lh | 9ed821d | 2023-04-07 01:36:19 -0700 | [diff] [blame] | 1 | /* |
| 2 | * linux/fs/nfs/dir.c |
| 3 | * |
| 4 | * Copyright (C) 1992 Rick Sladkey |
| 5 | * |
| 6 | * nfs directory handling functions |
| 7 | * |
| 8 | * 10 Apr 1996 Added silly rename for unlink --okir |
| 9 | * 28 Sep 1996 Improved directory cache --okir |
| 10 | * 23 Aug 1997 Claus Heine claus@momo.math.rwth-aachen.de |
| 11 | * Re-implemented silly rename for unlink, newly implemented |
| 12 | * silly rename for nfs_rename() following the suggestions |
| 13 | * of Olaf Kirch (okir) found in this file. |
| 14 | * Following Linus comments on my original hack, this version |
| 15 | * depends only on the dcache stuff and doesn't touch the inode |
| 16 | * layer (iput() and friends). |
| 17 | * 6 Jun 1999 Cache readdir lookups in the page cache. -DaveM |
| 18 | */ |
| 19 | |
| 20 | #include <linux/time.h> |
| 21 | #include <linux/errno.h> |
| 22 | #include <linux/stat.h> |
| 23 | #include <linux/fcntl.h> |
| 24 | #include <linux/string.h> |
| 25 | #include <linux/kernel.h> |
| 26 | #include <linux/slab.h> |
| 27 | #include <linux/mm.h> |
| 28 | #include <linux/sunrpc/clnt.h> |
| 29 | #include <linux/nfs_fs.h> |
| 30 | #include <linux/nfs_mount.h> |
| 31 | #include <linux/pagemap.h> |
| 32 | #include <linux/pagevec.h> |
| 33 | #include <linux/namei.h> |
| 34 | #include <linux/mount.h> |
| 35 | #include <linux/sched.h> |
| 36 | #include <linux/kmemleak.h> |
| 37 | #include <linux/xattr.h> |
| 38 | |
| 39 | #include "delegation.h" |
| 40 | #include "iostat.h" |
| 41 | #include "internal.h" |
| 42 | #include "fscache.h" |
| 43 | |
| 44 | /* #define NFS_DEBUG_VERBOSE 1 */ |
| 45 | |
| 46 | static int nfs_opendir(struct inode *, struct file *); |
| 47 | static int nfs_closedir(struct inode *, struct file *); |
| 48 | static int nfs_readdir(struct file *, void *, filldir_t); |
| 49 | static struct dentry *nfs_lookup(struct inode *, struct dentry *, struct nameidata *); |
| 50 | static int nfs_create(struct inode *, struct dentry *, umode_t, struct nameidata *); |
| 51 | static int nfs_mkdir(struct inode *, struct dentry *, umode_t); |
| 52 | static int nfs_rmdir(struct inode *, struct dentry *); |
| 53 | static int nfs_unlink(struct inode *, struct dentry *); |
| 54 | static int nfs_symlink(struct inode *, struct dentry *, const char *); |
| 55 | static int nfs_link(struct dentry *, struct inode *, struct dentry *); |
| 56 | static int nfs_mknod(struct inode *, struct dentry *, umode_t, dev_t); |
| 57 | static int nfs_rename(struct inode *, struct dentry *, |
| 58 | struct inode *, struct dentry *); |
| 59 | static int nfs_fsync_dir(struct file *, loff_t, loff_t, int); |
| 60 | static loff_t nfs_llseek_dir(struct file *, loff_t, int); |
| 61 | static void nfs_readdir_clear_array(struct page*); |
| 62 | |
| 63 | const struct file_operations nfs_dir_operations = { |
| 64 | .llseek = nfs_llseek_dir, |
| 65 | .read = generic_read_dir, |
| 66 | .readdir = nfs_readdir, |
| 67 | .open = nfs_opendir, |
| 68 | .release = nfs_closedir, |
| 69 | .fsync = nfs_fsync_dir, |
| 70 | }; |
| 71 | |
| 72 | const struct inode_operations nfs_dir_inode_operations = { |
| 73 | .create = nfs_create, |
| 74 | .lookup = nfs_lookup, |
| 75 | .link = nfs_link, |
| 76 | .unlink = nfs_unlink, |
| 77 | .symlink = nfs_symlink, |
| 78 | .mkdir = nfs_mkdir, |
| 79 | .rmdir = nfs_rmdir, |
| 80 | .mknod = nfs_mknod, |
| 81 | .rename = nfs_rename, |
| 82 | .permission = nfs_permission, |
| 83 | .getattr = nfs_getattr, |
| 84 | .setattr = nfs_setattr, |
| 85 | }; |
| 86 | |
| 87 | const struct address_space_operations nfs_dir_aops = { |
| 88 | .freepage = nfs_readdir_clear_array, |
| 89 | }; |
| 90 | |
| 91 | #ifdef CONFIG_NFS_V3 |
| 92 | const struct inode_operations nfs3_dir_inode_operations = { |
| 93 | .create = nfs_create, |
| 94 | .lookup = nfs_lookup, |
| 95 | .link = nfs_link, |
| 96 | .unlink = nfs_unlink, |
| 97 | .symlink = nfs_symlink, |
| 98 | .mkdir = nfs_mkdir, |
| 99 | .rmdir = nfs_rmdir, |
| 100 | .mknod = nfs_mknod, |
| 101 | .rename = nfs_rename, |
| 102 | .permission = nfs_permission, |
| 103 | .getattr = nfs_getattr, |
| 104 | .setattr = nfs_setattr, |
| 105 | .listxattr = nfs3_listxattr, |
| 106 | .getxattr = nfs3_getxattr, |
| 107 | .setxattr = nfs3_setxattr, |
| 108 | .removexattr = nfs3_removexattr, |
| 109 | }; |
| 110 | #endif /* CONFIG_NFS_V3 */ |
| 111 | |
| 112 | #ifdef CONFIG_NFS_V4 |
| 113 | |
| 114 | static struct dentry *nfs_atomic_lookup(struct inode *, struct dentry *, struct nameidata *); |
| 115 | static int nfs_open_create(struct inode *dir, struct dentry *dentry, umode_t mode, struct nameidata *nd); |
| 116 | const struct inode_operations nfs4_dir_inode_operations = { |
| 117 | .create = nfs_open_create, |
| 118 | .lookup = nfs_atomic_lookup, |
| 119 | .link = nfs_link, |
| 120 | .unlink = nfs_unlink, |
| 121 | .symlink = nfs_symlink, |
| 122 | .mkdir = nfs_mkdir, |
| 123 | .rmdir = nfs_rmdir, |
| 124 | .mknod = nfs_mknod, |
| 125 | .rename = nfs_rename, |
| 126 | .permission = nfs_permission, |
| 127 | .getattr = nfs_getattr, |
| 128 | .setattr = nfs_setattr, |
| 129 | .getxattr = generic_getxattr, |
| 130 | .setxattr = generic_setxattr, |
| 131 | .listxattr = generic_listxattr, |
| 132 | .removexattr = generic_removexattr, |
| 133 | }; |
| 134 | |
| 135 | #endif /* CONFIG_NFS_V4 */ |
| 136 | |
| 137 | static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir, struct rpc_cred *cred) |
| 138 | { |
| 139 | struct nfs_open_dir_context *ctx; |
| 140 | ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); |
| 141 | if (ctx != NULL) { |
| 142 | ctx->duped = 0; |
| 143 | ctx->attr_gencount = NFS_I(dir)->attr_gencount; |
| 144 | ctx->dir_cookie = 0; |
| 145 | ctx->dup_cookie = 0; |
| 146 | ctx->cred = get_rpccred(cred); |
| 147 | return ctx; |
| 148 | } |
| 149 | return ERR_PTR(-ENOMEM); |
| 150 | } |
| 151 | |
| 152 | static void put_nfs_open_dir_context(struct nfs_open_dir_context *ctx) |
| 153 | { |
| 154 | put_rpccred(ctx->cred); |
| 155 | kfree(ctx); |
| 156 | } |
| 157 | |
| 158 | /* |
| 159 | * Open file |
| 160 | */ |
| 161 | static int |
| 162 | nfs_opendir(struct inode *inode, struct file *filp) |
| 163 | { |
| 164 | int res = 0; |
| 165 | struct nfs_open_dir_context *ctx; |
| 166 | struct rpc_cred *cred; |
| 167 | |
| 168 | dfprintk(FILE, "NFS: open dir(%s/%s)\n", |
| 169 | filp->f_path.dentry->d_parent->d_name.name, |
| 170 | filp->f_path.dentry->d_name.name); |
| 171 | |
| 172 | nfs_inc_stats(inode, NFSIOS_VFSOPEN); |
| 173 | |
| 174 | cred = rpc_lookup_cred(); |
| 175 | if (IS_ERR(cred)) |
| 176 | return PTR_ERR(cred); |
| 177 | ctx = alloc_nfs_open_dir_context(inode, cred); |
| 178 | if (IS_ERR(ctx)) { |
| 179 | res = PTR_ERR(ctx); |
| 180 | goto out; |
| 181 | } |
| 182 | filp->private_data = ctx; |
| 183 | if (filp->f_path.dentry == filp->f_path.mnt->mnt_root) { |
| 184 | /* This is a mountpoint, so d_revalidate will never |
| 185 | * have been called, so we need to refresh the |
| 186 | * inode (for close-open consistency) ourselves. |
| 187 | */ |
| 188 | __nfs_revalidate_inode(NFS_SERVER(inode), inode); |
| 189 | } |
| 190 | out: |
| 191 | put_rpccred(cred); |
| 192 | return res; |
| 193 | } |
| 194 | |
| 195 | static int |
| 196 | nfs_closedir(struct inode *inode, struct file *filp) |
| 197 | { |
| 198 | put_nfs_open_dir_context(filp->private_data); |
| 199 | return 0; |
| 200 | } |
| 201 | |
| 202 | struct nfs_cache_array_entry { |
| 203 | u64 cookie; |
| 204 | u64 ino; |
| 205 | struct qstr string; |
| 206 | unsigned char d_type; |
| 207 | }; |
| 208 | |
| 209 | struct nfs_cache_array { |
| 210 | int size; |
| 211 | int eof_index; |
| 212 | u64 last_cookie; |
| 213 | struct nfs_cache_array_entry array[0]; |
| 214 | }; |
| 215 | |
| 216 | typedef int (*decode_dirent_t)(struct xdr_stream *, struct nfs_entry *, int); |
| 217 | typedef struct { |
| 218 | struct file *file; |
| 219 | struct page *page; |
| 220 | unsigned long page_index; |
| 221 | u64 *dir_cookie; |
| 222 | u64 last_cookie; |
| 223 | loff_t current_index; |
| 224 | decode_dirent_t decode; |
| 225 | |
| 226 | unsigned long timestamp; |
| 227 | unsigned long gencount; |
| 228 | unsigned int cache_entry_index; |
| 229 | unsigned int plus:1; |
| 230 | unsigned int eof:1; |
| 231 | } nfs_readdir_descriptor_t; |
| 232 | |
| 233 | /* |
| 234 | * The caller is responsible for calling nfs_readdir_release_array(page) |
| 235 | */ |
| 236 | static |
| 237 | struct nfs_cache_array *nfs_readdir_get_array(struct page *page) |
| 238 | { |
| 239 | void *ptr; |
| 240 | if (page == NULL) |
| 241 | return ERR_PTR(-EIO); |
| 242 | ptr = kmap(page); |
| 243 | if (ptr == NULL) |
| 244 | return ERR_PTR(-ENOMEM); |
| 245 | return ptr; |
| 246 | } |
| 247 | |
| 248 | static |
| 249 | void nfs_readdir_release_array(struct page *page) |
| 250 | { |
| 251 | kunmap(page); |
| 252 | } |
| 253 | |
| 254 | /* |
| 255 | * we are freeing strings created by nfs_add_to_readdir_array() |
| 256 | */ |
| 257 | static |
| 258 | void nfs_readdir_clear_array(struct page *page) |
| 259 | { |
| 260 | struct nfs_cache_array *array; |
| 261 | int i; |
| 262 | |
| 263 | array = kmap_atomic(page); |
| 264 | for (i = 0; i < array->size; i++) |
| 265 | kfree(array->array[i].string.name); |
| 266 | kunmap_atomic(array); |
| 267 | } |
| 268 | |
| 269 | /* |
| 270 | * the caller is responsible for freeing qstr.name |
| 271 | * when called by nfs_readdir_add_to_array, the strings will be freed in |
| 272 | * nfs_clear_readdir_array() |
| 273 | */ |
| 274 | static |
| 275 | int nfs_readdir_make_qstr(struct qstr *string, const char *name, unsigned int len) |
| 276 | { |
| 277 | string->len = len; |
| 278 | string->name = kmemdup(name, len, GFP_KERNEL); |
| 279 | if (string->name == NULL) |
| 280 | return -ENOMEM; |
| 281 | /* |
| 282 | * Avoid a kmemleak false positive. The pointer to the name is stored |
| 283 | * in a page cache page which kmemleak does not scan. |
| 284 | */ |
| 285 | kmemleak_not_leak(string->name); |
| 286 | string->hash = full_name_hash(name, len); |
| 287 | return 0; |
| 288 | } |
| 289 | |
| 290 | static |
| 291 | int nfs_readdir_add_to_array(struct nfs_entry *entry, struct page *page) |
| 292 | { |
| 293 | struct nfs_cache_array *array = nfs_readdir_get_array(page); |
