Message-ID: <9f26e6d4-77db-4dd2-a934-c83008cf1bdd@lucifer.local>
Date: Fri, 22 Nov 2024 17:27:36 +0000
From: Lorenzo Stoakes <lorenzo.stoakes@...cle.com>
To: Alice Ryhl <aliceryhl@...gle.com>
Cc: Miguel Ojeda <ojeda@...nel.org>, Matthew Wilcox <willy@...radead.org>,
        Vlastimil Babka <vbabka@...e.cz>, John Hubbard <jhubbard@...dia.com>,
        "Liam R. Howlett" <Liam.Howlett@...cle.com>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        Arnd Bergmann <arnd@...db.de>, Christian Brauner <brauner@...nel.org>,
        Jann Horn <jannh@...gle.com>, Suren Baghdasaryan <surenb@...gle.com>,
        Alex Gaynor <alex.gaynor@...il.com>, Boqun Feng <boqun.feng@...il.com>,
        Gary Guo <gary@...yguo.net>,
        Björn Roy Baron <bjorn3_gh@...tonmail.com>,
        Benno Lossin <benno.lossin@...ton.me>, linux-kernel@...r.kernel.org,
        linux-mm@...ck.org, rust-for-linux@...r.kernel.org,
        Andreas Hindborg <a.hindborg@...nel.org>
Subject: Re: [PATCH v9 1/8] mm: rust: add abstraction for struct mm_struct

On Fri, Nov 22, 2024 at 03:40:26PM +0000, Alice Ryhl wrote:
> These abstractions allow you to reference a `struct mm_struct` using
> both mmgrab and mmget refcounts. This is done using two Rust types:
>
> * Mm - represents an mm_struct where you don't know anything about the
>   value of mm_users.
> * MmWithUser - represents an mm_struct where you know at compile time
>   that mm_users is non-zero.
>
> This allows us to encode in the type system whether a method requires
> that mm_users is non-zero or not. For instance, you can always call
> `mmget_not_zero` but you can only call `mmap_read_lock` when mm_users is
> non-zero.
>
> It's possible to access current->mm without a refcount increment, but
> that is added in a later patch of this series.
>
> Signed-off-by: Alice Ryhl <aliceryhl@...gle.com>

I see you address the current thing in a later commit, so as the rest of the
patch looked fine previously (with help from your kind explanations on the rust
side :), so:

Acked-by: Lorenzo Stoakes <lorenzo.stoakes@...cle.com> (for mm bits)

