bio.c 49.2 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 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038
/*
 * Copyright (C) 2001 Jens Axboe <axboe@kernel.dk>
 *
 * 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 Licens
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-
 *
 */
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/uio.h>
#include <linux/iocontext.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/mempool.h>
#include <linux/workqueue.h>
#include <linux/cgroup.h>
#include <scsi/sg.h>		/* for struct sg_iovec */

#include <trace/events/block.h>

/*
 * Test patch to inline a certain number of bi_io_vec's inside the bio
 * itself, to shrink a bio data allocation from two mempool calls to one
 */
#define BIO_INLINE_VECS		4

/*
 * if you change this list, also change bvec_alloc or things will
 * break badly! cannot be bigger than what you can fit into an
 * unsigned short
 */
#define BV(x) { .nr_vecs = x, .name = "biovec-"__stringify(x) }
static struct biovec_slab bvec_slabs[BIOVEC_NR_POOLS] __read_mostly = {
	BV(1), BV(4), BV(16), BV(64), BV(128), BV(BIO_MAX_PAGES),
};
#undef BV

/*
 * fs_bio_set is the bio_set containing bio and iovec memory pools used by
 * IO code that does not need private memory pools.
 */
struct bio_set *fs_bio_set;
EXPORT_SYMBOL(fs_bio_set);

/*
 * Our slab pool management
 */
struct bio_slab {
	struct kmem_cache *slab;
	unsigned int slab_ref;
	unsigned int slab_size;
	char name[8];
};
static DEFINE_MUTEX(bio_slab_lock);
static struct bio_slab *bio_slabs;
static unsigned int bio_slab_nr, bio_slab_max;

static struct kmem_cache *bio_find_or_create_slab(unsigned int extra_size)
{
	unsigned int sz = sizeof(struct bio) + extra_size;
	struct kmem_cache *slab = NULL;
	struct bio_slab *bslab, *new_bio_slabs;
	unsigned int new_bio_slab_max;
	unsigned int i, entry = -1;

	mutex_lock(&bio_slab_lock);

	i = 0;
	while (i < bio_slab_nr) {
		bslab = &bio_slabs[i];

		if (!bslab->slab && entry == -1)
			entry = i;
		else if (bslab->slab_size == sz) {
			slab = bslab->slab;
			bslab->slab_ref++;
			break;
		}
		i++;
	}

	if (slab)
		goto out_unlock;

	if (bio_slab_nr == bio_slab_max && entry == -1) {
		new_bio_slab_max = bio_slab_max << 1;
		new_bio_slabs = krealloc(bio_slabs,
					 new_bio_slab_max * sizeof(struct bio_slab),
					 GFP_KERNEL);
		if (!new_bio_slabs)
			goto out_unlock;
		bio_slab_max = new_bio_slab_max;
		bio_slabs = new_bio_slabs;
	}
	if (entry == -1)
		entry = bio_slab_nr++;

	bslab = &bio_slabs[entry];

	snprintf(bslab->name, sizeof(bslab->name), "bio-%d", entry);
	slab = kmem_cache_create(bslab->name, sz, 0, SLAB_HWCACHE_ALIGN, NULL);
	if (!slab)
		goto out_unlock;

	printk(KERN_INFO "bio: create slab <%s> at %d\n", bslab->name, entry);
	bslab->slab = slab;
	bslab->slab_ref = 1;
	bslab->slab_size = sz;
out_unlock:
	mutex_unlock(&bio_slab_lock);
	return slab;
}

static void bio_put_slab(struct bio_set *bs)
{
	struct bio_slab *bslab = NULL;
	unsigned int i;

	mutex_lock(&bio_slab_lock);

	for (i = 0; i < bio_slab_nr; i++) {
		if (bs->bio_slab == bio_slabs[i].slab) {
			bslab = &bio_slabs[i];
			break;
		}
	}

	if (WARN(!bslab, KERN_ERR "bio: unable to find slab!\n"))
		goto out;

	WARN_ON(!bslab->slab_ref);

	if (--bslab->slab_ref)
		goto out;

	kmem_cache_destroy(bslab->slab);
	bslab->slab = NULL;

out:
	mutex_unlock(&bio_slab_lock);
}

unsigned int bvec_nr_vecs(unsigned short idx)
{
	return bvec_slabs[idx].nr_vecs;
}

void bvec_free(mempool_t *pool, struct bio_vec *bv, unsigned int idx)
{
	BIO_BUG_ON(idx >= BIOVEC_NR_POOLS);

	if (idx == BIOVEC_MAX_IDX)
		mempool_free(bv, pool);
	else {
		struct biovec_slab *bvs = bvec_slabs + idx;

		kmem_cache_free(bvs->slab, bv);
	}
}

struct bio_vec *bvec_alloc(gfp_t gfp_mask, int nr, unsigned long *idx,
			   mempool_t *pool)
{
	struct bio_vec *bvl;

	/*
	 * see comment near bvec_array define!
	 */
	switch (nr) {
	case 1:
		*idx = 0;
		break;
	case 2 ... 4:
		*idx = 1;
		break;
	case 5 ... 16:
		*idx = 2;
		break;
	case 17 ... 64:
		*idx = 3;
		break;
	case 65 ... 128:
		*idx = 4;
		break;
	case 129 ... BIO_MAX_PAGES:
		*idx = 5;
		break;
	default:
		return NULL;
	}

	/*
	 * idx now points to the pool we want to allocate from. only the
	 * 1-vec entry pool is mempool backed.
	 */
	if (*idx == BIOVEC_MAX_IDX) {
fallback:
		bvl = mempool_alloc(pool, gfp_mask);
	} else {
		struct biovec_slab *bvs = bvec_slabs + *idx;
		gfp_t __gfp_mask = gfp_mask & ~(__GFP_WAIT | __GFP_IO);

		/*
		 * Make this allocation restricted and don't dump info on
		 * allocation failures, since we'll fallback to the mempool
		 * in case of failure.
		 */
		__gfp_mask |= __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN;

		/*
		 * Try a slab allocation. If this fails and __GFP_WAIT
		 * is set, retry with the 1-entry mempool
		 */
		bvl = kmem_cache_alloc(bvs->slab, __gfp_mask);
		if (unlikely(!bvl && (gfp_mask & __GFP_WAIT))) {
			*idx = BIOVEC_MAX_IDX;
			goto fallback;
		}
	}

	return bvl;
}

static void __bio_free(struct bio *bio)
{
	bio_disassociate_task(bio);

	if (bio_integrity(bio))
		bio_integrity_free(bio);
}

static void bio_free(struct bio *bio)
{
	struct bio_set *bs = bio->bi_pool;
	void *p;

	__bio_free(bio);

	if (bs) {
		if (bio_flagged(bio, BIO_OWNS_VEC))
			bvec_free(bs->bvec_pool, bio->bi_io_vec, BIO_POOL_IDX(bio));

		/*
		 * If we have front padding, adjust the bio pointer before freeing
		 */
		p = bio;
		p -= bs->front_pad;

		mempool_free(p, bs->bio_pool);
	} else {
		/* Bio was allocated by bio_kmalloc() */
		kfree(bio);
	}
}

void bio_init(struct bio *bio)
{
	memset(bio, 0, sizeof(*bio));
	bio->bi_flags = 1 << BIO_UPTODATE;
	atomic_set(&bio->bi_remaining, 1);
	atomic_set(&bio->bi_cnt, 1);
}
EXPORT_SYMBOL(bio_init);

