lh | 9ed821d | 2023-04-07 01:36:19 -0700 | [diff] [blame] | 1 | /* |
| 2 | * fs/cifs/file.c |
| 3 | * |
| 4 | * vfs operations that deal with files |
| 5 | * |
| 6 | * Copyright (C) International Business Machines Corp., 2002,2010 |
| 7 | * Author(s): Steve French (sfrench@us.ibm.com) |
| 8 | * Jeremy Allison (jra@samba.org) |
| 9 | * |
| 10 | * This library is free software; you can redistribute it and/or modify |
| 11 | * it under the terms of the GNU Lesser General Public License as published |
| 12 | * by the Free Software Foundation; either version 2.1 of the License, or |
| 13 | * (at your option) any later version. |
| 14 | * |
| 15 | * This library is distributed in the hope that it will be useful, |
| 16 | * but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 17 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See |
| 18 | * the GNU Lesser General Public License for more details. |
| 19 | * |
| 20 | * You should have received a copy of the GNU Lesser General Public License |
| 21 | * along with this library; if not, write to the Free Software |
| 22 | * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA |
| 23 | */ |
| 24 | #include <linux/fs.h> |
| 25 | #include <linux/backing-dev.h> |
| 26 | #include <linux/stat.h> |
| 27 | #include <linux/fcntl.h> |
| 28 | #include <linux/pagemap.h> |
| 29 | #include <linux/pagevec.h> |
| 30 | #include <linux/writeback.h> |
| 31 | #include <linux/task_io_accounting_ops.h> |
| 32 | #include <linux/delay.h> |
| 33 | #include <linux/mount.h> |
| 34 | #include <linux/slab.h> |
| 35 | #include <linux/swap.h> |
| 36 | #include <asm/div64.h> |
| 37 | #include "cifsfs.h" |
| 38 | #include "cifspdu.h" |
| 39 | #include "cifsglob.h" |
| 40 | #include "cifsproto.h" |
| 41 | #include "cifs_unicode.h" |
| 42 | #include "cifs_debug.h" |
| 43 | #include "cifs_fs_sb.h" |
| 44 | #include "fscache.h" |
| 45 | |
| 46 | static inline int cifs_convert_flags(unsigned int flags) |
| 47 | { |
| 48 | if ((flags & O_ACCMODE) == O_RDONLY) |
| 49 | return GENERIC_READ; |
| 50 | else if ((flags & O_ACCMODE) == O_WRONLY) |
| 51 | return GENERIC_WRITE; |
| 52 | else if ((flags & O_ACCMODE) == O_RDWR) { |
| 53 | /* GENERIC_ALL is too much permission to request |
| 54 | can cause unnecessary access denied on create */ |
| 55 | /* return GENERIC_ALL; */ |
| 56 | return (GENERIC_READ | GENERIC_WRITE); |
| 57 | } |
| 58 | |
| 59 | return (READ_CONTROL | FILE_WRITE_ATTRIBUTES | FILE_READ_ATTRIBUTES | |
| 60 | FILE_WRITE_EA | FILE_APPEND_DATA | FILE_WRITE_DATA | |
| 61 | FILE_READ_DATA); |
| 62 | } |
| 63 | |
| 64 | static u32 cifs_posix_convert_flags(unsigned int flags) |
| 65 | { |
| 66 | u32 posix_flags = 0; |
| 67 | |
| 68 | if ((flags & O_ACCMODE) == O_RDONLY) |
| 69 | posix_flags = SMB_O_RDONLY; |
| 70 | else if ((flags & O_ACCMODE) == O_WRONLY) |
| 71 | posix_flags = SMB_O_WRONLY; |
| 72 | else if ((flags & O_ACCMODE) == O_RDWR) |
| 73 | posix_flags = SMB_O_RDWR; |
| 74 | |
| 75 | if (flags & O_CREAT) |
| 76 | posix_flags |= SMB_O_CREAT; |
| 77 | if (flags & O_EXCL) |
| 78 | posix_flags |= SMB_O_EXCL; |
| 79 | if (flags & O_TRUNC) |
| 80 | posix_flags |= SMB_O_TRUNC; |
| 81 | /* be safe and imply O_SYNC for O_DSYNC */ |
| 82 | if (flags & O_DSYNC) |
| 83 | posix_flags |= SMB_O_SYNC; |
| 84 | if (flags & O_DIRECTORY) |
| 85 | posix_flags |= SMB_O_DIRECTORY; |
| 86 | if (flags & O_NOFOLLOW) |
| 87 | posix_flags |= SMB_O_NOFOLLOW; |
| 88 | if (flags & O_DIRECT) |
| 89 | posix_flags |= SMB_O_DIRECT; |
| 90 | |
| 91 | return posix_flags; |
| 92 | } |
| 93 | |
| 94 | static inline int cifs_get_disposition(unsigned int flags) |
| 95 | { |
| 96 | if ((flags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL)) |
| 97 | return FILE_CREATE; |
| 98 | else if ((flags & (O_CREAT | O_TRUNC)) == (O_CREAT | O_TRUNC)) |
| 99 | return FILE_OVERWRITE_IF; |
| 100 | else if ((flags & O_CREAT) == O_CREAT) |
| 101 | return FILE_OPEN_IF; |
| 102 | else if ((flags & O_TRUNC) == O_TRUNC) |
| 103 | return FILE_OVERWRITE; |
| 104 | else |
| 105 | return FILE_OPEN; |
| 106 | } |
| 107 | |
| 108 | int cifs_posix_open(char *full_path, struct inode **pinode, |
| 109 | struct super_block *sb, int mode, unsigned int f_flags, |
| 110 | __u32 *poplock, __u16 *pnetfid, int xid) |
| 111 | { |
| 112 | int rc; |
| 113 | FILE_UNIX_BASIC_INFO *presp_data; |
| 114 | __u32 posix_flags = 0; |
| 115 | struct cifs_sb_info *cifs_sb = CIFS_SB(sb); |
| 116 | struct cifs_fattr fattr; |
| 117 | struct tcon_link *tlink; |
| 118 | struct cifs_tcon *tcon; |
| 119 | |
| 120 | cFYI(1, "posix open %s", full_path); |
| 121 | |
| 122 | presp_data = kzalloc(sizeof(FILE_UNIX_BASIC_INFO), GFP_KERNEL); |
| 123 | if (presp_data == NULL) |
| 124 | return -ENOMEM; |
| 125 | |
| 126 | tlink = cifs_sb_tlink(cifs_sb); |
| 127 | if (IS_ERR(tlink)) { |
| 128 | rc = PTR_ERR(tlink); |
| 129 | goto posix_open_ret; |
| 130 | } |
| 131 | |
| 132 | tcon = tlink_tcon(tlink); |
| 133 | mode &= ~current_umask(); |
| 134 | |
| 135 | posix_flags = cifs_posix_convert_flags(f_flags); |
| 136 | rc = CIFSPOSIXCreate(xid, tcon, posix_flags, mode, pnetfid, presp_data, |
| 137 | poplock, full_path, cifs_sb->local_nls, |
| 138 | cifs_sb->mnt_cifs_flags & |
| 139 | CIFS_MOUNT_MAP_SPECIAL_CHR); |
| 140 | cifs_put_tlink(tlink); |
| 141 | |
| 142 | if (rc) |
| 143 | goto posix_open_ret; |
| 144 | |
| 145 | if (presp_data->Type == cpu_to_le32(-1)) |
| 146 | goto posix_open_ret; /* open ok, caller does qpathinfo */ |
| 147 | |
| 148 | if (!pinode) |
| 149 | goto posix_open_ret; /* caller does not need info */ |
| 150 | |
| 151 | cifs_unix_basic_to_fattr(&fattr, presp_data, cifs_sb); |
| 152 | |
| 153 | /* get new inode and set it up */ |
| 154 | if (*pinode == NULL) { |
| 155 | cifs_fill_uniqueid(sb, &fattr); |
| 156 | *pinode = cifs_iget(sb, &fattr); |
| 157 | if (!*pinode) { |
| 158 | rc = -ENOMEM; |
| 159 | goto posix_open_ret; |
| 160 | } |
| 161 | } else { |
| 162 | cifs_fattr_to_inode(*pinode, &fattr); |
| 163 | } |
| 164 | |
| 165 | posix_open_ret: |
| 166 | kfree(presp_data); |
| 167 | return rc; |
| 168 | } |
| 169 | |
| 170 | static int |
| 171 | cifs_nt_open(char *full_path, struct inode *inode, struct cifs_sb_info *cifs_sb, |
| 172 | struct cifs_tcon *tcon, unsigned int f_flags, __u32 *poplock, |
| 173 | __u16 *pnetfid, int xid) |
| 174 | { |
| 175 | int rc; |
| 176 | int desiredAccess; |
| 177 | int disposition; |
| 178 | int create_options = CREATE_NOT_DIR; |
| 179 | FILE_ALL_INFO *buf; |
| 180 | |
| 181 | desiredAccess = cifs_convert_flags(f_flags); |
| 182 | |
| 183 | /********************************************************************* |
| 184 | * open flag mapping table: |
| 185 | * |
| 186 | * POSIX Flag CIFS Disposition |
| 187 | * ---------- ---------------- |
| 188 | * O_CREAT FILE_OPEN_IF |
| 189 | * O_CREAT | O_EXCL FILE_CREATE |
| 190 | * O_CREAT | O_TRUNC FILE_OVERWRITE_IF |
| 191 | * O_TRUNC FILE_OVERWRITE |
| 192 | * none of the above FILE_OPEN |
| 193 | * |
| 194 | * Note that there is not a direct match between disposition |
| 195 | * FILE_SUPERSEDE (ie create whether or not file exists although |
| 196 | * O_CREAT | O_TRUNC is similar but truncates the existing |
| 197 | * file rather than creating a new file as FILE_SUPERSEDE does |
| 198 | * (which uses the attributes / metadata passed in on open call) |
| 199 | *? |
| 200 | *? O_SYNC is a reasonable match to CIFS writethrough flag |
| 201 | *? and the read write flags match reasonably. O_LARGEFILE |
| 202 | *? is irrelevant because largefile support is always used |
| 203 | *? by this client. Flags O_APPEND, O_DIRECT, O_DIRECTORY, |
| 204 | * O_FASYNC, O_NOFOLLOW, O_NONBLOCK need further investigation |
| 205 | *********************************************************************/ |
| 206 | |
| 207 | disposition = cifs_get_disposition(f_flags); |
| 208 | |
| 209 | /* BB pass O_SYNC flag through on file attributes .. BB */ |
| 210 | |
| 211 | buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL); |
| 212 | if (!buf) |
| 213 | return -ENOMEM; |
| 214 | |
| 215 | if (backup_cred(cifs_sb)) |
| 216 | create_options |= CREATE_OPEN_BACKUP_INTENT; |
| 217 | |
| 218 | if (tcon->ses->capabilities & CAP_NT_SMBS) |
| 219 | rc = CIFSSMBOpen(xid, tcon, full_path, disposition, |
| 220 | desiredAccess, create_options, pnetfid, poplock, buf, |
| 221 | cifs_sb->local_nls, cifs_sb->mnt_cifs_flags |
| 222 | & CIFS_MOUNT_MAP_SPECIAL_CHR); |
| 223 | else |
| 224 | rc = SMBLegacyOpen(xid, tcon, full_path, disposition, |
| 225 | desiredAccess, CREATE_NOT_DIR, pnetfid, poplock, buf, |
| 226 | cifs_sb->local_nls, cifs_sb->mnt_cifs_flags |
| 227 | & CIFS_MOUNT_MAP_SPECIAL_CHR); |
| 228 | |
| 229 | if (rc) |
| 230 | goto out; |
| 231 | |
| 232 | if (tcon->unix_ext) |
| 233 | rc = cifs_get_inode_info_unix(&inode, full_path, inode->i_sb, |
| 234 | xid); |
| 235 | else |
| 236 | rc = cifs_get_inode_info(&inode, full_path, buf, inode->i_sb, |
| 237 | xid, pnetfid); |
| 238 | |
| 239 | out: |
| 240 | kfree(buf); |
| 241 | return rc; |
| 242 | } |
| 243 | |
| 244 | struct cifsFileInfo * |
| 245 | cifs_new_fileinfo(__u16 fileHandle, struct file *file, |
| 246 | struct tcon_link *tlink, __u32 oplock) |
| 247 | { |
| 248 | struct dentry *dentry = file->f_path.dentry; |
| 249 | struct inode *inode = dentry->d_inode; |
| 250 | struct cifsInodeInfo *pCifsInode = CIFS_I(inode); |
| 251 | struct cifsFileInfo *pCifsFile; |
| 252 | |
| 253 | pCifsFile = kzalloc(sizeof(struct cifsFileInfo), GFP_KERNEL); |
| 254 | if (pCifsFile == NULL) |
| 255 | return pCifsFile; |
| 256 | |
| 257 | pCifsFile->count = 1; |
| 258 | pCifsFile->netfid = fileHandle; |
| 259 | pCifsFile->pid = current->tgid; |
| 260 | pCifsFile->uid = current_fsuid(); |
| 261 | pCifsFile->dentry = dget(dentry); |
| 262 | pCifsFile->f_flags = file->f_flags; |
| 263 | pCifsFile->invalidHandle = false; |
| 264 | pCifsFile->tlink = cifs_get_tlink(tlink); |
| 265 | mutex_init(&pCifsFile->fh_mutex); |
| 266 | INIT_WORK(&pCifsFile->oplock_break, cifs_oplock_break); |
| 267 | |
| 268 | cifs_sb_active(inode->i_sb); |
| 269 | |
| 270 | spin_lock(&cifs_file_list_lock); |
| 271 | list_add(&pCifsFile->tlist, &(tlink_tcon(tlink)->openFileList)); |
| 272 | /* if readable file instance put first in list*/ |
| 273 | if (file->f_mode & FMODE_READ) |
| 274 | list_add(&pCifsFile->flist, &pCifsInode->openFileList); |
| 275 | else |
| 276 | list_add_tail(&pCifsFile->flist, &pCifsInode->openFileList); |
| 277 | spin_unlock(&cifs_file_list_lock); |
| 278 | |
| 279 | cifs_set_oplock_level(pCifsInode, oplock); |
| 280 | pCifsInode->can_cache_brlcks = pCifsInode->clientCanCacheAll; |
| 281 | |
| 282 | file->private_data = pCifsFile; |
| 283 | return pCifsFile; |
| 284 | } |
| 285 | |
| 286 | static void cifs_del_lock_waiters(struct cifsLockInfo *lock); |
| 287 | |
| 288 | /* |
| 289 | * Release a reference on the file private data. This may involve closing |
| 290 | * the filehandle out on the server. Must be called without holding |
| 291 | * cifs_file_list_lock. |
| 292 | */ |
| 293 | void cifsFileInfo_put(struct cifsFileInfo *cifs_file) |
| 294 | { |
| 295 | struct inode *inode = cifs_file->dentry->d_inode; |
| 296 | struct cifs_tcon *tcon = tlink_tcon(cifs_file->tlink); |
| 297 | struct cifsInodeInfo *cifsi = CIFS_I(inode); |
| 298 | struct super_block *sb = inode->i_sb; |
| 299 | struct cifs_sb_info *cifs_sb = CIFS_SB(sb); |
| 300 | struct cifsLockInfo *li, *tmp; |
| 301 | |
| 302 | spin_lock(&cifs_file_list_lock); |
| 303 | if (--cifs_file->count > 0) { |
| 304 | spin_unlock(&cifs_file_list_lock); |
| 305 | return; |
| 306 | } |
| 307 | |
| 308 | /* remove it from the lists */ |
| 309 | list_del(&cifs_file->flist); |
| 310 | list_del(&cifs_file->tlist); |
| 311 | |
| 312 | if (list_empty(&cifsi->openFileList)) { |
| 313 | cFYI(1, "closing last open instance for inode %p", |
| 314 | cifs_file->dentry->d_inode); |
| 315 | |
| 316 | /* in strict cache mode we need invalidate mapping on the last |
| 317 | close because it may cause a error when we open this file |
| 318 | again and get at least level II oplock */ |
| 319 | if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO) |
| 320 | CIFS_I(inode)->invalid_mapping = true; |
| 321 | |
| 322 | cifs_set_oplock_level(cifsi, 0); |
| 323 | } |
| 324 | spin_unlock(&cifs_file_list_lock); |
| 325 | |
| 326 | cancel_work_sync(&cifs_file->oplock_break); |
| 327 | |
| 328 | if (!tcon->need_reconnect && !cifs_file->invalidHandle) { |
| 329 | int xid, rc; |
| 330 | |
| 331 | xid = GetXid(); |
| 332 | rc = CIFSSMBClose(xid, tcon, cifs_file->netfid); |
| 333 | FreeXid(xid); |
| 334 | } |
| 335 | |
| 336 | /* Delete any outstanding lock records. We'll lose them when the file |
| 337 | * is closed anyway. |
| 338 | */ |
| 339 | mutex_lock(&cifsi->lock_mutex); |
| 340 | list_for_each_entry_safe(li, tmp, &cifsi->llist, llist) { |
| 341 | if (li->netfid != cifs_file->netfid) |
| 342 | continue; |
| 343 | list_del(&li->llist); |
| 344 | cifs_del_lock_waiters(li); |
| 345 | kfree(li); |
| 346 | } |
| 347 | mutex_unlock(&cifsi->lock_mutex); |
| 348 | |
| 349 | cifs_put_tlink(cifs_file->tlink); |
| 350 | dput(cifs_file->dentry); |
| 351 | cifs_sb_deactive(sb); |
| 352 | kfree(cifs_file); |
| 353 | } |
| 354 | |
| 355 | int cifs_open(struct inode *inode, struct file *file) |
| 356 | { |
| 357 | int rc = -EACCES; |
| 358 | int xid; |
| 359 | __u32 oplock; |
| 360 | struct cifs_sb_info *cifs_sb; |
| 361 | struct cifs_tcon *tcon; |
| 362 | struct tcon_link *tlink; |
| 363 | struct cifsFileInfo *pCifsFile = NULL; |
| 364 | char *full_path = NULL; |
