summaryrefslogtreecommitdiffstats
path: root/kernel/printk/printk_ringbuffer.c
blob: f5a8bb606fe507bc41e4ea7547314e821493b846 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
// SPDX-License-Identifier: GPL-2.0

#include <linux/kernel.h>
#include <linux/irqflags.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/bug.h>
#include "printk_ringbuffer.h"
#include "internal.h"

/**
 * DOC: printk_ringbuffer overview
 *
 * Data Structure
 * --------------
 * The printk_ringbuffer is made up of 3 internal ringbuffers:
 *
 *   desc_ring
 *     A ring of descriptors and their meta data (such as sequence number,
 *     timestamp, loglevel, etc.) as well as internal state information about
 *     the record and logical positions specifying where in the other
 *     ringbuffer the text strings are located.
 *
 *   text_data_ring
 *     A ring of data blocks. A data block consists of an unsigned long
 *     integer (ID) that maps to a desc_ring index followed by the text
 *     string of the record.
 *
 * The internal state information of a descriptor is the key element to allow
 * readers and writers to locklessly synchronize access to the data.
 *
 * Implementation
 * --------------
 *
 * Descriptor Ring
 * ~~~~~~~~~~~~~~~
 * The descriptor ring is an array of descriptors. A descriptor contains
 * essential meta data to track the data of a printk record using
 * blk_lpos structs pointing to associated text data blocks (see
 * "Data Rings" below). Each descriptor is assigned an ID that maps
 * directly to index values of the descriptor array and has a state. The ID
 * and the state are bitwise combined into a single descriptor field named
 * @state_var, allowing ID and state to be synchronously and atomically
 * updated.
 *
 * Descriptors have four states:
 *
 *   reserved
 *     A writer is modifying the record.
 *
 *   committed
 *     The record and all its data are written. A writer can reopen the
 *     descriptor (transitioning it back to reserved), but in the committed
 *     state the data is consistent.
 *
 *   finalized
 *     The record and all its data are complete and available for reading. A
 *     writer cannot reopen the descriptor.
 *
 *   reusable
 *     The record exists, but its text and/or meta data may no longer be
 *     available.
 *
 * Querying the @state_var of a record requires providing the ID of the
 * descriptor to query. This can yield a possible fifth (pseudo) state:
 *
 *   miss
 *     The descriptor being queried has an unexpected ID.
 *
 * The descriptor ring has a @tail_id that contains the ID of the oldest
 * descriptor and @head_id that contains the ID of the newest descriptor.
 *
 * When a new descriptor should be created (and the ring is full), the tail
 * descriptor is invalidated by first transitioning to the reusable state and
 * then invalidating all tail data blocks up to and including the data blocks
 * associated with the tail descriptor (for the text ring). Then
 * @tail_id is advanced, followed by advancing @head_id. And finally the
 * @state_var of the new descriptor is initialized to the new ID and reserved
 * state.
 *
 * The @tail_id can only be advanced if the new @tail_id would be in the
 * committed or reusable queried state. This makes it possible that a valid
 * sequence number of the tail is always available.
 *
 * Descriptor Finalization
 * ~~~~~~~~~~~~~~~~~~~~~~~
 * When a writer calls the commit function prb_commit(), record data is
 * fully stored and is consistent within the ringbuffer. However, a writer can
 * reopen that record, claiming exclusive access (as with prb_reserve()), and
 * modify that record. When finished, the writer must again commit the record.
 *
 * In order for a record to be made available to readers (and also become
 * recyclable for writers), it must be finalized. A finalized record cannot be
 * reopened and can never become "unfinalized". Record finalization can occur
 * in three different scenarios:
 *
 *   1) A writer can simultaneously commit and finalize its record by calling
 *      prb_final_commit() instead of prb_commit().
 *
 *   2) When a new record is reserved and the previous record has been
 *      committed via prb_commit(), that previous record is automatically
 *      finalized.
 *
 *   3) When a record is committed via prb_commit() and a newer record
 *      already exists, the record being committed is automatically finalized.
 *
 * Data Ring
 * ~~~~~~~~~
 * The text data ring is a byte array composed of data blocks. Data blocks are
 * referenced by blk_lpos structs that point to the logical position of the
 * beginning of a data block and the beginning of the next adjacent data
 * block. Logical positions are mapped directly to index values of the byte
 * array ringbuffer.
 *
 * Each data block consists of an ID followed by the writer data. The ID is
 * the identifier of a descriptor that is associated with the data block. A
 * given data block is considered valid if all of the following conditions
 * are met:
 *
 *   1) The descriptor associated with the data block is in the committed
 *      or finalized queried state.
 *
 *   2) The blk_lpos struct within the descriptor associated with the data
 *      block references back to the same data block.
 *
 *   3) The data block is within the head/tail logical position range.
 *
 * If the writer data of a data block would extend beyond the end of the
 * byte array, only the ID of the data block is stored at the logical
 * position and the full data block (ID and writer data) is stored at the
 * beginning of the byte array. The referencing blk_lpos will point to the
 * ID before the wrap and the next data block will be at the logical
 * position adjacent the full data block after the wrap.
 *
 * Data rings have a @tail_lpos that points to the beginning of the oldest
 * data block and a @head_lpos that points to the logical position of the
 * next (not yet existing) data block.
 *
 * When a new data block should be created (and the ring is full), tail data
 * blocks will first be invalidated by putting their associated descriptors
 * into the reusable state and then pushing the @tail_lpos forward beyond
 * them. Then the @head_lpos is pushed forward and is associated with a new
 * descriptor. If a data block is not valid, the @tail_lpos cannot be
 * advanced beyond it.
 *
 * Info Array
 * ~~~~~~~~~~
 * The general meta data of printk records are stored in printk_info structs,
 * stored in an array with the same number of elements as the descriptor ring.
 * Each info corresponds to the descriptor of the same index in the
 * descriptor ring. Info validity is confirmed by evaluating the corresponding
 * descriptor before and after loading the info.
 *
 * Usage
 * -----
 * Here are some simple examples demonstrating writers and readers. For the
 * examples a global ringbuffer (test_rb) is available (which is not the
 * actual ringbuffer used by printk)::
 *
 *	DEFINE_PRINTKRB(test_rb, 15, 5);
 *
 * This ringbuffer allows up to 32768 records (2 ^ 15) and has a size of
 * 1 MiB (2 ^ (15 + 5)) for text data.
 *
 * Sample writer code::
 *
 *	const char *textstr = "message text";
 *	struct prb_reserved_entry e;
 *	struct printk_record r;
 *
 *	// specify how much to allocate
 *	prb_rec_init_wr(&r, strlen(textstr) + 1);
 *
 *	if (prb_reserve(&e, &test_rb, &r)) {
 *		snprintf(r.text_buf, r.text_buf_size, "%s", textstr);
 *
 *		r.info->text_len = strlen(textstr);
 *		r.info->ts_nsec = local_clock();
 *		r.info->caller_id = printk_caller_id();
 *
 *		// commit and finalize the record
 *		prb_final_commit(&e);
 *	}
 *
 * Note that additional writer functions are available to extend a record
 * after it has been committed but not yet finalized. This can be done as
 * long as no new records have been reserved and the caller is the same.
 *
 * Sample writer code (record extending)::
 *
 *		// alternate rest of previous example
 *
 *		r.info->text_len = strlen(textstr);
 *		r.info->ts_nsec = local_clock();
 *		r.info->caller_id = printk_caller_id();
 *
 *		// commit the record (but do not finalize yet)
 *		prb_commit(&e);
 *	}
 *
 *	...
 *
 *	// specify additional 5 bytes text space to extend
 *	prb_rec_init_wr(&r, 5);
 *
 *	// try to extend, but only if it does not exceed 32 bytes
 *	if (prb_reserve_in_last(&e, &test_rb, &r, printk_caller_id(), 32)) {
 *		snprintf(&r.text_buf[r.info->text_len],
 *			 r.text_buf_size - r.info->text_len, "hello");
 *
 *		r.info->text_len += 5;
 *
 *		// commit and finalize the record
 *		prb_final_commit(&e);
 *	}
 *
 * Sample reader code::
 *
 *	struct printk_info info;
 *	struct printk_record r;
 *	char text_buf[32];
 *	u64 seq;
 *
 *	prb_rec_init_rd(&r, &info, &text_buf[0], sizeof(text_buf));
 *
 *	prb_for_each_record(0, &test_rb, &seq, &r) {
 *		if (info.seq != seq)
 *			pr_warn("lost %llu records\n", info.seq - seq);
 *
 *		if (info.text_len > r.text_buf_size) {
 *			pr_warn("record %llu text truncated\n", info.seq);
 *			text_buf[r.text_buf_size - 1] = 0;
 *		}
 *
 *		pr_info("%llu: %llu: %s\n", info.seq, info.ts_nsec,
 *			&text_buf[0]);
 *	}
 *
 * Note that additional less convenient reader functions are available to
 * allow complex record access.
 *
 * ABA Issues
 * ~~~~~~~~~~
 * To help avoid ABA issues, descriptors are referenced by IDs (array index
 * values combined with tagged bits counting array wraps) and data blocks are
 * referenced by logical positions (array index values combined with tagged
 * bits counting array wraps). However, on 32-bit systems the number of
 * tagged bits is relatively small such that an ABA incident is (at least
 * theoretically) possible. For example, if 4 million maximally sized (1KiB)
 * printk messages were to occur in NMI context on a 32-bit system, the
 * interrupted context would not be able to recognize that the 32-bit integer
 * completely wrapped and thus represents a different data block than the one
 * the interrupted context expects.
 *
 * To help combat this possibility, additional state checking is performed
 * (such as using cmpxchg() even though set() would suffice). These extra
 * checks are commented as such and will hopefully catch any ABA issue that
 * a 32-bit system might experience.
 *
 * Memory Barriers
 * ~~~~~~~~~~~~~~~
 * Multiple memory barriers are used. To simplify proving correctness and
 * generating litmus tests, lines of code related to memory barriers
 * (loads, stores, and the associated memory barriers) are labeled::
 *
 *	LMM(function:letter)
 *
 * Comments reference the labels using only the "function:letter" part.
 *
 * The memory barrier pairs and their ordering are:
 *
 *   desc_reserve:D / desc_reserve:B
 *     push descriptor tail (id), then push descriptor head (id)
 *
 *   desc_reserve:D / data_push_tail:B
 *     push data tail (lpos), then set new descriptor reserved (state)
 *
 *   desc_reserve:D / desc_push_tail:C
 *     push descriptor tail (id), then set new descriptor reserved (state)
 *
 *   desc_reserve:D / prb_first_seq:C
 *     push descriptor tail (id), then set new descriptor reserved (state)
 *
 *   desc_reserve:F / desc_read:D
 *     set new descriptor id and reserved (state), then allow writer changes
 *
 *   data_alloc:A (or data_realloc:A) / desc_read:D
 *     set old descriptor reusable (state), then modify new data block area
 *
 *   data_alloc:A (or data_realloc:A) / data_push_tail:B
 *     push data tail (lpos), then modify new data block area
 *
 *   _prb_commit:B / desc_read:B
 *     store writer changes, then set new descriptor committed (state)
 *
 *   desc_reopen_last:A / _prb_commit:B
 *     set descriptor reserved (state), then read descriptor data
 *
 *   _prb_commit:B / desc_reserve:D
 *     set new descriptor committed (state), then check descriptor head (id)
 *
 *   data_push_tail:D / data_push_tail:A
 *     set descriptor reusable (state), then push data tail (lpos)
 *
 *   desc_push_tail:B / desc_reserve:D
 *     set descriptor reusable (state), then push descriptor tail (id)
 *
 *   desc_update_last_finalized:A / desc_last_finalized_seq:A
 *     store finalized record, then set new highest finalized sequence number
 */

