Merge commit 'v2.6.31-rc9' into tracing/core

Merge reason: move from -rc5 to -rc9.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

61 files changed, 971 insertions, 562 deletions

diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index 332b5ff02fec..f7003cfac63d 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -76,7 +76,7 @@ static const match_table_t tokens = {
  * Return 0 upon success, -ERRNO upon failure.
  */
 
-static int v9fs_parse_options(struct v9fs_session_info *v9ses)
+static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts)
 {
 	char *options;
 	substring_t args[MAX_OPT_ARGS];
@@ -90,10 +90,10 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses)
 	v9ses->debug = 0;
 	v9ses->cache = 0;
 
-	if (!v9ses->options)
+	if (!opts)
 		return 0;
 
-	options = kstrdup(v9ses->options, GFP_KERNEL);
+	options = kstrdup(opts, GFP_KERNEL);
 	if (!options) {
 		P9_DPRINTK(P9_DEBUG_ERROR,
 			   "failed to allocate copy of option string\n");
@@ -206,24 +206,14 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 	v9ses->uid = ~0;
 	v9ses->dfltuid = V9FS_DEFUID;
 	v9ses->dfltgid = V9FS_DEFGID;
-	if (data) {
-		v9ses->options = kstrdup(data, GFP_KERNEL);
-		if (!v9ses->options) {
-			P9_DPRINTK(P9_DEBUG_ERROR,
-			   "failed to allocate copy of option string\n");
-			retval = -ENOMEM;
-			goto error;
-		}
-	}
 
-	rc = v9fs_parse_options(v9ses);
+	rc = v9fs_parse_options(v9ses, data);
 	if (rc < 0) {
 		retval = rc;
 		goto error;
 	}
 
-	v9ses->clnt = p9_client_create(dev_name, v9ses->options);
-
+	v9ses->clnt = p9_client_create(dev_name, data);
 	if (IS_ERR(v9ses->clnt)) {
 		retval = PTR_ERR(v9ses->clnt);
 		v9ses->clnt = NULL;
@@ -280,7 +270,6 @@ void v9fs_session_close(struct v9fs_session_info *v9ses)
 
 	__putname(v9ses->uname);
 	__putname(v9ses->aname);
-	kfree(v9ses->options);
 }
 
 /**
diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h
index a7d567192998..38762bf102a9 100644
--- a/fs/9p/v9fs.h
+++ b/fs/9p/v9fs.h
@@ -85,7 +85,6 @@ struct v9fs_session_info {
 	unsigned int afid;
 	unsigned int cache;
 
-	char *options;		/* copy of mount options */
 	char *uname;		/* user name to mount as */
 	char *aname;		/* name of remote hierarchy being mounted */
 	unsigned int maxdata;	/* max data for client interface */
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 81f8bbf12f9f..06a223d50a81 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -171,7 +171,6 @@ int v9fs_uflags2omode(int uflags, int extended)
 
 /**
  * v9fs_blank_wstat - helper function to setup a 9P stat structure
- * @v9ses: 9P session info (for determining extended mode)
  * @wstat: structure to initialize
  *
  */
@@ -207,65 +206,72 @@ v9fs_blank_wstat(struct p9_wstat *wstat)
 
 struct inode *v9fs_get_inode(struct super_block *sb, int mode)
 {
+	int err;
 	struct inode *inode;
 	struct v9fs_session_info *v9ses = sb->s_fs_info;
 
 	P9_DPRINTK(P9_DEBUG_VFS, "super block: %p mode: %o\n", sb, mode);
 
 	inode = new_inode(sb);
-	if (inode) {
-		inode->i_mode = mode;
-		inode->i_uid = current_fsuid();
-		inode->i_gid = current_fsgid();
-		inode->i_blocks = 0;
-		inode->i_rdev = 0;
-		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
-		inode->i_mapping->a_ops = &v9fs_addr_operations;
-
-		switch (mode & S_IFMT) {
-		case S_IFIFO:
-		case S_IFBLK:
-		case S_IFCHR:
-		case S_IFSOCK:
-			if (!v9fs_extended(v9ses)) {
-				P9_DPRINTK(P9_DEBUG_ERROR,
-				      "special files without extended mode\n");
-				return ERR_PTR(-EINVAL);
-			}
-			init_special_inode(inode, inode->i_mode,
-					   inode->i_rdev);
-			break;
-		case S_IFREG:
-			inode->i_op = &v9fs_file_inode_operations;
-			inode->i_fop = &v9fs_file_operations;
-			break;
-		case S_IFLNK:
-			if (!v9fs_extended(v9ses)) {
-				P9_DPRINTK(P9_DEBUG_ERROR,
-					"extended modes used w/o 9P2000.u\n");
-				return ERR_PTR(-EINVAL);
-			}
-			inode->i_op = &v9fs_symlink_inode_operations;
-			break;
-		case S_IFDIR:
-			inc_nlink(inode);
-			if (v9fs_extended(v9ses))
-				inode->i_op = &v9fs_dir_inode_operations_ext;
-			else
-				inode->i_op = &v9fs_dir_inode_operations;
-			inode->i_fop = &v9fs_dir_operations;
-			break;
-		default:
-			P9_DPRINTK(P9_DEBUG_ERROR,
-				"BAD mode 0x%x S_IFMT 0x%x\n",
-				mode, mode & S_IFMT);
-			return ERR_PTR(-EINVAL);
-		}
-	} else {
+	if (!inode) {
 		P9_EPRINTK(KERN_WARNING, "Problem allocating inode\n");
 		return ERR_PTR(-ENOMEM);
 	}
+
+	inode->i_mode = mode;
+	inode->i_uid = current_fsuid();
+	inode->i_gid = current_fsgid();
+	inode->i_blocks = 0;
+	inode->i_rdev = 0;
+	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+	inode->i_mapping->a_ops = &v9fs_addr_operations;
+
+	switch (mode & S_IFMT) {
+	case S_IFIFO:
+	case S_IFBLK:
+	case S_IFCHR:
+	case S_IFSOCK:
+		if (!v9fs_extended(v9ses)) {
+			P9_DPRINTK(P9_DEBUG_ERROR,
+				   "special files without extended mode\n");
+			err = -EINVAL;
+			goto error;
+		}
+		init_special_inode(inode, inode->i_mode, inode->i_rdev);
+		break;
+	case S_IFREG:
+		inode->i_op = &v9fs_file_inode_operations;
+		inode->i_fop = &v9fs_file_operations;
+		break;
+	case S_IFLNK:
+		if (!v9fs_extended(v9ses)) {
+			P9_DPRINTK(P9_DEBUG_ERROR,
+				   "extended modes used w/o 9P2000.u\n");
+			err = -EINVAL;
+			goto error;
+		}
+		inode->i_op = &v9fs_symlink_inode_operations;
+		break;
+	case S_IFDIR:
+		inc_nlink(inode);
+		if (v9fs_extended(v9ses))
+			inode->i_op = &v9fs_dir_inode_operations_ext;
+		else
+			inode->i_op = &v9fs_dir_inode_operations;
+		inode->i_fop = &v9fs_dir_operations;
+		break;
+	default:
+		P9_DPRINTK(P9_DEBUG_ERROR, "BAD mode 0x%x S_IFMT 0x%x\n",
+			   mode, mode & S_IFMT);
+		err = -EINVAL;
+		goto error;
+	}
+
 	return inode;
+
+error:
+	iput(inode);
+	return ERR_PTR(err);
 }
 
 /*
@@ -338,30 +344,25 @@ v9fs_inode_from_fid(struct v9fs_session_info *v9ses, struct p9_fid *fid,
 
 	ret = NULL;
 	st = p9_client_stat(fid);
-	if (IS_ERR(st)) {
-		err = PTR_ERR(st);
-		st = NULL;
-		goto error;
-	}
+	if (IS_ERR(st))
+		return ERR_CAST(st);
 
 	umode = p9mode2unixmode(v9ses, st->mode);
 	ret = v9fs_get_inode(sb, umode);
 	if (IS_ERR(ret)) {
 		err = PTR_ERR(ret);
-		ret = NULL;
 		goto error;
 	}
 
 	v9fs_stat2inode(st, ret, sb);
 	ret->i_ino = v9fs_qid2ino(&st->qid);
+	p9stat_free(st);
 	kfree(st);
 	return ret;
 
 error:
+	p9stat_free(st);
 	kfree(st);
-	if (ret)
-		iput(ret);
-
 	return ERR_PTR(err);
 }
 
@@ -403,9 +404,9 @@ v9fs_open_created(struct inode *inode, struct file *file)
  * @v9ses: session information
  * @dir: directory that dentry is being created in
  * @dentry:  dentry that is being created
+ * @extension: 9p2000.u extension string to support devices, etc.
  * @perm: create permissions
  * @mode: open mode
- * @extension: 9p2000.u extension string to support devices, etc.
  *
  */
 static struct p9_fid *
@@ -470,7 +471,10 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir,
 		dentry->d_op = &v9fs_dentry_operations;
 
 	d_instantiate(dentry, inode);
-	v9fs_fid_add(dentry, fid);
+	err = v9fs_fid_add(dentry, fid);
+	if (err < 0)
+		goto error;
+
 	return ofid;
 
 error:
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index 38d695d66a0b..8961f1a8f668 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -81,7 +81,7 @@ static int v9fs_set_super(struct super_block *s, void *data)
 
 static void
 v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses,
-		int flags)
+		int flags, void *data)
 {
 	sb->s_maxbytes = MAX_LFS_FILESIZE;
 	sb->s_blocksize_bits = fls(v9ses->maxdata - 1);
@@ -91,6 +91,8 @@ v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses,
 
 	sb->s_flags = flags | MS_ACTIVE | MS_SYNCHRONOUS | MS_DIRSYNC |
 	    MS_NOATIME;
+
+	save_mount_options(sb, data);
 }
 
 /**
@@ -113,14 +115,11 @@ static int v9fs_get_sb(struct file_system_type *fs_type, int flags,
 	struct v9fs_session_info *v9ses = NULL;
 	struct p9_wstat *st = NULL;
 	int mode = S_IRWXUGO | S_ISVTX;
-	uid_t uid = current_fsuid();
-	gid_t gid = current_fsgid();
 	struct p9_fid *fid;
 	int retval = 0;
 
 	P9_DPRINTK(P9_DEBUG_VFS, " \n");
 
-	st = NULL;
 	v9ses = kzalloc(sizeof(struct v9fs_session_info), GFP_KERNEL);
 	if (!v9ses)
 		return -ENOMEM;
@@ -142,7 +141,7 @@ static int v9fs_get_sb(struct file_system_type *fs_type, int flags,
 		retval = PTR_ERR(sb);
 		goto free_stat;
 	}
-	v9fs_fill_super(sb, v9ses, flags);
+	v9fs_fill_super(sb, v9ses, flags, data);
 
 	inode = v9fs_get_inode(sb, S_IFDIR | mode);
 	if (IS_ERR(inode)) {
@@ -150,9 +149,6 @@ static int v9fs_get_sb(struct file_system_type *fs_type, int flags,
 		goto release_sb;
 	}
 
-	inode->i_uid = uid;
-	inode->i_gid = gid;
-
 	root = d_alloc_root(inode);
 	if (!root) {
 		iput(inode);
@@ -173,10 +169,8 @@ P9_DPRINTK(P9_DEBUG_VFS, " simple set mount, return 0\n");
 	simple_set_mnt(mnt, sb);
 	return 0;
 
-release_sb:
-	deactivate_locked_super(sb);
-
 free_stat:
+	p9stat_free(st);
 	kfree(st);
 
 clunk_fid:
@@ -185,7 +179,12 @@ clunk_fid:
 close_session:
 	v9fs_session_close(v9ses);
 	kfree(v9ses);
+	return retval;
 
+release_sb:
+	p9stat_free(st);
+	kfree(st);
+	deactivate_locked_super(sb);
 	return retval;
 }
 
@@ -207,24 +206,10 @@ static void v9fs_kill_super(struct super_block *s)
 
 	v9fs_session_close(v9ses);
 	kfree(v9ses);
+	s->s_fs_info = NULL;
 	P9_DPRINTK(P9_DEBUG_VFS, "exiting kill_super\n");
 }
 
-/**
- * v9fs_show_options - Show mount options in /proc/mounts
- * @m: seq_file to write to
- * @mnt: mount descriptor
- *
- */
-
-static int v9fs_show_options(struct seq_file *m, struct vfsmount *mnt)
-{
-	struct v9fs_session_info *v9ses = mnt->mnt_sb->s_fs_info;
-
-	seq_printf(m, "%s", v9ses->options);
-	return 0;
-}
-
 static void
 v9fs_umount_begin(struct super_block *sb)
 {
@@ -237,7 +222,7 @@ v9fs_umount_begin(struct super_block *sb)
 static const struct super_operations v9fs_super_ops = {
 	.statfs = simple_statfs,
 	.clear_inode = v9fs_clear_inode,
-	.show_options = v9fs_show_options,
+	.show_options = generic_show_options,
 	.umount_begin = v9fs_umount_begin,
 };
 
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 0149dab365e7..681c2a7b013f 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -134,9 +134,16 @@ static int afs_readpage(struct file *file, struct page *page)
 
 	inode = page->mapping->host;
 
-	ASSERT(file != NULL);
-	key = file->private_data;
-	ASSERT(key != NULL);
+	if (file) {
+		key = file->private_data;
+		ASSERT(key != NULL);
+	} else {
+		key = afs_request_key(AFS_FS_S(inode->i_sb)->volume->cell);
+		if (IS_ERR(key)) {
+			ret = PTR_ERR(key);
+			goto error_nokey;
+		}
+	}
 
 	_enter("{%x},{%lu},{%lu}", key_serial(key), inode->i_ino, page->index);
 
@@ -207,12 +214,17 @@ static int afs_readpage(struct file *file, struct page *page)
 		unlock_page(page);
 	}
 
+	if (!file)
+		key_put(key);
 	_leave(" = 0");
 	return 0;
 
 error:
 	SetPageError(page);
 	unlock_page(page);
+	if (!file)
+		key_put(key);
+error_nokey:
 	_leave(" = %d", ret);
 	return ret;
 }
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index aa39ae83f019..3da18d453488 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -77,7 +77,7 @@ static int autofs4_mount_busy(struct vfsmount *mnt, struct dentry *dentry)
 	}
 
 	/* Update the expiry counter if fs is busy */
-	if (!may_umount_tree(mnt)) {
+	if (!may_umount_tree(path.mnt)) {
 		struct autofs_info *ino = autofs4_dentry_ino(top);
 		ino->last_used = jiffies;
 		goto done;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 272b9b2bea86..59cba180fe83 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3099,8 +3099,12 @@ static void inode_tree_add(struct inode *inode)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_inode *entry;
-	struct rb_node **p = &root->inode_tree.rb_node;
-	struct rb_node *parent = NULL;
+	struct rb_node **p;
+	struct rb_node *parent;
+
+again:
+	p = &root->inode_tree.rb_node;
+	parent = NULL;
 
 	spin_lock(&root->inode_lock);
 	while (*p) {
@@ -3108,13 +3112,16 @@ static void inode_tree_add(struct inode *inode)
 		entry = rb_entry(parent, struct btrfs_inode, rb_node);
 
 		if (inode->i_ino < entry->vfs_inode.i_ino)
-			p = &(*p)->rb_left;
+			p = &parent->rb_left;
 		else if (inode->i_ino > entry->vfs_inode.i_ino)
-			p = &(*p)->rb_right;
+			p = &parent->rb_right;
 		else {
 			WARN_ON(!(entry->vfs_inode.i_state &
 				  (I_WILL_FREE | I_FREEING | I_CLEAR)));
-			break;
+			rb_erase(parent, &root->inode_tree);
+			RB_CLEAR_NODE(parent);
+			spin_unlock(&root->inode_lock);
+			goto again;
 		}
 	}
 	rb_link_node(&BTRFS_I(inode)->rb_node, parent, p);
@@ -3126,12 +3133,12 @@ static void inode_tree_del(struct inode *inode)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 
+	spin_lock(&root->inode_lock);
 	if (!RB_EMPTY_NODE(&BTRFS_I(inode)->rb_node)) {
-		spin_lock(&root->inode_lock);
 		rb_erase(&BTRFS_I(inode)->rb_node, &root->inode_tree);
-		spin_unlock(&root->inode_lock);
 		RB_CLEAR_NODE(&BTRFS_I(inode)->rb_node);
 	}
+	spin_unlock(&root->inode_lock);
 }
 
 static noinline void init_btrfs_i(struct inode *inode)
diff --git a/fs/buffer.c b/fs/buffer.c
index a3ef091a45bd..28f320fac4d4 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1165,8 +1165,11 @@ void mark_buffer_dirty(struct buffer_head *bh)
 
 	if (!test_set_buffer_dirty(bh)) {
 		struct page *page = bh->b_page;
-		if (!TestSetPageDirty(page))
-			__set_page_dirty(page, page_mapping(page), 0);
+		if (!TestSetPageDirty(page)) {
+			struct address_space *mapping = page_mapping(page);
+			if (mapping)
+				__set_page_dirty(page, mapping, 0);
+		}
 	}
 }
 
diff --git a/fs/compat.c b/fs/compat.c
index 94502dab972a..6d6f98fe64a0 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -1485,20 +1485,15 @@ int compat_do_execve(char * filename,
 	if (!bprm)
 		goto out_files;
 
