namespace_devs.c 55.7 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 56 57 58 59
static struct device_type namespace_io_device_type = {
	.name = "nd_namespace_io",
	.release = namespace_io_release,
};

60 61 62 63 64 65 66 67 68 69
static struct device_type namespace_pmem_device_type = {
	.name = "nd_namespace_pmem",
	.release = namespace_pmem_release,
};

static struct device_type namespace_blk_device_type = {
	.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);

V
Vishal Verma 已提交
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;
V
Vishal Verma 已提交
171

172 173
	if (ndns->claim && is_nd_btt(ndns->claim))
		suffix = "s";
V
Vishal Verma 已提交
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)) {
V
Vishal Verma 已提交
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 : "");
V
Vishal Verma 已提交
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);


D
Dan Williams 已提交
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,
D
Dan Williams 已提交
361
			"namespace must be idle during label update\n");
362
	if (dev->driver || to_ndns(dev)->claim)
D
Dan Williams 已提交
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);
D
Dan Williams 已提交
371
		resource_size_t size = resource_size(&nspm->nsio.res);
D
Dan Williams 已提交
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)) {
D
Dan Williams 已提交
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);
D
Dan Williams 已提交
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)
{
D
Dan Williams 已提交
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);
D
Dan Williams 已提交
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);

D
Dan Williams 已提交
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
static bool space_valid(bool is_pmem, bool is_reserve,
		struct nd_label_id *label_id, struct resource *res)
534 535 536
{
	/*
	 * For BLK-space any space is valid, for PMEM-space, it must be
537 538
	 * contiguous with an existing allocation unless we are
	 * reserving pmem.
539
	 */
540
	if (is_reserve || !is_pmem)
541 542 543 544 545 546 547 548 549 550 551 552 553 554 555
		return true;
	if (!res || strcmp(res->name, label_id->id) == 0)
		return true;
	return false;
}

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;
556
	bool is_reserve = strcmp(label_id->id, "pmem-reserve") == 0;
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
	bool is_pmem = strncmp(label_id->id, "pmem", 4) == 0;
	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
	const resource_size_t to_allocate = n;
	struct resource *res;
	int first;

 retry:
	first = 0;
	for_each_dpa_resource(ndd, res) {
		resource_size_t allocate, available = 0, free_start, free_end;
		struct resource *next = res->sibling, *new_res = NULL;
		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) {
			free_start = nd_mapping->start;
			available = res->start - free_start;
582
			if (space_valid(is_pmem, is_reserve, label_id, NULL))
583 584 585 586 587 588 589
				loc = ALLOC_BEFORE;
		}

		/* space between allocations */
		if (!loc && next) {
			free_start = res->start + resource_size(res);
			free_end = min(mapping_end, next->start - 1);
590
			if (space_valid(is_pmem, is_reserve, label_id, res)
591 592 593 594 595 596 597 598 599 600
					&& free_start < free_end) {
				available = free_end + 1 - free_start;
				loc = ALLOC_MID;
			}
		}

		/* space at the end of the mapping */
		if (!loc && !next) {
			free_start = res->start + resource_size(res);
			free_end = mapping_end;
601
			if (space_valid(is_pmem, is_reserve, label_id, res)
602 603 604 605 606 607 608 609 610 611 612 613 614
					&& free_start < free_end) {
				available = free_end + 1 - free_start;
				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 */
615
				if (is_pmem && !is_reserve)
616 617 618 619 620 621 622 623 624 625
					return n;
				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 */
626
				if (is_pmem && !is_reserve)
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
					return n;
				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)
				free_start += available - allocate;
652
			else if (!is_reserve && free_start != nd_mapping->start)
653 654 655 656 657 658 659 660 661 662
				return n;

			new_res = nvdimm_allocate_dpa(ndd, label_id,
					free_start, allocate);
			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);
663 664
			if (rc == 0)
				res->flags |= DPA_RESOURCE_ADJUSTED;
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
		}

		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;
	}

690 691 692 693 694 695
	/*
	 * 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)
696 697 698 699
		return init_dpa_allocation(label_id, nd_region, nd_mapping, n);
	return n;
}

700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791
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;
}

792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807
/**
 * 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)
{
808 809
	struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(&nd_region->dev);
	bool is_pmem = strncmp(label_id->id, "pmem", 4) == 0;
810 811 812 813
	int i;

	for (i = 0; i < nd_region->ndr_mappings; i++) {
		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832
		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);
833

834 835 836 837 838 839 840 841 842 843 844 845 846
			/* 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);
847 848 849 850 851 852 853
		if (rc)
			return rc;
	}

	return 0;
}

854
static void nd_namespace_pmem_set_resource(struct nd_region *nd_region,
855 856 857
		struct nd_namespace_pmem *nspm, resource_size_t size)
{
	struct resource *res = &nspm->nsio.res;
858
	resource_size_t offset = 0;
859

860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892
	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;
893 894
}

895 896 897 898 899 900 901 902 903
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;
}

