btt.c 43.1 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 1737 1738 1739 1740 1741 1742 1743 1744 1745
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Block Translation Table
 * Copyright (c) 2014-2015, Intel Corporation.
 */
#include <linux/highmem.h>
#include <linux/debugfs.h>
#include <linux/blkdev.h>
#include <linux/module.h>
#include <linux/device.h>
#include <linux/mutex.h>
#include <linux/hdreg.h>
#include <linux/genhd.h>
#include <linux/sizes.h>
#include <linux/ndctl.h>
#include <linux/fs.h>
#include <linux/nd.h>
#include <linux/backing-dev.h>
#include "btt.h"
#include "nd.h"

enum log_ent_request {
	LOG_NEW_ENT = 0,
	LOG_OLD_ENT
};

static struct device *to_dev(struct arena_info *arena)
{
	return &arena->nd_btt->dev;
}

static u64 adjust_initial_offset(struct nd_btt *nd_btt, u64 offset)
{
	return offset + nd_btt->initial_offset;
}

static int arena_read_bytes(struct arena_info *arena, resource_size_t offset,
		void *buf, size_t n, unsigned long flags)
{
	struct nd_btt *nd_btt = arena->nd_btt;
	struct nd_namespace_common *ndns = nd_btt->ndns;

	/* arena offsets may be shifted from the base of the device */
	offset = adjust_initial_offset(nd_btt, offset);
	return nvdimm_read_bytes(ndns, offset, buf, n, flags);
}

static int arena_write_bytes(struct arena_info *arena, resource_size_t offset,
		void *buf, size_t n, unsigned long flags)
{
	struct nd_btt *nd_btt = arena->nd_btt;
	struct nd_namespace_common *ndns = nd_btt->ndns;

	/* arena offsets may be shifted from the base of the device */
	offset = adjust_initial_offset(nd_btt, offset);
	return nvdimm_write_bytes(ndns, offset, buf, n, flags);
}

static int btt_info_write(struct arena_info *arena, struct btt_sb *super)
{
	int ret;

	/*
	 * infooff and info2off should always be at least 512B aligned.
	 * We rely on that to make sure rw_bytes does error clearing
	 * correctly, so make sure that is the case.
	 */
	dev_WARN_ONCE(to_dev(arena), !IS_ALIGNED(arena->infooff, 512),
		"arena->infooff: %#llx is unaligned\n", arena->infooff);
	dev_WARN_ONCE(to_dev(arena), !IS_ALIGNED(arena->info2off, 512),
		"arena->info2off: %#llx is unaligned\n", arena->info2off);

	ret = arena_write_bytes(arena, arena->info2off, super,
			sizeof(struct btt_sb), 0);
	if (ret)
		return ret;

	return arena_write_bytes(arena, arena->infooff, super,
			sizeof(struct btt_sb), 0);
}

static int btt_info_read(struct arena_info *arena, struct btt_sb *super)
{
	return arena_read_bytes(arena, arena->infooff, super,
			sizeof(struct btt_sb), 0);
}

/*
 * 'raw' version of btt_map write
 * Assumptions:
 *   mapping is in little-endian
 *   mapping contains 'E' and 'Z' flags as desired
 */
static int __btt_map_write(struct arena_info *arena, u32 lba, __le32 mapping,
		unsigned long flags)
{
	u64 ns_off = arena->mapoff + (lba * MAP_ENT_SIZE);

	if (unlikely(lba >= arena->external_nlba))
		dev_err_ratelimited(to_dev(arena),
			"%s: lba %#x out of range (max: %#x)\n",
			__func__, lba, arena->external_nlba);
	return arena_write_bytes(arena, ns_off, &mapping, MAP_ENT_SIZE, flags);
}

static int btt_map_write(struct arena_info *arena, u32 lba, u32 mapping,
			u32 z_flag, u32 e_flag, unsigned long rwb_flags)
{
	u32 ze;
	__le32 mapping_le;

	/*
	 * This 'mapping' is supposed to be just the LBA mapping, without
	 * any flags set, so strip the flag bits.
	 */
	mapping = ent_lba(mapping);

	ze = (z_flag << 1) + e_flag;
	switch (ze) {
	case 0:
		/*
		 * We want to set neither of the Z or E flags, and
		 * in the actual layout, this means setting the bit
		 * positions of both to '1' to indicate a 'normal'
		 * map entry
		 */
		mapping |= MAP_ENT_NORMAL;
		break;
	case 1:
		mapping |= (1 << MAP_ERR_SHIFT);
		break;
	case 2:
		mapping |= (1 << MAP_TRIM_SHIFT);
		break;
	default:
		/*
		 * The case where Z and E are both sent in as '1' could be
		 * construed as a valid 'normal' case, but we decide not to,
		 * to avoid confusion
		 */
		dev_err_ratelimited(to_dev(arena),
			"Invalid use of Z and E flags\n");
		return -EIO;
	}

	mapping_le = cpu_to_le32(mapping);
	return __btt_map_write(arena, lba, mapping_le, rwb_flags);
}

static int btt_map_read(struct arena_info *arena, u32 lba, u32 *mapping,
			int *trim, int *error, unsigned long rwb_flags)
{
	int ret;
	__le32 in;
	u32 raw_mapping, postmap, ze, z_flag, e_flag;
	u64 ns_off = arena->mapoff + (lba * MAP_ENT_SIZE);

	if (unlikely(lba >= arena->external_nlba))
		dev_err_ratelimited(to_dev(arena),
			"%s: lba %#x out of range (max: %#x)\n",
			__func__, lba, arena->external_nlba);

	ret = arena_read_bytes(arena, ns_off, &in, MAP_ENT_SIZE, rwb_flags);
	if (ret)
		return ret;

	raw_mapping = le32_to_cpu(in);

	z_flag = ent_z_flag(raw_mapping);
	e_flag = ent_e_flag(raw_mapping);
	ze = (z_flag << 1) + e_flag;
	postmap = ent_lba(raw_mapping);

	/* Reuse the {z,e}_flag variables for *trim and *error */
	z_flag = 0;
	e_flag = 0;

	switch (ze) {
	case 0:
		/* Initial state. Return postmap = premap */
		*mapping = lba;
		break;
	case 1:
		*mapping = postmap;
		e_flag = 1;
		break;
	case 2:
		*mapping = postmap;
		z_flag = 1;
		break;
	case 3:
		*mapping = postmap;
		break;
	default:
		return -EIO;
	}

	if (trim)
		*trim = z_flag;
	if (error)
		*error = e_flag;

	return ret;
}

static int btt_log_group_read(struct arena_info *arena, u32 lane,
			struct log_group *log)
{
	return arena_read_bytes(arena,
			arena->logoff + (lane * LOG_GRP_SIZE), log,
			LOG_GRP_SIZE, 0);
}

static struct dentry *debugfs_root;

static void arena_debugfs_init(struct arena_info *a, struct dentry *parent,
				int idx)
{
	char dirname[32];
	struct dentry *d;