-	retval = -ERESTARTNOINTR;
-	if (mutex_lock_interruptible(&current->cred_guard_mutex))
+	retval = prepare_bprm_creds(bprm);
+	if (retval)
 		goto out_free;
-	current->in_execve = 1;
-
-	retval = -ENOMEM;
-	bprm->cred = prepare_exec_creds();
-	if (!bprm->cred)
-		goto out_unlock;
 
 	retval = check_unsafe_exec(bprm);
 	if (retval < 0)
-		goto out_unlock;
+		goto out_free;
 	clear_in_exec = retval;
+	current->in_execve = 1;
 
 	file = open_exec(filename);
 	retval = PTR_ERR(file);
@@ -1547,7 +1542,6 @@ int compat_do_execve(char * filename,
 	/* execve succeeded */
 	current->fs->in_exec = 0;
 	current->in_execve = 0;
-	mutex_unlock(&current->cred_guard_mutex);
 	acct_update_integrals(current);
 	free_bprm(bprm);
 	if (displaced)
@@ -1567,10 +1561,7 @@ out_file:
 out_unmark:
 	if (clear_in_exec)
 		current->fs->in_exec = 0;
-
-out_unlock:
 	current->in_execve = 0;
-	mutex_unlock(&current->cred_guard_mutex);
 
 out_free:
 	free_bprm(bprm);
diff --git a/fs/exec.c b/fs/exec.c
index 4a8849e45b21..172ceb6edde4 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -678,8 +678,8 @@ exit:
 }
 EXPORT_SYMBOL(open_exec);
 
-int kernel_read(struct file *file, unsigned long offset,
-	char *addr, unsigned long count)
+int kernel_read(struct file *file, loff_t offset,
+		char *addr, unsigned long count)
 {
 	mm_segment_t old_fs;
 	loff_t pos = offset;
@@ -1016,6 +1016,35 @@ out:
 EXPORT_SYMBOL(flush_old_exec);
 
 /*
+ * Prepare credentials and lock ->cred_guard_mutex.
+ * install_exec_creds() commits the new creds and drops the lock.
+ * Or, if exec fails before, free_bprm() should release ->cred and
+ * and unlock.
+ */
+int prepare_bprm_creds(struct linux_binprm *bprm)
+{
+	if (mutex_lock_interruptible(&current->cred_guard_mutex))
+		return -ERESTARTNOINTR;
+
+	bprm->cred = prepare_exec_creds();
+	if (likely(bprm->cred))
+		return 0;
+
+	mutex_unlock(&current->cred_guard_mutex);
+	return -ENOMEM;
+}
+
+void free_bprm(struct linux_binprm *bprm)
+{
+	free_arg_pages(bprm);
+	if (bprm->cred) {
+		mutex_unlock(&current->cred_guard_mutex);
+		abort_creds(bprm->cred);
+	}
+	kfree(bprm);
+}
+
+/*
  * install the new credentials for this executable
  */
 void install_exec_creds(struct linux_binprm *bprm)
@@ -1024,12 +1053,13 @@ void install_exec_creds(struct linux_binprm *bprm)
 
 	commit_creds(bprm->cred);
 	bprm->cred = NULL;
-
-	/* cred_guard_mutex must be held at least to this point to prevent
+	/*
+	 * cred_guard_mutex must be held at least to this point to prevent
 	 * ptrace_attach() from altering our determination of the task's
-	 * credentials; any time after this it may be unlocked */
-
+	 * credentials; any time after this it may be unlocked.
+	 */
 	security_bprm_committed_creds(bprm);
+	mutex_unlock(&current->cred_guard_mutex);
 }
 EXPORT_SYMBOL(install_exec_creds);
 
@@ -1246,14 +1276,6 @@ int search_binary_handler(struct linux_binprm *bprm,struct pt_regs *regs)
 
 EXPORT_SYMBOL(search_binary_handler);
 
-void free_bprm(struct linux_binprm *bprm)
-{
-	free_arg_pages(bprm);
-	if (bprm->cred)
-		abort_creds(bprm->cred);
-	kfree(bprm);
-}
-
 /*
  * sys_execve() executes a new program.
  */
@@ -1277,20 +1299,15 @@ int do_execve(char * filename,
 	if (!bprm)
 		goto out_files;
 
-	retval = -ERESTARTNOINTR;
-	if (mutex_lock_interruptible(&current->cred_guard_mutex))
+	retval = prepare_bprm_creds(bprm);
+	if (retval)
 		goto out_free;
-	current->in_execve = 1;
-
-	retval = -ENOMEM;
-	bprm->cred = prepare_exec_creds();
-	if (!bprm->cred)
-		goto out_unlock;
 
 	retval = check_unsafe_exec(bprm);
 	if (retval < 0)
-		goto out_unlock;
+		goto out_free;
 	clear_in_exec = retval;
+	current->in_execve = 1;
 
 	file = open_exec(filename);
 	retval = PTR_ERR(file);
@@ -1340,7 +1357,6 @@ int do_execve(char * filename,
 	/* execve succeeded */
 	current->fs->in_exec = 0;
 	current->in_execve = 0;
-	mutex_unlock(&current->cred_guard_mutex);
 	acct_update_integrals(current);
 	free_bprm(bprm);
 	if (displaced)
@@ -1360,10 +1376,7 @@ out_file:
 out_unmark:
 	if (clear_in_exec)
 		current->fs->in_exec = 0;
-
-out_unlock:
 	current->in_execve = 0;
-	mutex_unlock(&current->cred_guard_mutex);
 
 out_free:
 	free_bprm(bprm);
diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c
index e1dedb0f7873..78d9b925fc94 100644
--- a/fs/ext2/namei.c
+++ b/fs/ext2/namei.c
@@ -362,6 +362,10 @@ static int ext2_rename (struct inode * old_dir, struct dentry * old_dentry,
 	if (dir_de) {
 		if (old_dir != new_dir)
 			ext2_set_link(old_inode, dir_de, dir_page, new_dir, 0);
+		else {
+			kunmap(dir_page);
+			page_cache_release(dir_page);
+		}
 		inode_dec_link_count(old_dir);
 	}
 	return 0;
diff --git a/fs/ext3/Kconfig b/fs/ext3/Kconfig
index fb3c1a21b135..522b15498f45 100644
--- a/fs/ext3/Kconfig
+++ b/fs/ext3/Kconfig
@@ -29,23 +29,25 @@ config EXT3_FS
 	  module will be called ext3.
 
 config EXT3_DEFAULTS_TO_ORDERED
-	bool "Default to 'data=ordered' in ext3 (legacy option)"
+	bool "Default to 'data=ordered' in ext3"
 	depends on EXT3_FS
 	help
-	  If a filesystem does not explicitly specify a data ordering
-	  mode, and the journal capability allowed it, ext3 used to
-	  historically default to 'data=ordered'.
-
-	  That was a rather unfortunate choice, because it leads to all
-	  kinds of latency problems, and the 'data=writeback' mode is more
-	  appropriate these days.
-
-	  You should probably always answer 'n' here, and if you really
-	  want to use 'data=ordered' mode, set it in the filesystem itself
-	  with 'tune2fs -o journal_data_ordered'.
-
-	  But if you really want to enable the legacy default, you can do
-	  so by answering 'y' to this question.
+	  The journal mode options for ext3 have different tradeoffs
+	  between when data is guaranteed to be on disk and
+	  performance.	The use of "data=writeback" can cause
+	  unwritten data to appear in files after an system crash or
+	  power failure, which can be a security issue.	 However,
+	  "data=ordered" mode can also result in major performance
+	  problems, including seconds-long delays before an fsync()
+	  call returns.	 For details, see:
+
+	  http://ext4.wiki.kernel.org/index.php/Ext3_data_mode_tradeoffs
+
+	  If you have been historically happy with ext3's performance,
+	  data=ordered mode will be a safe choice and you should
+	  answer 'y' here.  If you understand the reliability and data
+	  privacy issues of data=writeback and are willing to make
+	  that trade off, answer 'n'.
 
 config EXT3_FS_XATTR
 	bool "Ext3 extended attributes"
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 524b349c6299..a8d80a7f1105 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -543,6 +543,19 @@ static inline void ext3_show_quota_options(struct seq_file *seq, struct super_bl
 #endif
 }
 
+static char *data_mode_string(unsigned long mode)
+{
+	switch (mode) {
+	case EXT3_MOUNT_JOURNAL_DATA:
+		return "journal";
+	case EXT3_MOUNT_ORDERED_DATA:
+		return "ordered";
+	case EXT3_MOUNT_WRITEBACK_DATA:
+		return "writeback";
+	}
+	return "unknown";
+}
+
 /*
  * Show an option if
  *  - it's set to a non-default value OR
@@ -616,13 +629,8 @@ static int ext3_show_options(struct seq_file *seq, struct vfsmount *vfs)
 	if (test_opt(sb, NOBH))
 		seq_puts(seq, ",nobh");
 
-	if (test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_JOURNAL_DATA)
-		seq_puts(seq, ",data=journal");
-	else if (test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_ORDERED_DATA)
-		seq_puts(seq, ",data=ordered");
-	else if (test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_WRITEBACK_DATA)
-		seq_puts(seq, ",data=writeback");
-
+	seq_printf(seq, ",data=%s", data_mode_string(sbi->s_mount_opt &
+						     EXT3_MOUNT_DATA_FLAGS));
 	if (test_opt(sb, DATA_ERR_ABORT))
 		seq_puts(seq, ",data_err=abort");
 
@@ -1024,12 +1032,18 @@ static int parse_options (char *options, struct super_block *sb,
 		datacheck:
 			if (is_remount) {
 				if ((sbi->s_mount_opt & EXT3_MOUNT_DATA_FLAGS)
-						!= data_opt) {
-					printk(KERN_ERR
-						"EXT3-fs: cannot change data "
-						"mode on remount\n");
-					return 0;
-				}
+						== data_opt)
+					break;
+				printk(KERN_ERR
+					"EXT3-fs (device %s): Cannot change "
+					"data mode on remount. The filesystem "
+					"is mounted in data=%s mode and you "
+					"try to remount it in data=%s mode.\n",
+					sb->s_id,
+					data_mode_string(sbi->s_mount_opt &
+							EXT3_MOUNT_DATA_FLAGS),
+					data_mode_string(data_opt));
+				return 0;
 			} else {
 				sbi->s_mount_opt &= ~EXT3_MOUNT_DATA_FLAGS;
 				sbi->s_mount_opt |= data_opt;
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index 23419dc3027b..a7cbfbd340c7 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -386,16 +386,16 @@ static ssize_t jid_show(struct gfs2_sbd *sdp, char *buf)
 #define GDLM_ATTR(_name,_mode,_show,_store) \
 static struct gfs2_attr gdlm_attr_##_name = __ATTR(_name,_mode,_show,_store)
 
-GDLM_ATTR(proto_name,     0444, proto_name_show,	NULL);
-GDLM_ATTR(block,          0644, block_show,		block_store);
-GDLM_ATTR(withdraw,       0644, withdraw_show,		withdraw_store);
-GDLM_ATTR(id,             0444, lkid_show,		NULL);
-GDLM_ATTR(jid,		  0444, jid_show,		NULL);
-GDLM_ATTR(first,          0444, lkfirst_show,		NULL);
-GDLM_ATTR(first_done,     0444, first_done_show,	NULL);
-GDLM_ATTR(recover,        0200, NULL,			recover_store);
-GDLM_ATTR(recover_done,   0444, recover_done_show,	NULL);
-GDLM_ATTR(recover_status, 0444, recover_status_show,	NULL);
+GDLM_ATTR(proto_name,		0444, proto_name_show,		NULL);
+GDLM_ATTR(block,		0644, block_show,		block_store);
+GDLM_ATTR(withdraw,		0644, withdraw_show,		withdraw_store);
+GDLM_ATTR(id,			0444, lkid_show,		NULL);
+GDLM_ATTR(jid,			0444, jid_show,			NULL);
+GDLM_ATTR(first,		0444, lkfirst_show,		NULL);
+GDLM_ATTR(first_done,		0444, first_done_show,		NULL);
+GDLM_ATTR(recover,		0600, NULL,			recover_store);
+GDLM_ATTR(recover_done,		0444, recover_done_show,	NULL);
+GDLM_ATTR(recover_status,	0444, recover_status_show,	NULL);
 
 static struct attribute *lock_module_attrs[] = {
 	&gdlm_attr_proto_name.attr,
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 941c8425c10b..cb88dac8ccaa 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -935,26 +935,28 @@ static int can_do_hugetlb_shm(void)
 	return capable(CAP_IPC_LOCK) || in_group_p(sysctl_hugetlb_shm_group);
 }
 
-struct file *hugetlb_file_setup(const char *name, size_t size, int acctflag)
+struct file *hugetlb_file_setup(const char *name, size_t size, int acctflag,
+						struct user_struct **user)
 {
 	int error = -ENOMEM;
-	int unlock_shm = 0;
 	struct file *file;
 	struct inode *inode;
 	struct dentry *dentry, *root;
 	struct qstr quick_string;
-	struct user_struct *user = current_user();
 
+	*user = NULL;
 	if (!hugetlbfs_vfsmount)
 		return ERR_PTR(-ENOENT);
 
 	if (!can_do_hugetlb_shm()) {
-		if (user_shm_lock(size, user)) {
-			unlock_shm = 1;
+		*user = current_user();
+		if (user_shm_lock(size, *user)) {
 			WARN_ONCE(1,
 			  "Using mlock ulimits for SHM_HUGETLB deprecated\n");
-		} else
+		} else {
+			*user = NULL;
 			return ERR_PTR(-EPERM);
+		}
 	}
 
 	root = hugetlbfs_vfsmount->mnt_root;
@@ -996,8 +998,10 @@ out_inode:
 out_dentry:
 	dput(dentry);
 out_shm_unlock:
-	if (unlock_shm)
-		user_shm_unlock(size, user);
+	if (*user) {
+		user_shm_unlock(size, *user);
+		*user = NULL;
+	}
 	return ERR_PTR(error);
 }
 
diff --git a/fs/jffs2/wbuf.c b/fs/jffs2/wbuf.c
index d9a721e6db70..5ef7bac265e5 100644
--- a/fs/jffs2/wbuf.c
+++ b/fs/jffs2/wbuf.c
@@ -1268,10 +1268,20 @@ int jffs2_nor_wbuf_flash_setup(struct jffs2_sb_info *c) {
 	if (!c->wbuf)
 		return -ENOMEM;
 
