Re: [PATCH v10 2/3] rust: add dma coherent allocator abstraction.

[Alice Ryhl]

On Tue, Jan 21, 2025 at 8:14 PM Abdiel Janulgue
<abdiel.janulgue@xxxxxxxxx> wrote:
>
> Add a simple dma coherent allocator rust abstraction. Based on
> Andreas Hindborg's dma abstractions from the rnvme driver, which
> was also based on earlier work by Wedson Almeida Filho.
>
> Signed-off-by: Abdiel Janulgue <abdiel.janulgue@xxxxxxxxx>
> ---
>  rust/bindings/bindings_helper.h |   1 +
>  rust/kernel/dma.rs              | 281 ++++++++++++++++++++++++++++++++
>  rust/kernel/lib.rs              |   1 +
>  3 files changed, 283 insertions(+)
>  create mode 100644 rust/kernel/dma.rs
>
> diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h
> index 5c4dfe22f41a..49bf713b9bb6 100644
> --- a/rust/bindings/bindings_helper.h
> +++ b/rust/bindings/bindings_helper.h
> @@ -11,6 +11,7 @@
>  #include <linux/blk_types.h>
>  #include <linux/blkdev.h>
>  #include <linux/cred.h>
> +#include <linux/dma-mapping.h>
>  #include <linux/errname.h>
>  #include <linux/ethtool.h>
>  #include <linux/file.h>
> diff --git a/rust/kernel/dma.rs b/rust/kernel/dma.rs
> new file mode 100644
> index 000000000000..ebae7270190e
> --- /dev/null
> +++ b/rust/kernel/dma.rs
> @@ -0,0 +1,281 @@
> +// SPDX-License-Identifier: GPL-2.0
> +
> +//! Direct memory access (DMA).
> +//!
> +//! C header: [`include/linux/dma-mapping.h`](srctree/include/linux/dma-mapping.h)
> +
> +use crate::{
> +    bindings, build_assert,
> +    device::Device,
> +    error::code::*,
> +    error::Result,
> +    transmute::{AsBytes, FromBytes},
> +    types::ARef,
> +};
> +
> +/// Possible attributes associated with a DMA mapping.
> +///
> +/// They can be combined with the operators `|`, `&`, and `!`.
> +///
> +/// Values can be used from the [`attrs`] module.
> +#[derive(Clone, Copy, PartialEq)]
> +#[repr(transparent)]
> +pub struct Attrs(u32);
> +
> +impl Attrs {
> +    /// Get the raw representation of this attribute.
> +    pub(crate) fn as_raw(self) -> crate::ffi::c_ulong {
> +        self.0 as _
> +    }
> +
> +    /// Check whether `flags` is contained in `self`.
> +    pub fn contains(self, flags: Attrs) -> bool {
> +        (self & flags) == flags
> +    }
> +}
> +
> +impl core::ops::BitOr for Attrs {
> +    type Output = Self;
> +    fn bitor(self, rhs: Self) -> Self::Output {
> +        Self(self.0 | rhs.0)
> +    }
> +}
> +
> +impl core::ops::BitAnd for Attrs {
> +    type Output = Self;
> +    fn bitand(self, rhs: Self) -> Self::Output {
> +        Self(self.0 & rhs.0)
> +    }
> +}
> +
> +impl core::ops::Not for Attrs {
> +    type Output = Self;
> +    fn not(self) -> Self::Output {
> +        Self(!self.0)
> +    }
> +}
> +
> +/// DMA mapping attrributes.
> +pub mod attrs {
> +    use super::Attrs;
> +
> +    /// Specifies that reads and writes to the mapping may be weakly ordered, that is that reads
> +    /// and writes may pass each other.
> +    pub const DMA_ATTR_WEAK_ORDERING: Attrs = Attrs(bindings::DMA_ATTR_WEAK_ORDERING);
> +
> +    /// Specifies that writes to the mapping may be buffered to improve performance.
> +    pub const DMA_ATTR_WRITE_COMBINE: Attrs = Attrs(bindings::DMA_ATTR_WRITE_COMBINE);
> +
> +    /// Lets the platform to avoid creating a kernel virtual mapping for the allocated buffer.
> +    pub const DMA_ATTR_NO_KERNEL_MAPPING: Attrs = Attrs(bindings::DMA_ATTR_NO_KERNEL_MAPPING);
> +
> +    /// Allows platform code to skip synchronization of the CPU cache for the given buffer assuming
> +    /// that it has been already transferred to 'device' domain.
> +    pub const DMA_ATTR_SKIP_CPU_SYNC: Attrs = Attrs(bindings::DMA_ATTR_SKIP_CPU_SYNC);
> +
> +    /// Forces contiguous allocation of the buffer in physical memory.
> +    pub const DMA_ATTR_FORCE_CONTIGUOUS: Attrs = Attrs(bindings::DMA_ATTR_FORCE_CONTIGUOUS);
> +
> +    /// This is a hint to the DMA-mapping subsystem that it's probably not worth the time to try
> +    /// to allocate memory to in a way that gives better TLB efficiency.
> +    pub const DMA_ATTR_ALLOC_SINGLE_PAGES: Attrs = Attrs(bindings::DMA_ATTR_ALLOC_SINGLE_PAGES);
> +
> +    /// This tells the DMA-mapping subsystem to suppress allocation failure reports (similarly to
> +    /// __GFP_NOWARN).
> +    pub const DMA_ATTR_NO_WARN: Attrs = Attrs(bindings::DMA_ATTR_NO_WARN);
> +
