summaryrefslogtreecommitdiffstats
path: root/include/linux/mempolicy.h
blob: 66247eff24a053227d7915342c2fe2a2dfc621a8 (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
#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
 */

/* Policies */
#define MPOL_DEFAULT	0
#define MPOL_PREFERRED	1
#define MPOL_BIND	2
#define MPOL_INTERLEAVE	3

#define MPOL_MAX MPOL_INTERLEAVE

/* Flags for get_mem_policy */
#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 */

/* 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 */

#ifdef __KERNEL__

#include <linux/config.h>
#include <linux/mmzone.h>
#include <linux/slab.h>
#include <linux/rbtree.h>
#include <linux/spinlock.h>
#include <linux/nodemask.h>

struct vm_area_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:
 * When policy is MPOL_BIND v.zonelist is kmalloc'ed and must be kfree'd.
 * All other policies don't have any external state. mpol_free() handles this.
 *
 * Copying policy objects:
 * For MPOL_BIND the zonelist must be always duplicated. mpol_clone() does this.
 */
struct mempolicy {
	atomic_t refcnt;
	short policy; 	/* See MPOL_* above */
	union {
		struct zonelist  *zonelist;	/* bind */
		short 		 preferred_node; /* preferred */
		nodemask_t	 nodes;		/* interleave */
		/* undefined for default */
	} v;
};

/*
 * 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_free(struct mempolicy *pol);
static inline void mpol_free(struct mempolicy *pol)
{
	if (pol)
		__mpol_free(pol);
}

extern struct mempolicy *__mpol_copy(struct mempolicy *pol);
static inline struct mempolicy *mpol_copy(struct mempolicy *pol)
{
	if (pol)
		pol = __mpol_copy(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);
}
#define vma_mpol_equal(a,b) mpol_equal(vma_policy(a), vma_policy(b))

/* Could later add inheritance of the process policy here. */

#define mpol_set_vma_default(vma) ((vma)->vm_policy = NULL)

/*
 * 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;
};

static inline void mpol_shared_policy_init(struct shared_policy *info)
{
	info->root = RB_ROOT;
	spin_lock_init(&info->lock);
}

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_vma_policy(struct task_struct *task,
			struct vm_area_struct *vma, unsigned long addr);

extern void numa_default_policy(void);
extern void numa_policy_init(void);
extern void numa_policy_rebind(const nodemask_t *old, const nodemask_t *new);
extern struct mempolicy default_policy;
extern struct zonelist *huge_zonelist(struct vm_area_struct *vma,
		unsigned long addr);

extern int policy_zone;

static inline void check_highest_zone(int k)
{
	if (k > policy_zone)
		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;
}
#define vma_mpol_equal(a,b) 1

#define mpol_set_vma_default(vma) do {} while(0)

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

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

static inline struct mempolicy *mpol_copy(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)
{
}

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 numa_policy_rebind(const nodemask_t *old,
					const nodemask_t *new)
{
}

static inline struct zonelist *huge_zonelist(struct vm_area_struct *vma,
		unsigned long addr)
{
	return NODE_DATA(0)->node_zonelists + gfp_zone(GFP_HIGHUSER);
}

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