Merge with rsync://fileserver/linux

18 files changed, 238 insertions, 247 deletions

diff --git a/fs/Kconfig b/fs/Kconfig
index 8d50a610c0e0..f93fd41b025d 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -29,6 +29,7 @@ config EXT2_FS_XATTR
 config EXT2_FS_POSIX_ACL
 	bool "Ext2 POSIX Access Control Lists"
 	depends on EXT2_FS_XATTR
+	select FS_POSIX_ACL
 	help
 	  Posix Access Control Lists (ACLs) support permissions for users and
 	  groups beyond the owner/group/world scheme.
@@ -114,6 +115,7 @@ config EXT3_FS_XATTR
 config EXT3_FS_POSIX_ACL
 	bool "Ext3 POSIX Access Control Lists"
 	depends on EXT3_FS_XATTR
+	select FS_POSIX_ACL
 	help
 	  Posix Access Control Lists (ACLs) support permissions for users and
 	  groups beyond the owner/group/world scheme.
@@ -241,6 +243,7 @@ config REISERFS_FS_XATTR
 config REISERFS_FS_POSIX_ACL
 	bool "ReiserFS POSIX Access Control Lists"
 	depends on REISERFS_FS_XATTR
+	select FS_POSIX_ACL
 	help
 	  Posix Access Control Lists (ACLs) support permissions for users and
 	  groups beyond the owner/group/world scheme.
@@ -274,6 +277,7 @@ config JFS_FS
 config JFS_POSIX_ACL
 	bool "JFS POSIX Access Control Lists"
 	depends on JFS_FS
+	select FS_POSIX_ACL
 	help
 	  Posix Access Control Lists (ACLs) support permissions for users and
 	  groups beyond the owner/group/world scheme.
@@ -318,8 +322,7 @@ config FS_POSIX_ACL
 # 	Never use this symbol for ifdefs.
 #
 	bool
-	depends on EXT2_FS_POSIX_ACL || EXT3_FS_POSIX_ACL || JFS_POSIX_ACL || REISERFS_FS_POSIX_ACL || NFSD_V4
-	default y
+	default n
 
 source "fs/xfs/Kconfig"
 
@@ -1430,6 +1433,7 @@ config NFSD_V4
 	select NFSD_TCP
 	select CRYPTO_MD5
 	select CRYPTO
+	select FS_POSIX_ACL
 	help
 	  If you would like to include the NFSv4 server as well as the NFSv2
 	  and NFSv3 servers, say Y here.  This feature is experimental, and
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index fa2348dcd671..3df86285a1c7 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -231,8 +231,8 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry,
 		int type = (notify == NFY_MOUNT ?
 			autofs_ptype_missing : autofs_ptype_expire_multi);
 
-		DPRINTK(("new wait id = 0x%08lx, name = %.*s, nfy=%d\n",
-			(unsigned long) wq->wait_queue_token, wq->len, wq->name, notify));
+		DPRINTK("new wait id = 0x%08lx, name = %.*s, nfy=%d\n",
+			(unsigned long) wq->wait_queue_token, wq->len, wq->name, notify);
 
 		/* autofs4_notify_daemon() may block */
 		autofs4_notify_daemon(sbi, wq, type);
diff --git a/fs/bio.c b/fs/bio.c
index 3a1472acc361..ca8f7a850fe3 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -52,7 +52,7 @@ struct biovec_slab {
  */
 
 #define BV(x) { .nr_vecs = x, .name = "biovec-"__stringify(x) }
-static struct biovec_slab bvec_slabs[BIOVEC_NR_POOLS] = {
+static struct biovec_slab bvec_slabs[BIOVEC_NR_POOLS] __read_mostly = {
 	BV(1), BV(4), BV(16), BV(64), BV(128), BV(BIO_MAX_PAGES),
 };
 #undef BV
diff --git a/fs/buffer.c b/fs/buffer.c
index 561e63a14966..6a25d7df89b1 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -513,8 +513,8 @@ static void free_more_memory(void)
  */
 static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
 {
-	static DEFINE_SPINLOCK(page_uptodate_lock);
 	unsigned long flags;
+	struct buffer_head *first;
 	struct buffer_head *tmp;
 	struct page *page;
 	int page_uptodate = 1;
@@ -536,7 +536,9 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
 	 * two buffer heads end IO at almost the same time and both
 	 * decide that the page is now completely done.
 	 */
-	spin_lock_irqsave(&page_uptodate_lock, flags);
+	first = page_buffers(page);
+	local_irq_save(flags);
+	bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
 	clear_buffer_async_read(bh);
 	unlock_buffer(bh);
 	tmp = bh;
@@ -549,7 +551,8 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
 		}
 		tmp = tmp->b_this_page;
 	} while (tmp != bh);
-	spin_unlock_irqrestore(&page_uptodate_lock, flags);
+	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
+	local_irq_restore(flags);
 
 	/*
 	 * If none of the buffers had errors and they are all
@@ -561,7 +564,8 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
 	return;
 
 still_busy:
-	spin_unlock_irqrestore(&page_uptodate_lock, flags);
+	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
+	local_irq_restore(flags);
 	return;
 }
 
@@ -572,8 +576,8 @@ still_busy:
 void end_buffer_async_write(struct buffer_head *bh, int uptodate)
 {
 	char b[BDEVNAME_SIZE];
-	static DEFINE_SPINLOCK(page_uptodate_lock);
 	unsigned long flags;
+	struct buffer_head *first;
 	struct buffer_head *tmp;
 	struct page *page;
 
@@ -594,7 +598,10 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate)
 		SetPageError(page);
 	}
 
