region_devs.c 25.5 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12
/*
 * 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.
 */
13
#include <linux/scatterlist.h>
14
#include <linux/highmem.h>
15
#include <linux/sched.h>
16
#include <linux/slab.h>
D
Dan Williams 已提交
17
#include <linux/hash.h>
18
#include <linux/pmem.h>
19
#include <linux/sort.h>
20
#include <linux/io.h>
21
#include <linux/nd.h>
22 23 24
#include "nd-core.h"
#include "nd.h"

25 26 27 28 29 30
/*
 * For readq() and writeq() on 32-bit builds, the hi-lo, lo-hi order is
 * irrelevant.
 */
#include <linux/io-64-nonatomic-hi-lo.h>

31
static DEFINE_IDA(region_ida);
D
Dan Williams 已提交
32
static DEFINE_PER_CPU(int, flush_idx);
33

34 35 36 37 38 39 40
static int nvdimm_map_flush(struct device *dev, struct nvdimm *nvdimm, int dimm,
		struct nd_region_data *ndrd)
{
	int i, j;

	dev_dbg(dev, "%s: map %d flush address%s\n", nvdimm_name(nvdimm),
			nvdimm->num_flush, nvdimm->num_flush == 1 ? "" : "es");
41
	for (i = 0; i < (1 << ndrd->hints_shift); i++) {
42 43 44 45 46 47 48 49 50 51 52 53 54 55 56
		struct resource *res = &nvdimm->flush_wpq[i];
		unsigned long pfn = PHYS_PFN(res->start);
		void __iomem *flush_page;

		/* check if flush hints share a page */
		for (j = 0; j < i; j++) {
			struct resource *res_j = &nvdimm->flush_wpq[j];
			unsigned long pfn_j = PHYS_PFN(res_j->start);

			if (pfn == pfn_j)
				break;
		}

		if (j < i)
			flush_page = (void __iomem *) ((unsigned long)
57 58
					ndrd_get_flush_wpq(ndrd, dimm, j)
					& PAGE_MASK);
59 60
		else
			flush_page = devm_nvdimm_ioremap(dev,
61
					PFN_PHYS(pfn), PAGE_SIZE);
62 63
		if (!flush_page)
			return -ENXIO;
64 65
		ndrd_set_flush_wpq(ndrd, dimm, i, flush_page
				+ (res->start & ~PAGE_MASK));
66 67 68 69 70 71 72
	}

	return 0;
}

int nd_region_activate(struct nd_region *nd_region)
{
73
	int i, j, num_flush = 0;
74 75 76 77 78 79 80 81 82 83 84
	struct nd_region_data *ndrd;
	struct device *dev = &nd_region->dev;
	size_t flush_data_size = sizeof(void *);

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

		/* at least one null hint slot per-dimm for the "no-hint" case */
		flush_data_size += sizeof(void *);
D
Dan Williams 已提交
85
		num_flush = min_not_zero(num_flush, nvdimm->num_flush);
86 87 88 89 90 91 92 93 94 95 96
		if (!nvdimm->num_flush)
			continue;
		flush_data_size += nvdimm->num_flush * sizeof(void *);
	}
	nvdimm_bus_unlock(&nd_region->dev);

	ndrd = devm_kzalloc(dev, sizeof(*ndrd) + flush_data_size, GFP_KERNEL);
	if (!ndrd)
		return -ENOMEM;
	dev_set_drvdata(dev, ndrd);

97 98 99 100
	if (!num_flush)
		return 0;

	ndrd->hints_shift = ilog2(num_flush);
101 102 103 104 105 106 107 108 109
	for (i = 0; i < nd_region->ndr_mappings; i++) {
		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
		struct nvdimm *nvdimm = nd_mapping->nvdimm;
		int rc = nvdimm_map_flush(&nd_region->dev, nvdimm, i, ndrd);

		if (rc)
			return rc;
	}

110 111 112 113 114 115 116 117 118 119 120 121 122 123 124
	/*
	 * Clear out entries that are duplicates. This should prevent the
	 * extra flushings.
	 */
	for (i = 0; i < nd_region->ndr_mappings - 1; i++) {
		/* ignore if NULL already */
		if (!ndrd_get_flush_wpq(ndrd, i, 0))
			continue;

		for (j = i + 1; j < nd_region->ndr_mappings; j++)
			if (ndrd_get_flush_wpq(ndrd, i, 0) ==
			    ndrd_get_flush_wpq(ndrd, j, 0))
				ndrd_set_flush_wpq(ndrd, j, 0, NULL);
	}

