1 files changed, 183 insertions, 94 deletions

diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 8e0a1378a4b1..3990f3e270cb 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -17,16 +17,23 @@
 
 #include "kernfs-internal.h"
 
-DECLARE_RWSEM(kernfs_rwsem);
 static DEFINE_SPINLOCK(kernfs_rename_lock);	/* kn->parent and ->name */
-static char kernfs_pr_cont_buf[PATH_MAX];	/* protected by rename_lock */
+/*
+ * Don't use rename_lock to piggy back on pr_cont_buf. We don't want to
+ * call pr_cont() while holding rename_lock. Because sometimes pr_cont()
+ * will perform wakeups when releasing console_sem. Holding rename_lock
+ * will introduce deadlock if the scheduler reads the kernfs_name in the
+ * wakeup path.
+ */
+static DEFINE_SPINLOCK(kernfs_pr_cont_lock);
+static char kernfs_pr_cont_buf[PATH_MAX];	/* protected by pr_cont_lock */
 static DEFINE_SPINLOCK(kernfs_idr_lock);	/* root->ino_idr */
 
 #define rb_to_kn(X) rb_entry((X), struct kernfs_node, rb)
 
 static bool kernfs_active(struct kernfs_node *kn)
 {
-	lockdep_assert_held(&kernfs_rwsem);
+	lockdep_assert_held(&kernfs_root(kn)->kernfs_rwsem);
 	return atomic_read(&kn->active) >= 0;
 }
 
@@ -230,12 +237,12 @@ void pr_cont_kernfs_name(struct kernfs_node *kn)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&kernfs_rename_lock, flags);
+	spin_lock_irqsave(&kernfs_pr_cont_lock, flags);
 
-	kernfs_name_locked(kn, kernfs_pr_cont_buf, sizeof(kernfs_pr_cont_buf));
+	kernfs_name(kn, kernfs_pr_cont_buf, sizeof(kernfs_pr_cont_buf));
 	pr_cont("%s", kernfs_pr_cont_buf);
 
-	spin_unlock_irqrestore(&kernfs_rename_lock, flags);
+	spin_unlock_irqrestore(&kernfs_pr_cont_lock, flags);
 }
 
 /**
@@ -249,10 +256,10 @@ void pr_cont_kernfs_path(struct kernfs_node *kn)
 	unsigned long flags;
 	int sz;
 
-	spin_lock_irqsave(&kernfs_rename_lock, flags);
+	spin_lock_irqsave(&kernfs_pr_cont_lock, flags);
 
-	sz = kernfs_path_from_node_locked(kn, NULL, kernfs_pr_cont_buf,
-					  sizeof(kernfs_pr_cont_buf));
+	sz = kernfs_path_from_node(kn, NULL, kernfs_pr_cont_buf,
+				   sizeof(kernfs_pr_cont_buf));
 	if (sz < 0) {
 		pr_cont("(error)");
 		goto out;
@@ -266,7 +273,7 @@ void pr_cont_kernfs_path(struct kernfs_node *kn)
 	pr_cont("%s", kernfs_pr_cont_buf);
 
 out:
-	spin_unlock_irqrestore(&kernfs_rename_lock, flags);
+	spin_unlock_irqrestore(&kernfs_pr_cont_lock, flags);
 }
 
 /**
@@ -457,14 +464,25 @@ void kernfs_put_active(struct kernfs_node *kn)
  * return after draining is complete.
  */
 static void kernfs_drain(struct kernfs_node *kn)
-	__releases(&kernfs_rwsem) __acquires(&kernfs_rwsem)
+	__releases(&kernfs_root(kn)->kernfs_rwsem)
+	__acquires(&kernfs_root(kn)->kernfs_rwsem)
 {
 	struct kernfs_root *root = kernfs_root(kn);
 
-	lockdep_assert_held_write(&kernfs_rwsem);
+	lockdep_assert_held_write(&root->kernfs_rwsem);
 	WARN_ON_ONCE(kernfs_active(kn));
 
