aboutsummaryrefslogtreecommitdiffstats
path: root/arch/ia64/mm/discontig.c
blob: 9b2d994cddf68cfe4d8417148df393aff76b7f8c (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (c) 2000, 2003 Silicon Graphics, Inc.  All rights reserved.
 * Copyright (c) 2001 Intel Corp.
 * Copyright (c) 2001 Tony Luck <tony.luck@intel.com>
 * Copyright (c) 2002 NEC Corp.
 * Copyright (c) 2002 Kimio Suganuma <k-suganuma@da.jp.nec.com>
 * Copyright (c) 2004 Silicon Graphics, Inc
 *	Russ Anderson <rja@sgi.com>
 *	Jesse Barnes <jbarnes@sgi.com>
 *	Jack Steiner <steiner@sgi.com>
 */

/*
 * Platform initialization for Discontig Memory
 */

#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/nmi.h>
#include <linux/swap.h>
#include <linux/bootmem.h>
#include <linux/acpi.h>
#include <linux/efi.h>
#include <linux/nodemask.h>
#include <linux/slab.h>
#include <asm/pgalloc.h>
#include <asm/tlb.h>
#include <asm/meminit.h>
#include <asm/numa.h>
#include <asm/sections.h>

/*
 * Track per-node information needed to setup the boot memory allocator, the
 * per-node areas, and the real VM.
 */
struct early_node_data {
	struct ia64_node_data *node_data;
	unsigned long pernode_addr;
	unsigned long pernode_size;
#ifdef CONFIG_ZONE_DMA
	unsigned long num_dma_physpages;
#endif
	unsigned long min_pfn;
	unsigned long max_pfn;
};

static struct early_node_data mem_data[MAX_NUMNODES] __initdata;
static nodemask_t memory_less_mask __initdata;

pg_data_t *pgdat_list[MAX_NUMNODES];

/*
 * To prevent cache aliasing effects, align per-node structures so that they
 * start at addresses that are strided by node number.
 */
#define MAX_NODE_ALIGN_OFFSET	(32 * 1024 * 1024)
#define NODEDATA_ALIGN(addr, node)						\
	((((addr) + 1024*1024-1) & ~(1024*1024-1)) + 				\
	     (((node)*PERCPU_PAGE_SIZE) & (MAX_NODE_ALIGN_OFFSET - 1)))

/**
 * build_node_maps - callback to setup bootmem structs for each node
 * @start: physical start of range
 * @len: length of range
 * @node: node where this range resides
 *
 * We allocate a struct bootmem_data for each piece of memory that we wish to
 * treat as a virtually contiguous block (i.e. each node). Each such block
 * must start on an %IA64_GRANULE_SIZE boundary, so we round the address down
 * if necessary.  Any non-existent pages will simply be part of the virtual
 * memmap.  We also update min_low_pfn and max_low_pfn here as we receive
 * memory ranges from the caller.
 */
static int __init build_node_maps(unsigned long start, unsigned long len,
				  int node)
{
	unsigned long spfn, epfn, end = start + len;
	struct bootmem_data *bdp = &bootmem_node_data[node];

	epfn = GRANULEROUNDUP(end) >> PAGE_SHIFT;
	spfn = GRANULEROUNDDOWN(start) >> PAGE_SHIFT;

	if (!bdp->node_low_pfn) {
		bdp->node_min_pfn = spfn;
		bdp->node_low_pfn = epfn;
	} else {
		bdp->node_min_pfn = min(spfn, bdp->node_min_pfn);
		bdp->node_low_pfn = max(epfn, bdp->node_low_pfn);
	}

	return 0;
}

/**
 * early_nr_cpus_node - return number of cpus on a given node
 * @node: node to check
 *
 * Count the number of cpus on @node.  We can't use nr_cpus_node() yet because
 * acpi_boot_init() (which builds the node_to_cpu_mask array) hasn't been
 * called yet.  Note that node 0 will also count all non-existent cpus.
 */
static int __meminit early_nr_cpus_node(int node)
{
	int cpu, n = 0;

	for_each_possible_early_cpu(cpu)
		if (node == node_cpuid[cpu].nid)
			n++;

	return n;
}

/**
 * compute_pernodesize - compute size of pernode data
 * @node: the node id.
 */
static unsigned long __meminit compute_pernodesize(int node)
{
	unsigned long pernodesize = 0, cpus;

	cpus = early_nr_cpus_node(node);
	pernodesize += PERCPU_PAGE_SIZE * cpus;
	pernodesize += node * L1_CACHE_BYTES;
	pernodesize += L1_CACHE_ALIGN(sizeof(pg_data_t));
	pernodesize += L1_CACHE_ALIGN(sizeof(struct ia64_node_data));
	pernodesize += L1_CACHE_ALIGN(sizeof(pg_data_t));
	pernodesize = PAGE_ALIGN(pernodesize);
	return pernodesize;
}

