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: (69 commits)
  fix handling of offsets in cris eeprom.c, get rid of fake on-stack files
  get rid of home-grown mutex in cris eeprom.c
  switch ecryptfs_write() to struct inode *, kill on-stack fake files
  switch ecryptfs_get_locked_page() to struct inode *
  simplify access to ecryptfs inodes in ->readpage() and friends
  AFS: Don't put struct file on the stack
  Ban ecryptfs over ecryptfs
  logfs: replace inode uid,gid,mode initialization with helper function
  ufs: replace inode uid,gid,mode initialization with helper function
  udf: replace inode uid,gid,mode init with helper
  ubifs: replace inode uid,gid,mode initialization with helper function
  sysv: replace inode uid,gid,mode initialization with helper function
  reiserfs: replace inode uid,gid,mode initialization with helper function
  ramfs: replace inode uid,gid,mode initialization with helper function
  omfs: replace inode uid,gid,mode initialization with helper function
  bfs: replace inode uid,gid,mode initialization with helper function
  ocfs2: replace inode uid,gid,mode initialization with helper function
  nilfs2: replace inode uid,gid,mode initialization with helper function
  minix: replace inode uid,gid,mode init with helper
  ext4: replace inode uid,gid,mode init with helper
  ...

Trivial conflict in fs/fs-writeback.c (mark bitfields unsigned)

fs/9p/vfs_inode.c

@@ -253,9 +253,7 @@ struct inode *v9fs_get_inode(struct super_block *sb, int mode)
 		return ERR_PTR(-ENOMEM);
 	}
 
-	inode->i_mode = mode;
-	inode->i_uid = current_fsuid();
-	inode->i_gid = current_fsgid();
+	inode_init_owner(inode, NULL, mode);
 	inode->i_blocks = 0;
 	inode->i_rdev = 0;
 	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;

fs/Makefile

@@ -11,7 +11,7 @@ obj-y :=	open.o read_write.o file_table.o super.o \
 		attr.o bad_inode.o file.o filesystems.o namespace.o \
 		seq_file.o xattr.o libfs.o fs-writeback.o \
 		pnode.o drop_caches.o splice.o sync.o utimes.o \
-		stack.o fs_struct.o
+		stack.o fs_struct.o statfs.o
 
 ifeq ($(CONFIG_BLOCK),y)
 obj-y +=	buffer.o bio.o block_dev.o direct-io.o mpage.o ioprio.o

fs/afs/dir.c

@@ -189,13 +189,9 @@ static struct page *afs_dir_get_page(struct inode *dir, unsigned long index,
 				     struct key *key)
 {
 	struct page *page;
-	struct file file = {
-		.private_data = key,
-	};
-
 	_enter("{%lu},%lu", dir->i_ino, index);
 
-	page = read_mapping_page(dir->i_mapping, index, &file);
+	page = read_cache_page(dir->i_mapping, index, afs_page_filler, key);
 	if (!IS_ERR(page)) {
 		kmap(page);
 		if (!PageChecked(page))

fs/afs/file.c

@@ -121,34 +121,19 @@ static void afs_file_readpage_read_complete(struct page *page,
 #endif
 
 /*
- * AFS read page from file, directory or symlink
+ * read page from file, directory or symlink, given a key to use
  */
-static int afs_readpage(struct file *file, struct page *page)
+int afs_page_filler(void *data, struct page *page)
 {
-	struct afs_vnode *vnode;
-	struct inode *inode;
-	struct key *key;
+	struct inode *inode = page->mapping->host;
+	struct afs_vnode *vnode = AFS_FS_I(inode);
+	struct key *key = data;
 	size_t len;
 	off_t offset;
 	int ret;
 
-	inode = page->mapping->host;
-
-	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);
 
-	vnode = AFS_FS_I(inode);
-
 	BUG_ON(!PageLocked(page));
 
 	ret = -ESTALE;
@@ -214,31 +199,56 @@ 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;
 }
 
