perf_event_mipsxx.c 40.3 KB
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
/*
 * Linux performance counter support for MIPS.
 *
 * Copyright (C) 2010 MIPS Technologies, Inc.
 * Copyright (C) 2011 Cavium Networks, Inc.
 * Author: Deng-Cheng Zhu
 *
 * This code is based on the implementation for ARM, which is in turn
 * based on the sparc64 perf event code and the x86 code. Performance
 * counter access is based on the MIPS Oprofile code. And the callchain
 * support references the code of MIPS stacktrace.c.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */

#include <linux/cpumask.h>
#include <linux/interrupt.h>
#include <linux/smp.h>
#include <linux/kernel.h>
#include <linux/perf_event.h>
#include <linux/uaccess.h>

#include <asm/irq.h>
#include <asm/irq_regs.h>
#include <asm/stacktrace.h>
#include <asm/time.h> /* For perf_irq */

#define MIPS_MAX_HWEVENTS 4

struct cpu_hw_events {
	/* Array of events on this cpu. */
	struct perf_event	*events[MIPS_MAX_HWEVENTS];

	/*
	 * Set the bit (indexed by the counter number) when the counter
	 * is used for an event.
	 */
	unsigned long		used_mask[BITS_TO_LONGS(MIPS_MAX_HWEVENTS)];

	/*
	 * Software copy of the control register for each performance counter.
	 * MIPS CPUs vary in performance counters. They use this differently,
	 * and even may not use it.
	 */
	unsigned int		saved_ctrl[MIPS_MAX_HWEVENTS];
};
DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
	.saved_ctrl = {0},
};

/* The description of MIPS performance events. */
struct mips_perf_event {
	unsigned int event_id;
	/*
	 * MIPS performance counters are indexed starting from 0.
	 * CNTR_EVEN indicates the indexes of the counters to be used are
	 * even numbers.
	 */
	unsigned int cntr_mask;
	#define CNTR_EVEN	0x55555555
	#define CNTR_ODD	0xaaaaaaaa
	#define CNTR_ALL	0xffffffff
#ifdef CONFIG_MIPS_MT_SMP
	enum {
		T  = 0,
		V  = 1,
		P  = 2,
	} range;
#else
	#define T
	#define V
	#define P
#endif
};

static struct mips_perf_event raw_event;
static DEFINE_MUTEX(raw_event_mutex);

#define UNSUPPORTED_PERF_EVENT_ID 0xffffffff
#define C(x) PERF_COUNT_HW_CACHE_##x

struct mips_pmu {
	u64		max_period;
	u64		valid_count;
	u64		overflow;
	const char	*name;
	int		irq;
	u64		(*read_counter)(unsigned int idx);
	void		(*write_counter)(unsigned int idx, u64 val);
	const struct mips_perf_event *(*map_raw_event)(u64 config);
	const struct mips_perf_event (*general_event_map)[PERF_COUNT_HW_MAX];
	const struct mips_perf_event (*cache_event_map)
				[PERF_COUNT_HW_CACHE_MAX]
				[PERF_COUNT_HW_CACHE_OP_MAX]
				[PERF_COUNT_HW_CACHE_RESULT_MAX];
	unsigned int	num_counters;
};

static struct mips_pmu mipspmu;

#define M_CONFIG1_PC	(1 << 4)

#define M_PERFCTL_EXL			(1      <<  0)
#define M_PERFCTL_KERNEL		(1      <<  1)
#define M_PERFCTL_SUPERVISOR		(1      <<  2)
#define M_PERFCTL_USER			(1      <<  3)
#define M_PERFCTL_INTERRUPT_ENABLE	(1      <<  4)
#define M_PERFCTL_EVENT(event)		(((event) & 0x3ff)  << 5)
#define M_PERFCTL_VPEID(vpe)		((vpe)    << 16)
#define M_PERFCTL_MT_EN(filter)		((filter) << 20)
#define    M_TC_EN_ALL			M_PERFCTL_MT_EN(0)
#define    M_TC_EN_VPE			M_PERFCTL_MT_EN(1)
#define    M_TC_EN_TC			M_PERFCTL_MT_EN(2)
#define M_PERFCTL_TCID(tcid)		((tcid)   << 22)
#define M_PERFCTL_WIDE			(1      << 30)
#define M_PERFCTL_MORE			(1      << 31)

#define M_PERFCTL_COUNT_EVENT_WHENEVER	(M_PERFCTL_EXL |		\
					M_PERFCTL_KERNEL |		\
					M_PERFCTL_USER |		\
					M_PERFCTL_SUPERVISOR |		\
					M_PERFCTL_INTERRUPT_ENABLE)

#ifdef CONFIG_MIPS_MT_SMP
#define M_PERFCTL_CONFIG_MASK		0x3fff801f
#else
#define M_PERFCTL_CONFIG_MASK		0x1f
#endif
#define M_PERFCTL_EVENT_MASK		0xfe0


#ifdef CONFIG_MIPS_MT_SMP
static int cpu_has_mipsmt_pertccounters;

static DEFINE_RWLOCK(pmuint_rwlock);

/*
 * FIXME: For VSMP, vpe_id() is redefined for Perf-events, because
 * cpu_data[cpuid].vpe_id reports 0 for _both_ CPUs.
 */
#if defined(CONFIG_HW_PERF_EVENTS)
#define vpe_id()	(cpu_has_mipsmt_pertccounters ? \
			0 : smp_processor_id())
#else
#define vpe_id()	(cpu_has_mipsmt_pertccounters ? \
			0 : cpu_data[smp_processor_id()].vpe_id)
#endif

/* Copied from op_model_mipsxx.c */
static unsigned int vpe_shift(void)
{
	if (num_possible_cpus() > 1)
		return 1;

	return 0;
}

static unsigned int counters_total_to_per_cpu(unsigned int counters)
{
	return counters >> vpe_shift();
}

static unsigned int counters_per_cpu_to_total(unsigned int counters)
{
	return counters << vpe_shift();
}