/**
 * bio_reset - reinitialize a bio
 * @bio:	bio to reset
 *
 * Description:
 *   After calling bio_reset(), @bio will be in the same state as a freshly
 *   allocated bio returned bio bio_alloc_bioset() - the only fields that are
 *   preserved are the ones that are initialized by bio_alloc_bioset(). See
 *   comment in struct bio.
 */
void bio_reset(struct bio *bio)
{
	unsigned long flags = bio->bi_flags & (~0UL << BIO_RESET_BITS);

	__bio_free(bio);

	memset(bio, 0, BIO_RESET_BYTES);
	bio->bi_flags = flags|(1 << BIO_UPTODATE);
	atomic_set(&bio->bi_remaining, 1);
}
EXPORT_SYMBOL(bio_reset);

static void bio_chain_endio(struct bio *bio, int error)
{
	bio_endio(bio->bi_private, error);
	bio_put(bio);
}

/**
 * bio_chain - chain bio completions
 *
 * The caller won't have a bi_end_io called when @bio completes - instead,
 * @parent's bi_end_io won't be called until both @parent and @bio have
 * completed; the chained bio will also be freed when it completes.
 *
 * The caller must not set bi_private or bi_end_io in @bio.
 */
void bio_chain(struct bio *bio, struct bio *parent)
{
	BUG_ON(bio->bi_private || bio->bi_end_io);

	bio->bi_private = parent;
	bio->bi_end_io	= bio_chain_endio;
	atomic_inc(&parent->bi_remaining);
}
EXPORT_SYMBOL(bio_chain);

static void bio_alloc_rescue(struct work_struct *work)
{
	struct bio_set *bs = container_of(work, struct bio_set, rescue_work);
	struct bio *bio;

	while (1) {
		spin_lock(&bs->rescue_lock);
		bio = bio_list_pop(&bs->rescue_list);
		spin_unlock(&bs->rescue_lock);

		if (!bio)
			break;

		generic_make_request(bio);
	}
}

static void punt_bios_to_rescuer(struct bio_set *bs)
{
	struct bio_list punt, nopunt;
	struct bio *bio;

	/*
	 * In order to guarantee forward progress we must punt only bios that
	 * were allocated from this bio_set; otherwise, if there was a bio on
	 * there for a stacking driver higher up in the stack, processing it
	 * could require allocating bios from this bio_set, and doing that from
	 * our own rescuer would be bad.
	 *
	 * Since bio lists are singly linked, pop them all instead of trying to
	 * remove from the middle of the list:
	 */

	bio_list_init(&punt);
	bio_list_init(&nopunt);

	while ((bio = bio_list_pop(current->bio_list)))
		bio_list_add(bio->bi_pool == bs ? &punt : &nopunt, bio);

	*current->bio_list = nopunt;

	spin_lock(&bs->rescue_lock);
	bio_list_merge(&bs->rescue_list, &punt);
	spin_unlock(&bs->rescue_lock);

	queue_work(bs->rescue_workqueue, &bs->rescue_work);
}

/**
 * bio_alloc_bioset - allocate a bio for I/O
 * @gfp_mask:   the GFP_ mask given to the slab allocator
 * @nr_iovecs:	number of iovecs to pre-allocate
 * @bs:		the bio_set to allocate from.
 *
 * Description:
 *   If @bs is NULL, uses kmalloc() to allocate the bio; else the allocation is
 *   backed by the @bs's mempool.
 *
 *   When @bs is not NULL, if %__GFP_WAIT is set then bio_alloc will always be
 *   able to allocate a bio. This is due to the mempool guarantees. To make this
 *   work, callers must never allocate more than 1 bio at a time from this pool.
 *   Callers that need to allocate more than 1 bio must always submit the
 *   previously allocated bio for IO before attempting to allocate a new one.
 *   Failure to do so can cause deadlocks under memory pressure.
 *
 *   Note that when running under generic_make_request() (i.e. any block
 *   driver), bios are not submitted until after you return - see the code in
 *   generic_make_request() that converts recursion into iteration, to prevent
 *   stack overflows.
 *
 *   This would normally mean allocating multiple bios under
 *   generic_make_request() would be susceptible to deadlocks, but we have
 *   deadlock avoidance code that resubmits any blocked bios from a rescuer
 *   thread.
 *
 *   However, we do not guarantee forward progress for allocations from other
 *   mempools. Doing multiple allocations from the same mempool under
 *   generic_make_request() should be avoided - instead, use bio_set's front_pad
 *   for per bio allocations.
 *
 *   RETURNS:
 *   Pointer to new bio on success, NULL on failure.
 */
struct bio *bio_alloc_bioset(gfp_t gfp_mask, int nr_iovecs, struct bio_set *bs)
{
	gfp_t saved_gfp = gfp_mask;
	unsigned front_pad;
	unsigned inline_vecs;
	unsigned long idx = BIO_POOL_NONE;
	struct bio_vec *bvl = NULL;
	struct bio *bio;
	void *p;

	if (!bs) {
		if (nr_iovecs > UIO_MAXIOV)
			return NULL;

		p = kmalloc(sizeof(struct bio) +
			    nr_iovecs * sizeof(struct bio_vec),
			    gfp_mask);
		front_pad = 0;
		inline_vecs = nr_iovecs;
	} else {
		/*
		 * generic_make_request() converts recursion to iteration; this
		 * means if we're running beneath it, any bios we allocate and
		 * submit will not be submitted (and thus freed) until after we
		 * return.
		 *
		 * This exposes us to a potential deadlock if we allocate
		 * multiple bios from the same bio_set() while running
		 * underneath generic_make_request(). If we were to allocate
		 * multiple bios (say a stacking block driver that was splitting
		 * bios), we would deadlock if we exhausted the mempool's
		 * reserve.
		 *
		 * We solve this, and guarantee forward progress, with a rescuer
		 * workqueue per bio_set. If we go to allocate and there are
		 * bios on current->bio_list, we first try the allocation
		 * without __GFP_WAIT; if that fails, we punt those bios we
		 * would be blocking to the rescuer workqueue before we retry
		 * with the original gfp_flags.
		 */

		if (current->bio_list && !bio_list_empty(current->bio_list))
			gfp_mask &= ~__GFP_WAIT;

		p = mempool_alloc(bs->bio_pool, gfp_mask);
		if (!p && gfp_mask != saved_gfp) {
			punt_bios_to_rescuer(bs);
			gfp_mask = saved_gfp;
			p = mempool_alloc(bs->bio_pool, gfp_mask);
		}

		front_pad = bs->front_pad;
		inline_vecs = BIO_INLINE_VECS;
	}

	if (unlikely(!p))
		return NULL;

	bio = p + front_pad;
	bio_init(bio);

	if (nr_iovecs > inline_vecs) {
		bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, bs->bvec_pool);
		if (!bvl && gfp_mask != saved_gfp) {
			punt_bios_to_rescuer(bs);
			gfp_mask = saved_gfp;
			bvl = bvec_alloc(gfp_mask, nr_iovecs, &idx, bs->bvec_pool);
		}

		if (unlikely(!bvl))
			goto err_free;

		bio->bi_flags |= 1 << BIO_OWNS_VEC;
	} else if (nr_iovecs) {
		bvl = bio->bi_inline_vecs;
	}

	bio->bi_pool = bs;
	bio->bi_flags |= idx << BIO_POOL_OFFSET;
	bio->bi_max_vecs = nr_iovecs;
	bio->bi_io_vec = bvl;
	return bio;

err_free:
	mempool_free(p, bs->bio_pool);
	return NULL;
}
EXPORT_SYMBOL(bio_alloc_bioset);

void zero_fill_bio(struct bio *bio)
{
	unsigned long flags;
	struct bio_vec bv;
	struct bvec_iter iter;

	bio_for_each_segment(bv, bio, iter) {
		char *data = bvec_kmap_irq(&bv, &flags);
		memset(data, 0, bv.bv_len);
		flush_dcache_page(bv.bv_page);
		bvec_kunmap_irq(data, &flags);
	}
}
EXPORT_SYMBOL(zero_fill_bio);

