Blame view
fs/ceph/inode.c
48.8 KB
3d14c5d2b ceph: factor out ... |
1 |
#include <linux/ceph/ceph_debug.h> |
355da1eb7 ceph: inode opera... |
2 3 4 |
#include <linux/module.h> #include <linux/fs.h> |
355da1eb7 ceph: inode opera... |
5 6 7 8 9 10 11 12 13 |
#include <linux/slab.h> #include <linux/string.h> #include <linux/uaccess.h> #include <linux/kernel.h> #include <linux/namei.h> #include <linux/writeback.h> #include <linux/vmalloc.h> #include "super.h" |
3d14c5d2b ceph: factor out ... |
14 15 |
#include "mds_client.h" #include <linux/ceph/decode.h> |
355da1eb7 ceph: inode opera... |
16 17 18 19 20 21 22 23 24 25 26 27 28 29 |
/* * Ceph inode operations * * Implement basic inode helpers (get, alloc) and inode ops (getattr, * setattr, etc.), xattr helpers, and helpers for assimilating * metadata returned by the MDS into our cache. * * Also define helpers for doing asynchronous writeback, invalidation, * and truncation for the benefit of those who can't afford to block * (typically because they are in the message handler path). */ static const struct inode_operations ceph_symlink_iops; |
3c6f6b79a ceph: cleanup asy... |
30 31 32 |
static void ceph_invalidate_work(struct work_struct *work); static void ceph_writeback_work(struct work_struct *work); static void ceph_vmtruncate_work(struct work_struct *work); |
355da1eb7 ceph: inode opera... |
33 34 35 36 |
/* * find or create an inode, given the ceph ino number */ |
ad1fee96c ceph: add ino32 m... |
37 38 39 40 41 42 |
static int ceph_set_ino_cb(struct inode *inode, void *data) { ceph_inode(inode)->i_vino = *(struct ceph_vino *)data; inode->i_ino = ceph_vino_to_ino(*(struct ceph_vino *)data); return 0; } |
355da1eb7 ceph: inode opera... |
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 |
struct inode *ceph_get_inode(struct super_block *sb, struct ceph_vino vino) { struct inode *inode; ino_t t = ceph_vino_to_ino(vino); inode = iget5_locked(sb, t, ceph_ino_compare, ceph_set_ino_cb, &vino); if (inode == NULL) return ERR_PTR(-ENOMEM); if (inode->i_state & I_NEW) { dout("get_inode created new inode %p %llx.%llx ino %llx ", inode, ceph_vinop(inode), (u64)inode->i_ino); unlock_new_inode(inode); } dout("get_inode on %lu=%llx.%llx got %p ", inode->i_ino, vino.ino, vino.snap, inode); return inode; } /* * get/constuct snapdir inode for a given directory */ struct inode *ceph_get_snapdir(struct inode *parent) { struct ceph_vino vino = { .ino = ceph_ino(parent), .snap = CEPH_SNAPDIR, }; struct inode *inode = ceph_get_inode(parent->i_sb, vino); |
b377ff13b ceph: initialize ... |
74 |
struct ceph_inode_info *ci = ceph_inode(inode); |
355da1eb7 ceph: inode opera... |
75 76 77 |
BUG_ON(!S_ISDIR(parent->i_mode)); if (IS_ERR(inode)) |
7e34bc524 fs/ceph: Use ERR_... |
78 |
return inode; |
355da1eb7 ceph: inode opera... |
79 80 81 82 83 |
inode->i_mode = parent->i_mode; inode->i_uid = parent->i_uid; inode->i_gid = parent->i_gid; inode->i_op = &ceph_dir_iops; inode->i_fop = &ceph_dir_fops; |
b377ff13b ceph: initialize ... |
84 85 |
ci->i_snap_caps = CEPH_CAP_PIN; /* so we can open */ ci->i_rbytes = 0; |
355da1eb7 ceph: inode opera... |
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 |
return inode; } const struct inode_operations ceph_file_iops = { .permission = ceph_permission, .setattr = ceph_setattr, .getattr = ceph_getattr, .setxattr = ceph_setxattr, .getxattr = ceph_getxattr, .listxattr = ceph_listxattr, .removexattr = ceph_removexattr, }; /* * We use a 'frag tree' to keep track of the MDS's directory fragments * for a given inode (usually there is just a single fragment). We * need to know when a child frag is delegated to a new MDS, or when * it is flagged as replicated, so we can direct our requests * accordingly. */ /* * find/create a frag in the tree */ static struct ceph_inode_frag *__get_or_create_frag(struct ceph_inode_info *ci, u32 f) { struct rb_node **p; struct rb_node *parent = NULL; struct ceph_inode_frag *frag; int c; p = &ci->i_fragtree.rb_node; while (*p) { parent = *p; frag = rb_entry(parent, struct ceph_inode_frag, node); c = ceph_frag_compare(f, frag->frag); if (c < 0) p = &(*p)->rb_left; else if (c > 0) p = &(*p)->rb_right; else return frag; } frag = kmalloc(sizeof(*frag), GFP_NOFS); if (!frag) { pr_err("__get_or_create_frag ENOMEM on %p %llx.%llx " "frag %x ", &ci->vfs_inode, ceph_vinop(&ci->vfs_inode), f); return ERR_PTR(-ENOMEM); } frag->frag = f; frag->split_by = 0; frag->mds = -1; frag->ndist = 0; rb_link_node(&frag->node, parent, p); rb_insert_color(&frag->node, &ci->i_fragtree); dout("get_or_create_frag added %llx.%llx frag %x ", ceph_vinop(&ci->vfs_inode), f); return frag; } /* * find a specific frag @f */ struct ceph_inode_frag *__ceph_find_frag(struct ceph_inode_info *ci, u32 f) { struct rb_node *n = ci->i_fragtree.rb_node; while (n) { struct ceph_inode_frag *frag = rb_entry(n, struct ceph_inode_frag, node); int c = ceph_frag_compare(f, frag->frag); if (c < 0) n = n->rb_left; else if (c > 0) n = n->rb_right; else return frag; } return NULL; } /* * Choose frag containing the given value @v. If @pfrag is * specified, copy the frag delegation info to the caller if * it is present. */ u32 ceph_choose_frag(struct ceph_inode_info *ci, u32 v, struct ceph_inode_frag *pfrag, int *found) { u32 t = ceph_frag_make(0, 0); struct ceph_inode_frag *frag; unsigned nway, i; u32 n; if (found) *found = 0; mutex_lock(&ci->i_fragtree_mutex); while (1) { WARN_ON(!ceph_frag_contains_value(t, v)); frag = __ceph_find_frag(ci, t); if (!frag) break; /* t is a leaf */ if (frag->split_by == 0) { if (pfrag) memcpy(pfrag, frag, sizeof(*pfrag)); if (found) *found = 1; break; } /* choose child */ nway = 1 << frag->split_by; dout("choose_frag(%x) %x splits by %d (%d ways) ", v, t, frag->split_by, nway); for (i = 0; i < nway; i++) { n = ceph_frag_make_child(t, frag->split_by, i); if (ceph_frag_contains_value(n, v)) { t = n; break; } } BUG_ON(i == nway); } dout("choose_frag(%x) = %x ", v, t); mutex_unlock(&ci->i_fragtree_mutex); return t; } /* * Process dirfrag (delegation) info from the mds. Include leaf * fragment in tree ONLY if ndist > 0. Otherwise, only * branches/splits are included in i_fragtree) */ static int ceph_fill_dirfrag(struct inode *inode, struct ceph_mds_reply_dirfrag *dirinfo) { struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_inode_frag *frag; u32 id = le32_to_cpu(dirinfo->frag); int mds = le32_to_cpu(dirinfo->auth); int ndist = le32_to_cpu(dirinfo->ndist); int i; int err = 0; mutex_lock(&ci->i_fragtree_mutex); if (ndist == 0) { /* no delegation info needed. */ frag = __ceph_find_frag(ci, id); if (!frag) goto out; if (frag->split_by == 0) { /* tree leaf, remove */ dout("fill_dirfrag removed %llx.%llx frag %x" " (no ref) ", ceph_vinop(inode), id); rb_erase(&frag->node, &ci->i_fragtree); kfree(frag); } else { /* tree branch, keep and clear */ dout("fill_dirfrag cleared %llx.%llx frag %x" " referral ", ceph_vinop(inode), id); frag->mds = -1; frag->ndist = 0; } goto out; } /* find/add this frag to store mds delegation info */ frag = __get_or_create_frag(ci, id); if (IS_ERR(frag)) { /* this is not the end of the world; we can continue with bad/inaccurate delegation info */ pr_err("fill_dirfrag ENOMEM on mds ref %llx.%llx fg %x ", ceph_vinop(inode), le32_to_cpu(dirinfo->frag)); err = -ENOMEM; goto out; } frag->mds = mds; frag->ndist = min_t(u32, ndist, CEPH_MAX_DIRFRAG_REP); for (i = 0; i < frag->ndist; i++) frag->dist[i] = le32_to_cpu(dirinfo->dist[i]); dout("fill_dirfrag %llx.%llx frag %x ndist=%d ", ceph_vinop(inode), frag->frag, frag->ndist); out: mutex_unlock(&ci->i_fragtree_mutex); return err; } /* * initialize a newly allocated inode. */ struct inode *ceph_alloc_inode(struct super_block *sb) { struct ceph_inode_info *ci; int i; ci = kmem_cache_alloc(ceph_inode_cachep, GFP_NOFS); if (!ci) return NULL; dout("alloc_inode %p ", &ci->vfs_inode); |
