• Brent Casavant's avatar
    [PATCH] alloc_large_system_hash: NUMA interleaving · dcee73c4
    Brent Casavant authored
    NUMA systems running current Linux kernels suffer from substantial inequities
    in the amount of memory allocated from each NUMA node during boot.  In
    particular, several large hashes are allocated using alloc_bootmem, and as
    such are allocated contiguously from a single node each.
    
    This becomes a problem for certain workloads that are relatively common on
    big-iron HPC NUMA systems.  In particular, a number of MPI and OpenMP
    applications which require nearly all available processors in the system and
    nearly all the memory on each node run into difficulties.  Due to the uneven
    memory distribution onto a few nodes, any thread on those nodes will require a
    portion of its memory be allocated from remote nodes.  Any access to those
    memory locations will be slower than local accesses, and thereby slows down
    the effective computation rate for the affected CPUs/threads.  This problem is
    further amplified if the application is tightly synchronized between threads
    (as is often the case), as they entire job can run only at the speed of the
    slowest thread.
    
    Additionally since these hashes are usually accessed by all CPUS in the
    system, the NUMA network link on the node which hosts the hash experiences
    disproportionate traffic levels, thereby reducing the memory bandwidth
    available to that node's CPUs, and further penalizing performance of the
    threads executed thereupon.
    
    As such, it is desired to find a way to distribute these large hash
    allocations more evenly across NUMA nodes.  Fortunately current kernels do
    perform allocation interleaving for vmalloc() during boot, which provides a
    stepping stone to a solution.
    
    This series of patches enables (but does not require) the kernel to allocate
    several boot time hashes using vmalloc rather than alloc_bootmem, thereby
    causing the hashes to be interleaved amongst NUMA nodes.  In particular the
    dentry cache, inode cache, TCP ehash, and TCP bhash have been changed to be
    allocated in this manner.  Due to the limited vmalloc space on architectures
    such as i386, this behavior is turned on by default only for IA64 NUMA systems
    (though there is no reason other interested architectures could not enable it
    if desired).  Non-IA64 and non-NUMA systems continue to use the existing
    alloc_bootmem() allocation mechanism.  A boot line parameter "hashdist" can be
    set to override the default behavior.
    
    The following two sets of example output show the uneven distribution just
    after boot, using init=/bin/sh to eliminate as much non-kernel allocation as
    possible.
    
    Without the boot hash distribution patches:
    
     Nid  MemTotal   MemFree   MemUsed      (in kB)
       0   3870656   3697696    172960
       1   3882992   3866656     16336
       2   3883008   3866784     16224
       3   3882992   3866464     16528
       4   3883008   3866592     16416
       5   3883008   3866720     16288
       6   3882992   3342176    540816
       7   3883008   3865440     17568
       8   3882992   3866560     16432
       9   3883008   3866400     16608
      10   3882992   3866592     16400
      11   3883008   3866400     16608
      12   3882992   3866400     16592
      13   3883008   3866432     16576
      14   3883008   3866528     16480
      15   3864768   3848256     16512
     ToT  62097440  61152096    945344
    
    Notice that nodes 0 and 6 have a substantially larger memory utilization
    than all other nodes.
    
    With the boot hash distribution patch:
    
     Nid  MemTotal   MemFree   MemUsed      (in kB)
       0   3870656   3789792     80864
       1   3882992   3843776     39216
       2   3883008   3843808     39200
       3   3882992   3843904     39088
       4   3883008   3827488     55520
       5   3883008   3843712     39296
       6   3882992   3843936     39056
       7   3883008   3844096     38912
       8   3882992   3843712     39280
       9   3883008   3844000     39008
      10   3882992   3843872     39120
      11   3883008   3843872     39136
      12   3882992   3843808     39184
      13   3883008   3843936     39072
      14   3883008   3843712     39296
      15   3864768   3825760     39008
     ToT  62097440  61413184    684256
    
    While not perfectly even, we can see that there is a substantial improvement
    in the spread of memory allocated by the kernel during boot.  The remaining
    uneveness may be due in part to further boot time allocations that could be
    addressed in a similar manner, but some difference is due to the somewhat
    special nature of node 0 during boot.  However the uneveness has fallen to a
    much more acceptable level (at least to a level that SGI isn't concerned
    about).
    
    The astute reader will also notice that in this example, with this patch
    approximately 256 MB less memory was allocated during boot.  This is due to
    the size limits of a single vmalloc.  More specifically, this is because the
    automatically computed size of the TCP ehash exceeds the maximum size which a
    single vmalloc can accomodate.  However this is of little practical concern as
    the vmalloc size limit simply reduces one ridiculously large allocation
    (512MB) to a slightly less ridiculously large allocation (256MB).  In practice
    machines with large memory configurations are using the thash_entries setting
    to limit the size of the TCP ehash _much_ lower than either of the
    automatically computed values.  Illustrative of the exceedingly large nature
    of the automatically computed size, SGI currently recommends that customers
    boot with thash_entries=2097152, which works out to a 32MB allocation.  In any
    case, setting hashdist=0 will allow for allocations in excess of vmalloc
    limits, if so desired.
    
    Other than the vmalloc limit, great care was taken to ensure that the size of
    TCP hash allocations was not altered by this patch.  Due to slightly different
    computation techniques between the existing TCP code and
    alloc_large_system_hash (which is now utilized), some of the magic constants
    in the TCP hash allocation code were changed.  On all sizes of system (128MB
    through 64GB) that I had access to, the patched code preserves the previous
    hash size, as long as the vmalloc limit (256MB on IA64) is not encountered.
    
    There was concern that changing the TCP-related hashes to use vmalloc space
    may adversely impact network performance.  To this end the netperf set of
    benchmarks was run.  Some individual tests seemed to benefit slightly, some
    seemed to be harmed slightly, but in all cases the average difference with and
    without these patches was well within the variabilty I would see from run to
    run.
    
    The following is the overall netperf averages (30 10 second runs each) against
    an older kernel with these same patches.  These tests were run over loopback
    as GigE results were so inconsistent run to run both with and without these
    patches that they provided no meaningful comparison that I could discern.  I
    used the same kernel (IA64 generic) for each run, simply varying the new
    "hashdist" boot parameter to turn on or off the new allocation behavior.  In
    all cases the thash_entries value was manually specified as discussed
    previously to eliminate any variability that might result from that size
    difference.
    
    HP ZX1, hashdist=0
    ==================
    TCP_RR = 19389
    TCP_MAERTS = 6561 
    TCP_STREAM = 6590 
    TCP_CC = 9483
    TCP_CRR = 8633 
    
    HP ZX1, hashdist=1
    ==================
    TCP_RR = 19411
    TCP_MAERTS = 6559 
    TCP_STREAM = 6584 
    TCP_CC = 9454
    TCP_CRR = 8626 
    
    SGI Altix, hashdist=0
    =====================
    TCP_RR = 16871
    TCP_MAERTS = 3925 
    TCP_STREAM = 4055 
    TCP_CC = 8438
    TCP_CRR = 7750 
    
    SGI Altix, hashdist=1
    =====================
    TCP_RR = 17040
    TCP_MAERTS = 3913 
    TCP_STREAM = 4044 
    TCP_CC = 8367
    TCP_CRR = 7538 
    
    I believe the TCP_CC and TCP_CRR are the tests most sensitive to this
    particular change.  But again, I want to emphasize that even the differences
    you see above are _well_ within the variability I saw from run to run of any
    given test.
    
