summaryrefslogtreecommitdiff
path: root/include/linux/mempolicy.h
blob: b0fab9e80655b919d65e55496bb9677daa3884bb (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
315
316
317
318
319
#ifndef _LINUX_MEMPOLICY_H
#define _LINUX_MEMPOLICY_H 1

#include <linux/errno.h>

/*
 * NUMA memory policies for Linux.
 * Copyright 2003,2004 Andi Kleen SuSE Labs
 */

/*
 * Both the MPOL_* mempolicy mode and the MPOL_F_* optional mode flags are
 * passed by the user to either set_mempolicy() or mbind() in an 'int' actual.
 * The MPOL_MODE_FLAGS macro determines the legal set of optional mode flags.
 */

/* Policies */
enum {
	MPOL_DEFAULT,
	MPOL_PREFERRED,
	MPOL_BIND,
	MPOL_INTERLEAVE,
	MPOL_MAX,	/* always last member of enum */
};

/* Flags for set_mempolicy */
#define MPOL_F_STATIC_NODES	(1 << 15)
#define MPOL_F_RELATIVE_NODES	(1 << 14)

/*
 * MPOL_MODE_FLAGS is the union of all possible optional mode flags passed to
 * either set_mempolicy() or mbind().
 */
#define MPOL_MODE_FLAGS	(MPOL_F_STATIC_NODES | MPOL_F_RELATIVE_NODES)

/* Flags for get_mempolicy */
#define MPOL_F_NODE	(1<<0)	/* return next IL mode instead of node mask */
#define MPOL_F_ADDR	(1<<1)	/* look up vma using address */
#define MPOL_F_MEMS_ALLOWED (1<<2) /* return allowed memories */

/* Flags for mbind */
#define MPOL_MF_STRICT	(1<<0)	/* Verify existing pages in the mapping */
#define MPOL_MF_MOVE	(1<<1)	/* Move pages owned by this process to conform to mapping */
#define MPOL_MF_MOVE_ALL (1<<2)	/* Move every page to conform to mapping */
#define MPOL_MF_INTERNAL (1<<3)	/* Internal flags start here */

/*
 * Internal flags that share the struct mempolicy flags word with
 * "mode flags".  These flags are allocated from bit 0 up, as they
 * are never OR'ed into the mode in mempolicy API arguments.
 */
#define MPOL_F_SHARED  (1 << 0)	/* identify shared policies */
#define MPOL_F_LOCAL   (1 << 1)	/* preferred local allocation */

#ifdef __KERNEL__

#include <linux/mmzone.h>
#include <linux/slab.h>
#include <linux/rbtree.h>
#include <linux/spinlock.h>
#include <linux/nodemask.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_cond_copy(struct mempolicy *tompol,
					  struct mempolicy *frompol);
static inline struct mempolicy *mpol_cond_copy(struct mempolicy *tompol,
						struct mempolicy *frompol)
{
	if (!frompol)
		return frompol;
	return __mpol_cond_copy(tompol, frompol);
}

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)
#define vma_set_policy(vma, pol) ((vma)->vm_policy = (pol))

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

extern int __mpol_equal(struct mempolicy *a, struct mempolicy *b);
static inline int mpol_equal(struct mempolicy *a, struct mempolicy *b)
{
	if (a == b)
		return 1;
	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;
	spinlock_t lock;
};

void mpol_shared_policy_init(struct shared_policy *info, unsigned short mode,
				unsigned short flags, nodemask_t *nodes);
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);

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 void mpol_fix_fork_child_flag(struct task_struct *p);

extern struct zonelist *huge_zonelist(struct vm_area_struct *vma,
				unsigned long addr, gfp_t gfp_flags,
				struct mempolicy **mpol, nodemask_t **nodemask);
extern unsigned slab_node(struct mempolicy *policy);

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_nodes, const nodemask_t *to_nodes, int flags);

#else

struct mempolicy {};

static inline int mpol_equal(struct mempolicy *a, struct mempolicy *b)
{
	return 1;
}

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

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

static inline struct mempolicy *mpol_cond_copy(struct mempolicy *to,
						struct mempolicy *from)
{
	return from;
}

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

static inline struct mempolicy *mpol_dup(struct mempolicy *old)
{
	return NULL;
}

struct shared_policy {};

static inline int mpol_set_shared_policy(struct shared_policy *info,
					struct vm_area_struct *vma,
					struct mempolicy *new)
{
	return -EINVAL;
}

static inline void mpol_shared_policy_init(struct shared_policy *info,
		unsigned short mode, unsigned short flags, nodemask_t *nodes)
{
}

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
#define vma_set_policy(vma, pol) do {} while(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 void mpol_fix_fork_child_flag(struct task_struct *p)
{
}

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

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

static inline void check_highest_zone(int k)
{
}
#endif /* CONFIG_NUMA */
#endif /* __KERNEL__ */

#endif