be655596b ceph: use i_ceph_... |
308 |
spin_lock_init(&ci->i_ceph_lock); |
355da1eb7 ceph: inode opera... |
309 310 311 312 313 |
ci->i_version = 0; ci->i_time_warp_seq = 0; ci->i_ceph_flags = 0; ci->i_release_count = 0; ci->i_symlink = NULL; |
6c0f3af72 ceph: add dir_lay... |
314 |
memset(&ci->i_dir_layout, 0, sizeof(ci->i_dir_layout)); |
355da1eb7 ceph: inode opera... |
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 |
ci->i_fragtree = RB_ROOT; mutex_init(&ci->i_fragtree_mutex); ci->i_xattrs.blob = NULL; ci->i_xattrs.prealloc_blob = NULL; ci->i_xattrs.dirty = false; ci->i_xattrs.index = RB_ROOT; ci->i_xattrs.count = 0; ci->i_xattrs.names_size = 0; ci->i_xattrs.vals_size = 0; ci->i_xattrs.version = 0; ci->i_xattrs.index_version = 0; ci->i_caps = RB_ROOT; ci->i_auth_cap = NULL; ci->i_dirty_caps = 0; ci->i_flushing_caps = 0; INIT_LIST_HEAD(&ci->i_dirty_item); INIT_LIST_HEAD(&ci->i_flushing_item); ci->i_cap_flush_seq = 0; ci->i_cap_flush_last_tid = 0; memset(&ci->i_cap_flush_tid, 0, sizeof(ci->i_cap_flush_tid)); init_waitqueue_head(&ci->i_cap_wq); ci->i_hold_caps_min = 0; ci->i_hold_caps_max = 0; INIT_LIST_HEAD(&ci->i_cap_delay_list); ci->i_cap_exporting_mds = 0; ci->i_cap_exporting_mseq = 0; ci->i_cap_exporting_issued = 0; INIT_LIST_HEAD(&ci->i_cap_snaps); ci->i_head_snapc = NULL; ci->i_snap_caps = 0; for (i = 0; i < CEPH_FILE_MODE_NUM; i++) ci->i_nr_by_mode[i] = 0; ci->i_truncate_seq = 0; ci->i_truncate_size = 0; ci->i_truncate_pending = 0; ci->i_max_size = 0; ci->i_reported_size = 0; ci->i_wanted_max_size = 0; ci->i_requested_max_size = 0; ci->i_pin_ref = 0; ci->i_rd_ref = 0; ci->i_rdcache_ref = 0; ci->i_wr_ref = 0; |
d3d0720d4 ceph: do not use ... |
364 |
ci->i_wb_ref = 0; |
355da1eb7 ceph: inode opera... |
365 366 367 368 369 370 371 372 373 374 375 376 377 |
ci->i_wrbuffer_ref = 0; ci->i_wrbuffer_ref_head = 0; ci->i_shared_gen = 0; ci->i_rdcache_gen = 0; ci->i_rdcache_revoking = 0; INIT_LIST_HEAD(&ci->i_unsafe_writes); INIT_LIST_HEAD(&ci->i_unsafe_dirops); spin_lock_init(&ci->i_unsafe_lock); ci->i_snap_realm = NULL; INIT_LIST_HEAD(&ci->i_snap_realm_item); INIT_LIST_HEAD(&ci->i_snap_flush_item); |
3c6f6b79a ceph: cleanup asy... |
378 379 |
INIT_WORK(&ci->i_wb_work, ceph_writeback_work); INIT_WORK(&ci->i_pg_inv_work, ceph_invalidate_work); |
355da1eb7 ceph: inode opera... |
380 381 382 383 384 |
INIT_WORK(&ci->i_vmtruncate_work, ceph_vmtruncate_work); return &ci->vfs_inode; } |
fa0d7e3de fs: icache RCU fr... |
385 386 387 388 |
static void ceph_i_callback(struct rcu_head *head) { struct inode *inode = container_of(head, struct inode, i_rcu); struct ceph_inode_info *ci = ceph_inode(inode); |
fa0d7e3de fs: icache RCU fr... |
389 390 |
kmem_cache_free(ceph_inode_cachep, ci); } |
355da1eb7 ceph: inode opera... |
391 392 393 394 395 396 397 398 399 400 |
void ceph_destroy_inode(struct inode *inode) { struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_inode_frag *frag; struct rb_node *n; dout("destroy_inode %p ino %llx.%llx ", inode, ceph_vinop(inode)); ceph_queue_caps_release(inode); |
8b218b8a4 ceph: fix inode r... |
401 402 403 404 405 406 |
/* * we may still have a snap_realm reference if there are stray * caps in i_cap_exporting_issued or i_snap_caps. */ if (ci->i_snap_realm) { struct ceph_mds_client *mdsc = |
3d14c5d2b ceph: factor out ... |
407 |
ceph_sb_to_client(ci->vfs_inode.i_sb)->mdsc; |
8b218b8a4 ceph: fix inode r... |
408 409 410 411 412 413 414 415 416 |
struct ceph_snap_realm *realm = ci->i_snap_realm; dout(" dropping residual ref to snap realm %p ", realm); spin_lock(&realm->inodes_with_caps_lock); list_del_init(&ci->i_snap_realm_item); spin_unlock(&realm->inodes_with_caps_lock); ceph_put_snap_realm(mdsc, realm); } |
355da1eb7 ceph: inode opera... |
417 418 419 420 421 422 423 424 |
kfree(ci->i_symlink); while ((n = rb_first(&ci->i_fragtree)) != NULL) { frag = rb_entry(n, struct ceph_inode_frag, node); rb_erase(n, &ci->i_fragtree); kfree(frag); } __ceph_destroy_xattrs(ci); |
b6c1d5b81 ceph: simplify ce... |
425 426 427 428 |
if (ci->i_xattrs.blob) ceph_buffer_put(ci->i_xattrs.blob); if (ci->i_xattrs.prealloc_blob) ceph_buffer_put(ci->i_xattrs.prealloc_blob); |
355da1eb7 ceph: inode opera... |
429 |
|
fa0d7e3de fs: icache RCU fr... |
430 |
call_rcu(&inode->i_rcu, ceph_i_callback); |
355da1eb7 ceph: inode opera... |
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 |
} /* * Helpers to fill in size, ctime, mtime, and atime. We have to be * careful because either the client or MDS may have more up to date * info, depending on which capabilities are held, and whether * time_warp_seq or truncate_seq have increased. (Ordinarily, mtime * and size are monotonically increasing, except when utimes() or * truncate() increments the corresponding _seq values.) */ int ceph_fill_file_size(struct inode *inode, int issued, u32 truncate_seq, u64 truncate_size, u64 size) { struct ceph_inode_info *ci = ceph_inode(inode); int queue_trunc = 0; if (ceph_seq_cmp(truncate_seq, ci->i_truncate_seq) > 0 || (truncate_seq == ci->i_truncate_seq && size > inode->i_size)) { dout("size %lld -> %llu ", inode->i_size, size); inode->i_size = size; inode->i_blocks = (size + (1<<9) - 1) >> 9; ci->i_reported_size = size; if (truncate_seq != ci->i_truncate_seq) { dout("truncate_seq %u -> %u ", ci->i_truncate_seq, truncate_seq); ci->i_truncate_seq = truncate_seq; |
3d497d858 ceph: fix truncat... |
460 461 462 463 464 465 466 |
/* * If we hold relevant caps, or in the case where we're * not the only client referencing this file and we * don't hold those caps, then we need to check whether * the file is either opened or mmaped */ if ((issued & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_RD| |
2962507ca ceph: perform laz... |
467 468 469 |
CEPH_CAP_FILE_WR|CEPH_CAP_FILE_BUFFER| CEPH_CAP_FILE_EXCL| CEPH_CAP_FILE_LAZYIO)) || |
3d497d858 ceph: fix truncat... |
470 471 |
mapping_mapped(inode->i_mapping) || __ceph_caps_file_wanted(ci)) { |
355da1eb7 ceph: inode opera... |
472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 |
ci->i_truncate_pending++; queue_trunc = 1; } } } if (ceph_seq_cmp(truncate_seq, ci->i_truncate_seq) >= 0 && ci->i_truncate_size != truncate_size) { dout("truncate_size %lld -> %llu ", ci->i_truncate_size, truncate_size); ci->i_truncate_size = truncate_size; } return queue_trunc; } void ceph_fill_file_time(struct inode *inode, int issued, u64 time_warp_seq, struct timespec *ctime, struct timespec *mtime, struct timespec *atime) { struct ceph_inode_info *ci = ceph_inode(inode); int warn = 0; if (issued & (CEPH_CAP_FILE_EXCL| CEPH_CAP_FILE_WR| |
d8672d64b ceph: fix update ... |
496 497 498 |
CEPH_CAP_FILE_BUFFER| CEPH_CAP_AUTH_EXCL| CEPH_CAP_XATTR_EXCL)) { |
355da1eb7 ceph: inode opera... |
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 |
if (timespec_compare(ctime, &inode->i_ctime) > 0) { dout("ctime %ld.%09ld -> %ld.%09ld inc w/ cap ", inode->i_ctime.tv_sec, inode->i_ctime.tv_nsec, ctime->tv_sec, ctime->tv_nsec); inode->i_ctime = *ctime; } if (ceph_seq_cmp(time_warp_seq, ci->i_time_warp_seq) > 0) { /* the MDS did a utimes() */ dout("mtime %ld.%09ld -> %ld.%09ld " "tw %d -> %d ", inode->i_mtime.tv_sec, inode->i_mtime.tv_nsec, mtime->tv_sec, mtime->tv_nsec, ci->i_time_warp_seq, (int)time_warp_seq); inode->i_mtime = *mtime; inode->i_atime = *atime; ci->i_time_warp_seq = time_warp_seq; } else if (time_warp_seq == ci->i_time_warp_seq) { /* nobody did utimes(); take the max */ if (timespec_compare(mtime, &inode->i_mtime) > 0) { dout("mtime %ld.%09ld -> %ld.%09ld inc ", inode->i_mtime.tv_sec, inode->i_mtime.tv_nsec, mtime->tv_sec, mtime->tv_nsec); inode->i_mtime = *mtime; } if (timespec_compare(atime, &inode->i_atime) > 0) { dout("atime %ld.%09ld -> %ld.%09ld inc ", inode->i_atime.tv_sec, inode->i_atime.tv_nsec, atime->tv_sec, atime->tv_nsec); inode->i_atime = *atime; } } else if (issued & CEPH_CAP_FILE_EXCL) { /* we did a utimes(); ignore mds values */ } else { warn = 1; } } else { |
