migrate.h 10.0 KB
Newer Older
1
/* SPDX-License-Identifier: GPL-2.0 */
C
Christoph Lameter 已提交
2 3 4 5
#ifndef _LINUX_MIGRATE_H
#define _LINUX_MIGRATE_H

#include <linux/mm.h>
6
#include <linux/mempolicy.h>
7
#include <linux/migrate_mode.h>
8
#include <linux/hugetlb.h>
C
Christoph Lameter 已提交
9

10 11 12
typedef struct page *new_page_t(struct page *page, unsigned long private,
				int **reason);
typedef void free_page_t(struct page *page, unsigned long private);
13

14 15 16 17 18 19
/*
 * Return values from addresss_space_operations.migratepage():
 * - negative errno on page migration failure;
 * - zero on page migration success;
 */
#define MIGRATEPAGE_SUCCESS		0
20

21 22 23 24 25 26
enum migrate_reason {
	MR_COMPACTION,
	MR_MEMORY_FAILURE,
	MR_MEMORY_HOTPLUG,
	MR_SYSCALL,		/* also applies to cpusets */
	MR_MEMPOLICY_MBIND,
27
	MR_NUMA_MISPLACED,
28
	MR_CONTIG_RANGE,
29
	MR_TYPES
30
};
31

32 33 34
/* In mm/debug.c; also keep sync with include/trace/events/migrate.h */
extern char *migrate_reason_names[MR_TYPES];

35 36 37
static inline struct page *new_page_nodemask(struct page *page,
				int preferred_nid, nodemask_t *nodemask)
{
38
	gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL;
39 40
	unsigned int order = 0;
	struct page *new_page = NULL;
41 42 43

	if (PageHuge(page))
		return alloc_huge_page_nodemask(page_hstate(compound_head(page)),
44
				preferred_nid, nodemask);
45

46 47 48 49 50
	if (thp_migration_supported() && PageTransHuge(page)) {
		order = HPAGE_PMD_ORDER;
		gfp_mask |= GFP_TRANSHUGE;
	}

51 52 53
	if (PageHighMem(page) || (zone_idx(page_zone(page)) == ZONE_MOVABLE))
		gfp_mask |= __GFP_HIGHMEM;

54 55 56
	new_page = __alloc_pages_nodemask(gfp_mask, order,
				preferred_nid, nodemask);

57
	if (new_page && PageTransHuge(new_page))
58 59 60
		prep_transhuge_page(new_page);

	return new_page;
61 62
}

63
#ifdef CONFIG_MIGRATION
64

65
extern void putback_movable_pages(struct list_head *l);
66 67 68
extern int migrate_page(struct address_space *mapping,
			struct page *newpage, struct page *page,
			enum migrate_mode mode);
69
extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free,
70
		unsigned long private, enum migrate_mode mode, int reason);
71
extern int isolate_movable_page(struct page *page, isolate_mode_t mode);
72
extern void putback_movable_page(struct page *page);
73

C
Christoph Lameter 已提交
74
extern int migrate_prep(void);
75
extern int migrate_prep_local(void);
76
extern void migrate_page_states(struct page *newpage, struct page *page);
N
Naoya Horiguchi 已提交
77 78 79
extern void migrate_page_copy(struct page *newpage, struct page *page);
extern int migrate_huge_page_move_mapping(struct address_space *mapping,
				  struct page *newpage, struct page *page);
80 81
extern int migrate_page_move_mapping(struct address_space *mapping,
		struct page *newpage, struct page *page,
82 83
		struct buffer_head *head, enum migrate_mode mode,
		int extra_count);
C
Christoph Lameter 已提交
84
#else
85

86
static inline void putback_movable_pages(struct list_head *l) {}
87 88 89
static inline int migrate_pages(struct list_head *l, new_page_t new,
		free_page_t free, unsigned long private, enum migrate_mode mode,
		int reason)
90
	{ return -ENOSYS; }
91 92
static inline int isolate_movable_page(struct page *page, isolate_mode_t mode)
	{ return -EBUSY; }
93

C
Christoph Lameter 已提交
94
static inline int migrate_prep(void) { return -ENOSYS; }
95
static inline int migrate_prep_local(void) { return -ENOSYS; }
C
Christoph Lameter 已提交
96

