summaryrefslogtreecommitdiff
path: root/src/core/main.c
blob: f36f6c4c9e9e3e5ffd4907e9d7b071a762a82419 (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
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
/* SPDX-License-Identifier: LGPL-2.1-or-later */

#include <errno.h>
#include <fcntl.h>
#include <getopt.h>
#include <linux/oom.h>
#include <sys/mount.h>
#include <sys/prctl.h>
#include <sys/utsname.h>
#include <unistd.h>
#if HAVE_SECCOMP
#include <seccomp.h>
#endif
#if HAVE_VALGRIND_VALGRIND_H
#  include <valgrind/valgrind.h>
#endif

#include "sd-bus.h"
#include "sd-daemon.h"
#include "sd-messages.h"

#include "alloc-util.h"
#include "apparmor-setup.h"
#include "architecture.h"
#include "argv-util.h"
#if HAVE_LIBBPF
#include "bpf-lsm.h"
#endif
#include "build.h"
#include "bus-error.h"
#include "bus-util.h"
#include "capability-util.h"
#include "cgroup-util.h"
#include "clock-util.h"
#include "conf-parser.h"
#include "cpu-set-util.h"
#include "crash-handler.h"
#include "dbus-manager.h"
#include "dbus.h"
#include "constants.h"
#include "dev-setup.h"
#include "efi-random.h"
#include "efivars.h"
#include "emergency-action.h"
#include "env-util.h"
#include "exit-status.h"
#include "fd-util.h"
#include "fdset.h"
#include "fileio.h"
#include "format-util.h"
#include "fs-util.h"
#include "getopt-defs.h"
#include "hexdecoct.h"
#include "hostname-setup.h"
#include "ima-setup.h"
#include "import-creds.h"
#include "initrd-util.h"
#include "killall.h"
#include "kmod-setup.h"
#include "limits-util.h"
#include "load-fragment.h"
#include "log.h"
#include "loopback-setup.h"
#include "machine-id-setup.h"
#include "main.h"
#include "manager.h"
#include "manager-dump.h"
#include "manager-serialize.h"
#include "mkdir-label.h"
#include "mount-setup.h"
#include "os-util.h"
#include "pager.h"
#include "parse-argument.h"
#include "parse-util.h"
#include "path-util.h"
#include "pretty-print.h"
#include "proc-cmdline.h"
#include "process-util.h"
#include "psi-util.h"
#include "random-util.h"
#include "rlimit-util.h"
#if HAVE_SECCOMP
#include "seccomp-util.h"
#endif
#include "selinux-setup.h"
#include "selinux-util.h"
#include "signal-util.h"
#include "smack-setup.h"
#include "special.h"
#include "stat-util.h"
#include "stdio-util.h"
#include "strv.h"
#include "switch-root.h"
#include "sysctl-util.h"
#include "terminal-util.h"
#include "time-util.h"
#include "umask-util.h"
#include "user-util.h"
#include "virt.h"
#include "watchdog.h"

#if HAS_FEATURE_ADDRESS_SANITIZER
#include <sanitizer/lsan_interface.h>
#endif

#define DEFAULT_TASKS_MAX ((TasksMax) { 15U, 100U }) /* 15% */

static enum {
        ACTION_RUN,
        ACTION_HELP,
        ACTION_VERSION,
        ACTION_TEST,
        ACTION_DUMP_CONFIGURATION_ITEMS,
        ACTION_DUMP_BUS_PROPERTIES,
        ACTION_BUS_INTROSPECT,
} arg_action = ACTION_RUN;

static const char *arg_bus_introspect = NULL;

/* Those variables are initialized to 0 automatically, so we avoid uninitialized memory access.  Real
 * defaults are assigned in reset_arguments() below. */
static char *arg_default_unit;
static RuntimeScope arg_runtime_scope;
bool arg_dump_core;
int arg_crash_chvt;
bool arg_crash_shell;
bool arg_crash_reboot;
static char *arg_confirm_spawn;
static ShowStatus arg_show_status;
static StatusUnitFormat arg_status_unit_format;
static bool arg_switched_root;
static PagerFlags arg_pager_flags;
static bool arg_service_watchdogs;
static ExecOutput arg_default_std_output;
static ExecOutput arg_default_std_error;
static usec_t arg_default_restart_usec;
static usec_t arg_default_timeout_start_usec;
static usec_t arg_default_timeout_stop_usec;
static usec_t arg_default_timeout_abort_usec;
static usec_t arg_default_device_timeout_usec;
static bool arg_default_timeout_abort_set;
static usec_t arg_default_start_limit_interval;
static unsigned arg_default_start_limit_burst;
static usec_t arg_runtime_watchdog;
static usec_t arg_reboot_watchdog;
static usec_t arg_kexec_watchdog;
static usec_t arg_pretimeout_watchdog;
static char *arg_early_core_pattern;
static char *arg_watchdog_pretimeout_governor;
static char *arg_watchdog_device;
static char **arg_default_environment;
static char **arg_manager_environment;
static struct rlimit *arg_default_rlimit[_RLIMIT_MAX];
static uint64_t arg_capability_bounding_set;
static bool arg_no_new_privs;
static nsec_t arg_timer_slack_nsec;
static usec_t arg_default_timer_accuracy_usec;
static Set* arg_syscall_archs;
static FILE* arg_serialization;
static int arg_default_cpu_accounting;
static bool arg_default_io_accounting;
static bool arg_default_ip_accounting;
static bool arg_default_blockio_accounting;
static bool arg_default_memory_accounting;
static bool arg_default_tasks_accounting;
static TasksMax arg_default_tasks_max;
static usec_t arg_default_memory_pressure_threshold_usec;
static CGroupPressureWatch arg_default_memory_pressure_watch;
static sd_id128_t arg_machine_id;
static EmergencyAction arg_cad_burst_action;
static OOMPolicy arg_default_oom_policy;
static CPUSet arg_cpu_affinity;
static NUMAPolicy arg_numa_policy;
static usec_t arg_clock_usec;
static void *arg_random_seed;
static size_t arg_random_seed_size;
static int arg_default_oom_score_adjust;
static bool arg_default_oom_score_adjust_set;
static char *arg_default_smack_process_label;
static usec_t arg_reload_limit_interval_sec;
static unsigned arg_reload_limit_burst;

/* A copy of the original environment block */
static char **saved_env = NULL;

static int parse_configuration(const struct rlimit *saved_rlimit_nofile,
                               const struct rlimit *saved_rlimit_memlock);

static int manager_find_user_config_paths(char ***ret_files, char ***ret_dirs) {
        _cleanup_free_ char *base = NULL;
        _cleanup_strv_free_ char **files = NULL, **dirs = NULL;
        int r;

        r = xdg_user_config_dir(&base, "/systemd");
        if (r < 0)
                return r;

        r = strv_extendf(&files, "%s/user.conf", base);
        if (r < 0)
                return r;

        r = strv_extend(&files, PKGSYSCONFDIR "/user.conf");
        if (r < 0)
                return r;

        r = strv_consume(&dirs, TAKE_PTR(base));
        if (r < 0)
                return r;

        r = strv_extend_strv(&dirs, CONF_PATHS_STRV("systemd"), false);
        if (r < 0)
                return r;

        *ret_files = TAKE_PTR(files);
        *ret_dirs = TAKE_PTR(dirs);
        return 0;
}

static int console_setup(void) {
        _cleanup_close_ int tty_fd = -EBADF;
        int r;

        tty_fd = open_terminal("/dev/console", O_WRONLY|O_NOCTTY|O_CLOEXEC);
        if (tty_fd < 0)
                return log_error_errno(tty_fd, "Failed to open /dev/console: %m");

        /* We don't want to force text mode.  plymouth may be showing
         * pictures already from initrd. */
        r = reset_terminal_fd(tty_fd, false);
        if (r < 0)
                return log_error_errno(r, "Failed to reset /dev/console: %m");

        return 0;
}

static int set_machine_id(const char *m) {
        sd_id128_t t;
        assert(m);

        if (sd_id128_from_string(m, &t) < 0)
                return -EINVAL;

        if (sd_id128_is_null(t))
                return -EINVAL;

        arg_machine_id = t;
        return 0;
}

static int parse_proc_cmdline_item(const char *key, const char *value, void *data) {
        int r;

        assert(key);

        if (STR_IN_SET(key, "systemd.unit", "rd.systemd.unit")) {

                if (proc_cmdline_value_missing(key, value))
                        return 0;

                if (!unit_name_is_valid(value, UNIT_NAME_PLAIN|UNIT_NAME_INSTANCE))
                        log_warning("Unit name specified on %s= is not valid, ignoring: %s", key, value);
                else if (in_initrd() == !!startswith(key, "rd."))
                        return free_and_strdup_warn(&arg_default_unit, value);

        } else if (proc_cmdline_key_streq(key, "systemd.dump_core")) {

                r = value ? parse_boolean(value) : true;
                if (r < 0)
                        log_warning_errno(r, "Failed to parse dump core switch %s, ignoring: %m", value);
                else
                        arg_dump_core = r;

        } else if (proc_cmdline_key_streq(key, "systemd.early_core_pattern")) {

                if (proc_cmdline_value_missing(key, value))
                        return 0;

                if (path_is_absolute(value))
                        (void) parse_path_argument(value, false, &arg_early_core_pattern);
                else
                        log_warning("Specified core pattern '%s' is not an absolute path, ignoring.", value);

        } else if (proc_cmdline_key_streq(key, "systemd.crash_chvt")) {

                if (!value)
                        arg_crash_chvt = 0; /* turn on */
                else {
                        r = parse_crash_chvt(value, &arg_crash_chvt);
                        if (r < 0)
                                log_warning_errno(r, "Failed to parse crash chvt switch %s, ignoring: %m", value);
                }

        } else if (proc_cmdline_key_streq(key, "systemd.crash_shell")) {

                r = value ? parse_boolean(value) : true;
                if (r < 0)
                        log_warning_errno(r, "Failed to parse crash shell switch %s, ignoring: %m", value);
                else
                        arg_crash_shell = r;

        } else if (proc_cmdline_key_streq(key, "systemd.crash_reboot")) {

                r = value ? parse_boolean(value) : true;
                if (r < 0)
                        log_warning_errno(r, "Failed to parse crash reboot switch %s, ignoring: %m", value);
                else
                        arg_crash_reboot = r;

        } else if (proc_cmdline_key_streq(key, "systemd.confirm_spawn")) {
                char *s;

                r = parse_confirm_spawn(value, &s);
                if (r < 0)
                        log_warning_errno(r, "Failed to parse confirm_spawn switch %s, ignoring: %m", value);
                else
                        free_and_replace(arg_confirm_spawn, s);

        } else if (proc_cmdline_key_streq(key, "systemd.service_watchdogs")) {

                r = value ? parse_boolean(value) : true;
                if (r < 0)
                        log_warning_errno(r, "Failed to parse service watchdog switch %s, ignoring: %m", value);
                else
                        arg_service_watchdogs = r;

        } else if (proc_cmdline_key_streq(key, "systemd.show_status")) {

                if (value) {
                        r = parse_show_status(value, &arg_show_status);
                        if (r < 0)
                                log_warning_errno(r, "Failed to parse show status switch %s, ignoring: %m", value);
                } else
                        arg_show_status = SHOW_STATUS_YES;

        } else if (proc_cmdline_key_streq(key, "systemd.status_unit_format")) {

                if (proc_cmdline_value_missing(key, value))
                        return 0;

                r = status_unit_format_from_string(value);
                if (r < 0)
                        log_warning_errno(r, "Failed to parse %s=%s, ignoring: %m", key, value);
                else
                        arg_status_unit_format = r;

        } else if (proc_cmdline_key_streq(key, "systemd.default_standard_output")) {

                if (proc_cmdline_value_missing(key, value))
                        return 0;

                r = exec_output_from_string(value);
                if (r < 0)
                        log_warning_errno(r, "Failed to parse default standard output switch %s, ignoring: %m", value);
                else
                        arg_default_std_output = r;

        } else if (proc_cmdline_key_streq(key, "systemd.default_standard_error")) {

                if (proc_cmdline_value_missing(key, value))
                        return 0;

                r = exec_output_from_string(value);
                if (r < 0)
                        log_warning_errno(r, "Failed to parse default standard error switch %s, ignoring: %m", value);
                else
                        arg_default_std_error = r;

        } else if (streq(key, "systemd.setenv")) {

                if (proc_cmdline_value_missing(key, value))
                        return 0;

                if (!env_assignment_is_valid(value))
                        log_warning("Environment variable assignment '%s' is not valid. Ignoring.", value);
                else {
                        r = strv_env_replace_strdup(&arg_default_environment, value);
                        if (r < 0)
                                return log_oom();
                }

        } else if (proc_cmdline_key_streq(key, "systemd.machine_id")) {

                if (proc_cmdline_value_missing(key, value))
                        return 0;

                r = set_machine_id(value);
                if (r < 0)
                        log_warning_errno(r, "MachineID '%s' is not valid, ignoring: %m", value);

        } else if (proc_cmdline_key_streq(key, "systemd.default_timeout_start_sec")) {

                if (proc_cmdline_value_missing(key, value))
                        return 0;

                r = parse_sec(value, &arg_default_timeout_start_usec);
                if (r < 0)
                        log_warning_errno(r, "Failed to parse default start timeout '%s', ignoring: %m", value);

                if (arg_default_timeout_start_usec <= 0)
                        arg_default_timeout_start_usec = USEC_INFINITY;

        } else if (proc_cmdline_key_streq(key, "systemd.cpu_affinity")) {

                if (proc_cmdline_value_missing(key, value))
                        return 0;

                r = parse_cpu_set(value, &arg_cpu_affinity);
                if (r < 0)
                        log_warning_errno(r, "Failed to parse CPU affinity mask '%s', ignoring: %m", value);

        } else if (proc_cmdline_key_streq(key, "systemd.watchdog_device")) {

                if (proc_cmdline_value_missing(key, value))
                        return 0;

                (void) parse_path_argument(value, false, &arg_watchdog_device);

        } else if (proc_cmdline_key_streq(key, "systemd.watchdog_sec")) {

                if (proc_cmdline_value_missing(key, value))
                        return 0;

                if (streq(value, "default"))
                        arg_runtime_watchdog = USEC_INFINITY;
                else if (streq(value, "off"))
                        arg_runtime_watchdog = 0;
                else {
                        r = parse_sec(value, &arg_runtime_watchdog);
                        if (r < 0) {
                                log_warning_errno(r, "Failed to parse systemd.watchdog_sec= argument '%s', ignoring: %m", value);
                                return 0;
                        }
                }

                arg_kexec_watchdog = arg_reboot_watchdog = arg_runtime_watchdog;