-	up_write(&kernfs_rwsem);
+	/*
+	 * Skip draining if already fully drained. This avoids draining and its
+	 * lockdep annotations for nodes which have never been activated
+	 * allowing embedding kernfs_remove() in create error paths without
+	 * worrying about draining.
+	 */
+	if (atomic_read(&kn->active) == KN_DEACTIVATED_BIAS &&
+	    !kernfs_should_drain_open_files(kn))
+		return;
+
+	up_write(&root->kernfs_rwsem);
 
 	if (kernfs_lockdep(kn)) {
 		rwsem_acquire(&kn->dep_map, 0, 0, _RET_IP_);
@@ -472,7 +490,6 @@ static void kernfs_drain(struct kernfs_node *kn)
 			lock_contended(&kn->dep_map, _RET_IP_);
 	}
 
-	/* but everyone should wait for draining */
 	wait_event(root->deactivate_waitq,
 		   atomic_read(&kn->active) == KN_DEACTIVATED_BIAS);
 
@@ -481,9 +498,10 @@ static void kernfs_drain(struct kernfs_node *kn)
 		rwsem_release(&kn->dep_map, _RET_IP_);
 	}
 
-	kernfs_drain_open_files(kn);
+	if (kernfs_should_drain_open_files(kn))
+		kernfs_drain_open_files(kn);
 
-	down_write(&kernfs_rwsem);
+	down_write(&root->kernfs_rwsem);
 }
 
 /**
@@ -687,13 +705,7 @@ struct kernfs_node *kernfs_find_and_get_node_by_id(struct kernfs_root *root,
 			goto err_unlock;
 	}
 
-	/*
-	 * ACTIVATED is protected with kernfs_mutex but it was clear when
-	 * @kn was added to idr and we just wanna see it set.  No need to
-	 * grab kernfs_mutex.
-	 */
-	if (unlikely(!(kn->flags & KERNFS_ACTIVATED) ||
-		     !atomic_inc_not_zero(&kn->count)))
+	if (unlikely(!kernfs_active(kn) || !atomic_inc_not_zero(&kn->count)))
 		goto err_unlock;
 
 	spin_unlock(&kernfs_idr_lock);
@@ -718,11 +730,12 @@ err_unlock:
 int kernfs_add_one(struct kernfs_node *kn)
 {
 	struct kernfs_node *parent = kn->parent;
+	struct kernfs_root *root = kernfs_root(parent);
 	struct kernfs_iattrs *ps_iattr;
 	bool has_ns;
 	int ret;
 
-	down_write(&kernfs_rwsem);
+	down_write(&root->kernfs_rwsem);
 
 	ret = -EINVAL;
 	has_ns = kernfs_ns_enabled(parent);
@@ -734,10 +747,7 @@ int kernfs_add_one(struct kernfs_node *kn)
 		goto out_unlock;
 
 	ret = -ENOENT;
-	if (parent->flags & KERNFS_EMPTY_DIR)
-		goto out_unlock;
-
-	if ((parent->flags & KERNFS_ACTIVATED) && !kernfs_active(parent))
+	if (parent->flags & (KERNFS_REMOVING | KERNFS_EMPTY_DIR))
 		goto out_unlock;
 
 	kn->hash = kernfs_name_hash(kn->name, kn->ns);
@@ -753,7 +763,7 @@ int kernfs_add_one(struct kernfs_node *kn)
 		ps_iattr->ia_mtime = ps_iattr->ia_ctime;
 	}
 
-	up_write(&kernfs_rwsem);
+	up_write(&root->kernfs_rwsem);
 
 	/*
 	 * Activate the new node unless CREATE_DEACTIVATED is requested.
@@ -767,7 +777,7 @@ int kernfs_add_one(struct kernfs_node *kn)
 	return 0;
 
 out_unlock:
-	up_write(&kernfs_rwsem);
+	up_write(&root->kernfs_rwsem);
 	return ret;
 }
 
@@ -788,7 +798,7 @@ static struct kernfs_node *kernfs_find_ns(struct kernfs_node *parent,
 	bool has_ns = kernfs_ns_enabled(parent);
 	unsigned int hash;
 
-	lockdep_assert_held(&kernfs_rwsem);
+	lockdep_assert_held(&kernfs_root(parent)->kernfs_rwsem);
 
 	if (has_ns != (bool)ns) {
 		WARN(1, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n",
@@ -820,15 +830,14 @@ static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent,
 	size_t len;
 	char *p, *name;
 
-	lockdep_assert_held_read(&kernfs_rwsem);
+	lockdep_assert_held_read(&kernfs_root(parent)->kernfs_rwsem);
 