| 365 | bool posix_open_ok = false; |
| 366 | __u16 netfid; |
| 367 | |
| 368 | xid = GetXid(); |
| 369 | |
| 370 | cifs_sb = CIFS_SB(inode->i_sb); |
| 371 | tlink = cifs_sb_tlink(cifs_sb); |
| 372 | if (IS_ERR(tlink)) { |
| 373 | FreeXid(xid); |
| 374 | return PTR_ERR(tlink); |
| 375 | } |
| 376 | tcon = tlink_tcon(tlink); |
| 377 | |
| 378 | full_path = build_path_from_dentry(file->f_path.dentry); |
| 379 | if (full_path == NULL) { |
| 380 | rc = -ENOMEM; |
| 381 | goto out; |
| 382 | } |
| 383 | |
| 384 | cFYI(1, "inode = 0x%p file flags are 0x%x for %s", |
| 385 | inode, file->f_flags, full_path); |
| 386 | |
| 387 | if (tcon->ses->server->oplocks) |
| 388 | oplock = REQ_OPLOCK; |
| 389 | else |
| 390 | oplock = 0; |
| 391 | |
| 392 | if (!tcon->broken_posix_open && tcon->unix_ext && |
| 393 | (tcon->ses->capabilities & CAP_UNIX) && |
| 394 | (CIFS_UNIX_POSIX_PATH_OPS_CAP & |
| 395 | le64_to_cpu(tcon->fsUnixInfo.Capability))) { |
| 396 | /* can not refresh inode info since size could be stale */ |
| 397 | rc = cifs_posix_open(full_path, &inode, inode->i_sb, |
| 398 | cifs_sb->mnt_file_mode /* ignored */, |
| 399 | file->f_flags, &oplock, &netfid, xid); |
| 400 | if (rc == 0) { |
| 401 | cFYI(1, "posix open succeeded"); |
| 402 | posix_open_ok = true; |
| 403 | } else if ((rc == -EINVAL) || (rc == -EOPNOTSUPP)) { |
| 404 | if (tcon->ses->serverNOS) |
| 405 | cERROR(1, "server %s of type %s returned" |
| 406 | " unexpected error on SMB posix open" |
| 407 | ", disabling posix open support." |
| 408 | " Check if server update available.", |
| 409 | tcon->ses->serverName, |
| 410 | tcon->ses->serverNOS); |
| 411 | tcon->broken_posix_open = true; |
| 412 | } else if ((rc != -EIO) && (rc != -EREMOTE) && |
| 413 | (rc != -EOPNOTSUPP)) /* path not found or net err */ |
| 414 | goto out; |
| 415 | /* else fallthrough to retry open the old way on network i/o |
| 416 | or DFS errors */ |
| 417 | } |
| 418 | |
| 419 | if (!posix_open_ok) { |
| 420 | rc = cifs_nt_open(full_path, inode, cifs_sb, tcon, |
| 421 | file->f_flags, &oplock, &netfid, xid); |
| 422 | if (rc) |
| 423 | goto out; |
| 424 | } |
| 425 | |
| 426 | pCifsFile = cifs_new_fileinfo(netfid, file, tlink, oplock); |
| 427 | if (pCifsFile == NULL) { |
| 428 | CIFSSMBClose(xid, tcon, netfid); |
| 429 | rc = -ENOMEM; |
| 430 | goto out; |
| 431 | } |
| 432 | |
| 433 | cifs_fscache_set_inode_cookie(inode, file); |
| 434 | |
| 435 | if ((oplock & CIFS_CREATE_ACTION) && !posix_open_ok && tcon->unix_ext) { |
| 436 | /* time to set mode which we can not set earlier due to |
| 437 | problems creating new read-only files */ |
| 438 | struct cifs_unix_set_info_args args = { |
| 439 | .mode = inode->i_mode, |
| 440 | .uid = NO_CHANGE_64, |
| 441 | .gid = NO_CHANGE_64, |
| 442 | .ctime = NO_CHANGE_64, |
| 443 | .atime = NO_CHANGE_64, |
| 444 | .mtime = NO_CHANGE_64, |
| 445 | .device = 0, |
| 446 | }; |
| 447 | CIFSSMBUnixSetFileInfo(xid, tcon, &args, netfid, |
| 448 | pCifsFile->pid); |
| 449 | } |
| 450 | |
| 451 | out: |
| 452 | kfree(full_path); |
| 453 | FreeXid(xid); |
| 454 | cifs_put_tlink(tlink); |
| 455 | return rc; |
| 456 | } |
| 457 | |
| 458 | /* Try to reacquire byte range locks that were released when session */ |
| 459 | /* to server was lost */ |
| 460 | static int cifs_relock_file(struct cifsFileInfo *cifsFile) |
| 461 | { |
| 462 | int rc = 0; |
| 463 | |
| 464 | /* BB list all locks open on this file and relock */ |
| 465 | |
| 466 | return rc; |
| 467 | } |
| 468 | |
| 469 | static int cifs_reopen_file(struct cifsFileInfo *pCifsFile, bool can_flush) |
| 470 | { |
| 471 | int rc = -EACCES; |
| 472 | int xid; |
| 473 | __u32 oplock; |
| 474 | struct cifs_sb_info *cifs_sb; |
| 475 | struct cifs_tcon *tcon; |
| 476 | struct cifsInodeInfo *pCifsInode; |
| 477 | struct inode *inode; |
| 478 | char *full_path = NULL; |
| 479 | int desiredAccess; |
| 480 | int disposition = FILE_OPEN; |
| 481 | int create_options = CREATE_NOT_DIR; |
| 482 | __u16 netfid; |
| 483 | |
| 484 | xid = GetXid(); |
| 485 | mutex_lock(&pCifsFile->fh_mutex); |
| 486 | if (!pCifsFile->invalidHandle) { |
| 487 | mutex_unlock(&pCifsFile->fh_mutex); |
| 488 | rc = 0; |
| 489 | FreeXid(xid); |
| 490 | return rc; |
| 491 | } |
| 492 | |
| 493 | inode = pCifsFile->dentry->d_inode; |
| 494 | cifs_sb = CIFS_SB(inode->i_sb); |
| 495 | tcon = tlink_tcon(pCifsFile->tlink); |
| 496 | |
| 497 | /* can not grab rename sem here because various ops, including |
| 498 | those that already have the rename sem can end up causing writepage |
| 499 | to get called and if the server was down that means we end up here, |
| 500 | and we can never tell if the caller already has the rename_sem */ |
| 501 | full_path = build_path_from_dentry(pCifsFile->dentry); |
| 502 | if (full_path == NULL) { |
| 503 | rc = -ENOMEM; |
| 504 | mutex_unlock(&pCifsFile->fh_mutex); |
| 505 | FreeXid(xid); |
| 506 | return rc; |
| 507 | } |
| 508 | |
| 509 | cFYI(1, "inode = 0x%p file flags 0x%x for %s", |
| 510 | inode, pCifsFile->f_flags, full_path); |
| 511 | |
| 512 | if (tcon->ses->server->oplocks) |
| 513 | oplock = REQ_OPLOCK; |
| 514 | else |
| 515 | oplock = 0; |
| 516 | |
| 517 | if (tcon->unix_ext && (tcon->ses->capabilities & CAP_UNIX) && |
| 518 | (CIFS_UNIX_POSIX_PATH_OPS_CAP & |
| 519 | le64_to_cpu(tcon->fsUnixInfo.Capability))) { |
| 520 | |
| 521 | /* |
| 522 | * O_CREAT, O_EXCL and O_TRUNC already had their effect on the |
| 523 | * original open. Must mask them off for a reopen. |
| 524 | */ |
| 525 | unsigned int oflags = pCifsFile->f_flags & |
| 526 | ~(O_CREAT | O_EXCL | O_TRUNC); |
| 527 | |
| 528 | rc = cifs_posix_open(full_path, NULL, inode->i_sb, |
| 529 | cifs_sb->mnt_file_mode /* ignored */, |
| 530 | oflags, &oplock, &netfid, xid); |
| 531 | if (rc == 0) { |
| 532 | cFYI(1, "posix reopen succeeded"); |
| 533 | goto reopen_success; |
| 534 | } |
| 535 | /* fallthrough to retry open the old way on errors, especially |
| 536 | in the reconnect path it is important to retry hard */ |
| 537 | } |
| 538 | |
| 539 | desiredAccess = cifs_convert_flags(pCifsFile->f_flags); |
| 540 | |
| 541 | if (backup_cred(cifs_sb)) |
| 542 | create_options |= CREATE_OPEN_BACKUP_INTENT; |
| 543 | |
| 544 | /* Can not refresh inode by passing in file_info buf to be returned |
| 545 | by SMBOpen and then calling get_inode_info with returned buf |
| 546 | since file might have write behind data that needs to be flushed |
| 547 | and server version of file size can be stale. If we knew for sure |
| 548 | that inode was not dirty locally we could do this */ |
| 549 | |
| 550 | rc = CIFSSMBOpen(xid, tcon, full_path, disposition, desiredAccess, |
| 551 | create_options, &netfid, &oplock, NULL, |
| 552 | cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & |
| 553 | CIFS_MOUNT_MAP_SPECIAL_CHR); |
| 554 | if (rc) { |
| 555 | mutex_unlock(&pCifsFile->fh_mutex); |
| 556 | cFYI(1, "cifs_open returned 0x%x", rc); |
| 557 | cFYI(1, "oplock: %d", oplock); |
| 558 | goto reopen_error_exit; |
| 559 | } |
| 560 | |
| 561 | reopen_success: |
| 562 | pCifsFile->netfid = netfid; |
| 563 | pCifsFile->invalidHandle = false; |
| 564 | mutex_unlock(&pCifsFile->fh_mutex); |
| 565 | pCifsInode = CIFS_I(inode); |
| 566 | |
| 567 | if (can_flush) { |
| 568 | rc = filemap_write_and_wait(inode->i_mapping); |
| 569 | mapping_set_error(inode->i_mapping, rc); |
| 570 | |
| 571 | if (tcon->unix_ext) |
| 572 | rc = cifs_get_inode_info_unix(&inode, |
| 573 | full_path, inode->i_sb, xid); |
| 574 | else |
| 575 | rc = cifs_get_inode_info(&inode, |
| 576 | full_path, NULL, inode->i_sb, |
| 577 | xid, NULL); |
| 578 | } /* else we are writing out data to server already |
| 579 | and could deadlock if we tried to flush data, and |
| 580 | since we do not know if we have data that would |
| 581 | invalidate the current end of file on the server |
| 582 | we can not go to the server to get the new inod |
| 583 | info */ |
| 584 | |
| 585 | cifs_set_oplock_level(pCifsInode, oplock); |
| 586 | |
| 587 | cifs_relock_file(pCifsFile); |
| 588 | |
| 589 | reopen_error_exit: |
| 590 | kfree(full_path); |
| 591 | FreeXid(xid); |
| 592 | return rc; |
| 593 | } |
| 594 | |
| 595 | int cifs_close(struct inode *inode, struct file *file) |
| 596 | { |
| 597 | if (file->private_data != NULL) { |
| 598 | cifsFileInfo_put(file->private_data); |
| 599 | file->private_data = NULL; |
| 600 | } |
| 601 | |
| 602 | /* return code from the ->release op is always ignored */ |
| 603 | return 0; |
| 604 | } |
| 605 | |
| 606 | int cifs_closedir(struct inode *inode, struct file *file) |
| 607 | { |
| 608 | int rc = 0; |
| 609 | int xid; |
| 610 | struct cifsFileInfo *pCFileStruct = file->private_data; |
| 611 | char *ptmp; |
| 612 | |
| 613 | cFYI(1, "Closedir inode = 0x%p", inode); |
| 614 | |
| 615 | xid = GetXid(); |
| 616 | |
| 617 | if (pCFileStruct) { |
| 618 | struct cifs_tcon *pTcon = tlink_tcon(pCFileStruct->tlink); |
| 619 | |
| 620 | cFYI(1, "Freeing private data in close dir"); |
| 621 | spin_lock(&cifs_file_list_lock); |
| 622 | if (!pCFileStruct->srch_inf.endOfSearch && |
| 623 | !pCFileStruct->invalidHandle) { |
| 624 | pCFileStruct->invalidHandle = true; |
| 625 | spin_unlock(&cifs_file_list_lock); |
| 626 | rc = CIFSFindClose(xid, pTcon, pCFileStruct->netfid); |
| 627 | cFYI(1, "Closing uncompleted readdir with rc %d", |
| 628 | rc); |
| 629 | /* not much we can do if it fails anyway, ignore rc */ |
| 630 | rc = 0; |
| 631 | } else |
| 632 | spin_unlock(&cifs_file_list_lock); |
| 633 | ptmp = pCFileStruct->srch_inf.ntwrk_buf_start; |
| 634 | if (ptmp) { |
| 635 | cFYI(1, "closedir free smb buf in srch struct"); |
| 636 | pCFileStruct->srch_inf.ntwrk_buf_start = NULL; |
| 637 | if (pCFileStruct->srch_inf.smallBuf) |
| 638 | cifs_small_buf_release(ptmp); |
| 639 | else |
| 640 | cifs_buf_release(ptmp); |
| 641 | } |
| 642 | cifs_put_tlink(pCFileStruct->tlink); |
| 643 | kfree(file->private_data); |
| 644 | file->private_data = NULL; |
| 645 | } |
| 646 | /* BB can we lock the filestruct while this is going on? */ |
| 647 | FreeXid(xid); |
| 648 | return rc; |
| 649 | } |
| 650 | |
| 651 | static struct cifsLockInfo * |
| 652 | cifs_lock_init(__u64 offset, __u64 length, __u8 type, __u16 netfid) |
| 653 | { |
| 654 | struct cifsLockInfo *lock = |
| 655 | kmalloc(sizeof(struct cifsLockInfo), GFP_KERNEL); |
| 656 | if (!lock) |
| 657 | return lock; |
| 658 | lock->offset = offset; |
| 659 | lock->length = length; |
| 660 | lock->type = type; |
| 661 | lock->netfid = netfid; |
| 662 | lock->pid = current->tgid; |
| 663 | INIT_LIST_HEAD(&lock->blist); |
| 664 | init_waitqueue_head(&lock->block_q); |
| 665 | return lock; |
| 666 | } |
| 667 | |
| 668 | static void |
| 669 | cifs_del_lock_waiters(struct cifsLockInfo *lock) |
| 670 | { |
| 671 | struct cifsLockInfo *li, *tmp; |
| 672 | list_for_each_entry_safe(li, tmp, &lock->blist, blist) { |
| 673 | list_del_init(&li->blist); |
| 674 | wake_up(&li->block_q); |
| 675 | } |
| 676 | } |
| 677 | |
| 678 | static bool |
| 679 | __cifs_find_lock_conflict(struct cifsInodeInfo *cinode, __u64 offset, |
| 680 | __u64 length, __u8 type, __u16 netfid, |
| 681 | struct cifsLockInfo **conf_lock) |
| 682 | { |
| 683 | struct cifsLockInfo *li, *tmp; |
| 684 | |
| 685 | list_for_each_entry_safe(li, tmp, &cinode->llist, llist) { |
| 686 | if (offset + length <= li->offset || |
| 687 | offset >= li->offset + li->length) |
| 688 | continue; |
| 689 | else if ((type & LOCKING_ANDX_SHARED_LOCK) && |
| 690 | ((netfid == li->netfid && current->tgid == li->pid) || |
| 691 | type == li->type)) |
| 692 | continue; |
| 693 | else { |
| 694 | *conf_lock = li; |
| 695 | return true; |
| 696 | } |
| 697 | } |
| 698 | return false; |
| 699 | } |
| 700 | |
| 701 | static bool |
| 702 | cifs_find_lock_conflict(struct cifsInodeInfo *cinode, struct cifsLockInfo *lock, |
| 703 | struct cifsLockInfo **conf_lock) |
| 704 | { |
| 705 | return __cifs_find_lock_conflict(cinode, lock->offset, lock->length, |
| 706 | lock->type, lock->netfid, conf_lock); |
| 707 | } |
| 708 | |
| 709 | /* |
| 710 | * Check if there is another lock that prevents us to set the lock (mandatory |
| 711 | * style). If such a lock exists, update the flock structure with its |
| 712 | * properties. Otherwise, set the flock type to F_UNLCK if we can cache brlocks |
| 713 | * or leave it the same if we can't. Returns 0 if we don't need to request to |
| 714 | * the server or 1 otherwise. |
| 715 | */ |
| 716 | static int |
| 717 | cifs_lock_test(struct cifsInodeInfo *cinode, __u64 offset, __u64 length, |
| 718 | __u8 type, __u16 netfid, struct file_lock *flock) |
| 719 | { |
| 720 | int rc = 0; |
| 721 | struct cifsLockInfo *conf_lock; |
| 722 | bool exist; |
| 723 | |
| 724 | mutex_lock(&cinode->lock_mutex); |
| 725 | |
| 726 | exist = __cifs_find_lock_conflict(cinode, offset, length, type, netfid, |
| 727 | &conf_lock); |
| 728 | if (exist) { |
| 729 | flock->fl_start = conf_lock->offset; |
| 730 | flock->fl_end = conf_lock->offset + conf_lock->length - 1; |
| 731 | flock->fl_pid = conf_lock->pid; |
| 732 | if (conf_lock->type & LOCKING_ANDX_SHARED_LOCK) |
| 733 | flock->fl_type = F_RDLCK; |
| 734 | else |
| 735 | flock->fl_type = F_WRLCK; |
| 736 | } else if (!cinode->can_cache_brlcks) |
| 737 | rc = 1; |
| 738 | else |
| 739 | flock->fl_type = F_UNLCK; |
| 740 | |
| 741 | mutex_unlock(&cinode->lock_mutex); |
| 742 | return rc; |
| 743 | } |
| 744 | |
| 745 | static void |
| 746 | cifs_lock_add(struct cifsInodeInfo *cinode, struct cifsLockInfo *lock) |
