4 files changed, 104 insertions, 46 deletions

diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index 8b2bd65d70e7..458519e416fe 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -54,9 +54,9 @@ static bool kernfs_lockdep(struct kernfs_node *kn)
 static int kernfs_name_locked(struct kernfs_node *kn, char *buf, size_t buflen)
 {
 	if (!kn)
-		return strlcpy(buf, "(null)", buflen);
+		return strscpy(buf, "(null)", buflen);
 
-	return strlcpy(buf, kn->parent ? kn->name : "/", buflen);
+	return strscpy(buf, kn->parent ? kn->name : "/", buflen);
 }
 
 /* kernfs_node_depth - compute depth from @from to @to */
@@ -127,7 +127,7 @@ static struct kernfs_node *kernfs_common_ancestor(struct kernfs_node *a,
  *
  * [3] when @kn_to is %NULL result will be "(null)"
  *
- * Return: the length of the full path.  If the full length is equal to or
+ * Return: the length of the constructed path.  If the path would have been
  * greater than @buflen, @buf contains the truncated path with the trailing
  * '\0'.  On error, -errno is returned.
  */
@@ -138,16 +138,17 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to,
 	struct kernfs_node *kn, *common;
 	const char parent_str[] = "/..";
 	size_t depth_from, depth_to, len = 0;
+	ssize_t copied;
 	int i, j;
 
 	if (!kn_to)
-		return strlcpy(buf, "(null)", buflen);
+		return strscpy(buf, "(null)", buflen);
 
 	if (!kn_from)
 		kn_from = kernfs_root(kn_to)->kn;
 
 	if (kn_from == kn_to)
-		return strlcpy(buf, "/", buflen);
+		return strscpy(buf, "/", buflen);
 
 	common = kernfs_common_ancestor(kn_from, kn_to);
 	if (WARN_ON(!common))
@@ -158,18 +159,19 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to,
 
 	buf[0] = '\0';
 
-	for (i = 0; i < depth_from; i++)
-		len += strlcpy(buf + len, parent_str,
-			       len < buflen ? buflen - len : 0);
+	for (i = 0; i < depth_from; i++) {
+		copied = strscpy(buf + len, parent_str, buflen - len);
+		if (copied < 0)
+			return copied;
+		len += copied;
+	}
 
 	/* Calculate how many bytes we need for the rest */
 	for (i = depth_to - 1; i >= 0; i--) {
 		for (kn = kn_to, j = 0; j < i; j++)
 			kn = kn->parent;
-		len += strlcpy(buf + len, "/",
-			       len < buflen ? buflen - len : 0);
-		len += strlcpy(buf + len, kn->name,
-			       len < buflen ? buflen - len : 0);
+
+		len += scnprintf(buf + len, buflen - len, "/%s", kn->name);
 	}
 
 	return len;
@@ -182,12 +184,12 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to,
  * @buflen: size of @buf
  *
  * Copies the name of @kn into @buf of @buflen bytes.  The behavior is
- * similar to strlcpy().
+ * similar to strscpy().
  *
  * Fills buffer with "(null)" if @kn is %NULL.
  *
- * Return: the length of @kn's name and if @buf isn't long enough,
- * it's filled up to @buflen-1 and nul terminated.
+ * Return: the resulting length of @buf. If @buf isn't long enough,
+ * it's filled up to @buflen-1 and nul terminated, and returns -E2BIG.
  *
  * This function can be called from any context.
  */
@@ -214,7 +216,7 @@ int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen)
  * path (which includes '..'s) as needed to reach from @from to @to is
  * returned.
  *
- * Return: the length of the full path.  If the full length is equal to or
+ * Return: the length of the constructed path.  If the path would have been
  * greater than @buflen, @buf contains the truncated path with the trailing
  * '\0'.  On error, -errno is returned.
  */
@@ -265,12 +267,10 @@ void pr_cont_kernfs_path(struct kernfs_node *kn)
 	sz = kernfs_path_from_node(kn, NULL, kernfs_pr_cont_buf,
 				   sizeof(kernfs_pr_cont_buf));
 	if (sz < 0) {
-		pr_cont("(error)");
-		goto out;
-	}
-
-	if (sz >= sizeof(kernfs_pr_cont_buf)) {
-		pr_cont("(name too long)");
+		if (sz == -E2BIG)
+			pr_cont("(name too long)");
+		else
+			pr_cont("(error)");
 		goto out;
 	}
 
@@ -529,6 +529,20 @@ void kernfs_get(struct kernfs_node *kn)
 }
 EXPORT_SYMBOL_GPL(kernfs_get);
 
