numa.c 20.0 KB
Newer Older
1
/* Common code for 32 and 64-bit NUMA */
2 3 4 5
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/init.h>
6
#include <linux/bootmem.h>
7 8 9 10 11 12 13 14 15 16 17
#include <linux/memblock.h>
#include <linux/mmzone.h>
#include <linux/ctype.h>
#include <linux/module.h>
#include <linux/nodemask.h>
#include <linux/sched.h>
#include <linux/topology.h>

#include <asm/e820.h>
#include <asm/proto.h>
#include <asm/dma.h>
18
#include <asm/acpi.h>
19 20 21
#include <asm/amd_nb.h>

#include "numa_internal.h"
22 23

int __initdata numa_off;
24
nodemask_t numa_nodes_parsed __initdata;
25

26 27 28 29 30 31 32 33 34 35 36 37
struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
EXPORT_SYMBOL(node_data);

static struct numa_meminfo numa_meminfo
#ifndef CONFIG_MEMORY_HOTPLUG
__initdata
#endif
;

static int numa_distance_cnt;
static u8 *numa_distance;

38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54
static __init int numa_setup(char *opt)
{
	if (!opt)
		return -EINVAL;
	if (!strncmp(opt, "off", 3))
		numa_off = 1;
#ifdef CONFIG_NUMA_EMU
	if (!strncmp(opt, "fake=", 5))
		numa_emu_cmdline(opt + 5);
#endif
#ifdef CONFIG_ACPI_NUMA
	if (!strncmp(opt, "noacpi", 6))
		acpi_numa = -1;
#endif
	return 0;
}
early_param("numa", numa_setup);
55 56

/*
57
 * apicid, cpu, node mappings
58
 */
59 60 61 62
s16 __apicid_to_node[MAX_LOCAL_APIC] __cpuinitdata = {
	[0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
};

63 64 65 66 67 68 69 70 71
int __cpuinit numa_cpu_node(int cpu)
{
	int apicid = early_per_cpu(x86_cpu_to_apicid, cpu);

	if (apicid != BAD_APICID)
		return __apicid_to_node[apicid];
	return NUMA_NO_NODE;
}

72
cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
73 74
EXPORT_SYMBOL(node_to_cpumask_map);

75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108
/*
 * Map cpu index to node index
 */
DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE);
EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map);

void __cpuinit numa_set_node(int cpu, int node)
{
	int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map);

	/* early setting, no percpu area yet */
	if (cpu_to_node_map) {
		cpu_to_node_map[cpu] = node;
		return;
	}

#ifdef CONFIG_DEBUG_PER_CPU_MAPS
	if (cpu >= nr_cpu_ids || !cpu_possible(cpu)) {
		printk(KERN_ERR "numa_set_node: invalid cpu# (%d)\n", cpu);
		dump_stack();
		return;
	}
#endif
	per_cpu(x86_cpu_to_node_map, cpu) = node;

	if (node != NUMA_NO_NODE)
		set_cpu_numa_node(cpu, node);
}

void __cpuinit numa_clear_node(int cpu)
{
	numa_set_node(cpu, NUMA_NO_NODE);
}

109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127
/*
 * Allocate node_to_cpumask_map based on number of available nodes
 * Requires node_possible_map to be valid.
 *
 * Note: node_to_cpumask() is not valid until after this is done.
 * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.)
 */
void __init setup_node_to_cpumask_map(void)
{
	unsigned int node, num = 0;

	/* setup nr_node_ids if not done yet */
	if (nr_node_ids == MAX_NUMNODES) {
		for_each_node_mask(node, node_possible_map)
			num = node;
		nr_node_ids = num + 1;
	}

	/* allocate the map */
128 129
	for (node = 0; node < nr_node_ids; node++)
		alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]);
130

131 132
	/* cpumask_of_node() will now work */
	pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids);
133 134
}

