Merge git://git.linux-nfs.org/pub/linux/nfs-2.6

* git://git.linux-nfs.org/pub/linux/nfs-2.6: (51 commits)
  nfs: remove nfs_put_link()
  nfs-build-fix-99
  git-nfs-build-fixes
  Merge branch 'odirect'
  NFS: alloc nfs_read/write_data as direct I/O is scheduled
  NFS: Eliminate nfs_get_user_pages()
  NFS: refactor nfs_direct_free_user_pages
  NFS: remove user_addr, user_count, and pos from nfs_direct_req
  NFS: "open code" the NFS direct write rescheduler
  NFS: Separate functions for counting outstanding NFS direct I/Os
  NLM: Fix reclaim races
  NLM: sem to mutex conversion
  locks.c: add the fl_owner to nlm_compare_locks
  NFS: Display the chosen RPCSEC_GSS security flavour in /proc/mounts
  NFS: Split fs/nfs/inode.c
  NFS: Fix typo in nfs_do_clone_mount()
  NFS: Fix compile errors introduced by referrals patches
  NFSv4: Ensure that referral mounts bind to a reserved port
  NFSv4: A root pathname is sent as a zero component4
  NFSv4: Follow a referral
  ...

Documentation/filesystems/automount-support.txt

@@ -19,7 +19,7 @@ following procedure:
 
  (2) Have the follow_link() op do the following steps:
 
-     (a) Call do_kern_mount() to call the appropriate filesystem to set up a
+     (a) Call vfs_kern_mount() to call the appropriate filesystem to set up a
          superblock and gain a vfsmount structure representing it.
 
      (b) Copy the nameidata provided as an argument and substitute the dentry

drivers/usb/core/inode.c

@@ -569,7 +569,7 @@ static int create_special_files (void)
 	ignore_mount = 1;
 
 	/* create the devices special file */
-	retval = simple_pin_fs("usbfs", &usbfs_mount, &usbfs_mount_count);
+	retval = simple_pin_fs(&usb_fs_type, &usbfs_mount, &usbfs_mount_count);
 	if (retval) {
 		err ("Unable to get usbfs mount");
 		goto exit;

fs/9p/vfs_super.c

@@ -256,11 +256,12 @@ static int v9fs_show_options(struct seq_file *m, struct vfsmount *mnt)
 }
 
 static void
-v9fs_umount_begin(struct super_block *sb)
+v9fs_umount_begin(struct vfsmount *vfsmnt, int flags)
 {
-	struct v9fs_session_info *v9ses = sb->s_fs_info;
+	struct v9fs_session_info *v9ses = vfsmnt->mnt_sb->s_fs_info;
 
-	v9fs_session_cancel(v9ses);
+	if (flags & MNT_FORCE)
+		v9fs_session_cancel(v9ses);
 }
 
 static struct super_operations v9fs_super_ops = {

fs/afs/mntpt.c

@@ -203,7 +203,7 @@ static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt)
 
 	/* try and do the mount */
 	kdebug("--- attempting mount %s -o %s ---", devname, options);
-	mnt = do_kern_mount("afs", 0, devname, options);
+	mnt = vfs_kern_mount(&afs_fs_type, 0, devname, options);
 	kdebug("--- mount result %p ---", mnt);
 
 	free_page((unsigned long) devname);

fs/afs/super.c

@@ -48,7 +48,7 @@ static void afs_put_super(struct super_block *sb);
 
 static void afs_destroy_inode(struct inode *inode);
 
-static struct file_system_type afs_fs_type = {
+struct file_system_type afs_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "afs",
 	.get_sb		= afs_get_sb,

fs/afs/super.h

@@ -38,6 +38,8 @@ static inline struct afs_super_info *AFS_FS_S(struct super_block *sb)
 	return sb->s_fs_info;
 }
 
+extern struct file_system_type afs_fs_type;
+
 #endif /* __KERNEL__ */
 
 #endif /* _LINUX_AFS_SUPER_H */

fs/binfmt_misc.c

@@ -55,6 +55,7 @@ typedef struct {
 } Node;
 
 static DEFINE_RWLOCK(entries_lock);
+static struct file_system_type bm_fs_type;
 static struct vfsmount *bm_mnt;
 static int entry_count;
 
