intel_rapl.c 36 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
/*
 * Intel Running Average Power Limit (RAPL) Driver
 * Copyright (c) 2013, Intel Corporation.
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms and conditions of the GNU General Public License,
 * version 2, as published by the Free Software Foundation.
 *
 * This program is distributed in the hope it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 * more details.
 *
 * You should have received a copy of the GNU General Public License along with
 * this program; if not, write to the Free Software Foundation, Inc.
 *
 */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/list.h>
#include <linux/types.h>
#include <linux/device.h>
#include <linux/slab.h>
#include <linux/log2.h>
#include <linux/bitmap.h>
#include <linux/delay.h>
#include <linux/sysfs.h>
#include <linux/cpu.h>
#include <linux/powercap.h>

#include <asm/processor.h>
#include <asm/cpu_device_id.h>

/* bitmasks for RAPL MSRs, used by primitive access functions */
#define ENERGY_STATUS_MASK      0xffffffff

#define POWER_LIMIT1_MASK       0x7FFF
#define POWER_LIMIT1_ENABLE     BIT(15)
#define POWER_LIMIT1_CLAMP      BIT(16)

#define POWER_LIMIT2_MASK       (0x7FFFULL<<32)
#define POWER_LIMIT2_ENABLE     BIT_ULL(47)
#define POWER_LIMIT2_CLAMP      BIT_ULL(48)
#define POWER_PACKAGE_LOCK      BIT_ULL(63)
#define POWER_PP_LOCK           BIT(31)

#define TIME_WINDOW1_MASK       (0x7FULL<<17)
#define TIME_WINDOW2_MASK       (0x7FULL<<49)

#define POWER_UNIT_OFFSET	0
#define POWER_UNIT_MASK		0x0F

#define ENERGY_UNIT_OFFSET	0x08
#define ENERGY_UNIT_MASK	0x1F00

#define TIME_UNIT_OFFSET	0x10
#define TIME_UNIT_MASK		0xF0000

#define POWER_INFO_MAX_MASK     (0x7fffULL<<32)
#define POWER_INFO_MIN_MASK     (0x7fffULL<<16)
#define POWER_INFO_MAX_TIME_WIN_MASK     (0x3fULL<<48)
#define POWER_INFO_THERMAL_SPEC_MASK     0x7fff

#define PERF_STATUS_THROTTLE_TIME_MASK 0xffffffff
#define PP_POLICY_MASK         0x1F

/* Non HW constants */
#define RAPL_PRIMITIVE_DERIVED       BIT(1) /* not from raw data */
#define RAPL_PRIMITIVE_DUMMY         BIT(2)

/* scale RAPL units to avoid floating point math inside kernel */
#define POWER_UNIT_SCALE     (1000000)
#define ENERGY_UNIT_SCALE    (1000000)
#define TIME_UNIT_SCALE      (1000000)

#define TIME_WINDOW_MAX_MSEC 40000
#define TIME_WINDOW_MIN_MSEC 250

enum unit_type {
	ARBITRARY_UNIT, /* no translation */
	POWER_UNIT,
	ENERGY_UNIT,
	TIME_UNIT,
};

enum rapl_domain_type {
	RAPL_DOMAIN_PACKAGE, /* entire package/socket */
	RAPL_DOMAIN_PP0, /* core power plane */
	RAPL_DOMAIN_PP1, /* graphics uncore */
	RAPL_DOMAIN_DRAM,/* DRAM control_type */
	RAPL_DOMAIN_MAX,
};

enum rapl_domain_msr_id {
	RAPL_DOMAIN_MSR_LIMIT,
	RAPL_DOMAIN_MSR_STATUS,
	RAPL_DOMAIN_MSR_PERF,
	RAPL_DOMAIN_MSR_POLICY,
	RAPL_DOMAIN_MSR_INFO,
	RAPL_DOMAIN_MSR_MAX,
};

/* per domain data, some are optional */
enum rapl_primitives {
	ENERGY_COUNTER,
	POWER_LIMIT1,
	POWER_LIMIT2,
	FW_LOCK,

	PL1_ENABLE,  /* power limit 1, aka long term */
	PL1_CLAMP,   /* allow frequency to go below OS request */
	PL2_ENABLE,  /* power limit 2, aka short term, instantaneous */
	PL2_CLAMP,

	TIME_WINDOW1, /* long term */
	TIME_WINDOW2, /* short term */
	THERMAL_SPEC_POWER,
	MAX_POWER,

	MIN_POWER,
	MAX_TIME_WINDOW,
	THROTTLED_TIME,
	PRIORITY_LEVEL,

	/* below are not raw primitive data */
	AVERAGE_POWER,
	NR_RAPL_PRIMITIVES,
};

#define NR_RAW_PRIMITIVES (NR_RAPL_PRIMITIVES - 2)

/* Can be expanded to include events, etc.*/
struct rapl_domain_data {
	u64 primitives[NR_RAPL_PRIMITIVES];
	unsigned long timestamp;
};


#define	DOMAIN_STATE_INACTIVE           BIT(0)
#define	DOMAIN_STATE_POWER_LIMIT_SET    BIT(1)
#define DOMAIN_STATE_BIOS_LOCKED        BIT(2)

#define NR_POWER_LIMITS (2)
struct rapl_power_limit {
	struct powercap_zone_constraint *constraint;
	int prim_id; /* primitive ID used to enable */
	struct rapl_domain *domain;
	const char *name;
};

static const char pl1_name[] = "long_term";
static const char pl2_name[] = "short_term";

struct rapl_domain {
	const char *name;
	enum rapl_domain_type id;
	int msrs[RAPL_DOMAIN_MSR_MAX];
	struct powercap_zone power_zone;
	struct rapl_domain_data rdd;
	struct rapl_power_limit rpl[NR_POWER_LIMITS];
	u64 attr_map; /* track capabilities */
	unsigned int state;
	int package_id;
};
#define power_zone_to_rapl_domain(_zone) \
	container_of(_zone, struct rapl_domain, power_zone)


