summaryrefslogtreecommitdiffstats
path: root/include/linux/mempolicy.h
blob: bac395f1d00a0f9691b12ec6841f2401a10ca4fc (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
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
/* SPDX-License-Identifier: GPL-2.0 */
/*
 * NUMA memory policies for Linux.
 * Copyright 2003,2004 Andi Kleen SuSE Labs
 */
#ifndef _LINUX_MEMPOLICY_H
#define _LINUX_MEMPOLICY_H 1


#include <linux/mmzone.h>
#include <linux/dax.h>
#include <linux/slab.h>
#include <linux/rbtree.h>
#include <linux/spinlock.h>
#include <linux/nodemask.h>
#include <linux/pagemap.h>
#include <uapi/linux/mempolicy.h>

struct mm_struct;

#ifdef CONFIG_NUMA

/*
 * Describe a memory policy.
 *
 * A mempolicy can be either associated with a process or with a VMA.
 * For VMA related allocations the VMA policy is preferred, otherwise
 * the process policy is used. Interrupts ignore the memory policy
 * of the current process.
 *
 * Locking policy for interlave:
 * In process context there is no locking because only the process accesses
 * its own state. All vma manipulation is somewhat protected by a down_read on
 * mmap_sem.
 *
 * Freeing policy:
 * Mempolicy objects are reference counted.  A mempolicy will be freed when
 * mpol_put() decrements the reference count to zero.
 *
 * Duplicating policy objects:
 * mpol_dup() allocates a new mempolicy and copies the specified mempolicy
 * to the new storage.  The reference count of the new object is initialized
 * to 1, representing the caller of mpol_dup().
 */
struct mempolicy {
	atomic_t refcnt;
	unsigned short mode; 	/* See MPOL_* above */
	unsigned short flags;	/* See set_mempolicy() MPOL_F_* above */
	union {
		short 		 preferred_node; /* preferred */
		nodemask_t	 nodes;		/* interleave/bind */
		/* undefined for default */
	} v;
	union {
		nodemask_t cpuset_mems_allowed;	/* relative to these nodes */
		nodemask_t user_nodemask;	/* nodemask passed by user */
	} w;
};

/*
 * Support for managing mempolicy data objects (clone, copy, destroy)
 * The default fast path of a NULL MPOL_DEFAULT policy is always inlined.
 */

extern void __mpol_put(struct mempolicy *pol);
static inline void mpol_put(struct mempolicy *pol)
{
	if (pol)
		__mpol_put(pol);
}

/*
 * Does mempolicy pol need explicit unref after use?
 * Currently only needed for shared policies.
 */
static inline int mpol_needs_cond_ref(struct mempolicy *pol)
{
	return (pol && (pol->flags & MPOL_F_SHARED));
}

static inline void mpol_cond_put(struct mempolicy *pol)
{
	if (mpol_needs_cond_ref(pol))
		__mpol_put(pol);
}

extern struct mempolicy *__mpol_dup(struct mempolicy *pol);
static inline struct mempolicy *mpol_dup(struct mempolicy *pol)
{
	if (pol)
		pol = __mpol_dup(pol);
	return pol;
}

#define vma_policy(vma) ((vma)->vm_policy)

static inline void mpol_get(struct mempolicy *pol)
{
	if (pol)
		atomic_inc(&pol->refcnt);
}

extern bool __mpol_equal(struct mempolicy *a, struct mempolicy *b);
static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b)
{
	if (a == b)
		return true;
	return __mpol_equal(a, b);
}