125 126 127
	return 0;
}

128 129 130 131 132 133 134 135 136 137 138
static void nd_region_release(struct device *dev)
{
	struct nd_region *nd_region = to_nd_region(dev);
	u16 i;

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

		put_device(&nvdimm->dev);
	}
V
Vishal Verma 已提交
139
	free_percpu(nd_region->lane);
140
	ida_simple_remove(&region_ida, nd_region->id);
141 142 143 144
	if (is_nd_blk(dev))
		kfree(to_nd_blk_region(dev));
	else
		kfree(nd_region);
145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161
}

static struct device_type nd_blk_device_type = {
	.name = "nd_blk",
	.release = nd_region_release,
};

static struct device_type nd_pmem_device_type = {
	.name = "nd_pmem",
	.release = nd_region_release,
};

static struct device_type nd_volatile_device_type = {
	.name = "nd_volatile",
	.release = nd_region_release,
};

162
bool is_nd_pmem(struct device *dev)
163 164 165 166
{
	return dev ? dev->type == &nd_pmem_device_type : false;
}

167 168 169 170 171
bool is_nd_blk(struct device *dev)
{
	return dev ? dev->type == &nd_blk_device_type : false;
}

172 173 174 175 176 177 178 179 180
struct nd_region *to_nd_region(struct device *dev)
{
	struct nd_region *nd_region = container_of(dev, struct nd_region, dev);

	WARN_ON(dev->type->release != nd_region_release);
	return nd_region;
}
EXPORT_SYMBOL_GPL(to_nd_region);

181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207
struct nd_blk_region *to_nd_blk_region(struct device *dev)
{
	struct nd_region *nd_region = to_nd_region(dev);

	WARN_ON(!is_nd_blk(dev));
	return container_of(nd_region, struct nd_blk_region, nd_region);
}
EXPORT_SYMBOL_GPL(to_nd_blk_region);

void *nd_region_provider_data(struct nd_region *nd_region)
{
	return nd_region->provider_data;
}
EXPORT_SYMBOL_GPL(nd_region_provider_data);

void *nd_blk_region_provider_data(struct nd_blk_region *ndbr)
{
	return ndbr->blk_provider_data;
}
EXPORT_SYMBOL_GPL(nd_blk_region_provider_data);

void nd_blk_region_set_provider_data(struct nd_blk_region *ndbr, void *data)
{
	ndbr->blk_provider_data = data;
}
EXPORT_SYMBOL_GPL(nd_blk_region_set_provider_data);

208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237
/**
 * nd_region_to_nstype() - region to an integer namespace type
 * @nd_region: region-device to interrogate
 *
 * This is the 'nstype' attribute of a region as well, an input to the
 * MODALIAS for namespace devices, and bit number for a nvdimm_bus to match
 * namespace devices with namespace drivers.
 */
int nd_region_to_nstype(struct nd_region *nd_region)
{
	if (is_nd_pmem(&nd_region->dev)) {
		u16 i, alias;

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

			if (nvdimm->flags & NDD_ALIASING)
				alias++;
		}
		if (alias)
			return ND_DEVICE_NAMESPACE_PMEM;
		else
			return ND_DEVICE_NAMESPACE_IO;
	} else if (is_nd_blk(&nd_region->dev)) {
		return ND_DEVICE_NAMESPACE_BLK;
	}

	return 0;
}
238 239
EXPORT_SYMBOL(nd_region_to_nstype);

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
static ssize_t size_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_region *nd_region = to_nd_region(dev);
	unsigned long long size = 0;

	if (is_nd_pmem(dev)) {
		size = nd_region->ndr_size;
	} else if (nd_region->ndr_mappings == 1) {
		struct nd_mapping *nd_mapping = &nd_region->mapping[0];

		size = nd_mapping->size;
	}

	return sprintf(buf, "%llu\n", size);
}
static DEVICE_ATTR_RO(size);

static ssize_t mappings_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_region *nd_region = to_nd_region(dev);

	return sprintf(buf, "%d\n", nd_region->ndr_mappings);
}
static DEVICE_ATTR_RO(mappings);

267 268 269 270 271 272 273 274 275
static ssize_t nstype_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_region *nd_region = to_nd_region(dev);