	/* If for some reason, parent bttN was not created, exit */
	if (!parent)
		return;

	snprintf(dirname, 32, "arena%d", idx);
	d = debugfs_create_dir(dirname, parent);
	if (IS_ERR_OR_NULL(d))
		return;
	a->debugfs_dir = d;

	debugfs_create_x64("size", S_IRUGO, d, &a->size);
	debugfs_create_x64("external_lba_start", S_IRUGO, d,
				&a->external_lba_start);
	debugfs_create_x32("internal_nlba", S_IRUGO, d, &a->internal_nlba);
	debugfs_create_u32("internal_lbasize", S_IRUGO, d,
				&a->internal_lbasize);
	debugfs_create_x32("external_nlba", S_IRUGO, d, &a->external_nlba);
	debugfs_create_u32("external_lbasize", S_IRUGO, d,
				&a->external_lbasize);
	debugfs_create_u32("nfree", S_IRUGO, d, &a->nfree);
	debugfs_create_u16("version_major", S_IRUGO, d, &a->version_major);
	debugfs_create_u16("version_minor", S_IRUGO, d, &a->version_minor);
	debugfs_create_x64("nextoff", S_IRUGO, d, &a->nextoff);
	debugfs_create_x64("infooff", S_IRUGO, d, &a->infooff);
	debugfs_create_x64("dataoff", S_IRUGO, d, &a->dataoff);
	debugfs_create_x64("mapoff", S_IRUGO, d, &a->mapoff);
	debugfs_create_x64("logoff", S_IRUGO, d, &a->logoff);
	debugfs_create_x64("info2off", S_IRUGO, d, &a->info2off);
	debugfs_create_x32("flags", S_IRUGO, d, &a->flags);
	debugfs_create_u32("log_index_0", S_IRUGO, d, &a->log_index[0]);
	debugfs_create_u32("log_index_1", S_IRUGO, d, &a->log_index[1]);
}

static void btt_debugfs_init(struct btt *btt)
{
	int i = 0;
	struct arena_info *arena;

	btt->debugfs_dir = debugfs_create_dir(dev_name(&btt->nd_btt->dev),
						debugfs_root);
	if (IS_ERR_OR_NULL(btt->debugfs_dir))
		return;

	list_for_each_entry(arena, &btt->arena_list, list) {
		arena_debugfs_init(arena, btt->debugfs_dir, i);
		i++;
	}
}

static u32 log_seq(struct log_group *log, int log_idx)
{
	return le32_to_cpu(log->ent[log_idx].seq);
}

/*
 * This function accepts two log entries, and uses the
 * sequence number to find the 'older' entry.
 * It also updates the sequence number in this old entry to
 * make it the 'new' one if the mark_flag is set.
 * Finally, it returns which of the entries was the older one.
 *
 * TODO The logic feels a bit kludge-y. make it better..
 */
static int btt_log_get_old(struct arena_info *a, struct log_group *log)
{
	int idx0 = a->log_index[0];
	int idx1 = a->log_index[1];
	int old;

	/*
	 * the first ever time this is seen, the entry goes into [0]
	 * the next time, the following logic works out to put this
	 * (next) entry into [1]
	 */
	if (log_seq(log, idx0) == 0) {
		log->ent[idx0].seq = cpu_to_le32(1);
		return 0;
	}

	if (log_seq(log, idx0) == log_seq(log, idx1))
		return -EINVAL;
	if (log_seq(log, idx0) + log_seq(log, idx1) > 5)
		return -EINVAL;

	if (log_seq(log, idx0) < log_seq(log, idx1)) {
		if ((log_seq(log, idx1) - log_seq(log, idx0)) == 1)
			old = 0;
		else
			old = 1;
	} else {
		if ((log_seq(log, idx0) - log_seq(log, idx1)) == 1)
			old = 1;
		else
			old = 0;
	}

	return old;
}

/*
 * This function copies the desired (old/new) log entry into ent if
 * it is not NULL. It returns the sub-slot number (0 or 1)
 * where the desired log entry was found. Negative return values
 * indicate errors.
 */
static int btt_log_read(struct arena_info *arena, u32 lane,
			struct log_entry *ent, int old_flag)
{
	int ret;
	int old_ent, ret_ent;
	struct log_group log;

	ret = btt_log_group_read(arena, lane, &log);
	if (ret)
		return -EIO;

	old_ent = btt_log_get_old(arena, &log);
	if (old_ent < 0 || old_ent > 1) {
		dev_err(to_dev(arena),
				"log corruption (%d): lane %d seq [%d, %d]\n",
				old_ent, lane, log.ent[arena->log_index[0]].seq,
				log.ent[arena->log_index[1]].seq);
		/* TODO set error state? */
		return -EIO;
	}

	ret_ent = (old_flag ? old_ent : (1 - old_ent));

	if (ent != NULL)
		memcpy(ent, &log.ent[arena->log_index[ret_ent]], LOG_ENT_SIZE);

	return ret_ent;
}

/*
 * This function commits a log entry to media
 * It does _not_ prepare the freelist entry for the next write
 * btt_flog_write is the wrapper for updating the freelist elements
 */
static int __btt_log_write(struct arena_info *arena, u32 lane,
			u32 sub, struct log_entry *ent, unsigned long flags)
{
	int ret;
	u32 group_slot = arena->log_index[sub];
	unsigned int log_half = LOG_ENT_SIZE / 2;
	void *src = ent;
	u64 ns_off;

	ns_off = arena->logoff + (lane * LOG_GRP_SIZE) +
		(group_slot * LOG_ENT_SIZE);
	/* split the 16B write into atomic, durable halves */
	ret = arena_write_bytes(arena, ns_off, src, log_half, flags);
	if (ret)
		return ret;

	ns_off += log_half;
	src += log_half;
	return arena_write_bytes(arena, ns_off, src, log_half, flags);
}

static int btt_flog_write(struct arena_info *arena, u32 lane, u32 sub,
			struct log_entry *ent)
{
	int ret;

	ret = __btt_log_write(arena, lane, sub, ent, NVDIMM_IO_ATOMIC);
	if (ret)
		return ret;

	/* prepare the next free entry */
	arena->freelist[lane].sub = 1 - arena->freelist[lane].sub;
	if (++(arena->freelist[lane].seq) == 4)
		arena->freelist[lane].seq = 1;
	if (ent_e_flag(le32_to_cpu(ent->old_map)))
		arena->freelist[lane].has_err = 1;
	arena->freelist[lane].block = ent_lba(le32_to_cpu(ent->old_map));

	return ret;
}

/*
 * This function initializes the BTT map to the initial state, which is
 * all-zeroes, and indicates an identity mapping
 */
static int btt_map_init(struct arena_info *arena)
{
	int ret = -EINVAL;
	void *zerobuf;
	size_t offset = 0;
	size_t chunk_size = SZ_2M;
	size_t mapsize = arena->logoff - arena->mapoff;

	zerobuf = kzalloc(chunk_size, GFP_KERNEL);
	if (!zerobuf)
		return -ENOMEM;

