summaryrefslogtreecommitdiffstats
blob: e7c13e0c8970d69bdbdc34fecbea4c3dab71e2a0 (plain) (blame)
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
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
/*
 * Copyright (C) 2013 The Android Open Source Project
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 *      http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

#define LOG_TAG "lowmemorykiller"

#include <errno.h>
#include <inttypes.h>
#include <pwd.h>
#include <sched.h>
#include <signal.h>
#include <stdbool.h>
#include <stdlib.h>
#include <string.h>
#include <sys/cdefs.h>
#include <sys/epoll.h>
#include <sys/eventfd.h>
#include <sys/mman.h>
#include <sys/socket.h>
#include <sys/sysinfo.h>
#include <sys/types.h>
#include <unistd.h>

#include <cutils/properties.h>
#include <cutils/sockets.h>
#include <lmkd.h>
#include <log/log.h>

/*
 * Define LMKD_TRACE_KILLS to record lmkd kills in kernel traces
 * to profile and correlate with OOM kills
 */
#ifdef LMKD_TRACE_KILLS

#define ATRACE_TAG ATRACE_TAG_ALWAYS
#include <cutils/trace.h>

#define TRACE_KILL_START(pid) ATRACE_INT(__FUNCTION__, pid);
#define TRACE_KILL_END()      ATRACE_INT(__FUNCTION__, 0);

#else /* LMKD_TRACE_KILLS */

#define TRACE_KILL_START(pid)
#define TRACE_KILL_END()

#endif /* LMKD_TRACE_KILLS */

#ifndef __unused
#define __unused __attribute__((__unused__))
#endif

#define MEMCG_SYSFS_PATH "/dev/memcg/"
#define MEMCG_MEMORY_USAGE "/dev/memcg/memory.usage_in_bytes"
#define MEMCG_MEMORYSW_USAGE "/dev/memcg/memory.memsw.usage_in_bytes"
#define ZONEINFO_PATH "/proc/zoneinfo"
#define MEMINFO_PATH "/proc/meminfo"
#define LINE_MAX 128

/* gid containing AID_SYSTEM required */
#define INKERNEL_MINFREE_PATH "/sys/module/lowmemorykiller/parameters/minfree"
#define INKERNEL_ADJ_PATH "/sys/module/lowmemorykiller/parameters/adj"

#define ARRAY_SIZE(x)   (sizeof(x) / sizeof(*(x)))
#define EIGHT_MEGA (1 << 23)

/* Defined as ProcessList.SYSTEM_ADJ in ProcessList.java */
#define SYSTEM_ADJ (-900)

/* default to old in-kernel interface if no memory pressure events */
static bool use_inkernel_interface = true;
static bool has_inkernel_module;

/* memory pressure levels */
enum vmpressure_level {
    VMPRESS_LEVEL_LOW = 0,
    VMPRESS_LEVEL_MEDIUM,
    VMPRESS_LEVEL_CRITICAL,
    VMPRESS_LEVEL_COUNT
};

static const char *level_name[] = {
    "low",
    "medium",
    "critical"
};

struct {
    int64_t min_nr_free_pages; /* recorded but not used yet */
    int64_t max_nr_free_pages;
} low_pressure_mem = { -1, -1 };

static int level_oomadj[VMPRESS_LEVEL_COUNT];
static int mpevfd[VMPRESS_LEVEL_COUNT] = { -1, -1, -1 };
static bool debug_process_killing;
static bool enable_pressure_upgrade;
static int64_t upgrade_pressure;
static int64_t downgrade_pressure;
static bool low_ram_device;
static bool kill_heaviest_task;
static unsigned long kill_timeout_ms;
static bool use_minfree_levels;
static bool per_app_memcg;

/* data required to handle events */
struct event_handler_info {
    int data;
    void (*handler)(int data, uint32_t events);
};

/* data required to handle socket events */
struct sock_event_handler_info {
    int sock;
    struct event_handler_info handler_info;
};

/* max supported number of data connections */
#define MAX_DATA_CONN 2

/* socket event handler data */
static struct sock_event_handler_info ctrl_sock;
static struct sock_event_handler_info data_sock[MAX_DATA_CONN];

/* vmpressure event handler data */
static struct event_handler_info vmpressure_hinfo[VMPRESS_LEVEL_COUNT];

/* 3 memory pressure levels, 1 ctrl listen socket, 2 ctrl data socket */
#define MAX_EPOLL_EVENTS (1 + MAX_DATA_CONN + VMPRESS_LEVEL_COUNT)
static int epollfd;
static int maxevents;

/* OOM score values used by both kernel and framework */
#define OOM_SCORE_ADJ_MIN       (-1000)
#define OOM_SCORE_ADJ_MAX       1000

static int lowmem_adj[MAX_TARGETS];
static int lowmem_minfree[MAX_TARGETS];
static int lowmem_targets_size;

/* Fields to parse in /proc/zoneinfo */
enum zoneinfo_field {
    ZI_NR_FREE_PAGES = 0,
    ZI_NR_FILE_PAGES,
    ZI_NR_SHMEM,
    ZI_NR_UNEVICTABLE,
    ZI_WORKINGSET_REFAULT,
    ZI_HIGH,
    ZI_FIELD_COUNT
};

static const char* const zoneinfo_field_names[ZI_FIELD_COUNT] = {
    "nr_free_pages",
    "nr_file_pages",
    "nr_shmem",
    "nr_unevictable",
    "workingset_refault",
    "high",
};

union zoneinfo {
    struct {
        int64_t nr_free_pages;
        int64_t nr_file_pages;
        int64_t nr_shmem;
        int64_t nr_unevictable;
        int64_t workingset_refault;
        int64_t high;
        /* fields below are calculated rather than read from the file */
        int64_t totalreserve_pages;
    } field;
    int64_t arr[ZI_FIELD_COUNT];
};