| 294 | struct nfs_cache_array_entry *cache_entry; |
| 295 | int ret; |
| 296 | |
| 297 | if (IS_ERR(array)) |
| 298 | return PTR_ERR(array); |
| 299 | |
| 300 | cache_entry = &array->array[array->size]; |
| 301 | |
| 302 | /* Check that this entry lies within the page bounds */ |
| 303 | ret = -ENOSPC; |
| 304 | if ((char *)&cache_entry[1] - (char *)page_address(page) > PAGE_SIZE) |
| 305 | goto out; |
| 306 | |
| 307 | cache_entry->cookie = entry->prev_cookie; |
| 308 | cache_entry->ino = entry->ino; |
| 309 | cache_entry->d_type = entry->d_type; |
| 310 | ret = nfs_readdir_make_qstr(&cache_entry->string, entry->name, entry->len); |
| 311 | if (ret) |
| 312 | goto out; |
| 313 | array->last_cookie = entry->cookie; |
| 314 | array->size++; |
| 315 | if (entry->eof != 0) |
| 316 | array->eof_index = array->size; |
| 317 | out: |
| 318 | nfs_readdir_release_array(page); |
| 319 | return ret; |
| 320 | } |
| 321 | |
| 322 | static |
| 323 | int nfs_readdir_search_for_pos(struct nfs_cache_array *array, nfs_readdir_descriptor_t *desc) |
| 324 | { |
| 325 | loff_t diff = desc->file->f_pos - desc->current_index; |
| 326 | unsigned int index; |
| 327 | |
| 328 | if (diff < 0) |
| 329 | goto out_eof; |
| 330 | if (diff >= array->size) { |
| 331 | if (array->eof_index >= 0) |
| 332 | goto out_eof; |
| 333 | return -EAGAIN; |
| 334 | } |
| 335 | |
| 336 | index = (unsigned int)diff; |
| 337 | *desc->dir_cookie = array->array[index].cookie; |
| 338 | desc->cache_entry_index = index; |
| 339 | return 0; |
| 340 | out_eof: |
| 341 | desc->eof = 1; |
| 342 | return -EBADCOOKIE; |
| 343 | } |
| 344 | |
| 345 | static |
| 346 | int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_descriptor_t *desc) |
| 347 | { |
| 348 | int i; |
| 349 | loff_t new_pos; |
| 350 | int status = -EAGAIN; |
| 351 | |
| 352 | for (i = 0; i < array->size; i++) { |
| 353 | if (array->array[i].cookie == *desc->dir_cookie) { |
| 354 | struct nfs_inode *nfsi = NFS_I(desc->file->f_path.dentry->d_inode); |
| 355 | struct nfs_open_dir_context *ctx = desc->file->private_data; |
| 356 | |
| 357 | new_pos = desc->current_index + i; |
| 358 | if (ctx->attr_gencount != nfsi->attr_gencount |
| 359 | || (nfsi->cache_validity & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA))) { |
| 360 | ctx->duped = 0; |
| 361 | ctx->attr_gencount = nfsi->attr_gencount; |
| 362 | } else if (new_pos < desc->file->f_pos) { |
| 363 | if (ctx->duped > 0 |
| 364 | && ctx->dup_cookie == *desc->dir_cookie) { |
| 365 | if (printk_ratelimit()) { |
| 366 | pr_notice("NFS: directory %s/%s contains a readdir loop." |
| 367 | "Please contact your server vendor. " |
| 368 | "The file: %s has duplicate cookie %llu\n", |
| 369 | desc->file->f_dentry->d_parent->d_name.name, |
| 370 | desc->file->f_dentry->d_name.name, |
| 371 | array->array[i].string.name, |
| 372 | *desc->dir_cookie); |
| 373 | } |
| 374 | status = -ELOOP; |
| 375 | goto out; |
| 376 | } |
| 377 | ctx->dup_cookie = *desc->dir_cookie; |
| 378 | ctx->duped = -1; |
| 379 | } |
| 380 | desc->file->f_pos = new_pos; |
| 381 | desc->cache_entry_index = i; |
| 382 | return 0; |
| 383 | } |
| 384 | } |
| 385 | if (array->eof_index >= 0) { |
| 386 | status = -EBADCOOKIE; |
| 387 | if (*desc->dir_cookie == array->last_cookie) |
| 388 | desc->eof = 1; |
| 389 | } |
| 390 | out: |
| 391 | return status; |
| 392 | } |
| 393 | |
| 394 | static |
| 395 | int nfs_readdir_search_array(nfs_readdir_descriptor_t *desc) |
| 396 | { |
| 397 | struct nfs_cache_array *array; |
| 398 | int status; |
| 399 | |
| 400 | array = nfs_readdir_get_array(desc->page); |
| 401 | if (IS_ERR(array)) { |
| 402 | status = PTR_ERR(array); |
| 403 | goto out; |
| 404 | } |
| 405 | |
| 406 | if (*desc->dir_cookie == 0) |
| 407 | status = nfs_readdir_search_for_pos(array, desc); |
| 408 | else |
| 409 | status = nfs_readdir_search_for_cookie(array, desc); |
| 410 | |
| 411 | if (status == -EAGAIN) { |
| 412 | desc->last_cookie = array->last_cookie; |
| 413 | desc->current_index += array->size; |
| 414 | desc->page_index++; |
| 415 | } |
| 416 | nfs_readdir_release_array(desc->page); |
| 417 | out: |
| 418 | return status; |
| 419 | } |
| 420 | |
| 421 | /* Fill a page with xdr information before transferring to the cache page */ |
| 422 | static |
| 423 | int nfs_readdir_xdr_filler(struct page **pages, nfs_readdir_descriptor_t *desc, |
| 424 | struct nfs_entry *entry, struct file *file, struct inode *inode) |
| 425 | { |
| 426 | struct nfs_open_dir_context *ctx = file->private_data; |
| 427 | struct rpc_cred *cred = ctx->cred; |
| 428 | unsigned long timestamp, gencount; |
| 429 | int error; |
| 430 | |
| 431 | again: |
| 432 | timestamp = jiffies; |
| 433 | gencount = nfs_inc_attr_generation_counter(); |
| 434 | error = NFS_PROTO(inode)->readdir(file->f_path.dentry, cred, entry->cookie, pages, |
| 435 | NFS_SERVER(inode)->dtsize, desc->plus); |
| 436 | if (error < 0) { |
| 437 | /* We requested READDIRPLUS, but the server doesn't grok it */ |
| 438 | if (error == -ENOTSUPP && desc->plus) { |
| 439 | NFS_SERVER(inode)->caps &= ~NFS_CAP_READDIRPLUS; |
| 440 | clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags); |
| 441 | desc->plus = 0; |
| 442 | goto again; |
| 443 | } |
| 444 | goto error; |
| 445 | } |
| 446 | desc->timestamp = timestamp; |
| 447 | desc->gencount = gencount; |
| 448 | error: |
| 449 | return error; |
| 450 | } |
| 451 | |
| 452 | static int xdr_decode(nfs_readdir_descriptor_t *desc, |
| 453 | struct nfs_entry *entry, struct xdr_stream *xdr) |
| 454 | { |
| 455 | int error; |
| 456 | |
| 457 | error = desc->decode(xdr, entry, desc->plus); |
| 458 | if (error) |
| 459 | return error; |
| 460 | entry->fattr->time_start = desc->timestamp; |
| 461 | entry->fattr->gencount = desc->gencount; |
| 462 | return 0; |
| 463 | } |
| 464 | |
| 465 | static |
| 466 | int nfs_same_file(struct dentry *dentry, struct nfs_entry *entry) |
| 467 | { |
| 468 | if (dentry->d_inode == NULL) |
| 469 | goto different; |
| 470 | if (nfs_compare_fh(entry->fh, NFS_FH(dentry->d_inode)) != 0) |
| 471 | goto different; |
| 472 | return 1; |
| 473 | different: |
| 474 | return 0; |
| 475 | } |
| 476 | |
| 477 | static |
| 478 | void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry) |
| 479 | { |
| 480 | struct qstr filename = { |
| 481 | .len = entry->len, |
| 482 | .name = entry->name, |
| 483 | }; |
| 484 | struct dentry *dentry; |
| 485 | struct dentry *alias; |
| 486 | struct inode *dir = parent->d_inode; |
| 487 | struct inode *inode; |
| 488 | |
| 489 | if (filename.name[0] == '.') { |
| 490 | if (filename.len == 1) |
| 491 | return; |
| 492 | if (filename.len == 2 && filename.name[1] == '.') |
| 493 | return; |
| 494 | } |
| 495 | filename.hash = full_name_hash(filename.name, filename.len); |
| 496 | |
| 497 | dentry = d_lookup(parent, &filename); |
| 498 | if (dentry != NULL) { |
| 499 | if (nfs_same_file(dentry, entry)) { |
| 500 | nfs_refresh_inode(dentry->d_inode, entry->fattr); |
| 501 | goto out; |
| 502 | } else { |
| 503 | d_drop(dentry); |
| 504 | dput(dentry); |
| 505 | } |
| 506 | } |
| 507 | |
| 508 | dentry = d_alloc(parent, &filename); |
| 509 | if (dentry == NULL) |
| 510 | return; |
| 511 | |
| 512 | inode = nfs_fhget(dentry->d_sb, entry->fh, entry->fattr); |
| 513 | if (IS_ERR(inode)) |
| 514 | goto out; |
| 515 | |
| 516 | alias = d_materialise_unique(dentry, inode); |
| 517 | if (IS_ERR(alias)) |
| 518 | goto out; |
| 519 | else if (alias) { |
| 520 | nfs_set_verifier(alias, nfs_save_change_attribute(dir)); |
| 521 | dput(alias); |
| 522 | } else |
| 523 | nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); |
| 524 | |
| 525 | out: |
| 526 | dput(dentry); |
| 527 | } |
| 528 | |
| 529 | /* Perform conversion from xdr to cache array */ |
| 530 | static |
| 531 | int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *entry, |
| 532 | struct page **xdr_pages, struct page *page, unsigned int buflen) |
| 533 | { |
| 534 | struct xdr_stream stream; |
| 535 | struct xdr_buf buf; |
| 536 | struct page *scratch; |
| 537 | struct nfs_cache_array *array; |
| 538 | unsigned int count = 0; |
| 539 | int status; |
| 540 | |
| 541 | scratch = alloc_page(GFP_KERNEL); |
| 542 | if (scratch == NULL) |
| 543 | return -ENOMEM; |
| 544 | |
| 545 | xdr_init_decode_pages(&stream, &buf, xdr_pages, buflen); |
| 546 | xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE); |
| 547 | |
| 548 | do { |
| 549 | status = xdr_decode(desc, entry, &stream); |
| 550 | if (status != 0) { |
| 551 | if (status == -EAGAIN) |
| 552 | status = 0; |
| 553 | break; |
| 554 | } |
| 555 | |
| 556 | count++; |
| 557 | |
| 558 | if (desc->plus != 0) |
| 559 | nfs_prime_dcache(desc->file->f_path.dentry, entry); |
| 560 | |
| 561 | status = nfs_readdir_add_to_array(entry, page); |
| 562 | if (status != 0) |
| 563 | break; |
| 564 | } while (!entry->eof); |
| 565 | |
| 566 | if (count == 0 || (status == -EBADCOOKIE && entry->eof != 0)) { |
| 567 | array = nfs_readdir_get_array(page); |
| 568 | if (!IS_ERR(array)) { |
| 569 | array->eof_index = array->size; |
| 570 | status = 0; |
| 571 | nfs_readdir_release_array(page); |
| 572 | } else |
| 573 | status = PTR_ERR(array); |
| 574 | } |
| 575 | |
| 576 | put_page(scratch); |
| 577 | return status; |
| 578 | } |
| 579 | |
| 580 | static |
| 581 | void nfs_readdir_free_pagearray(struct page **pages, unsigned int npages) |
| 582 | { |
| 583 | unsigned int i; |
| 584 | for (i = 0; i < npages; i++) |
| 585 | put_page(pages[i]); |
| 586 | } |
| 587 | |
| 588 | static |
| 589 | void nfs_readdir_free_large_page(void *ptr, struct page **pages, |
| 590 | unsigned int npages) |
| 591 | { |
| 592 | nfs_readdir_free_pagearray(pages, npages); |
| 593 | } |
| 594 | |
| 595 | /* |
| 596 | * nfs_readdir_large_page will allocate pages that must be freed with a call |
| 597 | * to nfs_readdir_free_large_page |
| 598 | */ |
| 599 | static |
| 600 | int nfs_readdir_large_page(struct page **pages, unsigned int npages) |
| 601 | { |
| 602 | unsigned int i; |
| 603 | |
| 604 | for (i = 0; i < npages; i++) { |
| 605 | struct page *page = alloc_page(GFP_KERNEL); |
| 606 | if (page == NULL) |
| 607 | goto out_freepages; |
| 608 | pages[i] = page; |
| 609 | } |
| 610 | return 0; |
| 611 | |
| 612 | out_freepages: |
| 613 | nfs_readdir_free_pagearray(pages, i); |
