dcache.c

/*
 * fs/dcache.c
 *
 * Complete reimplementation
 * (C) 1997 Thomas Schoebel-Theuer,
 * with heavy changes by Linus Torvalds
 */

/*
 * Notes on the allocation strategy:
 *
 * The dcache is a master of the icache - whenever a dcache entry
 * exists, the inode will always exist. "iput()" is done either when
 * the dcache entry is deleted or garbage collected.
 */

#include <linux/syscalls.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/fsnotify.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/hash.h>
#include <linux/cache.h>
#include <linux/module.h>
#include <linux/mount.h>
#include <linux/file.h>
#include <asm/uaccess.h>
#include <linux/security.h>
#include <linux/seqlock.h>
#include <linux/swap.h>
#include <linux/bootmem.h>
#include "internal.h"


int sysctl_vfs_cache_pressure __read_mostly = 100;
EXPORT_SYMBOL_GPL(sysctl_vfs_cache_pressure);

 __cacheline_aligned_in_smp DEFINE_SPINLOCK(dcache_lock);
__cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock);

EXPORT_SYMBOL(dcache_lock);

static struct kmem_cache *dentry_cache __read_mostly;

#define DNAME_INLINE_LEN (sizeof(struct dentry)-offsetof(struct dentry,d_iname))

/*
 * This is the single most critical data structure when it comes
 * to the dcache: the hashtable for lookups. Somebody should try
 * to make this good - I've just made it work.
 *
 * This hash-function tries to avoid losing too many bits of hash
 * information, yet avoid using a prime hash-size or similar.
 */
#define D_HASHBITS     d_hash_shift
#define D_HASHMASK     d_hash_mask

static unsigned int d_hash_mask __read_mostly;
static unsigned int d_hash_shift __read_mostly;
static struct hlist_head *dentry_hashtable __read_mostly;
static LIST_HEAD(dentry_unused);

/* Statistics gathering. */
struct dentry_stat_t dentry_stat = {
	.age_limit = 45,
};

static void __d_free(struct dentry *dentry)
{
	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.
 */
static void d_free(struct dentry *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);
	else
		call_rcu(&dentry->d_u.d_rcu, d_callback);
}

static void dentry_lru_remove(struct dentry *dentry)
{
	if (!list_empty(&dentry->d_lru)) {
		list_del_init(&dentry->d_lru);
		dentry_stat.nr_unused--;
	}
}

/*
 * Release the dentry's inode, using the filesystem
 * d_iput() operation if defined.
 * Called with dcache_lock and per dentry lock held, drops both.
 */
static void dentry_iput(struct dentry * dentry)
{
	struct inode *inode = dentry->d_inode;
	if (inode) {
		dentry->d_inode = NULL;
		list_del_init(&dentry->d_alias);
		spin_unlock(&dentry->d_lock);
		spin_unlock(&dcache_lock);
		if (!inode->i_nlink)
			fsnotify_inoderemove(inode);
		if (dentry->d_op && dentry->d_op->d_iput)
			dentry->d_op->d_iput(dentry, inode);
		else
			iput(inode);
	} else {
		spin_unlock(&dentry->d_lock);
		spin_unlock(&dcache_lock);
	}
}

/**
 * d_kill - kill dentry and return parent
 * @dentry: dentry to kill
 *
 * Called with dcache_lock and d_lock, releases both.  The dentry must
 * already be unhashed and removed from the LRU.
 *
 * If this is the root of the dentry tree, return NULL.
 */
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);
	parent = dentry->d_parent;
	d_free(dentry);
	return dentry == parent ? NULL : parent;
}

/* 
 * This is dput
 *
 * This is complicated by the fact that we do not want to put
 * dentries that are no longer on any hash chain on the unused
 * list: we'd much rather just get rid of them immediately.
 *
 * However, that implies that we have to traverse the dentry
 * tree upwards to the parents which might _also_ now be
 * scheduled for deletion (it may have been only waiting for
 * its last child to go away).
 *
 * This tail recursion is done by hand as we don't want to depend
 * on the compiler to always get this right (gcc generally doesn't).
 * Real recursion would eat up our stack space.
 */