> ---
>  rust/helpers/helpers.c |   1 +
>  rust/helpers/mm.c      |  39 +++++++++
>  rust/kernel/lib.rs     |   1 +
>  rust/kernel/mm.rs      | 219 +++++++++++++++++++++++++++++++++++++++++++++++++
>  4 files changed, 260 insertions(+)
>
> diff --git a/rust/helpers/helpers.c b/rust/helpers/helpers.c
> index 6d90afd38c40..2ee3af594633 100644
> --- a/rust/helpers/helpers.c
> +++ b/rust/helpers/helpers.c
> @@ -15,6 +15,7 @@
>  #include "err.c"
>  #include "fs.c"
>  #include "kunit.c"
> +#include "mm.c"
>  #include "mutex.c"
>  #include "page.c"
>  #include "rbtree.c"
> diff --git a/rust/helpers/mm.c b/rust/helpers/mm.c
> new file mode 100644
> index 000000000000..7201747a5d31
> --- /dev/null
> +++ b/rust/helpers/mm.c
> @@ -0,0 +1,39 @@
> +// SPDX-License-Identifier: GPL-2.0
> +
> +#include <linux/mm.h>
> +#include <linux/sched/mm.h>
> +
> +void rust_helper_mmgrab(struct mm_struct *mm)
> +{
> +	mmgrab(mm);
> +}
> +
> +void rust_helper_mmdrop(struct mm_struct *mm)
> +{
> +	mmdrop(mm);
> +}
> +
> +void rust_helper_mmget(struct mm_struct *mm)
> +{
> +	mmget(mm);
> +}
> +
> +bool rust_helper_mmget_not_zero(struct mm_struct *mm)
> +{
> +	return mmget_not_zero(mm);
> +}
> +
> +void rust_helper_mmap_read_lock(struct mm_struct *mm)
> +{
> +	mmap_read_lock(mm);
> +}
> +
> +bool rust_helper_mmap_read_trylock(struct mm_struct *mm)
> +{
> +	return mmap_read_trylock(mm);
> +}
> +
> +void rust_helper_mmap_read_unlock(struct mm_struct *mm)
> +{
> +	mmap_read_unlock(mm);
> +}
> diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
> index bf98caa6d6a5..104e619f5dbd 100644
> --- a/rust/kernel/lib.rs
> +++ b/rust/kernel/lib.rs
> @@ -45,6 +45,7 @@
>  pub mod kunit;
>  pub mod list;
>  pub mod miscdevice;
> +pub mod mm;
>  #[cfg(CONFIG_NET)]
>  pub mod net;
>  pub mod page;
> diff --git a/rust/kernel/mm.rs b/rust/kernel/mm.rs
> new file mode 100644
> index 000000000000..84cba581edaa
> --- /dev/null
> +++ b/rust/kernel/mm.rs
> @@ -0,0 +1,219 @@
> +// SPDX-License-Identifier: GPL-2.0
> +
> +// Copyright (C) 2024 Google LLC.
> +
> +//! Memory management.
> +//!
> +//! C header: [`include/linux/mm.h`](srctree/include/linux/mm.h)
> +
> +use crate::{
> +    bindings,
> +    types::{ARef, AlwaysRefCounted, NotThreadSafe, Opaque},
> +};
> +use core::{ops::Deref, ptr::NonNull};
> +
> +/// A wrapper for the kernel's `struct mm_struct`.
> +///
> +/// Since `mm_users` may be zero, the associated address space may not exist anymore. You can use
> +/// [`mmget_not_zero`] to be able to access the address space.
> +///
> +/// The `ARef<Mm>` smart pointer holds an `mmgrab` refcount. Its destructor may sleep.
> +///
> +/// # Invariants
> +///
> +/// Values of this type are always refcounted using `mmgrab`.
> +///
> +/// [`mmget_not_zero`]: Mm::mmget_not_zero
> +#[repr(transparent)]
> +pub struct Mm {
> +    mm: Opaque<bindings::mm_struct>,
> +}
> +
> +// SAFETY: It is safe to call `mmdrop` on another thread than where `mmgrab` was called.
> +unsafe impl Send for Mm {}
> +// SAFETY: All methods on `Mm` can be called in parallel from several threads.
> +unsafe impl Sync for Mm {}
> +
> +// SAFETY: By the type invariants, this type is always refcounted.
> +unsafe impl AlwaysRefCounted for Mm {
> +    #[inline]
> +    fn inc_ref(&self) {
> +        // SAFETY: The pointer is valid since self is a reference.
> +        unsafe { bindings::mmgrab(self.as_raw()) };
> +    }
> +
> +    #[inline]
> +    unsafe fn dec_ref(obj: NonNull<Self>) {
> +        // SAFETY: The caller is giving up their refcount.
> +        unsafe { bindings::mmdrop(obj.cast().as_ptr()) };
> +    }
> +}
> +
> +/// A wrapper for the kernel's `struct mm_struct`.
> +///
> +/// This type is like [`Mm`], but with non-zero `mm_users`. It can only be used when `mm_users` can
> +/// be proven to be non-zero at compile-time, usually because the relevant code holds an `mmget`
> +/// refcount. It can be used to access the associated address space.
> +///
> +/// The `ARef<MmWithUser>` smart pointer holds an `mmget` refcount. Its destructor may sleep.
> +///
> +/// # Invariants
> +///
> +/// Values of this type are always refcounted using `mmget`. The value of `mm_users` is non-zero.
> +#[repr(transparent)]
> +pub struct MmWithUser {
> +    mm: Mm,
> +}
> +
> +// SAFETY: It is safe to call `mmput` on another thread than where `mmget` was called.
> +unsafe impl Send for MmWithUser {}
> +// SAFETY: All methods on `MmWithUser` can be called in parallel from several threads.
> +unsafe impl Sync for MmWithUser {}
> +
> +// SAFETY: By the type invariants, this type is always refcounted.
> +unsafe impl AlwaysRefCounted for MmWithUser {
> +    #[inline]
> +    fn inc_ref(&self) {
> +        // SAFETY: The pointer is valid since self is a reference.
> +        unsafe { bindings::mmget(self.as_raw()) };