904 905 906 907 908 909 910 911 912 913 914
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);
	struct nd_mapping *nd_mapping;
	struct nvdimm_drvdata *ndd;
	struct nd_label_id label_id;
	u32 flags = 0, remainder;
	u8 *uuid = NULL;
	int rc, i;

915
	if (dev->driver || to_ndns(dev)->claim)
916 917 918 919 920 921 922
		return -EBUSY;

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

		uuid = nspm->uuid;
	} else if (is_namespace_blk(dev)) {
923 924 925 926
		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);

		uuid = nsblk->uuid;
		flags = NSLABEL_FLAG_LOCAL;
927 928 929 930 931 932
	}

	/*
	 * We need a uuid for the allocation-label and dimm(s) on which
	 * to store the label.
	 */
933
	if (uuid_not_set(uuid, dev, __func__))
934
		return -ENXIO;
935 936 937 938
	if (nd_region->ndr_mappings == 0) {
		dev_dbg(dev, "%s: not associated with dimm(s)\n", __func__);
		return -ENXIO;
	}
939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982

	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);

983
		nd_namespace_pmem_set_resource(nd_region, nspm,
984
				val * nd_region->ndr_mappings);
985
	} else if (is_namespace_blk(dev)) {
986 987
		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);

988 989
		/*
		 * Try to delete the namespace if we deleted all of its
990 991 992
		 * allocation, this is not the seed device for the
		 * region, and it is not actively claimed by a btt
		 * instance.
993
		 */
994 995
		if (val == 0 && nd_region->ns_seed != dev
				&& !nsblk->common.claim)
996
			nd_device_unregister(dev, ND_ASYNC);
997 998 999 1000 1001 1002 1003 1004
	}

	return rc;
}

static ssize_t size_store(struct device *dev,
		struct device_attribute *attr, const char *buf, size_t len)
{
D
Dan Williams 已提交
1005
	struct nd_region *nd_region = to_nd_region(dev->parent);
1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017
	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);
D
Dan Williams 已提交
1018 1019
	if (rc >= 0)
		rc = nd_namespace_label_update(nd_region, dev);
1020 1021 1022 1023 1024 1025

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

		uuid = &nspm->uuid;
	} else if (is_namespace_blk(dev)) {
1026 1027 1028
		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);

		uuid = &nsblk->uuid;
1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042
	}

	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);

D
Dan Williams 已提交
1043
	return rc < 0 ? rc : len;
1044 1045
}

1046
resource_size_t __nvdimm_namespace_capacity(struct nd_namespace_common *ndns)
1047
{
1048
	struct device *dev = &ndns->dev;
1049

1050 1051 1052
	if (is_namespace_pmem(dev)) {
		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);

1053
		return resource_size(&nspm->nsio.res);
1054
	} else if (is_namespace_blk(dev)) {
1055
		return nd_namespace_blk_size(to_nd_namespace_blk(dev));
1056 1057 1058
	} else if (is_namespace_io(dev)) {
		struct nd_namespace_io *nsio = to_nd_namespace_io(dev);

1059 1060 1061 1062 1063 1064 1065 1066 1067
		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;
1068

1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081
	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)));
1082 1083 1084
}
static DEVICE_ATTR(size, S_IRUGO, size_show, size_store);

1085
static u8 *namespace_to_uuid(struct device *dev)
1086 1087 1088 1089
{
	if (is_namespace_pmem(dev)) {
		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);

1090
		return nspm->uuid;
1091
	} else if (is_namespace_blk(dev)) {
1092 1093
		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);

1094
		return nsblk->uuid;
1095
	} else
1096 1097 1098 1099 1100 1101 1102
		return ERR_PTR(-ENXIO);
}

static ssize_t uuid_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	u8 *uuid = namespace_to_uuid(dev);
1103

1104 1105
	if (IS_ERR(uuid))
		return PTR_ERR(uuid);
1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123
	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;
D
Dan Williams 已提交
1124
	int i;
1125

D
Dan Williams 已提交
1126 1127
	if (!nd_is_uuid_unique(dev, new_uuid))
		return -EINVAL;
1128 1129 1130 1131

	if (*old_uuid == NULL)
		goto out;

D
Dan Williams 已提交
1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147
	/*
	 * 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?
		 */
1148
		if (list_empty(&nd_mapping->labels))
D
Dan Williams 已提交
1149 1150 1151
			return -EBUSY;
	}

1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174
	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;
1175
	ssize_t rc = 0;
1176 1177 1178 1179 1180 1181 1182
	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)) {
1183 1184 1185
		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);

		ns_uuid = &nsblk->uuid;
1186 1187 1188 1189 1190 1191
	} else
		return -ENXIO;

	device_lock(dev);
	nvdimm_bus_lock(dev);
	wait_nvdimm_bus_probe_idle(dev);
1192 1193 1194 1195
	if (to_ndns(dev)->claim)
		rc = -EBUSY;
	if (rc >= 0)
		rc = nd_uuid_store(dev, &uuid, buf, len);
1196 1197
	if (rc >= 0)
		rc = namespace_update_uuid(nd_region, dev, uuid, ns_uuid);
D
Dan Williams 已提交
1198 1199 1200 1201
	if (rc >= 0)
		rc = nd_namespace_label_update(nd_region, dev);
	else
		kfree(uuid);
1202 1203 1204 1205 1206
	dev_dbg(dev, "%s: result: %zd wrote: %s%s", __func__,
			rc, buf, buf[len - 1] == '\n' ? "" : "\n");
	nvdimm_bus_unlock(dev);
	device_unlock(dev);