#else /* !CONFIG_MIPS_MT_SMP */
#define vpe_id()	0

#endif /* CONFIG_MIPS_MT_SMP */

static void resume_local_counters(void);
static void pause_local_counters(void);
static irqreturn_t mipsxx_pmu_handle_irq(int, void *);
static int mipsxx_pmu_handle_shared_irq(void);

static unsigned int mipsxx_pmu_swizzle_perf_idx(unsigned int idx)
{
	if (vpe_id() == 1)
		idx = (idx + 2) & 3;
	return idx;
}

static u64 mipsxx_pmu_read_counter(unsigned int idx)
{
	idx = mipsxx_pmu_swizzle_perf_idx(idx);

	switch (idx) {
	case 0:
		/*
		 * The counters are unsigned, we must cast to truncate
		 * off the high bits.
		 */
		return (u32)read_c0_perfcntr0();
	case 1:
		return (u32)read_c0_perfcntr1();
	case 2:
		return (u32)read_c0_perfcntr2();
	case 3:
		return (u32)read_c0_perfcntr3();
	default:
		WARN_ONCE(1, "Invalid performance counter number (%d)\n", idx);
		return 0;
	}
}

static u64 mipsxx_pmu_read_counter_64(unsigned int idx)
{
	idx = mipsxx_pmu_swizzle_perf_idx(idx);

	switch (idx) {
	case 0:
		return read_c0_perfcntr0_64();
	case 1:
		return read_c0_perfcntr1_64();
	case 2:
		return read_c0_perfcntr2_64();
	case 3:
		return read_c0_perfcntr3_64();
	default:
		WARN_ONCE(1, "Invalid performance counter number (%d)\n", idx);
		return 0;
	}
}

static void mipsxx_pmu_write_counter(unsigned int idx, u64 val)
{
	idx = mipsxx_pmu_swizzle_perf_idx(idx);

	switch (idx) {
	case 0:
		write_c0_perfcntr0(val);
		return;
	case 1:
		write_c0_perfcntr1(val);
		return;
	case 2:
		write_c0_perfcntr2(val);
		return;
	case 3:
		write_c0_perfcntr3(val);
		return;
	}
}

static void mipsxx_pmu_write_counter_64(unsigned int idx, u64 val)
{
	idx = mipsxx_pmu_swizzle_perf_idx(idx);

	switch (idx) {
	case 0:
		write_c0_perfcntr0_64(val);
		return;
	case 1:
		write_c0_perfcntr1_64(val);
		return;
	case 2:
		write_c0_perfcntr2_64(val);
		return;
	case 3:
		write_c0_perfcntr3_64(val);
		return;
	}
}

static unsigned int mipsxx_pmu_read_control(unsigned int idx)
{
	idx = mipsxx_pmu_swizzle_perf_idx(idx);

	switch (idx) {
	case 0:
		return read_c0_perfctrl0();
	case 1:
		return read_c0_perfctrl1();
	case 2:
		return read_c0_perfctrl2();
	case 3:
		return read_c0_perfctrl3();
	default:
		WARN_ONCE(1, "Invalid performance counter number (%d)\n", idx);
		return 0;
	}
}

static void mipsxx_pmu_write_control(unsigned int idx, unsigned int val)
{
	idx = mipsxx_pmu_swizzle_perf_idx(idx);

	switch (idx) {
	case 0:
		write_c0_perfctrl0(val);
		return;
	case 1:
		write_c0_perfctrl1(val);
		return;
	case 2:
		write_c0_perfctrl2(val);
		return;
	case 3:
		write_c0_perfctrl3(val);
		return;
	}
}

static int mipsxx_pmu_alloc_counter(struct cpu_hw_events *cpuc,
				    struct hw_perf_event *hwc)
{
	int i;

	/*
	 * We only need to care the counter mask. The range has been
	 * checked definitely.
	 */
	unsigned long cntr_mask = (hwc->event_base >> 8) & 0xffff;

	for (i = mipspmu.num_counters - 1; i >= 0; i--) {
		/*
		 * Note that some MIPS perf events can be counted by both
		 * even and odd counters, wheresas many other are only by
		 * even _or_ odd counters. This introduces an issue that
		 * when the former kind of event takes the counter the
		 * latter kind of event wants to use, then the "counter
		 * allocation" for the latter event will fail. In fact if
		 * they can be dynamically swapped, they both feel happy.
		 * But here we leave this issue alone for now.
		 */
		if (test_bit(i, &cntr_mask) &&
			!test_and_set_bit(i, cpuc->used_mask))
			return i;
	}

	return -EAGAIN;
}

static void mipsxx_pmu_enable_event(struct hw_perf_event *evt, int idx)
{
	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);

	WARN_ON(idx < 0 || idx >= mipspmu.num_counters);

	cpuc->saved_ctrl[idx] = M_PERFCTL_EVENT(evt->event_base & 0xff) |
		(evt->config_base & M_PERFCTL_CONFIG_MASK) |
		/* Make sure interrupt enabled. */
		M_PERFCTL_INTERRUPT_ENABLE;
	/*
	 * We do not actually let the counter run. Leave it until start().
	 */
}

static void mipsxx_pmu_disable_event(int idx)
{
	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
	unsigned long flags;

	WARN_ON(idx < 0 || idx >= mipspmu.num_counters);

	local_irq_save(flags);
	cpuc->saved_ctrl[idx] = mipsxx_pmu_read_control(idx) &
		~M_PERFCTL_COUNT_EVENT_WHENEVER;
	mipsxx_pmu_write_control(idx, cpuc->saved_ctrl[idx]);
	local_irq_restore(flags);
}

static int mipspmu_event_set_period(struct perf_event *event,
				    struct hw_perf_event *hwc,
				    int idx)
{
	u64 left = local64_read(&hwc->period_left);
	u64 period = hwc->sample_period;
	int ret = 0;

	if (unlikely((left + period) & (1ULL << 63))) {
		/* left underflowed by more than period. */
		left = period;
		local64_set(&hwc->period_left, left);
		hwc->last_period = period;
		ret = 1;
	} else	if (unlikely((left + period) <= period)) {
		/* left underflowed by less than period. */
		left += period;
		local64_set(&hwc->period_left, left);
		hwc->last_period = period;
		ret = 1;
	}

	if (left > mipspmu.max_period) {
		left = mipspmu.max_period;
		local64_set(&hwc->period_left, left);
	}

	local64_set(&hwc->prev_count, mipspmu.overflow - left);

	mipspmu.write_counter(idx, mipspmu.overflow - left);

	perf_event_update_userpage(event);

	return ret;
}

static void mipspmu_event_update(struct perf_event *event,
				 struct hw_perf_event *hwc,
				 int idx)
{
	u64 prev_raw_count, new_raw_count;
	u64 delta;