-	/* grab kernfs_rename_lock to piggy back on kernfs_pr_cont_buf */
-	spin_lock_irq(&kernfs_rename_lock);
+	spin_lock_irq(&kernfs_pr_cont_lock);
 
 	len = strlcpy(kernfs_pr_cont_buf, path, sizeof(kernfs_pr_cont_buf));
 
 	if (len >= sizeof(kernfs_pr_cont_buf)) {
-		spin_unlock_irq(&kernfs_rename_lock);
+		spin_unlock_irq(&kernfs_pr_cont_lock);
 		return NULL;
 	}
 
@@ -840,7 +849,7 @@ static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent,
 		parent = kernfs_find_ns(parent, name, ns);
 	}
 
-	spin_unlock_irq(&kernfs_rename_lock);
+	spin_unlock_irq(&kernfs_pr_cont_lock);
 
 	return parent;
 }
@@ -859,11 +868,12 @@ struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent,
 					   const char *name, const void *ns)
 {
 	struct kernfs_node *kn;
+	struct kernfs_root *root = kernfs_root(parent);
 
-	down_read(&kernfs_rwsem);
+	down_read(&root->kernfs_rwsem);
 	kn = kernfs_find_ns(parent, name, ns);
 	kernfs_get(kn);
-	up_read(&kernfs_rwsem);
+	up_read(&root->kernfs_rwsem);
 
 	return kn;
 }
@@ -883,11 +893,12 @@ struct kernfs_node *kernfs_walk_and_get_ns(struct kernfs_node *parent,
 					   const char *path, const void *ns)
 {
 	struct kernfs_node *kn;
+	struct kernfs_root *root = kernfs_root(parent);
 
-	down_read(&kernfs_rwsem);
+	down_read(&root->kernfs_rwsem);
 	kn = kernfs_walk_ns(parent, path, ns);
 	kernfs_get(kn);
-	up_read(&kernfs_rwsem);
+	up_read(&root->kernfs_rwsem);
 
 	return kn;
 }
@@ -912,6 +923,7 @@ struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops,
 		return ERR_PTR(-ENOMEM);
 
 	idr_init(&root->ino_idr);
+	init_rwsem(&root->kernfs_rwsem);
 	INIT_LIST_HEAD(&root->supers);
 
 	/*
@@ -957,7 +969,22 @@ struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops,
  */
 void kernfs_destroy_root(struct kernfs_root *root)
 {
-	kernfs_remove(root->kn);	/* will also free @root */
+	/*
+	 *  kernfs_remove holds kernfs_rwsem from the root so the root
+	 *  shouldn't be freed during the operation.
+	 */
+	kernfs_get(root->kn);
+	kernfs_remove(root->kn);
+	kernfs_put(root->kn); /* will also free @root */
+}
+
+/**
+ * kernfs_root_to_node - return the kernfs_node associated with a kernfs_root
+ * @root: root to use to lookup
+ */
+struct kernfs_node *kernfs_root_to_node(struct kernfs_root *root)
+{
+	return root->kn;
 }
 
 /**
@@ -1035,6 +1062,7 @@ struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent,
 static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	struct kernfs_node *kn;
+	struct kernfs_root *root;
 
 	if (flags & LOOKUP_RCU)
 		return -ECHILD;
@@ -1046,18 +1074,19 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags)
 		/* If the kernfs parent node has changed discard and
 		 * proceed to ->lookup.
 		 */
-		down_read(&kernfs_rwsem);
 		spin_lock(&dentry->d_lock);
 		parent = kernfs_dentry_node(dentry->d_parent);
 		if (parent) {
+			spin_unlock(&dentry->d_lock);
+			root = kernfs_root(parent);
+			down_read(&root->kernfs_rwsem);
 			if (kernfs_dir_changed(parent, dentry)) {
-				spin_unlock(&dentry->d_lock);
-				up_read(&kernfs_rwsem);
+				up_read(&root->kernfs_rwsem);
 				return 0;
 			}
-		}
-		spin_unlock(&dentry->d_lock);
-		up_read(&kernfs_rwsem);
+			up_read(&root->kernfs_rwsem);
+		} else
+			spin_unlock(&dentry->d_lock);
 
