aboutsummaryrefslogtreecommitdiffstats
path: root/arch/arm/kernel/perf_event.c
blob: 49643b1467e62d529d4edd661990bb64da1e1f73 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
#undef DEBUG

/*
 * ARM performance counter support.
 *
 * Copyright (C) 2009 picoChip Designs, Ltd., Jamie Iles
 *
 * ARMv7 support: Jean Pihet <jpihet@mvista.com>
 * 2010 (c) MontaVista Software, LLC.
 *
 * This code is based on the sparc64 perf event code, which is in turn based
 * on the x86 code. Callchain code is based on the ARM OProfile backtrace
 * code.
 */
#define pr_fmt(fmt) "hw perfevents: " fmt

#include <linux/interrupt.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/perf_event.h>
#include <linux/platform_device.h>
#include <linux/spinlock.h>
#include <linux/uaccess.h>

#include <asm/cputype.h>
#include <asm/irq.h>
#include <asm/irq_regs.h>
#include <asm/pmu.h>
#include <asm/stacktrace.h>

static struct platform_device *pmu_device;

/*
 * Hardware lock to serialize accesses to PMU registers. Needed for the
 * read/modify/write sequences.
 */
DEFINE_SPINLOCK(pmu_lock);

/*
 * ARMv6 supports a maximum of 3 events, starting from index 1. If we add
 * another platform that supports more, we need to increase this to be the
 * largest of all platforms.
 *
 * ARMv7 supports up to 32 events:
 *  cycle counter CCNT + 31 events counters CNT0..30.
 *  Cortex-A8 has 1+4 counters, Cortex-A9 has 1+6 counters.
 */
#define ARMPMU_MAX_HWEVENTS		33

/* The events for a given CPU. */
struct cpu_hw_events {
	/*
	 * The events that are active on the CPU for the given index. Index 0
	 * is reserved.
	 */
	struct perf_event	*events[ARMPMU_MAX_HWEVENTS];

	/*
	 * A 1 bit for an index indicates that the counter is being used for
	 * an event. A 0 means that the counter can be used.
	 */
	unsigned long		used_mask[BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)];

	/*
	 * A 1 bit for an index indicates that the counter is actively being
	 * used.
	 */
	unsigned long		active_mask[BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)];
};
DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events);

/* PMU names. */
static const char *arm_pmu_names[] = {
	[ARM_PERF_PMU_ID_XSCALE1] = "xscale1",
	[ARM_PERF_PMU_ID_XSCALE2] = "xscale2",
	[ARM_PERF_PMU_ID_V6]	  = "v6",
	[ARM_PERF_PMU_ID_V6MP]	  = "v6mpcore",
	[ARM_PERF_PMU_ID_CA8]	  = "ARMv7 Cortex-A8",
	[ARM_PERF_PMU_ID_CA9]	  = "ARMv7 Cortex-A9",
};

struct arm_pmu {
	enum arm_perf_pmu_ids id;
	irqreturn_t	(*handle_irq)(int irq_num, void *dev);
	void		(*enable)(struct hw_perf_event *evt, int idx);
	void		(*disable)(struct hw_perf_event *evt, int idx);
	int		(*event_map)(int evt);
	u64		(*raw_event)(u64);
	int		(*get_event_idx)(struct cpu_hw_events *cpuc,
					 struct hw_perf_event *hwc);
	u32		(*read_counter)(int idx);
	void		(*write_counter)(int idx, u32 val);
	void		(*start)(void);
	void		(*stop)(void);
	int		num_events;
	u64		max_period;
};

/* Set at runtime when we know what CPU type we are. */
static const struct arm_pmu *armpmu;

enum arm_perf_pmu_ids
armpmu_get_pmu_id(void)
{
	int id = -ENODEV;

	if (armpmu != NULL)
		id = armpmu->id;

	return id;
}
EXPORT_SYMBOL_GPL(armpmu_get_pmu_id);

int
armpmu_get_max_events(void)
{
	int max_events = 0;

	if (armpmu != NULL)
		max_events = armpmu->num_events;

	return max_events;
}
EXPORT_SYMBOL_GPL(armpmu_get_max_events);

int perf_num_counters(void)
{
	return armpmu_get_max_events();
}
EXPORT_SYMBOL_GPL(perf_num_counters);

#define HW_OP_UNSUPPORTED		0xFFFF

#define C(_x) \
	PERF_COUNT_HW_CACHE_##_x

#define CACHE_OP_UNSUPPORTED		0xFFFF

static unsigned armpmu_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
				     [PERF_COUNT_HW_CACHE_OP_MAX]
				     [PERF_COUNT_HW_CACHE_RESULT_MAX];

static int
armpmu_map_cache_event(u64 config)
{
	unsigned int cache_type, cache_op, cache_result, ret;

	cache_type = (config >>  0) & 0xff;
	if (cache_type >= PERF_COUNT_HW_CACHE_MAX)
		return -EINVAL;

	cache_op = (config >>  8) & 0xff;
	if (cache_op >= PERF_COUNT_HW_CACHE_OP_MAX)
		return -EINVAL;

	cache_result = (config >> 16) & 0xff;
	if (cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX)
		return -EINVAL;

	ret = (int)armpmu_perf_cache_map[cache_type][cache_op][cache_result];

	if (ret == CACHE_OP_UNSUPPORTED)
		return -ENOENT;

	return ret;
}

static int
armpmu_event_set_period(struct perf_event *event,
			struct hw_perf_event *hwc,
			int idx)
{
	s64 left = local64_read(&hwc->period_left);
	s64 period = hwc->sample_period;
	int ret = 0;

	if (unlikely(left <= -period)) {
		left = period;
		local64_set(&hwc->period_left, left);
		hwc->last_period = period;
		ret = 1;
	}

	if (unlikely(left <= 0)) {
		left += period;
		local64_set(&hwc->period_left, left);
		hwc->last_period = period;
		ret = 1;
	}

	if (left > (s64)armpmu->max_period)
		left = armpmu->max_period;

	local64_set(&hwc->prev_count, (u64)-left);

	armpmu->write_counter(idx, (u64)(-left) & 0xffffffff);

	perf_event_update_userpage(event);

	return ret;
}

static u64
armpmu_event_update(struct perf_event *event,
		    struct hw_perf_event *hwc,
		    int idx)
{
	int shift = 64 - 32;
	s64 prev_raw_count, new_raw_count;
	u64 delta;

again:
	prev_raw_count = local64_read(&hwc->prev_count);
	new_raw_count = armpmu->read_counter(idx);

	if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
			     new_raw_count) != prev_raw_count)
		goto again;

	delta = (new_raw_count << shift) - (prev_raw_count << shift);
	delta >>= shift;

	local64_add(delta, &event->count);
	local64_sub(delta, &hwc->period_left);

	return new_raw_count;
}

static void
armpmu_read(struct perf_event *event)
{
	struct hw_perf_event *hwc = &event->hw;

	/* Don't read disabled counters! */
	if (hwc->idx < 0)
		return;

	armpmu_event_update(event, hwc, hwc->idx);
}

static void
armpmu_stop(struct perf_event *event, int flags)
{
	struct hw_perf_event *hwc = &event->hw;

	if (!armpmu)
		return;

	/*
	 * ARM pmu always has to update the counter, so ignore
	 * PERF_EF_UPDATE, see comments in armpmu_start().
	 */
	if (!(hwc->state & PERF_HES_STOPPED)) {
		armpmu->disable(hwc, hwc->idx);
		barrier(); /* why? */
		armpmu_event_update(event, hwc, hwc->idx);
		hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
	}
}

static void
armpmu_start(struct perf_event *event, int flags)
{
	struct hw_perf_event *hwc = &event->hw;

	if (!armpmu)
		return;

	/*
	 * ARM pmu always has to reprogram the period, so ignore
	 * PERF_EF_RELOAD, see the comment below.
	 */
	if (flags & PERF_EF_RELOAD)
		WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));

	hwc->state = 0;
	/*
	 * Set the period again. Some counters can't be stopped, so when we
	 * were stopped we simply disabled the IRQ source and the counter
	 * may have been left counting. If we don't do this step then we may
	 * get an interrupt too soon or *way* too late if the overflow has
	 * happened since disabling.
	 */
	armpmu_event_set_period(event, hwc, hwc->idx);
	armpmu->enable(hwc, hwc->idx);
}

static void
armpmu_del(struct perf_event *event, int flags)
{
	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
	struct hw_perf_event *hwc = &event->hw;
	int idx = hwc->idx;

	WARN_ON(idx < 0);

	clear_bit(idx, cpuc->active_mask);
	armpmu_stop(event, PERF_EF_UPDATE);
	cpuc->events[idx] = NULL;
	clear_bit(idx, cpuc->used_mask);

	perf_event_update_userpage(event);
}

static int
armpmu_add(struct perf_event *event, int flags)
{
	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
	struct hw_perf_event *hwc = &event->hw;
	int idx;
	int err = 0;

	perf_pmu_disable(event->pmu);

	/* If we don't have a space for the counter then finish early. */
	idx = armpmu->get_event_idx(cpuc, hwc);
	if (idx < 0) {
		err = idx;
		goto out;
	}

	/*
	 * If there is an event in the counter we are going to use then make
	 * sure it is disabled.
	 */
	event->hw.idx = idx;
	armpmu->disable(hwc, idx);
	cpuc->events[idx] = event;
	set_bit(idx, cpuc->active_mask);

	hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
	if (flags & PERF_EF_START)
		armpmu_start(event, PERF_EF_RELOAD);

	/* Propagate our changes to the userspace mapping. */
	perf_event_update_userpage(event);

out:
	perf_pmu_enable(event->pmu);
	return err;
}

static struct pmu pmu;

static int
validate_event(struct cpu_hw_events *cpuc,
	       struct perf_event *event)
{
	struct hw_perf_event fake_event = event->hw;

	if (event->pmu != &pmu || event->state <= PERF_EVENT_STATE_OFF)
		return 1;

	return armpmu->get_event_idx(cpuc, &fake_event) >= 0;
}

static int
validate_group(struct perf_event *event)
{
	struct perf_event *sibling, *leader = event->group_leader;
	struct cpu_hw_events fake_pmu;

	memset(&fake_pmu, 0, sizeof(fake_pmu));

	if (!validate_event(&fake_pmu, leader))
		return -ENOSPC;

	list_for_each_entry(sibling, &leader->sibling_list, group_entry) {
		if (!validate_event(&fake_pmu, sibling))
			return -ENOSPC;
	}

	if (!validate_event(&fake_pmu, event))
		return -ENOSPC;

	return 0;
}

static int
armpmu_reserve_hardware(void)
{
	int i, err = -ENODEV, irq;

	pmu_device = reserve_pmu(ARM_PMU_DEVICE_CPU);
	if (IS_ERR(pmu_device)) {
		pr_warning("unable to reserve pmu\n");
		return PTR_ERR(pmu_device);
	}

	init_pmu(ARM_PMU_DEVICE_CPU);

	if (pmu_device->num_resources < 1) {
		pr_err("no irqs for PMUs defined\n");
		return -ENODEV;
	}

	for (i = 0; i < pmu_device->num_resources; ++i) {
		irq = platform_get_irq(pmu_device, i);
		if (irq < 0)
			continue;

		err = request_irq(irq, armpmu->handle_irq,
				  IRQF_DISABLED | IRQF_NOBALANCING,
				  "armpmu", NULL);
		if (err) {
			pr_warning("unable to request IRQ%d for ARM perf "
				"counters\n", irq);
			break;
		}
	}

	if (err) {
		for (i = i - 1; i >= 0; --i) {
			irq = platform_get_irq(pmu_device, i);
			if (irq >= 0)
				free_irq(irq, NULL);
		}
		release_pmu(pmu_device);
		pmu_device = NULL;
	}

	return err;
}

static void
armpmu_release_hardware(void)
{
	int i, irq;

	for (i = pmu_device->num_resources - 1; i >= 0; --i) {
		irq = platform_get_irq(pmu_device, i);
		if (irq >= 0)
			free_irq(irq, NULL);
	}
	armpmu->stop();

	release_pmu(pmu_device);
	pmu_device = NULL;
}

static atomic_t active_events = ATOMIC_INIT(0);
static DEFINE_MUTEX(pmu_reserve_mutex);

static void
hw_perf_event_destroy(struct perf_event *event)
{
	if (atomic_dec_and_mutex_lock(&active_events, &pmu_reserve_mutex)) {
		armpmu_release_hardware();
		mutex_unlock(&pmu_reserve_mutex);
	}
}

static int
__hw_perf_event_init(struct perf_event *event)
{
	struct hw_perf_event *hwc = &event->hw;
	int mapping, err;

