aboutsummaryrefslogtreecommitdiffstats
path: root/arch/powerpc/mm/numa.c
blob: 092355f373996798075e5aa2f49074fa689e676a (plain) (blame)
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
543
544
545
546
547
548
549
550
551
552
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
606
607
608
609
610
611
612
613
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
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
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
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
/*
 * pSeries NUMA support
 *
 * Copyright (C) 2002 Anton Blanchard <anton@au.ibm.com>, IBM
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; either version
 * 2 of the License, or (at your option) any later version.
 */
#include <linux/threads.h>
#include <linux/bootmem.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/mmzone.h>
#include <linux/module.h>
#include <linux/nodemask.h>
#include <linux/cpu.h>
#include <linux/notifier.h>
#include <asm/sparsemem.h>
#include <asm/lmb.h>
#include <asm/system.h>
#include <asm/smp.h>

static int numa_enabled = 1;

static int numa_debug;
#define dbg(args...) if (numa_debug) { printk(KERN_INFO args); }

int numa_cpu_lookup_table[NR_CPUS];
cpumask_t numa_cpumask_lookup_table[MAX_NUMNODES];
struct pglist_data *node_data[MAX_NUMNODES];

EXPORT_SYMBOL(numa_cpu_lookup_table);
EXPORT_SYMBOL(numa_cpumask_lookup_table);
EXPORT_SYMBOL(node_data);

static bootmem_data_t __initdata plat_node_bdata[MAX_NUMNODES];
static int min_common_depth;
static int n_mem_addr_cells, n_mem_size_cells;

/*
 * We need somewhere to store start/end/node for each region until we have
 * allocated the real node_data structures.
 */
#define MAX_REGIONS	(MAX_LMB_REGIONS*2)
static struct {
	unsigned long start_pfn;
	unsigned long end_pfn;
	int nid;
} init_node_data[MAX_REGIONS] __initdata;

int __init early_pfn_to_nid(unsigned long pfn)
{
	unsigned int i;

	for (i = 0; init_node_data[i].end_pfn; i++) {
		unsigned long start_pfn = init_node_data[i].start_pfn;
		unsigned long end_pfn = init_node_data[i].end_pfn;

		if ((start_pfn <= pfn) && (pfn < end_pfn))
			return init_node_data[i].nid;
	}

	return -1;
}

void __init add_region(unsigned int nid, unsigned long start_pfn,
		       unsigned long pages)
{
	unsigned int i;

	dbg("add_region nid %d start_pfn 0x%lx pages 0x%lx\n",
		nid, start_pfn, pages);

	for (i = 0; init_node_data[i].end_pfn; i++) {
		if (init_node_data[i].nid != nid)
			continue;
		if (init_node_data[i].end_pfn == start_pfn) {
			init_node_data[i].end_pfn += pages;
			return;
		}
		if (init_node_data[i].start_pfn == (start_pfn + pages)) {
			init_node_data[i].start_pfn -= pages;
			return;
		}
	}

	/*
	 * Leave last entry NULL so we dont iterate off the end (we use
	 * entry.end_pfn to terminate the walk).
	 */
	if (i >= (MAX_REGIONS - 1)) {
		printk(KERN_ERR "WARNING: too many memory regions in "
				"numa code, truncating\n");
		return;
	}

	init_node_data[i].start_pfn = start_pfn;
	init_node_data[i].end_pfn = start_pfn + pages;
	init_node_data[i].nid = nid;
}

/* We assume init_node_data has no overlapping regions */
void __init get_region(unsigned int nid, unsigned long *start_pfn,
		       unsigned long *end_pfn, unsigned long *pages_present)
{
	unsigned int i;

	*start_pfn = -1UL;
	*end_pfn = *pages_present = 0;

	for (i = 0; init_node_data[i].end_pfn; i++) {
		if (init_node_data[i].nid != nid)
			continue;

		*pages_present += init_node_data[i].end_pfn -
			init_node_data[i].start_pfn;

		if (init_node_data[i].start_pfn < *start_pfn)
			*start_pfn = init_node_data[i].start_pfn;

		if (init_node_data[i].end_pfn > *end_pfn)
			*end_pfn = init_node_data[i].end_pfn;
	}

