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: (52 commits)
  split invalidate_inodes()
  fs: skip I_FREEING inodes in writeback_sb_inodes
  fs: fold invalidate_list into invalidate_inodes
  fs: do not drop inode_lock in dispose_list
  fs: inode split IO and LRU lists
  fs: switch bdev inode bdi's correctly
  fs: fix buffer invalidation in invalidate_list
  fsnotify: use dget_parent
  smbfs: use dget_parent
  exportfs: use dget_parent
  fs: use RCU read side protection in d_validate
  fs: clean up dentry lru modification
  fs: split __shrink_dcache_sb
  fs: improve DCACHE_REFERENCED usage
  fs: use percpu counter for nr_dentry and nr_dentry_unused
  fs: simplify __d_free
  fs: take dcache_lock inside __d_path
  fs: do not assign default i_ino in new_inode
  fs: introduce a per-cpu last_ino allocator
  new helper: ihold()
  ...

Documentation/filesystems/Locking

@@ -349,21 +349,36 @@ call this method upon the IO completion.
 
 --------------------------- block_device_operations -----------------------
 prototypes:
-	int (*open) (struct inode *, struct file *);
-	int (*release) (struct inode *, struct file *);
-	int (*ioctl) (struct inode *, struct file *, unsigned, unsigned long);
+	int (*open) (struct block_device *, fmode_t);
+	int (*release) (struct gendisk *, fmode_t);
+	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
+	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
+	int (*direct_access) (struct block_device *, sector_t, void **, unsigned long *);
 	int (*media_changed) (struct gendisk *);
+	void (*unlock_native_capacity) (struct gendisk *);
 	int (*revalidate_disk) (struct gendisk *);
+	int (*getgeo)(struct block_device *, struct hd_geometry *);
+	void (*swap_slot_free_notify) (struct block_device *, unsigned long);
 
 locking rules:
-			BKL	bd_sem
-open:			yes	yes
-release:		yes	yes
-ioctl:			yes	no
+			BKL	bd_mutex
+open:			no	yes
+release:		no	yes
+ioctl:			no	no
+compat_ioctl:		no	no
+direct_access:		no	no
 media_changed:		no	no
+unlock_native_capacity:	no	no
 revalidate_disk:	no	no
+getgeo:			no	no
+swap_slot_free_notify:	no	no	(see below)
+
+media_changed, unlock_native_capacity and revalidate_disk are called only from
+check_disk_change().
+
+swap_slot_free_notify is called with swap_lock and sometimes the page lock
+held.
 
-The last two are called only from check_disk_change().
 
 --------------------------- file_operations -------------------------------
 prototypes:

Documentation/filesystems/sharedsubtree.txt

@@ -62,10 +62,10 @@ replicas continue to be exactly same.
 	# mount /dev/sd0  /tmp/a
 
 	#ls /tmp/a
-	t1 t2 t2
+	t1 t2 t3
 
 	#ls /mnt/a
-	t1 t2 t2
+	t1 t2 t3
 
 	Note that the mount has propagated to the mount at /mnt as well.
 

drivers/char/mem.c

@@ -876,6 +876,10 @@ static int memory_open(struct inode *inode, struct file *filp)
 	if (dev->dev_info)
 		filp->f_mapping->backing_dev_info = dev->dev_info;
 
+	/* Is /dev/mem or /dev/kmem ? */
+	if (dev->dev_info == &directly_mappable_cdev_bdi)
+		filp->f_mode |= FMODE_UNSIGNED_OFFSET;
+
 	if (dev->fops->open)
 		return dev->fops->open(inode, filp);
 

drivers/infiniband/hw/ipath/ipath_fs.c

@@ -57,6 +57,7 @@ static int ipathfs_mknod(struct inode *dir, struct dentry *dentry,
 		goto bail;
 	}
 
+	inode->i_ino = get_next_ino();
 	inode->i_mode = mode;
 	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 	inode->i_private = data;

drivers/infiniband/hw/qib/qib_fs.c

@@ -58,6 +58,7 @@ static int qibfs_mknod(struct inode *dir, struct dentry *dentry,
 		goto bail;
 	}
 
