1 files changed, 128 insertions, 50 deletions

diff --git a/fs/dcache.c b/fs/dcache.c
index 2bac4ba1d1d3..d68631f18df1 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -43,7 +43,7 @@ static __cacheline_aligned_in_smp DEFINE_SEQLOCK(rename_lock);
 
 EXPORT_SYMBOL(dcache_lock);
 
-static kmem_cache_t *dentry_cache __read_mostly;
+static struct kmem_cache *dentry_cache __read_mostly;
 
 #define DNAME_INLINE_LEN (sizeof(struct dentry)-offsetof(struct dentry,d_iname))
 
@@ -68,15 +68,19 @@ struct dentry_stat_t dentry_stat = {
         .age_limit = 45,
 };
 
-static void d_callback(struct rcu_head *head)
+static void __d_free(struct dentry *dentry)
 {
-        struct dentry * dentry = container_of(head, struct dentry, d_u.d_rcu);
-
         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.
@@ -85,7 +89,11 @@ static void d_free(struct dentry *dentry)
 {
         if (dentry->d_op && dentry->d_op->d_release)
                 dentry->d_op->d_release(dentry);
-        call_rcu(&dentry->d_u.d_rcu, d_callback);
+        /* if dentry was never inserted into hash, immediate free is OK */
+        if (dentry->d_hash.pprev == NULL)
+                __d_free(dentry);
+        else
+                call_rcu(&dentry->d_u.d_rcu, d_callback);
 }
 
 /*
@@ -478,11 +486,12 @@ static void prune_dcache(int count, struct super_block *sb)
                         up_read(s_umount);
                 }
                 spin_unlock(&dentry->d_lock);
-                /* Cannot remove the first dentry, and it isn't appropriate
-                 * to move it to the head of the list, so give up, and try
-                 * later
+                /*
+                 * Insert dentry at the head of the list as inserting at the
+                 * tail leads to a cycle.
                  */
-                break;
+                list_add(&dentry->d_lru, &dentry_unused);
+                dentry_stat.nr_unused++;
         }
         spin_unlock(&dcache_lock);
 }
@@ -556,6 +565,7 @@ repeat:
 static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
 {
         struct dentry *parent;
+        unsigned detached = 0;
 
         BUG_ON(!IS_ROOT(dentry));
 
@@ -620,7 +630,7 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
                                 atomic_dec(&parent->d_count);
 
                         list_del(&dentry->d_u.d_child);
-                        dentry_stat.nr_dentry--;        /* For d_free, below */
+                        detached++;
 
                         inode = dentry->d_inode;
                         if (inode) {
@@ -638,7 +648,7 @@ 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)
-                                return;
+                                goto out;
 
                         dentry = parent;
 
@@ -647,6 +657,11 @@ static void shrink_dcache_for_umount_subtree(struct dentry *dentry)
                 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);
 }
 
 /*
@@ -1469,23 +1484,21 @@ static void switch_names(struct dentry *dentry, struct dentry *target)
  * deleted it.
  */
  
-/**
- * d_move - move a dentry
+/*
+ * d_move_locked - move a dentry
  * @dentry: entry to move
  * @target: new dentry
  *
  * Update the dcache to reflect the move of a file name. Negative
  * dcache entries should not be moved in this way.
  */
-
-void d_move(struct dentry * dentry, struct dentry * target)
+static void d_move_locked(struct dentry * dentry, struct dentry * target)
 {
         struct hlist_head *list;
 
         if (!dentry->d_inode)
                 printk(KERN_WARNING "VFS: moving negative dcache entry\n");
 