	/* Decode the generic type into an ARM event identifier. */
	if (PERF_TYPE_HARDWARE == event->attr.type) {
		mapping = armpmu->event_map(event->attr.config);
	} else if (PERF_TYPE_HW_CACHE == event->attr.type) {
		mapping = armpmu_map_cache_event(event->attr.config);
	} else if (PERF_TYPE_RAW == event->attr.type) {
		mapping = armpmu->raw_event(event->attr.config);
	} else {
		pr_debug("event type %x not supported\n", event->attr.type);
		return -EOPNOTSUPP;
	}

	if (mapping < 0) {
		pr_debug("event %x:%llx not supported\n", event->attr.type,
			 event->attr.config);
		return mapping;
	}

	/*
	 * Check whether we need to exclude the counter from certain modes.
	 * The ARM performance counters are on all of the time so if someone
	 * has asked us for some excludes then we have to fail.
	 */
	if (event->attr.exclude_kernel || event->attr.exclude_user ||
	    event->attr.exclude_hv || event->attr.exclude_idle) {
		pr_debug("ARM performance counters do not support "
			 "mode exclusion\n");
		return -EPERM;
	}

	/*
	 * We don't assign an index until we actually place the event onto
	 * hardware. Use -1 to signify that we haven't decided where to put it
	 * yet. For SMP systems, each core has it's own PMU so we can't do any
	 * clever allocation or constraints checking at this point.
	 */
	hwc->idx = -1;

	/*
	 * Store the event encoding into the config_base field. config and
	 * event_base are unused as the only 2 things we need to know are
	 * the event mapping and the counter to use. The counter to use is
	 * also the indx and the config_base is the event type.
	 */
	hwc->config_base	    = (unsigned long)mapping;
	hwc->config		    = 0;
	hwc->event_base		    = 0;

	if (!hwc->sample_period) {
		hwc->sample_period  = armpmu->max_period;
		hwc->last_period    = hwc->sample_period;
		local64_set(&hwc->period_left, hwc->sample_period);
	}

	err = 0;
	if (event->group_leader != event) {
		err = validate_group(event);
		if (err)
			return -EINVAL;
	}

	return err;
}

static int armpmu_event_init(struct perf_event *event)
{
	int err = 0;

	switch (event->attr.type) {
	case PERF_TYPE_RAW:
	case PERF_TYPE_HARDWARE:
	case PERF_TYPE_HW_CACHE:
		break;

	default:
		return -ENOENT;
	}

	if (!armpmu)
		return -ENODEV;

	event->destroy = hw_perf_event_destroy;

	if (!atomic_inc_not_zero(&active_events)) {
		if (atomic_read(&active_events) > armpmu->num_events) {
			atomic_dec(&active_events);
			return -ENOSPC;
		}

		mutex_lock(&pmu_reserve_mutex);
		if (atomic_read(&active_events) == 0) {
			err = armpmu_reserve_hardware();
		}

		if (!err)
			atomic_inc(&active_events);
		mutex_unlock(&pmu_reserve_mutex);
	}

	if (err)
		return err;

	err = __hw_perf_event_init(event);
	if (err)
		hw_perf_event_destroy(event);

	return err;
}

static void armpmu_enable(struct pmu *pmu)
{
	/* Enable all of the perf events on hardware. */
	int idx;
	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);

	if (!armpmu)
		return;

	for (idx = 0; idx <= armpmu->num_events; ++idx) {
		struct perf_event *event = cpuc->events[idx];

		if (!event)
			continue;

		armpmu->enable(&event->hw, idx);
	}

	armpmu->start();
}

static void armpmu_disable(struct pmu *pmu)
{
	if (armpmu)
		armpmu->stop();
}

static struct pmu pmu = {
	.pmu_enable	= armpmu_enable,
	.pmu_disable	= armpmu_disable,
	.event_init	= armpmu_event_init,
	.add		= armpmu_add,
	.del		= armpmu_del,
	.start		= armpmu_start,
	.stop		= armpmu_stop,
	.read		= armpmu_read,
};

/*
 * ARMv6 Performance counter handling code.
 *
 * ARMv6 has 2 configurable performance counters and a single cycle counter.
 * They all share a single reset bit but can be written to zero so we can use
 * that for a reset.
 *
 * The counters can't be individually enabled or disabled so when we remove
 * one event and replace it with another we could get spurious counts from the
 * wrong event. However, we can take advantage of the fact that the
 * performance counters can export events to the event bus, and the event bus
 * itself can be monitored. This requires that we *don't* export the events to
 * the event bus. The procedure for disabling a configurable counter is:
 *	- change the counter to count the ETMEXTOUT[0] signal (0x20). This
 *	  effectively stops the counter from counting.
 *	- disable the counter's interrupt generation (each counter has it's
 *	  own interrupt enable bit).
 * Once stopped, the counter value can be written as 0 to reset.
 *
 * To enable a counter:
 *	- enable the counter's interrupt generation.
 *	- set the new event type.
 *
 * Note: the dedicated cycle counter only counts cycles and can't be
 * enabled/disabled independently of the others. When we want to disable the
 * cycle counter, we have to just disable the interrupt reporting and start
 * ignoring that counter. When re-enabling, we have to reset the value and
 * enable the interrupt.
 */

enum armv6_perf_types {
	ARMV6_PERFCTR_ICACHE_MISS	    = 0x0,
	ARMV6_PERFCTR_IBUF_STALL	    = 0x1,
	ARMV6_PERFCTR_DDEP_STALL	    = 0x2,
	ARMV6_PERFCTR_ITLB_MISS		    = 0x3,
	ARMV6_PERFCTR_DTLB_MISS		    = 0x4,
	ARMV6_PERFCTR_BR_EXEC		    = 0x5,
	ARMV6_PERFCTR_BR_MISPREDICT	    = 0x6,
	ARMV6_PERFCTR_INSTR_EXEC	    = 0x7,
	ARMV6_PERFCTR_DCACHE_HIT	    = 0x9,
	ARMV6_PERFCTR_DCACHE_ACCESS	    = 0xA,
	ARMV6_PERFCTR_DCACHE_MISS	    = 0xB,
	ARMV6_PERFCTR_DCACHE_WBACK	    = 0xC,
	ARMV6_PERFCTR_SW_PC_CHANGE	    = 0xD,
	ARMV6_PERFCTR_MAIN_TLB_MISS	    = 0xF,
	ARMV6_PERFCTR_EXPL_D_ACCESS	    = 0x10,
	ARMV6_PERFCTR_LSU_FULL_STALL	    = 0x11,
	ARMV6_PERFCTR_WBUF_DRAINED	    = 0x12,
	ARMV6_PERFCTR_CPU_CYCLES	    = 0xFF,
	ARMV6_PERFCTR_NOP		    = 0x20,
};

enum armv6_counters {
	ARMV6_CYCLE_COUNTER = 1,
	ARMV6_COUNTER0,
	ARMV6_COUNTER1,
};

/*
 * The hardware events that we support. We do support cache operations but
 * we have harvard caches and no way to combine instruction and data
 * accesses/misses in hardware.
 */
static const unsigned armv6_perf_map[PERF_COUNT_HW_MAX] = {
	[PERF_COUNT_HW_CPU_CYCLES]	    = ARMV6_PERFCTR_CPU_CYCLES,
	[PERF_COUNT_HW_INSTRUCTIONS]	    = ARMV6_PERFCTR_INSTR_EXEC,
	[PERF_COUNT_HW_CACHE_REFERENCES]    = HW_OP_UNSUPPORTED,
	[PERF_COUNT_HW_CACHE_MISSES]	    = HW_OP_UNSUPPORTED,
	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV6_PERFCTR_BR_EXEC,
	[PERF_COUNT_HW_BRANCH_MISSES]	    = ARMV6_PERFCTR_BR_MISPREDICT,
	[PERF_COUNT_HW_BUS_CYCLES]	    = HW_OP_UNSUPPORTED,
};

static const unsigned armv6_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
					  [PERF_COUNT_HW_CACHE_OP_MAX]
					  [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
	[C(L1D)] = {
		/*
		 * The performance counters don't differentiate between read
		 * and write accesses/misses so this isn't strictly correct,
		 * but it's the best we can do. Writes and reads get
		 * combined.
		 */
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]	= ARMV6_PERFCTR_DCACHE_ACCESS,
			[C(RESULT_MISS)]	= ARMV6_PERFCTR_DCACHE_MISS,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]	= ARMV6_PERFCTR_DCACHE_ACCESS,
			[C(RESULT_MISS)]	= ARMV6_PERFCTR_DCACHE_MISS,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
	},
	[C(L1I)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= ARMV6_PERFCTR_ICACHE_MISS,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= ARMV6_PERFCTR_ICACHE_MISS,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
	},
	[C(LL)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
	},
	[C(DTLB)] = {
		/*
		 * The ARM performance counters can count micro DTLB misses,
		 * micro ITLB misses and main TLB misses. There isn't an event
		 * for TLB misses, so use the micro misses here and if users
		 * want the main TLB misses they can use a raw counter.
		 */
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= ARMV6_PERFCTR_DTLB_MISS,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= ARMV6_PERFCTR_DTLB_MISS,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
	},
	[C(ITLB)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= ARMV6_PERFCTR_ITLB_MISS,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= ARMV6_PERFCTR_ITLB_MISS,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
	},
	[C(BPU)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
	},
};

enum armv6mpcore_perf_types {
	ARMV6MPCORE_PERFCTR_ICACHE_MISS	    = 0x0,
	ARMV6MPCORE_PERFCTR_IBUF_STALL	    = 0x1,
	ARMV6MPCORE_PERFCTR_DDEP_STALL	    = 0x2,
	ARMV6MPCORE_PERFCTR_ITLB_MISS	    = 0x3,
	ARMV6MPCORE_PERFCTR_DTLB_MISS	    = 0x4,
	ARMV6MPCORE_PERFCTR_BR_EXEC	    = 0x5,
	ARMV6MPCORE_PERFCTR_BR_NOTPREDICT   = 0x6,
	ARMV6MPCORE_PERFCTR_BR_MISPREDICT   = 0x7,
	ARMV6MPCORE_PERFCTR_INSTR_EXEC	    = 0x8,
	ARMV6MPCORE_PERFCTR_DCACHE_RDACCESS = 0xA,
	ARMV6MPCORE_PERFCTR_DCACHE_RDMISS   = 0xB,
	ARMV6MPCORE_PERFCTR_DCACHE_WRACCESS = 0xC,
	ARMV6MPCORE_PERFCTR_DCACHE_WRMISS   = 0xD,
	ARMV6MPCORE_PERFCTR_DCACHE_EVICTION = 0xE,
	ARMV6MPCORE_PERFCTR_SW_PC_CHANGE    = 0xF,
	ARMV6MPCORE_PERFCTR_MAIN_TLB_MISS   = 0x10,
	ARMV6MPCORE_PERFCTR_EXPL_MEM_ACCESS = 0x11,
	ARMV6MPCORE_PERFCTR_LSU_FULL_STALL  = 0x12,
	ARMV6MPCORE_PERFCTR_WBUF_DRAINED    = 0x13,
	ARMV6MPCORE_PERFCTR_CPU_CYCLES	    = 0xFF,
};

/*
 * The hardware events that we support. We do support cache operations but
 * we have harvard caches and no way to combine instruction and data
 * accesses/misses in hardware.
 */
static const unsigned armv6mpcore_perf_map[PERF_COUNT_HW_MAX] = {
	[PERF_COUNT_HW_CPU_CYCLES]	    = ARMV6MPCORE_PERFCTR_CPU_CYCLES,
	[PERF_COUNT_HW_INSTRUCTIONS]	    = ARMV6MPCORE_PERFCTR_INSTR_EXEC,
	[PERF_COUNT_HW_CACHE_REFERENCES]    = HW_OP_UNSUPPORTED,
	[PERF_COUNT_HW_CACHE_MISSES]	    = HW_OP_UNSUPPORTED,
	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV6MPCORE_PERFCTR_BR_EXEC,
	[PERF_COUNT_HW_BRANCH_MISSES]	    = ARMV6MPCORE_PERFCTR_BR_MISPREDICT,
	[PERF_COUNT_HW_BUS_CYCLES]	    = HW_OP_UNSUPPORTED,
};

static const unsigned armv6mpcore_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
					[PERF_COUNT_HW_CACHE_OP_MAX]
					[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
	[C(L1D)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]  =
				ARMV6MPCORE_PERFCTR_DCACHE_RDACCESS,
			[C(RESULT_MISS)]    =
				ARMV6MPCORE_PERFCTR_DCACHE_RDMISS,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]  =
				ARMV6MPCORE_PERFCTR_DCACHE_WRACCESS,
			[C(RESULT_MISS)]    =
				ARMV6MPCORE_PERFCTR_DCACHE_WRMISS,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
		},
	},
	[C(L1I)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_ICACHE_MISS,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_ICACHE_MISS,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
		},
	},
	[C(LL)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
		},
	},
	[C(DTLB)] = {
		/*
		 * The ARM performance counters can count micro DTLB misses,
		 * micro ITLB misses and main TLB misses. There isn't an event
		 * for TLB misses, so use the micro misses here and if users
		 * want the main TLB misses they can use a raw counter.
		 */
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_DTLB_MISS,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_DTLB_MISS,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
		},
	},
	[C(ITLB)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_ITLB_MISS,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]    = ARMV6MPCORE_PERFCTR_ITLB_MISS,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
		},
	},
	[C(BPU)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]  = CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]    = CACHE_OP_UNSUPPORTED,
		},
	},
};

static inline unsigned long
armv6_pmcr_read(void)
{
	u32 val;
	asm volatile("mrc   p15, 0, %0, c15, c12, 0" : "=r"(val));
	return val;
}

static inline void
armv6_pmcr_write(unsigned long val)
{
	asm volatile("mcr   p15, 0, %0, c15, c12, 0" : : "r"(val));
}