	/*
	 * mapoff should always be at least 512B  aligned. We rely on that to
	 * make sure rw_bytes does error clearing correctly, so make sure that
	 * is the case.
	 */
	dev_WARN_ONCE(to_dev(arena), !IS_ALIGNED(arena->mapoff, 512),
		"arena->mapoff: %#llx is unaligned\n", arena->mapoff);

	while (mapsize) {
		size_t size = min(mapsize, chunk_size);

		dev_WARN_ONCE(to_dev(arena), size < 512,
			"chunk size: %#zx is unaligned\n", size);
		ret = arena_write_bytes(arena, arena->mapoff + offset, zerobuf,
				size, 0);
		if (ret)
			goto free;

		offset += size;
		mapsize -= size;
		cond_resched();
	}

 free:
	kfree(zerobuf);
	return ret;
}

/*
 * This function initializes the BTT log with 'fake' entries pointing
 * to the initial reserved set of blocks as being free
 */
static int btt_log_init(struct arena_info *arena)
{
	size_t logsize = arena->info2off - arena->logoff;
	size_t chunk_size = SZ_4K, offset = 0;
	struct log_entry ent;
	void *zerobuf;
	int ret;
	u32 i;

	zerobuf = kzalloc(chunk_size, GFP_KERNEL);
	if (!zerobuf)
		return -ENOMEM;
	/*
	 * logoff should always be at least 512B  aligned. We rely on that to
	 * make sure rw_bytes does error clearing correctly, so make sure that
	 * is the case.
	 */
	dev_WARN_ONCE(to_dev(arena), !IS_ALIGNED(arena->logoff, 512),
		"arena->logoff: %#llx is unaligned\n", arena->logoff);

	while (logsize) {
		size_t size = min(logsize, chunk_size);

		dev_WARN_ONCE(to_dev(arena), size < 512,
			"chunk size: %#zx is unaligned\n", size);
		ret = arena_write_bytes(arena, arena->logoff + offset, zerobuf,
				size, 0);
		if (ret)
			goto free;

		offset += size;
		logsize -= size;
		cond_resched();
	}

	for (i = 0; i < arena->nfree; i++) {
		ent.lba = cpu_to_le32(i);
		ent.old_map = cpu_to_le32(arena->external_nlba + i);
		ent.new_map = cpu_to_le32(arena->external_nlba + i);
		ent.seq = cpu_to_le32(LOG_SEQ_INIT);
		ret = __btt_log_write(arena, i, 0, &ent, 0);
		if (ret)
			goto free;
	}

 free:
	kfree(zerobuf);
	return ret;
}

static u64 to_namespace_offset(struct arena_info *arena, u64 lba)
{
	return arena->dataoff + ((u64)lba * arena->internal_lbasize);
}

static int arena_clear_freelist_error(struct arena_info *arena, u32 lane)
{
	int ret = 0;

	if (arena->freelist[lane].has_err) {
		void *zero_page = page_address(ZERO_PAGE(0));
		u32 lba = arena->freelist[lane].block;
		u64 nsoff = to_namespace_offset(arena, lba);
		unsigned long len = arena->sector_size;

		mutex_lock(&arena->err_lock);

		while (len) {
			unsigned long chunk = min(len, PAGE_SIZE);

			ret = arena_write_bytes(arena, nsoff, zero_page,
				chunk, 0);
			if (ret)
				break;
			len -= chunk;
			nsoff += chunk;
			if (len == 0)
				arena->freelist[lane].has_err = 0;
		}
		mutex_unlock(&arena->err_lock);
	}
	return ret;
}

static int btt_freelist_init(struct arena_info *arena)
{
	int new, ret;
	struct log_entry log_new;
	u32 i, map_entry, log_oldmap, log_newmap;

	arena->freelist = kcalloc(arena->nfree, sizeof(struct free_entry),
					GFP_KERNEL);
	if (!arena->freelist)
		return -ENOMEM;

	for (i = 0; i < arena->nfree; i++) {
		new = btt_log_read(arena, i, &log_new, LOG_NEW_ENT);
		if (new < 0)
			return new;

		/* old and new map entries with any flags stripped out */
		log_oldmap = ent_lba(le32_to_cpu(log_new.old_map));
		log_newmap = ent_lba(le32_to_cpu(log_new.new_map));

		/* sub points to the next one to be overwritten */
		arena->freelist[i].sub = 1 - new;
		arena->freelist[i].seq = nd_inc_seq(le32_to_cpu(log_new.seq));
		arena->freelist[i].block = log_oldmap;

		/*
		 * FIXME: if error clearing fails during init, we want to make
		 * the BTT read-only
		 */
		if (ent_e_flag(le32_to_cpu(log_new.old_map)) &&
		    !ent_normal(le32_to_cpu(log_new.old_map))) {
			arena->freelist[i].has_err = 1;
			ret = arena_clear_freelist_error(arena, i);
			if (ret)
				dev_err_ratelimited(to_dev(arena),
					"Unable to clear known errors\n");
		}

		/* This implies a newly created or untouched flog entry */
		if (log_oldmap == log_newmap)
			continue;

		/* Check if map recovery is needed */
		ret = btt_map_read(arena, le32_to_cpu(log_new.lba), &map_entry,
				NULL, NULL, 0);
		if (ret)
			return ret;

		/*
		 * The map_entry from btt_read_map is stripped of any flag bits,
		 * so use the stripped out versions from the log as well for
		 * testing whether recovery is needed. For restoration, use the
		 * 'raw' version of the log entries as that captured what we
		 * were going to write originally.
		 */
		if ((log_newmap != map_entry) && (log_oldmap == map_entry)) {
			/*
			 * Last transaction wrote the flog, but wasn't able
			 * to complete the map write. So fix up the map.
			 */
			ret = btt_map_write(arena, le32_to_cpu(log_new.lba),
					le32_to_cpu(log_new.new_map), 0, 0, 0);
			if (ret)
				return ret;
		}
	}

	return 0;
}

static bool ent_is_padding(struct log_entry *ent)
{
	return (ent->lba == 0) && (ent->old_map == 0) && (ent->new_map == 0)
		&& (ent->seq == 0);
}