| 747 | { |
| 748 | mutex_lock(&cinode->lock_mutex); |
| 749 | list_add_tail(&lock->llist, &cinode->llist); |
| 750 | mutex_unlock(&cinode->lock_mutex); |
| 751 | } |
| 752 | |
| 753 | /* |
| 754 | * Set the byte-range lock (mandatory style). Returns: |
| 755 | * 1) 0, if we set the lock and don't need to request to the server; |
| 756 | * 2) 1, if no locks prevent us but we need to request to the server; |
| 757 | * 3) -EACCESS, if there is a lock that prevents us and wait is false. |
| 758 | */ |
| 759 | static int |
| 760 | cifs_lock_add_if(struct cifsInodeInfo *cinode, struct cifsLockInfo *lock, |
| 761 | bool wait) |
| 762 | { |
| 763 | struct cifsLockInfo *conf_lock; |
| 764 | bool exist; |
| 765 | int rc = 0; |
| 766 | |
| 767 | try_again: |
| 768 | exist = false; |
| 769 | mutex_lock(&cinode->lock_mutex); |
| 770 | |
| 771 | exist = cifs_find_lock_conflict(cinode, lock, &conf_lock); |
| 772 | if (!exist && cinode->can_cache_brlcks) { |
| 773 | list_add_tail(&lock->llist, &cinode->llist); |
| 774 | mutex_unlock(&cinode->lock_mutex); |
| 775 | return rc; |
| 776 | } |
| 777 | |
| 778 | if (!exist) |
| 779 | rc = 1; |
| 780 | else if (!wait) |
| 781 | rc = -EACCES; |
| 782 | else { |
| 783 | list_add_tail(&lock->blist, &conf_lock->blist); |
| 784 | mutex_unlock(&cinode->lock_mutex); |
| 785 | rc = wait_event_interruptible(lock->block_q, |
| 786 | (lock->blist.prev == &lock->blist) && |
| 787 | (lock->blist.next == &lock->blist)); |
| 788 | if (!rc) |
| 789 | goto try_again; |
| 790 | mutex_lock(&cinode->lock_mutex); |
| 791 | list_del_init(&lock->blist); |
| 792 | } |
| 793 | |
| 794 | mutex_unlock(&cinode->lock_mutex); |
| 795 | return rc; |
| 796 | } |
| 797 | |
| 798 | /* |
| 799 | * Check if there is another lock that prevents us to set the lock (posix |
| 800 | * style). If such a lock exists, update the flock structure with its |
| 801 | * properties. Otherwise, set the flock type to F_UNLCK if we can cache brlocks |
| 802 | * or leave it the same if we can't. Returns 0 if we don't need to request to |
| 803 | * the server or 1 otherwise. |
| 804 | */ |
| 805 | static int |
| 806 | cifs_posix_lock_test(struct file *file, struct file_lock *flock) |
| 807 | { |
| 808 | int rc = 0; |
| 809 | struct cifsInodeInfo *cinode = CIFS_I(file->f_path.dentry->d_inode); |
| 810 | unsigned char saved_type = flock->fl_type; |
| 811 | |
| 812 | if ((flock->fl_flags & FL_POSIX) == 0) |
| 813 | return 1; |
| 814 | |
| 815 | mutex_lock(&cinode->lock_mutex); |
| 816 | posix_test_lock(file, flock); |
| 817 | |
| 818 | if (flock->fl_type == F_UNLCK && !cinode->can_cache_brlcks) { |
| 819 | flock->fl_type = saved_type; |
| 820 | rc = 1; |
| 821 | } |
| 822 | |
| 823 | mutex_unlock(&cinode->lock_mutex); |
| 824 | return rc; |
| 825 | } |
| 826 | |
| 827 | /* |
| 828 | * Set the byte-range lock (posix style). Returns: |
| 829 | * 1) 0, if we set the lock and don't need to request to the server; |
| 830 | * 2) 1, if we need to request to the server; |
| 831 | * 3) <0, if the error occurs while setting the lock. |
| 832 | */ |
| 833 | static int |
| 834 | cifs_posix_lock_set(struct file *file, struct file_lock *flock) |
| 835 | { |
| 836 | struct cifsInodeInfo *cinode = CIFS_I(file->f_path.dentry->d_inode); |
| 837 | int rc = 1; |
| 838 | |
| 839 | if ((flock->fl_flags & FL_POSIX) == 0) |
| 840 | return rc; |
| 841 | |
| 842 | try_again: |
| 843 | mutex_lock(&cinode->lock_mutex); |
| 844 | if (!cinode->can_cache_brlcks) { |
| 845 | mutex_unlock(&cinode->lock_mutex); |
| 846 | return rc; |
| 847 | } |
| 848 | |
| 849 | rc = posix_lock_file(file, flock, NULL); |
| 850 | mutex_unlock(&cinode->lock_mutex); |
| 851 | if (rc == FILE_LOCK_DEFERRED) { |
| 852 | rc = wait_event_interruptible(flock->fl_wait, !flock->fl_next); |
| 853 | if (!rc) |
| 854 | goto try_again; |
| 855 | locks_delete_block(flock); |
| 856 | } |
| 857 | return rc; |
| 858 | } |
| 859 | |
| 860 | static int |
| 861 | cifs_push_mandatory_locks(struct cifsFileInfo *cfile) |
| 862 | { |
| 863 | int xid, rc = 0, stored_rc; |
| 864 | struct cifsLockInfo *li, *tmp; |
| 865 | struct cifs_tcon *tcon; |
| 866 | struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode); |
| 867 | unsigned int num, max_num; |
| 868 | LOCKING_ANDX_RANGE *buf, *cur; |
| 869 | int types[] = {LOCKING_ANDX_LARGE_FILES, |
| 870 | LOCKING_ANDX_SHARED_LOCK | LOCKING_ANDX_LARGE_FILES}; |
| 871 | int i; |
| 872 | |
| 873 | xid = GetXid(); |
| 874 | tcon = tlink_tcon(cfile->tlink); |
| 875 | |
| 876 | mutex_lock(&cinode->lock_mutex); |
| 877 | if (!cinode->can_cache_brlcks) { |
| 878 | mutex_unlock(&cinode->lock_mutex); |
| 879 | FreeXid(xid); |
| 880 | return rc; |
| 881 | } |
| 882 | |
| 883 | max_num = (tcon->ses->server->maxBuf - sizeof(struct smb_hdr)) / |
| 884 | sizeof(LOCKING_ANDX_RANGE); |
| 885 | buf = kzalloc(max_num * sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL); |
| 886 | if (!buf) { |
| 887 | mutex_unlock(&cinode->lock_mutex); |
| 888 | FreeXid(xid); |
| 889 | return -ENOMEM; |
| 890 | } |
| 891 | |
| 892 | for (i = 0; i < 2; i++) { |
| 893 | cur = buf; |
| 894 | num = 0; |
| 895 | list_for_each_entry_safe(li, tmp, &cinode->llist, llist) { |
| 896 | if (li->type != types[i]) |
| 897 | continue; |
| 898 | cur->Pid = cpu_to_le16(li->pid); |
| 899 | cur->LengthLow = cpu_to_le32((u32)li->length); |
| 900 | cur->LengthHigh = cpu_to_le32((u32)(li->length>>32)); |
| 901 | cur->OffsetLow = cpu_to_le32((u32)li->offset); |
| 902 | cur->OffsetHigh = cpu_to_le32((u32)(li->offset>>32)); |
| 903 | if (++num == max_num) { |
| 904 | stored_rc = cifs_lockv(xid, tcon, cfile->netfid, |
| 905 | li->type, 0, num, buf); |
| 906 | if (stored_rc) |
| 907 | rc = stored_rc; |
| 908 | cur = buf; |
| 909 | num = 0; |
| 910 | } else |
| 911 | cur++; |
| 912 | } |
| 913 | |
| 914 | if (num) { |
| 915 | stored_rc = cifs_lockv(xid, tcon, cfile->netfid, |
| 916 | types[i], 0, num, buf); |
| 917 | if (stored_rc) |
| 918 | rc = stored_rc; |
| 919 | } |
| 920 | } |
| 921 | |
| 922 | cinode->can_cache_brlcks = false; |
| 923 | mutex_unlock(&cinode->lock_mutex); |
| 924 | |
| 925 | kfree(buf); |
| 926 | FreeXid(xid); |
| 927 | return rc; |
| 928 | } |
| 929 | |
| 930 | /* copied from fs/locks.c with a name change */ |
| 931 | #define cifs_for_each_lock(inode, lockp) \ |
| 932 | for (lockp = &inode->i_flock; *lockp != NULL; \ |
| 933 | lockp = &(*lockp)->fl_next) |
| 934 | |
| 935 | struct lock_to_push { |
| 936 | struct list_head llist; |
| 937 | __u64 offset; |
| 938 | __u64 length; |
| 939 | __u32 pid; |
| 940 | __u16 netfid; |
| 941 | __u8 type; |
| 942 | }; |
| 943 | |
| 944 | static int |
| 945 | cifs_push_posix_locks(struct cifsFileInfo *cfile) |
| 946 | { |
| 947 | struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode); |
| 948 | struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); |
| 949 | struct file_lock *flock, **before; |
| 950 | unsigned int count = 0, i = 0; |
| 951 | int rc = 0, xid, type; |
| 952 | struct list_head locks_to_send, *el; |
| 953 | struct lock_to_push *lck, *tmp; |
| 954 | __u64 length; |
| 955 | |
| 956 | xid = GetXid(); |
| 957 | |
| 958 | mutex_lock(&cinode->lock_mutex); |
| 959 | if (!cinode->can_cache_brlcks) { |
| 960 | mutex_unlock(&cinode->lock_mutex); |
| 961 | FreeXid(xid); |
| 962 | return rc; |
| 963 | } |
| 964 | |
| 965 | lock_flocks(); |
| 966 | cifs_for_each_lock(cfile->dentry->d_inode, before) { |
| 967 | if ((*before)->fl_flags & FL_POSIX) |
| 968 | count++; |
| 969 | } |
| 970 | unlock_flocks(); |
| 971 | |
| 972 | INIT_LIST_HEAD(&locks_to_send); |
| 973 | |
| 974 | /* |
| 975 | * Allocating count locks is enough because no FL_POSIX locks can be |
| 976 | * added to the list while we are holding cinode->lock_mutex that |
| 977 | * protects locking operations of this inode. |
| 978 | */ |
| 979 | for (; i < count; i++) { |
| 980 | lck = kmalloc(sizeof(struct lock_to_push), GFP_KERNEL); |
| 981 | if (!lck) { |
| 982 | rc = -ENOMEM; |
| 983 | goto err_out; |
| 984 | } |
| 985 | list_add_tail(&lck->llist, &locks_to_send); |
| 986 | } |
| 987 | |
| 988 | el = locks_to_send.next; |
| 989 | lock_flocks(); |
| 990 | cifs_for_each_lock(cfile->dentry->d_inode, before) { |
| 991 | flock = *before; |
| 992 | if ((flock->fl_flags & FL_POSIX) == 0) |
| 993 | continue; |
| 994 | if (el == &locks_to_send) { |
| 995 | /* |
| 996 | * The list ended. We don't have enough allocated |
| 997 | * structures - something is really wrong. |
| 998 | */ |
| 999 | cERROR(1, "Can't push all brlocks!"); |
| 1000 | break; |
| 1001 | } |
| 1002 | length = 1 + flock->fl_end - flock->fl_start; |
| 1003 | if (flock->fl_type == F_RDLCK || flock->fl_type == F_SHLCK) |
| 1004 | type = CIFS_RDLCK; |
| 1005 | else |
| 1006 | type = CIFS_WRLCK; |
| 1007 | lck = list_entry(el, struct lock_to_push, llist); |
| 1008 | lck->pid = flock->fl_pid; |
| 1009 | lck->netfid = cfile->netfid; |
| 1010 | lck->length = length; |
| 1011 | lck->type = type; |
| 1012 | lck->offset = flock->fl_start; |
| 1013 | el = el->next; |
| 1014 | } |
| 1015 | unlock_flocks(); |
| 1016 | |
| 1017 | list_for_each_entry_safe(lck, tmp, &locks_to_send, llist) { |
| 1018 | struct file_lock tmp_lock; |
| 1019 | int stored_rc; |
| 1020 | |
| 1021 | tmp_lock.fl_start = lck->offset; |
| 1022 | stored_rc = CIFSSMBPosixLock(xid, tcon, lck->netfid, lck->pid, |
| 1023 | 0, lck->length, &tmp_lock, |
| 1024 | lck->type, 0); |
| 1025 | if (stored_rc) |
| 1026 | rc = stored_rc; |
| 1027 | list_del(&lck->llist); |
| 1028 | kfree(lck); |
| 1029 | } |
| 1030 | |
| 1031 | out: |
| 1032 | cinode->can_cache_brlcks = false; |
| 1033 | mutex_unlock(&cinode->lock_mutex); |
| 1034 | |
| 1035 | FreeXid(xid); |
| 1036 | return rc; |
| 1037 | err_out: |
| 1038 | list_for_each_entry_safe(lck, tmp, &locks_to_send, llist) { |
| 1039 | list_del(&lck->llist); |
| 1040 | kfree(lck); |
| 1041 | } |
| 1042 | goto out; |
| 1043 | } |
| 1044 | |
| 1045 | static int |
| 1046 | cifs_push_locks(struct cifsFileInfo *cfile) |
| 1047 | { |
| 1048 | struct cifs_sb_info *cifs_sb = CIFS_SB(cfile->dentry->d_sb); |
| 1049 | struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); |
| 1050 | |
| 1051 | if ((tcon->ses->capabilities & CAP_UNIX) && |
| 1052 | (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) && |
| 1053 | ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0)) |
| 1054 | return cifs_push_posix_locks(cfile); |
| 1055 | |
| 1056 | return cifs_push_mandatory_locks(cfile); |
| 1057 | } |
| 1058 | |
| 1059 | static void |
| 1060 | cifs_read_flock(struct file_lock *flock, __u8 *type, int *lock, int *unlock, |
| 1061 | bool *wait_flag) |
| 1062 | { |
| 1063 | if (flock->fl_flags & FL_POSIX) |
| 1064 | cFYI(1, "Posix"); |
| 1065 | if (flock->fl_flags & FL_FLOCK) |
| 1066 | cFYI(1, "Flock"); |
| 1067 | if (flock->fl_flags & FL_SLEEP) { |
| 1068 | cFYI(1, "Blocking lock"); |
| 1069 | *wait_flag = true; |
| 1070 | } |
| 1071 | if (flock->fl_flags & FL_ACCESS) |
| 1072 | cFYI(1, "Process suspended by mandatory locking - " |
| 1073 | "not implemented yet"); |
| 1074 | if (flock->fl_flags & FL_LEASE) |
| 1075 | cFYI(1, "Lease on file - not implemented yet"); |
| 1076 | if (flock->fl_flags & |
| 1077 | (~(FL_POSIX | FL_FLOCK | FL_SLEEP | FL_ACCESS | FL_LEASE))) |
| 1078 | cFYI(1, "Unknown lock flags 0x%x", flock->fl_flags); |
| 1079 | |
| 1080 | *type = LOCKING_ANDX_LARGE_FILES; |
| 1081 | if (flock->fl_type == F_WRLCK) { |
| 1082 | cFYI(1, "F_WRLCK "); |
| 1083 | *lock = 1; |
| 1084 | } else if (flock->fl_type == F_UNLCK) { |
| 1085 | cFYI(1, "F_UNLCK"); |
| 1086 | *unlock = 1; |
| 1087 | /* Check if unlock includes more than one lock range */ |
| 1088 | } else if (flock->fl_type == F_RDLCK) { |
| 1089 | cFYI(1, "F_RDLCK"); |
| 1090 | *type |= LOCKING_ANDX_SHARED_LOCK; |
| 1091 | *lock = 1; |
| 1092 | } else if (flock->fl_type == F_EXLCK) { |
| 1093 | cFYI(1, "F_EXLCK"); |
| 1094 | *lock = 1; |
| 1095 | } else if (flock->fl_type == F_SHLCK) { |
| 1096 | cFYI(1, "F_SHLCK"); |
| 1097 | *type |= LOCKING_ANDX_SHARED_LOCK; |
| 1098 | *lock = 1; |
| 1099 | } else |
| 1100 | cFYI(1, "Unknown type of lock"); |
| 1101 | } |
| 1102 | |
| 1103 | static int |
| 1104 | cifs_getlk(struct file *file, struct file_lock *flock, __u8 type, |
| 1105 | bool wait_flag, bool posix_lck, int xid) |
| 1106 | { |
| 1107 | int rc = 0; |
| 1108 | __u64 length = 1 + flock->fl_end - flock->fl_start; |
| 1109 | struct cifsFileInfo *cfile = (struct cifsFileInfo *)file->private_data; |
| 1110 | struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); |
| 1111 | struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode); |
| 1112 | __u16 netfid = cfile->netfid; |
| 1113 | |
| 1114 | if (posix_lck) { |
| 1115 | int posix_lock_type; |
| 1116 | |
| 1117 | rc = cifs_posix_lock_test(file, flock); |
| 1118 | if (!rc) |
| 1119 | return rc; |
| 1120 | |
| 1121 | if (type & LOCKING_ANDX_SHARED_LOCK) |
| 1122 | posix_lock_type = CIFS_RDLCK; |
| 1123 | else |
| 1124 | posix_lock_type = CIFS_WRLCK; |
| 1125 | rc = CIFSSMBPosixLock(xid, tcon, netfid, current->tgid, |
| 1126 | 1 /* get */, length, flock, |
| 1127 | posix_lock_type, wait_flag); |
| 1128 | return rc; |
| 1129 | } |
| 1130 | |
| 1131 | rc = cifs_lock_test(cinode, flock->fl_start, length, type, netfid, |
| 1132 | flock); |
| 1133 | if (!rc) |
| 1134 | return rc; |
| 1135 | |
| 1136 | /* BB we could chain these into one lock request BB */ |
| 1137 | rc = CIFSSMBLock(xid, tcon, netfid, current->tgid, length, |
| 1138 | flock->fl_start, 0, 1, type, 0, 0); |
| 1139 | if (rc == 0) { |
