dma-debug.c 44.2 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 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
/*
 * Copyright (C) 2008 Advanced Micro Devices, Inc.
 *
 * Author: Joerg Roedel <joerg.roedel@amd.com>
 *
 * 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.
 *
 * This program is distributed in the hope that 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., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
 */

#include <linux/sched/task_stack.h>
#include <linux/scatterlist.h>
#include <linux/dma-mapping.h>
#include <linux/sched/task.h>
#include <linux/stacktrace.h>
#include <linux/dma-debug.h>
#include <linux/spinlock.h>
#include <linux/vmalloc.h>
#include <linux/debugfs.h>
#include <linux/uaccess.h>
#include <linux/export.h>
#include <linux/device.h>
#include <linux/types.h>
#include <linux/sched.h>
#include <linux/ctype.h>
#include <linux/list.h>
#include <linux/slab.h>

#include <asm/sections.h>

#define HASH_SIZE       1024ULL
#define HASH_FN_SHIFT   13
#define HASH_FN_MASK    (HASH_SIZE - 1)

enum {
	dma_debug_single,
	dma_debug_page,
	dma_debug_sg,
	dma_debug_coherent,
	dma_debug_resource,
};

enum map_err_types {
	MAP_ERR_CHECK_NOT_APPLICABLE,
	MAP_ERR_NOT_CHECKED,
	MAP_ERR_CHECKED,
};

#define DMA_DEBUG_STACKTRACE_ENTRIES 5

/**
 * struct dma_debug_entry - track a dma_map* or dma_alloc_coherent mapping
 * @list: node on pre-allocated free_entries list
 * @dev: 'dev' argument to dma_map_{page|single|sg} or dma_alloc_coherent
 * @type: single, page, sg, coherent
 * @pfn: page frame of the start address
 * @offset: offset of mapping relative to pfn
 * @size: length of the mapping
 * @direction: enum dma_data_direction
 * @sg_call_ents: 'nents' from dma_map_sg
 * @sg_mapped_ents: 'mapped_ents' from dma_map_sg
 * @map_err_type: track whether dma_mapping_error() was checked
 * @stacktrace: support backtraces when a violation is detected
 */
struct dma_debug_entry {
	struct list_head list;
	struct device    *dev;
	int              type;
	unsigned long	 pfn;
	size_t		 offset;
	u64              dev_addr;
	u64              size;
	int              direction;
	int		 sg_call_ents;
	int		 sg_mapped_ents;
	enum map_err_types  map_err_type;
#ifdef CONFIG_STACKTRACE
	struct		 stack_trace stacktrace;
	unsigned long	 st_entries[DMA_DEBUG_STACKTRACE_ENTRIES];
#endif
};

typedef bool (*match_fn)(struct dma_debug_entry *, struct dma_debug_entry *);

struct hash_bucket {
	struct list_head list;
	spinlock_t lock;
} ____cacheline_aligned_in_smp;

/* Hash list to save the allocated dma addresses */
static struct hash_bucket dma_entry_hash[HASH_SIZE];
/* List of pre-allocated dma_debug_entry's */
static LIST_HEAD(free_entries);
/* Lock for the list above */
static DEFINE_SPINLOCK(free_entries_lock);

/* Global disable flag - will be set in case of an error */
static bool global_disable __read_mostly;

/* Early initialization disable flag, set at the end of dma_debug_init */
static bool dma_debug_initialized __read_mostly;

static inline bool dma_debug_disabled(void)
{
	return global_disable || !dma_debug_initialized;
}

/* Global error count */
static u32 error_count;

/* Global error show enable*/
static u32 show_all_errors __read_mostly;
/* Number of errors to show */
static u32 show_num_errors = 1;

static u32 num_free_entries;
static u32 min_free_entries;
static u32 nr_total_entries;

/* number of preallocated entries requested by kernel cmdline */
static u32 req_entries;

/* debugfs dentry's for the stuff above */
static struct dentry *dma_debug_dent        __read_mostly;
static struct dentry *global_disable_dent   __read_mostly;
static struct dentry *error_count_dent      __read_mostly;
static struct dentry *show_all_errors_dent  __read_mostly;
static struct dentry *show_num_errors_dent  __read_mostly;
static struct dentry *num_free_entries_dent __read_mostly;
static struct dentry *min_free_entries_dent __read_mostly;
static struct dentry *filter_dent           __read_mostly;

/* per-driver filter related state */

#define NAME_MAX_LEN	64

static char                  current_driver_name[NAME_MAX_LEN] __read_mostly;
static struct device_driver *current_driver                    __read_mostly;

static DEFINE_RWLOCK(driver_name_lock);

static const char *const maperr2str[] = {
	[MAP_ERR_CHECK_NOT_APPLICABLE] = "dma map error check not applicable",
	[MAP_ERR_NOT_CHECKED] = "dma map error not checked",
	[MAP_ERR_CHECKED] = "dma map error checked",
};

static const char *type2name[5] = { "single", "page",
				    "scather-gather", "coherent",
				    "resource" };

static const char *dir2name[4] = { "DMA_BIDIRECTIONAL", "DMA_TO_DEVICE",
				   "DMA_FROM_DEVICE", "DMA_NONE" };

/*
 * The access to some variables in this macro is racy. We can't use atomic_t
 * here because all these variables are exported to debugfs. Some of them even
 * writeable. This is also the reason why a lock won't help much. But anyway,
 * the races are no big deal. Here is why:
 *
 *   error_count: the addition is racy, but the worst thing that can happen is
 *                that we don't count some errors
 *   show_num_errors: the subtraction is racy. Also no big deal because in
 *                    worst case this will result in one warning more in the
 *                    system log than the user configured. This variable is
 *                    writeable via debugfs.
 */
static inline void dump_entry_trace(struct dma_debug_entry *entry)
{
#ifdef CONFIG_STACKTRACE
	if (entry) {
		pr_warning("Mapped at:\n");
		print_stack_trace(&entry->stacktrace, 0);
	}
#endif
}

static bool driver_filter(struct device *dev)
{
	struct device_driver *drv;
	unsigned long flags;
	bool ret;

	/* driver filter off */
	if (likely(!current_driver_name[0]))
		return true;

	/* driver filter on and initialized */
	if (current_driver && dev && dev->driver == current_driver)
		return true;

	/* driver filter on, but we can't filter on a NULL device... */
	if (!dev)
		return false;

	if (current_driver || !current_driver_name[0])
		return false;

	/* driver filter on but not yet initialized */
	drv = dev->driver;
	if (!drv)
		return false;

