aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/printk/printk.c
blob: a1a81fd9889bb35d54102ce3cbc84a76cca24020 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
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
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
// SPDX-License-Identifier: GPL-2.0-only
/*
 *  linux/kernel/printk.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
 * Modified to make sys_syslog() more flexible: added commands to
 * return the last 4k of kernel messages, regardless of whether
 * they've been read or not.  Added option to suppress kernel printk's
 * to the console.  Added hook for sending the console messages
 * elsewhere, in preparation for a serial line console (someday).
 * Ted Ts'o, 2/11/93.
 * Modified for sysctl support, 1/8/97, Chris Horn.
 * Fixed SMP synchronization, 08/08/99, Manfred Spraul
 *     manfred@colorfullife.com
 * Rewrote bits to get rid of console_lock
 *	01Mar01 Andrew Morton
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/tty.h>
#include <linux/tty_driver.h>
#include <linux/console.h>
#include <linux/init.h>
#include <linux/jiffies.h>
#include <linux/nmi.h>
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/delay.h>
#include <linux/smp.h>
#include <linux/security.h>
#include <linux/memblock.h>
#include <linux/syscalls.h>
#include <linux/crash_core.h>
#include <linux/ratelimit.h>
#include <linux/kmsg_dump.h>
#include <linux/syslog.h>
#include <linux/cpu.h>
#include <linux/rculist.h>
#include <linux/poll.h>
#include <linux/irq_work.h>
#include <linux/ctype.h>
#include <linux/uio.h>
#include <linux/sched/clock.h>
#include <linux/sched/debug.h>
#include <linux/sched/task_stack.h>

#include <linux/uaccess.h>
#include <asm/sections.h>

#include <trace/events/initcall.h>
#define CREATE_TRACE_POINTS
#include <trace/events/printk.h>

#include "printk_ringbuffer.h"
#include "console_cmdline.h"
#include "braille.h"
#include "internal.h"

int console_printk[4] = {
	CONSOLE_LOGLEVEL_DEFAULT,	/* console_loglevel */
	MESSAGE_LOGLEVEL_DEFAULT,	/* default_message_loglevel */
	CONSOLE_LOGLEVEL_MIN,		/* minimum_console_loglevel */
	CONSOLE_LOGLEVEL_DEFAULT,	/* default_console_loglevel */
};
EXPORT_SYMBOL_GPL(console_printk);

atomic_t ignore_console_lock_warning __read_mostly = ATOMIC_INIT(0);
EXPORT_SYMBOL(ignore_console_lock_warning);

/*
 * Low level drivers may need that to know if they can schedule in
 * their unblank() callback or not. So let's export it.
 */
int oops_in_progress;
EXPORT_SYMBOL(oops_in_progress);

/*
 * console_sem protects the console_drivers list, and also
 * provides serialisation for access to the entire console
 * driver system.
 */
static DEFINE_SEMAPHORE(console_sem);
struct console *console_drivers;
EXPORT_SYMBOL_GPL(console_drivers);

/*
 * System may need to suppress printk message under certain
 * circumstances, like after kernel panic happens.
 */
int __read_mostly suppress_printk;

/*
 * During panic, heavy printk by other CPUs can delay the
 * panic and risk deadlock on console resources.
 */
static int __read_mostly suppress_panic_printk;

#ifdef CONFIG_LOCKDEP
static struct lockdep_map console_lock_dep_map = {
	.name = "console_lock"
};
#endif

enum devkmsg_log_bits {
	__DEVKMSG_LOG_BIT_ON = 0,
	__DEVKMSG_LOG_BIT_OFF,
	__DEVKMSG_LOG_BIT_LOCK,
};

enum devkmsg_log_masks {
	DEVKMSG_LOG_MASK_ON             = BIT(__DEVKMSG_LOG_BIT_ON),
	DEVKMSG_LOG_MASK_OFF            = BIT(__DEVKMSG_LOG_BIT_OFF),
	DEVKMSG_LOG_MASK_LOCK           = BIT(__DEVKMSG_LOG_BIT_LOCK),
};

/* Keep both the 'on' and 'off' bits clear, i.e. ratelimit by default: */
#define DEVKMSG_LOG_MASK_DEFAULT	0

static unsigned int __read_mostly devkmsg_log = DEVKMSG_LOG_MASK_DEFAULT;

static int __control_devkmsg(char *str)
{
	size_t len;

	if (!str)
		return -EINVAL;

	len = str_has_prefix(str, "on");
	if (len) {
		devkmsg_log = DEVKMSG_LOG_MASK_ON;
		return len;
	}

	len = str_has_prefix(str, "off");
	if (len) {
		devkmsg_log = DEVKMSG_LOG_MASK_OFF;
		return len;
	}

	len = str_has_prefix(str, "ratelimit");
	if (len) {
		devkmsg_log = DEVKMSG_LOG_MASK_DEFAULT;
		return len;
	}

	return -EINVAL;
}

static int __init control_devkmsg(char *str)
{
	if (__control_devkmsg(str) < 0) {
		pr_warn("printk.devkmsg: bad option string '%s'\n", str);
		return 1;
	}

	/*
	 * Set sysctl string accordingly:
	 */
	if (devkmsg_log == DEVKMSG_LOG_MASK_ON)
		strcpy(devkmsg_log_str, "on");
	else if (devkmsg_log == DEVKMSG_LOG_MASK_OFF)
		strcpy(devkmsg_log_str, "off");
	/* else "ratelimit" which is set by default. */

	/*
	 * Sysctl cannot change it anymore. The kernel command line setting of
	 * this parameter is to force the setting to be permanent throughout the
	 * runtime of the system. This is a precation measure against userspace
	 * trying to be a smarta** and attempting to change it up on us.
	 */
	devkmsg_log |= DEVKMSG_LOG_MASK_LOCK;

	return 1;
}
__setup("printk.devkmsg=", control_devkmsg);

char devkmsg_log_str[DEVKMSG_STR_MAX_SIZE] = "ratelimit";
#if defined(CONFIG_PRINTK) && defined(CONFIG_SYSCTL)
int devkmsg_sysctl_set_loglvl(struct ctl_table *table, int write,
			      void *buffer, size_t *lenp, loff_t *ppos)
{
	char old_str[DEVKMSG_STR_MAX_SIZE];
	unsigned int old;
	int err;

	if (write) {
		if (devkmsg_log & DEVKMSG_LOG_MASK_LOCK)
			return -EINVAL;

		old = devkmsg_log;
		strncpy(old_str, devkmsg_log_str, DEVKMSG_STR_MAX_SIZE);
	}

	err = proc_dostring(table, write, buffer, lenp, ppos);
	if (err)
		return err;

	if (write) {
		err = __control_devkmsg(devkmsg_log_str);

		/*
		 * Do not accept an unknown string OR a known string with
		 * trailing crap...
		 */
		if (err < 0 || (err + 1 != *lenp)) {

			/* ... and restore old setting. */
			devkmsg_log = old;
			strncpy(devkmsg_log_str, old_str, DEVKMSG_STR_MAX_SIZE);

			return -EINVAL;
		}
	}

	return 0;
}
#endif /* CONFIG_PRINTK && CONFIG_SYSCTL */

/* Number of registered extended console drivers. */
static int nr_ext_console_drivers;

/*
 * Helper macros to handle lockdep when locking/unlocking console_sem. We use
 * macros instead of functions so that _RET_IP_ contains useful information.
 */
#define down_console_sem() do { \
	down(&console_sem);\
	mutex_acquire(&console_lock_dep_map, 0, 0, _RET_IP_);\
} while (0)

static int __down_trylock_console_sem(unsigned long ip)
{
	int lock_failed;
	unsigned long flags;

	/*
	 * Here and in __up_console_sem() we need to be in safe mode,
	 * because spindump/WARN/etc from under console ->lock will
	 * deadlock in printk()->down_trylock_console_sem() otherwise.
	 */
	printk_safe_enter_irqsave(flags);
	lock_failed = down_trylock(&console_sem);
	printk_safe_exit_irqrestore(flags);

	if (lock_failed)
		return 1;
	mutex_acquire(&console_lock_dep_map, 0, 1, ip);
	return 0;
}
#define down_trylock_console_sem() __down_trylock_console_sem(_RET_IP_)

static void __up_console_sem(unsigned long ip)
{
	unsigned long flags;

	mutex_release(&console_lock_dep_map, ip);

	printk_safe_enter_irqsave(flags);
	up(&console_sem);
	printk_safe_exit_irqrestore(flags);
}
#define up_console_sem() __up_console_sem(_RET_IP_)

static bool panic_in_progress(void)
{
	return unlikely(atomic_read(&panic_cpu) != PANIC_CPU_INVALID);
}

/*
 * This is used for debugging the mess that is the VT code by
 * keeping track if we have the console semaphore held. It's
 * definitely not the perfect debug tool (we don't know if _WE_
 * hold it and are racing, but it helps tracking those weird code
 * paths in the console code where we end up in places I want
 * locked without the console semaphore held).
 */
static int console_locked, console_suspended;

/*
 *	Array of consoles built from command line options (console=)
 */

#define MAX_CMDLINECONSOLES 8

static struct console_cmdline console_cmdline[MAX_CMDLINECONSOLES];

static int preferred_console = -1;
int console_set_on_cmdline;
EXPORT_SYMBOL(console_set_on_cmdline);

/* Flag: console code may call schedule() */
static int console_may_schedule;

enum con_msg_format_flags {
	MSG_FORMAT_DEFAULT	= 0,
	MSG_FORMAT_SYSLOG	= (1 << 0),
};

static int console_msg_format = MSG_FORMAT_DEFAULT;

/*
 * The printk log buffer consists of a sequenced collection of records, each
 * containing variable length message text. Every record also contains its
 * own meta-data (@info).
 *
 * Every record meta-data carries the timestamp in microseconds, as well as
 * the standard userspace syslog level and syslog facility. The usual kernel
 * messages use LOG_KERN; userspace-injected messages always carry a matching
 * syslog facility, by default LOG_USER. The origin of every message can be
 * reliably determined that way.
 *
 * The human readable log message of a record is available in @text, the
 * length of the message text in @text_len. The stored message is not
 * terminated.
 *
 * Optionally, a record can carry a dictionary of properties (key/value
 * pairs), to provide userspace with a machine-readable message context.
 *
 * Examples for well-defined, commonly used property names are:
 *   DEVICE=b12:8               device identifier
 *                                b12:8         block dev_t
 *                                c127:3        char dev_t
 *                                n8            netdev ifindex
 *                                +sound:card0  subsystem:devname
 *   SUBSYSTEM=pci              driver-core subsystem name
 *
 * Valid characters in property names are [a-zA-Z0-9.-_]. Property names
 * and values are terminated by a '\0' character.
 *
 * Example of record values:
 *   record.text_buf                = "it's a line" (unterminated)
 *   record.info.seq                = 56
 *   record.info.ts_nsec            = 36863
 *   record.info.text_len           = 11
 *   record.info.facility           = 0 (LOG_KERN)
 *   record.info.flags              = 0
 *   record.info.level              = 3 (LOG_ERR)
 *   record.info.caller_id          = 299 (task 299)
 *   record.info.dev_info.subsystem = "pci" (terminated)
 *   record.info.dev_info.device    = "+pci:0000:00:01.0" (terminated)
 *
 * The 'struct printk_info' buffer must never be directly exported to
 * userspace, it is a kernel-private implementation detail that might
 * need to be changed in the future, when the requirements change.
 *
 * /dev/kmsg exports the structured data in the following line format:
 *   "<level>,<sequnum>,<timestamp>,<contflag>[,additional_values, ... ];<message text>\n"
 *
 * Users of the export format should ignore possible additional values
 * separated by ',', and find the message after the ';' character.
 *
 * The optional key/value pairs are attached as continuation lines starting
 * with a space character and terminated by a newline. All possible
 * non-prinatable characters are escaped in the "\xff" notation.
 */

/* syslog_lock protects syslog_* variables and write access to clear_seq. */
static DEFINE_MUTEX(syslog_lock);

#ifdef CONFIG_PRINTK
DECLARE_WAIT_QUEUE_HEAD(log_wait);
/* All 3 protected by @syslog_lock. */
/* the next printk record to read by syslog(READ) or /proc/kmsg */
static u64 syslog_seq;
static size_t syslog_partial;
static bool syslog_time;

struct latched_seq {
	seqcount_latch_t	latch;
	u64			val[2];
};

/*
 * The next printk record to read after the last 'clear' command. There are
 * two copies (updated with seqcount_latch) so that reads can locklessly
 * access a valid value. Writers are synchronized by @syslog_lock.
 */
static struct latched_seq clear_seq = {
	.latch		= SEQCNT_LATCH_ZERO(clear_seq.latch),
	.val[0]		= 0,
	.val[1]		= 0,
};

#ifdef CONFIG_PRINTK_CALLER
#define PREFIX_MAX		48
#else
#define PREFIX_MAX		32
#endif

/* the maximum size of a formatted record (i.e. with prefix added per line) */
#define CONSOLE_LOG_MAX		1024

/* the maximum size for a dropped text message */
#define DROPPED_TEXT_MAX	64

/* the maximum size allowed to be reserved for a record */
#define LOG_LINE_MAX		(CONSOLE_LOG_MAX - PREFIX_MAX)

#define LOG_LEVEL(v)		((v) & 0x07)
#define LOG_FACILITY(v)		((v) >> 3 & 0xff)

/* record buffer */
#define LOG_ALIGN __alignof__(unsigned long)
#define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT)
#define LOG_BUF_LEN_MAX (u32)(1 << 31)
static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN);
static char *log_buf = __log_buf;
static u32 log_buf_len = __LOG_BUF_LEN;

/*
 * Define the average message size. This only affects the number of
 * descriptors that will be available. Underestimating is better than
 * overestimating (too many available descriptors is better than not enough).
 */
#define PRB_AVGBITS 5	/* 32 character average length */

#if CONFIG_LOG_BUF_SHIFT <= PRB_AVGBITS
#error CONFIG_LOG_BUF_SHIFT value too small.
#endif
_DEFINE_PRINTKRB(printk_rb_static, CONFIG_LOG_BUF_SHIFT - PRB_AVGBITS,
		 PRB_AVGBITS, &__log_buf[0]);

static struct printk_ringbuffer printk_rb_dynamic;

static struct printk_ringbuffer *prb = &printk_rb_static;