d8672d64b ceph: fix update ... |
542 |
/* we have no write|excl caps; whatever the MDS says is true */ |
355da1eb7 ceph: inode opera... |
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 |
if (ceph_seq_cmp(time_warp_seq, ci->i_time_warp_seq) >= 0) { inode->i_ctime = *ctime; inode->i_mtime = *mtime; inode->i_atime = *atime; ci->i_time_warp_seq = time_warp_seq; } else { warn = 1; } } if (warn) /* time_warp_seq shouldn't go backwards */ dout("%p mds time_warp_seq %llu < %u ", inode, time_warp_seq, ci->i_time_warp_seq); } /* * Populate an inode based on info from mds. May be called on new or * existing inodes. */ static int fill_inode(struct inode *inode, struct ceph_mds_reply_info_in *iinfo, struct ceph_mds_reply_dirfrag *dirinfo, struct ceph_mds_session *session, unsigned long ttl_from, int cap_fmode, struct ceph_cap_reservation *caps_reservation) { struct ceph_mds_reply_inode *info = iinfo->in; struct ceph_inode_info *ci = ceph_inode(inode); int i; |
dfabbed6f ceph: set dir com... |
572 573 |
int issued = 0, implemented; int updating_inode = 0; |
355da1eb7 ceph: inode opera... |
574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 |
struct timespec mtime, atime, ctime; u32 nsplits; struct ceph_buffer *xattr_blob = NULL; int err = 0; int queue_trunc = 0; dout("fill_inode %p ino %llx.%llx v %llu had %llu ", inode, ceph_vinop(inode), le64_to_cpu(info->version), ci->i_version); /* * prealloc xattr data, if it looks like we'll need it. only * if len > 4 (meaning there are actually xattrs; the first 4 * bytes are the xattr count). */ if (iinfo->xattr_len > 4) { |
b6c1d5b81 ceph: simplify ce... |
591 |
xattr_blob = ceph_buffer_new(iinfo->xattr_len, GFP_NOFS); |
355da1eb7 ceph: inode opera... |
592 593 594 595 596 |
if (!xattr_blob) pr_err("fill_inode ENOMEM xattr blob %d bytes ", iinfo->xattr_len); } |
be655596b ceph: use i_ceph_... |
597 |
spin_lock(&ci->i_ceph_lock); |
355da1eb7 ceph: inode opera... |
598 599 600 |
/* * provided version will be odd if inode value is projected, |
8bd59e018 ceph: fix version... |
601 602 603 604 605 606 607 608 |
* even if stable. skip the update if we have newer stable * info (ours>=theirs, e.g. due to racing mds replies), unless * we are getting projected (unstable) info (in which case the * version is odd, and we want ours>theirs). * us them * 2 2 skip * 3 2 skip * 3 3 update |
355da1eb7 ceph: inode opera... |
609 610 |
*/ if (le64_to_cpu(info->version) > 0 && |
8bd59e018 ceph: fix version... |
611 |
(ci->i_version & ~1) >= le64_to_cpu(info->version)) |
355da1eb7 ceph: inode opera... |
612 |
goto no_change; |
dfabbed6f ceph: set dir com... |
613 614 |
updating_inode = 1; |
355da1eb7 ceph: inode opera... |
615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 |
issued = __ceph_caps_issued(ci, &implemented); issued |= implemented | __ceph_caps_dirty(ci); /* update inode */ ci->i_version = le64_to_cpu(info->version); inode->i_version++; inode->i_rdev = le32_to_cpu(info->rdev); if ((issued & CEPH_CAP_AUTH_EXCL) == 0) { inode->i_mode = le32_to_cpu(info->mode); inode->i_uid = le32_to_cpu(info->uid); inode->i_gid = le32_to_cpu(info->gid); dout("%p mode 0%o uid.gid %d.%d ", inode, inode->i_mode, inode->i_uid, inode->i_gid); } if ((issued & CEPH_CAP_LINK_EXCL) == 0) |
bfe868486 filesystems: add ... |
633 |
set_nlink(inode, le32_to_cpu(info->nlink)); |
355da1eb7 ceph: inode opera... |
634 635 636 637 638 639 640 641 |
/* be careful with mtime, atime, size */ ceph_decode_timespec(&atime, &info->atime); ceph_decode_timespec(&mtime, &info->mtime); ceph_decode_timespec(&ctime, &info->ctime); queue_trunc = ceph_fill_file_size(inode, issued, le32_to_cpu(info->truncate_seq), le64_to_cpu(info->truncate_size), |
355da1eb7 ceph: inode opera... |
642 643 644 645 |
le64_to_cpu(info->size)); ceph_fill_file_time(inode, issued, le32_to_cpu(info->time_warp_seq), &ctime, &mtime, &atime); |
912a9b031 ceph: only let au... |
646 647 648 649 650 651 652 653 |
/* only update max_size on auth cap */ if ((info->cap.flags & CEPH_CAP_FLAG_AUTH) && ci->i_max_size != le64_to_cpu(info->max_size)) { dout("max_size %lld -> %llu ", ci->i_max_size, le64_to_cpu(info->max_size)); ci->i_max_size = le64_to_cpu(info->max_size); } |
355da1eb7 ceph: inode opera... |
654 655 656 657 658 659 660 661 662 663 664 665 666 667 |
ci->i_layout = info->layout; inode->i_blkbits = fls(le32_to_cpu(info->layout.fl_stripe_unit)) - 1; /* xattrs */ /* note that if i_xattrs.len <= 4, i_xattrs.data will still be NULL. */ if ((issued & CEPH_CAP_XATTR_EXCL) == 0 && le64_to_cpu(info->xattr_version) > ci->i_xattrs.version) { if (ci->i_xattrs.blob) ceph_buffer_put(ci->i_xattrs.blob); ci->i_xattrs.blob = xattr_blob; if (xattr_blob) memcpy(ci->i_xattrs.blob->vec.iov_base, iinfo->xattr_data, iinfo->xattr_len); ci->i_xattrs.version = le64_to_cpu(info->xattr_version); |
a6424e48c ceph: fix xattr d... |
668 |
xattr_blob = NULL; |
355da1eb7 ceph: inode opera... |
669 670 671 672 |
} inode->i_mapping->a_ops = &ceph_aops; inode->i_mapping->backing_dev_info = |
640ef79d2 ceph: use ceph_sb... |
673 |
&ceph_sb_to_client(inode->i_sb)->backing_dev_info; |
355da1eb7 ceph: inode opera... |
674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 |
switch (inode->i_mode & S_IFMT) { case S_IFIFO: case S_IFBLK: case S_IFCHR: case S_IFSOCK: init_special_inode(inode, inode->i_mode, inode->i_rdev); inode->i_op = &ceph_file_iops; break; case S_IFREG: inode->i_op = &ceph_file_iops; inode->i_fop = &ceph_file_fops; break; case S_IFLNK: inode->i_op = &ceph_symlink_iops; if (!ci->i_symlink) { int symlen = iinfo->symlink_len; char *sym; BUG_ON(symlen != inode->i_size); |
be655596b ceph: use i_ceph_... |
694 |
spin_unlock(&ci->i_ceph_lock); |
355da1eb7 ceph: inode opera... |
695 696 697 698 699 700 701 |
err = -ENOMEM; sym = kmalloc(symlen+1, GFP_NOFS); if (!sym) goto out; memcpy(sym, iinfo->symlink, symlen); sym[symlen] = 0; |
be655596b ceph: use i_ceph_... |
702 |
spin_lock(&ci->i_ceph_lock); |
355da1eb7 ceph: inode opera... |
703 704 705 706 707 708 709 710 711 |
if (!ci->i_symlink) ci->i_symlink = sym; else kfree(sym); /* lost a race */ } break; case S_IFDIR: inode->i_op = &ceph_dir_iops; inode->i_fop = &ceph_dir_fops; |
14303d20f ceph: implement D... |
712 |
ci->i_dir_layout = iinfo->dir_layout; |
355da1eb7 ceph: inode opera... |
713 714 715 716 717 718 |
ci->i_files = le64_to_cpu(info->files); ci->i_subdirs = le64_to_cpu(info->subdirs); ci->i_rbytes = le64_to_cpu(info->rbytes); ci->i_rfiles = le64_to_cpu(info->rfiles); ci->i_rsubdirs = le64_to_cpu(info->rsubdirs); ceph_decode_timespec(&ci->i_rctime, &info->rctime); |
355da1eb7 ceph: inode opera... |
719 720 721 722 723 724 725 726 |
break; default: pr_err("fill_inode %llx.%llx BAD mode 0%o ", ceph_vinop(inode), inode->i_mode); } no_change: |
be655596b ceph: use i_ceph_... |
727 |
spin_unlock(&ci->i_ceph_lock); |
355da1eb7 ceph: inode opera... |
728 729 730 |
/* queue truncate if we saw i_size decrease */ if (queue_trunc) |
3c6f6b79a ceph: cleanup asy... |
731 |
ceph_queue_vmtruncate(inode); |
355da1eb7 ceph: inode opera... |
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 |
