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 @@ again:
 	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);
 

fs/buffer.c

@@ -1833,9 +1833,11 @@ void page_zero_new_buffers(struct page *page, unsigned from, unsigned to)
 }
 EXPORT_SYMBOL(page_zero_new_buffers);
 
-int block_prepare_write(struct page *page, unsigned from, unsigned to,
+int __block_write_begin(struct page *page, loff_t pos, unsigned len,
 		get_block_t *get_block)
 {
+	unsigned from = pos & (PAGE_CACHE_SIZE - 1);
+	unsigned to = from + len;
 	struct inode *inode = page->mapping->host;
 	unsigned block_start, block_end;
 	sector_t block;
@@ -1915,7 +1917,7 @@ int block_prepare_write(struct page *page, unsigned from, unsigned to,
 	}
 	return err;
 }
-EXPORT_SYMBOL(block_prepare_write);
+EXPORT_SYMBOL(__block_write_begin);
 
 static int __block_commit_write(struct inode *inode, struct page *page,
 		unsigned from, unsigned to)
@@ -1952,15 +1954,6 @@ static int __block_commit_write(struct inode *inode, struct page *page,
 	return 0;
 }
 
-int __block_write_begin(struct page *page, loff_t pos, unsigned len,
-		get_block_t *get_block)
-{
-	unsigned start = pos & (PAGE_CACHE_SIZE - 1);
-
-	return block_prepare_write(page, start, start + len, get_block);
-}
-EXPORT_SYMBOL(__block_write_begin);
-
 /*
  * block_write_begin takes care of the basic task of block allocation and
  * bringing partial write blocks uptodate first.
@@ -2378,7 +2371,7 @@ block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
 	else
 		end = PAGE_CACHE_SIZE;
 
-	ret = block_prepare_write(page, 0, end, get_block);
+	ret = __block_write_begin(page, 0, end, get_block);
 	if (!ret)
 		ret = block_commit_write(page, 0, end);
 
@@ -2465,11 +2458,10 @@ int nobh_write_begin(struct address_space *mapping,
 	*fsdata = NULL;
 
 	if (page_has_buffers(page)) {
-		unlock_page(page);
-		page_cache_release(page);
-		*pagep = NULL;
-		return block_write_begin(mapping, pos, len, flags, pagep,
-					 get_block);
+		ret = __block_write_begin(page, pos, len, get_block);
+		if (unlikely(ret))
+			goto out_release;
+		return ret;
 	}
 
 	if (PageMappedToDisk(page))

fs/coda/dir.c

@@ -276,7 +276,7 @@ static int coda_link(struct dentry *source_de, struct inode *dir_inode,
 	}
 
 	coda_dir_update_mtime(dir_inode);
-	atomic_inc(&inode->i_count);
+	ihold(inode);
 	d_instantiate(de, inode);
 	inc_nlink(inode);
 	return 0;

fs/configfs/inode.c

@@ -135,6 +135,7 @@ struct inode * configfs_new_inode(mode_t mode, struct configfs_dirent * sd)
 {
 	struct inode * inode = new_inode(configfs_sb);
 	if (inode) {
+		inode->i_ino = get_next_ino();
 		inode->i_mapping->a_ops = &configfs_aops;
 		inode->i_mapping->backing_dev_info = &configfs_backing_dev_info;
 		inode->i_op = &configfs_inode_operations;

fs/dcache.c

@@ -67,33 +67,43 @@ struct dentry_stat_t dentry_stat = {
 	.age_limit = 45,
 };
 
-static void __d_free(struct dentry *dentry)
+static struct percpu_counter nr_dentry __cacheline_aligned_in_smp;
+static struct percpu_counter nr_dentry_unused __cacheline_aligned_in_smp;
+
+#if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
+int proc_nr_dentry(ctl_table *table, int write, void __user *buffer,
+		   size_t *lenp, loff_t *ppos)
+{
+	dentry_stat.nr_dentry = percpu_counter_sum_positive(&nr_dentry);
+	dentry_stat.nr_unused = percpu_counter_sum_positive(&nr_dentry_unused);
+	return proc_dointvec(table, write, buffer, lenp, ppos);
+}
+#endif
+
+static void __d_free(struct rcu_head *head)
 {
+	struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);
+
 	WARN_ON(!list_empty(&dentry->d_alias));
 	if (dname_external(dentry))
 		kfree(dentry->d_name.name);
 	kmem_cache_free(dentry_cache, dentry); 
 }
 
-static void d_callback(struct rcu_head *head)
-{
-	struct dentry * dentry = container_of(head, struct dentry, d_u.d_rcu);
-	__d_free(dentry);
-}
-
 /*
- * no dcache_lock, please.  The caller must decrement dentry_stat.nr_dentry
- * inside dcache_lock.
+ * no dcache_lock, please.
  */
 static void d_free(struct dentry *dentry)
 {
+	percpu_counter_dec(&nr_dentry);
 	if (dentry->d_op && dentry->d_op->d_release)
 		dentry->d_op->d_release(dentry);
+
 	/* if dentry was never inserted into hash, immediate free is OK */
 	if (hlist_unhashed(&dentry->d_hash))
-		__d_free(dentry);
+		__d_free(&dentry->d_u.d_rcu);
 	else
-		call_rcu(&dentry->d_u.d_rcu, d_callback);
+		call_rcu(&dentry->d_u.d_rcu, __d_free);
 }
 
 /*
@@ -123,37 +133,34 @@ static void dentry_iput(struct dentry * dentry)
 }
 
 /*
- * dentry_lru_(add|add_tail|del|del_init) must be called with dcache_lock held.
+ * dentry_lru_(add|del|move_tail) must be called with dcache_lock held.
  */
 static void dentry_lru_add(struct dentry *dentry)
 {
-	list_add(&dentry->d_lru, &dentry->d_sb->s_dentry_lru);
-	dentry->d_sb->s_nr_dentry_unused++;
-	dentry_stat.nr_unused++;
-}
-
-static void dentry_lru_add_tail(struct dentry *dentry)
-{
-	list_add_tail(&dentry->d_lru, &dentry->d_sb->s_dentry_lru);
-	dentry->d_sb->s_nr_dentry_unused++;
-	dentry_stat.nr_unused++;
+	if (list_empty(&dentry->d_lru)) {
+		list_add(&dentry->d_lru, &dentry->d_sb->s_dentry_lru);
+		dentry->d_sb->s_nr_dentry_unused++;
+		percpu_counter_inc(&nr_dentry_unused);
+	}
 }
 
 static void dentry_lru_del(struct dentry *dentry)
 {
 	if (!list_empty(&dentry->d_lru)) {
-		list_del(&dentry->d_lru);
+		list_del_init(&dentry->d_lru);
 		dentry->d_sb->s_nr_dentry_unused--;
-		dentry_stat.nr_unused--;
+		percpu_counter_dec(&nr_dentry_unused);
 	}
 }
 
-static void dentry_lru_del_init(struct dentry *dentry)
+static void dentry_lru_move_tail(struct dentry *dentry)
 {
-	if (likely(!list_empty(&dentry->d_lru))) {
-		list_del_init(&dentry->d_lru);
-		dentry->d_sb->s_nr_dentry_unused--;
-		dentry_stat.nr_unused--;
+	if (list_empty(&dentry->d_lru)) {
+		list_add_tail(&dentry->d_lru, &dentry->d_sb->s_dentry_lru);
+		dentry->d_sb->s_nr_dentry_unused++;
+		percpu_counter_inc(&nr_dentry_unused);
+	} else {
+		list_move_tail(&dentry->d_lru, &dentry->d_sb->s_dentry_lru);
 	}
 }
 
@@ -172,7 +179,6 @@ static struct dentry *d_kill(struct dentry *dentry)
 	struct dentry *parent;
 
 	list_del(&dentry->d_u.d_child);
-	dentry_stat.nr_dentry--;	/* For d_free, below */
 	/*drops the locks, at that point nobody can reach this dentry */
 	dentry_iput(dentry);
 	if (IS_ROOT(dentry))
@@ -237,13 +243,15 @@ repeat:
 		if (dentry->d_op->d_delete(dentry))
 			goto unhash_it;
 	}
+
 	/* Unreachable? Get rid of it */
  	if (d_unhashed(dentry))
 		goto kill_it;
-  	if (list_empty(&dentry->d_lru)) {
-  		dentry->d_flags |= DCACHE_REFERENCED;
-		dentry_lru_add(dentry);
-  	}
+
+	/* Otherwise leave it cached and ensure it's on the LRU */
+	dentry->d_flags |= DCACHE_REFERENCED;
+	dentry_lru_add(dentry);
+
  	spin_unlock(&dentry->d_lock);
 	spin_unlock(&dcache_lock);
 	return;
@@ -318,11 +326,10 @@ int d_invalidate(struct dentry * dentry)
 EXPORT_SYMBOL(d_invalidate);
 
 /* This should be called _only_ with dcache_lock held */
-
 static inline struct dentry * __dget_locked(struct dentry *dentry)
 {
 	atomic_inc(&dentry->d_count);
-	dentry_lru_del_init(dentry);
+	dentry_lru_del(dentry);
 	return dentry;
 }
 
@@ -441,73 +448,27 @@ static void prune_one_dentry(struct dentry * dentry)
 
 		if (dentry->d_op && dentry->d_op->d_delete)
 			dentry->d_op->d_delete(dentry);
-		dentry_lru_del_init(dentry);
+		dentry_lru_del(dentry);
 		__d_drop(dentry);
 		dentry = d_kill(dentry);
 		spin_lock(&dcache_lock);
 	}
 }
 
-/*
- * Shrink the dentry LRU on a given superblock.
- * @sb   : superblock to shrink dentry LRU.
- * @count: If count is NULL, we prune all dentries on superblock.
- * @flags: If flags is non-zero, we need to do special processing based on
- * which flags are set. This means we don't need to maintain multiple
- * similar copies of this loop.
- */
-static void __shrink_dcache_sb(struct super_block *sb, int *count, int flags)
+static void shrink_dentry_list(struct list_head *list)
 {
-	LIST_HEAD(referenced);
-	LIST_HEAD(tmp);
 	struct dentry *dentry;
-	int cnt = 0;
 
-	BUG_ON(!sb);
-	BUG_ON((flags & DCACHE_REFERENCED) && count == NULL);
-	spin_lock(&dcache_lock);
-	if (count != NULL)
-		/* called from prune_dcache() and shrink_dcache_parent() */
-		cnt = *count;
-restart:
-	if (count == NULL)
-		list_splice_init(&sb->s_dentry_lru, &tmp);
-	else {
-		while (!list_empty(&sb->s_dentry_lru)) {
-			dentry = list_entry(sb->s_dentry_lru.prev,
-					struct dentry, d_lru);
-			BUG_ON(dentry->d_sb != sb);
+	while (!list_empty(list)) {
+		dentry = list_entry(list->prev, struct dentry, d_lru);
+		dentry_lru_del(dentry);
 
-			spin_lock(&dentry->d_lock);
-			/*
-			 * If we are honouring the DCACHE_REFERENCED flag and
-			 * the dentry has this flag set, don't free it. Clear
-			 * the flag and put it back on the LRU.
-			 */
-			if ((flags & DCACHE_REFERENCED)
-				&& (dentry->d_flags & DCACHE_REFERENCED)) {
-				dentry->d_flags &= ~DCACHE_REFERENCED;
-				list_move(&dentry->d_lru, &referenced);
-				spin_unlock(&dentry->d_lock);
-			} else {
-				list_move_tail(&dentry->d_lru, &tmp);
-				spin_unlock(&dentry->d_lock);
-				cnt--;
-				if (!cnt)
-					break;
-			}
-			cond_resched_lock(&dcache_lock);
-		}
-	}
-	while (!list_empty(&tmp)) {
-		dentry = list_entry(tmp.prev, struct dentry, d_lru);
-		dentry_lru_del_init(dentry);
-		spin_lock(&dentry->d_lock);
 		/*
 		 * We found an inuse dentry which was not removed from
 		 * the LRU because of laziness during lookup.  Do not free
 		 * it - just keep it off the LRU list.
 		 */
+		spin_lock(&dentry->d_lock);
 		if (atomic_read(&dentry->d_count)) {
 			spin_unlock(&dentry->d_lock);
 			continue;
@@ -516,13 +477,60 @@ restart:
 		/* dentry->d_lock was dropped in prune_one_dentry() */
 		cond_resched_lock(&dcache_lock);
 	}
-	if (count == NULL && !list_empty(&sb->s_dentry_lru))
-		goto restart;
-	if (count != NULL)
-		*count = cnt;
+}
+
+/**
+ * __shrink_dcache_sb - shrink the dentry LRU on a given superblock
+ * @sb:		superblock to shrink dentry LRU.
+ * @count:	number of entries to prune
+ * @flags:	flags to control the dentry processing
+ *
+ * If flags contains DCACHE_REFERENCED reference dentries will not be pruned.
+ */
+static void __shrink_dcache_sb(struct super_block *sb, int *count, int flags)
+{
+	/* called from prune_dcache() and shrink_dcache_parent() */
+	struct dentry *dentry;
+	LIST_HEAD(referenced);
+	LIST_HEAD(tmp);
+	int cnt = *count;
+
+	spin_lock(&dcache_lock);
+	while (!list_empty(&sb->s_dentry_lru)) {
+		dentry = list_entry(sb->s_dentry_lru.prev,
+				struct dentry, d_lru);
+		BUG_ON(dentry->d_sb != sb);
+
+		/*
+		 * If we are honouring the DCACHE_REFERENCED flag and the
+		 * dentry has this flag set, don't free it.  Clear the flag
+		 * and put it back on the LRU.
+		 */
+		if (flags & DCACHE_REFERENCED) {
+			spin_lock(&dentry->d_lock);
+			if (dentry->d_flags & DCACHE_REFERENCED) {
+				dentry->d_flags &= ~DCACHE_REFERENCED;
+				list_move(&dentry->d_lru, &referenced);
+				spin_unlock(&dentry->d_lock);
+				cond_resched_lock(&dcache_lock);
+				continue;
+			}
+			spin_unlock(&dentry->d_lock);
+		}
+
+		list_move_tail(&dentry->d_lru, &tmp);
+		if (!--cnt)
+			break;
+		cond_resched_lock(&dcache_lock);
+	}
+
+	*count = cnt;
+	shrink_dentry_list(&tmp);
+
 	if (!list_empty(&referenced))
 		list_splice(&referenced, &sb->s_dentry_lru);
 	spin_unlock(&dcache_lock);
+
 }
 
