1 files changed, 201 insertions, 331 deletions

diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index e0201837d244..590717861c7a 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -25,7 +25,6 @@
 #include "sysfs.h"
 
 DEFINE_MUTEX(sysfs_mutex);
-DEFINE_MUTEX(sysfs_rename_mutex);
 DEFINE_SPINLOCK(sysfs_assoc_lock);
 
 static DEFINE_SPINLOCK(sysfs_ino_lock);
@@ -85,46 +84,6 @@ static void sysfs_unlink_sibling(struct sysfs_dirent *sd)
 }
 
 /**
- *      sysfs_get_dentry - get dentry for the given sysfs_dirent
- *      @sd: sysfs_dirent of interest
- *
- *      Get dentry for @sd.  Dentry is looked up if currently not
- *      present.  This function descends from the root looking up
- *      dentry for each step.
- *
- *      LOCKING:
- *      mutex_lock(sysfs_rename_mutex)
- *
- *      RETURNS:
- *      Pointer to found dentry on success, ERR_PTR() value on error.
- */
-struct dentry *sysfs_get_dentry(struct sysfs_dirent *sd)
-{
-        struct dentry *dentry = dget(sysfs_sb->s_root);
-
-        while (dentry->d_fsdata != sd) {
-                struct sysfs_dirent *cur;
-                struct dentry *parent;
-
-                /* find the first ancestor which hasn't been looked up */
-                cur = sd;
-                while (cur->s_parent != dentry->d_fsdata)
-                        cur = cur->s_parent;
-
-                /* look it up */
-                parent = dentry;
-                mutex_lock(&parent->d_inode->i_mutex);
-                dentry = lookup_one_noperm(cur->s_name, parent);
-                mutex_unlock(&parent->d_inode->i_mutex);
-                dput(parent);
-
-                if (IS_ERR(dentry))
-                        break;
-        }
-        return dentry;
-}
-
-/**
  *      sysfs_get_active - get an active reference to sysfs_dirent
  *      @sd: sysfs_dirent to get an active reference to
  *
@@ -134,7 +93,7 @@ struct dentry *sysfs_get_dentry(struct sysfs_dirent *sd)
  *      RETURNS:
  *      Pointer to @sd on success, NULL on failure.
  */
-static struct sysfs_dirent *sysfs_get_active(struct sysfs_dirent *sd)
+struct sysfs_dirent *sysfs_get_active(struct sysfs_dirent *sd)
 {
         if (unlikely(!sd))
                 return NULL;
@@ -147,8 +106,10 @@ static struct sysfs_dirent *sysfs_get_active(struct sysfs_dirent *sd)
                         return NULL;
 
                 t = atomic_cmpxchg(&sd->s_active, v, v + 1);
-                if (likely(t == v))
+                if (likely(t == v)) {
+                        rwsem_acquire_read(&sd->dep_map, 0, 1, _RET_IP_);
                         return sd;
+                }
                 if (t < 0)
                         return NULL;
 
@@ -163,7 +124,7 @@ static struct sysfs_dirent *sysfs_get_active(struct sysfs_dirent *sd)
  *      Put an active reference to @sd.  This function is noop if @sd
  *      is NULL.
  */
-static void sysfs_put_active(struct sysfs_dirent *sd)
+void sysfs_put_active(struct sysfs_dirent *sd)
 {
         struct completion *cmpl;
         int v;
@@ -171,6 +132,7 @@ static void sysfs_put_active(struct sysfs_dirent *sd)
         if (unlikely(!sd))
                 return;
 
+        rwsem_release(&sd->dep_map, 1, _RET_IP_);
         v = atomic_dec_return(&sd->s_active);
         if (likely(v != SD_DEACTIVATED_BIAS))
                 return;
@@ -183,45 +145,6 @@ static void sysfs_put_active(struct sysfs_dirent *sd)
 }
 
