hmat.c 20.9 KB
Newer Older
1 2 3 4 5 6 7 8 9 10
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (c) 2019, Intel Corporation.
 *
 * Heterogeneous Memory Attributes Table (HMAT) representation
 *
 * This program parses and reports the platform's HMAT tables, and registers
 * the applicable attributes with the node's interfaces.
 */

11 12 13
#define pr_fmt(fmt) "acpi/hmat: " fmt
#define dev_fmt(fmt) "acpi/hmat: " fmt

14 15 16 17 18
#include <linux/acpi.h>
#include <linux/bitops.h>
#include <linux/device.h>
#include <linux/init.h>
#include <linux/list.h>
19 20
#include <linux/mm.h>
#include <linux/platform_device.h>
21
#include <linux/list_sort.h>
22
#include <linux/memregion.h>
23 24
#include <linux/memory.h>
#include <linux/mutex.h>
25 26 27
#include <linux/node.h>
#include <linux/sysfs.h>

28
static u8 hmat_revision;
29

30 31 32 33 34
static LIST_HEAD(targets);
static LIST_HEAD(initiators);
static LIST_HEAD(localities);

static DEFINE_MUTEX(target_lock);
35 36 37 38 39 40 41 42 43 44 45 46 47 48

/*
 * The defined enum order is used to prioritize attributes to break ties when
 * selecting the best performing node.
 */
enum locality_types {
	WRITE_LATENCY,
	READ_LATENCY,
	WRITE_BANDWIDTH,
	READ_BANDWIDTH,
};

static struct memory_locality *localities_types[4];

49 50 51 52 53
struct target_cache {
	struct list_head node;
	struct node_cache_attrs cache_attrs;
};

54 55 56 57
struct memory_target {
	struct list_head node;
	unsigned int memory_pxm;
	unsigned int processor_pxm;
58
	struct resource memregions;
59
	struct node_hmem_attrs hmem_attrs;
60
	struct list_head caches;
61 62
	struct node_cache_attrs cache_attrs;
	bool registered;
63 64 65 66 67 68 69 70 71 72 73 74
};

struct memory_initiator {
	struct list_head node;
	unsigned int processor_pxm;
};

struct memory_locality {
	struct list_head node;
	struct acpi_hmat_locality *hmat_loc;
};

75
static struct memory_initiator *find_mem_initiator(unsigned int cpu_pxm)
76 77 78 79 80 81 82 83 84
{
	struct memory_initiator *initiator;

	list_for_each_entry(initiator, &initiators, node)
		if (initiator->processor_pxm == cpu_pxm)
			return initiator;
	return NULL;
}

85
static struct memory_target *find_mem_target(unsigned int mem_pxm)
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
{
	struct memory_target *target;

	list_for_each_entry(target, &targets, node)
		if (target->memory_pxm == mem_pxm)
			return target;
	return NULL;
}

static __init void alloc_memory_initiator(unsigned int cpu_pxm)
{
	struct memory_initiator *initiator;

	if (pxm_to_node(cpu_pxm) == NUMA_NO_NODE)
		return;

	initiator = find_mem_initiator(cpu_pxm);
	if (initiator)
		return;

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

	initiator->processor_pxm = cpu_pxm;
	list_add_tail(&initiator->node, &initiators);
}

114 115
static __init void alloc_memory_target(unsigned int mem_pxm,
		resource_size_t start, resource_size_t len)
116 117 118 119
{
	struct memory_target *target;

	target = find_mem_target(mem_pxm);
120 121 122 123 124 125 126 127 128 129 130 131 132 133 134
	if (!target) {
		target = kzalloc(sizeof(*target), GFP_KERNEL);
		if (!target)
			return;
		target->memory_pxm = mem_pxm;
		target->processor_pxm = PXM_INVAL;
		target->memregions = (struct resource) {
			.name	= "ACPI mem",
			.start	= 0,
			.end	= -1,
			.flags	= IORESOURCE_MEM,
		};
		list_add_tail(&target->node, &targets);
		INIT_LIST_HEAD(&target->caches);
	}
135