	/* lock to protect against change of current_driver_name */
	read_lock_irqsave(&driver_name_lock, flags);

	ret = false;
	if (drv->name &&
	    strncmp(current_driver_name, drv->name, NAME_MAX_LEN - 1) == 0) {
		current_driver = drv;
		ret = true;
	}

	read_unlock_irqrestore(&driver_name_lock, flags);

	return ret;
}

#define err_printk(dev, entry, format, arg...) do {			\
		error_count += 1;					\
		if (driver_filter(dev) &&				\
		    (show_all_errors || show_num_errors > 0)) {		\
			WARN(1, "%s %s: " format,			\
			     dev ? dev_driver_string(dev) : "NULL",	\
			     dev ? dev_name(dev) : "NULL", ## arg);	\
			dump_entry_trace(entry);			\
		}							\
		if (!show_all_errors && show_num_errors > 0)		\
			show_num_errors -= 1;				\
	} while (0);

/*
 * Hash related functions
 *
 * Every DMA-API request is saved into a struct dma_debug_entry. To
 * have quick access to these structs they are stored into a hash.
 */
static int hash_fn(struct dma_debug_entry *entry)
{
	/*
	 * Hash function is based on the dma address.
	 * We use bits 20-27 here as the index into the hash
	 */
	return (entry->dev_addr >> HASH_FN_SHIFT) & HASH_FN_MASK;
}

/*
 * Request exclusive access to a hash bucket for a given dma_debug_entry.
 */
static struct hash_bucket *get_hash_bucket(struct dma_debug_entry *entry,
					   unsigned long *flags)
	__acquires(&dma_entry_hash[idx].lock)
{
	int idx = hash_fn(entry);
	unsigned long __flags;

	spin_lock_irqsave(&dma_entry_hash[idx].lock, __flags);
	*flags = __flags;
	return &dma_entry_hash[idx];
}

/*
 * Give up exclusive access to the hash bucket
 */
static void put_hash_bucket(struct hash_bucket *bucket,
			    unsigned long *flags)
	__releases(&bucket->lock)
{
	unsigned long __flags = *flags;

	spin_unlock_irqrestore(&bucket->lock, __flags);
}

static bool exact_match(struct dma_debug_entry *a, struct dma_debug_entry *b)
{
	return ((a->dev_addr == b->dev_addr) &&
		(a->dev == b->dev)) ? true : false;
}

static bool containing_match(struct dma_debug_entry *a,
			     struct dma_debug_entry *b)
{
	if (a->dev != b->dev)
		return false;

	if ((b->dev_addr <= a->dev_addr) &&
	    ((b->dev_addr + b->size) >= (a->dev_addr + a->size)))
		return true;

	return false;
}

/*
 * Search a given entry in the hash bucket list
 */
static struct dma_debug_entry *__hash_bucket_find(struct hash_bucket *bucket,
						  struct dma_debug_entry *ref,
						  match_fn match)
{
	struct dma_debug_entry *entry, *ret = NULL;
	int matches = 0, match_lvl, last_lvl = -1;

	list_for_each_entry(entry, &bucket->list, list) {
		if (!match(ref, entry))
			continue;

		/*
		 * Some drivers map the same physical address multiple
		 * times. Without a hardware IOMMU this results in the
		 * same device addresses being put into the dma-debug
		 * hash multiple times too. This can result in false
		 * positives being reported. Therefore we implement a
		 * best-fit algorithm here which returns the entry from
		 * the hash which fits best to the reference value
		 * instead of the first-fit.
		 */
		matches += 1;
		match_lvl = 0;
		entry->size         == ref->size         ? ++match_lvl : 0;
		entry->type         == ref->type         ? ++match_lvl : 0;
		entry->direction    == ref->direction    ? ++match_lvl : 0;
		entry->sg_call_ents == ref->sg_call_ents ? ++match_lvl : 0;

		if (match_lvl == 4) {
			/* perfect-fit - return the result */
			return entry;
		} else if (match_lvl > last_lvl) {
			/*
			 * We found an entry that fits better then the
			 * previous one or it is the 1st match.
			 */
			last_lvl = match_lvl;
			ret      = entry;
		}
	}

	/*
	 * If we have multiple matches but no perfect-fit, just return
	 * NULL.
	 */
	ret = (matches == 1) ? ret : NULL;

	return ret;
}

static struct dma_debug_entry *bucket_find_exact(struct hash_bucket *bucket,
						 struct dma_debug_entry *ref)
{
	return __hash_bucket_find(bucket, ref, exact_match);
}

static struct dma_debug_entry *bucket_find_contain(struct hash_bucket **bucket,
						   struct dma_debug_entry *ref,
						   unsigned long *flags)
{

	unsigned int max_range = dma_get_max_seg_size(ref->dev);
	struct dma_debug_entry *entry, index = *ref;
	unsigned int range = 0;

	while (range <= max_range) {
		entry = __hash_bucket_find(*bucket, ref, containing_match);

		if (entry)
			return entry;

		/*
		 * Nothing found, go back a hash bucket
		 */
		put_hash_bucket(*bucket, flags);
		range          += (1 << HASH_FN_SHIFT);
		index.dev_addr -= (1 << HASH_FN_SHIFT);
		*bucket = get_hash_bucket(&index, flags);
	}

	return NULL;
}

/*
 * Add an entry to a hash bucket
 */
static void hash_bucket_add(struct hash_bucket *bucket,
			    struct dma_debug_entry *entry)
{
	list_add_tail(&entry->list, &bucket->list);
}

/*
 * Remove entry from a hash bucket list
 */
static void hash_bucket_del(struct dma_debug_entry *entry)
{
	list_del(&entry->list);
}

static unsigned long long phys_addr(struct dma_debug_entry *entry)
{
	if (entry->type == dma_debug_resource)
		return __pfn_to_phys(entry->pfn) + entry->offset;

	return page_to_phys(pfn_to_page(entry->pfn)) + entry->offset;
}

/*
 * Dump mapping entries for debugging purposes
 */
void debug_dma_dump_mappings(struct device *dev)
{
	int idx;

	for (idx = 0; idx < HASH_SIZE; idx++) {
		struct hash_bucket *bucket = &dma_entry_hash[idx];
		struct dma_debug_entry *entry;
		unsigned long flags;

		spin_lock_irqsave(&bucket->lock, flags);

		list_for_each_entry(entry, &bucket->list, list) {
			if (!dev || dev == entry->dev) {
				dev_info(entry->dev,
					 "%s idx %d P=%Lx N=%lx D=%Lx L=%Lx %s %s\n",
					 type2name[entry->type], idx,
					 phys_addr(entry), entry->pfn,
					 entry->dev_addr, entry->size,
					 dir2name[entry->direction],
					 maperr2str[entry->map_err_type]);
			}
		}

		spin_unlock_irqrestore(&bucket->lock, flags);
	}
}
EXPORT_SYMBOL(debug_dma_dump_mappings);