/*
 * We cannot access per-CPU data (e.g. per-CPU flush irq_work) before
 * per_cpu_areas are initialised. This variable is set to true when
 * it's safe to access per-CPU data.
 */
static bool __printk_percpu_data_ready __read_mostly;

bool printk_percpu_data_ready(void)
{
	return __printk_percpu_data_ready;
}

/* Must be called under syslog_lock. */
static void latched_seq_write(struct latched_seq *ls, u64 val)
{
	raw_write_seqcount_latch(&ls->latch);
	ls->val[0] = val;
	raw_write_seqcount_latch(&ls->latch);
	ls->val[1] = val;
}

/* Can be called from any context. */
static u64 latched_seq_read_nolock(struct latched_seq *ls)
{
	unsigned int seq;
	unsigned int idx;
	u64 val;

	do {
		seq = raw_read_seqcount_latch(&ls->latch);
		idx = seq & 0x1;
		val = ls->val[idx];
	} while (read_seqcount_latch_retry(&ls->latch, seq));

	return val;
}

/* Return log buffer address */
char *log_buf_addr_get(void)
{
	return log_buf;
}

/* Return log buffer size */
u32 log_buf_len_get(void)
{
	return log_buf_len;
}

/*
 * Define how much of the log buffer we could take at maximum. The value
 * must be greater than two. Note that only half of the buffer is available
 * when the index points to the middle.
 */
#define MAX_LOG_TAKE_PART 4
static const char trunc_msg[] = "<truncated>";

static void truncate_msg(u16 *text_len, u16 *trunc_msg_len)
{
	/*
	 * The message should not take the whole buffer. Otherwise, it might
	 * get removed too soon.
	 */
	u32 max_text_len = log_buf_len / MAX_LOG_TAKE_PART;

	if (*text_len > max_text_len)
		*text_len = max_text_len;

	/* enable the warning message (if there is room) */
	*trunc_msg_len = strlen(trunc_msg);
	if (*text_len >= *trunc_msg_len)
		*text_len -= *trunc_msg_len;
	else
		*trunc_msg_len = 0;
}

int dmesg_restrict = IS_ENABLED(CONFIG_SECURITY_DMESG_RESTRICT);

static int syslog_action_restricted(int type)
{
	if (dmesg_restrict)
		return 1;
	/*
	 * Unless restricted, we allow "read all" and "get buffer size"
	 * for everybody.
	 */
	return type != SYSLOG_ACTION_READ_ALL &&
	       type != SYSLOG_ACTION_SIZE_BUFFER;
}

static int check_syslog_permissions(int type, int source)
{
	/*
	 * If this is from /proc/kmsg and we've already opened it, then we've
	 * already done the capabilities checks at open time.
	 */
	if (source == SYSLOG_FROM_PROC && type != SYSLOG_ACTION_OPEN)
		goto ok;

	if (syslog_action_restricted(type)) {
		if (capable(CAP_SYSLOG))
			goto ok;
		/*
		 * For historical reasons, accept CAP_SYS_ADMIN too, with
		 * a warning.
		 */
		if (capable(CAP_SYS_ADMIN)) {
			pr_warn_once("%s (%d): Attempt to access syslog with "
				     "CAP_SYS_ADMIN but no CAP_SYSLOG "
				     "(deprecated).\n",
				 current->comm, task_pid_nr(current));
			goto ok;
		}
		return -EPERM;
	}
ok:
	return security_syslog(type);
}

static void append_char(char **pp, char *e, char c)
{
	if (*pp < e)
		*(*pp)++ = c;
}

static ssize_t info_print_ext_header(char *buf, size_t size,
				     struct printk_info *info)
{
	u64 ts_usec = info->ts_nsec;
	char caller[20];
#ifdef CONFIG_PRINTK_CALLER
	u32 id = info->caller_id;

	snprintf(caller, sizeof(caller), ",caller=%c%u",
		 id & 0x80000000 ? 'C' : 'T', id & ~0x80000000);
#else
	caller[0] = '\0';
#endif

	do_div(ts_usec, 1000);

	return scnprintf(buf, size, "%u,%llu,%llu,%c%s;",
			 (info->facility << 3) | info->level, info->seq,
			 ts_usec, info->flags & LOG_CONT ? 'c' : '-', caller);
}

static ssize_t msg_add_ext_text(char *buf, size_t size,
				const char *text, size_t text_len,
				unsigned char endc)
{
	char *p = buf, *e = buf + size;
	size_t i;

	/* escape non-printable characters */
	for (i = 0; i < text_len; i++) {
		unsigned char c = text[i];

		if (c < ' ' || c >= 127 || c == '\\')
			p += scnprintf(p, e - p, "\\x%02x", c);
		else
			append_char(&p, e, c);
	}
	append_char(&p, e, endc);

	return p - buf;
}

static ssize_t msg_add_dict_text(char *buf, size_t size,
				 const char *key, const char *val)
{
	size_t val_len = strlen(val);
	ssize_t len;

	if (!val_len)
		return 0;

	len = msg_add_ext_text(buf, size, "", 0, ' ');	/* dict prefix */
	len += msg_add_ext_text(buf + len, size - len, key, strlen(key), '=');
	len += msg_add_ext_text(buf + len, size - len, val, val_len, '\n');

	return len;
}

static ssize_t msg_print_ext_body(char *buf, size_t size,
				  char *text, size_t text_len,
				  struct dev_printk_info *dev_info)
{
	ssize_t len;

	len = msg_add_ext_text(buf, size, text, text_len, '\n');

	if (!dev_info)
		goto out;

	len += msg_add_dict_text(buf + len, size - len, "SUBSYSTEM",
				 dev_info->subsystem);
	len += msg_add_dict_text(buf + len, size - len, "DEVICE",
				 dev_info->device);
out:
	return len;
}

/* /dev/kmsg - userspace message inject/listen interface */
struct devkmsg_user {
	atomic64_t seq;
	struct ratelimit_state rs;
	struct mutex lock;
	char buf[CONSOLE_EXT_LOG_MAX];

	struct printk_info info;
	char text_buf[CONSOLE_EXT_LOG_MAX];
	struct printk_record record;
};

static __printf(3, 4) __cold
int devkmsg_emit(int facility, int level, const char *fmt, ...)
{
	va_list args;
	int r;

	va_start(args, fmt);
	r = vprintk_emit(facility, level, NULL, fmt, args);
	va_end(args);

	return r;
}

static ssize_t devkmsg_write(struct kiocb *iocb, struct iov_iter *from)
{
	char *buf, *line;
	int level = default_message_loglevel;
	int facility = 1;	/* LOG_USER */
	struct file *file = iocb->ki_filp;
	struct devkmsg_user *user = file->private_data;
	size_t len = iov_iter_count(from);
	ssize_t ret = len;

	if (!user || len > LOG_LINE_MAX)
		return -EINVAL;

	/* Ignore when user logging is disabled. */
	if (devkmsg_log & DEVKMSG_LOG_MASK_OFF)
		return len;

	/* Ratelimit when not explicitly enabled. */
	if (!(devkmsg_log & DEVKMSG_LOG_MASK_ON)) {
		if (!___ratelimit(&user->rs, current->comm))
			return ret;
	}

	buf = kmalloc(len+1, GFP_KERNEL);
	if (buf == NULL)
		return -ENOMEM;

	buf[len] = '\0';
	if (!copy_from_iter_full(buf, len, from)) {
		kfree(buf);
		return -EFAULT;
	}

	/*
	 * Extract and skip the syslog prefix <[0-9]*>. Coming from userspace
	 * the decimal value represents 32bit, the lower 3 bit are the log
	 * level, the rest are the log facility.
	 *
	 * If no prefix or no userspace facility is specified, we
	 * enforce LOG_USER, to be able to reliably distinguish
	 * kernel-generated messages from userspace-injected ones.
	 */
	line = buf;
	if (line[0] == '<') {
		char *endp = NULL;
		unsigned int u;

		u = simple_strtoul(line + 1, &endp, 10);
		if (endp && endp[0] == '>') {
			level = LOG_LEVEL(u);
			if (LOG_FACILITY(u) != 0)
				facility = LOG_FACILITY(u);
			endp++;
			line = endp;
		}
	}

	devkmsg_emit(facility, level, "%s", line);
	kfree(buf);
	return ret;
}

static ssize_t devkmsg_read(struct file *file, char __user *buf,
			    size_t count, loff_t *ppos)
{
	struct devkmsg_user *user = file->private_data;
	struct printk_record *r = &user->record;
	size_t len;
	ssize_t ret;

	if (!user)
		return -EBADF;

	ret = mutex_lock_interruptible(&user->lock);
	if (ret)
		return ret;

	if (!prb_read_valid(prb, atomic64_read(&user->seq), r)) {
		if (file->f_flags & O_NONBLOCK) {
			ret = -EAGAIN;
			goto out;
		}

		/*
		 * Guarantee this task is visible on the waitqueue before
		 * checking the wake condition.
		 *
		 * The full memory barrier within set_current_state() of
		 * prepare_to_wait_event() pairs with the full memory barrier
		 * within wq_has_sleeper().
		 *
		 * This pairs with __wake_up_klogd:A.
		 */
		ret = wait_event_interruptible(log_wait,
				prb_read_valid(prb,
					atomic64_read(&user->seq), r)); /* LMM(devkmsg_read:A) */
		if (ret)
			goto out;
	}

	if (r->info->seq != atomic64_read(&user->seq)) {
		/* our last seen message is gone, return error and reset */
		atomic64_set(&user->seq, r->info->seq);
		ret = -EPIPE;
		goto out;
	}

	len = info_print_ext_header(user->buf, sizeof(user->buf), r->info);
	len += msg_print_ext_body(user->buf + len, sizeof(user->buf) - len,
				  &r->text_buf[0], r->info->text_len,
				  &r->info->dev_info);

	atomic64_set(&user->seq, r->info->seq + 1);

	if (len > count) {
		ret = -EINVAL;
		goto out;
	}

	if (copy_to_user(buf, user->buf, len)) {
		ret = -EFAULT;
		goto out;
	}
	ret = len;
out:
	mutex_unlock(&user->lock);
	return ret;
}

/*
 * Be careful when modifying this function!!!
 *
 * Only few operations are supported because the device works only with the
 * entire variable length messages (records). Non-standard values are
 * returned in the other cases and has been this way for quite some time.
 * User space applications might depend on this behavior.
 */
static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence)
{
	struct devkmsg_user *user = file->private_data;
	loff_t ret = 0;

	if (!user)
		return -EBADF;
	if (offset)
		return -ESPIPE;

	switch (whence) {
	case SEEK_SET:
		/* the first record */
		atomic64_set(&user->seq, prb_first_valid_seq(prb));
		break;
	case SEEK_DATA:
		/*
		 * The first record after the last SYSLOG_ACTION_CLEAR,
		 * like issued by 'dmesg -c'. Reading /dev/kmsg itself
		 * changes no global state, and does not clear anything.
		 */
		atomic64_set(&user->seq, latched_seq_read_nolock(&clear_seq));
		break;
	case SEEK_END:
		/* after the last record */
		atomic64_set(&user->seq, prb_next_seq(prb));
		break;
	default:
		ret = -EINVAL;
	}
	return ret;
}

static __poll_t devkmsg_poll(struct file *file, poll_table *wait)
{
	struct devkmsg_user *user = file->private_data;
	struct printk_info info;
	__poll_t ret = 0;

	if (!user)
		return EPOLLERR|EPOLLNVAL;

	poll_wait(file, &log_wait, wait);

	if (prb_read_valid_info(prb, atomic64_read(&user->seq), &info, NULL)) {
		/* return error when data has vanished underneath us */
		if (info.seq != atomic64_read(&user->seq))
			ret = EPOLLIN|EPOLLRDNORM|EPOLLERR|EPOLLPRI;
		else
			ret = EPOLLIN|EPOLLRDNORM;
	}

	return ret;
}

static int devkmsg_open(struct inode *inode, struct file *file)
{
	struct devkmsg_user *user;
	int err;

	if (devkmsg_log & DEVKMSG_LOG_MASK_OFF)
		return -EPERM;

	/* write-only does not need any file context */
	if ((file->f_flags & O_ACCMODE) != O_WRONLY) {
		err = check_syslog_permissions(SYSLOG_ACTION_READ_ALL,
					       SYSLOG_FROM_READER);
		if (err)
			return err;
	}

	user = kvmalloc(sizeof(struct devkmsg_user), GFP_KERNEL);
	if (!user)
		return -ENOMEM;

	ratelimit_default_init(&user->rs);
	ratelimit_set_flags(&user->rs, RATELIMIT_MSG_ON_RELEASE);

	mutex_init(&user->lock);

	prb_rec_init_rd(&user->record, &user->info,
			&user->text_buf[0], sizeof(user->text_buf));

	atomic64_set(&user->seq, prb_first_valid_seq(prb));

	file->private_data = user;
	return 0;
}

static int devkmsg_release(struct inode *inode, struct file *file)
{
	struct devkmsg_user *user = file->private_data;

	if (!user)
		return 0;

	ratelimit_state_exit(&user->rs);

	mutex_destroy(&user->lock);
	kvfree(user);
	return 0;
}

const struct file_operations kmsg_fops = {
	.open = devkmsg_open,
	.read = devkmsg_read,
	.write_iter = devkmsg_write,
	.llseek = devkmsg_llseek,
	.poll = devkmsg_poll,
	.release = devkmsg_release,
};

#ifdef CONFIG_CRASH_CORE
/*
 * This appends the listed symbols to /proc/vmcore
 *
 * /proc/vmcore is used by various utilities, like crash and makedumpfile to
 * obtain access to symbols that are otherwise very difficult to locate.  These
 * symbols are specifically used so that utilities can access and extract the
 * dmesg log from a vmcore file after a crash.
 */
void log_buf_vmcoreinfo_setup(void)
{
	struct dev_printk_info *dev_info = NULL;

	VMCOREINFO_SYMBOL(prb);
	VMCOREINFO_SYMBOL(printk_rb_static);
	VMCOREINFO_SYMBOL(clear_seq);

	/*
	 * Export struct size and field offsets. User space tools can
	 * parse it and detect any changes to structure down the line.
	 */

	VMCOREINFO_STRUCT_SIZE(printk_ringbuffer);
	VMCOREINFO_OFFSET(printk_ringbuffer, desc_ring);
	VMCOREINFO_OFFSET(printk_ringbuffer, text_data_ring);
	VMCOREINFO_OFFSET(printk_ringbuffer, fail);

	VMCOREINFO_STRUCT_SIZE(prb_desc_ring);
	VMCOREINFO_OFFSET(prb_desc_ring, count_bits);
	VMCOREINFO_OFFSET(prb_desc_ring, descs);
	VMCOREINFO_OFFSET(prb_desc_ring, infos);
	VMCOREINFO_OFFSET(prb_desc_ring, head_id);
	VMCOREINFO_OFFSET(prb_desc_ring, tail_id);

