summaryrefslogtreecommitdiff
path: root/kernel/trace/ring_buffer.c
blob: dcf1c4dd3efe6954b7d030b986f43bd0a897f052 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
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
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
/*
 * Generic ring buffer
 *
 * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com>
 */
#include <linux/trace_events.h>
#include <linux/ring_buffer.h>
#include <linux/trace_clock.h>
#include <linux/sched/clock.h>
#include <linux/trace_seq.h>
#include <linux/spinlock.h>
#include <linux/irq_work.h>
#include <linux/uaccess.h>
#include <linux/hardirq.h>
#include <linux/kthread.h>	/* for self test */
#include <linux/module.h>
#include <linux/percpu.h>
#include <linux/mutex.h>
#include <linux/delay.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/hash.h>
#include <linux/list.h>
#include <linux/cpu.h>

#include <asm/local.h>

static void update_pages_handler(struct work_struct *work);

/*
 * The ring buffer header is special. We must manually up keep it.
 */
int ring_buffer_print_entry_header(struct trace_seq *s)
{
	trace_seq_puts(s, "# compressed entry header\n");
	trace_seq_puts(s, "\ttype_len    :    5 bits\n");
	trace_seq_puts(s, "\ttime_delta  :   27 bits\n");
	trace_seq_puts(s, "\tarray       :   32 bits\n");
	trace_seq_putc(s, '\n');
	trace_seq_printf(s, "\tpadding     : type == %d\n",
			 RINGBUF_TYPE_PADDING);
	trace_seq_printf(s, "\ttime_extend : type == %d\n",
			 RINGBUF_TYPE_TIME_EXTEND);
	trace_seq_printf(s, "\tdata max type_len  == %d\n",
			 RINGBUF_TYPE_DATA_TYPE_LEN_MAX);

	return !trace_seq_has_overflowed(s);
}

/*
 * The ring buffer is made up of a list of pages. A separate list of pages is
 * allocated for each CPU. A writer may only write to a buffer that is
 * associated with the CPU it is currently executing on.  A reader may read
 * from any per cpu buffer.
 *
 * The reader is special. For each per cpu buffer, the reader has its own
 * reader page. When a reader has read the entire reader page, this reader
 * page is swapped with another page in the ring buffer.
 *
 * Now, as long as the writer is off the reader page, the reader can do what
 * ever it wants with that page. The writer will never write to that page
 * again (as long as it is out of the ring buffer).
 *
 * Here's some silly ASCII art.
 *
 *   +------+
 *   |reader|          RING BUFFER
 *   |page  |
 *   +------+        +---+   +---+   +---+
 *                   |   |-->|   |-->|   |
 *                   +---+   +---+   +---+
 *                     ^               |
 *                     |               |
 *                     +---------------+
 *
 *
 *   +------+
 *   |reader|          RING BUFFER
 *   |page  |------------------v
 *   +------+        +---+   +---+   +---+
 *                   |   |-->|   |-->|   |
 *                   +---+   +---+   +---+
 *                     ^               |
 *                     |               |
 *                     +---------------+
 *
 *
 *   +------+
 *   |reader|          RING BUFFER
 *   |page  |------------------v
 *   +------+        +---+   +---+   +---+
 *      ^            |   |-->|   |-->|   |
 *      |            +---+   +---+   +---+
 *      |                              |
 *      |                              |
 *      +------------------------------+
 *
 *
 *   +------+
 *   |buffer|          RING BUFFER
 *   |page  |------------------v
 *   +------+        +---+   +---+   +---+
 *      ^            |   |   |   |-->|   |
 *      |   New      +---+   +---+   +---+
 *      |  Reader------^               |
 *      |   page                       |
 *      +------------------------------+
 *
 *
 * After we make this swap, the reader can hand this page off to the splice
 * code and be done with it. It can even allocate a new page if it needs to
 * and swap that into the ring buffer.
 *
 * We will be using cmpxchg soon to make all this lockless.
 *
 */

/* Used for individual buffers (after the counter) */
#define RB_BUFFER_OFF		(1 << 20)

#define BUF_PAGE_HDR_SIZE offsetof(struct buffer_data_page, data)

#define RB_EVNT_HDR_SIZE (offsetof(struct ring_buffer_event, array))
#define RB_ALIGNMENT		4U
#define RB_MAX_SMALL_DATA	(RB_ALIGNMENT * RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
#define RB_EVNT_MIN_SIZE	8U	/* two 32bit words */

#ifndef CONFIG_HAVE_64BIT_ALIGNED_ACCESS
# define RB_FORCE_8BYTE_ALIGNMENT	0
# define RB_ARCH_ALIGNMENT		RB_ALIGNMENT
#else
# define RB_FORCE_8BYTE_ALIGNMENT	1
# define RB_ARCH_ALIGNMENT		8U
#endif

#define RB_ALIGN_DATA		__aligned(RB_ARCH_ALIGNMENT)

/* define RINGBUF_TYPE_DATA for 'case RINGBUF_TYPE_DATA:' */
#define RINGBUF_TYPE_DATA 0 ... RINGBUF_TYPE_DATA_TYPE_LEN_MAX

enum {
	RB_LEN_TIME_EXTEND = 8,
	RB_LEN_TIME_STAMP = 16,
};

#define skip_time_extend(event) \
	((struct ring_buffer_event *)((char *)event + RB_LEN_TIME_EXTEND))

static inline int rb_null_event(struct ring_buffer_event *event)
{
	return event->type_len == RINGBUF_TYPE_PADDING && !event->time_delta;
}

static void rb_event_set_padding(struct ring_buffer_event *event)
{
	/* padding has a NULL time_delta */
	event->type_len = RINGBUF_TYPE_PADDING;
	event->time_delta = 0;
}

static unsigned
rb_event_data_length(struct ring_buffer_event *event)
{
	unsigned length;

	if (event->type_len)
		length = event->type_len * RB_ALIGNMENT;
	else
		length = event->array[0];
	return length + RB_EVNT_HDR_SIZE;
}

/*
 * Return the length of the given event. Will return
 * the length of the time extend if the event is a
 * time extend.
 */
static inline unsigned
rb_event_length(struct ring_buffer_event *event)
{
	switch (event->type_len) {
	case RINGBUF_TYPE_PADDING:
		if (rb_null_event(event))
			/* undefined */
			return -1;
		return  event->array[0] + RB_EVNT_HDR_SIZE;

	case RINGBUF_TYPE_TIME_EXTEND:
		return RB_LEN_TIME_EXTEND;

	case RINGBUF_TYPE_TIME_STAMP:
		return RB_LEN_TIME_STAMP;

	case RINGBUF_TYPE_DATA:
		return rb_event_data_length(event);
	default:
		BUG();
	}
	/* not hit */
	return 0;
}

/*
 * Return total length of time extend and data,
 *   or just the event length for all other events.
 */
static inline unsigned
rb_event_ts_length(struct ring_buffer_event *event)
{
	unsigned len = 0;

	if (event->type_len == RINGBUF_TYPE_TIME_EXTEND) {
		/* time extends include the data event after it */
		len = RB_LEN_TIME_EXTEND;
		event = skip_time_extend(event);
	}
	return len + rb_event_length(event);
}

/**
 * ring_buffer_event_length - return the length of the event
 * @event: the event to get the length of
 *
 * Returns the size of the data load of a data event.
 * If the event is something other than a data event, it
 * returns the size of the event itself. With the exception
 * of a TIME EXTEND, where it still returns the size of the
 * data load of the data event after it.
 */
unsigned ring_buffer_event_length(struct ring_buffer_event *event)
{
	unsigned length;

	if (event->type_len == RINGBUF_TYPE_TIME_EXTEND)
		event = skip_time_extend(event);

	length = rb_event_length(event);
	if (event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
		return length;
	length -= RB_EVNT_HDR_SIZE;
	if (length > RB_MAX_SMALL_DATA + sizeof(event->array[0]))
                length -= sizeof(event->array[0]);
	return length;
}
EXPORT_SYMBOL_GPL(ring_buffer_event_length);

/* inline for ring buffer fast paths */
static __always_inline void *
rb_event_data(struct ring_buffer_event *event)
{
	if (event->type_len == RINGBUF_TYPE_TIME_EXTEND)
		event = skip_time_extend(event);
	BUG_ON(event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX);
	/* If length is in len field, then array[0] has the data */
	if (event->type_len)
		return (void *)&event->array[0];
	/* Otherwise length is in array[0] and array[1] has the data */
	return (void *)&event->array[1];
}

/**
 * ring_buffer_event_data - return the data of the event
 * @event: the event to get the data from
 */
void *ring_buffer_event_data(struct ring_buffer_event *event)
{
	return rb_event_data(event);
}
EXPORT_SYMBOL_GPL(ring_buffer_event_data);

#define for_each_buffer_cpu(buffer, cpu)		\
	for_each_cpu(cpu, buffer->cpumask)

#define TS_SHIFT	27
#define TS_MASK		((1ULL << TS_SHIFT) - 1)
#define TS_DELTA_TEST	(~TS_MASK)

/* Flag when events were overwritten */
#define RB_MISSED_EVENTS	(1 << 31)
/* Missed count stored at end */
#define RB_MISSED_STORED	(1 << 30)

#define RB_MISSED_FLAGS		(RB_MISSED_EVENTS|RB_MISSED_STORED)

struct buffer_data_page {
	u64		 time_stamp;	/* page time stamp */
	local_t		 commit;	/* write committed index */
	unsigned char	 data[] RB_ALIGN_DATA;	/* data of buffer page */
};

/*
 * Note, the buffer_page list must be first. The buffer pages
 * are allocated in cache lines, which means that each buffer
 * page will be at the beginning of a cache line, and thus
 * the least significant bits will be zero. We use this to
 * add flags in the list struct pointers, to make the ring buffer
 * lockless.
 */
struct buffer_page {
	struct list_head list;		/* list of buffer pages */
	local_t		 write;		/* index for next write */
	unsigned	 read;		/* index for next read */
	local_t		 entries;	/* entries on this page */
	unsigned long	 real_end;	/* real end of data */
	struct buffer_data_page *page;	/* Actual data page */
};

/*
 * The buffer page counters, write and entries, must be reset
 * atomically when crossing page boundaries. To synchronize this
 * update, two counters are inserted into the number. One is
 * the actual counter for the write position or count on the page.
 *
 * The other is a counter of updaters. Before an update happens
 * the update partition of the counter is incremented. This will
 * allow the updater to update the counter atomically.
 *
 * The counter is 20 bits, and the state data is 12.
 */
#define RB_WRITE_MASK		0xfffff
#define RB_WRITE_INTCNT		(1 << 20)

static void rb_init_page(struct buffer_data_page *bpage)
{
	local_set(&bpage->commit, 0);
}

/**
 * ring_buffer_page_len - the size of data on the page.
 * @page: The page to read
 *
 * Returns the amount of data on the page, including buffer page header.
 */
size_t ring_buffer_page_len(void *page)
{
	struct buffer_data_page *bpage = page;

	return (local_read(&bpage->commit) & ~RB_MISSED_FLAGS)
		+ BUF_PAGE_HDR_SIZE;
}

/*
 * Also stolen from mm/slob.c. Thanks to Mathieu Desnoyers for pointing
 * this issue out.
 */
static void free_buffer_page(struct buffer_page *bpage)
{
	free_page((unsigned long)bpage->page);
	kfree(bpage);
}

/*
 * We need to fit the time_stamp delta into 27 bits.
 */
static inline int test_time_stamp(u64 delta)
{
	if (delta & TS_DELTA_TEST)
		return 1;
	return 0;
}

#define BUF_PAGE_SIZE (PAGE_SIZE - BUF_PAGE_HDR_SIZE)

/* Max payload is BUF_PAGE_SIZE - header (8bytes) */
#define BUF_MAX_DATA_SIZE (BUF_PAGE_SIZE - (sizeof(u32) * 2))

int ring_buffer_print_page_header(struct trace_seq *s)
{
	struct buffer_data_page field;

	trace_seq_printf(s, "\tfield: u64 timestamp;\t"
			 "offset:0;\tsize:%u;\tsigned:%u;\n",
			 (unsigned int)sizeof(field.time_stamp),
			 (unsigned int)is_signed_type(u64));

	trace_seq_printf(s, "\tfield: local_t commit;\t"
			 "offset:%u;\tsize:%u;\tsigned:%u;\n",
			 (unsigned int)offsetof(typeof(field), commit),
			 (unsigned int)sizeof(field.commit),
			 (unsigned int)is_signed_type(long));

	trace_seq_printf(s, "\tfield: int overwrite;\t"
			 "offset:%u;\tsize:%u;\tsigned:%u;\n",
			 (unsigned int)offsetof(typeof(field), commit),
			 1,
			 (unsigned int)is_signed_type(long));

	trace_seq_printf(s, "\tfield: char data;\t"
			 "offset:%u;\tsize:%u;\tsigned:%u;\n",
			 (unsigned int)offsetof(typeof(field), data),
			 (unsigned int)BUF_PAGE_SIZE,
			 (unsigned int)is_signed_type(char));

	return !trace_seq_has_overflowed(s);
}

struct rb_irq_work {
	struct irq_work			work;
	wait_queue_head_t		waiters;
	wait_queue_head_t		full_waiters;
	bool				waiters_pending;
	bool				full_waiters_pending;
	bool				wakeup_full;
};

/*
 * Structure to hold event state and handle nested events.
 */
struct rb_event_info {
	u64			ts;
	u64			delta;
	unsigned long		length;
	struct buffer_page	*tail_page;
	int			add_timestamp;
};

/*
 * Used for which event context the event is in.
 *  NMI     = 0
 *  IRQ     = 1
 *  SOFTIRQ = 2
 *  NORMAL  = 3
 *
 * See trace_recursive_lock() comment below for more details.
 */
enum {
	RB_CTX_NMI,
	RB_CTX_IRQ,
	RB_CTX_SOFTIRQ,
	RB_CTX_NORMAL,
	RB_CTX_MAX
};

/*
 * head_page == tail_page && head == tail then buffer is empty.
 */
struct ring_buffer_per_cpu {
	int				cpu;
	atomic_t			record_disabled;
	struct ring_buffer		*buffer;
	raw_spinlock_t			reader_lock;	/* serialize readers */
	arch_spinlock_t			lock;
	struct lock_class_key		lock_key;
	struct buffer_data_page		*free_page;
	unsigned long			nr_pages;
	unsigned int			current_context;
	struct list_head		*pages;
	struct buffer_page		*head_page;	/* read from head */
	struct buffer_page		*tail_page;	/* write to tail */
	struct buffer_page		*commit_page;	/* committed pages */
	struct buffer_page		*reader_page;
	unsigned long			lost_events;
	unsigned long			last_overrun;
	local_t				entries_bytes;
	local_t				entries;
	local_t				overrun;
	local_t				commit_overrun;
	local_t				dropped_events;
	local_t				committing;
	local_t				commits;
	unsigned long			read;
	unsigned long			read_bytes;
	u64				write_stamp;
	u64				read_stamp;
	/* ring buffer pages to update, > 0 to add, < 0 to remove */
	long				nr_pages_to_update;
	struct list_head		new_pages; /* new pages to add */
	struct work_struct		update_pages_work;
	struct completion		update_done;

	struct rb_irq_work		irq_work;
};

struct ring_buffer {
	unsigned			flags;
	int				cpus;
	atomic_t			record_disabled;
	atomic_t			resize_disabled;
	cpumask_var_t			cpumask;

	struct lock_class_key		*reader_lock_key;

	struct mutex			mutex;

	struct ring_buffer_per_cpu	**buffers;

	struct hlist_node		node;
	u64				(*clock)(void);

	struct rb_irq_work		irq_work;
};

struct ring_buffer_iter {
	struct ring_buffer_per_cpu	*cpu_buffer;
	unsigned long			head;
	struct buffer_page		*head_page;
	struct buffer_page		*cache_reader_page;
	unsigned long			cache_read;
	u64				read_stamp;
};

/*
 * rb_wake_up_waiters - wake up tasks waiting for ring buffer input
 *
 * Schedules a delayed work to wake up any task that is blocked on the
 * ring buffer waiters queue.
 */
static void rb_wake_up_waiters(struct irq_work *work)
{
	struct rb_irq_work *rbwork = container_of(work, struct rb_irq_work, work);

	wake_up_all(&rbwork->waiters);
	if (rbwork->wakeup_full) {
		rbwork->wakeup_full = false;
		wake_up_all(&rbwork->full_waiters);
	}
}

/**
 * ring_buffer_wait - wait for input to the ring buffer
 * @buffer: buffer to wait on
 * @cpu: the cpu buffer to wait on
 * @full: wait until a full page is available, if @cpu != RING_BUFFER_ALL_CPUS
 *
 * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon
 * as data is added to any of the @buffer's cpu buffers. Otherwise
 * it will wait for data to be added to a specific cpu buffer.
 */
int ring_buffer_wait(struct ring_buffer *buffer, int cpu, bool full)
{
	struct ring_buffer_per_cpu *uninitialized_var(cpu_buffer);
	DEFINE_WAIT(wait);
	struct rb_irq_work *work;
	int ret = 0;

	/*
	 * Depending on what the caller is waiting for, either any
	 * data in any cpu buffer, or a specific buffer, put the
	 * caller on the appropriate wait queue.
	 */
	if (cpu == RING_BUFFER_ALL_CPUS) {
		work = &buffer->irq_work;
		/* Full only makes sense on per cpu reads */
		full = false;
	} else {
		if (!cpumask_test_cpu(cpu, buffer->cpumask))
			return -ENODEV;
		cpu_buffer = buffer->buffers[cpu];
		work = &cpu_buffer->irq_work;
	}


	while (true) {
		if (full)
			prepare_to_wait(&work->full_waiters, &wait, TASK_INTERRUPTIBLE);
		else
			prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE);