@@ -637,7 +638,7 @@ static ssize_t bm_register_write(struct file *file, const char __user *buffer,
 	if (!inode)
 		goto out2;
 
-	err = simple_pin_fs("binfmt_misc", &bm_mnt, &entry_count);
+	err = simple_pin_fs(&bm_fs_type, &bm_mnt, &entry_count);
 	if (err) {
 		iput(inode);
 		inode = NULL;

fs/cifs/cifsfs.c

@@ -403,12 +403,14 @@ static struct quotactl_ops cifs_quotactl_ops = {
 #endif
 
 #ifdef CONFIG_CIFS_EXPERIMENTAL
-static void cifs_umount_begin(struct super_block * sblock)
+static void cifs_umount_begin(struct vfsmount * vfsmnt, int flags)
 {
 	struct cifs_sb_info *cifs_sb;
 	struct cifsTconInfo * tcon;
 
-	cifs_sb = CIFS_SB(sblock);
+	if (!(flags & MNT_FORCE))
+		return;
+	cifs_sb = CIFS_SB(vfsmnt->mnt_sb);
 	if(cifs_sb == NULL)
 		return;
 

fs/configfs/mount.c

@@ -118,7 +118,7 @@ static struct file_system_type configfs_fs_type = {
 
 int configfs_pin_fs(void)
 {
-	return simple_pin_fs("configfs", &configfs_mount,
+	return simple_pin_fs(&configfs_fs_type, &configfs_mount,
 			     &configfs_mnt_count);
 }
 

fs/debugfs/inode.c

@@ -199,7 +199,7 @@ struct dentry *debugfs_create_file(const char *name, mode_t mode,
 
 	pr_debug("debugfs: creating file '%s'\n",name);
 
-	error = simple_pin_fs("debugfs", &debugfs_mount, &debugfs_mount_count);
+	error = simple_pin_fs(&debug_fs_type, &debugfs_mount, &debugfs_mount_count);
 	if (error)
 		goto exit;
 

fs/fuse/inode.c

@@ -198,9 +198,10 @@ struct inode *fuse_iget(struct super_block *sb, unsigned long nodeid,
 	return inode;
 }
 
-static void fuse_umount_begin(struct super_block *sb)
+static void fuse_umount_begin(struct vfsmount *vfsmnt, int flags)
 {
-	fuse_abort_conn(get_fuse_conn_super(sb));
+	if (flags & MNT_FORCE)
+		fuse_abort_conn(get_fuse_conn_super(vfsmnt->mnt_sb));
 }
 
 static void fuse_put_super(struct super_block *sb)

fs/libfs.c

@@ -424,13 +424,13 @@ out:
 
 static DEFINE_SPINLOCK(pin_fs_lock);
 
-int simple_pin_fs(char *name, struct vfsmount **mount, int *count)
+int simple_pin_fs(struct file_system_type *type, struct vfsmount **mount, int *count)
 {
 	struct vfsmount *mnt = NULL;
 	spin_lock(&pin_fs_lock);
 	if (unlikely(!*mount)) {
 		spin_unlock(&pin_fs_lock);
-		mnt = do_kern_mount(name, 0, name, NULL);
+		mnt = vfs_kern_mount(type, 0, type->name, NULL);
 		if (IS_ERR(mnt))
 			return PTR_ERR(mnt);
 		spin_lock(&pin_fs_lock);

fs/lockd/clntlock.c

@@ -147,11 +147,10 @@ u32 nlmclnt_grant(const struct sockaddr_in *addr, const struct nlm_lock *lock)
  * Someone has sent us an SM_NOTIFY. Ensure we bind to the new port number,
  * that we mark locks for reclaiming, and that we bump the pseudo NSM state.
  */
-static inline
-void nlmclnt_prepare_reclaim(struct nlm_host *host, u32 newstate)
+static void nlmclnt_prepare_reclaim(struct nlm_host *host)
 {
+	down_write(&host->h_rwsem);
 	host->h_monitored = 0;
-	host->h_nsmstate = newstate;
 	host->h_state++;
 	host->h_nextrebind = 0;
 	nlm_rebind_host(host);
@@ -164,6 +163,13 @@ void nlmclnt_prepare_reclaim(struct nlm_host *host, u32 newstate)
 	dprintk("NLM: reclaiming locks for host %s", host->h_name);
 }
 
