inode.c

/*
 * (C) 1997 Linus Torvalds
 * (C) 1999 Andrea Arcangeli <andrea@suse.de> (dynamic inode allocation)
 */
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/dcache.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/writeback.h>
#include <linux/module.h>
#include <linux/backing-dev.h>
#include <linux/wait.h>
#include <linux/rwsem.h>
#include <linux/hash.h>
#include <linux/swap.h>
#include <linux/security.h>
#include <linux/pagemap.h>
#include <linux/cdev.h>
#include <linux/bootmem.h>
#include <linux/fsnotify.h>
#include <linux/mount.h>
#include <linux/async.h>
#include <linux/posix_acl.h>
#include <linux/prefetch.h>
#include <linux/ima.h>
#include <linux/cred.h>
#include <linux/buffer_head.h> /* for inode_has_buffers */
#include "internal.h"

/*
 * Inode locking rules:
 *
 * inode->i_lock protects:
 *   inode->i_state, inode->i_hash, __iget()
 * inode_lru_lock protects:
 *   inode_lru, inode->i_lru
 * inode_sb_list_lock protects:
 *   sb->s_inodes, inode->i_sb_list
 * bdi->wb.list_lock protects:
 *   bdi->wb.b_{dirty,io,more_io}, inode->i_wb_list
 * inode_hash_lock protects:
 *   inode_hashtable, inode->i_hash
 *
 * Lock ordering:
 *
 * inode_sb_list_lock
 *   inode->i_lock
 *     inode_lru_lock
 *
 * bdi->wb.list_lock
 *   inode->i_lock
 *
 * inode_hash_lock
 *   inode_sb_list_lock
 *   inode->i_lock
 *
 * iunique_lock
 *   inode_hash_lock
 */

static unsigned int i_hash_mask __read_mostly;
static unsigned int i_hash_shift __read_mostly;
static struct hlist_head *inode_hashtable __read_mostly;
static __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_hash_lock);

static LIST_HEAD(inode_lru);
static DEFINE_SPINLOCK(inode_lru_lock);

__cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_sb_list_lock);

/*
 * iprune_sem provides exclusion between the icache shrinking and the
 * umount path.
 *
 * We don't actually need it to protect anything in the umount path,
 * but only need to cycle through it to make sure any inode that
 * prune_icache took off the LRU list has been fully torn down by the
 * time we are past evict_inodes.
 */
static DECLARE_RWSEM(iprune_sem);

/*
 * Empty aops. Can be used for the cases where the user does not
 * define any of the address_space operations.
 */
const struct address_space_operations empty_aops = {
};
EXPORT_SYMBOL(empty_aops);

/*
 * Statistics gathering..
 */
struct inodes_stat_t inodes_stat;

static DEFINE_PER_CPU(unsigned int, nr_inodes);

static struct kmem_cache *inode_cachep __read_mostly;

static int get_nr_inodes(void)
{
	int i;
	int sum = 0;
	for_each_possible_cpu(i)
		sum += per_cpu(nr_inodes, i);
	return sum < 0 ? 0 : sum;
}

static inline int get_nr_inodes_unused(void)
{
	return inodes_stat.nr_unused;
}

int get_nr_dirty_inodes(void)
{
	/* not actually dirty inodes, but a wild approximation */
	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();
	return proc_dointvec(table, write, buffer, lenp, ppos);
}
#endif

/**
 * inode_init_always - perform inode structure intialisation
 * @sb: superblock inode belongs to
 * @inode: inode to initialise
 *
 * These are initializations that need to be done on every inode
 * allocation as the fields are not initialised by slab allocation.
 */
int inode_init_always(struct super_block *sb, struct inode *inode)
{
	static const struct inode_operations empty_iops;
	static const struct file_operations empty_fops;
	struct address_space *const mapping = &inode->i_data;