		/*
		 * The events can happen in critical sections where
		 * checking a work queue can cause deadlocks.
		 * After adding a task to the queue, this flag is set
		 * only to notify events to try to wake up the queue
		 * using irq_work.
		 *
		 * We don't clear it even if the buffer is no longer
		 * empty. The flag only causes the next event to run
		 * irq_work to do the work queue wake up. The worse
		 * that can happen if we race with !trace_empty() is that
		 * an event will cause an irq_work to try to wake up
		 * an empty queue.
		 *
		 * There's no reason to protect this flag either, as
		 * the work queue and irq_work logic will do the necessary
		 * synchronization for the wake ups. The only thing
		 * that is necessary is that the wake up happens after
		 * a task has been queued. It's OK for spurious wake ups.
		 */
		if (full)
			work->full_waiters_pending = true;
		else
			work->waiters_pending = true;

		if (signal_pending(current)) {
			ret = -EINTR;
			break;
		}

		if (cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer))
			break;

		if (cpu != RING_BUFFER_ALL_CPUS &&
		    !ring_buffer_empty_cpu(buffer, cpu)) {
			unsigned long flags;
			bool pagebusy;

			if (!full)
				break;

			raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
			pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page;
			raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);

			if (!pagebusy)
				break;
		}

		schedule();
	}

	if (full)
		finish_wait(&work->full_waiters, &wait);
	else
		finish_wait(&work->waiters, &wait);

	return ret;
}

/**
 * ring_buffer_poll_wait - poll on buffer input
 * @buffer: buffer to wait on
 * @cpu: the cpu buffer to wait on
 * @filp: the file descriptor
 * @poll_table: The poll descriptor
 *
 * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon
 * as data is added to any of the @buffer's cpu buffers. Otherwise
 * it will wait for data to be added to a specific cpu buffer.
 *
 * Returns EPOLLIN | EPOLLRDNORM if data exists in the buffers,
 * zero otherwise.
 */
__poll_t ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu,
			  struct file *filp, poll_table *poll_table)
{
	struct ring_buffer_per_cpu *cpu_buffer;
	struct rb_irq_work *work;

	if (cpu == RING_BUFFER_ALL_CPUS)
		work = &buffer->irq_work;
	else {
		if (!cpumask_test_cpu(cpu, buffer->cpumask))
			return -EINVAL;

		cpu_buffer = buffer->buffers[cpu];
		work = &cpu_buffer->irq_work;
	}

	poll_wait(filp, &work->waiters, poll_table);
	work->waiters_pending = true;
	/*
	 * There's a tight race between setting the waiters_pending and
	 * checking if the ring buffer is empty.  Once the waiters_pending bit
	 * is set, the next event will wake the task up, but we can get stuck
	 * if there's only a single event in.
	 *
	 * FIXME: Ideally, we need a memory barrier on the writer side as well,
	 * but adding a memory barrier to all events will cause too much of a
	 * performance hit in the fast path.  We only need a memory barrier when
	 * the buffer goes from empty to having content.  But as this race is
	 * extremely small, and it's not a problem if another event comes in, we
	 * will fix it later.
	 */
	smp_mb();

	if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) ||
	    (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu)))
		return EPOLLIN | EPOLLRDNORM;
	return 0;
}

/* buffer may be either ring_buffer or ring_buffer_per_cpu */
#define RB_WARN_ON(b, cond)						\
	({								\
		int _____ret = unlikely(cond);				\
		if (_____ret) {						\
			if (__same_type(*(b), struct ring_buffer_per_cpu)) { \
				struct ring_buffer_per_cpu *__b =	\
					(void *)b;			\
				atomic_inc(&__b->buffer->record_disabled); \
			} else						\
				atomic_inc(&b->record_disabled);	\
			WARN_ON(1);					\
		}							\
		_____ret;						\
	})

/* Up this if you want to test the TIME_EXTENTS and normalization */
#define DEBUG_SHIFT 0

static inline u64 rb_time_stamp(struct ring_buffer *buffer)
{
	/* shift to debug/test normalization and TIME_EXTENTS */
	return buffer->clock() << DEBUG_SHIFT;
}

u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu)
{
	u64 time;

	preempt_disable_notrace();
	time = rb_time_stamp(buffer);
	preempt_enable_no_resched_notrace();

	return time;
}
EXPORT_SYMBOL_GPL(ring_buffer_time_stamp);

void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer,
				      int cpu, u64 *ts)
{
	/* Just stupid testing the normalize function and deltas */
	*ts >>= DEBUG_SHIFT;
}
EXPORT_SYMBOL_GPL(ring_buffer_normalize_time_stamp);

/*
 * Making the ring buffer lockless makes things tricky.
 * Although writes only happen on the CPU that they are on,
 * and they only need to worry about interrupts. Reads can
 * happen on any CPU.
 *
 * The reader page is always off the ring buffer, but when the
 * reader finishes with a page, it needs to swap its page with
 * a new one from the buffer. The reader needs to take from
 * the head (writes go to the tail). But if a writer is in overwrite
 * mode and wraps, it must push the head page forward.
 *
 * Here lies the problem.
 *
 * The reader must be careful to replace only the head page, and
 * not another one. As described at the top of the file in the
 * ASCII art, the reader sets its old page to point to the next
 * page after head. It then sets the page after head to point to
 * the old reader page. But if the writer moves the head page
 * during this operation, the reader could end up with the tail.
 *
 * We use cmpxchg to help prevent this race. We also do something
 * special with the page before head. We set the LSB to 1.
 *
 * When the writer must push the page forward, it will clear the
 * bit that points to the head page, move the head, and then set
 * the bit that points to the new head page.
 *
 * We also don't want an interrupt coming in and moving the head
 * page on another writer. Thus we use the second LSB to catch
 * that too. Thus:
 *
 * head->list->prev->next        bit 1          bit 0
 *                              -------        -------
 * Normal page                     0              0
 * Points to head page             0              1
 * New head page                   1              0
 *
 * Note we can not trust the prev pointer of the head page, because:
 *
 * +----+       +-----+        +-----+
 * |    |------>|  T  |---X--->|  N  |
 * |    |<------|     |        |     |
 * +----+       +-----+        +-----+
 *   ^                           ^ |
 *   |          +-----+          | |
 *   +----------|  R  |----------+ |
 *              |     |<-----------+
 *              +-----+
 *
 * Key:  ---X-->  HEAD flag set in pointer
 *         T      Tail page
 *         R      Reader page
 *         N      Next page
 *
 * (see __rb_reserve_next() to see where this happens)
 *
 *  What the above shows is that the reader just swapped out
 *  the reader page with a page in the buffer, but before it
 *  could make the new header point back to the new page added
 *  it was preempted by a writer. The writer moved forward onto
 *  the new page added by the reader and is about to move forward
 *  again.
 *
 *  You can see, it is legitimate for the previous pointer of
 *  the head (or any page) not to point back to itself. But only
 *  temporarially.
 */

#define RB_PAGE_NORMAL		0UL
#define RB_PAGE_HEAD		1UL
#define RB_PAGE_UPDATE		2UL


#define RB_FLAG_MASK		3UL

/* PAGE_MOVED is not part of the mask */
#define RB_PAGE_MOVED		4UL

/*
 * rb_list_head - remove any bit
 */
static struct list_head *rb_list_head(struct list_head *list)
{
	unsigned long val = (unsigned long)list;

	return (struct list_head *)(val & ~RB_FLAG_MASK);
}

/*
 * rb_is_head_page - test if the given page is the head page
 *
 * Because the reader may move the head_page pointer, we can
 * not trust what the head page is (it may be pointing to
 * the reader page). But if the next page is a header page,
 * its flags will be non zero.
 */
static inline int
rb_is_head_page(struct ring_buffer_per_cpu *cpu_buffer,
		struct buffer_page *page, struct list_head *list)
{
	unsigned long val;

	val = (unsigned long)list->next;

	if ((val & ~RB_FLAG_MASK) != (unsigned long)&page->list)
		return RB_PAGE_MOVED;

	return val & RB_FLAG_MASK;
}

/*
 * rb_is_reader_page
 *
 * The unique thing about the reader page, is that, if the
 * writer is ever on it, the previous pointer never points
 * back to the reader page.
 */
static bool rb_is_reader_page(struct buffer_page *page)
{
	struct list_head *list = page->list.prev;

	return rb_list_head(list->next) != &page->list;
}

/*
 * rb_set_list_to_head - set a list_head to be pointing to head.
 */
static void rb_set_list_to_head(struct ring_buffer_per_cpu *cpu_buffer,
				struct list_head *list)
{
	unsigned long *ptr;

	ptr = (unsigned long *)&list->next;
	*ptr |= RB_PAGE_HEAD;
	*ptr &= ~RB_PAGE_UPDATE;
}

/*
 * rb_head_page_activate - sets up head page
 */
static void rb_head_page_activate(struct ring_buffer_per_cpu *cpu_buffer)
{
	struct buffer_page *head;

	head = cpu_buffer->head_page;
	if (!head)
		return;

	/*
	 * Set the previous list pointer to have the HEAD flag.
	 */
	rb_set_list_to_head(cpu_buffer, head->list.prev);
}

static void rb_list_head_clear(struct list_head *list)
{
	unsigned long *ptr = (unsigned long *)&list->next;

	*ptr &= ~RB_FLAG_MASK;
}

/*
 * rb_head_page_dactivate - clears head page ptr (for free list)
 */
static void
rb_head_page_deactivate(struct ring_buffer_per_cpu *cpu_buffer)
{
	struct list_head *hd;

	/* Go through the whole list and clear any pointers found. */
	rb_list_head_clear(cpu_buffer->pages);

	list_for_each(hd, cpu_buffer->pages)
		rb_list_head_clear(hd);
}

static int rb_head_page_set(struct ring_buffer_per_cpu *cpu_buffer,
			    struct buffer_page *head,
			    struct buffer_page *prev,
			    int old_flag, int new_flag)
{
	struct list_head *list;
	unsigned long val = (unsigned long)&head->list;
	unsigned long ret;

	list = &prev->list;

	val &= ~RB_FLAG_MASK;

	ret = cmpxchg((unsigned long *)&list->next,
		      val | old_flag, val | new_flag);

	/* check if the reader took the page */
	if ((ret & ~RB_FLAG_MASK) != val)
		return RB_PAGE_MOVED;

	return ret & RB_FLAG_MASK;
}

static int rb_head_page_set_update(struct ring_buffer_per_cpu *cpu_buffer,
				   struct buffer_page *head,
				   struct buffer_page *prev,
				   int old_flag)
{
	return rb_head_page_set(cpu_buffer, head, prev,
				old_flag, RB_PAGE_UPDATE);
}

static int rb_head_page_set_head(struct ring_buffer_per_cpu *cpu_buffer,
				 struct buffer_page *head,
				 struct buffer_page *prev,
				 int old_flag)
{
	return rb_head_page_set(cpu_buffer, head, prev,
				old_flag, RB_PAGE_HEAD);
}

static int rb_head_page_set_normal(struct ring_buffer_per_cpu *cpu_buffer,
				   struct buffer_page *head,
				   struct buffer_page *prev,
				   int old_flag)
{
	return rb_head_page_set(cpu_buffer, head, prev,
				old_flag, RB_PAGE_NORMAL);
}

static inline void rb_inc_page(struct ring_buffer_per_cpu *cpu_buffer,
			       struct buffer_page **bpage)
{
	struct list_head *p = rb_list_head((*bpage)->list.next);

	*bpage = list_entry(p, struct buffer_page, list);
}

static struct buffer_page *
rb_set_head_page(struct ring_buffer_per_cpu *cpu_buffer)
{
	struct buffer_page *head;
	struct buffer_page *page;
	struct list_head *list;
	int i;

	if (RB_WARN_ON(cpu_buffer, !cpu_buffer->head_page))
		return NULL;

	/* sanity check */
	list = cpu_buffer->pages;
	if (RB_WARN_ON(cpu_buffer, rb_list_head(list->prev->next) != list))
		return NULL;

	page = head = cpu_buffer->head_page;
	/*
	 * It is possible that the writer moves the header behind
	 * where we started, and we miss in one loop.
	 * A second loop should grab the header, but we'll do
	 * three loops just because I'm paranoid.
	 */
	for (i = 0; i < 3; i++) {
		do {
			if (rb_is_head_page(cpu_buffer, page, page->list.prev)) {
				cpu_buffer->head_page = page;
				return page;
			}
			rb_inc_page(cpu_buffer, &page);
		} while (page != head);
	}

	RB_WARN_ON(cpu_buffer, 1);

	return NULL;
}

static int rb_head_page_replace(struct buffer_page *old,
				struct buffer_page *new)
{
	unsigned long *ptr = (unsigned long *)&old->list.prev->next;
	unsigned long val;
	unsigned long ret;

	val = *ptr & ~RB_FLAG_MASK;
	val |= RB_PAGE_HEAD;

	ret = cmpxchg(ptr, val, (unsigned long)&new->list);

	return ret == val;
}

/*
 * rb_tail_page_update - move the tail page forward
 */
static void rb_tail_page_update(struct ring_buffer_per_cpu *cpu_buffer,
			       struct buffer_page *tail_page,
			       struct buffer_page *next_page)
{
	unsigned long old_entries;
	unsigned long old_write;

	/*
	 * The tail page now needs to be moved forward.
	 *
	 * We need to reset the tail page, but without messing
	 * with possible erasing of data brought in by interrupts
	 * that have moved the tail page and are currently on it.
	 *
	 * We add a counter to the write field to denote this.
	 */
	old_write = local_add_return(RB_WRITE_INTCNT, &next_page->write);
	old_entries = local_add_return(RB_WRITE_INTCNT, &next_page->entries);

	/*
	 * Just make sure we have seen our old_write and synchronize
	 * with any interrupts that come in.
	 */
	barrier();

	/*
	 * If the tail page is still the same as what we think
	 * it is, then it is up to us to update the tail
	 * pointer.
	 */
	if (tail_page == READ_ONCE(cpu_buffer->tail_page)) {
		/* Zero the write counter */
		unsigned long val = old_write & ~RB_WRITE_MASK;
		unsigned long eval = old_entries & ~RB_WRITE_MASK;

		/*
		 * This will only succeed if an interrupt did
		 * not come in and change it. In which case, we
		 * do not want to modify it.
		 *
		 * We add (void) to let the compiler know that we do not care
		 * about the return value of these functions. We use the
		 * cmpxchg to only update if an interrupt did not already
		 * do it for us. If the cmpxchg fails, we don't care.
		 */
		(void)local_cmpxchg(&next_page->write, old_write, val);
		(void)local_cmpxchg(&next_page->entries, old_entries, eval);

		/*
		 * No need to worry about races with clearing out the commit.
		 * it only can increment when a commit takes place. But that
		 * only happens in the outer most nested commit.
		 */
		local_set(&next_page->page->commit, 0);

		/* Again, either we update tail_page or an interrupt does */
		(void)cmpxchg(&cpu_buffer->tail_page, tail_page, next_page);
	}
}

static int rb_check_bpage(struct ring_buffer_per_cpu *cpu_buffer,
			  struct buffer_page *bpage)
{
	unsigned long val = (unsigned long)bpage;

	if (RB_WARN_ON(cpu_buffer, val & RB_FLAG_MASK))
		return 1;

	return 0;
}

/**
 * rb_check_list - make sure a pointer to a list has the last bits zero
 */
static int rb_check_list(struct ring_buffer_per_cpu *cpu_buffer,
			 struct list_head *list)
{
	if (RB_WARN_ON(cpu_buffer, rb_list_head(list->prev) != list->prev))
		return 1;
	if (RB_WARN_ON(cpu_buffer, rb_list_head(list->next) != list->next))
		return 1;
	return 0;
}

/**
 * rb_check_pages - integrity check of buffer pages
 * @cpu_buffer: CPU buffer with pages to test
 *
 * As a safety measure we check to make sure the data pages have not
 * been corrupted.
 */
static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer)
{
	struct list_head *head = cpu_buffer->pages;
	struct buffer_page *bpage, *tmp;

	/* Reset the head page if it exists */
	if (cpu_buffer->head_page)
		rb_set_head_page(cpu_buffer);

	rb_head_page_deactivate(cpu_buffer);

	if (RB_WARN_ON(cpu_buffer, head->next->prev != head))
		return -1;
	if (RB_WARN_ON(cpu_buffer, head->prev->next != head))
		return -1;

	if (rb_check_list(cpu_buffer, head))
		return -1;

	list_for_each_entry_safe(bpage, tmp, head, list) {
		if (RB_WARN_ON(cpu_buffer,
			       bpage->list.next->prev != &bpage->list))
			return -1;
		if (RB_WARN_ON(cpu_buffer,
			       bpage->list.prev->next != &bpage->list))
			return -1;
		if (rb_check_list(cpu_buffer, &bpage->list))
			return -1;
	}

	rb_head_page_activate(cpu_buffer);

	return 0;
}

static int __rb_allocate_pages(long nr_pages, struct list_head *pages, int cpu)
{
	struct buffer_page *bpage, *tmp;
	long i;

	for (i = 0; i < nr_pages; i++) {
		struct page *page;
		/*
		 * __GFP_RETRY_MAYFAIL flag makes sure that the allocation fails
		 * gracefully without invoking oom-killer and the system is not
		 * destabilized.
		 */
		bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()),
				    GFP_KERNEL | __GFP_RETRY_MAYFAIL,
				    cpu_to_node(cpu));
		if (!bpage)
			goto free_pages;

		list_add(&bpage->list, pages);

		page = alloc_pages_node(cpu_to_node(cpu),
					GFP_KERNEL | __GFP_RETRY_MAYFAIL, 0);
		if (!page)
			goto free_pages;
		bpage->page = page_address(page);
		rb_init_page(bpage->page);
	}

	return 0;

free_pages:
	list_for_each_entry_safe(bpage, tmp, pages, list) {
		list_del_init(&bpage->list);
		free_buffer_page(bpage);
	}

	return -ENOMEM;
}

static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
			     unsigned long nr_pages)
{
	LIST_HEAD(pages);

	WARN_ON(!nr_pages);

	if (__rb_allocate_pages(nr_pages, &pages, cpu_buffer->cpu))
		return -ENOMEM;

	/*
	 * The ring buffer page list is a circular list that does not
	 * start and end with a list head. All page list items point to
	 * other pages.
	 */
	cpu_buffer->pages = pages.next;
	list_del(&pages);

	cpu_buffer->nr_pages = nr_pages;

	rb_check_pages(cpu_buffer);

	return 0;
}

static struct ring_buffer_per_cpu *
rb_allocate_cpu_buffer(struct ring_buffer *buffer, long nr_pages, int cpu)
{
	struct ring_buffer_per_cpu *cpu_buffer;
	struct buffer_page *bpage;
	struct page *page;
	int ret;

	cpu_buffer = kzalloc_node(ALIGN(sizeof(*cpu_buffer), cache_line_size()),
				  GFP_KERNEL, cpu_to_node(cpu));
	if (!cpu_buffer)
		return NULL;

	cpu_buffer->cpu = cpu;
	cpu_buffer->buffer = buffer;
	raw_spin_lock_init(&cpu_buffer->reader_lock);
	lockdep_set_class(&cpu_buffer->reader_lock, buffer->reader_lock_key);
	cpu_buffer->lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
	INIT_WORK(&cpu_buffer->update_pages_work, update_pages_handler);
	init_completion(&cpu_buffer->update_done);
	init_irq_work(&cpu_buffer->irq_work.work, rb_wake_up_waiters);
	init_waitqueue_head(&cpu_buffer->irq_work.waiters);
	init_waitqueue_head(&cpu_buffer->irq_work.full_waiters);

	bpage = kzalloc_node(ALIGN(sizeof(*bpage), cache_line_size()),
			    GFP_KERNEL, cpu_to_node(cpu));
	if (!bpage)
		goto fail_free_buffer;

	rb_check_bpage(cpu_buffer, bpage);

	cpu_buffer->reader_page = bpage;
	page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL, 0);
	if (!page)
		goto fail_free_reader;
	bpage->page = page_address(page);
	rb_init_page(bpage->page);