/*
 * For each mapping (initial cacheline in the case of
 * dma_alloc_coherent/dma_map_page, initial cacheline in each page of a
 * scatterlist, or the cacheline specified in dma_map_single) insert
 * into this tree using the cacheline as the key. At
 * dma_unmap_{single|sg|page} or dma_free_coherent delete the entry.  If
 * the entry already exists at insertion time add a tag as a reference
 * count for the overlapping mappings.  For now, the overlap tracking
 * just ensures that 'unmaps' balance 'maps' before marking the
 * cacheline idle, but we should also be flagging overlaps as an API
 * violation.
 *
 * Memory usage is mostly constrained by the maximum number of available
 * dma-debug entries in that we need a free dma_debug_entry before
 * inserting into the tree.  In the case of dma_map_page and
 * dma_alloc_coherent there is only one dma_debug_entry and one
 * dma_active_cacheline entry to track per event.  dma_map_sg(), on the
 * other hand, consumes a single dma_debug_entry, but inserts 'nents'
 * entries into the tree.
 *
 * At any time debug_dma_assert_idle() can be called to trigger a
 * warning if any cachelines in the given page are in the active set.
 */
static RADIX_TREE(dma_active_cacheline, GFP_NOWAIT);
static DEFINE_SPINLOCK(radix_lock);
#define ACTIVE_CACHELINE_MAX_OVERLAP ((1 << RADIX_TREE_MAX_TAGS) - 1)
#define CACHELINE_PER_PAGE_SHIFT (PAGE_SHIFT - L1_CACHE_SHIFT)
#define CACHELINES_PER_PAGE (1 << CACHELINE_PER_PAGE_SHIFT)

static phys_addr_t to_cacheline_number(struct dma_debug_entry *entry)
{
	return (entry->pfn << CACHELINE_PER_PAGE_SHIFT) +
		(entry->offset >> L1_CACHE_SHIFT);
}

static int active_cacheline_read_overlap(phys_addr_t cln)
{
	int overlap = 0, i;

	for (i = RADIX_TREE_MAX_TAGS - 1; i >= 0; i--)
		if (radix_tree_tag_get(&dma_active_cacheline, cln, i))
			overlap |= 1 << i;
	return overlap;
}

static int active_cacheline_set_overlap(phys_addr_t cln, int overlap)
{
	int i;

	if (overlap > ACTIVE_CACHELINE_MAX_OVERLAP || overlap < 0)
		return overlap;

	for (i = RADIX_TREE_MAX_TAGS - 1; i >= 0; i--)
		if (overlap & 1 << i)
			radix_tree_tag_set(&dma_active_cacheline, cln, i);
		else
			radix_tree_tag_clear(&dma_active_cacheline, cln, i);

	return overlap;
}

static void active_cacheline_inc_overlap(phys_addr_t cln)
{
	int overlap = active_cacheline_read_overlap(cln);

	overlap = active_cacheline_set_overlap(cln, ++overlap);

	/* If we overflowed the overlap counter then we're potentially
	 * leaking dma-mappings.  Otherwise, if maps and unmaps are
	 * balanced then this overflow may cause false negatives in
	 * debug_dma_assert_idle() as the cacheline may be marked idle
	 * prematurely.
	 */
	WARN_ONCE(overlap > ACTIVE_CACHELINE_MAX_OVERLAP,
		  "DMA-API: exceeded %d overlapping mappings of cacheline %pa\n",
		  ACTIVE_CACHELINE_MAX_OVERLAP, &cln);
}

static int active_cacheline_dec_overlap(phys_addr_t cln)
{
	int overlap = active_cacheline_read_overlap(cln);

	return active_cacheline_set_overlap(cln, --overlap);
}

static int active_cacheline_insert(struct dma_debug_entry *entry)
{
	phys_addr_t cln = to_cacheline_number(entry);
	unsigned long flags;
	int rc;

	/* If the device is not writing memory then we don't have any
	 * concerns about the cpu consuming stale data.  This mitigates
	 * legitimate usages of overlapping mappings.
	 */
	if (entry->direction == DMA_TO_DEVICE)
		return 0;

	spin_lock_irqsave(&radix_lock, flags);
	rc = radix_tree_insert(&dma_active_cacheline, cln, entry);
	if (rc == -EEXIST)
		active_cacheline_inc_overlap(cln);
	spin_unlock_irqrestore(&radix_lock, flags);

	return rc;
}

static void active_cacheline_remove(struct dma_debug_entry *entry)
{
	phys_addr_t cln = to_cacheline_number(entry);
	unsigned long flags;

	/* ...mirror the insert case */
	if (entry->direction == DMA_TO_DEVICE)
		return;

	spin_lock_irqsave(&radix_lock, flags);
	/* since we are counting overlaps the final put of the
	 * cacheline will occur when the overlap count is 0.
	 * active_cacheline_dec_overlap() returns -1 in that case
	 */
	if (active_cacheline_dec_overlap(cln) < 0)
		radix_tree_delete(&dma_active_cacheline, cln);
	spin_unlock_irqrestore(&radix_lock, flags);
}

/**
 * debug_dma_assert_idle() - assert that a page is not undergoing dma
 * @page: page to lookup in the dma_active_cacheline tree
 *
 * Place a call to this routine in cases where the cpu touching the page
 * before the dma completes (page is dma_unmapped) will lead to data
 * corruption.
 */
void debug_dma_assert_idle(struct page *page)
{
	static struct dma_debug_entry *ents[CACHELINES_PER_PAGE];
	struct dma_debug_entry *entry = NULL;
	void **results = (void **) &ents;
	unsigned int nents, i;
	unsigned long flags;
	phys_addr_t cln;

	if (dma_debug_disabled())
		return;

	if (!page)
		return;

	cln = (phys_addr_t) page_to_pfn(page) << CACHELINE_PER_PAGE_SHIFT;
	spin_lock_irqsave(&radix_lock, flags);
	nents = radix_tree_gang_lookup(&dma_active_cacheline, results, cln,
				       CACHELINES_PER_PAGE);
	for (i = 0; i < nents; i++) {
		phys_addr_t ent_cln = to_cacheline_number(ents[i]);

		if (ent_cln == cln) {
			entry = ents[i];
			break;
		} else if (ent_cln >= cln + CACHELINES_PER_PAGE)
			break;
	}
	spin_unlock_irqrestore(&radix_lock, flags);

	if (!entry)
		return;

	cln = to_cacheline_number(entry);
	err_printk(entry->dev, entry,
		   "DMA-API: cpu touching an active dma mapped cacheline [cln=%pa]\n",
		   &cln);
}