/*
 * Detecting valid log indices: We read a log group (see the comments in btt.h
 * for a description of a 'log_group' and its 'slots'), and iterate over its
 * four slots. We expect that a padding slot will be all-zeroes, and use this
 * to detect a padding slot vs. an actual entry.
 *
 * If a log_group is in the initial state, i.e. hasn't been used since the
 * creation of this BTT layout, it will have three of the four slots with
 * zeroes. We skip over these log_groups for the detection of log_index. If
 * all log_groups are in the initial state (i.e. the BTT has never been
 * written to), it is safe to assume the 'new format' of log entries in slots
 * (0, 1).
 */
static int log_set_indices(struct arena_info *arena)
{
	bool idx_set = false, initial_state = true;
	int ret, log_index[2] = {-1, -1};
	u32 i, j, next_idx = 0;
	struct log_group log;
	u32 pad_count = 0;

	for (i = 0; i < arena->nfree; i++) {
		ret = btt_log_group_read(arena, i, &log);
		if (ret < 0)
			return ret;

		for (j = 0; j < 4; j++) {
			if (!idx_set) {
				if (ent_is_padding(&log.ent[j])) {
					pad_count++;
					continue;
				} else {
					/* Skip if index has been recorded */
					if ((next_idx == 1) &&
						(j == log_index[0]))
						continue;
					/* valid entry, record index */
					log_index[next_idx] = j;
					next_idx++;
				}
				if (next_idx == 2) {
					/* two valid entries found */
					idx_set = true;
				} else if (next_idx > 2) {
					/* too many valid indices */
					return -ENXIO;
				}
			} else {
				/*
				 * once the indices have been set, just verify
				 * that all subsequent log groups are either in
				 * their initial state or follow the same
				 * indices.
				 */
				if (j == log_index[0]) {
					/* entry must be 'valid' */
					if (ent_is_padding(&log.ent[j]))
						return -ENXIO;
				} else if (j == log_index[1]) {
					;
					/*
					 * log_index[1] can be padding if the
					 * lane never got used and it is still
					 * in the initial state (three 'padding'
					 * entries)
					 */
				} else {
					/* entry must be invalid (padding) */
					if (!ent_is_padding(&log.ent[j]))
						return -ENXIO;
				}
			}
		}
		/*
		 * If any of the log_groups have more than one valid,
		 * non-padding entry, then the we are no longer in the
		 * initial_state
		 */
		if (pad_count < 3)
			initial_state = false;
		pad_count = 0;
	}

	if (!initial_state && !idx_set)
		return -ENXIO;

	/*
	 * If all the entries in the log were in the initial state,
	 * assume new padding scheme
	 */
	if (initial_state)
		log_index[1] = 1;

	/*
	 * Only allow the known permutations of log/padding indices,
	 * i.e. (0, 1), and (0, 2)
	 */
	if ((log_index[0] == 0) && ((log_index[1] == 1) || (log_index[1] == 2)))
		; /* known index possibilities */
	else {
		dev_err(to_dev(arena), "Found an unknown padding scheme\n");
		return -ENXIO;
	}

	arena->log_index[0] = log_index[0];
	arena->log_index[1] = log_index[1];
	dev_dbg(to_dev(arena), "log_index_0 = %d\n", log_index[0]);
	dev_dbg(to_dev(arena), "log_index_1 = %d\n", log_index[1]);
	return 0;
}

static int btt_rtt_init(struct arena_info *arena)
{
	arena->rtt = kcalloc(arena->nfree, sizeof(u32), GFP_KERNEL);
	if (arena->rtt == NULL)
		return -ENOMEM;

	return 0;
}

static int btt_maplocks_init(struct arena_info *arena)
{
	u32 i;

	arena->map_locks = kcalloc(arena->nfree, sizeof(struct aligned_lock),
				GFP_KERNEL);
	if (!arena->map_locks)
		return -ENOMEM;

	for (i = 0; i < arena->nfree; i++)
		spin_lock_init(&arena->map_locks[i].lock);

	return 0;
}

static struct arena_info *alloc_arena(struct btt *btt, size_t size,
				size_t start, size_t arena_off)
{
	struct arena_info *arena;
	u64 logsize, mapsize, datasize;
	u64 available = size;

	arena = kzalloc(sizeof(struct arena_info), GFP_KERNEL);
	if (!arena)
		return NULL;
	arena->nd_btt = btt->nd_btt;
	arena->sector_size = btt->sector_size;
	mutex_init(&arena->err_lock);

	if (!size)
		return arena;

	arena->size = size;
	arena->external_lba_start = start;
	arena->external_lbasize = btt->lbasize;
	arena->internal_lbasize = roundup(arena->external_lbasize,
					INT_LBASIZE_ALIGNMENT);
	arena->nfree = BTT_DEFAULT_NFREE;
	arena->version_major = btt->nd_btt->version_major;
	arena->version_minor = btt->nd_btt->version_minor;

	if (available % BTT_PG_SIZE)
		available -= (available % BTT_PG_SIZE);

	/* Two pages are reserved for the super block and its copy */
	available -= 2 * BTT_PG_SIZE;

	/* The log takes a fixed amount of space based on nfree */
	logsize = roundup(arena->nfree * LOG_GRP_SIZE, BTT_PG_SIZE);
	available -= logsize;

	/* Calculate optimal split between map and data area */
	arena->internal_nlba = div_u64(available - BTT_PG_SIZE,
			arena->internal_lbasize + MAP_ENT_SIZE);
	arena->external_nlba = arena->internal_nlba - arena->nfree;

	mapsize = roundup((arena->external_nlba * MAP_ENT_SIZE), BTT_PG_SIZE);
	datasize = available - mapsize;

	/* 'Absolute' values, relative to start of storage space */
	arena->infooff = arena_off;
	arena->dataoff = arena->infooff + BTT_PG_SIZE;
	arena->mapoff = arena->dataoff + datasize;
	arena->logoff = arena->mapoff + mapsize;
	arena->info2off = arena->logoff + logsize;

	/* Default log indices are (0,1) */
	arena->log_index[0] = 0;
	arena->log_index[1] = 1;
	return arena;
}

static void free_arenas(struct btt *btt)
{
	struct arena_info *arena, *next;

	list_for_each_entry_safe(arena, next, &btt->arena_list, list) {
		list_del(&arena->list);
		kfree(arena->rtt);
		kfree(arena->map_locks);
		kfree(arena->freelist);
		debugfs_remove_recursive(arena->debugfs_dir);
		kfree(arena);
	}
}

/*
 * This function reads an existing valid btt superblock and
 * populates the corresponding arena_info struct
 */
static void parse_arena_meta(struct arena_info *arena, struct btt_sb *super,
				u64 arena_off)
{
	arena->internal_nlba = le32_to_cpu(super->internal_nlba);
	arena->internal_lbasize = le32_to_cpu(super->internal_lbasize);
	arena->external_nlba = le32_to_cpu(super->external_nlba);
	arena->external_lbasize = le32_to_cpu(super->external_lbasize);
	arena->nfree = le32_to_cpu(super->nfree);
	arena->version_major = le16_to_cpu(super->version_major);
	arena->version_minor = le16_to_cpu(super->version_minor);

	arena->nextoff = (super->nextoff == 0) ? 0 : (arena_off +
			le64_to_cpu(super->nextoff));
	arena->infooff = arena_off;
	arena->dataoff = arena_off + le64_to_cpu(super->dataoff);
	arena->mapoff = arena_off + le64_to_cpu(super->mapoff);
	arena->logoff = arena_off + le64_to_cpu(super->logoff);
	arena->info2off = arena_off + le64_to_cpu(super->info2off);

