Loading...
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 | // SPDX-License-Identifier: GPL-2.0
/*
* GPL HEADER START
*
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 only,
* 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 version 2 for more details (a copy is included
* in the LICENSE file that accompanied this code).
*
* You should have received a copy of the GNU General Public License
* version 2 along with this program; If not, see
* http://www.gnu.org/licenses/gpl-2.0.html
*
* GPL HEADER END
*/
/*
* Copyright (c) 2002, 2010, Oracle and/or its affiliates. All rights reserved.
* Use is subject to license terms.
*
* Copyright (c) 2011, 2015, Intel Corporation.
*/
/*
* This file is part of Lustre, http://www.lustre.org/
* Lustre is a trademark of Sun Microsystems, Inc.
*/
#include <linux/fs.h>
#include <linux/sched.h>
#include <linux/mm.h>
#include <linux/quotaops.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/security.h>
#define DEBUG_SUBSYSTEM S_LLITE
#include <obd_support.h>
#include <lustre_fid.h>
#include <lustre_dlm.h>
#include "llite_internal.h"
static int ll_create_it(struct inode *dir, struct dentry *dentry,
struct lookup_intent *it);
/* called from iget5_locked->find_inode() under inode_hash_lock spinlock */
static int ll_test_inode(struct inode *inode, void *opaque)
{
struct ll_inode_info *lli = ll_i2info(inode);
struct lustre_md *md = opaque;
if (unlikely(!(md->body->mbo_valid & OBD_MD_FLID))) {
CERROR("MDS body missing FID\n");
return 0;
}
if (!lu_fid_eq(&lli->lli_fid, &md->body->mbo_fid1))
return 0;
return 1;
}
static int ll_set_inode(struct inode *inode, void *opaque)
{
struct ll_inode_info *lli = ll_i2info(inode);
struct mdt_body *body = ((struct lustre_md *)opaque)->body;
if (unlikely(!(body->mbo_valid & OBD_MD_FLID))) {
CERROR("MDS body missing FID\n");
return -EINVAL;
}
lli->lli_fid = body->mbo_fid1;
if (unlikely(!(body->mbo_valid & OBD_MD_FLTYPE))) {
CERROR("Can not initialize inode " DFID
" without object type: valid = %#llx\n",
PFID(&lli->lli_fid), body->mbo_valid);
return -EINVAL;
}
inode->i_mode = (inode->i_mode & ~S_IFMT) | (body->mbo_mode & S_IFMT);
if (unlikely(inode->i_mode == 0)) {
CERROR("Invalid inode " DFID " type\n", PFID(&lli->lli_fid));
return -EINVAL;
}
ll_lli_init(lli);
return 0;
}
/**
* Get an inode by inode number(@hash), which is already instantiated by
* the intent lookup).
*/
struct inode *ll_iget(struct super_block *sb, ino_t hash,
struct lustre_md *md)
{
struct inode *inode;
int rc = 0;
LASSERT(hash != 0);
inode = iget5_locked(sb, hash, ll_test_inode, ll_set_inode, md);
if (!inode)
return ERR_PTR(-ENOMEM);
if (inode->i_state & I_NEW) {
rc = ll_read_inode2(inode, md);
if (!rc && S_ISREG(inode->i_mode) &&
!ll_i2info(inode)->lli_clob)
rc = cl_file_inode_init(inode, md);
if (rc) {
/*
* Let's clear directory lsm here, otherwise
* make_bad_inode() will reset the inode mode
* to regular, then ll_clear_inode will not
* be able to clear lsm_md
*/
if (S_ISDIR(inode->i_mode))
ll_dir_clear_lsm_md(inode);
make_bad_inode(inode);
unlock_new_inode(inode);
iput(inode);
inode = ERR_PTR(rc);
} else {
unlock_new_inode(inode);
}
} else if (!(inode->i_state & (I_FREEING | I_CLEAR))) {
rc = ll_update_inode(inode, md);
CDEBUG(D_VFSTRACE, "got inode: " DFID "(%p): rc = %d\n",
PFID(&md->body->mbo_fid1), inode, rc);
if (rc) {
if (S_ISDIR(inode->i_mode))
ll_dir_clear_lsm_md(inode);
iput(inode);
inode = ERR_PTR(rc);
}
}
return inode;
}
static void ll_invalidate_negative_children(struct inode *dir)
{
struct dentry *dentry, *tmp_subdir;
spin_lock(&dir->i_lock);
hlist_for_each_entry(dentry, &dir->i_dentry, d_u.d_alias) {
spin_lock(&dentry->d_lock);