 /**
@@ -538,7 +546,7 @@ static void prune_dcache(int count)
 {
 	struct super_block *sb, *p = NULL;
 	int w_count;
-	int unused = dentry_stat.nr_unused;
+	int unused = percpu_counter_sum_positive(&nr_dentry_unused);
 	int prune_ratio;
 	int pruned;
 
@@ -608,13 +616,19 @@ static void prune_dcache(int count)
  * shrink_dcache_sb - shrink dcache for a superblock
  * @sb: superblock
  *
- * Shrink the dcache for the specified super block. This
- * is used to free the dcache before unmounting a file
- * system
+ * Shrink the dcache for the specified super block. This is used to free
+ * the dcache before unmounting a file system.
  */
-void shrink_dcache_sb(struct super_block * sb)
+void shrink_dcache_sb(struct super_block *sb)
 {
-	__shrink_dcache_sb(sb, NULL, 0);
+	LIST_HEAD(tmp);
+
+	spin_lock(&dcache_lock);
+	while (!list_empty(&sb->s_dentry_lru)) {
+		list_splice_init(&sb->s_dentry_lru, &tmp);
+		shrink_dentry_list(&tmp);
+	}
+	spin_unlock(&dcache_lock);
 }
 EXPORT_SYMBOL(shrink_dcache_sb);
 
@@ -632,7 +646,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
 
 	/* detach this root from the system */
 	spin_lock(&dcache_lock);
-	dentry_lru_del_init(dentry);
+	dentry_lru_del(dentry);
 	__d_drop(dentry);
 	spin_unlock(&dcache_lock);
 
@@ -646,7 +660,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
 			spin_lock(&dcache_lock);
 			list_for_each_entry(loop, &dentry->d_subdirs,
 					    d_u.d_child) {
-				dentry_lru_del_init(loop);
+				dentry_lru_del(loop);
 				__d_drop(loop);
 				cond_resched_lock(&dcache_lock);
 			}
@@ -703,20 +717,13 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
 			 * otherwise we ascend to the parent and move to the
 			 * next sibling if there is one */
 			if (!parent)
-				goto out;
-
+				return;
 			dentry = parent;
-
 		} while (list_empty(&dentry->d_subdirs));
 
 		dentry = list_entry(dentry->d_subdirs.next,
 				    struct dentry, d_u.d_child);
 	}
-out:
-	/* several dentries were freed, need to correct nr_dentry */
-	spin_lock(&dcache_lock);
-	dentry_stat.nr_dentry -= detached;
-	spin_unlock(&dcache_lock);
 }
 
 /*
@@ -830,14 +837,15 @@ resume:
 		struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child);
 		next = tmp->next;
 
-		dentry_lru_del_init(dentry);
 		/* 
 		 * move only zero ref count dentries to the end 
 		 * of the unused list for prune_dcache
 		 */
 		if (!atomic_read(&dentry->d_count)) {
-			dentry_lru_add_tail(dentry);
+			dentry_lru_move_tail(dentry);
 			found++;
+		} else {
+			dentry_lru_del(dentry);
 		}
 
 		/*
@@ -900,12 +908,16 @@ EXPORT_SYMBOL(shrink_dcache_parent);
  */
 static int shrink_dcache_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask)
 {
+	int nr_unused;
+
 	if (nr) {
 		if (!(gfp_mask & __GFP_FS))
 			return -1;
 		prune_dcache(nr);
 	}
-	return (dentry_stat.nr_unused / 100) * sysctl_vfs_cache_pressure;
+
+	nr_unused = percpu_counter_sum_positive(&nr_dentry_unused);
+	return (nr_unused / 100) * sysctl_vfs_cache_pressure;
 }
 
 static struct shrinker dcache_shrinker = {
@@ -972,9 +984,10 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name)
 	spin_lock(&dcache_lock);
 	if (parent)
 		list_add(&dentry->d_u.d_child, &parent->d_subdirs);
-	dentry_stat.nr_dentry++;
 	spin_unlock(&dcache_lock);
 
+	percpu_counter_inc(&nr_dentry);
+
 	return dentry;
 }
 EXPORT_SYMBOL(d_alloc);
@@ -1478,33 +1491,26 @@ out:
  * This is used by ncpfs in its readdir implementation.
  * Zero is returned in the dentry is invalid.
  */
- 
-int d_validate(struct dentry *dentry, struct dentry *dparent)
+int d_validate(struct dentry *dentry, struct dentry *parent)
 {
-	struct hlist_head *base;
-	struct hlist_node *lhp;
+	struct hlist_head *head = d_hash(parent, dentry->d_name.hash);
+	struct hlist_node *node;
+	struct dentry *d;
 
 	/* Check whether the ptr might be valid at all.. */
 	if (!kmem_ptr_validate(dentry_cache, dentry))
-		goto out;
-
-	if (dentry->d_parent != dparent)
-		goto out;
+		return 0;
+	if (dentry->d_parent != parent)
+		return 0;
 
-	spin_lock(&dcache_lock);
-	base = d_hash(dparent, dentry->d_name.hash);
-	hlist_for_each(lhp,base) { 
-		/* hlist_for_each_entry_rcu() not required for d_hash list
-		 * as it is parsed under dcache_lock
-		 */
-		if (dentry == hlist_entry(lhp, struct dentry, d_hash)) {
-			__dget_locked(dentry);
-			spin_unlock(&dcache_lock);
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(d, node, head, d_hash) {
+		if (d == dentry) {
+			dget(dentry);
 			return 1;
 		}
 	}
-	spin_unlock(&dcache_lock);
-out:
+	rcu_read_unlock();
 	return 0;
 }
 EXPORT_SYMBOL(d_validate);
@@ -1994,7 +2000,7 @@ global_root:
  * Returns a pointer into the buffer or an error code if the
  * path was too long.
  *
- * "buflen" should be positive. Caller holds the dcache_lock.
+ * "buflen" should be positive.
  *
  * If path is not reachable from the supplied root, then the value of
  * root is changed (without modifying refcounts).
@@ -2006,10 +2012,12 @@ char *__d_path(const struct path *path, struct path *root,
 	int error;
 
 	prepend(&res, &buflen, "\0", 1);
+	spin_lock(&dcache_lock);
 	error = prepend_path(path, root, &res, &buflen);
+	spin_unlock(&dcache_lock);
+
 	if (error)
 		return ERR_PTR(error);
-
 	return res;
 }
 
@@ -2419,6 +2427,9 @@ static void __init dcache_init(void)
 {
 	int loop;
 
+	percpu_counter_init(&nr_dentry, 0);
+	percpu_counter_init(&nr_dentry_unused, 0);
+
 	/* 
 	 * A constructor could be added for stable state like the lists,
 	 * but it is probably not worth it because of the cache nature

fs/debugfs/inode.c

@@ -40,6 +40,7 @@ static struct inode *debugfs_get_inode(struct super_block *sb, int mode, dev_t d
 	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;
 		switch (mode & S_IFMT) {

fs/exofs/file.c

@@ -46,10 +46,6 @@ static int exofs_file_fsync(struct file *filp, int datasync)
 {
 	int ret;
 	struct inode *inode = filp->f_mapping->host;
-	struct writeback_control wbc = {
-		.sync_mode = WB_SYNC_ALL,
-		.nr_to_write = 0, /* metadata-only; caller takes care of data */
-	};
 	struct super_block *sb;
 
 	if (!(inode->i_state & I_DIRTY))
@@ -57,7 +53,7 @@ static int exofs_file_fsync(struct file *filp, int datasync)
 	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
 		return 0;
 
-	ret = sync_inode(inode, &wbc);
+	ret = sync_inode_metadata(inode, 1);
 
 	/* This is a good place to write the sb */
 	/* TODO: Sechedule an sb-sync on create */

fs/exofs/namei.c

@@ -153,7 +153,7 @@ static int exofs_link(struct dentry *old_dentry, struct inode *dir,
 
 	inode->i_ctime = CURRENT_TIME;
 	inode_inc_link_count(inode);
-	atomic_inc(&inode->i_count);
+	ihold(inode);
 
 	return exofs_add_nondir(dentry, inode);
 }

fs/exportfs/expfs.c

@@ -74,21 +74,20 @@ static struct dentry *
 find_disconnected_root(struct dentry *dentry)
 {
 	dget(dentry);
-	spin_lock(&dentry->d_lock);
-	while (!IS_ROOT(dentry) &&
-	       (dentry->d_parent->d_flags & DCACHE_DISCONNECTED)) {
-		struct dentry *parent = dentry->d_parent;
-		dget(parent);
-		spin_unlock(&dentry->d_lock);
+	while (!IS_ROOT(dentry)) {
+		struct dentry *parent = dget_parent(dentry);
+
+		if (!(parent->d_flags & DCACHE_DISCONNECTED)) {
+			dput(parent);
+			break;
+		}
+
 		dput(dentry);
 		dentry = parent;
-		spin_lock(&dentry->d_lock);
 	}
-	spin_unlock(&dentry->d_lock);
 	return dentry;
 }
 
-
 /*
  * Make sure target_dir is fully connected to the dentry tree.
  *

fs/ext2/dir.c

@@ -98,7 +98,7 @@ static int ext2_commit_chunk(struct page *page, loff_t pos, unsigned len)
 	if (IS_DIRSYNC(dir)) {
 		err = write_one_page(page, 1);
 		if (!err)
-			err = ext2_sync_inode(dir);
+			err = sync_inode_metadata(dir, 1);
 	} else {
 		unlock_page(page);
 	}

fs/ext2/ext2.h

@@ -120,7 +120,6 @@ extern unsigned long ext2_count_free (struct buffer_head *, unsigned);
 extern struct inode *ext2_iget (struct super_block *, unsigned long);
 extern int ext2_write_inode (struct inode *, struct writeback_control *);
 extern void ext2_evict_inode(struct inode *);
-extern int ext2_sync_inode (struct inode *);
 extern int ext2_get_block(struct inode *, sector_t, struct buffer_head *, int);
 extern int ext2_setattr (struct dentry *, struct iattr *);
 extern void ext2_set_inode_flags(struct inode *inode);

fs/ext2/inode.c

@@ -1203,7 +1203,7 @@ static int ext2_setsize(struct inode *inode, loff_t newsize)
 	inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC;
 	if (inode_needs_sync(inode)) {
 		sync_mapping_buffers(inode->i_mapping);
-		ext2_sync_inode (inode);
+		sync_inode_metadata(inode, 1);
 	} else {
 		mark_inode_dirty(inode);
 	}
@@ -1523,15 +1523,6 @@ int ext2_write_inode(struct inode *inode, struct writeback_control *wbc)
 	return __ext2_write_inode(inode, wbc->sync_mode == WB_SYNC_ALL);
 }
 
-int ext2_sync_inode(struct inode *inode)
-{
-	struct writeback_control wbc = {
-		.sync_mode = WB_SYNC_ALL,
-		.nr_to_write = 0,	/* sys_fsync did this */
-	};
-	return sync_inode(inode, &wbc);
-}
-
 int ext2_setattr(struct dentry *dentry, struct iattr *iattr)
 {
 	struct inode *inode = dentry->d_inode;

fs/ext2/namei.c

@@ -206,7 +206,7 @@ static int ext2_link (struct dentry * old_dentry, struct inode * dir,
 
 	inode->i_ctime = CURRENT_TIME_SEC;
 	inode_inc_link_count(inode);
-	atomic_inc(&inode->i_count);
+	ihold(inode);
 
 	err = ext2_add_link(dentry, inode);
 	if (!err) {

fs/ext2/super.c

@@ -1221,9 +1221,7 @@ static int ext2_remount (struct super_block * sb, int * flags, char * data)
 	}
 
 	es = sbi->s_es;
-	if (((sbi->s_mount_opt & EXT2_MOUNT_XIP) !=
-	    (old_mount_opt & EXT2_MOUNT_XIP)) &&
-	    invalidate_inodes(sb)) {
+	if ((sbi->s_mount_opt ^ old_mount_opt) & EXT2_MOUNT_XIP) {
 		ext2_msg(sb, KERN_WARNING, "warning: refusing change of "
 			 "xip flag with busy inodes while remounting");
 		sbi->s_mount_opt &= ~EXT2_MOUNT_XIP;

fs/ext2/xattr.c

@@ -699,7 +699,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
 	EXT2_I(inode)->i_file_acl = new_bh ? new_bh->b_blocknr : 0;
 	inode->i_ctime = CURRENT_TIME_SEC;
 	if (IS_SYNC(inode)) {
-		error = ext2_sync_inode (inode);
+		error = sync_inode_metadata(inode, 1);
 		/* In case sync failed due to ENOSPC the inode was actually
 		 * written (only some dirty data were not) so we just proceed
 		 * as if nothing happened and cleanup the unused block */

fs/ext3/inode.c

@@ -1696,8 +1696,8 @@ static int ext3_journalled_writepage(struct page *page,
 		 * doesn't seem much point in redirtying the page here.
 		 */
 		ClearPageChecked(page);
-		ret = block_prepare_write(page, 0, PAGE_CACHE_SIZE,
-					ext3_get_block);
+		ret = __block_write_begin(page, 0, PAGE_CACHE_SIZE,
+					  ext3_get_block);
 		if (ret != 0) {
 			ext3_journal_stop(handle);
 			goto out_unlock;

fs/ext3/namei.c

@@ -2260,7 +2260,7 @@ retry:
 
 	inode->i_ctime = CURRENT_TIME_SEC;
 	inc_nlink(inode);
-	atomic_inc(&inode->i_count);
+	ihold(inode);
 