+static void nlmclnt_finish_reclaim(struct nlm_host *host)
+{
+	host->h_reclaiming = 0;
+	up_write(&host->h_rwsem);
+	dprintk("NLM: done reclaiming locks for host %s", host->h_name);
+}
+
 /*
  * Reclaim all locks on server host. We do this by spawning a separate
  * reclaimer thread.
@@ -171,12 +177,10 @@ void nlmclnt_prepare_reclaim(struct nlm_host *host, u32 newstate)
 void
 nlmclnt_recovery(struct nlm_host *host, u32 newstate)
 {
-	if (host->h_reclaiming++) {
-		if (host->h_nsmstate == newstate)
-			return;
-		nlmclnt_prepare_reclaim(host, newstate);
-	} else {
-		nlmclnt_prepare_reclaim(host, newstate);
+	if (host->h_nsmstate == newstate)
+		return;
+	host->h_nsmstate = newstate;
+	if (!host->h_reclaiming++) {
 		nlm_get_host(host);
 		__module_get(THIS_MODULE);
 		if (kernel_thread(reclaimer, host, CLONE_KERNEL) < 0)
@@ -190,6 +194,7 @@ reclaimer(void *ptr)
 	struct nlm_host	  *host = (struct nlm_host *) ptr;
 	struct nlm_wait	  *block;
 	struct file_lock *fl, *next;
+	u32 nsmstate;
 
 	daemonize("%s-reclaim", host->h_name);
 	allow_signal(SIGKILL);
@@ -199,19 +204,25 @@ reclaimer(void *ptr)
 	lock_kernel();
 	lockd_up();
 
+	nlmclnt_prepare_reclaim(host);
 	/* First, reclaim all locks that have been marked. */
 restart:
+	nsmstate = host->h_nsmstate;
 	list_for_each_entry_safe(fl, next, &host->h_reclaim, fl_u.nfs_fl.list) {
 		list_del_init(&fl->fl_u.nfs_fl.list);
 
 		if (signalled())
 			continue;
-		if (nlmclnt_reclaim(host, fl) == 0)
-			list_add_tail(&fl->fl_u.nfs_fl.list, &host->h_granted);
-		goto restart;
+		if (nlmclnt_reclaim(host, fl) != 0)
+			continue;
+		list_add_tail(&fl->fl_u.nfs_fl.list, &host->h_granted);
+		if (host->h_nsmstate != nsmstate) {
+			/* Argh! The server rebooted again! */
+			list_splice_init(&host->h_granted, &host->h_reclaim);
+			goto restart;
+		}
 	}
-
-	host->h_reclaiming = 0;
+	nlmclnt_finish_reclaim(host);
 
 	/* Now, wake up all processes that sleep on a blocked lock */
 	list_for_each_entry(block, &nlm_blocked, b_list) {

fs/lockd/clntproc.c

@@ -508,7 +508,10 @@ nlmclnt_lock(struct nlm_rqst *req, struct file_lock *fl)
 	}
 
 	block = nlmclnt_prepare_block(host, fl);
+again:
 	for(;;) {
+		/* Reboot protection */
+		fl->fl_u.nfs_fl.state = host->h_state;
 		status = nlmclnt_call(req, NLMPROC_LOCK);
 		if (status < 0)
 			goto out_unblock;
@@ -531,10 +534,16 @@ nlmclnt_lock(struct nlm_rqst *req, struct file_lock *fl)
 	}
 
 	if (resp->status == NLM_LCK_GRANTED) {
-		fl->fl_u.nfs_fl.state = host->h_state;
+		down_read(&host->h_rwsem);
+		/* Check whether or not the server has rebooted */
+		if (fl->fl_u.nfs_fl.state != host->h_state) {
+			up_read(&host->h_rwsem);
+			goto again;
+		}
 		fl->fl_flags |= FL_SLEEP;
 		/* Ensure the resulting lock will get added to granted list */
 		do_vfs_lock(fl);
+		up_read(&host->h_rwsem);
 	}
 	status = nlm_stat_to_errno(resp->status);
 out_unblock:
@@ -596,6 +605,7 @@ nlmclnt_reclaim(struct nlm_host *host, struct file_lock *fl)
 static int
 nlmclnt_unlock(struct nlm_rqst *req, struct file_lock *fl)
 {
+	struct nlm_host	*host = req->a_host;
 	struct nlm_res	*resp = &req->a_res;
 	int		status;
 