135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192
static int __init numa_add_memblk_to(int nid, u64 start, u64 end,
				     struct numa_meminfo *mi)
{
	/* ignore zero length blks */
	if (start == end)
		return 0;

	/* whine about and ignore invalid blks */
	if (start > end || nid < 0 || nid >= MAX_NUMNODES) {
		pr_warning("NUMA: Warning: invalid memblk node %d (%Lx-%Lx)\n",
			   nid, start, end);
		return 0;
	}

	if (mi->nr_blks >= NR_NODE_MEMBLKS) {
		pr_err("NUMA: too many memblk ranges\n");
		return -EINVAL;
	}

	mi->blk[mi->nr_blks].start = start;
	mi->blk[mi->nr_blks].end = end;
	mi->blk[mi->nr_blks].nid = nid;
	mi->nr_blks++;
	return 0;
}

/**
 * numa_remove_memblk_from - Remove one numa_memblk from a numa_meminfo
 * @idx: Index of memblk to remove
 * @mi: numa_meminfo to remove memblk from
 *
 * Remove @idx'th numa_memblk from @mi by shifting @mi->blk[] and
 * decrementing @mi->nr_blks.
 */
void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi)
{
	mi->nr_blks--;
	memmove(&mi->blk[idx], &mi->blk[idx + 1],
		(mi->nr_blks - idx) * sizeof(mi->blk[0]));
}

/**
 * numa_add_memblk - Add one numa_memblk to numa_meminfo
 * @nid: NUMA node ID of the new memblk
 * @start: Start address of the new memblk
 * @end: End address of the new memblk
 *
 * Add a new memblk to the default numa_meminfo.
 *
 * RETURNS:
 * 0 on success, -errno on failure.
 */
int __init numa_add_memblk(int nid, u64 start, u64 end)
{
	return numa_add_memblk_to(nid, start, end, &numa_meminfo);
}

/* Initialize bootmem allocator for a node */
193
static void __init setup_node_bootmem(int nid, u64 start, u64 end)
194
{
195 196
	const u64 nd_low = PFN_PHYS(MAX_DMA_PFN);
	const u64 nd_high = PFN_PHYS(max_pfn_mapped);
197
	const size_t nd_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
198
	bool remapped = false;
199
	u64 nd_pa;
200
	void *nd;
201 202 203 204 205 206 207 208 209
	int tnid;

	/*
	 * Don't confuse VM with a node that doesn't have the
	 * minimum amount of memory:
	 */
	if (end && (end - start) < NODE_MIN_SIZE)
		return;

210 211 212
	/* initialize remap allocator before aligning to ZONE_ALIGN */
	init_alloc_remap(nid, start, end);

213 214
	start = roundup(start, ZONE_ALIGN);

215
	printk(KERN_INFO "Initmem setup node %d %016Lx-%016Lx\n",
216 217 218
	       nid, start, end);

	/*
219 220
	 * Allocate node data.  Try remap allocator first, node-local
	 * memory and then any node.  Never allocate in DMA zone.
221
	 */
222 223 224 225 226 227
	nd = alloc_remap(nid, nd_size);
	if (nd) {
		nd_pa = __pa(nd);
		remapped = true;
	} else {
		nd_pa = memblock_x86_find_in_range_node(nid, nd_low, nd_high,
228
						nd_size, SMP_CACHE_BYTES);
229 230 231 232 233 234 235 236 237 238
		if (nd_pa == MEMBLOCK_ERROR)
			nd_pa = memblock_find_in_range(nd_low, nd_high,
						nd_size, SMP_CACHE_BYTES);
		if (nd_pa == MEMBLOCK_ERROR) {
			pr_err("Cannot find %zu bytes in node %d\n",
			       nd_size, nid);
			return;
		}
		memblock_x86_reserve_range(nd_pa, nd_pa + nd_size, "NODE_DATA");
		nd = __va(nd_pa);
239 240 241
	}