 	err = ext3_add_entry(handle, dentry, inode);
 	if (!err) {

fs/ext4/inode.c

@@ -1538,10 +1538,10 @@ static int do_journal_get_write_access(handle_t *handle,
 	if (!buffer_mapped(bh) || buffer_freed(bh))
 		return 0;
 	/*
-	 * __block_prepare_write() could have dirtied some buffers. Clean
+	 * __block_write_begin() could have dirtied some buffers. Clean
 	 * the dirty bit as jbd2_journal_get_write_access() could complain
 	 * otherwise about fs integrity issues. Setting of the dirty bit
-	 * by __block_prepare_write() isn't a real problem here as we clear
+	 * by __block_write_begin() isn't a real problem here as we clear
 	 * the bit before releasing a page lock and thus writeback cannot
 	 * ever write the buffer.
 	 */
@@ -2550,8 +2550,7 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
 		if (buffer_delay(bh))
 			return 0; /* Not sure this could or should happen */
 		/*
-		 * XXX: __block_prepare_write() unmaps passed block,
-		 * is it OK?
+		 * XXX: __block_write_begin() unmaps passed block, is it OK?
 		 */
 		ret = ext4_da_reserve_space(inode, iblock);
 		if (ret)
@@ -2583,7 +2582,7 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
 /*
  * This function is used as a standard get_block_t calback function
  * when there is no desire to allocate any blocks.  It is used as a
- * callback function for block_prepare_write() and block_write_full_page().
+ * callback function for block_write_begin() and block_write_full_page().
  * These functions should only try to map a single block at a time.
  *
  * Since this function doesn't do block allocations even if the caller
@@ -2743,7 +2742,7 @@ static int ext4_writepage(struct page *page,
 		 * all are mapped and non delay. We don't want to
 		 * do block allocation here.
 		 */
-		ret = block_prepare_write(page, 0, len,
+		ret = __block_write_begin(page, 0, len,
 					  noalloc_get_block_write);
 		if (!ret) {
 			page_bufs = page_buffers(page);

fs/ext4/mballoc.c

@@ -2373,6 +2373,7 @@ static int ext4_mb_init_backend(struct super_block *sb)
 		printk(KERN_ERR "EXT4-fs: can't get new inode\n");
 		goto err_freesgi;
 	}
+	sbi->s_buddy_cache->i_ino = get_next_ino();
 	EXT4_I(sbi->s_buddy_cache)->i_disksize = 0;
 	for (i = 0; i < ngroups; i++) {
 		desc = ext4_get_group_desc(sb, i, NULL);

fs/ext4/namei.c

@@ -2312,7 +2312,7 @@ retry:
 
 	inode->i_ctime = ext4_current_time(inode);
 	ext4_inc_count(handle, inode);
-	atomic_inc(&inode->i_count);
+	ihold(inode);
 
 	err = ext4_add_entry(handle, dentry, inode);
 	if (!err) {

fs/freevxfs/vxfs_inode.c

@@ -260,6 +260,7 @@ vxfs_get_fake_inode(struct super_block *sbp, struct vxfs_inode_info *vip)
 	struct inode			*ip = NULL;
 
 	if ((ip = new_inode(sbp))) {
+		ip->i_ino = get_next_ino();
 		vxfs_iinit(ip, vip);
 		ip->i_mapping->a_ops = &vxfs_aops;
 	}

fs/fs-writeback.c

@@ -79,6 +79,11 @@ static inline struct backing_dev_info *inode_to_bdi(struct inode *inode)
 	return sb->s_bdi;
 }
 
+static inline struct inode *wb_inode(struct list_head *head)
+{
+	return list_entry(head, struct inode, i_wb_list);
+}
+
 static void bdi_queue_work(struct backing_dev_info *bdi,
 		struct wb_writeback_work *work)
 {
@@ -172,11 +177,11 @@ static void redirty_tail(struct inode *inode)
 	if (!list_empty(&wb->b_dirty)) {
 		struct inode *tail;
 
-		tail = list_entry(wb->b_dirty.next, struct inode, i_list);
+		tail = wb_inode(wb->b_dirty.next);
 		if (time_before(inode->dirtied_when, tail->dirtied_when))
 			inode->dirtied_when = jiffies;
 	}
-	list_move(&inode->i_list, &wb->b_dirty);
+	list_move(&inode->i_wb_list, &wb->b_dirty);
 }
 
 /*
@@ -186,7 +191,7 @@ static void requeue_io(struct inode *inode)
 {
 	struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
 
-	list_move(&inode->i_list, &wb->b_more_io);
+	list_move(&inode->i_wb_list, &wb->b_more_io);
 }
 
 static void inode_sync_complete(struct inode *inode)
@@ -227,14 +232,14 @@ static void move_expired_inodes(struct list_head *delaying_queue,
 	int do_sb_sort = 0;
 
 	while (!list_empty(delaying_queue)) {
-		inode = list_entry(delaying_queue->prev, struct inode, i_list);
+		inode = wb_inode(delaying_queue->prev);
 		if (older_than_this &&
 		    inode_dirtied_after(inode, *older_than_this))
 			break;
 		if (sb && sb != inode->i_sb)
 			do_sb_sort = 1;
 		sb = inode->i_sb;
-		list_move(&inode->i_list, &tmp);
+		list_move(&inode->i_wb_list, &tmp);
 	}
 
 	/* just one sb in list, splice to dispatch_queue and we're done */
@@ -245,12 +250,11 @@ static void move_expired_inodes(struct list_head *delaying_queue,
 
 	/* Move inodes from one superblock together */
 	while (!list_empty(&tmp)) {
-		inode = list_entry(tmp.prev, struct inode, i_list);
-		sb = inode->i_sb;
+		sb = wb_inode(tmp.prev)->i_sb;
 		list_for_each_prev_safe(pos, node, &tmp) {
-			inode = list_entry(pos, struct inode, i_list);
+			inode = wb_inode(pos);
 			if (inode->i_sb == sb)
-				list_move(&inode->i_list, dispatch_queue);
+				list_move(&inode->i_wb_list, dispatch_queue);
 		}
 	}
 }
@@ -408,16 +412,13 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 			 * completion.
 			 */
 			redirty_tail(inode);
-		} else if (atomic_read(&inode->i_count)) {
-			/*
-			 * The inode is clean, inuse
-			 */
-			list_move(&inode->i_list, &inode_in_use);
 		} else {
 			/*
-			 * The inode is clean, unused
+			 * The inode is clean.  At this point we either have
+			 * a reference to the inode or it's on it's way out.
+			 * No need to add it back to the LRU.
 			 */
-			list_move(&inode->i_list, &inode_unused);
+			list_del_init(&inode->i_wb_list);
 		}
 	}
 	inode_sync_complete(inode);
@@ -465,8 +466,7 @@ static int writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb,
 {
 	while (!list_empty(&wb->b_io)) {
 		long pages_skipped;
-		struct inode *inode = list_entry(wb->b_io.prev,
-						 struct inode, i_list);
+		struct inode *inode = wb_inode(wb->b_io.prev);
 
 		if (inode->i_sb != sb) {
 			if (only_this_sb) {
@@ -487,10 +487,16 @@ static int writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb,
 			return 0;
 		}
 
-		if (inode->i_state & (I_NEW | I_WILL_FREE)) {
+		/*
+		 * Don't bother with new inodes or inodes beeing freed, first
+		 * kind does not need peridic writeout yet, and for the latter
+		 * kind writeout is handled by the freer.
+		 */
+		if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
 			requeue_io(inode);
 			continue;
 		}
+
 		/*
 		 * Was this inode dirtied after sync_sb_inodes was called?
 		 * This keeps sync from extra jobs and livelock.
@@ -498,7 +504,6 @@ static int writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb,
 		if (inode_dirtied_after(inode, wbc->wb_start))
 			return 1;
 
-		BUG_ON(inode->i_state & I_FREEING);
 		__iget(inode);
 		pages_skipped = wbc->pages_skipped;
 		writeback_single_inode(inode, wbc);
@@ -536,8 +541,7 @@ void writeback_inodes_wb(struct bdi_writeback *wb,
 		queue_io(wb, wbc->older_than_this);
 
 	while (!list_empty(&wb->b_io)) {
-		struct inode *inode = list_entry(wb->b_io.prev,
-						 struct inode, i_list);
+		struct inode *inode = wb_inode(wb->b_io.prev);
 		struct super_block *sb = inode->i_sb;
 
 		if (!pin_sb_for_writeback(sb)) {
@@ -675,8 +679,7 @@ static long wb_writeback(struct bdi_writeback *wb,
 		 */
 		spin_lock(&inode_lock);
 		if (!list_empty(&wb->b_more_io))  {
-			inode = list_entry(wb->b_more_io.prev,
-						struct inode, i_list);
+			inode = wb_inode(wb->b_more_io.prev);
 			trace_wbc_writeback_wait(&wbc, wb->bdi);
 			inode_wait_for_writeback(inode);
 		}
@@ -727,7 +730,7 @@ static long wb_check_old_data_flush(struct bdi_writeback *wb)
 	 */
 	nr_pages = global_page_state(NR_FILE_DIRTY) +
 			global_page_state(NR_UNSTABLE_NFS) +
-			(inodes_stat.nr_inodes - inodes_stat.nr_unused);
+			get_nr_dirty_inodes();
 
 	if (nr_pages) {
 		struct wb_writeback_work work = {
@@ -966,7 +969,7 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 		 * dirty list.  Add blockdev inodes as well.
 		 */
 		if (!S_ISBLK(inode->i_mode)) {
-			if (hlist_unhashed(&inode->i_hash))
+			if (inode_unhashed(inode))
 				goto out;
 		}
 		if (inode->i_state & I_FREEING)
@@ -994,7 +997,7 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 			}
 
 			inode->dirtied_when = jiffies;
-			list_move(&inode->i_list, &bdi->wb.b_dirty);
+			list_move(&inode->i_wb_list, &bdi->wb.b_dirty);
 		}
 	}
 out:
@@ -1094,8 +1097,7 @@ void writeback_inodes_sb(struct super_block *sb)
 
 	WARN_ON(!rwsem_is_locked(&sb->s_umount));
 
-	work.nr_pages = nr_dirty + nr_unstable +
-			(inodes_stat.nr_inodes - inodes_stat.nr_unused);
+	work.nr_pages = nr_dirty + nr_unstable + get_nr_dirty_inodes();
 
 	bdi_queue_work(sb->s_bdi, &work);
 	wait_for_completion(&done);
@@ -1202,3 +1204,23 @@ int sync_inode(struct inode *inode, struct writeback_control *wbc)
 	return ret;
 }
 EXPORT_SYMBOL(sync_inode);
+
+/**
+ * sync_inode - write an inode to disk
+ * @inode: the inode to sync
+ * @wait: wait for I/O to complete.
+ *
+ * Write an inode to disk and adjust it's dirty state after completion.
+ *
+ * Note: only writes the actual inode, no associated data or other metadata.
+ */
+int sync_inode_metadata(struct inode *inode, int wait)
+{
+	struct writeback_control wbc = {
+		.sync_mode = wait ? WB_SYNC_ALL : WB_SYNC_NONE,
+		.nr_to_write = 0, /* metadata-only */
+	};
+
+	return sync_inode(inode, &wbc);
+}
+EXPORT_SYMBOL(sync_inode_metadata);

fs/fuse/control.c

@@ -222,6 +222,7 @@ static struct dentry *fuse_ctl_add_dentry(struct dentry *parent,
 	if (!inode)
 		return NULL;
 
+	inode->i_ino = get_next_ino();
 	inode->i_mode = mode;
 	inode->i_uid = fc->user_id;
 	inode->i_gid = fc->group_id;

fs/gfs2/aops.c

@@ -618,7 +618,6 @@ static int gfs2_write_begin(struct file *file, struct address_space *mapping,
 	struct gfs2_alloc *al = NULL;
 	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
 	unsigned from = pos & (PAGE_CACHE_SIZE - 1);
-	unsigned to = from + len;
 	struct page *page;
 
 	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &ip->i_gh);
@@ -691,7 +690,7 @@ static int gfs2_write_begin(struct file *file, struct address_space *mapping,
 	}
 
 prepare_write:
-	error = block_prepare_write(page, from, to, gfs2_block_map);
+	error = __block_write_begin(page, from, len, gfs2_block_map);
 out:
 	if (error == 0)
 		return 0;

fs/gfs2/ops_fstype.c

@@ -1219,7 +1219,6 @@ fail_sb:
 fail_locking:
 	init_locking(sdp, &mount_gh, UNDO);
 fail_lm:
-	invalidate_inodes(sb);
 	gfs2_gl_hash_clear(sdp);
 	gfs2_lm_unmount(sdp);
 fail_sys:

fs/gfs2/ops_inode.c

@@ -255,7 +255,7 @@ out_parent:
 	gfs2_holder_uninit(ghs);
 	gfs2_holder_uninit(ghs + 1);
 	if (!error) {
-		atomic_inc(&inode->i_count);
+		ihold(inode);
 		d_instantiate(dentry, inode);
 		mark_inode_dirty(inode);
 	}
@@ -1294,7 +1294,7 @@ static int write_empty_blocks(struct page *page, unsigned from, unsigned to)
 	int error;
 
 	if (!page_has_buffers(page)) {
-		error = block_prepare_write(page, from, to, gfs2_block_map);
+		error = __block_write_begin(page, from, to - from, gfs2_block_map);
 		if (unlikely(error))
 			return error;
 
@@ -1313,7 +1313,7 @@ static int write_empty_blocks(struct page *page, unsigned from, unsigned to)
 		next += bh->b_size;
 		if (buffer_mapped(bh)) {
 			if (end) {
-				error = block_prepare_write(page, start, end,
+				error = __block_write_begin(page, start, end - start,
 							    gfs2_block_map);
 				if (unlikely(error))
 					return error;
@@ -1328,7 +1328,7 @@ static int write_empty_blocks(struct page *page, unsigned from, unsigned to)
 	} while (next < to);
 
 	if (end) {
-		error = block_prepare_write(page, start, end, gfs2_block_map);
+		error = __block_write_begin(page, start, end - start, gfs2_block_map);
 		if (unlikely(error))
 			return error;
 		empty_write_end(page, start, end);

fs/gfs2/super.c

@@ -857,7 +857,6 @@ restart:
 	gfs2_clear_rgrpd(sdp);
 	gfs2_jindex_free(sdp);
 	/*  Take apart glock structures and buffer lists  */
-	invalidate_inodes(sdp->sd_vfs);
 	gfs2_gl_hash_clear(sdp);
 	/*  Unmount the locking protocol  */
 	gfs2_lm_unmount(sdp);

fs/hfs/hfs_fs.h

@@ -147,8 +147,6 @@ struct hfs_sb_info {
 	u16 blockoffset;
 
 	int fs_div;
-
-	struct hlist_head rsrc_inodes;
 };
 
 #define HFS_FLG_BITMAP_DIRTY	0
@@ -254,17 +252,6 @@ static inline void hfs_bitmap_dirty(struct super_block *sb)
 	sb->s_dirt = 1;
 }
 