	inode->i_sb = sb;
	inode->i_blkbits = sb->s_blocksize_bits;
	inode->i_flags = 0;
	atomic_set(&inode->i_count, 1);
	inode->i_op = &empty_iops;
	inode->i_fop = &empty_fops;
	inode->i_nlink = 1;
	inode->i_uid = 0;
	inode->i_gid = 0;
	atomic_set(&inode->i_writecount, 0);
	inode->i_size = 0;
	inode->i_blocks = 0;
	inode->i_bytes = 0;
	inode->i_generation = 0;
#ifdef CONFIG_QUOTA
	memset(&inode->i_dquot, 0, sizeof(inode->i_dquot));
#endif
	inode->i_pipe = NULL;
	inode->i_bdev = NULL;
	inode->i_cdev = NULL;
	inode->i_rdev = 0;
	inode->dirtied_when = 0;

	if (security_inode_alloc(inode))
		goto out;
	spin_lock_init(&inode->i_lock);
	lockdep_set_class(&inode->i_lock, &sb->s_type->i_lock_key);

	mutex_init(&inode->i_mutex);
	lockdep_set_class(&inode->i_mutex, &sb->s_type->i_mutex_key);

	init_rwsem(&inode->i_alloc_sem);
	lockdep_set_class(&inode->i_alloc_sem, &sb->s_type->i_alloc_sem_key);

	mapping->a_ops = &empty_aops;
	mapping->host = inode;
	mapping->flags = 0;
	mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE);
	mapping->assoc_mapping = NULL;
	mapping->backing_dev_info = &default_backing_dev_info;
	mapping->writeback_index = 0;

	/*
	 * If the block_device provides a backing_dev_info for client
	 * inodes then use that.  Otherwise the inode share the bdev's
	 * backing_dev_info.
	 */
	if (sb->s_bdev) {
		struct backing_dev_info *bdi;

		bdi = sb->s_bdev->bd_inode->i_mapping->backing_dev_info;
		mapping->backing_dev_info = bdi;
	}
	inode->i_private = NULL;
	inode->i_mapping = mapping;
#ifdef CONFIG_FS_POSIX_ACL
	inode->i_acl = inode->i_default_acl = ACL_NOT_CACHED;
#endif

#ifdef CONFIG_FSNOTIFY
	inode->i_fsnotify_mask = 0;
#endif

	this_cpu_inc(nr_inodes);

	return 0;
out:
	return -ENOMEM;
}
EXPORT_SYMBOL(inode_init_always);

static struct inode *alloc_inode(struct super_block *sb)
{
	struct inode *inode;

	if (sb->s_op->alloc_inode)
		inode = sb->s_op->alloc_inode(sb);
	else
		inode = kmem_cache_alloc(inode_cachep, GFP_KERNEL);

	if (!inode)
		return NULL;

	if (unlikely(inode_init_always(sb, inode))) {
		if (inode->i_sb->s_op->destroy_inode)
			inode->i_sb->s_op->destroy_inode(inode);
		else
			kmem_cache_free(inode_cachep, inode);
		return NULL;
	}

	return inode;
}

void free_inode_nonrcu(struct inode *inode)
{
	kmem_cache_free(inode_cachep, inode);
}
EXPORT_SYMBOL(free_inode_nonrcu);

void __destroy_inode(struct inode *inode)
{
	BUG_ON(inode_has_buffers(inode));
	security_inode_free(inode);
	fsnotify_inode_delete(inode);
#ifdef CONFIG_FS_POSIX_ACL
	if (inode->i_acl && inode->i_acl != ACL_NOT_CACHED)
		posix_acl_release(inode->i_acl);
	if (inode->i_default_acl && inode->i_default_acl != ACL_NOT_CACHED)
		posix_acl_release(inode->i_default_acl);
#endif
	this_cpu_dec(nr_inodes);
}
EXPORT_SYMBOL(__destroy_inode);

static void i_callback(struct rcu_head *head)
{
	struct inode *inode = container_of(head, struct inode, i_rcu);
	INIT_LIST_HEAD(&inode->i_dentry);
	kmem_cache_free(inode_cachep, 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);
	else
		call_rcu(&inode->i_rcu, i_callback);
}

void address_space_init_once(struct address_space *mapping)
{
	memset(mapping, 0, sizeof(*mapping));
	INIT_RADIX_TREE(&mapping->page_tree, GFP_ATOMIC);
	spin_lock_init(&mapping->tree_lock);
	mutex_init(&mapping->i_mmap_mutex);
	INIT_LIST_HEAD(&mapping->private_list);
	spin_lock_init(&mapping->private_lock);
	INIT_RAW_PRIO_TREE_ROOT(&mapping->i_mmap);
	INIT_LIST_HEAD(&mapping->i_mmap_nonlinear);
}
EXPORT_SYMBOL(address_space_init_once);