D
Dan Williams 已提交
1207
	return rc < 0 ? rc : len;
1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233
}
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);

1234 1235
static const unsigned long ns_lbasize_supported[] = { 512, 520, 528,
	4096, 4104, 4160, 4224, 0 };
1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251

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);
D
Dan Williams 已提交
1252
	struct nd_region *nd_region = to_nd_region(dev->parent);
1253
	ssize_t rc = 0;
1254 1255 1256 1257 1258 1259

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

	device_lock(dev);
	nvdimm_bus_lock(dev);
1260 1261 1262 1263 1264
	if (to_ndns(dev)->claim)
		rc = -EBUSY;
	if (rc >= 0)
		rc = nd_sector_size_store(dev, buf, &nsblk->lbasize,
				ns_lbasize_supported);
D
Dan Williams 已提交
1265 1266 1267 1268 1269
	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");
1270 1271 1272 1273 1274 1275 1276
	nvdimm_bus_unlock(dev);
	device_unlock(dev);

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

D
Dan Williams 已提交
1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318
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);

1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332
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);

1333 1334 1335 1336 1337 1338 1339 1340 1341 1342
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;
1343
	if (claim && is_nd_btt(claim))
1344
		mode = "safe";
1345 1346
	else if (claim && is_nd_pfn(claim))
		mode = "memory";
1347 1348
	else if (claim && is_nd_dax(claim))
		mode = "dax";
1349 1350
	else if (!claim && pmem_should_map_pages(dev))
		mode = "memory";
1351 1352 1353 1354 1355 1356 1357 1358 1359
	else
		mode = "raw";
	rc = sprintf(buf, "%s\n", mode);
	device_unlock(dev);

	return rc;
}
static DEVICE_ATTR_RO(mode);

1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379
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);

1380 1381
static struct attribute *nd_namespace_attributes[] = {
	&dev_attr_nstype.attr,
1382
	&dev_attr_size.attr,
1383
	&dev_attr_mode.attr,
1384
	&dev_attr_uuid.attr,
1385
	&dev_attr_holder.attr,
1386 1387
	&dev_attr_resource.attr,
	&dev_attr_alt_name.attr,
1388
	&dev_attr_force_raw.attr,
1389
	&dev_attr_sector_size.attr,
D
Dan Williams 已提交
1390
	&dev_attr_dpa_extents.attr,
1391 1392 1393
	NULL,
};

1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407
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)
			return S_IWUSR | S_IRUGO;
1408 1409 1410 1411

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

1412 1413 1414
		return a->mode;
	}

1415 1416
	if (a == &dev_attr_nstype.attr || a == &dev_attr_size.attr
			|| a == &dev_attr_holder.attr
1417 1418
			|| a == &dev_attr_force_raw.attr
			|| a == &dev_attr_mode.attr)
1419 1420 1421 1422 1423
		return a->mode;

	return 0;
}

1424 1425
static struct attribute_group nd_namespace_attribute_group = {
	.attrs = nd_namespace_attributes,
1426
	.is_visible = namespace_visible,
1427 1428 1429 1430 1431
};

static const struct attribute_group *nd_namespace_attribute_groups[] = {
	&nd_device_attribute_group,
	&nd_namespace_attribute_group,
1432
	&nd_numa_attribute_group,
1433 1434 1435
	NULL,
};

1436 1437 1438
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;
1439
	struct nd_pfn *nd_pfn = is_nd_pfn(dev) ? to_nd_pfn(dev) : NULL;
1440
	struct nd_dax *nd_dax = is_nd_dax(dev) ? to_nd_dax(dev) : NULL;
1441
	struct nd_namespace_common *ndns = NULL;
1442 1443
	resource_size_t size;

1444
	if (nd_btt || nd_pfn || nd_dax) {
1445
		if (nd_btt)
1446
			ndns = nd_btt->ndns;
1447
		else if (nd_pfn)
1448
			ndns = nd_pfn->ndns;
1449 1450
		else if (nd_dax)
			ndns = nd_dax->nd_pfn.ndns;
1451