    In addition, Jose Santos at IBM has run specSFS, which has been particularly
    sensitive to TLB issues, against these patches and saw no performance
    degredation (differences down in the noise).
    
    
    
    This patch:
    
    Modifies alloc_large_system_hash to enable the use of vmalloc to alleviate
    boottime allocation imbalances on NUMA systems.
    
    Due to limited vmalloc space on some architectures (i.e.  x86), the use of
    vmalloc is enabled by default only on NUMA IA64 kernels.  There should be
    no problem enabling this change for any other interested NUMA architecture.
    Signed-off-by: default avatarBrent Casavant <bcasavan@sgi.com>
    Signed-off-by: default avatarAndrew Morton <akpm@osdl.org>
    Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
    dcee73c4
dcache.c 41.4 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
/*
 * fs/dcache.c
 *
 * Complete reimplementation
 * (C) 1997 Thomas Schoebel-Theuer,
 * with heavy changes by Linus Torvalds
 */

/*
 * Notes on the allocation strategy:
 *
 * The dcache is a master of the icache - whenever a dcache entry
 * exists, the inode will always exist. "iput()" is done either when
 * the dcache entry is deleted or garbage collected.
 */

#include <linux/config.h>
#include <linux/syscalls.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/smp_lock.h>
#include <linux/hash.h>
#include <linux/cache.h>
#include <linux/module.h>
#include <linux/mount.h>
#include <linux/file.h>
#include <asm/uaccess.h>
#include <linux/security.h>
#include <linux/seqlock.h>
#include <linux/swap.h>
#include <linux/bootmem.h>

/* #define DCACHE_DEBUG 1 */

int sysctl_vfs_cache_pressure = 100;

spinlock_t dcache_lock __cacheline_aligned_in_smp = SPIN_LOCK_UNLOCKED;
seqlock_t rename_lock __cacheline_aligned_in_smp = SEQLOCK_UNLOCKED;

EXPORT_SYMBOL(dcache_lock);

static kmem_cache_t *dentry_cache; 

#define DNAME_INLINE_LEN (sizeof(struct dentry)-offsetof(struct dentry,d_iname))

/*
 * This is the single most critical data structure when it comes
 * to the dcache: the hashtable for lookups. Somebody should try
 * to make this good - I've just made it work.
 *
 * This hash-function tries to avoid losing too many bits of hash
 * information, yet avoid using a prime hash-size or similar.
 */
#define D_HASHBITS     d_hash_shift
#define D_HASHMASK     d_hash_mask

static unsigned int d_hash_mask;
static unsigned int d_hash_shift;
static struct hlist_head *dentry_hashtable;
static LIST_HEAD(dentry_unused);

/* Statistics gathering. */
struct dentry_stat_t dentry_stat = {
	.age_limit = 45,
};

static void d_callback(struct rcu_head *head)
{
	struct dentry * dentry = container_of(head, struct dentry, d_rcu);

	if (dname_external(dentry))
		kfree(dentry->d_name.name);
	kmem_cache_free(dentry_cache, dentry); 
}

/*
 * no dcache_lock, please.  The caller must decrement dentry_stat.nr_dentry
 * inside dcache_lock.
 */
static void d_free(struct dentry *dentry)
{
	if (dentry->d_op && dentry->d_op->d_release)
		dentry->d_op->d_release(dentry);
 	call_rcu(&dentry->d_rcu, d_callback);
}

/*
 * Release the dentry's inode, using the filesystem
 * d_iput() operation if defined.
 * Called with dcache_lock and per dentry lock held, drops both.
 */
static inline void dentry_iput(struct dentry * dentry)
{
	struct inode *inode = dentry->d_inode;
	if (inode) {
		dentry->d_inode = NULL;
		list_del_init(&dentry->d_alias);
		spin_unlock(&dentry->d_lock);
		spin_unlock(&dcache_lock);
		if (dentry->d_op && dentry->d_op->d_iput)
			dentry->d_op->d_iput(dentry, inode);
		else
			iput(inode);
	} else {
		spin_unlock(&dentry->d_lock);
		spin_unlock(&dcache_lock);
	}
}

/* 
 * This is dput
 *
 * This is complicated by the fact that we do not want to put
 * dentries that are no longer on any hash chain on the unused
 * list: we'd much rather just get rid of them immediately.
 *
 * However, that implies that we have to traverse the dentry
 * tree upwards to the parents which might _also_ now be
 * scheduled for deletion (it may have been only waiting for
 * its last child to go away).
 *
 * This tail recursion is done by hand as we don't want to depend
 * on the compiler to always get this right (gcc generally doesn't).
 * Real recursion would eat up our stack space.
 */

/*
 * dput - release a dentry
 * @dentry: dentry to release 
 *
 * Release a dentry. This will drop the usage count and if appropriate
 * call the dentry unlink method as well as removing it from the queues and
 * releasing its resources. If the parent dentries were scheduled for release
 * they too may now get deleted.
 *
 * no dcache lock, please.
 */

void dput(struct dentry *dentry)
{
	if (!dentry)
		return;

repeat:
	if (atomic_read(&dentry->d_count) == 1)
		might_sleep();
	if (!atomic_dec_and_lock(&dentry->d_count, &dcache_lock))
		return;

	spin_lock(&dentry->d_lock);
	if (atomic_read(&dentry->d_count)) {
		spin_unlock(&dentry->d_lock);
		spin_unlock(&dcache_lock);
		return;
	}
			
	/*
	 * AV: ->d_delete() is _NOT_ allowed to block now.
	 */
	if (dentry->d_op && dentry->d_op->d_delete) {
		if (dentry->d_op->d_delete(dentry))
			goto unhash_it;
	}
	/* Unreachable? Get rid of it */
 	if (d_unhashed(dentry))
		goto kill_it;
  	if (list_empty(&dentry->d_lru)) {
  		dentry->d_flags |= DCACHE_REFERENCED;
  		list_add(&dentry->d_lru, &dentry_unused);
  		dentry_stat.nr_unused++;
  	}
 	spin_unlock(&dentry->d_lock);
	spin_unlock(&dcache_lock);
	return;

unhash_it:
	__d_drop(dentry);

kill_it: {
		struct dentry *parent;

		/* If dentry was on d_lru list
		 * delete it from there
		 */
  		if (!list_empty(&dentry->d_lru)) {
  			list_del(&dentry->d_lru);
  			dentry_stat.nr_unused--;
  		}
  		list_del(&dentry->d_child);
		dentry_stat.nr_dentry--;	/* For d_free, below */
		/*drops the locks, at that point nobody can reach this dentry */
		dentry_iput(dentry);
		parent = dentry->d_parent;
		d_free(dentry);
		if (dentry == parent)
			return;
		dentry = parent;
		goto repeat;
	}
}