/*
 * dput - release a dentry
 * @dentry: dentry to release 
 *
 * Release a dentry. This will drop the usage count and if appropriate
 * call the dentry unlink method as well as removing it from the queues and
 * releasing its resources. If the parent dentries were scheduled for release
 * they too may now get deleted.
 *
 * no dcache lock, please.
 */

void dput(struct dentry *dentry)
{
	if (!dentry)
		return;

repeat:
	if (atomic_read(&dentry->d_count) == 1)
		might_sleep();
	if (!atomic_dec_and_lock(&dentry->d_count, &dcache_lock))
		return;

	spin_lock(&dentry->d_lock);
	if (atomic_read(&dentry->d_count)) {
		spin_unlock(&dentry->d_lock);
		spin_unlock(&dcache_lock);
		return;
	}

	/*
	 * AV: ->d_delete() is _NOT_ allowed to block now.
	 */
	if (dentry->d_op && dentry->d_op->d_delete) {
		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;
  		list_add(&dentry->d_lru, &dentry_unused);
  		dentry_stat.nr_unused++;
  	}
 	spin_unlock(&dentry->d_lock);
	spin_unlock(&dcache_lock);
	return;

unhash_it:
	__d_drop(dentry);
kill_it:
	dentry_lru_remove(dentry);
	dentry = d_kill(dentry);
	if (dentry)
		goto repeat;
}

/**
 * d_invalidate - invalidate a dentry
 * @dentry: dentry to invalidate
 *
 * Try to invalidate the dentry if it turns out to be
 * possible. If there are other dentries that can be
 * reached through this one we can't delete it and we
 * return -EBUSY. On success we return 0.
 *
 * no dcache lock.
 */
 
int d_invalidate(struct dentry * dentry)
{
	/*
	 * If it's already been dropped, return OK.
	 */
	spin_lock(&dcache_lock);
	if (d_unhashed(dentry)) {
		spin_unlock(&dcache_lock);
		return 0;
	}
	/*
	 * Check whether to do a partial shrink_dcache
	 * to get rid of unused child entries.
	 */
	if (!list_empty(&dentry->d_subdirs)) {
		spin_unlock(&dcache_lock);
		shrink_dcache_parent(dentry);
		spin_lock(&dcache_lock);
	}

	/*
	 * Somebody else still using it?
	 *
	 * If it's a directory, we can't drop it
	 * for fear of somebody re-populating it
	 * with children (even though dropping it
	 * would make it unreachable from the root,
	 * we might still populate it if it was a
	 * working directory or similar).
	 */
	spin_lock(&dentry->d_lock);
	if (atomic_read(&dentry->d_count) > 1) {
		if (dentry->d_inode && S_ISDIR(dentry->d_inode->i_mode)) {
			spin_unlock(&dentry->d_lock);
			spin_unlock(&dcache_lock);
			return -EBUSY;
		}
	}

	__d_drop(dentry);
	spin_unlock(&dentry->d_lock);
	spin_unlock(&dcache_lock);
	return 0;
}

/* 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_remove(dentry);
	return dentry;
}

struct dentry * dget_locked(struct dentry *dentry)
{
	return __dget_locked(dentry);
}

/**
 * d_find_alias - grab a hashed alias of inode
 * @inode: inode in question
 * @want_discon:  flag, used by d_splice_alias, to request
 *          that only a DISCONNECTED alias be returned.
 *
 * If inode has a hashed alias, or is a directory and has any alias,
 * acquire the reference to alias and return it. Otherwise return NULL.
 * Notice that if inode is a directory there can be only one alias and
 * it can be unhashed only if it has no children, or if it is the root
 * of a filesystem.
 *
 * If the inode has an IS_ROOT, DCACHE_DISCONNECTED alias, then prefer
 * any other hashed alias over that one unless @want_discon is set,
 * in which case only return an IS_ROOT, DCACHE_DISCONNECTED alias.
 */

static struct dentry * __d_find_alias(struct inode *inode, int want_discon)
{
	struct list_head *head, *next, *tmp;
	struct dentry *alias, *discon_alias=NULL;