+	inode->i_ino = get_next_ino();
 	inode->i_mode = mode;
 	inode->i_uid = 0;
 	inode->i_gid = 0;

drivers/misc/ibmasm/ibmasmfs.c

@@ -146,6 +146,7 @@ static struct inode *ibmasmfs_make_inode(struct super_block *sb, int mode)
 	struct inode *ret = new_inode(sb);
 
 	if (ret) {
+		ret->i_ino = get_next_ino();
 		ret->i_mode = mode;
 		ret->i_atime = ret->i_mtime = ret->i_ctime = CURRENT_TIME;
 	}

drivers/oprofile/oprofilefs.c

@@ -28,6 +28,7 @@ static struct inode *oprofilefs_get_inode(struct super_block *sb, int mode)
 	struct inode *inode = new_inode(sb);
 
 	if (inode) {
+		inode->i_ino = get_next_ino();
 		inode->i_mode = mode;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 	}

drivers/staging/pohmelfs/inode.c

@@ -882,12 +882,8 @@ static struct inode *pohmelfs_alloc_inode(struct super_block *sb)
 static int pohmelfs_fsync(struct file *file, int datasync)
 {
 	struct inode *inode = file->f_mapping->host;
-	struct writeback_control wbc = {
-		.sync_mode = WB_SYNC_ALL,
-		.nr_to_write = 0,	/* sys_fsync did this */
-	};
 
-	return sync_inode(inode, &wbc);
+	return sync_inode_metadata(inode, 1);
 }
 
 ssize_t pohmelfs_write(struct file *file, const char __user *buf,

drivers/usb/core/inode.c

@@ -276,6 +276,7 @@ static struct inode *usbfs_get_inode (struct super_block *sb, int mode, dev_t de
 	struct inode *inode = new_inode(sb);
 
 	if (inode) {
+		inode->i_ino = get_next_ino();
 		inode->i_mode = mode;
 		inode->i_uid = current_fsuid();
 		inode->i_gid = current_fsgid();

drivers/usb/gadget/f_fs.c

@@ -980,6 +980,7 @@ ffs_sb_make_inode(struct super_block *sb, void *data,
 	if (likely(inode)) {
 		struct timespec current_time = CURRENT_TIME;
 
+		inode->i_ino	 = usbfs_get_inode();
 		inode->i_mode    = perms->mode;
 		inode->i_uid     = perms->uid;
 		inode->i_gid     = perms->gid;

drivers/usb/gadget/inode.c

@@ -1991,6 +1991,7 @@ gadgetfs_make_inode (struct super_block *sb,
 	struct inode *inode = new_inode (sb);
 
 	if (inode) {
+		inode->i_ino = get_next_ino();
 		inode->i_mode = mode;
 		inode->i_uid = default_uid;
 		inode->i_gid = default_gid;

fs/9p/vfs_inode.c

@@ -1789,9 +1789,10 @@ v9fs_vfs_link_dotl(struct dentry *old_dentry, struct inode *dir,
 		kfree(st);
 	} else {
 		/* Caching disabled. No need to get upto date stat info.
-		 * This dentry will be released immediately. So, just i_count++
+		 * This dentry will be released immediately. So, just hold the
+		 * inode
 		 */
-		atomic_inc(&old_dentry->d_inode->i_count);
+		ihold(old_dentry->d_inode);
 	}
 
 	dentry->d_op = old_dentry->d_op;

fs/affs/file.c

@@ -894,9 +894,9 @@ affs_truncate(struct inode *inode)
 		if (AFFS_SB(sb)->s_flags & SF_OFS) {
 			struct buffer_head *bh = affs_bread_ino(inode, last_blk, 0);
 			u32 tmp;
-			if (IS_ERR(ext_bh)) {
+			if (IS_ERR(bh)) {
 				affs_warning(sb, "truncate", "unexpected read error for last block %u (%d)",
-					     ext, PTR_ERR(ext_bh));
+					     ext, PTR_ERR(bh));
 				return;
 			}
 			tmp = be32_to_cpu(AFFS_DATA_HEAD(bh)->next);

fs/affs/inode.c

@@ -388,7 +388,7 @@ affs_add_entry(struct inode *dir, struct inode *inode, struct dentry *dentry, s3
 		affs_adjust_checksum(inode_bh, block - be32_to_cpu(chain));
 		mark_buffer_dirty_inode(inode_bh, inode);
 		inode->i_nlink = 2;
-		atomic_inc(&inode->i_count);
+		ihold(inode);
 	}
 	affs_fix_checksum(sb, bh);
 	mark_buffer_dirty_inode(bh, inode);

fs/afs/dir.c

@@ -1045,7 +1045,7 @@ static int afs_link(struct dentry *from, struct inode *dir,
 	if (ret < 0)
 		goto link_error;
 