 		/* The kernfs parent node hasn't changed, leave the
 		 * dentry negative and return success.
@@ -1066,7 +1095,8 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags)
 	}
 
 	kn = kernfs_dentry_node(dentry);
-	down_read(&kernfs_rwsem);
+	root = kernfs_root(kn);
+	down_read(&root->kernfs_rwsem);
 
 	/* The kernfs node has been deactivated */
 	if (!kernfs_active(kn))
@@ -1085,10 +1115,10 @@ static int kernfs_dop_revalidate(struct dentry *dentry, unsigned int flags)
 	    kernfs_info(dentry->d_sb)->ns != kn->ns)
 		goto out_bad;
 
-	up_read(&kernfs_rwsem);
+	up_read(&root->kernfs_rwsem);
 	return 1;
 out_bad:
-	up_read(&kernfs_rwsem);
+	up_read(&root->kernfs_rwsem);
 	return 0;
 }
 
@@ -1102,10 +1132,12 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir,
 {
 	struct kernfs_node *parent = dir->i_private;
 	struct kernfs_node *kn;
+	struct kernfs_root *root;
 	struct inode *inode = NULL;
 	const void *ns = NULL;
 
-	down_read(&kernfs_rwsem);
+	root = kernfs_root(parent);
+	down_read(&root->kernfs_rwsem);
 	if (kernfs_ns_enabled(parent))
 		ns = kernfs_info(dir->i_sb)->ns;
 
@@ -1116,7 +1148,7 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir,
 		 * create a negative.
 		 */
 		if (!kernfs_active(kn)) {
-			up_read(&kernfs_rwsem);
+			up_read(&root->kernfs_rwsem);
 			return NULL;
 		}
 		inode = kernfs_get_inode(dir->i_sb, kn);
@@ -1131,7 +1163,7 @@ static struct dentry *kernfs_iop_lookup(struct inode *dir,
 	 */
 	if (!IS_ERR(inode))
 		kernfs_set_rev(parent, dentry);
-	up_read(&kernfs_rwsem);
+	up_read(&root->kernfs_rwsem);
 
 	/* instantiate and hash (possibly negative) dentry */
 	return d_splice_alias(inode, dentry);
@@ -1254,7 +1286,7 @@ static struct kernfs_node *kernfs_next_descendant_post(struct kernfs_node *pos,
 {
 	struct rb_node *rbn;
 
-	lockdep_assert_held_write(&kernfs_rwsem);
+	lockdep_assert_held_write(&kernfs_root(root)->kernfs_rwsem);
 
 	/* if first iteration, visit leftmost descendant which may be root */
 	if (!pos)
@@ -1273,6 +1305,21 @@ static struct kernfs_node *kernfs_next_descendant_post(struct kernfs_node *pos,
 	return pos->parent;
 }
 
+static void kernfs_activate_one(struct kernfs_node *kn)
+{
+	lockdep_assert_held_write(&kernfs_root(kn)->kernfs_rwsem);
+
+	kn->flags |= KERNFS_ACTIVATED;
+
+	if (kernfs_active(kn) || (kn->flags & (KERNFS_HIDDEN | KERNFS_REMOVING)))
+		return;
+
+	WARN_ON_ONCE(kn->parent && RB_EMPTY_NODE(&kn->rb));
+	WARN_ON_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS);
+
+	atomic_sub(KN_DEACTIVATED_BIAS, &kn->active);
+}
+
 /**
  * kernfs_activate - activate a node which started deactivated
  * @kn: kernfs_node whose subtree is to be activated
@@ -1289,68 +1336,92 @@ static struct kernfs_node *kernfs_next_descendant_post(struct kernfs_node *pos,
 void kernfs_activate(struct kernfs_node *kn)
 {
 	struct kernfs_node *pos;
+	struct kernfs_root *root = kernfs_root(kn);
 
-	down_write(&kernfs_rwsem);
+	down_write(&root->kernfs_rwsem);
 
 	pos = NULL;
-	while ((pos = kernfs_next_descendant_post(pos, kn))) {
-		if (pos->flags & KERNFS_ACTIVATED)
-			continue;
+	while ((pos = kernfs_next_descendant_post(pos, kn)))
+		kernfs_activate_one(pos);
 