/*
 * Tree of shared policies for a shared memory region.
 * Maintain the policies in a pseudo mm that contains vmas. The vmas
 * carry the policy. As a special twist the pseudo mm is indexed in pages, not
 * bytes, so that we can work with shared memory segments bigger than
 * unsigned long.
 */

struct sp_node {
	struct rb_node nd;
	unsigned long start, end;
	struct mempolicy *policy;
};

struct shared_policy {
	struct rb_root root;
	rwlock_t lock;
};

int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst);
void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol);
int mpol_set_shared_policy(struct shared_policy *info,
				struct vm_area_struct *vma,
				struct mempolicy *new);
void mpol_free_shared_policy(struct shared_policy *p);
struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp,
					    unsigned long idx);

struct mempolicy *get_task_policy(struct task_struct *p);
struct mempolicy *__get_vma_policy(struct vm_area_struct *vma,
		unsigned long addr);
struct mempolicy *get_vma_policy(struct vm_area_struct *vma,
						unsigned long addr);
bool vma_policy_mof(struct vm_area_struct *vma);

extern void numa_default_policy(void);
extern void numa_policy_init(void);
extern void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new);
extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new);

extern int huge_node(struct vm_area_struct *vma,
				unsigned long addr, gfp_t gfp_flags,
				struct mempolicy **mpol, nodemask_t **nodemask);
extern bool init_nodemask_of_mempolicy(nodemask_t *mask);
extern bool mempolicy_nodemask_intersects(struct task_struct *tsk,
				const nodemask_t *mask);
extern unsigned int mempolicy_slab_node(void);

extern enum zone_type policy_zone;

static inline void check_highest_zone(enum zone_type k)
{
	if (k > policy_zone && k != ZONE_MOVABLE)
		policy_zone = k;
}

int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
		     const nodemask_t *to, int flags);


#ifdef CONFIG_TMPFS
extern int mpol_parse_str(char *str, struct mempolicy **mpol);
#endif

extern void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol);

/* Check if a vma is migratable */
static inline bool vma_migratable(struct vm_area_struct *vma)
{
	if (vma->vm_flags & (VM_IO | VM_PFNMAP))
		return false;

	/*
	 * DAX device mappings require predictable access latency, so avoid
	 * incurring periodic faults.
	 */
	if (vma_is_dax(vma))
		return false;

#ifndef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
	if (vma->vm_flags & VM_HUGETLB)
		return false;
#endif

	/*
	 * Migration allocates pages in the highest zone. If we cannot
	 * do so then migration (at least from node to node) is not
	 * possible.
	 */
	if (vma->vm_file &&
		gfp_zone(mapping_gfp_mask(vma->vm_file->f_mapping))
								< policy_zone)
			return false;
	return true;
}

extern int mpol_misplaced(struct page *, struct vm_area_struct *, unsigned long);
extern void mpol_put_task_policy(struct task_struct *);

#else

struct mempolicy {};

static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b)
{
	return true;
}

static inline void mpol_put(struct mempolicy *p)
{
}

static inline void mpol_cond_put(struct mempolicy *pol)
{
}

static inline void mpol_get(struct mempolicy *pol)
{
}

struct shared_policy {};

static inline void mpol_shared_policy_init(struct shared_policy *sp,
						struct mempolicy *mpol)
{
}

static inline void mpol_free_shared_policy(struct shared_policy *p)
{
}

static inline struct mempolicy *
mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx)
{
	return NULL;
}

#define vma_policy(vma) NULL

static inline int
vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst)
{
	return 0;
}

static inline void numa_policy_init(void)
{
}

static inline void numa_default_policy(void)
{
}

static inline void mpol_rebind_task(struct task_struct *tsk,
				const nodemask_t *new)
{
}

static inline void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new)
{
}

static inline int huge_node(struct vm_area_struct *vma,
				unsigned long addr, gfp_t gfp_flags,
				struct mempolicy **mpol, nodemask_t **nodemask)
{
	*mpol = NULL;
	*nodemask = NULL;
	return 0;
}

static inline bool init_nodemask_of_mempolicy(nodemask_t *m)
{
	return false;
}

static inline int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
				   const nodemask_t *to, int flags)
{
	return 0;
}

static inline void check_highest_zone(int k)
{
}

#ifdef CONFIG_TMPFS
static inline int mpol_parse_str(char *str, struct mempolicy **mpol)
{
	return 1;	/* error */
}
#endif

static inline int mpol_misplaced(struct page *page, struct vm_area_struct *vma,
				 unsigned long address)
{
	return -1; /* no node preference */
}

static inline void mpol_put_task_policy(struct task_struct *task)
{
}
#endif /* CONFIG_NUMA */
#endif