1452
		if (!ndns)
1453 1454 1455 1456 1457 1458 1459 1460 1461 1462
			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",
1463
					dev_name(dev));
1464 1465
			return ERR_PTR(-EBUSY);
		}
1466
		if (dev_WARN_ONCE(&ndns->dev, ndns->claim != dev,
1467
					"host (%s) vs claim (%s) mismatch\n",
1468
					dev_name(dev),
1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491
					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);
1492
		if (uuid_not_set(nspm->uuid, &ndns->dev, __func__))
1493 1494
			return ERR_PTR(-ENODEV);
	} else if (is_namespace_blk(&ndns->dev)) {
1495 1496 1497
		struct nd_namespace_blk *nsblk;

		nsblk = to_nd_namespace_blk(&ndns->dev);
1498 1499 1500 1501 1502 1503 1504
		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);
		}
1505 1506
		if (!nd_namespace_blk_validate(nsblk))
			return ERR_PTR(-ENODEV);
1507 1508 1509 1510 1511 1512
	}

	return ndns;
}
EXPORT_SYMBOL(nvdimm_namespace_common_probe);

1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528
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;
	}

1529
	dev = &nsio->common.dev;
1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541
	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;
}

1542 1543 1544 1545 1546 1547 1548 1549
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];
1550
		struct nd_label_ent *label_ent;
1551 1552
		bool found_uuid = false;

1553 1554 1555 1556 1557 1558 1559 1560 1561 1562
		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);
1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598

			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];
1599
		struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
1600
		struct nd_namespace_label *nd_label = NULL;
1601
		u64 hw_start, hw_end, pmem_start, pmem_end;
1602
		struct nd_label_ent *label_ent;
1603

1604
		WARN_ON(!mutex_is_locked(&nd_mapping->lock));
1605 1606 1607 1608
		list_for_each_entry(label_ent, &nd_mapping->labels, list) {
			nd_label = label_ent->label;
			if (!nd_label)
				continue;
1609 1610
			if (memcmp(nd_label->uuid, pmem_id, NSLABEL_UUID_LEN) == 0)
				break;
1611 1612
			nd_label = NULL;
		}
1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624

		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;
1625 1626
		pmem_start = __le64_to_cpu(nd_label->dpa);
		pmem_end = pmem_start + __le64_to_cpu(nd_label->rawsize);
1627 1628
		if (pmem_start >= hw_start && pmem_start < hw_end
				&& pmem_end <= hw_end && pmem_end > hw_start)
1629
			/* pass */;
1630 1631 1632
		else {
			dev_dbg(&nd_region->dev, "%s invalid label for %pUb\n",
					dev_name(ndd->dev), nd_label->uuid);
1633
			return -EINVAL;
1634
		}
1635

1636 1637
		/* move recently validated label to the front of the list */
		list_move(&label_ent->list, &nd_mapping->labels);
1638 1639 1640 1641 1642
	}
	return 0;
}

/**
1643
 * create_namespace_pmem - validate interleave set labelling, retrieve label0
1644
 * @nd_region: region with mappings to validate
1645 1646
 * @nspm: target namespace to create
 * @nd_label: target pmem namespace label to evaluate
1647
 */
1648 1649
struct device *create_namespace_pmem(struct nd_region *nd_region,
		struct nd_namespace_label *nd_label)
1650 1651
{
	u64 cookie = nd_region_interleave_set_cookie(nd_region);
1652
	struct nd_label_ent *label_ent;
1653
	struct nd_namespace_pmem *nspm;
1654
	struct nd_mapping *nd_mapping;
1655
	resource_size_t size = 0;
1656 1657
	struct resource *res;
	struct device *dev;
1658
	int rc = 0;
1659 1660
	u16 i;

1661 1662
	if (cookie == 0) {
		dev_dbg(&nd_region->dev, "invalid interleave-set-cookie\n");
1663
		return ERR_PTR(-ENXIO);
1664
	}
1665

1666 1667 1668 1669
	if (__le64_to_cpu(nd_label->isetcookie) != cookie) {
		dev_dbg(&nd_region->dev, "invalid cookie in label: %pUb\n",
				nd_label->uuid);
		return ERR_PTR(-EAGAIN);
1670
	}
1671

1672 1673 1674
	nspm = kzalloc(sizeof(*nspm), GFP_KERNEL);
	if (!nspm)
		return ERR_PTR(-ENOMEM);
1675

1676
	nspm->id = -1;
1677 1678 1679 1680 1681 1682
	dev = &nspm->nsio.common.dev;
	dev->type = &namespace_pmem_device_type;
	dev->parent = &nd_region->dev;
	res = &nspm->nsio.res;
	res->name = dev_name(&nd_region->dev);
	res->flags = IORESOURCE_MEM;
1683

1684 1685 1686 1687
	for (i = 0; i < nd_region->ndr_mappings; i++)
		if (!has_uuid_at_pos(nd_region, nd_label->uuid, cookie, i))
			break;
	if (i < nd_region->ndr_mappings) {
1688 1689
		struct nvdimm_drvdata *ndd = to_ndd(&nd_region->mapping[i]);

1690 1691 1692 1693 1694
		/*
		 * Give up if we don't find an instance of a uuid at each
		 * position (from 0 to nd_region->ndr_mappings - 1), or if we
		 * find a dimm with two instances of the same uuid.
		 */
1695 1696
		dev_err(&nd_region->dev, "%s missing label for %pUb\n",
				dev_name(ndd->dev), nd_label->uuid);
1697
		rc = -EINVAL;
1698
		goto err;
1699
	}
1700 1701 1702 1703 1704 1705 1706 1707 1708