| 1140 | rc = CIFSSMBLock(xid, tcon, netfid, current->tgid, |
| 1141 | length, flock->fl_start, 1, 0, |
| 1142 | type, 0, 0); |
| 1143 | flock->fl_type = F_UNLCK; |
| 1144 | if (rc != 0) |
| 1145 | cERROR(1, "Error unlocking previously locked " |
| 1146 | "range %d during test of lock", rc); |
| 1147 | return 0; |
| 1148 | } |
| 1149 | |
| 1150 | if (type & LOCKING_ANDX_SHARED_LOCK) { |
| 1151 | flock->fl_type = F_WRLCK; |
| 1152 | return 0; |
| 1153 | } |
| 1154 | |
| 1155 | rc = CIFSSMBLock(xid, tcon, netfid, current->tgid, length, |
| 1156 | flock->fl_start, 0, 1, |
| 1157 | type | LOCKING_ANDX_SHARED_LOCK, 0, 0); |
| 1158 | if (rc == 0) { |
| 1159 | rc = CIFSSMBLock(xid, tcon, netfid, current->tgid, |
| 1160 | length, flock->fl_start, 1, 0, |
| 1161 | type | LOCKING_ANDX_SHARED_LOCK, |
| 1162 | 0, 0); |
| 1163 | flock->fl_type = F_RDLCK; |
| 1164 | if (rc != 0) |
| 1165 | cERROR(1, "Error unlocking previously locked " |
| 1166 | "range %d during test of lock", rc); |
| 1167 | } else |
| 1168 | flock->fl_type = F_WRLCK; |
| 1169 | |
| 1170 | return 0; |
| 1171 | } |
| 1172 | |
| 1173 | static void |
| 1174 | cifs_move_llist(struct list_head *source, struct list_head *dest) |
| 1175 | { |
| 1176 | struct list_head *li, *tmp; |
| 1177 | list_for_each_safe(li, tmp, source) |
| 1178 | list_move(li, dest); |
| 1179 | } |
| 1180 | |
| 1181 | static void |
| 1182 | cifs_free_llist(struct list_head *llist) |
| 1183 | { |
| 1184 | struct cifsLockInfo *li, *tmp; |
| 1185 | list_for_each_entry_safe(li, tmp, llist, llist) { |
| 1186 | cifs_del_lock_waiters(li); |
| 1187 | list_del(&li->llist); |
| 1188 | kfree(li); |
| 1189 | } |
| 1190 | } |
| 1191 | |
| 1192 | static int |
| 1193 | cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock, int xid) |
| 1194 | { |
| 1195 | int rc = 0, stored_rc; |
| 1196 | int types[] = {LOCKING_ANDX_LARGE_FILES, |
| 1197 | LOCKING_ANDX_SHARED_LOCK | LOCKING_ANDX_LARGE_FILES}; |
| 1198 | unsigned int i; |
| 1199 | unsigned int max_num, num; |
| 1200 | LOCKING_ANDX_RANGE *buf, *cur; |
| 1201 | struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); |
| 1202 | struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode); |
| 1203 | struct cifsLockInfo *li, *tmp; |
| 1204 | __u64 length = 1 + flock->fl_end - flock->fl_start; |
| 1205 | struct list_head tmp_llist; |
| 1206 | |
| 1207 | INIT_LIST_HEAD(&tmp_llist); |
| 1208 | |
| 1209 | max_num = (tcon->ses->server->maxBuf - sizeof(struct smb_hdr)) / |
| 1210 | sizeof(LOCKING_ANDX_RANGE); |
| 1211 | buf = kzalloc(max_num * sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL); |
| 1212 | if (!buf) |
| 1213 | return -ENOMEM; |
| 1214 | |
| 1215 | mutex_lock(&cinode->lock_mutex); |
| 1216 | for (i = 0; i < 2; i++) { |
| 1217 | cur = buf; |
| 1218 | num = 0; |
| 1219 | list_for_each_entry_safe(li, tmp, &cinode->llist, llist) { |
| 1220 | if (flock->fl_start > li->offset || |
| 1221 | (flock->fl_start + length) < |
| 1222 | (li->offset + li->length)) |
| 1223 | continue; |
| 1224 | if (current->tgid != li->pid) |
| 1225 | continue; |
| 1226 | if (cfile->netfid != li->netfid) |
| 1227 | continue; |
| 1228 | if (types[i] != li->type) |
| 1229 | continue; |
| 1230 | if (!cinode->can_cache_brlcks) { |
| 1231 | cur->Pid = cpu_to_le16(li->pid); |
| 1232 | cur->LengthLow = cpu_to_le32((u32)li->length); |
| 1233 | cur->LengthHigh = |
| 1234 | cpu_to_le32((u32)(li->length>>32)); |
| 1235 | cur->OffsetLow = cpu_to_le32((u32)li->offset); |
| 1236 | cur->OffsetHigh = |
| 1237 | cpu_to_le32((u32)(li->offset>>32)); |
| 1238 | /* |
| 1239 | * We need to save a lock here to let us add |
| 1240 | * it again to the inode list if the unlock |
| 1241 | * range request fails on the server. |
| 1242 | */ |
| 1243 | list_move(&li->llist, &tmp_llist); |
| 1244 | if (++num == max_num) { |
| 1245 | stored_rc = cifs_lockv(xid, tcon, |
| 1246 | cfile->netfid, |
| 1247 | li->type, num, |
| 1248 | 0, buf); |
| 1249 | if (stored_rc) { |
| 1250 | /* |
| 1251 | * We failed on the unlock range |
| 1252 | * request - add all locks from |
| 1253 | * the tmp list to the head of |
| 1254 | * the inode list. |
| 1255 | */ |
| 1256 | cifs_move_llist(&tmp_llist, |
| 1257 | &cinode->llist); |
| 1258 | rc = stored_rc; |
| 1259 | } else |
| 1260 | /* |
| 1261 | * The unlock range request |
| 1262 | * succeed - free the tmp list. |
| 1263 | */ |
| 1264 | cifs_free_llist(&tmp_llist); |
| 1265 | cur = buf; |
| 1266 | num = 0; |
| 1267 | } else |
| 1268 | cur++; |
| 1269 | } else { |
| 1270 | /* |
| 1271 | * We can cache brlock requests - simply remove |
| 1272 | * a lock from the inode list. |
| 1273 | */ |
| 1274 | list_del(&li->llist); |
| 1275 | cifs_del_lock_waiters(li); |
| 1276 | kfree(li); |
| 1277 | } |
| 1278 | } |
| 1279 | if (num) { |
| 1280 | stored_rc = cifs_lockv(xid, tcon, cfile->netfid, |
| 1281 | types[i], num, 0, buf); |
| 1282 | if (stored_rc) { |
| 1283 | cifs_move_llist(&tmp_llist, &cinode->llist); |
| 1284 | rc = stored_rc; |
| 1285 | } else |
| 1286 | cifs_free_llist(&tmp_llist); |
| 1287 | } |
| 1288 | } |
| 1289 | |
| 1290 | mutex_unlock(&cinode->lock_mutex); |
| 1291 | kfree(buf); |
| 1292 | return rc; |
| 1293 | } |
| 1294 | |
| 1295 | static int |
| 1296 | cifs_setlk(struct file *file, struct file_lock *flock, __u8 type, |
| 1297 | bool wait_flag, bool posix_lck, int lock, int unlock, int xid) |
| 1298 | { |
| 1299 | int rc = 0; |
| 1300 | __u64 length = 1 + flock->fl_end - flock->fl_start; |
| 1301 | struct cifsFileInfo *cfile = (struct cifsFileInfo *)file->private_data; |
| 1302 | struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); |
| 1303 | struct cifsInodeInfo *cinode = CIFS_I(file->f_path.dentry->d_inode); |
| 1304 | __u16 netfid = cfile->netfid; |
| 1305 | |
| 1306 | if (posix_lck) { |
| 1307 | int posix_lock_type; |
| 1308 | |
| 1309 | rc = cifs_posix_lock_set(file, flock); |
| 1310 | if (!rc || rc < 0) |
| 1311 | return rc; |
| 1312 | |
| 1313 | if (type & LOCKING_ANDX_SHARED_LOCK) |
| 1314 | posix_lock_type = CIFS_RDLCK; |
| 1315 | else |
| 1316 | posix_lock_type = CIFS_WRLCK; |
| 1317 | |
| 1318 | if (unlock == 1) |
| 1319 | posix_lock_type = CIFS_UNLCK; |
| 1320 | |
| 1321 | rc = CIFSSMBPosixLock(xid, tcon, netfid, current->tgid, |
| 1322 | 0 /* set */, length, flock, |
| 1323 | posix_lock_type, wait_flag); |
| 1324 | goto out; |
| 1325 | } |
| 1326 | |
| 1327 | if (lock) { |
| 1328 | struct cifsLockInfo *lock; |
| 1329 | |
| 1330 | lock = cifs_lock_init(flock->fl_start, length, type, netfid); |
| 1331 | if (!lock) |
| 1332 | return -ENOMEM; |
| 1333 | |
| 1334 | rc = cifs_lock_add_if(cinode, lock, wait_flag); |
| 1335 | if (rc < 0) |
| 1336 | kfree(lock); |
| 1337 | if (rc <= 0) |
| 1338 | goto out; |
| 1339 | |
| 1340 | rc = CIFSSMBLock(xid, tcon, netfid, current->tgid, length, |
| 1341 | flock->fl_start, 0, 1, type, wait_flag, 0); |
| 1342 | if (rc) { |
| 1343 | kfree(lock); |
| 1344 | goto out; |
| 1345 | } |
| 1346 | |
| 1347 | cifs_lock_add(cinode, lock); |
| 1348 | } else if (unlock) |
| 1349 | rc = cifs_unlock_range(cfile, flock, xid); |
| 1350 | |
| 1351 | out: |
| 1352 | if (flock->fl_flags & FL_POSIX) |
| 1353 | posix_lock_file_wait(file, flock); |
| 1354 | return rc; |
| 1355 | } |
| 1356 | |
| 1357 | int cifs_lock(struct file *file, int cmd, struct file_lock *flock) |
| 1358 | { |
| 1359 | int rc, xid; |
| 1360 | int lock = 0, unlock = 0; |
| 1361 | bool wait_flag = false; |
| 1362 | bool posix_lck = false; |
| 1363 | struct cifs_sb_info *cifs_sb; |
| 1364 | struct cifs_tcon *tcon; |
| 1365 | struct cifsInodeInfo *cinode; |
| 1366 | struct cifsFileInfo *cfile; |
| 1367 | __u16 netfid; |
| 1368 | __u8 type; |
| 1369 | |
| 1370 | rc = -EACCES; |
| 1371 | xid = GetXid(); |
| 1372 | |
| 1373 | cFYI(1, "Lock parm: 0x%x flockflags: 0x%x flocktype: 0x%x start: %lld " |
| 1374 | "end: %lld", cmd, flock->fl_flags, flock->fl_type, |
| 1375 | flock->fl_start, flock->fl_end); |
| 1376 | |
| 1377 | cifs_read_flock(flock, &type, &lock, &unlock, &wait_flag); |
| 1378 | |
| 1379 | cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); |
| 1380 | cfile = (struct cifsFileInfo *)file->private_data; |
| 1381 | tcon = tlink_tcon(cfile->tlink); |
| 1382 | netfid = cfile->netfid; |
| 1383 | cinode = CIFS_I(file->f_path.dentry->d_inode); |
| 1384 | |
| 1385 | if ((tcon->ses->capabilities & CAP_UNIX) && |
| 1386 | (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) && |
| 1387 | ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0)) |
| 1388 | posix_lck = true; |
| 1389 | /* |
| 1390 | * BB add code here to normalize offset and length to account for |
| 1391 | * negative length which we can not accept over the wire. |
| 1392 | */ |
| 1393 | if (IS_GETLK(cmd)) { |
| 1394 | rc = cifs_getlk(file, flock, type, wait_flag, posix_lck, xid); |
| 1395 | FreeXid(xid); |
| 1396 | return rc; |
| 1397 | } |
| 1398 | |
| 1399 | if (!lock && !unlock) { |
| 1400 | /* |
| 1401 | * if no lock or unlock then nothing to do since we do not |
| 1402 | * know what it is |
| 1403 | */ |
| 1404 | FreeXid(xid); |
| 1405 | return -EOPNOTSUPP; |
| 1406 | } |
| 1407 | |
| 1408 | rc = cifs_setlk(file, flock, type, wait_flag, posix_lck, lock, unlock, |
| 1409 | xid); |
| 1410 | FreeXid(xid); |
| 1411 | return rc; |
| 1412 | } |
| 1413 | |
| 1414 | /* |
| 1415 | * update the file size (if needed) after a write. Should be called with |
| 1416 | * the inode->i_lock held |
| 1417 | */ |
| 1418 | void |
| 1419 | cifs_update_eof(struct cifsInodeInfo *cifsi, loff_t offset, |
| 1420 | unsigned int bytes_written) |
| 1421 | { |
| 1422 | loff_t end_of_write = offset + bytes_written; |
| 1423 | |
| 1424 | if (end_of_write > cifsi->server_eof) |
| 1425 | cifsi->server_eof = end_of_write; |
| 1426 | } |
| 1427 | |
| 1428 | static ssize_t cifs_write(struct cifsFileInfo *open_file, __u32 pid, |
| 1429 | const char *write_data, size_t write_size, |
| 1430 | loff_t *poffset) |
| 1431 | { |
| 1432 | int rc = 0; |
| 1433 | unsigned int bytes_written = 0; |
| 1434 | unsigned int total_written; |
| 1435 | struct cifs_sb_info *cifs_sb; |
| 1436 | struct cifs_tcon *pTcon; |
| 1437 | int xid; |
| 1438 | struct dentry *dentry = open_file->dentry; |
| 1439 | struct cifsInodeInfo *cifsi = CIFS_I(dentry->d_inode); |
| 1440 | struct cifs_io_parms io_parms; |
| 1441 | |
| 1442 | cifs_sb = CIFS_SB(dentry->d_sb); |
| 1443 | |
| 1444 | cFYI(1, "write %zd bytes to offset %lld of %s", write_size, |
| 1445 | *poffset, dentry->d_name.name); |
| 1446 | |
| 1447 | pTcon = tlink_tcon(open_file->tlink); |
| 1448 | |
| 1449 | xid = GetXid(); |
| 1450 | |
| 1451 | for (total_written = 0; write_size > total_written; |
| 1452 | total_written += bytes_written) { |
| 1453 | rc = -EAGAIN; |
| 1454 | while (rc == -EAGAIN) { |
| 1455 | struct kvec iov[2]; |
| 1456 | unsigned int len; |
| 1457 | |
| 1458 | if (open_file->invalidHandle) { |
| 1459 | /* we could deadlock if we called |
| 1460 | filemap_fdatawait from here so tell |
| 1461 | reopen_file not to flush data to |
| 1462 | server now */ |
| 1463 | rc = cifs_reopen_file(open_file, false); |
| 1464 | if (rc != 0) |
| 1465 | break; |
| 1466 | } |
| 1467 | |
| 1468 | len = min((size_t)cifs_sb->wsize, |
| 1469 | write_size - total_written); |
| 1470 | /* iov[0] is reserved for smb header */ |
| 1471 | iov[1].iov_base = (char *)write_data + total_written; |
| 1472 | iov[1].iov_len = len; |
| 1473 | io_parms.netfid = open_file->netfid; |
| 1474 | io_parms.pid = pid; |
| 1475 | io_parms.tcon = pTcon; |
| 1476 | io_parms.offset = *poffset; |
| 1477 | io_parms.length = len; |
| 1478 | rc = CIFSSMBWrite2(xid, &io_parms, &bytes_written, iov, |
| 1479 | 1, 0); |
| 1480 | } |
| 1481 | if (rc || (bytes_written == 0)) { |
| 1482 | if (total_written) |
| 1483 | break; |
| 1484 | else { |
| 1485 | FreeXid(xid); |
| 1486 | return rc; |
| 1487 | } |
| 1488 | } else { |
| 1489 | spin_lock(&dentry->d_inode->i_lock); |
| 1490 | cifs_update_eof(cifsi, *poffset, bytes_written); |
| 1491 | spin_unlock(&dentry->d_inode->i_lock); |
| 1492 | *poffset += bytes_written; |
| 1493 | } |
| 1494 | } |
| 1495 | |
| 1496 | cifs_stats_bytes_written(pTcon, total_written); |
| 1497 | |
| 1498 | if (total_written > 0) { |
| 1499 | spin_lock(&dentry->d_inode->i_lock); |
| 1500 | if (*poffset > dentry->d_inode->i_size) |
| 1501 | i_size_write(dentry->d_inode, *poffset); |
| 1502 | spin_unlock(&dentry->d_inode->i_lock); |
| 1503 | } |
| 1504 | mark_inode_dirty_sync(dentry->d_inode); |
| 1505 | FreeXid(xid); |
| 1506 | return total_written; |
| 1507 | } |
| 1508 | |
| 1509 | struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode, |
| 1510 | bool fsuid_only) |
| 1511 | { |
| 1512 | struct cifsFileInfo *open_file = NULL; |
| 1513 | struct cifs_sb_info *cifs_sb = CIFS_SB(cifs_inode->vfs_inode.i_sb); |
| 1514 | |
| 1515 | /* only filter by fsuid on multiuser mounts */ |
| 1516 | if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER)) |
| 1517 | fsuid_only = false; |
| 1518 | |
| 1519 | spin_lock(&cifs_file_list_lock); |
| 1520 | /* we could simply get the first_list_entry since write-only entries |
| 1521 | are always at the end of the list but since the first entry might |
| 1522 | have a close pending, we go through the whole list */ |
| 1523 | list_for_each_entry(open_file, &cifs_inode->openFileList, flist) { |
| 1524 | if (fsuid_only && open_file->uid != current_fsuid()) |
| 1525 | continue; |
| 1526 | if (OPEN_FMODE(open_file->f_flags) & FMODE_READ) { |
| 1527 | if (!open_file->invalidHandle) { |
| 1528 | /* found a good file */ |
| 1529 | /* lock it so it will not be closed on us */ |