	/* We didnt find a matching region, return start/end as 0 */
	if (*start_pfn == -1UL)
		*start_pfn = 0;
}

static void __cpuinit map_cpu_to_node(int cpu, int node)
{
	numa_cpu_lookup_table[cpu] = node;

	dbg("adding cpu %d to node %d\n", cpu, node);

	if (!(cpu_isset(cpu, numa_cpumask_lookup_table[node])))
		cpu_set(cpu, numa_cpumask_lookup_table[node]);
}

#ifdef CONFIG_HOTPLUG_CPU
static void unmap_cpu_from_node(unsigned long cpu)
{
	int node = numa_cpu_lookup_table[cpu];

	dbg("removing cpu %lu from node %d\n", cpu, node);

	if (cpu_isset(cpu, numa_cpumask_lookup_table[node])) {
		cpu_clear(cpu, numa_cpumask_lookup_table[node]);
	} else {
		printk(KERN_ERR "WARNING: cpu %lu not found in node %d\n",
		       cpu, node);
	}
}
#endif /* CONFIG_HOTPLUG_CPU */

static struct device_node * __cpuinit find_cpu_node(unsigned int cpu)
{
	unsigned int hw_cpuid = get_hard_smp_processor_id(cpu);
	struct device_node *cpu_node = NULL;
	unsigned int *interrupt_server, *reg;
	int len;

	while ((cpu_node = of_find_node_by_type(cpu_node, "cpu")) != NULL) {
		/* Try interrupt server first */
		interrupt_server = (unsigned int *)get_property(cpu_node,
					"ibm,ppc-interrupt-server#s", &len);

		len = len / sizeof(u32);

		if (interrupt_server && (len > 0)) {
			while (len--) {
				if (interrupt_server[len] == hw_cpuid)
					return cpu_node;
			}
		} else {
			reg = (unsigned int *)get_property(cpu_node,
							   "reg", &len);
			if (reg && (len > 0) && (reg[0] == hw_cpuid))
				return cpu_node;
		}
	}

	return NULL;
}

/* must hold reference to node during call */
static int *of_get_associativity(struct device_node *dev)
{
	return (unsigned int *)get_property(dev, "ibm,associativity", NULL);
}

/* Returns nid in the range [0..MAX_NUMNODES-1], or -1 if no useful numa
 * info is found.
 */
static int of_node_to_nid_single(struct device_node *device)
{
	int nid = -1;
	unsigned int *tmp;

	if (min_common_depth == -1)
		goto out;

	tmp = of_get_associativity(device);
	if (!tmp)
		goto out;

	if (tmp[0] >= min_common_depth)
		nid = tmp[min_common_depth];

	/* POWER4 LPAR uses 0xffff as invalid node */
	if (nid == 0xffff || nid >= MAX_NUMNODES)
		nid = -1;
out:
	return nid;
}

/* Walk the device tree upwards, looking for an associativity id */
int of_node_to_nid(struct device_node *device)
{
	struct device_node *tmp;
	int nid = -1;

	of_node_get(device);
	while (device) {
		nid = of_node_to_nid_single(device);
		if (nid != -1)
			break;

	        tmp = device;
		device = of_get_parent(tmp);
		of_node_put(tmp);
	}
	of_node_put(device);

	return nid;
}
EXPORT_SYMBOL_GPL(of_node_to_nid);

/*
 * In theory, the "ibm,associativity" property may contain multiple
 * associativity lists because a resource may be multiply connected
 * into the machine.  This resource then has different associativity
 * characteristics relative to its multiple connections.  We ignore
 * this for now.  We also assume that all cpu and memory sets have
 * their distances represented at a common level.  This won't be
 * true for heirarchical NUMA.
 *
 * In any case the ibm,associativity-reference-points should give
 * the correct depth for a normal NUMA system.
 *
 * - Dave Hansen <haveblue@us.ibm.com>
 */
static int __init find_min_common_depth(void)
{
	int depth;
	unsigned int *ref_points;
	struct device_node *rtas_root;
	unsigned int len;

	rtas_root = of_find_node_by_path("/rtas");

	if (!rtas_root)
		return -1;