-	spin_lock_irqsave(&page_uptodate_lock, flags);
+	first = page_buffers(page);
+	local_irq_save(flags);
+	bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
+
 	clear_buffer_async_write(bh);
 	unlock_buffer(bh);
 	tmp = bh->b_this_page;
@@ -605,12 +612,14 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate)
 		}
 		tmp = tmp->b_this_page;
 	}
-	spin_unlock_irqrestore(&page_uptodate_lock, flags);
+	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
+	local_irq_restore(flags);
 	end_page_writeback(page);
 	return;
 
 still_busy:
-	spin_unlock_irqrestore(&page_uptodate_lock, flags);
+	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
+	local_irq_restore(flags);
 	return;
 }
 
diff --git a/fs/dcookies.c b/fs/dcookies.c
index 581aac959cd3..02aa0ddc582a 100644
--- a/fs/dcookies.c
+++ b/fs/dcookies.c
@@ -94,12 +94,10 @@ static struct dcookie_struct * alloc_dcookie(struct dentry * dentry,
 	if (!dcs)
 		return NULL;
 
-	atomic_inc(&dentry->d_count);
-	atomic_inc(&vfsmnt->mnt_count);
 	dentry->d_cookie = dcs;
 
-	dcs->dentry = dentry;
-	dcs->vfsmnt = vfsmnt;
+	dcs->dentry = dget(dentry);
+	dcs->vfsmnt = mntget(vfsmnt);
 	hash_dcookie(dcs);
 
 	return dcs;
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 0b2db4f618cb..9989fdcf4d5a 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -2663,7 +2663,7 @@ static int ext3_do_update_inode(handle_t *handle,
 	} else for (block = 0; block < EXT3_N_BLOCKS; block++)
 		raw_inode->i_block[block] = ei->i_data[block];
 
-	if (EXT3_INODE_SIZE(inode->i_sb) > EXT3_GOOD_OLD_INODE_SIZE)
+	if (ei->i_extra_isize)
 		raw_inode->i_extra_isize = cpu_to_le16(ei->i_extra_isize);
 
 	BUFFER_TRACE(bh, "call ext3_journal_dirty_metadata");
diff --git a/fs/hppfs/hppfs_kern.c b/fs/hppfs/hppfs_kern.c
index f8e0cbd0cb60..6f553e17c375 100644
--- a/fs/hppfs/hppfs_kern.c
+++ b/fs/hppfs/hppfs_kern.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/fs.h>
+#include <linux/file.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/slab.h>
@@ -491,7 +492,7 @@ static int hppfs_open(struct inode *inode, struct file *file)
 		fd = open_host_sock(host_file, &filter);
 		if(fd > 0){
 			data->contents = hppfs_get_data(fd, filter,
-							&data->proc_file,
+							data->proc_file,
 							file, &data->len);
 			if(!IS_ERR(data->contents))
 				data->host_fd = fd;
@@ -543,7 +544,7 @@ static int hppfs_dir_open(struct inode *inode, struct file *file)
 static loff_t hppfs_llseek(struct file *file, loff_t off, int where)
 {
 	struct hppfs_private *data = file->private_data;
-	struct file *proc_file = &data->proc_file;
+	struct file *proc_file = data->proc_file;
 	loff_t (*llseek)(struct file *, loff_t, int);
 	loff_t ret;
 
@@ -586,7 +587,7 @@ static int hppfs_filldir(void *d, const char *name, int size,
 static int hppfs_readdir(struct file *file, void *ent, filldir_t filldir)
 {
 	struct hppfs_private *data = file->private_data;
-	struct file *proc_file = &data->proc_file;
+	struct file *proc_file = data->proc_file;
 	int (*readdir)(struct file *, void *, filldir_t);
 	struct hppfs_dirent dirent = ((struct hppfs_dirent)
 		                      { .vfs_dirent  	= ent,
diff --git a/fs/inode.c b/fs/inode.c
index 1f9a3a2b89bc..6d695037a0a3 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1052,7 +1052,7 @@ static void generic_forget_inode(struct inode *inode)
  * inode when the usage count drops to zero, and
  * i_nlink is zero.
  */
-static void generic_drop_inode(struct inode *inode)
+void generic_drop_inode(struct inode *inode)
 {
 	if (!inode->i_nlink)
 		generic_delete_inode(inode);
@@ -1060,6 +1060,8 @@ static void generic_drop_inode(struct inode *inode)
 		generic_forget_inode(inode);
 }
 
+EXPORT_SYMBOL_GPL(generic_drop_inode);
+
 /*
  * Called when we're dropping the last reference
  * to an inode. 
diff --git a/fs/ioprio.c b/fs/ioprio.c
index 663e420636d6..97e1f088ba00 100644
--- a/fs/ioprio.c
+++ b/fs/ioprio.c
@@ -43,7 +43,7 @@ static int set_task_ioprio(struct task_struct *task, int ioprio)
 	return 0;
 }
 
-asmlinkage int sys_ioprio_set(int which, int who, int ioprio)
+asmlinkage long sys_ioprio_set(int which, int who, int ioprio)
 {
 	int class = IOPRIO_PRIO_CLASS(ioprio);
 	int data = IOPRIO_PRIO_DATA(ioprio);
@@ -115,7 +115,7 @@ asmlinkage int sys_ioprio_set(int which, int who, int ioprio)
 	return ret;
 }
 