@@ -604,7 +614,9 @@ nlmclnt_unlock(struct nlm_rqst *req, struct file_lock *fl)
 	 * request, or to deny it with NLM_LCK_DENIED_GRACE_PERIOD. In either
 	 * case, we want to unlock.
 	 */
+	down_read(&host->h_rwsem);
 	do_vfs_lock(fl);
+	up_read(&host->h_rwsem);
 
 	if (req->a_flags & RPC_TASK_ASYNC)
 		return nlm_async_call(req, NLMPROC_UNLOCK, &nlmclnt_unlock_ops);

fs/lockd/host.c

@@ -112,11 +112,12 @@ nlm_lookup_host(int server, struct sockaddr_in *sin,
 	host->h_version    = version;
 	host->h_proto      = proto;
 	host->h_rpcclnt    = NULL;
-	init_MUTEX(&host->h_sema);
+	mutex_init(&host->h_mutex);
 	host->h_nextrebind = jiffies + NLM_HOST_REBIND;
 	host->h_expires    = jiffies + NLM_HOST_EXPIRE;
 	atomic_set(&host->h_count, 1);
 	init_waitqueue_head(&host->h_gracewait);
+	init_rwsem(&host->h_rwsem);
 	host->h_state      = 0;			/* pseudo NSM state */
 	host->h_nsmstate   = 0;			/* real NSM state */
 	host->h_server	   = server;
@@ -172,7 +173,7 @@ nlm_bind_host(struct nlm_host *host)
 			(unsigned)ntohl(host->h_addr.sin_addr.s_addr));
 
 	/* Lock host handle */
-	down(&host->h_sema);
+	mutex_lock(&host->h_mutex);
 
 	/* If we've already created an RPC client, check whether
 	 * RPC rebind is required
@@ -204,12 +205,12 @@ nlm_bind_host(struct nlm_host *host)
 		host->h_rpcclnt = clnt;
 	}
 
-	up(&host->h_sema);
+	mutex_unlock(&host->h_mutex);
 	return clnt;
 
 forgetit:
 	printk("lockd: couldn't create RPC handle for %s\n", host->h_name);
-	up(&host->h_sema);
+	mutex_unlock(&host->h_mutex);
 	return NULL;
 }
 

fs/namespace.c

@@ -585,8 +585,8 @@ static int do_umount(struct vfsmount *mnt, int flags)
 	 */
 
 	lock_kernel();
-	if ((flags & MNT_FORCE) && sb->s_op->umount_begin)
-		sb->s_op->umount_begin(sb);
+	if (sb->s_op->umount_begin)
+		sb->s_op->umount_begin(mnt, flags);
 	unlock_kernel();
 
 	/*
@@ -1171,6 +1171,40 @@ static void expire_mount(struct vfsmount *mnt, struct list_head *mounts,
 	}
 }
 