if (!list_empty(&dentry->d_subdirs)) {
struct dentry *child;
list_for_each_entry_safe(child, tmp_subdir,
&dentry->d_subdirs,
d_child) {
if (d_really_is_negative(child))
d_lustre_invalidate(child, 1);
}
}
spin_unlock(&dentry->d_lock);
}
spin_unlock(&dir->i_lock);
}
int ll_test_inode_by_fid(struct inode *inode, void *opaque)
{
return lu_fid_eq(&ll_i2info(inode)->lli_fid, opaque);
}
int ll_md_blocking_ast(struct ldlm_lock *lock, struct ldlm_lock_desc *desc,
void *data, int flag)
{
struct lustre_handle lockh;
int rc;
switch (flag) {
case LDLM_CB_BLOCKING:
ldlm_lock2handle(lock, &lockh);
rc = ldlm_cli_cancel(&lockh, LCF_ASYNC);
if (rc < 0) {
CDEBUG(D_INODE, "ldlm_cli_cancel: rc = %d\n", rc);
return rc;
}
break;
case LDLM_CB_CANCELING: {
struct inode *inode = ll_inode_from_resource_lock(lock);
__u64 bits = lock->l_policy_data.l_inodebits.bits;
/* Inode is set to lock->l_resource->lr_lvb_inode
* for mdc - bug 24555
*/
LASSERT(!lock->l_ast_data);
if (!inode)
break;
/* Invalidate all dentries associated with this inode */
LASSERT(ldlm_is_canceling(lock));
if (!fid_res_name_eq(ll_inode2fid(inode),
&lock->l_resource->lr_name)) {
LDLM_ERROR(lock,
"data mismatch with object " DFID "(%p)",
PFID(ll_inode2fid(inode)), inode);
LBUG();
}
if (bits & MDS_INODELOCK_XATTR) {
if (S_ISDIR(inode->i_mode))
ll_i2info(inode)->lli_def_stripe_offset = -1;
ll_xattr_cache_destroy(inode);
bits &= ~MDS_INODELOCK_XATTR;
}
/* For OPEN locks we differentiate between lock modes
* LCK_CR, LCK_CW, LCK_PR - bug 22891
*/
if (bits & MDS_INODELOCK_OPEN)
ll_have_md_lock(inode, &bits, lock->l_req_mode);
if (bits & MDS_INODELOCK_OPEN) {
fmode_t fmode;
switch (lock->l_req_mode) {
case LCK_CW:
fmode = FMODE_WRITE;
break;
case LCK_PR:
fmode = FMODE_EXEC;
break;
case LCK_CR:
fmode = FMODE_READ;
break;
default:
LDLM_ERROR(lock, "bad lock mode for OPEN lock");
LBUG();
}
ll_md_real_close(inode, fmode);
}
if (bits & (MDS_INODELOCK_LOOKUP | MDS_INODELOCK_UPDATE |
MDS_INODELOCK_LAYOUT | MDS_INODELOCK_PERM))
ll_have_md_lock(inode, &bits, LCK_MINMODE);
if (bits & MDS_INODELOCK_LAYOUT) {
struct cl_object_conf conf = {
.coc_opc = OBJECT_CONF_INVALIDATE,
.coc_inode = inode,
};
rc = ll_layout_conf(inode, &conf);
if (rc < 0)
CDEBUG(D_INODE, "cannot invalidate layout of "
DFID ": rc = %d\n",
PFID(ll_inode2fid(inode)), rc);
}
if (bits & MDS_INODELOCK_UPDATE) {
struct ll_inode_info *lli = ll_i2info(inode);
spin_lock(&lli->lli_lock);
LTIME_S(inode->i_mtime) = 0;
LTIME_S(inode->i_atime) = 0;
LTIME_S(inode->i_ctime) = 0;
spin_unlock(&lli->lli_lock);
}
if ((bits & MDS_INODELOCK_UPDATE) && S_ISDIR(inode->i_mode)) {
struct ll_inode_info *lli = ll_i2info(inode);
CDEBUG(D_INODE, "invalidating inode " DFID " lli = %p, pfid = " DFID "\n",
PFID(ll_inode2fid(inode)), lli,
PFID(&lli->lli_pfid));
truncate_inode_pages(inode->i_mapping, 0);
if (unlikely(!fid_is_zero(&lli->lli_pfid))) {
struct inode *master_inode = NULL;
unsigned long hash;
/*
* This is slave inode, since all of the child
* dentry is connected on the master inode, so
* we have to invalidate the negative children
* on master inode
*/
CDEBUG(D_INODE,
"Invalidate s" DFID " m" DFID "\n",
PFID(ll_inode2fid(inode)),
PFID(&lli->lli_pfid));
hash = cl_fid_build_ino(&lli->lli_pfid,
ll_need_32bit_api(ll_i2sbi(inode)));
/*
* Do not lookup the inode with ilookup5,
* otherwise it will cause dead lock,
*
* 1. Client1 send chmod req to the MDT0, then
* on MDT0, it enqueues master and all of its
* slaves lock, (mdt_attr_set() ->
* mdt_lock_slaves()), after gets master and
* stripe0 lock, it will send the enqueue req
* (for stripe1) to MDT1, then MDT1 finds the
* lock has been granted to client2. Then MDT1
* sends blocking ast to client2.