        } else if (proc_cmdline_key_streq(key, "systemd.watchdog_pre_sec")) {

                if (proc_cmdline_value_missing(key, value))
                        return 0;

                if (streq(value, "default"))
                        arg_pretimeout_watchdog = USEC_INFINITY;
                else if (streq(value, "off"))
                        arg_pretimeout_watchdog = 0;
                else {
                        r = parse_sec(value, &arg_pretimeout_watchdog);
                        if (r < 0) {
                                log_warning_errno(r, "Failed to parse systemd.watchdog_pre_sec= argument '%s', ignoring: %m", value);
                                return 0;
                        }
                }

        } else if (proc_cmdline_key_streq(key, "systemd.watchdog_pretimeout_governor")) {

                if (proc_cmdline_value_missing(key, value) || isempty(value)) {
                        arg_watchdog_pretimeout_governor = mfree(arg_watchdog_pretimeout_governor);
                        return 0;
                }

                if (!string_is_safe(value)) {
                        log_warning("Watchdog pretimeout governor '%s' is not valid, ignoring.", value);
                        return 0;
                }

                return free_and_strdup_warn(&arg_watchdog_pretimeout_governor, value);

        } else if (proc_cmdline_key_streq(key, "systemd.clock_usec")) {

                if (proc_cmdline_value_missing(key, value))
                        return 0;

                r = safe_atou64(value, &arg_clock_usec);
                if (r < 0)
                        log_warning_errno(r, "Failed to parse systemd.clock_usec= argument, ignoring: %s", value);

        } else if (proc_cmdline_key_streq(key, "systemd.random_seed")) {
                void *p;
                size_t sz;

                if (proc_cmdline_value_missing(key, value))
                        return 0;

                r = unbase64mem(value, SIZE_MAX, &p, &sz);
                if (r < 0)
                        log_warning_errno(r, "Failed to parse systemd.random_seed= argument, ignoring: %s", value);

                free(arg_random_seed);
                arg_random_seed = sz > 0 ? p : mfree(p);
                arg_random_seed_size = sz;

        } else if (proc_cmdline_key_streq(key, "systemd.reload_limit_interval_sec")) {

                if (proc_cmdline_value_missing(key, value))
                        return 0;

                r = parse_sec(value, &arg_reload_limit_interval_sec);
                if (r < 0) {
                        log_warning_errno(r, "Failed to parse systemd.reload_limit_interval_sec= argument '%s', ignoring: %m", value);
                        return 0;
                }

        } else if (proc_cmdline_key_streq(key, "systemd.reload_limit_burst")) {

                if (proc_cmdline_value_missing(key, value))
                        return 0;

                r = safe_atou(value, &arg_reload_limit_burst);
                if (r < 0) {
                        log_warning_errno(r, "Failed to parse systemd.reload_limit_burst= argument '%s', ignoring: %m", value);
                        return 0;
                }

        } else if (streq(key, "quiet") && !value) {

                if (arg_show_status == _SHOW_STATUS_INVALID)
                        arg_show_status = SHOW_STATUS_ERROR;

        } else if (streq(key, "debug") && !value) {

                /* Note that log_parse_environment() handles 'debug'
                 * too, and sets the log level to LOG_DEBUG. */

                if (detect_container() > 0)
                        log_set_target(LOG_TARGET_CONSOLE);

        } else if (!value) {
                const char *target;

                /* Compatible with SysV, but supported independently even if SysV compatibility is disabled. */
                target = runlevel_to_target(key);
                if (target)
                        return free_and_strdup_warn(&arg_default_unit, target);
        }

        return 0;
}

#define DEFINE_SETTER(name, func, descr)                              \
        static int name(const char *unit,                             \
                        const char *filename,                         \
                        unsigned line,                                \
                        const char *section,                          \
                        unsigned section_line,                        \
                        const char *lvalue,                           \
                        int ltype,                                    \
                        const char *rvalue,                           \
                        void *data,                                   \
                        void *userdata) {                             \
                                                                      \
                int r;                                                \
                                                                      \
                assert(filename);                                     \
                assert(lvalue);                                       \
                assert(rvalue);                                       \
                                                                      \
                r = func(rvalue);                                     \
                if (r < 0)                                            \
                        log_syntax(unit, LOG_ERR, filename, line, r,  \
                                   "Invalid " descr "'%s': %m",       \
                                   rvalue);                           \
                                                                      \
                return 0;                                             \
        }

DEFINE_SETTER(config_parse_level2, log_set_max_level_from_string, "log level");
DEFINE_SETTER(config_parse_target, log_set_target_from_string, "target");
DEFINE_SETTER(config_parse_color, log_show_color_from_string, "color");
DEFINE_SETTER(config_parse_location, log_show_location_from_string, "location");
DEFINE_SETTER(config_parse_time, log_show_time_from_string, "time");

static int config_parse_default_timeout_abort(
                const char *unit,
                const char *filename,
                unsigned line,
                const char *section,
                unsigned section_line,
                const char *lvalue,
                int ltype,
                const char *rvalue,
                void *data,
                void *userdata) {
        int r;

        r = config_parse_timeout_abort(unit, filename, line, section, section_line, lvalue, ltype, rvalue,
                                       &arg_default_timeout_abort_usec, userdata);
        if (r >= 0)
                arg_default_timeout_abort_set = r;
        return 0;
}

static int config_parse_oom_score_adjust(
                const char *unit,
                const char *filename,
                unsigned line,
                const char *section,
                unsigned section_line,
                const char *lvalue,
                int ltype,
                const char *rvalue,
                void *data,
                void *userdata) {

        int oa, r;

        if (isempty(rvalue)) {
                arg_default_oom_score_adjust_set = false;
                return 0;
        }

        r = parse_oom_score_adjust(rvalue, &oa);
        if (r < 0) {
                log_syntax(unit, LOG_WARNING, filename, line, r, "Failed to parse the OOM score adjust value '%s', ignoring: %m", rvalue);
                return 0;
        }

        arg_default_oom_score_adjust = oa;
        arg_default_oom_score_adjust_set = true;

        return 0;
}

static int parse_config_file(void) {
        const ConfigTableItem items[] = {
                { "Manager", "LogLevel",                     config_parse_level2,                0,                        NULL                              },
                { "Manager", "LogTarget",                    config_parse_target,                0,                        NULL                              },
                { "Manager", "LogColor",                     config_parse_color,                 0,                        NULL                              },
                { "Manager", "LogLocation",                  config_parse_location,              0,                        NULL                              },
                { "Manager", "LogTime",                      config_parse_time,                  0,                        NULL                              },
                { "Manager", "DumpCore",                     config_parse_bool,                  0,                        &arg_dump_core                    },
                { "Manager", "CrashChVT", /* legacy */       config_parse_crash_chvt,            0,                        &arg_crash_chvt                   },
                { "Manager", "CrashChangeVT",                config_parse_crash_chvt,            0,                        &arg_crash_chvt                   },
                { "Manager", "CrashShell",                   config_parse_bool,                  0,                        &arg_crash_shell                  },
                { "Manager", "CrashReboot",                  config_parse_bool,                  0,                        &arg_crash_reboot                 },
                { "Manager", "ShowStatus",                   config_parse_show_status,           0,                        &arg_show_status                  },
                { "Manager", "StatusUnitFormat",             config_parse_status_unit_format,    0,                        &arg_status_unit_format           },
                { "Manager", "CPUAffinity",                  config_parse_cpu_affinity2,         0,                        &arg_cpu_affinity                 },
                { "Manager", "NUMAPolicy",                   config_parse_numa_policy,           0,                        &arg_numa_policy.type             },
                { "Manager", "NUMAMask",                     config_parse_numa_mask,             0,                        &arg_numa_policy                  },
                { "Manager", "JoinControllers",              config_parse_warn_compat,           DISABLED_CONFIGURATION,   NULL                              },
                { "Manager", "RuntimeWatchdogSec",           config_parse_watchdog_sec,          0,                        &arg_runtime_watchdog             },
                { "Manager", "RuntimeWatchdogPreSec",        config_parse_watchdog_sec,          0,                        &arg_pretimeout_watchdog          },
                { "Manager", "RebootWatchdogSec",            config_parse_watchdog_sec,          0,                        &arg_reboot_watchdog              },
                { "Manager", "ShutdownWatchdogSec",          config_parse_watchdog_sec,          0,                        &arg_reboot_watchdog              }, /* obsolete alias */
                { "Manager", "KExecWatchdogSec",             config_parse_watchdog_sec,          0,                        &arg_kexec_watchdog               },
                { "Manager", "WatchdogDevice",               config_parse_path,                  0,                        &arg_watchdog_device              },
                { "Manager", "RuntimeWatchdogPreGovernor",   config_parse_string,                CONFIG_PARSE_STRING_SAFE, &arg_watchdog_pretimeout_governor },
                { "Manager", "CapabilityBoundingSet",        config_parse_capability_set,        0,                        &arg_capability_bounding_set      },
                { "Manager", "NoNewPrivileges",              config_parse_bool,                  0,                        &arg_no_new_privs                 },
#if HAVE_SECCOMP
                { "Manager", "SystemCallArchitectures",      config_parse_syscall_archs,         0,                        &arg_syscall_archs                },
#else
                { "Manager", "SystemCallArchitectures",      config_parse_warn_compat,           DISABLED_CONFIGURATION,   NULL                              },

#endif
                { "Manager", "TimerSlackNSec",               config_parse_nsec,                  0,                        &arg_timer_slack_nsec             },
                { "Manager", "DefaultTimerAccuracySec",      config_parse_sec,                   0,                        &arg_default_timer_accuracy_usec  },
                { "Manager", "DefaultStandardOutput",        config_parse_output_restricted,     0,                        &arg_default_std_output           },
                { "Manager", "DefaultStandardError",         config_parse_output_restricted,     0,                        &arg_default_std_error            },
                { "Manager", "DefaultTimeoutStartSec",       config_parse_sec,                   0,                        &arg_default_timeout_start_usec   },
                { "Manager", "DefaultTimeoutStopSec",        config_parse_sec,                   0,                        &arg_default_timeout_stop_usec    },
                { "Manager", "DefaultTimeoutAbortSec",       config_parse_default_timeout_abort, 0,                        NULL                              },
                { "Manager", "DefaultDeviceTimeoutSec",      config_parse_sec,                   0,                        &arg_default_device_timeout_usec  },
                { "Manager", "DefaultRestartSec",            config_parse_sec,                   0,                        &arg_default_restart_usec         },
                { "Manager", "DefaultStartLimitInterval",    config_parse_sec,                   0,                        &arg_default_start_limit_interval }, /* obsolete alias */
                { "Manager", "DefaultStartLimitIntervalSec", config_parse_sec,                   0,                        &arg_default_start_limit_interval },
                { "Manager", "DefaultStartLimitBurst",       config_parse_unsigned,              0,                        &arg_default_start_limit_burst    },
                { "Manager", "DefaultEnvironment",           config_parse_environ,               arg_runtime_scope,        &arg_default_environment          },
                { "Manager", "ManagerEnvironment",           config_parse_environ,               arg_runtime_scope,        &arg_manager_environment          },
                { "Manager", "DefaultLimitCPU",              config_parse_rlimit,                RLIMIT_CPU,               arg_default_rlimit                },
                { "Manager", "DefaultLimitFSIZE",            config_parse_rlimit,                RLIMIT_FSIZE,             arg_default_rlimit                },
                { "Manager", "DefaultLimitDATA",             config_parse_rlimit,                RLIMIT_DATA,              arg_default_rlimit                },
                { "Manager", "DefaultLimitSTACK",            config_parse_rlimit,                RLIMIT_STACK,             arg_default_rlimit                },
                { "Manager", "DefaultLimitCORE",             config_parse_rlimit,                RLIMIT_CORE,              arg_default_rlimit                },
                { "Manager", "DefaultLimitRSS",              config_parse_rlimit,                RLIMIT_RSS,               arg_default_rlimit                },
                { "Manager", "DefaultLimitNOFILE",           config_parse_rlimit,                RLIMIT_NOFILE,            arg_default_rlimit                },
                { "Manager", "DefaultLimitAS",               config_parse_rlimit,                RLIMIT_AS,                arg_default_rlimit                },
                { "Manager", "DefaultLimitNPROC",            config_parse_rlimit,                RLIMIT_NPROC,             arg_default_rlimit                },
                { "Manager", "DefaultLimitMEMLOCK",          config_parse_rlimit,                RLIMIT_MEMLOCK,           arg_default_rlimit                },
                { "Manager", "DefaultLimitLOCKS",            config_parse_rlimit,                RLIMIT_LOCKS,             arg_default_rlimit                },
                { "Manager", "DefaultLimitSIGPENDING",       config_parse_rlimit,                RLIMIT_SIGPENDING,        arg_default_rlimit                },
                { "Manager", "DefaultLimitMSGQUEUE",         config_parse_rlimit,                RLIMIT_MSGQUEUE,          arg_default_rlimit                },
                { "Manager", "DefaultLimitNICE",             config_parse_rlimit,                RLIMIT_NICE,              arg_default_rlimit                },
                { "Manager", "DefaultLimitRTPRIO",           config_parse_rlimit,                RLIMIT_RTPRIO,            arg_default_rlimit                },
                { "Manager", "DefaultLimitRTTIME",           config_parse_rlimit,                RLIMIT_RTTIME,            arg_default_rlimit                },
                { "Manager", "DefaultCPUAccounting",         config_parse_tristate,              0,                        &arg_default_cpu_accounting       },
                { "Manager", "DefaultIOAccounting",          config_parse_bool,                  0,                        &arg_default_io_accounting        },
                { "Manager", "DefaultIPAccounting",          config_parse_bool,                  0,                        &arg_default_ip_accounting        },
                { "Manager", "DefaultBlockIOAccounting",     config_parse_bool,                  0,                        &arg_default_blockio_accounting   },
                { "Manager", "DefaultMemoryAccounting",      config_parse_bool,                  0,                        &arg_default_memory_accounting    },
                { "Manager", "DefaultTasksAccounting",       config_parse_bool,                  0,                        &arg_default_tasks_accounting     },
                { "Manager", "DefaultTasksMax",              config_parse_tasks_max,             0,                        &arg_default_tasks_max            },
                { "Manager", "DefaultMemoryPressureThresholdSec", config_parse_sec,              0,                        &arg_default_memory_pressure_threshold_usec },
                { "Manager", "DefaultMemoryPressureWatch",   config_parse_memory_pressure_watch, 0,                        &arg_default_memory_pressure_watch },
                { "Manager", "CtrlAltDelBurstAction",        config_parse_emergency_action,      arg_runtime_scope,        &arg_cad_burst_action             },
                { "Manager", "DefaultOOMPolicy",             config_parse_oom_policy,            0,                        &arg_default_oom_policy           },
                { "Manager", "DefaultOOMScoreAdjust",        config_parse_oom_score_adjust,      0,                        NULL                              },
                { "Manager", "ReloadLimitIntervalSec",       config_parse_sec,                   0,                        &arg_reload_limit_interval_sec    },
                { "Manager", "ReloadLimitBurst",             config_parse_unsigned,              0,                        &arg_reload_limit_burst           },
#if ENABLE_SMACK
                { "Manager", "DefaultSmackProcessLabel",     config_parse_string,                0,                        &arg_default_smack_process_label  },
#else
                { "Manager", "DefaultSmackProcessLabel",     config_parse_warn_compat,           DISABLED_CONFIGURATION,   NULL                              },
#endif
                {}
        };

        if (arg_runtime_scope == RUNTIME_SCOPE_SYSTEM)
                (void) config_parse_config_file("system.conf",
                                                "Manager\0",
                                                config_item_table_lookup, items,
                                                CONFIG_PARSE_WARN,
                                                NULL);
        else {
                _cleanup_strv_free_ char **files = NULL, **dirs = NULL;
                int r;

                assert(arg_runtime_scope == RUNTIME_SCOPE_USER);

                r = manager_find_user_config_paths(&files, &dirs);
                if (r < 0)
                        return log_error_errno(r, "Failed to determine config file paths: %m");