/**
 * bio_put - release a reference to a bio
 * @bio:   bio to release reference to
 *
 * Description:
 *   Put a reference to a &struct bio, either one you have gotten with
 *   bio_alloc, bio_get or bio_clone. The last put of a bio will free it.
 **/
void bio_put(struct bio *bio)
{
	BIO_BUG_ON(!atomic_read(&bio->bi_cnt));

	/*
	 * last put frees it
	 */
	if (atomic_dec_and_test(&bio->bi_cnt))
		bio_free(bio);
}
EXPORT_SYMBOL(bio_put);

inline int bio_phys_segments(struct request_queue *q, struct bio *bio)
{
	if (unlikely(!bio_flagged(bio, BIO_SEG_VALID)))
		blk_recount_segments(q, bio);

	return bio->bi_phys_segments;
}
EXPORT_SYMBOL(bio_phys_segments);

/**
 * 	__bio_clone_fast - clone a bio that shares the original bio's biovec
 * 	@bio: destination bio
 * 	@bio_src: bio to clone
 *
 *	Clone a &bio. Caller will own the returned bio, but not
 *	the actual data it points to. Reference count of returned
 * 	bio will be one.
 *
 * 	Caller must ensure that @bio_src is not freed before @bio.
 */
void __bio_clone_fast(struct bio *bio, struct bio *bio_src)
{
	BUG_ON(bio->bi_pool && BIO_POOL_IDX(bio) != BIO_POOL_NONE);

	/*
	 * most users will be overriding ->bi_bdev with a new target,
	 * so we don't set nor calculate new physical/hw segment counts here
	 */
	bio->bi_bdev = bio_src->bi_bdev;
	bio->bi_flags |= 1 << BIO_CLONED;
	bio->bi_rw = bio_src->bi_rw;
	bio->bi_iter = bio_src->bi_iter;
	bio->bi_io_vec = bio_src->bi_io_vec;
}
EXPORT_SYMBOL(__bio_clone_fast);

/**
 *	bio_clone_fast - clone a bio that shares the original bio's biovec
 *	@bio: bio to clone
 *	@gfp_mask: allocation priority
 *	@bs: bio_set to allocate from
 *
 * 	Like __bio_clone_fast, only also allocates the returned bio
 */
struct bio *bio_clone_fast(struct bio *bio, gfp_t gfp_mask, struct bio_set *bs)
{
	struct bio *b;

	b = bio_alloc_bioset(gfp_mask, 0, bs);
	if (!b)
		return NULL;

	__bio_clone_fast(b, bio);

	if (bio_integrity(bio)) {
		int ret;

		ret = bio_integrity_clone(b, bio, gfp_mask);

		if (ret < 0) {
			bio_put(b);
			return NULL;
		}
	}

	return b;
}
EXPORT_SYMBOL(bio_clone_fast);

/**
 * 	bio_clone_bioset - clone a bio
 * 	@bio_src: bio to clone
 *	@gfp_mask: allocation priority
 *	@bs: bio_set to allocate from
 *
 *	Clone bio. Caller will own the returned bio, but not the actual data it
 *	points to. Reference count of returned bio will be one.
 */
struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask,
			     struct bio_set *bs)
{
	struct bvec_iter iter;
	struct bio_vec bv;
	struct bio *bio;

	/*
	 * Pre immutable biovecs, __bio_clone() used to just do a memcpy from
	 * bio_src->bi_io_vec to bio->bi_io_vec.
	 *
	 * We can't do that anymore, because:
	 *
	 *  - The point of cloning the biovec is to produce a bio with a biovec
	 *    the caller can modify: bi_idx and bi_bvec_done should be 0.
	 *
	 *  - The original bio could've had more than BIO_MAX_PAGES biovecs; if
	 *    we tried to clone the whole thing bio_alloc_bioset() would fail.
	 *    But the clone should succeed as long as the number of biovecs we
	 *    actually need to allocate is fewer than BIO_MAX_PAGES.
	 *
	 *  - Lastly, bi_vcnt should not be looked at or relied upon by code
	 *    that does not own the bio - reason being drivers don't use it for
	 *    iterating over the biovec anymore, so expecting it to be kept up
	 *    to date (i.e. for clones that share the parent biovec) is just
	 *    asking for trouble and would force extra work on
	 *    __bio_clone_fast() anyways.
	 */

	bio = bio_alloc_bioset(gfp_mask, bio_segments(bio_src), bs);
	if (!bio)
		return NULL;

	bio->bi_bdev		= bio_src->bi_bdev;
	bio->bi_rw		= bio_src->bi_rw;
	bio->bi_iter.bi_sector	= bio_src->bi_iter.bi_sector;
	bio->bi_iter.bi_size	= bio_src->bi_iter.bi_size;

	if (bio->bi_rw & REQ_DISCARD)
		goto integrity_clone;

	if (bio->bi_rw & REQ_WRITE_SAME) {
		bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0];
		goto integrity_clone;
	}

	bio_for_each_segment(bv, bio_src, iter)
		bio->bi_io_vec[bio->bi_vcnt++] = bv;

integrity_clone:
	if (bio_integrity(bio_src)) {
		int ret;

		ret = bio_integrity_clone(bio, bio_src, gfp_mask);
		if (ret < 0) {
			bio_put(bio);
			return NULL;
		}
	}

	return bio;
}
EXPORT_SYMBOL(bio_clone_bioset);

/**
 *	bio_get_nr_vecs		- return approx number of vecs
 *	@bdev:  I/O target
 *
 *	Return the approximate number of pages we can send to this target.
 *	There's no guarantee that you will be able to fit this number of pages
 *	into a bio, it does not account for dynamic restrictions that vary
 *	on offset.
 */
int bio_get_nr_vecs(struct block_device *bdev)
{
	struct request_queue *q = bdev_get_queue(bdev);
	int nr_pages;

	nr_pages = min_t(unsigned,
		     queue_max_segments(q),
		     queue_max_sectors(q) / (PAGE_SIZE >> 9) + 1);

	return min_t(unsigned, nr_pages, BIO_MAX_PAGES);

}
EXPORT_SYMBOL(bio_get_nr_vecs);

static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
			  *page, unsigned int len, unsigned int offset,
			  unsigned int max_sectors)
{
	int retried_segments = 0;
	struct bio_vec *bvec;

	/*
	 * cloned bio must not modify vec list
	 */
	if (unlikely(bio_flagged(bio, BIO_CLONED)))
		return 0;

	if (((bio->bi_iter.bi_size + len) >> 9) > max_sectors)
		return 0;

	/*
	 * For filesystems with a blocksize smaller than the pagesize
	 * we will often be called with the same page as last time and
	 * a consecutive offset.  Optimize this special case.
	 */
	if (bio->bi_vcnt > 0) {
		struct bio_vec *prev = &bio->bi_io_vec[bio->bi_vcnt - 1];

		if (page == prev->bv_page &&
		    offset == prev->bv_offset + prev->bv_len) {
			unsigned int prev_bv_len = prev->bv_len;
			prev->bv_len += len;

			if (q->merge_bvec_fn) {
				struct bvec_merge_data bvm = {
					/* prev_bvec is already charged in
					   bi_size, discharge it in order to
					   simulate merging updated prev_bvec
					   as new bvec. */
					.bi_bdev = bio->bi_bdev,
					.bi_sector = bio->bi_iter.bi_sector,
					.bi_size = bio->bi_iter.bi_size -
						prev_bv_len,
					.bi_rw = bio->bi_rw,
				};

				if (q->merge_bvec_fn(q, &bvm, prev) < prev->bv_len) {
					prev->bv_len -= len;
					return 0;
				}
			}

			goto done;
		}
	}

	if (bio->bi_vcnt >= bio->bi_max_vecs)
		return 0;

