summaryrefslogtreecommitdiff
path: root/src/core/cgroup.c
blob: 17d3eb2e5235f0d26a3e0789602d4bbc5ebedbe5 (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
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
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
/***
  This file is part of systemd.

  Copyright 2013 Lennart Poettering

  systemd is free software; you can redistribute it and/or modify it
  under the terms of the GNU Lesser General Public License as published by
  the Free Software Foundation; either version 2.1 of the License, or
  (at your option) any later version.

  systemd 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
  Lesser General Public License for more details.

  You should have received a copy of the GNU Lesser General Public License
  along with systemd; If not, see <http://www.gnu.org/licenses/>.
***/

#include <fcntl.h>
#include <fnmatch.h>

#include "alloc-util.h"
#include "cgroup-util.h"
#include "cgroup.h"
#include "fd-util.h"
#include "fileio.h"
#include "fs-util.h"
#include "parse-util.h"
#include "path-util.h"
#include "process-util.h"
//#include "special.h"
#include "string-table.h"
#include "string-util.h"
#include "stdio-util.h"

#define CGROUP_CPU_QUOTA_PERIOD_USEC ((usec_t) 100 * USEC_PER_MSEC)

#if 0 /// UNNEEDED by elogind
static void cgroup_compat_warn(void) {
        static bool cgroup_compat_warned = false;

        if (cgroup_compat_warned)
                return;

        log_warning("cgroup compatibility translation between legacy and unified hierarchy settings activated. See cgroup-compat debug messages for details.");
        cgroup_compat_warned = true;
}

#define log_cgroup_compat(unit, fmt, ...) do {                                  \
                cgroup_compat_warn();                                           \
                log_unit_debug(unit, "cgroup-compat: " fmt, ##__VA_ARGS__);     \
        } while (false)

void cgroup_context_init(CGroupContext *c) {
        assert(c);

        /* Initialize everything to the kernel defaults, assuming the
         * structure is preinitialized to 0 */

        c->cpu_weight = CGROUP_WEIGHT_INVALID;
        c->startup_cpu_weight = CGROUP_WEIGHT_INVALID;
        c->cpu_quota_per_sec_usec = USEC_INFINITY;

        c->cpu_shares = CGROUP_CPU_SHARES_INVALID;
        c->startup_cpu_shares = CGROUP_CPU_SHARES_INVALID;

        c->memory_high = CGROUP_LIMIT_MAX;
        c->memory_max = CGROUP_LIMIT_MAX;
        c->memory_swap_max = CGROUP_LIMIT_MAX;

        c->memory_limit = CGROUP_LIMIT_MAX;

        c->io_weight = CGROUP_WEIGHT_INVALID;
        c->startup_io_weight = CGROUP_WEIGHT_INVALID;

        c->blockio_weight = CGROUP_BLKIO_WEIGHT_INVALID;
        c->startup_blockio_weight = CGROUP_BLKIO_WEIGHT_INVALID;

        c->tasks_max = (uint64_t) -1;
}

void cgroup_context_free_device_allow(CGroupContext *c, CGroupDeviceAllow *a) {
        assert(c);
        assert(a);

        LIST_REMOVE(device_allow, c->device_allow, a);
        free(a->path);
        free(a);
}

void cgroup_context_free_io_device_weight(CGroupContext *c, CGroupIODeviceWeight *w) {
        assert(c);
        assert(w);

        LIST_REMOVE(device_weights, c->io_device_weights, w);
        free(w->path);
        free(w);
}

void cgroup_context_free_io_device_limit(CGroupContext *c, CGroupIODeviceLimit *l) {
        assert(c);
        assert(l);

        LIST_REMOVE(device_limits, c->io_device_limits, l);
        free(l->path);
        free(l);
}

void cgroup_context_free_blockio_device_weight(CGroupContext *c, CGroupBlockIODeviceWeight *w) {
        assert(c);
        assert(w);

        LIST_REMOVE(device_weights, c->blockio_device_weights, w);
        free(w->path);
        free(w);
}

void cgroup_context_free_blockio_device_bandwidth(CGroupContext *c, CGroupBlockIODeviceBandwidth *b) {
        assert(c);
        assert(b);

        LIST_REMOVE(device_bandwidths, c->blockio_device_bandwidths, b);
        free(b->path);
        free(b);
}

void cgroup_context_done(CGroupContext *c) {
        assert(c);

        while (c->io_device_weights)
                cgroup_context_free_io_device_weight(c, c->io_device_weights);

        while (c->io_device_limits)
                cgroup_context_free_io_device_limit(c, c->io_device_limits);

        while (c->blockio_device_weights)
                cgroup_context_free_blockio_device_weight(c, c->blockio_device_weights);

        while (c->blockio_device_bandwidths)
                cgroup_context_free_blockio_device_bandwidth(c, c->blockio_device_bandwidths);

        while (c->device_allow)
                cgroup_context_free_device_allow(c, c->device_allow);

        c->ip_address_allow = ip_address_access_free_all(c->ip_address_allow);
        c->ip_address_deny = ip_address_access_free_all(c->ip_address_deny);
}

void cgroup_context_dump(CGroupContext *c, FILE* f, const char *prefix) {
        CGroupIODeviceLimit *il;
        CGroupIODeviceWeight *iw;
        CGroupBlockIODeviceBandwidth *b;
        CGroupBlockIODeviceWeight *w;
        CGroupDeviceAllow *a;
        char u[FORMAT_TIMESPAN_MAX];

        assert(c);
        assert(f);

        prefix = strempty(prefix);

        fprintf(f,
                "%sCPUAccounting=%s\n"
                "%sIOAccounting=%s\n"
                "%sBlockIOAccounting=%s\n"
                "%sMemoryAccounting=%s\n"
                "%sTasksAccounting=%s\n"
                "%sCPUWeight=%" PRIu64 "\n"
                "%sStartupCPUWeight=%" PRIu64 "\n"
                "%sCPUShares=%" PRIu64 "\n"
                "%sStartupCPUShares=%" PRIu64 "\n"
                "%sCPUQuotaPerSecSec=%s\n"
                "%sIOWeight=%" PRIu64 "\n"
                "%sStartupIOWeight=%" PRIu64 "\n"
                "%sBlockIOWeight=%" PRIu64 "\n"
                "%sStartupBlockIOWeight=%" PRIu64 "\n"
                "%sMemoryLow=%" PRIu64 "\n"
                "%sMemoryHigh=%" PRIu64 "\n"
                "%sMemoryMax=%" PRIu64 "\n"
                "%sMemorySwapMax=%" PRIu64 "\n"
                "%sMemoryLimit=%" PRIu64 "\n"
                "%sTasksMax=%" PRIu64 "\n"
                "%sDevicePolicy=%s\n"
                "%sDelegate=%s\n",
                prefix, yes_no(c->cpu_accounting),
                prefix, yes_no(c->io_accounting),
                prefix, yes_no(c->blockio_accounting),
                prefix, yes_no(c->memory_accounting),
                prefix, yes_no(c->tasks_accounting),
                prefix, c->cpu_weight,
                prefix, c->startup_cpu_weight,
                prefix, c->cpu_shares,
                prefix, c->startup_cpu_shares,
                prefix, format_timespan(u, sizeof(u), c->cpu_quota_per_sec_usec, 1),
                prefix, c->io_weight,
                prefix, c->startup_io_weight,
                prefix, c->blockio_weight,
                prefix, c->startup_blockio_weight,
                prefix, c->memory_low,
                prefix, c->memory_high,
                prefix, c->memory_max,
                prefix, c->memory_swap_max,
                prefix, c->memory_limit,
                prefix, c->tasks_max,
                prefix, cgroup_device_policy_to_string(c->device_policy),
                prefix, yes_no(c->delegate));

        LIST_FOREACH(device_allow, a, c->device_allow)
                fprintf(f,
                        "%sDeviceAllow=%s %s%s%s\n",
                        prefix,
                        a->path,
                        a->r ? "r" : "", a->w ? "w" : "", a->m ? "m" : "");

        LIST_FOREACH(device_weights, iw, c->io_device_weights)
                fprintf(f,
                        "%sIODeviceWeight=%s %" PRIu64,
                        prefix,
                        iw->path,
                        iw->weight);

        LIST_FOREACH(device_limits, il, c->io_device_limits) {
                char buf[FORMAT_BYTES_MAX];
                CGroupIOLimitType type;

                for (type = 0; type < _CGROUP_IO_LIMIT_TYPE_MAX; type++)
                        if (il->limits[type] != cgroup_io_limit_defaults[type])
                                fprintf(f,
                                        "%s%s=%s %s\n",
                                        prefix,
                                        cgroup_io_limit_type_to_string(type),
                                        il->path,
                                        format_bytes(buf, sizeof(buf), il->limits[type]));
        }

        LIST_FOREACH(device_weights, w, c->blockio_device_weights)
                fprintf(f,
                        "%sBlockIODeviceWeight=%s %" PRIu64,
                        prefix,
                        w->path,
                        w->weight);

        LIST_FOREACH(device_bandwidths, b, c->blockio_device_bandwidths) {
                char buf[FORMAT_BYTES_MAX];

                if (b->rbps != CGROUP_LIMIT_MAX)
                        fprintf(f,
                                "%sBlockIOReadBandwidth=%s %s\n",
                                prefix,
                                b->path,
                                format_bytes(buf, sizeof(buf), b->rbps));
                if (b->wbps != CGROUP_LIMIT_MAX)
                        fprintf(f,
                                "%sBlockIOWriteBandwidth=%s %s\n",
                                prefix,
                                b->path,
                                format_bytes(buf, sizeof(buf), b->wbps));
        }
}

static int lookup_block_device(const char *p, dev_t *dev) {
        struct stat st;
        int r;

        assert(p);
        assert(dev);

        r = stat(p, &st);
        if (r < 0)
                return log_warning_errno(errno, "Couldn't stat device %s: %m", p);

        if (S_ISBLK(st.st_mode))
                *dev = st.st_rdev;
        else if (major(st.st_dev) != 0) {
                /* If this is not a device node then find the block
                 * device this file is stored on */
                *dev = st.st_dev;