/**
 * per_cpu_node_setup - setup per-cpu areas on each node
 * @cpu_data: per-cpu area on this node
 * @node: node to setup
 *
 * Copy the static per-cpu data into the region we just set aside and then
 * setup __per_cpu_offset for each CPU on this node.  Return a pointer to
 * the end of the area.
 */
static void *per_cpu_node_setup(void *cpu_data, int node)
{
#ifdef CONFIG_SMP
	int cpu;

	for_each_possible_early_cpu(cpu) {
		void *src = cpu == 0 ? __cpu0_per_cpu : __phys_per_cpu_start;

		if (node != node_cpuid[cpu].nid)
			continue;

		memcpy(__va(cpu_data), src, __per_cpu_end - __per_cpu_start);
		__per_cpu_offset[cpu] = (char *)__va(cpu_data) -
			__per_cpu_start;

		/*
		 * percpu area for cpu0 is moved from the __init area
		 * which is setup by head.S and used till this point.
		 * Update ar.k3.  This move is ensures that percpu
		 * area for cpu0 is on the correct node and its
		 * virtual address isn't insanely far from other
		 * percpu areas which is important for congruent
		 * percpu allocator.
		 */
		if (cpu == 0)
			ia64_set_kr(IA64_KR_PER_CPU_DATA,
				    (unsigned long)cpu_data -
				    (unsigned long)__per_cpu_start);

		cpu_data += PERCPU_PAGE_SIZE;
	}
#endif
	return cpu_data;
}

#ifdef CONFIG_SMP
/**
 * setup_per_cpu_areas - setup percpu areas
 *
 * Arch code has already allocated and initialized percpu areas.  All
 * this function has to do is to teach the determined layout to the
 * dynamic percpu allocator, which happens to be more complex than
 * creating whole new ones using helpers.
 */
void __init setup_per_cpu_areas(void)
{
	struct pcpu_alloc_info *ai;
	struct pcpu_group_info *uninitialized_var(gi);
	unsigned int *cpu_map;
	void *base;
	unsigned long base_offset;
	unsigned int cpu;
	ssize_t static_size, reserved_size, dyn_size;
	int node, prev_node, unit, nr_units, rc;

	ai = pcpu_alloc_alloc_info(MAX_NUMNODES, nr_cpu_ids);
	if (!ai)
		panic("failed to allocate pcpu_alloc_info");
	cpu_map = ai->groups[0].cpu_map;

	/* determine base */
	base = (void *)ULONG_MAX;
	for_each_possible_cpu(cpu)
		base = min(base,
			   (void *)(__per_cpu_offset[cpu] + __per_cpu_start));
	base_offset = (void *)__per_cpu_start - base;

	/* build cpu_map, units are grouped by node */
	unit = 0;
	for_each_node(node)
		for_each_possible_cpu(cpu)
			if (node == node_cpuid[cpu].nid)
				cpu_map[unit++] = cpu;
	nr_units = unit;

	/* set basic parameters */
	static_size = __per_cpu_end - __per_cpu_start;
	reserved_size = PERCPU_MODULE_RESERVE;
	dyn_size = PERCPU_PAGE_SIZE - static_size - reserved_size;
	if (dyn_size < 0)
		panic("percpu area overflow static=%zd reserved=%zd\n",
		      static_size, reserved_size);

	ai->static_size		= static_size;
	ai->reserved_size	= reserved_size;
	ai->dyn_size		= dyn_size;
	ai->unit_size		= PERCPU_PAGE_SIZE;
	ai->atom_size		= PAGE_SIZE;
	ai->alloc_size		= PERCPU_PAGE_SIZE;