	/*
	 * we might lose a segment or two here, but rather that than
	 * make this too complex.
	 */

	while (bio->bi_phys_segments >= queue_max_segments(q)) {

		if (retried_segments)
			return 0;

		retried_segments = 1;
		blk_recount_segments(q, bio);
	}

	/*
	 * setup the new entry, we might clear it again later if we
	 * cannot add the page
	 */
	bvec = &bio->bi_io_vec[bio->bi_vcnt];
	bvec->bv_page = page;
	bvec->bv_len = len;
	bvec->bv_offset = offset;

	/*
	 * if queue has other restrictions (eg varying max sector size
	 * depending on offset), it can specify a merge_bvec_fn in the
	 * queue to get further control
	 */
	if (q->merge_bvec_fn) {
		struct bvec_merge_data bvm = {
			.bi_bdev = bio->bi_bdev,
			.bi_sector = bio->bi_iter.bi_sector,
			.bi_size = bio->bi_iter.bi_size,
			.bi_rw = bio->bi_rw,
		};

		/*
		 * merge_bvec_fn() returns number of bytes it can accept
		 * at this offset
		 */
		if (q->merge_bvec_fn(q, &bvm, bvec) < bvec->bv_len) {
			bvec->bv_page = NULL;
			bvec->bv_len = 0;
			bvec->bv_offset = 0;
			return 0;
		}
	}

	/* If we may be able to merge these biovecs, force a recount */
	if (bio->bi_vcnt && (BIOVEC_PHYS_MERGEABLE(bvec-1, bvec)))
		bio->bi_flags &= ~(1 << BIO_SEG_VALID);

	bio->bi_vcnt++;
	bio->bi_phys_segments++;
 done:
	bio->bi_iter.bi_size += len;
	return len;
}

/**
 *	bio_add_pc_page	-	attempt to add page to bio
 *	@q: the target queue
 *	@bio: destination bio
 *	@page: page to add
 *	@len: vec entry length
 *	@offset: vec entry offset
 *
 *	Attempt to add a page to the bio_vec maplist. This can fail for a
 *	number of reasons, such as the bio being full or target block device
 *	limitations. The target block device must allow bio's up to PAGE_SIZE,
 *	so it is always possible to add a single page to an empty bio.
 *
 *	This should only be used by REQ_PC bios.
 */
int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page *page,
		    unsigned int len, unsigned int offset)
{
	return __bio_add_page(q, bio, page, len, offset,
			      queue_max_hw_sectors(q));
}
EXPORT_SYMBOL(bio_add_pc_page);

/**
 *	bio_add_page	-	attempt to add page to bio
 *	@bio: destination bio
 *	@page: page to add
 *	@len: vec entry length
 *	@offset: vec entry offset
 *
 *	Attempt to add a page to the bio_vec maplist. This can fail for a
 *	number of reasons, such as the bio being full or target block device
 *	limitations. The target block device must allow bio's up to PAGE_SIZE,
 *	so it is always possible to add a single page to an empty bio.
 */
int bio_add_page(struct bio *bio, struct page *page, unsigned int len,
		 unsigned int offset)
{
	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
	return __bio_add_page(q, bio, page, len, offset, queue_max_sectors(q));
}
EXPORT_SYMBOL(bio_add_page);

struct submit_bio_ret {
	struct completion event;
	int error;
};

static void submit_bio_wait_endio(struct bio *bio, int error)
{
	struct submit_bio_ret *ret = bio->bi_private;

	ret->error = error;
	complete(&ret->event);
}

/**
 * submit_bio_wait - submit a bio, and wait until it completes
 * @rw: whether to %READ or %WRITE, or maybe to %READA (read ahead)
 * @bio: The &struct bio which describes the I/O
 *
 * Simple wrapper around submit_bio(). Returns 0 on success, or the error from
 * bio_endio() on failure.
 */
int submit_bio_wait(int rw, struct bio *bio)
{
	struct submit_bio_ret ret;

	rw |= REQ_SYNC;
	init_completion(&ret.event);
	bio->bi_private = &ret;
	bio->bi_end_io = submit_bio_wait_endio;
	submit_bio(rw, bio);
	wait_for_completion(&ret.event);

	return ret.error;
}
EXPORT_SYMBOL(submit_bio_wait);

/**
 * bio_advance - increment/complete a bio by some number of bytes
 * @bio:	bio to advance
 * @bytes:	number of bytes to complete
 *
 * This updates bi_sector, bi_size and bi_idx; if the number of bytes to
 * complete doesn't align with a bvec boundary, then bv_len and bv_offset will
 * be updated on the last bvec as well.
 *
 * @bio will then represent the remaining, uncompleted portion of the io.
 */
void bio_advance(struct bio *bio, unsigned bytes)
{
	if (bio_integrity(bio))
		bio_integrity_advance(bio, bytes);

	bio_advance_iter(bio, &bio->bi_iter, bytes);
}
EXPORT_SYMBOL(bio_advance);

/**
 * bio_alloc_pages - allocates a single page for each bvec in a bio
 * @bio: bio to allocate pages for
 * @gfp_mask: flags for allocation
 *
 * Allocates pages up to @bio->bi_vcnt.
 *
 * Returns 0 on success, -ENOMEM on failure. On failure, any allocated pages are
 * freed.
 */
int bio_alloc_pages(struct bio *bio, gfp_t gfp_mask)
{
	int i;
	struct bio_vec *bv;

	bio_for_each_segment_all(bv, bio, i) {
		bv->bv_page = alloc_page(gfp_mask);
		if (!bv->bv_page) {
			while (--bv >= bio->bi_io_vec)
				__free_page(bv->bv_page);
			return -ENOMEM;
		}
	}

	return 0;
}
EXPORT_SYMBOL(bio_alloc_pages);

/**
 * bio_copy_data - copy contents of data buffers from one chain of bios to
 * another
 * @src: source bio list
 * @dst: destination bio list
 *
 * If @src and @dst are single bios, bi_next must be NULL - otherwise, treats
 * @src and @dst as linked lists of bios.
 *
 * Stops when it reaches the end of either @src or @dst - that is, copies
 * min(src->bi_size, dst->bi_size) bytes (or the equivalent for lists of bios).
 */
void bio_copy_data(struct bio *dst, struct bio *src)
{
	struct bvec_iter src_iter, dst_iter;
	struct bio_vec src_bv, dst_bv;
	void *src_p, *dst_p;
	unsigned bytes;

	src_iter = src->bi_iter;
	dst_iter = dst->bi_iter;

	while (1) {
		if (!src_iter.bi_size) {
			src = src->bi_next;
			if (!src)
				break;

			src_iter = src->bi_iter;
		}

		if (!dst_iter.bi_size) {
			dst = dst->bi_next;
			if (!dst)
				break;

			dst_iter = dst->bi_iter;
		}

		src_bv = bio_iter_iovec(src, src_iter);
		dst_bv = bio_iter_iovec(dst, dst_iter);

		bytes = min(src_bv.bv_len, dst_bv.bv_len);

		src_p = kmap_atomic(src_bv.bv_page);
		dst_p = kmap_atomic(dst_bv.bv_page);

		memcpy(dst_p + dst_bv.bv_offset,
		       src_p + src_bv.bv_offset,
		       bytes);

		kunmap_atomic(dst_p);
		kunmap_atomic(src_p);

		bio_advance_iter(src, &src_iter, bytes);
		bio_advance_iter(dst, &dst_iter, bytes);
	}
}
EXPORT_SYMBOL(bio_copy_data);