/*
 * These are initializations that only need to be done
 * once, because the fields are idempotent across use
 * of the inode, so let the slab aware of that.
 */
void inode_init_once(struct inode *inode)
{
	memset(inode, 0, sizeof(*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);
	address_space_init_once(&inode->i_data);
	i_size_ordered_init(inode);
#ifdef CONFIG_FSNOTIFY
	INIT_HLIST_HEAD(&inode->i_fsnotify_marks);
#endif
}
EXPORT_SYMBOL(inode_init_once);

static void init_once(void *foo)
{
	struct inode *inode = (struct inode *) foo;

	inode_init_once(inode);
}

/*
 * inode->i_lock must be held
 */
void __iget(struct inode *inode)
{
	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)
{
	spin_lock(&inode_lru_lock);
	if (list_empty(&inode->i_lru)) {
		list_add(&inode->i_lru, &inode_lru);
		inodes_stat.nr_unused++;
	}
	spin_unlock(&inode_lru_lock);
}

static void inode_lru_list_del(struct inode *inode)
{
	spin_lock(&inode_lru_lock);
	if (!list_empty(&inode->i_lru)) {
		list_del_init(&inode->i_lru);
		inodes_stat.nr_unused--;
	}
	spin_unlock(&inode_lru_lock);
}

/**
 * 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_sb_list_lock);
	list_add(&inode->i_sb_list, &inode->i_sb->s_inodes);
	spin_unlock(&inode_sb_list_lock);
}
EXPORT_SYMBOL_GPL(inode_sb_list_add);

static inline void inode_sb_list_del(struct inode *inode)
{
	spin_lock(&inode_sb_list_lock);
	list_del_init(&inode->i_sb_list);
	spin_unlock(&inode_sb_list_lock);
}

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_hash_shift);
	return tmp & i_hash_mask;
}

/**
 *	__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_hash_lock);
	spin_lock(&inode->i_lock);
	hlist_add_head(&inode->i_hash, b);
	spin_unlock(&inode->i_lock);
	spin_unlock(&inode_hash_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_hash_lock);
	spin_lock(&inode->i_lock);
	hlist_del_init(&inode->i_hash);
	spin_unlock(&inode->i_lock);
	spin_unlock(&inode_hash_lock);
}
EXPORT_SYMBOL(remove_inode_hash);

void end_writeback(struct inode *inode)
{
	might_sleep();
	BUG_ON(inode->i_data.nrpages);
	BUG_ON(!list_empty(&inode->i_data.private_list));
	BUG_ON(!(inode->i_state & I_FREEING));
	BUG_ON(inode->i_state & I_CLEAR);
	inode_sync_wait(inode);
	/* don't need i_lock here, no concurrent mods to i_state */
	inode->i_state = I_FREEING | I_CLEAR;
}
EXPORT_SYMBOL(end_writeback);

/*
 * Free the inode passed in, removing it from the lists it is still connected
 * to. We remove any pages still attached to the inode and wait for any IO that
 * is still in progress before finally destroying the inode.
 *
 * An inode must already be marked I_FREEING so that we avoid the inode being
 * moved back onto lists if we race with other code that manipulates the lists
 * (e.g. writeback_single_inode). The caller is responsible for setting this.
 *
 * An inode must already be removed from the LRU list before being evicted from
 * the cache. This should occur atomically with setting the I_FREEING state
 * flag, so no inodes here should ever be on the LRU when being evicted.
 */
static void evict(struct inode *inode)
{
	const struct super_operations *op = inode->i_sb->s_op;