-asmlinkage int sys_ioprio_get(int which, int who)
+asmlinkage long sys_ioprio_get(int which, int who)
 {
 	struct task_struct *g, *p;
 	struct user_struct *user;
diff --git a/fs/locks.c b/fs/locks.c
index a0bc03495bd4..29fa5da6c117 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1276,7 +1276,7 @@ int fcntl_getlease(struct file *filp)
  */
 static int __setlease(struct file *filp, long arg, struct file_lock **flp)
 {
-	struct file_lock *fl, **before, **my_before = NULL, *lease = *flp;
+	struct file_lock *fl, **before, **my_before = NULL, *lease;
 	struct dentry *dentry = filp->f_dentry;
 	struct inode *inode = dentry->d_inode;
 	int error, rdlease_count = 0, wrlease_count = 0;
@@ -1287,6 +1287,8 @@ static int __setlease(struct file *filp, long arg, struct file_lock **flp)
 	if (!flp || !(*flp) || !(*flp)->fl_lmops || !(*flp)->fl_lmops->fl_break)
 		goto out;
 
+	lease = *flp;
+
 	error = -EAGAIN;
 	if ((arg == F_RDLCK) && (atomic_read(&inode->i_writecount) > 0))
 		goto out;
diff --git a/fs/namei.c b/fs/namei.c
index fa8df81ce8ca..1d93cb4f7c5f 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -314,7 +314,7 @@ void path_release(struct nameidata *nd)
 void path_release_on_umount(struct nameidata *nd)
 {
 	dput(nd->dentry);
-	_mntput(nd->mnt);
+	mntput_no_expire(nd->mnt);
 }
 
 /*
diff --git a/fs/namespace.c b/fs/namespace.c
index 208c079e9fdb..587eb0d707ee 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -61,7 +61,7 @@ struct vfsmount *alloc_vfsmnt(const char *name)
 		INIT_LIST_HEAD(&mnt->mnt_child);
 		INIT_LIST_HEAD(&mnt->mnt_mounts);
 		INIT_LIST_HEAD(&mnt->mnt_list);
-		INIT_LIST_HEAD(&mnt->mnt_fslink);
+		INIT_LIST_HEAD(&mnt->mnt_expire);
 		if (name) {
 			int size = strlen(name)+1;
 			char *newname = kmalloc(size, GFP_KERNEL);
@@ -165,8 +165,8 @@ clone_mnt(struct vfsmount *old, struct dentry *root)
 		/* stick the duplicate mount on the same expiry list
 		 * as the original if that was on one */
 		spin_lock(&vfsmount_lock);
-		if (!list_empty(&old->mnt_fslink))
-			list_add(&mnt->mnt_fslink, &old->mnt_fslink);
+		if (!list_empty(&old->mnt_expire))
+			list_add(&mnt->mnt_expire, &old->mnt_expire);
 		spin_unlock(&vfsmount_lock);
 	}
 	return mnt;
@@ -345,12 +345,13 @@ static void umount_tree(struct vfsmount *mnt)
 	for (p = mnt; p; p = next_mnt(p, mnt)) {
 		list_del(&p->mnt_list);
 		list_add(&p->mnt_list, &kill);
+		p->mnt_namespace = NULL;
 	}
 
 	while (!list_empty(&kill)) {
 		mnt = list_entry(kill.next, struct vfsmount, mnt_list);
 		list_del_init(&mnt->mnt_list);
-		list_del_init(&mnt->mnt_fslink);
+		list_del_init(&mnt->mnt_expire);
 		if (mnt->mnt_parent == mnt) {
 			spin_unlock(&vfsmount_lock);
 		} else {
@@ -644,7 +645,7 @@ static int do_loopback(struct nameidata *nd, char *old_name, int recurse)
 	if (mnt) {
 		/* stop bind mounts from expiring */
 		spin_lock(&vfsmount_lock);
-		list_del_init(&mnt->mnt_fslink);
+		list_del_init(&mnt->mnt_expire);
 		spin_unlock(&vfsmount_lock);
 
 		err = graft_tree(mnt, nd);
@@ -743,7 +744,7 @@ static int do_move_mount(struct nameidata *nd, char *old_name)
 
 	/* if the mount is moved, it should no longer be expire
 	 * automatically */
-	list_del_init(&old_nd.mnt->mnt_fslink);
+	list_del_init(&old_nd.mnt->mnt_expire);
 out2:
 	spin_unlock(&vfsmount_lock);
 out1:
@@ -807,12 +808,13 @@ int do_add_mount(struct vfsmount *newmnt, struct nameidata *nd,
 		goto unlock;
 
 	newmnt->mnt_flags = mnt_flags;
+	newmnt->mnt_namespace = current->namespace;
 	err = graft_tree(newmnt, nd);
 
 	if (err == 0 && fslist) {
 		/* add to the specified expiration list */
 		spin_lock(&vfsmount_lock);
-		list_add_tail(&newmnt->mnt_fslink, fslist);
+		list_add_tail(&newmnt->mnt_expire, fslist);
 		spin_unlock(&vfsmount_lock);
 	}
 
@@ -824,6 +826,54 @@ unlock:
 
 EXPORT_SYMBOL_GPL(do_add_mount);
 