	VMCOREINFO_STRUCT_SIZE(prb_desc);
	VMCOREINFO_OFFSET(prb_desc, state_var);
	VMCOREINFO_OFFSET(prb_desc, text_blk_lpos);

	VMCOREINFO_STRUCT_SIZE(prb_data_blk_lpos);
	VMCOREINFO_OFFSET(prb_data_blk_lpos, begin);
	VMCOREINFO_OFFSET(prb_data_blk_lpos, next);

	VMCOREINFO_STRUCT_SIZE(printk_info);
	VMCOREINFO_OFFSET(printk_info, seq);
	VMCOREINFO_OFFSET(printk_info, ts_nsec);
	VMCOREINFO_OFFSET(printk_info, text_len);
	VMCOREINFO_OFFSET(printk_info, caller_id);
	VMCOREINFO_OFFSET(printk_info, dev_info);

	VMCOREINFO_STRUCT_SIZE(dev_printk_info);
	VMCOREINFO_OFFSET(dev_printk_info, subsystem);
	VMCOREINFO_LENGTH(printk_info_subsystem, sizeof(dev_info->subsystem));
	VMCOREINFO_OFFSET(dev_printk_info, device);
	VMCOREINFO_LENGTH(printk_info_device, sizeof(dev_info->device));

	VMCOREINFO_STRUCT_SIZE(prb_data_ring);
	VMCOREINFO_OFFSET(prb_data_ring, size_bits);
	VMCOREINFO_OFFSET(prb_data_ring, data);
	VMCOREINFO_OFFSET(prb_data_ring, head_lpos);
	VMCOREINFO_OFFSET(prb_data_ring, tail_lpos);

	VMCOREINFO_SIZE(atomic_long_t);
	VMCOREINFO_TYPE_OFFSET(atomic_long_t, counter);

	VMCOREINFO_STRUCT_SIZE(latched_seq);
	VMCOREINFO_OFFSET(latched_seq, val);
}
#endif

/* requested log_buf_len from kernel cmdline */
static unsigned long __initdata new_log_buf_len;

/* we practice scaling the ring buffer by powers of 2 */
static void __init log_buf_len_update(u64 size)
{
	if (size > (u64)LOG_BUF_LEN_MAX) {
		size = (u64)LOG_BUF_LEN_MAX;
		pr_err("log_buf over 2G is not supported.\n");
	}

	if (size)
		size = roundup_pow_of_two(size);
	if (size > log_buf_len)
		new_log_buf_len = (unsigned long)size;
}

/* save requested log_buf_len since it's too early to process it */
static int __init log_buf_len_setup(char *str)
{
	u64 size;

	if (!str)
		return -EINVAL;

	size = memparse(str, &str);

	log_buf_len_update(size);

	return 0;
}
early_param("log_buf_len", log_buf_len_setup);

#ifdef CONFIG_SMP
#define __LOG_CPU_MAX_BUF_LEN (1 << CONFIG_LOG_CPU_MAX_BUF_SHIFT)

static void __init log_buf_add_cpu(void)
{
	unsigned int cpu_extra;

	/*
	 * archs should set up cpu_possible_bits properly with
	 * set_cpu_possible() after setup_arch() but just in
	 * case lets ensure this is valid.
	 */
	if (num_possible_cpus() == 1)
		return;

	cpu_extra = (num_possible_cpus() - 1) * __LOG_CPU_MAX_BUF_LEN;

	/* by default this will only continue through for large > 64 CPUs */
	if (cpu_extra <= __LOG_BUF_LEN / 2)
		return;

	pr_info("log_buf_len individual max cpu contribution: %d bytes\n",
		__LOG_CPU_MAX_BUF_LEN);
	pr_info("log_buf_len total cpu_extra contributions: %d bytes\n",
		cpu_extra);
	pr_info("log_buf_len min size: %d bytes\n", __LOG_BUF_LEN);

	log_buf_len_update(cpu_extra + __LOG_BUF_LEN);
}
#else /* !CONFIG_SMP */
static inline void log_buf_add_cpu(void) {}
#endif /* CONFIG_SMP */

static void __init set_percpu_data_ready(void)
{
	__printk_percpu_data_ready = true;
}

static unsigned int __init add_to_rb(struct printk_ringbuffer *rb,
				     struct printk_record *r)
{
	struct prb_reserved_entry e;
	struct printk_record dest_r;

	prb_rec_init_wr(&dest_r, r->info->text_len);

	if (!prb_reserve(&e, rb, &dest_r))
		return 0;

	memcpy(&dest_r.text_buf[0], &r->text_buf[0], r->info->text_len);
	dest_r.info->text_len = r->info->text_len;
	dest_r.info->facility = r->info->facility;
	dest_r.info->level = r->info->level;
	dest_r.info->flags = r->info->flags;
	dest_r.info->ts_nsec = r->info->ts_nsec;
	dest_r.info->caller_id = r->info->caller_id;
	memcpy(&dest_r.info->dev_info, &r->info->dev_info, sizeof(dest_r.info->dev_info));

	prb_final_commit(&e);

	return prb_record_text_space(&e);
}

static char setup_text_buf[LOG_LINE_MAX] __initdata;

void __init setup_log_buf(int early)
{
	struct printk_info *new_infos;
	unsigned int new_descs_count;
	struct prb_desc *new_descs;
	struct printk_info info;
	struct printk_record r;
	unsigned int text_size;
	size_t new_descs_size;
	size_t new_infos_size;
	unsigned long flags;
	char *new_log_buf;
	unsigned int free;
	u64 seq;

	/*
	 * Some archs call setup_log_buf() multiple times - first is very
	 * early, e.g. from setup_arch(), and second - when percpu_areas
	 * are initialised.
	 */
	if (!early)
		set_percpu_data_ready();

	if (log_buf != __log_buf)
		return;

	if (!early && !new_log_buf_len)
		log_buf_add_cpu();

	if (!new_log_buf_len)
		return;

	new_descs_count = new_log_buf_len >> PRB_AVGBITS;
	if (new_descs_count == 0) {
		pr_err("new_log_buf_len: %lu too small\n", new_log_buf_len);
		return;
	}

	new_log_buf = memblock_alloc(new_log_buf_len, LOG_ALIGN);
	if (unlikely(!new_log_buf)) {
		pr_err("log_buf_len: %lu text bytes not available\n",
		       new_log_buf_len);
		return;
	}

	new_descs_size = new_descs_count * sizeof(struct prb_desc);
	new_descs = memblock_alloc(new_descs_size, LOG_ALIGN);
	if (unlikely(!new_descs)) {
		pr_err("log_buf_len: %zu desc bytes not available\n",
		       new_descs_size);
		goto err_free_log_buf;
	}

	new_infos_size = new_descs_count * sizeof(struct printk_info);
	new_infos = memblock_alloc(new_infos_size, LOG_ALIGN);
	if (unlikely(!new_infos)) {
		pr_err("log_buf_len: %zu info bytes not available\n",
		       new_infos_size);
		goto err_free_descs;
	}

	prb_rec_init_rd(&r, &info, &setup_text_buf[0], sizeof(setup_text_buf));

	prb_init(&printk_rb_dynamic,
		 new_log_buf, ilog2(new_log_buf_len),
		 new_descs, ilog2(new_descs_count),
		 new_infos);

	local_irq_save(flags);

	log_buf_len = new_log_buf_len;
	log_buf = new_log_buf;
	new_log_buf_len = 0;

	free = __LOG_BUF_LEN;
	prb_for_each_record(0, &printk_rb_static, seq, &r) {
		text_size = add_to_rb(&printk_rb_dynamic, &r);
		if (text_size > free)
			free = 0;
		else
			free -= text_size;
	}

	prb = &printk_rb_dynamic;

	local_irq_restore(flags);

	/*
	 * Copy any remaining messages that might have appeared from
	 * NMI context after copying but before switching to the
	 * dynamic buffer.
	 */
	prb_for_each_record(seq, &printk_rb_static, seq, &r) {
		text_size = add_to_rb(&printk_rb_dynamic, &r);
		if (text_size > free)
			free = 0;
		else
			free -= text_size;
	}

	if (seq != prb_next_seq(&printk_rb_static)) {
		pr_err("dropped %llu messages\n",
		       prb_next_seq(&printk_rb_static) - seq);
	}

	pr_info("log_buf_len: %u bytes\n", log_buf_len);
	pr_info("early log buf free: %u(%u%%)\n",
		free, (free * 100) / __LOG_BUF_LEN);
	return;

err_free_descs:
	memblock_free(new_descs, new_descs_size);
err_free_log_buf:
	memblock_free(new_log_buf, new_log_buf_len);
}

static bool __read_mostly ignore_loglevel;

static int __init ignore_loglevel_setup(char *str)
{
	ignore_loglevel = true;
	pr_info("debug: ignoring loglevel setting.\n");

	return 0;
}

early_param("ignore_loglevel", ignore_loglevel_setup);
module_param(ignore_loglevel, bool, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(ignore_loglevel,
		 "ignore loglevel setting (prints all kernel messages to the console)");

static bool suppress_message_printing(int level)
{
	return (level >= console_loglevel && !ignore_loglevel);
}

#ifdef CONFIG_BOOT_PRINTK_DELAY

static int boot_delay; /* msecs delay after each printk during bootup */
static unsigned long long loops_per_msec;	/* based on boot_delay */

static int __init boot_delay_setup(char *str)
{
	unsigned long lpj;

	lpj = preset_lpj ? preset_lpj : 1000000;	/* some guess */
	loops_per_msec = (unsigned long long)lpj / 1000 * HZ;

	get_option(&str, &boot_delay);
	if (boot_delay > 10 * 1000)
		boot_delay = 0;

	pr_debug("boot_delay: %u, preset_lpj: %ld, lpj: %lu, "
		"HZ: %d, loops_per_msec: %llu\n",
		boot_delay, preset_lpj, lpj, HZ, loops_per_msec);
	return 0;
}
early_param("boot_delay", boot_delay_setup);

static void boot_delay_msec(int level)
{
	unsigned long long k;
	unsigned long timeout;

	if ((boot_delay == 0 || system_state >= SYSTEM_RUNNING)
		|| suppress_message_printing(level)) {
		return;
	}

	k = (unsigned long long)loops_per_msec * boot_delay;

	timeout = jiffies + msecs_to_jiffies(boot_delay);
	while (k) {
		k--;
		cpu_relax();
		/*
		 * use (volatile) jiffies to prevent
		 * compiler reduction; loop termination via jiffies
		 * is secondary and may or may not happen.
		 */
		if (time_after(jiffies, timeout))
			break;
		touch_nmi_watchdog();
	}
}
#else
static inline void boot_delay_msec(int level)
{
}
#endif

static bool printk_time = IS_ENABLED(CONFIG_PRINTK_TIME);
module_param_named(time, printk_time, bool, S_IRUGO | S_IWUSR);

static size_t print_syslog(unsigned int level, char *buf)
{
	return sprintf(buf, "<%u>", level);
}

static size_t print_time(u64 ts, char *buf)
{
	unsigned long rem_nsec = do_div(ts, 1000000000);

	return sprintf(buf, "[%5lu.%06lu]",
		       (unsigned long)ts, rem_nsec / 1000);
}

#ifdef CONFIG_PRINTK_CALLER
static size_t print_caller(u32 id, char *buf)
{
	char caller[12];

	snprintf(caller, sizeof(caller), "%c%u",
		 id & 0x80000000 ? 'C' : 'T', id & ~0x80000000);
	return sprintf(buf, "[%6s]", caller);
}
#else
#define print_caller(id, buf) 0
#endif

static size_t info_print_prefix(const struct printk_info  *info, bool syslog,
				bool time, char *buf)
{
	size_t len = 0;

	if (syslog)
		len = print_syslog((info->facility << 3) | info->level, buf);

	if (time)
		len += print_time(info->ts_nsec, buf + len);

	len += print_caller(info->caller_id, buf + len);

	if (IS_ENABLED(CONFIG_PRINTK_CALLER) || time) {
		buf[len++] = ' ';
		buf[len] = '\0';
	}

	return len;
}

/*
 * Prepare the record for printing. The text is shifted within the given
 * buffer to avoid a need for another one. The following operations are
 * done:
 *
 *   - Add prefix for each line.
 *   - Drop truncated lines that no longer fit into the buffer.
 *   - Add the trailing newline that has been removed in vprintk_store().
 *   - Add a string terminator.
 *
 * Since the produced string is always terminated, the maximum possible
 * return value is @r->text_buf_size - 1;
 *
 * Return: The length of the updated/prepared text, including the added
 * prefixes and the newline. The terminator is not counted. The dropped
 * line(s) are not counted.
 */
static size_t record_print_text(struct printk_record *r, bool syslog,
				bool time)
{
	size_t text_len = r->info->text_len;
	size_t buf_size = r->text_buf_size;
	char *text = r->text_buf;
	char prefix[PREFIX_MAX];
	bool truncated = false;
	size_t prefix_len;
	size_t line_len;
	size_t len = 0;
	char *next;

	/*
	 * If the message was truncated because the buffer was not large
	 * enough, treat the available text as if it were the full text.
	 */
	if (text_len > buf_size)
		text_len = buf_size;

	prefix_len = info_print_prefix(r->info, syslog, time, prefix);

	/*
	 * @text_len: bytes of unprocessed text
	 * @line_len: bytes of current line _without_ newline
	 * @text:     pointer to beginning of current line
	 * @len:      number of bytes prepared in r->text_buf
	 */
	for (;;) {
		next = memchr(text, '\n', text_len);
		if (next) {
			line_len = next - text;
		} else {
			/* Drop truncated line(s). */
			if (truncated)
				break;
			line_len = text_len;
		}

		/*
		 * Truncate the text if there is not enough space to add the
		 * prefix and a trailing newline and a terminator.
		 */
		if (len + prefix_len + text_len + 1 + 1 > buf_size) {
			/* Drop even the current line if no space. */
			if (len + prefix_len + line_len + 1 + 1 > buf_size)
				break;

			text_len = buf_size - len - prefix_len - 1 - 1;
			truncated = true;
		}

		memmove(text + prefix_len, text, text_len);
		memcpy(text, prefix, prefix_len);

		/*
		 * Increment the prepared length to include the text and
		 * prefix that were just moved+copied. Also increment for the
		 * newline at the end of this line. If this is the last line,
		 * there is no newline, but it will be added immediately below.
		 */
		len += prefix_len + line_len + 1;
		if (text_len == line_len) {
			/*
			 * This is the last line. Add the trailing newline
			 * removed in vprintk_store().
			 */
			text[prefix_len + line_len] = '\n';
			break;
		}