136 137 138 139 140 141 142 143
	/*
	 * There are potentially multiple ranges per PXM, so record each
	 * in the per-target memregions resource tree.
	 */
	if (!__request_region(&target->memregions, start, len, "memory target",
				IORESOURCE_MEM))
		pr_warn("failed to reserve %#llx - %#llx in pxm: %d\n",
				start, start + len, mem_pxm);
144 145
}

146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181
static __init const char *hmat_data_type(u8 type)
{
	switch (type) {
	case ACPI_HMAT_ACCESS_LATENCY:
		return "Access Latency";
	case ACPI_HMAT_READ_LATENCY:
		return "Read Latency";
	case ACPI_HMAT_WRITE_LATENCY:
		return "Write Latency";
	case ACPI_HMAT_ACCESS_BANDWIDTH:
		return "Access Bandwidth";
	case ACPI_HMAT_READ_BANDWIDTH:
		return "Read Bandwidth";
	case ACPI_HMAT_WRITE_BANDWIDTH:
		return "Write Bandwidth";
	default:
		return "Reserved";
	}
}

static __init const char *hmat_data_type_suffix(u8 type)
{
	switch (type) {
	case ACPI_HMAT_ACCESS_LATENCY:
	case ACPI_HMAT_READ_LATENCY:
	case ACPI_HMAT_WRITE_LATENCY:
		return " nsec";
	case ACPI_HMAT_ACCESS_BANDWIDTH:
	case ACPI_HMAT_READ_BANDWIDTH:
	case ACPI_HMAT_WRITE_BANDWIDTH:
		return " MB/s";
	default:
		return "";
	}
}

182
static u32 hmat_normalize(u16 entry, u64 base, u8 type)
183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216
{
	u32 value;

	/*
	 * Check for invalid and overflow values
	 */
	if (entry == 0xffff || !entry)
		return 0;
	else if (base > (UINT_MAX / (entry)))
		return 0;

	/*
	 * Divide by the base unit for version 1, convert latency from
	 * picosenonds to nanoseconds if revision 2.
	 */
	value = entry * base;
	if (hmat_revision == 1) {
		if (value < 10)
			return 0;
		value = DIV_ROUND_UP(value, 10);
	} else if (hmat_revision == 2) {
		switch (type) {
		case ACPI_HMAT_ACCESS_LATENCY:
		case ACPI_HMAT_READ_LATENCY:
		case ACPI_HMAT_WRITE_LATENCY:
			value = DIV_ROUND_UP(value, 1000);
			break;
		default:
			break;
		}
	}
	return value;
}

217
static void hmat_update_target_access(struct memory_target *target,
218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284
					     u8 type, u32 value)
{
	switch (type) {
	case ACPI_HMAT_ACCESS_LATENCY:
		target->hmem_attrs.read_latency = value;
		target->hmem_attrs.write_latency = value;
		break;
	case ACPI_HMAT_READ_LATENCY:
		target->hmem_attrs.read_latency = value;
		break;
	case ACPI_HMAT_WRITE_LATENCY:
		target->hmem_attrs.write_latency = value;
		break;
	case ACPI_HMAT_ACCESS_BANDWIDTH:
		target->hmem_attrs.read_bandwidth = value;
		target->hmem_attrs.write_bandwidth = value;
		break;
	case ACPI_HMAT_READ_BANDWIDTH:
		target->hmem_attrs.read_bandwidth = value;
		break;
	case ACPI_HMAT_WRITE_BANDWIDTH:
		target->hmem_attrs.write_bandwidth = value;
		break;
	default:
		break;
	}
}

static __init void hmat_add_locality(struct acpi_hmat_locality *hmat_loc)
{
	struct memory_locality *loc;

	loc = kzalloc(sizeof(*loc), GFP_KERNEL);
	if (!loc) {
		pr_notice_once("Failed to allocate HMAT locality\n");
		return;
	}

	loc->hmat_loc = hmat_loc;
	list_add_tail(&loc->node, &localities);

	switch (hmat_loc->data_type) {
	case ACPI_HMAT_ACCESS_LATENCY:
		localities_types[READ_LATENCY] = loc;
		localities_types[WRITE_LATENCY] = loc;
		break;
	case ACPI_HMAT_READ_LATENCY:
		localities_types[READ_LATENCY] = loc;
		break;
	case ACPI_HMAT_WRITE_LATENCY:
		localities_types[WRITE_LATENCY] = loc;
		break;
	case ACPI_HMAT_ACCESS_BANDWIDTH:
		localities_types[READ_BANDWIDTH] = loc;
		localities_types[WRITE_BANDWIDTH] = loc;
		break;
	case ACPI_HMAT_READ_BANDWIDTH:
		localities_types[READ_BANDWIDTH] = loc;
		break;
	case ACPI_HMAT_WRITE_BANDWIDTH:
		localities_types[WRITE_BANDWIDTH] = loc;
		break;
	default:
		break;
	}
}