/**
 * d_invalidate - invalidate a dentry
 * @dentry: dentry to invalidate
 *
 * Try to invalidate the dentry if it turns out to be
 * possible. If there are other dentries that can be
 * reached through this one we can't delete it and we
 * return -EBUSY. On success we return 0.
 *
 * no dcache lock.
 */
 
int d_invalidate(struct dentry * dentry)
{
	/*
	 * If it's already been dropped, return OK.
	 */
	spin_lock(&dcache_lock);
	if (d_unhashed(dentry)) {
		spin_unlock(&dcache_lock);
		return 0;
	}
	/*
	 * Check whether to do a partial shrink_dcache
	 * to get rid of unused child entries.
	 */
	if (!list_empty(&dentry->d_subdirs)) {
		spin_unlock(&dcache_lock);
		shrink_dcache_parent(dentry);
		spin_lock(&dcache_lock);
	}

	/*
	 * Somebody else still using it?
	 *
	 * If it's a directory, we can't drop it
	 * for fear of somebody re-populating it
	 * with children (even though dropping it
	 * would make it unreachable from the root,
	 * we might still populate it if it was a
	 * working directory or similar).
	 */
	spin_lock(&dentry->d_lock);
	if (atomic_read(&dentry->d_count) > 1) {
		if (dentry->d_inode && S_ISDIR(dentry->d_inode->i_mode)) {
			spin_unlock(&dentry->d_lock);
			spin_unlock(&dcache_lock);
			return -EBUSY;
		}
	}

	__d_drop(dentry);
	spin_unlock(&dentry->d_lock);
	spin_unlock(&dcache_lock);
	return 0;
}

/* This should be called _only_ with dcache_lock held */

static inline struct dentry * __dget_locked(struct dentry *dentry)
{
	atomic_inc(&dentry->d_count);
	if (!list_empty(&dentry->d_lru)) {
		dentry_stat.nr_unused--;
		list_del_init(&dentry->d_lru);
	}
	return dentry;
}

struct dentry * dget_locked(struct dentry *dentry)
{
	return __dget_locked(dentry);
}

/**
 * d_find_alias - grab a hashed alias of inode
 * @inode: inode in question
 * @want_discon:  flag, used by d_splice_alias, to request
 *          that only a DISCONNECTED alias be returned.
 *
 * If inode has a hashed alias, or is a directory and has any alias,
 * acquire the reference to alias and return it. Otherwise return NULL.
 * Notice that if inode is a directory there can be only one alias and
 * it can be unhashed only if it has no children, or if it is the root
 * of a filesystem.
 *
 * If the inode has a DCACHE_DISCONNECTED alias, then prefer
 * any other hashed alias over that one unless @want_discon is set,
 * in which case only return a DCACHE_DISCONNECTED alias.
 */

static struct dentry * __d_find_alias(struct inode *inode, int want_discon)
{
	struct list_head *head, *next, *tmp;
	struct dentry *alias, *discon_alias=NULL;

	head = &inode->i_dentry;
	next = inode->i_dentry.next;
	while (next != head) {
		tmp = next;
		next = tmp->next;
		prefetch(next);
		alias = list_entry(tmp, struct dentry, d_alias);
 		if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) {
			if (alias->d_flags & DCACHE_DISCONNECTED)
				discon_alias = alias;
			else if (!want_discon) {
				__dget_locked(alias);
				return alias;
			}
		}
	}
	if (discon_alias)
		__dget_locked(discon_alias);
	return discon_alias;
}

struct dentry * d_find_alias(struct inode *inode)
{
	struct dentry *de;
	spin_lock(&dcache_lock);
	de = __d_find_alias(inode, 0);
	spin_unlock(&dcache_lock);
	return de;
}

/*
 *	Try to kill dentries associated with this inode.
 * WARNING: you must own a reference to inode.
 */
void d_prune_aliases(struct inode *inode)
{
	struct list_head *tmp, *head = &inode->i_dentry;
restart:
	spin_lock(&dcache_lock);
	tmp = head;
	while ((tmp = tmp->next) != head) {
		struct dentry *dentry = list_entry(tmp, struct dentry, d_alias);
		if (!atomic_read(&dentry->d_count)) {
			__dget_locked(dentry);
			__d_drop(dentry);
			spin_unlock(&dcache_lock);
			dput(dentry);
			goto restart;
		}
	}
	spin_unlock(&dcache_lock);
}

/*
 * Throw away a dentry - free the inode, dput the parent.
 * This requires that the LRU list has already been
 * removed.
 * Called with dcache_lock, drops it and then regains.
 */
static inline void prune_one_dentry(struct dentry * dentry)
{
	struct dentry * parent;

	__d_drop(dentry);
	list_del(&dentry->d_child);
	dentry_stat.nr_dentry--;	/* For d_free, below */
	dentry_iput(dentry);
	parent = dentry->d_parent;
	d_free(dentry);
	if (parent != dentry)
		dput(parent);
	spin_lock(&dcache_lock);
}

/**
 * prune_dcache - shrink the dcache
 * @count: number of entries to try and free
 *
 * Shrink the dcache. This is done when we need
 * more memory, or simply when we need to unmount
 * something (at which point we need to unuse
 * all dentries).
 *
 * This function may fail to free any resources if
 * all the dentries are in use.
 */
 
static void prune_dcache(int count)
{
	spin_lock(&dcache_lock);
	for (; count ; count--) {
		struct dentry *dentry;
		struct list_head *tmp;

		tmp = dentry_unused.prev;
		if (tmp == &dentry_unused)
			break;
		list_del_init(tmp);
		prefetch(dentry_unused.prev);
 		dentry_stat.nr_unused--;
		dentry = list_entry(tmp, struct dentry, d_lru);

 		spin_lock(&dentry->d_lock);
		/*
		 * We found an inuse dentry which was not removed from
		 * dentry_unused because of laziness during lookup.  Do not free
		 * it - just keep it off the dentry_unused list.
		 */
 		if (atomic_read(&dentry->d_count)) {
 			spin_unlock(&dentry->d_lock);
			continue;
		}
		/* If the dentry was recently referenced, don't free it. */
		if (dentry->d_flags & DCACHE_REFERENCED) {
			dentry->d_flags &= ~DCACHE_REFERENCED;
 			list_add(&dentry->d_lru, &dentry_unused);
 			dentry_stat.nr_unused++;
 			spin_unlock(&dentry->d_lock);
			continue;
		}
		prune_one_dentry(dentry);
	}
	spin_unlock(&dcache_lock);
}

/*
 * Shrink the dcache for the specified super block.
 * This allows us to unmount a device without disturbing
 * the dcache for the other devices.
 *
 * This implementation makes just two traversals of the
 * unused list.  On the first pass we move the selected
 * dentries to the most recent end, and on the second
 * pass we free them.  The second pass must restart after
 * each dput(), but since the target dentries are all at
 * the end, it's really just a single traversal.
 */

/**
 * shrink_dcache_sb - shrink dcache for a superblock
 * @sb: superblock
 *
 * Shrink the dcache for the specified super block. This
 * is used to free the dcache before unmounting a file
 * system
 */

void shrink_dcache_sb(struct super_block * sb)
{
	struct list_head *tmp, *next;
	struct dentry *dentry;

	/*
	 * Pass one ... move the dentries for the specified
	 * superblock to the most recent end of the unused list.
	 */
	spin_lock(&dcache_lock);
	next = dentry_unused.next;
	while (next != &dentry_unused) {
		tmp = next;
		next = tmp->next;
		dentry = list_entry(tmp, struct dentry, d_lru);
		if (dentry->d_sb != sb)
			continue;
		list_del(tmp);
		list_add(tmp, &dentry_unused);
	}

