summaryrefslogtreecommitdiffstats
path: root/include/linux/memory_hotplug.h
blob: 8f60e899b33c574b58be6d0a0d928c8f094941ea (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
#ifndef __LINUX_MEMORY_HOTPLUG_H
#define __LINUX_MEMORY_HOTPLUG_H

#include <linux/mmzone.h>
#include <linux/spinlock.h>
#include <linux/notifier.h>
#include <linux/bug.h>

struct page;
struct zone;
struct pglist_data;
struct mem_section;
struct memory_block;

#ifdef CONFIG_MEMORY_HOTPLUG

/*
 * Types for free bootmem stored in page->lru.next. These have to be in
 * some random range in unsigned long space for debugging purposes.
 */
enum {
	MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 12,
	SECTION_INFO = MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE,
	MIX_SECTION_INFO,
	NODE_INFO,
	MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE = NODE_INFO,
};

/* Types for control the zone type of onlined and offlined memory */
enum {
	MMOP_OFFLINE = -1,
	MMOP_ONLINE_KEEP,
	MMOP_ONLINE_KERNEL,
	MMOP_ONLINE_MOVABLE,
};

/*
 * pgdat resizing functions
 */
static inline
void pgdat_resize_lock(struct pglist_data *pgdat, unsigned long *flags)
{
	spin_lock_irqsave(&pgdat->node_size_lock, *flags);
}
static inline
void pgdat_resize_unlock(struct pglist_data *pgdat, unsigned long *flags)
{
	spin_unlock_irqrestore(&pgdat->node_size_lock, *flags);
}
static inline
void pgdat_resize_init(struct pglist_data *pgdat)
{
	spin_lock_init(&pgdat->node_size_lock);
}
/*
 * Zone resizing functions
 *
 * Note: any attempt to resize a zone should has pgdat_resize_lock()
 * zone_span_writelock() both held. This ensure the size of a zone
 * can't be changed while pgdat_resize_lock() held.
 */
static inline unsigned zone_span_seqbegin(struct zone *zone)
{
	return read_seqbegin(&zone->span_seqlock);
}
static inline int zone_span_seqretry(struct zone *zone, unsigned iv)
{
	return read_seqretry(&zone->span_seqlock, iv);
}
static inline void zone_span_writelock(struct zone *zone)
{
	write_seqlock(&zone->span_seqlock);
}
static inline void zone_span_writeunlock(struct zone *zone)
{
	write_sequnlock(&zone->span_seqlock);
}
static inline void zone_seqlock_init(struct zone *zone)
{
	seqlock_init(&zone->span_seqlock);
}
extern int zone_grow_free_lists(struct zone *zone, unsigned long new_nr_pages);
extern int zone_grow_waitqueues(struct zone *zone, unsigned long nr_pages);
extern int add_one_highpage(struct page *page, int pfn, int bad_ppro);
/* VM interface that may be used by firmware interface */
extern int online_pages(unsigned long, unsigned long, int);
extern int test_pages_in_a_zone(unsigned long, unsigned long);
extern void __offline_isolated_pages(unsigned long, unsigned long);

typedef void (*online_page_callback_t)(struct page *page);

extern int set_online_page_callback(online_page_callback_t callback);
extern int restore_online_page_callback(online_page_callback_t callback);

extern void __online_page_set_limits(struct page *page);
extern void __online_page_increment_counters(struct page *page);
extern void __online_page_free(struct page *page);

extern int try_online_node(int nid);

#ifdef CONFIG_MEMORY_HOTREMOVE
extern bool is_pageblock_removable_nolock(struct page *page);
extern int arch_remove_memory(u64 start, u64 size);
extern int __remove_pages(struct zone *zone, unsigned long start_pfn,
	unsigned long nr_pages);
#endif /* CONFIG_MEMORY_HOTREMOVE */

/* reasonably generic interface to expand the physical pages in a zone  */
extern int __add_pages(int nid, struct zone *zone, unsigned long start_pfn,
	unsigned long nr_pages);

#ifdef CONFIG_NUMA
extern int memory_add_physaddr_to_nid(u64 start);
#else
static inline int memory_add_physaddr_to_nid(u64 start)
{
	return 0;
}
#endif

#ifdef CONFIG_HAVE_ARCH_NODEDATA_EXTENSION
/*
 * For supporting node-hotadd, we have to allocate a new pgdat.
 *
 * If an arch has generic style NODE_DATA(),
 * node_data[nid] = kzalloc() works well. But it depends on the architecture.
 *
 * In general, generic_alloc_nodedata() is used.
 * Now, arch_free_nodedata() is just defined for error path of node_hot_add.
 *
 */
extern pg_data_t *arch_alloc_nodedata(int nid);
extern void arch_free_nodedata(pg_data_t *pgdat);
extern void arch_refresh_nodedata(int nid, pg_data_t *pgdat);