*
* 2. At the same time, client2 tries to unlink
* the striped dir (rm -rf striped_dir), and
* during lookup, it will hold the master inode
* of the striped directory, whose inode state
* is NEW, then tries to revalidate all of its
* slaves, (ll_prep_inode()->ll_iget()->
* ll_read_inode2()-> ll_update_inode().). And
* it will be blocked on the server side because
* of 1.
*
* 3. Then the client get the blocking_ast req,
* cancel the lock, but being blocked if using
* ->ilookup5()), because master inode state is
* NEW.
*/
master_inode = ilookup5_nowait(inode->i_sb,
hash,
ll_test_inode_by_fid,
(void *)&lli->lli_pfid);
if (master_inode) {
ll_invalidate_negative_children(master_inode);
iput(master_inode);
}
} else {
ll_invalidate_negative_children(inode);
}
}
if ((bits & (MDS_INODELOCK_LOOKUP | MDS_INODELOCK_PERM)) &&
inode->i_sb->s_root &&
!is_root_inode(inode))
ll_invalidate_aliases(inode);
iput(inode);
break;
}
default:
LBUG();
}
return 0;
}
__u32 ll_i2suppgid(struct inode *i)
{
if (in_group_p(i->i_gid))
return (__u32)from_kgid(&init_user_ns, i->i_gid);
else
return (__u32)(-1);
}
/* Pack the required supplementary groups into the supplied groups array.
* If we don't need to use the groups from the target inode(s) then we
* instead pack one or more groups from the user's supplementary group
* array in case it might be useful. Not needed if doing an MDS-side upcall.
*/
void ll_i2gids(__u32 *suppgids, struct inode *i1, struct inode *i2)
{
LASSERT(i1);
suppgids[0] = ll_i2suppgid(i1);
if (i2)
suppgids[1] = ll_i2suppgid(i2);
else
suppgids[1] = -1;
}
/*
* try to reuse three types of dentry:
* 1. unhashed alias, this one is unhashed by d_invalidate (but it may be valid
* by concurrent .revalidate).
* 2. INVALID alias (common case for no valid ldlm lock held, but this flag may
* be cleared by others calling d_lustre_revalidate).
* 3. DISCONNECTED alias.
*/
static struct dentry *ll_find_alias(struct inode *inode, struct dentry *dentry)
{
struct dentry *alias, *discon_alias, *invalid_alias;
if (hlist_empty(&inode->i_dentry))
return NULL;
discon_alias = NULL;
invalid_alias = NULL;
spin_lock(&inode->i_lock);
hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
LASSERT(alias != dentry);
spin_lock(&alias->d_lock);
if ((alias->d_flags & DCACHE_DISCONNECTED) &&
S_ISDIR(inode->i_mode))
/* LASSERT(last_discon == NULL); LU-405, bz 20055 */
discon_alias = alias;
else if (alias->d_parent == dentry->d_parent &&
alias->d_name.hash == dentry->d_name.hash &&
alias->d_name.len == dentry->d_name.len &&
memcmp(alias->d_name.name, dentry->d_name.name,
dentry->d_name.len) == 0)
invalid_alias = alias;
spin_unlock(&alias->d_lock);
if (invalid_alias)
break;
}
alias = invalid_alias ?: discon_alias ?: NULL;
if (alias) {
spin_lock(&alias->d_lock);
dget_dlock(alias);
spin_unlock(&alias->d_lock);
}
spin_unlock(&inode->i_lock);
return alias;
}
/*
* Similar to d_splice_alias(), but lustre treats invalid alias
* similar to DCACHE_DISCONNECTED, and tries to use it anyway.
*/
struct dentry *ll_splice_alias(struct inode *inode, struct dentry *de)
{
if (inode) {
struct dentry *new = ll_find_alias(inode, de);
if (new) {
d_move(new, de);
iput(inode);
CDEBUG(D_DENTRY,
"Reuse dentry %p inode %p refc %d flags %#x\n",
new, d_inode(new), d_count(new), new->d_flags);
return new;
}
}
d_add(de, inode);
CDEBUG(D_DENTRY, "Add dentry %p inode %p refc %d flags %#x\n",
de, d_inode(de), d_count(de), de->d_flags);
return de;
}
static int ll_lookup_it_finish(struct ptlrpc_request *request,
struct lookup_intent *it,
struct inode *parent, struct dentry **de)
{
struct inode *inode = NULL;
__u64 bits = 0;
int rc = 0;
struct dentry *alias;
/* NB 1 request reference will be taken away by ll_intent_lock()
* when I return
*/
CDEBUG(D_DENTRY, "it %p it_disposition %x\n", it,
it->it_disposition);
if (!it_disposition(it, DISP_LOOKUP_NEG)) {
rc = ll_prep_inode(&inode, request, (*de)->d_sb, it);
if (rc)
return rc;
ll_set_lock_data(ll_i2sbi(parent)->ll_md_exp, inode, it, &bits);
/* We used to query real size from OSTs here, but actually
* this is not needed. For stat() calls size would be updated
* from subsequent do_revalidate()->ll_inode_revalidate_it() in
* 2.4 and
* vfs_getattr_it->ll_getattr()->ll_inode_revalidate_it() in 2.6
* Everybody else who needs correct file size would call
* ll_glimpse_size or some equivalent themselves anyway.
