namespace_devs.c 47.4 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15
/*
 * 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>
#include <linux/slab.h>
16
#include <linux/pmem.h>
17
#include <linux/nd.h>
18
#include "nd-core.h"
19 20 21 22 23 24 25 26 27
#include "nd.h"

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

	kfree(nsio);
}

28 29 30 31 32 33 34 35 36 37 38
static void namespace_pmem_release(struct device *dev)
{
	struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);

	kfree(nspm->alt_name);
	kfree(nspm->uuid);
	kfree(nspm);
}

static void namespace_blk_release(struct device *dev)
{
39 40 41 42 43 44 45 46 47
	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);
48 49
}

50 51 52 53 54
static struct device_type namespace_io_device_type = {
	.name = "nd_namespace_io",
	.release = namespace_io_release,
};

55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79
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,
};

static bool is_namespace_pmem(struct device *dev)
{
	return dev ? dev->type == &namespace_pmem_device_type : false;
}

static bool is_namespace_blk(struct device *dev)
{
	return dev ? dev->type == &namespace_blk_device_type : false;
}

static bool is_namespace_io(struct device *dev)
{
	return dev ? dev->type == &namespace_io_device_type : false;
}

80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100
bool pmem_should_map_pages(struct device *dev)
{
	struct nd_region *nd_region = to_nd_region(dev->parent);

	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;

#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
101 102 103 104
const char *nvdimm_namespace_disk_name(struct nd_namespace_common *ndns,
		char *name)
{
	struct nd_region *nd_region = to_nd_region(ndns->dev.parent);
105
	const char *suffix = NULL;
V
Vishal Verma 已提交
106

107 108 109 110 111 112 113 114 115 116
	if (ndns->claim) {
		if (is_nd_btt(ndns->claim))
			suffix = "s";
		else if (is_nd_pfn(ndns->claim))
			suffix = "m";
		else
			dev_WARN_ONCE(&ndns->dev, 1,
					"unknown claim type by %s\n",
					dev_name(ndns->claim));
	}
V
Vishal Verma 已提交
117

118 119 120 121 122
	if (is_namespace_pmem(&ndns->dev) || is_namespace_io(&ndns->dev)) {
		if (!suffix && pmem_should_map_pages(&ndns->dev))
			suffix = "m";
		sprintf(name, "pmem%d%s", nd_region->id, suffix ? suffix : "");
	} else if (is_namespace_blk(&ndns->dev)) {
V
Vishal Verma 已提交
123 124 125
		struct nd_namespace_blk *nsblk;

		nsblk = to_nd_namespace_blk(&ndns->dev);
126 127
		sprintf(name, "ndblk%d.%d%s", nd_region->id, nsblk->id,
				suffix ? suffix : "");
V
Vishal Verma 已提交
128 129 130 131 132 133 134 135
	} else {
		return NULL;
	}

	return name;
}
EXPORT_SYMBOL(nvdimm_namespace_disk_name);

136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155
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);

156 157 158 159 160 161 162 163 164
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);

165 166 167 168 169 170 171 172 173 174 175
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)) {
176 177 178
		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);

		ns_altname = &nsblk->alt_name;
179 180 181
	} else
		return -ENXIO;

182
	if (dev->driver || to_ndns(dev)->claim)
183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210
		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;
}

211 212
static resource_size_t nd_namespace_blk_size(struct nd_namespace_blk *nsblk)
{
213
	struct nd_region *nd_region = to_nd_region(nsblk->common.dev.parent);
214 215 216 217 218 219 220 221 222 223 224 225 226 227 228
	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;
}

229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287
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;
		/*
		 * Resources with unacknoweldged adjustments indicate a
		 * 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
288 289 290
static int nd_namespace_label_update(struct nd_region *nd_region,
		struct device *dev)
{
291
	dev_WARN_ONCE(dev, dev->driver || to_ndns(dev)->claim,
D
Dan Williams 已提交
292
			"namespace must be idle during label update\n");
293
	if (dev->driver || to_ndns(dev)->claim)
D
Dan Williams 已提交
294 295 296 297 298 299 300 301
		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
302
		resource_size_t size = resource_size(&nspm->nsio.res);
D
Dan Williams 已提交
303 304 305 306 307 308 309 310