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

276 277 278 279 280 281 282 283 284 285 286 287 288 289 290
static ssize_t set_cookie_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_region *nd_region = to_nd_region(dev);
	struct nd_interleave_set *nd_set = nd_region->nd_set;

	if (is_nd_pmem(dev) && nd_set)
		/* pass, should be precluded by region_visible */;
	else
		return -ENXIO;

	return sprintf(buf, "%#llx\n", nd_set->cookie);
}
static DEVICE_ATTR_RO(set_cookie);

291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315
resource_size_t nd_region_available_dpa(struct nd_region *nd_region)
{
	resource_size_t blk_max_overlap = 0, available, overlap;
	int i;

	WARN_ON(!is_nvdimm_bus_locked(&nd_region->dev));

 retry:
	available = 0;
	overlap = blk_max_overlap;
	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);

		/* if a dimm is disabled the available capacity is zero */
		if (!ndd)
			return 0;

		if (is_nd_pmem(&nd_region->dev)) {
			available += nd_pmem_available_dpa(nd_region,
					nd_mapping, &overlap);
			if (overlap > blk_max_overlap) {
				blk_max_overlap = overlap;
				goto retry;
			}
316 317
		} else if (is_nd_blk(&nd_region->dev))
			available += nd_blk_available_dpa(nd_region);
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
	}

	return available;
}

static ssize_t available_size_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_region *nd_region = to_nd_region(dev);
	unsigned long long available = 0;

	/*
	 * Flush in-flight updates and grab a snapshot of the available
	 * size.  Of course, this value is potentially invalidated the
	 * memory nvdimm_bus_lock() is dropped, but that's userspace's
	 * problem to not race itself.
	 */
	nvdimm_bus_lock(dev);
	wait_nvdimm_bus_probe_idle(dev);
	available = nd_region_available_dpa(nd_region);
	nvdimm_bus_unlock(dev);

	return sprintf(buf, "%llu\n", available);
}
static DEVICE_ATTR_RO(available_size);

344 345 346
static ssize_t init_namespaces_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
347
	struct nd_region_data *ndrd = dev_get_drvdata(dev);
348 349 350
	ssize_t rc;

	nvdimm_bus_lock(dev);
351 352
	if (ndrd)
		rc = sprintf(buf, "%d/%d\n", ndrd->ns_active, ndrd->ns_count);
353 354 355 356 357 358 359 360
	else
		rc = -ENXIO;
	nvdimm_bus_unlock(dev);

	return rc;
}
static DEVICE_ATTR_RO(init_namespaces);

361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376
static ssize_t namespace_seed_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_region *nd_region = to_nd_region(dev);
	ssize_t rc;

	nvdimm_bus_lock(dev);
	if (nd_region->ns_seed)
		rc = sprintf(buf, "%s\n", dev_name(nd_region->ns_seed));
	else
		rc = sprintf(buf, "\n");
	nvdimm_bus_unlock(dev);
	return rc;
}
static DEVICE_ATTR_RO(namespace_seed);

377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393
static ssize_t btt_seed_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_region *nd_region = to_nd_region(dev);
	ssize_t rc;

	nvdimm_bus_lock(dev);
	if (nd_region->btt_seed)
		rc = sprintf(buf, "%s\n", dev_name(nd_region->btt_seed));
	else
		rc = sprintf(buf, "\n");
	nvdimm_bus_unlock(dev);

	return rc;
}
static DEVICE_ATTR_RO(btt_seed);

394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410
static ssize_t pfn_seed_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_region *nd_region = to_nd_region(dev);
	ssize_t rc;

	nvdimm_bus_lock(dev);
	if (nd_region->pfn_seed)
		rc = sprintf(buf, "%s\n", dev_name(nd_region->pfn_seed));
	else
		rc = sprintf(buf, "\n");
	nvdimm_bus_unlock(dev);

	return rc;
}
static DEVICE_ATTR_RO(pfn_seed);

411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427
static ssize_t dax_seed_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_region *nd_region = to_nd_region(dev);
	ssize_t rc;

	nvdimm_bus_lock(dev);
	if (nd_region->dax_seed)
		rc = sprintf(buf, "%s\n", dev_name(nd_region->dax_seed));
	else
		rc = sprintf(buf, "\n");
	nvdimm_bus_unlock(dev);

	return rc;
}
static DEVICE_ATTR_RO(dax_seed);

428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450
static ssize_t read_only_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct nd_region *nd_region = to_nd_region(dev);

	return sprintf(buf, "%d\n", nd_region->ro);
}

static ssize_t read_only_store(struct device *dev,
		struct device_attribute *attr, const char *buf, size_t len)
{
	bool ro;
	int rc = strtobool(buf, &ro);
	struct nd_region *nd_region = to_nd_region(dev);

	if (rc)
		return rc;

	nd_region->ro = ro;
	return len;
}
static DEVICE_ATTR_RW(read_only);