                /* If this is a partition, try to get the originating
                 * block device */
                block_get_whole_disk(*dev, dev);
        } else {
                log_warning("%s is not a block device and file system block device cannot be determined or is not local.", p);
                return -ENODEV;
        }

        return 0;
}

static int whitelist_device(const char *path, const char *node, const char *acc) {
        char buf[2+DECIMAL_STR_MAX(dev_t)*2+2+4];
        struct stat st;
        bool ignore_notfound;
        int r;

        assert(path);
        assert(acc);

        if (node[0] == '-') {
                /* Non-existent paths starting with "-" must be silently ignored */
                node++;
                ignore_notfound = true;
        } else
                ignore_notfound = false;

        if (stat(node, &st) < 0) {
                if (errno == ENOENT && ignore_notfound)
                        return 0;

                return log_warning_errno(errno, "Couldn't stat device %s: %m", node);
        }

        if (!S_ISCHR(st.st_mode) && !S_ISBLK(st.st_mode)) {
                log_warning("%s is not a device.", node);
                return -ENODEV;
        }

        sprintf(buf,
                "%c %u:%u %s",
                S_ISCHR(st.st_mode) ? 'c' : 'b',
                major(st.st_rdev), minor(st.st_rdev),
                acc);

        r = cg_set_attribute("devices", path, "devices.allow", buf);
        if (r < 0)
                log_full_errno(IN_SET(r, -ENOENT, -EROFS, -EINVAL, -EACCES) ? LOG_DEBUG : LOG_WARNING, r,
                               "Failed to set devices.allow on %s: %m", path);

        return r;
}

static int whitelist_major(const char *path, const char *name, char type, const char *acc) {
        _cleanup_fclose_ FILE *f = NULL;
        char line[LINE_MAX];
        bool good = false;
        int r;

        assert(path);
        assert(acc);
        assert(type == 'b' || type == 'c');

        f = fopen("/proc/devices", "re");
        if (!f)
                return log_warning_errno(errno, "Cannot open /proc/devices to resolve %s (%c): %m", name, type);

        FOREACH_LINE(line, f, goto fail) {
                char buf[2+DECIMAL_STR_MAX(unsigned)+3+4], *p, *w;
                unsigned maj;

                truncate_nl(line);

                if (type == 'c' && streq(line, "Character devices:")) {
                        good = true;
                        continue;
                }

                if (type == 'b' && streq(line, "Block devices:")) {
                        good = true;
                        continue;
                }

                if (isempty(line)) {
                        good = false;
                        continue;
                }

                if (!good)
                        continue;

                p = strstrip(line);

                w = strpbrk(p, WHITESPACE);
                if (!w)
                        continue;
                *w = 0;

                r = safe_atou(p, &maj);
                if (r < 0)
                        continue;
                if (maj <= 0)
                        continue;

                w++;
                w += strspn(w, WHITESPACE);

                if (fnmatch(name, w, 0) != 0)
                        continue;

                sprintf(buf,
                        "%c %u:* %s",
                        type,
                        maj,
                        acc);

                r = cg_set_attribute("devices", path, "devices.allow", buf);
                if (r < 0)
                        log_full_errno(IN_SET(r, -ENOENT, -EROFS, -EINVAL, -EACCES) ? LOG_DEBUG : LOG_WARNING, r,
                                       "Failed to set devices.allow on %s: %m", path);
        }

        return 0;

fail:
        return log_warning_errno(errno, "Failed to read /proc/devices: %m");
}

static bool cgroup_context_has_cpu_weight(CGroupContext *c) {
        return c->cpu_weight != CGROUP_WEIGHT_INVALID ||
                c->startup_cpu_weight != CGROUP_WEIGHT_INVALID;
}

static bool cgroup_context_has_cpu_shares(CGroupContext *c) {
        return c->cpu_shares != CGROUP_CPU_SHARES_INVALID ||
                c->startup_cpu_shares != CGROUP_CPU_SHARES_INVALID;
}

static uint64_t cgroup_context_cpu_weight(CGroupContext *c, ManagerState state) {
        if (IN_SET(state, MANAGER_STARTING, MANAGER_INITIALIZING) &&
            c->startup_cpu_weight != CGROUP_WEIGHT_INVALID)
                return c->startup_cpu_weight;
        else if (c->cpu_weight != CGROUP_WEIGHT_INVALID)
                return c->cpu_weight;
        else
                return CGROUP_WEIGHT_DEFAULT;
}

static uint64_t cgroup_context_cpu_shares(CGroupContext *c, ManagerState state) {
        if (IN_SET(state, MANAGER_STARTING, MANAGER_INITIALIZING) &&
            c->startup_cpu_shares != CGROUP_CPU_SHARES_INVALID)
                return c->startup_cpu_shares;
        else if (c->cpu_shares != CGROUP_CPU_SHARES_INVALID)
                return c->cpu_shares;
        else
                return CGROUP_CPU_SHARES_DEFAULT;
}

static void cgroup_apply_unified_cpu_config(Unit *u, uint64_t weight, uint64_t quota) {
        char buf[MAX(DECIMAL_STR_MAX(uint64_t) + 1, (DECIMAL_STR_MAX(usec_t) + 1) * 2)];
        int r;

        xsprintf(buf, "%" PRIu64 "\n", weight);
        r = cg_set_attribute("cpu", u->cgroup_path, "cpu.weight", buf);
        if (r < 0)
                log_unit_full(u, IN_SET(r, -ENOENT, -EROFS, -EACCES) ? LOG_DEBUG : LOG_WARNING, r,
                              "Failed to set cpu.weight: %m");

        if (quota != USEC_INFINITY)
                xsprintf(buf, USEC_FMT " " USEC_FMT "\n",
                         quota * CGROUP_CPU_QUOTA_PERIOD_USEC / USEC_PER_SEC, CGROUP_CPU_QUOTA_PERIOD_USEC);
        else
                xsprintf(buf, "max " USEC_FMT "\n", CGROUP_CPU_QUOTA_PERIOD_USEC);

        r = cg_set_attribute("cpu", u->cgroup_path, "cpu.max", buf);

        if (r < 0)
                log_unit_full(u, IN_SET(r, -ENOENT, -EROFS, -EACCES) ? LOG_DEBUG : LOG_WARNING, r,
                              "Failed to set cpu.max: %m");
}

static void cgroup_apply_legacy_cpu_config(Unit *u, uint64_t shares, uint64_t quota) {
        char buf[MAX(DECIMAL_STR_MAX(uint64_t), DECIMAL_STR_MAX(usec_t)) + 1];
        int r;

        xsprintf(buf, "%" PRIu64 "\n", shares);
        r = cg_set_attribute("cpu", u->cgroup_path, "cpu.shares", buf);
        if (r < 0)
                log_unit_full(u, IN_SET(r, -ENOENT, -EROFS, -EACCES) ? LOG_DEBUG : LOG_WARNING, r,
                              "Failed to set cpu.shares: %m");

        xsprintf(buf, USEC_FMT "\n", CGROUP_CPU_QUOTA_PERIOD_USEC);
        r = cg_set_attribute("cpu", u->cgroup_path, "cpu.cfs_period_us", buf);
        if (r < 0)
                log_unit_full(u, IN_SET(r, -ENOENT, -EROFS, -EACCES) ? LOG_DEBUG : LOG_WARNING, r,
                              "Failed to set cpu.cfs_period_us: %m");

        if (quota != USEC_INFINITY) {
                xsprintf(buf, USEC_FMT "\n", quota * CGROUP_CPU_QUOTA_PERIOD_USEC / USEC_PER_SEC);
                r = cg_set_attribute("cpu", u->cgroup_path, "cpu.cfs_quota_us", buf);
        } else
                r = cg_set_attribute("cpu", u->cgroup_path, "cpu.cfs_quota_us", "-1");
        if (r < 0)
                log_unit_full(u, IN_SET(r, -ENOENT, -EROFS, -EACCES) ? LOG_DEBUG : LOG_WARNING, r,
                              "Failed to set cpu.cfs_quota_us: %m");
}

static uint64_t cgroup_cpu_shares_to_weight(uint64_t shares) {
        return CLAMP(shares * CGROUP_WEIGHT_DEFAULT / CGROUP_CPU_SHARES_DEFAULT,
                     CGROUP_WEIGHT_MIN, CGROUP_WEIGHT_MAX);
}

static uint64_t cgroup_cpu_weight_to_shares(uint64_t weight) {
        return CLAMP(weight * CGROUP_CPU_SHARES_DEFAULT / CGROUP_WEIGHT_DEFAULT,
                     CGROUP_CPU_SHARES_MIN, CGROUP_CPU_SHARES_MAX);
}

static bool cgroup_context_has_io_config(CGroupContext *c) {
        return c->io_accounting ||
                c->io_weight != CGROUP_WEIGHT_INVALID ||
                c->startup_io_weight != CGROUP_WEIGHT_INVALID ||
                c->io_device_weights ||
                c->io_device_limits;
}

static bool cgroup_context_has_blockio_config(CGroupContext *c) {
        return c->blockio_accounting ||
                c->blockio_weight != CGROUP_BLKIO_WEIGHT_INVALID ||
                c->startup_blockio_weight != CGROUP_BLKIO_WEIGHT_INVALID ||
                c->blockio_device_weights ||
                c->blockio_device_bandwidths;
}

static uint64_t cgroup_context_io_weight(CGroupContext *c, ManagerState state) {
        if (IN_SET(state, MANAGER_STARTING, MANAGER_INITIALIZING) &&
            c->startup_io_weight != CGROUP_WEIGHT_INVALID)
                return c->startup_io_weight;
        else if (c->io_weight != CGROUP_WEIGHT_INVALID)
                return c->io_weight;
        else
                return CGROUP_WEIGHT_DEFAULT;
}