/* Each physical package contains multiple domains, these are the common
 * data across RAPL domains within a package.
 */
struct rapl_package {
	unsigned int id; /* physical package/socket id */
	unsigned int nr_domains;
	unsigned long domain_map; /* bit map of active domains */
	unsigned int power_unit_divisor;
	unsigned int energy_unit_divisor;
	unsigned int time_unit_divisor;
	struct rapl_domain *domains; /* array of domains, sized at runtime */
	struct powercap_zone *power_zone; /* keep track of parent zone */
	int nr_cpus; /* active cpus on the package, topology info is lost during
		      * cpu hotplug. so we have to track ourselves.
		      */
	unsigned long power_limit_irq; /* keep track of package power limit
					* notify interrupt enable status.
					*/
	struct list_head plist;
};
#define PACKAGE_PLN_INT_SAVED   BIT(0)
#define MAX_PRIM_NAME (32)

/* per domain data. used to describe individual knobs such that access function
 * can be consolidated into one instead of many inline functions.
 */
struct rapl_primitive_info {
	const char *name;
	u64 mask;
	int shift;
	enum rapl_domain_msr_id id;
	enum unit_type unit;
	u32 flag;
};

#define PRIMITIVE_INFO_INIT(p, m, s, i, u, f) {	\
		.name = #p,			\
		.mask = m,			\
		.shift = s,			\
		.id = i,			\
		.unit = u,			\
		.flag = f			\
	}

static void rapl_init_domains(struct rapl_package *rp);
static int rapl_read_data_raw(struct rapl_domain *rd,
			enum rapl_primitives prim,
			bool xlate, u64 *data);
static int rapl_write_data_raw(struct rapl_domain *rd,
			enum rapl_primitives prim,
			unsigned long long value);
static u64 rapl_unit_xlate(int package, enum unit_type type, u64 value,
			int to_raw);
static void package_power_limit_irq_save(int package_id);

static LIST_HEAD(rapl_packages); /* guarded by CPU hotplug lock */

static const char * const rapl_domain_names[] = {
	"package",
	"core",
	"uncore",
	"dram",
};

static struct powercap_control_type *control_type; /* PowerCap Controller */

/* caller to ensure CPU hotplug lock is held */
static struct rapl_package *find_package_by_id(int id)
{
	struct rapl_package *rp;

	list_for_each_entry(rp, &rapl_packages, plist) {
		if (rp->id == id)
			return rp;
	}

	return NULL;
}

/* caller to ensure CPU hotplug lock is held */
static int find_active_cpu_on_package(int package_id)
{
	int i;

	for_each_online_cpu(i) {
		if (topology_physical_package_id(i) == package_id)
			return i;
	}
	/* all CPUs on this package are offline */

	return -ENODEV;
}

/* caller must hold cpu hotplug lock */
static void rapl_cleanup_data(void)
{
	struct rapl_package *p, *tmp;

	list_for_each_entry_safe(p, tmp, &rapl_packages, plist) {
		kfree(p->domains);
		list_del(&p->plist);
		kfree(p);
	}
}

static int get_energy_counter(struct powercap_zone *power_zone, u64 *energy_raw)
{
	struct rapl_domain *rd;
	u64 energy_now;

	/* prevent CPU hotplug, make sure the RAPL domain does not go
	 * away while reading the counter.
	 */
	get_online_cpus();
	rd = power_zone_to_rapl_domain(power_zone);

	if (!rapl_read_data_raw(rd, ENERGY_COUNTER, true, &energy_now)) {
		*energy_raw = energy_now;
		put_online_cpus();

		return 0;
	}
	put_online_cpus();

	return -EIO;
}

static int get_max_energy_counter(struct powercap_zone *pcd_dev, u64 *energy)
{
	*energy = rapl_unit_xlate(0, ENERGY_UNIT, ENERGY_STATUS_MASK, 0);
	return 0;
}

static int release_zone(struct powercap_zone *power_zone)
{
	struct rapl_domain *rd = power_zone_to_rapl_domain(power_zone);
	struct rapl_package *rp;

	/* package zone is the last zone of a package, we can free
	 * memory here since all children has been unregistered.
	 */
	if (rd->id == RAPL_DOMAIN_PACKAGE) {
		rp = find_package_by_id(rd->package_id);
		if (!rp) {
			dev_warn(&power_zone->dev, "no package id %s\n",
				rd->name);
			return -ENODEV;
		}
		kfree(rd);
		rp->domains = NULL;
	}

	return 0;

}

static int find_nr_power_limit(struct rapl_domain *rd)
{
	int i;

	for (i = 0; i < NR_POWER_LIMITS; i++) {
		if (rd->rpl[i].name == NULL)
			break;
	}

	return i;
}

static int set_domain_enable(struct powercap_zone *power_zone, bool mode)
{
	struct rapl_domain *rd = power_zone_to_rapl_domain(power_zone);
	int nr_powerlimit;

	if (rd->state & DOMAIN_STATE_BIOS_LOCKED)
		return -EACCES;
	get_online_cpus();
	nr_powerlimit = find_nr_power_limit(rd);
	/* here we activate/deactivate the hardware for power limiting */
	rapl_write_data_raw(rd, PL1_ENABLE, mode);
	/* always enable clamp such that p-state can go below OS requested
	 * range. power capping priority over guranteed frequency.
	 */
	rapl_write_data_raw(rd, PL1_CLAMP, mode);
	/* some domains have pl2 */
	if (nr_powerlimit > 1) {
		rapl_write_data_raw(rd, PL2_ENABLE, mode);
		rapl_write_data_raw(rd, PL2_CLAMP, mode);
	}
	put_online_cpus();

	return 0;
}

static int get_domain_enable(struct powercap_zone *power_zone, bool *mode)
{
	struct rapl_domain *rd = power_zone_to_rapl_domain(power_zone);
	u64 val;

	if (rd->state & DOMAIN_STATE_BIOS_LOCKED) {
		*mode = false;
		return 0;
	}
	get_online_cpus();
	if (rapl_read_data_raw(rd, PL1_ENABLE, true, &val)) {
		put_online_cpus();
		return -EIO;
	}
	*mode = val;
	put_online_cpus();