	/*
	 * Pass two ... free the dentries for this superblock.
	 */
repeat:
	next = dentry_unused.next;
	while (next != &dentry_unused) {
		tmp = next;
		next = tmp->next;
		dentry = list_entry(tmp, struct dentry, d_lru);
		if (dentry->d_sb != sb)
			continue;
		dentry_stat.nr_unused--;
		list_del_init(tmp);
		spin_lock(&dentry->d_lock);
		if (atomic_read(&dentry->d_count)) {
			spin_unlock(&dentry->d_lock);
			continue;
		}
		prune_one_dentry(dentry);
		goto repeat;
	}
	spin_unlock(&dcache_lock);
}

/*
 * Search for at least 1 mount point in the dentry's subdirs.
 * We descend to the next level whenever the d_subdirs
 * list is non-empty and continue searching.
 */
 
/**
 * have_submounts - check for mounts over a dentry
 * @parent: dentry to check.
 *
 * Return true if the parent or its subdirectories contain
 * a mount point
 */
 
int have_submounts(struct dentry *parent)
{
	struct dentry *this_parent = parent;
	struct list_head *next;

	spin_lock(&dcache_lock);
	if (d_mountpoint(parent))
		goto positive;
repeat:
	next = this_parent->d_subdirs.next;
resume:
	while (next != &this_parent->d_subdirs) {
		struct list_head *tmp = next;
		struct dentry *dentry = list_entry(tmp, struct dentry, d_child);
		next = tmp->next;
		/* Have we found a mount point ? */
		if (d_mountpoint(dentry))
			goto positive;
		if (!list_empty(&dentry->d_subdirs)) {
			this_parent = dentry;
			goto repeat;
		}
	}
	/*
	 * All done at this level ... ascend and resume the search.
	 */
	if (this_parent != parent) {
		next = this_parent->d_child.next; 
		this_parent = this_parent->d_parent;
		goto resume;
	}
	spin_unlock(&dcache_lock);
	return 0; /* No mount points found in tree */
positive:
	spin_unlock(&dcache_lock);
	return 1;
}

/*
 * Search the dentry child list for the specified parent,
 * and move any unused dentries to the end of the unused
 * list for prune_dcache(). We descend to the next level
 * whenever the d_subdirs list is non-empty and continue
 * searching.
 */
static int select_parent(struct dentry * parent)
{
	struct dentry *this_parent = parent;
	struct list_head *next;
	int found = 0;

	spin_lock(&dcache_lock);
repeat:
	next = this_parent->d_subdirs.next;
resume:
	while (next != &this_parent->d_subdirs) {
		struct list_head *tmp = next;
		struct dentry *dentry = list_entry(tmp, struct dentry, d_child);
		next = tmp->next;

		if (!list_empty(&dentry->d_lru)) {
			dentry_stat.nr_unused--;
			list_del_init(&dentry->d_lru);
		}
		/* 
		 * move only zero ref count dentries to the end 
		 * of the unused list for prune_dcache
		 */
		if (!atomic_read(&dentry->d_count)) {
			list_add(&dentry->d_lru, dentry_unused.prev);
			dentry_stat.nr_unused++;
			found++;
		}
		/*
		 * Descend a level if the d_subdirs list is non-empty.
		 */
		if (!list_empty(&dentry->d_subdirs)) {
			this_parent = dentry;
#ifdef DCACHE_DEBUG
printk(KERN_DEBUG "select_parent: descending to %s/%s, found=%d\n",
dentry->d_parent->d_name.name, dentry->d_name.name, found);
#endif
			goto repeat;
		}
	}
	/*
	 * All done at this level ... ascend and resume the search.
	 */
	if (this_parent != parent) {
		next = this_parent->d_child.next; 
		this_parent = this_parent->d_parent;
#ifdef DCACHE_DEBUG
printk(KERN_DEBUG "select_parent: ascending to %s/%s, found=%d\n",
this_parent->d_parent->d_name.name, this_parent->d_name.name, found);
#endif
		goto resume;
	}
	spin_unlock(&dcache_lock);
	return found;
}

/**
 * shrink_dcache_parent - prune dcache
 * @parent: parent of entries to prune
 *
 * Prune the dcache to remove unused children of the parent dentry.
 */
 
void shrink_dcache_parent(struct dentry * parent)
{
	int found;

	while ((found = select_parent(parent)) != 0)
		prune_dcache(found);
}

/**
 * shrink_dcache_anon - further prune the cache
 * @head: head of d_hash list of dentries to prune
 *
 * Prune the dentries that are anonymous
 *
 * parsing d_hash list does not hlist_for_each_rcu() as it
 * done under dcache_lock.
 *
 */
void shrink_dcache_anon(struct hlist_head *head)
{
	struct hlist_node *lp;
	int found;
	do {
		found = 0;
		spin_lock(&dcache_lock);
		hlist_for_each(lp, head) {
			struct dentry *this = hlist_entry(lp, struct dentry, d_hash);
			if (!list_empty(&this->d_lru)) {
				dentry_stat.nr_unused--;
				list_del_init(&this->d_lru);
			}

			/* 
			 * move only zero ref count dentries to the end 
			 * of the unused list for prune_dcache
			 */
			if (!atomic_read(&this->d_count)) {
				list_add_tail(&this->d_lru, &dentry_unused);
				dentry_stat.nr_unused++;
				found++;
			}
		}
		spin_unlock(&dcache_lock);
		prune_dcache(found);
	} while(found);
}

/*
 * Scan `nr' dentries and return the number which remain.
 *
 * We need to avoid reentering the filesystem if the caller is performing a
 * GFP_NOFS allocation attempt.  One example deadlock is:
 *
 * ext2_new_block->getblk->GFP->shrink_dcache_memory->prune_dcache->
 * prune_one_dentry->dput->dentry_iput->iput->inode->i_sb->s_op->put_inode->
 * ext2_discard_prealloc->ext2_free_blocks->lock_super->DEADLOCK.
 *
 * In this case we return -1 to tell the caller that we baled.
 */
static int shrink_dcache_memory(int nr, unsigned int gfp_mask)
{
	if (nr) {
		if (!(gfp_mask & __GFP_FS))
			return -1;
		prune_dcache(nr);
	}
	return (dentry_stat.nr_unused / 100) * sysctl_vfs_cache_pressure;
}