| 614 | return -ENOMEM; |
| 615 | } |
| 616 | |
| 617 | static |
| 618 | int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page, struct inode *inode) |
| 619 | { |
| 620 | struct page *pages[NFS_MAX_READDIR_PAGES]; |
| 621 | void *pages_ptr = NULL; |
| 622 | struct nfs_entry entry; |
| 623 | struct file *file = desc->file; |
| 624 | struct nfs_cache_array *array; |
| 625 | int status = -ENOMEM; |
| 626 | unsigned int array_size = ARRAY_SIZE(pages); |
| 627 | |
| 628 | entry.prev_cookie = 0; |
| 629 | entry.cookie = desc->last_cookie; |
| 630 | entry.eof = 0; |
| 631 | entry.fh = nfs_alloc_fhandle(); |
| 632 | entry.fattr = nfs_alloc_fattr(); |
| 633 | entry.server = NFS_SERVER(inode); |
| 634 | if (entry.fh == NULL || entry.fattr == NULL) |
| 635 | goto out; |
| 636 | |
| 637 | array = nfs_readdir_get_array(page); |
| 638 | if (IS_ERR(array)) { |
| 639 | status = PTR_ERR(array); |
| 640 | goto out; |
| 641 | } |
| 642 | memset(array, 0, sizeof(struct nfs_cache_array)); |
| 643 | array->eof_index = -1; |
| 644 | |
| 645 | status = nfs_readdir_large_page(pages, array_size); |
| 646 | if (status < 0) |
| 647 | goto out_release_array; |
| 648 | do { |
| 649 | unsigned int pglen; |
| 650 | status = nfs_readdir_xdr_filler(pages, desc, &entry, file, inode); |
| 651 | |
| 652 | if (status < 0) |
| 653 | break; |
| 654 | pglen = status; |
| 655 | status = nfs_readdir_page_filler(desc, &entry, pages, page, pglen); |
| 656 | if (status < 0) { |
| 657 | if (status == -ENOSPC) |
| 658 | status = 0; |
| 659 | break; |
| 660 | } |
| 661 | } while (array->eof_index < 0); |
| 662 | |
| 663 | nfs_readdir_free_large_page(pages_ptr, pages, array_size); |
| 664 | out_release_array: |
| 665 | nfs_readdir_release_array(page); |
| 666 | out: |
| 667 | nfs_free_fattr(entry.fattr); |
| 668 | nfs_free_fhandle(entry.fh); |
| 669 | return status; |
| 670 | } |
| 671 | |
| 672 | /* |
| 673 | * Now we cache directories properly, by converting xdr information |
| 674 | * to an array that can be used for lookups later. This results in |
| 675 | * fewer cache pages, since we can store more information on each page. |
| 676 | * We only need to convert from xdr once so future lookups are much simpler |
| 677 | */ |
| 678 | static |
| 679 | int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page* page) |
| 680 | { |
| 681 | struct inode *inode = desc->file->f_path.dentry->d_inode; |
| 682 | int ret; |
| 683 | |
| 684 | ret = nfs_readdir_xdr_to_array(desc, page, inode); |
| 685 | if (ret < 0) |
| 686 | goto error; |
| 687 | SetPageUptodate(page); |
| 688 | |
| 689 | if (invalidate_inode_pages2_range(inode->i_mapping, page->index + 1, -1) < 0) { |
| 690 | /* Should never happen */ |
| 691 | nfs_zap_mapping(inode, inode->i_mapping); |
| 692 | } |
| 693 | unlock_page(page); |
| 694 | return 0; |
| 695 | error: |
| 696 | unlock_page(page); |
| 697 | return ret; |
| 698 | } |
| 699 | |
| 700 | static |
| 701 | void cache_page_release(nfs_readdir_descriptor_t *desc) |
| 702 | { |
| 703 | if (!desc->page->mapping) |
| 704 | nfs_readdir_clear_array(desc->page); |
| 705 | page_cache_release(desc->page); |
| 706 | desc->page = NULL; |
| 707 | } |
| 708 | |
| 709 | static |
| 710 | struct page *get_cache_page(nfs_readdir_descriptor_t *desc) |
| 711 | { |
| 712 | return read_cache_page(desc->file->f_path.dentry->d_inode->i_mapping, |
| 713 | desc->page_index, (filler_t *)nfs_readdir_filler, desc); |
| 714 | } |
| 715 | |
| 716 | /* |
| 717 | * Returns 0 if desc->dir_cookie was found on page desc->page_index |
| 718 | */ |
| 719 | static |
| 720 | int find_cache_page(nfs_readdir_descriptor_t *desc) |
| 721 | { |
| 722 | int res; |
| 723 | |
| 724 | desc->page = get_cache_page(desc); |
| 725 | if (IS_ERR(desc->page)) |
| 726 | return PTR_ERR(desc->page); |
| 727 | |
| 728 | res = nfs_readdir_search_array(desc); |
| 729 | if (res != 0) |
| 730 | cache_page_release(desc); |
| 731 | return res; |
| 732 | } |
| 733 | |
| 734 | /* Search for desc->dir_cookie from the beginning of the page cache */ |
| 735 | static inline |
| 736 | int readdir_search_pagecache(nfs_readdir_descriptor_t *desc) |
| 737 | { |
| 738 | int res; |
| 739 | |
| 740 | if (desc->page_index == 0) { |
| 741 | desc->current_index = 0; |
| 742 | desc->last_cookie = 0; |
| 743 | } |
| 744 | do { |
| 745 | res = find_cache_page(desc); |
| 746 | } while (res == -EAGAIN); |
| 747 | return res; |
| 748 | } |
| 749 | |
| 750 | /* |
| 751 | * Once we've found the start of the dirent within a page: fill 'er up... |
| 752 | */ |
| 753 | static |
| 754 | int nfs_do_filldir(nfs_readdir_descriptor_t *desc, void *dirent, |
| 755 | filldir_t filldir) |
| 756 | { |
| 757 | struct file *file = desc->file; |
| 758 | int i = 0; |
| 759 | int res = 0; |
| 760 | struct nfs_cache_array *array = NULL; |
| 761 | struct nfs_open_dir_context *ctx = file->private_data; |
| 762 | |
| 763 | array = nfs_readdir_get_array(desc->page); |
| 764 | if (IS_ERR(array)) { |
| 765 | res = PTR_ERR(array); |
| 766 | goto out; |
| 767 | } |
| 768 | |
| 769 | for (i = desc->cache_entry_index; i < array->size; i++) { |
| 770 | struct nfs_cache_array_entry *ent; |
| 771 | |
| 772 | ent = &array->array[i]; |
| 773 | if (filldir(dirent, ent->string.name, ent->string.len, |
| 774 | file->f_pos, nfs_compat_user_ino64(ent->ino), |
| 775 | ent->d_type) < 0) { |
| 776 | desc->eof = 1; |
| 777 | break; |
| 778 | } |
| 779 | file->f_pos++; |
| 780 | if (i < (array->size-1)) |
| 781 | *desc->dir_cookie = array->array[i+1].cookie; |
| 782 | else |
| 783 | *desc->dir_cookie = array->last_cookie; |
| 784 | if (ctx->duped != 0) |
| 785 | ctx->duped = 1; |
| 786 | } |
| 787 | if (array->eof_index >= 0) |
| 788 | desc->eof = 1; |
| 789 | |
| 790 | nfs_readdir_release_array(desc->page); |
| 791 | out: |
| 792 | cache_page_release(desc); |
| 793 | dfprintk(DIRCACHE, "NFS: nfs_do_filldir() filling ended @ cookie %Lu; returning = %d\n", |
| 794 | (unsigned long long)*desc->dir_cookie, res); |
| 795 | return res; |
| 796 | } |
| 797 | |
| 798 | /* |
| 799 | * If we cannot find a cookie in our cache, we suspect that this is |
| 800 | * because it points to a deleted file, so we ask the server to return |
| 801 | * whatever it thinks is the next entry. We then feed this to filldir. |
| 802 | * If all goes well, we should then be able to find our way round the |
| 803 | * cache on the next call to readdir_search_pagecache(); |
| 804 | * |
| 805 | * NOTE: we cannot add the anonymous page to the pagecache because |
| 806 | * the data it contains might not be page aligned. Besides, |
| 807 | * we should already have a complete representation of the |
| 808 | * directory in the page cache by the time we get here. |
| 809 | */ |
| 810 | static inline |
| 811 | int uncached_readdir(nfs_readdir_descriptor_t *desc, void *dirent, |
| 812 | filldir_t filldir) |
| 813 | { |
| 814 | struct page *page = NULL; |
| 815 | int status; |
| 816 | struct inode *inode = desc->file->f_path.dentry->d_inode; |
| 817 | struct nfs_open_dir_context *ctx = desc->file->private_data; |
| 818 | |
| 819 | dfprintk(DIRCACHE, "NFS: uncached_readdir() searching for cookie %Lu\n", |
| 820 | (unsigned long long)*desc->dir_cookie); |
| 821 | |
| 822 | page = alloc_page(GFP_HIGHUSER); |
| 823 | if (!page) { |
| 824 | status = -ENOMEM; |
| 825 | goto out; |
| 826 | } |
| 827 | |
| 828 | desc->page_index = 0; |
| 829 | desc->last_cookie = *desc->dir_cookie; |
| 830 | desc->page = page; |
| 831 | ctx->duped = 0; |
| 832 | |
| 833 | status = nfs_readdir_xdr_to_array(desc, page, inode); |
| 834 | if (status < 0) |
| 835 | goto out_release; |
| 836 | |
| 837 | status = nfs_do_filldir(desc, dirent, filldir); |
| 838 | |
| 839 | out: |
| 840 | dfprintk(DIRCACHE, "NFS: %s: returns %d\n", |
| 841 | __func__, status); |
| 842 | return status; |
| 843 | out_release: |
| 844 | cache_page_release(desc); |
| 845 | goto out; |
| 846 | } |
| 847 | |
| 848 | /* The file offset position represents the dirent entry number. A |
| 849 | last cookie cache takes care of the common case of reading the |
| 850 | whole directory. |
| 851 | */ |
| 852 | static int nfs_readdir(struct file *filp, void *dirent, filldir_t filldir) |
| 853 | { |
| 854 | struct dentry *dentry = filp->f_path.dentry; |
| 855 | struct inode *inode = dentry->d_inode; |
| 856 | nfs_readdir_descriptor_t my_desc, |
| 857 | *desc = &my_desc; |
| 858 | struct nfs_open_dir_context *dir_ctx = filp->private_data; |
| 859 | int res; |
| 860 | |
| 861 | dfprintk(FILE, "NFS: readdir(%s/%s) starting at cookie %llu\n", |
| 862 | dentry->d_parent->d_name.name, dentry->d_name.name, |
| 863 | (long long)filp->f_pos); |
| 864 | nfs_inc_stats(inode, NFSIOS_VFSGETDENTS); |
| 865 | |
| 866 | /* |
| 867 | * filp->f_pos points to the dirent entry number. |
| 868 | * *desc->dir_cookie has the cookie for the next entry. We have |
| 869 | * to either find the entry with the appropriate number or |
| 870 | * revalidate the cookie. |
| 871 | */ |
| 872 | memset(desc, 0, sizeof(*desc)); |
| 873 | |
| 874 | desc->file = filp; |
| 875 | desc->dir_cookie = &dir_ctx->dir_cookie; |
| 876 | desc->decode = NFS_PROTO(inode)->decode_dirent; |
| 877 | desc->plus = NFS_USE_READDIRPLUS(inode); |
| 878 | |
| 879 | nfs_block_sillyrename(dentry); |
| 880 | res = nfs_revalidate_mapping(inode, filp->f_mapping); |
| 881 | if (res < 0) |
| 882 | goto out; |
| 883 | |
| 884 | do { |
| 885 | res = readdir_search_pagecache(desc); |
| 886 | |
| 887 | if (res == -EBADCOOKIE) { |
| 888 | res = 0; |
| 889 | /* This means either end of directory */ |
| 890 | if (*desc->dir_cookie && desc->eof == 0) { |
| 891 | /* Or that the server has 'lost' a cookie */ |
| 892 | res = uncached_readdir(desc, dirent, filldir); |
| 893 | if (res == 0) |
| 894 | continue; |
| 895 | } |
| 896 | break; |
| 897 | } |
| 898 | if (res == -ETOOSMALL && desc->plus) { |
| 899 | clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags); |
| 900 | nfs_zap_caches(inode); |
| 901 | desc->page_index = 0; |
| 902 | desc->plus = 0; |
| 903 | desc->eof = 0; |
| 904 | continue; |
| 905 | } |
| 906 | if (res < 0) |
| 907 | break; |
| 908 | |
| 909 | res = nfs_do_filldir(desc, dirent, filldir); |
| 910 | if (res < 0) |
| 911 | break; |
| 912 | } while (!desc->eof); |
| 913 | out: |
| 914 | nfs_unblock_sillyrename(dentry); |