285 286 287 288
static __init int hmat_parse_locality(union acpi_subtable_headers *header,
				      const unsigned long end)
{
	struct acpi_hmat_locality *hmat_loc = (void *)header;
289
	struct memory_target *target;
290 291 292
	unsigned int init, targ, total_size, ipds, tpds;
	u32 *inits, *targs, value;
	u16 *entries;
293
	u8 type, mem_hier;
294 295

	if (hmat_loc->header.length < sizeof(*hmat_loc)) {
296
		pr_notice("HMAT: Unexpected locality header length: %u\n",
297 298 299 300 301
			 hmat_loc->header.length);
		return -EINVAL;
	}

	type = hmat_loc->data_type;
302
	mem_hier = hmat_loc->flags & ACPI_HMAT_MEMORY_HIERARCHY;
303 304 305 306 307
	ipds = hmat_loc->number_of_initiator_Pds;
	tpds = hmat_loc->number_of_target_Pds;
	total_size = sizeof(*hmat_loc) + sizeof(*entries) * ipds * tpds +
		     sizeof(*inits) * ipds + sizeof(*targs) * tpds;
	if (hmat_loc->header.length < total_size) {
308
		pr_notice("HMAT: Unexpected locality header length:%u, minimum required:%u\n",
309 310 311 312
			 hmat_loc->header.length, total_size);
		return -EINVAL;
	}

313
	pr_info("HMAT: Locality: Flags:%02x Type:%s Initiator Domains:%u Target Domains:%u Base:%lld\n",
314 315 316 317 318 319 320
		hmat_loc->flags, hmat_data_type(type), ipds, tpds,
		hmat_loc->entry_base_unit);

	inits = (u32 *)(hmat_loc + 1);
	targs = inits + ipds;
	entries = (u16 *)(targs + tpds);
	for (init = 0; init < ipds; init++) {
321
		alloc_memory_initiator(inits[init]);
322 323 324 325
		for (targ = 0; targ < tpds; targ++) {
			value = hmat_normalize(entries[init * tpds + targ],
					       hmat_loc->entry_base_unit,
					       type);
326
			pr_info("  Initiator-Target[%u-%u]:%u%s\n",
327 328
				inits[init], targs[targ], value,
				hmat_data_type_suffix(type));
329 330 331 332 333 334

			if (mem_hier == ACPI_HMAT_MEMORY) {
				target = find_mem_target(targs[targ]);
				if (target && target->processor_pxm == inits[init])
					hmat_update_target_access(target, type, value);
			}
335 336 337
		}
	}

338 339 340
	if (mem_hier == ACPI_HMAT_MEMORY)
		hmat_add_locality(hmat_loc);

341 342 343 344 345 346 347
	return 0;
}

static __init int hmat_parse_cache(union acpi_subtable_headers *header,
				   const unsigned long end)
{
	struct acpi_hmat_cache *cache = (void *)header;
348 349
	struct memory_target *target;
	struct target_cache *tcache;
350 351 352
	u32 attrs;

	if (cache->header.length < sizeof(*cache)) {
353
		pr_notice("HMAT: Unexpected cache header length: %u\n",
354 355 356 357 358
			 cache->header.length);
		return -EINVAL;
	}

	attrs = cache->cache_attributes;
359
	pr_info("HMAT: Cache: Domain:%u Size:%llu Attrs:%08x SMBIOS Handles:%d\n",
360 361 362
		cache->memory_PD, cache->cache_size, attrs,
		cache->number_of_SMBIOShandles);