	/*
	 * CPUs are put into groups according to node.  Walk cpu_map
	 * and create new groups at node boundaries.
	 */
	prev_node = -1;
	ai->nr_groups = 0;
	for (unit = 0; unit < nr_units; unit++) {
		cpu = cpu_map[unit];
		node = node_cpuid[cpu].nid;

		if (node == prev_node) {
			gi->nr_units++;
			continue;
		}
		prev_node = node;

		gi = &ai->groups[ai->nr_groups++];
		gi->nr_units		= 1;
		gi->base_offset		= __per_cpu_offset[cpu] + base_offset;
		gi->cpu_map		= &cpu_map[unit];
	}

	rc = pcpu_setup_first_chunk(ai, base);
	if (rc)
		panic("failed to setup percpu area (err=%d)", rc);

	pcpu_free_alloc_info(ai);
}
#endif

/**
 * fill_pernode - initialize pernode data.
 * @node: the node id.
 * @pernode: physical address of pernode data
 * @pernodesize: size of the pernode data
 */
static void __init fill_pernode(int node, unsigned long pernode,
	unsigned long pernodesize)
{
	void *cpu_data;
	int cpus = early_nr_cpus_node(node);
	struct bootmem_data *bdp = &bootmem_node_data[node];

	mem_data[node].pernode_addr = pernode;
	mem_data[node].pernode_size = pernodesize;
	memset(__va(pernode), 0, pernodesize);

	cpu_data = (void *)pernode;
	pernode += PERCPU_PAGE_SIZE * cpus;
	pernode += node * L1_CACHE_BYTES;

	pgdat_list[node] = __va(pernode);
	pernode += L1_CACHE_ALIGN(sizeof(pg_data_t));

	mem_data[node].node_data = __va(pernode);
	pernode += L1_CACHE_ALIGN(sizeof(struct ia64_node_data));

	pgdat_list[node]->bdata = bdp;
	pernode += L1_CACHE_ALIGN(sizeof(pg_data_t));

	cpu_data = per_cpu_node_setup(cpu_data, node);

	return;
}

/**
 * find_pernode_space - allocate memory for memory map and per-node structures
 * @start: physical start of range
 * @len: length of range
 * @node: node where this range resides
 *
 * This routine reserves space for the per-cpu data struct, the list of
 * pg_data_ts and the per-node data struct.  Each node will have something like
 * the following in the first chunk of addr. space large enough to hold it.
 *
 *    ________________________
 *   |                        |
 *   |~~~~~~~~~~~~~~~~~~~~~~~~| <-- NODEDATA_ALIGN(start, node) for the first
 *   |    PERCPU_PAGE_SIZE *  |     start and length big enough
 *   |    cpus_on_this_node   | Node 0 will also have entries for all non-existent cpus.
 *   |------------------------|
 *   |   local pg_data_t *    |
 *   |------------------------|
 *   |  local ia64_node_data  |
 *   |------------------------|
 *   |          ???           |
 *   |________________________|
 *
 * Once this space has been set aside, the bootmem maps are initialized.  We
 * could probably move the allocation of the per-cpu and ia64_node_data space
 * outside of this function and use alloc_bootmem_node(), but doing it here
 * is straightforward and we get the alignments we want so...
 */
static int __init find_pernode_space(unsigned long start, unsigned long len,
				     int node)
{
	unsigned long spfn, epfn;
	unsigned long pernodesize = 0, pernode, pages, mapsize;
	struct bootmem_data *bdp = &bootmem_node_data[node];

	spfn = start >> PAGE_SHIFT;
	epfn = (start + len) >> PAGE_SHIFT;

	pages = bdp->node_low_pfn - bdp->node_min_pfn;
	mapsize = bootmem_bootmap_pages(pages) << PAGE_SHIFT;

	/*
	 * Make sure this memory falls within this node's usable memory
	 * since we may have thrown some away in build_maps().
	 */
	if (spfn < bdp->node_min_pfn || epfn > bdp->node_low_pfn)
		return 0;

	/* Don't setup this node's local space twice... */
	if (mem_data[node].pernode_addr)
		return 0;

	/*
	 * Calculate total size needed, incl. what's necessary
	 * for good alignment and alias prevention.
	 */
	pernodesize = compute_pernodesize(node);
	pernode = NODEDATA_ALIGN(start, node);