-static inline void hfs_buffer_sync(struct buffer_head *bh)
-{
-	while (buffer_locked(bh)) {
-		wait_on_buffer(bh);
-	}
-	if (buffer_dirty(bh)) {
-		ll_rw_block(WRITE, 1, &bh);
-		wait_on_buffer(bh);
-	}
-}
-
 #define sb_bread512(sb, sec, data) ({			\
 	struct buffer_head *__bh;			\
 	sector_t __block;				\

fs/hfs/inode.c

@@ -524,7 +524,7 @@ static struct dentry *hfs_file_lookup(struct inode *dir, struct dentry *dentry,
 	HFS_I(inode)->rsrc_inode = dir;
 	HFS_I(dir)->rsrc_inode = inode;
 	igrab(dir);
-	hlist_add_head(&inode->i_hash, &HFS_SB(dir->i_sb)->rsrc_inodes);
+	hlist_add_fake(&inode->i_hash);
 	mark_inode_dirty(inode);
 out:
 	d_add(dentry, inode);

fs/hfs/mdb.c

@@ -220,7 +220,7 @@ int hfs_mdb_get(struct super_block *sb)
 		mdb->drLsMod = hfs_mtime();
 
 		mark_buffer_dirty(HFS_SB(sb)->mdb_bh);
-		hfs_buffer_sync(HFS_SB(sb)->mdb_bh);
+		sync_dirty_buffer(HFS_SB(sb)->mdb_bh);
 	}
 
 	return 0;
@@ -287,7 +287,7 @@ void hfs_mdb_commit(struct super_block *sb)
 		HFS_SB(sb)->alt_mdb->drAtrb |= cpu_to_be16(HFS_SB_ATTRIB_UNMNT);
 		HFS_SB(sb)->alt_mdb->drAtrb &= cpu_to_be16(~HFS_SB_ATTRIB_INCNSTNT);
 		mark_buffer_dirty(HFS_SB(sb)->alt_mdb_bh);
-		hfs_buffer_sync(HFS_SB(sb)->alt_mdb_bh);
+		sync_dirty_buffer(HFS_SB(sb)->alt_mdb_bh);
 	}
 
 	if (test_and_clear_bit(HFS_FLG_BITMAP_DIRTY, &HFS_SB(sb)->flags)) {

fs/hfs/super.c

@@ -382,7 +382,6 @@ static int hfs_fill_super(struct super_block *sb, void *data, int silent)
 		return -ENOMEM;
 
 	sb->s_fs_info = sbi;
-	INIT_HLIST_HEAD(&sbi->rsrc_inodes);
 
 	res = -EINVAL;
 	if (!parse_options((char *)data, sbi)) {

fs/hfsplus/dir.c

@@ -286,7 +286,7 @@ static int hfsplus_link(struct dentry *src_dentry, struct inode *dst_dir,
 
 	inc_nlink(inode);
 	hfsplus_instantiate(dst_dentry, inode, cnid);
-	atomic_inc(&inode->i_count);
+	ihold(inode);
 	inode->i_ctime = CURRENT_TIME_SEC;
 	mark_inode_dirty(inode);
 	sbi->file_count++;

fs/hfsplus/inode.c

@@ -211,7 +211,7 @@ static struct dentry *hfsplus_file_lookup(struct inode *dir, struct dentry *dent
 	 * appear hashed, but do not put on any lists.  hlist_del()
 	 * will work fine and require no locking.
 	 */
-	inode->i_hash.pprev = &inode->i_hash.next;
+	hlist_add_fake(&inode->i_hash);
 
 	mark_inode_dirty(inode);
 out:

fs/hugetlbfs/inode.c

@@ -456,6 +456,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, uid_t uid,
 	inode = new_inode(sb);
 	if (inode) {
 		struct hugetlbfs_inode_info *info;
+		inode->i_ino = get_next_ino();
 		inode->i_mode = mode;
 		inode->i_uid = uid;
 		inode->i_gid = gid;

fs/inode.c

@@ -29,7 +29,6 @@
 /*
  * This is needed for the following functions:
  *  - inode_has_buffers
- *  - invalidate_inode_buffers
  *  - invalidate_bdev
  *
  * FIXME: remove all knowledge of the buffer layer from this file
@@ -73,8 +72,7 @@ static unsigned int i_hash_shift __read_mostly;
  * allowing for low-overhead inode sync() operations.
  */
 
-LIST_HEAD(inode_in_use);
-LIST_HEAD(inode_unused);
+static LIST_HEAD(inode_lru);
 static struct hlist_head *inode_hashtable __read_mostly;
 
 /*
@@ -104,8 +102,41 @@ static DECLARE_RWSEM(iprune_sem);
  */
 struct inodes_stat_t inodes_stat;
 
+static struct percpu_counter nr_inodes __cacheline_aligned_in_smp;
+static struct percpu_counter nr_inodes_unused __cacheline_aligned_in_smp;
+
 static struct kmem_cache *inode_cachep __read_mostly;
 
+static inline int get_nr_inodes(void)
+{
+	return percpu_counter_sum_positive(&nr_inodes);
+}
+
+static inline int get_nr_inodes_unused(void)
+{
+	return percpu_counter_sum_positive(&nr_inodes_unused);
+}
+
+int get_nr_dirty_inodes(void)
+{
+	int nr_dirty = get_nr_inodes() - get_nr_inodes_unused();
+	return nr_dirty > 0 ? nr_dirty : 0;
+
+}
+
+/*
+ * Handle nr_inode sysctl
+ */
+#ifdef CONFIG_SYSCTL
+int proc_nr_inodes(ctl_table *table, int write,
+		   void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	inodes_stat.nr_inodes = get_nr_inodes();
+	inodes_stat.nr_unused = get_nr_inodes_unused();
+	return proc_dointvec(table, write, buffer, lenp, ppos);
+}
+#endif
+
 static void wake_up_inode(struct inode *inode)
 {
 	/*
@@ -193,6 +224,8 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	inode->i_fsnotify_mask = 0;
 #endif
 
+	percpu_counter_inc(&nr_inodes);
+
 	return 0;
 out:
 	return -ENOMEM;
@@ -233,11 +266,13 @@ void __destroy_inode(struct inode *inode)
 	if (inode->i_default_acl && inode->i_default_acl != ACL_NOT_CACHED)
 		posix_acl_release(inode->i_default_acl);
 #endif
+	percpu_counter_dec(&nr_inodes);
 }
 EXPORT_SYMBOL(__destroy_inode);
 
-void destroy_inode(struct inode *inode)
+static void destroy_inode(struct inode *inode)
 {
+	BUG_ON(!list_empty(&inode->i_lru));
 	__destroy_inode(inode);
 	if (inode->i_sb->s_op->destroy_inode)
 		inode->i_sb->s_op->destroy_inode(inode);
@@ -256,6 +291,8 @@ void inode_init_once(struct inode *inode)
 	INIT_HLIST_NODE(&inode->i_hash);
 	INIT_LIST_HEAD(&inode->i_dentry);
 	INIT_LIST_HEAD(&inode->i_devices);
+	INIT_LIST_HEAD(&inode->i_wb_list);
+	INIT_LIST_HEAD(&inode->i_lru);
 	INIT_RADIX_TREE(&inode->i_data.page_tree, GFP_ATOMIC);
 	spin_lock_init(&inode->i_data.tree_lock);
 	spin_lock_init(&inode->i_data.i_mmap_lock);
@@ -282,14 +319,109 @@ static void init_once(void *foo)
  */
 void __iget(struct inode *inode)
 {
-	if (atomic_inc_return(&inode->i_count) != 1)
-		return;
+	atomic_inc(&inode->i_count);
+}
+
+/*
+ * get additional reference to inode; caller must already hold one.
+ */
+void ihold(struct inode *inode)
+{
+	WARN_ON(atomic_inc_return(&inode->i_count) < 2);
+}
+EXPORT_SYMBOL(ihold);
+
+static void inode_lru_list_add(struct inode *inode)
+{
+	if (list_empty(&inode->i_lru)) {
+		list_add(&inode->i_lru, &inode_lru);
+		percpu_counter_inc(&nr_inodes_unused);
+	}
+}
 
-	if (!(inode->i_state & (I_DIRTY|I_SYNC)))
-		list_move(&inode->i_list, &inode_in_use);
-	inodes_stat.nr_unused--;
+static void inode_lru_list_del(struct inode *inode)
+{
+	if (!list_empty(&inode->i_lru)) {
+		list_del_init(&inode->i_lru);
+		percpu_counter_dec(&nr_inodes_unused);
+	}
+}
+
+static inline void __inode_sb_list_add(struct inode *inode)
+{
+	list_add(&inode->i_sb_list, &inode->i_sb->s_inodes);
 }
 
+/**
+ * inode_sb_list_add - add inode to the superblock list of inodes
+ * @inode: inode to add
+ */
+void inode_sb_list_add(struct inode *inode)
+{
+	spin_lock(&inode_lock);
+	__inode_sb_list_add(inode);
+	spin_unlock(&inode_lock);
+}
+EXPORT_SYMBOL_GPL(inode_sb_list_add);
+
+static inline void __inode_sb_list_del(struct inode *inode)
+{
+	list_del_init(&inode->i_sb_list);
+}
+
+static unsigned long hash(struct super_block *sb, unsigned long hashval)
+{
+	unsigned long tmp;
+
+	tmp = (hashval * (unsigned long)sb) ^ (GOLDEN_RATIO_PRIME + hashval) /
+			L1_CACHE_BYTES;
+	tmp = tmp ^ ((tmp ^ GOLDEN_RATIO_PRIME) >> I_HASHBITS);
+	return tmp & I_HASHMASK;
+}
+
+/**
+ *	__insert_inode_hash - hash an inode
+ *	@inode: unhashed inode
+ *	@hashval: unsigned long value used to locate this object in the
+ *		inode_hashtable.
+ *
+ *	Add an inode to the inode hash for this superblock.
+ */
+void __insert_inode_hash(struct inode *inode, unsigned long hashval)
+{
+	struct hlist_head *b = inode_hashtable + hash(inode->i_sb, hashval);
+
+	spin_lock(&inode_lock);
+	hlist_add_head(&inode->i_hash, b);
+	spin_unlock(&inode_lock);
+}
+EXPORT_SYMBOL(__insert_inode_hash);
+
+/**
+ *	__remove_inode_hash - remove an inode from the hash
+ *	@inode: inode to unhash
+ *
+ *	Remove an inode from the superblock.
+ */
+static void __remove_inode_hash(struct inode *inode)
+{
+	hlist_del_init(&inode->i_hash);
+}
+
+/**
+ *	remove_inode_hash - remove an inode from the hash
+ *	@inode: inode to unhash
+ *
+ *	Remove an inode from the superblock.
+ */
+void remove_inode_hash(struct inode *inode)
+{
+	spin_lock(&inode_lock);
+	hlist_del_init(&inode->i_hash);
+	spin_unlock(&inode_lock);
+}
+EXPORT_SYMBOL(remove_inode_hash);
+
 void end_writeback(struct inode *inode)
 {
 	might_sleep();
@@ -328,101 +460,113 @@ static void evict(struct inode *inode)
  */
 static void dispose_list(struct list_head *head)
 {
-	int nr_disposed = 0;
-
 	while (!list_empty(head)) {
 		struct inode *inode;
 
-		inode = list_first_entry(head, struct inode, i_list);
-		list_del(&inode->i_list);
+		inode = list_first_entry(head, struct inode, i_lru);
+		list_del_init(&inode->i_lru);
 
 		evict(inode);
 
 		spin_lock(&inode_lock);
-		hlist_del_init(&inode->i_hash);
-		list_del_init(&inode->i_sb_list);
+		__remove_inode_hash(inode);
+		__inode_sb_list_del(inode);
 		spin_unlock(&inode_lock);
 
 		wake_up_inode(inode);
 		destroy_inode(inode);
-		nr_disposed++;
 	}
-	spin_lock(&inode_lock);
-	inodes_stat.nr_inodes -= nr_disposed;
-	spin_unlock(&inode_lock);
 }
 
-/*
- * Invalidate all inodes for a device.
+/**
+ * evict_inodes	- evict all evictable inodes for a superblock
+ * @sb:		superblock to operate on
+ *
+ * Make sure that no inodes with zero refcount are retained.  This is
+ * called by superblock shutdown after having MS_ACTIVE flag removed,
+ * so any inode reaching zero refcount during or after that call will
+ * be immediately evicted.
  */
-static int invalidate_list(struct list_head *head, struct list_head *dispose)
+void evict_inodes(struct super_block *sb)
 {
-	struct list_head *next;
-	int busy = 0, count = 0;
-
-	next = head->next;
-	for (;;) {
-		struct list_head *tmp = next;
-		struct inode *inode;
+	struct inode *inode, *next;
+	LIST_HEAD(dispose);
 
-		/*
-		 * We can reschedule here without worrying about the list's
-		 * consistency because the per-sb list of inodes must not
-		 * change during umount anymore, and because iprune_sem keeps
-		 * shrink_icache_memory() away.
-		 */
-		cond_resched_lock(&inode_lock);
+	down_write(&iprune_sem);
 
-		next = next->next;
-		if (tmp == head)
-			break;
-		inode = list_entry(tmp, struct inode, i_sb_list);
-		if (inode->i_state & I_NEW)
+	spin_lock(&inode_lock);
+	list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
+		if (atomic_read(&inode->i_count))
 			continue;
-		invalidate_inode_buffers(inode);
-		if (!atomic_read(&inode->i_count)) {
-			list_move(&inode->i_list, dispose);
-			WARN_ON(inode->i_state & I_NEW);
-			inode->i_state |= I_FREEING;
-			count++;
+
+		if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
+			WARN_ON(1);
 			continue;
 		}
-		busy = 1;
+
+		inode->i_state |= I_FREEING;
+
+		/*
+		 * Move the inode off the IO lists and LRU once I_FREEING is
+		 * set so that it won't get moved back on there if it is dirty.
+		 */
+		list_move(&inode->i_lru, &dispose);
+		list_del_init(&inode->i_wb_list);
+		if (!(inode->i_state & (I_DIRTY | I_SYNC)))
+			percpu_counter_dec(&nr_inodes_unused);
 	}
-	/* only unused inodes may be cached with i_count zero */
-	inodes_stat.nr_unused -= count;
-	return busy;
+	spin_unlock(&inode_lock);
+
+	dispose_list(&dispose);
+	up_write(&iprune_sem);
 }
 