 /**
- *      sysfs_get_active_two - get active references to sysfs_dirent and parent
- *      @sd: sysfs_dirent of interest
- *
- *      Get active reference to @sd and its parent.  Parent's active
- *      reference is grabbed first.  This function is noop if @sd is
- *      NULL.
- *
- *      RETURNS:
- *      Pointer to @sd on success, NULL on failure.
- */
-struct sysfs_dirent *sysfs_get_active_two(struct sysfs_dirent *sd)
-{
-        if (sd) {
-                if (sd->s_parent && unlikely(!sysfs_get_active(sd->s_parent)))
-                        return NULL;
-                if (unlikely(!sysfs_get_active(sd))) {
-                        sysfs_put_active(sd->s_parent);
-                        return NULL;
-                }
-        }
-        return sd;
-}
-
-/**
- *      sysfs_put_active_two - put active references to sysfs_dirent and parent
- *      @sd: sysfs_dirent of interest
- *
- *      Put active references to @sd and its parent.  This function is
- *      noop if @sd is NULL.
- */
-void sysfs_put_active_two(struct sysfs_dirent *sd)
-{
-        if (sd) {
-                sysfs_put_active(sd);
-                sysfs_put_active(sd->s_parent);
-        }
-}
-
-/**
  *      sysfs_deactivate - deactivate sysfs_dirent
  *      @sd: sysfs_dirent to deactivate
  *
@@ -233,17 +156,27 @@ static void sysfs_deactivate(struct sysfs_dirent *sd)
         int v;
 
         BUG_ON(sd->s_sibling || !(sd->s_flags & SYSFS_FLAG_REMOVED));
+
+        if (!(sysfs_type(sd) & SYSFS_ACTIVE_REF))
+                return;
+
         sd->s_sibling = (void *)&wait;
 
+        rwsem_acquire(&sd->dep_map, 0, 0, _RET_IP_);
         /* atomic_add_return() is a mb(), put_active() will always see
          * the updated sd->s_sibling.
          */
         v = atomic_add_return(SD_DEACTIVATED_BIAS, &sd->s_active);
 
-        if (v != SD_DEACTIVATED_BIAS)
+        if (v != SD_DEACTIVATED_BIAS) {
+                lock_contended(&sd->dep_map, _RET_IP_);
                 wait_for_completion(&wait);
+        }
 
         sd->s_sibling = NULL;
+
+        lock_acquired(&sd->dep_map, _RET_IP_);
+        rwsem_release(&sd->dep_map, 1, _RET_IP_);
 }
 
 static int sysfs_alloc_ino(ino_t *pino)
@@ -298,7 +231,61 @@ void release_sysfs_dirent(struct sysfs_dirent * sd)
                 goto repeat;
 }
 
-static void sysfs_d_iput(struct dentry * dentry, struct inode * inode)
+static int sysfs_dentry_delete(struct dentry *dentry)
+{
+        struct sysfs_dirent *sd = dentry->d_fsdata;
+        return !!(sd->s_flags & SYSFS_FLAG_REMOVED);
+}
+
+static int sysfs_dentry_revalidate(struct dentry *dentry, struct nameidata *nd)
+{
+        struct sysfs_dirent *sd = dentry->d_fsdata;
+        int is_dir;
+
+        mutex_lock(&sysfs_mutex);
+
+        /* The sysfs dirent has been deleted */
+        if (sd->s_flags & SYSFS_FLAG_REMOVED)
+                goto out_bad;
+
+        /* The sysfs dirent has been moved? */
+        if (dentry->d_parent->d_fsdata != sd->s_parent)
+                goto out_bad;
+
+        /* The sysfs dirent has been renamed */
+        if (strcmp(dentry->d_name.name, sd->s_name) != 0)
+                goto out_bad;
+
+        mutex_unlock(&sysfs_mutex);
+out_valid:
+        return 1;
+out_bad:
+        /* Remove the dentry from the dcache hashes.
+         * If this is a deleted dentry we use d_drop instead of d_delete
+         * so sysfs doesn't need to cope with negative dentries.
+         *
+         * If this is a dentry that has simply been renamed we
+         * use d_drop to remove it from the dcache lookup on its
+         * old parent.  If this dentry persists later when a lookup
+         * is performed at its new name the dentry will be readded
+         * to the dcache hashes.
+         */
+        is_dir = (sysfs_type(sd) == SYSFS_DIR);
+        mutex_unlock(&sysfs_mutex);
+        if (is_dir) {
+                /* If we have submounts we must allow the vfs caches
+                 * to lie about the state of the filesystem to prevent
+                 * leaks and other nasty things.
+                 */
+                if (have_submounts(dentry))
+                        goto out_valid;
+                shrink_dcache_parent(dentry);
+        }
+        d_drop(dentry);
+        return 0;
+}
+
+static void sysfs_dentry_iput(struct dentry *dentry, struct inode *inode)
 {
         struct sysfs_dirent * sd = dentry->d_fsdata;
 