                (void) config_parse_many(
                                (const char* const*) files,
                                (const char* const*) dirs,
                                "user.conf.d",
                                "Manager\0",
                                config_item_table_lookup, items,
                                CONFIG_PARSE_WARN,
                                NULL, NULL, NULL);
        }

        /* Traditionally "0" was used to turn off the default unit timeouts. Fix this up so that we use
         * USEC_INFINITY like everywhere else. */
        if (arg_default_timeout_start_usec <= 0)
                arg_default_timeout_start_usec = USEC_INFINITY;
        if (arg_default_timeout_stop_usec <= 0)
                arg_default_timeout_stop_usec = USEC_INFINITY;

        return 0;
}

static void set_manager_defaults(Manager *m) {

        assert(m);

        /* Propagates the various default unit property settings into the manager object, i.e. properties that do not
         * affect the manager itself, but are just what newly allocated units will have set if they haven't set
         * anything else. (Also see set_manager_settings() for the settings that affect the manager's own behaviour) */

        m->default_timer_accuracy_usec = arg_default_timer_accuracy_usec;
        m->default_std_output = arg_default_std_output;
        m->default_std_error = arg_default_std_error;
        m->default_timeout_start_usec = arg_default_timeout_start_usec;
        m->default_timeout_stop_usec = arg_default_timeout_stop_usec;
        m->default_timeout_abort_usec = arg_default_timeout_abort_usec;
        m->default_timeout_abort_set = arg_default_timeout_abort_set;
        m->default_device_timeout_usec = arg_default_device_timeout_usec;
        m->default_restart_usec = arg_default_restart_usec;
        m->default_start_limit_interval = arg_default_start_limit_interval;
        m->default_start_limit_burst = arg_default_start_limit_burst;

        /* On 4.15+ with unified hierarchy, CPU accounting is essentially free as it doesn't require the CPU
         * controller to be enabled, so the default is to enable it unless we got told otherwise. */
        if (arg_default_cpu_accounting >= 0)
                m->default_cpu_accounting = arg_default_cpu_accounting;
        else
                m->default_cpu_accounting = cpu_accounting_is_cheap();

        m->default_io_accounting = arg_default_io_accounting;
        m->default_ip_accounting = arg_default_ip_accounting;
        m->default_blockio_accounting = arg_default_blockio_accounting;
        m->default_memory_accounting = arg_default_memory_accounting;
        m->default_tasks_accounting = arg_default_tasks_accounting;
        m->default_tasks_max = arg_default_tasks_max;
        m->default_memory_pressure_watch = arg_default_memory_pressure_watch;
        m->default_memory_pressure_threshold_usec = arg_default_memory_pressure_threshold_usec;
        m->default_oom_policy = arg_default_oom_policy;
        m->default_oom_score_adjust_set = arg_default_oom_score_adjust_set;
        m->default_oom_score_adjust = arg_default_oom_score_adjust;

        (void) manager_set_default_smack_process_label(m, arg_default_smack_process_label);

        (void) manager_set_default_rlimits(m, arg_default_rlimit);

        (void) manager_default_environment(m);
        (void) manager_transient_environment_add(m, arg_default_environment);
}

static void set_manager_settings(Manager *m) {
        int r;

        assert(m);

        /* Propagates the various manager settings into the manager object, i.e. properties that
         * effect the manager itself (as opposed to just being inherited into newly allocated
         * units, see set_manager_defaults() above). */

        m->confirm_spawn = arg_confirm_spawn;
        m->service_watchdogs = arg_service_watchdogs;
        m->cad_burst_action = arg_cad_burst_action;
        /* Note that we don't do structured initialization here, otherwise it will reset the rate limit
         * counter on every daemon-reload. */
        m->reload_ratelimit.interval = arg_reload_limit_interval_sec;
        m->reload_ratelimit.burst = arg_reload_limit_burst;

        manager_set_watchdog(m, WATCHDOG_RUNTIME, arg_runtime_watchdog);
        manager_set_watchdog(m, WATCHDOG_REBOOT, arg_reboot_watchdog);
        manager_set_watchdog(m, WATCHDOG_KEXEC, arg_kexec_watchdog);
        manager_set_watchdog(m, WATCHDOG_PRETIMEOUT, arg_pretimeout_watchdog);
        r = manager_set_watchdog_pretimeout_governor(m, arg_watchdog_pretimeout_governor);
        if (r < 0)
                log_warning_errno(r, "Failed to set watchdog pretimeout governor to '%s', ignoring: %m", arg_watchdog_pretimeout_governor);

        manager_set_show_status(m, arg_show_status, "commandline");
        m->status_unit_format = arg_status_unit_format;
}

static int parse_argv(int argc, char *argv[]) {
        enum {
                COMMON_GETOPT_ARGS,
                SYSTEMD_GETOPT_ARGS,
        };

        static const struct option options[] = {
                COMMON_GETOPT_OPTIONS,
                SYSTEMD_GETOPT_OPTIONS,
                {}
        };

        int c, r;
        bool user_arg_seen = false;

        assert(argc >= 1);
        assert(argv);

        if (getpid_cached() == 1)
                opterr = 0;

        while ((c = getopt_long(argc, argv, SYSTEMD_GETOPT_SHORT_OPTIONS, options, NULL)) >= 0)

                switch (c) {

                case ARG_LOG_LEVEL:
                        r = log_set_max_level_from_string(optarg);
                        if (r < 0)
                                return log_error_errno(r, "Failed to parse log level \"%s\": %m", optarg);

                        break;

                case ARG_LOG_TARGET:
                        r = log_set_target_from_string(optarg);
                        if (r < 0)
                                return log_error_errno(r, "Failed to parse log target \"%s\": %m", optarg);

                        break;

                case ARG_LOG_COLOR:

                        if (optarg) {
                                r = log_show_color_from_string(optarg);
                                if (r < 0)
                                        return log_error_errno(r, "Failed to parse log color setting \"%s\": %m",
                                                               optarg);
                        } else
                                log_show_color(true);

                        break;

                case ARG_LOG_LOCATION:
                        if (optarg) {
                                r = log_show_location_from_string(optarg);
                                if (r < 0)
                                        return log_error_errno(r, "Failed to parse log location setting \"%s\": %m",
                                                               optarg);
                        } else
                                log_show_location(true);

                        break;

                case ARG_LOG_TIME:

                        if (optarg) {
                                r = log_show_time_from_string(optarg);
                                if (r < 0)
                                        return log_error_errno(r, "Failed to parse log time setting \"%s\": %m",
                                                               optarg);
                        } else
                                log_show_time(true);

                        break;

                case ARG_DEFAULT_STD_OUTPUT:
                        r = exec_output_from_string(optarg);
                        if (r < 0)
                                return log_error_errno(r, "Failed to parse default standard output setting \"%s\": %m",
                                                       optarg);
                        arg_default_std_output = r;
                        break;

                case ARG_DEFAULT_STD_ERROR:
                        r = exec_output_from_string(optarg);
                        if (r < 0)
                                return log_error_errno(r, "Failed to parse default standard error output setting \"%s\": %m",
                                                       optarg);
                        arg_default_std_error = r;
                        break;

                case ARG_UNIT:
                        r = free_and_strdup(&arg_default_unit, optarg);
                        if (r < 0)
                                return log_error_errno(r, "Failed to set default unit \"%s\": %m", optarg);

                        break;

                case ARG_SYSTEM:
                        arg_runtime_scope = RUNTIME_SCOPE_SYSTEM;
                        break;

                case ARG_USER:
                        arg_runtime_scope = RUNTIME_SCOPE_USER;
                        user_arg_seen = true;
                        break;

                case ARG_TEST:
                        arg_action = ACTION_TEST;
                        break;

                case ARG_NO_PAGER:
                        arg_pager_flags |= PAGER_DISABLE;
                        break;

                case ARG_VERSION:
                        arg_action = ACTION_VERSION;
                        break;

                case ARG_DUMP_CONFIGURATION_ITEMS:
                        arg_action = ACTION_DUMP_CONFIGURATION_ITEMS;
                        break;

                case ARG_DUMP_BUS_PROPERTIES:
                        arg_action = ACTION_DUMP_BUS_PROPERTIES;
                        break;

                case ARG_BUS_INTROSPECT:
                        arg_bus_introspect = optarg;
                        arg_action = ACTION_BUS_INTROSPECT;
                        break;

                case ARG_DUMP_CORE:
                        r = parse_boolean_argument("--dump-core", optarg, &arg_dump_core);
                        if (r < 0)
                                return r;
                        break;

                case ARG_CRASH_CHVT:
                        r = parse_crash_chvt(optarg, &arg_crash_chvt);
                        if (r < 0)
                                return log_error_errno(r, "Failed to parse crash virtual terminal index: \"%s\": %m",
                                                       optarg);
                        break;

                case ARG_CRASH_SHELL:
                        r = parse_boolean_argument("--crash-shell", optarg, &arg_crash_shell);
                        if (r < 0)
                                return r;
                        break;

                case ARG_CRASH_REBOOT:
                        r = parse_boolean_argument("--crash-reboot", optarg, &arg_crash_reboot);
                        if (r < 0)
                                return r;
                        break;

                case ARG_CONFIRM_SPAWN:
                        arg_confirm_spawn = mfree(arg_confirm_spawn);

                        r = parse_confirm_spawn(optarg, &arg_confirm_spawn);
                        if (r < 0)
                                return log_error_errno(r, "Failed to parse confirm spawn option: \"%s\": %m",
                                                       optarg);
                        break;

                case ARG_SERVICE_WATCHDOGS:
                        r = parse_boolean_argument("--service-watchdogs=", optarg, &arg_service_watchdogs);
                        if (r < 0)
                                return r;
                        break;

                case ARG_SHOW_STATUS:
                        if (optarg) {
                                r = parse_show_status(optarg, &arg_show_status);
                                if (r < 0)
                                        return log_error_errno(r, "Failed to parse show status boolean: \"%s\": %m",
                                                               optarg);
                        } else
                                arg_show_status = SHOW_STATUS_YES;
                        break;

                case ARG_DESERIALIZE: {
                        int fd;
                        FILE *f;

                        fd = parse_fd(optarg);
                        if (fd == -ERANGE)
                                return log_error_errno(fd, "Invalid serialization fd: %s", optarg);
                        if (fd < 0)
                                return log_error_errno(fd, "Failed to parse deserialize option \"%s\": %m", optarg);

                        (void) fd_cloexec(fd, true);

                        f = fdopen(fd, "r");
                        if (!f)
                                return log_error_errno(errno, "Failed to open serialization fd %d: %m", fd);

                        safe_fclose(arg_serialization);
                        arg_serialization = f;

                        break;
                }

                case ARG_SWITCHED_ROOT:
                        arg_switched_root = true;
                        break;

                case ARG_MACHINE_ID:
                        r = set_machine_id(optarg);
                        if (r < 0)
                                return log_error_errno(r, "MachineID '%s' is not valid: %m", optarg);
                        break;

                case 'h':
                        arg_action = ACTION_HELP;
                        break;

                case 'D':
                        log_set_max_level(LOG_DEBUG);
                        break;

                case 'b':
                case 's':
                case 'z':
                        /* Just to eat away the sysvinit kernel cmdline args that we'll parse in
                         * parse_proc_cmdline_item() or ignore, without any getopt() error messages.
                         */
                case '?':
                        if (getpid_cached() != 1)
                                return -EINVAL;
                        else
                                return 0;

                default:
                        assert_not_reached();
                }

        if (optind < argc && getpid_cached() != 1)
                /* Hmm, when we aren't run as init system let's complain about excess arguments */
                return log_error_errno(SYNTHETIC_ERRNO(EINVAL), "Excess arguments.");

        if (arg_action == ACTION_RUN && arg_runtime_scope == RUNTIME_SCOPE_USER && !user_arg_seen)
                return log_error_errno(SYNTHETIC_ERRNO(EINVAL),
                                       "Explicit --user argument required to run as user manager.");

        return 0;
}

static int help(void) {
        _cleanup_free_ char *link = NULL;
        int r;

        r = terminal_urlify_man("systemd", "1", &link);
        if (r < 0)
                return log_oom();

        printf("%s [OPTIONS...]\n\n"
               "%sStarts and monitors system and user services.%s\n\n"
               "This program takes no positional arguments.\n\n"
               "%sOptions%s:\n"
               "  -h --help                      Show this help\n"
               "     --version                   Show version\n"
               "     --test                      Determine initial transaction, dump it and exit\n"
               "     --system                    Combined with --test: operate in system mode\n"
               "     --user                      Combined with --test: operate in user mode\n"
               "     --dump-configuration-items  Dump understood unit configuration items\n"
               "     --dump-bus-properties       Dump exposed bus properties\n"
               "     --bus-introspect=PATH       Write XML introspection data\n"
               "     --unit=UNIT                 Set default unit\n"
               "     --dump-core[=BOOL]          Dump core on crash\n"
               "     --crash-vt=NR               Change to specified VT on crash\n"
               "     --crash-reboot[=BOOL]       Reboot on crash\n"
               "     --crash-shell[=BOOL]        Run shell on crash\n"
               "     --confirm-spawn[=BOOL]      Ask for confirmation when spawning processes\n"
               "     --show-status[=BOOL]        Show status updates on the console during boot\n"
               "     --log-target=TARGET         Set log target (console, journal, kmsg,\n"
               "                                                 journal-or-kmsg, null)\n"
               "     --log-level=LEVEL           Set log level (debug, info, notice, warning,\n"
               "                                                err, crit, alert, emerg)\n"
               "     --log-color[=BOOL]          Highlight important log messages\n"
               "     --log-location[=BOOL]       Include code location in log messages\n"
               "     --log-time[=BOOL]           Prefix log messages with current time\n"
               "     --default-standard-output=  Set default standard output for services\n"
               "     --default-standard-error=   Set default standard error output for services\n"
               "     --no-pager                  Do not pipe output into a pager\n"
               "\nSee the %s for details.\n",
               program_invocation_short_name,
               ansi_highlight(),
               ansi_normal(),
               ansi_underline(),
               ansi_normal(),
               link);

        return 0;
}

static int prepare_reexecute(
                Manager *m,
                FILE **ret_f,
                FDSet **ret_fds,
                bool switching_root) {