+static void expire_mount(struct vfsmount *mnt, struct list_head *mounts)
+{
+	spin_lock(&vfsmount_lock);
+
+	/*
+	 * Check if mount is still attached, if not, let whoever holds it deal
+	 * with the sucker
+	 */
+	if (mnt->mnt_parent == mnt) {
+		spin_unlock(&vfsmount_lock);
+		return;
+	}
+
+	/*
+	 * Check that it is still dead: the count should now be 2 - as
+	 * contributed by the vfsmount parent and the mntget above
+	 */
+	if (atomic_read(&mnt->mnt_count) == 2) {
+		struct nameidata old_nd;
+
+		/* delete from the namespace */
+		list_del_init(&mnt->mnt_list);
+		mnt->mnt_namespace = NULL;
+		detach_mnt(mnt, &old_nd);
+		spin_unlock(&vfsmount_lock);
+		path_release(&old_nd);
+
+		/*
+		 * Now lay it to rest if this was the last ref on the superblock
+		 */
+		if (atomic_read(&mnt->mnt_sb->s_active) == 1) {
+			/* last instance - try to be smart */
+			lock_kernel();
+			DQUOT_OFF(mnt->mnt_sb);
+			acct_auto_close(mnt->mnt_sb);
+			unlock_kernel();
+		}
+		mntput(mnt);
+	} else {
+		/*
+		 * Someone brought it back to life whilst we didn't have any
+		 * locks held so return it to the expiration list
+		 */
+		list_add_tail(&mnt->mnt_expire, mounts);
+		spin_unlock(&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
@@ -846,13 +896,13 @@ void mark_mounts_for_expiry(struct list_head *mounts)
 	 * - still marked for expiry (marked on the last call here; marks are
 	 *   cleared by mntput())
 	 */
-	list_for_each_entry_safe(mnt, next, mounts, mnt_fslink) {
+	list_for_each_entry_safe(mnt, next, mounts, mnt_expire) {
 		if (!xchg(&mnt->mnt_expiry_mark, 1) ||
 		    atomic_read(&mnt->mnt_count) != 1)
 			continue;
 
 		mntget(mnt);
-		list_move(&mnt->mnt_fslink, &graveyard);
+		list_move(&mnt->mnt_expire, &graveyard);
 	}
 
 	/*
@@ -862,61 +912,19 @@ void mark_mounts_for_expiry(struct list_head *mounts)
 	 * - dispose of the corpse
 	 */
 	while (!list_empty(&graveyard)) {
-		mnt = list_entry(graveyard.next, struct vfsmount, mnt_fslink);
-		list_del_init(&mnt->mnt_fslink);
+		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 || atomic_read(&namespace->count) <= 0)
+		if (!namespace || !namespace->root)
 			continue;
 		get_namespace(namespace);
 
 		spin_unlock(&vfsmount_lock);
 		down_write(&namespace->sem);
-		spin_lock(&vfsmount_lock);
-
-		/* check that it is still dead: the count should now be 2 - as
-		 * contributed by the vfsmount parent and the mntget above */
-		if (atomic_read(&mnt->mnt_count) == 2) {
-			struct vfsmount *xdmnt;
-			struct dentry *xdentry;
-
-			/* delete from the namespace */
-			list_del_init(&mnt->mnt_list);
-			list_del_init(&mnt->mnt_child);
-			list_del_init(&mnt->mnt_hash);
-			mnt->mnt_mountpoint->d_mounted--;
-
-			xdentry = mnt->mnt_mountpoint;
-			mnt->mnt_mountpoint = mnt->mnt_root;
-			xdmnt = mnt->mnt_parent;
-			mnt->mnt_parent = mnt;
-
-			spin_unlock(&vfsmount_lock);
-
-			mntput(xdmnt);
-			dput(xdentry);
-
-			/* now lay it to rest if this was the last ref on the
-			 * superblock */
-			if (atomic_read(&mnt->mnt_sb->s_active) == 1) {
-				/* last instance - try to be smart */
-				lock_kernel();
-				DQUOT_OFF(mnt->mnt_sb);
-				acct_auto_close(mnt->mnt_sb);
-				unlock_kernel();
-			}
-
-			mntput(mnt);
-		} else {
-			/* someone brought it back to life whilst we didn't
-			 * have any locks held so return it to the expiration
-			 * list */
-			list_add_tail(&mnt->mnt_fslink, mounts);
-			spin_unlock(&vfsmount_lock);
-		}
-
+		expire_mount(mnt, mounts);
 		up_write(&namespace->sem);
 
 		mntput(mnt);
@@ -1449,16 +1457,12 @@ void __init mnt_init(unsigned long mempages)
 
 void __put_namespace(struct namespace *namespace)
 {
-	struct vfsmount *mnt;
-
+	struct vfsmount *root = namespace->root;
+	namespace->root = NULL;
+	spin_unlock(&vfsmount_lock);
 	down_write(&namespace->sem);
 	spin_lock(&vfsmount_lock);
-
-	list_for_each_entry(mnt, &namespace->list, mnt_list) {
-		mnt->mnt_namespace = NULL;
-	}
-
-	umount_tree(namespace->root);
+	umount_tree(root);
 	spin_unlock(&vfsmount_lock);
 	up_write(&namespace->sem);
 	kfree(namespace);
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index d71f14517b9c..e08edc17c6a0 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -169,12 +169,6 @@ nfsd4_open(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open
 		(int)open->op_fname.len, open->op_fname.data,
 		open->op_stateowner);
 
-	if (nfs4_in_grace() && open->op_claim_type != NFS4_OPEN_CLAIM_PREVIOUS)
-		return nfserr_grace;
-
-	if (!nfs4_in_grace() && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS)
-		return nfserr_no_grace;
-
 	/* This check required by spec. */
 	if (open->op_create && open->op_claim_type != NFS4_OPEN_CLAIM_NULL)
 		return nfserr_inval;
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 095f1740f3ae..57ed50fe7f85 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -119,25 +119,12 @@ out:
 	return status;
 }
 