	/*
	 * Fix up each mapping's 'labels' to have the validated pmem label for
	 * that position at labels[0], and NULL at labels[1].  In the process,
	 * check that the namespace aligns with interleave-set.  We know
	 * that it does not overlap with any blk namespaces by virtue of
	 * the dimm being enabled (i.e. nd_label_reserve_dpa()
	 * succeeded).
	 */
1709
	rc = select_pmem_id(nd_region, nd_label->uuid);
1710 1711 1712 1713 1714
	if (rc)
		goto err;

	/* Calculate total size and populate namespace properties from label0 */
	for (i = 0; i < nd_region->ndr_mappings; i++) {
1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725
		struct nd_namespace_label *label0;

		nd_mapping = &nd_region->mapping[i];
		label_ent = list_first_entry_or_null(&nd_mapping->labels,
				typeof(*label_ent), list);
		label0 = label_ent ? label_ent->label : 0;

		if (!label0) {
			WARN_ON(1);
			continue;
		}
1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741

		size += __le64_to_cpu(label0->rawsize);
		if (__le16_to_cpu(label0->position) != 0)
			continue;
		WARN_ON(nspm->alt_name || nspm->uuid);
		nspm->alt_name = kmemdup((void __force *) label0->name,
				NSLABEL_NAME_LEN, GFP_KERNEL);
		nspm->uuid = kmemdup((void __force *) label0->uuid,
				NSLABEL_UUID_LEN, GFP_KERNEL);
	}

	if (!nspm->alt_name || !nspm->uuid) {
		rc = -ENOMEM;
		goto err;
	}

1742
	nd_namespace_pmem_set_resource(nd_region, nspm, size);
1743

1744
	return dev;
1745
 err:
1746
	namespace_pmem_release(dev);
1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758
	switch (rc) {
	case -EINVAL:
		dev_dbg(&nd_region->dev, "%s: invalid label(s)\n", __func__);
		break;
	case -ENODEV:
		dev_dbg(&nd_region->dev, "%s: label not found\n", __func__);
		break;
	default:
		dev_dbg(&nd_region->dev, "%s: unexpected err: %d\n",
				__func__, rc);
		break;
	}
1759
	return ERR_PTR(rc);
1760 1761
}

1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796
struct resource *nsblk_add_resource(struct nd_region *nd_region,
		struct nvdimm_drvdata *ndd, struct nd_namespace_blk *nsblk,
		resource_size_t start)
{
	struct nd_label_id label_id;
	struct resource *res;

	nd_label_gen_id(&label_id, nsblk->uuid, NSLABEL_FLAG_LOCAL);
	res = krealloc(nsblk->res,
			sizeof(void *) * (nsblk->num_resources + 1),
			GFP_KERNEL);
	if (!res)
		return NULL;
	nsblk->res = (struct resource **) res;
	for_each_dpa_resource(ndd, res)
		if (strcmp(res->name, label_id.id) == 0
				&& res->start == start) {
			nsblk->res[nsblk->num_resources++] = res;
			return res;
		}
	return NULL;
}

static struct device *nd_namespace_blk_create(struct nd_region *nd_region)
{
	struct nd_namespace_blk *nsblk;
	struct device *dev;

	if (!is_nd_blk(&nd_region->dev))
		return NULL;

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

1797
	dev = &nsblk->common.dev;
1798 1799 1800 1801 1802 1803 1804 1805 1806 1807
	dev->type = &namespace_blk_device_type;
	nsblk->id = ida_simple_get(&nd_region->ns_ida, 0, 0, GFP_KERNEL);
	if (nsblk->id < 0) {
		kfree(nsblk);
		return NULL;
	}
	dev_set_name(dev, "namespace%d.%d", nd_region->id, nsblk->id);
	dev->parent = &nd_region->dev;
	dev->groups = nd_namespace_attribute_groups;

1808
	return &nsblk->common.dev;
1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824
}

void nd_region_create_blk_seed(struct nd_region *nd_region)
{
	WARN_ON(!is_nvdimm_bus_locked(&nd_region->dev));
	nd_region->ns_seed = nd_namespace_blk_create(nd_region);
	/*
	 * Seed creation failures are not fatal, provisioning is simply
	 * disabled until memory becomes available
	 */
	if (!nd_region->ns_seed)
		dev_err(&nd_region->dev, "failed to create blk namespace\n");
	else
		nd_device_register(nd_region->ns_seed);
}

1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836
void nd_region_create_dax_seed(struct nd_region *nd_region)
{
	WARN_ON(!is_nvdimm_bus_locked(&nd_region->dev));
	nd_region->dax_seed = nd_dax_create(nd_region);
	/*
	 * Seed creation failures are not fatal, provisioning is simply
	 * disabled until memory becomes available
	 */
	if (!nd_region->dax_seed)
		dev_err(&nd_region->dev, "failed to create dax namespace\n");
}