363 364 365 366 367 368 369 370 371 372 373 374 375
	target = find_mem_target(cache->memory_PD);
	if (!target)
		return 0;

	tcache = kzalloc(sizeof(*tcache), GFP_KERNEL);
	if (!tcache) {
		pr_notice_once("Failed to allocate HMAT cache info\n");
		return 0;
	}

	tcache->cache_attrs.size = cache->cache_size;
	tcache->cache_attrs.level = (attrs & ACPI_HMAT_CACHE_LEVEL) >> 4;
	tcache->cache_attrs.line_size = (attrs & ACPI_HMAT_CACHE_LINE_SIZE) >> 16;
376 377 378

	switch ((attrs & ACPI_HMAT_CACHE_ASSOCIATIVITY) >> 8) {
	case ACPI_HMAT_CA_DIRECT_MAPPED:
379
		tcache->cache_attrs.indexing = NODE_CACHE_DIRECT_MAP;
380 381
		break;
	case ACPI_HMAT_CA_COMPLEX_CACHE_INDEXING:
382
		tcache->cache_attrs.indexing = NODE_CACHE_INDEXED;
383 384 385
		break;
	case ACPI_HMAT_CA_NONE:
	default:
386
		tcache->cache_attrs.indexing = NODE_CACHE_OTHER;
387 388 389 390 391
		break;
	}

	switch ((attrs & ACPI_HMAT_WRITE_POLICY) >> 12) {
	case ACPI_HMAT_CP_WB:
392
		tcache->cache_attrs.write_policy = NODE_CACHE_WRITE_BACK;
393 394
		break;
	case ACPI_HMAT_CP_WT:
395
		tcache->cache_attrs.write_policy = NODE_CACHE_WRITE_THROUGH;
396 397 398
		break;
	case ACPI_HMAT_CP_NONE:
	default:
399
		tcache->cache_attrs.write_policy = NODE_CACHE_WRITE_OTHER;
400 401
		break;
	}
402
	list_add_tail(&tcache->node, &target->caches);
403

404 405 406 407 408 409 410
	return 0;
}

static int __init hmat_parse_proximity_domain(union acpi_subtable_headers *header,
					      const unsigned long end)
{
	struct acpi_hmat_proximity_domain *p = (void *)header;
411
	struct memory_target *target = NULL;
412 413

	if (p->header.length != sizeof(*p)) {
414
		pr_notice("HMAT: Unexpected address range header length: %u\n",
415 416 417 418 419
			 p->header.length);
		return -EINVAL;
	}

	if (hmat_revision == 1)
420
		pr_info("HMAT: Memory (%#llx length %#llx) Flags:%04x Processor Domain:%u Memory Domain:%u\n",
421 422 423
			p->reserved3, p->reserved4, p->flags, p->processor_PD,
			p->memory_PD);
	else
424
		pr_info("HMAT: Memory Flags:%04x Processor Domain:%u Memory Domain:%u\n",
425 426
			p->flags, p->processor_PD, p->memory_PD);

427
	if (p->flags & ACPI_HMAT_MEMORY_PD_VALID && hmat_revision == 1) {
428 429 430 431 432 433 434 435 436 437 438 439 440
		target = find_mem_target(p->memory_PD);
		if (!target) {
			pr_debug("HMAT: Memory Domain missing from SRAT\n");
			return -EINVAL;
		}
	}
	if (target && p->flags & ACPI_HMAT_PROCESSOR_PD_VALID) {
		int p_node = pxm_to_node(p->processor_PD);

		if (p_node == NUMA_NO_NODE) {
			pr_debug("HMAT: Invalid Processor Domain\n");
			return -EINVAL;
		}
441
		target->processor_pxm = p->processor_PD;
442 443
	}

444 445 446 447 448 449 450 451 452 453 454 455
	return 0;
}

static int __init hmat_parse_subtable(union acpi_subtable_headers *header,
				      const unsigned long end)
{
	struct acpi_hmat_structure *hdr = (void *)header;

	if (!hdr)
		return -EINVAL;

	switch (hdr->type) {
456
	case ACPI_HMAT_TYPE_PROXIMITY:
457 458 459 460 461 462 463 464 465 466
		return hmat_parse_proximity_domain(header, end);
	case ACPI_HMAT_TYPE_LOCALITY:
		return hmat_parse_locality(header, end);
	case ACPI_HMAT_TYPE_CACHE:
		return hmat_parse_cache(header, end);
	default:
		return -EINVAL;
	}
}