/*
 * Wrapper function for adding an entry to the hash.
 * This function takes care of locking itself.
 */
static void add_dma_entry(struct dma_debug_entry *entry)
{
	struct hash_bucket *bucket;
	unsigned long flags;
	int rc;

	bucket = get_hash_bucket(entry, &flags);
	hash_bucket_add(bucket, entry);
	put_hash_bucket(bucket, &flags);

	rc = active_cacheline_insert(entry);
	if (rc == -ENOMEM) {
		pr_err("DMA-API: cacheline tracking ENOMEM, dma-debug disabled\n");
		global_disable = true;
	}

	/* TODO: report -EEXIST errors here as overlapping mappings are
	 * not supported by the DMA API
	 */
}

static struct dma_debug_entry *__dma_entry_alloc(void)
{
	struct dma_debug_entry *entry;

	entry = list_entry(free_entries.next, struct dma_debug_entry, list);
	list_del(&entry->list);
	memset(entry, 0, sizeof(*entry));

	num_free_entries -= 1;
	if (num_free_entries < min_free_entries)
		min_free_entries = num_free_entries;

	return entry;
}

/* struct dma_entry allocator
 *
 * The next two functions implement the allocator for
 * struct dma_debug_entries.
 */
static struct dma_debug_entry *dma_entry_alloc(void)
{
	struct dma_debug_entry *entry;
	unsigned long flags;

	spin_lock_irqsave(&free_entries_lock, flags);

	if (list_empty(&free_entries)) {
		global_disable = true;
		spin_unlock_irqrestore(&free_entries_lock, flags);
		pr_err("DMA-API: debugging out of memory - disabling\n");
		return NULL;
	}

	entry = __dma_entry_alloc();

	spin_unlock_irqrestore(&free_entries_lock, flags);

#ifdef CONFIG_STACKTRACE
	entry->stacktrace.max_entries = DMA_DEBUG_STACKTRACE_ENTRIES;
	entry->stacktrace.entries = entry->st_entries;
	entry->stacktrace.skip = 2;
	save_stack_trace(&entry->stacktrace);
#endif

	return entry;
}

static void dma_entry_free(struct dma_debug_entry *entry)
{
	unsigned long flags;

	active_cacheline_remove(entry);

	/*
	 * add to beginning of the list - this way the entries are
	 * more likely cache hot when they are reallocated.
	 */
	spin_lock_irqsave(&free_entries_lock, flags);
	list_add(&entry->list, &free_entries);
	num_free_entries += 1;
	spin_unlock_irqrestore(&free_entries_lock, flags);
}

int dma_debug_resize_entries(u32 num_entries)
{
	int i, delta, ret = 0;
	unsigned long flags;
	struct dma_debug_entry *entry;
	LIST_HEAD(tmp);

	spin_lock_irqsave(&free_entries_lock, flags);

	if (nr_total_entries < num_entries) {
		delta = num_entries - nr_total_entries;

		spin_unlock_irqrestore(&free_entries_lock, flags);

		for (i = 0; i < delta; i++) {
			entry = kzalloc(sizeof(*entry), GFP_KERNEL);
			if (!entry)
				break;

			list_add_tail(&entry->list, &tmp);
		}

		spin_lock_irqsave(&free_entries_lock, flags);

		list_splice(&tmp, &free_entries);
		nr_total_entries += i;
		num_free_entries += i;
	} else {
		delta = nr_total_entries - num_entries;

		for (i = 0; i < delta && !list_empty(&free_entries); i++) {
			entry = __dma_entry_alloc();
			kfree(entry);
		}

		nr_total_entries -= i;
	}

	if (nr_total_entries != num_entries)
		ret = 1;

	spin_unlock_irqrestore(&free_entries_lock, flags);

	return ret;
}
EXPORT_SYMBOL(dma_debug_resize_entries);

/*
 * DMA-API debugging init code
 *
 * The init code does two things:
 *   1. Initialize core data structures
 *   2. Preallocate a given number of dma_debug_entry structs
 */

static int prealloc_memory(u32 num_entries)
{
	struct dma_debug_entry *entry, *next_entry;
	int i;

	for (i = 0; i < num_entries; ++i) {
		entry = kzalloc(sizeof(*entry), GFP_KERNEL);
		if (!entry)
			goto out_err;

		list_add_tail(&entry->list, &free_entries);
	}

	num_free_entries = num_entries;
	min_free_entries = num_entries;

	pr_info("DMA-API: preallocated %d debug entries\n", num_entries);

	return 0;

out_err:

	list_for_each_entry_safe(entry, next_entry, &free_entries, list) {
		list_del(&entry->list);
		kfree(entry);
	}

	return -ENOMEM;
}

static ssize_t filter_read(struct file *file, char __user *user_buf,
			   size_t count, loff_t *ppos)
{
	char buf[NAME_MAX_LEN + 1];
	unsigned long flags;
	int len;

	if (!current_driver_name[0])
		return 0;

	/*
	 * We can't copy to userspace directly because current_driver_name can
	 * only be read under the driver_name_lock with irqs disabled. So
	 * create a temporary copy first.
	 */
	read_lock_irqsave(&driver_name_lock, flags);
	len = scnprintf(buf, NAME_MAX_LEN + 1, "%s\n", current_driver_name);
	read_unlock_irqrestore(&driver_name_lock, flags);

	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
}

static ssize_t filter_write(struct file *file, const char __user *userbuf,
			    size_t count, loff_t *ppos)
{
	char buf[NAME_MAX_LEN];
	unsigned long flags;
	size_t len;
	int i;

	/*
	 * We can't copy from userspace directly. Access to
	 * current_driver_name is protected with a write_lock with irqs
	 * disabled. Since copy_from_user can fault and may sleep we
	 * need to copy to temporary buffer first
	 */
	len = min(count, (size_t)(NAME_MAX_LEN - 1));
	if (copy_from_user(buf, userbuf, len))
		return -EFAULT;

	buf[len] = 0;

	write_lock_irqsave(&driver_name_lock, flags);