	/*
	 * this property is 2 32-bit integers, each representing a level of
	 * depth in the associativity nodes.  The first is for an SMP
	 * configuration (should be all 0's) and the second is for a normal
	 * NUMA configuration.
	 */
	ref_points = (unsigned int *)get_property(rtas_root,
			"ibm,associativity-reference-points", &len);

	if ((len >= 1) && ref_points) {
		depth = ref_points[1];
	} else {
		dbg("NUMA: ibm,associativity-reference-points not found.\n");
		depth = -1;
	}
	of_node_put(rtas_root);

	return depth;
}

static void __init get_n_mem_cells(int *n_addr_cells, int *n_size_cells)
{
	struct device_node *memory = NULL;

	memory = of_find_node_by_type(memory, "memory");
	if (!memory)
		panic("numa.c: No memory nodes found!");

	*n_addr_cells = prom_n_addr_cells(memory);
	*n_size_cells = prom_n_size_cells(memory);
	of_node_put(memory);
}

static unsigned long __devinit read_n_cells(int n, unsigned int **buf)
{
	unsigned long result = 0;

	while (n--) {
		result = (result << 32) | **buf;
		(*buf)++;
	}
	return result;
}

/*
 * Figure out to which domain a cpu belongs and stick it there.
 * Return the id of the domain used.
 */
static int __cpuinit numa_setup_cpu(unsigned long lcpu)
{
	int nid = 0;
	struct device_node *cpu = find_cpu_node(lcpu);

	if (!cpu) {
		WARN_ON(1);
		goto out;
	}

	nid = of_node_to_nid_single(cpu);

	if (nid < 0 || !node_online(nid))
		nid = any_online_node(NODE_MASK_ALL);
out:
	map_cpu_to_node(lcpu, nid);

	of_node_put(cpu);

	return nid;
}

static int cpu_numa_callback(struct notifier_block *nfb,
			     unsigned long action,
			     void *hcpu)
{
	unsigned long lcpu = (unsigned long)hcpu;
	int ret = NOTIFY_DONE;

	switch (action) {
	case CPU_UP_PREPARE:
		numa_setup_cpu(lcpu);
		ret = NOTIFY_OK;
		break;
#ifdef CONFIG_HOTPLUG_CPU
	case CPU_DEAD:
	case CPU_UP_CANCELED:
		unmap_cpu_from_node(lcpu);
		break;
		ret = NOTIFY_OK;
#endif
	}
	return ret;
}

/*
 * Check and possibly modify a memory region to enforce the memory limit.
 *
 * Returns the size the region should have to enforce the memory limit.
 * This will either be the original value of size, a truncated value,
 * or zero. If the returned value of size is 0 the region should be
 * discarded as it lies wholy above the memory limit.
 */
static unsigned long __init numa_enforce_memory_limit(unsigned long start,
						      unsigned long size)
{
	/*
	 * We use lmb_end_of_DRAM() in here instead of memory_limit because
	 * we've already adjusted it for the limit and it takes care of
	 * having memory holes below the limit.
	 */

	if (! memory_limit)
		return size;

	if (start + size <= lmb_end_of_DRAM())
		return size;

	if (start >= lmb_end_of_DRAM())
		return 0;

	return lmb_end_of_DRAM() - start;
}

static int __init parse_numa_properties(void)
{
	struct device_node *cpu = NULL;
	struct device_node *memory = NULL;
	int default_nid = 0;
	unsigned long i;

	if (numa_enabled == 0) {
		printk(KERN_WARNING "NUMA disabled by user\n");
		return -1;
	}

	min_common_depth = find_min_common_depth();

	if (min_common_depth < 0)
		return min_common_depth;

	dbg("NUMA associativity depth for CPU/Memory: %d\n", min_common_depth);

	/*
	 * Even though we connect cpus to numa domains later in SMP
	 * init, we need to know the node ids now. This is because
	 * each node to be onlined must have NODE_DATA etc backing it.
	 */
	for_each_present_cpu(i) {
		int nid;

		cpu = find_cpu_node(i);
		BUG_ON(!cpu);
		nid = of_node_to_nid_single(cpu);
		of_node_put(cpu);

