Merge branch 'linus' into rt/base

Conflicts:
	kernel/perf_counter.c

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

42 files changed, 571 insertions, 269 deletions

diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index 697f6b5f1313..e92f229e3c6e 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -828,15 +828,22 @@ static int load_flat_shared_library(int id, struct lib_info *libs)
 	if (IS_ERR(bprm.file))
 		return res;
 
+	bprm.cred = prepare_exec_creds();
+	res = -ENOMEM;
+	if (!bprm.cred)
+		goto out;
+
 	res = prepare_binprm(&bprm);
 
 	if (res <= (unsigned long)-4096)
 		res = load_flat_file(&bprm, libs, id, NULL);
-	if (bprm.file) {
-		allow_write_access(bprm.file);
-		fput(bprm.file);
-		bprm.file = NULL;
-	}
+
+	abort_creds(bprm.cred);
+
+out:
+	allow_write_access(bprm.file);
+	fput(bprm.file);
+
 	return(res);
 }
 
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 3a6d4fb2a329..94dfda24c06e 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -564,6 +564,16 @@ struct block_device *bdget(dev_t dev)
 
 EXPORT_SYMBOL(bdget);
 
+/**
+ * bdgrab -- Grab a reference to an already referenced block device
+ * @bdev:	Block device to grab a reference to.
+ */
+struct block_device *bdgrab(struct block_device *bdev)
+{
+	atomic_inc(&bdev->bd_inode->i_count);
+	return bdev;
+}
+
 long nr_blockdev_pages(void)
 {
 	struct block_device *bdev;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 215ef8cae823..837435ce84ca 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -825,6 +825,7 @@ struct btrfs_fs_info {
 	struct mutex drop_mutex;
 	struct mutex volume_mutex;
 	struct mutex tree_reloc_mutex;
+	struct rw_semaphore extent_commit_sem;
 
 	/*
 	 * this protects the ordered operations list only while we are
@@ -959,9 +960,6 @@ struct btrfs_root {
 	/* the node lock is held while changing the node pointer */
 	spinlock_t node_lock;
 
-	/* taken when updating the commit root */
-	struct rw_semaphore commit_root_sem;
-
 	struct extent_buffer *commit_root;
 	struct btrfs_root *log_root;
 	struct btrfs_root *reloc_root;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 7dcaa8138864..e83be2e4602c 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -909,7 +909,6 @@ static int __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
 	spin_lock_init(&root->inode_lock);
 	mutex_init(&root->objectid_mutex);
 	mutex_init(&root->log_mutex);
-	init_rwsem(&root->commit_root_sem);
 	init_waitqueue_head(&root->log_writer_wait);
 	init_waitqueue_head(&root->log_commit_wait[0]);
 	init_waitqueue_head(&root->log_commit_wait[1]);
@@ -1640,6 +1639,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	mutex_init(&fs_info->cleaner_mutex);
 	mutex_init(&fs_info->volume_mutex);
 	mutex_init(&fs_info->tree_reloc_mutex);
+	init_rwsem(&fs_info->extent_commit_sem);
 
 	btrfs_init_free_cluster(&fs_info->meta_alloc_cluster);
 	btrfs_init_free_cluster(&fs_info->data_alloc_cluster);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index fadf69a2764b..72a2b9c28e9f 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -265,10 +265,6 @@ static int caching_kthread(void *data)
 
 	atomic_inc(&block_group->space_info->caching_threads);
 	last = max_t(u64, block_group->key.objectid, BTRFS_SUPER_INFO_OFFSET);
-again:
-	/* need to make sure the commit_root doesn't disappear */
-	down_read(&fs_info->extent_root->commit_root_sem);
-
 	/*
 	 * We don't want to deadlock with somebody trying to allocate a new
 	 * extent for the extent root while also trying to search the extent
@@ -282,6 +278,10 @@ again:
 	key.objectid = last;
 	key.offset = 0;
 	btrfs_set_key_type(&key, BTRFS_EXTENT_ITEM_KEY);
+again:
+	/* need to make sure the commit_root doesn't disappear */
+	down_read(&fs_info->extent_commit_sem);
+
 	ret = btrfs_search_slot(NULL, fs_info->extent_root, &key, path, 0, 0);
 	if (ret < 0)
 		goto err;
@@ -302,10 +302,24 @@ again:
 			else if (ret)
 				break;
 
-			if (need_resched()) {
+			if (need_resched() ||
+			    btrfs_transaction_in_commit(fs_info)) {
+				leaf = path->nodes[0];
+
+				/* this shouldn't happen, but if the
+				 * leaf is empty just move on.
+				 */
+				if (btrfs_header_nritems(leaf) == 0)
+					break;
+				/*
+				 * we need to copy the key out so that
+				 * we are sure the next search advances
+				 * us forward in the btree.
+				 */
+				btrfs_item_key_to_cpu(leaf, &key, 0);
 				btrfs_release_path(fs_info->extent_root, path);
-				up_read(&fs_info->extent_root->commit_root_sem);
-				cond_resched();
+				up_read(&fs_info->extent_commit_sem);
+				schedule_timeout(1);
 				goto again;
 			}
 
@@ -345,7 +359,7 @@ next:
 
 err:
 	btrfs_free_path(path);
-	up_read(&fs_info->extent_root->commit_root_sem);
+	up_read(&fs_info->extent_commit_sem);
 	atomic_dec(&block_group->space_info->caching_threads);
 	wake_up(&block_group->caching_q);
 
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index af99b78b288e..5edcee3a617f 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -414,11 +414,29 @@ static noinline int remove_from_bitmap(struct btrfs_block_group_cache *block_gro
 			      u64 *offset, u64 *bytes)
 {
 	u64 end;
+	u64 search_start, search_bytes;
+	int ret;
 
 again:
 	end = bitmap_info->offset +
 		(u64)(BITS_PER_BITMAP * block_group->sectorsize) - 1;
 
+	/*
+	 * XXX - this can go away after a few releases.
+	 *
+	 * since the only user of btrfs_remove_free_space is the tree logging
+	 * stuff, and the only way to test that is under crash conditions, we
+	 * want to have this debug stuff here just in case somethings not
+	 * working.  Search the bitmap for the space we are trying to use to
+	 * make sure its actually there.  If its not there then we need to stop
+	 * because something has gone wrong.
+	 */
+	search_start = *offset;
+	search_bytes = *bytes;
+	ret = search_bitmap(block_group, bitmap_info, &search_start,
+			    &search_bytes);
+	BUG_ON(ret < 0 || search_start != *offset);
+
 	if (*offset > bitmap_info->offset && *offset + *bytes > end) {
 		bitmap_clear_bits(block_group, bitmap_info, *offset,
 				  end - *offset + 1);
@@ -430,6 +448,7 @@ again:
 	}
 
 	if (*bytes) {
+		struct rb_node *next = rb_next(&bitmap_info->offset_index);
 		if (!bitmap_info->bytes) {
 			unlink_free_space(block_group, bitmap_info);
 			kfree(bitmap_info->bitmap);
@@ -438,16 +457,36 @@ again:
 			recalculate_thresholds(block_group);
 		}
 
-		bitmap_info = tree_search_offset(block_group,
-						 offset_to_bitmap(block_group,
-								  *offset),
-						 1, 0);
-		if (!bitmap_info)
+		/*
+		 * no entry after this bitmap, but we still have bytes to
+		 * remove, so something has gone wrong.
+		 */
+		if (!next)
 			return -EINVAL;
 
+		bitmap_info = rb_entry(next, struct btrfs_free_space,
+				       offset_index);
+
+		/*
+		 * if the next entry isn't a bitmap we need to return to let the
+		 * extent stuff do its work.
+		 */
 		if (!bitmap_info->bitmap)
 			return -EAGAIN;
 
+		/*
+		 * Ok the next item is a bitmap, but it may not actually hold
+		 * the information for the rest of this free space stuff, so
+		 * look for it, and if we don't find it return so we can try
+		 * everything over again.
+		 */
+		search_start = *offset;
+		search_bytes = *bytes;
+		ret = search_bitmap(block_group, bitmap_info, &search_start,
+				    &search_bytes);
+		if (ret < 0 || search_start != *offset)
+			return -EAGAIN;
+
 		goto again;
 	} else if (!bitmap_info->bytes) {
 		unlink_free_space(block_group, bitmap_info);
@@ -644,8 +683,17 @@ int btrfs_remove_free_space(struct btrfs_block_group_cache *block_group,
 again:
 	info = tree_search_offset(block_group, offset, 0, 0);
 	if (!info) {
-		WARN_ON(1);
-		goto out_lock;
+		/*
+		 * oops didn't find an extent that matched the space we wanted
+		 * to remove, look for a bitmap instead
+		 */
+		info = tree_search_offset(block_group,
+					  offset_to_bitmap(block_group, offset),
+					  1, 0);
+		if (!info) {
+			WARN_ON(1);
+			goto out_lock;
+		}
 	}
 
 	if (info->bytes < bytes && rb_next(&info->offset_index)) {
@@ -957,8 +1005,15 @@ static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group,
 	if (cluster->block_group != block_group)
 		goto out;
 
