summaryrefslogtreecommitdiff
path: root/arch/x86/mm/numa_64.c
blob: a96767cb068f52e2b8d024f9dd15519ae3c7deaa (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
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
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
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
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
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
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
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
288
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
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
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
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
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
/*
 * Generic VM initialization for x86-64 NUMA setups.
 * Copyright 2002,2003 Andi Kleen, SuSE Labs.
 */
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/bootmem.h>
#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/acpi.h>

#include <asm/e820.h>
#include <asm/proto.h>
#include <asm/dma.h>
#include <asm/acpi.h>
#include <asm/amd_nb.h>

#include "numa_internal.h"

struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
EXPORT_SYMBOL(node_data);

nodemask_t numa_nodes_parsed __initdata;

static struct numa_meminfo numa_meminfo __initdata;
static int numa_distance_cnt;
static u8 *numa_distance;

static void * __init early_node_mem(int nodeid, unsigned long start,
				    unsigned long end, unsigned long size,
				    unsigned long align)
{
	unsigned long mem;

	/*
	 * put it on high as possible
	 * something will go with NODE_DATA
	 */
	if (start < (MAX_DMA_PFN<<PAGE_SHIFT))
		start = MAX_DMA_PFN<<PAGE_SHIFT;
	if (start < (MAX_DMA32_PFN<<PAGE_SHIFT) &&
	    end > (MAX_DMA32_PFN<<PAGE_SHIFT))
		start = MAX_DMA32_PFN<<PAGE_SHIFT;
	mem = memblock_x86_find_in_range_node(nodeid, start, end, size, align);
	if (mem != MEMBLOCK_ERROR)
		return __va(mem);

	/* extend the search scope */
	end = max_pfn_mapped << PAGE_SHIFT;
	start = MAX_DMA_PFN << PAGE_SHIFT;
	mem = memblock_find_in_range(start, end, size, align);
	if (mem != MEMBLOCK_ERROR)
		return __va(mem);

	printk(KERN_ERR "Cannot find %lu bytes in node %d\n",
		       size, nodeid);

	return NULL;
}

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 */
void __init
setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
{
	unsigned long start_pfn, last_pfn, nodedata_phys;
	const int pgdat_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
	int nid;

	if (!end)
		return;

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

	start = roundup(start, ZONE_ALIGN);

	printk(KERN_INFO "Initmem setup node %d %016lx-%016lx\n", nodeid,
	       start, end);

	start_pfn = start >> PAGE_SHIFT;
	last_pfn = end >> PAGE_SHIFT;

	node_data[nodeid] = early_node_mem(nodeid, start, end, pgdat_size,
					   SMP_CACHE_BYTES);
	if (node_data[nodeid] == NULL)
		return;
	nodedata_phys = __pa(node_data[nodeid]);
	memblock_x86_reserve_range(nodedata_phys, nodedata_phys + pgdat_size, "NODE_DATA");
	printk(KERN_INFO "  NODE_DATA [%016lx - %016lx]\n", nodedata_phys,
		nodedata_phys + pgdat_size - 1);
	nid = early_pfn_to_nid(nodedata_phys >> PAGE_SHIFT);
	if (nid != nodeid)
		printk(KERN_INFO "    NODE_DATA(%d) on node %d\n", nodeid, nid);

	memset(NODE_DATA(nodeid), 0, sizeof(pg_data_t));
	NODE_DATA(nodeid)->node_id = nodeid;
	NODE_DATA(nodeid)->node_start_pfn = start_pfn;
	NODE_DATA(nodeid)->node_spanned_pages = last_pfn - start_pfn;

	node_set_online(nodeid);
}

/**
 * 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;
	const u64 high = (u64)max_pfn << PAGE_SHIFT;
	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];
			unsigned long start, end;

			/*
			 * 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;
			printk(KERN_INFO "NUMA: Node %d [%Lx,%Lx) + [%Lx,%Lx) -> [%lx,%lx)\n",
			       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]);

	phys = memblock_find_in_range(0, (u64)max_pfn_mapped << PAGE_SHIFT,
				      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)
{
	unsigned long numaram, e820ram;
	int i;

	numaram = 0;
	for (i = 0; i < mi->nr_blks; i++) {
		unsigned long s = mi->blk[i].start >> PAGE_SHIFT;
		unsigned long e = mi->blk[i].end >> PAGE_SHIFT;
		numaram += e - s;
		numaram -= __absent_pages_in_range(mi->blk[i].nid, s, e);
		if ((long)numaram < 0)
			numaram = 0;
	}

	e820ram = max_pfn - (memblock_x86_hole_size(0,
					max_pfn << PAGE_SHIFT) >> PAGE_SHIFT);
	/* We seem to lose 3 pages somewhere. Allow 1M of slack. */
	if ((long)(e820ram - numaram) >= (1 << (20 - PAGE_SHIFT))) {
		printk(KERN_ERR "NUMA: nodes only cover %luMB of your %luMB e820 RAM. Not used.\n",
		       (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) {
		u64 start = (u64)max_pfn << PAGE_SHIFT;
		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;
}

/**
 * dummy_numma_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");
	printk(KERN_INFO "Faking a node at %016lx-%016lx\n",
	       0LU, max_pfn << PAGE_SHIFT);

	node_set(0, numa_nodes_parsed);
	numa_add_memblk(0, 0, (u64)max_pfn << PAGE_SHIFT);

	return 0;
}

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;
}

void __init initmem_init(void)
{
	if (!numa_off) {
#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);
}

unsigned long __init numa_free_all_bootmem(void)
{
	unsigned long pages = 0;
	int i;

	for_each_online_node(i)
		pages += free_all_bootmem_node(NODE_DATA(i));

	pages += free_all_memory_core_early(MAX_NUMNODES);

	return pages;
}

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;
}