	INIT_LIST_HEAD(&cpu_buffer->reader_page->list);
	INIT_LIST_HEAD(&cpu_buffer->new_pages);

	ret = rb_allocate_pages(cpu_buffer, nr_pages);
	if (ret < 0)
		goto fail_free_reader;

	cpu_buffer->head_page
		= list_entry(cpu_buffer->pages, struct buffer_page, list);
	cpu_buffer->tail_page = cpu_buffer->commit_page = cpu_buffer->head_page;

	rb_head_page_activate(cpu_buffer);

	return cpu_buffer;

 fail_free_reader:
	free_buffer_page(cpu_buffer->reader_page);

 fail_free_buffer:
	kfree(cpu_buffer);
	return NULL;
}

static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
{
	struct list_head *head = cpu_buffer->pages;
	struct buffer_page *bpage, *tmp;

	free_buffer_page(cpu_buffer->reader_page);

	rb_head_page_deactivate(cpu_buffer);

	if (head) {
		list_for_each_entry_safe(bpage, tmp, head, list) {
			list_del_init(&bpage->list);
			free_buffer_page(bpage);
		}
		bpage = list_entry(head, struct buffer_page, list);
		free_buffer_page(bpage);
	}

	kfree(cpu_buffer);
}

/**
 * __ring_buffer_alloc - allocate a new ring_buffer
 * @size: the size in bytes per cpu that is needed.
 * @flags: attributes to set for the ring buffer.
 *
 * Currently the only flag that is available is the RB_FL_OVERWRITE
 * flag. This flag means that the buffer will overwrite old data
 * when the buffer wraps. If this flag is not set, the buffer will
 * drop data when the tail hits the head.
 */
struct ring_buffer *__ring_buffer_alloc(unsigned long size, unsigned flags,
					struct lock_class_key *key)
{
	struct ring_buffer *buffer;
	long nr_pages;
	int bsize;
	int cpu;
	int ret;

	/* keep it in its own cache line */
	buffer = kzalloc(ALIGN(sizeof(*buffer), cache_line_size()),
			 GFP_KERNEL);
	if (!buffer)
		return NULL;

	if (!zalloc_cpumask_var(&buffer->cpumask, GFP_KERNEL))
		goto fail_free_buffer;

	nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
	buffer->flags = flags;
	buffer->clock = trace_clock_local;
	buffer->reader_lock_key = key;

	init_irq_work(&buffer->irq_work.work, rb_wake_up_waiters);
	init_waitqueue_head(&buffer->irq_work.waiters);

	/* need at least two pages */
	if (nr_pages < 2)
		nr_pages = 2;

	buffer->cpus = nr_cpu_ids;

	bsize = sizeof(void *) * nr_cpu_ids;
	buffer->buffers = kzalloc(ALIGN(bsize, cache_line_size()),
				  GFP_KERNEL);
	if (!buffer->buffers)
		goto fail_free_cpumask;

	cpu = raw_smp_processor_id();
	cpumask_set_cpu(cpu, buffer->cpumask);
	buffer->buffers[cpu] = rb_allocate_cpu_buffer(buffer, nr_pages, cpu);
	if (!buffer->buffers[cpu])
		goto fail_free_buffers;

	ret = cpuhp_state_add_instance(CPUHP_TRACE_RB_PREPARE, &buffer->node);
	if (ret < 0)
		goto fail_free_buffers;

	mutex_init(&buffer->mutex);

	return buffer;

 fail_free_buffers:
	for_each_buffer_cpu(buffer, cpu) {
		if (buffer->buffers[cpu])
			rb_free_cpu_buffer(buffer->buffers[cpu]);
	}
	kfree(buffer->buffers);

 fail_free_cpumask:
	free_cpumask_var(buffer->cpumask);

 fail_free_buffer:
	kfree(buffer);
	return NULL;
}
EXPORT_SYMBOL_GPL(__ring_buffer_alloc);

/**
 * ring_buffer_free - free a ring buffer.
 * @buffer: the buffer to free.
 */
void
ring_buffer_free(struct ring_buffer *buffer)
{
	int cpu;

	cpuhp_state_remove_instance(CPUHP_TRACE_RB_PREPARE, &buffer->node);

	for_each_buffer_cpu(buffer, cpu)
		rb_free_cpu_buffer(buffer->buffers[cpu]);

	kfree(buffer->buffers);
	free_cpumask_var(buffer->cpumask);

	kfree(buffer);
}
EXPORT_SYMBOL_GPL(ring_buffer_free);

void ring_buffer_set_clock(struct ring_buffer *buffer,
			   u64 (*clock)(void))
{
	buffer->clock = clock;
}

static void rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer);

static inline unsigned long rb_page_entries(struct buffer_page *bpage)
{
	return local_read(&bpage->entries) & RB_WRITE_MASK;
}

static inline unsigned long rb_page_write(struct buffer_page *bpage)
{
	return local_read(&bpage->write) & RB_WRITE_MASK;
}

static int
rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned long nr_pages)
{
	struct list_head *tail_page, *to_remove, *next_page;
	struct buffer_page *to_remove_page, *tmp_iter_page;
	struct buffer_page *last_page, *first_page;
	unsigned long nr_removed;
	unsigned long head_bit;
	int page_entries;

	head_bit = 0;

	raw_spin_lock_irq(&cpu_buffer->reader_lock);
	atomic_inc(&cpu_buffer->record_disabled);
	/*
	 * We don't race with the readers since we have acquired the reader
	 * lock. We also don't race with writers after disabling recording.
	 * This makes it easy to figure out the first and the last page to be
	 * removed from the list. We unlink all the pages in between including
	 * the first and last pages. This is done in a busy loop so that we
	 * lose the least number of traces.
	 * The pages are freed after we restart recording and unlock readers.
	 */
	tail_page = &cpu_buffer->tail_page->list;

	/*
	 * tail page might be on reader page, we remove the next page
	 * from the ring buffer
	 */
	if (cpu_buffer->tail_page == cpu_buffer->reader_page)
		tail_page = rb_list_head(tail_page->next);
	to_remove = tail_page;

	/* start of pages to remove */
	first_page = list_entry(rb_list_head(to_remove->next),
				struct buffer_page, list);

	for (nr_removed = 0; nr_removed < nr_pages; nr_removed++) {
		to_remove = rb_list_head(to_remove)->next;
		head_bit |= (unsigned long)to_remove & RB_PAGE_HEAD;
	}

	next_page = rb_list_head(to_remove)->next;

	/*
	 * Now we remove all pages between tail_page and next_page.
	 * Make sure that we have head_bit value preserved for the
	 * next page
	 */
	tail_page->next = (struct list_head *)((unsigned long)next_page |
						head_bit);
	next_page = rb_list_head(next_page);
	next_page->prev = tail_page;

	/* make sure pages points to a valid page in the ring buffer */
	cpu_buffer->pages = next_page;

	/* update head page */
	if (head_bit)
		cpu_buffer->head_page = list_entry(next_page,
						struct buffer_page, list);

	/*
	 * change read pointer to make sure any read iterators reset
	 * themselves
	 */
	cpu_buffer->read = 0;

	/* pages are removed, resume tracing and then free the pages */
	atomic_dec(&cpu_buffer->record_disabled);
	raw_spin_unlock_irq(&cpu_buffer->reader_lock);

	RB_WARN_ON(cpu_buffer, list_empty(cpu_buffer->pages));

	/* last buffer page to remove */
	last_page = list_entry(rb_list_head(to_remove), struct buffer_page,
				list);
	tmp_iter_page = first_page;

	do {
		to_remove_page = tmp_iter_page;
		rb_inc_page(cpu_buffer, &tmp_iter_page);

		/* update the counters */
		page_entries = rb_page_entries(to_remove_page);
		if (page_entries) {
			/*
			 * If something was added to this page, it was full
			 * since it is not the tail page. So we deduct the
			 * bytes consumed in ring buffer from here.
			 * Increment overrun to account for the lost events.
			 */
			local_add(page_entries, &cpu_buffer->overrun);
			local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes);
		}

		/*
		 * We have already removed references to this list item, just
		 * free up the buffer_page and its page
		 */
		free_buffer_page(to_remove_page);
		nr_removed--;

	} while (to_remove_page != last_page);

	RB_WARN_ON(cpu_buffer, nr_removed);

	return nr_removed == 0;
}

static int
rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer)
{
	struct list_head *pages = &cpu_buffer->new_pages;
	int retries, success;

	raw_spin_lock_irq(&cpu_buffer->reader_lock);
	/*
	 * We are holding the reader lock, so the reader page won't be swapped
	 * in the ring buffer. Now we are racing with the writer trying to
	 * move head page and the tail page.
	 * We are going to adapt the reader page update process where:
	 * 1. We first splice the start and end of list of new pages between
	 *    the head page and its previous page.
	 * 2. We cmpxchg the prev_page->next to point from head page to the
	 *    start of new pages list.
	 * 3. Finally, we update the head->prev to the end of new list.
	 *
	 * We will try this process 10 times, to make sure that we don't keep
	 * spinning.
	 */
	retries = 10;
	success = 0;
	while (retries--) {
		struct list_head *head_page, *prev_page, *r;
		struct list_head *last_page, *first_page;
		struct list_head *head_page_with_bit;

		head_page = &rb_set_head_page(cpu_buffer)->list;
		if (!head_page)
			break;
		prev_page = head_page->prev;

		first_page = pages->next;
		last_page  = pages->prev;

		head_page_with_bit = (struct list_head *)
				     ((unsigned long)head_page | RB_PAGE_HEAD);

		last_page->next = head_page_with_bit;
		first_page->prev = prev_page;

		r = cmpxchg(&prev_page->next, head_page_with_bit, first_page);

		if (r == head_page_with_bit) {
			/*
			 * yay, we replaced the page pointer to our new list,
			 * now, we just have to update to head page's prev
			 * pointer to point to end of list
			 */
			head_page->prev = last_page;
			success = 1;
			break;
		}
	}

	if (success)
		INIT_LIST_HEAD(pages);
	/*
	 * If we weren't successful in adding in new pages, warn and stop
	 * tracing
	 */
	RB_WARN_ON(cpu_buffer, !success);
	raw_spin_unlock_irq(&cpu_buffer->reader_lock);

	/* free pages if they weren't inserted */
	if (!success) {
		struct buffer_page *bpage, *tmp;
		list_for_each_entry_safe(bpage, tmp, &cpu_buffer->new_pages,
					 list) {
			list_del_init(&bpage->list);
			free_buffer_page(bpage);
		}
	}
	return success;
}

static void rb_update_pages(struct ring_buffer_per_cpu *cpu_buffer)
{
	int success;

	if (cpu_buffer->nr_pages_to_update > 0)
		success = rb_insert_pages(cpu_buffer);
	else
		success = rb_remove_pages(cpu_buffer,
					-cpu_buffer->nr_pages_to_update);

	if (success)
		cpu_buffer->nr_pages += cpu_buffer->nr_pages_to_update;
}

static void update_pages_handler(struct work_struct *work)
{
	struct ring_buffer_per_cpu *cpu_buffer = container_of(work,
			struct ring_buffer_per_cpu, update_pages_work);
	rb_update_pages(cpu_buffer);
	complete(&cpu_buffer->update_done);
}

/**
 * ring_buffer_resize - resize the ring buffer
 * @buffer: the buffer to resize.
 * @size: the new size.
 * @cpu_id: the cpu buffer to resize
 *
 * Minimum size is 2 * BUF_PAGE_SIZE.
 *
 * Returns 0 on success and < 0 on failure.
 */
int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size,
			int cpu_id)
{
	struct ring_buffer_per_cpu *cpu_buffer;
	unsigned long nr_pages;
	int cpu, err = 0;

	/*
	 * Always succeed at resizing a non-existent buffer:
	 */
	if (!buffer)
		return size;

	/* Make sure the requested buffer exists */
	if (cpu_id != RING_BUFFER_ALL_CPUS &&
	    !cpumask_test_cpu(cpu_id, buffer->cpumask))
		return size;

	nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);

	/* we need a minimum of two pages */
	if (nr_pages < 2)
		nr_pages = 2;

	size = nr_pages * BUF_PAGE_SIZE;

	/*
	 * Don't succeed if resizing is disabled, as a reader might be
	 * manipulating the ring buffer and is expecting a sane state while
	 * this is true.
	 */
	if (atomic_read(&buffer->resize_disabled))
		return -EBUSY;

	/* prevent another thread from changing buffer sizes */
	mutex_lock(&buffer->mutex);

	if (cpu_id == RING_BUFFER_ALL_CPUS) {
		/* calculate the pages to update */
		for_each_buffer_cpu(buffer, cpu) {
			cpu_buffer = buffer->buffers[cpu];

			cpu_buffer->nr_pages_to_update = nr_pages -
							cpu_buffer->nr_pages;
			/*
			 * nothing more to do for removing pages or no update
			 */
			if (cpu_buffer->nr_pages_to_update <= 0)
				continue;
			/*
			 * to add pages, make sure all new pages can be
			 * allocated without receiving ENOMEM
			 */
			INIT_LIST_HEAD(&cpu_buffer->new_pages);
			if (__rb_allocate_pages(cpu_buffer->nr_pages_to_update,
						&cpu_buffer->new_pages, cpu)) {
				/* not enough memory for new pages */
				err = -ENOMEM;
				goto out_err;
			}
		}

		get_online_cpus();
		/*
		 * Fire off all the required work handlers
		 * We can't schedule on offline CPUs, but it's not necessary
		 * since we can change their buffer sizes without any race.
		 */
		for_each_buffer_cpu(buffer, cpu) {
			cpu_buffer = buffer->buffers[cpu];
			if (!cpu_buffer->nr_pages_to_update)
				continue;

			/* Can't run something on an offline CPU. */
			if (!cpu_online(cpu)) {
				rb_update_pages(cpu_buffer);
				cpu_buffer->nr_pages_to_update = 0;
			} else {
				schedule_work_on(cpu,
						&cpu_buffer->update_pages_work);
			}
		}

		/* wait for all the updates to complete */
		for_each_buffer_cpu(buffer, cpu) {
			cpu_buffer = buffer->buffers[cpu];
			if (!cpu_buffer->nr_pages_to_update)
				continue;

			if (cpu_online(cpu))
				wait_for_completion(&cpu_buffer->update_done);
			cpu_buffer->nr_pages_to_update = 0;
		}

		put_online_cpus();
	} else {
		/* Make sure this CPU has been intitialized */
		if (!cpumask_test_cpu(cpu_id, buffer->cpumask))
			goto out;

		cpu_buffer = buffer->buffers[cpu_id];

		if (nr_pages == cpu_buffer->nr_pages)
			goto out;

		cpu_buffer->nr_pages_to_update = nr_pages -
						cpu_buffer->nr_pages;

		INIT_LIST_HEAD(&cpu_buffer->new_pages);
		if (cpu_buffer->nr_pages_to_update > 0 &&
			__rb_allocate_pages(cpu_buffer->nr_pages_to_update,
					    &cpu_buffer->new_pages, cpu_id)) {
			err = -ENOMEM;
			goto out_err;
		}

		get_online_cpus();

		/* Can't run something on an offline CPU. */
		if (!cpu_online(cpu_id))
			rb_update_pages(cpu_buffer);
		else {
			schedule_work_on(cpu_id,
					 &cpu_buffer->update_pages_work);
			wait_for_completion(&cpu_buffer->update_done);
		}

		cpu_buffer->nr_pages_to_update = 0;
		put_online_cpus();
	}

 out:
	/*
	 * The ring buffer resize can happen with the ring buffer
	 * enabled, so that the update disturbs the tracing as little
	 * as possible. But if the buffer is disabled, we do not need
	 * to worry about that, and we can take the time to verify
	 * that the buffer is not corrupt.
	 */
	if (atomic_read(&buffer->record_disabled)) {
		atomic_inc(&buffer->record_disabled);
		/*
		 * Even though the buffer was disabled, we must make sure
		 * that it is truly disabled before calling rb_check_pages.
		 * There could have been a race between checking
		 * record_disable and incrementing it.
		 */
		synchronize_sched();
		for_each_buffer_cpu(buffer, cpu) {
			cpu_buffer = buffer->buffers[cpu];
			rb_check_pages(cpu_buffer);
		}
		atomic_dec(&buffer->record_disabled);
	}

	mutex_unlock(&buffer->mutex);
	return size;

 out_err:
	for_each_buffer_cpu(buffer, cpu) {
		struct buffer_page *bpage, *tmp;

		cpu_buffer = buffer->buffers[cpu];
		cpu_buffer->nr_pages_to_update = 0;

		if (list_empty(&cpu_buffer->new_pages))
			continue;

		list_for_each_entry_safe(bpage, tmp, &cpu_buffer->new_pages,
					list) {
			list_del_init(&bpage->list);
			free_buffer_page(bpage);
		}
	}
	mutex_unlock(&buffer->mutex);
	return err;
}
EXPORT_SYMBOL_GPL(ring_buffer_resize);

void ring_buffer_change_overwrite(struct ring_buffer *buffer, int val)
{
	mutex_lock(&buffer->mutex);
	if (val)
		buffer->flags |= RB_FL_OVERWRITE;
	else
		buffer->flags &= ~RB_FL_OVERWRITE;
	mutex_unlock(&buffer->mutex);
}
EXPORT_SYMBOL_GPL(ring_buffer_change_overwrite);

static __always_inline void *__rb_page_index(struct buffer_page *bpage, unsigned index)
{
	return bpage->page->data + index;
}

static __always_inline struct ring_buffer_event *
rb_reader_event(struct ring_buffer_per_cpu *cpu_buffer)
{
	return __rb_page_index(cpu_buffer->reader_page,
			       cpu_buffer->reader_page->read);
}

static __always_inline struct ring_buffer_event *
rb_iter_head_event(struct ring_buffer_iter *iter)
{
	return __rb_page_index(iter->head_page, iter->head);
}

static __always_inline unsigned rb_page_commit(struct buffer_page *bpage)
{
	return local_read(&bpage->page->commit);
}

/* Size is determined by what has been committed */
static __always_inline unsigned rb_page_size(struct buffer_page *bpage)
{
	return rb_page_commit(bpage);
}

static __always_inline unsigned
rb_commit_index(struct ring_buffer_per_cpu *cpu_buffer)
{
	return rb_page_commit(cpu_buffer->commit_page);
}

static __always_inline unsigned
rb_event_index(struct ring_buffer_event *event)
{
	unsigned long addr = (unsigned long)event;

	return (addr & ~PAGE_MASK) - BUF_PAGE_HDR_SIZE;
}

static void rb_inc_iter(struct ring_buffer_iter *iter)
{
	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;

