Merge branch 'master' of /pub/scm/linux/kernel/git/torvalds/linux-2.6

25 files changed, 289 insertions, 189 deletions

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 7346c96..99d6af8 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -706,8 +706,13 @@ retry:
  * @bdev is about to be opened exclusively.  Check @bdev can be opened
  * exclusively and mark that an exclusive open is in progress.  Each
  * successful call to this function must be matched with a call to
- * either bd_claim() or bd_abort_claiming().  If this function
- * succeeds, the matching bd_claim() is guaranteed to succeed.
+ * either bd_finish_claiming() or bd_abort_claiming() (which do not
+ * fail).
+ *
+ * This function is used to gain exclusive access to the block device
+ * without actually causing other exclusive open attempts to fail. It
+ * should be used when the open sequence itself requires exclusive
+ * access but may subsequently fail.
  *
  * CONTEXT:
  * Might sleep.
@@ -734,6 +739,7 @@ static struct block_device *bd_start_claiming(struct block_device *bdev,
 		return ERR_PTR(-ENXIO);
 
 	whole = bdget_disk(disk, 0);
+	module_put(disk->fops->owner);
 	put_disk(disk);
 	if (!whole)
 		return ERR_PTR(-ENOMEM);
@@ -782,15 +788,46 @@ static void bd_abort_claiming(struct block_device *whole, void *holder)
 	__bd_abort_claiming(whole, holder);		/* releases bdev_lock */
 }
 
+/* increment holders when we have a legitimate claim. requires bdev_lock */
+static void __bd_claim(struct block_device *bdev, struct block_device *whole,
+					void *holder)
+{
+	/* note that for a whole device bd_holders
+	 * will be incremented twice, and bd_holder will
+	 * be set to bd_claim before being set to holder
+	 */
+	whole->bd_holders++;
+	whole->bd_holder = bd_claim;
+	bdev->bd_holders++;
+	bdev->bd_holder = holder;
+}
+
+/**
+ * bd_finish_claiming - finish claiming a block device
+ * @bdev: block device of interest (passed to bd_start_claiming())
+ * @whole: whole block device returned by bd_start_claiming()
+ * @holder: holder trying to claim @bdev
+ *
+ * Finish a claiming block started by bd_start_claiming().
+ *
+ * CONTEXT:
+ * Grabs and releases bdev_lock.
+ */
+static void bd_finish_claiming(struct block_device *bdev,
+				struct block_device *whole, void *holder)
+{
+	spin_lock(&bdev_lock);
+	BUG_ON(!bd_may_claim(bdev, whole, holder));
+	__bd_claim(bdev, whole, holder);
+	__bd_abort_claiming(whole, holder); /* not actually an abort */
+}
+
 /**
  * bd_claim - claim a block device
  * @bdev: block device to claim
  * @holder: holder trying to claim @bdev
  *
- * Try to claim @bdev which must have been opened successfully.  This
- * function may be called with or without preceding
- * blk_start_claiming().  In the former case, this function is always
- * successful and terminates the claiming block.
+ * Try to claim @bdev which must have been opened successfully.
  *
  * CONTEXT:
  * Might sleep.
@@ -806,23 +843,10 @@ int bd_claim(struct block_device *bdev, void *holder)
 	might_sleep();
 
 	spin_lock(&bdev_lock);
-
 	res = bd_prepare_to_claim(bdev, whole, holder);
-	if (res == 0) {
-		/* note that for a whole device bd_holders
-		 * will be incremented twice, and bd_holder will
-		 * be set to bd_claim before being set to holder
-		 */
-		whole->bd_holders++;
-		whole->bd_holder = bd_claim;
-		bdev->bd_holders++;
-		bdev->bd_holder = holder;
-	}
-
-	if (whole->bd_claiming)
-		__bd_abort_claiming(whole, holder);	/* releases bdev_lock */
-	else
-		spin_unlock(&bdev_lock);
+	if (res == 0)
+		__bd_claim(bdev, whole, holder);
+	spin_unlock(&bdev_lock);
 
 	return res;
 }
@@ -1476,7 +1500,7 @@ static int blkdev_open(struct inode * inode, struct file * filp)
 
 	if (whole) {
 		if (res == 0)
-			BUG_ON(bd_claim(bdev, filp) != 0);
+			bd_finish_claiming(bdev, whole, filp);
 		else
 			bd_abort_claiming(whole, filp);
 	}
@@ -1712,7 +1736,7 @@ struct block_device *open_bdev_exclusive(const char *path, fmode_t mode, void *h
 	if ((mode & FMODE_WRITE) && bdev_read_only(bdev))
 		goto out_blkdev_put;
 
-	BUG_ON(bd_claim(bdev, holder) != 0);
+	bd_finish_claiming(bdev, whole, holder);
 	return bdev;
 
 out_blkdev_put:
diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index 8d432cd..2222d16 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -60,6 +60,8 @@ static struct posix_acl *btrfs_get_acl(struct inode *inode, int type)
 		size = __btrfs_getxattr(inode, name, value, size);
 		if (size > 0) {
 			acl = posix_acl_from_xattr(value, size);
+			if (IS_ERR(acl))
+				return acl;
 			set_cached_acl(inode, type, acl);
 		}
 		kfree(value);
@@ -160,6 +162,12 @@ static int btrfs_xattr_acl_set(struct dentry *dentry, const char *name,
 	int ret;
 	struct posix_acl *acl = NULL;
 
