = ndns->claim;
1395
	if (claim && is_nd_btt(claim))
1396
		mode = "safe";
1397 1398
	else if (claim && is_nd_pfn(claim))
		mode = "memory";
1399 1400
	else if (claim && is_nd_dax(claim))
		mode = "dax";
1401 1402
	else if (!claim && pmem_should_map_pages(dev))
		mode = "memory";
1403 1404 1405 1406 1407 1408 1409 1410 1411
	else
		mode = "raw";
	rc = sprintf(buf, "%s\n", mode);
	device_unlock(dev);

	return rc;
}
static DEVICE_ATTR_RO(mode);

1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431
static ssize_t force_raw_store(struct device *dev,
		struct device_attribute *attr, const char *buf, size_t len)
{
	bool force_raw;
	int rc = strtobool(buf, &force_raw);

	if (rc)
		return rc;

	to_ndns(dev)->force_raw = force_raw;
	return len;
}

static ssize_t force_raw_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	return sprintf(buf, "%d\n", to_ndns(dev)->force_raw);
}
static DEVICE_ATTR_RW(force_raw);

1432 1433
static struct attribute *nd_namespace_attributes[] = {
	&dev_attr_nstype.attr,
1434
	&dev_attr_size.attr,
1435
	&dev_attr_mode.attr,
1436
	&dev_attr_uuid.attr,
1437
	&dev_attr_holder.attr,
1438 1439
	&dev_attr_resource.attr,
	&dev_attr_alt_name.attr,
1440
	&dev_attr_force_raw.attr,
1441
	&dev_attr_sector_size.attr,
1442
	&dev_attr_dpa_extents.attr,
1443 1444 1445
	NULL,
};

1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458
static umode_t namespace_visible(struct kobject *kobj,
		struct attribute *a, int n)
{
	struct device *dev = container_of(kobj, struct device, kobj);

	if (a == &dev_attr_resource.attr) {
		if (is_namespace_blk(dev))
			return 0;
		return a->mode;
	}

	if (is_namespace_pmem(dev) || is_namespace_blk(dev)) {
		if (a == &dev_attr_size.attr)
1459
			return 0644;
1460 1461 1462 1463

		if (is_namespace_pmem(dev) && a == &dev_attr_sector_size.attr)
			return 0;

1464 1465 1466
		return a->mode;
	}

1467 1468
	if (a == &dev_attr_nstype.attr || a == &dev_attr_size.attr
			|| a == &dev_attr_holder.attr
1469 1470
			|| a == &dev_attr_force_raw.attr
			|| a == &dev_attr_mode.attr)
1471 1472 1473 1474 1475
		return a->mode;

	return 0;
}

1476 1477
static struct attribute_group nd_namespace_attribute_group = {
	.attrs = nd_namespace_attributes,
1478
	.is_visible = namespace_visible,
1479 1480 1481 1482 1483
};

static const struct attribute_group *nd_namespace_attribute_groups[] = {
	&nd_device_attribute_group,
	&nd_namespace_attribute_group,
1484
	&nd_numa_attribute_group,
1485 1486 1487
	NULL,
};

1488 1489 1490
struct nd_namespace_common *nvdimm_namespace_common_probe(struct device *dev)
{
	struct nd_btt *nd_btt = is_nd_btt(dev) ? to_nd_btt(dev) : NULL;
1491
	struct nd_pfn *nd_pfn = is_nd_pfn(dev) ? to_nd_pfn(dev) : NULL;
1492
	struct nd_dax *nd_dax = is_nd_dax(dev) ? to_nd_dax(dev) : NULL;
1493
	struct nd_namespace_common *ndns = NULL;
1494 1495
	resource_size_t size;

1496
	if (nd_btt || nd_pfn || nd_dax) {
1497
		if (nd_btt)
1498
			ndns = nd_btt->ndns;
1499
		else if (nd_pfn)
1500
			ndns = nd_pfn->ndns;
1501 1502
		else if (nd_dax)
			ndns = nd_dax->nd_pfn.ndns;
1503

1504
		if (!ndns)
1505 1506 1507 1508 1509 1510 1511 1512 1513 1514
			return ERR_PTR(-ENODEV);

		/*
		 * Flush any in-progess probes / removals in the driver
		 * for the raw personality of this namespace.
		 */
		device_lock(&ndns->dev);
		device_unlock(&ndns->dev);
		if (ndns->dev.driver) {
			dev_dbg(&ndns->dev, "is active, can't bind %s\n",
1515
					dev_name(dev));
1516 1517
			return ERR_PTR(-EBUSY);
		}
1518
		if (dev_WARN_ONCE(&ndns->dev, ndns->claim != dev,
1519
					"host (%s) vs claim (%s) mismatch\n",
1520
					dev_name(dev),
1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543
					dev_name(ndns->claim)))
			return ERR_PTR(-ENXIO);
	} else {
		ndns = to_ndns(dev);
		if (ndns->claim) {
			dev_dbg(dev, "claimed by %s, failing probe\n",
				dev_name(ndns->claim));

			return ERR_PTR(-ENXIO);
		}
	}

	size = nvdimm_namespace_capacity(ndns);
	if (size < ND_MIN_NAMESPACE_SIZE) {
		dev_dbg(&ndns->dev, "%pa, too small must be at least %#x\n",
				&size, ND_MIN_NAMESPACE_SIZE);
		return ERR_PTR(-ENODEV);
	}

