rust: sync: introduce CondVar

This is the traditional condition variable or monitor synchronisation
primitive. It is implemented with C's `wait_queue_head_t`.

It allows users to release a lock and go to sleep while guaranteeing
that notifications won't be missed. This is achieved by enqueuing a wait
entry before releasing the lock.

It also allows users to wait without releasing any locks, which makes it
just a wait queue (with the possibility of spurious wakes).

Cc: Peter Zijlstra <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Will Deacon <[email protected]>
Cc: Waiman Long <[email protected]>
Signed-off-by: Wedson Almeida Filho <[email protected]>

rust/bindings/bindings_helper.h

@@ -8,6 +8,7 @@
 
 #include <linux/slab.h>
 #include <linux/refcount.h>
+#include <linux/wait.h>
 #include <linux/sched.h>
 
 /* `bindgen` gets confused at certain things. */

rust/helpers.c

@@ -24,6 +24,7 @@
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
 #include <linux/sched/signal.h>
+#include <linux/wait.h>
 
 __noreturn void rust_helper_BUG(void)
 {
@@ -76,6 +77,12 @@ void rust_helper_spin_unlock_irqrestore(spinlock_t *lock, unsigned long flags)
 }
 EXPORT_SYMBOL_GPL(rust_helper_spin_unlock_irqrestore);
 
+void rust_helper_init_wait(struct wait_queue_entry *wq_entry)
+{
+	init_wait(wq_entry);
+}
+EXPORT_SYMBOL_GPL(rust_helper_init_wait);
+
 int rust_helper_signal_pending(struct task_struct *t)
 {
 	return signal_pending(t);

rust/kernel/sync.rs

@@ -8,10 +8,12 @@
 use crate::types::Opaque;
 
 mod arc;
+mod condvar;
 mod lock;
 
 pub use arc::{Arc, ArcBorrow, UniqueArc};
-pub use lock::{mutex::Mutex, spinlock::SpinLock};
+pub use condvar::CondVar;
+pub use lock::{mutex::Mutex, spinlock::SpinLock, Guard};
 
 /// Represents a lockdep class. It's a wrapper around C's `lock_class_key`.
 #[repr(transparent)]