	arena->size = (le64_to_cpu(super->nextoff) > 0)
		? (le64_to_cpu(super->nextoff))
		: (arena->info2off - arena->infooff + BTT_PG_SIZE);

	arena->flags = le32_to_cpu(super->flags);
}

static int discover_arenas(struct btt *btt)
{
	int ret = 0;
	struct arena_info *arena;
	struct btt_sb *super;
	size_t remaining = btt->rawsize;
	u64 cur_nlba = 0;
	size_t cur_off = 0;
	int num_arenas = 0;

	super = kzalloc(sizeof(*super), GFP_KERNEL);
	if (!super)
		return -ENOMEM;

	while (remaining) {
		/* Alloc memory for arena */
		arena = alloc_arena(btt, 0, 0, 0);
		if (!arena) {
			ret = -ENOMEM;
			goto out_super;
		}

		arena->infooff = cur_off;
		ret = btt_info_read(arena, super);
		if (ret)
			goto out;

		if (!nd_btt_arena_is_valid(btt->nd_btt, super)) {
			if (remaining == btt->rawsize) {
				btt->init_state = INIT_NOTFOUND;
				dev_info(to_dev(arena), "No existing arenas\n");
				goto out;
			} else {
				dev_err(to_dev(arena),
						"Found corrupted metadata!\n");
				ret = -ENODEV;
				goto out;
			}
		}

		arena->external_lba_start = cur_nlba;
		parse_arena_meta(arena, super, cur_off);

		ret = log_set_indices(arena);
		if (ret) {
			dev_err(to_dev(arena),
				"Unable to deduce log/padding indices\n");
			goto out;
		}

		ret = btt_freelist_init(arena);
		if (ret)
			goto out;

		ret = btt_rtt_init(arena);
		if (ret)
			goto out;

		ret = btt_maplocks_init(arena);
		if (ret)
			goto out;

		list_add_tail(&arena->list, &btt->arena_list);

		remaining -= arena->size;
		cur_off += arena->size;
		cur_nlba += arena->external_nlba;
		num_arenas++;

		if (arena->nextoff == 0)
			break;
	}
	btt->num_arenas = num_arenas;
	btt->nlba = cur_nlba;
	btt->init_state = INIT_READY;

	kfree(super);
	return ret;

 out:
	kfree(arena);
	free_arenas(btt);
 out_super:
	kfree(super);
	return ret;
}

static int create_arenas(struct btt *btt)
{
	size_t remaining = btt->rawsize;
	size_t cur_off = 0;

	while (remaining) {
		struct arena_info *arena;
		size_t arena_size = min_t(u64, ARENA_MAX_SIZE, remaining);

		remaining -= arena_size;
		if (arena_size < ARENA_MIN_SIZE)
			break;

		arena = alloc_arena(btt, arena_size, btt->nlba, cur_off);
		if (!arena) {
			free_arenas(btt);
			return -ENOMEM;
		}
		btt->nlba += arena->external_nlba;
		if (remaining >= ARENA_MIN_SIZE)
			arena->nextoff = arena->size;
		else
			arena->nextoff = 0;
		cur_off += arena_size;
		list_add_tail(&arena->list, &btt->arena_list);
	}

	return 0;
}

/*
 * This function completes arena initialization by writing
 * all the metadata.
 * It is only called for an uninitialized arena when a write
 * to that arena occurs for the first time.
 */
static int btt_arena_write_layout(struct arena_info *arena)
{
	int ret;
	u64 sum;
	struct btt_sb *super;
	struct nd_btt *nd_btt = arena->nd_btt;
	const u8 *parent_uuid = nd_dev_to_uuid(&nd_btt->ndns->dev);

	ret = btt_map_init(arena);
	if (ret)
		return ret;

	ret = btt_log_init(arena);
	if (ret)
		return ret;

	super = kzalloc(sizeof(struct btt_sb), GFP_NOIO);
	if (!super)
		return -ENOMEM;

	strncpy(super->signature, BTT_SIG, BTT_SIG_LEN);
	memcpy(super->uuid, nd_btt->uuid, 16);
	memcpy(super->parent_uuid, parent_uuid, 16);
	super->flags = cpu_to_le32(arena->flags);
	super->version_major = cpu_to_le16(arena->version_major);
	super->version_minor = cpu_to_le16(arena->version_minor);
	super->external_lbasize = cpu_to_le32(arena->external_lbasize);
	super->external_nlba = cpu_to_le32(arena->external_nlba);
	super->internal_lbasize = cpu_to_le32(arena->internal_lbasize);
	super->internal_nlba = cpu_to_le32(arena->internal_nlba);
	super->nfree = cpu_to_le32(arena->nfree);
	super->infosize = cpu_to_le32(sizeof(struct btt_sb));
	super->nextoff = cpu_to_le64(arena->nextoff);
	/*
	 * Subtract arena->infooff (arena start) so numbers are relative
	 * to 'this' arena
	 */
	super->dataoff = cpu_to_le64(arena->dataoff - arena->infooff);
	super->mapoff = cpu_to_le64(arena->mapoff - arena->infooff);
	super->logoff = cpu_to_le64(arena->logoff - arena->infooff);
	super->info2off = cpu_to_le64(arena->info2off - arena->infooff);

	super->flags = 0;
	sum = nd_sb_checksum((struct nd_gen_sb *) super);
	super->checksum = cpu_to_le64(sum);

	ret = btt_info_write(arena, super);

	kfree(super);
	return ret;
}

/*
 * This function completes the initialization for the BTT namespace
 * such that it is ready to accept IOs
 */
static int btt_meta_init(struct btt *btt)
{
	int ret = 0;
	struct arena_info *arena;

	mutex_lock(&btt->init_lock);
	list_for_each_entry(arena, &btt->arena_list, list) {
		ret = btt_arena_write_layout(arena);
		if (ret)
			goto unlock;

		ret = btt_freelist_init(arena);
		if (ret)
			goto unlock;

		ret = btt_rtt_init(arena);
		if (ret)
			goto unlock;

		ret = btt_maplocks_init(arena);
		if (ret)
			goto unlock;
	}

	btt->init_state = INIT_READY;

 unlock:
	mutex_unlock(&btt->init_lock);
	return ret;
}

static u32 btt_meta_size(struct btt *btt)
{
	return btt->lbasize - btt->sector_size;
}