451 452
static struct attribute *nd_region_attributes[] = {
	&dev_attr_size.attr,
453
	&dev_attr_nstype.attr,
454
	&dev_attr_mappings.attr,
455
	&dev_attr_btt_seed.attr,
456
	&dev_attr_pfn_seed.attr,
457
	&dev_attr_dax_seed.attr,
458
	&dev_attr_read_only.attr,
459
	&dev_attr_set_cookie.attr,
460 461
	&dev_attr_available_size.attr,
	&dev_attr_namespace_seed.attr,
462
	&dev_attr_init_namespaces.attr,
463 464 465
	NULL,
};

466 467 468 469 470
static umode_t region_visible(struct kobject *kobj, struct attribute *a, int n)
{
	struct device *dev = container_of(kobj, typeof(*dev), kobj);
	struct nd_region *nd_region = to_nd_region(dev);
	struct nd_interleave_set *nd_set = nd_region->nd_set;
471
	int type = nd_region_to_nstype(nd_region);
472

473 474 475
	if (!is_nd_pmem(dev) && a == &dev_attr_pfn_seed.attr)
		return 0;

476 477 478
	if (!is_nd_pmem(dev) && a == &dev_attr_dax_seed.attr)
		return 0;

479 480
	if (a != &dev_attr_set_cookie.attr
			&& a != &dev_attr_available_size.attr)
481 482
		return a->mode;

483 484 485 486 487 488
	if ((type == ND_DEVICE_NAMESPACE_PMEM
				|| type == ND_DEVICE_NAMESPACE_BLK)
			&& a == &dev_attr_available_size.attr)
		return a->mode;
	else if (is_nd_pmem(dev) && nd_set)
		return a->mode;
489 490 491 492

	return 0;
}

493 494
struct attribute_group nd_region_attribute_group = {
	.attrs = nd_region_attributes,
495
	.is_visible = region_visible,
496 497 498
};
EXPORT_SYMBOL_GPL(nd_region_attribute_group);

499 500 501 502 503 504 505 506 507
u64 nd_region_interleave_set_cookie(struct nd_region *nd_region)
{
	struct nd_interleave_set *nd_set = nd_region->nd_set;

	if (nd_set)
		return nd_set->cookie;
	return 0;
}

508 509 510 511 512 513 514 515 516
u64 nd_region_interleave_set_altcookie(struct nd_region *nd_region)
{
	struct nd_interleave_set *nd_set = nd_region->nd_set;

	if (nd_set)
		return nd_set->altcookie;
	return 0;
}

517 518 519 520
void nd_mapping_free_labels(struct nd_mapping *nd_mapping)
{
	struct nd_label_ent *label_ent, *e;

521
	lockdep_assert_held(&nd_mapping->lock);
522 523 524 525 526 527
	list_for_each_entry_safe(label_ent, e, &nd_mapping->labels, list) {
		list_del(&label_ent->list);
		kfree(label_ent);
	}
}

528 529
/*
 * Upon successful probe/remove, take/release a reference on the
530
 * associated interleave set (if present), and plant new btt + namespace
531 532
 * seeds.  Also, on the removal of a BLK region, notify the provider to
 * disable the region.
533 534 535 536
 */
static void nd_region_notify_driver_action(struct nvdimm_bus *nvdimm_bus,
		struct device *dev, bool probe)
{
537 538
	struct nd_region *nd_region;

539
	if (!probe && (is_nd_pmem(dev) || is_nd_blk(dev))) {
540 541
		int i;

542
		nd_region = to_nd_region(dev);
543 544
		for (i = 0; i < nd_region->ndr_mappings; i++) {
			struct nd_mapping *nd_mapping = &nd_region->mapping[i];
545
			struct nvdimm_drvdata *ndd = nd_mapping->ndd;
546 547
			struct nvdimm *nvdimm = nd_mapping->nvdimm;

548 549 550 551
			mutex_lock(&nd_mapping->lock);
			nd_mapping_free_labels(nd_mapping);
			mutex_unlock(&nd_mapping->lock);