/* Fields to parse in /proc/meminfo */
enum meminfo_field {
    MI_NR_FREE_PAGES = 0,
    MI_CACHED,
    MI_SWAP_CACHED,
    MI_BUFFERS,
    MI_SHMEM,
    MI_UNEVICTABLE,
    MI_FREE_SWAP,
    MI_DIRTY,
    MI_FIELD_COUNT
};

static const char* const meminfo_field_names[MI_FIELD_COUNT] = {
    "MemFree:",
    "Cached:",
    "SwapCached:",
    "Buffers:",
    "Shmem:",
    "Unevictable:",
    "SwapFree:",
    "Dirty:",
};

union meminfo {
    struct {
        int64_t nr_free_pages;
        int64_t cached;
        int64_t swap_cached;
        int64_t buffers;
        int64_t shmem;
        int64_t unevictable;
        int64_t free_swap;
        int64_t dirty;
        /* fields below are calculated rather than read from the file */
        int64_t nr_file_pages;
    } field;
    int64_t arr[MI_FIELD_COUNT];
};

enum field_match_result {
    NO_MATCH,
    PARSE_FAIL,
    PARSE_SUCCESS
};

struct adjslot_list {
    struct adjslot_list *next;
    struct adjslot_list *prev;
};

struct proc {
    struct adjslot_list asl;
    int pid;
    uid_t uid;
    int oomadj;
    struct proc *pidhash_next;
};

struct reread_data {
    const char* const filename;
    int fd;
};

#define PIDHASH_SZ 1024
static struct proc *pidhash[PIDHASH_SZ];
#define pid_hashfn(x) ((((x) >> 8) ^ (x)) & (PIDHASH_SZ - 1))

#define ADJTOSLOT(adj) ((adj) + -OOM_SCORE_ADJ_MIN)
static struct adjslot_list procadjslot_list[ADJTOSLOT(OOM_SCORE_ADJ_MAX) + 1];

/* PAGE_SIZE / 1024 */
static long page_k;

static bool parse_int64(const char* str, int64_t* ret) {
    char* endptr;
    long long val = strtoll(str, &endptr, 10);
    if (str == endptr || val > INT64_MAX) {
        return false;
    }
    *ret = (int64_t)val;
    return true;
}

static enum field_match_result match_field(const char* cp, const char* ap,
                                   const char* const field_names[],
                                   int field_count, int64_t* field,
                                   int *field_idx) {
    int64_t val;
    int i;

    for (i = 0; i < field_count; i++) {
        if (!strcmp(cp, field_names[i])) {
            *field_idx = i;
            return parse_int64(ap, field) ? PARSE_SUCCESS : PARSE_FAIL;
        }
    }
    return NO_MATCH;
}

/*
 * Read file content from the beginning up to max_len bytes or EOF
 * whichever happens first.
 */
static ssize_t read_all(int fd, char *buf, size_t max_len)
{
    ssize_t ret = 0;
    off_t offset = 0;

    while (max_len > 0) {
        ssize_t r = TEMP_FAILURE_RETRY(pread(fd, buf, max_len, offset));
        if (r == 0) {
            break;
        }
        if (r == -1) {
            return -1;
        }
        ret += r;
        buf += r;
        offset += r;
        max_len -= r;
    }

    return ret;
}

/*
 * Read a new or already opened file from the beginning.
 * If the file has not been opened yet data->fd should be set to -1.
 * To be used with files which are read often and possibly during high
 * memory pressure to minimize file opening which by itself requires kernel
 * memory allocation and might result in a stall on memory stressed system.
 */
static int reread_file(struct reread_data *data, char *buf, size_t buf_size) {
    ssize_t size;

    if (data->fd == -1) {
        data->fd = open(data->filename, O_RDONLY | O_CLOEXEC);
        if (data->fd == -1) {
            ALOGE("%s open: %s", data->filename, strerror(errno));
            return -1;
        }
    }

    size = read_all(data->fd, buf, buf_size - 1);
    if (size < 0) {
        ALOGE("%s read: %s", data->filename, strerror(errno));
        close(data->fd);
        data->fd = -1;
        return -1;
    }
    ALOG_ASSERT((size_t)size < buf_size - 1, "%s too large", data->filename);
    buf[size] = 0;

    return 0;
}

static struct proc *pid_lookup(int pid) {
    struct proc *procp;

    for (procp = pidhash[pid_hashfn(pid)]; procp && procp->pid != pid;
         procp = procp->pidhash_next)
            ;

    return procp;
}

static void adjslot_insert(struct adjslot_list *head, struct adjslot_list *new)
{
    struct adjslot_list *next = head->next;
    new->prev = head;
    new->next = next;
    next->prev = new;
    head->next = new;
}

static void adjslot_remove(struct adjslot_list *old)
{
    struct adjslot_list *prev = old->prev;
    struct adjslot_list *next = old->next;
    next->prev = prev;
    prev->next = next;
}

static struct adjslot_list *adjslot_tail(struct adjslot_list *head) {
    struct adjslot_list *asl = head->prev;

    return asl == head ? NULL : asl;
}

static void proc_slot(struct proc *procp) {
    int adjslot = ADJTOSLOT(procp->oomadj);

    adjslot_insert(&procadjslot_list[adjslot], &procp->asl);
}

static void proc_unslot(struct proc *procp) {
    adjslot_remove(&procp->asl);
}

static void proc_insert(struct proc *procp) {
    int hval = pid_hashfn(procp->pid);

    procp->pidhash_next = pidhash[hval];
    pidhash[hval] = procp;
    proc_slot(procp);
}

static int pid_remove(int pid) {
    int hval = pid_hashfn(pid);
    struct proc *procp;
    struct proc *prevp;

    for (procp = pidhash[hval], prevp = NULL; procp && procp->pid != pid;
         procp = procp->pidhash_next)
            prevp = procp;

    if (!procp)
        return -1;

    if (!prevp)
        pidhash[hval] = procp->pidhash_next;
    else
        prevp->pidhash_next = procp->pidhash_next;