-static int
-nfsd4_rec_fsync(struct dentry *dentry)
+static void
+nfsd4_sync_rec_dir(void)
 {
-	struct file *filp;
-	int status = nfs_ok;
-
-	dprintk("NFSD: nfs4_fsync_rec_dir\n");
-	filp = dentry_open(dget(dentry), mntget(rec_dir.mnt), O_RDWR);
-	if (IS_ERR(filp)) {
-		status = PTR_ERR(filp);
-		goto out;
-	}
-	if (filp->f_op && filp->f_op->fsync)
-		status = filp->f_op->fsync(filp, filp->f_dentry, 0);
-	fput(filp);
-out:
-	if (status)
-		printk("nfsd4: unable to sync recovery directory\n");
-	return status;
+	down(&rec_dir.dentry->d_inode->i_sem);
+	nfsd_sync_dir(rec_dir.dentry);
+	up(&rec_dir.dentry->d_inode->i_sem);
 }
 
 int
@@ -176,7 +163,7 @@ out_unlock:
 	up(&rec_dir.dentry->d_inode->i_sem);
 	if (status == 0) {
 		clp->cl_firststate = 1;
-		status = nfsd4_rec_fsync(rec_dir.dentry);
+		nfsd4_sync_rec_dir();
 	}
 	nfs4_reset_user(uid, gid);
 	dprintk("NFSD: nfsd4_create_clid_dir returns %d\n", status);
@@ -302,7 +289,9 @@ nfsd4_unlink_clid_dir(char *name, int namlen)
 
 	dprintk("NFSD: nfsd4_unlink_clid_dir. name %.*s\n", namlen, name);
 
+	down(&rec_dir.dentry->d_inode->i_sem);
 	dentry = lookup_one_len(name, rec_dir.dentry, namlen);
+	up(&rec_dir.dentry->d_inode->i_sem);
 	if (IS_ERR(dentry)) {
 		status = PTR_ERR(dentry);
 		return status;
@@ -327,11 +316,12 @@ nfsd4_remove_clid_dir(struct nfs4_client *clp)
 	if (!rec_dir_init || !clp->cl_firststate)
 		return;
 
+	clp->cl_firststate = 0;
 	nfs4_save_user(&uid, &gid);
 	status = nfsd4_unlink_clid_dir(clp->cl_recdir, HEXDIR_LEN-1);
 	nfs4_reset_user(uid, gid);
 	if (status == 0)
-		status = nfsd4_rec_fsync(rec_dir.dentry);
+		nfsd4_sync_rec_dir();
 	if (status)
 		printk("NFSD: Failed to remove expired client state directory"
 				" %.*s\n", HEXDIR_LEN, clp->cl_recdir);
@@ -362,7 +352,7 @@ nfsd4_recdir_purge_old(void) {
 		return;
 	status = nfsd4_list_rec_dir(rec_dir.dentry, purge_old);
 	if (status == 0)
-		status = nfsd4_rec_fsync(rec_dir.dentry);
+		nfsd4_sync_rec_dir();
 	if (status)
 		printk("nfsd4: failed to purge old clients from recovery"
 			" directory %s\n", rec_dir.dentry->d_name.name);
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 89e36526d7f2..b83f8fb441e1 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -874,6 +874,7 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, struct nfsd4_setclientid_confi
 			  * change request correctly. */
 			atomic_set(&conf->cl_callback.cb_set, 0);
 			gen_confirm(conf);
+			nfsd4_remove_clid_dir(unconf);
 			expire_client(unconf);
 			status = nfs_ok;
 
@@ -1159,6 +1160,7 @@ init_stateid(struct nfs4_stateid *stp, struct nfs4_file *fp, struct nfsd4_open *
 	stp->st_deny_bmap = 0;
 	__set_bit(open->op_share_access, &stp->st_access_bmap);
 	__set_bit(open->op_share_deny, &stp->st_deny_bmap);
+	stp->st_openstp = NULL;
 }
 
 static void
@@ -1294,7 +1296,7 @@ nfs4_share_conflict(struct svc_fh *current_fh, unsigned int deny_type)
 	fp = find_file(ino);
 	if (!fp)
 		return nfs_ok;
-	ret = nfserr_share_denied;
+	ret = nfserr_locked;
 	/* Search for conflicting share reservations */
 	list_for_each_entry(stp, &fp->fi_stateids, st_perfile) {
 		if (test_bit(deny_type, &stp->st_deny_bmap) ||
@@ -1482,7 +1484,7 @@ nfsd4_process_open1(struct nfsd4_open *open)
 	if (sop) {
 		open->op_stateowner = sop;
 		/* check for replay */
-		if (open->op_seqid == sop->so_seqid){
+		if (open->op_seqid == sop->so_seqid - 1){
 			if (sop->so_replay.rp_buflen)
 				return NFSERR_REPLAY_ME;
 			else {
@@ -1497,7 +1499,7 @@ nfsd4_process_open1(struct nfsd4_open *open)
 				goto renew;
 			}
 		} else if (sop->so_confirmed) {
-			if (open->op_seqid == sop->so_seqid + 1)
+			if (open->op_seqid == sop->so_seqid)
 				goto renew;
 			status = nfserr_bad_seqid;
 			goto out;
@@ -1530,8 +1532,6 @@ renew:
 	status = nfs_ok;
 	renew_client(sop->so_client);
 out:
-	if (status && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS)
-		status = nfserr_reclaim_bad;
 	return status;
 }
 
@@ -1685,19 +1685,11 @@ nfs4_upgrade_open(struct svc_rqst *rqstp, struct svc_fh *cur_fh, struct nfs4_sta
 }
 
 
-/* decrement seqid on successful reclaim, it will be bumped in encode_open */
 static void
-nfs4_set_claim_prev(struct nfsd4_open *open, int *status)
+nfs4_set_claim_prev(struct nfsd4_open *open)
 {
-	if (open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS) {
-		if (*status)
-			*status = nfserr_reclaim_bad;
-		else {
-			open->op_stateowner->so_confirmed = 1;
-			open->op_stateowner->so_client->cl_firststate = 1;
-			open->op_stateowner->so_seqid--;
-		}
-	}
+	open->op_stateowner->so_confirmed = 1;
+	open->op_stateowner->so_client->cl_firststate = 1;
 }
 
 /*
@@ -1789,6 +1781,12 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 	struct nfs4_delegation *dp = NULL;
 	int status;
 
