summaryrefslogtreecommitdiffstats
path: root/kernel/trace/trace_events.c
blob: 3d4155892a1e78cf6b8b7850e9a64c460fe825b5 (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
/*
 * event tracer
 *
 * Copyright (C) 2008 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
 *
 *  - Added format output of fields of the trace point.
 *    This was based off of work by Tom Zanussi <tzanussi@gmail.com>.
 *
 */

#define pr_fmt(fmt) fmt

#include <linux/workqueue.h>
#include <linux/spinlock.h>
#include <linux/kthread.h>
#include <linux/tracefs.h>
#include <linux/uaccess.h>
#include <linux/vmalloc.h>
#include <linux/module.h>
#include <linux/ctype.h>
#include <linux/sort.h>
#include <linux/slab.h>
#include <linux/delay.h>

#include <trace/events/sched.h>

#include <asm/setup.h>

#include "trace_output.h"

#undef TRACE_SYSTEM
#define TRACE_SYSTEM "TRACE_SYSTEM"

DEFINE_MUTEX(event_mutex);

LIST_HEAD(ftrace_events);
static LIST_HEAD(ftrace_generic_fields);
static LIST_HEAD(ftrace_common_fields);

#define GFP_TRACE (GFP_KERNEL | __GFP_ZERO)

static struct kmem_cache *field_cachep;
static struct kmem_cache *file_cachep;

static inline int system_refcount(struct event_subsystem *system)
{
	return system->ref_count;
}

static int system_refcount_inc(struct event_subsystem *system)
{
	return system->ref_count++;
}

static int system_refcount_dec(struct event_subsystem *system)
{
	return --system->ref_count;
}

/* Double loops, do not use break, only goto's work */
#define do_for_each_event_file(tr, file)			\
	list_for_each_entry(tr, &ftrace_trace_arrays, list) {	\
		list_for_each_entry(file, &tr->events, list)

#define do_for_each_event_file_safe(tr, file)			\
	list_for_each_entry(tr, &ftrace_trace_arrays, list) {	\
		struct trace_event_file *___n;				\
		list_for_each_entry_safe(file, ___n, &tr->events, list)

#define while_for_each_event_file()		\
	}

static struct list_head *
trace_get_fields(struct trace_event_call *event_call)
{
	if (!event_call->class->get_fields)
		return &event_call->class->fields;
	return event_call->class->get_fields(event_call);
}

static struct ftrace_event_field *
__find_event_field(struct list_head *head, char *name)
{
	struct ftrace_event_field *field;

	list_for_each_entry(field, head, link) {
		if (!strcmp(field->name, name))
			return field;
	}

	return NULL;
}

struct ftrace_event_field *
trace_find_event_field(struct trace_event_call *call, char *name)
{
	struct ftrace_event_field *field;
	struct list_head *head;

	head = trace_get_fields(call);
	field = __find_event_field(head, name);
	if (field)
		return field;

	field = __find_event_field(&ftrace_generic_fields, name);
	if (field)
		return field;

	return __find_event_field(&ftrace_common_fields, name);
}

static int __trace_define_field(struct list_head *head, const char *type,
				const char *name, int offset, int size,
				int is_signed, int filter_type)
{
	struct ftrace_event_field *field;

	field = kmem_cache_alloc(field_cachep, GFP_TRACE);
	if (!field)
		return -ENOMEM;

	field->name = name;
	field->type = type;

	if (filter_type == FILTER_OTHER)
		field->filter_type = filter_assign_type(type);
	else
		field->filter_type = filter_type;

	field->offset = offset;
	field->size = size;
	field->is_signed = is_signed;

	list_add(&field->link, head);

	return 0;
}

int trace_define_field(struct trace_event_call *call, const char *type,
		       const char *name, int offset, int size, int is_signed,
		       int filter_type)
{
	struct list_head *head;

	if (WARN_ON(!call->class))
		return 0;

	head = trace_get_fields(call);
	return __trace_define_field(head, type, name, offset, size,
				    is_signed, filter_type);
}
EXPORT_SYMBOL_GPL(trace_define_field);

#define __generic_field(type, item, filter_type)			\
	ret = __trace_define_field(&ftrace_generic_fields, #type,	\
				   #item, 0, 0, is_signed_type(type),	\
				   filter_type);			\
	if (ret)							\
		return ret;

#define __common_field(type, item)					\
	ret = __trace_define_field(&ftrace_common_fields, #type,	\
				   "common_" #item,			\
				   offsetof(typeof(ent), item),		\
				   sizeof(ent.item),			\
				   is_signed_type(type), FILTER_OTHER);	\
	if (ret)							\
		return ret;

static int trace_define_generic_fields(void)
{
	int ret;

	__generic_field(int, CPU, FILTER_CPU);
	__generic_field(int, cpu, FILTER_CPU);
	__generic_field(char *, COMM, FILTER_COMM);
	__generic_field(char *, comm, FILTER_COMM);

	return ret;
}

static int trace_define_common_fields(void)
{
	int ret;
	struct trace_entry ent;

	__common_field(unsigned short, type);
	__common_field(unsigned char, flags);
	__common_field(unsigned char, preempt_count);
	__common_field(int, pid);

	return ret;
}

static void trace_destroy_fields(struct trace_event_call *call)
{
	struct ftrace_event_field *field, *next;
	struct list_head *head;

	head = trace_get_fields(call);
	list_for_each_entry_safe(field, next, head, link) {
		list_del(&field->link);
		kmem_cache_free(field_cachep, field);
	}
}

/*
 * run-time version of trace_event_get_offsets_<call>() that returns the last
 * accessible offset of trace fields excluding __dynamic_array bytes
 */
int trace_event_get_offsets(struct trace_event_call *call)
{
	struct ftrace_event_field *tail;
	struct list_head *head;

	head = trace_get_fields(call);
	/*
	 * head->next points to the last field with the largest offset,
	 * since it was added last by trace_define_field()
	 */
	tail = list_first_entry(head, struct ftrace_event_field, link);
	return tail->offset + tail->size;
}

int trace_event_raw_init(struct trace_event_call *call)
{
	int id;

	id = register_trace_event(&call->event);
	if (!id)
		return -ENODEV;

	return 0;
}
EXPORT_SYMBOL_GPL(trace_event_raw_init);

bool trace_event_ignore_this_pid(struct trace_event_file *trace_file)
{
	struct trace_array *tr = trace_file->tr;
	struct trace_array_cpu *data;
	struct trace_pid_list *pid_list;

	pid_list = rcu_dereference_sched(tr->filtered_pids);
	if (!pid_list)
		return false;

	data = this_cpu_ptr(tr->trace_buffer.data);

	return data->ignore_pid;
}
EXPORT_SYMBOL_GPL(trace_event_ignore_this_pid);

void *trace_event_buffer_reserve(struct trace_event_buffer *fbuffer,
				 struct trace_event_file *trace_file,
				 unsigned long len)
{
	struct trace_event_call *event_call = trace_file->event_call;

	if ((trace_file->flags & EVENT_FILE_FL_PID_FILTER) &&
	    trace_event_ignore_this_pid(trace_file))
		return NULL;

	local_save_flags(fbuffer->flags);
	fbuffer->pc = preempt_count();
	fbuffer->trace_file = trace_file;

	fbuffer->event =
		trace_event_buffer_lock_reserve(&fbuffer->buffer, trace_file,
						event_call->event.type, len,
						fbuffer->flags, fbuffer->pc);
	if (!fbuffer->event)
		return NULL;

	fbuffer->entry = ring_buffer_event_data(fbuffer->event);
	return fbuffer->entry;
}
EXPORT_SYMBOL_GPL(trace_event_buffer_reserve);

static DEFINE_SPINLOCK(tracepoint_iter_lock);

static void output_printk(struct trace_event_buffer *fbuffer)
{
	struct trace_event_call *event_call;
	struct trace_event *event;
	unsigned long flags;
	struct trace_iterator *iter = tracepoint_print_iter;

	if (!iter)
		return;

	event_call = fbuffer->trace_file->event_call;
	if (!event_call || !event_call->event.funcs ||
	    !event_call->event.funcs->trace)
		return;

	event = &fbuffer->trace_file->event_call->event;

	spin_lock_irqsave(&tracepoint_iter_lock, flags);
	trace_seq_init(&iter->seq);
	iter->ent = fbuffer->entry;
	event_call->event.funcs->trace(iter, 0, event);
	trace_seq_putc(&iter->seq, 0);
	printk("%s", iter->seq.buffer);

	spin_unlock_irqrestore(&tracepoint_iter_lock, flags);
}

void trace_event_buffer_commit(struct trace_event_buffer *fbuffer)
{
	if (tracepoint_printk)
		output_printk(fbuffer);

	event_trigger_unlock_commit(fbuffer->trace_file, fbuffer->buffer,
				    fbuffer->event, fbuffer->entry,
				    fbuffer->flags, fbuffer->pc);
}
EXPORT_SYMBOL_GPL(trace_event_buffer_commit);

int trace_event_reg(struct trace_event_call *call,
		    enum trace_reg type, void *data)
{
	struct trace_event_file *file = data;

	WARN_ON(!(call->flags & TRACE_EVENT_FL_TRACEPOINT));
	switch (type) {
	case TRACE_REG_REGISTER:
		return tracepoint_probe_register(call->tp,
						 call->class->probe,
						 file);
	case TRACE_REG_UNREGISTER:
		tracepoint_probe_unregister(call->tp,
					    call->class->probe,
					    file);
		return 0;

#ifdef CONFIG_PERF_EVENTS
	case TRACE_REG_PERF_REGISTER:
		return tracepoint_probe_register(call->tp,
						 call->class->perf_probe,
						 call);
	case TRACE_REG_PERF_UNREGISTER:
		tracepoint_probe_unregister(call->tp,
					    call->class->perf_probe,
					    call);
		return 0;
	case TRACE_REG_PERF_OPEN:
	case TRACE_REG_PERF_CLOSE:
	case TRACE_REG_PERF_ADD:
	case TRACE_REG_PERF_DEL:
		return 0;
#endif
	}
	return 0;
}
EXPORT_SYMBOL_GPL(trace_event_reg);

void trace_event_enable_cmd_record(bool enable)
{
	struct trace_event_file *file;
	struct trace_array *tr;

	mutex_lock(&event_mutex);
	do_for_each_event_file(tr, file) {

		if (!(file->flags & EVENT_FILE_FL_ENABLED))
			continue;

		if (enable) {
			tracing_start_cmdline_record();
			set_bit(EVENT_FILE_FL_RECORDED_CMD_BIT, &file->flags);
		} else {
			tracing_stop_cmdline_record();
			clear_bit(EVENT_FILE_FL_RECORDED_CMD_BIT, &file->flags);
		}
	} while_for_each_event_file();
	mutex_unlock(&event_mutex);
}

static int __ftrace_event_enable_disable(struct trace_event_file *file,
					 int enable, int soft_disable)
{
	struct trace_event_call *call = file->event_call;
	struct trace_array *tr = file->tr;
	unsigned long file_flags = file->flags;
	int ret = 0;
	int disable;

	switch (enable) {
	case 0:
		/*
		 * When soft_disable is set and enable is cleared, the sm_ref
		 * reference counter is decremented. If it reaches 0, we want
		 * to clear the SOFT_DISABLED flag but leave the event in the
		 * state that it was. That is, if the event was enabled and
		 * SOFT_DISABLED isn't set, then do nothing. But if SOFT_DISABLED
		 * is set we do not want the event to be enabled before we
		 * clear the bit.
		 *
		 * When soft_disable is not set but the SOFT_MODE flag is,
		 * we do nothing. Do not disable the tracepoint, otherwise
		 * "soft enable"s (clearing the SOFT_DISABLED bit) wont work.
		 */
		if (soft_disable) {
			if (atomic_dec_return(&file->sm_ref) > 0)
				break;
			disable = file->flags & EVENT_FILE_FL_SOFT_DISABLED;
			clear_bit(EVENT_FILE_FL_SOFT_MODE_BIT, &file->flags);
		} else
			disable = !(file->flags & EVENT_FILE_FL_SOFT_MODE);

