file.c 52.5 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23
/*
 *   fs/cifs/file.c
 *
 *   vfs operations that deal with files
 * 
 *   Copyright (C) International Business Machines  Corp., 2002,2003
 *   Author(s): Steve French (sfrench@us.ibm.com)
 *
 *   This library is free software; you can redistribute it and/or modify
 *   it under the terms of the GNU Lesser General Public License as published
 *   by the Free Software Foundation; either version 2.1 of the License, or
 *   (at your option) any later version.
 *
 *   This library is distributed in the hope that it will be useful,
 *   but WITHOUT ANY WARRANTY; without even the implied warranty of
 *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See
 *   the GNU Lesser General Public License for more details.
 *
 *   You should have received a copy of the GNU Lesser General Public License
 *   along with this library; if not, write to the Free Software
 *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
 */
#include <linux/fs.h>
24
#include <linux/backing-dev.h>
Linus Torvalds's avatar
Linus Torvalds committed
25 26
#include <linux/stat.h>
#include <linux/fcntl.h>
27
#include <linux/mpage.h>
Linus Torvalds's avatar
Linus Torvalds committed
28 29 30
#include <linux/pagemap.h>
#include <linux/pagevec.h>
#include <linux/smp_lock.h>
31
#include <linux/writeback.h>
32
#include <linux/delay.h>
Linus Torvalds's avatar
Linus Torvalds committed
33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53
#include <asm/div64.h>
#include "cifsfs.h"
#include "cifspdu.h"
#include "cifsglob.h"
#include "cifsproto.h"
#include "cifs_unicode.h"
#include "cifs_debug.h"
#include "cifs_fs_sb.h"

static inline struct cifsFileInfo *cifs_init_private(
	struct cifsFileInfo *private_data, struct inode *inode,
	struct file *file, __u16 netfid)
{
	memset(private_data, 0, sizeof(struct cifsFileInfo));
	private_data->netfid = netfid;
	private_data->pid = current->tgid;	
	init_MUTEX(&private_data->fh_sem);
	private_data->pfile = file; /* needed for writepage */
	private_data->pInode = inode;
	private_data->invalidHandle = FALSE;
	private_data->closePend = FALSE;
54 55 56 57 58
	/* we have to track num writers to the inode, since writepages
	does not tell us which handle the write is for so there can
	be a close (overlapping with write) of the filehandle that
	cifs_writepages chose to use */
	atomic_set(&private_data->wrtPending,0); 
Linus Torvalds's avatar
Linus Torvalds committed
59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129

	return private_data;
}

static inline int cifs_convert_flags(unsigned int flags)
{
	if ((flags & O_ACCMODE) == O_RDONLY)
		return GENERIC_READ;
	else if ((flags & O_ACCMODE) == O_WRONLY)
		return GENERIC_WRITE;
	else if ((flags & O_ACCMODE) == O_RDWR) {
		/* GENERIC_ALL is too much permission to request
		   can cause unnecessary access denied on create */
		/* return GENERIC_ALL; */
		return (GENERIC_READ | GENERIC_WRITE);
	}

	return 0x20197;
}

static inline int cifs_get_disposition(unsigned int flags)
{
	if ((flags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL))
		return FILE_CREATE;
	else if ((flags & (O_CREAT | O_TRUNC)) == (O_CREAT | O_TRUNC))
		return FILE_OVERWRITE_IF;
	else if ((flags & O_CREAT) == O_CREAT)
		return FILE_OPEN_IF;
	else
		return FILE_OPEN;
}

/* all arguments to this function must be checked for validity in caller */
static inline int cifs_open_inode_helper(struct inode *inode, struct file *file,
	struct cifsInodeInfo *pCifsInode, struct cifsFileInfo *pCifsFile,
	struct cifsTconInfo *pTcon, int *oplock, FILE_ALL_INFO *buf,
	char *full_path, int xid)
{
	struct timespec temp;
	int rc;

	/* want handles we can use to read with first
	   in the list so we do not have to walk the
	   list to search for one in prepare_write */
	if ((file->f_flags & O_ACCMODE) == O_WRONLY) {
		list_add_tail(&pCifsFile->flist, 
			      &pCifsInode->openFileList);
	} else {
		list_add(&pCifsFile->flist,
			 &pCifsInode->openFileList);
	}
	write_unlock(&GlobalSMBSeslock);
	write_unlock(&file->f_owner.lock);
	if (pCifsInode->clientCanCacheRead) {
		/* we have the inode open somewhere else
		   no need to discard cache data */
		goto client_can_cache;
	}

	/* BB need same check in cifs_create too? */
	/* if not oplocked, invalidate inode pages if mtime or file
	   size changed */
	temp = cifs_NTtimeToUnix(le64_to_cpu(buf->LastWriteTime));
	if (timespec_equal(&file->f_dentry->d_inode->i_mtime, &temp) && 
			   (file->f_dentry->d_inode->i_size == 
			    (loff_t)le64_to_cpu(buf->EndOfFile))) {
		cFYI(1, ("inode unchanged on server"));
	} else {
		if (file->f_dentry->d_inode->i_mapping) {
		/* BB no need to lock inode until after invalidate
		   since namei code should already have it locked? */
130
			filemap_write_and_wait(file->f_dentry->d_inode->i_mapping);
Linus Torvalds's avatar
Linus Torvalds committed
131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205
		}
		cFYI(1, ("invalidating remote inode since open detected it "
			 "changed"));
		invalidate_remote_inode(file->f_dentry->d_inode);
	}

client_can_cache:
	if (pTcon->ses->capabilities & CAP_UNIX)
		rc = cifs_get_inode_info_unix(&file->f_dentry->d_inode,
			full_path, inode->i_sb, xid);
	else
		rc = cifs_get_inode_info(&file->f_dentry->d_inode,
			full_path, buf, inode->i_sb, xid);

	if ((*oplock & 0xF) == OPLOCK_EXCLUSIVE) {
		pCifsInode->clientCanCacheAll = TRUE;
		pCifsInode->clientCanCacheRead = TRUE;
		cFYI(1, ("Exclusive Oplock granted on inode %p",
			 file->f_dentry->d_inode));
	} else if ((*oplock & 0xF) == OPLOCK_READ)
		pCifsInode->clientCanCacheRead = TRUE;

	return rc;
}

int cifs_open(struct inode *inode, struct file *file)
{
	int rc = -EACCES;
	int xid, oplock;
	struct cifs_sb_info *cifs_sb;
	struct cifsTconInfo *pTcon;
	struct cifsFileInfo *pCifsFile;
	struct cifsInodeInfo *pCifsInode;
	struct list_head *tmp;
	char *full_path = NULL;
	int desiredAccess;
	int disposition;
	__u16 netfid;
	FILE_ALL_INFO *buf = NULL;

	xid = GetXid();

	cifs_sb = CIFS_SB(inode->i_sb);
	pTcon = cifs_sb->tcon;

	if (file->f_flags & O_CREAT) {
		/* search inode for this file and fill in file->private_data */
		pCifsInode = CIFS_I(file->f_dentry->d_inode);
		read_lock(&GlobalSMBSeslock);
		list_for_each(tmp, &pCifsInode->openFileList) {
			pCifsFile = list_entry(tmp, struct cifsFileInfo,
					       flist);
			if ((pCifsFile->pfile == NULL) &&
			    (pCifsFile->pid == current->tgid)) {
				/* mode set in cifs_create */

				/* needed for writepage */
				pCifsFile->pfile = file;
				
				file->private_data = pCifsFile;
				break;
			}
		}
		read_unlock(&GlobalSMBSeslock);
		if (file->private_data != NULL) {
			rc = 0;
			FreeXid(xid);
			return rc;
		} else {
			if (file->f_flags & O_EXCL)
				cERROR(1, ("could not find file instance for "
					   "new file %p ", file));
		}
	}

206
	full_path = build_path_from_dentry(file->f_dentry);
Linus Torvalds's avatar
Linus Torvalds committed
207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262
	if (full_path == NULL) {
		FreeXid(xid);
		return -ENOMEM;
	}

	cFYI(1, (" inode = 0x%p file flags are 0x%x for %s",
		 inode, file->f_flags, full_path));
	desiredAccess = cifs_convert_flags(file->f_flags);