	/*
	 * The iterator could be on the reader page (it starts there).
	 * But the head could have moved, since the reader was
	 * found. Check for this case and assign the iterator
	 * to the head page instead of next.
	 */
	if (iter->head_page == cpu_buffer->reader_page)
		iter->head_page = rb_set_head_page(cpu_buffer);
	else
		rb_inc_page(cpu_buffer, &iter->head_page);

	iter->read_stamp = iter->head_page->page->time_stamp;
	iter->head = 0;
}

/*
 * rb_handle_head_page - writer hit the head page
 *
 * Returns: +1 to retry page
 *           0 to continue
 *          -1 on error
 */
static int
rb_handle_head_page(struct ring_buffer_per_cpu *cpu_buffer,
		    struct buffer_page *tail_page,
		    struct buffer_page *next_page)
{
	struct buffer_page *new_head;
	int entries;
	int type;
	int ret;

	entries = rb_page_entries(next_page);

	/*
	 * The hard part is here. We need to move the head
	 * forward, and protect against both readers on
	 * other CPUs and writers coming in via interrupts.
	 */
	type = rb_head_page_set_update(cpu_buffer, next_page, tail_page,
				       RB_PAGE_HEAD);

	/*
	 * type can be one of four:
	 *  NORMAL - an interrupt already moved it for us
	 *  HEAD   - we are the first to get here.
	 *  UPDATE - we are the interrupt interrupting
	 *           a current move.
	 *  MOVED  - a reader on another CPU moved the next
	 *           pointer to its reader page. Give up
	 *           and try again.
	 */

	switch (type) {
	case RB_PAGE_HEAD:
		/*
		 * We changed the head to UPDATE, thus
		 * it is our responsibility to update
		 * the counters.
		 */
		local_add(entries, &cpu_buffer->overrun);
		local_sub(BUF_PAGE_SIZE, &cpu_buffer->entries_bytes);

		/*
		 * The entries will be zeroed out when we move the
		 * tail page.
		 */

		/* still more to do */
		break;

	case RB_PAGE_UPDATE:
		/*
		 * This is an interrupt that interrupt the
		 * previous update. Still more to do.
		 */
		break;
	case RB_PAGE_NORMAL:
		/*
		 * An interrupt came in before the update
		 * and processed this for us.
		 * Nothing left to do.
		 */
		return 1;
	case RB_PAGE_MOVED:
		/*
		 * The reader is on another CPU and just did
		 * a swap with our next_page.
		 * Try again.
		 */
		return 1;
	default:
		RB_WARN_ON(cpu_buffer, 1); /* WTF??? */
		return -1;
	}

	/*
	 * Now that we are here, the old head pointer is
	 * set to UPDATE. This will keep the reader from
	 * swapping the head page with the reader page.
	 * The reader (on another CPU) will spin till
	 * we are finished.
	 *
	 * We just need to protect against interrupts
	 * doing the job. We will set the next pointer
	 * to HEAD. After that, we set the old pointer
	 * to NORMAL, but only if it was HEAD before.
	 * otherwise we are an interrupt, and only
	 * want the outer most commit to reset it.
	 */
	new_head = next_page;
	rb_inc_page(cpu_buffer, &new_head);

	ret = rb_head_page_set_head(cpu_buffer, new_head, next_page,
				    RB_PAGE_NORMAL);

	/*
	 * Valid returns are:
	 *  HEAD   - an interrupt came in and already set it.
	 *  NORMAL - One of two things:
	 *            1) We really set it.
	 *            2) A bunch of interrupts came in and moved
	 *               the page forward again.
	 */
	switch (ret) {
	case RB_PAGE_HEAD:
	case RB_PAGE_NORMAL:
		/* OK */
		break;
	default:
		RB_WARN_ON(cpu_buffer, 1);
		return -1;
	}

	/*
	 * It is possible that an interrupt came in,
	 * set the head up, then more interrupts came in
	 * and moved it again. When we get back here,
	 * the page would have been set to NORMAL but we
	 * just set it back to HEAD.
	 *
	 * How do you detect this? Well, if that happened
	 * the tail page would have moved.
	 */
	if (ret == RB_PAGE_NORMAL) {
		struct buffer_page *buffer_tail_page;

		buffer_tail_page = READ_ONCE(cpu_buffer->tail_page);
		/*
		 * If the tail had moved passed next, then we need
		 * to reset the pointer.
		 */
		if (buffer_tail_page != tail_page &&
		    buffer_tail_page != next_page)
			rb_head_page_set_normal(cpu_buffer, new_head,
						next_page,
						RB_PAGE_HEAD);
	}

	/*
	 * If this was the outer most commit (the one that
	 * changed the original pointer from HEAD to UPDATE),
	 * then it is up to us to reset it to NORMAL.
	 */
	if (type == RB_PAGE_HEAD) {
		ret = rb_head_page_set_normal(cpu_buffer, next_page,
					      tail_page,
					      RB_PAGE_UPDATE);
		if (RB_WARN_ON(cpu_buffer,
			       ret != RB_PAGE_UPDATE))
			return -1;
	}

	return 0;
}

static inline void
rb_reset_tail(struct ring_buffer_per_cpu *cpu_buffer,
	      unsigned long tail, struct rb_event_info *info)
{
	struct buffer_page *tail_page = info->tail_page;
	struct ring_buffer_event *event;
	unsigned long length = info->length;

	/*
	 * Only the event that crossed the page boundary
	 * must fill the old tail_page with padding.
	 */
	if (tail >= BUF_PAGE_SIZE) {
		/*
		 * If the page was filled, then we still need
		 * to update the real_end. Reset it to zero
		 * and the reader will ignore it.
		 */
		if (tail == BUF_PAGE_SIZE)
			tail_page->real_end = 0;

		local_sub(length, &tail_page->write);
		return;
	}

	event = __rb_page_index(tail_page, tail);

	/* account for padding bytes */
	local_add(BUF_PAGE_SIZE - tail, &cpu_buffer->entries_bytes);

	/*
	 * Save the original length to the meta data.
	 * This will be used by the reader to add lost event
	 * counter.
	 */
	tail_page->real_end = tail;

	/*
	 * If this event is bigger than the minimum size, then
	 * we need to be careful that we don't subtract the
	 * write counter enough to allow another writer to slip
	 * in on this page.
	 * We put in a discarded commit instead, to make sure
	 * that this space is not used again.
	 *
	 * If we are less than the minimum size, we don't need to
	 * worry about it.
	 */
	if (tail > (BUF_PAGE_SIZE - RB_EVNT_MIN_SIZE)) {
		/* No room for any events */

		/* Mark the rest of the page with padding */
		rb_event_set_padding(event);

		/* Set the write back to the previous setting */
		local_sub(length, &tail_page->write);
		return;
	}

	/* Put in a discarded event */
	event->array[0] = (BUF_PAGE_SIZE - tail) - RB_EVNT_HDR_SIZE;
	event->type_len = RINGBUF_TYPE_PADDING;
	/* time delta must be non zero */
	event->time_delta = 1;

	/* Set write to end of buffer */
	length = (tail + length) - BUF_PAGE_SIZE;
	local_sub(length, &tail_page->write);
}

static inline void rb_end_commit(struct ring_buffer_per_cpu *cpu_buffer);

/*
 * This is the slow path, force gcc not to inline it.
 */
static noinline struct ring_buffer_event *
rb_move_tail(struct ring_buffer_per_cpu *cpu_buffer,
	     unsigned long tail, struct rb_event_info *info)
{
	struct buffer_page *tail_page = info->tail_page;
	struct buffer_page *commit_page = cpu_buffer->commit_page;
	struct ring_buffer *buffer = cpu_buffer->buffer;
	struct buffer_page *next_page;
	int ret;

	next_page = tail_page;

	rb_inc_page(cpu_buffer, &next_page);

	/*
	 * If for some reason, we had an interrupt storm that made
	 * it all the way around the buffer, bail, and warn
	 * about it.
	 */
	if (unlikely(next_page == commit_page)) {
		local_inc(&cpu_buffer->commit_overrun);
		goto out_reset;
	}

	/*
	 * This is where the fun begins!
	 *
	 * We are fighting against races between a reader that
	 * could be on another CPU trying to swap its reader
	 * page with the buffer head.
	 *
	 * We are also fighting against interrupts coming in and
	 * moving the head or tail on us as well.
	 *
	 * If the next page is the head page then we have filled
	 * the buffer, unless the commit page is still on the
	 * reader page.
	 */
	if (rb_is_head_page(cpu_buffer, next_page, &tail_page->list)) {

		/*
		 * If the commit is not on the reader page, then
		 * move the header page.
		 */
		if (!rb_is_reader_page(cpu_buffer->commit_page)) {
			/*
			 * If we are not in overwrite mode,
			 * this is easy, just stop here.
			 */
			if (!(buffer->flags & RB_FL_OVERWRITE)) {
				local_inc(&cpu_buffer->dropped_events);
				goto out_reset;
			}

			ret = rb_handle_head_page(cpu_buffer,
						  tail_page,
						  next_page);
			if (ret < 0)
				goto out_reset;
			if (ret)
				goto out_again;
		} else {
			/*
			 * We need to be careful here too. The
			 * commit page could still be on the reader
			 * page. We could have a small buffer, and
			 * have filled up the buffer with events
			 * from interrupts and such, and wrapped.
			 *
			 * Note, if the tail page is also the on the
			 * reader_page, we let it move out.
			 */
			if (unlikely((cpu_buffer->commit_page !=
				      cpu_buffer->tail_page) &&
				     (cpu_buffer->commit_page ==
				      cpu_buffer->reader_page))) {
				local_inc(&cpu_buffer->commit_overrun);
				goto out_reset;
			}
		}
	}

	rb_tail_page_update(cpu_buffer, tail_page, next_page);

 out_again:

	rb_reset_tail(cpu_buffer, tail, info);

	/* Commit what we have for now. */
	rb_end_commit(cpu_buffer);
	/* rb_end_commit() decs committing */
	local_inc(&cpu_buffer->committing);

	/* fail and let the caller try again */
	return ERR_PTR(-EAGAIN);

 out_reset:
	/* reset write */
	rb_reset_tail(cpu_buffer, tail, info);

	return NULL;
}

/* Slow path, do not inline */
static noinline struct ring_buffer_event *
rb_add_time_stamp(struct ring_buffer_event *event, u64 delta)
{
	event->type_len = RINGBUF_TYPE_TIME_EXTEND;

	/* Not the first event on the page? */
	if (rb_event_index(event)) {
		event->time_delta = delta & TS_MASK;
		event->array[0] = delta >> TS_SHIFT;
	} else {
		/* nope, just zero it */
		event->time_delta = 0;
		event->array[0] = 0;
	}

	return skip_time_extend(event);
}

static inline bool rb_event_is_commit(struct ring_buffer_per_cpu *cpu_buffer,
				     struct ring_buffer_event *event);

/**
 * rb_update_event - update event type and data
 * @event: the event to update
 * @type: the type of event
 * @length: the size of the event field in the ring buffer
 *
 * Update the type and data fields of the event. The length
 * is the actual size that is written to the ring buffer,
 * and with this, we can determine what to place into the
 * data field.
 */
static void
rb_update_event(struct ring_buffer_per_cpu *cpu_buffer,
		struct ring_buffer_event *event,
		struct rb_event_info *info)
{
	unsigned length = info->length;
	u64 delta = info->delta;

	/* Only a commit updates the timestamp */
	if (unlikely(!rb_event_is_commit(cpu_buffer, event)))
		delta = 0;

	/*
	 * If we need to add a timestamp, then we
	 * add it to the start of the resevered space.
	 */
	if (unlikely(info->add_timestamp)) {
		event = rb_add_time_stamp(event, delta);
		length -= RB_LEN_TIME_EXTEND;
		delta = 0;
	}

	event->time_delta = delta;
	length -= RB_EVNT_HDR_SIZE;
	if (length > RB_MAX_SMALL_DATA || RB_FORCE_8BYTE_ALIGNMENT) {
		event->type_len = 0;
		event->array[0] = length;
	} else
		event->type_len = DIV_ROUND_UP(length, RB_ALIGNMENT);
}

static unsigned rb_calculate_event_length(unsigned length)
{
	struct ring_buffer_event event; /* Used only for sizeof array */

	/* zero length can cause confusions */
	if (!length)
		length++;

	if (length > RB_MAX_SMALL_DATA || RB_FORCE_8BYTE_ALIGNMENT)
		length += sizeof(event.array[0]);

	length += RB_EVNT_HDR_SIZE;
	length = ALIGN(length, RB_ARCH_ALIGNMENT);

	/*
	 * In case the time delta is larger than the 27 bits for it
	 * in the header, we need to add a timestamp. If another
	 * event comes in when trying to discard this one to increase
	 * the length, then the timestamp will be added in the allocated
	 * space of this event. If length is bigger than the size needed
	 * for the TIME_EXTEND, then padding has to be used. The events
	 * length must be either RB_LEN_TIME_EXTEND, or greater than or equal
	 * to RB_LEN_TIME_EXTEND + 8, as 8 is the minimum size for padding.
	 * As length is a multiple of 4, we only need to worry if it
	 * is 12 (RB_LEN_TIME_EXTEND + 4).
	 */
	if (length == RB_LEN_TIME_EXTEND + RB_ALIGNMENT)
		length += RB_ALIGNMENT;

	return length;
}

#ifndef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
static inline bool sched_clock_stable(void)
{
	return true;
}
#endif

static inline int
rb_try_to_discard(struct ring_buffer_per_cpu *cpu_buffer,
		  struct ring_buffer_event *event)
{
	unsigned long new_index, old_index;
	struct buffer_page *bpage;
	unsigned long index;
	unsigned long addr;

	new_index = rb_event_index(event);
	old_index = new_index + rb_event_ts_length(event);
	addr = (unsigned long)event;
	addr &= PAGE_MASK;

	bpage = READ_ONCE(cpu_buffer->tail_page);

	if (bpage->page == (void *)addr && rb_page_write(bpage) == old_index) {
		unsigned long write_mask =
			local_read(&bpage->write) & ~RB_WRITE_MASK;
		unsigned long event_length = rb_event_length(event);
		/*
		 * This is on the tail page. It is possible that
		 * a write could come in and move the tail page
		 * and write to the next page. That is fine
		 * because we just shorten what is on this page.
		 */
		old_index += write_mask;
		new_index += write_mask;
		index = local_cmpxchg(&bpage->write, old_index, new_index);
		if (index == old_index) {
			/* update counters */
			local_sub(event_length, &cpu_buffer->entries_bytes);
			return 1;
		}
	}

	/* could not discard */
	return 0;
}

static void rb_start_commit(struct ring_buffer_per_cpu *cpu_buffer)
{
	local_inc(&cpu_buffer->committing);
	local_inc(&cpu_buffer->commits);
}

static __always_inline void
rb_set_commit_to_write(struct ring_buffer_per_cpu *cpu_buffer)
{
	unsigned long max_count;

	/*
	 * We only race with interrupts and NMIs on this CPU.
	 * If we own the commit event, then we can commit
	 * all others that interrupted us, since the interruptions
	 * are in stack format (they finish before they come
	 * back to us). This allows us to do a simple loop to
	 * assign the commit to the tail.
	 */
 again:
	max_count = cpu_buffer->nr_pages * 100;

	while (cpu_buffer->commit_page != READ_ONCE(cpu_buffer->tail_page)) {
		if (RB_WARN_ON(cpu_buffer, !(--max_count)))
			return;
		if (RB_WARN_ON(cpu_buffer,
			       rb_is_reader_page(cpu_buffer->tail_page)))
			return;
		local_set(&cpu_buffer->commit_page->page->commit,
			  rb_page_write(cpu_buffer->commit_page));
		rb_inc_page(cpu_buffer, &cpu_buffer->commit_page);
		/* Only update the write stamp if the page has an event */
		if (rb_page_write(cpu_buffer->commit_page))
			cpu_buffer->write_stamp =
				cpu_buffer->commit_page->page->time_stamp;
		/* add barrier to keep gcc from optimizing too much */
		barrier();
	}
	while (rb_commit_index(cpu_buffer) !=
	       rb_page_write(cpu_buffer->commit_page)) {

		local_set(&cpu_buffer->commit_page->page->commit,
			  rb_page_write(cpu_buffer->commit_page));
		RB_WARN_ON(cpu_buffer,
			   local_read(&cpu_buffer->commit_page->page->commit) &
			   ~RB_WRITE_MASK);
		barrier();
	}

	/* again, keep gcc from optimizing */
	barrier();

	/*
	 * If an interrupt came in just after the first while loop
	 * and pushed the tail page forward, we will be left with
	 * a dangling commit that will never go forward.
	 */
	if (unlikely(cpu_buffer->commit_page != READ_ONCE(cpu_buffer->tail_page)))
		goto again;
}

static __always_inline void rb_end_commit(struct ring_buffer_per_cpu *cpu_buffer)
{
	unsigned long commits;

	if (RB_WARN_ON(cpu_buffer,
		       !local_read(&cpu_buffer->committing)))
		return;

 again:
	commits = local_read(&cpu_buffer->commits);
	/* synchronize with interrupts */
	barrier();
	if (local_read(&cpu_buffer->committing) == 1)
		rb_set_commit_to_write(cpu_buffer);

	local_dec(&cpu_buffer->committing);

	/* synchronize with interrupts */
	barrier();

	/*
	 * Need to account for interrupts coming in between the
	 * updating of the commit page and the clearing of the
	 * committing counter.
	 */
	if (unlikely(local_read(&cpu_buffer->commits) != commits) &&
	    !local_read(&cpu_buffer->committing)) {
		local_inc(&cpu_buffer->committing);
		goto again;
	}
}

static inline void rb_event_discard(struct ring_buffer_event *event)
{
	if (event->type_len == RINGBUF_TYPE_TIME_EXTEND)
		event = skip_time_extend(event);

	/* array[0] holds the actual length for the discarded event */
	event->array[0] = rb_event_data_length(event) - RB_EVNT_HDR_SIZE;
	event->type_len = RINGBUF_TYPE_PADDING;
	/* time delta must be non zero */
	if (!event->time_delta)
		event->time_delta = 1;
}

static __always_inline bool
rb_event_is_commit(struct ring_buffer_per_cpu *cpu_buffer,
		   struct ring_buffer_event *event)
{
	unsigned long addr = (unsigned long)event;
	unsigned long index;

	index = rb_event_index(event);
	addr &= PAGE_MASK;

	return cpu_buffer->commit_page->page == (void *)addr &&
		rb_commit_index(cpu_buffer) == index;
}

static __always_inline void
rb_update_write_stamp(struct ring_buffer_per_cpu *cpu_buffer,
		      struct ring_buffer_event *event)
{
	u64 delta;