552 553
			put_ndd(ndd);
			nd_mapping->ndd = NULL;
554 555
			if (ndd)
				atomic_dec(&nvdimm->busy);
556
		}
557 558 559

		if (is_nd_pmem(dev))
			return;
560
	}
561 562
	if (dev->parent && (is_nd_blk(dev->parent) || is_nd_pmem(dev->parent))
			&& probe) {
563
		nd_region = to_nd_region(dev->parent);
564 565
		nvdimm_bus_lock(dev);
		if (nd_region->ns_seed == dev)
566
			nd_region_create_ns_seed(nd_region);
567
		nvdimm_bus_unlock(dev);
568
	}
569
	if (is_nd_btt(dev) && probe) {
570 571
		struct nd_btt *nd_btt = to_nd_btt(dev);

572 573 574 575
		nd_region = to_nd_region(dev->parent);
		nvdimm_bus_lock(dev);
		if (nd_region->btt_seed == dev)
			nd_region_create_btt_seed(nd_region);
576 577
		if (nd_region->ns_seed == &nd_btt->ndns->dev)
			nd_region_create_ns_seed(nd_region);
578 579
		nvdimm_bus_unlock(dev);
	}
580
	if (is_nd_pfn(dev) && probe) {
581 582
		struct nd_pfn *nd_pfn = to_nd_pfn(dev);

583 584 585 586
		nd_region = to_nd_region(dev->parent);
		nvdimm_bus_lock(dev);
		if (nd_region->pfn_seed == dev)
			nd_region_create_pfn_seed(nd_region);
587 588
		if (nd_region->ns_seed == &nd_pfn->ndns->dev)
			nd_region_create_ns_seed(nd_region);
589 590
		nvdimm_bus_unlock(dev);
	}
591
	if (is_nd_dax(dev) && probe) {
592 593
		struct nd_dax *nd_dax = to_nd_dax(dev);

594 595 596 597
		nd_region = to_nd_region(dev->parent);
		nvdimm_bus_lock(dev);
		if (nd_region->dax_seed == dev)
			nd_region_create_dax_seed(nd_region);
598 599
		if (nd_region->ns_seed == &nd_dax->nd_pfn.ndns->dev)
			nd_region_create_ns_seed(nd_region);
600 601
		nvdimm_bus_unlock(dev);
	}
602 603 604 605 606 607 608 609 610 611 612 613
}

void nd_region_probe_success(struct nvdimm_bus *nvdimm_bus, struct device *dev)
{
	nd_region_notify_driver_action(nvdimm_bus, dev, true);
}

void nd_region_disable(struct nvdimm_bus *nvdimm_bus, struct device *dev)
{
	nd_region_notify_driver_action(nvdimm_bus, dev, false);
}

614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725
static ssize_t mappingN(struct device *dev, char *buf, int n)
{
	struct nd_region *nd_region = to_nd_region(dev);
	struct nd_mapping *nd_mapping;
	struct nvdimm *nvdimm;

	if (n >= nd_region->ndr_mappings)
		return -ENXIO;
	nd_mapping = &nd_region->mapping[n];
	nvdimm = nd_mapping->nvdimm;

	return sprintf(buf, "%s,%llu,%llu\n", dev_name(&nvdimm->dev),
			nd_mapping->start, nd_mapping->size);
}

#define REGION_MAPPING(idx) \
static ssize_t mapping##idx##_show(struct device *dev,		\
		struct device_attribute *attr, char *buf)	\
{								\
	return mappingN(dev, buf, idx);				\
}								\
static DEVICE_ATTR_RO(mapping##idx)

/*
 * 32 should be enough for a while, even in the presence of socket
 * interleave a 32-way interleave set is a degenerate case.
 */
REGION_MAPPING(0);
REGION_MAPPING(1);
REGION_MAPPING(2);
REGION_MAPPING(3);
REGION_MAPPING(4);
REGION_MAPPING(5);
REGION_MAPPING(6);
REGION_MAPPING(7);
REGION_MAPPING(8);
REGION_MAPPING(9);
REGION_MAPPING(10);
REGION_MAPPING(11);
REGION_MAPPING(12);
REGION_MAPPING(13);
REGION_MAPPING(14);
REGION_MAPPING(15);
REGION_MAPPING(16);
REGION_MAPPING(17);
REGION_MAPPING(18);
REGION_MAPPING(19);
REGION_MAPPING(20);
REGION_MAPPING(21);
REGION_MAPPING(22);
REGION_MAPPING(23);
REGION_MAPPING(24);
REGION_MAPPING(25);
REGION_MAPPING(26);
REGION_MAPPING(27);
REGION_MAPPING(28);
REGION_MAPPING(29);
REGION_MAPPING(30);
REGION_MAPPING(31);