	return 0;
}

/* per RAPL domain ops, in the order of rapl_domain_type */
static struct powercap_zone_ops zone_ops[] = {
	/* RAPL_DOMAIN_PACKAGE */
	{
		.get_energy_uj = get_energy_counter,
		.get_max_energy_range_uj = get_max_energy_counter,
		.release = release_zone,
		.set_enable = set_domain_enable,
		.get_enable = get_domain_enable,
	},
	/* RAPL_DOMAIN_PP0 */
	{
		.get_energy_uj = get_energy_counter,
		.get_max_energy_range_uj = get_max_energy_counter,
		.release = release_zone,
		.set_enable = set_domain_enable,
		.get_enable = get_domain_enable,
	},
	/* RAPL_DOMAIN_PP1 */
	{
		.get_energy_uj = get_energy_counter,
		.get_max_energy_range_uj = get_max_energy_counter,
		.release = release_zone,
		.set_enable = set_domain_enable,
		.get_enable = get_domain_enable,
	},
	/* RAPL_DOMAIN_DRAM */
	{
		.get_energy_uj = get_energy_counter,
		.get_max_energy_range_uj = get_max_energy_counter,
		.release = release_zone,
		.set_enable = set_domain_enable,
		.get_enable = get_domain_enable,
	},
};

static int set_power_limit(struct powercap_zone *power_zone, int id,
			u64 power_limit)
{
	struct rapl_domain *rd;
	struct rapl_package *rp;
	int ret = 0;

	get_online_cpus();
	rd = power_zone_to_rapl_domain(power_zone);
	rp = find_package_by_id(rd->package_id);
	if (!rp) {
		ret = -ENODEV;
		goto set_exit;
	}

	if (rd->state & DOMAIN_STATE_BIOS_LOCKED) {
		dev_warn(&power_zone->dev, "%s locked by BIOS, monitoring only\n",
			rd->name);
		ret = -EACCES;
		goto set_exit;
	}

	switch (rd->rpl[id].prim_id) {
	case PL1_ENABLE:
		rapl_write_data_raw(rd, POWER_LIMIT1, power_limit);
		break;
	case PL2_ENABLE:
		rapl_write_data_raw(rd, POWER_LIMIT2, power_limit);
		break;
	default:
		ret = -EINVAL;
	}
	if (!ret)
		package_power_limit_irq_save(rd->package_id);
set_exit:
	put_online_cpus();
	return ret;
}

static int get_current_power_limit(struct powercap_zone *power_zone, int id,
					u64 *data)
{
	struct rapl_domain *rd;
	u64 val;
	int prim;
	int ret = 0;

	get_online_cpus();
	rd = power_zone_to_rapl_domain(power_zone);
	switch (rd->rpl[id].prim_id) {
	case PL1_ENABLE:
		prim = POWER_LIMIT1;
		break;
	case PL2_ENABLE:
		prim = POWER_LIMIT2;
		break;
	default:
		put_online_cpus();
		return -EINVAL;
	}
	if (rapl_read_data_raw(rd, prim, true, &val))
		ret = -EIO;
	else
		*data = val;

	put_online_cpus();

	return ret;
}

static int set_time_window(struct powercap_zone *power_zone, int id,
								u64 window)
{
	struct rapl_domain *rd;
	int ret = 0;

	get_online_cpus();
	rd = power_zone_to_rapl_domain(power_zone);
	switch (rd->rpl[id].prim_id) {
	case PL1_ENABLE:
		rapl_write_data_raw(rd, TIME_WINDOW1, window);
		break;
	case PL2_ENABLE:
		rapl_write_data_raw(rd, TIME_WINDOW2, window);
		break;
	default:
		ret = -EINVAL;
	}
	put_online_cpus();
	return ret;
}

static int get_time_window(struct powercap_zone *power_zone, int id, u64 *data)
{
	struct rapl_domain *rd;
	u64 val;
	int ret = 0;

	get_online_cpus();
	rd = power_zone_to_rapl_domain(power_zone);
	switch (rd->rpl[id].prim_id) {
	case PL1_ENABLE:
		ret = rapl_read_data_raw(rd, TIME_WINDOW1, true, &val);
		break;
	case PL2_ENABLE:
		ret = rapl_read_data_raw(rd, TIME_WINDOW2, true, &val);
		break;
	default:
		put_online_cpus();
		return -EINVAL;
	}
	if (!ret)
		*data = val;
	put_online_cpus();

	return ret;
}

static const char *get_constraint_name(struct powercap_zone *power_zone, int id)
{
	struct rapl_power_limit *rpl;
	struct rapl_domain *rd;

	rd = power_zone_to_rapl_domain(power_zone);
	rpl = (struct rapl_power_limit *) &rd->rpl[id];

	return rpl->name;
}


static int get_max_power(struct powercap_zone *power_zone, int id,
					u64 *data)
{
	struct rapl_domain *rd;
	u64 val;
	int prim;
	int ret = 0;

	get_online_cpus();
	rd = power_zone_to_rapl_domain(power_zone);
	switch (rd->rpl[id].prim_id) {
	case PL1_ENABLE:
		prim = THERMAL_SPEC_POWER;
		break;
	case PL2_ENABLE:
		prim = MAX_POWER;
		break;
	default:
		put_online_cpus();
		return -EINVAL;
	}
	if (rapl_read_data_raw(rd, prim, true, &val))
		ret = -EIO;
	else
		*data = val;

	put_online_cpus();

	return ret;
}

static struct powercap_zone_constraint_ops constraint_ops = {
	.set_power_limit_uw = set_power_limit,
	.get_power_limit_uw = get_current_power_limit,
	.set_time_window_us = set_time_window,
	.get_time_window_us = get_time_window,
	.get_max_power_uw = get_max_power,
	.get_name = get_constraint_name,
};