	/*
	 * The event first in the commit queue updates the
	 * time stamp.
	 */
	if (rb_event_is_commit(cpu_buffer, event)) {
		/*
		 * A commit event that is first on a page
		 * updates the write timestamp with the page stamp
		 */
		if (!rb_event_index(event))
			cpu_buffer->write_stamp =
				cpu_buffer->commit_page->page->time_stamp;
		else if (event->type_len == RINGBUF_TYPE_TIME_EXTEND) {
			delta = event->array[0];
			delta <<= TS_SHIFT;
			delta += event->time_delta;
			cpu_buffer->write_stamp += delta;
		} else
			cpu_buffer->write_stamp += event->time_delta;
	}
}

static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer,
		      struct ring_buffer_event *event)
{
	local_inc(&cpu_buffer->entries);
	rb_update_write_stamp(cpu_buffer, event);
	rb_end_commit(cpu_buffer);
}

static __always_inline void
rb_wakeups(struct ring_buffer *buffer, struct ring_buffer_per_cpu *cpu_buffer)
{
	bool pagebusy;

	if (buffer->irq_work.waiters_pending) {
		buffer->irq_work.waiters_pending = false;
		/* irq_work_queue() supplies it's own memory barriers */
		irq_work_queue(&buffer->irq_work.work);
	}

	if (cpu_buffer->irq_work.waiters_pending) {
		cpu_buffer->irq_work.waiters_pending = false;
		/* irq_work_queue() supplies it's own memory barriers */
		irq_work_queue(&cpu_buffer->irq_work.work);
	}

	pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page;

	if (!pagebusy && cpu_buffer->irq_work.full_waiters_pending) {
		cpu_buffer->irq_work.wakeup_full = true;
		cpu_buffer->irq_work.full_waiters_pending = false;
		/* irq_work_queue() supplies it's own memory barriers */
		irq_work_queue(&cpu_buffer->irq_work.work);
	}
}

/*
 * The lock and unlock are done within a preempt disable section.
 * The current_context per_cpu variable can only be modified
 * by the current task between lock and unlock. But it can
 * be modified more than once via an interrupt. To pass this
 * information from the lock to the unlock without having to
 * access the 'in_interrupt()' functions again (which do show
 * a bit of overhead in something as critical as function tracing,
 * we use a bitmask trick.
 *
 *  bit 0 =  NMI context
 *  bit 1 =  IRQ context
 *  bit 2 =  SoftIRQ context
 *  bit 3 =  normal context.
 *
 * This works because this is the order of contexts that can
 * preempt other contexts. A SoftIRQ never preempts an IRQ
 * context.
 *
 * When the context is determined, the corresponding bit is
 * checked and set (if it was set, then a recursion of that context
 * happened).
 *
 * On unlock, we need to clear this bit. To do so, just subtract
 * 1 from the current_context and AND it to itself.
 *
 * (binary)
 *  101 - 1 = 100
 *  101 & 100 = 100 (clearing bit zero)
 *
 *  1010 - 1 = 1001
 *  1010 & 1001 = 1000 (clearing bit 1)
 *
 * The least significant bit can be cleared this way, and it
 * just so happens that it is the same bit corresponding to
 * the current context.
 */

static __always_inline int
trace_recursive_lock(struct ring_buffer_per_cpu *cpu_buffer)
{
	unsigned int val = cpu_buffer->current_context;
	unsigned long pc = preempt_count();
	int bit;

	if (!(pc & (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET)))
		bit = RB_CTX_NORMAL;
	else
		bit = pc & NMI_MASK ? RB_CTX_NMI :
			pc & HARDIRQ_MASK ? RB_CTX_IRQ : RB_CTX_SOFTIRQ;

	if (unlikely(val & (1 << bit)))
		return 1;

	val |= (1 << bit);
	cpu_buffer->current_context = val;

	return 0;
}

static __always_inline void
trace_recursive_unlock(struct ring_buffer_per_cpu *cpu_buffer)
{
	cpu_buffer->current_context &= cpu_buffer->current_context - 1;
}

/**
 * ring_buffer_unlock_commit - commit a reserved
 * @buffer: The buffer to commit to
 * @event: The event pointer to commit.
 *
 * This commits the data to the ring buffer, and releases any locks held.
 *
 * Must be paired with ring_buffer_lock_reserve.
 */
int ring_buffer_unlock_commit(struct ring_buffer *buffer,
			      struct ring_buffer_event *event)
{
	struct ring_buffer_per_cpu *cpu_buffer;
	int cpu = raw_smp_processor_id();

	cpu_buffer = buffer->buffers[cpu];

	rb_commit(cpu_buffer, event);

	rb_wakeups(buffer, cpu_buffer);

	trace_recursive_unlock(cpu_buffer);

	preempt_enable_notrace();

	return 0;
}
EXPORT_SYMBOL_GPL(ring_buffer_unlock_commit);

static noinline void
rb_handle_timestamp(struct ring_buffer_per_cpu *cpu_buffer,
		    struct rb_event_info *info)
{
	WARN_ONCE(info->delta > (1ULL << 59),
		  KERN_WARNING "Delta way too big! %llu ts=%llu write stamp = %llu\n%s",
		  (unsigned long long)info->delta,
		  (unsigned long long)info->ts,
		  (unsigned long long)cpu_buffer->write_stamp,
		  sched_clock_stable() ? "" :
		  "If you just came from a suspend/resume,\n"
		  "please switch to the trace global clock:\n"
		  "  echo global > /sys/kernel/debug/tracing/trace_clock\n");
	info->add_timestamp = 1;
}

static struct ring_buffer_event *
__rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
		  struct rb_event_info *info)
{
	struct ring_buffer_event *event;
	struct buffer_page *tail_page;
	unsigned long tail, write;

	/*
	 * If the time delta since the last event is too big to
	 * hold in the time field of the event, then we append a
	 * TIME EXTEND event ahead of the data event.
	 */
	if (unlikely(info->add_timestamp))
		info->length += RB_LEN_TIME_EXTEND;

	/* Don't let the compiler play games with cpu_buffer->tail_page */
	tail_page = info->tail_page = READ_ONCE(cpu_buffer->tail_page);
	write = local_add_return(info->length, &tail_page->write);

	/* set write to only the index of the write */
	write &= RB_WRITE_MASK;
	tail = write - info->length;

	/*
	 * If this is the first commit on the page, then it has the same
	 * timestamp as the page itself.
	 */
	if (!tail)
		info->delta = 0;

	/* See if we shot pass the end of this buffer page */
	if (unlikely(write > BUF_PAGE_SIZE))
		return rb_move_tail(cpu_buffer, tail, info);

	/* We reserved something on the buffer */

	event = __rb_page_index(tail_page, tail);
	rb_update_event(cpu_buffer, event, info);

	local_inc(&tail_page->entries);

	/*
	 * If this is the first commit on the page, then update
	 * its timestamp.
	 */
	if (!tail)
		tail_page->page->time_stamp = info->ts;

	/* account for these added bytes */
	local_add(info->length, &cpu_buffer->entries_bytes);

	return event;
}

static __always_inline struct ring_buffer_event *
rb_reserve_next_event(struct ring_buffer *buffer,
		      struct ring_buffer_per_cpu *cpu_buffer,
		      unsigned long length)
{
	struct ring_buffer_event *event;
	struct rb_event_info info;
	int nr_loops = 0;
	u64 diff;

	rb_start_commit(cpu_buffer);

#ifdef CONFIG_RING_BUFFER_ALLOW_SWAP
	/*
	 * Due to the ability to swap a cpu buffer from a buffer
	 * it is possible it was swapped before we committed.
	 * (committing stops a swap). We check for it here and
	 * if it happened, we have to fail the write.
	 */
	barrier();
	if (unlikely(READ_ONCE(cpu_buffer->buffer) != buffer)) {
		local_dec(&cpu_buffer->committing);
		local_dec(&cpu_buffer->commits);
		return NULL;
	}
#endif

	info.length = rb_calculate_event_length(length);
 again:
	info.add_timestamp = 0;
	info.delta = 0;

	/*
	 * We allow for interrupts to reenter here and do a trace.
	 * If one does, it will cause this original code to loop
	 * back here. Even with heavy interrupts happening, this
	 * should only happen a few times in a row. If this happens
	 * 1000 times in a row, there must be either an interrupt
	 * storm or we have something buggy.
	 * Bail!
	 */
	if (RB_WARN_ON(cpu_buffer, ++nr_loops > 1000))
		goto out_fail;

	info.ts = rb_time_stamp(cpu_buffer->buffer);
	diff = info.ts - cpu_buffer->write_stamp;

	/* make sure this diff is calculated here */
	barrier();

	/* Did the write stamp get updated already? */
	if (likely(info.ts >= cpu_buffer->write_stamp)) {
		info.delta = diff;
		if (unlikely(test_time_stamp(info.delta)))
			rb_handle_timestamp(cpu_buffer, &info);
	}

	event = __rb_reserve_next(cpu_buffer, &info);

	if (unlikely(PTR_ERR(event) == -EAGAIN)) {
		if (info.add_timestamp)
			info.length -= RB_LEN_TIME_EXTEND;
		goto again;
	}

	if (!event)
		goto out_fail;

	return event;

 out_fail:
	rb_end_commit(cpu_buffer);
	return NULL;
}

/**
 * ring_buffer_lock_reserve - reserve a part of the buffer
 * @buffer: the ring buffer to reserve from
 * @length: the length of the data to reserve (excluding event header)
 *
 * Returns a reseverd event on the ring buffer to copy directly to.
 * The user of this interface will need to get the body to write into
 * and can use the ring_buffer_event_data() interface.
 *
 * The length is the length of the data needed, not the event length
 * which also includes the event header.
 *
 * Must be paired with ring_buffer_unlock_commit, unless NULL is returned.
 * If NULL is returned, then nothing has been allocated or locked.
 */
struct ring_buffer_event *
ring_buffer_lock_reserve(struct ring_buffer *buffer, unsigned long length)
{
	struct ring_buffer_per_cpu *cpu_buffer;
	struct ring_buffer_event *event;
	int cpu;

	/* If we are tracing schedule, we don't want to recurse */
	preempt_disable_notrace();

	if (unlikely(atomic_read(&buffer->record_disabled)))
		goto out;

	cpu = raw_smp_processor_id();

	if (unlikely(!cpumask_test_cpu(cpu, buffer->cpumask)))
		goto out;

	cpu_buffer = buffer->buffers[cpu];

	if (unlikely(atomic_read(&cpu_buffer->record_disabled)))
		goto out;

	if (unlikely(length > BUF_MAX_DATA_SIZE))
		goto out;

	if (unlikely(trace_recursive_lock(cpu_buffer)))
		goto out;

	event = rb_reserve_next_event(buffer, cpu_buffer, length);
	if (!event)
		goto out_unlock;

	return event;

 out_unlock:
	trace_recursive_unlock(cpu_buffer);
 out:
	preempt_enable_notrace();
	return NULL;
}
EXPORT_SYMBOL_GPL(ring_buffer_lock_reserve);

/*
 * Decrement the entries to the page that an event is on.
 * The event does not even need to exist, only the pointer
 * to the page it is on. This may only be called before the commit
 * takes place.
 */
static inline void
rb_decrement_entry(struct ring_buffer_per_cpu *cpu_buffer,
		   struct ring_buffer_event *event)
{
	unsigned long addr = (unsigned long)event;
	struct buffer_page *bpage = cpu_buffer->commit_page;
	struct buffer_page *start;

	addr &= PAGE_MASK;

	/* Do the likely case first */
	if (likely(bpage->page == (void *)addr)) {
		local_dec(&bpage->entries);
		return;
	}

	/*
	 * Because the commit page may be on the reader page we
	 * start with the next page and check the end loop there.
	 */
	rb_inc_page(cpu_buffer, &bpage);
	start = bpage;
	do {
		if (bpage->page == (void *)addr) {
			local_dec(&bpage->entries);
			return;
		}
		rb_inc_page(cpu_buffer, &bpage);
	} while (bpage != start);

	/* commit not part of this buffer?? */
	RB_WARN_ON(cpu_buffer, 1);
}

/**
 * ring_buffer_commit_discard - discard an event that has not been committed
 * @buffer: the ring buffer
 * @event: non committed event to discard
 *
 * Sometimes an event that is in the ring buffer needs to be ignored.
 * This function lets the user discard an event in the ring buffer
 * and then that event will not be read later.
 *
 * This function only works if it is called before the the item has been
 * committed. It will try to free the event from the ring buffer
 * if another event has not been added behind it.
 *
 * If another event has been added behind it, it will set the event
 * up as discarded, and perform the commit.
 *
 * If this function is called, do not call ring_buffer_unlock_commit on
 * the event.
 */
void ring_buffer_discard_commit(struct ring_buffer *buffer,
				struct ring_buffer_event *event)
{
	struct ring_buffer_per_cpu *cpu_buffer;
	int cpu;

	/* The event is discarded regardless */
	rb_event_discard(event);

	cpu = smp_processor_id();
	cpu_buffer = buffer->buffers[cpu];

	/*
	 * This must only be called if the event has not been
	 * committed yet. Thus we can assume that preemption
	 * is still disabled.
	 */
	RB_WARN_ON(buffer, !local_read(&cpu_buffer->committing));

	rb_decrement_entry(cpu_buffer, event);
	if (rb_try_to_discard(cpu_buffer, event))
		goto out;

	/*
	 * The commit is still visible by the reader, so we
	 * must still update the timestamp.
	 */
	rb_update_write_stamp(cpu_buffer, event);
 out:
	rb_end_commit(cpu_buffer);

	trace_recursive_unlock(cpu_buffer);

	preempt_enable_notrace();

}
EXPORT_SYMBOL_GPL(ring_buffer_discard_commit);

/**
 * ring_buffer_write - write data to the buffer without reserving
 * @buffer: The ring buffer to write to.
 * @length: The length of the data being written (excluding the event header)
 * @data: The data to write to the buffer.
 *
 * This is like ring_buffer_lock_reserve and ring_buffer_unlock_commit as
 * one function. If you already have the data to write to the buffer, it
 * may be easier to simply call this function.
 *
 * Note, like ring_buffer_lock_reserve, the length is the length of the data
 * and not the length of the event which would hold the header.
 */
int ring_buffer_write(struct ring_buffer *buffer,
		      unsigned long length,
		      void *data)
{
	struct ring_buffer_per_cpu *cpu_buffer;
	struct ring_buffer_event *event;
	void *body;
	int ret = -EBUSY;
	int cpu;

	preempt_disable_notrace();

	if (atomic_read(&buffer->record_disabled))
		goto out;

	cpu = raw_smp_processor_id();

	if (!cpumask_test_cpu(cpu, buffer->cpumask))
		goto out;

	cpu_buffer = buffer->buffers[cpu];

	if (atomic_read(&cpu_buffer->record_disabled))
		goto out;

	if (length > BUF_MAX_DATA_SIZE)
		goto out;

	if (unlikely(trace_recursive_lock(cpu_buffer)))
		goto out;

	event = rb_reserve_next_event(buffer, cpu_buffer, length);
	if (!event)
		goto out_unlock;

	body = rb_event_data(event);

	memcpy(body, data, length);

	rb_commit(cpu_buffer, event);

	rb_wakeups(buffer, cpu_buffer);

	ret = 0;

 out_unlock:
	trace_recursive_unlock(cpu_buffer);

 out:
	preempt_enable_notrace();

	return ret;
}
EXPORT_SYMBOL_GPL(ring_buffer_write);

static bool rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer)
{
	struct buffer_page *reader = cpu_buffer->reader_page;
	struct buffer_page *head = rb_set_head_page(cpu_buffer);
	struct buffer_page *commit = cpu_buffer->commit_page;

	/* In case of error, head will be NULL */
	if (unlikely(!head))
		return true;

	return reader->read == rb_page_commit(reader) &&
		(commit == reader ||
		 (commit == head &&
		  head->read == rb_page_commit(commit)));
}

/**
 * ring_buffer_record_disable - stop all writes into the buffer
 * @buffer: The ring buffer to stop writes to.
 *
 * This prevents all writes to the buffer. Any attempt to write
 * to the buffer after this will fail and return NULL.
 *
 * The caller should call synchronize_sched() after this.
 */
void ring_buffer_record_disable(struct ring_buffer *buffer)
{
	atomic_inc(&buffer->record_disabled);
}
EXPORT_SYMBOL_GPL(ring_buffer_record_disable);

/**
 * ring_buffer_record_enable - enable writes to the buffer
 * @buffer: The ring buffer to enable writes
 *
 * Note, multiple disables will need the same number of enables
 * to truly enable the writing (much like preempt_disable).
 */
void ring_buffer_record_enable(struct ring_buffer *buffer)
{
	atomic_dec(&buffer->record_disabled);
}
EXPORT_SYMBOL_GPL(ring_buffer_record_enable);

/**
 * ring_buffer_record_off - stop all writes into the buffer
 * @buffer: The ring buffer to stop writes to.
 *
 * This prevents all writes to the buffer. Any attempt to write
 * to the buffer after this will fail and return NULL.
 *
 * This is different than ring_buffer_record_disable() as
 * it works like an on/off switch, where as the disable() version
 * must be paired with a enable().
 */
void ring_buffer_record_off(struct ring_buffer *buffer)
{
	unsigned int rd;
	unsigned int new_rd;

	do {
		rd = atomic_read(&buffer->record_disabled);
		new_rd = rd | RB_BUFFER_OFF;
	} while (atomic_cmpxchg(&buffer->record_disabled, rd, new_rd) != rd);
}
EXPORT_SYMBOL_GPL(ring_buffer_record_off);

/**
 * ring_buffer_record_on - restart writes into the buffer
 * @buffer: The ring buffer to start writes to.
 *
 * This enables all writes to the buffer that was disabled by
 * ring_buffer_record_off().
 *
 * This is different than ring_buffer_record_enable() as
 * it works like an on/off switch, where as the enable() version
 * must be paired with a disable().
 */
void ring_buffer_record_on(struct ring_buffer *buffer)
{
	unsigned int rd;
	unsigned int new_rd;

	do {
		rd = atomic_read(&buffer->record_disabled);
		new_rd = rd & ~RB_BUFFER_OFF;
	} while (atomic_cmpxchg(&buffer->record_disabled, rd, new_rd) != rd);
}
EXPORT_SYMBOL_GPL(ring_buffer_record_on);

/**
 * ring_buffer_record_is_on - return true if the ring buffer can write
 * @buffer: The ring buffer to see if write is enabled
 *
 * Returns true if the ring buffer is in a state that it accepts writes.
 */
int ring_buffer_record_is_on(struct ring_buffer *buffer)
{
	return !atomic_read(&buffer->record_disabled);
}

/**
 * ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer
 * @buffer: The ring buffer to stop writes to.
 * @cpu: The CPU buffer to stop
 *
 * This prevents all writes to the buffer. Any attempt to write
 * to the buffer after this will fail and return NULL.
 *
 * The caller should call synchronize_sched() after this.
 */
void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu)
{
	struct ring_buffer_per_cpu *cpu_buffer;

	if (!cpumask_test_cpu(cpu, buffer->cpumask))
		return;

	cpu_buffer = buffer->buffers[cpu];
	atomic_inc(&cpu_buffer->record_disabled);
}
EXPORT_SYMBOL_GPL(ring_buffer_record_disable_cpu);