-		WARN_ON_ONCE(pos->parent && RB_EMPTY_NODE(&pos->rb));
-		WARN_ON_ONCE(atomic_read(&pos->active) != KN_DEACTIVATED_BIAS);
+	up_write(&root->kernfs_rwsem);
+}
+
+/**
+ * kernfs_show - show or hide a node
+ * @kn: kernfs_node to show or hide
+ * @show: whether to show or hide
+ *
+ * If @show is %false, @kn is marked hidden and deactivated. A hidden node is
+ * ignored in future activaitons. If %true, the mark is removed and activation
+ * state is restored. This function won't implicitly activate a new node in a
+ * %KERNFS_ROOT_CREATE_DEACTIVATED root which hasn't been activated yet.
+ *
+ * To avoid recursion complexities, directories aren't supported for now.
+ */
+void kernfs_show(struct kernfs_node *kn, bool show)
+{
+	struct kernfs_root *root = kernfs_root(kn);
+
+	if (WARN_ON_ONCE(kernfs_type(kn) == KERNFS_DIR))
+		return;
 
-		atomic_sub(KN_DEACTIVATED_BIAS, &pos->active);
-		pos->flags |= KERNFS_ACTIVATED;
+	down_write(&root->kernfs_rwsem);
+
+	if (show) {
+		kn->flags &= ~KERNFS_HIDDEN;
+		if (kn->flags & KERNFS_ACTIVATED)
+			kernfs_activate_one(kn);
+	} else {
+		kn->flags |= KERNFS_HIDDEN;
+		if (kernfs_active(kn))
+			atomic_add(KN_DEACTIVATED_BIAS, &kn->active);
+		kernfs_drain(kn);
 	}
 
-	up_write(&kernfs_rwsem);
+	up_write(&root->kernfs_rwsem);
 }
 
 static void __kernfs_remove(struct kernfs_node *kn)
 {
 	struct kernfs_node *pos;
 
-	lockdep_assert_held_write(&kernfs_rwsem);
+	/* Short-circuit if non-root @kn has already finished removal. */
+	if (!kn)
+		return;
+
+	lockdep_assert_held_write(&kernfs_root(kn)->kernfs_rwsem);
 
 	/*
-	 * Short-circuit if non-root @kn has already finished removal.
 	 * This is for kernfs_remove_self() which plays with active ref
 	 * after removal.
 	 */
-	if (!kn || (kn->parent && RB_EMPTY_NODE(&kn->rb)))
+	if (kn->parent && RB_EMPTY_NODE(&kn->rb))
 		return;
 
 	pr_debug("kernfs %s: removing\n", kn->name);
 
-	/* prevent any new usage under @kn by deactivating all nodes */
+	/* prevent new usage by marking all nodes removing and deactivating */
 	pos = NULL;
-	while ((pos = kernfs_next_descendant_post(pos, kn)))
+	while ((pos = kernfs_next_descendant_post(pos, kn))) {
+		pos->flags |= KERNFS_REMOVING;
 		if (kernfs_active(pos))
 			atomic_add(KN_DEACTIVATED_BIAS, &pos->active);
+	}
 
 	/* deactivate and unlink the subtree node-by-node */
 	do {
 		pos = kernfs_leftmost_descendant(kn);
 
 		/*
-		 * kernfs_drain() drops kernfs_rwsem temporarily and @pos's
+		 * kernfs_drain() may drop kernfs_rwsem temporarily and @pos's
 		 * base ref could have been put by someone else by the time
 		 * the function returns.  Make sure it doesn't go away
 		 * underneath us.
 		 */
 		kernfs_get(pos);
 
-		/*
-		 * Drain iff @kn was activated.  This avoids draining and
-		 * its lockdep annotations for nodes which have never been
-		 * activated and allows embedding kernfs_remove() in create
-		 * error paths without worrying about draining.
-		 */
-		if (kn->flags & KERNFS_ACTIVATED)
-			kernfs_drain(pos);
-		else
-			WARN_ON_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS);
+		kernfs_drain(pos);
 
 		/*
 		 * kernfs_unlink_sibling() succeeds once per node.  Use it
@@ -1381,9 +1452,16 @@ static void __kernfs_remove(struct kernfs_node *kn)
  */
 void kernfs_remove(struct kernfs_node *kn)
 {
-	down_write(&kernfs_rwsem);
+	struct kernfs_root *root;
+
+	if (!kn)
+		return;
+
+	root = kernfs_root(kn);
+
+	down_write(&root->kernfs_rwsem);
 	__kernfs_remove(kn);
-	up_write(&kernfs_rwsem);
+	up_write(&root->kernfs_rwsem);
 }
 
