summaryrefslogtreecommitdiff
path: root/arch/powerpc/mm/numa.c
blob: f47364585ecd0bce3df61a5397fa3f9d0ccf7feb (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
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
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
/*
 * 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 <linux/memblock.h>
#include <linux/of.h>
#include <linux/pfn.h>
#include <asm/sparsemem.h>
#include <asm/prom.h>
#include <asm/system.h>
#include <asm/smp.h>

static int numa_enabled = 1;

static char *cmdline __initdata;

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

int numa_cpu_lookup_table[NR_CPUS];
cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
struct pglist_data *node_data[MAX_NUMNODES];

EXPORT_SYMBOL(numa_cpu_lookup_table);
EXPORT_SYMBOL(node_to_cpumask_map);
EXPORT_SYMBOL(node_data);

static int min_common_depth;
static int n_mem_addr_cells, n_mem_size_cells;

/*
 * 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.
 */
static 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 */
	for (node = 0; node < nr_node_ids; node++)
		alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]);

	/* cpumask_of_node() will now work */
	dbg("Node to cpumask map for %d nodes\n", nr_node_ids);
}

static int __cpuinit fake_numa_create_new_node(unsigned long end_pfn,
						unsigned int *nid)
{
	unsigned long long mem;
	char *p = cmdline;
	static unsigned int fake_nid;
	static unsigned long long curr_boundary;

	/*
	 * Modify node id, iff we started creating NUMA nodes
	 * We want to continue from where we left of the last time
	 */
	if (fake_nid)
		*nid = fake_nid;
	/*
	 * In case there are no more arguments to parse, the
	 * node_id should be the same as the last fake node id
	 * (we've handled this above).
	 */
	if (!p)
		return 0;

	mem = memparse(p, &p);
	if (!mem)
		return 0;

	if (mem < curr_boundary)
		return 0;

	curr_boundary = mem;

	if ((end_pfn << PAGE_SHIFT) > mem) {
		/*
		 * Skip commas and spaces
		 */
		while (*p == ',' || *p == ' ' || *p == '\t')
			p++;

		cmdline = p;
		fake_nid++;
		*nid = fake_nid;
		dbg("created new fake_node with id %d\n", fake_nid);
		return 1;
	}
	return 0;
}

/*
 * get_active_region_work_fn - A helper function for get_node_active_region
 *	Returns datax set to the start_pfn and end_pfn if they contain
 *	the initial value of datax->start_pfn between them
 * @start_pfn: start page(inclusive) of region to check
 * @end_pfn: end page(exclusive) of region to check
 * @datax: comes in with ->start_pfn set to value to search for and
 *	goes out with active range if it contains it
 * Returns 1 if search value is in range else 0
 */
static int __init get_active_region_work_fn(unsigned long start_pfn,
					unsigned long end_pfn, void *datax)
{
	struct node_active_region *data;
	data = (struct node_active_region *)datax;

	if (start_pfn <= data->start_pfn && end_pfn > data->start_pfn) {
		data->start_pfn = start_pfn;
		data->end_pfn = end_pfn;
		return 1;
	}
	return 0;

}

/*
 * get_node_active_region - Return active region containing start_pfn
 * Active range returned is empty if none found.
 * @start_pfn: The page to return the region for.
 * @node_ar: Returned set to the active region containing start_pfn
 */
static void __init get_node_active_region(unsigned long start_pfn,
		       struct node_active_region *node_ar)
{
	int nid = early_pfn_to_nid(start_pfn);

	node_ar->nid = nid;
	node_ar->start_pfn = start_pfn;
	node_ar->end_pfn = start_pfn;
	work_with_active_regions(nid, get_active_region_work_fn, node_ar);
}

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 (!(cpumask_test_cpu(cpu, node_to_cpumask_map[node])))
		cpumask_set_cpu(cpu, node_to_cpumask_map[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 (cpumask_test_cpu(cpu, node_to_cpumask_map[node])) {
		cpumask_set_cpu(cpu, node_to_cpumask_map[node]);
	} else {
		printk(KERN_ERR "WARNING: cpu %lu not found in node %d\n",
		       cpu, node);
	}
}
#endif /* CONFIG_HOTPLUG_CPU */