	head = &inode->i_dentry;
	next = inode->i_dentry.next;
	while (next != head) {
		tmp = next;
		next = tmp->next;
		prefetch(next);
		alias = list_entry(tmp, struct dentry, d_alias);
 		if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) {
			if (IS_ROOT(alias) &&
			    (alias->d_flags & DCACHE_DISCONNECTED))
				discon_alias = alias;
			else if (!want_discon) {
				__dget_locked(alias);
				return alias;
			}
		}
	}
	if (discon_alias)
		__dget_locked(discon_alias);
	return discon_alias;
}

struct dentry * d_find_alias(struct inode *inode)
{
	struct dentry *de = NULL;

	if (!list_empty(&inode->i_dentry)) {
		spin_lock(&dcache_lock);
		de = __d_find_alias(inode, 0);
		spin_unlock(&dcache_lock);
	}
	return de;
}

/*
 *	Try to kill dentries associated with this inode.
 * WARNING: you must own a reference to inode.
 */
void d_prune_aliases(struct inode *inode)
{
	struct dentry *dentry;
restart:
	spin_lock(&dcache_lock);
	list_for_each_entry(dentry, &inode->i_dentry, d_alias) {
		spin_lock(&dentry->d_lock);
		if (!atomic_read(&dentry->d_count)) {
			__dget_locked(dentry);
			__d_drop(dentry);
			spin_unlock(&dentry->d_lock);
			spin_unlock(&dcache_lock);
			dput(dentry);
			goto restart;
		}
		spin_unlock(&dentry->d_lock);
	}
	spin_unlock(&dcache_lock);
}

/*
 * Throw away a dentry - free the inode, dput the parent.  This requires that
 * the LRU list has already been removed.
 *
 * Try to prune ancestors as well.  This is necessary to prevent
 * quadratic behavior of shrink_dcache_parent(), but is also expected
 * to be beneficial in reducing dentry cache fragmentation.
 *
 * Called with dcache_lock, drops it and then regains.
 * Called with dentry->d_lock held, drops it.
 */
static void prune_one_dentry(struct dentry * dentry)
{
	__d_drop(dentry);
	dentry = d_kill(dentry);

	/*
	 * Prune ancestors.  Locking is simpler than in dput(),
	 * because dcache_lock needs to be taken anyway.
	 */
	spin_lock(&dcache_lock);
	while (dentry) {
		if (!atomic_dec_and_lock(&dentry->d_count, &dentry->d_lock))
			return;

		if (dentry->d_op && dentry->d_op->d_delete)
			dentry->d_op->d_delete(dentry);
		dentry_lru_remove(dentry);
		__d_drop(dentry);
		dentry = d_kill(dentry);
		spin_lock(&dcache_lock);
	}
}

/**
 * prune_dcache - shrink the dcache
 * @count: number of entries to try and free
 * @sb: if given, ignore dentries for other superblocks
 *         which are being unmounted.
 *
 * Shrink the dcache. This is done when we need
 * more memory, or simply when we need to unmount
 * something (at which point we need to unuse
 * all dentries).
 *
 * This function may fail to free any resources if
 * all the dentries are in use.
 */
 
static void prune_dcache(int count, struct super_block *sb)
{
	spin_lock(&dcache_lock);
	for (; count ; count--) {
		struct dentry *dentry;
		struct list_head *tmp;
		struct rw_semaphore *s_umount;

		cond_resched_lock(&dcache_lock);

		tmp = dentry_unused.prev;
		if (sb) {
			/* Try to find a dentry for this sb, but don't try
			 * too hard, if they aren't near the tail they will
			 * be moved down again soon
			 */
			int skip = count;
			while (skip && tmp != &dentry_unused &&
			    list_entry(tmp, struct dentry, d_lru)->d_sb != sb) {
				skip--;
				tmp = tmp->prev;
			}
		}
		if (tmp == &dentry_unused)
			break;
		list_del_init(tmp);
		prefetch(dentry_unused.prev);
 		dentry_stat.nr_unused--;
		dentry = list_entry(tmp, struct dentry, d_lru);

