Merge git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

58 files changed, 2076 insertions, 1307 deletions

diff --git a/fs/Makefile b/fs/Makefile
index 2168c902d5ca..d9f8afe6f0c4 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -81,8 +81,6 @@ obj-$(CONFIG_HUGETLBFS)		+= hugetlbfs/
 obj-$(CONFIG_CODA_FS)		+= coda/
 obj-$(CONFIG_MINIX_FS)		+= minix/
 obj-$(CONFIG_FAT_FS)		+= fat/
-obj-$(CONFIG_MSDOS_FS)		+= msdos/
-obj-$(CONFIG_VFAT_FS)		+= vfat/
 obj-$(CONFIG_BFS_FS)		+= bfs/
 obj-$(CONFIG_ISO9660_FS)	+= isofs/
 obj-$(CONFIG_HFSPLUS_FS)	+= hfsplus/ # Before hfs to find wrapped HFS+
diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c
index 625abf5422e2..33bf8cbfd051 100644
--- a/fs/autofs4/dev-ioctl.c
+++ b/fs/autofs4/dev-ioctl.c
@@ -128,9 +128,10 @@ static inline void free_dev_ioctl(struct autofs_dev_ioctl *param)
  */
 static int validate_dev_ioctl(int cmd, struct autofs_dev_ioctl *param)
 {
-	int err = -EINVAL;
+	int err;
 
-	if (check_dev_ioctl_version(cmd, param)) {
+	err = check_dev_ioctl_version(cmd, param);
+	if (err) {
 		AUTOFS_WARN("invalid device control module version "
 		     "supplied for cmd(0x%08x)", cmd);
 		goto out;
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index cde2f8e8935a..4b6fb3f628c0 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -56,12 +56,23 @@ static int autofs4_mount_busy(struct vfsmount *mnt, struct dentry *dentry)
 	mntget(mnt);
 	dget(dentry);
 
-	if (!autofs4_follow_mount(&mnt, &dentry))
+	if (!follow_down(&mnt, &dentry))
 		goto done;
 
-	/* This is an autofs submount, we can't expire it */
-	if (is_autofs4_dentry(dentry))
-		goto done;
+	if (is_autofs4_dentry(dentry)) {
+		struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
+
+		/* This is an autofs submount, we can't expire it */
+		if (sbi->type == AUTOFS_TYPE_INDIRECT)
+			goto done;
+
+		/*
+		 * Otherwise it's an offset mount and we need to check
+		 * if we can umount its mount, if there is one.
+		 */
+		if (!d_mountpoint(dentry))
+			goto done;
+	}
 
 	/* Update the expiry counter if fs is busy */
 	if (!may_umount_tree(mnt)) {
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 88a776fa0ef6..db831efbdbbd 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -986,7 +986,6 @@ static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
 static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 {
 	struct gendisk *disk;
-	struct hd_struct *part = NULL;
 	int ret;
 	int partno;
 	int perm = 0;
@@ -1004,24 +1003,25 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 		return ret;
 	}
 
-	ret = -ENXIO;
-
 	lock_kernel();
 
+	ret = -ENXIO;
 	disk = get_gendisk(bdev->bd_dev, &partno);
 	if (!disk)
 		goto out_unlock_kernel;
-	part = disk_get_part(disk, partno);
-	if (!part)
-		goto out_unlock_kernel;
 
 	mutex_lock_nested(&bdev->bd_mutex, for_part);
 	if (!bdev->bd_openers) {
 		bdev->bd_disk = disk;
-		bdev->bd_part = part;
 		bdev->bd_contains = bdev;
 		if (!partno) {
 			struct backing_dev_info *bdi;
+
+			ret = -ENXIO;
+			bdev->bd_part = disk_get_part(disk, partno);
+			if (!bdev->bd_part)
+				goto out_clear;
+
 			if (disk->fops->open) {
 				ret = disk->fops->open(bdev, mode);
 				if (ret)
@@ -1049,18 +1049,17 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 			bdev->bd_contains = whole;
 			bdev->bd_inode->i_data.backing_dev_info =
 			   whole->bd_inode->i_data.backing_dev_info;
+			bdev->bd_part = disk_get_part(disk, partno);
 			if (!(disk->flags & GENHD_FL_UP) ||
-			    !part || !part->nr_sects) {
+			    !bdev->bd_part || !bdev->bd_part->nr_sects) {
 				ret = -ENXIO;
 				goto out_clear;
 			}
-			bd_set_size(bdev, (loff_t)part->nr_sects << 9);
+			bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9);
 		}
 	} else {
-		disk_put_part(part);
 		put_disk(disk);
 		module_put(disk->fops->owner);
-		part = NULL;
 		disk = NULL;
 		if (bdev->bd_contains == bdev) {
 			if (bdev->bd_disk->fops->open) {
@@ -1080,6 +1079,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 	return 0;
 
  out_clear:
+	disk_put_part(bdev->bd_part);
 	bdev->bd_disk = NULL;
 	bdev->bd_part = NULL;
 	bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info;
@@ -1091,7 +1091,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
  out_unlock_kernel:
 	unlock_kernel();
 
-	disk_put_part(part);
 	if (disk)
 		module_put(disk->fops->owner);
 	put_disk(disk);
diff --git a/fs/cifs/CHANGES b/fs/cifs/CHANGES
index 8855331b2fba..e078b7aea143 100644
--- a/fs/cifs/CHANGES
+++ b/fs/cifs/CHANGES
@@ -8,7 +8,11 @@ handling fcntl(F_SETLEASE).  Convert cifs to using blocking tcp
 sends, and also let tcp autotune the socket send and receive buffers.
 This reduces the number of EAGAIN errors returned by TCP/IP in
 high stress workloads (and the number of retries on socket writes
-when sending large SMBWriteX requests).
+when sending large SMBWriteX requests).  Fix case in which a portion of
+data can in some cases not get written to the file on the server before the
+file is closed.  Fix DFS parsing to properly handle path consumed field,
+and to handle certain codepage conversions better.  Fix mount and
+umount race that can cause oops in mount or umount or reconnect.
 
 Version 1.54
 ------------
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index 69a12aae91d3..490e34bbf27a 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -107,12 +107,13 @@ void cifs_dump_mids(struct TCP_Server_Info *server)
 #ifdef CONFIG_PROC_FS
 static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
 {
-	struct list_head *tmp;
-	struct list_head *tmp1;
+	struct list_head *tmp1, *tmp2, *tmp3;
 	struct mid_q_entry *mid_entry;
+	struct TCP_Server_Info *server;
 	struct cifsSesInfo *ses;
 	struct cifsTconInfo *tcon;
-	int i;
+	int i, j;
+	__u32 dev_type;
 
 	seq_puts(m,
 		    "Display Internal CIFS Data Structures for Debugging\n"
@@ -122,46 +123,78 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
 	seq_printf(m, "Servers:");
 
 	i = 0;
-	read_lock(&GlobalSMBSeslock);
-	list_for_each(tmp, &GlobalSMBSessionList) {
+	read_lock(&cifs_tcp_ses_lock);
+	list_for_each(tmp1, &cifs_tcp_ses_list) {
+		server = list_entry(tmp1, struct TCP_Server_Info,
+				    tcp_ses_list);
 		i++;
-		ses = list_entry(tmp, struct cifsSesInfo, cifsSessionList);
-		if ((ses->serverDomain == NULL) || (ses->serverOS == NULL) ||
-		   (ses->serverNOS == NULL)) {
-			seq_printf(m, "\nentry for %s not fully "
-					"displayed\n\t", ses->serverName);
-		} else {
-			seq_printf(m,
-				    "\n%d) Name: %s  Domain: %s Mounts: %d OS:"
-				    " %s  \n\tNOS: %s\tCapability: 0x%x\n\tSMB"
+		list_for_each(tmp2, &server->smb_ses_list) {
+			ses = list_entry(tmp2, struct cifsSesInfo,
+					 smb_ses_list);
+			if ((ses->serverDomain == NULL) ||
+				(ses->serverOS == NULL) ||
+				(ses->serverNOS == NULL)) {
+				seq_printf(m, "\n%d) entry for %s not fully "
+					   "displayed\n\t", i, ses->serverName);
+			} else {
+				seq_printf(m,
+				    "\n%d) Name: %s  Domain: %s Uses: %d OS:"
+				    " %s\n\tNOS: %s\tCapability: 0x%x\n\tSMB"
 				    " session status: %d\t",
 				i, ses->serverName, ses->serverDomain,
-				atomic_read(&ses->inUse),
-				ses->serverOS, ses->serverNOS,
+				ses->ses_count, ses->serverOS, ses->serverNOS,
 				ses->capabilities, ses->status);
-		}
-		if (ses->server) {
+			}
 			seq_printf(m, "TCP status: %d\n\tLocal Users To "
-				    "Server: %d SecMode: 0x%x Req On Wire: %d",
-				ses->server->tcpStatus,
-				atomic_read(&ses->server->socketUseCount),
-				ses->server->secMode,
-				atomic_read(&ses->server->inFlight));
+				   "Server: %d SecMode: 0x%x Req On Wire: %d",
+				   server->tcpStatus, server->srv_count,
+				   server->secMode,
+				   atomic_read(&server->inFlight));
 
 #ifdef CONFIG_CIFS_STATS2
 			seq_printf(m, " In Send: %d In MaxReq Wait: %d",
-				atomic_read(&ses->server->inSend),
-				atomic_read(&ses->server->num_waiters));
+				atomic_read(&server->inSend),
+				atomic_read(&server->num_waiters));
 #endif
 
-			seq_puts(m, "\nMIDs:\n");
+			seq_puts(m, "\n\tShares:");
+			j = 0;
+			list_for_each(tmp3, &ses->tcon_list) {
+				tcon = list_entry(tmp3, struct cifsTconInfo,
+						  tcon_list);
+				++j;
+				dev_type = le32_to_cpu(tcon->fsDevInfo.DeviceType);
+				seq_printf(m, "\n\t%d) %s Mounts: %d ", j,
+					   tcon->treeName, tcon->tc_count);
+				if (tcon->nativeFileSystem) {
+					seq_printf(m, "Type: %s ",
+						   tcon->nativeFileSystem);
+				}
+				seq_printf(m, "DevInfo: 0x%x Attributes: 0x%x"
+					"\nPathComponentMax: %d Status: 0x%d",
+					le32_to_cpu(tcon->fsDevInfo.DeviceCharacteristics),
+					le32_to_cpu(tcon->fsAttrInfo.Attributes),
+					le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength),
+					tcon->tidStatus);
+				if (dev_type == FILE_DEVICE_DISK)
+					seq_puts(m, " type: DISK ");
+				else if (dev_type == FILE_DEVICE_CD_ROM)
+					seq_puts(m, " type: CDROM ");
+				else
+					seq_printf(m, " type: %d ", dev_type);
+
+				if (tcon->need_reconnect)
+					seq_puts(m, "\tDISCONNECTED ");
+				seq_putc(m, '\n');
+			}
+
+			seq_puts(m, "\n\tMIDs:\n");
 
 			spin_lock(&GlobalMid_Lock);
-			list_for_each(tmp1, &ses->server->pending_mid_q) {
-				mid_entry = list_entry(tmp1, struct
-					mid_q_entry,
+			list_for_each(tmp3, &server->pending_mid_q) {
+				mid_entry = list_entry(tmp3, struct mid_q_entry,
 					qhead);
-				seq_printf(m, "State: %d com: %d pid:"
+				seq_printf(m, "\tState: %d com: %d pid:"
 						" %d tsk: %p mid %d\n",
 						mid_entry->midState,
 						(int)mid_entry->command,
@@ -171,44 +204,8 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
 			}
 			spin_unlock(&GlobalMid_Lock);
 		}
-
-	}
-	read_unlock(&GlobalSMBSeslock);
-	seq_putc(m, '\n');
-
-	seq_puts(m, "Shares:");
-
-	i = 0;
-	read_lock(&GlobalSMBSeslock);
-	list_for_each(tmp, &GlobalTreeConnectionList) {
-		__u32 dev_type;
-		i++;
-		tcon = list_entry(tmp, struct cifsTconInfo, cifsConnectionList);
-		dev_type = le32_to_cpu(tcon->fsDevInfo.DeviceType);
-		seq_printf(m, "\n%d) %s Uses: %d ", i,
-				 tcon->treeName, atomic_read(&tcon->useCount));
-		if (tcon->nativeFileSystem) {
-			seq_printf(m, "Type: %s ",
-					 tcon->nativeFileSystem);
-		}
-		seq_printf(m, "DevInfo: 0x%x Attributes: 0x%x"
-				 "\nPathComponentMax: %d Status: %d",
-			    le32_to_cpu(tcon->fsDevInfo.DeviceCharacteristics),
-			    le32_to_cpu(tcon->fsAttrInfo.Attributes),
-			    le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength),
-			    tcon->tidStatus);
-		if (dev_type == FILE_DEVICE_DISK)
-			seq_puts(m, " type: DISK ");
-		else if (dev_type == FILE_DEVICE_CD_ROM)
-			seq_puts(m, " type: CDROM ");
-		else
-			seq_printf(m, " type: %d ", dev_type);
-
-		if (tcon->tidStatus == CifsNeedReconnect)
-			seq_puts(m, "\tDISCONNECTED ");
 	}
-	read_unlock(&GlobalSMBSeslock);
-
+	read_unlock(&cifs_tcp_ses_lock);
 	seq_putc(m, '\n');
 
 	/* BB add code to dump additional info such as TCP session info now */
@@ -234,7 +231,9 @@ static ssize_t cifs_stats_proc_write(struct file *file,
 {
 	char c;
 	int rc;
-	struct list_head *tmp;
+	struct list_head *tmp1, *tmp2, *tmp3;
+	struct TCP_Server_Info *server;
+	struct cifsSesInfo *ses;
 	struct cifsTconInfo *tcon;
 
 	rc = get_user(c, buffer);
@@ -242,33 +241,42 @@ static ssize_t cifs_stats_proc_write(struct file *file,
 		return rc;
 
 	if (c == '1' || c == 'y' || c == 'Y' || c == '0') {
-		read_lock(&GlobalSMBSeslock);
 #ifdef CONFIG_CIFS_STATS2
 		atomic_set(&totBufAllocCount, 0);
 		atomic_set(&totSmBufAllocCount, 0);
 #endif /* CONFIG_CIFS_STATS2 */
-		list_for_each(tmp, &GlobalTreeConnectionList) {
-			tcon = list_entry(tmp, struct cifsTconInfo,
-					cifsConnectionList);
-			atomic_set(&tcon->num_smbs_sent, 0);
-			atomic_set(&tcon->num_writes, 0);
-			atomic_set(&tcon->num_reads, 0);
-			atomic_set(&tcon->num_oplock_brks, 0);
-			atomic_set(&tcon->num_opens, 0);
-			atomic_set(&tcon->num_closes, 0);
-			atomic_set(&tcon->num_deletes, 0);
-			atomic_set(&tcon->num_mkdirs, 0);
-			atomic_set(&tcon->num_rmdirs, 0);
-			atomic_set(&tcon->num_renames, 0);
-			atomic_set(&tcon->num_t2renames, 0);
-			atomic_set(&tcon->num_ffirst, 0);
-			atomic_set(&tcon->num_fnext, 0);
-			atomic_set(&tcon->num_fclose, 0);
-			atomic_set(&tcon->num_hardlinks, 0);
-			atomic_set(&tcon->num_symlinks, 0);
-			atomic_set(&tcon->num_locks, 0);
+		read_lock(&cifs_tcp_ses_lock);
+		list_for_each(tmp1, &cifs_tcp_ses_list) {
+			server = list_entry(tmp1, struct TCP_Server_Info,
+					    tcp_ses_list);
+			list_for_each(tmp2, &server->smb_ses_list) {
+				ses = list_entry(tmp2, struct cifsSesInfo,
+						 smb_ses_list);
+				list_for_each(tmp3, &ses->tcon_list) {
+					tcon = list_entry(tmp3,
+							  struct cifsTconInfo,
+							  tcon_list);
+					atomic_set(&tcon->num_smbs_sent, 0);
+					atomic_set(&tcon->num_writes, 0);
+					atomic_set(&tcon->num_reads, 0);
+					atomic_set(&tcon->num_oplock_brks, 0);
+					atomic_set(&tcon->num_opens, 0);
+					atomic_set(&tcon->num_closes, 0);
+					atomic_set(&tcon->num_deletes, 0);
+					atomic_set(&tcon->num_mkdirs, 0);
+					atomic_set(&tcon->num_rmdirs, 0);
+					atomic_set(&tcon->num_renames, 0);
+					atomic_set(&tcon->num_t2renames, 0);
+					atomic_set(&tcon->num_ffirst, 0);
+					atomic_set(&tcon->num_fnext, 0);
+					atomic_set(&tcon->num_fclose, 0);
+					atomic_set(&tcon->num_hardlinks, 0);
+					atomic_set(&tcon->num_symlinks, 0);
+					atomic_set(&tcon->num_locks, 0);
+				}
+			}
 		}
-		read_unlock(&GlobalSMBSeslock);
+		read_unlock(&cifs_tcp_ses_lock);
 	}
 
 	return count;
@@ -277,7 +285,9 @@ static ssize_t cifs_stats_proc_write(struct file *file,
 static int cifs_stats_proc_show(struct seq_file *m, void *v)
 {
 	int i;
-	struct list_head *tmp;
+	struct list_head *tmp1, *tmp2, *tmp3;
+	struct TCP_Server_Info *server;
+	struct cifsSesInfo *ses;
 	struct cifsTconInfo *tcon;
 
 	seq_printf(m,
@@ -306,44 +316,55 @@ static int cifs_stats_proc_show(struct seq_file *m, void *v)
 		GlobalCurrentXid, GlobalMaxActiveXid);
 
 	i = 0;
-	read_lock(&GlobalSMBSeslock);
-	list_for_each(tmp, &GlobalTreeConnectionList) {
-		i++;
-		tcon = list_entry(tmp, struct cifsTconInfo, cifsConnectionList);
-		seq_printf(m, "\n%d) %s", i, tcon->treeName);
-		if (tcon->tidStatus == CifsNeedReconnect)
-			seq_puts(m, "\tDISCONNECTED ");
-		seq_printf(m, "\nSMBs: %d Oplock Breaks: %d",
-			atomic_read(&tcon->num_smbs_sent),
-			atomic_read(&tcon->num_oplock_brks));
-		seq_printf(m, "\nReads:  %d Bytes: %lld",
-			atomic_read(&tcon->num_reads),
-			(long long)(tcon->bytes_read));
-		seq_printf(m, "\nWrites: %d Bytes: %lld",
-			atomic_read(&tcon->num_writes),
-			(long long)(tcon->bytes_written));
-		seq_printf(m,
-			"\nLocks: %d HardLinks: %d Symlinks: %d",
-			atomic_read(&tcon->num_locks),
-			atomic_read(&tcon->num_hardlinks),
-			atomic_read(&tcon->num_symlinks));
-
-		seq_printf(m, "\nOpens: %d Closes: %d Deletes: %d",
-			atomic_read(&tcon->num_opens),
-			atomic_read(&tcon->num_closes),
-			atomic_read(&tcon->num_deletes));
-		seq_printf(m, "\nMkdirs: %d Rmdirs: %d",
-			atomic_read(&tcon->num_mkdirs),
-			atomic_read(&tcon->num_rmdirs));
-		seq_printf(m, "\nRenames: %d T2 Renames %d",
-			atomic_read(&tcon->num_renames),
-			atomic_read(&tcon->num_t2renames));
-		seq_printf(m, "\nFindFirst: %d FNext %d FClose %d",
-			atomic_read(&tcon->num_ffirst),
-			atomic_read(&tcon->num_fnext),
-			atomic_read(&tcon->num_fclose));
+	read_lock(&cifs_tcp_ses_lock);
+	list_for_each(tmp1, &cifs_tcp_ses_list) {
+		server = list_entry(tmp1, struct TCP_Server_Info,
+				    tcp_ses_list);
+		list_for_each(tmp2, &server->smb_ses_list) {
+			ses = list_entry(tmp2, struct cifsSesInfo,
+					 smb_ses_list);
+			list_for_each(tmp3, &ses->tcon_list) {
+				tcon = list_entry(tmp3,
+						  struct cifsTconInfo,
+						  tcon_list);
+				i++;
+				seq_printf(m, "\n%d) %s", i, tcon->treeName);
+				if (tcon->need_reconnect)
+					seq_puts(m, "\tDISCONNECTED ");
+				seq_printf(m, "\nSMBs: %d Oplock Breaks: %d",
+					atomic_read(&tcon->num_smbs_sent),
+					atomic_read(&tcon->num_oplock_brks));
+				seq_printf(m, "\nReads:  %d Bytes: %lld",
+					atomic_read(&tcon->num_reads),
+					(long long)(tcon->bytes_read));
+				seq_printf(m, "\nWrites: %d Bytes: %lld",
+					atomic_read(&tcon->num_writes),
+					(long long)(tcon->bytes_written));
+				seq_printf(m, "\nLocks: %d HardLinks: %d "
+					      "Symlinks: %d",
+					atomic_read(&tcon->num_locks),
+					atomic_read(&tcon->num_hardlinks),
+					atomic_read(&tcon->num_symlinks));
+				seq_printf(m, "\nOpens: %d Closes: %d"
+					      "Deletes: %d",
+					atomic_read(&tcon->num_opens),
+					atomic_read(&tcon->num_closes),
+					atomic_read(&tcon->num_deletes));
+				seq_printf(m, "\nMkdirs: %d Rmdirs: %d",
+					atomic_read(&tcon->num_mkdirs),
+					atomic_read(&tcon->num_rmdirs));
+				seq_printf(m, "\nRenames: %d T2 Renames %d",
+					atomic_read(&tcon->num_renames),
+					atomic_read(&tcon->num_t2renames));
+				seq_printf(m, "\nFindFirst: %d FNext %d "
+					      "FClose %d",
+					atomic_read(&tcon->num_ffirst),
+					atomic_read(&tcon->num_fnext),
+					atomic_read(&tcon->num_fclose));
+			}
+		}
 	}
-	read_unlock(&GlobalSMBSeslock);
+	read_unlock(&cifs_tcp_ses_lock);
 
 	seq_putc(m, '\n');
 	return 0;
diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index d2c8eef84f3c..e1c18362ba46 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -106,7 +106,8 @@ static char *cifs_get_share_name(const char *node_name)
 /**
  * compose_mount_options	-	creates mount options for refferral
  * @sb_mountdata:	parent/root DFS mount options (template)
- * @ref_unc:		refferral server UNC
+ * @dentry:		point where we are going to mount
+ * @ref:		server's referral
  * @devname:		pointer for saving device name
  *
  * creates mount options for submount based on template options sb_mountdata
@@ -116,7 +117,8 @@ static char *cifs_get_share_name(const char *node_name)
  * Caller is responcible for freeing retunrned value if it is not error.
  */
 static char *compose_mount_options(const char *sb_mountdata,
-				   const char *ref_unc,
+				   struct dentry *dentry,
+				   const struct dfs_info3_param *ref,
 				   char **devname)
 {
 	int rc;
@@ -126,11 +128,12 @@ static char *compose_mount_options(const char *sb_mountdata,
 	char *srvIP = NULL;
 	char sep = ',';
 	int off, noff;
+	char *fullpath;
 
 	if (sb_mountdata == NULL)
 		return ERR_PTR(-EINVAL);
 
-	*devname = cifs_get_share_name(ref_unc);
+	*devname = cifs_get_share_name(ref->node_name);
 	rc = dns_resolve_server_name_to_ip(*devname, &srvIP);
 	if (rc != 0) {
 		cERROR(1, ("%s: Failed to resolve server part of %s to IP",
@@ -138,7 +141,12 @@ static char *compose_mount_options(const char *sb_mountdata,
 		mountdata = ERR_PTR(rc);
 		goto compose_mount_options_out;
 	}
-	md_len = strlen(sb_mountdata) + strlen(srvIP) + strlen(ref_unc) + 3;
+	/* md_len = strlen(...) + 12 for 'sep+prefixpath='
+	 * assuming that we have 'unc=' and 'ip=' in
+	 * the original sb_mountdata
+	 */
+	md_len = strlen(sb_mountdata) + strlen(srvIP) +
+		strlen(ref->node_name) + 12;
 	mountdata = kzalloc(md_len+1, GFP_KERNEL);
 	if (mountdata == NULL) {
 		mountdata = ERR_PTR(-ENOMEM);
@@ -152,41 +160,56 @@ static char *compose_mount_options(const char *sb_mountdata,
 			strncpy(mountdata, sb_mountdata, 5);
 			off += 5;
 	}
-	while ((tkn_e = strchr(sb_mountdata+off, sep))) {
-		noff = (tkn_e - (sb_mountdata+off)) + 1;
-		if (strnicmp(sb_mountdata+off, "unc=", 4) == 0) {
+
+	do {
+		tkn_e = strchr(sb_mountdata + off, sep);
+		if (tkn_e == NULL)
+			noff = strlen(sb_mountdata + off);
+		else
+			noff = tkn_e - (sb_mountdata + off) + 1;
+
+		if (strnicmp(sb_mountdata + off, "unc=", 4) == 0) {
 			off += noff;
 			continue;
 		}
-		if (strnicmp(sb_mountdata+off, "ip=", 3) == 0) {
+		if (strnicmp(sb_mountdata + off, "ip=", 3) == 0) {
 			off += noff;
 			continue;
 		}
-		if (strnicmp(sb_mountdata+off, "prefixpath=", 3) == 0) {
+		if (strnicmp(sb_mountdata + off, "prefixpath=", 11) == 0) {
 			off += noff;
 			continue;
 		}
-		strncat(mountdata, sb_mountdata+off, noff);
+		strncat(mountdata, sb_mountdata + off, noff);
 		off += noff;
-	}
-	strcat(mountdata, sb_mountdata+off);
+	} while (tkn_e);
+	strcat(mountdata, sb_mountdata + off);
 	mountdata[md_len] = '\0';
 
 	/* copy new IP and ref share name */
-	strcat(mountdata, ",ip=");
+	if (mountdata[strlen(mountdata) - 1] != sep)
+		strncat(mountdata, &sep, 1);
+	strcat(mountdata, "ip=");
 	strcat(mountdata, srvIP);
-	strcat(mountdata, ",unc=");
+	strncat(mountdata, &sep, 1);
+	strcat(mountdata, "unc=");
 	strcat(mountdata, *devname);
 
 	/* find & copy prefixpath */
-	tkn_e = strchr(ref_unc+2, '\\');
-	if (tkn_e) {
-		tkn_e = strchr(tkn_e+1, '\\');
-		if (tkn_e) {
-			strcat(mountdata, ",prefixpath=");
-			strcat(mountdata, tkn_e+1);
-		}
+	tkn_e = strchr(ref->node_name + 2, '\\');
+	if (tkn_e == NULL) /* invalid unc, missing share name*/
+		goto compose_mount_options_out;
+
+	fullpath = build_path_from_dentry(dentry);
+	tkn_e = strchr(tkn_e + 1, '\\');
+	if (tkn_e || strlen(fullpath) - (ref->path_consumed)) {
+		strncat(mountdata, &sep, 1);
+		strcat(mountdata, "prefixpath=");
+		if (tkn_e)
+			strcat(mountdata, tkn_e + 1);
+		strcat(mountdata, fullpath + (ref->path_consumed));
 	}
+	kfree(fullpath);
 
 	/*cFYI(1,("%s: parent mountdata: %s", __func__,sb_mountdata));*/
 	/*cFYI(1, ("%s: submount mountdata: %s", __func__, mountdata ));*/
@@ -198,7 +221,7 @@ compose_mount_options_out:
 
 
 static struct vfsmount *cifs_dfs_do_refmount(const struct vfsmount *mnt_parent,
-		struct dentry *dentry, char *ref_unc)
+		struct dentry *dentry, const struct dfs_info3_param *ref)
 {
 	struct cifs_sb_info *cifs_sb;
 	struct vfsmount *mnt;
@@ -207,7 +230,7 @@ static struct vfsmount *cifs_dfs_do_refmount(const struct vfsmount *mnt_parent,
 
 	cifs_sb = CIFS_SB(dentry->d_inode->i_sb);
 	mountdata = compose_mount_options(cifs_sb->mountdata,
-						ref_unc, &devname);
+						dentry, ref, &devname);
 
 	if (IS_ERR(mountdata))
 		return (struct vfsmount *)mountdata;
@@ -310,7 +333,7 @@ cifs_dfs_follow_mountpoint(struct dentry *dentry, struct nameidata *nd)
 			}
 			mnt = cifs_dfs_do_refmount(nd->path.mnt,
 						nd->path.dentry,
-						referrals[i].node_name);
+						referrals + i);
 			cFYI(1, ("%s: cifs_dfs_do_refmount:%s , mnt:%p",
 					 __func__,
 					referrals[i].node_name, mnt));
diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c
index fcee9298b620..0ab2fb5afef1 100644
--- a/fs/cifs/cifs_spnego.c
+++ b/fs/cifs/cifs_spnego.c
@@ -73,8 +73,8 @@ struct key_type cifs_spnego_key_type = {
  * strlen(";sec=ntlmsspi") */
 #define MAX_MECH_STR_LEN	13
 
-/* max possible addr len eg FEDC:BA98:7654:3210:FEDC:BA98:7654:3210/60 */
-#define MAX_IPV6_ADDR_LEN	42
+/* max possible addr len eg FEDC:BA98:7654:3210:FEDC:BA98:7654:3210/128 */
+#define MAX_IPV6_ADDR_LEN	43
 
 /* strlen of "host=" */
 #define HOST_KEY_LEN		5
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index ac5915d61dca..d9cf467309e8 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -514,10 +514,11 @@ static void cifs_umount_begin(struct super_block *sb)
 	tcon = cifs_sb->tcon;
 	if (tcon == NULL)
 		return;
-	down(&tcon->tconSem);
-	if (atomic_read(&tcon->useCount) == 1)
+
+	read_lock(&cifs_tcp_ses_lock);
+	if (tcon->tc_count == 1)
 		tcon->tidStatus = CifsExiting;
-	up(&tcon->tconSem);
+	read_unlock(&cifs_tcp_ses_lock);
 