* Also see bug 7198.
*/
}
alias = ll_splice_alias(inode, *de);
if (IS_ERR(alias)) {
rc = PTR_ERR(alias);
goto out;
}
*de = alias;
if (!it_disposition(it, DISP_LOOKUP_NEG)) {
/* We have the "lookup" lock, so unhide dentry */
if (bits & MDS_INODELOCK_LOOKUP)
d_lustre_revalidate(*de);
} else if (!it_disposition(it, DISP_OPEN_CREATE)) {
/* If file created on server, don't depend on parent UPDATE
* lock to unhide it. It is left hidden and next lookup can
* find it in ll_splice_alias.
*/
/* Check that parent has UPDATE lock. */
struct lookup_intent parent_it = {
.it_op = IT_GETATTR,
.it_lock_handle = 0 };
struct lu_fid fid = ll_i2info(parent)->lli_fid;
/* If it is striped directory, get the real stripe parent */
if (unlikely(ll_i2info(parent)->lli_lsm_md)) {
rc = md_get_fid_from_lsm(ll_i2mdexp(parent),
ll_i2info(parent)->lli_lsm_md,
(*de)->d_name.name,
(*de)->d_name.len, &fid);
if (rc)
return rc;
}
if (md_revalidate_lock(ll_i2mdexp(parent), &parent_it, &fid,
NULL)) {
d_lustre_revalidate(*de);
ll_intent_release(&parent_it);
}
}
out:
if (rc != 0 && it->it_op & IT_OPEN)
ll_open_cleanup((*de)->d_sb, request);
return rc;
}
static struct dentry *ll_lookup_it(struct inode *parent, struct dentry *dentry,
struct lookup_intent *it)
{
struct lookup_intent lookup_it = { .it_op = IT_LOOKUP };
struct dentry *save = dentry, *retval;
struct ptlrpc_request *req = NULL;
struct md_op_data *op_data = NULL;
struct inode *inode;
__u32 opc;
int rc;
if (dentry->d_name.len > ll_i2sbi(parent)->ll_namelen)
return ERR_PTR(-ENAMETOOLONG);
CDEBUG(D_VFSTRACE, "VFS Op:name=%pd, dir=" DFID "(%p),intent=%s\n",
dentry, PFID(ll_inode2fid(parent)), parent, LL_IT2STR(it));
if (d_mountpoint(dentry))
CERROR("Tell Peter, lookup on mtpt, it %s\n", LL_IT2STR(it));
if (!it || it->it_op == IT_GETXATTR)
it = &lookup_it;
if (it->it_op == IT_GETATTR && dentry_may_statahead(parent, dentry)) {
rc = ll_statahead(parent, &dentry, 0);
if (rc == 1) {
if (dentry == save)
retval = NULL;
else
retval = dentry;
goto out;
}
}
if (it->it_op & IT_OPEN && it->it_flags & FMODE_WRITE && sb_rdonly(dentry->d_sb))
return ERR_PTR(-EROFS);
if (it->it_op & IT_CREAT)
opc = LUSTRE_OPC_CREATE;
else
opc = LUSTRE_OPC_ANY;
op_data = ll_prep_md_op_data(NULL, parent, NULL, dentry->d_name.name,
dentry->d_name.len, 0, opc, NULL);
if (IS_ERR(op_data))
return (void *)op_data;
/* enforce umask if acl disabled or MDS doesn't support umask */
if (!IS_POSIXACL(parent) || !exp_connect_umask(ll_i2mdexp(parent)))
it->it_create_mode &= ~current_umask();
rc = md_intent_lock(ll_i2mdexp(parent), op_data, it, &req,
&ll_md_blocking_ast, 0);
/*
* If the MDS allows the client to chgrp (CFS_SETGRP_PERM), but the
* client does not know which suppgid should be sent to the MDS, or
* some other(s) changed the target file's GID after this RPC sent
* to the MDS with the suppgid as the original GID, then we should
* try again with right suppgid.