| 915 | if (res > 0) |
| 916 | res = 0; |
| 917 | dfprintk(FILE, "NFS: readdir(%s/%s) returns %d\n", |
| 918 | dentry->d_parent->d_name.name, dentry->d_name.name, |
| 919 | res); |
| 920 | return res; |
| 921 | } |
| 922 | |
| 923 | static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int origin) |
| 924 | { |
| 925 | struct dentry *dentry = filp->f_path.dentry; |
| 926 | struct inode *inode = dentry->d_inode; |
| 927 | struct nfs_open_dir_context *dir_ctx = filp->private_data; |
| 928 | |
| 929 | dfprintk(FILE, "NFS: llseek dir(%s/%s, %lld, %d)\n", |
| 930 | dentry->d_parent->d_name.name, |
| 931 | dentry->d_name.name, |
| 932 | offset, origin); |
| 933 | |
| 934 | mutex_lock(&inode->i_mutex); |
| 935 | switch (origin) { |
| 936 | case 1: |
| 937 | offset += filp->f_pos; |
| 938 | case 0: |
| 939 | if (offset >= 0) |
| 940 | break; |
| 941 | default: |
| 942 | offset = -EINVAL; |
| 943 | goto out; |
| 944 | } |
| 945 | if (offset != filp->f_pos) { |
| 946 | filp->f_pos = offset; |
| 947 | dir_ctx->dir_cookie = 0; |
| 948 | dir_ctx->duped = 0; |
| 949 | } |
| 950 | out: |
| 951 | mutex_unlock(&inode->i_mutex); |
| 952 | return offset; |
| 953 | } |
| 954 | |
| 955 | /* |
| 956 | * All directory operations under NFS are synchronous, so fsync() |
| 957 | * is a dummy operation. |
| 958 | */ |
| 959 | static int nfs_fsync_dir(struct file *filp, loff_t start, loff_t end, |
| 960 | int datasync) |
| 961 | { |
| 962 | struct dentry *dentry = filp->f_path.dentry; |
| 963 | struct inode *inode = dentry->d_inode; |
| 964 | |
| 965 | dfprintk(FILE, "NFS: fsync dir(%s/%s) datasync %d\n", |
| 966 | dentry->d_parent->d_name.name, dentry->d_name.name, |
| 967 | datasync); |
| 968 | |
| 969 | mutex_lock(&inode->i_mutex); |
| 970 | nfs_inc_stats(dentry->d_inode, NFSIOS_VFSFSYNC); |
| 971 | mutex_unlock(&inode->i_mutex); |
| 972 | return 0; |
| 973 | } |
| 974 | |
| 975 | /** |
| 976 | * nfs_force_lookup_revalidate - Mark the directory as having changed |
| 977 | * @dir - pointer to directory inode |
| 978 | * |
| 979 | * This forces the revalidation code in nfs_lookup_revalidate() to do a |
| 980 | * full lookup on all child dentries of 'dir' whenever a change occurs |
| 981 | * on the server that might have invalidated our dcache. |
| 982 | * |
| 983 | * The caller should be holding dir->i_lock |
| 984 | */ |
| 985 | void nfs_force_lookup_revalidate(struct inode *dir) |
| 986 | { |
| 987 | NFS_I(dir)->cache_change_attribute++; |
| 988 | } |
| 989 | |
| 990 | /* |
| 991 | * A check for whether or not the parent directory has changed. |
| 992 | * In the case it has, we assume that the dentries are untrustworthy |
| 993 | * and may need to be looked up again. |
| 994 | */ |
| 995 | static int nfs_check_verifier(struct inode *dir, struct dentry *dentry) |
| 996 | { |
| 997 | if (IS_ROOT(dentry)) |
| 998 | return 1; |
| 999 | if (NFS_SERVER(dir)->flags & NFS_MOUNT_LOOKUP_CACHE_NONE) |
| 1000 | return 0; |
| 1001 | if (!nfs_verify_change_attribute(dir, dentry->d_time)) |
| 1002 | return 0; |
| 1003 | /* Revalidate nfsi->cache_change_attribute before we declare a match */ |
| 1004 | if (nfs_revalidate_inode(NFS_SERVER(dir), dir) < 0) |
| 1005 | return 0; |
| 1006 | if (!nfs_verify_change_attribute(dir, dentry->d_time)) |
| 1007 | return 0; |
| 1008 | return 1; |
| 1009 | } |
| 1010 | |
| 1011 | /* |
| 1012 | * Return the intent data that applies to this particular path component |
| 1013 | * |
| 1014 | * Note that the current set of intents only apply to the very last |
| 1015 | * component of the path and none of them is set before that last |
| 1016 | * component. |
| 1017 | */ |
| 1018 | static inline unsigned int nfs_lookup_check_intent(struct nameidata *nd, |
| 1019 | unsigned int mask) |
| 1020 | { |
| 1021 | return nd->flags & mask; |
| 1022 | } |
| 1023 | |
| 1024 | /* |
| 1025 | * Use intent information to check whether or not we're going to do |
| 1026 | * an O_EXCL create using this path component. |
| 1027 | */ |
| 1028 | static int nfs_is_exclusive_create(struct inode *dir, struct nameidata *nd) |
| 1029 | { |
| 1030 | if (NFS_PROTO(dir)->version == 2) |
| 1031 | return 0; |
| 1032 | return nd && nfs_lookup_check_intent(nd, LOOKUP_EXCL); |
| 1033 | } |
| 1034 | |
| 1035 | /* |
| 1036 | * Inode and filehandle revalidation for lookups. |
| 1037 | * |
| 1038 | * We force revalidation in the cases where the VFS sets LOOKUP_REVAL, |
| 1039 | * or if the intent information indicates that we're about to open this |
| 1040 | * particular file and the "nocto" mount flag is not set. |
| 1041 | * |
| 1042 | */ |
| 1043 | static inline |
| 1044 | int nfs_lookup_verify_inode(struct inode *inode, struct nameidata *nd) |
| 1045 | { |
| 1046 | struct nfs_server *server = NFS_SERVER(inode); |
| 1047 | |
| 1048 | if (IS_AUTOMOUNT(inode)) |
| 1049 | return 0; |
| 1050 | if (nd != NULL) { |
| 1051 | /* VFS wants an on-the-wire revalidation */ |
| 1052 | if (nd->flags & LOOKUP_REVAL) |
| 1053 | goto out_force; |
| 1054 | /* This is an open(2) */ |
| 1055 | if (nfs_lookup_check_intent(nd, LOOKUP_OPEN) != 0 && |
| 1056 | !(server->flags & NFS_MOUNT_NOCTO) && |
| 1057 | (S_ISREG(inode->i_mode) || |
| 1058 | S_ISDIR(inode->i_mode))) |
| 1059 | goto out_force; |
| 1060 | return 0; |
| 1061 | } |
| 1062 | return nfs_revalidate_inode(server, inode); |
| 1063 | out_force: |
| 1064 | return __nfs_revalidate_inode(server, inode); |
| 1065 | } |
| 1066 | |
| 1067 | /* |
| 1068 | * We judge how long we want to trust negative |
| 1069 | * dentries by looking at the parent inode mtime. |
| 1070 | * |
| 1071 | * If parent mtime has changed, we revalidate, else we wait for a |
| 1072 | * period corresponding to the parent's attribute cache timeout value. |
| 1073 | */ |
| 1074 | static inline |
| 1075 | int nfs_neg_need_reval(struct inode *dir, struct dentry *dentry, |
| 1076 | struct nameidata *nd) |
| 1077 | { |
| 1078 | /* Don't revalidate a negative dentry if we're creating a new file */ |
| 1079 | if (nd != NULL && nfs_lookup_check_intent(nd, LOOKUP_CREATE) != 0) |
| 1080 | return 0; |
| 1081 | if (NFS_SERVER(dir)->flags & NFS_MOUNT_LOOKUP_CACHE_NONEG) |
| 1082 | return 1; |
| 1083 | return !nfs_check_verifier(dir, dentry); |
| 1084 | } |
| 1085 | |
| 1086 | /* |
| 1087 | * This is called every time the dcache has a lookup hit, |
| 1088 | * and we should check whether we can really trust that |
| 1089 | * lookup. |
| 1090 | * |
| 1091 | * NOTE! The hit can be a negative hit too, don't assume |
| 1092 | * we have an inode! |
| 1093 | * |
| 1094 | * If the parent directory is seen to have changed, we throw out the |
| 1095 | * cached dentry and do a new lookup. |
| 1096 | */ |
| 1097 | static int nfs_lookup_revalidate(struct dentry *dentry, struct nameidata *nd) |
| 1098 | { |
| 1099 | struct inode *dir; |
| 1100 | struct inode *inode; |
| 1101 | struct dentry *parent; |
| 1102 | struct nfs_fh *fhandle = NULL; |
| 1103 | struct nfs_fattr *fattr = NULL; |
| 1104 | int error; |
| 1105 | |
| 1106 | if (nd && (nd->flags & LOOKUP_RCU)) |
| 1107 | return -ECHILD; |
| 1108 | |
| 1109 | parent = dget_parent(dentry); |
| 1110 | dir = parent->d_inode; |
| 1111 | nfs_inc_stats(dir, NFSIOS_DENTRYREVALIDATE); |
| 1112 | inode = dentry->d_inode; |
| 1113 | |
| 1114 | if (!inode) { |
| 1115 | if (nfs_neg_need_reval(dir, dentry, nd)) |
| 1116 | goto out_bad; |
| 1117 | goto out_valid; |
| 1118 | } |
| 1119 | |
| 1120 | if (is_bad_inode(inode)) { |
| 1121 | dfprintk(LOOKUPCACHE, "%s: %s/%s has dud inode\n", |
| 1122 | __func__, dentry->d_parent->d_name.name, |
| 1123 | dentry->d_name.name); |
| 1124 | goto out_bad; |
| 1125 | } |
| 1126 | |
| 1127 | if (nfs_have_delegation(inode, FMODE_READ)) |
| 1128 | goto out_set_verifier; |
| 1129 | |
| 1130 | /* Force a full look up iff the parent directory has changed */ |
| 1131 | if (!nfs_is_exclusive_create(dir, nd) && nfs_check_verifier(dir, dentry)) { |
| 1132 | if (nfs_lookup_verify_inode(inode, nd)) |
| 1133 | goto out_zap_parent; |
| 1134 | goto out_valid; |
| 1135 | } |
| 1136 | |
| 1137 | if (NFS_STALE(inode)) |
| 1138 | goto out_bad; |
| 1139 | |
| 1140 | error = -ENOMEM; |
| 1141 | fhandle = nfs_alloc_fhandle(); |
| 1142 | fattr = nfs_alloc_fattr(); |
| 1143 | if (fhandle == NULL || fattr == NULL) |
| 1144 | goto out_error; |
| 1145 | |
| 1146 | error = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, &dentry->d_name, fhandle, fattr); |
| 1147 | if (error) |
| 1148 | goto out_bad; |
| 1149 | if (nfs_compare_fh(NFS_FH(inode), fhandle)) |
| 1150 | goto out_bad; |
| 1151 | if ((error = nfs_refresh_inode(inode, fattr)) != 0) |
| 1152 | goto out_bad; |
| 1153 | |
| 1154 | nfs_free_fattr(fattr); |
| 1155 | nfs_free_fhandle(fhandle); |
| 1156 | out_set_verifier: |
| 1157 | nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); |
| 1158 | out_valid: |
| 1159 | dput(parent); |
| 1160 | dfprintk(LOOKUPCACHE, "NFS: %s(%s/%s) is valid\n", |
| 1161 | __func__, dentry->d_parent->d_name.name, |
| 1162 | dentry->d_name.name); |
| 1163 | return 1; |
| 1164 | out_zap_parent: |
| 1165 | nfs_zap_caches(dir); |
| 1166 | out_bad: |
| 1167 | nfs_mark_for_revalidate(dir); |
| 1168 | if (inode && S_ISDIR(inode->i_mode)) { |
| 1169 | /* Purge readdir caches. */ |
| 1170 | nfs_zap_caches(inode); |
| 1171 | /* If we have submounts, don't unhash ! */ |
| 1172 | if (have_submounts(dentry)) |
| 1173 | goto out_valid; |
| 1174 | if (dentry->d_flags & DCACHE_DISCONNECTED) |
| 1175 | goto out_valid; |
| 1176 | shrink_dcache_parent(dentry); |
| 1177 | } |
| 1178 | d_drop(dentry); |
| 1179 | nfs_free_fattr(fattr); |
| 1180 | nfs_free_fhandle(fhandle); |
| 1181 | dput(parent); |
| 1182 | dfprintk(LOOKUPCACHE, "NFS: %s(%s/%s) is invalid\n", |
| 1183 | __func__, dentry->d_parent->d_name.name, |
| 1184 | dentry->d_name.name); |
| 1185 | return 0; |
| 1186 | out_error: |
| 1187 | nfs_free_fattr(fattr); |
| 1188 | nfs_free_fhandle(fhandle); |
| 1189 | dput(parent); |
| 1190 | dfprintk(LOOKUPCACHE, "NFS: %s(%s/%s) lookup returned error %d\n", |
| 1191 | __func__, dentry->d_parent->d_name.name, |
| 1192 | dentry->d_name.name, error); |
| 1193 | return error; |
| 1194 | } |
| 1195 | |
| 1196 | /* |
| 1197 | * This is called from dput() when d_count is going to 0. |
| 1198 | */ |
| 1199 | static int nfs_dentry_delete(const struct dentry *dentry) |