 /**
@@ -1469,8 +1547,9 @@ void kernfs_unbreak_active_protection(struct kernfs_node *kn)
 bool kernfs_remove_self(struct kernfs_node *kn)
 {
 	bool ret;
+	struct kernfs_root *root = kernfs_root(kn);
 
-	down_write(&kernfs_rwsem);
+	down_write(&root->kernfs_rwsem);
 	kernfs_break_active_protection(kn);
 
 	/*
@@ -1498,9 +1577,9 @@ bool kernfs_remove_self(struct kernfs_node *kn)
 			    atomic_read(&kn->active) == KN_DEACTIVATED_BIAS)
 				break;
 
-			up_write(&kernfs_rwsem);
+			up_write(&root->kernfs_rwsem);
 			schedule();
-			down_write(&kernfs_rwsem);
+			down_write(&root->kernfs_rwsem);
 		}
 		finish_wait(waitq, &wait);
 		WARN_ON_ONCE(!RB_EMPTY_NODE(&kn->rb));
@@ -1513,7 +1592,7 @@ bool kernfs_remove_self(struct kernfs_node *kn)
 	 */
 	kernfs_unbreak_active_protection(kn);
 
-	up_write(&kernfs_rwsem);
+	up_write(&root->kernfs_rwsem);
 	return ret;
 }
 
@@ -1530,6 +1609,7 @@ int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name,
 			     const void *ns)
 {
 	struct kernfs_node *kn;
+	struct kernfs_root *root;
 
 	if (!parent) {
 		WARN(1, KERN_WARNING "kernfs: can not remove '%s', no directory\n",
@@ -1537,13 +1617,17 @@ int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name,
 		return -ENOENT;
 	}
 
-	down_write(&kernfs_rwsem);
+	root = kernfs_root(parent);
+	down_write(&root->kernfs_rwsem);
 
 	kn = kernfs_find_ns(parent, name, ns);
-	if (kn)
+	if (kn) {
+		kernfs_get(kn);
 		__kernfs_remove(kn);
+		kernfs_put(kn);
+	}
 
-	up_write(&kernfs_rwsem);
+	up_write(&root->kernfs_rwsem);
 
 	if (kn)
 		return 0;
@@ -1562,6 +1646,7 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
 		     const char *new_name, const void *new_ns)
 {
 	struct kernfs_node *old_parent;
+	struct kernfs_root *root;
 	const char *old_name = NULL;
 	int error;
 
@@ -1569,7 +1654,8 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
 	if (!kn->parent)
 		return -EINVAL;
 
-	down_write(&kernfs_rwsem);
+	root = kernfs_root(kn);
+	down_write(&root->kernfs_rwsem);
 
 	error = -ENOENT;
 	if (!kernfs_active(kn) || !kernfs_active(new_parent) ||
@@ -1623,7 +1709,7 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent,
 
 	error = 0;
  out:
-	up_write(&kernfs_rwsem);
+	up_write(&root->kernfs_rwsem);
 	return error;
 }
 
@@ -1694,11 +1780,14 @@ static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx)
 	struct dentry *dentry = file->f_path.dentry;
 	struct kernfs_node *parent = kernfs_dentry_node(dentry);
 	struct kernfs_node *pos = file->private_data;
+	struct kernfs_root *root;
 	const void *ns = NULL;
 
 	if (!dir_emit_dots(file, ctx))
 		return 0;
-	down_read(&kernfs_rwsem);
+
+	root = kernfs_root(parent);
+	down_read(&root->kernfs_rwsem);
 
 	if (kernfs_ns_enabled(parent))
 		ns = kernfs_info(dentry->d_sb)->ns;
@@ -1715,12 +1804,12 @@ static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx)
 		file->private_data = pos;
 		kernfs_get(pos);
 
-		up_read(&kernfs_rwsem);
+		up_read(&root->kernfs_rwsem);
 		if (!dir_emit(ctx, name, len, ino, type))
 			return 0;
-		down_read(&kernfs_rwsem);
+		down_read(&root->kernfs_rwsem);
 	}
-	up_read(&kernfs_rwsem);
+	up_read(&root->kernfs_rwsem);
 	file->private_data = NULL;
 	ctx->pos = INT_MAX;
 	return 0;