/*********************************************************************
 *  open flag mapping table:
 *  
 *	POSIX Flag            CIFS Disposition
 *	----------            ---------------- 
 *	O_CREAT               FILE_OPEN_IF
 *	O_CREAT | O_EXCL      FILE_CREATE
 *	O_CREAT | O_TRUNC     FILE_OVERWRITE_IF
 *	O_TRUNC               FILE_OVERWRITE
 *	none of the above     FILE_OPEN
 *
 *	Note that there is not a direct match between disposition
 *	FILE_SUPERSEDE (ie create whether or not file exists although 
 *	O_CREAT | O_TRUNC is similar but truncates the existing
 *	file rather than creating a new file as FILE_SUPERSEDE does
 *	(which uses the attributes / metadata passed in on open call)
 *?
 *?  O_SYNC is a reasonable match to CIFS writethrough flag  
 *?  and the read write flags match reasonably.  O_LARGEFILE
 *?  is irrelevant because largefile support is always used
 *?  by this client. Flags O_APPEND, O_DIRECT, O_DIRECTORY,
 *	 O_FASYNC, O_NOFOLLOW, O_NONBLOCK need further investigation
 *********************************************************************/

	disposition = cifs_get_disposition(file->f_flags);

	if (oplockEnabled)
		oplock = REQ_OPLOCK;
	else
		oplock = FALSE;

	/* BB pass O_SYNC flag through on file attributes .. BB */

	/* Also refresh inode by passing in file_info buf returned by SMBOpen
	   and calling get_inode_info with returned buf (at least helps
	   non-Unix server case) */

	/* BB we can not do this if this is the second open of a file 
	   and the first handle has writebehind data, we might be 
	   able to simply do a filemap_fdatawrite/filemap_fdatawait first */
	buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL);
	if (!buf) {
		rc = -ENOMEM;
		goto out;
	}
	rc = CIFSSMBOpen(xid, pTcon, full_path, disposition, desiredAccess,
			 CREATE_NOT_DIR, &netfid, &oplock, buf,
263 264
			 cifs_sb->local_nls, cifs_sb->mnt_cifs_flags
				 & CIFS_MOUNT_MAP_SPECIAL_CHR);
265 266 267 268 269 270 271
	if (rc == -EIO) {
		/* Old server, try legacy style OpenX */
		rc = SMBLegacyOpen(xid, pTcon, full_path, disposition,
			desiredAccess, CREATE_NOT_DIR, &netfid, &oplock, buf,
			cifs_sb->local_nls, cifs_sb->mnt_cifs_flags
				& CIFS_MOUNT_MAP_SPECIAL_CHR);
	}
Linus Torvalds's avatar
Linus Torvalds committed
272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303
	if (rc) {
		cFYI(1, ("cifs_open returned 0x%x ", rc));
		goto out;
	}
	file->private_data =
		kmalloc(sizeof(struct cifsFileInfo), GFP_KERNEL);
	if (file->private_data == NULL) {
		rc = -ENOMEM;
		goto out;
	}
	pCifsFile = cifs_init_private(file->private_data, inode, file, netfid);
	write_lock(&file->f_owner.lock);
	write_lock(&GlobalSMBSeslock);
	list_add(&pCifsFile->tlist, &pTcon->openFileList);

	pCifsInode = CIFS_I(file->f_dentry->d_inode);
	if (pCifsInode) {
		rc = cifs_open_inode_helper(inode, file, pCifsInode,
					    pCifsFile, pTcon,
					    &oplock, buf, full_path, xid);
	} else {
		write_unlock(&GlobalSMBSeslock);
		write_unlock(&file->f_owner.lock);
	}

	if (oplock & CIFS_CREATE_ACTION) {           
		/* time to set mode which we can not set earlier due to
		   problems creating new read-only files */
		if (cifs_sb->tcon->ses->capabilities & CAP_UNIX) {
			CIFSSMBUnixSetPerms(xid, pTcon, full_path,
					    inode->i_mode,
					    (__u64)-1, (__u64)-1, 0 /* dev */,
304 305 306
					    cifs_sb->local_nls,
					    cifs_sb->mnt_cifs_flags & 
						CIFS_MOUNT_MAP_SPECIAL_CHR);
Linus Torvalds's avatar
Linus Torvalds committed
307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374
		} else {
			/* BB implement via Windows security descriptors eg
			   CIFSSMBWinSetPerms(xid, pTcon, full_path, mode,
					      -1, -1, local_nls);
			   in the meantime could set r/o dos attribute when
			   perms are eg: mode & 0222 == 0 */
		}
	}

out:
	kfree(buf);
	kfree(full_path);
	FreeXid(xid);
	return rc;
}

/* Try to reaquire byte range locks that were released when session */
/* to server was lost */
static int cifs_relock_file(struct cifsFileInfo *cifsFile)
{
	int rc = 0;

/* BB list all locks open on this file and relock */

	return rc;
}

static int cifs_reopen_file(struct inode *inode, struct file *file, 
	int can_flush)
{
	int rc = -EACCES;
	int xid, oplock;
	struct cifs_sb_info *cifs_sb;
	struct cifsTconInfo *pTcon;
	struct cifsFileInfo *pCifsFile;
	struct cifsInodeInfo *pCifsInode;
	char *full_path = NULL;
	int desiredAccess;
	int disposition = FILE_OPEN;
	__u16 netfid;

	if (inode == NULL)
		return -EBADF;
	if (file->private_data) {
		pCifsFile = (struct cifsFileInfo *)file->private_data;
	} else
		return -EBADF;

	xid = GetXid();
	down(&pCifsFile->fh_sem);
	if (pCifsFile->invalidHandle == FALSE) {
		up(&pCifsFile->fh_sem);
		FreeXid(xid);
		return 0;
	}

	if (file->f_dentry == NULL) {
		up(&pCifsFile->fh_sem);
		cFYI(1, ("failed file reopen, no valid name if dentry freed"));
		FreeXid(xid);
		return -EBADF;
	}
	cifs_sb = CIFS_SB(inode->i_sb);
	pTcon = cifs_sb->tcon;
/* can not grab rename sem here because various ops, including
   those that already have the rename sem can end up causing writepage
   to get called and if the server was down that means we end up here,
   and we can never tell if the caller already has the rename_sem */
375
	full_path = build_path_from_dentry(file->f_dentry);
Linus Torvalds's avatar
Linus Torvalds committed
376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405
	if (full_path == NULL) {
		up(&pCifsFile->fh_sem);
		FreeXid(xid);
		return -ENOMEM;
	}

	cFYI(1, (" inode = 0x%p file flags are 0x%x for %s",
		 inode, file->f_flags,full_path));
	desiredAccess = cifs_convert_flags(file->f_flags);

	if (oplockEnabled)
		oplock = REQ_OPLOCK;
	else
		oplock = FALSE;

	/* Can not refresh inode by passing in file_info buf to be returned
	   by SMBOpen and then calling get_inode_info with returned buf 
	   since file might have write behind data that needs to be flushed 
	   and server version of file size can be stale. If we knew for sure
	   that inode was not dirty locally we could do this */