        _cleanup_fdset_free_ FDSet *fds = NULL;
        _cleanup_fclose_ FILE *f = NULL;
        int r;

        assert(m);
        assert(ret_f);
        assert(ret_fds);

        r = manager_open_serialization(m, &f);
        if (r < 0)
                return log_error_errno(r, "Failed to create serialization file: %m");

        /* Make sure nothing is really destructed when we shut down */
        m->n_reloading++;
        bus_manager_send_reloading(m, true);

        fds = fdset_new();
        if (!fds)
                return log_oom();

        r = manager_serialize(m, f, fds, switching_root);
        if (r < 0)
                return r;

        if (fseeko(f, 0, SEEK_SET) == (off_t) -1)
                return log_error_errno(errno, "Failed to rewind serialization fd: %m");

        r = fd_cloexec(fileno(f), false);
        if (r < 0)
                return log_error_errno(r, "Failed to disable O_CLOEXEC for serialization: %m");

        r = fdset_cloexec(fds, false);
        if (r < 0)
                return log_error_errno(r, "Failed to disable O_CLOEXEC for serialization fds: %m");

        *ret_f = TAKE_PTR(f);
        *ret_fds = TAKE_PTR(fds);

        return 0;
}

static void bump_file_max_and_nr_open(void) {

        /* Let's bump fs.file-max and fs.nr_open to their respective maximums. On current kernels large
         * numbers of file descriptors are no longer a performance problem and their memory is properly
         * tracked by memcg, thus counting them and limiting them in another two layers of limits is
         * unnecessary and just complicates things. This function hence turns off 2 of the 4 levels of limits
         * on file descriptors, and makes RLIMIT_NOLIMIT (soft + hard) the only ones that really matter. */

#if BUMP_PROC_SYS_FS_FILE_MAX || BUMP_PROC_SYS_FS_NR_OPEN
        int r;
#endif

#if BUMP_PROC_SYS_FS_FILE_MAX
        /* The maximum the kernel allows for this since 5.2 is LONG_MAX, use that. (Previously things were
         * different, but the operation would fail silently.) */
        r = sysctl_write("fs/file-max", LONG_MAX_STR);
        if (r < 0)
                log_full_errno(IN_SET(r, -EROFS, -EPERM, -EACCES) ? LOG_DEBUG : LOG_WARNING,
                               r, "Failed to bump fs.file-max, ignoring: %m");
#endif

#if BUMP_PROC_SYS_FS_NR_OPEN
        int v = INT_MAX;

        /* Argh! The kernel enforces maximum and minimum values on the fs.nr_open, but we don't really know
         * what they are. The expression by which the maximum is determined is dependent on the architecture,
         * and is something we don't really want to copy to userspace, as it is dependent on implementation
         * details of the kernel. Since the kernel doesn't expose the maximum value to us, we can only try
         * and hope. Hence, let's start with INT_MAX, and then keep halving the value until we find one that
         * works. Ugly? Yes, absolutely, but kernel APIs are kernel APIs, so what do can we do... 🤯 */

        for (;;) {
                int k;

                v &= ~(__SIZEOF_POINTER__ - 1); /* Round down to next multiple of the pointer size */
                if (v < 1024) {
                        log_warning("Can't bump fs.nr_open, value too small.");
                        break;
                }

                k = read_nr_open();
                if (k < 0) {
                        log_error_errno(k, "Failed to read fs.nr_open: %m");
                        break;
                }
                if (k >= v) { /* Already larger */
                        log_debug("Skipping bump, value is already larger.");
                        break;
                }

                r = sysctl_writef("fs/nr_open", "%i", v);
                if (r == -EINVAL) {
                        log_debug("Couldn't write fs.nr_open as %i, halving it.", v);
                        v /= 2;
                        continue;
                }
                if (r < 0) {
                        log_full_errno(IN_SET(r, -EROFS, -EPERM, -EACCES) ? LOG_DEBUG : LOG_WARNING, r, "Failed to bump fs.nr_open, ignoring: %m");
                        break;
                }

                log_debug("Successfully bumped fs.nr_open to %i", v);
                break;
        }
#endif
}

static int bump_rlimit_nofile(const struct rlimit *saved_rlimit) {
        struct rlimit new_rlimit;
        int r, nr;

        /* Get the underlying absolute limit the kernel enforces */
        nr = read_nr_open();

        /* Calculate the new limits to use for us. Never lower from what we inherited. */
        new_rlimit = (struct rlimit) {
                .rlim_cur = MAX((rlim_t) nr, saved_rlimit->rlim_cur),
                .rlim_max = MAX((rlim_t) nr, saved_rlimit->rlim_max),
        };

        /* Shortcut if nothing changes. */
        if (saved_rlimit->rlim_max >= new_rlimit.rlim_max &&
            saved_rlimit->rlim_cur >= new_rlimit.rlim_cur) {
                log_debug("RLIMIT_NOFILE is already as high or higher than we need it, not bumping.");
                return 0;
        }

        /* Bump up the resource limit for ourselves substantially, all the way to the maximum the kernel allows, for
         * both hard and soft. */
        r = setrlimit_closest(RLIMIT_NOFILE, &new_rlimit);
        if (r < 0)
                return log_warning_errno(r, "Setting RLIMIT_NOFILE failed, ignoring: %m");

        return 0;
}

static int bump_rlimit_memlock(const struct rlimit *saved_rlimit) {
        struct rlimit new_rlimit;
        uint64_t mm;
        int r;

        /* BPF_MAP_TYPE_LPM_TRIE bpf maps are charged against RLIMIT_MEMLOCK, even if we have CAP_IPC_LOCK
         * which should normally disable such checks. We need them to implement IPAddressAllow= and
         * IPAddressDeny=, hence let's bump the value high enough for our user. */

        /* Using MAX() on resource limits only is safe if RLIM_INFINITY is > 0. POSIX declares that rlim_t
         * must be unsigned, hence this is a given, but let's make this clear here. */
        assert_cc(RLIM_INFINITY > 0);

        mm = physical_memory_scale(1, 8); /* Let's scale how much we allow to be locked by the amount of
                                           * physical RAM. We allow an eighth to be locked by us, just to
                                           * pick a value. */

        new_rlimit = (struct rlimit) {
                .rlim_cur = MAX3(HIGH_RLIMIT_MEMLOCK, saved_rlimit->rlim_cur, mm),
                .rlim_max = MAX3(HIGH_RLIMIT_MEMLOCK, saved_rlimit->rlim_max, mm),
        };

        if (saved_rlimit->rlim_max >= new_rlimit.rlim_cur &&
            saved_rlimit->rlim_cur >= new_rlimit.rlim_max) {
                log_debug("RLIMIT_MEMLOCK is already as high or higher than we need it, not bumping.");
                return 0;
        }

        r = setrlimit_closest(RLIMIT_MEMLOCK, &new_rlimit);
        if (r < 0)
                return log_warning_errno(r, "Setting RLIMIT_MEMLOCK failed, ignoring: %m");

        return 0;
}

static void test_usr(void) {

        /* Check that /usr is either on the same file system as / or mounted already. */

        if (dir_is_empty("/usr", /* ignore_hidden_or_backup= */ false) <= 0)
                return;

        log_warning("/usr appears to be on its own filesystem and is not already mounted. This is not a supported setup. "
                    "Some things will probably break (sometimes even silently) in mysterious ways. "
                    "Consult https://www.freedesktop.org/wiki/Software/systemd/separate-usr-is-broken for more information.");
}

static int enforce_syscall_archs(Set *archs) {
#if HAVE_SECCOMP
        int r;

        if (!is_seccomp_available())
                return 0;

        r = seccomp_restrict_archs(arg_syscall_archs);
        if (r < 0)
                return log_error_errno(r, "Failed to enforce system call architecture restrication: %m");
#endif
        return 0;
}

static int os_release_status(void) {
        _cleanup_free_ char *pretty_name = NULL, *name = NULL, *version = NULL,
                            *ansi_color = NULL, *support_end = NULL;
        int r;

        r = parse_os_release(NULL,
                             "PRETTY_NAME", &pretty_name,
                             "NAME",        &name,
                             "VERSION",     &version,
                             "ANSI_COLOR",  &ansi_color,
                             "SUPPORT_END", &support_end);
        if (r < 0)
                return log_full_errno(r == -ENOENT ? LOG_DEBUG : LOG_WARNING, r,
                                      "Failed to read os-release file, ignoring: %m");

        const char *label = os_release_pretty_name(pretty_name, name);

        if (show_status_on(arg_show_status)) {
                if (log_get_show_color())
                        status_printf(NULL, 0,
                                      "\nWelcome to \x1B[%sm%s\x1B[0m!\n",
                                      empty_to_null(ansi_color) ?: "1",
                                      label);
                else
                        status_printf(NULL, 0,
                                      "\nWelcome to %s!\n",
                                      label);
        }

        if (support_end && os_release_support_ended(support_end, /* quiet */ false, NULL) > 0)
                /* pretty_name may include the version already, so we'll print the version only if we
                 * have it and we're not using pretty_name. */
                status_printf(ANSI_HIGHLIGHT_RED "  !!  " ANSI_NORMAL, 0,
                              "This OS version (%s%s%s) is past its end-of-support date (%s)",
                              label,
                              (pretty_name || !version) ? "" : " version ",
                              (pretty_name || !version) ? "" : version,
                              support_end);

        return 0;
}

static int write_container_id(void) {
        const char *c;
        int r = 0;  /* avoid false maybe-uninitialized warning */

        c = getenv("container");
        if (isempty(c))
                return 0;

        WITH_UMASK(0022)
                r = write_string_file("/run/systemd/container", c, WRITE_STRING_FILE_CREATE);
        if (r < 0)
                return log_warning_errno(r, "Failed to write /run/systemd/container, ignoring: %m");

        return 1;
}

static int bump_unix_max_dgram_qlen(void) {
        _cleanup_free_ char *qlen = NULL;
        unsigned long v;
        int r;

        /* Let's bump the net.unix.max_dgram_qlen sysctl. The kernel default of 16 is simply too low. We set
         * the value really really early during boot, so that it is actually applied to all our sockets,
         * including the $NOTIFY_SOCKET one. */

        r = read_one_line_file("/proc/sys/net/unix/max_dgram_qlen", &qlen);
        if (r < 0)
                return log_full_errno(r == -ENOENT ? LOG_DEBUG : LOG_WARNING, r,
                                      "Failed to read AF_UNIX datagram queue length, ignoring: %m");

        r = safe_atolu(qlen, &v);
        if (r < 0)
                return log_warning_errno(r, "Failed to parse AF_UNIX datagram queue length '%s', ignoring: %m", qlen);

        if (v >= DEFAULT_UNIX_MAX_DGRAM_QLEN)
                return 0;

        r = sysctl_write("net/unix/max_dgram_qlen", STRINGIFY(DEFAULT_UNIX_MAX_DGRAM_QLEN));
        if (r < 0)
                return log_full_errno(IN_SET(r, -EROFS, -EPERM, -EACCES) ? LOG_DEBUG : LOG_WARNING, r,
                                      "Failed to bump AF_UNIX datagram queue length, ignoring: %m");

        return 1;
}

static int fixup_environment(void) {
        _cleanup_free_ char *term = NULL;
        const char *t;
        int r;

        /* Only fix up the environment when we are started as PID 1 */
        if (getpid_cached() != 1)
                return 0;

        /* We expect the environment to be set correctly if run inside a container. */
        if (detect_container() > 0)
                return 0;

        /* When started as PID1, the kernel uses /dev/console for our stdios and uses TERM=linux whatever the
         * backend device used by the console. We try to make a better guess here since some consoles might
         * not have support for color mode for example.
         *
         * However if TERM was configured through the kernel command line then leave it alone. */
        r = proc_cmdline_get_key("TERM", 0, &term);
        if (r < 0)
                return r;

        t = term ?: default_term_for_tty("/dev/console");

        if (setenv("TERM", t, 1) < 0)
                return -errno;

        /* The kernels sets HOME=/ for init. Let's undo this. */
        if (path_equal_ptr(getenv("HOME"), "/"))
                assert_se(unsetenv("HOME") == 0);

        return 0;
}

static void redirect_telinit(int argc, char *argv[]) {

        /* This is compatibility support for SysV, where calling init as a user is identical to telinit. */

#if HAVE_SYSV_COMPAT
        if (getpid_cached() == 1)
                return;

        if (!invoked_as(argv, "init"))
                return;

        execv(SYSTEMCTL_BINARY_PATH, argv);
        log_error_errno(errno, "Failed to exec " SYSTEMCTL_BINARY_PATH ": %m");
        exit(EXIT_FAILURE);
#endif
}

static int become_shutdown(int objective, int retval) {
        static const char* const table[_MANAGER_OBJECTIVE_MAX] = {
                [MANAGER_EXIT]     = "exit",
                [MANAGER_REBOOT]   = "reboot",
                [MANAGER_POWEROFF] = "poweroff",
                [MANAGER_HALT]     = "halt",
                [MANAGER_KEXEC]    = "kexec",
        };

        char log_level[STRLEN("--log-level=") + DECIMAL_STR_MAX(int)],
             timeout[STRLEN("--timeout=") + DECIMAL_STR_MAX(usec_t) + STRLEN("us")],
             exit_code[STRLEN("--exit-code=") + DECIMAL_STR_MAX(uint8_t)];