+#ifdef CONFIG_JFFS2_FS_WBUF_VERIFY
+	c->wbuf_verify = kmalloc(c->wbuf_pagesize, GFP_KERNEL);
+	if (!c->wbuf_verify) {
+		kfree(c->wbuf);
+		return -ENOMEM;
+	}
+#endif
 	return 0;
 }
 
 void jffs2_nor_wbuf_flash_cleanup(struct jffs2_sb_info *c) {
+#ifdef CONFIG_JFFS2_FS_WBUF_VERIFY
+	kfree(c->wbuf_verify);
+#endif
 	kfree(c->wbuf);
 }
 
diff --git a/fs/libfs.c b/fs/libfs.c
index ddfa89948c3f..dcec3d3ea64f 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -217,7 +217,7 @@ int get_sb_pseudo(struct file_system_type *fs_type, char *name,
 		return PTR_ERR(s);
 
 	s->s_flags = MS_NOUSER;
-	s->s_maxbytes = ~0ULL;
+	s->s_maxbytes = MAX_LFS_FILESIZE;
 	s->s_blocksize = PAGE_SIZE;
 	s->s_blocksize_bits = PAGE_SHIFT;
 	s->s_magic = magic;
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 489fc01a3204..e4e089a8f294 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -255,7 +255,7 @@ static void nfs_direct_read_release(void *calldata)
 
 	if (put_dreq(dreq))
 		nfs_direct_complete(dreq);
-	nfs_readdata_release(calldata);
+	nfs_readdata_free(data);
 }
 
 static const struct rpc_call_ops nfs_read_direct_ops = {
@@ -314,14 +314,14 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq,
 					data->npages, 1, 0, data->pagevec, NULL);
 		up_read(&current->mm->mmap_sem);
 		if (result < 0) {
-			nfs_readdata_release(data);
+			nfs_readdata_free(data);
 			break;
 		}
 		if ((unsigned)result < data->npages) {
 			bytes = result * PAGE_SIZE;
 			if (bytes <= pgbase) {
 				nfs_direct_release_pages(data->pagevec, result);
-				nfs_readdata_release(data);
+				nfs_readdata_free(data);
 				break;
 			}
 			bytes -= pgbase;
@@ -334,7 +334,7 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_direct_req *dreq,
 		data->inode = inode;
 		data->cred = msg.rpc_cred;
 		data->args.fh = NFS_FH(inode);
-		data->args.context = get_nfs_open_context(ctx);
+		data->args.context = ctx;
 		data->args.offset = pos;
 		data->args.pgbase = pgbase;
 		data->args.pages = data->pagevec;
@@ -441,7 +441,7 @@ static void nfs_direct_free_writedata(struct nfs_direct_req *dreq)
 		struct nfs_write_data *data = list_entry(dreq->rewrite_list.next, struct nfs_write_data, pages);
 		list_del(&data->pages);
 		nfs_direct_release_pages(data->pagevec, data->npages);
-		nfs_writedata_release(data);
+		nfs_writedata_free(data);
 	}
 }
 
@@ -534,7 +534,7 @@ static void nfs_direct_commit_release(void *calldata)
 
 	dprintk("NFS: %5u commit returned %d\n", data->task.tk_pid, status);
 	nfs_direct_write_complete(dreq, data->inode);
-	nfs_commitdata_release(calldata);
+	nfs_commit_free(data);
 }
 
 static const struct rpc_call_ops nfs_commit_direct_ops = {
@@ -570,7 +570,7 @@ static void nfs_direct_commit_schedule(struct nfs_direct_req *dreq)
 	data->args.fh = NFS_FH(data->inode);
 	data->args.offset = 0;
 	data->args.count = 0;
-	data->args.context = get_nfs_open_context(dreq->ctx);
+	data->args.context = dreq->ctx;
 	data->res.count = 0;
 	data->res.fattr = &data->fattr;
 	data->res.verf = &data->verf;
@@ -734,14 +734,14 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_direct_req *dreq,
 					data->npages, 0, 0, data->pagevec, NULL);
 		up_read(&current->mm->mmap_sem);
 		if (result < 0) {
-			nfs_writedata_release(data);
+			nfs_writedata_free(data);
 			break;
 		}
 		if ((unsigned)result < data->npages) {
 			bytes = result * PAGE_SIZE;
 			if (bytes <= pgbase) {
 				nfs_direct_release_pages(data->pagevec, result);
-				nfs_writedata_release(data);
+				nfs_writedata_free(data);
 				break;
 			}
 			bytes -= pgbase;
@@ -756,7 +756,7 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_direct_req *dreq,
 		data->inode = inode;
 		data->cred = msg.rpc_cred;
 		data->args.fh = NFS_FH(inode);
-		data->args.context = get_nfs_open_context(ctx);
+		data->args.context = ctx;
 		data->args.offset = pos;
 		data->args.pgbase = pgbase;
 		data->args.pages = data->pagevec;
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 65ca8c18476f..1434080aefeb 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1250,8 +1250,8 @@ static void nfs4_state_manager(struct nfs_client *clp)
 				continue;
 		}
 		/* Initialize or reset the session */
-		if (nfs4_has_session(clp) &&
-		   test_and_clear_bit(NFS4CLNT_SESSION_SETUP, &clp->cl_state)) {
+		if (test_and_clear_bit(NFS4CLNT_SESSION_SETUP, &clp->cl_state)
+		   && nfs4_has_session(clp)) {
 			if (clp->cl_cons_state == NFS_CS_SESSION_INITING)
 				status = nfs4_initialize_session(clp);
 			else
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 73ea5e8d66ce..12c9e66d3f1d 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -60,17 +60,15 @@ struct nfs_read_data *nfs_readdata_alloc(unsigned int pagecount)
 	return p;
 }
 
-static void nfs_readdata_free(struct nfs_read_data *p)
+void nfs_readdata_free(struct nfs_read_data *p)
 {
 	if (p && (p->pagevec != &p->page_array[0]))
 		kfree(p->pagevec);
 	mempool_free(p, nfs_rdata_mempool);
 }
 
-void nfs_readdata_release(void *data)
+static void nfs_readdata_release(struct nfs_read_data *rdata)
 {
-	struct nfs_read_data *rdata = data;
-
 	put_nfs_open_context(rdata->args.context);
 	nfs_readdata_free(rdata);
 }
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 0a0a2ff767c3..a34fae21fe10 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -87,17 +87,15 @@ struct nfs_write_data *nfs_writedata_alloc(unsigned int pagecount)
 	return p;
 }
 
-static void nfs_writedata_free(struct nfs_write_data *p)
+void nfs_writedata_free(struct nfs_write_data *p)
 {
 	if (p && (p->pagevec != &p->page_array[0]))
 		kfree(p->pagevec);
 	mempool_free(p, nfs_wdata_mempool);
 }
 
-void nfs_writedata_release(void *data)
+static void nfs_writedata_release(struct nfs_write_data *wdata)
 {
-	struct nfs_write_data *wdata = data;
-
 	put_nfs_open_context(wdata->args.context);
 	nfs_writedata_free(wdata);
 }
diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c
index 7e0b61be212e..c668bca579c1 100644
--- a/fs/nilfs2/btnode.c
+++ b/fs/nilfs2/btnode.c
@@ -209,6 +209,7 @@ int nilfs_btnode_prepare_change_key(struct address_space *btnc,
 		 * We cannot call radix_tree_preload for the kernels older
 		 * than 2.6.23, because it is not exported for modules.
 		 */
+retry:
 		err = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM);
 		if (err)
 			goto failed_unlock;
@@ -219,7 +220,6 @@ int nilfs_btnode_prepare_change_key(struct address_space *btnc,
 				       (unsigned long long)oldkey,
 				       (unsigned long long)newkey);
 
-retry:
 		spin_lock_irq(&btnc->tree_lock);
 		err = radix_tree_insert(&btnc->page_tree, newkey, obh->b_page);
 		spin_unlock_irq(&btnc->tree_lock);
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 8e2ec43b18f4..151964f0de4c 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -416,8 +416,10 @@ int nilfs_attach_checkpoint(struct nilfs_sb_info *sbi, __u64 cno)
 	if (unlikely(err))
 		goto failed;
 
+	down_read(&nilfs->ns_segctor_sem);
 	err = nilfs_cpfile_get_checkpoint(nilfs->ns_cpfile, cno, 0, &raw_cp,
 					  &bh_cp);
+	up_read(&nilfs->ns_segctor_sem);
 	if (unlikely(err)) {
 		if (err == -ENOENT || err == -EINVAL) {
 			printk(KERN_ERR
diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h
index e8adbffc626f..1b9caafb8662 100644
--- a/fs/nilfs2/the_nilfs.h
+++ b/fs/nilfs2/the_nilfs.h
@@ -253,7 +253,7 @@ nilfs_detach_writer(struct the_nilfs *nilfs, struct nilfs_sb_info *sbi)
 
 static inline void nilfs_put_sbinfo(struct nilfs_sb_info *sbi)
 {
-	if (!atomic_dec_and_test(&sbi->s_count))
+	if (atomic_dec_and_test(&sbi->s_count))
 		kfree(sbi);
 }
 
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index 47cd258fd24d..c9ee67b442e1 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -62,13 +62,14 @@ static int inotify_handle_event(struct fsnotify_group *group, struct fsnotify_ev
 	event_priv->wd = wd;
 
 	ret = fsnotify_add_notify_event(group, event, fsn_event_priv);
-	/* EEXIST is not an error */
-	if (ret == -EEXIST)
-		ret = 0;
-
-	/* did event_priv get attached? */
-	if (list_empty(&fsn_event_priv->event_list))
+	if (ret) {
 		inotify_free_event_priv(fsn_event_priv);
+		/* EEXIST says we tail matched, EOVERFLOW isn't something
+		 * to report up the stack. */
+		if ((ret == -EEXIST) ||
+		    (ret == -EOVERFLOW))
+			ret = 0;
+	}
 
 	/*
 	 * If we hold the entry until after the event is on the queue
@@ -104,16 +105,45 @@ static bool inotify_should_send_event(struct fsnotify_group *group, struct inode
 	return send;
 }
 
+/*
+ * This is NEVER supposed to be called.  Inotify marks should either have been
+ * removed from the idr when the watch was removed or in the
+ * fsnotify_destroy_mark_by_group() call when the inotify instance was being
+ * torn down.  This is only called if the idr is about to be freed but there
+ * are still marks in it.
+ */
 static int idr_callback(int id, void *p, void *data)
 {
-	BUG();
+	struct fsnotify_mark_entry *entry;
+	struct inotify_inode_mark_entry *ientry;
+	static bool warned = false;
+
+	if (warned)
+		return 0;
+
+	warned = false;
+	entry = p;
+	ientry = container_of(entry, struct inotify_inode_mark_entry, fsn_entry);
+
+	WARN(1, "inotify closing but id=%d for entry=%p in group=%p still in "
+		"idr.  Probably leaking memory\n", id, p, data);
+
+	/*
+	 * I'm taking the liberty of assuming that the mark in question is a
+	 * valid address and I'm dereferencing it.  This might help to figure
+	 * out why we got here and the panic is no worse than the original
+	 * BUG() that was here.
+	 */
+	if (entry)
+		printk(KERN_WARNING "entry->group=%p inode=%p wd=%d\n",
+			entry->group, entry->inode, ientry->wd);
 	return 0;
 }
 
 static void inotify_free_group_priv(struct fsnotify_group *group)
 {
 	/* ideally the idr is empty and we won't hit the BUG in teh callback */
-	idr_for_each(&group->inotify_data.idr, idr_callback, NULL);
+	idr_for_each(&group->inotify_data.idr, idr_callback, group);
 	idr_remove_all(&group->inotify_data.idr);
 	idr_destroy(&group->inotify_data.idr);
 }
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index f30d9bbc2e1b..dcd2040d330c 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -47,9 +47,6 @@
 
 static struct vfsmount *inotify_mnt __read_mostly;
 
-/* this just sits here and wastes global memory.  used to just pad userspace messages with zeros */
-static struct inotify_event nul_inotify_event;
-
 /* these are configurable via /proc/sys/fs/inotify/ */
 static int inotify_max_user_instances __read_mostly;
 static int inotify_max_queued_events __read_mostly;
@@ -157,7 +154,8 @@ static struct fsnotify_event *get_one_event(struct fsnotify_group *group,
 
 	event = fsnotify_peek_notify_event(group);
 
-	event_size += roundup(event->name_len, event_size);
+	if (event->name_len)
+		event_size += roundup(event->name_len + 1, event_size);
 
 	if (event_size > count)
 		return ERR_PTR(-EINVAL);
@@ -183,7 +181,7 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
 	struct fsnotify_event_private_data *fsn_priv;
 	struct inotify_event_private_data *priv;
 	size_t event_size = sizeof(struct inotify_event);
-	size_t name_len;
+	size_t name_len = 0;
 
 	/* we get the inotify watch descriptor from the event private data */
 	spin_lock(&event->lock);
@@ -199,8 +197,12 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
 		inotify_free_event_priv(fsn_priv);
 	}
 
-	/* round up event->name_len so it is a multiple of event_size */
-	name_len = roundup(event->name_len, event_size);
+	/*
+	 * round up event->name_len so it is a multiple of event_size
+	 * plus an extra byte for the terminating '\0'.
+	 */
+	if (event->name_len)
+		name_len = roundup(event->name_len + 1, event_size);
 	inotify_event.len = name_len;
 
 	inotify_event.mask = inotify_mask_to_arg(event->mask);
@@ -224,8 +226,8 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
 			return -EFAULT;
 		buf += event->name_len;
 
-		/* fill userspace with 0's from nul_inotify_event */
-		if (copy_to_user(buf, &nul_inotify_event, len_to_zero))
+		/* fill userspace with 0's */
+		if (clear_user(buf, len_to_zero))
 			return -EFAULT;
 		buf += len_to_zero;
 		event_size += name_len;
@@ -326,8 +328,9 @@ static long inotify_ioctl(struct file *file, unsigned int cmd,
 		list_for_each_entry(holder, &group->notification_list, event_list) {
 			event = holder->event;
 			send_len += sizeof(struct inotify_event);
-			send_len += roundup(event->name_len,
-					     sizeof(struct inotify_event));
+			if (event->name_len)
+				send_len += roundup(event->name_len + 1,
+						sizeof(struct inotify_event));
 		}
 		mutex_unlock(&group->notification_mutex);
 		ret = put_user(send_len, (int __user *) p);
@@ -364,20 +367,53 @@ static int inotify_find_inode(const char __user *dirname, struct path *path, uns
 	return error;
 }
 
+/*
+ * Remove the mark from the idr (if present) and drop the reference
+ * on the mark because it was in the idr.
+ */
 static void inotify_remove_from_idr(struct fsnotify_group *group,
 				    struct inotify_inode_mark_entry *ientry)
 {
 	struct idr *idr;
+	struct fsnotify_mark_entry *entry;
+	struct inotify_inode_mark_entry *found_ientry;
+	int wd;
 
 	spin_lock(&group->inotify_data.idr_lock);
 	idr = &group->inotify_data.idr;
-	idr_remove(idr, ientry->wd);
-	spin_unlock(&group->inotify_data.idr_lock);
+	wd = ientry->wd;
+
+	if (wd == -1)
+		goto out;
+
+	entry = idr_find(&group->inotify_data.idr, wd);
+	if (unlikely(!entry))
+		goto out;
+
+	found_ientry = container_of(entry, struct inotify_inode_mark_entry, fsn_entry);
+	if (unlikely(found_ientry != ientry)) {
+		/* We found an entry in the idr with the right wd, but it's
+		 * not the entry we were told to remove.  eparis seriously
+		 * fucked up somewhere. */
+		WARN_ON(1);
+		ientry->wd = -1;
+		goto out;
+	}
+
+	/* One ref for being in the idr, one ref held by the caller */
+	BUG_ON(atomic_read(&entry->refcnt) < 2);
+
+	idr_remove(idr, wd);
 	ientry->wd = -1;
+
+	/* removed from the idr, drop that ref */
+	fsnotify_put_mark(entry);
+out:
+	spin_unlock(&group->inotify_data.idr_lock);
 }
+
 /*
- * Send IN_IGNORED for this wd, remove this wd from the idr, and drop the
- * internal reference help on the mark because it is in the idr.
+ * Send IN_IGNORED for this wd, remove this wd from the idr.
  */
 void inotify_ignored_and_remove_idr(struct fsnotify_mark_entry *entry,
 				    struct fsnotify_group *group)
@@ -386,6 +422,7 @@ void inotify_ignored_and_remove_idr(struct fsnotify_mark_entry *entry,
 	struct fsnotify_event *ignored_event;
 	struct inotify_event_private_data *event_priv;
 	struct fsnotify_event_private_data *fsn_event_priv;
+	int ret;
 
 	ignored_event = fsnotify_create_event(NULL, FS_IN_IGNORED, NULL,
 					      FSNOTIFY_EVENT_NONE, NULL, 0,
@@ -404,10 +441,8 @@ void inotify_ignored_and_remove_idr(struct fsnotify_mark_entry *entry,
 	fsn_event_priv->group = group;
 	event_priv->wd = ientry->wd;
 