*/
if (rc == -EACCES && it->it_op & IT_OPEN &&
it_disposition(it, DISP_OPEN_DENY)) {
struct mdt_body *body;
LASSERT(req);
body = req_capsule_server_get(&req->rq_pill, &RMF_MDT_BODY);
if (op_data->op_suppgids[0] == body->mbo_gid ||
op_data->op_suppgids[1] == body->mbo_gid ||
!in_group_p(make_kgid(&init_user_ns, body->mbo_gid))) {
retval = ERR_PTR(-EACCES);
goto out;
}
fid_zero(&op_data->op_fid2);
op_data->op_suppgids[1] = body->mbo_gid;
ptlrpc_req_finished(req);
req = NULL;
ll_intent_release(it);
rc = md_intent_lock(ll_i2mdexp(parent), op_data, it, &req,
ll_md_blocking_ast, 0);
}
if (rc < 0) {
retval = ERR_PTR(rc);
goto out;
}
rc = ll_lookup_it_finish(req, it, parent, &dentry);
if (rc != 0) {
ll_intent_release(it);
retval = ERR_PTR(rc);
goto out;
}
inode = d_inode(dentry);
if ((it->it_op & IT_OPEN) && inode &&
!S_ISREG(inode->i_mode) &&
!S_ISDIR(inode->i_mode)) {
ll_release_openhandle(inode, it);
}
ll_lookup_finish_locks(it, inode);
if (dentry == save)
retval = NULL;
else
retval = dentry;
out:
if (op_data && !IS_ERR(op_data))
ll_finish_md_op_data(op_data);
ptlrpc_req_finished(req);
return retval;
}
static struct dentry *ll_lookup_nd(struct inode *parent, struct dentry *dentry,
unsigned int flags)
{
struct lookup_intent *itp, it = { .it_op = IT_GETATTR };
struct dentry *de;
CDEBUG(D_VFSTRACE, "VFS Op:name=%pd, dir=" DFID "(%p),flags=%u\n",
dentry, PFID(ll_inode2fid(parent)), parent, flags);
/* Optimize away (CREATE && !OPEN). Let .create handle the race.
* but only if we have write permissions there, otherwise we need
* to proceed with lookup. LU-4185
*/
if ((flags & LOOKUP_CREATE) && !(flags & LOOKUP_OPEN) &&
(inode_permission(parent, MAY_WRITE | MAY_EXEC) == 0))
return NULL;
if (flags & (LOOKUP_PARENT | LOOKUP_OPEN | LOOKUP_CREATE))
itp = NULL;
else
itp = ⁢
de = ll_lookup_it(parent, dentry, itp);
if (itp)
ll_intent_release(itp);
return de;
}
/*
* For cached negative dentry and new dentry, handle lookup/create/open
* together.
*/
static int ll_atomic_open(struct inode *dir, struct dentry *dentry,
struct file *file, unsigned int open_flags,
umode_t mode, int *opened)
{
struct lookup_intent *it;
struct dentry *de;
int rc = 0;
CDEBUG(D_VFSTRACE, "VFS Op:name=%pd, dir=" DFID "(%p),file %p,open_flags %x,mode %x opened %d\n",
dentry, PFID(ll_inode2fid(dir)), dir, file, open_flags, mode,
*opened);
/* Only negative dentries enter here */
LASSERT(!d_inode(dentry));
if (!d_in_lookup(dentry)) {
/* A valid negative dentry that just passed revalidation,
* there's little point to try and open it server-side,
* even though there's a minuscle chance it might succeed.
* Either way it's a valid race to just return -ENOENT here.
*/
if (!(open_flags & O_CREAT))
return -ENOENT;
/* Otherwise we just unhash it to be rehashed afresh via
* lookup if necessary
*/
d_drop(dentry);
}
it = kzalloc(sizeof(*it), GFP_NOFS);
if (!it)
return -ENOMEM;
it->it_op = IT_OPEN;
if (open_flags & O_CREAT)
it->it_op |= IT_CREAT;
it->it_create_mode = (mode & S_IALLUGO) | S_IFREG;
it->it_flags = (open_flags & ~O_ACCMODE) | OPEN_FMODE(open_flags);
it->it_flags &= ~MDS_OPEN_FL_INTERNAL;
/* Dentry added to dcache tree in ll_lookup_it */
de = ll_lookup_it(dir, dentry, it);
if (IS_ERR(de))
rc = PTR_ERR(de);
else if (de)
dentry = de;
if (!rc) {
if (it_disposition(it, DISP_OPEN_CREATE)) {
/* Dentry instantiated in ll_create_it. */
rc = ll_create_it(dir, dentry, it);
if (rc) {
/* We dget in ll_splice_alias. */
if (de)
dput(de);
goto out_release;
}
*opened |= FILE_CREATED;
}
if (d_really_is_positive(dentry) &&
it_disposition(it, DISP_OPEN_OPEN)) {
/* Open dentry. */
if (S_ISFIFO(d_inode(dentry)->i_mode)) {
/* We cannot call open here as it might
* deadlock. This case is unreachable in
* practice because of OBD_CONNECT_NODEVOH.
*/
rc = finish_no_open(file, de);
} else {
file->private_data = it;
rc = finish_open(file, dentry, NULL, opened);
/* We dget in ll_splice_alias. finish_open takes
* care of dget for fd open.