	/*
	 * Now handle the string we got from userspace very carefully.
	 * The rules are:
	 *         - only use the first token we got
	 *         - token delimiter is everything looking like a space
	 *           character (' ', '\n', '\t' ...)
	 *
	 */
	if (!isalnum(buf[0])) {
		/*
		 * If the first character userspace gave us is not
		 * alphanumerical then assume the filter should be
		 * switched off.
		 */
		if (current_driver_name[0])
			pr_info("DMA-API: switching off dma-debug driver filter\n");
		current_driver_name[0] = 0;
		current_driver = NULL;
		goto out_unlock;
	}

	/*
	 * Now parse out the first token and use it as the name for the
	 * driver to filter for.
	 */
	for (i = 0; i < NAME_MAX_LEN - 1; ++i) {
		current_driver_name[i] = buf[i];
		if (isspace(buf[i]) || buf[i] == ' ' || buf[i] == 0)
			break;
	}
	current_driver_name[i] = 0;
	current_driver = NULL;

	pr_info("DMA-API: enable driver filter for driver [%s]\n",
		current_driver_name);

out_unlock:
	write_unlock_irqrestore(&driver_name_lock, flags);

	return count;
}

static const struct file_operations filter_fops = {
	.read  = filter_read,
	.write = filter_write,
	.llseek = default_llseek,
};

static int dma_debug_fs_init(void)
{
	dma_debug_dent = debugfs_create_dir("dma-api", NULL);
	if (!dma_debug_dent) {
		pr_err("DMA-API: can not create debugfs directory\n");
		return -ENOMEM;
	}

	global_disable_dent = debugfs_create_bool("disabled", 0444,
			dma_debug_dent,
			&global_disable);
	if (!global_disable_dent)
		goto out_err;

	error_count_dent = debugfs_create_u32("error_count", 0444,
			dma_debug_dent, &error_count);
	if (!error_count_dent)
		goto out_err;

	show_all_errors_dent = debugfs_create_u32("all_errors", 0644,
			dma_debug_dent,
			&show_all_errors);
	if (!show_all_errors_dent)
		goto out_err;

	show_num_errors_dent = debugfs_create_u32("num_errors", 0644,
			dma_debug_dent,
			&show_num_errors);
	if (!show_num_errors_dent)
		goto out_err;

	num_free_entries_dent = debugfs_create_u32("num_free_entries", 0444,
			dma_debug_dent,
			&num_free_entries);
	if (!num_free_entries_dent)
		goto out_err;

	min_free_entries_dent = debugfs_create_u32("min_free_entries", 0444,
			dma_debug_dent,
			&min_free_entries);
	if (!min_free_entries_dent)
		goto out_err;

	filter_dent = debugfs_create_file("driver_filter", 0644,
					  dma_debug_dent, NULL, &filter_fops);
	if (!filter_dent)
		goto out_err;

	return 0;

out_err:
	debugfs_remove_recursive(dma_debug_dent);

	return -ENOMEM;
}

static int device_dma_allocations(struct device *dev, struct dma_debug_entry **out_entry)
{
	struct dma_debug_entry *entry;
	unsigned long flags;
	int count = 0, i;

	for (i = 0; i < HASH_SIZE; ++i) {
		spin_lock_irqsave(&dma_entry_hash[i].lock, flags);
		list_for_each_entry(entry, &dma_entry_hash[i].list, list) {
			if (entry->dev == dev) {
				count += 1;
				*out_entry = entry;
			}
		}
		spin_unlock_irqrestore(&dma_entry_hash[i].lock, flags);
	}

	return count;
}

static int dma_debug_device_change(struct notifier_block *nb, unsigned long action, void *data)
{
	struct device *dev = data;
	struct dma_debug_entry *uninitialized_var(entry);
	int count;

	if (dma_debug_disabled())
		return 0;

	switch (action) {
	case BUS_NOTIFY_UNBOUND_DRIVER:
		count = device_dma_allocations(dev, &entry);
		if (count == 0)
			break;
		err_printk(dev, entry, "DMA-API: device driver has pending "
				"DMA allocations while released from device "
				"[count=%d]\n"
				"One of leaked entries details: "
				"[device address=0x%016llx] [size=%llu bytes] "
				"[mapped with %s] [mapped as %s]\n",
			count, entry->dev_addr, entry->size,
			dir2name[entry->direction], type2name[entry->type]);
		break;
	default:
		break;
	}

	return 0;
}

void dma_debug_add_bus(struct bus_type *bus)
{
	struct notifier_block *nb;

	if (dma_debug_disabled())
		return;

	nb = kzalloc(sizeof(struct notifier_block), GFP_KERNEL);
	if (nb == NULL) {
		pr_err("dma_debug_add_bus: out of memory\n");
		return;
	}

	nb->notifier_call = dma_debug_device_change;

	bus_register_notifier(bus, nb);
}

/*
 * Let the architectures decide how many entries should be preallocated.
 */
void dma_debug_init(u32 num_entries)
{
	int i;

	/* Do not use dma_debug_initialized here, since we really want to be
	 * called to set dma_debug_initialized
	 */
	if (global_disable)
		return;

	for (i = 0; i < HASH_SIZE; ++i) {
		INIT_LIST_HEAD(&dma_entry_hash[i].list);
		spin_lock_init(&dma_entry_hash[i].lock);
	}

	if (dma_debug_fs_init() != 0) {
		pr_err("DMA-API: error creating debugfs entries - disabling\n");
		global_disable = true;

		return;
	}

	if (req_entries)
		num_entries = req_entries;

	if (prealloc_memory(num_entries) != 0) {
		pr_err("DMA-API: debugging out of memory error - disabled\n");
		global_disable = true;

		return;
	}

	nr_total_entries = num_free_entries;

	dma_debug_initialized = true;

	pr_info("DMA-API: debugging enabled by kernel config\n");
}

static __init int dma_debug_cmdline(char *str)
{
	if (!str)
		return -EINVAL;

	if (strncmp(str, "off", 3) == 0) {
		pr_info("DMA-API: debugging disabled on kernel command line\n");
		global_disable = true;
	}

	return 0;
}

static __init int dma_debug_entries_cmdline(char *str)
{
	int res;

	if (!str)
		return -EINVAL;

	res = get_option(&str, &req_entries);

	if (!res)
		req_entries = 0;

	return 0;
}

__setup("dma_debug=", dma_debug_cmdline);
__setup("dma_debug_entries=", dma_debug_entries_cmdline);

static void check_unmap(struct dma_debug_entry *ref)
{
	struct dma_debug_entry *entry;
	struct hash_bucket *bucket;
	unsigned long flags;

	bucket = get_hash_bucket(ref, &flags);
	entry = bucket_find_exact(bucket, ref);

	if (!entry) {
		/* must drop lock before calling dma_mapping_error */
		put_hash_bucket(bucket, &flags);