+	if (!is_owner_or_cap(dentry->d_inode))
+		return -EPERM;
+
+	if (!IS_POSIXACL(dentry->d_inode))
+		return -EOPNOTSUPP;
+
 	if (value) {
 		acl = posix_acl_from_xattr(value, size);
 		if (acl == NULL) {
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index f3b287c..34f7c37 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1941,8 +1941,11 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 		     btrfs_level_size(tree_root,
 				      btrfs_super_log_root_level(disk_super));
 
-		log_tree_root = kzalloc(sizeof(struct btrfs_root),
-						      GFP_NOFS);
+		log_tree_root = kzalloc(sizeof(struct btrfs_root), GFP_NOFS);
+		if (!log_tree_root) {
+			err = -ENOMEM;
+			goto fail_trans_kthread;
+		}
 
 		__setup_root(nodesize, leafsize, sectorsize, stripesize,
 			     log_tree_root, fs_info, BTRFS_TREE_LOG_OBJECTID);
@@ -1982,6 +1985,10 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	fs_info->fs_root = btrfs_read_fs_root_no_name(fs_info, &location);
 	if (!fs_info->fs_root)
 		goto fail_trans_kthread;
+	if (IS_ERR(fs_info->fs_root)) {
+		err = PTR_ERR(fs_info->fs_root);
+		goto fail_trans_kthread;
+	}
 
 	if (!(sb->s_flags & MS_RDONLY)) {
 		down_read(&fs_info->cleanup_work_sem);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index b9080d7..32d0940 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4360,7 +4360,8 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 
 	block_rsv = get_block_rsv(trans, root);
 	cache = btrfs_lookup_block_group(root->fs_info, buf->start);
-	BUG_ON(block_rsv->space_info != cache->space_info);
+	if (block_rsv->space_info != cache->space_info)
+		goto out;
 
 	if (btrfs_header_generation(buf) == trans->transid) {
 		if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 787b50a..e354c33 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1140,7 +1140,7 @@ int btrfs_sync_file(struct file *file, int datasync)
 	/*
 	 * ok we haven't committed the transaction yet, lets do a commit
 	 */
-	if (file && file->private_data)
+	if (file->private_data)
 		btrfs_ioctl_trans_end(file);
 
 	trans = btrfs_start_transaction(root, 0);
@@ -1190,14 +1190,22 @@ static const struct vm_operations_struct btrfs_file_vm_ops = {
 
 static int btrfs_file_mmap(struct file	*filp, struct vm_area_struct *vma)
 {
-	vma->vm_ops = &btrfs_file_vm_ops;
+	struct address_space *mapping = filp->f_mapping;
+
+	if (!mapping->a_ops->readpage)
+		return -ENOEXEC;
+
 	file_accessed(filp);
+	vma->vm_ops = &btrfs_file_vm_ops;
+	vma->vm_flags |= VM_CAN_NONLINEAR;
+
 	return 0;
 }
 
 const struct file_operations btrfs_file_operations = {
 	.llseek		= generic_file_llseek,
 	.read		= do_sync_read,
+	.write		= do_sync_write,
 	.aio_read       = generic_file_aio_read,
 	.splice_read	= generic_file_splice_read,
 	.aio_write	= btrfs_file_aio_write,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index fa6ccc1..1bff92a 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -2673,7 +2673,7 @@ static int check_path_shared(struct btrfs_root *root,
 	struct extent_buffer *eb;
 	int level;
 	int ret;
-	u64 refs;
+	u64 refs = 1;
 
 	for (level = 0; level < BTRFS_MAX_LEVEL; level++) {
 		if (!path->nodes[level])
@@ -6884,7 +6884,7 @@ static long btrfs_fallocate(struct inode *inode, int mode,
 		if (em->block_start == EXTENT_MAP_HOLE ||
 		    (cur_offset >= inode->i_size &&
 		     !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) {
-			ret = btrfs_prealloc_file_range(inode, 0, cur_offset,
+			ret = btrfs_prealloc_file_range(inode, mode, cur_offset,
 							last_byte - cur_offset,
 							1 << inode->i_blkbits,
 							offset + len,
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 4cdb98c..4dbaf89 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1280,7 +1280,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 	trans = btrfs_start_transaction(root, 0);
 	if (IS_ERR(trans)) {
 		err = PTR_ERR(trans);
-		goto out;
+		goto out_up_write;
 	}
 	trans->block_rsv = &root->fs_info->global_block_rsv;
 
@@ -1845,7 +1845,7 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp)
 	dir_id = btrfs_super_root_dir(&root->fs_info->super_copy);
 	di = btrfs_lookup_dir_item(trans, root->fs_info->tree_root, path,
 				   dir_id, "default", 7, 1);
-	if (!di) {
+	if (IS_ERR_OR_NULL(di)) {
 		btrfs_free_path(path);
 		btrfs_end_transaction(trans, root);
 		printk(KERN_ERR "Umm, you don't have the default dir item, "
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 05d41e5..b37d723 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -784,16 +784,17 @@ again:
 				struct btrfs_extent_ref_v0 *ref0;
 				ref0 = btrfs_item_ptr(eb, path1->slots[0],
 						struct btrfs_extent_ref_v0);
-				root = find_tree_root(rc, eb, ref0);
-				if (!root->ref_cows)
-					cur->cowonly = 1;
 				if (key.objectid == key.offset) {
+					root = find_tree_root(rc, eb, ref0);
 					if (root && !should_ignore_root(root))
 						cur->root = root;
 					else
 						list_add(&cur->list, &useless);
 					break;
 				}
+				if (is_cowonly_root(btrfs_ref_root_v0(eb,
+								      ref0)))
+					cur->cowonly = 1;
 			}
 #else
 		BUG_ON(key.type == BTRFS_EXTENT_REF_V0_KEY);
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index b91ccd9..2d958be 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -330,7 +330,6 @@ int btrfs_del_root(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 {
 	struct btrfs_path *path;
 	int ret;
-	u32 refs;
 	struct btrfs_root_item *ri;
 	struct extent_buffer *leaf;
 