 	/* cancel_brl_requests(tcon); */ /* BB mark all brl mids as exiting */
 	/* cancel_notify_requests(tcon); */
@@ -1013,7 +1014,7 @@ static int cifs_oplock_thread(void *dummyarg)
 				not bother sending an oplock release if session
 				to server still is disconnected since oplock
 				already released by the server in that case */
-			if (pTcon->tidStatus != CifsNeedReconnect) {
+			if (!pTcon->need_reconnect) {
 				rc = CIFSSMBLock(0, pTcon, netfid,
 						0 /* len */ , 0 /* offset */, 0,
 						0, LOCKING_ANDX_OPLOCK_RELEASE,
@@ -1031,24 +1032,24 @@ static int cifs_oplock_thread(void *dummyarg)
 static int cifs_dnotify_thread(void *dummyarg)
 {
 	struct list_head *tmp;
-	struct cifsSesInfo *ses;
+	struct TCP_Server_Info *server;
 
 	do {
 		if (try_to_freeze())
 			continue;
 		set_current_state(TASK_INTERRUPTIBLE);
 		schedule_timeout(15*HZ);
-		read_lock(&GlobalSMBSeslock);
 		/* check if any stuck requests that need
 		   to be woken up and wakeq so the
 		   thread can wake up and error out */
-		list_for_each(tmp, &GlobalSMBSessionList) {
-			ses = list_entry(tmp, struct cifsSesInfo,
-				cifsSessionList);
-			if (ses->server && atomic_read(&ses->server->inFlight))
-				wake_up_all(&ses->server->response_q);
+		read_lock(&cifs_tcp_ses_lock);
+		list_for_each(tmp, &cifs_tcp_ses_list) {
+			server = list_entry(tmp, struct TCP_Server_Info,
+					 tcp_ses_list);
+			if (atomic_read(&server->inFlight))
+				wake_up_all(&server->response_q);
 		}
-		read_unlock(&GlobalSMBSeslock);
+		read_unlock(&cifs_tcp_ses_lock);
 	} while (!kthread_should_stop());
 
 	return 0;
@@ -1059,9 +1060,7 @@ init_cifs(void)
 {
 	int rc = 0;
 	cifs_proc_init();
-/*	INIT_LIST_HEAD(&GlobalServerList);*/	/* BB not implemented yet */
-	INIT_LIST_HEAD(&GlobalSMBSessionList);
-	INIT_LIST_HEAD(&GlobalTreeConnectionList);
+	INIT_LIST_HEAD(&cifs_tcp_ses_list);
 	INIT_LIST_HEAD(&GlobalOplock_Q);
 #ifdef CONFIG_CIFS_EXPERIMENTAL
 	INIT_LIST_HEAD(&GlobalDnotifyReqList);
@@ -1089,6 +1088,7 @@ init_cifs(void)
 	GlobalMaxActiveXid = 0;
 	memset(Local_System_Name, 0, 15);
 	rwlock_init(&GlobalSMBSeslock);
+	rwlock_init(&cifs_tcp_ses_lock);
 	spin_lock_init(&GlobalMid_Lock);
 
 	if (cifs_max_pending < 2) {
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 1cb1189f24e0..c57c0565547f 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -85,8 +85,7 @@ enum securityEnum {
 };
 
 enum protocolEnum {
-	IPV4 = 0,
-	IPV6,
+	TCP = 0,
 	SCTP
 	/* Netbios frames protocol not supported at this time */
 };
@@ -122,6 +121,9 @@ struct cifs_cred {
  */
 
 struct TCP_Server_Info {
+	struct list_head tcp_ses_list;
+	struct list_head smb_ses_list;
+	int srv_count; /* reference counter */
 	/* 15 character server name + 0x20 16th byte indicating type = srv */
 	char server_RFC1001_name[SERVER_NAME_LEN_WITH_NULL];
 	char unicode_server_Name[SERVER_NAME_LEN_WITH_NULL * 2];
@@ -143,7 +145,6 @@ struct TCP_Server_Info {
 	bool svlocal:1;			/* local server or remote */
 	bool noblocksnd;		/* use blocking sendmsg */
 	bool noautotune;		/* do not autotune send buf sizes */
-	atomic_t socketUseCount; /* number of open cifs sessions on socket */
 	atomic_t inFlight;  /* number of requests on the wire to server */
 #ifdef CONFIG_CIFS_STATS2
 	atomic_t inSend; /* requests trying to send */
@@ -194,13 +195,14 @@ struct cifsUidInfo {
  * Session structure.  One of these for each uid session with a particular host
  */
 struct cifsSesInfo {
-	struct list_head cifsSessionList;
+	struct list_head smb_ses_list;
+	struct list_head tcon_list;
 	struct semaphore sesSem;
 #if 0
 	struct cifsUidInfo *uidInfo;	/* pointer to user info */
 #endif
 	struct TCP_Server_Info *server;	/* pointer to server info */
-	atomic_t inUse; /* # of mounts (tree connections) on this ses */
+	int ses_count;		/* reference counter */
 	enum statusEnum status;
 	unsigned overrideSecFlg;  /* if non-zero override global sec flags */
 	__u16 ipc_tid;		/* special tid for connection to IPC share */
@@ -216,6 +218,7 @@ struct cifsSesInfo {
 	char userName[MAX_USERNAME_SIZE + 1];
 	char *domainName;
 	char *password;
+	bool need_reconnect:1; /* connection reset, uid now invalid */
 };
 /* no more than one of the following three session flags may be set */
 #define CIFS_SES_NT4 1
@@ -230,16 +233,15 @@ struct cifsSesInfo {
  * session
  */
 struct cifsTconInfo {
-	struct list_head cifsConnectionList;
+	struct list_head tcon_list;
+	int tc_count;
 	struct list_head openFileList;
-	struct semaphore tconSem;
 	struct cifsSesInfo *ses;	/* pointer to session associated with */
 	char treeName[MAX_TREE_SIZE + 1]; /* UNC name of resource in ASCII */
 	char *nativeFileSystem;
 	__u16 tid;		/* The 2 byte tree id */
 	__u16 Flags;		/* optional support bits */
 	enum statusEnum tidStatus;
-	atomic_t useCount;	/* how many explicit/implicit mounts to share */
 #ifdef CONFIG_CIFS_STATS
 	atomic_t num_smbs_sent;
 	atomic_t num_writes;
@@ -288,6 +290,7 @@ struct cifsTconInfo {
 	bool unix_ext:1;  /* if false disable Linux extensions to CIFS protocol
 				for this mount even if server would support */
 	bool local_lease:1; /* check leases (only) on local system not remote */
+	bool need_reconnect:1; /* connection reset, tid now invalid */
 	/* BB add field for back pointer to sb struct(s)? */
 };
 
@@ -588,22 +591,30 @@ require use of the stronger protocol */
 #endif
 
 /*
- * The list of servers that did not respond with NT LM 0.12.
- * This list helps improve performance and eliminate the messages indicating
- * that we had a communications error talking to the server in this list.
+ * the list of TCP_Server_Info structures, ie each of the sockets
+ * connecting our client to a distinct server (ip address), is
+ * chained together by cifs_tcp_ses_list. The list of all our SMB
+ * sessions (and from that the tree connections) can be found
+ * by iterating over cifs_tcp_ses_list
  */
-/* Feature not supported */
-/* GLOBAL_EXTERN struct servers_not_supported *NotSuppList; */
+GLOBAL_EXTERN struct list_head		cifs_tcp_ses_list;
 
 /*
- * The following is a hash table of all the users we know about.
+ * This lock protects the cifs_tcp_ses_list, the list of smb sessions per
+ * tcp session, and the list of tcon's per smb session. It also protects
+ * the reference counters for the server, smb session, and tcon. Finally,
+ * changes to the tcon->tidStatus should be done while holding this lock.
  */
-GLOBAL_EXTERN struct smbUidInfo *GlobalUidList[UID_HASH];
+GLOBAL_EXTERN rwlock_t		cifs_tcp_ses_lock;
 
-/* GLOBAL_EXTERN struct list_head GlobalServerList; BB not implemented yet */
-GLOBAL_EXTERN struct list_head GlobalSMBSessionList;
-GLOBAL_EXTERN struct list_head GlobalTreeConnectionList;
-GLOBAL_EXTERN rwlock_t GlobalSMBSeslock;  /* protects list inserts on 3 above */
+/*
+ * This lock protects the cifs_file->llist and cifs_file->flist
+ * list operations, and updates to some flags (cifs_file->invalidHandle)
+ * It will be moved to either use the tcon->stat_lock or equivalent later.
+ * If cifs_tcp_ses_lock and the lock below are both needed to be held, then
+ * the cifs_tcp_ses_lock must be grabbed first and released last.
+ */
+GLOBAL_EXTERN rwlock_t GlobalSMBSeslock;
 
 GLOBAL_EXTERN struct list_head GlobalOplock_Q;
 
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index d5eac48fc415..2af8626ced43 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -190,10 +190,10 @@ small_smb_init(int smb_command, int wct, struct cifsTconInfo *tcon,
 		/* need to prevent multiple threads trying to
 		simultaneously reconnect the same SMB session */
 			down(&tcon->ses->sesSem);
-			if (tcon->ses->status == CifsNeedReconnect)
+			if (tcon->ses->need_reconnect)
 				rc = cifs_setup_session(0, tcon->ses,
 							nls_codepage);
-			if (!rc && (tcon->tidStatus == CifsNeedReconnect)) {
+			if (!rc && (tcon->need_reconnect)) {
 				mark_open_files_invalid(tcon);
 				rc = CIFSTCon(0, tcon->ses, tcon->treeName,
 					      tcon, nls_codepage);
@@ -337,10 +337,10 @@ smb_init(int smb_command, int wct, struct cifsTconInfo *tcon,
 		/* need to prevent multiple threads trying to
 		simultaneously reconnect the same SMB session */
 			down(&tcon->ses->sesSem);
-			if (tcon->ses->status == CifsNeedReconnect)
+			if (tcon->ses->need_reconnect)
 				rc = cifs_setup_session(0, tcon->ses,
 							nls_codepage);
-			if (!rc && (tcon->tidStatus == CifsNeedReconnect)) {
+			if (!rc && (tcon->need_reconnect)) {
 				mark_open_files_invalid(tcon);
 				rc = CIFSTCon(0, tcon->ses, tcon->treeName,
 					      tcon, nls_codepage);
@@ -664,8 +664,9 @@ CIFSSMBNegotiate(unsigned int xid, struct cifsSesInfo *ses)
 			rc = -EIO;
 			goto neg_err_exit;
 		}
-
-		if (server->socketUseCount.counter > 1) {
+		read_lock(&cifs_tcp_ses_lock);
+		if (server->srv_count > 1) {
+			read_unlock(&cifs_tcp_ses_lock);
 			if (memcmp(server->server_GUID,
 				   pSMBr->u.extended_response.
 				   GUID, 16) != 0) {
@@ -674,9 +675,11 @@ CIFSSMBNegotiate(unsigned int xid, struct cifsSesInfo *ses)
 					pSMBr->u.extended_response.GUID,
 					16);
 			}
-		} else
+		} else {
+			read_unlock(&cifs_tcp_ses_lock);
 			memcpy(server->server_GUID,
 			       pSMBr->u.extended_response.GUID, 16);
+		}
 
 		if (count == 16) {
 			server->secType = RawNTLMSSP;
@@ -739,50 +742,31 @@ CIFSSMBTDis(const int xid, struct cifsTconInfo *tcon)
 	int rc = 0;
 
 	cFYI(1, ("In tree disconnect"));
-	/*
-	 *  If last user of the connection and
-	 *  connection alive - disconnect it
-	 *  If this is the last connection on the server session disconnect it
-	 *  (and inside session disconnect we should check if tcp socket needs
-	 *  to be freed and kernel thread woken up).
-	 */
-	if (tcon)
-		down(&tcon->tconSem);
-	else
-		return -EIO;
 
-	atomic_dec(&tcon->useCount);
-	if (atomic_read(&tcon->useCount) > 0) {
-		up(&tcon->tconSem);
-		return -EBUSY;
-	}
+	/* BB: do we need to check this? These should never be NULL. */
+	if ((tcon->ses == NULL) || (tcon->ses->server == NULL))
+		return -EIO;
 
-	/* No need to return error on this operation if tid invalidated and
-	closed on server already e.g. due to tcp session crashing */
-	if (tcon->tidStatus == CifsNeedReconnect) {
-		up(&tcon->tconSem);
+	/*
+	 * No need to return error on this operation if tid invalidated and
+	 * closed on server already e.g. due to tcp session crashing. Also,
+	 * the tcon is no longer on the list, so no need to take lock before
+	 * checking this.
+	 */
+	if (tcon->need_reconnect)
 		return 0;
-	}
 
-	if ((tcon->ses == NULL) || (tcon->ses->server == NULL)) {
-		up(&tcon->tconSem);
-		return -EIO;
-	}
 	rc = small_smb_init(SMB_COM_TREE_DISCONNECT, 0, tcon,
 			    (void **)&smb_buffer);
-	if (rc) {
-		up(&tcon->tconSem);
+	if (rc)
 		return rc;
-	}
 
 	rc = SendReceiveNoRsp(xid, tcon->ses, smb_buffer, 0);
 	if (rc)
 		cFYI(1, ("Tree disconnect failed %d", rc));
 
-	up(&tcon->tconSem);
-
 	/* No need to return error on this operation if tid invalidated and
-	closed on server already e.g. due to tcp session crashing */
+	   closed on server already e.g. due to tcp session crashing */
 	if (rc == -EAGAIN)
 		rc = 0;
 
@@ -796,43 +780,36 @@ CIFSSMBLogoff(const int xid, struct cifsSesInfo *ses)
 	int rc = 0;
 
 	cFYI(1, ("In SMBLogoff for session disconnect"));
-	if (ses)
-		down(&ses->sesSem);
-	else
+
+	/*
+	 * BB: do we need to check validity of ses and server? They should
+	 * always be valid since we have an active reference. If not, that
+	 * should probably be a BUG()
+	 */
+	if (!ses || !ses->server)
 		return -EIO;
 
-	atomic_dec(&ses->inUse);
-	if (atomic_read(&ses->inUse) > 0) {
-		up(&ses->sesSem);
-		return -EBUSY;
-	}
+	down(&ses->sesSem);
+	if (ses->need_reconnect)
+		goto session_already_dead; /* no need to send SMBlogoff if uid
+					      already closed due to reconnect */
 	rc = small_smb_init(SMB_COM_LOGOFF_ANDX, 2, NULL, (void **)&pSMB);
 	if (rc) {
 		up(&ses->sesSem);
 		return rc;
 	}
 
-	if (ses->server) {
-		pSMB->hdr.Mid = GetNextMid(ses->server);
+	pSMB->hdr.Mid = GetNextMid(ses->server);
 
-		if (ses->server->secMode &
+	if (ses->server->secMode &
 		   (SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED))
 			pSMB->hdr.Flags2 |= SMBFLG2_SECURITY_SIGNATURE;
-	}
 
 	pSMB->hdr.Uid = ses->Suid;
 
 	pSMB->AndXCommand = 0xFF;
 	rc = SendReceiveNoRsp(xid, ses, (struct smb_hdr *) pSMB, 0);
-	if (ses->server) {
-		atomic_dec(&ses->server->socketUseCount);
-		if (atomic_read(&ses->server->socketUseCount) == 0) {
-			spin_lock(&GlobalMid_Lock);
-			ses->server->tcpStatus = CifsExiting;
-			spin_unlock(&GlobalMid_Lock);
-			rc = -ESHUTDOWN;
-		}
-	}
+session_already_dead:
 	up(&ses->sesSem);
 
 	/* if session dead then we do not need to do ulogoff,
@@ -3922,6 +3899,27 @@ GetInodeNumOut:
 	return rc;
 }
 
+/* computes length of UCS string converted to host codepage
+ * @src:	UCS string
+ * @maxlen:	length of the input string in UCS characters
+ * 		(not in bytes)
+ *
+ * return:	size of input string in host codepage
+ */
+static int hostlen_fromUCS(const __le16 *src, const int maxlen,
+		const struct nls_table *nls_codepage) {
+	int i;
+	int hostlen = 0;
+	char to[4];
+	int charlen;
+	for (i = 0; (i < maxlen) && src[i]; ++i) {
+		charlen = nls_codepage->uni2char(le16_to_cpu(src[i]),
+				to, NLS_MAX_CHARSET_SIZE);
+		hostlen += charlen > 0 ? charlen : 1;
+	}
+	return hostlen;
+}
+
 /* parses DFS refferal V3 structure
  * caller is responsible for freeing target_nodes
  * returns:
@@ -3932,7 +3930,8 @@ static int
 parse_DFS_referrals(TRANSACTION2_GET_DFS_REFER_RSP *pSMBr,
 		unsigned int *num_of_nodes,
 		struct dfs_info3_param **target_nodes,
-		const struct nls_table *nls_codepage)
+		const struct nls_table *nls_codepage, int remap,
+		const char *searchName)
 {
 	int i, rc = 0;
 	char *data_end;
@@ -3983,7 +3982,17 @@ parse_DFS_referrals(TRANSACTION2_GET_DFS_REFER_RSP *pSMBr,
 		struct dfs_info3_param *node = (*target_nodes)+i;
 
 		node->flags = le16_to_cpu(pSMBr->DFSFlags);
-		node->path_consumed = le16_to_cpu(pSMBr->PathConsumed);
+		if (is_unicode) {
+			__le16 *tmp = kmalloc(strlen(searchName)*2, GFP_KERNEL);
+			cifsConvertToUCS((__le16 *) tmp, searchName,
+					PATH_MAX, nls_codepage, remap);
+			node->path_consumed = hostlen_fromUCS(tmp,
+					le16_to_cpu(pSMBr->PathConsumed)/2,
+					nls_codepage);
+			kfree(tmp);
+		} else
+			node->path_consumed = le16_to_cpu(pSMBr->PathConsumed);
+
 		node->server_type = le16_to_cpu(ref->ServerType);
 		node->ref_flag = le16_to_cpu(ref->ReferralEntryFlags);
 
@@ -4116,7 +4125,8 @@ getDFSRetry:
 
 	/* parse returned result into more usable form */
 	rc = parse_DFS_referrals(pSMBr, num_of_nodes,
-				 target_nodes, nls_codepage);
+				 target_nodes, nls_codepage, remap,
+				 searchName);
 
 GetDFSRefExit:
 	cifs_buf_release(pSMB);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index e9f9248cb3fe..c7d341714586 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -124,7 +124,7 @@ static int
 cifs_reconnect(struct TCP_Server_Info *server)
 {
 	int rc = 0;
-	struct list_head *tmp;
+	struct list_head *tmp, *tmp2;
 	struct cifsSesInfo *ses;
 	struct cifsTconInfo *tcon;
 	struct mid_q_entry *mid_entry;
@@ -144,23 +144,17 @@ cifs_reconnect(struct TCP_Server_Info *server)
 
 	/* before reconnecting the tcp session, mark the smb session (uid)
 		and the tid bad so they are not used until reconnected */
-	read_lock(&GlobalSMBSeslock);
-	list_for_each(tmp, &GlobalSMBSessionList) {
-		ses = list_entry(tmp, struct cifsSesInfo, cifsSessionList);
-		if (ses->server) {
-			if (ses->server == server) {
-				ses->status = CifsNeedReconnect;
-				ses->ipc_tid = 0;
-			}
+	read_lock(&cifs_tcp_ses_lock);
+	list_for_each(tmp, &server->smb_ses_list) {
+		ses = list_entry(tmp, struct cifsSesInfo, smb_ses_list);
+		ses->need_reconnect = true;
+		ses->ipc_tid = 0;
+		list_for_each(tmp2, &ses->tcon_list) {
+			tcon = list_entry(tmp2, struct cifsTconInfo, tcon_list);
+			tcon->need_reconnect = true;
 		}
-		/* else tcp and smb sessions need reconnection */
-	}
-	list_for_each(tmp, &GlobalTreeConnectionList) {
-		tcon = list_entry(tmp, struct cifsTconInfo, cifsConnectionList);
-		if ((tcon->ses) && (tcon->ses->server == server))
-			tcon->tidStatus = CifsNeedReconnect;
 	}
-	read_unlock(&GlobalSMBSeslock);
+	read_unlock(&cifs_tcp_ses_lock);
 	/* do not want to be sending data on a socket we are freeing */
 	down(&server->tcpSem);
 	if (server->ssocket) {
@@ -193,7 +187,7 @@ cifs_reconnect(struct TCP_Server_Info *server)
 	while ((server->tcpStatus != CifsExiting) &&
 	       (server->tcpStatus != CifsGood)) {
 		try_to_freeze();
-		if (server->protocolType == IPV6) {
+		if (server->addr.sockAddr6.sin6_family == AF_INET6) {
 			rc = ipv6_connect(&server->addr.sockAddr6,
 					  &server->ssocket, server->noautotune);
 		} else {
@@ -417,9 +411,14 @@ incomplete_rcv:
 			msleep(1); /* minimum sleep to prevent looping
 				allowing socket to clear and app threads to set
 				tcpStatus CifsNeedReconnect if server hung */
-			if (pdu_length < 4)
+			if (pdu_length < 4) {
+				iov.iov_base = (4 - pdu_length) +
+							(char *)smb_buffer;
+				iov.iov_len = pdu_length;
+				smb_msg.msg_control = NULL;
+				smb_msg.msg_controllen = 0;
 				goto incomplete_rcv;
-			else
+			} else
 				continue;
 		} else if (length <= 0) {
 			if (server->tcpStatus == CifsNew) {
@@ -654,6 +653,11 @@ multi_t2_fnd:
 		}
 	} /* end while !EXITING */
 
+	/* take it off the list, if it's not already */
+	write_lock(&cifs_tcp_ses_lock);
+	list_del_init(&server->tcp_ses_list);
+	write_unlock(&cifs_tcp_ses_lock);
+
 	spin_lock(&GlobalMid_Lock);
 	server->tcpStatus = CifsExiting;
 	spin_unlock(&GlobalMid_Lock);
@@ -686,29 +690,29 @@ multi_t2_fnd:
 	if (smallbuf) /* no sense logging a debug message if NULL */
 		cifs_small_buf_release(smallbuf);
 
-	read_lock(&GlobalSMBSeslock);
+	/*
+	 * BB: we shouldn't have to do any of this. It shouldn't be
+	 * possible to exit from the thread with active SMB sessions
+	 */
+	read_lock(&cifs_tcp_ses_lock);
 	if (list_empty(&server->pending_mid_q)) {
 		/* loop through server session structures attached to this and
 		    mark them dead */
-		list_for_each(tmp, &GlobalSMBSessionList) {
-			ses =
-			    list_entry(tmp, struct cifsSesInfo,
-				       cifsSessionList);
-			if (ses->server == server) {
-				ses->status = CifsExiting;
-				ses->server = NULL;
-			}
+		list_for_each(tmp, &server->smb_ses_list) {
+			ses = list_entry(tmp, struct cifsSesInfo,
+					 smb_ses_list);
+			ses->status = CifsExiting;
+			ses->server = NULL;
 		}
-		read_unlock(&GlobalSMBSeslock);
+		read_unlock(&cifs_tcp_ses_lock);
 	} else {
 		/* although we can not zero the server struct pointer yet,
 		since there are active requests which may depnd on them,
 		mark the corresponding SMB sessions as exiting too */
-		list_for_each(tmp, &GlobalSMBSessionList) {
+		list_for_each(tmp, &server->smb_ses_list) {
 			ses = list_entry(tmp, struct cifsSesInfo,
-					 cifsSessionList);
-			if (ses->server == server)
-				ses->status = CifsExiting;
+					 smb_ses_list);
+			ses->status = CifsExiting;
 		}
 
 		spin_lock(&GlobalMid_Lock);
@@ -723,7 +727,7 @@ multi_t2_fnd:
 			}
 		}
 		spin_unlock(&GlobalMid_Lock);
-		read_unlock(&GlobalSMBSeslock);
+		read_unlock(&cifs_tcp_ses_lock);
 		/* 1/8th of sec is more than enough time for them to exit */
 		msleep(125);
 	}
@@ -745,14 +749,13 @@ multi_t2_fnd:
 	if there are any pointing to this (e.g
 	if a crazy root user tried to kill cifsd
 	kernel thread explicitly this might happen) */
-	write_lock(&GlobalSMBSeslock);
-	list_for_each(tmp, &GlobalSMBSessionList) {
-		ses = list_entry(tmp, struct cifsSesInfo,
-				cifsSessionList);
-		if (ses->server == server)
-			ses->server = NULL;
+	/* BB: This shouldn't be necessary, see above */
+	read_lock(&cifs_tcp_ses_lock);
+	list_for_each(tmp, &server->smb_ses_list) {
+		ses = list_entry(tmp, struct cifsSesInfo, smb_ses_list);
+		ses->server = NULL;
 	}
-	write_unlock(&GlobalSMBSeslock);
+	read_unlock(&cifs_tcp_ses_lock);
 
 	kfree(server->hostname);
 	task_to_wake = xchg(&server->tsk, NULL);
@@ -1352,94 +1355,158 @@ cifs_parse_mount_options(char *options, const char *devname,
 	return 0;
 }
 
-static struct cifsSesInfo *
-cifs_find_tcp_session(struct in_addr *target_ip_addr,
-		      struct in6_addr *target_ip6_addr,
-		      char *userName, struct TCP_Server_Info **psrvTcp)
+static struct TCP_Server_Info *
+cifs_find_tcp_session(struct sockaddr *addr)
 {
 	struct list_head *tmp;
-	struct cifsSesInfo *ses;
-
-	*psrvTcp = NULL;
+	struct TCP_Server_Info *server;
+	struct sockaddr_in *addr4 = (struct sockaddr_in *) addr;
+	struct sockaddr_in6 *addr6 = (struct sockaddr_in6 *) addr;
+
+	write_lock(&cifs_tcp_ses_lock);
+	list_for_each(tmp, &cifs_tcp_ses_list) {
+		server = list_entry(tmp, struct TCP_Server_Info,
+				    tcp_ses_list);
+		/*
+		 * the demux thread can exit on its own while still in CifsNew
+		 * so don't accept any sockets in that state. Since the
+		 * tcpStatus never changes back to CifsNew it's safe to check
+		 * for this without a lock.
+		 */
+		if (server->tcpStatus == CifsNew)
+			continue;
 
-	read_lock(&GlobalSMBSeslock);
-	list_for_each(tmp, &GlobalSMBSessionList) {
-		ses = list_entry(tmp, struct cifsSesInfo, cifsSessionList);
-		if (!ses->server)
+		if (addr->sa_family == AF_INET &&
+		    (addr4->sin_addr.s_addr !=
+		     server->addr.sockAddr.sin_addr.s_addr))
+			continue;
+		else if (addr->sa_family == AF_INET6 &&
+			 memcmp(&server->addr.sockAddr6.sin6_addr,
+				&addr6->sin6_addr, sizeof(addr6->sin6_addr)))
 			continue;
 
-		if (target_ip_addr &&
-		    ses->server->addr.sockAddr.sin_addr.s_addr != target_ip_addr->s_addr)
-				continue;
-		else if (target_ip6_addr &&
-			 memcmp(&ses->server->addr.sockAddr6.sin6_addr,
-				target_ip6_addr, sizeof(*target_ip6_addr)))
-				continue;
-		/* BB lock server and tcp session; increment use count here?? */
+		++server->srv_count;
+		write_unlock(&cifs_tcp_ses_lock);
+		cFYI(1, ("Existing tcp session with server found"));
+		return server;
+	}
+	write_unlock(&cifs_tcp_ses_lock);
+	return NULL;
+}
 
-		/* found a match on the TCP session */
-		*psrvTcp = ses->server;
+static void
+cifs_put_tcp_session(struct TCP_Server_Info *server)
+{
+	struct task_struct *task;
 
-		/* BB check if reconnection needed */
-		if (strncmp(ses->userName, userName, MAX_USERNAME_SIZE) == 0) {
-			read_unlock(&GlobalSMBSeslock);
-			/* Found exact match on both TCP and
-			   SMB sessions */
-			return ses;
-		}
-		/* else tcp and smb sessions need reconnection */
+	write_lock(&cifs_tcp_ses_lock);
+	if (--server->srv_count > 0) {
+		write_unlock(&cifs_tcp_ses_lock);
+		return;
 	}
-	read_unlock(&GlobalSMBSeslock);
 
-	return NULL;
+	list_del_init(&server->tcp_ses_list);
+	write_unlock(&cifs_tcp_ses_lock);
+
+	spin_lock(&GlobalMid_Lock);
+	server->tcpStatus = CifsExiting;
+	spin_unlock(&GlobalMid_Lock);
+
+	task = xchg(&server->tsk, NULL);
+	if (task)
+		force_sig(SIGKILL, task);
 }
 
-static struct cifsTconInfo *
-find_unc(__be32 new_target_ip_addr, char *uncName, char *userName)
+static struct cifsSesInfo *
+cifs_find_smb_ses(struct TCP_Server_Info *server, char *username)
 {
 	struct list_head *tmp;
-	struct cifsTconInfo *tcon;
-	__be32 old_ip;
-
-	read_lock(&GlobalSMBSeslock);
+	struct cifsSesInfo *ses;
 
-	list_for_each(tmp, &GlobalTreeConnectionList) {
-		cFYI(1, ("Next tcon"));
-		tcon = list_entry(tmp, struct cifsTconInfo, cifsConnectionList);
-		if (!tcon->ses || !tcon->ses->server)
+	write_lock(&cifs_tcp_ses_lock);
+	list_for_each(tmp, &server->smb_ses_list) {
+		ses = list_entry(tmp, struct cifsSesInfo, smb_ses_list);
+		if (strncmp(ses->userName, username, MAX_USERNAME_SIZE))
 			continue;
 
-		old_ip = tcon->ses->server->addr.sockAddr.sin_addr.s_addr;
-		cFYI(1, ("old ip addr: %x == new ip %x ?",
-			old_ip, new_target_ip_addr));
+		++ses->ses_count;
+		write_unlock(&cifs_tcp_ses_lock);
+		return ses;
+	}
+	write_unlock(&cifs_tcp_ses_lock);
+	return NULL;
+}
 
-		if (old_ip != new_target_ip_addr)
-			continue;
+static void
+cifs_put_smb_ses(struct cifsSesInfo *ses)
+{
+	int xid;
+	struct TCP_Server_Info *server = ses->server;
 
-		/* BB lock tcon, server, tcp session and increment use count? */
-		/* found a match on the TCP session */
-		/* BB check if reconnection needed */
-		cFYI(1, ("IP match, old UNC: %s new: %s",
-			tcon->treeName, uncName));
+	write_lock(&cifs_tcp_ses_lock);
+	if (--ses->ses_count > 0) {
+		write_unlock(&cifs_tcp_ses_lock);
+		return;
+	}
 
-		if (strncmp(tcon->treeName, uncName, MAX_TREE_SIZE))
-			continue;
+	list_del_init(&ses->smb_ses_list);
+	write_unlock(&cifs_tcp_ses_lock);
 
-		cFYI(1, ("and old usr: %s new: %s",
-			tcon->treeName, uncName));
+	if (ses->status == CifsGood) {
+		xid = GetXid();
+		CIFSSMBLogoff(xid, ses);
+		_FreeXid(xid);
+	}
+	sesInfoFree(ses);
+	cifs_put_tcp_session(server);
+}
 
-		if (strncmp(tcon->ses->userName, userName, MAX_USERNAME_SIZE))
+static struct cifsTconInfo *
+cifs_find_tcon(struct cifsSesInfo *ses, const char *unc)
+{
+	struct list_head *tmp;
+	struct cifsTconInfo *tcon;
+
+	write_lock(&cifs_tcp_ses_lock);
+	list_for_each(tmp, &ses->tcon_list) {
+		tcon = list_entry(tmp, struct cifsTconInfo, tcon_list);
+		if (tcon->tidStatus == CifsExiting)
+			continue;
+		if (strncmp(tcon->treeName, unc, MAX_TREE_SIZE))
 			continue;
 