	/* Is this range big enough for what we want to store here? */
	if (start + len > (pernode + pernodesize + mapsize))
		fill_pernode(node, pernode, pernodesize);

	return 0;
}

/**
 * free_node_bootmem - free bootmem allocator memory for use
 * @start: physical start of range
 * @len: length of range
 * @node: node where this range resides
 *
 * Simply calls the bootmem allocator to free the specified ranged from
 * the given pg_data_t's bdata struct.  After this function has been called
 * for all the entries in the EFI memory map, the bootmem allocator will
 * be ready to service allocation requests.
 */
static int __init free_node_bootmem(unsigned long start, unsigned long len,
				    int node)
{
	free_bootmem_node(pgdat_list[node], start, len);

	return 0;
}

/**
 * reserve_pernode_space - reserve memory for per-node space
 *
 * Reserve the space used by the bootmem maps & per-node space in the boot
 * allocator so that when we actually create the real mem maps we don't
 * use their memory.
 */
static void __init reserve_pernode_space(void)
{
	unsigned long base, size, pages;
	struct bootmem_data *bdp;
	int node;

	for_each_online_node(node) {
		pg_data_t *pdp = pgdat_list[node];

		if (node_isset(node, memory_less_mask))
			continue;

		bdp = pdp->bdata;

		/* First the bootmem_map itself */
		pages = bdp->node_low_pfn - bdp->node_min_pfn;
		size = bootmem_bootmap_pages(pages) << PAGE_SHIFT;
		base = __pa(bdp->node_bootmem_map);
		reserve_bootmem_node(pdp, base, size, BOOTMEM_DEFAULT);

		/* Now the per-node space */
		size = mem_data[node].pernode_size;
		base = __pa(mem_data[node].pernode_addr);
		reserve_bootmem_node(pdp, base, size, BOOTMEM_DEFAULT);
	}
}

static void __meminit scatter_node_data(void)
{
	pg_data_t **dst;
	int node;

	/*
	 * for_each_online_node() can't be used at here.
	 * node_online_map is not set for hot-added nodes at this time,
	 * because we are halfway through initialization of the new node's
	 * structures.  If for_each_online_node() is used, a new node's
	 * pg_data_ptrs will be not initialized. Instead of using it,
	 * pgdat_list[] is checked.
	 */
	for_each_node(node) {
		if (pgdat_list[node]) {
			dst = LOCAL_DATA_ADDR(pgdat_list[node])->pg_data_ptrs;
			memcpy(dst, pgdat_list, sizeof(pgdat_list));
		}
	}
}

/**
 * initialize_pernode_data - fixup per-cpu & per-node pointers
 *
 * Each node's per-node area has a copy of the global pg_data_t list, so
 * we copy that to each node here, as well as setting the per-cpu pointer
 * to the local node data structure.  The active_cpus field of the per-node
 * structure gets setup by the platform_cpu_init() function later.
 */
static void __init initialize_pernode_data(void)
{
	int cpu, node;

	scatter_node_data();

#ifdef CONFIG_SMP
	/* Set the node_data pointer for each per-cpu struct */
	for_each_possible_early_cpu(cpu) {
		node = node_cpuid[cpu].nid;
		per_cpu(ia64_cpu_info, cpu).node_data =
			mem_data[node].node_data;
	}
#else
	{
		struct cpuinfo_ia64 *cpu0_cpu_info;
		cpu = 0;
		node = node_cpuid[cpu].nid;
		cpu0_cpu_info = (struct cpuinfo_ia64 *)(__phys_per_cpu_start +
			((char *)&ia64_cpu_info - __per_cpu_start));
		cpu0_cpu_info->node_data = mem_data[node].node_data;
	}
#endif /* CONFIG_SMP */
}

