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
|
#include <linux/mm.h>
#include <linux/mm_event.h>
#include <linux/sched.h>
#include <linux/vmalloc.h>
#include <linux/seq_file.h>
#include <linux/debugfs.h>
#define CREATE_TRACE_POINTS
#include <trace/events/mm_event.h>
/* msec */
static unsigned long period_ms __read_mostly = 500;
static unsigned long vmstat_period_ms __read_mostly = 1000;
static unsigned long vmstat_next_period;
static DEFINE_SPINLOCK(vmstat_lock);
static DEFINE_RWLOCK(period_lock);
void mm_event_task_init(struct task_struct *tsk)
{
memset(tsk->mm_event, 0, sizeof(tsk->mm_event));
tsk->next_period = 0;
}
static void record_vmstat(void)
{
int cpu;
struct mm_event_vmstat vmstat;
if (time_is_after_jiffies(vmstat_next_period))
return;
/* Need double check under the lock */
spin_lock(&vmstat_lock);
if (time_is_after_jiffies(vmstat_next_period)) {
spin_unlock(&vmstat_lock);
return;
}
vmstat_next_period = jiffies + msecs_to_jiffies(vmstat_period_ms);
spin_unlock(&vmstat_lock);
memset(&vmstat, 0, sizeof(vmstat));
vmstat.free = global_zone_page_state(NR_FREE_PAGES);
vmstat.slab = global_node_page_state(NR_SLAB_RECLAIMABLE) +
global_node_page_state(NR_SLAB_UNRECLAIMABLE);
vmstat.file = global_node_page_state(NR_ACTIVE_FILE) +
global_node_page_state(NR_INACTIVE_FILE);
vmstat.anon = global_node_page_state(NR_ACTIVE_ANON) +
global_node_page_state(NR_INACTIVE_ANON);
vmstat.ion = global_node_page_state(NR_ION_HEAP);
vmstat.ws_refault = global_node_page_state(WORKINGSET_REFAULT);
vmstat.ws_activate = global_node_page_state(WORKINGSET_ACTIVATE);
vmstat.mapped = global_node_page_state(NR_FILE_MAPPED);
for_each_online_cpu(cpu) {
struct vm_event_state *this = &per_cpu(vm_event_states, cpu);
/* sectors to kbytes for PGPGIN/PGPGOUT */
vmstat.pgin += this->event[PGPGIN] / 2;
vmstat.pgout += this->event[PGPGOUT] / 2;
vmstat.swpin += this->event[PSWPIN];
vmstat.swpout += this->event[PSWPOUT];
vmstat.reclaim_steal += this->event[PGSTEAL_DIRECT] +
this->event[PGSTEAL_KSWAPD];
vmstat.reclaim_scan += this->event[PGSCAN_DIRECT] +
this->event[PGSCAN_KSWAPD];
vmstat.compact_scan += this->event[COMPACTFREE_SCANNED] +
this->event[COMPACTMIGRATE_SCANNED];
}
trace_mm_event_vmstat_record(&vmstat);
}
static void record_stat(void)
{
int i;
if (time_is_after_jiffies(current->next_period))
return;
read_lock(&period_lock);
current->next_period = jiffies + msecs_to_jiffies(period_ms);
read_unlock(&period_lock);
for (i = 0; i < MM_TYPE_NUM; i++) {
if (current->mm_event[i].count == 0)
continue;
trace_mm_event_record(i, ¤t->mm_event[i]);
memset(¤t->mm_event[i], 0,
sizeof(struct mm_event_task));
}
record_vmstat();
}
void mm_event_start(ktime_t *time)
{
*time = ktime_get();
}
void mm_event_end(enum mm_event_type event, ktime_t start)
{
s64 elapsed = ktime_us_delta(ktime_get(), start);
current->mm_event[event].count++;
current->mm_event[event].accm_lat += elapsed;
if (elapsed > current->mm_event[event].max_lat)
current->mm_event[event].max_lat = elapsed;
record_stat();
}
EXPORT_SYMBOL_GPL(mm_event_end);
void mm_event_count(enum mm_event_type event, int count)
{
current->mm_event[event].count += count;
record_stat();
}
EXPORT_SYMBOL_GPL(mm_event_count);
static struct dentry *mm_event_root;
static int period_ms_set(void *data, u64 val)
{
if (val < 1 || val > ULONG_MAX)
return -EINVAL;
write_lock(&period_lock);
period_ms = (unsigned long)val;
write_unlock(&period_lock);
return 0;
}
static int period_ms_get(void *data, u64 *val)
{
read_lock(&period_lock);
*val = period_ms;
read_unlock(&period_lock);
return 0;
}
static int vmstat_period_ms_set(void *data, u64 val)
{
if (val < 1 || val > ULONG_MAX)
return -EINVAL;
spin_lock(&vmstat_lock);
vmstat_period_ms = (unsigned long)val;
spin_unlock(&vmstat_lock);
return 0;
}
static int vmstat_period_ms_get(void *data, u64 *val)
{
spin_lock(&vmstat_lock);
*val = vmstat_period_ms;
spin_unlock(&vmstat_lock);
return 0;
}
DEFINE_SIMPLE_ATTRIBUTE(period_ms_operations, period_ms_get,
period_ms_set, "%llu\n");
DEFINE_SIMPLE_ATTRIBUTE(vmstat_period_ms_operations, vmstat_period_ms_get,
vmstat_period_ms_set, "%llu\n");
static int __init mm_event_init(void)
{
struct dentry *entry;
mm_event_root = debugfs_create_dir("mm_event", NULL);
if (!mm_event_root) {
pr_warn("debugfs dir <mm_event> creation failed\n");
return PTR_ERR(mm_event_root);
}
entry = debugfs_create_file("period_ms", 0644,
mm_event_root, NULL, &period_ms_operations);
if (IS_ERR(entry)) {
pr_warn("debugfs file mm_event_task creation failed\n");
debugfs_remove_recursive(mm_event_root);
return PTR_ERR(entry);
}
entry = debugfs_create_file("vmstat_period_ms", 0644,
mm_event_root, NULL, &vmstat_period_ms_operations);
if (IS_ERR(entry)) {
pr_warn("debugfs file vmstat_mm_event_task creation failed\n");
debugfs_remove_recursive(mm_event_root);
return PTR_ERR(entry);
}
return 0;
}
subsys_initcall(mm_event_init);
|