		if (disable && (file->flags & EVENT_FILE_FL_ENABLED)) {
			clear_bit(EVENT_FILE_FL_ENABLED_BIT, &file->flags);
			if (file->flags & EVENT_FILE_FL_RECORDED_CMD) {
				tracing_stop_cmdline_record();
				clear_bit(EVENT_FILE_FL_RECORDED_CMD_BIT, &file->flags);
			}
			call->class->reg(call, TRACE_REG_UNREGISTER, file);
		}
		/* If in SOFT_MODE, just set the SOFT_DISABLE_BIT, else clear it */
		if (file->flags & EVENT_FILE_FL_SOFT_MODE)
			set_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags);
		else
			clear_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags);
		break;
	case 1:
		/*
		 * When soft_disable is set and enable is set, we want to
		 * register the tracepoint for the event, but leave the event
		 * as is. That means, if the event was already enabled, we do
		 * nothing (but set SOFT_MODE). If the event is disabled, we
		 * set SOFT_DISABLED before enabling the event tracepoint, so
		 * it still seems to be disabled.
		 */
		if (!soft_disable)
			clear_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags);
		else {
			if (atomic_inc_return(&file->sm_ref) > 1)
				break;
			set_bit(EVENT_FILE_FL_SOFT_MODE_BIT, &file->flags);
		}

		if (!(file->flags & EVENT_FILE_FL_ENABLED)) {

			/* Keep the event disabled, when going to SOFT_MODE. */
			if (soft_disable)
				set_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags);

			if (tr->trace_flags & TRACE_ITER_RECORD_CMD) {
				tracing_start_cmdline_record();
				set_bit(EVENT_FILE_FL_RECORDED_CMD_BIT, &file->flags);
			}
			ret = call->class->reg(call, TRACE_REG_REGISTER, file);
			if (ret) {
				tracing_stop_cmdline_record();
				pr_info("event trace: Could not enable event "
					"%s\n", trace_event_name(call));
				break;
			}
			set_bit(EVENT_FILE_FL_ENABLED_BIT, &file->flags);

			/* WAS_ENABLED gets set but never cleared. */
			call->flags |= TRACE_EVENT_FL_WAS_ENABLED;
		}
		break;
	}

	/* Enable or disable use of trace_buffered_event */
	if ((file_flags & EVENT_FILE_FL_SOFT_DISABLED) !=
	    (file->flags & EVENT_FILE_FL_SOFT_DISABLED)) {
		if (file->flags & EVENT_FILE_FL_SOFT_DISABLED)
			trace_buffered_event_enable();
		else
			trace_buffered_event_disable();
	}

	return ret;
}

int trace_event_enable_disable(struct trace_event_file *file,
			       int enable, int soft_disable)
{
	return __ftrace_event_enable_disable(file, enable, soft_disable);
}

static int ftrace_event_enable_disable(struct trace_event_file *file,
				       int enable)
{
	return __ftrace_event_enable_disable(file, enable, 0);
}

static void ftrace_clear_events(struct trace_array *tr)
{
	struct trace_event_file *file;

	mutex_lock(&event_mutex);
	list_for_each_entry(file, &tr->events, list) {
		ftrace_event_enable_disable(file, 0);
	}
	mutex_unlock(&event_mutex);
}

/* Shouldn't this be in a header? */
extern int pid_max;

/* Returns true if found in filter */
static bool
find_filtered_pid(struct trace_pid_list *filtered_pids, pid_t search_pid)
{
	/*
	 * If pid_max changed after filtered_pids was created, we
	 * by default ignore all pids greater than the previous pid_max.
	 */
	if (search_pid >= filtered_pids->pid_max)
		return false;

	return test_bit(search_pid, filtered_pids->pids);
}

static bool
ignore_this_task(struct trace_pid_list *filtered_pids, struct task_struct *task)
{
	/*
	 * Return false, because if filtered_pids does not exist,
	 * all pids are good to trace.
	 */
	if (!filtered_pids)
		return false;

	return !find_filtered_pid(filtered_pids, task->pid);
}

static void filter_add_remove_task(struct trace_pid_list *pid_list,
				   struct task_struct *self,
				   struct task_struct *task)
{
	if (!pid_list)
		return;

	/* For forks, we only add if the forking task is listed */
	if (self) {
		if (!find_filtered_pid(pid_list, self->pid))
			return;
	}

	/* Sorry, but we don't support pid_max changing after setting */
	if (task->pid >= pid_list->pid_max)
		return;

	/* "self" is set for forks, and NULL for exits */
	if (self)
		set_bit(task->pid, pid_list->pids);
	else
		clear_bit(task->pid, pid_list->pids);
}

static void
event_filter_pid_sched_process_exit(void *data, struct task_struct *task)
{
	struct trace_pid_list *pid_list;
	struct trace_array *tr = data;

	pid_list = rcu_dereference_sched(tr->filtered_pids);
	filter_add_remove_task(pid_list, NULL, task);
}

static void
event_filter_pid_sched_process_fork(void *data,
				    struct task_struct *self,
				    struct task_struct *task)
{
	struct trace_pid_list *pid_list;
	struct trace_array *tr = data;

	pid_list = rcu_dereference_sched(tr->filtered_pids);
	filter_add_remove_task(pid_list, self, task);
}

void trace_event_follow_fork(struct trace_array *tr, bool enable)
{
	if (enable) {
		register_trace_prio_sched_process_fork(event_filter_pid_sched_process_fork,
						       tr, INT_MIN);
		register_trace_prio_sched_process_exit(event_filter_pid_sched_process_exit,
						       tr, INT_MAX);
	} else {
		unregister_trace_sched_process_fork(event_filter_pid_sched_process_fork,
						    tr);
		unregister_trace_sched_process_exit(event_filter_pid_sched_process_exit,
						    tr);
	}
}

static void
event_filter_pid_sched_switch_probe_pre(void *data, bool preempt,
		    struct task_struct *prev, struct task_struct *next)
{
	struct trace_array *tr = data;
	struct trace_pid_list *pid_list;

	pid_list = rcu_dereference_sched(tr->filtered_pids);

	this_cpu_write(tr->trace_buffer.data->ignore_pid,
		       ignore_this_task(pid_list, prev) &&
		       ignore_this_task(pid_list, next));
}

static void
event_filter_pid_sched_switch_probe_post(void *data, bool preempt,
		    struct task_struct *prev, struct task_struct *next)
{
	struct trace_array *tr = data;
	struct trace_pid_list *pid_list;

	pid_list = rcu_dereference_sched(tr->filtered_pids);

	this_cpu_write(tr->trace_buffer.data->ignore_pid,
		       ignore_this_task(pid_list, next));
}

static void
event_filter_pid_sched_wakeup_probe_pre(void *data, struct task_struct *task)
{
	struct trace_array *tr = data;
	struct trace_pid_list *pid_list;

	/* Nothing to do if we are already tracing */
	if (!this_cpu_read(tr->trace_buffer.data->ignore_pid))
		return;

	pid_list = rcu_dereference_sched(tr->filtered_pids);

	this_cpu_write(tr->trace_buffer.data->ignore_pid,
		       ignore_this_task(pid_list, task));
}

static void
event_filter_pid_sched_wakeup_probe_post(void *data, struct task_struct *task)
{
	struct trace_array *tr = data;
	struct trace_pid_list *pid_list;

	/* Nothing to do if we are not tracing */
	if (this_cpu_read(tr->trace_buffer.data->ignore_pid))
		return;

	pid_list = rcu_dereference_sched(tr->filtered_pids);

	/* Set tracing if current is enabled */
	this_cpu_write(tr->trace_buffer.data->ignore_pid,
		       ignore_this_task(pid_list, current));
}

static void __ftrace_clear_event_pids(struct trace_array *tr)
{
	struct trace_pid_list *pid_list;
	struct trace_event_file *file;
	int cpu;

	pid_list = rcu_dereference_protected(tr->filtered_pids,
					     lockdep_is_held(&event_mutex));
	if (!pid_list)
		return;

	unregister_trace_sched_switch(event_filter_pid_sched_switch_probe_pre, tr);
	unregister_trace_sched_switch(event_filter_pid_sched_switch_probe_post, tr);

	unregister_trace_sched_wakeup(event_filter_pid_sched_wakeup_probe_pre, tr);
	unregister_trace_sched_wakeup(event_filter_pid_sched_wakeup_probe_post, tr);

	unregister_trace_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_pre, tr);
	unregister_trace_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_post, tr);

	unregister_trace_sched_waking(event_filter_pid_sched_wakeup_probe_pre, tr);
	unregister_trace_sched_waking(event_filter_pid_sched_wakeup_probe_post, tr);

	list_for_each_entry(file, &tr->events, list) {
		clear_bit(EVENT_FILE_FL_PID_FILTER_BIT, &file->flags);
	}

	for_each_possible_cpu(cpu)
		per_cpu_ptr(tr->trace_buffer.data, cpu)->ignore_pid = false;

	rcu_assign_pointer(tr->filtered_pids, NULL);

	/* Wait till all users are no longer using pid filtering */
	synchronize_sched();

	vfree(pid_list->pids);
	kfree(pid_list);
}

static void ftrace_clear_event_pids(struct trace_array *tr)
{
	mutex_lock(&event_mutex);
	__ftrace_clear_event_pids(tr);
	mutex_unlock(&event_mutex);
}

static void __put_system(struct event_subsystem *system)
{
	struct event_filter *filter = system->filter;

	WARN_ON_ONCE(system_refcount(system) == 0);
	if (system_refcount_dec(system))
		return;

	list_del(&system->list);

	if (filter) {
		kfree(filter->filter_string);
		kfree(filter);
	}
	kfree_const(system->name);
	kfree(system);
}

static void __get_system(struct event_subsystem *system)
{
	WARN_ON_ONCE(system_refcount(system) == 0);
	system_refcount_inc(system);
}

static void __get_system_dir(struct trace_subsystem_dir *dir)
{
	WARN_ON_ONCE(dir->ref_count == 0);
	dir->ref_count++;
	__get_system(dir->subsystem);
}

static void __put_system_dir(struct trace_subsystem_dir *dir)
{
	WARN_ON_ONCE(dir->ref_count == 0);
	/* If the subsystem is about to be freed, the dir must be too */
	WARN_ON_ONCE(system_refcount(dir->subsystem) == 1 && dir->ref_count != 1);

	__put_system(dir->subsystem);
	if (!--dir->ref_count)
		kfree(dir);
}

static void put_system(struct trace_subsystem_dir *dir)
{
	mutex_lock(&event_mutex);
	__put_system_dir(dir);
	mutex_unlock(&event_mutex);
}

static void remove_subsystem(struct trace_subsystem_dir *dir)
{
	if (!dir)
		return;

	if (!--dir->nr_events) {
		tracefs_remove_recursive(dir->entry);
		list_del(&dir->list);
		__put_system_dir(dir);
	}
}

static void remove_event_file_dir(struct trace_event_file *file)
{
	struct dentry *dir = file->dir;
	struct dentry *child;

	if (dir) {
		spin_lock(&dir->d_lock);	/* probably unneeded */
		list_for_each_entry(child, &dir->d_subdirs, d_child) {
			if (d_really_is_positive(child))	/* probably unneeded */
				d_inode(child)->i_private = NULL;
		}
		spin_unlock(&dir->d_lock);

		tracefs_remove_recursive(dir);
	}

	list_del(&file->list);
	remove_subsystem(file->system);
	free_event_filter(file->filter);
	kmem_cache_free(file_cachep, file);
}