| 1200 | { |
| 1201 | dfprintk(VFS, "NFS: dentry_delete(%s/%s, %x)\n", |
| 1202 | dentry->d_parent->d_name.name, dentry->d_name.name, |
| 1203 | dentry->d_flags); |
| 1204 | |
| 1205 | /* Unhash any dentry with a stale inode */ |
| 1206 | if (dentry->d_inode != NULL && NFS_STALE(dentry->d_inode)) |
| 1207 | return 1; |
| 1208 | |
| 1209 | if (dentry->d_flags & DCACHE_NFSFS_RENAMED) { |
| 1210 | /* Unhash it, so that ->d_iput() would be called */ |
| 1211 | return 1; |
| 1212 | } |
| 1213 | if (!(dentry->d_sb->s_flags & MS_ACTIVE)) { |
| 1214 | /* Unhash it, so that ancestors of killed async unlink |
| 1215 | * files will be cleaned up during umount */ |
| 1216 | return 1; |
| 1217 | } |
| 1218 | return 0; |
| 1219 | |
| 1220 | } |
| 1221 | |
| 1222 | /* Ensure that we revalidate inode->i_nlink */ |
| 1223 | static void nfs_drop_nlink(struct inode *inode) |
| 1224 | { |
| 1225 | spin_lock(&inode->i_lock); |
| 1226 | /* drop the inode if we're reasonably sure this is the last link */ |
| 1227 | if (inode->i_nlink == 1) |
| 1228 | clear_nlink(inode); |
| 1229 | NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ATTR; |
| 1230 | spin_unlock(&inode->i_lock); |
| 1231 | } |
| 1232 | |
| 1233 | /* |
| 1234 | * Called when the dentry loses inode. |
| 1235 | * We use it to clean up silly-renamed files. |
| 1236 | */ |
| 1237 | static void nfs_dentry_iput(struct dentry *dentry, struct inode *inode) |
| 1238 | { |
| 1239 | if (S_ISDIR(inode->i_mode)) |
| 1240 | /* drop any readdir cache as it could easily be old */ |
| 1241 | NFS_I(inode)->cache_validity |= NFS_INO_INVALID_DATA; |
| 1242 | |
| 1243 | if (dentry->d_flags & DCACHE_NFSFS_RENAMED) { |
| 1244 | nfs_complete_unlink(dentry, inode); |
| 1245 | nfs_drop_nlink(inode); |
| 1246 | } |
| 1247 | iput(inode); |
| 1248 | } |
| 1249 | |
| 1250 | static void nfs_d_release(struct dentry *dentry) |
| 1251 | { |
| 1252 | /* free cached devname value, if it survived that far */ |
| 1253 | if (unlikely(dentry->d_fsdata)) { |
| 1254 | if (dentry->d_flags & DCACHE_NFSFS_RENAMED) |
| 1255 | WARN_ON(1); |
| 1256 | else |
| 1257 | kfree(dentry->d_fsdata); |
| 1258 | } |
| 1259 | } |
| 1260 | |
| 1261 | const struct dentry_operations nfs_dentry_operations = { |
| 1262 | .d_revalidate = nfs_lookup_revalidate, |
| 1263 | .d_delete = nfs_dentry_delete, |
| 1264 | .d_iput = nfs_dentry_iput, |
| 1265 | .d_automount = nfs_d_automount, |
| 1266 | .d_release = nfs_d_release, |
| 1267 | }; |
| 1268 | |
| 1269 | static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd) |
| 1270 | { |
| 1271 | struct dentry *res; |
| 1272 | struct dentry *parent; |
| 1273 | struct inode *inode = NULL; |
| 1274 | struct nfs_fh *fhandle = NULL; |
| 1275 | struct nfs_fattr *fattr = NULL; |
| 1276 | int error; |
| 1277 | |
| 1278 | dfprintk(VFS, "NFS: lookup(%s/%s)\n", |
| 1279 | dentry->d_parent->d_name.name, dentry->d_name.name); |
| 1280 | nfs_inc_stats(dir, NFSIOS_VFSLOOKUP); |
| 1281 | |
| 1282 | res = ERR_PTR(-ENAMETOOLONG); |
| 1283 | if (dentry->d_name.len > NFS_SERVER(dir)->namelen) |
| 1284 | goto out; |
| 1285 | |
| 1286 | /* |
| 1287 | * If we're doing an exclusive create, optimize away the lookup |
| 1288 | * but don't hash the dentry. |
| 1289 | */ |
| 1290 | if (nfs_is_exclusive_create(dir, nd)) { |
| 1291 | d_instantiate(dentry, NULL); |
| 1292 | res = NULL; |
| 1293 | goto out; |
| 1294 | } |
| 1295 | |
| 1296 | res = ERR_PTR(-ENOMEM); |
| 1297 | fhandle = nfs_alloc_fhandle(); |
| 1298 | fattr = nfs_alloc_fattr(); |
| 1299 | if (fhandle == NULL || fattr == NULL) |
| 1300 | goto out; |
| 1301 | |
| 1302 | parent = dentry->d_parent; |
| 1303 | /* Protect against concurrent sillydeletes */ |
| 1304 | nfs_block_sillyrename(parent); |
| 1305 | error = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, &dentry->d_name, fhandle, fattr); |
| 1306 | if (error == -ENOENT) |
| 1307 | goto no_entry; |
| 1308 | if (error < 0) { |
| 1309 | res = ERR_PTR(error); |
| 1310 | goto out_unblock_sillyrename; |
| 1311 | } |
| 1312 | inode = nfs_fhget(dentry->d_sb, fhandle, fattr); |
| 1313 | res = ERR_CAST(inode); |
| 1314 | if (IS_ERR(res)) |
| 1315 | goto out_unblock_sillyrename; |
| 1316 | |
| 1317 | no_entry: |
| 1318 | res = d_materialise_unique(dentry, inode); |
| 1319 | if (res != NULL) { |
| 1320 | if (IS_ERR(res)) |
| 1321 | goto out_unblock_sillyrename; |
| 1322 | dentry = res; |
| 1323 | } |
| 1324 | nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); |
| 1325 | out_unblock_sillyrename: |
| 1326 | nfs_unblock_sillyrename(parent); |
| 1327 | out: |
| 1328 | nfs_free_fattr(fattr); |
| 1329 | nfs_free_fhandle(fhandle); |
| 1330 | return res; |
| 1331 | } |
| 1332 | |
| 1333 | #ifdef CONFIG_NFS_V4 |
| 1334 | static int nfs_open_revalidate(struct dentry *, struct nameidata *); |
| 1335 | |
| 1336 | const struct dentry_operations nfs4_dentry_operations = { |
| 1337 | .d_revalidate = nfs_open_revalidate, |
| 1338 | .d_delete = nfs_dentry_delete, |
| 1339 | .d_iput = nfs_dentry_iput, |
| 1340 | .d_automount = nfs_d_automount, |
| 1341 | .d_release = nfs_d_release, |
| 1342 | }; |
| 1343 | |
| 1344 | /* |
| 1345 | * Use intent information to determine whether we need to substitute |
| 1346 | * the NFSv4-style stateful OPEN for the LOOKUP call |
| 1347 | */ |
| 1348 | static int is_atomic_open(struct nameidata *nd) |
| 1349 | { |
| 1350 | if (nd == NULL || nfs_lookup_check_intent(nd, LOOKUP_OPEN) == 0) |
| 1351 | return 0; |
| 1352 | /* NFS does not (yet) have a stateful open for directories */ |
| 1353 | if (nd->flags & LOOKUP_DIRECTORY) |
| 1354 | return 0; |
| 1355 | /* Are we trying to write to a read only partition? */ |
| 1356 | if (__mnt_is_readonly(nd->path.mnt) && |
| 1357 | (nd->intent.open.flags & (O_CREAT|O_TRUNC|O_ACCMODE))) |
| 1358 | return 0; |
| 1359 | return 1; |
| 1360 | } |
| 1361 | |
| 1362 | static fmode_t flags_to_mode(int flags) |
| 1363 | { |
| 1364 | fmode_t res = (__force fmode_t)flags & FMODE_EXEC; |
| 1365 | if ((flags & O_ACCMODE) != O_WRONLY) |
| 1366 | res |= FMODE_READ; |
| 1367 | if ((flags & O_ACCMODE) != O_RDONLY) |
| 1368 | res |= FMODE_WRITE; |
| 1369 | return res; |
| 1370 | } |
| 1371 | |
| 1372 | static struct nfs_open_context *create_nfs_open_context(struct dentry *dentry, int open_flags) |
| 1373 | { |
| 1374 | return alloc_nfs_open_context(dentry, flags_to_mode(open_flags)); |
| 1375 | } |
| 1376 | |
| 1377 | static int do_open(struct inode *inode, struct file *filp) |
| 1378 | { |
| 1379 | nfs_fscache_set_inode_cookie(inode, filp); |
| 1380 | return 0; |
| 1381 | } |
| 1382 | |
| 1383 | static int nfs_intent_set_file(struct nameidata *nd, struct nfs_open_context *ctx) |
| 1384 | { |
| 1385 | struct file *filp; |
| 1386 | int ret = 0; |
| 1387 | |
| 1388 | /* If the open_intent is for execute, we have an extra check to make */ |
| 1389 | if (ctx->mode & FMODE_EXEC) { |
| 1390 | ret = nfs_may_open(ctx->dentry->d_inode, |
| 1391 | ctx->cred, |
| 1392 | nd->intent.open.flags); |
| 1393 | if (ret < 0) |
| 1394 | goto out; |
| 1395 | } |
| 1396 | filp = lookup_instantiate_filp(nd, ctx->dentry, do_open); |
| 1397 | if (IS_ERR(filp)) |
| 1398 | ret = PTR_ERR(filp); |
| 1399 | else |
| 1400 | nfs_file_set_open_context(filp, ctx); |
| 1401 | out: |
| 1402 | put_nfs_open_context(ctx); |
| 1403 | return ret; |
| 1404 | } |
| 1405 | |
| 1406 | static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) |
| 1407 | { |
| 1408 | struct nfs_open_context *ctx; |
| 1409 | struct iattr attr; |
| 1410 | struct dentry *res = NULL; |
| 1411 | struct inode *inode; |
| 1412 | int open_flags; |
| 1413 | int err; |
| 1414 | |
| 1415 | dfprintk(VFS, "NFS: atomic_lookup(%s/%ld), %s\n", |
| 1416 | dir->i_sb->s_id, dir->i_ino, dentry->d_name.name); |
| 1417 | |
| 1418 | /* Check that we are indeed trying to open this file */ |
| 1419 | if (!is_atomic_open(nd)) |
| 1420 | goto no_open; |
| 1421 | |
| 1422 | if (dentry->d_name.len > NFS_SERVER(dir)->namelen) { |
| 1423 | res = ERR_PTR(-ENAMETOOLONG); |
| 1424 | goto out; |
| 1425 | } |
| 1426 | |
| 1427 | /* Let vfs_create() deal with O_EXCL. Instantiate, but don't hash |
| 1428 | * the dentry. */ |
| 1429 | if (nd->flags & LOOKUP_EXCL) { |
| 1430 | d_instantiate(dentry, NULL); |
| 1431 | goto out; |
| 1432 | } |
| 1433 | |
| 1434 | open_flags = nd->intent.open.flags; |
| 1435 | attr.ia_valid = ATTR_OPEN; |
| 1436 | |
| 1437 | ctx = create_nfs_open_context(dentry, open_flags); |
| 1438 | res = ERR_CAST(ctx); |
| 1439 | if (IS_ERR(ctx)) |
| 1440 | goto out; |
| 1441 | |
| 1442 | if (nd->flags & LOOKUP_CREATE) { |
| 1443 | attr.ia_mode = nd->intent.open.create_mode; |
| 1444 | attr.ia_valid |= ATTR_MODE; |
| 1445 | attr.ia_mode &= ~current_umask(); |
| 1446 | } else |
| 1447 | open_flags &= ~(O_EXCL | O_CREAT); |
| 1448 | |
| 1449 | if (open_flags & O_TRUNC) { |
| 1450 | attr.ia_valid |= ATTR_SIZE; |
| 1451 | attr.ia_size = 0; |
| 1452 | } |
| 1453 | |
| 1454 | /* Open the file on the server */ |
| 1455 | nfs_block_sillyrename(dentry->d_parent); |
| 1456 | inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr); |
| 1457 | if (IS_ERR(inode)) { |
| 1458 | nfs_unblock_sillyrename(dentry->d_parent); |
| 1459 | put_nfs_open_context(ctx); |
| 1460 | switch (PTR_ERR(inode)) { |
| 1461 | /* Make a negative dentry */ |
| 1462 | case -ENOENT: |
| 1463 | d_add(dentry, NULL); |
| 1464 | res = NULL; |
| 1465 | goto out; |
| 1466 | /* This turned out not to be a regular file */ |
| 1467 | case -EISDIR: |
| 1468 | case -ENOTDIR: |
| 1469 | goto no_open; |
| 1470 | case -ELOOP: |
| 1471 | if (!(nd->intent.open.flags & O_NOFOLLOW)) |
| 1472 | goto no_open; |
| 1473 | /* case -EINVAL: */ |
| 1474 | default: |
| 1475 | res = ERR_CAST(inode); |
| 1476 | goto out; |
| 1477 | } |
| 1478 | } |
| 1479 | res = d_add_unique(dentry, inode); |
| 1480 | nfs_unblock_sillyrename(dentry->d_parent); |
| 1481 | if (res != NULL) { |
| 1482 | dput(ctx->dentry); |
| 1483 | ctx->dentry = dget(res); |
| 1484 | dentry = res; |
| 1485 | } |
| 1486 | err = nfs_intent_set_file(nd, ctx); |
| 1487 | if (err < 0) { |
| 1488 | if (res != NULL) |
| 1489 | dput(res); |
| 1490 | return ERR_PTR(err); |
| 1491 | } |
| 1492 | out: |
| 1493 | nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); |
| 1494 | return res; |
| 1495 | no_open: |
| 1496 | return nfs_lookup(dir, dentry, nd); |