+static void kernfs_free_rcu(struct rcu_head *rcu)
+{
+	struct kernfs_node *kn = container_of(rcu, struct kernfs_node, rcu);
+
+	kfree_const(kn->name);
+
+	if (kn->iattr) {
+		simple_xattrs_free(&kn->iattr->xattrs, NULL);
+		kmem_cache_free(kernfs_iattrs_cache, kn->iattr);
+	}
+
+	kmem_cache_free(kernfs_node_cache, kn);
+}
+
 /**
  * kernfs_put - put a reference count on a kernfs_node
  * @kn: the target kernfs_node
@@ -557,16 +571,11 @@ void kernfs_put(struct kernfs_node *kn)
 	if (kernfs_type(kn) == KERNFS_LINK)
 		kernfs_put(kn->symlink.target_kn);
 
-	kfree_const(kn->name);
-
-	if (kn->iattr) {
-		simple_xattrs_free(&kn->iattr->xattrs, NULL);
-		kmem_cache_free(kernfs_iattrs_cache, kn->iattr);
-	}
 	spin_lock(&kernfs_idr_lock);
 	idr_remove(&root->ino_idr, (u32)kernfs_ino(kn));
 	spin_unlock(&kernfs_idr_lock);
-	kmem_cache_free(kernfs_node_cache, kn);
+
+	call_rcu(&kn->rcu, kernfs_free_rcu);
 
 	kn = parent;
 	if (kn) {
@@ -575,7 +584,7 @@ void kernfs_put(struct kernfs_node *kn)
 	} else {
 		/* just released the root kn, free @root too */
 		idr_destroy(&root->ino_idr);
-		kfree(root);
+		kfree_rcu(root, rcu);
 	}
 }
 EXPORT_SYMBOL_GPL(kernfs_put);
@@ -676,6 +685,18 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent,
 {
 	struct kernfs_node *kn;
 
+	if (parent->mode & S_ISGID) {
+		/* this code block imitates inode_init_owner() for
+		 * kernfs
+		 */
+
+		if (parent->iattr)
+			gid = parent->iattr->ia_gid;
+
+		if (flags & KERNFS_DIR)
+			mode |= S_ISGID;
+	}
+
 	kn = __kernfs_new_node(kernfs_root(parent), parent,
 			       name, mode, uid, gid, flags);
 	if (kn) {
@@ -703,7 +724,7 @@ struct kernfs_node *kernfs_find_and_get_node_by_id(struct kernfs_root *root,
 	ino_t ino = kernfs_id_ino(id);
 	u32 gen = kernfs_id_gen(id);
 
-	spin_lock(&kernfs_idr_lock);
+	rcu_read_lock();
 
 	kn = idr_find(&root->ino_idr, (u32)ino);
 	if (!kn)
@@ -727,10 +748,10 @@ struct kernfs_node *kernfs_find_and_get_node_by_id(struct kernfs_root *root,
 	if (unlikely(!__kernfs_active(kn) || !atomic_inc_not_zero(&kn->count)))
 		goto err_unlock;
 
-	spin_unlock(&kernfs_idr_lock);
+	rcu_read_unlock();
 	return kn;
 err_unlock:
-	spin_unlock(&kernfs_idr_lock);
+	rcu_read_unlock();
 	return NULL;
 }
 
@@ -850,16 +871,16 @@ static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent,
 					  const unsigned char *path,
 					  const void *ns)
 {
-	size_t len;
+	ssize_t len;
 	char *p, *name;
 
 	lockdep_assert_held_read(&kernfs_root(parent)->kernfs_rwsem);
 
 	spin_lock_irq(&kernfs_pr_cont_lock);
 
-	len = strlcpy(kernfs_pr_cont_buf, path, sizeof(kernfs_pr_cont_buf));
+	len = strscpy(kernfs_pr_cont_buf, path, sizeof(kernfs_pr_cont_buf));
 