/*	buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL);
	if (buf == 0) {
		up(&pCifsFile->fh_sem);
		kfree(full_path);
		FreeXid(xid);
		return -ENOMEM;
	} */
	rc = CIFSSMBOpen(xid, pTcon, full_path, disposition, desiredAccess,
			 CREATE_NOT_DIR, &netfid, &oplock, NULL,
406 407
			 cifs_sb->local_nls, cifs_sb->mnt_cifs_flags & 
				CIFS_MOUNT_MAP_SPECIAL_CHR);
Linus Torvalds's avatar
Linus Torvalds committed
408 409 410 411 412 413 414 415 416 417 418
	if (rc) {
		up(&pCifsFile->fh_sem);
		cFYI(1, ("cifs_open returned 0x%x ", rc));
		cFYI(1, ("oplock: %d ", oplock));
	} else {
		pCifsFile->netfid = netfid;
		pCifsFile->invalidHandle = FALSE;
		up(&pCifsFile->fh_sem);
		pCifsInode = CIFS_I(inode);
		if (pCifsInode) {
			if (can_flush) {
419
				filemap_write_and_wait(inode->i_mapping);
Linus Torvalds's avatar
Linus Torvalds committed
420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477
			/* temporarily disable caching while we
			   go to server to get inode info */
				pCifsInode->clientCanCacheAll = FALSE;
				pCifsInode->clientCanCacheRead = FALSE;
				if (pTcon->ses->capabilities & CAP_UNIX)
					rc = cifs_get_inode_info_unix(&inode,
						full_path, inode->i_sb, xid);
				else
					rc = cifs_get_inode_info(&inode,
						full_path, NULL, inode->i_sb,
						xid);
			} /* else we are writing out data to server already
			     and could deadlock if we tried to flush data, and
			     since we do not know if we have data that would
			     invalidate the current end of file on the server
			     we can not go to the server to get the new inod
			     info */
			if ((oplock & 0xF) == OPLOCK_EXCLUSIVE) {
				pCifsInode->clientCanCacheAll = TRUE;
				pCifsInode->clientCanCacheRead = TRUE;
				cFYI(1, ("Exclusive Oplock granted on inode %p",
					 file->f_dentry->d_inode));
			} else if ((oplock & 0xF) == OPLOCK_READ) {
				pCifsInode->clientCanCacheRead = TRUE;
				pCifsInode->clientCanCacheAll = FALSE;
			} else {
				pCifsInode->clientCanCacheRead = FALSE;
				pCifsInode->clientCanCacheAll = FALSE;
			}
			cifs_relock_file(pCifsFile);
		}
	}

	kfree(full_path);
	FreeXid(xid);
	return rc;
}

int cifs_close(struct inode *inode, struct file *file)
{
	int rc = 0;
	int xid;
	struct cifs_sb_info *cifs_sb;
	struct cifsTconInfo *pTcon;
	struct cifsFileInfo *pSMBFile =
		(struct cifsFileInfo *)file->private_data;

	xid = GetXid();

	cifs_sb = CIFS_SB(inode->i_sb);
	pTcon = cifs_sb->tcon;
	if (pSMBFile) {
		pSMBFile->closePend = TRUE;
		write_lock(&file->f_owner.lock);
		if (pTcon) {
			/* no sense reconnecting to close a file that is
			   already closed */
			if (pTcon->tidStatus != CifsNeedReconnect) {
478 479 480 481 482 483 484 485 486 487
				int timeout = 2;
				while((atomic_read(&pSMBFile->wrtPending) != 0)
					 && (timeout < 1000) ) {
					/* Give write a better chance to get to
					server ahead of the close.  We do not
					want to add a wait_q here as it would
					increase the memory utilization as
					the struct would be in each open file,
					but this should give enough time to 
					clear the socket */
488
					write_unlock(&file->f_owner.lock);
489 490
					cERROR(1,("close with pending writes"));
					msleep(timeout);
491
					write_lock(&file->f_owner.lock);
492 493
					timeout *= 4;
				} 
Linus Torvalds's avatar
Linus Torvalds committed
494 495 496 497 498 499
				write_unlock(&file->f_owner.lock);
				rc = CIFSSMBClose(xid, pTcon,
						  pSMBFile->netfid);
				write_lock(&file->f_owner.lock);
			}
		}
500
		write_lock(&GlobalSMBSeslock);
Linus Torvalds's avatar
Linus Torvalds committed
501 502
		list_del(&pSMBFile->flist);
		list_del(&pSMBFile->tlist);
503
		write_unlock(&GlobalSMBSeslock);
Linus Torvalds's avatar
Linus Torvalds committed
504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542
		write_unlock(&file->f_owner.lock);
		kfree(pSMBFile->search_resume_name);
		kfree(file->private_data);
		file->private_data = NULL;
	} else
		rc = -EBADF;

	if (list_empty(&(CIFS_I(inode)->openFileList))) {
		cFYI(1, ("closing last open instance for inode %p", inode));
		/* if the file is not open we do not know if we can cache info
		   on this inode, much less write behind and read ahead */
		CIFS_I(inode)->clientCanCacheRead = FALSE;
		CIFS_I(inode)->clientCanCacheAll  = FALSE;
	}
	if ((rc ==0) && CIFS_I(inode)->write_behind_rc)
		rc = CIFS_I(inode)->write_behind_rc;
	FreeXid(xid);
	return rc;
}

int cifs_closedir(struct inode *inode, struct file *file)
{
	int rc = 0;
	int xid;
	struct cifsFileInfo *pCFileStruct =
	    (struct cifsFileInfo *)file->private_data;
	char *ptmp;

	cFYI(1, ("Closedir inode = 0x%p with ", inode));

	xid = GetXid();

	if (pCFileStruct) {
		struct cifsTconInfo *pTcon;
		struct cifs_sb_info *cifs_sb = CIFS_SB(file->f_dentry->d_sb);

		pTcon = cifs_sb->tcon;

		cFYI(1, ("Freeing private data in close dir"));
543 544
		if ((pCFileStruct->srch_inf.endOfSearch == FALSE) &&
		   (pCFileStruct->invalidHandle == FALSE)) {
Linus Torvalds's avatar
Linus Torvalds committed
545 546 547 548 549 550 551 552 553
			pCFileStruct->invalidHandle = TRUE;
			rc = CIFSFindClose(xid, pTcon, pCFileStruct->netfid);
			cFYI(1, ("Closing uncompleted readdir with rc %d",
				 rc));
			/* not much we can do if it fails anyway, ignore rc */
			rc = 0;
		}
		ptmp = pCFileStruct->srch_inf.ntwrk_buf_start;
		if (ptmp) {
554
			cFYI(1, ("closedir free smb buf in srch struct"));
Linus Torvalds's avatar
Linus Torvalds committed
555
			pCFileStruct->srch_inf.ntwrk_buf_start = NULL;
556 557 558 559
			if(pCFileStruct->srch_inf.smallBuf)
				cifs_small_buf_release(ptmp);
			else
				cifs_buf_release(ptmp);
Linus Torvalds's avatar
Linus Torvalds committed
560 561 562
		}
		ptmp = pCFileStruct->search_resume_name;
		if (ptmp) {
563
			cFYI(1, ("closedir free resume name"));
Linus Torvalds's avatar
Linus Torvalds committed
564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583
			pCFileStruct->search_resume_name = NULL;
			kfree(ptmp);
		}
		kfree(file->private_data);
		file->private_data = NULL;
	}
	/* BB can we lock the filestruct while this is going on? */
	FreeXid(xid);
	return rc;
}

int cifs_lock(struct file *file, int cmd, struct file_lock *pfLock)
{
	int rc, xid;
	__u32 numLock = 0;
	__u32 numUnlock = 0;
	__u64 length;
	int wait_flag = FALSE;
	struct cifs_sb_info *cifs_sb;
	struct cifsTconInfo *pTcon;
584 585
	__u16 netfid;
	__u8 lockType = LOCKING_ANDX_LARGE_FILES;
Linus Torvalds's avatar
Linus Torvalds committed
586 587 588 589 590 591 592 593 594 595 596

	length = 1 + pfLock->fl_end - pfLock->fl_start;
	rc = -EACCES;
	xid = GetXid();

	cFYI(1, ("Lock parm: 0x%x flockflags: "
		 "0x%x flocktype: 0x%x start: %lld end: %lld",
	        cmd, pfLock->fl_flags, pfLock->fl_type, pfLock->fl_start,
	        pfLock->fl_end));