-	atomic_inc(&vnode->vfs_inode.i_count);
+	ihold(&vnode->vfs_inode);
 	d_instantiate(dentry, &vnode->vfs_inode);
 	key_put(key);
 	_leave(" = 0");

fs/aio.c

@@ -1543,7 +1543,19 @@ static void aio_batch_add(struct address_space *mapping,
 	}
 
 	abe = mempool_alloc(abe_pool, GFP_KERNEL);
-	BUG_ON(!igrab(mapping->host));
+
+	/*
+	 * we should be using igrab here, but
+	 * we don't want to hammer on the global
+	 * inode spinlock just to take an extra
+	 * reference on a file that we must already
+	 * have a reference to.
+	 *
+	 * When we're called, we always have a reference
+	 * on the file, so we must always have a reference
+	 * on the inode, so ihold() is safe here.
+	 */
+	ihold(mapping->host);
 	abe->mapping = mapping;
 	hlist_add_head(&abe->list, &batch_hash[bucket]);
 	return;

fs/anon_inodes.c

@@ -111,10 +111,9 @@ struct file *anon_inode_getfile(const char *name,
 	path.mnt = mntget(anon_inode_mnt);
 	/*
 	 * We know the anon_inode inode count is always greater than zero,
-	 * so we can avoid doing an igrab() and we can use an open-coded
-	 * atomic_inc().
+	 * so ihold() is safe.
 	 */
-	atomic_inc(&anon_inode_inode->i_count);
+	ihold(anon_inode_inode);
 
 	path.dentry->d_op = &anon_inodefs_dentry_operations;
 	d_instantiate(path.dentry, anon_inode_inode);
@@ -194,6 +193,7 @@ static struct inode *anon_inode_mkinode(void)
 	if (!inode)
 		return ERR_PTR(-ENOMEM);
 
+	inode->i_ino = get_next_ino();
 	inode->i_fop = &anon_inode_fops;
 
 	inode->i_mapping->a_ops = &anon_aops;

fs/autofs4/inode.c

@@ -398,6 +398,7 @@ struct inode *autofs4_get_inode(struct super_block *sb,
 		inode->i_gid = sb->s_root->d_inode->i_gid;
 	}
 	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+	inode->i_ino = get_next_ino();
 
 	if (S_ISDIR(inf->mode)) {
 		inode->i_nlink = 2;

fs/bfs/dir.c

@@ -176,7 +176,7 @@ static int bfs_link(struct dentry *old, struct inode *dir,
 	inc_nlink(inode);
 	inode->i_ctime = CURRENT_TIME_SEC;
 	mark_inode_dirty(inode);
-	atomic_inc(&inode->i_count);
+	ihold(inode);
 	d_instantiate(new, inode);
 	mutex_unlock(&info->bfs_lock);
 	return 0;

fs/binfmt_misc.c

@@ -495,6 +495,7 @@ static struct inode *bm_get_inode(struct super_block *sb, int mode)
 	struct inode * inode = new_inode(sb);
 
 	if (inode) {
+		inode->i_ino = get_next_ino();
 		inode->i_mode = mode;
 		inode->i_atime = inode->i_mtime = inode->i_ctime =
 			current_fs_time(inode->i_sb);

fs/block_dev.c

@@ -48,6 +48,21 @@ inline struct block_device *I_BDEV(struct inode *inode)
 
 EXPORT_SYMBOL(I_BDEV);
 