-		/* matched smb session (user name) */
-		read_unlock(&GlobalSMBSeslock);
+		++tcon->tc_count;
+		write_unlock(&cifs_tcp_ses_lock);
 		return tcon;
 	}
-
-	read_unlock(&GlobalSMBSeslock);
+	write_unlock(&cifs_tcp_ses_lock);
 	return NULL;
 }
 
+static void
+cifs_put_tcon(struct cifsTconInfo *tcon)
+{
+	int xid;
+	struct cifsSesInfo *ses = tcon->ses;
+
+	write_lock(&cifs_tcp_ses_lock);
+	if (--tcon->tc_count > 0) {
+		write_unlock(&cifs_tcp_ses_lock);
+		return;
+	}
+
+	list_del_init(&tcon->tcon_list);
+	write_unlock(&cifs_tcp_ses_lock);
+
+	xid = GetXid();
+	CIFSSMBTDis(xid, tcon);
+	_FreeXid(xid);
+
+	DeleteTconOplockQEntries(tcon);
+	tconInfoFree(tcon);
+	cifs_put_smb_ses(ses);
+}
+
 int
 get_dfs_path(int xid, struct cifsSesInfo *pSesInfo, const char *old_path,
 	     const struct nls_table *nls_codepage, unsigned int *pnum_referrals,
@@ -1876,14 +1943,90 @@ convert_delimiter(char *path, char delim)
 	}
 }
 
-static void
-kill_cifsd(struct TCP_Server_Info *server)
+static void setup_cifs_sb(struct smb_vol *pvolume_info,
+			  struct cifs_sb_info *cifs_sb)
 {
-	struct task_struct *task;
-
-	task = xchg(&server->tsk, NULL);
-	if (task)
-		force_sig(SIGKILL, task);
+	if (pvolume_info->rsize > CIFSMaxBufSize) {
+		cERROR(1, ("rsize %d too large, using MaxBufSize",
+			pvolume_info->rsize));
+		cifs_sb->rsize = CIFSMaxBufSize;
+	} else if ((pvolume_info->rsize) &&
+			(pvolume_info->rsize <= CIFSMaxBufSize))
+		cifs_sb->rsize = pvolume_info->rsize;
+	else /* default */
+		cifs_sb->rsize = CIFSMaxBufSize;
+
+	if (pvolume_info->wsize > PAGEVEC_SIZE * PAGE_CACHE_SIZE) {
+		cERROR(1, ("wsize %d too large, using 4096 instead",
+			  pvolume_info->wsize));
+		cifs_sb->wsize = 4096;
+	} else if (pvolume_info->wsize)
+		cifs_sb->wsize = pvolume_info->wsize;
+	else
+		cifs_sb->wsize = min_t(const int,
+					PAGEVEC_SIZE * PAGE_CACHE_SIZE,
+					127*1024);
+		/* old default of CIFSMaxBufSize was too small now
+		   that SMB Write2 can send multiple pages in kvec.
+		   RFC1001 does not describe what happens when frame
+		   bigger than 128K is sent so use that as max in
+		   conjunction with 52K kvec constraint on arch with 4K
+		   page size  */
+
+	if (cifs_sb->rsize < 2048) {
+		cifs_sb->rsize = 2048;
+		/* Windows ME may prefer this */
+		cFYI(1, ("readsize set to minimum: 2048"));
+	}
+	/* calculate prepath */
+	cifs_sb->prepath = pvolume_info->prepath;
+	if (cifs_sb->prepath) {
+		cifs_sb->prepathlen = strlen(cifs_sb->prepath);
+		/* we can not convert the / to \ in the path
+		separators in the prefixpath yet because we do not
+		know (until reset_cifs_unix_caps is called later)
+		whether POSIX PATH CAP is available. We normalize
+		the / to \ after reset_cifs_unix_caps is called */
+		pvolume_info->prepath = NULL;
+	} else
+		cifs_sb->prepathlen = 0;
+	cifs_sb->mnt_uid = pvolume_info->linux_uid;
+	cifs_sb->mnt_gid = pvolume_info->linux_gid;
+	cifs_sb->mnt_file_mode = pvolume_info->file_mode;
+	cifs_sb->mnt_dir_mode = pvolume_info->dir_mode;
+	cFYI(1, ("file mode: 0x%x  dir mode: 0x%x",
+		cifs_sb->mnt_file_mode, cifs_sb->mnt_dir_mode));
+
+	if (pvolume_info->noperm)
+		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_PERM;
+	if (pvolume_info->setuids)
+		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_SET_UID;
+	if (pvolume_info->server_ino)
+		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_SERVER_INUM;
+	if (pvolume_info->remap)
+		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_MAP_SPECIAL_CHR;
+	if (pvolume_info->no_xattr)
+		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_XATTR;
+	if (pvolume_info->sfu_emul)
+		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_UNX_EMUL;
+	if (pvolume_info->nobrl)
+		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_BRL;
+	if (pvolume_info->cifs_acl)
+		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_CIFS_ACL;
+	if (pvolume_info->override_uid)
+		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_OVERR_UID;
+	if (pvolume_info->override_gid)
+		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_OVERR_GID;
+	if (pvolume_info->dynperm)
+		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_DYNPERM;
+	if (pvolume_info->direct_io) {
+		cFYI(1, ("mounting share using direct i/o"));
+		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_DIRECT_IO;
+	}
+
+	if ((pvolume_info->cifs_acl) && (pvolume_info->dynperm))
+		cERROR(1, ("mount option dynperm ignored if cifsacl "
+			   "mount option supported"));
 }
 
 int
@@ -1892,13 +2035,12 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb,
 {
 	int rc = 0;
 	int xid;
-	int address_type = AF_INET;
 	struct socket *csocket = NULL;
-	struct sockaddr_in sin_server;
-	struct sockaddr_in6 sin_server6;
+	struct sockaddr addr;
+	struct sockaddr_in *sin_server = (struct sockaddr_in *) &addr;
+	struct sockaddr_in6 *sin_server6 = (struct sockaddr_in6 *) &addr;
 	struct smb_vol volume_info;
 	struct cifsSesInfo *pSesInfo = NULL;
-	struct cifsSesInfo *existingCifsSes = NULL;
 	struct cifsTconInfo *tcon = NULL;
 	struct TCP_Server_Info *srvTcp = NULL;
 
@@ -1906,6 +2048,7 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb,
 
 /* cFYI(1, ("Entering cifs_mount. Xid: %d with: %s", xid, mount_data)); */
 
+	memset(&addr, 0, sizeof(struct sockaddr));
 	memset(&volume_info, 0, sizeof(struct smb_vol));
 	if (cifs_parse_mount_options(mount_data, devname, &volume_info)) {
 		rc = -EINVAL;
@@ -1928,16 +2071,16 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb,
 
 	if (volume_info.UNCip && volume_info.UNC) {
 		rc = cifs_inet_pton(AF_INET, volume_info.UNCip,
-				    &sin_server.sin_addr.s_addr);
+				    &sin_server->sin_addr.s_addr);
 
 		if (rc <= 0) {
 			/* not ipv4 address, try ipv6 */
 			rc = cifs_inet_pton(AF_INET6, volume_info.UNCip,
-					    &sin_server6.sin6_addr.in6_u);
+					    &sin_server6->sin6_addr.in6_u);
 			if (rc > 0)
-				address_type = AF_INET6;
+				addr.sa_family = AF_INET6;
 		} else {
-			address_type = AF_INET;
+			addr.sa_family = AF_INET;
 		}
 
 		if (rc <= 0) {
@@ -1977,41 +2120,25 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb,
 		}
 	}
 
-	if (address_type == AF_INET)
-		existingCifsSes = cifs_find_tcp_session(&sin_server.sin_addr,
-			NULL /* no ipv6 addr */,
-			volume_info.username, &srvTcp);
-	else if (address_type == AF_INET6) {
-		cFYI(1, ("looking for ipv6 address"));
-		existingCifsSes = cifs_find_tcp_session(NULL /* no ipv4 addr */,
-			&sin_server6.sin6_addr,
-			volume_info.username, &srvTcp);
-	} else {
-		rc = -EINVAL;
-		goto out;
-	}
-
-	if (srvTcp) {
-		cFYI(1, ("Existing tcp session with server found"));
-	} else {	/* create socket */
-		if (volume_info.port)
-			sin_server.sin_port = htons(volume_info.port);
-		else
-			sin_server.sin_port = 0;
-		if (address_type == AF_INET6) {
+	srvTcp = cifs_find_tcp_session(&addr);
+	if (!srvTcp) { /* create socket */
+		if (addr.sa_family == AF_INET6) {
 			cFYI(1, ("attempting ipv6 connect"));
 			/* BB should we allow ipv6 on port 139? */
 			/* other OS never observed in Wild doing 139 with v6 */
-			rc = ipv6_connect(&sin_server6, &csocket,
+			sin_server6->sin6_port = htons(volume_info.port);
+			rc = ipv6_connect(sin_server6, &csocket,
 					volume_info.noblocksnd);
-		} else
-			rc = ipv4_connect(&sin_server, &csocket,
+		} else {
+			sin_server->sin_port = htons(volume_info.port);
+			rc = ipv4_connect(sin_server, &csocket,
 				  volume_info.source_rfc1001_name,
 				  volume_info.target_rfc1001_name,
 				  volume_info.noblocksnd,
 				  volume_info.noautotune);
+		}
 		if (rc < 0) {
-			cERROR(1, ("Error connecting to IPv4 socket. "
+			cERROR(1, ("Error connecting to socket. "
 				   "Aborting operation"));
 			if (csocket != NULL)
 				sock_release(csocket);
@@ -2026,12 +2153,15 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb,
 		} else {
 			srvTcp->noblocksnd = volume_info.noblocksnd;
 			srvTcp->noautotune = volume_info.noautotune;
-			memcpy(&srvTcp->addr.sockAddr, &sin_server,
-				sizeof(struct sockaddr_in));
+			if (addr.sa_family == AF_INET6)
+				memcpy(&srvTcp->addr.sockAddr6, sin_server6,
+					sizeof(struct sockaddr_in6));
+			else
+				memcpy(&srvTcp->addr.sockAddr, sin_server,
+					sizeof(struct sockaddr_in));
 			atomic_set(&srvTcp->inFlight, 0);
 			/* BB Add code for ipv6 case too */
 			srvTcp->ssocket = csocket;
-			srvTcp->protocolType = IPV4;
 			srvTcp->hostname = extract_hostname(volume_info.UNC);
 			if (IS_ERR(srvTcp->hostname)) {
 				rc = PTR_ERR(srvTcp->hostname);
@@ -2061,15 +2191,28 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb,
 			memcpy(srvTcp->server_RFC1001_name,
 				volume_info.target_rfc1001_name, 16);
 			srvTcp->sequence_number = 0;
+			INIT_LIST_HEAD(&srvTcp->tcp_ses_list);
+			INIT_LIST_HEAD(&srvTcp->smb_ses_list);
+			++srvTcp->srv_count;
+			write_lock(&cifs_tcp_ses_lock);
+			list_add(&srvTcp->tcp_ses_list,
+				 &cifs_tcp_ses_list);
+			write_unlock(&cifs_tcp_ses_lock);
 		}
 	}
 
-	if (existingCifsSes) {
-		pSesInfo = existingCifsSes;
+	pSesInfo = cifs_find_smb_ses(srvTcp, volume_info.username);
+	if (pSesInfo) {
 		cFYI(1, ("Existing smb sess found (status=%d)",
 			pSesInfo->status));
+		/*
+		 * The existing SMB session already has a reference to srvTcp,
+		 * so we can put back the extra one we got before
+		 */
+		cifs_put_tcp_session(srvTcp);
+
 		down(&pSesInfo->sesSem);
-		if (pSesInfo->status == CifsNeedReconnect) {
+		if (pSesInfo->need_reconnect) {
 			cFYI(1, ("Session needs reconnect"));
 			rc = cifs_setup_session(xid, pSesInfo,
 						cifs_sb->local_nls);
@@ -2078,187 +2221,101 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb,
 	} else if (!rc) {
 		cFYI(1, ("Existing smb sess not found"));
 		pSesInfo = sesInfoAlloc();
-		if (pSesInfo == NULL)
+		if (pSesInfo == NULL) {
 			rc = -ENOMEM;
-		else {
-			pSesInfo->server = srvTcp;
-			sprintf(pSesInfo->serverName, "%u.%u.%u.%u",
-				NIPQUAD(sin_server.sin_addr.s_addr));
-		}
+			goto mount_fail_check;
+		}
+
+		/* new SMB session uses our srvTcp ref */
+		pSesInfo->server = srvTcp;
+		sprintf(pSesInfo->serverName, "%u.%u.%u.%u",
+			NIPQUAD(sin_server->sin_addr.s_addr));
+
+		write_lock(&cifs_tcp_ses_lock);
+		list_add(&pSesInfo->smb_ses_list, &srvTcp->smb_ses_list);
+		write_unlock(&cifs_tcp_ses_lock);
+
+		/* volume_info.password freed at unmount */
+		if (volume_info.password) {
+			pSesInfo->password = volume_info.password;
+			/* set to NULL to prevent freeing on exit */
+			volume_info.password = NULL;
+		}
+		if (volume_info.username)
+			strncpy(pSesInfo->userName, volume_info.username,
+				MAX_USERNAME_SIZE);
+		if (volume_info.domainname) {
+			int len = strlen(volume_info.domainname);
+			pSesInfo->domainName = kmalloc(len + 1, GFP_KERNEL);
+			if (pSesInfo->domainName)
+				strcpy(pSesInfo->domainName,
+					volume_info.domainname);
+		}
+		pSesInfo->linux_uid = volume_info.linux_uid;
+		pSesInfo->overrideSecFlg = volume_info.secFlg;
+		down(&pSesInfo->sesSem);
 
-		if (!rc) {
-			/* volume_info.password freed at unmount */
-			if (volume_info.password) {
-				pSesInfo->password = volume_info.password;
-				/* set to NULL to prevent freeing on exit */
-				volume_info.password = NULL;
-			}
-			if (volume_info.username)
-				strncpy(pSesInfo->userName,
-					volume_info.username,
-					MAX_USERNAME_SIZE);
-			if (volume_info.domainname) {
-				int len = strlen(volume_info.domainname);
-				pSesInfo->domainName =
-					kmalloc(len + 1, GFP_KERNEL);
-				if (pSesInfo->domainName)
-					strcpy(pSesInfo->domainName,
-						volume_info.domainname);
-			}
-			pSesInfo->linux_uid = volume_info.linux_uid;
-			pSesInfo->overrideSecFlg = volume_info.secFlg;
-			down(&pSesInfo->sesSem);
-			/* BB FIXME need to pass vol->secFlgs BB */
-			rc = cifs_setup_session(xid, pSesInfo,
-						cifs_sb->local_nls);
-			up(&pSesInfo->sesSem);
-			if (!rc)
-				atomic_inc(&srvTcp->socketUseCount);
-		}
+		/* BB FIXME need to pass vol->secFlgs BB */
+		rc = cifs_setup_session(xid, pSesInfo,
+					cifs_sb->local_nls);
+		up(&pSesInfo->sesSem);
 	}
 
 	/* search for existing tcon to this server share */
 	if (!rc) {
-		if (volume_info.rsize > CIFSMaxBufSize) {
-			cERROR(1, ("rsize %d too large, using MaxBufSize",
-				volume_info.rsize));
-			cifs_sb->rsize = CIFSMaxBufSize;
-		} else if ((volume_info.rsize) &&
-				(volume_info.rsize <= CIFSMaxBufSize))
-			cifs_sb->rsize = volume_info.rsize;
-		else /* default */
-			cifs_sb->rsize = CIFSMaxBufSize;
-
-		if (volume_info.wsize > PAGEVEC_SIZE * PAGE_CACHE_SIZE) {
-			cERROR(1, ("wsize %d too large, using 4096 instead",
-				  volume_info.wsize));
-			cifs_sb->wsize = 4096;
-		} else if (volume_info.wsize)
-			cifs_sb->wsize = volume_info.wsize;
-		else
-			cifs_sb->wsize =
-				min_t(const int, PAGEVEC_SIZE * PAGE_CACHE_SIZE,
-					127*1024);
-			/* old default of CIFSMaxBufSize was too small now
-			   that SMB Write2 can send multiple pages in kvec.
-			   RFC1001 does not describe what happens when frame
-			   bigger than 128K is sent so use that as max in
-			   conjunction with 52K kvec constraint on arch with 4K
-			   page size  */
-
-		if (cifs_sb->rsize < 2048) {
-			cifs_sb->rsize = 2048;
-			/* Windows ME may prefer this */
-			cFYI(1, ("readsize set to minimum: 2048"));
-		}
-		/* calculate prepath */
-		cifs_sb->prepath = volume_info.prepath;
-		if (cifs_sb->prepath) {
-			cifs_sb->prepathlen = strlen(cifs_sb->prepath);
-			/* we can not convert the / to \ in the path
-			separators in the prefixpath yet because we do not
-			know (until reset_cifs_unix_caps is called later)
-			whether POSIX PATH CAP is available. We normalize
-			the / to \ after reset_cifs_unix_caps is called */
-			volume_info.prepath = NULL;
-		} else
-			cifs_sb->prepathlen = 0;
-		cifs_sb->mnt_uid = volume_info.linux_uid;
-		cifs_sb->mnt_gid = volume_info.linux_gid;
-		cifs_sb->mnt_file_mode = volume_info.file_mode;
-		cifs_sb->mnt_dir_mode = volume_info.dir_mode;
-		cFYI(1, ("file mode: 0x%x  dir mode: 0x%x",
-			cifs_sb->mnt_file_mode, cifs_sb->mnt_dir_mode));
-
-		if (volume_info.noperm)
-			cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_PERM;
-		if (volume_info.setuids)
-			cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_SET_UID;
-		if (volume_info.server_ino)
-			cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_SERVER_INUM;
-		if (volume_info.remap)
-			cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_MAP_SPECIAL_CHR;
-		if (volume_info.no_xattr)
-			cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_XATTR;
-		if (volume_info.sfu_emul)
-			cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_UNX_EMUL;
-		if (volume_info.nobrl)
-			cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_NO_BRL;
-		if (volume_info.cifs_acl)
-			cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_CIFS_ACL;
-		if (volume_info.override_uid)
-			cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_OVERR_UID;
-		if (volume_info.override_gid)
-			cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_OVERR_GID;
-		if (volume_info.dynperm)
-			cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_DYNPERM;
-		if (volume_info.direct_io) {
-			cFYI(1, ("mounting share using direct i/o"));
-			cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_DIRECT_IO;
-		}
+		setup_cifs_sb(&volume_info, cifs_sb);
 
-		if ((volume_info.cifs_acl) && (volume_info.dynperm))
-			cERROR(1, ("mount option dynperm ignored if cifsacl "
-				   "mount option supported"));
-
-		tcon =
-		    find_unc(sin_server.sin_addr.s_addr, volume_info.UNC,
-			     volume_info.username);
+		tcon = cifs_find_tcon(pSesInfo, volume_info.UNC);
 		if (tcon) {
 			cFYI(1, ("Found match on UNC path"));
-			/* we can have only one retry value for a connection
-			   to a share so for resources mounted more than once
-			   to the same server share the last value passed in
-			   for the retry flag is used */
-			tcon->retry = volume_info.retry;
-			tcon->nocase = volume_info.nocase;
-			tcon->local_lease = volume_info.local_lease;
+			/* existing tcon already has a reference */
+			cifs_put_smb_ses(pSesInfo);
 			if (tcon->seal != volume_info.seal)
 				cERROR(1, ("transport encryption setting "
 					   "conflicts with existing tid"));
 		} else {
 			tcon = tconInfoAlloc();
-			if (tcon == NULL)
+			if (tcon == NULL) {
 				rc = -ENOMEM;
-			else {
-				/* check for null share name ie connecting to
-				 * dfs root */
-
-				/* BB check if this works for exactly length
-				 * three strings */
-				if ((strchr(volume_info.UNC + 3, '\\') == NULL)
-				    && (strchr(volume_info.UNC + 3, '/') ==
-					NULL)) {
-/*					rc = connect_to_dfs_path(xid, pSesInfo,
-						"", cifs_sb->local_nls,
-						cifs_sb->mnt_cifs_flags &
-						  CIFS_MOUNT_MAP_SPECIAL_CHR);*/
-					cFYI(1, ("DFS root not supported"));
-					rc = -ENODEV;
-					goto out;
-				} else {
-					/* BB Do we need to wrap sesSem around
-					 * this TCon call and Unix SetFS as
-					 * we do on SessSetup and reconnect? */
-					rc = CIFSTCon(xid, pSesInfo,
-						volume_info.UNC,
-						tcon, cifs_sb->local_nls);
-					cFYI(1, ("CIFS Tcon rc = %d", rc));
-					if (volume_info.nodfs) {
-						tcon->Flags &=
-							~SMB_SHARE_IS_IN_DFS;
-						cFYI(1, ("DFS disabled (%d)",
-							tcon->Flags));
-					}
-				}
-				if (!rc) {
-					atomic_inc(&pSesInfo->inUse);
-					tcon->retry = volume_info.retry;
-					tcon->nocase = volume_info.nocase;
-					tcon->seal = volume_info.seal;
+				goto mount_fail_check;
+			}
+			tcon->ses = pSesInfo;
+
+			/* check for null share name ie connect to dfs root */
+			if ((strchr(volume_info.UNC + 3, '\\') == NULL)
+			    && (strchr(volume_info.UNC + 3, '/') == NULL)) {
+				/* rc = connect_to_dfs_path(...) */
+				cFYI(1, ("DFS root not supported"));
+				rc = -ENODEV;
+				goto mount_fail_check;
+			} else {
+				/* BB Do we need to wrap sesSem around
+				 * this TCon call and Unix SetFS as
+				 * we do on SessSetup and reconnect? */
+				rc = CIFSTCon(xid, pSesInfo, volume_info.UNC,
+					      tcon, cifs_sb->local_nls);
+				cFYI(1, ("CIFS Tcon rc = %d", rc));
+				if (volume_info.nodfs) {
+					tcon->Flags &= ~SMB_SHARE_IS_IN_DFS;
+					cFYI(1, ("DFS disabled (%d)",
+						tcon->Flags));
 				}
 			}
-		}
+			if (rc)
+				goto mount_fail_check;
+			tcon->seal = volume_info.seal;
+			write_lock(&cifs_tcp_ses_lock);
+			list_add(&tcon->tcon_list, &pSesInfo->tcon_list);
+			write_unlock(&cifs_tcp_ses_lock);
+		}
+
+		/* we can have only one retry value for a connection
+		   to a share so for resources mounted more than once
+		   to the same server share the last value passed in
+		   for the retry flag is used */
+		tcon->retry = volume_info.retry;
+		tcon->nocase = volume_info.nocase;
+		tcon->local_lease = volume_info.local_lease;
 	}
 	if (pSesInfo) {
 		if (pSesInfo->capabilities & CAP_LARGE_FILES) {
@@ -2270,80 +2327,49 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb,
 	/* BB FIXME fix time_gran to be larger for LANMAN sessions */
 	sb->s_time_gran = 100;
 
-/* on error free sesinfo and tcon struct if needed */
+mount_fail_check:
+	/* on error free sesinfo and tcon struct if needed */
 	if (rc) {
-		/* if session setup failed, use count is zero but
-		we still need to free cifsd thread */
-		if (atomic_read(&srvTcp->socketUseCount) == 0) {
-			spin_lock(&GlobalMid_Lock);
-			srvTcp->tcpStatus = CifsExiting;
-			spin_unlock(&GlobalMid_Lock);
-			kill_cifsd(srvTcp);
-		}
-		 /* If find_unc succeeded then rc == 0 so we can not end */
-		if (tcon)  /* up accidently freeing someone elses tcon struct */
-			tconInfoFree(tcon);
-		if (existingCifsSes == NULL) {
-			if (pSesInfo) {
-				if ((pSesInfo->server) &&
-				    (pSesInfo->status == CifsGood)) {
-					int temp_rc;
-					temp_rc = CIFSSMBLogoff(xid, pSesInfo);
-					/* if the socketUseCount is now zero */
-					if ((temp_rc == -ESHUTDOWN) &&
-					    (pSesInfo->server))
-						kill_cifsd(pSesInfo->server);
-				} else {
-					cFYI(1, ("No session or bad tcon"));
-					if (pSesInfo->server) {
-						spin_lock(&GlobalMid_Lock);
-						srvTcp->tcpStatus = CifsExiting;
-						spin_unlock(&GlobalMid_Lock);
-						kill_cifsd(pSesInfo->server);
-					}
-				}
-				sesInfoFree(pSesInfo);
-				/* pSesInfo = NULL; */
-			}
-		}
-	} else {
-		atomic_inc(&tcon->useCount);
-		cifs_sb->tcon = tcon;
-		tcon->ses = pSesInfo;
-
-		/* do not care if following two calls succeed - informational */
-		if (!tcon->ipc) {
-			CIFSSMBQFSDeviceInfo(xid, tcon);
-			CIFSSMBQFSAttributeInfo(xid, tcon);
-		}
-
-		/* tell server which Unix caps we support */
-		if (tcon->ses->capabilities & CAP_UNIX)
-			/* reset of caps checks mount to see if unix extensions
-			   disabled for just this mount */
-			reset_cifs_unix_caps(xid, tcon, sb, &volume_info);
+		/* If find_unc succeeded then rc == 0 so we can not end */
+		/* up accidently freeing someone elses tcon struct */
+		if (tcon)
+			cifs_put_tcon(tcon);
+		else if (pSesInfo)
+			cifs_put_smb_ses(pSesInfo);
 		else
-			tcon->unix_ext = 0; /* server does not support them */
+			cifs_put_tcp_session(srvTcp);
+		goto out;
+	}
+	cifs_sb->tcon = tcon;
 
-		/* convert forward to back slashes in prepath here if needed */
-		if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) == 0)
-			convert_delimiter(cifs_sb->prepath,
-					  CIFS_DIR_SEP(cifs_sb));
+	/* do not care if following two calls succeed - informational */
+	if (!tcon->ipc) {
+		CIFSSMBQFSDeviceInfo(xid, tcon);
+		CIFSSMBQFSAttributeInfo(xid, tcon);
+	}
 
-		if ((tcon->unix_ext == 0) && (cifs_sb->rsize > (1024 * 127))) {
-			cifs_sb->rsize = 1024 * 127;
-			cFYI(DBG2,
-				("no very large read support, rsize now 127K"));
-		}
-		if (!(tcon->ses->capabilities & CAP_LARGE_WRITE_X))
-			cifs_sb->wsize = min(cifs_sb->wsize,
-					     (tcon->ses->server->maxBuf -
-					      MAX_CIFS_HDR_SIZE));
-		if (!(tcon->ses->capabilities & CAP_LARGE_READ_X))
-			cifs_sb->rsize = min(cifs_sb->rsize,
-					     (tcon->ses->server->maxBuf -
-					      MAX_CIFS_HDR_SIZE));
+	/* tell server which Unix caps we support */
+	if (tcon->ses->capabilities & CAP_UNIX)
+		/* reset of caps checks mount to see if unix extensions
+		   disabled for just this mount */
+		reset_cifs_unix_caps(xid, tcon, sb, &volume_info);
+	else
+		tcon->unix_ext = 0; /* server does not support them */
+
+	/* convert forward to back slashes in prepath here if needed */
+	if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS) == 0)
+		convert_delimiter(cifs_sb->prepath, CIFS_DIR_SEP(cifs_sb));
+
+	if ((tcon->unix_ext == 0) && (cifs_sb->rsize > (1024 * 127))) {
+		cifs_sb->rsize = 1024 * 127;
+		cFYI(DBG2, ("no very large read support, rsize now 127K"));
 	}
+	if (!(tcon->ses->capabilities & CAP_LARGE_WRITE_X))
+		cifs_sb->wsize = min(cifs_sb->wsize,
+			       (tcon->ses->server->maxBuf - MAX_CIFS_HDR_SIZE));
+	if (!(tcon->ses->capabilities & CAP_LARGE_READ_X))
+		cifs_sb->rsize = min(cifs_sb->rsize,
+			       (tcon->ses->server->maxBuf - MAX_CIFS_HDR_SIZE));
 
 	/* volume_info.password is freed above when existing session found
 	(in which case it is not needed anymore) but when new sesion is created
@@ -3513,6 +3539,7 @@ CIFSTCon(unsigned int xid, struct cifsSesInfo *ses,
 	/* above now done in SendReceive */
 	if ((rc == 0) && (tcon != NULL)) {
 		tcon->tidStatus = CifsGood;
+		tcon->need_reconnect = false;
 		tcon->tid = smb_buffer_response->Tid;
 		bcc_ptr = pByteArea(smb_buffer_response);
 		length = strnlen(bcc_ptr, BCC(smb_buffer_response) - 2);
@@ -3584,48 +3611,17 @@ int
 cifs_umount(struct super_block *sb, struct cifs_sb_info *cifs_sb)
 {
 	int rc = 0;
-	int xid;
-	struct cifsSesInfo *ses = NULL;
 	char *tmp;
 
-	xid = GetXid();
-
-	if (cifs_sb->tcon) {
-		ses = cifs_sb->tcon->ses; /* save ptr to ses before delete tcon!*/
-		rc = CIFSSMBTDis(xid, cifs_sb->tcon);
-		if (rc == -EBUSY) {
-			FreeXid(xid);
-			return 0;
-		}
-		DeleteTconOplockQEntries(cifs_sb->tcon);
-		tconInfoFree(cifs_sb->tcon);
-		if ((ses) && (ses->server)) {
-			/* save off task so we do not refer to ses later */
-			cFYI(1, ("About to do SMBLogoff "));
-			rc = CIFSSMBLogoff(xid, ses);
-			if (rc == -EBUSY) {
-				FreeXid(xid);
-				return 0;
-			} else if (rc == -ESHUTDOWN) {
-				cFYI(1, ("Waking up socket by sending signal"));
-				if (ses->server)
-					kill_cifsd(ses->server);
-				rc = 0;
-			} /* else - we have an smb session
-				left on this socket do not kill cifsd */
-		} else
-			cFYI(1, ("No session or bad tcon"));
-	}
+	if (cifs_sb->tcon)
+		cifs_put_tcon(cifs_sb->tcon);
 
 	cifs_sb->tcon = NULL;
 	tmp = cifs_sb->prepath;
 	cifs_sb->prepathlen = 0;
 	cifs_sb->prepath = NULL;
 	kfree(tmp);
-	if (ses)
-		sesInfoFree(ses);
 
-	FreeXid(xid);
 	return rc;
 }
 
@@ -3741,6 +3737,7 @@ int cifs_setup_session(unsigned int xid, struct cifsSesInfo *pSesInfo,
 		cFYI(1, ("CIFS Session Established successfully"));
 			spin_lock(&GlobalMid_Lock);
 			pSesInfo->status = CifsGood;
+			pSesInfo->need_reconnect = false;
 			spin_unlock(&GlobalMid_Lock);
 	}
 