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

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

	delta = new_raw_count - prev_raw_count;

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

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

	if (flags & PERF_EF_RELOAD)
		WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));

	hwc->state = 0;

	/* Set the period for the event. */
	mipspmu_event_set_period(event, hwc, hwc->idx);

	/* Enable the event. */
	mipsxx_pmu_enable_event(hwc, hwc->idx);
}

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

	if (!(hwc->state & PERF_HES_STOPPED)) {
		/* We are working on a local event. */
		mipsxx_pmu_disable_event(hwc->idx);
		barrier();
		mipspmu_event_update(event, hwc, hwc->idx);
		hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
	}
}

static int mipspmu_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);

	/* To look for a free counter for this event. */
	idx = mipsxx_pmu_alloc_counter(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;
	mipsxx_pmu_disable_event(idx);
	cpuc->events[idx] = event;

	hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
	if (flags & PERF_EF_START)
		mipspmu_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 void mipspmu_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 || idx >= mipspmu.num_counters);

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

	perf_event_update_userpage(event);
}

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

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

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

static void mipspmu_enable(struct pmu *pmu)
{
#ifdef CONFIG_MIPS_MT_SMP
	write_unlock(&pmuint_rwlock);
#endif
	resume_local_counters();
}

/*
 * MIPS performance counters can be per-TC. The control registers can
 * not be directly accessed accross CPUs. Hence if we want to do global
 * control, we need cross CPU calls. on_each_cpu() can help us, but we
 * can not make sure this function is called with interrupts enabled. So
 * here we pause local counters and then grab a rwlock and leave the
 * counters on other CPUs alone. If any counter interrupt raises while
 * we own the write lock, simply pause local counters on that CPU and
 * spin in the handler. Also we know we won't be switched to another
 * CPU after pausing local counters and before grabbing the lock.
 */
static void mipspmu_disable(struct pmu *pmu)
{
	pause_local_counters();
#ifdef CONFIG_MIPS_MT_SMP
	write_lock(&pmuint_rwlock);
#endif
}

static atomic_t active_events = ATOMIC_INIT(0);
static DEFINE_MUTEX(pmu_reserve_mutex);
static int (*save_perf_irq)(void);

static int mipspmu_get_irq(void)
{
	int err;

	if (mipspmu.irq >= 0) {
		/* Request my own irq handler. */
		err = request_irq(mipspmu.irq, mipsxx_pmu_handle_irq,
			IRQF_PERCPU | IRQF_NOBALANCING,
			"mips_perf_pmu", NULL);
		if (err) {
			pr_warning("Unable to request IRQ%d for MIPS "
			   "performance counters!\n", mipspmu.irq);
		}
	} else if (cp0_perfcount_irq < 0) {
		/*
		 * We are sharing the irq number with the timer interrupt.
		 */
		save_perf_irq = perf_irq;
		perf_irq = mipsxx_pmu_handle_shared_irq;
		err = 0;
	} else {
		pr_warning("The platform hasn't properly defined its "
			"interrupt controller.\n");
		err = -ENOENT;
	}

	return err;
}

static void mipspmu_free_irq(void)
{
	if (mipspmu.irq >= 0)
		free_irq(mipspmu.irq, NULL);
	else if (cp0_perfcount_irq < 0)
		perf_irq = save_perf_irq;
}

/*
 * mipsxx/rm9000/loongson2 have different performance counters, they have
 * specific low-level init routines.
 */
static void reset_counters(void *arg);
static int __hw_perf_event_init(struct perf_event *event);

static void hw_perf_event_destroy(struct perf_event *event)
{
	if (atomic_dec_and_mutex_lock(&active_events,
				&pmu_reserve_mutex)) {
		/*
		 * We must not call the destroy function with interrupts
		 * disabled.
		 */
		on_each_cpu(reset_counters,
			(void *)(long)mipspmu.num_counters, 1);
		mipspmu_free_irq();
		mutex_unlock(&pmu_reserve_mutex);
	}
}

static int mipspmu_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 (event->cpu >= nr_cpumask_bits ||
	    (event->cpu >= 0 && !cpu_online(event->cpu)))
		return -ENODEV;

	if (!atomic_inc_not_zero(&active_events)) {
		mutex_lock(&pmu_reserve_mutex);
		if (atomic_read(&active_events) == 0)
			err = mipspmu_get_irq();

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

	if (err)
		return err;

	return __hw_perf_event_init(event);
}

static struct pmu pmu = {
	.pmu_enable	= mipspmu_enable,
	.pmu_disable	= mipspmu_disable,
	.event_init	= mipspmu_event_init,
	.add		= mipspmu_add,
	.del		= mipspmu_del,
	.start		= mipspmu_start,
	.stop		= mipspmu_stop,
	.read		= mipspmu_read,
};

static unsigned int mipspmu_perf_event_encode(const struct mips_perf_event *pev)
{
/*
 * Top 8 bits for range, next 16 bits for cntr_mask, lowest 8 bits for
 * event_id.
 */
#ifdef CONFIG_MIPS_MT_SMP
	return ((unsigned int)pev->range << 24) |
		(pev->cntr_mask & 0xffff00) |
		(pev->event_id & 0xff);
#else
	return (pev->cntr_mask & 0xffff00) |
		(pev->event_id & 0xff);
#endif
}

static const struct mips_perf_event *mipspmu_map_general_event(int idx)
{
	const struct mips_perf_event *pev;

	pev = ((*mipspmu.general_event_map)[idx].event_id ==
		UNSUPPORTED_PERF_EVENT_ID ? ERR_PTR(-EOPNOTSUPP) :
		&(*mipspmu.general_event_map)[idx]);

	return pev;
}

static const struct mips_perf_event *mipspmu_map_cache_event(u64 config)
{
	unsigned int cache_type, cache_op, cache_result;
	const struct mips_perf_event *pev;