-	fsnotify_add_notify_event(group, ignored_event, fsn_event_priv);
-
-	/* did the private data get added? */
-	if (list_empty(&fsn_event_priv->event_list))
+	ret = fsnotify_add_notify_event(group, ignored_event, fsn_event_priv);
+	if (ret)
 		inotify_free_event_priv(fsn_event_priv);
 
 skip_send_ignore:
@@ -418,9 +453,6 @@ skip_send_ignore:
 	/* remove this entry from the idr */
 	inotify_remove_from_idr(group, ientry);
 
-	/* removed from idr, drop that reference */
-	fsnotify_put_mark(entry);
-
 	atomic_dec(&group->inotify_data.user->inotify_watches);
 }
 
@@ -432,80 +464,29 @@ static void inotify_free_mark(struct fsnotify_mark_entry *entry)
 	kmem_cache_free(inotify_inode_mark_cachep, ientry);
 }
 
-static int inotify_update_watch(struct fsnotify_group *group, struct inode *inode, u32 arg)
+static int inotify_update_existing_watch(struct fsnotify_group *group,
+					 struct inode *inode,
+					 u32 arg)
 {
-	struct fsnotify_mark_entry *entry = NULL;
+	struct fsnotify_mark_entry *entry;
 	struct inotify_inode_mark_entry *ientry;
-	struct inotify_inode_mark_entry *tmp_ientry;
-	int ret = 0;
-	int add = (arg & IN_MASK_ADD);
-	__u32 mask;
 	__u32 old_mask, new_mask;
+	__u32 mask;
+	int add = (arg & IN_MASK_ADD);
+	int ret;
 
 	/* don't allow invalid bits: we don't want flags set */
 	mask = inotify_arg_to_mask(arg);
 	if (unlikely(!mask))
 		return -EINVAL;
 
-	tmp_ientry = kmem_cache_alloc(inotify_inode_mark_cachep, GFP_KERNEL);
-	if (unlikely(!tmp_ientry))
-		return -ENOMEM;
-	/* we set the mask at the end after attaching it */
-	fsnotify_init_mark(&tmp_ientry->fsn_entry, inotify_free_mark);
-	tmp_ientry->wd = -1;
-
-find_entry:
 	spin_lock(&inode->i_lock);
 	entry = fsnotify_find_mark_entry(group, inode);
 	spin_unlock(&inode->i_lock);
-	if (entry) {
-		ientry = container_of(entry, struct inotify_inode_mark_entry, fsn_entry);
-	} else {
-		ret = -ENOSPC;
-		if (atomic_read(&group->inotify_data.user->inotify_watches) >= inotify_max_user_watches)
-			goto out_err;
-retry:
-		ret = -ENOMEM;
-		if (unlikely(!idr_pre_get(&group->inotify_data.idr, GFP_KERNEL)))
-			goto out_err;
-
-		spin_lock(&group->inotify_data.idr_lock);
-		ret = idr_get_new_above(&group->inotify_data.idr, &tmp_ientry->fsn_entry,
-					group->inotify_data.last_wd,
-					&tmp_ientry->wd);
-		spin_unlock(&group->inotify_data.idr_lock);
-		if (ret) {
-			if (ret == -EAGAIN)
-				goto retry;
-			goto out_err;
-		}
+	if (!entry)
+		return -ENOENT;
 
-		ret = fsnotify_add_mark(&tmp_ientry->fsn_entry, group, inode);
-		if (ret) {
-			inotify_remove_from_idr(group, tmp_ientry);
-			if (ret == -EEXIST)
-				goto find_entry;
-			goto out_err;
-		}
-
-		/* tmp_ientry has been added to the inode, so we are all set up.
-		 * now we just need to make sure tmp_ientry doesn't get freed and
-		 * we need to set up entry and ientry so the generic code can
-		 * do its thing. */
-		ientry = tmp_ientry;
-		entry = &ientry->fsn_entry;
-		tmp_ientry = NULL;
-
-		atomic_inc(&group->inotify_data.user->inotify_watches);
-
-		/* update the idr hint */
-		group->inotify_data.last_wd = ientry->wd;
-
-		/* we put the mark on the idr, take a reference */
-		fsnotify_get_mark(entry);
-	}
-
-	ret = ientry->wd;
+	ientry = container_of(entry, struct inotify_inode_mark_entry, fsn_entry);
 
 	spin_lock(&entry->lock);
 
@@ -537,18 +518,107 @@ retry:
 			fsnotify_recalc_group_mask(group);
 	}
 
-	/* this either matches fsnotify_find_mark_entry, or init_mark_entry
-	 * depending on which path we took... */
+	/* return the wd */
+	ret = ientry->wd;
+
+	/* match the get from fsnotify_find_mark_entry() */
 	fsnotify_put_mark(entry);
 
+	return ret;
+}
+
+static int inotify_new_watch(struct fsnotify_group *group,
+			     struct inode *inode,
+			     u32 arg)
+{
+	struct inotify_inode_mark_entry *tmp_ientry;
+	__u32 mask;
+	int ret;
+
+	/* don't allow invalid bits: we don't want flags set */
+	mask = inotify_arg_to_mask(arg);
+	if (unlikely(!mask))
+		return -EINVAL;
+
+	tmp_ientry = kmem_cache_alloc(inotify_inode_mark_cachep, GFP_KERNEL);
+	if (unlikely(!tmp_ientry))
+		return -ENOMEM;
+
+	fsnotify_init_mark(&tmp_ientry->fsn_entry, inotify_free_mark);
+	tmp_ientry->fsn_entry.mask = mask;
+	tmp_ientry->wd = -1;
+
+	ret = -ENOSPC;
+	if (atomic_read(&group->inotify_data.user->inotify_watches) >= inotify_max_user_watches)
+		goto out_err;
+retry:
+	ret = -ENOMEM;
+	if (unlikely(!idr_pre_get(&group->inotify_data.idr, GFP_KERNEL)))
+		goto out_err;
+
+	spin_lock(&group->inotify_data.idr_lock);
+	ret = idr_get_new_above(&group->inotify_data.idr, &tmp_ientry->fsn_entry,
+				group->inotify_data.last_wd,
+				&tmp_ientry->wd);
+	spin_unlock(&group->inotify_data.idr_lock);
+	if (ret) {
+		/* idr was out of memory allocate and try again */
+		if (ret == -EAGAIN)
+			goto retry;
+		goto out_err;
+	}
+
+	/* we put the mark on the idr, take a reference */
+	fsnotify_get_mark(&tmp_ientry->fsn_entry);
+
+	/* we are on the idr, now get on the inode */
+	ret = fsnotify_add_mark(&tmp_ientry->fsn_entry, group, inode);
+	if (ret) {
+		/* we failed to get on the inode, get off the idr */
+		inotify_remove_from_idr(group, tmp_ientry);
+		goto out_err;
+	}
+
+	/* update the idr hint, who cares about races, it's just a hint */
+	group->inotify_data.last_wd = tmp_ientry->wd;
+
+	/* increment the number of watches the user has */
+	atomic_inc(&group->inotify_data.user->inotify_watches);
+
+	/* return the watch descriptor for this new entry */
+	ret = tmp_ientry->wd;
+
+	/* match the ref from fsnotify_init_markentry() */
+	fsnotify_put_mark(&tmp_ientry->fsn_entry);
+
+	/* if this mark added a new event update the group mask */
+	if (mask & ~group->mask)
+		fsnotify_recalc_group_mask(group);
+
 out_err:
-	/* could be an error, could be that we found an existing mark */
-	if (tmp_ientry) {
-		/* on the idr but didn't make it on the inode */
-		if (tmp_ientry->wd != -1)
-			inotify_remove_from_idr(group, tmp_ientry);
+	if (ret < 0)
 		kmem_cache_free(inotify_inode_mark_cachep, tmp_ientry);
-	}
+
+	return ret;
+}
+
+static int inotify_update_watch(struct fsnotify_group *group, struct inode *inode, u32 arg)
+{
+	int ret = 0;
+
+retry:
+	/* try to update and existing watch with the new arg */
+	ret = inotify_update_existing_watch(group, inode, arg);
+	/* no mark present, try to add a new one */
+	if (ret == -ENOENT)
+		ret = inotify_new_watch(group, inode, arg);
+	/*
+	 * inotify_new_watch could race with another thread which did an
+	 * inotify_new_watch between the update_existing and the add watch
+	 * here, go back and try to update an existing mark again.
+	 */
+	if (ret == -EEXIST)
+		goto retry;
 
 	return ret;
 }
@@ -568,7 +638,7 @@ static struct fsnotify_group *inotify_new_group(struct user_struct *user, unsign
 
 	spin_lock_init(&group->inotify_data.idr_lock);
 	idr_init(&group->inotify_data.idr);
-	group->inotify_data.last_wd = 0;
+	group->inotify_data.last_wd = 1;
 	group->inotify_data.user = user;
 	group->inotify_data.fa = NULL;
 
diff --git a/fs/notify/notification.c b/fs/notify/notification.c
index 521368574e97..3816d5750dd5 100644
--- a/fs/notify/notification.c
+++ b/fs/notify/notification.c
@@ -153,6 +153,10 @@ static bool event_compare(struct fsnotify_event *old, struct fsnotify_event *new
 				return true;
 			break;
 		case (FSNOTIFY_EVENT_NONE):
+			if (old->mask & FS_Q_OVERFLOW)
+				return true;
+			else if (old->mask & FS_IN_IGNORED)
+				return false;
 			return false;
 		};
 	}
@@ -171,9 +175,7 @@ int fsnotify_add_notify_event(struct fsnotify_group *group, struct fsnotify_even
 	struct list_head *list = &group->notification_list;
 	struct fsnotify_event_holder *last_holder;
 	struct fsnotify_event *last_event;
-
-	/* easy to tell if priv was attached to the event */
-	INIT_LIST_HEAD(&priv->event_list);
+	int ret = 0;
 
 	/*
 	 * There is one fsnotify_event_holder embedded inside each fsnotify_event.
@@ -194,6 +196,7 @@ alloc_holder:
 
 	if (group->q_len >= group->max_events) {
 		event = &q_overflow_event;
+		ret = -EOVERFLOW;
 		/* sorry, no private data on the overflow event */
 		priv = NULL;
 	}
@@ -235,7 +238,7 @@ alloc_holder:
 	mutex_unlock(&group->notification_mutex);
 
 	wake_up(&group->notification_waitq);
-	return 0;
+	return ret;
 }
 
 /*
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 9edcde4974aa..ab513ddaeff2 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -1914,7 +1914,8 @@ static void ocfs2_adjust_adjacent_records(struct ocfs2_extent_rec *left_rec,
 	 * immediately to their right.
 	 */
 	left_clusters = le32_to_cpu(right_child_el->l_recs[0].e_cpos);
-	if (ocfs2_is_empty_extent(&right_child_el->l_recs[0])) {
+	if (!ocfs2_rec_clusters(right_child_el, &right_child_el->l_recs[0])) {
+		BUG_ON(right_child_el->l_tree_depth);
 		BUG_ON(le16_to_cpu(right_child_el->l_next_free_rec) <= 1);
 		left_clusters = le32_to_cpu(right_child_el->l_recs[1].e_cpos);
 	}
@@ -2476,15 +2477,37 @@ out_ret_path:
 	return ret;
 }
 
-static void ocfs2_update_edge_lengths(struct inode *inode, handle_t *handle,
-				      struct ocfs2_path *path)
+static int ocfs2_update_edge_lengths(struct inode *inode, handle_t *handle,
+				     int subtree_index, struct ocfs2_path *path)
 {
-	int i, idx;
+	int i, idx, ret;
 	struct ocfs2_extent_rec *rec;
 	struct ocfs2_extent_list *el;
 	struct ocfs2_extent_block *eb;
 	u32 range;
 
+	/*
+	 * In normal tree rotation process, we will never touch the
+	 * tree branch above subtree_index and ocfs2_extend_rotate_transaction
+	 * doesn't reserve the credits for them either.
+	 *
+	 * But we do have a special case here which will update the rightmost
+	 * records for all the bh in the path.
+	 * So we have to allocate extra credits and access them.
+	 */
+	ret = ocfs2_extend_trans(handle,
+				 handle->h_buffer_credits + subtree_index);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ret = ocfs2_journal_access_path(inode, handle, path);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
 	/* Path should always be rightmost. */
 	eb = (struct ocfs2_extent_block *)path_leaf_bh(path)->b_data;
 	BUG_ON(eb->h_next_leaf_blk != 0ULL);
@@ -2505,6 +2528,8 @@ static void ocfs2_update_edge_lengths(struct inode *inode, handle_t *handle,
 
 		ocfs2_journal_dirty(handle, path->p_node[i].bh);
 	}
+out:
+	return ret;
 }
 
 static void ocfs2_unlink_path(struct inode *inode, handle_t *handle,
@@ -2717,7 +2742,12 @@ static int ocfs2_rotate_subtree_left(struct inode *inode, handle_t *handle,
 	if (del_right_subtree) {
 		ocfs2_unlink_subtree(inode, handle, left_path, right_path,
 				     subtree_index, dealloc);
-		ocfs2_update_edge_lengths(inode, handle, left_path);
+		ret = ocfs2_update_edge_lengths(inode, handle, subtree_index,
+						left_path);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
 
 		eb = (struct ocfs2_extent_block *)path_leaf_bh(left_path)->b_data;
 		ocfs2_et_set_last_eb_blk(et, le64_to_cpu(eb->h_blkno));
@@ -3034,7 +3064,12 @@ static int ocfs2_remove_rightmost_path(struct inode *inode, handle_t *handle,
 
 		ocfs2_unlink_subtree(inode, handle, left_path, path,
 				     subtree_index, dealloc);
-		ocfs2_update_edge_lengths(inode, handle, left_path);
+		ret = ocfs2_update_edge_lengths(inode, handle, subtree_index,
+						left_path);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
 
 		eb = (struct ocfs2_extent_block *)path_leaf_bh(left_path)->b_data;
 		ocfs2_et_set_last_eb_blk(et, le64_to_cpu(eb->h_blkno));
@@ -6816,7 +6851,7 @@ static int ocfs2_do_truncate(struct ocfs2_super *osb,
 	}
 	status = 0;
 bail:
-
+	brelse(last_eb_bh);
 	mlog_exit(status);
 	return status;
 }
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index b2c52b3a1484..8a1e61545f41 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -193,6 +193,7 @@ static int ocfs2_get_block(struct inode *inode, sector_t iblock,
 			     (unsigned long long)OCFS2_I(inode)->ip_blkno);
 			mlog(ML_ERROR, "Size %llu, clusters %u\n", (unsigned long long)i_size_read(inode), OCFS2_I(inode)->ip_clusters);
 			dump_stack();
+			goto bail;
 		}
 
 		past_eof = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode));
@@ -894,18 +895,17 @@ struct ocfs2_write_cluster_desc {
 	 */
 	unsigned	c_new;
 	unsigned	c_unwritten;
+	unsigned	c_needs_zero;
 };
 
-static inline int ocfs2_should_zero_cluster(struct ocfs2_write_cluster_desc *d)
-{
-	return d->c_new || d->c_unwritten;
-}
-
 struct ocfs2_write_ctxt {
 	/* Logical cluster position / len of write */
 	u32				w_cpos;
 	u32				w_clen;
 
+	/* First cluster allocated in a nonsparse extend */
+	u32				w_first_new_cpos;
+
 	struct ocfs2_write_cluster_desc	w_desc[OCFS2_MAX_CLUSTERS_PER_PAGE];
 
 	/*
@@ -983,6 +983,7 @@ static int ocfs2_alloc_write_ctxt(struct ocfs2_write_ctxt **wcp,
 		return -ENOMEM;
 
 	wc->w_cpos = pos >> osb->s_clustersize_bits;
+	wc->w_first_new_cpos = UINT_MAX;
 	cend = (pos + len - 1) >> osb->s_clustersize_bits;
 	wc->w_clen = cend - wc->w_cpos + 1;
 	get_bh(di_bh);
@@ -1217,20 +1218,18 @@ out:
  */
 static int ocfs2_write_cluster(struct address_space *mapping,
 			       u32 phys, unsigned int unwritten,
+			       unsigned int should_zero,
 			       struct ocfs2_alloc_context *data_ac,
 			       struct ocfs2_alloc_context *meta_ac,
 			       struct ocfs2_write_ctxt *wc, u32 cpos,
 			       loff_t user_pos, unsigned user_len)
 {
-	int ret, i, new, should_zero = 0;
+	int ret, i, new;
 	u64 v_blkno, p_blkno;
 	struct inode *inode = mapping->host;
 	struct ocfs2_extent_tree et;
 
 	new = phys == 0 ? 1 : 0;
-	if (new || unwritten)
-		should_zero = 1;
-
 	if (new) {
 		u32 tmp_pos;
 