@@ -307,7 +294,9 @@ static void sysfs_d_iput(struct dentry * dentry, struct inode * inode)
 }
 
 static const struct dentry_operations sysfs_dentry_ops = {
-        .d_iput         = sysfs_d_iput,
+        .d_revalidate   = sysfs_dentry_revalidate,
+        .d_delete       = sysfs_dentry_delete,
+        .d_iput         = sysfs_dentry_iput,
 };
 
 struct sysfs_dirent *sysfs_new_dirent(const char *name, umode_t mode, int type)
@@ -344,12 +333,6 @@ struct sysfs_dirent *sysfs_new_dirent(const char *name, umode_t mode, int type)
         return NULL;
 }
 
-static int sysfs_ilookup_test(struct inode *inode, void *arg)
-{
-        struct sysfs_dirent *sd = arg;
-        return inode->i_ino == sd->s_ino;
-}
-
 /**
  *      sysfs_addrm_start - prepare for sysfs_dirent add/remove
  *      @acxt: pointer to sysfs_addrm_cxt to be used
@@ -357,47 +340,20 @@ static int sysfs_ilookup_test(struct inode *inode, void *arg)
  *
  *      This function is called when the caller is about to add or
  *      remove sysfs_dirent under @parent_sd.  This function acquires
- *      sysfs_mutex, grabs inode for @parent_sd if available and lock
- *      i_mutex of it.  @acxt is used to keep and pass context to
+ *      sysfs_mutex.  @acxt is used to keep and pass context to
  *      other addrm functions.
  *
  *      LOCKING:
  *      Kernel thread context (may sleep).  sysfs_mutex is locked on
- *      return.  i_mutex of parent inode is locked on return if
- *      available.
+ *      return.
  */
 void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt,
                        struct sysfs_dirent *parent_sd)
 {
-        struct inode *inode;
-
         memset(acxt, 0, sizeof(*acxt));
         acxt->parent_sd = parent_sd;
 
-        /* Lookup parent inode.  inode initialization is protected by
-         * sysfs_mutex, so inode existence can be determined by
-         * looking up inode while holding sysfs_mutex.
-         */
         mutex_lock(&sysfs_mutex);
-
-        inode = ilookup5(sysfs_sb, parent_sd->s_ino, sysfs_ilookup_test,
-                         parent_sd);
-        if (inode) {
-                WARN_ON(inode->i_state & I_NEW);
-
-                /* parent inode available */
-                acxt->parent_inode = inode;
-
-                /* sysfs_mutex is below i_mutex in lock hierarchy.
-                 * First, trylock i_mutex.  If fails, unlock
-                 * sysfs_mutex and lock them in order.
-                 */
-                if (!mutex_trylock(&inode->i_mutex)) {
-                        mutex_unlock(&sysfs_mutex);
-                        mutex_lock(&inode->i_mutex);
-                        mutex_lock(&sysfs_mutex);
-                }
-        }
 }
 
 /**
@@ -422,18 +378,22 @@ void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt,
  */
 int __sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
 {
+        struct sysfs_inode_attrs *ps_iattr;
+
         if (sysfs_find_dirent(acxt->parent_sd, sd->s_name))
                 return -EEXIST;
 
         sd->s_parent = sysfs_get(acxt->parent_sd);
 
-        if (sysfs_type(sd) == SYSFS_DIR && acxt->parent_inode)
-                inc_nlink(acxt->parent_inode);
-
-        acxt->cnt++;
-
         sysfs_link_sibling(sd);
 