@@ -344,8 +343,6 @@ int btrfs_del_root(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	leaf = path->nodes[0];
 	ri = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_root_item);
 
-	refs = btrfs_disk_root_refs(leaf, ri);
-	BUG_ON(refs != 0);
 	ret = btrfs_del_item(trans, root, path);
 out:
 	btrfs_free_path(path);
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index d34b2df..f2393b3 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -360,6 +360,8 @@ static struct dentry *get_default_root(struct super_block *sb,
 	 */
 	dir_id = btrfs_super_root_dir(&root->fs_info->super_copy);
 	di = btrfs_lookup_dir_item(NULL, root, path, dir_id, "default", 7, 0);
+	if (IS_ERR(di))
+		return ERR_CAST(di);
 	if (!di) {
 		/*
 		 * Ok the default dir item isn't there.  This is weird since
@@ -390,8 +392,8 @@ setup_root:
 	location.offset = 0;
 
 	inode = btrfs_iget(sb, &location, new_root, &new);
-	if (!inode)
-		return ERR_PTR(-ENOMEM);
+	if (IS_ERR(inode))
+		return ERR_CAST(inode);
 
 	/*
 	 * If we're just mounting the root most subvol put the inode and return
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index ae3e3a3..619b616 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -981,6 +981,46 @@ static int send_cap_msg(struct ceph_mds_session *session,
 	return 0;
 }
 
+static void __queue_cap_release(struct ceph_mds_session *session,
+				u64 ino, u64 cap_id, u32 migrate_seq,
+				u32 issue_seq)
+{
+	struct ceph_msg *msg;
+	struct ceph_mds_cap_release *head;
+	struct ceph_mds_cap_item *item;
+
+	spin_lock(&session->s_cap_lock);
+	BUG_ON(!session->s_num_cap_releases);
+	msg = list_first_entry(&session->s_cap_releases,
+			       struct ceph_msg, list_head);
+
+	dout(" adding %llx release to mds%d msg %p (%d left)\n",
+	     ino, session->s_mds, msg, session->s_num_cap_releases);
+
+	BUG_ON(msg->front.iov_len + sizeof(*item) > PAGE_CACHE_SIZE);
+	head = msg->front.iov_base;
+	head->num = cpu_to_le32(le32_to_cpu(head->num) + 1);
+	item = msg->front.iov_base + msg->front.iov_len;
+	item->ino = cpu_to_le64(ino);
+	item->cap_id = cpu_to_le64(cap_id);
+	item->migrate_seq = cpu_to_le32(migrate_seq);
+	item->seq = cpu_to_le32(issue_seq);
+
+	session->s_num_cap_releases--;
+
+	msg->front.iov_len += sizeof(*item);
+	if (le32_to_cpu(head->num) == CEPH_CAPS_PER_RELEASE) {
+		dout(" release msg %p full\n", msg);
+		list_move_tail(&msg->list_head, &session->s_cap_releases_done);
+	} else {
+		dout(" release msg %p at %d/%d (%d)\n", msg,
+		     (int)le32_to_cpu(head->num),
+		     (int)CEPH_CAPS_PER_RELEASE,
+		     (int)msg->front.iov_len);
+	}
+	spin_unlock(&session->s_cap_lock);
+}
+
 /*
  * Queue cap releases when an inode is dropped from our cache.  Since
  * inode is about to be destroyed, there is no need for i_lock.
@@ -994,41 +1034,9 @@ void ceph_queue_caps_release(struct inode *inode)
 	while (p) {
 		struct ceph_cap *cap = rb_entry(p, struct ceph_cap, ci_node);
 		struct ceph_mds_session *session = cap->session;
-		struct ceph_msg *msg;
-		struct ceph_mds_cap_release *head;
-		struct ceph_mds_cap_item *item;
 
-		spin_lock(&session->s_cap_lock);
-		BUG_ON(!session->s_num_cap_releases);
-		msg = list_first_entry(&session->s_cap_releases,
-				       struct ceph_msg, list_head);
-
-		dout(" adding %p release to mds%d msg %p (%d left)\n",
-		     inode, session->s_mds, msg, session->s_num_cap_releases);
-
-		BUG_ON(msg->front.iov_len + sizeof(*item) > PAGE_CACHE_SIZE);
-		head = msg->front.iov_base;
-		head->num = cpu_to_le32(le32_to_cpu(head->num) + 1);
-		item = msg->front.iov_base + msg->front.iov_len;
-		item->ino = cpu_to_le64(ceph_ino(inode));
-		item->cap_id = cpu_to_le64(cap->cap_id);
-		item->migrate_seq = cpu_to_le32(cap->mseq);
-		item->seq = cpu_to_le32(cap->issue_seq);
-
-		session->s_num_cap_releases--;
-
-		msg->front.iov_len += sizeof(*item);
-		if (le32_to_cpu(head->num) == CEPH_CAPS_PER_RELEASE) {
-			dout(" release msg %p full\n", msg);
-			list_move_tail(&msg->list_head,
-				       &session->s_cap_releases_done);
-		} else {
-			dout(" release msg %p at %d/%d (%d)\n", msg,
-			     (int)le32_to_cpu(head->num),
-			     (int)CEPH_CAPS_PER_RELEASE,
-			     (int)msg->front.iov_len);
-		}
-		spin_unlock(&session->s_cap_lock);
+		__queue_cap_release(session, ceph_ino(inode), cap->cap_id,
+				    cap->mseq, cap->issue_seq);
 		p = rb_next(p);
 		__ceph_remove_cap(cap);
 	}
@@ -2655,7 +2663,7 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 	struct ceph_mds_caps *h;
 	int mds = session->s_mds;
 	int op;
-	u32 seq;
+	u32 seq, mseq;
 	struct ceph_vino vino;
 	u64 cap_id;
 	u64 size, max_size;
@@ -2675,6 +2683,7 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 	vino.snap = CEPH_NOSNAP;
 	cap_id = le64_to_cpu(h->cap_id);
 	seq = le32_to_cpu(h->seq);
+	mseq = le32_to_cpu(h->migrate_seq);
 	size = le64_to_cpu(h->size);
 	max_size = le64_to_cpu(h->max_size);
 