#define DATA_SIZE(data_ring)		_DATA_SIZE((data_ring)->size_bits)
#define DATA_SIZE_MASK(data_ring)	(DATA_SIZE(data_ring) - 1)

#define DESCS_COUNT(desc_ring)		_DESCS_COUNT((desc_ring)->count_bits)
#define DESCS_COUNT_MASK(desc_ring)	(DESCS_COUNT(desc_ring) - 1)

/* Determine the data array index from a logical position. */
#define DATA_INDEX(data_ring, lpos)	((lpos) & DATA_SIZE_MASK(data_ring))

/* Determine the desc array index from an ID or sequence number. */
#define DESC_INDEX(desc_ring, n)	((n) & DESCS_COUNT_MASK(desc_ring))

/* Determine how many times the data array has wrapped. */
#define DATA_WRAPS(data_ring, lpos)	((lpos) >> (data_ring)->size_bits)

/* Determine if a logical position refers to a data-less block. */
#define LPOS_DATALESS(lpos)		((lpos) & 1UL)
#define BLK_DATALESS(blk)		(LPOS_DATALESS((blk)->begin) && \
					 LPOS_DATALESS((blk)->next))

/* Get the logical position at index 0 of the current wrap. */
#define DATA_THIS_WRAP_START_LPOS(data_ring, lpos) \
((lpos) & ~DATA_SIZE_MASK(data_ring))

/* Get the ID for the same index of the previous wrap as the given ID. */
#define DESC_ID_PREV_WRAP(desc_ring, id) \
DESC_ID((id) - DESCS_COUNT(desc_ring))

/*
 * A data block: mapped directly to the beginning of the data block area
 * specified as a logical position within the data ring.
 *
 * @id:   the ID of the associated descriptor
 * @data: the writer data
 *
 * Note that the size of a data block is only known by its associated
 * descriptor.
 */
struct prb_data_block {
	unsigned long	id;
	char		data[];
};

/*
 * Return the descriptor associated with @n. @n can be either a
 * descriptor ID or a sequence number.
 */
static struct prb_desc *to_desc(struct prb_desc_ring *desc_ring, u64 n)
{
	return &desc_ring->descs[DESC_INDEX(desc_ring, n)];
}

/*
 * Return the printk_info associated with @n. @n can be either a
 * descriptor ID or a sequence number.
 */
static struct printk_info *to_info(struct prb_desc_ring *desc_ring, u64 n)
{
	return &desc_ring->infos[DESC_INDEX(desc_ring, n)];
}

static struct prb_data_block *to_block(struct prb_data_ring *data_ring,
				       unsigned long begin_lpos)
{
	return (void *)&data_ring->data[DATA_INDEX(data_ring, begin_lpos)];
}

/*
 * Increase the data size to account for data block meta data plus any
 * padding so that the adjacent data block is aligned on the ID size.
 */
static unsigned int to_blk_size(unsigned int size)
{
	struct prb_data_block *db = NULL;

	size += sizeof(*db);
	size = ALIGN(size, sizeof(db->id));
	return size;
}

/*
 * Sanity checker for reserve size. The ringbuffer code assumes that a data
 * block does not exceed the maximum possible size that could fit within the
 * ringbuffer. This function provides that basic size check so that the
 * assumption is safe.
 */
static bool data_check_size(struct prb_data_ring *data_ring, unsigned int size)
{
	struct prb_data_block *db = NULL;

	if (size == 0)
		return true;

	/*
	 * Ensure the alignment padded size could possibly fit in the data
	 * array. The largest possible data block must still leave room for
	 * at least the ID of the next block.
	 */
	size = to_blk_size(size);
	if (size > DATA_SIZE(data_ring) - sizeof(db->id))
		return false;

	return true;
}

/* Query the state of a descriptor. */
static enum desc_state get_desc_state(unsigned long id,
				      unsigned long state_val)
{
	if (id != DESC_ID(state_val))
		return desc_miss;

	return DESC_STATE(state_val);
}

/*
 * Get a copy of a specified descriptor and return its queried state. If the
 * descriptor is in an inconsistent state (miss or reserved), the caller can
 * only expect the descriptor's @state_var field to be valid.
 *
 * The sequence number and caller_id can be optionally retrieved. Like all
 * non-state_var data, they are only valid if the descriptor is in a
 * consistent state.
 */
static enum desc_state desc_read(struct prb_desc_ring *desc_ring,
				 unsigned long id, struct prb_desc *desc_out,
				 u64 *seq_out, u32 *caller_id_out)
{
	struct printk_info *info = to_info(desc_ring, id);
	struct prb_desc *desc = to_desc(desc_ring, id);
	atomic_long_t *state_var = &desc->state_var;
	enum desc_state d_state;
	unsigned long state_val;

	/* Check the descriptor state. */
	state_val = atomic_long_read(state_var); /* LMM(desc_read:A) */
	d_state = get_desc_state(id, state_val);
	if (d_state == desc_miss || d_state == desc_reserved) {
		/*
		 * The descriptor is in an inconsistent state. Set at least
		 * @state_var so that the caller can see the details of
		 * the inconsistent state.
		 */
		goto out;
	}

	/*
	 * Guarantee the state is loaded before copying the descriptor
	 * content. This avoids copying obsolete descriptor content that might
	 * not apply to the descriptor state. This pairs with _prb_commit:B.
	 *
	 * Memory barrier involvement:
	 *
	 * If desc_read:A reads from _prb_commit:B, then desc_read:C reads
	 * from _prb_commit:A.
	 *
	 * Relies on:
	 *
	 * WMB from _prb_commit:A to _prb_commit:B
	 *    matching
	 * RMB from desc_read:A to desc_read:C
	 */
	smp_rmb(); /* LMM(desc_read:B) */

	/*
	 * Copy the descriptor data. The data is not valid until the
	 * state has been re-checked. A memcpy() for all of @desc
	 * cannot be used because of the atomic_t @state_var field.
	 */
	if (desc_out) {
		memcpy(&desc_out->text_blk_lpos, &desc->text_blk_lpos,
		       sizeof(desc_out->text_blk_lpos)); /* LMM(desc_read:C) */
	}
	if (seq_out)
		*seq_out = info->seq; /* also part of desc_read:C */
	if (caller_id_out)
		*caller_id_out = info->caller_id; /* also part of desc_read:C */

	/*
	 * 1. Guarantee the descriptor content is loaded before re-checking
	 *    the state. This avoids reading an obsolete descriptor state
	 *    that may not apply to the copied content. This pairs with
	 *    desc_reserve:F.
	 *
	 *    Memory barrier involvement:
	 *
	 *    If desc_read:C reads from desc_reserve:G, then desc_read:E
	 *    reads from desc_reserve:F.
	 *
	 *    Relies on:
	 *
	 *    WMB from desc_reserve:F to desc_reserve:G
	 *       matching
	 *    RMB from desc_read:C to desc_read:E
	 *
	 * 2. Guarantee the record data is loaded before re-checking the
	 *    state. This avoids reading an obsolete descriptor state that may
	 *    not apply to the copied data. This pairs with data_alloc:A and
	 *    data_realloc:A.
	 *
	 *    Memory barrier involvement:
	 *
	 *    If copy_data:A reads from data_alloc:B, then desc_read:E
	 *    reads from desc_make_reusable:A.
	 *
	 *    Relies on:
	 *
	 *    MB from desc_make_reusable:A to data_alloc:B
	 *       matching
	 *    RMB from desc_read:C to desc_read:E
	 *
	 *    Note: desc_make_reusable:A and data_alloc:B can be different
	 *          CPUs. However, the data_alloc:B CPU (which performs the
	 *          full memory barrier) must have previously seen
	 *          desc_make_reusable:A.
	 */
	smp_rmb(); /* LMM(desc_read:D) */

	/*
	 * The data has been copied. Return the current descriptor state,
	 * which may have changed since the load above.
	 */
	state_val = atomic_long_read(state_var); /* LMM(desc_read:E) */
	d_state = get_desc_state(id, state_val);
out:
	if (desc_out)
		atomic_long_set(&desc_out->state_var, state_val);
	return d_state;
}

/*
 * Take a specified descriptor out of the finalized state by attempting
 * the transition from finalized to reusable. Either this context or some
 * other context will have been successful.
 */
static void desc_make_reusable(struct prb_desc_ring *desc_ring,
			       unsigned long id)
{
	unsigned long val_finalized = DESC_SV(id, desc_finalized);
	unsigned long val_reusable = DESC_SV(id, desc_reusable);
	struct prb_desc *desc = to_desc(desc_ring, id);
	atomic_long_t *state_var = &desc->state_var;

	atomic_long_cmpxchg_relaxed(state_var, val_finalized,
				    val_reusable); /* LMM(desc_make_reusable:A) */
}