#define ARMV6_PMCR_ENABLE		(1 << 0)
#define ARMV6_PMCR_CTR01_RESET		(1 << 1)
#define ARMV6_PMCR_CCOUNT_RESET		(1 << 2)
#define ARMV6_PMCR_CCOUNT_DIV		(1 << 3)
#define ARMV6_PMCR_COUNT0_IEN		(1 << 4)
#define ARMV6_PMCR_COUNT1_IEN		(1 << 5)
#define ARMV6_PMCR_CCOUNT_IEN		(1 << 6)
#define ARMV6_PMCR_COUNT0_OVERFLOW	(1 << 8)
#define ARMV6_PMCR_COUNT1_OVERFLOW	(1 << 9)
#define ARMV6_PMCR_CCOUNT_OVERFLOW	(1 << 10)
#define ARMV6_PMCR_EVT_COUNT0_SHIFT	20
#define ARMV6_PMCR_EVT_COUNT0_MASK	(0xFF << ARMV6_PMCR_EVT_COUNT0_SHIFT)
#define ARMV6_PMCR_EVT_COUNT1_SHIFT	12
#define ARMV6_PMCR_EVT_COUNT1_MASK	(0xFF << ARMV6_PMCR_EVT_COUNT1_SHIFT)

#define ARMV6_PMCR_OVERFLOWED_MASK \
	(ARMV6_PMCR_COUNT0_OVERFLOW | ARMV6_PMCR_COUNT1_OVERFLOW | \
	 ARMV6_PMCR_CCOUNT_OVERFLOW)

static inline int
armv6_pmcr_has_overflowed(unsigned long pmcr)
{
	return (pmcr & ARMV6_PMCR_OVERFLOWED_MASK);
}

static inline int
armv6_pmcr_counter_has_overflowed(unsigned long pmcr,
				  enum armv6_counters counter)
{
	int ret = 0;

	if (ARMV6_CYCLE_COUNTER == counter)
		ret = pmcr & ARMV6_PMCR_CCOUNT_OVERFLOW;
	else if (ARMV6_COUNTER0 == counter)
		ret = pmcr & ARMV6_PMCR_COUNT0_OVERFLOW;
	else if (ARMV6_COUNTER1 == counter)
		ret = pmcr & ARMV6_PMCR_COUNT1_OVERFLOW;
	else
		WARN_ONCE(1, "invalid counter number (%d)\n", counter);

	return ret;
}

static inline u32
armv6pmu_read_counter(int counter)
{
	unsigned long value = 0;

	if (ARMV6_CYCLE_COUNTER == counter)
		asm volatile("mrc   p15, 0, %0, c15, c12, 1" : "=r"(value));
	else if (ARMV6_COUNTER0 == counter)
		asm volatile("mrc   p15, 0, %0, c15, c12, 2" : "=r"(value));
	else if (ARMV6_COUNTER1 == counter)
		asm volatile("mrc   p15, 0, %0, c15, c12, 3" : "=r"(value));
	else
		WARN_ONCE(1, "invalid counter number (%d)\n", counter);

	return value;
}

static inline void
armv6pmu_write_counter(int counter,
		       u32 value)
{
	if (ARMV6_CYCLE_COUNTER == counter)
		asm volatile("mcr   p15, 0, %0, c15, c12, 1" : : "r"(value));
	else if (ARMV6_COUNTER0 == counter)
		asm volatile("mcr   p15, 0, %0, c15, c12, 2" : : "r"(value));
	else if (ARMV6_COUNTER1 == counter)
		asm volatile("mcr   p15, 0, %0, c15, c12, 3" : : "r"(value));
	else
		WARN_ONCE(1, "invalid counter number (%d)\n", counter);
}

void
armv6pmu_enable_event(struct hw_perf_event *hwc,
		      int idx)
{
	unsigned long val, mask, evt, flags;

	if (ARMV6_CYCLE_COUNTER == idx) {
		mask	= 0;
		evt	= ARMV6_PMCR_CCOUNT_IEN;
	} else if (ARMV6_COUNTER0 == idx) {
		mask	= ARMV6_PMCR_EVT_COUNT0_MASK;
		evt	= (hwc->config_base << ARMV6_PMCR_EVT_COUNT0_SHIFT) |
			  ARMV6_PMCR_COUNT0_IEN;
	} else if (ARMV6_COUNTER1 == idx) {
		mask	= ARMV6_PMCR_EVT_COUNT1_MASK;
		evt	= (hwc->config_base << ARMV6_PMCR_EVT_COUNT1_SHIFT) |
			  ARMV6_PMCR_COUNT1_IEN;
	} else {
		WARN_ONCE(1, "invalid counter number (%d)\n", idx);
		return;
	}

	/*
	 * Mask out the current event and set the counter to count the event
	 * that we're interested in.
	 */
	spin_lock_irqsave(&pmu_lock, flags);
	val = armv6_pmcr_read();
	val &= ~mask;
	val |= evt;
	armv6_pmcr_write(val);
	spin_unlock_irqrestore(&pmu_lock, flags);
}

static irqreturn_t
armv6pmu_handle_irq(int irq_num,
		    void *dev)
{
	unsigned long pmcr = armv6_pmcr_read();
	struct perf_sample_data data;
	struct cpu_hw_events *cpuc;
	struct pt_regs *regs;
	int idx;

	if (!armv6_pmcr_has_overflowed(pmcr))
		return IRQ_NONE;

	regs = get_irq_regs();

	/*
	 * The interrupts are cleared by writing the overflow flags back to
	 * the control register. All of the other bits don't have any effect
	 * if they are rewritten, so write the whole value back.
	 */
	armv6_pmcr_write(pmcr);

	perf_sample_data_init(&data, 0);

	cpuc = &__get_cpu_var(cpu_hw_events);
	for (idx = 0; idx <= armpmu->num_events; ++idx) {
		struct perf_event *event = cpuc->events[idx];
		struct hw_perf_event *hwc;

		if (!test_bit(idx, cpuc->active_mask))
			continue;

		/*
		 * We have a single interrupt for all counters. Check that
		 * each counter has overflowed before we process it.
		 */
		if (!armv6_pmcr_counter_has_overflowed(pmcr, idx))
			continue;

		hwc = &event->hw;
		armpmu_event_update(event, hwc, idx);
		data.period = event->hw.last_period;
		if (!armpmu_event_set_period(event, hwc, idx))
			continue;

		if (perf_event_overflow(event, 0, &data, regs))
			armpmu->disable(hwc, idx);
	}

	/*
	 * Handle the pending perf events.
	 *
	 * Note: this call *must* be run with interrupts disabled. For
	 * platforms that can have the PMU interrupts raised as an NMI, this
	 * will not work.
	 */
	irq_work_run();

	return IRQ_HANDLED;
}

static void
armv6pmu_start(void)
{
	unsigned long flags, val;

	spin_lock_irqsave(&pmu_lock, flags);
	val = armv6_pmcr_read();
	val |= ARMV6_PMCR_ENABLE;
	armv6_pmcr_write(val);
	spin_unlock_irqrestore(&pmu_lock, flags);
}

void
armv6pmu_stop(void)
{
	unsigned long flags, val;

	spin_lock_irqsave(&pmu_lock, flags);
	val = armv6_pmcr_read();
	val &= ~ARMV6_PMCR_ENABLE;
	armv6_pmcr_write(val);
	spin_unlock_irqrestore(&pmu_lock, flags);
}

static inline int
armv6pmu_event_map(int config)
{
	int mapping = armv6_perf_map[config];
	if (HW_OP_UNSUPPORTED == mapping)
		mapping = -EOPNOTSUPP;
	return mapping;
}

static inline int
armv6mpcore_pmu_event_map(int config)
{
	int mapping = armv6mpcore_perf_map[config];
	if (HW_OP_UNSUPPORTED == mapping)
		mapping = -EOPNOTSUPP;
	return mapping;
}

static u64
armv6pmu_raw_event(u64 config)
{
	return config & 0xff;
}

static int
armv6pmu_get_event_idx(struct cpu_hw_events *cpuc,
		       struct hw_perf_event *event)
{
	/* Always place a cycle counter into the cycle counter. */
	if (ARMV6_PERFCTR_CPU_CYCLES == event->config_base) {
		if (test_and_set_bit(ARMV6_CYCLE_COUNTER, cpuc->used_mask))
			return -EAGAIN;

		return ARMV6_CYCLE_COUNTER;
	} else {
		/*
		 * For anything other than a cycle counter, try and use
		 * counter0 and counter1.
		 */
		if (!test_and_set_bit(ARMV6_COUNTER1, cpuc->used_mask)) {
			return ARMV6_COUNTER1;
		}

		if (!test_and_set_bit(ARMV6_COUNTER0, cpuc->used_mask)) {
			return ARMV6_COUNTER0;
		}

		/* The counters are all in use. */
		return -EAGAIN;
	}
}

static void
armv6pmu_disable_event(struct hw_perf_event *hwc,
		       int idx)
{
	unsigned long val, mask, evt, flags;

	if (ARMV6_CYCLE_COUNTER == idx) {
		mask	= ARMV6_PMCR_CCOUNT_IEN;
		evt	= 0;
	} else if (ARMV6_COUNTER0 == idx) {
		mask	= ARMV6_PMCR_COUNT0_IEN | ARMV6_PMCR_EVT_COUNT0_MASK;
		evt	= ARMV6_PERFCTR_NOP << ARMV6_PMCR_EVT_COUNT0_SHIFT;
	} else if (ARMV6_COUNTER1 == idx) {
		mask	= ARMV6_PMCR_COUNT1_IEN | ARMV6_PMCR_EVT_COUNT1_MASK;
		evt	= ARMV6_PERFCTR_NOP << ARMV6_PMCR_EVT_COUNT1_SHIFT;
	} else {
		WARN_ONCE(1, "invalid counter number (%d)\n", idx);
		return;
	}

	/*
	 * Mask out the current event and set the counter to count the number
	 * of ETM bus signal assertion cycles. The external reporting should
	 * be disabled and so this should never increment.
	 */
	spin_lock_irqsave(&pmu_lock, flags);
	val = armv6_pmcr_read();
	val &= ~mask;
	val |= evt;
	armv6_pmcr_write(val);
	spin_unlock_irqrestore(&pmu_lock, flags);
}

static void
armv6mpcore_pmu_disable_event(struct hw_perf_event *hwc,
			      int idx)
{
	unsigned long val, mask, flags, evt = 0;

	if (ARMV6_CYCLE_COUNTER == idx) {
		mask	= ARMV6_PMCR_CCOUNT_IEN;
	} else if (ARMV6_COUNTER0 == idx) {
		mask	= ARMV6_PMCR_COUNT0_IEN;
	} else if (ARMV6_COUNTER1 == idx) {
		mask	= ARMV6_PMCR_COUNT1_IEN;
	} else {
		WARN_ONCE(1, "invalid counter number (%d)\n", idx);
		return;
	}

