Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

Conflicts:

	drivers/net/wireless/ath5k/base.c
	net/8021q/vlan_core.c

40 files changed, 925 insertions, 395 deletions

diff --git a/fs/Makefile b/fs/Makefile
index 2168c902d5c..d9f8afe6f0c 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 625abf5422e..33bf8cbfd05 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 cde2f8e8935..4b6fb3f628c 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 88a776fa0ef..db831efbdbb 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 8f528ea24c4..8855331b2fb 100644
--- a/fs/cifs/CHANGES
+++ b/fs/cifs/CHANGES
@@ -4,7 +4,11 @@ Various fixes to make delete of open files behavior more predictable
 (when delete of an open file fails we mark the file as "delete-on-close"
 in a way that more servers accept, but only if we can first rename the
 file to a temporary name).  Add experimental support for more safely
-handling fcntl(F_SETLEASE).
+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).
 
 Version 1.54
 ------------
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index c791e5b5a91..1cb1189f24e 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -141,6 +141,8 @@ struct TCP_Server_Info {
 	char versionMajor;
 	char versionMinor;
 	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
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index 0cff7fe986e..6f21ecb85ce 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -36,7 +36,7 @@ extern void cifs_buf_release(void *);
 extern struct smb_hdr *cifs_small_buf_get(void);
 extern void cifs_small_buf_release(void *);
 extern int smb_send(struct socket *, struct smb_hdr *,
-			unsigned int /* length */ , struct sockaddr *);
+			unsigned int /* length */ , struct sockaddr *, bool);
 extern unsigned int _GetXid(void);
 extern void _FreeXid(unsigned int);
 #define GetXid() (int)_GetXid(); cFYI(1,("CIFS VFS: in %s as Xid: %d with uid: %d",__func__, xid,current->fsuid));
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 843a85fb8b9..d5eac48fc41 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -1536,7 +1536,7 @@ CIFSSMBWrite(const int xid, struct cifsTconInfo *tcon,
 	__u32 bytes_sent;
 	__u16 byte_count;
 
-	/* cFYI(1,("write at %lld %d bytes",offset,count));*/
+	/* cFYI(1, ("write at %lld %d bytes", offset, count));*/
 	if (tcon->ses == NULL)
 		return -ECONNABORTED;
 
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index cd54fee3f05..2df8e6d0fb0 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -92,6 +92,8 @@ struct smb_vol {
 	bool seal:1;       /* request transport encryption on share */
 	bool nodfs:1;      /* Do not request DFS, even if available */
 	bool local_lease:1; /* check leases only on local system, not remote */
+	bool noblocksnd:1;
+	bool noautotune:1;
 	unsigned int rsize;
 	unsigned int wsize;
 	unsigned int sockopt;
@@ -102,9 +104,11 @@ struct smb_vol {
 static int ipv4_connect(struct sockaddr_in *psin_server,
 			struct socket **csocket,
 			char *netb_name,
-			char *server_netb_name);
+			char *server_netb_name,
+			bool noblocksnd,
+			bool nosndbuf); /* ipv6 never set sndbuf size */
 static int ipv6_connect(struct sockaddr_in6 *psin_server,
-			struct socket **csocket);
+			struct socket **csocket, bool noblocksnd);
 
 
 	/*
@@ -191,12 +195,13 @@ cifs_reconnect(struct TCP_Server_Info *server)
 		try_to_freeze();
 		if (server->protocolType == IPV6) {
 			rc = ipv6_connect(&server->addr.sockAddr6,
-					  &server->ssocket);
+					  &server->ssocket, server->noautotune);
 		} else {
 			rc = ipv4_connect(&server->addr.sockAddr,
 					&server->ssocket,
 					server->workstation_RFC1001_name,
-					server->server_RFC1001_name);
+					server->server_RFC1001_name,
+					server->noblocksnd, server->noautotune);
 		}
 		if (rc) {
 			cFYI(1, ("reconnect error %d", rc));
@@ -1192,6 +1197,10 @@ cifs_parse_mount_options(char *options, const char *devname,
 			/* ignore */
 		} else if (strnicmp(data, "rw", 2) == 0) {
 			vol->rw = true;
+		} else if (strnicmp(data, "noblocksend", 11) == 0) {
+			vol->noblocksnd = 1;
+		} else if (strnicmp(data, "noautotune", 10) == 0) {
+			vol->noautotune = 1;
 		} else if ((strnicmp(data, "suid", 4) == 0) ||
 				   (strnicmp(data, "nosuid", 6) == 0) ||
 				   (strnicmp(data, "exec", 4) == 0) ||
@@ -1518,7 +1527,8 @@ static void rfc1002mangle(char *target, char *source, unsigned int length)
 