static uint64_t cgroup_context_blkio_weight(CGroupContext *c, ManagerState state) {
        if (IN_SET(state, MANAGER_STARTING, MANAGER_INITIALIZING) &&
            c->startup_blockio_weight != CGROUP_BLKIO_WEIGHT_INVALID)
                return c->startup_blockio_weight;
        else if (c->blockio_weight != CGROUP_BLKIO_WEIGHT_INVALID)
                return c->blockio_weight;
        else
                return CGROUP_BLKIO_WEIGHT_DEFAULT;
}

static uint64_t cgroup_weight_blkio_to_io(uint64_t blkio_weight) {
        return CLAMP(blkio_weight * CGROUP_WEIGHT_DEFAULT / CGROUP_BLKIO_WEIGHT_DEFAULT,
                     CGROUP_WEIGHT_MIN, CGROUP_WEIGHT_MAX);
}

static uint64_t cgroup_weight_io_to_blkio(uint64_t io_weight) {
        return CLAMP(io_weight * CGROUP_BLKIO_WEIGHT_DEFAULT / CGROUP_WEIGHT_DEFAULT,
                     CGROUP_BLKIO_WEIGHT_MIN, CGROUP_BLKIO_WEIGHT_MAX);
}

static void cgroup_apply_io_device_weight(Unit *u, const char *dev_path, uint64_t io_weight) {
        char buf[DECIMAL_STR_MAX(dev_t)*2+2+DECIMAL_STR_MAX(uint64_t)+1];
        dev_t dev;
        int r;

        r = lookup_block_device(dev_path, &dev);
        if (r < 0)
                return;

        xsprintf(buf, "%u:%u %" PRIu64 "\n", major(dev), minor(dev), io_weight);
        r = cg_set_attribute("io", u->cgroup_path, "io.weight", buf);
        if (r < 0)
                log_unit_full(u, IN_SET(r, -ENOENT, -EROFS, -EACCES) ? LOG_DEBUG : LOG_WARNING, r,
                              "Failed to set io.weight: %m");
}

static void cgroup_apply_blkio_device_weight(Unit *u, const char *dev_path, uint64_t blkio_weight) {
        char buf[DECIMAL_STR_MAX(dev_t)*2+2+DECIMAL_STR_MAX(uint64_t)+1];
        dev_t dev;
        int r;

        r = lookup_block_device(dev_path, &dev);
        if (r < 0)
                return;

        xsprintf(buf, "%u:%u %" PRIu64 "\n", major(dev), minor(dev), blkio_weight);
        r = cg_set_attribute("blkio", u->cgroup_path, "blkio.weight_device", buf);
        if (r < 0)
                log_unit_full(u, IN_SET(r, -ENOENT, -EROFS, -EACCES) ? LOG_DEBUG : LOG_WARNING, r,
                              "Failed to set blkio.weight_device: %m");
}

static unsigned cgroup_apply_io_device_limit(Unit *u, const char *dev_path, uint64_t *limits) {
        char limit_bufs[_CGROUP_IO_LIMIT_TYPE_MAX][DECIMAL_STR_MAX(uint64_t)];
        char buf[DECIMAL_STR_MAX(dev_t)*2+2+(6+DECIMAL_STR_MAX(uint64_t)+1)*4];
        CGroupIOLimitType type;
        dev_t dev;
        unsigned n = 0;
        int r;

        r = lookup_block_device(dev_path, &dev);
        if (r < 0)
                return 0;

        for (type = 0; type < _CGROUP_IO_LIMIT_TYPE_MAX; type++) {
                if (limits[type] != cgroup_io_limit_defaults[type]) {
                        xsprintf(limit_bufs[type], "%" PRIu64, limits[type]);
                        n++;
                } else {
                        xsprintf(limit_bufs[type], "%s", limits[type] == CGROUP_LIMIT_MAX ? "max" : "0");
                }
        }

        xsprintf(buf, "%u:%u rbps=%s wbps=%s riops=%s wiops=%s\n", major(dev), minor(dev),
                 limit_bufs[CGROUP_IO_RBPS_MAX], limit_bufs[CGROUP_IO_WBPS_MAX],
                 limit_bufs[CGROUP_IO_RIOPS_MAX], limit_bufs[CGROUP_IO_WIOPS_MAX]);
        r = cg_set_attribute("io", u->cgroup_path, "io.max", buf);
        if (r < 0)
                log_unit_full(u, IN_SET(r, -ENOENT, -EROFS, -EACCES) ? LOG_DEBUG : LOG_WARNING, r,
                              "Failed to set io.max: %m");
        return n;
}

static unsigned cgroup_apply_blkio_device_limit(Unit *u, const char *dev_path, uint64_t rbps, uint64_t wbps) {
        char buf[DECIMAL_STR_MAX(dev_t)*2+2+DECIMAL_STR_MAX(uint64_t)+1];
        dev_t dev;
        unsigned n = 0;
        int r;

        r = lookup_block_device(dev_path, &dev);
        if (r < 0)
                return 0;

        if (rbps != CGROUP_LIMIT_MAX)
                n++;
        sprintf(buf, "%u:%u %" PRIu64 "\n", major(dev), minor(dev), rbps);
        r = cg_set_attribute("blkio", u->cgroup_path, "blkio.throttle.read_bps_device", buf);
        if (r < 0)
                log_unit_full(u, IN_SET(r, -ENOENT, -EROFS, -EACCES) ? LOG_DEBUG : LOG_WARNING, r,
                              "Failed to set blkio.throttle.read_bps_device: %m");

        if (wbps != CGROUP_LIMIT_MAX)
                n++;
        sprintf(buf, "%u:%u %" PRIu64 "\n", major(dev), minor(dev), wbps);
        r = cg_set_attribute("blkio", u->cgroup_path, "blkio.throttle.write_bps_device", buf);
        if (r < 0)
                log_unit_full(u, IN_SET(r, -ENOENT, -EROFS, -EACCES) ? LOG_DEBUG : LOG_WARNING, r,
                              "Failed to set blkio.throttle.write_bps_device: %m");

        return n;
}

static bool cgroup_context_has_unified_memory_config(CGroupContext *c) {
        return c->memory_low > 0 || c->memory_high != CGROUP_LIMIT_MAX || c->memory_max != CGROUP_LIMIT_MAX || c->memory_swap_max != CGROUP_LIMIT_MAX;
}

static void cgroup_apply_unified_memory_limit(Unit *u, const char *file, uint64_t v) {
        char buf[DECIMAL_STR_MAX(uint64_t) + 1] = "max";
        int r;

        if (v != CGROUP_LIMIT_MAX)
                xsprintf(buf, "%" PRIu64 "\n", v);

        r = cg_set_attribute("memory", u->cgroup_path, file, buf);
        if (r < 0)
                log_unit_full(u, IN_SET(r, -ENOENT, -EROFS, -EACCES) ? LOG_DEBUG : LOG_WARNING, r,
                              "Failed to set %s: %m", file);
}

static void cgroup_context_apply(Unit *u, CGroupMask mask, ManagerState state) {
        const char *path;
        CGroupContext *c;
        bool is_root;
        int r;

        assert(u);

        c = unit_get_cgroup_context(u);
        path = u->cgroup_path;

        assert(c);
        assert(path);

        if (mask == 0)
                return;

        /* Some cgroup attributes are not supported on the root cgroup,
         * hence silently ignore */
        is_root = isempty(path) || path_equal(path, "/");
        if (is_root)
                /* Make sure we don't try to display messages with an empty path. */
                path = "/";

        /* We generally ignore errors caused by read-only mounted
         * cgroup trees (assuming we are running in a container then),
         * and missing cgroups, i.e. EROFS and ENOENT. */

        if ((mask & CGROUP_MASK_CPU) && !is_root) {
                bool has_weight = cgroup_context_has_cpu_weight(c);
                bool has_shares = cgroup_context_has_cpu_shares(c);

                if (cg_all_unified() > 0) {
                        uint64_t weight;

                        if (has_weight)
                                weight = cgroup_context_cpu_weight(c, state);
                        else if (has_shares) {
                                uint64_t shares = cgroup_context_cpu_shares(c, state);

                                weight = cgroup_cpu_shares_to_weight(shares);

                                log_cgroup_compat(u, "Applying [Startup]CpuShares %" PRIu64 " as [Startup]CpuWeight %" PRIu64 " on %s",
                                                  shares, weight, path);
                        } else
                                weight = CGROUP_WEIGHT_DEFAULT;

                        cgroup_apply_unified_cpu_config(u, weight, c->cpu_quota_per_sec_usec);
                } else {
                        uint64_t shares;

                        if (has_weight) {
                                uint64_t weight = cgroup_context_cpu_weight(c, state);

                                shares = cgroup_cpu_weight_to_shares(weight);

                                log_cgroup_compat(u, "Applying [Startup]CpuWeight %" PRIu64 " as [Startup]CpuShares %" PRIu64 " on %s",
                                                  weight, shares, path);
                        } else if (has_shares)
                                shares = cgroup_context_cpu_shares(c, state);
                        else
                                shares = CGROUP_CPU_SHARES_DEFAULT;

                        cgroup_apply_legacy_cpu_config(u, shares, c->cpu_quota_per_sec_usec);
                }
        }

        if (mask & CGROUP_MASK_IO) {
                bool has_io = cgroup_context_has_io_config(c);
                bool has_blockio = cgroup_context_has_blockio_config(c);

                if (!is_root) {
                        char buf[8+DECIMAL_STR_MAX(uint64_t)+1];
                        uint64_t weight;

                        if (has_io)
                                weight = cgroup_context_io_weight(c, state);
                        else if (has_blockio) {
                                uint64_t blkio_weight = cgroup_context_blkio_weight(c, state);

                                weight = cgroup_weight_blkio_to_io(blkio_weight);

                                log_cgroup_compat(u, "Applying [Startup]BlockIOWeight %" PRIu64 " as [Startup]IOWeight %" PRIu64,
                                                  blkio_weight, weight);
                        } else
                                weight = CGROUP_WEIGHT_DEFAULT;

                        xsprintf(buf, "default %" PRIu64 "\n", weight);
                        r = cg_set_attribute("io", path, "io.weight", buf);
                        if (r < 0)
                                log_unit_full(u, IN_SET(r, -ENOENT, -EROFS, -EACCES) ? LOG_DEBUG : LOG_WARNING, r,
                                              "Failed to set io.weight: %m");