rust/kernel/sync/condvar.rs

@@ -0,0 +1,251 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! A condition variable.
+//!
+//! This module allows Rust code to use the kernel's [`struct wait_queue_head`] as a condition
+//! variable.
+
+use super::{lock::Backend, Guard, LockClassKey};
+use crate::{bindings, init::PinInit, pin_init, str::CStr, task::Task, types::Opaque};
+use core::marker::PhantomPinned;
+use macros::pin_data;
+
+/// Creates a [`CondVar`] initialiser with the given name and a newly-created lock class.
+#[macro_export]
+macro_rules! new_condvar {
+    ($name:literal) => {{
+        let name = $crate::c_str!($name);
+        $crate::sync::CondVar::new(name, $crate::static_lock_class!())
+    }};
+}
+
+/// A conditional variable.
+///
+/// Exposes the kernel's [`struct wait_queue_head`] as a condition variable. It allows the caller to
+/// atomically release the given lock and go to sleep. It reacquires the lock when it wakes up. And
+/// it wakes up when notified by another thread (via [`CondVar::notify_one`] or
+/// [`CondVar::notify_all`]) or because the thread received a signal.
+///
+/// # Examples
+///
+/// The following is an example of using a condvar with a mutex:
+///
+/// ```
+/// use kernel::sync::{CondVar, Mutex};
+/// use kernel::{new_condvar, new_mutex};
+///
+/// #[pin_data]
+/// pub struct Example {
+///     #[pin]
+///     value: Mutex<u32>,
+///
+///     #[pin]
+///     value_changed: CondVar,
+/// }
+///
+/// /// Waits for `e.value` to become `v`.
+/// fn wait_for_vaue(e: &Example, v: u32) {
+///     let mut guard = e.value.lock();
+///     while *guard != v {
+///         e.value_changed.wait_uninterruptible(&mut guard);
+///     }
+/// }
+///
+/// /// Increments `e.value` and notifies all potential waiters.
+/// fn increment(e: &Example) {
+///     *e.value.lock() += 1;
+///     e.value_changed.notify_all();
+/// }
+///
+/// /// Allocates a new boxed `Example`.
+/// fn new_example() -> Result<Pin<Box<Example>>> {
+///     Box::pin_init(pin_init!(Example {
+///         value <- new_mutex!(0, "Example::vlaue"),
+///         value_changed <- new_condvar!("Example::value_changed"),
+///     }))
+/// }
+/// ```
+///
+/// The following is an example of using a condvar with an atomic variable:
+///
+/// ```
+/// use kernel::sync::CondVar;
+/// use core::sync::atomic::{AtomicU32, Ordering};
+///
+/// /// Example.
+/// #[pin_data]
+/// pub struct Example {
+///     value: AtomicU32,
+///
+///     #[pin]
+///     value_changed: CondVar,
+/// }
+///
+/// /// Waits for `e.value` to become `v`.
+/// fn wait_for_vaue(e: &Example, v: u32) {
+///     while e.value.load(Ordering::Acquire) != v {
+///         e.value_changed.wait_nolock_uninterruptible();
+///     }
+/// }
+///
+/// /// Increments `e.value` and notifies all potential waiters.
+/// fn increment(e: &Example) {
+///     e.value.fetch_add(1, Ordering::Release);
+///     e.value_changed.notify_all();
+/// }
+///
+/// /// Allocates a new boxed `Example`.
+/// fn new_example() -> Result<Pin<Box<Example>>> {
+///     Box::pin_init(pin_init!(Example {
+///         value: AtomicU32::new(0),
+///         value_changed <- new_condvar!("Example::value_changed"),
+///     }))
+/// }
+/// ```
+///
+/// [`struct wait_queue_head`]: ../../../include/linux/wait.h
+#[pin_data]
+pub struct CondVar {
+    #[pin]
+    pub(crate) wait_list: Opaque<bindings::wait_queue_head>,
+
+    /// A condvar needs to be pinned because it contains a [`struct list_head`] that is
+    /// self-referential, so it cannot be safely moved once it is initialised.
+    #[pin]
+    _pin: PhantomPinned,
+}
+
+// SAFETY: `CondVar` only uses a `struct wait_queue_head`, which is safe to use on any thread.
+#[allow(clippy::non_send_fields_in_send_ty)]
+unsafe impl Send for CondVar {}
+
+// SAFETY: `CondVar` only uses a `struct wait_queue_head`, which is safe to use on multiple threads
+// concurrently.
+unsafe impl Sync for CondVar {}
+
+impl CondVar {
+    /// Constructs a new condvar initialiser.
+    #[allow(clippy::new_ret_no_self)]
+    pub fn new(name: &'static CStr, key: &'static LockClassKey) -> impl PinInit<Self> {
+        pin_init!(Self {
+            _pin: PhantomPinned,
+            // SAFETY: `__init_waitqueue_head` initialises the waitqueue head, and both `name` and
+            // `key` have static lifetimes so they live indefinitely.
+            wait_list <- unsafe {
+                Opaque::ffi_init2(
+                    bindings::__init_waitqueue_head,
+                    name.as_char_ptr(),
+                    key.as_ptr(),
+                )
+            },
+        })
+    }
+
+    /// Atomically releases the given lock (whose ownership is proven by the guard) and puts the
+    /// thread to sleep. It wakes up when notified by [`CondVar::notify_one`] or