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

/*
 * Returns the property linux,drconf-usable-memory if
 * it exists (the property exists only in kexec/kdump kernels,
 * added by kexec-tools)
 */
static const u32 *of_get_usable_memory(struct device_node *memory)
{
	const u32 *prop;
	u32 len;
	prop = of_get_property(memory, "linux,drconf-usable-memory", &len);
	if (!prop || len < sizeof(unsigned int))
		return 0;
	return prop;
}

/* 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;
	const 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 hierarchical 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, index;
	const unsigned int *ref_points;
	struct device_node *rtas_root;
	unsigned int len;
	struct device_node *chosen;
	const char *vec5;

	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.
	 */
	index = 1;
	ref_points = of_get_property(rtas_root,
			"ibm,associativity-reference-points", &len);

	/*
	 * For form 1 affinity information we want the first field
	 */
#define VEC5_AFFINITY_BYTE	5
#define VEC5_AFFINITY		0x80
	chosen = of_find_node_by_path("/chosen");
	if (chosen) {
		vec5 = of_get_property(chosen, "ibm,architecture-vec-5", NULL);
		if (vec5 && (vec5[VEC5_AFFINITY_BYTE] & VEC5_AFFINITY)) {
			dbg("Using form 1 affinity\n");
			index = 0;
		}
	}

	if ((len >= 2 * sizeof(unsigned int)) && ref_points) {
		depth = ref_points[index];
	} 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 = of_n_addr_cells(memory);
	*n_size_cells = of_n_size_cells(memory);
	of_node_put(memory);
}

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

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

struct of_drconf_cell {
	u64	base_addr;
	u32	drc_index;
	u32	reserved;
	u32	aa_index;
	u32	flags;
};

#define DRCONF_MEM_ASSIGNED	0x00000008
#define DRCONF_MEM_AI_INVALID	0x00000040
#define DRCONF_MEM_RESERVED	0x00000080

/*
 * Read the next memblock list entry from the ibm,dynamic-memory property
 * and return the information in the provided of_drconf_cell structure.
 */
static void read_drconf_cell(struct of_drconf_cell *drmem, const u32 **cellp)
{
	const u32 *cp;

	drmem->base_addr = read_n_cells(n_mem_addr_cells, cellp);

	cp = *cellp;
	drmem->drc_index = cp[0];
	drmem->reserved = cp[1];
	drmem->aa_index = cp[2];
	drmem->flags = cp[3];

	*cellp = cp + 4;
}

/*
 * Retreive and validate the ibm,dynamic-memory property of the device tree.
 *
 * The layout of the ibm,dynamic-memory property is a number N of memblock
 * list entries followed by N memblock list entries.  Each memblock list entry
 * contains information as layed out in the of_drconf_cell struct above.
 */
static int of_get_drconf_memory(struct device_node *memory, const u32 **dm)
{
	const u32 *prop;
	u32 len, entries;

	prop = of_get_property(memory, "ibm,dynamic-memory", &len);
	if (!prop || len < sizeof(unsigned int))
		return 0;

	entries = *prop++;

	/* Now that we know the number of entries, revalidate the size
	 * of the property read in to ensure we have everything
	 */
	if (len < (entries * (n_mem_addr_cells + 4) + 1) * sizeof(unsigned int))
		return 0;

	*dm = prop;
	return entries;
}

/*
 * Retreive and validate the ibm,memblock-size property for drconf memory
 * from the device tree.
 */
static u64 of_get_memblock_size(struct device_node *memory)
{
	const u32 *prop;
	u32 len;

	prop = of_get_property(memory, "ibm,memblock-size", &len);
	if (!prop || len < sizeof(unsigned int))
		return 0;

	return read_n_cells(n_mem_size_cells, &prop);
}

struct assoc_arrays {
	u32	n_arrays;
	u32	array_sz;
	const u32 *arrays;
};