                        if (has_io) {
                                CGroupIODeviceWeight *w;

                                /* FIXME: no way to reset this list */
                                LIST_FOREACH(device_weights, w, c->io_device_weights)
                                        cgroup_apply_io_device_weight(u, w->path, w->weight);
                        } else if (has_blockio) {
                                CGroupBlockIODeviceWeight *w;

                                /* FIXME: no way to reset this list */
                                LIST_FOREACH(device_weights, w, c->blockio_device_weights) {
                                        weight = cgroup_weight_blkio_to_io(w->weight);

                                        log_cgroup_compat(u, "Applying BlockIODeviceWeight %" PRIu64 " as IODeviceWeight %" PRIu64 " for %s",
                                                          w->weight, weight, w->path);

                                        cgroup_apply_io_device_weight(u, w->path, weight);
                                }
                        }
                }

                /* Apply limits and free ones without config. */
                if (has_io) {
                        CGroupIODeviceLimit *l, *next;

                        LIST_FOREACH_SAFE(device_limits, l, next, c->io_device_limits) {
                                if (!cgroup_apply_io_device_limit(u, l->path, l->limits))
                                        cgroup_context_free_io_device_limit(c, l);
                        }
                } else if (has_blockio) {
                        CGroupBlockIODeviceBandwidth *b, *next;

                        LIST_FOREACH_SAFE(device_bandwidths, b, next, c->blockio_device_bandwidths) {
                                uint64_t limits[_CGROUP_IO_LIMIT_TYPE_MAX];
                                CGroupIOLimitType type;

                                for (type = 0; type < _CGROUP_IO_LIMIT_TYPE_MAX; type++)
                                        limits[type] = cgroup_io_limit_defaults[type];

                                limits[CGROUP_IO_RBPS_MAX] = b->rbps;
                                limits[CGROUP_IO_WBPS_MAX] = b->wbps;

                                log_cgroup_compat(u, "Applying BlockIO{Read|Write}Bandwidth %" PRIu64 " %" PRIu64 " as IO{Read|Write}BandwidthMax for %s",
                                                  b->rbps, b->wbps, b->path);

                                if (!cgroup_apply_io_device_limit(u, b->path, limits))
                                        cgroup_context_free_blockio_device_bandwidth(c, b);
                        }
                }
        }

        if (mask & CGROUP_MASK_BLKIO) {
                bool has_io = cgroup_context_has_io_config(c);
                bool has_blockio = cgroup_context_has_blockio_config(c);

                if (!is_root) {
                        char buf[DECIMAL_STR_MAX(uint64_t)+1];
                        uint64_t weight;

                        if (has_io) {
                                uint64_t io_weight = cgroup_context_io_weight(c, state);

                                weight = cgroup_weight_io_to_blkio(cgroup_context_io_weight(c, state));

                                log_cgroup_compat(u, "Applying [Startup]IOWeight %" PRIu64 " as [Startup]BlockIOWeight %" PRIu64,
                                                  io_weight, weight);
                        } else if (has_blockio)
                                weight = cgroup_context_blkio_weight(c, state);
                        else
                                weight = CGROUP_BLKIO_WEIGHT_DEFAULT;

                        xsprintf(buf, "%" PRIu64 "\n", weight);
                        r = cg_set_attribute("blkio", path, "blkio.weight", buf);
                        if (r < 0)
                                log_unit_full(u, IN_SET(r, -ENOENT, -EROFS, -EACCES) ? LOG_DEBUG : LOG_WARNING, r,
                                              "Failed to set blkio.weight: %m");

                        if (has_io) {
                                CGroupIODeviceWeight *w;

                                /* FIXME: no way to reset this list */
                                LIST_FOREACH(device_weights, w, c->io_device_weights) {
                                        weight = cgroup_weight_io_to_blkio(w->weight);

                                        log_cgroup_compat(u, "Applying IODeviceWeight %" PRIu64 " as BlockIODeviceWeight %" PRIu64 " for %s",
                                                          w->weight, weight, w->path);

                                        cgroup_apply_blkio_device_weight(u, w->path, weight);
                                }
                        } else if (has_blockio) {
                                CGroupBlockIODeviceWeight *w;

                                /* FIXME: no way to reset this list */
                                LIST_FOREACH(device_weights, w, c->blockio_device_weights)
                                        cgroup_apply_blkio_device_weight(u, w->path, w->weight);
                        }
                }

                /* Apply limits and free ones without config. */
                if (has_io) {
                        CGroupIODeviceLimit *l, *next;

                        LIST_FOREACH_SAFE(device_limits, l, next, c->io_device_limits) {
                                log_cgroup_compat(u, "Applying IO{Read|Write}Bandwidth %" PRIu64 " %" PRIu64 " as BlockIO{Read|Write}BandwidthMax for %s",
                                                  l->limits[CGROUP_IO_RBPS_MAX], l->limits[CGROUP_IO_WBPS_MAX], l->path);

                                if (!cgroup_apply_blkio_device_limit(u, l->path, l->limits[CGROUP_IO_RBPS_MAX], l->limits[CGROUP_IO_WBPS_MAX]))
                                        cgroup_context_free_io_device_limit(c, l);
                        }
                } else if (has_blockio) {
                        CGroupBlockIODeviceBandwidth *b, *next;

                        LIST_FOREACH_SAFE(device_bandwidths, b, next, c->blockio_device_bandwidths)
                                if (!cgroup_apply_blkio_device_limit(u, b->path, b->rbps, b->wbps))
                                        cgroup_context_free_blockio_device_bandwidth(c, b);
                }
        }

        if ((mask & CGROUP_MASK_MEMORY) && !is_root) {
                if (cg_all_unified() > 0) {
                        uint64_t max, swap_max = CGROUP_LIMIT_MAX;

                        if (cgroup_context_has_unified_memory_config(c)) {
                                max = c->memory_max;
                                swap_max = c->memory_swap_max;
                        } else {
                                max = c->memory_limit;

                                if (max != CGROUP_LIMIT_MAX)
                                        log_cgroup_compat(u, "Applying MemoryLimit %" PRIu64 " as MemoryMax", max);
                        }

                        cgroup_apply_unified_memory_limit(u, "memory.low", c->memory_low);
                        cgroup_apply_unified_memory_limit(u, "memory.high", c->memory_high);
                        cgroup_apply_unified_memory_limit(u, "memory.max", max);
                        cgroup_apply_unified_memory_limit(u, "memory.swap.max", swap_max);
                } else {
                        char buf[DECIMAL_STR_MAX(uint64_t) + 1];
                        uint64_t val;

                        if (cgroup_context_has_unified_memory_config(c)) {
                                val = c->memory_max;
                                log_cgroup_compat(u, "Applying MemoryMax %" PRIi64 " as MemoryLimit", val);
                        } else
                                val = c->memory_limit;

                        if (val == CGROUP_LIMIT_MAX)
                                strncpy(buf, "-1\n", sizeof(buf));
                        else
                                xsprintf(buf, "%" PRIu64 "\n", val);

                        r = cg_set_attribute("memory", path, "memory.limit_in_bytes", buf);
                        if (r < 0)
                                log_unit_full(u, IN_SET(r, -ENOENT, -EROFS, -EACCES) ? LOG_DEBUG : LOG_WARNING, r,
                                              "Failed to set memory.limit_in_bytes: %m");
                }
        }

        if ((mask & CGROUP_MASK_DEVICES) && !is_root) {
                CGroupDeviceAllow *a;

                /* Changing the devices list of a populated cgroup
                 * might result in EINVAL, hence ignore EINVAL
                 * here. */

                if (c->device_allow || c->device_policy != CGROUP_AUTO)
                        r = cg_set_attribute("devices", path, "devices.deny", "a");
                else
                        r = cg_set_attribute("devices", path, "devices.allow", "a");
                if (r < 0)
                        log_unit_full(u, IN_SET(r, -ENOENT, -EROFS, -EINVAL, -EACCES) ? LOG_DEBUG : LOG_WARNING, r,
                                      "Failed to reset devices.list: %m");

                if (c->device_policy == CGROUP_CLOSED ||
                    (c->device_policy == CGROUP_AUTO && c->device_allow)) {
                        static const char auto_devices[] =
                                "/dev/null\0" "rwm\0"
                                "/dev/zero\0" "rwm\0"
                                "/dev/full\0" "rwm\0"
                                "/dev/random\0" "rwm\0"
                                "/dev/urandom\0" "rwm\0"
                                "/dev/tty\0" "rwm\0"
                                "/dev/pts/ptmx\0" "rw\0" /* /dev/pts/ptmx may not be duplicated, but accessed */
                                /* Allow /run/elogind/inaccessible/{chr,blk} devices for mapping InaccessiblePaths */
                                /* Allow /run/systemd/inaccessible/{chr,blk} devices for mapping InaccessiblePaths */
                                "-/run/systemd/inaccessible/chr\0" "rwm\0"
                                "-/run/systemd/inaccessible/blk\0" "rwm\0";

                        const char *x, *y;

                        NULSTR_FOREACH_PAIR(x, y, auto_devices)
                                whitelist_device(path, x, y);

                        whitelist_major(path, "pts", 'c', "rw");
                }

                LIST_FOREACH(device_allow, a, c->device_allow) {
                        char acc[4], *val;
                        unsigned k = 0;

                        if (a->r)
                                acc[k++] = 'r';
                        if (a->w)
                                acc[k++] = 'w';
                        if (a->m)
                                acc[k++] = 'm';

                        if (k == 0)
                                continue;

                        acc[k++] = 0;

                        if (path_startswith(a->path, "/dev/"))
                                whitelist_device(path, a->path, acc);
                        else if ((val = startswith(a->path, "block-")))
                                whitelist_major(path, val, 'b', acc);
                        else if ((val = startswith(a->path, "char-")))
                                whitelist_major(path, val, 'c', acc);
                        else
                                log_unit_debug(u, "Ignoring device %s while writing cgroup attribute.", a->path);
                }
        }

        if ((mask & CGROUP_MASK_PIDS) && !is_root) {

                if (c->tasks_max != CGROUP_LIMIT_MAX) {
                        char buf[DECIMAL_STR_MAX(uint64_t) + 2];