		/*
		 * Advance beyond the added prefix and the related line with
		 * its newline.
		 */
		text += prefix_len + line_len + 1;

		/*
		 * The remaining text has only decreased by the line with its
		 * newline.
		 *
		 * Note that @text_len can become zero. It happens when @text
		 * ended with a newline (either due to truncation or the
		 * original string ending with "\n\n"). The loop is correctly
		 * repeated and (if not truncated) an empty line with a prefix
		 * will be prepared.
		 */
		text_len -= line_len + 1;
	}

	/*
	 * If a buffer was provided, it will be terminated. Space for the
	 * string terminator is guaranteed to be available. The terminator is
	 * not counted in the return value.
	 */
	if (buf_size > 0)
		r->text_buf[len] = 0;

	return len;
}

static size_t get_record_print_text_size(struct printk_info *info,
					 unsigned int line_count,
					 bool syslog, bool time)
{
	char prefix[PREFIX_MAX];
	size_t prefix_len;

	prefix_len = info_print_prefix(info, syslog, time, prefix);

	/*
	 * Each line will be preceded with a prefix. The intermediate
	 * newlines are already within the text, but a final trailing
	 * newline will be added.
	 */
	return ((prefix_len * line_count) + info->text_len + 1);
}

/*
 * Beginning with @start_seq, find the first record where it and all following
 * records up to (but not including) @max_seq fit into @size.
 *
 * @max_seq is simply an upper bound and does not need to exist. If the caller
 * does not require an upper bound, -1 can be used for @max_seq.
 */
static u64 find_first_fitting_seq(u64 start_seq, u64 max_seq, size_t size,
				  bool syslog, bool time)
{
	struct printk_info info;
	unsigned int line_count;
	size_t len = 0;
	u64 seq;

	/* Determine the size of the records up to @max_seq. */
	prb_for_each_info(start_seq, prb, seq, &info, &line_count) {
		if (info.seq >= max_seq)
			break;
		len += get_record_print_text_size(&info, line_count, syslog, time);
	}

	/*
	 * Adjust the upper bound for the next loop to avoid subtracting
	 * lengths that were never added.
	 */
	if (seq < max_seq)
		max_seq = seq;

	/*
	 * Move first record forward until length fits into the buffer. Ignore
	 * newest messages that were not counted in the above cycle. Messages
	 * might appear and get lost in the meantime. This is a best effort
	 * that prevents an infinite loop that could occur with a retry.
	 */
	prb_for_each_info(start_seq, prb, seq, &info, &line_count) {
		if (len <= size || info.seq >= max_seq)
			break;
		len -= get_record_print_text_size(&info, line_count, syslog, time);
	}

	return seq;
}

/* The caller is responsible for making sure @size is greater than 0. */
static int syslog_print(char __user *buf, int size)
{
	struct printk_info info;
	struct printk_record r;
	char *text;
	int len = 0;
	u64 seq;

	text = kmalloc(CONSOLE_LOG_MAX, GFP_KERNEL);
	if (!text)
		return -ENOMEM;

	prb_rec_init_rd(&r, &info, text, CONSOLE_LOG_MAX);

	mutex_lock(&syslog_lock);

	/*
	 * Wait for the @syslog_seq record to be available. @syslog_seq may
	 * change while waiting.
	 */
	do {
		seq = syslog_seq;

		mutex_unlock(&syslog_lock);
		/*
		 * Guarantee this task is visible on the waitqueue before
		 * checking the wake condition.
		 *
		 * The full memory barrier within set_current_state() of
		 * prepare_to_wait_event() pairs with the full memory barrier
		 * within wq_has_sleeper().
		 *
		 * This pairs with __wake_up_klogd:A.
		 */
		len = wait_event_interruptible(log_wait,
				prb_read_valid(prb, seq, NULL)); /* LMM(syslog_print:A) */
		mutex_lock(&syslog_lock);

		if (len)
			goto out;
	} while (syslog_seq != seq);

	/*
	 * Copy records that fit into the buffer. The above cycle makes sure
	 * that the first record is always available.
	 */
	do {
		size_t n;
		size_t skip;
		int err;

		if (!prb_read_valid(prb, syslog_seq, &r))
			break;

		if (r.info->seq != syslog_seq) {
			/* message is gone, move to next valid one */
			syslog_seq = r.info->seq;
			syslog_partial = 0;
		}

		/*
		 * To keep reading/counting partial line consistent,
		 * use printk_time value as of the beginning of a line.
		 */
		if (!syslog_partial)
			syslog_time = printk_time;

		skip = syslog_partial;
		n = record_print_text(&r, true, syslog_time);
		if (n - syslog_partial <= size) {
			/* message fits into buffer, move forward */
			syslog_seq = r.info->seq + 1;
			n -= syslog_partial;
			syslog_partial = 0;
		} else if (!len){
			/* partial read(), remember position */
			n = size;
			syslog_partial += n;
		} else
			n = 0;

		if (!n)
			break;

		mutex_unlock(&syslog_lock);
		err = copy_to_user(buf, text + skip, n);
		mutex_lock(&syslog_lock);

		if (err) {
			if (!len)
				len = -EFAULT;
			break;
		}

		len += n;
		size -= n;
		buf += n;
	} while (size);
out:
	mutex_unlock(&syslog_lock);
	kfree(text);
	return len;
}

static int syslog_print_all(char __user *buf, int size, bool clear)
{
	struct printk_info info;
	struct printk_record r;
	char *text;
	int len = 0;
	u64 seq;
	bool time;

	text = kmalloc(CONSOLE_LOG_MAX, GFP_KERNEL);
	if (!text)
		return -ENOMEM;

	time = printk_time;
	/*
	 * Find first record that fits, including all following records,
	 * into the user-provided buffer for this dump.
	 */
	seq = find_first_fitting_seq(latched_seq_read_nolock(&clear_seq), -1,
				     size, true, time);

	prb_rec_init_rd(&r, &info, text, CONSOLE_LOG_MAX);

	len = 0;
	prb_for_each_record(seq, prb, seq, &r) {
		int textlen;

		textlen = record_print_text(&r, true, time);

		if (len + textlen > size) {
			seq--;
			break;
		}

		if (copy_to_user(buf + len, text, textlen))
			len = -EFAULT;
		else
			len += textlen;

		if (len < 0)
			break;
	}

	if (clear) {
		mutex_lock(&syslog_lock);
		latched_seq_write(&clear_seq, seq);
		mutex_unlock(&syslog_lock);
	}

	kfree(text);
	return len;
}

static void syslog_clear(void)
{
	mutex_lock(&syslog_lock);
	latched_seq_write(&clear_seq, prb_next_seq(prb));
	mutex_unlock(&syslog_lock);
}

int do_syslog(int type, char __user *buf, int len, int source)
{
	struct printk_info info;
	bool clear = false;
	static int saved_console_loglevel = LOGLEVEL_DEFAULT;
	int error;

	error = check_syslog_permissions(type, source);
	if (error)
		return error;

	switch (type) {
	case SYSLOG_ACTION_CLOSE:	/* Close log */
		break;
	case SYSLOG_ACTION_OPEN:	/* Open log */
		break;
	case SYSLOG_ACTION_READ:	/* Read from log */
		if (!buf || len < 0)
			return -EINVAL;
		if (!len)
			return 0;
		if (!access_ok(buf, len))
			return -EFAULT;
		error = syslog_print(buf, len);
		break;
	/* Read/clear last kernel messages */
	case SYSLOG_ACTION_READ_CLEAR:
		clear = true;
		fallthrough;
	/* Read last kernel messages */
	case SYSLOG_ACTION_READ_ALL:
		if (!buf || len < 0)
			return -EINVAL;
		if (!len)
			return 0;
		if (!access_ok(buf, len))
			return -EFAULT;
		error = syslog_print_all(buf, len, clear);
		break;
	/* Clear ring buffer */
	case SYSLOG_ACTION_CLEAR:
		syslog_clear();
		break;
	/* Disable logging to console */
	case SYSLOG_ACTION_CONSOLE_OFF:
		if (saved_console_loglevel == LOGLEVEL_DEFAULT)
			saved_console_loglevel = console_loglevel;
		console_loglevel = minimum_console_loglevel;
		break;
	/* Enable logging to console */
	case SYSLOG_ACTION_CONSOLE_ON:
		if (saved_console_loglevel != LOGLEVEL_DEFAULT) {
			console_loglevel = saved_console_loglevel;
			saved_console_loglevel = LOGLEVEL_DEFAULT;
		}
		break;
	/* Set level of messages printed to console */
	case SYSLOG_ACTION_CONSOLE_LEVEL:
		if (len < 1 || len > 8)
			return -EINVAL;
		if (len < minimum_console_loglevel)
			len = minimum_console_loglevel;
		console_loglevel = len;
		/* Implicitly re-enable logging to console */
		saved_console_loglevel = LOGLEVEL_DEFAULT;
		break;
	/* Number of chars in the log buffer */
	case SYSLOG_ACTION_SIZE_UNREAD:
		mutex_lock(&syslog_lock);
		if (!prb_read_valid_info(prb, syslog_seq, &info, NULL)) {
			/* No unread messages. */
			mutex_unlock(&syslog_lock);
			return 0;
		}
		if (info.seq != syslog_seq) {
			/* messages are gone, move to first one */
			syslog_seq = info.seq;
			syslog_partial = 0;
		}
		if (source == SYSLOG_FROM_PROC) {
			/*
			 * Short-cut for poll(/"proc/kmsg") which simply checks
			 * for pending data, not the size; return the count of
			 * records, not the length.
			 */
			error = prb_next_seq(prb) - syslog_seq;
		} else {
			bool time = syslog_partial ? syslog_time : printk_time;
			unsigned int line_count;
			u64 seq;

			prb_for_each_info(syslog_seq, prb, seq, &info,
					  &line_count) {
				error += get_record_print_text_size(&info, line_count,
								    true, time);
				time = printk_time;
			}
			error -= syslog_partial;
		}
		mutex_unlock(&syslog_lock);
		break;
	/* Size of the log buffer */
	case SYSLOG_ACTION_SIZE_BUFFER:
		error = log_buf_len;
		break;
	default:
		error = -EINVAL;
		break;
	}

	return error;
}

SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len)
{
	return do_syslog(type, buf, len, SYSLOG_FROM_READER);
}

/*
 * Special console_lock variants that help to reduce the risk of soft-lockups.
 * They allow to pass console_lock to another printk() call using a busy wait.
 */

#ifdef CONFIG_LOCKDEP
static struct lockdep_map console_owner_dep_map = {
	.name = "console_owner"
};
#endif

static DEFINE_RAW_SPINLOCK(console_owner_lock);
static struct task_struct *console_owner;
static bool console_waiter;

/**
 * console_lock_spinning_enable - mark beginning of code where another
 *	thread might safely busy wait
 *
 * This basically converts console_lock into a spinlock. This marks
 * the section where the console_lock owner can not sleep, because
 * there may be a waiter spinning (like a spinlock). Also it must be
 * ready to hand over the lock at the end of the section.
 */
static void console_lock_spinning_enable(void)
{
	raw_spin_lock(&console_owner_lock);
	console_owner = current;
	raw_spin_unlock(&console_owner_lock);

	/* The waiter may spin on us after setting console_owner */
	spin_acquire(&console_owner_dep_map, 0, 0, _THIS_IP_);
}

/**
 * console_lock_spinning_disable_and_check - mark end of code where another
 *	thread was able to busy wait and check if there is a waiter
 *
 * This is called at the end of the section where spinning is allowed.
 * It has two functions. First, it is a signal that it is no longer
 * safe to start busy waiting for the lock. Second, it checks if
 * there is a busy waiter and passes the lock rights to her.
 *
 * Important: Callers lose the lock if there was a busy waiter.
 *	They must not touch items synchronized by console_lock
 *	in this case.
 *
 * Return: 1 if the lock rights were passed, 0 otherwise.
 */
static int console_lock_spinning_disable_and_check(void)
{
	int waiter;

	raw_spin_lock(&console_owner_lock);
	waiter = READ_ONCE(console_waiter);
	console_owner = NULL;
	raw_spin_unlock(&console_owner_lock);

	if (!waiter) {
		spin_release(&console_owner_dep_map, _THIS_IP_);
		return 0;
	}

	/* The waiter is now free to continue */
	WRITE_ONCE(console_waiter, false);

	spin_release(&console_owner_dep_map, _THIS_IP_);

	/*
	 * Hand off console_lock to waiter. The waiter will perform
	 * the up(). After this, the waiter is the console_lock owner.
	 */
	mutex_release(&console_lock_dep_map, _THIS_IP_);
	return 1;
}

/**
 * console_trylock_spinning - try to get console_lock by busy waiting
 *
 * This allows to busy wait for the console_lock when the current
 * owner is running in specially marked sections. It means that
 * the current owner is running and cannot reschedule until it
 * is ready to lose the lock.
 *
 * Return: 1 if we got the lock, 0 othrewise
 */
static int console_trylock_spinning(void)
{
	struct task_struct *owner = NULL;
	bool waiter;
	bool spin = false;
	unsigned long flags;

	if (console_trylock())
		return 1;

	/*
	 * It's unsafe to spin once a panic has begun. If we are the
	 * panic CPU, we may have already halted the owner of the
	 * console_sem. If we are not the panic CPU, then we should
	 * avoid taking console_sem, so the panic CPU has a better
	 * chance of cleanly acquiring it later.
	 */
	if (panic_in_progress())
		return 0;

	printk_safe_enter_irqsave(flags);

	raw_spin_lock(&console_owner_lock);
	owner = READ_ONCE(console_owner);
	waiter = READ_ONCE(console_waiter);
	if (!waiter && owner && owner != current) {
		WRITE_ONCE(console_waiter, true);
		spin = true;
	}
	raw_spin_unlock(&console_owner_lock);

	/*
	 * If there is an active printk() writing to the
	 * consoles, instead of having it write our data too,
	 * see if we can offload that load from the active
	 * printer, and do some printing ourselves.
	 * Go into a spin only if there isn't already a waiter
	 * spinning, and there is an active printer, and
	 * that active printer isn't us (recursive printk?).
	 */
	if (!spin) {
		printk_safe_exit_irqrestore(flags);
		return 0;
	}