/**
 * ring_buffer_record_enable_cpu - enable writes to the buffer
 * @buffer: The ring buffer to enable writes
 * @cpu: The CPU to enable.
 *
 * Note, multiple disables will need the same number of enables
 * to truly enable the writing (much like preempt_disable).
 */
void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu)
{
	struct ring_buffer_per_cpu *cpu_buffer;

	if (!cpumask_test_cpu(cpu, buffer->cpumask))
		return;

	cpu_buffer = buffer->buffers[cpu];
	atomic_dec(&cpu_buffer->record_disabled);
}
EXPORT_SYMBOL_GPL(ring_buffer_record_enable_cpu);

/*
 * The total entries in the ring buffer is the running counter
 * of entries entered into the ring buffer, minus the sum of
 * the entries read from the ring buffer and the number of
 * entries that were overwritten.
 */
static inline unsigned long
rb_num_of_entries(struct ring_buffer_per_cpu *cpu_buffer)
{
	return local_read(&cpu_buffer->entries) -
		(local_read(&cpu_buffer->overrun) + cpu_buffer->read);
}

/**
 * ring_buffer_oldest_event_ts - get the oldest event timestamp from the buffer
 * @buffer: The ring buffer
 * @cpu: The per CPU buffer to read from.
 */
u64 ring_buffer_oldest_event_ts(struct ring_buffer *buffer, int cpu)
{
	unsigned long flags;
	struct ring_buffer_per_cpu *cpu_buffer;
	struct buffer_page *bpage;
	u64 ret = 0;

	if (!cpumask_test_cpu(cpu, buffer->cpumask))
		return 0;

	cpu_buffer = buffer->buffers[cpu];
	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
	/*
	 * if the tail is on reader_page, oldest time stamp is on the reader
	 * page
	 */
	if (cpu_buffer->tail_page == cpu_buffer->reader_page)
		bpage = cpu_buffer->reader_page;
	else
		bpage = rb_set_head_page(cpu_buffer);
	if (bpage)
		ret = bpage->page->time_stamp;
	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);

	return ret;
}
EXPORT_SYMBOL_GPL(ring_buffer_oldest_event_ts);

/**
 * ring_buffer_bytes_cpu - get the number of bytes consumed in a cpu buffer
 * @buffer: The ring buffer
 * @cpu: The per CPU buffer to read from.
 */
unsigned long ring_buffer_bytes_cpu(struct ring_buffer *buffer, int cpu)
{
	struct ring_buffer_per_cpu *cpu_buffer;
	unsigned long ret;

	if (!cpumask_test_cpu(cpu, buffer->cpumask))
		return 0;

	cpu_buffer = buffer->buffers[cpu];
	ret = local_read(&cpu_buffer->entries_bytes) - cpu_buffer->read_bytes;

	return ret;
}
EXPORT_SYMBOL_GPL(ring_buffer_bytes_cpu);

/**
 * ring_buffer_entries_cpu - get the number of entries in a cpu buffer
 * @buffer: The ring buffer
 * @cpu: The per CPU buffer to get the entries from.
 */
unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu)
{
	struct ring_buffer_per_cpu *cpu_buffer;

	if (!cpumask_test_cpu(cpu, buffer->cpumask))
		return 0;

	cpu_buffer = buffer->buffers[cpu];

	return rb_num_of_entries(cpu_buffer);
}
EXPORT_SYMBOL_GPL(ring_buffer_entries_cpu);

/**
 * ring_buffer_overrun_cpu - get the number of overruns caused by the ring
 * buffer wrapping around (only if RB_FL_OVERWRITE is on).
 * @buffer: The ring buffer
 * @cpu: The per CPU buffer to get the number of overruns from
 */
unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu)
{
	struct ring_buffer_per_cpu *cpu_buffer;
	unsigned long ret;

	if (!cpumask_test_cpu(cpu, buffer->cpumask))
		return 0;

	cpu_buffer = buffer->buffers[cpu];
	ret = local_read(&cpu_buffer->overrun);

	return ret;
}
EXPORT_SYMBOL_GPL(ring_buffer_overrun_cpu);

/**
 * ring_buffer_commit_overrun_cpu - get the number of overruns caused by
 * commits failing due to the buffer wrapping around while there are uncommitted
 * events, such as during an interrupt storm.
 * @buffer: The ring buffer
 * @cpu: The per CPU buffer to get the number of overruns from
 */
unsigned long
ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu)
{
	struct ring_buffer_per_cpu *cpu_buffer;
	unsigned long ret;

	if (!cpumask_test_cpu(cpu, buffer->cpumask))
		return 0;

	cpu_buffer = buffer->buffers[cpu];
	ret = local_read(&cpu_buffer->commit_overrun);

	return ret;
}
EXPORT_SYMBOL_GPL(ring_buffer_commit_overrun_cpu);

/**
 * ring_buffer_dropped_events_cpu - get the number of dropped events caused by
 * the ring buffer filling up (only if RB_FL_OVERWRITE is off).
 * @buffer: The ring buffer
 * @cpu: The per CPU buffer to get the number of overruns from
 */
unsigned long
ring_buffer_dropped_events_cpu(struct ring_buffer *buffer, int cpu)
{
	struct ring_buffer_per_cpu *cpu_buffer;
	unsigned long ret;

	if (!cpumask_test_cpu(cpu, buffer->cpumask))
		return 0;

	cpu_buffer = buffer->buffers[cpu];
	ret = local_read(&cpu_buffer->dropped_events);

	return ret;
}
EXPORT_SYMBOL_GPL(ring_buffer_dropped_events_cpu);

/**
 * ring_buffer_read_events_cpu - get the number of events successfully read
 * @buffer: The ring buffer
 * @cpu: The per CPU buffer to get the number of events read
 */
unsigned long
ring_buffer_read_events_cpu(struct ring_buffer *buffer, int cpu)
{
	struct ring_buffer_per_cpu *cpu_buffer;

	if (!cpumask_test_cpu(cpu, buffer->cpumask))
		return 0;

	cpu_buffer = buffer->buffers[cpu];
	return cpu_buffer->read;
}
EXPORT_SYMBOL_GPL(ring_buffer_read_events_cpu);

/**
 * ring_buffer_entries - get the number of entries in a buffer
 * @buffer: The ring buffer
 *
 * Returns the total number of entries in the ring buffer
 * (all CPU entries)
 */
unsigned long ring_buffer_entries(struct ring_buffer *buffer)
{
	struct ring_buffer_per_cpu *cpu_buffer;
	unsigned long entries = 0;
	int cpu;

	/* if you care about this being correct, lock the buffer */
	for_each_buffer_cpu(buffer, cpu) {
		cpu_buffer = buffer->buffers[cpu];
		entries += rb_num_of_entries(cpu_buffer);
	}

	return entries;
}
EXPORT_SYMBOL_GPL(ring_buffer_entries);

/**
 * ring_buffer_overruns - get the number of overruns in buffer
 * @buffer: The ring buffer
 *
 * Returns the total number of overruns in the ring buffer
 * (all CPU entries)
 */
unsigned long ring_buffer_overruns(struct ring_buffer *buffer)
{
	struct ring_buffer_per_cpu *cpu_buffer;
	unsigned long overruns = 0;
	int cpu;

	/* if you care about this being correct, lock the buffer */
	for_each_buffer_cpu(buffer, cpu) {
		cpu_buffer = buffer->buffers[cpu];
		overruns += local_read(&cpu_buffer->overrun);
	}

	return overruns;
}
EXPORT_SYMBOL_GPL(ring_buffer_overruns);

static void rb_iter_reset(struct ring_buffer_iter *iter)
{
	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;

	/* Iterator usage is expected to have record disabled */
	iter->head_page = cpu_buffer->reader_page;
	iter->head = cpu_buffer->reader_page->read;

	iter->cache_reader_page = iter->head_page;
	iter->cache_read = cpu_buffer->read;

	if (iter->head)
		iter->read_stamp = cpu_buffer->read_stamp;
	else
		iter->read_stamp = iter->head_page->page->time_stamp;
}

/**
 * ring_buffer_iter_reset - reset an iterator
 * @iter: The iterator to reset
 *
 * Resets the iterator, so that it will start from the beginning
 * again.
 */
void ring_buffer_iter_reset(struct ring_buffer_iter *iter)
{
	struct ring_buffer_per_cpu *cpu_buffer;
	unsigned long flags;

	if (!iter)
		return;

	cpu_buffer = iter->cpu_buffer;

	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
	rb_iter_reset(iter);
	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
}
EXPORT_SYMBOL_GPL(ring_buffer_iter_reset);

/**
 * ring_buffer_iter_empty - check if an iterator has no more to read
 * @iter: The iterator to check
 */
int ring_buffer_iter_empty(struct ring_buffer_iter *iter)
{
	struct ring_buffer_per_cpu *cpu_buffer;
	struct buffer_page *reader;
	struct buffer_page *head_page;
	struct buffer_page *commit_page;
	unsigned commit;

	cpu_buffer = iter->cpu_buffer;

	/* Remember, trace recording is off when iterator is in use */
	reader = cpu_buffer->reader_page;
	head_page = cpu_buffer->head_page;
	commit_page = cpu_buffer->commit_page;
	commit = rb_page_commit(commit_page);

	return ((iter->head_page == commit_page && iter->head == commit) ||
		(iter->head_page == reader && commit_page == head_page &&
		 head_page->read == commit &&
		 iter->head == rb_page_commit(cpu_buffer->reader_page)));
}
EXPORT_SYMBOL_GPL(ring_buffer_iter_empty);

static void
rb_update_read_stamp(struct ring_buffer_per_cpu *cpu_buffer,
		     struct ring_buffer_event *event)
{
	u64 delta;

	switch (event->type_len) {
	case RINGBUF_TYPE_PADDING:
		return;

	case RINGBUF_TYPE_TIME_EXTEND:
		delta = event->array[0];
		delta <<= TS_SHIFT;
		delta += event->time_delta;
		cpu_buffer->read_stamp += delta;
		return;

	case RINGBUF_TYPE_TIME_STAMP:
		/* FIXME: not implemented */
		return;

	case RINGBUF_TYPE_DATA:
		cpu_buffer->read_stamp += event->time_delta;
		return;

	default:
		BUG();
	}
	return;
}

static void
rb_update_iter_read_stamp(struct ring_buffer_iter *iter,
			  struct ring_buffer_event *event)
{
	u64 delta;

	switch (event->type_len) {
	case RINGBUF_TYPE_PADDING:
		return;

	case RINGBUF_TYPE_TIME_EXTEND:
		delta = event->array[0];
		delta <<= TS_SHIFT;
		delta += event->time_delta;
		iter->read_stamp += delta;
		return;

	case RINGBUF_TYPE_TIME_STAMP:
		/* FIXME: not implemented */
		return;

	case RINGBUF_TYPE_DATA:
		iter->read_stamp += event->time_delta;
		return;

	default:
		BUG();
	}
	return;
}

static struct buffer_page *
rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
{
	struct buffer_page *reader = NULL;
	unsigned long overwrite;
	unsigned long flags;
	int nr_loops = 0;
	int ret;

	local_irq_save(flags);
	arch_spin_lock(&cpu_buffer->lock);

 again:
	/*
	 * This should normally only loop twice. But because the
	 * start of the reader inserts an empty page, it causes
	 * a case where we will loop three times. There should be no
	 * reason to loop four times (that I know of).
	 */
	if (RB_WARN_ON(cpu_buffer, ++nr_loops > 3)) {
		reader = NULL;
		goto out;
	}

	reader = cpu_buffer->reader_page;

	/* If there's more to read, return this page */
	if (cpu_buffer->reader_page->read < rb_page_size(reader))
		goto out;

	/* Never should we have an index greater than the size */
	if (RB_WARN_ON(cpu_buffer,
		       cpu_buffer->reader_page->read > rb_page_size(reader)))
		goto out;

	/* check if we caught up to the tail */
	reader = NULL;
	if (cpu_buffer->commit_page == cpu_buffer->reader_page)
		goto out;

	/* Don't bother swapping if the ring buffer is empty */
	if (rb_num_of_entries(cpu_buffer) == 0)
		goto out;

	/*
	 * Reset the reader page to size zero.
	 */
	local_set(&cpu_buffer->reader_page->write, 0);
	local_set(&cpu_buffer->reader_page->entries, 0);
	local_set(&cpu_buffer->reader_page->page->commit, 0);
	cpu_buffer->reader_page->real_end = 0;

 spin:
	/*
	 * Splice the empty reader page into the list around the head.
	 */
	reader = rb_set_head_page(cpu_buffer);
	if (!reader)
		goto out;
	cpu_buffer->reader_page->list.next = rb_list_head(reader->list.next);
	cpu_buffer->reader_page->list.prev = reader->list.prev;

	/*
	 * cpu_buffer->pages just needs to point to the buffer, it
	 *  has no specific buffer page to point to. Lets move it out
	 *  of our way so we don't accidentally swap it.
	 */
	cpu_buffer->pages = reader->list.prev;

	/* The reader page will be pointing to the new head */
	rb_set_list_to_head(cpu_buffer, &cpu_buffer->reader_page->list);

	/*
	 * We want to make sure we read the overruns after we set up our
	 * pointers to the next object. The writer side does a
	 * cmpxchg to cross pages which acts as the mb on the writer
	 * side. Note, the reader will constantly fail the swap
	 * while the writer is updating the pointers, so this
	 * guarantees that the overwrite recorded here is the one we
	 * want to compare with the last_overrun.
	 */
	smp_mb();
	overwrite = local_read(&(cpu_buffer->overrun));

	/*
	 * Here's the tricky part.
	 *
	 * We need to move the pointer past the header page.
	 * But we can only do that if a writer is not currently
	 * moving it. The page before the header page has the
	 * flag bit '1' set if it is pointing to the page we want.
	 * but if the writer is in the process of moving it
	 * than it will be '2' or already moved '0'.
	 */

	ret = rb_head_page_replace(reader, cpu_buffer->reader_page);

	/*
	 * If we did not convert it, then we must try again.
	 */
	if (!ret)
		goto spin;

	/*
	 * Yeah! We succeeded in replacing the page.
	 *
	 * Now make the new head point back to the reader page.
	 */
	rb_list_head(reader->list.next)->prev = &cpu_buffer->reader_page->list;
	rb_inc_page(cpu_buffer, &cpu_buffer->head_page);

	/* Finally update the reader page to the new head */
	cpu_buffer->reader_page = reader;
	cpu_buffer->reader_page->read = 0;

	if (overwrite != cpu_buffer->last_overrun) {
		cpu_buffer->lost_events = overwrite - cpu_buffer->last_overrun;
		cpu_buffer->last_overrun = overwrite;
	}

	goto again;

 out:
	/* Update the read_stamp on the first event */
	if (reader && reader->read == 0)
		cpu_buffer->read_stamp = reader->page->time_stamp;

	arch_spin_unlock(&cpu_buffer->lock);
	local_irq_restore(flags);

	return reader;
}

static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer)
{
	struct ring_buffer_event *event;
	struct buffer_page *reader;
	unsigned length;

	reader = rb_get_reader_page(cpu_buffer);

	/* This function should not be called when buffer is empty */
	if (RB_WARN_ON(cpu_buffer, !reader))
		return;

	event = rb_reader_event(cpu_buffer);

	if (event->type_len <= RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
		cpu_buffer->read++;

	rb_update_read_stamp(cpu_buffer, event);

	length = rb_event_length(event);
	cpu_buffer->reader_page->read += length;
}

static void rb_advance_iter(struct ring_buffer_iter *iter)
{
	struct ring_buffer_per_cpu *cpu_buffer;
	struct ring_buffer_event *event;
	unsigned length;

	cpu_buffer = iter->cpu_buffer;

	/*
	 * Check if we are at the end of the buffer.
	 */
	if (iter->head >= rb_page_size(iter->head_page)) {
		/* discarded commits can make the page empty */
		if (iter->head_page == cpu_buffer->commit_page)
			return;
		rb_inc_iter(iter);
		return;
	}

	event = rb_iter_head_event(iter);

	length = rb_event_length(event);

	/*
	 * This should not be called to advance the header if we are
	 * at the tail of the buffer.
	 */
	if (RB_WARN_ON(cpu_buffer,
		       (iter->head_page == cpu_buffer->commit_page) &&
		       (iter->head + length > rb_commit_index(cpu_buffer))))
		return;

	rb_update_iter_read_stamp(iter, event);

	iter->head += length;

	/* check for end of page padding */
	if ((iter->head >= rb_page_size(iter->head_page)) &&
	    (iter->head_page != cpu_buffer->commit_page))
		rb_inc_iter(iter);
}

static int rb_lost_events(struct ring_buffer_per_cpu *cpu_buffer)
{
	return cpu_buffer->lost_events;
}

static struct ring_buffer_event *
rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts,
	       unsigned long *lost_events)
{
	struct ring_buffer_event *event;
	struct buffer_page *reader;
	int nr_loops = 0;

 again:
	/*
	 * We repeat when a time extend is encountered.
	 * Since the time extend is always attached to a data event,
	 * we should never loop more than once.
	 * (We never hit the following condition more than twice).
	 */
	if (RB_WARN_ON(cpu_buffer, ++nr_loops > 2))
		return NULL;

	reader = rb_get_reader_page(cpu_buffer);
	if (!reader)
		return NULL;

	event = rb_reader_event(cpu_buffer);

	switch (event->type_len) {
	case RINGBUF_TYPE_PADDING:
		if (rb_null_event(event))
			RB_WARN_ON(cpu_buffer, 1);
		/*
		 * Because the writer could be discarding every
		 * event it creates (which would probably be bad)
		 * if we were to go back to "again" then we may never
		 * catch up, and will trigger the warn on, or lock
		 * the box. Return the padding, and we will release
		 * the current locks, and try again.
		 */
		return event;

	case RINGBUF_TYPE_TIME_EXTEND:
		/* Internal data, OK to advance */
		rb_advance_reader(cpu_buffer);
		goto again;

	case RINGBUF_TYPE_TIME_STAMP:
		/* FIXME: not implemented */
		rb_advance_reader(cpu_buffer);
		goto again;

	case RINGBUF_TYPE_DATA:
		if (ts) {
			*ts = cpu_buffer->read_stamp + event->time_delta;
			ring_buffer_normalize_time_stamp(cpu_buffer->buffer,
							 cpu_buffer->cpu, ts);
		}
		if (lost_events)
			*lost_events = rb_lost_events(cpu_buffer);
		return event;

	default:
		BUG();
	}

	return NULL;
}
EXPORT_SYMBOL_GPL(ring_buffer_peek);

static struct ring_buffer_event *
rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
{
	struct ring_buffer *buffer;
	struct ring_buffer_per_cpu *cpu_buffer;
	struct ring_buffer_event *event;
	int nr_loops = 0;

	cpu_buffer = iter->cpu_buffer;
	buffer = cpu_buffer->buffer;