/*
 * Retreive and validate the list of associativity arrays for drconf
 * memory from the ibm,associativity-lookup-arrays property of the
 * device tree..
 *
 * The layout of the ibm,associativity-lookup-arrays property is a number N
 * indicating the number of associativity arrays, followed by a number M
 * indicating the size of each associativity array, followed by a list
 * of N associativity arrays.
 */
static int of_get_assoc_arrays(struct device_node *memory,
			       struct assoc_arrays *aa)
{
	const u32 *prop;
	u32 len;

	prop = of_get_property(memory, "ibm,associativity-lookup-arrays", &len);
	if (!prop || len < 2 * sizeof(unsigned int))
		return -1;

	aa->n_arrays = *prop++;
	aa->array_sz = *prop++;

	/* Now that we know the number of arrrays and size of each array,
	 * revalidate the size of the property read in.
	 */
	if (len < (aa->n_arrays * aa->array_sz + 2) * sizeof(unsigned int))
		return -1;

	aa->arrays = prop;
	return 0;
}

/*
 * This is like of_node_to_nid_single() for memory represented in the
 * ibm,dynamic-reconfiguration-memory node.
 */
static int of_drconf_to_nid_single(struct of_drconf_cell *drmem,
				   struct assoc_arrays *aa)
{
	int default_nid = 0;
	int nid = default_nid;
	int index;

	if (min_common_depth > 0 && min_common_depth <= aa->array_sz &&
	    !(drmem->flags & DRCONF_MEM_AI_INVALID) &&
	    drmem->aa_index < aa->n_arrays) {
		index = drmem->aa_index * aa->array_sz + min_common_depth - 1;
		nid = aa->arrays[index];

		if (nid == 0xffff || nid >= MAX_NUMNODES)
			nid = default_nid;
	}

	return nid;
}

/*
 * 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 = of_get_cpu_node(lcpu, NULL);

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

	nid = of_node_to_nid_single(cpu);

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

	of_node_put(cpu);

	return nid;
}

static int __cpuinit 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:
	case CPU_UP_PREPARE_FROZEN:
		numa_setup_cpu(lcpu);
		ret = NOTIFY_OK;
		break;
#ifdef CONFIG_HOTPLUG_CPU
	case CPU_DEAD:
	case CPU_DEAD_FROZEN:
	case CPU_UP_CANCELED:
	case CPU_UP_CANCELED_FROZEN:
		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 memblock_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.  Also, in the case of
	 * iommu_is_off, memory_limit is not set but is implicitly enforced.
	 */

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

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

	return memblock_end_of_DRAM() - start;
}

/*
 * Reads the counter for a given entry in
 * linux,drconf-usable-memory property
 */
static inline int __init read_usm_ranges(const u32 **usm)
{
	/*
	 * For each memblock in ibm,dynamic-memory a corresponding
	 * entry in linux,drconf-usable-memory property contains
	 * a counter followed by that many (base, size) duple.
	 * read the counter from linux,drconf-usable-memory
	 */
	return read_n_cells(n_mem_size_cells, usm);
}

/*
 * Extract NUMA information from the ibm,dynamic-reconfiguration-memory
 * node.  This assumes n_mem_{addr,size}_cells have been set.
 */
static void __init parse_drconf_memory(struct device_node *memory)
{
	const u32 *dm, *usm;
	unsigned int n, rc, ranges, is_kexec_kdump = 0;
	unsigned long memblock_size, base, size, sz;
	int nid;
	struct assoc_arrays aa;

	n = of_get_drconf_memory(memory, &dm);
	if (!n)
		return;

	memblock_size = of_get_memblock_size(memory);
	if (!memblock_size)
		return;

	rc = of_get_assoc_arrays(memory, &aa);
	if (rc)
		return;

	/* check if this is a kexec/kdump kernel */
	usm = of_get_usable_memory(memory);
	if (usm != NULL)
		is_kexec_kdump = 1;

	for (; n != 0; --n) {
		struct of_drconf_cell drmem;

		read_drconf_cell(&drmem, &dm);

