Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6:
  merge fchmod() and fchmodat() guts, kill ancient broken kludge
  xfs: fix misspelled S_IS...()
  xfs: get rid of open-coded S_ISREG(), etc.
  vfs: document locking requirements for d_move, __d_move and d_materialise_unique
  omfs: fix (mode & S_IFDIR) abuse
  btrfs: S_ISREG(mode) is not mode & S_IFREG...
  ima: fmode_t misspelled as mode_t...
  pci-label.c: size_t misspelled as mode_t
  jffs2: S_ISLNK(mode & S_IFMT) is pointless
  snd_msnd ->mode is fmode_t, not mode_t
  v9fs_iop_get_acl: get rid of unused variable
  vfs: dont chain pipe/anon/socket on superblock s_inodes list
  Documentation: Exporting: update description of d_splice_alias
  fs: add missing unlock in default_llseek()

Author: torvalds

Documentation/filesystems/nfs/Exporting

@@ -92,7 +92,14 @@ For a filesystem to be exportable it must:
    1/ provide the filehandle fragment routines described below.
    2/ make sure that d_splice_alias is used rather than d_add
       when ->lookup finds an inode for a given parent and name.
-      Typically the ->lookup routine will end with a:
+
+      If inode is NULL, d_splice_alias(inode, dentry) is eqivalent to
+
+		d_add(dentry, inode), NULL
+
+      Similarly, d_splice_alias(ERR_PTR(err), dentry) = ERR_PTR(err)
+
+      Typically the ->lookup routine will simply end with a:
 
 		return d_splice_alias(inode, dentry);
 	}

drivers/pci/pci-label.c

@@ -55,7 +55,7 @@ enum smbios_attr_enum {
 	SMBIOS_ATTR_INSTANCE_SHOW,
 };
 
-static mode_t
+static size_t
 find_smbios_instance_string(struct pci_dev *pdev, char *buf,
 			    enum smbios_attr_enum attribute)
 {

fs/anon_inodes.c

@@ -187,7 +187,7 @@ EXPORT_SYMBOL_GPL(anon_inode_getfd);
  */
 static struct inode *anon_inode_mkinode(void)
 {
-	struct inode *inode = new_inode(anon_inode_mnt->mnt_sb);
+	struct inode *inode = new_inode_pseudo(anon_inode_mnt->mnt_sb);
 
 	if (!inode)
 		return ERR_PTR(-ENOMEM);

fs/btrfs/inode.c

@@ -4467,7 +4467,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 	inode->i_generation = BTRFS_I(inode)->generation;
 	btrfs_set_inode_space_info(root, inode);
 
-	if (mode & S_IFDIR)
+	if (S_ISDIR(mode))
 		owner = 0;
 	else
 		owner = 1;
@@ -4512,7 +4512,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 
 	btrfs_inherit_iflags(inode, dir);
 
-	if ((mode & S_IFREG)) {
+	if (S_ISREG(mode)) {
 		if (btrfs_test_opt(root, NODATASUM))
 			BTRFS_I(inode)->flags |= BTRFS_INODE_NODATASUM;
 		if (btrfs_test_opt(root, NODATACOW) ||

fs/dcache.c

@@ -2138,8 +2138,9 @@ static void dentry_unlock_parents_for_move(struct dentry *dentry,
  * @target: new dentry
  *
  * Update the dcache to reflect the move of a file name. Negative
- * dcache entries should not be moved in this way.  Caller hold
- * rename_lock.
+ * dcache entries should not be moved in this way. Caller must hold
+ * rename_lock, the i_mutex of the source and target directories,
+ * and the sb->s_vfs_rename_mutex if they differ. See lock_rename().
  */
 static void __d_move(struct dentry * dentry, struct dentry * target)
 {
@@ -2202,7 +2203,8 @@ static void __d_move(struct dentry * dentry, struct dentry * target)
  * @target: new dentry
  *
  * Update the dcache to reflect the move of a file name. Negative
- * dcache entries should not be moved in this way.
+ * dcache entries should not be moved in this way. See the locking
+ * requirements for __d_move.
  */
 void d_move(struct dentry *dentry, struct dentry *target)
 {
@@ -2320,7 +2322,8 @@ static void __d_materialise_dentry(struct dentry *dentry, struct dentry *anon)
  * @inode: inode to bind to the dentry, to which aliases may be attached
  *
  * Introduces an dentry into the tree, substituting an extant disconnected
- * root directory alias in its place if there is one
+ * root directory alias in its place if there is one. Caller must hold the
+ * i_mutex of the parent directory.
  */
 struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode)
 {

fs/inode.c

@@ -361,9 +361,11 @@ EXPORT_SYMBOL_GPL(inode_sb_list_add);
 
 static inline void inode_sb_list_del(struct inode *inode)
 {
-	spin_lock(&inode_sb_list_lock);
-	list_del_init(&inode->i_sb_list);
-	spin_unlock(&inode_sb_list_lock);
+	if (!list_empty(&inode->i_sb_list)) {
+		spin_lock(&inode_sb_list_lock);
+		list_del_init(&inode->i_sb_list);
+		spin_unlock(&inode_sb_list_lock);
+	}
 }
 
 static unsigned long hash(struct super_block *sb, unsigned long hashval)
@@ -795,6 +797,29 @@ unsigned int get_next_ino(void)
 }
 EXPORT_SYMBOL(get_next_ino);
 
