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
|
/* drivers/misc/lowmemorykiller.c
*
* The lowmemorykiller driver lets user-space specify a set of memory thresholds
* where processes with a range of oom_adj values will get killed. Specify the
* minimum oom_adj values in /sys/module/lowmemorykiller/parameters/adj and the
* number of free pages in /sys/module/lowmemorykiller/parameters/minfree. Both
* files take a comma separated list of numbers in ascending order.
*
* For example, write "0,8" to /sys/module/lowmemorykiller/parameters/adj and
* "1024,4096" to /sys/module/lowmemorykiller/parameters/minfree to kill
* processes with a oom_adj value of 8 or higher when the free memory drops
* below 4096 pages and kill processes with a oom_adj value of 0 or higher
* when the free memory drops below 1024 pages.
*
* The driver considers memory used for caches to be free, but if a large
* percentage of the cached memory is locked this can be very inaccurate
* and processes may not get killed until the normal oom killer is triggered.
*
* Copyright (C) 2007-2008 Google, Inc.
*
* This software is licensed under the terms of the GNU General Public
* License version 2, as published by the Free Software Foundation, and
* may be copied, distributed, and modified under those terms.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
*/
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/oom.h>
#include <linux/sched.h>
#include <linux/rcupdate.h>
#include <linux/notifier.h>
#define ENHANCED_LMK_ROUTINE
#ifdef ENHANCED_LMK_ROUTINE
#define LOWMEM_DEATHPENDING_DEPTH 3
#endif
static uint32_t lowmem_debug_level = 2;
static int lowmem_adj[6] = {
0,
1,
6,
12,
};
static int lowmem_adj_size = 4;
static size_t lowmem_minfree[6] = {
3 * 512, /* 6MB */
2 * 1024, /* 8MB */
4 * 1024, /* 16MB */
16 * 1024, /* 64MB */
};
static int lowmem_minfree_size = 4;
#ifdef ENHANCED_LMK_ROUTINE
static struct task_struct *lowmem_deathpending[LOWMEM_DEATHPENDING_DEPTH] = {NULL,};
#else
static struct task_struct *lowmem_deathpending;
#endif
static unsigned long lowmem_deathpending_timeout;
#define lowmem_print(level, x...) \
do { \
if (lowmem_debug_level >= (level)) \
printk(x); \
} while (0)
static int
task_notify_func(struct notifier_block *self, unsigned long val, void *data);
static struct notifier_block task_nb = {
.notifier_call = task_notify_func,
};
static int
task_notify_func(struct notifier_block *self, unsigned long val, void *data)
{
struct task_struct *task = data;
#ifdef ENHANCED_LMK_ROUTINE
int i = 0;
for (i = 0; i < LOWMEM_DEATHPENDING_DEPTH; i++)
if (task == lowmem_deathpending[i]) {
lowmem_deathpending[i] = NULL;
break;
}
#else
if (task == lowmem_deathpending)
lowmem_deathpending = NULL;
#endif
return NOTIFY_OK;
}
static int lowmem_shrink(struct shrinker *s, struct shrink_control *sc)
{
struct task_struct *tsk;
#ifdef ENHANCED_LMK_ROUTINE
struct task_struct *selected[LOWMEM_DEATHPENDING_DEPTH] = {NULL,};
#else
struct task_struct *selected = NULL;
#endif
int rem = 0;
int tasksize;
int i;
int min_adj = OOM_ADJUST_MAX + 1;
#ifdef ENHANCED_LMK_ROUTINE
int selected_tasksize[LOWMEM_DEATHPENDING_DEPTH] = {0,};
int selected_oom_adj[LOWMEM_DEATHPENDING_DEPTH] = {OOM_ADJUST_MAX,};
int all_selected_oom = 0;
int max_selected_oom_idx = 0;
#else
int selected_tasksize = 0;
int selected_oom_adj;
#endif
int array_size = ARRAY_SIZE(lowmem_adj);
#ifndef CONFIG_DMA_CMA
int other_free = global_page_state(NR_FREE_PAGES);
#else
int other_free = global_page_state(NR_FREE_PAGES) -
global_page_state(NR_FREE_CMA_PAGES);
#endif
int other_file = global_page_state(NR_FILE_PAGES) -
global_page_state(NR_SHMEM);
/*
* If we already have a death outstanding, then
* bail out right away; indicating to vmscan
* that we have nothing further to offer on
* this pass.