		/*
		 * Don't fall back to default_nid yet -- we will plug
		 * cpus into nodes once the memory scan has discovered
		 * the topology.
		 */
		if (nid < 0)
			continue;
		node_set_online(nid);
	}

	get_n_mem_cells(&n_mem_addr_cells, &n_mem_size_cells);
	memory = NULL;
	while ((memory = of_find_node_by_type(memory, "memory")) != NULL) {
		unsigned long start;
		unsigned long size;
		int nid;
		int ranges;
		unsigned int *memcell_buf;
		unsigned int len;

		memcell_buf = (unsigned int *)get_property(memory,
			"linux,usable-memory", &len);
		if (!memcell_buf || len <= 0)
			memcell_buf =
				(unsigned int *)get_property(memory, "reg",
					&len);
		if (!memcell_buf || len <= 0)
			continue;

		/* ranges in cell */
		ranges = (len >> 2) / (n_mem_addr_cells + n_mem_size_cells);
new_range:
		/* these are order-sensitive, and modify the buffer pointer */
		start = read_n_cells(n_mem_addr_cells, &memcell_buf);
		size = read_n_cells(n_mem_size_cells, &memcell_buf);

		/*
		 * Assumption: either all memory nodes or none will
		 * have associativity properties.  If none, then
		 * everything goes to default_nid.
		 */
		nid = of_node_to_nid_single(memory);
		if (nid < 0)
			nid = default_nid;
		node_set_online(nid);

		if (!(size = numa_enforce_memory_limit(start, size))) {
			if (--ranges)
				goto new_range;
			else
				continue;
		}

		add_region(nid, start >> PAGE_SHIFT,
			   size >> PAGE_SHIFT);

		if (--ranges)
			goto new_range;
	}

	return 0;
}

static void __init setup_nonnuma(void)
{
	unsigned long top_of_ram = lmb_end_of_DRAM();
	unsigned long total_ram = lmb_phys_mem_size();
	unsigned int i;

	printk(KERN_INFO "Top of RAM: 0x%lx, Total RAM: 0x%lx\n",
	       top_of_ram, total_ram);
	printk(KERN_INFO "Memory hole size: %ldMB\n",
	       (top_of_ram - total_ram) >> 20);

	for (i = 0; i < lmb.memory.cnt; ++i)
		add_region(0, lmb.memory.region[i].base >> PAGE_SHIFT,
			   lmb_size_pages(&lmb.memory, i));
	node_set_online(0);
}

void __init dump_numa_cpu_topology(void)
{
	unsigned int node;
	unsigned int cpu, count;

	if (min_common_depth == -1 || !numa_enabled)
		return;

	for_each_online_node(node) {
		printk(KERN_INFO "Node %d CPUs:", node);

		count = 0;
		/*
		 * If we used a CPU iterator here we would miss printing
		 * the holes in the cpumap.
		 */
		for (cpu = 0; cpu < NR_CPUS; cpu++) {
			if (cpu_isset(cpu, numa_cpumask_lookup_table[node])) {
				if (count == 0)
					printk(" %u", cpu);
				++count;
			} else {
				if (count > 1)
					printk("-%u", cpu - 1);
				count = 0;
			}
		}

		if (count > 1)
			printk("-%u", NR_CPUS - 1);
		printk("\n");
	}
}

static void __init dump_numa_memory_topology(void)
{
	unsigned int node;
	unsigned int count;

	if (min_common_depth == -1 || !numa_enabled)
		return;

	for_each_online_node(node) {
		unsigned long i;

		printk(KERN_INFO "Node %d Memory:", node);

		count = 0;

		for (i = 0; i < lmb_end_of_DRAM();
		     i += (1 << SECTION_SIZE_BITS)) {
			if (early_pfn_to_nid(i >> PAGE_SHIFT) == node) {
				if (count == 0)
					printk(" 0x%lx", i);
				++count;
			} else {
				if (count > 0)
					printk("-0x%lx", i);
				count = 0;
			}
		}

		if (count > 0)
			printk("-0x%lx", i);
		printk("\n");
	}
}

/*
 * Allocate some memory, satisfying the lmb or bootmem allocator where
 * required. nid is the preferred node and end is the physical address of
 * the highest address in the node.
 *
 * Returns the physical address of the memory.
 */
static void __init *careful_allocation(int nid, unsigned long size,
				       unsigned long align,
				       unsigned long end_pfn)
{
	int new_nid;
	unsigned long ret = __lmb_alloc_base(size, align, end_pfn << PAGE_SHIFT);