@@ -1301,7 +1300,7 @@ static int ocfs2_write_cluster(struct address_space *mapping,
 		if (tmpret) {
 			mlog_errno(tmpret);
 			if (ret == 0)
-				tmpret = ret;
+				ret = tmpret;
 		}
 	}
 
@@ -1341,7 +1340,9 @@ static int ocfs2_write_cluster_by_desc(struct address_space *mapping,
 			local_len = osb->s_clustersize - cluster_off;
 
 		ret = ocfs2_write_cluster(mapping, desc->c_phys,
-					  desc->c_unwritten, data_ac, meta_ac,
+					  desc->c_unwritten,
+					  desc->c_needs_zero,
+					  data_ac, meta_ac,
 					  wc, desc->c_cpos, pos, local_len);
 		if (ret) {
 			mlog_errno(ret);
@@ -1391,14 +1392,14 @@ static void ocfs2_set_target_boundaries(struct ocfs2_super *osb,
 		 * newly allocated cluster.
 		 */
 		desc = &wc->w_desc[0];
-		if (ocfs2_should_zero_cluster(desc))
+		if (desc->c_needs_zero)
 			ocfs2_figure_cluster_boundaries(osb,
 							desc->c_cpos,
 							&wc->w_target_from,
 							NULL);
 
 		desc = &wc->w_desc[wc->w_clen - 1];
-		if (ocfs2_should_zero_cluster(desc))
+		if (desc->c_needs_zero)
 			ocfs2_figure_cluster_boundaries(osb,
 							desc->c_cpos,
 							NULL,
@@ -1466,13 +1467,28 @@ static int ocfs2_populate_write_desc(struct inode *inode,
 			phys++;
 		}
 
+		/*
+		 * If w_first_new_cpos is < UINT_MAX, we have a non-sparse
+		 * file that got extended.  w_first_new_cpos tells us
+		 * where the newly allocated clusters are so we can
+		 * zero them.
+		 */
+		if (desc->c_cpos >= wc->w_first_new_cpos) {
+			BUG_ON(phys == 0);
+			desc->c_needs_zero = 1;
+		}
+
 		desc->c_phys = phys;
 		if (phys == 0) {
 			desc->c_new = 1;
+			desc->c_needs_zero = 1;
 			*clusters_to_alloc = *clusters_to_alloc + 1;
 		}
-		if (ext_flags & OCFS2_EXT_UNWRITTEN)
+
+		if (ext_flags & OCFS2_EXT_UNWRITTEN) {
 			desc->c_unwritten = 1;
+			desc->c_needs_zero = 1;
+		}
 
 		num_clusters--;
 	}
@@ -1632,10 +1648,13 @@ static int ocfs2_expand_nonsparse_inode(struct inode *inode, loff_t pos,
 	if (newsize <= i_size_read(inode))
 		return 0;
 
-	ret = ocfs2_extend_no_holes(inode, newsize, newsize - len);
+	ret = ocfs2_extend_no_holes(inode, newsize, pos);
 	if (ret)
 		mlog_errno(ret);
 
+	wc->w_first_new_cpos =
+		ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode));
+
 	return ret;
 }
 
@@ -1644,7 +1663,7 @@ int ocfs2_write_begin_nolock(struct address_space *mapping,
 			     struct page **pagep, void **fsdata,
 			     struct buffer_head *di_bh, struct page *mmap_page)
 {
-	int ret, credits = OCFS2_INODE_UPDATE_CREDITS;
+	int ret, cluster_of_pages, credits = OCFS2_INODE_UPDATE_CREDITS;
 	unsigned int clusters_to_alloc, extents_to_split;
 	struct ocfs2_write_ctxt *wc;
 	struct inode *inode = mapping->host;
@@ -1722,8 +1741,19 @@ int ocfs2_write_begin_nolock(struct address_space *mapping,
 
 	}
 
-	ocfs2_set_target_boundaries(osb, wc, pos, len,
-				    clusters_to_alloc + extents_to_split);
+	/*
+	 * We have to zero sparse allocated clusters, unwritten extent clusters,
+	 * and non-sparse clusters we just extended.  For non-sparse writes,
+	 * we know zeros will only be needed in the first and/or last cluster.
+	 */
+	if (clusters_to_alloc || extents_to_split ||
+	    (wc->w_clen && (wc->w_desc[0].c_needs_zero ||
+			    wc->w_desc[wc->w_clen - 1].c_needs_zero)))
+		cluster_of_pages = 1;
+	else
+		cluster_of_pages = 0;
+
+	ocfs2_set_target_boundaries(osb, wc, pos, len, cluster_of_pages);
 
 	handle = ocfs2_start_trans(osb, credits);
 	if (IS_ERR(handle)) {
@@ -1756,8 +1786,7 @@ int ocfs2_write_begin_nolock(struct address_space *mapping,
 	 * extent.
 	 */
 	ret = ocfs2_grab_pages_for_write(mapping, wc, wc->w_cpos, pos,
-					 clusters_to_alloc + extents_to_split,
-					 mmap_page);
+					 cluster_of_pages, mmap_page);
 	if (ret) {
 		mlog_errno(ret);
 		goto out_quota;
diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c
index b574431a031d..b4957c7d9fe2 100644
--- a/fs/ocfs2/dcache.c
+++ b/fs/ocfs2/dcache.c
@@ -85,6 +85,17 @@ static int ocfs2_dentry_revalidate(struct dentry *dentry,
 		goto bail;
 	}
 
+	/*
+	 * If the last lookup failed to create dentry lock, let us
+	 * redo it.
+	 */
+	if (!dentry->d_fsdata) {
+		mlog(0, "Inode %llu doesn't have dentry lock, "
+		     "returning false\n",
+		     (unsigned long long)OCFS2_I(inode)->ip_blkno);
+		goto bail;
+	}
+
 	ret = 1;
 
 bail:
@@ -310,22 +321,19 @@ out_attach:
 	return ret;
 }
 
-static DEFINE_SPINLOCK(dentry_list_lock);
+DEFINE_SPINLOCK(dentry_list_lock);
 
 /* We limit the number of dentry locks to drop in one go. We have
  * this limit so that we don't starve other users of ocfs2_wq. */
 #define DL_INODE_DROP_COUNT 64
 
 /* Drop inode references from dentry locks */
-void ocfs2_drop_dl_inodes(struct work_struct *work)
+static void __ocfs2_drop_dl_inodes(struct ocfs2_super *osb, int drop_count)
 {
-	struct ocfs2_super *osb = container_of(work, struct ocfs2_super,
-					       dentry_lock_work);
 	struct ocfs2_dentry_lock *dl;
-	int drop_count = DL_INODE_DROP_COUNT;
 
 	spin_lock(&dentry_list_lock);
-	while (osb->dentry_lock_list && drop_count--) {
+	while (osb->dentry_lock_list && (drop_count < 0 || drop_count--)) {
 		dl = osb->dentry_lock_list;
 		osb->dentry_lock_list = dl->dl_next;
 		spin_unlock(&dentry_list_lock);
@@ -333,11 +341,32 @@ void ocfs2_drop_dl_inodes(struct work_struct *work)
 		kfree(dl);
 		spin_lock(&dentry_list_lock);
 	}
-	if (osb->dentry_lock_list)
+	spin_unlock(&dentry_list_lock);
+}
+
+void ocfs2_drop_dl_inodes(struct work_struct *work)
+{
+	struct ocfs2_super *osb = container_of(work, struct ocfs2_super,
+					       dentry_lock_work);
+
+	__ocfs2_drop_dl_inodes(osb, DL_INODE_DROP_COUNT);
+	/*
+	 * Don't queue dropping if umount is in progress. We flush the
+	 * list in ocfs2_dismount_volume
+	 */
+	spin_lock(&dentry_list_lock);
+	if (osb->dentry_lock_list &&
+	    !ocfs2_test_osb_flag(osb, OCFS2_OSB_DROP_DENTRY_LOCK_IMMED))
 		queue_work(ocfs2_wq, &osb->dentry_lock_work);
 	spin_unlock(&dentry_list_lock);
 }
 
+/* Flush the whole work queue */
+void ocfs2_drop_all_dl_inodes(struct ocfs2_super *osb)
+{
+	__ocfs2_drop_dl_inodes(osb, -1);
+}
+
 /*
  * ocfs2_dentry_iput() and friends.
  *
@@ -368,7 +397,8 @@ static void ocfs2_drop_dentry_lock(struct ocfs2_super *osb,
 	/* We leave dropping of inode reference to ocfs2_wq as that can
 	 * possibly lead to inode deletion which gets tricky */
 	spin_lock(&dentry_list_lock);
-	if (!osb->dentry_lock_list)
+	if (!osb->dentry_lock_list &&
+	    !ocfs2_test_osb_flag(osb, OCFS2_OSB_DROP_DENTRY_LOCK_IMMED))
 		queue_work(ocfs2_wq, &osb->dentry_lock_work);
 	dl->dl_next = osb->dentry_lock_list;
 	osb->dentry_lock_list = dl;
diff --git a/fs/ocfs2/dcache.h b/fs/ocfs2/dcache.h
index faa12e75f98d..f5dd1789acf1 100644
--- a/fs/ocfs2/dcache.h
+++ b/fs/ocfs2/dcache.h
@@ -49,10 +49,13 @@ struct ocfs2_dentry_lock {
 int ocfs2_dentry_attach_lock(struct dentry *dentry, struct inode *inode,
 			     u64 parent_blkno);
 
+extern spinlock_t dentry_list_lock;
+
 void ocfs2_dentry_lock_put(struct ocfs2_super *osb,
 			   struct ocfs2_dentry_lock *dl);
 
 void ocfs2_drop_dl_inodes(struct work_struct *work);
+void ocfs2_drop_all_dl_inodes(struct ocfs2_super *osb);
 
 struct dentry *ocfs2_find_local_alias(struct inode *inode, u64 parent_blkno,
 				      int skip_unhashed);
diff --git a/fs/ocfs2/dlm/dlmast.c b/fs/ocfs2/dlm/dlmast.c
index d07ddbe4b283..81eff8e58322 100644
--- a/fs/ocfs2/dlm/dlmast.c
+++ b/fs/ocfs2/dlm/dlmast.c
@@ -103,7 +103,6 @@ static void __dlm_queue_ast(struct dlm_ctxt *dlm, struct dlm_lock *lock)
 		     lock->ast_pending, lock->ml.type);
 		BUG();
 	}
-	BUG_ON(!list_empty(&lock->ast_list));
 	if (lock->ast_pending)
 		mlog(0, "lock has an ast getting flushed right now\n");
 
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index bcb9260c3735..43e6e3280569 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -1118,7 +1118,7 @@ static int dlm_send_mig_lockres_msg(struct dlm_ctxt *dlm,
 
 	mlog(0, "%s:%.*s: sending mig lockres (%s) to %u\n",
 	     dlm->name, res->lockname.len, res->lockname.name,
-	     orig_flags & DLM_MRES_MIGRATION ? "migrate" : "recovery",
+	     orig_flags & DLM_MRES_MIGRATION ? "migration" : "recovery",
 	     send_to);
 
 	/* send it */
diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c
index fcf879ed6930..756f5b0998e0 100644
--- a/fs/ocfs2/dlm/dlmunlock.c
+++ b/fs/ocfs2/dlm/dlmunlock.c
@@ -122,7 +122,7 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm,
 	 * that still has AST's pending... */
 	in_use = !list_empty(&lock->ast_list);
 	spin_unlock(&dlm->ast_lock);
-	if (in_use) {
+	if (in_use && !(flags & LKM_CANCEL)) {
 	       mlog(ML_ERROR, "lockres %.*s: Someone is calling dlmunlock "
 		    "while waiting for an ast!", res->lockname.len,
 		    res->lockname.name);
@@ -131,7 +131,7 @@ static enum dlm_status dlmunlock_common(struct dlm_ctxt *dlm,
 
 	spin_lock(&res->spinlock);
 	if (res->state & DLM_LOCK_RES_IN_PROGRESS) {
-		if (master_node) {
+		if (master_node && !(flags & LKM_CANCEL)) {
 			mlog(ML_ERROR, "lockres in progress!\n");
 			spin_unlock(&res->spinlock);
 			return DLM_FORWARD;
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 62442e413a00..aa501d3f93f1 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1851,6 +1851,7 @@ relock:
 		if (ret)
 			goto out_dio;
 
+		count = ocount;
 		ret = generic_write_checks(file, ppos, &count,
 					   S_ISBLK(inode->i_mode));
 		if (ret)
@@ -1918,8 +1919,10 @@ out_sems:
 
 	mutex_unlock(&inode->i_mutex);
 
+	if (written)
+		ret = written;
 	mlog_exit(ret);
-	return written ? written : ret;
+	return ret;
 }
 
 static int ocfs2_splice_to_file(struct pipe_inode_info *pipe,
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index f033760ecbea..c48b93ac6b65 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -1954,10 +1954,16 @@ void ocfs2_orphan_scan_init(struct ocfs2_super *osb)
 	os->os_osb = osb;
 	os->os_count = 0;
 	os->os_seqno = 0;
-	os->os_scantime = CURRENT_TIME;
 	mutex_init(&os->os_lock);
 	INIT_DELAYED_WORK(&os->os_orphan_scan_work, ocfs2_orphan_scan_work);
+}
 
+void ocfs2_orphan_scan_start(struct ocfs2_super *osb)
+{
+	struct ocfs2_orphan_scan *os;
+
+	os = &osb->osb_orphan_scan;
+	os->os_scantime = CURRENT_TIME;
 	if (ocfs2_is_hard_readonly(osb) || ocfs2_mount_local(osb))
 		atomic_set(&os->os_state, ORPHAN_SCAN_INACTIVE);
 	else {
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index 5432c7f79cc6..2c3222aec622 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -145,6 +145,7 @@ static inline void ocfs2_inode_set_new(struct ocfs2_super *osb,
 
 /* Exported only for the journal struct init code in super.c. Do not call. */
 void ocfs2_orphan_scan_init(struct ocfs2_super *osb);
+void ocfs2_orphan_scan_start(struct ocfs2_super *osb);
 void ocfs2_orphan_scan_stop(struct ocfs2_super *osb);
 void ocfs2_orphan_scan_exit(struct ocfs2_super *osb);
 
@@ -329,20 +330,27 @@ int                  ocfs2_journal_dirty(handle_t *handle,
 /* extended attribute block update */
 #define OCFS2_XATTR_BLOCK_UPDATE_CREDITS 1
 
+/* Update of a single quota block */
+#define OCFS2_QUOTA_BLOCK_UPDATE_CREDITS 1
+
 /* global quotafile inode update, data block */
-#define OCFS2_QINFO_WRITE_CREDITS (OCFS2_INODE_UPDATE_CREDITS + 1)
+#define OCFS2_QINFO_WRITE_CREDITS (OCFS2_INODE_UPDATE_CREDITS + \
+				   OCFS2_QUOTA_BLOCK_UPDATE_CREDITS)
 
+#define OCFS2_LOCAL_QINFO_WRITE_CREDITS OCFS2_QUOTA_BLOCK_UPDATE_CREDITS
 /*
  * The two writes below can accidentally see global info dirty due
  * to set_info() quotactl so make them prepared for the writes.
  */
 /* quota data block, global info */
 /* Write to local quota file */
-#define OCFS2_QWRITE_CREDITS (OCFS2_QINFO_WRITE_CREDITS + 1)
+#define OCFS2_QWRITE_CREDITS (OCFS2_QINFO_WRITE_CREDITS + \
+			      OCFS2_QUOTA_BLOCK_UPDATE_CREDITS)
 
 /* global quota data block, local quota data block, global quota inode,
  * global quota info */
-#define OCFS2_QSYNC_CREDITS (OCFS2_INODE_UPDATE_CREDITS + 3)
+#define OCFS2_QSYNC_CREDITS (OCFS2_QINFO_WRITE_CREDITS + \
+			     2 * OCFS2_QUOTA_BLOCK_UPDATE_CREDITS)
 
 static inline int ocfs2_quota_trans_credits(struct super_block *sb)
 {
@@ -355,11 +363,6 @@ static inline int ocfs2_quota_trans_credits(struct super_block *sb)
 	return credits;
 }
 