/*
 * __ftrace_set_clr_event(NULL, NULL, NULL, set) will set/unset all events.
 */
static int
__ftrace_set_clr_event_nolock(struct trace_array *tr, const char *match,
			      const char *sub, const char *event, int set)
{
	struct trace_event_file *file;
	struct trace_event_call *call;
	const char *name;
	int ret = -EINVAL;

	list_for_each_entry(file, &tr->events, list) {

		call = file->event_call;
		name = trace_event_name(call);

		if (!name || !call->class || !call->class->reg)
			continue;

		if (call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)
			continue;

		if (match &&
		    strcmp(match, name) != 0 &&
		    strcmp(match, call->class->system) != 0)
			continue;

		if (sub && strcmp(sub, call->class->system) != 0)
			continue;

		if (event && strcmp(event, name) != 0)
			continue;

		ftrace_event_enable_disable(file, set);

		ret = 0;
	}

	return ret;
}

static int __ftrace_set_clr_event(struct trace_array *tr, const char *match,
				  const char *sub, const char *event, int set)
{
	int ret;

	mutex_lock(&event_mutex);
	ret = __ftrace_set_clr_event_nolock(tr, match, sub, event, set);
	mutex_unlock(&event_mutex);

	return ret;
}

static int ftrace_set_clr_event(struct trace_array *tr, char *buf, int set)
{
	char *event = NULL, *sub = NULL, *match;
	int ret;

	/*
	 * The buf format can be <subsystem>:<event-name>
	 *  *:<event-name> means any event by that name.
	 *  :<event-name> is the same.
	 *
	 *  <subsystem>:* means all events in that subsystem
	 *  <subsystem>: means the same.
	 *
	 *  <name> (no ':') means all events in a subsystem with
	 *  the name <name> or any event that matches <name>
	 */

	match = strsep(&buf, ":");
	if (buf) {
		sub = match;
		event = buf;
		match = NULL;

		if (!strlen(sub) || strcmp(sub, "*") == 0)
			sub = NULL;
		if (!strlen(event) || strcmp(event, "*") == 0)
			event = NULL;
	}

	ret = __ftrace_set_clr_event(tr, match, sub, event, set);

	/* Put back the colon to allow this to be called again */
	if (buf)
		*(buf - 1) = ':';

	return ret;
}

/**
 * trace_set_clr_event - enable or disable an event
 * @system: system name to match (NULL for any system)
 * @event: event name to match (NULL for all events, within system)
 * @set: 1 to enable, 0 to disable
 *
 * This is a way for other parts of the kernel to enable or disable
 * event recording.
 *
 * Returns 0 on success, -EINVAL if the parameters do not match any
 * registered events.
 */
int trace_set_clr_event(const char *system, const char *event, int set)
{
	struct trace_array *tr = top_trace_array();

	if (!tr)
		return -ENODEV;

	return __ftrace_set_clr_event(tr, NULL, system, event, set);
}
EXPORT_SYMBOL_GPL(trace_set_clr_event);

/* 128 should be much more than enough */
#define EVENT_BUF_SIZE		127

static ssize_t
ftrace_event_write(struct file *file, const char __user *ubuf,
		   size_t cnt, loff_t *ppos)
{
	struct trace_parser parser;
	struct seq_file *m = file->private_data;
	struct trace_array *tr = m->private;
	ssize_t read, ret;

	if (!cnt)
		return 0;

	ret = tracing_update_buffers();
	if (ret < 0)
		return ret;

	if (trace_parser_get_init(&parser, EVENT_BUF_SIZE + 1))
		return -ENOMEM;

	read = trace_get_user(&parser, ubuf, cnt, ppos);

	if (read >= 0 && trace_parser_loaded((&parser))) {
		int set = 1;

		if (*parser.buffer == '!')
			set = 0;

		parser.buffer[parser.idx] = 0;

		ret = ftrace_set_clr_event(tr, parser.buffer + !set, set);
		if (ret)
			goto out_put;
	}

	ret = read;

 out_put:
	trace_parser_put(&parser);

	return ret;
}

static void *
t_next(struct seq_file *m, void *v, loff_t *pos)
{
	struct trace_event_file *file = v;
	struct trace_event_call *call;
	struct trace_array *tr = m->private;

	(*pos)++;

	list_for_each_entry_continue(file, &tr->events, list) {
		call = file->event_call;
		/*
		 * The ftrace subsystem is for showing formats only.
		 * They can not be enabled or disabled via the event files.
		 */
		if (call->class && call->class->reg &&
		    !(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE))
			return file;
	}

	return NULL;
}

static void *t_start(struct seq_file *m, loff_t *pos)
{
	struct trace_event_file *file;
	struct trace_array *tr = m->private;
	loff_t l;

	mutex_lock(&event_mutex);

	file = list_entry(&tr->events, struct trace_event_file, list);
	for (l = 0; l <= *pos; ) {
		file = t_next(m, file, &l);
		if (!file)
			break;
	}
	return file;
}

static void *
s_next(struct seq_file *m, void *v, loff_t *pos)
{
	struct trace_event_file *file = v;
	struct trace_array *tr = m->private;

	(*pos)++;

	list_for_each_entry_continue(file, &tr->events, list) {
		if (file->flags & EVENT_FILE_FL_ENABLED)
			return file;
	}

	return NULL;
}

static void *s_start(struct seq_file *m, loff_t *pos)
{
	struct trace_event_file *file;
	struct trace_array *tr = m->private;
	loff_t l;

	mutex_lock(&event_mutex);

	file = list_entry(&tr->events, struct trace_event_file, list);
	for (l = 0; l <= *pos; ) {
		file = s_next(m, file, &l);
		if (!file)
			break;
	}
	return file;
}

static int t_show(struct seq_file *m, void *v)
{
	struct trace_event_file *file = v;
	struct trace_event_call *call = file->event_call;

	if (strcmp(call->class->system, TRACE_SYSTEM) != 0)
		seq_printf(m, "%s:", call->class->system);
	seq_printf(m, "%s\n", trace_event_name(call));

	return 0;
}

static void t_stop(struct seq_file *m, void *p)
{
	mutex_unlock(&event_mutex);
}

static void *
p_next(struct seq_file *m, void *v, loff_t *pos)
{
	struct trace_array *tr = m->private;
	struct trace_pid_list *pid_list = rcu_dereference_sched(tr->filtered_pids);
	unsigned long pid = (unsigned long)v;

	(*pos)++;

	/* pid already is +1 of the actual prevous bit */
	pid = find_next_bit(pid_list->pids, pid_list->pid_max, pid);

	/* Return pid + 1 to allow zero to be represented */
	if (pid < pid_list->pid_max)
		return (void *)(pid + 1);

	return NULL;
}

static void *p_start(struct seq_file *m, loff_t *pos)
	__acquires(RCU)
{
	struct trace_pid_list *pid_list;
	struct trace_array *tr = m->private;
	unsigned long pid;
	loff_t l = 0;

	/*
	 * Grab the mutex, to keep calls to p_next() having the same
	 * tr->filtered_pids as p_start() has.
	 * If we just passed the tr->filtered_pids around, then RCU would
	 * have been enough, but doing that makes things more complex.
	 */
	mutex_lock(&event_mutex);
	rcu_read_lock_sched();

	pid_list = rcu_dereference_sched(tr->filtered_pids);

	if (!pid_list)
		return NULL;

	pid = find_first_bit(pid_list->pids, pid_list->pid_max);
	if (pid >= pid_list->pid_max)
		return NULL;

	/* Return pid + 1 so that zero can be the exit value */
	for (pid++; pid && l < *pos;
	     pid = (unsigned long)p_next(m, (void *)pid, &l))
		;
	return (void *)pid;
}

static void p_stop(struct seq_file *m, void *p)
	__releases(RCU)
{
	rcu_read_unlock_sched();
	mutex_unlock(&event_mutex);
}

static int p_show(struct seq_file *m, void *v)
{
	unsigned long pid = (unsigned long)v - 1;

	seq_printf(m, "%lu\n", pid);
	return 0;
}

static ssize_t
event_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
		  loff_t *ppos)
{
	struct trace_event_file *file;
	unsigned long flags;
	char buf[4] = "0";

	mutex_lock(&event_mutex);
	file = event_file_data(filp);
	if (likely(file))
		flags = file->flags;
	mutex_unlock(&event_mutex);

	if (!file)
		return -ENODEV;

	if (flags & EVENT_FILE_FL_ENABLED &&
	    !(flags & EVENT_FILE_FL_SOFT_DISABLED))
		strcpy(buf, "1");

	if (flags & EVENT_FILE_FL_SOFT_DISABLED ||
	    flags & EVENT_FILE_FL_SOFT_MODE)
		strcat(buf, "*");

	strcat(buf, "\n");

	return simple_read_from_buffer(ubuf, cnt, ppos, buf, strlen(buf));
}

static ssize_t
event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
		   loff_t *ppos)
{
	struct trace_event_file *file;
	unsigned long val;
	int ret;

	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
	if (ret)
		return ret;

	ret = tracing_update_buffers();
	if (ret < 0)
		return ret;

	switch (val) {
	case 0:
	case 1:
		ret = -ENODEV;
		mutex_lock(&event_mutex);
		file = event_file_data(filp);
		if (likely(file))
			ret = ftrace_event_enable_disable(file, val);
		mutex_unlock(&event_mutex);
		break;

	default:
		return -EINVAL;
	}

	*ppos += cnt;

	return ret ? ret : cnt;
}

static ssize_t
system_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
		   loff_t *ppos)
{
	const char set_to_char[4] = { '?', '0', '1', 'X' };
	struct trace_subsystem_dir *dir = filp->private_data;
	struct event_subsystem *system = dir->subsystem;
	struct trace_event_call *call;
	struct trace_event_file *file;
	struct trace_array *tr = dir->tr;
	char buf[2];
	int set = 0;
	int ret;

	mutex_lock(&event_mutex);
	list_for_each_entry(file, &tr->events, list) {
		call = file->event_call;
		if (!trace_event_name(call) || !call->class || !call->class->reg)
			continue;

		if (system && strcmp(call->class->system, system->name) != 0)
			continue;

		/*
		 * We need to find out if all the events are set
		 * or if all events or cleared, or if we have
		 * a mixture.
		 */
		set |= (1 << !!(file->flags & EVENT_FILE_FL_ENABLED));

		/*
		 * If we have a mixture, no need to look further.
		 */
		if (set == 3)
			break;
	}
	mutex_unlock(&event_mutex);

	buf[0] = set_to_char[set];
	buf[1] = '\n';

	ret = simple_read_from_buffer(ubuf, cnt, ppos, buf, 2);

	return ret;
}

static ssize_t
system_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
		    loff_t *ppos)
{
	struct trace_subsystem_dir *dir = filp->private_data;
	struct event_subsystem *system = dir->subsystem;
	const char *name = NULL;
	unsigned long val;
	ssize_t ret;

	ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
	if (ret)
		return ret;

	ret = tracing_update_buffers();
	if (ret < 0)
		return ret;

	if (val != 0 && val != 1)
		return -EINVAL;