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index ead1a3bb0256..b691b893a848 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -488,12 +488,13 @@ int cifs_close(struct inode *inode, struct file *file)
 	pTcon = cifs_sb->tcon;
 	if (pSMBFile) {
 		struct cifsLockInfo *li, *tmp;
-
+		write_lock(&GlobalSMBSeslock);
 		pSMBFile->closePend = true;
 		if (pTcon) {
 			/* no sense reconnecting to close a file that is
 			   already closed */
-			if (pTcon->tidStatus != CifsNeedReconnect) {
+			if (!pTcon->need_reconnect) {
+				write_unlock(&GlobalSMBSeslock);
 				timeout = 2;
 				while ((atomic_read(&pSMBFile->wrtPending) != 0)
 					&& (timeout <= 2048)) {
@@ -510,12 +511,15 @@ int cifs_close(struct inode *inode, struct file *file)
 					timeout *= 4;
 				}
 				if (atomic_read(&pSMBFile->wrtPending))
-					cERROR(1,
-						("close with pending writes"));
-				rc = CIFSSMBClose(xid, pTcon,
+					cERROR(1, ("close with pending write"));
+				if (!pTcon->need_reconnect &&
+				    !pSMBFile->invalidHandle)
+					rc = CIFSSMBClose(xid, pTcon,
 						  pSMBFile->netfid);
-			}
-		}
+			} else
+				write_unlock(&GlobalSMBSeslock);
+		} else
+			write_unlock(&GlobalSMBSeslock);
 
 		/* Delete any outstanding lock records.
 		   We'll lose them when the file is closed anyway. */
@@ -587,15 +591,18 @@ int cifs_closedir(struct inode *inode, struct file *file)
 		pTcon = cifs_sb->tcon;
 
 		cFYI(1, ("Freeing private data in close dir"));
+		write_lock(&GlobalSMBSeslock);
 		if (!pCFileStruct->srch_inf.endOfSearch &&
 		    !pCFileStruct->invalidHandle) {
 			pCFileStruct->invalidHandle = true;
+			write_unlock(&GlobalSMBSeslock);
 			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;
-		}
+		} else
+			write_unlock(&GlobalSMBSeslock);
 		ptmp = pCFileStruct->srch_inf.ntwrk_buf_start;
 		if (ptmp) {
 			cFYI(1, ("closedir free smb buf in srch struct"));
@@ -1404,7 +1411,10 @@ retry:
 			if ((wbc->nr_to_write -= n_iov) <= 0)
 				done = 1;
 			index = next;
-		}
+		} else
+			/* Need to re-find the pages we skipped */
+			index = pvec.pages[0]->index + 1;
+
 		pagevec_release(&pvec);
 	}
 	if (!scanned && !done) {
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 88786ba02d27..9ee3f689c2b0 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -75,12 +75,12 @@ sesInfoAlloc(void)
 
 	ret_buf = kzalloc(sizeof(struct cifsSesInfo), GFP_KERNEL);
 	if (ret_buf) {
-		write_lock(&GlobalSMBSeslock);
 		atomic_inc(&sesInfoAllocCount);
 		ret_buf->status = CifsNew;
-		list_add(&ret_buf->cifsSessionList, &GlobalSMBSessionList);
+		++ret_buf->ses_count;
+		INIT_LIST_HEAD(&ret_buf->smb_ses_list);
+		INIT_LIST_HEAD(&ret_buf->tcon_list);
 		init_MUTEX(&ret_buf->sesSem);
-		write_unlock(&GlobalSMBSeslock);
 	}
 	return ret_buf;
 }
@@ -93,10 +93,7 @@ sesInfoFree(struct cifsSesInfo *buf_to_free)
 		return;
 	}
 
-	write_lock(&GlobalSMBSeslock);
 	atomic_dec(&sesInfoAllocCount);
-	list_del(&buf_to_free->cifsSessionList);
-	write_unlock(&GlobalSMBSeslock);
 	kfree(buf_to_free->serverOS);
 	kfree(buf_to_free->serverDomain);
 	kfree(buf_to_free->serverNOS);
@@ -111,17 +108,14 @@ tconInfoAlloc(void)
 	struct cifsTconInfo *ret_buf;
 	ret_buf = kzalloc(sizeof(struct cifsTconInfo), GFP_KERNEL);
 	if (ret_buf) {
-		write_lock(&GlobalSMBSeslock);
 		atomic_inc(&tconInfoAllocCount);
-		list_add(&ret_buf->cifsConnectionList,
-			 &GlobalTreeConnectionList);
 		ret_buf->tidStatus = CifsNew;
+		++ret_buf->tc_count;
 		INIT_LIST_HEAD(&ret_buf->openFileList);
-		init_MUTEX(&ret_buf->tconSem);
+		INIT_LIST_HEAD(&ret_buf->tcon_list);
 #ifdef CONFIG_CIFS_STATS
 		spin_lock_init(&ret_buf->stat_lock);
 #endif
-		write_unlock(&GlobalSMBSeslock);
 	}
 	return ret_buf;
 }
@@ -133,10 +127,7 @@ tconInfoFree(struct cifsTconInfo *buf_to_free)
 		cFYI(1, ("Null buffer passed to tconInfoFree"));
 		return;
 	}
-	write_lock(&GlobalSMBSeslock);
 	atomic_dec(&tconInfoAllocCount);
-	list_del(&buf_to_free->cifsConnectionList);
-	write_unlock(&GlobalSMBSeslock);
 	kfree(buf_to_free->nativeFileSystem);
 	kfree(buf_to_free);
 }
@@ -350,9 +341,9 @@ header_assemble(struct smb_hdr *buffer, char smb_command /* command */ ,
 				if (current->fsuid != treeCon->ses->linux_uid) {
 					cFYI(1, ("Multiuser mode and UID "
 						 "did not match tcon uid"));
-					read_lock(&GlobalSMBSeslock);
-					list_for_each(temp_item, &GlobalSMBSessionList) {
-						ses = list_entry(temp_item, struct cifsSesInfo, cifsSessionList);
+					read_lock(&cifs_tcp_ses_lock);
+					list_for_each(temp_item, &treeCon->ses->server->smb_ses_list) {
+						ses = list_entry(temp_item, struct cifsSesInfo, smb_ses_list);
 						if (ses->linux_uid == current->fsuid) {
 							if (ses->server == treeCon->ses->server) {
 								cFYI(1, ("found matching uid substitute right smb_uid"));
@@ -364,7 +355,7 @@ header_assemble(struct smb_hdr *buffer, char smb_command /* command */ ,
 							}
 						}
 					}
-					read_unlock(&GlobalSMBSeslock);
+					read_unlock(&cifs_tcp_ses_lock);
 				}
 			}
 		}
@@ -497,9 +488,10 @@ bool
 is_valid_oplock_break(struct smb_hdr *buf, struct TCP_Server_Info *srv)
 {
 	struct smb_com_lock_req *pSMB = (struct smb_com_lock_req *)buf;
-	struct list_head *tmp;
-	struct list_head *tmp1;
+	struct list_head *tmp, *tmp1, *tmp2;
+	struct cifsSesInfo *ses;
 	struct cifsTconInfo *tcon;
+	struct cifsInodeInfo *pCifsInode;
 	struct cifsFileInfo *netfile;
 
 	cFYI(1, ("Checking for oplock break or dnotify response"));
@@ -554,42 +546,45 @@ is_valid_oplock_break(struct smb_hdr *buf, struct TCP_Server_Info *srv)
 		return false;
 
 	/* look up tcon based on tid & uid */
-	read_lock(&GlobalSMBSeslock);
-	list_for_each(tmp, &GlobalTreeConnectionList) {
-		tcon = list_entry(tmp, struct cifsTconInfo, cifsConnectionList);
-		if ((tcon->tid == buf->Tid) && (srv == tcon->ses->server)) {
+	read_lock(&cifs_tcp_ses_lock);
+	list_for_each(tmp, &srv->smb_ses_list) {
+		ses = list_entry(tmp, struct cifsSesInfo, smb_ses_list);
+		list_for_each(tmp1, &ses->tcon_list) {
+			tcon = list_entry(tmp1, struct cifsTconInfo, tcon_list);
+			if (tcon->tid != buf->Tid)
+				continue;
+
 			cifs_stats_inc(&tcon->num_oplock_brks);
-			list_for_each(tmp1, &tcon->openFileList) {
-				netfile = list_entry(tmp1, struct cifsFileInfo,
+			write_lock(&GlobalSMBSeslock);
+			list_for_each(tmp2, &tcon->openFileList) {
+				netfile = list_entry(tmp2, struct cifsFileInfo,
 						     tlist);
-				if (pSMB->Fid == netfile->netfid) {
-					struct cifsInodeInfo *pCifsInode;
-					read_unlock(&GlobalSMBSeslock);
-					cFYI(1,
-					    ("file id match, oplock break"));
-					pCifsInode =
-						CIFS_I(netfile->pInode);
-					pCifsInode->clientCanCacheAll = false;
-					if (pSMB->OplockLevel == 0)
-						pCifsInode->clientCanCacheRead
-							= false;
-					pCifsInode->oplockPending = true;
-					AllocOplockQEntry(netfile->pInode,
-							  netfile->netfid,
-							  tcon);
-					cFYI(1,
-					    ("about to wake up oplock thread"));
-					if (oplockThread)
-					    wake_up_process(oplockThread);
-					return true;
-				}
+				if (pSMB->Fid != netfile->netfid)
+					continue;
+
+				write_unlock(&GlobalSMBSeslock);
+				read_unlock(&cifs_tcp_ses_lock);
+				cFYI(1, ("file id match, oplock break"));
+				pCifsInode = CIFS_I(netfile->pInode);
+				pCifsInode->clientCanCacheAll = false;
+				if (pSMB->OplockLevel == 0)
+					pCifsInode->clientCanCacheRead = false;
+				pCifsInode->oplockPending = true;
+				AllocOplockQEntry(netfile->pInode,
+						  netfile->netfid, tcon);
+				cFYI(1, ("about to wake up oplock thread"));
+				if (oplockThread)
+					wake_up_process(oplockThread);
+
+				return true;
 			}
-			read_unlock(&GlobalSMBSeslock);
+			write_unlock(&GlobalSMBSeslock);
+			read_unlock(&cifs_tcp_ses_lock);
 			cFYI(1, ("No matching file for oplock break"));
 			return true;
 		}
 	}
-	read_unlock(&GlobalSMBSeslock);
+	read_unlock(&cifs_tcp_ses_lock);
 	cFYI(1, ("Can not process oplock break for non-existent connection"));
 	return true;
 }
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index 58d57299f2a0..9f51f9bf0292 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -741,11 +741,14 @@ static int find_cifs_entry(const int xid, struct cifsTconInfo *pTcon,
 	   (index_to_find < first_entry_in_buffer)) {
 		/* close and restart search */
 		cFYI(1, ("search backing up - close and restart search"));
+		write_lock(&GlobalSMBSeslock);
 		if (!cifsFile->srch_inf.endOfSearch &&
 		    !cifsFile->invalidHandle) {
 			cifsFile->invalidHandle = true;
+			write_unlock(&GlobalSMBSeslock);
 			CIFSFindClose(xid, pTcon, cifsFile->netfid);
-		}
+		} else
+			write_unlock(&GlobalSMBSeslock);
 		if (cifsFile->srch_inf.ntwrk_buf_start) {
 			cFYI(1, ("freeing SMB ff cache buf on search rewind"));
 			if (cifsFile->srch_inf.smallBuf)
diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c
index d910501de6d2..8d86b7960f0d 100644
--- a/fs/dlm/lockspace.c
+++ b/fs/dlm/lockspace.c
@@ -812,7 +812,7 @@ int dlm_release_lockspace(void *lockspace, int force)
 	error = release_lockspace(ls, force);
 	if (!error)
 		ls_count--;
-	else if (!ls_count)
+	if (!ls_count)
 		threads_stop();
 	mutex_unlock(&ls_lock);
 
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index e22bc3961345..0d713b691941 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -1037,17 +1037,14 @@ static int
 decrypt_passphrase_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok,
 					 struct ecryptfs_crypt_stat *crypt_stat)
 {
-	struct scatterlist dst_sg;
-	struct scatterlist src_sg;
+	struct scatterlist dst_sg[2];
+	struct scatterlist src_sg[2];
 	struct mutex *tfm_mutex;
 	struct blkcipher_desc desc = {
 		.flags = CRYPTO_TFM_REQ_MAY_SLEEP
 	};
 	int rc = 0;
 
-	sg_init_table(&dst_sg, 1);
-	sg_init_table(&src_sg, 1);
-
 	if (unlikely(ecryptfs_verbosity > 0)) {
 		ecryptfs_printk(
 			KERN_DEBUG, "Session key encryption key (size [%d]):\n",
@@ -1066,8 +1063,8 @@ decrypt_passphrase_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok,
 	}
 	rc = virt_to_scatterlist(auth_tok->session_key.encrypted_key,
 				 auth_tok->session_key.encrypted_key_size,
-				 &src_sg, 1);
-	if (rc != 1) {
+				 src_sg, 2);
+	if (rc < 1 || rc > 2) {
 		printk(KERN_ERR "Internal error whilst attempting to convert "
 			"auth_tok->session_key.encrypted_key to scatterlist; "
 			"expected rc = 1; got rc = [%d]. "
@@ -1079,8 +1076,8 @@ decrypt_passphrase_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok,
 		auth_tok->session_key.encrypted_key_size;
 	rc = virt_to_scatterlist(auth_tok->session_key.decrypted_key,
 				 auth_tok->session_key.decrypted_key_size,
-				 &dst_sg, 1);
-	if (rc != 1) {
+				 dst_sg, 2);
+	if (rc < 1 || rc > 2) {
 		printk(KERN_ERR "Internal error whilst attempting to convert "
 			"auth_tok->session_key.decrypted_key to scatterlist; "
 			"expected rc = 1; got rc = [%d]\n", rc);
@@ -1096,7 +1093,7 @@ decrypt_passphrase_encrypted_session_key(struct ecryptfs_auth_tok *auth_tok,
 		rc = -EINVAL;
 		goto out;
 	}
-	rc = crypto_blkcipher_decrypt(&desc, &dst_sg, &src_sg,
+	rc = crypto_blkcipher_decrypt(&desc, dst_sg, src_sg,
 				      auth_tok->session_key.encrypted_key_size);
 	mutex_unlock(tfm_mutex);
 	if (unlikely(rc)) {
@@ -1539,8 +1536,8 @@ write_tag_3_packet(char *dest, size_t *remaining_bytes,
 	size_t i;
 	size_t encrypted_session_key_valid = 0;
 	char session_key_encryption_key[ECRYPTFS_MAX_KEY_BYTES];
-	struct scatterlist dst_sg;
-	struct scatterlist src_sg;
+	struct scatterlist dst_sg[2];
+	struct scatterlist src_sg[2];
 	struct mutex *tfm_mutex = NULL;
 	u8 cipher_code;
 	size_t packet_size_length;
@@ -1619,8 +1616,8 @@ write_tag_3_packet(char *dest, size_t *remaining_bytes,
 		ecryptfs_dump_hex(session_key_encryption_key, 16);
 	}
 	rc = virt_to_scatterlist(crypt_stat->key, key_rec->enc_key_size,
-				 &src_sg, 1);
-	if (rc != 1) {
+				 src_sg, 2);
+	if (rc < 1 || rc > 2) {
 		ecryptfs_printk(KERN_ERR, "Error generating scatterlist "
 				"for crypt_stat session key; expected rc = 1; "
 				"got rc = [%d]. key_rec->enc_key_size = [%d]\n",
@@ -1629,8 +1626,8 @@ write_tag_3_packet(char *dest, size_t *remaining_bytes,
 		goto out;
 	}
 	rc = virt_to_scatterlist(key_rec->enc_key, key_rec->enc_key_size,
-				 &dst_sg, 1);
-	if (rc != 1) {
+				 dst_sg, 2);
+	if (rc < 1 || rc > 2) {
 		ecryptfs_printk(KERN_ERR, "Error generating scatterlist "
 				"for crypt_stat encrypted session key; "
 				"expected rc = 1; got rc = [%d]. "
@@ -1651,7 +1648,7 @@ write_tag_3_packet(char *dest, size_t *remaining_bytes,
 	rc = 0;
 	ecryptfs_printk(KERN_DEBUG, "Encrypting [%d] bytes of the key\n",
 			crypt_stat->key_size);
-	rc = crypto_blkcipher_encrypt(&desc, &dst_sg, &src_sg,
+	rc = crypto_blkcipher_encrypt(&desc, dst_sg, src_sg,
 				      (*key_rec).enc_key_size);
 	mutex_unlock(tfm_mutex);
 	if (rc) {
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index e5717a4fae67..f6c94f232ec1 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -2375,12 +2375,9 @@ int ext3_force_commit(struct super_block *sb)
 /*
  * Ext3 always journals updates to the superblock itself, so we don't
  * have to propagate any other updates to the superblock on disk at this
- * point.  Just start an async writeback to get the buffers on their way
- * to the disk.
- *
- * This implicitly triggers the writebehind on sync().
+ * point.  (We can probably nuke this function altogether, and remove
+ * any mention to sb->s_dirt in all of fs/ext3; eventual cleanup...)
  */
-
 static void ext3_write_super (struct super_block * sb)
 {
 	if (mutex_trylock(&sb->s_lock) != 0)
@@ -2390,13 +2387,12 @@ static void ext3_write_super (struct super_block * sb)
 
 static int ext3_sync_fs(struct super_block *sb, int wait)
 {
-	tid_t target;
-
 	sb->s_dirt = 0;
-	if (journal_start_commit(EXT3_SB(sb)->s_journal, &target)) {
-		if (wait)
-			log_wait_commit(EXT3_SB(sb)->s_journal, target);
-	}
+	if (wait)
+		ext3_force_commit(sb);
+	else
+		journal_start_commit(EXT3_SB(sb)->s_journal, NULL);
+
 	return 0;
 }
 
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index fe34d74cfb19..2a117e286e54 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -718,6 +718,8 @@ got:
 			gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
 			free = ext4_free_blocks_after_init(sb, group, gdp);
 			gdp->bg_free_blocks_count = cpu_to_le16(free);
+			gdp->bg_checksum = ext4_group_desc_csum(sbi, group,
+								gdp);
 		}
 		spin_unlock(sb_bgl_lock(sbi, group));
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 8dbf6953845b..be21a5ae33cb 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2329,6 +2329,8 @@ static int ext4_da_writepage(struct page *page,
 			unlock_page(page);
 			return 0;
 		}
+		/* now mark the buffer_heads as dirty and uptodate */
+		block_commit_write(page, 0, PAGE_CACHE_SIZE);
 	}
 
 	if (test_opt(inode->i_sb, NOBH) && ext4_should_writeback_data(inode))
@@ -4580,9 +4582,10 @@ static int ext4_indirect_trans_blocks(struct inode *inode, int nrblocks,
 static int ext4_index_trans_blocks(struct inode *inode, int nrblocks, int chunk)
 {
 	if (!(EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL))
-		return ext4_indirect_trans_blocks(inode, nrblocks, 0);
-	return ext4_ext_index_trans_blocks(inode, nrblocks, 0);
+		return ext4_indirect_trans_blocks(inode, nrblocks, chunk);
+	return ext4_ext_index_trans_blocks(inode, nrblocks, chunk);
 }
+
 /*
  * Account for index blocks, block groups bitmaps and block group
  * descriptor blocks if modify datablocks and index blocks
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index dfe17a134052..444ad998f72e 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -4441,6 +4441,7 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
 		else if (block >= (entry->start_blk + entry->count))
 			n = &(*n)->rb_right;
 		else {
+			ext4_unlock_group(sb, group);
 			ext4_error(sb, __func__,
 			    "Double free of blocks %d (%d %d)\n",
 			    block, entry->start_blk, entry->count);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 994859df010e..e4a241c65dbe 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1458,9 +1458,8 @@ static int ext4_fill_flex_info(struct super_block *sb)
 
 	/* We allocate both existing and potentially added groups */
 	flex_group_count = ((sbi->s_groups_count + groups_per_flex - 1) +
-			    ((sbi->s_es->s_reserved_gdt_blocks +1 ) <<
-			      EXT4_DESC_PER_BLOCK_BITS(sb))) /
-			   groups_per_flex;
+			((le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) + 1) <<
+			      EXT4_DESC_PER_BLOCK_BITS(sb))) / groups_per_flex;
 	sbi->s_flex_groups = kzalloc(flex_group_count *
 				     sizeof(struct flex_groups), GFP_KERNEL);
 	if (sbi->s_flex_groups == NULL) {
@@ -2885,12 +2884,9 @@ int ext4_force_commit(struct super_block *sb)
 /*
  * Ext4 always journals updates to the superblock itself, so we don't
  * have to propagate any other updates to the superblock on disk at this
- * point.  Just start an async writeback to get the buffers on their way
- * to the disk.
- *
- * This implicitly triggers the writebehind on sync().
+ * point.  (We can probably nuke this function altogether, and remove
+ * any mention to sb->s_dirt in all of fs/ext4; eventual cleanup...)
  */
-
 static void ext4_write_super(struct super_block *sb)
 {
 	if (mutex_trylock(&sb->s_lock) != 0)
@@ -2900,15 +2896,15 @@ static void ext4_write_super(struct super_block *sb)
 
 static int ext4_sync_fs(struct super_block *sb, int wait)
 {
-	tid_t target;
+	int ret = 0;
 
 	trace_mark(ext4_sync_fs, "dev %s wait %d", sb->s_id, wait);
 	sb->s_dirt = 0;
-	if (jbd2_journal_start_commit(EXT4_SB(sb)->s_journal, &target)) {
-		if (wait)
-			jbd2_log_wait_commit(EXT4_SB(sb)->s_journal, target);
-	}
-	return 0;
+	if (wait)
+		ret = ext4_force_commit(sb);
+	else
+		jbd2_journal_start_commit(EXT4_SB(sb)->s_journal, NULL);
+	return ret;
 }
 
 /*
diff --git a/fs/fat/Makefile b/fs/fat/Makefile
index bfb5f06cf2c8..e06190322c1c 100644
--- a/fs/fat/Makefile
+++ b/fs/fat/Makefile
@@ -3,5 +3,9 @@
 #
 
 obj-$(CONFIG_FAT_FS) += fat.o
+obj-$(CONFIG_VFAT_FS) += vfat.o
+obj-$(CONFIG_MSDOS_FS) += msdos.o
 
-fat-objs := cache.o dir.o fatent.o file.o inode.o misc.o
+fat-y := cache.o dir.o fatent.o file.o inode.o misc.o
+vfat-y := namei_vfat.o
+msdos-y := namei_msdos.o
diff --git a/fs/fat/cache.c b/fs/fat/cache.c
index 3222f51c41cf..b42602298087 100644
--- a/fs/fat/cache.c
+++ b/fs/fat/cache.c
@@ -9,8 +9,8 @@
  */
 
 #include <linux/fs.h>
-#include <linux/msdos_fs.h>
 #include <linux/buffer_head.h>
+#include "fat.h"
 
 /* this must be > 0. */
 #define FAT_MAX_CACHE	8
@@ -293,10 +293,12 @@ static int fat_bmap_cluster(struct inode *inode, int cluster)
 }
 
 int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys,
-	     unsigned long *mapped_blocks)
+	     unsigned long *mapped_blocks, int create)
 {
 	struct super_block *sb = inode->i_sb;
 	struct msdos_sb_info *sbi = MSDOS_SB(sb);
+	const unsigned long blocksize = sb->s_blocksize;
+	const unsigned char blocksize_bits = sb->s_blocksize_bits;
 	sector_t last_block;
 	int cluster, offset;
 
@@ -309,10 +311,21 @@ int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys,
 		}
 		return 0;
 	}
-	last_block = (MSDOS_I(inode)->mmu_private + (sb->s_blocksize - 1))
-		>> sb->s_blocksize_bits;
-	if (sector >= last_block)
-		return 0;
+
+	last_block = (i_size_read(inode) + (blocksize - 1)) >> blocksize_bits;
+	if (sector >= last_block) {
+		if (!create)
+			return 0;
+
+		/*
+		 * ->mmu_private can access on only allocation path.
+		 * (caller must hold ->i_mutex)
+		 */
+		last_block = (MSDOS_I(inode)->mmu_private + (blocksize - 1))
+			>> blocksize_bits;
+		if (sector >= last_block)
+			return 0;
+	}
 
 	cluster = sector >> (sbi->cluster_bits - sb->s_blocksize_bits);
 	offset  = sector & (sbi->sec_per_clus - 1);
diff --git a/fs/fat/dir.c b/fs/fat/dir.c
index bae1c3292522..67e058357098 100644
--- a/fs/fat/dir.c
+++ b/fs/fat/dir.c
@@ -16,11 +16,11 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/time.h>
-#include <linux/msdos_fs.h>
 #include <linux/smp_lock.h>
 #include <linux/buffer_head.h>
 #include <linux/compat.h>
 #include <asm/uaccess.h>
+#include "fat.h"
 
 static inline loff_t fat_make_i_pos(struct super_block *sb,
 				    struct buffer_head *bh,
@@ -77,7 +77,7 @@ next:
 
 	*bh = NULL;
 	iblock = *pos >> sb->s_blocksize_bits;
-	err = fat_bmap(dir, iblock, &phys, &mapped_blocks);
+	err = fat_bmap(dir, iblock, &phys, &mapped_blocks, 0);
 	if (err || !phys)
 		return -1;	/* beyond EOF or error */
 
@@ -86,7 +86,7 @@ next:
 	*bh = sb_bread(sb, phys);
 	if (*bh == NULL) {
 		printk(KERN_ERR "FAT: Directory bread(block %llu) failed\n",
-		       (unsigned long long)phys);
+		       (llu)phys);
 		/* skip this block */
 		*pos = (iblock + 1) << sb->s_blocksize_bits;
 		goto next;
@@ -373,9 +373,10 @@ parse_record:
 		if (de->attr == ATTR_EXT) {
 			int status = fat_parse_long(inode, &cpos, &bh, &de,
 						    &unicode, &nr_slots);
-			if (status < 0)
-				return status;
-			else if (status == PARSE_INVALID)
+			if (status < 0) {
+				err = status;
+				goto end_of_dir;
+			} else if (status == PARSE_INVALID)
 				continue;
 			else if (status == PARSE_NOT_LONGNAME)
 				goto parse_record;
@@ -832,6 +833,7 @@ static long fat_compat_dir_ioctl(struct file *filp, unsigned cmd,
 #endif /* CONFIG_COMPAT */
 
 const struct file_operations fat_dir_operations = {
+	.llseek		= generic_file_llseek,
 	.read		= generic_read_dir,
 	.readdir	= fat_readdir,
 	.ioctl		= fat_dir_ioctl,
@@ -1089,6 +1091,7 @@ int fat_alloc_new_dir(struct inode *dir, struct timespec *ts)
 	struct msdos_dir_entry *de;
 	sector_t blknr;
 	__le16 date, time;
+	u8 time_cs;
 	int err, cluster;
 
 	err = fat_alloc_clusters(dir, &cluster, 1);
@@ -1102,7 +1105,7 @@ int fat_alloc_new_dir(struct inode *dir, struct timespec *ts)
 		goto error_free;
 	}
 