		/* skip this block if the reserved bit is set in flags (0x80)
		   or if the block is not assigned to this partition (0x8) */
		if ((drmem.flags & DRCONF_MEM_RESERVED)
		    || !(drmem.flags & DRCONF_MEM_ASSIGNED))
			continue;

		base = drmem.base_addr;
		size = memblock_size;
		ranges = 1;

		if (is_kexec_kdump) {
			ranges = read_usm_ranges(&usm);
			if (!ranges) /* there are no (base, size) duple */
				continue;
		}
		do {
			if (is_kexec_kdump) {
				base = read_n_cells(n_mem_addr_cells, &usm);
				size = read_n_cells(n_mem_size_cells, &usm);
			}
			nid = of_drconf_to_nid_single(&drmem, &aa);
			fake_numa_create_new_node(
				((base + size) >> PAGE_SHIFT),
					   &nid);
			node_set_online(nid);
			sz = numa_enforce_memory_limit(base, size);
			if (sz)
				add_active_range(nid, base >> PAGE_SHIFT,
						 (base >> PAGE_SHIFT)
						 + (sz >> PAGE_SHIFT));
		} while (--ranges);
	}
}

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 = of_get_cpu_node(i, NULL);
		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;
		const unsigned int *memcell_buf;
		unsigned int len;

		memcell_buf = of_get_property(memory,
			"linux,usable-memory", &len);
		if (!memcell_buf || len <= 0)
			memcell_buf = of_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;

		fake_numa_create_new_node(((start + size) >> PAGE_SHIFT), &nid);
		node_set_online(nid);

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

		add_active_range(nid, start >> PAGE_SHIFT,
				(start >> PAGE_SHIFT) + (size >> PAGE_SHIFT));

		if (--ranges)
			goto new_range;
	}

	/*
	 * Now do the same thing for each MEMBLOCK listed in the ibm,dynamic-memory
	 * property in the ibm,dynamic-reconfiguration-memory node.
	 */
	memory = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
	if (memory)
		parse_drconf_memory(memory);

	return 0;
}

static void __init setup_nonnuma(void)
{
	unsigned long top_of_ram = memblock_end_of_DRAM();
	unsigned long total_ram = memblock_phys_mem_size();
	unsigned long start_pfn, end_pfn;
	unsigned int i, nid = 0;

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

	for (i = 0; i < memblock.memory.cnt; ++i) {
		start_pfn = memblock.memory.region[i].base >> PAGE_SHIFT;
		end_pfn = start_pfn + memblock_size_pages(&memblock.memory, i);

		fake_numa_create_new_node(end_pfn, &nid);
		add_active_range(nid, start_pfn, end_pfn);
		node_set_online(nid);
	}
}

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_DEBUG "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_cpu_ids; cpu++) {
			if (cpumask_test_cpu(cpu,
					node_to_cpumask_map[node])) {
				if (count == 0)
					printk(" %u", cpu);
				++count;
			} else {
				if (count > 1)
					printk("-%u", cpu - 1);
				count = 0;
			}
		}

		if (count > 1)
			printk("-%u", nr_cpu_ids - 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_DEBUG "Node %d Memory:", node);

		count = 0;

		for (i = 0; i < memblock_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 memblock 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 virtual address of the memory.
 */
static void __init *careful_zallocation(int nid, unsigned long size,
				       unsigned long align,
				       unsigned long end_pfn)
{
	void *ret;
	int new_nid;
	unsigned long ret_paddr;

	ret_paddr = __memblock_alloc_base(size, align, end_pfn << PAGE_SHIFT);

	/* retry over all memory */
	if (!ret_paddr)
		ret_paddr = __memblock_alloc_base(size, align, memblock_end_of_DRAM());

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

	ret = __va(ret_paddr);

	/*
	 * We initialize the nodes in numeric order: 0, 1, 2...
	 * and hand over control from the MEMBLOCK allocator to the
	 * bootmem allocator.  If this function is called for
	 * node 5, then we know that all nodes <5 are using the
	 * bootmem allocator instead of the MEMBLOCK allocator.
	 *
	 * So, check the nid from which this allocation came
	 * and double check to see if we need to use bootmem
	 * instead of the MEMBLOCK.  We don't free the MEMBLOCK memory
	 * since it would be useless.
	 */
	new_nid = early_pfn_to_nid(ret_paddr >> PAGE_SHIFT);
	if (new_nid < nid) {
		ret = __alloc_bootmem_node(NODE_DATA(new_nid),
				size, align, 0);