	/* report and initialize */
242 243
	printk(KERN_INFO "  NODE_DATA [%016Lx - %016Lx]%s\n",
	       nd_pa, nd_pa + nd_size - 1, remapped ? " (remapped)" : "");
244
	tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT);
245
	if (!remapped && tnid != nid)
246 247
		printk(KERN_INFO "    NODE_DATA(%d) on node %d\n", nid, tnid);

248
	node_data[nid] = nd;
249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269
	memset(NODE_DATA(nid), 0, sizeof(pg_data_t));
	NODE_DATA(nid)->node_id = nid;
	NODE_DATA(nid)->node_start_pfn = start >> PAGE_SHIFT;
	NODE_DATA(nid)->node_spanned_pages = (end - start) >> PAGE_SHIFT;

	node_set_online(nid);
}

/**
 * numa_cleanup_meminfo - Cleanup a numa_meminfo
 * @mi: numa_meminfo to clean up
 *
 * Sanitize @mi by merging and removing unncessary memblks.  Also check for
 * conflicts and clear unused memblks.
 *
 * RETURNS:
 * 0 on success, -errno on failure.
 */
int __init numa_cleanup_meminfo(struct numa_meminfo *mi)
{
	const u64 low = 0;
270
	const u64 high = PFN_PHYS(max_pfn);
271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287
	int i, j, k;

	for (i = 0; i < mi->nr_blks; i++) {
		struct numa_memblk *bi = &mi->blk[i];

		/* make sure all blocks are inside the limits */
		bi->start = max(bi->start, low);
		bi->end = min(bi->end, high);

		/* and there's no empty block */
		if (bi->start >= bi->end) {
			numa_remove_memblk_from(i--, mi);
			continue;
		}

		for (j = i + 1; j < mi->nr_blks; j++) {
			struct numa_memblk *bj = &mi->blk[j];
288
			u64 start, end;
289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325

			/*
			 * See whether there are overlapping blocks.  Whine
			 * about but allow overlaps of the same nid.  They
			 * will be merged below.
			 */
			if (bi->end > bj->start && bi->start < bj->end) {
				if (bi->nid != bj->nid) {
					pr_err("NUMA: node %d (%Lx-%Lx) overlaps with node %d (%Lx-%Lx)\n",
					       bi->nid, bi->start, bi->end,
					       bj->nid, bj->start, bj->end);
					return -EINVAL;
				}
				pr_warning("NUMA: Warning: node %d (%Lx-%Lx) overlaps with itself (%Lx-%Lx)\n",
					   bi->nid, bi->start, bi->end,
					   bj->start, bj->end);
			}

			/*
			 * Join together blocks on the same node, holes
			 * between which don't overlap with memory on other
			 * nodes.
			 */
			if (bi->nid != bj->nid)
				continue;
			start = max(min(bi->start, bj->start), low);
			end = min(max(bi->end, bj->end), high);
			for (k = 0; k < mi->nr_blks; k++) {
				struct numa_memblk *bk = &mi->blk[k];

				if (bi->nid == bk->nid)
					continue;
				if (start < bk->end && end > bk->start)
					break;
			}
			if (k < mi->nr_blks)
				continue;
326
			printk(KERN_INFO "NUMA: Node %d [%Lx,%Lx) + [%Lx,%Lx) -> [%Lx,%Lx)\n",
327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390
			       bi->nid, bi->start, bi->end, bj->start, bj->end,
			       start, end);
			bi->start = start;
			bi->end = end;
			numa_remove_memblk_from(j--, mi);
		}
	}

	for (i = mi->nr_blks; i < ARRAY_SIZE(mi->blk); i++) {
		mi->blk[i].start = mi->blk[i].end = 0;
		mi->blk[i].nid = NUMA_NO_NODE;
	}

	return 0;
}

/*
 * Set nodes, which have memory in @mi, in *@nodemask.
 */
static void __init numa_nodemask_from_meminfo(nodemask_t *nodemask,
					      const struct numa_meminfo *mi)
{
	int i;

	for (i = 0; i < ARRAY_SIZE(mi->blk); i++)
		if (mi->blk[i].start != mi->blk[i].end &&
		    mi->blk[i].nid != NUMA_NO_NODE)
			node_set(mi->blk[i].nid, *nodemask);
}