                        sprintf(buf, "%" PRIu64 "\n", c->tasks_max);
                        r = cg_set_attribute("pids", path, "pids.max", buf);
                } else
                        r = cg_set_attribute("pids", path, "pids.max", "max");

                if (r < 0)
                        log_unit_full(u, IN_SET(r, -ENOENT, -EROFS, -EACCES) ? LOG_DEBUG : LOG_WARNING, r,
                                      "Failed to set pids.max: %m");
        }
}

CGroupMask cgroup_context_get_mask(CGroupContext *c) {
        CGroupMask mask = 0;

        /* Figure out which controllers we need */

        if (c->cpu_accounting ||
            cgroup_context_has_cpu_weight(c) ||
            cgroup_context_has_cpu_shares(c) ||
            c->cpu_quota_per_sec_usec != USEC_INFINITY)
                mask |= CGROUP_MASK_CPUACCT | CGROUP_MASK_CPU;

        if (cgroup_context_has_io_config(c) || cgroup_context_has_blockio_config(c))
                mask |= CGROUP_MASK_IO | CGROUP_MASK_BLKIO;

        if (c->memory_accounting ||
            c->memory_limit != CGROUP_LIMIT_MAX ||
            cgroup_context_has_unified_memory_config(c))
                mask |= CGROUP_MASK_MEMORY;

        if (c->device_allow ||
            c->device_policy != CGROUP_AUTO)
                mask |= CGROUP_MASK_DEVICES;

        if (c->tasks_accounting ||
            c->tasks_max != (uint64_t) -1)
                mask |= CGROUP_MASK_PIDS;

        return mask;
}

CGroupMask unit_get_own_mask(Unit *u) {
        CGroupContext *c;

        /* Returns the mask of controllers the unit needs for itself */

        c = unit_get_cgroup_context(u);
        if (!c)
                return 0;

        /* If delegation is turned on, then turn on all cgroups,
         * unless we are on the legacy hierarchy and the process we
         * fork into it is known to drop privileges, and hence
         * shouldn't get access to the controllers.
         *
         * Note that on the unified hierarchy it is safe to delegate
         * controllers to unprivileged services. */

        if (c->delegate) {
                ExecContext *e;

                e = unit_get_exec_context(u);
                if (!e ||
                    exec_context_maintains_privileges(e) ||
                    cg_all_unified() > 0)
                        return _CGROUP_MASK_ALL;
        }

        return cgroup_context_get_mask(c);
}

CGroupMask unit_get_members_mask(Unit *u) {
        assert(u);

        /* Returns the mask of controllers all of the unit's children
         * require, merged */

        if (u->cgroup_members_mask_valid)
                return u->cgroup_members_mask;

        u->cgroup_members_mask = 0;

        if (u->type == UNIT_SLICE) {
                Unit *member;
                Iterator i;

                SET_FOREACH(member, u->dependencies[UNIT_BEFORE], i) {

                        if (member == u)
                                continue;

                        if (UNIT_DEREF(member->slice) != u)
                                continue;

                        u->cgroup_members_mask |=
                                unit_get_own_mask(member) |
                                unit_get_members_mask(member);
                }
        }

        u->cgroup_members_mask_valid = true;
        return u->cgroup_members_mask;
}

CGroupMask unit_get_siblings_mask(Unit *u) {
        assert(u);

        /* Returns the mask of controllers all of the unit's siblings
         * require, i.e. the members mask of the unit's parent slice
         * if there is one. */

        if (UNIT_ISSET(u->slice))
                return unit_get_members_mask(UNIT_DEREF(u->slice));

        return unit_get_own_mask(u) | unit_get_members_mask(u);
}

CGroupMask unit_get_subtree_mask(Unit *u) {

        /* Returns the mask of this subtree, meaning of the group
         * itself and its children. */

        return unit_get_own_mask(u) | unit_get_members_mask(u);
}

CGroupMask unit_get_target_mask(Unit *u) {
        CGroupMask mask;

        /* This returns the cgroup mask of all controllers to enable
         * for a specific cgroup, i.e. everything it needs itself,
         * plus all that its children need, plus all that its siblings
         * need. This is primarily useful on the legacy cgroup
         * hierarchy, where we need to duplicate each cgroup in each
         * hierarchy that shall be enabled for it. */

        mask = unit_get_own_mask(u) | unit_get_members_mask(u) | unit_get_siblings_mask(u);
        mask &= u->manager->cgroup_supported;

        return mask;
}

CGroupMask unit_get_enable_mask(Unit *u) {
        CGroupMask mask;

        /* This returns the cgroup mask of all controllers to enable
         * for the children of a specific cgroup. This is primarily
         * useful for the unified cgroup hierarchy, where each cgroup
         * controls which controllers are enabled for its children. */

        mask = unit_get_members_mask(u);
        mask &= u->manager->cgroup_supported;

        return mask;
}

/* Recurse from a unit up through its containing slices, propagating
 * mask bits upward. A unit is also member of itself. */
void unit_update_cgroup_members_masks(Unit *u) {
        CGroupMask m;
        bool more;

        assert(u);

        /* Calculate subtree mask */
        m = unit_get_subtree_mask(u);

        /* See if anything changed from the previous invocation. If
         * not, we're done. */
        if (u->cgroup_subtree_mask_valid && m == u->cgroup_subtree_mask)
                return;

        more =
                u->cgroup_subtree_mask_valid &&
                ((m & ~u->cgroup_subtree_mask) != 0) &&
                ((~m & u->cgroup_subtree_mask) == 0);

        u->cgroup_subtree_mask = m;
        u->cgroup_subtree_mask_valid = true;

        if (UNIT_ISSET(u->slice)) {
                Unit *s = UNIT_DEREF(u->slice);

                if (more)
                        /* There's more set now than before. We
                         * propagate the new mask to the parent's mask
                         * (not caring if it actually was valid or
                         * not). */

                        s->cgroup_members_mask |= m;

                else
                        /* There's less set now than before (or we
                         * don't know), we need to recalculate
                         * everything, so let's invalidate the
                         * parent's members mask */

                        s->cgroup_members_mask_valid = false;

                /* And now make sure that this change also hits our
                 * grandparents */
                unit_update_cgroup_members_masks(s);
        }
}

static const char *migrate_callback(CGroupMask mask, void *userdata) {
        Unit *u = userdata;

        assert(mask != 0);
        assert(u);

        while (u) {
                if (u->cgroup_path &&
                    u->cgroup_realized &&
                    (u->cgroup_realized_mask & mask) == mask)
                        return u->cgroup_path;

                u = UNIT_DEREF(u->slice);
        }

        return NULL;
}

char *unit_default_cgroup_path(Unit *u) {
        _cleanup_free_ char *escaped = NULL, *slice = NULL;
        int r;

        assert(u);

        if (unit_has_name(u, SPECIAL_ROOT_SLICE))
                return strdup(u->manager->cgroup_root);

        if (UNIT_ISSET(u->slice) && !unit_has_name(UNIT_DEREF(u->slice), SPECIAL_ROOT_SLICE)) {
                r = cg_slice_to_path(UNIT_DEREF(u->slice)->id, &slice);
                if (r < 0)
                        return NULL;
        }

        escaped = cg_escape(u->id);
        if (!escaped)
                return NULL;

        if (slice)
                return strjoin(u->manager->cgroup_root, "/", slice, "/",
                               escaped);
        else
                return strjoin(u->manager->cgroup_root, "/", escaped);
}

int unit_set_cgroup_path(Unit *u, const char *path) {
        _cleanup_free_ char *p = NULL;
        int r;

        assert(u);

        if (path) {
                p = strdup(path);
                if (!p)
                        return -ENOMEM;
        } else
                p = NULL;

        if (streq_ptr(u->cgroup_path, p))
                return 0;

        if (p) {
                r = hashmap_put(u->manager->cgroup_unit, p, u);
                if (r < 0)
                        return r;
        }

        unit_release_cgroup(u);

        u->cgroup_path = p;
        p = NULL;

        return 1;
}

int unit_watch_cgroup(Unit *u) {
        _cleanup_free_ char *events = NULL;
        int r;

        assert(u);

        if (!u->cgroup_path)
                return 0;

        if (u->cgroup_inotify_wd >= 0)
                return 0;

        /* Only applies to the unified hierarchy */
        r = cg_unified_controller(SYSTEMD_CGROUP_CONTROLLER);
        if (r < 0)
                return log_error_errno(r, "Failed to determine whether the name=systemd hierarchy is unified: %m");
        if (r == 0)
                return 0;

        /* Don't watch the root slice, it's pointless. */
        if (unit_has_name(u, SPECIAL_ROOT_SLICE))
                return 0;

        r = hashmap_ensure_allocated(&u->manager->cgroup_inotify_wd_unit, &trivial_hash_ops);
        if (r < 0)
                return log_oom();

        r = cg_get_path(SYSTEMD_CGROUP_CONTROLLER, u->cgroup_path, "cgroup.events", &events);
        if (r < 0)
                return log_oom();

        u->cgroup_inotify_wd = inotify_add_watch(u->manager->cgroup_inotify_fd, events, IN_MODIFY);
        if (u->cgroup_inotify_wd < 0) {

                if (errno == ENOENT) /* If the directory is already
                                      * gone we don't need to track
                                      * it, so this is not an error */
                        return 0;

                return log_unit_error_errno(u, errno, "Failed to add inotify watch descriptor for control group %s: %m", u->cgroup_path);
        }

        r = hashmap_put(u->manager->cgroup_inotify_wd_unit, INT_TO_PTR(u->cgroup_inotify_wd), u);
        if (r < 0)
                return log_unit_error_errno(u, r, "Failed to add inotify watch descriptor to hash map: %m");

        return 0;
}

static int unit_create_cgroup(
                Unit *u,
                CGroupMask target_mask,
                CGroupMask enable_mask) {