| 1530 | cifsFileInfo_get(open_file); |
| 1531 | spin_unlock(&cifs_file_list_lock); |
| 1532 | return open_file; |
| 1533 | } /* else might as well continue, and look for |
| 1534 | another, or simply have the caller reopen it |
| 1535 | again rather than trying to fix this handle */ |
| 1536 | } else /* write only file */ |
| 1537 | break; /* write only files are last so must be done */ |
| 1538 | } |
| 1539 | spin_unlock(&cifs_file_list_lock); |
| 1540 | return NULL; |
| 1541 | } |
| 1542 | |
| 1543 | struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode, |
| 1544 | bool fsuid_only) |
| 1545 | { |
| 1546 | struct cifsFileInfo *open_file, *inv_file = NULL; |
| 1547 | struct cifs_sb_info *cifs_sb; |
| 1548 | bool any_available = false; |
| 1549 | int rc; |
| 1550 | unsigned int refind = 0; |
| 1551 | |
| 1552 | /* Having a null inode here (because mapping->host was set to zero by |
| 1553 | the VFS or MM) should not happen but we had reports of on oops (due to |
| 1554 | it being zero) during stress testcases so we need to check for it */ |
| 1555 | |
| 1556 | if (cifs_inode == NULL) { |
| 1557 | cERROR(1, "Null inode passed to cifs_writeable_file"); |
| 1558 | dump_stack(); |
| 1559 | return NULL; |
| 1560 | } |
| 1561 | |
| 1562 | cifs_sb = CIFS_SB(cifs_inode->vfs_inode.i_sb); |
| 1563 | |
| 1564 | /* only filter by fsuid on multiuser mounts */ |
| 1565 | if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER)) |
| 1566 | fsuid_only = false; |
| 1567 | |
| 1568 | spin_lock(&cifs_file_list_lock); |
| 1569 | refind_writable: |
| 1570 | if (refind > MAX_REOPEN_ATT) { |
| 1571 | spin_unlock(&cifs_file_list_lock); |
| 1572 | return NULL; |
| 1573 | } |
| 1574 | list_for_each_entry(open_file, &cifs_inode->openFileList, flist) { |
| 1575 | if (!any_available && open_file->pid != current->tgid) |
| 1576 | continue; |
| 1577 | if (fsuid_only && open_file->uid != current_fsuid()) |
| 1578 | continue; |
| 1579 | if (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE) { |
| 1580 | if (!open_file->invalidHandle) { |
| 1581 | /* found a good writable file */ |
| 1582 | cifsFileInfo_get(open_file); |
| 1583 | spin_unlock(&cifs_file_list_lock); |
| 1584 | return open_file; |
| 1585 | } else { |
| 1586 | if (!inv_file) |
| 1587 | inv_file = open_file; |
| 1588 | } |
| 1589 | } |
| 1590 | } |
| 1591 | /* couldn't find useable FH with same pid, try any available */ |
| 1592 | if (!any_available) { |
| 1593 | any_available = true; |
| 1594 | goto refind_writable; |
| 1595 | } |
| 1596 | |
| 1597 | if (inv_file) { |
| 1598 | any_available = false; |
| 1599 | cifsFileInfo_get(inv_file); |
| 1600 | } |
| 1601 | |
| 1602 | spin_unlock(&cifs_file_list_lock); |
| 1603 | |
| 1604 | if (inv_file) { |
| 1605 | rc = cifs_reopen_file(inv_file, false); |
| 1606 | if (!rc) |
| 1607 | return inv_file; |
| 1608 | else { |
| 1609 | spin_lock(&cifs_file_list_lock); |
| 1610 | list_move_tail(&inv_file->flist, |
| 1611 | &cifs_inode->openFileList); |
| 1612 | spin_unlock(&cifs_file_list_lock); |
| 1613 | cifsFileInfo_put(inv_file); |
| 1614 | spin_lock(&cifs_file_list_lock); |
| 1615 | ++refind; |
| 1616 | inv_file = NULL; |
| 1617 | goto refind_writable; |
| 1618 | } |
| 1619 | } |
| 1620 | |
| 1621 | return NULL; |
| 1622 | } |
| 1623 | |
| 1624 | static int cifs_partialpagewrite(struct page *page, unsigned from, unsigned to) |
| 1625 | { |
| 1626 | struct address_space *mapping = page->mapping; |
| 1627 | loff_t offset = (loff_t)page->index << PAGE_CACHE_SHIFT; |
| 1628 | char *write_data; |
| 1629 | int rc = -EFAULT; |
| 1630 | int bytes_written = 0; |
| 1631 | struct inode *inode; |
| 1632 | struct cifsFileInfo *open_file; |
| 1633 | |
| 1634 | if (!mapping || !mapping->host) |
| 1635 | return -EFAULT; |
| 1636 | |
| 1637 | inode = page->mapping->host; |
| 1638 | |
| 1639 | offset += (loff_t)from; |
| 1640 | write_data = kmap(page); |
| 1641 | write_data += from; |
| 1642 | |
| 1643 | if ((to > PAGE_CACHE_SIZE) || (from > to)) { |
| 1644 | kunmap(page); |
| 1645 | return -EIO; |
| 1646 | } |
| 1647 | |
| 1648 | /* racing with truncate? */ |
| 1649 | if (offset > mapping->host->i_size) { |
| 1650 | kunmap(page); |
| 1651 | return 0; /* don't care */ |
| 1652 | } |
| 1653 | |
| 1654 | /* check to make sure that we are not extending the file */ |
| 1655 | if (mapping->host->i_size - offset < (loff_t)to) |
| 1656 | to = (unsigned)(mapping->host->i_size - offset); |
| 1657 | |
| 1658 | open_file = find_writable_file(CIFS_I(mapping->host), false); |
| 1659 | if (open_file) { |
| 1660 | bytes_written = cifs_write(open_file, open_file->pid, |
| 1661 | write_data, to - from, &offset); |
| 1662 | cifsFileInfo_put(open_file); |
| 1663 | /* Does mm or vfs already set times? */ |
| 1664 | inode->i_atime = inode->i_mtime = current_fs_time(inode->i_sb); |
| 1665 | if ((bytes_written > 0) && (offset)) |
| 1666 | rc = 0; |
| 1667 | else if (bytes_written < 0) |
| 1668 | rc = bytes_written; |
| 1669 | } else { |
| 1670 | cFYI(1, "No writeable filehandles for inode"); |
| 1671 | rc = -EIO; |
| 1672 | } |
| 1673 | |
| 1674 | kunmap(page); |
| 1675 | return rc; |
| 1676 | } |
| 1677 | |
| 1678 | /* |
| 1679 | * Marshal up the iov array, reserving the first one for the header. Also, |
| 1680 | * set wdata->bytes. |
| 1681 | */ |
| 1682 | static void |
| 1683 | cifs_writepages_marshal_iov(struct kvec *iov, struct cifs_writedata *wdata) |
| 1684 | { |
| 1685 | int i; |
| 1686 | struct inode *inode = wdata->cfile->dentry->d_inode; |
| 1687 | loff_t size = i_size_read(inode); |
| 1688 | |
| 1689 | /* marshal up the pages into iov array */ |
| 1690 | wdata->bytes = 0; |
| 1691 | for (i = 0; i < wdata->nr_pages; i++) { |
| 1692 | iov[i + 1].iov_len = min(size - page_offset(wdata->pages[i]), |
| 1693 | (loff_t)PAGE_CACHE_SIZE); |
| 1694 | iov[i + 1].iov_base = kmap(wdata->pages[i]); |
| 1695 | wdata->bytes += iov[i + 1].iov_len; |
| 1696 | } |
| 1697 | } |
| 1698 | |
| 1699 | static int cifs_writepages(struct address_space *mapping, |
| 1700 | struct writeback_control *wbc) |
| 1701 | { |
| 1702 | struct cifs_sb_info *cifs_sb = CIFS_SB(mapping->host->i_sb); |
| 1703 | bool done = false, scanned = false, range_whole = false; |
| 1704 | pgoff_t end, index; |
| 1705 | struct cifs_writedata *wdata; |
| 1706 | struct page *page; |
| 1707 | int rc = 0; |
| 1708 | |
| 1709 | /* |
| 1710 | * If wsize is smaller than the page cache size, default to writing |
| 1711 | * one page at a time via cifs_writepage |
| 1712 | */ |
| 1713 | if (cifs_sb->wsize < PAGE_CACHE_SIZE) |
| 1714 | return generic_writepages(mapping, wbc); |
| 1715 | |
| 1716 | if (wbc->range_cyclic) { |
| 1717 | index = mapping->writeback_index; /* Start from prev offset */ |
| 1718 | end = -1; |
| 1719 | } else { |
| 1720 | index = wbc->range_start >> PAGE_CACHE_SHIFT; |
| 1721 | end = wbc->range_end >> PAGE_CACHE_SHIFT; |
| 1722 | if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) |
| 1723 | range_whole = true; |
| 1724 | scanned = true; |
| 1725 | } |
| 1726 | retry: |
| 1727 | while (!done && index <= end) { |
| 1728 | unsigned int i, nr_pages, found_pages; |
| 1729 | pgoff_t next = 0, tofind; |
| 1730 | struct page **pages; |
| 1731 | |
| 1732 | tofind = min((cifs_sb->wsize / PAGE_CACHE_SIZE) - 1, |
| 1733 | end - index) + 1; |
| 1734 | |
| 1735 | wdata = cifs_writedata_alloc((unsigned int)tofind, |
| 1736 | cifs_writev_complete); |
| 1737 | if (!wdata) { |
| 1738 | rc = -ENOMEM; |
| 1739 | break; |
| 1740 | } |
| 1741 | |
| 1742 | /* |
| 1743 | * find_get_pages_tag seems to return a max of 256 on each |
| 1744 | * iteration, so we must call it several times in order to |
| 1745 | * fill the array or the wsize is effectively limited to |
| 1746 | * 256 * PAGE_CACHE_SIZE. |
| 1747 | */ |
| 1748 | found_pages = 0; |
| 1749 | pages = wdata->pages; |
| 1750 | do { |
| 1751 | nr_pages = find_get_pages_tag(mapping, &index, |
| 1752 | PAGECACHE_TAG_DIRTY, |
| 1753 | tofind, pages); |
| 1754 | found_pages += nr_pages; |
| 1755 | tofind -= nr_pages; |
| 1756 | pages += nr_pages; |
| 1757 | } while (nr_pages && tofind && index <= end); |
| 1758 | |
| 1759 | if (found_pages == 0) { |
| 1760 | kref_put(&wdata->refcount, cifs_writedata_release); |
| 1761 | break; |
| 1762 | } |
| 1763 | |
| 1764 | nr_pages = 0; |
| 1765 | for (i = 0; i < found_pages; i++) { |
| 1766 | page = wdata->pages[i]; |
| 1767 | /* |
| 1768 | * At this point we hold neither mapping->tree_lock nor |
| 1769 | * lock on the page itself: the page may be truncated or |
| 1770 | * invalidated (changing page->mapping to NULL), or even |
| 1771 | * swizzled back from swapper_space to tmpfs file |
| 1772 | * mapping |
| 1773 | */ |
| 1774 | |
| 1775 | if (nr_pages == 0) |
| 1776 | lock_page(page); |
| 1777 | else if (!trylock_page(page)) |
| 1778 | break; |
| 1779 | |
| 1780 | if (unlikely(page->mapping != mapping)) { |
| 1781 | unlock_page(page); |
| 1782 | break; |
| 1783 | } |
| 1784 | |
| 1785 | if (!wbc->range_cyclic && page->index > end) { |
| 1786 | done = true; |
| 1787 | unlock_page(page); |
| 1788 | break; |
| 1789 | } |
| 1790 | |
| 1791 | if (next && (page->index != next)) { |
| 1792 | /* Not next consecutive page */ |
| 1793 | unlock_page(page); |
| 1794 | break; |
| 1795 | } |
| 1796 | |
| 1797 | if (wbc->sync_mode != WB_SYNC_NONE) |
| 1798 | wait_on_page_writeback(page); |
| 1799 | |
| 1800 | if (PageWriteback(page) || |
| 1801 | !clear_page_dirty_for_io(page)) { |
| 1802 | unlock_page(page); |
| 1803 | break; |
| 1804 | } |
| 1805 | |
| 1806 | /* |
| 1807 | * This actually clears the dirty bit in the radix tree. |
| 1808 | * See cifs_writepage() for more commentary. |
| 1809 | */ |
| 1810 | set_page_writeback(page); |
| 1811 | |
| 1812 | if (page_offset(page) >= mapping->host->i_size) { |
| 1813 | done = true; |
| 1814 | unlock_page(page); |
| 1815 | end_page_writeback(page); |
| 1816 | break; |
| 1817 | } |
| 1818 | |
| 1819 | wdata->pages[i] = page; |
| 1820 | next = page->index + 1; |
| 1821 | ++nr_pages; |
| 1822 | } |
| 1823 | |
| 1824 | /* reset index to refind any pages skipped */ |
| 1825 | if (nr_pages == 0) |
| 1826 | index = wdata->pages[0]->index + 1; |
| 1827 | |
| 1828 | /* put any pages we aren't going to use */ |
| 1829 | for (i = nr_pages; i < found_pages; i++) { |
| 1830 | page_cache_release(wdata->pages[i]); |
| 1831 | wdata->pages[i] = NULL; |
| 1832 | } |
| 1833 | |
| 1834 | /* nothing to write? */ |
| 1835 | if (nr_pages == 0) { |
| 1836 | kref_put(&wdata->refcount, cifs_writedata_release); |
| 1837 | continue; |
| 1838 | } |
| 1839 | |
| 1840 | wdata->sync_mode = wbc->sync_mode; |
| 1841 | wdata->nr_pages = nr_pages; |
| 1842 | wdata->offset = page_offset(wdata->pages[0]); |
| 1843 | wdata->marshal_iov = cifs_writepages_marshal_iov; |
| 1844 | |
| 1845 | do { |
| 1846 | if (wdata->cfile != NULL) |
| 1847 | cifsFileInfo_put(wdata->cfile); |
| 1848 | wdata->cfile = find_writable_file(CIFS_I(mapping->host), |
| 1849 | false); |
| 1850 | if (!wdata->cfile) { |
| 1851 | cERROR(1, "No writable handles for inode"); |
| 1852 | rc = -EBADF; |
| 1853 | break; |
| 1854 | } |
| 1855 | wdata->pid = wdata->cfile->pid; |
| 1856 | rc = cifs_async_writev(wdata); |
| 1857 | } while (wbc->sync_mode == WB_SYNC_ALL && rc == -EAGAIN); |
| 1858 | |
| 1859 | for (i = 0; i < nr_pages; ++i) |
| 1860 | unlock_page(wdata->pages[i]); |
| 1861 | |
| 1862 | /* send failure -- clean up the mess */ |
| 1863 | if (rc != 0) { |
| 1864 | for (i = 0; i < nr_pages; ++i) { |
| 1865 | if (rc == -EAGAIN) |
| 1866 | redirty_page_for_writepage(wbc, |
| 1867 | wdata->pages[i]); |
| 1868 | else |
| 1869 | SetPageError(wdata->pages[i]); |
| 1870 | end_page_writeback(wdata->pages[i]); |
| 1871 | page_cache_release(wdata->pages[i]); |
| 1872 | } |
| 1873 | if (rc != -EAGAIN) |
| 1874 | mapping_set_error(mapping, rc); |
| 1875 | } |
| 1876 | kref_put(&wdata->refcount, cifs_writedata_release); |
| 1877 | |
| 1878 | wbc->nr_to_write -= nr_pages; |
| 1879 | if (wbc->nr_to_write <= 0) |
| 1880 | done = true; |
| 1881 | |
| 1882 | index = next; |
| 1883 | } |
| 1884 | |
| 1885 | if (!scanned && !done) { |
| 1886 | /* |
| 1887 | * We hit the last page and there is more work to be done: wrap |
| 1888 | * back to the start of the file |
| 1889 | */ |
| 1890 | scanned = true; |
| 1891 | index = 0; |
| 1892 | goto retry; |
| 1893 | } |
| 1894 | |
| 1895 | if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0)) |
| 1896 | mapping->writeback_index = index; |
| 1897 | |
| 1898 | return rc; |
| 1899 | } |
| 1900 | |
| 1901 | static int |
| 1902 | cifs_writepage_locked(struct page *page, struct writeback_control *wbc) |
| 1903 | { |
| 1904 | int rc; |
| 1905 | int xid; |
| 1906 | |
| 1907 | xid = GetXid(); |
| 1908 | /* BB add check for wbc flags */ |
| 1909 | page_cache_get(page); |
| 1910 | if (!PageUptodate(page)) |
| 1911 | cFYI(1, "ppw - page not up to date"); |
| 1912 | |
| 1913 | /* |
| 1914 | * Set the "writeback" flag, and clear "dirty" in the radix tree. |
| 1915 | * |
| 1916 | * A writepage() implementation always needs to do either this, |
| 1917 | * or re-dirty the page with "redirty_page_for_writepage()" in |
| 1918 | * the case of a failure. |
| 1919 | * |
| 1920 | * Just unlocking the page will cause the radix tree tag-bits |
| 1921 | * to fail to update with the state of the page correctly. |
| 1922 | */ |
| 1923 | set_page_writeback(page); |
| 1924 | retry_write: |
| 1925 | rc = cifs_partialpagewrite(page, 0, PAGE_CACHE_SIZE); |
| 1926 | if (rc == -EAGAIN && wbc->sync_mode == WB_SYNC_ALL) |
| 1927 | goto retry_write; |