> +    /// Used to indicate that the buffer is fully accessible at an elevated privilege level (and
> +    /// ideally inaccessible or at least read-only at lesser-privileged levels).
> +    pub const DMA_ATTR_PRIVILEGED: Attrs = Attrs(bindings::DMA_ATTR_PRIVILEGED);
> +}
> +
> +/// An abstraction of the `dma_alloc_coherent` API.
> +///
> +/// This is an abstraction around the `dma_alloc_coherent` API which is used to allocate and map
> +/// large consistent DMA regions.
> +///
> +/// A [`CoherentAllocation`] instance contains a pointer to the allocated region (in the
> +/// processor's virtual address space) and the device address which can be given to the device
> +/// as the DMA address base of the region. The region is released once [`CoherentAllocation`]
> +/// is dropped.
> +///
> +/// # Invariants
> +///
> +/// For the lifetime of an instance of [`CoherentAllocation`], the cpu address is a valid pointer
> +/// to an allocated region of consistent memory and we hold a reference to the device.
> +pub struct CoherentAllocation<T: AsBytes + FromBytes> {
> +    dev: ARef<Device>,
> +    dma_handle: bindings::dma_addr_t,
> +    count: usize,
> +    cpu_addr: *mut T,
> +    dma_attrs: Attrs,
> +}
> +
> +impl<T: AsBytes + FromBytes> CoherentAllocation<T> {
> +    /// Allocates a region of `size_of::<T> * count` of consistent memory.
> +    ///
> +    /// # Examples
> +    ///
> +    /// ```
> +    /// use kernel::device::Device;
> +    /// use kernel::dma::{attrs::*, CoherentAllocation};
> +    ///
> +    /// # fn test(dev: &Device) -> Result {
> +    /// let c: CoherentAllocation<u64> = CoherentAllocation::alloc_attrs(dev.into(), 4, GFP_KERNEL,
> +    ///                                                                  DMA_ATTR_NO_WARN)?;
> +    /// # Ok::<(), Error>(()) }
> +    /// ```
> +    pub fn alloc_attrs(
> +        dev: ARef<Device>,
> +        count: usize,
> +        gfp_flags: kernel::alloc::Flags,
> +        dma_attrs: Attrs,
> +    ) -> Result<CoherentAllocation<T>> {
> +        build_assert!(
> +            core::mem::size_of::<T>() > 0,
> +            "It doesn't make sense for the allocated type to be a ZST"
> +        );
> +
> +        let size = count
> +            .checked_mul(core::mem::size_of::<T>())
> +            .ok_or(EOVERFLOW)?;
> +        let mut dma_handle = 0;
> +        // SAFETY: device pointer is guaranteed as valid by invariant on `Device`.
> +        // We ensure that we catch the failure on this function and throw an ENOMEM
> +        let ret = unsafe {
> +            bindings::dma_alloc_attrs(
> +                dev.as_raw(),
> +                size,
> +                &mut dma_handle,
> +                gfp_flags.as_raw(),
> +                dma_attrs.as_raw(),
> +            )
> +        };
> +        if ret.is_null() {
> +            return Err(ENOMEM);
> +        }
> +        // INVARIANT: We just successfully allocated a coherent region which is accessible for
> +        // `count` elements, hence the cpu address is valid. We also hold a refcounted reference
> +        // to the device.
> +        Ok(Self {
> +            dev,
> +            dma_handle,
> +            count,
> +            cpu_addr: ret as *mut T,
> +            dma_attrs,
> +        })
> +    }
> +
> +    /// Performs the same functionality as `alloc_attrs`, except the `dma_attrs` is 0 by default.
> +    pub fn alloc_coherent(
> +        dev: ARef<Device>,
> +        count: usize,
> +        gfp_flags: kernel::alloc::Flags,
> +    ) -> Result<CoherentAllocation<T>> {
> +        CoherentAllocation::alloc_attrs(dev, count, gfp_flags, Attrs(0))
> +    }
> +
> +    /// Returns the device, base address, dma handle, attributes and the size of the
> +    /// allocated region.
> +    ///
> +    /// The caller takes ownership of the returned resources, i.e., will have the responsibility
> +    /// in calling `bindings::dma_free_attrs`. The allocated region is valid as long as
> +    /// the returned device exists.
> +    pub fn into_parts(
> +        self,
> +    ) -> (
> +        ARef<Device>,
> +        *mut T,
> +        bindings::dma_addr_t,
> +        crate::ffi::c_ulong,
> +        usize,
> +    ) {
> +        let size = self.count * core::mem::size_of::<T>();
> +        let ret = (
> +            self.dev.clone(),

Calling clone here increments the refcount, but you don't want to do
that since it leaks a count.

otherwise lgtm

Alice