/*
 * This function calculates the arena in which the given LBA lies
 * by doing a linear walk. This is acceptable since we expect only
 * a few arenas. If we have backing devices that get much larger,
 * we can construct a balanced binary tree of arenas at init time
 * so that this range search becomes faster.
 */
static int lba_to_arena(struct btt *btt, sector_t sector, __u32 *premap,
				struct arena_info **arena)
{
	struct arena_info *arena_list;
	__u64 lba = div_u64(sector << SECTOR_SHIFT, btt->sector_size);

	list_for_each_entry(arena_list, &btt->arena_list, list) {
		if (lba < arena_list->external_nlba) {
			*arena = arena_list;
			*premap = lba;
			return 0;
		}
		lba -= arena_list->external_nlba;
	}

	return -EIO;
}

/*
 * The following (lock_map, unlock_map) are mostly just to improve
 * readability, since they index into an array of locks
 */
static void lock_map(struct arena_info *arena, u32 premap)
		__acquires(&arena->map_locks[idx].lock)
{
	u32 idx = (premap * MAP_ENT_SIZE / L1_CACHE_BYTES) % arena->nfree;

	spin_lock(&arena->map_locks[idx].lock);
}

static void unlock_map(struct arena_info *arena, u32 premap)
		__releases(&arena->map_locks[idx].lock)
{
	u32 idx = (premap * MAP_ENT_SIZE / L1_CACHE_BYTES) % arena->nfree;

	spin_unlock(&arena->map_locks[idx].lock);
}

static int btt_data_read(struct arena_info *arena, struct page *page,
			unsigned int off, u32 lba, u32 len)
{
	int ret;
	u64 nsoff = to_namespace_offset(arena, lba);
	void *mem = kmap_atomic(page);

	ret = arena_read_bytes(arena, nsoff, mem + off, len, NVDIMM_IO_ATOMIC);
	kunmap_atomic(mem);

	return ret;
}

static int btt_data_write(struct arena_info *arena, u32 lba,
			struct page *page, unsigned int off, u32 len)
{
	int ret;
	u64 nsoff = to_namespace_offset(arena, lba);
	void *mem = kmap_atomic(page);

	ret = arena_write_bytes(arena, nsoff, mem + off, len, NVDIMM_IO_ATOMIC);
	kunmap_atomic(mem);

	return ret;
}

static void zero_fill_data(struct page *page, unsigned int off, u32 len)
{
	void *mem = kmap_atomic(page);

	memset(mem + off, 0, len);
	kunmap_atomic(mem);
}

#ifdef CONFIG_BLK_DEV_INTEGRITY
static int btt_rw_integrity(struct btt *btt, struct bio_integrity_payload *bip,
			struct arena_info *arena, u32 postmap, int rw)
{
	unsigned int len = btt_meta_size(btt);
	u64 meta_nsoff;
	int ret = 0;

	if (bip == NULL)
		return 0;

	meta_nsoff = to_namespace_offset(arena, postmap) + btt->sector_size;

	while (len) {
		unsigned int cur_len;
		struct bio_vec bv;
		void *mem;

		bv = bvec_iter_bvec(bip->bip_vec, bip->bip_iter);
		/*
		 * The 'bv' obtained from bvec_iter_bvec has its .bv_len and
		 * .bv_offset already adjusted for iter->bi_bvec_done, and we
		 * can use those directly
		 */

		cur_len = min(len, bv.bv_len);
		mem = kmap_atomic(bv.bv_page);
		if (rw)
			ret = arena_write_bytes(arena, meta_nsoff,
					mem + bv.bv_offset, cur_len,
					NVDIMM_IO_ATOMIC);
		else
			ret = arena_read_bytes(arena, meta_nsoff,
					mem + bv.bv_offset, cur_len,
					NVDIMM_IO_ATOMIC);

		kunmap_atomic(mem);
		if (ret)
			return ret;

		len -= cur_len;
		meta_nsoff += cur_len;
		if (!bvec_iter_advance(bip->bip_vec, &bip->bip_iter, cur_len))
			return -EIO;
	}

	return ret;
}

#else /* CONFIG_BLK_DEV_INTEGRITY */
static int btt_rw_integrity(struct btt *btt, struct bio_integrity_payload *bip,
			struct arena_info *arena, u32 postmap, int rw)
{
	return 0;
}
#endif

static int btt_read_pg(struct btt *btt, struct bio_integrity_payload *bip,
			struct page *page, unsigned int off, sector_t sector,
			unsigned int len)
{
	int ret = 0;
	int t_flag, e_flag;
	struct arena_info *arena = NULL;
	u32 lane = 0, premap, postmap;

	while (len) {
		u32 cur_len;

		lane = nd_region_acquire_lane(btt->nd_region);

		ret = lba_to_arena(btt, sector, &premap, &arena);
		if (ret)
			goto out_lane;

		cur_len = min(btt->sector_size, len);

		ret = btt_map_read(arena, premap, &postmap, &t_flag, &e_flag,
				NVDIMM_IO_ATOMIC);
		if (ret)
			goto out_lane;

		/*
		 * We loop to make sure that the post map LBA didn't change
		 * from under us between writing the RTT and doing the actual
		 * read.
		 */
		while (1) {
			u32 new_map;
			int new_t, new_e;

			if (t_flag) {
				zero_fill_data(page, off, cur_len);
				goto out_lane;
			}

			if (e_flag) {
				ret = -EIO;
				goto out_lane;
			}

			arena->rtt[lane] = RTT_VALID | postmap;
			/*
			 * Barrier to make sure this write is not reordered
			 * to do the verification map_read before the RTT store
			 */
			barrier();

			ret = btt_map_read(arena, premap, &new_map, &new_t,
						&new_e, NVDIMM_IO_ATOMIC);
			if (ret)
				goto out_rtt;

			if ((postmap == new_map) && (t_flag == new_t) &&
					(e_flag == new_e))
				break;

			postmap = new_map;
			t_flag = new_t;
			e_flag = new_e;
		}

		ret = btt_data_read(arena, page, off, postmap, cur_len);
		if (ret) {
			/* Media error - set the e_flag */
			if (btt_map_write(arena, premap, postmap, 0, 1, NVDIMM_IO_ATOMIC))
				dev_warn_ratelimited(to_dev(arena),
					"Error persistently tracking bad blocks at %#x\n",
					premap);
			goto out_rtt;
		}

		if (bip) {
			ret = btt_rw_integrity(btt, bip, arena, postmap, READ);
			if (ret)
				goto out_rtt;
		}

		arena->rtt[lane] = RTT_INVALID;
		nd_region_release_lane(btt->nd_region, lane);

		len -= cur_len;
		off += cur_len;
		sector += btt->sector_size >> SECTOR_SHIFT;
	}

	return 0;

 out_rtt:
	arena->rtt[lane] = RTT_INVALID;
 out_lane:
	nd_region_release_lane(btt->nd_region, lane);
	return ret;
}