/**
 * d_alloc	-	allocate a dcache entry
 * @parent: parent of entry to allocate
 * @name: qstr of the name
 *
 * Allocates a dentry. It returns %NULL if there is insufficient memory
 * available. On a success the dentry is returned. The name passed in is
 * copied and the copy passed in may be reused after this call.
 */
 
struct dentry *d_alloc(struct dentry * parent, const struct qstr *name)
{
	struct dentry *dentry;
	char *dname;

	dentry = kmem_cache_alloc(dentry_cache, GFP_KERNEL); 
	if (!dentry)
		return NULL;

	if (name->len > DNAME_INLINE_LEN-1) {
		dname = kmalloc(name->len + 1, GFP_KERNEL);
		if (!dname) {
			kmem_cache_free(dentry_cache, dentry); 
			return NULL;
		}
	} else  {
		dname = dentry->d_iname;
	}	
	dentry->d_name.name = dname;

	dentry->d_name.len = name->len;
	dentry->d_name.hash = name->hash;
	memcpy(dname, name->name, name->len);
	dname[name->len] = 0;

	atomic_set(&dentry->d_count, 1);
	dentry->d_flags = DCACHE_UNHASHED;
	dentry->d_lock = SPIN_LOCK_UNLOCKED;
	dentry->d_inode = NULL;
	dentry->d_parent = NULL;
	dentry->d_sb = NULL;
	dentry->d_op = NULL;
	dentry->d_fsdata = NULL;
	dentry->d_mounted = 0;
	dentry->d_cookie = NULL;
	INIT_HLIST_NODE(&dentry->d_hash);
	INIT_LIST_HEAD(&dentry->d_lru);
	INIT_LIST_HEAD(&dentry->d_subdirs);
	INIT_LIST_HEAD(&dentry->d_alias);

	if (parent) {
		dentry->d_parent = dget(parent);
		dentry->d_sb = parent->d_sb;
	} else {
		INIT_LIST_HEAD(&dentry->d_child);
	}

	spin_lock(&dcache_lock);
	if (parent)
		list_add(&dentry->d_child, &parent->d_subdirs);
	dentry_stat.nr_dentry++;
	spin_unlock(&dcache_lock);

	return dentry;
}

struct dentry *d_alloc_name(struct dentry *parent, const char *name)
{
	struct qstr q;

	q.name = name;
	q.len = strlen(name);
	q.hash = full_name_hash(q.name, q.len);
	return d_alloc(parent, &q);
}

/**
 * d_instantiate - fill in inode information for a dentry
 * @entry: dentry to complete
 * @inode: inode to attach to this dentry
 *
 * Fill in inode information in the entry.
 *
 * This turns negative dentries into productive full members
 * of society.
 *
 * NOTE! This assumes that the inode count has been incremented
 * (or otherwise set) by the caller to indicate that it is now
 * in use by the dcache.
 */
 
void d_instantiate(struct dentry *entry, struct inode * inode)
{
	if (!list_empty(&entry->d_alias)) BUG();
	spin_lock(&dcache_lock);
	if (inode)
		list_add(&entry->d_alias, &inode->i_dentry);
	entry->d_inode = inode;
	spin_unlock(&dcache_lock);
	security_d_instantiate(entry, inode);
}

/**
 * d_alloc_root - allocate root dentry
 * @root_inode: inode to allocate the root for
 *
 * Allocate a root ("/") dentry for the inode given. The inode is
 * instantiated and returned. %NULL is returned if there is insufficient
 * memory or the inode passed is %NULL.
 */
 
struct dentry * d_alloc_root(struct inode * root_inode)
{
	struct dentry *res = NULL;

	if (root_inode) {
		static const struct qstr name = { .name = "/", .len = 1 };

		res = d_alloc(NULL, &name);
		if (res) {
			res->d_sb = root_inode->i_sb;
			res->d_parent = res;
			d_instantiate(res, root_inode);
		}
	}
	return res;
}

static inline struct hlist_head *d_hash(struct dentry *parent,
					unsigned long hash)
{
	hash += ((unsigned long) parent ^ GOLDEN_RATIO_PRIME) / L1_CACHE_BYTES;
	hash = hash ^ ((hash ^ GOLDEN_RATIO_PRIME) >> D_HASHBITS);
	return dentry_hashtable + (hash & D_HASHMASK);
}

/**
 * d_alloc_anon - allocate an anonymous dentry
 * @inode: inode to allocate the dentry for
 *
 * This is similar to d_alloc_root.  It is used by filesystems when
 * creating a dentry for a given inode, often in the process of 
 * mapping a filehandle to a dentry.  The returned dentry may be
 * anonymous, or may have a full name (if the inode was already
 * in the cache).  The file system may need to make further
 * efforts to connect this dentry into the dcache properly.
 *
 * When called on a directory inode, we must ensure that
 * the inode only ever has one dentry.  If a dentry is
 * found, that is returned instead of allocating a new one.
 *
 * On successful return, the reference to the inode has been transferred
 * to the dentry.  If %NULL is returned (indicating kmalloc failure),
 * the reference on the inode has not been released.
 */

struct dentry * d_alloc_anon(struct inode *inode)
{
	static const struct qstr anonstring = { .name = "" };
	struct dentry *tmp;
	struct dentry *res;

	if ((res = d_find_alias(inode))) {
		iput(inode);
		return res;
	}

	tmp = d_alloc(NULL, &anonstring);
	if (!tmp)
		return NULL;

	tmp->d_parent = tmp; /* make sure dput doesn't croak */
	
	spin_lock(&dcache_lock);
	res = __d_find_alias(inode, 0);
	if (!res) {
		/* attach a disconnected dentry */
		res = tmp;
		tmp = NULL;
		spin_lock(&res->d_lock);
		res->d_sb = inode->i_sb;
		res->d_parent = res;
		res->d_inode = inode;
		res->d_flags |= DCACHE_DISCONNECTED;
		res->d_flags &= ~DCACHE_UNHASHED;
		list_add(&res->d_alias, &inode->i_dentry);
		hlist_add_head(&res->d_hash, &inode->i_sb->s_anon);
		spin_unlock(&res->d_lock);

		inode = NULL; /* don't drop reference */
	}
	spin_unlock(&dcache_lock);

	if (inode)
		iput(inode);
	if (tmp)
		dput(tmp);
	return res;
}


/**
 * d_splice_alias - splice a disconnected dentry into the tree if one exists
 * @inode:  the inode which may have a disconnected dentry
 * @dentry: a negative dentry which we want to point to the inode.
 *
 * If inode is a directory and has a 'disconnected' dentry (i.e. IS_ROOT and
 * DCACHE_DISCONNECTED), then d_move that in place of the given dentry
 * and return it, else simply d_add the inode to the dentry and return NULL.
 *
 * This is needed in the lookup routine of any filesystem that is exportable
 * (via knfsd) so that we can build dcache paths to directories effectively.
 *
 * If a dentry was found and moved, then it is returned.  Otherwise NULL
 * is returned.  This matches the expected return value of ->lookup.
 *
 */
struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry)
{
	struct dentry *new = NULL;

	if (inode) {
		spin_lock(&dcache_lock);
		new = __d_find_alias(inode, 1);
		if (new) {
			BUG_ON(!(new->d_flags & DCACHE_DISCONNECTED));
			spin_unlock(&dcache_lock);
			security_d_instantiate(new, inode);
			d_rehash(dentry);
			d_move(new, dentry);
			iput(inode);
		} else {
			/* d_instantiate takes dcache_lock, so we do it by hand */
			list_add(&dentry->d_alias, &inode->i_dentry);
			dentry->d_inode = inode;
			spin_unlock(&dcache_lock);
			security_d_instantiate(dentry, inode);
			d_rehash(dentry);
		}
	} else
		d_add(dentry, inode);
	return new;
}