struct bio_map_data {
	int nr_sgvecs;
	int is_our_pages;
	struct sg_iovec sgvecs[];
};

static void bio_set_map_data(struct bio_map_data *bmd, struct bio *bio,
			     struct sg_iovec *iov, int iov_count,
			     int is_our_pages)
{
	memcpy(bmd->sgvecs, iov, sizeof(struct sg_iovec) * iov_count);
	bmd->nr_sgvecs = iov_count;
	bmd->is_our_pages = is_our_pages;
	bio->bi_private = bmd;
}

static struct bio_map_data *bio_alloc_map_data(int nr_segs,
					       unsigned int iov_count,
					       gfp_t gfp_mask)
{
	if (iov_count > UIO_MAXIOV)
		return NULL;

	return kmalloc(sizeof(struct bio_map_data) +
		       sizeof(struct sg_iovec) * iov_count, gfp_mask);
}

static int __bio_copy_iov(struct bio *bio, struct sg_iovec *iov, int iov_count,
			  int to_user, int from_user, int do_free_page)
{
	int ret = 0, i;
	struct bio_vec *bvec;
	int iov_idx = 0;
	unsigned int iov_off = 0;

	bio_for_each_segment_all(bvec, bio, i) {
		char *bv_addr = page_address(bvec->bv_page);
		unsigned int bv_len = bvec->bv_len;

		while (bv_len && iov_idx < iov_count) {
			unsigned int bytes;
			char __user *iov_addr;

			bytes = min_t(unsigned int,
				      iov[iov_idx].iov_len - iov_off, bv_len);
			iov_addr = iov[iov_idx].iov_base + iov_off;

			if (!ret) {
				if (to_user)
					ret = copy_to_user(iov_addr, bv_addr,
							   bytes);

				if (from_user)
					ret = copy_from_user(bv_addr, iov_addr,
							     bytes);

				if (ret)
					ret = -EFAULT;
			}

			bv_len -= bytes;
			bv_addr += bytes;
			iov_addr += bytes;
			iov_off += bytes;

			if (iov[iov_idx].iov_len == iov_off) {
				iov_idx++;
				iov_off = 0;
			}
		}

		if (do_free_page)
			__free_page(bvec->bv_page);
	}

	return ret;
}

/**
 *	bio_uncopy_user	-	finish previously mapped bio
 *	@bio: bio being terminated
 *
 *	Free pages allocated from bio_copy_user() and write back data
 *	to user space in case of a read.
 */
int bio_uncopy_user(struct bio *bio)
{
	struct bio_map_data *bmd = bio->bi_private;
	struct bio_vec *bvec;
	int ret = 0, i;

	if (!bio_flagged(bio, BIO_NULL_MAPPED)) {
		/*
		 * if we're in a workqueue, the request is orphaned, so
		 * don't copy into a random user address space, just free.
		 */
		if (current->mm)
			ret = __bio_copy_iov(bio, bmd->sgvecs, bmd->nr_sgvecs,
					     bio_data_dir(bio) == READ,
					     0, bmd->is_our_pages);
		else if (bmd->is_our_pages)
			bio_for_each_segment_all(bvec, bio, i)
				__free_page(bvec->bv_page);
	}
	kfree(bmd);
	bio_put(bio);
	return ret;
}
EXPORT_SYMBOL(bio_uncopy_user);

/**
 *	bio_copy_user_iov	-	copy user data to bio
 *	@q: destination block queue
 *	@map_data: pointer to the rq_map_data holding pages (if necessary)
 *	@iov:	the iovec.
 *	@iov_count: number of elements in the iovec
 *	@write_to_vm: bool indicating writing to pages or not
 *	@gfp_mask: memory allocation flags
 *
 *	Prepares and returns a bio for indirect user io, bouncing data
 *	to/from kernel pages as necessary. Must be paired with
 *	call bio_uncopy_user() on io completion.
 */
struct bio *bio_copy_user_iov(struct request_queue *q,
			      struct rq_map_data *map_data,
			      struct sg_iovec *iov, int iov_count,
			      int write_to_vm, gfp_t gfp_mask)
{
	struct bio_map_data *bmd;
	struct bio_vec *bvec;
	struct page *page;
	struct bio *bio;
	int i, ret;
	int nr_pages = 0;
	unsigned int len = 0;
	unsigned int offset = map_data ? map_data->offset & ~PAGE_MASK : 0;

	for (i = 0; i < iov_count; i++) {
		unsigned long uaddr;
		unsigned long end;
		unsigned long start;

		uaddr = (unsigned long)iov[i].iov_base;
		end = (uaddr + iov[i].iov_len + PAGE_SIZE - 1) >> PAGE_SHIFT;
		start = uaddr >> PAGE_SHIFT;

		/*
		 * Overflow, abort
		 */
		if (end < start)
			return ERR_PTR(-EINVAL);

		nr_pages += end - start;
		len += iov[i].iov_len;
	}

	if (offset)
		nr_pages++;

	bmd = bio_alloc_map_data(nr_pages, iov_count, gfp_mask);
	if (!bmd)
		return ERR_PTR(-ENOMEM);

	ret = -ENOMEM;
	bio = bio_kmalloc(gfp_mask, nr_pages);
	if (!bio)
		goto out_bmd;

	if (!write_to_vm)
		bio->bi_rw |= REQ_WRITE;

	ret = 0;

	if (map_data) {
		nr_pages = 1 << map_data->page_order;
		i = map_data->offset / PAGE_SIZE;
	}
	while (len) {
		unsigned int bytes = PAGE_SIZE;

		bytes -= offset;

		if (bytes > len)
			bytes = len;

		if (map_data) {
			if (i == map_data->nr_entries * nr_pages) {
				ret = -ENOMEM;
				break;
			}

			page = map_data->pages[i / nr_pages];
			page += (i % nr_pages);

			i++;
		} else {
			page = alloc_page(q->bounce_gfp | gfp_mask);
			if (!page) {
				ret = -ENOMEM;
				break;
			}
		}

		if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes)
			break;

		len -= bytes;
		offset = 0;
	}

	if (ret)
		goto cleanup;

	/*
	 * success
	 */
	if ((!write_to_vm && (!map_data || !map_data->null_mapped)) ||
	    (map_data && map_data->from_user)) {
		ret = __bio_copy_iov(bio, iov, iov_count, 0, 1, 0);
		if (ret)
			goto cleanup;
	}

	bio_set_map_data(bmd, bio, iov, iov_count, map_data ? 0 : 1);
	return bio;
cleanup:
	if (!map_data)
		bio_for_each_segment_all(bvec, bio, i)
			__free_page(bvec->bv_page);

	bio_put(bio);
out_bmd:
	kfree(bmd);
	return ERR_PTR(ret);
}

/**
 *	bio_copy_user	-	copy user data to bio
 *	@q: destination block queue
 *	@map_data: pointer to the rq_map_data holding pages (if necessary)
 *	@uaddr: start of user address
 *	@len: length in bytes
 *	@write_to_vm: bool indicating writing to pages or not
 *	@gfp_mask: memory allocation flags
 *
 *	Prepares and returns a bio for indirect user io, bouncing data
 *	to/from kernel pages as necessary. Must be paired with
 *	call bio_uncopy_user() on io completion.
 */
struct bio *bio_copy_user(struct request_queue *q, struct rq_map_data *map_data,
			  unsigned long uaddr, unsigned int len,
			  int write_to_vm, gfp_t gfp_mask)
{
	struct sg_iovec iov;

	iov.iov_base = (void __user *)uaddr;
	iov.iov_len = len;

	return bio_copy_user_iov(q, map_data, &iov, 1, write_to_vm, gfp_mask);
}
EXPORT_SYMBOL(bio_copy_user);

static struct bio *__bio_map_user_iov(struct request_queue *q,
				      struct block_device *bdev,
				      struct sg_iovec *iov, int iov_count,
				      int write_to_vm, gfp_t gfp_mask)
{
	int i, j;
	int nr_pages = 0;
	struct page **pages;
	struct bio *bio;
	int cur_page = 0;
	int ret, offset;

	for (i = 0; i < iov_count; i++) {
		unsigned long uaddr = (unsigned long)iov[i].iov_base;
		unsigned long len = iov[i].iov_len;
		unsigned long end = (uaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
		unsigned long start = uaddr >> PAGE_SHIFT;