-	entry = tree_search_offset(block_group, search_start, 0, 0);
-
+	/*
+	 * search_start is the beginning of the bitmap, but at some point it may
+	 * be a good idea to point to the actual start of the free area in the
+	 * bitmap, so do the offset_to_bitmap trick anyway, and set bitmap_only
+	 * to 1 to make sure we get the bitmap entry
+	 */
+	entry = tree_search_offset(block_group,
+				   offset_to_bitmap(block_group, search_start),
+				   1, 0);
 	if (!entry || !entry->bitmap)
 		goto out;
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 56fe83fa60c4..272b9b2bea86 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4785,8 +4785,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	 * and the replacement file is large.  Start IO on it now so
 	 * we don't add too much work to the end of the transaction
 	 */
-	if (new_inode && old_inode && S_ISREG(old_inode->i_mode) &&
-	    new_inode->i_size &&
+	if (new_inode && S_ISREG(old_inode->i_mode) && new_inode->i_size &&
 	    old_inode->i_size > BTRFS_ORDERED_OPERATIONS_FLUSH_LIMIT)
 		filemap_flush(old_inode->i_mapping);
 
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index e71264d1c2c9..c04f7f212602 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -2553,8 +2553,13 @@ int relocate_inode_pages(struct inode *inode, u64 start, u64 len)
 	last_index = (start + len - 1) >> PAGE_CACHE_SHIFT;
 
 	/* make sure the dirty trick played by the caller work */
-	ret = invalidate_inode_pages2_range(inode->i_mapping,
-					    first_index, last_index);
+	while (1) {
+		ret = invalidate_inode_pages2_range(inode->i_mapping,
+						    first_index, last_index);
+		if (ret != -EBUSY)
+			break;
+		schedule_timeout(HZ/10);
+	}
 	if (ret)
 		goto out_unlock;
 
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index e51d2bc532f8..cdbb5022da52 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -42,10 +42,8 @@ static noinline void put_transaction(struct btrfs_transaction *transaction)
 
 static noinline void switch_commit_root(struct btrfs_root *root)
 {
-	down_write(&root->commit_root_sem);
 	free_extent_buffer(root->commit_root);
 	root->commit_root = btrfs_root_node(root);
-	up_write(&root->commit_root_sem);
 }
 
 /*
@@ -466,7 +464,10 @@ static int update_cowonly_root(struct btrfs_trans_handle *trans,
 		ret = btrfs_write_dirty_block_groups(trans, root);
 		BUG_ON(ret);
 	}
-	switch_commit_root(root);
+
+	if (root != root->fs_info->extent_root)
+		switch_commit_root(root);
+
 	return 0;
 }
 
@@ -499,6 +500,11 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans,
 
 		update_cowonly_root(trans, root);
 	}
+
+	down_write(&fs_info->extent_commit_sem);
+	switch_commit_root(fs_info->extent_root);
+	up_write(&fs_info->extent_commit_sem);
+
 	return 0;
 }
 
@@ -851,6 +857,16 @@ static void update_super_roots(struct btrfs_root *root)
 	super->root_level = root_item->level;
 }
 
+int btrfs_transaction_in_commit(struct btrfs_fs_info *info)
+{
+	int ret = 0;
+	spin_lock(&info->new_trans_lock);
+	if (info->running_transaction)
+		ret = info->running_transaction->in_commit;
+	spin_unlock(&info->new_trans_lock);
+	return ret;
+}
+
 int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root)
 {
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 961c3ee5a2e1..663c67404918 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -107,4 +107,5 @@ int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
 				struct btrfs_root *root);
 int btrfs_write_and_wait_marked_extents(struct btrfs_root *root,
 					struct extent_io_tree *dirty_pages);
+int btrfs_transaction_in_commit(struct btrfs_fs_info *info);
 #endif
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index ecfbce836d32..3e2b90eaa239 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -208,7 +208,7 @@ int btrfs_zlib_compress_pages(struct address_space *mapping,
 	*total_in = 0;
 
 	workspace = find_zlib_workspace();
-	if (!workspace)
+	if (IS_ERR(workspace))
 		return -1;
 
 	if (Z_OK != zlib_deflateInit(&workspace->def_strm, 3)) {
@@ -366,7 +366,7 @@ int btrfs_zlib_decompress_biovec(struct page **pages_in,
 	char *kaddr;
 
 	workspace = find_zlib_workspace();
-	if (!workspace)
+	if (IS_ERR(workspace))
 		return -ENOMEM;
 
 	data_in = kmap(pages_in[page_in_index]);
@@ -547,7 +547,7 @@ int btrfs_zlib_decompress(unsigned char *data_in,
 		return -ENOMEM;
 
 	workspace = find_zlib_workspace();
-	if (!workspace)
+	if (IS_ERR(workspace))
 		return -ENOMEM;
 
 	workspace->inf_strm.next_in = data_in;
diff --git a/fs/cifs/CHANGES b/fs/cifs/CHANGES
index 92888aa90749..e85b1e4389e0 100644
--- a/fs/cifs/CHANGES
+++ b/fs/cifs/CHANGES
@@ -1,3 +1,10 @@
+Version 1.60
+-------------
+Fix memory leak in reconnect.  Fix oops in DFS mount error path.
+Set s_maxbytes to smaller (the max that vfs can handle) so that
+sendfile will now work over cifs mounts again.  Add noforcegid
+and noforceuid mount parameters.
+
 Version 1.59
 ------------
 Client uses server inode numbers (which are persistent) rather than
diff --git a/fs/cifs/README b/fs/cifs/README
index ad92921dbde4..79c1a93400be 100644
--- a/fs/cifs/README
+++ b/fs/cifs/README
@@ -262,11 +262,11 @@ A partial list of the supported mount options follows:
 		mount.	
   domain	Set the SMB/CIFS workgroup name prepended to the
 		username during CIFS session establishment
-  forceuid	Set the default uid for inodes based on the uid
-		passed in. For mounts to servers
+  forceuid	Set the default uid for inodes to the uid
+		passed in on mount. For mounts to servers
 		which do support the CIFS Unix extensions, such as a
 		properly configured Samba server, the server provides
-		the uid, gid and mode so this parameter should  not be
+		the uid, gid and mode so this parameter should not be
 		specified unless the server and clients uid and gid
 		numbering differ.  If the server and client are in the
 		same domain (e.g. running winbind or nss_ldap) and
@@ -278,11 +278,7 @@ A partial list of the supported mount options follows:
 		of existing files will be the uid (gid) of the person
 		who executed the mount (root, except when mount.cifs
 		is configured setuid for user mounts) unless the "uid=" 
-		(gid) mount option is specified.  For the uid (gid) of newly
-		created files and directories, ie files created since 
-		the last mount of the server share, the expected uid 
-		(gid) is cached as long as the inode remains in 
-		memory on the client.   Also note that permission
+		(gid) mount option is specified. Also note that permission
 		checks (authorization checks) on accesses to a file occur
 		at the server, but there are cases in which an administrator
 		may want to restrict at the client as well.  For those
@@ -290,12 +286,15 @@ A partial list of the supported mount options follows:
 		(such as Windows), permissions can also be checked at the
 		client, and a crude form of client side permission checking 
 		can be enabled by specifying file_mode and dir_mode on 
-		the client.  Note that the mount.cifs helper must be
-		at version 1.10 or higher to support specifying the uid
-		(or gid) in non-numeric form.
-  forcegid	(similar to above but for the groupid instead of uid)
+		the client.  (default)
+  forcegid	(similar to above but for the groupid instead of uid) (default)
+  noforceuid	Fill in file owner information (uid) by requesting it from
+		the server if possible. With this option, the value given in
+		the uid= option (on mount) will only be used if the server
+		can not support returning uids on inodes.
+  noforcegid	(similar to above but for the group owner, gid, instead of uid)
   uid		Set the default uid for inodes, and indicate to the
-		cifs kernel driver which local user mounted . If the server
+		cifs kernel driver which local user mounted. If the server
 		supports the unix extensions the default uid is
 		not used to fill in the owner fields of inodes (files)
 		unless the "forceuid" parameter is specified.
diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index 3bb11be8b6a8..606912d8f2a8 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -55,7 +55,7 @@ void cifs_dfs_release_automount_timer(void)
  * i.e. strips from UNC trailing path that is not part of share
  * name and fixup missing '\' in the begining of DFS node refferal
  * if neccessary.
- * Returns pointer to share name on success or NULL on error.
+ * Returns pointer to share name on success or ERR_PTR on error.
  * Caller is responsible for freeing returned string.
  */
 static char *cifs_get_share_name(const char *node_name)
@@ -68,7 +68,7 @@ static char *cifs_get_share_name(const char *node_name)
 	UNC = kmalloc(len+2 /*for term null and additional \ if it's missed */,
 			 GFP_KERNEL);
 	if (!UNC)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	/* get share name and server name */
 	if (node_name[1] != '\\') {
@@ -87,7 +87,7 @@ static char *cifs_get_share_name(const char *node_name)
 		cERROR(1, ("%s: no server name end in node name: %s",
 			__func__, node_name));
 		kfree(UNC);
-		return NULL;
+		return ERR_PTR(-EINVAL);
 	}
 