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

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

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

	pev = &((*mipspmu.cache_event_map)
					[cache_type]
					[cache_op]
					[cache_result]);

	if (pev->event_id == UNSUPPORTED_PERF_EVENT_ID)
		return ERR_PTR(-EOPNOTSUPP);

	return pev;

}

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

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

	if (mipsxx_pmu_alloc_counter(&fake_cpuc, &leader->hw) < 0)
		return -EINVAL;

	list_for_each_entry(sibling, &leader->sibling_list, group_entry) {
		if (mipsxx_pmu_alloc_counter(&fake_cpuc, &sibling->hw) < 0)
			return -EINVAL;
	}

	if (mipsxx_pmu_alloc_counter(&fake_cpuc, &event->hw) < 0)
		return -EINVAL;

	return 0;
}

/* This is needed by specific irq handlers in perf_event_*.c */
static void handle_associated_event(struct cpu_hw_events *cpuc,
				    int idx, struct perf_sample_data *data,
				    struct pt_regs *regs)
{
	struct perf_event *event = cpuc->events[idx];
	struct hw_perf_event *hwc = &event->hw;

	mipspmu_event_update(event, hwc, idx);
	data->period = event->hw.last_period;
	if (!mipspmu_event_set_period(event, hwc, idx))
		return;

	if (perf_event_overflow(event, data, regs))
		mipsxx_pmu_disable_event(idx);
}


static int __n_counters(void)
{
	if (!(read_c0_config1() & M_CONFIG1_PC))
		return 0;
	if (!(read_c0_perfctrl0() & M_PERFCTL_MORE))
		return 1;
	if (!(read_c0_perfctrl1() & M_PERFCTL_MORE))
		return 2;
	if (!(read_c0_perfctrl2() & M_PERFCTL_MORE))
		return 3;

	return 4;
}

static int n_counters(void)
{
	int counters;

	switch (current_cpu_type()) {
	case CPU_R10000:
		counters = 2;
		break;

	case CPU_R12000:
	case CPU_R14000:
		counters = 4;
		break;

	default:
		counters = __n_counters();
	}

	return counters;
}

static void reset_counters(void *arg)
{
	int counters = (int)(long)arg;
	switch (counters) {
	case 4:
		mipsxx_pmu_write_control(3, 0);
		mipspmu.write_counter(3, 0);
	case 3:
		mipsxx_pmu_write_control(2, 0);
		mipspmu.write_counter(2, 0);
	case 2:
		mipsxx_pmu_write_control(1, 0);
		mipspmu.write_counter(1, 0);
	case 1:
		mipsxx_pmu_write_control(0, 0);
		mipspmu.write_counter(0, 0);
	}
}

/* 24K/34K/1004K cores can share the same event map. */
static const struct mips_perf_event mipsxxcore_event_map
				[PERF_COUNT_HW_MAX] = {
	[PERF_COUNT_HW_CPU_CYCLES] = { 0x00, CNTR_EVEN | CNTR_ODD, P },
	[PERF_COUNT_HW_INSTRUCTIONS] = { 0x01, CNTR_EVEN | CNTR_ODD, T },
	[PERF_COUNT_HW_CACHE_REFERENCES] = { UNSUPPORTED_PERF_EVENT_ID },
	[PERF_COUNT_HW_CACHE_MISSES] = { UNSUPPORTED_PERF_EVENT_ID },
	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = { 0x02, CNTR_EVEN, T },
	[PERF_COUNT_HW_BRANCH_MISSES] = { 0x02, CNTR_ODD, T },
	[PERF_COUNT_HW_BUS_CYCLES] = { UNSUPPORTED_PERF_EVENT_ID },
};

/* 74K core has different branch event code. */
static const struct mips_perf_event mipsxx74Kcore_event_map
				[PERF_COUNT_HW_MAX] = {
	[PERF_COUNT_HW_CPU_CYCLES] = { 0x00, CNTR_EVEN | CNTR_ODD, P },
	[PERF_COUNT_HW_INSTRUCTIONS] = { 0x01, CNTR_EVEN | CNTR_ODD, T },
	[PERF_COUNT_HW_CACHE_REFERENCES] = { UNSUPPORTED_PERF_EVENT_ID },
	[PERF_COUNT_HW_CACHE_MISSES] = { UNSUPPORTED_PERF_EVENT_ID },
	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = { 0x27, CNTR_EVEN, T },
	[PERF_COUNT_HW_BRANCH_MISSES] = { 0x27, CNTR_ODD, T },
	[PERF_COUNT_HW_BUS_CYCLES] = { UNSUPPORTED_PERF_EVENT_ID },
};

static const struct mips_perf_event octeon_event_map[PERF_COUNT_HW_MAX] = {
	[PERF_COUNT_HW_CPU_CYCLES] = { 0x01, CNTR_ALL },
	[PERF_COUNT_HW_INSTRUCTIONS] = { 0x03, CNTR_ALL },
	[PERF_COUNT_HW_CACHE_REFERENCES] = { 0x2b, CNTR_ALL },
	[PERF_COUNT_HW_CACHE_MISSES] = { 0x2e, CNTR_ALL  },
	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = { 0x08, CNTR_ALL },
	[PERF_COUNT_HW_BRANCH_MISSES] = { 0x09, CNTR_ALL },
	[PERF_COUNT_HW_BUS_CYCLES] = { 0x25, CNTR_ALL },
};