		/*
		 * Overflow, abort
		 */
		if (end < start)
			return ERR_PTR(-EINVAL);

		nr_pages += end - start;
		/*
		 * buffer must be aligned to at least hardsector size for now
		 */
		if (uaddr & queue_dma_alignment(q))
			return ERR_PTR(-EINVAL);
	}

	if (!nr_pages)
		return ERR_PTR(-EINVAL);

	bio = bio_kmalloc(gfp_mask, nr_pages);
	if (!bio)
		return ERR_PTR(-ENOMEM);

	ret = -ENOMEM;
	pages = kcalloc(nr_pages, sizeof(struct page *), gfp_mask);
	if (!pages)
		goto out;

	for (i = 0; i < iov_count; i++) {
		unsigned long uaddr = (unsigned long)iov[i].iov_base;
		unsigned long len = iov[i].iov_len;
		unsigned long end = (uaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
		unsigned long start = uaddr >> PAGE_SHIFT;
		const int local_nr_pages = end - start;
		const int page_limit = cur_page + local_nr_pages;

		ret = get_user_pages_fast(uaddr, local_nr_pages,
				write_to_vm, &pages[cur_page]);
		if (ret < local_nr_pages) {
			ret = -EFAULT;
			goto out_unmap;
		}

		offset = uaddr & ~PAGE_MASK;
		for (j = cur_page; j < page_limit; j++) {
			unsigned int bytes = PAGE_SIZE - offset;

			if (len <= 0)
				break;
			
			if (bytes > len)
				bytes = len;

			/*
			 * sorry...
			 */
			if (bio_add_pc_page(q, bio, pages[j], bytes, offset) <
					    bytes)
				break;

			len -= bytes;
			offset = 0;
		}

		cur_page = j;
		/*
		 * release the pages we didn't map into the bio, if any
		 */
		while (j < page_limit)
			page_cache_release(pages[j++]);
	}

	kfree(pages);

	/*
	 * set data direction, and check if mapped pages need bouncing
	 */
	if (!write_to_vm)
		bio->bi_rw |= REQ_WRITE;

	bio->bi_bdev = bdev;
	bio->bi_flags |= (1 << BIO_USER_MAPPED);
	return bio;

 out_unmap:
	for (i = 0; i < nr_pages; i++) {
		if(!pages[i])
			break;
		page_cache_release(pages[i]);
	}
 out:
	kfree(pages);
	bio_put(bio);
	return ERR_PTR(ret);
}

/**
 *	bio_map_user	-	map user address into bio
 *	@q: the struct request_queue for the bio
 *	@bdev: destination block device
 *	@uaddr: start of user address
 *	@len: length in bytes
 *	@write_to_vm: bool indicating writing to pages or not
 *	@gfp_mask: memory allocation flags
 *
 *	Map the user space address into a bio suitable for io to a block
 *	device. Returns an error pointer in case of error.
 */
struct bio *bio_map_user(struct request_queue *q, struct block_device *bdev,
			 unsigned long uaddr, unsigned int len, int write_to_vm,
			 gfp_t gfp_mask)
{
	struct sg_iovec iov;

	iov.iov_base = (void __user *)uaddr;
	iov.iov_len = len;

	return bio_map_user_iov(q, bdev, &iov, 1, write_to_vm, gfp_mask);
}
EXPORT_SYMBOL(bio_map_user);

/**
 *	bio_map_user_iov - map user sg_iovec table into bio
 *	@q: the struct request_queue for the bio
 *	@bdev: destination block device
 *	@iov:	the iovec.
 *	@iov_count: number of elements in the iovec
 *	@write_to_vm: bool indicating writing to pages or not
 *	@gfp_mask: memory allocation flags
 *
 *	Map the user space address into a bio suitable for io to a block
 *	device. Returns an error pointer in case of error.
 */
struct bio *bio_map_user_iov(struct request_queue *q, struct block_device *bdev,
			     struct sg_iovec *iov, int iov_count,
			     int write_to_vm, gfp_t gfp_mask)
{
	struct bio *bio;

	bio = __bio_map_user_iov(q, bdev, iov, iov_count, write_to_vm,
				 gfp_mask);
	if (IS_ERR(bio))
		return bio;

	/*
	 * subtle -- if __bio_map_user() ended up bouncing a bio,
	 * it would normally disappear when its bi_end_io is run.
	 * however, we need it for the unmap, so grab an extra
	 * reference to it
	 */
	bio_get(bio);

	return bio;
}

static void __bio_unmap_user(struct bio *bio)
{
	struct bio_vec *bvec;
	int i;

	/*
	 * make sure we dirty pages we wrote to
	 */
	bio_for_each_segment_all(bvec, bio, i) {
		if (bio_data_dir(bio) == READ)
			set_page_dirty_lock(bvec->bv_page);

		page_cache_release(bvec->bv_page);
	}

	bio_put(bio);
}

/**
 *	bio_unmap_user	-	unmap a bio
 *	@bio:		the bio being unmapped
 *
 *	Unmap a bio previously mapped by bio_map_user(). Must be called with
 *	a process context.
 *
 *	bio_unmap_user() may sleep.
 */
void bio_unmap_user(struct bio *bio)
{
	__bio_unmap_user(bio);
	bio_put(bio);
}
EXPORT_SYMBOL(bio_unmap_user);

static void bio_map_kern_endio(struct bio *bio, int err)
{
	bio_put(bio);
}

static struct bio *__bio_map_kern(struct request_queue *q, void *data,
				  unsigned int len, gfp_t gfp_mask)
{
	unsigned long kaddr = (unsigned long)data;
	unsigned long end = (kaddr + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
	unsigned long start = kaddr >> PAGE_SHIFT;
	const int nr_pages = end - start;
	int offset, i;
	struct bio *bio;

	bio = bio_kmalloc(gfp_mask, nr_pages);
	if (!bio)
		return ERR_PTR(-ENOMEM);

	offset = offset_in_page(kaddr);
	for (i = 0; i < nr_pages; i++) {
		unsigned int bytes = PAGE_SIZE - offset;

		if (len <= 0)
			break;

		if (bytes > len)
			bytes = len;

		if (bio_add_pc_page(q, bio, virt_to_page(data), bytes,
				    offset) < bytes)
			break;

		data += bytes;
		len -= bytes;
		offset = 0;
	}

	bio->bi_end_io = bio_map_kern_endio;
	return bio;
}

/**
 *	bio_map_kern	-	map kernel address into bio
 *	@q: the struct request_queue for the bio
 *	@data: pointer to buffer to map
 *	@len: length in bytes
 *	@gfp_mask: allocation flags for bio allocation
 *
 *	Map the kernel address into a bio suitable for io to a block
 *	device. Returns an error pointer in case of error.
 */
struct bio *bio_map_kern(struct request_queue *q, void *data, unsigned int len,
			 gfp_t gfp_mask)
{
	struct bio *bio;

	bio = __bio_map_kern(q, data, len, gfp_mask);
	if (IS_ERR(bio))
		return bio;

	if (bio->bi_iter.bi_size == len)
		return bio;