 	/* find sharename end */
@@ -133,6 +133,12 @@ char *cifs_compose_mount_options(const char *sb_mountdata,
 		return ERR_PTR(-EINVAL);
 
 	*devname = cifs_get_share_name(ref->node_name);
+	if (IS_ERR(*devname)) {
+		rc = PTR_ERR(*devname);
+		*devname = NULL;
+		goto compose_mount_options_err;
+	}
+
 	rc = dns_resolve_server_name_to_ip(*devname, &srvIP);
 	if (rc != 0) {
 		cERROR(1, ("%s: Failed to resolve server part of %s to IP: %d",
diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c
index 60e3c4253de0..714a542cbafc 100644
--- a/fs/cifs/cifs_unicode.c
+++ b/fs/cifs/cifs_unicode.c
@@ -44,7 +44,7 @@ cifs_ucs2_bytes(const __le16 *from, int maxbytes,
 	int maxwords = maxbytes / 2;
 	char tmp[NLS_MAX_CHARSET_SIZE];
 
-	for (i = 0; from[i] && i < maxwords; i++) {
+	for (i = 0; i < maxwords && from[i]; i++) {
 		charlen = codepage->uni2char(le16_to_cpu(from[i]), tmp,
 					     NLS_MAX_CHARSET_SIZE);
 		if (charlen > 0)
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 44f30504b82d..84b75253b05a 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -376,10 +376,14 @@ cifs_show_options(struct seq_file *s, struct vfsmount *m)
 	seq_printf(s, ",uid=%d", cifs_sb->mnt_uid);
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_UID)
 		seq_printf(s, ",forceuid");
+	else
+		seq_printf(s, ",noforceuid");
 
 	seq_printf(s, ",gid=%d", cifs_sb->mnt_gid);
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_OVERR_GID)
 		seq_printf(s, ",forcegid");
+	else
+		seq_printf(s, ",noforcegid");
 
 	cifs_show_address(s, tcon->ses->server);
 
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index fafff3e359e5..67046053f61e 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -803,6 +803,10 @@ cifs_parse_mount_options(char *options, const char *devname,
 	char *data;
 	unsigned int  temp_len, i, j;
 	char separator[2];
+	short int override_uid = -1;
+	short int override_gid = -1;
+	bool uid_specified = false;
+	bool gid_specified = false;
 
 	separator[0] = ',';
 	separator[1] = 0;
@@ -1093,18 +1097,20 @@ cifs_parse_mount_options(char *options, const char *devname,
 						    "too long.\n");
 				return 1;
 			}
-		} else if (strnicmp(data, "uid", 3) == 0) {
-			if (value && *value)
-				vol->linux_uid =
-					simple_strtoul(value, &value, 0);
-		} else if (strnicmp(data, "forceuid", 8) == 0) {
-				vol->override_uid = 1;
-		} else if (strnicmp(data, "gid", 3) == 0) {
-			if (value && *value)
-				vol->linux_gid =
-					simple_strtoul(value, &value, 0);
-		} else if (strnicmp(data, "forcegid", 8) == 0) {
-				vol->override_gid = 1;
+		} else if (!strnicmp(data, "uid", 3) && value && *value) {
+			vol->linux_uid = simple_strtoul(value, &value, 0);
+			uid_specified = true;
+		} else if (!strnicmp(data, "forceuid", 8)) {
+			override_uid = 1;
+		} else if (!strnicmp(data, "noforceuid", 10)) {
+			override_uid = 0;
+		} else if (!strnicmp(data, "gid", 3) && value && *value) {
+			vol->linux_gid = simple_strtoul(value, &value, 0);
+			gid_specified = true;
+		} else if (!strnicmp(data, "forcegid", 8)) {
+			override_gid = 1;
+		} else if (!strnicmp(data, "noforcegid", 10)) {
+			override_gid = 0;
 		} else if (strnicmp(data, "file_mode", 4) == 0) {
 			if (value && *value) {
 				vol->file_mode =
@@ -1355,6 +1361,18 @@ cifs_parse_mount_options(char *options, const char *devname,
 	if (vol->UNCip == NULL)
 		vol->UNCip = &vol->UNC[2];
 
+	if (uid_specified)
+		vol->override_uid = override_uid;
+	else if (override_uid == 1)
+		printk(KERN_NOTICE "CIFS: ignoring forceuid mount option "
+				   "specified with no uid= option.\n");
+
+	if (gid_specified)
+		vol->override_gid = override_gid;
+	else if (override_gid == 1)
+		printk(KERN_NOTICE "CIFS: ignoring forcegid mount option "
+				   "specified with no gid= option.\n");
+
 	return 0;
 }
 
@@ -2544,11 +2562,20 @@ remote_path_check:
 
 			if (mount_data != mount_data_global)
 				kfree(mount_data);
+
 			mount_data = cifs_compose_mount_options(
 					cifs_sb->mountdata, full_path + 1,
 					referrals, &fake_devname);
-			kfree(fake_devname);
+
 			free_dfs_info_array(referrals, num_referrals);
+			kfree(fake_devname);
+			kfree(full_path);
+
+			if (IS_ERR(mount_data)) {
+				rc = PTR_ERR(mount_data);
+				mount_data = NULL;
+				goto mount_fail_check;
+			}
 
 			if (tcon)
 				cifs_put_tcon(tcon);
@@ -2556,8 +2583,6 @@ remote_path_check:
 				cifs_put_smb_ses(pSesInfo);
 
 			cleanup_volume_info(&volume_info);
-			FreeXid(xid);
-			kfree(full_path);
 			referral_walks_count++;
 			goto try_mount_again;
 		}
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index f28f070a60fc..f91fd51b32e3 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -1905,6 +1905,7 @@ COMPATIBLE_IOCTL(FIONCLEX)
 COMPATIBLE_IOCTL(FIOASYNC)
 COMPATIBLE_IOCTL(FIONBIO)
 COMPATIBLE_IOCTL(FIONREAD)  /* This is also TIOCINQ */
+COMPATIBLE_IOCTL(FS_IOC_FIEMAP)
 /* 0x00 */
 COMPATIBLE_IOCTL(FIBMAP)
 COMPATIBLE_IOCTL(FIGETBSZ)
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 03ebb439ace0..7ebae9a4ecc0 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -624,6 +624,7 @@ static int gfs2_write_begin(struct file *file, struct address_space *mapping,
 {
 	struct gfs2_inode *ip = GFS2_I(mapping->host);
 	struct gfs2_sbd *sdp = GFS2_SB(mapping->host);
+	struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
 	unsigned int data_blocks = 0, ind_blocks = 0, rblocks;
 	int alloc_required;
 	int error = 0;
@@ -637,6 +638,14 @@ static int gfs2_write_begin(struct file *file, struct address_space *mapping,
 	error = gfs2_glock_nq(&ip->i_gh);
 	if (unlikely(error))
 		goto out_uninit;
+	if (&ip->i_inode == sdp->sd_rindex) {
+		error = gfs2_glock_nq_init(m_ip->i_gl, LM_ST_EXCLUSIVE,
+					   GL_NOCACHE, &m_ip->i_gh);
+		if (unlikely(error)) {
+			gfs2_glock_dq(&ip->i_gh);
+			goto out_uninit;
+		}
+	}
 
 	error = gfs2_write_alloc_required(ip, pos, len, &alloc_required);
 	if (error)
@@ -667,6 +676,8 @@ static int gfs2_write_begin(struct file *file, struct address_space *mapping,
 		rblocks += data_blocks ? data_blocks : 1;
 	if (ind_blocks || data_blocks)
 		rblocks += RES_STATFS + RES_QUOTA;
+	if (&ip->i_inode == sdp->sd_rindex)
+		rblocks += 2 * RES_STATFS;
 
 	error = gfs2_trans_begin(sdp, rblocks,
 				 PAGE_CACHE_SIZE/sdp->sd_sb.sb_bsize);
@@ -712,6 +723,10 @@ out_alloc_put:
 		gfs2_alloc_put(ip);
 	}
 out_unlock:
+	if (&ip->i_inode == sdp->sd_rindex) {
+		gfs2_glock_dq(&m_ip->i_gh);
+		gfs2_holder_uninit(&m_ip->i_gh);
+	}
 	gfs2_glock_dq(&ip->i_gh);
 out_uninit:
 	gfs2_holder_uninit(&ip->i_gh);
@@ -725,14 +740,21 @@ out_uninit:
 static void adjust_fs_space(struct inode *inode)
 {
 	struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
+	struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
+	struct gfs2_inode *l_ip = GFS2_I(sdp->sd_sc_inode);
 	struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
 	struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
+	struct buffer_head *m_bh, *l_bh;
 	u64 fs_total, new_free;
 