	/*
	 * Unlike UP ARMv6, we don't have a way of stopping the counters. We
	 * simply disable the interrupt reporting.
	 */
	spin_lock_irqsave(&pmu_lock, flags);
	val = armv6_pmcr_read();
	val &= ~mask;
	val |= evt;
	armv6_pmcr_write(val);
	spin_unlock_irqrestore(&pmu_lock, flags);
}

static const struct arm_pmu armv6pmu = {
	.id			= ARM_PERF_PMU_ID_V6,
	.handle_irq		= armv6pmu_handle_irq,
	.enable			= armv6pmu_enable_event,
	.disable		= armv6pmu_disable_event,
	.event_map		= armv6pmu_event_map,
	.raw_event		= armv6pmu_raw_event,
	.read_counter		= armv6pmu_read_counter,
	.write_counter		= armv6pmu_write_counter,
	.get_event_idx		= armv6pmu_get_event_idx,
	.start			= armv6pmu_start,
	.stop			= armv6pmu_stop,
	.num_events		= 3,
	.max_period		= (1LLU << 32) - 1,
};

/*
 * ARMv6mpcore is almost identical to single core ARMv6 with the exception
 * that some of the events have different enumerations and that there is no
 * *hack* to stop the programmable counters. To stop the counters we simply
 * disable the interrupt reporting and update the event. When unthrottling we
 * reset the period and enable the interrupt reporting.
 */
static const struct arm_pmu armv6mpcore_pmu = {
	.id			= ARM_PERF_PMU_ID_V6MP,
	.handle_irq		= armv6pmu_handle_irq,
	.enable			= armv6pmu_enable_event,
	.disable		= armv6mpcore_pmu_disable_event,
	.event_map		= armv6mpcore_pmu_event_map,
	.raw_event		= armv6pmu_raw_event,
	.read_counter		= armv6pmu_read_counter,
	.write_counter		= armv6pmu_write_counter,
	.get_event_idx		= armv6pmu_get_event_idx,
	.start			= armv6pmu_start,
	.stop			= armv6pmu_stop,
	.num_events		= 3,
	.max_period		= (1LLU << 32) - 1,
};

/*
 * ARMv7 Cortex-A8 and Cortex-A9 Performance Events handling code.
 *
 * Copied from ARMv6 code, with the low level code inspired
 *  by the ARMv7 Oprofile code.
 *
 * Cortex-A8 has up to 4 configurable performance counters and
 *  a single cycle counter.
 * Cortex-A9 has up to 31 configurable performance counters and
 *  a single cycle counter.
 *
 * All counters can be enabled/disabled and IRQ masked separately. The cycle
 *  counter and all 4 performance counters together can be reset separately.
 */

/* Common ARMv7 event types */
enum armv7_perf_types {
	ARMV7_PERFCTR_PMNC_SW_INCR		= 0x00,
	ARMV7_PERFCTR_IFETCH_MISS		= 0x01,
	ARMV7_PERFCTR_ITLB_MISS			= 0x02,
	ARMV7_PERFCTR_DCACHE_REFILL		= 0x03,
	ARMV7_PERFCTR_DCACHE_ACCESS		= 0x04,
	ARMV7_PERFCTR_DTLB_REFILL		= 0x05,
	ARMV7_PERFCTR_DREAD			= 0x06,
	ARMV7_PERFCTR_DWRITE			= 0x07,

	ARMV7_PERFCTR_EXC_TAKEN			= 0x09,
	ARMV7_PERFCTR_EXC_EXECUTED		= 0x0A,
	ARMV7_PERFCTR_CID_WRITE			= 0x0B,
	/* ARMV7_PERFCTR_PC_WRITE is equivalent to HW_BRANCH_INSTRUCTIONS.
	 * It counts:
	 *  - all branch instructions,
	 *  - instructions that explicitly write the PC,
	 *  - exception generating instructions.
	 */
	ARMV7_PERFCTR_PC_WRITE			= 0x0C,
	ARMV7_PERFCTR_PC_IMM_BRANCH		= 0x0D,
	ARMV7_PERFCTR_UNALIGNED_ACCESS		= 0x0F,
	ARMV7_PERFCTR_PC_BRANCH_MIS_PRED	= 0x10,
	ARMV7_PERFCTR_CLOCK_CYCLES		= 0x11,

	ARMV7_PERFCTR_PC_BRANCH_MIS_USED	= 0x12,

	ARMV7_PERFCTR_CPU_CYCLES		= 0xFF
};

/* ARMv7 Cortex-A8 specific event types */
enum armv7_a8_perf_types {
	ARMV7_PERFCTR_INSTR_EXECUTED		= 0x08,

	ARMV7_PERFCTR_PC_PROC_RETURN		= 0x0E,

	ARMV7_PERFCTR_WRITE_BUFFER_FULL		= 0x40,
	ARMV7_PERFCTR_L2_STORE_MERGED		= 0x41,
	ARMV7_PERFCTR_L2_STORE_BUFF		= 0x42,
	ARMV7_PERFCTR_L2_ACCESS			= 0x43,
	ARMV7_PERFCTR_L2_CACH_MISS		= 0x44,
	ARMV7_PERFCTR_AXI_READ_CYCLES		= 0x45,
	ARMV7_PERFCTR_AXI_WRITE_CYCLES		= 0x46,
	ARMV7_PERFCTR_MEMORY_REPLAY		= 0x47,
	ARMV7_PERFCTR_UNALIGNED_ACCESS_REPLAY	= 0x48,
	ARMV7_PERFCTR_L1_DATA_MISS		= 0x49,
	ARMV7_PERFCTR_L1_INST_MISS		= 0x4A,
	ARMV7_PERFCTR_L1_DATA_COLORING		= 0x4B,
	ARMV7_PERFCTR_L1_NEON_DATA		= 0x4C,
	ARMV7_PERFCTR_L1_NEON_CACH_DATA		= 0x4D,
	ARMV7_PERFCTR_L2_NEON			= 0x4E,
	ARMV7_PERFCTR_L2_NEON_HIT		= 0x4F,
	ARMV7_PERFCTR_L1_INST			= 0x50,
	ARMV7_PERFCTR_PC_RETURN_MIS_PRED	= 0x51,
	ARMV7_PERFCTR_PC_BRANCH_FAILED		= 0x52,
	ARMV7_PERFCTR_PC_BRANCH_TAKEN		= 0x53,
	ARMV7_PERFCTR_PC_BRANCH_EXECUTED	= 0x54,
	ARMV7_PERFCTR_OP_EXECUTED		= 0x55,
	ARMV7_PERFCTR_CYCLES_INST_STALL		= 0x56,
	ARMV7_PERFCTR_CYCLES_INST		= 0x57,
	ARMV7_PERFCTR_CYCLES_NEON_DATA_STALL	= 0x58,
	ARMV7_PERFCTR_CYCLES_NEON_INST_STALL	= 0x59,
	ARMV7_PERFCTR_NEON_CYCLES		= 0x5A,

	ARMV7_PERFCTR_PMU0_EVENTS		= 0x70,
	ARMV7_PERFCTR_PMU1_EVENTS		= 0x71,
	ARMV7_PERFCTR_PMU_EVENTS		= 0x72,
};

/* ARMv7 Cortex-A9 specific event types */
enum armv7_a9_perf_types {
	ARMV7_PERFCTR_JAVA_HW_BYTECODE_EXEC	= 0x40,
	ARMV7_PERFCTR_JAVA_SW_BYTECODE_EXEC	= 0x41,
	ARMV7_PERFCTR_JAZELLE_BRANCH_EXEC	= 0x42,

	ARMV7_PERFCTR_COHERENT_LINE_MISS	= 0x50,
	ARMV7_PERFCTR_COHERENT_LINE_HIT		= 0x51,

	ARMV7_PERFCTR_ICACHE_DEP_STALL_CYCLES	= 0x60,
	ARMV7_PERFCTR_DCACHE_DEP_STALL_CYCLES	= 0x61,
	ARMV7_PERFCTR_TLB_MISS_DEP_STALL_CYCLES	= 0x62,
	ARMV7_PERFCTR_STREX_EXECUTED_PASSED	= 0x63,
	ARMV7_PERFCTR_STREX_EXECUTED_FAILED	= 0x64,
	ARMV7_PERFCTR_DATA_EVICTION		= 0x65,
	ARMV7_PERFCTR_ISSUE_STAGE_NO_INST	= 0x66,
	ARMV7_PERFCTR_ISSUE_STAGE_EMPTY		= 0x67,
	ARMV7_PERFCTR_INST_OUT_OF_RENAME_STAGE	= 0x68,

	ARMV7_PERFCTR_PREDICTABLE_FUNCT_RETURNS	= 0x6E,

	ARMV7_PERFCTR_MAIN_UNIT_EXECUTED_INST	= 0x70,
	ARMV7_PERFCTR_SECOND_UNIT_EXECUTED_INST	= 0x71,
	ARMV7_PERFCTR_LD_ST_UNIT_EXECUTED_INST	= 0x72,
	ARMV7_PERFCTR_FP_EXECUTED_INST		= 0x73,
	ARMV7_PERFCTR_NEON_EXECUTED_INST	= 0x74,

	ARMV7_PERFCTR_PLD_FULL_DEP_STALL_CYCLES	= 0x80,
	ARMV7_PERFCTR_DATA_WR_DEP_STALL_CYCLES	= 0x81,
	ARMV7_PERFCTR_ITLB_MISS_DEP_STALL_CYCLES	= 0x82,
	ARMV7_PERFCTR_DTLB_MISS_DEP_STALL_CYCLES	= 0x83,
	ARMV7_PERFCTR_MICRO_ITLB_MISS_DEP_STALL_CYCLES	= 0x84,
	ARMV7_PERFCTR_MICRO_DTLB_MISS_DEP_STALL_CYCLES 	= 0x85,
	ARMV7_PERFCTR_DMB_DEP_STALL_CYCLES	= 0x86,

	ARMV7_PERFCTR_INTGR_CLK_ENABLED_CYCLES	= 0x8A,
	ARMV7_PERFCTR_DATA_ENGINE_CLK_EN_CYCLES	= 0x8B,

	ARMV7_PERFCTR_ISB_INST			= 0x90,
	ARMV7_PERFCTR_DSB_INST			= 0x91,
	ARMV7_PERFCTR_DMB_INST			= 0x92,
	ARMV7_PERFCTR_EXT_INTERRUPTS		= 0x93,

	ARMV7_PERFCTR_PLE_CACHE_LINE_RQST_COMPLETED	= 0xA0,
	ARMV7_PERFCTR_PLE_CACHE_LINE_RQST_SKIPPED	= 0xA1,
	ARMV7_PERFCTR_PLE_FIFO_FLUSH		= 0xA2,
	ARMV7_PERFCTR_PLE_RQST_COMPLETED	= 0xA3,
	ARMV7_PERFCTR_PLE_FIFO_OVERFLOW		= 0xA4,
	ARMV7_PERFCTR_PLE_RQST_PROG		= 0xA5
};

/*
 * Cortex-A8 HW events mapping
 *
 * The hardware events that we support. We do support cache operations but
 * we have harvard caches and no way to combine instruction and data
 * accesses/misses in hardware.
 */
static const unsigned armv7_a8_perf_map[PERF_COUNT_HW_MAX] = {
	[PERF_COUNT_HW_CPU_CYCLES]	    = ARMV7_PERFCTR_CPU_CYCLES,
	[PERF_COUNT_HW_INSTRUCTIONS]	    = ARMV7_PERFCTR_INSTR_EXECUTED,
	[PERF_COUNT_HW_CACHE_REFERENCES]    = HW_OP_UNSUPPORTED,
	[PERF_COUNT_HW_CACHE_MISSES]	    = HW_OP_UNSUPPORTED,
	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE,
	[PERF_COUNT_HW_BRANCH_MISSES]	    = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
	[PERF_COUNT_HW_BUS_CYCLES]	    = ARMV7_PERFCTR_CLOCK_CYCLES,
};

static const unsigned armv7_a8_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
					  [PERF_COUNT_HW_CACHE_OP_MAX]
					  [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
	[C(L1D)] = {
		/*
		 * The performance counters don't differentiate between read
		 * and write accesses/misses so this isn't strictly correct,
		 * but it's the best we can do. Writes and reads get
		 * combined.
		 */
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_DCACHE_ACCESS,
			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DCACHE_REFILL,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_DCACHE_ACCESS,
			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DCACHE_REFILL,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
	},
	[C(L1I)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_INST,
			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_INST_MISS,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_INST,
			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_INST_MISS,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
	},
	[C(LL)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L2_ACCESS,
			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACH_MISS,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L2_ACCESS,
			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACH_MISS,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
	},
	[C(DTLB)] = {
		/*
		 * Only ITLB misses and DTLB refills are supported.
		 * If users want the DTLB refills misses a raw counter
		 * must be used.
		 */
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
	},
	[C(ITLB)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_MISS,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_MISS,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
	},
	[C(BPU)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_WRITE,
			[C(RESULT_MISS)]
					= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_WRITE,
			[C(RESULT_MISS)]
					= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
	},
};