-/* Number of credits needed for removing quota structure from file */
-int ocfs2_calc_qdel_credits(struct super_block *sb, int type);
-/* Number of credits needed for initialization of new quota structure */
-int ocfs2_calc_qinit_credits(struct super_block *sb, int type);
-
 /* group extend. inode update and last group update. */
 #define OCFS2_GROUP_EXTEND_CREDITS	(OCFS2_INODE_UPDATE_CREDITS + 1)
 
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index c9345ebb8493..39e1d5a39505 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -224,10 +224,12 @@ enum ocfs2_mount_options
 	OCFS2_MOUNT_GRPQUOTA = 1 << 10, /* We support group quotas */
 };
 
-#define OCFS2_OSB_SOFT_RO	0x0001
-#define OCFS2_OSB_HARD_RO	0x0002
-#define OCFS2_OSB_ERROR_FS	0x0004
-#define OCFS2_DEFAULT_ATIME_QUANTUM	60
+#define OCFS2_OSB_SOFT_RO			0x0001
+#define OCFS2_OSB_HARD_RO			0x0002
+#define OCFS2_OSB_ERROR_FS			0x0004
+#define OCFS2_OSB_DROP_DENTRY_LOCK_IMMED	0x0008
+
+#define OCFS2_DEFAULT_ATIME_QUANTUM		60
 
 struct ocfs2_journal;
 struct ocfs2_slot_info;
@@ -490,6 +492,18 @@ static inline void ocfs2_set_osb_flag(struct ocfs2_super *osb,
 	spin_unlock(&osb->osb_lock);
 }
 
+
+static inline unsigned long  ocfs2_test_osb_flag(struct ocfs2_super *osb,
+						 unsigned long flag)
+{
+	unsigned long ret;
+
+	spin_lock(&osb->osb_lock);
+	ret = osb->osb_flags & flag;
+	spin_unlock(&osb->osb_lock);
+	return ret;
+}
+
 static inline void ocfs2_set_ro_flag(struct ocfs2_super *osb,
 				     int hard)
 {
diff --git a/fs/ocfs2/ocfs2_lockid.h b/fs/ocfs2/ocfs2_lockid.h
index fcdba091af3d..c212cf5a2bdf 100644
--- a/fs/ocfs2/ocfs2_lockid.h
+++ b/fs/ocfs2/ocfs2_lockid.h
@@ -108,6 +108,7 @@ static char *ocfs2_lock_type_strings[] = {
 	[OCFS2_LOCK_TYPE_OPEN] = "Open",
 	[OCFS2_LOCK_TYPE_FLOCK] = "Flock",
 	[OCFS2_LOCK_TYPE_QINFO] = "Quota",
+	[OCFS2_LOCK_TYPE_NFS_SYNC] = "NFSSync",
 	[OCFS2_LOCK_TYPE_ORPHAN_SCAN] = "OrphanScan",
 };
 
diff --git a/fs/ocfs2/quota.h b/fs/ocfs2/quota.h
index 7365e2e08706..3fb96fcd4c81 100644
--- a/fs/ocfs2/quota.h
+++ b/fs/ocfs2/quota.h
@@ -50,7 +50,6 @@ struct ocfs2_mem_dqinfo {
 	unsigned int dqi_chunks;	/* Number of chunks in local quota file */
 	unsigned int dqi_blocks;	/* Number of blocks allocated for local quota file */
 	unsigned int dqi_syncms;	/* How often should we sync with other nodes */
-	unsigned int dqi_syncjiff;	/* Precomputed dqi_syncms in jiffies */
 	struct list_head dqi_chunk;	/* List of chunks */
 	struct inode *dqi_gqinode;	/* Global quota file inode */
 	struct ocfs2_lock_res dqi_gqlock;	/* Lock protecting quota information structure */
diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c
index edfa60cd155c..44f2a5e1d042 100644
--- a/fs/ocfs2/quota_global.c
+++ b/fs/ocfs2/quota_global.c
@@ -23,6 +23,7 @@
 #include "sysfile.h"
 #include "dlmglue.h"
 #include "uptodate.h"
+#include "super.h"
 #include "quota.h"
 
 static struct workqueue_struct *ocfs2_quota_wq = NULL;
@@ -69,6 +70,7 @@ static void ocfs2_global_mem2diskdqb(void *dp, struct dquot *dquot)
 	d->dqb_curspace = cpu_to_le64(m->dqb_curspace);
 	d->dqb_btime = cpu_to_le64(m->dqb_btime);
 	d->dqb_itime = cpu_to_le64(m->dqb_itime);
+	d->dqb_pad1 = d->dqb_pad2 = 0;
 }
 
 static int ocfs2_global_is_id(void *dp, struct dquot *dquot)
@@ -113,6 +115,15 @@ int ocfs2_read_quota_block(struct inode *inode, u64 v_block,
 	int rc = 0;
 	struct buffer_head *tmp = *bh;
 
+	if (i_size_read(inode) >> inode->i_sb->s_blocksize_bits <= v_block) {
+		ocfs2_error(inode->i_sb,
+			    "Quota file %llu is probably corrupted! Requested "
+			    "to read block %Lu but file has size only %Lu\n",
+			    (unsigned long long)OCFS2_I(inode)->ip_blkno,
+			    (unsigned long long)v_block,
+			    (unsigned long long)i_size_read(inode));
+		return -EIO;
+	}
 	rc = ocfs2_read_virt_blocks(inode, v_block, 1, &tmp, 0,
 				    ocfs2_validate_quota_block);
 	if (rc)
@@ -211,14 +222,13 @@ ssize_t ocfs2_quota_write(struct super_block *sb, int type,
 
 	mutex_lock_nested(&gqinode->i_mutex, I_MUTEX_QUOTA);
 	if (gqinode->i_size < off + len) {
-		down_write(&OCFS2_I(gqinode)->ip_alloc_sem);
-		err = ocfs2_extend_no_holes(gqinode, off + len, off);
-		up_write(&OCFS2_I(gqinode)->ip_alloc_sem);
-		if (err < 0)
-			goto out;
+		loff_t rounded_end =
+				ocfs2_align_bytes_to_blocks(sb, off + len);
+
+		/* Space is already allocated in ocfs2_global_read_dquot() */
 		err = ocfs2_simple_size_update(gqinode,
 					       oinfo->dqi_gqi_bh,
-					       off + len);
+					       rounded_end);
 		if (err < 0)
 			goto out;
 		new = 1;
@@ -234,7 +244,7 @@ ssize_t ocfs2_quota_write(struct super_block *sb, int type,
 	}
 	if (err) {
 		mlog_errno(err);
-		return err;
+		goto out;
 	}
 	lock_buffer(bh);
 	if (new)
@@ -342,7 +352,6 @@ int ocfs2_global_read_info(struct super_block *sb, int type)
 	info->dqi_bgrace = le32_to_cpu(dinfo.dqi_bgrace);
 	info->dqi_igrace = le32_to_cpu(dinfo.dqi_igrace);
 	oinfo->dqi_syncms = le32_to_cpu(dinfo.dqi_syncms);
-	oinfo->dqi_syncjiff = msecs_to_jiffies(oinfo->dqi_syncms);
 	oinfo->dqi_gi.dqi_blocks = le32_to_cpu(dinfo.dqi_blocks);
 	oinfo->dqi_gi.dqi_free_blk = le32_to_cpu(dinfo.dqi_free_blk);
 	oinfo->dqi_gi.dqi_free_entry = le32_to_cpu(dinfo.dqi_free_entry);
@@ -352,7 +361,7 @@ int ocfs2_global_read_info(struct super_block *sb, int type)
 	oinfo->dqi_gi.dqi_qtree_depth = qtree_depth(&oinfo->dqi_gi);
 	INIT_DELAYED_WORK(&oinfo->dqi_sync_work, qsync_work_fn);
 	queue_delayed_work(ocfs2_quota_wq, &oinfo->dqi_sync_work,
-			   oinfo->dqi_syncjiff);
+			   msecs_to_jiffies(oinfo->dqi_syncms));
 
 out_err:
 	mlog_exit(status);
@@ -402,13 +411,36 @@ int ocfs2_global_write_info(struct super_block *sb, int type)
 	return err;
 }
 
+static int ocfs2_global_qinit_alloc(struct super_block *sb, int type)
+{
+	struct ocfs2_mem_dqinfo *oinfo = sb_dqinfo(sb, type)->dqi_priv;
+
+	/*
+	 * We may need to allocate tree blocks and a leaf block but not the
+	 * root block
+	 */
+	return oinfo->dqi_gi.dqi_qtree_depth;
+}
+
+static int ocfs2_calc_global_qinit_credits(struct super_block *sb, int type)
+{
+	/* We modify all the allocated blocks, tree root, and info block */
+	return (ocfs2_global_qinit_alloc(sb, type) + 2) *
+			OCFS2_QUOTA_BLOCK_UPDATE_CREDITS;
+}
+
 /* Read in information from global quota file and acquire a reference to it.
  * dquot_acquire() has already started the transaction and locked quota file */
 int ocfs2_global_read_dquot(struct dquot *dquot)
 {
 	int err, err2, ex = 0;
-	struct ocfs2_mem_dqinfo *info =
-			sb_dqinfo(dquot->dq_sb, dquot->dq_type)->dqi_priv;
+	struct super_block *sb = dquot->dq_sb;
+	int type = dquot->dq_type;
+	struct ocfs2_mem_dqinfo *info = sb_dqinfo(sb, type)->dqi_priv;
+	struct ocfs2_super *osb = OCFS2_SB(sb);
+	struct inode *gqinode = info->dqi_gqinode;
+	int need_alloc = ocfs2_global_qinit_alloc(sb, type);
+	handle_t *handle = NULL;
 
 	err = ocfs2_qinfo_lock(info, 0);
 	if (err < 0)
@@ -419,14 +451,33 @@ int ocfs2_global_read_dquot(struct dquot *dquot)
 	OCFS2_DQUOT(dquot)->dq_use_count++;
 	OCFS2_DQUOT(dquot)->dq_origspace = dquot->dq_dqb.dqb_curspace;
 	OCFS2_DQUOT(dquot)->dq_originodes = dquot->dq_dqb.dqb_curinodes;
+	ocfs2_qinfo_unlock(info, 0);
+
 	if (!dquot->dq_off) {	/* No real quota entry? */
-		/* Upgrade to exclusive lock for allocation */
-		ocfs2_qinfo_unlock(info, 0);
-		err = ocfs2_qinfo_lock(info, 1);
-		if (err < 0)
-			goto out_qlock;
 		ex = 1;
+		/*
+		 * Add blocks to quota file before we start a transaction since
+		 * locking allocators ranks above a transaction start
+		 */
+		WARN_ON(journal_current_handle());
+		down_write(&OCFS2_I(gqinode)->ip_alloc_sem);
+		err = ocfs2_extend_no_holes(gqinode,
+			gqinode->i_size + (need_alloc << sb->s_blocksize_bits),
+			gqinode->i_size);
+		up_write(&OCFS2_I(gqinode)->ip_alloc_sem);
+		if (err < 0)
+			goto out;
 	}
+
+	handle = ocfs2_start_trans(osb,
+				   ocfs2_calc_global_qinit_credits(sb, type));
+	if (IS_ERR(handle)) {
+		err = PTR_ERR(handle);
+		goto out;
+	}
+	err = ocfs2_qinfo_lock(info, ex);
+	if (err < 0)
+		goto out_trans;
 	err = qtree_write_dquot(&info->dqi_gi, dquot);
 	if (ex && info_dirty(sb_dqinfo(dquot->dq_sb, dquot->dq_type))) {
 		err2 = __ocfs2_global_write_info(dquot->dq_sb, dquot->dq_type);
@@ -438,6 +489,9 @@ out_qlock:
 		ocfs2_qinfo_unlock(info, 1);
 	else
 		ocfs2_qinfo_unlock(info, 0);
+out_trans:
+	if (handle)
+		ocfs2_commit_trans(osb, handle);
 out:
 	if (err < 0)
 		mlog_errno(err);
@@ -607,7 +661,7 @@ static void qsync_work_fn(struct work_struct *work)
 
 	dquot_scan_active(sb, ocfs2_sync_dquot_helper, oinfo->dqi_type);
 	queue_delayed_work(ocfs2_quota_wq, &oinfo->dqi_sync_work,
-			   oinfo->dqi_syncjiff);
+			   msecs_to_jiffies(oinfo->dqi_syncms));
 }
 
 /*
@@ -635,20 +689,18 @@ out:
 	return status;
 }
 
-int ocfs2_calc_qdel_credits(struct super_block *sb, int type)
+static int ocfs2_calc_qdel_credits(struct super_block *sb, int type)
 {
-	struct ocfs2_mem_dqinfo *oinfo;
-	int features[MAXQUOTAS] = { OCFS2_FEATURE_RO_COMPAT_USRQUOTA,
-				    OCFS2_FEATURE_RO_COMPAT_GRPQUOTA };
-
-	if (!OCFS2_HAS_RO_COMPAT_FEATURE(sb, features[type]))
-		return 0;
-
-	oinfo = sb_dqinfo(sb, type)->dqi_priv;
-	/* We modify tree, leaf block, global info, local chunk header,
-	 * global and local inode */
-	return oinfo->dqi_gi.dqi_qtree_depth + 2 + 1 +
-	       2 * OCFS2_INODE_UPDATE_CREDITS;
+	struct ocfs2_mem_dqinfo *oinfo = sb_dqinfo(sb, type)->dqi_priv;
+	/*
+	 * We modify tree, leaf block, global info, local chunk header,
+	 * global and local inode; OCFS2_QINFO_WRITE_CREDITS already
+	 * accounts for inode update
+	 */
+	return (oinfo->dqi_gi.dqi_qtree_depth + 2) *
+	       OCFS2_QUOTA_BLOCK_UPDATE_CREDITS +
+	       OCFS2_QINFO_WRITE_CREDITS +
+	       OCFS2_INODE_UPDATE_CREDITS;
 }
 
 static int ocfs2_release_dquot(struct dquot *dquot)
@@ -680,33 +732,10 @@ out:
 	return status;
 }
 
-int ocfs2_calc_qinit_credits(struct super_block *sb, int type)
-{
-	struct ocfs2_mem_dqinfo *oinfo;
-	int features[MAXQUOTAS] = { OCFS2_FEATURE_RO_COMPAT_USRQUOTA,
-				    OCFS2_FEATURE_RO_COMPAT_GRPQUOTA };
-	struct ocfs2_dinode *lfe, *gfe;
-
-	if (!OCFS2_HAS_RO_COMPAT_FEATURE(sb, features[type]))
-		return 0;
-
-	oinfo = sb_dqinfo(sb, type)->dqi_priv;
-	gfe = (struct ocfs2_dinode *)oinfo->dqi_gqi_bh->b_data;
-	lfe = (struct ocfs2_dinode *)oinfo->dqi_lqi_bh->b_data;
-	/* We can extend local file + global file. In local file we
-	 * can modify info, chunk header block and dquot block. In
-	 * global file we can modify info, tree and leaf block */
-	return ocfs2_calc_extend_credits(sb, &lfe->id2.i_list, 0) +
-	       ocfs2_calc_extend_credits(sb, &gfe->id2.i_list, 0) +
-	       3 + oinfo->dqi_gi.dqi_qtree_depth + 2;
-}
-
 static int ocfs2_acquire_dquot(struct dquot *dquot)
 {
-	handle_t *handle;
 	struct ocfs2_mem_dqinfo *oinfo =
 			sb_dqinfo(dquot->dq_sb, dquot->dq_type)->dqi_priv;
-	struct ocfs2_super *osb = OCFS2_SB(dquot->dq_sb);
 	int status = 0;
 
 	mlog_entry("id=%u, type=%d", dquot->dq_id, dquot->dq_type);
@@ -715,16 +744,7 @@ static int ocfs2_acquire_dquot(struct dquot *dquot)
 	status = ocfs2_lock_global_qf(oinfo, 1);
 	if (status < 0)
 		goto out;
-	handle = ocfs2_start_trans(osb,
-		ocfs2_calc_qinit_credits(dquot->dq_sb, dquot->dq_type));
-	if (IS_ERR(handle)) {
-		status = PTR_ERR(handle);
-		mlog_errno(status);
-		goto out_ilock;
-	}
 	status = dquot_acquire(dquot);
-	ocfs2_commit_trans(osb, handle);
-out_ilock:
 	ocfs2_unlock_global_qf(oinfo, 1);
 out:
 	mlog_exit(status);
diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c
index 5a460fa82553..bdb09cb6e1fe 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -20,6 +20,7 @@
 #include "sysfile.h"
 #include "dlmglue.h"
 #include "quota.h"
+#include "uptodate.h"
 