/*
 * Given the text data ring, put the associated descriptor of each
 * data block from @lpos_begin until @lpos_end into the reusable state.
 *
 * If there is any problem making the associated descriptor reusable, either
 * the descriptor has not yet been finalized or another writer context has
 * already pushed the tail lpos past the problematic data block. Regardless,
 * on error the caller can re-load the tail lpos to determine the situation.
 */
static bool data_make_reusable(struct printk_ringbuffer *rb,
			       unsigned long lpos_begin,
			       unsigned long lpos_end,
			       unsigned long *lpos_out)
{

	struct prb_data_ring *data_ring = &rb->text_data_ring;
	struct prb_desc_ring *desc_ring = &rb->desc_ring;
	struct prb_data_block *blk;
	enum desc_state d_state;
	struct prb_desc desc;
	struct prb_data_blk_lpos *blk_lpos = &desc.text_blk_lpos;
	unsigned long id;

	/* Loop until @lpos_begin has advanced to or beyond @lpos_end. */
	while ((lpos_end - lpos_begin) - 1 < DATA_SIZE(data_ring)) {
		blk = to_block(data_ring, lpos_begin);

		/*
		 * Load the block ID from the data block. This is a data race
		 * against a writer that may have newly reserved this data
		 * area. If the loaded value matches a valid descriptor ID,
		 * the blk_lpos of that descriptor will be checked to make
		 * sure it points back to this data block. If the check fails,
		 * the data area has been recycled by another writer.
		 */
		id = blk->id; /* LMM(data_make_reusable:A) */

		d_state = desc_read(desc_ring, id, &desc,
				    NULL, NULL); /* LMM(data_make_reusable:B) */

		switch (d_state) {
		case desc_miss:
		case desc_reserved:
		case desc_committed:
			return false;
		case desc_finalized:
			/*
			 * This data block is invalid if the descriptor
			 * does not point back to it.
			 */
			if (blk_lpos->begin != lpos_begin)
				return false;
			desc_make_reusable(desc_ring, id);
			break;
		case desc_reusable:
			/*
			 * This data block is invalid if the descriptor
			 * does not point back to it.
			 */
			if (blk_lpos->begin != lpos_begin)
				return false;
			break;
		}

		/* Advance @lpos_begin to the next data block. */
		lpos_begin = blk_lpos->next;
	}

	*lpos_out = lpos_begin;
	return true;
}

/*
 * Advance the data ring tail to at least @lpos. This function puts
 * descriptors into the reusable state if the tail is pushed beyond
 * their associated data block.
 */
static bool data_push_tail(struct printk_ringbuffer *rb, unsigned long lpos)
{
	struct prb_data_ring *data_ring = &rb->text_data_ring;
	unsigned long tail_lpos_new;
	unsigned long tail_lpos;
	unsigned long next_lpos;

	/* If @lpos is from a data-less block, there is nothing to do. */
	if (LPOS_DATALESS(lpos))
		return true;

	/*
	 * Any descriptor states that have transitioned to reusable due to the
	 * data tail being pushed to this loaded value will be visible to this
	 * CPU. This pairs with data_push_tail:D.
	 *
	 * Memory barrier involvement:
	 *
	 * If data_push_tail:A reads from data_push_tail:D, then this CPU can
	 * see desc_make_reusable:A.
	 *
	 * Relies on:
	 *
	 * MB from desc_make_reusable:A to data_push_tail:D
	 *    matches
	 * READFROM from data_push_tail:D to data_push_tail:A
	 *    thus
	 * READFROM from desc_make_reusable:A to this CPU
	 */
	tail_lpos = atomic_long_read(&data_ring->tail_lpos); /* LMM(data_push_tail:A) */

	/*
	 * Loop until the tail lpos is at or beyond @lpos. This condition
	 * may already be satisfied, resulting in no full memory barrier
	 * from data_push_tail:D being performed. However, since this CPU
	 * sees the new tail lpos, any descriptor states that transitioned to
	 * the reusable state must already be visible.
	 */
	while ((lpos - tail_lpos) - 1 < DATA_SIZE(data_ring)) {
		/*
		 * Make all descriptors reusable that are associated with
		 * data blocks before @lpos.
		 */
		if (!data_make_reusable(rb, tail_lpos, lpos, &next_lpos)) {
			/*
			 * 1. Guarantee the block ID loaded in
			 *    data_make_reusable() is performed before
			 *    reloading the tail lpos. The failed
			 *    data_make_reusable() may be due to a newly
			 *    recycled data area causing the tail lpos to
			 *    have been previously pushed. This pairs with
			 *    data_alloc:A and data_realloc:A.
			 *
			 *    Memory barrier involvement:
			 *
			 *    If data_make_reusable:A reads from data_alloc:B,
			 *    then data_push_tail:C reads from
			 *    data_push_tail:D.
			 *
			 *    Relies on:
			 *
			 *    MB from data_push_tail:D to data_alloc:B
			 *       matching
			 *    RMB from data_make_reusable:A to
			 *    data_push_tail:C
			 *
			 *    Note: data_push_tail:D and data_alloc:B can be
			 *          different CPUs. However, the data_alloc:B
			 *          CPU (which performs the full memory
			 *          barrier) must have previously seen
			 *          data_push_tail:D.
			 *
			 * 2. Guarantee the descriptor state loaded in
			 *    data_make_reusable() is performed before
			 *    reloading the tail lpos. The failed
			 *    data_make_reusable() may be due to a newly
			 *    recycled descriptor causing the tail lpos to
			 *    have been previously pushed. This pairs with
			 *    desc_reserve:D.
			 *
			 *    Memory barrier involvement:
			 *
			 *    If data_make_reusable:B reads from
			 *    desc_reserve:F, then data_push_tail:C reads
			 *    from data_push_tail:D.
			 *
			 *    Relies on:
			 *
			 *    MB from data_push_tail:D to desc_reserve:F
			 *       matching
			 *    RMB from data_make_reusable:B to
			 *    data_push_tail:C
			 *
			 *    Note: data_push_tail:D and desc_reserve:F can
			 *          be different CPUs. However, the
			 *          desc_reserve:F CPU (which performs the
			 *          full memory barrier) must have previously
			 *          seen data_push_tail:D.
			 */
			smp_rmb(); /* LMM(data_push_tail:B) */

			tail_lpos_new = atomic_long_read(&data_ring->tail_lpos
							); /* LMM(data_push_tail:C) */
			if (tail_lpos_new == tail_lpos)
				return false;

			/* Another CPU pushed the tail. Try again. */
			tail_lpos = tail_lpos_new;
			continue;
		}

		/*
		 * Guarantee any descriptor states that have transitioned to
		 * reusable are stored before pushing the tail lpos. A full
		 * memory barrier is needed since other CPUs may have made
		 * the descriptor states reusable. This pairs with
		 * data_push_tail:A.
		 */
		if (atomic_long_try_cmpxchg(&data_ring->tail_lpos, &tail_lpos,
					    next_lpos)) { /* LMM(data_push_tail:D) */
			break;
		}
	}

	return true;
}

/*
 * Advance the desc ring tail. This function advances the tail by one
 * descriptor, thus invalidating the oldest descriptor. Before advancing
 * the tail, the tail descriptor is made reusable and all data blocks up to
 * and including the descriptor's data block are invalidated (i.e. the data
 * ring tail is pushed past the data block of the descriptor being made
 * reusable).
 */
static bool desc_push_tail(struct printk_ringbuffer *rb,
			   unsigned long tail_id)
{
	struct prb_desc_ring *desc_ring = &rb->desc_ring;
	enum desc_state d_state;
	struct prb_desc desc;

	d_state = desc_read(desc_ring, tail_id, &desc, NULL, NULL);

	switch (d_state) {
	case desc_miss:
		/*
		 * If the ID is exactly 1 wrap behind the expected, it is
		 * in the process of being reserved by another writer and
		 * must be considered reserved.
		 */
		if (DESC_ID(atomic_long_read(&desc.state_var)) ==
		    DESC_ID_PREV_WRAP(desc_ring, tail_id)) {
			return false;
		}

		/*
		 * The ID has changed. Another writer must have pushed the
		 * tail and recycled the descriptor already. Success is
		 * returned because the caller is only interested in the
		 * specified tail being pushed, which it was.
		 */
		return true;
	case desc_reserved:
	case desc_committed:
		return false;
	case desc_finalized:
		desc_make_reusable(desc_ring, tail_id);
		break;
	case desc_reusable:
		break;
	}

	/*
	 * Data blocks must be invalidated before their associated
	 * descriptor can be made available for recycling. Invalidating
	 * them later is not possible because there is no way to trust
	 * data blocks once their associated descriptor is gone.
	 */

	if (!data_push_tail(rb, desc.text_blk_lpos.next))
		return false;

	/*
	 * Check the next descriptor after @tail_id before pushing the tail
	 * to it because the tail must always be in a finalized or reusable
	 * state. The implementation of prb_first_seq() relies on this.
	 *
	 * A successful read implies that the next descriptor is less than or
	 * equal to @head_id so there is no risk of pushing the tail past the
	 * head.
	 */
	d_state = desc_read(desc_ring, DESC_ID(tail_id + 1), &desc,
			    NULL, NULL); /* LMM(desc_push_tail:A) */

	if (d_state == desc_finalized || d_state == desc_reusable) {
		/*
		 * Guarantee any descriptor states that have transitioned to
		 * reusable are stored before pushing the tail ID. This allows
		 * verifying the recycled descriptor state. A full memory
		 * barrier is needed since other CPUs may have made the
		 * descriptor states reusable. This pairs with desc_reserve:D.
		 */
		atomic_long_cmpxchg(&desc_ring->tail_id, tail_id,
				    DESC_ID(tail_id + 1)); /* LMM(desc_push_tail:B) */
	} else {
		/*
		 * Guarantee the last state load from desc_read() is before
		 * reloading @tail_id in order to see a new tail ID in the
		 * case that the descriptor has been recycled. This pairs
		 * with desc_reserve:D.
		 *
		 * Memory barrier involvement:
		 *
		 * If desc_push_tail:A reads from desc_reserve:F, then
		 * desc_push_tail:D reads from desc_push_tail:B.
		 *
		 * Relies on:
		 *
		 * MB from desc_push_tail:B to desc_reserve:F
		 *    matching
		 * RMB from desc_push_tail:A to desc_push_tail:D
		 *
		 * Note: desc_push_tail:B and desc_reserve:F can be different
		 *       CPUs. However, the desc_reserve:F CPU (which performs
		 *       the full memory barrier) must have previously seen
		 *       desc_push_tail:B.
		 */
		smp_rmb(); /* LMM(desc_push_tail:C) */