        _cleanup_strv_free_ char **env_block = NULL;
        usec_t watchdog_timer = 0;
        int r;

        assert(objective >= 0 && objective < _MANAGER_OBJECTIVE_MAX);
        assert(table[objective]);

        xsprintf(log_level, "--log-level=%d", log_get_max_level());
        xsprintf(timeout, "--timeout=%" PRI_USEC "us", arg_default_timeout_stop_usec);

        const char* command_line[10] = {
                SYSTEMD_SHUTDOWN_BINARY_PATH,
                table[objective],
                log_level,
                timeout,
                /* Note that the last position is a terminator and must contain NULL. */
        };
        size_t pos = 4;

        assert(command_line[pos-1]);
        assert(!command_line[pos]);

        switch (log_get_target()) {

        case LOG_TARGET_KMSG:
        case LOG_TARGET_JOURNAL_OR_KMSG:
        case LOG_TARGET_SYSLOG_OR_KMSG:
                command_line[pos++] = "--log-target=kmsg";
                break;

        case LOG_TARGET_NULL:
                command_line[pos++] = "--log-target=null";
                break;

        case LOG_TARGET_CONSOLE:
        default:
                command_line[pos++] = "--log-target=console";
                break;
        };

        if (log_get_show_color())
                command_line[pos++] = "--log-color";

        if (log_get_show_location())
                command_line[pos++] = "--log-location";

        if (log_get_show_time())
                command_line[pos++] = "--log-time";

        if (objective == MANAGER_EXIT) {
                xsprintf(exit_code, "--exit-code=%d", retval);
                command_line[pos++] = exit_code;
        }

        assert(pos < ELEMENTSOF(command_line));

        /* The watchdog: */

        if (objective == MANAGER_REBOOT)
                watchdog_timer = arg_reboot_watchdog;
        else if (objective == MANAGER_KEXEC)
                watchdog_timer = arg_kexec_watchdog;

        /* If we reboot or kexec let's set the shutdown watchdog and tell the
         * shutdown binary to repeatedly ping it.
         * Disable the pretimeout watchdog, as we do not support it from the shutdown binary. */
        (void) watchdog_setup_pretimeout(0);
        (void) watchdog_setup_pretimeout_governor(NULL);
        r = watchdog_setup(watchdog_timer);
        watchdog_close(r < 0);

        /* The environment block: */

        env_block = strv_copy(environ);

        /* Tell the binary how often to ping, ignore failure */
        (void) strv_extendf(&env_block, "WATCHDOG_USEC="USEC_FMT, watchdog_timer);

        if (arg_watchdog_device)
                (void) strv_extendf(&env_block, "WATCHDOG_DEVICE=%s", arg_watchdog_device);

        /* Avoid the creation of new processes forked by the kernel; at this
         * point, we will not listen to the signals anyway */
        if (detect_container() <= 0)
                (void) cg_uninstall_release_agent(SYSTEMD_CGROUP_CONTROLLER);

        execve(SYSTEMD_SHUTDOWN_BINARY_PATH, (char **) command_line, env_block);
        return -errno;
}

static void initialize_clock(void) {
        int r;

        /* This is called very early on, before we parse the kernel command line or otherwise figure out why
         * we are running, but only once. */

        if (clock_is_localtime(NULL) > 0) {
                int min;

                /* The very first call of settimeofday() also does a time warp in the kernel.
                 *
                 * In the rtc-in-local time mode, we set the kernel's timezone, and rely on external tools to
                 * take care of maintaining the RTC and do all adjustments.  This matches the behavior of
                 * Windows, which leaves the RTC alone if the registry tells that the RTC runs in UTC.
                 */
                r = clock_set_timezone(&min);
                if (r < 0)
                        log_error_errno(r, "Failed to apply local time delta, ignoring: %m");
                else
                        log_info("RTC configured in localtime, applying delta of %i minutes to system time.", min);

        } else if (!in_initrd())
                /*
                 * Do a dummy very first call to seal the kernel's time warp magic.
                 *
                 * Do not call this from inside the initrd. The initrd might not carry /etc/adjtime with
                 * LOCAL, but the real system could be set up that way. In such case, we need to delay the
                 * time-warp or the sealing until we reach the real system.
                 *
                 * Do no set the kernel's timezone. The concept of local time cannot be supported reliably,
                 * the time will jump or be incorrect at every daylight saving time change. All kernel local
                 * time concepts will be treated as UTC that way.
                 */
                (void) clock_reset_timewarp();

        ClockChangeDirection change_dir;
        r = clock_apply_epoch(&change_dir);
        if (r > 0 && change_dir == CLOCK_CHANGE_FORWARD)
                log_info("System time before build time, advancing clock.");
        else if (r > 0 && change_dir == CLOCK_CHANGE_BACKWARD)
                log_info("System time is further ahead than %s after build time, resetting clock to build time.",
                         FORMAT_TIMESPAN(CLOCK_VALID_RANGE_USEC_MAX, USEC_PER_DAY));
        else if (r < 0 && change_dir == CLOCK_CHANGE_FORWARD)
                log_error_errno(r, "Current system time is before build time, but cannot correct: %m");
        else if (r < 0 && change_dir == CLOCK_CHANGE_BACKWARD)
                log_error_errno(r, "Current system time is further ahead %s after build time, but cannot correct: %m",
                                FORMAT_TIMESPAN(CLOCK_VALID_RANGE_USEC_MAX, USEC_PER_DAY));
}

static void apply_clock_update(void) {
        /* This is called later than initialize_clock(), i.e. after we parsed configuration files/kernel
         * command line and such. */

        if (arg_clock_usec == 0)
                return;

        if (getpid_cached() != 1)
                return;

        if (clock_settime(CLOCK_REALTIME, TIMESPEC_STORE(arg_clock_usec)) < 0)
                log_error_errno(errno, "Failed to set system clock to time specified on kernel command line: %m");
        else
                log_info("Set system clock to %s, as specified on the kernel command line.",
                         FORMAT_TIMESTAMP(arg_clock_usec));
}

static void cmdline_take_random_seed(void) {
        size_t suggested;
        int r;

        if (arg_random_seed_size == 0)
                return;

        if (getpid_cached() != 1)
                return;

        assert(arg_random_seed);
        suggested = random_pool_size();

        if (arg_random_seed_size < suggested)
                log_warning("Random seed specified on kernel command line has size %zu, but %zu bytes required to fill entropy pool.",
                            arg_random_seed_size, suggested);

        r = random_write_entropy(-1, arg_random_seed, arg_random_seed_size, true);
        if (r < 0) {
                log_warning_errno(r, "Failed to credit entropy specified on kernel command line, ignoring: %m");
                return;
        }

        log_notice("Successfully credited entropy passed on kernel command line.\n"
                   "Note that the seed provided this way is accessible to unprivileged programs. "
                   "This functionality should not be used outside of testing environments.");
}

static void initialize_coredump(bool skip_setup) {
        if (getpid_cached() != 1)
                return;

        /* Don't limit the core dump size, so that coredump handlers such as systemd-coredump (which honour
         * the limit) will process core dumps for system services by default. */
        if (setrlimit(RLIMIT_CORE, &RLIMIT_MAKE_CONST(RLIM_INFINITY)) < 0)
                log_warning_errno(errno, "Failed to set RLIMIT_CORE: %m");

        /* But at the same time, turn off the core_pattern logic by default, so that no coredumps are stored
         * until the systemd-coredump tool is enabled via sysctl. However it can be changed via the kernel
         * command line later so core dumps can still be generated during early startup and in initrd. */
        if (!skip_setup)
                disable_coredumps();
}

static void initialize_core_pattern(bool skip_setup) {
        int r;

        if (skip_setup || !arg_early_core_pattern)
                return;

        if (getpid_cached() != 1)
                return;

        r = write_string_file("/proc/sys/kernel/core_pattern", arg_early_core_pattern, WRITE_STRING_FILE_DISABLE_BUFFER);
        if (r < 0)
                log_warning_errno(r, "Failed to write '%s' to /proc/sys/kernel/core_pattern, ignoring: %m",
                                  arg_early_core_pattern);
}

static void update_cpu_affinity(bool skip_setup) {
        _cleanup_free_ char *mask = NULL;

        if (skip_setup || !arg_cpu_affinity.set)
                return;

        assert(arg_cpu_affinity.allocated > 0);

        mask = cpu_set_to_range_string(&arg_cpu_affinity);
        log_debug("Setting CPU affinity to {%s}.", strnull(mask));

        if (sched_setaffinity(0, arg_cpu_affinity.allocated, arg_cpu_affinity.set) < 0)
                log_warning_errno(errno, "Failed to set CPU affinity, ignoring: %m");
}

static void update_numa_policy(bool skip_setup) {
        int r;
        _cleanup_free_ char *nodes = NULL;
        const char * policy = NULL;

        if (skip_setup || !mpol_is_valid(numa_policy_get_type(&arg_numa_policy)))
                return;

        if (DEBUG_LOGGING) {
                policy = mpol_to_string(numa_policy_get_type(&arg_numa_policy));
                nodes = cpu_set_to_range_string(&arg_numa_policy.nodes);
                log_debug("Setting NUMA policy to %s, with nodes {%s}.", strnull(policy), strnull(nodes));
        }

        r = apply_numa_policy(&arg_numa_policy);
        if (r == -EOPNOTSUPP)
                log_debug_errno(r, "NUMA support not available, ignoring.");
        else if (r < 0)
                log_warning_errno(r, "Failed to set NUMA memory policy, ignoring: %m");
}

static void filter_args(
                const char* dst[],
                size_t *dst_index,
                char **src,
                int argc) {

        assert(dst);
        assert(dst_index);

        /* Copy some filtered arguments into the dst array from src. */
        for (int i = 1; i < argc; i++) {
                if (STR_IN_SET(src[i],
                               "--switched-root",
                               "--system",
                               "--user"))
                        continue;

                if (startswith(src[i], "--deserialize="))
                        continue;
                if (streq(src[i], "--deserialize")) {
                        i++;                            /* Skip the argument too */
                        continue;
                }

                /* Skip target unit designators. We already acted upon this information and have queued
                 * appropriate jobs. We don't want to redo all this after reexecution. */
                if (startswith(src[i], "--unit="))
                        continue;
                if (streq(src[i], "--unit")) {
                        i++;                            /* Skip the argument too */
                        continue;
                }

                /* Seems we have a good old option. Let's pass it over to the new instance. */
                dst[(*dst_index)++] = src[i];
        }
}

static int do_reexecute(
                ManagerObjective objective,
                int argc,
                char* argv[],
                const struct rlimit *saved_rlimit_nofile,
                const struct rlimit *saved_rlimit_memlock,
                FDSet *fds,
                const char *switch_root_dir,
                const char *switch_root_init,
                const char **ret_error_message) {

        size_t i, args_size;
        const char **args;
        int r;

        assert(IN_SET(objective, MANAGER_REEXECUTE, MANAGER_SWITCH_ROOT));
        assert(argc >= 0);
        assert(saved_rlimit_nofile);
        assert(saved_rlimit_memlock);
        assert(ret_error_message);

        /* Close and disarm the watchdog, so that the new instance can reinitialize it, but doesn't get
         * rebooted while we do that */
        watchdog_close(true);

        /* Reset RLIMIT_NOFILE + RLIMIT_MEMLOCK back to the kernel defaults, so that the new systemd can pass
         * the kernel default to its child processes */
        if (saved_rlimit_nofile->rlim_cur != 0)
                (void) setrlimit(RLIMIT_NOFILE, saved_rlimit_nofile);
        if (saved_rlimit_memlock->rlim_cur != RLIM_INFINITY)
                (void) setrlimit(RLIMIT_MEMLOCK, saved_rlimit_memlock);

        if (switch_root_dir) {
                /* Kill all remaining processes from the initrd, but don't wait for them, so that we can
                 * handle the SIGCHLD for them after deserializing. */
                broadcast_signal(SIGTERM, false, true, arg_default_timeout_stop_usec);

                /* And switch root with MS_MOVE, because we remove the old directory afterwards and detach it. */
                r = switch_root(switch_root_dir, /* old_root_after= */ NULL, MS_MOVE);
                if (r < 0)
                        log_error_errno(r, "Failed to switch root, trying to continue: %m");
        }

        args_size = argc + 5;
        args = newa(const char*, args_size);

        if (!switch_root_init) {
                char sfd[STRLEN("--deserialize=") + DECIMAL_STR_MAX(int)];

                /* First try to spawn ourselves with the right path, and with full serialization. We do this
                 * only if the user didn't specify an explicit init to spawn. */

                assert(arg_serialization);
                assert(fds);

                xsprintf(sfd, "--deserialize=%i", fileno(arg_serialization));

                i = 1;         /* Leave args[0] empty for now. */
                filter_args(args, &i, argv, argc);

                if (switch_root_dir)
                        args[i++] = "--switched-root";
                args[i++] = runtime_scope_cmdline_option_to_string(arg_runtime_scope);
                args[i++] = sfd;
                args[i++] = NULL;

                assert(i <= args_size);

                /*
                 * We want valgrind to print its memory usage summary before reexecution. Valgrind won't do
                 * this is on its own on exec(), but it will do it on exit(). Hence, to ensure we get a
                 * summary here, fork() off a child, let it exit() cleanly, so that it prints the summary,
                 * and wait() for it in the parent, before proceeding into the exec().
                 */
                valgrind_summary_hack();

                args[0] = SYSTEMD_BINARY_PATH;
                (void) execv(args[0], (char* const*) args);

                if (objective == MANAGER_REEXECUTE) {
                        *ret_error_message = "Failed to execute our own binary";
                        return log_error_errno(errno, "Failed to execute our own binary %s: %m", args[0]);
                }

                log_debug_errno(errno, "Failed to execute our own binary %s, trying fallback: %m", args[0]);
        }

        /* Try the fallback, if there is any, without any serialization. We pass the original argv[] and
         * envp[]. (Well, modulo the ordering changes due to getopt() in argv[], and some cleanups in envp[],
         * but let's hope that doesn't matter.) */

        arg_serialization = safe_fclose(arg_serialization);
        fds = fdset_free(fds);

        /* Reopen the console */
        (void) make_console_stdio();

        i = 1;         /* Leave args[0] empty for now. */
        for (int j = 1; j <= argc; j++)
                args[i++] = argv[j];
        assert(i <= args_size);

        /* Re-enable any blocked signals, especially important if we switch from initrd to init=... */
        (void) reset_all_signal_handlers();
        (void) reset_signal_mask();
        (void) rlimit_nofile_safe();

        if (switch_root_init) {
                args[0] = switch_root_init;
                (void) execve(args[0], (char* const*) args, saved_env);
                log_warning_errno(errno, "Failed to execute configured init %s, trying fallback: %m", args[0]);
        }

        args[0] = "/sbin/init";
        (void) execv(args[0], (char* const*) args);
        r = -errno;

        manager_status_printf(NULL, STATUS_TYPE_EMERGENCY,
                              ANSI_HIGHLIGHT_RED "  !!  " ANSI_NORMAL,
                              "Failed to execute /sbin/init");