	/* We spin waiting for the owner to release us */
	spin_acquire(&console_owner_dep_map, 0, 0, _THIS_IP_);
	/* Owner will clear console_waiter on hand off */
	while (READ_ONCE(console_waiter))
		cpu_relax();
	spin_release(&console_owner_dep_map, _THIS_IP_);

	printk_safe_exit_irqrestore(flags);
	/*
	 * The owner passed the console lock to us.
	 * Since we did not spin on console lock, annotate
	 * this as a trylock. Otherwise lockdep will
	 * complain.
	 */
	mutex_acquire(&console_lock_dep_map, 0, 1, _THIS_IP_);

	return 1;
}

/*
 * Call the specified console driver, asking it to write out the specified
 * text and length. If @dropped_text is non-NULL and any records have been
 * dropped, a dropped message will be written out first.
 */
static void call_console_driver(struct console *con, const char *text, size_t len,
				char *dropped_text)
{
	size_t dropped_len;

	if (con->dropped && dropped_text) {
		dropped_len = snprintf(dropped_text, DROPPED_TEXT_MAX,
				       "** %lu printk messages dropped **\n",
				       con->dropped);
		con->dropped = 0;
		con->write(con, dropped_text, dropped_len);
	}

	con->write(con, text, len);
}

/*
 * Recursion is tracked separately on each CPU. If NMIs are supported, an
 * additional NMI context per CPU is also separately tracked. Until per-CPU
 * is available, a separate "early tracking" is performed.
 */
static DEFINE_PER_CPU(u8, printk_count);
static u8 printk_count_early;
#ifdef CONFIG_HAVE_NMI
static DEFINE_PER_CPU(u8, printk_count_nmi);
static u8 printk_count_nmi_early;
#endif

/*
 * Recursion is limited to keep the output sane. printk() should not require
 * more than 1 level of recursion (allowing, for example, printk() to trigger
 * a WARN), but a higher value is used in case some printk-internal errors
 * exist, such as the ringbuffer validation checks failing.
 */
#define PRINTK_MAX_RECURSION 3

/*
 * Return a pointer to the dedicated counter for the CPU+context of the
 * caller.
 */
static u8 *__printk_recursion_counter(void)
{
#ifdef CONFIG_HAVE_NMI
	if (in_nmi()) {
		if (printk_percpu_data_ready())
			return this_cpu_ptr(&printk_count_nmi);
		return &printk_count_nmi_early;
	}
#endif
	if (printk_percpu_data_ready())
		return this_cpu_ptr(&printk_count);
	return &printk_count_early;
}

/*
 * Enter recursion tracking. Interrupts are disabled to simplify tracking.
 * The caller must check the boolean return value to see if the recursion is
 * allowed. On failure, interrupts are not disabled.
 *
 * @recursion_ptr must be a variable of type (u8 *) and is the same variable
 * that is passed to printk_exit_irqrestore().
 */
#define printk_enter_irqsave(recursion_ptr, flags)	\
({							\
	bool success = true;				\
							\
	typecheck(u8 *, recursion_ptr);			\
	local_irq_save(flags);				\
	(recursion_ptr) = __printk_recursion_counter();	\
	if (*(recursion_ptr) > PRINTK_MAX_RECURSION) {	\
		local_irq_restore(flags);		\
		success = false;			\
	} else {					\
		(*(recursion_ptr))++;			\
	}						\
	success;					\
})

/* Exit recursion tracking, restoring interrupts. */
#define printk_exit_irqrestore(recursion_ptr, flags)	\
	do {						\
		typecheck(u8 *, recursion_ptr);		\
		(*(recursion_ptr))--;			\
		local_irq_restore(flags);		\
	} while (0)

int printk_delay_msec __read_mostly;

static inline void printk_delay(int level)
{
	boot_delay_msec(level);

	if (unlikely(printk_delay_msec)) {
		int m = printk_delay_msec;

		while (m--) {
			mdelay(1);
			touch_nmi_watchdog();
		}
	}
}

static inline u32 printk_caller_id(void)
{
	return in_task() ? task_pid_nr(current) :
		0x80000000 + smp_processor_id();
}

/**
 * printk_parse_prefix - Parse level and control flags.
 *
 * @text:     The terminated text message.
 * @level:    A pointer to the current level value, will be updated.
 * @flags:    A pointer to the current printk_info flags, will be updated.
 *
 * @level may be NULL if the caller is not interested in the parsed value.
 * Otherwise the variable pointed to by @level must be set to
 * LOGLEVEL_DEFAULT in order to be updated with the parsed value.
 *
 * @flags may be NULL if the caller is not interested in the parsed value.
 * Otherwise the variable pointed to by @flags will be OR'd with the parsed
 * value.
 *
 * Return: The length of the parsed level and control flags.
 */
u16 printk_parse_prefix(const char *text, int *level,
			enum printk_info_flags *flags)
{
	u16 prefix_len = 0;
	int kern_level;

	while (*text) {
		kern_level = printk_get_level(text);
		if (!kern_level)
			break;

		switch (kern_level) {
		case '0' ... '7':
			if (level && *level == LOGLEVEL_DEFAULT)
				*level = kern_level - '0';
			break;
		case 'c':	/* KERN_CONT */
			if (flags)
				*flags |= LOG_CONT;
		}

		prefix_len += 2;
		text += 2;
	}

	return prefix_len;
}

__printf(5, 0)
static u16 printk_sprint(char *text, u16 size, int facility,
			 enum printk_info_flags *flags, const char *fmt,
			 va_list args)
{
	u16 text_len;

	text_len = vscnprintf(text, size, fmt, args);

	/* Mark and strip a trailing newline. */
	if (text_len && text[text_len - 1] == '\n') {
		text_len--;
		*flags |= LOG_NEWLINE;
	}

	/* Strip log level and control flags. */
	if (facility == 0) {
		u16 prefix_len;

		prefix_len = printk_parse_prefix(text, NULL, NULL);
		if (prefix_len) {
			text_len -= prefix_len;
			memmove(text, text + prefix_len, text_len);
		}
	}

	trace_console_rcuidle(text, text_len);

	return text_len;
}

__printf(4, 0)
int vprintk_store(int facility, int level,
		  const struct dev_printk_info *dev_info,
		  const char *fmt, va_list args)
{
	struct prb_reserved_entry e;
	enum printk_info_flags flags = 0;
	struct printk_record r;
	unsigned long irqflags;
	u16 trunc_msg_len = 0;
	char prefix_buf[8];
	u8 *recursion_ptr;
	u16 reserve_size;
	va_list args2;
	u32 caller_id;
	u16 text_len;
	int ret = 0;
	u64 ts_nsec;

	if (!printk_enter_irqsave(recursion_ptr, irqflags))
		return 0;

	/*
	 * Since the duration of printk() can vary depending on the message
	 * and state of the ringbuffer, grab the timestamp now so that it is
	 * close to the call of printk(). This provides a more deterministic
	 * timestamp with respect to the caller.
	 */
	ts_nsec = local_clock();

	caller_id = printk_caller_id();

	/*
	 * The sprintf needs to come first since the syslog prefix might be
	 * passed in as a parameter. An extra byte must be reserved so that
	 * later the vscnprintf() into the reserved buffer has room for the
	 * terminating '\0', which is not counted by vsnprintf().
	 */
	va_copy(args2, args);
	reserve_size = vsnprintf(&prefix_buf[0], sizeof(prefix_buf), fmt, args2) + 1;
	va_end(args2);

	if (reserve_size > LOG_LINE_MAX)
		reserve_size = LOG_LINE_MAX;

	/* Extract log level or control flags. */
	if (facility == 0)
		printk_parse_prefix(&prefix_buf[0], &level, &flags);

	if (level == LOGLEVEL_DEFAULT)
		level = default_message_loglevel;

	if (dev_info)
		flags |= LOG_NEWLINE;

	if (flags & LOG_CONT) {
		prb_rec_init_wr(&r, reserve_size);
		if (prb_reserve_in_last(&e, prb, &r, caller_id, LOG_LINE_MAX)) {
			text_len = printk_sprint(&r.text_buf[r.info->text_len], reserve_size,
						 facility, &flags, fmt, args);
			r.info->text_len += text_len;

			if (flags & LOG_NEWLINE) {
				r.info->flags |= LOG_NEWLINE;
				prb_final_commit(&e);
			} else {
				prb_commit(&e);
			}

			ret = text_len;
			goto out;
		}
	}

	/*
	 * Explicitly initialize the record before every prb_reserve() call.
	 * prb_reserve_in_last() and prb_reserve() purposely invalidate the
	 * structure when they fail.
	 */
	prb_rec_init_wr(&r, reserve_size);
	if (!prb_reserve(&e, prb, &r)) {
		/* truncate the message if it is too long for empty buffer */
		truncate_msg(&reserve_size, &trunc_msg_len);

		prb_rec_init_wr(&r, reserve_size + trunc_msg_len);
		if (!prb_reserve(&e, prb, &r))
			goto out;
	}

	/* fill message */
	text_len = printk_sprint(&r.text_buf[0], reserve_size, facility, &flags, fmt, args);
	if (trunc_msg_len)
		memcpy(&r.text_buf[text_len], trunc_msg, trunc_msg_len);
	r.info->text_len = text_len + trunc_msg_len;
	r.info->facility = facility;
	r.info->level = level & 7;
	r.info->flags = flags & 0x1f;
	r.info->ts_nsec = ts_nsec;
	r.info->caller_id = caller_id;
	if (dev_info)
		memcpy(&r.info->dev_info, dev_info, sizeof(r.info->dev_info));

	/* A message without a trailing newline can be continued. */
	if (!(flags & LOG_NEWLINE))
		prb_commit(&e);
	else
		prb_final_commit(&e);

	ret = text_len + trunc_msg_len;
out:
	printk_exit_irqrestore(recursion_ptr, irqflags);
	return ret;
}

asmlinkage int vprintk_emit(int facility, int level,
			    const struct dev_printk_info *dev_info,
			    const char *fmt, va_list args)
{
	int printed_len;
	bool in_sched = false;

	/* Suppress unimportant messages after panic happens */
	if (unlikely(suppress_printk))
		return 0;

	if (unlikely(suppress_panic_printk) &&
	    atomic_read(&panic_cpu) != raw_smp_processor_id())
		return 0;

	if (level == LOGLEVEL_SCHED) {
		level = LOGLEVEL_DEFAULT;
		in_sched = true;
	}

	printk_delay(level);

	printed_len = vprintk_store(facility, level, dev_info, fmt, args);

	/* If called from the scheduler, we can not call up(). */
	if (!in_sched) {
		/*
		 * The caller may be holding system-critical or
		 * timing-sensitive locks. Disable preemption during
		 * printing of all remaining records to all consoles so that
		 * this context can return as soon as possible. Hopefully
		 * another printk() caller will take over the printing.
		 */
		preempt_disable();
		/*
		 * Try to acquire and then immediately release the console
		 * semaphore. The release will print out buffers. With the
		 * spinning variant, this context tries to take over the
		 * printing from another printing context.
		 */
		if (console_trylock_spinning())
			console_unlock();
		preempt_enable();
	}

	wake_up_klogd();
	return printed_len;
}
EXPORT_SYMBOL(vprintk_emit);

int vprintk_default(const char *fmt, va_list args)
{
	return vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, fmt, args);
}
EXPORT_SYMBOL_GPL(vprintk_default);

asmlinkage __visible int _printk(const char *fmt, ...)
{
	va_list args;
	int r;

	va_start(args, fmt);
	r = vprintk(fmt, args);
	va_end(args);

	return r;
}
EXPORT_SYMBOL(_printk);

static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress);

#else /* CONFIG_PRINTK */

#define CONSOLE_LOG_MAX		0
#define DROPPED_TEXT_MAX	0
#define printk_time		false

#define prb_read_valid(rb, seq, r)	false
#define prb_first_valid_seq(rb)		0
#define prb_next_seq(rb)		0

static u64 syslog_seq;

static size_t record_print_text(const struct printk_record *r,
				bool syslog, bool time)
{
	return 0;
}
static ssize_t info_print_ext_header(char *buf, size_t size,
				     struct printk_info *info)
{
	return 0;
}
static ssize_t msg_print_ext_body(char *buf, size_t size,
				  char *text, size_t text_len,
				  struct dev_printk_info *dev_info) { return 0; }
static void console_lock_spinning_enable(void) { }
static int console_lock_spinning_disable_and_check(void) { return 0; }
static void call_console_driver(struct console *con, const char *text, size_t len,
				char *dropped_text)
{
}
static bool suppress_message_printing(int level) { return false; }
static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress) { return true; }

#endif /* CONFIG_PRINTK */

#ifdef CONFIG_EARLY_PRINTK
struct console *early_console;

asmlinkage __visible void early_printk(const char *fmt, ...)
{
	va_list ap;
	char buf[512];
	int n;

	if (!early_console)
		return;

	va_start(ap, fmt);
	n = vscnprintf(buf, sizeof(buf), fmt, ap);
	va_end(ap);

	early_console->write(early_console, buf, n);
}
#endif

static void set_user_specified(struct console_cmdline *c, bool user_specified)
{
	if (!user_specified)
		return;

	/*
	 * @c console was defined by the user on the command line.
	 * Do not clear when added twice also by SPCR or the device tree.
	 */
	c->user_specified = true;
	/* At least one console defined by the user on the command line. */
	console_set_on_cmdline = 1;
}

static int __add_preferred_console(char *name, int idx, char *options,
				   char *brl_options, bool user_specified)
{
	struct console_cmdline *c;
	int i;

	/*
	 *	See if this tty is not yet registered, and
	 *	if we have a slot free.
	 */
	for (i = 0, c = console_cmdline;
	     i < MAX_CMDLINECONSOLES && c->name[0];
	     i++, c++) {
		if (strcmp(c->name, name) == 0 && c->index == idx) {
			if (!brl_options)
				preferred_console = i;
			set_user_specified(c, user_specified);
			return 0;
		}
	}
	if (i == MAX_CMDLINECONSOLES)
		return -E2BIG;
	if (!brl_options)
		preferred_console = i;
	strlcpy(c->name, name, sizeof(c->name));
	c->options = options;
	set_user_specified(c, user_specified);
	braille_set_options(c, brl_options);

	c->index = idx;
	return 0;
}

static int __init console_msg_format_setup(char *str)
{
	if (!strcmp(str, "syslog"))
		console_msg_format = MSG_FORMAT_SYSLOG;
	if (!strcmp(str, "default"))
		console_msg_format = MSG_FORMAT_DEFAULT;
	return 1;
}
__setup("console_msg_format=", console_msg_format_setup);

/*
 * Set up a console.  Called via do_early_param() in init/main.c
 * for each "console=" parameter in the boot command line.
 */
static int __init console_setup(char *str)
{
	char buf[sizeof(console_cmdline[0].name) + 4]; /* 4 for "ttyS" */
	char *s, *options, *brl_options = NULL;
	int idx;

	/*
	 * console="" or console=null have been suggested as a way to
	 * disable console output. Use ttynull that has been created
	 * for exactly this purpose.
	 */
	if (str[0] == 0 || strcmp(str, "null") == 0) {
		__add_preferred_console("ttynull", 0, NULL, NULL, true);
		return 1;
	}

	if (_braille_console_setup(&str, &brl_options))
		return 1;