/* called after domain detection and package level data are set */
static void rapl_init_domains(struct rapl_package *rp)
{
	int i;
	struct rapl_domain *rd = rp->domains;

	for (i = 0; i < RAPL_DOMAIN_MAX; i++) {
		unsigned int mask = rp->domain_map & (1 << i);
		switch (mask) {
		case BIT(RAPL_DOMAIN_PACKAGE):
			rd->name = rapl_domain_names[RAPL_DOMAIN_PACKAGE];
			rd->id = RAPL_DOMAIN_PACKAGE;
			rd->msrs[0] = MSR_PKG_POWER_LIMIT;
			rd->msrs[1] = MSR_PKG_ENERGY_STATUS;
			rd->msrs[2] = MSR_PKG_PERF_STATUS;
			rd->msrs[3] = 0;
			rd->msrs[4] = MSR_PKG_POWER_INFO;
			rd->rpl[0].prim_id = PL1_ENABLE;
			rd->rpl[0].name = pl1_name;
			rd->rpl[1].prim_id = PL2_ENABLE;
			rd->rpl[1].name = pl2_name;
			break;
		case BIT(RAPL_DOMAIN_PP0):
			rd->name = rapl_domain_names[RAPL_DOMAIN_PP0];
			rd->id = RAPL_DOMAIN_PP0;
			rd->msrs[0] = MSR_PP0_POWER_LIMIT;
			rd->msrs[1] = MSR_PP0_ENERGY_STATUS;
			rd->msrs[2] = 0;
			rd->msrs[3] = MSR_PP0_POLICY;
			rd->msrs[4] = 0;
			rd->rpl[0].prim_id = PL1_ENABLE;
			rd->rpl[0].name = pl1_name;
			break;
		case BIT(RAPL_DOMAIN_PP1):
			rd->name = rapl_domain_names[RAPL_DOMAIN_PP1];
			rd->id = RAPL_DOMAIN_PP1;
			rd->msrs[0] = MSR_PP1_POWER_LIMIT;
			rd->msrs[1] = MSR_PP1_ENERGY_STATUS;
			rd->msrs[2] = 0;
			rd->msrs[3] = MSR_PP1_POLICY;
			rd->msrs[4] = 0;
			rd->rpl[0].prim_id = PL1_ENABLE;
			rd->rpl[0].name = pl1_name;
			break;
		case BIT(RAPL_DOMAIN_DRAM):
			rd->name = rapl_domain_names[RAPL_DOMAIN_DRAM];
			rd->id = RAPL_DOMAIN_DRAM;
			rd->msrs[0] = MSR_DRAM_POWER_LIMIT;
			rd->msrs[1] = MSR_DRAM_ENERGY_STATUS;
			rd->msrs[2] = MSR_DRAM_PERF_STATUS;
			rd->msrs[3] = 0;
			rd->msrs[4] = MSR_DRAM_POWER_INFO;
			rd->rpl[0].prim_id = PL1_ENABLE;
			rd->rpl[0].name = pl1_name;
			break;
		}
		if (mask) {
			rd->package_id = rp->id;
			rd++;
		}
	}
}

static u64 rapl_unit_xlate(int package, enum unit_type type, u64 value,
			int to_raw)
{
	u64 divisor = 1;
	int scale = 1; /* scale to user friendly data without floating point */
	u64 f, y; /* fraction and exp. used for time unit */
	struct rapl_package *rp;

	rp = find_package_by_id(package);
	if (!rp)
		return value;

	switch (type) {
	case POWER_UNIT:
		divisor = rp->power_unit_divisor;
		scale = POWER_UNIT_SCALE;
		break;
	case ENERGY_UNIT:
		scale = ENERGY_UNIT_SCALE;
		divisor = rp->energy_unit_divisor;
		break;
	case TIME_UNIT:
		divisor = rp->time_unit_divisor;
		scale = TIME_UNIT_SCALE;
		/* special processing based on 2^Y*(1+F)/4 = val/divisor, refer
		 * to Intel Software Developer's manual Vol. 3a, CH 14.7.4.
		 */
		if (!to_raw) {
			f = (value & 0x60) >> 5;
			y = value & 0x1f;
			value = (1 << y) * (4 + f) * scale / 4;
			return div64_u64(value, divisor);
		} else {
			do_div(value, scale);
			value *= divisor;
			y = ilog2(value);
			f = div64_u64(4 * (value - (1 << y)), 1 << y);
			value = (y & 0x1f) | ((f & 0x3) << 5);
			return value;
		}
		break;
	case ARBITRARY_UNIT:
	default:
		return value;
	};

	if (to_raw)
		return div64_u64(value * divisor, scale);
	else
		return div64_u64(value * scale, divisor);
}