	/*
	 * Opening of "enable" adds a ref count to system,
	 * so the name is safe to use.
	 */
	if (system)
		name = system->name;

	ret = __ftrace_set_clr_event(dir->tr, NULL, name, NULL, val);
	if (ret)
		goto out;

	ret = cnt;

out:
	*ppos += cnt;

	return ret;
}

enum {
	FORMAT_HEADER		= 1,
	FORMAT_FIELD_SEPERATOR	= 2,
	FORMAT_PRINTFMT		= 3,
};

static void *f_next(struct seq_file *m, void *v, loff_t *pos)
{
	struct trace_event_call *call = event_file_data(m->private);
	struct list_head *common_head = &ftrace_common_fields;
	struct list_head *head = trace_get_fields(call);
	struct list_head *node = v;

	(*pos)++;

	switch ((unsigned long)v) {
	case FORMAT_HEADER:
		node = common_head;
		break;

	case FORMAT_FIELD_SEPERATOR:
		node = head;
		break;

	case FORMAT_PRINTFMT:
		/* all done */
		return NULL;
	}

	node = node->prev;
	if (node == common_head)
		return (void *)FORMAT_FIELD_SEPERATOR;
	else if (node == head)
		return (void *)FORMAT_PRINTFMT;
	else
		return node;
}

static int f_show(struct seq_file *m, void *v)
{
	struct trace_event_call *call = event_file_data(m->private);
	struct ftrace_event_field *field;
	const char *array_descriptor;

	switch ((unsigned long)v) {
	case FORMAT_HEADER:
		seq_printf(m, "name: %s\n", trace_event_name(call));
		seq_printf(m, "ID: %d\n", call->event.type);
		seq_puts(m, "format:\n");
		return 0;

	case FORMAT_FIELD_SEPERATOR:
		seq_putc(m, '\n');
		return 0;

	case FORMAT_PRINTFMT:
		seq_printf(m, "\nprint fmt: %s\n",
			   call->print_fmt);
		return 0;
	}

	field = list_entry(v, struct ftrace_event_field, link);
	/*
	 * Smartly shows the array type(except dynamic array).
	 * Normal:
	 *	field:TYPE VAR
	 * If TYPE := TYPE[LEN], it is shown:
	 *	field:TYPE VAR[LEN]
	 */
	array_descriptor = strchr(field->type, '[');

	if (!strncmp(field->type, "__data_loc", 10))
		array_descriptor = NULL;

	if (!array_descriptor)
		seq_printf(m, "\tfield:%s %s;\toffset:%u;\tsize:%u;\tsigned:%d;\n",
			   field->type, field->name, field->offset,
			   field->size, !!field->is_signed);
	else
		seq_printf(m, "\tfield:%.*s %s%s;\toffset:%u;\tsize:%u;\tsigned:%d;\n",
			   (int)(array_descriptor - field->type),
			   field->type, field->name,
			   array_descriptor, field->offset,
			   field->size, !!field->is_signed);

	return 0;
}

static void *f_start(struct seq_file *m, loff_t *pos)
{
	void *p = (void *)FORMAT_HEADER;
	loff_t l = 0;

	/* ->stop() is called even if ->start() fails */
	mutex_lock(&event_mutex);
	if (!event_file_data(m->private))
		return ERR_PTR(-ENODEV);

	while (l < *pos && p)
		p = f_next(m, p, &l);

	return p;
}

static void f_stop(struct seq_file *m, void *p)
{
	mutex_unlock(&event_mutex);
}

static const struct seq_operations trace_format_seq_ops = {
	.start		= f_start,
	.next		= f_next,
	.stop		= f_stop,
	.show		= f_show,
};

static int trace_format_open(struct inode *inode, struct file *file)
{
	struct seq_file *m;
	int ret;

	ret = seq_open(file, &trace_format_seq_ops);
	if (ret < 0)
		return ret;

	m = file->private_data;
	m->private = file;

	return 0;
}

static ssize_t
event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
{
	int id = (long)event_file_data(filp);
	char buf[32];
	int len;

	if (*ppos)
		return 0;

	if (unlikely(!id))
		return -ENODEV;

	len = sprintf(buf, "%d\n", id);

	return simple_read_from_buffer(ubuf, cnt, ppos, buf, len);
}

static ssize_t
event_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
		  loff_t *ppos)
{
	struct trace_event_file *file;
	struct trace_seq *s;
	int r = -ENODEV;

	if (*ppos)
		return 0;

	s = kmalloc(sizeof(*s), GFP_KERNEL);

	if (!s)
		return -ENOMEM;

	trace_seq_init(s);

	mutex_lock(&event_mutex);
	file = event_file_data(filp);
	if (file)
		print_event_filter(file, s);
	mutex_unlock(&event_mutex);

	if (file)
		r = simple_read_from_buffer(ubuf, cnt, ppos,
					    s->buffer, trace_seq_used(s));

	kfree(s);

	return r;
}

static ssize_t
event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
		   loff_t *ppos)
{
	struct trace_event_file *file;
	char *buf;
	int err = -ENODEV;

	if (cnt >= PAGE_SIZE)
		return -EINVAL;

	buf = memdup_user_nul(ubuf, cnt);
	if (IS_ERR(buf))
		return PTR_ERR(buf);

	mutex_lock(&event_mutex);
	file = event_file_data(filp);
	if (file)
		err = apply_event_filter(file, buf);
	mutex_unlock(&event_mutex);

	kfree(buf);
	if (err < 0)
		return err;

	*ppos += cnt;

	return cnt;
}

static LIST_HEAD(event_subsystems);

static int subsystem_open(struct inode *inode, struct file *filp)
{
	struct event_subsystem *system = NULL;
	struct trace_subsystem_dir *dir = NULL; /* Initialize for gcc */
	struct trace_array *tr;
	int ret;

	if (tracing_is_disabled())
		return -ENODEV;

	/* Make sure the system still exists */
	mutex_lock(&trace_types_lock);
	mutex_lock(&event_mutex);
	list_for_each_entry(tr, &ftrace_trace_arrays, list) {
		list_for_each_entry(dir, &tr->systems, list) {
			if (dir == inode->i_private) {
				/* Don't open systems with no events */
				if (dir->nr_events) {
					__get_system_dir(dir);
					system = dir->subsystem;
				}
				goto exit_loop;
			}
		}
	}
 exit_loop:
	mutex_unlock(&event_mutex);
	mutex_unlock(&trace_types_lock);

	if (!system)
		return -ENODEV;

	/* Some versions of gcc think dir can be uninitialized here */
	WARN_ON(!dir);

	/* Still need to increment the ref count of the system */
	if (trace_array_get(tr) < 0) {
		put_system(dir);
		return -ENODEV;
	}

	ret = tracing_open_generic(inode, filp);
	if (ret < 0) {
		trace_array_put(tr);
		put_system(dir);
	}

	return ret;
}

static int system_tr_open(struct inode *inode, struct file *filp)
{
	struct trace_subsystem_dir *dir;
	struct trace_array *tr = inode->i_private;
	int ret;

	if (tracing_is_disabled())
		return -ENODEV;

	if (trace_array_get(tr) < 0)
		return -ENODEV;

	/* Make a temporary dir that has no system but points to tr */
	dir = kzalloc(sizeof(*dir), GFP_KERNEL);
	if (!dir) {
		trace_array_put(tr);
		return -ENOMEM;
	}

	dir->tr = tr;

	ret = tracing_open_generic(inode, filp);
	if (ret < 0) {
		trace_array_put(tr);
		kfree(dir);
		return ret;
	}

	filp->private_data = dir;

	return 0;
}

static int subsystem_release(struct inode *inode, struct file *file)
{
	struct trace_subsystem_dir *dir = file->private_data;

	trace_array_put(dir->tr);

	/*
	 * If dir->subsystem is NULL, then this is a temporary
	 * descriptor that was made for a trace_array to enable
	 * all subsystems.
	 */
	if (dir->subsystem)
		put_system(dir);
	else
		kfree(dir);

	return 0;
}

static ssize_t
subsystem_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
		      loff_t *ppos)
{
	struct trace_subsystem_dir *dir = filp->private_data;
	struct event_subsystem *system = dir->subsystem;
	struct trace_seq *s;
	int r;

	if (*ppos)
		return 0;

	s = kmalloc(sizeof(*s), GFP_KERNEL);
	if (!s)
		return -ENOMEM;

	trace_seq_init(s);

	print_subsystem_event_filter(system, s);
	r = simple_read_from_buffer(ubuf, cnt, ppos,
				    s->buffer, trace_seq_used(s));

	kfree(s);

	return r;
}

static ssize_t
subsystem_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
		       loff_t *ppos)
{
	struct trace_subsystem_dir *dir = filp->private_data;
	char *buf;
	int err;

	if (cnt >= PAGE_SIZE)
		return -EINVAL;

	buf = memdup_user_nul(ubuf, cnt);
	if (IS_ERR(buf))
		return PTR_ERR(buf);

	err = apply_subsystem_event_filter(dir, buf);
	kfree(buf);
	if (err < 0)
		return err;

	*ppos += cnt;

	return cnt;
}

static ssize_t
show_header(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
{
	int (*func)(struct trace_seq *s) = filp->private_data;
	struct trace_seq *s;
	int r;

	if (*ppos)
		return 0;

	s = kmalloc(sizeof(*s), GFP_KERNEL);
	if (!s)
		return -ENOMEM;

	trace_seq_init(s);

	func(s);
	r = simple_read_from_buffer(ubuf, cnt, ppos,
				    s->buffer, trace_seq_used(s));

	kfree(s);

	return r;
}

static void ignore_task_cpu(void *data)
{
	struct trace_array *tr = data;
	struct trace_pid_list *pid_list;

	/*
	 * This function is called by on_each_cpu() while the
	 * event_mutex is held.
	 */
	pid_list = rcu_dereference_protected(tr->filtered_pids,
					     mutex_is_locked(&event_mutex));

	this_cpu_write(tr->trace_buffer.data->ignore_pid,
		       ignore_this_task(pid_list, current));
}

static ssize_t
ftrace_event_pid_write(struct file *filp, const char __user *ubuf,
		       size_t cnt, loff_t *ppos)
{
	struct seq_file *m = filp->private_data;
	struct trace_array *tr = m->private;
	struct trace_pid_list *filtered_pids = NULL;
	struct trace_pid_list *pid_list;
	struct trace_event_file *file;
	struct trace_parser parser;
	unsigned long val;
	loff_t this_pos;
	ssize_t read = 0;
	ssize_t ret = 0;
	pid_t pid;
	int nr_pids = 0;

	if (!cnt)
		return 0;

	ret = tracing_update_buffers();
	if (ret < 0)
		return ret;

	if (trace_parser_get_init(&parser, EVENT_BUF_SIZE + 1))
		return -ENOMEM;

	mutex_lock(&event_mutex);
	filtered_pids = rcu_dereference_protected(tr->filtered_pids,
					     lockdep_is_held(&event_mutex));