        CGroupContext *c;
        int r;

        assert(u);

        c = unit_get_cgroup_context(u);
        if (!c)
                return 0;

        if (!u->cgroup_path) {
                _cleanup_free_ char *path = NULL;

                path = unit_default_cgroup_path(u);
                if (!path)
                        return log_oom();

                r = unit_set_cgroup_path(u, path);
                if (r == -EEXIST)
                        return log_unit_error_errno(u, r, "Control group %s exists already.", path);
                if (r < 0)
                        return log_unit_error_errno(u, r, "Failed to set unit's control group path to %s: %m", path);
        }

        /* First, create our own group */
        r = cg_create_everywhere(u->manager->cgroup_supported, target_mask, u->cgroup_path);
        if (r < 0)
                return log_unit_error_errno(u, r, "Failed to create cgroup %s: %m", u->cgroup_path);

        /* Start watching it */
        (void) unit_watch_cgroup(u);

        /* Enable all controllers we need */
        r = cg_enable_everywhere(u->manager->cgroup_supported, enable_mask, u->cgroup_path);
        if (r < 0)
                log_unit_warning_errno(u, r, "Failed to enable controllers on cgroup %s, ignoring: %m", u->cgroup_path);

        /* Keep track that this is now realized */
        u->cgroup_realized = true;
        u->cgroup_realized_mask = target_mask;
        u->cgroup_enabled_mask = enable_mask;

        if (u->type != UNIT_SLICE && !c->delegate) {

                /* Then, possibly move things over, but not if
                 * subgroups may contain processes, which is the case
                 * for slice and delegation units. */
                r = cg_migrate_everywhere(u->manager->cgroup_supported, u->cgroup_path, u->cgroup_path, migrate_callback, u);
                if (r < 0)
                        log_unit_warning_errno(u, r, "Failed to migrate cgroup from to %s, ignoring: %m", u->cgroup_path);
        }

        return 0;
}

int unit_attach_pids_to_cgroup(Unit *u) {
        int r;
        assert(u);

        r = unit_realize_cgroup(u);
        if (r < 0)
                return r;

        r = cg_attach_many_everywhere(u->manager->cgroup_supported, u->cgroup_path, u->pids, migrate_callback, u);
        if (r < 0)
                return r;

        return 0;
}

static void cgroup_xattr_apply(Unit *u) {
        char ids[SD_ID128_STRING_MAX];
        int r;

        assert(u);

        if (!MANAGER_IS_SYSTEM(u->manager))
                return;

        if (sd_id128_is_null(u->invocation_id))
                return;

        r = cg_set_xattr(SYSTEMD_CGROUP_CONTROLLER, u->cgroup_path,
                         "trusted.invocation_id",
                         sd_id128_to_string(u->invocation_id, ids), 32,
                         0);
        if (r < 0)
                log_unit_warning_errno(u, r, "Failed to set invocation ID on control group %s, ignoring: %m", u->cgroup_path);
}

static bool unit_has_mask_realized(Unit *u, CGroupMask target_mask, CGroupMask enable_mask) {
        assert(u);

        return u->cgroup_realized && u->cgroup_realized_mask == target_mask && u->cgroup_enabled_mask == enable_mask;
}

/* Check if necessary controllers and attributes for a unit are in place.
 *
 * If so, do nothing.
 * If not, create paths, move processes over, and set attributes.
 *
 * Returns 0 on success and < 0 on failure. */
static int unit_realize_cgroup_now(Unit *u, ManagerState state) {
        CGroupMask target_mask, enable_mask;
        int r;

        assert(u);

        if (u->in_cgroup_queue) {
                LIST_REMOVE(cgroup_queue, u->manager->cgroup_queue, u);
                u->in_cgroup_queue = false;
        }

        target_mask = unit_get_target_mask(u);
        enable_mask = unit_get_enable_mask(u);

        if (unit_has_mask_realized(u, target_mask, enable_mask))
                return 0;

        /* First, realize parents */
        if (UNIT_ISSET(u->slice)) {
                r = unit_realize_cgroup_now(UNIT_DEREF(u->slice), state);
                if (r < 0)
                        return r;
        }

        /* And then do the real work */
        r = unit_create_cgroup(u, target_mask, enable_mask);
        if (r < 0)
                return r;

        /* Finally, apply the necessary attributes. */
        cgroup_context_apply(u, target_mask, state);
        cgroup_xattr_apply(u);

        return 0;
}

static void unit_add_to_cgroup_queue(Unit *u) {

        if (u->in_cgroup_queue)
                return;

        LIST_PREPEND(cgroup_queue, u->manager->cgroup_queue, u);
        u->in_cgroup_queue = true;
}

unsigned manager_dispatch_cgroup_queue(Manager *m) {
        ManagerState state;
        unsigned n = 0;
        Unit *i;
        int r;

        state = manager_state(m);

        while ((i = m->cgroup_queue)) {
                assert(i->in_cgroup_queue);

                r = unit_realize_cgroup_now(i, state);
                if (r < 0)
                        log_warning_errno(r, "Failed to realize cgroups for queued unit %s, ignoring: %m", i->id);

                n++;
        }

        return n;
}

static void unit_queue_siblings(Unit *u) {
        Unit *slice;

        /* This adds the siblings of the specified unit and the
         * siblings of all parent units to the cgroup queue. (But
         * neither the specified unit itself nor the parents.) */

        while ((slice = UNIT_DEREF(u->slice))) {
                Iterator i;
                Unit *m;

                SET_FOREACH(m, slice->dependencies[UNIT_BEFORE], i) {
                        if (m == u)
                                continue;

                        /* Skip units that have a dependency on the slice
                         * but aren't actually in it. */
                        if (UNIT_DEREF(m->slice) != slice)
                                continue;

                        /* No point in doing cgroup application for units
                         * without active processes. */
                        if (UNIT_IS_INACTIVE_OR_FAILED(unit_active_state(m)))
                                continue;

                        /* If the unit doesn't need any new controllers
                         * and has current ones realized, it doesn't need
                         * any changes. */
                        if (unit_has_mask_realized(m, unit_get_target_mask(m), unit_get_enable_mask(m)))
                                continue;

                        unit_add_to_cgroup_queue(m);
                }

                u = slice;
        }
}

int unit_realize_cgroup(Unit *u) {
        assert(u);

        if (!UNIT_HAS_CGROUP_CONTEXT(u))
                return 0;

        /* So, here's the deal: when realizing the cgroups for this
         * unit, we need to first create all parents, but there's more
         * actually: for the weight-based controllers we also need to
         * make sure that all our siblings (i.e. units that are in the
         * same slice as we are) have cgroups, too. Otherwise, things
         * would become very uneven as each of their processes would
         * get as much resources as all our group together. This call
         * will synchronously create the parent cgroups, but will
         * defer work on the siblings to the next event loop
         * iteration. */

        /* Add all sibling slices to the cgroup queue. */
        unit_queue_siblings(u);

        /* And realize this one now (and apply the values) */
        return unit_realize_cgroup_now(u, manager_state(u->manager));
}

void unit_release_cgroup(Unit *u) {
        assert(u);

        /* Forgets all cgroup details for this cgroup */

        if (u->cgroup_path) {
                (void) hashmap_remove(u->manager->cgroup_unit, u->cgroup_path);
                u->cgroup_path = mfree(u->cgroup_path);
        }

        if (u->cgroup_inotify_wd >= 0) {
                if (inotify_rm_watch(u->manager->cgroup_inotify_fd, u->cgroup_inotify_wd) < 0)
                        log_unit_debug_errno(u, errno, "Failed to remove cgroup inotify watch %i for %s, ignoring", u->cgroup_inotify_wd, u->id);

                (void) hashmap_remove(u->manager->cgroup_inotify_wd_unit, INT_TO_PTR(u->cgroup_inotify_wd));
                u->cgroup_inotify_wd = -1;
        }
}

void unit_prune_cgroup(Unit *u) {
        int r;
        bool is_root_slice;

        assert(u);

        /* Removes the cgroup, if empty and possible, and stops watching it. */

        if (!u->cgroup_path)
                return;

        (void) unit_get_cpu_usage(u, NULL); /* Cache the last CPU usage value before we destroy the cgroup */

        is_root_slice = unit_has_name(u, SPECIAL_ROOT_SLICE);

        r = cg_trim_everywhere(u->manager->cgroup_supported, u->cgroup_path, !is_root_slice);
        if (r < 0) {
                log_unit_debug_errno(u, r, "Failed to destroy cgroup %s, ignoring: %m", u->cgroup_path);
                return;
        }

        if (is_root_slice)
                return;

        unit_release_cgroup(u);

        u->cgroup_realized = false;
        u->cgroup_realized_mask = 0;
        u->cgroup_enabled_mask = 0;
}

int unit_search_main_pid(Unit *u, pid_t *ret) {
        _cleanup_fclose_ FILE *f = NULL;
        pid_t pid = 0, npid, mypid;
        int r;

        assert(u);
        assert(ret);

        if (!u->cgroup_path)
                return -ENXIO;

        r = cg_enumerate_processes(SYSTEMD_CGROUP_CONTROLLER, u->cgroup_path, &f);
        if (r < 0)
                return r;

        mypid = getpid_cached();
        while (cg_read_pid(f, &npid) > 0)  {
                pid_t ppid;

                if (npid == pid)
                        continue;

                /* Ignore processes that aren't our kids */
                if (get_process_ppid(npid, &ppid) >= 0 && ppid != mypid)
                        continue;

                if (pid != 0)
                        /* Dang, there's more than one daemonized PID
                        in this group, so we don't know what process
                        is the main process. */