 	/* Total up the file system space, according to the latest rindex. */
 	fs_total = gfs2_ri_total(sdp);
+	if (gfs2_meta_inode_buffer(m_ip, &m_bh) != 0)
+		return;
 
 	spin_lock(&sdp->sd_statfs_spin);
+	gfs2_statfs_change_in(m_sc, m_bh->b_data +
+			      sizeof(struct gfs2_dinode));
 	if (fs_total > (m_sc->sc_total + l_sc->sc_total))
 		new_free = fs_total - (m_sc->sc_total + l_sc->sc_total);
 	else
@@ -741,6 +763,13 @@ static void adjust_fs_space(struct inode *inode)
 	fs_warn(sdp, "File system extended by %llu blocks.\n",
 		(unsigned long long)new_free);
 	gfs2_statfs_change(sdp, new_free, new_free, 0);
+
+	if (gfs2_meta_inode_buffer(l_ip, &l_bh) != 0)
+		goto out;
+	update_statfs(sdp, m_bh, l_bh);
+	brelse(l_bh);
+out:
+	brelse(m_bh);
 }
 
 /**
@@ -763,6 +792,7 @@ static int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
 	u64 to = pos + copied;
 	void *kaddr;
 	unsigned char *buf = dibh->b_data + sizeof(struct gfs2_dinode);
@@ -794,6 +824,10 @@ static int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
 
 	brelse(dibh);
 	gfs2_trans_end(sdp);
+	if (inode == sdp->sd_rindex) {
+		gfs2_glock_dq(&m_ip->i_gh);
+		gfs2_holder_uninit(&m_ip->i_gh);
+	}
 	gfs2_glock_dq(&ip->i_gh);
 	gfs2_holder_uninit(&ip->i_gh);
 	return copied;
@@ -823,6 +857,7 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping,
 	struct inode *inode = page->mapping->host;
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
 	struct buffer_head *dibh;
 	struct gfs2_alloc *al = ip->i_alloc;
 	unsigned int from = pos & (PAGE_CACHE_SIZE - 1);
@@ -865,6 +900,10 @@ failed:
 		gfs2_quota_unlock(ip);
 		gfs2_alloc_put(ip);
 	}
+	if (inode == sdp->sd_rindex) {
+		gfs2_glock_dq(&m_ip->i_gh);
+		gfs2_holder_uninit(&m_ip->i_gh);
+	}
 	gfs2_glock_dq(&ip->i_gh);
 	gfs2_holder_uninit(&ip->i_gh);
 	return ret;
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 297421c0427a..8b674b1f3a55 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -63,6 +63,7 @@ static void do_xmote(struct gfs2_glock *gl, struct gfs2_holder *gh, unsigned int
 static DECLARE_RWSEM(gfs2_umount_flush_sem);
 static struct dentry *gfs2_root;
 static struct workqueue_struct *glock_workqueue;
+struct workqueue_struct *gfs2_delete_workqueue;
 static LIST_HEAD(lru_list);
 static atomic_t lru_count = ATOMIC_INIT(0);
 static DEFINE_SPINLOCK(lru_lock);
@@ -167,13 +168,33 @@ static void glock_free(struct gfs2_glock *gl)
  *
  */
 
-static void gfs2_glock_hold(struct gfs2_glock *gl)
+void gfs2_glock_hold(struct gfs2_glock *gl)
 {
 	GLOCK_BUG_ON(gl, atomic_read(&gl->gl_ref) == 0);
 	atomic_inc(&gl->gl_ref);
 }
 
 /**
+ * demote_ok - Check to see if it's ok to unlock a glock
+ * @gl: the glock
+ *
+ * Returns: 1 if it's ok
+ */
+
+static int demote_ok(const struct gfs2_glock *gl)
+{
+	const struct gfs2_glock_operations *glops = gl->gl_ops;
+
+	if (gl->gl_state == LM_ST_UNLOCKED)
+		return 0;
+	if (!list_empty(&gl->gl_holders))
+		return 0;
+	if (glops->go_demote_ok)
+		return glops->go_demote_ok(gl);
+	return 1;
+}
+
+/**
  * gfs2_glock_schedule_for_reclaim - Add a glock to the reclaim list
  * @gl: the glock
  *
@@ -181,8 +202,13 @@ static void gfs2_glock_hold(struct gfs2_glock *gl)
 
 static void gfs2_glock_schedule_for_reclaim(struct gfs2_glock *gl)
 {
+	int may_reclaim;
+	may_reclaim = (demote_ok(gl) &&
+		       (atomic_read(&gl->gl_ref) == 1 ||
+			(gl->gl_name.ln_type == LM_TYPE_INODE &&
+			 atomic_read(&gl->gl_ref) <= 2)));
 	spin_lock(&lru_lock);
-	if (list_empty(&gl->gl_lru) && gl->gl_state != LM_ST_UNLOCKED) {
+	if (list_empty(&gl->gl_lru) && may_reclaim) {
 		list_add_tail(&gl->gl_lru, &lru_list);
 		atomic_inc(&lru_count);
 	}
@@ -190,6 +216,21 @@ static void gfs2_glock_schedule_for_reclaim(struct gfs2_glock *gl)
 }
 
 /**
+ * gfs2_glock_put_nolock() - Decrement reference count on glock
+ * @gl: The glock to put
+ *
+ * This function should only be used if the caller has its own reference
+ * to the glock, in addition to the one it is dropping.
+ */
+
+void gfs2_glock_put_nolock(struct gfs2_glock *gl)
+{
+	if (atomic_dec_and_test(&gl->gl_ref))
+		GLOCK_BUG_ON(gl, 1);
+	gfs2_glock_schedule_for_reclaim(gl);
+}
+
+/**
  * gfs2_glock_put() - Decrement reference count on glock
  * @gl: The glock to put
  *
@@ -214,9 +255,9 @@ int gfs2_glock_put(struct gfs2_glock *gl)
 		rv = 1;
 		goto out;
 	}
-	/* 1 for being hashed, 1 for having state != LM_ST_UNLOCKED */
-	if (atomic_read(&gl->gl_ref) == 2)
-		gfs2_glock_schedule_for_reclaim(gl);
+	spin_lock(&gl->gl_spin);
+	gfs2_glock_schedule_for_reclaim(gl);
+	spin_unlock(&gl->gl_spin);
 	write_unlock(gl_lock_addr(gl->gl_hash));
 out:
 	return rv;
@@ -398,7 +439,7 @@ static void state_change(struct gfs2_glock *gl, unsigned int new_state)
 		if (held2)
 			gfs2_glock_hold(gl);
 		else
-			gfs2_glock_put(gl);
+			gfs2_glock_put_nolock(gl);
 	}
 
 	gl->gl_state = new_state;
@@ -633,12 +674,35 @@ out:
 out_sched:
 	gfs2_glock_hold(gl);
 	if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
-		gfs2_glock_put(gl);
+		gfs2_glock_put_nolock(gl);
 out_unlock:
 	clear_bit(GLF_LOCK, &gl->gl_flags);
 	goto out;
 }
 
+static void delete_work_func(struct work_struct *work)
+{
+	struct gfs2_glock *gl = container_of(work, struct gfs2_glock, gl_delete);
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_inode *ip = NULL;
+	struct inode *inode;
+	u64 no_addr = 0;
+
+	spin_lock(&gl->gl_spin);
+	ip = (struct gfs2_inode *)gl->gl_object;
+	if (ip)
+		no_addr = ip->i_no_addr;
+	spin_unlock(&gl->gl_spin);
+	if (ip) {
+		inode = gfs2_ilookup(sdp->sd_vfs, no_addr);
+		if (inode) {
+			d_prune_aliases(inode);
+			iput(inode);
+		}
+	}
+	gfs2_glock_put(gl);
+}
+
 static void glock_work_func(struct work_struct *work)
 {
 	unsigned long delay = 0;
@@ -717,6 +781,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 	gl->gl_sbd = sdp;
 	gl->gl_aspace = NULL;
 	INIT_DELAYED_WORK(&gl->gl_work, glock_work_func);
+	INIT_WORK(&gl->gl_delete, delete_work_func);
 
 	/* If this glock protects actual on-disk data or metadata blocks,
 	   create a VFS inode to manage the pages/buffers holding them. */
@@ -858,6 +923,8 @@ static void handle_callback(struct gfs2_glock *gl, unsigned int state,
 			gl->gl_demote_state != state) {
 		gl->gl_demote_state = LM_ST_UNLOCKED;
 	}
+	if (gl->gl_ops->go_callback)
+		gl->gl_ops->go_callback(gl);
 	trace_gfs2_demote_rq(gl);
 }
 
@@ -1274,33 +1341,12 @@ void gfs2_glock_complete(struct gfs2_glock *gl, int ret)
 		gfs2_glock_put(gl);
 }
 