static umode_t mapping_visible(struct kobject *kobj, struct attribute *a, int n)
{
	struct device *dev = container_of(kobj, struct device, kobj);
	struct nd_region *nd_region = to_nd_region(dev);

	if (n < nd_region->ndr_mappings)
		return a->mode;
	return 0;
}

static struct attribute *mapping_attributes[] = {
	&dev_attr_mapping0.attr,
	&dev_attr_mapping1.attr,
	&dev_attr_mapping2.attr,
	&dev_attr_mapping3.attr,
	&dev_attr_mapping4.attr,
	&dev_attr_mapping5.attr,
	&dev_attr_mapping6.attr,
	&dev_attr_mapping7.attr,
	&dev_attr_mapping8.attr,
	&dev_attr_mapping9.attr,
	&dev_attr_mapping10.attr,
	&dev_attr_mapping11.attr,
	&dev_attr_mapping12.attr,
	&dev_attr_mapping13.attr,
	&dev_attr_mapping14.attr,
	&dev_attr_mapping15.attr,
	&dev_attr_mapping16.attr,
	&dev_attr_mapping17.attr,
	&dev_attr_mapping18.attr,
	&dev_attr_mapping19.attr,
	&dev_attr_mapping20.attr,
	&dev_attr_mapping21.attr,
	&dev_attr_mapping22.attr,
	&dev_attr_mapping23.attr,
	&dev_attr_mapping24.attr,
	&dev_attr_mapping25.attr,
	&dev_attr_mapping26.attr,
	&dev_attr_mapping27.attr,
	&dev_attr_mapping28.attr,
	&dev_attr_mapping29.attr,
	&dev_attr_mapping30.attr,
	&dev_attr_mapping31.attr,
	NULL,
};

struct attribute_group nd_mapping_attribute_group = {
	.is_visible = mapping_visible,
	.attrs = mapping_attributes,
};
EXPORT_SYMBOL_GPL(nd_mapping_attribute_group);

726
int nd_blk_region_init(struct nd_region *nd_region)
727
{
728 729 730 731 732 733 734 735 736 737 738 739
	struct device *dev = &nd_region->dev;
	struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);

	if (!is_nd_blk(dev))
		return 0;

	if (nd_region->ndr_mappings < 1) {
		dev_err(dev, "invalid BLK region\n");
		return -ENXIO;
	}

	return to_nd_blk_region(dev)->enable(nvdimm_bus, dev);
740 741
}

V
Vishal Verma 已提交
742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794
/**
 * nd_region_acquire_lane - allocate and lock a lane
 * @nd_region: region id and number of lanes possible
 *
 * A lane correlates to a BLK-data-window and/or a log slot in the BTT.
 * We optimize for the common case where there are 256 lanes, one
 * per-cpu.  For larger systems we need to lock to share lanes.  For now
 * this implementation assumes the cost of maintaining an allocator for
 * free lanes is on the order of the lock hold time, so it implements a
 * static lane = cpu % num_lanes mapping.
 *
 * In the case of a BTT instance on top of a BLK namespace a lane may be
 * acquired recursively.  We lock on the first instance.
 *
 * In the case of a BTT instance on top of PMEM, we only acquire a lane
 * for the BTT metadata updates.
 */
unsigned int nd_region_acquire_lane(struct nd_region *nd_region)
{
	unsigned int cpu, lane;

	cpu = get_cpu();
	if (nd_region->num_lanes < nr_cpu_ids) {
		struct nd_percpu_lane *ndl_lock, *ndl_count;

		lane = cpu % nd_region->num_lanes;
		ndl_count = per_cpu_ptr(nd_region->lane, cpu);
		ndl_lock = per_cpu_ptr(nd_region->lane, lane);
		if (ndl_count->count++ == 0)
			spin_lock(&ndl_lock->lock);
	} else
		lane = cpu;

	return lane;
}
EXPORT_SYMBOL(nd_region_acquire_lane);

void nd_region_release_lane(struct nd_region *nd_region, unsigned int lane)
{
	if (nd_region->num_lanes < nr_cpu_ids) {
		unsigned int cpu = get_cpu();
		struct nd_percpu_lane *ndl_lock, *ndl_count;

		ndl_count = per_cpu_ptr(nd_region->lane, cpu);
		ndl_lock = per_cpu_ptr(nd_region->lane, lane);
		if (--ndl_count->count == 0)
			spin_unlock(&ndl_lock->lock);
		put_cpu();
	}
	put_cpu();
}
EXPORT_SYMBOL(nd_region_release_lane);