 /* Number of local quota structures per block */
 static inline unsigned int ol_quota_entries_per_block(struct super_block *sb)
@@ -100,7 +101,8 @@ static int ocfs2_modify_bh(struct inode *inode, struct buffer_head *bh,
 	handle_t *handle;
 	int status;
 
-	handle = ocfs2_start_trans(OCFS2_SB(sb), 1);
+	handle = ocfs2_start_trans(OCFS2_SB(sb),
+				   OCFS2_QUOTA_BLOCK_UPDATE_CREDITS);
 	if (IS_ERR(handle)) {
 		status = PTR_ERR(handle);
 		mlog_errno(status);
@@ -610,7 +612,8 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb,
 			goto out_bh;
 		/* Mark quota file as clean if we are recovering quota file of
 		 * some other node. */
-		handle = ocfs2_start_trans(osb, 1);
+		handle = ocfs2_start_trans(osb,
+					   OCFS2_LOCAL_QINFO_WRITE_CREDITS);
 		if (IS_ERR(handle)) {
 			status = PTR_ERR(handle);
 			mlog_errno(status);
@@ -940,7 +943,7 @@ static struct ocfs2_quota_chunk *ocfs2_local_quota_add_chunk(
 	struct ocfs2_local_disk_chunk *dchunk;
 	int status;
 	handle_t *handle;
-	struct buffer_head *bh = NULL;
+	struct buffer_head *bh = NULL, *dbh = NULL;
 	u64 p_blkno;
 
 	/* We are protected by dqio_sem so no locking needed */
@@ -964,32 +967,35 @@ static struct ocfs2_quota_chunk *ocfs2_local_quota_add_chunk(
 		mlog_errno(status);
 		goto out;
 	}
+	/* Local quota info and two new blocks we initialize */
+	handle = ocfs2_start_trans(OCFS2_SB(sb),
+			OCFS2_LOCAL_QINFO_WRITE_CREDITS +
+			2 * OCFS2_QUOTA_BLOCK_UPDATE_CREDITS);
+	if (IS_ERR(handle)) {
+		status = PTR_ERR(handle);
+		mlog_errno(status);
+		goto out;
+	}
 
+	/* Initialize chunk header */
 	down_read(&OCFS2_I(lqinode)->ip_alloc_sem);
 	status = ocfs2_extent_map_get_blocks(lqinode, oinfo->dqi_blocks,
 					     &p_blkno, NULL, NULL);
 	up_read(&OCFS2_I(lqinode)->ip_alloc_sem);
 	if (status < 0) {
 		mlog_errno(status);
-		goto out;
+		goto out_trans;
 	}
 	bh = sb_getblk(sb, p_blkno);
 	if (!bh) {
 		status = -ENOMEM;
 		mlog_errno(status);
-		goto out;
+		goto out_trans;
 	}
 	dchunk = (struct ocfs2_local_disk_chunk *)bh->b_data;
-
-	handle = ocfs2_start_trans(OCFS2_SB(sb), 2);
-	if (IS_ERR(handle)) {
-		status = PTR_ERR(handle);
-		mlog_errno(status);
-		goto out;
-	}
-
+	ocfs2_set_new_buffer_uptodate(lqinode, bh);
 	status = ocfs2_journal_access_dq(handle, lqinode, bh,
-					 OCFS2_JOURNAL_ACCESS_WRITE);
+					 OCFS2_JOURNAL_ACCESS_CREATE);
 	if (status < 0) {
 		mlog_errno(status);
 		goto out_trans;
@@ -999,7 +1005,6 @@ static struct ocfs2_quota_chunk *ocfs2_local_quota_add_chunk(
 	memset(dchunk->dqc_bitmap, 0,
 	       sb->s_blocksize - sizeof(struct ocfs2_local_disk_chunk) -
 	       OCFS2_QBLK_RESERVED_SPACE);
-	set_buffer_uptodate(bh);
 	unlock_buffer(bh);
 	status = ocfs2_journal_dirty(handle, bh);
 	if (status < 0) {
@@ -1007,6 +1012,38 @@ static struct ocfs2_quota_chunk *ocfs2_local_quota_add_chunk(
 		goto out_trans;
 	}
 
+	/* Initialize new block with structures */
+	down_read(&OCFS2_I(lqinode)->ip_alloc_sem);
+	status = ocfs2_extent_map_get_blocks(lqinode, oinfo->dqi_blocks + 1,
+					     &p_blkno, NULL, NULL);
+	up_read(&OCFS2_I(lqinode)->ip_alloc_sem);
+	if (status < 0) {
+		mlog_errno(status);
+		goto out_trans;
+	}
+	dbh = sb_getblk(sb, p_blkno);
+	if (!dbh) {
+		status = -ENOMEM;
+		mlog_errno(status);
+		goto out_trans;
+	}
+	ocfs2_set_new_buffer_uptodate(lqinode, dbh);
+	status = ocfs2_journal_access_dq(handle, lqinode, dbh,
+					 OCFS2_JOURNAL_ACCESS_CREATE);
+	if (status < 0) {
+		mlog_errno(status);
+		goto out_trans;
+	}
+	lock_buffer(dbh);
+	memset(dbh->b_data, 0, sb->s_blocksize - OCFS2_QBLK_RESERVED_SPACE);
+	unlock_buffer(dbh);
+	status = ocfs2_journal_dirty(handle, dbh);
+	if (status < 0) {
+		mlog_errno(status);
+		goto out_trans;
+	}
+
+	/* Update local quotafile info */
 	oinfo->dqi_blocks += 2;
 	oinfo->dqi_chunks++;
 	status = ocfs2_local_write_info(sb, type);
@@ -1031,6 +1068,7 @@ out_trans:
 	ocfs2_commit_trans(OCFS2_SB(sb), handle);
 out:
 	brelse(bh);
+	brelse(dbh);
 	kmem_cache_free(ocfs2_qf_chunk_cachep, chunk);
 	return ERR_PTR(status);
 }
@@ -1048,6 +1086,8 @@ static struct ocfs2_quota_chunk *ocfs2_extend_local_quota_file(
 	struct ocfs2_local_disk_chunk *dchunk;
 	int epb = ol_quota_entries_per_block(sb);
 	unsigned int chunk_blocks;
+	struct buffer_head *bh;
+	u64 p_blkno;
 	int status;
 	handle_t *handle;
 
@@ -1075,12 +1115,49 @@ static struct ocfs2_quota_chunk *ocfs2_extend_local_quota_file(
 		mlog_errno(status);
 		goto out;
 	}
-	handle = ocfs2_start_trans(OCFS2_SB(sb), 2);
+
+	/* Get buffer from the just added block */
+	down_read(&OCFS2_I(lqinode)->ip_alloc_sem);
+	status = ocfs2_extent_map_get_blocks(lqinode, oinfo->dqi_blocks,
+					     &p_blkno, NULL, NULL);
+	up_read(&OCFS2_I(lqinode)->ip_alloc_sem);
+	if (status < 0) {
+		mlog_errno(status);
+		goto out;
+	}
+	bh = sb_getblk(sb, p_blkno);
+	if (!bh) {
+		status = -ENOMEM;
+		mlog_errno(status);
+		goto out;
+	}
+	ocfs2_set_new_buffer_uptodate(lqinode, bh);
+
+	/* Local quota info, chunk header and the new block we initialize */
+	handle = ocfs2_start_trans(OCFS2_SB(sb),
+			OCFS2_LOCAL_QINFO_WRITE_CREDITS +
+			2 * OCFS2_QUOTA_BLOCK_UPDATE_CREDITS);
 	if (IS_ERR(handle)) {
 		status = PTR_ERR(handle);
 		mlog_errno(status);
 		goto out;
 	}
+	/* Zero created block */
+	status = ocfs2_journal_access_dq(handle, lqinode, bh,
+				 OCFS2_JOURNAL_ACCESS_CREATE);
+	if (status < 0) {
+		mlog_errno(status);
+		goto out_trans;
+	}
+	lock_buffer(bh);
+	memset(bh->b_data, 0, sb->s_blocksize);
+	unlock_buffer(bh);
+	status = ocfs2_journal_dirty(handle, bh);
+	if (status < 0) {
+		mlog_errno(status);
+		goto out_trans;
+	}
+	/* Update chunk header */
 	status = ocfs2_journal_access_dq(handle, lqinode, chunk->qc_headerbh,
 				 OCFS2_JOURNAL_ACCESS_WRITE);
 	if (status < 0) {
@@ -1097,6 +1174,7 @@ static struct ocfs2_quota_chunk *ocfs2_extend_local_quota_file(
 		mlog_errno(status);
 		goto out_trans;
 	}
+	/* Update file header */
 	oinfo->dqi_blocks++;
 	status = ocfs2_local_write_info(sb, type);
 	if (status < 0) {
diff --git a/fs/ocfs2/stack_o2cb.c b/fs/ocfs2/stack_o2cb.c
index 3f661376a2de..e49c41050264 100644
--- a/fs/ocfs2/stack_o2cb.c
+++ b/fs/ocfs2/stack_o2cb.c
@@ -17,6 +17,7 @@
  * General Public License for more details.
  */
 
+#include <linux/kernel.h>
 #include <linux/crc32.h>
 #include <linux/module.h>
 
@@ -153,7 +154,7 @@ static int status_map[] = {
 
 static int dlm_status_to_errno(enum dlm_status status)
 {
-	BUG_ON(status > (sizeof(status_map) / sizeof(status_map[0])));
+	BUG_ON(status < 0 || status >= ARRAY_SIZE(status_map));
 
 	return status_map[status];
 }
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 7efb349fb9bd..a3f8871d21fd 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -777,6 +777,7 @@ static int ocfs2_sb_probe(struct super_block *sb,
 		}
 		di = (struct ocfs2_dinode *) (*bh)->b_data;
 		memset(stats, 0, sizeof(struct ocfs2_blockcheck_stats));
+		spin_lock_init(&stats->b_lock);
 		status = ocfs2_verify_volume(di, *bh, blksize, stats);
 		if (status >= 0)
 			goto bail;
@@ -1182,7 +1183,7 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
 	wake_up(&osb->osb_mount_event);
 
 	/* Start this when the mount is almost sure of being successful */
-	ocfs2_orphan_scan_init(osb);
+	ocfs2_orphan_scan_start(osb);
 
 	mlog_exit(status);
 	return status;
@@ -1213,14 +1214,31 @@ static int ocfs2_get_sb(struct file_system_type *fs_type,
 			   mnt);
 }
 
+static void ocfs2_kill_sb(struct super_block *sb)
+{
+	struct ocfs2_super *osb = OCFS2_SB(sb);
+
+	/* Failed mount? */
+	if (!osb || atomic_read(&osb->vol_state) == VOLUME_DISABLED)
+		goto out;
+
+	/* Prevent further queueing of inode drop events */
+	spin_lock(&dentry_list_lock);
+	ocfs2_set_osb_flag(osb, OCFS2_OSB_DROP_DENTRY_LOCK_IMMED);
+	spin_unlock(&dentry_list_lock);
+	/* Wait for work to finish and/or remove it */
+	cancel_work_sync(&osb->dentry_lock_work);
+out:
+	kill_block_super(sb);
+}
+
 static struct file_system_type ocfs2_fs_type = {
 	.owner          = THIS_MODULE,
 	.name           = "ocfs2",
 	.get_sb         = ocfs2_get_sb, /* is this called when we mount
 					* the fs? */
-	.kill_sb        = kill_block_super, /* set to the generic one
-					     * right now, but do we
-					     * need to change that? */
+	.kill_sb        = ocfs2_kill_sb,
+
 	.fs_flags       = FS_REQUIRES_DEV|FS_RENAME_DOES_D_MOVE,
 	.next           = NULL
 };
@@ -1819,6 +1837,12 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
 
 	debugfs_remove(osb->osb_ctxt);
 
+	/*
+	 * Flush inode dropping work queue so that deletes are
+	 * performed while the filesystem is still working
+	 */
+	ocfs2_drop_all_dl_inodes(osb);
+
 	/* Orphan scan should be stopped as early as possible */
 	ocfs2_orphan_scan_stop(osb);
 
@@ -1981,6 +2005,8 @@ static int ocfs2_initialize_super(struct super_block *sb,
 	snprintf(osb->dev_str, sizeof(osb->dev_str), "%u,%u",
 		 MAJOR(osb->sb->s_dev), MINOR(osb->sb->s_dev));
 
+	ocfs2_orphan_scan_init(osb);
+
 	status = ocfs2_recovery_init(osb);
 	if (status) {
 		mlog(ML_ERROR, "Unable to initialize recovery state\n");
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index ba320e250747..d1a27cda984f 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -1052,7 +1052,8 @@ static int ocfs2_xattr_block_get(struct inode *inode,
 	struct ocfs2_xattr_block *xb;
 	struct ocfs2_xattr_value_root *xv;
 	size_t size;
-	int ret = -ENODATA, name_offset, name_len, block_off, i;
+	int ret = -ENODATA, name_offset, name_len, i;
+	int uninitialized_var(block_off);
 
 	xs->bucket = ocfs2_xattr_bucket_new(inode);
 	if (!xs->bucket) {
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 175db258942f..6f742f6658a9 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1003,12 +1003,7 @@ static ssize_t oom_adjust_read(struct file *file, char __user *buf,
 
 	if (!task)
 		return -ESRCH;
-	task_lock(task);
-	if (task->mm)
-		oom_adjust = task->mm->oom_adj;
-	else
-		oom_adjust = OOM_DISABLE;
-	task_unlock(task);
+	oom_adjust = task->oomkilladj;
 	put_task_struct(task);
 
 	len = snprintf(buffer, sizeof(buffer), "%i\n", oom_adjust);
@@ -1037,19 +1032,11 @@ static ssize_t oom_adjust_write(struct file *file, const char __user *buf,
 	task = get_proc_task(file->f_path.dentry->d_inode);
 	if (!task)
 		return -ESRCH;
-	task_lock(task);
-	if (!task->mm) {
-		task_unlock(task);
-		put_task_struct(task);
-		return -EINVAL;
-	}
-	if (oom_adjust < task->mm->oom_adj && !capable(CAP_SYS_RESOURCE)) {
-		task_unlock(task);
+	if (oom_adjust < task->oomkilladj && !capable(CAP_SYS_RESOURCE)) {
 		put_task_struct(task);
 		return -EACCES;
 	}
-	task->mm->oom_adj = oom_adjust;
-	task_unlock(task);
+	task->oomkilladj = oom_adjust;
 	put_task_struct(task);
 	if (end - buffer == 0)
 		return -EIO;
diff --git a/fs/select.c b/fs/select.c
index d870237e42c7..8084834e123e 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -110,6 +110,7 @@ void poll_initwait(struct poll_wqueues *pwq)
 {
 	init_poll_funcptr(&pwq->pt, __pollwait);
 	pwq->polling_task = current;
+	pwq->triggered = 0;
 	pwq->error = 0;
 	pwq->table = NULL;
 	pwq->inline_index = 0;
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index 0c93c7ef3d18..965df1227d64 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -770,7 +770,7 @@ xfs_buf_associate_memory(
 	bp->b_pages = NULL;
 	bp->b_addr = mem;
 
-	rval = _xfs_buf_get_pages(bp, page_count, 0);
+	rval = _xfs_buf_get_pages(bp, page_count, XBF_DONT_BLOCK);
 	if (rval)
 		return rval;
 
diff --git a/fs/xfs/linux-2.6/xfs_ioctl32.c b/fs/xfs/linux-2.6/xfs_ioctl32.c
index 0882d166239a..eafcc7c18706 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl32.c
+++ b/fs/xfs/linux-2.6/xfs_ioctl32.c
@@ -619,7 +619,7 @@ xfs_file_compat_ioctl(
 	case XFS_IOC_GETVERSION_32:
 		cmd = _NATIVE_IOC(cmd, long);
 		return xfs_file_ioctl(filp, cmd, p);
-	case XFS_IOC_SWAPEXT: {
+	case XFS_IOC_SWAPEXT_32: {
 		struct xfs_swapext	  sxp;
 		struct compat_xfs_swapext __user *sxu = arg;
 