	/*
	 * Decode str into name, index, options.
	 */
	if (str[0] >= '0' && str[0] <= '9') {
		strcpy(buf, "ttyS");
		strncpy(buf + 4, str, sizeof(buf) - 5);
	} else {
		strncpy(buf, str, sizeof(buf) - 1);
	}
	buf[sizeof(buf) - 1] = 0;
	options = strchr(str, ',');
	if (options)
		*(options++) = 0;
#ifdef __sparc__
	if (!strcmp(str, "ttya"))
		strcpy(buf, "ttyS0");
	if (!strcmp(str, "ttyb"))
		strcpy(buf, "ttyS1");
#endif
	for (s = buf; *s; s++)
		if (isdigit(*s) || *s == ',')
			break;
	idx = simple_strtoul(s, NULL, 10);
	*s = 0;

	__add_preferred_console(buf, idx, options, brl_options, true);
	return 1;
}
__setup("console=", console_setup);

/**
 * add_preferred_console - add a device to the list of preferred consoles.
 * @name: device name
 * @idx: device index
 * @options: options for this console
 *
 * The last preferred console added will be used for kernel messages
 * and stdin/out/err for init.  Normally this is used by console_setup
 * above to handle user-supplied console arguments; however it can also
 * be used by arch-specific code either to override the user or more
 * commonly to provide a default console (ie from PROM variables) when
 * the user has not supplied one.
 */
int add_preferred_console(char *name, int idx, char *options)
{
	return __add_preferred_console(name, idx, options, NULL, false);
}

bool console_suspend_enabled = true;
EXPORT_SYMBOL(console_suspend_enabled);

static int __init console_suspend_disable(char *str)
{
	console_suspend_enabled = false;
	return 1;
}
__setup("no_console_suspend", console_suspend_disable);
module_param_named(console_suspend, console_suspend_enabled,
		bool, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(console_suspend, "suspend console during suspend"
	" and hibernate operations");

static bool printk_console_no_auto_verbose;

void console_verbose(void)
{
	if (console_loglevel && !printk_console_no_auto_verbose)
		console_loglevel = CONSOLE_LOGLEVEL_MOTORMOUTH;
}
EXPORT_SYMBOL_GPL(console_verbose);

module_param_named(console_no_auto_verbose, printk_console_no_auto_verbose, bool, 0644);
MODULE_PARM_DESC(console_no_auto_verbose, "Disable console loglevel raise to highest on oops/panic/etc");

/**
 * suspend_console - suspend the console subsystem
 *
 * This disables printk() while we go into suspend states
 */
void suspend_console(void)
{
	if (!console_suspend_enabled)
		return;
	pr_info("Suspending console(s) (use no_console_suspend to debug)\n");
	pr_flush(1000, true);
	console_lock();
	console_suspended = 1;
	up_console_sem();
}

void resume_console(void)
{
	if (!console_suspend_enabled)
		return;
	down_console_sem();
	console_suspended = 0;
	console_unlock();
	pr_flush(1000, true);
}

/**
 * console_cpu_notify - print deferred console messages after CPU hotplug
 * @cpu: unused
 *
 * If printk() is called from a CPU that is not online yet, the messages
 * will be printed on the console only if there are CON_ANYTIME consoles.
 * This function is called when a new CPU comes online (or fails to come
 * up) or goes offline.
 */
static int console_cpu_notify(unsigned int cpu)
{
	if (!cpuhp_tasks_frozen) {
		/* If trylock fails, someone else is doing the printing */
		if (console_trylock())
			console_unlock();
	}
	return 0;
}

/**
 * console_lock - lock the console system for exclusive use.
 *
 * Acquires a lock which guarantees that the caller has
 * exclusive access to the console system and the console_drivers list.
 *
 * Can sleep, returns nothing.
 */
void console_lock(void)
{
	might_sleep();

	down_console_sem();
	if (console_suspended)
		return;
	console_locked = 1;
	console_may_schedule = 1;
}
EXPORT_SYMBOL(console_lock);

/**
 * console_trylock - try to lock the console system for exclusive use.
 *
 * Try to acquire a lock which guarantees that the caller has exclusive
 * access to the console system and the console_drivers list.
 *
 * returns 1 on success, and 0 on failure to acquire the lock.
 */
int console_trylock(void)
{
	if (down_trylock_console_sem())
		return 0;
	if (console_suspended) {
		up_console_sem();
		return 0;
	}
	console_locked = 1;
	console_may_schedule = 0;
	return 1;
}
EXPORT_SYMBOL(console_trylock);

int is_console_locked(void)
{
	return console_locked;
}
EXPORT_SYMBOL(is_console_locked);

/*
 * Return true when this CPU should unlock console_sem without pushing all
 * messages to the console. This reduces the chance that the console is
 * locked when the panic CPU tries to use it.
 */
static bool abandon_console_lock_in_panic(void)
{
	if (!panic_in_progress())
		return false;

	/*
	 * We can use raw_smp_processor_id() here because it is impossible for
	 * the task to be migrated to the panic_cpu, or away from it. If
	 * panic_cpu has already been set, and we're not currently executing on
	 * that CPU, then we never will be.
	 */
	return atomic_read(&panic_cpu) != raw_smp_processor_id();
}

/*
 * Check if the given console is currently capable and allowed to print
 * records.
 *
 * Requires the console_lock.
 */
static inline bool console_is_usable(struct console *con)
{
	if (!(con->flags & CON_ENABLED))
		return false;

	if (!con->write)
		return false;

	/*
	 * Console drivers may assume that per-cpu resources have been
	 * allocated. So unless they're explicitly marked as being able to
	 * cope (CON_ANYTIME) don't call them until this CPU is officially up.
	 */
	if (!cpu_online(raw_smp_processor_id()) &&
	    !(con->flags & CON_ANYTIME))
		return false;

	return true;
}

static void __console_unlock(void)
{
	console_locked = 0;
	up_console_sem();
}

/*
 * Print one record for the given console. The record printed is whatever
 * record is the next available record for the given console.
 *
 * @text is a buffer of size CONSOLE_LOG_MAX.
 *
 * If extended messages should be printed, @ext_text is a buffer of size
 * CONSOLE_EXT_LOG_MAX. Otherwise @ext_text must be NULL.
 *
 * If dropped messages should be printed, @dropped_text is a buffer of size
 * DROPPED_TEXT_MAX. Otherwise @dropped_text must be NULL.
 *
 * @handover will be set to true if a printk waiter has taken over the
 * console_lock, in which case the caller is no longer holding the
 * console_lock. Otherwise it is set to false.
 *
 * Returns false if the given console has no next record to print, otherwise
 * true.
 *
 * Requires the console_lock.
 */
static bool console_emit_next_record(struct console *con, char *text, char *ext_text,
				     char *dropped_text, bool *handover)
{
	static int panic_console_dropped;
	struct printk_info info;
	struct printk_record r;
	unsigned long flags;
	char *write_text;
	size_t len;

	prb_rec_init_rd(&r, &info, text, CONSOLE_LOG_MAX);

	*handover = false;

	if (!prb_read_valid(prb, con->seq, &r))
		return false;

	if (con->seq != r.info->seq) {
		con->dropped += r.info->seq - con->seq;
		con->seq = r.info->seq;
		if (panic_in_progress() && panic_console_dropped++ > 10) {
			suppress_panic_printk = 1;
			pr_warn_once("Too many dropped messages. Suppress messages on non-panic CPUs to prevent livelock.\n");
		}
	}

	/* Skip record that has level above the console loglevel. */
	if (suppress_message_printing(r.info->level)) {
		con->seq++;
		goto skip;
	}

	if (ext_text) {
		write_text = ext_text;
		len = info_print_ext_header(ext_text, CONSOLE_EXT_LOG_MAX, r.info);
		len += msg_print_ext_body(ext_text + len, CONSOLE_EXT_LOG_MAX - len,
					  &r.text_buf[0], r.info->text_len, &r.info->dev_info);
	} else {
		write_text = text;
		len = record_print_text(&r, console_msg_format & MSG_FORMAT_SYSLOG, printk_time);
	}

	/*
	 * While actively printing out messages, if another printk()
	 * were to occur on another CPU, it may wait for this one to
	 * finish. This task can not be preempted if there is a
	 * waiter waiting to take over.
	 *
	 * Interrupts are disabled because the hand over to a waiter
	 * must not be interrupted until the hand over is completed
	 * (@console_waiter is cleared).
	 */
	printk_safe_enter_irqsave(flags);
	console_lock_spinning_enable();

	stop_critical_timings();	/* don't trace print latency */
	call_console_driver(con, write_text, len, dropped_text);
	start_critical_timings();

	con->seq++;

	*handover = console_lock_spinning_disable_and_check();
	printk_safe_exit_irqrestore(flags);
skip:
	return true;
}

/*
 * Print out all remaining records to all consoles.
 *
 * @do_cond_resched is set by the caller. It can be true only in schedulable
 * context.
 *
 * @next_seq is set to the sequence number after the last available record.
 * The value is valid only when this function returns true. It means that all
 * usable consoles are completely flushed.
 *
 * @handover will be set to true if a printk waiter has taken over the
 * console_lock, in which case the caller is no longer holding the
 * console_lock. Otherwise it is set to false.
 *
 * Returns true when there was at least one usable console and all messages
 * were flushed to all usable consoles. A returned false informs the caller
 * that everything was not flushed (either there were no usable consoles or
 * another context has taken over printing or it is a panic situation and this
 * is not the panic CPU). Regardless the reason, the caller should assume it
 * is not useful to immediately try again.
 *
 * Requires the console_lock.
 */
static bool console_flush_all(bool do_cond_resched, u64 *next_seq, bool *handover)
{
	static char dropped_text[DROPPED_TEXT_MAX];
	static char ext_text[CONSOLE_EXT_LOG_MAX];
	static char text[CONSOLE_LOG_MAX];
	bool any_usable = false;
	struct console *con;
	bool any_progress;

	*next_seq = 0;
	*handover = false;

	do {
		any_progress = false;

		for_each_console(con) {
			bool progress;

			if (!console_is_usable(con))
				continue;
			any_usable = true;

			if (con->flags & CON_EXTENDED) {
				/* Extended consoles do not print "dropped messages". */
				progress = console_emit_next_record(con, &text[0],
								    &ext_text[0], NULL,
								    handover);
			} else {
				progress = console_emit_next_record(con, &text[0],
								    NULL, &dropped_text[0],
								    handover);
			}
			if (*handover)
				return false;

			/* Track the next of the highest seq flushed. */
			if (con->seq > *next_seq)
				*next_seq = con->seq;

			if (!progress)
				continue;
			any_progress = true;

			/* Allow panic_cpu to take over the consoles safely. */
			if (abandon_console_lock_in_panic())
				return false;

			if (do_cond_resched)
				cond_resched();
		}
	} while (any_progress);

	return any_usable;
}

/**
 * console_unlock - unlock the console system
 *
 * Releases the console_lock which the caller holds on the console system
 * and the console driver list.
 *
 * While the console_lock was held, console output may have been buffered
 * by printk().  If this is the case, console_unlock(); emits
 * the output prior to releasing the lock.
 *
 * console_unlock(); may be called from any context.
 */
void console_unlock(void)
{
	bool do_cond_resched;
	bool handover;
	bool flushed;
	u64 next_seq;

	if (console_suspended) {
		up_console_sem();
		return;
	}

	/*
	 * Console drivers are called with interrupts disabled, so
	 * @console_may_schedule should be cleared before; however, we may
	 * end up dumping a lot of lines, for example, if called from
	 * console registration path, and should invoke cond_resched()
	 * between lines if allowable.  Not doing so can cause a very long
	 * scheduling stall on a slow console leading to RCU stall and
	 * softlockup warnings which exacerbate the issue with more
	 * messages practically incapacitating the system. Therefore, create
	 * a local to use for the printing loop.
	 */
	do_cond_resched = console_may_schedule;

	do {
		console_may_schedule = 0;

		flushed = console_flush_all(do_cond_resched, &next_seq, &handover);
		if (!handover)
			__console_unlock();

		/*
		 * Abort if there was a failure to flush all messages to all
		 * usable consoles. Either it is not possible to flush (in
		 * which case it would be an infinite loop of retrying) or
		 * another context has taken over printing.
		 */
		if (!flushed)
			break;

		/*
		 * Some context may have added new records after
		 * console_flush_all() but before unlocking the console.
		 * Re-check if there is a new record to flush. If the trylock
		 * fails, another context is already handling the printing.
		 */
	} while (prb_read_valid(prb, next_seq, NULL) && console_trylock());
}
EXPORT_SYMBOL(console_unlock);

/**
 * console_conditional_schedule - yield the CPU if required
 *
 * If the console code is currently allowed to sleep, and
 * if this CPU should yield the CPU to another task, do
 * so here.
 *
 * Must be called within console_lock();.
 */
void __sched console_conditional_schedule(void)
{
	if (console_may_schedule)
		cond_resched();
}
EXPORT_SYMBOL(console_conditional_schedule);

void console_unblank(void)
{
	struct console *c;

	/*
	 * console_unblank can no longer be called in interrupt context unless
	 * oops_in_progress is set to 1..
	 */
	if (oops_in_progress) {
		if (down_trylock_console_sem() != 0)
			return;
	} else
		console_lock();

	console_locked = 1;
	console_may_schedule = 0;
	for_each_console(c)
		if ((c->flags & CON_ENABLED) && c->unblank)
			c->unblank();
	console_unlock();

	if (!oops_in_progress)
		pr_flush(1000, true);
}

/**
 * console_flush_on_panic - flush console content on panic
 * @mode: flush all messages in buffer or just the pending ones
 *
 * Immediately output all pending messages no matter what.
 */
void console_flush_on_panic(enum con_flush_mode mode)
{
	/*
	 * If someone else is holding the console lock, trylock will fail
	 * and may_schedule may be set.  Ignore and proceed to unlock so
	 * that messages are flushed out.  As this can be called from any
	 * context and we don't want to get preempted while flushing,
	 * ensure may_schedule is cleared.
	 */
	console_trylock();
	console_may_schedule = 0;

	if (mode == CONSOLE_REPLAY_ALL) {
		struct console *c;
		u64 seq;

		seq = prb_first_valid_seq(prb);
		for_each_console(c)
			c->seq = seq;
	}
	console_unlock();
}