		if (dma_mapping_error(ref->dev, ref->dev_addr)) {
			err_printk(ref->dev, NULL,
				   "DMA-API: device driver tries to free an "
				   "invalid DMA memory address\n");
		} else {
			err_printk(ref->dev, NULL,
				   "DMA-API: device driver tries to free DMA "
				   "memory it has not allocated [device "
				   "address=0x%016llx] [size=%llu bytes]\n",
				   ref->dev_addr, ref->size);
		}
		return;
	}

	if (ref->size != entry->size) {
		err_printk(ref->dev, entry, "DMA-API: device driver frees "
			   "DMA memory with different size "
			   "[device address=0x%016llx] [map size=%llu bytes] "
			   "[unmap size=%llu bytes]\n",
			   ref->dev_addr, entry->size, ref->size);
	}

	if (ref->type != entry->type) {
		err_printk(ref->dev, entry, "DMA-API: device driver frees "
			   "DMA memory with wrong function "
			   "[device address=0x%016llx] [size=%llu bytes] "
			   "[mapped as %s] [unmapped as %s]\n",
			   ref->dev_addr, ref->size,
			   type2name[entry->type], type2name[ref->type]);
	} else if ((entry->type == dma_debug_coherent) &&
		   (phys_addr(ref) != phys_addr(entry))) {
		err_printk(ref->dev, entry, "DMA-API: device driver frees "
			   "DMA memory with different CPU address "
			   "[device address=0x%016llx] [size=%llu bytes] "
			   "[cpu alloc address=0x%016llx] "
			   "[cpu free address=0x%016llx]",
			   ref->dev_addr, ref->size,
			   phys_addr(entry),
			   phys_addr(ref));
	}

	if (ref->sg_call_ents && ref->type == dma_debug_sg &&
	    ref->sg_call_ents != entry->sg_call_ents) {
		err_printk(ref->dev, entry, "DMA-API: device driver frees "
			   "DMA sg list with different entry count "
			   "[map count=%d] [unmap count=%d]\n",
			   entry->sg_call_ents, ref->sg_call_ents);
	}

	/*
	 * This may be no bug in reality - but most implementations of the
	 * DMA API don't handle this properly, so check for it here
	 */
	if (ref->direction != entry->direction) {
		err_printk(ref->dev, entry, "DMA-API: device driver frees "
			   "DMA memory with different direction "
			   "[device address=0x%016llx] [size=%llu bytes] "
			   "[mapped with %s] [unmapped with %s]\n",
			   ref->dev_addr, ref->size,
			   dir2name[entry->direction],
			   dir2name[ref->direction]);
	}

	/*
	 * Drivers should use dma_mapping_error() to check the returned
	 * addresses of dma_map_single() and dma_map_page().
	 * If not, print this warning message. See Documentation/DMA-API.txt.
	 */
	if (entry->map_err_type == MAP_ERR_NOT_CHECKED) {
		err_printk(ref->dev, entry,
			   "DMA-API: device driver failed to check map error"
			   "[device address=0x%016llx] [size=%llu bytes] "
			   "[mapped as %s]",
			   ref->dev_addr, ref->size,
			   type2name[entry->type]);
	}

	hash_bucket_del(entry);
	dma_entry_free(entry);

	put_hash_bucket(bucket, &flags);
}

static void check_for_stack(struct device *dev,
			    struct page *page, size_t offset)
{
	void *addr;
	struct vm_struct *stack_vm_area = task_stack_vm_area(current);

	if (!stack_vm_area) {
		/* Stack is direct-mapped. */
		if (PageHighMem(page))
			return;
		addr = page_address(page) + offset;
		if (object_is_on_stack(addr))
			err_printk(dev, NULL, "DMA-API: device driver maps memory from stack [addr=%p]\n", addr);
	} else {
		/* Stack is vmalloced. */
		int i;

		for (i = 0; i < stack_vm_area->nr_pages; i++) {
			if (page != stack_vm_area->pages[i])
				continue;

			addr = (u8 *)current->stack + i * PAGE_SIZE + offset;
			err_printk(dev, NULL, "DMA-API: device driver maps memory from stack [probable addr=%p]\n", addr);
			break;
		}
	}
}

static inline bool overlap(void *addr, unsigned long len, void *start, void *end)
{
	unsigned long a1 = (unsigned long)addr;
	unsigned long b1 = a1 + len;
	unsigned long a2 = (unsigned long)start;
	unsigned long b2 = (unsigned long)end;

	return !(b1 <= a2 || a1 >= b2);
}

static void check_for_illegal_area(struct device *dev, void *addr, unsigned long len)
{
	if (overlap(addr, len, _stext, _etext) ||
	    overlap(addr, len, __start_rodata, __end_rodata))
		err_printk(dev, NULL, "DMA-API: device driver maps memory from kernel text or rodata [addr=%p] [len=%lu]\n", addr, len);
}

static void check_sync(struct device *dev,
		       struct dma_debug_entry *ref,
		       bool to_cpu)
{
	struct dma_debug_entry *entry;
	struct hash_bucket *bucket;
	unsigned long flags;

	bucket = get_hash_bucket(ref, &flags);

	entry = bucket_find_contain(&bucket, ref, &flags);

	if (!entry) {
		err_printk(dev, NULL, "DMA-API: device driver tries "
				"to sync DMA memory it has not allocated "
				"[device address=0x%016llx] [size=%llu bytes]\n",
				(unsigned long long)ref->dev_addr, ref->size);
		goto out;
	}

	if (ref->size > entry->size) {
		err_printk(dev, entry, "DMA-API: device driver syncs"
				" DMA memory outside allocated range "
				"[device address=0x%016llx] "
				"[allocation size=%llu bytes] "
				"[sync offset+size=%llu]\n",
				entry->dev_addr, entry->size,
				ref->size);
	}

	if (entry->direction == DMA_BIDIRECTIONAL)
		goto out;

	if (ref->direction != entry->direction) {
		err_printk(dev, entry, "DMA-API: device driver syncs "
				"DMA memory with different direction "
				"[device address=0x%016llx] [size=%llu bytes] "
				"[mapped with %s] [synced with %s]\n",
				(unsigned long long)ref->dev_addr, entry->size,
				dir2name[entry->direction],
				dir2name[ref->direction]);
	}

	if (to_cpu && !(entry->direction == DMA_FROM_DEVICE) &&
		      !(ref->direction == DMA_TO_DEVICE))
		err_printk(dev, entry, "DMA-API: device driver syncs "
				"device read-only DMA memory for cpu "
				"[device address=0x%016llx] [size=%llu bytes] "
				"[mapped with %s] [synced with %s]\n",
				(unsigned long long)ref->dev_addr, entry->size,
				dir2name[entry->direction],
				dir2name[ref->direction]);