467 468 469 470 471 472 473 474 475
static __init int srat_parse_mem_affinity(union acpi_subtable_headers *header,
					  const unsigned long end)
{
	struct acpi_srat_mem_affinity *ma = (void *)header;

	if (!ma)
		return -EINVAL;
	if (!(ma->flags & ACPI_SRAT_MEM_ENABLED))
		return 0;
476
	alloc_memory_target(ma->proximity_domain, ma->base_address, ma->length);
477 478 479
	return 0;
}

480
static u32 hmat_initiator_perf(struct memory_target *target,
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
			       struct memory_initiator *initiator,
			       struct acpi_hmat_locality *hmat_loc)
{
	unsigned int ipds, tpds, i, idx = 0, tdx = 0;
	u32 *inits, *targs;
	u16 *entries;

	ipds = hmat_loc->number_of_initiator_Pds;
	tpds = hmat_loc->number_of_target_Pds;
	inits = (u32 *)(hmat_loc + 1);
	targs = inits + ipds;
	entries = (u16 *)(targs + tpds);

	for (i = 0; i < ipds; i++) {
		if (inits[i] == initiator->processor_pxm) {
			idx = i;
			break;
		}
	}

	if (i == ipds)
		return 0;

	for (i = 0; i < tpds; i++) {
		if (targs[i] == target->memory_pxm) {
			tdx = i;
			break;
		}
	}
	if (i == tpds)
		return 0;

	return hmat_normalize(entries[idx * tpds + tdx],
			      hmat_loc->entry_base_unit,
			      hmat_loc->data_type);
}

518
static bool hmat_update_best(u8 type, u32 value, u32 *best)
519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561
{
	bool updated = false;

	if (!value)
		return false;

	switch (type) {
	case ACPI_HMAT_ACCESS_LATENCY:
	case ACPI_HMAT_READ_LATENCY:
	case ACPI_HMAT_WRITE_LATENCY:
		if (!*best || *best > value) {
			*best = value;
			updated = true;
		}
		break;
	case ACPI_HMAT_ACCESS_BANDWIDTH:
	case ACPI_HMAT_READ_BANDWIDTH:
	case ACPI_HMAT_WRITE_BANDWIDTH:
		if (!*best || *best < value) {
			*best = value;
			updated = true;
		}
		break;
	}

	return updated;
}

static int initiator_cmp(void *priv, struct list_head *a, struct list_head *b)
{
	struct memory_initiator *ia;
	struct memory_initiator *ib;
	unsigned long *p_nodes = priv;

	ia = list_entry(a, struct memory_initiator, node);
	ib = list_entry(b, struct memory_initiator, node);

	set_bit(ia->processor_pxm, p_nodes);
	set_bit(ib->processor_pxm, p_nodes);

	return ia->processor_pxm - ib->processor_pxm;
}

562
static void hmat_register_target_initiators(struct memory_target *target)
563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621
{
	static DECLARE_BITMAP(p_nodes, MAX_NUMNODES);
	struct memory_initiator *initiator;
	unsigned int mem_nid, cpu_nid;
	struct memory_locality *loc = NULL;
	u32 best = 0;
	int i;

	mem_nid = pxm_to_node(target->memory_pxm);
	/*
	 * If the Address Range Structure provides a local processor pxm, link
	 * only that one. Otherwise, find the best performance attributes and
	 * register all initiators that match.
	 */
	if (target->processor_pxm != PXM_INVAL) {
		cpu_nid = pxm_to_node(target->processor_pxm);
		register_memory_node_under_compute_node(mem_nid, cpu_nid, 0);
		return;
	}

	if (list_empty(&localities))
		return;

	/*
	 * We need the initiator list sorted so we can use bitmap_clear for
	 * previously set initiators when we find a better memory accessor.
	 * We'll also use the sorting to prime the candidate nodes with known
	 * initiators.
	 */
	bitmap_zero(p_nodes, MAX_NUMNODES);
	list_sort(p_nodes, &initiators, initiator_cmp);
	for (i = WRITE_LATENCY; i <= READ_BANDWIDTH; i++) {
		loc = localities_types[i];
		if (!loc)
			continue;

		best = 0;
		list_for_each_entry(initiator, &initiators, node) {
			u32 value;