	/*
	 * Check if someone performed a consuming read to
	 * the buffer. A consuming read invalidates the iterator
	 * and we need to reset the iterator in this case.
	 */
	if (unlikely(iter->cache_read != cpu_buffer->read ||
		     iter->cache_reader_page != cpu_buffer->reader_page))
		rb_iter_reset(iter);

 again:
	if (ring_buffer_iter_empty(iter))
		return NULL;

	/*
	 * We repeat when a time extend is encountered or we hit
	 * the end of the page. Since the time extend is always attached
	 * to a data event, we should never loop more than three times.
	 * Once for going to next page, once on time extend, and
	 * finally once to get the event.
	 * (We never hit the following condition more than thrice).
	 */
	if (RB_WARN_ON(cpu_buffer, ++nr_loops > 3))
		return NULL;

	if (rb_per_cpu_empty(cpu_buffer))
		return NULL;

	if (iter->head >= rb_page_size(iter->head_page)) {
		rb_inc_iter(iter);
		goto again;
	}

	event = rb_iter_head_event(iter);

	switch (event->type_len) {
	case RINGBUF_TYPE_PADDING:
		if (rb_null_event(event)) {
			rb_inc_iter(iter);
			goto again;
		}
		rb_advance_iter(iter);
		return event;

	case RINGBUF_TYPE_TIME_EXTEND:
		/* Internal data, OK to advance */
		rb_advance_iter(iter);
		goto again;

	case RINGBUF_TYPE_TIME_STAMP:
		/* FIXME: not implemented */
		rb_advance_iter(iter);
		goto again;

	case RINGBUF_TYPE_DATA:
		if (ts) {
			*ts = iter->read_stamp + event->time_delta;
			ring_buffer_normalize_time_stamp(buffer,
							 cpu_buffer->cpu, ts);
		}
		return event;

	default:
		BUG();
	}

	return NULL;
}
EXPORT_SYMBOL_GPL(ring_buffer_iter_peek);

static inline bool rb_reader_lock(struct ring_buffer_per_cpu *cpu_buffer)
{
	if (likely(!in_nmi())) {
		raw_spin_lock(&cpu_buffer->reader_lock);
		return true;
	}

	/*
	 * If an NMI die dumps out the content of the ring buffer
	 * trylock must be used to prevent a deadlock if the NMI
	 * preempted a task that holds the ring buffer locks. If
	 * we get the lock then all is fine, if not, then continue
	 * to do the read, but this can corrupt the ring buffer,
	 * so it must be permanently disabled from future writes.
	 * Reading from NMI is a oneshot deal.
	 */
	if (raw_spin_trylock(&cpu_buffer->reader_lock))
		return true;

	/* Continue without locking, but disable the ring buffer */
	atomic_inc(&cpu_buffer->record_disabled);
	return false;
}

static inline void
rb_reader_unlock(struct ring_buffer_per_cpu *cpu_buffer, bool locked)
{
	if (likely(locked))
		raw_spin_unlock(&cpu_buffer->reader_lock);
	return;
}

/**
 * ring_buffer_peek - peek at the next event to be read
 * @buffer: The ring buffer to read
 * @cpu: The cpu to peak at
 * @ts: The timestamp counter of this event.
 * @lost_events: a variable to store if events were lost (may be NULL)
 *
 * This will return the event that will be read next, but does
 * not consume the data.
 */
struct ring_buffer_event *
ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts,
		 unsigned long *lost_events)
{
	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
	struct ring_buffer_event *event;
	unsigned long flags;
	bool dolock;

	if (!cpumask_test_cpu(cpu, buffer->cpumask))
		return NULL;

 again:
	local_irq_save(flags);
	dolock = rb_reader_lock(cpu_buffer);
	event = rb_buffer_peek(cpu_buffer, ts, lost_events);
	if (event && event->type_len == RINGBUF_TYPE_PADDING)
		rb_advance_reader(cpu_buffer);
	rb_reader_unlock(cpu_buffer, dolock);
	local_irq_restore(flags);

	if (event && event->type_len == RINGBUF_TYPE_PADDING)
		goto again;

	return event;
}

/**
 * ring_buffer_iter_peek - peek at the next event to be read
 * @iter: The ring buffer iterator
 * @ts: The timestamp counter of this event.
 *
 * This will return the event that will be read next, but does
 * not increment the iterator.
 */
struct ring_buffer_event *
ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
{
	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
	struct ring_buffer_event *event;
	unsigned long flags;

 again:
	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
	event = rb_iter_peek(iter, ts);
	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);

	if (event && event->type_len == RINGBUF_TYPE_PADDING)
		goto again;

	return event;
}

/**
 * ring_buffer_consume - return an event and consume it
 * @buffer: The ring buffer to get the next event from
 * @cpu: the cpu to read the buffer from
 * @ts: a variable to store the timestamp (may be NULL)
 * @lost_events: a variable to store if events were lost (may be NULL)
 *
 * Returns the next event in the ring buffer, and that event is consumed.
 * Meaning, that sequential reads will keep returning a different event,
 * and eventually empty the ring buffer if the producer is slower.
 */
struct ring_buffer_event *
ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts,
		    unsigned long *lost_events)
{
	struct ring_buffer_per_cpu *cpu_buffer;
	struct ring_buffer_event *event = NULL;
	unsigned long flags;
	bool dolock;

 again:
	/* might be called in atomic */
	preempt_disable();

	if (!cpumask_test_cpu(cpu, buffer->cpumask))
		goto out;

	cpu_buffer = buffer->buffers[cpu];
	local_irq_save(flags);
	dolock = rb_reader_lock(cpu_buffer);

	event = rb_buffer_peek(cpu_buffer, ts, lost_events);
	if (event) {
		cpu_buffer->lost_events = 0;
		rb_advance_reader(cpu_buffer);
	}

	rb_reader_unlock(cpu_buffer, dolock);
	local_irq_restore(flags);

 out:
	preempt_enable();

	if (event && event->type_len == RINGBUF_TYPE_PADDING)
		goto again;

	return event;
}
EXPORT_SYMBOL_GPL(ring_buffer_consume);

/**
 * ring_buffer_read_prepare - Prepare for a non consuming read of the buffer
 * @buffer: The ring buffer to read from
 * @cpu: The cpu buffer to iterate over
 *
 * This performs the initial preparations necessary to iterate
 * through the buffer.  Memory is allocated, buffer recording
 * is disabled, and the iterator pointer is returned to the caller.
 *
 * Disabling buffer recordng prevents the reading from being
 * corrupted. This is not a consuming read, so a producer is not
 * expected.
 *
 * After a sequence of ring_buffer_read_prepare calls, the user is
 * expected to make at least one call to ring_buffer_read_prepare_sync.
 * Afterwards, ring_buffer_read_start is invoked to get things going
 * for real.
 *
 * This overall must be paired with ring_buffer_read_finish.
 */
struct ring_buffer_iter *
ring_buffer_read_prepare(struct ring_buffer *buffer, int cpu)
{
	struct ring_buffer_per_cpu *cpu_buffer;
	struct ring_buffer_iter *iter;

	if (!cpumask_test_cpu(cpu, buffer->cpumask))
		return NULL;

	iter = kmalloc(sizeof(*iter), GFP_KERNEL);
	if (!iter)
		return NULL;

	cpu_buffer = buffer->buffers[cpu];

	iter->cpu_buffer = cpu_buffer;

	atomic_inc(&buffer->resize_disabled);
	atomic_inc(&cpu_buffer->record_disabled);

	return iter;
}
EXPORT_SYMBOL_GPL(ring_buffer_read_prepare);

/**
 * ring_buffer_read_prepare_sync - Synchronize a set of prepare calls
 *
 * All previously invoked ring_buffer_read_prepare calls to prepare
 * iterators will be synchronized.  Afterwards, read_buffer_read_start
 * calls on those iterators are allowed.
 */
void
ring_buffer_read_prepare_sync(void)
{
	synchronize_sched();
}
EXPORT_SYMBOL_GPL(ring_buffer_read_prepare_sync);

/**
 * ring_buffer_read_start - start a non consuming read of the buffer
 * @iter: The iterator returned by ring_buffer_read_prepare
 *
 * This finalizes the startup of an iteration through the buffer.
 * The iterator comes from a call to ring_buffer_read_prepare and
 * an intervening ring_buffer_read_prepare_sync must have been
 * performed.
 *
 * Must be paired with ring_buffer_read_finish.
 */
void
ring_buffer_read_start(struct ring_buffer_iter *iter)
{
	struct ring_buffer_per_cpu *cpu_buffer;
	unsigned long flags;

	if (!iter)
		return;

	cpu_buffer = iter->cpu_buffer;

	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
	arch_spin_lock(&cpu_buffer->lock);
	rb_iter_reset(iter);
	arch_spin_unlock(&cpu_buffer->lock);
	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
}
EXPORT_SYMBOL_GPL(ring_buffer_read_start);

/**
 * ring_buffer_read_finish - finish reading the iterator of the buffer
 * @iter: The iterator retrieved by ring_buffer_start
 *
 * This re-enables the recording to the buffer, and frees the
 * iterator.
 */
void
ring_buffer_read_finish(struct ring_buffer_iter *iter)
{
	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
	unsigned long flags;

	/*
	 * Ring buffer is disabled from recording, here's a good place
	 * to check the integrity of the ring buffer.
	 * Must prevent readers from trying to read, as the check
	 * clears the HEAD page and readers require it.
	 */
	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
	rb_check_pages(cpu_buffer);
	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);

	atomic_dec(&cpu_buffer->record_disabled);
	atomic_dec(&cpu_buffer->buffer->resize_disabled);
	kfree(iter);
}
EXPORT_SYMBOL_GPL(ring_buffer_read_finish);

/**
 * ring_buffer_read - read the next item in the ring buffer by the iterator
 * @iter: The ring buffer iterator
 * @ts: The time stamp of the event read.
 *
 * This reads the next event in the ring buffer and increments the iterator.
 */
struct ring_buffer_event *
ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts)
{
	struct ring_buffer_event *event;
	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
	unsigned long flags;

	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 again:
	event = rb_iter_peek(iter, ts);
	if (!event)
		goto out;

	if (event->type_len == RINGBUF_TYPE_PADDING)
		goto again;

	rb_advance_iter(iter);
 out:
	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);

	return event;
}
EXPORT_SYMBOL_GPL(ring_buffer_read);

/**
 * ring_buffer_size - return the size of the ring buffer (in bytes)
 * @buffer: The ring buffer.
 */
unsigned long ring_buffer_size(struct ring_buffer *buffer, int cpu)
{
	/*
	 * Earlier, this method returned
	 *	BUF_PAGE_SIZE * buffer->nr_pages
	 * Since the nr_pages field is now removed, we have converted this to
	 * return the per cpu buffer value.
	 */
	if (!cpumask_test_cpu(cpu, buffer->cpumask))
		return 0;

	return BUF_PAGE_SIZE * buffer->buffers[cpu]->nr_pages;
}
EXPORT_SYMBOL_GPL(ring_buffer_size);

static void
rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
{
	rb_head_page_deactivate(cpu_buffer);

	cpu_buffer->head_page
		= list_entry(cpu_buffer->pages, struct buffer_page, list);
	local_set(&cpu_buffer->head_page->write, 0);
	local_set(&cpu_buffer->head_page->entries, 0);
	local_set(&cpu_buffer->head_page->page->commit, 0);

	cpu_buffer->head_page->read = 0;

	cpu_buffer->tail_page = cpu_buffer->head_page;
	cpu_buffer->commit_page = cpu_buffer->head_page;

	INIT_LIST_HEAD(&cpu_buffer->reader_page->list);
	INIT_LIST_HEAD(&cpu_buffer->new_pages);
	local_set(&cpu_buffer->reader_page->write, 0);
	local_set(&cpu_buffer->reader_page->entries, 0);
	local_set(&cpu_buffer->reader_page->page->commit, 0);
	cpu_buffer->reader_page->read = 0;

	local_set(&cpu_buffer->entries_bytes, 0);
	local_set(&cpu_buffer->overrun, 0);
	local_set(&cpu_buffer->commit_overrun, 0);
	local_set(&cpu_buffer->dropped_events, 0);
	local_set(&cpu_buffer->entries, 0);
	local_set(&cpu_buffer->committing, 0);
	local_set(&cpu_buffer->commits, 0);
	cpu_buffer->read = 0;
	cpu_buffer->read_bytes = 0;

	cpu_buffer->write_stamp = 0;
	cpu_buffer->read_stamp = 0;

	cpu_buffer->lost_events = 0;
	cpu_buffer->last_overrun = 0;

	rb_head_page_activate(cpu_buffer);
}

/**
 * ring_buffer_reset_cpu - reset a ring buffer per CPU buffer
 * @buffer: The ring buffer to reset a per cpu buffer of
 * @cpu: The CPU buffer to be reset
 */
void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
{
	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
	unsigned long flags;

	if (!cpumask_test_cpu(cpu, buffer->cpumask))
		return;

	atomic_inc(&buffer->resize_disabled);
	atomic_inc(&cpu_buffer->record_disabled);

	/* Make sure all commits have finished */
	synchronize_sched();

	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);

	if (RB_WARN_ON(cpu_buffer, local_read(&cpu_buffer->committing)))
		goto out;

	arch_spin_lock(&cpu_buffer->lock);

	rb_reset_cpu(cpu_buffer);

	arch_spin_unlock(&cpu_buffer->lock);

 out:
	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);

	atomic_dec(&cpu_buffer->record_disabled);
	atomic_dec(&buffer->resize_disabled);
}
EXPORT_SYMBOL_GPL(ring_buffer_reset_cpu);

/**
 * ring_buffer_reset - reset a ring buffer
 * @buffer: The ring buffer to reset all cpu buffers
 */
void ring_buffer_reset(struct ring_buffer *buffer)
{
	int cpu;

	for_each_buffer_cpu(buffer, cpu)
		ring_buffer_reset_cpu(buffer, cpu);
}
EXPORT_SYMBOL_GPL(ring_buffer_reset);

/**
 * rind_buffer_empty - is the ring buffer empty?
 * @buffer: The ring buffer to test
 */
bool ring_buffer_empty(struct ring_buffer *buffer)
{
	struct ring_buffer_per_cpu *cpu_buffer;
	unsigned long flags;
	bool dolock;
	int cpu;
	int ret;

	/* yes this is racy, but if you don't like the race, lock the buffer */
	for_each_buffer_cpu(buffer, cpu) {
		cpu_buffer = buffer->buffers[cpu];
		local_irq_save(flags);
		dolock = rb_reader_lock(cpu_buffer);
		ret = rb_per_cpu_empty(cpu_buffer);
		rb_reader_unlock(cpu_buffer, dolock);
		local_irq_restore(flags);

		if (!ret)
			return false;
	}

	return true;
}
EXPORT_SYMBOL_GPL(ring_buffer_empty);

/**
 * ring_buffer_empty_cpu - is a cpu buffer of a ring buffer empty?
 * @buffer: The ring buffer
 * @cpu: The CPU buffer to test
 */
bool ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu)
{
	struct ring_buffer_per_cpu *cpu_buffer;
	unsigned long flags;
	bool dolock;
	int ret;

	if (!cpumask_test_cpu(cpu, buffer->cpumask))
		return true;

	cpu_buffer = buffer->buffers[cpu];
	local_irq_save(flags);
	dolock = rb_reader_lock(cpu_buffer);
	ret = rb_per_cpu_empty(cpu_buffer);
	rb_reader_unlock(cpu_buffer, dolock);
	local_irq_restore(flags);

	return ret;
}
EXPORT_SYMBOL_GPL(ring_buffer_empty_cpu);

#ifdef CONFIG_RING_BUFFER_ALLOW_SWAP
/**
 * ring_buffer_swap_cpu - swap a CPU buffer between two ring buffers
 * @buffer_a: One buffer to swap with
 * @buffer_b: The other buffer to swap with
 *
 * This function is useful for tracers that want to take a "snapshot"
 * of a CPU buffer and has another back up buffer lying around.
 * it is expected that the tracer handles the cpu buffer not being
 * used at the moment.
 */
int ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
			 struct ring_buffer *buffer_b, int cpu)
{
	struct ring_buffer_per_cpu *cpu_buffer_a;
	struct ring_buffer_per_cpu *cpu_buffer_b;
	int ret = -EINVAL;

	if (!cpumask_test_cpu(cpu, buffer_a->cpumask) ||
	    !cpumask_test_cpu(cpu, buffer_b->cpumask))
		goto out;

	cpu_buffer_a = buffer_a->buffers[cpu];
	cpu_buffer_b = buffer_b->buffers[cpu];

	/* At least make sure the two buffers are somewhat the same */
	if (cpu_buffer_a->nr_pages != cpu_buffer_b->nr_pages)
		goto out;

	ret = -EAGAIN;

	if (atomic_read(&buffer_a->record_disabled))
		goto out;

	if (atomic_read(&buffer_b->record_disabled))
		goto out;

	if (atomic_read(&cpu_buffer_a->record_disabled))
		goto out;

	if (atomic_read(&cpu_buffer_b->record_disabled))
		goto out;

	/*
	 * We can't do a synchronize_sched here because this
	 * function can be called in atomic context.
	 * Normally this will be called from the same CPU as cpu.
	 * If not it's up to the caller to protect this.
	 */
	atomic_inc(&cpu_buffer_a->record_disabled);
	atomic_inc(&cpu_buffer_b->record_disabled);

	ret = -EBUSY;
	if (local_read(&cpu_buffer_a->committing))
		goto out_dec;
	if (local_read(&cpu_buffer_b->committing))
		goto out_dec;

	buffer_a->buffers[cpu] = cpu_buffer_b;
	buffer_b->buffers[cpu] = cpu_buffer_a;

	cpu_buffer_b->buffer = buffer_a;
	cpu_buffer_a->buffer = buffer_b;

	ret = 0;

out_dec:
	atomic_dec(&cpu_buffer_a->record_disabled);
	atomic_dec(&cpu_buffer_b->record_disabled);
out:
	return ret;
}
EXPORT_SYMBOL_GPL(ring_buffer_swap_cpu);
#endif /* CONFIG_RING_BUFFER_ALLOW_SWAP */