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

	memset(ret, 0, size);
	return ret;
}

static struct notifier_block __cpuinitdata ppc64_numa_nb = {
	.notifier_call = cpu_numa_callback,
	.priority = 1 /* Must run before sched domains notifier. */
};

static void mark_reserved_regions_for_nid(int nid)
{
	struct pglist_data *node = NODE_DATA(nid);
	int i;

	for (i = 0; i < memblock.reserved.cnt; i++) {
		unsigned long physbase = memblock.reserved.region[i].base;
		unsigned long size = memblock.reserved.region[i].size;
		unsigned long start_pfn = physbase >> PAGE_SHIFT;
		unsigned long end_pfn = PFN_UP(physbase + size);
		struct node_active_region node_ar;
		unsigned long node_end_pfn = node->node_start_pfn +
					     node->node_spanned_pages;

		/*
		 * Check to make sure that this memblock.reserved area is
		 * within the bounds of the node that we care about.
		 * Checking the nid of the start and end points is not
		 * sufficient because the reserved area could span the
		 * entire node.
		 */
		if (end_pfn <= node->node_start_pfn ||
		    start_pfn >= node_end_pfn)
			continue;

		get_node_active_region(start_pfn, &node_ar);
		while (start_pfn < end_pfn &&
			node_ar.start_pfn < node_ar.end_pfn) {
			unsigned long reserve_size = size;
			/*
			 * if reserved region extends past active region
			 * then trim size to active region
			 */
			if (end_pfn > node_ar.end_pfn)
				reserve_size = (node_ar.end_pfn << PAGE_SHIFT)
					- physbase;
			/*
			 * Only worry about *this* node, others may not
			 * yet have valid NODE_DATA().
			 */
			if (node_ar.nid == nid) {
				dbg("reserve_bootmem %lx %lx nid=%d\n",
					physbase, reserve_size, node_ar.nid);
				reserve_bootmem_node(NODE_DATA(node_ar.nid),
						physbase, reserve_size,
						BOOTMEM_DEFAULT);
			}
			/*
			 * if reserved region is contained in the active region
			 * then done.
			 */
			if (end_pfn <= node_ar.end_pfn)
				break;

			/*
			 * reserved region extends past the active region
			 *   get next active region that contains this
			 *   reserved region
			 */
			start_pfn = node_ar.end_pfn;
			physbase = start_pfn << PAGE_SHIFT;
			size = size - reserve_size;
			get_node_active_region(start_pfn, &node_ar);
		}
	}
}


void __init do_init_bootmem(void)
{
	int nid;

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

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

	for_each_online_node(nid) {
		unsigned long start_pfn, end_pfn;
		void *bootmem_vaddr;
		unsigned long bootmap_pages;

		get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);

		/*
		 * Allocate the node structure node local if possible
		 *
		 * Be careful moving this around, as it relies on all
		 * previous nodes' bootmem to be initialized and have
		 * all reserved areas marked.
		 */
		NODE_DATA(nid) = careful_zallocation(nid,
					sizeof(struct pglist_data),
					SMP_CACHE_BYTES, end_pfn);

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

		NODE_DATA(nid)->bdata = &bootmem_node_data[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_vaddr = careful_zallocation(nid,
					bootmap_pages << PAGE_SHIFT,
					PAGE_SIZE, end_pfn);

		dbg("bootmap_vaddr = %p\n", bootmem_vaddr);

		init_bootmem_node(NODE_DATA(nid),
				  __pa(bootmem_vaddr) >> PAGE_SHIFT,
				  start_pfn, end_pfn);

		free_bootmem_with_active_regions(nid, end_pfn);
		/*
		 * Be very careful about moving this around.  Future
		 * calls to careful_zallocation() depend on this getting
		 * done correctly.
		 */
		mark_reserved_regions_for_nid(nid);
		sparse_memory_present_with_active_regions(nid);
	}

	init_bootmem_done = 1;