	/*
	 * Don't support partial mappings.
	 */
	bio_put(bio);
	return ERR_PTR(-EINVAL);
}
EXPORT_SYMBOL(bio_map_kern);

static void bio_copy_kern_endio(struct bio *bio, int err)
{
	struct bio_vec *bvec;
	const int read = bio_data_dir(bio) == READ;
	struct bio_map_data *bmd = bio->bi_private;
	int i;
	char *p = bmd->sgvecs[0].iov_base;

	bio_for_each_segment_all(bvec, bio, i) {
		char *addr = page_address(bvec->bv_page);

		if (read)
			memcpy(p, addr, bvec->bv_len);

		__free_page(bvec->bv_page);
		p += bvec->bv_len;
	}

	kfree(bmd);
	bio_put(bio);
}

/**
 *	bio_copy_kern	-	copy kernel address into bio
 *	@q: the struct request_queue for the bio
 *	@data: pointer to buffer to copy
 *	@len: length in bytes
 *	@gfp_mask: allocation flags for bio and page allocation
 *	@reading: data direction is READ
 *
 *	copy the kernel address into a bio suitable for io to a block
 *	device. Returns an error pointer in case of error.
 */
struct bio *bio_copy_kern(struct request_queue *q, void *data, unsigned int len,
			  gfp_t gfp_mask, int reading)
{
	struct bio *bio;
	struct bio_vec *bvec;
	int i;

	bio = bio_copy_user(q, NULL, (unsigned long)data, len, 1, gfp_mask);
	if (IS_ERR(bio))
		return bio;

	if (!reading) {
		void *p = data;

		bio_for_each_segment_all(bvec, bio, i) {
			char *addr = page_address(bvec->bv_page);

			memcpy(addr, p, bvec->bv_len);
			p += bvec->bv_len;
		}
	}

	bio->bi_end_io = bio_copy_kern_endio;

	return bio;
}
EXPORT_SYMBOL(bio_copy_kern);

/*
 * bio_set_pages_dirty() and bio_check_pages_dirty() are support functions
 * for performing direct-IO in BIOs.
 *
 * The problem is that we cannot run set_page_dirty() from interrupt context
 * because the required locks are not interrupt-safe.  So what we can do is to
 * mark the pages dirty _before_ performing IO.  And in interrupt context,
 * check that the pages are still dirty.   If so, fine.  If not, redirty them
 * in process context.
 *
 * We special-case compound pages here: normally this means reads into hugetlb
 * pages.  The logic in here doesn't really work right for compound pages
 * because the VM does not uniformly chase down the head page in all cases.
 * But dirtiness of compound pages is pretty meaningless anyway: the VM doesn't
 * handle them at all.  So we skip compound pages here at an early stage.
 *
 * Note that this code is very hard to test under normal circumstances because
 * direct-io pins the pages with get_user_pages().  This makes
 * is_page_cache_freeable return false, and the VM will not clean the pages.
 * But other code (eg, flusher threads) could clean the pages if they are mapped
 * pagecache.
 *
 * Simply disabling the call to bio_set_pages_dirty() is a good way to test the
 * deferred bio dirtying paths.
 */

/*
 * bio_set_pages_dirty() will mark all the bio's pages as dirty.
 */
void bio_set_pages_dirty(struct bio *bio)
{
	struct bio_vec *bvec;
	int i;

	bio_for_each_segment_all(bvec, bio, i) {
		struct page *page = bvec->bv_page;

		if (page && !PageCompound(page))
			set_page_dirty_lock(page);
	}
}

static void bio_release_pages(struct bio *bio)
{
	struct bio_vec *bvec;
	int i;

	bio_for_each_segment_all(bvec, bio, i) {
		struct page *page = bvec->bv_page;

		if (page)
			put_page(page);
	}
}

/*
 * bio_check_pages_dirty() will check that all the BIO's pages are still dirty.
 * If they are, then fine.  If, however, some pages are clean then they must
 * have been written out during the direct-IO read.  So we take another ref on
 * the BIO and the offending pages and re-dirty the pages in process context.
 *
 * It is expected that bio_check_pages_dirty() will wholly own the BIO from
 * here on.  It will run one page_cache_release() against each page and will
 * run one bio_put() against the BIO.
 */

static void bio_dirty_fn(struct work_struct *work);

static DECLARE_WORK(bio_dirty_work, bio_dirty_fn);
static DEFINE_SPINLOCK(bio_dirty_lock);
static struct bio *bio_dirty_list;

/*
 * This runs in process context
 */
static void bio_dirty_fn(struct work_struct *work)
{
	unsigned long flags;
	struct bio *bio;

	spin_lock_irqsave(&bio_dirty_lock, flags);
	bio = bio_dirty_list;
	bio_dirty_list = NULL;
	spin_unlock_irqrestore(&bio_dirty_lock, flags);

	while (bio) {
		struct bio *next = bio->bi_private;

		bio_set_pages_dirty(bio);
		bio_release_pages(bio);
		bio_put(bio);
		bio = next;
	}
}

void bio_check_pages_dirty(struct bio *bio)
{
	struct bio_vec *bvec;
	int nr_clean_pages = 0;
	int i;

	bio_for_each_segment_all(bvec, bio, i) {
		struct page *page = bvec->bv_page;

		if (PageDirty(page) || PageCompound(page)) {
			page_cache_release(page);
			bvec->bv_page = NULL;
		} else {
			nr_clean_pages++;
		}
	}

	if (nr_clean_pages) {
		unsigned long flags;

		spin_lock_irqsave(&bio_dirty_lock, flags);
		bio->bi_private = bio_dirty_list;
		bio_dirty_list = bio;
		spin_unlock_irqrestore(&bio_dirty_lock, flags);
		schedule_work(&bio_dirty_work);
	} else {
		bio_put(bio);
	}
}

#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
void bio_flush_dcache_pages(struct bio *bi)
{
	struct bio_vec bvec;
	struct bvec_iter iter;

	bio_for_each_segment(bvec, bi, iter)
		flush_dcache_page(bvec.bv_page);
}
EXPORT_SYMBOL(bio_flush_dcache_pages);
#endif

/**
 * bio_endio - end I/O on a bio
 * @bio:	bio
 * @error:	error, if any
 *
 * Description:
 *   bio_endio() will end I/O on the whole bio. bio_endio() is the
 *   preferred way to end I/O on a bio, it takes care of clearing
 *   BIO_UPTODATE on error. @error is 0 on success, and and one of the
 *   established -Exxxx (-EIO, for instance) error values in case
 *   something went wrong. No one should call bi_end_io() directly on a
 *   bio unless they own it and thus know that it has an end_io
 *   function.
 **/
void bio_endio(struct bio *bio, int error)
{
	while (bio) {
		BUG_ON(atomic_read(&bio->bi_remaining) <= 0);

		if (error)
			clear_bit(BIO_UPTODATE, &bio->bi_flags);
		else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
			error = -EIO;

		if (!atomic_dec_and_test(&bio->bi_remaining))
			return;

		/*
		 * Need to have a real endio function for chained bios,
		 * otherwise various corner cases will break (like stacking
		 * block devices that save/restore bi_end_io) - however, we want
		 * to avoid unbounded recursion and blowing the stack. Tail call
		 * optimization would handle this, but compiling with frame
		 * pointers also disables gcc's sibling call optimization.
		 */
		if (bio->bi_end_io == bio_chain_endio) {
			struct bio *parent = bio->bi_private;
			bio_put(bio);
			bio = parent;
		} else {
			if (bio->bi_end_io)
				bio->bi_end_io(bio, error);
			bio = NULL;
		}
	}
}
EXPORT_SYMBOL(bio_endio);