 static int
 ipv4_connect(struct sockaddr_in *psin_server, struct socket **csocket,
-	     char *netbios_name, char *target_name)
+	     char *netbios_name, char *target_name,
+	     bool noblocksnd, bool noautotune)
 {
 	int rc = 0;
 	int connected = 0;
@@ -1590,11 +1600,16 @@ ipv4_connect(struct sockaddr_in *psin_server, struct socket **csocket,
 		 (*csocket)->sk->sk_sndbuf,
 		 (*csocket)->sk->sk_rcvbuf, (*csocket)->sk->sk_rcvtimeo));
 	(*csocket)->sk->sk_rcvtimeo = 7 * HZ;
+	if (!noblocksnd)
+		(*csocket)->sk->sk_sndtimeo = 3 * HZ;
+
 	/* make the bufsizes depend on wsize/rsize and max requests */
-	if ((*csocket)->sk->sk_sndbuf < (200 * 1024))
-		(*csocket)->sk->sk_sndbuf = 200 * 1024;
-	if ((*csocket)->sk->sk_rcvbuf < (140 * 1024))
-		(*csocket)->sk->sk_rcvbuf = 140 * 1024;
+	if (noautotune) {
+		if ((*csocket)->sk->sk_sndbuf < (200 * 1024))
+			(*csocket)->sk->sk_sndbuf = 200 * 1024;
+		if ((*csocket)->sk->sk_rcvbuf < (140 * 1024))
+			(*csocket)->sk->sk_rcvbuf = 140 * 1024;
+	}
 
 	/* send RFC1001 sessinit */
 	if (psin_server->sin_port == htons(RFC1001_PORT)) {
@@ -1631,7 +1646,7 @@ ipv4_connect(struct sockaddr_in *psin_server, struct socket **csocket,
 			/* sizeof RFC1002_SESSION_REQUEST with no scope */
 			smb_buf->smb_buf_length = 0x81000044;
 			rc = smb_send(*csocket, smb_buf, 0x44,
-				(struct sockaddr *)psin_server);
+				(struct sockaddr *)psin_server, noblocksnd);
 			kfree(ses_init_buf);
 			msleep(1); /* RFC1001 layer in at least one server
 				      requires very short break before negprot
@@ -1651,7 +1666,8 @@ ipv4_connect(struct sockaddr_in *psin_server, struct socket **csocket,
 }
 
 static int
-ipv6_connect(struct sockaddr_in6 *psin_server, struct socket **csocket)
+ipv6_connect(struct sockaddr_in6 *psin_server, struct socket **csocket,
+	     bool noblocksnd)
 {
 	int rc = 0;
 	int connected = 0;
@@ -1720,6 +1736,9 @@ ipv6_connect(struct sockaddr_in6 *psin_server, struct socket **csocket)
 		the default. sock_setsockopt not used because it expects
 		user space buffer */
 	(*csocket)->sk->sk_rcvtimeo = 7 * HZ;
+	if (!noblocksnd)
+		(*csocket)->sk->sk_sndtimeo = 3 * HZ;
+
 