/*
 * Cortex-A9 HW events mapping
 */
static const unsigned armv7_a9_perf_map[PERF_COUNT_HW_MAX] = {
	[PERF_COUNT_HW_CPU_CYCLES]	    = ARMV7_PERFCTR_CPU_CYCLES,
	[PERF_COUNT_HW_INSTRUCTIONS]	    =
					ARMV7_PERFCTR_INST_OUT_OF_RENAME_STAGE,
	[PERF_COUNT_HW_CACHE_REFERENCES]    = ARMV7_PERFCTR_COHERENT_LINE_HIT,
	[PERF_COUNT_HW_CACHE_MISSES]	    = ARMV7_PERFCTR_COHERENT_LINE_MISS,
	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE,
	[PERF_COUNT_HW_BRANCH_MISSES]	    = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
	[PERF_COUNT_HW_BUS_CYCLES]	    = ARMV7_PERFCTR_CLOCK_CYCLES,
};

static const unsigned armv7_a9_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
					  [PERF_COUNT_HW_CACHE_OP_MAX]
					  [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
	[C(L1D)] = {
		/*
		 * The performance counters don't differentiate between read
		 * and write accesses/misses so this isn't strictly correct,
		 * but it's the best we can do. Writes and reads get
		 * combined.
		 */
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_DCACHE_ACCESS,
			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DCACHE_REFILL,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_DCACHE_ACCESS,
			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DCACHE_REFILL,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
	},
	[C(L1I)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= ARMV7_PERFCTR_IFETCH_MISS,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= ARMV7_PERFCTR_IFETCH_MISS,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
	},
	[C(LL)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
	},
	[C(DTLB)] = {
		/*
		 * Only ITLB misses and DTLB refills are supported.
		 * If users want the DTLB refills misses a raw counter
		 * must be used.
		 */
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
	},
	[C(ITLB)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_MISS,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_MISS,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
	},
	[C(BPU)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_WRITE,
			[C(RESULT_MISS)]
					= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_WRITE,
			[C(RESULT_MISS)]
					= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
	},
};

/*
 * Perf Events counters
 */
enum armv7_counters {
	ARMV7_CYCLE_COUNTER 		= 1,	/* Cycle counter */
	ARMV7_COUNTER0			= 2,	/* First event counter */
};

/*
 * The cycle counter is ARMV7_CYCLE_COUNTER.
 * The first event counter is ARMV7_COUNTER0.
 * The last event counter is (ARMV7_COUNTER0 + armpmu->num_events - 1).
 */
#define	ARMV7_COUNTER_LAST	(ARMV7_COUNTER0 + armpmu->num_events - 1)

/*
 * ARMv7 low level PMNC access
 */

/*
 * Per-CPU PMNC: config reg
 */
#define ARMV7_PMNC_E		(1 << 0) /* Enable all counters */
#define ARMV7_PMNC_P		(1 << 1) /* Reset all counters */
#define ARMV7_PMNC_C		(1 << 2) /* Cycle counter reset */
#define ARMV7_PMNC_D		(1 << 3) /* CCNT counts every 64th cpu cycle */
#define ARMV7_PMNC_X		(1 << 4) /* Export to ETM */
#define ARMV7_PMNC_DP		(1 << 5) /* Disable CCNT if non-invasive debug*/
#define	ARMV7_PMNC_N_SHIFT	11	 /* Number of counters supported */
#define	ARMV7_PMNC_N_MASK	0x1f
#define	ARMV7_PMNC_MASK		0x3f	 /* Mask for writable bits */

/*
 * Available counters
 */
#define ARMV7_CNT0 		0	/* First event counter */
#define ARMV7_CCNT 		31	/* Cycle counter */

/* Perf Event to low level counters mapping */
#define ARMV7_EVENT_CNT_TO_CNTx	(ARMV7_COUNTER0 - ARMV7_CNT0)

/*
 * CNTENS: counters enable reg
 */
#define ARMV7_CNTENS_P(idx)	(1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
#define ARMV7_CNTENS_C		(1 << ARMV7_CCNT)

/*
 * CNTENC: counters disable reg
 */
#define ARMV7_CNTENC_P(idx)	(1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
#define ARMV7_CNTENC_C		(1 << ARMV7_CCNT)

/*
 * INTENS: counters overflow interrupt enable reg
 */
#define ARMV7_INTENS_P(idx)	(1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
#define ARMV7_INTENS_C		(1 << ARMV7_CCNT)

/*
 * INTENC: counters overflow interrupt disable reg
 */
#define ARMV7_INTENC_P(idx)	(1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
#define ARMV7_INTENC_C		(1 << ARMV7_CCNT)

/*
 * EVTSEL: Event selection reg
 */
#define	ARMV7_EVTSEL_MASK	0xff		/* Mask for writable bits */

/*
 * SELECT: Counter selection reg
 */
#define	ARMV7_SELECT_MASK	0x1f		/* Mask for writable bits */

/*
 * FLAG: counters overflow flag status reg
 */
#define ARMV7_FLAG_P(idx)	(1 << (idx - ARMV7_EVENT_CNT_TO_CNTx))
#define ARMV7_FLAG_C		(1 << ARMV7_CCNT)
#define	ARMV7_FLAG_MASK		0xffffffff	/* Mask for writable bits */
#define	ARMV7_OVERFLOWED_MASK	ARMV7_FLAG_MASK

static inline unsigned long armv7_pmnc_read(void)
{
	u32 val;
	asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r"(val));
	return val;
}

static inline void armv7_pmnc_write(unsigned long val)
{
	val &= ARMV7_PMNC_MASK;
	asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r"(val));
}

static inline int armv7_pmnc_has_overflowed(unsigned long pmnc)
{
	return pmnc & ARMV7_OVERFLOWED_MASK;
}

static inline int armv7_pmnc_counter_has_overflowed(unsigned long pmnc,
					enum armv7_counters counter)
{
	int ret;

	if (counter == ARMV7_CYCLE_COUNTER)
		ret = pmnc & ARMV7_FLAG_C;
	else if ((counter >= ARMV7_COUNTER0) && (counter <= ARMV7_COUNTER_LAST))
		ret = pmnc & ARMV7_FLAG_P(counter);
	else
		pr_err("CPU%u checking wrong counter %d overflow status\n",
			smp_processor_id(), counter);

	return ret;
}

static inline int armv7_pmnc_select_counter(unsigned int idx)
{
	u32 val;

	if ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST)) {
		pr_err("CPU%u selecting wrong PMNC counter"
			" %d\n", smp_processor_id(), idx);
		return -1;
	}

	val = (idx - ARMV7_EVENT_CNT_TO_CNTx) & ARMV7_SELECT_MASK;
	asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (val));

	return idx;
}

static inline u32 armv7pmu_read_counter(int idx)
{
	unsigned long value = 0;

	if (idx == ARMV7_CYCLE_COUNTER)
		asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (value));
	else if ((idx >= ARMV7_COUNTER0) && (idx <= ARMV7_COUNTER_LAST)) {
		if (armv7_pmnc_select_counter(idx) == idx)
			asm volatile("mrc p15, 0, %0, c9, c13, 2"
				     : "=r" (value));
	} else
		pr_err("CPU%u reading wrong counter %d\n",
			smp_processor_id(), idx);

	return value;
}

static inline void armv7pmu_write_counter(int idx, u32 value)
{
	if (idx == ARMV7_CYCLE_COUNTER)
		asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (value));
	else if ((idx >= ARMV7_COUNTER0) && (idx <= ARMV7_COUNTER_LAST)) {
		if (armv7_pmnc_select_counter(idx) == idx)
			asm volatile("mcr p15, 0, %0, c9, c13, 2"
				     : : "r" (value));
	} else
		pr_err("CPU%u writing wrong counter %d\n",
			smp_processor_id(), idx);
}

static inline void armv7_pmnc_write_evtsel(unsigned int idx, u32 val)
{
	if (armv7_pmnc_select_counter(idx) == idx) {
		val &= ARMV7_EVTSEL_MASK;
		asm volatile("mcr p15, 0, %0, c9, c13, 1" : : "r" (val));
	}
}

static inline u32 armv7_pmnc_enable_counter(unsigned int idx)
{
	u32 val;

	if ((idx != ARMV7_CYCLE_COUNTER) &&
	    ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
		pr_err("CPU%u enabling wrong PMNC counter"
			" %d\n", smp_processor_id(), idx);
		return -1;
	}

	if (idx == ARMV7_CYCLE_COUNTER)
		val = ARMV7_CNTENS_C;
	else
		val = ARMV7_CNTENS_P(idx);

	asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (val));

	return idx;
}

static inline u32 armv7_pmnc_disable_counter(unsigned int idx)
{
	u32 val;


	if ((idx != ARMV7_CYCLE_COUNTER) &&
	    ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
		pr_err("CPU%u disabling wrong PMNC counter"
			" %d\n", smp_processor_id(), idx);
		return -1;
	}

	if (idx == ARMV7_CYCLE_COUNTER)
		val = ARMV7_CNTENC_C;
	else
		val = ARMV7_CNTENC_P(idx);

	asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (val));

	return idx;
}

static inline u32 armv7_pmnc_enable_intens(unsigned int idx)
{
	u32 val;

	if ((idx != ARMV7_CYCLE_COUNTER) &&
	    ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
		pr_err("CPU%u enabling wrong PMNC counter"
			" interrupt enable %d\n", smp_processor_id(), idx);
		return -1;
	}

	if (idx == ARMV7_CYCLE_COUNTER)
		val = ARMV7_INTENS_C;
	else
		val = ARMV7_INTENS_P(idx);

	asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (val));

	return idx;
}

static inline u32 armv7_pmnc_disable_intens(unsigned int idx)
{
	u32 val;

	if ((idx != ARMV7_CYCLE_COUNTER) &&
	    ((idx < ARMV7_COUNTER0) || (idx > ARMV7_COUNTER_LAST))) {
		pr_err("CPU%u disabling wrong PMNC counter"
			" interrupt enable %d\n", smp_processor_id(), idx);
		return -1;
	}

	if (idx == ARMV7_CYCLE_COUNTER)
		val = ARMV7_INTENC_C;
	else
		val = ARMV7_INTENC_P(idx);

	asm volatile("mcr p15, 0, %0, c9, c14, 2" : : "r" (val));

	return idx;
}

static inline u32 armv7_pmnc_getreset_flags(void)
{
	u32 val;

	/* Read */
	asm volatile("mrc p15, 0, %0, c9, c12, 3" : "=r" (val));

	/* Write to clear flags */
	val &= ARMV7_FLAG_MASK;
	asm volatile("mcr p15, 0, %0, c9, c12, 3" : : "r" (val));

	return val;
}

#ifdef DEBUG
static void armv7_pmnc_dump_regs(void)
{
	u32 val;
	unsigned int cnt;

	printk(KERN_INFO "PMNC registers dump:\n");

	asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r" (val));
	printk(KERN_INFO "PMNC  =0x%08x\n", val);

	asm volatile("mrc p15, 0, %0, c9, c12, 1" : "=r" (val));
	printk(KERN_INFO "CNTENS=0x%08x\n", val);

	asm volatile("mrc p15, 0, %0, c9, c14, 1" : "=r" (val));
	printk(KERN_INFO "INTENS=0x%08x\n", val);

	asm volatile("mrc p15, 0, %0, c9, c12, 3" : "=r" (val));
	printk(KERN_INFO "FLAGS =0x%08x\n", val);

	asm volatile("mrc p15, 0, %0, c9, c12, 5" : "=r" (val));
	printk(KERN_INFO "SELECT=0x%08x\n", val);

	asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (val));
	printk(KERN_INFO "CCNT  =0x%08x\n", val);

	for (cnt = ARMV7_COUNTER0; cnt < ARMV7_COUNTER_LAST; cnt++) {
		armv7_pmnc_select_counter(cnt);
		asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (val));
		printk(KERN_INFO "CNT[%d] count =0x%08x\n",
			cnt-ARMV7_EVENT_CNT_TO_CNTx, val);
		asm volatile("mrc p15, 0, %0, c9, c13, 1" : "=r" (val));
		printk(KERN_INFO "CNT[%d] evtsel=0x%08x\n",
			cnt-ARMV7_EVENT_CNT_TO_CNTx, val);
	}
}
#endif

void armv7pmu_enable_event(struct hw_perf_event *hwc, int idx)
{
	unsigned long flags;

	/*
	 * Enable counter and interrupt, and set the counter to count
	 * the event that we're interested in.
	 */
	spin_lock_irqsave(&pmu_lock, flags);

	/*
	 * Disable counter
	 */
	armv7_pmnc_disable_counter(idx);