        *ret_error_message = "Failed to execute fallback shell";
        if (r == -ENOENT) {
                log_warning("No /sbin/init, trying fallback");

                args[0] = "/bin/sh";
                args[1] = NULL;
                (void) execve(args[0], (char* const*) args, saved_env);
                return log_error_errno(errno, "Failed to execute /bin/sh, giving up: %m");
        } else
                return log_error_errno(r, "Failed to execute /sbin/init, giving up: %m");
}

static int invoke_main_loop(
                Manager *m,
                const struct rlimit *saved_rlimit_nofile,
                const struct rlimit *saved_rlimit_memlock,
                int *ret_retval,                   /* Return parameters relevant for shutting down */
                FDSet **ret_fds,                   /* Return parameters for reexecuting */
                char **ret_switch_root_dir,        /* … */
                char **ret_switch_root_init,       /* … */
                const char **ret_error_message) {

        int r;

        assert(m);
        assert(saved_rlimit_nofile);
        assert(saved_rlimit_memlock);
        assert(ret_retval);
        assert(ret_fds);
        assert(ret_switch_root_dir);
        assert(ret_switch_root_init);
        assert(ret_error_message);

        for (;;) {
                int objective = manager_loop(m);
                if (objective < 0) {
                        *ret_error_message = "Failed to run main loop";
                        return log_emergency_errno(objective, "Failed to run main loop: %m");
                }

                switch (objective) {

                case MANAGER_RELOAD: {
                        LogTarget saved_log_target;
                        int saved_log_level;

                        manager_send_reloading(m);

                        log_info("Reloading...");

                        /* First, save any overridden log level/target, then parse the configuration file,
                         * which might change the log level to new settings. */

                        saved_log_level = m->log_level_overridden ? log_get_max_level() : -1;
                        saved_log_target = m->log_target_overridden ? log_get_target() : _LOG_TARGET_INVALID;

                        (void) parse_configuration(saved_rlimit_nofile, saved_rlimit_memlock);

                        set_manager_defaults(m);
                        set_manager_settings(m);

                        update_cpu_affinity(false);
                        update_numa_policy(false);

                        if (saved_log_level >= 0)
                                manager_override_log_level(m, saved_log_level);
                        if (saved_log_target >= 0)
                                manager_override_log_target(m, saved_log_target);

                        if (manager_reload(m) < 0)
                                /* Reloading failed before the point of no return.
                                 * Let's continue running as if nothing happened. */
                                m->objective = MANAGER_OK;
                        else
                                log_info("Reloading finished in " USEC_FMT " ms.",
                                         usec_sub_unsigned(now(CLOCK_MONOTONIC), m->timestamps[MANAGER_TIMESTAMP_UNITS_LOAD].monotonic) / USEC_PER_MSEC);

                        continue;
                }

                case MANAGER_REEXECUTE:

                        manager_send_reloading(m); /* From the perspective of the manager calling us this is
                                                    * pretty much the same as a reload */

                        r = prepare_reexecute(m, &arg_serialization, ret_fds, false);
                        if (r < 0) {
                                *ret_error_message = "Failed to prepare for reexecution";
                                return r;
                        }

                        log_notice("Reexecuting.");

                        *ret_retval = EXIT_SUCCESS;
                        *ret_switch_root_dir = *ret_switch_root_init = NULL;

                        return objective;

                case MANAGER_SWITCH_ROOT:

                        manager_send_reloading(m); /* From the perspective of the manager calling us this is
                                                    * pretty much the same as a reload */

                        manager_set_switching_root(m, true);

                        if (!m->switch_root_init) {
                                r = prepare_reexecute(m, &arg_serialization, ret_fds, true);
                                if (r < 0) {
                                        *ret_error_message = "Failed to prepare for reexecution";
                                        return r;
                                }
                        } else
                                *ret_fds = NULL;

                        log_notice("Switching root.");

                        *ret_retval = EXIT_SUCCESS;

                        /* Steal the switch root parameters */
                        *ret_switch_root_dir = TAKE_PTR(m->switch_root);
                        *ret_switch_root_init = TAKE_PTR(m->switch_root_init);

                        return objective;

                case MANAGER_EXIT:
                        if (MANAGER_IS_USER(m)) {
                                log_debug("Exit.");

                                *ret_retval = m->return_value;
                                *ret_fds = NULL;
                                *ret_switch_root_dir = *ret_switch_root_init = NULL;

                                return objective;
                        }

                        _fallthrough_;
                case MANAGER_REBOOT:
                case MANAGER_POWEROFF:
                case MANAGER_HALT:
                case MANAGER_KEXEC: {
                        log_notice("Shutting down.");

                        *ret_retval = m->return_value;
                        *ret_fds = NULL;
                        *ret_switch_root_dir = *ret_switch_root_init = NULL;

                        return objective;
                }

                default:
                        assert_not_reached();
                }
        }
}

static void log_execution_mode(bool *ret_first_boot) {
        bool first_boot = false;
        int r;

        assert(ret_first_boot);

        switch (arg_runtime_scope) {

        case RUNTIME_SCOPE_SYSTEM: {
                struct utsname uts;
                int v;

                log_info("systemd " GIT_VERSION " running in %ssystem mode (%s)",
                         arg_action == ACTION_TEST ? "test " : "",
                         systemd_features);

                v = detect_virtualization();
                if (v > 0)
                        log_info("Detected virtualization %s.", virtualization_to_string(v));

                log_info("Detected architecture %s.", architecture_to_string(uname_architecture()));

                if (in_initrd())
                        log_info("Running in initrd.");
                else {
                        _cleanup_free_ char *id_text = NULL;

                        /* Let's check whether we are in first boot. First, check if an override was
                         * specified on the kernel commandline. If yes, we honour that. */

                        r = proc_cmdline_get_bool("systemd.condition-first-boot", &first_boot);
                        if (r < 0)
                                log_debug_errno(r, "Failed to parse systemd.condition-first-boot= kernel commandline argument, ignoring: %m");

                        if (r > 0)
                                log_full(first_boot ? LOG_INFO : LOG_DEBUG,
                                         "Kernel commandline argument says we are %s first boot.",
                                         first_boot ? "in" : "not in");
                        else {
                                /* Second, perform autodetection. We use /etc/machine-id as flag file for
                                 * this: If it is missing or contains the value "uninitialized", this is the
                                 * first boot. In other cases, it is not. This allows container managers and
                                 * installers to provision a couple of files in /etc but still permit the
                                 * first-boot initialization to occur. If the container manager wants to
                                 * provision the machine ID it should pass $container_uuid to PID 1. */

                                r = read_one_line_file("/etc/machine-id", &id_text);
                                if (r < 0 || streq(id_text, "uninitialized")) {
                                        if (r < 0 && r != -ENOENT)
                                                log_warning_errno(r, "Unexpected error while reading /etc/machine-id, ignoring: %m");

                                        first_boot = true;
                                        log_info("Detected first boot.");
                                } else
                                        log_debug("Detected initialized system, this is not the first boot.");
                        }
                }

                assert_se(uname(&uts) >= 0);

                if (strverscmp_improved(uts.release, KERNEL_BASELINE_VERSION) < 0)
                        log_warning("Warning! Reported kernel version %s is older than systemd's required baseline kernel version %s. "
                                    "Your mileage may vary.", uts.release, KERNEL_BASELINE_VERSION);
                else
                        log_debug("Kernel version %s, our baseline is %s", uts.release, KERNEL_BASELINE_VERSION);

                break;
        }

        case RUNTIME_SCOPE_USER:
                if (DEBUG_LOGGING) {
                        _cleanup_free_ char *t = NULL;

                        t = uid_to_name(getuid());
                        log_debug("systemd " GIT_VERSION " running in %suser mode for user " UID_FMT "/%s. (%s)",
                                  arg_action == ACTION_TEST ? " test" : "",
                                  getuid(), strna(t), systemd_features);
                }

                break;

        default:
                assert_not_reached();
        }

        *ret_first_boot = first_boot;
}

static int initialize_runtime(
                bool skip_setup,
                bool first_boot,
                struct rlimit *saved_rlimit_nofile,
                struct rlimit *saved_rlimit_memlock,
                const char **ret_error_message) {
        int r;

        assert(ret_error_message);

        /* Sets up various runtime parameters. Many of these initializations are conditionalized:
         *
         * - Some only apply to --system instances
         * - Some only apply to --user instances
         * - Some only apply when we first start up, but not when we reexecute
         */

        if (arg_action != ACTION_RUN)
                return 0;

        update_cpu_affinity(skip_setup);
        update_numa_policy(skip_setup);

        switch (arg_runtime_scope) {

        case RUNTIME_SCOPE_SYSTEM:
                /* Make sure we leave a core dump without panicking the kernel. */
                install_crash_handler();

                if (!skip_setup) {
                        r = mount_cgroup_controllers();
                        if (r < 0) {
                                *ret_error_message = "Failed to mount cgroup hierarchies";
                                return r;
                        }

                        (void) os_release_status();
                        (void) hostname_setup(true);
                        /* Force transient machine-id on first boot. */
                        machine_id_setup(NULL, /* force_transient= */ first_boot, arg_machine_id, NULL);
                        (void) loopback_setup();
                        bump_unix_max_dgram_qlen();
                        bump_file_max_and_nr_open();
                        test_usr();
                        write_container_id();
                }

                r = watchdog_set_device(arg_watchdog_device);
                if (r < 0)
                        log_warning_errno(r, "Failed to set watchdog device to %s, ignoring: %m", arg_watchdog_device);

                break;

        case RUNTIME_SCOPE_USER: {
                _cleanup_free_ char *p = NULL;

                /* Create the runtime directory and place the inaccessible device nodes there, if we run in
                 * user mode. In system mode mount_setup() already did that. */

                r = xdg_user_runtime_dir(&p, "/systemd");
                if (r < 0) {
                        *ret_error_message = "$XDG_RUNTIME_DIR is not set";
                        return log_emergency_errno(r, "Failed to determine $XDG_RUNTIME_DIR path: %m");
                }

                (void) mkdir_p_label(p, 0755);
                (void) make_inaccessible_nodes(p, UID_INVALID, GID_INVALID);
                break;
        }

        default:
                assert_not_reached();
        }

        if (arg_timer_slack_nsec != NSEC_INFINITY)
                if (prctl(PR_SET_TIMERSLACK, arg_timer_slack_nsec) < 0)
                        log_warning_errno(errno, "Failed to adjust timer slack, ignoring: %m");

        if (arg_runtime_scope == RUNTIME_SCOPE_SYSTEM) {

                if (!cap_test_all(arg_capability_bounding_set)) {
                        r = capability_bounding_set_drop_usermode(arg_capability_bounding_set);
                        if (r < 0) {
                                *ret_error_message = "Failed to drop capability bounding set of usermode helpers";
                                return log_emergency_errno(r, "Failed to drop capability bounding set of usermode helpers: %m");
                        }

                        r = capability_bounding_set_drop(arg_capability_bounding_set, true);
                        if (r < 0) {
                                *ret_error_message = "Failed to drop capability bounding set";
                                return log_emergency_errno(r, "Failed to drop capability bounding set: %m");
                        }
                }

                if (arg_no_new_privs) {
                        if (prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0) < 0) {
                                *ret_error_message = "Failed to disable new privileges";
                                return log_emergency_errno(errno, "Failed to disable new privileges: %m");
                        }
                }
        }

        if (arg_syscall_archs) {
                r = enforce_syscall_archs(arg_syscall_archs);
                if (r < 0) {
                        *ret_error_message = "Failed to set syscall architectures";
                        return r;
                }
        }

        if (arg_runtime_scope == RUNTIME_SCOPE_USER)
                /* Become reaper of our children */
                if (prctl(PR_SET_CHILD_SUBREAPER, 1) < 0)
                        log_warning_errno(errno, "Failed to make us a subreaper, ignoring: %m");

        /* Bump up RLIMIT_NOFILE for systemd itself */
        (void) bump_rlimit_nofile(saved_rlimit_nofile);
        (void) bump_rlimit_memlock(saved_rlimit_memlock);

        /* Pull credentials from various sources into a common credential directory */
        if (arg_runtime_scope == RUNTIME_SCOPE_SYSTEM && !skip_setup)
                (void) import_credentials();

        return 0;
}

static int do_queue_default_job(
                Manager *m,
                const char **ret_error_message) {

        _cleanup_(sd_bus_error_free) sd_bus_error error = SD_BUS_ERROR_NULL;
        const char *unit;
        Job *job;
        Unit *target;
        int r;

        if (arg_default_unit)
                unit = arg_default_unit;
        else if (in_initrd())
                unit = SPECIAL_INITRD_TARGET;
        else
                unit = SPECIAL_DEFAULT_TARGET;

        log_debug("Activating default unit: %s", unit);

        r = manager_load_startable_unit_or_warn(m, unit, NULL, &target);
        if (r < 0 && in_initrd() && !arg_default_unit) {
                /* Fall back to default.target, which we used to always use by default. Only do this if no
                 * explicit configuration was given. */

                log_info("Falling back to " SPECIAL_DEFAULT_TARGET ".");

                r = manager_load_startable_unit_or_warn(m, SPECIAL_DEFAULT_TARGET, NULL, &target);
        }
        if (r < 0) {
                log_info("Falling back to " SPECIAL_RESCUE_TARGET ".");

                r = manager_load_startable_unit_or_warn(m, SPECIAL_RESCUE_TARGET, NULL, &target);
                if (r < 0) {
                        *ret_error_message = r == -ERFKILL ? SPECIAL_RESCUE_TARGET " masked"
                                                           : "Failed to load " SPECIAL_RESCUE_TARGET;
                        return r;
                }
        }

        assert(target->load_state == UNIT_LOADED);

        r = manager_add_job(m, JOB_START, target, JOB_ISOLATE, NULL, &error, &job);
        if (r == -EPERM) {
                log_debug_errno(r, "Default target could not be isolated, starting instead: %s", bus_error_message(&error, r));

                sd_bus_error_free(&error);

                r = manager_add_job(m, JOB_START, target, JOB_REPLACE, NULL, &error, &job);
                if (r < 0) {
                        *ret_error_message = "Failed to start default target";
                        return log_emergency_errno(r, "Failed to start default target: %s", bus_error_message(&error, r));
                }

        } else if (r < 0) {
                *ret_error_message = "Failed to isolate default target";
                return log_emergency_errno(r, "Failed to isolate default target: %s", bus_error_message(&error, r));
        } else
                log_info("Queued %s job for default target %s.",
                         job_type_to_string(job->type),
                         unit_status_string(job->unit, NULL));

        m->default_unit_job_id = job->id;

        return 0;
}

static void save_rlimits(struct rlimit *saved_rlimit_nofile,
                         struct rlimit *saved_rlimit_memlock) {

        assert(saved_rlimit_nofile);
        assert(saved_rlimit_memlock);

        if (getrlimit(RLIMIT_NOFILE, saved_rlimit_nofile) < 0)
                log_warning_errno(errno, "Reading RLIMIT_NOFILE failed, ignoring: %m");

        if (getrlimit(RLIMIT_MEMLOCK, saved_rlimit_memlock) < 0)
                log_warning_errno(errno, "Reading RLIMIT_MEMLOCK failed, ignoring: %m");
}

static void fallback_rlimit_nofile(const struct rlimit *saved_rlimit_nofile) {
        struct rlimit *rl;

        if (arg_default_rlimit[RLIMIT_NOFILE])
                return;

