Re: [PATCH v3 2/5] rust: rbtree: add `RBTreeIterator`

[Benno Lossin]

On 18.04.24 16:15, Matt Gilbride wrote:
> @@ -188,6 +212,25 @@ pub fn try_reserve_node() -> Result<RBTreeNodeReservation<K, V>> {
>      pub fn try_allocate_node(key: K, value: V) -> Result<RBTreeNode<K, V>> {
>          Ok(Self::try_reserve_node()?.into_node(key, value))
>      }
> +
> +    /// Returns an iterator over the tree nodes, sorted by key.
> +    pub fn iter(&self) -> RBTreeIterator<'_, K, V> {
> +        RBTreeIterator {

There is a missing `INVARIANT` comment here justifying the invariants of
`RBTreeIterator`.

> +            _tree: PhantomData,
> +            // SAFETY: `root` is valid as it's embedded in `self` and we have a valid `self`.
> +            next: unsafe { bindings::rb_first(&self.root) },
> +        }
> +    }
> +
> +    /// Returns an iterator over the keys of the nodes in the tree, in sorted order.
> +    pub fn keys(&self) -> impl Iterator<Item = &'_ K> {
> +        self.iter().map(|(k, _)| k)
> +    }
> +
> +    /// Returns an iterator over the values of the nodes in the tree, sorted by key.
> +    pub fn values(&self) -> impl Iterator<Item = &'_ V> {
> +        self.iter().map(|(_, v)| v)
> +    }
>  }
> 
>  impl<K, V> RBTree<K, V>
> @@ -373,6 +416,56 @@ fn drop(&mut self) {
>      }
>  }
> 
> +impl<'a, K, V> IntoIterator for &'a RBTree<K, V> {
> +    type Item = (&'a K, &'a V);
> +    type IntoIter = RBTreeIterator<'a, K, V>;
> +
> +    fn into_iter(self) -> Self::IntoIter {
> +        self.iter()
> +    }
> +}
> +
> +/// An iterator over the nodes of a [`RBTree`].
> +///
> +/// Instances are created by calling [`RBTree::iter`].
> +///
> +/// # Invariants
> +/// - `self.next` is a valid pointer.
> +/// - `self.next` points to a node stored inside of a valid `RBTree`.
> +pub struct RBTreeIterator<'a, K, V> {
> +    _tree: PhantomData<&'a RBTree<K, V>>,
> +    next: *mut bindings::rb_node,
> +}
> +
> +// SAFETY: The [`RBTreeIterator`] gives out immutable references to K and V, so it has the same
> +// thread safety requirements as immutable references.
> +unsafe impl<'a, K: Sync, V: Sync> Send for RBTreeIterator<'a, K, V> {}

The bounds on `K` and `V` look like typos to me. They should be `Send`
instead.

> +
> +// SAFETY: The [`RBTreeIterator`] gives out immutable references to K and V, so it has the same
> +// thread safety requirements as immutable references.
> +unsafe impl<'a, K: Sync, V: Sync> Sync for RBTreeIterator<'a, K, V> {}
> +
> +impl<'a, K, V> Iterator for RBTreeIterator<'a, K, V> {
> +    type Item = (&'a K, &'a V);
> +
> +    fn next(&mut self) -> Option<Self::Item> {
> +        if self.next.is_null() {
> +            return None;
> +        }
> +
> +        // SAFETY: By the type invariant of `Self`, all non-null `rb_node` pointers stored in `self`

This is not an invariant of `Self`, but rather `RBTree` and `self`
should be "`RBtree`s".

-- 
Cheers,
Benno

> +        // point to the links field of `Node<K, V>` objects.
> +        let cur = unsafe { container_of!(self.next, Node<K, V>, links) };
> +
> +        // SAFETY: `self.next` is a valid tree node by the type invariants.
> +        self.next = unsafe { bindings::rb_next(self.next) };
> +
> +        // SAFETY: By the same reasoning above, it is safe to dereference the node. Additionally,
> +        // it is ok to return a reference to members because the iterator must outlive it.
> +        Some(unsafe { (&(*cur).key, &(*cur).value) })
> +    }
> +}
> +
>  /// A memory reservation for a red-black tree node.
>  ///
>  /// It contains the memory needed to hold a node that can be inserted into a red-black tree. One
> 
> --
> 2.44.0.769.g3c40516874-goog
>