 		spin_lock(&dentry->d_lock);
		/*
		 * We found an inuse dentry which was not removed from
		 * dentry_unused because of laziness during lookup.  Do not free
		 * it - just keep it off the dentry_unused list.
		 */
 		if (atomic_read(&dentry->d_count)) {
 			spin_unlock(&dentry->d_lock);
			continue;
		}
		/* If the dentry was recently referenced, don't free it. */
		if (dentry->d_flags & DCACHE_REFERENCED) {
			dentry->d_flags &= ~DCACHE_REFERENCED;
 			list_add(&dentry->d_lru, &dentry_unused);
 			dentry_stat.nr_unused++;
 			spin_unlock(&dentry->d_lock);
			continue;
		}
		/*
		 * If the dentry is not DCACHED_REFERENCED, it is time
		 * to remove it from the dcache, provided the super block is
		 * NULL (which means we are trying to reclaim memory)
		 * or this dentry belongs to the same super block that
		 * we want to shrink.
		 */
		/*
		 * If this dentry is for "my" filesystem, then I can prune it
		 * without taking the s_umount lock (I already hold it).
		 */
		if (sb && dentry->d_sb == sb) {
			prune_one_dentry(dentry);
			continue;
		}
		/*
		 * ...otherwise we need to be sure this filesystem isn't being
		 * unmounted, otherwise we could race with
		 * generic_shutdown_super(), and end up holding a reference to
		 * an inode while the filesystem is unmounted.
		 * So we try to get s_umount, and make sure s_root isn't NULL.
		 * (Take a local copy of s_umount to avoid a use-after-free of
		 * `dentry').
		 */
		s_umount = &dentry->d_sb->s_umount;
		if (down_read_trylock(s_umount)) {
			if (dentry->d_sb->s_root != NULL) {
				prune_one_dentry(dentry);
				up_read(s_umount);
				continue;
			}
			up_read(s_umount);
		}
		spin_unlock(&dentry->d_lock);
		/*
		 * Insert dentry at the head of the list as inserting at the
		 * tail leads to a cycle.
		 */
 		list_add(&dentry->d_lru, &dentry_unused);
		dentry_stat.nr_unused++;
	}
	spin_unlock(&dcache_lock);
}

/*
 * Shrink the dcache for the specified super block.
 * This allows us to unmount a device without disturbing
 * the dcache for the other devices.
 *
 * This implementation makes just two traversals of the
 * unused list.  On the first pass we move the selected
 * dentries to the most recent end, and on the second
 * pass we free them.  The second pass must restart after
 * each dput(), but since the target dentries are all at
 * the end, it's really just a single traversal.
 */

/**
 * 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
 */

void shrink_dcache_sb(struct super_block * sb)
{
	struct list_head *tmp, *next;
	struct dentry *dentry;

	/*
	 * Pass one ... move the dentries for the specified
	 * superblock to the most recent end of the unused list.
	 */
	spin_lock(&dcache_lock);
	list_for_each_prev_safe(tmp, next, &dentry_unused) {
		dentry = list_entry(tmp, struct dentry, d_lru);
		if (dentry->d_sb != sb)
			continue;
		list_move_tail(tmp, &dentry_unused);
	}

	/*
	 * Pass two ... free the dentries for this superblock.
	 */
repeat:
	list_for_each_prev_safe(tmp, next, &dentry_unused) {
		dentry = list_entry(tmp, struct dentry, d_lru);
		if (dentry->d_sb != sb)
			continue;
		dentry_stat.nr_unused--;
		list_del_init(tmp);
		spin_lock(&dentry->d_lock);
		if (atomic_read(&dentry->d_count)) {
			spin_unlock(&dentry->d_lock);
			continue;
		}
		prune_one_dentry(dentry);
		cond_resched_lock(&dcache_lock);
		goto repeat;
	}
	spin_unlock(&dcache_lock);
}

/*
 * destroy a single subtree of dentries for unmount
 * - see the comments on shrink_dcache_for_umount() for a description of the
 *   locking
 */
static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
{
	struct dentry *parent;
	unsigned detached = 0;