	BUG_ON(!(inode->i_state & I_FREEING));
	BUG_ON(!list_empty(&inode->i_lru));

	inode_wb_list_del(inode);
	inode_sb_list_del(inode);

	if (op->evict_inode) {
		op->evict_inode(inode);
	} else {
		if (inode->i_data.nrpages)
			truncate_inode_pages(&inode->i_data, 0);
		end_writeback(inode);
	}
	if (S_ISBLK(inode->i_mode) && inode->i_bdev)
		bd_forget(inode);
	if (S_ISCHR(inode->i_mode) && inode->i_cdev)
		cd_forget(inode);

	remove_inode_hash(inode);

	spin_lock(&inode->i_lock);
	wake_up_bit(&inode->i_state, __I_NEW);
	BUG_ON(inode->i_state != (I_FREEING | I_CLEAR));
	spin_unlock(&inode->i_lock);

	destroy_inode(inode);
}

/*
 * dispose_list - dispose of the contents of a local list
 * @head: the head of the list to free
 *
 * Dispose-list gets a local list with local inodes in it, so it doesn't
 * need to worry about list corruption and SMP locks.
 */
static void dispose_list(struct list_head *head)
{
	while (!list_empty(head)) {
		struct inode *inode;

		inode = list_first_entry(head, struct inode, i_lru);
		list_del_init(&inode->i_lru);

		evict(inode);
	}
}

/**
 * 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.
 */
void evict_inodes(struct super_block *sb)
{
	struct inode *inode, *next;
	LIST_HEAD(dispose);

	spin_lock(&inode_sb_list_lock);
	list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
		if (atomic_read(&inode->i_count))
			continue;

		spin_lock(&inode->i_lock);
		if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
			spin_unlock(&inode->i_lock);
			continue;
		}

		inode->i_state |= I_FREEING;
		inode_lru_list_del(inode);
		spin_unlock(&inode->i_lock);
		list_add(&inode->i_lru, &dispose);
	}
	spin_unlock(&inode_sb_list_lock);

	dispose_list(&dispose);

	/*
	 * Cycle through iprune_sem to make sure any inode that prune_icache
	 * moved off the list before we took the lock has been fully torn
	 * down.
	 */
	down_write(&iprune_sem);
	up_write(&iprune_sem);
}

/**
 * invalidate_inodes	- attempt to free all inodes on a superblock
 * @sb:		superblock to operate on
 * @kill_dirty: flag to guide handling of dirty inodes
 *
 * Attempts to free all inodes for a given superblock.  If there were any
 * busy inodes return a non-zero value, else zero.
 * If @kill_dirty is set, discard dirty inodes too, otherwise treat
 * them as busy.
 */
int invalidate_inodes(struct super_block *sb, bool kill_dirty)
{
	int busy = 0;
	struct inode *inode, *next;
	LIST_HEAD(dispose);

	spin_lock(&inode_sb_list_lock);
	list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
		spin_lock(&inode->i_lock);
		if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
			spin_unlock(&inode->i_lock);
			continue;
		}
		if (inode->i_state & I_DIRTY && !kill_dirty) {
			spin_unlock(&inode->i_lock);
			busy = 1;
			continue;
		}
		if (atomic_read(&inode->i_count)) {
			spin_unlock(&inode->i_lock);
			busy = 1;
			continue;
		}

		inode->i_state |= I_FREEING;
		inode_lru_list_del(inode);
		spin_unlock(&inode->i_lock);
		list_add(&inode->i_lru, &dispose);
	}
	spin_unlock(&inode_sb_list_lock);

	dispose_list(&dispose);

	return busy;
}

static int can_unuse(struct inode *inode)
{
	if (inode->i_state & ~I_REFERENCED)
		return 0;
	if (inode_has_buffers(inode))
		return 0;
	if (atomic_read(&inode->i_count))
		return 0;
	if (inode->i_data.nrpages)
		return 0;
	return 1;
}