/* in the order of enum rapl_primitives */
static struct rapl_primitive_info rpi[] = {
	/* name, mask, shift, msr index, unit divisor */
	PRIMITIVE_INFO_INIT(ENERGY_COUNTER, ENERGY_STATUS_MASK, 0,
				RAPL_DOMAIN_MSR_STATUS, ENERGY_UNIT, 0),
	PRIMITIVE_INFO_INIT(POWER_LIMIT1, POWER_LIMIT1_MASK, 0,
				RAPL_DOMAIN_MSR_LIMIT, POWER_UNIT, 0),
	PRIMITIVE_INFO_INIT(POWER_LIMIT2, POWER_LIMIT2_MASK, 32,
				RAPL_DOMAIN_MSR_LIMIT, POWER_UNIT, 0),
	PRIMITIVE_INFO_INIT(FW_LOCK, POWER_PP_LOCK, 31,
				RAPL_DOMAIN_MSR_LIMIT, ARBITRARY_UNIT, 0),
	PRIMITIVE_INFO_INIT(PL1_ENABLE, POWER_LIMIT1_ENABLE, 15,
				RAPL_DOMAIN_MSR_LIMIT, ARBITRARY_UNIT, 0),
	PRIMITIVE_INFO_INIT(PL1_CLAMP, POWER_LIMIT1_CLAMP, 16,
				RAPL_DOMAIN_MSR_LIMIT, ARBITRARY_UNIT, 0),
	PRIMITIVE_INFO_INIT(PL2_ENABLE, POWER_LIMIT2_ENABLE, 47,
				RAPL_DOMAIN_MSR_LIMIT, ARBITRARY_UNIT, 0),
	PRIMITIVE_INFO_INIT(PL2_CLAMP, POWER_LIMIT2_CLAMP, 48,
				RAPL_DOMAIN_MSR_LIMIT, ARBITRARY_UNIT, 0),
	PRIMITIVE_INFO_INIT(TIME_WINDOW1, TIME_WINDOW1_MASK, 17,
				RAPL_DOMAIN_MSR_LIMIT, TIME_UNIT, 0),
	PRIMITIVE_INFO_INIT(TIME_WINDOW2, TIME_WINDOW2_MASK, 49,
				RAPL_DOMAIN_MSR_LIMIT, TIME_UNIT, 0),
	PRIMITIVE_INFO_INIT(THERMAL_SPEC_POWER, POWER_INFO_THERMAL_SPEC_MASK,
				0, RAPL_DOMAIN_MSR_INFO, POWER_UNIT, 0),
	PRIMITIVE_INFO_INIT(MAX_POWER, POWER_INFO_MAX_MASK, 32,
				RAPL_DOMAIN_MSR_INFO, POWER_UNIT, 0),
	PRIMITIVE_INFO_INIT(MIN_POWER, POWER_INFO_MIN_MASK, 16,
				RAPL_DOMAIN_MSR_INFO, POWER_UNIT, 0),
	PRIMITIVE_INFO_INIT(MAX_TIME_WINDOW, POWER_INFO_MAX_TIME_WIN_MASK, 48,
				RAPL_DOMAIN_MSR_INFO, TIME_UNIT, 0),
	PRIMITIVE_INFO_INIT(THROTTLED_TIME, PERF_STATUS_THROTTLE_TIME_MASK, 0,
				RAPL_DOMAIN_MSR_PERF, TIME_UNIT, 0),
	PRIMITIVE_INFO_INIT(PRIORITY_LEVEL, PP_POLICY_MASK, 0,
				RAPL_DOMAIN_MSR_POLICY, ARBITRARY_UNIT, 0),
	/* non-hardware */
	PRIMITIVE_INFO_INIT(AVERAGE_POWER, 0, 0, 0, POWER_UNIT,
				RAPL_PRIMITIVE_DERIVED),
	{NULL, 0, 0, 0},
};

/* Read primitive data based on its related struct rapl_primitive_info.
 * if xlate flag is set, return translated data based on data units, i.e.
 * time, energy, and power.
 * RAPL MSRs are non-architectual and are laid out not consistently across
 * domains. Here we use primitive info to allow writing consolidated access
 * functions.
 * For a given primitive, it is processed by MSR mask and shift. Unit conversion
 * is pre-assigned based on RAPL unit MSRs read at init time.
 * 63-------------------------- 31--------------------------- 0
 * |                           xxxxx (mask)                   |
 * |                                |<- shift ----------------|
 * 63-------------------------- 31--------------------------- 0
 */
static int rapl_read_data_raw(struct rapl_domain *rd,
			enum rapl_primitives prim,
			bool xlate, u64 *data)
{
	u64 value, final;
	u32 msr;
	struct rapl_primitive_info *rp = &rpi[prim];
	int cpu;

	if (!rp->name || rp->flag & RAPL_PRIMITIVE_DUMMY)
		return -EINVAL;

	msr = rd->msrs[rp->id];
	if (!msr)
		return -EINVAL;
	/* use physical package id to look up active cpus */
	cpu = find_active_cpu_on_package(rd->package_id);
	if (cpu < 0)
		return cpu;

	/* special-case package domain, which uses a different bit*/
	if (prim == FW_LOCK && rd->id == RAPL_DOMAIN_PACKAGE) {
		rp->mask = POWER_PACKAGE_LOCK;
		rp->shift = 63;
	}
	/* non-hardware data are collected by the polling thread */
	if (rp->flag & RAPL_PRIMITIVE_DERIVED) {
		*data = rd->rdd.primitives[prim];
		return 0;
	}

	if (rdmsrl_safe_on_cpu(cpu, msr, &value)) {
		pr_debug("failed to read msr 0x%x on cpu %d\n", msr, cpu);
		return -EIO;
	}

	final = value & rp->mask;
	final = final >> rp->shift;
	if (xlate)
		*data = rapl_unit_xlate(rd->package_id, rp->unit, final, 0);
	else
		*data = final;

	return 0;
}

/* Similar use of primitive info in the read counterpart */
static int rapl_write_data_raw(struct rapl_domain *rd,
			enum rapl_primitives prim,
			unsigned long long value)
{
	u64 msr_val;
	u32 msr;
	struct rapl_primitive_info *rp = &rpi[prim];
	int cpu;

	cpu = find_active_cpu_on_package(rd->package_id);
	if (cpu < 0)
		return cpu;
	msr = rd->msrs[rp->id];
	if (rdmsrl_safe_on_cpu(cpu, msr, &msr_val)) {
		dev_dbg(&rd->power_zone.dev,
			"failed to read msr 0x%x on cpu %d\n", msr, cpu);
		return -EIO;
	}
	value = rapl_unit_xlate(rd->package_id, rp->unit, value, 1);
	msr_val &= ~rp->mask;
	msr_val |= value << rp->shift;
	if (wrmsrl_safe_on_cpu(cpu, msr, msr_val)) {
		dev_dbg(&rd->power_zone.dev,
			"failed to write msr 0x%x on cpu %d\n", msr, cpu);
		return -EIO;
	}

	return 0;
}

static const struct x86_cpu_id energy_unit_quirk_ids[] = {
	{ X86_VENDOR_INTEL, 6, 0x37},/* VLV */
	{}
};

static int rapl_check_unit(struct rapl_package *rp, int cpu)
{
	u64 msr_val;
	u32 value;

	if (rdmsrl_safe_on_cpu(cpu, MSR_RAPL_POWER_UNIT, &msr_val)) {
		pr_err("Failed to read power unit MSR 0x%x on CPU %d, exit.\n",
			MSR_RAPL_POWER_UNIT, cpu);
		return -ENODEV;
	}