1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848
void nd_region_create_pfn_seed(struct nd_region *nd_region)
{
	WARN_ON(!is_nvdimm_bus_locked(&nd_region->dev));
	nd_region->pfn_seed = nd_pfn_create(nd_region);
	/*
	 * Seed creation failures are not fatal, provisioning is simply
	 * disabled until memory becomes available
	 */
	if (!nd_region->pfn_seed)
		dev_err(&nd_region->dev, "failed to create pfn namespace\n");
}

1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860
void nd_region_create_btt_seed(struct nd_region *nd_region)
{
	WARN_ON(!is_nvdimm_bus_locked(&nd_region->dev));
	nd_region->btt_seed = nd_btt_create(nd_region);
	/*
	 * Seed creation failures are not fatal, provisioning is simply
	 * disabled until memory becomes available
	 */
	if (!nd_region->btt_seed)
		dev_err(&nd_region->dev, "failed to create btt namespace\n");
}

1861 1862 1863
static int add_namespace_resource(struct nd_region *nd_region,
		struct nd_namespace_label *nd_label, struct device **devs,
		int count)
1864
{
1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903
	struct nd_mapping *nd_mapping = &nd_region->mapping[0];
	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
	int i;

	for (i = 0; i < count; i++) {
		u8 *uuid = namespace_to_uuid(devs[i]);
		struct resource *res;

		if (IS_ERR_OR_NULL(uuid)) {
			WARN_ON(1);
			continue;
		}

		if (memcmp(uuid, nd_label->uuid, NSLABEL_UUID_LEN) != 0)
			continue;
		if (is_namespace_blk(devs[i])) {
			res = nsblk_add_resource(nd_region, ndd,
					to_nd_namespace_blk(devs[i]),
					__le64_to_cpu(nd_label->dpa));
			if (!res)
				return -ENXIO;
			nd_dbg_dpa(nd_region, ndd, res, "%d assign\n", count);
		} else {
			dev_err(&nd_region->dev,
					"error: conflicting extents for uuid: %pUb\n",
					nd_label->uuid);
			return -ENXIO;
		}
		break;
	}

	return i;
}

struct device *create_namespace_blk(struct nd_region *nd_region,
		struct nd_namespace_label *nd_label, int count)
{

	struct nd_mapping *nd_mapping = &nd_region->mapping[0];
1904
	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
1905
	struct nd_namespace_blk *nsblk;
1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936
	char *name[NSLABEL_NAME_LEN];
	struct device *dev = NULL;
	struct resource *res;

	nsblk = kzalloc(sizeof(*nsblk), GFP_KERNEL);
	if (!nsblk)
		return ERR_PTR(-ENOMEM);
	dev = &nsblk->common.dev;
	dev->type = &namespace_blk_device_type;
	dev->parent = &nd_region->dev;
	nsblk->id = -1;
	nsblk->lbasize = __le64_to_cpu(nd_label->lbasize);
	nsblk->uuid = kmemdup(nd_label->uuid, NSLABEL_UUID_LEN,
			GFP_KERNEL);
	if (!nsblk->uuid)
		goto blk_err;
	memcpy(name, nd_label->name, NSLABEL_NAME_LEN);
	if (name[0])
		nsblk->alt_name = kmemdup(name, NSLABEL_NAME_LEN,
				GFP_KERNEL);
	res = nsblk_add_resource(nd_region, ndd, nsblk,
			__le64_to_cpu(nd_label->dpa));
	if (!res)
		goto blk_err;
	nd_dbg_dpa(nd_region, ndd, res, "%d: assign\n", count);
	return dev;
 blk_err:
	namespace_blk_release(dev);
	return ERR_PTR(-ENXIO);
}

1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961
static int cmp_dpa(const void *a, const void *b)
{
	const struct device *dev_a = *(const struct device **) a;
	const struct device *dev_b = *(const struct device **) b;
	struct nd_namespace_blk *nsblk_a, *nsblk_b;
	struct nd_namespace_pmem *nspm_a, *nspm_b;

	if (is_namespace_io(dev_a))
		return 0;

	if (is_namespace_blk(dev_a)) {
		nsblk_a = to_nd_namespace_blk(dev_a);
		nsblk_b = to_nd_namespace_blk(dev_b);

		return memcmp(&nsblk_a->res[0]->start, &nsblk_b->res[0]->start,
				sizeof(resource_size_t));
	}

	nspm_a = to_nd_namespace_pmem(dev_a);
	nspm_b = to_nd_namespace_pmem(dev_b);

	return memcmp(&nspm_a->nsio.res.start, &nspm_b->nsio.res.start,
			sizeof(resource_size_t));
}

1962 1963 1964 1965 1966
static struct device **scan_labels(struct nd_region *nd_region)
{
	struct nd_mapping *nd_mapping = &nd_region->mapping[0];
	struct device *dev, **devs = NULL;
	struct nd_label_ent *label_ent, *e;
1967
	int i, count = 0;
1968