		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
311 312 313 314 315 316 317 318 319
		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
320 321 322 323
	} else
		return -ENXIO;
}

324 325 326
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
327
	struct nd_region *nd_region = to_nd_region(dev->parent);
328 329 330 331 332 333
	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
334 335
	if (rc >= 0)
		rc = nd_namespace_label_update(nd_region, dev);
336 337 338 339
	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
340
	return rc < 0 ? rc : len;
341 342 343 344 345 346 347 348 349 350 351 352
}

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)) {
353 354 355
		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);

		ns_altname = nsblk->alt_name;
356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400
	} 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);
401 402
		if (rc == 0)
			res->flags |= DPA_RESOURCE_ADJUSTED;
403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462
		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;
}

463 464
static bool space_valid(bool is_pmem, bool is_reserve,
		struct nd_label_id *label_id, struct resource *res)
465 466 467
{
	/*
	 * For BLK-space any space is valid, for PMEM-space, it must be
468 469
	 * contiguous with an existing allocation unless we are
	 * reserving pmem.
470
	 */
471
	if (is_reserve || !is_pmem)
472 473 474 475 476 477 478 479 480 481 482 483 484 485 486
		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;
487
	bool is_reserve = strcmp(label_id->id, "pmem-reserve") == 0;
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
	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;
513
			if (space_valid(is_pmem, is_reserve, label_id, NULL))
514 515 516 517 518 519 520
				loc = ALLOC_BEFORE;
		}

		/* space between allocations */
		if (!loc && next) {
			free_start = res->start + resource_size(res);
			free_end = min(mapping_end, next->start - 1);
521
			if (space_valid(is_pmem, is_reserve, label_id, res)
522 523 524 525 526 527 528 529 530 531
					&& 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;
532
			if (space_valid(is_pmem, is_reserve, label_id, res)
533 534 535 536 537 538 539 540 541 542 543 544 545
					&& 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 */
546
				if (is_pmem && !is_reserve)
547 548 549 550 551 552 553 554 555 556
					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 */
557
				if (is_pmem && !is_reserve)
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
					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;
583
			else if (!is_reserve && free_start != nd_mapping->start)
584 585 586 587 588 589 590 591 592 593
				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);
594 595
			if (rc == 0)
				res->flags |= DPA_RESOURCE_ADJUSTED;
596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620
		}

		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;
	}

621 622 623 624 625 626
	/*
	 * 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)
627 628 629 630
		return init_dpa_allocation(label_id, nd_region, nd_mapping, n);
	return n;
}

631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722
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;
}

723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738
/**
 * 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)
{
739 740
	struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(&nd_region->dev);
	bool is_pmem = strncmp(label_id->id, "pmem", 4) == 0;
741 742 743 744
	int i;

	for (i = 0; i < nd_region->ndr_mappings; i++) {
		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763
		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);
764

765 766 767 768 769 770 771 772 773 774 775 776 777
			/* 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);
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
		if (rc)
			return rc;
	}

	return 0;
}

static void nd_namespace_pmem_set_size(struct nd_region *nd_region,
		struct nd_namespace_pmem *nspm, resource_size_t size)
{
	struct resource *res = &nspm->nsio.res;

	res->start = nd_region->ndr_start;
	res->end = nd_region->ndr_start + size - 1;
}

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;

805
	if (dev->driver || to_ndns(dev)->claim)
806 807 808 809 810 811 812
		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)) {
813 814 815 816
		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);

		uuid = nsblk->uuid;
		flags = NSLABEL_FLAG_LOCAL;
817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870
	}

	/*
	 * We need a uuid for the allocation-label and dimm(s) on which
	 * to store the label.
	 */
	if (!uuid || nd_region->ndr_mappings == 0)
		return -ENXIO;

	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);

		nd_namespace_pmem_set_size(nd_region, nspm,
				val * nd_region->ndr_mappings);
871
	} else if (is_namespace_blk(dev)) {
872 873
		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);