-	if (len >= sizeof(kernfs_pr_cont_buf)) {
+	if (len < 0) {
 		spin_unlock_irq(&kernfs_pr_cont_lock);
 		return NULL;
 	}
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index aaa76410e550..8502ef68459b 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -447,7 +447,7 @@ static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma)
 	 * warnings and we don't want to add spurious locking dependency
 	 * between the two.  Check whether mmap is actually implemented
 	 * without grabbing @of->mutex by testing HAS_MMAP flag.  See the
-	 * comment in kernfs_file_open() for more details.
+	 * comment in kernfs_fop_open() for more details.
 	 */
 	if (!(of->kn->flags & KERNFS_HAS_MMAP))
 		return -ENODEV;
@@ -483,9 +483,11 @@ static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma)
 		goto out_put;
 
 	rc = 0;
-	of->mmapped = true;
-	of_on(of)->nr_mmapped++;
-	of->vm_ops = vma->vm_ops;
+	if (!of->mmapped) {
+		of->mmapped = true;
+		of_on(of)->nr_mmapped++;
+		of->vm_ops = vma->vm_ops;
+	}
 	vma->vm_ops = &kernfs_vm_ops;
 out_put:
 	kernfs_put_active(of->kn);
@@ -634,11 +636,18 @@ static int kernfs_fop_open(struct inode *inode, struct file *file)
 	 * each file a separate locking class.  Let's differentiate on
 	 * whether the file has mmap or not for now.
 	 *
-	 * Both paths of the branch look the same.  They're supposed to
+	 * For similar reasons, writable and readonly files are given different
+	 * lockdep key, because the writable file /sys/power/resume may call vfs
+	 * lookup helpers for arbitrary paths and readonly files can be read by
+	 * overlayfs from vfs helpers when sysfs is a lower layer of overalyfs.
+	 *
+	 * All three cases look the same.  They're supposed to
 	 * look that way and give @of->mutex different static lockdep keys.
 	 */
 	if (has_mmap)
 		mutex_init(&of->mutex);
+	else if (file->f_mode & FMODE_WRITE)
+		mutex_init(&of->mutex);
 	else
 		mutex_init(&of->mutex);
 
@@ -854,6 +863,33 @@ static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait)
 	return ret;
 }
 
+static loff_t kernfs_fop_llseek(struct file *file, loff_t offset, int whence)
+{
+	struct kernfs_open_file *of = kernfs_of(file);
+	const struct kernfs_ops *ops;
+	loff_t ret;
+
+	/*
+	 * @of->mutex nests outside active ref and is primarily to ensure that
+	 * the ops aren't called concurrently for the same open file.
+	 */
+	mutex_lock(&of->mutex);
+	if (!kernfs_get_active(of->kn)) {
+		mutex_unlock(&of->mutex);
+		return -ENODEV;
+	}
+
+	ops = kernfs_ops(of->kn);
+	if (ops->llseek)
+		ret = ops->llseek(of, offset, whence);
+	else
+		ret = generic_file_llseek(file, offset, whence);
+
+	kernfs_put_active(of->kn);
+	mutex_unlock(&of->mutex);
+	return ret;
+}
+
 static void kernfs_notify_workfn(struct work_struct *work)
 {
 	struct kernfs_node *kn;
@@ -956,7 +992,7 @@ EXPORT_SYMBOL_GPL(kernfs_notify);
 const struct file_operations kernfs_file_fops = {
 	.read_iter	= kernfs_fop_read_iter,
 	.write_iter	= kernfs_fop_write_iter,
-	.llseek		= generic_file_llseek,
+	.llseek		= kernfs_fop_llseek,
 	.mmap		= kernfs_fop_mmap,
 	.open		= kernfs_fop_open,
 	.release	= kernfs_fop_release,
diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h
index 237f2764b941..b42ee6547cdc 100644
--- a/fs/kernfs/kernfs-internal.h
+++ b/fs/kernfs/kernfs-internal.h
@@ -49,6 +49,8 @@ struct kernfs_root {
 	struct rw_semaphore	kernfs_rwsem;
 	struct rw_semaphore	kernfs_iattr_rwsem;
 	struct rw_semaphore	kernfs_supers_rwsem;
+
+	struct rcu_head		rcu;
 };
 
 /* +1 to avoid triggering overflow warning when negating it */
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index 4628edde2e7e..e29f4edf9572 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -125,9 +125,6 @@ static struct dentry *__kernfs_fh_to_dentry(struct super_block *sb,
 
 	inode = kernfs_get_inode(sb, kn);
 	kernfs_put(kn);
-	if (!inode)
-		return ERR_PTR(-ESTALE);
-
 	return d_obtain_alias(inode);
 }
 
@@ -361,7 +358,9 @@ int kernfs_get_tree(struct fs_context *fc)
 		}
 		sb->s_flags |= SB_ACTIVE;
 
-		uuid_gen(&sb->s_uuid);
+		uuid_t uuid;
+		uuid_gen(&uuid);
+		super_set_uuid(sb, uuid.b, sizeof(uuid));
 
 		down_write(&root->kernfs_supers_rwsem);
 		list_add(&info->node, &info->root->supers);