@@ -2689,6 +2698,18 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 	     vino.snap, inode);
 	if (!inode) {
 		dout(" i don't have ino %llx\n", vino.ino);
+
+		if (op == CEPH_CAP_OP_IMPORT)
+			__queue_cap_release(session, vino.ino, cap_id,
+					    mseq, seq);
+
+		/*
+		 * send any full release message to try to move things
+		 * along for the mds (who clearly thinks we still have this
+		 * cap).
+		 */
+		ceph_add_cap_releases(mdsc, session, -1);
+		ceph_send_cap_releases(mdsc, session);
 		goto done;
 	}
 
@@ -2714,7 +2735,7 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 	spin_lock(&inode->i_lock);
 	cap = __get_cap_for_mds(ceph_inode(inode), mds);
 	if (!cap) {
-		dout("no cap on %p ino %llx.%llx from mds%d, releasing\n",
+		dout(" no cap on %p ino %llx.%llx from mds%d\n",
 		     inode, ceph_ino(inode), ceph_snap(inode), mds);
 		spin_unlock(&inode->i_lock);
 		goto done;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 226f5a5..ab47f46 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -827,7 +827,7 @@ static void ceph_set_dentry_offset(struct dentry *dn)
 
 	spin_lock(&dcache_lock);
 	spin_lock(&dn->d_lock);
-	list_move_tail(&dir->d_subdirs, &dn->d_u.d_child);
+	list_move(&dn->d_u.d_child, &dir->d_subdirs);
 	dout("set_dentry_offset %p %lld (%p %p)\n", dn, di->offset,
 	     dn->d_u.d_child.prev, dn->d_u.d_child.next);
 	spin_unlock(&dn->d_lock);
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index b49f128..1766947 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1066,9 +1066,9 @@ static int trim_caps(struct ceph_mds_client *mdsc,
  *
  * Called under s_mutex.
  */
-static int add_cap_releases(struct ceph_mds_client *mdsc,
-			    struct ceph_mds_session *session,
-			    int extra)
+int ceph_add_cap_releases(struct ceph_mds_client *mdsc,
+			  struct ceph_mds_session *session,
+			  int extra)
 {
 	struct ceph_msg *msg;
 	struct ceph_mds_cap_release *head;
@@ -1176,8 +1176,8 @@ static int check_cap_flush(struct ceph_mds_client *mdsc, u64 want_flush_seq)
 /*
  * called under s_mutex
  */
-static void send_cap_releases(struct ceph_mds_client *mdsc,
-		       struct ceph_mds_session *session)
+void ceph_send_cap_releases(struct ceph_mds_client *mdsc,
+			    struct ceph_mds_session *session)
 {
 	struct ceph_msg *msg;
 
@@ -1980,7 +1980,7 @@ out_err:
 	}
 	mutex_unlock(&mdsc->mutex);
 
-	add_cap_releases(mdsc, req->r_session, -1);
+	ceph_add_cap_releases(mdsc, req->r_session, -1);
 	mutex_unlock(&session->s_mutex);
 
 	/* kick calling process */
@@ -2433,6 +2433,7 @@ static void handle_lease(struct ceph_mds_client *mdsc,
 	struct ceph_dentry_info *di;
 	int mds = session->s_mds;
 	struct ceph_mds_lease *h = msg->front.iov_base;
+	u32 seq;
 	struct ceph_vino vino;
 	int mask;
 	struct qstr dname;
@@ -2446,6 +2447,7 @@ static void handle_lease(struct ceph_mds_client *mdsc,
 	vino.ino = le64_to_cpu(h->ino);
 	vino.snap = CEPH_NOSNAP;
 	mask = le16_to_cpu(h->mask);
+	seq = le32_to_cpu(h->seq);
 	dname.name = (void *)h + sizeof(*h) + sizeof(u32);
 	dname.len = msg->front.iov_len - sizeof(*h) - sizeof(u32);
 	if (dname.len != get_unaligned_le32(h+1))
@@ -2456,8 +2458,9 @@ static void handle_lease(struct ceph_mds_client *mdsc,
 