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index b619d6b8ca43..98ef624d9baf 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -708,6 +708,16 @@ xfs_reclaim_inode(
 	return 0;
 }
 
+void
+__xfs_inode_set_reclaim_tag(
+	struct xfs_perag	*pag,
+	struct xfs_inode	*ip)
+{
+	radix_tree_tag_set(&pag->pag_ici_root,
+			   XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino),
+			   XFS_ICI_RECLAIM_TAG);
+}
+
 /*
  * We set the inode flag atomically with the radix tree tag.
  * Once we get tag lookups on the radix tree, this inode flag
@@ -722,8 +732,7 @@ xfs_inode_set_reclaim_tag(
 
 	read_lock(&pag->pag_ici_lock);
 	spin_lock(&ip->i_flags_lock);
-	radix_tree_tag_set(&pag->pag_ici_root,
-			XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_RECLAIM_TAG);
+	__xfs_inode_set_reclaim_tag(pag, ip);
 	__xfs_iflags_set(ip, XFS_IRECLAIMABLE);
 	spin_unlock(&ip->i_flags_lock);
 	read_unlock(&pag->pag_ici_lock);
diff --git a/fs/xfs/linux-2.6/xfs_sync.h b/fs/xfs/linux-2.6/xfs_sync.h
index 2a10301c99c7..59120602588a 100644
--- a/fs/xfs/linux-2.6/xfs_sync.h
+++ b/fs/xfs/linux-2.6/xfs_sync.h
@@ -48,6 +48,7 @@ int xfs_reclaim_inode(struct xfs_inode *ip, int locked, int sync_mode);
 int xfs_reclaim_inodes(struct xfs_mount *mp, int mode);
 
 void xfs_inode_set_reclaim_tag(struct xfs_inode *ip);
+void __xfs_inode_set_reclaim_tag(struct xfs_perag *pag, struct xfs_inode *ip);
 void xfs_inode_clear_reclaim_tag(struct xfs_inode *ip);
 void __xfs_inode_clear_reclaim_tag(struct xfs_mount *mp, struct xfs_perag *pag,
 				struct xfs_inode *ip);
diff --git a/fs/xfs/xfs_attr.c b/fs/xfs/xfs_attr.c
index db15feb906ff..4ece1906bd41 100644
--- a/fs/xfs/xfs_attr.c
+++ b/fs/xfs/xfs_attr.c
@@ -2010,7 +2010,9 @@ xfs_attr_rmtval_get(xfs_da_args_t *args)
 			dblkno = XFS_FSB_TO_DADDR(mp, map[i].br_startblock);
 			blkcnt = XFS_FSB_TO_BB(mp, map[i].br_blockcount);
 			error = xfs_read_buf(mp, mp->m_ddev_targp, dblkno,
-					     blkcnt, XFS_BUF_LOCK, &bp);
+					     blkcnt,
+					     XFS_BUF_LOCK | XBF_DONT_BLOCK,
+					     &bp);
 			if (error)
 				return(error);
 
@@ -2141,8 +2143,8 @@ xfs_attr_rmtval_set(xfs_da_args_t *args)
 		dblkno = XFS_FSB_TO_DADDR(mp, map.br_startblock),
 		blkcnt = XFS_FSB_TO_BB(mp, map.br_blockcount);
 
-		bp = xfs_buf_get_flags(mp->m_ddev_targp, dblkno,
-							blkcnt, XFS_BUF_LOCK);
+		bp = xfs_buf_get_flags(mp->m_ddev_targp, dblkno, blkcnt,
+				       XFS_BUF_LOCK | XBF_DONT_BLOCK);
 		ASSERT(bp);
 		ASSERT(!XFS_BUF_GETERROR(bp));
 
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index 7928b9983c1d..8ee5b5a76a2a 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -6009,7 +6009,7 @@ xfs_getbmap(
 	 */
 	error = ENOMEM;
 	subnex = 16;
-	map = kmem_alloc(subnex * sizeof(*map), KM_MAYFAIL);
+	map = kmem_alloc(subnex * sizeof(*map), KM_MAYFAIL | KM_NOFS);
 	if (!map)
 		goto out_unlock_ilock;
 
diff --git a/fs/xfs/xfs_btree.c b/fs/xfs/xfs_btree.c
index e9df99574829..26717388acf5 100644
--- a/fs/xfs/xfs_btree.c
+++ b/fs/xfs/xfs_btree.c
@@ -120,8 +120,8 @@ xfs_btree_check_sblock(
 			XFS_RANDOM_BTREE_CHECK_SBLOCK))) {
 		if (bp)
 			xfs_buftrace("SBTREE ERROR", bp);
-		XFS_ERROR_REPORT("xfs_btree_check_sblock", XFS_ERRLEVEL_LOW,
-				 cur->bc_mp);
+		XFS_CORRUPTION_ERROR("xfs_btree_check_sblock",
+			XFS_ERRLEVEL_LOW, cur->bc_mp, block);
 		return XFS_ERROR(EFSCORRUPTED);
 	}
 	return 0;
diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c
index 9ff6e57a5075..2847bbc1c534 100644
--- a/fs/xfs/xfs_da_btree.c
+++ b/fs/xfs/xfs_da_btree.c
@@ -2201,7 +2201,7 @@ kmem_zone_t *xfs_dabuf_zone;		/* dabuf zone */
 xfs_da_state_t *
 xfs_da_state_alloc(void)
 {
-	return kmem_zone_zalloc(xfs_da_state_zone, KM_SLEEP);
+	return kmem_zone_zalloc(xfs_da_state_zone, KM_NOFS);
 }
 
 /*
@@ -2261,9 +2261,9 @@ xfs_da_buf_make(int nbuf, xfs_buf_t **bps, inst_t *ra)
 	int		off;
 
 	if (nbuf == 1)
-		dabuf = kmem_zone_alloc(xfs_dabuf_zone, KM_SLEEP);
+		dabuf = kmem_zone_alloc(xfs_dabuf_zone, KM_NOFS);
 	else
-		dabuf = kmem_alloc(XFS_DA_BUF_SIZE(nbuf), KM_SLEEP);
+		dabuf = kmem_alloc(XFS_DA_BUF_SIZE(nbuf), KM_NOFS);
 	dabuf->dirty = 0;
 #ifdef XFS_DABUF_DEBUG
 	dabuf->ra = ra;
diff --git a/fs/xfs/xfs_dir2.c b/fs/xfs/xfs_dir2.c
index c657bec6d951..bb1d58eb3982 100644
--- a/fs/xfs/xfs_dir2.c
+++ b/fs/xfs/xfs_dir2.c
@@ -256,7 +256,7 @@ xfs_dir_cilookup_result(
 					!(args->op_flags & XFS_DA_OP_CILOOKUP))
 		return EEXIST;
 
-	args->value = kmem_alloc(len, KM_MAYFAIL);
+	args->value = kmem_alloc(len, KM_NOFS | KM_MAYFAIL);
 	if (!args->value)
 		return ENOMEM;
 
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index cbd451bb4848..2d0b3e1da9e6 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -167,17 +167,25 @@ xfs_growfs_data_private(
 	new = nb - mp->m_sb.sb_dblocks;
 	oagcount = mp->m_sb.sb_agcount;
 	if (nagcount > oagcount) {
+		void *new_perag, *old_perag;
+
 		xfs_filestream_flush(mp);
+
+		new_perag = kmem_zalloc(sizeof(xfs_perag_t) * nagcount,
+					KM_MAYFAIL);
+		if (!new_perag)
+			return XFS_ERROR(ENOMEM);
+
 		down_write(&mp->m_peraglock);
-		mp->m_perag = kmem_realloc(mp->m_perag,
-			sizeof(xfs_perag_t) * nagcount,
-			sizeof(xfs_perag_t) * oagcount,
-			KM_SLEEP);
-		memset(&mp->m_perag[oagcount], 0,
-			(nagcount - oagcount) * sizeof(xfs_perag_t));
+		memcpy(new_perag, mp->m_perag, sizeof(xfs_perag_t) * oagcount);
+		old_perag = mp->m_perag;
+		mp->m_perag = new_perag;
+
 		mp->m_flags |= XFS_MOUNT_32BITINODES;
 		nagimax = xfs_initialize_perag(mp, nagcount);
 		up_write(&mp->m_peraglock);
+
+		kmem_free(old_perag);
 	}
 	tp = xfs_trans_alloc(mp, XFS_TRANS_GROWFS);
 	tp->t_flags |= XFS_TRANS_RESERVE;
diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c
index 34ec86923f7e..ecbf8b4d2e2e 100644
--- a/fs/xfs/xfs_iget.c
+++ b/fs/xfs/xfs_iget.c
@@ -191,80 +191,82 @@ xfs_iget_cache_hit(
 	int			flags,
 	int			lock_flags) __releases(pag->pag_ici_lock)
 {
+	struct inode		*inode = VFS_I(ip);
 	struct xfs_mount	*mp = ip->i_mount;
-	int			error = EAGAIN;
+	int			error;
+
+	spin_lock(&ip->i_flags_lock);
 
 	/*
-	 * If INEW is set this inode is being set up
-	 * If IRECLAIM is set this inode is being torn down
-	 * Pause and try again.
+	 * If we are racing with another cache hit that is currently
+	 * instantiating this inode or currently recycling it out of
+	 * reclaimabe state, wait for the initialisation to complete
+	 * before continuing.
+	 *
+	 * XXX(hch): eventually we should do something equivalent to
+	 *	     wait_on_inode to wait for these flags to be cleared
+	 *	     instead of polling for it.
 	 */
-	if (xfs_iflags_test(ip, (XFS_INEW|XFS_IRECLAIM))) {
+	if (ip->i_flags & (XFS_INEW|XFS_IRECLAIM)) {
 		XFS_STATS_INC(xs_ig_frecycle);
+		error = EAGAIN;
 		goto out_error;
 	}
 
-	/* If IRECLAIMABLE is set, we've torn down the vfs inode part */
-	if (xfs_iflags_test(ip, XFS_IRECLAIMABLE)) {
-
-		/*
-		 * If lookup is racing with unlink, then we should return an
-		 * error immediately so we don't remove it from the reclaim
-		 * list and potentially leak the inode.
-		 */
-		if ((ip->i_d.di_mode == 0) && !(flags & XFS_IGET_CREATE)) {
-			error = ENOENT;
-			goto out_error;
-		}
+	/*
+	 * If lookup is racing with unlink return an error immediately.
+	 */
+	if (ip->i_d.di_mode == 0 && !(flags & XFS_IGET_CREATE)) {
+		error = ENOENT;
+		goto out_error;
+	}
 
+	/*
+	 * If IRECLAIMABLE is set, we've torn down the VFS inode already.
+	 * Need to carefully get it back into useable state.
+	 */
+	if (ip->i_flags & XFS_IRECLAIMABLE) {
 		xfs_itrace_exit_tag(ip, "xfs_iget.alloc");
 
 		/*
-		 * We need to re-initialise the VFS inode as it has been
-		 * 'freed' by the VFS. Do this here so we can deal with
-		 * errors cleanly, then tag it so it can be set up correctly
-		 * later.
+		 * We need to set XFS_INEW atomically with clearing the
+		 * reclaimable tag so that we do have an indicator of the
+		 * inode still being initialized.
 		 */
-		if (inode_init_always(mp->m_super, VFS_I(ip))) {
-			error = ENOMEM;
-			goto out_error;
-		}
+		ip->i_flags |= XFS_INEW;
+		ip->i_flags &= ~XFS_IRECLAIMABLE;
+		__xfs_inode_clear_reclaim_tag(mp, pag, ip);
 
-		/*
-		 * We must set the XFS_INEW flag before clearing the
-		 * XFS_IRECLAIMABLE flag so that if a racing lookup does
-		 * not find the XFS_IRECLAIMABLE above but has the igrab()
-		 * below succeed we can safely check XFS_INEW to detect
-		 * that this inode is still being initialised.
-		 */
-		xfs_iflags_set(ip, XFS_INEW);
-		xfs_iflags_clear(ip, XFS_IRECLAIMABLE);
+		spin_unlock(&ip->i_flags_lock);
+		read_unlock(&pag->pag_ici_lock);
 
-		/* clear the radix tree reclaim flag as well. */
-		__xfs_inode_clear_reclaim_tag(mp, pag, ip);
-	} else if (!igrab(VFS_I(ip))) {
+		error = -inode_init_always(mp->m_super, inode);
+		if (error) {
+			/*
+			 * Re-initializing the inode failed, and we are in deep
+			 * trouble.  Try to re-add it to the reclaim list.
+			 */
+			read_lock(&pag->pag_ici_lock);
+			spin_lock(&ip->i_flags_lock);
+
+			ip->i_flags &= ~XFS_INEW;
+			ip->i_flags |= XFS_IRECLAIMABLE;
+			__xfs_inode_set_reclaim_tag(pag, ip);
+			goto out_error;
+		}
+		inode->i_state = I_LOCK|I_NEW;
+	} else {
 		/* If the VFS inode is being torn down, pause and try again. */
-		XFS_STATS_INC(xs_ig_frecycle);
-		goto out_error;
-	} else if (xfs_iflags_test(ip, XFS_INEW)) {
-		/*
-		 * We are racing with another cache hit that is
-		 * currently recycling this inode out of the XFS_IRECLAIMABLE
-		 * state. Wait for the initialisation to complete before
-		 * continuing.
-		 */
-		wait_on_inode(VFS_I(ip));
-	}
+		if (!igrab(inode)) {
+			error = EAGAIN;
+			goto out_error;
+		}
 
-	if (ip->i_d.di_mode == 0 && !(flags & XFS_IGET_CREATE)) {
-		error = ENOENT;
-		iput(VFS_I(ip));
-		goto out_error;
+		/* We've got a live one. */
+		spin_unlock(&ip->i_flags_lock);
+		read_unlock(&pag->pag_ici_lock);
 	}
 
-	/* We've got a live one. */
-	read_unlock(&pag->pag_ici_lock);
-
 	if (lock_flags != 0)
 		xfs_ilock(ip, lock_flags);
 
@@ -274,6 +276,7 @@ xfs_iget_cache_hit(
 	return 0;
 
 out_error:
+	spin_unlock(&ip->i_flags_lock);
 	read_unlock(&pag->pag_ici_lock);
 	return error;
 }
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 1f22d65fed0a..da428b3fe0f5 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -343,6 +343,16 @@ xfs_iformat(
 		return XFS_ERROR(EFSCORRUPTED);
 	}
 
+	if (unlikely((ip->i_d.di_flags & XFS_DIFLAG_REALTIME) &&
+		     !ip->i_mount->m_rtdev_targp)) {
+		xfs_fs_repair_cmn_err(CE_WARN, ip->i_mount,
+			"corrupt dinode %Lu, has realtime flag set.",
+			ip->i_ino);
+		XFS_CORRUPTION_ERROR("xfs_iformat(realtime)",
+				     XFS_ERRLEVEL_LOW, ip->i_mount, dip);
+		return XFS_ERROR(EFSCORRUPTED);
+	}
+
 	switch (ip->i_d.di_mode & S_IFMT) {
 	case S_IFIFO:
 	case S_IFCHR:
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 3750f04ede0b..9dbdff3ea484 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -3180,7 +3180,7 @@ try_again:
 STATIC void
 xlog_state_want_sync(xlog_t *log, xlog_in_core_t *iclog)
 {
-	ASSERT(spin_is_locked(&log->l_icloglock));
+	assert_spin_locked(&log->l_icloglock);
 
 	if (iclog->ic_state == XLOG_STATE_ACTIVE) {
 		xlog_state_switch_iclogs(log, iclog, 0);
diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index c4eca5ed5dab..492d75bae2bf 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -538,7 +538,9 @@ xfs_readlink_bmap(
 		d = XFS_FSB_TO_DADDR(mp, mval[n].br_startblock);
 		byte_cnt = XFS_FSB_TO_B(mp, mval[n].br_blockcount);
 
-		bp = xfs_buf_read(mp->m_ddev_targp, d, BTOBB(byte_cnt), 0);
+		bp = xfs_buf_read_flags(mp->m_ddev_targp, d, BTOBB(byte_cnt),
+					XBF_LOCK | XBF_MAPPED |
+					XBF_DONT_BLOCK);
 		error = XFS_BUF_GETERROR(bp);
 		if (error) {
 			xfs_ioerror_alert("xfs_readlink",