	if (pfLock->fl_flags & FL_POSIX)
597
		cFYI(1, ("Posix"));
Linus Torvalds's avatar
Linus Torvalds committed
598
	if (pfLock->fl_flags & FL_FLOCK)
599
		cFYI(1, ("Flock"));
Linus Torvalds's avatar
Linus Torvalds committed
600
	if (pfLock->fl_flags & FL_SLEEP) {
601
		cFYI(1, ("Blocking lock"));
Linus Torvalds's avatar
Linus Torvalds committed
602 603 604 605 606 607 608 609 610 611 612 613 614 615 616
		wait_flag = TRUE;
	}
	if (pfLock->fl_flags & FL_ACCESS)
		cFYI(1, ("Process suspended by mandatory locking - "
			 "not implemented yet "));
	if (pfLock->fl_flags & FL_LEASE)
		cFYI(1, ("Lease on file - not implemented yet"));
	if (pfLock->fl_flags & 
	    (~(FL_POSIX | FL_FLOCK | FL_SLEEP | FL_ACCESS | FL_LEASE)))
		cFYI(1, ("Unknown lock flags 0x%x", pfLock->fl_flags));

	if (pfLock->fl_type == F_WRLCK) {
		cFYI(1, ("F_WRLCK "));
		numLock = 1;
	} else if (pfLock->fl_type == F_UNLCK) {
617
		cFYI(1, ("F_UNLCK"));
Linus Torvalds's avatar
Linus Torvalds committed
618
		numUnlock = 1;
619 620
		/* Check if unlock includes more than
		one lock range */
Linus Torvalds's avatar
Linus Torvalds committed
621
	} else if (pfLock->fl_type == F_RDLCK) {
622
		cFYI(1, ("F_RDLCK"));
Linus Torvalds's avatar
Linus Torvalds committed
623 624 625
		lockType |= LOCKING_ANDX_SHARED_LOCK;
		numLock = 1;
	} else if (pfLock->fl_type == F_EXLCK) {
626
		cFYI(1, ("F_EXLCK"));
Linus Torvalds's avatar
Linus Torvalds committed
627 628
		numLock = 1;
	} else if (pfLock->fl_type == F_SHLCK) {
629
		cFYI(1, ("F_SHLCK"));
Linus Torvalds's avatar
Linus Torvalds committed
630 631 632
		lockType |= LOCKING_ANDX_SHARED_LOCK;
		numLock = 1;
	} else
633
		cFYI(1, ("Unknown type of lock"));
Linus Torvalds's avatar
Linus Torvalds committed
634 635 636 637 638 639 640 641

	cifs_sb = CIFS_SB(file->f_dentry->d_sb);
	pTcon = cifs_sb->tcon;

	if (file->private_data == NULL) {
		FreeXid(xid);
		return -EBADF;
	}
642 643
	netfid = ((struct cifsFileInfo *)file->private_data)->netfid;

Linus Torvalds's avatar
Linus Torvalds committed
644

645 646 647
	/* BB add code here to normalize offset and length to
	account for negative length which we can not accept over the
	wire */
Linus Torvalds's avatar
Linus Torvalds committed
648
	if (IS_GETLK(cmd)) {
649
		if(experimEnabled && 
650 651 652
		   (cifs_sb->tcon->ses->capabilities & CAP_UNIX) &&
		   (CIFS_UNIX_FCNTL_CAP & 
			le64_to_cpu(cifs_sb->tcon->fsUnixInfo.Capability))) {
653 654 655 656 657 658
			int posix_lock_type;
			if(lockType & LOCKING_ANDX_SHARED_LOCK)
				posix_lock_type = CIFS_RDLCK;
			else
				posix_lock_type = CIFS_WRLCK;
			rc = CIFSSMBPosixLock(xid, pTcon, netfid, 1 /* get */,
659
					length,	pfLock,
660 661 662 663 664 665 666 667
					posix_lock_type, wait_flag);
			FreeXid(xid);
			return rc;
		}

		/* BB we could chain these into one lock request BB */
		rc = CIFSSMBLock(xid, pTcon, netfid, length, pfLock->fl_start,
				 0, 1, lockType, 0 /* wait flag */ );
Linus Torvalds's avatar
Linus Torvalds committed
668
		if (rc == 0) {
669
			rc = CIFSSMBLock(xid, pTcon, netfid, length, 
Linus Torvalds's avatar
Linus Torvalds committed
670 671 672 673 674 675
					 pfLock->fl_start, 1 /* numUnlock */ ,
					 0 /* numLock */ , lockType,
					 0 /* wait flag */ );
			pfLock->fl_type = F_UNLCK;
			if (rc != 0)
				cERROR(1, ("Error unlocking previously locked "
676
					   "range %d during test of lock", rc));
Linus Torvalds's avatar
Linus Torvalds committed
677 678 679 680 681 682 683 684 685 686 687
			rc = 0;

		} else {
			/* if rc == ERR_SHARING_VIOLATION ? */
			rc = 0;	/* do not change lock type to unlock
				   since range in use */
		}

		FreeXid(xid);
		return rc;
	}
688
	if (experimEnabled &&
689 690 691
		(cifs_sb->tcon->ses->capabilities & CAP_UNIX) &&
		(CIFS_UNIX_FCNTL_CAP &
			 le64_to_cpu(cifs_sb->tcon->fsUnixInfo.Capability))) {
692 693 694 695 696 697 698
		int posix_lock_type;
		if(lockType & LOCKING_ANDX_SHARED_LOCK)
			posix_lock_type = CIFS_RDLCK;
		else
			posix_lock_type = CIFS_WRLCK;
		
		if(numUnlock == 1)
699
			posix_lock_type = CIFS_UNLCK;
700 701 702 703 704 705 706
		else if(numLock == 0) {
			/* if no lock or unlock then nothing
			to do since we do not know what it is */
			FreeXid(xid);
			return -EOPNOTSUPP;
		}
		rc = CIFSSMBPosixLock(xid, pTcon, netfid, 0 /* set */,
707
				      length, pfLock,
708 709 710 711
				      posix_lock_type, wait_flag);
	} else
		rc = CIFSSMBLock(xid, pTcon, netfid, length, pfLock->fl_start,
				numUnlock, numLock, lockType, wait_flag);
712
	if (pfLock->fl_flags & FL_POSIX)
Linus Torvalds's avatar
Linus Torvalds committed
713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812
		posix_lock_file_wait(file, pfLock);
	FreeXid(xid);
	return rc;
}

ssize_t cifs_user_write(struct file *file, const char __user *write_data,
	size_t write_size, loff_t *poffset)
{
	int rc = 0;
	unsigned int bytes_written = 0;
	unsigned int total_written;
	struct cifs_sb_info *cifs_sb;
	struct cifsTconInfo *pTcon;
	int xid, long_op;
	struct cifsFileInfo *open_file;

	if (file->f_dentry == NULL)
		return -EBADF;

	cifs_sb = CIFS_SB(file->f_dentry->d_sb);
	if (cifs_sb == NULL)
		return -EBADF;

	pTcon = cifs_sb->tcon;

	/* cFYI(1,
	   (" write %d bytes to offset %lld of %s", write_size,
	   *poffset, file->f_dentry->d_name.name)); */

	if (file->private_data == NULL)
		return -EBADF;
	else
		open_file = (struct cifsFileInfo *) file->private_data;
	
	xid = GetXid();
	if (file->f_dentry->d_inode == NULL) {
		FreeXid(xid);
		return -EBADF;
	}

	if (*poffset > file->f_dentry->d_inode->i_size)
		long_op = 2; /* writes past end of file can take a long time */
	else
		long_op = 1;

	for (total_written = 0; write_size > total_written;
	     total_written += bytes_written) {
		rc = -EAGAIN;
		while (rc == -EAGAIN) {
			if (file->private_data == NULL) {
				/* file has been closed on us */
				FreeXid(xid);
			/* if we have gotten here we have written some data
			   and blocked, and the file has been freed on us while
			   we blocked so return what we managed to write */
				return total_written;
			} 
			if (open_file->closePend) {
				FreeXid(xid);
				if (total_written)
					return total_written;
				else
					return -EBADF;
			}
			if (open_file->invalidHandle) {
				if ((file->f_dentry == NULL) ||
				    (file->f_dentry->d_inode == NULL)) {
					FreeXid(xid);
					return total_written;
				}
				/* we could deadlock if we called
				   filemap_fdatawait from here so tell
				   reopen_file not to flush data to server
				   now */
				rc = cifs_reopen_file(file->f_dentry->d_inode,
					file, FALSE);
				if (rc != 0)
					break;
			}

			rc = CIFSSMBWrite(xid, pTcon,
				open_file->netfid,
				min_t(const int, cifs_sb->wsize,
				      write_size - total_written),
				*poffset, &bytes_written,
				NULL, write_data + total_written, long_op);
		}
		if (rc || (bytes_written == 0)) {
			if (total_written)
				break;
			else {
				FreeXid(xid);
				return rc;
			}
		} else
			*poffset += bytes_written;
		long_op = FALSE; /* subsequent writes fast -
				    15 seconds is plenty */
	}