/**
 * memory_less_node_alloc - * attempt to allocate memory on the best NUMA slit
 * 	node but fall back to any other node when __alloc_bootmem_node fails
 *	for best.
 * @nid: node id
 * @pernodesize: size of this node's pernode data
 */
static void __init *memory_less_node_alloc(int nid, unsigned long pernodesize)
{
	void *ptr = NULL;
	u8 best = 0xff;
	int bestnode = -1, node, anynode = 0;

	for_each_online_node(node) {
		if (node_isset(node, memory_less_mask))
			continue;
		else if (node_distance(nid, node) < best) {
			best = node_distance(nid, node);
			bestnode = node;
		}
		anynode = node;
	}

	if (bestnode == -1)
		bestnode = anynode;

	ptr = __alloc_bootmem_node(pgdat_list[bestnode], pernodesize,
		PERCPU_PAGE_SIZE, __pa(MAX_DMA_ADDRESS));

	return ptr;
}

/**
 * memory_less_nodes - allocate and initialize CPU only nodes pernode
 *	information.
 */
static void __init memory_less_nodes(void)
{
	unsigned long pernodesize;
	void *pernode;
	int node;

	for_each_node_mask(node, memory_less_mask) {
		pernodesize = compute_pernodesize(node);
		pernode = memory_less_node_alloc(node, pernodesize);
		fill_pernode(node, __pa(pernode), pernodesize);
	}

	return;
}

/**
 * find_memory - walk the EFI memory map and setup the bootmem allocator
 *
 * Called early in boot to setup the bootmem allocator, and to
 * allocate the per-cpu and per-node structures.
 */
void __init find_memory(void)
{
	int node;

	reserve_memory();

	if (num_online_nodes() == 0) {
		printk(KERN_ERR "node info missing!\n");
		node_set_online(0);
	}

	nodes_or(memory_less_mask, memory_less_mask, node_online_map);
	min_low_pfn = -1;
	max_low_pfn = 0;

	/* These actually end up getting called by call_pernode_memory() */
	efi_memmap_walk(filter_rsvd_memory, build_node_maps);
	efi_memmap_walk(filter_rsvd_memory, find_pernode_space);
	efi_memmap_walk(find_max_min_low_pfn, NULL);

	for_each_online_node(node)
		if (bootmem_node_data[node].node_low_pfn) {
			node_clear(node, memory_less_mask);
			mem_data[node].min_pfn = ~0UL;
		}

	efi_memmap_walk(filter_memory, register_active_ranges);

	/*
	 * Initialize the boot memory maps in reverse order since that's
	 * what the bootmem allocator expects
	 */
	for (node = MAX_NUMNODES - 1; node >= 0; node--) {
		unsigned long pernode, pernodesize, map;
		struct bootmem_data *bdp;

		if (!node_online(node))
			continue;
		else if (node_isset(node, memory_less_mask))
			continue;

		bdp = &bootmem_node_data[node];
		pernode = mem_data[node].pernode_addr;
		pernodesize = mem_data[node].pernode_size;
		map = pernode + pernodesize;

		init_bootmem_node(pgdat_list[node],
				  map>>PAGE_SHIFT,
				  bdp->node_min_pfn,
				  bdp->node_low_pfn);
	}

	efi_memmap_walk(filter_rsvd_memory, free_node_bootmem);

	reserve_pernode_space();
	memory_less_nodes();
	initialize_pernode_data();

	max_pfn = max_low_pfn;

	find_initrd();
}

#ifdef CONFIG_SMP
/**
 * per_cpu_init - setup per-cpu variables
 *
 * find_pernode_space() does most of this already, we just need to set
 * local_per_cpu_offset
 */
void *per_cpu_init(void)
{
	int cpu;
	static int first_time = 1;

	if (first_time) {
		first_time = 0;
		for_each_possible_early_cpu(cpu)
			per_cpu(local_per_cpu_offset, cpu) = __per_cpu_offset[cpu];
	}

	return __per_cpu_start + __per_cpu_offset[smp_processor_id()];
}
#endif /* CONFIG_SMP */

/**
 * call_pernode_memory - use SRAT to call callback functions with node info
 * @start: physical start of range
 * @len: length of range
 * @arg: function to call for each range
 *
 * efi_memmap_walk() knows nothing about layout of memory across nodes. Find
 * out to which node a block of memory belongs.  Ignore memory that we cannot
 * identify, and split blocks that run across multiple nodes.
 *
 * Take this opportunity to round the start address up and the end address
 * down to page boundaries.
 */
void call_pernode_memory(unsigned long start, unsigned long len, void *arg)
{
	unsigned long rs, re, end = start + len;
	void (*func)(unsigned long, unsigned long, int);
	int i;

	start = PAGE_ALIGN(start);
	end &= PAGE_MASK;
	if (start >= end)
		return;