-        spin_lock(&dcache_lock);
         write_seqlock(&rename_lock);
         /*
          * XXXX: do we really need to take target->d_lock?
@@ -1536,7 +1549,81 @@ already_unhashed:
         fsnotify_d_move(dentry);
         spin_unlock(&dentry->d_lock);
         write_sequnlock(&rename_lock);
+}
+
+/**
+ * d_move - move a dentry
+ * @dentry: entry to move
+ * @target: new dentry
+ *
+ * Update the dcache to reflect the move of a file name. Negative
+ * dcache entries should not be moved in this way.
+ */
+
+void d_move(struct dentry * dentry, struct dentry * target)
+{
+        spin_lock(&dcache_lock);
+        d_move_locked(dentry, target);
+        spin_unlock(&dcache_lock);
+}
+
+/*
+ * Helper that returns 1 if p1 is a parent of p2, else 0
+ */
+static int d_isparent(struct dentry *p1, struct dentry *p2)
+{
+        struct dentry *p;
+
+        for (p = p2; p->d_parent != p; p = p->d_parent) {
+                if (p->d_parent == p1)
+                        return 1;
+        }
+        return 0;
+}
+
+/*
+ * This helper attempts to cope with remotely renamed directories
+ *
+ * It assumes that the caller is already holding
+ * dentry->d_parent->d_inode->i_mutex and the dcache_lock
+ *
+ * Note: If ever the locking in lock_rename() changes, then please
+ * remember to update this too...
+ *
+ * On return, dcache_lock will have been unlocked.
+ */
+static struct dentry *__d_unalias(struct dentry *dentry, struct dentry *alias)
+{
+        struct mutex *m1 = NULL, *m2 = NULL;
+        struct dentry *ret;
+
+        /* If alias and dentry share a parent, then no extra locks required */
+        if (alias->d_parent == dentry->d_parent)
+                goto out_unalias;
+
+        /* Check for loops */
+        ret = ERR_PTR(-ELOOP);
+        if (d_isparent(alias, dentry))
+                goto out_err;
+
+        /* See lock_rename() */
+        ret = ERR_PTR(-EBUSY);
+        if (!mutex_trylock(&dentry->d_sb->s_vfs_rename_mutex))
+                goto out_err;
+        m1 = &dentry->d_sb->s_vfs_rename_mutex;
+        if (!mutex_trylock(&alias->d_parent->d_inode->i_mutex))
+                goto out_err;
+        m2 = &alias->d_parent->d_inode->i_mutex;
+out_unalias:
+        d_move_locked(alias, dentry);
+        ret = alias;
+out_err:
         spin_unlock(&dcache_lock);
+        if (m2)
+                mutex_unlock(m2);
+        if (m1)
+                mutex_unlock(m1);
+        return ret;
 }
 
 /*
@@ -1581,7 +1668,7 @@ static void __d_materialise_dentry(struct dentry *dentry, struct dentry *anon)
  */
 struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode)
 {
-        struct dentry *alias, *actual;
+        struct dentry *actual;
 
         BUG_ON(!d_unhashed(dentry));
 
@@ -1593,26 +1680,27 @@ struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode)
                 goto found_lock;
         }
 
-        /* See if a disconnected directory already exists as an anonymous root
-         * that we should splice into the tree instead */
-        if (S_ISDIR(inode->i_mode) && (alias = __d_find_alias(inode, 1))) {
-                spin_lock(&alias->d_lock);
-
-                /* Is this a mountpoint that we could splice into our tree? */
-                if (IS_ROOT(alias))
-                        goto connect_mountpoint;
-
-                if (alias->d_name.len == dentry->d_name.len &&
-                    alias->d_parent == dentry->d_parent &&
-                    memcmp(alias->d_name.name,
-                           dentry->d_name.name,
-                           dentry->d_name.len) == 0)
-                        goto replace_with_alias;
-
-                spin_unlock(&alias->d_lock);
-
-                /* Doh! Seem to be aliasing directories for some reason... */
-                dput(alias);
+        if (S_ISDIR(inode->i_mode)) {
+                struct dentry *alias;
+
+                /* Does an aliased dentry already exist? */
+                alias = __d_find_alias(inode, 0);
+                if (alias) {
+                        actual = alias;
+                        /* Is this an anonymous mountpoint that we could splice
+                         * into our tree? */
+                        if (IS_ROOT(alias)) {
+                                spin_lock(&alias->d_lock);
+                                __d_materialise_dentry(dentry, alias);
+                                __d_drop(alias);
+                                goto found;
+                        }
+                        /* Nope, but we must(!) avoid directory aliasing */
+                        actual = __d_unalias(dentry, alias);
+                        if (IS_ERR(actual))
+                                dput(alias);
+                        goto out_nolock;
+                }
         }
 
         /* Add a unique reference */
@@ -1628,7 +1716,7 @@ found:
         _d_rehash(actual);
         spin_unlock(&actual->d_lock);
         spin_unlock(&dcache_lock);
-
+out_nolock:
         if (actual == dentry) {
                 security_d_instantiate(dentry, inode);
                 return NULL;
@@ -1637,16 +1725,6 @@ found:
         iput(inode);
         return actual;
 
-        /* Convert the anonymous/root alias into an ordinary dentry */
-connect_mountpoint:
-        __d_materialise_dentry(dentry, alias);
-
-        /* Replace the candidate dentry with the alias in the tree */
-replace_with_alias:
-        __d_drop(alias);
-        actual = alias;
-        goto found;
-
 shouldnt_be_hashed:
         spin_unlock(&dcache_lock);
         BUG();
@@ -2002,10 +2080,10 @@ static void __init dcache_init(unsigned long mempages)
 }
 
 /* SLAB cache for __getname() consumers */
-kmem_cache_t *names_cachep __read_mostly;
+struct kmem_cache *names_cachep __read_mostly;
 
 /* SLAB cache for file structures */
-kmem_cache_t *filp_cachep __read_mostly;
+struct kmem_cache *filp_cachep __read_mostly;
 
 EXPORT_SYMBOL(d_genocide);