| 1928 | else if (rc == -EAGAIN) |
| 1929 | redirty_page_for_writepage(wbc, page); |
| 1930 | else if (rc != 0) |
| 1931 | SetPageError(page); |
| 1932 | else |
| 1933 | SetPageUptodate(page); |
| 1934 | end_page_writeback(page); |
| 1935 | page_cache_release(page); |
| 1936 | FreeXid(xid); |
| 1937 | return rc; |
| 1938 | } |
| 1939 | |
| 1940 | static int cifs_writepage(struct page *page, struct writeback_control *wbc) |
| 1941 | { |
| 1942 | int rc = cifs_writepage_locked(page, wbc); |
| 1943 | unlock_page(page); |
| 1944 | return rc; |
| 1945 | } |
| 1946 | |
| 1947 | static int cifs_write_end(struct file *file, struct address_space *mapping, |
| 1948 | loff_t pos, unsigned len, unsigned copied, |
| 1949 | struct page *page, void *fsdata) |
| 1950 | { |
| 1951 | int rc; |
| 1952 | struct inode *inode = mapping->host; |
| 1953 | struct cifsFileInfo *cfile = file->private_data; |
| 1954 | struct cifs_sb_info *cifs_sb = CIFS_SB(cfile->dentry->d_sb); |
| 1955 | __u32 pid; |
| 1956 | |
| 1957 | if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD) |
| 1958 | pid = cfile->pid; |
| 1959 | else |
| 1960 | pid = current->tgid; |
| 1961 | |
| 1962 | cFYI(1, "write_end for page %p from pos %lld with %d bytes", |
| 1963 | page, pos, copied); |
| 1964 | |
| 1965 | if (PageChecked(page)) { |
| 1966 | if (copied == len) |
| 1967 | SetPageUptodate(page); |
| 1968 | ClearPageChecked(page); |
| 1969 | } else if (!PageUptodate(page) && copied == PAGE_CACHE_SIZE) |
| 1970 | SetPageUptodate(page); |
| 1971 | |
| 1972 | if (!PageUptodate(page)) { |
| 1973 | char *page_data; |
| 1974 | unsigned offset = pos & (PAGE_CACHE_SIZE - 1); |
| 1975 | int xid; |
| 1976 | |
| 1977 | xid = GetXid(); |
| 1978 | /* this is probably better than directly calling |
| 1979 | partialpage_write since in this function the file handle is |
| 1980 | known which we might as well leverage */ |
| 1981 | /* BB check if anything else missing out of ppw |
| 1982 | such as updating last write time */ |
| 1983 | page_data = kmap(page); |
| 1984 | rc = cifs_write(cfile, pid, page_data + offset, copied, &pos); |
| 1985 | /* if (rc < 0) should we set writebehind rc? */ |
| 1986 | kunmap(page); |
| 1987 | |
| 1988 | FreeXid(xid); |
| 1989 | } else { |
| 1990 | rc = copied; |
| 1991 | pos += copied; |
| 1992 | set_page_dirty(page); |
| 1993 | } |
| 1994 | |
| 1995 | if (rc > 0) { |
| 1996 | spin_lock(&inode->i_lock); |
| 1997 | if (pos > inode->i_size) |
| 1998 | i_size_write(inode, pos); |
| 1999 | spin_unlock(&inode->i_lock); |
| 2000 | } |
| 2001 | |
| 2002 | unlock_page(page); |
| 2003 | page_cache_release(page); |
| 2004 | |
| 2005 | return rc; |
| 2006 | } |
| 2007 | |
| 2008 | int cifs_strict_fsync(struct file *file, loff_t start, loff_t end, |
| 2009 | int datasync) |
| 2010 | { |
| 2011 | int xid; |
| 2012 | int rc = 0; |
| 2013 | struct cifs_tcon *tcon; |
| 2014 | struct cifsFileInfo *smbfile = file->private_data; |
| 2015 | struct inode *inode = file->f_path.dentry->d_inode; |
| 2016 | struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); |
| 2017 | |
| 2018 | rc = filemap_write_and_wait_range(inode->i_mapping, start, end); |
| 2019 | if (rc) |
| 2020 | return rc; |
| 2021 | mutex_lock(&inode->i_mutex); |
| 2022 | |
| 2023 | xid = GetXid(); |
| 2024 | |
| 2025 | cFYI(1, "Sync file - name: %s datasync: 0x%x", |
| 2026 | file->f_path.dentry->d_name.name, datasync); |
| 2027 | |
| 2028 | if (!CIFS_I(inode)->clientCanCacheRead) { |
| 2029 | rc = cifs_invalidate_mapping(inode); |
| 2030 | if (rc) { |
| 2031 | cFYI(1, "rc: %d during invalidate phase", rc); |
| 2032 | rc = 0; /* don't care about it in fsync */ |
| 2033 | } |
| 2034 | } |
| 2035 | |
| 2036 | tcon = tlink_tcon(smbfile->tlink); |
| 2037 | if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)) |
| 2038 | rc = CIFSSMBFlush(xid, tcon, smbfile->netfid); |
| 2039 | |
| 2040 | FreeXid(xid); |
| 2041 | mutex_unlock(&inode->i_mutex); |
| 2042 | return rc; |
| 2043 | } |
| 2044 | |
| 2045 | int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync) |
| 2046 | { |
| 2047 | int xid; |
| 2048 | int rc = 0; |
| 2049 | struct cifs_tcon *tcon; |
| 2050 | struct cifsFileInfo *smbfile = file->private_data; |
| 2051 | struct cifs_sb_info *cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); |
| 2052 | struct inode *inode = file->f_mapping->host; |
| 2053 | |
| 2054 | rc = filemap_write_and_wait_range(inode->i_mapping, start, end); |
| 2055 | if (rc) |
| 2056 | return rc; |
| 2057 | mutex_lock(&inode->i_mutex); |
| 2058 | |
| 2059 | xid = GetXid(); |
| 2060 | |
| 2061 | cFYI(1, "Sync file - name: %s datasync: 0x%x", |
| 2062 | file->f_path.dentry->d_name.name, datasync); |
| 2063 | |
| 2064 | tcon = tlink_tcon(smbfile->tlink); |
| 2065 | if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)) |
| 2066 | rc = CIFSSMBFlush(xid, tcon, smbfile->netfid); |
| 2067 | |
| 2068 | FreeXid(xid); |
| 2069 | mutex_unlock(&inode->i_mutex); |
| 2070 | return rc; |
| 2071 | } |
| 2072 | |
| 2073 | /* |
| 2074 | * As file closes, flush all cached write data for this inode checking |
| 2075 | * for write behind errors. |
| 2076 | */ |
| 2077 | int cifs_flush(struct file *file, fl_owner_t id) |
| 2078 | { |
| 2079 | struct inode *inode = file->f_path.dentry->d_inode; |
| 2080 | int rc = 0; |
| 2081 | |
| 2082 | if (file->f_mode & FMODE_WRITE) |
| 2083 | rc = filemap_write_and_wait(inode->i_mapping); |
| 2084 | |
| 2085 | cFYI(1, "Flush inode %p file %p rc %d", inode, file, rc); |
| 2086 | |
| 2087 | return rc; |
| 2088 | } |
| 2089 | |
| 2090 | static int |
| 2091 | cifs_write_allocate_pages(struct page **pages, unsigned long num_pages) |
| 2092 | { |
| 2093 | int rc = 0; |
| 2094 | unsigned long i; |
| 2095 | |
| 2096 | for (i = 0; i < num_pages; i++) { |
| 2097 | pages[i] = alloc_page(GFP_KERNEL|__GFP_HIGHMEM); |
| 2098 | if (!pages[i]) { |
| 2099 | /* |
| 2100 | * save number of pages we have already allocated and |
| 2101 | * return with ENOMEM error |
| 2102 | */ |
| 2103 | num_pages = i; |
| 2104 | rc = -ENOMEM; |
| 2105 | break; |
| 2106 | } |
| 2107 | } |
| 2108 | |
| 2109 | if (rc) { |
| 2110 | for (i = 0; i < num_pages; i++) |
| 2111 | put_page(pages[i]); |
| 2112 | } |
| 2113 | return rc; |
| 2114 | } |
| 2115 | |
| 2116 | static inline |
| 2117 | size_t get_numpages(const size_t wsize, const size_t len, size_t *cur_len) |
| 2118 | { |
| 2119 | size_t num_pages; |
| 2120 | size_t clen; |
| 2121 | |
| 2122 | clen = min_t(const size_t, len, wsize); |
| 2123 | num_pages = DIV_ROUND_UP(clen, PAGE_SIZE); |
| 2124 | |
| 2125 | if (cur_len) |
| 2126 | *cur_len = clen; |
| 2127 | |
| 2128 | return num_pages; |
| 2129 | } |
| 2130 | |
| 2131 | static void |
| 2132 | cifs_uncached_marshal_iov(struct kvec *iov, struct cifs_writedata *wdata) |
| 2133 | { |
| 2134 | int i; |
| 2135 | size_t bytes = wdata->bytes; |
| 2136 | |
| 2137 | /* marshal up the pages into iov array */ |
| 2138 | for (i = 0; i < wdata->nr_pages; i++) { |
| 2139 | iov[i + 1].iov_len = min_t(size_t, bytes, PAGE_SIZE); |
| 2140 | iov[i + 1].iov_base = kmap(wdata->pages[i]); |
| 2141 | bytes -= iov[i + 1].iov_len; |
| 2142 | } |
| 2143 | } |
| 2144 | |
| 2145 | static void |
| 2146 | cifs_uncached_writev_complete(struct work_struct *work) |
| 2147 | { |
| 2148 | int i; |
| 2149 | struct cifs_writedata *wdata = container_of(work, |
| 2150 | struct cifs_writedata, work); |
| 2151 | struct inode *inode = wdata->cfile->dentry->d_inode; |
| 2152 | struct cifsInodeInfo *cifsi = CIFS_I(inode); |
| 2153 | |
| 2154 | spin_lock(&inode->i_lock); |
| 2155 | cifs_update_eof(cifsi, wdata->offset, wdata->bytes); |
| 2156 | if (cifsi->server_eof > inode->i_size) |
| 2157 | i_size_write(inode, cifsi->server_eof); |
| 2158 | spin_unlock(&inode->i_lock); |
| 2159 | |
| 2160 | complete(&wdata->done); |
| 2161 | |
| 2162 | if (wdata->result != -EAGAIN) { |
| 2163 | for (i = 0; i < wdata->nr_pages; i++) |
| 2164 | put_page(wdata->pages[i]); |
| 2165 | } |
| 2166 | |
| 2167 | kref_put(&wdata->refcount, cifs_writedata_release); |
| 2168 | } |
| 2169 | |
| 2170 | /* attempt to send write to server, retry on any -EAGAIN errors */ |
| 2171 | static int |
| 2172 | cifs_uncached_retry_writev(struct cifs_writedata *wdata) |
| 2173 | { |
| 2174 | int rc; |
| 2175 | |
| 2176 | do { |
| 2177 | if (wdata->cfile->invalidHandle) { |
| 2178 | rc = cifs_reopen_file(wdata->cfile, false); |
| 2179 | if (rc != 0) |
| 2180 | continue; |
| 2181 | } |
| 2182 | rc = cifs_async_writev(wdata); |
| 2183 | } while (rc == -EAGAIN); |
| 2184 | |
| 2185 | return rc; |
| 2186 | } |
| 2187 | |
| 2188 | static ssize_t |
| 2189 | cifs_iovec_write(struct file *file, const struct iovec *iov, |
| 2190 | unsigned long nr_segs, loff_t *poffset) |
| 2191 | { |
| 2192 | unsigned long nr_pages, i; |
| 2193 | size_t bytes, copied, len, cur_len; |
| 2194 | ssize_t total_written = 0; |
| 2195 | loff_t offset; |
| 2196 | struct iov_iter it; |
| 2197 | struct cifsFileInfo *open_file; |
| 2198 | struct cifs_tcon *tcon; |
| 2199 | struct cifs_sb_info *cifs_sb; |
| 2200 | struct cifs_writedata *wdata, *tmp; |
| 2201 | struct list_head wdata_list; |
| 2202 | int rc; |
| 2203 | pid_t pid; |
| 2204 | |
| 2205 | len = iov_length(iov, nr_segs); |
| 2206 | if (!len) |
| 2207 | return 0; |
| 2208 | |
| 2209 | rc = generic_write_checks(file, poffset, &len, 0); |
| 2210 | if (rc) |
| 2211 | return rc; |
| 2212 | |
| 2213 | INIT_LIST_HEAD(&wdata_list); |
| 2214 | cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); |
| 2215 | open_file = file->private_data; |
| 2216 | tcon = tlink_tcon(open_file->tlink); |
| 2217 | offset = *poffset; |
| 2218 | |
| 2219 | if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD) |
| 2220 | pid = open_file->pid; |
| 2221 | else |
| 2222 | pid = current->tgid; |
| 2223 | |
| 2224 | iov_iter_init(&it, iov, nr_segs, len, 0); |
| 2225 | do { |
| 2226 | size_t save_len; |
| 2227 | |
| 2228 | nr_pages = get_numpages(cifs_sb->wsize, len, &cur_len); |
| 2229 | wdata = cifs_writedata_alloc(nr_pages, |
| 2230 | cifs_uncached_writev_complete); |
| 2231 | if (!wdata) { |
| 2232 | rc = -ENOMEM; |
| 2233 | break; |
| 2234 | } |
| 2235 | |
| 2236 | rc = cifs_write_allocate_pages(wdata->pages, nr_pages); |
| 2237 | if (rc) { |
| 2238 | kfree(wdata); |
| 2239 | break; |
| 2240 | } |
| 2241 | |
| 2242 | save_len = cur_len; |
| 2243 | for (i = 0; i < nr_pages; i++) { |
| 2244 | bytes = min_t(const size_t, cur_len, PAGE_SIZE); |
| 2245 | copied = iov_iter_copy_from_user(wdata->pages[i], &it, |
| 2246 | 0, bytes); |
| 2247 | cur_len -= copied; |
| 2248 | iov_iter_advance(&it, copied); |
| 2249 | /* |
| 2250 | * If we didn't copy as much as we expected, then that |
| 2251 | * may mean we trod into an unmapped area. Stop copying |
| 2252 | * at that point. On the next pass through the big |
| 2253 | * loop, we'll likely end up getting a zero-length |
| 2254 | * write and bailing out of it. |
| 2255 | */ |
| 2256 | if (copied < bytes) |
| 2257 | break; |
| 2258 | } |
| 2259 | cur_len = save_len - cur_len; |
| 2260 | |
| 2261 | /* |
| 2262 | * If we have no data to send, then that probably means that |
| 2263 | * the copy above failed altogether. That's most likely because |
| 2264 | * the address in the iovec was bogus. Set the rc to -EFAULT, |
| 2265 | * free anything we allocated and bail out. |
| 2266 | */ |
| 2267 | if (!cur_len) { |
| 2268 | for (i = 0; i < nr_pages; i++) |
| 2269 | put_page(wdata->pages[i]); |
| 2270 | kfree(wdata); |
| 2271 | rc = -EFAULT; |
| 2272 | break; |
| 2273 | } |
| 2274 | |
| 2275 | /* |
| 2276 | * i + 1 now represents the number of pages we actually used in |
| 2277 | * the copy phase above. Bring nr_pages down to that, and free |
| 2278 | * any pages that we didn't use. |
| 2279 | */ |
| 2280 | for ( ; nr_pages > i + 1; nr_pages--) |
| 2281 | put_page(wdata->pages[nr_pages - 1]); |
| 2282 | |
| 2283 | wdata->sync_mode = WB_SYNC_ALL; |
| 2284 | wdata->nr_pages = nr_pages; |
| 2285 | wdata->offset = (__u64)offset; |
| 2286 | wdata->cfile = cifsFileInfo_get(open_file); |
| 2287 | wdata->pid = pid; |
| 2288 | wdata->bytes = cur_len; |
| 2289 | wdata->marshal_iov = cifs_uncached_marshal_iov; |
| 2290 | rc = cifs_uncached_retry_writev(wdata); |
| 2291 | if (rc) { |
| 2292 | kref_put(&wdata->refcount, cifs_writedata_release); |
| 2293 | break; |
| 2294 | } |
| 2295 | |
| 2296 | list_add_tail(&wdata->list, &wdata_list); |
| 2297 | offset += cur_len; |
| 2298 | len -= cur_len; |
| 2299 | } while (len > 0); |
| 2300 | |
| 2301 | /* |
| 2302 | * If at least one write was successfully sent, then discard any rc |
| 2303 | * value from the later writes. If the other write succeeds, then |
| 2304 | * we'll end up returning whatever was written. If it fails, then |
| 2305 | * we'll get a new rc value from that. |
| 2306 | */ |
| 2307 | if (!list_empty(&wdata_list)) |
| 2308 | rc = 0; |
| 2309 | |
| 2310 | /* |
| 2311 | * Wait for and collect replies for any successful sends in order of |
| 2312 | * increasing offset. Once an error is hit or we get a fatal signal |
| 2313 | * while waiting, then return without waiting for any more replies. |
| 2314 | */ |
| 2315 | restart_loop: |
| 2316 | list_for_each_entry_safe(wdata, tmp, &wdata_list, list) { |
| 2317 | if (!rc) { |
| 2318 | /* FIXME: freezable too? */ |
| 2319 | rc = wait_for_completion_killable(&wdata->done); |
| 2320 | if (rc) |
| 2321 | rc = -EINTR; |
| 2322 | else if (wdata->result) |
| 2323 | rc = wdata->result; |
| 2324 | else |
| 2325 | total_written += wdata->bytes; |
| 2326 | |