-	fat_date_unix2dos(ts->tv_sec, &time, &date, sbi->options.tz_utc);
+	fat_time_unix2fat(sbi, ts, &time, &date, &time_cs);
 
 	de = (struct msdos_dir_entry *)bhs[0]->b_data;
 	/* filling the new directory slots ("." and ".." entries) */
@@ -1112,13 +1115,14 @@ int fat_alloc_new_dir(struct inode *dir, struct timespec *ts)
 	de[0].lcase = de[1].lcase = 0;
 	de[0].time = de[1].time = time;
 	de[0].date = de[1].date = date;
-	de[0].ctime_cs = de[1].ctime_cs = 0;
 	if (sbi->options.isvfat) {
 		/* extra timestamps */
 		de[0].ctime = de[1].ctime = time;
+		de[0].ctime_cs = de[1].ctime_cs = time_cs;
 		de[0].adate = de[0].cdate = de[1].adate = de[1].cdate = date;
 	} else {
 		de[0].ctime = de[1].ctime = 0;
+		de[0].ctime_cs = de[1].ctime_cs = 0;
 		de[0].adate = de[0].cdate = de[1].adate = de[1].cdate = 0;
 	}
 	de[0].start = cpu_to_le16(cluster);
diff --git a/fs/fat/fat.h b/fs/fat/fat.h
new file mode 100644
index 000000000000..ea440d65819c
--- /dev/null
+++ b/fs/fat/fat.h
@@ -0,0 +1,329 @@
+#ifndef _FAT_H
+#define _FAT_H
+
+#include <linux/buffer_head.h>
+#include <linux/string.h>
+#include <linux/nls.h>
+#include <linux/fs.h>
+#include <linux/mutex.h>
+#include <linux/msdos_fs.h>
+
+/*
+ * vfat shortname flags
+ */
+#define VFAT_SFN_DISPLAY_LOWER	0x0001 /* convert to lowercase for display */
+#define VFAT_SFN_DISPLAY_WIN95	0x0002 /* emulate win95 rule for display */
+#define VFAT_SFN_DISPLAY_WINNT	0x0004 /* emulate winnt rule for display */
+#define VFAT_SFN_CREATE_WIN95	0x0100 /* emulate win95 rule for create */
+#define VFAT_SFN_CREATE_WINNT	0x0200 /* emulate winnt rule for create */
+
+struct fat_mount_options {
+	uid_t fs_uid;
+	gid_t fs_gid;
+	unsigned short fs_fmask;
+	unsigned short fs_dmask;
+	unsigned short codepage;  /* Codepage for shortname conversions */
+	char *iocharset;          /* Charset used for filename input/display */
+	unsigned short shortname; /* flags for shortname display/create rule */
+	unsigned char name_check; /* r = relaxed, n = normal, s = strict */
+	unsigned short allow_utime;/* permission for setting the [am]time */
+	unsigned quiet:1,         /* set = fake successful chmods and chowns */
+		 showexec:1,      /* set = only set x bit for com/exe/bat */
+		 sys_immutable:1, /* set = system files are immutable */
+		 dotsOK:1,        /* set = hidden and system files are named '.filename' */
+		 isvfat:1,        /* 0=no vfat long filename support, 1=vfat support */
+		 utf8:1,	  /* Use of UTF-8 character set (Default) */
+		 unicode_xlate:1, /* create escape sequences for unhandled Unicode */
+		 numtail:1,       /* Does first alias have a numeric '~1' type tail? */
+		 flush:1,	  /* write things quickly */
+		 nocase:1,	  /* Does this need case conversion? 0=need case conversion*/
+		 usefree:1,	  /* Use free_clusters for FAT32 */
+		 tz_utc:1,	  /* Filesystem timestamps are in UTC */
+		 rodir:1;	  /* allow ATTR_RO for directory */
+};
+
+#define FAT_HASH_BITS	8
+#define FAT_HASH_SIZE	(1UL << FAT_HASH_BITS)
+
+/*
+ * MS-DOS file system in-core superblock data
+ */
+struct msdos_sb_info {
+	unsigned short sec_per_clus; /* sectors/cluster */
+	unsigned short cluster_bits; /* log2(cluster_size) */
+	unsigned int cluster_size;   /* cluster size */
+	unsigned char fats,fat_bits; /* number of FATs, FAT bits (12 or 16) */
+	unsigned short fat_start;
+	unsigned long fat_length;    /* FAT start & length (sec.) */
+	unsigned long dir_start;
+	unsigned short dir_entries;  /* root dir start & entries */
+	unsigned long data_start;    /* first data sector */
+	unsigned long max_cluster;   /* maximum cluster number */
+	unsigned long root_cluster;  /* first cluster of the root directory */
+	unsigned long fsinfo_sector; /* sector number of FAT32 fsinfo */
+	struct mutex fat_lock;
+	unsigned int prev_free;      /* previously allocated cluster number */
+	unsigned int free_clusters;  /* -1 if undefined */
+	unsigned int free_clus_valid; /* is free_clusters valid? */
+	struct fat_mount_options options;
+	struct nls_table *nls_disk;  /* Codepage used on disk */
+	struct nls_table *nls_io;    /* Charset used for input and display */
+	const void *dir_ops;		     /* Opaque; default directory operations */
+	int dir_per_block;	     /* dir entries per block */
+	int dir_per_block_bits;	     /* log2(dir_per_block) */
+
+	int fatent_shift;
+	struct fatent_operations *fatent_ops;
+
+	spinlock_t inode_hash_lock;
+	struct hlist_head inode_hashtable[FAT_HASH_SIZE];
+};
+
+#define FAT_CACHE_VALID	0	/* special case for valid cache */
+
+/*
+ * MS-DOS file system inode data in memory
+ */
+struct msdos_inode_info {
+	spinlock_t cache_lru_lock;
+	struct list_head cache_lru;
+	int nr_caches;
+	/* for avoiding the race between fat_free() and fat_get_cluster() */
+	unsigned int cache_valid_id;
+
+	/* NOTE: mmu_private is 64bits, so must hold ->i_mutex to access */
+	loff_t mmu_private;	/* physically allocated size */
+
+	int i_start;		/* first cluster or 0 */
+	int i_logstart;		/* logical first cluster */
+	int i_attrs;		/* unused attribute bits */
+	loff_t i_pos;		/* on-disk position of directory entry or 0 */
+	struct hlist_node i_fat_hash;	/* hash by i_location */
+	struct inode vfs_inode;
+};
+
+struct fat_slot_info {
+	loff_t i_pos;		/* on-disk position of directory entry */
+	loff_t slot_off;	/* offset for slot or de start */
+	int nr_slots;		/* number of slots + 1(de) in filename */
+	struct msdos_dir_entry *de;
+	struct buffer_head *bh;
+};
+
+static inline struct msdos_sb_info *MSDOS_SB(struct super_block *sb)
+{
+	return sb->s_fs_info;
+}
+
+static inline struct msdos_inode_info *MSDOS_I(struct inode *inode)
+{
+	return container_of(inode, struct msdos_inode_info, vfs_inode);
+}
+
+/*
+ * If ->i_mode can't hold S_IWUGO (i.e. ATTR_RO), we use ->i_attrs to
+ * save ATTR_RO instead of ->i_mode.
+ *
+ * If it's directory and !sbi->options.rodir, ATTR_RO isn't read-only
+ * bit, it's just used as flag for app.
+ */
+static inline int fat_mode_can_hold_ro(struct inode *inode)
+{
+	struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
+	mode_t mask;
+
+	if (S_ISDIR(inode->i_mode)) {
+		if (!sbi->options.rodir)
+			return 0;
+		mask = ~sbi->options.fs_dmask;
+	} else
+		mask = ~sbi->options.fs_fmask;
+
+	if (!(mask & S_IWUGO))
+		return 0;
+	return 1;
+}
+
+/* Convert attribute bits and a mask to the UNIX mode. */
+static inline mode_t fat_make_mode(struct msdos_sb_info *sbi,
+				   u8 attrs, mode_t mode)
+{
+	if (attrs & ATTR_RO && !((attrs & ATTR_DIR) && !sbi->options.rodir))
+		mode &= ~S_IWUGO;
+
+	if (attrs & ATTR_DIR)
+		return (mode & ~sbi->options.fs_dmask) | S_IFDIR;
+	else
+		return (mode & ~sbi->options.fs_fmask) | S_IFREG;
+}
+
+/* Return the FAT attribute byte for this inode */
+static inline u8 fat_make_attrs(struct inode *inode)
+{
+	u8 attrs = MSDOS_I(inode)->i_attrs;
+	if (S_ISDIR(inode->i_mode))
+		attrs |= ATTR_DIR;
+	if (fat_mode_can_hold_ro(inode) && !(inode->i_mode & S_IWUGO))
+		attrs |= ATTR_RO;
+	return attrs;
+}
+
+static inline void fat_save_attrs(struct inode *inode, u8 attrs)
+{
+	if (fat_mode_can_hold_ro(inode))
+		MSDOS_I(inode)->i_attrs = attrs & ATTR_UNUSED;
+	else
+		MSDOS_I(inode)->i_attrs = attrs & (ATTR_UNUSED | ATTR_RO);
+}
+
+static inline unsigned char fat_checksum(const __u8 *name)
+{
+	unsigned char s = name[0];
+	s = (s<<7) + (s>>1) + name[1];	s = (s<<7) + (s>>1) + name[2];
+	s = (s<<7) + (s>>1) + name[3];	s = (s<<7) + (s>>1) + name[4];
+	s = (s<<7) + (s>>1) + name[5];	s = (s<<7) + (s>>1) + name[6];
+	s = (s<<7) + (s>>1) + name[7];	s = (s<<7) + (s>>1) + name[8];
+	s = (s<<7) + (s>>1) + name[9];	s = (s<<7) + (s>>1) + name[10];
+	return s;
+}
+
+static inline sector_t fat_clus_to_blknr(struct msdos_sb_info *sbi, int clus)
+{
+	return ((sector_t)clus - FAT_START_ENT) * sbi->sec_per_clus
+		+ sbi->data_start;
+}
+
+static inline void fat16_towchar(wchar_t *dst, const __u8 *src, size_t len)
+{
+#ifdef __BIG_ENDIAN
+	while (len--) {
+		*dst++ = src[0] | (src[1] << 8);
+		src += 2;
+	}
+#else
+	memcpy(dst, src, len * 2);
+#endif
+}
+
+static inline void fatwchar_to16(__u8 *dst, const wchar_t *src, size_t len)
+{
+#ifdef __BIG_ENDIAN
+	while (len--) {
+		dst[0] = *src & 0x00FF;
+		dst[1] = (*src & 0xFF00) >> 8;
+		dst += 2;
+		src++;
+	}
+#else
+	memcpy(dst, src, len * 2);
+#endif
+}
+
+/* fat/cache.c */
+extern void fat_cache_inval_inode(struct inode *inode);
+extern int fat_get_cluster(struct inode *inode, int cluster,
+			   int *fclus, int *dclus);
+extern int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys,
+		    unsigned long *mapped_blocks, int create);
+
+/* fat/dir.c */
+extern const struct file_operations fat_dir_operations;
+extern int fat_search_long(struct inode *inode, const unsigned char *name,
+			   int name_len, struct fat_slot_info *sinfo);
+extern int fat_dir_empty(struct inode *dir);
+extern int fat_subdirs(struct inode *dir);
+extern int fat_scan(struct inode *dir, const unsigned char *name,
+		    struct fat_slot_info *sinfo);
+extern int fat_get_dotdot_entry(struct inode *dir, struct buffer_head **bh,
+				struct msdos_dir_entry **de, loff_t *i_pos);
+extern int fat_alloc_new_dir(struct inode *dir, struct timespec *ts);
+extern int fat_add_entries(struct inode *dir, void *slots, int nr_slots,
+			   struct fat_slot_info *sinfo);
+extern int fat_remove_entries(struct inode *dir, struct fat_slot_info *sinfo);
+
+/* fat/fatent.c */
+struct fat_entry {
+	int entry;
+	union {
+		u8 *ent12_p[2];
+		__le16 *ent16_p;
+		__le32 *ent32_p;
+	} u;
+	int nr_bhs;
+	struct buffer_head *bhs[2];
+};
+
+static inline void fatent_init(struct fat_entry *fatent)
+{
+	fatent->nr_bhs = 0;
+	fatent->entry = 0;
+	fatent->u.ent32_p = NULL;
+	fatent->bhs[0] = fatent->bhs[1] = NULL;
+}
+
+static inline void fatent_set_entry(struct fat_entry *fatent, int entry)
+{
+	fatent->entry = entry;
+	fatent->u.ent32_p = NULL;
+}
+
+static inline void fatent_brelse(struct fat_entry *fatent)
+{
+	int i;
+	fatent->u.ent32_p = NULL;
+	for (i = 0; i < fatent->nr_bhs; i++)
+		brelse(fatent->bhs[i]);
+	fatent->nr_bhs = 0;
+	fatent->bhs[0] = fatent->bhs[1] = NULL;
+}
+
+extern void fat_ent_access_init(struct super_block *sb);
+extern int fat_ent_read(struct inode *inode, struct fat_entry *fatent,
+			int entry);
+extern int fat_ent_write(struct inode *inode, struct fat_entry *fatent,
+			 int new, int wait);
+extern int fat_alloc_clusters(struct inode *inode, int *cluster,
+			      int nr_cluster);
+extern int fat_free_clusters(struct inode *inode, int cluster);
+extern int fat_count_free_clusters(struct super_block *sb);
+
+/* fat/file.c */
+extern int fat_generic_ioctl(struct inode *inode, struct file *filp,
+			     unsigned int cmd, unsigned long arg);
+extern const struct file_operations fat_file_operations;
+extern const struct inode_operations fat_file_inode_operations;
+extern int fat_setattr(struct dentry * dentry, struct iattr * attr);
+extern void fat_truncate(struct inode *inode);
+extern int fat_getattr(struct vfsmount *mnt, struct dentry *dentry,
+		       struct kstat *stat);
+
+/* fat/inode.c */
+extern void fat_attach(struct inode *inode, loff_t i_pos);
+extern void fat_detach(struct inode *inode);
+extern struct inode *fat_iget(struct super_block *sb, loff_t i_pos);
+extern struct inode *fat_build_inode(struct super_block *sb,
+			struct msdos_dir_entry *de, loff_t i_pos);
+extern int fat_sync_inode(struct inode *inode);
+extern int fat_fill_super(struct super_block *sb, void *data, int silent,
+			const struct inode_operations *fs_dir_inode_ops, int isvfat);
+
+extern int fat_flush_inodes(struct super_block *sb, struct inode *i1,
+		            struct inode *i2);
+/* fat/misc.c */
+extern void fat_fs_panic(struct super_block *s, const char *fmt, ...)
+	__attribute__ ((format (printf, 2, 3))) __cold;
+extern void fat_clusters_flush(struct super_block *sb);
+extern int fat_chain_add(struct inode *inode, int new_dclus, int nr_cluster);
+extern void fat_time_fat2unix(struct msdos_sb_info *sbi, struct timespec *ts,
+			      __le16 __time, __le16 __date, u8 time_cs);
+extern void fat_time_unix2fat(struct msdos_sb_info *sbi, struct timespec *ts,
+			      __le16 *time, __le16 *date, u8 *time_cs);
+extern int fat_sync_bhs(struct buffer_head **bhs, int nr_bhs);
+
+int fat_cache_init(void);
+void fat_cache_destroy(void);
+
+/* helper for printk */
+typedef unsigned long long	llu;
+
+#endif /* !_FAT_H */
diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c
index fb98b3d847ed..da6eea47872f 100644
--- a/fs/fat/fatent.c
+++ b/fs/fat/fatent.c
@@ -7,6 +7,7 @@
 #include <linux/fs.h>
 #include <linux/msdos_fs.h>
 #include <linux/blkdev.h>
+#include "fat.h"
 
 struct fatent_operations {
 	void (*ent_blocknr)(struct super_block *, int, int *, sector_t *);
@@ -92,8 +93,7 @@ static int fat12_ent_bread(struct super_block *sb, struct fat_entry *fatent,
 err_brelse:
 	brelse(bhs[0]);
 err:
-	printk(KERN_ERR "FAT: FAT read failed (blocknr %llu)\n",
-	       (unsigned long long)blocknr);
+	printk(KERN_ERR "FAT: FAT read failed (blocknr %llu)\n", (llu)blocknr);
 	return -EIO;
 }
 
@@ -106,7 +106,7 @@ static int fat_ent_bread(struct super_block *sb, struct fat_entry *fatent,
 	fatent->bhs[0] = sb_bread(sb, blocknr);
 	if (!fatent->bhs[0]) {
 		printk(KERN_ERR "FAT: FAT read failed (blocknr %llu)\n",
-		       (unsigned long long)blocknr);
+		       (llu)blocknr);
 		return -EIO;
 	}
 	fatent->nr_bhs = 1;
@@ -316,10 +316,20 @@ static inline int fat_ent_update_ptr(struct super_block *sb,
 	/* Is this fatent's blocks including this entry? */
 	if (!fatent->nr_bhs || bhs[0]->b_blocknr != blocknr)
 		return 0;
-	/* Does this entry need the next block? */
-	if (sbi->fat_bits == 12 && (offset + 1) >= sb->s_blocksize) {
-		if (fatent->nr_bhs != 2 || bhs[1]->b_blocknr != (blocknr + 1))
-			return 0;
+	if (sbi->fat_bits == 12) {
+		if ((offset + 1) < sb->s_blocksize) {
+			/* This entry is on bhs[0]. */
+			if (fatent->nr_bhs == 2) {
+				brelse(bhs[1]);
+				fatent->nr_bhs = 1;
+			}
+		} else {
+			/* This entry needs the next block. */
+			if (fatent->nr_bhs != 2)
+				return 0;
+			if (bhs[1]->b_blocknr != (blocknr + 1))
+				return 0;
+		}
 	}
 	ops->ent_set_ptr(fatent, offset);
 	return 1;
diff --git a/fs/fat/file.c b/fs/fat/file.c
index ddde37025ca6..f06a4e525ece 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -10,13 +10,13 @@
 #include <linux/module.h>
 #include <linux/mount.h>
 #include <linux/time.h>
-#include <linux/msdos_fs.h>
 #include <linux/buffer_head.h>
 #include <linux/writeback.h>
 #include <linux/backing-dev.h>
 #include <linux/blkdev.h>
 #include <linux/fsnotify.h>
 #include <linux/security.h>
+#include "fat.h"
 
 int fat_generic_ioctl(struct inode *inode, struct file *filp,
 		      unsigned int cmd, unsigned long arg)
@@ -29,10 +29,9 @@ int fat_generic_ioctl(struct inode *inode, struct file *filp,
 	{
 		u32 attr;
 
-		if (inode->i_ino == MSDOS_ROOT_INO)
-			attr = ATTR_DIR;
-		else
-			attr = fat_attr(inode);
+		mutex_lock(&inode->i_mutex);
+		attr = fat_make_attrs(inode);
+		mutex_unlock(&inode->i_mutex);
 
 		return put_user(attr, user_attr);
 	}
@@ -62,20 +61,16 @@ int fat_generic_ioctl(struct inode *inode, struct file *filp,
 		/* Merge in ATTR_VOLUME and ATTR_DIR */
 		attr |= (MSDOS_I(inode)->i_attrs & ATTR_VOLUME) |
 			(is_dir ? ATTR_DIR : 0);
-		oldattr = fat_attr(inode);
+		oldattr = fat_make_attrs(inode);
 
 		/* Equivalent to a chmod() */
 		ia.ia_valid = ATTR_MODE | ATTR_CTIME;
 		ia.ia_ctime = current_fs_time(inode->i_sb);
-		if (is_dir) {
-			ia.ia_mode = MSDOS_MKMODE(attr,
-				S_IRWXUGO & ~sbi->options.fs_dmask)
-				| S_IFDIR;
-		} else {
-			ia.ia_mode = MSDOS_MKMODE(attr,
-				(S_IRUGO | S_IWUGO | (inode->i_mode & S_IXUGO))
-				& ~sbi->options.fs_fmask)
-				| S_IFREG;
+		if (is_dir)
+			ia.ia_mode = fat_make_mode(sbi, attr, S_IRWXUGO);
+		else {
+			ia.ia_mode = fat_make_mode(sbi, attr,
+				S_IRUGO | S_IWUGO | (inode->i_mode & S_IXUGO));
 		}
 
 		/* The root directory has no attributes */
@@ -115,7 +110,7 @@ int fat_generic_ioctl(struct inode *inode, struct file *filp,
 				inode->i_flags &= S_IMMUTABLE;
 		}
 
-		MSDOS_I(inode)->i_attrs = attr & ATTR_UNUSED;
+		fat_save_attrs(inode, attr);
 		mark_inode_dirty(inode);
 up:
 		mnt_drop_write(filp->f_path.mnt);
@@ -274,7 +269,7 @@ static int fat_sanitize_mode(const struct msdos_sb_info *sbi,
 
 	/*
 	 * Note, the basic check is already done by a caller of
-	 * (attr->ia_mode & ~MSDOS_VALID_MODE)
+	 * (attr->ia_mode & ~FAT_VALID_MODE)
 	 */
 
 	if (S_ISREG(inode->i_mode))
@@ -287,11 +282,18 @@ static int fat_sanitize_mode(const struct msdos_sb_info *sbi,
 	/*
 	 * Of the r and x bits, all (subject to umask) must be present. Of the
 	 * w bits, either all (subject to umask) or none must be present.
+	 *
+	 * If fat_mode_can_hold_ro(inode) is false, can't change w bits.
 	 */
 	if ((perm & (S_IRUGO | S_IXUGO)) != (inode->i_mode & (S_IRUGO|S_IXUGO)))
 		return -EPERM;
-	if ((perm & S_IWUGO) && ((perm & S_IWUGO) != (S_IWUGO & ~mask)))
-		return -EPERM;
+	if (fat_mode_can_hold_ro(inode)) {
+		if ((perm & S_IWUGO) && ((perm & S_IWUGO) != (S_IWUGO & ~mask)))
+			return -EPERM;
+	} else {
+		if ((perm & S_IWUGO) != (S_IWUGO & ~mask))
+			return -EPERM;
+	}
 
 	*mode_ptr &= S_IFMT | perm;
 
@@ -314,13 +316,15 @@ static int fat_allow_set_time(struct msdos_sb_info *sbi, struct inode *inode)
 }
 
 #define TIMES_SET_FLAGS	(ATTR_MTIME_SET | ATTR_ATIME_SET | ATTR_TIMES_SET)
+/* valid file mode bits */
+#define FAT_VALID_MODE	(S_IFREG | S_IFDIR | S_IRWXUGO)
 
 int fat_setattr(struct dentry *dentry, struct iattr *attr)
 {
 	struct msdos_sb_info *sbi = MSDOS_SB(dentry->d_sb);
 	struct inode *inode = dentry->d_inode;
-	int error = 0;
 	unsigned int ia_valid;
+	int error;
 
 	/*
 	 * Expand the file. Since inode_setattr() updates ->i_size
@@ -356,7 +360,7 @@ int fat_setattr(struct dentry *dentry, struct iattr *attr)
 	    ((attr->ia_valid & ATTR_GID) &&
 	     (attr->ia_gid != sbi->options.fs_gid)) ||
 	    ((attr->ia_valid & ATTR_MODE) &&
-	     (attr->ia_mode & ~MSDOS_VALID_MODE)))
+	     (attr->ia_mode & ~FAT_VALID_MODE)))
 		error = -EPERM;
 
 	if (error) {
@@ -374,7 +378,8 @@ int fat_setattr(struct dentry *dentry, struct iattr *attr)
 			attr->ia_valid &= ~ATTR_MODE;
 	}
 
-	error = inode_setattr(inode, attr);
+	if (attr->ia_valid)
+		error = inode_setattr(inode, attr);
 out:
 	return error;
 }
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 2b2eec1283bf..bdd8fb7be2ca 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -16,7 +16,6 @@
 #include <linux/slab.h>
 #include <linux/smp_lock.h>
 #include <linux/seq_file.h>
-#include <linux/msdos_fs.h>
 #include <linux/pagemap.h>
 #include <linux/mpage.h>
 #include <linux/buffer_head.h>
@@ -27,7 +26,9 @@
 #include <linux/uio.h>
 #include <linux/writeback.h>
 #include <linux/log2.h>
+#include <linux/hash.h>
 #include <asm/unaligned.h>
+#include "fat.h"
 
 #ifndef CONFIG_FAT_DEFAULT_IOCHARSET
 /* if user don't select VFAT, this is undefined. */
@@ -63,7 +64,7 @@ static inline int __fat_get_block(struct inode *inode, sector_t iblock,
 	sector_t phys;
 	int err, offset;
 
-	err = fat_bmap(inode, iblock, &phys, &mapped_blocks);
+	err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create);
 	if (err)
 		return err;
 	if (phys) {
@@ -93,7 +94,7 @@ static inline int __fat_get_block(struct inode *inode, sector_t iblock,
 	*max_blocks = min(mapped_blocks, *max_blocks);
 	MSDOS_I(inode)->mmu_private += *max_blocks << sb->s_blocksize_bits;
 
-	err = fat_bmap(inode, iblock, &phys, &mapped_blocks);
+	err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create);
 	if (err)
 		return err;
 
@@ -198,7 +199,14 @@ static ssize_t fat_direct_IO(int rw, struct kiocb *iocb,
 
 static sector_t _fat_bmap(struct address_space *mapping, sector_t block)
 {
-	return generic_block_bmap(mapping, block, fat_get_block);
+	sector_t blocknr;
+
+	/* fat_get_cluster() assumes the requested blocknr isn't truncated. */
+	mutex_lock(&mapping->host->i_mutex);
+	blocknr = generic_block_bmap(mapping, block, fat_get_block);
+	mutex_unlock(&mapping->host->i_mutex);
+
+	return blocknr;
 }
 
 static const struct address_space_operations fat_aops = {
@@ -247,25 +255,21 @@ static void fat_hash_init(struct super_block *sb)
 		INIT_HLIST_HEAD(&sbi->inode_hashtable[i]);
 }
 
-static inline unsigned long fat_hash(struct super_block *sb, loff_t i_pos)
+static inline unsigned long fat_hash(loff_t i_pos)
 {
-	unsigned long tmp = (unsigned long)i_pos | (unsigned long) sb;
-	tmp = tmp + (tmp >> FAT_HASH_BITS) + (tmp >> FAT_HASH_BITS * 2);
-	return tmp & FAT_HASH_MASK;
+	return hash_32(i_pos, FAT_HASH_BITS);
 }
 
 void fat_attach(struct inode *inode, loff_t i_pos)
 {
-	struct super_block *sb = inode->i_sb;
-	struct msdos_sb_info *sbi = MSDOS_SB(sb);
+	struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
+	struct hlist_head *head = sbi->inode_hashtable + fat_hash(i_pos);
 
 	spin_lock(&sbi->inode_hash_lock);
 	MSDOS_I(inode)->i_pos = i_pos;
-	hlist_add_head(&MSDOS_I(inode)->i_fat_hash,
-			sbi->inode_hashtable + fat_hash(sb, i_pos));
+	hlist_add_head(&MSDOS_I(inode)->i_fat_hash, head);
 	spin_unlock(&sbi->inode_hash_lock);
 }
-
 EXPORT_SYMBOL_GPL(fat_attach);
 
 void fat_detach(struct inode *inode)
@@ -276,13 +280,12 @@ void fat_detach(struct inode *inode)
 	hlist_del_init(&MSDOS_I(inode)->i_fat_hash);
 	spin_unlock(&sbi->inode_hash_lock);
 }
-
 EXPORT_SYMBOL_GPL(fat_detach);
 
 struct inode *fat_iget(struct super_block *sb, loff_t i_pos)
 {
 	struct msdos_sb_info *sbi = MSDOS_SB(sb);
-	struct hlist_head *head = sbi->inode_hashtable + fat_hash(sb, i_pos);
+	struct hlist_head *head = sbi->inode_hashtable + fat_hash(i_pos);
 	struct hlist_node *_p;
 	struct msdos_inode_info *i;
 	struct inode *inode = NULL;
@@ -341,8 +344,7 @@ static int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de)
 
 	if ((de->attr & ATTR_DIR) && !IS_FREE(de->name)) {
 		inode->i_generation &= ~1;
-		inode->i_mode = MSDOS_MKMODE(de->attr,
-			S_IRWXUGO & ~sbi->options.fs_dmask) | S_IFDIR;
+		inode->i_mode = fat_make_mode(sbi, de->attr, S_IRWXUGO);
 		inode->i_op = sbi->dir_ops;
 		inode->i_fop = &fat_dir_operations;
 
@@ -359,10 +361,9 @@ static int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de)
 		inode->i_nlink = fat_subdirs(inode);
 	} else { /* not a directory */
 		inode->i_generation |= 1;
-		inode->i_mode = MSDOS_MKMODE(de->attr,
-		    ((sbi->options.showexec && !is_exec(de->name + 8))
-			? S_IRUGO|S_IWUGO : S_IRWXUGO)
-		    & ~sbi->options.fs_fmask) | S_IFREG;
+		inode->i_mode = fat_make_mode(sbi, de->attr,
+			((sbi->options.showexec && !is_exec(de->name + 8))
+			 ? S_IRUGO|S_IWUGO : S_IRWXUGO));
 		MSDOS_I(inode)->i_start = le16_to_cpu(de->start);
 		if (sbi->fat_bits == 32)
 			MSDOS_I(inode)->i_start |= (le16_to_cpu(de->starthi) << 16);
@@ -378,25 +379,16 @@ static int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de)
 		if (sbi->options.sys_immutable)
 			inode->i_flags |= S_IMMUTABLE;
 	}
-	MSDOS_I(inode)->i_attrs = de->attr & ATTR_UNUSED;
+	fat_save_attrs(inode, de->attr);
+
 	inode->i_blocks = ((inode->i_size + (sbi->cluster_size - 1))
 			   & ~((loff_t)sbi->cluster_size - 1)) >> 9;
-	inode->i_mtime.tv_sec =
-		date_dos2unix(le16_to_cpu(de->time), le16_to_cpu(de->date),
-			      sbi->options.tz_utc);
-	inode->i_mtime.tv_nsec = 0;
+
+	fat_time_fat2unix(sbi, &inode->i_mtime, de->time, de->date, 0);
 	if (sbi->options.isvfat) {
-		int secs = de->ctime_cs / 100;
-		int csecs = de->ctime_cs % 100;
-		inode->i_ctime.tv_sec  =
-			date_dos2unix(le16_to_cpu(de->ctime),
-				      le16_to_cpu(de->cdate),
-				      sbi->options.tz_utc) + secs;
-		inode->i_ctime.tv_nsec = csecs * 10000000;
-		inode->i_atime.tv_sec =
-			date_dos2unix(0, le16_to_cpu(de->adate),
-				      sbi->options.tz_utc);
-		inode->i_atime.tv_nsec = 0;
+		fat_time_fat2unix(sbi, &inode->i_ctime, de->ctime,
+				  de->cdate, de->ctime_cs);
+		fat_time_fat2unix(sbi, &inode->i_atime, 0, de->adate, 0);
 	} else
 		inode->i_ctime = inode->i_atime = inode->i_mtime;
 
@@ -443,13 +435,8 @@ static void fat_delete_inode(struct inode *inode)
 
 static void fat_clear_inode(struct inode *inode)
 {
-	struct super_block *sb = inode->i_sb;
-	struct msdos_sb_info *sbi = MSDOS_SB(sb);
-
-	spin_lock(&sbi->inode_hash_lock);
 	fat_cache_inval_inode(inode);
-	hlist_del_init(&MSDOS_I(inode)->i_fat_hash);
-	spin_unlock(&sbi->inode_hash_lock);
+	fat_detach(inode);
 }
 
 static void fat_write_super(struct super_block *sb)
@@ -555,6 +542,20 @@ static int fat_statfs(struct dentry *dentry, struct kstatfs *buf)
 	return 0;
 }
 
+static inline loff_t fat_i_pos_read(struct msdos_sb_info *sbi,
+				    struct inode *inode)
+{
+	loff_t i_pos;
+#if BITS_PER_LONG == 32
+	spin_lock(&sbi->inode_hash_lock);
+#endif
+	i_pos = MSDOS_I(inode)->i_pos;
+#if BITS_PER_LONG == 32
+	spin_unlock(&sbi->inode_hash_lock);
+#endif
+	return i_pos;
+}
+
 static int fat_write_inode(struct inode *inode, int wait)
 {
 	struct super_block *sb = inode->i_sb;
@@ -564,9 +565,12 @@ static int fat_write_inode(struct inode *inode, int wait)
 	loff_t i_pos;
 	int err;
 
+	if (inode->i_ino == MSDOS_ROOT_INO)
+		return 0;
+
 retry:
-	i_pos = MSDOS_I(inode)->i_pos;
-	if (inode->i_ino == MSDOS_ROOT_INO || !i_pos)
+	i_pos = fat_i_pos_read(sbi, inode);
+	if (!i_pos)
 		return 0;
 
 	bh = sb_bread(sb, i_pos >> sbi->dir_per_block_bits);
@@ -588,19 +592,17 @@ retry:
 		raw_entry->size = 0;
 	else
 		raw_entry->size = cpu_to_le32(inode->i_size);
-	raw_entry->attr = fat_attr(inode);
+	raw_entry->attr = fat_make_attrs(inode);
 	raw_entry->start = cpu_to_le16(MSDOS_I(inode)->i_logstart);
 	raw_entry->starthi = cpu_to_le16(MSDOS_I(inode)->i_logstart >> 16);
-	fat_date_unix2dos(inode->i_mtime.tv_sec, &raw_entry->time,
-			  &raw_entry->date, sbi->options.tz_utc);
+	fat_time_unix2fat(sbi, &inode->i_mtime, &raw_entry->time,
+			  &raw_entry->date, NULL);
 	if (sbi->options.isvfat) {
 		__le16 atime;
-		fat_date_unix2dos(inode->i_ctime.tv_sec, &raw_entry->ctime,
-				  &raw_entry->cdate, sbi->options.tz_utc);
-		fat_date_unix2dos(inode->i_atime.tv_sec, &atime,
-				  &raw_entry->adate, sbi->options.tz_utc);
-		raw_entry->ctime_cs = (inode->i_ctime.tv_sec & 1) * 100 +
-			inode->i_ctime.tv_nsec / 10000000;
+		fat_time_unix2fat(sbi, &inode->i_ctime, &raw_entry->ctime,
+				  &raw_entry->cdate, &raw_entry->ctime_cs);
+		fat_time_unix2fat(sbi, &inode->i_atime, &atime,
+				  &raw_entry->adate, NULL);
 	}
 	spin_unlock(&sbi->inode_hash_lock);
 	mark_buffer_dirty(bh);
@@ -819,8 +821,10 @@ static int fat_show_options(struct seq_file *m, struct vfsmount *mnt)
 			seq_puts(m, ",uni_xlate");
 		if (!opts->numtail)
 			seq_puts(m, ",nonumtail");
+		if (opts->rodir)
+			seq_puts(m, ",rodir");
 	}
-	if (sbi->options.flush)
+	if (opts->flush)
 		seq_puts(m, ",flush");
 	if (opts->tz_utc)
 		seq_puts(m, ",tz=UTC");
@@ -836,7 +840,7 @@ enum {
 	Opt_charset, Opt_shortname_lower, Opt_shortname_win95,
 	Opt_shortname_winnt, Opt_shortname_mixed, Opt_utf8_no, Opt_utf8_yes,
 	Opt_uni_xl_no, Opt_uni_xl_yes, Opt_nonumtail_no, Opt_nonumtail_yes,
-	Opt_obsolate, Opt_flush, Opt_tz_utc, Opt_err,
+	Opt_obsolate, Opt_flush, Opt_tz_utc, Opt_rodir, Opt_err,
 };
 
 static const match_table_t fat_tokens = {
@@ -908,6 +912,7 @@ static const match_table_t vfat_tokens = {
 	{Opt_nonumtail_yes, "nonumtail=yes"},
 	{Opt_nonumtail_yes, "nonumtail=true"},
 	{Opt_nonumtail_yes, "nonumtail"},
+	{Opt_rodir, "rodir"},
 	{Opt_err, NULL}
 };
 