+	if (nfs4_in_grace() && open->op_claim_type != NFS4_OPEN_CLAIM_PREVIOUS)
+		return nfserr_grace;
+
+	if (!nfs4_in_grace() && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS)
+		return nfserr_no_grace;
+
 	status = nfserr_inval;
 	if (!TEST_ACCESS(open->op_share_access) || !TEST_DENY(open->op_share_deny))
 		goto out;
@@ -1823,6 +1821,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 		status = nfs4_upgrade_open(rqstp, current_fh, stp, open);
 		if (status)
 			goto out;
+		update_stateid(&stp->st_stateid);
 	} else {
 		/* Stateid was not found, this is a new OPEN */
 		int flags = 0;
@@ -1856,8 +1855,8 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
 out:
 	if (fp)
 		put_nfs4_file(fp);
-	/* CLAIM_PREVIOUS has different error returns */
-	nfs4_set_claim_prev(open, &status);
+	if (status == 0 && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS)
+		nfs4_set_claim_prev(open);
 	/*
 	* To finish the open response, we just need to set the rflags.
 	*/
@@ -1990,14 +1989,11 @@ laundromat_main(void *not_used)
 	queue_delayed_work(laundry_wq, &laundromat_work, t*HZ);
 }
 
-/* search ownerid_hashtbl[] and close_lru for stateid owner
- * (stateid->si_stateownerid)
- */
 static struct nfs4_stateowner *
-find_openstateowner_id(u32 st_id, int flags) {
+search_close_lru(u32 st_id, int flags)
+{
 	struct nfs4_stateowner *local = NULL;
 
-	dprintk("NFSD: find_openstateowner_id %d\n", st_id);
 	if (flags & CLOSE_STATE) {
 		list_for_each_entry(local, &close_lru, so_close_lru) {
 			if (local->so_id == st_id)
@@ -2163,14 +2159,19 @@ out:
 	return status;
 }
 
+static inline int
+setlkflg (int type)
+{
+	return (type == NFS4_READW_LT || type == NFS4_READ_LT) ?
+		RD_STATE : WR_STATE;
+}
 
 /* 
  * Checks for sequence id mutating operations. 
  */
 static int
-nfs4_preprocess_seqid_op(struct svc_fh *current_fh, u32 seqid, stateid_t *stateid, int flags, struct nfs4_stateowner **sopp, struct nfs4_stateid **stpp, clientid_t *lockclid)
+nfs4_preprocess_seqid_op(struct svc_fh *current_fh, u32 seqid, stateid_t *stateid, int flags, struct nfs4_stateowner **sopp, struct nfs4_stateid **stpp, struct nfsd4_lock *lock)
 {
-	int status;
 	struct nfs4_stateid *stp;
 	struct nfs4_stateowner *sop;
 
@@ -2178,53 +2179,65 @@ nfs4_preprocess_seqid_op(struct svc_fh *current_fh, u32 seqid, stateid_t *statei
 			"stateid = (%08x/%08x/%08x/%08x)\n", seqid,
 		stateid->si_boot, stateid->si_stateownerid, stateid->si_fileid,
 		stateid->si_generation);
-			        
+
 	*stpp = NULL;
 	*sopp = NULL;
 
-	status = nfserr_bad_stateid;
 	if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) {
 		printk("NFSD: preprocess_seqid_op: magic stateid!\n");
-		goto out;
+		return nfserr_bad_stateid;
 	}
 
-	status = nfserr_stale_stateid;
 	if (STALE_STATEID(stateid))
-		goto out;
+		return nfserr_stale_stateid;
 	/*
 	* We return BAD_STATEID if filehandle doesn't match stateid, 
 	* the confirmed flag is incorrecly set, or the generation 
 	* number is incorrect.  
-	* If there is no entry in the openfile table for this id, 
-	* we can't always return BAD_STATEID;
-	* this might be a retransmitted CLOSE which has arrived after 
-	* the openfile has been released.
 	*/
-	if (!(stp = find_stateid(stateid, flags)))
-		goto no_nfs4_stateid;
-
-	status = nfserr_bad_stateid;
+	stp = find_stateid(stateid, flags);
+	if (stp == NULL) {
+		/*
+		 * Also, we should make sure this isn't just the result of
+		 * a replayed close:
+		 */
+		sop = search_close_lru(stateid->si_stateownerid, flags);
+		if (sop == NULL)
+			return nfserr_bad_stateid;
+		*sopp = sop;
+		goto check_replay;
+	}
 
-	/* for new lock stateowners:
-	 * check that the lock->v.new.open_stateid
-	 * refers to an open stateowner
-	 *
-	 * check that the lockclid (nfs4_lock->v.new.clientid) is the same
-	 * as the open_stateid->st_stateowner->so_client->clientid
-	 */
-	if (lockclid) {
+	if (lock) {
 		struct nfs4_stateowner *sop = stp->st_stateowner;
+		clientid_t *lockclid = &lock->v.new.clientid;
 		struct nfs4_client *clp = sop->so_client;
+		int lkflg = 0;
+		int status;
+
+		lkflg = setlkflg(lock->lk_type);
+
+		if (lock->lk_is_new) {
+                       if (!sop->so_is_open_owner)
+			       return nfserr_bad_stateid;
+                       if (!cmp_clid(&clp->cl_clientid, lockclid))
+			       return nfserr_bad_stateid;
+                       /* stp is the open stateid */
+                       status = nfs4_check_openmode(stp, lkflg);
+                       if (status)
+			       return status;
+               } else {
+                       /* stp is the lock stateid */
+                       status = nfs4_check_openmode(stp->st_openstp, lkflg);
+                       if (status)
+			       return status;
+               }
 