 	return rc;
 }
@@ -1983,11 +2002,14 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb,
 			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);
+			rc = ipv6_connect(&sin_server6, &csocket,
+					volume_info.noblocksnd);
 		} else
 			rc = ipv4_connect(&sin_server, &csocket,
 				  volume_info.source_rfc1001_name,
-				  volume_info.target_rfc1001_name);
+				  volume_info.target_rfc1001_name,
+				  volume_info.noblocksnd,
+				  volume_info.noautotune);
 		if (rc < 0) {
 			cERROR(1, ("Error connecting to IPv4 socket. "
 				   "Aborting operation"));
@@ -2002,6 +2024,8 @@ cifs_mount(struct super_block *sb, struct cifs_sb_info *cifs_sb,
 			sock_release(csocket);
 			goto out;
 		} else {
+			srvTcp->noblocksnd = volume_info.noblocksnd;
+			srvTcp->noautotune = volume_info.noautotune;
 			memcpy(&srvTcp->addr.sockAddr, &sin_server,
 				sizeof(struct sockaddr_in));
 			atomic_set(&srvTcp->inFlight, 0);
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 62d8bd8f14c..ead1a3bb025 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -1824,7 +1824,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
 	pTcon = cifs_sb->tcon;
 
 	pagevec_init(&lru_pvec, 0);
-		cFYI(DBG2, ("rpages: num pages %d", num_pages));
+	cFYI(DBG2, ("rpages: num pages %d", num_pages));
 	for (i = 0; i < num_pages; ) {
 		unsigned contig_pages;
 		struct page *tmp_page;
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index d54fa8aeaea..ff8c68de4a9 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -1361,9 +1361,11 @@ int cifs_rename(struct inode *source_dir, struct dentry *source_dentry,
 					CIFS_MOUNT_MAP_SPECIAL_CHR);
 
 		if (tmprc == 0 && (info_buf_source->UniqueId ==
-				   info_buf_target->UniqueId))
+				   info_buf_target->UniqueId)) {
 			/* same file, POSIX says that this is a noop */
+			rc = 0;
 			goto cifs_rename_exit;
+		}
 	} /* else ... BB we could add the same check for Windows by
 		     checking the UniqueId via FILE_INTERNAL_INFO */
 
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index bf0e6d8e382..ff8243a8fe3 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -161,7 +161,7 @@ void DeleteTconOplockQEntries(struct cifsTconInfo *tcon)
 
 int
 smb_send(struct socket *ssocket, struct smb_hdr *smb_buffer,
-	 unsigned int smb_buf_length, struct sockaddr *sin)
+	 unsigned int smb_buf_length, struct sockaddr *sin, bool noblocksnd)
 {
 	int rc = 0;
 	int i = 0;
@@ -178,7 +178,10 @@ smb_send(struct socket *ssocket, struct smb_hdr *smb_buffer,
 	smb_msg.msg_namelen = sizeof(struct sockaddr);
 	smb_msg.msg_control = NULL;
 	smb_msg.msg_controllen = 0;
-	smb_msg.msg_flags = MSG_DONTWAIT + MSG_NOSIGNAL; /* BB add more flags?*/
+	if (noblocksnd)
+		smb_msg.msg_flags = MSG_DONTWAIT + MSG_NOSIGNAL;
+	else
+		smb_msg.msg_flags = MSG_NOSIGNAL;
 
 	/* smb header is converted in header_assemble. bcc and rest of SMB word
 	   area, and byte area if necessary, is converted to littleendian in
@@ -229,8 +232,8 @@ smb_send(struct socket *ssocket, struct smb_hdr *smb_buffer,
 }
 
 static int
-smb_send2(struct socket *ssocket, struct kvec *iov, int n_vec,
-	  struct sockaddr *sin)
+smb_send2(struct TCP_Server_Info *server, struct kvec *iov, int n_vec,
+	  struct sockaddr *sin, bool noblocksnd)
 {
 	int rc = 0;
 	int i = 0;
@@ -240,6 +243,7 @@ smb_send2(struct socket *ssocket, struct kvec *iov, int n_vec,
 	unsigned int total_len;
 	int first_vec = 0;
 	unsigned int smb_buf_length = smb_buffer->smb_buf_length;
+	struct socket *ssocket = server->ssocket;
 