795 796 797 798 799 800
static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus,
		struct nd_region_desc *ndr_desc, struct device_type *dev_type,
		const char *caller)
{
	struct nd_region *nd_region;
	struct device *dev;
801
	void *region_buf;
V
Vishal Verma 已提交
802
	unsigned int i;
803
	int ro = 0;
804 805

	for (i = 0; i < ndr_desc->num_mappings; i++) {
806 807
		struct nd_mapping_desc *mapping = &ndr_desc->mapping[i];
		struct nvdimm *nvdimm = mapping->nvdimm;
808

809
		if ((mapping->start | mapping->size) % SZ_4K) {
810 811 812 813 814
			dev_err(&nvdimm_bus->dev, "%s: %s mapping%d is not 4K aligned\n",
					caller, dev_name(&nvdimm->dev), i);

			return NULL;
		}
815 816 817

		if (nvdimm->flags & NDD_UNARMED)
			ro = 1;
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
	if (dev_type == &nd_blk_device_type) {
		struct nd_blk_region_desc *ndbr_desc;
		struct nd_blk_region *ndbr;

		ndbr_desc = to_blk_region_desc(ndr_desc);
		ndbr = kzalloc(sizeof(*ndbr) + sizeof(struct nd_mapping)
				* ndr_desc->num_mappings,
				GFP_KERNEL);
		if (ndbr) {
			nd_region = &ndbr->nd_region;
			ndbr->enable = ndbr_desc->enable;
			ndbr->do_io = ndbr_desc->do_io;
		}
		region_buf = ndbr;
	} else {
		nd_region = kzalloc(sizeof(struct nd_region)
				+ sizeof(struct nd_mapping)
				* ndr_desc->num_mappings,
				GFP_KERNEL);
		region_buf = nd_region;
	}

	if (!region_buf)
843 844
		return NULL;
	nd_region->id = ida_simple_get(&region_ida, 0, 0, GFP_KERNEL);
V
Vishal Verma 已提交
845 846 847 848 849 850 851 852 853 854 855 856 857
	if (nd_region->id < 0)
		goto err_id;

	nd_region->lane = alloc_percpu(struct nd_percpu_lane);
	if (!nd_region->lane)
		goto err_percpu;

        for (i = 0; i < nr_cpu_ids; i++) {
		struct nd_percpu_lane *ndl;

		ndl = per_cpu_ptr(nd_region->lane, i);
		spin_lock_init(&ndl->lock);
		ndl->count = 0;
858 859 860
	}

	for (i = 0; i < ndr_desc->num_mappings; i++) {
861 862 863 864 865 866
		struct nd_mapping_desc *mapping = &ndr_desc->mapping[i];
		struct nvdimm *nvdimm = mapping->nvdimm;

		nd_region->mapping[i].nvdimm = nvdimm;
		nd_region->mapping[i].start = mapping->start;
		nd_region->mapping[i].size = mapping->size;
867 868
		INIT_LIST_HEAD(&nd_region->mapping[i].labels);
		mutex_init(&nd_region->mapping[i].lock);
869 870 871 872 873

		get_device(&nvdimm->dev);
	}
	nd_region->ndr_mappings = ndr_desc->num_mappings;
	nd_region->provider_data = ndr_desc->provider_data;
874
	nd_region->nd_set = ndr_desc->nd_set;
V
Vishal Verma 已提交
875
	nd_region->num_lanes = ndr_desc->num_lanes;
876
	nd_region->flags = ndr_desc->flags;
877
	nd_region->ro = ro;
878
	nd_region->numa_node = ndr_desc->numa_node;
879
	ida_init(&nd_region->ns_ida);
880
	ida_init(&nd_region->btt_ida);
881
	ida_init(&nd_region->pfn_ida);
882
	ida_init(&nd_region->dax_ida);
883 884 885 886 887 888 889 890 891 892
	dev = &nd_region->dev;
	dev_set_name(dev, "region%d", nd_region->id);
	dev->parent = &nvdimm_bus->dev;
	dev->type = dev_type;
	dev->groups = ndr_desc->attr_groups;
	nd_region->ndr_size = resource_size(ndr_desc->res);
	nd_region->ndr_start = ndr_desc->res->start;
	nd_device_register(dev);