/*
 * Scan `goal' inodes on the unused list for freeable ones. They are moved to a
 * temporary list and then are freed outside inode_lru_lock by dispose_list().
 *
 * Any inodes which are pinned purely because of attached pagecache have their
 * pagecache removed.  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_scanned;
	unsigned long reap = 0;

	down_read(&iprune_sem);
	spin_lock(&inode_lru_lock);
	for (nr_scanned = 0; nr_scanned < nr_to_scan; nr_scanned++) {
		struct inode *inode;

		if (list_empty(&inode_lru))
			break;

		inode = list_entry(inode_lru.prev, struct inode, i_lru);

		/*
		 * we are inverting the inode_lru_lock/inode->i_lock here,
		 * so use a trylock. If we fail to get the lock, just move the
		 * inode to the back of the list so we don't spin on it.
		 */
		if (!spin_trylock(&inode->i_lock)) {
			list_move(&inode->i_lru, &inode_lru);
			continue;
		}

		/*
		 * 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);
			spin_unlock(&inode->i_lock);
			inodes_stat.nr_unused--;
			continue;
		}

		/* recently referenced inodes get one more pass */
		if (inode->i_state & I_REFERENCED) {
			inode->i_state &= ~I_REFERENCED;
			list_move(&inode->i_lru, &inode_lru);
			spin_unlock(&inode->i_lock);
			continue;
		}
		if (inode_has_buffers(inode) || inode->i_data.nrpages) {
			__iget(inode);
			spin_unlock(&inode->i_lock);
			spin_unlock(&inode_lru_lock);
			if (remove_inode_buffers(inode))
				reap += invalidate_mapping_pages(&inode->i_data,
								0, -1);
			iput(inode);
			spin_lock(&inode_lru_lock);

			if (inode != list_entry(inode_lru.next,
						struct inode, i_lru))
				continue;	/* wrong inode or list_empty */
			/* avoid lock inversions with trylock */
			if (!spin_trylock(&inode->i_lock))
				continue;
			if (!can_unuse(inode)) {
				spin_unlock(&inode->i_lock);
				continue;
			}
		}
		WARN_ON(inode->i_state & I_NEW);
		inode->i_state |= I_FREEING;
		spin_unlock(&inode->i_lock);

		list_move(&inode->i_lru, &freeable);
		inodes_stat.nr_unused--;
	}
	if (current_is_kswapd())
		__count_vm_events(KSWAPD_INODESTEAL, reap);
	else
		__count_vm_events(PGINODESTEAL, reap);
	spin_unlock(&inode_lru_lock);

	dispose_list(&freeable);
	up_read(&iprune_sem);
}

/*
 * shrink_icache_memory() will attempt to reclaim some unused inodes.  Here,
 * "unused" means that no dentries are referring to the inodes: the files are
 * not open and the dcache references to those inodes have already been
 * reclaimed.
 *
 * This function is passed the number of inodes to scan, and it returns the
 * total number of remaining possibly-reclaimable inodes.
 */
static int shrink_icache_memory(struct shrinker *shrink,
				struct shrink_control *sc)
{
	int nr = sc->nr_to_scan;
	gfp_t gfp_mask = sc->gfp_mask;

	if (nr) {
		/*
		 * Nasty deadlock avoidance.  We may hold various FS locks,
		 * and we don't want to recurse into the FS that called us
		 * in clear_inode() and friends..
		 */
		if (!(gfp_mask & __GFP_FS))
			return -1;
		prune_icache(nr);
	}
	return (get_nr_inodes_unused() / 100) * sysctl_vfs_cache_pressure;
}

static struct shrinker icache_shrinker = {
	.shrink = shrink_icache_memory,
	.seeks = DEFAULT_SEEKS,
};

static void __wait_on_freeing_inode(struct inode *inode);
/*
 * Called with the inode lock held.
 */
static struct inode *find_inode(struct super_block *sb,
				struct hlist_head *head,
				int (*test)(struct inode *, void *),
				void *data)
{
	struct hlist_node *node;
	struct inode *inode = NULL;

repeat:
	hlist_for_each_entry(inode, node, head, i_hash) {
		spin_lock(&inode->i_lock);
		if (inode->i_sb != sb) {
			spin_unlock(&inode->i_lock);
			continue;
		}
		if (!test(inode, data)) {
			spin_unlock(&inode->i_lock);
			continue;
		}
		if (inode->i_state & (I_FREEING|I_WILL_FREE)) {
			__wait_on_freeing_inode(inode);
			goto repeat;
		}
		__iget(inode);
		spin_unlock(&inode->i_lock);
		return inode;
	}
	return NULL;
}