874 875
		/*
		 * Try to delete the namespace if we deleted all of its
876 877 878
		 * allocation, this is not the seed device for the
		 * region, and it is not actively claimed by a btt
		 * instance.
879
		 */
880 881
		if (val == 0 && nd_region->ns_seed != dev
				&& !nsblk->common.claim)
882
			nd_device_unregister(dev, ND_ASYNC);
883 884 885 886 887 888 889 890
	}

	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
891
	struct nd_region *nd_region = to_nd_region(dev->parent);
892 893 894 895 896 897 898 899 900 901 902 903
	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
904 905
	if (rc >= 0)
		rc = nd_namespace_label_update(nd_region, dev);
906 907 908 909 910 911

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

		uuid = &nspm->uuid;
	} else if (is_namespace_blk(dev)) {
912 913 914
		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);

		uuid = &nsblk->uuid;
915 916 917 918 919 920 921 922 923 924 925 926 927 928
	}

	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
929
	return rc < 0 ? rc : len;
930 931
}

932
resource_size_t __nvdimm_namespace_capacity(struct nd_namespace_common *ndns)
933
{
934
	struct device *dev = &ndns->dev;
935

936 937 938
	if (is_namespace_pmem(dev)) {
		struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);

939
		return resource_size(&nspm->nsio.res);
940
	} else if (is_namespace_blk(dev)) {
941
		return nd_namespace_blk_size(to_nd_namespace_blk(dev));
942 943 944
	} else if (is_namespace_io(dev)) {
		struct nd_namespace_io *nsio = to_nd_namespace_io(dev);

945 946 947 948 949 950 951 952 953
		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;
954

955 956 957 958 959 960 961 962 963 964 965 966 967
	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)));
968 969 970 971 972 973 974 975 976 977 978 979 980
}
static DEVICE_ATTR(size, S_IRUGO, size_show, size_store);

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

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

		uuid = nspm->uuid;
	} else if (is_namespace_blk(dev)) {
981 982 983
		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);

		uuid = nsblk->uuid;
984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004
	} else
		return -ENXIO;

	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
1005
	int i;
1006

D
Dan Williams 已提交
1007 1008
	if (!nd_is_uuid_unique(dev, new_uuid))
		return -EINVAL;
1009 1010 1011 1012

	if (*old_uuid == NULL)
		goto out;

D
Dan Williams 已提交
1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032
	/*
	 * 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?
		 */
		if (nd_mapping->labels)
			return -EBUSY;
	}

1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055
	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;
1056
	ssize_t rc = 0;
1057 1058 1059 1060 1061 1062 1063
	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)) {
1064 1065 1066
		struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);

		ns_uuid = &nsblk->uuid;
1067 1068 1069 1070 1071 1072
	} else
		return -ENXIO;

	device_lock(dev);
	nvdimm_bus_lock(dev);
	wait_nvdimm_bus_probe_idle(dev);
1073 1074 1075 1076
	if (to_ndns(dev)->claim)
		rc = -EBUSY;
	if (rc >= 0)
		rc = nd_uuid_store(dev, &uuid, buf, len);
1077 1078
	if (rc >= 0)
		rc = namespace_update_uuid(nd_region, dev, uuid, ns_uuid);
D
Dan Williams 已提交
1079 1080 1081 1082
	if (rc >= 0)
		rc = nd_namespace_label_update(nd_region, dev);
	else
		kfree(uuid);
1083 1084 1085 1086 1087
	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
1088
	return rc < 0 ? rc : len;
1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114
}
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);

1115 1116
static const unsigned long ns_lbasize_supported[] = { 512, 520, 528,
	4096, 4104, 4160, 4224, 0 };
1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132

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
1133
	struct nd_region *nd_region = to_nd_region(dev->parent);
1134
	ssize_t rc = 0;
1135 1136 1137 1138 1139 1140

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

	device_lock(dev);
	nvdimm_bus_lock(dev);
1141 1142 1143 1144 1145
	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
1146 1147 1148 1149 1150
	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");
1151 1152 1153 1154 1155 1156 1157
	nvdimm_bus_unlock(dev);
	device_unlock(dev);

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

D
Dan Williams 已提交
1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199
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);

1200 1201 1202 1203 1204 1205 1206 1207 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 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);

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);