/* 24K/34K/1004K cores can share the same cache event map. */
static const struct mips_perf_event mipsxxcore_cache_map
				[PERF_COUNT_HW_CACHE_MAX]
				[PERF_COUNT_HW_CACHE_OP_MAX]
				[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
[C(L1D)] = {
	/*
	 * Like some other architectures (e.g. ARM), 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)]	= { 0x0a, CNTR_EVEN, T },
		[C(RESULT_MISS)]	= { 0x0b, CNTR_EVEN | CNTR_ODD, T },
	},
	[C(OP_WRITE)] = {
		[C(RESULT_ACCESS)]	= { 0x0a, CNTR_EVEN, T },
		[C(RESULT_MISS)]	= { 0x0b, CNTR_EVEN | CNTR_ODD, T },
	},
	[C(OP_PREFETCH)] = {
		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
},
[C(L1I)] = {
	[C(OP_READ)] = {
		[C(RESULT_ACCESS)]	= { 0x09, CNTR_EVEN, T },
		[C(RESULT_MISS)]	= { 0x09, CNTR_ODD, T },
	},
	[C(OP_WRITE)] = {
		[C(RESULT_ACCESS)]	= { 0x09, CNTR_EVEN, T },
		[C(RESULT_MISS)]	= { 0x09, CNTR_ODD, T },
	},
	[C(OP_PREFETCH)] = {
		[C(RESULT_ACCESS)]	= { 0x14, CNTR_EVEN, T },
		/*
		 * Note that MIPS has only "hit" events countable for
		 * the prefetch operation.
		 */
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
},
[C(LL)] = {
	[C(OP_READ)] = {
		[C(RESULT_ACCESS)]	= { 0x15, CNTR_ODD, P },
		[C(RESULT_MISS)]	= { 0x16, CNTR_EVEN, P },
	},
	[C(OP_WRITE)] = {
		[C(RESULT_ACCESS)]	= { 0x15, CNTR_ODD, P },
		[C(RESULT_MISS)]	= { 0x16, CNTR_EVEN, P },
	},
	[C(OP_PREFETCH)] = {
		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
},
[C(DTLB)] = {
	[C(OP_READ)] = {
		[C(RESULT_ACCESS)]	= { 0x06, CNTR_EVEN, T },
		[C(RESULT_MISS)]	= { 0x06, CNTR_ODD, T },
	},
	[C(OP_WRITE)] = {
		[C(RESULT_ACCESS)]	= { 0x06, CNTR_EVEN, T },
		[C(RESULT_MISS)]	= { 0x06, CNTR_ODD, T },
	},
	[C(OP_PREFETCH)] = {
		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
},
[C(ITLB)] = {
	[C(OP_READ)] = {
		[C(RESULT_ACCESS)]	= { 0x05, CNTR_EVEN, T },
		[C(RESULT_MISS)]	= { 0x05, CNTR_ODD, T },
	},
	[C(OP_WRITE)] = {
		[C(RESULT_ACCESS)]	= { 0x05, CNTR_EVEN, T },
		[C(RESULT_MISS)]	= { 0x05, CNTR_ODD, T },
	},
	[C(OP_PREFETCH)] = {
		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
},
[C(BPU)] = {
	/* Using the same code for *HW_BRANCH* */
	[C(OP_READ)] = {
		[C(RESULT_ACCESS)]	= { 0x02, CNTR_EVEN, T },
		[C(RESULT_MISS)]	= { 0x02, CNTR_ODD, T },
	},
	[C(OP_WRITE)] = {
		[C(RESULT_ACCESS)]	= { 0x02, CNTR_EVEN, T },
		[C(RESULT_MISS)]	= { 0x02, CNTR_ODD, T },
	},
	[C(OP_PREFETCH)] = {
		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
},
[C(NODE)] = {
	[C(OP_READ)] = {
		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
	[C(OP_WRITE)] = {
		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
	[C(OP_PREFETCH)] = {
		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
},
};

/* 74K core has completely different cache event map. */
static const struct mips_perf_event mipsxx74Kcore_cache_map
				[PERF_COUNT_HW_CACHE_MAX]
				[PERF_COUNT_HW_CACHE_OP_MAX]
				[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
[C(L1D)] = {
	/*
	 * Like some other architectures (e.g. ARM), 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)]	= { 0x17, CNTR_ODD, T },
		[C(RESULT_MISS)]	= { 0x18, CNTR_ODD, T },
	},
	[C(OP_WRITE)] = {
		[C(RESULT_ACCESS)]	= { 0x17, CNTR_ODD, T },
		[C(RESULT_MISS)]	= { 0x18, CNTR_ODD, T },
	},
	[C(OP_PREFETCH)] = {
		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
},
[C(L1I)] = {
	[C(OP_READ)] = {
		[C(RESULT_ACCESS)]	= { 0x06, CNTR_EVEN, T },
		[C(RESULT_MISS)]	= { 0x06, CNTR_ODD, T },
	},
	[C(OP_WRITE)] = {
		[C(RESULT_ACCESS)]	= { 0x06, CNTR_EVEN, T },
		[C(RESULT_MISS)]	= { 0x06, CNTR_ODD, T },
	},
	[C(OP_PREFETCH)] = {
		[C(RESULT_ACCESS)]	= { 0x34, CNTR_EVEN, T },
		/*
		 * Note that MIPS has only "hit" events countable for
		 * the prefetch operation.
		 */
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
},
[C(LL)] = {
	[C(OP_READ)] = {
		[C(RESULT_ACCESS)]	= { 0x1c, CNTR_ODD, P },
		[C(RESULT_MISS)]	= { 0x1d, CNTR_EVEN | CNTR_ODD, P },
	},
	[C(OP_WRITE)] = {
		[C(RESULT_ACCESS)]	= { 0x1c, CNTR_ODD, P },
		[C(RESULT_MISS)]	= { 0x1d, CNTR_EVEN | CNTR_ODD, P },
	},
	[C(OP_PREFETCH)] = {
		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
},
[C(DTLB)] = {
	/* 74K core does not have specific DTLB events. */
	[C(OP_READ)] = {
		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
	[C(OP_WRITE)] = {
		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
	[C(OP_PREFETCH)] = {
		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
},
[C(ITLB)] = {
	[C(OP_READ)] = {
		[C(RESULT_ACCESS)]	= { 0x04, CNTR_EVEN, T },
		[C(RESULT_MISS)]	= { 0x04, CNTR_ODD, T },
	},
	[C(OP_WRITE)] = {
		[C(RESULT_ACCESS)]	= { 0x04, CNTR_EVEN, T },
		[C(RESULT_MISS)]	= { 0x04, CNTR_ODD, T },
	},
	[C(OP_PREFETCH)] = {
		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
},
[C(BPU)] = {
	/* Using the same code for *HW_BRANCH* */
	[C(OP_READ)] = {
		[C(RESULT_ACCESS)]	= { 0x27, CNTR_EVEN, T },
		[C(RESULT_MISS)]	= { 0x27, CNTR_ODD, T },
	},
	[C(OP_WRITE)] = {
		[C(RESULT_ACCESS)]	= { 0x27, CNTR_EVEN, T },
		[C(RESULT_MISS)]	= { 0x27, CNTR_ODD, T },
	},
	[C(OP_PREFETCH)] = {
		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
},
[C(NODE)] = {
	[C(OP_READ)] = {
		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
	[C(OP_WRITE)] = {
		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
	[C(OP_PREFETCH)] = {
		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
},
};