	if (!to_cpu && !(entry->direction == DMA_TO_DEVICE) &&
		       !(ref->direction == DMA_FROM_DEVICE))
		err_printk(dev, entry, "DMA-API: device driver syncs "
				"device write-only DMA memory to device "
				"[device address=0x%016llx] [size=%llu bytes] "
				"[mapped with %s] [synced with %s]\n",
				(unsigned long long)ref->dev_addr, entry->size,
				dir2name[entry->direction],
				dir2name[ref->direction]);

	if (ref->sg_call_ents && ref->type == dma_debug_sg &&
	    ref->sg_call_ents != entry->sg_call_ents) {
		err_printk(ref->dev, entry, "DMA-API: device driver syncs "
			   "DMA sg list with different entry count "
			   "[map count=%d] [sync count=%d]\n",
			   entry->sg_call_ents, ref->sg_call_ents);
	}

out:
	put_hash_bucket(bucket, &flags);
}

void debug_dma_map_page(struct device *dev, struct page *page, size_t offset,
			size_t size, int direction, dma_addr_t dma_addr,
			bool map_single)
{
	struct dma_debug_entry *entry;

	if (unlikely(dma_debug_disabled()))
		return;

	if (dma_mapping_error(dev, dma_addr))
		return;

	entry = dma_entry_alloc();
	if (!entry)
		return;

	entry->dev       = dev;
	entry->type      = dma_debug_page;
	entry->pfn	 = page_to_pfn(page);
	entry->offset	 = offset,
	entry->dev_addr  = dma_addr;
	entry->size      = size;
	entry->direction = direction;
	entry->map_err_type = MAP_ERR_NOT_CHECKED;

	if (map_single)
		entry->type = dma_debug_single;

	check_for_stack(dev, page, offset);

	if (!PageHighMem(page)) {
		void *addr = page_address(page) + offset;

		check_for_illegal_area(dev, addr, size);
	}

	add_dma_entry(entry);
}
EXPORT_SYMBOL(debug_dma_map_page);

void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
{
	struct dma_debug_entry ref;
	struct dma_debug_entry *entry;
	struct hash_bucket *bucket;
	unsigned long flags;

	if (unlikely(dma_debug_disabled()))
		return;

	ref.dev = dev;
	ref.dev_addr = dma_addr;
	bucket = get_hash_bucket(&ref, &flags);

	list_for_each_entry(entry, &bucket->list, list) {
		if (!exact_match(&ref, entry))
			continue;

		/*
		 * The same physical address can be mapped multiple
		 * times. Without a hardware IOMMU this results in the
		 * same device addresses being put into the dma-debug
		 * hash multiple times too. This can result in false
		 * positives being reported. Therefore we implement a
		 * best-fit algorithm here which updates the first entry
		 * from the hash which fits the reference value and is
		 * not currently listed as being checked.
		 */
		if (entry->map_err_type == MAP_ERR_NOT_CHECKED) {
			entry->map_err_type = MAP_ERR_CHECKED;
			break;
		}
	}

	put_hash_bucket(bucket, &flags);
}
EXPORT_SYMBOL(debug_dma_mapping_error);

void debug_dma_unmap_page(struct device *dev, dma_addr_t addr,
			  size_t size, int direction, bool map_single)
{
	struct dma_debug_entry ref = {
		.type           = dma_debug_page,
		.dev            = dev,
		.dev_addr       = addr,
		.size           = size,
		.direction      = direction,
	};

	if (unlikely(dma_debug_disabled()))
		return;

	if (map_single)
		ref.type = dma_debug_single;

	check_unmap(&ref);
}
EXPORT_SYMBOL(debug_dma_unmap_page);

void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
		      int nents, int mapped_ents, int direction)
{
	struct dma_debug_entry *entry;
	struct scatterlist *s;
	int i;

	if (unlikely(dma_debug_disabled()))
		return;

	for_each_sg(sg, s, mapped_ents, i) {
		entry = dma_entry_alloc();
		if (!entry)
			return;

		entry->type           = dma_debug_sg;
		entry->dev            = dev;
		entry->pfn	      = page_to_pfn(sg_page(s));
		entry->offset	      = s->offset,
		entry->size           = sg_dma_len(s);
		entry->dev_addr       = sg_dma_address(s);
		entry->direction      = direction;
		entry->sg_call_ents   = nents;
		entry->sg_mapped_ents = mapped_ents;

		check_for_stack(dev, sg_page(s), s->offset);

		if (!PageHighMem(sg_page(s))) {
			check_for_illegal_area(dev, sg_virt(s), sg_dma_len(s));
		}

		add_dma_entry(entry);
	}
}
EXPORT_SYMBOL(debug_dma_map_sg);

static int get_nr_mapped_entries(struct device *dev,
				 struct dma_debug_entry *ref)
{
	struct dma_debug_entry *entry;
	struct hash_bucket *bucket;
	unsigned long flags;
	int mapped_ents;

	bucket       = get_hash_bucket(ref, &flags);
	entry        = bucket_find_exact(bucket, ref);
	mapped_ents  = 0;

	if (entry)
		mapped_ents = entry->sg_mapped_ents;
	put_hash_bucket(bucket, &flags);

	return mapped_ents;
}

void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
			int nelems, int dir)
{
	struct scatterlist *s;
	int mapped_ents = 0, i;

	if (unlikely(dma_debug_disabled()))
		return;

	for_each_sg(sglist, s, nelems, i) {

		struct dma_debug_entry ref = {
			.type           = dma_debug_sg,
			.dev            = dev,
			.pfn		= page_to_pfn(sg_page(s)),
			.offset		= s->offset,
			.dev_addr       = sg_dma_address(s),
			.size           = sg_dma_len(s),
			.direction      = dir,
			.sg_call_ents   = nelems,
		};

		if (mapped_ents && i >= mapped_ents)
			break;

		if (!i)
			mapped_ents = get_nr_mapped_entries(dev, &ref);

		check_unmap(&ref);
	}
}
EXPORT_SYMBOL(debug_dma_unmap_sg);

void debug_dma_alloc_coherent(struct device *dev, size_t size,
			      dma_addr_t dma_addr, void *virt)
{
	struct dma_debug_entry *entry;

	if (unlikely(dma_debug_disabled()))
		return;

	if (unlikely(virt == NULL))
		return;

	entry = dma_entry_alloc();
	if (!entry)
		return;