1234 1235
static struct attribute *nd_namespace_attributes[] = {
	&dev_attr_nstype.attr,
1236 1237
	&dev_attr_size.attr,
	&dev_attr_uuid.attr,
1238
	&dev_attr_holder.attr,
1239 1240
	&dev_attr_resource.attr,
	&dev_attr_alt_name.attr,
1241
	&dev_attr_force_raw.attr,
1242
	&dev_attr_sector_size.attr,
D
Dan Williams 已提交
1243
	&dev_attr_dpa_extents.attr,
1244 1245 1246
	NULL,
};

1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260
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;
1261 1262 1263 1264

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

1265 1266 1267
		return a->mode;
	}

1268 1269 1270
	if (a == &dev_attr_nstype.attr || a == &dev_attr_size.attr
			|| a == &dev_attr_holder.attr
			|| a == &dev_attr_force_raw.attr)
1271 1272 1273 1274 1275
		return a->mode;

	return 0;
}

1276 1277
static struct attribute_group nd_namespace_attribute_group = {
	.attrs = nd_namespace_attributes,
1278
	.is_visible = namespace_visible,
1279 1280 1281 1282 1283
};

static const struct attribute_group *nd_namespace_attribute_groups[] = {
	&nd_device_attribute_group,
	&nd_namespace_attribute_group,
1284
	&nd_numa_attribute_group,
1285 1286 1287
	NULL,
};

1288 1289 1290
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;
1291
	struct nd_pfn *nd_pfn = is_nd_pfn(dev) ? to_nd_pfn(dev) : NULL;
1292 1293 1294
	struct nd_namespace_common *ndns;
	resource_size_t size;

1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306
	if (nd_btt || nd_pfn) {
		struct device *host = NULL;

		if (nd_btt) {
			host = &nd_btt->dev;
			ndns = nd_btt->ndns;
		} else if (nd_pfn) {
			host = &nd_pfn->dev;
			ndns = nd_pfn->ndns;
		}

		if (!ndns || !host)
1307 1308 1309 1310 1311 1312 1313 1314 1315 1316
			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",
1317
					dev_name(host));
1318 1319
			return ERR_PTR(-EBUSY);
		}
1320
		if (dev_WARN_ONCE(&ndns->dev, ndns->claim != host,
1321
					"host (%s) vs claim (%s) mismatch\n",
1322
					dev_name(host),
1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350
					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);
		if (!nspm->uuid) {
			dev_dbg(&ndns->dev, "%s: uuid not set\n", __func__);
			return ERR_PTR(-ENODEV);
		}
	} else if (is_namespace_blk(&ndns->dev)) {
1351 1352 1353 1354 1355
		struct nd_namespace_blk *nsblk;

		nsblk = to_nd_namespace_blk(&ndns->dev);
		if (!nd_namespace_blk_validate(nsblk))
			return ERR_PTR(-ENODEV);
1356 1357 1358 1359 1360 1361
	}

	return ndns;
}
EXPORT_SYMBOL(nvdimm_namespace_common_probe);

1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377
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;
	}

1378
	dev = &nsio->common.dev;
1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390
	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;
}

1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 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
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];
		struct nd_namespace_label *nd_label;
		bool found_uuid = false;
		int l;

		for_each_label(l, nd_label, nd_mapping->labels) {
			u64 isetcookie = __le64_to_cpu(nd_label->isetcookie);
			u16 position = __le16_to_cpu(nd_label->position);
			u16 nlabel = __le16_to_cpu(nd_label->nlabel);

			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)
{
	struct nd_namespace_label *select = NULL;
	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];
		struct nd_namespace_label *nd_label;
		u64 hw_start, hw_end, pmem_start, pmem_end;
		int l;

		for_each_label(l, nd_label, nd_mapping->labels)
			if (memcmp(nd_label->uuid, pmem_id, NSLABEL_UUID_LEN) == 0)
				break;