/**
 * numa_reset_distance - Reset NUMA distance table
 *
 * The current table is freed.  The next numa_set_distance() call will
 * create a new one.
 */
void __init numa_reset_distance(void)
{
	size_t size = numa_distance_cnt * numa_distance_cnt * sizeof(numa_distance[0]);

	/* numa_distance could be 1LU marking allocation failure, test cnt */
	if (numa_distance_cnt)
		memblock_x86_free_range(__pa(numa_distance),
					__pa(numa_distance) + size);
	numa_distance_cnt = 0;
	numa_distance = NULL;	/* enable table creation */
}

static int __init numa_alloc_distance(void)
{
	nodemask_t nodes_parsed;
	size_t size;
	int i, j, cnt = 0;
	u64 phys;

	/* size the new table and allocate it */
	nodes_parsed = numa_nodes_parsed;
	numa_nodemask_from_meminfo(&nodes_parsed, &numa_meminfo);

	for_each_node_mask(i, nodes_parsed)
		cnt = i;
	cnt++;
	size = cnt * cnt * sizeof(numa_distance[0]);

391
	phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466
				      size, PAGE_SIZE);
	if (phys == MEMBLOCK_ERROR) {
		pr_warning("NUMA: Warning: can't allocate distance table!\n");
		/* don't retry until explicitly reset */
		numa_distance = (void *)1LU;
		return -ENOMEM;
	}
	memblock_x86_reserve_range(phys, phys + size, "NUMA DIST");

	numa_distance = __va(phys);
	numa_distance_cnt = cnt;

	/* fill with the default distances */
	for (i = 0; i < cnt; i++)
		for (j = 0; j < cnt; j++)
			numa_distance[i * cnt + j] = i == j ?
				LOCAL_DISTANCE : REMOTE_DISTANCE;
	printk(KERN_DEBUG "NUMA: Initialized distance table, cnt=%d\n", cnt);

	return 0;
}

/**
 * numa_set_distance - Set NUMA distance from one NUMA to another
 * @from: the 'from' node to set distance
 * @to: the 'to'  node to set distance
 * @distance: NUMA distance
 *
 * Set the distance from node @from to @to to @distance.  If distance table
 * doesn't exist, one which is large enough to accommodate all the currently
 * known nodes will be created.
 *
 * If such table cannot be allocated, a warning is printed and further
 * calls are ignored until the distance table is reset with
 * numa_reset_distance().
 *
 * If @from or @to is higher than the highest known node at the time of
 * table creation or @distance doesn't make sense, the call is ignored.
 * This is to allow simplification of specific NUMA config implementations.
 */
void __init numa_set_distance(int from, int to, int distance)
{
	if (!numa_distance && numa_alloc_distance() < 0)
		return;

	if (from >= numa_distance_cnt || to >= numa_distance_cnt) {
		printk_once(KERN_DEBUG "NUMA: Debug: distance out of bound, from=%d to=%d distance=%d\n",
			    from, to, distance);
		return;
	}

	if ((u8)distance != distance ||
	    (from == to && distance != LOCAL_DISTANCE)) {
		pr_warn_once("NUMA: Warning: invalid distance parameter, from=%d to=%d distance=%d\n",
			     from, to, distance);
		return;
	}

	numa_distance[from * numa_distance_cnt + to] = distance;
}

int __node_distance(int from, int to)
{
	if (from >= numa_distance_cnt || to >= numa_distance_cnt)
		return from == to ? LOCAL_DISTANCE : REMOTE_DISTANCE;
	return numa_distance[from * numa_distance_cnt + to];
}
EXPORT_SYMBOL(__node_distance);

