aboutsummaryrefslogtreecommitdiffstats
path: root/include/linux/vmstat.h
blob: 461c0119664ff88d2bf8797f2541ccae74ce0698 (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
#ifndef _LINUX_VMSTAT_H
#define _LINUX_VMSTAT_H

#include <linux/types.h>
#include <linux/percpu.h>
#include <linux/mm.h>
#include <linux/mmzone.h>
#include <asm/atomic.h>

#ifdef CONFIG_ZONE_DMA
#define DMA_ZONE(xx) xx##_DMA,
#else
#define DMA_ZONE(xx)
#endif

#ifdef CONFIG_ZONE_DMA32
#define DMA32_ZONE(xx) xx##_DMA32,
#else
#define DMA32_ZONE(xx)
#endif

#ifdef CONFIG_HIGHMEM
#define HIGHMEM_ZONE(xx) , xx##_HIGH
#else
#define HIGHMEM_ZONE(xx)
#endif


#define FOR_ALL_ZONES(xx) DMA_ZONE(xx) DMA32_ZONE(xx) xx##_NORMAL HIGHMEM_ZONE(xx) , xx##_MOVABLE

enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
		FOR_ALL_ZONES(PGALLOC),
		PGFREE, PGACTIVATE, PGDEACTIVATE,
		PGFAULT, PGMAJFAULT,
		FOR_ALL_ZONES(PGREFILL),
		FOR_ALL_ZONES(PGSTEAL),
		FOR_ALL_ZONES(PGSCAN_KSWAPD),
		FOR_ALL_ZONES(PGSCAN_DIRECT),
#ifdef CONFIG_NUMA
		PGSCAN_ZONE_RECLAIM_FAILED,
#endif
		PGINODESTEAL, SLABS_SCANNED, KSWAPD_STEAL, KSWAPD_INODESTEAL,
		KSWAPD_LOW_WMARK_HIT_QUICKLY, KSWAPD_HIGH_WMARK_HIT_QUICKLY,
		KSWAPD_SKIP_CONGESTION_WAIT,
		PAGEOUTRUN, ALLOCSTALL, PGROTATED,
#ifdef CONFIG_COMPACTION
		COMPACTBLOCKS, COMPACTPAGES, COMPACTPAGEFAILED,
		COMPACTSTALL, COMPACTFAIL, COMPACTSUCCESS,
#endif
#ifdef CONFIG_HUGETLB_PAGE
		HTLB_BUDDY_PGALLOC, HTLB_BUDDY_PGALLOC_FAIL,
#endif
		UNEVICTABLE_PGCULLED,	/* culled to noreclaim list */
		UNEVICTABLE_PGSCANNED,	/* scanned for reclaimability */
		UNEVICTABLE_PGRESCUED,	/* rescued from noreclaim list */
		UNEVICTABLE_PGMLOCKED,
		UNEVICTABLE_PGMUNLOCKED,
		UNEVICTABLE_PGCLEARED,	/* on COW, page truncate */
		UNEVICTABLE_PGSTRANDED,	/* unable to isolate on unlock */
		UNEVICTABLE_MLOCKFREED,
		NR_VM_EVENT_ITEMS
};

extern int sysctl_stat_interval;

#ifdef CONFIG_VM_EVENT_COUNTERS
/*
 * Light weight per cpu counter implementation.
 *
 * Counters should only be incremented and no critical kernel component
 * should rely on the counter values.
 *
 * Counters are handled completely inline. On many platforms the code
 * generated will simply be the increment of a global address.
 */

struct vm_event_state {
	unsigned long event[NR_VM_EVENT_ITEMS];
};

DECLARE_PER_CPU(struct vm_event_state, vm_event_states);

static inline void __count_vm_event(enum vm_event_item item)
{
	__this_cpu_inc(vm_event_states.event[item]);
}

static inline void count_vm_event(enum vm_event_item item)
{
	this_cpu_inc(vm_event_states.event[item]);
}

static inline void __count_vm_events(enum vm_event_item item, long delta)
{
	__this_cpu_add(vm_event_states.event[item], delta);
}

static inline void count_vm_events(enum vm_event_item item, long delta)
{
	this_cpu_add(vm_event_states.event[item], delta);
}

extern void all_vm_events(unsigned long *);
#ifdef CONFIG_HOTPLUG
extern void vm_events_fold_cpu(int cpu);
#else
static inline void vm_events_fold_cpu(int cpu)
{
}
#endif

#else

/* Disable counters */
static inline void count_vm_event(enum vm_event_item item)
{
}
static inline void count_vm_events(enum vm_event_item item, long delta)
{
}
static inline void __count_vm_event(enum vm_event_item item)
{
}
static inline void __count_vm_events(enum vm_event_item item, long delta)
{
}
static inline void all_vm_events(unsigned long *ret)
{
}
static inline void vm_events_fold_cpu(int cpu)
{
}

#endif /* CONFIG_VM_EVENT_COUNTERS */

#define __count_zone_vm_events(item, zone, delta) \
		__count_vm_events(item##_NORMAL - ZONE_NORMAL + \
		zone_idx(zone), delta)