+/*
+ * read page from file, directory or symlink, given a file to nominate the key
+ * to be used
+ */
+static int afs_readpage(struct file *file, struct page *page)
+{
+	struct key *key;
+	int ret;
+
+	if (file) {
+		key = file->private_data;
+		ASSERT(key != NULL);
+		ret = afs_page_filler(key, page);
+	} else {
+		struct inode *inode = page->mapping->host;
+		key = afs_request_key(AFS_FS_S(inode->i_sb)->volume->cell);
+		if (IS_ERR(key)) {
+			ret = PTR_ERR(key);
+		} else {
+			ret = afs_page_filler(key, page);
+			key_put(key);
+		}
+	}
+	return ret;
+}
+
 /*
  * read a set of pages
  */
 static int afs_readpages(struct file *file, struct address_space *mapping,
 			 struct list_head *pages, unsigned nr_pages)
 {
+	struct key *key = file->private_data;
 	struct afs_vnode *vnode;
 	int ret = 0;
 
-	_enter(",{%lu},,%d", mapping->host->i_ino, nr_pages);
+	_enter("{%d},{%lu},,%d",
+	       key_serial(key), mapping->host->i_ino, nr_pages);
+
+	ASSERT(key != NULL);
 
 	vnode = AFS_FS_I(mapping->host);
 	if (vnode->flags & AFS_VNODE_DELETED) {
@@ -279,7 +289,7 @@ static int afs_readpages(struct file *file, struct address_space *mapping,
 	}
 
 	/* load the missing pages from the network */
-	ret = read_cache_pages(mapping, pages, (void *) afs_readpage, file);
+	ret = read_cache_pages(mapping, pages, afs_page_filler, key);
 
 	_leave(" = %d [netting]", ret);
 	return ret;

fs/afs/internal.h

@@ -494,6 +494,7 @@ extern const struct file_operations afs_file_operations;
 
 extern int afs_open(struct inode *, struct file *);
 extern int afs_release(struct inode *, struct file *);
+extern int afs_page_filler(void *, struct page *);
 
 /*
  * flock.c

fs/afs/mntpt.c

@@ -49,9 +49,6 @@ static unsigned long afs_mntpt_expiry_timeout = 10 * 60;
  */
 int afs_mntpt_check_symlink(struct afs_vnode *vnode, struct key *key)
 {
-	struct file file = {
-		.private_data = key,
-	};
 	struct page *page;
 	size_t size;
 	char *buf;
@@ -61,7 +58,8 @@ int afs_mntpt_check_symlink(struct afs_vnode *vnode, struct key *key)
 	       vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique);
 
 	/* read the contents of the symlink into the pagecache */
-	page = read_mapping_page(AFS_VNODE_TO_I(vnode)->i_mapping, 0, &file);
+	page = read_cache_page(AFS_VNODE_TO_I(vnode)->i_mapping, 0,
+			       afs_page_filler, key);
 	if (IS_ERR(page)) {
 		ret = PTR_ERR(page);
 		goto out;

fs/anon_inodes.c

@@ -205,7 +205,7 @@ static struct inode *anon_inode_mkinode(void)
 	 * that it already _is_ on the dirty list.
 	 */
 	inode->i_state = I_DIRTY;
-	inode->i_mode = S_IRUSR | S_IWUSR;
+	inode->i_mode = S_IFREG | S_IRUSR | S_IWUSR;
 	inode->i_uid = current_fsuid();
 	inode->i_gid = current_fsgid();
 	inode->i_flags |= S_PRIVATE;

fs/bfs/dir.c

@@ -105,14 +105,12 @@ static int bfs_create(struct inode *dir, struct dentry *dentry, int mode,
 	}
 	set_bit(ino, info->si_imap);
 	info->si_freei--;
-	inode->i_uid = current_fsuid();
-	inode->i_gid = (dir->i_mode & S_ISGID) ? dir->i_gid : current_fsgid();
+	inode_init_owner(inode, dir, mode);
 	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC;
 	inode->i_blocks = 0;
 	inode->i_op = &bfs_file_inops;
 	inode->i_fop = &bfs_file_operations;
 	inode->i_mapping->a_ops = &bfs_aops;
-	inode->i_mode = mode;
 	inode->i_ino = ino;
 	BFS_I(inode)->i_dsk_ino = ino;
 	BFS_I(inode)->i_sblock = 0;