/*
 * Normally, arena_{read,write}_bytes will take care of the initial offset
 * adjustment, but in the case of btt_is_badblock, where we query is_bad_pmem,
 * we need the final, raw namespace offset here
 */
static bool btt_is_badblock(struct btt *btt, struct arena_info *arena,
		u32 postmap)
{
	u64 nsoff = adjust_initial_offset(arena->nd_btt,
			to_namespace_offset(arena, postmap));
	sector_t phys_sector = nsoff >> 9;

	return is_bad_pmem(btt->phys_bb, phys_sector, arena->internal_lbasize);
}

static int btt_write_pg(struct btt *btt, struct bio_integrity_payload *bip,
			sector_t sector, struct page *page, unsigned int off,
			unsigned int len)
{
	int ret = 0;
	struct arena_info *arena = NULL;
	u32 premap = 0, old_postmap, new_postmap, lane = 0, i;
	struct log_entry log;
	int sub;

	while (len) {
		u32 cur_len;
		int e_flag;

 retry:
		lane = nd_region_acquire_lane(btt->nd_region);

		ret = lba_to_arena(btt, sector, &premap, &arena);
		if (ret)
			goto out_lane;
		cur_len = min(btt->sector_size, len);

		if ((arena->flags & IB_FLAG_ERROR_MASK) != 0) {
			ret = -EIO;
			goto out_lane;
		}

		if (btt_is_badblock(btt, arena, arena->freelist[lane].block))
			arena->freelist[lane].has_err = 1;

		if (mutex_is_locked(&arena->err_lock)
				|| arena->freelist[lane].has_err) {
			nd_region_release_lane(btt->nd_region, lane);

			ret = arena_clear_freelist_error(arena, lane);
			if (ret)
				return ret;

			/* OK to acquire a different lane/free block */
			goto retry;
		}

		new_postmap = arena->freelist[lane].block;

		/* Wait if the new block is being read from */
		for (i = 0; i < arena->nfree; i++)
			while (arena->rtt[i] == (RTT_VALID | new_postmap))
				cpu_relax();


		if (new_postmap >= arena->internal_nlba) {
			ret = -EIO;
			goto out_lane;
		}

		ret = btt_data_write(arena, new_postmap, page, off, cur_len);
		if (ret)
			goto out_lane;

		if (bip) {
			ret = btt_rw_integrity(btt, bip, arena, new_postmap,
						WRITE);
			if (ret)
				goto out_lane;
		}

		lock_map(arena, premap);
		ret = btt_map_read(arena, premap, &old_postmap, NULL, &e_flag,
				NVDIMM_IO_ATOMIC);
		if (ret)
			goto out_map;
		if (old_postmap >= arena->internal_nlba) {
			ret = -EIO;
			goto out_map;
		}
		if (e_flag)
			set_e_flag(old_postmap);

		log.lba = cpu_to_le32(premap);
		log.old_map = cpu_to_le32(old_postmap);
		log.new_map = cpu_to_le32(new_postmap);
		log.seq = cpu_to_le32(arena->freelist[lane].seq);
		sub = arena->freelist[lane].sub;
		ret = btt_flog_write(arena, lane, sub, &log);
		if (ret)
			goto out_map;

		ret = btt_map_write(arena, premap, new_postmap, 0, 0,
			NVDIMM_IO_ATOMIC);
		if (ret)
			goto out_map;

		unlock_map(arena, premap);
		nd_region_release_lane(btt->nd_region, lane);

		if (e_flag) {
			ret = arena_clear_freelist_error(arena, lane);
			if (ret)
				return ret;
		}

		len -= cur_len;
		off += cur_len;
		sector += btt->sector_size >> SECTOR_SHIFT;
	}

	return 0;

 out_map:
	unlock_map(arena, premap);
 out_lane:
	nd_region_release_lane(btt->nd_region, lane);
	return ret;
}

static int btt_do_bvec(struct btt *btt, struct bio_integrity_payload *bip,
			struct page *page, unsigned int len, unsigned int off,
			unsigned int op, sector_t sector)
{
	int ret;

	if (!op_is_write(op)) {
		ret = btt_read_pg(btt, bip, page, off, sector, len);
		flush_dcache_page(page);
	} else {
		flush_dcache_page(page);
		ret = btt_write_pg(btt, bip, sector, page, off, len);
	}

	return ret;
}

static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio)
{
	struct bio_integrity_payload *bip = bio_integrity(bio);
	struct btt *btt = q->queuedata;
	struct bvec_iter iter;
	unsigned long start;
	struct bio_vec bvec;
	int err = 0;
	bool do_acct;

	if (!bio_integrity_prep(bio))
		return BLK_QC_T_NONE;

	do_acct = nd_iostat_start(bio, &start);
	bio_for_each_segment(bvec, bio, iter) {
		unsigned int len = bvec.bv_len;

		if (len > PAGE_SIZE || len < btt->sector_size ||
				len % btt->sector_size) {
			dev_err_ratelimited(&btt->nd_btt->dev,
				"unaligned bio segment (len: %d)\n", len);
			bio->bi_status = BLK_STS_IOERR;
			break;
		}

		err = btt_do_bvec(btt, bip, bvec.bv_page, len, bvec.bv_offset,
				  bio_op(bio), iter.bi_sector);
		if (err) {
			dev_err(&btt->nd_btt->dev,
					"io error in %s sector %lld, len %d,\n",
					(op_is_write(bio_op(bio))) ? "WRITE" :
					"READ",
					(unsigned long long) iter.bi_sector, len);
			bio->bi_status = errno_to_blk_status(err);
			break;
		}
	}
	if (do_acct)
		nd_iostat_end(bio, start);

	bio_endio(bio);
	return BLK_QC_T_NONE;
}

static int btt_rw_page(struct block_device *bdev, sector_t sector,
		struct page *page, unsigned int op)
{
	struct btt *btt = bdev->bd_disk->private_data;
	int rc;
	unsigned int len;

	len = hpage_nr_pages(page) * PAGE_SIZE;
	rc = btt_do_bvec(btt, NULL, page, len, 0, op, sector);
	if (rc == 0)
		page_endio(page, op_is_write(op), 0);

	return rc;
}


static int btt_getgeo(struct block_device *bd, struct hd_geometry *geo)
{
	/* some standard values */
	geo->heads = 1 << 6;
	geo->sectors = 1 << 5;
	geo->cylinders = get_capacity(bd->bd_disk) >> 11;
	return 0;
}

static const struct block_device_operations btt_fops = {
	.owner =		THIS_MODULE,
	.rw_page =		btt_rw_page,
	.getgeo =		btt_getgeo,
	.revalidate_disk =	nvdimm_revalidate_disk,
};

static int btt_blk_init(struct btt *btt)
{
	struct nd_btt *nd_btt = btt->nd_btt;
	struct nd_namespace_common *ndns = nd_btt->ndns;