/* populate frag tree */ /* FIXME: move me up, if/when version reflects fragtree changes */ nsplits = le32_to_cpu(info->fragtree.nsplits); mutex_lock(&ci->i_fragtree_mutex); for (i = 0; i < nsplits; i++) { u32 id = le32_to_cpu(info->fragtree.splits[i].frag); struct ceph_inode_frag *frag = __get_or_create_frag(ci, id); if (IS_ERR(frag)) continue; frag->split_by = le32_to_cpu(info->fragtree.splits[i].by); dout(" frag %x split by %d ", frag->frag, frag->split_by); } mutex_unlock(&ci->i_fragtree_mutex); /* were we issued a capability? */ if (info->cap.caps) { if (ceph_snap(inode) == CEPH_NOSNAP) { ceph_add_cap(inode, session, le64_to_cpu(info->cap.cap_id), cap_fmode, le32_to_cpu(info->cap.caps), le32_to_cpu(info->cap.wanted), le32_to_cpu(info->cap.seq), le32_to_cpu(info->cap.mseq), le64_to_cpu(info->cap.realm), info->cap.flags, caps_reservation); } else { |
be655596b ceph: use i_ceph_... |
763 |
spin_lock(&ci->i_ceph_lock); |
355da1eb7 ceph: inode opera... |
764 765 766 767 768 769 |
dout(" %p got snap_caps %s ", inode, ceph_cap_string(le32_to_cpu(info->cap.caps))); ci->i_snap_caps |= le32_to_cpu(info->cap.caps); if (cap_fmode >= 0) __ceph_get_fmode(ci, cap_fmode); |
be655596b ceph: use i_ceph_... |
770 |
spin_unlock(&ci->i_ceph_lock); |
355da1eb7 ceph: inode opera... |
771 |
} |
04d000eb3 ceph: fix open fi... |
772 773 774 775 776 |
} else if (cap_fmode >= 0) { pr_warning("mds issued no caps on %llx.%llx ", ceph_vinop(inode)); __ceph_get_fmode(ci, cap_fmode); |
355da1eb7 ceph: inode opera... |
777 |
} |
dfabbed6f ceph: set dir com... |
778 779 780 781 782 783 784 |
/* set dir completion flag? */ if (S_ISDIR(inode->i_mode) && updating_inode && /* didn't jump to no_change */ ci->i_files == 0 && ci->i_subdirs == 0 && ceph_snap(inode) == CEPH_NOSNAP && (le32_to_cpu(info->cap.caps) & CEPH_CAP_FILE_SHARED) && (issued & CEPH_CAP_FILE_EXCL) == 0 && |
c6ffe1001 ceph: use new D_C... |
785 |
!ceph_dir_test_complete(inode)) { |
dfabbed6f ceph: set dir com... |
786 787 |
dout(" marking %p complete (empty) ", inode); |
c6ffe1001 ceph: use new D_C... |
788 |
ceph_dir_set_complete(inode); |
dfabbed6f ceph: set dir com... |
789 790 |
ci->i_max_offset = 2; } |
355da1eb7 ceph: inode opera... |
791 792 793 794 795 796 797 |
/* update delegation info? */ if (dirinfo) ceph_fill_dirfrag(inode, dirinfo); err = 0; out: |
b6c1d5b81 ceph: simplify ce... |
798 799 |
if (xattr_blob) ceph_buffer_put(xattr_blob); |
355da1eb7 ceph: inode opera... |
800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 |
return err; } /* * caller should hold session s_mutex. */ static void update_dentry_lease(struct dentry *dentry, struct ceph_mds_reply_lease *lease, struct ceph_mds_session *session, unsigned long from_time) { struct ceph_dentry_info *di = ceph_dentry(dentry); long unsigned duration = le32_to_cpu(lease->duration_ms); long unsigned ttl = from_time + (duration * HZ) / 1000; long unsigned half_ttl = from_time + (duration * HZ / 2) / 1000; struct inode *dir; /* only track leases on regular dentries */ if (dentry->d_op != &ceph_dentry_ops) return; spin_lock(&dentry->d_lock); |
2f90b852e ceph: ignore leas... |
822 823 824 |
dout("update_dentry_lease %p duration %lu ms ttl %lu ", dentry, duration, ttl); |
355da1eb7 ceph: inode opera... |
825 826 827 828 |
/* make lease_rdcache_gen match directory */ dir = dentry->d_parent->d_inode; di->lease_shared_gen = ceph_inode(dir)->i_shared_gen; |
2f90b852e ceph: ignore leas... |
829 |
if (duration == 0) |
355da1eb7 ceph: inode opera... |
830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 |
goto out_unlock; if (di->lease_gen == session->s_cap_gen && time_before(ttl, dentry->d_time)) goto out_unlock; /* we already have a newer lease. */ if (di->lease_session && di->lease_session != session) goto out_unlock; ceph_dentry_lru_touch(dentry); if (!di->lease_session) di->lease_session = ceph_get_mds_session(session); di->lease_gen = session->s_cap_gen; di->lease_seq = le32_to_cpu(lease->seq); di->lease_renew_after = half_ttl; di->lease_renew_from = 0; dentry->d_time = ttl; out_unlock: spin_unlock(&dentry->d_lock); return; } /* |
1cd3935be ceph: set dn offs... |
854 855 |
* Set dentry's directory position based on the current dir's max, and * order it in d_subdirs, so that dcache_readdir behaves. |
4f1772645 ceph: document lo... |
856 857 |
* * Always called under directory's i_mutex. |
1cd3935be ceph: set dn offs... |
858 859 860 861 |
*/ static void ceph_set_dentry_offset(struct dentry *dn) { struct dentry *dir = dn->d_parent; |
4f1772645 ceph: document lo... |
862 |
struct inode *inode = dir->d_inode; |
b8cd952b5 ceph: dereference... |
863 |
struct ceph_inode_info *ci; |
1cd3935be ceph: set dn offs... |
864 865 866 |
struct ceph_dentry_info *di; BUG_ON(!inode); |
b8cd952b5 ceph: dereference... |
867 |
ci = ceph_inode(inode); |
1cd3935be ceph: set dn offs... |
868 |
di = ceph_dentry(dn); |
be655596b ceph: use i_ceph_... |
869 |
spin_lock(&ci->i_ceph_lock); |
c6ffe1001 ceph: use new D_C... |
870 |
if (!ceph_dir_test_complete(inode)) { |
be655596b ceph: use i_ceph_... |
871 |
spin_unlock(&ci->i_ceph_lock); |
1cd3935be ceph: set dn offs... |
872 873 874 |
return; } di->offset = ceph_inode(inode)->i_max_offset++; |
be655596b ceph: use i_ceph_... |
875 |
spin_unlock(&ci->i_ceph_lock); |
1cd3935be ceph: set dn offs... |
876 |
|
2fd6b7f50 fs: dcache scale ... |
877 878 |
spin_lock(&dir->d_lock); spin_lock_nested(&dn->d_lock, DENTRY_D_LOCK_NESTED); |
13a4214cd ceph: fix d_subdi... |
879 |
list_move(&dn->d_u.d_child, &dir->d_subdirs); |
1cd3935be ceph: set dn offs... |
880 881 882 883 |
dout("set_dentry_offset %p %lld (%p %p) ", dn, di->offset, dn->d_u.d_child.prev, dn->d_u.d_child.next); spin_unlock(&dn->d_lock); |
2fd6b7f50 fs: dcache scale ... |
884 |
spin_unlock(&dir->d_lock); |
1cd3935be ceph: set dn offs... |
885 886 887 |
} /* |
355da1eb7 ceph: inode opera... |
888 889 890 891 892 893 894 895 |
* splice a dentry to an inode. * caller must hold directory i_mutex for this to be safe. * * we will only rehash the resulting dentry if @prehash is * true; @prehash will be set to false (for the benefit of * the caller) if we fail. */ static struct dentry *splice_dentry(struct dentry *dn, struct inode *in, |
467c52510 ceph: fix dn offs... |
896 |
bool *prehash, bool set_offset) |
355da1eb7 ceph: inode opera... |
897 898 |
{ struct dentry *realdn; |
1cd3935be ceph: set dn offs... |
899 |
BUG_ON(dn->d_inode); |
355da1eb7 ceph: inode opera... |
900 901 902 903 904 |
/* dn must be unhashed */ if (!d_unhashed(dn)) d_drop(dn); realdn = d_materialise_unique(dn, in); if (IS_ERR(realdn)) { |
d69ed05a8 ceph: handle spli... |
905 906 907 |
pr_err("splice_dentry error %ld %p inode %p ino %llx.%llx ", PTR_ERR(realdn), dn, in, ceph_vinop(in)); |
355da1eb7 ceph: inode opera... |
908 909 910 911 912 913 914 915 |
if (prehash) *prehash = false; /* don't rehash on error */ dn = realdn; /* note realdn contains the error */ goto out; } else if (realdn) { dout("dn %p (%d) spliced with %p (%d) " "inode %p ino %llx.%llx ", |
b7ab39f63 fs: dcache scale ... |
916 917 |
dn, dn->d_count, realdn, realdn->d_count, |
355da1eb7 ceph: inode opera... |
918 919 920 921 922 |
realdn->d_inode, ceph_vinop(realdn->d_inode)); dput(dn); dn = realdn; } else { BUG_ON(!ceph_dentry(dn)); |
355da1eb7 ceph: inode opera... |
923 924 925 926 927 928 |
dout("dn %p attached to %p ino %llx.%llx ", dn, dn->d_inode, ceph_vinop(dn->d_inode)); } if ((!prehash || *prehash) && d_unhashed(dn)) d_rehash(dn); |
467c52510 ceph: fix dn offs... |
929 930 |
if (set_offset) ceph_set_dentry_offset(dn); |
355da1eb7 ceph: inode opera... |
931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 |
out: return dn; } /* * Incorporate results into the local cache. This is either just * one inode, or a directory, dentry, and possibly linked-to inode (e.g., * after a lookup). * * A reply may contain * a directory inode along with a dentry. * and/or a target inode * * Called with snap_rwsem (read). */ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req, struct ceph_mds_session *session) { struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info; struct inode *in = NULL; struct ceph_mds_reply_inode *ininfo; struct ceph_vino vino; |