-/**
- * demote_ok - Check to see if it's ok to unlock a glock
- * @gl: the glock
- *
- * Returns: 1 if it's ok
- */
-
-static int demote_ok(const struct gfs2_glock *gl)
-{
-	const struct gfs2_glock_operations *glops = gl->gl_ops;
-
-	if (gl->gl_state == LM_ST_UNLOCKED)
-		return 0;
-	if (!list_empty(&gl->gl_holders))
-		return 0;
-	if (glops->go_demote_ok)
-		return glops->go_demote_ok(gl);
-	return 1;
-}
-
 
 static int gfs2_shrink_glock_memory(int nr, gfp_t gfp_mask)
 {
 	struct gfs2_glock *gl;
 	int may_demote;
 	int nr_skipped = 0;
-	int got_ref = 0;
 	LIST_HEAD(skipped);
 
 	if (nr == 0)
@@ -1315,37 +1361,29 @@ static int gfs2_shrink_glock_memory(int nr, gfp_t gfp_mask)
 		list_del_init(&gl->gl_lru);
 		atomic_dec(&lru_count);
 
+		/* Check if glock is about to be freed */
+		if (atomic_read(&gl->gl_ref) == 0)
+			continue;
+
 		/* Test for being demotable */
 		if (!test_and_set_bit(GLF_LOCK, &gl->gl_flags)) {
 			gfs2_glock_hold(gl);
-			got_ref = 1;
 			spin_unlock(&lru_lock);
 			spin_lock(&gl->gl_spin);
 			may_demote = demote_ok(gl);
-			spin_unlock(&gl->gl_spin);
-			clear_bit(GLF_LOCK, &gl->gl_flags);
 			if (may_demote) {
 				handle_callback(gl, LM_ST_UNLOCKED, 0);
 				nr--;
-				if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
-					gfs2_glock_put(gl);
-				got_ref = 0;
 			}
+			if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
+				gfs2_glock_put_nolock(gl);
+			spin_unlock(&gl->gl_spin);
+			clear_bit(GLF_LOCK, &gl->gl_flags);
 			spin_lock(&lru_lock);
-			if (may_demote)
-				continue;
-		}
-		if (list_empty(&gl->gl_lru) &&
-		    (atomic_read(&gl->gl_ref) <= (2 + got_ref))) {
-			nr_skipped++;
-			list_add(&gl->gl_lru, &skipped);
-		}
-		if (got_ref) {
-			spin_unlock(&lru_lock);
-			gfs2_glock_put(gl);
-			spin_lock(&lru_lock);
-			got_ref = 0;
+			continue;
 		}
+		nr_skipped++;
+		list_add(&gl->gl_lru, &skipped);
 	}
 	list_splice(&skipped, &lru_list);
 	atomic_add(nr_skipped, &lru_count);
@@ -1727,6 +1765,11 @@ int __init gfs2_glock_init(void)
 	glock_workqueue = create_workqueue("glock_workqueue");
 	if (IS_ERR(glock_workqueue))
 		return PTR_ERR(glock_workqueue);
+	gfs2_delete_workqueue = create_workqueue("delete_workqueue");
+	if (IS_ERR(gfs2_delete_workqueue)) {
+		destroy_workqueue(glock_workqueue);
+		return PTR_ERR(gfs2_delete_workqueue);
+	}
 
 	register_shrinker(&glock_shrinker);
 
@@ -1737,6 +1780,7 @@ void gfs2_glock_exit(void)
 {
 	unregister_shrinker(&glock_shrinker);
 	destroy_workqueue(glock_workqueue);
+	destroy_workqueue(gfs2_delete_workqueue);
 }
 
 static int gfs2_glock_iter_next(struct gfs2_glock_iter *gi)
diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h
index a602a28f6f08..c609894ec0d0 100644
--- a/fs/gfs2/glock.h
+++ b/fs/gfs2/glock.h
@@ -143,6 +143,7 @@ struct lm_lockops {
 
 #define GLR_TRYFAILED		13
 
+extern struct workqueue_struct *gfs2_delete_workqueue;
 static inline struct gfs2_holder *gfs2_glock_is_locked_by_me(struct gfs2_glock *gl)
 {
 	struct gfs2_holder *gh;
@@ -191,6 +192,8 @@ static inline int gfs2_glock_is_blocking(struct gfs2_glock *gl)
 int gfs2_glock_get(struct gfs2_sbd *sdp,
 		   u64 number, const struct gfs2_glock_operations *glops,
 		   int create, struct gfs2_glock **glp);
+void gfs2_glock_hold(struct gfs2_glock *gl);
+void gfs2_glock_put_nolock(struct gfs2_glock *gl);
 int gfs2_glock_put(struct gfs2_glock *gl);
 void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, unsigned flags,
 		      struct gfs2_holder *gh);
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index d5e4ab155ca0..6985eef06c39 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -323,6 +323,7 @@ static void trans_go_sync(struct gfs2_glock *gl)
 
 	if (gl->gl_state != LM_ST_UNLOCKED &&
 	    test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
+		flush_workqueue(gfs2_delete_workqueue);
 		gfs2_meta_syncfs(sdp);
 		gfs2_log_shutdown(sdp);
 	}
@@ -372,6 +373,25 @@ static int trans_go_demote_ok(const struct gfs2_glock *gl)
 	return 0;
 }
 
+/**
+ * iopen_go_callback - schedule the dcache entry for the inode to be deleted
+ * @gl: the glock
+ *
+ * gl_spin lock is held while calling this
+ */
+static void iopen_go_callback(struct gfs2_glock *gl)
+{
+	struct gfs2_inode *ip = (struct gfs2_inode *)gl->gl_object;
+
+	if (gl->gl_demote_state == LM_ST_UNLOCKED &&
+	    gl->gl_state == LM_ST_SHARED &&
+	    ip && test_bit(GIF_USER, &ip->i_flags)) {
+		gfs2_glock_hold(gl);
+		if (queue_work(gfs2_delete_workqueue, &gl->gl_delete) == 0)
+			gfs2_glock_put_nolock(gl);
+	}
+}
+
 const struct gfs2_glock_operations gfs2_meta_glops = {
 	.go_type = LM_TYPE_META,
 };
@@ -406,6 +426,7 @@ const struct gfs2_glock_operations gfs2_trans_glops = {
 
 const struct gfs2_glock_operations gfs2_iopen_glops = {
 	.go_type = LM_TYPE_IOPEN,
+	.go_callback = iopen_go_callback,
 };
 
 const struct gfs2_glock_operations gfs2_flock_glops = {
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 225347fbff3c..61801ada36f0 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -159,6 +159,7 @@ struct gfs2_glock_operations {
 	int (*go_lock) (struct gfs2_holder *gh);
 	void (*go_unlock) (struct gfs2_holder *gh);
 	int (*go_dump)(struct seq_file *seq, const struct gfs2_glock *gl);
+	void (*go_callback) (struct gfs2_glock *gl);
 	const int go_type;
 	const unsigned long go_min_hold_time;
 };
@@ -228,6 +229,7 @@ struct gfs2_glock {
 	struct list_head gl_ail_list;
 	atomic_t gl_ail_count;
 	struct delayed_work gl_work;
+	struct work_struct gl_delete;
 };
 
 #define GFS2_MIN_LVB_SIZE 32	/* Min size of LVB that gfs2 supports */
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index daa4ae341a29..fba795798d3a 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -285,27 +285,19 @@ void gfs2_rgrp_verify(struct gfs2_rgrpd *rgd)
 	}
 
 	tmp = rgd->rd_data - rgd->rd_free - rgd->rd_dinodes;
-	if (count[1] + count[2] != tmp) {
+	if (count[1] != tmp) {
 		if (gfs2_consist_rgrpd(rgd))
 			fs_err(sdp, "used data mismatch:  %u != %u\n",
 			       count[1], tmp);
 		return;
 	}
 
-	if (count[3] != rgd->rd_dinodes) {
+	if (count[2] + count[3] != rgd->rd_dinodes) {
 		if (gfs2_consist_rgrpd(rgd))
 			fs_err(sdp, "used metadata mismatch:  %u != %u\n",
-			       count[3], rgd->rd_dinodes);
+			       count[2] + count[3], rgd->rd_dinodes);
 		return;
 	}
-
-	if (count[2] > count[3]) {
-		if (gfs2_consist_rgrpd(rgd))
-			fs_err(sdp, "unlinked inodes > inodes:  %u\n",
-			       count[2]);
-		return;
-	}
-
 }
 
 static inline int rgrp_contains_block(struct gfs2_rgrpd *rgd, u64 block)
@@ -961,7 +953,8 @@ static int try_rgrp_fit(struct gfs2_rgrpd *rgd, struct gfs2_alloc *al)
  * Returns: The inode, if one has been found
  */
 
