Re: [PATCH v2 13/13] rust: sync: introduce `LockedBy`

[Benno Lossin]

On 08.04.23 06:11, Wedson Almeida Filho wrote:
> On Fri, 7 Apr 2023 at 18:00, Benno Lossin <y86-dev@xxxxxxxxxxxxxx> wrote:
>>
>> On 05.04.23 19:51, Wedson Almeida Filho wrote:
>>> From: Wedson Almeida Filho <walmeida@xxxxxxxxxxxxx>
>>>
>>> This allows us to have data protected by a lock despite not being
>>> wrapped by it. Access is granted by providing evidence that the lock is
>>> held by the caller.
>>>
>>> Signed-off-by: Wedson Almeida Filho <walmeida@xxxxxxxxxxxxx>
>>> ---
>>> v1 -> v2: Added build_assert to rule out zero-sized types
>>>
>>>    rust/kernel/sync.rs           |   2 +
>>>    rust/kernel/sync/lock.rs      |   2 +-
>>>    rust/kernel/sync/locked_by.rs | 128 ++++++++++++++++++++++++++++++++++
>>>    3 files changed, 131 insertions(+), 1 deletion(-)
>>>    create mode 100644 rust/kernel/sync/locked_by.rs
>>>
>>> diff --git a/rust/kernel/sync.rs b/rust/kernel/sync.rs
>>> index d6dd0e2c1678..f8edb6d0d794 100644
>>> --- a/rust/kernel/sync.rs
>>> +++ b/rust/kernel/sync.rs
>>> @@ -10,10 +10,12 @@ use crate::types::Opaque;
>>>    mod arc;
>>>    mod condvar;
>>>    pub mod lock;
>>> +mod locked_by;
>>>
>>>    pub use arc::{Arc, ArcBorrow, UniqueArc};
>>>    pub use condvar::CondVar;
>>>    pub use lock::{mutex::Mutex, spinlock::SpinLock};
>>> +pub use locked_by::LockedBy;
>>>
>>>    /// Represents a lockdep class. It's a wrapper around C's `lock_class_key`.
>>>    #[repr(transparent)]
>>> diff --git a/rust/kernel/sync/lock.rs b/rust/kernel/sync/lock.rs
>>> index f52ba9ab1b70..51c996ca2109 100644
>>> --- a/rust/kernel/sync/lock.rs
>>> +++ b/rust/kernel/sync/lock.rs
>>> @@ -111,7 +111,7 @@ pub struct Lock<T: ?Sized, B: Backend> {
>>>        _pin: PhantomPinned,
>>>
>>>        /// The data protected by the lock.
>>> -    data: UnsafeCell<T>,
>>> +    pub(crate) data: UnsafeCell<T>,
>>>    }
>>>
>>>    // SAFETY: `Lock` can be transferred across thread boundaries iff the data it protects can.
>>> diff --git a/rust/kernel/sync/locked_by.rs b/rust/kernel/sync/locked_by.rs
>>> new file mode 100644
>>> index 000000000000..191e37d804e5
>>> --- /dev/null
>>> +++ b/rust/kernel/sync/locked_by.rs
>>> @@ -0,0 +1,128 @@
>>> +// SPDX-License-Identifier: GPL-2.0
>>> +
>>> +//! A wrapper for data protected by a lock that does not wrap it.
>>> +
>>> +use super::{lock::Backend, lock::Lock};
>>> +use core::{cell::UnsafeCell, ptr};
>>> +
>>> +/// Allows access to some data to be serialised by a lock that does not wrap it.
>>> +///
>>> +/// In most cases, data protected by a lock is wrapped by the appropriate lock type, e.g.,
>>> +/// [`super::Mutex`] or [`super::SpinLock`]. [`LockedBy`] is meant for cases when this is not
>>> +/// possible. For example, if a container has a lock and some data in the contained elements needs
>>> +/// to be protected by the same lock.
>>> +///
>>> +/// [`LockedBy`] wraps the data in lieu of another locking primitive, and only allows access to it
>>> +/// when the caller shows evidence that the 'external' lock is locked.
>>> +///
>>
>> Maybe add that the `access`/`access_mut` functions panic when the supplied
>> external value is not the correct one.
>
> Will do for v3.
>
>>> +/// # Examples
>>> +///
>>> +/// The following is an example for illustrative purposes: `InnerDirectory::bytes_used` is an
>>> +/// aggregate of all `InnerFile::bytes_used` and must be kept consistent; so we wrap `InnerFile` in
>>> +/// a `LockedBy` so that it shares a lock with `InnerDirectory`. This allows us to enforce at
>>> +/// compile-time that access to `InnerFile` is only granted when an `InnerDirectory` is also
>>> +/// locked; we enforce at run time that the right `InnerDirectory` is locked.
>>> +///
>>> +/// ```
>>> +/// use kernel::sync::{LockedBy, Mutex};
>>> +///
>>> +/// struct InnerFile {
>>> +///     bytes_used: u64,
>>> +/// }
>>> +///
>>> +/// struct File {
>>> +///     _ino: u32,
>>> +///     inner: LockedBy<InnerFile, InnerDirectory>,
>>> +/// }
>>> +///
>>> +/// struct InnerDirectory {
>>> +///     /// The sum of the bytes used by all files.
>>> +///     bytes_used: u64,
>>> +///     _files: Vec<File>,
>>> +/// }
>>> +///
>>> +/// struct Directory {
>>> +///     _ino: u32,
>>> +///     inner: Mutex<InnerDirectory>,
>>> +/// }
>>> +///
>>> +/// /// Prints `bytes_used` from both the directory and file.
>>> +/// fn print_bytes_used(dir: &Directory, file: &File) {
>>> +///     let guard = dir.inner.lock();
>>> +///     let inner_file = file.inner.access(&guard);
>>> +///     pr_info!("{} {}", guard.bytes_used, inner_file.bytes_used);
>>> +/// }
>>> +///
>>> +/// /// Increments `bytes_used` for both the directory and file.
>>> +/// fn inc_bytes_used(dir: &Directory, file: &File) {
>>> +///     let mut guard = dir.inner.lock();
>>> +///     guard.bytes_used += 10;
>>> +///
>>> +///     let file_inner = file.inner.access_mut(&mut guard);
>>> +///     file_inner.bytes_used += 10;
>>> +/// }
>>> +///
>>> +/// /// Creates a new file.
>>> +/// fn new_file(ino: u32, dir: &Directory) -> File {
>>> +///     File {
>>> +///         _ino: ino,
>>> +///         inner: LockedBy::new(&dir.inner, InnerFile { bytes_used: 0 }),
>>> +///     }
>>> +/// }
>>> +/// ```
>>> +pub struct LockedBy<T: ?Sized, U: ?Sized> {
>>> +    owner: *const U,
>>> +    data: UnsafeCell<T>,
>>> +}
>>> +
>>> +// SAFETY: `LockedBy` can be transferred across thread boundaries iff the data it protects can.
>>> +unsafe impl<T: ?Sized + Send, U: ?Sized> Send for LockedBy<T, U> {}
>>> +
>>> +// SAFETY: `LockedBy` serialises the interior mutability it provides, so it is `Sync` as long as the
>>> +// data it protects is `Send`.
>>> +unsafe impl<T: ?Sized + Send, U: ?Sized> Sync for LockedBy<T, U> {}
>>> +
>>> +impl<T, U: ?Sized> LockedBy<T, U> {
>>> +    /// Constructs a new instance of [`LockedBy`].
>>> +    ///
>>> +    /// It stores a raw pointer to the owner that is never dereferenced. It is only used to ensure
>>> +    /// that the right owner is being used to access the protected data. If the owner is freed, the
>>> +    /// data becomes inaccessible; if another instance of the owner is allocated *on the same
>>> +    /// memory location*, the data becomes accessible again: none of this affects memory safety
>>> +    /// because in any case at most one thread (or CPU) can access the protected data at a time.
>>> +    pub fn new(owner: &Lock<U, impl Backend>, data: T) -> Self {
>>
>> I think it would be sensible to also do the ZST check here, then it will
>> fail immediately on construction (but also keep the other location, as it
>> does not add any runtime cost).
>
> This ZST restriction on `U` applies to `access` and `access_mut`, but
> doesn't apply to versions of these functions that work on `Guard`
> instances, which we have in the `rust` branch but not here yet. (The
> restrictions there are different.) So it doesn't make sense to block
> the _creation_ of `LockedBy` instances if `access`/`access_mut` are
> never used.