 	/* lookup inode */
 	inode = ceph_find_inode(sb, vino);
-	dout("handle_lease '%s', mask %d, ino %llx %p\n",
-	     ceph_lease_op_name(h->action), mask, vino.ino, inode);
+	dout("handle_lease %s, mask %d, ino %llx %p %.*s\n",
+	     ceph_lease_op_name(h->action), mask, vino.ino, inode,
+	     dname.len, dname.name);
 	if (inode == NULL) {
 		dout("handle_lease no inode %llx\n", vino.ino);
 		goto release;
@@ -2482,7 +2485,8 @@ static void handle_lease(struct ceph_mds_client *mdsc,
 	switch (h->action) {
 	case CEPH_MDS_LEASE_REVOKE:
 		if (di && di->lease_session == session) {
-			h->seq = cpu_to_le32(di->lease_seq);
+			if (ceph_seq_cmp(di->lease_seq, seq) > 0)
+				h->seq = cpu_to_le32(di->lease_seq);
 			__ceph_mdsc_drop_dentry_lease(dentry);
 		}
 		release = 1;
@@ -2496,7 +2500,7 @@ static void handle_lease(struct ceph_mds_client *mdsc,
 			unsigned long duration =
 				le32_to_cpu(h->duration_ms) * HZ / 1000;
 
-			di->lease_seq = le32_to_cpu(h->seq);
+			di->lease_seq = seq;
 			dentry->d_time = di->lease_renew_from + duration;
 			di->lease_renew_after = di->lease_renew_from +
 				(duration >> 1);
@@ -2686,10 +2690,10 @@ static void delayed_work(struct work_struct *work)
 			send_renew_caps(mdsc, s);
 		else
 			ceph_con_keepalive(&s->s_con);
-		add_cap_releases(mdsc, s, -1);
+		ceph_add_cap_releases(mdsc, s, -1);
 		if (s->s_state == CEPH_MDS_SESSION_OPEN ||
 		    s->s_state == CEPH_MDS_SESSION_HUNG)
-			send_cap_releases(mdsc, s);
+			ceph_send_cap_releases(mdsc, s);
 		mutex_unlock(&s->s_mutex);
 		ceph_put_mds_session(s);
 
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index d9936c4..b292fa4 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -322,6 +322,12 @@ static inline void ceph_mdsc_put_request(struct ceph_mds_request *req)
 	kref_put(&req->r_kref, ceph_mdsc_release_request);
 }
 
+extern int ceph_add_cap_releases(struct ceph_mds_client *mdsc,
+				 struct ceph_mds_session *session,
+				 int extra);
+extern void ceph_send_cap_releases(struct ceph_mds_client *mdsc,
+				   struct ceph_mds_session *session);
+
 extern void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc);
 
 extern char *ceph_mdsc_build_path(struct dentry *dentry, int *plen, u64 *base,
diff --git a/fs/ceph/mon_client.c b/fs/ceph/mon_client.c
index 21c62e9..07a5399 100644
--- a/fs/ceph/mon_client.c
+++ b/fs/ceph/mon_client.c
@@ -400,6 +400,8 @@ static void release_generic_request(struct kref *kref)
 		ceph_msg_put(req->reply);
 	if (req->request)
 		ceph_msg_put(req->request);
+
+	kfree(req);
 }
 
 static void put_generic_request(struct ceph_mon_generic_request *req)
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 4e0bee2..fa87f51 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -89,7 +89,7 @@ static int ceph_statfs(struct dentry *dentry, struct kstatfs *buf)
 
 	buf->f_files = le64_to_cpu(st.num_objects);
 	buf->f_ffree = -1;
-	buf->f_namelen = PATH_MAX;
+	buf->f_namelen = NAME_MAX;
 	buf->f_frsize = PAGE_CACHE_SIZE;
 
 	/* leave fsid little-endian, regardless of host endianness */
@@ -926,7 +926,7 @@ static int ceph_compare_super(struct super_block *sb, void *data)
 /*
  * construct our own bdi so we can control readahead, etc.
  */
-static atomic_long_t bdi_seq = ATOMIC_INIT(0);
+static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
 
 static int ceph_register_bdi(struct super_block *sb, struct ceph_client *client)
 {
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 19df61c..42272d6 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4942,20 +4942,26 @@ void ext4_set_inode_flags(struct inode *inode)
 /* Propagate flags from i_flags to EXT4_I(inode)->i_flags */
 void ext4_get_inode_flags(struct ext4_inode_info *ei)
 {
-	unsigned int flags = ei->vfs_inode.i_flags;
-
-	ei->i_flags &= ~(EXT4_SYNC_FL|EXT4_APPEND_FL|
-			EXT4_IMMUTABLE_FL|EXT4_NOATIME_FL|EXT4_DIRSYNC_FL);
-	if (flags & S_SYNC)
-		ei->i_flags |= EXT4_SYNC_FL;
-	if (flags & S_APPEND)
-		ei->i_flags |= EXT4_APPEND_FL;
-	if (flags & S_IMMUTABLE)
-		ei->i_flags |= EXT4_IMMUTABLE_FL;
-	if (flags & S_NOATIME)
-		ei->i_flags |= EXT4_NOATIME_FL;
-	if (flags & S_DIRSYNC)
-		ei->i_flags |= EXT4_DIRSYNC_FL;
+	unsigned int vfs_fl;
+	unsigned long old_fl, new_fl;
+
+	do {
+		vfs_fl = ei->vfs_inode.i_flags;
+		old_fl = ei->i_flags;
+		new_fl = old_fl & ~(EXT4_SYNC_FL|EXT4_APPEND_FL|
+				EXT4_IMMUTABLE_FL|EXT4_NOATIME_FL|
+				EXT4_DIRSYNC_FL);
+		if (vfs_fl & S_SYNC)
+			new_fl |= EXT4_SYNC_FL;
+		if (vfs_fl & S_APPEND)
+			new_fl |= EXT4_APPEND_FL;
+		if (vfs_fl & S_IMMUTABLE)
+			new_fl |= EXT4_IMMUTABLE_FL;
+		if (vfs_fl & S_NOATIME)
+			new_fl |= EXT4_NOATIME_FL;
+		if (vfs_fl & S_DIRSYNC)
+			new_fl |= EXT4_DIRSYNC_FL;
+	} while (cmpxchg(&ei->i_flags, old_fl, new_fl) != old_fl);
 }
 