-		if (!sop->so_is_open_owner)
-			goto out;
-		if (!cmp_clid(&clp->cl_clientid, lockclid))
-			goto out;
 	}
 
 	if ((flags & CHECK_FH) && nfs4_check_fh(current_fh, stp)) {
 		printk("NFSD: preprocess_seqid_op: fh-stateid mismatch!\n");
-		goto out;
+		return nfserr_bad_stateid;
 	}
 
 	*stpp = stp;
@@ -2235,63 +2248,41 @@ nfs4_preprocess_seqid_op(struct svc_fh *current_fh, u32 seqid, stateid_t *statei
 	*  For the moment, we ignore the possibility of 
 	*  generation number wraparound.
 	*/
-	if (seqid != sop->so_seqid + 1)
+	if (seqid != sop->so_seqid)
 		goto check_replay;
 
-	if (sop->so_confirmed) {
-		if (flags & CONFIRM) {
-			printk("NFSD: preprocess_seqid_op: expected unconfirmed stateowner!\n");
-			goto out;
-		}
+	if (sop->so_confirmed && flags & CONFIRM) {
+		printk("NFSD: preprocess_seqid_op: expected"
+				" unconfirmed stateowner!\n");
+		return nfserr_bad_stateid;
 	}
-	else {
-		if (!(flags & CONFIRM)) {
-			printk("NFSD: preprocess_seqid_op: stateowner not confirmed yet!\n");
-			goto out;
-		}
+	if (!sop->so_confirmed && !(flags & CONFIRM)) {
+		printk("NFSD: preprocess_seqid_op: stateowner not"
+				" confirmed yet!\n");
+		return nfserr_bad_stateid;
 	}
 	if (stateid->si_generation > stp->st_stateid.si_generation) {
 		printk("NFSD: preprocess_seqid_op: future stateid?!\n");
-		goto out;
+		return nfserr_bad_stateid;
 	}
 
-	status = nfserr_old_stateid;
 	if (stateid->si_generation < stp->st_stateid.si_generation) {
 		printk("NFSD: preprocess_seqid_op: old stateid!\n");
-		goto out;
+		return nfserr_old_stateid;
 	}
-	/* XXX renew the client lease here */
-	status = nfs_ok;
-
-out:
-	return status;
-
-no_nfs4_stateid:
-
-	/*
-	* We determine whether this is a bad stateid or a replay, 
-	* starting by trying to look up the stateowner.
-	* If stateowner is not found - stateid is bad.
-	*/
-	if (!(sop = find_openstateowner_id(stateid->si_stateownerid, flags))) {
-		printk("NFSD: preprocess_seqid_op: no stateowner or nfs4_stateid!\n");
-		status = nfserr_bad_stateid;
-		goto out;
-	}
-	*sopp = sop;
+	renew_client(sop->so_client);
+	return nfs_ok;
 
 check_replay:
-	if (seqid == sop->so_seqid) {
+	if (seqid == sop->so_seqid - 1) {
 		printk("NFSD: preprocess_seqid_op: retransmission?\n");
 		/* indicate replay to calling function */
-		status = NFSERR_REPLAY_ME;
-	} else  {
-		printk("NFSD: preprocess_seqid_op: bad seqid (expected %d, got %d\n", sop->so_seqid +1, seqid);
-
-		*sopp = NULL;
-		status = nfserr_bad_seqid;
+		return NFSERR_REPLAY_ME;
 	}
-	goto out;
+	printk("NFSD: preprocess_seqid_op: bad seqid (expected %d, got %d)\n",
+			sop->so_seqid, seqid);
+	*sopp = NULL;
+	return nfserr_bad_seqid;
 }
 
 int
@@ -2609,7 +2600,6 @@ find_lockstateowner_str(struct inode *inode, clientid_t *clid,
  * occured. 
  *
  * strhashval = lock_ownerstr_hashval 
- * so_seqid = lock->lk_new_lock_seqid - 1: it gets bumped in encode 
  */
 
 static struct nfs4_stateowner *
@@ -2634,7 +2624,7 @@ alloc_init_lock_stateowner(unsigned int strhashval, struct nfs4_client *clp, str
 	sop->so_is_open_owner = 0;
 	sop->so_id = current_ownerid++;
 	sop->so_client = clp;
-	sop->so_seqid = lock->lk_new_lock_seqid - 1;
+	sop->so_seqid = lock->lk_new_lock_seqid;
 	sop->so_confirmed = 1;
 	rp = &sop->so_replay;
 	rp->rp_status = NFSERR_SERVERFAULT;
@@ -2669,6 +2659,7 @@ alloc_init_lock_stateid(struct nfs4_stateowner *sop, struct nfs4_file *fp, struc
 	stp->st_vfs_file = open_stp->st_vfs_file; /* FIXME refcount?? */
 	stp->st_access_bmap = open_stp->st_access_bmap;
 	stp->st_deny_bmap = open_stp->st_deny_bmap;
+	stp->st_openstp = open_stp;
 
 out:
 	return stp;
@@ -2699,22 +2690,17 @@ nfsd4_lock(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_lock
 		(long long) lock->lk_offset,
 		(long long) lock->lk_length);
 
-	if (nfs4_in_grace() && !lock->lk_reclaim)
-		return nfserr_grace;
-	if (!nfs4_in_grace() && lock->lk_reclaim)
-		return nfserr_no_grace;
-
 	if (check_lock_length(lock->lk_offset, lock->lk_length))
 		 return nfserr_inval;
 
 	nfs4_lock_state();
 
 	if (lock->lk_is_new) {
-	/*
-	 * Client indicates that this is a new lockowner.
-	 * Use open owner and open stateid to create lock owner and lock 
-	 * stateid.
-	 */
+		/*
+		 * Client indicates that this is a new lockowner.
+		 * Use open owner and open stateid to create lock owner and
+		 * lock stateid.
+		 */
 		struct nfs4_stateid *open_stp = NULL;
 		struct nfs4_file *fp;
 		
