aboutsummaryrefslogtreecommitdiffstats
path: root/mm/memory_hotplug.c
blob: 855e0fc928b3cc6b1685b07a98231ff9077215ab (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
/*
 *  linux/mm/memory_hotplug.c
 *
 *  Copyright (C)
 */

#include <linux/config.h>
#include <linux/stddef.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/interrupt.h>
#include <linux/pagemap.h>
#include <linux/bootmem.h>
#include <linux/compiler.h>
#include <linux/module.h>
#include <linux/pagevec.h>
#include <linux/slab.h>
#include <linux/sysctl.h>
#include <linux/cpu.h>
#include <linux/memory.h>
#include <linux/memory_hotplug.h>
#include <linux/highmem.h>
#include <linux/vmalloc.h>

#include <asm/tlbflush.h>

static struct page *__kmalloc_section_memmap(unsigned long nr_pages)
{
	struct page *page, *ret;
	unsigned long memmap_size = sizeof(struct page) * nr_pages;

	page = alloc_pages(GFP_KERNEL, get_order(memmap_size));
	if (page)
		goto got_map_page;

	ret = vmalloc(memmap_size);
	if (ret)
		goto got_map_ptr;

	return NULL;
got_map_page:
	ret = (struct page *)pfn_to_kaddr(page_to_pfn(page));
got_map_ptr:
	memset(ret, 0, memmap_size);

	return ret;
}

extern void zonetable_add(struct zone *zone, int nid, int zid, unsigned long pfn,
			  unsigned long size);
static void __add_zone(struct zone *zone, unsigned long phys_start_pfn)
{
	struct pglist_data *pgdat = zone->zone_pgdat;
	int nr_pages = PAGES_PER_SECTION;
	int nid = pgdat->node_id;
	int zone_type;

	zone_type = zone - pgdat->node_zones;
	memmap_init_zone(nr_pages, nid, zone_type, phys_start_pfn);
	zonetable_add(zone, nid, zone_type, phys_start_pfn, nr_pages);
}

extern int sparse_add_one_section(struct zone *, unsigned long,
				  struct page *mem_map);
static int __add_section(struct zone *zone, unsigned long phys_start_pfn)
{
	struct pglist_data *pgdat = zone->zone_pgdat;
	int nr_pages = PAGES_PER_SECTION;
	struct page *memmap;
	int ret;

	/*
	 * This can potentially allocate memory, and does its own
	 * internal locking.
	 */
	sparse_index_init(pfn_to_section_nr(phys_start_pfn), pgdat->node_id);

	pgdat_resize_lock(pgdat, &flags);
	memmap = __kmalloc_section_memmap(nr_pages);
	ret = sparse_add_one_section(zone, phys_start_pfn, memmap);
	pgdat_resize_unlock(pgdat, &flags);

	if (ret <= 0) {
		/* the mem_map didn't get used */
		if (memmap >= (struct page *)VMALLOC_START &&
		    memmap < (struct page *)VMALLOC_END)
			vfree(memmap);
		else
			free_pages((unsigned long)memmap,
				   get_order(sizeof(struct page) * nr_pages));
	}

	if (ret < 0)
		return ret;

	__add_zone(zone, phys_start_pfn);
	return register_new_memory(__pfn_to_section(phys_start_pfn));
}

/*
 * Reasonably generic function for adding memory.  It is
 * expected that archs that support memory hotplug will
 * call this function after deciding the zone to which to
 * add the new pages.
 */
int __add_pages(struct zone *zone, unsigned long phys_start_pfn,
		 unsigned long nr_pages)
{
	unsigned long i;
	int err = 0;

	for (i = 0; i < nr_pages; i += PAGES_PER_SECTION) {
		err = __add_section(zone, phys_start_pfn + i);

		if (err)
			break;
	}

	return err;
}

static void grow_zone_span(struct zone *zone,
		unsigned long start_pfn, unsigned long end_pfn)
{
	unsigned long old_zone_end_pfn;

	zone_span_writelock(zone);

	old_zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages;
	if (start_pfn < zone->zone_start_pfn)
		zone->zone_start_pfn = start_pfn;

	if (end_pfn > old_zone_end_pfn)
		zone->spanned_pages = end_pfn - zone->zone_start_pfn;

	zone_span_writeunlock(zone);
}

static void grow_pgdat_span(struct pglist_data *pgdat,
		unsigned long start_pfn, unsigned long end_pfn)
{
	unsigned long old_pgdat_end_pfn =
		pgdat->node_start_pfn + pgdat->node_spanned_pages;

	if (start_pfn < pgdat->node_start_pfn)
		pgdat->node_start_pfn = start_pfn;

	if (end_pfn > old_pgdat_end_pfn)
		pgdat->node_spanned_pages = end_pfn - pgdat->node_spanned_pages;
}

int online_pages(unsigned long pfn, unsigned long nr_pages)
{
	unsigned long i;
	unsigned long flags;
	unsigned long onlined_pages = 0;
	struct zone *zone;

	/*
	 * This doesn't need a lock to do pfn_to_page().
	 * The section can't be removed here because of the
	 * memory_block->state_sem.
	 */
	zone = page_zone(pfn_to_page(pfn));
	pgdat_resize_lock(zone->zone_pgdat, &flags);
	grow_zone_span(zone, pfn, pfn + nr_pages);
	grow_pgdat_span(zone->zone_pgdat, pfn, pfn + nr_pages);
	pgdat_resize_unlock(zone->zone_pgdat, &flags);

	for (i = 0; i < nr_pages; i++) {
		struct page *page = pfn_to_page(pfn + i);
		online_page(page);
		onlined_pages++;
	}
	zone->present_pages += onlined_pages;

	return 0;
}