 /**
- *	invalidate_inodes	- discard the inodes on a device
- *	@sb: superblock
+ * invalidate_inodes	- attempt to free all inodes on a superblock
+ * @sb:		superblock to operate on
  *
- *	Discard all of the inodes for a given superblock. If the discard
- *	fails because there are busy inodes then a non zero value is returned.
- *	If the discard is successful all the inodes have been discarded.
+ * Attempts to free all inodes for a given superblock.  If there were any
+ * busy inodes return a non-zero value, else zero.
  */
 int invalidate_inodes(struct super_block *sb)
 {
-	int busy;
-	LIST_HEAD(throw_away);
+	int busy = 0;
+	struct inode *inode, *next;
+	LIST_HEAD(dispose);
 
 	down_write(&iprune_sem);
+
 	spin_lock(&inode_lock);
-	fsnotify_unmount_inodes(&sb->s_inodes);
-	busy = invalidate_list(&sb->s_inodes, &throw_away);
+	list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
+		if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE))
+			continue;
+		if (atomic_read(&inode->i_count)) {
+			busy = 1;
+			continue;
+		}
+
+		inode->i_state |= I_FREEING;
+
+		/*
+		 * Move the inode off the IO lists and LRU once I_FREEING is
+		 * set so that it won't get moved back on there if it is dirty.
+		 */
+		list_move(&inode->i_lru, &dispose);
+		list_del_init(&inode->i_wb_list);
+		if (!(inode->i_state & (I_DIRTY | I_SYNC)))
+			percpu_counter_dec(&nr_inodes_unused);
+	}
 	spin_unlock(&inode_lock);
 
-	dispose_list(&throw_away);
+	dispose_list(&dispose);
 	up_write(&iprune_sem);
 
 	return busy;
 }
-EXPORT_SYMBOL(invalidate_inodes);
 
 static int can_unuse(struct inode *inode)
 {
-	if (inode->i_state)
+	if (inode->i_state & ~I_REFERENCED)
 		return 0;
 	if (inode_has_buffers(inode))
 		return 0;
@@ -434,22 +578,24 @@ static int can_unuse(struct inode *inode)
 }
 
 /*
- * Scan `goal' inodes on the unused list for freeable ones. They are moved to
- * a temporary list and then are freed outside inode_lock by dispose_list().
+ * Scan `goal' inodes on the unused list for freeable ones. They are moved to a
+ * temporary list and then are freed outside inode_lock by dispose_list().
  *
  * Any inodes which are pinned purely because of attached pagecache have their
- * pagecache removed.  We expect the final iput() on that inode to add it to
- * the front of the inode_unused list.  So look for it there and if the
- * inode is still freeable, proceed.  The right inode is found 99.9% of the
- * time in testing on a 4-way.
+ * pagecache removed.  If the inode has metadata buffers attached to
+ * mapping->private_list then try to remove them.
  *
- * If the inode has metadata buffers attached to mapping->private_list then
- * try to remove them.
+ * If the inode has the I_REFERENCED flag set, then it means that it has been
+ * used recently - the flag is set in iput_final(). When we encounter such an
+ * inode, clear the flag and move it to the back of the LRU so it gets another
+ * pass through the LRU before it gets reclaimed. This is necessary because of
+ * the fact we are doing lazy LRU updates to minimise lock contention so the
+ * LRU does not have strict ordering. Hence we don't want to reclaim inodes
+ * with this flag set because they are the inodes that are out of order.
  */
 static void prune_icache(int nr_to_scan)
 {
 	LIST_HEAD(freeable);
-	int nr_pruned = 0;
 	int nr_scanned;
 	unsigned long reap = 0;
 
@@ -458,13 +604,26 @@ static void prune_icache(int nr_to_scan)
 	for (nr_scanned = 0; nr_scanned < nr_to_scan; nr_scanned++) {
 		struct inode *inode;
 
-		if (list_empty(&inode_unused))
+		if (list_empty(&inode_lru))
 			break;
 
-		inode = list_entry(inode_unused.prev, struct inode, i_list);
+		inode = list_entry(inode_lru.prev, struct inode, i_lru);
 
-		if (inode->i_state || atomic_read(&inode->i_count)) {
-			list_move(&inode->i_list, &inode_unused);
+		/*
+		 * Referenced or dirty inodes are still in use. Give them
+		 * another pass through the LRU as we canot reclaim them now.
+		 */
+		if (atomic_read(&inode->i_count) ||
+		    (inode->i_state & ~I_REFERENCED)) {
+			list_del_init(&inode->i_lru);
+			percpu_counter_dec(&nr_inodes_unused);
+			continue;
+		}
+
+		/* recently referenced inodes get one more pass */
+		if (inode->i_state & I_REFERENCED) {
+			list_move(&inode->i_lru, &inode_lru);
+			inode->i_state &= ~I_REFERENCED;
 			continue;
 		}
 		if (inode_has_buffers(inode) || inode->i_data.nrpages) {
@@ -476,18 +635,23 @@ static void prune_icache(int nr_to_scan)
 			iput(inode);
 			spin_lock(&inode_lock);
 
-			if (inode != list_entry(inode_unused.next,
-						struct inode, i_list))
+			if (inode != list_entry(inode_lru.next,
+						struct inode, i_lru))
 				continue;	/* wrong inode or list_empty */
 			if (!can_unuse(inode))
 				continue;
 		}
-		list_move(&inode->i_list, &freeable);
 		WARN_ON(inode->i_state & I_NEW);
 		inode->i_state |= I_FREEING;
-		nr_pruned++;
+
+		/*
+		 * Move the inode off the IO lists and LRU once I_FREEING is
+		 * set so that it won't get moved back on there if it is dirty.
+		 */
+		list_move(&inode->i_lru, &freeable);
+		list_del_init(&inode->i_wb_list);
+		percpu_counter_dec(&nr_inodes_unused);
 	}
-	inodes_stat.nr_unused -= nr_pruned;
 	if (current_is_kswapd())
 		__count_vm_events(KSWAPD_INODESTEAL, reap);
 	else
@@ -519,7 +683,7 @@ static int shrink_icache_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask)
 			return -1;
 		prune_icache(nr);
 	}
-	return (inodes_stat.nr_unused / 100) * sysctl_vfs_cache_pressure;
+	return (get_nr_inodes_unused() / 100) * sysctl_vfs_cache_pressure;
 }
 
 static struct shrinker icache_shrinker = {
@@ -530,9 +694,6 @@ static struct shrinker icache_shrinker = {
 static void __wait_on_freeing_inode(struct inode *inode);
 /*
  * Called with the inode lock held.
- * NOTE: we are not increasing the inode-refcount, you must call __iget()
- * by hand after calling find_inode now! This simplifies iunique and won't
- * add any additional branch in the common code.
  */
 static struct inode *find_inode(struct super_block *sb,
 				struct hlist_head *head,
@@ -552,9 +713,10 @@ repeat:
 			__wait_on_freeing_inode(inode);
 			goto repeat;
 		}
-		break;
+		__iget(inode);
+		return inode;
 	}
-	return node ? inode : NULL;
+	return NULL;
 }
 
 /*
@@ -577,53 +739,49 @@ repeat:
 			__wait_on_freeing_inode(inode);
 			goto repeat;
 		}
-		break;
+		__iget(inode);
+		return inode;
 	}
-	return node ? inode : NULL;
-}
-
-static unsigned long hash(struct super_block *sb, unsigned long hashval)
-{
-	unsigned long tmp;
-
-	tmp = (hashval * (unsigned long)sb) ^ (GOLDEN_RATIO_PRIME + hashval) /
-			L1_CACHE_BYTES;
-	tmp = tmp ^ ((tmp ^ GOLDEN_RATIO_PRIME) >> I_HASHBITS);
-	return tmp & I_HASHMASK;
-}
-
-static inline void
-__inode_add_to_lists(struct super_block *sb, struct hlist_head *head,
-			struct inode *inode)
-{
-	inodes_stat.nr_inodes++;
-	list_add(&inode->i_list, &inode_in_use);
-	list_add(&inode->i_sb_list, &sb->s_inodes);
-	if (head)
-		hlist_add_head(&inode->i_hash, head);
+	return NULL;
 }
 
-/**
- * inode_add_to_lists - add a new inode to relevant lists
- * @sb: superblock inode belongs to
- * @inode: inode to mark in use
+/*
+ * Each cpu owns a range of LAST_INO_BATCH numbers.
+ * 'shared_last_ino' is dirtied only once out of LAST_INO_BATCH allocations,
+ * to renew the exhausted range.
  *
- * When an inode is allocated it needs to be accounted for, added to the in use
- * list, the owning superblock and the inode hash. This needs to be done under
- * the inode_lock, so export a function to do this rather than the inode lock
- * itself. We calculate the hash list to add to here so it is all internal
- * which requires the caller to have already set up the inode number in the
- * inode to add.
+ * This does not significantly increase overflow rate because every CPU can
+ * consume at most LAST_INO_BATCH-1 unused inode numbers. So there is
+ * NR_CPUS*(LAST_INO_BATCH-1) wastage. At 4096 and 1024, this is ~0.1% of the
+ * 2^32 range, and is a worst-case. Even a 50% wastage would only increase
+ * overflow rate by 2x, which does not seem too significant.
+ *
+ * On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW
+ * error if st_ino won't fit in target struct field. Use 32bit counter
+ * here to attempt to avoid that.
  */
-void inode_add_to_lists(struct super_block *sb, struct inode *inode)
+#define LAST_INO_BATCH 1024
+static DEFINE_PER_CPU(unsigned int, last_ino);
+
+unsigned int get_next_ino(void)
 {
-	struct hlist_head *head = inode_hashtable + hash(sb, inode->i_ino);
+	unsigned int *p = &get_cpu_var(last_ino);
+	unsigned int res = *p;
 
-	spin_lock(&inode_lock);
-	__inode_add_to_lists(sb, head, inode);
-	spin_unlock(&inode_lock);
+#ifdef CONFIG_SMP
+	if (unlikely((res & (LAST_INO_BATCH-1)) == 0)) {
+		static atomic_t shared_last_ino;
+		int next = atomic_add_return(LAST_INO_BATCH, &shared_last_ino);
+
+		res = next - LAST_INO_BATCH;
+	}
+#endif
+
+	*p = ++res;
+	put_cpu_var(last_ino);
+	return res;
 }
-EXPORT_SYMBOL_GPL(inode_add_to_lists);
+EXPORT_SYMBOL(get_next_ino);
 
 /**
  *	new_inode 	- obtain an inode
@@ -639,12 +797,6 @@ EXPORT_SYMBOL_GPL(inode_add_to_lists);
  */
 struct inode *new_inode(struct super_block *sb)
 {
-	/*
-	 * On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW
-	 * error if st_ino won't fit in target struct field. Use 32bit counter
-	 * here to attempt to avoid that.
-	 */
-	static unsigned int last_ino;
 	struct inode *inode;
 
 	spin_lock_prefetch(&inode_lock);
@@ -652,8 +804,7 @@ struct inode *new_inode(struct super_block *sb)
 	inode = alloc_inode(sb);
 	if (inode) {
 		spin_lock(&inode_lock);
-		__inode_add_to_lists(sb, NULL, inode);
-		inode->i_ino = ++last_ino;
+		__inode_sb_list_add(inode);
 		inode->i_state = 0;
 		spin_unlock(&inode_lock);
 	}
@@ -664,7 +815,7 @@ EXPORT_SYMBOL(new_inode);
 void unlock_new_inode(struct inode *inode)
 {
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
-	if (inode->i_mode & S_IFDIR) {
+	if (S_ISDIR(inode->i_mode)) {
 		struct file_system_type *type = inode->i_sb->s_type;
 
 		/* Set new key only if filesystem hasn't already changed it */
@@ -721,7 +872,8 @@ static struct inode *get_new_inode(struct super_block *sb,
 			if (set(inode, data))
 				goto set_failed;
 
-			__inode_add_to_lists(sb, head, inode);
+			hlist_add_head(&inode->i_hash, head);
+			__inode_sb_list_add(inode);
 			inode->i_state = I_NEW;
 			spin_unlock(&inode_lock);
 
@@ -736,7 +888,6 @@ static struct inode *get_new_inode(struct super_block *sb,
 		 * us. Use the old inode instead of the one we just
 		 * allocated.
 		 */
-		__iget(old);
 		spin_unlock(&inode_lock);
 		destroy_inode(inode);
 		inode = old;
@@ -768,7 +919,8 @@ static struct inode *get_new_inode_fast(struct super_block *sb,
 		old = find_inode_fast(sb, head, ino);
 		if (!old) {
 			inode->i_ino = ino;
-			__inode_add_to_lists(sb, head, inode);
+			hlist_add_head(&inode->i_hash, head);
+			__inode_sb_list_add(inode);
 			inode->i_state = I_NEW;
 			spin_unlock(&inode_lock);
 
@@ -783,7 +935,6 @@ static struct inode *get_new_inode_fast(struct super_block *sb,
 		 * us. Use the old inode instead of the one we just
 		 * allocated.
 		 */
-		__iget(old);
 		spin_unlock(&inode_lock);
 		destroy_inode(inode);
 		inode = old;
@@ -792,6 +943,27 @@ static struct inode *get_new_inode_fast(struct super_block *sb,
 	return inode;
 }
 