static const struct mips_perf_event octeon_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)]	= { 0x2b, CNTR_ALL },
		[C(RESULT_MISS)]	= { 0x2e, CNTR_ALL },
	},
	[C(OP_WRITE)] = {
		[C(RESULT_ACCESS)]	= { 0x30, CNTR_ALL },
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
	[C(OP_PREFETCH)] = {
		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
},
[C(L1I)] = {
	[C(OP_READ)] = {
		[C(RESULT_ACCESS)]	= { 0x18, CNTR_ALL },
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
	[C(OP_WRITE)] = {
		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
	[C(OP_PREFETCH)] = {
		[C(RESULT_ACCESS)]	= { 0x19, CNTR_ALL },
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
},
[C(LL)] = {
	[C(OP_READ)] = {
		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
	[C(OP_WRITE)] = {
		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
	[C(OP_PREFETCH)] = {
		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
},
[C(DTLB)] = {
	/*
	 * Only general DTLB misses are counted use the same event for
	 * read and write.
	 */
	[C(OP_READ)] = {
		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
		[C(RESULT_MISS)]	= { 0x35, CNTR_ALL },
	},
	[C(OP_WRITE)] = {
		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
		[C(RESULT_MISS)]	= { 0x35, CNTR_ALL },
	},
	[C(OP_PREFETCH)] = {
		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
},
[C(ITLB)] = {
	[C(OP_READ)] = {
		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
		[C(RESULT_MISS)]	= { 0x37, CNTR_ALL },
	},
	[C(OP_WRITE)] = {
		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
	[C(OP_PREFETCH)] = {
		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
},
[C(BPU)] = {
	/* Using the same code for *HW_BRANCH* */
	[C(OP_READ)] = {
		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
	[C(OP_WRITE)] = {
		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
	[C(OP_PREFETCH)] = {
		[C(RESULT_ACCESS)]	= { UNSUPPORTED_PERF_EVENT_ID },
		[C(RESULT_MISS)]	= { UNSUPPORTED_PERF_EVENT_ID },
	},
},
};

#ifdef CONFIG_MIPS_MT_SMP
static void check_and_calc_range(struct perf_event *event,
				 const struct mips_perf_event *pev)
{
	struct hw_perf_event *hwc = &event->hw;

	if (event->cpu >= 0) {
		if (pev->range > V) {
			/*
			 * The user selected an event that is processor
			 * wide, while expecting it to be VPE wide.
			 */
			hwc->config_base |= M_TC_EN_ALL;
		} else {
			/*
			 * FIXME: cpu_data[event->cpu].vpe_id reports 0
			 * for both CPUs.
			 */
			hwc->config_base |= M_PERFCTL_VPEID(event->cpu);
			hwc->config_base |= M_TC_EN_VPE;
		}
	} else
		hwc->config_base |= M_TC_EN_ALL;
}
#else
static void check_and_calc_range(struct perf_event *event,
				 const struct mips_perf_event *pev)
{
}
#endif

static int __hw_perf_event_init(struct perf_event *event)
{
	struct perf_event_attr *attr = &event->attr;
	struct hw_perf_event *hwc = &event->hw;
	const struct mips_perf_event *pev;
	int err;

	/* Returning MIPS event descriptor for generic perf event. */
	if (PERF_TYPE_HARDWARE == event->attr.type) {
		if (event->attr.config >= PERF_COUNT_HW_MAX)
			return -EINVAL;
		pev = mipspmu_map_general_event(event->attr.config);
	} else if (PERF_TYPE_HW_CACHE == event->attr.type) {
		pev = mipspmu_map_cache_event(event->attr.config);
	} else if (PERF_TYPE_RAW == event->attr.type) {
		/* We are working on the global raw event. */
		mutex_lock(&raw_event_mutex);
		pev = mipspmu.map_raw_event(event->attr.config);
	} else {
		/* The event type is not (yet) supported. */
		return -EOPNOTSUPP;
	}

	if (IS_ERR(pev)) {
		if (PERF_TYPE_RAW == event->attr.type)
			mutex_unlock(&raw_event_mutex);
		return PTR_ERR(pev);
	}

	/*
	 * We allow max flexibility on how each individual counter shared
	 * by the single CPU operates (the mode exclusion and the range).
	 */
	hwc->config_base = M_PERFCTL_INTERRUPT_ENABLE;

	/* Calculate range bits and validate it. */
	if (num_possible_cpus() > 1)
		check_and_calc_range(event, pev);

	hwc->event_base = mipspmu_perf_event_encode(pev);
	if (PERF_TYPE_RAW == event->attr.type)
		mutex_unlock(&raw_event_mutex);

	if (!attr->exclude_user)
		hwc->config_base |= M_PERFCTL_USER;
	if (!attr->exclude_kernel) {
		hwc->config_base |= M_PERFCTL_KERNEL;
		/* MIPS kernel mode: KSU == 00b || EXL == 1 || ERL == 1 */
		hwc->config_base |= M_PERFCTL_EXL;
	}
	if (!attr->exclude_hv)
		hwc->config_base |= M_PERFCTL_SUPERVISOR;

	hwc->config_base &= M_PERFCTL_CONFIG_MASK;
	/*
	 * The event can belong to another cpu. We do not assign a local
	 * counter for it for now.
	 */
	hwc->idx = -1;
	hwc->config = 0;