 static blkcnt_t ext4_inode_blocks(struct ext4_inode *raw_inode,
@@ -5191,7 +5197,7 @@ static int ext4_inode_blocks_set(handle_t *handle,
 		 */
 		raw_inode->i_blocks_lo   = cpu_to_le32(i_blocks);
 		raw_inode->i_blocks_high = 0;
-		ei->i_flags &= ~EXT4_HUGE_FILE_FL;
+		ext4_clear_inode_flag(inode, EXT4_INODE_HUGE_FILE);
 		return 0;
 	}
 	if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_HUGE_FILE))
@@ -5204,9 +5210,9 @@ static int ext4_inode_blocks_set(handle_t *handle,
 		 */
 		raw_inode->i_blocks_lo   = cpu_to_le32(i_blocks);
 		raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32);
-		ei->i_flags &= ~EXT4_HUGE_FILE_FL;
+		ext4_clear_inode_flag(inode, EXT4_INODE_HUGE_FILE);
 	} else {
-		ei->i_flags |= EXT4_HUGE_FILE_FL;
+		ext4_set_inode_flag(inode, EXT4_INODE_HUGE_FILE);
 		/* i_block is stored in file system block size */
 		i_blocks = i_blocks >> (inode->i_blkbits - 9);
 		raw_inode->i_blocks_lo   = cpu_to_le32(i_blocks);
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 3a6c92a..52abfa1 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -960,6 +960,9 @@ mext_check_arguments(struct inode *orig_inode,
 		return -EINVAL;
 	}
 
+	if (IS_IMMUTABLE(donor_inode) || IS_APPEND(donor_inode))
+		return -EPERM;
+
 	/* Ext4 move extent does not support swapfile */
 	if (IS_SWAPFILE(orig_inode) || IS_SWAPFILE(donor_inode)) {
 		ext4_debug("ext4 move extent: The argument files should "
diff --git a/fs/jffs2/acl.c b/fs/jffs2/acl.c
index a33aab6..54a92fd 100644
--- a/fs/jffs2/acl.c
+++ b/fs/jffs2/acl.c
@@ -234,8 +234,9 @@ static int jffs2_set_acl(struct inode *inode, int type, struct posix_acl *acl)
 			if (inode->i_mode != mode) {
 				struct iattr attr;
 
-				attr.ia_valid = ATTR_MODE;
+				attr.ia_valid = ATTR_MODE | ATTR_CTIME;
 				attr.ia_mode = mode;
+				attr.ia_ctime = CURRENT_TIME_SEC;
 				rc = jffs2_do_setattr(inode, &attr);
 				if (rc < 0)
 					return rc;
diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index 7aa4417..166062a 100644
--- a/fs/jffs2/dir.c
+++ b/fs/jffs2/dir.c
@@ -222,15 +222,18 @@ static int jffs2_create(struct inode *dir_i, struct dentry *dentry, int mode,
 	dir_i->i_mtime = dir_i->i_ctime = ITIME(je32_to_cpu(ri->ctime));
 
 	jffs2_free_raw_inode(ri);
-	d_instantiate(dentry, inode);
 
 	D1(printk(KERN_DEBUG "jffs2_create: Created ino #%lu with mode %o, nlink %d(%d). nrpages %ld\n",
 		  inode->i_ino, inode->i_mode, inode->i_nlink,
 		  f->inocache->pino_nlink, inode->i_mapping->nrpages));
+
+	d_instantiate(dentry, inode);
+	unlock_new_inode(inode);
 	return 0;
 
  fail:
 	make_bad_inode(inode);
+	unlock_new_inode(inode);
 	iput(inode);
 	jffs2_free_raw_inode(ri);
 	return ret;
@@ -360,8 +363,8 @@ static int jffs2_symlink (struct inode *dir_i, struct dentry *dentry, const char
 		/* Eeek. Wave bye bye */
 		mutex_unlock(&f->sem);
 		jffs2_complete_reservation(c);
-		jffs2_clear_inode(inode);
-		return PTR_ERR(fn);
+		ret = PTR_ERR(fn);
+		goto fail;
 	}
 