	/* Raw RAPL data stored in MSRs are in certain scales. We need to
	 * convert them into standard units based on the divisors reported in
	 * the RAPL unit MSRs.
	 * i.e.
	 * energy unit: 1/enery_unit_divisor Joules
	 * power unit: 1/power_unit_divisor Watts
	 * time unit: 1/time_unit_divisor Seconds
	 */
	value = (msr_val & ENERGY_UNIT_MASK) >> ENERGY_UNIT_OFFSET;
	/* some CPUs have different way to calculate energy unit */
	if (x86_match_cpu(energy_unit_quirk_ids))
		rp->energy_unit_divisor = 1000000 / (1 << value);
	else
		rp->energy_unit_divisor = 1 << value;

	value = (msr_val & POWER_UNIT_MASK) >> POWER_UNIT_OFFSET;
	rp->power_unit_divisor = 1 << value;

	value = (msr_val & TIME_UNIT_MASK) >> TIME_UNIT_OFFSET;
	rp->time_unit_divisor = 1 << value;

	pr_debug("Physical package %d units: energy=%d, time=%d, power=%d\n",
		rp->id,
		rp->energy_unit_divisor,
		rp->time_unit_divisor,
		rp->power_unit_divisor);

	return 0;
}

/* REVISIT:
 * When package power limit is set artificially low by RAPL, LVT
 * thermal interrupt for package power limit should be ignored
 * since we are not really exceeding the real limit. The intention
 * is to avoid excessive interrupts while we are trying to save power.
 * A useful feature might be routing the package_power_limit interrupt
 * to userspace via eventfd. once we have a usecase, this is simple
 * to do by adding an atomic notifier.
 */

static void package_power_limit_irq_save(int package_id)
{
	u32 l, h = 0;
	int cpu;
	struct rapl_package *rp;

	rp = find_package_by_id(package_id);
	if (!rp)
		return;

	if (!boot_cpu_has(X86_FEATURE_PTS) || !boot_cpu_has(X86_FEATURE_PLN))
		return;

	cpu = find_active_cpu_on_package(package_id);
	if (cpu < 0)
		return;
	/* save the state of PLN irq mask bit before disabling it */
	rdmsr_safe_on_cpu(cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT, &l, &h);
	if (!(rp->power_limit_irq & PACKAGE_PLN_INT_SAVED)) {
		rp->power_limit_irq = l & PACKAGE_THERM_INT_PLN_ENABLE;
		rp->power_limit_irq |= PACKAGE_PLN_INT_SAVED;
	}
	l &= ~PACKAGE_THERM_INT_PLN_ENABLE;
	wrmsr_on_cpu(cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT, l, h);
}

/* restore per package power limit interrupt enable state */
static void package_power_limit_irq_restore(int package_id)
{
	u32 l, h;
	int cpu;
	struct rapl_package *rp;

	rp = find_package_by_id(package_id);
	if (!rp)
		return;

	if (!boot_cpu_has(X86_FEATURE_PTS) || !boot_cpu_has(X86_FEATURE_PLN))
		return;

	cpu = find_active_cpu_on_package(package_id);
	if (cpu < 0)
		return;

	/* irq enable state not saved, nothing to restore */
	if (!(rp->power_limit_irq & PACKAGE_PLN_INT_SAVED))
		return;
	rdmsr_safe_on_cpu(cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT, &l, &h);

	if (rp->power_limit_irq & PACKAGE_THERM_INT_PLN_ENABLE)
		l |= PACKAGE_THERM_INT_PLN_ENABLE;
	else
		l &= ~PACKAGE_THERM_INT_PLN_ENABLE;

	wrmsr_on_cpu(cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT, l, h);
}

static const struct x86_cpu_id rapl_ids[] = {
	{ X86_VENDOR_INTEL, 6, 0x2a},/* SNB */
	{ X86_VENDOR_INTEL, 6, 0x2d},/* SNB EP */
	{ X86_VENDOR_INTEL, 6, 0x37},/* VLV */
	{ X86_VENDOR_INTEL, 6, 0x3a},/* IVB */
	{ X86_VENDOR_INTEL, 6, 0x45},/* HSW */
	/* TODO: Add more CPU IDs after testing */
	{}
};
MODULE_DEVICE_TABLE(x86cpu, rapl_ids);

/* read once for all raw primitive data for all packages, domains */
static void rapl_update_domain_data(void)
{
	int dmn, prim;
	u64 val;
	struct rapl_package *rp;

	list_for_each_entry(rp, &rapl_packages, plist) {
		for (dmn = 0; dmn < rp->nr_domains; dmn++) {
			pr_debug("update package %d domain %s data\n", rp->id,
				rp->domains[dmn].name);
			/* exclude non-raw primitives */
			for (prim = 0; prim < NR_RAW_PRIMITIVES; prim++)
				if (!rapl_read_data_raw(&rp->domains[dmn], prim,
								rpi[prim].unit,
								&val))
					rp->domains[dmn].rdd.primitives[prim] =
									val;
		}
	}

}

static int rapl_unregister_powercap(void)
{
	struct rapl_package *rp;
	struct rapl_domain *rd, *rd_package = NULL;

	/* unregister all active rapl packages from the powercap layer,
	 * hotplug lock held
	 */
	list_for_each_entry(rp, &rapl_packages, plist) {
		package_power_limit_irq_restore(rp->id);

		for (rd = rp->domains; rd < rp->domains + rp->nr_domains;
		     rd++) {
			pr_debug("remove package, undo power limit on %d: %s\n",
				rp->id, rd->name);
			rapl_write_data_raw(rd, PL1_ENABLE, 0);
			rapl_write_data_raw(rd, PL2_ENABLE, 0);
			rapl_write_data_raw(rd, PL1_CLAMP, 0);
			rapl_write_data_raw(rd, PL2_CLAMP, 0);
			if (rd->id == RAPL_DOMAIN_PACKAGE) {
				rd_package = rd;
				continue;
			}
			powercap_unregister_zone(control_type, &rd->power_zone);
		}
		/* do the package zone last */
		if (rd_package)
			powercap_unregister_zone(control_type,
						&rd_package->power_zone);
	}
	powercap_unregister_control_type(control_type);

	return 0;
}

static int rapl_package_register_powercap(struct rapl_package *rp)
{
	struct rapl_domain *rd;
	int ret = 0;
	char dev_name[17]; /* max domain name = 7 + 1 + 8 for int + 1 for null*/
	struct powercap_zone *power_zone = NULL;
	int nr_pl;