/*
 * Sanity check to catch more bad NUMA configurations (they are amazingly
 * common).  Make sure the nodes cover all memory.
 */
static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi)
{
467
	u64 numaram, e820ram;
468 469 470 471
	int i;

	numaram = 0;
	for (i = 0; i < mi->nr_blks; i++) {
472 473
		u64 s = mi->blk[i].start >> PAGE_SHIFT;
		u64 e = mi->blk[i].end >> PAGE_SHIFT;
474 475
		numaram += e - s;
		numaram -= __absent_pages_in_range(mi->blk[i].nid, s, e);
476
		if ((s64)numaram < 0)
477 478 479 480
			numaram = 0;
	}

	e820ram = max_pfn - (memblock_x86_hole_size(0,
481
					PFN_PHYS(max_pfn)) >> PAGE_SHIFT);
482
	/* We seem to lose 3 pages somewhere. Allow 1M of slack. */
483 484
	if ((s64)(e820ram - numaram) >= (1 << (20 - PAGE_SHIFT))) {
		printk(KERN_ERR "NUMA: nodes only cover %LuMB of your %LuMB e820 RAM. Not used.\n",
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
		       (numaram << PAGE_SHIFT) >> 20,
		       (e820ram << PAGE_SHIFT) >> 20);
		return false;
	}
	return true;
}

static int __init numa_register_memblks(struct numa_meminfo *mi)
{
	int i, nid;

	/* Account for nodes with cpus and no memory */
	node_possible_map = numa_nodes_parsed;
	numa_nodemask_from_meminfo(&node_possible_map, mi);
	if (WARN_ON(nodes_empty(node_possible_map)))
		return -EINVAL;

	for (i = 0; i < mi->nr_blks; i++)
		memblock_x86_register_active_regions(mi->blk[i].nid,
					mi->blk[i].start >> PAGE_SHIFT,
					mi->blk[i].end >> PAGE_SHIFT);

	/* for out of order entries */
	sort_node_map();
	if (!numa_meminfo_cover_memory(mi))
		return -EINVAL;

	/* Finally register nodes. */
	for_each_node_mask(nid, node_possible_map) {
514
		u64 start = PFN_PHYS(max_pfn);
515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530
		u64 end = 0;

		for (i = 0; i < mi->nr_blks; i++) {
			if (nid != mi->blk[i].nid)
				continue;
			start = min(mi->blk[i].start, start);
			end = max(mi->blk[i].end, end);
		}

		if (start < end)
			setup_node_bootmem(nid, start, end);
	}

	return 0;
}

531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552
/*
 * There are unfortunately some poorly designed mainboards around that
 * only connect memory to a single CPU. This breaks the 1:1 cpu->node
 * mapping. To avoid this fill in the mapping for all possible CPUs,
 * as the number of CPUs is not known yet. We round robin the existing
 * nodes.
 */
void __init numa_init_array(void)
{
	int rr, i;

	rr = first_node(node_online_map);
	for (i = 0; i < nr_cpu_ids; i++) {
		if (early_cpu_to_node(i) != NUMA_NO_NODE)
			continue;
		numa_set_node(i, rr);
		rr = next_node(rr, node_online_map);
		if (rr == MAX_NUMNODES)
			rr = first_node(node_online_map);
	}
}

553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605
static int __init numa_init(int (*init_func)(void))
{
	int i;
	int ret;

	for (i = 0; i < MAX_LOCAL_APIC; i++)
		set_apicid_to_node(i, NUMA_NO_NODE);

	nodes_clear(numa_nodes_parsed);
	nodes_clear(node_possible_map);
	nodes_clear(node_online_map);
	memset(&numa_meminfo, 0, sizeof(numa_meminfo));
	remove_all_active_ranges();
	numa_reset_distance();

	ret = init_func();
	if (ret < 0)
		return ret;
	ret = numa_cleanup_meminfo(&numa_meminfo);
	if (ret < 0)
		return ret;

	numa_emulation(&numa_meminfo, numa_distance_cnt);

	ret = numa_register_memblks(&numa_meminfo);
	if (ret < 0)
		return ret;

	for (i = 0; i < nr_cpu_ids; i++) {
		int nid = early_cpu_to_node(i);

		if (nid == NUMA_NO_NODE)
			continue;
		if (!node_online(nid))
			numa_clear_node(i);
	}
	numa_init_array();
	return 0;
}