+        /* Update timestamps on the parent */
+        ps_iattr = acxt->parent_sd->s_iattr;
+        if (ps_iattr) {
+                struct iattr *ps_iattrs = &ps_iattr->ia_iattr;
+                ps_iattrs->ia_ctime = ps_iattrs->ia_mtime = CURRENT_TIME;
+        }
+
         return 0;
 }
 
@@ -512,70 +472,22 @@ int sysfs_add_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
  */
 void sysfs_remove_one(struct sysfs_addrm_cxt *acxt, struct sysfs_dirent *sd)
 {
+        struct sysfs_inode_attrs *ps_iattr;
+
         BUG_ON(sd->s_flags & SYSFS_FLAG_REMOVED);
 
         sysfs_unlink_sibling(sd);
 
+        /* Update timestamps on the parent */
+        ps_iattr = acxt->parent_sd->s_iattr;
+        if (ps_iattr) {
+                struct iattr *ps_iattrs = &ps_iattr->ia_iattr;
+                ps_iattrs->ia_ctime = ps_iattrs->ia_mtime = CURRENT_TIME;
+        }
+
         sd->s_flags |= SYSFS_FLAG_REMOVED;
         sd->s_sibling = acxt->removed;
         acxt->removed = sd;
-
-        if (sysfs_type(sd) == SYSFS_DIR && acxt->parent_inode)
-                drop_nlink(acxt->parent_inode);
-
-        acxt->cnt++;
-}
-
-/**
- *      sysfs_drop_dentry - drop dentry for the specified sysfs_dirent
- *      @sd: target sysfs_dirent
- *
- *      Drop dentry for @sd.  @sd must have been unlinked from its
- *      parent on entry to this function such that it can't be looked
- *      up anymore.
- */
-static void sysfs_drop_dentry(struct sysfs_dirent *sd)
-{
-        struct inode *inode;
-        struct dentry *dentry;
-
-        inode = ilookup(sysfs_sb, sd->s_ino);
-        if (!inode)
-                return;
-
-        /* Drop any existing dentries associated with sd.
-         *
-         * For the dentry to be properly freed we need to grab a
-         * reference to the dentry under the dcache lock,  unhash it,
-         * and then put it.  The playing with the dentry count allows
-         * dput to immediately free the dentry  if it is not in use.
-         */
-repeat:
-        spin_lock(&dcache_lock);
-        list_for_each_entry(dentry, &inode->i_dentry, d_alias) {
-                if (d_unhashed(dentry))
-                        continue;
-                dget_locked(dentry);
-                spin_lock(&dentry->d_lock);
-                __d_drop(dentry);
-                spin_unlock(&dentry->d_lock);
-                spin_unlock(&dcache_lock);
-                dput(dentry);
-                goto repeat;
-        }
-        spin_unlock(&dcache_lock);
-
-        /* adjust nlink and update timestamp */
-        mutex_lock(&inode->i_mutex);
-
-        inode->i_ctime = CURRENT_TIME;
-        drop_nlink(inode);
-        if (sysfs_type(sd) == SYSFS_DIR)
-                drop_nlink(inode);
-
-        mutex_unlock(&inode->i_mutex);
-
-        iput(inode);
 }
 
 /**
@@ -584,25 +496,15 @@ repeat:
  *
  *      Finish up sysfs_dirent add/remove.  Resources acquired by
  *      sysfs_addrm_start() are released and removed sysfs_dirents are
- *      cleaned up.  Timestamps on the parent inode are updated.
+ *      cleaned up.
  *
  *      LOCKING:
- *      All mutexes acquired by sysfs_addrm_start() are released.
+ *      sysfs_mutex is released.
  */
 void sysfs_addrm_finish(struct sysfs_addrm_cxt *acxt)
 {
         /* release resources acquired by sysfs_addrm_start() */
         mutex_unlock(&sysfs_mutex);
-        if (acxt->parent_inode) {
-                struct inode *inode = acxt->parent_inode;
-
-                /* if added/removed, update timestamps on the parent */
-                if (acxt->cnt)
-                        inode->i_ctime = inode->i_mtime = CURRENT_TIME;
-
-                mutex_unlock(&inode->i_mutex);
-                iput(inode);
-        }
 