fs/block_dev.c

@@ -245,37 +245,14 @@ struct super_block *freeze_bdev(struct block_device *bdev)
 	sb = get_active_super(bdev);
 	if (!sb)
 		goto out;
-	if (sb->s_flags & MS_RDONLY) {
-		sb->s_frozen = SB_FREEZE_TRANS;
-		up_write(&sb->s_umount);
+	error = freeze_super(sb);
+	if (error) {
+		deactivate_super(sb);
+		bdev->bd_fsfreeze_count--;
 		mutex_unlock(&bdev->bd_fsfreeze_mutex);
-		return sb;
+		return ERR_PTR(error);
 	}
-
-	sb->s_frozen = SB_FREEZE_WRITE;
-	smp_wmb();
-
-	sync_filesystem(sb);
-
-	sb->s_frozen = SB_FREEZE_TRANS;
-	smp_wmb();
-
-	sync_blockdev(sb->s_bdev);
-
-	if (sb->s_op->freeze_fs) {
-		error = sb->s_op->freeze_fs(sb);
-		if (error) {
-			printk(KERN_ERR
-				"VFS:Filesystem freeze failed\n");
-			sb->s_frozen = SB_UNFROZEN;
-			deactivate_locked_super(sb);
-			bdev->bd_fsfreeze_count--;
-			mutex_unlock(&bdev->bd_fsfreeze_mutex);
-			return ERR_PTR(error);
-		}
-	}
-	up_write(&sb->s_umount);
-
+	deactivate_super(sb);
  out:
 	sync_blockdev(bdev);
 	mutex_unlock(&bdev->bd_fsfreeze_mutex);
@@ -296,40 +273,22 @@ int thaw_bdev(struct block_device *bdev, struct super_block *sb)
 
 	mutex_lock(&bdev->bd_fsfreeze_mutex);
 	if (!bdev->bd_fsfreeze_count)
-		goto out_unlock;
+		goto out;
 
 	error = 0;
 	if (--bdev->bd_fsfreeze_count > 0)
-		goto out_unlock;
+		goto out;
 
 	if (!sb)
-		goto out_unlock;
+		goto out;
 
-	BUG_ON(sb->s_bdev != bdev);
-	down_write(&sb->s_umount);
-	if (sb->s_flags & MS_RDONLY)
-		goto out_unfrozen;
-
-	if (sb->s_op->unfreeze_fs) {
-		error = sb->s_op->unfreeze_fs(sb);
-		if (error) {
-			printk(KERN_ERR
-				"VFS:Filesystem thaw failed\n");
-			sb->s_frozen = SB_FREEZE_TRANS;
-			bdev->bd_fsfreeze_count++;
-			mutex_unlock(&bdev->bd_fsfreeze_mutex);
-			return error;
-		}
+	error = thaw_super(sb);
+	if (error) {
+		bdev->bd_fsfreeze_count++;
+		mutex_unlock(&bdev->bd_fsfreeze_mutex);
+		return error;
 	}
-
-out_unfrozen:
-	sb->s_frozen = SB_UNFROZEN;
-	smp_wmb();
-	wake_up(&sb->s_wait_unfrozen);
-
-	if (sb)
-		deactivate_locked_super(sb);
-out_unlock:
+out:
 	mutex_unlock(&bdev->bd_fsfreeze_mutex);
 	return 0;
 }

fs/btrfs/acl.c

@@ -282,14 +282,14 @@ int btrfs_acl_chmod(struct inode *inode)
 	return ret;
 }
 
-struct xattr_handler btrfs_xattr_acl_default_handler = {
+const struct xattr_handler btrfs_xattr_acl_default_handler = {
 	.prefix = POSIX_ACL_XATTR_DEFAULT,
 	.flags	= ACL_TYPE_DEFAULT,
 	.get	= btrfs_xattr_acl_get,
 	.set	= btrfs_xattr_acl_set,
 };
 
-struct xattr_handler btrfs_xattr_acl_access_handler = {
+const struct xattr_handler btrfs_xattr_acl_access_handler = {
 	.prefix = POSIX_ACL_XATTR_ACCESS,
 	.flags	= ACL_TYPE_ACCESS,
 	.get	= btrfs_xattr_acl_get,

fs/btrfs/inode.c

@@ -4121,16 +4121,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 	if (ret != 0)
 		goto fail;
 