+    /// [`CondVar::notify_all`], or when the thread receives a signal.
+    ///
+    /// Returns whether there is a signal pending.
+    pub fn wait_internal<T, B>(&self, wait_state: u32, guard: Option<&mut Guard<'_, T, B>>)
+    where
+        T: ?Sized,
+        B: Backend,
+    {
+        let wait = Opaque::<bindings::wait_queue_entry>::uninit();
+
+        // SAFETY: `wait` points to valid memory.
+        unsafe { bindings::init_wait(wait.get()) };
+
+        // SAFETY: Both `wait` and `wait_list` point to valid memory.
+        unsafe {
+            bindings::prepare_to_wait_exclusive(self.wait_list.get(), wait.get(), wait_state as _)
+        };
+
+        if let Some(g) = guard {
+            // SAFETY: No arguments, switches to another thread.
+            g.do_unlocked(|| unsafe { bindings::schedule() });
+        } else {
+            // SAFETY: No arguments, switches to another thread.
+            unsafe { bindings::schedule() };
+        }
+
+        // SAFETY: Both `wait` and `wait_list` point to valid memory.
+        unsafe { bindings::finish_wait(self.wait_list.get(), wait.get()) };
+    }
+
+    /// Releases the lock and waits for a notification in interruptible mode.
+    ///
+    /// Atomically releases the given lock (whose ownership is proven by the guard) and puts the
+    /// thread to sleep. It wakes up when notified by [`CondVar::notify_one`] or
+    /// [`CondVar::notify_all`], or when the thread receives a signal. It may also wake up
+    /// spuriously.
+    ///
+    /// Returns whether there is a signal pending.
+    #[must_use = "wait returns if a signal is pending, so the caller must check the return value"]
+    pub fn wait<T: ?Sized, B: Backend>(&self, guard: &mut Guard<'_, T, B>) -> bool {
+        self.wait_internal(bindings::TASK_INTERRUPTIBLE, Some(guard));
+        Task::current().signal_pending()
+    }
+
+    /// Waits for a notification in interruptible mode.
+    ///
+    /// It may also wake up spuriously.
+    ///
+    /// Returns whether there is a signal pending.
+    #[must_use = "wait returns if a signal is pending, so the caller must check the return value"]
+    pub fn wait_nolock(&self) -> bool {
+        self.wait_internal::<(), super::lock::mutex::MutexBackend>(
+            bindings::TASK_INTERRUPTIBLE,
+            None,
+        );
+        Task::current().signal_pending()
+    }
+
+    /// Releases the lock and waits for a notification in uninterruptible mode.
+    ///
+    /// Similar to [`CondVar::wait`], except that the wait is not interruptible. That is, the
+    /// thread won't wake up due to signals. It may, however, wake up supirously.
+    pub fn wait_uninterruptible<T: ?Sized, B: Backend>(&self, guard: &mut Guard<'_, T, B>) {
+        self.wait_internal(bindings::TASK_UNINTERRUPTIBLE, Some(guard))
+    }
+
+    /// Waits for a notification in uninterruptible mode.
+    ///
+    /// Similar to [`CondVar::wait`], except that the wait is not interruptible. That is, the
+    /// thread won't wake up due to signals. It may, however, wake up supirously.
+    pub fn wait_nolock_uninterruptible(&self) {
+        self.wait_internal::<(), super::lock::mutex::MutexBackend>(
+            bindings::TASK_UNINTERRUPTIBLE,
+            None,
+        )
+    }
+
+    /// Calls the kernel function to notify the appropriate number of threads with the given flags.
+    fn notify(&self, count: i32, flags: u32) {
+        // SAFETY: `wait_list` points to valid memory.
+        unsafe {
+            bindings::__wake_up(
+                self.wait_list.get(),
+                bindings::TASK_NORMAL,
+                count,
+                flags as _,
+            )
+        };
+    }
+
+    /// Wakes a single waiter up, if any.
+    ///
+    /// This is not 'sticky' in the sense that if no thread is waiting, the notification is lost
+    /// completely (as opposed to automatically waking up the next waiter).
+    pub fn notify_one(&self) {
+        self.notify(1, 0);
+    }
+
+    /// Wakes all waiters up, if any.
+    ///
+    /// This is not 'sticky' in the sense that if no thread is waiting, the notification is lost
+    /// completely (as opposed to automatically waking up the next waiter).
+    pub fn notify_all(&self) {
+        self.notify(0, 0);
+    }
+}

rust/kernel/sync/lock.rs

@@ -170,7 +170,6 @@ pub struct Guard<'a, T: ?Sized, B: Backend> {
 unsafe impl<T: Sync + ?Sized, B: Backend> Sync for Guard<'_, T, B> {}
 
 impl<T: ?Sized, B: Backend> Guard<'_, T, B> {
-    #[allow(dead_code)]
     pub(crate) fn do_unlocked(&mut self, cb: impl FnOnce()) {
         // SAFETY: The caller owns the lock, so it is safe to unlock it.
         unsafe { B::unlock(self.lock.state.get(), &self.state) };