Ah because you can only get a `Guard` safely via a `Lock` and at
the moment, all locks cannot be zero-sized even if the data is.

But if we at some point decide to add a `Backend` with the
`State` being a ZST, then this code becomes unsound.

What about adding a `build_assert!(mem::size_of::<Lock<T, B>>() > 0)`
(you will sadly have to spell out the generic parameter of `Backend`).
I worry that we might not remember all of these details when
we add new locks.

--
Cheers,
Benno

>> Also, I think you should mention in the documentation that ZSTs are not
>> supported. And it would be good to have an explaining comment on the
>> `build_assert!` why we disallow ZSTs here.
>
> I'll add comments in v3 to access/access_mut.
>
>>> +        Self {
>>> +            owner: owner.data.get(),
>>> +            data: UnsafeCell::new(data),
>>> +        }
>>> +    }
>>> +}
>>> +
>>> +impl<T: ?Sized, U> LockedBy<T, U> {
>>> +    /// Returns a reference to the protected data when the caller provides evidence (via a
>>> +    /// reference) that the owner is locked.
>>
>> Maybe add a `# Panic` section, also for `access_mut`.
>>
>> --
>> Cheers,
>> Benno
>>
>>> +    pub fn access<'a>(&'a self, owner: &'a U) -> &'a T {
>>> +        crate::build_assert!(core::mem::size_of::<U>() > 0);
>>> +        if !ptr::eq(owner, self.owner) {
>>> +            panic!("mismatched owners");
>>> +        }
>>> +
>>> +        // SAFETY: `owner` is evidence that the owner is locked.
>>> +        unsafe { &*self.data.get() }
>>> +    }
>>> +
>>> +    /// Returns a mutable reference to the protected data when the caller provides evidence (via a
>>> +    /// mutable owner) that the owner is locked mutably.
>>> +    ///
>>> +    /// Showing a mutable reference to the owner is sufficient because we know no other references
>>> +    /// can exist to it.
>>> +    pub fn access_mut<'a>(&'a self, owner: &'a mut U) -> &'a mut T {
>>> +        crate::build_assert!(core::mem::size_of::<U>() > 0);
>>> +        if !ptr::eq(owner, self.owner) {
>>> +            panic!("mismatched owners");
>>> +        }
>>> +
>>> +        // SAFETY: `owner` is evidence that there is only one reference to the owner.
>>> +        unsafe { &mut *self.data.get() }
>>> +    }
>>> +}
>>> --
>>> 2.34.1
>>>
>>