 	/* We use f->target field to store the target path. */
@@ -370,8 +373,8 @@ static int jffs2_symlink (struct inode *dir_i, struct dentry *dentry, const char
 		printk(KERN_WARNING "Can't allocate %d bytes of memory\n", targetlen + 1);
 		mutex_unlock(&f->sem);
 		jffs2_complete_reservation(c);
-		jffs2_clear_inode(inode);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto fail;
 	}
 
 	memcpy(f->target, target, targetlen + 1);
@@ -386,30 +389,24 @@ static int jffs2_symlink (struct inode *dir_i, struct dentry *dentry, const char
 	jffs2_complete_reservation(c);
 
 	ret = jffs2_init_security(inode, dir_i);
-	if (ret) {
-		jffs2_clear_inode(inode);
-		return ret;
-	}
+	if (ret)
+		goto fail;
+
 	ret = jffs2_init_acl_post(inode);
-	if (ret) {
-		jffs2_clear_inode(inode);
-		return ret;
-	}
+	if (ret)
+		goto fail;
 
 	ret = jffs2_reserve_space(c, sizeof(*rd)+namelen, &alloclen,
 				  ALLOC_NORMAL, JFFS2_SUMMARY_DIRENT_SIZE(namelen));
-	if (ret) {
-		/* Eep. */
-		jffs2_clear_inode(inode);
-		return ret;
-	}
+	if (ret)
+		goto fail;
 
 	rd = jffs2_alloc_raw_dirent();
 	if (!rd) {
 		/* Argh. Now we treat it like a normal delete */
 		jffs2_complete_reservation(c);
-		jffs2_clear_inode(inode);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto fail;
 	}
 
 	dir_f = JFFS2_INODE_INFO(dir_i);
@@ -437,8 +434,8 @@ static int jffs2_symlink (struct inode *dir_i, struct dentry *dentry, const char
 		jffs2_complete_reservation(c);
 		jffs2_free_raw_dirent(rd);
 		mutex_unlock(&dir_f->sem);
-		jffs2_clear_inode(inode);
-		return PTR_ERR(fd);
+		ret = PTR_ERR(fd);
+		goto fail;
 	}
 
 	dir_i->i_mtime = dir_i->i_ctime = ITIME(je32_to_cpu(rd->mctime));
@@ -453,7 +450,14 @@ static int jffs2_symlink (struct inode *dir_i, struct dentry *dentry, const char
 	jffs2_complete_reservation(c);
 
 	d_instantiate(dentry, inode);
+	unlock_new_inode(inode);
 	return 0;
+
+ fail:
+	make_bad_inode(inode);
+	unlock_new_inode(inode);
+	iput(inode);
+	return ret;
 }
 
 
@@ -519,8 +523,8 @@ static int jffs2_mkdir (struct inode *dir_i, struct dentry *dentry, int mode)
 		/* Eeek. Wave bye bye */
 		mutex_unlock(&f->sem);
 		jffs2_complete_reservation(c);
-		jffs2_clear_inode(inode);
-		return PTR_ERR(fn);
+		ret = PTR_ERR(fn);
+		goto fail;
 	}
 	/* No data here. Only a metadata node, which will be
 	   obsoleted by the first data write
@@ -531,30 +535,24 @@ static int jffs2_mkdir (struct inode *dir_i, struct dentry *dentry, int mode)
 	jffs2_complete_reservation(c);
 
 	ret = jffs2_init_security(inode, dir_i);
-	if (ret) {
-		jffs2_clear_inode(inode);
-		return ret;
-	}
+	if (ret)
+		goto fail;
+
 	ret = jffs2_init_acl_post(inode);
-	if (ret) {
-		jffs2_clear_inode(inode);
-		return ret;
-	}
+	if (ret)
+		goto fail;
 
 	ret = jffs2_reserve_space(c, sizeof(*rd)+namelen, &alloclen,
 				  ALLOC_NORMAL, JFFS2_SUMMARY_DIRENT_SIZE(namelen));
-	if (ret) {
-		/* Eep. */
-		jffs2_clear_inode(inode);
-		return ret;
-	}
+	if (ret)
+		goto fail;
 
 	rd = jffs2_alloc_raw_dirent();
 	if (!rd) {
 		/* Argh. Now we treat it like a normal delete */
 		jffs2_complete_reservation(c);
-		jffs2_clear_inode(inode);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto fail;
 	}
 
 	dir_f = JFFS2_INODE_INFO(dir_i);
@@ -582,8 +580,8 @@ static int jffs2_mkdir (struct inode *dir_i, struct dentry *dentry, int mode)
 		jffs2_complete_reservation(c);
 		jffs2_free_raw_dirent(rd);
 		mutex_unlock(&dir_f->sem);
-		jffs2_clear_inode(inode);
-		return PTR_ERR(fd);
+		ret = PTR_ERR(fd);
+		goto fail;
 	}
 
 	dir_i->i_mtime = dir_i->i_ctime = ITIME(je32_to_cpu(rd->mctime));
@@ -599,7 +597,14 @@ static int jffs2_mkdir (struct inode *dir_i, struct dentry *dentry, int mode)
 	jffs2_complete_reservation(c);
 
 	d_instantiate(dentry, inode);
+	unlock_new_inode(inode);
 	return 0;
+
+ fail:
+	make_bad_inode(inode);
+	unlock_new_inode(inode);
+	iput(inode);
+	return ret;
 }
 
 static int jffs2_rmdir (struct inode *dir_i, struct dentry *dentry)
@@ -693,8 +698,8 @@ static int jffs2_mknod (struct inode *dir_i, struct dentry *dentry, int mode, de
 		/* Eeek. Wave bye bye */
 		mutex_unlock(&f->sem);
 		jffs2_complete_reservation(c);
-		jffs2_clear_inode(inode);
-		return PTR_ERR(fn);
+		ret = PTR_ERR(fn);
+		goto fail;
 	}
 	/* No data here. Only a metadata node, which will be
 	   obsoleted by the first data write
@@ -705,30 +710,24 @@ static int jffs2_mknod (struct inode *dir_i, struct dentry *dentry, int mode, de
 	jffs2_complete_reservation(c);
 