/*
 * Return the console tty driver structure and its associated index
 */
struct tty_driver *console_device(int *index)
{
	struct console *c;
	struct tty_driver *driver = NULL;

	console_lock();
	for_each_console(c) {
		if (!c->device)
			continue;
		driver = c->device(c, index);
		if (driver)
			break;
	}
	console_unlock();
	return driver;
}

/*
 * Prevent further output on the passed console device so that (for example)
 * serial drivers can disable console output before suspending a port, and can
 * re-enable output afterwards.
 */
void console_stop(struct console *console)
{
	__pr_flush(console, 1000, true);
	console_lock();
	console->flags &= ~CON_ENABLED;
	console_unlock();
}
EXPORT_SYMBOL(console_stop);

void console_start(struct console *console)
{
	console_lock();
	console->flags |= CON_ENABLED;
	console_unlock();
	__pr_flush(console, 1000, true);
}
EXPORT_SYMBOL(console_start);

static int __read_mostly keep_bootcon;

static int __init keep_bootcon_setup(char *str)
{
	keep_bootcon = 1;
	pr_info("debug: skip boot console de-registration.\n");

	return 0;
}

early_param("keep_bootcon", keep_bootcon_setup);

/*
 * This is called by register_console() to try to match
 * the newly registered console with any of the ones selected
 * by either the command line or add_preferred_console() and
 * setup/enable it.
 *
 * Care need to be taken with consoles that are statically
 * enabled such as netconsole
 */
static int try_enable_preferred_console(struct console *newcon,
					bool user_specified)
{
	struct console_cmdline *c;
	int i, err;

	for (i = 0, c = console_cmdline;
	     i < MAX_CMDLINECONSOLES && c->name[0];
	     i++, c++) {
		if (c->user_specified != user_specified)
			continue;
		if (!newcon->match ||
		    newcon->match(newcon, c->name, c->index, c->options) != 0) {
			/* default matching */
			BUILD_BUG_ON(sizeof(c->name) != sizeof(newcon->name));
			if (strcmp(c->name, newcon->name) != 0)
				continue;
			if (newcon->index >= 0 &&
			    newcon->index != c->index)
				continue;
			if (newcon->index < 0)
				newcon->index = c->index;

			if (_braille_register_console(newcon, c))
				return 0;

			if (newcon->setup &&
			    (err = newcon->setup(newcon, c->options)) != 0)
				return err;
		}
		newcon->flags |= CON_ENABLED;
		if (i == preferred_console)
			newcon->flags |= CON_CONSDEV;
		return 0;
	}

	/*
	 * Some consoles, such as pstore and netconsole, can be enabled even
	 * without matching. Accept the pre-enabled consoles only when match()
	 * and setup() had a chance to be called.
	 */
	if (newcon->flags & CON_ENABLED && c->user_specified ==	user_specified)
		return 0;

	return -ENOENT;
}

/* Try to enable the console unconditionally */
static void try_enable_default_console(struct console *newcon)
{
	if (newcon->index < 0)
		newcon->index = 0;

	if (newcon->setup && newcon->setup(newcon, NULL) != 0)
		return;

	newcon->flags |= CON_ENABLED;

	if (newcon->device)
		newcon->flags |= CON_CONSDEV;
}

#define con_printk(lvl, con, fmt, ...)			\
	printk(lvl pr_fmt("%sconsole [%s%d] " fmt),	\
	       (con->flags & CON_BOOT) ? "boot" : "",	\
	       con->name, con->index, ##__VA_ARGS__)

/*
 * The console driver calls this routine during kernel initialization
 * to register the console printing procedure with printk() and to
 * print any messages that were printed by the kernel before the
 * console driver was initialized.
 *
 * This can happen pretty early during the boot process (because of
 * early_printk) - sometimes before setup_arch() completes - be careful
 * of what kernel features are used - they may not be initialised yet.
 *
 * There are two types of consoles - bootconsoles (early_printk) and
 * "real" consoles (everything which is not a bootconsole) which are
 * handled differently.
 *  - Any number of bootconsoles can be registered at any time.
 *  - As soon as a "real" console is registered, all bootconsoles
 *    will be unregistered automatically.
 *  - Once a "real" console is registered, any attempt to register a
 *    bootconsoles will be rejected
 */
void register_console(struct console *newcon)
{
	struct console *con;
	bool bootcon_enabled = false;
	bool realcon_enabled = false;
	int err;

	for_each_console(con) {
		if (WARN(con == newcon, "console '%s%d' already registered\n",
					 con->name, con->index))
			return;
	}

	for_each_console(con) {
		if (con->flags & CON_BOOT)
			bootcon_enabled = true;
		else
			realcon_enabled = true;
	}

	/* Do not register boot consoles when there already is a real one. */
	if (newcon->flags & CON_BOOT && realcon_enabled) {
		pr_info("Too late to register bootconsole %s%d\n",
			newcon->name, newcon->index);
		return;
	}

	/*
	 * See if we want to enable this console driver by default.
	 *
	 * Nope when a console is preferred by the command line, device
	 * tree, or SPCR.
	 *
	 * The first real console with tty binding (driver) wins. More
	 * consoles might get enabled before the right one is found.
	 *
	 * Note that a console with tty binding will have CON_CONSDEV
	 * flag set and will be first in the list.
	 */
	if (preferred_console < 0) {
		if (!console_drivers || !console_drivers->device ||
		    console_drivers->flags & CON_BOOT) {
			try_enable_default_console(newcon);
		}
	}

	/* See if this console matches one we selected on the command line */
	err = try_enable_preferred_console(newcon, true);

	/* If not, try to match against the platform default(s) */
	if (err == -ENOENT)
		err = try_enable_preferred_console(newcon, false);

	/* printk() messages are not printed to the Braille console. */
	if (err || newcon->flags & CON_BRL)
		return;

	/*
	 * If we have a bootconsole, and are switching to a real console,
	 * don't print everything out again, since when the boot console, and
	 * the real console are the same physical device, it's annoying to
	 * see the beginning boot messages twice
	 */
	if (bootcon_enabled &&
	    ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV)) {
		newcon->flags &= ~CON_PRINTBUFFER;
	}

	/*
	 *	Put this console in the list - keep the
	 *	preferred driver at the head of the list.
	 */
	console_lock();
	if ((newcon->flags & CON_CONSDEV) || console_drivers == NULL) {
		newcon->next = console_drivers;
		console_drivers = newcon;
		if (newcon->next)
			newcon->next->flags &= ~CON_CONSDEV;
		/* Ensure this flag is always set for the head of the list */
		newcon->flags |= CON_CONSDEV;
	} else {
		newcon->next = console_drivers->next;
		console_drivers->next = newcon;
	}

	if (newcon->flags & CON_EXTENDED)
		nr_ext_console_drivers++;

	newcon->dropped = 0;
	if (newcon->flags & CON_PRINTBUFFER) {
		/* Get a consistent copy of @syslog_seq. */
		mutex_lock(&syslog_lock);
		newcon->seq = syslog_seq;
		mutex_unlock(&syslog_lock);
	} else {
		/* Begin with next message. */
		newcon->seq = prb_next_seq(prb);
	}
	console_unlock();
	console_sysfs_notify();

	/*
	 * By unregistering the bootconsoles after we enable the real console
	 * we get the "console xxx enabled" message on all the consoles -
	 * boot consoles, real consoles, etc - this is to ensure that end
	 * users know there might be something in the kernel's log buffer that
	 * went to the bootconsole (that they do not see on the real console)
	 */
	con_printk(KERN_INFO, newcon, "enabled\n");
	if (bootcon_enabled &&
	    ((newcon->flags & (CON_CONSDEV | CON_BOOT)) == CON_CONSDEV) &&
	    !keep_bootcon) {
		/* We need to iterate through all boot consoles, to make
		 * sure we print everything out, before we unregister them.
		 */
		for_each_console(con)
			if (con->flags & CON_BOOT)
				unregister_console(con);
	}
}
EXPORT_SYMBOL(register_console);

int unregister_console(struct console *console)
{
	struct console *con;
	int res;

	con_printk(KERN_INFO, console, "disabled\n");

	res = _braille_unregister_console(console);
	if (res < 0)
		return res;
	if (res > 0)
		return 0;

	res = -ENODEV;
	console_lock();
	if (console_drivers == console) {
		console_drivers=console->next;
		res = 0;
	} else {
		for_each_console(con) {
			if (con->next == console) {
				con->next = console->next;
				res = 0;
				break;
			}
		}
	}

	if (res)
		goto out_disable_unlock;

	if (console->flags & CON_EXTENDED)
		nr_ext_console_drivers--;

	/*
	 * If this isn't the last console and it has CON_CONSDEV set, we
	 * need to set it on the next preferred console.
	 */
	if (console_drivers != NULL && console->flags & CON_CONSDEV)
		console_drivers->flags |= CON_CONSDEV;

	console->flags &= ~CON_ENABLED;
	console_unlock();
	console_sysfs_notify();

	if (console->exit)
		res = console->exit(console);

	return res;

out_disable_unlock:
	console->flags &= ~CON_ENABLED;
	console_unlock();

	return res;
}
EXPORT_SYMBOL(unregister_console);

/*
 * Initialize the console device. This is called *early*, so
 * we can't necessarily depend on lots of kernel help here.
 * Just do some early initializations, and do the complex setup
 * later.
 */
void __init console_init(void)
{
	int ret;
	initcall_t call;
	initcall_entry_t *ce;

	/* Setup the default TTY line discipline. */
	n_tty_init();

	/*
	 * set up the console device so that later boot sequences can
	 * inform about problems etc..
	 */
	ce = __con_initcall_start;
	trace_initcall_level("console");
	while (ce < __con_initcall_end) {
		call = initcall_from_entry(ce);
		trace_initcall_start(call);
		ret = call();
		trace_initcall_finish(call, ret);
		ce++;
	}
}

/*
 * Some boot consoles access data that is in the init section and which will
 * be discarded after the initcalls have been run. To make sure that no code
 * will access this data, unregister the boot consoles in a late initcall.
 *
 * If for some reason, such as deferred probe or the driver being a loadable
 * module, the real console hasn't registered yet at this point, there will
 * be a brief interval in which no messages are logged to the console, which
 * makes it difficult to diagnose problems that occur during this time.
 *
 * To mitigate this problem somewhat, only unregister consoles whose memory
 * intersects with the init section. Note that all other boot consoles will
 * get unregistered when the real preferred console is registered.
 */
static int __init printk_late_init(void)
{
	struct console *con;
	int ret;

	for_each_console(con) {
		if (!(con->flags & CON_BOOT))
			continue;

		/* Check addresses that might be used for enabled consoles. */
		if (init_section_intersects(con, sizeof(*con)) ||
		    init_section_contains(con->write, 0) ||
		    init_section_contains(con->read, 0) ||
		    init_section_contains(con->device, 0) ||
		    init_section_contains(con->unblank, 0) ||
		    init_section_contains(con->data, 0)) {
			/*
			 * Please, consider moving the reported consoles out
			 * of the init section.
			 */
			pr_warn("bootconsole [%s%d] uses init memory and must be disabled even before the real one is ready\n",
				con->name, con->index);
			unregister_console(con);
		}
	}
	ret = cpuhp_setup_state_nocalls(CPUHP_PRINTK_DEAD, "printk:dead", NULL,
					console_cpu_notify);
	WARN_ON(ret < 0);
	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "printk:online",
					console_cpu_notify, NULL);
	WARN_ON(ret < 0);
	printk_sysctl_init();
	return 0;
}
late_initcall(printk_late_init);

#if defined CONFIG_PRINTK
/* If @con is specified, only wait for that console. Otherwise wait for all. */
static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progress)
{
	int remaining = timeout_ms;
	struct console *c;
	u64 last_diff = 0;
	u64 printk_seq;
	u64 diff;
	u64 seq;

	might_sleep();

	seq = prb_next_seq(prb);

	for (;;) {
		diff = 0;

		console_lock();

		for_each_console(c) {
			if (con && con != c)
				continue;
			if (!console_is_usable(c))
				continue;
			printk_seq = c->seq;
			if (printk_seq < seq)
				diff += seq - printk_seq;
		}

		/*
		 * If consoles are suspended, it cannot be expected that they
		 * make forward progress, so timeout immediately. @diff is
		 * still used to return a valid flush status.
		 */
		if (console_suspended)
			remaining = 0;
		else if (diff != last_diff && reset_on_progress)
			remaining = timeout_ms;

		console_unlock();

		if (diff == 0 || remaining == 0)
			break;

		if (remaining < 0) {
			/* no timeout limit */
			msleep(100);
		} else if (remaining < 100) {
			msleep(remaining);
			remaining = 0;
		} else {
			msleep(100);
			remaining -= 100;
		}

		last_diff = diff;
	}

	return (diff == 0);
}

/**
 * pr_flush() - Wait for printing threads to catch up.
 *
 * @timeout_ms:        The maximum time (in ms) to wait.
 * @reset_on_progress: Reset the timeout if forward progress is seen.
 *
 * A value of 0 for @timeout_ms means no waiting will occur. A value of -1
 * represents infinite waiting.
 *
 * If @reset_on_progress is true, the timeout will be reset whenever any
 * printer has been seen to make some forward progress.
 *
 * Context: Process context. May sleep while acquiring console lock.
 * Return: true if all enabled printers are caught up.
 */
bool pr_flush(int timeout_ms, bool reset_on_progress)
{
	return __pr_flush(NULL, timeout_ms, reset_on_progress);
}
EXPORT_SYMBOL(pr_flush);