	/*
	 * Set event (if destined for PMNx counters)
	 * We don't need to set the event if it's a cycle count
	 */
	if (idx != ARMV7_CYCLE_COUNTER)
		armv7_pmnc_write_evtsel(idx, hwc->config_base);

	/*
	 * Enable interrupt for this counter
	 */
	armv7_pmnc_enable_intens(idx);

	/*
	 * Enable counter
	 */
	armv7_pmnc_enable_counter(idx);

	spin_unlock_irqrestore(&pmu_lock, flags);
}

static void armv7pmu_disable_event(struct hw_perf_event *hwc, int idx)
{
	unsigned long flags;

	/*
	 * Disable counter and interrupt
	 */
	spin_lock_irqsave(&pmu_lock, flags);

	/*
	 * Disable counter
	 */
	armv7_pmnc_disable_counter(idx);

	/*
	 * Disable interrupt for this counter
	 */
	armv7_pmnc_disable_intens(idx);

	spin_unlock_irqrestore(&pmu_lock, flags);
}

static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
{
	unsigned long pmnc;
	struct perf_sample_data data;
	struct cpu_hw_events *cpuc;
	struct pt_regs *regs;
	int idx;

	/*
	 * Get and reset the IRQ flags
	 */
	pmnc = armv7_pmnc_getreset_flags();

	/*
	 * Did an overflow occur?
	 */
	if (!armv7_pmnc_has_overflowed(pmnc))
		return IRQ_NONE;

	/*
	 * Handle the counter(s) overflow(s)
	 */
	regs = get_irq_regs();

	perf_sample_data_init(&data, 0);

	cpuc = &__get_cpu_var(cpu_hw_events);
	for (idx = 0; idx <= armpmu->num_events; ++idx) {
		struct perf_event *event = cpuc->events[idx];
		struct hw_perf_event *hwc;

		if (!test_bit(idx, cpuc->active_mask))
			continue;

		/*
		 * We have a single interrupt for all counters. Check that
		 * each counter has overflowed before we process it.
		 */
		if (!armv7_pmnc_counter_has_overflowed(pmnc, idx))
			continue;

		hwc = &event->hw;
		armpmu_event_update(event, hwc, idx);
		data.period = event->hw.last_period;
		if (!armpmu_event_set_period(event, hwc, idx))
			continue;

		if (perf_event_overflow(event, 0, &data, regs))
			armpmu->disable(hwc, idx);
	}

	/*
	 * Handle the pending perf events.
	 *
	 * Note: this call *must* be run with interrupts disabled. For
	 * platforms that can have the PMU interrupts raised as an NMI, this
	 * will not work.
	 */
	irq_work_run();

	return IRQ_HANDLED;
}

static void armv7pmu_start(void)
{
	unsigned long flags;

	spin_lock_irqsave(&pmu_lock, flags);
	/* Enable all counters */
	armv7_pmnc_write(armv7_pmnc_read() | ARMV7_PMNC_E);
	spin_unlock_irqrestore(&pmu_lock, flags);
}

static void armv7pmu_stop(void)
{
	unsigned long flags;

	spin_lock_irqsave(&pmu_lock, flags);
	/* Disable all counters */
	armv7_pmnc_write(armv7_pmnc_read() & ~ARMV7_PMNC_E);
	spin_unlock_irqrestore(&pmu_lock, flags);
}

static inline int armv7_a8_pmu_event_map(int config)
{
	int mapping = armv7_a8_perf_map[config];
	if (HW_OP_UNSUPPORTED == mapping)
		mapping = -EOPNOTSUPP;
	return mapping;
}

static inline int armv7_a9_pmu_event_map(int config)
{
	int mapping = armv7_a9_perf_map[config];
	if (HW_OP_UNSUPPORTED == mapping)
		mapping = -EOPNOTSUPP;
	return mapping;
}

static u64 armv7pmu_raw_event(u64 config)
{
	return config & 0xff;
}

static int armv7pmu_get_event_idx(struct cpu_hw_events *cpuc,
				  struct hw_perf_event *event)
{
	int idx;

	/* Always place a cycle counter into the cycle counter. */
	if (event->config_base == ARMV7_PERFCTR_CPU_CYCLES) {
		if (test_and_set_bit(ARMV7_CYCLE_COUNTER, cpuc->used_mask))
			return -EAGAIN;

		return ARMV7_CYCLE_COUNTER;
	} else {
		/*
		 * For anything other than a cycle counter, try and use
		 * the events counters
		 */
		for (idx = ARMV7_COUNTER0; idx <= armpmu->num_events; ++idx) {
			if (!test_and_set_bit(idx, cpuc->used_mask))
				return idx;
		}

		/* The counters are all in use. */
		return -EAGAIN;
	}
}

static struct arm_pmu armv7pmu = {
	.handle_irq		= armv7pmu_handle_irq,
	.enable			= armv7pmu_enable_event,
	.disable		= armv7pmu_disable_event,
	.raw_event		= armv7pmu_raw_event,
	.read_counter		= armv7pmu_read_counter,
	.write_counter		= armv7pmu_write_counter,
	.get_event_idx		= armv7pmu_get_event_idx,
	.start			= armv7pmu_start,
	.stop			= armv7pmu_stop,
	.max_period		= (1LLU << 32) - 1,
};

static u32 __init armv7_reset_read_pmnc(void)
{
	u32 nb_cnt;

	/* Initialize & Reset PMNC: C and P bits */
	armv7_pmnc_write(ARMV7_PMNC_P | ARMV7_PMNC_C);

	/* Read the nb of CNTx counters supported from PMNC */
	nb_cnt = (armv7_pmnc_read() >> ARMV7_PMNC_N_SHIFT) & ARMV7_PMNC_N_MASK;

	/* Add the CPU cycles counter and return */
	return nb_cnt + 1;
}

/*
 * ARMv5 [xscale] Performance counter handling code.
 *
 * Based on xscale OProfile code.
 *
 * There are two variants of the xscale PMU that we support:
 * 	- xscale1pmu: 2 event counters and a cycle counter
 * 	- xscale2pmu: 4 event counters and a cycle counter
 * The two variants share event definitions, but have different
 * PMU structures.
 */

enum xscale_perf_types {
	XSCALE_PERFCTR_ICACHE_MISS		= 0x00,
	XSCALE_PERFCTR_ICACHE_NO_DELIVER	= 0x01,
	XSCALE_PERFCTR_DATA_STALL		= 0x02,
	XSCALE_PERFCTR_ITLB_MISS		= 0x03,
	XSCALE_PERFCTR_DTLB_MISS		= 0x04,
	XSCALE_PERFCTR_BRANCH			= 0x05,
	XSCALE_PERFCTR_BRANCH_MISS		= 0x06,
	XSCALE_PERFCTR_INSTRUCTION		= 0x07,
	XSCALE_PERFCTR_DCACHE_FULL_STALL	= 0x08,
	XSCALE_PERFCTR_DCACHE_FULL_STALL_CONTIG	= 0x09,
	XSCALE_PERFCTR_DCACHE_ACCESS		= 0x0A,
	XSCALE_PERFCTR_DCACHE_MISS		= 0x0B,
	XSCALE_PERFCTR_DCACHE_WRITE_BACK	= 0x0C,
	XSCALE_PERFCTR_PC_CHANGED		= 0x0D,
	XSCALE_PERFCTR_BCU_REQUEST		= 0x10,
	XSCALE_PERFCTR_BCU_FULL			= 0x11,
	XSCALE_PERFCTR_BCU_DRAIN		= 0x12,
	XSCALE_PERFCTR_BCU_ECC_NO_ELOG		= 0x14,
	XSCALE_PERFCTR_BCU_1_BIT_ERR		= 0x15,
	XSCALE_PERFCTR_RMW			= 0x16,
	/* XSCALE_PERFCTR_CCNT is not hardware defined */
	XSCALE_PERFCTR_CCNT			= 0xFE,
	XSCALE_PERFCTR_UNUSED			= 0xFF,
};

enum xscale_counters {
	XSCALE_CYCLE_COUNTER	= 1,
	XSCALE_COUNTER0,
	XSCALE_COUNTER1,
	XSCALE_COUNTER2,
	XSCALE_COUNTER3,
};

static const unsigned xscale_perf_map[PERF_COUNT_HW_MAX] = {
	[PERF_COUNT_HW_CPU_CYCLES]	    = XSCALE_PERFCTR_CCNT,
	[PERF_COUNT_HW_INSTRUCTIONS]	    = XSCALE_PERFCTR_INSTRUCTION,
	[PERF_COUNT_HW_CACHE_REFERENCES]    = HW_OP_UNSUPPORTED,
	[PERF_COUNT_HW_CACHE_MISSES]	    = HW_OP_UNSUPPORTED,
	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = XSCALE_PERFCTR_BRANCH,
	[PERF_COUNT_HW_BRANCH_MISSES]	    = XSCALE_PERFCTR_BRANCH_MISS,
	[PERF_COUNT_HW_BUS_CYCLES]	    = HW_OP_UNSUPPORTED,
};

static const unsigned xscale_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
					   [PERF_COUNT_HW_CACHE_OP_MAX]
					   [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
	[C(L1D)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]	= XSCALE_PERFCTR_DCACHE_ACCESS,
			[C(RESULT_MISS)]	= XSCALE_PERFCTR_DCACHE_MISS,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]	= XSCALE_PERFCTR_DCACHE_ACCESS,
			[C(RESULT_MISS)]	= XSCALE_PERFCTR_DCACHE_MISS,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
	},
	[C(L1I)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= XSCALE_PERFCTR_ICACHE_MISS,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= XSCALE_PERFCTR_ICACHE_MISS,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
	},
	[C(LL)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
	},
	[C(DTLB)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= XSCALE_PERFCTR_DTLB_MISS,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= XSCALE_PERFCTR_DTLB_MISS,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
	},
	[C(ITLB)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= XSCALE_PERFCTR_ITLB_MISS,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= XSCALE_PERFCTR_ITLB_MISS,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
	},
	[C(BPU)] = {
		[C(OP_READ)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
		[C(OP_WRITE)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
		[C(OP_PREFETCH)] = {
			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
		},
	},
};

#define	XSCALE_PMU_ENABLE	0x001
#define XSCALE_PMN_RESET	0x002
#define	XSCALE_CCNT_RESET	0x004
#define	XSCALE_PMU_RESET	(CCNT_RESET | PMN_RESET)
#define XSCALE_PMU_CNT64	0x008

static inline int
xscalepmu_event_map(int config)
{
	int mapping = xscale_perf_map[config];
	if (HW_OP_UNSUPPORTED == mapping)
		mapping = -EOPNOTSUPP;
	return mapping;
}

static u64
xscalepmu_raw_event(u64 config)
{
	return config & 0xff;
}

#define XSCALE1_OVERFLOWED_MASK	0x700
#define XSCALE1_CCOUNT_OVERFLOW	0x400
#define XSCALE1_COUNT0_OVERFLOW	0x100
#define XSCALE1_COUNT1_OVERFLOW	0x200
#define XSCALE1_CCOUNT_INT_EN	0x040
#define XSCALE1_COUNT0_INT_EN	0x010
#define XSCALE1_COUNT1_INT_EN	0x020
#define XSCALE1_COUNT0_EVT_SHFT	12
#define XSCALE1_COUNT0_EVT_MASK	(0xff << XSCALE1_COUNT0_EVT_SHFT)
#define XSCALE1_COUNT1_EVT_SHFT	20
#define XSCALE1_COUNT1_EVT_MASK	(0xff << XSCALE1_COUNT1_EVT_SHFT)

static inline u32
xscale1pmu_read_pmnc(void)
{
	u32 val;
	asm volatile("mrc p14, 0, %0, c0, c0, 0" : "=r" (val));
	return val;
}

static inline void
xscale1pmu_write_pmnc(u32 val)
{
	/* upper 4bits and 7, 11 are write-as-0 */
	val &= 0xffff77f;
	asm volatile("mcr p14, 0, %0, c0, c0, 0" : : "r" (val));
}

static inline int
xscale1_pmnc_counter_has_overflowed(unsigned long pmnc,
					enum xscale_counters counter)
{
	int ret = 0;

	switch (counter) {
	case XSCALE_CYCLE_COUNTER:
		ret = pmnc & XSCALE1_CCOUNT_OVERFLOW;
		break;
	case XSCALE_COUNTER0:
		ret = pmnc & XSCALE1_COUNT0_OVERFLOW;
		break;
	case XSCALE_COUNTER1:
		ret = pmnc & XSCALE1_COUNT1_OVERFLOW;
		break;
	default:
		WARN_ONCE(1, "invalid counter number (%d)\n", counter);
	}

	return ret;
}

static irqreturn_t
xscale1pmu_handle_irq(int irq_num, void *dev)
{
	unsigned long pmnc;
	struct perf_sample_data data;
	struct cpu_hw_events *cpuc;
	struct pt_regs *regs;
	int idx;