813
	cifs_stats_bytes_written(pTcon, total_written);
Linus Torvalds's avatar
Linus Torvalds committed
814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852

	/* since the write may have blocked check these pointers again */
	if (file->f_dentry) {
		if (file->f_dentry->d_inode) {
			struct inode *inode = file->f_dentry->d_inode;
			inode->i_ctime = inode->i_mtime =
				current_fs_time(inode->i_sb);
			if (total_written > 0) {
				if (*poffset > file->f_dentry->d_inode->i_size)
					i_size_write(file->f_dentry->d_inode,
					*poffset);
			}
			mark_inode_dirty_sync(file->f_dentry->d_inode);
		}
	}
	FreeXid(xid);
	return total_written;
}

static ssize_t cifs_write(struct file *file, const char *write_data,
	size_t write_size, loff_t *poffset)
{
	int rc = 0;
	unsigned int bytes_written = 0;
	unsigned int total_written;
	struct cifs_sb_info *cifs_sb;
	struct cifsTconInfo *pTcon;
	int xid, long_op;
	struct cifsFileInfo *open_file;

	if (file->f_dentry == NULL)
		return -EBADF;

	cifs_sb = CIFS_SB(file->f_dentry->d_sb);
	if (cifs_sb == NULL)
		return -EBADF;

	pTcon = cifs_sb->tcon;

Steve French's avatar
Steve French committed
853 854
	cFYI(1,("write %zd bytes to offset %lld of %s", write_size,
	   *poffset, file->f_dentry->d_name.name));
Linus Torvalds's avatar
Linus Torvalds committed
855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906

	if (file->private_data == NULL)
		return -EBADF;
	else
		open_file = (struct cifsFileInfo *)file->private_data;
	
	xid = GetXid();
	if (file->f_dentry->d_inode == NULL) {
		FreeXid(xid);
		return -EBADF;
	}

	if (*poffset > file->f_dentry->d_inode->i_size)
		long_op = 2; /* writes past end of file can take a long time */
	else
		long_op = 1;

	for (total_written = 0; write_size > total_written;
	     total_written += bytes_written) {
		rc = -EAGAIN;
		while (rc == -EAGAIN) {
			if (file->private_data == NULL) {
				/* file has been closed on us */
				FreeXid(xid);
			/* if we have gotten here we have written some data
			   and blocked, and the file has been freed on us
			   while we blocked so return what we managed to 
			   write */
				return total_written;
			} 
			if (open_file->closePend) {
				FreeXid(xid);
				if (total_written)
					return total_written;
				else
					return -EBADF;
			}
			if (open_file->invalidHandle) {
				if ((file->f_dentry == NULL) ||
				   (file->f_dentry->d_inode == NULL)) {
					FreeXid(xid);
					return total_written;
				}
				/* we could deadlock if we called
				   filemap_fdatawait from here so tell
				   reopen_file not to flush data to 
				   server now */
				rc = cifs_reopen_file(file->f_dentry->d_inode,
					file, FALSE);
				if (rc != 0)
					break;
			}
Steve French's avatar
Steve French committed
907
			if(experimEnabled || (pTcon->ses->server &&
908 909
				((pTcon->ses->server->secMode & 
				(SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED))
Steve French's avatar
Steve French committed
910
				== 0))) {
911 912 913
				struct kvec iov[2];
				unsigned int len;

914
				len = min((size_t)cifs_sb->wsize,
915 916 917 918 919
					  write_size - total_written);
				/* iov[0] is reserved for smb header */
				iov[1].iov_base = (char *)write_data +
						  total_written;
				iov[1].iov_len = len;
920
				rc = CIFSSMBWrite2(xid, pTcon,
921
						open_file->netfid, len,
922
						*poffset, &bytes_written,
923
						iov, 1, long_op);
924
			} else
925 926 927 928 929 930 931
				rc = CIFSSMBWrite(xid, pTcon,
					 open_file->netfid,
					 min_t(const int, cifs_sb->wsize,
					       write_size - total_written),
					 *poffset, &bytes_written,
					 write_data + total_written,
					 NULL, long_op);
Linus Torvalds's avatar
Linus Torvalds committed
932 933 934 935 936 937 938 939 940 941 942 943 944 945
		}
		if (rc || (bytes_written == 0)) {
			if (total_written)
				break;
			else {
				FreeXid(xid);
				return rc;
			}
		} else
			*poffset += bytes_written;
		long_op = FALSE; /* subsequent writes fast - 
				    15 seconds is plenty */
	}

946
	cifs_stats_bytes_written(pTcon, total_written);
Linus Torvalds's avatar
Linus Torvalds committed
947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964

	/* since the write may have blocked check these pointers again */
	if (file->f_dentry) {
		if (file->f_dentry->d_inode) {
			file->f_dentry->d_inode->i_ctime = 
			file->f_dentry->d_inode->i_mtime = CURRENT_TIME;
			if (total_written > 0) {
				if (*poffset > file->f_dentry->d_inode->i_size)
					i_size_write(file->f_dentry->d_inode, 
						     *poffset);
			}
			mark_inode_dirty_sync(file->f_dentry->d_inode);
		}
	}
	FreeXid(xid);
	return total_written;
}

965
struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode)
966 967
{
	struct cifsFileInfo *open_file;
968
	int rc;
969

970 971 972 973 974 975 976 977 978 979
	/* Having a null inode here (because mapping->host was set to zero by
	the VFS or MM) should not happen but we had reports of on oops (due to
	it being zero) during stress testcases so we need to check for it */

	if(cifs_inode == NULL) {
		cERROR(1,("Null inode passed to cifs_writeable_file"));
		dump_stack();
		return NULL;
	}

980 981 982 983 984 985 986
	read_lock(&GlobalSMBSeslock);
	list_for_each_entry(open_file, &cifs_inode->openFileList, flist) {
		if (open_file->closePend)
			continue;
		if (open_file->pfile &&
		    ((open_file->pfile->f_flags & O_RDWR) ||
		     (open_file->pfile->f_flags & O_WRONLY))) {
987
			atomic_inc(&open_file->wrtPending);
988
			read_unlock(&GlobalSMBSeslock);
989
			if((open_file->invalidHandle) && 
990
			   (!open_file->closePend) /* BB fixme -since the second clause can not be true remove it BB */) {
991
				rc = cifs_reopen_file(&cifs_inode->vfs_inode, 
992 993 994 995
						      open_file->pfile, FALSE);
				/* if it fails, try another handle - might be */
				/* dangerous to hold up writepages with retry */
				if(rc) {
996
					cFYI(1,("failed on reopen file in wp"));
997
					read_lock(&GlobalSMBSeslock);
998 999 1000 1001
					/* can not use this handle, no write
					pending on this one after all */
					atomic_dec
					     (&open_file->wrtPending);
1002 1003 1004
					continue;
				}
			}
1005 1006 1007 1008 1009 1010 1011
			return open_file;
		}
	}
	read_unlock(&GlobalSMBSeslock);
	return NULL;
}