 	if (ssocket == NULL)
 		return -ENOTSOCK; /* BB eventually add reconnect code here */
@@ -248,7 +252,10 @@ smb_send2(struct socket *ssocket, struct kvec *iov, int n_vec,
 	smb_msg.msg_namelen = sizeof(struct sockaddr);
 	smb_msg.msg_control = NULL;
 	smb_msg.msg_controllen = 0;
-	smb_msg.msg_flags = MSG_DONTWAIT + MSG_NOSIGNAL; /* BB add more flags?*/
+	if (noblocksnd)
+		smb_msg.msg_flags = MSG_DONTWAIT + MSG_NOSIGNAL;
+	else
+		smb_msg.msg_flags = MSG_NOSIGNAL;
 
 	/* smb header is converted in header_assemble. bcc and rest of SMB word
 	   area, and byte area if necessary, is converted to littleendian in
@@ -283,8 +290,11 @@ smb_send2(struct socket *ssocket, struct kvec *iov, int n_vec,
 		if (rc < 0)
 			break;
 
-		if (rc >= total_len) {
-			WARN_ON(rc > total_len);
+		if (rc == total_len) {
+			total_len = 0;
+			break;
+		} else if (rc > total_len) {
+			cERROR(1, ("sent %d requested %d", rc, total_len));
 			break;
 		}
 		if (rc == 0) {
@@ -312,6 +322,16 @@ smb_send2(struct socket *ssocket, struct kvec *iov, int n_vec,
 		i = 0; /* in case we get ENOSPC on the next send */
 	}
 
+	if ((total_len > 0) && (total_len != smb_buf_length + 4)) {
+		cFYI(1, ("partial send (%d remaining), terminating session",
+			total_len));
+		/* If we have only sent part of an SMB then the next SMB
+		   could be taken as the remainder of this one.  We need
+		   to kill the socket so the server throws away the partial
+		   SMB */
+		server->tcpStatus = CifsNeedReconnect;
+	}
+
 	if (rc < 0) {
 		cERROR(1, ("Error %d sending data on socket to server", rc));
 	} else
@@ -518,8 +538,9 @@ SendReceive2(const unsigned int xid, struct cifsSesInfo *ses,
 #ifdef CONFIG_CIFS_STATS2
 	atomic_inc(&ses->server->inSend);
 #endif
-	rc = smb_send2(ses->server->ssocket, iov, n_vec,
-		      (struct sockaddr *) &(ses->server->addr.sockAddr));
+	rc = smb_send2(ses->server, iov, n_vec,
+		      (struct sockaddr *) &(ses->server->addr.sockAddr),
+		       ses->server->noblocksnd);
 #ifdef CONFIG_CIFS_STATS2
 	atomic_dec(&ses->server->inSend);
 	midQ->when_sent = jiffies;
@@ -711,7 +732,8 @@ SendReceive(const unsigned int xid, struct cifsSesInfo *ses,
 	atomic_inc(&ses->server->inSend);
 #endif
 	rc = smb_send(ses->server->ssocket, in_buf, in_buf->smb_buf_length,
-		      (struct sockaddr *) &(ses->server->addr.sockAddr));
+		      (struct sockaddr *) &(ses->server->addr.sockAddr),
+		      ses->server->noblocksnd);
 #ifdef CONFIG_CIFS_STATS2
 	atomic_dec(&ses->server->inSend);
 	midQ->when_sent = jiffies;
@@ -851,7 +873,8 @@ send_nt_cancel(struct cifsTconInfo *tcon, struct smb_hdr *in_buf,
 		return rc;
 	}
 	rc = smb_send(ses->server->ssocket, in_buf, in_buf->smb_buf_length,
-	      (struct sockaddr *) &(ses->server->addr.sockAddr));
+	      (struct sockaddr *) &(ses->server->addr.sockAddr),
+	      ses->server->noblocksnd);
 	up(&ses->server->tcpSem);
 	return rc;
 }
@@ -941,7 +964,8 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifsTconInfo *tcon,
 	atomic_inc(&ses->server->inSend);
 #endif
 	rc = smb_send(ses->server->ssocket, in_buf, in_buf->smb_buf_length,
-		      (struct sockaddr *) &(ses->server->addr.sockAddr));
+		      (struct sockaddr *) &(ses->server->addr.sockAddr),
+		      ses->server->noblocksnd);
 #ifdef CONFIG_CIFS_STATS2
 	atomic_dec(&ses->server->inSend);
 	midQ->when_sent = jiffies;
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 18eaa78ecb4..5dec6d1356c 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -281,7 +281,8 @@ void ext3_abort (struct super_block * sb, const char * function,
 	EXT3_SB(sb)->s_mount_state |= EXT3_ERROR_FS;
 	sb->s_flags |= MS_RDONLY;
 	EXT3_SB(sb)->s_mount_opt |= EXT3_MOUNT_ABORT;
-	journal_abort(EXT3_SB(sb)->s_journal, -EIO);
+	if (EXT3_SB(sb)->s_journal)
+		journal_abort(EXT3_SB(sb)->s_journal, -EIO);
 }
 