*
*/
#ifdef ENHANCED_LMK_ROUTINE
for (i = 0; i < LOWMEM_DEATHPENDING_DEPTH; i++) {
if (lowmem_deathpending[i] &&
time_before_eq(jiffies, lowmem_deathpending_timeout))
return 0;
}
#else
if (lowmem_deathpending &&
time_before_eq(jiffies, lowmem_deathpending_timeout))
return 0;
#endif
if (lowmem_adj_size < array_size)
array_size = lowmem_adj_size;
if (lowmem_minfree_size < array_size)
array_size = lowmem_minfree_size;
for (i = 0; i < array_size; i++) {
if (other_free < lowmem_minfree[i] &&
other_file < lowmem_minfree[i]) {
min_adj = lowmem_adj[i];
break;
}
}
if (sc->nr_to_scan > 0)
lowmem_print(3, "lowmem_shrink %lu, %x, ofree %d %d, ma %d\n",
sc->nr_to_scan, sc->gfp_mask, other_free,
other_file, min_adj);
rem = global_page_state(NR_ACTIVE_ANON) +
global_page_state(NR_ACTIVE_FILE) +
global_page_state(NR_INACTIVE_ANON) +
global_page_state(NR_INACTIVE_FILE);
if (sc->nr_to_scan <= 0 || min_adj == OOM_ADJUST_MAX + 1) {
lowmem_print(5, "lowmem_shrink %lu, %x, return %d\n",
sc->nr_to_scan, sc->gfp_mask, rem);
return rem;
}
#ifdef ENHANCED_LMK_ROUTINE
for (i = 0; i < LOWMEM_DEATHPENDING_DEPTH; i++)
selected_oom_adj[i] = min_adj;
#else
selected_oom_adj = min_adj;
#endif
rcu_read_lock();
for_each_process(tsk) {
struct task_struct *p;
int oom_adj;
#ifdef ENHANCED_LMK_ROUTINE
int is_exist_oom_task = 0;
#endif
if (tsk->flags & PF_KTHREAD)
continue;
p = find_lock_task_mm(tsk);
if (!p)
continue;
oom_adj = p->signal->oom_adj;
if (oom_adj < min_adj) {
task_unlock(p);
continue;
}
tasksize = get_mm_rss(p->mm);
task_unlock(p);
if (tasksize <= 0)
continue;
#ifdef ENHANCED_LMK_ROUTINE
if (all_selected_oom < LOWMEM_DEATHPENDING_DEPTH) {
for (i = 0; i < LOWMEM_DEATHPENDING_DEPTH; i++) {
if (!selected[i]) {
is_exist_oom_task = 1;
max_selected_oom_idx = i;
break;
}
}
} else if (selected_oom_adj[max_selected_oom_idx] < oom_adj ||
(selected_oom_adj[max_selected_oom_idx] == oom_adj &&
selected_tasksize[max_selected_oom_idx] < tasksize)) {
is_exist_oom_task = 1;
}
if (is_exist_oom_task) {
selected[max_selected_oom_idx] = p;
selected_tasksize[max_selected_oom_idx] = tasksize;
selected_oom_adj[max_selected_oom_idx] = oom_adj;
if (all_selected_oom < LOWMEM_DEATHPENDING_DEPTH)
all_selected_oom++;
if (all_selected_oom == LOWMEM_DEATHPENDING_DEPTH) {
for (i = 0; i < LOWMEM_DEATHPENDING_DEPTH; i++) {
if (selected_oom_adj[i] < selected_oom_adj[max_selected_oom_idx])
max_selected_oom_idx = i;
else if (selected_oom_adj[i] == selected_oom_adj[max_selected_oom_idx] &&
selected_tasksize[i] < selected_tasksize[max_selected_oom_idx])
max_selected_oom_idx = i;
}
}
lowmem_print(2, "select %d (%s), adj %d, size %d, to kill\n",
p->pid, p->comm, oom_adj, tasksize);
}
#else
if (selected) {
if (oom_adj < selected_oom_adj)
continue;
if (oom_adj == selected_oom_adj &&
tasksize <= selected_tasksize)
continue;
}
selected = p;
selected_tasksize = tasksize;
selected_oom_adj = oom_adj;
lowmem_print(2, "select %d (%s), adj %d, size %d, to kill\n",
p->pid, p->comm, oom_adj, tasksize);
#endif
}
#ifdef ENHANCED_LMK_ROUTINE
for (i = 0; i < LOWMEM_DEATHPENDING_DEPTH; i++) {
if (selected[i]) {
lowmem_print(1, "send sigkill to %d (%s), adj %d, size %d\n",
selected[i]->pid, selected[i]->comm,
selected_oom_adj[i], selected_tasksize[i]);
lowmem_deathpending[i] = selected[i];
lowmem_deathpending_timeout = jiffies + HZ;
force_sig(SIGKILL, selected[i]);
rem -= selected_tasksize[i];
}
}
#else
if (selected) {
lowmem_print(1, "send sigkill to %d (%s), adj %d, size %d\n",
selected->pid, selected->comm,
selected_oom_adj, selected_tasksize);
lowmem_deathpending = selected;
lowmem_deathpending_timeout = jiffies + HZ;
send_sig(SIGKILL, selected, 0);
rem -= selected_tasksize;
}
#endif
lowmem_print(4, "lowmem_shrink %lu, %x, return %d\n",
sc->nr_to_scan, sc->gfp_mask, rem);
rcu_read_unlock();
return rem;
}
static struct shrinker lowmem_shrinker = {
.shrink = lowmem_shrink,
.seeks = DEFAULT_SEEKS * 16
};
static int __init lowmem_init(void)
{
task_free_register(&task_nb);
register_shrinker(&lowmem_shrinker);
return 0;
}
static void __exit lowmem_exit(void)
{
unregister_shrinker(&lowmem_shrinker);
task_free_unregister(&task_nb);
}
module_param_named(cost, lowmem_shrinker.seeks, int, S_IRUGO | S_IWUSR);
module_param_array_named(adj, lowmem_adj, int, &lowmem_adj_size,
S_IRUGO | S_IWUSR);
module_param_array_named(minfree, lowmem_minfree, uint, &lowmem_minfree_size,
S_IRUGO | S_IWUSR);
module_param_named(debug_level, lowmem_debug_level, uint, S_IRUGO | S_IWUSR);
module_init(lowmem_init);
module_exit(lowmem_exit);
MODULE_LICENSE("GPL");
|