    proc_unslot(procp);
    free(procp);
    return 0;
}

/*
 * Write a string to a file.
 * Returns false if the file does not exist.
 */
static bool writefilestring(const char *path, const char *s,
                            bool err_if_missing) {
    int fd = open(path, O_WRONLY | O_CLOEXEC);
    ssize_t len = strlen(s);
    ssize_t ret;

    if (fd < 0) {
        if (err_if_missing) {
            ALOGE("Error opening %s; errno=%d", path, errno);
        }
        return false;
    }

    ret = TEMP_FAILURE_RETRY(write(fd, s, len));
    if (ret < 0) {
        ALOGE("Error writing %s; errno=%d", path, errno);
    } else if (ret < len) {
        ALOGE("Short write on %s; length=%zd", path, ret);
    }

    close(fd);
    return true;
}

static void cmd_procprio(LMKD_CTRL_PACKET packet) {
    struct proc *procp;
    char path[80];
    char val[20];
    int soft_limit_mult;
    struct lmk_procprio params;
    bool is_system_server;
    struct passwd *pwdrec;

    lmkd_pack_get_procprio(packet, &params);

    if (params.oomadj < OOM_SCORE_ADJ_MIN ||
        params.oomadj > OOM_SCORE_ADJ_MAX) {
        ALOGE("Invalid PROCPRIO oomadj argument %d", params.oomadj);
        return;
    }

    /* gid containing AID_READPROC required */
    /* CAP_SYS_RESOURCE required */
    /* CAP_DAC_OVERRIDE required */
    snprintf(path, sizeof(path), "/proc/%d/oom_score_adj", params.pid);
    snprintf(val, sizeof(val), "%d", params.oomadj);
    if (!writefilestring(path, val, false)) {
        ALOGW("Failed to open %s; errno=%d: process %d might have been killed",
              path, errno, params.pid);
        /* If this file does not exist the process is dead. */
        return;
    }

    if (use_inkernel_interface) {
        return;
    }

    if (per_app_memcg) {
        if (params.oomadj >= 900) {
            soft_limit_mult = 0;
        } else if (params.oomadj >= 800) {
            soft_limit_mult = 0;
        } else if (params.oomadj >= 700) {
            soft_limit_mult = 0;
        } else if (params.oomadj >= 600) {
            // Launcher should be perceptible, don't kill it.
            params.oomadj = 200;
            soft_limit_mult = 1;
        } else if (params.oomadj >= 500) {
            soft_limit_mult = 0;
        } else if (params.oomadj >= 400) {
            soft_limit_mult = 0;
        } else if (params.oomadj >= 300) {
            soft_limit_mult = 1;
        } else if (params.oomadj >= 200) {
            soft_limit_mult = 2;
        } else if (params.oomadj >= 100) {
            soft_limit_mult = 10;
        } else if (params.oomadj >=   0) {
            soft_limit_mult = 20;
        } else {
            // Persistent processes will have a large
            // soft limit 512MB.
            soft_limit_mult = 64;
        }

        snprintf(path, sizeof(path), MEMCG_SYSFS_PATH
                 "apps/uid_%d/pid_%d/memory.soft_limit_in_bytes",
                 params.uid, params.pid);
        snprintf(val, sizeof(val), "%d", soft_limit_mult * EIGHT_MEGA);

        /*
         * system_server process has no memcg under /dev/memcg/apps but should be
         * registered with lmkd. This is the best way so far to identify it.
         */
        is_system_server = (params.oomadj == SYSTEM_ADJ &&
                            (pwdrec = getpwnam("system")) != NULL &&
                            params.uid == pwdrec->pw_uid);
        writefilestring(path, val, !is_system_server);
    }

    procp = pid_lookup(params.pid);
    if (!procp) {
            procp = malloc(sizeof(struct proc));
            if (!procp) {
                // Oh, the irony.  May need to rebuild our state.
                return;
            }

            procp->pid = params.pid;
            procp->uid = params.uid;
            procp->oomadj = params.oomadj;
            proc_insert(procp);
    } else {
        proc_unslot(procp);
        procp->oomadj = params.oomadj;
        proc_slot(procp);
    }
}

static void cmd_procremove(LMKD_CTRL_PACKET packet) {
    struct lmk_procremove params;

    if (use_inkernel_interface) {
        return;
    }

    lmkd_pack_get_procremove(packet, &params);
    pid_remove(params.pid);
}

static void cmd_target(int ntargets, LMKD_CTRL_PACKET packet) {
    int i;
    struct lmk_target target;

    if (ntargets > (int)ARRAY_SIZE(lowmem_adj))
        return;

    for (i = 0; i < ntargets; i++) {
        lmkd_pack_get_target(packet, i, &target);
        lowmem_minfree[i] = target.minfree;
        lowmem_adj[i] = target.oom_adj_score;
    }

    lowmem_targets_size = ntargets;

    if (has_inkernel_module) {
        char minfreestr[128];
        char killpriostr[128];

        minfreestr[0] = '\0';
        killpriostr[0] = '\0';

        for (i = 0; i < lowmem_targets_size; i++) {
            char val[40];

            if (i) {
                strlcat(minfreestr, ",", sizeof(minfreestr));
                strlcat(killpriostr, ",", sizeof(killpriostr));
            }

            snprintf(val, sizeof(val), "%d", use_inkernel_interface ? lowmem_minfree[i] : 0);
            strlcat(minfreestr, val, sizeof(minfreestr));
            snprintf(val, sizeof(val), "%d", use_inkernel_interface ? lowmem_adj[i] : 0);
            strlcat(killpriostr, val, sizeof(killpriostr));
        }

        writefilestring(INKERNEL_MINFREE_PATH, minfreestr, true);
        writefilestring(INKERNEL_ADJ_PATH, killpriostr, true);
    }
}

static void ctrl_data_close(int dsock_idx) {
    struct epoll_event epev;