	entry->type      = dma_debug_coherent;
	entry->dev       = dev;
	entry->pfn	 = page_to_pfn(virt_to_page(virt));
	entry->offset	 = offset_in_page(virt);
	entry->size      = size;
	entry->dev_addr  = dma_addr;
	entry->direction = DMA_BIDIRECTIONAL;

	add_dma_entry(entry);
}
EXPORT_SYMBOL(debug_dma_alloc_coherent);

void debug_dma_free_coherent(struct device *dev, size_t size,
			 void *virt, dma_addr_t addr)
{
	struct dma_debug_entry ref = {
		.type           = dma_debug_coherent,
		.dev            = dev,
		.pfn		= page_to_pfn(virt_to_page(virt)),
		.offset		= offset_in_page(virt),
		.dev_addr       = addr,
		.size           = size,
		.direction      = DMA_BIDIRECTIONAL,
	};

	if (unlikely(dma_debug_disabled()))
		return;

	check_unmap(&ref);
}
EXPORT_SYMBOL(debug_dma_free_coherent);

void debug_dma_map_resource(struct device *dev, phys_addr_t addr, size_t size,
			    int direction, dma_addr_t dma_addr)
{
	struct dma_debug_entry *entry;

	if (unlikely(dma_debug_disabled()))
		return;

	entry = dma_entry_alloc();
	if (!entry)
		return;

	entry->type		= dma_debug_resource;
	entry->dev		= dev;
	entry->pfn		= PHYS_PFN(addr);
	entry->offset		= offset_in_page(addr);
	entry->size		= size;
	entry->dev_addr		= dma_addr;
	entry->direction	= direction;
	entry->map_err_type	= MAP_ERR_NOT_CHECKED;

	add_dma_entry(entry);
}
EXPORT_SYMBOL(debug_dma_map_resource);

void debug_dma_unmap_resource(struct device *dev, dma_addr_t dma_addr,
			      size_t size, int direction)
{
	struct dma_debug_entry ref = {
		.type           = dma_debug_resource,
		.dev            = dev,
		.dev_addr       = dma_addr,
		.size           = size,
		.direction      = direction,
	};

	if (unlikely(dma_debug_disabled()))
		return;

	check_unmap(&ref);
}
EXPORT_SYMBOL(debug_dma_unmap_resource);

void debug_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
				   size_t size, int direction)
{
	struct dma_debug_entry ref;

	if (unlikely(dma_debug_disabled()))
		return;

	ref.type         = dma_debug_single;
	ref.dev          = dev;
	ref.dev_addr     = dma_handle;
	ref.size         = size;
	ref.direction    = direction;
	ref.sg_call_ents = 0;

	check_sync(dev, &ref, true);
}
EXPORT_SYMBOL(debug_dma_sync_single_for_cpu);

void debug_dma_sync_single_for_device(struct device *dev,
				      dma_addr_t dma_handle, size_t size,
				      int direction)
{
	struct dma_debug_entry ref;

	if (unlikely(dma_debug_disabled()))
		return;

	ref.type         = dma_debug_single;
	ref.dev          = dev;
	ref.dev_addr     = dma_handle;
	ref.size         = size;
	ref.direction    = direction;
	ref.sg_call_ents = 0;

	check_sync(dev, &ref, false);
}
EXPORT_SYMBOL(debug_dma_sync_single_for_device);

void debug_dma_sync_single_range_for_cpu(struct device *dev,
					 dma_addr_t dma_handle,
					 unsigned long offset, size_t size,
					 int direction)
{
	struct dma_debug_entry ref;

	if (unlikely(dma_debug_disabled()))
		return;

	ref.type         = dma_debug_single;
	ref.dev          = dev;
	ref.dev_addr     = dma_handle;
	ref.size         = offset + size;
	ref.direction    = direction;
	ref.sg_call_ents = 0;

	check_sync(dev, &ref, true);
}
EXPORT_SYMBOL(debug_dma_sync_single_range_for_cpu);

void debug_dma_sync_single_range_for_device(struct device *dev,
					    dma_addr_t dma_handle,
					    unsigned long offset,
					    size_t size, int direction)
{
	struct dma_debug_entry ref;

	if (unlikely(dma_debug_disabled()))
		return;

	ref.type         = dma_debug_single;
	ref.dev          = dev;
	ref.dev_addr     = dma_handle;
	ref.size         = offset + size;
	ref.direction    = direction;
	ref.sg_call_ents = 0;

	check_sync(dev, &ref, false);
}
EXPORT_SYMBOL(debug_dma_sync_single_range_for_device);

void debug_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
			       int nelems, int direction)
{
	struct scatterlist *s;
	int mapped_ents = 0, i;

	if (unlikely(dma_debug_disabled()))
		return;

	for_each_sg(sg, s, nelems, i) {

		struct dma_debug_entry ref = {
			.type           = dma_debug_sg,
			.dev            = dev,
			.pfn		= page_to_pfn(sg_page(s)),
			.offset		= s->offset,
			.dev_addr       = sg_dma_address(s),
			.size           = sg_dma_len(s),
			.direction      = direction,
			.sg_call_ents   = nelems,
		};

		if (!i)
			mapped_ents = get_nr_mapped_entries(dev, &ref);

		if (i >= mapped_ents)
			break;

		check_sync(dev, &ref, true);
	}
}
EXPORT_SYMBOL(debug_dma_sync_sg_for_cpu);

void debug_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
				  int nelems, int direction)
{
	struct scatterlist *s;
	int mapped_ents = 0, i;

	if (unlikely(dma_debug_disabled()))
		return;

	for_each_sg(sg, s, nelems, i) {

		struct dma_debug_entry ref = {
			.type           = dma_debug_sg,
			.dev            = dev,
			.pfn		= page_to_pfn(sg_page(s)),
			.offset		= s->offset,
			.dev_addr       = sg_dma_address(s),
			.size           = sg_dma_len(s),
			.direction      = direction,
			.sg_call_ents   = nelems,
		};
		if (!i)
			mapped_ents = get_nr_mapped_entries(dev, &ref);

		if (i >= mapped_ents)
			break;

		check_sync(dev, &ref, false);
	}
}
EXPORT_SYMBOL(debug_dma_sync_sg_for_device);

static int __init dma_debug_driver_setup(char *str)
{
	int i;

	for (i = 0; i < NAME_MAX_LEN - 1; ++i, ++str) {
		current_driver_name[i] = *str;
		if (*str == 0)
			break;
	}

	if (current_driver_name[0])
		pr_info("DMA-API: enable driver filter for driver [%s]\n",
			current_driver_name);


	return 1;
}
__setup("dma_debug_driver=", dma_debug_driver_setup);