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

		select = nd_label;
		/*
		 * 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;
		pmem_start = __le64_to_cpu(select->dpa);
		pmem_end = pmem_start + __le64_to_cpu(select->rawsize);
		if (pmem_start == hw_start && pmem_end <= hw_end)
			/* pass */;
		else
			return -EINVAL;

		nd_mapping->labels[0] = select;
		nd_mapping->labels[1] = NULL;
	}
	return 0;
}

/**
 * find_pmem_label_set - validate interleave set labelling, retrieve label0
 * @nd_region: region with mappings to validate
 */
static int find_pmem_label_set(struct nd_region *nd_region,
		struct nd_namespace_pmem *nspm)
{
	u64 cookie = nd_region_interleave_set_cookie(nd_region);
	struct nd_namespace_label *nd_label;
	u8 select_id[NSLABEL_UUID_LEN];
	resource_size_t size = 0;
	u8 *pmem_id = NULL;
	int rc = -ENODEV, l;
	u16 i;

	if (cookie == 0)
		return -ENXIO;

	/*
	 * Find a complete set of labels by uuid.  By definition we can start
	 * with any mapping as the reference label
	 */
	for_each_label(l, nd_label, nd_region->mapping[0].labels) {
		u64 isetcookie = __le64_to_cpu(nd_label->isetcookie);

		if (isetcookie != cookie)
			continue;

		for (i = 0; nd_region->ndr_mappings; i++)
			if (!has_uuid_at_pos(nd_region, nd_label->uuid,
						cookie, i))
				break;
		if (i < nd_region->ndr_mappings) {
			/*
			 * 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.
			 */
			rc = -EINVAL;
			goto err;
		} else if (pmem_id) {
			/*
			 * If there is more than one valid uuid set, we
			 * need userspace to clean this up.
			 */
			rc = -EBUSY;
			goto err;
		}
		memcpy(select_id, nd_label->uuid, NSLABEL_UUID_LEN);
		pmem_id = select_id;
	}

	/*
	 * 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).
	 */
	rc = select_pmem_id(nd_region, pmem_id);
	if (rc)
		goto err;

	/* Calculate total size and populate namespace properties from label0 */
	for (i = 0; i < nd_region->ndr_mappings; i++) {
		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
		struct nd_namespace_label *label0 = nd_mapping->labels[0];

		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;
	}

	nd_namespace_pmem_set_size(nd_region, nspm, size);

	return 0;
 err:
	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;
	}
	return rc;
}

static struct device **create_namespace_pmem(struct nd_region *nd_region)
{
	struct nd_namespace_pmem *nspm;
	struct device *dev, **devs;
	struct resource *res;
	int rc;

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

1592
	dev = &nspm->nsio.common.dev;
1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624
	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;
	rc = find_pmem_label_set(nd_region, nspm);
	if (rc == -ENODEV) {
		int i;

		/* Pass, try to permit namespace creation... */
		for (i = 0; i < nd_region->ndr_mappings; i++) {
			struct nd_mapping *nd_mapping = &nd_region->mapping[i];

			kfree(nd_mapping->labels);
			nd_mapping->labels = NULL;
		}

		/* Publish a zero-sized namespace for userspace to configure. */
		nd_namespace_pmem_set_size(nd_region, nspm, 0);

		rc = 0;
	} else if (rc)
		goto err;

	devs = kcalloc(2, sizeof(struct device *), GFP_KERNEL);
	if (!devs)
		goto err;

	devs[0] = dev;
	return devs;

 err:
1625
	namespace_pmem_release(&nspm->nsio.common.dev);
1626 1627 1628
	return NULL;
}

1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663
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;

1664
	dev = &nsblk->common.dev;
1665 1666 1667 1668 1669 1670 1671 1672 1673 1674
	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;

1675
	return &nsblk->common.dev;
1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691
}

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);
}

1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703
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");
}

1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736
static struct device **create_namespace_blk(struct nd_region *nd_region)
{
	struct nd_mapping *nd_mapping = &nd_region->mapping[0];
	struct nd_namespace_label *nd_label;
	struct device *dev, **devs = NULL;
	struct nd_namespace_blk *nsblk;
	struct nvdimm_drvdata *ndd;
	int i, l, count = 0;
	struct resource *res;