/**
 * bio_endio_nodec - end I/O on a bio, without decrementing bi_remaining
 * @bio:	bio
 * @error:	error, if any
 *
 * For code that has saved and restored bi_end_io; thing hard before using this
 * function, probably you should've cloned the entire bio.
 **/
void bio_endio_nodec(struct bio *bio, int error)
{
	atomic_inc(&bio->bi_remaining);
	bio_endio(bio, error);
}
EXPORT_SYMBOL(bio_endio_nodec);

/**
 * bio_split - split a bio
 * @bio:	bio to split
 * @sectors:	number of sectors to split from the front of @bio
 * @gfp:	gfp mask
 * @bs:		bio set to allocate from
 *
 * Allocates and returns a new bio which represents @sectors from the start of
 * @bio, and updates @bio to represent the remaining sectors.
 *
 * The newly allocated bio will point to @bio's bi_io_vec; it is the caller's
 * responsibility to ensure that @bio is not freed before the split.
 */
struct bio *bio_split(struct bio *bio, int sectors,
		      gfp_t gfp, struct bio_set *bs)
{
	struct bio *split = NULL;

	BUG_ON(sectors <= 0);
	BUG_ON(sectors >= bio_sectors(bio));

	split = bio_clone_fast(bio, gfp, bs);
	if (!split)
		return NULL;

	split->bi_iter.bi_size = sectors << 9;

	if (bio_integrity(split))
		bio_integrity_trim(split, 0, sectors);

	bio_advance(bio, split->bi_iter.bi_size);

	return split;
}
EXPORT_SYMBOL(bio_split);

/**
 * bio_trim - trim a bio
 * @bio:	bio to trim
 * @offset:	number of sectors to trim from the front of @bio
 * @size:	size we want to trim @bio to, in sectors
 */
void bio_trim(struct bio *bio, int offset, int size)
{
	/* 'bio' is a cloned bio which we need to trim to match
	 * the given offset and size.
	 */

	size <<= 9;
	if (offset == 0 && size == bio->bi_iter.bi_size)
		return;

	clear_bit(BIO_SEG_VALID, &bio->bi_flags);

	bio_advance(bio, offset << 9);

	bio->bi_iter.bi_size = size;
}
EXPORT_SYMBOL_GPL(bio_trim);

/*
 * create memory pools for biovec's in a bio_set.
 * use the global biovec slabs created for general use.
 */
mempool_t *biovec_create_pool(struct bio_set *bs, int pool_entries)
{
	struct biovec_slab *bp = bvec_slabs + BIOVEC_MAX_IDX;

	return mempool_create_slab_pool(pool_entries, bp->slab);
}

void bioset_free(struct bio_set *bs)
{
	if (bs->rescue_workqueue)
		destroy_workqueue(bs->rescue_workqueue);

	if (bs->bio_pool)
		mempool_destroy(bs->bio_pool);

	if (bs->bvec_pool)
		mempool_destroy(bs->bvec_pool);

	bioset_integrity_free(bs);
	bio_put_slab(bs);

	kfree(bs);
}
EXPORT_SYMBOL(bioset_free);

/**
 * bioset_create  - Create a bio_set
 * @pool_size:	Number of bio and bio_vecs to cache in the mempool
 * @front_pad:	Number of bytes to allocate in front of the returned bio
 *
 * Description:
 *    Set up a bio_set to be used with @bio_alloc_bioset. Allows the caller
 *    to ask for a number of bytes to be allocated in front of the bio.
 *    Front pad allocation is useful for embedding the bio inside
 *    another structure, to avoid allocating extra data to go with the bio.
 *    Note that the bio must be embedded at the END of that structure always,
 *    or things will break badly.
 */
struct bio_set *bioset_create(unsigned int pool_size, unsigned int front_pad)
{
	unsigned int back_pad = BIO_INLINE_VECS * sizeof(struct bio_vec);
	struct bio_set *bs;

	bs = kzalloc(sizeof(*bs), GFP_KERNEL);
	if (!bs)
		return NULL;

	bs->front_pad = front_pad;

	spin_lock_init(&bs->rescue_lock);
	bio_list_init(&bs->rescue_list);
	INIT_WORK(&bs->rescue_work, bio_alloc_rescue);

	bs->bio_slab = bio_find_or_create_slab(front_pad + back_pad);
	if (!bs->bio_slab) {
		kfree(bs);
		return NULL;
	}

	bs->bio_pool = mempool_create_slab_pool(pool_size, bs->bio_slab);
	if (!bs->bio_pool)
		goto bad;

	bs->bvec_pool = biovec_create_pool(bs, pool_size);
	if (!bs->bvec_pool)
		goto bad;

	bs->rescue_workqueue = alloc_workqueue("bioset", WQ_MEM_RECLAIM, 0);
	if (!bs->rescue_workqueue)
		goto bad;

	return bs;
bad:
	bioset_free(bs);
	return NULL;
}
EXPORT_SYMBOL(bioset_create);

#ifdef CONFIG_BLK_CGROUP
/**
 * bio_associate_current - associate a bio with %current
 * @bio: target bio
 *
 * Associate @bio with %current if it hasn't been associated yet.  Block
 * layer will treat @bio as if it were issued by %current no matter which
 * task actually issues it.
 *
 * This function takes an extra reference of @task's io_context and blkcg
 * which will be put when @bio is released.  The caller must own @bio,
 * ensure %current->io_context exists, and is responsible for synchronizing
 * calls to this function.
 */
int bio_associate_current(struct bio *bio)
{
	struct io_context *ioc;
	struct cgroup_subsys_state *css;

	if (bio->bi_ioc)
		return -EBUSY;

	ioc = current->io_context;
	if (!ioc)
		return -ENOENT;

	/* acquire active ref on @ioc and associate */
	get_io_context_active(ioc);
	bio->bi_ioc = ioc;

	/* associate blkcg if exists */
	rcu_read_lock();
	css = task_css(current, blkio_subsys_id);
	if (css && css_tryget(css))
		bio->bi_css = css;
	rcu_read_unlock();

	return 0;
}

/**
 * bio_disassociate_task - undo bio_associate_current()
 * @bio: target bio
 */
void bio_disassociate_task(struct bio *bio)
{
	if (bio->bi_ioc) {
		put_io_context(bio->bi_ioc);
		bio->bi_ioc = NULL;
	}
	if (bio->bi_css) {
		css_put(bio->bi_css);
		bio->bi_css = NULL;
	}
}

#endif /* CONFIG_BLK_CGROUP */

static void __init biovec_init_slabs(void)
{
	int i;

	for (i = 0; i < BIOVEC_NR_POOLS; i++) {
		int size;
		struct biovec_slab *bvs = bvec_slabs + i;

		if (bvs->nr_vecs <= BIO_INLINE_VECS) {
			bvs->slab = NULL;
			continue;
		}

		size = bvs->nr_vecs * sizeof(struct bio_vec);
		bvs->slab = kmem_cache_create(bvs->name, size, 0,
                                SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
	}
}

static int __init init_bio(void)
{
	bio_slab_max = 2;
	bio_slab_nr = 0;
	bio_slabs = kzalloc(bio_slab_max * sizeof(struct bio_slab), GFP_KERNEL);
	if (!bio_slabs)
		panic("bio: can't allocate bios\n");

	bio_integrity_init();
	biovec_init_slabs();

	fs_bio_set = bioset_create(BIO_POOL_SIZE, 0);
	if (!fs_bio_set)
		panic("bio: can't allocate bios\n");

	if (bioset_integrity_create(fs_bio_set, BIO_POOL_SIZE))
		panic("bio: can't create integrity pool\n");

	return 0;
}
subsys_initcall(init_bio);