> +    }
> +
> +    #[inline]
> +    unsafe fn dec_ref(obj: NonNull<Self>) {
> +        // SAFETY: The caller is giving up their refcount.
> +        unsafe { bindings::mmput(obj.cast().as_ptr()) };
> +    }
> +}
> +
> +// Make all `Mm` methods available on `MmWithUser`.
> +impl Deref for MmWithUser {
> +    type Target = Mm;
> +
> +    #[inline]
> +    fn deref(&self) -> &Mm {
> +        &self.mm
> +    }
> +}
> +
> +// These methods are safe to call even if `mm_users` is zero.
> +impl Mm {
> +    /// Call `mmgrab` on `current.mm`.
> +    #[inline]
> +    pub fn mmgrab_current() -> Option<ARef<Mm>> {
> +        // SAFETY: It's safe to get the `mm` field from current.
> +        let mm = unsafe {
> +            let current = bindings::get_current();
> +            (*current).mm
> +        };
> +
> +        if mm.is_null() {
> +            return None;
> +        }
> +
> +        // SAFETY: The value of `current->mm` is guaranteed to be null or a valid `mm_struct`. We
> +        // just checked that it's not null. Furthermore, the returned `&Mm` is valid only for the
> +        // duration of this function, and `current->mm` will stay valid for that long.
> +        let mm = unsafe { Mm::from_raw(mm) };
> +
> +        // This increments the refcount using `mmgrab`.
> +        Some(ARef::from(mm))
> +    }
> +
> +    /// Returns a raw pointer to the inner `mm_struct`.
> +    #[inline]
> +    pub fn as_raw(&self) -> *mut bindings::mm_struct {
> +        self.mm.get()
> +    }
> +
> +    /// Obtain a reference from a raw pointer.
> +    ///
> +    /// # Safety
> +    ///
> +    /// The caller must ensure that `ptr` points at an `mm_struct`, and that it is not deallocated
> +    /// during the lifetime 'a.
> +    #[inline]
> +    pub unsafe fn from_raw<'a>(ptr: *const bindings::mm_struct) -> &'a Mm {
> +        // SAFETY: Caller promises that the pointer is valid for 'a. Layouts are compatible due to
> +        // repr(transparent).
> +        unsafe { &*ptr.cast() }
> +    }
> +
> +    /// Calls `mmget_not_zero` and returns a handle if it succeeds.
> +    #[inline]
> +    pub fn mmget_not_zero(&self) -> Option<ARef<MmWithUser>> {
> +        // SAFETY: The pointer is valid since self is a reference.
> +        let success = unsafe { bindings::mmget_not_zero(self.as_raw()) };
> +
> +        if success {
> +            // SAFETY: We just created an `mmget` refcount.
> +            Some(unsafe { ARef::from_raw(NonNull::new_unchecked(self.as_raw().cast())) })
> +        } else {
> +            None
> +        }
> +    }
> +}
> +
> +// These methods require `mm_users` to be non-zero.
> +impl MmWithUser {
> +    /// Obtain a reference from a raw pointer.
> +    ///
> +    /// # Safety
> +    ///
> +    /// The caller must ensure that `ptr` points at an `mm_struct`, and that `mm_users` remains
> +    /// non-zero for the duration of the lifetime 'a.
> +    #[inline]
> +    pub unsafe fn from_raw<'a>(ptr: *const bindings::mm_struct) -> &'a MmWithUser {
> +        // SAFETY: Caller promises that the pointer is valid for 'a. The layout is compatible due
> +        // to repr(transparent).
> +        unsafe { &*ptr.cast() }
> +    }
> +
> +    /// Lock the mmap read lock.
> +    #[inline]
> +    pub fn mmap_read_lock(&self) -> MmapReadGuard<'_> {
> +        // SAFETY: The pointer is valid since self is a reference.
> +        unsafe { bindings::mmap_read_lock(self.as_raw()) };
> +
> +        // INVARIANT: We just acquired the read lock.
> +        MmapReadGuard {
> +            mm: self,
> +            _nts: NotThreadSafe,
> +        }
> +    }
> +
> +    /// Try to lock the mmap read lock.
> +    #[inline]
> +    pub fn mmap_read_trylock(&self) -> Option<MmapReadGuard<'_>> {
> +        // SAFETY: The pointer is valid since self is a reference.
> +        let success = unsafe { bindings::mmap_read_trylock(self.as_raw()) };
> +
> +        if success {
> +            // INVARIANT: We just acquired the read lock.
> +            Some(MmapReadGuard {
> +                mm: self,
> +                _nts: NotThreadSafe,
> +            })
> +        } else {
> +            None
> +        }
> +    }
> +}
> +
> +/// A guard for the mmap read lock.
> +///
> +/// # Invariants
> +///
> +/// This `MmapReadGuard` guard owns the mmap read lock.
> +pub struct MmapReadGuard<'a> {
> +    mm: &'a MmWithUser,
> +    // `mmap_read_lock` and `mmap_read_unlock` must be called on the same thread
> +    _nts: NotThreadSafe,
> +}
> +
> +impl Drop for MmapReadGuard<'_> {
> +    #[inline]
> +    fn drop(&mut self) {
> +        // SAFETY: We hold the read lock by the type invariants.
> +        unsafe { bindings::mmap_read_unlock(self.mm.as_raw()) };
> +    }
> +}
>
> --
> 2.47.0.371.ga323438b13-goog
>

Powered by blists - more mailing lists