 void ext3_warning (struct super_block * sb, const char * function,
@@ -390,11 +391,14 @@ static void ext3_put_super (struct super_block * sb)
 {
 	struct ext3_sb_info *sbi = EXT3_SB(sb);
 	struct ext3_super_block *es = sbi->s_es;
-	int i;
+	int i, err;
 
 	ext3_xattr_put_super(sb);
-	if (journal_destroy(sbi->s_journal) < 0)
+	err = journal_destroy(sbi->s_journal);
+	sbi->s_journal = NULL;
+	if (err < 0)
 		ext3_abort(sb, __func__, "Couldn't clean up the journal");
+
 	if (!(sb->s_flags & MS_RDONLY)) {
 		EXT3_CLEAR_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER);
 		es->s_state = cpu_to_le16(sbi->s_mount_state);
@@ -2386,13 +2390,12 @@ 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/balloc.c b/fs/ext4/balloc.c
index b9821be709b..d2003cdc36a 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -589,21 +589,23 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode,
 	return;
 }
 
-int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
-						s64 nblocks)
+/**
+ * ext4_has_free_blocks()
+ * @sbi:	in-core super block structure.
+ * @nblocks:	number of needed blocks
+ *
+ * Check if filesystem has nblocks free & available for allocation.
+ * On success return 1, return 0 on failure.
+ */
+int ext4_has_free_blocks(struct ext4_sb_info *sbi, s64 nblocks)
 {
-	s64 free_blocks, dirty_blocks;
-	s64 root_blocks = 0;
+	s64 free_blocks, dirty_blocks, root_blocks;
 	struct percpu_counter *fbc = &sbi->s_freeblocks_counter;
 	struct percpu_counter *dbc = &sbi->s_dirtyblocks_counter;
 
 	free_blocks  = percpu_counter_read_positive(fbc);
 	dirty_blocks = percpu_counter_read_positive(dbc);
-
-	if (!capable(CAP_SYS_RESOURCE) &&
-		sbi->s_resuid != current->fsuid &&
-		(sbi->s_resgid == 0 || !in_group_p(sbi->s_resgid)))
-		root_blocks = ext4_r_blocks_count(sbi->s_es);
+	root_blocks = ext4_r_blocks_count(sbi->s_es);
 
 	if (free_blocks - (nblocks + root_blocks + dirty_blocks) <
 						EXT4_FREEBLOCKS_WATERMARK) {
@@ -616,57 +618,32 @@ int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
 		}
 	}
 	/* Check whether we have space after
-	 * accounting for current dirty blocks
+	 * accounting for current dirty blocks & root reserved blocks.
 	 */
-	if (free_blocks < ((root_blocks + nblocks) + dirty_blocks))
-		/* we don't have free space */
-		return -ENOSPC;
+	if (free_blocks >= ((root_blocks + nblocks) + dirty_blocks))
+		return 1;
+
+	/* Hm, nope.  Are (enough) root reserved blocks available? */
+	if (sbi->s_resuid == current->fsuid ||
+	    ((sbi->s_resgid != 0) && in_group_p(sbi->s_resgid)) ||
+	    capable(CAP_SYS_RESOURCE)) {
+		if (free_blocks >= (nblocks + dirty_blocks))
+			return 1;
+	}
 