Linus Torvalds's avatar
Linus Torvalds committed
1012 1013 1014 1015 1016 1017 1018 1019 1020 1021
static int cifs_partialpagewrite(struct page *page, unsigned from, unsigned to)
{
	struct address_space *mapping = page->mapping;
	loff_t offset = (loff_t)page->index << PAGE_CACHE_SHIFT;
	char *write_data;
	int rc = -EFAULT;
	int bytes_written = 0;
	struct cifs_sb_info *cifs_sb;
	struct cifsTconInfo *pTcon;
	struct inode *inode;
1022
	struct cifsFileInfo *open_file;
Linus Torvalds's avatar
Linus Torvalds committed
1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049

	if (!mapping || !mapping->host)
		return -EFAULT;

	inode = page->mapping->host;
	cifs_sb = CIFS_SB(inode->i_sb);
	pTcon = cifs_sb->tcon;

	offset += (loff_t)from;
	write_data = kmap(page);
	write_data += from;

	if ((to > PAGE_CACHE_SIZE) || (from > to)) {
		kunmap(page);
		return -EIO;
	}

	/* racing with truncate? */
	if (offset > mapping->host->i_size) {
		kunmap(page);
		return 0; /* don't care */
	}

	/* check to make sure that we are not extending the file */
	if (mapping->host->i_size - offset < (loff_t)to)
		to = (unsigned)(mapping->host->i_size - offset); 

1050 1051 1052 1053
	open_file = find_writable_file(CIFS_I(mapping->host));
	if (open_file) {
		bytes_written = cifs_write(open_file->pfile, write_data,
					   to-from, &offset);
1054
		atomic_dec(&open_file->wrtPending);
Linus Torvalds's avatar
Linus Torvalds committed
1055
		/* Does mm or vfs already set times? */
1056 1057 1058 1059 1060 1061
		inode->i_atime = inode->i_mtime = current_fs_time(inode->i_sb);
		if ((bytes_written > 0) && (offset)) {
			rc = 0;
		} else if (bytes_written < 0) {
			if (rc != -EBADF)
				rc = bytes_written;
Linus Torvalds's avatar
Linus Torvalds committed
1062
		}
1063
	} else {
Linus Torvalds's avatar
Linus Torvalds committed
1064 1065 1066 1067 1068 1069 1070 1071 1072
		cFYI(1, ("No writeable filehandles for inode"));
		rc = -EIO;
	}

	kunmap(page);
	return rc;
}

static int cifs_writepages(struct address_space *mapping,
1073
			   struct writeback_control *wbc)
Linus Torvalds's avatar
Linus Torvalds committed
1074
{
1075 1076 1077 1078 1079 1080 1081 1082 1083
	struct backing_dev_info *bdi = mapping->backing_dev_info;
	unsigned int bytes_to_write;
	unsigned int bytes_written;
	struct cifs_sb_info *cifs_sb;
	int done = 0;
	pgoff_t end = -1;
	pgoff_t index;
	int is_range = 0;
	struct kvec iov[32];
1084
	int len;
1085 1086 1087 1088
	int n_iov = 0;
	pgoff_t next;
	int nr_pages;
	__u64 offset = 0;
1089
	struct cifsFileInfo *open_file;
1090 1091 1092 1093
	struct page *page;
	struct pagevec pvec;
	int rc = 0;
	int scanned = 0;
Linus Torvalds's avatar
Linus Torvalds committed
1094 1095
	int xid;

1096 1097 1098 1099 1100 1101 1102 1103 1104
	cifs_sb = CIFS_SB(mapping->host->i_sb);
	
	/*
	 * If wsize is smaller that the page cache size, default to writing
	 * one page at a time via cifs_writepage
	 */
	if (cifs_sb->wsize < PAGE_CACHE_SIZE)
		return generic_writepages(mapping, wbc);

1105 1106 1107
	if((cifs_sb->tcon->ses) && (cifs_sb->tcon->ses->server))
		if(cifs_sb->tcon->ses->server->secMode &
                          (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED))
1108 1109
			if(!experimEnabled)
				return generic_writepages(mapping, wbc);
1110

1111 1112 1113 1114 1115 1116 1117 1118 1119
	/*
	 * BB: Is this meaningful for a non-block-device file system?
	 * If it is, we should test it again after we do I/O
	 */
	if (wbc->nonblocking && bdi_write_congested(bdi)) {
		wbc->encountered_congestion = 1;
		return 0;
	}

Linus Torvalds's avatar
Linus Torvalds committed
1120 1121
	xid = GetXid();

1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187
	pagevec_init(&pvec, 0);
	if (wbc->sync_mode == WB_SYNC_NONE)
		index = mapping->writeback_index; /* Start from prev offset */
	else {
		index = 0;
		scanned = 1;
	}
	if (wbc->start || wbc->end) {
		index = wbc->start >> PAGE_CACHE_SHIFT;
		end = wbc->end >> PAGE_CACHE_SHIFT;
		is_range = 1;
		scanned = 1;
	}
retry:
	while (!done && (index <= end) &&
	       (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
			PAGECACHE_TAG_DIRTY,
			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1))) {
		int first;
		unsigned int i;

		first = -1;
		next = 0;
		n_iov = 0;
		bytes_to_write = 0;

		for (i = 0; i < nr_pages; i++) {
			page = pvec.pages[i];
			/*
			 * At this point we hold neither mapping->tree_lock nor
			 * lock on the page itself: the page may be truncated or
			 * invalidated (changing page->mapping to NULL), or even
			 * swizzled back from swapper_space to tmpfs file
			 * mapping
			 */

			if (first < 0)
				lock_page(page);
			else if (TestSetPageLocked(page))
				break;

			if (unlikely(page->mapping != mapping)) {
				unlock_page(page);
				break;
			}

			if (unlikely(is_range) && (page->index > end)) {
				done = 1;
				unlock_page(page);
				break;
			}

			if (next && (page->index != next)) {
				/* Not next consecutive page */
				unlock_page(page);
				break;
			}

			if (wbc->sync_mode != WB_SYNC_NONE)
				wait_on_page_writeback(page);

			if (PageWriteback(page) ||
					!test_clear_page_dirty(page)) {
				unlock_page(page);
				break;
			}
1188 1189 1190 1191 1192 1193 1194

			if (page_offset(page) >= mapping->host->i_size) {
				done = 1;
				unlock_page(page);
				break;
			}

1195 1196 1197 1198 1199
			/*
			 * BB can we get rid of this?  pages are held by pvec
			 */
			page_cache_get(page);

1200 1201 1202
			len = min(mapping->host->i_size - page_offset(page),
				  (loff_t)PAGE_CACHE_SIZE);

1203 1204 1205
			/* reserve iov[0] for the smb header */
			n_iov++;
			iov[n_iov].iov_base = kmap(page);
1206 1207
			iov[n_iov].iov_len = len;
			bytes_to_write += len;
1208 1209 1210 1211 1212 1213 1214 1215 1216 1217

			if (first < 0) {
				first = i;
				offset = page_offset(page);
			}
			next = page->index + 1;
			if (bytes_to_write + PAGE_CACHE_SIZE > cifs_sb->wsize)
				break;
		}
		if (n_iov) {
1218 1219 1220 1221 1222 1223 1224 1225
			/* Search for a writable handle every time we call
			 * CIFSSMBWrite2.  We can't rely on the last handle
			 * we used to still be valid
			 */
			open_file = find_writable_file(CIFS_I(mapping->host));
			if (!open_file) {
				cERROR(1, ("No writable handles for inode"));
				rc = -EBADF;
Steve French's avatar
Steve French committed
1226
			} else {
1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242
				rc = CIFSSMBWrite2(xid, cifs_sb->tcon,
						   open_file->netfid,
						   bytes_to_write, offset,
						   &bytes_written, iov, n_iov,
						   1);
				atomic_dec(&open_file->wrtPending);
				if (rc || bytes_written < bytes_to_write) {
					cERROR(1,("Write2 ret %d, written = %d",
						  rc, bytes_written));
					/* BB what if continued retry is
					   requested via mount flags? */
					set_bit(AS_EIO, &mapping->flags);
				} else {
					cifs_stats_bytes_written(cifs_sb->tcon,
								 bytes_written);
				}
1243 1244 1245
			}
			for (i = 0; i < n_iov; i++) {
				page = pvec.pages[first + i];
1246 1247 1248 1249 1250 1251 1252
				/* Should we also set page error on
				success rc but too little data written? */
				/* BB investigate retry logic on temporary
				server crash cases and how recovery works
				when page marked as error */ 
				if(rc)
					SetPageError(page);
1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274
				kunmap(page);
				unlock_page(page);
				page_cache_release(page);
			}
			if ((wbc->nr_to_write -= n_iov) <= 0)
				done = 1;
			index = next;
		}
		pagevec_release(&pvec);
	}
	if (!scanned && !done) {
		/*
		 * We hit the last page and there is more work to be done: wrap
		 * back to the start of the file
		 */
		scanned = 1;
		index = 0;
		goto retry;
	}
	if (!is_range)
		mapping->writeback_index = index;