| 1497 | } |
| 1498 | |
| 1499 | static int nfs_open_revalidate(struct dentry *dentry, struct nameidata *nd) |
| 1500 | { |
| 1501 | struct dentry *parent = NULL; |
| 1502 | struct inode *inode; |
| 1503 | struct inode *dir; |
| 1504 | struct nfs_open_context *ctx; |
| 1505 | struct iattr attr; |
| 1506 | int openflags, ret = 0; |
| 1507 | |
| 1508 | if (nd && (nd->flags & LOOKUP_RCU)) |
| 1509 | return -ECHILD; |
| 1510 | |
| 1511 | inode = dentry->d_inode; |
| 1512 | if (!is_atomic_open(nd) || d_mountpoint(dentry)) |
| 1513 | goto no_open; |
| 1514 | |
| 1515 | parent = dget_parent(dentry); |
| 1516 | dir = parent->d_inode; |
| 1517 | |
| 1518 | /* We can't create new files in nfs_open_revalidate(), so we |
| 1519 | * optimize away revalidation of negative dentries. |
| 1520 | */ |
| 1521 | if (inode == NULL) { |
| 1522 | if (!nfs_neg_need_reval(dir, dentry, nd)) |
| 1523 | ret = 1; |
| 1524 | goto out; |
| 1525 | } |
| 1526 | |
| 1527 | /* NFS only supports OPEN on regular files */ |
| 1528 | if (!S_ISREG(inode->i_mode)) |
| 1529 | goto no_open_dput; |
| 1530 | openflags = nd->intent.open.flags; |
| 1531 | /* We cannot do exclusive creation on a positive dentry */ |
| 1532 | if ((openflags & (O_CREAT|O_EXCL)) == (O_CREAT|O_EXCL)) |
| 1533 | goto no_open_dput; |
| 1534 | /* We can't create new files here */ |
| 1535 | openflags &= ~(O_CREAT|O_EXCL); |
| 1536 | |
| 1537 | ctx = create_nfs_open_context(dentry, openflags); |
| 1538 | ret = PTR_ERR(ctx); |
| 1539 | if (IS_ERR(ctx)) |
| 1540 | goto out; |
| 1541 | |
| 1542 | attr.ia_valid = ATTR_OPEN; |
| 1543 | if (openflags & O_TRUNC) { |
| 1544 | attr.ia_valid |= ATTR_SIZE; |
| 1545 | attr.ia_size = 0; |
| 1546 | nfs_wb_all(inode); |
| 1547 | } |
| 1548 | |
| 1549 | /* |
| 1550 | * Note: we're not holding inode->i_mutex and so may be racing with |
| 1551 | * operations that change the directory. We therefore save the |
| 1552 | * change attribute *before* we do the RPC call. |
| 1553 | */ |
| 1554 | inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, &attr); |
| 1555 | if (IS_ERR(inode)) { |
| 1556 | ret = PTR_ERR(inode); |
| 1557 | switch (ret) { |
| 1558 | case -EPERM: |
| 1559 | case -EACCES: |
| 1560 | case -EDQUOT: |
| 1561 | case -ENOSPC: |
| 1562 | case -EROFS: |
| 1563 | goto out_put_ctx; |
| 1564 | default: |
| 1565 | goto out_drop; |
| 1566 | } |
| 1567 | } |
| 1568 | iput(inode); |
| 1569 | if (inode != dentry->d_inode) |
| 1570 | goto out_drop; |
| 1571 | |
| 1572 | nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); |
| 1573 | ret = nfs_intent_set_file(nd, ctx); |
| 1574 | if (ret >= 0) |
| 1575 | ret = 1; |
| 1576 | out: |
| 1577 | dput(parent); |
| 1578 | return ret; |
| 1579 | out_drop: |
| 1580 | d_drop(dentry); |
| 1581 | ret = 0; |
| 1582 | out_put_ctx: |
| 1583 | put_nfs_open_context(ctx); |
| 1584 | goto out; |
| 1585 | |
| 1586 | no_open_dput: |
| 1587 | dput(parent); |
| 1588 | no_open: |
| 1589 | return nfs_lookup_revalidate(dentry, nd); |
| 1590 | } |
| 1591 | |
| 1592 | static int nfs_open_create(struct inode *dir, struct dentry *dentry, |
| 1593 | umode_t mode, struct nameidata *nd) |
| 1594 | { |
| 1595 | struct nfs_open_context *ctx = NULL; |
| 1596 | struct iattr attr; |
| 1597 | int error; |
| 1598 | int open_flags = O_CREAT|O_EXCL; |
| 1599 | |
| 1600 | dfprintk(VFS, "NFS: create(%s/%ld), %s\n", |
| 1601 | dir->i_sb->s_id, dir->i_ino, dentry->d_name.name); |
| 1602 | |
| 1603 | attr.ia_mode = mode; |
| 1604 | attr.ia_valid = ATTR_MODE; |
| 1605 | |
| 1606 | if (nd) |
| 1607 | open_flags = nd->intent.open.flags; |
| 1608 | |
| 1609 | ctx = create_nfs_open_context(dentry, open_flags); |
| 1610 | error = PTR_ERR(ctx); |
| 1611 | if (IS_ERR(ctx)) |
| 1612 | goto out_err_drop; |
| 1613 | |
| 1614 | error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags, ctx); |
| 1615 | if (error != 0) |
| 1616 | goto out_put_ctx; |
| 1617 | if (nd) { |
| 1618 | error = nfs_intent_set_file(nd, ctx); |
| 1619 | if (error < 0) |
| 1620 | goto out_err; |
| 1621 | } else { |
| 1622 | put_nfs_open_context(ctx); |
| 1623 | } |
| 1624 | return 0; |
| 1625 | out_put_ctx: |
| 1626 | put_nfs_open_context(ctx); |
| 1627 | out_err_drop: |
| 1628 | d_drop(dentry); |
| 1629 | out_err: |
| 1630 | return error; |
| 1631 | } |
| 1632 | |
| 1633 | #endif /* CONFIG_NFSV4 */ |
| 1634 | |
| 1635 | /* |
| 1636 | * Code common to create, mkdir, and mknod. |
| 1637 | */ |
| 1638 | int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fhandle, |
| 1639 | struct nfs_fattr *fattr) |
| 1640 | { |
| 1641 | struct dentry *parent = dget_parent(dentry); |
| 1642 | struct inode *dir = parent->d_inode; |
| 1643 | struct inode *inode; |
| 1644 | int error = -EACCES; |
| 1645 | |
| 1646 | d_drop(dentry); |
| 1647 | |
| 1648 | /* We may have been initialized further down */ |
| 1649 | if (dentry->d_inode) |
| 1650 | goto out; |
| 1651 | if (fhandle->size == 0) { |
| 1652 | error = NFS_PROTO(dir)->lookup(NFS_SERVER(dir)->client, dir, &dentry->d_name, fhandle, fattr); |
| 1653 | if (error) |
| 1654 | goto out_error; |
| 1655 | } |
| 1656 | nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); |
| 1657 | if (!(fattr->valid & NFS_ATTR_FATTR)) { |
| 1658 | struct nfs_server *server = NFS_SB(dentry->d_sb); |
| 1659 | error = server->nfs_client->rpc_ops->getattr(server, fhandle, fattr); |
| 1660 | if (error < 0) |
| 1661 | goto out_error; |
| 1662 | } |
| 1663 | inode = nfs_fhget(dentry->d_sb, fhandle, fattr); |
| 1664 | error = PTR_ERR(inode); |
| 1665 | if (IS_ERR(inode)) |
| 1666 | goto out_error; |
| 1667 | d_add(dentry, inode); |
| 1668 | out: |
| 1669 | dput(parent); |
| 1670 | return 0; |
| 1671 | out_error: |
| 1672 | nfs_mark_for_revalidate(dir); |
| 1673 | dput(parent); |
| 1674 | return error; |
| 1675 | } |
| 1676 | |
| 1677 | /* |
| 1678 | * Following a failed create operation, we drop the dentry rather |
| 1679 | * than retain a negative dentry. This avoids a problem in the event |
| 1680 | * that the operation succeeded on the server, but an error in the |
| 1681 | * reply path made it appear to have failed. |
| 1682 | */ |
| 1683 | static int nfs_create(struct inode *dir, struct dentry *dentry, |
| 1684 | umode_t mode, struct nameidata *nd) |
| 1685 | { |
| 1686 | struct iattr attr; |
| 1687 | int error; |
| 1688 | int open_flags = O_CREAT|O_EXCL; |
| 1689 | |
| 1690 | dfprintk(VFS, "NFS: create(%s/%ld), %s\n", |
| 1691 | dir->i_sb->s_id, dir->i_ino, dentry->d_name.name); |
| 1692 | |
| 1693 | attr.ia_mode = mode; |
| 1694 | attr.ia_valid = ATTR_MODE; |
| 1695 | |
| 1696 | if (nd) |
| 1697 | open_flags = nd->intent.open.flags; |
| 1698 | |
| 1699 | error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags, NULL); |
| 1700 | if (error != 0) |
| 1701 | goto out_err; |
| 1702 | return 0; |
| 1703 | out_err: |
| 1704 | d_drop(dentry); |
| 1705 | return error; |
| 1706 | } |
| 1707 | |
| 1708 | /* |
| 1709 | * See comments for nfs_proc_create regarding failed operations. |
| 1710 | */ |
| 1711 | static int |
| 1712 | nfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) |
| 1713 | { |
| 1714 | struct iattr attr; |
| 1715 | int status; |
| 1716 | |
| 1717 | dfprintk(VFS, "NFS: mknod(%s/%ld), %s\n", |
| 1718 | dir->i_sb->s_id, dir->i_ino, dentry->d_name.name); |
| 1719 | |
| 1720 | if (!new_valid_dev(rdev)) |
| 1721 | return -EINVAL; |
| 1722 | |
| 1723 | attr.ia_mode = mode; |
| 1724 | attr.ia_valid = ATTR_MODE; |
| 1725 | |
| 1726 | status = NFS_PROTO(dir)->mknod(dir, dentry, &attr, rdev); |
| 1727 | if (status != 0) |
| 1728 | goto out_err; |
| 1729 | return 0; |
| 1730 | out_err: |
| 1731 | d_drop(dentry); |
| 1732 | return status; |
| 1733 | } |
| 1734 | |
| 1735 | /* |
| 1736 | * See comments for nfs_proc_create regarding failed operations. |
| 1737 | */ |
| 1738 | static int nfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) |
| 1739 | { |
| 1740 | struct iattr attr; |
| 1741 | int error; |
| 1742 | |
| 1743 | dfprintk(VFS, "NFS: mkdir(%s/%ld), %s\n", |
| 1744 | dir->i_sb->s_id, dir->i_ino, dentry->d_name.name); |
| 1745 | |
| 1746 | attr.ia_valid = ATTR_MODE; |
| 1747 | attr.ia_mode = mode | S_IFDIR; |
| 1748 | |
| 1749 | error = NFS_PROTO(dir)->mkdir(dir, dentry, &attr); |
| 1750 | if (error != 0) |
| 1751 | goto out_err; |
| 1752 | return 0; |
| 1753 | out_err: |
| 1754 | d_drop(dentry); |
| 1755 | return error; |
| 1756 | } |
| 1757 | |
| 1758 | static void nfs_dentry_handle_enoent(struct dentry *dentry) |
| 1759 | { |
| 1760 | if (dentry->d_inode != NULL && !d_unhashed(dentry)) |
| 1761 | d_delete(dentry); |
| 1762 | } |
| 1763 | |
| 1764 | static int nfs_rmdir(struct inode *dir, struct dentry *dentry) |
| 1765 | { |
| 1766 | int error; |
| 1767 | |
| 1768 | dfprintk(VFS, "NFS: rmdir(%s/%ld), %s\n", |
| 1769 | dir->i_sb->s_id, dir->i_ino, dentry->d_name.name); |
| 1770 | |
| 1771 | error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name); |
| 1772 | /* Ensure the VFS deletes this inode */ |
| 1773 | if (error == 0 && dentry->d_inode != NULL) |
| 1774 | clear_nlink(dentry->d_inode); |
| 1775 | else if (error == -ENOENT) |
| 1776 | nfs_dentry_handle_enoent(dentry); |
| 1777 | |
| 1778 | return error; |
| 1779 | } |
| 1780 | |
| 1781 | /* |
| 1782 | * Remove a file after making sure there are no pending writes, |
| 1783 | * and after checking that the file has only one user. |
| 1784 | * |
| 1785 | * We invalidate the attribute cache and free the inode prior to the operation |
| 1786 | * to avoid possible races if the server reuses the inode. |
| 1787 | */ |
| 1788 | static int nfs_safe_remove(struct dentry *dentry) |
| 1789 | { |
| 1790 | struct inode *dir = dentry->d_parent->d_inode; |
| 1791 | struct inode *inode = dentry->d_inode; |
| 1792 | int error = -EBUSY; |
| 1793 | |
| 1794 | dfprintk(VFS, "NFS: safe_remove(%s/%s)\n", |
| 1795 | dentry->d_parent->d_name.name, dentry->d_name.name); |
| 1796 | |
| 1797 | /* If the dentry was sillyrenamed, we simply call d_delete() */ |
| 1798 | if (dentry->d_flags & DCACHE_NFSFS_RENAMED) { |
| 1799 | error = 0; |
| 1800 | goto out; |
| 1801 | } |
| 1802 | |
| 1803 | if (inode != NULL) { |
| 1804 | nfs_inode_return_delegation(inode); |
| 1805 | error = NFS_PROTO(dir)->remove(dir, &dentry->d_name); |
| 1806 | if (error == 0) |
| 1807 | nfs_drop_nlink(inode); |
| 1808 | } else |