		/*
		 * Re-check the tail ID. The descriptor following @tail_id is
		 * not in an allowed tail state. But if the tail has since
		 * been moved by another CPU, then it does not matter.
		 */
		if (atomic_long_read(&desc_ring->tail_id) == tail_id) /* LMM(desc_push_tail:D) */
			return false;
	}

	return true;
}

/* Reserve a new descriptor, invalidating the oldest if necessary. */
static bool desc_reserve(struct printk_ringbuffer *rb, unsigned long *id_out)
{
	struct prb_desc_ring *desc_ring = &rb->desc_ring;
	unsigned long prev_state_val;
	unsigned long id_prev_wrap;
	struct prb_desc *desc;
	unsigned long head_id;
	unsigned long id;

	head_id = atomic_long_read(&desc_ring->head_id); /* LMM(desc_reserve:A) */

	do {
		id = DESC_ID(head_id + 1);
		id_prev_wrap = DESC_ID_PREV_WRAP(desc_ring, id);

		/*
		 * Guarantee the head ID is read before reading the tail ID.
		 * Since the tail ID is updated before the head ID, this
		 * guarantees that @id_prev_wrap is never ahead of the tail
		 * ID. This pairs with desc_reserve:D.
		 *
		 * Memory barrier involvement:
		 *
		 * If desc_reserve:A reads from desc_reserve:D, then
		 * desc_reserve:C reads from desc_push_tail:B.
		 *
		 * Relies on:
		 *
		 * MB from desc_push_tail:B to desc_reserve:D
		 *    matching
		 * RMB from desc_reserve:A to desc_reserve:C
		 *
		 * Note: desc_push_tail:B and desc_reserve:D can be different
		 *       CPUs. However, the desc_reserve:D CPU (which performs
		 *       the full memory barrier) must have previously seen
		 *       desc_push_tail:B.
		 */
		smp_rmb(); /* LMM(desc_reserve:B) */

		if (id_prev_wrap == atomic_long_read(&desc_ring->tail_id
						    )) { /* LMM(desc_reserve:C) */
			/*
			 * Make space for the new descriptor by
			 * advancing the tail.
			 */
			if (!desc_push_tail(rb, id_prev_wrap))
				return false;
		}

		/*
		 * 1. Guarantee the tail ID is read before validating the
		 *    recycled descriptor state. A read memory barrier is
		 *    sufficient for this. This pairs with desc_push_tail:B.
		 *
		 *    Memory barrier involvement:
		 *
		 *    If desc_reserve:C reads from desc_push_tail:B, then
		 *    desc_reserve:E reads from desc_make_reusable:A.
		 *
		 *    Relies on:
		 *
		 *    MB from desc_make_reusable:A to desc_push_tail:B
		 *       matching
		 *    RMB from desc_reserve:C to desc_reserve:E
		 *
		 *    Note: desc_make_reusable:A and desc_push_tail:B can be
		 *          different CPUs. However, the desc_push_tail:B CPU
		 *          (which performs the full memory barrier) must have
		 *          previously seen desc_make_reusable:A.
		 *
		 * 2. Guarantee the tail ID is stored before storing the head
		 *    ID. This pairs with desc_reserve:B.
		 *
		 * 3. Guarantee any data ring tail changes are stored before
		 *    recycling the descriptor. Data ring tail changes can
		 *    happen via desc_push_tail()->data_push_tail(). A full
		 *    memory barrier is needed since another CPU may have
		 *    pushed the data ring tails. This pairs with
		 *    data_push_tail:B.
		 *
		 * 4. Guarantee a new tail ID is stored before recycling the
		 *    descriptor. A full memory barrier is needed since
		 *    another CPU may have pushed the tail ID. This pairs
		 *    with desc_push_tail:C and this also pairs with
		 *    prb_first_seq:C.
		 *
		 * 5. Guarantee the head ID is stored before trying to
		 *    finalize the previous descriptor. This pairs with
		 *    _prb_commit:B.
		 */
	} while (!atomic_long_try_cmpxchg(&desc_ring->head_id, &head_id,
					  id)); /* LMM(desc_reserve:D) */

	desc = to_desc(desc_ring, id);

	/*
	 * If the descriptor has been recycled, verify the old state val.
	 * See "ABA Issues" about why this verification is performed.
	 */
	prev_state_val = atomic_long_read(&desc->state_var); /* LMM(desc_reserve:E) */
	if (prev_state_val &&
	    get_desc_state(id_prev_wrap, prev_state_val) != desc_reusable) {
		WARN_ON_ONCE(1);
		return false;
	}

	/*
	 * Assign the descriptor a new ID and set its state to reserved.
	 * See "ABA Issues" about why cmpxchg() instead of set() is used.
	 *
	 * Guarantee the new descriptor ID and state is stored before making
	 * any other changes. A write memory barrier is sufficient for this.
	 * This pairs with desc_read:D.
	 */
	if (!atomic_long_try_cmpxchg(&desc->state_var, &prev_state_val,
			DESC_SV(id, desc_reserved))) { /* LMM(desc_reserve:F) */
		WARN_ON_ONCE(1);
		return false;
	}

	/* Now data in @desc can be modified: LMM(desc_reserve:G) */

	*id_out = id;
	return true;
}

/* Determine the end of a data block. */
static unsigned long get_next_lpos(struct prb_data_ring *data_ring,
				   unsigned long lpos, unsigned int size)
{
	unsigned long begin_lpos;
	unsigned long next_lpos;

	begin_lpos = lpos;
	next_lpos = lpos + size;

	/* First check if the data block does not wrap. */
	if (DATA_WRAPS(data_ring, begin_lpos) == DATA_WRAPS(data_ring, next_lpos))
		return next_lpos;

	/* Wrapping data blocks store their data at the beginning. */
	return (DATA_THIS_WRAP_START_LPOS(data_ring, next_lpos) + size);
}

/*
 * Allocate a new data block, invalidating the oldest data block(s)
 * if necessary. This function also associates the data block with
 * a specified descriptor.
 */
static char *data_alloc(struct printk_ringbuffer *rb, unsigned int size,
			struct prb_data_blk_lpos *blk_lpos, unsigned long id)
{
	struct prb_data_ring *data_ring = &rb->text_data_ring;
	struct prb_data_block *blk;
	unsigned long begin_lpos;
	unsigned long next_lpos;

	if (size == 0) {
		/* Specify a data-less block. */
		blk_lpos->begin = NO_LPOS;
		blk_lpos->next = NO_LPOS;
		return NULL;
	}

	size = to_blk_size(size);

	begin_lpos = atomic_long_read(&data_ring->head_lpos);

	do {
		next_lpos = get_next_lpos(data_ring, begin_lpos, size);

		if (!data_push_tail(rb, next_lpos - DATA_SIZE(data_ring))) {
			/* Failed to allocate, specify a data-less block. */
			blk_lpos->begin = FAILED_LPOS;
			blk_lpos->next = FAILED_LPOS;
			return NULL;
		}

		/*
		 * 1. Guarantee any descriptor states that have transitioned
		 *    to reusable are stored before modifying the newly
		 *    allocated data area. A full memory barrier is needed
		 *    since other CPUs may have made the descriptor states
		 *    reusable. See data_push_tail:A about why the reusable
		 *    states are visible. This pairs with desc_read:D.
		 *
		 * 2. Guarantee any updated tail lpos is stored before
		 *    modifying the newly allocated data area. Another CPU may
		 *    be in data_make_reusable() and is reading a block ID
		 *    from this area. data_make_reusable() can handle reading
		 *    a garbage block ID value, but then it must be able to
		 *    load a new tail lpos. A full memory barrier is needed
		 *    since other CPUs may have updated the tail lpos. This
		 *    pairs with data_push_tail:B.
		 */
	} while (!atomic_long_try_cmpxchg(&data_ring->head_lpos, &begin_lpos,
					  next_lpos)); /* LMM(data_alloc:A) */

	blk = to_block(data_ring, begin_lpos);
	blk->id = id; /* LMM(data_alloc:B) */

	if (DATA_WRAPS(data_ring, begin_lpos) != DATA_WRAPS(data_ring, next_lpos)) {
		/* Wrapping data blocks store their data at the beginning. */
		blk = to_block(data_ring, 0);

		/*
		 * Store the ID on the wrapped block for consistency.
		 * The printk_ringbuffer does not actually use it.
		 */
		blk->id = id;
	}

	blk_lpos->begin = begin_lpos;
	blk_lpos->next = next_lpos;

	return &blk->data[0];
}

/*
 * Try to resize an existing data block associated with the descriptor
 * specified by @id. If the resized data block should become wrapped, it
 * copies the old data to the new data block. If @size yields a data block
 * with the same or less size, the data block is left as is.
 *
 * Fail if this is not the last allocated data block or if there is not
 * enough space or it is not possible make enough space.
 *
 * Return a pointer to the beginning of the entire data buffer or NULL on
 * failure.
 */
static char *data_realloc(struct printk_ringbuffer *rb, unsigned int size,
			  struct prb_data_blk_lpos *blk_lpos, unsigned long id)
{
	struct prb_data_ring *data_ring = &rb->text_data_ring;
	struct prb_data_block *blk;
	unsigned long head_lpos;
	unsigned long next_lpos;
	bool wrapped;

	/* Reallocation only works if @blk_lpos is the newest data block. */
	head_lpos = atomic_long_read(&data_ring->head_lpos);
	if (head_lpos != blk_lpos->next)
		return NULL;

	/* Keep track if @blk_lpos was a wrapping data block. */
	wrapped = (DATA_WRAPS(data_ring, blk_lpos->begin) != DATA_WRAPS(data_ring, blk_lpos->next));

	size = to_blk_size(size);

	next_lpos = get_next_lpos(data_ring, blk_lpos->begin, size);