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

	ndd = to_ndd(nd_mapping);
	for_each_label(l, nd_label, nd_mapping->labels) {
		u32 flags = __le32_to_cpu(nd_label->flags);
		char *name[NSLABEL_NAME_LEN];
		struct device **__devs;

		if (flags & NSLABEL_FLAG_LOCAL)
			/* pass */;
		else
			continue;

		for (i = 0; i < count; i++) {
			nsblk = to_nd_namespace_blk(devs[i]);
			if (memcmp(nsblk->uuid, nd_label->uuid,
						NSLABEL_UUID_LEN) == 0) {
				res = nsblk_add_resource(nd_region, ndd, nsblk,
						__le64_to_cpu(nd_label->dpa));
				if (!res)
					goto err;
				nd_dbg_dpa(nd_region, ndd, res, "%s assign\n",
1737
					dev_name(&nsblk->common.dev));
1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752
				break;
			}
		}
		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;

		nsblk = kzalloc(sizeof(*nsblk), GFP_KERNEL);
		if (!nsblk)
			goto err;
1753
		dev = &nsblk->common.dev;
1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772
		dev->type = &namespace_blk_device_type;
		dev->parent = &nd_region->dev;
		dev_set_name(dev, "namespace%d.%d", nd_region->id, count);
		devs[count++] = 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 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 err;
		nd_dbg_dpa(nd_region, ndd, res, "%s assign\n",
1773
				dev_name(&nsblk->common.dev));
1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793
	}

	dev_dbg(&nd_region->dev, "%s: discovered %d blk namespace%s\n",
			__func__, count, count == 1 ? "" : "s");

	if (count == 0) {
		/* Publish a zero-sized namespace for userspace to configure. */
		for (i = 0; i < nd_region->ndr_mappings; i++) {
			struct nd_mapping *nd_mapping = &nd_region->mapping[i];

			kfree(nd_mapping->labels);
			nd_mapping->labels = NULL;
		}

		devs = kcalloc(2, sizeof(dev), GFP_KERNEL);
		if (!devs)
			goto err;
		nsblk = kzalloc(sizeof(*nsblk), GFP_KERNEL);
		if (!nsblk)
			goto err;
1794
		dev = &nsblk->common.dev;
1795 1796 1797 1798 1799 1800 1801 1802 1803 1804
		dev->type = &namespace_blk_device_type;
		dev->parent = &nd_region->dev;
		devs[count++] = dev;
	}

	return devs;

err:
	for (i = 0; i < count; i++) {
		nsblk = to_nd_namespace_blk(devs[i]);
1805
		namespace_blk_release(&nsblk->common.dev);
1806 1807 1808 1809 1810
	}
	kfree(devs);
	return NULL;
}

1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854
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;
		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;
		nd_mapping->labels = kcalloc(count + 1, sizeof(void *),
				GFP_KERNEL);
		if (!nd_mapping->labels)
			return -ENOMEM;
		for (j = 0; j < count; j++) {
			struct nd_namespace_label *label;

			label = nd_label_active(ndd, j);
			nd_mapping->labels[j] = label;
		}
	}

	return 0;
}

1855 1856 1857
int nd_region_register_namespaces(struct nd_region *nd_region, int *err)
{
	struct device **devs = NULL;
1858
	int i, rc = 0, type;
1859 1860

	*err = 0;
1861 1862 1863 1864 1865 1866 1867 1868 1869
	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) {
1870 1871 1872
	case ND_DEVICE_NAMESPACE_IO:
		devs = create_namespace_io(nd_region);
		break;
1873 1874 1875
	case ND_DEVICE_NAMESPACE_PMEM:
		devs = create_namespace_pmem(nd_region);
		break;
1876 1877 1878
	case ND_DEVICE_NAMESPACE_BLK:
		devs = create_namespace_blk(nd_region);
		break;
1879 1880 1881
	default:
		break;
	}
1882
	nvdimm_bus_unlock(&nd_region->dev);
1883 1884 1885 1886 1887 1888

	if (!devs)
		return -ENODEV;

	for (i = 0; devs[i]; i++) {
		struct device *dev = devs[i];
1889
		int id;
1890

1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903
		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;
		} else
			id = i;

		if (id < 0)
			break;
		dev_set_name(dev, "namespace%d.%d", nd_region->id, id);
1904 1905 1906
		dev->groups = nd_namespace_attribute_groups;
		nd_device_register(dev);
	}
1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926
	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;
	}
1927 1928
	kfree(devs);

1929 1930 1931
	if (rc == -ENODEV)
		return rc;

1932 1933
	return i;
}