	BUG_ON(!IS_ROOT(dentry));

	/* detach this root from the system */
	spin_lock(&dcache_lock);
	dentry_lru_remove(dentry);
	__d_drop(dentry);
	spin_unlock(&dcache_lock);

	for (;;) {
		/* descend to the first leaf in the current subtree */
		while (!list_empty(&dentry->d_subdirs)) {
			struct dentry *loop;

			/* this is a branch with children - detach all of them
			 * from the system in one go */
			spin_lock(&dcache_lock);
			list_for_each_entry(loop, &dentry->d_subdirs,
					    d_u.d_child) {
				dentry_lru_remove(loop);
				__d_drop(loop);
				cond_resched_lock(&dcache_lock);
			}
			spin_unlock(&dcache_lock);

			/* move to the first child */
			dentry = list_entry(dentry->d_subdirs.next,
					    struct dentry, d_u.d_child);
		}

		/* consume the dentries from this leaf up through its parents
		 * until we find one with children or run out altogether */
		do {
			struct inode *inode;

			if (atomic_read(&dentry->d_count) != 0) {
				printk(KERN_ERR
				       "BUG: Dentry %p{i=%lx,n=%s}"
				       " still in use (%d)"
				       " [unmount of %s %s]\n",
				       dentry,
				       dentry->d_inode ?
				       dentry->d_inode->i_ino : 0UL,
				       dentry->d_name.name,
				       atomic_read(&dentry->d_count),
				       dentry->d_sb->s_type->name,
				       dentry->d_sb->s_id);
				BUG();
			}

			parent = dentry->d_parent;
			if (parent == dentry)
				parent = NULL;
			else
				atomic_dec(&parent->d_count);

			list_del(&dentry->d_u.d_child);
			detached++;

			inode = dentry->d_inode;
			if (inode) {
				dentry->d_inode = NULL;
				list_del_init(&dentry->d_alias);
				if (dentry->d_op && dentry->d_op->d_iput)
					dentry->d_op->d_iput(dentry, inode);
				else
					iput(inode);
			}

			d_free(dentry);

			/* finished when we fall off the top of the tree,
			 * otherwise we ascend to the parent and move to the
			 * next sibling if there is one */
			if (!parent)
				goto out;

			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);
}

/*
 * destroy the dentries attached to a superblock on unmounting
 * - we don't need to use dentry->d_lock, and only need dcache_lock when
 *   removing the dentry from the system lists and hashes because:
 *   - the superblock is detached from all mountings and open files, so the
 *     dentry trees will not be rearranged by the VFS
 *   - s_umount is write-locked, so the memory pressure shrinker will ignore
 *     any dentries belonging to this superblock that it comes across
 *   - the filesystem itself is no longer permitted to rearrange the dentries
 *     in this superblock
 */
void shrink_dcache_for_umount(struct super_block *sb)
{
	struct dentry *dentry;

	if (down_read_trylock(&sb->s_umount))
		BUG();

	dentry = sb->s_root;
	sb->s_root = NULL;
	atomic_dec(&dentry->d_count);
	shrink_dcache_for_umount_subtree(dentry);

	while (!hlist_empty(&sb->s_anon)) {
		dentry = hlist_entry(sb->s_anon.first, struct dentry, d_hash);
		shrink_dcache_for_umount_subtree(dentry);
	}
}

/*
 * Search for at least 1 mount point in the dentry's subdirs.
 * We descend to the next level whenever the d_subdirs
 * list is non-empty and continue searching.
 */
 