	/* If the data block does not increase, there is nothing to do. */
	if (head_lpos - next_lpos < DATA_SIZE(data_ring)) {
		if (wrapped)
			blk = to_block(data_ring, 0);
		else
			blk = to_block(data_ring, blk_lpos->begin);
		return &blk->data[0];
	}

	if (!data_push_tail(rb, next_lpos - DATA_SIZE(data_ring)))
		return NULL;

	/* The memory barrier involvement is the same as data_alloc:A. */
	if (!atomic_long_try_cmpxchg(&data_ring->head_lpos, &head_lpos,
				     next_lpos)) { /* LMM(data_realloc:A) */
		return NULL;
	}

	blk = to_block(data_ring, blk_lpos->begin);

	if (DATA_WRAPS(data_ring, blk_lpos->begin) != DATA_WRAPS(data_ring, next_lpos)) {
		struct prb_data_block *old_blk = blk;

		/* Wrapping data blocks store their data at the beginning. */
		blk = to_block(data_ring, 0);

		/*
		 * Store the ID on the wrapped block for consistency.
		 * The printk_ringbuffer does not actually use it.
		 */
		blk->id = id;

		if (!wrapped) {
			/*
			 * Since the allocated space is now in the newly
			 * created wrapping data block, copy the content
			 * from the old data block.
			 */
			memcpy(&blk->data[0], &old_blk->data[0],
			       (blk_lpos->next - blk_lpos->begin) - sizeof(blk->id));
		}
	}

	blk_lpos->next = next_lpos;

	return &blk->data[0];
}

/* Return the number of bytes used by a data block. */
static unsigned int space_used(struct prb_data_ring *data_ring,
			       struct prb_data_blk_lpos *blk_lpos)
{
	/* Data-less blocks take no space. */
	if (BLK_DATALESS(blk_lpos))
		return 0;

	if (DATA_WRAPS(data_ring, blk_lpos->begin) == DATA_WRAPS(data_ring, blk_lpos->next)) {
		/* Data block does not wrap. */
		return (DATA_INDEX(data_ring, blk_lpos->next) -
			DATA_INDEX(data_ring, blk_lpos->begin));
	}

	/*
	 * For wrapping data blocks, the trailing (wasted) space is
	 * also counted.
	 */
	return (DATA_INDEX(data_ring, blk_lpos->next) +
		DATA_SIZE(data_ring) - DATA_INDEX(data_ring, blk_lpos->begin));
}

/*
 * Given @blk_lpos, return a pointer to the writer data from the data block
 * and calculate the size of the data part. A NULL pointer is returned if
 * @blk_lpos specifies values that could never be legal.
 *
 * This function (used by readers) performs strict validation on the lpos
 * values to possibly detect bugs in the writer code. A WARN_ON_ONCE() is
 * triggered if an internal error is detected.
 */
static const char *get_data(struct prb_data_ring *data_ring,
			    struct prb_data_blk_lpos *blk_lpos,
			    unsigned int *data_size)
{
	struct prb_data_block *db;

	/* Data-less data block description. */
	if (BLK_DATALESS(blk_lpos)) {
		if (blk_lpos->begin == NO_LPOS && blk_lpos->next == NO_LPOS) {
			*data_size = 0;
			return "";
		}
		return NULL;
	}

	/* Regular data block: @begin less than @next and in same wrap. */
	if (DATA_WRAPS(data_ring, blk_lpos->begin) == DATA_WRAPS(data_ring, blk_lpos->next) &&
	    blk_lpos->begin < blk_lpos->next) {
		db = to_block(data_ring, blk_lpos->begin);
		*data_size = blk_lpos->next - blk_lpos->begin;

	/* Wrapping data block: @begin is one wrap behind @next. */
	} else if (DATA_WRAPS(data_ring, blk_lpos->begin + DATA_SIZE(data_ring)) ==
		   DATA_WRAPS(data_ring, blk_lpos->next)) {
		db = to_block(data_ring, 0);
		*data_size = DATA_INDEX(data_ring, blk_lpos->next);

	/* Illegal block description. */
	} else {
		WARN_ON_ONCE(1);
		return NULL;
	}

	/* A valid data block will always be aligned to the ID size. */
	if (WARN_ON_ONCE(blk_lpos->begin != ALIGN(blk_lpos->begin, sizeof(db->id))) ||
	    WARN_ON_ONCE(blk_lpos->next != ALIGN(blk_lpos->next, sizeof(db->id)))) {
		return NULL;
	}

	/* A valid data block will always have at least an ID. */
	if (WARN_ON_ONCE(*data_size < sizeof(db->id)))
		return NULL;

	/* Subtract block ID space from size to reflect data size. */
	*data_size -= sizeof(db->id);

	return &db->data[0];
}

/*
 * Attempt to transition the newest descriptor from committed back to reserved
 * so that the record can be modified by a writer again. This is only possible
 * if the descriptor is not yet finalized and the provided @caller_id matches.
 */
static struct prb_desc *desc_reopen_last(struct prb_desc_ring *desc_ring,
					 u32 caller_id, unsigned long *id_out)
{
	unsigned long prev_state_val;
	enum desc_state d_state;
	struct prb_desc desc;
	struct prb_desc *d;
	unsigned long id;
	u32 cid;

	id = atomic_long_read(&desc_ring->head_id);

	/*
	 * To reduce unnecessarily reopening, first check if the descriptor
	 * state and caller ID are correct.
	 */
	d_state = desc_read(desc_ring, id, &desc, NULL, &cid);
	if (d_state != desc_committed || cid != caller_id)
		return NULL;

	d = to_desc(desc_ring, id);

	prev_state_val = DESC_SV(id, desc_committed);

	/*
	 * Guarantee the reserved state is stored before reading any
	 * record data. A full memory barrier is needed because @state_var
	 * modification is followed by reading. This pairs with _prb_commit:B.
	 *
	 * Memory barrier involvement:
	 *
	 * If desc_reopen_last:A reads from _prb_commit:B, then
	 * prb_reserve_in_last:A reads from _prb_commit:A.
	 *
	 * Relies on:
	 *
	 * WMB from _prb_commit:A to _prb_commit:B
	 *    matching
	 * MB If desc_reopen_last:A to prb_reserve_in_last:A
	 */
	if (!atomic_long_try_cmpxchg(&d->state_var, &prev_state_val,
			DESC_SV(id, desc_reserved))) { /* LMM(desc_reopen_last:A) */
		return NULL;
	}

	*id_out = id;
	return d;
}

/**
 * prb_reserve_in_last() - Re-reserve and extend the space in the ringbuffer
 *                         used by the newest record.
 *
 * @e:         The entry structure to setup.
 * @rb:        The ringbuffer to re-reserve and extend data in.
 * @r:         The record structure to allocate buffers for.
 * @caller_id: The caller ID of the caller (reserving writer).
 * @max_size:  Fail if the extended size would be greater than this.
 *
 * This is the public function available to writers to re-reserve and extend
 * data.
 *
 * The writer specifies the text size to extend (not the new total size) by
 * setting the @text_buf_size field of @r. To ensure proper initialization
 * of @r, prb_rec_init_wr() should be used.
 *
 * This function will fail if @caller_id does not match the caller ID of the
 * newest record. In that case the caller must reserve new data using
 * prb_reserve().
 *
 * Context: Any context. Disables local interrupts on success.
 * Return: true if text data could be extended, otherwise false.
 *
 * On success:
 *
 *   - @r->text_buf points to the beginning of the entire text buffer.
 *
 *   - @r->text_buf_size is set to the new total size of the buffer.
 *
 *   - @r->info is not touched so that @r->info->text_len could be used
 *     to append the text.
 *
 *   - prb_record_text_space() can be used on @e to query the new
 *     actually used space.
 *
 * Important: All @r->info fields will already be set with the current values
 *            for the record. I.e. @r->info->text_len will be less than
 *            @text_buf_size. Writers can use @r->info->text_len to know
 *            where concatenation begins and writers should update
 *            @r->info->text_len after concatenating.
 */
bool prb_reserve_in_last(struct prb_reserved_entry *e, struct printk_ringbuffer *rb,
			 struct printk_record *r, u32 caller_id, unsigned int max_size)
{
	struct prb_desc_ring *desc_ring = &rb->desc_ring;
	struct printk_info *info;
	unsigned int data_size;
	struct prb_desc *d;
	unsigned long id;

	local_irq_save(e->irqflags);

	/* Transition the newest descriptor back to the reserved state. */
	d = desc_reopen_last(desc_ring, caller_id, &id);
	if (!d) {
		local_irq_restore(e->irqflags);
		goto fail_reopen;
	}

	/* Now the writer has exclusive access: LMM(prb_reserve_in_last:A) */

	info = to_info(desc_ring, id);

	/*
	 * Set the @e fields here so that prb_commit() can be used if
	 * anything fails from now on.
	 */
	e->rb = rb;
	e->id = id;

	/*
	 * desc_reopen_last() checked the caller_id, but there was no
	 * exclusive access at that point. The descriptor may have
	 * changed since then.
	 */
	if (caller_id != info->caller_id)
		goto fail;

	if (BLK_DATALESS(&d->text_blk_lpos)) {
		if (WARN_ON_ONCE(info->text_len != 0)) {
			pr_warn_once("wrong text_len value (%hu, expecting 0)\n",
				     info->text_len);
			info->text_len = 0;
		}

		if (!data_check_size(&rb->text_data_ring, r->text_buf_size))
			goto fail;

		if (r->text_buf_size > max_size)
			goto fail;

		r->text_buf = data_alloc(rb, r->text_buf_size,
					 &d->text_blk_lpos, id);
	} else {
		if (!get_data(&rb->text_data_ring, &d->text_blk_lpos, &data_size))
			goto fail;

