memory_hotplug.h 11.1 KB
Newer Older
1
/* SPDX-License-Identifier: GPL-2.0 */
2 3 4 5 6
#ifndef __LINUX_MEMORY_HOTPLUG_H
#define __LINUX_MEMORY_HOTPLUG_H

#include <linux/mmzone.h>
#include <linux/spinlock.h>
7
#include <linux/notifier.h>
8
#include <linux/bug.h>
9

10 11 12
struct page;
struct zone;
struct pglist_data;
13
struct mem_section;
14
struct memory_block;
15
struct resource;
16
struct vmem_altmap;
17

18
#ifdef CONFIG_MEMORY_HOTPLUG
19 20 21 22 23
/*
 * Return page for the valid pfn only if the page is online. All pfn
 * walkers which rely on the fully initialized page->flags and others
 * should use this rather than pfn_valid && pfn_to_page
 */
24 25 26 27 28 29 30 31 32 33
#define pfn_to_online_page(pfn)					   \
({								   \
	struct page *___page = NULL;				   \
	unsigned long ___pfn = pfn;				   \
	unsigned long ___nr = pfn_to_section_nr(___pfn);	   \
								   \
	if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr) && \
	    pfn_valid_within(___pfn))				   \
		___page = pfn_to_page(___pfn);			   \
	___page;						   \
34
})
35 36

/*
A
Andrea Arcangeli 已提交
37 38
 * Types for free bootmem stored in page->lru.next. These have to be in
 * some random range in unsigned long space for debugging purposes.
39
 */
A
Andrea Arcangeli 已提交
40 41 42 43 44 45 46
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,
};
47

48
/* Types for control the zone type of onlined and offlined memory */
49
enum {
50
	/* Offline the memory. */
51
	MMOP_OFFLINE = 0,
52 53 54
	/* Online the memory. Zone depends, see default_zone_for_pfn(). */
	MMOP_ONLINE,
	/* Online the memory to ZONE_NORMAL. */
55
	MMOP_ONLINE_KERNEL,
56
	/* Online the memory to ZONE_MOVABLE. */
57
	MMOP_ONLINE_MOVABLE,
58 59
};

60
/*
61 62
 * Extended parameters for memory hotplug:
 * altmap: alternative allocator for memmap array (optional)
63 64
 * pgprot: page protection flags to apply to newly created page tables
 *	(required)
65
 */
66
struct mhp_params {
67
	struct vmem_altmap *altmap;
68
	pgprot_t pgprot;
69 70
};

71 72
/*
 * Zone resizing functions
73 74 75 76
 *
 * 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.
77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97
 */
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);
}
98 99 100 101
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 */
102 103
extern int online_pages(unsigned long pfn, unsigned long nr_pages,
			int online_type, int nid);
104 105
extern struct zone *test_pages_in_a_zone(unsigned long start_pfn,
					 unsigned long end_pfn);
106 107
extern void __offline_isolated_pages(unsigned long start_pfn,
				     unsigned long end_pfn);
108

109
typedef void (*online_page_callback_t)(struct page *page, unsigned int order);
110

111
extern void generic_online_page(struct page *page, unsigned int order);
112 113 114
extern int set_online_page_callback(online_page_callback_t callback);
extern int restore_online_page_callback(online_page_callback_t callback);

115 116
extern int try_online_node(int nid);

117
extern int arch_add_memory(int nid, u64 start, u64 size,
118
			   struct mhp_params *params);
119 120
extern u64 max_mem_size;

121 122
extern int memhp_online_type_from_str(const char *str);

123 124
/* Default online_type (MMOP_*) when new memory blocks are added. */
extern int memhp_default_online_type;
125 126 127 128 129 130
/* If movable_node boot option specified */
extern bool movable_node_enabled;
static inline bool movable_node_is_enabled(void)
{
	return movable_node_enabled;
}
131

132 133
extern void arch_remove_memory(int nid, u64 start, u64 size,
			       struct vmem_altmap *altmap);
134 135
extern void __remove_pages(unsigned long start_pfn, unsigned long nr_pages,
			   struct vmem_altmap *altmap);
136

137
/* reasonably generic interface to expand the physical pages */
138
extern int __add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
139
		       struct mhp_params *params);
140

141 142
#ifndef CONFIG_ARCH_HAS_ADD_PAGES
static inline int add_pages(int nid, unsigned long start_pfn,
143
		unsigned long nr_pages, struct mhp_params *params)
144
{
145
	return __add_pages(nid, start_pfn, nr_pages, params);
146 147
}
#else /* ARCH_HAS_ADD_PAGES */
148
int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
149
	      struct mhp_params *params);
150 151
#endif /* ARCH_HAS_ADD_PAGES */

152 153 154 155 156 157 158 159 160 161 162
#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.
 *
 */
163 164
extern pg_data_t *arch_alloc_nodedata(int nid);
extern void arch_free_nodedata(pg_data_t *pgdat);
165
extern void arch_refresh_nodedata(int nid, pg_data_t *pgdat);
166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188