Linus Torvalds's avatar
Linus Torvalds committed
1275
	FreeXid(xid);
1276

Linus Torvalds's avatar
Linus Torvalds committed
1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387
	return rc;
}

static int cifs_writepage(struct page* page, struct writeback_control *wbc)
{
	int rc = -EFAULT;
	int xid;

	xid = GetXid();
/* BB add check for wbc flags */
	page_cache_get(page);
        if (!PageUptodate(page)) {
		cFYI(1, ("ppw - page not up to date"));
	}
	
	rc = cifs_partialpagewrite(page, 0, PAGE_CACHE_SIZE);
	SetPageUptodate(page); /* BB add check for error and Clearuptodate? */
	unlock_page(page);
	page_cache_release(page);	
	FreeXid(xid);
	return rc;
}

static int cifs_commit_write(struct file *file, struct page *page,
	unsigned offset, unsigned to)
{
	int xid;
	int rc = 0;
	struct inode *inode = page->mapping->host;
	loff_t position = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
	char *page_data;

	xid = GetXid();
	cFYI(1, ("commit write for page %p up to position %lld for %d", 
		 page, position, to));
	if (position > inode->i_size) {
		i_size_write(inode, position);
		/* if (file->private_data == NULL) {
			rc = -EBADF;
		} else {
			open_file = (struct cifsFileInfo *)file->private_data;
			cifs_sb = CIFS_SB(inode->i_sb);
			rc = -EAGAIN;
			while (rc == -EAGAIN) {
				if ((open_file->invalidHandle) && 
				    (!open_file->closePend)) {
					rc = cifs_reopen_file(
						file->f_dentry->d_inode, file);
					if (rc != 0)
						break;
				}
				if (!open_file->closePend) {
					rc = CIFSSMBSetFileSize(xid,
						cifs_sb->tcon, position,
						open_file->netfid,
						open_file->pid, FALSE);
				} else {
					rc = -EBADF;
					break;
				}
			}
			cFYI(1, (" SetEOF (commit write) rc = %d", rc));
		} */
	}
	if (!PageUptodate(page)) {
		position =  ((loff_t)page->index << PAGE_CACHE_SHIFT) + offset;
		/* can not rely on (or let) writepage write this data */
		if (to < offset) {
			cFYI(1, ("Illegal offsets, can not copy from %d to %d",
				offset, to));
			FreeXid(xid);
			return rc;
		}
		/* this is probably better than directly calling
		   partialpage_write since in this function the file handle is
		   known which we might as well	leverage */
		/* BB check if anything else missing out of ppw
		   such as updating last write time */
		page_data = kmap(page);
		rc = cifs_write(file, page_data + offset, to-offset,
				&position);
		if (rc > 0)
			rc = 0;
		/* else if (rc < 0) should we set writebehind rc? */
		kunmap(page);
	} else {	
		set_page_dirty(page);
	}

	FreeXid(xid);
	return rc;
}

int cifs_fsync(struct file *file, struct dentry *dentry, int datasync)
{
	int xid;
	int rc = 0;
	struct inode *inode = file->f_dentry->d_inode;

	xid = GetXid();

	cFYI(1, ("Sync file - name: %s datasync: 0x%x ", 
		dentry->d_name.name, datasync));
	
	rc = filemap_fdatawrite(inode->i_mapping);
	if (rc == 0)
		CIFS_I(inode)->write_behind_rc = 0;
	FreeXid(xid);
	return rc;
}

1388
/* static void cifs_sync_page(struct page *page)
Linus Torvalds's avatar
Linus Torvalds committed
1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401
{
	struct address_space *mapping;
	struct inode *inode;
	unsigned long index = page->index;
	unsigned int rpages = 0;
	int rc = 0;

	cFYI(1, ("sync page %p",page));
	mapping = page->mapping;
	if (!mapping)
		return 0;
	inode = mapping->host;
	if (!inode)
1402
		return; */
Linus Torvalds's avatar
Linus Torvalds committed
1403 1404 1405 1406 1407 1408

/*	fill in rpages then 
	result = cifs_pagein_inode(inode, index, rpages); */ /* BB finish */

/*	cFYI(1, ("rpages is %d for sync page of Index %ld ", rpages, index));

1409
#if 0
Linus Torvalds's avatar
Linus Torvalds committed
1410 1411 1412
	if (rc < 0)
		return rc;
	return 0;
1413
#endif
Linus Torvalds's avatar
Linus Torvalds committed
1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478
} */

/*
 * As file closes, flush all cached write data for this inode checking
 * for write behind errors.
 */
int cifs_flush(struct file *file)
{
	struct inode * inode = file->f_dentry->d_inode;
	int rc = 0;

	/* Rather than do the steps manually:
	   lock the inode for writing
	   loop through pages looking for write behind data (dirty pages)
	   coalesce into contiguous 16K (or smaller) chunks to write to server
	   send to server (prefer in parallel)
	   deal with writebehind errors
	   unlock inode for writing
	   filemapfdatawrite appears easier for the time being */

	rc = filemap_fdatawrite(inode->i_mapping);
	if (!rc) /* reset wb rc if we were able to write out dirty pages */
		CIFS_I(inode)->write_behind_rc = 0;
		
	cFYI(1, ("Flush inode %p file %p rc %d",inode,file,rc));

	return rc;
}

ssize_t cifs_user_read(struct file *file, char __user *read_data,
	size_t read_size, loff_t *poffset)
{
	int rc = -EACCES;
	unsigned int bytes_read = 0;
	unsigned int total_read = 0;
	unsigned int current_read_size;
	struct cifs_sb_info *cifs_sb;
	struct cifsTconInfo *pTcon;
	int xid;
	struct cifsFileInfo *open_file;
	char *smb_read_data;
	char __user *current_offset;
	struct smb_com_read_rsp *pSMBr;

	xid = GetXid();
	cifs_sb = CIFS_SB(file->f_dentry->d_sb);
	pTcon = cifs_sb->tcon;

	if (file->private_data == NULL) {
		FreeXid(xid);
		return -EBADF;
	}
	open_file = (struct cifsFileInfo *)file->private_data;

	if ((file->f_flags & O_ACCMODE) == O_WRONLY) {
		cFYI(1, ("attempting read on write only file instance"));
	}
	for (total_read = 0, current_offset = read_data;
	     read_size > total_read;
	     total_read += bytes_read, current_offset += bytes_read) {
		current_read_size = min_t(const int, read_size - total_read, 
					  cifs_sb->rsize);
		rc = -EAGAIN;
		smb_read_data = NULL;
		while (rc == -EAGAIN) {
1479
			int buf_type = CIFS_NO_BUFFER;
Linus Torvalds's avatar
Linus Torvalds committed
1480 1481 1482 1483 1484 1485 1486
			if ((open_file->invalidHandle) && 
			    (!open_file->closePend)) {
				rc = cifs_reopen_file(file->f_dentry->d_inode,
					file, TRUE);
				if (rc != 0)
					break;
			}
1487
			rc = CIFSSMBRead(xid, pTcon,
1488 1489 1490 1491
					 open_file->netfid,
					 current_read_size, *poffset,
					 &bytes_read, &smb_read_data,
					 &buf_type);
Linus Torvalds's avatar
Linus Torvalds committed
1492 1493
			pSMBr = (struct smb_com_read_rsp *)smb_read_data;
			if (smb_read_data) {
1494 1495 1496 1497 1498 1499 1500 1501
				if (copy_to_user(current_offset,
						smb_read_data +
						4 /* RFC1001 length field */ +
						le16_to_cpu(pSMBr->DataOffset),
						bytes_read)) {
					rc = -EFAULT;
				}