-	inode->i_uid = current_fsuid();
-
-	if (dir && (dir->i_mode & S_ISGID)) {
-		inode->i_gid = dir->i_gid;
-		if (S_ISDIR(mode))
-			mode |= S_ISGID;
-	} else
-		inode->i_gid = current_fsgid();
-
-	inode->i_mode = mode;
+	inode_init_owner(inode, dir, mode);
 	inode->i_ino = objectid;
 	inode_set_bytes(inode, 0);
 	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;

fs/btrfs/xattr.c

@@ -282,7 +282,7 @@ err:
  * List of handlers for synthetic system.* attributes.  All real ondisk
  * attributes are handled directly.
  */
-struct xattr_handler *btrfs_xattr_handlers[] = {
+const struct xattr_handler *btrfs_xattr_handlers[] = {
 #ifdef CONFIG_BTRFS_FS_POSIX_ACL
 	&btrfs_xattr_acl_access_handler,
 	&btrfs_xattr_acl_default_handler,

fs/btrfs/xattr.h

@@ -21,9 +21,9 @@
 
 #include <linux/xattr.h>
 
-extern struct xattr_handler btrfs_xattr_acl_access_handler;
-extern struct xattr_handler btrfs_xattr_acl_default_handler;
-extern struct xattr_handler *btrfs_xattr_handlers[];
+extern const struct xattr_handler btrfs_xattr_acl_access_handler;
+extern const struct xattr_handler btrfs_xattr_acl_default_handler;
+extern const struct xattr_handler *btrfs_xattr_handlers[];
 
 extern ssize_t __btrfs_getxattr(struct inode *inode, const char *name,
 		void *buffer, size_t size);

fs/buffer.c

@@ -561,26 +561,17 @@ repeat:
 	return err;
 }
 
+static void do_thaw_one(struct super_block *sb, void *unused)
+{
+	char b[BDEVNAME_SIZE];
+	while (sb->s_bdev && !thaw_bdev(sb->s_bdev, sb))
+		printk(KERN_WARNING "Emergency Thaw on %s\n",
+		       bdevname(sb->s_bdev, b));
+}
+
 static void do_thaw_all(struct work_struct *work)
 {
-	struct super_block *sb;
-	char b[BDEVNAME_SIZE];
-
-	spin_lock(&sb_lock);
-restart:
-	list_for_each_entry(sb, &super_blocks, s_list) {
-		sb->s_count++;
-		spin_unlock(&sb_lock);
-		down_read(&sb->s_umount);
-		while (sb->s_bdev && !thaw_bdev(sb->s_bdev, sb))
-			printk(KERN_WARNING "Emergency Thaw on %s\n",
-			       bdevname(sb->s_bdev, b));
-		up_read(&sb->s_umount);
-		spin_lock(&sb_lock);
-		if (__put_super_and_need_restart(sb))
-			goto restart;
-	}
-	spin_unlock(&sb_lock);
+	iterate_supers(do_thaw_one, NULL);
 	kfree(work);
 	printk(KERN_WARNING "Emergency Thaw complete\n");
 }

fs/ceph/file.c

@@ -844,8 +844,7 @@ retry_snap:
 		if ((ret >= 0 || ret == -EIOCBQUEUED) &&
 		    ((file->f_flags & O_SYNC) || IS_SYNC(file->f_mapping->host)
 		     || ceph_osdmap_flag(osdc->osdmap, CEPH_OSDMAP_NEARFULL))) {
-			err = vfs_fsync_range(file, file->f_path.dentry,
-					      pos, pos + ret - 1, 1);
+			err = vfs_fsync_range(file, pos, pos + ret - 1, 1);
 			if (err < 0)
 				ret = err;
 		}

fs/ceph/super.c

@@ -952,8 +952,7 @@ static int ceph_get_sb(struct file_system_type *fs_type,
 
 out_splat:
 	ceph_mdsc_close_sessions(&client->mdsc);
-	up_write(&sb->s_umount);
-	deactivate_super(sb);
+	deactivate_locked_super(sb);
 	goto out_final;
 
 out:

fs/coda/file.c

@@ -217,7 +217,7 @@ int coda_fsync(struct file *coda_file, struct dentry *coda_dentry, int datasync)
 	BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC);
 	host_file = cfi->cfi_container;
 