| 1809 | error = NFS_PROTO(dir)->remove(dir, &dentry->d_name); |
| 1810 | if (error == -ENOENT) |
| 1811 | nfs_dentry_handle_enoent(dentry); |
| 1812 | out: |
| 1813 | return error; |
| 1814 | } |
| 1815 | |
| 1816 | /* We do silly rename. In case sillyrename() returns -EBUSY, the inode |
| 1817 | * belongs to an active ".nfs..." file and we return -EBUSY. |
| 1818 | * |
| 1819 | * If sillyrename() returns 0, we do nothing, otherwise we unlink. |
| 1820 | */ |
| 1821 | static int nfs_unlink(struct inode *dir, struct dentry *dentry) |
| 1822 | { |
| 1823 | int error; |
| 1824 | int need_rehash = 0; |
| 1825 | |
| 1826 | dfprintk(VFS, "NFS: unlink(%s/%ld, %s)\n", dir->i_sb->s_id, |
| 1827 | dir->i_ino, dentry->d_name.name); |
| 1828 | |
| 1829 | spin_lock(&dentry->d_lock); |
| 1830 | if (dentry->d_count > 1) { |
| 1831 | spin_unlock(&dentry->d_lock); |
| 1832 | /* Start asynchronous writeout of the inode */ |
| 1833 | write_inode_now(dentry->d_inode, 0); |
| 1834 | error = nfs_sillyrename(dir, dentry); |
| 1835 | return error; |
| 1836 | } |
| 1837 | if (!d_unhashed(dentry)) { |
| 1838 | __d_drop(dentry); |
| 1839 | need_rehash = 1; |
| 1840 | } |
| 1841 | spin_unlock(&dentry->d_lock); |
| 1842 | error = nfs_safe_remove(dentry); |
| 1843 | if (!error || error == -ENOENT) { |
| 1844 | nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); |
| 1845 | } else if (need_rehash) |
| 1846 | d_rehash(dentry); |
| 1847 | return error; |
| 1848 | } |
| 1849 | |
| 1850 | /* |
| 1851 | * To create a symbolic link, most file systems instantiate a new inode, |
| 1852 | * add a page to it containing the path, then write it out to the disk |
| 1853 | * using prepare_write/commit_write. |
| 1854 | * |
| 1855 | * Unfortunately the NFS client can't create the in-core inode first |
| 1856 | * because it needs a file handle to create an in-core inode (see |
| 1857 | * fs/nfs/inode.c:nfs_fhget). We only have a file handle *after* the |
| 1858 | * symlink request has completed on the server. |
| 1859 | * |
| 1860 | * So instead we allocate a raw page, copy the symname into it, then do |
| 1861 | * the SYMLINK request with the page as the buffer. If it succeeds, we |
| 1862 | * now have a new file handle and can instantiate an in-core NFS inode |
| 1863 | * and move the raw page into its mapping. |
| 1864 | */ |
| 1865 | static int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) |
| 1866 | { |
| 1867 | struct pagevec lru_pvec; |
| 1868 | struct page *page; |
| 1869 | char *kaddr; |
| 1870 | struct iattr attr; |
| 1871 | unsigned int pathlen = strlen(symname); |
| 1872 | int error; |
| 1873 | |
| 1874 | dfprintk(VFS, "NFS: symlink(%s/%ld, %s, %s)\n", dir->i_sb->s_id, |
| 1875 | dir->i_ino, dentry->d_name.name, symname); |
| 1876 | |
| 1877 | if (pathlen > PAGE_SIZE) |
| 1878 | return -ENAMETOOLONG; |
| 1879 | |
| 1880 | attr.ia_mode = S_IFLNK | S_IRWXUGO; |
| 1881 | attr.ia_valid = ATTR_MODE; |
| 1882 | |
| 1883 | page = alloc_page(GFP_HIGHUSER); |
| 1884 | if (!page) |
| 1885 | return -ENOMEM; |
| 1886 | |
| 1887 | kaddr = kmap_atomic(page); |
| 1888 | memcpy(kaddr, symname, pathlen); |
| 1889 | if (pathlen < PAGE_SIZE) |
| 1890 | memset(kaddr + pathlen, 0, PAGE_SIZE - pathlen); |
| 1891 | kunmap_atomic(kaddr); |
| 1892 | |
| 1893 | error = NFS_PROTO(dir)->symlink(dir, dentry, page, pathlen, &attr); |
| 1894 | if (error != 0) { |
| 1895 | dfprintk(VFS, "NFS: symlink(%s/%ld, %s, %s) error %d\n", |
| 1896 | dir->i_sb->s_id, dir->i_ino, |
| 1897 | dentry->d_name.name, symname, error); |
| 1898 | d_drop(dentry); |
| 1899 | __free_page(page); |
| 1900 | return error; |
| 1901 | } |
| 1902 | |
| 1903 | /* |
| 1904 | * No big deal if we can't add this page to the page cache here. |
| 1905 | * READLINK will get the missing page from the server if needed. |
| 1906 | */ |
| 1907 | pagevec_init(&lru_pvec, 0); |
| 1908 | if (!add_to_page_cache(page, dentry->d_inode->i_mapping, 0, |
| 1909 | GFP_KERNEL)) { |
| 1910 | pagevec_add(&lru_pvec, page); |
| 1911 | pagevec_lru_add_file(&lru_pvec); |
| 1912 | SetPageUptodate(page); |
| 1913 | unlock_page(page); |
| 1914 | } else |
| 1915 | __free_page(page); |
| 1916 | |
| 1917 | return 0; |
| 1918 | } |
| 1919 | |
| 1920 | static int |
| 1921 | nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) |
| 1922 | { |
| 1923 | struct inode *inode = old_dentry->d_inode; |
| 1924 | int error; |
| 1925 | |
| 1926 | dfprintk(VFS, "NFS: link(%s/%s -> %s/%s)\n", |
| 1927 | old_dentry->d_parent->d_name.name, old_dentry->d_name.name, |
| 1928 | dentry->d_parent->d_name.name, dentry->d_name.name); |
| 1929 | |
| 1930 | nfs_inode_return_delegation(inode); |
| 1931 | |
| 1932 | d_drop(dentry); |
| 1933 | error = NFS_PROTO(dir)->link(inode, dir, &dentry->d_name); |
| 1934 | if (error == 0) { |
| 1935 | ihold(inode); |
| 1936 | d_add(dentry, inode); |
| 1937 | } |
| 1938 | return error; |
| 1939 | } |
| 1940 | |
| 1941 | /* |
| 1942 | * RENAME |
| 1943 | * FIXME: Some nfsds, like the Linux user space nfsd, may generate a |
| 1944 | * different file handle for the same inode after a rename (e.g. when |
| 1945 | * moving to a different directory). A fail-safe method to do so would |
| 1946 | * be to look up old_dir/old_name, create a link to new_dir/new_name and |
| 1947 | * rename the old file using the sillyrename stuff. This way, the original |
| 1948 | * file in old_dir will go away when the last process iput()s the inode. |
| 1949 | * |
| 1950 | * FIXED. |
| 1951 | * |
| 1952 | * It actually works quite well. One needs to have the possibility for |
| 1953 | * at least one ".nfs..." file in each directory the file ever gets |
| 1954 | * moved or linked to which happens automagically with the new |
| 1955 | * implementation that only depends on the dcache stuff instead of |
| 1956 | * using the inode layer |
| 1957 | * |
| 1958 | * Unfortunately, things are a little more complicated than indicated |
| 1959 | * above. For a cross-directory move, we want to make sure we can get |
| 1960 | * rid of the old inode after the operation. This means there must be |
| 1961 | * no pending writes (if it's a file), and the use count must be 1. |
| 1962 | * If these conditions are met, we can drop the dentries before doing |
| 1963 | * the rename. |
| 1964 | */ |
| 1965 | static int nfs_rename(struct inode *old_dir, struct dentry *old_dentry, |
| 1966 | struct inode *new_dir, struct dentry *new_dentry) |
| 1967 | { |
| 1968 | struct inode *old_inode = old_dentry->d_inode; |
| 1969 | struct inode *new_inode = new_dentry->d_inode; |
| 1970 | struct dentry *dentry = NULL, *rehash = NULL; |
| 1971 | int error = -EBUSY; |
| 1972 | |
| 1973 | dfprintk(VFS, "NFS: rename(%s/%s -> %s/%s, ct=%d)\n", |
| 1974 | old_dentry->d_parent->d_name.name, old_dentry->d_name.name, |
| 1975 | new_dentry->d_parent->d_name.name, new_dentry->d_name.name, |
| 1976 | new_dentry->d_count); |
| 1977 | |
| 1978 | /* |
| 1979 | * For non-directories, check whether the target is busy and if so, |
| 1980 | * make a copy of the dentry and then do a silly-rename. If the |
| 1981 | * silly-rename succeeds, the copied dentry is hashed and becomes |
| 1982 | * the new target. |
| 1983 | */ |
| 1984 | if (new_inode && !S_ISDIR(new_inode->i_mode)) { |
| 1985 | /* |
| 1986 | * To prevent any new references to the target during the |
| 1987 | * rename, we unhash the dentry in advance. |
| 1988 | */ |
| 1989 | if (!d_unhashed(new_dentry)) { |
| 1990 | d_drop(new_dentry); |
| 1991 | rehash = new_dentry; |
| 1992 | } |
| 1993 | |
| 1994 | if (new_dentry->d_count > 2) { |
| 1995 | int err; |
| 1996 | |
| 1997 | /* copy the target dentry's name */ |
| 1998 | dentry = d_alloc(new_dentry->d_parent, |
| 1999 | &new_dentry->d_name); |
| 2000 | if (!dentry) |
| 2001 | goto out; |
| 2002 | |
| 2003 | /* silly-rename the existing target ... */ |
| 2004 | err = nfs_sillyrename(new_dir, new_dentry); |
| 2005 | if (err) |
| 2006 | goto out; |
| 2007 | |
| 2008 | new_dentry = dentry; |
| 2009 | rehash = NULL; |
| 2010 | new_inode = NULL; |
| 2011 | } |
| 2012 | } |
| 2013 | |
| 2014 | nfs_inode_return_delegation(old_inode); |
| 2015 | if (new_inode != NULL) |
| 2016 | nfs_inode_return_delegation(new_inode); |
| 2017 | |
| 2018 | error = NFS_PROTO(old_dir)->rename(old_dir, &old_dentry->d_name, |
| 2019 | new_dir, &new_dentry->d_name); |
| 2020 | nfs_mark_for_revalidate(old_inode); |
| 2021 | out: |
| 2022 | if (rehash) |
| 2023 | d_rehash(rehash); |
| 2024 | if (!error) { |
| 2025 | if (new_inode != NULL) |
| 2026 | nfs_drop_nlink(new_inode); |
| 2027 | d_move(old_dentry, new_dentry); |
| 2028 | nfs_set_verifier(new_dentry, |
| 2029 | nfs_save_change_attribute(new_dir)); |
| 2030 | } else if (error == -ENOENT) |
| 2031 | nfs_dentry_handle_enoent(old_dentry); |
| 2032 | |
| 2033 | /* new dentry created? */ |
| 2034 | if (dentry) |
| 2035 | dput(dentry); |
| 2036 | return error; |
| 2037 | } |
| 2038 | |
| 2039 | static DEFINE_SPINLOCK(nfs_access_lru_lock); |
| 2040 | static LIST_HEAD(nfs_access_lru_list); |
| 2041 | static atomic_long_t nfs_access_nr_entries; |
| 2042 | |
| 2043 | static void nfs_access_free_entry(struct nfs_access_entry *entry) |
| 2044 | { |
| 2045 | put_rpccred(entry->cred); |
| 2046 | kfree(entry); |
| 2047 | smp_mb__before_atomic_dec(); |
| 2048 | atomic_long_dec(&nfs_access_nr_entries); |
| 2049 | smp_mb__after_atomic_dec(); |
| 2050 | } |
| 2051 | |
| 2052 | static void nfs_access_free_list(struct list_head *head) |
| 2053 | { |
| 2054 | struct nfs_access_entry *cache; |
| 2055 | |
| 2056 | while (!list_empty(head)) { |
| 2057 | cache = list_entry(head->next, struct nfs_access_entry, lru); |
| 2058 | list_del(&cache->lru); |
| 2059 | nfs_access_free_entry(cache); |
| 2060 | } |
| 2061 | } |
| 2062 | |
| 2063 | int nfs_access_cache_shrinker(struct shrinker *shrink, |
| 2064 | struct shrink_control *sc) |
| 2065 | { |
| 2066 | LIST_HEAD(head); |
| 2067 | struct nfs_inode *nfsi, *next; |
| 2068 | struct nfs_access_entry *cache; |
| 2069 | int nr_to_scan = sc->nr_to_scan; |
| 2070 | gfp_t gfp_mask = sc->gfp_mask; |
| 2071 | |
| 2072 | if ((gfp_mask & GFP_KERNEL) != GFP_KERNEL) |
| 2073 | return (nr_to_scan == 0) ? 0 : -1; |
| 2074 | |
| 2075 | spin_lock(&nfs_access_lru_lock); |
| 2076 | list_for_each_entry_safe(nfsi, next, &nfs_access_lru_list, access_cache_inode_lru) { |