3d14c5d2b ceph: factor out ... |
953 |
struct ceph_fs_client *fsc = ceph_sb_to_client(sb); |
355da1eb7 ceph: inode opera... |
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 |
int i = 0; int err = 0; dout("fill_trace %p is_dentry %d is_target %d ", req, rinfo->head->is_dentry, rinfo->head->is_target); #if 0 /* * Debugging hook: * * If we resend completed ops to a recovering mds, we get no * trace. Since that is very rare, pretend this is the case * to ensure the 'no trace' handlers in the callers behave. * * Fill in inodes unconditionally to avoid breaking cap * invariants. */ if (rinfo->head->op & CEPH_MDS_OP_WRITE) { pr_info("fill_trace faking empty trace on %lld %s ", req->r_tid, ceph_mds_op_name(rinfo->head->op)); if (rinfo->head->is_dentry) { rinfo->head->is_dentry = 0; err = fill_inode(req->r_locked_dir, &rinfo->diri, rinfo->dirfrag, session, req->r_request_started, -1); } if (rinfo->head->is_target) { rinfo->head->is_target = 0; ininfo = rinfo->targeti.in; vino.ino = le64_to_cpu(ininfo->ino); vino.snap = le64_to_cpu(ininfo->snapid); in = ceph_get_inode(sb, vino); err = fill_inode(in, &rinfo->targeti, NULL, session, req->r_request_started, req->r_fmode); iput(in); } } #endif if (!rinfo->head->is_target && !rinfo->head->is_dentry) { dout("fill_trace reply is empty! "); |
167c9e352 ceph: use common ... |
999 1000 |
if (rinfo->head->result == 0 && req->r_locked_dir) ceph_invalidate_dir_request(req); |
355da1eb7 ceph: inode opera... |
1001 1002 1003 1004 |
return 0; } if (rinfo->head->is_dentry) { |
5b1daecd5 ceph: properly ha... |
1005 1006 1007 1008 1009 1010 1011 1012 |
struct inode *dir = req->r_locked_dir; err = fill_inode(dir, &rinfo->diri, rinfo->dirfrag, session, req->r_request_started, -1, &req->r_caps_reservation); if (err < 0) return err; } |
9358c6d4c ceph: fix dentry ... |
1013 1014 1015 1016 1017 1018 |
/* * ignore null lease/binding on snapdir ENOENT, or else we * will have trouble splicing in the virtual snapdir later */ if (rinfo->head->is_dentry && !req->r_aborted && (rinfo->head->is_target || strncmp(req->r_dentry->d_name.name, |
3d14c5d2b ceph: factor out ... |
1019 |
fsc->mount_options->snapdir_name, |
9358c6d4c ceph: fix dentry ... |
1020 |
req->r_dentry->d_name.len))) { |
355da1eb7 ceph: inode opera... |
1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 |
/* * lookup link rename : null -> possibly existing inode * mknod symlink mkdir : null -> new inode * unlink : linked -> null */ struct inode *dir = req->r_locked_dir; struct dentry *dn = req->r_dentry; bool have_dir_cap, have_lease; BUG_ON(!dn); BUG_ON(!dir); BUG_ON(dn->d_parent->d_inode != dir); BUG_ON(ceph_ino(dir) != le64_to_cpu(rinfo->diri.in->ino)); BUG_ON(ceph_snap(dir) != le64_to_cpu(rinfo->diri.in->snapid)); |
355da1eb7 ceph: inode opera... |
1037 1038 1039 1040 1041 1042 1043 |
/* do we have a lease on the whole dir? */ have_dir_cap = (le32_to_cpu(rinfo->diri.in->cap.caps) & CEPH_CAP_FILE_SHARED); /* do we have a dn lease? */ have_lease = have_dir_cap || |
2f90b852e ceph: ignore leas... |
1044 |
le32_to_cpu(rinfo->dlease->duration_ms); |
355da1eb7 ceph: inode opera... |
1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 |
if (!have_lease) dout("fill_trace no dentry lease or dir cap "); /* rename? */ if (req->r_old_dentry && req->r_op == CEPH_MDS_OP_RENAME) { dout(" src %p '%.*s' dst %p '%.*s' ", req->r_old_dentry, req->r_old_dentry->d_name.len, req->r_old_dentry->d_name.name, dn, dn->d_name.len, dn->d_name.name); dout("fill_trace doing d_move %p -> %p ", req->r_old_dentry, dn); |
c10f5e12b ceph: clear dir c... |
1060 |
|
355da1eb7 ceph: inode opera... |
1061 1062 1063 1064 1065 1066 1067 |
d_move(req->r_old_dentry, dn); dout(" src %p '%.*s' dst %p '%.*s' ", req->r_old_dentry, req->r_old_dentry->d_name.len, req->r_old_dentry->d_name.name, dn, dn->d_name.len, dn->d_name.name); |
81a6cf2d3 ceph: invalidate ... |
1068 |
|
c4a29f26d ceph: ensure rena... |
1069 1070 |
/* ensure target dentry is invalidated, despite rehashing bug in vfs_rename_dir */ |
81a6cf2d3 ceph: invalidate ... |
1071 |
ceph_invalidate_dentry_lease(dn); |
09adc80c6 ceph: preserve I_... |
1072 1073 1074 1075 |
/* * d_move() puts the renamed dentry at the end of * d_subdirs. We need to assign it an appropriate * directory offset so we can behave when holding |
c6ffe1001 ceph: use new D_C... |
1076 |
* D_COMPLETE. |
09adc80c6 ceph: preserve I_... |
1077 1078 1079 1080 |
*/ ceph_set_dentry_offset(req->r_old_dentry); dout("dn %p gets new offset %lld ", req->r_old_dentry, |
1cd3935be ceph: set dn offs... |
1081 |
ceph_dentry(req->r_old_dentry)->offset); |
81a6cf2d3 ceph: invalidate ... |
1082 |
|
355da1eb7 ceph: inode opera... |
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 |
dn = req->r_old_dentry; /* use old_dentry */ in = dn->d_inode; } /* null dentry? */ if (!rinfo->head->is_target) { dout("fill_trace null dentry "); if (dn->d_inode) { dout("d_delete %p ", dn); d_delete(dn); } else { dout("d_instantiate %p NULL ", dn); d_instantiate(dn, NULL); if (have_lease && d_unhashed(dn)) d_rehash(dn); update_dentry_lease(dn, rinfo->dlease, session, req->r_request_started); } goto done; } /* attach proper inode */ ininfo = rinfo->targeti.in; vino.ino = le64_to_cpu(ininfo->ino); vino.snap = le64_to_cpu(ininfo->snapid); |
d8b16b3d1 ceph: fix bad poi... |
1112 1113 |
in = dn->d_inode; if (!in) { |
355da1eb7 ceph: inode opera... |
1114 1115 1116 1117 1118 1119 1120 1121 1122 |
in = ceph_get_inode(sb, vino); if (IS_ERR(in)) { pr_err("fill_trace bad get_inode " "%llx.%llx ", vino.ino, vino.snap); err = PTR_ERR(in); d_delete(dn); goto done; } |
467c52510 ceph: fix dn offs... |
1123 |
dn = splice_dentry(dn, in, &have_lease, true); |
355da1eb7 ceph: inode opera... |
1124 1125 1126 1127 1128 |
if (IS_ERR(dn)) { err = PTR_ERR(dn); goto done; } req->r_dentry = dn; /* may have spliced */ |
70b666c3b ceph: use ihold w... |
1129 |
ihold(in); |
355da1eb7 ceph: inode opera... |
1130 1131 |
} else if (ceph_ino(in) == vino.ino && ceph_snap(in) == vino.snap) { |
70b666c3b ceph: use ihold w... |
1132 |
ihold(in); |
355da1eb7 ceph: inode opera... |
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 |
} else { dout(" %p links to %p %llx.%llx, not %llx.%llx ", dn, in, ceph_ino(in), ceph_snap(in), vino.ino, vino.snap); have_lease = false; in = NULL; } if (have_lease) update_dentry_lease(dn, rinfo->dlease, session, req->r_request_started); dout(" final dn %p ", dn); i++; } else if (req->r_op == CEPH_MDS_OP_LOOKUPSNAP || req->r_op == CEPH_MDS_OP_MKSNAP) { struct dentry *dn = req->r_dentry; /* fill out a snapdir LOOKUPSNAP dentry */ BUG_ON(!dn); BUG_ON(!req->r_locked_dir); BUG_ON(ceph_snap(req->r_locked_dir) != CEPH_SNAPDIR); ininfo = rinfo->targeti.in; vino.ino = le64_to_cpu(ininfo->ino); vino.snap = le64_to_cpu(ininfo->snapid); in = ceph_get_inode(sb, vino); if (IS_ERR(in)) { pr_err("fill_inode get_inode badness %llx.%llx ", vino.ino, vino.snap); err = PTR_ERR(in); d_delete(dn); goto done; } dout(" linking snapped dir %p to dn %p ", in, dn); |
467c52510 ceph: fix dn offs... |
1170 |
dn = splice_dentry(dn, in, NULL, true); |
355da1eb7 ceph: inode opera... |
1171 1172 1173 1174 1175 |
if (IS_ERR(dn)) { err = PTR_ERR(dn); goto done; } req->r_dentry = dn; /* may have spliced */ |
70b666c3b ceph: use ihold w... |
1176 |
ihold(in); |
355da1eb7 ceph: inode opera... |
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 |