    ALOGI("closing lmkd data connection");
    if (epoll_ctl(epollfd, EPOLL_CTL_DEL, data_sock[dsock_idx].sock, &epev) == -1) {
        // Log a warning and keep going
        ALOGW("epoll_ctl for data connection socket failed; errno=%d", errno);
    }
    maxevents--;

    close(data_sock[dsock_idx].sock);
    data_sock[dsock_idx].sock = -1;
}

static int ctrl_data_read(int dsock_idx, char *buf, size_t bufsz) {
    int ret = 0;

    ret = TEMP_FAILURE_RETRY(read(data_sock[dsock_idx].sock, buf, bufsz));

    if (ret == -1) {
        ALOGE("control data socket read failed; errno=%d", errno);
    } else if (ret == 0) {
        ALOGE("Got EOF on control data socket");
        ret = -1;
    }

    return ret;
}

static void ctrl_command_handler(int dsock_idx) {
    LMKD_CTRL_PACKET packet;
    int len;
    enum lmk_cmd cmd;
    int nargs;
    int targets;

    len = ctrl_data_read(dsock_idx, (char *)packet, CTRL_PACKET_MAX_SIZE);
    if (len <= 0)
        return;

    if (len < (int)sizeof(int)) {
        ALOGE("Wrong control socket read length len=%d", len);
        return;
    }

    cmd = lmkd_pack_get_cmd(packet);
    nargs = len / sizeof(int) - 1;
    if (nargs < 0)
        goto wronglen;

    switch(cmd) {
    case LMK_TARGET:
        targets = nargs / 2;
        if (nargs & 0x1 || targets > (int)ARRAY_SIZE(lowmem_adj))
            goto wronglen;
        cmd_target(targets, packet);
        break;
    case LMK_PROCPRIO:
        if (nargs != 3)
            goto wronglen;
        cmd_procprio(packet);
        break;
    case LMK_PROCREMOVE:
        if (nargs != 1)
            goto wronglen;
        cmd_procremove(packet);
        break;
    default:
        ALOGE("Received unknown command code %d", cmd);
        return;
    }

    return;

wronglen:
    ALOGE("Wrong control socket read length cmd=%d len=%d", cmd, len);
}

static void ctrl_data_handler(int data, uint32_t events) {
    if (events & EPOLLIN) {
        ctrl_command_handler(data);
    }
}

static int get_free_dsock() {
    for (int i = 0; i < MAX_DATA_CONN; i++) {
        if (data_sock[i].sock < 0) {
            return i;
        }
    }
    return -1;
}

static void ctrl_connect_handler(int data __unused, uint32_t events __unused) {
    struct epoll_event epev;
    int free_dscock_idx = get_free_dsock();

    if (free_dscock_idx < 0) {
        /*
         * Number of data connections exceeded max supported. This should not
         * happen but if it does we drop all existing connections and accept
         * the new one. This prevents inactive connections from monopolizing
         * data socket and if we drop ActivityManager connection it will
         * immediately reconnect.
         */
        for (int i = 0; i < MAX_DATA_CONN; i++) {
            ctrl_data_close(i);
        }
        free_dscock_idx = 0;
    }

    data_sock[free_dscock_idx].sock = accept(ctrl_sock.sock, NULL, NULL);
    if (data_sock[free_dscock_idx].sock < 0) {
        ALOGE("lmkd control socket accept failed; errno=%d", errno);
        return;
    }

    ALOGI("lmkd data connection established");
    /* use data to store data connection idx */
    data_sock[free_dscock_idx].handler_info.data = free_dscock_idx;
    data_sock[free_dscock_idx].handler_info.handler = ctrl_data_handler;
    epev.events = EPOLLIN;
    epev.data.ptr = (void *)&(data_sock[free_dscock_idx].handler_info);
    if (epoll_ctl(epollfd, EPOLL_CTL_ADD, data_sock[free_dscock_idx].sock, &epev) == -1) {
        ALOGE("epoll_ctl for data connection socket failed; errno=%d", errno);
        ctrl_data_close(free_dscock_idx);
        return;
    }
    maxevents++;
}

/* /prop/zoneinfo parsing routines */
static int64_t zoneinfo_parse_protection(char *cp) {
    int64_t max = 0;
    long long zoneval;
    char *save_ptr;

    for (cp = strtok_r(cp, "(), ", &save_ptr); cp;
         cp = strtok_r(NULL, "), ", &save_ptr)) {
        zoneval = strtoll(cp, &cp, 0);
        if (zoneval > max) {
            max = (zoneval > INT64_MAX) ? INT64_MAX : zoneval;
        }
    }

    return max;
}

static bool zoneinfo_parse_line(char *line, union zoneinfo *zi) {
    char *cp = line;
    char *ap;
    char *save_ptr;
    int64_t val;
    int field_idx;

    cp = strtok_r(line, " ", &save_ptr);
    if (!cp) {
        return true;
    }

    if (!strcmp(cp, "protection:")) {
        ap = strtok_r(NULL, ")", &save_ptr);
    } else {
        ap = strtok_r(NULL, " ", &save_ptr);
    }

    if (!ap) {
        return true;
    }

    switch (match_field(cp, ap, zoneinfo_field_names,
                        ZI_FIELD_COUNT, &val, &field_idx)) {
    case (PARSE_SUCCESS):
        zi->arr[field_idx] += val;
        break;
    case (NO_MATCH):
        if (!strcmp(cp, "protection:")) {
            zi->field.totalreserve_pages +=
                zoneinfo_parse_protection(ap);
        }
        break;
    case (PARSE_FAIL):
    default:
        return false;
    }
    return true;
}

static int zoneinfo_parse(union zoneinfo *zi) {
    static struct reread_data file_data = {
        .filename = ZONEINFO_PATH,
        .fd = -1,
    };
    char buf[PAGE_SIZE];
    char *save_ptr;
    char *line;

    memset(zi, 0, sizeof(union zoneinfo));

    if (reread_file(&file_data, buf, sizeof(buf)) < 0) {
        return -1;
    }

    for (line = strtok_r(buf, "\n", &save_ptr); line;
         line = strtok_r(NULL, "\n", &save_ptr)) {
        if (!zoneinfo_parse_line(line, zi)) {
            ALOGE("%s parse error", file_data.filename);
            return -1;
        }
    }
    zi->field.totalreserve_pages += zi->field.high;