+/*
+ * search the inode cache for a matching inode number.
+ * If we find one, then the inode number we are trying to
+ * allocate is not unique and so we should not use it.
+ *
+ * Returns 1 if the inode number is unique, 0 if it is not.
+ */
+static int test_inode_iunique(struct super_block *sb, unsigned long ino)
+{
+	struct hlist_head *b = inode_hashtable + hash(sb, ino);
+	struct hlist_node *node;
+	struct inode *inode;
+
+	hlist_for_each_entry(inode, node, b, i_hash) {
+		if (inode->i_ino == ino && inode->i_sb == sb)
+			return 0;
+	}
+
+	return 1;
+}
+
 /**
  *	iunique - get a unique inode number
  *	@sb: superblock
@@ -813,19 +985,18 @@ ino_t iunique(struct super_block *sb, ino_t max_reserved)
 	 * error if st_ino won't fit in target struct field. Use 32bit counter
 	 * here to attempt to avoid that.
 	 */
+	static DEFINE_SPINLOCK(iunique_lock);
 	static unsigned int counter;
-	struct inode *inode;
-	struct hlist_head *head;
 	ino_t res;
 
 	spin_lock(&inode_lock);
+	spin_lock(&iunique_lock);
 	do {
 		if (counter <= max_reserved)
 			counter = max_reserved + 1;
 		res = counter++;
-		head = inode_hashtable + hash(sb, res);
-		inode = find_inode_fast(sb, head, res);
-	} while (inode != NULL);
+	} while (!test_inode_iunique(sb, res));
+	spin_unlock(&iunique_lock);
 	spin_unlock(&inode_lock);
 
 	return res;
@@ -877,7 +1048,6 @@ static struct inode *ifind(struct super_block *sb,
 	spin_lock(&inode_lock);
 	inode = find_inode(sb, head, test, data);
 	if (inode) {
-		__iget(inode);
 		spin_unlock(&inode_lock);
 		if (likely(wait))
 			wait_on_inode(inode);
@@ -910,7 +1080,6 @@ static struct inode *ifind_fast(struct super_block *sb,
 	spin_lock(&inode_lock);
 	inode = find_inode_fast(sb, head, ino);
 	if (inode) {
-		__iget(inode);
 		spin_unlock(&inode_lock);
 		wait_on_inode(inode);
 		return inode;
@@ -1096,7 +1265,7 @@ int insert_inode_locked(struct inode *inode)
 		__iget(old);
 		spin_unlock(&inode_lock);
 		wait_on_inode(old);
-		if (unlikely(!hlist_unhashed(&old->i_hash))) {
+		if (unlikely(!inode_unhashed(old))) {
 			iput(old);
 			return -EBUSY;
 		}
@@ -1135,7 +1304,7 @@ int insert_inode_locked4(struct inode *inode, unsigned long hashval,
 		__iget(old);
 		spin_unlock(&inode_lock);
 		wait_on_inode(old);
-		if (unlikely(!hlist_unhashed(&old->i_hash))) {
+		if (unlikely(!inode_unhashed(old))) {
 			iput(old);
 			return -EBUSY;
 		}
@@ -1144,36 +1313,6 @@ int insert_inode_locked4(struct inode *inode, unsigned long hashval,
 }
 EXPORT_SYMBOL(insert_inode_locked4);
 
-/**
- *	__insert_inode_hash - hash an inode
- *	@inode: unhashed inode
- *	@hashval: unsigned long value used to locate this object in the
- *		inode_hashtable.
- *
- *	Add an inode to the inode hash for this superblock.
- */
-void __insert_inode_hash(struct inode *inode, unsigned long hashval)
-{
-	struct hlist_head *head = inode_hashtable + hash(inode->i_sb, hashval);
-	spin_lock(&inode_lock);
-	hlist_add_head(&inode->i_hash, head);
-	spin_unlock(&inode_lock);
-}
-EXPORT_SYMBOL(__insert_inode_hash);
-
-/**
- *	remove_inode_hash - remove an inode from the hash
- *	@inode: inode to unhash
- *
- *	Remove an inode from the superblock.
- */
-void remove_inode_hash(struct inode *inode)
-{
-	spin_lock(&inode_lock);
-	hlist_del_init(&inode->i_hash);
-	spin_unlock(&inode_lock);
-}
-EXPORT_SYMBOL(remove_inode_hash);
 
 int generic_delete_inode(struct inode *inode)
 {
@@ -1188,7 +1327,7 @@ EXPORT_SYMBOL(generic_delete_inode);
  */
 int generic_drop_inode(struct inode *inode)
 {
-	return !inode->i_nlink || hlist_unhashed(&inode->i_hash);
+	return !inode->i_nlink || inode_unhashed(inode);
 }
 EXPORT_SYMBOL_GPL(generic_drop_inode);
 
@@ -1214,10 +1353,11 @@ static void iput_final(struct inode *inode)
 		drop = generic_drop_inode(inode);
 
 	if (!drop) {
-		if (!(inode->i_state & (I_DIRTY|I_SYNC)))
-			list_move(&inode->i_list, &inode_unused);
-		inodes_stat.nr_unused++;
 		if (sb->s_flags & MS_ACTIVE) {
+			inode->i_state |= I_REFERENCED;
+			if (!(inode->i_state & (I_DIRTY|I_SYNC))) {
+				inode_lru_list_add(inode);
+			}
 			spin_unlock(&inode_lock);
 			return;
 		}
@@ -1228,19 +1368,23 @@ static void iput_final(struct inode *inode)
 		spin_lock(&inode_lock);
 		WARN_ON(inode->i_state & I_NEW);
 		inode->i_state &= ~I_WILL_FREE;
-		inodes_stat.nr_unused--;
-		hlist_del_init(&inode->i_hash);
+		__remove_inode_hash(inode);
 	}
-	list_del_init(&inode->i_list);
-	list_del_init(&inode->i_sb_list);
+
 	WARN_ON(inode->i_state & I_NEW);
 	inode->i_state |= I_FREEING;
-	inodes_stat.nr_inodes--;
+
+	/*
+	 * Move the inode off the IO lists and LRU once I_FREEING is
+	 * set so that it won't get moved back on there if it is dirty.
+	 */
+	inode_lru_list_del(inode);
+	list_del_init(&inode->i_wb_list);
+
+	__inode_sb_list_del(inode);
 	spin_unlock(&inode_lock);
 	evict(inode);
-	spin_lock(&inode_lock);
-	hlist_del_init(&inode->i_hash);
-	spin_unlock(&inode_lock);
+	remove_inode_hash(inode);
 	wake_up_inode(inode);
 	BUG_ON(inode->i_state != (I_FREEING | I_CLEAR));
 	destroy_inode(inode);
@@ -1504,6 +1648,8 @@ void __init inode_init(void)
 					 SLAB_MEM_SPREAD),
 					 init_once);
 	register_shrinker(&icache_shrinker);
+	percpu_counter_init(&nr_inodes, 0);
+	percpu_counter_init(&nr_inodes_unused, 0);
 
 	/* Hash may have been set up in inode_init_early */
 	if (!hashdist)

fs/internal.h

@@ -101,3 +101,10 @@ extern void put_super(struct super_block *sb);
 struct nameidata;
 extern struct file *nameidata_to_filp(struct nameidata *);
 extern void release_open_intent(struct nameidata *);
+
+/*
+ * inode.c
+ */
+extern int get_nr_dirty_inodes(void);
+extern int evict_inodes(struct super_block *);
+extern int invalidate_inodes(struct super_block *);

fs/isofs/inode.c

@@ -962,25 +962,23 @@ static int isofs_statfs (struct dentry *dentry, struct kstatfs *buf)
  * or getblk() if they are not.  Returns the number of blocks inserted
  * (-ve == error.)
  */
-int isofs_get_blocks(struct inode *inode, sector_t iblock_s,
+int isofs_get_blocks(struct inode *inode, sector_t iblock,
 		     struct buffer_head **bh, unsigned long nblocks)
 {
-	unsigned long b_off;
+	unsigned long b_off = iblock;
 	unsigned offset, sect_size;
 	unsigned int firstext;
 	unsigned long nextblk, nextoff;
-	long iblock = (long)iblock_s;
 	int section, rv, error;
 	struct iso_inode_info *ei = ISOFS_I(inode);
 
 	error = -EIO;
 	rv = 0;
-	if (iblock < 0 || iblock != iblock_s) {
+	if (iblock != b_off) {
 		printk(KERN_DEBUG "%s: block number too large\n", __func__);
 		goto abort;
 	}
 
-	b_off = iblock;
 
 	offset = 0;
 	firstext = ei->i_first_extent;
@@ -998,8 +996,9 @@ int isofs_get_blocks(struct inode *inode, sector_t iblock_s,
 		 * I/O errors.
 		 */
 		if (b_off > ((inode->i_size + PAGE_CACHE_SIZE - 1) >> ISOFS_BUFFER_BITS(inode))) {
-			printk(KERN_DEBUG "%s: block >= EOF (%ld, %ld)\n",
-				__func__, iblock, (unsigned long) inode->i_size);
+			printk(KERN_DEBUG "%s: block >= EOF (%lu, %llu)\n",
+				__func__, b_off,
+				(unsigned long long)inode->i_size);
 			goto abort;
 		}
 
@@ -1025,9 +1024,9 @@ int isofs_get_blocks(struct inode *inode, sector_t iblock_s,
 			if (++section > 100) {
 				printk(KERN_DEBUG "%s: More than 100 file sections ?!?"
 					" aborting...\n", __func__);
-				printk(KERN_DEBUG "%s: block=%ld firstext=%u sect_size=%u "
+				printk(KERN_DEBUG "%s: block=%lu firstext=%u sect_size=%u "
 					"nextblk=%lu nextoff=%lu\n", __func__,
-					iblock, firstext, (unsigned) sect_size,
+					b_off, firstext, (unsigned) sect_size,
 					nextblk, nextoff);
 				goto abort;
 			}

fs/jffs2/dir.c

@@ -289,7 +289,7 @@ static int jffs2_link (struct dentry *old_dentry, struct inode *dir_i, struct de
 		mutex_unlock(&f->sem);
 		d_instantiate(dentry, old_dentry->d_inode);
 		dir_i->i_mtime = dir_i->i_ctime = ITIME(now);
-		atomic_inc(&old_dentry->d_inode->i_count);
+		ihold(old_dentry->d_inode);
 	}
 	return ret;
 }
@@ -864,7 +864,7 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry,
 		printk(KERN_NOTICE "jffs2_rename(): Link succeeded, unlink failed (err %d). You now have a hard link\n", ret);
 		/* Might as well let the VFS know */
 		d_instantiate(new_dentry, old_dentry->d_inode);
-		atomic_inc(&old_dentry->d_inode->i_count);
+		ihold(old_dentry->d_inode);
 		new_dir_i->i_mtime = new_dir_i->i_ctime = ITIME(now);
 		return ret;
 	}

fs/jfs/jfs_imap.c

@@ -497,7 +497,7 @@ struct inode *diReadSpecial(struct super_block *sb, ino_t inum, int secondary)
 	 * appear hashed, but do not put on any lists.  hlist_del()
 	 * will work fine and require no locking.
 	 */
-	ip->i_hash.pprev = &ip->i_hash.next;
+	hlist_add_fake(&ip->i_hash);
 
 	return (ip);
 }

fs/jfs/jfs_txnmgr.c

@@ -1279,7 +1279,7 @@ int txCommit(tid_t tid,		/* transaction identifier */
 	 * lazy commit thread finishes processing
 	 */
 	if (tblk->xflag & COMMIT_DELETE) {
-		atomic_inc(&tblk->u.ip->i_count);
+		ihold(tblk->u.ip);
 		/*
 		 * Avoid a rare deadlock
 		 *

fs/jfs/namei.c

@@ -839,7 +839,7 @@ static int jfs_link(struct dentry *old_dentry,
 	ip->i_ctime = CURRENT_TIME;
 	dir->i_ctime = dir->i_mtime = CURRENT_TIME;
 	mark_inode_dirty(dir);
-	atomic_inc(&ip->i_count);
+	ihold(ip);
 
 	iplist[0] = ip;
 	iplist[1] = dir;

fs/libfs.c

@@ -255,7 +255,7 @@ int simple_link(struct dentry *old_dentry, struct inode *dir, struct dentry *den
 
 	inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME;
 	inc_nlink(inode);
-	atomic_inc(&inode->i_count);
+	ihold(inode);
 	dget(dentry);
 	d_instantiate(dentry, inode);
 	return 0;
@@ -892,10 +892,6 @@ EXPORT_SYMBOL_GPL(generic_fh_to_parent);
  */
 int generic_file_fsync(struct file *file, int datasync)
 {
-	struct writeback_control wbc = {
-		.sync_mode = WB_SYNC_ALL,
-		.nr_to_write = 0, /* metadata-only; caller takes care of data */
-	};
 	struct inode *inode = file->f_mapping->host;
 	int err;
 	int ret;
@@ -906,7 +902,7 @@ int generic_file_fsync(struct file *file, int datasync)
 	if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
 		return ret;
 
-	err = sync_inode(inode, &wbc);
+	err = sync_inode_metadata(inode, 1);
 	if (ret == 0)
 		ret = err;
 	return ret;

fs/logfs/dir.c

@@ -569,7 +569,7 @@ static int logfs_link(struct dentry *old_dentry, struct inode *dir,
 		return -EMLINK;
 
 	inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME;
-	atomic_inc(&inode->i_count);
+	ihold(inode);
 	inode->i_nlink++;
 	mark_inode_dirty_sync(inode);
 

fs/minix/namei.c

@@ -101,7 +101,7 @@ static int minix_link(struct dentry * old_dentry, struct inode * dir,
 
 	inode->i_ctime = CURRENT_TIME_SEC;
 	inode_inc_link_count(inode);
-	atomic_inc(&inode->i_count);
+	ihold(inode);
 	return add_nondir(dentry, inode);
 }
 

fs/namei.c

@@ -1121,11 +1121,13 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt,
 static struct dentry *__lookup_hash(struct qstr *name,
 		struct dentry *base, struct nameidata *nd)
 {
+	struct inode *inode = base->d_inode;
 	struct dentry *dentry;
-	struct inode *inode;
 	int err;
 
-	inode = base->d_inode;
+	err = exec_permission(inode);
+	if (err)
+		return ERR_PTR(err);
 
 	/*
 	 * See if the low-level filesystem might want
@@ -1161,11 +1163,6 @@ out:
  */
 static struct dentry *lookup_hash(struct nameidata *nd)
 {
-	int err;
-
-	err = exec_permission(nd->path.dentry->d_inode);
-	if (err)
-		return ERR_PTR(err);
 	return __lookup_hash(&nd->last, nd->path.dentry, nd);
 }
 
@@ -1213,9 +1210,6 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
 	if (err)
 		return ERR_PTR(err);
 
-	err = exec_permission(base->d_inode);
-	if (err)
-		return ERR_PTR(err);
 	return __lookup_hash(&this, base, NULL);
 }
 
@@ -2291,7 +2285,7 @@ static long do_unlinkat(int dfd, const char __user *pathname)
 			goto slashes;
 		inode = dentry->d_inode;
 		if (inode)
-			atomic_inc(&inode->i_count);
+			ihold(inode);
 		error = mnt_want_write(nd.path.mnt);
 		if (error)
 			goto exit2;

fs/namespace.c

@@ -595,7 +595,7 @@ static struct vfsmount *clone_mnt(struct vfsmount *old, struct dentry *root,
 				goto out_free;
 		}
 