| 2327 | /* resend call if it's a retryable error */ |
| 2328 | if (rc == -EAGAIN) { |
| 2329 | rc = cifs_uncached_retry_writev(wdata); |
| 2330 | goto restart_loop; |
| 2331 | } |
| 2332 | } |
| 2333 | list_del_init(&wdata->list); |
| 2334 | kref_put(&wdata->refcount, cifs_writedata_release); |
| 2335 | } |
| 2336 | |
| 2337 | if (total_written > 0) |
| 2338 | *poffset += total_written; |
| 2339 | |
| 2340 | cifs_stats_bytes_written(tcon, total_written); |
| 2341 | return total_written ? total_written : (ssize_t)rc; |
| 2342 | } |
| 2343 | |
| 2344 | ssize_t cifs_user_writev(struct kiocb *iocb, const struct iovec *iov, |
| 2345 | unsigned long nr_segs, loff_t pos) |
| 2346 | { |
| 2347 | ssize_t written; |
| 2348 | struct inode *inode; |
| 2349 | |
| 2350 | inode = iocb->ki_filp->f_path.dentry->d_inode; |
| 2351 | |
| 2352 | /* |
| 2353 | * BB - optimize the way when signing is disabled. We can drop this |
| 2354 | * extra memory-to-memory copying and use iovec buffers for constructing |
| 2355 | * write request. |
| 2356 | */ |
| 2357 | |
| 2358 | written = cifs_iovec_write(iocb->ki_filp, iov, nr_segs, &pos); |
| 2359 | if (written > 0) { |
| 2360 | CIFS_I(inode)->invalid_mapping = true; |
| 2361 | iocb->ki_pos = pos; |
| 2362 | } |
| 2363 | |
| 2364 | return written; |
| 2365 | } |
| 2366 | |
| 2367 | ssize_t cifs_strict_writev(struct kiocb *iocb, const struct iovec *iov, |
| 2368 | unsigned long nr_segs, loff_t pos) |
| 2369 | { |
| 2370 | struct inode *inode; |
| 2371 | |
| 2372 | inode = iocb->ki_filp->f_path.dentry->d_inode; |
| 2373 | |
| 2374 | if (CIFS_I(inode)->clientCanCacheAll) |
| 2375 | return generic_file_aio_write(iocb, iov, nr_segs, pos); |
| 2376 | |
| 2377 | /* |
| 2378 | * In strict cache mode we need to write the data to the server exactly |
| 2379 | * from the pos to pos+len-1 rather than flush all affected pages |
| 2380 | * because it may cause a error with mandatory locks on these pages but |
| 2381 | * not on the region from pos to ppos+len-1. |
| 2382 | */ |
| 2383 | |
| 2384 | return cifs_user_writev(iocb, iov, nr_segs, pos); |
| 2385 | } |
| 2386 | |
| 2387 | static ssize_t |
| 2388 | cifs_iovec_read(struct file *file, const struct iovec *iov, |
| 2389 | unsigned long nr_segs, loff_t *poffset) |
| 2390 | { |
| 2391 | int rc; |
| 2392 | int xid; |
| 2393 | ssize_t total_read; |
| 2394 | unsigned int bytes_read = 0; |
| 2395 | size_t len, cur_len; |
| 2396 | int iov_offset = 0; |
| 2397 | struct cifs_sb_info *cifs_sb; |
| 2398 | struct cifs_tcon *pTcon; |
| 2399 | struct cifsFileInfo *open_file; |
| 2400 | struct smb_com_read_rsp *pSMBr; |
| 2401 | struct cifs_io_parms io_parms; |
| 2402 | char *read_data; |
| 2403 | unsigned int rsize; |
| 2404 | __u32 pid; |
| 2405 | |
| 2406 | if (!nr_segs) |
| 2407 | return 0; |
| 2408 | |
| 2409 | len = iov_length(iov, nr_segs); |
| 2410 | if (!len) |
| 2411 | return 0; |
| 2412 | |
| 2413 | xid = GetXid(); |
| 2414 | cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); |
| 2415 | |
| 2416 | /* FIXME: set up handlers for larger reads and/or convert to async */ |
| 2417 | rsize = min_t(unsigned int, cifs_sb->rsize, CIFSMaxBufSize); |
| 2418 | |
| 2419 | open_file = file->private_data; |
| 2420 | pTcon = tlink_tcon(open_file->tlink); |
| 2421 | |
| 2422 | if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD) |
| 2423 | pid = open_file->pid; |
| 2424 | else |
| 2425 | pid = current->tgid; |
| 2426 | |
| 2427 | if ((file->f_flags & O_ACCMODE) == O_WRONLY) |
| 2428 | cFYI(1, "attempting read on write only file instance"); |
| 2429 | |
| 2430 | for (total_read = 0; total_read < len; total_read += bytes_read) { |
| 2431 | cur_len = min_t(const size_t, len - total_read, rsize); |
| 2432 | rc = -EAGAIN; |
| 2433 | read_data = NULL; |
| 2434 | |
| 2435 | while (rc == -EAGAIN) { |
| 2436 | int buf_type = CIFS_NO_BUFFER; |
| 2437 | if (open_file->invalidHandle) { |
| 2438 | rc = cifs_reopen_file(open_file, true); |
| 2439 | if (rc != 0) |
| 2440 | break; |
| 2441 | } |
| 2442 | io_parms.netfid = open_file->netfid; |
| 2443 | io_parms.pid = pid; |
| 2444 | io_parms.tcon = pTcon; |
| 2445 | io_parms.offset = *poffset; |
| 2446 | io_parms.length = cur_len; |
| 2447 | rc = CIFSSMBRead(xid, &io_parms, &bytes_read, |
| 2448 | &read_data, &buf_type); |
| 2449 | pSMBr = (struct smb_com_read_rsp *)read_data; |
| 2450 | if (read_data) { |
| 2451 | char *data_offset = read_data + 4 + |
| 2452 | le16_to_cpu(pSMBr->DataOffset); |
| 2453 | if (memcpy_toiovecend(iov, data_offset, |
| 2454 | iov_offset, bytes_read)) |
| 2455 | rc = -EFAULT; |
| 2456 | if (buf_type == CIFS_SMALL_BUFFER) |
| 2457 | cifs_small_buf_release(read_data); |
| 2458 | else if (buf_type == CIFS_LARGE_BUFFER) |
| 2459 | cifs_buf_release(read_data); |
| 2460 | read_data = NULL; |
| 2461 | iov_offset += bytes_read; |
| 2462 | } |
| 2463 | } |
| 2464 | |
| 2465 | if (rc || (bytes_read == 0)) { |
| 2466 | if (total_read) { |
| 2467 | break; |
| 2468 | } else { |
| 2469 | FreeXid(xid); |
| 2470 | return rc; |
| 2471 | } |
| 2472 | } else { |
| 2473 | cifs_stats_bytes_read(pTcon, bytes_read); |
| 2474 | *poffset += bytes_read; |
| 2475 | } |
| 2476 | } |
| 2477 | |
| 2478 | FreeXid(xid); |
| 2479 | return total_read; |
| 2480 | } |
| 2481 | |
| 2482 | ssize_t cifs_user_readv(struct kiocb *iocb, const struct iovec *iov, |
| 2483 | unsigned long nr_segs, loff_t pos) |
| 2484 | { |
| 2485 | ssize_t read; |
| 2486 | |
| 2487 | read = cifs_iovec_read(iocb->ki_filp, iov, nr_segs, &pos); |
| 2488 | if (read > 0) |
| 2489 | iocb->ki_pos = pos; |
| 2490 | |
| 2491 | return read; |
| 2492 | } |
| 2493 | |
| 2494 | ssize_t cifs_strict_readv(struct kiocb *iocb, const struct iovec *iov, |
| 2495 | unsigned long nr_segs, loff_t pos) |
| 2496 | { |
| 2497 | struct inode *inode; |
| 2498 | |
| 2499 | inode = iocb->ki_filp->f_path.dentry->d_inode; |
| 2500 | |
| 2501 | if (CIFS_I(inode)->clientCanCacheRead) |
| 2502 | return generic_file_aio_read(iocb, iov, nr_segs, pos); |
| 2503 | |
| 2504 | /* |
| 2505 | * In strict cache mode we need to read from the server all the time |
| 2506 | * if we don't have level II oplock because the server can delay mtime |
| 2507 | * change - so we can't make a decision about inode invalidating. |
| 2508 | * And we can also fail with pagereading if there are mandatory locks |
| 2509 | * on pages affected by this read but not on the region from pos to |
| 2510 | * pos+len-1. |
| 2511 | */ |
| 2512 | |
| 2513 | return cifs_user_readv(iocb, iov, nr_segs, pos); |
| 2514 | } |
| 2515 | |
| 2516 | static ssize_t cifs_read(struct file *file, char *read_data, size_t read_size, |
| 2517 | loff_t *poffset) |
| 2518 | { |
| 2519 | int rc = -EACCES; |
| 2520 | unsigned int bytes_read = 0; |
| 2521 | unsigned int total_read; |
| 2522 | unsigned int current_read_size; |
| 2523 | unsigned int rsize; |
| 2524 | struct cifs_sb_info *cifs_sb; |
| 2525 | struct cifs_tcon *pTcon; |
| 2526 | int xid; |
| 2527 | char *current_offset; |
| 2528 | struct cifsFileInfo *open_file; |
| 2529 | struct cifs_io_parms io_parms; |
| 2530 | int buf_type = CIFS_NO_BUFFER; |
| 2531 | __u32 pid; |
| 2532 | |
| 2533 | xid = GetXid(); |
| 2534 | cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); |
| 2535 | |
| 2536 | /* FIXME: set up handlers for larger reads and/or convert to async */ |
| 2537 | rsize = min_t(unsigned int, cifs_sb->rsize, CIFSMaxBufSize); |
| 2538 | |
| 2539 | if (file->private_data == NULL) { |
| 2540 | rc = -EBADF; |
| 2541 | FreeXid(xid); |
| 2542 | return rc; |
| 2543 | } |
| 2544 | open_file = file->private_data; |
| 2545 | pTcon = tlink_tcon(open_file->tlink); |
| 2546 | |
| 2547 | if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD) |
| 2548 | pid = open_file->pid; |
| 2549 | else |
| 2550 | pid = current->tgid; |
| 2551 | |
| 2552 | if ((file->f_flags & O_ACCMODE) == O_WRONLY) |
| 2553 | cFYI(1, "attempting read on write only file instance"); |
| 2554 | |
| 2555 | for (total_read = 0, current_offset = read_data; |
| 2556 | read_size > total_read; |
| 2557 | total_read += bytes_read, current_offset += bytes_read) { |
| 2558 | current_read_size = min_t(uint, read_size - total_read, rsize); |
| 2559 | |
| 2560 | /* For windows me and 9x we do not want to request more |
| 2561 | than it negotiated since it will refuse the read then */ |
| 2562 | if ((pTcon->ses) && |
| 2563 | !(pTcon->ses->capabilities & CAP_LARGE_FILES)) { |
| 2564 | current_read_size = min_t(uint, current_read_size, |
| 2565 | CIFSMaxBufSize); |
| 2566 | } |
| 2567 | rc = -EAGAIN; |
| 2568 | while (rc == -EAGAIN) { |
| 2569 | if (open_file->invalidHandle) { |
| 2570 | rc = cifs_reopen_file(open_file, true); |
| 2571 | if (rc != 0) |
| 2572 | break; |
| 2573 | } |
| 2574 | io_parms.netfid = open_file->netfid; |
| 2575 | io_parms.pid = pid; |
| 2576 | io_parms.tcon = pTcon; |
| 2577 | io_parms.offset = *poffset; |
| 2578 | io_parms.length = current_read_size; |
| 2579 | rc = CIFSSMBRead(xid, &io_parms, &bytes_read, |
| 2580 | ¤t_offset, &buf_type); |
| 2581 | } |
| 2582 | if (rc || (bytes_read == 0)) { |
| 2583 | if (total_read) { |
| 2584 | break; |
| 2585 | } else { |
| 2586 | FreeXid(xid); |
| 2587 | return rc; |
| 2588 | } |
| 2589 | } else { |
| 2590 | cifs_stats_bytes_read(pTcon, total_read); |
| 2591 | *poffset += bytes_read; |
| 2592 | } |
| 2593 | } |
| 2594 | FreeXid(xid); |
| 2595 | return total_read; |
| 2596 | } |
| 2597 | |
| 2598 | /* |
| 2599 | * If the page is mmap'ed into a process' page tables, then we need to make |
| 2600 | * sure that it doesn't change while being written back. |
| 2601 | */ |
| 2602 | static int |
| 2603 | cifs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) |
| 2604 | { |
| 2605 | struct page *page = vmf->page; |
| 2606 | |
| 2607 | lock_page(page); |
| 2608 | return VM_FAULT_LOCKED; |
| 2609 | } |
| 2610 | |
| 2611 | static struct vm_operations_struct cifs_file_vm_ops = { |
| 2612 | .fault = filemap_fault, |
| 2613 | .page_mkwrite = cifs_page_mkwrite, |
| 2614 | }; |
| 2615 | |
| 2616 | int cifs_file_strict_mmap(struct file *file, struct vm_area_struct *vma) |
| 2617 | { |
| 2618 | int rc, xid; |
| 2619 | struct inode *inode = file->f_path.dentry->d_inode; |
| 2620 | |
| 2621 | xid = GetXid(); |
| 2622 | |
| 2623 | if (!CIFS_I(inode)->clientCanCacheRead) { |
| 2624 | rc = cifs_invalidate_mapping(inode); |
| 2625 | if (rc) |
| 2626 | return rc; |
| 2627 | } |
| 2628 | |
| 2629 | rc = generic_file_mmap(file, vma); |
| 2630 | if (rc == 0) |
| 2631 | vma->vm_ops = &cifs_file_vm_ops; |
| 2632 | FreeXid(xid); |
| 2633 | return rc; |
| 2634 | } |
| 2635 | |
| 2636 | int cifs_file_mmap(struct file *file, struct vm_area_struct *vma) |
| 2637 | { |
| 2638 | int rc, xid; |
| 2639 | |
| 2640 | xid = GetXid(); |
| 2641 | rc = cifs_revalidate_file(file); |
| 2642 | if (rc) { |
| 2643 | cFYI(1, "Validation prior to mmap failed, error=%d", rc); |
| 2644 | FreeXid(xid); |
| 2645 | return rc; |
| 2646 | } |
| 2647 | rc = generic_file_mmap(file, vma); |
| 2648 | if (rc == 0) |
| 2649 | vma->vm_ops = &cifs_file_vm_ops; |
| 2650 | FreeXid(xid); |
| 2651 | return rc; |
| 2652 | } |
| 2653 | |
| 2654 | static int cifs_readpages(struct file *file, struct address_space *mapping, |
| 2655 | struct list_head *page_list, unsigned num_pages) |
| 2656 | { |
| 2657 | int rc; |
| 2658 | struct list_head tmplist; |
| 2659 | struct cifsFileInfo *open_file = file->private_data; |
| 2660 | struct cifs_sb_info *cifs_sb = CIFS_SB(file->f_path.dentry->d_sb); |
| 2661 | unsigned int rsize = cifs_sb->rsize; |
| 2662 | pid_t pid; |
| 2663 | |
| 2664 | /* |
| 2665 | * Give up immediately if rsize is too small to read an entire page. |
| 2666 | * The VFS will fall back to readpage. We should never reach this |
| 2667 | * point however since we set ra_pages to 0 when the rsize is smaller |
| 2668 | * than a cache page. |
| 2669 | */ |
| 2670 | if (unlikely(rsize < PAGE_CACHE_SIZE)) |
| 2671 | return 0; |
| 2672 | |
| 2673 | /* |
| 2674 | * Reads as many pages as possible from fscache. Returns -ENOBUFS |
| 2675 | * immediately if the cookie is negative |
| 2676 | */ |
| 2677 | rc = cifs_readpages_from_fscache(mapping->host, mapping, page_list, |
| 2678 | &num_pages); |
| 2679 | if (rc == 0) |
| 2680 | return rc; |
| 2681 | |
| 2682 | if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD) |
| 2683 | pid = open_file->pid; |
| 2684 | else |
| 2685 | pid = current->tgid; |
| 2686 | |
| 2687 | rc = 0; |
| 2688 | INIT_LIST_HEAD(&tmplist); |
| 2689 | |
| 2690 | cFYI(1, "%s: file=%p mapping=%p num_pages=%u", __func__, file, |
| 2691 | mapping, num_pages); |
| 2692 | |
| 2693 | /* |
| 2694 | * Start with the page at end of list and move it to private |
| 2695 | * list. Do the same with any following pages until we hit |
| 2696 | * the rsize limit, hit an index discontinuity, or run out of |
| 2697 | * pages. Issue the async read and then start the loop again |
| 2698 | * until the list is empty. |
| 2699 | * |
| 2700 | * Note that list order is important. The page_list is in |
| 2701 | * the order of declining indexes. When we put the pages in |
| 2702 | * the rdata->pages, then we want them in increasing order. |
| 2703 | */ |
| 2704 | while (!list_empty(page_list)) { |
| 2705 | unsigned int bytes = PAGE_CACHE_SIZE; |
| 2706 | unsigned int expected_index; |
| 2707 | unsigned int nr_pages = 1; |
| 2708 | loff_t offset; |
| 2709 | struct page *page, *tpage; |
| 2710 | struct cifs_readdata *rdata; |
| 2711 | |
| 2712 | page = list_entry(page_list->prev, struct page, lru); |
| 2713 | |
| 2714 | /* |