 	ret = jffs2_init_security(inode, dir_i);
-	if (ret) {
-		jffs2_clear_inode(inode);
-		return ret;
-	}
+	if (ret)
+		goto fail;
+
 	ret = jffs2_init_acl_post(inode);
-	if (ret) {
-		jffs2_clear_inode(inode);
-		return ret;
-	}
+	if (ret)
+		goto fail;
 
 	ret = jffs2_reserve_space(c, sizeof(*rd)+namelen, &alloclen,
 				  ALLOC_NORMAL, JFFS2_SUMMARY_DIRENT_SIZE(namelen));
-	if (ret) {
-		/* Eep. */
-		jffs2_clear_inode(inode);
-		return ret;
-	}
+	if (ret)
+		goto fail;
 
 	rd = jffs2_alloc_raw_dirent();
 	if (!rd) {
 		/* Argh. Now we treat it like a normal delete */
 		jffs2_complete_reservation(c);
-		jffs2_clear_inode(inode);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto fail;
 	}
 
 	dir_f = JFFS2_INODE_INFO(dir_i);
@@ -759,8 +758,8 @@ static int jffs2_mknod (struct inode *dir_i, struct dentry *dentry, int mode, de
 		jffs2_complete_reservation(c);
 		jffs2_free_raw_dirent(rd);
 		mutex_unlock(&dir_f->sem);
-		jffs2_clear_inode(inode);
-		return PTR_ERR(fd);
+		ret = PTR_ERR(fd);
+		goto fail;
 	}
 
 	dir_i->i_mtime = dir_i->i_ctime = ITIME(je32_to_cpu(rd->mctime));
@@ -775,8 +774,14 @@ static int jffs2_mknod (struct inode *dir_i, struct dentry *dentry, int mode, de
 	jffs2_complete_reservation(c);
 
 	d_instantiate(dentry, inode);
-
+	unlock_new_inode(inode);
 	return 0;
+
+ fail:
+	make_bad_inode(inode);
+	unlock_new_inode(inode);
+	iput(inode);
+	return ret;
 }
 
 static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry,
diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c
index 8bc2c80..459d39d 100644
--- a/fs/jffs2/fs.c
+++ b/fs/jffs2/fs.c
@@ -465,7 +465,12 @@ struct inode *jffs2_new_inode (struct inode *dir_i, int mode, struct jffs2_raw_i
 	inode->i_blocks = 0;
 	inode->i_size = 0;
 
-	insert_inode_hash(inode);
+	if (insert_inode_locked(inode) < 0) {
+		make_bad_inode(inode);
+		unlock_new_inode(inode);
+		iput(inode);
+		return ERR_PTR(-EINVAL);
+	}
 
 	return inode;
 }
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 12f7109..4a27347 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4122,8 +4122,8 @@ nfs4_state_shutdown(void)
 	nfs4_lock_state();
 	nfs4_release_reclaim();
 	__nfs4_state_shutdown();
-	nfsd4_destroy_callback_queue();
 	nfs4_unlock_state();
+	nfsd4_destroy_callback_queue();
 }
 
 /*
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index ebbf3b6..3c11112 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -443,8 +443,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 	if (size_change)
 		put_write_access(inode);
 	if (!err)
-		if (EX_ISSYNC(fhp->fh_export))
-			write_inode_now(inode, 1);
+		commit_metadata(fhp);
 out:
 	return err;
 
diff --git a/fs/pipe.c b/fs/pipe.c
index 69c4c7c..279eef9 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -1145,13 +1145,20 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long nr_pages)
 	 * and adjust the indexes.
 	 */
 	if (pipe->nrbufs) {
-		const unsigned int tail = pipe->nrbufs & (pipe->buffers - 1);
-		const unsigned int head = pipe->nrbufs - tail;
+		unsigned int tail;
+		unsigned int head;
 
+		tail = pipe->curbuf + pipe->nrbufs;
+		if (tail < pipe->buffers)
+			tail = 0;
+		else
+			tail &= (pipe->buffers - 1);
+
+		head = pipe->nrbufs - tail;
 		if (head)
 			memcpy(bufs, pipe->bufs + pipe->curbuf, head * sizeof(struct pipe_buffer));
 		if (tail)
-			memcpy(bufs + head, pipe->bufs + pipe->curbuf, tail * sizeof(struct pipe_buffer));
+			memcpy(bufs + head, pipe->bufs, tail * sizeof(struct pipe_buffer));
 	}
 
 	pipe->curbuf = 0;
@@ -1208,12 +1215,13 @@ long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
 		size = round_pipe_size(arg);
 		nr_pages = size >> PAGE_SHIFT;
 
+		ret = -EINVAL;
+		if (!nr_pages)
+			goto out;
+
 		if (!capable(CAP_SYS_RESOURCE) && size > pipe_max_size) {
 			ret = -EPERM;
 			goto out;
-		} else if (nr_pages < PAGE_SIZE) {
-			ret = -EINVAL;
-			goto out;
 		}
 		ret = pipe_set_size(pipe, nr_pages);
 		break;
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index a0fa3bf..34640d6 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -1381,14 +1381,6 @@ xfs_vm_writepage(
 	if (!page_has_buffers(page))
 		create_empty_buffers(page, 1 << inode->i_blkbits, 0);
 
-
-	/*
-	 *  VM calculation for nr_to_write seems off.  Bump it way
-	 *  up, this gets simple streaming writes zippy again.
-	 *  To be reviewed again after Jens' writeback changes.
-	 */
-	wbc->nr_to_write *= 4;
-
 	/*
 	 * Convert delayed allocate, unwritten or unmapped space
 	 * to real space and flush out to disk.