rust: rbtree: add mutable iterator

Add mutable Iterator implementation for `RBTree`,
allowing iteration over (key, value) pairs in key order. Only values are
mutable, as mutating keys implies modifying a node's position in the tree.

Mutable iteration is used by the binder driver during shutdown to
clean up the tree maintained by the "range allocator" [1].

Link: https://lore.kernel.org/rust-for-linux/20231101-rust-binder-v1-6-08ba9197f637@google.com/ [1]
Signed-off-by: Wedson Almeida Filho <wedsonaf@gmail.com>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Tested-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Boqun Feng <boqun.feng@gmail.com>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Signed-off-by: Matt Gilbride <mattgilbride@google.com>
Link: https://lore.kernel.org/r/20240822-b4-rbtree-v12-3-014561758a57@google.com
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
This commit is contained in:
Wedson Almeida Filho 2024-08-22 16:37:55 +00:00 committed by Miguel Ojeda
parent e601f1bb8e
commit cf5397d177

View File

@ -12,7 +12,7 @@ use core::{
cmp::{Ord, Ordering},
marker::PhantomData,
mem::MaybeUninit,
ptr::{addr_of_mut, NonNull},
ptr::{addr_of_mut, from_mut, NonNull},
};
/// A red-black tree with owned nodes.
@ -194,11 +194,31 @@ impl<K, V> RBTree<K, V> {
/// Returns an iterator over the tree nodes, sorted by key.
pub fn iter(&self) -> Iter<'_, K, V> {
// INVARIANT: `bindings::rb_first` returns a valid pointer to a tree node given a valid pointer to a tree root.
Iter {
_tree: PhantomData,
// SAFETY: `self.root` is a valid pointer to the tree root.
next: unsafe { bindings::rb_first(&self.root) },
// INVARIANT:
// - `self.root` is a valid pointer to a tree root.
// - `bindings::rb_first` produces a valid pointer to a node given `root` is valid.
iter_raw: IterRaw {
// SAFETY: by the invariants, all pointers are valid.
next: unsafe { bindings::rb_first(&self.root) },
_phantom: PhantomData,
},
}
}
/// Returns a mutable iterator over the tree nodes, sorted by key.
pub fn iter_mut(&mut self) -> IterMut<'_, K, V> {
IterMut {
_tree: PhantomData,
// INVARIANT:
// - `self.root` is a valid pointer to a tree root.
// - `bindings::rb_first` produces a valid pointer to a node given `root` is valid.
iter_raw: IterRaw {
// SAFETY: by the invariants, all pointers are valid.
next: unsafe { bindings::rb_first(from_mut(&mut self.root)) },
_phantom: PhantomData,
},
}
}
@ -211,6 +231,11 @@ impl<K, V> RBTree<K, V> {
pub fn values(&self) -> impl Iterator<Item = &'_ V> {
self.iter().map(|(_, v)| v)
}
/// Returns a mutable iterator over the values of the nodes in the tree, sorted by key.
pub fn values_mut(&mut self) -> impl Iterator<Item = &'_ mut V> {
self.iter_mut().map(|(_, v)| v)
}
}
impl<K, V> RBTree<K, V>
@ -414,13 +439,9 @@ impl<'a, K, V> IntoIterator for &'a RBTree<K, V> {
/// 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 Iter<'a, K, V> {
_tree: PhantomData<&'a RBTree<K, V>>,
next: *mut bindings::rb_node,
iter_raw: IterRaw<K, V>,
}
// SAFETY: The [`Iter`] gives out immutable references to K and V, so it has the same
@ -434,21 +455,75 @@ unsafe impl<'a, K: Sync, V: Sync> Sync for Iter<'a, K, V> {}
impl<'a, K, V> Iterator for Iter<'a, K, V> {
type Item = (&'a K, &'a V);
fn next(&mut self) -> Option<Self::Item> {
// SAFETY: Due to `self._tree`, `k` and `v` are valid for the lifetime of `'a`.
self.iter_raw.next().map(|(k, v)| unsafe { (&*k, &*v) })
}
}
impl<'a, K, V> IntoIterator for &'a mut RBTree<K, V> {
type Item = (&'a K, &'a mut V);
type IntoIter = IterMut<'a, K, V>;
fn into_iter(self) -> Self::IntoIter {
self.iter_mut()
}
}
/// A mutable iterator over the nodes of a [`RBTree`].
///
/// Instances are created by calling [`RBTree::iter_mut`].
pub struct IterMut<'a, K, V> {
_tree: PhantomData<&'a mut RBTree<K, V>>,
iter_raw: IterRaw<K, V>,
}
// SAFETY: The [`IterMut`] has exclusive access to both `K` and `V`, so it is sufficient to require them to be `Send`.
// The iterator only gives out immutable references to the keys, but since the iterator has excusive access to those same
// keys, `Send` is sufficient. `Sync` would be okay, but it is more restrictive to the user.
unsafe impl<'a, K: Send, V: Send> Send for IterMut<'a, K, V> {}
// SAFETY: The [`IterMut`] gives out immutable references to K and mutable references to V, so it has the same
// thread safety requirements as mutable references.
unsafe impl<'a, K: Sync, V: Sync> Sync for IterMut<'a, K, V> {}
impl<'a, K, V> Iterator for IterMut<'a, K, V> {
type Item = (&'a K, &'a mut V);
fn next(&mut self) -> Option<Self::Item> {
self.iter_raw.next().map(|(k, v)|
// SAFETY: Due to `&mut self`, we have exclusive access to `k` and `v`, for the lifetime of `'a`.
unsafe { (&*k, &mut *v) })
}
}
/// A raw iterator over the nodes of a [`RBTree`].
///
/// # Invariants
/// - `self.next` is a valid pointer.
/// - `self.next` points to a node stored inside of a valid `RBTree`.
struct IterRaw<K, V> {
next: *mut bindings::rb_node,
_phantom: PhantomData<fn() -> (K, V)>,
}
impl<K, V> Iterator for IterRaw<K, V> {
type Item = (*mut K, *mut V);
fn next(&mut self) -> Option<Self::Item> {
if self.next.is_null() {
return None;
}
// SAFETY: By the type invariant of `Iter`, `self.next` is a valid node in an `RBTree`,
// SAFETY: By the type invariant of `IterRaw`, `self.next` is a valid node in an `RBTree`,
// and by the type invariant of `RBTree`, all nodes point to the links field of `Node<K, V>` objects.
let cur = unsafe { container_of!(self.next, Node<K, V>, links) };
let cur = unsafe { container_of!(self.next, Node<K, V>, links) }.cast_mut();
// 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) })
// SAFETY: By the same reasoning above, it is safe to dereference the node.
Some(unsafe { (addr_of_mut!((*cur).key), addr_of_mut!((*cur).value)) })
}
}