/**
 * d_lookup - search for a dentry
 * @parent: parent dentry
 * @name: qstr of name we wish to find
 *
 * Searches the children of the parent dentry for the name in question. If
 * the dentry is found its reference count is incremented and the dentry
 * is returned. The caller must use d_put to free the entry when it has
 * finished using it. %NULL is returned on failure.
 *
 * __d_lookup is dcache_lock free. The hash list is protected using RCU.
 * Memory barriers are used while updating and doing lockless traversal. 
 * To avoid races with d_move while rename is happening, d_lock is used.
 *
 * Overflows in memcmp(), while d_move, are avoided by keeping the length
 * and name pointer in one structure pointed by d_qstr.
 *
 * rcu_read_lock() and rcu_read_unlock() are used to disable preemption while
 * lookup is going on.
 *
 * dentry_unused list is not updated even if lookup finds the required dentry
 * in there. It is updated in places such as prune_dcache, shrink_dcache_sb,
 * select_parent and __dget_locked. This laziness saves lookup from dcache_lock
 * acquisition.
 *
 * d_lookup() is protected against the concurrent renames in some unrelated
 * directory using the seqlockt_t rename_lock.
 */

struct dentry * d_lookup(struct dentry * parent, struct qstr * name)
{
	struct dentry * dentry = NULL;
	unsigned long seq;

        do {
                seq = read_seqbegin(&rename_lock);
                dentry = __d_lookup(parent, name);
                if (dentry)
			break;
	} while (read_seqretry(&rename_lock, seq));
	return dentry;
}

struct dentry * __d_lookup(struct dentry * parent, struct qstr * name)
{
	unsigned int len = name->len;
	unsigned int hash = name->hash;
	const unsigned char *str = name->name;
	struct hlist_head *head = d_hash(parent,hash);
	struct dentry *found = NULL;
	struct hlist_node *node;

	rcu_read_lock();
	
	hlist_for_each_rcu(node, head) {
		struct dentry *dentry; 
		struct qstr *qstr;

		dentry = hlist_entry(node, struct dentry, d_hash);

		if (dentry->d_name.hash != hash)
			continue;
		if (dentry->d_parent != parent)
			continue;

		spin_lock(&dentry->d_lock);

		/*
		 * Recheck the dentry after taking the lock - d_move may have
		 * changed things.  Don't bother checking the hash because we're
		 * about to compare the whole name anyway.
		 */
		if (dentry->d_parent != parent)
			goto next;

		/*
		 * It is safe to compare names since d_move() cannot
		 * change the qstr (protected by d_lock).
		 */
		qstr = &dentry->d_name;
		if (parent->d_op && parent->d_op->d_compare) {
			if (parent->d_op->d_compare(parent, qstr, name))
				goto next;
		} else {
			if (qstr->len != len)
				goto next;
			if (memcmp(qstr->name, str, len))
				goto next;
		}

		if (!d_unhashed(dentry)) {
			atomic_inc(&dentry->d_count);
			found = dentry;
		}
		spin_unlock(&dentry->d_lock);
		break;
next:
		spin_unlock(&dentry->d_lock);
 	}
 	rcu_read_unlock();

 	return found;
}

/**
 * d_validate - verify dentry provided from insecure source
 * @dentry: The dentry alleged to be valid child of @dparent
 * @dparent: The parent dentry (known to be valid)
 * @hash: Hash of the dentry
 * @len: Length of the name
 *
 * An insecure source has sent us a dentry, here we verify it and dget() it.
 * This is used by ncpfs in its readdir implementation.
 * Zero is returned in the dentry is invalid.
 */
 
int d_validate(struct dentry *dentry, struct dentry *dparent)
{
	struct hlist_head *base;
	struct hlist_node *lhp;

	/* Check whether the ptr might be valid at all.. */
	if (!kmem_ptr_validate(dentry_cache, dentry))
		goto out;

	if (dentry->d_parent != dparent)
		goto out;

	spin_lock(&dcache_lock);
	base = d_hash(dparent, dentry->d_name.hash);
	hlist_for_each(lhp,base) { 
		/* hlist_for_each_rcu() not required for d_hash list
		 * as it is parsed under dcache_lock
		 */
		if (dentry == hlist_entry(lhp, struct dentry, d_hash)) {
			__dget_locked(dentry);
			spin_unlock(&dcache_lock);
			return 1;
		}
	}
	spin_unlock(&dcache_lock);
out:
	return 0;
}

/*
 * When a file is deleted, we have two options:
 * - turn this dentry into a negative dentry
 * - unhash this dentry and free it.
 *
 * Usually, we want to just turn this into
 * a negative dentry, but if anybody else is
 * currently using the dentry or the inode
 * we can't do that and we fall back on removing
 * it from the hash queues and waiting for
 * it to be deleted later when it has no users
 */
 
/**
 * d_delete - delete a dentry
 * @dentry: The dentry to delete
 *
 * Turn the dentry into a negative dentry if possible, otherwise
 * remove it from the hash queues so it can be deleted later
 */
 
void d_delete(struct dentry * dentry)
{
	/*
	 * Are we the only user?
	 */
	spin_lock(&dcache_lock);
	spin_lock(&dentry->d_lock);
	if (atomic_read(&dentry->d_count) == 1) {
		dentry_iput(dentry);
		return;
	}

	if (!d_unhashed(dentry))
		__d_drop(dentry);

	spin_unlock(&dentry->d_lock);
	spin_unlock(&dcache_lock);
}

static void __d_rehash(struct dentry * entry, struct hlist_head *list)
{

 	entry->d_flags &= ~DCACHE_UNHASHED;
 	hlist_add_head_rcu(&entry->d_hash, list);
}

/**
 * d_rehash	- add an entry back to the hash
 * @entry: dentry to add to the hash
 *
 * Adds a dentry to the hash according to its name.
 */
 
void d_rehash(struct dentry * entry)
{
	struct hlist_head *list = d_hash(entry->d_parent, entry->d_name.hash);

	spin_lock(&dcache_lock);
	spin_lock(&entry->d_lock);
	__d_rehash(entry, list);
	spin_unlock(&entry->d_lock);
	spin_unlock(&dcache_lock);
}

#define do_switch(x,y) do { \
	__typeof__ (x) __tmp = x; \
	x = y; y = __tmp; } while (0)

/*
 * When switching names, the actual string doesn't strictly have to
 * be preserved in the target - because we're dropping the target
 * anyway. As such, we can just do a simple memcpy() to copy over
 * the new name before we switch.
 *
 * Note that we have to be a lot more careful about getting the hash
 * switched - we have to switch the hash value properly even if it
 * then no longer matches the actual (corrupted) string of the target.
 * The hash value has to match the hash queue that the dentry is on..
 */
static void switch_names(struct dentry *dentry, struct dentry *target)
{
	if (dname_external(target)) {
		if (dname_external(dentry)) {
			/*
			 * Both external: swap the pointers
			 */
			do_switch(target->d_name.name, dentry->d_name.name);
		} else {
			/*
			 * dentry:internal, target:external.  Steal target's
			 * storage and make target internal.
			 */
			dentry->d_name.name = target->d_name.name;
			target->d_name.name = target->d_iname;
		}
	} else {
		if (dname_external(dentry)) {
			/*
			 * dentry:external, target:internal.  Give dentry's
			 * storage to target and make dentry internal
			 */
			memcpy(dentry->d_iname, target->d_name.name,
					target->d_name.len + 1);
			target->d_name.name = dentry->d_name.name;
			dentry->d_name.name = dentry->d_iname;
		} else {
			/*
			 * Both are internal.  Just copy target to dentry
			 */
			memcpy(dentry->d_iname, target->d_name.name,
					target->d_name.len + 1);
		}
	}
}