rinfo->head->is_dentry = 1; /* fool notrace handlers */ } if (rinfo->head->is_target) { vino.ino = le64_to_cpu(rinfo->targeti.in->ino); vino.snap = le64_to_cpu(rinfo->targeti.in->snapid); if (in == NULL || ceph_ino(in) != vino.ino || ceph_snap(in) != vino.snap) { in = ceph_get_inode(sb, vino); if (IS_ERR(in)) { err = PTR_ERR(in); goto done; } } req->r_target_inode = in; err = fill_inode(in, &rinfo->targeti, NULL, session, req->r_request_started, (le32_to_cpu(rinfo->head->result) == 0) ? req->r_fmode : -1, &req->r_caps_reservation); if (err < 0) { pr_err("fill_inode badness %p %llx.%llx ", in, ceph_vinop(in)); goto done; } } done: dout("fill_trace done err=%d ", err); return err; } /* * Prepopulate our cache with readdir results, leases, etc. */ int ceph_readdir_prepopulate(struct ceph_mds_request *req, struct ceph_mds_session *session) { struct dentry *parent = req->r_dentry; struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info; struct qstr dname; struct dentry *dn; struct inode *in; int err = 0, i; struct inode *snapdir = NULL; struct ceph_mds_request_head *rhead = req->r_request->front.iov_base; u64 frag = le32_to_cpu(rhead->args.readdir.frag); struct ceph_dentry_info *di; if (le32_to_cpu(rinfo->head->op) == CEPH_MDS_OP_LSSNAP) { snapdir = ceph_get_snapdir(parent->d_inode); parent = d_find_alias(snapdir); dout("readdir_prepopulate %d items under SNAPDIR dn %p ", rinfo->dir_nr, parent); } else { dout("readdir_prepopulate %d items under dn %p ", rinfo->dir_nr, parent); if (rinfo->dir_dir) ceph_fill_dirfrag(parent->d_inode, rinfo->dir_dir); } for (i = 0; i < rinfo->dir_nr; i++) { struct ceph_vino vino; dname.name = rinfo->dir_dname[i]; dname.len = rinfo->dir_dname_len[i]; dname.hash = full_name_hash(dname.name, dname.len); vino.ino = le64_to_cpu(rinfo->dir_in[i].in->ino); vino.snap = le64_to_cpu(rinfo->dir_in[i].in->snapid); retry_lookup: dn = d_lookup(parent, &dname); dout("d_lookup on parent=%p name=%.*s got %p ", parent, dname.len, dname.name, dn); if (!dn) { dn = d_alloc(parent, &dname); dout("d_alloc %p '%.*s' = %p ", parent, dname.len, dname.name, dn); if (dn == NULL) { dout("d_alloc badness "); err = -ENOMEM; goto out; } err = ceph_init_dentry(dn); |
8c696737a ceph: fix leak of... |
1273 1274 |
if (err < 0) { dput(dn); |
355da1eb7 ceph: inode opera... |
1275 |
goto out; |
8c696737a ceph: fix leak of... |
1276 |
} |
355da1eb7 ceph: inode opera... |
1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 |
} else if (dn->d_inode && (ceph_ino(dn->d_inode) != vino.ino || ceph_snap(dn->d_inode) != vino.snap)) { dout(" dn %p points to wrong inode %p ", dn, dn->d_inode); d_delete(dn); dput(dn); goto retry_lookup; } else { /* reorder parent's d_subdirs */ |
2fd6b7f50 fs: dcache scale ... |
1288 1289 |
spin_lock(&parent->d_lock); spin_lock_nested(&dn->d_lock, DENTRY_D_LOCK_NESTED); |
355da1eb7 ceph: inode opera... |
1290 1291 |
list_move(&dn->d_u.d_child, &parent->d_subdirs); spin_unlock(&dn->d_lock); |
2fd6b7f50 fs: dcache scale ... |
1292 |
spin_unlock(&parent->d_lock); |
355da1eb7 ceph: inode opera... |
1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 |
} di = dn->d_fsdata; di->offset = ceph_make_fpos(frag, i + req->r_readdir_offset); /* inode */ if (dn->d_inode) { in = dn->d_inode; } else { in = ceph_get_inode(parent->d_sb, vino); |
ac1f12ef5 ceph: ceph_get_in... |
1303 |
if (IS_ERR(in)) { |
355da1eb7 ceph: inode opera... |
1304 1305 1306 1307 |
dout("new_inode badness "); d_delete(dn); dput(dn); |
ac1f12ef5 ceph: ceph_get_in... |
1308 |
err = PTR_ERR(in); |
355da1eb7 ceph: inode opera... |
1309 1310 |
goto out; } |
467c52510 ceph: fix dn offs... |
1311 |
dn = splice_dentry(dn, in, NULL, false); |
d69ed05a8 ceph: handle spli... |
1312 1313 |
if (IS_ERR(dn)) dn = NULL; |
355da1eb7 ceph: inode opera... |
1314 1315 1316 1317 1318 1319 1320 |
} if (fill_inode(in, &rinfo->dir_in[i], NULL, session, req->r_request_started, -1, &req->r_caps_reservation) < 0) { pr_err("fill_inode badness on %p ", in); |
d69ed05a8 ceph: handle spli... |
1321 |
goto next_item; |
355da1eb7 ceph: inode opera... |
1322 |
} |
d69ed05a8 ceph: handle spli... |
1323 1324 1325 1326 1327 1328 1329 |
if (dn) update_dentry_lease(dn, rinfo->dir_dlease[i], req->r_session, req->r_request_started); next_item: if (dn) dput(dn); |
355da1eb7 ceph: inode opera... |
1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 |
} req->r_did_prepopulate = true; out: if (snapdir) { iput(snapdir); dput(parent); } dout("readdir_prepopulate done "); return err; } int ceph_inode_set_size(struct inode *inode, loff_t size) { struct ceph_inode_info *ci = ceph_inode(inode); int ret = 0; |
be655596b ceph: use i_ceph_... |
1347 |
spin_lock(&ci->i_ceph_lock); |
355da1eb7 ceph: inode opera... |
1348 1349 1350 1351 1352 1353 1354 1355 1356 |
dout("set_size %p %llu -> %llu ", inode, inode->i_size, size); inode->i_size = size; inode->i_blocks = (size + (1 << 9) - 1) >> 9; /* tell the MDS if we are approaching max_size */ if ((size << 1) >= ci->i_max_size && (ci->i_reported_size << 1) < ci->i_max_size) ret = 1; |
be655596b ceph: use i_ceph_... |
1357 |
spin_unlock(&ci->i_ceph_lock); |
355da1eb7 ceph: inode opera... |
1358 1359 1360 1361 1362 1363 1364 |
return ret; } /* * Write back inode data in a worker thread. (This can't be done * in the message handler context.) */ |
3c6f6b79a ceph: cleanup asy... |
1365 1366 |
void ceph_queue_writeback(struct inode *inode) { |
15a2015fb ceph: fix iput ra... |
1367 |
ihold(inode); |
3c6f6b79a ceph: cleanup asy... |
1368 1369 |
if (queue_work(ceph_inode_to_client(inode)->wb_wq, &ceph_inode(inode)->i_wb_work)) { |
2c27c9a57 ceph: fix typo in... |
1370 1371 |
dout("ceph_queue_writeback %p ", inode); |
3c6f6b79a ceph: cleanup asy... |
1372 |
} else { |
2c27c9a57 ceph: fix typo in... |
1373 1374 |
dout("ceph_queue_writeback %p failed ", inode); |
15a2015fb ceph: fix iput ra... |
1375 |
iput(inode); |
3c6f6b79a ceph: cleanup asy... |
1376 1377 1378 1379 |
} } static void ceph_writeback_work(struct work_struct *work) |
355da1eb7 ceph: inode opera... |
1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 |
{ struct ceph_inode_info *ci = container_of(work, struct ceph_inode_info, i_wb_work); struct inode *inode = &ci->vfs_inode; dout("writeback %p ", inode); filemap_fdatawrite(&inode->i_data); iput(inode); } /* |
3c6f6b79a ceph: cleanup asy... |
1392 1393 1394 1395 |
* queue an async invalidation */ void ceph_queue_invalidate(struct inode *inode) { |
15a2015fb ceph: fix iput ra... |
1396 |
ihold(inode); |
3c6f6b79a ceph: cleanup asy... |
1397 1398 1399 1400 |
if (queue_work(ceph_inode_to_client(inode)->pg_inv_wq, &ceph_inode(inode)->i_pg_inv_work)) { dout("ceph_queue_invalidate %p ", inode); |
3c6f6b79a ceph: cleanup asy... |
1401 1402 1403 |
} else { dout("ceph_queue_invalidate %p failed ", inode); |
15a2015fb ceph: fix iput ra... |
1404 |
iput(inode); |
3c6f6b79a ceph: cleanup asy... |
1405 1406 1407 1408 |
} } /* |
355da1eb7 ceph: inode opera... |
1409 1410 1411 |
* Invalidate inode pages in a worker thread. (This can't be done * in the message handler context.) */ |
3c6f6b79a ceph: cleanup asy... |
1412 |
static void ceph_invalidate_work(struct work_struct *work) |
355da1eb7 ceph: inode opera... |
1413 1414 1415 1416 1417 1418 |
{ struct ceph_inode_info *ci = container_of(work, struct ceph_inode_info, i_pg_inv_work); struct inode *inode = &ci->vfs_inode; u32 orig_gen; int check = 0; |
be655596b ceph: use i_ceph_... |
1419 |
spin_lock(&ci->i_ceph_lock); |
355da1eb7 ceph: inode opera... |
1420 1421 1422 |
dout("invalidate_pages %p gen %d revoking %d ", inode, ci->i_rdcache_gen, ci->i_rdcache_revoking); |
cd045cb42 ceph: fix rdcache... |
1423 |
if (ci->i_rdcache_revoking != ci->i_rdcache_gen) { |
355da1eb7 ceph: inode opera... |
1424 |
/* nevermind! */ |
be655596b ceph: use i_ceph_... |
1425 |
spin_unlock(&ci->i_ceph_lock); |