         /* kill removed sysfs_dirents */
         while (acxt->removed) {
@@ -611,7 +513,6 @@ void sysfs_addrm_finish(struct sysfs_addrm_cxt *acxt)
                 acxt->removed = sd->s_sibling;
                 sd->s_sibling = NULL;
 
-                sysfs_drop_dentry(sd);
                 sysfs_deactivate(sd);
                 unmap_bin_file(sd);
                 sysfs_put(sd);
@@ -744,17 +645,22 @@ static struct dentry * sysfs_lookup(struct inode *dir, struct dentry *dentry,
         }
 
         /* attach dentry and inode */
-        inode = sysfs_get_inode(sd);
+        inode = sysfs_get_inode(dir->i_sb, sd);
         if (!inode) {
                 ret = ERR_PTR(-ENOMEM);
                 goto out_unlock;
         }
 
         /* instantiate and hash dentry */
-        dentry->d_op = &sysfs_dentry_ops;
-        dentry->d_fsdata = sysfs_get(sd);
-        d_instantiate(dentry, inode);
-        d_rehash(dentry);
+        ret = d_find_alias(inode);
+        if (!ret) {
+                dentry->d_op = &sysfs_dentry_ops;
+                dentry->d_fsdata = sysfs_get(sd);
+                d_add(dentry, inode);
+        } else {
+                d_move(ret, dentry);
+                iput(inode);
+        }
 
  out_unlock:
         mutex_unlock(&sysfs_mutex);
@@ -763,7 +669,9 @@ static struct dentry * sysfs_lookup(struct inode *dir, struct dentry *dentry,
 
 const struct inode_operations sysfs_dir_inode_operations = {
         .lookup         = sysfs_lookup,
+        .permission     = sysfs_permission,
         .setattr        = sysfs_setattr,
+        .getattr        = sysfs_getattr,
         .setxattr       = sysfs_setxattr,
 };
 
@@ -826,141 +734,65 @@ void sysfs_remove_dir(struct kobject * kobj)
         __sysfs_remove_dir(sd);
 }
 
-int sysfs_rename_dir(struct kobject * kobj, const char *new_name)
+int sysfs_rename(struct sysfs_dirent *sd,
+        struct sysfs_dirent *new_parent_sd, const char *new_name)
 {
-        struct sysfs_dirent *sd = kobj->sd;
-        struct dentry *parent = NULL;
-        struct dentry *old_dentry = NULL, *new_dentry = NULL;
         const char *dup_name = NULL;
         int error;
 
-        mutex_lock(&sysfs_rename_mutex);
+        mutex_lock(&sysfs_mutex);
 
         error = 0;
-        if (strcmp(sd->s_name, new_name) == 0)
+        if ((sd->s_parent == new_parent_sd) &&
+            (strcmp(sd->s_name, new_name) == 0))
                 goto out;       /* nothing to rename */
 
-        /* get the original dentry */
-        old_dentry = sysfs_get_dentry(sd);
-        if (IS_ERR(old_dentry)) {
-                error = PTR_ERR(old_dentry);
-                old_dentry = NULL;
-                goto out;
-        }
-
-        parent = old_dentry->d_parent;
-
-        /* lock parent and get dentry for new name */
-        mutex_lock(&parent->d_inode->i_mutex);
-        mutex_lock(&sysfs_mutex);
-
         error = -EEXIST;
-        if (sysfs_find_dirent(sd->s_parent, new_name))
-                goto out_unlock;
-
-        error = -ENOMEM;
-        new_dentry = d_alloc_name(parent, new_name);
-        if (!new_dentry)
-                goto out_unlock;
+        if (sysfs_find_dirent(new_parent_sd, new_name))
+                goto out;
 
         /* rename sysfs_dirent */
-        error = -ENOMEM;
-        new_name = dup_name = kstrdup(new_name, GFP_KERNEL);
-        if (!new_name)
-                goto out_unlock;
-
-        dup_name = sd->s_name;
-        sd->s_name = new_name;
+        if (strcmp(sd->s_name, new_name) != 0) {
+                error = -ENOMEM;
+                new_name = dup_name = kstrdup(new_name, GFP_KERNEL);
+                if (!new_name)
+                        goto out;
+
+                dup_name = sd->s_name;
+                sd->s_name = new_name;
+        }
 