    return 0;
}

/* /prop/meminfo parsing routines */
static bool meminfo_parse_line(char *line, union meminfo *mi) {
    char *cp = line;
    char *ap;
    char *save_ptr;
    int64_t val;
    int field_idx;
    enum field_match_result match_res;

    cp = strtok_r(line, " ", &save_ptr);
    if (!cp) {
        return false;
    }

    ap = strtok_r(NULL, " ", &save_ptr);
    if (!ap) {
        return false;
    }

    match_res = match_field(cp, ap, meminfo_field_names, MI_FIELD_COUNT,
        &val, &field_idx);
    if (match_res == PARSE_SUCCESS) {
        mi->arr[field_idx] = val / page_k;
    }
    return (match_res != PARSE_FAIL);
}

static int meminfo_parse(union meminfo *mi) {
    static struct reread_data file_data = {
        .filename = MEMINFO_PATH,
        .fd = -1,
    };
    char buf[PAGE_SIZE];
    char *save_ptr;
    char *line;

    memset(mi, 0, sizeof(union meminfo));

    if (reread_file(&file_data, buf, sizeof(buf)) < 0) {
        return -1;
    }

    for (line = strtok_r(buf, "\n", &save_ptr); line;
         line = strtok_r(NULL, "\n", &save_ptr)) {
        if (!meminfo_parse_line(line, mi)) {
            ALOGE("%s parse error", file_data.filename);
            return -1;
        }
    }
    mi->field.nr_file_pages = mi->field.cached + mi->field.swap_cached +
        mi->field.buffers;

    return 0;
}

static int proc_get_size(int pid) {
    char path[PATH_MAX];
    char line[LINE_MAX];
    int fd;
    int rss = 0;
    int total;
    ssize_t ret;

    /* gid containing AID_READPROC required */
    snprintf(path, PATH_MAX, "/proc/%d/statm", pid);
    fd = open(path, O_RDONLY | O_CLOEXEC);
    if (fd == -1)
        return -1;

    ret = read_all(fd, line, sizeof(line) - 1);
    if (ret < 0) {
        close(fd);
        return -1;
    }

    sscanf(line, "%d %d ", &total, &rss);
    close(fd);
    return rss;
}

static char *proc_get_name(int pid) {
    char path[PATH_MAX];
    static char line[LINE_MAX];
    int fd;
    char *cp;
    ssize_t ret;

    /* gid containing AID_READPROC required */
    snprintf(path, PATH_MAX, "/proc/%d/cmdline", pid);
    fd = open(path, O_RDONLY | O_CLOEXEC);
    if (fd == -1)
        return NULL;
    ret = read_all(fd, line, sizeof(line) - 1);
    close(fd);
    if (ret < 0) {
        return NULL;
    }

    cp = strchr(line, ' ');
    if (cp)
        *cp = '\0';

    return line;
}

static struct proc *proc_adj_lru(int oomadj) {
    return (struct proc *)adjslot_tail(&procadjslot_list[ADJTOSLOT(oomadj)]);
}

static struct proc *proc_get_heaviest(int oomadj) {
    struct adjslot_list *head = &procadjslot_list[ADJTOSLOT(oomadj)];
    struct adjslot_list *curr = head->next;
    struct proc *maxprocp = NULL;
    int maxsize = 0;
    while (curr != head) {
        int pid = ((struct proc *)curr)->pid;
        int tasksize = proc_get_size(pid);
        if (tasksize <= 0) {
            struct adjslot_list *next = curr->next;
            pid_remove(pid);
            curr = next;
        } else {
            if (tasksize > maxsize) {
                maxsize = tasksize;
                maxprocp = (struct proc *)curr;
            }
            curr = curr->next;
        }
    }
    return maxprocp;
}

/* Kill one process specified by procp.  Returns the size of the process killed */
static int kill_one_process(struct proc* procp, int min_score_adj,
                            enum vmpressure_level level) {
    int pid = procp->pid;
    uid_t uid = procp->uid;
    char *taskname;
    int tasksize;
    int r;

    taskname = proc_get_name(pid);
    if (!taskname) {
        pid_remove(pid);
        return -1;
    }

    tasksize = proc_get_size(pid);
    if (tasksize <= 0) {
        pid_remove(pid);
        return -1;
    }

    TRACE_KILL_START(pid);

    /* CAP_KILL required */
    r = kill(pid, SIGKILL);
    ALOGI(
        "Killing '%s' (%d), uid %d, adj %d\n"
        "   to free %ldkB because system is under %s memory pressure (min_oom_adj=%d)\n",
        taskname, pid, uid, procp->oomadj, tasksize * page_k,
        level_name[level], min_score_adj);
    pid_remove(pid);

    TRACE_KILL_END();

    if (r) {
        ALOGE("kill(%d): errno=%d", pid, errno);
        return -1;
    }

    return tasksize;
}

/*
 * Find processes to kill to free required number of pages.
 * If pages_to_free is set to 0 only one process will be killed.
 * Returns the size of the killed processes.
 */
static int find_and_kill_processes(enum vmpressure_level level,
                                   int min_score_adj, int pages_to_free) {
    int i;
    int killed_size;
    int pages_freed = 0;

    for (i = OOM_SCORE_ADJ_MAX; i >= min_score_adj; i--) {
        struct proc *procp;

        while (true) {
            procp = kill_heaviest_task ?
                proc_get_heaviest(i) : proc_adj_lru(i);

            if (!procp)
                break;

            killed_size = kill_one_process(procp, min_score_adj, level);
            if (killed_size >= 0) {
                pages_freed += killed_size;
                if (pages_freed >= pages_to_free) {
                    return pages_freed;
                }
            }
        }
    }

    return pages_freed;
}

static int64_t get_memory_usage(struct reread_data *file_data) {
    int ret;
    int64_t mem_usage;
    char buf[32];