+/*
+ * go through the vfsmounts we've just consigned to the graveyard to
+ * - check that they're still dead
+ * - delete the vfsmount from the appropriate namespace under lock
+ * - dispose of the corpse
+ */
+static void expire_mount_list(struct list_head *graveyard, struct list_head *mounts)
+{
+	struct namespace *namespace;
+	struct vfsmount *mnt;
+
+	while (!list_empty(graveyard)) {
+		LIST_HEAD(umounts);
+		mnt = list_entry(graveyard->next, struct vfsmount, mnt_expire);
+		list_del_init(&mnt->mnt_expire);
+
+		/* don't do anything if the namespace is dead - all the
+		 * vfsmounts from it are going away anyway */
+		namespace = mnt->mnt_namespace;
+		if (!namespace || !namespace->root)
+			continue;
+		get_namespace(namespace);
+
+		spin_unlock(&vfsmount_lock);
+		down_write(&namespace_sem);
+		expire_mount(mnt, mounts, &umounts);
+		up_write(&namespace_sem);
+		release_mounts(&umounts);
+		mntput(mnt);
+		put_namespace(namespace);
+		spin_lock(&vfsmount_lock);
+	}
+}
+
 /*
  * process a list of expirable mountpoints with the intent of discarding any
  * mountpoints that aren't in use and haven't been touched since last we came
@@ -1178,7 +1212,6 @@ static void expire_mount(struct vfsmount *mnt, struct list_head *mounts,
  */
 void mark_mounts_for_expiry(struct list_head *mounts)
 {
-	struct namespace *namespace;
 	struct vfsmount *mnt, *next;
 	LIST_HEAD(graveyard);
 
@@ -1202,38 +1235,79 @@ void mark_mounts_for_expiry(struct list_head *mounts)
 		list_move(&mnt->mnt_expire, &graveyard);
 	}
 
-	/*
-	 * go through the vfsmounts we've just consigned to the graveyard to
-	 * - check that they're still dead
-	 * - delete the vfsmount from the appropriate namespace under lock
-	 * - dispose of the corpse
-	 */
-	while (!list_empty(&graveyard)) {
-		LIST_HEAD(umounts);
-		mnt = list_entry(graveyard.next, struct vfsmount, mnt_expire);
-		list_del_init(&mnt->mnt_expire);
+	expire_mount_list(&graveyard, mounts);
 
-		/* don't do anything if the namespace is dead - all the
-		 * vfsmounts from it are going away anyway */
-		namespace = mnt->mnt_namespace;
-		if (!namespace || !namespace->root)
+	spin_unlock(&vfsmount_lock);
+}
+
+EXPORT_SYMBOL_GPL(mark_mounts_for_expiry);
+
+/*
+ * Ripoff of 'select_parent()'
+ *
+ * search the list of submounts for a given mountpoint, and move any
+ * shrinkable submounts to the 'graveyard' list.
+ */
+static int select_submounts(struct vfsmount *parent, struct list_head *graveyard)
+{
+	struct vfsmount *this_parent = parent;
+	struct list_head *next;
+	int found = 0;
+
+repeat:
+	next = this_parent->mnt_mounts.next;
+resume:
+	while (next != &this_parent->mnt_mounts) {
+		struct list_head *tmp = next;
+		struct vfsmount *mnt = list_entry(tmp, struct vfsmount, mnt_child);
+
+		next = tmp->next;
+		if (!(mnt->mnt_flags & MNT_SHRINKABLE))
 			continue;
-		get_namespace(namespace);
+		/*
+		 * Descend a level if the d_mounts list is non-empty.
+		 */
+		if (!list_empty(&mnt->mnt_mounts)) {
+			this_parent = mnt;
+			goto repeat;
+		}
 
-		spin_unlock(&vfsmount_lock);
-		down_write(&namespace_sem);
-		expire_mount(mnt, mounts, &umounts);
-		up_write(&namespace_sem);
-		release_mounts(&umounts);
-		mntput(mnt);
-		put_namespace(namespace);
-		spin_lock(&vfsmount_lock);
+		if (!propagate_mount_busy(mnt, 1)) {
+			mntget(mnt);
+			list_move_tail(&mnt->mnt_expire, graveyard);
+			found++;
+		}
 	}
+	/*
+	 * All done at this level ... ascend and resume the search
+	 */
+	if (this_parent != parent) {
+		next = this_parent->mnt_child.next;
+		this_parent = this_parent->mnt_parent;
+		goto resume;
+	}
+	return found;
+}
+
+/*
+ * process a list of expirable mountpoints with the intent of discarding any
+ * submounts of a specific parent mountpoint
+ */
+void shrink_submounts(struct vfsmount *mountpoint, struct list_head *mounts)
+{
+	LIST_HEAD(graveyard);
+	int found;
+
+	spin_lock(&vfsmount_lock);
+
+	/* extract submounts of 'mountpoint' from the expiration list */
+	while ((found = select_submounts(mountpoint, &graveyard)) != 0)
+		expire_mount_list(&graveyard, mounts);
 
 	spin_unlock(&vfsmount_lock);
 }
 
-EXPORT_SYMBOL_GPL(mark_mounts_for_expiry);
+EXPORT_SYMBOL_GPL(shrink_submounts);
 