@@ -927,10 +932,13 @@ static int parse_options(char *options, int is_vfat, int silent, int *debug,
 	opts->allow_utime = -1;
 	opts->codepage = fat_default_codepage;
 	opts->iocharset = fat_default_iocharset;
-	if (is_vfat)
+	if (is_vfat) {
 		opts->shortname = VFAT_SFN_DISPLAY_LOWER|VFAT_SFN_CREATE_WIN95;
-	else
+		opts->rodir = 0;
+	} else {
 		opts->shortname = 0;
+		opts->rodir = 1;
+	}
 	opts->name_check = 'n';
 	opts->quiet = opts->showexec = opts->sys_immutable = opts->dotsOK =  0;
 	opts->utf8 = opts->unicode_xlate = 0;
@@ -1081,6 +1089,9 @@ static int parse_options(char *options, int is_vfat, int silent, int *debug,
 		case Opt_nonumtail_yes:		/* empty or 1 or yes or true */
 			opts->numtail = 0;	/* negated option */
 			break;
+		case Opt_rodir:
+			opts->rodir = 1;
+			break;
 
 		/* obsolete mount options */
 		case Opt_obsolate:
@@ -1126,7 +1137,7 @@ static int fat_read_root(struct inode *inode)
 	inode->i_gid = sbi->options.fs_gid;
 	inode->i_version++;
 	inode->i_generation = 0;
-	inode->i_mode = (S_IRWXUGO & ~sbi->options.fs_dmask) | S_IFDIR;
+	inode->i_mode = fat_make_mode(sbi, ATTR_DIR, S_IRWXUGO);
 	inode->i_op = sbi->dir_ops;
 	inode->i_fop = &fat_dir_operations;
 	if (sbi->fat_bits == 32) {
@@ -1143,7 +1154,7 @@ static int fat_read_root(struct inode *inode)
 	MSDOS_I(inode)->i_logstart = 0;
 	MSDOS_I(inode)->mmu_private = inode->i_size;
 
-	MSDOS_I(inode)->i_attrs = ATTR_NONE;
+	fat_save_attrs(inode, ATTR_DIR);
 	inode->i_mtime.tv_sec = inode->i_atime.tv_sec = inode->i_ctime.tv_sec = 0;
 	inode->i_mtime.tv_nsec = inode->i_atime.tv_nsec = inode->i_ctime.tv_nsec = 0;
 	inode->i_nlink = fat_subdirs(inode)+2;
diff --git a/fs/fat/misc.c b/fs/fat/misc.c
index 79fb98ad36d4..ac39ebcc1496 100644
--- a/fs/fat/misc.c
+++ b/fs/fat/misc.c
@@ -8,8 +8,8 @@
 
 #include <linux/module.h>
 #include <linux/fs.h>
-#include <linux/msdos_fs.h>
 #include <linux/buffer_head.h>
+#include "fat.h"
 
 /*
  * fat_fs_panic reports a severe file system problem and sets the file system
@@ -124,8 +124,9 @@ int fat_chain_add(struct inode *inode, int new_dclus, int nr_cluster)
 			mark_inode_dirty(inode);
 	}
 	if (new_fclus != (inode->i_blocks >> (sbi->cluster_bits - 9))) {
-		fat_fs_panic(sb, "clusters badly computed (%d != %lu)",
-			new_fclus, inode->i_blocks >> (sbi->cluster_bits - 9));
+		fat_fs_panic(sb, "clusters badly computed (%d != %llu)",
+			     new_fclus,
+			     (llu)(inode->i_blocks >> (sbi->cluster_bits - 9)));
 		fat_cache_inval_inode(inode);
 	}
 	inode->i_blocks += nr_cluster << (sbi->cluster_bits - 9);
@@ -135,65 +136,131 @@ int fat_chain_add(struct inode *inode, int new_dclus, int nr_cluster)
 
 extern struct timezone sys_tz;
 
+/*
+ * The epoch of FAT timestamp is 1980.
+ *     :  bits :     value
+ * date:  0 -  4: day	(1 -  31)
+ * date:  5 -  8: month	(1 -  12)
+ * date:  9 - 15: year	(0 - 127) from 1980
+ * time:  0 -  4: sec	(0 -  29) 2sec counts
+ * time:  5 - 10: min	(0 -  59)
+ * time: 11 - 15: hour	(0 -  23)
+ */
+#define SECS_PER_MIN	60
+#define SECS_PER_HOUR	(60 * 60)
+#define SECS_PER_DAY	(SECS_PER_HOUR * 24)
+#define UNIX_SECS_1980	315532800L
+#if BITS_PER_LONG == 64
+#define UNIX_SECS_2108	4354819200L
+#endif
+/* days between 1.1.70 and 1.1.80 (2 leap days) */
+#define DAYS_DELTA	(365 * 10 + 2)
+/* 120 (2100 - 1980) isn't leap year */
+#define YEAR_2100	120
+#define IS_LEAP_YEAR(y)	(!((y) & 3) && (y) != YEAR_2100)
+
 /* Linear day numbers of the respective 1sts in non-leap years. */
-static int day_n[] = {
-   /* Jan  Feb  Mar  Apr   May  Jun  Jul  Aug  Sep  Oct  Nov  Dec */
-	0,  31,  59,  90,  120, 151, 181, 212, 243, 273, 304, 334, 0, 0, 0, 0
+static time_t days_in_year[] = {
+	/* Jan  Feb  Mar  Apr  May  Jun  Jul  Aug  Sep  Oct  Nov  Dec */
+	0,   0,  31,  59,  90, 120, 151, 181, 212, 243, 273, 304, 334, 0, 0, 0,
 };
 
-/* Convert a MS-DOS time/date pair to a UNIX date (seconds since 1 1 70). */
-int date_dos2unix(unsigned short time, unsigned short date, int tz_utc)
+/* Convert a FAT time/date pair to a UNIX date (seconds since 1 1 70). */
+void fat_time_fat2unix(struct msdos_sb_info *sbi, struct timespec *ts,
+		       __le16 __time, __le16 __date, u8 time_cs)
 {
-	int month, year, secs;
+	u16 time = le16_to_cpu(__time), date = le16_to_cpu(__date);
+	time_t second, day, leap_day, month, year;
 
-	/*
-	 * first subtract and mask after that... Otherwise, if
-	 * date == 0, bad things happen
-	 */
-	month = ((date >> 5) - 1) & 15;
-	year = date >> 9;
-	secs = (time & 31)*2+60*((time >> 5) & 63)+(time >> 11)*3600+86400*
-	    ((date & 31)-1+day_n[month]+(year/4)+year*365-((year & 3) == 0 &&
-	    month < 2 ? 1 : 0)+3653);
-			/* days since 1.1.70 plus 80's leap day */
-	if (!tz_utc)
-		secs += sys_tz.tz_minuteswest*60;
-	return secs;
+	year  = date >> 9;
+	month = max(1, (date >> 5) & 0xf);
+	day   = max(1, date & 0x1f) - 1;
+
+	leap_day = (year + 3) / 4;
+	if (year > YEAR_2100)		/* 2100 isn't leap year */
+		leap_day--;
+	if (IS_LEAP_YEAR(year) && month > 2)
+		leap_day++;
+
+	second =  (time & 0x1f) << 1;
+	second += ((time >> 5) & 0x3f) * SECS_PER_MIN;
+	second += (time >> 11) * SECS_PER_HOUR;
+	second += (year * 365 + leap_day
+		   + days_in_year[month] + day
+		   + DAYS_DELTA) * SECS_PER_DAY;
+
+	if (!sbi->options.tz_utc)
+		second += sys_tz.tz_minuteswest * SECS_PER_MIN;
+
+	if (time_cs) {
+		ts->tv_sec = second + (time_cs / 100);
+		ts->tv_nsec = (time_cs % 100) * 10000000;
+	} else {
+		ts->tv_sec = second;
+		ts->tv_nsec = 0;
+	}
 }
 
-/* Convert linear UNIX date to a MS-DOS time/date pair. */
-void fat_date_unix2dos(int unix_date, __le16 *time, __le16 *date, int tz_utc)
+/* Convert linear UNIX date to a FAT time/date pair. */
+void fat_time_unix2fat(struct msdos_sb_info *sbi, struct timespec *ts,
+		       __le16 *time, __le16 *date, u8 *time_cs)
 {
-	int day, year, nl_day, month;
+	time_t second = ts->tv_sec;
+	time_t day, leap_day, month, year;
 
-	if (!tz_utc)
-		unix_date -= sys_tz.tz_minuteswest*60;
+	if (!sbi->options.tz_utc)
+		second -= sys_tz.tz_minuteswest * SECS_PER_MIN;
 
 	/* Jan 1 GMT 00:00:00 1980. But what about another time zone? */
-	if (unix_date < 315532800)
-		unix_date = 315532800;
-
-	*time = cpu_to_le16((unix_date % 60)/2+(((unix_date/60) % 60) << 5)+
-	    (((unix_date/3600) % 24) << 11));
-	day = unix_date/86400-3652;
-	year = day/365;
-	if ((year+3)/4+365*year > day)
+	if (second < UNIX_SECS_1980) {
+		*time = 0;
+		*date = cpu_to_le16((0 << 9) | (1 << 5) | 1);
+		if (time_cs)
+			*time_cs = 0;
+		return;
+	}
+#if BITS_PER_LONG == 64
+	if (second >= UNIX_SECS_2108) {
+		*time = cpu_to_le16((23 << 11) | (59 << 5) | 29);
+		*date = cpu_to_le16((127 << 9) | (12 << 5) | 31);
+		if (time_cs)
+			*time_cs = 199;
+		return;
+	}
+#endif
+
+	day = second / SECS_PER_DAY - DAYS_DELTA;
+	year = day / 365;
+	leap_day = (year + 3) / 4;
+	if (year > YEAR_2100)		/* 2100 isn't leap year */
+		leap_day--;
+	if (year * 365 + leap_day > day)
 		year--;
-	day -= (year+3)/4+365*year;
-	if (day == 59 && !(year & 3)) {
-		nl_day = day;
+	leap_day = (year + 3) / 4;
+	if (year > YEAR_2100)		/* 2100 isn't leap year */
+		leap_day--;
+	day -= year * 365 + leap_day;
+
+	if (IS_LEAP_YEAR(year) && day == days_in_year[3]) {
 		month = 2;
 	} else {
-		nl_day = (year & 3) || day <= 59 ? day : day-1;
-		for (month = 0; month < 12; month++) {
-			if (day_n[month] > nl_day)
+		if (IS_LEAP_YEAR(year) && day > days_in_year[3])
+			day--;
+		for (month = 1; month < 12; month++) {
+			if (days_in_year[month + 1] > day)
 				break;
 		}
 	}
-	*date = cpu_to_le16(nl_day-day_n[month-1]+1+(month << 5)+(year << 9));
-}
+	day -= days_in_year[month];
 
-EXPORT_SYMBOL_GPL(fat_date_unix2dos);
+	*time = cpu_to_le16(((second / SECS_PER_HOUR) % 24) << 11
+			    | ((second / SECS_PER_MIN) % 60) << 5
+			    | (second % SECS_PER_MIN) >> 1);
+	*date = cpu_to_le16((year << 9) | (month << 5) | (day + 1));
+	if (time_cs)
+		*time_cs = (ts->tv_sec & 1) * 100 + ts->tv_nsec / 10000000;
+}
+EXPORT_SYMBOL_GPL(fat_time_unix2fat);
 
 int fat_sync_bhs(struct buffer_head **bhs, int nr_bhs)
 {
diff --git a/fs/msdos/namei.c b/fs/fat/namei_msdos.c
index e844b9809d27..7ba03a4acbe0 100644
--- a/fs/msdos/namei.c
+++ b/fs/fat/namei_msdos.c
@@ -9,8 +9,8 @@
 #include <linux/module.h>
 #include <linux/time.h>
 #include <linux/buffer_head.h>
-#include <linux/msdos_fs.h>
 #include <linux/smp_lock.h>
+#include "fat.h"
 
 /* Characters that are undesirable in an MS-DOS file name */
 static unsigned char bad_chars[] = "*?<>|\"";
@@ -203,33 +203,37 @@ static struct dentry *msdos_lookup(struct inode *dir, struct dentry *dentry,
 {
 	struct super_block *sb = dir->i_sb;
 	struct fat_slot_info sinfo;
-	struct inode *inode = NULL;
-	int res;
-
-	dentry->d_op = &msdos_dentry_operations;
+	struct inode *inode;
+	int err;
 
 	lock_super(sb);
-	res = msdos_find(dir, dentry->d_name.name, dentry->d_name.len, &sinfo);
-	if (res == -ENOENT)
-		goto add;
-	if (res < 0)
-		goto out;
+
+	err = msdos_find(dir, dentry->d_name.name, dentry->d_name.len, &sinfo);
+	if (err) {
+		if (err == -ENOENT) {
+			inode = NULL;
+			goto out;
+		}
+		goto error;
+	}
+
 	inode = fat_build_inode(sb, sinfo.de, sinfo.i_pos);
 	brelse(sinfo.bh);
 	if (IS_ERR(inode)) {
-		res = PTR_ERR(inode);
-		goto out;
+		err = PTR_ERR(inode);
+		goto error;
 	}
-add:
-	res = 0;
+out:
+	unlock_super(sb);
+	dentry->d_op = &msdos_dentry_operations;
 	dentry = d_splice_alias(inode, dentry);
 	if (dentry)
 		dentry->d_op = &msdos_dentry_operations;
-out:
+	return dentry;
+
+error:
 	unlock_super(sb);
-	if (!res)
-		return dentry;
-	return ERR_PTR(res);
+	return ERR_PTR(err);
 }
 
 /***** Creates a directory entry (name is already formatted). */
@@ -247,7 +251,7 @@ static int msdos_add_entry(struct inode *dir, const unsigned char *name,
 	if (is_hid)
 		de.attr |= ATTR_HIDDEN;
 	de.lcase = 0;
-	fat_date_unix2dos(ts->tv_sec, &time, &date, sbi->options.tz_utc);
+	fat_time_unix2fat(sbi, ts, &time, &date, NULL);
 	de.cdate = de.adate = 0;
 	de.ctime = 0;
 	de.ctime_cs = 0;
diff --git a/fs/vfat/namei.c b/fs/fat/namei_vfat.c
index 155c10b4adbd..bf326d4356a3 100644
--- a/fs/vfat/namei.c
+++ b/fs/fat/namei_vfat.c
@@ -16,36 +16,75 @@
  */
 
 #include <linux/module.h>
-
 #include <linux/jiffies.h>
-#include <linux/msdos_fs.h>
 #include <linux/ctype.h>
 #include <linux/slab.h>
 #include <linux/smp_lock.h>
 #include <linux/buffer_head.h>
 #include <linux/namei.h>
+#include "fat.h"
 
-static int vfat_revalidate(struct dentry *dentry, struct nameidata *nd)
+/*
+ * If new entry was created in the parent, it could create the 8.3
+ * alias (the shortname of logname).  So, the parent may have the
+ * negative-dentry which matches the created 8.3 alias.
+ *
+ * If it happened, the negative dentry isn't actually negative
+ * anymore.  So, drop it.
+ */
+static int vfat_revalidate_shortname(struct dentry *dentry)
 {
 	int ret = 1;
-
-	if (!dentry->d_inode &&
-	    nd && !(nd->flags & LOOKUP_CONTINUE) && (nd->flags & LOOKUP_CREATE))
-		/*
-		 * negative dentry is dropped, in order to make sure
-		 * to use the name which a user desires if this is
-		 * create path.
-		 */
+	spin_lock(&dentry->d_lock);
+	if (dentry->d_time != dentry->d_parent->d_inode->i_version)
 		ret = 0;
-	else {
-		spin_lock(&dentry->d_lock);
-		if (dentry->d_time != dentry->d_parent->d_inode->i_version)
-			ret = 0;
-		spin_unlock(&dentry->d_lock);
-	}
+	spin_unlock(&dentry->d_lock);
 	return ret;
 }
 
+static int vfat_revalidate(struct dentry *dentry, struct nameidata *nd)
+{
+	/* This is not negative dentry. Always valid. */
+	if (dentry->d_inode)
+		return 1;
+	return vfat_revalidate_shortname(dentry);
+}
+
+static int vfat_revalidate_ci(struct dentry *dentry, struct nameidata *nd)
+{
+	/*
+	 * This is not negative dentry. Always valid.
+	 *
+	 * Note, rename() to existing directory entry will have ->d_inode,
+	 * and will use existing name which isn't specified name by user.
+	 *
+	 * We may be able to drop this positive dentry here. But dropping
+	 * positive dentry isn't good idea. So it's unsupported like
+	 * rename("filename", "FILENAME") for now.
+	 */
+	if (dentry->d_inode)
+		return 1;
+
+	/*
+	 * This may be nfsd (or something), anyway, we can't see the
+	 * intent of this. So, since this can be for creation, drop it.
+	 */
+	if (!nd)
+		return 0;
+
+	/*
+	 * Drop the negative dentry, in order to make sure to use the
+	 * case sensitive name which is specified by user if this is
+	 * for creation.
+	 */
+	if (!(nd->flags & (LOOKUP_CONTINUE | LOOKUP_PARENT))) {
+		if (nd->flags & LOOKUP_CREATE)
+			return 0;
+	}
+
+	return vfat_revalidate_shortname(dentry);
+}
+
 /* returns the length of a struct qstr, ignoring trailing dots */
 static unsigned int vfat_striptail_len(struct qstr *qstr)
 {
@@ -127,25 +166,16 @@ static int vfat_cmp(struct dentry *dentry, struct qstr *a, struct qstr *b)
 	return 1;
 }
 
-static struct dentry_operations vfat_dentry_ops[4] = {
-	{
-		.d_hash		= vfat_hashi,
-		.d_compare	= vfat_cmpi,
-	},
-	{
-		.d_revalidate	= vfat_revalidate,
-		.d_hash		= vfat_hashi,
-		.d_compare	= vfat_cmpi,
-	},
-	{
-		.d_hash		= vfat_hash,
-		.d_compare	= vfat_cmp,
-	},
-	{
-		.d_revalidate	= vfat_revalidate,
-		.d_hash		= vfat_hash,
-		.d_compare	= vfat_cmp,
-	}
+static struct dentry_operations vfat_ci_dentry_ops = {
+	.d_revalidate	= vfat_revalidate_ci,
+	.d_hash		= vfat_hashi,
+	.d_compare	= vfat_cmpi,
+};
+
+static struct dentry_operations vfat_dentry_ops = {
+	.d_revalidate	= vfat_revalidate,
+	.d_hash		= vfat_hash,
+	.d_compare	= vfat_cmp,
 };
 
 /* Characters that are undesirable in an MS-DOS file name */
@@ -569,6 +599,7 @@ static int vfat_build_slots(struct inode *dir, const unsigned char *name,
 	unsigned char msdos_name[MSDOS_NAME];
 	wchar_t *uname;
 	__le16 time, date;
+	u8 time_cs;
 	int err, ulen, usize, i;
 	loff_t offset;
 
@@ -621,10 +652,10 @@ shortname:
 	memcpy(de->name, msdos_name, MSDOS_NAME);
 	de->attr = is_dir ? ATTR_DIR : ATTR_ARCH;
 	de->lcase = lcase;
-	fat_date_unix2dos(ts->tv_sec, &time, &date, sbi->options.tz_utc);
+	fat_time_unix2fat(sbi, ts, &time, &date, &time_cs);
 	de->time = de->ctime = time;
 	de->date = de->cdate = de->adate = date;
-	de->ctime_cs = 0;
+	de->ctime_cs = time_cs;
 	de->start = cpu_to_le16(cluster);
 	de->starthi = cpu_to_le16(cluster >> 16);
 	de->size = 0;
@@ -683,46 +714,58 @@ static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry,
 {
 	struct super_block *sb = dir->i_sb;
 	struct fat_slot_info sinfo;
-	struct inode *inode = NULL;
+	struct inode *inode;
 	struct dentry *alias;
-	int err, table;
+	int err;
 
 	lock_super(sb);
-	table = (MSDOS_SB(sb)->options.name_check == 's') ? 2 : 0;
-	dentry->d_op = &vfat_dentry_ops[table];
 
 	err = vfat_find(dir, &dentry->d_name, &sinfo);
 	if (err) {
-		table++;
+		if (err == -ENOENT) {
+			inode = NULL;
+			goto out;
+		}
 		goto error;
 	}
+
 	inode = fat_build_inode(sb, sinfo.de, sinfo.i_pos);
 	brelse(sinfo.bh);
 	if (IS_ERR(inode)) {
-		unlock_super(sb);
-		return ERR_CAST(inode);
+		err = PTR_ERR(inode);
+		goto error;
 	}
-	alias = d_find_alias(inode);
-	if (alias) {
-		if (d_invalidate(alias) == 0)
-			dput(alias);
-		else {
-			iput(inode);
-			unlock_super(sb);
-			return alias;
-		}
 
+	alias = d_find_alias(inode);
+	if (alias && !(alias->d_flags & DCACHE_DISCONNECTED)) {
+		/*
+		 * This inode has non DCACHE_DISCONNECTED dentry. This
+		 * means, the user did ->lookup() by an another name
+		 * (longname vs 8.3 alias of it) in past.
+		 *
+		 * Switch to new one for reason of locality if possible.
+		 */
+		BUG_ON(d_unhashed(alias));
+		if (!S_ISDIR(inode->i_mode))
+			d_move(alias, dentry);
+		iput(inode);
+		unlock_super(sb);
+		return alias;
 	}
-error:
+out:
 	unlock_super(sb);
-	dentry->d_op = &vfat_dentry_ops[table];
+	dentry->d_op = sb->s_root->d_op;
 	dentry->d_time = dentry->d_parent->d_inode->i_version;
 	dentry = d_splice_alias(inode, dentry);
 	if (dentry) {
-		dentry->d_op = &vfat_dentry_ops[table];
+		dentry->d_op = sb->s_root->d_op;
 		dentry->d_time = dentry->d_parent->d_inode->i_version;
 	}
 	return dentry;
+
+error:
+	unlock_super(sb);
+	return ERR_PTR(err);
 }
 
 static int vfat_create(struct inode *dir, struct dentry *dentry, int mode,
@@ -1014,9 +1057,9 @@ static int vfat_fill_super(struct super_block *sb, void *data, int silent)
 		return res;
 
 	if (MSDOS_SB(sb)->options.name_check != 's')
-		sb->s_root->d_op = &vfat_dentry_ops[0];
+		sb->s_root->d_op = &vfat_ci_dentry_ops;
 	else
-		sb->s_root->d_op = &vfat_dentry_ops[2];
+		sb->s_root->d_op = &vfat_dentry_ops;
 
 	return 0;
 }
diff --git a/fs/hostfs/hostfs.h b/fs/hostfs/hostfs.h
index 6ae9011b95eb..2f34f8f2134b 100644
--- a/fs/hostfs/hostfs.h
+++ b/fs/hostfs/hostfs.h
@@ -81,7 +81,7 @@ extern int do_rmdir(const char *file);
 extern int do_mknod(const char *file, int mode, unsigned int major,
 		    unsigned int minor);
 extern int link_file(const char *from, const char *to);
-extern int do_readlink(char *file, char *buf, int size);
+extern int hostfs_do_readlink(char *file, char *buf, int size);
 extern int rename_file(char *from, char *to);
 extern int do_statfs(char *root, long *bsize_out, long long *blocks_out,
 		     long long *bfree_out, long long *bavail_out,
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 7f34f4385de0..3a31451ac170 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -168,7 +168,7 @@ static char *follow_link(char *link)
 		if (name == NULL)
 			goto out;
 
-		n = do_readlink(link, name, len);
+		n = hostfs_do_readlink(link, name, len);
 		if (n < len)
 			break;
 		len *= 2;
@@ -943,7 +943,7 @@ int hostfs_link_readpage(struct file *file, struct page *page)
 	name = inode_name(page->mapping->host, 0);
 	if (name == NULL)
 		return -ENOMEM;
-	err = do_readlink(name, buffer, PAGE_CACHE_SIZE);
+	err = hostfs_do_readlink(name, buffer, PAGE_CACHE_SIZE);
 	kfree(name);
 	if (err == PAGE_CACHE_SIZE)
 		err = -E2BIG;
diff --git a/fs/hostfs/hostfs_user.c b/fs/hostfs/hostfs_user.c
index 53fd0a67c11a..b79424f93282 100644
--- a/fs/hostfs/hostfs_user.c
+++ b/fs/hostfs/hostfs_user.c
@@ -377,7 +377,7 @@ int link_file(const char *to, const char *from)
 	return 0;
 }
 
-int do_readlink(char *file, char *buf, int size)
+int hostfs_do_readlink(char *file, char *buf, int size)
 {
 	int n;
 
diff --git a/fs/inotify.c b/fs/inotify.c
index 690e72595e6e..7bbed1b89825 100644
--- a/fs/inotify.c
+++ b/fs/inotify.c
@@ -106,6 +106,20 @@ void get_inotify_watch(struct inotify_watch *watch)
 }
 EXPORT_SYMBOL_GPL(get_inotify_watch);
 
+int pin_inotify_watch(struct inotify_watch *watch)
+{
+	struct super_block *sb = watch->inode->i_sb;
+	spin_lock(&sb_lock);
+	if (sb->s_count >= S_BIAS) {
+		atomic_inc(&sb->s_active);
+		spin_unlock(&sb_lock);
+		atomic_inc(&watch->count);
+		return 1;
+	}
+	spin_unlock(&sb_lock);
+	return 0;
+}
+
 /**
  * put_inotify_watch - decrements the ref count on a given watch.  cleans up
  * watch references if the count reaches zero.  inotify_watch is freed by
@@ -124,6 +138,13 @@ void put_inotify_watch(struct inotify_watch *watch)
 }
 EXPORT_SYMBOL_GPL(put_inotify_watch);
 
+void unpin_inotify_watch(struct inotify_watch *watch)
+{
+	struct super_block *sb = watch->inode->i_sb;
+	put_inotify_watch(watch);
+	deactivate_super(sb);
+}
+
 /*
  * inotify_handle_get_wd - returns the next WD for use by the given handle
  *
@@ -479,6 +500,112 @@ void inotify_init_watch(struct inotify_watch *watch)
 }
 EXPORT_SYMBOL_GPL(inotify_init_watch);
 