    if (reread_file(file_data, buf, sizeof(buf)) < 0) {
        return -1;
    }

    if (!parse_int64(buf, &mem_usage)) {
        ALOGE("%s parse error", file_data->filename);
        return -1;
    }
    if (mem_usage == 0) {
        ALOGE("No memory!");
        return -1;
    }
    return mem_usage;
}

void record_low_pressure_levels(union meminfo *mi) {
    if (low_pressure_mem.min_nr_free_pages == -1 ||
        low_pressure_mem.min_nr_free_pages > mi->field.nr_free_pages) {
        if (debug_process_killing) {
            ALOGI("Low pressure min memory update from %" PRId64 " to %" PRId64,
                low_pressure_mem.min_nr_free_pages, mi->field.nr_free_pages);
        }
        low_pressure_mem.min_nr_free_pages = mi->field.nr_free_pages;
    }
    /*
     * Free memory at low vmpressure events occasionally gets spikes,
     * possibly a stale low vmpressure event with memory already
     * freed up (no memory pressure should have been reported).
     * Ignore large jumps in max_nr_free_pages that would mess up our stats.
     */
    if (low_pressure_mem.max_nr_free_pages == -1 ||
        (low_pressure_mem.max_nr_free_pages < mi->field.nr_free_pages &&
         mi->field.nr_free_pages - low_pressure_mem.max_nr_free_pages <
         low_pressure_mem.max_nr_free_pages * 0.1)) {
        if (debug_process_killing) {
            ALOGI("Low pressure max memory update from %" PRId64 " to %" PRId64,
                low_pressure_mem.max_nr_free_pages, mi->field.nr_free_pages);
        }
        low_pressure_mem.max_nr_free_pages = mi->field.nr_free_pages;
    }
}

enum vmpressure_level upgrade_level(enum vmpressure_level level) {
    return (enum vmpressure_level)((level < VMPRESS_LEVEL_CRITICAL) ?
        level + 1 : level);
}

enum vmpressure_level downgrade_level(enum vmpressure_level level) {
    return (enum vmpressure_level)((level > VMPRESS_LEVEL_LOW) ?
        level - 1 : level);
}

static inline unsigned long get_time_diff_ms(struct timeval *from,
                                             struct timeval *to) {
    return (to->tv_sec - from->tv_sec) * 1000 +
           (to->tv_usec - from->tv_usec) / 1000;
}

static void mp_event_common(int data, uint32_t events __unused) {
    int ret;
    unsigned long long evcount;
    int64_t mem_usage, memsw_usage;
    int64_t mem_pressure;
    enum vmpressure_level lvl;
    union meminfo mi;
    union zoneinfo zi;
    static struct timeval last_report_tm;
    static unsigned long skip_count = 0;
    enum vmpressure_level level = (enum vmpressure_level)data;
    long other_free = 0, other_file = 0;
    int min_score_adj;
    int pages_to_free = 0;
    int minfree = 0;
    static struct reread_data mem_usage_file_data = {
        .filename = MEMCG_MEMORY_USAGE,
        .fd = -1,
    };
    static struct reread_data memsw_usage_file_data = {
        .filename = MEMCG_MEMORYSW_USAGE,
        .fd = -1,
    };

    /*
     * Check all event counters from low to critical
     * and upgrade to the highest priority one. By reading
     * eventfd we also reset the event counters.
     */
    for (lvl = VMPRESS_LEVEL_LOW; lvl < VMPRESS_LEVEL_COUNT; lvl++) {
        if (mpevfd[lvl] != -1 &&
            TEMP_FAILURE_RETRY(read(mpevfd[lvl],
                               &evcount, sizeof(evcount))) > 0 &&
            evcount > 0 && lvl > level) {
            level = lvl;
        }
    }

    if (kill_timeout_ms) {
        struct timeval curr_tm;
        gettimeofday(&curr_tm, NULL);
        if (get_time_diff_ms(&last_report_tm, &curr_tm) < kill_timeout_ms) {
            skip_count++;
            return;
        }
    }

    if (skip_count > 0) {
        if (debug_process_killing) {
            ALOGI("%lu memory pressure events were skipped after a kill!",
                skip_count);
        }
        skip_count = 0;
    }

    if (meminfo_parse(&mi) < 0 || zoneinfo_parse(&zi) < 0) {
        ALOGE("Failed to get free memory!");
        return;
    }

    if (use_minfree_levels) {
        int i;

        other_free = mi.field.nr_free_pages - zi.field.totalreserve_pages;
        if (mi.field.nr_file_pages > (mi.field.shmem + mi.field.unevictable + mi.field.swap_cached)) {
            other_file = (mi.field.nr_file_pages - mi.field.shmem -
                          mi.field.unevictable - mi.field.swap_cached);
        } else {
            other_file = 0;
        }

        min_score_adj = OOM_SCORE_ADJ_MAX + 1;
        for (i = 0; i < lowmem_targets_size; i++) {
            minfree = lowmem_minfree[i];
            if (other_free < minfree && other_file < minfree) {
                min_score_adj = lowmem_adj[i];
                break;
            }
        }

        if (min_score_adj == OOM_SCORE_ADJ_MAX + 1) {
            if (debug_process_killing) {
                ALOGI("Ignore %s memory pressure event "
                      "(free memory=%ldkB, cache=%ldkB, limit=%ldkB)",
                      level_name[level], other_free * page_k, other_file * page_k,
                      (long)lowmem_minfree[lowmem_targets_size - 1] * page_k);
            }
            return;
        }

        /* Free up enough pages to push over the highest minfree level */
        pages_to_free = lowmem_minfree[lowmem_targets_size - 1] -
            ((other_free < other_file) ? other_free : other_file);
        goto do_kill;
    }

    if (level == VMPRESS_LEVEL_LOW) {
        record_low_pressure_levels(&mi);
    }

    if (level_oomadj[level] > OOM_SCORE_ADJ_MAX) {
        /* Do not monitor this pressure level */
        return;
    }

    if ((mem_usage = get_memory_usage(&mem_usage_file_data)) < 0) {
        goto do_kill;
    }
    if ((memsw_usage = get_memory_usage(&memsw_usage_file_data)) < 0) {
        goto do_kill;
    }