*/
if (de)
dput(de);
}
} else {
rc = finish_no_open(file, de);
}
}
out_release:
ll_intent_release(it);
kfree(it);
return rc;
}
/* We depend on "mode" being set with the proper file type/umask by now */
static struct inode *ll_create_node(struct inode *dir, struct lookup_intent *it)
{
struct inode *inode = NULL;
struct ptlrpc_request *request = NULL;
struct ll_sb_info *sbi = ll_i2sbi(dir);
int rc;
LASSERT(it && it->it_disposition);
LASSERT(it_disposition(it, DISP_ENQ_CREATE_REF));
request = it->it_request;
it_clear_disposition(it, DISP_ENQ_CREATE_REF);
rc = ll_prep_inode(&inode, request, dir->i_sb, it);
if (rc) {
inode = ERR_PTR(rc);
goto out;
}
LASSERT(hlist_empty(&inode->i_dentry));
/* We asked for a lock on the directory, but were granted a
* lock on the inode. Since we finally have an inode pointer,
* stuff it in the lock.
*/
CDEBUG(D_DLMTRACE, "setting l_ast_data to inode " DFID "(%p)\n",
PFID(ll_inode2fid(dir)), inode);
ll_set_lock_data(sbi->ll_md_exp, inode, it, NULL);
out:
ptlrpc_req_finished(request);
return inode;
}
/*
* By the time this is called, we already have created the directory cache
* entry for the new file, but it is so far negative - it has no inode.
*
* We defer creating the OBD object(s) until open, to keep the intent and
* non-intent code paths similar, and also because we do not have the MDS
* inode number before calling ll_create_node() (which is needed for LOV),
* so we would need to do yet another RPC to the MDS to store the LOV EA
* data on the MDS. If needed, we would pass the PACKED lmm as data and
* lmm_size in datalen (the MDS still has code which will handle that).
*
* If the create succeeds, we fill in the inode information
* with d_instantiate().
*/
static int ll_create_it(struct inode *dir, struct dentry *dentry,
struct lookup_intent *it)
{
struct inode *inode;
int rc = 0;
CDEBUG(D_VFSTRACE, "VFS Op:name=%pd, dir=" DFID "(%p), intent=%s\n",
dentry, PFID(ll_inode2fid(dir)), dir, LL_IT2STR(it));
rc = it_open_error(DISP_OPEN_CREATE, it);
if (rc)
return rc;
inode = ll_create_node(dir, it);
if (IS_ERR(inode))
return PTR_ERR(inode);
d_instantiate(dentry, inode);
return ll_init_security(dentry, inode, dir);
}
void ll_update_times(struct ptlrpc_request *request, struct inode *inode)
{
struct mdt_body *body = req_capsule_server_get(&request->rq_pill,
&RMF_MDT_BODY);
LASSERT(body);
if (body->mbo_valid & OBD_MD_FLMTIME &&
body->mbo_mtime > LTIME_S(inode->i_mtime)) {
CDEBUG(D_INODE, "setting fid " DFID " mtime from %lu to %llu\n",
PFID(ll_inode2fid(inode)), LTIME_S(inode->i_mtime),
body->mbo_mtime);
LTIME_S(inode->i_mtime) = body->mbo_mtime;
}
if (body->mbo_valid & OBD_MD_FLCTIME &&
body->mbo_ctime > LTIME_S(inode->i_ctime))
LTIME_S(inode->i_ctime) = body->mbo_ctime;
}
static int ll_new_node(struct inode *dir, struct dentry *dentry,
const char *tgt, umode_t mode, int rdev,
__u32 opc)
{
struct ptlrpc_request *request = NULL;
struct md_op_data *op_data;
struct inode *inode = NULL;
struct ll_sb_info *sbi = ll_i2sbi(dir);
int tgt_len = 0;
int err;
if (unlikely(tgt))
tgt_len = strlen(tgt) + 1;
again:
op_data = ll_prep_md_op_data(NULL, dir, NULL,
dentry->d_name.name,
dentry->d_name.len,
0, opc, NULL);
if (IS_ERR(op_data)) {
err = PTR_ERR(op_data);
goto err_exit;
}
err = md_create(sbi->ll_md_exp, op_data, tgt, tgt_len, mode,
from_kuid(&init_user_ns, current_fsuid()),
from_kgid(&init_user_ns, current_fsgid()),
cfs_curproc_cap_pack(), rdev, &request);
ll_finish_md_op_data(op_data);
if (err < 0 && err != -EREMOTE)
goto err_exit;
/*
* If the client doesn't know where to create a subdirectory (or
* in case of a race that sends the RPC to the wrong MDS), the
* MDS will return -EREMOTE and the client will fetch the layout
* of the directory, then create the directory on the right MDT.
*/
if (unlikely(err == -EREMOTE)) {
struct ll_inode_info *lli = ll_i2info(dir);
struct lmv_user_md *lum;
int lumsize, err2;
ptlrpc_req_finished(request);
request = NULL;
err2 = ll_dir_getstripe(dir, (void **)&lum, &lumsize, &request,
OBD_MD_DEFAULT_MEA);
if (!err2) {
/* Update stripe_offset and retry */
lli->lli_def_stripe_offset = lum->lum_stripe_offset;
} else if (err2 == -ENODATA &&
lli->lli_def_stripe_offset != -1) {
/*
* If there are no default stripe EA on the MDT, but the
* client has default stripe, then it probably means
* default stripe EA has just been deleted.