#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)

189 190 191 192 193 194
extern pg_data_t *node_data[];
static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)
{
	node_data[nid] = pgdat;
}

195 196 197 198 199 200 201 202 203 204 205
#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)
{
}
206 207 208
static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)
{
}
209 210 211
#endif /* CONFIG_NUMA */
#endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */

212
#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
213
extern void __init register_page_bootmem_info_node(struct pglist_data *pgdat);
214
#else
215 216 217 218
static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
{
}
#endif
219 220 221
extern void put_page_bootmem(struct page *page);
extern void get_page_bootmem(unsigned long ingo, struct page *page,
			     unsigned long type);
222

223 224
void get_online_mems(void);
void put_online_mems(void);
225

226 227 228
void mem_hotplug_begin(void);
void mem_hotplug_done(void);

229
#else /* ! CONFIG_MEMORY_HOTPLUG */
230 231 232 233 234 235 236 237
#define pfn_to_online_page(pfn)			\
({						\
	struct page *___page = NULL;		\
	if (pfn_valid(pfn))			\
		___page = pfn_to_page(pfn);	\
	___page;				\
 })

238 239 240 241 242 243 244 245 246 247 248
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) {}
249 250 251 252 253 254 255 256

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

257 258 259 260
static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
{
}

261 262 263 264 265
static inline int try_online_node(int nid)
{
	return 0;
}

266 267
static inline void get_online_mems(void) {}
static inline void put_online_mems(void) {}
268

269 270 271
static inline void mem_hotplug_begin(void) {}
static inline void mem_hotplug_done(void) {}

272 273 274 275
static inline bool movable_node_is_enabled(void)
{
	return false;
}
276
#endif /* ! CONFIG_MEMORY_HOTPLUG */
277

278 279 280 281 282 283 284 285 286 287 288 289 290 291
#ifdef CONFIG_NUMA
extern int memory_add_physaddr_to_nid(u64 start);
extern int phys_to_target_node(u64 start);
#else
static inline int memory_add_physaddr_to_nid(u64 start)
{
	return 0;
}
static inline int phys_to_target_node(u64 start)
{
	return 0;
}
#endif

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
#if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT)
/*
 * 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);
}
#else /* !(CONFIG_MEMORY_HOTPLUG || CONFIG_DEFERRED_STRUCT_PAGE_INIT) */
/*
 * 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) {}
#endif /* !(CONFIG_MEMORY_HOTPLUG || CONFIG_DEFERRED_STRUCT_PAGE_INIT) */

320 321
#ifdef CONFIG_MEMORY_HOTREMOVE

322
extern void try_offline_node(int nid);
323
extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages);
324
extern int remove_memory(int nid, u64 start, u64 size);
325
extern void __remove_memory(int nid, u64 start, u64 size);
326
extern int offline_and_remove_memory(int nid, u64 start, u64 size);
327 328

#else
329
static inline void try_offline_node(int nid) {}
330 331 332 333 334 335

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

336 337 338 339 340
static inline int remove_memory(int nid, u64 start, u64 size)
{
	return -EBUSY;
}

341
static inline void __remove_memory(int nid, u64 start, u64 size) {}
342 343
#endif /* CONFIG_MEMORY_HOTREMOVE */

344 345 346
extern void set_zone_contiguous(struct zone *zone);
extern void clear_zone_contiguous(struct zone *zone);

347
extern void __ref free_area_init_core_hotplug(int nid);
348
extern int __add_memory(int nid, u64 start, u64 size);
349
extern int add_memory(int nid, u64 start, u64 size);
350
extern int add_memory_resource(int nid, struct resource *resource);
351 352
extern int add_memory_driver_managed(int nid, u64 start, u64 size,
				     const char *resource_name);
353
extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
354
		unsigned long nr_pages, struct vmem_altmap *altmap);
355 356 357
extern void remove_pfn_range_from_zone(struct zone *zone,
				       unsigned long start_pfn,
				       unsigned long nr_pages);
358
extern bool is_memblock_offlined(struct memory_block *mem);
359 360
extern int sparse_add_section(int nid, unsigned long pfn,
		unsigned long nr_pages, struct vmem_altmap *altmap);
361
extern void sparse_remove_section(struct mem_section *ms,
362
		unsigned long pfn, unsigned long nr_pages,
363
		unsigned long map_offset, struct vmem_altmap *altmap);
364 365
extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
					  unsigned long pnum);
366 367
extern bool allow_online_pfn_range(int nid, unsigned long pfn, unsigned long nr_pages,
		int online_type);
368
extern struct zone *zone_for_pfn_range(int online_type, int nid, unsigned start_pfn,
369
		unsigned long nr_pages);
370
#endif /* __LINUX_MEMORY_HOTPLUG_H */