/**
 * dummy_numa_init - Fallback dummy NUMA init
 *
 * Used if there's no underlying NUMA architecture, NUMA initialization
 * fails, or NUMA is disabled on the command line.
 *
 * Must online at least one node and add memory blocks that cover all
 * allowed memory.  This function must not fail.
 */
static int __init dummy_numa_init(void)
{
	printk(KERN_INFO "%s\n",
	       numa_off ? "NUMA turned off" : "No NUMA configuration found");
606 607
	printk(KERN_INFO "Faking a node at %016Lx-%016Lx\n",
	       0LLU, PFN_PHYS(max_pfn));
608 609

	node_set(0, numa_nodes_parsed);
610
	numa_add_memblk(0, 0, PFN_PHYS(max_pfn));
611 612 613 614 615 616 617 618 619 620 621 622 623 624

	return 0;
}

/**
 * x86_numa_init - Initialize NUMA
 *
 * Try each configured NUMA initialization method until one succeeds.  The
 * last fallback is dummy single node config encomapssing whole memory and
 * never fails.
 */
void __init x86_numa_init(void)
{
	if (!numa_off) {
625 626 627 628
#ifdef CONFIG_X86_NUMAQ
		if (!numa_init(numaq_numa_init))
			return;
#endif
629 630 631 632 633 634 635 636 637 638 639 640 641
#ifdef CONFIG_ACPI_NUMA
		if (!numa_init(x86_acpi_numa_init))
			return;
#endif
#ifdef CONFIG_AMD_NUMA
		if (!numa_init(amd_numa_init))
			return;
#endif
	}

	numa_init(dummy_numa_init);
}

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
static __init int find_near_online_node(int node)
{
	int n, val;
	int min_val = INT_MAX;
	int best_node = -1;

	for_each_online_node(n) {
		val = node_distance(node, n);

		if (val < min_val) {
			min_val = val;
			best_node = n;
		}
	}

	return best_node;
}

/*
 * Setup early cpu_to_node.
 *
 * Populate cpu_to_node[] only if x86_cpu_to_apicid[],
 * and apicid_to_node[] tables have valid entries for a CPU.
 * This means we skip cpu_to_node[] initialisation for NUMA
 * emulation and faking node case (when running a kernel compiled
 * for NUMA on a non NUMA box), which is OK as cpu_to_node[]
 * is already initialized in a round robin manner at numa_init_array,
 * prior to this call, and this initialization is good enough
 * for the fake NUMA cases.
 *
 * Called before the per_cpu areas are setup.
 */
void __init init_cpu_to_node(void)
{
	int cpu;
	u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid);

	BUG_ON(cpu_to_apicid == NULL);

	for_each_possible_cpu(cpu) {
		int node = numa_cpu_node(cpu);

		if (node == NUMA_NO_NODE)
			continue;
		if (!node_online(node))
			node = find_near_online_node(node);
		numa_set_node(cpu, node);
	}
}

692 693 694 695 696 697 698 699 700 701 702 703 704 705 706
#ifndef CONFIG_DEBUG_PER_CPU_MAPS

# ifndef CONFIG_NUMA_EMU
void __cpuinit numa_add_cpu(int cpu)
{
	cpumask_set_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
}

void __cpuinit numa_remove_cpu(int cpu)
{
	cpumask_clear_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
}
# endif	/* !CONFIG_NUMA_EMU */