	/* create a new disk and request queue for btt */
	btt->btt_queue = blk_alloc_queue(GFP_KERNEL);
	if (!btt->btt_queue)
		return -ENOMEM;

	btt->btt_disk = alloc_disk(0);
	if (!btt->btt_disk) {
		blk_cleanup_queue(btt->btt_queue);
		return -ENOMEM;
	}

	nvdimm_namespace_disk_name(ndns, btt->btt_disk->disk_name);
	btt->btt_disk->first_minor = 0;
	btt->btt_disk->fops = &btt_fops;
	btt->btt_disk->private_data = btt;
	btt->btt_disk->queue = btt->btt_queue;
	btt->btt_disk->flags = GENHD_FL_EXT_DEVT;
	btt->btt_disk->queue->backing_dev_info->capabilities |=
			BDI_CAP_SYNCHRONOUS_IO;

	blk_queue_make_request(btt->btt_queue, btt_make_request);
	blk_queue_logical_block_size(btt->btt_queue, btt->sector_size);
	blk_queue_max_hw_sectors(btt->btt_queue, UINT_MAX);
	blk_queue_flag_set(QUEUE_FLAG_NONROT, btt->btt_queue);
	btt->btt_queue->queuedata = btt;

	if (btt_meta_size(btt)) {
		int rc = nd_integrity_init(btt->btt_disk, btt_meta_size(btt));

		if (rc) {
			del_gendisk(btt->btt_disk);
			put_disk(btt->btt_disk);
			blk_cleanup_queue(btt->btt_queue);
			return rc;
		}
	}
	set_capacity(btt->btt_disk, btt->nlba * btt->sector_size >> 9);
	device_add_disk(&btt->nd_btt->dev, btt->btt_disk, NULL);
	btt->nd_btt->size = btt->nlba * (u64)btt->sector_size;
	revalidate_disk(btt->btt_disk);

	return 0;
}

static void btt_blk_cleanup(struct btt *btt)
{
	del_gendisk(btt->btt_disk);
	put_disk(btt->btt_disk);
	blk_cleanup_queue(btt->btt_queue);
}

/**
 * btt_init - initialize a block translation table for the given device
 * @nd_btt:	device with BTT geometry and backing device info
 * @rawsize:	raw size in bytes of the backing device
 * @lbasize:	lba size of the backing device
 * @uuid:	A uuid for the backing device - this is stored on media
 * @maxlane:	maximum number of parallel requests the device can handle
 *
 * Initialize a Block Translation Table on a backing device to provide
 * single sector power fail atomicity.
 *
 * Context:
 * Might sleep.
 *
 * Returns:
 * Pointer to a new struct btt on success, NULL on failure.
 */
static struct btt *btt_init(struct nd_btt *nd_btt, unsigned long long rawsize,
		u32 lbasize, u8 *uuid, struct nd_region *nd_region)
{
	int ret;
	struct btt *btt;
	struct nd_namespace_io *nsio;
	struct device *dev = &nd_btt->dev;

	btt = devm_kzalloc(dev, sizeof(struct btt), GFP_KERNEL);
	if (!btt)
		return NULL;

	btt->nd_btt = nd_btt;
	btt->rawsize = rawsize;
	btt->lbasize = lbasize;
	btt->sector_size = ((lbasize >= 4096) ? 4096 : 512);
	INIT_LIST_HEAD(&btt->arena_list);
	mutex_init(&btt->init_lock);
	btt->nd_region = nd_region;
	nsio = to_nd_namespace_io(&nd_btt->ndns->dev);
	btt->phys_bb = &nsio->bb;

	ret = discover_arenas(btt);
	if (ret) {
		dev_err(dev, "init: error in arena_discover: %d\n", ret);
		return NULL;
	}

	if (btt->init_state != INIT_READY && nd_region->ro) {
		dev_warn(dev, "%s is read-only, unable to init btt metadata\n",
				dev_name(&nd_region->dev));
		return NULL;
	} else if (btt->init_state != INIT_READY) {
		btt->num_arenas = (rawsize / ARENA_MAX_SIZE) +
			((rawsize % ARENA_MAX_SIZE) ? 1 : 0);
		dev_dbg(dev, "init: %d arenas for %llu rawsize\n",
				btt->num_arenas, rawsize);

		ret = create_arenas(btt);
		if (ret) {
			dev_info(dev, "init: create_arenas: %d\n", ret);
			return NULL;
		}

		ret = btt_meta_init(btt);
		if (ret) {
			dev_err(dev, "init: error in meta_init: %d\n", ret);
			return NULL;
		}
	}

	ret = btt_blk_init(btt);
	if (ret) {
		dev_err(dev, "init: error in blk_init: %d\n", ret);
		return NULL;
	}

	btt_debugfs_init(btt);

	return btt;
}

/**
 * btt_fini - de-initialize a BTT
 * @btt:	the BTT handle that was generated by btt_init
 *
 * De-initialize a Block Translation Table on device removal
 *
 * Context:
 * Might sleep.
 */
static void btt_fini(struct btt *btt)
{
	if (btt) {
		btt_blk_cleanup(btt);
		free_arenas(btt);
		debugfs_remove_recursive(btt->debugfs_dir);
	}
}

int nvdimm_namespace_attach_btt(struct nd_namespace_common *ndns)
{
	struct nd_btt *nd_btt = to_nd_btt(ndns->claim);
	struct nd_region *nd_region;
	struct btt_sb *btt_sb;
	struct btt *btt;
	size_t rawsize;

	if (!nd_btt->uuid || !nd_btt->ndns || !nd_btt->lbasize) {
		dev_dbg(&nd_btt->dev, "incomplete btt configuration\n");
		return -ENODEV;
	}

	btt_sb = devm_kzalloc(&nd_btt->dev, sizeof(*btt_sb), GFP_KERNEL);
	if (!btt_sb)
		return -ENOMEM;

	/*
	 * If this returns < 0, that is ok as it just means there wasn't
	 * an existing BTT, and we're creating a new one. We still need to
	 * call this as we need the version dependent fields in nd_btt to be
	 * set correctly based on the holder class
	 */
	nd_btt_version(nd_btt, ndns, btt_sb);

	rawsize = nvdimm_namespace_capacity(ndns) - nd_btt->initial_offset;
	if (rawsize < ARENA_MIN_SIZE) {
		dev_dbg(&nd_btt->dev, "%s must be at least %ld bytes\n",
				dev_name(&ndns->dev),
				ARENA_MIN_SIZE + nd_btt->initial_offset);
		return -ENXIO;
	}
	nd_region = to_nd_region(nd_btt->dev.parent);
	btt = btt_init(nd_btt, rawsize, nd_btt->lbasize, nd_btt->uuid,
			nd_region);
	if (!btt)
		return -ENOMEM;
	nd_btt->btt = btt;

	return 0;
}
EXPORT_SYMBOL(nvdimm_namespace_attach_btt);

int nvdimm_namespace_detach_btt(struct nd_btt *nd_btt)
{
	struct btt *btt = nd_btt->btt;

	btt_fini(btt);
	nd_btt->btt = NULL;

	return 0;
}
EXPORT_SYMBOL(nvdimm_namespace_detach_btt);

static int __init nd_btt_init(void)
{
	int rc = 0;

	debugfs_root = debugfs_create_dir("btt", NULL);
	if (IS_ERR_OR_NULL(debugfs_root))
		rc = -ENXIO;

	return rc;
}

static void __exit nd_btt_exit(void)
{
	debugfs_remove_recursive(debugfs_root);
}

MODULE_ALIAS_ND_DEVICE(ND_DEVICE_BTT);
MODULE_AUTHOR("Vishal Verma <vishal.l.verma@linux.intel.com>");
MODULE_LICENSE("GPL v2");
module_init(nd_btt_init);
module_exit(nd_btt_exit);