	/*
	 * Always recreate a new array. The write is an all or nothing
	 * operation. Always create a new array when adding new pids by
	 * the user. If the operation fails, then the current list is
	 * not modified.
	 */
	pid_list = kmalloc(sizeof(*pid_list), GFP_KERNEL);
	if (!pid_list) {
		read = -ENOMEM;
		goto out;
	}
	pid_list->pid_max = READ_ONCE(pid_max);
	/* Only truncating will shrink pid_max */
	if (filtered_pids && filtered_pids->pid_max > pid_list->pid_max)
		pid_list->pid_max = filtered_pids->pid_max;
	pid_list->pids = vzalloc((pid_list->pid_max + 7) >> 3);
	if (!pid_list->pids) {
		kfree(pid_list);
		read = -ENOMEM;
		goto out;
	}
	if (filtered_pids) {
		/* copy the current bits to the new max */
		pid = find_first_bit(filtered_pids->pids,
				     filtered_pids->pid_max);
		while (pid < filtered_pids->pid_max) {
			set_bit(pid, pid_list->pids);
			pid = find_next_bit(filtered_pids->pids,
					    filtered_pids->pid_max,
					    pid + 1);
			nr_pids++;
		}
	}

	while (cnt > 0) {

		this_pos = 0;

		ret = trace_get_user(&parser, ubuf, cnt, &this_pos);
		if (ret < 0 || !trace_parser_loaded(&parser))
			break;

		read += ret;
		ubuf += ret;
		cnt -= ret;

		parser.buffer[parser.idx] = 0;

		ret = -EINVAL;
		if (kstrtoul(parser.buffer, 0, &val))
			break;
		if (val >= pid_list->pid_max)
			break;

		pid = (pid_t)val;

		set_bit(pid, pid_list->pids);
		nr_pids++;

		trace_parser_clear(&parser);
		ret = 0;
	}
	trace_parser_put(&parser);

	if (ret < 0) {
		vfree(pid_list->pids);
		kfree(pid_list);
		read = ret;
		goto out;
	}

	if (!nr_pids) {
		/* Cleared the list of pids */
		vfree(pid_list->pids);
		kfree(pid_list);
		read = ret;
		if (!filtered_pids)
			goto out;
		pid_list = NULL;
	}
	rcu_assign_pointer(tr->filtered_pids, pid_list);

	list_for_each_entry(file, &tr->events, list) {
		set_bit(EVENT_FILE_FL_PID_FILTER_BIT, &file->flags);
	}

	if (filtered_pids) {
		synchronize_sched();

		vfree(filtered_pids->pids);
		kfree(filtered_pids);
	} else {
		/*
		 * Register a probe that is called before all other probes
		 * to set ignore_pid if next or prev do not match.
		 * Register a probe this is called after all other probes
		 * to only keep ignore_pid set if next pid matches.
		 */
		register_trace_prio_sched_switch(event_filter_pid_sched_switch_probe_pre,
						 tr, INT_MAX);
		register_trace_prio_sched_switch(event_filter_pid_sched_switch_probe_post,
						 tr, 0);

		register_trace_prio_sched_wakeup(event_filter_pid_sched_wakeup_probe_pre,
						 tr, INT_MAX);
		register_trace_prio_sched_wakeup(event_filter_pid_sched_wakeup_probe_post,
						 tr, 0);

		register_trace_prio_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_pre,
						     tr, INT_MAX);
		register_trace_prio_sched_wakeup_new(event_filter_pid_sched_wakeup_probe_post,
						     tr, 0);

		register_trace_prio_sched_waking(event_filter_pid_sched_wakeup_probe_pre,
						 tr, INT_MAX);
		register_trace_prio_sched_waking(event_filter_pid_sched_wakeup_probe_post,
						 tr, 0);
	}

	/*
	 * Ignoring of pids is done at task switch. But we have to
	 * check for those tasks that are currently running.
	 * Always do this in case a pid was appended or removed.
	 */
	on_each_cpu(ignore_task_cpu, tr, 1);

 out:
	mutex_unlock(&event_mutex);

	ret = read;
	if (read > 0)
		*ppos += read;

	return ret;
}

static int ftrace_event_avail_open(struct inode *inode, struct file *file);
static int ftrace_event_set_open(struct inode *inode, struct file *file);
static int ftrace_event_set_pid_open(struct inode *inode, struct file *file);
static int ftrace_event_release(struct inode *inode, struct file *file);

static const struct seq_operations show_event_seq_ops = {
	.start = t_start,
	.next = t_next,
	.show = t_show,
	.stop = t_stop,
};

static const struct seq_operations show_set_event_seq_ops = {
	.start = s_start,
	.next = s_next,
	.show = t_show,
	.stop = t_stop,
};

static const struct seq_operations show_set_pid_seq_ops = {
	.start = p_start,
	.next = p_next,
	.show = p_show,
	.stop = p_stop,
};

static const struct file_operations ftrace_avail_fops = {
	.open = ftrace_event_avail_open,
	.read = seq_read,
	.llseek = seq_lseek,
	.release = seq_release,
};

static const struct file_operations ftrace_set_event_fops = {
	.open = ftrace_event_set_open,
	.read = seq_read,
	.write = ftrace_event_write,
	.llseek = seq_lseek,
	.release = ftrace_event_release,
};

static const struct file_operations ftrace_set_event_pid_fops = {
	.open = ftrace_event_set_pid_open,
	.read = seq_read,
	.write = ftrace_event_pid_write,
	.llseek = seq_lseek,
	.release = ftrace_event_release,
};

static const struct file_operations ftrace_enable_fops = {
	.open = tracing_open_generic,
	.read = event_enable_read,
	.write = event_enable_write,
	.llseek = default_llseek,
};

static const struct file_operations ftrace_event_format_fops = {
	.open = trace_format_open,
	.read = seq_read,
	.llseek = seq_lseek,
	.release = seq_release,
};

static const struct file_operations ftrace_event_id_fops = {
	.read = event_id_read,
	.llseek = default_llseek,
};

static const struct file_operations ftrace_event_filter_fops = {
	.open = tracing_open_generic,
	.read = event_filter_read,
	.write = event_filter_write,
	.llseek = default_llseek,
};

static const struct file_operations ftrace_subsystem_filter_fops = {
	.open = subsystem_open,
	.read = subsystem_filter_read,
	.write = subsystem_filter_write,
	.llseek = default_llseek,
	.release = subsystem_release,
};

static const struct file_operations ftrace_system_enable_fops = {
	.open = subsystem_open,
	.read = system_enable_read,
	.write = system_enable_write,
	.llseek = default_llseek,
	.release = subsystem_release,
};

static const struct file_operations ftrace_tr_enable_fops = {
	.open = system_tr_open,
	.read = system_enable_read,
	.write = system_enable_write,
	.llseek = default_llseek,
	.release = subsystem_release,
};

static const struct file_operations ftrace_show_header_fops = {
	.open = tracing_open_generic,
	.read = show_header,
	.llseek = default_llseek,
};

static int
ftrace_event_open(struct inode *inode, struct file *file,
		  const struct seq_operations *seq_ops)
{
	struct seq_file *m;
	int ret;

	ret = seq_open(file, seq_ops);
	if (ret < 0)
		return ret;
	m = file->private_data;
	/* copy tr over to seq ops */
	m->private = inode->i_private;

	return ret;
}

static int ftrace_event_release(struct inode *inode, struct file *file)
{
	struct trace_array *tr = inode->i_private;

	trace_array_put(tr);

	return seq_release(inode, file);
}

static int
ftrace_event_avail_open(struct inode *inode, struct file *file)
{
	const struct seq_operations *seq_ops = &show_event_seq_ops;

	return ftrace_event_open(inode, file, seq_ops);
}

static int
ftrace_event_set_open(struct inode *inode, struct file *file)
{
	const struct seq_operations *seq_ops = &show_set_event_seq_ops;
	struct trace_array *tr = inode->i_private;
	int ret;

	if (trace_array_get(tr) < 0)
		return -ENODEV;

	if ((file->f_mode & FMODE_WRITE) &&
	    (file->f_flags & O_TRUNC))
		ftrace_clear_events(tr);

	ret = ftrace_event_open(inode, file, seq_ops);
	if (ret < 0)
		trace_array_put(tr);
	return ret;
}

static int
ftrace_event_set_pid_open(struct inode *inode, struct file *file)
{
	const struct seq_operations *seq_ops = &show_set_pid_seq_ops;
	struct trace_array *tr = inode->i_private;
	int ret;

	if (trace_array_get(tr) < 0)
		return -ENODEV;

	if ((file->f_mode & FMODE_WRITE) &&
	    (file->f_flags & O_TRUNC))
		ftrace_clear_event_pids(tr);

	ret = ftrace_event_open(inode, file, seq_ops);
	if (ret < 0)
		trace_array_put(tr);
	return ret;
}

static struct event_subsystem *
create_new_subsystem(const char *name)
{
	struct event_subsystem *system;

	/* need to create new entry */
	system = kmalloc(sizeof(*system), GFP_KERNEL);
	if (!system)
		return NULL;

	system->ref_count = 1;

	/* Only allocate if dynamic (kprobes and modules) */
	system->name = kstrdup_const(name, GFP_KERNEL);
	if (!system->name)
		goto out_free;

	system->filter = NULL;

	system->filter = kzalloc(sizeof(struct event_filter), GFP_KERNEL);
	if (!system->filter)
		goto out_free;

	list_add(&system->list, &event_subsystems);

	return system;

 out_free:
	kfree_const(system->name);
	kfree(system);
	return NULL;
}

static struct dentry *
event_subsystem_dir(struct trace_array *tr, const char *name,
		    struct trace_event_file *file, struct dentry *parent)
{
	struct trace_subsystem_dir *dir;
	struct event_subsystem *system;
	struct dentry *entry;

	/* First see if we did not already create this dir */
	list_for_each_entry(dir, &tr->systems, list) {
		system = dir->subsystem;
		if (strcmp(system->name, name) == 0) {
			dir->nr_events++;
			file->system = dir;
			return dir->entry;
		}
	}

	/* Now see if the system itself exists. */
	list_for_each_entry(system, &event_subsystems, list) {
		if (strcmp(system->name, name) == 0)
			break;
	}
	/* Reset system variable when not found */
	if (&system->list == &event_subsystems)
		system = NULL;

	dir = kmalloc(sizeof(*dir), GFP_KERNEL);
	if (!dir)
		goto out_fail;

	if (!system) {
		system = create_new_subsystem(name);
		if (!system)
			goto out_free;
	} else
		__get_system(system);

	dir->entry = tracefs_create_dir(name, parent);
	if (!dir->entry) {
		pr_warn("Failed to create system directory %s\n", name);
		__put_system(system);
		goto out_free;
	}

	dir->tr = tr;
	dir->ref_count = 1;
	dir->nr_events = 1;
	dir->subsystem = system;
	file->system = dir;

	entry = tracefs_create_file("filter", 0644, dir->entry, dir,
				    &ftrace_subsystem_filter_fops);
	if (!entry) {
		kfree(system->filter);
		system->filter = NULL;
		pr_warn("Could not create tracefs '%s/filter' entry\n", name);
	}

	trace_create_file("enable", 0644, dir->entry, dir,
			  &ftrace_system_enable_fops);

	list_add(&dir->list, &tr->systems);

	return dir->entry;

 out_free:
	kfree(dir);
 out_fail:
	/* Only print this message if failed on memory allocation */
	if (!dir || !system)
		pr_warn("No memory to create event subsystem %s\n", name);
	return NULL;
}

static int
event_create_dir(struct dentry *parent, struct trace_event_file *file)
{
	struct trace_event_call *call = file->event_call;
	struct trace_array *tr = file->tr;
	struct list_head *head;
	struct dentry *d_events;
	const char *name;
	int ret;

	/*
	 * If the trace point header did not define TRACE_SYSTEM
	 * then the system would be called "TRACE_SYSTEM".
	 */
	if (strcmp(call->class->system, TRACE_SYSTEM) != 0) {
		d_events = event_subsystem_dir(tr, call->class->system, file, parent);
		if (!d_events)
			return -ENOMEM;
	} else
		d_events = parent;

	name = trace_event_name(call);
	file->dir = tracefs_create_dir(name, d_events);
	if (!file->dir) {
		pr_warn("Could not create tracefs '%s' directory\n", name);
		return -1;
	}

	if (call->class->reg && !(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE))
		trace_create_file("enable", 0644, file->dir, file,
				  &ftrace_enable_fops);