+/**
+ *	new_inode_pseudo 	- obtain an inode
+ *	@sb: superblock
+ *
+ *	Allocates a new inode for given superblock.
+ *	Inode wont be chained in superblock s_inodes list
+ *	This means :
+ *	- fs can't be unmount
+ *	- quotas, fsnotify, writeback can't work
+ */
+struct inode *new_inode_pseudo(struct super_block *sb)
+{
+	struct inode *inode = alloc_inode(sb);
+
+	if (inode) {
+		spin_lock(&inode->i_lock);
+		inode->i_state = 0;
+		spin_unlock(&inode->i_lock);
+		INIT_LIST_HEAD(&inode->i_sb_list);
+	}
+	return inode;
+}
+
 /**
  *	new_inode 	- obtain an inode
  *	@sb: superblock
@@ -813,13 +838,9 @@ struct inode *new_inode(struct super_block *sb)
 
 	spin_lock_prefetch(&inode_sb_list_lock);
 
-	inode = alloc_inode(sb);
-	if (inode) {
-		spin_lock(&inode->i_lock);
-		inode->i_state = 0;
-		spin_unlock(&inode->i_lock);
+	inode = new_inode_pseudo(sb);
+	if (inode)
 		inode_sb_list_add(inode);
-	}
 	return inode;
 }
 EXPORT_SYMBOL(new_inode);

fs/jffs2/fs.c

@@ -80,7 +80,7 @@ int jffs2_do_setattr (struct inode *inode, struct iattr *iattr)
 				  ALLOC_NORMAL, JFFS2_SUMMARY_INODE_SIZE);
 	if (ret) {
 		jffs2_free_raw_inode(ri);
-		if (S_ISLNK(inode->i_mode & S_IFMT))
+		if (S_ISLNK(inode->i_mode))
 			 kfree(mdata);
 		return ret;
 	}

fs/omfs/dir.c

@@ -93,7 +93,7 @@ int omfs_make_empty(struct inode *inode, struct super_block *sb)
 
 	memset(bh->b_data, 0, sizeof(struct omfs_inode));
 
-	if (inode->i_mode & S_IFDIR) {
+	if (S_ISDIR(inode->i_mode)) {
 		memset(&bh->b_data[OMFS_DIR_START], 0xff,
 			sbi->s_sys_blocksize - OMFS_DIR_START);
 	} else

fs/open.c

@@ -446,74 +446,52 @@ SYSCALL_DEFINE1(chroot, const char __user *, filename)
 	return error;
 }
 
-SYSCALL_DEFINE2(fchmod, unsigned int, fd, mode_t, mode)
+static int chmod_common(struct path *path, umode_t mode)
 {
-	struct inode * inode;
-	struct dentry * dentry;
-	struct file * file;
-	int err = -EBADF;
+	struct inode *inode = path->dentry->d_inode;
 	struct iattr newattrs;
+	int error;
 
-	file = fget(fd);
-	if (!file)
-		goto out;
-
-	dentry = file->f_path.dentry;
-	inode = dentry->d_inode;
-
-	audit_inode(NULL, dentry);
-
-	err = mnt_want_write_file(file);
-	if (err)
-		goto out_putf;
+	error = mnt_want_write(path->mnt);
+	if (error)
+		return error;
 	mutex_lock(&inode->i_mutex);
-	err = security_path_chmod(dentry, file->f_vfsmnt, mode);
-	if (err)
+	error = security_path_chmod(path->dentry, path->mnt, mode);
+	if (error)
 		goto out_unlock;
-	if (mode == (mode_t) -1)
-		mode = inode->i_mode;
 	newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO);
 	newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
-	err = notify_change(dentry, &newattrs);
+	error = notify_change(path->dentry, &newattrs);
 out_unlock:
 	mutex_unlock(&inode->i_mutex);
-	mnt_drop_write(file->f_path.mnt);
-out_putf:
-	fput(file);
-out:
+	mnt_drop_write(path->mnt);
+	return error;
+}
+
+SYSCALL_DEFINE2(fchmod, unsigned int, fd, mode_t, mode)
+{
+	struct file * file;
+	int err = -EBADF;
+
+	file = fget(fd);
+	if (file) {
+		audit_inode(NULL, file->f_path.dentry);
+		err = chmod_common(&file->f_path, mode);
+		fput(file);
+	}
 	return err;
 }
 