	/* first we register package domain as the parent zone*/
	for (rd = rp->domains; rd < rp->domains + rp->nr_domains; rd++) {
		if (rd->id == RAPL_DOMAIN_PACKAGE) {
			nr_pl = find_nr_power_limit(rd);
			pr_debug("register socket %d package domain %s\n",
				rp->id, rd->name);
			memset(dev_name, 0, sizeof(dev_name));
			snprintf(dev_name, sizeof(dev_name), "%s-%d",
				rd->name, rp->id);
			power_zone = powercap_register_zone(&rd->power_zone,
							control_type,
							dev_name, NULL,
							&zone_ops[rd->id],
							nr_pl,
							&constraint_ops);
			if (IS_ERR(power_zone)) {
				pr_debug("failed to register package, %d\n",
					rp->id);
				ret = PTR_ERR(power_zone);
				goto exit_package;
			}
			/* track parent zone in per package/socket data */
			rp->power_zone = power_zone;
			/* done, only one package domain per socket */
			break;
		}
	}
	if (!power_zone) {
		pr_err("no package domain found, unknown topology!\n");
		ret = -ENODEV;
		goto exit_package;
	}
	/* now register domains as children of the socket/package*/
	for (rd = rp->domains; rd < rp->domains + rp->nr_domains; rd++) {
		if (rd->id == RAPL_DOMAIN_PACKAGE)
			continue;
		/* number of power limits per domain varies */
		nr_pl = find_nr_power_limit(rd);
		power_zone = powercap_register_zone(&rd->power_zone,
						control_type, rd->name,
						rp->power_zone,
						&zone_ops[rd->id], nr_pl,
						&constraint_ops);

		if (IS_ERR(power_zone)) {
			pr_debug("failed to register power_zone, %d:%s:%s\n",
				rp->id, rd->name, dev_name);
			ret = PTR_ERR(power_zone);
			goto err_cleanup;
		}
	}

exit_package:
	return ret;
err_cleanup:
	/* clean up previously initialized domains within the package if we
	 * failed after the first domain setup.
	 */
	while (--rd >= rp->domains) {
		pr_debug("unregister package %d domain %s\n", rp->id, rd->name);
		powercap_unregister_zone(control_type, &rd->power_zone);
	}

	return ret;
}

static int rapl_register_powercap(void)
{
	struct rapl_domain *rd;
	struct rapl_package *rp;
	int ret = 0;

	control_type = powercap_register_control_type(NULL, "intel-rapl", NULL);
	if (IS_ERR(control_type)) {
		pr_debug("failed to register powercap control_type.\n");
		return PTR_ERR(control_type);
	}
	/* read the initial data */
	rapl_update_domain_data();
	list_for_each_entry(rp, &rapl_packages, plist)
		if (rapl_package_register_powercap(rp))
			goto err_cleanup_package;
	return ret;

err_cleanup_package:
	/* clean up previously initialized packages */
	list_for_each_entry_continue_reverse(rp, &rapl_packages, plist) {
		for (rd = rp->domains; rd < rp->domains + rp->nr_domains;
		     rd++) {
			pr_debug("unregister zone/package %d, %s domain\n",
				rp->id, rd->name);
			powercap_unregister_zone(control_type, &rd->power_zone);
		}
	}

	return ret;
}

static int rapl_check_domain(int cpu, int domain)
{
	unsigned msr;
	u64 val1, val2 = 0;
	int retry = 0;

	switch (domain) {
	case RAPL_DOMAIN_PACKAGE:
		msr = MSR_PKG_ENERGY_STATUS;
		break;
	case RAPL_DOMAIN_PP0:
		msr = MSR_PP0_ENERGY_STATUS;
		break;
	case RAPL_DOMAIN_PP1:
		msr = MSR_PP1_ENERGY_STATUS;
		break;
	case RAPL_DOMAIN_DRAM:
		msr = MSR_DRAM_ENERGY_STATUS;
		break;
	default:
		pr_err("invalid domain id %d\n", domain);
		return -EINVAL;
	}
	if (rdmsrl_safe_on_cpu(cpu, msr, &val1))
		return -ENODEV;

	/* energy counters roll slowly on some domains */
	while (++retry < 10) {
		usleep_range(10000, 15000);
		rdmsrl_safe_on_cpu(cpu, msr, &val2);
		if ((val1 & ENERGY_STATUS_MASK) != (val2 & ENERGY_STATUS_MASK))
			return 0;
	}
	/* if energy counter does not change, report as bad domain */
	pr_info("domain %s energy ctr %llu:%llu not working, skip\n",
		rapl_domain_names[domain], val1, val2);

	return -ENODEV;
}

/* Detect active and valid domains for the given CPU, caller must
 * ensure the CPU belongs to the targeted package and CPU hotlug is disabled.
 */
static int rapl_detect_domains(struct rapl_package *rp, int cpu)
{
	int i;
	int ret = 0;
	struct rapl_domain *rd;
	u64 locked;

	for (i = 0; i < RAPL_DOMAIN_MAX; i++) {
		/* use physical package id to read counters */
		if (!rapl_check_domain(cpu, i))
			rp->domain_map |= 1 << i;
	}
	rp->nr_domains = bitmap_weight(&rp->domain_map,	RAPL_DOMAIN_MAX);
	if (!rp->nr_domains) {
		pr_err("no valid rapl domains found in package %d\n", rp->id);
		ret = -ENODEV;
		goto done;
	}
	pr_debug("found %d domains on package %d\n", rp->nr_domains, rp->id);

	rp->domains = kcalloc(rp->nr_domains + 1, sizeof(struct rapl_domain),
			GFP_KERNEL);
	if (!rp->domains) {
		ret = -ENOMEM;
		goto done;
	}
	rapl_init_domains(rp);

	for (rd = rp->domains; rd < rp->domains + rp->nr_domains; rd++) {
		/* check if the domain is locked by BIOS */
		if (rapl_read_data_raw(rd, FW_LOCK, false, &locked)) {
			pr_info("RAPL package %d domain %s locked by BIOS\n",
				rp->id, rd->name);
				rd->state |= DOMAIN_STATE_BIOS_LOCKED;
		}
	}


done:
	return ret;
}

static bool is_package_new(int package)
{
	struct rapl_package *rp;