97 98 99 100
static inline void migrate_page_states(struct page *newpage, struct page *page)
{
}

N
Naoya Horiguchi 已提交
101 102 103
static inline void migrate_page_copy(struct page *newpage,
				     struct page *page) {}

104
static inline int migrate_huge_page_move_mapping(struct address_space *mapping,
N
Naoya Horiguchi 已提交
105 106 107 108 109
				  struct page *newpage, struct page *page)
{
	return -ENOSYS;
}

C
Christoph Lameter 已提交
110
#endif /* CONFIG_MIGRATION */
111

112 113 114 115 116 117 118 119 120 121 122 123 124 125 126
#ifdef CONFIG_COMPACTION
extern int PageMovable(struct page *page);
extern void __SetPageMovable(struct page *page, struct address_space *mapping);
extern void __ClearPageMovable(struct page *page);
#else
static inline int PageMovable(struct page *page) { return 0; };
static inline void __SetPageMovable(struct page *page,
				struct address_space *mapping)
{
}
static inline void __ClearPageMovable(struct page *page)
{
}
#endif

127
#ifdef CONFIG_NUMA_BALANCING
128
extern bool pmd_trans_migrating(pmd_t pmd);
129 130
extern int migrate_misplaced_page(struct page *page,
				  struct vm_area_struct *vma, int node);
131
#else
132 133 134 135
static inline bool pmd_trans_migrating(pmd_t pmd)
{
	return false;
}
136 137
static inline int migrate_misplaced_page(struct page *page,
					 struct vm_area_struct *vma, int node)
138 139 140
{
	return -EAGAIN; /* can't migrate now */
}
141
#endif /* CONFIG_NUMA_BALANCING */
142

143 144 145 146 147 148 149
#if defined(CONFIG_NUMA_BALANCING) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
extern int migrate_misplaced_transhuge_page(struct mm_struct *mm,
			struct vm_area_struct *vma,
			pmd_t *pmd, pmd_t entry,
			unsigned long address,
			struct page *page, int node);
#else
150 151 152 153 154 155 156 157
static inline int migrate_misplaced_transhuge_page(struct mm_struct *mm,
			struct vm_area_struct *vma,
			pmd_t *pmd, pmd_t entry,
			unsigned long address,
			struct page *page, int node)
{
	return -EAGAIN;
}
158
#endif /* CONFIG_NUMA_BALANCING && CONFIG_TRANSPARENT_HUGEPAGE*/
159

160 161 162

#ifdef CONFIG_MIGRATION

163 164 165 166 167
/*
 * Watch out for PAE architecture, which has an unsigned long, and might not
 * have enough bits to store all physical address and flags. So far we have
 * enough room for all our flags.
 */
168 169 170 171
#define MIGRATE_PFN_VALID	(1UL << 0)
#define MIGRATE_PFN_MIGRATE	(1UL << 1)
#define MIGRATE_PFN_LOCKED	(1UL << 2)
#define MIGRATE_PFN_WRITE	(1UL << 3)
172 173 174
#define MIGRATE_PFN_DEVICE	(1UL << 4)
#define MIGRATE_PFN_ERROR	(1UL << 5)
#define MIGRATE_PFN_SHIFT	6
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

static inline struct page *migrate_pfn_to_page(unsigned long mpfn)
{
	if (!(mpfn & MIGRATE_PFN_VALID))
		return NULL;
	return pfn_to_page(mpfn >> MIGRATE_PFN_SHIFT);
}

static inline unsigned long migrate_pfn(unsigned long pfn)
{
	return (pfn << MIGRATE_PFN_SHIFT) | MIGRATE_PFN_VALID;
}