			if (!test_bit(initiator->processor_pxm, p_nodes))
				continue;

			value = hmat_initiator_perf(target, initiator, loc->hmat_loc);
			if (hmat_update_best(loc->hmat_loc->data_type, value, &best))
				bitmap_clear(p_nodes, 0, initiator->processor_pxm);
			if (value != best)
				clear_bit(initiator->processor_pxm, p_nodes);
		}
		if (best)
			hmat_update_target_access(target, loc->hmat_loc->data_type, best);
	}

	for_each_set_bit(i, p_nodes, MAX_NUMNODES) {
		cpu_nid = pxm_to_node(i);
		register_memory_node_under_compute_node(mem_nid, cpu_nid, 0);
	}
}

622
static void hmat_register_target_cache(struct memory_target *target)
623 624 625 626 627 628 629 630
{
	unsigned mem_nid = pxm_to_node(target->memory_pxm);
	struct target_cache *tcache;

	list_for_each_entry(tcache, &target->caches, node)
		node_add_cache(mem_nid, &tcache->cache_attrs);
}

631
static void hmat_register_target_perf(struct memory_target *target)
632 633 634 635 636
{
	unsigned mem_nid = pxm_to_node(target->memory_pxm);
	node_set_perf_attrs(mem_nid, &target->hmem_attrs, 0);
}

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
static void hmat_register_target_device(struct memory_target *target,
		struct resource *r)
{
	/* define a clean / non-busy resource for the platform device */
	struct resource res = {
		.start = r->start,
		.end = r->end,
		.flags = IORESOURCE_MEM,
	};
	struct platform_device *pdev;
	struct memregion_info info;
	int rc, id;

	rc = region_intersects(res.start, resource_size(&res), IORESOURCE_MEM,
			IORES_DESC_SOFT_RESERVED);
	if (rc != REGION_INTERSECTS)
		return;

	id = memregion_alloc(GFP_KERNEL);
	if (id < 0) {
		pr_err("memregion allocation failure for %pr\n", &res);
		return;
	}

	pdev = platform_device_alloc("hmem", id);
	if (!pdev) {
		pr_err("hmem device allocation failure for %pr\n", &res);
		goto out_pdev;
	}

667
	pdev->dev.numa_node = pxm_to_online_node(target->memory_pxm);
668
	info = (struct memregion_info) {
669
		.target_node = pxm_to_node(target->memory_pxm),
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
	};
	rc = platform_device_add_data(pdev, &info, sizeof(info));
	if (rc < 0) {
		pr_err("hmem memregion_info allocation failure for %pr\n", &res);
		goto out_pdev;
	}

	rc = platform_device_add_resources(pdev, &res, 1);
	if (rc < 0) {
		pr_err("hmem resource allocation failure for %pr\n", &res);
		goto out_resource;
	}

	rc = platform_device_add(pdev);
	if (rc < 0) {
		dev_err(&pdev->dev, "device add failed for %pr\n", &res);
		goto out_resource;
	}

	return;

out_resource:
	put_device(&pdev->dev);
out_pdev:
	memregion_free(id);
}

697
static void hmat_register_target_devices(struct memory_target *target)
698 699 700 701 702 703 704 705 706 707 708 709 710 711
{
	struct resource *res;

	/*
	 * Do not bother creating devices if no driver is available to
	 * consume them.
	 */
	if (!IS_ENABLED(CONFIG_DEV_DAX_HMEM))
		return;

	for (res = target->memregions.child; res; res = res->sibling)
		hmat_register_target_device(target, res);
}

712
static void hmat_register_target(struct memory_target *target)
713
{
714 715
	int nid = pxm_to_node(target->memory_pxm);

716 717 718 719 720 721
	/*
	 * Devices may belong to either an offline or online
	 * node, so unconditionally add them.
	 */
	hmat_register_target_devices(target);

722 723 724 725 726 727 728 729
	/*
	 * Skip offline nodes. This can happen when memory
	 * marked EFI_MEMORY_SP, "specific purpose", is applied
	 * to all the memory in a promixity domain leading to
	 * the node being marked offline / unplugged, or if
	 * memory-only "hotplug" node is offline.
	 */
	if (nid == NUMA_NO_NODE || !node_online(nid))
730 731
		return;