355da1eb7 ceph: inode opera... |
1426 1427 1428 |
goto out; } orig_gen = ci->i_rdcache_gen; |
be655596b ceph: use i_ceph_... |
1429 |
spin_unlock(&ci->i_ceph_lock); |
355da1eb7 ceph: inode opera... |
1430 |
|
83eaea22b Revert "ceph: don... |
1431 |
truncate_inode_pages(&inode->i_data, 0); |
355da1eb7 ceph: inode opera... |
1432 |
|
be655596b ceph: use i_ceph_... |
1433 |
spin_lock(&ci->i_ceph_lock); |
cd045cb42 ceph: fix rdcache... |
1434 1435 |
if (orig_gen == ci->i_rdcache_gen && orig_gen == ci->i_rdcache_revoking) { |
355da1eb7 ceph: inode opera... |
1436 1437 1438 |
dout("invalidate_pages %p gen %d successful ", inode, ci->i_rdcache_gen); |
cd045cb42 ceph: fix rdcache... |
1439 |
ci->i_rdcache_revoking--; |
355da1eb7 ceph: inode opera... |
1440 1441 |
check = 1; } else { |
cd045cb42 ceph: fix rdcache... |
1442 1443 1444 1445 |
dout("invalidate_pages %p gen %d raced, now %d revoking %d ", inode, orig_gen, ci->i_rdcache_gen, ci->i_rdcache_revoking); |
355da1eb7 ceph: inode opera... |
1446 |
} |
be655596b ceph: use i_ceph_... |
1447 |
spin_unlock(&ci->i_ceph_lock); |
355da1eb7 ceph: inode opera... |
1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 |
if (check) ceph_check_caps(ci, 0, NULL); out: iput(inode); } /* * called by trunc_wq; take i_mutex ourselves * * We also truncate in a separate thread as well. */ |
3c6f6b79a ceph: cleanup asy... |
1461 |
static void ceph_vmtruncate_work(struct work_struct *work) |
355da1eb7 ceph: inode opera... |
1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 |
{ struct ceph_inode_info *ci = container_of(work, struct ceph_inode_info, i_vmtruncate_work); struct inode *inode = &ci->vfs_inode; dout("vmtruncate_work %p ", inode); mutex_lock(&inode->i_mutex); __ceph_do_pending_vmtruncate(inode); mutex_unlock(&inode->i_mutex); iput(inode); } /* |
3c6f6b79a ceph: cleanup asy... |
1476 1477 1478 1479 1480 1481 |
* Queue an async vmtruncate. If we fail to queue work, we will handle * the truncation the next time we call __ceph_do_pending_vmtruncate. */ void ceph_queue_vmtruncate(struct inode *inode) { struct ceph_inode_info *ci = ceph_inode(inode); |
15a2015fb ceph: fix iput ra... |
1482 |
ihold(inode); |
640ef79d2 ceph: use ceph_sb... |
1483 |
if (queue_work(ceph_sb_to_client(inode->i_sb)->trunc_wq, |
3c6f6b79a ceph: cleanup asy... |
1484 1485 1486 |
&ci->i_vmtruncate_work)) { dout("ceph_queue_vmtruncate %p ", inode); |
3c6f6b79a ceph: cleanup asy... |
1487 1488 1489 1490 |
} else { dout("ceph_queue_vmtruncate %p failed, pending=%d ", inode, ci->i_truncate_pending); |
15a2015fb ceph: fix iput ra... |
1491 |
iput(inode); |
3c6f6b79a ceph: cleanup asy... |
1492 1493 1494 1495 |
} } /* |
355da1eb7 ceph: inode opera... |
1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 |
* called with i_mutex held. * * Make sure any pending truncation is applied before doing anything * that may depend on it. */ void __ceph_do_pending_vmtruncate(struct inode *inode) { struct ceph_inode_info *ci = ceph_inode(inode); u64 to; int wrbuffer_refs, wake = 0; retry: |
be655596b ceph: use i_ceph_... |
1508 |
spin_lock(&ci->i_ceph_lock); |
355da1eb7 ceph: inode opera... |
1509 1510 1511 |
if (ci->i_truncate_pending == 0) { dout("__do_pending_vmtruncate %p none pending ", inode); |
be655596b ceph: use i_ceph_... |
1512 |
spin_unlock(&ci->i_ceph_lock); |
355da1eb7 ceph: inode opera... |
1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 |
return; } /* * make sure any dirty snapped pages are flushed before we * possibly truncate them.. so write AND block! */ if (ci->i_wrbuffer_ref_head < ci->i_wrbuffer_ref) { dout("__do_pending_vmtruncate %p flushing snaps first ", inode); |
be655596b ceph: use i_ceph_... |
1524 |
spin_unlock(&ci->i_ceph_lock); |
355da1eb7 ceph: inode opera... |
1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 |
filemap_write_and_wait_range(&inode->i_data, 0, inode->i_sb->s_maxbytes); goto retry; } to = ci->i_truncate_size; wrbuffer_refs = ci->i_wrbuffer_ref; dout("__do_pending_vmtruncate %p (%d) to %lld ", inode, ci->i_truncate_pending, to); |
be655596b ceph: use i_ceph_... |
1535 |
spin_unlock(&ci->i_ceph_lock); |
355da1eb7 ceph: inode opera... |
1536 1537 |
truncate_inode_pages(inode->i_mapping, to); |
be655596b ceph: use i_ceph_... |
1538 |
spin_lock(&ci->i_ceph_lock); |
355da1eb7 ceph: inode opera... |
1539 1540 1541 |
ci->i_truncate_pending--; if (ci->i_truncate_pending == 0) wake = 1; |
be655596b ceph: use i_ceph_... |
1542 |
spin_unlock(&ci->i_ceph_lock); |
355da1eb7 ceph: inode opera... |
1543 1544 1545 1546 |
if (wrbuffer_refs == 0) ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL); if (wake) |
03066f234 ceph: use complet... |
1547 |
wake_up_all(&ci->i_cap_wq); |
355da1eb7 ceph: inode opera... |
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 |
} /* * symlinks */ static void *ceph_sym_follow_link(struct dentry *dentry, struct nameidata *nd) { struct ceph_inode_info *ci = ceph_inode(dentry->d_inode); nd_set_link(nd, ci->i_symlink); return NULL; } static const struct inode_operations ceph_symlink_iops = { .readlink = generic_readlink, .follow_link = ceph_sym_follow_link, }; /* * setattr */ int ceph_setattr(struct dentry *dentry, struct iattr *attr) { struct inode *inode = dentry->d_inode; struct ceph_inode_info *ci = ceph_inode(inode); |
5f21c96dd ceph: protect acc... |
1573 |
struct inode *parent_inode; |
355da1eb7 ceph: inode opera... |
1574 1575 |
const unsigned int ia_valid = attr->ia_valid; struct ceph_mds_request *req; |
3d14c5d2b ceph: factor out ... |
1576 |
struct ceph_mds_client *mdsc = ceph_sb_to_client(dentry->d_sb)->mdsc; |
355da1eb7 ceph: inode opera... |
1577 1578 1579 1580 |
int issued; int release = 0, dirtied = 0; int mask = 0; int err = 0; |
fca65b4ad ceph: do not call... |
1581 |
int inode_dirty_flags = 0; |
355da1eb7 ceph: inode opera... |
1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 |
if (ceph_snap(inode) != CEPH_NOSNAP) return -EROFS; __ceph_do_pending_vmtruncate(inode); err = inode_change_ok(inode, attr); if (err != 0) return err; req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETATTR, USE_AUTH_MDS); if (IS_ERR(req)) return PTR_ERR(req); |
be655596b ceph: use i_ceph_... |
1596 |
spin_lock(&ci->i_ceph_lock); |
355da1eb7 ceph: inode opera... |
1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 |
issued = __ceph_caps_issued(ci, NULL); dout("setattr %p issued %s ", inode, ceph_cap_string(issued)); if (ia_valid & ATTR_UID) { dout("setattr %p uid %d -> %d ", inode, inode->i_uid, attr->ia_uid); if (issued & CEPH_CAP_AUTH_EXCL) { inode->i_uid = attr->ia_uid; dirtied |= CEPH_CAP_AUTH_EXCL; } else if ((issued & CEPH_CAP_AUTH_SHARED) == 0 || attr->ia_uid != inode->i_uid) { req->r_args.setattr.uid = cpu_to_le32(attr->ia_uid); mask |= CEPH_SETATTR_UID; release |= CEPH_CAP_AUTH_SHARED; } } if (ia_valid & ATTR_GID) { dout("setattr %p gid %d -> %d ", inode, inode->i_gid, attr->ia_gid); if (issued & CEPH_CAP_AUTH_EXCL) { inode->i_gid = attr->ia_gid; dirtied |= CEPH_CAP_AUTH_EXCL; } else if ((issued & CEPH_CAP_AUTH_SHARED) == 0 || attr->ia_gid != inode->i_gid) { req->r_args.setattr.gid = cpu_to_le32(attr->ia_gid); mask |= CEPH_SETATTR_GID; release |= CEPH_CAP_AUTH_SHARED; } } if (ia_valid & ATTR_MODE) { dout("setattr %p mode 0%o -> 0%o ", inode, inode->i_mode, attr->ia_mode); if (issued & CEPH_CAP_AUTH_EXCL) { inode->i_mode = attr->ia_mode; dirtied |= CEPH_CAP_AUTH_EXCL; } else if ((issued & CEPH_CAP_AUTH_SHARED) == 0 || attr->ia_mode != inode->i_mode) { req->r_args.setattr.mode = cpu_to_le32(attr->ia_mode); mask |= CEPH_SETATTR_MODE; release |= CEPH_CAP_AUTH_SHARED; } } if (ia_valid & ATTR_ATIME) { dout("setattr %p atime %ld.%ld -> %ld.