	/* retry over all memory */
	if (!ret)
		ret = __lmb_alloc_base(size, align, lmb_end_of_DRAM());

	if (!ret)
		panic("numa.c: cannot allocate %lu bytes on node %d",
		      size, nid);

	/*
	 * If the memory came from a previously allocated node, we must
	 * retry with the bootmem allocator.
	 */
	new_nid = early_pfn_to_nid(ret >> PAGE_SHIFT);
	if (new_nid < nid) {
		ret = (unsigned long)__alloc_bootmem_node(NODE_DATA(new_nid),
				size, align, 0);

		if (!ret)
			panic("numa.c: cannot allocate %lu bytes on node %d",
			      size, new_nid);

		ret = __pa(ret);

		dbg("alloc_bootmem %lx %lx\n", ret, size);
	}

	return (void *)ret;
}

void __init do_init_bootmem(void)
{
	int nid;
	unsigned int i;
	static struct notifier_block ppc64_numa_nb = {
		.notifier_call = cpu_numa_callback,
		.priority = 1 /* Must run before sched domains notifier. */
	};

	min_low_pfn = 0;
	max_low_pfn = lmb_end_of_DRAM() >> PAGE_SHIFT;
	max_pfn = max_low_pfn;

	if (parse_numa_properties())
		setup_nonnuma();
	else
		dump_numa_memory_topology();

	register_cpu_notifier(&ppc64_numa_nb);
	cpu_numa_callback(&ppc64_numa_nb, CPU_UP_PREPARE,
			  (void *)(unsigned long)boot_cpuid);

	for_each_online_node(nid) {
		unsigned long start_pfn, end_pfn, pages_present;
		unsigned long bootmem_paddr;
		unsigned long bootmap_pages;

		get_region(nid, &start_pfn, &end_pfn, &pages_present);

		/* Allocate the node structure node local if possible */
		NODE_DATA(nid) = careful_allocation(nid,
					sizeof(struct pglist_data),
					SMP_CACHE_BYTES, end_pfn);
		NODE_DATA(nid) = __va(NODE_DATA(nid));
		memset(NODE_DATA(nid), 0, sizeof(struct pglist_data));

  		dbg("node %d\n", nid);
		dbg("NODE_DATA() = %p\n", NODE_DATA(nid));

		NODE_DATA(nid)->bdata = &plat_node_bdata[nid];
		NODE_DATA(nid)->node_start_pfn = start_pfn;
		NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn;

		if (NODE_DATA(nid)->node_spanned_pages == 0)
  			continue;

  		dbg("start_paddr = %lx\n", start_pfn << PAGE_SHIFT);
  		dbg("end_paddr = %lx\n", end_pfn << PAGE_SHIFT);

		bootmap_pages = bootmem_bootmap_pages(end_pfn - start_pfn);
		bootmem_paddr = (unsigned long)careful_allocation(nid,
					bootmap_pages << PAGE_SHIFT,
					PAGE_SIZE, end_pfn);
		memset(__va(bootmem_paddr), 0, bootmap_pages << PAGE_SHIFT);

		dbg("bootmap_paddr = %lx\n", bootmem_paddr);

		init_bootmem_node(NODE_DATA(nid), bootmem_paddr >> PAGE_SHIFT,
				  start_pfn, end_pfn);

		/* Add free regions on this node */
		for (i = 0; init_node_data[i].end_pfn; i++) {
			unsigned long start, end;

			if (init_node_data[i].nid != nid)
				continue;

			start = init_node_data[i].start_pfn << PAGE_SHIFT;
			end = init_node_data[i].end_pfn << PAGE_SHIFT;

			dbg("free_bootmem %lx %lx\n", start, end - start);
  			free_bootmem_node(NODE_DATA(nid), start, end - start);
		}