                        return -ENODATA;

                pid = npid;
        }

        *ret = pid;
        return 0;
}

static int unit_watch_pids_in_path(Unit *u, const char *path) {
        _cleanup_closedir_ DIR *d = NULL;
        _cleanup_fclose_ FILE *f = NULL;
        int ret = 0, r;

        assert(u);
        assert(path);

        r = cg_enumerate_processes(SYSTEMD_CGROUP_CONTROLLER, path, &f);
        if (r < 0)
                ret = r;
        else {
                pid_t pid;

                while ((r = cg_read_pid(f, &pid)) > 0) {
                        r = unit_watch_pid(u, pid);
                        if (r < 0 && ret >= 0)
                                ret = r;
                }

                if (r < 0 && ret >= 0)
                        ret = r;
        }

        r = cg_enumerate_subgroups(SYSTEMD_CGROUP_CONTROLLER, path, &d);
        if (r < 0) {
                if (ret >= 0)
                        ret = r;
        } else {
                char *fn;

                while ((r = cg_read_subgroup(d, &fn)) > 0) {
                        _cleanup_free_ char *p = NULL;

                        p = strjoin(path, "/", fn);
                        free(fn);

                        if (!p)
                                return -ENOMEM;

                        r = unit_watch_pids_in_path(u, p);
                        if (r < 0 && ret >= 0)
                                ret = r;
                }

                if (r < 0 && ret >= 0)
                        ret = r;
        }

        return ret;
}

int unit_watch_all_pids(Unit *u) {
        int r;

        assert(u);

        /* Adds all PIDs from our cgroup to the set of PIDs we
         * watch. This is a fallback logic for cases where we do not
         * get reliable cgroup empty notifications: we try to use
         * SIGCHLD as replacement. */

        if (!u->cgroup_path)
                return -ENOENT;

        r = cg_unified_controller(SYSTEMD_CGROUP_CONTROLLER);
        if (r < 0)
                return r;
        if (r > 0) /* On unified we can use proper notifications */
                return 0;

        return unit_watch_pids_in_path(u, u->cgroup_path);
}

int unit_notify_cgroup_empty(Unit *u) {
        int r;

        assert(u);

        if (!u->cgroup_path)
                return 0;

        r = cg_is_empty_recursive(SYSTEMD_CGROUP_CONTROLLER, u->cgroup_path);
        if (r <= 0)
                return r;

        unit_add_to_gc_queue(u);

        if (UNIT_VTABLE(u)->notify_cgroup_empty)
                UNIT_VTABLE(u)->notify_cgroup_empty(u);

        return 0;
}

static int on_cgroup_inotify_event(sd_event_source *s, int fd, uint32_t revents, void *userdata) {
        Manager *m = userdata;

        assert(s);
        assert(fd >= 0);
        assert(m);

        for (;;) {
                union inotify_event_buffer buffer;
                struct inotify_event *e;
                ssize_t l;

                l = read(fd, &buffer, sizeof(buffer));
                if (l < 0) {
                        if (errno == EINTR || errno == EAGAIN)
                                return 0;

                        return log_error_errno(errno, "Failed to read control group inotify events: %m");
                }

                FOREACH_INOTIFY_EVENT(e, buffer, l) {
                        Unit *u;

                        if (e->wd < 0)
                                /* Queue overflow has no watch descriptor */
                                continue;

                        if (e->mask & IN_IGNORED)
                                /* The watch was just removed */
                                continue;

                        u = hashmap_get(m->cgroup_inotify_wd_unit, INT_TO_PTR(e->wd));
                        if (!u) /* Not that inotify might deliver
                                 * events for a watch even after it
                                 * was removed, because it was queued
                                 * before the removal. Let's ignore
                                 * this here safely. */
                                continue;

                        (void) unit_notify_cgroup_empty(u);
                }
        }
}
#endif // 0

int manager_setup_cgroup(Manager *m) {
        _cleanup_free_ char *path = NULL;
        const char *scope_path;
        CGroupController c;
        int r, all_unified;
        char *e;

        assert(m);

        /* 1. Determine hierarchy */
        m->cgroup_root = mfree(m->cgroup_root);
#if 0 /// elogind is not init and must therefore search for PID 1 instead of self.
        r = cg_pid_get_path(SYSTEMD_CGROUP_CONTROLLER, 0, &m->cgroup_root);
#else
        r = cg_pid_get_path(SYSTEMD_CGROUP_CONTROLLER, 1, &m->cgroup_root);
#endif // 0
        if (r < 0)
                return log_error_errno(r, "Cannot determine cgroup we are running in: %m");

#if 0 /// elogind does not support systemd scopes and slices
        /* Chop off the init scope, if we are already located in it */
        e = endswith(m->cgroup_root, "/" SPECIAL_INIT_SCOPE);

        /* LEGACY: Also chop off the system slice if we are in
         * it. This is to support live upgrades from older systemd
         * versions where PID 1 was moved there. Also see
         * cg_get_root_path(). */
        if (!e && MANAGER_IS_SYSTEM(m)) {
                e = endswith(m->cgroup_root, "/" SPECIAL_SYSTEM_SLICE);
                if (!e)
                        e = endswith(m->cgroup_root, "/system"); /* even more legacy */
        }
        if (e)
                *e = 0;
#endif // 0

        /* And make sure to store away the root value without trailing
         * slash, even for the root dir, so that we can easily prepend
         * it everywhere. */
        while ((e = endswith(m->cgroup_root, "/")))
                *e = 0;
        log_debug_elogind("Cgroup Controller \"%s\" -> root \"%s\"",
                          SYSTEMD_CGROUP_CONTROLLER, m->cgroup_root);

        /* 2. Show data */
        r = cg_get_path(SYSTEMD_CGROUP_CONTROLLER, m->cgroup_root, NULL, &path);
        if (r < 0)
                return log_error_errno(r, "Cannot find cgroup mount point: %m");

        r = cg_unified_flush();
        if (r < 0)
                return log_error_errno(r, "Couldn't determine if we are running in the unified hierarchy: %m");

        all_unified = cg_all_unified();
        if (r < 0)
                return log_error_errno(r, "Couldn't determine whether we are in all unified mode: %m");
        if (r > 0)
                log_debug("Unified cgroup hierarchy is located at %s.", path);
        else {
                r = cg_unified_controller(SYSTEMD_CGROUP_CONTROLLER);
                if (r < 0)
                        return log_error_errno(r, "Failed to determine whether systemd's own controller is in unified mode: %m");
                if (r > 0)
                        log_debug("Unified cgroup hierarchy is located at %s. Controllers are on legacy hierarchies.", path);
                else
                        log_debug("Using cgroup controller " SYSTEMD_CGROUP_CONTROLLER_LEGACY ". File system hierarchy is at %s.", path);
        }

#if 0 /// elogind is not init, and does not install the agent here.
        /* 3. Install agent */
        if (cg_unified_controller(SYSTEMD_CGROUP_CONTROLLER) > 0) {

                /* In the unified hierarchy we can get
                 * cgroup empty notifications via inotify. */

                m->cgroup_inotify_event_source = sd_event_source_unref(m->cgroup_inotify_event_source);
                safe_close(m->cgroup_inotify_fd);

                m->cgroup_inotify_fd = inotify_init1(IN_NONBLOCK|IN_CLOEXEC);
                if (m->cgroup_inotify_fd < 0)
                        return log_error_errno(errno, "Failed to create control group inotify object: %m");

                r = sd_event_add_io(m->event, &m->cgroup_inotify_event_source, m->cgroup_inotify_fd, EPOLLIN, on_cgroup_inotify_event, m);
                if (r < 0)
                        return log_error_errno(r, "Failed to watch control group inotify object: %m");

                /* Process cgroup empty notifications early, but after service notifications and SIGCHLD. Also
                 * see handling of cgroup agent notifications, for the classic cgroup hierarchy support. */
                r = sd_event_source_set_priority(m->cgroup_inotify_event_source, SD_EVENT_PRIORITY_NORMAL-5);
                if (r < 0)
                        return log_error_errno(r, "Failed to set priority of inotify event source: %m");

                (void) sd_event_source_set_description(m->cgroup_inotify_event_source, "cgroup-inotify");

        } else if (MANAGER_IS_SYSTEM(m) && m->test_run_flags == 0) {

                /* On the legacy hierarchy we only get notifications via cgroup agents. (Which isn't really reliable,
                 * since it does not generate events when control groups with children run empty. */

                r = cg_install_release_agent(SYSTEMD_CGROUP_CONTROLLER, SYSTEMD_CGROUP_AGENT_PATH);
                if (r < 0)
                        log_warning_errno(r, "Failed to install release agent, ignoring: %m");
                else if (r > 0)
                        log_debug("Installed release agent.");
                else if (r == 0)
                        log_debug("Release agent already installed.");
        }

        /* 4. Make sure we are in the special "init.scope" unit in the root slice. */
        scope_path = strjoina(m->cgroup_root, "/" SPECIAL_INIT_SCOPE);
        r = cg_create_and_attach(SYSTEMD_CGROUP_CONTROLLER, scope_path, 0);
#else
        /* Note:
                * This method is in core, and normally called by systemd
                * being init. As elogind is never init, we can not install
                * our agent here. We do so when mounting our cgroup file
                * system, so only if elogind is its own tiny controller.
                * Further, elogind is not meant to run in systemd init scope. */
        if (MANAGER_IS_SYSTEM(m))
                // we are our own cgroup controller
                scope_path = strjoina("");
        else if (streq(m->cgroup_root, "/elogind"))
                // root already is our cgroup
                scope_path = strjoina(m->cgroup_root);
        else
                // we have to create our own group
                scope_path = strjoina(m->cgroup_root, "/elogind");
        r = cg_create_and_attach(SYSTEMD_CGROUP_CONTROLLER, scope_path, 0);
#endif // 0
        if (r < 0)
                return log_error_errno(r, "Failed to create %s control group: %m", scope_path);
        log_debug_elogind("Created control group \"%s\"", scope_path);

#if 0 /// elogind is not a "sub-controller" like systemd, so migration is not needed.
        /* also, move all other userspace processes remaining
         * in the root cgroup into that scope. */
        r = cg_migrate(SYSTEMD_CGROUP_CONTROLLER, m->cgroup_root, SYSTEMD_CGROUP_CONTROLLER, scope_path, 0);
        if (r < 0)
                log_warning_errno(r, "Couldn't move remaining userspace processes, ignoring: %m");
#endif // 0