	if (!hwc->sample_period) {
		hwc->sample_period  = mipspmu.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);

	event->destroy = hw_perf_event_destroy;

	if (err)
		event->destroy(event);

	return err;
}

static void pause_local_counters(void)
{
	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
	int ctr = mipspmu.num_counters;
	unsigned long flags;

	local_irq_save(flags);
	do {
		ctr--;
		cpuc->saved_ctrl[ctr] = mipsxx_pmu_read_control(ctr);
		mipsxx_pmu_write_control(ctr, cpuc->saved_ctrl[ctr] &
					 ~M_PERFCTL_COUNT_EVENT_WHENEVER);
	} while (ctr > 0);
	local_irq_restore(flags);
}

static void resume_local_counters(void)
{
	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
	int ctr = mipspmu.num_counters;

	do {
		ctr--;
		mipsxx_pmu_write_control(ctr, cpuc->saved_ctrl[ctr]);
	} while (ctr > 0);
}

static int mipsxx_pmu_handle_shared_irq(void)
{
	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
	struct perf_sample_data data;
	unsigned int counters = mipspmu.num_counters;
	u64 counter;
	int handled = IRQ_NONE;
	struct pt_regs *regs;

	if (cpu_has_mips_r2 && !(read_c0_cause() & (1 << 26)))
		return handled;
	/*
	 * First we pause the local counters, so that when we are locked
	 * here, the counters are all paused. When it gets locked due to
	 * perf_disable(), the timer interrupt handler will be delayed.
	 *
	 * See also mipsxx_pmu_start().
	 */
	pause_local_counters();
#ifdef CONFIG_MIPS_MT_SMP
	read_lock(&pmuint_rwlock);
#endif

	regs = get_irq_regs();

	perf_sample_data_init(&data, 0);

	switch (counters) {
#define HANDLE_COUNTER(n)						\
	case n + 1:							\
		if (test_bit(n, cpuc->used_mask)) {			\
			counter = mipspmu.read_counter(n);		\
			if (counter & mipspmu.overflow) {		\
				handle_associated_event(cpuc, n, &data, regs); \
				handled = IRQ_HANDLED;			\
			}						\
		}
	HANDLE_COUNTER(3)
	HANDLE_COUNTER(2)
	HANDLE_COUNTER(1)
	HANDLE_COUNTER(0)
	}

	/*
	 * Do all the work for the pending perf events. We can do this
	 * in here because the performance counter interrupt is a regular
	 * interrupt, not NMI.
	 */
	if (handled == IRQ_HANDLED)
		irq_work_run();

#ifdef CONFIG_MIPS_MT_SMP
	read_unlock(&pmuint_rwlock);
#endif
	resume_local_counters();
	return handled;
}

static irqreturn_t mipsxx_pmu_handle_irq(int irq, void *dev)
{
	return mipsxx_pmu_handle_shared_irq();
}

/* 24K */
#define IS_BOTH_COUNTERS_24K_EVENT(b)					\
	((b) == 0 || (b) == 1 || (b) == 11)

/* 34K */
#define IS_BOTH_COUNTERS_34K_EVENT(b)					\
	((b) == 0 || (b) == 1 || (b) == 11)
#ifdef CONFIG_MIPS_MT_SMP
#define IS_RANGE_P_34K_EVENT(r, b)					\
	((b) == 0 || (r) == 18 || (b) == 21 || (b) == 22 ||		\
	 (b) == 25 || (b) == 39 || (r) == 44 || (r) == 174 ||		\
	 (r) == 176 || ((b) >= 50 && (b) <= 55) ||			\
	 ((b) >= 64 && (b) <= 67))
#define IS_RANGE_V_34K_EVENT(r)	((r) == 47)
#endif

/* 74K */
#define IS_BOTH_COUNTERS_74K_EVENT(b)					\
	((b) == 0 || (b) == 1)

/* 1004K */
#define IS_BOTH_COUNTERS_1004K_EVENT(b)					\
	((b) == 0 || (b) == 1 || (b) == 11)
#ifdef CONFIG_MIPS_MT_SMP
#define IS_RANGE_P_1004K_EVENT(r, b)					\
	((b) == 0 || (r) == 18 || (b) == 21 || (b) == 22 ||		\
	 (b) == 25 || (b) == 36 || (b) == 39 || (r) == 44 ||		\
	 (r) == 174 || (r) == 176 || ((b) >= 50 && (b) <= 59) ||	\
	 (r) == 188 || (b) == 61 || (b) == 62 ||			\
	 ((b) >= 64 && (b) <= 67))
#define IS_RANGE_V_1004K_EVENT(r)	((r) == 47)
#endif

/*
 * User can use 0-255 raw events, where 0-127 for the events of even
 * counters, and 128-255 for odd counters. Note that bit 7 is used to
 * indicate the parity. So, for example, when user wants to take the
 * Event Num of 15 for odd counters (by referring to the user manual),
 * then 128 needs to be added to 15 as the input for the event config,
 * i.e., 143 (0x8F) to be used.
 */
static const struct mips_perf_event *mipsxx_pmu_map_raw_event(u64 config)
{
	unsigned int raw_id = config & 0xff;
	unsigned int base_id = raw_id & 0x7f;

	raw_event.event_id = base_id;