/**
 * ring_buffer_alloc_read_page - allocate a page to read from buffer
 * @buffer: the buffer to allocate for.
 * @cpu: the cpu buffer to allocate.
 *
 * This function is used in conjunction with ring_buffer_read_page.
 * When reading a full page from the ring buffer, these functions
 * can be used to speed up the process. The calling function should
 * allocate a few pages first with this function. Then when it
 * needs to get pages from the ring buffer, it passes the result
 * of this function into ring_buffer_read_page, which will swap
 * the page that was allocated, with the read page of the buffer.
 *
 * Returns:
 *  The page allocated, or ERR_PTR
 */
void *ring_buffer_alloc_read_page(struct ring_buffer *buffer, int cpu)
{
	struct ring_buffer_per_cpu *cpu_buffer;
	struct buffer_data_page *bpage = NULL;
	unsigned long flags;
	struct page *page;

	if (!cpumask_test_cpu(cpu, buffer->cpumask))
		return ERR_PTR(-ENODEV);

	cpu_buffer = buffer->buffers[cpu];
	local_irq_save(flags);
	arch_spin_lock(&cpu_buffer->lock);

	if (cpu_buffer->free_page) {
		bpage = cpu_buffer->free_page;
		cpu_buffer->free_page = NULL;
	}

	arch_spin_unlock(&cpu_buffer->lock);
	local_irq_restore(flags);

	if (bpage)
		goto out;

	page = alloc_pages_node(cpu_to_node(cpu),
				GFP_KERNEL | __GFP_NORETRY, 0);
	if (!page)
		return ERR_PTR(-ENOMEM);

	bpage = page_address(page);

 out:
	rb_init_page(bpage);

	return bpage;
}
EXPORT_SYMBOL_GPL(ring_buffer_alloc_read_page);

/**
 * ring_buffer_free_read_page - free an allocated read page
 * @buffer: the buffer the page was allocate for
 * @cpu: the cpu buffer the page came from
 * @data: the page to free
 *
 * Free a page allocated from ring_buffer_alloc_read_page.
 */
void ring_buffer_free_read_page(struct ring_buffer *buffer, int cpu, void *data)
{
	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
	struct buffer_data_page *bpage = data;
	struct page *page = virt_to_page(bpage);
	unsigned long flags;

	/* If the page is still in use someplace else, we can't reuse it */
	if (page_ref_count(page) > 1)
		goto out;

	local_irq_save(flags);
	arch_spin_lock(&cpu_buffer->lock);

	if (!cpu_buffer->free_page) {
		cpu_buffer->free_page = bpage;
		bpage = NULL;
	}

	arch_spin_unlock(&cpu_buffer->lock);
	local_irq_restore(flags);

 out:
	free_page((unsigned long)bpage);
}
EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);

/**
 * ring_buffer_read_page - extract a page from the ring buffer
 * @buffer: buffer to extract from
 * @data_page: the page to use allocated from ring_buffer_alloc_read_page
 * @len: amount to extract
 * @cpu: the cpu of the buffer to extract
 * @full: should the extraction only happen when the page is full.
 *
 * This function will pull out a page from the ring buffer and consume it.
 * @data_page must be the address of the variable that was returned
 * from ring_buffer_alloc_read_page. This is because the page might be used
 * to swap with a page in the ring buffer.
 *
 * for example:
 *	rpage = ring_buffer_alloc_read_page(buffer, cpu);
 *	if (IS_ERR(rpage))
 *		return PTR_ERR(rpage);
 *	ret = ring_buffer_read_page(buffer, &rpage, len, cpu, 0);
 *	if (ret >= 0)
 *		process_page(rpage, ret);
 *
 * When @full is set, the function will not return true unless
 * the writer is off the reader page.
 *
 * Note: it is up to the calling functions to handle sleeps and wakeups.
 *  The ring buffer can be used anywhere in the kernel and can not
 *  blindly call wake_up. The layer that uses the ring buffer must be
 *  responsible for that.
 *
 * Returns:
 *  >=0 if data has been transferred, returns the offset of consumed data.
 *  <0 if no data has been transferred.
 */
int ring_buffer_read_page(struct ring_buffer *buffer,
			  void **data_page, size_t len, int cpu, int full)
{
	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
	struct ring_buffer_event *event;
	struct buffer_data_page *bpage;
	struct buffer_page *reader;
	unsigned long missed_events;
	unsigned long flags;
	unsigned int commit;
	unsigned int read;
	u64 save_timestamp;
	int ret = -1;

	if (!cpumask_test_cpu(cpu, buffer->cpumask))
		goto out;

	/*
	 * If len is not big enough to hold the page header, then
	 * we can not copy anything.
	 */
	if (len <= BUF_PAGE_HDR_SIZE)
		goto out;

	len -= BUF_PAGE_HDR_SIZE;

	if (!data_page)
		goto out;

	bpage = *data_page;
	if (!bpage)
		goto out;

	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);

	reader = rb_get_reader_page(cpu_buffer);
	if (!reader)
		goto out_unlock;

	event = rb_reader_event(cpu_buffer);

	read = reader->read;
	commit = rb_page_commit(reader);

	/* Check if any events were dropped */
	missed_events = cpu_buffer->lost_events;

	/*
	 * If this page has been partially read or
	 * if len is not big enough to read the rest of the page or
	 * a writer is still on the page, then
	 * we must copy the data from the page to the buffer.
	 * Otherwise, we can simply swap the page with the one passed in.
	 */
	if (read || (len < (commit - read)) ||
	    cpu_buffer->reader_page == cpu_buffer->commit_page) {
		struct buffer_data_page *rpage = cpu_buffer->reader_page->page;
		unsigned int rpos = read;
		unsigned int pos = 0;
		unsigned int size;

		if (full)
			goto out_unlock;

		if (len > (commit - read))
			len = (commit - read);

		/* Always keep the time extend and data together */
		size = rb_event_ts_length(event);

		if (len < size)
			goto out_unlock;

		/* save the current timestamp, since the user will need it */
		save_timestamp = cpu_buffer->read_stamp;

		/* Need to copy one event at a time */
		do {
			/* We need the size of one event, because
			 * rb_advance_reader only advances by one event,
			 * whereas rb_event_ts_length may include the size of
			 * one or two events.
			 * We have already ensured there's enough space if this
			 * is a time extend. */
			size = rb_event_length(event);
			memcpy(bpage->data + pos, rpage->data + rpos, size);

			len -= size;

			rb_advance_reader(cpu_buffer);
			rpos = reader->read;
			pos += size;

			if (rpos >= commit)
				break;

			event = rb_reader_event(cpu_buffer);
			/* Always keep the time extend and data together */
			size = rb_event_ts_length(event);
		} while (len >= size);

		/* update bpage */
		local_set(&bpage->commit, pos);
		bpage->time_stamp = save_timestamp;

		/* we copied everything to the beginning */
		read = 0;
	} else {
		/* update the entry counter */
		cpu_buffer->read += rb_page_entries(reader);
		cpu_buffer->read_bytes += BUF_PAGE_SIZE;

		/* swap the pages */
		rb_init_page(bpage);
		bpage = reader->page;
		reader->page = *data_page;
		local_set(&reader->write, 0);
		local_set(&reader->entries, 0);
		reader->read = 0;
		*data_page = bpage;

		/*
		 * Use the real_end for the data size,
		 * This gives us a chance to store the lost events
		 * on the page.
		 */
		if (reader->real_end)
			local_set(&bpage->commit, reader->real_end);
	}
	ret = read;

	cpu_buffer->lost_events = 0;

	commit = local_read(&bpage->commit);
	/*
	 * Set a flag in the commit field if we lost events
	 */
	if (missed_events) {
		/* If there is room at the end of the page to save the
		 * missed events, then record it there.
		 */
		if (BUF_PAGE_SIZE - commit >= sizeof(missed_events)) {
			memcpy(&bpage->data[commit], &missed_events,
			       sizeof(missed_events));
			local_add(RB_MISSED_STORED, &bpage->commit);
			commit += sizeof(missed_events);
		}
		local_add(RB_MISSED_EVENTS, &bpage->commit);
	}

	/*
	 * This page may be off to user land. Zero it out here.
	 */
	if (commit < BUF_PAGE_SIZE)
		memset(&bpage->data[commit], 0, BUF_PAGE_SIZE - commit);

 out_unlock:
	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);

 out:
	return ret;
}
EXPORT_SYMBOL_GPL(ring_buffer_read_page);

/*
 * We only allocate new buffers, never free them if the CPU goes down.
 * If we were to free the buffer, then the user would lose any trace that was in
 * the buffer.
 */
int trace_rb_cpu_prepare(unsigned int cpu, struct hlist_node *node)
{
	struct ring_buffer *buffer;
	long nr_pages_same;
	int cpu_i;
	unsigned long nr_pages;

	buffer = container_of(node, struct ring_buffer, node);
	if (cpumask_test_cpu(cpu, buffer->cpumask))
		return 0;

	nr_pages = 0;
	nr_pages_same = 1;
	/* check if all cpu sizes are same */
	for_each_buffer_cpu(buffer, cpu_i) {
		/* fill in the size from first enabled cpu */
		if (nr_pages == 0)
			nr_pages = buffer->buffers[cpu_i]->nr_pages;
		if (nr_pages != buffer->buffers[cpu_i]->nr_pages) {
			nr_pages_same = 0;
			break;
		}
	}
	/* allocate minimum pages, user can later expand it */
	if (!nr_pages_same)
		nr_pages = 2;
	buffer->buffers[cpu] =
		rb_allocate_cpu_buffer(buffer, nr_pages, cpu);
	if (!buffer->buffers[cpu]) {
		WARN(1, "failed to allocate ring buffer on CPU %u\n",
		     cpu);
		return -ENOMEM;
	}
	smp_wmb();
	cpumask_set_cpu(cpu, buffer->cpumask);
	return 0;
}

#ifdef CONFIG_RING_BUFFER_STARTUP_TEST
/*
 * This is a basic integrity check of the ring buffer.
 * Late in the boot cycle this test will run when configured in.
 * It will kick off a thread per CPU that will go into a loop
 * writing to the per cpu ring buffer various sizes of data.
 * Some of the data will be large items, some small.
 *
 * Another thread is created that goes into a spin, sending out
 * IPIs to the other CPUs to also write into the ring buffer.
 * this is to test the nesting ability of the buffer.
 *
 * Basic stats are recorded and reported. If something in the
 * ring buffer should happen that's not expected, a big warning
 * is displayed and all ring buffers are disabled.
 */
static struct task_struct *rb_threads[NR_CPUS] __initdata;

struct rb_test_data {
	struct ring_buffer	*buffer;
	unsigned long		events;
	unsigned long		bytes_written;
	unsigned long		bytes_alloc;
	unsigned long		bytes_dropped;
	unsigned long		events_nested;
	unsigned long		bytes_written_nested;
	unsigned long		bytes_alloc_nested;
	unsigned long		bytes_dropped_nested;
	int			min_size_nested;
	int			max_size_nested;
	int			max_size;
	int			min_size;
	int			cpu;
	int			cnt;
};

static struct rb_test_data rb_data[NR_CPUS] __initdata;

/* 1 meg per cpu */
#define RB_TEST_BUFFER_SIZE	1048576

static char rb_string[] __initdata =
	"abcdefghijklmnopqrstuvwxyz1234567890!@#$%^&*()?+\\"
	"?+|:';\",.<>/?abcdefghijklmnopqrstuvwxyz1234567890"
	"!@#$%^&*()?+\\?+|:';\",.<>/?abcdefghijklmnopqrstuv";

static bool rb_test_started __initdata;

struct rb_item {
	int size;
	char str[];
};

static __init int rb_write_something(struct rb_test_data *data, bool nested)
{
	struct ring_buffer_event *event;
	struct rb_item *item;
	bool started;
	int event_len;
	int size;
	int len;
	int cnt;

	/* Have nested writes different that what is written */
	cnt = data->cnt + (nested ? 27 : 0);

	/* Multiply cnt by ~e, to make some unique increment */
	size = (data->cnt * 68 / 25) % (sizeof(rb_string) - 1);

	len = size + sizeof(struct rb_item);

	started = rb_test_started;
	/* read rb_test_started before checking buffer enabled */
	smp_rmb();

	event = ring_buffer_lock_reserve(data->buffer, len);
	if (!event) {
		/* Ignore dropped events before test starts. */
		if (started) {
			if (nested)
				data->bytes_dropped += len;
			else
				data->bytes_dropped_nested += len;
		}
		return len;
	}

	event_len = ring_buffer_event_length(event);

	if (RB_WARN_ON(data->buffer, event_len < len))
		goto out;

	item = ring_buffer_event_data(event);
	item->size = size;
	memcpy(item->str, rb_string, size);

	if (nested) {
		data->bytes_alloc_nested += event_len;
		data->bytes_written_nested += len;
		data->events_nested++;
		if (!data->min_size_nested || len < data->min_size_nested)
			data->min_size_nested = len;
		if (len > data->max_size_nested)
			data->max_size_nested = len;
	} else {
		data->bytes_alloc += event_len;
		data->bytes_written += len;
		data->events++;
		if (!data->min_size || len < data->min_size)
			data->max_size = len;
		if (len > data->max_size)
			data->max_size = len;
	}

 out:
	ring_buffer_unlock_commit(data->buffer, event);

	return 0;
}

static __init int rb_test(void *arg)
{
	struct rb_test_data *data = arg;

	while (!kthread_should_stop()) {
		rb_write_something(data, false);
		data->cnt++;

		set_current_state(TASK_INTERRUPTIBLE);
		/* Now sleep between a min of 100-300us and a max of 1ms */
		usleep_range(((data->cnt % 3) + 1) * 100, 1000);
	}

	return 0;
}

static __init void rb_ipi(void *ignore)
{
	struct rb_test_data *data;
	int cpu = smp_processor_id();

	data = &rb_data[cpu];
	rb_write_something(data, true);
}

static __init int rb_hammer_test(void *arg)
{
	while (!kthread_should_stop()) {

		/* Send an IPI to all cpus to write data! */
		smp_call_function(rb_ipi, NULL, 1);
		/* No sleep, but for non preempt, let others run */
		schedule();
	}

	return 0;
}

static __init int test_ringbuffer(void)
{
	struct task_struct *rb_hammer;
	struct ring_buffer *buffer;
	int cpu;
	int ret = 0;

	pr_info("Running ring buffer tests...\n");

	buffer = ring_buffer_alloc(RB_TEST_BUFFER_SIZE, RB_FL_OVERWRITE);
	if (WARN_ON(!buffer))
		return 0;

	/* Disable buffer so that threads can't write to it yet */
	ring_buffer_record_off(buffer);

	for_each_online_cpu(cpu) {
		rb_data[cpu].buffer = buffer;
		rb_data[cpu].cpu = cpu;
		rb_data[cpu].cnt = cpu;
		rb_threads[cpu] = kthread_create(rb_test, &rb_data[cpu],
						 "rbtester/%d", cpu);
		if (WARN_ON(IS_ERR(rb_threads[cpu]))) {
			pr_cont("FAILED\n");
			ret = PTR_ERR(rb_threads[cpu]);
			goto out_free;
		}

		kthread_bind(rb_threads[cpu], cpu);
 		wake_up_process(rb_threads[cpu]);
	}

	/* Now create the rb hammer! */
	rb_hammer = kthread_run(rb_hammer_test, NULL, "rbhammer");
	if (WARN_ON(IS_ERR(rb_hammer))) {
		pr_cont("FAILED\n");
		ret = PTR_ERR(rb_hammer);
		goto out_free;
	}

	ring_buffer_record_on(buffer);
	/*
	 * Show buffer is enabled before setting rb_test_started.
	 * Yes there's a small race window where events could be
	 * dropped and the thread wont catch it. But when a ring
	 * buffer gets enabled, there will always be some kind of
	 * delay before other CPUs see it. Thus, we don't care about
	 * those dropped events. We care about events dropped after
	 * the threads see that the buffer is active.
	 */
	smp_wmb();
	rb_test_started = true;

	set_current_state(TASK_INTERRUPTIBLE);
	/* Just run for 10 seconds */;
	schedule_timeout(10 * HZ);

	kthread_stop(rb_hammer);

 out_free:
	for_each_online_cpu(cpu) {
		if (!rb_threads[cpu])
			break;
		kthread_stop(rb_threads[cpu]);
	}
	if (ret) {
		ring_buffer_free(buffer);
		return ret;
	}

	/* Report! */
	pr_info("finished\n");
	for_each_online_cpu(cpu) {
		struct ring_buffer_event *event;
		struct rb_test_data *data = &rb_data[cpu];
		struct rb_item *item;
		unsigned long total_events;
		unsigned long total_dropped;
		unsigned long total_written;
		unsigned long total_alloc;
		unsigned long total_read = 0;
		unsigned long total_size = 0;
		unsigned long total_len = 0;
		unsigned long total_lost = 0;
		unsigned long lost;
		int big_event_size;
		int small_event_size;

		ret = -1;

		total_events = data->events + data->events_nested;
		total_written = data->bytes_written + data->bytes_written_nested;
		total_alloc = data->bytes_alloc + data->bytes_alloc_nested;
		total_dropped = data->bytes_dropped + data->bytes_dropped_nested;

		big_event_size = data->max_size + data->max_size_nested;
		small_event_size = data->min_size + data->min_size_nested;

		pr_info("CPU %d:\n", cpu);
		pr_info("              events:    %ld\n", total_events);
		pr_info("       dropped bytes:    %ld\n", total_dropped);
		pr_info("       alloced bytes:    %ld\n", total_alloc);
		pr_info("       written bytes:    %ld\n", total_written);
		pr_info("       biggest event:    %d\n", big_event_size);
		pr_info("      smallest event:    %d\n", small_event_size);

		if (RB_WARN_ON(buffer, total_dropped))
			break;

		ret = 0;

		while ((event = ring_buffer_consume(buffer, cpu, NULL, &lost))) {
			total_lost += lost;
			item = ring_buffer_event_data(event);
			total_len += ring_buffer_event_length(event);
			total_size += item->size + sizeof(struct rb_item);
			if (memcmp(&item->str[0], rb_string, item->size) != 0) {
				pr_info("FAILED!\n");
				pr_info("buffer had: %.*s\n", item->size, item->str);
				pr_info("expected:   %.*s\n", item->size, rb_string);
				RB_WARN_ON(buffer, 1);
				ret = -1;
				break;
			}
			total_read++;
		}
		if (ret)
			break;

		ret = -1;

		pr_info("         read events:   %ld\n", total_read);
		pr_info("         lost events:   %ld\n", total_lost);
		pr_info("        total events:   %ld\n", total_lost + total_read);
		pr_info("  recorded len bytes:   %ld\n", total_len);
		pr_info(" recorded size bytes:   %ld\n", total_size);
		if (total_lost)
			pr_info(" With dropped events, record len and size may not match\n"
				" alloced and written from above\n");
		if (!total_lost) {
			if (RB_WARN_ON(buffer, total_len != total_alloc ||
				       total_size != total_written))
				break;
		}
		if (RB_WARN_ON(buffer, total_lost + total_read != total_events))
			break;

		ret = 0;
	}
	if (!ret)
		pr_info("Ring buffer PASSED!\n");

	ring_buffer_free(buffer);
	return 0;
}

late_initcall(test_ringbuffer);
#endif /* CONFIG_RING_BUFFER_STARTUP_TEST */