-	err = vfs_fsync(host_file, host_file->f_path.dentry, datasync);
+	err = vfs_fsync(host_file, datasync);
 	if ( !err && !datasync ) {
 		lock_kernel();
 		err = venus_fsync(coda_inode->i_sb, coda_i2f(coda_inode));

fs/dcache.c

@@ -536,7 +536,7 @@ restart:
  */
 static void prune_dcache(int count)
 {
-	struct super_block *sb;
+	struct super_block *sb, *n;
 	int w_count;
 	int unused = dentry_stat.nr_unused;
 	int prune_ratio;
@@ -545,13 +545,14 @@ static void prune_dcache(int count)
 	if (unused == 0 || count == 0)
 		return;
 	spin_lock(&dcache_lock);
-restart:
 	if (count >= unused)
 		prune_ratio = 1;
 	else
 		prune_ratio = unused / count;
 	spin_lock(&sb_lock);
-	list_for_each_entry(sb, &super_blocks, s_list) {
+	list_for_each_entry_safe(sb, n, &super_blocks, s_list) {
+		if (list_empty(&sb->s_instances))
+			continue;
 		if (sb->s_nr_dentry_unused == 0)
 			continue;
 		sb->s_count++;
@@ -590,14 +591,10 @@ restart:
 		}
 		spin_lock(&sb_lock);
 		count -= pruned;
-		/*
-		 * restart only when sb is no longer on the list and
-		 * we have more work to do.
-		 */
-		if (__put_super_and_need_restart(sb) && count > 0) {
-			spin_unlock(&sb_lock);
-			goto restart;
-		}
+		__put_super(sb);
+		/* more work left to do? */
+		if (count <= 0)
+			break;
 	}
 	spin_unlock(&sb_lock);
 	spin_unlock(&dcache_lock);
@@ -1529,6 +1526,7 @@ void d_delete(struct dentry * dentry)
 	spin_lock(&dentry->d_lock);
 	isdir = S_ISDIR(dentry->d_inode->i_mode);
 	if (atomic_read(&dentry->d_count) == 1) {
+		dentry->d_flags &= ~DCACHE_CANT_MOUNT;
 		dentry_iput(dentry);
 		fsnotify_nameremove(dentry, isdir);
 		return;

fs/devpts/inode.c

@@ -384,19 +384,16 @@ static int devpts_get_sb(struct file_system_type *fs_type,
 		s->s_flags |= MS_ACTIVE;
 	}
 
-	simple_set_mnt(mnt, s);
-
 	memcpy(&(DEVPTS_SB(s))->mount_opts, &opts, sizeof(opts));
 
 	error = mknod_ptmx(s);
 	if (error)
-		goto out_dput;
+		goto out_undo_sget;
+
+	simple_set_mnt(mnt, s);
 
 	return 0;
 
-out_dput:
-	dput(s->s_root); /* undo dget() in simple_set_mnt() */
-
 out_undo_sget:
 	deactivate_locked_super(s);
 	return error;

fs/drop_caches.c

@@ -12,7 +12,7 @@
 /* A global variable is a bit ugly, but it keeps the code simple */
 int sysctl_drop_caches;
 
-static void drop_pagecache_sb(struct super_block *sb)
+static void drop_pagecache_sb(struct super_block *sb, void *unused)
 {
 	struct inode *inode, *toput_inode = NULL;
 
@@ -33,26 +33,6 @@ static void drop_pagecache_sb(struct super_block *sb)
 	iput(toput_inode);
 }
 
-static void drop_pagecache(void)
-{
-	struct super_block *sb;
-
-	spin_lock(&sb_lock);
-restart:
-	list_for_each_entry(sb, &super_blocks, s_list) {
-		sb->s_count++;
-		spin_unlock(&sb_lock);
-		down_read(&sb->s_umount);
-		if (sb->s_root)
-			drop_pagecache_sb(sb);
-		up_read(&sb->s_umount);
-		spin_lock(&sb_lock);
-		if (__put_super_and_need_restart(sb))
-			goto restart;
-	}
-	spin_unlock(&sb_lock);
-}
-
 static void drop_slab(void)
 {
 	int nr_objects;
@@ -68,7 +48,7 @@ int drop_caches_sysctl_handler(ctl_table *table, int write,
 	proc_dointvec_minmax(table, write, buffer, length, ppos);
 	if (write) {
 		if (sysctl_drop_caches & 1)
-			drop_pagecache();
+			iterate_supers(drop_pagecache_sb, NULL);
 		if (sysctl_drop_caches & 2)
 			drop_slab();
 	}