-static struct inode *try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked)
+static struct inode *try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked,
+				     u64 skip)
 {
 	struct inode *inode;
 	u32 goal = 0, block;
@@ -985,6 +978,8 @@ static struct inode *try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked)
 		goal++;
 		if (*last_unlinked != NO_BLOCK && no_addr <= *last_unlinked)
 			continue;
+		if (no_addr == skip)
+			continue;
 		*last_unlinked = no_addr;
 		inode = gfs2_inode_lookup(rgd->rd_sbd->sd_vfs, DT_UNKNOWN,
 					  no_addr, -1, 1);
@@ -1104,7 +1099,7 @@ static struct inode *get_local_rgrp(struct gfs2_inode *ip, u64 *last_unlinked)
 			if (try_rgrp_fit(rgd, al))
 				goto out;
 			if (rgd->rd_flags & GFS2_RDF_CHECK)
-				inode = try_rgrp_unlink(rgd, last_unlinked);
+				inode = try_rgrp_unlink(rgd, last_unlinked, ip->i_no_addr);
 			if (!rg_locked)
 				gfs2_glock_dq_uninit(&al->al_rgd_gh);
 			if (inode)
@@ -1138,7 +1133,7 @@ static struct inode *get_local_rgrp(struct gfs2_inode *ip, u64 *last_unlinked)
 			if (try_rgrp_fit(rgd, al))
 				goto out;
 			if (rgd->rd_flags & GFS2_RDF_CHECK)
-				inode = try_rgrp_unlink(rgd, last_unlinked);
+				inode = try_rgrp_unlink(rgd, last_unlinked, ip->i_no_addr);
 			if (!rg_locked)
 				gfs2_glock_dq_uninit(&al->al_rgd_gh);
 			if (inode)
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 0a6801336470..f522bb017973 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -353,7 +353,7 @@ fail:
 	return error;
 }
 
-static void gfs2_statfs_change_in(struct gfs2_statfs_change_host *sc, const void *buf)
+void gfs2_statfs_change_in(struct gfs2_statfs_change_host *sc, const void *buf)
 {
 	const struct gfs2_statfs_change *str = buf;
 
@@ -441,6 +441,29 @@ void gfs2_statfs_change(struct gfs2_sbd *sdp, s64 total, s64 free,
 	brelse(l_bh);
 }
 
+void update_statfs(struct gfs2_sbd *sdp, struct buffer_head *m_bh,
+		   struct buffer_head *l_bh)
+{
+	struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
+	struct gfs2_inode *l_ip = GFS2_I(sdp->sd_sc_inode);
+	struct gfs2_statfs_change_host *m_sc = &sdp->sd_statfs_master;
+	struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
+
+	gfs2_trans_add_bh(l_ip->i_gl, l_bh, 1);
+
+	spin_lock(&sdp->sd_statfs_spin);
+	m_sc->sc_total += l_sc->sc_total;
+	m_sc->sc_free += l_sc->sc_free;
+	m_sc->sc_dinodes += l_sc->sc_dinodes;
+	memset(l_sc, 0, sizeof(struct gfs2_statfs_change));
+	memset(l_bh->b_data + sizeof(struct gfs2_dinode),
+	       0, sizeof(struct gfs2_statfs_change));
+	spin_unlock(&sdp->sd_statfs_spin);
+
+	gfs2_trans_add_bh(m_ip->i_gl, m_bh, 1);
+	gfs2_statfs_change_out(m_sc, m_bh->b_data + sizeof(struct gfs2_dinode));
+}
+
 int gfs2_statfs_sync(struct gfs2_sbd *sdp)
 {
 	struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
@@ -477,19 +500,7 @@ int gfs2_statfs_sync(struct gfs2_sbd *sdp)
 	if (error)
 		goto out_bh2;
 
-	gfs2_trans_add_bh(l_ip->i_gl, l_bh, 1);
-
-	spin_lock(&sdp->sd_statfs_spin);
-	m_sc->sc_total += l_sc->sc_total;
-	m_sc->sc_free += l_sc->sc_free;
-	m_sc->sc_dinodes += l_sc->sc_dinodes;
-	memset(l_sc, 0, sizeof(struct gfs2_statfs_change));
-	memset(l_bh->b_data + sizeof(struct gfs2_dinode),
-	       0, sizeof(struct gfs2_statfs_change));
-	spin_unlock(&sdp->sd_statfs_spin);
-
-	gfs2_trans_add_bh(m_ip->i_gl, m_bh, 1);
-	gfs2_statfs_change_out(m_sc, m_bh->b_data + sizeof(struct gfs2_dinode));
+	update_statfs(sdp, m_bh, l_bh);
 
 	gfs2_trans_end(sdp);
 
@@ -680,6 +691,7 @@ static int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
 	struct gfs2_holder t_gh;
 	int error;
 
+	flush_workqueue(gfs2_delete_workqueue);
 	gfs2_quota_sync(sdp);
 	gfs2_statfs_sync(sdp);
 
diff --git a/fs/gfs2/super.h b/fs/gfs2/super.h
index b56413e3e40d..22e0417ed996 100644
--- a/fs/gfs2/super.h
+++ b/fs/gfs2/super.h
@@ -40,6 +40,10 @@ extern int gfs2_make_fs_rw(struct gfs2_sbd *sdp);
 extern int gfs2_statfs_init(struct gfs2_sbd *sdp);
 extern void gfs2_statfs_change(struct gfs2_sbd *sdp, s64 total, s64 free,
 			       s64 dinodes);
+extern void gfs2_statfs_change_in(struct gfs2_statfs_change_host *sc,
+				  const void *buf);
+extern void update_statfs(struct gfs2_sbd *sdp, struct buffer_head *m_bh,
+			  struct buffer_head *l_bh);
 extern int gfs2_statfs_sync(struct gfs2_sbd *sdp);
 
 extern int gfs2_freeze_fs(struct gfs2_sbd *sdp);
diff --git a/fs/inode.c b/fs/inode.c
index cb277d694a32..a9588139127f 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -120,12 +120,11 @@ static void wake_up_inode(struct inode *inode)
  * These are initializations that need to be done on every inode
  * allocation as the fields are not initialised by slab allocation.
  */
-struct inode *inode_init_always(struct super_block *sb, struct inode *inode)
+int inode_init_always(struct super_block *sb, struct inode *inode)
 {
 	static const struct address_space_operations empty_aops;
 	static struct inode_operations empty_iops;
 	static const struct file_operations empty_fops;
-
 	struct address_space *const mapping = &inode->i_data;
 
 	inode->i_sb = sb;
@@ -152,7 +151,7 @@ struct inode *inode_init_always(struct super_block *sb, struct inode *inode)
 	inode->dirtied_when = 0;
 
 	if (security_inode_alloc(inode))
-		goto out_free_inode;
+		goto out;
 
 	/* allocate and initialize an i_integrity */
 	if (ima_inode_alloc(inode))
@@ -198,16 +197,12 @@ struct inode *inode_init_always(struct super_block *sb, struct inode *inode)
 	inode->i_fsnotify_mask = 0;
 #endif
 
-	return inode;
+	return 0;
 
 out_free_security:
 	security_inode_free(inode);
-out_free_inode:
-	if (inode->i_sb->s_op->destroy_inode)
-		inode->i_sb->s_op->destroy_inode(inode);
-	else
-		kmem_cache_free(inode_cachep, (inode));
-	return NULL;
+out:
+	return -ENOMEM;
 }
 EXPORT_SYMBOL(inode_init_always);
 
@@ -220,12 +215,21 @@ static struct inode *alloc_inode(struct super_block *sb)
 	else
 		inode = kmem_cache_alloc(inode_cachep, GFP_KERNEL);
 
-	if (inode)
-		return inode_init_always(sb, inode);
-	return NULL;
+	if (!inode)
+		return NULL;
+
+	if (unlikely(inode_init_always(sb, inode))) {
+		if (inode->i_sb->s_op->destroy_inode)
+			inode->i_sb->s_op->destroy_inode(inode);
+		else
+			kmem_cache_free(inode_cachep, inode);
+		return NULL;
+	}
+
+	return inode;
 }
 
-void destroy_inode(struct inode *inode)
+void __destroy_inode(struct inode *inode)
 {
 	BUG_ON(inode_has_buffers(inode));
 	ima_inode_free(inode);
@@ -237,13 +241,17 @@ void destroy_inode(struct inode *inode)
 	if (inode->i_default_acl && inode->i_default_acl != ACL_NOT_CACHED)
 		posix_acl_release(inode->i_default_acl);
 #endif
+}
+EXPORT_SYMBOL(__destroy_inode);
+
+void destroy_inode(struct inode *inode)
+{
+	__destroy_inode(inode);
 	if (inode->i_sb->s_op->destroy_inode)
 		inode->i_sb->s_op->destroy_inode(inode);
 	else
 		kmem_cache_free(inode_cachep, (inode));
 }
-EXPORT_SYMBOL(destroy_inode);
-
 
 /*
  * These are initializations that only need to be done
diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c
index 5edc2bf20581..23c947539864 100644
--- a/fs/jffs2/file.c
+++ b/fs/jffs2/file.c
@@ -99,7 +99,7 @@ static int jffs2_do_readpage_nolock (struct inode *inode, struct page *pg)
 	kunmap(pg);
 