	return nd_region;
V
Vishal Verma 已提交
893 894 895 896

 err_percpu:
	ida_simple_remove(&region_ida, nd_region->id);
 err_id:
897
	kfree(region_buf);
V
Vishal Verma 已提交
898
	return NULL;
899 900 901 902 903
}

struct nd_region *nvdimm_pmem_region_create(struct nvdimm_bus *nvdimm_bus,
		struct nd_region_desc *ndr_desc)
{
V
Vishal Verma 已提交
904
	ndr_desc->num_lanes = ND_MAX_LANES;
905 906 907 908 909 910 911 912 913 914
	return nd_region_create(nvdimm_bus, ndr_desc, &nd_pmem_device_type,
			__func__);
}
EXPORT_SYMBOL_GPL(nvdimm_pmem_region_create);

struct nd_region *nvdimm_blk_region_create(struct nvdimm_bus *nvdimm_bus,
		struct nd_region_desc *ndr_desc)
{
	if (ndr_desc->num_mappings > 1)
		return NULL;
V
Vishal Verma 已提交
915
	ndr_desc->num_lanes = min(ndr_desc->num_lanes, ND_MAX_LANES);
916 917 918 919 920 921 922 923
	return nd_region_create(nvdimm_bus, ndr_desc, &nd_blk_device_type,
			__func__);
}
EXPORT_SYMBOL_GPL(nvdimm_blk_region_create);

struct nd_region *nvdimm_volatile_region_create(struct nvdimm_bus *nvdimm_bus,
		struct nd_region_desc *ndr_desc)
{
V
Vishal Verma 已提交
924
	ndr_desc->num_lanes = ND_MAX_LANES;
925 926 927 928
	return nd_region_create(nvdimm_bus, ndr_desc, &nd_volatile_device_type,
			__func__);
}
EXPORT_SYMBOL_GPL(nvdimm_volatile_region_create);
D
Dan Williams 已提交
929

930 931 932 933 934 935 936
/**
 * nvdimm_flush - flush any posted write queues between the cpu and pmem media
 * @nd_region: blk or interleaved pmem region
 */
void nvdimm_flush(struct nd_region *nd_region)
{
	struct nd_region_data *ndrd = dev_get_drvdata(&nd_region->dev);
D
Dan Williams 已提交
937 938 939 940 941 942 943 944
	int i, idx;

	/*
	 * Try to encourage some diversity in flush hint addresses
	 * across cpus assuming a limited number of flush hints.
	 */
	idx = this_cpu_read(flush_idx);
	idx = this_cpu_add_return(flush_idx, hash_32(current->pid + idx, 8));
945 946 947 948 949 950 951 952 953 954

	/*
	 * The first wmb() is needed to 'sfence' all previous writes
	 * such that they are architecturally visible for the platform
	 * buffer flush.  Note that we've already arranged for pmem
	 * writes to avoid the cache via arch_memcpy_to_pmem().  The
	 * final wmb() ensures ordering for the NVDIMM flush write.
	 */
	wmb();
	for (i = 0; i < nd_region->ndr_mappings; i++)
955 956
		if (ndrd_get_flush_wpq(ndrd, i, 0))
			writeq(1, ndrd_get_flush_wpq(ndrd, i, idx));
957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979
	wmb();
}
EXPORT_SYMBOL_GPL(nvdimm_flush);

/**
 * nvdimm_has_flush - determine write flushing requirements
 * @nd_region: blk or interleaved pmem region
 *
 * Returns 1 if writes require flushing
 * Returns 0 if writes do not require flushing
 * Returns -ENXIO if flushing capability can not be determined
 */
int nvdimm_has_flush(struct nd_region *nd_region)
{
	struct nd_region_data *ndrd = dev_get_drvdata(&nd_region->dev);
	int i;

	/* no nvdimm == flushing capability unknown */
	if (nd_region->ndr_mappings == 0)
		return -ENXIO;

	for (i = 0; i < nd_region->ndr_mappings; i++)
		/* flush hints present, flushing required */
980
		if (ndrd_get_flush_wpq(ndrd, i, 0))
981 982 983 984 985 986 987 988 989 990
			return 1;

	/*
	 * The platform defines dimm devices without hints, assume
	 * platform persistence mechanism like ADR
	 */
	return 0;
}
EXPORT_SYMBOL_GPL(nvdimm_has_flush);

D
Dan Williams 已提交
991 992 993 994
void __exit nd_region_devs_exit(void)
{
	ida_destroy(&region_ida);
}