#else /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */

#define arch_alloc_nodedata(nid)	generic_alloc_nodedata(nid)
#define arch_free_nodedata(pgdat)	generic_free_nodedata(pgdat)

#ifdef CONFIG_NUMA
/*
 * If ARCH_HAS_NODEDATA_EXTENSION=n, this func is used to allocate pgdat.
 * XXX: kmalloc_node() can't work well to get new node's memory at this time.
 *	Because, pgdat for the new node is not allocated/initialized yet itself.
 *	To use new node's memory, more consideration will be necessary.
 */
#define generic_alloc_nodedata(nid)				\
({								\
	kzalloc(sizeof(pg_data_t), GFP_KERNEL);			\
})
/*
 * This definition is just for error path in node hotadd.
 * For node hotremove, we have to replace this.
 */
#define generic_free_nodedata(pgdat)	kfree(pgdat)

extern pg_data_t *node_data[];
static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)
{
	node_data[nid] = pgdat;
}

#else /* !CONFIG_NUMA */

/* never called */
static inline pg_data_t *generic_alloc_nodedata(int nid)
{
	BUG();
	return NULL;
}
static inline void generic_free_nodedata(pg_data_t *pgdat)
{
}
static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)
{
}
#endif /* CONFIG_NUMA */
#endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */

#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
extern void register_page_bootmem_info_node(struct pglist_data *pgdat);
#else
static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
{
}
#endif
extern void put_page_bootmem(struct page *page);
extern void get_page_bootmem(unsigned long ingo, struct page *page,
			     unsigned long type);

void get_online_mems(void);
void put_online_mems(void);

void mem_hotplug_begin(void);
void mem_hotplug_done(void);

#else /* ! CONFIG_MEMORY_HOTPLUG */
/*
 * Stub functions for when hotplug is off
 */
static inline void pgdat_resize_lock(struct pglist_data *p, unsigned long *f) {}
static inline void pgdat_resize_unlock(struct pglist_data *p, unsigned long *f) {}
static inline void pgdat_resize_init(struct pglist_data *pgdat) {}

static inline unsigned zone_span_seqbegin(struct zone *zone)
{
	return 0;
}
static inline int zone_span_seqretry(struct zone *zone, unsigned iv)
{
	return 0;
}
static inline void zone_span_writelock(struct zone *zone) {}
static inline void zone_span_writeunlock(struct zone *zone) {}
static inline void zone_seqlock_init(struct zone *zone) {}

static inline int mhp_notimplemented(const char *func)
{
	printk(KERN_WARNING "%s() called, with CONFIG_MEMORY_HOTPLUG disabled\n", func);
	dump_stack();
	return -ENOSYS;
}

static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
{
}

static inline int try_online_node(int nid)
{
	return 0;
}

static inline void get_online_mems(void) {}
static inline void put_online_mems(void) {}

static inline void mem_hotplug_begin(void) {}
static inline void mem_hotplug_done(void) {}

#endif /* ! CONFIG_MEMORY_HOTPLUG */

#ifdef CONFIG_MEMORY_HOTREMOVE

extern int is_mem_section_removable(unsigned long pfn, unsigned long nr_pages);
extern void try_offline_node(int nid);
extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages);
extern void remove_memory(int nid, u64 start, u64 size);

#else
static inline int is_mem_section_removable(unsigned long pfn,
					unsigned long nr_pages)
{
	return 0;
}

static inline void try_offline_node(int nid) {}

static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages)
{
	return -EINVAL;
}

static inline void remove_memory(int nid, u64 start, u64 size) {}
#endif /* CONFIG_MEMORY_HOTREMOVE */

extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn,
		void *arg, int (*func)(struct memory_block *, void *));
extern int add_memory(int nid, u64 start, u64 size);
extern int zone_for_memory(int nid, u64 start, u64 size, int zone_default,
		bool for_device);
extern int arch_add_memory(int nid, u64 start, u64 size, bool for_device);
extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages);
extern bool is_memblock_offlined(struct memory_block *mem);
extern void remove_memory(int nid, u64 start, u64 size);
extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn);
extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms);
extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
					  unsigned long pnum);

#endif /* __LINUX_MEMORY_HOTPLUG_H */