 	D2(printk(KERN_DEBUG "readpage finished\n"));
-	return 0;
+	return ret;
 }
 
 int jffs2_do_readpage_unlock(struct inode *inode, struct page *pg)
diff --git a/fs/namespace.c b/fs/namespace.c
index 277c28a63ead..7230787d18b0 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -316,7 +316,8 @@ EXPORT_SYMBOL_GPL(mnt_clone_write);
  */
 int mnt_want_write_file(struct file *file)
 {
-	if (!(file->f_mode & FMODE_WRITE))
+	struct inode *inode = file->f_dentry->d_inode;
+	if (!(file->f_mode & FMODE_WRITE) || special_file(inode->i_mode))
 		return mnt_want_write(file->f_path.mnt);
 	else
 		return mnt_clone_write(file->f_path.mnt);
diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
index 1fe77872cf50..42b639445af5 100644
--- a/fs/nilfs2/mdt.c
+++ b/fs/nilfs2/mdt.c
@@ -412,8 +412,10 @@ nilfs_mdt_write_page(struct page *page, struct writeback_control *wbc)
 		return 0; /* Do not request flush for shadow page cache */
 	if (!sb) {
 		writer = nilfs_get_writer(NILFS_MDT(inode)->mi_nilfs);
-		if (!writer)
+		if (!writer) {
+			nilfs_put_writer(NILFS_MDT(inode)->mi_nilfs);
 			return -EROFS;
+		}
 		sb = writer->s_super;
 	}
 
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index 8b5e4778cf28..51ff3d0a4ee2 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -1859,12 +1859,26 @@ static void nilfs_end_page_io(struct page *page, int err)
 	if (!page)
 		return;
 
-	if (buffer_nilfs_node(page_buffers(page)) && !PageWriteback(page))
+	if (buffer_nilfs_node(page_buffers(page)) && !PageWriteback(page)) {
 		/*
 		 * For b-tree node pages, this function may be called twice
 		 * or more because they might be split in a segment.
 		 */
+		if (PageDirty(page)) {
+			/*
+			 * For pages holding split b-tree node buffers, dirty
+			 * flag on the buffers may be cleared discretely.
+			 * In that case, the page is once redirtied for
+			 * remaining buffers, and it must be cancelled if
+			 * all the buffers get cleaned later.
+			 */
+			lock_page(page);
+			if (nilfs_page_buffers_clean(page))
+				__nilfs_clear_page_dirty(page);
+			unlock_page(page);
+		}
 		return;
+	}
 
 	__nilfs_end_page_io(page, err);
 }
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 3ce5ae9e3d2d..175db258942f 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -234,23 +234,20 @@ static int check_mem_permission(struct task_struct *task)
 
 struct mm_struct *mm_for_maps(struct task_struct *task)
 {
-	struct mm_struct *mm = get_task_mm(task);
-	if (!mm)
+	struct mm_struct *mm;
+
+	if (mutex_lock_killable(&task->cred_guard_mutex))
 		return NULL;
-	down_read(&mm->mmap_sem);
-	task_lock(task);
-	if (task->mm != mm)
-		goto out;
-	if (task->mm != current->mm &&
-	    __ptrace_may_access(task, PTRACE_MODE_READ) < 0)
-		goto out;
-	task_unlock(task);
+
+	mm = get_task_mm(task);
+	if (mm && mm != current->mm &&
+			!ptrace_may_access(task, PTRACE_MODE_READ)) {
+		mmput(mm);
+		mm = NULL;
+	}
+	mutex_unlock(&task->cred_guard_mutex);
+
 	return mm;
-out:
-	task_unlock(task);
-	up_read(&mm->mmap_sem);
-	mmput(mm);
-	return NULL;
 }
 
 static int proc_pid_cmdline(struct task_struct *task, char * buffer)
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 6f61b7cc32e0..9bd8be1d235c 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -119,6 +119,7 @@ static void *m_start(struct seq_file *m, loff_t *pos)
 	mm = mm_for_maps(priv->task);
 	if (!mm)
 		return NULL;
+	down_read(&mm->mmap_sem);
 
 	tail_vma = get_gate_vma(priv->task);
 	priv->tail_vma = tail_vma;
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index 64a72e2e7650..8f5c05d3dbd3 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -189,6 +189,7 @@ static void *m_start(struct seq_file *m, loff_t *pos)
 		priv->task = NULL;
 		return NULL;
 	}
+	down_read(&mm->mmap_sem);
 
 	/* start from the Nth VMA */
 	for (p = rb_first(&mm->mm_rb); p; p = rb_next(p))
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 70f36c043d62..38f7bd559f35 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -2043,7 +2043,6 @@ static int vfs_load_quota_inode(struct inode *inode, int type, int format_id,
 		invalidate_bdev(sb->s_bdev);
 	}
 	mutex_lock(&dqopt->dqonoff_mutex);
-	mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA);
 	if (sb_has_quota_loaded(sb, type)) {
 		error = -EBUSY;
 		goto out_lock;
@@ -2054,9 +2053,11 @@ static int vfs_load_quota_inode(struct inode *inode, int type, int format_id,
 		 * possible) Also nobody should write to the file - we use
 		 * special IO operations which ignore the immutable bit. */
 		down_write(&dqopt->dqptr_sem);
+		mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA);
 		oldflags = inode->i_flags & (S_NOATIME | S_IMMUTABLE |
 					     S_NOQUOTA);
 		inode->i_flags |= S_NOQUOTA | S_NOATIME | S_IMMUTABLE;
+		mutex_unlock(&inode->i_mutex);
 		up_write(&dqopt->dqptr_sem);
 		sb->dq_op->drop(inode);
 	}
@@ -2080,7 +2081,6 @@ static int vfs_load_quota_inode(struct inode *inode, int type, int format_id,
 		goto out_file_init;
 	}
 	mutex_unlock(&dqopt->dqio_mutex);
-	mutex_unlock(&inode->i_mutex);
 	spin_lock(&dq_state_lock);
 	dqopt->flags |= dquot_state_flag(flags, type);
 	spin_unlock(&dq_state_lock);
@@ -2096,13 +2096,14 @@ out_file_init:
 out_lock:
 	if (oldflags != -1) {
 		down_write(&dqopt->dqptr_sem);
+		mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA);
 		/* Set the flags back (in the case of accidental quotaon()
 		 * on a wrong file we don't want to mess up the flags) */
 		inode->i_flags &= ~(S_NOATIME | S_NOQUOTA | S_IMMUTABLE);
 		inode->i_flags |= oldflags;
+		mutex_unlock(&inode->i_mutex);
 		up_write(&dqopt->dqptr_sem);
 	}
-	mutex_unlock(&inode->i_mutex);
 	mutex_unlock(&dqopt->dqonoff_mutex);
 out_fmt:
 	put_quota_format(fmt);
diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
index ebb2c417912c..11f0c06316de 100644
--- a/fs/ramfs/file-nommu.c
+++ b/fs/ramfs/file-nommu.c
@@ -20,6 +20,7 @@
 #include <linux/ramfs.h>
 #include <linux/pagevec.h>
 #include <linux/mman.h>
+#include <linux/sched.h>
 
 #include <asm/uaccess.h>
 #include "internal.h"
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index d88d0fac9fa5..14f2d71ea3ce 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -939,8 +939,10 @@ again:
 	/* Remove from old parent's list and insert into new parent's list. */
 	sysfs_unlink_sibling(sd);
 	sysfs_get(new_parent_sd);
+	drop_nlink(old_parent->d_inode);
 	sysfs_put(sd->s_parent);
 	sd->s_parent = new_parent_sd;
+	inc_nlink(new_parent->d_inode);
 	sysfs_link_sibling(sd);
 
  out_unlock:
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 6832135159b6..9d1b8c2e6c45 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -1087,11 +1087,23 @@ static int udf_load_vat(struct super_block *sb, int p_index, int type1_index)
 	struct udf_inode_info *vati;
 	uint32_t pos;
 	struct virtualAllocationTable20 *vat20;
+	sector_t blocks = sb->s_bdev->bd_inode->i_size >> sb->s_blocksize_bits;
 
 	/* VAT file entry is in the last recorded block */
 	ino.partitionReferenceNum = type1_index;
 	ino.logicalBlockNum = sbi->s_last_block - map->s_partition_root;
 	sbi->s_vat_inode = udf_iget(sb, &ino);
+	if (!sbi->s_vat_inode &&
+	    sbi->s_last_block != blocks - 1) {
+		printk(KERN_NOTICE "UDF-fs: Failed to read VAT inode from the"
+		       " last recorded block (%lu), retrying with the last "
+		       "block of the device (%lu).\n",
+		       (unsigned long)sbi->s_last_block,
+		       (unsigned long)blocks - 1);
+		ino.partitionReferenceNum = type1_index;
+		ino.logicalBlockNum = blocks - 1 - map->s_partition_root;
+		sbi->s_vat_inode = udf_iget(sb, &ino);
+	}
 	if (!sbi->s_vat_inode)
 		return 1;
 