/*
 * find_inode_fast is the fast path version of find_inode, see the comment at
 * iget_locked for details.
 */
static struct inode *find_inode_fast(struct super_block *sb,
				struct hlist_head *head, unsigned long ino)
{
	struct hlist_node *node;
	struct inode *inode = NULL;

repeat:
	hlist_for_each_entry(inode, node, head, i_hash) {
		spin_lock(&inode->i_lock);
		if (inode->i_ino != ino) {
			spin_unlock(&inode->i_lock);
			continue;
		}
		if (inode->i_sb != sb) {
			spin_unlock(&inode->i_lock);
			continue;
		}
		if (inode->i_state & (I_FREEING|I_WILL_FREE)) {
			__wait_on_freeing_inode(inode);
			goto repeat;
		}
		__iget(inode);
		spin_unlock(&inode->i_lock);
		return inode;
	}
	return NULL;
}

/*
 * 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.
 *
 * 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.
 */
#define LAST_INO_BATCH 1024
static DEFINE_PER_CPU(unsigned int, last_ino);

unsigned int get_next_ino(void)
{
	unsigned int *p = &get_cpu_var(last_ino);
	unsigned int res = *p;

#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(get_next_ino);

/**
 *	new_inode 	- obtain an inode
 *	@sb: superblock
 *
 *	Allocates a new inode for given superblock. The default gfp_mask
 *	for allocations related to inode->i_mapping is GFP_HIGHUSER_MOVABLE.
 *	If HIGHMEM pages are unsuitable or it is known that pages allocated
 *	for the page cache are not reclaimable or migratable,
 *	mapping_set_gfp_mask() must be called with suitable flags on the
 *	newly created inode's mapping
 *
 */
struct inode *new_inode(struct super_block *sb)
{
	struct inode *inode;

	spin_lock_prefetch(&inode_sb_list_lock);

	inode = alloc_inode(sb);
	if (inode) {
		spin_lock(&inode->i_lock);
		inode->i_state = 0;
		spin_unlock(&inode->i_lock);
		inode_sb_list_add(inode);
	}
	return inode;
}
EXPORT_SYMBOL(new_inode);

/**
 * unlock_new_inode - clear the I_NEW state and wake up any waiters
 * @inode:	new inode to unlock
 *
 * Called when the inode is fully initialised to clear the new state of the
 * inode and wake up anyone waiting for the inode to finish initialisation.
 */
void unlock_new_inode(struct inode *inode)
{
#ifdef CONFIG_DEBUG_LOCK_ALLOC
	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 */
		if (!lockdep_match_class(&inode->i_mutex,
		    &type->i_mutex_key)) {
			/*
			 * ensure nobody is actually holding i_mutex
			 */
			mutex_destroy(&inode->i_mutex);
			mutex_init(&inode->i_mutex);
			lockdep_set_class(&inode->i_mutex,
					  &type->i_mutex_dir_key);
		}
	}
#endif
	spin_lock(&inode->i_lock);
	WARN_ON(!(inode->i_state & I_NEW));
	inode->i_state &= ~I_NEW;
	wake_up_bit(&inode->i_state, __I_NEW);
	spin_unlock(&inode->i_lock);
}
EXPORT_SYMBOL(unlock_new_inode);