@@ -2724,23 +2710,14 @@ nfsd4_lock(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_lock
 			goto out;
 		}
 
-		/* is the new lock seqid presented by the client zero? */
-		status = nfserr_bad_seqid;
-		if (lock->v.new.lock_seqid != 0)
-			goto out;
-
 		/* validate and update open stateid and open seqid */
 		status = nfs4_preprocess_seqid_op(current_fh, 
 				        lock->lk_new_open_seqid,
 		                        &lock->lk_new_open_stateid,
 		                        CHECK_FH | OPEN_STATE,
-		                        &open_sop, &open_stp,
-					&lock->v.new.clientid);
-		if (status) {
-			if (lock->lk_reclaim)
-				status = nfserr_reclaim_bad;
+		                        &open_sop, &open_stp, lock);
+		if (status)
 			goto out;
-		}
 		/* create lockowner and lock stateid */
 		fp = open_stp->st_file;
 		strhashval = lock_ownerstr_hashval(fp->fi_inode, 
@@ -2766,7 +2743,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_lock
 				       lock->lk_old_lock_seqid, 
 				       &lock->lk_old_lock_stateid, 
 				       CHECK_FH | LOCK_STATE, 
-				       &lock->lk_stateowner, &lock_stp, NULL);
+				       &lock->lk_stateowner, &lock_stp, lock);
 		if (status)
 			goto out;
 	}
@@ -2778,6 +2755,13 @@ nfsd4_lock(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_lock
 		goto out;
 	}
 
+	status = nfserr_grace;
+	if (nfs4_in_grace() && !lock->lk_reclaim)
+		goto out;
+	status = nfserr_no_grace;
+	if (!nfs4_in_grace() && lock->lk_reclaim)
+		goto out;
+
 	locks_init_lock(&file_lock);
 	switch (lock->lk_type) {
 		case NFS4_READ_LT:
@@ -2844,10 +2828,10 @@ conflicting_lock:
 out_destroy_new_stateid:
 	if (lock->lk_is_new) {
 		dprintk("NFSD: nfsd4_lock: destroy new stateid!\n");
-	/*
-	* An error encountered after instantiation of the new
-	* stateid has forced us to destroy it.
-	*/
+		/*
+		 * An error encountered after instantiation of the new
+		 * stateid has forced us to destroy it.
+		 */
 		if (!seqid_mutating_err(status))
 			open_sop->so_seqid--;
 
@@ -3083,7 +3067,12 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp, struct nfsd4_release_lockowner *
 	 * of the lockowner state released; so don't release any until all
 	 * have been checked. */
 	status = nfs_ok;
-	list_for_each_entry(sop, &matches, so_perclient) {
+	while (!list_empty(&matches)) {
+		sop = list_entry(matches.next, struct nfs4_stateowner,
+								so_perclient);
+		/* unhash_stateowner deletes so_perclient only
+		 * for openowners. */
+		list_del(&sop->so_perclient);
 		release_stateowner(sop);
 	}
 out:
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 91fb171d2ace..4c4146350236 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -1210,16 +1210,15 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
 	save = resp->p;
 
 /*
- * Routine for encoding the result of a
- * "seqid-mutating" NFSv4 operation.  This is
- * where seqids are incremented, and the
- * replay cache is filled.
+ * Routine for encoding the result of a "seqid-mutating" NFSv4 operation.  This
+ * is where sequence id's are incremented, and the replay cache is filled.
+ * Note that we increment sequence id's here, at the last moment, so we're sure
+ * we know whether the error to be returned is a sequence id mutating error.
  */
 
 #define ENCODE_SEQID_OP_TAIL(stateowner) do {			\
 	if (seqid_mutating_err(nfserr) && stateowner) { 	\
-		if (stateowner->so_confirmed)			\
-			stateowner->so_seqid++;			\
+		stateowner->so_seqid++;				\
 		stateowner->so_replay.rp_status = nfserr;   	\
 		stateowner->so_replay.rp_buflen = 		\
 			  (((char *)(resp)->p - (char *)save)); \
@@ -1367,9 +1366,9 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
 		if ((buflen -= 4) < 0)
 			goto out_resource;
 		if (exp->ex_flags & NFSEXP_NOSUBTREECHECK)
-			WRITE32(NFS4_FH_VOLATILE_ANY);
+			WRITE32(NFS4_FH_PERSISTENT);
 		else
-			WRITE32(NFS4_FH_VOLATILE_ANY|NFS4_FH_VOL_RENAME);
+			WRITE32(NFS4_FH_PERSISTENT|NFS4_FH_VOL_RENAME);
 	}
 	if (bmval0 & FATTR4_WORD0_CHANGE) {
 		/*
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index be24ead89d94..5e0bf3917607 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -733,7 +733,7 @@ nfsd_sync(struct file *filp)
 	up(&inode->i_sem);
 }
 
-static void
+void
 nfsd_sync_dir(struct dentry *dp)
 {
 	nfsd_dosync(NULL, dp, dp->d_inode->i_fop);
diff --git a/fs/super.c b/fs/super.c
index 25bc1ec6bc5d..6e57ee252e14 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -840,7 +840,6 @@ do_kern_mount(const char *fstype, int flags, const char *name, void *data)
 	mnt->mnt_root = dget(sb->s_root);
 	mnt->mnt_mountpoint = sb->s_root;
 	mnt->mnt_parent = mnt;
-	mnt->mnt_namespace = current->namespace;
 	up_write(&sb->s_umount);
 	free_secdata(secdata);
 	put_filesystem(type);