1502 1503 1504 1505
				if(buf_type == CIFS_SMALL_BUFFER)
					cifs_small_buf_release(smb_read_data);
				else if(buf_type == CIFS_LARGE_BUFFER)
					cifs_buf_release(smb_read_data);
Linus Torvalds's avatar
Linus Torvalds committed
1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516
				smb_read_data = NULL;
			}
		}
		if (rc || (bytes_read == 0)) {
			if (total_read) {
				break;
			} else {
				FreeXid(xid);
				return rc;
			}
		} else {
1517
			cifs_stats_bytes_read(pTcon, bytes_read);
Linus Torvalds's avatar
Linus Torvalds committed
1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537
			*poffset += bytes_read;
		}
	}
	FreeXid(xid);
	return total_read;
}


static ssize_t cifs_read(struct file *file, char *read_data, size_t read_size,
	loff_t *poffset)
{
	int rc = -EACCES;
	unsigned int bytes_read = 0;
	unsigned int total_read;
	unsigned int current_read_size;
	struct cifs_sb_info *cifs_sb;
	struct cifsTconInfo *pTcon;
	int xid;
	char *current_offset;
	struct cifsFileInfo *open_file;
1538
	int buf_type = CIFS_NO_BUFFER;
Linus Torvalds's avatar
Linus Torvalds committed
1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557

	xid = GetXid();
	cifs_sb = CIFS_SB(file->f_dentry->d_sb);
	pTcon = cifs_sb->tcon;

	if (file->private_data == NULL) {
		FreeXid(xid);
		return -EBADF;
	}
	open_file = (struct cifsFileInfo *)file->private_data;

	if ((file->f_flags & O_ACCMODE) == O_WRONLY)
		cFYI(1, ("attempting read on write only file instance"));

	for (total_read = 0, current_offset = read_data; 
	     read_size > total_read;
	     total_read += bytes_read, current_offset += bytes_read) {
		current_read_size = min_t(const int, read_size - total_read,
					  cifs_sb->rsize);
1558 1559 1560 1561 1562 1563 1564
		/* For windows me and 9x we do not want to request more
		than it negotiated since it will refuse the read then */
		if((pTcon->ses) && 
			!(pTcon->ses->capabilities & CAP_LARGE_FILES)) {
			current_read_size = min_t(const int, current_read_size,
					pTcon->ses->server->maxBuf - 128);
		}
Linus Torvalds's avatar
Linus Torvalds committed
1565 1566 1567 1568 1569 1570 1571 1572 1573
		rc = -EAGAIN;
		while (rc == -EAGAIN) {
			if ((open_file->invalidHandle) && 
			    (!open_file->closePend)) {
				rc = cifs_reopen_file(file->f_dentry->d_inode,
					file, TRUE);
				if (rc != 0)
					break;
			}
1574
			rc = CIFSSMBRead(xid, pTcon,
1575 1576 1577 1578
					 open_file->netfid,
					 current_read_size, *poffset,
					 &bytes_read, &current_offset,
					 &buf_type);
Linus Torvalds's avatar
Linus Torvalds committed
1579 1580 1581 1582 1583 1584 1585 1586 1587
		}
		if (rc || (bytes_read == 0)) {
			if (total_read) {
				break;
			} else {
				FreeXid(xid);
				return rc;
			}
		} else {
1588
			cifs_stats_bytes_read(pTcon, total_read);
Linus Torvalds's avatar
Linus Torvalds committed
1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631
			*poffset += bytes_read;
		}
	}
	FreeXid(xid);
	return total_read;
}

int cifs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
	struct dentry *dentry = file->f_dentry;
	int rc, xid;

	xid = GetXid();
	rc = cifs_revalidate(dentry);
	if (rc) {
		cFYI(1, ("Validation prior to mmap failed, error=%d", rc));
		FreeXid(xid);
		return rc;
	}
	rc = generic_file_mmap(file, vma);
	FreeXid(xid);
	return rc;
}


static void cifs_copy_cache_pages(struct address_space *mapping, 
	struct list_head *pages, int bytes_read, char *data,
	struct pagevec *plru_pvec)
{
	struct page *page;
	char *target;

	while (bytes_read > 0) {
		if (list_empty(pages))
			break;

		page = list_entry(pages->prev, struct page, lru);
		list_del(&page->lru);

		if (add_to_page_cache(page, mapping, page->index,
				      GFP_KERNEL)) {
			page_cache_release(page);
			cFYI(1, ("Add page cache failed"));
1632 1633
			data += PAGE_CACHE_SIZE;
			bytes_read -= PAGE_CACHE_SIZE;
Linus Torvalds's avatar
Linus Torvalds committed
1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675
			continue;
		}

		target = kmap_atomic(page,KM_USER0);

		if (PAGE_CACHE_SIZE > bytes_read) {
			memcpy(target, data, bytes_read);
			/* zero the tail end of this partial page */
			memset(target + bytes_read, 0, 
			       PAGE_CACHE_SIZE - bytes_read);
			bytes_read = 0;
		} else {
			memcpy(target, data, PAGE_CACHE_SIZE);
			bytes_read -= PAGE_CACHE_SIZE;
		}
		kunmap_atomic(target, KM_USER0);

		flush_dcache_page(page);
		SetPageUptodate(page);
		unlock_page(page);
		if (!pagevec_add(plru_pvec, page))
			__pagevec_lru_add(plru_pvec);
		data += PAGE_CACHE_SIZE;
	}
	return;
}

static int cifs_readpages(struct file *file, struct address_space *mapping,
	struct list_head *page_list, unsigned num_pages)
{
	int rc = -EACCES;
	int xid;
	loff_t offset;
	struct page *page;
	struct cifs_sb_info *cifs_sb;
	struct cifsTconInfo *pTcon;
	int bytes_read = 0;
	unsigned int read_size,i;
	char *smb_read_data = NULL;
	struct smb_com_read_rsp *pSMBr;
	struct pagevec lru_pvec;
	struct cifsFileInfo *open_file;
1676
	int buf_type = CIFS_NO_BUFFER;
Linus Torvalds's avatar
Linus Torvalds committed
1677 1678 1679 1680 1681 1682 1683 1684 1685

	xid = GetXid();
	if (file->private_data == NULL) {
		FreeXid(xid);
		return -EBADF;
	}
	open_file = (struct cifsFileInfo *)file->private_data;
	cifs_sb = CIFS_SB(file->f_dentry->d_sb);
	pTcon = cifs_sb->tcon;
1686

Linus Torvalds's avatar
Linus Torvalds committed
1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731
	pagevec_init(&lru_pvec, 0);

	for (i = 0; i < num_pages; ) {
		unsigned contig_pages;
		struct page *tmp_page;
		unsigned long expected_index;

		if (list_empty(page_list))
			break;

		page = list_entry(page_list->prev, struct page, lru);
		offset = (loff_t)page->index << PAGE_CACHE_SHIFT;

		/* count adjacent pages that we will read into */
		contig_pages = 0;
		expected_index = 
			list_entry(page_list->prev, struct page, lru)->index;
		list_for_each_entry_reverse(tmp_page,page_list,lru) {
			if (tmp_page->index == expected_index) {
				contig_pages++;
				expected_index++;
			} else
				break; 
		}
		if (contig_pages + i >  num_pages)
			contig_pages = num_pages - i;

		/* for reads over a certain size could initiate async
		   read ahead */

		read_size = contig_pages * PAGE_CACHE_SIZE;
		/* Read size needs to be in multiples of one page */
		read_size = min_t(const unsigned int, read_size,
				  cifs_sb->rsize & PAGE_CACHE_MASK);

		rc = -EAGAIN;
		while (rc == -EAGAIN) {
			if ((open_file->invalidHandle) && 
			    (!open_file->closePend)) {
				rc = cifs_reopen_file(file->f_dentry->