	func = arg;

	if (!num_node_memblks) {
		/* No SRAT table, so assume one node (node 0) */
		if (start < end)
			(*func)(start, end - start, 0);
		return;
	}

	for (i = 0; i < num_node_memblks; i++) {
		rs = max(start, node_memblk[i].start_paddr);
		re = min(end, node_memblk[i].start_paddr +
			 node_memblk[i].size);

		if (rs < re)
			(*func)(rs, re - rs, node_memblk[i].nid);

		if (re == end)
			break;
	}
}

/**
 * count_node_pages - callback to build per-node memory info structures
 * @start: physical start of range
 * @len: length of range
 * @node: node where this range resides
 *
 * Each node has it's own number of physical pages, DMAable pages, start, and
 * end page frame number.  This routine will be called by call_pernode_memory()
 * for each piece of usable memory and will setup these values for each node.
 * Very similar to build_maps().
 */
static __init int count_node_pages(unsigned long start, unsigned long len, int node)
{
	unsigned long end = start + len;

#ifdef CONFIG_ZONE_DMA
	if (start <= __pa(MAX_DMA_ADDRESS))
		mem_data[node].num_dma_physpages +=
			(min(end, __pa(MAX_DMA_ADDRESS)) - start) >>PAGE_SHIFT;
#endif
	start = GRANULEROUNDDOWN(start);
	end = GRANULEROUNDUP(end);
	mem_data[node].max_pfn = max(mem_data[node].max_pfn,
				     end >> PAGE_SHIFT);
	mem_data[node].min_pfn = min(mem_data[node].min_pfn,
				     start >> PAGE_SHIFT);

	return 0;
}

/**
 * paging_init - setup page tables
 *
 * paging_init() sets up the page tables for each node of the system and frees
 * the bootmem allocator memory for general use.
 */
void __init paging_init(void)
{
	unsigned long max_dma;
	unsigned long pfn_offset = 0;
	unsigned long max_pfn = 0;
	int node;
	unsigned long max_zone_pfns[MAX_NR_ZONES];

	max_dma = virt_to_phys((void *) MAX_DMA_ADDRESS) >> PAGE_SHIFT;

	efi_memmap_walk(filter_rsvd_memory, count_node_pages);

	sparse_memory_present_with_active_regions(MAX_NUMNODES);
	sparse_init();

#ifdef CONFIG_VIRTUAL_MEM_MAP
	VMALLOC_END -= PAGE_ALIGN(ALIGN(max_low_pfn, MAX_ORDER_NR_PAGES) *
		sizeof(struct page));
	vmem_map = (struct page *) VMALLOC_END;
	efi_memmap_walk(create_mem_map_page_table, NULL);
	printk("Virtual mem_map starts at 0x%p\n", vmem_map);
#endif

	for_each_online_node(node) {
		pfn_offset = mem_data[node].min_pfn;

#ifdef CONFIG_VIRTUAL_MEM_MAP
		NODE_DATA(node)->node_mem_map = vmem_map + pfn_offset;
#endif
		if (mem_data[node].max_pfn > max_pfn)
			max_pfn = mem_data[node].max_pfn;
	}

	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
#ifdef CONFIG_ZONE_DMA
	max_zone_pfns[ZONE_DMA] = max_dma;
#endif
	max_zone_pfns[ZONE_NORMAL] = max_pfn;
	free_area_init_nodes(max_zone_pfns);

	zero_page_memmap_ptr = virt_to_page(ia64_imva(empty_zero_page));
}

#ifdef CONFIG_MEMORY_HOTPLUG
pg_data_t *arch_alloc_nodedata(int nid)
{
	unsigned long size = compute_pernodesize(nid);

	return kzalloc(size, GFP_KERNEL);
}

void arch_free_nodedata(pg_data_t *pgdat)
{
	kfree(pgdat);
}

void arch_refresh_nodedata(int update_node, pg_data_t *update_pgdat)
{
	pgdat_list[update_node] = update_pgdat;
	scatter_node_data();
}
#endif

#ifdef CONFIG_SPARSEMEM_VMEMMAP
int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
{
	return vmemmap_populate_basepages(start, end, node);
}

void vmemmap_free(unsigned long start, unsigned long end)
{
}
#endif