#else	/* !CONFIG_DEBUG_PER_CPU_MAPS */
707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737

int __cpu_to_node(int cpu)
{
	if (early_per_cpu_ptr(x86_cpu_to_node_map)) {
		printk(KERN_WARNING
			"cpu_to_node(%d): usage too early!\n", cpu);
		dump_stack();
		return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
	}
	return per_cpu(x86_cpu_to_node_map, cpu);
}
EXPORT_SYMBOL(__cpu_to_node);

/*
 * Same function as cpu_to_node() but used if called before the
 * per_cpu areas are setup.
 */
int early_cpu_to_node(int cpu)
{
	if (early_per_cpu_ptr(x86_cpu_to_node_map))
		return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];

	if (!cpu_possible(cpu)) {
		printk(KERN_WARNING
			"early_cpu_to_node(%d): no per_cpu area!\n", cpu);
		dump_stack();
		return NUMA_NO_NODE;
	}
	return per_cpu(x86_cpu_to_node_map, cpu);
}

738
void debug_cpumask_set_cpu(int cpu, int node, bool enable)
739 740 741 742
{
	struct cpumask *mask;
	char buf[64];

743 744
	if (node == NUMA_NO_NODE) {
		/* early_cpu_to_node() already emits a warning and trace */
745
		return;
746
	}
747 748 749 750
	mask = node_to_cpumask_map[node];
	if (!mask) {
		pr_err("node_to_cpumask_map[%i] NULL\n", node);
		dump_stack();
751
		return;
752 753
	}

754 755 756 757 758
	if (enable)
		cpumask_set_cpu(cpu, mask);
	else
		cpumask_clear_cpu(cpu, mask);

759 760 761 762
	cpulist_scnprintf(buf, sizeof(buf), mask);
	printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n",
		enable ? "numa_add_cpu" : "numa_remove_cpu",
		cpu, node, buf);
763
	return;
764 765 766
}

# ifndef CONFIG_NUMA_EMU
767
static void __cpuinit numa_set_cpumask(int cpu, bool enable)
768
{
769
	debug_cpumask_set_cpu(cpu, early_cpu_to_node(cpu), enable);
770 771 772 773
}

void __cpuinit numa_add_cpu(int cpu)
{
774
	numa_set_cpumask(cpu, true);
775 776 777 778
}

void __cpuinit numa_remove_cpu(int cpu)
{
779
	numa_set_cpumask(cpu, false);
780 781 782
}
# endif	/* !CONFIG_NUMA_EMU */

783 784 785
/*
 * Returns a pointer to the bitmask of CPUs on Node 'node'.
 */
786
const struct cpumask *cpumask_of_node(int node)
787 788 789 790 791 792 793 794
{
	if (node >= nr_node_ids) {
		printk(KERN_WARNING
			"cpumask_of_node(%d): node > nr_node_ids(%d)\n",
			node, nr_node_ids);
		dump_stack();
		return cpu_none_mask;
	}
795 796 797 798 799 800 801
	if (node_to_cpumask_map[node] == NULL) {
		printk(KERN_WARNING
			"cpumask_of_node(%d): no node_to_cpumask_map!\n",
			node);
		dump_stack();
		return cpu_online_mask;
	}
802
	return node_to_cpumask_map[node];
803 804
}
EXPORT_SYMBOL(cpumask_of_node);
805

806
#endif	/* !CONFIG_DEBUG_PER_CPU_MAPS */
807

808
#ifdef CONFIG_MEMORY_HOTPLUG
809 810 811 812 813 814 815 816 817 818 819 820 821
int memory_add_physaddr_to_nid(u64 start)
{
	struct numa_meminfo *mi = &numa_meminfo;
	int nid = mi->blk[0].nid;
	int i;

	for (i = 0; i < mi->nr_blks; i++)
		if (mi->blk[i].start <= start && mi->blk[i].end > start)
			nid = mi->blk[i].nid;
	return nid;
}
EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
#endif