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index 7ec89fc05b2b..aecf2519db76 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -1268,6 +1268,14 @@ 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.
diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c
index 58973bb46038..8070b34cc287 100644
--- a/fs/xfs/linux-2.6/xfs_iops.c
+++ b/fs/xfs/linux-2.6/xfs_iops.c
@@ -680,8 +680,8 @@ xfs_vn_fiemap(
 	else
 		bm.bmv_length = BTOBB(length);
 
-	/* our formatter will tell xfs_getbmap when to stop. */
-	bm.bmv_count = MAXEXTNUM;
+	/* We add one because in getbmap world count includes the header */
+	bm.bmv_count = fieinfo->fi_extents_max + 1;
 	bm.bmv_iflags = BMV_IF_PREALLOC;
 	if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR)
 		bm.bmv_iflags |= BMV_IF_ATTRFORK;
diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c
index 5fcec6f020a7..34ec86923f7e 100644
--- a/fs/xfs/xfs_iget.c
+++ b/fs/xfs/xfs_iget.c
@@ -64,6 +64,10 @@ xfs_inode_alloc(
 	ip = kmem_zone_alloc(xfs_inode_zone, KM_SLEEP);
 	if (!ip)
 		return NULL;
+	if (inode_init_always(mp->m_super, VFS_I(ip))) {
+		kmem_zone_free(xfs_inode_zone, ip);
+		return NULL;
+	}
 
 	ASSERT(atomic_read(&ip->i_iocount) == 0);
 	ASSERT(atomic_read(&ip->i_pincount) == 0);
@@ -105,17 +109,6 @@ xfs_inode_alloc(
 #ifdef XFS_DIR2_TRACE
 	ip->i_dir_trace = ktrace_alloc(XFS_DIR2_KTRACE_SIZE, KM_NOFS);
 #endif
-	/*
-	* Now initialise the VFS inode. We do this after the xfs_inode
-	* initialisation as internal failures will result in ->destroy_inode
-	* being called and that will pass down through the reclaim path and
-	* free the XFS inode. This path requires the XFS inode to already be
-	* initialised. Hence if this call fails, the xfs_inode has already
-	* been freed and we should not reference it at all in the error
-	* handling.
-	*/
-	if (!inode_init_always(mp->m_super, VFS_I(ip)))
-		return NULL;
 
 	/* prevent anyone from using this yet */
 	VFS_I(ip)->i_state = I_NEW|I_LOCK;
@@ -123,6 +116,71 @@ xfs_inode_alloc(
 	return ip;
 }
 
+STATIC void
+xfs_inode_free(
+	struct xfs_inode	*ip)
+{
+	switch (ip->i_d.di_mode & S_IFMT) {
+	case S_IFREG:
+	case S_IFDIR:
+	case S_IFLNK:
+		xfs_idestroy_fork(ip, XFS_DATA_FORK);
+		break;
+	}
+
+	if (ip->i_afp)
+		xfs_idestroy_fork(ip, XFS_ATTR_FORK);
+
+#ifdef XFS_INODE_TRACE
+	ktrace_free(ip->i_trace);
+#endif
+#ifdef XFS_BMAP_TRACE
+	ktrace_free(ip->i_xtrace);
+#endif
+#ifdef XFS_BTREE_TRACE
+	ktrace_free(ip->i_btrace);
+#endif
+#ifdef XFS_RW_TRACE
+	ktrace_free(ip->i_rwtrace);
+#endif
+#ifdef XFS_ILOCK_TRACE
+	ktrace_free(ip->i_lock_trace);
+#endif
+#ifdef XFS_DIR2_TRACE
+	ktrace_free(ip->i_dir_trace);
+#endif
+
+	if (ip->i_itemp) {
+		/*
+		 * Only if we are shutting down the fs will we see an
+		 * inode still in the AIL. If it is there, we should remove
+		 * it to prevent a use-after-free from occurring.
+		 */
+		xfs_log_item_t	*lip = &ip->i_itemp->ili_item;
+		struct xfs_ail	*ailp = lip->li_ailp;
+
+		ASSERT(((lip->li_flags & XFS_LI_IN_AIL) == 0) ||
+				       XFS_FORCED_SHUTDOWN(ip->i_mount));
+		if (lip->li_flags & XFS_LI_IN_AIL) {
+			spin_lock(&ailp->xa_lock);
+			if (lip->li_flags & XFS_LI_IN_AIL)
+				xfs_trans_ail_delete(ailp, lip);
+			else
+				spin_unlock(&ailp->xa_lock);
+		}
+		xfs_inode_item_destroy(ip);
+		ip->i_itemp = NULL;
+	}
+
+	/* asserts to verify all state is correct here */
+	ASSERT(atomic_read(&ip->i_iocount) == 0);
+	ASSERT(atomic_read(&ip->i_pincount) == 0);
+	ASSERT(!spin_is_locked(&ip->i_flags_lock));
+	ASSERT(completion_done(&ip->i_flush));
+
+	kmem_zone_free(xfs_inode_zone, ip);
+}
+
 /*
  * Check the validity of the inode we just found it the cache
  */
@@ -167,7 +225,7 @@ xfs_iget_cache_hit(
 		 * errors cleanly, then tag it so it can be set up correctly
 		 * later.
 		 */
-		if (!inode_init_always(mp->m_super, VFS_I(ip))) {
+		if (inode_init_always(mp->m_super, VFS_I(ip))) {
 			error = ENOMEM;
 			goto out_error;
 		}
@@ -299,7 +357,8 @@ out_preload_end:
 	if (lock_flags)
 		xfs_iunlock(ip, lock_flags);
 out_destroy:
-	xfs_destroy_inode(ip);
+	__destroy_inode(VFS_I(ip));
+	xfs_inode_free(ip);
 	return error;
 }
 
@@ -504,62 +563,7 @@ xfs_ireclaim(
 	xfs_qm_dqdetach(ip);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
 
-	switch (ip->i_d.di_mode & S_IFMT) {
-	case S_IFREG:
-	case S_IFDIR:
-	case S_IFLNK:
-		xfs_idestroy_fork(ip, XFS_DATA_FORK);
-		break;
-	}
-
-	if (ip->i_afp)
-		xfs_idestroy_fork(ip, XFS_ATTR_FORK);
-
-#ifdef XFS_INODE_TRACE
-	ktrace_free(ip->i_trace);
-#endif
-#ifdef XFS_BMAP_TRACE
-	ktrace_free(ip->i_xtrace);
-#endif
-#ifdef XFS_BTREE_TRACE
-	ktrace_free(ip->i_btrace);
-#endif
-#ifdef XFS_RW_TRACE
-	ktrace_free(ip->i_rwtrace);
-#endif
-#ifdef XFS_ILOCK_TRACE
-	ktrace_free(ip->i_lock_trace);
-#endif
-#ifdef XFS_DIR2_TRACE
-	ktrace_free(ip->i_dir_trace);
-#endif
-	if (ip->i_itemp) {
-		/*
-		 * Only if we are shutting down the fs will we see an
-		 * inode still in the AIL. If it is there, we should remove
-		 * it to prevent a use-after-free from occurring.
-		 */
-		xfs_log_item_t	*lip = &ip->i_itemp->ili_item;
-		struct xfs_ail	*ailp = lip->li_ailp;
-
-		ASSERT(((lip->li_flags & XFS_LI_IN_AIL) == 0) ||
-				       XFS_FORCED_SHUTDOWN(ip->i_mount));
-		if (lip->li_flags & XFS_LI_IN_AIL) {
-			spin_lock(&ailp->xa_lock);
-			if (lip->li_flags & XFS_LI_IN_AIL)
-				xfs_trans_ail_delete(ailp, lip);
-			else
-				spin_unlock(&ailp->xa_lock);
-		}
-		xfs_inode_item_destroy(ip);
-		ip->i_itemp = NULL;
-	}
-	/* asserts to verify all state is correct here */
-	ASSERT(atomic_read(&ip->i_iocount) == 0);
-	ASSERT(atomic_read(&ip->i_pincount) == 0);
-	ASSERT(!spin_is_locked(&ip->i_flags_lock));
-	ASSERT(completion_done(&ip->i_flush));
-	kmem_zone_free(xfs_inode_zone, ip);
+	xfs_inode_free(ip);
 }
 
 /*
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 1804f866a71d..65f24a3cc992 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -310,23 +310,6 @@ static inline struct inode *VFS_I(struct xfs_inode *ip)
 }
 
 /*
- * Get rid of a partially initialized inode.
- *
- * We have to go through destroy_inode to make sure allocations
- * from init_inode_always like the security data are undone.
- *
- * We mark the inode bad so that it takes the short cut in
- * the reclaim path instead of going through the flush path
- * which doesn't make sense for an inode that has never seen the
- * light of day.
- */
-static inline void xfs_destroy_inode(struct xfs_inode *ip)
-{
-	make_bad_inode(VFS_I(ip));
-	return destroy_inode(VFS_I(ip));
-}
-
-/*
  * i_flags helper functions
  */
 static inline void