		/*
		 * Increase the buffer size to include the original size. If
		 * the meta data (@text_len) is not sane, use the full data
		 * block size.
		 */
		if (WARN_ON_ONCE(info->text_len > data_size)) {
			pr_warn_once("wrong text_len value (%hu, expecting <=%u)\n",
				     info->text_len, data_size);
			info->text_len = data_size;
		}
		r->text_buf_size += info->text_len;

		if (!data_check_size(&rb->text_data_ring, r->text_buf_size))
			goto fail;

		if (r->text_buf_size > max_size)
			goto fail;

		r->text_buf = data_realloc(rb, r->text_buf_size,
					   &d->text_blk_lpos, id);
	}
	if (r->text_buf_size && !r->text_buf)
		goto fail;

	r->info = info;

	e->text_space = space_used(&rb->text_data_ring, &d->text_blk_lpos);

	return true;
fail:
	prb_commit(e);
	/* prb_commit() re-enabled interrupts. */
fail_reopen:
	/* Make it clear to the caller that the re-reserve failed. */
	memset(r, 0, sizeof(*r));
	return false;
}

/*
 * @last_finalized_seq value guarantees that all records up to and including
 * this sequence number are finalized and can be read. The only exception are
 * too old records which have already been overwritten.
 *
 * It is also guaranteed that @last_finalized_seq only increases.
 *
 * Be aware that finalized records following non-finalized records are not
 * reported because they are not yet available to the reader. For example,
 * a new record stored via printk() will not be available to a printer if
 * it follows a record that has not been finalized yet. However, once that
 * non-finalized record becomes finalized, @last_finalized_seq will be
 * appropriately updated and the full set of finalized records will be
 * available to the printer. And since each printk() caller will either
 * directly print or trigger deferred printing of all available unprinted
 * records, all printk() messages will get printed.
 */
static u64 desc_last_finalized_seq(struct printk_ringbuffer *rb)
{
	struct prb_desc_ring *desc_ring = &rb->desc_ring;
	unsigned long ulseq;

	/*
	 * Guarantee the sequence number is loaded before loading the
	 * associated record in order to guarantee that the record can be
	 * seen by this CPU. This pairs with desc_update_last_finalized:A.
	 */
	ulseq = atomic_long_read_acquire(&desc_ring->last_finalized_seq
					); /* LMM(desc_last_finalized_seq:A) */

	return __ulseq_to_u64seq(rb, ulseq);
}

static bool _prb_read_valid(struct printk_ringbuffer *rb, u64 *seq,
			    struct printk_record *r, unsigned int *line_count);

/*
 * Check if there are records directly following @last_finalized_seq that are
 * finalized. If so, update @last_finalized_seq to the latest of these
 * records. It is not allowed to skip over records that are not yet finalized.
 */
static void desc_update_last_finalized(struct printk_ringbuffer *rb)
{
	struct prb_desc_ring *desc_ring = &rb->desc_ring;
	u64 old_seq = desc_last_finalized_seq(rb);
	unsigned long oldval;
	unsigned long newval;
	u64 finalized_seq;
	u64 try_seq;

try_again:
	finalized_seq = old_seq;
	try_seq = finalized_seq + 1;

	/* Try to find later finalized records. */
	while (_prb_read_valid(rb, &try_seq, NULL, NULL)) {
		finalized_seq = try_seq;
		try_seq++;
	}

	/* No update needed if no later finalized record was found. */
	if (finalized_seq == old_seq)
		return;

	oldval = __u64seq_to_ulseq(old_seq);
	newval = __u64seq_to_ulseq(finalized_seq);

	/*
	 * Set the sequence number of a later finalized record that has been
	 * seen.
	 *
	 * Guarantee the record data is visible to other CPUs before storing
	 * its sequence number. This pairs with desc_last_finalized_seq:A.
	 *
	 * Memory barrier involvement:
	 *
	 * If desc_last_finalized_seq:A reads from
	 * desc_update_last_finalized:A, then desc_read:A reads from
	 * _prb_commit:B.
	 *
	 * Relies on:
	 *
	 * RELEASE from _prb_commit:B to desc_update_last_finalized:A
	 *    matching
	 * ACQUIRE from desc_last_finalized_seq:A to desc_read:A
	 *
	 * Note: _prb_commit:B and desc_update_last_finalized:A can be
	 *       different CPUs. However, the desc_update_last_finalized:A
	 *       CPU (which performs the release) must have previously seen
	 *       _prb_commit:B.
	 */
	if (!atomic_long_try_cmpxchg_release(&desc_ring->last_finalized_seq,
				&oldval, newval)) { /* LMM(desc_update_last_finalized:A) */
		old_seq = __ulseq_to_u64seq(rb, oldval);
		goto try_again;
	}
}

/*
 * Attempt to finalize a specified descriptor. If this fails, the descriptor
 * is either already final or it will finalize itself when the writer commits.
 */
static void desc_make_final(struct printk_ringbuffer *rb, unsigned long id)
{
	struct prb_desc_ring *desc_ring = &rb->desc_ring;
	unsigned long prev_state_val = DESC_SV(id, desc_committed);
	struct prb_desc *d = to_desc(desc_ring, id);

	if (atomic_long_try_cmpxchg_relaxed(&d->state_var, &prev_state_val,
			DESC_SV(id, desc_finalized))) { /* LMM(desc_make_final:A) */
		desc_update_last_finalized(rb);
	}
}

/**
 * prb_reserve() - Reserve space in the ringbuffer.
 *
 * @e:  The entry structure to setup.
 * @rb: The ringbuffer to reserve data in.
 * @r:  The record structure to allocate buffers for.
 *
 * This is the public function available to writers to reserve data.
 *
 * The writer specifies the text size to reserve by setting the
 * @text_buf_size field of @r. To ensure proper initialization of @r,
 * prb_rec_init_wr() should be used.
 *
 * Context: Any context. Disables local interrupts on success.
 * Return: true if at least text data could be allocated, otherwise false.
 *
 * On success, the fields @info and @text_buf of @r will be set by this
 * function and should be filled in by the writer before committing. Also
 * on success, prb_record_text_space() can be used on @e to query the actual
 * space used for the text data block.
 *
 * Important: @info->text_len needs to be set correctly by the writer in
 *            order for data to be readable and/or extended. Its value
 *            is initialized to 0.
 */
bool prb_reserve(struct prb_reserved_entry *e, struct printk_ringbuffer *rb,
		 struct printk_record *r)
{
	struct prb_desc_ring *desc_ring = &rb->desc_ring;
	struct printk_info *info;
	struct prb_desc *d;
	unsigned long id;
	u64 seq;

	if (!data_check_size(&rb->text_data_ring, r->text_buf_size))
		goto fail;

	/*
	 * Descriptors in the reserved state act as blockers to all further
	 * reservations once the desc_ring has fully wrapped. Disable
	 * interrupts during the reserve/commit window in order to minimize
	 * the likelihood of this happening.
	 */
	local_irq_save(e->irqflags);

	if (!desc_reserve(rb, &id)) {
		/* Descriptor reservation failures are tracked. */
		atomic_long_inc(&rb->fail);
		local_irq_restore(e->irqflags);
		goto fail;
	}

	d = to_desc(desc_ring, id);
	info = to_info(desc_ring, id);

	/*
	 * All @info fields (except @seq) are cleared and must be filled in
	 * by the writer. Save @seq before clearing because it is used to
	 * determine the new sequence number.
	 */
	seq = info->seq;
	memset(info, 0, sizeof(*info));

	/*
	 * Set the @e fields here so that prb_commit() can be used if
	 * text data allocation fails.
	 */
	e->rb = rb;
	e->id = id;

	/*
	 * Initialize the sequence number if it has "never been set".
	 * Otherwise just increment it by a full wrap.
	 *
	 * @seq is considered "never been set" if it has a value of 0,
	 * _except_ for @infos[0], which was specially setup by the ringbuffer
	 * initializer and therefore is always considered as set.
	 *
	 * See the "Bootstrap" comment block in printk_ringbuffer.h for
	 * details about how the initializer bootstraps the descriptors.
	 */
	if (seq == 0 && DESC_INDEX(desc_ring, id) != 0)
		info->seq = DESC_INDEX(desc_ring, id);
	else
		info->seq = seq + DESCS_COUNT(desc_ring);

	/*
	 * New data is about to be reserved. Once that happens, previous
	 * descriptors are no longer able to be extended. Finalize the
	 * previous descriptor now so that it can be made available to
	 * readers. (For seq==0 there is no previous descriptor.)
	 */
	if (info->seq > 0)
		desc_make_final(rb, DESC_ID(id - 1));

	r->text_buf = data_alloc(rb, r->text_buf_size, &d->text_blk_lpos, id);
	/* If text data allocation fails, a data-less record is committed. */
	if (r->text_buf_size && !r->text_buf) {
		prb_commit(e);
		/* prb_commit() re-enabled interrupts. */
		goto fail;
	}

	r->info = info;

	/* Record full text space used by record. */
	e->text_space = space_used(&rb->text_data_ring, &d->text_blk_lpos);

	return true;
fail:
	/* Make it clear to the caller that the reserve failed. */
	memset(r, 0, sizeof(*r));
	return false;
}

/* Commit the data (possibly finalizing it) and restore interrupts. */
static void _prb_commit(struct prb_reserved_entry *e, unsigned long state_val)
{
	struct prb_desc_ring *desc_ring = &e->rb->desc_ring;
	struct prb_desc *d = to_desc(desc_ring, e->id);
	unsigned long prev_state_val = DESC_SV(e->id, desc_reserved);

	/* Now the writer has finished all writing: LMM(_prb_commit:A) */

	/*
	 * Set the descriptor as committed. See "ABA Issues" about why
	 * cmpxchg() instead of set() is used.
	 *
	 * 1  Guarantee all record data is stored before the descriptor state
	 *    is stored as committed. A write memory barrier is sufficient
	 *    for this. This pairs with desc_read:B and desc_reopen_last:A.
	 *
	 * 2. Guarantee the descriptor state is stored as committed before
	 *    re-checking the head ID in order to possibly finalize this
	 *    descriptor. This pairs with desc_reserve:D.
	 *
	 *    Memory barrier involvement:
	 *
	 *    If prb_commit:A reads from desc_reserve:D, then
	 *    desc_make_final:A reads from _prb_commit:B.
	 *
	 *    Relies on:
	 *
	 *    MB _prb_commit:B to prb_commit:A
	 *       matching
	 *    MB desc_reserve:D to desc_make_final:A
	 */
	if (!atomic_long_try_cmpxchg(&d->state_var, &prev_state_val,
			DESC_SV(e->id, state_val))) { /* LMM(_prb_commit:B) */
		WARN_ON_ONCE(1);
	}