        /* Make sure forked processes get limits based on the original kernel setting */

        rl = newdup(struct rlimit, saved_rlimit_nofile, 1);
        if (!rl) {
                log_oom();
                return;
        }

        /* Bump the hard limit for system services to a substantially higher value. The default
         * hard limit current kernels set is pretty low (4K), mostly for historical
         * reasons. According to kernel developers, the fd handling in recent kernels has been
         * optimized substantially enough, so that we can bump the limit now, without paying too
         * high a price in memory or performance. Note however that we only bump the hard limit,
         * not the soft limit. That's because select() works the way it works, and chokes on fds
         * >= 1024. If we'd bump the soft limit globally, it might accidentally happen to
         * unexpecting programs that they get fds higher than what they can process using
         * select(). By only bumping the hard limit but leaving the low limit as it is we avoid
         * this pitfall:  programs that are written by folks aware of the select() problem in mind
         * (and thus use poll()/epoll instead of select(), the way everybody should) can
         * explicitly opt into high fds by bumping their soft limit beyond 1024, to the hard limit
         * we pass. */
        if (arg_runtime_scope == RUNTIME_SCOPE_SYSTEM) {
                int nr;

                /* Get the underlying absolute limit the kernel enforces */
                nr = read_nr_open();

                rl->rlim_max = MIN((rlim_t) nr, MAX(rl->rlim_max, (rlim_t) HIGH_RLIMIT_NOFILE));
        }

        /* If for some reason we were invoked with a soft limit above 1024 (which should never
         * happen!, but who knows what we get passed in from pam_limit when invoked as --user
         * instance), then lower what we pass on to not confuse our children */
        rl->rlim_cur = MIN(rl->rlim_cur, (rlim_t) FD_SETSIZE);

        arg_default_rlimit[RLIMIT_NOFILE] = rl;
}

static void fallback_rlimit_memlock(const struct rlimit *saved_rlimit_memlock) {
        struct rlimit *rl;

        /* Pass the original value down to invoked processes */

        if (arg_default_rlimit[RLIMIT_MEMLOCK])
                return;

        rl = newdup(struct rlimit, saved_rlimit_memlock, 1);
        if (!rl) {
                log_oom();
                return;
        }

        if (arg_runtime_scope == RUNTIME_SCOPE_SYSTEM)  {
                /* Raise the default limit to 8M also on old kernels and in containers (8M is the kernel
                 * default for this since kernel 5.16) */
                rl->rlim_max = MAX(rl->rlim_max, (rlim_t) DEFAULT_RLIMIT_MEMLOCK);
                rl->rlim_cur = MAX(rl->rlim_cur, (rlim_t) DEFAULT_RLIMIT_MEMLOCK);
        }

        arg_default_rlimit[RLIMIT_MEMLOCK] = rl;
}

static void setenv_manager_environment(void) {
        int r;

        STRV_FOREACH(p, arg_manager_environment) {
                log_debug("Setting '%s' in our own environment.", *p);

                r = putenv_dup(*p, true);
                if (r < 0)
                        log_warning_errno(errno, "Failed to setenv \"%s\", ignoring: %m", *p);
        }
}

static void reset_arguments(void) {
        /* Frees/resets arg_* variables, with a few exceptions commented below. */

        arg_default_unit = mfree(arg_default_unit);

        /* arg_runtime_scope — ignore */

        arg_dump_core = true;
        arg_crash_chvt = -1;
        arg_crash_shell = false;
        arg_crash_reboot = false;
        arg_confirm_spawn = mfree(arg_confirm_spawn);
        arg_show_status = _SHOW_STATUS_INVALID;
        arg_status_unit_format = STATUS_UNIT_FORMAT_DEFAULT;
        arg_switched_root = false;
        arg_pager_flags = 0;
        arg_service_watchdogs = true;
        arg_default_std_output = EXEC_OUTPUT_JOURNAL;
        arg_default_std_error = EXEC_OUTPUT_INHERIT;
        arg_default_restart_usec = DEFAULT_RESTART_USEC;
        arg_default_timeout_start_usec = manager_default_timeout(arg_runtime_scope);
        arg_default_timeout_stop_usec = manager_default_timeout(arg_runtime_scope);
        arg_default_timeout_abort_usec = manager_default_timeout(arg_runtime_scope);
        arg_default_timeout_abort_set = false;
        arg_default_device_timeout_usec = manager_default_timeout(arg_runtime_scope);
        arg_default_start_limit_interval = DEFAULT_START_LIMIT_INTERVAL;
        arg_default_start_limit_burst = DEFAULT_START_LIMIT_BURST;
        arg_runtime_watchdog = 0;
        arg_reboot_watchdog = 10 * USEC_PER_MINUTE;
        arg_kexec_watchdog = 0;
        arg_pretimeout_watchdog = 0;
        arg_early_core_pattern = mfree(arg_early_core_pattern);
        arg_watchdog_device = mfree(arg_watchdog_device);
        arg_watchdog_pretimeout_governor = mfree(arg_watchdog_pretimeout_governor);

        arg_default_environment = strv_free(arg_default_environment);
        arg_manager_environment = strv_free(arg_manager_environment);
        rlimit_free_all(arg_default_rlimit);

        arg_capability_bounding_set = CAP_MASK_UNSET;
        arg_no_new_privs = false;
        arg_timer_slack_nsec = NSEC_INFINITY;
        arg_default_timer_accuracy_usec = 1 * USEC_PER_MINUTE;

        arg_syscall_archs = set_free(arg_syscall_archs);

        /* arg_serialization — ignore */

        arg_default_cpu_accounting = -1;
        arg_default_io_accounting = false;
        arg_default_ip_accounting = false;
        arg_default_blockio_accounting = false;
        arg_default_memory_accounting = MEMORY_ACCOUNTING_DEFAULT;
        arg_default_tasks_accounting = true;
        arg_default_tasks_max = DEFAULT_TASKS_MAX;
        arg_default_memory_pressure_threshold_usec = MEMORY_PRESSURE_DEFAULT_THRESHOLD_USEC;
        arg_default_memory_pressure_watch = CGROUP_PRESSURE_WATCH_AUTO;
        arg_machine_id = (sd_id128_t) {};
        arg_cad_burst_action = EMERGENCY_ACTION_REBOOT_FORCE;
        arg_default_oom_policy = OOM_STOP;

        cpu_set_reset(&arg_cpu_affinity);
        numa_policy_reset(&arg_numa_policy);

        arg_random_seed = mfree(arg_random_seed);
        arg_random_seed_size = 0;
        arg_clock_usec = 0;

        arg_default_oom_score_adjust_set = false;
        arg_default_smack_process_label = mfree(arg_default_smack_process_label);

        arg_reload_limit_interval_sec = 0;
        arg_reload_limit_burst = 0;
}

static void determine_default_oom_score_adjust(void) {
        int r, a, b;

        /* Run our services at slightly higher OOM score than ourselves. But let's be conservative here, and
         * do this only if we don't run as root (i.e. only if we are run in user mode, for an unprivileged
         * user). */

        if (arg_default_oom_score_adjust_set)
                return;

        if (getuid() == 0)
                return;

        r = get_oom_score_adjust(&a);
        if (r < 0)
                return (void) log_warning_errno(r, "Failed to determine current OOM score adjustment value, ignoring: %m");

        assert_cc(100 <= OOM_SCORE_ADJ_MAX);
        b = a >= OOM_SCORE_ADJ_MAX - 100 ? OOM_SCORE_ADJ_MAX : a + 100;

        if (a == b)
                return;

        arg_default_oom_score_adjust = b;
        arg_default_oom_score_adjust_set = true;
}

static int parse_configuration(const struct rlimit *saved_rlimit_nofile,
                               const struct rlimit *saved_rlimit_memlock) {
        int r;

        assert(saved_rlimit_nofile);
        assert(saved_rlimit_memlock);

        /* Assign configuration defaults */
        reset_arguments();

        r = parse_config_file();
        if (r < 0)
                log_warning_errno(r, "Failed to parse config file, ignoring: %m");

        if (arg_runtime_scope == RUNTIME_SCOPE_SYSTEM) {
                r = proc_cmdline_parse(parse_proc_cmdline_item, NULL, 0);
                if (r < 0)
                        log_warning_errno(r, "Failed to parse kernel command line, ignoring: %m");
        }

        /* Initialize some default rlimits for services if they haven't been configured */
        fallback_rlimit_nofile(saved_rlimit_nofile);
        fallback_rlimit_memlock(saved_rlimit_memlock);

        /* Note that this also parses bits from the kernel command line, including "debug". */
        log_parse_environment();

        /* Initialize the show status setting if it hasn't been set explicitly yet */
        if (arg_show_status == _SHOW_STATUS_INVALID)
                arg_show_status = SHOW_STATUS_YES;

        /* Slightly raise the OOM score for our services if we are running for unprivileged users. */
        determine_default_oom_score_adjust();

        /* Push variables into the manager environment block */
        setenv_manager_environment();

        /* Parse log environment variables again to take into account any new environment variables. */
        log_parse_environment();

        return 0;
}

static int safety_checks(void) {

        if (getpid_cached() == 1 &&
            arg_action != ACTION_RUN)
                return log_error_errno(SYNTHETIC_ERRNO(EPERM),
                                       "Unsupported execution mode while PID 1.");

        if (getpid_cached() == 1 &&
            arg_runtime_scope == RUNTIME_SCOPE_USER)
                return log_error_errno(SYNTHETIC_ERRNO(EPERM),
                                       "Can't run --user mode as PID 1.");

        if (arg_action == ACTION_RUN &&
            arg_runtime_scope == RUNTIME_SCOPE_SYSTEM &&
            getpid_cached() != 1)
                return log_error_errno(SYNTHETIC_ERRNO(EPERM),
                                       "Can't run system mode unless PID 1.");

        if (arg_action == ACTION_TEST &&
            geteuid() == 0)
                return log_error_errno(SYNTHETIC_ERRNO(EPERM),
                                       "Don't run test mode as root.");

        switch (arg_runtime_scope) {

        case RUNTIME_SCOPE_USER:

                if (arg_action == ACTION_RUN &&
                    sd_booted() <= 0)
                        return log_error_errno(SYNTHETIC_ERRNO(EOPNOTSUPP),
                                               "Trying to run as user instance, but the system has not been booted with systemd.");

                if (arg_action == ACTION_RUN &&
                    !getenv("XDG_RUNTIME_DIR"))
                        return log_error_errno(SYNTHETIC_ERRNO(EUNATCH),
                                               "Trying to run as user instance, but $XDG_RUNTIME_DIR is not set.");

                break;

        case RUNTIME_SCOPE_SYSTEM:
                if (arg_action == ACTION_RUN &&
                    running_in_chroot() > 0)
                        return log_error_errno(SYNTHETIC_ERRNO(EOPNOTSUPP),
                                               "Cannot be run in a chroot() environment.");
                break;

        default:
                assert_not_reached();
        }

        return 0;
}

static int initialize_security(
                bool *loaded_policy,
                dual_timestamp *security_start_timestamp,
                dual_timestamp *security_finish_timestamp,
                const char **ret_error_message) {

        int r;

        assert(loaded_policy);
        assert(security_start_timestamp);
        assert(security_finish_timestamp);
        assert(ret_error_message);

        dual_timestamp_get(security_start_timestamp);

        r = mac_selinux_setup(loaded_policy);
        if (r < 0) {
                *ret_error_message = "Failed to load SELinux policy";
                return r;
        }

        r = mac_smack_setup(loaded_policy);
        if (r < 0) {
                *ret_error_message = "Failed to load SMACK policy";
                return r;
        }

        r = mac_apparmor_setup();
        if (r < 0) {
                *ret_error_message = "Failed to load AppArmor policy";
                return r;
        }

        r = ima_setup();
        if (r < 0) {
                *ret_error_message = "Failed to load IMA policy";
                return r;
        }

        dual_timestamp_get(security_finish_timestamp);
        return 0;
}

static int collect_fds(FDSet **ret_fds, const char **ret_error_message) {
        int r;

        assert(ret_fds);
        assert(ret_error_message);

        r = fdset_new_fill(ret_fds);
        if (r < 0) {
                *ret_error_message = "Failed to allocate fd set";
                return log_emergency_errno(r, "Failed to allocate fd set: %m");
        }

        fdset_cloexec(*ret_fds, true);

        if (arg_serialization)
                assert_se(fdset_remove(*ret_fds, fileno(arg_serialization)) >= 0);

        return 0;
}

static void setup_console_terminal(bool skip_setup) {

        if (arg_runtime_scope != RUNTIME_SCOPE_SYSTEM)
                return;

        /* Become a session leader if we aren't one yet. */
        (void) setsid();

        /* If we are init, we connect stdin/stdout/stderr to /dev/null and make sure we don't have a
         * controlling tty. */
        (void) release_terminal();

        /* Reset the console, but only if this is really init and we are freshly booted */
        if (getpid_cached() == 1 && !skip_setup)
                (void) console_setup();
}

static bool early_skip_setup_check(int argc, char *argv[]) {
        bool found_deserialize = false;

        /* Determine if this is a reexecution or normal bootup. We do the full command line parsing much
         * later, so let's just have a quick peek here. Note that if we have switched root, do all the
         * special setup things anyway, even if in that case we also do deserialization. */

        for (int i = 1; i < argc; i++)
                if (streq(argv[i], "--switched-root"))
                        return false; /* If we switched root, don't skip the setup. */
                else if (startswith(argv[i], "--deserialize=") || streq(argv[i], "--deserialize"))
                        found_deserialize = true;

        return found_deserialize; /* When we are deserializing, then we are reexecuting, hence avoid the extensive setup */
}

static int save_env(void) {
        char **l;

        l = strv_copy(environ);
        if (!l)
                return -ENOMEM;

        strv_free_and_replace(saved_env, l);
        return 0;
}

int main(int argc, char *argv[]) {
        dual_timestamp
                initrd_timestamp = DUAL_TIMESTAMP_NULL,
                userspace_timestamp = DUAL_TIMESTAMP_NULL,
                kernel_timestamp = DUAL_TIMESTAMP_NULL,
                security_start_timestamp = DUAL_TIMESTAMP_NULL,
                security_finish_timestamp = DUAL_TIMESTAMP_NULL;
        struct rlimit saved_rlimit_nofile = RLIMIT_MAKE_CONST(0),
                saved_rlimit_memlock = RLIMIT_MAKE_CONST(RLIM_INFINITY); /* The original rlimits we passed
                                                                          * in. Note we use different values
                                                                          * for the two that indicate whether
                                                                          * these fields are initialized! */
        bool skip_setup, loaded_policy = false, queue_default_job = false, first_boot = false;
        char *switch_root_dir = NULL, *switch_root_init = NULL;
        usec_t before_startup, after_startup;
        static char systemd[] = "systemd";
        const char *error_message = NULL;
        int r, retval = EXIT_FAILURE;
        Manager *m = NULL;
        FDSet *fds = NULL;

        assert_se(argc > 0 && !isempty(argv[0]));