/*
 * Zone based page accounting with per cpu differentials.
 */
extern atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];

static inline void zone_page_state_add(long x, struct zone *zone,
				 enum zone_stat_item item)
{
	atomic_long_add(x, &zone->vm_stat[item]);
	atomic_long_add(x, &vm_stat[item]);
}

static inline unsigned long global_page_state(enum zone_stat_item item)
{
	long x = atomic_long_read(&vm_stat[item]);
#ifdef CONFIG_SMP
	if (x < 0)
		x = 0;
#endif
	return x;
}

static inline unsigned long zone_page_state(struct zone *zone,
					enum zone_stat_item item)
{
	long x = atomic_long_read(&zone->vm_stat[item]);
#ifdef CONFIG_SMP
	if (x < 0)
		x = 0;
#endif
	return x;
}

/*
 * More accurate version that also considers the currently pending
 * deltas. For that we need to loop over all cpus to find the current
 * deltas. There is no synchronization so the result cannot be
 * exactly accurate either.
 */
static inline unsigned long zone_page_state_snapshot(struct zone *zone,
					enum zone_stat_item item)
{
	long x = atomic_long_read(&zone->vm_stat[item]);

#ifdef CONFIG_SMP
	int cpu;
	for_each_online_cpu(cpu)
		x += per_cpu_ptr(zone->pageset, cpu)->vm_stat_diff[item];

	if (x < 0)
		x = 0;
#endif
	return x;
}

extern unsigned long global_reclaimable_pages(void);
extern unsigned long zone_reclaimable_pages(struct zone *zone);

#ifdef CONFIG_NUMA
/*
 * Determine the per node value of a stat item. This function
 * is called frequently in a NUMA machine, so try to be as
 * frugal as possible.
 */
static inline unsigned long node_page_state(int node,
				 enum zone_stat_item item)
{
	struct zone *zones = NODE_DATA(node)->node_zones;

	return
#ifdef CONFIG_ZONE_DMA
		zone_page_state(&zones[ZONE_DMA], item) +
#endif
#ifdef CONFIG_ZONE_DMA32
		zone_page_state(&zones[ZONE_DMA32], item) +
#endif
#ifdef CONFIG_HIGHMEM
		zone_page_state(&zones[ZONE_HIGHMEM], item) +
#endif
		zone_page_state(&zones[ZONE_NORMAL], item) +
		zone_page_state(&zones[ZONE_MOVABLE], item);
}

extern void zone_statistics(struct zone *, struct zone *, gfp_t gfp);

#else

#define node_page_state(node, item) global_page_state(item)
#define zone_statistics(_zl, _z, gfp) do { } while (0)

#endif /* CONFIG_NUMA */

#define add_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, __d)
#define sub_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, -(__d))

static inline void zap_zone_vm_stats(struct zone *zone)
{
	memset(zone->vm_stat, 0, sizeof(zone->vm_stat));
}

extern void inc_zone_state(struct zone *, enum zone_stat_item);

#ifdef CONFIG_SMP
void __mod_zone_page_state(struct zone *, enum zone_stat_item item, int);
void __inc_zone_page_state(struct page *, enum zone_stat_item);
void __dec_zone_page_state(struct page *, enum zone_stat_item);

void mod_zone_page_state(struct zone *, enum zone_stat_item, int);
void inc_zone_page_state(struct page *, enum zone_stat_item);
void dec_zone_page_state(struct page *, enum zone_stat_item);

extern void inc_zone_state(struct zone *, enum zone_stat_item);
extern void __inc_zone_state(struct zone *, enum zone_stat_item);
extern void dec_zone_state(struct zone *, enum zone_stat_item);
extern void __dec_zone_state(struct zone *, enum zone_stat_item);

void refresh_cpu_vm_stats(int);

int calculate_pressure_threshold(struct zone *zone);
int calculate_normal_threshold(struct zone *zone);
void set_pgdat_percpu_threshold(pg_data_t *pgdat,
				int (*calculate_pressure)(struct zone *));
#else /* CONFIG_SMP */

/*
 * We do not maintain differentials in a single processor configuration.
 * The functions directly modify the zone and global counters.
 */
static inline void __mod_zone_page_state(struct zone *zone,
			enum zone_stat_item item, int delta)
{
	zone_page_state_add(delta, zone, item);
}

static inline void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
{
	atomic_long_inc(&zone->vm_stat[item]);
	atomic_long_inc(&vm_stat[item]);
}

static inline void __inc_zone_page_state(struct page *page,
			enum zone_stat_item item)
{
	__inc_zone_state(page_zone(page), item);
}

static inline void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
{
	atomic_long_dec(&zone->vm_stat[item]);
	atomic_long_dec(&vm_stat[item]);
}

static inline void __dec_zone_page_state(struct page *page,
			enum zone_stat_item item)
{
	__dec_zone_state(page_zone(page), item);
}

/*
 * We only use atomic operations to update counters. So there is no need to
 * disable interrupts.
 */
#define inc_zone_page_state __inc_zone_page_state
#define dec_zone_page_state __dec_zone_page_state
#define mod_zone_page_state __mod_zone_page_state

#define set_pgdat_percpu_threshold(pgdat, callback) { }

static inline void refresh_cpu_vm_stats(int cpu) { }
#endif

#endif /* _LINUX_VMSTAT_H */