-		mnt->mnt_flags = old->mnt_flags;
+		mnt->mnt_flags = old->mnt_flags & ~MNT_WRITE_HOLD;
 		atomic_inc(&sb->s_active);
 		mnt->mnt_sb = sb;
 		mnt->mnt_root = dget(root);

fs/nfs/dir.c

@@ -1801,7 +1801,7 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
 	d_drop(dentry);
 	error = NFS_PROTO(dir)->link(inode, dir, &dentry->d_name);
 	if (error == 0) {
-		atomic_inc(&inode->i_count);
+		ihold(inode);
 		d_add(dentry, inode);
 	}
 	return error;

fs/nfs/getroot.c

@@ -54,8 +54,7 @@ static int nfs_superblock_set_dummy_root(struct super_block *sb, struct inode *i
 			iput(inode);
 			return -ENOMEM;
 		}
-		/* Circumvent igrab(): we know the inode is not being freed */
-		atomic_inc(&inode->i_count);
+		ihold(inode);
 		/*
 		 * Ensure that this dentry is invisible to d_find_alias().
 		 * Otherwise, it may be spliced into the tree by

fs/nfsd/vfs.c

@@ -281,23 +281,13 @@ commit_metadata(struct svc_fh *fhp)
 {
 	struct inode *inode = fhp->fh_dentry->d_inode;
 	const struct export_operations *export_ops = inode->i_sb->s_export_op;
-	int error = 0;
 
 	if (!EX_ISSYNC(fhp->fh_export))
 		return 0;
 
-	if (export_ops->commit_metadata) {
-		error = export_ops->commit_metadata(inode);
-	} else {
-		struct writeback_control wbc = {
-			.sync_mode = WB_SYNC_ALL,
-			.nr_to_write = 0, /* metadata only */
-		};
-
-		error = sync_inode(inode, &wbc);
-	}
-
-	return error;
+	if (export_ops->commit_metadata)
+		return export_ops->commit_metadata(inode);
+	return sync_inode_metadata(inode, 1);
 }
 
 /*

fs/nilfs2/namei.c

@@ -207,7 +207,7 @@ static int nilfs_link(struct dentry *old_dentry, struct inode *dir,
 
 	inode->i_ctime = CURRENT_TIME;
 	inode_inc_link_count(inode);
-	atomic_inc(&inode->i_count);
+	ihold(inode);
 
 	err = nilfs_add_nondir(dentry, inode);
 	if (!err)

fs/notify/fsnotify.c

@@ -88,8 +88,6 @@ void __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask)
 {
 	struct dentry *parent;
 	struct inode *p_inode;
-	bool send = false;
-	bool should_update_children = false;
 
 	if (!dentry)
 		dentry = path->dentry;
@@ -97,29 +95,12 @@ void __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask)
 	if (!(dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED))
 		return;
 
-	spin_lock(&dentry->d_lock);
-	parent = dentry->d_parent;
+	parent = dget_parent(dentry);
 	p_inode = parent->d_inode;
 
-	if (fsnotify_inode_watches_children(p_inode)) {
-		if (p_inode->i_fsnotify_mask & mask) {
-			dget(parent);
-			send = true;
-		}
-	} else {
-		/*
-		 * The parent doesn't care about events on it's children but
-		 * at least one child thought it did.  We need to run all the
-		 * children and update their d_flags to let them know p_inode
-		 * doesn't care about them any more.
-		 */
-		dget(parent);
-		should_update_children = true;
-	}
-
-	spin_unlock(&dentry->d_lock);
-
-	if (send) {
+	if (unlikely(!fsnotify_inode_watches_children(p_inode)))
+		__fsnotify_update_child_dentry_flags(p_inode);
+	else if (p_inode->i_fsnotify_mask & mask) {
 		/* we are notifying a parent so come up with the new mask which
 		 * specifies these are events which came from a child. */
 		mask |= FS_EVENT_ON_CHILD;
@@ -130,13 +111,9 @@ void __fsnotify_parent(struct path *path, struct dentry *dentry, __u32 mask)
 		else
 			fsnotify(p_inode, mask, dentry->d_inode, FSNOTIFY_EVENT_INODE,
 				 dentry->d_name.name, 0);
-		dput(parent);
 	}
 
-	if (unlikely(should_update_children)) {
-		__fsnotify_update_child_dentry_flags(p_inode);
-		dput(parent);
-	}
+	dput(parent);
 }
 EXPORT_SYMBOL_GPL(__fsnotify_parent);
 

fs/notify/inode_mark.c

@@ -240,6 +240,7 @@ void fsnotify_unmount_inodes(struct list_head *list)
 {
 	struct inode *inode, *next_i, *need_iput = NULL;
 
+	spin_lock(&inode_lock);
 	list_for_each_entry_safe(inode, next_i, list, i_sb_list) {
 		struct inode *need_iput_tmp;
 
@@ -297,4 +298,5 @@ void fsnotify_unmount_inodes(struct list_head *list)
 
 		spin_lock(&inode_lock);
 	}
+	spin_unlock(&inode_lock);
 }

fs/ntfs/super.c

@@ -2911,8 +2911,8 @@ static int ntfs_fill_super(struct super_block *sb, void *opt, const int silent)
 		goto unl_upcase_iput_tmp_ino_err_out_now;
 	}
 	if ((sb->s_root = d_alloc_root(vol->root_ino))) {
-		/* We increment i_count simulating an ntfs_iget(). */
-		atomic_inc(&vol->root_ino->i_count);
+		/* We grab a reference, simulating an ntfs_iget(). */
+		ihold(vol->root_ino);
 		ntfs_debug("Exiting, status successful.");
 		/* Release the default upcase if it has no users. */
 		mutex_lock(&ntfs_lock);
@@ -3021,21 +3021,6 @@ iput_tmp_ino_err_out_now:
 	if (vol->mft_ino && vol->mft_ino != tmp_ino)
 		iput(vol->mft_ino);
 	vol->mft_ino = NULL;
-	/*
-	 * This is needed to get ntfs_clear_extent_inode() called for each
-	 * inode we have ever called ntfs_iget()/iput() on, otherwise we A)
-	 * leak resources and B) a subsequent mount fails automatically due to
-	 * ntfs_iget() never calling down into our ntfs_read_locked_inode()
-	 * method again... FIXME: Do we need to do this twice now because of
-	 * attribute inodes? I think not, so leave as is for now... (AIA)
-	 */
-	if (invalidate_inodes(sb)) {
-		ntfs_error(sb, "Busy inodes left. This is most likely a NTFS "
-				"driver bug.");
-		/* Copied from fs/super.c. I just love this message. (-; */
-		printk("NTFS: Busy inodes after umount. Self-destruct in 5 "
-				"seconds.  Have a nice day...\n");
-	}
 	/* Errors at this stage are irrelevant. */
 err_out_now:
 	sb->s_fs_info = NULL;

fs/ocfs2/aops.c

@@ -165,7 +165,7 @@ int ocfs2_get_block(struct inode *inode, sector_t iblock,
 	 * ocfs2 never allocates in this function - the only time we
 	 * need to use BH_New is when we're extending i_size on a file
 	 * system which doesn't support holes, in which case BH_New
-	 * allows block_prepare_write() to zero.
+	 * allows __block_write_begin() to zero.
 	 *
 	 * If we see this on a sparse file system, then a truncate has
 	 * raced us and removed the cluster. In this case, we clear
@@ -407,21 +407,6 @@ static int ocfs2_writepage(struct page *page, struct writeback_control *wbc)
 	return ret;
 }
 
-/*
- * This is called from ocfs2_write_zero_page() which has handled it's
- * own cluster locking and has ensured allocation exists for those
- * blocks to be written.
- */
-int ocfs2_prepare_write_nolock(struct inode *inode, struct page *page,
-			       unsigned from, unsigned to)
-{
-	int ret;
-
-	ret = block_prepare_write(page, from, to, ocfs2_get_block);
-
-	return ret;
-}
-
 /* Taken from ext3. We don't necessarily need the full blown
  * functionality yet, but IMHO it's better to cut and paste the whole
  * thing so we can avoid introducing our own bugs (and easily pick up
@@ -732,7 +717,7 @@ static int ocfs2_should_read_blk(struct inode *inode, struct page *page,
 }
 
 /*
- * Some of this taken from block_prepare_write(). We already have our
+ * Some of this taken from __block_write_begin(). We already have our
  * mapping by now though, and the entire write will be allocating or
  * it won't, so not much need to use BH_New.
  *

fs/ocfs2/aops.h

@@ -22,9 +22,6 @@
 #ifndef OCFS2_AOPS_H
 #define OCFS2_AOPS_H
 
-int ocfs2_prepare_write_nolock(struct inode *inode, struct page *page,
-			       unsigned from, unsigned to);
-
 handle_t *ocfs2_start_walk_page_trans(struct inode *inode,
 							 struct page *page,
 							 unsigned from,

fs/ocfs2/dlmfs/dlmfs.c

@@ -400,6 +400,7 @@ static struct inode *dlmfs_get_root_inode(struct super_block *sb)
 	if (inode) {
 		ip = DLMFS_I(inode);
 
+		inode->i_ino = get_next_ino();
 		inode->i_mode = mode;
 		inode->i_uid = current_fsuid();
 		inode->i_gid = current_fsgid();
@@ -425,6 +426,7 @@ static struct inode *dlmfs_get_inode(struct inode *parent,
 	if (!inode)
 		return NULL;
 
+	inode->i_ino = get_next_ino();
 	inode->i_mode = mode;
 	inode->i_uid = current_fsuid();
 	inode->i_gid = current_fsgid();

fs/ocfs2/file.c

@@ -796,13 +796,12 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
 		block_end = block_start + (1 << inode->i_blkbits);
 
 		/*
-		 * block_start is block-aligned.  Bump it by one to
-		 * force ocfs2_{prepare,commit}_write() to zero the
+		 * block_start is block-aligned.  Bump it by one to force
+		 * __block_write_begin and block_commit_write to zero the
 		 * whole block.
 		 */
-		ret = ocfs2_prepare_write_nolock(inode, page,
-						 block_start + 1,
-						 block_start + 1);
+		ret = __block_write_begin(page, block_start + 1, 0,
+					  ocfs2_get_block);
 		if (ret < 0) {
 			mlog_errno(ret);
 			goto out_unlock;

fs/ocfs2/namei.c

@@ -742,7 +742,7 @@ static int ocfs2_link(struct dentry *old_dentry,
 		goto out_commit;
 	}
 
-	atomic_inc(&inode->i_count);
+	ihold(inode);
 	dentry->d_op = &ocfs2_dentry_ops;
 	d_instantiate(dentry, inode);
 

fs/pipe.c

@@ -954,6 +954,8 @@ static struct inode * get_pipe_inode(void)
 	if (!inode)
 		goto fail_inode;
 
+	inode->i_ino = get_next_ino();
+
 	pipe = alloc_pipe_info(inode);
 	if (!pipe)
 		goto fail_iput;

fs/proc/base.c

@@ -771,6 +771,8 @@ static const struct file_operations proc_single_file_operations = {
 static int mem_open(struct inode* inode, struct file* file)
 {
 	file->private_data = (void*)((long)current->self_exec_id);
+	/* OK to pass negative loff_t, we can catch out-of-range */
+	file->f_mode |= FMODE_UNSIGNED_OFFSET;
 	return 0;
 }
 
@@ -1646,6 +1648,7 @@ static struct inode *proc_pid_make_inode(struct super_block * sb, struct task_st
 
 	/* Common stuff */
 	ei = PROC_I(inode);
+	inode->i_ino = get_next_ino();
 	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
 	inode->i_op = &proc_def_inode_operations;
 
@@ -2592,6 +2595,7 @@ static struct dentry *proc_base_instantiate(struct inode *dir,
 
 	/* Initialize the inode */
 	ei = PROC_I(inode);
+	inode->i_ino = get_next_ino();
 	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
 
 	/*

fs/proc/proc_sysctl.c

@@ -23,6 +23,8 @@ static struct inode *proc_sys_make_inode(struct super_block *sb,
 	if (!inode)
 		goto out;
 
+	inode->i_ino = get_next_ino();
+
 	sysctl_head_get(head);
 	ei = PROC_I(inode);
 	ei->sysctl = head;

fs/ramfs/inode.c

@@ -58,6 +58,7 @@ struct inode *ramfs_get_inode(struct super_block *sb,
 	struct inode * inode = new_inode(sb);
 
 	if (inode) {
+		inode->i_ino = get_next_ino();
 		inode_init_owner(inode, dir, mode);
 		inode->i_mapping->a_ops = &ramfs_aops;
 		inode->i_mapping->backing_dev_info = &ramfs_backing_dev_info;

fs/read_write.c

@@ -31,6 +31,20 @@ const struct file_operations generic_ro_fops = {
 
 EXPORT_SYMBOL(generic_ro_fops);
 
+static int
+__negative_fpos_check(struct file *file, loff_t pos, size_t count)
+{
+	/*
+	 * pos or pos+count is negative here, check overflow.
+	 * too big "count" will be caught in rw_verify_area().
+	 */
+	if ((pos < 0) && (pos + count < pos))
+		return -EOVERFLOW;
+	if (file->f_mode & FMODE_UNSIGNED_OFFSET)
+		return 0;
+	return -EINVAL;
+}
+
 /**
  * generic_file_llseek_unlocked - lockless generic llseek implementation
  * @file:	file structure to seek on
@@ -62,7 +76,9 @@ generic_file_llseek_unlocked(struct file *file, loff_t offset, int origin)
 		break;
 	}
 
-	if (offset < 0 || offset > inode->i_sb->s_maxbytes)
+	if (offset < 0 && __negative_fpos_check(file, offset, 0))
+		return -EINVAL;
+	if (offset > inode->i_sb->s_maxbytes)
 		return -EINVAL;
 
 	/* Special lock needed here? */
@@ -137,7 +153,7 @@ loff_t default_llseek(struct file *file, loff_t offset, int origin)
 			offset += file->f_pos;
 	}
 	retval = -EINVAL;
-	if (offset >= 0) {
+	if (offset >= 0 || !__negative_fpos_check(file, offset, 0)) {
 		if (offset != file->f_pos) {
 			file->f_pos = offset;
 			file->f_version = 0;
@@ -221,6 +237,7 @@ bad:
 }
 #endif
 