#ifdef CONFIG_PERF_EVENTS
	if (call->event.type && call->class->reg)
		trace_create_file("id", 0444, file->dir,
				  (void *)(long)call->event.type,
				  &ftrace_event_id_fops);
#endif

	/*
	 * Other events may have the same class. Only update
	 * the fields if they are not already defined.
	 */
	head = trace_get_fields(call);
	if (list_empty(head)) {
		ret = call->class->define_fields(call);
		if (ret < 0) {
			pr_warn("Could not initialize trace point events/%s\n",
				name);
			return -1;
		}
	}
	trace_create_file("filter", 0644, file->dir, file,
			  &ftrace_event_filter_fops);

	/*
	 * Only event directories that can be enabled should have
	 * triggers.
	 */
	if (!(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE))
		trace_create_file("trigger", 0644, file->dir, file,
				  &event_trigger_fops);

#ifdef CONFIG_HIST_TRIGGERS
	trace_create_file("hist", 0444, file->dir, file,
			  &event_hist_fops);
#endif
	trace_create_file("format", 0444, file->dir, call,
			  &ftrace_event_format_fops);

	return 0;
}

static void remove_event_from_tracers(struct trace_event_call *call)
{
	struct trace_event_file *file;
	struct trace_array *tr;

	do_for_each_event_file_safe(tr, file) {
		if (file->event_call != call)
			continue;

		remove_event_file_dir(file);
		/*
		 * The do_for_each_event_file_safe() is
		 * a double loop. After finding the call for this
		 * trace_array, we use break to jump to the next
		 * trace_array.
		 */
		break;
	} while_for_each_event_file();
}

static void event_remove(struct trace_event_call *call)
{
	struct trace_array *tr;
	struct trace_event_file *file;

	do_for_each_event_file(tr, file) {
		if (file->event_call != call)
			continue;
		ftrace_event_enable_disable(file, 0);
		/*
		 * The do_for_each_event_file() is
		 * a double loop. After finding the call for this
		 * trace_array, we use break to jump to the next
		 * trace_array.
		 */
		break;
	} while_for_each_event_file();

	if (call->event.funcs)
		__unregister_trace_event(&call->event);
	remove_event_from_tracers(call);
	list_del(&call->list);
}

static int event_init(struct trace_event_call *call)
{
	int ret = 0;
	const char *name;

	name = trace_event_name(call);
	if (WARN_ON(!name))
		return -EINVAL;

	if (call->class->raw_init) {
		ret = call->class->raw_init(call);
		if (ret < 0 && ret != -ENOSYS)
			pr_warn("Could not initialize trace events/%s\n", name);
	}

	return ret;
}

static int
__register_event(struct trace_event_call *call, struct module *mod)
{
	int ret;

	ret = event_init(call);
	if (ret < 0)
		return ret;

	list_add(&call->list, &ftrace_events);
	call->mod = mod;

	return 0;
}

static char *enum_replace(char *ptr, struct trace_enum_map *map, int len)
{
	int rlen;
	int elen;

	/* Find the length of the enum value as a string */
	elen = snprintf(ptr, 0, "%ld", map->enum_value);
	/* Make sure there's enough room to replace the string with the value */
	if (len < elen)
		return NULL;

	snprintf(ptr, elen + 1, "%ld", map->enum_value);

	/* Get the rest of the string of ptr */
	rlen = strlen(ptr + len);
	memmove(ptr + elen, ptr + len, rlen);
	/* Make sure we end the new string */
	ptr[elen + rlen] = 0;

	return ptr + elen;
}

static void update_event_printk(struct trace_event_call *call,
				struct trace_enum_map *map)
{
	char *ptr;
	int quote = 0;
	int len = strlen(map->enum_string);

	for (ptr = call->print_fmt; *ptr; ptr++) {
		if (*ptr == '\\') {
			ptr++;
			/* paranoid */
			if (!*ptr)
				break;
			continue;
		}
		if (*ptr == '"') {
			quote ^= 1;
			continue;
		}
		if (quote)
			continue;
		if (isdigit(*ptr)) {
			/* skip numbers */
			do {
				ptr++;
				/* Check for alpha chars like ULL */
			} while (isalnum(*ptr));
			if (!*ptr)
				break;
			/*
			 * A number must have some kind of delimiter after
			 * it, and we can ignore that too.
			 */
			continue;
		}
		if (isalpha(*ptr) || *ptr == '_') {
			if (strncmp(map->enum_string, ptr, len) == 0 &&
			    !isalnum(ptr[len]) && ptr[len] != '_') {
				ptr = enum_replace(ptr, map, len);
				/* Hmm, enum string smaller than value */
				if (WARN_ON_ONCE(!ptr))
					return;
				/*
				 * No need to decrement here, as enum_replace()
				 * returns the pointer to the character passed
				 * the enum, and two enums can not be placed
				 * back to back without something in between.
				 * We can skip that something in between.
				 */
				continue;
			}
		skip_more:
			do {
				ptr++;
			} while (isalnum(*ptr) || *ptr == '_');
			if (!*ptr)
				break;
			/*
			 * If what comes after this variable is a '.' or
			 * '->' then we can continue to ignore that string.
			 */
			if (*ptr == '.' || (ptr[0] == '-' && ptr[1] == '>')) {
				ptr += *ptr == '.' ? 1 : 2;
				if (!*ptr)
					break;
				goto skip_more;
			}
			/*
			 * Once again, we can skip the delimiter that came
			 * after the string.
			 */
			continue;
		}
	}
}

void trace_event_enum_update(struct trace_enum_map **map, int len)
{
	struct trace_event_call *call, *p;
	const char *last_system = NULL;
	int last_i;
	int i;

	down_write(&trace_event_sem);
	list_for_each_entry_safe(call, p, &ftrace_events, list) {
		/* events are usually grouped together with systems */
		if (!last_system || call->class->system != last_system) {
			last_i = 0;
			last_system = call->class->system;
		}

		for (i = last_i; i < len; i++) {
			if (call->class->system == map[i]->system) {
				/* Save the first system if need be */
				if (!last_i)
					last_i = i;
				update_event_printk(call, map[i]);
			}
		}
	}
	up_write(&trace_event_sem);
}

static struct trace_event_file *
trace_create_new_event(struct trace_event_call *call,
		       struct trace_array *tr)
{
	struct trace_event_file *file;

	file = kmem_cache_alloc(file_cachep, GFP_TRACE);
	if (!file)
		return NULL;

	file->event_call = call;
	file->tr = tr;
	atomic_set(&file->sm_ref, 0);
	atomic_set(&file->tm_ref, 0);
	INIT_LIST_HEAD(&file->triggers);
	list_add(&file->list, &tr->events);

	return file;
}

/* Add an event to a trace directory */
static int
__trace_add_new_event(struct trace_event_call *call, struct trace_array *tr)
{
	struct trace_event_file *file;

	file = trace_create_new_event(call, tr);
	if (!file)
		return -ENOMEM;

	return event_create_dir(tr->event_dir, file);
}

/*
 * Just create a decriptor for early init. A descriptor is required
 * for enabling events at boot. We want to enable events before
 * the filesystem is initialized.
 */
static __init int
__trace_early_add_new_event(struct trace_event_call *call,
			    struct trace_array *tr)
{
	struct trace_event_file *file;

	file = trace_create_new_event(call, tr);
	if (!file)
		return -ENOMEM;

	return 0;
}

struct ftrace_module_file_ops;
static void __add_event_to_tracers(struct trace_event_call *call);

/* Add an additional event_call dynamically */
int trace_add_event_call(struct trace_event_call *call)
{
	int ret;
	mutex_lock(&trace_types_lock);
	mutex_lock(&event_mutex);

	ret = __register_event(call, NULL);
	if (ret >= 0)
		__add_event_to_tracers(call);

	mutex_unlock(&event_mutex);
	mutex_unlock(&trace_types_lock);
	return ret;
}

/*
 * Must be called under locking of trace_types_lock, event_mutex and
 * trace_event_sem.
 */
static void __trace_remove_event_call(struct trace_event_call *call)
{
	event_remove(call);
	trace_destroy_fields(call);
	free_event_filter(call->filter);
	call->filter = NULL;
}

static int probe_remove_event_call(struct trace_event_call *call)
{
	struct trace_array *tr;
	struct trace_event_file *file;

#ifdef CONFIG_PERF_EVENTS
	if (call->perf_refcount)
		return -EBUSY;
#endif
	do_for_each_event_file(tr, file) {
		if (file->event_call != call)
			continue;
		/*
		 * We can't rely on ftrace_event_enable_disable(enable => 0)
		 * we are going to do, EVENT_FILE_FL_SOFT_MODE can suppress
		 * TRACE_REG_UNREGISTER.
		 */
		if (file->flags & EVENT_FILE_FL_ENABLED)
			return -EBUSY;
		/*
		 * The do_for_each_event_file_safe() is
		 * a double loop. After finding the call for this
		 * trace_array, we use break to jump to the next
		 * trace_array.
		 */
		break;
	} while_for_each_event_file();

	__trace_remove_event_call(call);

	return 0;
}

/* Remove an event_call */
int trace_remove_event_call(struct trace_event_call *call)
{
	int ret;

	mutex_lock(&trace_types_lock);
	mutex_lock(&event_mutex);
	down_write(&trace_event_sem);
	ret = probe_remove_event_call(call);
	up_write(&trace_event_sem);
	mutex_unlock(&event_mutex);
	mutex_unlock(&trace_types_lock);

	return ret;
}

#define for_each_event(event, start, end)			\
	for (event = start;					\
	     (unsigned long)event < (unsigned long)end;		\
	     event++)

#ifdef CONFIG_MODULES

static void trace_module_add_events(struct module *mod)
{
	struct trace_event_call **call, **start, **end;

	if (!mod->num_trace_events)
		return;

	/* Don't add infrastructure for mods without tracepoints */
	if (trace_module_has_bad_taint(mod)) {
		pr_err("%s: module has bad taint, not creating trace events\n",
		       mod->name);
		return;
	}

	start = mod->trace_events;
	end = mod->trace_events + mod->num_trace_events;

	for_each_event(call, start, end) {
		__register_event(*call, mod);
		__add_event_to_tracers(*call);
	}
}

static void trace_module_remove_events(struct module *mod)
{
	struct trace_event_call *call, *p;
	bool clear_trace = false;

	down_write(&trace_event_sem);
	list_for_each_entry_safe(call, p, &ftrace_events, list) {
		if (call->mod == mod) {
			if (call->flags & TRACE_EVENT_FL_WAS_ENABLED)
				clear_trace = true;
			__trace_remove_event_call(call);
		}
	}
	up_write(&trace_event_sem);

	/*
	 * It is safest to reset the ring buffer if the module being unloaded
	 * registered any events that were used. The only worry is if
	 * a new module gets loaded, and takes on the same id as the events
	 * of this module. When printing out the buffer, traced events left
	 * over from this module may be passed to the new module events and
	 * unexpected results may occur.
	 */
	if (clear_trace)
		tracing_reset_all_online_cpus();
}

static int trace_module_notify(struct notifier_block *self,
			       unsigned long val, void *data)
{
	struct module *mod = data;

	mutex_lock(&trace_types_lock);
	mutex_lock(&event_mutex);
	switch (val) {
	case MODULE_STATE_COMING:
		trace_module_add_events(mod);
		break;
	case MODULE_STATE_GOING:
		trace_module_remove_events(mod);
		break;
	}
	mutex_unlock(&event_mutex);
	mutex_unlock(&trace_types_lock);

	return 0;
}

static struct notifier_block trace_module_nb = {
	.notifier_call = trace_module_notify,
	.priority = 1, /* higher than trace.c module notify */
};
#endif /* CONFIG_MODULES */