	/*
	 * NOTE: there's an A stepping erratum that states if an overflow
	 *       bit already exists and another occurs, the previous
	 *       Overflow bit gets cleared. There's no workaround.
	 *	 Fixed in B stepping or later.
	 */
	pmnc = xscale1pmu_read_pmnc();

	/*
	 * Write the value back to clear the overflow flags. Overflow
	 * flags remain in pmnc for use below. We also disable the PMU
	 * while we process the interrupt.
	 */
	xscale1pmu_write_pmnc(pmnc & ~XSCALE_PMU_ENABLE);

	if (!(pmnc & XSCALE1_OVERFLOWED_MASK))
		return IRQ_NONE;

	regs = get_irq_regs();

	perf_sample_data_init(&data, 0);

	cpuc = &__get_cpu_var(cpu_hw_events);
	for (idx = 0; idx <= armpmu->num_events; ++idx) {
		struct perf_event *event = cpuc->events[idx];
		struct hw_perf_event *hwc;

		if (!test_bit(idx, cpuc->active_mask))
			continue;

		if (!xscale1_pmnc_counter_has_overflowed(pmnc, idx))
			continue;

		hwc = &event->hw;
		armpmu_event_update(event, hwc, idx);
		data.period = event->hw.last_period;
		if (!armpmu_event_set_period(event, hwc, idx))
			continue;

		if (perf_event_overflow(event, 0, &data, regs))
			armpmu->disable(hwc, idx);
	}

	irq_work_run();

	/*
	 * Re-enable the PMU.
	 */
	pmnc = xscale1pmu_read_pmnc() | XSCALE_PMU_ENABLE;
	xscale1pmu_write_pmnc(pmnc);

	return IRQ_HANDLED;
}

static void
xscale1pmu_enable_event(struct hw_perf_event *hwc, int idx)
{
	unsigned long val, mask, evt, flags;

	switch (idx) {
	case XSCALE_CYCLE_COUNTER:
		mask = 0;
		evt = XSCALE1_CCOUNT_INT_EN;
		break;
	case XSCALE_COUNTER0:
		mask = XSCALE1_COUNT0_EVT_MASK;
		evt = (hwc->config_base << XSCALE1_COUNT0_EVT_SHFT) |
			XSCALE1_COUNT0_INT_EN;
		break;
	case XSCALE_COUNTER1:
		mask = XSCALE1_COUNT1_EVT_MASK;
		evt = (hwc->config_base << XSCALE1_COUNT1_EVT_SHFT) |
			XSCALE1_COUNT1_INT_EN;
		break;
	default:
		WARN_ONCE(1, "invalid counter number (%d)\n", idx);
		return;
	}

	spin_lock_irqsave(&pmu_lock, flags);
	val = xscale1pmu_read_pmnc();
	val &= ~mask;
	val |= evt;
	xscale1pmu_write_pmnc(val);
	spin_unlock_irqrestore(&pmu_lock, flags);
}

static void
xscale1pmu_disable_event(struct hw_perf_event *hwc, int idx)
{
	unsigned long val, mask, evt, flags;

	switch (idx) {
	case XSCALE_CYCLE_COUNTER:
		mask = XSCALE1_CCOUNT_INT_EN;
		evt = 0;
		break;
	case XSCALE_COUNTER0:
		mask = XSCALE1_COUNT0_INT_EN | XSCALE1_COUNT0_EVT_MASK;
		evt = XSCALE_PERFCTR_UNUSED << XSCALE1_COUNT0_EVT_SHFT;
		break;
	case XSCALE_COUNTER1:
		mask = XSCALE1_COUNT1_INT_EN | XSCALE1_COUNT1_EVT_MASK;
		evt = XSCALE_PERFCTR_UNUSED << XSCALE1_COUNT1_EVT_SHFT;
		break;
	default:
		WARN_ONCE(1, "invalid counter number (%d)\n", idx);
		return;
	}

	spin_lock_irqsave(&pmu_lock, flags);
	val = xscale1pmu_read_pmnc();
	val &= ~mask;
	val |= evt;
	xscale1pmu_write_pmnc(val);
	spin_unlock_irqrestore(&pmu_lock, flags);
}

static int
xscale1pmu_get_event_idx(struct cpu_hw_events *cpuc,
			struct hw_perf_event *event)
{
	if (XSCALE_PERFCTR_CCNT == event->config_base) {
		if (test_and_set_bit(XSCALE_CYCLE_COUNTER, cpuc->used_mask))
			return -EAGAIN;

		return XSCALE_CYCLE_COUNTER;
	} else {
		if (!test_and_set_bit(XSCALE_COUNTER1, cpuc->used_mask)) {
			return XSCALE_COUNTER1;
		}

		if (!test_and_set_bit(XSCALE_COUNTER0, cpuc->used_mask)) {
			return XSCALE_COUNTER0;
		}

		return -EAGAIN;
	}
}

static void
xscale1pmu_start(void)
{
	unsigned long flags, val;

	spin_lock_irqsave(&pmu_lock, flags);
	val = xscale1pmu_read_pmnc();
	val |= XSCALE_PMU_ENABLE;
	xscale1pmu_write_pmnc(val);
	spin_unlock_irqrestore(&pmu_lock, flags);
}

static void
xscale1pmu_stop(void)
{
	unsigned long flags, val;

	spin_lock_irqsave(&pmu_lock, flags);
	val = xscale1pmu_read_pmnc();
	val &= ~XSCALE_PMU_ENABLE;
	xscale1pmu_write_pmnc(val);
	spin_unlock_irqrestore(&pmu_lock, flags);
}

static inline u32
xscale1pmu_read_counter(int counter)
{
	u32 val = 0;

	switch (counter) {
	case XSCALE_CYCLE_COUNTER:
		asm volatile("mrc p14, 0, %0, c1, c0, 0" : "=r" (val));
		break;
	case XSCALE_COUNTER0:
		asm volatile("mrc p14, 0, %0, c2, c0, 0" : "=r" (val));
		break;
	case XSCALE_COUNTER1:
		asm volatile("mrc p14, 0, %0, c3, c0, 0" : "=r" (val));
		break;
	}

	return val;
}

static inline void
xscale1pmu_write_counter(int counter, u32 val)
{
	switch (counter) {
	case XSCALE_CYCLE_COUNTER:
		asm volatile("mcr p14, 0, %0, c1, c0, 0" : : "r" (val));
		break;
	case XSCALE_COUNTER0:
		asm volatile("mcr p14, 0, %0, c2, c0, 0" : : "r" (val));
		break;
	case XSCALE_COUNTER1:
		asm volatile("mcr p14, 0, %0, c3, c0, 0" : : "r" (val));
		break;
	}
}

static const struct arm_pmu xscale1pmu = {
	.id		= ARM_PERF_PMU_ID_XSCALE1,
	.handle_irq	= xscale1pmu_handle_irq,
	.enable		= xscale1pmu_enable_event,
	.disable	= xscale1pmu_disable_event,
	.event_map	= xscalepmu_event_map,
	.raw_event	= xscalepmu_raw_event,
	.read_counter	= xscale1pmu_read_counter,
	.write_counter	= xscale1pmu_write_counter,
	.get_event_idx	= xscale1pmu_get_event_idx,
	.start		= xscale1pmu_start,
	.stop		= xscale1pmu_stop,
	.num_events	= 3,
	.max_period	= (1LLU << 32) - 1,
};

#define XSCALE2_OVERFLOWED_MASK	0x01f
#define XSCALE2_CCOUNT_OVERFLOW	0x001
#define XSCALE2_COUNT0_OVERFLOW	0x002
#define XSCALE2_COUNT1_OVERFLOW	0x004
#define XSCALE2_COUNT2_OVERFLOW	0x008
#define XSCALE2_COUNT3_OVERFLOW	0x010
#define XSCALE2_CCOUNT_INT_EN	0x001
#define XSCALE2_COUNT0_INT_EN	0x002
#define XSCALE2_COUNT1_INT_EN	0x004
#define XSCALE2_COUNT2_INT_EN	0x008
#define XSCALE2_COUNT3_INT_EN	0x010
#define XSCALE2_COUNT0_EVT_SHFT	0
#define XSCALE2_COUNT0_EVT_MASK	(0xff << XSCALE2_COUNT0_EVT_SHFT)
#define XSCALE2_COUNT1_EVT_SHFT	8
#define XSCALE2_COUNT1_EVT_MASK	(0xff << XSCALE2_COUNT1_EVT_SHFT)
#define XSCALE2_COUNT2_EVT_SHFT	16
#define XSCALE2_COUNT2_EVT_MASK	(0xff << XSCALE2_COUNT2_EVT_SHFT)
#define XSCALE2_COUNT3_EVT_SHFT	24
#define XSCALE2_COUNT3_EVT_MASK	(0xff << XSCALE2_COUNT3_EVT_SHFT)

static inline u32
xscale2pmu_read_pmnc(void)
{
	u32 val;
	asm volatile("mrc p14, 0, %0, c0, c1, 0" : "=r" (val));
	/* bits 1-2 and 4-23 are read-unpredictable */
	return val & 0xff000009;
}

static inline void
xscale2pmu_write_pmnc(u32 val)
{
	/* bits 4-23 are write-as-0, 24-31 are write ignored */
	val &= 0xf;
	asm volatile("mcr p14, 0, %0, c0, c1, 0" : : "r" (val));
}

static inline u32
xscale2pmu_read_overflow_flags(void)
{
	u32 val;
	asm volatile("mrc p14, 0, %0, c5, c1, 0" : "=r" (val));
	return val;
}

static inline void
xscale2pmu_write_overflow_flags(u32 val)
{
	asm volatile("mcr p14, 0, %0, c5, c1, 0" : : "r" (val));
}

static inline u32
xscale2pmu_read_event_select(void)
{
	u32 val;
	asm volatile("mrc p14, 0, %0, c8, c1, 0" : "=r" (val));
	return val;
}

static inline void
xscale2pmu_write_event_select(u32 val)
{
	asm volatile("mcr p14, 0, %0, c8, c1, 0" : : "r"(val));
}

static inline u32
xscale2pmu_read_int_enable(void)
{
	u32 val;
	asm volatile("mrc p14, 0, %0, c4, c1, 0" : "=r" (val));
	return val;
}

static void
xscale2pmu_write_int_enable(u32 val)
{
	asm volatile("mcr p14, 0, %0, c4, c1, 0" : : "r" (val));
}

static inline int
xscale2_pmnc_counter_has_overflowed(unsigned long of_flags,
					enum xscale_counters counter)
{
	int ret = 0;

	switch (counter) {
	case XSCALE_CYCLE_COUNTER:
		ret = of_flags & XSCALE2_CCOUNT_OVERFLOW;
		break;
	case XSCALE_COUNTER0:
		ret = of_flags & XSCALE2_COUNT0_OVERFLOW;
		break;
	case XSCALE_COUNTER1:
		ret = of_flags & XSCALE2_COUNT1_OVERFLOW;
		break;
	case XSCALE_COUNTER2:
		ret = of_flags & XSCALE2_COUNT2_OVERFLOW;
		break;
	case XSCALE_COUNTER3:
		ret = of_flags & XSCALE2_COUNT3_OVERFLOW;
		break;
	default:
		WARN_ONCE(1, "invalid counter number (%d)\n", counter);
	}

	return ret;
}

static irqreturn_t
xscale2pmu_handle_irq(int irq_num, void *dev)
{
	unsigned long pmnc, of_flags;
	struct perf_sample_data data;
	struct cpu_hw_events *cpuc;
	struct pt_regs *regs;
	int idx;

	/* Disable the PMU. */
	pmnc = xscale2pmu_read_pmnc();
	xscale2pmu_write_pmnc(pmnc & ~XSCALE_PMU_ENABLE);

	/* Check the overflow flag register. */
	of_flags = xscale2pmu_read_overflow_flags();
	if (!(of_flags & XSCALE2_OVERFLOWED_MASK))
		return IRQ_NONE;

	/* Clear the overflow bits. */
	xscale2pmu_write_overflow_flags(of_flags);

	regs = get_irq_regs();

	perf_sample_data_init(&data, 0);

	cpuc = &__get_cpu_var(cpu_hw_events);
	for (idx = 0; idx <= armpmu->num_events; ++idx) {
		struct perf_event *event = cpuc->events[idx];
		struct hw_perf_event *hwc;

		if (!test_bit(idx, cpuc->active_mask))
			continue;

		if (!xscale2_pmnc_counter_has_overflowed(pmnc, idx))
			continue;

		hwc = &event->hw;
		armpmu_event_update(event, hwc, idx);
		data.period = event->hw.last_period;
		if (!armpmu_event_set_period(event, hwc, idx))
			continue;

		if (perf_event_overflow(event, 0, &data, regs))
			armpmu->disable(hwc, idx);
	}

	irq_work_run();