-	/* Add the blocks to nblocks */
-	percpu_counter_add(dbc, nblocks);
 	return 0;
 }
 
-/**
- * ext4_has_free_blocks()
- * @sbi:	in-core super block structure.
- * @nblocks:	number of neeed blocks
- *
- * Check if filesystem has free blocks available for allocation.
- * Return the number of blocks avaible for allocation for this request
- * On success, return nblocks
- */
-ext4_fsblk_t ext4_has_free_blocks(struct ext4_sb_info *sbi,
+int ext4_claim_free_blocks(struct ext4_sb_info *sbi,
 						s64 nblocks)
 {
-	s64 free_blocks, dirty_blocks;
-	s64 root_blocks = 0;
-	struct percpu_counter *fbc = &sbi->s_freeblocks_counter;
-	struct percpu_counter *dbc = &sbi->s_dirtyblocks_counter;
-
-	free_blocks  = percpu_counter_read_positive(fbc);
-	dirty_blocks = percpu_counter_read_positive(dbc);
-
-	if (!capable(CAP_SYS_RESOURCE) &&
-		sbi->s_resuid != current->fsuid &&
-		(sbi->s_resgid == 0 || !in_group_p(sbi->s_resgid)))
-		root_blocks = ext4_r_blocks_count(sbi->s_es);
-
-	if (free_blocks - (nblocks + root_blocks + dirty_blocks) <
-						EXT4_FREEBLOCKS_WATERMARK) {
-		free_blocks  = percpu_counter_sum(fbc);
-		dirty_blocks = percpu_counter_sum(dbc);
-	}
-	if (free_blocks <= (root_blocks + dirty_blocks))
-		/* we don't have free space */
+	if (ext4_has_free_blocks(sbi, nblocks)) {
+		percpu_counter_add(&sbi->s_dirtyblocks_counter, nblocks);
 		return 0;
-
-	if (free_blocks - (root_blocks + dirty_blocks) < nblocks)
-		return free_blocks - (root_blocks + dirty_blocks);
-	return nblocks;
+	} else
+		return -ENOSPC;
 }
 
-
 /**
  * ext4_should_retry_alloc()
  * @sb:			super block
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 4880cc3e672..b0537c82702 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1003,8 +1003,7 @@ extern ext4_fsblk_t ext4_new_blocks(handle_t *handle, struct inode *inode,
 					ext4_lblk_t iblock, ext4_fsblk_t goal,
 					unsigned long *count, int *errp);
 extern int ext4_claim_free_blocks(struct ext4_sb_info *sbi, s64 nblocks);
-extern ext4_fsblk_t ext4_has_free_blocks(struct ext4_sb_info *sbi,
-					 s64 nblocks);
+extern int ext4_has_free_blocks(struct ext4_sb_info *sbi, s64 nblocks);
 extern void ext4_free_blocks(handle_t *handle, struct inode *inode,
 			ext4_fsblk_t block, unsigned long count, int metadata);
 extern void ext4_free_blocks_sb(handle_t *handle, struct super_block *sb,
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index bdddea14e78..994859df010 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -333,7 +333,8 @@ void ext4_abort(struct super_block *sb, const char *function,
 	EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
 	sb->s_flags |= MS_RDONLY;
 	EXT4_SB(sb)->s_mount_opt |= EXT4_MOUNT_ABORT;
-	jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
+	if (EXT4_SB(sb)->s_journal)
+		jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
 }
 
 void ext4_warning(struct super_block *sb, const char *function,
@@ -442,14 +443,16 @@