/* Create a new event directory structure for a trace directory. */
static void
__trace_add_event_dirs(struct trace_array *tr)
{
	struct trace_event_call *call;
	int ret;

	list_for_each_entry(call, &ftrace_events, list) {
		ret = __trace_add_new_event(call, tr);
		if (ret < 0)
			pr_warn("Could not create directory for event %s\n",
				trace_event_name(call));
	}
}

struct trace_event_file *
find_event_file(struct trace_array *tr, const char *system,  const char *event)
{
	struct trace_event_file *file;
	struct trace_event_call *call;
	const char *name;

	list_for_each_entry(file, &tr->events, list) {

		call = file->event_call;
		name = trace_event_name(call);

		if (!name || !call->class || !call->class->reg)
			continue;

		if (call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)
			continue;

		if (strcmp(event, name) == 0 &&
		    strcmp(system, call->class->system) == 0)
			return file;
	}
	return NULL;
}

#ifdef CONFIG_DYNAMIC_FTRACE

/* Avoid typos */
#define ENABLE_EVENT_STR	"enable_event"
#define DISABLE_EVENT_STR	"disable_event"

struct event_probe_data {
	struct trace_event_file	*file;
	unsigned long			count;
	int				ref;
	bool				enable;
};

static void
event_enable_probe(unsigned long ip, unsigned long parent_ip, void **_data)
{
	struct event_probe_data **pdata = (struct event_probe_data **)_data;
	struct event_probe_data *data = *pdata;

	if (!data)
		return;

	if (data->enable)
		clear_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &data->file->flags);
	else
		set_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &data->file->flags);
}

static void
event_enable_count_probe(unsigned long ip, unsigned long parent_ip, void **_data)
{
	struct event_probe_data **pdata = (struct event_probe_data **)_data;
	struct event_probe_data *data = *pdata;

	if (!data)
		return;

	if (!data->count)
		return;

	/* Skip if the event is in a state we want to switch to */
	if (data->enable == !(data->file->flags & EVENT_FILE_FL_SOFT_DISABLED))
		return;

	if (data->count != -1)
		(data->count)--;

	event_enable_probe(ip, parent_ip, _data);
}

static int
event_enable_print(struct seq_file *m, unsigned long ip,
		      struct ftrace_probe_ops *ops, void *_data)
{
	struct event_probe_data *data = _data;

	seq_printf(m, "%ps:", (void *)ip);

	seq_printf(m, "%s:%s:%s",
		   data->enable ? ENABLE_EVENT_STR : DISABLE_EVENT_STR,
		   data->file->event_call->class->system,
		   trace_event_name(data->file->event_call));

	if (data->count == -1)
		seq_puts(m, ":unlimited\n");
	else
		seq_printf(m, ":count=%ld\n", data->count);

	return 0;
}

static int
event_enable_init(struct ftrace_probe_ops *ops, unsigned long ip,
		  void **_data)
{
	struct event_probe_data **pdata = (struct event_probe_data **)_data;
	struct event_probe_data *data = *pdata;

	data->ref++;
	return 0;
}

static void
event_enable_free(struct ftrace_probe_ops *ops, unsigned long ip,
		  void **_data)
{
	struct event_probe_data **pdata = (struct event_probe_data **)_data;
	struct event_probe_data *data = *pdata;

	if (WARN_ON_ONCE(data->ref <= 0))
		return;

	data->ref--;
	if (!data->ref) {
		/* Remove the SOFT_MODE flag */
		__ftrace_event_enable_disable(data->file, 0, 1);
		module_put(data->file->event_call->mod);
		kfree(data);
	}
	*pdata = NULL;
}

static struct ftrace_probe_ops event_enable_probe_ops = {
	.func			= event_enable_probe,
	.print			= event_enable_print,
	.init			= event_enable_init,
	.free			= event_enable_free,
};

static struct ftrace_probe_ops event_enable_count_probe_ops = {
	.func			= event_enable_count_probe,
	.print			= event_enable_print,
	.init			= event_enable_init,
	.free			= event_enable_free,
};

static struct ftrace_probe_ops event_disable_probe_ops = {
	.func			= event_enable_probe,
	.print			= event_enable_print,
	.init			= event_enable_init,
	.free			= event_enable_free,
};

static struct ftrace_probe_ops event_disable_count_probe_ops = {
	.func			= event_enable_count_probe,
	.print			= event_enable_print,
	.init			= event_enable_init,
	.free			= event_enable_free,
};

static int
event_enable_func(struct ftrace_hash *hash,
		  char *glob, char *cmd, char *param, int enabled)
{
	struct trace_array *tr = top_trace_array();
	struct trace_event_file *file;
	struct ftrace_probe_ops *ops;
	struct event_probe_data *data;
	const char *system;
	const char *event;
	char *number;
	bool enable;
	int ret;

	if (!tr)
		return -ENODEV;

	/* hash funcs only work with set_ftrace_filter */
	if (!enabled || !param)
		return -EINVAL;

	system = strsep(&param, ":");
	if (!param)
		return -EINVAL;

	event = strsep(&param, ":");

	mutex_lock(&event_mutex);

	ret = -EINVAL;
	file = find_event_file(tr, system, event);
	if (!file)
		goto out;

	enable = strcmp(cmd, ENABLE_EVENT_STR) == 0;

	if (enable)
		ops = param ? &event_enable_count_probe_ops : &event_enable_probe_ops;
	else
		ops = param ? &event_disable_count_probe_ops : &event_disable_probe_ops;

	if (glob[0] == '!') {
		unregister_ftrace_function_probe_func(glob+1, ops);
		ret = 0;
		goto out;
	}

	ret = -ENOMEM;
	data = kzalloc(sizeof(*data), GFP_KERNEL);
	if (!data)
		goto out;

	data->enable = enable;
	data->count = -1;
	data->file = file;

	if (!param)
		goto out_reg;

	number = strsep(&param, ":");

	ret = -EINVAL;
	if (!strlen(number))
		goto out_free;

	/*
	 * We use the callback data field (which is a pointer)
	 * as our counter.
	 */
	ret = kstrtoul(number, 0, &data->count);
	if (ret)
		goto out_free;

 out_reg:
	/* Don't let event modules unload while probe registered */
	ret = try_module_get(file->event_call->mod);
	if (!ret) {
		ret = -EBUSY;
		goto out_free;
	}

	ret = __ftrace_event_enable_disable(file, 1, 1);
	if (ret < 0)
		goto out_put;
	ret = register_ftrace_function_probe(glob, ops, data);
	/*
	 * The above returns on success the # of functions enabled,
	 * but if it didn't find any functions it returns zero.
	 * Consider no functions a failure too.
	 */
	if (!ret) {
		ret = -ENOENT;
		goto out_disable;
	} else if (ret < 0)
		goto out_disable;
	/* Just return zero, not the number of enabled functions */
	ret = 0;
 out:
	mutex_unlock(&event_mutex);
	return ret;

 out_disable:
	__ftrace_event_enable_disable(file, 0, 1);
 out_put:
	module_put(file->event_call->mod);
 out_free:
	kfree(data);
	goto out;
}

static struct ftrace_func_command event_enable_cmd = {
	.name			= ENABLE_EVENT_STR,
	.func			= event_enable_func,
};

static struct ftrace_func_command event_disable_cmd = {
	.name			= DISABLE_EVENT_STR,
	.func			= event_enable_func,
};

static __init int register_event_cmds(void)
{
	int ret;

	ret = register_ftrace_command(&event_enable_cmd);
	if (WARN_ON(ret < 0))
		return ret;
	ret = register_ftrace_command(&event_disable_cmd);
	if (WARN_ON(ret < 0))
		unregister_ftrace_command(&event_enable_cmd);
	return ret;
}
#else
static inline int register_event_cmds(void) { return 0; }
#endif /* CONFIG_DYNAMIC_FTRACE */

/*
 * The top level array has already had its trace_event_file
 * descriptors created in order to allow for early events to
 * be recorded. This function is called after the tracefs has been
 * initialized, and we now have to create the files associated
 * to the events.
 */
static __init void
__trace_early_add_event_dirs(struct trace_array *tr)
{
	struct trace_event_file *file;
	int ret;


	list_for_each_entry(file, &tr->events, list) {
		ret = event_create_dir(tr->event_dir, file);
		if (ret < 0)
			pr_warn("Could not create directory for event %s\n",
				trace_event_name(file->event_call));
	}
}

/*
 * For early boot up, the top trace array requires to have
 * a list of events that can be enabled. This must be done before
 * the filesystem is set up in order to allow events to be traced
 * early.
 */
static __init void
__trace_early_add_events(struct trace_array *tr)
{
	struct trace_event_call *call;
	int ret;

	list_for_each_entry(call, &ftrace_events, list) {
		/* Early boot up should not have any modules loaded */
		if (WARN_ON_ONCE(call->mod))
			continue;

		ret = __trace_early_add_new_event(call, tr);
		if (ret < 0)
			pr_warn("Could not create early event %s\n",
				trace_event_name(call));
	}
}

/* Remove the event directory structure for a trace directory. */
static void
__trace_remove_event_dirs(struct trace_array *tr)
{
	struct trace_event_file *file, *next;

	list_for_each_entry_safe(file, next, &tr->events, list)
		remove_event_file_dir(file);
}

static void __add_event_to_tracers(struct trace_event_call *call)
{
	struct trace_array *tr;

	list_for_each_entry(tr, &ftrace_trace_arrays, list)
		__trace_add_new_event(call, tr);
}

extern struct trace_event_call *__start_ftrace_events[];
extern struct trace_event_call *__stop_ftrace_events[];

static char bootup_event_buf[COMMAND_LINE_SIZE] __initdata;

static __init int setup_trace_event(char *str)
{
	strlcpy(bootup_event_buf, str, COMMAND_LINE_SIZE);
	ring_buffer_expanded = true;
	tracing_selftest_disabled = true;

	return 1;
}
__setup("trace_event=", setup_trace_event);

/* Expects to have event_mutex held when called */
static int
create_event_toplevel_files(struct dentry *parent, struct trace_array *tr)
{
	struct dentry *d_events;
	struct dentry *entry;

	entry = tracefs_create_file("set_event", 0644, parent,
				    tr, &ftrace_set_event_fops);
	if (!entry) {
		pr_warn("Could not create tracefs 'set_event' entry\n");
		return -ENOMEM;
	}

	d_events = tracefs_create_dir("events", parent);
	if (!d_events) {
		pr_warn("Could not create tracefs 'events' directory\n");
		return -ENOMEM;
	}

	entry = tracefs_create_file("set_event_pid", 0644, parent,
				    tr, &ftrace_set_event_pid_fops);

	/* ring buffer internal formats */
	trace_create_file("header_page", 0444, d_events,
			  ring_buffer_print_page_header,
			  &ftrace_show_header_fops);

	trace_create_file("header_event", 0444, d_events,
			  ring_buffer_print_entry_header,
			  &ftrace_show_header_fops);

	trace_create_file("enable", 0644, d_events,
			  tr, &ftrace_tr_enable_fops);

	tr->event_dir = d_events;

	return 0;
}

/**
 * event_trace_add_tracer - add a instance of a trace_array to events
 * @parent: The parent dentry to place the files/directories for events in
 * @tr: The trace array associated with these events
 *
 * When a new instance is created, it needs to set up its events
 * directory, as well as other files associated with events. It also
 * creates the event hierachry in the @parent/events directory.
 *
 * Returns 0 on success.
 */
int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr)
{
	int ret;

	mutex_lock(&event_mutex);

	ret = create_event_toplevel_files(parent, tr);
	if (ret)
		goto out_unlock;

	down_write(&trace_event_sem);
	__trace_add_event_dirs(tr);
	up_write(&trace_event_sem);

 out_unlock:
	mutex_unlock(&event_mutex);

	return ret;
}

/*
 * The top trace array already had its file descriptors created.
 * Now the files themselves need to be created.
 */
static __init int
early_event_add_tracer(struct dentry *parent, struct trace_array *tr)
{
	int ret;

	mutex_lock(&event_mutex);

	ret = create_event_toplevel_files(parent, tr);
	if (ret)
		goto out_unlock;

	down_write(&trace_event_sem);
	__trace_early_add_event_dirs(tr);
	up_write(&trace_event_sem);

 out_unlock:
	mutex_unlock(&event_mutex);

	return ret;
}

int event_trace_del_tracer(struct trace_array *tr)
{
	mutex_lock(&event_mutex);