-        /* rename */
-        d_add(new_dentry, NULL);
-        d_move(old_dentry, new_dentry);
+        /* Remove from old parent's list and insert into new parent's list. */
+        if (sd->s_parent != new_parent_sd) {
+                sysfs_unlink_sibling(sd);
+                sysfs_get(new_parent_sd);
+                sysfs_put(sd->s_parent);
+                sd->s_parent = new_parent_sd;
+                sysfs_link_sibling(sd);
+        }
 
         error = 0;
- out_unlock:
+ out:
         mutex_unlock(&sysfs_mutex);
-        mutex_unlock(&parent->d_inode->i_mutex);
         kfree(dup_name);
-        dput(old_dentry);
-        dput(new_dentry);
- out:
-        mutex_unlock(&sysfs_rename_mutex);
         return error;
 }
 
+int sysfs_rename_dir(struct kobject *kobj, const char *new_name)
+{
+        return sysfs_rename(kobj->sd, kobj->sd->s_parent, new_name);
+}
+
 int sysfs_move_dir(struct kobject *kobj, struct kobject *new_parent_kobj)
 {
         struct sysfs_dirent *sd = kobj->sd;
         struct sysfs_dirent *new_parent_sd;
-        struct dentry *old_parent, *new_parent = NULL;
-        struct dentry *old_dentry = NULL, *new_dentry = NULL;
-        int error;
 
-        mutex_lock(&sysfs_rename_mutex);
         BUG_ON(!sd->s_parent);
-        new_parent_sd = (new_parent_kobj && new_parent_kobj->sd) ?
+        new_parent_sd = new_parent_kobj && new_parent_kobj->sd ?
                 new_parent_kobj->sd : &sysfs_root;
 
-        error = 0;
-        if (sd->s_parent == new_parent_sd)
-                goto out;       /* nothing to move */
-
-        /* get dentries */
-        old_dentry = sysfs_get_dentry(sd);
-        if (IS_ERR(old_dentry)) {
-                error = PTR_ERR(old_dentry);
-                old_dentry = NULL;
-                goto out;
-        }
-        old_parent = old_dentry->d_parent;
-
-        new_parent = sysfs_get_dentry(new_parent_sd);
-        if (IS_ERR(new_parent)) {
-                error = PTR_ERR(new_parent);
-                new_parent = NULL;
-                goto out;
-        }
-
-again:
-        mutex_lock(&old_parent->d_inode->i_mutex);
-        if (!mutex_trylock(&new_parent->d_inode->i_mutex)) {
-                mutex_unlock(&old_parent->d_inode->i_mutex);
-                goto again;
-        }
-        mutex_lock(&sysfs_mutex);
-
-        error = -EEXIST;
-        if (sysfs_find_dirent(new_parent_sd, sd->s_name))
-                goto out_unlock;
-
-        error = -ENOMEM;
-        new_dentry = d_alloc_name(new_parent, sd->s_name);
-        if (!new_dentry)
-                goto out_unlock;
-
-        error = 0;
-        d_add(new_dentry, NULL);
-        d_move(old_dentry, new_dentry);
-
-        /* Remove from old parent's list and insert into new parent's list. */
-        sysfs_unlink_sibling(sd);
-        sysfs_get(new_parent_sd);
-        drop_nlink(old_parent->d_inode);
-        sysfs_put(sd->s_parent);
-        sd->s_parent = new_parent_sd;
-        inc_nlink(new_parent->d_inode);
-        sysfs_link_sibling(sd);
-
- out_unlock:
-        mutex_unlock(&sysfs_mutex);
-        mutex_unlock(&new_parent->d_inode->i_mutex);
-        mutex_unlock(&old_parent->d_inode->i_mutex);
- out:
-        dput(new_parent);
-        dput(old_dentry);
-        dput(new_dentry);
-        mutex_unlock(&sysfs_rename_mutex);
-        return error;
+        return sysfs_rename(sd, new_parent_sd, sd->s_name);
 }
 