		/* Mark reserved regions on this node */
		for (i = 0; i < lmb.reserved.cnt; i++) {
			unsigned long physbase = lmb.reserved.region[i].base;
			unsigned long size = lmb.reserved.region[i].size;
			unsigned long start_paddr = start_pfn << PAGE_SHIFT;
			unsigned long end_paddr = end_pfn << PAGE_SHIFT;

			if (early_pfn_to_nid(physbase >> PAGE_SHIFT) != nid &&
			    early_pfn_to_nid((physbase+size-1) >> PAGE_SHIFT) != nid)
				continue;

			if (physbase < end_paddr &&
			    (physbase+size) > start_paddr) {
				/* overlaps */
				if (physbase < start_paddr) {
					size -= start_paddr - physbase;
					physbase = start_paddr;
				}

				if (size > end_paddr - physbase)
					size = end_paddr - physbase;

				dbg("reserve_bootmem %lx %lx\n", physbase,
				    size);
				reserve_bootmem_node(NODE_DATA(nid), physbase,
						     size);
			}
		}

		/* Add regions into sparsemem */
		for (i = 0; init_node_data[i].end_pfn; i++) {
			unsigned long start, end;

			if (init_node_data[i].nid != nid)
				continue;

			start = init_node_data[i].start_pfn;
			end = init_node_data[i].end_pfn;

			memory_present(nid, start, end);
		}
	}
}

void __init paging_init(void)
{
	unsigned long zones_size[MAX_NR_ZONES];
	unsigned long zholes_size[MAX_NR_ZONES];
	int nid;

	memset(zones_size, 0, sizeof(zones_size));
	memset(zholes_size, 0, sizeof(zholes_size));

	for_each_online_node(nid) {
		unsigned long start_pfn, end_pfn, pages_present;

		get_region(nid, &start_pfn, &end_pfn, &pages_present);

		zones_size[ZONE_DMA] = end_pfn - start_pfn;
		zholes_size[ZONE_DMA] = zones_size[ZONE_DMA] - pages_present;

		dbg("free_area_init node %d %lx %lx (hole: %lx)\n", nid,
		    zones_size[ZONE_DMA], start_pfn, zholes_size[ZONE_DMA]);

		free_area_init_node(nid, NODE_DATA(nid), zones_size, start_pfn,
				    zholes_size);
	}
}

static int __init early_numa(char *p)
{
	if (!p)
		return 0;

	if (strstr(p, "off"))
		numa_enabled = 0;

	if (strstr(p, "debug"))
		numa_debug = 1;

	return 0;
}
early_param("numa", early_numa);

#ifdef CONFIG_MEMORY_HOTPLUG
/*
 * Find the node associated with a hot added memory section.  Section
 * corresponds to a SPARSEMEM section, not an LMB.  It is assumed that
 * sections are fully contained within a single LMB.
 */
int hot_add_scn_to_nid(unsigned long scn_addr)
{
	struct device_node *memory = NULL;
	nodemask_t nodes;
	int default_nid = any_online_node(NODE_MASK_ALL);
	int nid;

	if (!numa_enabled || (min_common_depth < 0))
		return default_nid;

	while ((memory = of_find_node_by_type(memory, "memory")) != NULL) {
		unsigned long start, size;
		int ranges;
		unsigned int *memcell_buf;
		unsigned int len;

		memcell_buf = (unsigned int *)get_property(memory, "reg", &len);
		if (!memcell_buf || len <= 0)
			continue;

		/* ranges in cell */
		ranges = (len >> 2) / (n_mem_addr_cells + n_mem_size_cells);
ha_new_range:
		start = read_n_cells(n_mem_addr_cells, &memcell_buf);
		size = read_n_cells(n_mem_size_cells, &memcell_buf);
		nid = of_node_to_nid_single(memory);

		/* Domains not present at boot default to 0 */
		if (nid < 0 || !node_online(nid))
			nid = default_nid;

		if ((scn_addr >= start) && (scn_addr < (start + size))) {
			of_node_put(memory);
			goto got_nid;
		}

		if (--ranges)		/* process all ranges in cell */
			goto ha_new_range;
	}
	BUG();	/* section address should be found above */
	return 0;

	/* Temporary code to ensure that returned node is not empty */
got_nid:
	nodes_setall(nodes);
	while (NODE_DATA(nid)->node_spanned_pages == 0) {
		node_clear(nid, nodes);
		nid = any_online_node(nodes);
	}
	return nid;
}
#endif /* CONFIG_MEMORY_HOTPLUG */