/*
 * Delayed printk version, for scheduler-internal messages:
 */
#define PRINTK_PENDING_WAKEUP	0x01
#define PRINTK_PENDING_OUTPUT	0x02

static DEFINE_PER_CPU(int, printk_pending);

static void wake_up_klogd_work_func(struct irq_work *irq_work)
{
	int pending = this_cpu_xchg(printk_pending, 0);

	if (pending & PRINTK_PENDING_OUTPUT) {
		/* If trylock fails, someone else is doing the printing */
		if (console_trylock())
			console_unlock();
	}

	if (pending & PRINTK_PENDING_WAKEUP)
		wake_up_interruptible(&log_wait);
}

static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) =
	IRQ_WORK_INIT_LAZY(wake_up_klogd_work_func);

static void __wake_up_klogd(int val)
{
	if (!printk_percpu_data_ready())
		return;

	preempt_disable();
	/*
	 * Guarantee any new records can be seen by tasks preparing to wait
	 * before this context checks if the wait queue is empty.
	 *
	 * The full memory barrier within wq_has_sleeper() pairs with the full
	 * memory barrier within set_current_state() of
	 * prepare_to_wait_event(), which is called after ___wait_event() adds
	 * the waiter but before it has checked the wait condition.
	 *
	 * This pairs with devkmsg_read:A and syslog_print:A.
	 */
	if (wq_has_sleeper(&log_wait) || /* LMM(__wake_up_klogd:A) */
	    (val & PRINTK_PENDING_OUTPUT)) {
		this_cpu_or(printk_pending, val);
		irq_work_queue(this_cpu_ptr(&wake_up_klogd_work));
	}
	preempt_enable();
}

void wake_up_klogd(void)
{
	__wake_up_klogd(PRINTK_PENDING_WAKEUP);
}

void defer_console_output(void)
{
	/*
	 * New messages may have been added directly to the ringbuffer
	 * using vprintk_store(), so wake any waiters as well.
	 */
	__wake_up_klogd(PRINTK_PENDING_WAKEUP | PRINTK_PENDING_OUTPUT);
}

void printk_trigger_flush(void)
{
	defer_console_output();
}

int vprintk_deferred(const char *fmt, va_list args)
{
	int r;

	r = vprintk_emit(0, LOGLEVEL_SCHED, NULL, fmt, args);
	defer_console_output();

	return r;
}

int _printk_deferred(const char *fmt, ...)
{
	va_list args;
	int r;

	va_start(args, fmt);
	r = vprintk_deferred(fmt, args);
	va_end(args);

	return r;
}

/*
 * printk rate limiting, lifted from the networking subsystem.
 *
 * This enforces a rate limit: not more than 10 kernel messages
 * every 5s to make a denial-of-service attack impossible.
 */
DEFINE_RATELIMIT_STATE(printk_ratelimit_state, 5 * HZ, 10);

int __printk_ratelimit(const char *func)
{
	return ___ratelimit(&printk_ratelimit_state, func);
}
EXPORT_SYMBOL(__printk_ratelimit);

/**
 * printk_timed_ratelimit - caller-controlled printk ratelimiting
 * @caller_jiffies: pointer to caller's state
 * @interval_msecs: minimum interval between prints
 *
 * printk_timed_ratelimit() returns true if more than @interval_msecs
 * milliseconds have elapsed since the last time printk_timed_ratelimit()
 * returned true.
 */
bool printk_timed_ratelimit(unsigned long *caller_jiffies,
			unsigned int interval_msecs)
{
	unsigned long elapsed = jiffies - *caller_jiffies;

	if (*caller_jiffies && elapsed <= msecs_to_jiffies(interval_msecs))
		return false;

	*caller_jiffies = jiffies;
	return true;
}
EXPORT_SYMBOL(printk_timed_ratelimit);

static DEFINE_SPINLOCK(dump_list_lock);
static LIST_HEAD(dump_list);

/**
 * kmsg_dump_register - register a kernel log dumper.
 * @dumper: pointer to the kmsg_dumper structure
 *
 * Adds a kernel log dumper to the system. The dump callback in the
 * structure will be called when the kernel oopses or panics and must be
 * set. Returns zero on success and %-EINVAL or %-EBUSY otherwise.
 */
int kmsg_dump_register(struct kmsg_dumper *dumper)
{
	unsigned long flags;
	int err = -EBUSY;

	/* The dump callback needs to be set */
	if (!dumper->dump)
		return -EINVAL;

	spin_lock_irqsave(&dump_list_lock, flags);
	/* Don't allow registering multiple times */
	if (!dumper->registered) {
		dumper->registered = 1;
		list_add_tail_rcu(&dumper->list, &dump_list);
		err = 0;
	}
	spin_unlock_irqrestore(&dump_list_lock, flags);

	return err;
}
EXPORT_SYMBOL_GPL(kmsg_dump_register);

/**
 * kmsg_dump_unregister - unregister a kmsg dumper.
 * @dumper: pointer to the kmsg_dumper structure
 *
 * Removes a dump device from the system. Returns zero on success and
 * %-EINVAL otherwise.
 */
int kmsg_dump_unregister(struct kmsg_dumper *dumper)
{
	unsigned long flags;
	int err = -EINVAL;

	spin_lock_irqsave(&dump_list_lock, flags);
	if (dumper->registered) {
		dumper->registered = 0;
		list_del_rcu(&dumper->list);
		err = 0;
	}
	spin_unlock_irqrestore(&dump_list_lock, flags);
	synchronize_rcu();

	return err;
}
EXPORT_SYMBOL_GPL(kmsg_dump_unregister);

static bool always_kmsg_dump;
module_param_named(always_kmsg_dump, always_kmsg_dump, bool, S_IRUGO | S_IWUSR);

const char *kmsg_dump_reason_str(enum kmsg_dump_reason reason)
{
	switch (reason) {
	case KMSG_DUMP_PANIC:
		return "Panic";
	case KMSG_DUMP_OOPS:
		return "Oops";
	case KMSG_DUMP_EMERG:
		return "Emergency";
	case KMSG_DUMP_SHUTDOWN:
		return "Shutdown";
	default:
		return "Unknown";
	}
}
EXPORT_SYMBOL_GPL(kmsg_dump_reason_str);

/**
 * kmsg_dump - dump kernel log to kernel message dumpers.
 * @reason: the reason (oops, panic etc) for dumping
 *
 * Call each of the registered dumper's dump() callback, which can
 * retrieve the kmsg records with kmsg_dump_get_line() or
 * kmsg_dump_get_buffer().
 */
void kmsg_dump(enum kmsg_dump_reason reason)
{
	struct kmsg_dumper *dumper;

	rcu_read_lock();
	list_for_each_entry_rcu(dumper, &dump_list, list) {
		enum kmsg_dump_reason max_reason = dumper->max_reason;

		/*
		 * If client has not provided a specific max_reason, default
		 * to KMSG_DUMP_OOPS, unless always_kmsg_dump was set.
		 */
		if (max_reason == KMSG_DUMP_UNDEF) {
			max_reason = always_kmsg_dump ? KMSG_DUMP_MAX :
							KMSG_DUMP_OOPS;
		}
		if (reason > max_reason)
			continue;

		/* invoke dumper which will iterate over records */
		dumper->dump(dumper, reason);
	}
	rcu_read_unlock();
}

/**
 * kmsg_dump_get_line - retrieve one kmsg log line
 * @iter: kmsg dump iterator
 * @syslog: include the "<4>" prefixes
 * @line: buffer to copy the line to
 * @size: maximum size of the buffer
 * @len: length of line placed into buffer
 *
 * Start at the beginning of the kmsg buffer, with the oldest kmsg
 * record, and copy one record into the provided buffer.
 *
 * Consecutive calls will return the next available record moving
 * towards the end of the buffer with the youngest messages.
 *
 * A return value of FALSE indicates that there are no more records to
 * read.
 */
bool kmsg_dump_get_line(struct kmsg_dump_iter *iter, bool syslog,
			char *line, size_t size, size_t *len)
{
	u64 min_seq = latched_seq_read_nolock(&clear_seq);
	struct printk_info info;
	unsigned int line_count;
	struct printk_record r;
	size_t l = 0;
	bool ret = false;

	if (iter->cur_seq < min_seq)
		iter->cur_seq = min_seq;

	prb_rec_init_rd(&r, &info, line, size);

	/* Read text or count text lines? */
	if (line) {
		if (!prb_read_valid(prb, iter->cur_seq, &r))
			goto out;
		l = record_print_text(&r, syslog, printk_time);
	} else {
		if (!prb_read_valid_info(prb, iter->cur_seq,
					 &info, &line_count)) {
			goto out;
		}
		l = get_record_print_text_size(&info, line_count, syslog,
					       printk_time);

	}

	iter->cur_seq = r.info->seq + 1;
	ret = true;
out:
	if (len)
		*len = l;
	return ret;
}
EXPORT_SYMBOL_GPL(kmsg_dump_get_line);

/**
 * kmsg_dump_get_buffer - copy kmsg log lines
 * @iter: kmsg dump iterator
 * @syslog: include the "<4>" prefixes
 * @buf: buffer to copy the line to
 * @size: maximum size of the buffer
 * @len_out: length of line placed into buffer
 *
 * Start at the end of the kmsg buffer and fill the provided buffer
 * with as many of the *youngest* kmsg records that fit into it.
 * If the buffer is large enough, all available kmsg records will be
 * copied with a single call.
 *
 * Consecutive calls will fill the buffer with the next block of
 * available older records, not including the earlier retrieved ones.
 *
 * A return value of FALSE indicates that there are no more records to
 * read.
 */
bool kmsg_dump_get_buffer(struct kmsg_dump_iter *iter, bool syslog,
			  char *buf, size_t size, size_t *len_out)
{
	u64 min_seq = latched_seq_read_nolock(&clear_seq);
	struct printk_info info;
	struct printk_record r;
	u64 seq;
	u64 next_seq;
	size_t len = 0;
	bool ret = false;
	bool time = printk_time;

	if (!buf || !size)
		goto out;

	if (iter->cur_seq < min_seq)
		iter->cur_seq = min_seq;

	if (prb_read_valid_info(prb, iter->cur_seq, &info, NULL)) {
		if (info.seq != iter->cur_seq) {
			/* messages are gone, move to first available one */
			iter->cur_seq = info.seq;
		}
	}

	/* last entry */
	if (iter->cur_seq >= iter->next_seq)
		goto out;

	/*
	 * Find first record that fits, including all following records,
	 * into the user-provided buffer for this dump. Pass in size-1
	 * because this function (by way of record_print_text()) will
	 * not write more than size-1 bytes of text into @buf.
	 */
	seq = find_first_fitting_seq(iter->cur_seq, iter->next_seq,
				     size - 1, syslog, time);

	/*
	 * Next kmsg_dump_get_buffer() invocation will dump block of
	 * older records stored right before this one.
	 */
	next_seq = seq;

	prb_rec_init_rd(&r, &info, buf, size);

	len = 0;
	prb_for_each_record(seq, prb, seq, &r) {
		if (r.info->seq >= iter->next_seq)
			break;

		len += record_print_text(&r, syslog, time);

		/* Adjust record to store to remaining buffer space. */
		prb_rec_init_rd(&r, &info, buf + len, size - len);
	}

	iter->next_seq = next_seq;
	ret = true;
out:
	if (len_out)
		*len_out = len;
	return ret;
}
EXPORT_SYMBOL_GPL(kmsg_dump_get_buffer);

/**
 * kmsg_dump_rewind - reset the iterator
 * @iter: kmsg dump iterator
 *
 * Reset the dumper's iterator so that kmsg_dump_get_line() and
 * kmsg_dump_get_buffer() can be called again and used multiple
 * times within the same dumper.dump() callback.
 */
void kmsg_dump_rewind(struct kmsg_dump_iter *iter)
{
	iter->cur_seq = latched_seq_read_nolock(&clear_seq);
	iter->next_seq = prb_next_seq(prb);
}
EXPORT_SYMBOL_GPL(kmsg_dump_rewind);

#endif

#ifdef CONFIG_SMP
static atomic_t printk_cpu_sync_owner = ATOMIC_INIT(-1);
static atomic_t printk_cpu_sync_nested = ATOMIC_INIT(0);

/**
 * __printk_cpu_sync_wait() - Busy wait until the printk cpu-reentrant
 *                            spinning lock is not owned by any CPU.
 *
 * Context: Any context.
 */
void __printk_cpu_sync_wait(void)
{
	do {
		cpu_relax();
	} while (atomic_read(&printk_cpu_sync_owner) != -1);
}
EXPORT_SYMBOL(__printk_cpu_sync_wait);

/**
 * __printk_cpu_sync_try_get() - Try to acquire the printk cpu-reentrant
 *                               spinning lock.
 *
 * If no processor has the lock, the calling processor takes the lock and
 * becomes the owner. If the calling processor is already the owner of the
 * lock, this function succeeds immediately.
 *
 * Context: Any context. Expects interrupts to be disabled.
 * Return: 1 on success, otherwise 0.
 */
int __printk_cpu_sync_try_get(void)
{
	int cpu;
	int old;

	cpu = smp_processor_id();

	/*
	 * Guarantee loads and stores from this CPU when it is the lock owner
	 * are _not_ visible to the previous lock owner. This pairs with
	 * __printk_cpu_sync_put:B.
	 *
	 * Memory barrier involvement:
	 *
	 * If __printk_cpu_sync_try_get:A reads from __printk_cpu_sync_put:B,
	 * then __printk_cpu_sync_put:A can never read from
	 * __printk_cpu_sync_try_get:B.
	 *
	 * Relies on:
	 *
	 * RELEASE from __printk_cpu_sync_put:A to __printk_cpu_sync_put:B
	 * of the previous CPU
	 *    matching
	 * ACQUIRE from __printk_cpu_sync_try_get:A to
	 * __printk_cpu_sync_try_get:B of this CPU
	 */
	old = atomic_cmpxchg_acquire(&printk_cpu_sync_owner, -1,
				     cpu); /* LMM(__printk_cpu_sync_try_get:A) */
	if (old == -1) {
		/*
		 * This CPU is now the owner and begins loading/storing
		 * data: LMM(__printk_cpu_sync_try_get:B)
		 */
		return 1;

	} else if (old == cpu) {
		/* This CPU is already the owner. */
		atomic_inc(&printk_cpu_sync_nested);
		return 1;
	}

	return 0;
}
EXPORT_SYMBOL(__printk_cpu_sync_try_get);

/**
 * __printk_cpu_sync_put() - Release the printk cpu-reentrant spinning lock.
 *
 * The calling processor must be the owner of the lock.
 *
 * Context: Any context. Expects interrupts to be disabled.
 */
void __printk_cpu_sync_put(void)
{
	if (atomic_read(&printk_cpu_sync_nested)) {
		atomic_dec(&printk_cpu_sync_nested);
		return;
	}

	/*
	 * This CPU is finished loading/storing data:
	 * LMM(__printk_cpu_sync_put:A)
	 */

	/*
	 * Guarantee loads and stores from this CPU when it was the
	 * lock owner are visible to the next lock owner. This pairs
	 * with __printk_cpu_sync_try_get:A.
	 *
	 * Memory barrier involvement:
	 *
	 * If __printk_cpu_sync_try_get:A reads from __printk_cpu_sync_put:B,
	 * then __printk_cpu_sync_try_get:B reads from __printk_cpu_sync_put:A.
	 *
	 * Relies on:
	 *
	 * RELEASE from __printk_cpu_sync_put:A to __printk_cpu_sync_put:B
	 * of this CPU
	 *    matching
	 * ACQUIRE from __printk_cpu_sync_try_get:A to
	 * __printk_cpu_sync_try_get:B of the next CPU
	 */
	atomic_set_release(&printk_cpu_sync_owner,
			   -1); /* LMM(__printk_cpu_sync_put:B) */
}
EXPORT_SYMBOL(__printk_cpu_sync_put);
#endif /* CONFIG_SMP */