+
 /*
  * rw_verify_area doesn't like huge counts. We limit
  * them to something that fits in "int" so that others
@@ -238,8 +255,11 @@ int rw_verify_area(int read_write, struct file *file, loff_t *ppos, size_t count
 	if (unlikely((ssize_t) count < 0))
 		return retval;
 	pos = *ppos;
-	if (unlikely((pos < 0) || (loff_t) (pos + count) < 0))
-		return retval;
+	if (unlikely((pos < 0) || (loff_t) (pos + count) < 0)) {
+		retval = __negative_fpos_check(file, pos, count);
+		if (retval)
+			return retval;
+	}
 
 	if (unlikely(inode->i_flock && mandatory_lock(inode))) {
 		retval = locks_mandatory_area(

fs/reiserfs/inode.c

@@ -22,8 +22,6 @@
 
 int reiserfs_commit_write(struct file *f, struct page *page,
 			  unsigned from, unsigned to);
-int reiserfs_prepare_write(struct file *f, struct page *page,
-			   unsigned from, unsigned to);
 
 void reiserfs_evict_inode(struct inode *inode)
 {
@@ -165,7 +163,7 @@ inline void make_le_item_head(struct item_head *ih, const struct cpu_key *key,
 ** but tail is still sitting in a direct item, and we can't write to
 ** it.  So, look through this page, and check all the mapped buffers
 ** to make sure they have valid block numbers.  Any that don't need
-** to be unmapped, so that block_prepare_write will correctly call
+** to be unmapped, so that __block_write_begin will correctly call
 ** reiserfs_get_block to convert the tail into an unformatted node
 */
 static inline void fix_tail_page_for_writing(struct page *page)
@@ -439,13 +437,13 @@ static int reiserfs_bmap(struct inode *inode, sector_t block,
 }
 
 /* special version of get_block that is only used by grab_tail_page right
-** now.  It is sent to block_prepare_write, and when you try to get a
+** now.  It is sent to __block_write_begin, and when you try to get a
 ** block past the end of the file (or a block from a hole) it returns
-** -ENOENT instead of a valid buffer.  block_prepare_write expects to
+** -ENOENT instead of a valid buffer.  __block_write_begin expects to
 ** be able to do i/o on the buffers returned, unless an error value
 ** is also returned.
 **
-** So, this allows block_prepare_write to be used for reading a single block
+** So, this allows __block_write_begin to be used for reading a single block
 ** in a page.  Where it does not produce a valid page for holes, or past the
 ** end of the file.  This turns out to be exactly what we need for reading
 ** tails for conversion.
@@ -558,11 +556,12 @@ static int convert_tail_for_hole(struct inode *inode,
 	 **
 	 ** We must fix the tail page for writing because it might have buffers
 	 ** that are mapped, but have a block number of 0.  This indicates tail
-	 ** data that has been read directly into the page, and block_prepare_write
-	 ** won't trigger a get_block in this case.
+	 ** data that has been read directly into the page, and
+	 ** __block_write_begin won't trigger a get_block in this case.
 	 */
 	fix_tail_page_for_writing(tail_page);
-	retval = reiserfs_prepare_write(NULL, tail_page, tail_start, tail_end);
+	retval = __reiserfs_write_begin(tail_page, tail_start,
+				      tail_end - tail_start);
 	if (retval)
 		goto unlock;
 
@@ -2033,7 +2032,7 @@ static int grab_tail_page(struct inode *inode,
 	/* start within the page of the last block in the file */
 	start = (offset / blocksize) * blocksize;
 
-	error = block_prepare_write(page, start, offset,
+	error = __block_write_begin(page, start, offset - start,
 				    reiserfs_get_block_create_0);
 	if (error)
 		goto unlock;
@@ -2628,8 +2627,7 @@ static int reiserfs_write_begin(struct file *file,
 	return ret;
 }
 
-int reiserfs_prepare_write(struct file *f, struct page *page,
-			   unsigned from, unsigned to)
+int __reiserfs_write_begin(struct page *page, unsigned from, unsigned len)
 {
 	struct inode *inode = page->mapping->host;
 	int ret;
@@ -2650,7 +2648,7 @@ int reiserfs_prepare_write(struct file *f, struct page *page,
 		th->t_refcount++;
 	}
 
-	ret = block_prepare_write(page, from, to, reiserfs_get_block);
+	ret = __block_write_begin(page, from, len, reiserfs_get_block);
 	if (ret && reiserfs_transaction_running(inode->i_sb)) {
 		struct reiserfs_transaction_handle *th = current->journal_info;
 		/* this gets a little ugly.  If reiserfs_get_block returned an

fs/reiserfs/ioctl.c

@@ -160,8 +160,6 @@ long reiserfs_compat_ioctl(struct file *file, unsigned int cmd,
 
 int reiserfs_commit_write(struct file *f, struct page *page,
 			  unsigned from, unsigned to);
-int reiserfs_prepare_write(struct file *f, struct page *page,
-			   unsigned from, unsigned to);
 /*
 ** reiserfs_unpack
 ** Function try to convert tail from direct item into indirect.
@@ -200,7 +198,7 @@ int reiserfs_unpack(struct inode *inode, struct file *filp)
 	}
 
 	/* we unpack by finding the page with the tail, and calling
-	 ** reiserfs_prepare_write on that page.  This will force a
+	 ** __reiserfs_write_begin on that page.  This will force a
 	 ** reiserfs_get_block to unpack the tail for us.
 	 */
 	index = inode->i_size >> PAGE_CACHE_SHIFT;
@@ -210,7 +208,7 @@ int reiserfs_unpack(struct inode *inode, struct file *filp)
 	if (!page) {
 		goto out;
 	}
-	retval = reiserfs_prepare_write(NULL, page, write_from, write_from);
+	retval = __reiserfs_write_begin(page, write_from, 0);
 	if (retval)
 		goto out_unlock;
 

fs/reiserfs/namei.c

@@ -1156,7 +1156,7 @@ static int reiserfs_link(struct dentry *old_dentry, struct inode *dir,
 	inode->i_ctime = CURRENT_TIME_SEC;
 	reiserfs_update_sd(&th, inode);
 
-	atomic_inc(&inode->i_count);
+	ihold(inode);
 	d_instantiate(dentry, inode);
 	retval = journal_end(&th, dir->i_sb, jbegin_count);
 	reiserfs_write_unlock(dir->i_sb);

fs/reiserfs/xattr.c

@@ -418,13 +418,11 @@ static inline __u32 xattr_hash(const char *msg, int len)
 
 int reiserfs_commit_write(struct file *f, struct page *page,
 			  unsigned from, unsigned to);
-int reiserfs_prepare_write(struct file *f, struct page *page,
-			   unsigned from, unsigned to);
 
 static void update_ctime(struct inode *inode)
 {
 	struct timespec now = current_fs_time(inode->i_sb);
-	if (hlist_unhashed(&inode->i_hash) || !inode->i_nlink ||
+	if (inode_unhashed(inode) || !inode->i_nlink ||
 	    timespec_equal(&inode->i_ctime, &now))
 		return;
 
@@ -532,8 +530,7 @@ reiserfs_xattr_set_handle(struct reiserfs_transaction_handle *th,
 			rxh->h_hash = cpu_to_le32(xahash);
 		}
 
-		err = reiserfs_prepare_write(NULL, page, page_offset,
-					    page_offset + chunk + skip);
+		err = __reiserfs_write_begin(page, page_offset, chunk + skip);
 		if (!err) {
 			if (buffer)
 				memcpy(data + skip, buffer + buffer_pos, chunk);

fs/seq_file.c

@@ -462,9 +462,7 @@ int seq_path_root(struct seq_file *m, struct path *path, struct path *root,
 	if (size) {
 		char *p;
 
-		spin_lock(&dcache_lock);
 		p = __d_path(path, root, buf, size);
-		spin_unlock(&dcache_lock);
 		res = PTR_ERR(p);
 		if (!IS_ERR(p)) {
 			char *end = mangle_path(buf, p, esc);

fs/smbfs/dir.c

@@ -406,21 +406,15 @@ void
 smb_renew_times(struct dentry * dentry)
 {
 	dget(dentry);
-	spin_lock(&dentry->d_lock);
-	for (;;) {
-		struct dentry *parent;
+	dentry->d_time = jiffies;
 
-		dentry->d_time = jiffies;
-		if (IS_ROOT(dentry))
-			break;
-		parent = dentry->d_parent;
-		dget(parent);
-		spin_unlock(&dentry->d_lock);
+	while (!IS_ROOT(dentry)) {
+		struct dentry *parent = dget_parent(dentry);
 		dput(dentry);
 		dentry = parent;
-		spin_lock(&dentry->d_lock);
+
+		dentry->d_time = jiffies;
 	}
-	spin_unlock(&dentry->d_lock);
 	dput(dentry);
 }
 

fs/smbfs/inode.c

@@ -229,7 +229,6 @@ smb_invalidate_inodes(struct smb_sb_info *server)
 {
 	VERBOSE("\n");
 	shrink_dcache_sb(SB_of(server));
-	invalidate_inodes(SB_of(server));
 }
 
 /*

fs/smbfs/proc.c

@@ -332,16 +332,15 @@ static int smb_build_path(struct smb_sb_info *server, unsigned char *buf,
 	 * and store it in reversed order [see reverse_string()]
 	 */
 	dget(entry);
-	spin_lock(&entry->d_lock);
 	while (!IS_ROOT(entry)) {
 		struct dentry *parent;
 
 		if (maxlen < (3<<unicode)) {
-			spin_unlock(&entry->d_lock);
 			dput(entry);
 			return -ENAMETOOLONG;
 		}
 
+		spin_lock(&entry->d_lock);
 		len = server->ops->convert(path, maxlen-2, 
 				      entry->d_name.name, entry->d_name.len,
 				      server->local_nls, server->remote_nls);
@@ -359,15 +358,12 @@ static int smb_build_path(struct smb_sb_info *server, unsigned char *buf,
 		}
 		*path++ = '\\';
 		maxlen -= len+1;
-
-		parent = entry->d_parent;
-		dget(parent);
 		spin_unlock(&entry->d_lock);
+
+		parent = dget_parent(entry);
 		dput(entry);
 		entry = parent;
-		spin_lock(&entry->d_lock);
 	}
-	spin_unlock(&entry->d_lock);
 	dput(entry);
 	reverse_string(buf, path-buf);
 

fs/super.c

@@ -273,14 +273,14 @@ void generic_shutdown_super(struct super_block *sb)
 		get_fs_excl();
 		sb->s_flags &= ~MS_ACTIVE;
 
-		/* bad name - it should be evict_inodes() */
-		invalidate_inodes(sb);
+		fsnotify_unmount_inodes(&sb->s_inodes);
+
+		evict_inodes(sb);
 
 		if (sop->put_super)
 			sop->put_super(sb);
 
-		/* Forget any remaining inodes */
-		if (invalidate_inodes(sb)) {
+		if (!list_empty(&sb->s_inodes)) {
 			printk("VFS: Busy inodes after unmount of %s. "
 			   "Self-destruct in 5 seconds.  Have a nice day...\n",
 			   sb->s_id);

fs/sysv/namei.c

@@ -126,7 +126,7 @@ static int sysv_link(struct dentry * old_dentry, struct inode * dir,
 
 	inode->i_ctime = CURRENT_TIME_SEC;
 	inode_inc_link_count(inode);
-	atomic_inc(&inode->i_count);
+	ihold(inode);
 
 	return add_nondir(dentry, inode);
 }

fs/ubifs/dir.c

@@ -550,7 +550,7 @@ static int ubifs_link(struct dentry *old_dentry, struct inode *dir,
 
 	lock_2_inodes(dir, inode);
 	inc_nlink(inode);
-	atomic_inc(&inode->i_count);
+	ihold(inode);
 	inode->i_ctime = ubifs_current_time(inode);
 	dir->i_size += sz_change;
 	dir_ui->ui_size = dir->i_size;

fs/udf/namei.c

@@ -1101,7 +1101,7 @@ static int udf_link(struct dentry *old_dentry, struct inode *dir,
 	inc_nlink(inode);
 	inode->i_ctime = current_fs_time(inode->i_sb);
 	mark_inode_dirty(inode);
-	atomic_inc(&inode->i_count);
+	ihold(inode);
 	d_instantiate(dentry, inode);
 	unlock_kernel();
 

fs/ufs/namei.c

@@ -180,7 +180,7 @@ static int ufs_link (struct dentry * old_dentry, struct inode * dir,
 
 	inode->i_ctime = CURRENT_TIME_SEC;
 	inode_inc_link_count(inode);
-	atomic_inc(&inode->i_count);
+	ihold(inode);
 
 	error = ufs_add_nondir(dentry, inode);
 	unlock_kernel();

fs/xfs/linux-2.6/xfs_buf.c

@@ -1580,6 +1580,7 @@ xfs_mapping_buftarg(
 			XFS_BUFTARG_NAME(btp));
 		return ENOMEM;
 	}
+	inode->i_ino = get_next_ino();
 	inode->i_mode = S_IFBLK;
 	inode->i_bdev = bdev;
 	inode->i_rdev = bdev->bd_dev;

fs/xfs/linux-2.6/xfs_iops.c

@@ -317,7 +317,7 @@ xfs_vn_link(
 	if (unlikely(error))
 		return -error;
 
-	atomic_inc(&inode->i_count);
+	ihold(inode);
 	d_instantiate(dentry, inode);
 	return 0;
 }
@@ -760,7 +760,9 @@ xfs_setup_inode(
 
 	inode->i_ino = ip->i_ino;
 	inode->i_state = I_NEW;
-	inode_add_to_lists(ip->i_mount->m_super, inode);
+
+	inode_sb_list_add(inode);
+	insert_inode_hash(inode);
 
 	inode->i_mode	= ip->i_d.di_mode;
 	inode->i_nlink	= ip->i_d.di_nlink;

fs/xfs/linux-2.6/xfs_super.c

@@ -576,7 +576,7 @@ xfs_max_file_offset(
 
 	/* Figure out maximum filesize, on Linux this can depend on
 	 * the filesystem blocksize (on 32 bit platforms).
-	 * __block_prepare_write does this in an [unsigned] long...
+	 * __block_write_begin does this in an [unsigned] long...
 	 *      page->index << (PAGE_CACHE_SHIFT - bbits)
 	 * So, for page sized blocks (4K on 32 bit platforms),
 	 * this wraps at around 8Tb (hence MAX_LFS_FILESIZE which is