	/* Restore interrupts, the reserve/commit window is finished. */
	local_irq_restore(e->irqflags);
}

/**
 * prb_commit() - Commit (previously reserved) data to the ringbuffer.
 *
 * @e: The entry containing the reserved data information.
 *
 * This is the public function available to writers to commit data.
 *
 * Note that the data is not yet available to readers until it is finalized.
 * Finalizing happens automatically when space for the next record is
 * reserved.
 *
 * See prb_final_commit() for a version of this function that finalizes
 * immediately.
 *
 * Context: Any context. Enables local interrupts.
 */
void prb_commit(struct prb_reserved_entry *e)
{
	struct prb_desc_ring *desc_ring = &e->rb->desc_ring;
	unsigned long head_id;

	_prb_commit(e, desc_committed);

	/*
	 * If this descriptor is no longer the head (i.e. a new record has
	 * been allocated), extending the data for this record is no longer
	 * allowed and therefore it must be finalized.
	 */
	head_id = atomic_long_read(&desc_ring->head_id); /* LMM(prb_commit:A) */
	if (head_id != e->id)
		desc_make_final(e->rb, e->id);
}

/**
 * prb_final_commit() - Commit and finalize (previously reserved) data to
 *                      the ringbuffer.
 *
 * @e: The entry containing the reserved data information.
 *
 * This is the public function available to writers to commit+finalize data.
 *
 * By finalizing, the data is made immediately available to readers.
 *
 * This function should only be used if there are no intentions of extending
 * this data using prb_reserve_in_last().
 *
 * Context: Any context. Enables local interrupts.
 */
void prb_final_commit(struct prb_reserved_entry *e)
{
	_prb_commit(e, desc_finalized);

	desc_update_last_finalized(e->rb);
}

/*
 * Count the number of lines in provided text. All text has at least 1 line
 * (even if @text_size is 0). Each '\n' processed is counted as an additional
 * line.
 */
static unsigned int count_lines(const char *text, unsigned int text_size)
{
	unsigned int next_size = text_size;
	unsigned int line_count = 1;
	const char *next = text;

	while (next_size) {
		next = memchr(next, '\n', next_size);
		if (!next)
			break;
		line_count++;
		next++;
		next_size = text_size - (next - text);
	}

	return line_count;
}

/*
 * Given @blk_lpos, copy an expected @len of data into the provided buffer.
 * If @line_count is provided, count the number of lines in the data.
 *
 * This function (used by readers) performs strict validation on the data
 * size to possibly detect bugs in the writer code. A WARN_ON_ONCE() is
 * triggered if an internal error is detected.
 */
static bool copy_data(struct prb_data_ring *data_ring,
		      struct prb_data_blk_lpos *blk_lpos, u16 len, char *buf,
		      unsigned int buf_size, unsigned int *line_count)
{
	unsigned int data_size;
	const char *data;

	/* Caller might not want any data. */
	if ((!buf || !buf_size) && !line_count)
		return true;

	data = get_data(data_ring, blk_lpos, &data_size);
	if (!data)
		return false;

	/*
	 * Actual cannot be less than expected. It can be more than expected
	 * because of the trailing alignment padding.
	 *
	 * Note that invalid @len values can occur because the caller loads
	 * the value during an allowed data race.
	 */
	if (data_size < (unsigned int)len)
		return false;

	/* Caller interested in the line count? */
	if (line_count)
		*line_count = count_lines(data, len);

	/* Caller interested in the data content? */
	if (!buf || !buf_size)
		return true;

	data_size = min_t(unsigned int, buf_size, len);

	memcpy(&buf[0], data, data_size); /* LMM(copy_data:A) */
	return true;
}

/*
 * This is an extended version of desc_read(). It gets a copy of a specified
 * descriptor. However, it also verifies that the record is finalized and has
 * the sequence number @seq. On success, 0 is returned.
 *
 * Error return values:
 * -EINVAL: A finalized record with sequence number @seq does not exist.
 * -ENOENT: A finalized record with sequence number @seq exists, but its data
 *          is not available. This is a valid record, so readers should
 *          continue with the next record.
 */
static int desc_read_finalized_seq(struct prb_desc_ring *desc_ring,
				   unsigned long id, u64 seq,
				   struct prb_desc *desc_out)
{
	struct prb_data_blk_lpos *blk_lpos = &desc_out->text_blk_lpos;
	enum desc_state d_state;
	u64 s;

	d_state = desc_read(desc_ring, id, desc_out, &s, NULL);

	/*
	 * An unexpected @id (desc_miss) or @seq mismatch means the record
	 * does not exist. A descriptor in the reserved or committed state
	 * means the record does not yet exist for the reader.
	 */
	if (d_state == desc_miss ||
	    d_state == desc_reserved ||
	    d_state == desc_committed ||
	    s != seq) {
		return -EINVAL;
	}

	/*
	 * A descriptor in the reusable state may no longer have its data
	 * available; report it as existing but with lost data. Or the record
	 * may actually be a record with lost data.
	 */
	if (d_state == desc_reusable ||
	    (blk_lpos->begin == FAILED_LPOS && blk_lpos->next == FAILED_LPOS)) {
		return -ENOENT;
	}

	return 0;
}

/*
 * Copy the ringbuffer data from the record with @seq to the provided
 * @r buffer. On success, 0 is returned.
 *
 * See desc_read_finalized_seq() for error return values.
 */
static int prb_read(struct printk_ringbuffer *rb, u64 seq,
		    struct printk_record *r, unsigned int *line_count)
{
	struct prb_desc_ring *desc_ring = &rb->desc_ring;
	struct printk_info *info = to_info(desc_ring, seq);
	struct prb_desc *rdesc = to_desc(desc_ring, seq);
	atomic_long_t *state_var = &rdesc->state_var;
	struct prb_desc desc;
	unsigned long id;
	int err;

	/* Extract the ID, used to specify the descriptor to read. */
	id = DESC_ID(atomic_long_read(state_var));

	/* Get a local copy of the correct descriptor (if available). */
	err = desc_read_finalized_seq(desc_ring, id, seq, &desc);

	/*
	 * If @r is NULL, the caller is only interested in the availability
	 * of the record.
	 */
	if (err || !r)
		return err;

	/* If requested, copy meta data. */
	if (r->info)
		memcpy(r->info, info, sizeof(*(r->info)));

	/* Copy text data. If it fails, this is a data-less record. */
	if (!copy_data(&rb->text_data_ring, &desc.text_blk_lpos, info->text_len,
		       r->text_buf, r->text_buf_size, line_count)) {
		return -ENOENT;
	}

	/* Ensure the record is still finalized and has the same @seq. */
	return desc_read_finalized_seq(desc_ring, id, seq, &desc);
}

/* Get the sequence number of the tail descriptor. */
u64 prb_first_seq(struct printk_ringbuffer *rb)
{
	struct prb_desc_ring *desc_ring = &rb->desc_ring;
	enum desc_state d_state;
	struct prb_desc desc;
	unsigned long id;
	u64 seq;

	for (;;) {
		id = atomic_long_read(&rb->desc_ring.tail_id); /* LMM(prb_first_seq:A) */

		d_state = desc_read(desc_ring, id, &desc, &seq, NULL); /* LMM(prb_first_seq:B) */

		/*
		 * This loop will not be infinite because the tail is
		 * _always_ in the finalized or reusable state.
		 */
		if (d_state == desc_finalized || d_state == desc_reusable)
			break;

		/*
		 * Guarantee the last state load from desc_read() is before
		 * reloading @tail_id in order to see a new tail in the case
		 * that the descriptor has been recycled. This pairs with
		 * desc_reserve:D.
		 *
		 * Memory barrier involvement:
		 *
		 * If prb_first_seq:B reads from desc_reserve:F, then
		 * prb_first_seq:A reads from desc_push_tail:B.
		 *
		 * Relies on:
		 *
		 * MB from desc_push_tail:B to desc_reserve:F
		 *    matching
		 * RMB prb_first_seq:B to prb_first_seq:A
		 */
		smp_rmb(); /* LMM(prb_first_seq:C) */
	}

	return seq;
}

/**
 * prb_next_reserve_seq() - Get the sequence number after the most recently
 *                  reserved record.
 *
 * @rb:  The ringbuffer to get the sequence number from.
 *
 * This is the public function available to readers to see what sequence
 * number will be assigned to the next reserved record.
 *
 * Note that depending on the situation, this value can be equal to or
 * higher than the sequence number returned by prb_next_seq().
 *
 * Context: Any context.
 * Return: The sequence number that will be assigned to the next record
 *         reserved.
 */
u64 prb_next_reserve_seq(struct printk_ringbuffer *rb)
{
	struct prb_desc_ring *desc_ring = &rb->desc_ring;
	unsigned long last_finalized_id;
	atomic_long_t *state_var;
	u64 last_finalized_seq;
	unsigned long head_id;
	struct prb_desc desc;
	unsigned long diff;
	struct prb_desc *d;
	int err;

	/*
	 * It may not be possible to read a sequence number for @head_id.
	 * So the ID of @last_finailzed_seq is used to calculate what the
	 * sequence number of @head_id will be.
	 */

try_again:
	last_finalized_seq = desc_last_finalized_seq(rb);

	/*
	 * @head_id is loaded after @last_finalized_seq to ensure that
	 * it points to the record with @last_finalized_seq or newer.
	 *
	 * Memory barrier involvement:
	 *
	 * If desc_last_finalized_seq:A reads from
	 * desc_update_last_finalized:A, then
	 * prb_next_reserve_seq:A reads from desc_reserve:D.
	 *
	 * Relies on:
	 *
	 * RELEASE from desc_reserve:D to desc_update_last_finalized:A
	 *    matching
	 * ACQUIRE from desc_last_finalized_seq:A to prb_next_reserve_seq:A
	 *
	 * Note: desc_reserve:D and desc_update_last_finalized:A can be
	 *       different CPUs. However, the desc_update_last_finalized:A CPU
	 *       (which performs the release) must have previously seen
	 *       desc_read:C, which implies desc_reserve:D can be seen.
	 */
	head_id = atomic_long_read(&desc_ring->head_id); /* LMM(prb_next_reserve_seq:A) */

	d = to_desc(desc_ring, last_finalized_seq);
	state_var = &d->state_var;