 SYSCALL_DEFINE3(fchmodat, int, dfd, const char __user *, filename, mode_t, mode)
 {
 	struct path path;
-	struct inode *inode;
 	int error;
-	struct iattr newattrs;
 
 	error = user_path_at(dfd, filename, LOOKUP_FOLLOW, &path);
-	if (error)
-		goto out;
-	inode = path.dentry->d_inode;
-
-	error = mnt_want_write(path.mnt);
-	if (error)
-		goto dput_and_out;
-	mutex_lock(&inode->i_mutex);
-	error = security_path_chmod(path.dentry, path.mnt, mode);
-	if (error)
-		goto out_unlock;
-	if (mode == (mode_t) -1)
-		mode = inode->i_mode;
-	newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO);
-	newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
-	error = notify_change(path.dentry, &newattrs);
-out_unlock:
-	mutex_unlock(&inode->i_mutex);
-	mnt_drop_write(path.mnt);
-dput_and_out:
-	path_put(&path);
-out:
+	if (!error) {
+		error = chmod_common(&path, mode);
+		path_put(&path);
+	}
 	return error;
 }
 

fs/pipe.c

@@ -948,7 +948,7 @@ static const struct dentry_operations pipefs_dentry_operations = {
 
 static struct inode * get_pipe_inode(void)
 {
-	struct inode *inode = new_inode(pipe_mnt->mnt_sb);
+	struct inode *inode = new_inode_pseudo(pipe_mnt->mnt_sb);
 	struct pipe_inode_info *pipe;
 
 	if (!inode)

fs/read_write.c

@@ -166,17 +166,21 @@ loff_t default_llseek(struct file *file, loff_t offset, int origin)
 			 * long as offset isn't at the end of the file then the
 			 * offset is data.
 			 */
-			if (offset >= inode->i_size)
-				return -ENXIO;
+			if (offset >= inode->i_size) {
+				retval = -ENXIO;
+				goto out;
+			}
 			break;
 		case SEEK_HOLE:
 			/*
 			 * There is a virtual hole at the end of the file, so
 			 * as long as offset isn't i_size or larger, return
 			 * i_size.
 			 */
-			if (offset >= inode->i_size)
-				return -ENXIO;
+			if (offset >= inode->i_size) {
+				retval = -ENXIO;
+				goto out;
+			}
 			offset = inode->i_size;
 			break;
 	}

fs/xfs/linux-2.6/xfs_ioctl.c

@@ -265,7 +265,7 @@ xfs_open_by_handle(
 		return PTR_ERR(filp);
 	}
 
-	if (inode->i_mode & S_IFREG) {
+	if (S_ISREG(inode->i_mode)) {
 		filp->f_flags |= O_NOATIME;
 		filp->f_mode |= FMODE_NOCMTIME;
 	}
@@ -850,14 +850,14 @@ xfs_set_diflags(
 		di_flags |= XFS_DIFLAG_NODEFRAG;
 	if (xflags & XFS_XFLAG_FILESTREAM)
 		di_flags |= XFS_DIFLAG_FILESTREAM;
-	if ((ip->i_d.di_mode & S_IFMT) == S_IFDIR) {
+	if (S_ISDIR(ip->i_d.di_mode)) {
 		if (xflags & XFS_XFLAG_RTINHERIT)
 			di_flags |= XFS_DIFLAG_RTINHERIT;
 		if (xflags & XFS_XFLAG_NOSYMLINKS)
 			di_flags |= XFS_DIFLAG_NOSYMLINKS;
 		if (xflags & XFS_XFLAG_EXTSZINHERIT)
 			di_flags |= XFS_DIFLAG_EXTSZINHERIT;
-	} else if ((ip->i_d.di_mode & S_IFMT) == S_IFREG) {
+	} else if (S_ISREG(ip->i_d.di_mode)) {
 		if (xflags & XFS_XFLAG_REALTIME)
 			di_flags |= XFS_DIFLAG_REALTIME;
 		if (xflags & XFS_XFLAG_EXTSIZE)

fs/xfs/xfs_bmap.c

@@ -414,7 +414,7 @@ xfs_bmap_add_attrfork_local(
 
 	if (ip->i_df.if_bytes <= XFS_IFORK_DSIZE(ip))
 		return 0;
-	if ((ip->i_d.di_mode & S_IFMT) == S_IFDIR) {
+	if (S_ISDIR(ip->i_d.di_mode)) {
 		mp = ip->i_mount;
 		memset(&dargs, 0, sizeof(dargs));
 		dargs.dp = ip;
@@ -3344,8 +3344,7 @@ xfs_bmap_local_to_extents(
 	 * We don't want to deal with the case of keeping inode data inline yet.
 	 * So sending the data fork of a regular inode is invalid.
 	 */
-	ASSERT(!((ip->i_d.di_mode & S_IFMT) == S_IFREG &&
-		 whichfork == XFS_DATA_FORK));
+	ASSERT(!(S_ISREG(ip->i_d.di_mode) && whichfork == XFS_DATA_FORK));
 	ifp = XFS_IFORK_PTR(ip, whichfork);
 	ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL);
 	flags = 0;
@@ -4052,7 +4051,7 @@ xfs_bmap_one_block(
 
 #ifndef DEBUG
 	if (whichfork == XFS_DATA_FORK) {
-		return ((ip->i_d.di_mode & S_IFMT) == S_IFREG) ?
+		return S_ISREG(ip->i_d.di_mode) ?
 			(ip->i_size == ip->i_mount->m_sb.sb_blocksize) :
 			(ip->i_d.di_size == ip->i_mount->m_sb.sb_blocksize);
 	}