1969 1970
	/* "safe" because create_namespace_pmem() might list_move() label_ent */
	list_for_each_entry_safe(label_ent, e, &nd_mapping->labels, list) {
1971
		struct nd_namespace_label *nd_label = label_ent->label;
1972
		struct device **__devs;
1973
		u32 flags;
1974

1975 1976 1977
		if (!nd_label)
			continue;
		flags = __le32_to_cpu(nd_label->flags);
1978 1979 1980
		if (is_nd_blk(&nd_region->dev)
				== !!(flags & NSLABEL_FLAG_LOCAL))
			/* pass, region matches label type */;
1981 1982 1983
		else
			continue;

1984 1985 1986
		i = add_namespace_resource(nd_region, nd_label, devs, count);
		if (i < 0)
			goto err;
1987 1988 1989 1990 1991 1992 1993 1994 1995
		if (i < count)
			continue;
		__devs = kcalloc(count + 2, sizeof(dev), GFP_KERNEL);
		if (!__devs)
			goto err;
		memcpy(__devs, devs, sizeof(dev) * count);
		kfree(devs);
		devs = __devs;

1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019
		if (is_nd_blk(&nd_region->dev)) {
			dev = create_namespace_blk(nd_region, nd_label, count);
			if (IS_ERR(dev))
				goto err;
			devs[count++] = dev;
		} else {
			dev = create_namespace_pmem(nd_region, nd_label);
			if (IS_ERR(dev)) {
				switch (PTR_ERR(dev)) {
				case -EAGAIN:
					/* skip invalid labels */
					continue;
				case -ENODEV:
					/* fallthrough to seed creation */
					break;
				default:
					goto err;
				}
			} else
				devs[count++] = dev;

			/* we only expect one valid pmem label set per region */
			break;
		}
2020 2021
	}

2022 2023 2024
	dev_dbg(&nd_region->dev, "%s: discovered %d %s namespace%s\n",
			__func__, count, is_nd_blk(&nd_region->dev)
			? "blk" : "pmem", count == 1 ? "" : "s");
2025 2026 2027

	if (count == 0) {
		/* Publish a zero-sized namespace for userspace to configure. */
2028
		nd_mapping_free_labels(nd_mapping);
2029 2030 2031 2032

		devs = kcalloc(2, sizeof(dev), GFP_KERNEL);
		if (!devs)
			goto err;
2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048
		if (is_nd_blk(&nd_region->dev)) {
			struct nd_namespace_blk *nsblk;

			nsblk = kzalloc(sizeof(*nsblk), GFP_KERNEL);
			if (!nsblk)
				goto err;
			dev = &nsblk->common.dev;
			dev->type = &namespace_blk_device_type;
		} else {
			struct nd_namespace_pmem *nspm;

			nspm = kzalloc(sizeof(*nspm), GFP_KERNEL);
			if (!nspm)
				goto err;
			dev = &nspm->nsio.common.dev;
			dev->type = &namespace_pmem_device_type;
2049
			nd_namespace_pmem_set_resource(nd_region, nspm, 0);
2050
		}
2051 2052
		dev->parent = &nd_region->dev;
		devs[count++] = dev;
2053 2054 2055
	} else if (is_nd_pmem(&nd_region->dev)) {
		/* clean unselected labels */
		for (i = 0; i < nd_region->ndr_mappings; i++) {
2056 2057 2058 2059
			struct list_head *l, *e;
			LIST_HEAD(list);
			int j;

2060 2061 2062 2063 2064
			nd_mapping = &nd_region->mapping[i];
			if (list_empty(&nd_mapping->labels)) {
				WARN_ON(1);
				continue;
			}
2065 2066 2067 2068 2069 2070 2071

			j = count;
			list_for_each_safe(l, e, &nd_mapping->labels) {
				if (!j--)
					break;
				list_move_tail(l, &list);
			}
2072
			nd_mapping_free_labels(nd_mapping);
2073
			list_splice_init(&list, &nd_mapping->labels);
2074
		}
2075 2076
	}

2077 2078 2079
	if (count > 1)
		sort(devs, count, sizeof(struct device *), cmp_dpa, NULL);

2080 2081
	return devs;

2082
 err:
2083 2084 2085 2086 2087
	for (i = 0; devs[i]; i++)
		if (is_nd_blk(&nd_region->dev))
			namespace_blk_release(devs[i]);
		else
			namespace_pmem_release(devs[i]);
2088 2089 2090 2091
	kfree(devs);
	return NULL;
}

2092
static struct device **create_namespaces(struct nd_region *nd_region)
2093 2094 2095
{
	struct nd_mapping *nd_mapping = &nd_region->mapping[0];
	struct device **devs;
2096
	int i;
2097 2098 2099 2100

	if (nd_region->ndr_mappings == 0)
		return NULL;