%ld ", inode, inode->i_atime.tv_sec, inode->i_atime.tv_nsec, attr->ia_atime.tv_sec, attr->ia_atime.tv_nsec); if (issued & CEPH_CAP_FILE_EXCL) { ci->i_time_warp_seq++; inode->i_atime = attr->ia_atime; dirtied |= CEPH_CAP_FILE_EXCL; } else if ((issued & CEPH_CAP_FILE_WR) && timespec_compare(&inode->i_atime, &attr->ia_atime) < 0) { inode->i_atime = attr->ia_atime; dirtied |= CEPH_CAP_FILE_WR; } else if ((issued & CEPH_CAP_FILE_SHARED) == 0 || !timespec_equal(&inode->i_atime, &attr->ia_atime)) { ceph_encode_timespec(&req->r_args.setattr.atime, &attr->ia_atime); mask |= CEPH_SETATTR_ATIME; release |= CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_RD | CEPH_CAP_FILE_WR; } } if (ia_valid & ATTR_MTIME) { dout("setattr %p mtime %ld.%ld -> %ld.%ld ", inode, inode->i_mtime.tv_sec, inode->i_mtime.tv_nsec, attr->ia_mtime.tv_sec, attr->ia_mtime.tv_nsec); if (issued & CEPH_CAP_FILE_EXCL) { ci->i_time_warp_seq++; inode->i_mtime = attr->ia_mtime; dirtied |= CEPH_CAP_FILE_EXCL; } else if ((issued & CEPH_CAP_FILE_WR) && timespec_compare(&inode->i_mtime, &attr->ia_mtime) < 0) { inode->i_mtime = attr->ia_mtime; dirtied |= CEPH_CAP_FILE_WR; } else if ((issued & CEPH_CAP_FILE_SHARED) == 0 || !timespec_equal(&inode->i_mtime, &attr->ia_mtime)) { ceph_encode_timespec(&req->r_args.setattr.mtime, &attr->ia_mtime); mask |= CEPH_SETATTR_MTIME; release |= CEPH_CAP_FILE_SHARED | CEPH_CAP_FILE_RD | CEPH_CAP_FILE_WR; } } if (ia_valid & ATTR_SIZE) { dout("setattr %p size %lld -> %lld ", inode, inode->i_size, attr->ia_size); if (attr->ia_size > inode->i_sb->s_maxbytes) { err = -EINVAL; goto out; } if ((issued & CEPH_CAP_FILE_EXCL) && attr->ia_size > inode->i_size) { inode->i_size = attr->ia_size; |
355da1eb7 ceph: inode opera... |
1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 |
inode->i_blocks = (attr->ia_size + (1 << 9) - 1) >> 9; inode->i_ctime = attr->ia_ctime; ci->i_reported_size = attr->ia_size; dirtied |= CEPH_CAP_FILE_EXCL; } else if ((issued & CEPH_CAP_FILE_SHARED) == 0 || attr->ia_size != inode->i_size) { req->r_args.setattr.size = cpu_to_le64(attr->ia_size); req->r_args.setattr.old_size = cpu_to_le64(inode->i_size); mask |= CEPH_SETATTR_SIZE; release |= CEPH_CAP_FILE_SHARED | CEPH_CAP_FILE_RD | CEPH_CAP_FILE_WR; } } /* these do nothing */ if (ia_valid & ATTR_CTIME) { bool only = (ia_valid & (ATTR_SIZE|ATTR_MTIME|ATTR_ATIME| ATTR_MODE|ATTR_UID|ATTR_GID)) == 0; dout("setattr %p ctime %ld.%ld -> %ld.%ld (%s) ", inode, inode->i_ctime.tv_sec, inode->i_ctime.tv_nsec, attr->ia_ctime.tv_sec, attr->ia_ctime.tv_nsec, only ? "ctime only" : "ignored"); inode->i_ctime = attr->ia_ctime; if (only) { /* * if kernel wants to dirty ctime but nothing else, * we need to choose a cap to dirty under, or do * a almost-no-op setattr */ if (issued & CEPH_CAP_AUTH_EXCL) dirtied |= CEPH_CAP_AUTH_EXCL; else if (issued & CEPH_CAP_FILE_EXCL) dirtied |= CEPH_CAP_FILE_EXCL; else if (issued & CEPH_CAP_XATTR_EXCL) dirtied |= CEPH_CAP_XATTR_EXCL; else mask |= CEPH_SETATTR_CTIME; } } if (ia_valid & ATTR_FILE) dout("setattr %p ATTR_FILE ... hrm! ", inode); if (dirtied) { |
fca65b4ad ceph: do not call... |
1748 |
inode_dirty_flags = __ceph_mark_dirty_caps(ci, dirtied); |
355da1eb7 ceph: inode opera... |
1749 1750 1751 1752 |
inode->i_ctime = CURRENT_TIME; } release &= issued; |
be655596b ceph: use i_ceph_... |
1753 |
spin_unlock(&ci->i_ceph_lock); |
355da1eb7 ceph: inode opera... |
1754 |
|
fca65b4ad ceph: do not call... |
1755 1756 |
if (inode_dirty_flags) __mark_inode_dirty(inode, inode_dirty_flags); |
355da1eb7 ceph: inode opera... |
1757 |
if (mask) { |
70b666c3b ceph: use ihold w... |
1758 1759 |
req->r_inode = inode; ihold(inode); |
355da1eb7 ceph: inode opera... |
1760 1761 1762 |
req->r_inode_drop = release; req->r_args.setattr.mask = cpu_to_le32(mask); req->r_num_caps = 1; |
5f21c96dd ceph: protect acc... |
1763 |
parent_inode = ceph_get_dentry_parent_inode(dentry); |
355da1eb7 ceph: inode opera... |
1764 |
err = ceph_mdsc_do_request(mdsc, parent_inode, req); |
5f21c96dd ceph: protect acc... |
1765 |
iput(parent_inode); |
355da1eb7 ceph: inode opera... |
1766 1767 1768 1769 1770 1771 1772 1773 1774 |
} dout("setattr %p result=%d (%s locally, %d remote) ", inode, err, ceph_cap_string(dirtied), mask); ceph_mdsc_put_request(req); __ceph_do_pending_vmtruncate(inode); return err; out: |
be655596b ceph: use i_ceph_... |
1775 |
spin_unlock(&ci->i_ceph_lock); |
355da1eb7 ceph: inode opera... |
1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 |
ceph_mdsc_put_request(req); return err; } /* * Verify that we have a lease on the given mask. If not, * do a getattr against an mds. */ int ceph_do_getattr(struct inode *inode, int mask) { |
3d14c5d2b ceph: factor out ... |
1786 1787 |
struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb); struct ceph_mds_client *mdsc = fsc->mdsc; |
355da1eb7 ceph: inode opera... |
1788 1789 1790 1791 1792 1793 1794 1795 |
struct ceph_mds_request *req; int err; if (ceph_snap(inode) == CEPH_SNAPDIR) { dout("do_getattr inode %p SNAPDIR ", inode); return 0; } |
b7495fc2f ceph: make page a... |
1796 1797 |
dout("do_getattr inode %p mask %s mode 0%o ", inode, ceph_cap_string(mask), inode->i_mode); |
355da1eb7 ceph: inode opera... |
1798 1799 1800 1801 1802 1803 |
if (ceph_caps_issued_mask(ceph_inode(inode), mask, 1)) return 0; req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_GETATTR, USE_ANY_MDS); if (IS_ERR(req)) return PTR_ERR(req); |
70b666c3b ceph: use ihold w... |
1804 1805 |
req->r_inode = inode; ihold(inode); |
355da1eb7 ceph: inode opera... |
1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 |
req->r_num_caps = 1; req->r_args.getattr.mask = cpu_to_le32(mask); err = ceph_mdsc_do_request(mdsc, NULL, req); ceph_mdsc_put_request(req); dout("do_getattr result=%d ", err); return err; } /* * Check inode permissions. We verify we have a valid value for * the AUTH cap, then call the generic handler. */ |
10556cb21 ->permission() sa... |
1820 |
int ceph_permission(struct inode *inode, int mask) |
355da1eb7 ceph: inode opera... |
1821 |
{ |
b74c79e99 fs: provide rcu-w... |
1822 |
int err; |
10556cb21 ->permission() sa... |
1823 |
if (mask & MAY_NOT_BLOCK) |
b74c79e99 fs: provide rcu-w... |
1824 1825 1826 |
return -ECHILD; err = ceph_do_getattr(inode, CEPH_CAP_AUTH_SHARED); |
355da1eb7 ceph: inode opera... |
1827 1828 |
if (!err) |
2830ba7f3 ->permission() sa... |
1829 |
err = generic_permission(inode, mask); |
355da1eb7 ceph: inode opera... |
1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 |
return err; } /* * Get all attributes. Hopefully somedata we'll have a statlite() * and can limit the fields we require to be accurate. */ int ceph_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) { struct inode *inode = dentry->d_inode; |
232d4b013 ceph: move direct... |
1841 |
struct ceph_inode_info *ci = ceph_inode(inode); |
355da1eb7 ceph: inode opera... |
1842 1843 1844 1845 1846 |
int err; err = ceph_do_getattr(inode, CEPH_STAT_CAP_INODE_ALL); if (!err) { generic_fillattr(inode, stat); |
ad1fee96c ceph: add ino32 m... |
1847 |
stat->ino = ceph_translate_ino(inode->i_sb, inode->i_ino); |
355da1eb7 ceph: inode opera... |
1848 1849 1850 1851 |
if (ceph_snap(inode) != CEPH_NOSNAP) stat->dev = ceph_snap(inode); else stat->dev = 0; |
232d4b013 ceph: move direct... |
1852 |
if (S_ISDIR(inode->i_mode)) { |
1c1266bb9 ceph: fix getattr... |
1853 1854 1855 1856 1857 |
if (ceph_test_mount_opt(ceph_sb_to_client(inode->i_sb), RBYTES)) stat->size = ci->i_rbytes; else stat->size = ci->i_files + ci->i_subdirs; |
232d4b013 ceph: move direct... |
1858 |
stat->blocks = 0; |
355da1eb7 ceph: inode opera... |
1859 |
stat->blksize = 65536; |
232d4b013 ceph: move direct... |
1860 |
} |
355da1eb7 ceph: inode opera... |
1861 1862 1863 |
} return err; } |