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
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
|
#ifndef _LINUX_VMSTAT_H
#define _LINUX_VMSTAT_H
#include <linux/types.h>
#include <linux/percpu.h>
#include <linux/mmzone.h>
#include <linux/vm_event_item.h>
#include <linux/atomic.h>
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);
/*
* vm counters are allowed to be racy. Use raw_cpu_ops to avoid the
* local_irq_disable overhead.
*/
static inline void __count_vm_event(enum vm_event_item item)
{
raw_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)
{
raw_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 *);
extern void vm_events_fold_cpu(int cpu);
#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 */
#ifdef CONFIG_NUMA_BALANCING
#define count_vm_numa_event(x) count_vm_event(x)
#define count_vm_numa_events(x, y) count_vm_events(x, y)
#else
#define count_vm_numa_event(x) do {} while (0)
#define count_vm_numa_events(x, y) do { (void)(y); } while (0)
#endif /* CONFIG_NUMA_BALANCING */
#ifdef CONFIG_DEBUG_TLBFLUSH
#define count_vm_tlb_event(x) count_vm_event(x)
#define count_vm_tlb_events(x, y) count_vm_events(x, y)
#else
#define count_vm_tlb_event(x) do {} while (0)
#define count_vm_tlb_events(x, y) do { (void)(y); } while (0)
#endif
#ifdef CONFIG_DEBUG_VM_VMACACHE
#define count_vm_vmacache_event(x) count_vm_event(x)
#else
#define count_vm_vmacache_event(x) do {} while (0)
#endif
#define __count_zid_vm_events(item, zid, delta) \
__count_vm_events(item##_NORMAL - ZONE_NORMAL + zid, delta)
/*
* Zone and node-based page accounting with per cpu differentials.
*/
extern atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS];
extern atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS];
extern atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS];
#ifdef CONFIG_NUMA
static inline void zone_numa_state_add(long x, struct zone *zone,
enum numa_stat_item item)
{
atomic_long_add(x, &zone->vm_numa_stat[item]);
atomic_long_add(x, &vm_numa_stat[item]);
}
static inline unsigned long global_numa_state(enum numa_stat_item item)
{
long x = atomic_long_read(&vm_numa_stat[item]);
return x;
}
static inline unsigned long zone_numa_state(struct zone *zone,
enum numa_stat_item item)
{
long x = atomic_long_read(&zone->vm_numa_stat[item]);
return x;
}
#endif /* CONFIG_NUMA */
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_zone_stat[item]);
}
static inline void node_page_state_add(long x, struct pglist_data *pgdat,
enum node_stat_item item)
{
atomic_long_add(x, &pgdat->vm_stat[item]);
atomic_long_add(x, &vm_node_stat[item]);
}
static inline unsigned long global_zone_page_state(enum zone_stat_item item)
{
long x = atomic_long_read(&vm_zone_stat[item]);
#ifdef CONFIG_SMP
if (x < 0)
x = 0;
#endif
return x;
}
static inline unsigned long global_node_page_state(enum node_stat_item item)
{
long x = atomic_long_read(&vm_node_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;
}
static inline unsigned long node_page_state_snapshot(pg_data_t *pgdat,
enum node_stat_item item)
{
long x = atomic_long_read(&pgdat->vm_stat[item]);
#ifdef CONFIG_SMP
int cpu;
for_each_online_cpu(cpu)
x += per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->vm_node_stat_diff[item];
if (x < 0)
x = 0;
#endif
return x;
}
#ifdef CONFIG_NUMA
extern void __inc_numa_state(struct zone *zone, enum numa_stat_item item);
extern unsigned long sum_zone_node_page_state(int node,
enum zone_stat_item item);
extern unsigned long sum_zone_numa_state(int node, enum numa_stat_item item);
extern unsigned long node_page_state(struct pglist_data *pgdat,
enum node_stat_item item);
#else
#define sum_zone_node_page_state(node, item) global_zone_page_state(item)
#define node_page_state(node, item) global_node_page_state(item)
#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))
#define add_node_page_state(__p, __i, __d) mod_node_page_state(__p, __i, __d)
#define sub_node_page_state(__p, __i, __d) mod_node_page_state(__p, __i, -(__d))
#ifdef CONFIG_SMP
void __mod_zone_page_state(struct zone *, enum zone_stat_item item, long);
void __inc_zone_page_state(struct page *, enum zone_stat_item);
void __dec_zone_page_state(struct page *, enum zone_stat_item);
void __mod_node_page_state(struct pglist_data *, enum node_stat_item item, long);
void __inc_node_page_state(struct page *, enum node_stat_item);
void __dec_node_page_state(struct page *, enum node_stat_item);
void mod_zone_page_state(struct zone *, enum zone_stat_item, long);
void inc_zone_page_state(struct page *, enum zone_stat_item);
void dec_zone_page_state(struct page *, enum zone_stat_item);
void mod_node_page_state(struct pglist_data *, enum node_stat_item, long);
void inc_node_page_state(struct page *, enum node_stat_item);
void dec_node_page_state(struct page *, enum node_stat_item);
extern void inc_node_state(struct pglist_data *, enum node_stat_item);
extern void __inc_zone_state(struct zone *, enum zone_stat_item);
extern void __inc_node_state(struct pglist_data *, enum node_stat_item);
extern void dec_zone_state(struct zone *, enum zone_stat_item);
extern void __dec_zone_state(struct zone *, enum zone_stat_item);
extern void __dec_node_state(struct pglist_data *, enum node_stat_item);
void quiet_vmstat(void);
void cpu_vm_stats_fold(int cpu);
void refresh_zone_stat_thresholds(void);
struct ctl_table;
int vmstat_refresh(struct ctl_table *, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
void drain_zonestat(struct zone *zone, struct per_cpu_pageset *);
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, long delta)
{
zone_page_state_add(delta, zone, item);
}
static
|