*/
lli->lli_def_stripe_offset = -1;
} else {
goto err_exit;
}
ptlrpc_req_finished(request);
request = NULL;
goto again;
}
ll_update_times(request, dir);
err = ll_prep_inode(&inode, request, dir->i_sb, NULL);
if (err)
goto err_exit;
d_instantiate(dentry, inode);
err = ll_init_security(dentry, inode, dir);
err_exit:
if (request)
ptlrpc_req_finished(request);
return err;
}
static int ll_mknod(struct inode *dir, struct dentry *dchild,
umode_t mode, dev_t rdev)
{
int err;
CDEBUG(D_VFSTRACE, "VFS Op:name=%pd, dir=" DFID "(%p) mode %o dev %x\n",
dchild, PFID(ll_inode2fid(dir)), dir, mode,
old_encode_dev(rdev));
if (!IS_POSIXACL(dir) || !exp_connect_umask(ll_i2mdexp(dir)))
mode &= ~current_umask();
switch (mode & S_IFMT) {
case 0:
mode |= S_IFREG;
/* for mode = 0 case */
/* fall through */
case S_IFREG:
case S_IFCHR:
case S_IFBLK:
case S_IFIFO:
case S_IFSOCK:
err = ll_new_node(dir, dchild, NULL, mode,
old_encode_dev(rdev),
LUSTRE_OPC_MKNOD);
break;
case S_IFDIR:
err = -EPERM;
break;
default:
err = -EINVAL;
}
if (!err)
ll_stats_ops_tally(ll_i2sbi(dir), LPROC_LL_MKNOD, 1);
return err;
}
/*
* Plain create. Intent create is handled in atomic_open.
*/
static int ll_create_nd(struct inode *dir, struct dentry *dentry,
umode_t mode, bool want_excl)
{
int rc;
CDEBUG(D_VFSTRACE,
"VFS Op:name=%pd, dir=" DFID "(%p), flags=%u, excl=%d\n",
dentry, PFID(ll_inode2fid(dir)), dir, mode, want_excl);
rc = ll_mknod(dir, dentry, mode, 0);
ll_stats_ops_tally(ll_i2sbi(dir), LPROC_LL_CREATE, 1);
CDEBUG(D_VFSTRACE, "VFS Op:name=%pd, unhashed %d\n",
dentry, d_unhashed(dentry));
return rc;
}
static int ll_unlink(struct inode *dir, struct dentry *dchild)
{
struct ptlrpc_request *request = NULL;
struct md_op_data *op_data;
int rc;
CDEBUG(D_VFSTRACE, "VFS Op:name=%pd,dir=%lu/%u(%p)\n",
dchild, dir->i_ino, dir->i_generation, dir);
op_data = ll_prep_md_op_data(NULL, dir, NULL,
dchild->d_name.name,
dchild->d_name.len,
0, LUSTRE_OPC_ANY, NULL);
if (IS_ERR(op_data))
return PTR_ERR(op_data);
if (dchild->d_inode)
op_data->op_fid3 = *ll_inode2fid(dchild->d_inode);
op_data->op_fid2 = op_data->op_fid3;
rc = md_unlink(ll_i2sbi(dir)->ll_md_exp, op_data, &request);
ll_finish_md_op_data(op_data);
if (rc)
goto out;
ll_update_times(request, dir);
ll_stats_ops_tally(ll_i2sbi(dir), LPROC_LL_UNLINK, 1);
out:
ptlrpc_req_finished(request);
return rc;
}
static int ll_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
int err;
CDEBUG(D_VFSTRACE, "VFS Op:name=%pd, dir" DFID "(%p)\n",
dentry, PFID(ll_inode2fid(dir)), dir);
if (!IS_POSIXACL(dir) || !exp_connect_umask(ll_i2mdexp(dir)))
mode &= ~current_umask();
mode = (mode & (0777 | S_ISVTX)) | S_IFDIR;
err = ll_new_node(dir, dentry, NULL, mode, 0, LUSTRE_OPC_MKDIR);
if (!err)
ll_stats_ops_tally(ll_i2sbi(dir), LPROC_LL_MKDIR, 1);
return err;
}
static int ll_rmdir(struct inode *dir, struct dentry *dchild)
{
struct ptlrpc_request *request = NULL;
struct md_op_data *op_data;
int rc;
CDEBUG(D_VFSTRACE, "VFS Op:name=%pd, dir=" DFID "(%p)\n",
dchild, PFID(ll_inode2fid(dir)), dir);
op_data = ll_prep_md_op_data(NULL, dir, NULL,
dchild->d_name.name,
dchild->d_name.len,
S_IFDIR, LUSTRE_OPC_ANY, NULL);
if (IS_ERR(op_data))
return PTR_ERR(op_data);
if (dchild->d_inode)
op_data->op_fid3 = *ll_inode2fid(dchild->d_inode);