        /* 5. And pin it, so that it cannot be unmounted */
        safe_close(m->pin_cgroupfs_fd);
        m->pin_cgroupfs_fd = open(path, O_RDONLY|O_CLOEXEC|O_DIRECTORY|O_NOCTTY|O_NONBLOCK);
        if (m->pin_cgroupfs_fd < 0)
                return log_error_errno(errno, "Failed to open pin file: %m");

        /* 6.  Always enable hierarchical support if it exists... */
        if (!all_unified && m->test_run_flags == 0)
                (void) cg_set_attribute("memory", "/", "memory.use_hierarchy", "1");

        /* 7. Figure out which controllers are supported */
        r = cg_mask_supported(&m->cgroup_supported);
        if (r < 0)
                return log_error_errno(r, "Failed to determine supported controllers: %m");

        for (c = 0; c < _CGROUP_CONTROLLER_MAX; c++)
                log_debug("Controller '%s' supported: %s", cgroup_controller_to_string(c), yes_no(m->cgroup_supported & CGROUP_CONTROLLER_TO_MASK(c)));

        return 0;
}

void manager_shutdown_cgroup(Manager *m, bool delete) {
        assert(m);

        /* We can't really delete the group, since we are in it. But
         * let's trim it. */
        if (delete && m->cgroup_root)
                (void) cg_trim(SYSTEMD_CGROUP_CONTROLLER, m->cgroup_root, false);

#if 0 /// elogind does not support the unified hierarchy, yet.
        m->cgroup_inotify_wd_unit = hashmap_free(m->cgroup_inotify_wd_unit);

        m->cgroup_inotify_event_source = sd_event_source_unref(m->cgroup_inotify_event_source);
        m->cgroup_inotify_fd = safe_close(m->cgroup_inotify_fd);
#endif // 0

        m->pin_cgroupfs_fd = safe_close(m->pin_cgroupfs_fd);

        m->cgroup_root = mfree(m->cgroup_root);
}

#if 0 /// UNNEEDED by elogind
Unit* manager_get_unit_by_cgroup(Manager *m, const char *cgroup) {
        char *p;
        Unit *u;

        assert(m);
        assert(cgroup);

        u = hashmap_get(m->cgroup_unit, cgroup);
        if (u)
                return u;

        p = strdupa(cgroup);
        for (;;) {
                char *e;

                e = strrchr(p, '/');
                if (!e || e == p)
                        return hashmap_get(m->cgroup_unit, SPECIAL_ROOT_SLICE);

                *e = 0;

                u = hashmap_get(m->cgroup_unit, p);
                if (u)
                        return u;
        }
}

Unit *manager_get_unit_by_pid_cgroup(Manager *m, pid_t pid) {
        _cleanup_free_ char *cgroup = NULL;
        int r;

        assert(m);

        if (pid <= 0)
                return NULL;

        r = cg_pid_get_path(SYSTEMD_CGROUP_CONTROLLER, pid, &cgroup);
        if (r < 0)
                return NULL;

        return manager_get_unit_by_cgroup(m, cgroup);
}

Unit *manager_get_unit_by_pid(Manager *m, pid_t pid) {
        Unit *u;

        assert(m);

        if (pid <= 0)
                return NULL;

        if (pid == 1)
                return hashmap_get(m->units, SPECIAL_INIT_SCOPE);

        u = hashmap_get(m->watch_pids1, PID_TO_PTR(pid));
        if (u)
                return u;

        u = hashmap_get(m->watch_pids2, PID_TO_PTR(pid));
        if (u)
                return u;

        return manager_get_unit_by_pid_cgroup(m, pid);
}
#endif // 0

#if 0 /// elogind must substitute this with its own variant
int manager_notify_cgroup_empty(Manager *m, const char *cgroup) {
        Unit *u;

        assert(m);
        assert(cgroup);

        log_debug("Got cgroup empty notification for: %s", cgroup);

        u = manager_get_unit_by_cgroup(m, cgroup);
        if (!u)
                return 0;

        return unit_notify_cgroup_empty(u);
}
#else
int manager_notify_cgroup_empty(Manager *m, const char *cgroup) {
        Session *s;

        assert(m);
        assert(cgroup);

        log_debug("Got cgroup empty notification for: %s", cgroup);

        s = hashmap_get(m->sessions, cgroup);

        if (s) {
                session_finalize(s);
                session_free(s);
        } else
                log_warning("Session not found: %s", cgroup);

        return 0;
}
#endif // 0
#if 0 /// UNNEEDED by elogind
int unit_get_memory_current(Unit *u, uint64_t *ret) {
        _cleanup_free_ char *v = NULL;
        int r;

        assert(u);
        assert(ret);

        if (!u->cgroup_path)
                return -ENODATA;

        if ((u->cgroup_realized_mask & CGROUP_MASK_MEMORY) == 0)
                return -ENODATA;

        r = cg_all_unified();
        if (r < 0)
                return r;
        if (r > 0)
                r = cg_get_attribute("memory", u->cgroup_path, "memory.current", &v);
        else
                r = cg_get_attribute("memory", u->cgroup_path, "memory.usage_in_bytes", &v);
        if (r == -ENOENT)
                return -ENODATA;
        if (r < 0)
                return r;

        return safe_atou64(v, ret);
}

int unit_get_tasks_current(Unit *u, uint64_t *ret) {
        _cleanup_free_ char *v = NULL;
        int r;

        assert(u);
        assert(ret);

        if (!u->cgroup_path)
                return -ENODATA;

        if ((u->cgroup_realized_mask & CGROUP_MASK_PIDS) == 0)
                return -ENODATA;

        r = cg_get_attribute("pids", u->cgroup_path, "pids.current", &v);
        if (r == -ENOENT)
                return -ENODATA;
        if (r < 0)
                return r;

        return safe_atou64(v, ret);
}

static int unit_get_cpu_usage_raw(Unit *u, nsec_t *ret) {
        _cleanup_free_ char *v = NULL;
        uint64_t ns;
        int r;

        assert(u);
        assert(ret);

        if (!u->cgroup_path)
                return -ENODATA;

        r = cg_all_unified();
        if (r < 0)
                return r;
        if (r > 0) {
                const char *keys[] = { "usage_usec", NULL };
                _cleanup_free_ char *val = NULL;
                uint64_t us;

                if ((u->cgroup_realized_mask & CGROUP_MASK_CPU) == 0)
                        return -ENODATA;

                r = cg_get_keyed_attribute("cpu", u->cgroup_path, "cpu.stat", keys, &val);
                if (r < 0)
                        return r;

                r = safe_atou64(val, &us);
                if (r < 0)
                        return r;

                ns = us * NSEC_PER_USEC;
        } else {
                if ((u->cgroup_realized_mask & CGROUP_MASK_CPUACCT) == 0)
                        return -ENODATA;

                r = cg_get_attribute("cpuacct", u->cgroup_path, "cpuacct.usage", &v);
                if (r == -ENOENT)
                        return -ENODATA;
                if (r < 0)
                        return r;

                r = safe_atou64(v, &ns);
                if (r < 0)
                        return r;
        }

        *ret = ns;
        return 0;
}

int unit_get_cpu_usage(Unit *u, nsec_t *ret) {
        nsec_t ns;
        int r;

        assert(u);

        /* Retrieve the current CPU usage counter. This will subtract the CPU counter taken when the unit was
         * started. If the cgroup has been removed already, returns the last cached value. To cache the value, simply
         * call this function with a NULL return value. */

        r = unit_get_cpu_usage_raw(u, &ns);
        if (r == -ENODATA && u->cpu_usage_last != NSEC_INFINITY) {
                /* If we can't get the CPU usage anymore (because the cgroup was already removed, for example), use our
                 * cached value. */

                if (ret)
                        *ret = u->cpu_usage_last;
                return 0;
        }
        if (r < 0)
                return r;

        if (ns > u->cpu_usage_base)
                ns -= u->cpu_usage_base;
        else
                ns = 0;

        u->cpu_usage_last = ns;
        if (ret)
                *ret = ns;

        return 0;
}

int unit_reset_cpu_usage(Unit *u) {
        nsec_t ns;
        int r;

        assert(u);

        u->cpu_usage_last = NSEC_INFINITY;

        r = unit_get_cpu_usage_raw(u, &ns);
        if (r < 0) {
                u->cpu_usage_base = 0;
                return r;
        }

        u->cpu_usage_base = ns;
        return 0;
}

bool unit_cgroup_delegate(Unit *u) {
        CGroupContext *c;

        assert(u);

        c = unit_get_cgroup_context(u);
        if (!c)
                return false;

        return c->delegate;
}

void unit_invalidate_cgroup(Unit *u, CGroupMask m) {
        assert(u);

        if (!UNIT_HAS_CGROUP_CONTEXT(u))
                return;

        if (m == 0)
                return;

        /* always invalidate compat pairs together */
        if (m & (CGROUP_MASK_IO | CGROUP_MASK_BLKIO))
                m |= CGROUP_MASK_IO | CGROUP_MASK_BLKIO;

        if (m & (CGROUP_MASK_CPU | CGROUP_MASK_CPUACCT))
                m |= CGROUP_MASK_CPU | CGROUP_MASK_CPUACCT;

        if ((u->cgroup_realized_mask & m) == 0)
                return;

        u->cgroup_realized_mask &= ~m;
        unit_add_to_cgroup_queue(u);
}

void manager_invalidate_startup_units(Manager *m) {
        Iterator i;
        Unit *u;

        assert(m);

        SET_FOREACH(u, m->startup_units, i)
                unit_invalidate_cgroup(u, CGROUP_MASK_CPU|CGROUP_MASK_IO|CGROUP_MASK_BLKIO);
}

static const char* const cgroup_device_policy_table[_CGROUP_DEVICE_POLICY_MAX] = {
        [CGROUP_AUTO] = "auto",
        [CGROUP_CLOSED] = "closed",
        [CGROUP_STRICT] = "strict",
};

DEFINE_STRING_TABLE_LOOKUP(cgroup_device_policy, CGroupDevicePolicy);
#endif // 0