 /*
  * Some copy_from_user() implementations do not return the exact number of

fs/nfs/Makefile

@@ -4,14 +4,16 @@
 
 obj-$(CONFIG_NFS_FS) += nfs.o
 
-nfs-y 			:= dir.o file.o inode.o nfs2xdr.o pagelist.o \
-			   proc.o read.o symlink.o unlink.o write.o
+nfs-y 			:= dir.o file.o inode.o super.o nfs2xdr.o pagelist.o \
+			   proc.o read.o symlink.o unlink.o write.o \
+			   namespace.o
 nfs-$(CONFIG_ROOT_NFS)	+= nfsroot.o mount_clnt.o      
 nfs-$(CONFIG_NFS_V3)	+= nfs3proc.o nfs3xdr.o
 nfs-$(CONFIG_NFS_V3_ACL)	+= nfs3acl.o
 nfs-$(CONFIG_NFS_V4)	+= nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o \
 			   delegation.o idmap.o \
-			   callback.o callback_xdr.o callback_proc.o
+			   callback.o callback_xdr.o callback_proc.o \
+			   nfs4namespace.o
 nfs-$(CONFIG_NFS_DIRECTIO) += direct.o
 nfs-$(CONFIG_SYSCTL) += sysctl.o
 nfs-objs		:= $(nfs-y)

fs/nfs/callback.c

@@ -182,8 +182,6 @@ static int nfs_callback_authenticate(struct svc_rqst *rqstp)
 /*
  * Define NFS4 callback program
  */
-extern struct svc_version nfs4_callback_version1;
-
 static struct svc_version *nfs4_callback_version[] = {
 	[1] = &nfs4_callback_version1,
 };

fs/nfs/callback_xdr.c

@@ -202,7 +202,7 @@ static unsigned decode_recall_args(struct svc_rqst *rqstp, struct xdr_stream *xd
 	status = decode_fh(xdr, &args->fh);
 out:
 	dprintk("%s: exit with status = %d\n", __FUNCTION__, status);
-	return 0;
+	return status;
 }
 
 static unsigned encode_string(struct xdr_stream *xdr, unsigned int len, const char *str)

fs/nfs/dir.c

@@ -528,7 +528,7 @@ static int nfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
 
 	lock_kernel();
 
-	res = nfs_revalidate_inode(NFS_SERVER(inode), inode);
+	res = nfs_revalidate_mapping(inode, filp->f_mapping);
 	if (res < 0) {
 		unlock_kernel();
 		return res;
@@ -868,6 +868,17 @@ int nfs_is_exclusive_create(struct inode *dir, struct nameidata *nd)
 	return (nd->intent.open.flags & O_EXCL) != 0;
 }
 
+static inline int nfs_reval_fsid(struct inode *dir,
+		struct nfs_fh *fh, struct nfs_fattr *fattr)
+{
+	struct nfs_server *server = NFS_SERVER(dir);
+
+	if (!nfs_fsid_equal(&server->fsid, &fattr->fsid))
+		/* Revalidate fsid on root dir */
+		return __nfs_revalidate_inode(server, dir->i_sb->s_root->d_inode);
+	return 0;
+}
+
 static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd)
 {
 	struct dentry *res;
@@ -900,6 +911,11 @@ static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, stru
 		res = ERR_PTR(error);
 		goto out_unlock;
 	}
+	error = nfs_reval_fsid(dir, &fhandle, &fattr);
+	if (error < 0) {
+		res = ERR_PTR(error);
+		goto out_unlock;
+	}
 	inode = nfs_fhget(dentry->d_sb, &fhandle, &fattr);
 	res = (struct dentry *)inode;
 	if (IS_ERR(res))