/*
 * We cannibalize "target" when moving dentry on top of it,
 * because it's going to be thrown away anyway. We could be more
 * polite about it, though.
 *
 * This forceful removal will result in ugly /proc output if
 * somebody holds a file open that got deleted due to a rename.
 * We could be nicer about the deleted file, and let it show
 * up under the name it got deleted rather than the name that
 * deleted it.
 */
 
/**
 * d_move - move a dentry
 * @dentry: entry to move
 * @target: new dentry
 *
 * Update the dcache to reflect the move of a file name. Negative
 * dcache entries should not be moved in this way.
 */

void d_move(struct dentry * dentry, struct dentry * target)
{
	struct hlist_head *list;

	if (!dentry->d_inode)
		printk(KERN_WARNING "VFS: moving negative dcache entry\n");

	spin_lock(&dcache_lock);
	write_seqlock(&rename_lock);
	/*
	 * XXXX: do we really need to take target->d_lock?
	 */
	if (target < dentry) {
		spin_lock(&target->d_lock);
		spin_lock(&dentry->d_lock);
	} else {
		spin_lock(&dentry->d_lock);
		spin_lock(&target->d_lock);
	}

	/* Move the dentry to the target hash queue, if on different bucket */
	if (dentry->d_flags & DCACHE_UNHASHED)
		goto already_unhashed;

	hlist_del_rcu(&dentry->d_hash);

already_unhashed:
	list = d_hash(target->d_parent, target->d_name.hash);
	__d_rehash(dentry, list);

	/* Unhash the target: dput() will then get rid of it */
	__d_drop(target);

	list_del(&dentry->d_child);
	list_del(&target->d_child);

	/* Switch the names.. */
	switch_names(dentry, target);
	do_switch(dentry->d_name.len, target->d_name.len);
	do_switch(dentry->d_name.hash, target->d_name.hash);

	/* ... and switch the parents */
	if (IS_ROOT(dentry)) {
		dentry->d_parent = target->d_parent;
		target->d_parent = target;
		INIT_LIST_HEAD(&target->d_child);
	} else {
		do_switch(dentry->d_parent, target->d_parent);

		/* And add them back to the (new) parent lists */
		list_add(&target->d_child, &target->d_parent->d_subdirs);
	}

	list_add(&dentry->d_child, &dentry->d_parent->d_subdirs);
	spin_unlock(&target->d_lock);
	spin_unlock(&dentry->d_lock);
	write_sequnlock(&rename_lock);
	spin_unlock(&dcache_lock);
}

/**
 * d_path - return the path of a dentry
 * @dentry: dentry to report
 * @vfsmnt: vfsmnt to which the dentry belongs
 * @root: root dentry
 * @rootmnt: vfsmnt to which the root dentry belongs
 * @buffer: buffer to return value in
 * @buflen: buffer length
 *
 * Convert a dentry into an ASCII path name. If the entry has been deleted
 * the string " (deleted)" is appended. Note that this is ambiguous.
 *
 * Returns the buffer or an error code if the path was too long.
 *
 * "buflen" should be positive. Caller holds the dcache_lock.
 */
static char * __d_path( struct dentry *dentry, struct vfsmount *vfsmnt,
			struct dentry *root, struct vfsmount *rootmnt,
			char *buffer, int buflen)
{
	char * end = buffer+buflen;
	char * retval;
	int namelen;

	*--end = '\0';
	buflen--;
	if (!IS_ROOT(dentry) && d_unhashed(dentry)) {
		buflen -= 10;
		end -= 10;
		if (buflen < 0)
			goto Elong;
		memcpy(end, " (deleted)", 10);
	}

	if (buflen < 1)
		goto Elong;
	/* Get '/' right */
	retval = end-1;
	*retval = '/';

	for (;;) {
		struct dentry * parent;

		if (dentry == root && vfsmnt == rootmnt)
			break;
		if (dentry == vfsmnt->mnt_root || IS_ROOT(dentry)) {
			/* Global root? */
			spin_lock(&vfsmount_lock);
			if (vfsmnt->mnt_parent == vfsmnt) {
				spin_unlock(&vfsmount_lock);
				goto global_root;
			}
			dentry = vfsmnt->mnt_mountpoint;
			vfsmnt = vfsmnt->mnt_parent;
			spin_unlock(&vfsmount_lock);
			continue;
		}
		parent = dentry->d_parent;
		prefetch(parent);
		namelen = dentry->d_name.len;
		buflen -= namelen + 1;
		if (buflen < 0)
			goto Elong;
		end -= namelen;
		memcpy(end, dentry->d_name.name, namelen);
		*--end = '/';
		retval = end;
		dentry = parent;
	}

	return retval;

global_root:
	namelen = dentry->d_name.len;
	buflen -= namelen;
	if (buflen < 0)
		goto Elong;
	retval -= namelen-1;	/* hit the slash */
	memcpy(retval, dentry->d_name.name, namelen);
	return retval;
Elong:
	return ERR_PTR(-ENAMETOOLONG);
}

/* write full pathname into buffer and return start of pathname */
char * d_path(struct dentry *dentry, struct vfsmount *vfsmnt,
				char *buf, int buflen)
{
	char *res;
	struct vfsmount *rootmnt;
	struct dentry *root;

	read_lock(&current->fs->lock);
	rootmnt = mntget(current->fs->rootmnt);
	root = dget(current->fs->root);
	read_unlock(&current->fs->lock);
	spin_lock(&dcache_lock);
	res = __d_path(dentry, vfsmnt, root, rootmnt, buf, buflen);
	spin_unlock(&dcache_lock);
	dput(root);
	mntput(rootmnt);
	return res;
}

/*
 * NOTE! The user-level library version returns a
 * character pointer. The kernel system call just
 * returns the length of the buffer filled (which
 * includes the ending '\0' character), or a negative
 * error value. So libc would do something like
 *
 *	char *getcwd(char * buf, size_t size)
 *	{
 *		int retval;
 *
 *		retval = sys_getcwd(buf, size);
 *		if (retval >= 0)
 *			return buf;
 *		errno = -retval;
 *		return NULL;
 *	}
 */
asmlinkage long sys_getcwd(char __user *buf, unsigned long size)
{
	int error;
	struct vfsmount *pwdmnt, *rootmnt;
	struct dentry *pwd, *root;
	char *page = (char *) __get_free_page(GFP_USER);

	if (!page)
		return -ENOMEM;

	read_lock(&current->fs->lock);
	pwdmnt = mntget(current->fs->pwdmnt);
	pwd = dget(current->fs->pwd);
	rootmnt = mntget(current->fs->rootmnt);
	root = dget(current->fs->root);
	read_unlock(&current->fs->lock);

	error = -ENOENT;
	/* Has the current directory has been unlinked? */
	spin_lock(&dcache_lock);
	if (pwd->d_parent == pwd || !d_unhashed(pwd)) {
		unsigned long len;
		char * cwd;

		cwd = __d_path(pwd, pwdmnt, root, rootmnt, page, PAGE_SIZE);
		spin_unlock(&dcache_lock);

		error = PTR_ERR(cwd);
		if (IS_ERR(cwd))
			goto out;

		error = -ERANGE;
		len = PAGE_SIZE + page - cwd;
		if (len <= size) {
			error = len;
			if (copy_to_user(buf, cwd, len))
				error = -EFAULT;
		}
	} else
		spin_unlock(&dcache_lock);

out:
	dput(pwd);
	mntput(pwdmnt);
	dput(root);
	mntput(rootmnt);
	free_page((unsigned long) page);
	return error;
}