+/*
+ * move the inode from it's current bdi to the a new bdi. if the inode is dirty
+ * we need to move it onto the dirty list of @dst so that the inode is always
+ * on the right list.
+ */
+static void bdev_inode_switch_bdi(struct inode *inode,
+			struct backing_dev_info *dst)
+{
+	spin_lock(&inode_lock);
+	inode->i_data.backing_dev_info = dst;
+	if (inode->i_state & I_DIRTY)
+		list_move(&inode->i_wb_list, &dst->wb.b_dirty);
+	spin_unlock(&inode_lock);
+}
+
 static sector_t max_block(struct block_device *bdev)
 {
 	sector_t retval = ~((sector_t)0);
@@ -550,7 +565,7 @@ EXPORT_SYMBOL(bdget);
  */
 struct block_device *bdgrab(struct block_device *bdev)
 {
-	atomic_inc(&bdev->bd_inode->i_count);
+	ihold(bdev->bd_inode);
 	return bdev;
 }
 
@@ -580,7 +595,7 @@ static struct block_device *bd_acquire(struct inode *inode)
 	spin_lock(&bdev_lock);
 	bdev = inode->i_bdev;
 	if (bdev) {
-		atomic_inc(&bdev->bd_inode->i_count);
+		ihold(bdev->bd_inode);
 		spin_unlock(&bdev_lock);
 		return bdev;
 	}
@@ -591,12 +606,12 @@ static struct block_device *bd_acquire(struct inode *inode)
 		spin_lock(&bdev_lock);
 		if (!inode->i_bdev) {
 			/*
-			 * We take an additional bd_inode->i_count for inode,
+			 * We take an additional reference to bd_inode,
 			 * and it's released in clear_inode() of inode.
 			 * So, we can access it via ->i_mapping always
 			 * without igrab().
 			 */
-			atomic_inc(&bdev->bd_inode->i_count);
+			ihold(bdev->bd_inode);
 			inode->i_bdev = bdev;
 			inode->i_mapping = bdev->bd_inode->i_mapping;
 			list_add(&inode->i_devices, &bdev->bd_inodes);
@@ -1390,7 +1405,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 				bdi = blk_get_backing_dev_info(bdev);
 				if (bdi == NULL)
 					bdi = &default_backing_dev_info;
-				bdev->bd_inode->i_data.backing_dev_info = bdi;
+				bdev_inode_switch_bdi(bdev->bd_inode, bdi);
 			}
 			if (bdev->bd_invalidated)
 				rescan_partitions(disk, bdev);
@@ -1405,8 +1420,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 			if (ret)
 				goto out_clear;
 			bdev->bd_contains = whole;
-			bdev->bd_inode->i_data.backing_dev_info =
-			   whole->bd_inode->i_data.backing_dev_info;
+			bdev_inode_switch_bdi(bdev->bd_inode,
+				whole->bd_inode->i_data.backing_dev_info);
 			bdev->bd_part = disk_get_part(disk, partno);
 			if (!(disk->flags & GENHD_FL_UP) ||
 			    !bdev->bd_part || !bdev->bd_part->nr_sects) {
@@ -1439,7 +1454,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 	disk_put_part(bdev->bd_part);
 	bdev->bd_disk = NULL;
 	bdev->bd_part = NULL;
-	bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info;
+	bdev_inode_switch_bdi(bdev->bd_inode, &default_backing_dev_info);
 	if (bdev != bdev->bd_contains)
 		__blkdev_put(bdev->bd_contains, mode, 1);
 	bdev->bd_contains = NULL;
@@ -1533,7 +1548,8 @@ static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
 		disk_put_part(bdev->bd_part);
 		bdev->bd_part = NULL;
 		bdev->bd_disk = NULL;
-		bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info;
+		bdev_inode_switch_bdi(bdev->bd_inode,
+					&default_backing_dev_info);
 		if (bdev != bdev->bd_contains)
 			victim = bdev->bd_contains;
 		bdev->bd_contains = NULL;

fs/btrfs/inode.c

@@ -3849,7 +3849,7 @@ static void inode_tree_add(struct inode *inode)
 	p = &root->inode_tree.rb_node;
 	parent = NULL;
 
-	if (hlist_unhashed(&inode->i_hash))
+	if (inode_unhashed(inode))
 		return;
 
 	spin_lock(&root->inode_lock);
@@ -4758,7 +4758,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 	}
 
 	btrfs_set_trans_block_group(trans, dir);
-	atomic_inc(&inode->i_count);
+	ihold(inode);
 
 	err = btrfs_add_nondir(trans, dentry, inode, 1, index);