/**
 * iget5_locked - obtain an inode from a mounted file system
 * @sb:		super block of file system
 * @hashval:	hash value (usually inode number) to get
 * @test:	callback used for comparisons between inodes
 * @set:	callback used to initialize a new struct inode
 * @data:	opaque data pointer to pass to @test and @set
 *
 * Search for the inode specified by @hashval and @data in the inode cache,
 * and if present it is return it with an increased reference count. This is
 * a generalized version of iget_locked() for file systems where the inode
 * number is not sufficient for unique identification of an inode.
 *
 * If the inode is not in cache, allocate a new inode and return it locked,
 * hashed, and with the I_NEW flag set. The file system gets to fill it in
 * before unlocking it via unlock_new_inode().
 *
 * Note both @test and @set are called with the inode_hash_lock held, so can't
 * sleep.
 */
struct inode *iget5_locked(struct super_block *sb, unsigned long hashval,
		int (*test)(struct inode *, void *),
		int (*set)(struct inode *, void *), void *data)
{
	struct hlist_head *head = inode_hashtable + hash(sb, hashval);
	struct inode *inode;

	spin_lock(&inode_hash_lock);
	inode = find_inode(sb, head, test, data);
	spin_unlock(&inode_hash_lock);

	if (inode) {
		wait_on_inode(inode);
		return inode;
	}

	inode = alloc_inode(sb);
	if (inode) {
		struct inode *old;

		spin_lock(&inode_hash_lock);
		/* We released the lock, so.. */
		old = find_inode(sb, head, test, data);
		if (!old) {
			if (set(inode, data))
				goto set_failed;

			spin_lock(&inode->i_lock);
			inode->i_state = I_NEW;
			hlist_add_head(&inode->i_hash, head);
			spin_unlock(&inode->i_lock);
			inode_sb_list_add(inode);
			spin_unlock(&inode_hash_lock);

			/* Return the locked inode with I_NEW set, the
			 * caller is responsible for filling in the contents
			 */
			return inode;
		}

		/*
		 * Uhhuh, somebody else created the same inode under
		 * us. Use the old inode instead of the one we just
		 * allocated.
		 */
		spin_unlock(&inode_hash_lock);
		destroy_inode(inode);
		inode = old;
		wait_on_inode(inode);
	}
	return inode;

set_failed:
	spin_unlock(&inode_hash_lock);
	destroy_inode(inode);
	return NULL;
}
EXPORT_SYMBOL(iget5_locked);

/**
 * iget_locked - obtain an inode from a mounted file system
 * @sb:		super block of file system
 * @ino:	inode number to get
 *
 * Search for the inode specified by @ino in the inode cache and if present
 * return it with an increased reference count. This is for file systems
 * where the inode number is sufficient for unique identification of an inode.
 *
 * If the inode is not in cache, allocate a new inode and return it locked,
 * hashed, and with the I_NEW flag set.  The file system gets to fill it in
 * before unlocking it via unlock_new_inode().
 */
struct inode *iget_locked(struct super_block *sb, unsigned long ino)
{
	struct hlist_head *head = inode_hashtable + hash(sb, ino);
	struct inode *inode;

	spin_lock(&inode_hash_lock);
	inode = find_inode_fast(sb, head, ino);
	spin_unlock(&inode_hash_lock);
	if (inode) {
		wait_on_inode(inode);
		return inode;
	}

	inode = alloc_inode(sb);
	if (inode) {
		struct inode *old;

		spin_lock(&inode_hash_lock);
		/* We released the lock, so.. */
		old = find_inode_fast(sb, head, ino);
		if (!old) {
			inode->i_ino = ino;
			spin_lock(&inode->i_lock);
			inode->i_state = I_NEW;
			hlist_add_head(&inode->i_hash, head);
			spin_unlock(&inode->i_lock);
			inode_sb_list_add(inode);
			spin_unlock(&inode_hash_lock);

			/* Return the locked inode with I_NEW set, the
			 * caller is responsible for filling in the contents
			 */
			return inode;
		}

		/*
		 * Uhhuh, somebody else created the same inode under
		 * us. Use the old inode instead of the one we just
		 * allocated.
		 */
		spin_unlock(&inode_hash_lock);
		destroy_inode(inode);
		inode = old;
		wait_on_inode(inode);
	}
	return inode;
}
EXPORT_SYMBOL(iget_locked);