2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114
	/* lock down all mappings while we scan labels */
	for (i = 0; i < nd_region->ndr_mappings; i++) {
		nd_mapping = &nd_region->mapping[i];
		mutex_lock_nested(&nd_mapping->lock, i);
	}

	devs = scan_labels(nd_region);

	for (i = 0; i < nd_region->ndr_mappings; i++) {
		int reverse = nd_region->ndr_mappings - 1 - i;

		nd_mapping = &nd_region->mapping[reverse];
		mutex_unlock(&nd_mapping->lock);
	}
2115 2116 2117 2118

	return devs;
}

2119 2120 2121 2122 2123 2124 2125 2126
static int init_active_labels(struct nd_region *nd_region)
{
	int i;

	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 nvdimm *nvdimm = nd_mapping->nvdimm;
2127
		struct nd_label_ent *label_ent;
2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151
		int count, j;

		/*
		 * If the dimm is disabled then prevent the region from
		 * being activated if it aliases DPA.
		 */
		if (!ndd) {
			if ((nvdimm->flags & NDD_ALIASING) == 0)
				return 0;
			dev_dbg(&nd_region->dev, "%s: is disabled, failing probe\n",
					dev_name(&nd_mapping->nvdimm->dev));
			return -ENXIO;
		}
		nd_mapping->ndd = ndd;
		atomic_inc(&nvdimm->busy);
		get_ndd(ndd);

		count = nd_label_active_count(ndd);
		dev_dbg(ndd->dev, "%s: %d\n", __func__, count);
		if (!count)
			continue;
		for (j = 0; j < count; j++) {
			struct nd_namespace_label *label;

2152 2153 2154
			label_ent = kzalloc(sizeof(*label_ent), GFP_KERNEL);
			if (!label_ent)
				break;
2155
			label = nd_label_active(ndd, j);
2156 2157 2158 2159 2160
			label_ent->label = label;

			mutex_lock(&nd_mapping->lock);
			list_add_tail(&label_ent->list, &nd_mapping->labels);
			mutex_unlock(&nd_mapping->lock);
2161
		}
2162 2163 2164 2165 2166 2167 2168 2169

		if (j >= count)
			continue;

		mutex_lock(&nd_mapping->lock);
		nd_mapping_free_labels(nd_mapping);
		mutex_unlock(&nd_mapping->lock);
		return -ENOMEM;
2170 2171 2172 2173 2174
	}

	return 0;
}

2175 2176 2177
int nd_region_register_namespaces(struct nd_region *nd_region, int *err)
{
	struct device **devs = NULL;
2178
	int i, rc = 0, type;
2179 2180

	*err = 0;
2181 2182 2183 2184 2185 2186 2187 2188 2189
	nvdimm_bus_lock(&nd_region->dev);
	rc = init_active_labels(nd_region);
	if (rc) {
		nvdimm_bus_unlock(&nd_region->dev);
		return rc;
	}

	type = nd_region_to_nstype(nd_region);
	switch (type) {
2190 2191 2192
	case ND_DEVICE_NAMESPACE_IO:
		devs = create_namespace_io(nd_region);
		break;
2193
	case ND_DEVICE_NAMESPACE_PMEM:
2194
	case ND_DEVICE_NAMESPACE_BLK:
2195
		devs = create_namespaces(nd_region);
2196
		break;
2197 2198 2199
	default:
		break;
	}
2200
	nvdimm_bus_unlock(&nd_region->dev);
2201 2202 2203 2204 2205 2206

	if (!devs)
		return -ENODEV;

	for (i = 0; devs[i]; i++) {
		struct device *dev = devs[i];
2207
		int id;
2208

2209 2210 2211 2212 2213 2214 2215
		if (type == ND_DEVICE_NAMESPACE_BLK) {
			struct nd_namespace_blk *nsblk;

			nsblk = to_nd_namespace_blk(dev);
			id = ida_simple_get(&nd_region->ns_ida, 0, 0,
					GFP_KERNEL);
			nsblk->id = id;
2216 2217 2218 2219 2220 2221 2222
		} else if (type == ND_DEVICE_NAMESPACE_PMEM) {
			struct nd_namespace_pmem *nspm;

			nspm = to_nd_namespace_pmem(dev);
			id = ida_simple_get(&nd_region->ns_ida, 0, 0,
					GFP_KERNEL);
			nspm->id = id;
2223 2224 2225 2226 2227 2228
		} else
			id = i;

		if (id < 0)
			break;
		dev_set_name(dev, "namespace%d.%d", nd_region->id, id);
2229 2230 2231
		dev->groups = nd_namespace_attribute_groups;
		nd_device_register(dev);
	}
2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251
	if (i)
		nd_region->ns_seed = devs[0];

	if (devs[i]) {
		int j;

		for (j = i; devs[j]; j++) {
			struct device *dev = devs[j];

			device_initialize(dev);
			put_device(dev);
		}
		*err = j - i;
		/*
		 * All of the namespaces we tried to register failed, so
		 * fail region activation.
		 */
		if (*err == 0)
			rc = -ENODEV;
	}
2252 2253
	kfree(devs);

2254 2255 2256
	if (rc == -ENODEV)
		return rc;

2257 2258
	return i;
}