+/*
+ * Watch removals suck violently.  To kick the watch out we need (in this
+ * order) inode->inotify_mutex and ih->mutex.  That's fine if we have
+ * a hold on inode; however, for all other cases we need to make damn sure
+ * we don't race with umount.  We can *NOT* just grab a reference to a
+ * watch - inotify_unmount_inodes() will happily sail past it and we'll end
+ * with reference to inode potentially outliving its superblock.  Ideally
+ * we just want to grab an active reference to superblock if we can; that
+ * will make sure we won't go into inotify_umount_inodes() until we are
+ * done.  Cleanup is just deactivate_super().  However, that leaves a messy
+ * case - what if we *are* racing with umount() and active references to
+ * superblock can't be acquired anymore?  We can bump ->s_count, grab
+ * ->s_umount, which will almost certainly wait until the superblock is shut
+ * down and the watch in question is pining for fjords.  That's fine, but
+ * there is a problem - we might have hit the window between ->s_active
+ * getting to 0 / ->s_count - below S_BIAS (i.e. the moment when superblock
+ * is past the point of no return and is heading for shutdown) and the
+ * moment when deactivate_super() acquires ->s_umount.  We could just do
+ * drop_super() yield() and retry, but that's rather antisocial and this
+ * stuff is luser-triggerable.  OTOH, having grabbed ->s_umount and having
+ * found that we'd got there first (i.e. that ->s_root is non-NULL) we know
+ * that we won't race with inotify_umount_inodes().  So we could grab a
+ * reference to watch and do the rest as above, just with drop_super() instead
+ * of deactivate_super(), right?  Wrong.  We had to drop ih->mutex before we
+ * could grab ->s_umount.  So the watch could've been gone already.
+ *
+ * That still can be dealt with - we need to save watch->wd, do idr_find()
+ * and compare its result with our pointer.  If they match, we either have
+ * the damn thing still alive or we'd lost not one but two races at once,
+ * the watch had been killed and a new one got created with the same ->wd
+ * at the same address.  That couldn't have happened in inotify_destroy(),
+ * but inotify_rm_wd() could run into that.  Still, "new one got created"
+ * is not a problem - we have every right to kill it or leave it alone,
+ * whatever's more convenient.
+ *
+ * So we can use idr_find(...) == watch && watch->inode->i_sb == sb as
+ * "grab it and kill it" check.  If it's been our original watch, we are
+ * fine, if it's a newcomer - nevermind, just pretend that we'd won the
+ * race and kill the fscker anyway; we are safe since we know that its
+ * superblock won't be going away.
+ *
+ * And yes, this is far beyond mere "not very pretty"; so's the entire
+ * concept of inotify to start with.
+ */
+
+/**
+ * pin_to_kill - pin the watch down for removal
+ * @ih: inotify handle
+ * @watch: watch to kill
+ *
+ * Called with ih->mutex held, drops it.  Possible return values:
+ * 0 - nothing to do, it has died
+ * 1 - remove it, drop the reference and deactivate_super()
+ * 2 - remove it, drop the reference and drop_super(); we tried hard to avoid
+ * that variant, since it involved a lot of PITA, but that's the best that
+ * could've been done.
+ */
+static int pin_to_kill(struct inotify_handle *ih, struct inotify_watch *watch)
+{
+	struct super_block *sb = watch->inode->i_sb;
+	s32 wd = watch->wd;
+
+	spin_lock(&sb_lock);
+	if (sb->s_count >= S_BIAS) {
+		atomic_inc(&sb->s_active);
+		spin_unlock(&sb_lock);
+		get_inotify_watch(watch);
+		mutex_unlock(&ih->mutex);
+		return 1;	/* the best outcome */
+	}
+	sb->s_count++;
+	spin_unlock(&sb_lock);
+	mutex_unlock(&ih->mutex); /* can't grab ->s_umount under it */
+	down_read(&sb->s_umount);
+	if (likely(!sb->s_root)) {
+		/* fs is already shut down; the watch is dead */
+		drop_super(sb);
+		return 0;
+	}
+	/* raced with the final deactivate_super() */
+	mutex_lock(&ih->mutex);
+	if (idr_find(&ih->idr, wd) != watch || watch->inode->i_sb != sb) {
+		/* the watch is dead */
+		mutex_unlock(&ih->mutex);
+		drop_super(sb);
+		return 0;
+	}
+	/* still alive or freed and reused with the same sb and wd; kill */
+	get_inotify_watch(watch);
+	mutex_unlock(&ih->mutex);
+	return 2;
+}
+
+static void unpin_and_kill(struct inotify_watch *watch, int how)
+{
+	struct super_block *sb = watch->inode->i_sb;
+	put_inotify_watch(watch);
+	switch (how) {
+	case 1:
+		deactivate_super(sb);
+		break;
+	case 2:
+		drop_super(sb);
+	}
+}
+
 /**
  * inotify_destroy - clean up and destroy an inotify instance
  * @ih: inotify handle
@@ -490,11 +617,15 @@ void inotify_destroy(struct inotify_handle *ih)
 	 * pretty.  We cannot do a simple iteration over the list, because we
 	 * do not know the inode until we iterate to the watch.  But we need to
 	 * hold inode->inotify_mutex before ih->mutex.  The following works.
+	 *
+	 * AV: it had to become even uglier to start working ;-/
 	 */
 	while (1) {
 		struct inotify_watch *watch;
 		struct list_head *watches;
+		struct super_block *sb;
 		struct inode *inode;
+		int how;
 
 		mutex_lock(&ih->mutex);
 		watches = &ih->watches;
@@ -503,8 +634,10 @@ void inotify_destroy(struct inotify_handle *ih)
 			break;
 		}
 		watch = list_first_entry(watches, struct inotify_watch, h_list);
-		get_inotify_watch(watch);
-		mutex_unlock(&ih->mutex);
+		sb = watch->inode->i_sb;
+		how = pin_to_kill(ih, watch);
+		if (!how)
+			continue;
 
 		inode = watch->inode;
 		mutex_lock(&inode->inotify_mutex);
@@ -518,7 +651,7 @@ void inotify_destroy(struct inotify_handle *ih)
 
 		mutex_unlock(&ih->mutex);
 		mutex_unlock(&inode->inotify_mutex);
-		put_inotify_watch(watch);
+		unpin_and_kill(watch, how);
 	}
 
 	/* free this handle: the put matching the get in inotify_init() */
@@ -719,7 +852,9 @@ void inotify_evict_watch(struct inotify_watch *watch)
 int inotify_rm_wd(struct inotify_handle *ih, u32 wd)
 {
 	struct inotify_watch *watch;
+	struct super_block *sb;
 	struct inode *inode;
+	int how;
 
 	mutex_lock(&ih->mutex);
 	watch = idr_find(&ih->idr, wd);
@@ -727,9 +862,12 @@ int inotify_rm_wd(struct inotify_handle *ih, u32 wd)
 		mutex_unlock(&ih->mutex);
 		return -EINVAL;
 	}
-	get_inotify_watch(watch);
+	sb = watch->inode->i_sb;
+	how = pin_to_kill(ih, watch);
+	if (!how)
+		return 0;
+
 	inode = watch->inode;
-	mutex_unlock(&ih->mutex);
 
 	mutex_lock(&inode->inotify_mutex);
 	mutex_lock(&ih->mutex);
@@ -740,7 +878,7 @@ int inotify_rm_wd(struct inotify_handle *ih, u32 wd)
 
 	mutex_unlock(&ih->mutex);
 	mutex_unlock(&inode->inotify_mutex);
-	put_inotify_watch(watch);
+	unpin_and_kill(watch, how);
 
 	return 0;
 }
diff --git a/fs/jbd/checkpoint.c b/fs/jbd/checkpoint.c
index 1bd8d4acc6f2..61f32f3868cd 100644
--- a/fs/jbd/checkpoint.c
+++ b/fs/jbd/checkpoint.c
@@ -115,7 +115,7 @@ static int __try_to_free_cp_buf(struct journal_head *jh)
  */
 void __log_wait_for_space(journal_t *journal)
 {
-	int nblocks;
+	int nblocks, space_left;
 	assert_spin_locked(&journal->j_state_lock);
 
 	nblocks = jbd_space_needed(journal);
@@ -128,25 +128,42 @@ void __log_wait_for_space(journal_t *journal)
 		/*
 		 * Test again, another process may have checkpointed while we
 		 * were waiting for the checkpoint lock. If there are no
-		 * outstanding transactions there is nothing to checkpoint and
-		 * we can't make progress. Abort the journal in this case.
+		 * transactions ready to be checkpointed, try to recover
+		 * journal space by calling cleanup_journal_tail(), and if
+		 * that doesn't work, by waiting for the currently committing
+		 * transaction to complete.  If there is absolutely no way
+		 * to make progress, this is either a BUG or corrupted
+		 * filesystem, so abort the journal and leave a stack
+		 * trace for forensic evidence.
 		 */
 		spin_lock(&journal->j_state_lock);
 		spin_lock(&journal->j_list_lock);
 		nblocks = jbd_space_needed(journal);
-		if (__log_space_left(journal) < nblocks) {
+		space_left = __log_space_left(journal);
+		if (space_left < nblocks) {
 			int chkpt = journal->j_checkpoint_transactions != NULL;
+			tid_t tid = 0;
 
+			if (journal->j_committing_transaction)
+				tid = journal->j_committing_transaction->t_tid;
 			spin_unlock(&journal->j_list_lock);
 			spin_unlock(&journal->j_state_lock);
 			if (chkpt) {
 				log_do_checkpoint(journal);
+			} else if (cleanup_journal_tail(journal) == 0) {
+				/* We were able to recover space; yay! */
+				;
+			} else if (tid) {
+				log_wait_commit(journal, tid);
 			} else {
-				printk(KERN_ERR "%s: no transactions\n",
-				       __func__);
+				printk(KERN_ERR "%s: needed %d blocks and "
+				       "only had %d space available\n",
+				       __func__, nblocks, space_left);
+				printk(KERN_ERR "%s: no way to get more "
+				       "journal space\n", __func__);
+				WARN_ON(1);
 				journal_abort(journal, 0);
 			}
-
 			spin_lock(&journal->j_state_lock);
 		} else {
 			spin_unlock(&journal->j_list_lock);
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 9203c3332f17..9497718fe920 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -116,7 +116,7 @@ static int __try_to_free_cp_buf(struct journal_head *jh)
  */
 void __jbd2_log_wait_for_space(journal_t *journal)
 {
-	int nblocks;
+	int nblocks, space_left;
 	assert_spin_locked(&journal->j_state_lock);
 
 	nblocks = jbd_space_needed(journal);
@@ -129,25 +129,43 @@ void __jbd2_log_wait_for_space(journal_t *journal)
 		/*
 		 * Test again, another process may have checkpointed while we
 		 * were waiting for the checkpoint lock. If there are no
-		 * outstanding transactions there is nothing to checkpoint and
-		 * we can't make progress. Abort the journal in this case.
+		 * transactions ready to be checkpointed, try to recover
+		 * journal space by calling cleanup_journal_tail(), and if
+		 * that doesn't work, by waiting for the currently committing
+		 * transaction to complete.  If there is absolutely no way
+		 * to make progress, this is either a BUG or corrupted
+		 * filesystem, so abort the journal and leave a stack
+		 * trace for forensic evidence.
 		 */
 		spin_lock(&journal->j_state_lock);
 		spin_lock(&journal->j_list_lock);
 		nblocks = jbd_space_needed(journal);
-		if (__jbd2_log_space_left(journal) < nblocks) {
+		space_left = __jbd2_log_space_left(journal);
+		if (space_left < nblocks) {
 			int chkpt = journal->j_checkpoint_transactions != NULL;
+			tid_t tid = 0;
 
+			if (journal->j_committing_transaction)
+				tid = journal->j_committing_transaction->t_tid;
 			spin_unlock(&journal->j_list_lock);
 			spin_unlock(&journal->j_state_lock);
 			if (chkpt) {
 				jbd2_log_do_checkpoint(journal);
+			} else if (jbd2_cleanup_journal_tail(journal) == 0) {
+				/* We were able to recover space; yay! */
+				;
+			} else if (tid) {
+				jbd2_log_wait_commit(journal, tid);
 			} else {
-				printk(KERN_ERR "%s: no transactions\n",
-				       __func__);
+				printk(KERN_ERR "%s: needed %d blocks and "
+				       "only had %d space available\n",
+				       __func__, nblocks, space_left);
+				printk(KERN_ERR "%s: no way to get more "
+				       "journal space in %s\n", __func__,
+				       journal->j_devname);
+				WARN_ON(1);
 				jbd2_journal_abort(journal, 0);
 			}
-
 			spin_lock(&journal->j_state_lock);
 		} else {
 			spin_unlock(&journal->j_list_lock);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 783de118de92..e70d657a19f8 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1089,6 +1089,7 @@ journal_t * jbd2_journal_init_inode (struct inode *inode)
 	if (!journal->j_wbuf) {
 		printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n",
 			__func__);
+		jbd2_stats_proc_exit(journal);
 		kfree(journal);
 		return NULL;
 	}
@@ -1098,6 +1099,7 @@ journal_t * jbd2_journal_init_inode (struct inode *inode)
 	if (err) {
 		printk(KERN_ERR "%s: Cannnot locate journal superblock\n",
 		       __func__);
+		jbd2_stats_proc_exit(journal);
 		kfree(journal);
 		return NULL;
 	}
diff --git a/fs/jffs2/background.c b/fs/jffs2/background.c
index 8adebd3e43c6..3cceef4ad2b7 100644
--- a/fs/jffs2/background.c
+++ b/fs/jffs2/background.c
@@ -85,15 +85,15 @@ static int jffs2_garbage_collect_thread(void *_c)
 	for (;;) {
 		allow_signal(SIGHUP);
 	again:
+		spin_lock(&c->erase_completion_lock);
 		if (!jffs2_thread_should_wake(c)) {
 			set_current_state (TASK_INTERRUPTIBLE);
+			spin_unlock(&c->erase_completion_lock);
 			D1(printk(KERN_DEBUG "jffs2_garbage_collect_thread sleeping...\n"));
-			/* Yes, there's a race here; we checked jffs2_thread_should_wake()
-			   before setting current->state to TASK_INTERRUPTIBLE. But it doesn't
-			   matter - We don't care if we miss a wakeup, because the GC thread
-			   is only an optimisation anyway. */
 			schedule();
-		}
+		} else
+			spin_unlock(&c->erase_completion_lock);
+			
 
 		/* This thread is purely an optimisation. But if it runs when
 		   other things could be running, it actually makes things a
diff --git a/fs/jffs2/compr_lzo.c b/fs/jffs2/compr_lzo.c
index 47b045797e42..90cb60d09787 100644
--- a/fs/jffs2/compr_lzo.c
+++ b/fs/jffs2/compr_lzo.c
@@ -19,7 +19,7 @@
 
 static void *lzo_mem;
 static void *lzo_compress_buf;
-static DEFINE_MUTEX(deflate_mutex);
+static DEFINE_MUTEX(deflate_mutex);	/* for lzo_mem and lzo_compress_buf */
 
 static void free_workspace(void)
 {
@@ -49,18 +49,21 @@ static int jffs2_lzo_compress(unsigned char *data_in, unsigned char *cpage_out,
 
 	mutex_lock(&deflate_mutex);
 	ret = lzo1x_1_compress(data_in, *sourcelen, lzo_compress_buf, &compress_size, lzo_mem);
-	mutex_unlock(&deflate_mutex);
-
 	if (ret != LZO_E_OK)
-		return -1;
+		goto fail;
 
 	if (compress_size > *dstlen)
-		return -1;
+		goto fail;
 
 	memcpy(cpage_out, lzo_compress_buf, compress_size);
-	*dstlen = compress_size;
+	mutex_unlock(&deflate_mutex);
 
+	*dstlen = compress_size;
 	return 0;
+
+ fail:
+	mutex_unlock(&deflate_mutex);
+	return -1;
 }
 
 static int jffs2_lzo_decompress(unsigned char *data_in, unsigned char *cpage_out,
diff --git a/fs/jffs2/nodemgmt.c b/fs/jffs2/nodemgmt.c
index 0875b60b4bf7..21a052915aa9 100644
--- a/fs/jffs2/nodemgmt.c
+++ b/fs/jffs2/nodemgmt.c
@@ -261,9 +261,11 @@ static int jffs2_find_nextblock(struct jffs2_sb_info *c)
 
 	jffs2_sum_reset_collected(c->summary); /* reset collected summary */
 
+#ifdef CONFIG_JFFS2_FS_WRITEBUFFER
 	/* adjust write buffer offset, else we get a non contiguous write bug */
 	if (!(c->wbuf_ofs % c->sector_size) && !c->wbuf_len)
 		c->wbuf_ofs = 0xffffffff;
+#endif
 
 	D1(printk(KERN_DEBUG "jffs2_find_nextblock(): new nextblock = 0x%08x\n", c->nextblock->offset));
 
diff --git a/fs/msdos/Makefile b/fs/msdos/Makefile
deleted file mode 100644
index ea67646fcb95..000000000000
--- a/fs/msdos/Makefile
+++ /dev/null
@@ -1,7 +0,0 @@
-#
-# Makefile for the Linux msdos filesystem routines.
-#
-
-obj-$(CONFIG_MSDOS_FS) += msdos.o
-
-msdos-y := namei.o
diff --git a/fs/namei.c b/fs/namei.c
index 09ce58e49e72..d34e0f9681c6 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1378,7 +1378,7 @@ static int may_delete(struct inode *dir,struct dentry *victim,int isdir)
 	if (IS_APPEND(dir))
 		return -EPERM;
 	if (check_sticky(dir, victim->d_inode)||IS_APPEND(victim->d_inode)||
-	    IS_IMMUTABLE(victim->d_inode))
+	    IS_IMMUTABLE(victim->d_inode) || IS_SWAPFILE(victim->d_inode))
 		return -EPERM;
 	if (isdir) {
 		if (!S_ISDIR(victim->d_inode->i_mode))
diff --git a/fs/namespace.c b/fs/namespace.c
index cce46702d33c..65b3dc844c87 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1815,8 +1815,8 @@ static void shrink_submounts(struct vfsmount *mnt, struct list_head *umounts)
 		while (!list_empty(&graveyard)) {
 			m = list_first_entry(&graveyard, struct vfsmount,
 						mnt_expire);
-			touch_mnt_namespace(mnt->mnt_ns);
-			umount_tree(mnt, 1, umounts);
+			touch_mnt_namespace(m->mnt_ns);
+			umount_tree(m, 1, umounts);
 		}
 	}
 }
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 848a03e83a42..4433c8f00163 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1875,11 +1875,11 @@ static int nfsd_buffered_readdir(struct file *file, filldir_t func,
 		return -ENOMEM;
 
 	offset = *offsetp;
-	cdp->err = nfserr_eof; /* will be cleared on successful read */
 
 	while (1) {
 		unsigned int reclen;
 
+		cdp->err = nfserr_eof; /* will be cleared on successful read */
 		buf.used = 0;
 		buf.full = 0;
 
@@ -1912,9 +1912,6 @@ static int nfsd_buffered_readdir(struct file *file, filldir_t func,
 			de = (struct buffered_dirent *)((char *)de + reclen);
 		}
 		offset = vfs_llseek(file, 0, SEEK_CUR);
-		cdp->err = nfserr_eof;
-		if (!buf.full)
-			break;
 	}
 
  done:
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 7efe937a415f..e2570a3bc2b2 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -247,8 +247,8 @@ int ocfs2_update_inode_atime(struct inode *inode,
 	mlog_entry_void();
 
 	handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
-	if (handle == NULL) {
-		ret = -ENOMEM;
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
 		mlog_errno(ret);
 		goto out;
 	}
@@ -312,8 +312,8 @@ static int ocfs2_simple_size_update(struct inode *inode,
 	handle_t *handle = NULL;
 
 	handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
-	if (handle == NULL) {
-		ret = -ENOMEM;
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
 		mlog_errno(ret);
 		goto out;
 	}
@@ -1055,8 +1055,8 @@ static int __ocfs2_write_remove_suid(struct inode *inode,
 		   (unsigned long long)OCFS2_I(inode)->ip_blkno, inode->i_mode);
 
 	handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
-	if (handle == NULL) {
-		ret = -ENOMEM;
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
 		mlog_errno(ret);
 		goto out;
 	}
@@ -1259,8 +1259,8 @@ static int __ocfs2_remove_inode_range(struct inode *inode,
 	}
 
 	handle = ocfs2_start_trans(osb, OCFS2_REMOVE_EXTENT_CREDITS);
-	if (handle == NULL) {
-		ret = -ENOMEM;
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
 		mlog_errno(ret);
 		goto out;
 	}
@@ -1352,8 +1352,8 @@ static int ocfs2_zero_partial_clusters(struct inode *inode,
 		goto out;
 
 	handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
-	if (handle == NULL) {
-		ret = -ENOMEM;
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
 		mlog_errno(ret);
 		goto out;
 	}
@@ -1866,6 +1866,13 @@ relock:
 		written = generic_file_direct_write(iocb, iov, &nr_segs, *ppos,
 						    ppos, count, ocount);
 		if (written < 0) {
+			/*
+			 * direct write may have instantiated a few
+			 * blocks outside i_size. Trim these off again.
+			 * Don't need i_size_read because we hold i_mutex.
+			 */
+			if (*ppos + count > inode->i_size)
+				vmtruncate(inode, inode->i_size);
 			ret = written;
 			goto out_dio;
 		}
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index 4903688f72a9..7aa00d511874 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -1106,6 +1106,12 @@ void ocfs2_clear_inode(struct inode *inode)
 	oi->ip_last_trans = 0;
 	oi->ip_dir_start_lookup = 0;
 	oi->ip_blkno = 0ULL;
+
+	/*
+	 * ip_jinode is used to track txns against this inode. We ensure that
+	 * the journal is flushed before journal shutdown. Thus it is safe to
+	 * have inodes get cleaned up after journal shutdown.
+	 */
 	jbd2_journal_release_jbd_inode(OCFS2_SB(inode->i_sb)->journal->j_journal,
 				       &oi->ip_jinode);
 
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 81e40677eecb..99fe9d584f3c 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -690,6 +690,7 @@ void ocfs2_journal_shutdown(struct ocfs2_super *osb)
 
 	/* Shutdown the kernel journal system */
 	jbd2_journal_destroy(journal->j_journal);
+	journal->j_journal = NULL;
 
 	OCFS2_I(inode)->ip_open_count--;
 
diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c
index 3dc18d67557c..eea1d24713ea 100644
--- a/fs/ocfs2/mmap.c
+++ b/fs/ocfs2/mmap.c
@@ -113,7 +113,11 @@ static int __ocfs2_page_mkwrite(struct inode *inode, struct buffer_head *di_bh,
 	 * ocfs2_write_begin_nolock().
 	 */
 	if (!PageUptodate(page) || page->mapping != inode->i_mapping) {
-		ret = -EINVAL;
+		/*
+		 * the page has been umapped in ocfs2_data_downconvert_worker.
+		 * So return 0 here and let VFS retry.
+		 */
+		ret = 0;
 		goto out;
 	}
 
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 485a6aa0ad39..f4967e634ffd 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -378,8 +378,8 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb,
 	}
 
 	inode = new_inode(dir->i_sb);
-	if (IS_ERR(inode)) {
-		status = PTR_ERR(inode);
+	if (!inode) {
+		status = -ENOMEM;
 		mlog(ML_ERROR, "new_inode failed!\n");
 		goto leave;
 	}
@@ -491,8 +491,10 @@ leave:
 			brelse(*new_fe_bh);
 			*new_fe_bh = NULL;
 		}
-		if (inode)
+		if (inode) {
+			clear_nlink(inode);
 			iput(inode);
+		}
 	}
 
 	mlog_exit(status);
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index a21a465490c4..fef7ece32376 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -473,6 +473,9 @@ static inline int ocfs2_uses_extended_slot_map(struct ocfs2_super *osb)
 		(____gd)->bg_signature);				\
 } while (0)
 
+#define OCFS2_IS_VALID_XATTR_BLOCK(ptr)					\
+	(!strcmp((ptr)->xb_signature, OCFS2_XATTR_BLOCK_SIGNATURE))
+
 static inline unsigned long ino_from_blkno(struct super_block *sb,
 					   u64 blkno)
 {
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index f24ce3d3f956..5f180cf7abbd 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -742,12 +742,12 @@ struct ocfs2_group_desc
  */
 struct ocfs2_xattr_entry {
 	__le32	xe_name_hash;    /* hash value of xattr prefix+suffix. */
-	__le16	xe_name_offset;  /* byte offset from the 1st etnry in the local
+	__le16	xe_name_offset;  /* byte offset from the 1st entry in the
 				    local xattr storage(inode, xattr block or
 				    xattr bucket). */
 	__u8	xe_name_len;	 /* xattr name len, does't include prefix. */
-	__u8	xe_type;         /* the low 7 bits indicates the name prefix's
-				  * type and the highest 1 bits indicate whether
+	__u8	xe_type;         /* the low 7 bits indicate the name prefix
+				  * type and the highest bit indicates whether
 				  * the EA is stored in the local storage. */
 	__le64	xe_value_size;	 /* real xattr value length. */
 };
@@ -766,9 +766,10 @@ struct ocfs2_xattr_header {
 						   xattr. */
 	__le16	xh_name_value_len;              /* total length of name/value
 						   length in this bucket. */
-	__le16	xh_num_buckets;                 /* bucket nums in one extent
-						   record, only valid in the
-						   first bucket. */
+	__le16	xh_num_buckets;                 /* Number of xattr buckets
+						   in this extent record,
+						   only valid in the first
+						   bucket. */
 	__le64  xh_csum;
 	struct ocfs2_xattr_entry xh_entries[0]; /* xattr entry list. */
 };
@@ -776,8 +777,8 @@ struct ocfs2_xattr_header {
 /*
  * On disk structure for xattr value root.
  *
- * It is used when one extended attribute's size is larger, and we will save it
- * in an outside cluster. It will stored in a b-tree like file content.
+ * When an xattr's value is large enough, it is stored in an external
+ * b-tree like file data.  The xattr value root points to this structure.
  */
 struct ocfs2_xattr_value_root {
 /*00*/	__le32	xr_clusters;              /* clusters covered by xattr value. */
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index 802c41492214..054e2efb0b7e 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -3,25 +3,20 @@
  *
  * xattr.c
  *
- * Copyright (C) 2008 Oracle.  All rights reserved.
+ * Copyright (C) 2004, 2008 Oracle.  All rights reserved.
  *
  * CREDITS:
- * Lots of code in this file is taken from ext3.
+ * Lots of code in this file is copy from linux/fs/ext3/xattr.c.
+ * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de>
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public
- * License as published by the Free Software Foundation; either
- * version 2 of the License, or (at your option) any later version.
+ * License version 2 as published by the Free Software Foundation.
  *
  * This program is distributed in the hope that it will be useful,
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public
- * License along with this program; if not, write to the
- * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
- * Boston, MA 021110-1307, USA.
  */
 
 #include <linux/capability.h>
@@ -83,7 +78,7 @@ struct xattr_handler *ocfs2_xattr_handlers[] = {
 	NULL
 };
 
-static struct xattr_handler *ocfs2_xattr_handler_map[] = {
+static struct xattr_handler *ocfs2_xattr_handler_map[OCFS2_XATTR_MAX] = {
 	[OCFS2_XATTR_INDEX_USER]	= &ocfs2_xattr_user_handler,
 	[OCFS2_XATTR_INDEX_TRUSTED]	= &ocfs2_xattr_trusted_handler,
 };
@@ -116,6 +111,10 @@ static int ocfs2_xattr_bucket_get_name_value(struct inode *inode,
 					     int *block_off,
 					     int *new_offset);
 
+static int ocfs2_xattr_block_find(struct inode *inode,
+				  int name_index,
+				  const char *name,
+				  struct ocfs2_xattr_search *xs);
 static int ocfs2_xattr_index_block_find(struct inode *inode,
 					struct buffer_head *root_bh,
 					int name_index,
@@ -137,6 +136,24 @@ static int ocfs2_xattr_set_entry_index_block(struct inode *inode,
 static int ocfs2_delete_xattr_index_block(struct inode *inode,
 					  struct buffer_head *xb_bh);
 
+static inline u16 ocfs2_xattr_buckets_per_cluster(struct ocfs2_super *osb)
+{
+	return (1 << osb->s_clustersize_bits) / OCFS2_XATTR_BUCKET_SIZE;
+}
+
+static inline u16 ocfs2_blocks_per_xattr_bucket(struct super_block *sb)
+{
+	return OCFS2_XATTR_BUCKET_SIZE / (1 << sb->s_blocksize_bits);
+}
+
+static inline u16 ocfs2_xattr_max_xe_in_bucket(struct super_block *sb)
+{
+	u16 len = sb->s_blocksize -
+		 offsetof(struct ocfs2_xattr_header, xh_entries);
+
+	return len / sizeof(struct ocfs2_xattr_entry);
+}
+
 static inline const char *ocfs2_xattr_prefix(int name_index)
 {
 	struct xattr_handler *handler = NULL;
@@ -542,14 +559,12 @@ static int ocfs2_xattr_block_list(struct inode *inode,
 		mlog_errno(ret);
 		return ret;
 	}
-	/*Verify the signature of xattr block*/
-	if (memcmp((void *)blk_bh->b_data, OCFS2_XATTR_BLOCK_SIGNATURE,
-		   strlen(OCFS2_XATTR_BLOCK_SIGNATURE))) {
-		ret = -EFAULT;
-		goto cleanup;
-	}
 
 	xb = (struct ocfs2_xattr_block *)blk_bh->b_data;
+	if (!OCFS2_IS_VALID_XATTR_BLOCK(xb)) {
+		ret = -EIO;
+		goto cleanup;
+	}
 
 	if (!(le16_to_cpu(xb->xb_flags) & OCFS2_XATTR_INDEXED)) {
 		struct ocfs2_xattr_header *header = &xb->xb_attrs.xb_header;
@@ -749,47 +764,25 @@ static int ocfs2_xattr_block_get(struct inode *inode,
 				 size_t buffer_size,
 				 struct ocfs2_xattr_search *xs)
 {
-	struct ocfs2_dinode *di = (struct ocfs2_dinode *)xs->inode_bh->b_data;
-	struct buffer_head *blk_bh = NULL;
 	struct ocfs2_xattr_block *xb;
 	struct ocfs2_xattr_value_root *xv;
 	size_t size;
 	int ret = -ENODATA, name_offset, name_len, block_off, i;
 
-	if (!di->i_xattr_loc)
-		return ret;
-
 	memset(&xs->bucket, 0, sizeof(xs->bucket));
 
-	ret = ocfs2_read_block(inode, le64_to_cpu(di->i_xattr_loc), &blk_bh);
-	if (ret < 0) {
+	ret = ocfs2_xattr_block_find(inode, name_index, name, xs);
+	if (ret) {
 		mlog_errno(ret);
-		return ret;
-	}
-	/*Verify the signature of xattr block*/
-	if (memcmp((void *)blk_bh->b_data, OCFS2_XATTR_BLOCK_SIGNATURE,
-		   strlen(OCFS2_XATTR_BLOCK_SIGNATURE))) {
-		ret = -EFAULT;
 		goto cleanup;
 	}
 
-	xs->xattr_bh = blk_bh;
-	xb = (struct ocfs2_xattr_block *)blk_bh->b_data;
-
-	if (!(le16_to_cpu(xb->xb_flags) & OCFS2_XATTR_INDEXED)) {
-		xs->header = &xb->xb_attrs.xb_header;
-		xs->base = (void *)xs->header;
-		xs->end = (void *)(blk_bh->b_data) + blk_bh->b_size;
-		xs->here = xs->header->xh_entries;
-
-		ret = ocfs2_xattr_find_entry(name_index, name, xs);
-	} else
-		ret = ocfs2_xattr_index_block_find(inode, blk_bh,
-						   name_index,
-						   name, xs);
-
-	if (ret)
+	if (xs->not_found) {
+		ret = -ENODATA;
 		goto cleanup;
+	}
+
+	xb = (struct ocfs2_xattr_block *)xs->xattr_bh->b_data;
 	size = le64_to_cpu(xs->here->xe_value_size);
 	if (buffer) {
 		ret = -ERANGE;
@@ -828,7 +821,8 @@ cleanup:
 		brelse(xs->bucket.bhs[i]);
 	memset(&xs->bucket, 0, sizeof(xs->bucket));
 
-	brelse(blk_bh);
+	brelse(xs->xattr_bh);
+	xs->xattr_bh = NULL;
 	return ret;
 }
 
@@ -837,11 +831,11 @@ cleanup:
  * Copy an extended attribute into the buffer provided.
  * Buffer is NULL to compute the size of buffer required.
  */
-int ocfs2_xattr_get(struct inode *inode,
-		    int name_index,
-		    const char *name,
-		    void *buffer,
-		    size_t buffer_size)
+static int ocfs2_xattr_get(struct inode *inode,
+			   int name_index,
+			   const char *name,
+			   void *buffer,
+			   size_t buffer_size)
 {
 	int ret;
 	struct ocfs2_dinode *di = NULL;
@@ -871,7 +865,7 @@ int ocfs2_xattr_get(struct inode *inode,
 	down_read(&oi->ip_xattr_sem);
 	ret = ocfs2_xattr_ibody_get(inode, name_index, name, buffer,
 				    buffer_size, &xis);
-	if (ret == -ENODATA)
+	if (ret == -ENODATA && di->i_xattr_loc)
 		ret = ocfs2_xattr_block_get(inode, name_index, name, buffer,
 					    buffer_size, &xbs);
 	up_read(&oi->ip_xattr_sem);
@@ -1229,7 +1223,7 @@ static int ocfs2_xattr_set_entry(struct inode *inode,
 
 	free = min_offs - ((void *)last - xs->base) - sizeof(__u32);
 	if (free < 0)
-		return -EFAULT;
+		return -EIO;
 
 	if (!xs->not_found) {
 		size_t size = 0;
@@ -1514,10 +1508,9 @@ static int ocfs2_xattr_free_block(struct inode *inode,
 		goto out;
 	}
 