/**
 * have_submounts - check for mounts over a dentry
 * @parent: dentry to check.
 *
 * Return true if the parent or its subdirectories contain
 * a mount point
 */
 
int have_submounts(struct dentry *parent)
{
	struct dentry *this_parent = parent;
	struct list_head *next;

	spin_lock(&dcache_lock);
	if (d_mountpoint(parent))
		goto positive;
repeat:
	next = this_parent->d_subdirs.next;
resume:
	while (next != &this_parent->d_subdirs) {
		struct list_head *tmp = next;
		struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child);
		next = tmp->next;
		/* Have we found a mount point ? */
		if (d_mountpoint(dentry))
			goto positive;
		if (!list_empty(&dentry->d_subdirs)) {
			this_parent = dentry;
			goto repeat;
		}
	}
	/*
	 * All done at this level ... ascend and resume the search.
	 */
	if (this_parent != parent) {
		next = this_parent->d_u.d_child.next;
		this_parent = this_parent->d_parent;
		goto resume;
	}
	spin_unlock(&dcache_lock);
	return 0; /* No mount points found in tree */
positive:
	spin_unlock(&dcache_lock);
	return 1;
}

/*
 * Search the dentry child list for the specified parent,
 * and move any unused dentries to the end of the unused
 * list for prune_dcache(). We descend to the next level
 * whenever the d_subdirs list is non-empty and continue
 * searching.
 *
 * It returns zero iff there are no unused children,
 * otherwise  it returns the number of children moved to
 * the end of the unused list. This may not be the total
 * number of unused children, because select_parent can
 * drop the lock and return early due to latency
 * constraints.
 */
static int select_parent(struct dentry * parent)
{
	struct dentry *this_parent = parent;
	struct list_head *next;
	int found = 0;

	spin_lock(&dcache_lock);
repeat:
	next = this_parent->d_subdirs.next;
resume:
	while (next != &this_parent->d_subdirs) {
		struct list_head *tmp = next;
		struct dentry *dentry = list_entry(tmp, struct dentry, d_u.d_child);
		next = tmp->next;

		dentry_lru_remove(dentry);
		/* 
		 * move only zero ref count dentries to the end 
		 * of the unused list for prune_dcache
		 */
		if (!atomic_read(&dentry->d_count)) {
			list_add_tail(&dentry->d_lru, &dentry_unused);
			dentry_stat.nr_unused++;
			found++;
		}

		/*
		 * We can return to the caller if we have found some (this
		 * ensures forward progress). We'll be coming back to find
		 * the rest.
		 */
		if (found && need_resched())
			goto out;

		/*
		 * Descend a level if the d_subdirs list is non-empty.
		 */
		if (!list_empty(&dentry->d_subdirs)) {
			this_parent = dentry;
			goto repeat;
		}
	}
	/*
	 * All done at this level ... ascend and resume the search.
	 */
	if (this_parent != parent) {
		next = this_parent->d_u.d_child.next;
		this_parent = this_parent->d_parent;
		goto resume;
	}
out:
	spin_unlock(&dcache_lock);
	return found;
}

/**
 * shrink_dcache_parent - prune dcache
 * @parent: parent of entries to prune
 *
 * Prune the dcache to remove unused children of the parent dentry.
 */
 
void shrink_dcache_parent(struct dentry * parent)
{
	int found;

	while ((found = select_parent(parent)) != 0)
		prune_dcache(found, parent->d_sb);
}

/*
 * Scan `nr' dentries and return the number which remain.
 *
 * We need to avoid reentering the filesystem if the caller is performing a
 * GFP_NOFS allocation attempt.  One example deadlock is:
 *
 * ext2_new_block->getblk->GFP->shrink_dcache_memory->prune_dcache->
 * prune_one_dentry->dput->dentry_iput->iput->inode->i_sb->s_op->put_inode->
 * ext2_discard_prealloc->ext2_free_blocks->lock_super->DEADLOCK.
 *
 * In this case we return -1 to tell the caller that we baled.
 */
static int shrink_dcache_memory(int nr, gfp_t gfp_mask)
{
	if (nr) {
		if (!(gfp_mask & __GFP_FS))
			return -1;
		prune_dcache(nr, NULL);
	}
	return (dentry_stat.nr_unused / 100) * sysctl_vfs_cache_pressure;
}

static struct shrinker dcache_shrinker = {
	.shrink = shrink_dcache_memory,
	.seeks = DEFAULT_SEEKS,
};