	/*
	 * Re-enable the PMU.
	 */
	pmnc = xscale2pmu_read_pmnc() | XSCALE_PMU_ENABLE;
	xscale2pmu_write_pmnc(pmnc);

	return IRQ_HANDLED;
}

static void
xscale2pmu_enable_event(struct hw_perf_event *hwc, int idx)
{
	unsigned long flags, ien, evtsel;

	ien = xscale2pmu_read_int_enable();
	evtsel = xscale2pmu_read_event_select();

	switch (idx) {
	case XSCALE_CYCLE_COUNTER:
		ien |= XSCALE2_CCOUNT_INT_EN;
		break;
	case XSCALE_COUNTER0:
		ien |= XSCALE2_COUNT0_INT_EN;
		evtsel &= ~XSCALE2_COUNT0_EVT_MASK;
		evtsel |= hwc->config_base << XSCALE2_COUNT0_EVT_SHFT;
		break;
	case XSCALE_COUNTER1:
		ien |= XSCALE2_COUNT1_INT_EN;
		evtsel &= ~XSCALE2_COUNT1_EVT_MASK;
		evtsel |= hwc->config_base << XSCALE2_COUNT1_EVT_SHFT;
		break;
	case XSCALE_COUNTER2:
		ien |= XSCALE2_COUNT2_INT_EN;
		evtsel &= ~XSCALE2_COUNT2_EVT_MASK;
		evtsel |= hwc->config_base << XSCALE2_COUNT2_EVT_SHFT;
		break;
	case XSCALE_COUNTER3:
		ien |= XSCALE2_COUNT3_INT_EN;
		evtsel &= ~XSCALE2_COUNT3_EVT_MASK;
		evtsel |= hwc->config_base << XSCALE2_COUNT3_EVT_SHFT;
		break;
	default:
		WARN_ONCE(1, "invalid counter number (%d)\n", idx);
		return;
	}

	spin_lock_irqsave(&pmu_lock, flags);
	xscale2pmu_write_event_select(evtsel);
	xscale2pmu_write_int_enable(ien);
	spin_unlock_irqrestore(&pmu_lock, flags);
}

static void
xscale2pmu_disable_event(struct hw_perf_event *hwc, int idx)
{
	unsigned long flags, ien, evtsel;

	ien = xscale2pmu_read_int_enable();
	evtsel = xscale2pmu_read_event_select();

	switch (idx) {
	case XSCALE_CYCLE_COUNTER:
		ien &= ~XSCALE2_CCOUNT_INT_EN;
		break;
	case XSCALE_COUNTER0:
		ien &= ~XSCALE2_COUNT0_INT_EN;
		evtsel &= ~XSCALE2_COUNT0_EVT_MASK;
		evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT0_EVT_SHFT;
		break;
	case XSCALE_COUNTER1:
		ien &= ~XSCALE2_COUNT1_INT_EN;
		evtsel &= ~XSCALE2_COUNT1_EVT_MASK;
		evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT1_EVT_SHFT;
		break;
	case XSCALE_COUNTER2:
		ien &= ~XSCALE2_COUNT2_INT_EN;
		evtsel &= ~XSCALE2_COUNT2_EVT_MASK;
		evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT2_EVT_SHFT;
		break;
	case XSCALE_COUNTER3:
		ien &= ~XSCALE2_COUNT3_INT_EN;
		evtsel &= ~XSCALE2_COUNT3_EVT_MASK;
		evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT3_EVT_SHFT;
		break;
	default:
		WARN_ONCE(1, "invalid counter number (%d)\n", idx);
		return;
	}

	spin_lock_irqsave(&pmu_lock, flags);
	xscale2pmu_write_event_select(evtsel);
	xscale2pmu_write_int_enable(ien);
	spin_unlock_irqrestore(&pmu_lock, flags);
}

static int
xscale2pmu_get_event_idx(struct cpu_hw_events *cpuc,
			struct hw_perf_event *event)
{
	int idx = xscale1pmu_get_event_idx(cpuc, event);
	if (idx >= 0)
		goto out;

	if (!test_and_set_bit(XSCALE_COUNTER3, cpuc->used_mask))
		idx = XSCALE_COUNTER3;
	else if (!test_and_set_bit(XSCALE_COUNTER2, cpuc->used_mask))
		idx = XSCALE_COUNTER2;
out:
	return idx;
}

static void
xscale2pmu_start(void)
{
	unsigned long flags, val;

	spin_lock_irqsave(&pmu_lock, flags);
	val = xscale2pmu_read_pmnc() & ~XSCALE_PMU_CNT64;
	val |= XSCALE_PMU_ENABLE;
	xscale2pmu_write_pmnc(val);
	spin_unlock_irqrestore(&pmu_lock, flags);
}

static void
xscale2pmu_stop(void)
{
	unsigned long flags, val;

	spin_lock_irqsave(&pmu_lock, flags);
	val = xscale2pmu_read_pmnc();
	val &= ~XSCALE_PMU_ENABLE;
	xscale2pmu_write_pmnc(val);
	spin_unlock_irqrestore(&pmu_lock, flags);
}

static inline u32
xscale2pmu_read_counter(int counter)
{
	u32 val = 0;

	switch (counter) {
	case XSCALE_CYCLE_COUNTER:
		asm volatile("mrc p14, 0, %0, c1, c1, 0" : "=r" (val));
		break;
	case XSCALE_COUNTER0:
		asm volatile("mrc p14, 0, %0, c0, c2, 0" : "=r" (val));
		break;
	case XSCALE_COUNTER1:
		asm volatile("mrc p14, 0, %0, c1, c2, 0" : "=r" (val));
		break;
	case XSCALE_COUNTER2:
		asm volatile("mrc p14, 0, %0, c2, c2, 0" : "=r" (val));
		break;
	case XSCALE_COUNTER3:
		asm volatile("mrc p14, 0, %0, c3, c2, 0" : "=r" (val));
		break;
	}

	return val;
}

static inline void
xscale2pmu_write_counter(int counter, u32 val)
{
	switch (counter) {
	case XSCALE_CYCLE_COUNTER:
		asm volatile("mcr p14, 0, %0, c1, c1, 0" : : "r" (val));
		break;
	case XSCALE_COUNTER0:
		asm volatile("mcr p14, 0, %0, c0, c2, 0" : : "r" (val));
		break;
	case XSCALE_COUNTER1:
		asm volatile("mcr p14, 0, %0, c1, c2, 0" : : "r" (val));
		break;
	case XSCALE_COUNTER2:
		asm volatile("mcr p14, 0, %0, c2, c2, 0" : : "r" (val));
		break;
	case XSCALE_COUNTER3:
		asm volatile("mcr p14, 0, %0, c3, c2, 0" : : "r" (val));
		break;
	}
}

static const struct arm_pmu xscale2pmu = {
	.id		= ARM_PERF_PMU_ID_XSCALE2,
	.handle_irq	= xscale2pmu_handle_irq,
	.enable		= xscale2pmu_enable_event,
	.disable	= xscale2pmu_disable_event,
	.event_map	= xscalepmu_event_map,
	.raw_event	= xscalepmu_raw_event,
	.read_counter	= xscale2pmu_read_counter,
	.write_counter	= xscale2pmu_write_counter,
	.get_event_idx	= xscale2pmu_get_event_idx,
	.start		= xscale2pmu_start,
	.stop		= xscale2pmu_stop,
	.num_events	= 5,
	.max_period	= (1LLU << 32) - 1,
};

static int __init
init_hw_perf_events(void)
{
	unsigned long cpuid = read_cpuid_id();
	unsigned long implementor = (cpuid & 0xFF000000) >> 24;
	unsigned long part_number = (cpuid & 0xFFF0);

	/* ARM Ltd CPUs. */
	if (0x41 == implementor) {
		switch (part_number) {
		case 0xB360:	/* ARM1136 */
		case 0xB560:	/* ARM1156 */
		case 0xB760:	/* ARM1176 */
			armpmu = &armv6pmu;
			memcpy(armpmu_perf_cache_map, armv6_perf_cache_map,
					sizeof(armv6_perf_cache_map));
			break;
		case 0xB020:	/* ARM11mpcore */
			armpmu = &armv6mpcore_pmu;
			memcpy(armpmu_perf_cache_map,
			       armv6mpcore_perf_cache_map,
			       sizeof(armv6mpcore_perf_cache_map));
			break;
		case 0xC080:	/* Cortex-A8 */
			armv7pmu.id = ARM_PERF_PMU_ID_CA8;
			memcpy(armpmu_perf_cache_map, armv7_a8_perf_cache_map,
				sizeof(armv7_a8_perf_cache_map));
			armv7pmu.event_map = armv7_a8_pmu_event_map;
			armpmu = &armv7pmu;

			/* Reset PMNC and read the nb of CNTx counters
			    supported */
			armv7pmu.num_events = armv7_reset_read_pmnc();
			break;
		case 0xC090:	/* Cortex-A9 */
			armv7pmu.id = ARM_PERF_PMU_ID_CA9;
			memcpy(armpmu_perf_cache_map, armv7_a9_perf_cache_map,
				sizeof(armv7_a9_perf_cache_map));
			armv7pmu.event_map = armv7_a9_pmu_event_map;
			armpmu = &armv7pmu;

			/* Reset PMNC and read the nb of CNTx counters
			    supported */
			armv7pmu.num_events = armv7_reset_read_pmnc();
			break;
		}
	/* Intel CPUs [xscale]. */
	} else if (0x69 == implementor) {
		part_number = (cpuid >> 13) & 0x7;
		switch (part_number) {
		case 1:
			armpmu = &xscale1pmu;
			memcpy(armpmu_perf_cache_map, xscale_perf_cache_map,
					sizeof(xscale_perf_cache_map));
			break;
		case 2:
			armpmu = &xscale2pmu;
			memcpy(armpmu_perf_cache_map, xscale_perf_cache_map,
					sizeof(xscale_perf_cache_map));
			break;
		}
	}

	if (armpmu) {
		pr_info("enabled with %s PMU driver, %d counters available\n",
				arm_pmu_names[armpmu->id], armpmu->num_events);
	} else {
		pr_info("no hardware support available\n");
	}

	perf_pmu_register(&pmu);

	return 0;
}
arch_initcall(init_hw_perf_events);

/*
 * Callchain handling code.
 */

/*
 * The registers we're interested in are at the end of the variable
 * length saved register structure. The fp points at the end of this
 * structure so the address of this struct is:
 * (struct frame_tail *)(xxx->fp)-1
 *
 * This code has been adapted from the ARM OProfile support.
 */
struct frame_tail {
	struct frame_tail   *fp;
	unsigned long	    sp;
	unsigned long	    lr;
} __attribute__((packed));

/*
 * Get the return address for a single stackframe and return a pointer to the
 * next frame tail.
 */
static struct frame_tail *
user_backtrace(struct frame_tail *tail,
	       struct perf_callchain_entry *entry)
{
	struct frame_tail buftail;

	/* Also check accessibility of one struct frame_tail beyond */
	if (!access_ok(VERIFY_READ, tail, sizeof(buftail)))
		return NULL;
	if (__copy_from_user_inatomic(&buftail, tail, sizeof(buftail)))
		return NULL;

	perf_callchain_store(entry, buftail.lr);

	/*
	 * Frame pointers should strictly progress back up the stack
	 * (towards higher addresses).
	 */
	if (tail >= buftail.fp)
		return NULL;

	return buftail.fp - 1;
}

void
perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
{
	struct frame_tail *tail;


	tail = (struct frame_tail *)regs->ARM_fp - 1;

	while (tail && !((unsigned long)tail & 0x3))
		tail = user_backtrace(tail, entry);
}

/*
 * Gets called by walk_stackframe() for every stackframe. This will be called
 * whist unwinding the stackframe and is like a subroutine return so we use
 * the PC.
 */
static int
callchain_trace(struct stackframe *fr,
		void *data)
{
	struct perf_callchain_entry *entry = data;
	perf_callchain_store(entry, fr->pc);
	return 0;
}

void
perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
{
	struct stackframe fr;

	fr.fp = regs->ARM_fp;
	fr.sp = regs->ARM_sp;
	fr.lr = regs->ARM_lr;
	fr.pc = regs->ARM_pc;
	walk_stackframe(&fr, callchain_trace, entry);
}