	/* Disable any event triggers and associated soft-disabled events */
	clear_event_triggers(tr);

	/* Clear the pid list */
	__ftrace_clear_event_pids(tr);

	/* Disable any running events */
	__ftrace_set_clr_event_nolock(tr, NULL, NULL, NULL, 0);

	/* Access to events are within rcu_read_lock_sched() */
	synchronize_sched();

	down_write(&trace_event_sem);
	__trace_remove_event_dirs(tr);
	tracefs_remove_recursive(tr->event_dir);
	up_write(&trace_event_sem);

	tr->event_dir = NULL;

	mutex_unlock(&event_mutex);

	return 0;
}

static __init int event_trace_memsetup(void)
{
	field_cachep = KMEM_CACHE(ftrace_event_field, SLAB_PANIC);
	file_cachep = KMEM_CACHE(trace_event_file, SLAB_PANIC);
	return 0;
}

static __init void
early_enable_events(struct trace_array *tr, bool disable_first)
{
	char *buf = bootup_event_buf;
	char *token;
	int ret;

	while (true) {
		token = strsep(&buf, ",");

		if (!token)
			break;

		if (*token) {
			/* Restarting syscalls requires that we stop them first */
			if (disable_first)
				ftrace_set_clr_event(tr, token, 0);

			ret = ftrace_set_clr_event(tr, token, 1);
			if (ret)
				pr_warn("Failed to enable trace event: %s\n", token);
		}

		/* Put back the comma to allow this to be called again */
		if (buf)
			*(buf - 1) = ',';
	}
}

static __init int event_trace_enable(void)
{
	struct trace_array *tr = top_trace_array();
	struct trace_event_call **iter, *call;
	int ret;

	if (!tr)
		return -ENODEV;

	for_each_event(iter, __start_ftrace_events, __stop_ftrace_events) {

		call = *iter;
		ret = event_init(call);
		if (!ret)
			list_add(&call->list, &ftrace_events);
	}

	/*
	 * We need the top trace array to have a working set of trace
	 * points at early init, before the debug files and directories
	 * are created. Create the file entries now, and attach them
	 * to the actual file dentries later.
	 */
	__trace_early_add_events(tr);

	early_enable_events(tr, false);

	trace_printk_start_comm();

	register_event_cmds();

	register_trigger_cmds();

	return 0;
}

/*
 * event_trace_enable() is called from trace_event_init() first to
 * initialize events and perhaps start any events that are on the
 * command line. Unfortunately, there are some events that will not
 * start this early, like the system call tracepoints that need
 * to set the TIF_SYSCALL_TRACEPOINT flag of pid 1. But event_trace_enable()
 * is called before pid 1 starts, and this flag is never set, making
 * the syscall tracepoint never get reached, but the event is enabled
 * regardless (and not doing anything).
 */
static __init int event_trace_enable_again(void)
{
	struct trace_array *tr;

	tr = top_trace_array();
	if (!tr)
		return -ENODEV;

	early_enable_events(tr, true);

	return 0;
}

early_initcall(event_trace_enable_again);

static __init int event_trace_init(void)
{
	struct trace_array *tr;
	struct dentry *d_tracer;
	struct dentry *entry;
	int ret;

	tr = top_trace_array();
	if (!tr)
		return -ENODEV;

	d_tracer = tracing_init_dentry();
	if (IS_ERR(d_tracer))
		return 0;

	entry = tracefs_create_file("available_events", 0444, d_tracer,
				    tr, &ftrace_avail_fops);
	if (!entry)
		pr_warn("Could not create tracefs 'available_events' entry\n");

	if (trace_define_generic_fields())
		pr_warn("tracing: Failed to allocated generic fields");

	if (trace_define_common_fields())
		pr_warn("tracing: Failed to allocate common fields");

	ret = early_event_add_tracer(d_tracer, tr);
	if (ret)
		return ret;

#ifdef CONFIG_MODULES
	ret = register_module_notifier(&trace_module_nb);
	if (ret)
		pr_warn("Failed to register trace events module notifier\n");
#endif
	return 0;
}

void __init trace_event_init(void)
{
	event_trace_memsetup();
	init_ftrace_syscalls();
	event_trace_enable();
}

fs_initcall(event_trace_init);

#ifdef CONFIG_FTRACE_STARTUP_TEST

static DEFINE_SPINLOCK(test_spinlock);
static DEFINE_SPINLOCK(test_spinlock_irq);
static DEFINE_MUTEX(test_mutex);

static __init void test_work(struct work_struct *dummy)
{
	spin_lock(&test_spinlock);
	spin_lock_irq(&test_spinlock_irq);
	udelay(1);
	spin_unlock_irq(&test_spinlock_irq);
	spin_unlock(&test_spinlock);

	mutex_lock(&test_mutex);
	msleep(1);
	mutex_unlock(&test_mutex);
}

static __init int event_test_thread(void *unused)
{
	void *test_malloc;

	test_malloc = kmalloc(1234, GFP_KERNEL);
	if (!test_malloc)
		pr_info("failed to kmalloc\n");

	schedule_on_each_cpu(test_work);

	kfree(test_malloc);

	set_current_state(TASK_INTERRUPTIBLE);
	while (!kthread_should_stop()) {
		schedule();
		set_current_state(TASK_INTERRUPTIBLE);
	}
	__set_current_state(TASK_RUNNING);

	return 0;
}

/*
 * Do various things that may trigger events.
 */
static __init void event_test_stuff(void)
{
	struct task_struct *test_thread;

	test_thread = kthread_run(event_test_thread, NULL, "test-events");
	msleep(1);
	kthread_stop(test_thread);
}

/*
 * For every trace event defined, we will test each trace point separately,
 * and then by groups, and finally all trace points.
 */
static __init void event_trace_self_tests(void)
{
	struct trace_subsystem_dir *dir;
	struct trace_event_file *file;
	struct trace_event_call *call;
	struct event_subsystem *system;
	struct trace_array *tr;
	int ret;

	tr = top_trace_array();
	if (!tr)
		return;

	pr_info("Running tests on trace events:\n");

	list_for_each_entry(file, &tr->events, list) {

		call = file->event_call;

		/* Only test those that have a probe */
		if (!call->class || !call->class->probe)
			continue;

/*
 * Testing syscall events here is pretty useless, but
 * we still do it if configured. But this is time consuming.
 * What we really need is a user thread to perform the
 * syscalls as we test.
 */
#ifndef CONFIG_EVENT_TRACE_TEST_SYSCALLS
		if (call->class->system &&
		    strcmp(call->class->system, "syscalls") == 0)
			continue;
#endif

		pr_info("Testing event %s: ", trace_event_name(call));

		/*
		 * If an event is already enabled, someone is using
		 * it and the self test should not be on.
		 */
		if (file->flags & EVENT_FILE_FL_ENABLED) {
			pr_warn("Enabled event during self test!\n");
			WARN_ON_ONCE(1);
			continue;
		}

		ftrace_event_enable_disable(file, 1);
		event_test_stuff();
		ftrace_event_enable_disable(file, 0);

		pr_cont("OK\n");
	}

	/* Now test at the sub system level */

	pr_info("Running tests on trace event systems:\n");

	list_for_each_entry(dir, &tr->systems, list) {

		system = dir->subsystem;

		/* the ftrace system is special, skip it */
		if (strcmp(system->name, "ftrace") == 0)
			continue;

		pr_info("Testing event system %s: ", system->name);

		ret = __ftrace_set_clr_event(tr, NULL, system->name, NULL, 1);
		if (WARN_ON_ONCE(ret)) {
			pr_warn("error enabling system %s\n",
				system->name);
			continue;
		}

		event_test_stuff();

		ret = __ftrace_set_clr_event(tr, NULL, system->name, NULL, 0);
		if (WARN_ON_ONCE(ret)) {
			pr_warn("error disabling system %s\n",
				system->name);
			continue;
		}

		pr_cont("OK\n");
	}

	/* Test with all events enabled */

	pr_info("Running tests on all trace events:\n");
	pr_info("Testing all events: ");

	ret = __ftrace_set_clr_event(tr, NULL, NULL, NULL, 1);
	if (WARN_ON_ONCE(ret)) {
		pr_warn("error enabling all events\n");
		return;
	}

	event_test_stuff();

	/* reset sysname */
	ret = __ftrace_set_clr_event(tr, NULL, NULL, NULL, 0);
	if (WARN_ON_ONCE(ret)) {
		pr_warn("error disabling all events\n");
		return;
	}

	pr_cont("OK\n");
}

#ifdef CONFIG_FUNCTION_TRACER

static DEFINE_PER_CPU(atomic_t, ftrace_test_event_disable);

static struct trace_event_file event_trace_file __initdata;

static void __init
function_test_events_call(unsigned long ip, unsigned long parent_ip,
			  struct ftrace_ops *op, struct pt_regs *pt_regs)
{
	struct ring_buffer_event *event;
	struct ring_buffer *buffer;
	struct ftrace_entry *entry;
	unsigned long flags;
	long disabled;
	int cpu;
	int pc;

	pc = preempt_count();
	preempt_disable_notrace();
	cpu = raw_smp_processor_id();
	disabled = atomic_inc_return(&per_cpu(ftrace_test_event_disable, cpu));

	if (disabled != 1)
		goto out;

	local_save_flags(flags);

	event = trace_event_buffer_lock_reserve(&buffer, &event_trace_file,
						TRACE_FN, sizeof(*entry),
						flags, pc);
	if (!event)
		goto out;
	entry	= ring_buffer_event_data(event);
	entry->ip			= ip;
	entry->parent_ip		= parent_ip;

	event_trigger_unlock_commit(&event_trace_file, buffer, event,
				    entry, flags, pc);
 out:
	atomic_dec(&per_cpu(ftrace_test_event_disable, cpu));
	preempt_enable_notrace();
}

static struct ftrace_ops trace_ops __initdata  =
{
	.func = function_test_events_call,
	.flags = FTRACE_OPS_FL_RECURSION_SAFE,
};

static __init void event_trace_self_test_with_function(void)
{
	int ret;

	event_trace_file.tr = top_trace_array();
	if (WARN_ON(!event_trace_file.tr))
		return;

	ret = register_ftrace_function(&trace_ops);
	if (WARN_ON(ret < 0)) {
		pr_info("Failed to enable function tracer for event tests\n");
		return;
	}
	pr_info("Running tests again, along with the function tracer\n");
	event_trace_self_tests();
	unregister_ftrace_function(&trace_ops);
}
#else
static __init void event_trace_self_test_with_function(void)
{
}
#endif

static __init int event_trace_self_tests_init(void)
{
	if (!tracing_selftest_disabled) {
		event_trace_self_tests();
		event_trace_self_test_with_function();
	}

	return 0;
}

late_initcall(event_trace_self_tests_init);

#endif
OpenPOWER on IntegriCloud