	/*
	 * Now bootmem is initialised we can create the node to cpumask
	 * lookup tables and setup the cpu callback to populate them.
	 */
	setup_node_to_cpumask_map();

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

void __init paging_init(void)
{
	unsigned long max_zone_pfns[MAX_NR_ZONES];
	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
	max_zone_pfns[ZONE_DMA] = memblock_end_of_DRAM() >> PAGE_SHIFT;
	free_area_init_nodes(max_zone_pfns);
}

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;

	p = strstr(p, "fake=");
	if (p)
		cmdline = p + strlen("fake=");

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

#ifdef CONFIG_MEMORY_HOTPLUG
/*
 * Find the node associated with a hot added memory section for
 * memory represented in the device tree by the property
 * ibm,dynamic-reconfiguration-memory/ibm,dynamic-memory.
 */
static int hot_add_drconf_scn_to_nid(struct device_node *memory,
				     unsigned long scn_addr)
{
	const u32 *dm;
	unsigned int drconf_cell_cnt, rc;
	unsigned long memblock_size;
	struct assoc_arrays aa;
	int nid = -1;

	drconf_cell_cnt = of_get_drconf_memory(memory, &dm);
	if (!drconf_cell_cnt)
		return -1;

	memblock_size = of_get_memblock_size(memory);
	if (!memblock_size)
		return -1;

	rc = of_get_assoc_arrays(memory, &aa);
	if (rc)
		return -1;

	for (; drconf_cell_cnt != 0; --drconf_cell_cnt) {
		struct of_drconf_cell drmem;

		read_drconf_cell(&drmem, &dm);

		/* skip this block if it is reserved or not assigned to
		 * this partition */
		if ((drmem.flags & DRCONF_MEM_RESERVED)
		    || !(drmem.flags & DRCONF_MEM_ASSIGNED))
			continue;

		if ((scn_addr < drmem.base_addr)
		    || (scn_addr >= (drmem.base_addr + memblock_size)))
			continue;

		nid = of_drconf_to_nid_single(&drmem, &aa);
		break;
	}

	return nid;
}

/*
 * Find the node associated with a hot added memory section for memory
 * represented in the device tree as a node (i.e. memory@XXXX) for
 * each memblock.
 */
int hot_add_node_scn_to_nid(unsigned long scn_addr)
{
	struct device_node *memory = NULL;
	int nid = -1;

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

		memcell_buf = of_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);

		while (ranges--) {
			start = read_n_cells(n_mem_addr_cells, &memcell_buf);
			size = read_n_cells(n_mem_size_cells, &memcell_buf);

			if ((scn_addr < start) || (scn_addr >= (start + size)))
				continue;

			nid = of_node_to_nid_single(memory);
			break;
		}

		of_node_put(memory);
		if (nid >= 0)
			break;
	}

	return nid;
}

/*
 * Find the node associated with a hot added memory section.  Section
 * corresponds to a SPARSEMEM section, not an MEMBLOCK.  It is assumed that
 * sections are fully contained within a single MEMBLOCK.
 */
int hot_add_scn_to_nid(unsigned long scn_addr)
{
	struct device_node *memory = NULL;
	int nid, found = 0;

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

	memory = of_find_node_by_path("/ibm,dynamic-reconfiguration-memory");
	if (memory) {
		nid = hot_add_drconf_scn_to_nid(memory, scn_addr);
		of_node_put(memory);
	} else {
		nid = hot_add_node_scn_to_nid(scn_addr);
	}

	if (nid < 0 || !node_online(nid))
		nid = first_online_node;

	if (NODE_DATA(nid)->node_spanned_pages)
		return nid;

	for_each_online_node(nid) {
		if (NODE_DATA(nid)->node_spanned_pages) {
			found = 1;
			break;
		}
	}

	BUG_ON(!found);
	return nid;
}

#endif /* CONFIG_MEMORY_HOTPLUG */