/*
 * Test whether new_dentry is a subdirectory of old_dentry.
 *
 * Trivially implemented using the dcache structure
 */

/**
 * is_subdir - is new dentry a subdirectory of old_dentry
 * @new_dentry: new dentry
 * @old_dentry: old dentry
 *
 * Returns 1 if new_dentry is a subdirectory of the parent (at any depth).
 * Returns 0 otherwise.
 * Caller must ensure that "new_dentry" is pinned before calling is_subdir()
 */
  
int is_subdir(struct dentry * new_dentry, struct dentry * old_dentry)
{
	int result;
	struct dentry * saved = new_dentry;
	unsigned long seq;

	result = 0;
	/* need rcu_readlock to protect against the d_parent trashing due to
	 * d_move
	 */
	rcu_read_lock();
        do {
		/* for restarting inner loop in case of seq retry */
		new_dentry = saved;
		seq = read_seqbegin(&rename_lock);
		for (;;) {
			if (new_dentry != old_dentry) {
				struct dentry * parent = new_dentry->d_parent;
				if (parent == new_dentry)
					break;
				new_dentry = parent;
				continue;
			}
			result = 1;
			break;
		}
	} while (read_seqretry(&rename_lock, seq));
	rcu_read_unlock();

	return result;
}

void d_genocide(struct dentry *root)
{
	struct dentry *this_parent = root;
	struct list_head *next;

	spin_lock(&dcache_lock);
repeat:
	next = this_parent->d_subdirs.next;
resume:
	while (next != &this_parent->d_subdirs) {
		struct list_head *tmp = next;
		struct dentry *dentry = list_entry(tmp, struct dentry, d_child);
		next = tmp->next;
		if (d_unhashed(dentry)||!dentry->d_inode)
			continue;
		if (!list_empty(&dentry->d_subdirs)) {
			this_parent = dentry;
			goto repeat;
		}
		atomic_dec(&dentry->d_count);
	}
	if (this_parent != root) {
		next = this_parent->d_child.next; 
		atomic_dec(&this_parent->d_count);
		this_parent = this_parent->d_parent;
		goto resume;
	}
	spin_unlock(&dcache_lock);
}

/**
 * find_inode_number - check for dentry with name
 * @dir: directory to check
 * @name: Name to find.
 *
 * Check whether a dentry already exists for the given name,
 * and return the inode number if it has an inode. Otherwise
 * 0 is returned.
 *
 * This routine is used to post-process directory listings for
 * filesystems using synthetic inode numbers, and is necessary
 * to keep getcwd() working.
 */
 
ino_t find_inode_number(struct dentry *dir, struct qstr *name)
{
	struct dentry * dentry;
	ino_t ino = 0;

	/*
	 * Check for a fs-specific hash function. Note that we must
	 * calculate the standard hash first, as the d_op->d_hash()
	 * routine may choose to leave the hash value unchanged.
	 */
	name->hash = full_name_hash(name->name, name->len);
	if (dir->d_op && dir->d_op->d_hash)
	{
		if (dir->d_op->d_hash(dir, name) != 0)
			goto out;
	}

	dentry = d_lookup(dir, name);
	if (dentry)
	{
		if (dentry->d_inode)
			ino = dentry->d_inode->i_ino;
		dput(dentry);
	}
out:
	return ino;
}

static __initdata unsigned long dhash_entries;
static int __init set_dhash_entries(char *str)
{
	if (!str)
		return 0;
	dhash_entries = simple_strtoul(str, &str, 0);
	return 1;
}
__setup("dhash_entries=", set_dhash_entries);

static void __init dcache_init_early(void)
{
	int loop;

	dentry_hashtable =
		alloc_large_system_hash("Dentry cache",
					sizeof(struct hlist_head),
					dhash_entries,
					13,
					HASH_EARLY,
					&d_hash_shift,
					&d_hash_mask,
					0);

	for (loop = 0; loop < (1 << d_hash_shift); loop++)
		INIT_HLIST_HEAD(&dentry_hashtable[loop]);
}

static void __init dcache_init(unsigned long mempages)
{
	/* 
	 * A constructor could be added for stable state like the lists,
	 * but it is probably not worth it because of the cache nature
	 * of the dcache. 
	 */
	dentry_cache = kmem_cache_create("dentry_cache",
					 sizeof(struct dentry),
					 0,
					 SLAB_RECLAIM_ACCOUNT|SLAB_PANIC,
					 NULL, NULL);
	
	set_shrinker(DEFAULT_SEEKS, shrink_dcache_memory);
}

/* SLAB cache for __getname() consumers */
kmem_cache_t *names_cachep;

/* SLAB cache for file structures */
kmem_cache_t *filp_cachep;

EXPORT_SYMBOL(d_genocide);

extern void bdev_cache_init(void);
extern void chrdev_init(void);

void __init vfs_caches_init_early(void)
{
	dcache_init_early();
	inode_init_early();
}

void __init vfs_caches_init(unsigned long mempages)
{
	unsigned long reserve;

	/* Base hash sizes on available memory, with a reserve equal to
           150% of current kernel size */

	reserve = min((mempages - nr_free_pages()) * 3/2, mempages - 1);
	mempages -= reserve;

	names_cachep = kmem_cache_create("names_cache", PATH_MAX, 0,
			SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL);

	filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0,
			SLAB_HWCACHE_ALIGN|SLAB_PANIC, filp_ctor, filp_dtor);

	dcache_init(mempages);
	inode_init(mempages);
	files_init(mempages);
	mnt_init(mempages);
	bdev_cache_init();
	chrdev_init();
}

EXPORT_SYMBOL(d_alloc);
EXPORT_SYMBOL(d_alloc_anon);
EXPORT_SYMBOL(d_alloc_root);
EXPORT_SYMBOL(d_delete);
EXPORT_SYMBOL(d_find_alias);
EXPORT_SYMBOL(d_instantiate);
EXPORT_SYMBOL(d_invalidate);
EXPORT_SYMBOL(d_lookup);
EXPORT_SYMBOL(d_move);
EXPORT_SYMBOL(d_path);
EXPORT_SYMBOL(d_prune_aliases);
EXPORT_SYMBOL(d_rehash);
EXPORT_SYMBOL(d_splice_alias);
EXPORT_SYMBOL(d_validate);
EXPORT_SYMBOL(dget_locked);
EXPORT_SYMBOL(dput);
EXPORT_SYMBOL(find_inode_number);
EXPORT_SYMBOL(have_submounts);
EXPORT_SYMBOL(names_cachep);
EXPORT_SYMBOL(shrink_dcache_parent);
EXPORT_SYMBOL(shrink_dcache_sb);