    // Calculate percent for swappinness.
    mem_pressure = (mem_usage * 100) / memsw_usage;

    if (enable_pressure_upgrade && level != VMPRESS_LEVEL_CRITICAL) {
        // We are swapping too much.
        if (mem_pressure < upgrade_pressure) {
            level = upgrade_level(level);
            if (debug_process_killing) {
                ALOGI("Event upgraded to %s", level_name[level]);
            }
        }
    }

    // If the pressure is larger than downgrade_pressure lmk will not
    // kill any process, since enough memory is available.
    if (mem_pressure > downgrade_pressure) {
        if (debug_process_killing) {
            ALOGI("Ignore %s memory pressure", level_name[level]);
        }
        return;
    } else if (level == VMPRESS_LEVEL_CRITICAL &&
               mem_pressure > upgrade_pressure) {
        if (debug_process_killing) {
            ALOGI("Downgrade critical memory pressure");
        }
        // Downgrade event, since enough memory available.
        level = downgrade_level(level);
    }

do_kill:
    if (low_ram_device) {
        /* For Go devices kill only one task */
        if (find_and_kill_processes(level, level_oomadj[level], 0) == 0) {
            if (debug_process_killing) {
                ALOGI("Nothing to kill");
            }
        }
    } else {
        int pages_freed;

        if (!use_minfree_levels) {
            /* If pressure level is less than critical and enough free swap then ignore */
            if (level < VMPRESS_LEVEL_CRITICAL &&
                mi.field.free_swap > low_pressure_mem.max_nr_free_pages) {
                if (debug_process_killing) {
                    ALOGI("Ignoring pressure since %" PRId64
                          " swap pages are available ",
                          mi.field.free_swap);
                }
                return;
            }
            /* Free up enough memory to downgrate the memory pressure to low level */
            if (mi.field.nr_free_pages < low_pressure_mem.max_nr_free_pages) {
                pages_to_free = low_pressure_mem.max_nr_free_pages -
                    mi.field.nr_free_pages;
            } else {
                if (debug_process_killing) {
                    ALOGI("Ignoring pressure since more memory is "
                        "available (%" PRId64 ") than watermark (%" PRId64 ")",
                        mi.field.nr_free_pages, low_pressure_mem.max_nr_free_pages);
                }
                return;
            }
            min_score_adj = level_oomadj[level];
        } else {
            if (debug_process_killing) {
                ALOGI("Killing because cache %ldkB is below "
                      "limit %ldkB for oom_adj %d\n"
                      "   Free memory is %ldkB %s reserved",
                      other_file * page_k, minfree * page_k, min_score_adj,
                      other_free * page_k, other_free >= 0 ? "above" : "below");
            }
        }

        if (debug_process_killing) {
            ALOGI("Trying to free %d pages", pages_to_free);
        }
        pages_freed = find_and_kill_processes(level, min_score_adj, pages_to_free);
        if (pages_freed < pages_to_free) {
            if (debug_process_killing) {
                ALOGI("Unable to free enough memory (pages freed=%d)", pages_freed);
            }
        } else {
            gettimeofday(&last_report_tm, NULL);
        }
    }
}

static bool init_mp_common(enum vmpressure_level level) {
    int mpfd;
    int evfd;
    int evctlfd;
    char buf[256];
    struct epoll_event epev;
    int ret;
    int level_idx = (int)level;
    const char *levelstr = level_name[level_idx];

    /* gid containing AID_SYSTEM required */
    mpfd = open(MEMCG_SYSFS_PATH "memory.pressure_level", O_RDONLY | O_CLOEXEC);
    if (mpfd < 0) {
        ALOGI("No kernel memory.pressure_level support (errno=%d)", errno);
        goto err_open_mpfd;
    }

    evctlfd = open(MEMCG_SYSFS_PATH "cgroup.event_control", O_WRONLY | O_CLOEXEC);
    if (evctlfd < 0) {
        ALOGI("No kernel memory cgroup event control (errno=%d)", errno);
        goto err_open_evctlfd;
    }

    evfd = eventfd(0, EFD_NONBLOCK | EFD_CLOEXEC);
    if (evfd < 0) {
        ALOGE("eventfd failed for level %s; errno=%d", levelstr, errno);
        goto err_eventfd;
    }

    ret = snprintf(buf, sizeof(buf), "%d %d %s", evfd, mpfd, levelstr);
    if (ret >= (ssize_t)sizeof(buf)) {
        ALOGE("cgroup.event_control line overflow for level %s", levelstr);
        goto err;
    }

    ret = TEMP_FAILURE_RETRY(write(evctlfd, buf, strlen(buf) + 1));
    if (ret == -1) {
        ALOGE("cgroup.event_control write failed for level %s; errno=%d",
              levelstr, errno);
        goto err;
    }

    epev.events = EPOLLIN;
    /* use data to store event level */
    vmpressure_hinfo[level_idx].data = level_idx;
    vmpressure_hinfo[level_idx].handler = mp_event_common;
    epev.data.ptr = (void *)&vmpressure_hinfo[level_idx];
    ret = epoll_ctl(epollfd, EPOLL_CTL_ADD, evfd, &epev);
    if (ret == -1) {
        ALOGE("epoll_ctl for level %s failed; errno=%d", levelstr, errno);
        goto err;
    }
    maxevents++;
    mpevfd[level] = evfd;
    close(evctlfd);
    return true;

err:
    close(evfd);
err_eventfd:
    close(evctlfd);
err_open_evctlfd:
    close(mpfd);
err_open_mpfd:
    return false;
}

static int init(void) {
    struct epoll_event epev;
    int i;
    int ret;

    page_k = sysconf(_SC_PAGESIZE);
    if (page_k == -1)
        page_k = PAGE_SIZE;
    page_k /= 1024;

    epollfd = epoll_create(MAX_EPOLL_EVENTS);
    if (epollfd == -1) {
        ALOGE("epoll_create failed (errno=%d)", errno);
        return -1;
    }