/*
 * 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;

	spin_lock(&inode_hash_lock);
	hlist_for_each_entry(inode, node, b, i_hash) {
		if (inode->i_ino == ino && inode->i_sb == sb) {
			spin_unlock(&inode_hash_lock);
			return 0;
		}
	}
	spin_unlock(&inode_hash_lock);

	return 1;
}

/**
 *	iunique - get a unique inode number
 *	@sb: superblock
 *	@max_reserved: highest reserved inode number
 *
 *	Obtain an inode number that is unique on the system for a given
 *	superblock. This is used by file systems that have no natural
 *	permanent inode numbering system. An inode number is returned that
 *	is higher than the reserved limit but unique.
 *
 *	BUGS:
 *	With a large number of inodes live on the file system this function
 *	currently becomes quite slow.
 */
ino_t iunique(struct super_block *sb, ino_t max_reserved)
{
	/*
	 * 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 DEFINE_SPINLOCK(iunique_lock);
	static unsigned int counter;
	ino_t res;

	spin_lock(&iunique_lock);
	do {
		if (counter <= max_reserved)
			counter = max_reserved + 1;
		res = counter++;
	} while (!test_inode_iunique(sb, res));
	spin_unlock(&iunique_lock);

	return res;
}
EXPORT_SYMBOL(iunique);

struct inode *igrab(struct inode *inode)
{
	spin_lock(&inode->i_lock);
	if (!(inode->i_state & (I_FREEING|I_WILL_FREE))) {
		__iget(inode);
		spin_unlock(&inode->i_lock);
	} else {
		spin_unlock(&inode->i_lock);
		/*
		 * Handle the case where s_op->clear_inode is not been
		 * called yet, and somebody is calling igrab
		 * while the inode is getting freed.
		 */
		inode = NULL;
	}
	return inode;
}
EXPORT_SYMBOL(igrab);

/**
 * ilookup5_nowait - search for an inode in the inode cache
 * @sb:		super block of file system to search
 * @hashval:	hash value (usually inode number) to search for
 * @test:	callback used for comparisons between inodes
 * @data:	opaque data pointer to pass to @test
 *
 * Search for the inode specified by @hashval and @data in the inode cache.
 * If the inode is in the cache, the inode is returned with an incremented
 * reference count.
 *
 * Note: I_NEW is not waited upon so you have to be very careful what you do
 * with the returned inode.  You probably should be using ilookup5() instead.
 *
 * Note2: @test is called with the inode_hash_lock held, so can't sleep.
 */
struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval,
		int (*test)(struct inode *, void *), void *data)
{
	struct hlist_head *head = inode_hashtable + hash(sb, hashval);
	struct inode *inode;

	spin_lock(&inode_hash_lock);
	inode = find_inode(sb, head, test, data);
	spin_unlock(&inode_hash_lock);

	return inode;
}
EXPORT_SYMBOL(ilookup5_nowait);

/**
 * ilookup5 - search for an inode in the inode cache
 * @sb:		super block of file system to search
 * @hashval:	hash value (usually inode number) to search for
 * @test:	callback used for comparisons between inodes
 * @data:	opaque data pointer to pass to @test
 *
 * Search for the inode specified by @hashval and @data in the inode cache,
 * and if the inode is in the cache, return the inode with an incremented
 * reference count.  Waits on I_NEW before returning the inode.
 * returned with an incremented reference count.
 *
 * This is a generalized version of ilookup() for file systems where the
 * inode number is not sufficient for unique identification of an inode.
 *
 * Note: @test is called with the inode_hash_lock held, so can't sleep.
 */
struct inode *ilookup5(struct super_block *sb, unsigned long hashval,
		int (*test)(struct inode *, void *), void *data)
{
	struct inode *inode = ilookup5_nowait(sb, hashval, test, data);

	if (inode)
		wait_on_inode(inode);
	return inode;
}
EXPORT_SYMBOL(ilookup5);

/**
 * ilookup - search for an inode in the inode cache
 * @sb:		super block of file system to search
 * @ino:	inode number to search for
 *
 * Search for the inode @ino in the inode cache, and if the inode is in the
 * cache, the inode is returned with an incremented reference count.