/**
 * d_alloc	-	allocate a dcache entry
 * @parent: parent of entry to allocate
 * @name: qstr of the name
 *
 * Allocates a dentry. It returns %NULL if there is insufficient memory
 * available. On a success the dentry is returned. The name passed in is
 * copied and the copy passed in may be reused after this call.
 */
 
struct dentry *d_alloc(struct dentry * parent, const struct qstr *name)
{
	struct dentry *dentry;
	char *dname;

	dentry = kmem_cache_alloc(dentry_cache, GFP_KERNEL);
	if (!dentry)
		return NULL;

	if (name->len > DNAME_INLINE_LEN-1) {
		dname = kmalloc(name->len + 1, GFP_KERNEL);
		if (!dname) {
			kmem_cache_free(dentry_cache, dentry); 
			return NULL;
		}
	} else  {
		dname = dentry->d_iname;
	}	
	dentry->d_name.name = dname;

	dentry->d_name.len = name->len;
	dentry->d_name.hash = name->hash;
	memcpy(dname, name->name, name->len);
	dname[name->len] = 0;

	atomic_set(&dentry->d_count, 1);
	dentry->d_flags = DCACHE_UNHASHED;
	spin_lock_init(&dentry->d_lock);
	dentry->d_inode = NULL;
	dentry->d_parent = NULL;
	dentry->d_sb = NULL;
	dentry->d_op = NULL;
	dentry->d_fsdata = NULL;
	dentry->d_mounted = 0;
#ifdef CONFIG_PROFILING
	dentry->d_cookie = NULL;
#endif
	INIT_HLIST_NODE(&dentry->d_hash);
	INIT_LIST_HEAD(&dentry->d_lru);
	INIT_LIST_HEAD(&dentry->d_subdirs);
	INIT_LIST_HEAD(&dentry->d_alias);

	if (parent) {
		dentry->d_parent = dget(parent);
		dentry->d_sb = parent->d_sb;
	} else {
		INIT_LIST_HEAD(&dentry->d_u.d_child);
	}

	spin_lock(&dcache_lock);
	if (parent)
		list_add(&dentry->d_u.d_child, &parent->d_subdirs);
	dentry_stat.nr_dentry++;
	spin_unlock(&dcache_lock);

	return dentry;
}

struct dentry *d_alloc_name(struct dentry *parent, const char *name)
{
	struct qstr q;

	q.name = name;
	q.len = strlen(name);
	q.hash = full_name_hash(q.name, q.len);
	return d_alloc(parent, &q);
}

/**
 * d_instantiate - fill in inode information for a dentry
 * @entry: dentry to complete
 * @inode: inode to attach to this dentry
 *
 * Fill in inode information in the entry.
 *
 * This turns negative dentries into productive full members
 * of society.
 *
 * NOTE! This assumes that the inode count has been incremented
 * (or otherwise set) by the caller to indicate that it is now
 * in use by the dcache.
 */
 
void d_instantiate(struct dentry *entry, struct inode * inode)
{
	BUG_ON(!list_empty(&entry->d_alias));
	spin_lock(&dcache_lock);
	if (inode)
		list_add(&entry->d_alias, &inode->i_dentry);
	entry->d_inode = inode;
	fsnotify_d_instantiate(entry, inode);
	spin_unlock(&dcache_lock);
	security_d_instantiate(entry, inode);
}

/**
 * d_instantiate_unique - instantiate a non-aliased dentry
 * @entry: dentry to instantiate
 * @inode: inode to attach to this dentry
 *
 * Fill in inode information in the entry. On success, it returns NULL.
 * If an unhashed alias of "entry" already exists, then we return the
 * aliased dentry instead and drop one reference to inode.
 *
 * Note that in order to avoid conflicts with rename() etc, the caller
 * had better be holding the parent directory semaphore.
 *
 * This also assumes that the inode count has been incremented
 * (or otherwise set) by the caller to indicate that it is now
 * in use by the dcache.
 */
static struct dentry *__d_instantiate_unique(struct dentry *entry,
					     struct inode *inode)
{
	struct dentry *alias;
	int len = entry->d_name.len;
	const char *name = entry->d_name.name;
	unsigned int hash = entry->d_name.hash;