op_data->op_fid2 = op_data->op_fid3;
rc = md_unlink(ll_i2sbi(dir)->ll_md_exp, op_data, &request);
ll_finish_md_op_data(op_data);
if (rc == 0) {
ll_update_times(request, dir);
ll_stats_ops_tally(ll_i2sbi(dir), LPROC_LL_RMDIR, 1);
}
ptlrpc_req_finished(request);
return rc;
}
static int ll_symlink(struct inode *dir, struct dentry *dentry,
const char *oldname)
{
int err;
CDEBUG(D_VFSTRACE, "VFS Op:name=%pd, dir=" DFID "(%p),target=%.*s\n",
dentry, PFID(ll_inode2fid(dir)), dir, 3000, oldname);
err = ll_new_node(dir, dentry, oldname, S_IFLNK | 0777,
0, LUSTRE_OPC_SYMLINK);
if (!err)
ll_stats_ops_tally(ll_i2sbi(dir), LPROC_LL_SYMLINK, 1);
return err;
}
static int ll_link(struct dentry *old_dentry, struct inode *dir,
struct dentry *new_dentry)
{
struct inode *src = d_inode(old_dentry);
struct ll_sb_info *sbi = ll_i2sbi(dir);
struct ptlrpc_request *request = NULL;
struct md_op_data *op_data;
int err;
CDEBUG(D_VFSTRACE,
"VFS Op: inode=" DFID "(%p), dir=" DFID "(%p), target=%pd\n",
PFID(ll_inode2fid(src)), src, PFID(ll_inode2fid(dir)), dir,
new_dentry);
op_data = ll_prep_md_op_data(NULL, src, dir, new_dentry->d_name.name,
new_dentry->d_name.len,
0, LUSTRE_OPC_ANY, NULL);
if (IS_ERR(op_data))
return PTR_ERR(op_data);
err = md_link(sbi->ll_md_exp, op_data, &request);
ll_finish_md_op_data(op_data);
if (err)
goto out;
ll_update_times(request, dir);
ll_stats_ops_tally(sbi, LPROC_LL_LINK, 1);
out:
ptlrpc_req_finished(request);
return err;
}
static int ll_rename(struct inode *src, struct dentry *src_dchild,
struct inode *tgt, struct dentry *tgt_dchild,
unsigned int flags)
{
struct ptlrpc_request *request = NULL;
struct ll_sb_info *sbi = ll_i2sbi(src);
struct md_op_data *op_data;
int err;
if (flags)
return -EINVAL;
CDEBUG(D_VFSTRACE,
"VFS Op:oldname=%pd, src_dir=" DFID "(%p), newname=%pd, tgt_dir=" DFID "(%p)\n",
src_dchild, PFID(ll_inode2fid(src)), src,
tgt_dchild, PFID(ll_inode2fid(tgt)), tgt);
op_data = ll_prep_md_op_data(NULL, src, tgt, NULL, 0, 0,
LUSTRE_OPC_ANY, NULL);
if (IS_ERR(op_data))
return PTR_ERR(op_data);
if (src_dchild->d_inode)
op_data->op_fid3 = *ll_inode2fid(src_dchild->d_inode);
if (tgt_dchild->d_inode)
op_data->op_fid4 = *ll_inode2fid(tgt_dchild->d_inode);
err = md_rename(sbi->ll_md_exp, op_data,
src_dchild->d_name.name,
src_dchild->d_name.len,
tgt_dchild->d_name.name,
tgt_dchild->d_name.len, &request);
ll_finish_md_op_data(op_data);
if (!err) {
ll_update_times(request, src);
ll_update_times(request, tgt);
ll_stats_ops_tally(sbi, LPROC_LL_RENAME, 1);
}
ptlrpc_req_finished(request);
if (!err)
d_move(src_dchild, tgt_dchild);
return err;
}
const struct inode_operations ll_dir_inode_operations = {
.mknod = ll_mknod,
.atomic_open = ll_atomic_open,
.lookup = ll_lookup_nd,
.create = ll_create_nd,
/* We need all these non-raw things for NFSD, to not patch it. */
.unlink = ll_unlink,
.mkdir = ll_mkdir,
.rmdir = ll_rmdir,
.symlink = ll_symlink,
.link = ll_link,
.rename = ll_rename,
.setattr = ll_setattr,
.getattr = ll_getattr,
.permission = ll_inode_permission,
.listxattr = ll_listxattr,
.get_acl = ll_get_acl,
};
const struct inode_operations ll_special_inode_operations = {
.setattr = ll_setattr,
.getattr = ll_getattr,
.permission = ll_inode_permission,
.listxattr = ll_listxattr,
.get_acl = ll_get_acl,
};
|