732 733 734 735 736 737 738 739
	mutex_lock(&target_lock);
	if (!target->registered) {
		hmat_register_target_initiators(target);
		hmat_register_target_cache(target);
		hmat_register_target_perf(target);
		target->registered = true;
	}
	mutex_unlock(&target_lock);
740 741
}

742
static void hmat_register_targets(void)
743 744 745
{
	struct memory_target *target;

746 747
	list_for_each_entry(target, &targets, node)
		hmat_register_target(target);
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
static int hmat_callback(struct notifier_block *self,
			 unsigned long action, void *arg)
{
	struct memory_target *target;
	struct memory_notify *mnb = arg;
	int pxm, nid = mnb->status_change_nid;

	if (nid == NUMA_NO_NODE || action != MEM_ONLINE)
		return NOTIFY_OK;

	pxm = node_to_pxm(nid);
	target = find_mem_target(pxm);
	if (!target)
		return NOTIFY_OK;

	hmat_register_target(target);
	return NOTIFY_OK;
}

static struct notifier_block hmat_callback_nb = {
	.notifier_call = hmat_callback,
	.priority = 2,
};

774 775 776 777 778
static __init void hmat_free_structures(void)
{
	struct memory_target *target, *tnext;
	struct memory_locality *loc, *lnext;
	struct memory_initiator *initiator, *inext;
779
	struct target_cache *tcache, *cnext;
780 781

	list_for_each_entry_safe(target, tnext, &targets, node) {
782 783
		struct resource *res, *res_next;

784 785 786 787
		list_for_each_entry_safe(tcache, cnext, &target->caches, node) {
			list_del(&tcache->node);
			kfree(tcache);
		}
788

789
		list_del(&target->node);
790 791 792 793 794 795 796
		res = target->memregions.child;
		while (res) {
			res_next = res->sibling;
			__release_region(&target->memregions, res->start,
					resource_size(res));
			res = res_next;
		}
797 798 799 800 801 802 803 804 805 806 807 808 809 810
		kfree(target);
	}

	list_for_each_entry_safe(initiator, inext, &initiators, node) {
		list_del(&initiator->node);
		kfree(initiator);
	}

	list_for_each_entry_safe(loc, lnext, &localities, node) {
		list_del(&loc->node);
		kfree(loc);
	}
}

811 812 813 814 815 816 817 818 819
static __init int hmat_init(void)
{
	struct acpi_table_header *tbl;
	enum acpi_hmat_type i;
	acpi_status status;

	if (srat_disabled())
		return 0;

820 821 822 823 824 825 826 827 828 829 830
	status = acpi_get_table(ACPI_SIG_SRAT, 0, &tbl);
	if (ACPI_FAILURE(status))
		return 0;

	if (acpi_table_parse_entries(ACPI_SIG_SRAT,
				sizeof(struct acpi_table_srat),
				ACPI_SRAT_TYPE_MEMORY_AFFINITY,
				srat_parse_mem_affinity, 0) < 0)
		goto out_put;
	acpi_put_table(tbl);

831 832
	status = acpi_get_table(ACPI_SIG_HMAT, 0, &tbl);
	if (ACPI_FAILURE(status))
833
		goto out_put;
834 835 836 837 838 839 840 841 842 843 844

	hmat_revision = tbl->revision;
	switch (hmat_revision) {
	case 1:
	case 2:
		break;
	default:
		pr_notice("Ignoring HMAT: Unknown revision:%d\n", hmat_revision);
		goto out_put;
	}

845
	for (i = ACPI_HMAT_TYPE_PROXIMITY; i < ACPI_HMAT_TYPE_RESERVED; i++) {
846 847 848 849 850 851 852
		if (acpi_table_parse_entries(ACPI_SIG_HMAT,
					     sizeof(struct acpi_table_hmat), i,
					     hmat_parse_subtable, 0) < 0) {
			pr_notice("Ignoring HMAT: Invalid table");
			goto out_put;
		}
	}
853
	hmat_register_targets();
854 855 856 857

	/* Keep the table and structures if the notifier may use them */
	if (!register_hotmemory_notifier(&hmat_callback_nb))
		return 0;
858
out_put:
859
	hmat_free_structures();
860 861 862
	acpi_put_table(tbl);
	return 0;
}
863
device_initcall(hmat_init);