 /* Relationship between s_mode and the DT_xxx types */
@@ -969,11 +801,46 @@ static inline unsigned char dt_type(struct sysfs_dirent *sd)
         return (sd->s_mode >> 12) & 15;
 }
 
+static int sysfs_dir_release(struct inode *inode, struct file *filp)
+{
+        sysfs_put(filp->private_data);
+        return 0;
+}
+
+static struct sysfs_dirent *sysfs_dir_pos(struct sysfs_dirent *parent_sd,
+        ino_t ino, struct sysfs_dirent *pos)
+{
+        if (pos) {
+                int valid = !(pos->s_flags & SYSFS_FLAG_REMOVED) &&
+                        pos->s_parent == parent_sd &&
+                        ino == pos->s_ino;
+                sysfs_put(pos);
+                if (valid)
+                        return pos;
+        }
+        pos = NULL;
+        if ((ino > 1) && (ino < INT_MAX)) {
+                pos = parent_sd->s_dir.children;
+                while (pos && (ino > pos->s_ino))
+                        pos = pos->s_sibling;
+        }
+        return pos;
+}
+
+static struct sysfs_dirent *sysfs_dir_next_pos(struct sysfs_dirent *parent_sd,
+        ino_t ino, struct sysfs_dirent *pos)
+{
+        pos = sysfs_dir_pos(parent_sd, ino, pos);
+        if (pos)
+                pos = pos->s_sibling;
+        return pos;
+}
+
 static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
 {
         struct dentry *dentry = filp->f_path.dentry;
         struct sysfs_dirent * parent_sd = dentry->d_fsdata;
-        struct sysfs_dirent *pos;
+        struct sysfs_dirent *pos = filp->private_data;
         ino_t ino;
 
         if (filp->f_pos == 0) {
@@ -989,29 +856,31 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
                 if (filldir(dirent, "..", 2, filp->f_pos, ino, DT_DIR) == 0)
                         filp->f_pos++;
         }
-        if ((filp->f_pos > 1) && (filp->f_pos < INT_MAX)) {
-                mutex_lock(&sysfs_mutex);
-
-                /* Skip the dentries we have already reported */
-                pos = parent_sd->s_dir.children;
-                while (pos && (filp->f_pos > pos->s_ino))
-                        pos = pos->s_sibling;
-
-                for ( ; pos; pos = pos->s_sibling) {
-                        const char * name;
-                        int len;
-
-                        name = pos->s_name;
-                        len = strlen(name);
-                        filp->f_pos = ino = pos->s_ino;
+        mutex_lock(&sysfs_mutex);
+        for (pos = sysfs_dir_pos(parent_sd, filp->f_pos, pos);
+             pos;
+             pos = sysfs_dir_next_pos(parent_sd, filp->f_pos, pos)) {
+                const char * name;
+                unsigned int type;
+                int len, ret;
+
+                name = pos->s_name;
+                len = strlen(name);
+                ino = pos->s_ino;
+                type = dt_type(pos);
+                filp->f_pos = ino;
+                filp->private_data = sysfs_get(pos);
 
-                        if (filldir(dirent, name, len, filp->f_pos, ino,
-                                         dt_type(pos)) < 0)
-                                break;
-                }
-                if (!pos)
-                        filp->f_pos = INT_MAX;
                 mutex_unlock(&sysfs_mutex);
+                ret = filldir(dirent, name, len, filp->f_pos, ino, type);
+                mutex_lock(&sysfs_mutex);
+                if (ret < 0)
+                        break;
+        }
+        mutex_unlock(&sysfs_mutex);
+        if ((filp->f_pos > 1) && !pos) { /* EOF */
+                filp->f_pos = INT_MAX;
+                filp->private_data = NULL;
         }
         return 0;
 }
@@ -1020,5 +889,6 @@ static int sysfs_readdir(struct file * filp, void * dirent, filldir_t filldir)
 const struct file_operations sysfs_dir_operations = {
         .read           = generic_read_dir,
         .readdir        = sysfs_readdir,
+        .release        = sysfs_dir_release,
         .llseek         = generic_file_llseek,
 };