	/* Extract the ID, used to specify the descriptor to read. */
	last_finalized_id = DESC_ID(atomic_long_read(state_var));

	/* Ensure @last_finalized_id is correct. */
	err = desc_read_finalized_seq(desc_ring, last_finalized_id, last_finalized_seq, &desc);

	if (err == -EINVAL) {
		if (last_finalized_seq == 0) {
			/*
			 * No record has been finalized or even reserved yet.
			 *
			 * The @head_id is initialized such that the first
			 * increment will yield the first record (seq=0).
			 * Handle it separately to avoid a negative @diff
			 * below.
			 */
			if (head_id == DESC0_ID(desc_ring->count_bits))
				return 0;

			/*
			 * One or more descriptors are already reserved. Use
			 * the descriptor ID of the first one (@seq=0) for
			 * the @diff below.
			 */
			last_finalized_id = DESC0_ID(desc_ring->count_bits) + 1;
		} else {
			/* Record must have been overwritten. Try again. */
			goto try_again;
		}
	}

	/* Diff of known descriptor IDs to compute related sequence numbers. */
	diff = head_id - last_finalized_id;

	/*
	 * @head_id points to the most recently reserved record, but this
	 * function returns the sequence number that will be assigned to the
	 * next (not yet reserved) record. Thus +1 is needed.
	 */
	return (last_finalized_seq + diff + 1);
}

/*
 * Non-blocking read of a record.
 *
 * On success @seq is updated to the record that was read and (if provided)
 * @r and @line_count will contain the read/calculated data.
 *
 * On failure @seq is updated to a record that is not yet available to the
 * reader, but it will be the next record available to the reader.
 *
 * Note: When the current CPU is in panic, this function will skip over any
 *       non-existent/non-finalized records in order to allow the panic CPU
 *       to print any and all records that have been finalized.
 */
static bool _prb_read_valid(struct printk_ringbuffer *rb, u64 *seq,
			    struct printk_record *r, unsigned int *line_count)
{
	u64 tail_seq;
	int err;

	while ((err = prb_read(rb, *seq, r, line_count))) {
		tail_seq = prb_first_seq(rb);

		if (*seq < tail_seq) {
			/*
			 * Behind the tail. Catch up and try again. This
			 * can happen for -ENOENT and -EINVAL cases.
			 */
			*seq = tail_seq;

		} else if (err == -ENOENT) {
			/* Record exists, but the data was lost. Skip. */
			(*seq)++;

		} else {
			/*
			 * Non-existent/non-finalized record. Must stop.
			 *
			 * For panic situations it cannot be expected that
			 * non-finalized records will become finalized. But
			 * there may be other finalized records beyond that
			 * need to be printed for a panic situation. If this
			 * is the panic CPU, skip this
			 * non-existent/non-finalized record unless it is
			 * at or beyond the head, in which case it is not
			 * possible to continue.
			 *
			 * Note that new messages printed on panic CPU are
			 * finalized when we are here. The only exception
			 * might be the last message without trailing newline.
			 * But it would have the sequence number returned
			 * by "prb_next_reserve_seq() - 1".
			 */
			if (this_cpu_in_panic() && ((*seq + 1) < prb_next_reserve_seq(rb)))
				(*seq)++;
			else
				return false;
		}
	}

	return true;
}

/**
 * prb_read_valid() - Non-blocking read of a requested record or (if gone)
 *                    the next available record.
 *
 * @rb:  The ringbuffer to read from.
 * @seq: The sequence number of the record to read.
 * @r:   A record data buffer to store the read record to.
 *
 * This is the public function available to readers to read a record.
 *
 * The reader provides the @info and @text_buf buffers of @r to be
 * filled in. Any of the buffer pointers can be set to NULL if the reader
 * is not interested in that data. To ensure proper initialization of @r,
 * prb_rec_init_rd() should be used.
 *
 * Context: Any context.
 * Return: true if a record was read, otherwise false.
 *
 * On success, the reader must check r->info.seq to see which record was
 * actually read. This allows the reader to detect dropped records.
 *
 * Failure means @seq refers to a record not yet available to the reader.
 */
bool prb_read_valid(struct printk_ringbuffer *rb, u64 seq,
		    struct printk_record *r)
{
	return _prb_read_valid(rb, &seq, r, NULL);
}

/**
 * prb_read_valid_info() - Non-blocking read of meta data for a requested
 *                         record or (if gone) the next available record.
 *
 * @rb:         The ringbuffer to read from.
 * @seq:        The sequence number of the record to read.
 * @info:       A buffer to store the read record meta data to.
 * @line_count: A buffer to store the number of lines in the record text.
 *
 * This is the public function available to readers to read only the
 * meta data of a record.
 *
 * The reader provides the @info, @line_count buffers to be filled in.
 * Either of the buffer pointers can be set to NULL if the reader is not
 * interested in that data.
 *
 * Context: Any context.
 * Return: true if a record's meta data was read, otherwise false.
 *
 * On success, the reader must check info->seq to see which record meta data
 * was actually read. This allows the reader to detect dropped records.
 *
 * Failure means @seq refers to a record not yet available to the reader.
 */
bool prb_read_valid_info(struct printk_ringbuffer *rb, u64 seq,
			 struct printk_info *info, unsigned int *line_count)
{
	struct printk_record r;

	prb_rec_init_rd(&r, info, NULL, 0);

	return _prb_read_valid(rb, &seq, &r, line_count);
}

/**
 * prb_first_valid_seq() - Get the sequence number of the oldest available
 *                         record.
 *
 * @rb: The ringbuffer to get the sequence number from.
 *
 * This is the public function available to readers to see what the
 * first/oldest valid sequence number is.
 *
 * This provides readers a starting point to begin iterating the ringbuffer.
 *
 * Context: Any context.
 * Return: The sequence number of the first/oldest record or, if the
 *         ringbuffer is empty, 0 is returned.
 */
u64 prb_first_valid_seq(struct printk_ringbuffer *rb)
{
	u64 seq = 0;

	if (!_prb_read_valid(rb, &seq, NULL, NULL))
		return 0;

	return seq;
}

/**
 * prb_next_seq() - Get the sequence number after the last available record.
 *
 * @rb:  The ringbuffer to get the sequence number from.
 *
 * This is the public function available to readers to see what the next
 * newest sequence number available to readers will be.
 *
 * This provides readers a sequence number to jump to if all currently
 * available records should be skipped. It is guaranteed that all records
 * previous to the returned value have been finalized and are (or were)
 * available to the reader.
 *
 * Context: Any context.
 * Return: The sequence number of the next newest (not yet available) record
 *         for readers.
 */
u64 prb_next_seq(struct printk_ringbuffer *rb)
{
	u64 seq;

	seq = desc_last_finalized_seq(rb);

	/*
	 * Begin searching after the last finalized record.
	 *
	 * On 0, the search must begin at 0 because of hack#2
	 * of the bootstrapping phase it is not known if a
	 * record at index 0 exists.
	 */
	if (seq != 0)
		seq++;

	/*
	 * The information about the last finalized @seq might be inaccurate.
	 * Search forward to find the current one.
	 */
	while (_prb_read_valid(rb, &seq, NULL, NULL))
		seq++;

	return seq;
}

/**
 * prb_init() - Initialize a ringbuffer to use provided external buffers.
 *
 * @rb:       The ringbuffer to initialize.
 * @text_buf: The data buffer for text data.
 * @textbits: The size of @text_buf as a power-of-2 value.
 * @descs:    The descriptor buffer for ringbuffer records.
 * @descbits: The count of @descs items as a power-of-2 value.
 * @infos:    The printk_info buffer for ringbuffer records.
 *
 * This is the public function available to writers to setup a ringbuffer
 * during runtime using provided buffers.
 *
 * This must match the initialization of DEFINE_PRINTKRB().
 *
 * Context: Any context.
 */
void prb_init(struct printk_ringbuffer *rb,
	      char *text_buf, unsigned int textbits,
	      struct prb_desc *descs, unsigned int descbits,
	      struct printk_info *infos)
{
	memset(descs, 0, _DESCS_COUNT(descbits) * sizeof(descs[0]));
	memset(infos, 0, _DESCS_COUNT(descbits) * sizeof(infos[0]));

	rb->desc_ring.count_bits = descbits;
	rb->desc_ring.descs = descs;
	rb->desc_ring.infos = infos;
	atomic_long_set(&rb->desc_ring.head_id, DESC0_ID(descbits));
	atomic_long_set(&rb->desc_ring.tail_id, DESC0_ID(descbits));
	atomic_long_set(&rb->desc_ring.last_finalized_seq, 0);

	rb->text_data_ring.size_bits = textbits;
	rb->text_data_ring.data = text_buf;
	atomic_long_set(&rb->text_data_ring.head_lpos, BLK0_LPOS(textbits));
	atomic_long_set(&rb->text_data_ring.tail_lpos, BLK0_LPOS(textbits));

	atomic_long_set(&rb->fail, 0);

	atomic_long_set(&(descs[_DESCS_COUNT(descbits) - 1].state_var), DESC0_SV(descbits));
	descs[_DESCS_COUNT(descbits) - 1].text_blk_lpos.begin = FAILED_LPOS;
	descs[_DESCS_COUNT(descbits) - 1].text_blk_lpos.next = FAILED_LPOS;

	infos[0].seq = -(u64)_DESCS_COUNT(descbits);
	infos[_DESCS_COUNT(descbits) - 1].seq = 0;
}

/**
 * prb_record_text_space() - Query the full actual used ringbuffer space for
 *                           the text data of a reserved entry.
 *
 * @e: The successfully reserved entry to query.
 *
 * This is the public function available to writers to see how much actual
 * space is used in the ringbuffer to store the text data of the specified
 * entry.
 *
 * This function is only valid if @e has been successfully reserved using
 * prb_reserve().
 *
 * Context: Any context.
 * Return: The size in bytes used by the text data of the associated record.
 */
unsigned int prb_record_text_space(struct prb_reserved_entry *e)
{
	return e->text_space;
}