        /* SysV compatibility: redirect init → telinit */
        redirect_telinit(argc, argv);

        /* Take timestamps early on */
        dual_timestamp_from_monotonic(&kernel_timestamp, 0);
        dual_timestamp_get(&userspace_timestamp);

        /* Figure out whether we need to do initialize the system, or if we already did that because we are
         * reexecuting. */
        skip_setup = early_skip_setup_check(argc, argv);

        /* If we get started via the /sbin/init symlink then we are called 'init'. After a subsequent
         * reexecution we are then called 'systemd'. That is confusing, hence let's call us systemd
         * right-away. */
        program_invocation_short_name = systemd;
        (void) prctl(PR_SET_NAME, systemd);

        /* Save the original command line */
        save_argc_argv(argc, argv);

        /* Save the original environment as we might need to restore it if we're requested to execute another
         * system manager later. */
        r = save_env();
        if (r < 0) {
                error_message = "Failed to copy environment block";
                goto finish;
        }

        /* Make sure that if the user says "syslog" we actually log to the journal. */
        log_set_upgrade_syslog_to_journal(true);

        if (getpid_cached() == 1) {
                /* When we run as PID 1 force system mode */
                arg_runtime_scope = RUNTIME_SCOPE_SYSTEM;

                /* Disable the umask logic */
                umask(0);

                /* Make sure that at least initially we do not ever log to journald/syslogd, because it might
                 * not be activated yet (even though the log socket for it exists). */
                log_set_prohibit_ipc(true);

                /* Always reopen /dev/console when running as PID 1 or one of its pre-execve() children. This
                 * is important so that we never end up logging to any foreign stderr, for example if we have
                 * to log in a child process right before execve()'ing the actual binary, at a point in time
                 * where socket activation stderr/stdout area already set up. */
                log_set_always_reopen_console(true);

                if (detect_container() <= 0) {

                        /* Running outside of a container as PID 1 */
                        log_set_target_and_open(LOG_TARGET_KMSG);

                        if (in_initrd())
                                initrd_timestamp = userspace_timestamp;

                        if (!skip_setup) {
                                r = mount_setup_early();
                                if (r < 0) {
                                        error_message = "Failed to mount early API filesystems";
                                        goto finish;
                                }
                        }

                        /* We might have just mounted /proc, so let's try to parse the kernel
                         * command line log arguments immediately. */
                        log_parse_environment();

                        /* Let's open the log backend a second time, in case the first time didn't
                         * work. Quite possibly we have mounted /dev just now, so /dev/kmsg became
                         * available, and it previously wasn't. */
                        log_open();

                        if (!skip_setup) {
                                disable_printk_ratelimit();

                                r = initialize_security(
                                                &loaded_policy,
                                                &security_start_timestamp,
                                                &security_finish_timestamp,
                                                &error_message);
                                if (r < 0)
                                        goto finish;
                        }

                        if (mac_selinux_init() < 0) {
                                error_message = "Failed to initialize SELinux support";
                                goto finish;
                        }

                        if (!skip_setup)
                                initialize_clock();

                        /* Set the default for later on, but don't actually open the logs like this for
                         * now. Note that if we are transitioning from the initrd there might still be
                         * journal fd open, and we shouldn't attempt opening that before we parsed
                         * /proc/cmdline which might redirect output elsewhere. */
                        log_set_target(LOG_TARGET_JOURNAL_OR_KMSG);

                } else {
                        /* Running inside a container, as PID 1 */
                        log_set_target_and_open(LOG_TARGET_CONSOLE);

                        /* For later on, see above... */
                        log_set_target(LOG_TARGET_JOURNAL);

                        /* clear the kernel timestamp, because we are in a container */
                        kernel_timestamp = DUAL_TIMESTAMP_NULL;
                }

                initialize_coredump(skip_setup);

                r = fixup_environment();
                if (r < 0) {
                        log_emergency_errno(r, "Failed to fix up PID 1 environment: %m");
                        error_message = "Failed to fix up PID1 environment";
                        goto finish;
                }

                /* Try to figure out if we can use colors with the console. No need to do that for user
                 * instances since they never log into the console. */
                log_show_color(colors_enabled());

                r = make_null_stdio();
                if (r < 0)
                        log_warning_errno(r, "Failed to redirect standard streams to /dev/null, ignoring: %m");

                /* Load the kernel modules early. */
                if (!skip_setup)
                        (void) kmod_setup();

                /* Mount /proc, /sys and friends, so that /proc/cmdline and /proc/$PID/fd is available. */
                r = mount_setup(loaded_policy, skip_setup);
                if (r < 0) {
                        error_message = "Failed to mount API filesystems";
                        goto finish;
                }

                /* The efivarfs is now mounted, let's lock down the system token. */
                lock_down_efi_variables();

                /* Cache command-line options passed from EFI variables */
                if (!skip_setup)
                        (void) cache_efi_options_variable();
        } else {
                /* Running as user instance */
                arg_runtime_scope = RUNTIME_SCOPE_USER;
                log_set_always_reopen_console(true);
                log_set_target_and_open(LOG_TARGET_AUTO);

                /* clear the kernel timestamp, because we are not PID 1 */
                kernel_timestamp = DUAL_TIMESTAMP_NULL;

                /* Clear ambient capabilities, so services do not inherit them implicitly. Dropping them does
                 * not affect the permitted and effective sets which are important for the manager itself to
                 * operate. */
                capability_ambient_set_apply(0, /* also_inherit= */ false);

                if (mac_selinux_init() < 0) {
                        error_message = "Failed to initialize SELinux support";
                        goto finish;
                }
        }

        /* Save the original RLIMIT_NOFILE/RLIMIT_MEMLOCK so that we can reset it later when
         * transitioning from the initrd to the main systemd or suchlike. */
        save_rlimits(&saved_rlimit_nofile, &saved_rlimit_memlock);

        /* Reset all signal handlers. */
        (void) reset_all_signal_handlers();
        (void) ignore_signals(SIGNALS_IGNORE);

        (void) parse_configuration(&saved_rlimit_nofile, &saved_rlimit_memlock);

        r = parse_argv(argc, argv);
        if (r < 0) {
                error_message = "Failed to parse commandline arguments";
                goto finish;
        }

        r = safety_checks();
        if (r < 0)
                goto finish;

        if (IN_SET(arg_action, ACTION_TEST, ACTION_HELP, ACTION_DUMP_CONFIGURATION_ITEMS, ACTION_DUMP_BUS_PROPERTIES, ACTION_BUS_INTROSPECT))
                pager_open(arg_pager_flags);

        if (arg_action != ACTION_RUN)
                skip_setup = true;

        if (arg_action == ACTION_HELP) {
                retval = help() < 0 ? EXIT_FAILURE : EXIT_SUCCESS;
                goto finish;
        } else if (arg_action == ACTION_VERSION) {
                retval = version();
                goto finish;
        } else if (arg_action == ACTION_DUMP_CONFIGURATION_ITEMS) {
                unit_dump_config_items(stdout);
                retval = EXIT_SUCCESS;
                goto finish;
        } else if (arg_action == ACTION_DUMP_BUS_PROPERTIES) {
                dump_bus_properties(stdout);
                retval = EXIT_SUCCESS;
                goto finish;
        } else if (arg_action == ACTION_BUS_INTROSPECT) {
                r = bus_manager_introspect_implementations(stdout, arg_bus_introspect);
                retval = r >= 0 ? EXIT_SUCCESS : EXIT_FAILURE;
                goto finish;
        }

        assert_se(IN_SET(arg_action, ACTION_RUN, ACTION_TEST));

        /* Move out of the way, so that we won't block unmounts */
        assert_se(chdir("/") == 0);

        if (arg_action == ACTION_RUN) {
                if (!skip_setup) {
                        /* Apply the systemd.clock_usec= kernel command line switch */
                        apply_clock_update();

                        /* Apply random seed from kernel command line */
                        cmdline_take_random_seed();
                }

                /* A core pattern might have been specified via the cmdline.  */
                initialize_core_pattern(skip_setup);

                /* Close logging fds, in order not to confuse collecting passed fds and terminal logic below */
                log_close();

                /* Remember open file descriptors for later deserialization */
                r = collect_fds(&fds, &error_message);
                if (r < 0)
                        goto finish;

                /* Give up any control of the console, but make sure its initialized. */
                setup_console_terminal(skip_setup);

                /* Open the logging devices, if possible and necessary */
                log_open();
        }

        log_execution_mode(&first_boot);

        r = initialize_runtime(skip_setup,
                               first_boot,
                               &saved_rlimit_nofile,
                               &saved_rlimit_memlock,
                               &error_message);
        if (r < 0)
                goto finish;

        r = manager_new(arg_runtime_scope,
                        arg_action == ACTION_TEST ? MANAGER_TEST_FULL : 0,
                        &m);
        if (r < 0) {
                log_emergency_errno(r, "Failed to allocate manager object: %m");
                error_message = "Failed to allocate manager object";
                goto finish;
        }

        m->timestamps[MANAGER_TIMESTAMP_KERNEL] = kernel_timestamp;
        m->timestamps[MANAGER_TIMESTAMP_INITRD] = initrd_timestamp;
        m->timestamps[MANAGER_TIMESTAMP_USERSPACE] = userspace_timestamp;
        m->timestamps[manager_timestamp_initrd_mangle(MANAGER_TIMESTAMP_SECURITY_START)] = security_start_timestamp;
        m->timestamps[manager_timestamp_initrd_mangle(MANAGER_TIMESTAMP_SECURITY_FINISH)] = security_finish_timestamp;

        set_manager_defaults(m);
        set_manager_settings(m);
        manager_set_first_boot(m, first_boot);
        manager_set_switching_root(m, arg_switched_root);

        /* Remember whether we should queue the default job */
        queue_default_job = !arg_serialization || arg_switched_root;

        before_startup = now(CLOCK_MONOTONIC);

        r = manager_startup(m, arg_serialization, fds, /* root= */ NULL);
        if (r < 0) {
                error_message = "Failed to start up manager";
                goto finish;
        }

        /* This will close all file descriptors that were opened, but not claimed by any unit. */
        fds = fdset_free(fds);
        arg_serialization = safe_fclose(arg_serialization);

        if (queue_default_job) {
                r = do_queue_default_job(m, &error_message);
                if (r < 0)
                        goto finish;
        }

        after_startup = now(CLOCK_MONOTONIC);

        log_full(arg_action == ACTION_TEST ? LOG_INFO : LOG_DEBUG,
                 "Loaded units and determined initial transaction in %s.",
                 FORMAT_TIMESPAN(after_startup - before_startup, 100 * USEC_PER_MSEC));

        if (arg_action == ACTION_TEST) {
                manager_test_summary(m);
                retval = EXIT_SUCCESS;
                goto finish;
        }

        r = invoke_main_loop(m,
                             &saved_rlimit_nofile,
                             &saved_rlimit_memlock,
                             &retval,
                             &fds,
                             &switch_root_dir,
                             &switch_root_init,
                             &error_message);
        assert(r < 0 || IN_SET(r, MANAGER_EXIT,          /* MANAGER_OK is not expected here. */
                                  MANAGER_RELOAD,
                                  MANAGER_REEXECUTE,
                                  MANAGER_REBOOT,
                                  MANAGER_POWEROFF,
                                  MANAGER_HALT,
                                  MANAGER_KEXEC,
                                  MANAGER_SWITCH_ROOT));

finish:
        pager_close();

        if (m) {
                arg_reboot_watchdog = manager_get_watchdog(m, WATCHDOG_REBOOT);
                arg_kexec_watchdog = manager_get_watchdog(m, WATCHDOG_KEXEC);
                m = manager_free(m);
        }

        mac_selinux_finish();

        if (IN_SET(r, MANAGER_REEXECUTE, MANAGER_SWITCH_ROOT))
                r = do_reexecute(r,
                                 argc, argv,
                                 &saved_rlimit_nofile,
                                 &saved_rlimit_memlock,
                                 fds,
                                 switch_root_dir,
                                 switch_root_init,
                                 &error_message); /* This only returns if reexecution failed */

        arg_serialization = safe_fclose(arg_serialization);
        fds = fdset_free(fds);

        saved_env = strv_free(saved_env);

#if HAVE_VALGRIND_VALGRIND_H
        /* If we are PID 1 and running under valgrind, then let's exit
         * here explicitly. valgrind will only generate nice output on
         * exit(), not on exec(), hence let's do the former not the
         * latter here. */
        if (getpid_cached() == 1 && RUNNING_ON_VALGRIND) {
                /* Cleanup watchdog_device strings for valgrind. We need them
                 * in become_shutdown() so normally we cannot free them yet. */
                watchdog_free_device();
                reset_arguments();
                return retval;
        }
#endif

#if HAS_FEATURE_ADDRESS_SANITIZER
        __lsan_do_leak_check();
#endif

        if (r < 0)
                (void) sd_notifyf(0, "ERRNO=%i", -r);

        /* Try to invoke the shutdown binary unless we already failed.
         * If we failed above, we want to freeze after finishing cleanup. */
        if (arg_runtime_scope == RUNTIME_SCOPE_SYSTEM &&
            IN_SET(r, MANAGER_EXIT, MANAGER_REBOOT, MANAGER_POWEROFF, MANAGER_HALT, MANAGER_KEXEC)) {
                r = become_shutdown(r, retval);
                log_error_errno(r, "Failed to execute shutdown binary, %s: %m", getpid_cached() == 1 ? "freezing" : "quitting");
                error_message = "Failed to execute shutdown binary";
        }

        /* This is primarily useful when running systemd in a VM, as it provides the user running the VM with
         * a mechanism to pick up systemd's exit status in the VM. */
        (void) sd_notifyf(0, "EXIT_STATUS=%i", retval);

        watchdog_free_device();
        arg_watchdog_device = mfree(arg_watchdog_device);

        if (getpid_cached() == 1) {
                if (error_message)
                        manager_status_printf(NULL, STATUS_TYPE_EMERGENCY,
                                              ANSI_HIGHLIGHT_RED "!!!!!!" ANSI_NORMAL,
                                              "%s.", error_message);
                freeze_or_exit_or_reboot();
        }

        reset_arguments();
        return retval;
}