/*
 * struct migrate_vma_ops - migrate operation callback
 *
 * @alloc_and_copy: alloc destination memory and copy source memory to it
 * @finalize_and_map: allow caller to map the successfully migrated pages
 *
 *
 * The alloc_and_copy() callback happens once all source pages have been locked,
 * unmapped and checked (checked whether pinned or not). All pages that can be
 * migrated will have an entry in the src array set with the pfn value of the
 * page and with the MIGRATE_PFN_VALID and MIGRATE_PFN_MIGRATE flag set (other
 * flags might be set but should be ignored by the callback).
 *
 * The alloc_and_copy() callback can then allocate destination memory and copy
 * source memory to it for all those entries (ie with MIGRATE_PFN_VALID and
 * MIGRATE_PFN_MIGRATE flag set). Once these are allocated and copied, the
 * callback must update each corresponding entry in the dst array with the pfn
 * value of the destination page and with the MIGRATE_PFN_VALID and
 * MIGRATE_PFN_LOCKED flags set (destination pages must have their struct pages
 * locked, via lock_page()).
 *
 * At this point the alloc_and_copy() callback is done and returns.
 *
 * Note that the callback does not have to migrate all the pages that are
 * marked with MIGRATE_PFN_MIGRATE flag in src array unless this is a migration
 * from device memory to system memory (ie the MIGRATE_PFN_DEVICE flag is also
 * set in the src array entry). If the device driver cannot migrate a device
 * page back to system memory, then it must set the corresponding dst array
 * entry to MIGRATE_PFN_ERROR. This will trigger a SIGBUS if CPU tries to
 * access any of the virtual addresses originally backed by this page. Because
 * a SIGBUS is such a severe result for the userspace process, the device
 * driver should avoid setting MIGRATE_PFN_ERROR unless it is really in an
 * unrecoverable state.
 *
222 223 224 225 226 227 228 229 230
 * For empty entry inside CPU page table (pte_none() or pmd_none() is true) we
 * do set MIGRATE_PFN_MIGRATE flag inside the corresponding source array thus
 * allowing device driver to allocate device memory for those unback virtual
 * address. For this the device driver simply have to allocate device memory
 * and properly set the destination entry like for regular migration. Note that
 * this can still fails and thus inside the device driver must check if the
 * migration was successful for those entry inside the finalize_and_map()
 * callback just like for regular migration.
 *
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
 * THE alloc_and_copy() CALLBACK MUST NOT CHANGE ANY OF THE SRC ARRAY ENTRIES
 * OR BAD THINGS WILL HAPPEN !
 *
 *
 * The finalize_and_map() callback happens after struct page migration from
 * source to destination (destination struct pages are the struct pages for the
 * memory allocated by the alloc_and_copy() callback).  Migration can fail, and
 * thus the finalize_and_map() allows the driver to inspect which pages were
 * successfully migrated, and which were not. Successfully migrated pages will
 * have the MIGRATE_PFN_MIGRATE flag set for their src array entry.
 *
 * It is safe to update device page table from within the finalize_and_map()
 * callback because both destination and source page are still locked, and the
 * mmap_sem is held in read mode (hence no one can unmap the range being
 * migrated).
 *
 * Once callback is done cleaning up things and updating its page table (if it
 * chose to do so, this is not an obligation) then it returns. At this point,
 * the HMM core will finish up the final steps, and the migration is complete.
 *
 * THE finalize_and_map() CALLBACK MUST NOT CHANGE ANY OF THE SRC OR DST ARRAY
 * ENTRIES OR BAD THINGS WILL HAPPEN !
 */
struct migrate_vma_ops {
	void (*alloc_and_copy)(struct vm_area_struct *vma,
			       const unsigned long *src,
			       unsigned long *dst,
			       unsigned long start,
			       unsigned long end,
			       void *private);
	void (*finalize_and_map)(struct vm_area_struct *vma,
				 const unsigned long *src,
				 const unsigned long *dst,
				 unsigned long start,
				 unsigned long end,
				 void *private);
};

269
#if defined(CONFIG_MIGRATE_VMA_HELPER)
270 271 272 273 274 275 276
int migrate_vma(const struct migrate_vma_ops *ops,
		struct vm_area_struct *vma,
		unsigned long start,
		unsigned long end,
		unsigned long *src,
		unsigned long *dst,
		void *private);
277 278 279 280 281 282 283 284 285 286 287 288
#else
static inline int migrate_vma(const struct migrate_vma_ops *ops,
			      struct vm_area_struct *vma,
			      unsigned long start,
			      unsigned long end,
			      unsigned long *src,
			      unsigned long *dst,
			      void *private)
{
	return -EINVAL;
}
#endif /* IS_ENABLED(CONFIG_MIGRATE_VMA_HELPER) */
289 290 291

#endif /* CONFIG_MIGRATION */

C
Christoph Lameter 已提交
292
#endif /* _LINUX_MIGRATE_H */