    // mark data connections as not connected
    for (int i = 0; i < MAX_DATA_CONN; i++) {
        data_sock[i].sock = -1;
    }

    ctrl_sock.sock = android_get_control_socket("lmkd");
    if (ctrl_sock.sock < 0) {
        ALOGE("get lmkd control socket failed");
        return -1;
    }

    ret = listen(ctrl_sock.sock, MAX_DATA_CONN);
    if (ret < 0) {
        ALOGE("lmkd control socket listen failed (errno=%d)", errno);
        return -1;
    }

    epev.events = EPOLLIN;
    ctrl_sock.handler_info.handler = ctrl_connect_handler;
    epev.data.ptr = (void *)&(ctrl_sock.handler_info);
    if (epoll_ctl(epollfd, EPOLL_CTL_ADD, ctrl_sock.sock, &epev) == -1) {
        ALOGE("epoll_ctl for lmkd control socket failed (errno=%d)", errno);
        return -1;
    }
    maxevents++;

    has_inkernel_module = !access(INKERNEL_MINFREE_PATH, W_OK);
    use_inkernel_interface = has_inkernel_module;

    if (use_inkernel_interface) {
        ALOGI("Using in-kernel low memory killer interface");
    } else {
        if (!init_mp_common(VMPRESS_LEVEL_LOW) ||
            !init_mp_common(VMPRESS_LEVEL_MEDIUM) ||
            !init_mp_common(VMPRESS_LEVEL_CRITICAL)) {
            ALOGE("Kernel does not support memory pressure events or in-kernel low memory killer");
            return -1;
        }
    }

    for (i = 0; i <= ADJTOSLOT(OOM_SCORE_ADJ_MAX); i++) {
        procadjslot_list[i].next = &procadjslot_list[i];
        procadjslot_list[i].prev = &procadjslot_list[i];
    }

    return 0;
}

static void mainloop(void) {
    struct event_handler_info* handler_info;
    struct epoll_event *evt;

    while (1) {
        struct epoll_event events[maxevents];
        int nevents;
        int i;

        nevents = epoll_wait(epollfd, events, maxevents, -1);

        if (nevents == -1) {
            if (errno == EINTR)
                continue;
            ALOGE("epoll_wait failed (errno=%d)", errno);
            continue;
        }

        /*
         * First pass to see if any data socket connections were dropped.
         * Dropped connection should be handled before any other events
         * to deallocate data connection and correctly handle cases when
         * connection gets dropped and reestablished in the same epoll cycle.
         * In such cases it's essential to handle connection closures first.
         */
        for (i = 0, evt = &events[0]; i < nevents; ++i, evt++) {
            if ((evt->events & EPOLLHUP) && evt->data.ptr) {
                ALOGI("lmkd data connection dropped");
                handler_info = (struct event_handler_info*)evt->data.ptr;
                ctrl_data_close(handler_info->data);
            }
        }

        /* Second pass to handle all other events */
        for (i = 0, evt = &events[0]; i < nevents; ++i, evt++) {
            if (evt->events & EPOLLERR)
                ALOGD("EPOLLERR on event #%d", i);
            if (evt->events & EPOLLHUP) {
                /* This case was handled in the first pass */
                continue;
            }
            if (evt->data.ptr) {
                handler_info = (struct event_handler_info*)evt->data.ptr;
                handler_info->handler(handler_info->data, evt->events);
            }
        }
    }
}

int main(int argc __unused, char **argv __unused) {
    struct sched_param param = {
            .sched_priority = 1,
    };

    /* By default disable low level vmpressure events */
    level_oomadj[VMPRESS_LEVEL_LOW] =
        property_get_int32("ro.lmk.low", OOM_SCORE_ADJ_MAX + 1);
    level_oomadj[VMPRESS_LEVEL_MEDIUM] =
        property_get_int32("ro.lmk.medium", 800);
    level_oomadj[VMPRESS_LEVEL_CRITICAL] =
        property_get_int32("ro.lmk.critical", 0);
    debug_process_killing = property_get_bool("ro.lmk.debug", false);

    /* By default disable upgrade/downgrade logic */
    enable_pressure_upgrade =
        property_get_bool("ro.lmk.critical_upgrade", false);
    upgrade_pressure =
        (int64_t)property_get_int32("ro.lmk.upgrade_pressure", 100);
    downgrade_pressure =
        (int64_t)property_get_int32("ro.lmk.downgrade_pressure", 100);
    kill_heaviest_task =
        property_get_bool("ro.lmk.kill_heaviest_task", false);
    low_ram_device = property_get_bool("ro.config.low_ram", false);
    kill_timeout_ms =
        (unsigned long)property_get_int32("ro.lmk.kill_timeout_ms", 0);
    use_minfree_levels =
        property_get_bool("ro.lmk.use_minfree_levels", false);
    per_app_memcg =
        property_get_bool("ro.config.per_app_memcg", low_ram_device);

    if (!init()) {
        if (!use_inkernel_interface) {
            /*
             * MCL_ONFAULT pins pages as they fault instead of loading
             * everything immediately all at once. (Which would be bad,
             * because as of this writing, we have a lot of mapped pages we
             * never use.) Old kernels will see MCL_ONFAULT and fail with
             * EINVAL; we ignore this failure.
             *
             * N.B. read the man page for mlockall. MCL_CURRENT | MCL_ONFAULT
             * pins ⊆ MCL_CURRENT, converging to just MCL_CURRENT as we fault
             * in pages.
             */
            /* CAP_IPC_LOCK required */
            if (mlockall(MCL_CURRENT | MCL_FUTURE | MCL_ONFAULT) && (errno != EINVAL)) {
                ALOGW("mlockall failed %s", strerror(errno));
            }

            /* CAP_NICE required */
            if (sched_setscheduler(0, SCHED_FIFO, &param)) {
                ALOGW("set SCHED_FIFO failed %s", strerror(errno));
            }
        }

        mainloop();
    }

    ALOGI("exiting");
    return 0;
}