-	/*Verify the signature of xattr block*/
-	if (memcmp((void *)blk_bh->b_data, OCFS2_XATTR_BLOCK_SIGNATURE,
-		   strlen(OCFS2_XATTR_BLOCK_SIGNATURE))) {
-		ret = -EFAULT;
+	xb = (struct ocfs2_xattr_block *)blk_bh->b_data;
+	if (!OCFS2_IS_VALID_XATTR_BLOCK(xb)) {
+		ret = -EIO;
 		goto out;
 	}
 
@@ -1527,7 +1520,6 @@ static int ocfs2_xattr_free_block(struct inode *inode,
 		goto out;
 	}
 
-	xb = (struct ocfs2_xattr_block *)blk_bh->b_data;
 	blk = le64_to_cpu(xb->xb_blkno);
 	bit = le16_to_cpu(xb->xb_suballoc_bit);
 	bg_blkno = ocfs2_which_suballoc_group(blk, bit);
@@ -1771,15 +1763,14 @@ static int ocfs2_xattr_block_find(struct inode *inode,
 		mlog_errno(ret);
 		return ret;
 	}
-	/*Verify the signature of xattr block*/
-	if (memcmp((void *)blk_bh->b_data, OCFS2_XATTR_BLOCK_SIGNATURE,
-		   strlen(OCFS2_XATTR_BLOCK_SIGNATURE))) {
-			ret = -EFAULT;
-			goto cleanup;
+
+	xb = (struct ocfs2_xattr_block *)blk_bh->b_data;
+	if (!OCFS2_IS_VALID_XATTR_BLOCK(xb)) {
+		ret = -EIO;
+		goto cleanup;
 	}
 
 	xs->xattr_bh = blk_bh;
-	xb = (struct ocfs2_xattr_block *)blk_bh->b_data;
 
 	if (!(le16_to_cpu(xb->xb_flags) & OCFS2_XATTR_INDEXED)) {
 		xs->header = &xb->xb_attrs.xb_header;
@@ -1806,52 +1797,6 @@ cleanup:
 }
 
 /*
- * When all the xattrs are deleted from index btree, the ocfs2_xattr_tree
- * will be erased and ocfs2_xattr_block will have its ocfs2_xattr_header
- * re-initialized.
- */
-static int ocfs2_restore_xattr_block(struct inode *inode,
-				     struct ocfs2_xattr_search *xs)
-{
-	int ret;
-	handle_t *handle;
-	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
-	struct ocfs2_xattr_block *xb =
-		(struct ocfs2_xattr_block *)xs->xattr_bh->b_data;
-	struct ocfs2_extent_list *el = &xb->xb_attrs.xb_root.xt_list;
-	u16 xb_flags = le16_to_cpu(xb->xb_flags);
-
-	BUG_ON(!(xb_flags & OCFS2_XATTR_INDEXED) ||
-		le16_to_cpu(el->l_next_free_rec) != 0);
-
-	handle = ocfs2_start_trans(osb, OCFS2_XATTR_BLOCK_UPDATE_CREDITS);
-	if (IS_ERR(handle)) {
-		ret = PTR_ERR(handle);
-		handle = NULL;
-		goto out;
-	}
-
-	ret = ocfs2_journal_access(handle, inode, xs->xattr_bh,
-				   OCFS2_JOURNAL_ACCESS_WRITE);
-	if (ret < 0) {
-		mlog_errno(ret);
-		goto out_commit;
-	}
-
-	memset(&xb->xb_attrs, 0, inode->i_sb->s_blocksize -
-	       offsetof(struct ocfs2_xattr_block, xb_attrs));
-
-	xb->xb_flags = cpu_to_le16(xb_flags & ~OCFS2_XATTR_INDEXED);
-
-	ocfs2_journal_dirty(handle, xs->xattr_bh);
-
-out_commit:
-	ocfs2_commit_trans(osb, handle);
-out:
-	return ret;
-}
-
-/*
  * ocfs2_xattr_block_set()
  *
  * Set, replace or remove an extended attribute into external block.
@@ -1961,8 +1906,6 @@ out:
 	}
 
 	ret = ocfs2_xattr_set_entry_index_block(inode, xi, xs);
-	if (!ret && xblk->xb_attrs.xb_root.xt_list.l_next_free_rec == 0)
-		ret = ocfs2_restore_xattr_block(inode, xs);
 
 end:
 
@@ -2398,7 +2341,8 @@ static int ocfs2_xattr_index_block_find(struct inode *inode,
 	BUG_ON(p_blkno == 0 || num_clusters == 0 || first_hash > name_hash);
 
 	mlog(0, "find xattr extent rec %u clusters from %llu, the first hash "
-	     "in the rec is %u\n", num_clusters, p_blkno, first_hash);
+	     "in the rec is %u\n", num_clusters, (unsigned long long)p_blkno,
+	     first_hash);
 
 	ret = ocfs2_xattr_bucket_find(inode, name_index, name, name_hash,
 				      p_blkno, first_hash, num_clusters, xs);
@@ -2422,7 +2366,7 @@ static int ocfs2_iterate_xattr_buckets(struct inode *inode,
 	memset(&bucket, 0, sizeof(bucket));
 
 	mlog(0, "iterating xattr buckets in %u clusters starting from %llu\n",
-	     clusters, blkno);
+	     clusters, (unsigned long long)blkno);
 
 	for (i = 0; i < num_buckets; i++, blkno += blk_per_bucket) {
 		ret = ocfs2_read_blocks(inode, blkno, blk_per_bucket,
@@ -2440,7 +2384,8 @@ static int ocfs2_iterate_xattr_buckets(struct inode *inode,
 		if (i == 0)
 			num_buckets = le16_to_cpu(bucket.xh->xh_num_buckets);
 
-		mlog(0, "iterating xattr bucket %llu, first hash %u\n", blkno,
+		mlog(0, "iterating xattr bucket %llu, first hash %u\n",
+		     (unsigned long long)blkno,
 		     le32_to_cpu(bucket.xh->xh_entries[0].xe_name_hash));
 		if (func) {
 			ret = func(inode, &bucket, para);
@@ -2776,7 +2721,8 @@ static int ocfs2_xattr_create_index_block(struct inode *inode,
 	 */
 	blkno = ocfs2_clusters_to_blocks(inode->i_sb, bit_off);
 
-	mlog(0, "allocate 1 cluster from %llu to xattr block\n", blkno);
+	mlog(0, "allocate 1 cluster from %llu to xattr block\n",
+	     (unsigned long long)blkno);
 
 	xh_bh = sb_getblk(inode->i_sb, blkno);
 	if (!xh_bh) {
@@ -2818,7 +2764,11 @@ static int ocfs2_xattr_create_index_block(struct inode *inode,
 	if (data_bh)
 		ocfs2_journal_dirty(handle, data_bh);
 
-	ocfs2_xattr_update_xattr_search(inode, xs, xb_bh, xh_bh);
+	ret = ocfs2_xattr_update_xattr_search(inode, xs, xb_bh, xh_bh);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_commit;
+	}
 
 	/* Change from ocfs2_xattr_header to ocfs2_xattr_tree_root */
 	memset(&xb->xb_attrs, 0, inode->i_sb->s_blocksize -
@@ -2941,8 +2891,8 @@ static int ocfs2_defrag_xattr_bucket(struct inode *inode,
 
 	mlog(0, "adjust xattr bucket in %llu, count = %u, "
 	     "xh_free_start = %u, xh_name_value_len = %u.\n",
-	     blkno, le16_to_cpu(xh->xh_count), xh_free_start,
-	     le16_to_cpu(xh->xh_name_value_len));
+	     (unsigned long long)blkno, le16_to_cpu(xh->xh_count),
+	     xh_free_start, le16_to_cpu(xh->xh_name_value_len));
 
 	/*
 	 * sort all the entries by their offset.
@@ -3058,7 +3008,7 @@ static int ocfs2_mv_xattr_bucket_cross_cluster(struct inode *inode,
 	prev_blkno += (num_clusters - 1) * bpc + bpc / 2;
 
 	mlog(0, "move half of xattrs in cluster %llu to %llu\n",
-	     prev_blkno, new_blkno);
+	     (unsigned long long)prev_blkno, (unsigned long long)new_blkno);
 
 	/*
 	 * We need to update the 1st half of the new cluster and
@@ -3168,26 +3118,74 @@ static int ocfs2_read_xattr_bucket(struct inode *inode,
 }
 
 /*
- * Move half num of the xattrs in old bucket(blk) to new bucket(new_blk).
+ * Find the suitable pos when we divide a bucket into 2.
+ * We have to make sure the xattrs with the same hash value exist
+ * in the same bucket.
+ *
+ * If this ocfs2_xattr_header covers more than one hash value, find a
+ * place where the hash value changes.  Try to find the most even split.
+ * The most common case is that all entries have different hash values,
+ * and the first check we make will find a place to split.
+ */
+static int ocfs2_xattr_find_divide_pos(struct ocfs2_xattr_header *xh)
+{
+	struct ocfs2_xattr_entry *entries = xh->xh_entries;
+	int count = le16_to_cpu(xh->xh_count);
+	int delta, middle = count / 2;
+
+	/*
+	 * We start at the middle.  Each step gets farther away in both
+	 * directions.  We therefore hit the change in hash value
+	 * nearest to the middle.  Note that this loop does not execute for
+	 * count < 2.
+	 */
+	for (delta = 0; delta < middle; delta++) {
+		/* Let's check delta earlier than middle */
+		if (cmp_xe(&entries[middle - delta - 1],
+			   &entries[middle - delta]))
+			return middle - delta;
+
+		/* For even counts, don't walk off the end */
+		if ((middle + delta + 1) == count)
+			continue;
+
+		/* Now try delta past middle */
+		if (cmp_xe(&entries[middle + delta],
+			   &entries[middle + delta + 1]))
+			return middle + delta + 1;
+	}
+
+	/* Every entry had the same hash */
+	return count;
+}
+
+/*
+ * Move some xattrs in old bucket(blk) to new bucket(new_blk).
  * first_hash will record the 1st hash of the new bucket.
+ *
+ * Normally half of the xattrs will be moved.  But we have to make
+ * sure that the xattrs with the same hash value are stored in the
+ * same bucket. If all the xattrs in this bucket have the same hash
+ * value, the new bucket will be initialized as an empty one and the
+ * first_hash will be initialized as (hash_value+1).
  */
-static int ocfs2_half_xattr_bucket(struct inode *inode,
-				   handle_t *handle,
-				   u64 blk,
-				   u64 new_blk,
-				   u32 *first_hash,
-				   int new_bucket_head)
+static int ocfs2_divide_xattr_bucket(struct inode *inode,
+				    handle_t *handle,
+				    u64 blk,
+				    u64 new_blk,
+				    u32 *first_hash,
+				    int new_bucket_head)
 {
 	int ret, i;
-	u16 count, start, len, name_value_len, xe_len, name_offset;
+	int count, start, len, name_value_len = 0, xe_len, name_offset = 0;
 	u16 blk_per_bucket = ocfs2_blocks_per_xattr_bucket(inode->i_sb);
 	struct buffer_head **s_bhs, **t_bhs = NULL;
 	struct ocfs2_xattr_header *xh;
 	struct ocfs2_xattr_entry *xe;
 	int blocksize = inode->i_sb->s_blocksize;
 
-	mlog(0, "move half of xattrs from bucket %llu to %llu\n",
-	     blk, new_blk);
+	mlog(0, "move some of xattrs from bucket %llu to %llu\n",
+	     (unsigned long long)blk, (unsigned long long)new_blk);
 
 	s_bhs = kcalloc(blk_per_bucket, sizeof(struct buffer_head *), GFP_NOFS);
 	if (!s_bhs)
@@ -3220,21 +3218,44 @@ static int ocfs2_half_xattr_bucket(struct inode *inode,
 
 	for (i = 0; i < blk_per_bucket; i++) {
 		ret = ocfs2_journal_access(handle, inode, t_bhs[i],
-					   OCFS2_JOURNAL_ACCESS_CREATE);
+					   new_bucket_head ?
+					   OCFS2_JOURNAL_ACCESS_CREATE :
+					   OCFS2_JOURNAL_ACCESS_WRITE);
 		if (ret) {
 			mlog_errno(ret);
 			goto out;
 		}
 	}
 
+	xh = (struct ocfs2_xattr_header *)s_bhs[0]->b_data;
+	count = le16_to_cpu(xh->xh_count);
+	start = ocfs2_xattr_find_divide_pos(xh);
+
+	if (start == count) {
+		xe = &xh->xh_entries[start-1];
+
+		/*
+		 * initialized a new empty bucket here.
+		 * The hash value is set as one larger than
+		 * that of the last entry in the previous bucket.
+		 */
+		for (i = 0; i < blk_per_bucket; i++)
+			memset(t_bhs[i]->b_data, 0, blocksize);
+
+		xh = (struct ocfs2_xattr_header *)t_bhs[0]->b_data;
+		xh->xh_free_start = cpu_to_le16(blocksize);
+		xh->xh_entries[0].xe_name_hash = xe->xe_name_hash;
+		le32_add_cpu(&xh->xh_entries[0].xe_name_hash, 1);
+
+		goto set_num_buckets;
+	}
+
 	/* copy the whole bucket to the new first. */
 	for (i = 0; i < blk_per_bucket; i++)
 		memcpy(t_bhs[i]->b_data, s_bhs[i]->b_data, blocksize);
 
 	/* update the new bucket. */
 	xh = (struct ocfs2_xattr_header *)t_bhs[0]->b_data;
-	count = le16_to_cpu(xh->xh_count);
-	start = count / 2;
 
 	/*
 	 * Calculate the total name/value len and xh_free_start for
@@ -3291,6 +3312,7 @@ static int ocfs2_half_xattr_bucket(struct inode *inode,
 			xh->xh_free_start = xe->xe_name_offset;
 	}
 
+set_num_buckets:
 	/* set xh->xh_num_buckets for the new xh. */
 	if (new_bucket_head)
 		xh->xh_num_buckets = cpu_to_le16(1);
@@ -3308,9 +3330,13 @@ static int ocfs2_half_xattr_bucket(struct inode *inode,
 		*first_hash = le32_to_cpu(xh->xh_entries[0].xe_name_hash);
 
 	/*
-	 * Now only update the 1st block of the old bucket.
-	 * Please note that the entry has been sorted already above.
+	 * Now only update the 1st block of the old bucket.  If we
+	 * just added a new empty bucket, there is no need to modify
+	 * it.
 	 */
+	if (start == count)
+		goto out;
+
 	xh = (struct ocfs2_xattr_header *)s_bhs[0]->b_data;
 	memset(&xh->xh_entries[start], 0,
 	       sizeof(struct ocfs2_xattr_entry) * (count - start));
@@ -3358,7 +3384,8 @@ static int ocfs2_cp_xattr_bucket(struct inode *inode,
 	BUG_ON(s_blkno == t_blkno);
 
 	mlog(0, "cp bucket %llu to %llu, target is %d\n",
-	     s_blkno, t_blkno, t_is_new);
+	     (unsigned long long)s_blkno, (unsigned long long)t_blkno,
+	     t_is_new);
 
 	s_bhs = kzalloc(sizeof(struct buffer_head *) * blk_per_bucket,
 			GFP_NOFS);
@@ -3382,6 +3409,8 @@ static int ocfs2_cp_xattr_bucket(struct inode *inode,
 
 	for (i = 0; i < blk_per_bucket; i++) {
 		ret = ocfs2_journal_access(handle, inode, t_bhs[i],
+					   t_is_new ?
+					   OCFS2_JOURNAL_ACCESS_CREATE :
 					   OCFS2_JOURNAL_ACCESS_WRITE);
 		if (ret)
 			goto out;
@@ -3428,7 +3457,8 @@ static int ocfs2_cp_xattr_cluster(struct inode *inode,
 	struct ocfs2_xattr_header *xh;
 	u64 to_blk_start = to_blk;
 
-	mlog(0, "cp xattrs from cluster %llu to %llu\n", src_blk, to_blk);
+	mlog(0, "cp xattrs from cluster %llu to %llu\n",
+	     (unsigned long long)src_blk, (unsigned long long)to_blk);
 
 	/*
 	 * We need to update the new cluster and 1 more for the update of
@@ -3493,15 +3523,15 @@ out:
 }
 
 /*
- * Move half of the xattrs in this cluster to the new cluster.
+ * Move some xattrs in this cluster to the new cluster.
  * This function should only be called when bucket size == cluster size.
  * Otherwise ocfs2_mv_xattr_bucket_cross_cluster should be used instead.
  */
-static int ocfs2_half_xattr_cluster(struct inode *inode,
-				    handle_t *handle,
-				    u64 prev_blk,
-				    u64 new_blk,
-				    u32 *first_hash)
+static int ocfs2_divide_xattr_cluster(struct inode *inode,
+				      handle_t *handle,
+				      u64 prev_blk,
+				      u64 new_blk,
+				      u32 *first_hash)
 {
 	u16 blk_per_bucket = ocfs2_blocks_per_xattr_bucket(inode->i_sb);
 	int ret, credits = 2 * blk_per_bucket;
@@ -3515,8 +3545,8 @@ static int ocfs2_half_xattr_cluster(struct inode *inode,
 	}
 
 	/* Move half of the xattr in start_blk to the next bucket. */
-	return  ocfs2_half_xattr_bucket(inode, handle, prev_blk,
-					new_blk, first_hash, 1);
+	return  ocfs2_divide_xattr_bucket(inode, handle, prev_blk,
+					  new_blk, first_hash, 1);
 }
 
 /*
@@ -3559,7 +3589,8 @@ static int ocfs2_adjust_xattr_cross_cluster(struct inode *inode,
 	int bpc = ocfs2_clusters_to_blocks(inode->i_sb, 1);
 
 	mlog(0, "adjust xattrs from cluster %llu len %u to %llu\n",
-	     prev_blk, prev_clusters, new_blk);
+	     (unsigned long long)prev_blk, prev_clusters,
+	     (unsigned long long)new_blk);
 
 	if (ocfs2_xattr_buckets_per_cluster(OCFS2_SB(inode->i_sb)) > 1)
 		ret = ocfs2_mv_xattr_bucket_cross_cluster(inode,
@@ -3578,9 +3609,9 @@ static int ocfs2_adjust_xattr_cross_cluster(struct inode *inode,
 						     last_blk, new_blk,
 						     v_start);
 		else {
-			ret = ocfs2_half_xattr_cluster(inode, handle,
-						       last_blk, new_blk,
-						       v_start);
+			ret = ocfs2_divide_xattr_cluster(inode, handle,
+							 last_blk, new_blk,
+							 v_start);
 
 			if ((*header_bh)->b_blocknr == last_blk && extend)
 				*extend = 0;
@@ -3629,7 +3660,7 @@ static int ocfs2_add_new_xattr_cluster(struct inode *inode,
 	mlog(0, "Add new xattr cluster for %llu, previous xattr hash = %u, "
 	     "previous xattr blkno = %llu\n",
 	     (unsigned long long)OCFS2_I(inode)->ip_blkno,
-	     prev_cpos, prev_blkno);
+	     prev_cpos, (unsigned long long)prev_blkno);
 
 	ocfs2_init_xattr_tree_extent_tree(&et, inode, root_bh);
 
@@ -3716,7 +3747,7 @@ static int ocfs2_add_new_xattr_cluster(struct inode *inode,
 		}
 	}
 	mlog(0, "Insert %u clusters at block %llu for xattr at %u\n",
-	     num_bits, block, v_start);
+	     num_bits, (unsigned long long)block, v_start);
 	ret = ocfs2_insert_extent(osb, handle, inode, &et, v_start, block,
 				  num_bits, 0, meta_ac);
 	if (ret < 0) {
@@ -3761,7 +3792,7 @@ static int ocfs2_extend_xattr_bucket(struct inode *inode,
 	u16 bucket = le16_to_cpu(first_xh->xh_num_buckets);
 
 	mlog(0, "extend xattr bucket in %llu, xattr extend rec starting "
-	     "from %llu, len = %u\n", start_blk,
+	     "from %llu, len = %u\n", (unsigned long long)start_blk,
 	     (unsigned long long)first_bh->b_blocknr, num_clusters);
 
 	BUG_ON(bucket >= num_buckets);
@@ -3797,8 +3828,8 @@ static int ocfs2_extend_xattr_bucket(struct inode *inode,
 	}
 
 	/* Move half of the xattr in start_blk to the next bucket. */
-	ret = ocfs2_half_xattr_bucket(inode, handle, start_blk,
-				      start_blk + blk_per_bucket, NULL, 0);
+	ret = ocfs2_divide_xattr_bucket(inode, handle, start_blk,
+					start_blk + blk_per_bucket, NULL, 0);
 
 	le16_add_cpu(&first_xh->xh_num_buckets, 1);
 	ocfs2_journal_dirty(handle, first_bh);
@@ -4146,7 +4177,7 @@ static int ocfs2_xattr_value_update_size(struct inode *inode,
 	handle_t *handle = NULL;
 
 	handle = ocfs2_start_trans(osb, 1);
-	if (handle == NULL) {
+	if (IS_ERR(handle)) {
 		ret = -ENOMEM;
 		mlog_errno(ret);
 		goto out;
@@ -4313,7 +4344,7 @@ static int ocfs2_rm_xattr_cluster(struct inode *inode,
 	}
 
 	handle = ocfs2_start_trans(osb, OCFS2_REMOVE_EXTENT_CREDITS);
-	if (handle == NULL) {
+	if (IS_ERR(handle)) {
 		ret = -ENOMEM;
 		mlog_errno(ret);
 		goto out;
@@ -4489,11 +4520,21 @@ out:
 	return ret;
 }
 
-/* check whether the xattr bucket is filled up with the same hash value. */
+/*
+ * check whether the xattr bucket is filled up with the same hash value.
+ * If we want to insert the xattr with the same hash, return -ENOSPC.
+ * If we want to insert a xattr with different hash value, go ahead
+ * and ocfs2_divide_xattr_bucket will handle this.
+ */
 static int ocfs2_check_xattr_bucket_collision(struct inode *inode,
-					      struct ocfs2_xattr_bucket *bucket)
+					      struct ocfs2_xattr_bucket *bucket,
+					      const char *name)
 {
 	struct ocfs2_xattr_header *xh = bucket->xh;
+	u32 name_hash = ocfs2_xattr_name_hash(inode, name, strlen(name));
+
+	if (name_hash != le32_to_cpu(xh->xh_entries[0].xe_name_hash))
+		return 0;
 
 	if (xh->xh_entries[le16_to_cpu(xh->xh_count) - 1].xe_name_hash ==
 	    xh->xh_entries[0].xe_name_hash) {
@@ -4616,7 +4657,9 @@ try_again:
 		 * one bucket's worth, so check it here whether we need to
 		 * add a new bucket for the insert.
 		 */
-		ret = ocfs2_check_xattr_bucket_collision(inode, &xs->bucket);
+		ret = ocfs2_check_xattr_bucket_collision(inode,
+							 &xs->bucket,
+							 xi->name);
 		if (ret) {
 			mlog_errno(ret);
 			goto out;
@@ -4727,14 +4770,11 @@ out:
 /*
  * 'trusted' attributes support
  */
-
-#define XATTR_TRUSTED_PREFIX "trusted."
-
 static size_t ocfs2_xattr_trusted_list(struct inode *inode, char *list,
 				       size_t list_size, const char *name,
 				       size_t name_len)
 {
-	const size_t prefix_len = sizeof(XATTR_TRUSTED_PREFIX) - 1;
+	const size_t prefix_len = XATTR_TRUSTED_PREFIX_LEN;
 	const size_t total_len = prefix_len + name_len + 1;
 
 	if (list && total_len <= list_size) {
@@ -4771,18 +4811,14 @@ struct xattr_handler ocfs2_xattr_trusted_handler = {
 	.set	= ocfs2_xattr_trusted_set,
 };
 
-
 /*
  * 'user' attributes support
  */
-
-#define XATTR_USER_PREFIX "user."
-
 static size_t ocfs2_xattr_user_list(struct inode *inode, char *list,
 				    size_t list_size, const char *name,
 				    size_t name_len)
 {
-	const size_t prefix_len = sizeof(XATTR_USER_PREFIX) - 1;
+	const size_t prefix_len = XATTR_USER_PREFIX_LEN;
 	const size_t total_len = prefix_len + name_len + 1;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
diff --git a/fs/ocfs2/xattr.h b/fs/ocfs2/xattr.h
index c25c7c62a059..1d8314c7656d 100644
--- a/fs/ocfs2/xattr.h
+++ b/fs/ocfs2/xattr.h
@@ -3,24 +3,16 @@
  *
  * xattr.h
  *
- * Function prototypes
- *
- * Copyright (C) 2008 Oracle.  All rights reserved.
+ * Copyright (C) 2004, 2008 Oracle.  All rights reserved.
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public
- * License as published by the Free Software Foundation; either
- * version 2 of the License, or (at your option) any later version.
+ * License version 2 as published by the Free Software Foundation.
  *
  * This program is distributed in the hope that it will be useful,
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public
- * License along with this program; if not, write to the
- * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
- * Boston, MA 021110-1307, USA.
  */
 
 #ifndef OCFS2_XATTR_H
@@ -40,29 +32,11 @@ enum ocfs2_xattr_type {
 
 extern struct xattr_handler ocfs2_xattr_user_handler;
 extern struct xattr_handler ocfs2_xattr_trusted_handler;
-
-extern ssize_t ocfs2_listxattr(struct dentry *, char *, size_t);
-extern int ocfs2_xattr_get(struct inode *, int, const char *, void *, size_t);
-extern int ocfs2_xattr_set(struct inode *, int, const char *, const void *,
-			   size_t, int);
-extern int ocfs2_xattr_remove(struct inode *inode, struct buffer_head *di_bh);
 extern struct xattr_handler *ocfs2_xattr_handlers[];
 
-static inline u16 ocfs2_xattr_buckets_per_cluster(struct ocfs2_super *osb)
-{
-	return (1 << osb->s_clustersize_bits) / OCFS2_XATTR_BUCKET_SIZE;
-}
-
-static inline u16 ocfs2_blocks_per_xattr_bucket(struct super_block *sb)
-{
-	return OCFS2_XATTR_BUCKET_SIZE / (1 << sb->s_blocksize_bits);
-}
-
-static inline u16 ocfs2_xattr_max_xe_in_bucket(struct super_block *sb)
-{
-	u16 len = sb->s_blocksize -
-		 offsetof(struct ocfs2_xattr_header, xh_entries);
+ssize_t ocfs2_listxattr(struct dentry *, char *, size_t);
+int ocfs2_xattr_set(struct inode *, int, const char *, const void *,
+		    size_t, int);
+int ocfs2_xattr_remove(struct inode *, struct buffer_head *);
 
-	return len / sizeof(struct ocfs2_xattr_entry);
-}
 #endif /* OCFS2_XATTR_H */
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index 633f7a0ebb2c..6d5b213b8a9b 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -348,8 +348,8 @@ static ssize_t whole_disk_show(struct device *dev,
 static DEVICE_ATTR(whole_disk, S_IRUSR | S_IRGRP | S_IROTH,
 		   whole_disk_show, NULL);
 
-int add_partition(struct gendisk *disk, int partno,
-		  sector_t start, sector_t len, int flags)
+struct hd_struct *add_partition(struct gendisk *disk, int partno,
+				sector_t start, sector_t len, int flags)
 {
 	struct hd_struct *p;
 	dev_t devt = MKDEV(0, 0);
@@ -361,15 +361,15 @@ int add_partition(struct gendisk *disk, int partno,
 
 	err = disk_expand_part_tbl(disk, partno);
 	if (err)
-		return err;
+		return ERR_PTR(err);
 	ptbl = disk->part_tbl;
 
 	if (ptbl->part[partno])
-		return -EBUSY;
+		return ERR_PTR(-EBUSY);
 
 	p = kzalloc(sizeof(*p), GFP_KERNEL);
 	if (!p)
-		return -ENOMEM;
+		return ERR_PTR(-EBUSY);
 
 	if (!init_part_stats(p)) {
 		err = -ENOMEM;
@@ -395,7 +395,7 @@ int add_partition(struct gendisk *disk, int partno,
 
 	err = blk_alloc_devt(p, &devt);
 	if (err)
-		goto out_free;
+		goto out_free_stats;
 	pdev->devt = devt;
 
 	/* delay uevent until 'holders' subdir is created */
@@ -424,18 +424,20 @@ int add_partition(struct gendisk *disk, int partno,
 	if (!ddev->uevent_suppress)
 		kobject_uevent(&pdev->kobj, KOBJ_ADD);
 
-	return 0;
+	return p;
 
+out_free_stats:
+	free_part_stats(p);
 out_free:
 	kfree(p);
-	return err;
+	return ERR_PTR(err);
 out_del:
 	kobject_put(p->holder_dir);
 	device_del(pdev);
 out_put:
 	put_device(pdev);
 	blk_free_devt(devt);
-	return err;
+	return ERR_PTR(err);
 }
 
 /* Not exported, helper to add_disk(). */
@@ -566,15 +568,16 @@ int rescan_partitions(struct gendisk *disk, struct block_device *bdev)
 			       disk->disk_name, p, (unsigned long long) size);
 			size = get_capacity(disk) - from;
 		}
-		res = add_partition(disk, p, from, size, state->parts[p].flags);
-		if (res) {
-			printk(KERN_ERR " %s: p%d could not be added: %d\n",
-				disk->disk_name, p, -res);
+		part = add_partition(disk, p, from, size,
+				     state->parts[p].flags);
+		if (IS_ERR(part)) {
+			printk(KERN_ERR " %s: p%d could not be added: %ld\n",
+			       disk->disk_name, p, -PTR_ERR(part));
 			continue;
 		}
 #ifdef CONFIG_BLK_DEV_MD
 		if (state->parts[p].flags & ADDPART_FLAG_RAID)
-			md_autodetect_dev(bdev->bd_dev+p);
+			md_autodetect_dev(part_to_dev(part)->devt);
 #endif
 	}
 	kfree(state);
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 94fcfff6863a..06ed10b7da9e 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -31,6 +31,7 @@ static struct inode *proc_sys_make_inode(struct super_block *sb,
 	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
 	inode->i_flags |= S_PRIVATE; /* tell selinux to ignore this inode */
 	inode->i_mode = table->mode;
+	inode->i_uid = inode->i_gid = 0;
 	if (!table->child) {
 		inode->i_mode |= S_IFREG;
 		inode->i_op = &proc_sys_inode_operations;
diff --git a/fs/vfat/Makefile b/fs/vfat/Makefile
deleted file mode 100644
index 40f2798a4f08..000000000000
--- a/fs/vfat/Makefile
+++ /dev/null
@@ -1,7 +0,0 @@
-#
-# Makefile for the linux vfat-filesystem routines.
-#
-
-obj-$(CONFIG_VFAT_FS) += vfat.o
-
-vfat-y := namei.o