| 2077 | struct inode *inode; |
| 2078 | |
| 2079 | if (nr_to_scan-- == 0) |
| 2080 | break; |
| 2081 | inode = &nfsi->vfs_inode; |
| 2082 | spin_lock(&inode->i_lock); |
| 2083 | if (list_empty(&nfsi->access_cache_entry_lru)) |
| 2084 | goto remove_lru_entry; |
| 2085 | cache = list_entry(nfsi->access_cache_entry_lru.next, |
| 2086 | struct nfs_access_entry, lru); |
| 2087 | list_move(&cache->lru, &head); |
| 2088 | rb_erase(&cache->rb_node, &nfsi->access_cache); |
| 2089 | if (!list_empty(&nfsi->access_cache_entry_lru)) |
| 2090 | list_move_tail(&nfsi->access_cache_inode_lru, |
| 2091 | &nfs_access_lru_list); |
| 2092 | else { |
| 2093 | remove_lru_entry: |
| 2094 | list_del_init(&nfsi->access_cache_inode_lru); |
| 2095 | smp_mb__before_clear_bit(); |
| 2096 | clear_bit(NFS_INO_ACL_LRU_SET, &nfsi->flags); |
| 2097 | smp_mb__after_clear_bit(); |
| 2098 | } |
| 2099 | spin_unlock(&inode->i_lock); |
| 2100 | } |
| 2101 | spin_unlock(&nfs_access_lru_lock); |
| 2102 | nfs_access_free_list(&head); |
| 2103 | return (atomic_long_read(&nfs_access_nr_entries) / 100) * sysctl_vfs_cache_pressure; |
| 2104 | } |
| 2105 | |
| 2106 | static void __nfs_access_zap_cache(struct nfs_inode *nfsi, struct list_head *head) |
| 2107 | { |
| 2108 | struct rb_root *root_node = &nfsi->access_cache; |
| 2109 | struct rb_node *n; |
| 2110 | struct nfs_access_entry *entry; |
| 2111 | |
| 2112 | /* Unhook entries from the cache */ |
| 2113 | while ((n = rb_first(root_node)) != NULL) { |
| 2114 | entry = rb_entry(n, struct nfs_access_entry, rb_node); |
| 2115 | rb_erase(n, root_node); |
| 2116 | list_move(&entry->lru, head); |
| 2117 | } |
| 2118 | nfsi->cache_validity &= ~NFS_INO_INVALID_ACCESS; |
| 2119 | } |
| 2120 | |
| 2121 | void nfs_access_zap_cache(struct inode *inode) |
| 2122 | { |
| 2123 | LIST_HEAD(head); |
| 2124 | |
| 2125 | if (test_bit(NFS_INO_ACL_LRU_SET, &NFS_I(inode)->flags) == 0) |
| 2126 | return; |
| 2127 | /* Remove from global LRU init */ |
| 2128 | spin_lock(&nfs_access_lru_lock); |
| 2129 | if (test_and_clear_bit(NFS_INO_ACL_LRU_SET, &NFS_I(inode)->flags)) |
| 2130 | list_del_init(&NFS_I(inode)->access_cache_inode_lru); |
| 2131 | |
| 2132 | spin_lock(&inode->i_lock); |
| 2133 | __nfs_access_zap_cache(NFS_I(inode), &head); |
| 2134 | spin_unlock(&inode->i_lock); |
| 2135 | spin_unlock(&nfs_access_lru_lock); |
| 2136 | nfs_access_free_list(&head); |
| 2137 | } |
| 2138 | |
| 2139 | static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, struct rpc_cred *cred) |
| 2140 | { |
| 2141 | struct rb_node *n = NFS_I(inode)->access_cache.rb_node; |
| 2142 | struct nfs_access_entry *entry; |
| 2143 | |
| 2144 | while (n != NULL) { |
| 2145 | entry = rb_entry(n, struct nfs_access_entry, rb_node); |
| 2146 | |
| 2147 | if (cred < entry->cred) |
| 2148 | n = n->rb_left; |
| 2149 | else if (cred > entry->cred) |
| 2150 | n = n->rb_right; |
| 2151 | else |
| 2152 | return entry; |
| 2153 | } |
| 2154 | return NULL; |
| 2155 | } |
| 2156 | |
| 2157 | static int nfs_access_get_cached(struct inode *inode, struct rpc_cred *cred, struct nfs_access_entry *res) |
| 2158 | { |
| 2159 | struct nfs_inode *nfsi = NFS_I(inode); |
| 2160 | struct nfs_access_entry *cache; |
| 2161 | int err = -ENOENT; |
| 2162 | |
| 2163 | spin_lock(&inode->i_lock); |
| 2164 | if (nfsi->cache_validity & NFS_INO_INVALID_ACCESS) |
| 2165 | goto out_zap; |
| 2166 | cache = nfs_access_search_rbtree(inode, cred); |
| 2167 | if (cache == NULL) |
| 2168 | goto out; |
| 2169 | if (!nfs_have_delegated_attributes(inode) && |
| 2170 | !time_in_range_open(jiffies, cache->jiffies, cache->jiffies + nfsi->attrtimeo)) |
| 2171 | goto out_stale; |
| 2172 | res->jiffies = cache->jiffies; |
| 2173 | res->cred = cache->cred; |
| 2174 | res->mask = cache->mask; |
| 2175 | list_move_tail(&cache->lru, &nfsi->access_cache_entry_lru); |
| 2176 | err = 0; |
| 2177 | out: |
| 2178 | spin_unlock(&inode->i_lock); |
| 2179 | return err; |
| 2180 | out_stale: |
| 2181 | rb_erase(&cache->rb_node, &nfsi->access_cache); |
| 2182 | list_del(&cache->lru); |
| 2183 | spin_unlock(&inode->i_lock); |
| 2184 | nfs_access_free_entry(cache); |
| 2185 | return -ENOENT; |
| 2186 | out_zap: |
| 2187 | spin_unlock(&inode->i_lock); |
| 2188 | nfs_access_zap_cache(inode); |
| 2189 | return -ENOENT; |
| 2190 | } |
| 2191 | |
| 2192 | static void nfs_access_add_rbtree(struct inode *inode, struct nfs_access_entry *set) |
| 2193 | { |
| 2194 | struct nfs_inode *nfsi = NFS_I(inode); |
| 2195 | struct rb_root *root_node = &nfsi->access_cache; |
| 2196 | struct rb_node **p = &root_node->rb_node; |
| 2197 | struct rb_node *parent = NULL; |
| 2198 | struct nfs_access_entry *entry; |
| 2199 | |
| 2200 | spin_lock(&inode->i_lock); |
| 2201 | while (*p != NULL) { |
| 2202 | parent = *p; |
| 2203 | entry = rb_entry(parent, struct nfs_access_entry, rb_node); |
| 2204 | |
| 2205 | if (set->cred < entry->cred) |
| 2206 | p = &parent->rb_left; |
| 2207 | else if (set->cred > entry->cred) |
| 2208 | p = &parent->rb_right; |
| 2209 | else |
| 2210 | goto found; |
| 2211 | } |
| 2212 | rb_link_node(&set->rb_node, parent, p); |
| 2213 | rb_insert_color(&set->rb_node, root_node); |
| 2214 | list_add_tail(&set->lru, &nfsi->access_cache_entry_lru); |
| 2215 | spin_unlock(&inode->i_lock); |
| 2216 | return; |
| 2217 | found: |
| 2218 | rb_replace_node(parent, &set->rb_node, root_node); |
| 2219 | list_add_tail(&set->lru, &nfsi->access_cache_entry_lru); |
| 2220 | list_del(&entry->lru); |
| 2221 | spin_unlock(&inode->i_lock); |
| 2222 | nfs_access_free_entry(entry); |
| 2223 | } |
| 2224 | |
| 2225 | static void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set) |
| 2226 | { |
| 2227 | struct nfs_access_entry *cache = kmalloc(sizeof(*cache), GFP_KERNEL); |
| 2228 | if (cache == NULL) |
| 2229 | return; |
| 2230 | RB_CLEAR_NODE(&cache->rb_node); |
| 2231 | cache->jiffies = set->jiffies; |
| 2232 | cache->cred = get_rpccred(set->cred); |
| 2233 | cache->mask = set->mask; |
| 2234 | |
| 2235 | nfs_access_add_rbtree(inode, cache); |
| 2236 | |
| 2237 | /* Update accounting */ |
| 2238 | smp_mb__before_atomic_inc(); |
| 2239 | atomic_long_inc(&nfs_access_nr_entries); |
| 2240 | smp_mb__after_atomic_inc(); |
| 2241 | |
| 2242 | /* Add inode to global LRU list */ |
| 2243 | if (!test_bit(NFS_INO_ACL_LRU_SET, &NFS_I(inode)->flags)) { |
| 2244 | spin_lock(&nfs_access_lru_lock); |
| 2245 | if (!test_and_set_bit(NFS_INO_ACL_LRU_SET, &NFS_I(inode)->flags)) |
| 2246 | list_add_tail(&NFS_I(inode)->access_cache_inode_lru, |
| 2247 | &nfs_access_lru_list); |
| 2248 | spin_unlock(&nfs_access_lru_lock); |
| 2249 | } |
| 2250 | } |
| 2251 | |
| 2252 | static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask) |
| 2253 | { |
| 2254 | struct nfs_access_entry cache; |
| 2255 | int status; |
| 2256 | |
| 2257 | status = nfs_access_get_cached(inode, cred, &cache); |
| 2258 | if (status == 0) |
| 2259 | goto out; |
| 2260 | |
| 2261 | /* Be clever: ask server to check for all possible rights */ |
| 2262 | cache.mask = MAY_EXEC | MAY_WRITE | MAY_READ; |
| 2263 | cache.cred = cred; |
| 2264 | cache.jiffies = jiffies; |
| 2265 | status = NFS_PROTO(inode)->access(inode, &cache); |
| 2266 | if (status != 0) { |
| 2267 | if (status == -ESTALE) { |
| 2268 | nfs_zap_caches(inode); |
| 2269 | if (!S_ISDIR(inode->i_mode)) |
| 2270 | set_bit(NFS_INO_STALE, &NFS_I(inode)->flags); |
| 2271 | } |
| 2272 | return status; |
| 2273 | } |
| 2274 | nfs_access_add_cache(inode, &cache); |
| 2275 | out: |
| 2276 | if ((mask & ~cache.mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) == 0) |
| 2277 | return 0; |
| 2278 | return -EACCES; |
| 2279 | } |
| 2280 | |
| 2281 | static int nfs_open_permission_mask(int openflags) |
| 2282 | { |
| 2283 | int mask = 0; |
| 2284 | |
| 2285 | if ((openflags & O_ACCMODE) != O_WRONLY) |
| 2286 | mask |= MAY_READ; |
| 2287 | if ((openflags & O_ACCMODE) != O_RDONLY) |
| 2288 | mask |= MAY_WRITE; |
| 2289 | if (openflags & __FMODE_EXEC) |
| 2290 | mask |= MAY_EXEC; |
| 2291 | return mask; |
| 2292 | } |
| 2293 | |
| 2294 | int nfs_may_open(struct inode *inode, struct rpc_cred *cred, int openflags) |
| 2295 | { |
| 2296 | return nfs_do_access(inode, cred, nfs_open_permission_mask(openflags)); |
| 2297 | } |
| 2298 | |
| 2299 | int nfs_permission(struct inode *inode, int mask) |
| 2300 | { |
| 2301 | struct rpc_cred *cred; |
| 2302 | int res = 0; |
| 2303 | |
| 2304 | if (mask & MAY_NOT_BLOCK) |
| 2305 | return -ECHILD; |
| 2306 | |
| 2307 | nfs_inc_stats(inode, NFSIOS_VFSACCESS); |
| 2308 | |
| 2309 | if ((mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) == 0) |
| 2310 | goto out; |
| 2311 | /* Is this sys_access() ? */ |
| 2312 | if (mask & (MAY_ACCESS | MAY_CHDIR)) |
| 2313 | goto force_lookup; |
| 2314 | |
| 2315 | switch (inode->i_mode & S_IFMT) { |
| 2316 | case S_IFLNK: |
| 2317 | goto out; |
| 2318 | case S_IFREG: |
| 2319 | /* NFSv4 has atomic_open... */ |
| 2320 | if (nfs_server_capable(inode, NFS_CAP_ATOMIC_OPEN) |
| 2321 | && (mask & MAY_OPEN) |
| 2322 | && !(mask & MAY_EXEC)) |
| 2323 | goto out; |
| 2324 | break; |
| 2325 | case S_IFDIR: |
| 2326 | /* |
| 2327 | * Optimize away all write operations, since the server |
| 2328 | * will check permissions when we perform the op. |
| 2329 | */ |
| 2330 | if ((mask & MAY_WRITE) && !(mask & MAY_READ)) |
| 2331 | goto out; |
| 2332 | } |
| 2333 | |
| 2334 | force_lookup: |
| 2335 | if (!NFS_PROTO(inode)->access) |
| 2336 | goto out_notsup; |
| 2337 | |
| 2338 | cred = rpc_lookup_cred(); |
| 2339 | if (!IS_ERR(cred)) { |
| 2340 | res = nfs_do_access(inode, cred, mask); |
| 2341 | put_rpccred(cred); |
| 2342 | } else |
| 2343 | res = PTR_ERR(cred); |
| 2344 | out: |
| 2345 | if (!res && (mask & MAY_EXEC) && !execute_ok(inode)) |
| 2346 | res = -EACCES; |
| 2347 | |
| 2348 | dfprintk(VFS, "NFS: permission(%s/%ld), mask=0x%x, res=%d\n", |
| 2349 | inode->i_sb->s_id, inode->i_ino, mask, res); |
| 2350 | return res; |
| 2351 | out_notsup: |
| 2352 | res = nfs_revalidate_inode(NFS_SERVER(inode), inode); |
| 2353 | if (res == 0) |
| 2354 | res = generic_permission(inode, mask); |
| 2355 | goto out; |
| 2356 | } |
| 2357 | |
| 2358 | /* |
| 2359 | * Local variables: |
| 2360 | * version-control: t |
| 2361 | * kept-new-versions: 5 |
| 2362 | * End: |
| 2363 | */ |