	/* caller prevents cpu hotplug, there will be no new packages added
	 * or deleted while traversing the package list, no need for locking.
	 */
	list_for_each_entry(rp, &rapl_packages, plist)
		if (package == rp->id)
			return false;

	return true;
}

/* RAPL interface can be made of a two-level hierarchy: package level and domain
 * level. We first detect the number of packages then domains of each package.
 * We have to consider the possiblity of CPU online/offline due to hotplug and
 * other scenarios.
 */
static int rapl_detect_topology(void)
{
	int i;
	int phy_package_id;
	struct rapl_package *new_package, *rp;

	for_each_online_cpu(i) {
		phy_package_id = topology_physical_package_id(i);
		if (is_package_new(phy_package_id)) {
			new_package = kzalloc(sizeof(*rp), GFP_KERNEL);
			if (!new_package) {
				rapl_cleanup_data();
				return -ENOMEM;
			}
			/* add the new package to the list */
			new_package->id = phy_package_id;
			new_package->nr_cpus = 1;

			/* check if the package contains valid domains */
			if (rapl_detect_domains(new_package, i) ||
				rapl_check_unit(new_package, i)) {
				kfree(new_package->domains);
				kfree(new_package);
				/* free up the packages already initialized */
				rapl_cleanup_data();
				return -ENODEV;
			}
			INIT_LIST_HEAD(&new_package->plist);
			list_add(&new_package->plist, &rapl_packages);
		} else {
			rp = find_package_by_id(phy_package_id);
			if (rp)
				++rp->nr_cpus;
		}
	}

	return 0;
}

/* called from CPU hotplug notifier, hotplug lock held */
static void rapl_remove_package(struct rapl_package *rp)
{
	struct rapl_domain *rd, *rd_package = NULL;

	for (rd = rp->domains; rd < rp->domains + rp->nr_domains; rd++) {
		if (rd->id == RAPL_DOMAIN_PACKAGE) {
			rd_package = rd;
			continue;
		}
		pr_debug("remove package %d, %s domain\n", rp->id, rd->name);
		powercap_unregister_zone(control_type, &rd->power_zone);
	}
	/* do parent zone last */
	powercap_unregister_zone(control_type, &rd_package->power_zone);
	list_del(&rp->plist);
	kfree(rp);
}

/* called from CPU hotplug notifier, hotplug lock held */
static int rapl_add_package(int cpu)
{
	int ret = 0;
	int phy_package_id;
	struct rapl_package *rp;

	phy_package_id = topology_physical_package_id(cpu);
	rp = kzalloc(sizeof(struct rapl_package), GFP_KERNEL);
	if (!rp)
		return -ENOMEM;

	/* add the new package to the list */
	rp->id = phy_package_id;
	rp->nr_cpus = 1;
	/* check if the package contains valid domains */
	if (rapl_detect_domains(rp, cpu) ||
		rapl_check_unit(rp, cpu)) {
		ret = -ENODEV;
		goto err_free_package;
	}
	if (!rapl_package_register_powercap(rp)) {
		INIT_LIST_HEAD(&rp->plist);
		list_add(&rp->plist, &rapl_packages);
		return ret;
	}

err_free_package:
	kfree(rp->domains);
	kfree(rp);

	return ret;
}

/* Handles CPU hotplug on multi-socket systems.
 * If a CPU goes online as the first CPU of the physical package
 * we add the RAPL package to the system. Similarly, when the last
 * CPU of the package is removed, we remove the RAPL package and its
 * associated domains. Cooling devices are handled accordingly at
 * per-domain level.
 */
static int rapl_cpu_callback(struct notifier_block *nfb,
				unsigned long action, void *hcpu)
{
	unsigned long cpu = (unsigned long)hcpu;
	int phy_package_id;
	struct rapl_package *rp;

	phy_package_id = topology_physical_package_id(cpu);
	switch (action) {
	case CPU_ONLINE:
	case CPU_ONLINE_FROZEN:
	case CPU_DOWN_FAILED:
	case CPU_DOWN_FAILED_FROZEN:
		rp = find_package_by_id(phy_package_id);
		if (rp)
			++rp->nr_cpus;
		else
			rapl_add_package(cpu);
		break;
	case CPU_DOWN_PREPARE:
	case CPU_DOWN_PREPARE_FROZEN:
		rp = find_package_by_id(phy_package_id);
		if (!rp)
			break;
		if (--rp->nr_cpus == 0)
			rapl_remove_package(rp);
	}

	return NOTIFY_OK;
}

static struct notifier_block rapl_cpu_notifier = {
	.notifier_call = rapl_cpu_callback,
};

static int __init rapl_init(void)
{
	int ret = 0;

	if (!x86_match_cpu(rapl_ids)) {
		pr_err("driver does not support CPU family %d model %d\n",
			boot_cpu_data.x86, boot_cpu_data.x86_model);

		return -ENODEV;
	}
	/* prevent CPU hotplug during detection */
	get_online_cpus();
	ret = rapl_detect_topology();
	if (ret)
		goto done;

	if (rapl_register_powercap()) {
		rapl_cleanup_data();
		ret = -ENODEV;
		goto done;
	}
	register_hotcpu_notifier(&rapl_cpu_notifier);
done:
	put_online_cpus();

	return ret;
}

static void __exit rapl_exit(void)
{
	get_online_cpus();
	unregister_hotcpu_notifier(&rapl_cpu_notifier);
	rapl_unregister_powercap();
	rapl_cleanup_data();
	put_online_cpus();
}

module_init(rapl_init);
module_exit(rapl_exit);

MODULE_DESCRIPTION("Driver for Intel RAPL (Running Average Power Limit)");
MODULE_AUTHOR("Jacob Pan <jacob.jun.pan@intel.com>");
MODULE_LICENSE("GPL v2");