	if (is_namespace_pmem(&ndns->dev)) {
		struct nd_namespace_pmem *nspm;

		nspm = to_nd_namespace_pmem(&ndns->dev);
1544
		if (uuid_not_set(nspm->uuid, &ndns->dev, __func__))
1545 1546
			return ERR_PTR(-ENODEV);
	} else if (is_namespace_blk(&ndns->dev)) {
1547 1548 1549
		struct nd_namespace_blk *nsblk;

		nsblk = to_nd_namespace_blk(&ndns->dev);
1550 1551 1552 1553 1554 1555 1556
		if (uuid_not_set(nsblk->uuid, &ndns->dev, __func__))
			return ERR_PTR(-ENODEV);
		if (!nsblk->lbasize) {
			dev_dbg(&ndns->dev, "%s: sector size not set\n",
				__func__);
			return ERR_PTR(-ENODEV);
		}
1557 1558
		if (!nd_namespace_blk_validate(nsblk))
			return ERR_PTR(-ENODEV);
1559 1560 1561 1562 1563 1564
	}

	return ndns;
}
EXPORT_SYMBOL(nvdimm_namespace_common_probe);

1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580
static struct device **create_namespace_io(struct nd_region *nd_region)
{
	struct nd_namespace_io *nsio;
	struct device *dev, **devs;
	struct resource *res;

	nsio = kzalloc(sizeof(*nsio), GFP_KERNEL);
	if (!nsio)
		return NULL;

	devs = kcalloc(2, sizeof(struct device *), GFP_KERNEL);
	if (!devs) {
		kfree(nsio);
		return NULL;
	}

1581
	dev = &nsio->common.dev;
1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593
	dev->type = &namespace_io_device_type;
	dev->parent = &nd_region->dev;
	res = &nsio->res;
	res->name = dev_name(&nd_region->dev);
	res->flags = IORESOURCE_MEM;
	res->start = nd_region->ndr_start;
	res->end = res->start + nd_region->ndr_size - 1;

	devs[0] = dev;
	return devs;
}

1594 1595 1596 1597 1598 1599 1600 1601
static bool has_uuid_at_pos(struct nd_region *nd_region, u8 *uuid,
		u64 cookie, u16 pos)
{
	struct nd_namespace_label *found = NULL;
	int i;

	for (i = 0; i < nd_region->ndr_mappings; i++) {
		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
1602
		struct nd_label_ent *label_ent;
1603 1604
		bool found_uuid = false;

1605 1606 1607 1608 1609 1610 1611 1612 1613 1614
		list_for_each_entry(label_ent, &nd_mapping->labels, list) {
			struct nd_namespace_label *nd_label = label_ent->label;
			u16 position, nlabel;
			u64 isetcookie;

			if (!nd_label)
				continue;
			isetcookie = __le64_to_cpu(nd_label->isetcookie);
			position = __le16_to_cpu(nd_label->position);
			nlabel = __le16_to_cpu(nd_label->nlabel);
1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650

			if (isetcookie != cookie)
				continue;

			if (memcmp(nd_label->uuid, uuid, NSLABEL_UUID_LEN) != 0)
				continue;

			if (found_uuid) {
				dev_dbg(to_ndd(nd_mapping)->dev,
						"%s duplicate entry for uuid\n",
						__func__);
				return false;
			}
			found_uuid = true;
			if (nlabel != nd_region->ndr_mappings)
				continue;
			if (position != pos)
				continue;
			found = nd_label;
			break;
		}
		if (found)
			break;
	}
	return found != NULL;
}

static int select_pmem_id(struct nd_region *nd_region, u8 *pmem_id)
{
	int i;

	if (!pmem_id)
		return -ENODEV;

	for (i = 0; i < nd_region->ndr_mappings; i++) {
		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
1651
		struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
1652
		struct nd_namespace_label *nd_label = NULL;
1653
		u64 hw_start, hw_end, pmem_start, pmem_end;
1654
		struct nd_label_ent *label_ent;
1655

1656
		lockdep_assert_held(&nd_mapping->lock);
1657 1658 1659 1660
		list_for_each_entry(label_ent, &nd_mapping->labels, list) {
			nd_label = label_ent->label;
			if (!nd_label)
				continue;
1661 1662
			if (memcmp(nd_label->uuid, pmem_id, NSLABEL_UUID_LEN) == 0)
				break;
1663 1664
			nd_label = NULL;
		}
1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676

		if (!nd_label) {
			WARN_ON(1);
			return -EINVAL;
		}

		/*
		 * Check that this label is compliant with the dpa
		 * range published in NFIT
		 */
		hw_start = nd_mapping->start;
		hw_end = hw_start + nd_mapping->size;
1677 1678
		pmem_start = __le64_to_cpu(nd_label->dpa);
		pmem_end = pmem_start + __le64_to_cpu(nd_label->rawsize);
1679 1680
		if (pmem_start >= hw_start && pmem_start < hw_end
				&& pmem_end <= hw_end && pmem_end > hw_start)
1681
			/* pass */;
1682 1683 1684
		else {
			dev_dbg(&nd_region->dev, "%s invalid label for %pUb\n",
					dev_name(ndd->dev), nd_label->uuid);
1685
			return -EINVAL;