| 2715 | * Lock the page and put it in the cache. Since no one else |
| 2716 | * should have access to this page, we're safe to simply set |
| 2717 | * PG_locked without checking it first. |
| 2718 | */ |
| 2719 | __set_page_locked(page); |
| 2720 | rc = add_to_page_cache_locked(page, mapping, |
| 2721 | page->index, GFP_KERNEL); |
| 2722 | |
| 2723 | /* give up if we can't stick it in the cache */ |
| 2724 | if (rc) { |
| 2725 | __clear_page_locked(page); |
| 2726 | break; |
| 2727 | } |
| 2728 | |
| 2729 | /* move first page to the tmplist */ |
| 2730 | offset = (loff_t)page->index << PAGE_CACHE_SHIFT; |
| 2731 | list_move_tail(&page->lru, &tmplist); |
| 2732 | |
| 2733 | /* now try and add more pages onto the request */ |
| 2734 | expected_index = page->index + 1; |
| 2735 | list_for_each_entry_safe_reverse(page, tpage, page_list, lru) { |
| 2736 | /* discontinuity ? */ |
| 2737 | if (page->index != expected_index) |
| 2738 | break; |
| 2739 | |
| 2740 | /* would this page push the read over the rsize? */ |
| 2741 | if (bytes + PAGE_CACHE_SIZE > rsize) |
| 2742 | break; |
| 2743 | |
| 2744 | __set_page_locked(page); |
| 2745 | if (add_to_page_cache_locked(page, mapping, |
| 2746 | page->index, GFP_KERNEL)) { |
| 2747 | __clear_page_locked(page); |
| 2748 | break; |
| 2749 | } |
| 2750 | list_move_tail(&page->lru, &tmplist); |
| 2751 | bytes += PAGE_CACHE_SIZE; |
| 2752 | expected_index++; |
| 2753 | nr_pages++; |
| 2754 | } |
| 2755 | |
| 2756 | rdata = cifs_readdata_alloc(nr_pages); |
| 2757 | if (!rdata) { |
| 2758 | /* best to give up if we're out of mem */ |
| 2759 | list_for_each_entry_safe(page, tpage, &tmplist, lru) { |
| 2760 | list_del(&page->lru); |
| 2761 | lru_cache_add_file(page); |
| 2762 | unlock_page(page); |
| 2763 | page_cache_release(page); |
| 2764 | } |
| 2765 | rc = -ENOMEM; |
| 2766 | break; |
| 2767 | } |
| 2768 | |
| 2769 | spin_lock(&cifs_file_list_lock); |
| 2770 | cifsFileInfo_get(open_file); |
| 2771 | spin_unlock(&cifs_file_list_lock); |
| 2772 | rdata->cfile = open_file; |
| 2773 | rdata->mapping = mapping; |
| 2774 | rdata->offset = offset; |
| 2775 | rdata->bytes = bytes; |
| 2776 | rdata->pid = pid; |
| 2777 | list_splice_init(&tmplist, &rdata->pages); |
| 2778 | |
| 2779 | do { |
| 2780 | if (open_file->invalidHandle) { |
| 2781 | rc = cifs_reopen_file(open_file, true); |
| 2782 | if (rc != 0) |
| 2783 | continue; |
| 2784 | } |
| 2785 | rc = cifs_async_readv(rdata); |
| 2786 | } while (rc == -EAGAIN); |
| 2787 | |
| 2788 | if (rc != 0) { |
| 2789 | list_for_each_entry_safe(page, tpage, &rdata->pages, |
| 2790 | lru) { |
| 2791 | list_del(&page->lru); |
| 2792 | lru_cache_add_file(page); |
| 2793 | unlock_page(page); |
| 2794 | page_cache_release(page); |
| 2795 | } |
| 2796 | cifs_readdata_free(rdata); |
| 2797 | break; |
| 2798 | } |
| 2799 | } |
| 2800 | |
| 2801 | return rc; |
| 2802 | } |
| 2803 | |
| 2804 | static int cifs_readpage_worker(struct file *file, struct page *page, |
| 2805 | loff_t *poffset) |
| 2806 | { |
| 2807 | char *read_data; |
| 2808 | int rc; |
| 2809 | |
| 2810 | /* Is the page cached? */ |
| 2811 | rc = cifs_readpage_from_fscache(file->f_path.dentry->d_inode, page); |
| 2812 | if (rc == 0) |
| 2813 | goto read_complete; |
| 2814 | |
| 2815 | page_cache_get(page); |
| 2816 | read_data = kmap(page); |
| 2817 | /* for reads over a certain size could initiate async read ahead */ |
| 2818 | |
| 2819 | rc = cifs_read(file, read_data, PAGE_CACHE_SIZE, poffset); |
| 2820 | |
| 2821 | if (rc < 0) |
| 2822 | goto io_error; |
| 2823 | else |
| 2824 | cFYI(1, "Bytes read %d", rc); |
| 2825 | |
| 2826 | file->f_path.dentry->d_inode->i_atime = |
| 2827 | current_fs_time(file->f_path.dentry->d_inode->i_sb); |
| 2828 | |
| 2829 | if (PAGE_CACHE_SIZE > rc) |
| 2830 | memset(read_data + rc, 0, PAGE_CACHE_SIZE - rc); |
| 2831 | |
| 2832 | flush_dcache_page(page); |
| 2833 | SetPageUptodate(page); |
| 2834 | |
| 2835 | /* send this page to the cache */ |
| 2836 | cifs_readpage_to_fscache(file->f_path.dentry->d_inode, page); |
| 2837 | |
| 2838 | rc = 0; |
| 2839 | |
| 2840 | io_error: |
| 2841 | kunmap(page); |
| 2842 | page_cache_release(page); |
| 2843 | |
| 2844 | read_complete: |
| 2845 | return rc; |
| 2846 | } |
| 2847 | |
| 2848 | static int cifs_readpage(struct file *file, struct page *page) |
| 2849 | { |
| 2850 | loff_t offset = (loff_t)page->index << PAGE_CACHE_SHIFT; |
| 2851 | int rc = -EACCES; |
| 2852 | int xid; |
| 2853 | |
| 2854 | xid = GetXid(); |
| 2855 | |
| 2856 | if (file->private_data == NULL) { |
| 2857 | rc = -EBADF; |
| 2858 | FreeXid(xid); |
| 2859 | return rc; |
| 2860 | } |
| 2861 | |
| 2862 | cFYI(1, "readpage %p at offset %d 0x%x\n", |
| 2863 | page, (int)offset, (int)offset); |
| 2864 | |
| 2865 | rc = cifs_readpage_worker(file, page, &offset); |
| 2866 | |
| 2867 | unlock_page(page); |
| 2868 | |
| 2869 | FreeXid(xid); |
| 2870 | return rc; |
| 2871 | } |
| 2872 | |
| 2873 | static int is_inode_writable(struct cifsInodeInfo *cifs_inode) |
| 2874 | { |
| 2875 | struct cifsFileInfo *open_file; |
| 2876 | |
| 2877 | spin_lock(&cifs_file_list_lock); |
| 2878 | list_for_each_entry(open_file, &cifs_inode->openFileList, flist) { |
| 2879 | if (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE) { |
| 2880 | spin_unlock(&cifs_file_list_lock); |
| 2881 | return 1; |
| 2882 | } |
| 2883 | } |
| 2884 | spin_unlock(&cifs_file_list_lock); |
| 2885 | return 0; |
| 2886 | } |
| 2887 | |
| 2888 | /* We do not want to update the file size from server for inodes |
| 2889 | open for write - to avoid races with writepage extending |
| 2890 | the file - in the future we could consider allowing |
| 2891 | refreshing the inode only on increases in the file size |
| 2892 | but this is tricky to do without racing with writebehind |
| 2893 | page caching in the current Linux kernel design */ |
| 2894 | bool is_size_safe_to_change(struct cifsInodeInfo *cifsInode, __u64 end_of_file) |
| 2895 | { |
| 2896 | if (!cifsInode) |
| 2897 | return true; |
| 2898 | |
| 2899 | if (is_inode_writable(cifsInode)) { |
| 2900 | /* This inode is open for write at least once */ |
| 2901 | struct cifs_sb_info *cifs_sb; |
| 2902 | |
| 2903 | cifs_sb = CIFS_SB(cifsInode->vfs_inode.i_sb); |
| 2904 | if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DIRECT_IO) { |
| 2905 | /* since no page cache to corrupt on directio |
| 2906 | we can change size safely */ |
| 2907 | return true; |
| 2908 | } |
| 2909 | |
| 2910 | if (i_size_read(&cifsInode->vfs_inode) < end_of_file) |
| 2911 | return true; |
| 2912 | |
| 2913 | return false; |
| 2914 | } else |
| 2915 | return true; |
| 2916 | } |
| 2917 | |
| 2918 | static int cifs_write_begin(struct file *file, struct address_space *mapping, |
| 2919 | loff_t pos, unsigned len, unsigned flags, |
| 2920 | struct page **pagep, void **fsdata) |
| 2921 | { |
| 2922 | pgoff_t index = pos >> PAGE_CACHE_SHIFT; |
| 2923 | loff_t offset = pos & (PAGE_CACHE_SIZE - 1); |
| 2924 | loff_t page_start = pos & PAGE_MASK; |
| 2925 | loff_t i_size; |
| 2926 | struct page *page; |
| 2927 | int rc = 0; |
| 2928 | |
| 2929 | cFYI(1, "write_begin from %lld len %d", (long long)pos, len); |
| 2930 | |
| 2931 | page = grab_cache_page_write_begin(mapping, index, flags); |
| 2932 | if (!page) { |
| 2933 | rc = -ENOMEM; |
| 2934 | goto out; |
| 2935 | } |
| 2936 | |
| 2937 | if (PageUptodate(page)) |
| 2938 | goto out; |
| 2939 | |
| 2940 | /* |
| 2941 | * If we write a full page it will be up to date, no need to read from |
| 2942 | * the server. If the write is short, we'll end up doing a sync write |
| 2943 | * instead. |
| 2944 | */ |
| 2945 | if (len == PAGE_CACHE_SIZE) |
| 2946 | goto out; |
| 2947 | |
| 2948 | /* |
| 2949 | * optimize away the read when we have an oplock, and we're not |
| 2950 | * expecting to use any of the data we'd be reading in. That |
| 2951 | * is, when the page lies beyond the EOF, or straddles the EOF |
| 2952 | * and the write will cover all of the existing data. |
| 2953 | */ |
| 2954 | if (CIFS_I(mapping->host)->clientCanCacheRead) { |
| 2955 | i_size = i_size_read(mapping->host); |
| 2956 | if (page_start >= i_size || |
| 2957 | (offset == 0 && (pos + len) >= i_size)) { |
| 2958 | zero_user_segments(page, 0, offset, |
| 2959 | offset + len, |
| 2960 | PAGE_CACHE_SIZE); |
| 2961 | /* |
| 2962 | * PageChecked means that the parts of the page |
| 2963 | * to which we're not writing are considered up |
| 2964 | * to date. Once the data is copied to the |
| 2965 | * page, it can be set uptodate. |
| 2966 | */ |
| 2967 | SetPageChecked(page); |
| 2968 | goto out; |
| 2969 | } |
| 2970 | } |
| 2971 | |
| 2972 | if ((file->f_flags & O_ACCMODE) != O_WRONLY) { |
| 2973 | /* |
| 2974 | * might as well read a page, it is fast enough. If we get |
| 2975 | * an error, we don't need to return it. cifs_write_end will |
| 2976 | * do a sync write instead since PG_uptodate isn't set. |
| 2977 | */ |
| 2978 | cifs_readpage_worker(file, page, &page_start); |
| 2979 | } else { |
| 2980 | /* we could try using another file handle if there is one - |
| 2981 | but how would we lock it to prevent close of that handle |
| 2982 | racing with this read? In any case |
| 2983 | this will be written out by write_end so is fine */ |
| 2984 | } |
| 2985 | out: |
| 2986 | *pagep = page; |
| 2987 | return rc; |
| 2988 | } |
| 2989 | |
| 2990 | static int cifs_release_page(struct page *page, gfp_t gfp) |
| 2991 | { |
| 2992 | if (PagePrivate(page)) |
| 2993 | return 0; |
| 2994 | |
| 2995 | return cifs_fscache_release_page(page, gfp); |
| 2996 | } |
| 2997 | |
| 2998 | static void cifs_invalidate_page(struct page *page, unsigned long offset) |
| 2999 | { |
| 3000 | struct cifsInodeInfo *cifsi = CIFS_I(page->mapping->host); |
| 3001 | |
| 3002 | if (offset == 0) |
| 3003 | cifs_fscache_invalidate_page(page, &cifsi->vfs_inode); |
| 3004 | } |
| 3005 | |
| 3006 | static int cifs_launder_page(struct page *page) |
| 3007 | { |
| 3008 | int rc = 0; |
| 3009 | loff_t range_start = page_offset(page); |
| 3010 | loff_t range_end = range_start + (loff_t)(PAGE_CACHE_SIZE - 1); |
| 3011 | struct writeback_control wbc = { |
| 3012 | .sync_mode = WB_SYNC_ALL, |
| 3013 | .nr_to_write = 0, |
| 3014 | .range_start = range_start, |
| 3015 | .range_end = range_end, |
| 3016 | }; |
| 3017 | |
| 3018 | cFYI(1, "Launder page: %p", page); |
| 3019 | |
| 3020 | if (clear_page_dirty_for_io(page)) |
| 3021 | rc = cifs_writepage_locked(page, &wbc); |
| 3022 | |
| 3023 | cifs_fscache_invalidate_page(page, page->mapping->host); |
| 3024 | return rc; |
| 3025 | } |
| 3026 | |
| 3027 | void cifs_oplock_break(struct work_struct *work) |
| 3028 | { |
| 3029 | struct cifsFileInfo *cfile = container_of(work, struct cifsFileInfo, |
| 3030 | oplock_break); |
| 3031 | struct inode *inode = cfile->dentry->d_inode; |
| 3032 | struct cifsInodeInfo *cinode = CIFS_I(inode); |
| 3033 | int rc = 0; |
| 3034 | |
| 3035 | if (inode && S_ISREG(inode->i_mode)) { |
| 3036 | if (cinode->clientCanCacheRead) |
| 3037 | break_lease(inode, O_RDONLY); |
| 3038 | else |
| 3039 | break_lease(inode, O_WRONLY); |
| 3040 | rc = filemap_fdatawrite(inode->i_mapping); |
| 3041 | if (cinode->clientCanCacheRead == 0) { |
| 3042 | rc = filemap_fdatawait(inode->i_mapping); |
| 3043 | mapping_set_error(inode->i_mapping, rc); |
| 3044 | invalidate_remote_inode(inode); |
| 3045 | } |
| 3046 | cFYI(1, "Oplock flush inode %p rc %d", inode, rc); |
| 3047 | } |
| 3048 | |
| 3049 | rc = cifs_push_locks(cfile); |
| 3050 | if (rc) |
| 3051 | cERROR(1, "Push locks rc = %d", rc); |
| 3052 | |
| 3053 | /* |
| 3054 | * releasing stale oplock after recent reconnect of smb session using |
| 3055 | * a now incorrect file handle is not a data integrity issue but do |
| 3056 | * not bother sending an oplock release if session to server still is |
| 3057 | * disconnected since oplock already released by the server |
| 3058 | */ |
| 3059 | if (!cfile->oplock_break_cancelled) { |
| 3060 | rc = CIFSSMBLock(0, tlink_tcon(cfile->tlink), cfile->netfid, |
| 3061 | current->tgid, 0, 0, 0, 0, |
| 3062 | LOCKING_ANDX_OPLOCK_RELEASE, false, |
| 3063 | cinode->clientCanCacheRead ? 1 : 0); |
| 3064 | cFYI(1, "Oplock release rc = %d", rc); |
| 3065 | } |
| 3066 | } |
| 3067 | |
| 3068 | const struct address_space_operations cifs_addr_ops = { |
| 3069 | .readpage = cifs_readpage, |
| 3070 | .readpages = cifs_readpages, |
| 3071 | .writepage = cifs_writepage, |
| 3072 | .writepages = cifs_writepages, |
| 3073 | .write_begin = cifs_write_begin, |
| 3074 | .write_end = cifs_write_end, |
| 3075 | .set_page_dirty = __set_page_dirty_nobuffers, |
| 3076 | .releasepage = cifs_release_page, |
| 3077 | .invalidatepage = cifs_invalidate_page, |
| 3078 | .launder_page = cifs_launder_page, |
| 3079 | }; |
| 3080 | |
| 3081 | /* |
| 3082 | * cifs_readpages requires the server to support a buffer large enough to |
| 3083 | * contain the header plus one complete page of data. Otherwise, we need |
| 3084 | * to leave cifs_readpages out of the address space operations. |
| 3085 | */ |
| 3086 | const struct address_space_operations cifs_addr_ops_smallbuf = { |
| 3087 | .readpage = cifs_readpage, |
| 3088 | .writepage = cifs_writepage, |
| 3089 | .writepages = cifs_writepages, |
| 3090 | .write_begin = cifs_write_begin, |
| 3091 | .write_end = cifs_write_end, |
| 3092 | .set_page_dirty = __set_page_dirty_nobuffers, |
| 3093 | .releasepage = cifs_release_page, |
| 3094 | .invalidatepage = cifs_invalidate_page, |
| 3095 | .launder_page = cifs_launder_page, |
| 3096 | }; |