	switch (current_cpu_type()) {
	case CPU_24K:
		if (IS_BOTH_COUNTERS_24K_EVENT(base_id))
			raw_event.cntr_mask = CNTR_EVEN | CNTR_ODD;
		else
			raw_event.cntr_mask =
				raw_id > 127 ? CNTR_ODD : CNTR_EVEN;
#ifdef CONFIG_MIPS_MT_SMP
		/*
		 * This is actually doing nothing. Non-multithreading
		 * CPUs will not check and calculate the range.
		 */
		raw_event.range = P;
#endif
		break;
	case CPU_34K:
		if (IS_BOTH_COUNTERS_34K_EVENT(base_id))
			raw_event.cntr_mask = CNTR_EVEN | CNTR_ODD;
		else
			raw_event.cntr_mask =
				raw_id > 127 ? CNTR_ODD : CNTR_EVEN;
#ifdef CONFIG_MIPS_MT_SMP
		if (IS_RANGE_P_34K_EVENT(raw_id, base_id))
			raw_event.range = P;
		else if (unlikely(IS_RANGE_V_34K_EVENT(raw_id)))
			raw_event.range = V;
		else
			raw_event.range = T;
#endif
		break;
	case CPU_74K:
		if (IS_BOTH_COUNTERS_74K_EVENT(base_id))
			raw_event.cntr_mask = CNTR_EVEN | CNTR_ODD;
		else
			raw_event.cntr_mask =
				raw_id > 127 ? CNTR_ODD : CNTR_EVEN;
#ifdef CONFIG_MIPS_MT_SMP
		raw_event.range = P;
#endif
		break;
	case CPU_1004K:
		if (IS_BOTH_COUNTERS_1004K_EVENT(base_id))
			raw_event.cntr_mask = CNTR_EVEN | CNTR_ODD;
		else
			raw_event.cntr_mask =
				raw_id > 127 ? CNTR_ODD : CNTR_EVEN;
#ifdef CONFIG_MIPS_MT_SMP
		if (IS_RANGE_P_1004K_EVENT(raw_id, base_id))
			raw_event.range = P;
		else if (unlikely(IS_RANGE_V_1004K_EVENT(raw_id)))
			raw_event.range = V;
		else
			raw_event.range = T;
#endif
		break;
	}

	return &raw_event;
}

static const struct mips_perf_event *octeon_pmu_map_raw_event(u64 config)
{
	unsigned int raw_id = config & 0xff;
	unsigned int base_id = raw_id & 0x7f;


	raw_event.cntr_mask = CNTR_ALL;
	raw_event.event_id = base_id;

	if (current_cpu_type() == CPU_CAVIUM_OCTEON2) {
		if (base_id > 0x42)
			return ERR_PTR(-EOPNOTSUPP);
	} else {
		if (base_id > 0x3a)
			return ERR_PTR(-EOPNOTSUPP);
	}

	switch (base_id) {
	case 0x00:
	case 0x0f:
	case 0x1e:
	case 0x1f:
	case 0x2f:
	case 0x34:
	case 0x3b ... 0x3f:
		return ERR_PTR(-EOPNOTSUPP);
	default:
		break;
	}

	return &raw_event;
}

static int __init
init_hw_perf_events(void)
{
	int counters, irq;
	int counter_bits;

	pr_info("Performance counters: ");

	counters = n_counters();
	if (counters == 0) {
		pr_cont("No available PMU.\n");
		return -ENODEV;
	}

#ifdef CONFIG_MIPS_MT_SMP
	cpu_has_mipsmt_pertccounters = read_c0_config7() & (1<<19);
	if (!cpu_has_mipsmt_pertccounters)
		counters = counters_total_to_per_cpu(counters);
#endif

#ifdef MSC01E_INT_BASE
	if (cpu_has_veic) {
		/*
		 * Using platform specific interrupt controller defines.
		 */
		irq = MSC01E_INT_BASE + MSC01E_INT_PERFCTR;
	} else {
#endif
		if (cp0_perfcount_irq >= 0)
			irq = MIPS_CPU_IRQ_BASE + cp0_perfcount_irq;
		else
			irq = -1;
#ifdef MSC01E_INT_BASE
	}
#endif

	mipspmu.map_raw_event = mipsxx_pmu_map_raw_event;

	switch (current_cpu_type()) {
	case CPU_24K:
		mipspmu.name = "mips/24K";
		mipspmu.general_event_map = &mipsxxcore_event_map;
		mipspmu.cache_event_map = &mipsxxcore_cache_map;
		break;
	case CPU_34K:
		mipspmu.name = "mips/34K";
		mipspmu.general_event_map = &mipsxxcore_event_map;
		mipspmu.cache_event_map = &mipsxxcore_cache_map;
		break;
	case CPU_74K:
		mipspmu.name = "mips/74K";
		mipspmu.general_event_map = &mipsxx74Kcore_event_map;
		mipspmu.cache_event_map = &mipsxx74Kcore_cache_map;
		break;
	case CPU_1004K:
		mipspmu.name = "mips/1004K";
		mipspmu.general_event_map = &mipsxxcore_event_map;
		mipspmu.cache_event_map = &mipsxxcore_cache_map;
		break;
	case CPU_CAVIUM_OCTEON:
	case CPU_CAVIUM_OCTEON_PLUS:
	case CPU_CAVIUM_OCTEON2:
		mipspmu.name = "octeon";
		mipspmu.general_event_map = &octeon_event_map;
		mipspmu.cache_event_map = &octeon_cache_map;
		mipspmu.map_raw_event = octeon_pmu_map_raw_event;
		break;
	default:
		pr_cont("Either hardware does not support performance "
			"counters, or not yet implemented.\n");
		return -ENODEV;
	}

	mipspmu.num_counters = counters;
	mipspmu.irq = irq;

	if (read_c0_perfctrl0() & M_PERFCTL_WIDE) {
		mipspmu.max_period = (1ULL << 63) - 1;
		mipspmu.valid_count = (1ULL << 63) - 1;
		mipspmu.overflow = 1ULL << 63;
		mipspmu.read_counter = mipsxx_pmu_read_counter_64;
		mipspmu.write_counter = mipsxx_pmu_write_counter_64;
		counter_bits = 64;
	} else {
		mipspmu.max_period = (1ULL << 31) - 1;
		mipspmu.valid_count = (1ULL << 31) - 1;
		mipspmu.overflow = 1ULL << 31;
		mipspmu.read_counter = mipsxx_pmu_read_counter;
		mipspmu.write_counter = mipsxx_pmu_write_counter;
		counter_bits = 32;
	}

	on_each_cpu(reset_counters, (void *)(long)counters, 1);

	pr_cont("%s PMU enabled, %d %d-bit counters available to each "
		"CPU, irq %d%s\n", mipspmu.name, counters, counter_bits, irq,
		irq < 0 ? " (share with timer interrupt)" : "");

	perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);

	return 0;
}
early_initcall(init_hw_perf_events);