diff options
Diffstat (limited to 'rust/kernel/dma.rs')
-rw-r--r-- | rust/kernel/dma.rs | 355 |
1 files changed, 314 insertions, 41 deletions
diff --git a/rust/kernel/dma.rs b/rust/kernel/dma.rs index a33261c62e0c..b320779ea26f 100644 --- a/rust/kernel/dma.rs +++ b/rust/kernel/dma.rs @@ -5,14 +5,156 @@ //! C header: [`include/linux/dma-mapping.h`](srctree/include/linux/dma-mapping.h) use crate::{ - bindings, build_assert, - device::{Bound, Device}, - error::code::*, - error::Result, + bindings, build_assert, device, + device::{Bound, Core}, + error::{to_result, Result}, + prelude::*, transmute::{AsBytes, FromBytes}, types::ARef, }; +/// Trait to be implemented by DMA capable bus devices. +/// +/// The [`dma::Device`](Device) trait should be implemented by bus specific device representations, +/// where the underlying bus is DMA capable, such as [`pci::Device`](::kernel::pci::Device) or +/// [`platform::Device`](::kernel::platform::Device). +pub trait Device: AsRef<device::Device<Core>> { + /// Set up the device's DMA streaming addressing capabilities. + /// + /// This method is usually called once from `probe()` as soon as the device capabilities are + /// known. + /// + /// # Safety + /// + /// This method must not be called concurrently with any DMA allocation or mapping primitives, + /// such as [`CoherentAllocation::alloc_attrs`]. + unsafe fn dma_set_mask(&self, mask: DmaMask) -> Result { + // SAFETY: + // - By the type invariant of `device::Device`, `self.as_ref().as_raw()` is valid. + // - The safety requirement of this function guarantees that there are no concurrent calls + // to DMA allocation and mapping primitives using this mask. + to_result(unsafe { bindings::dma_set_mask(self.as_ref().as_raw(), mask.value()) }) + } + + /// Set up the device's DMA coherent addressing capabilities. + /// + /// This method is usually called once from `probe()` as soon as the device capabilities are + /// known. + /// + /// # Safety + /// + /// This method must not be called concurrently with any DMA allocation or mapping primitives, + /// such as [`CoherentAllocation::alloc_attrs`]. + unsafe fn dma_set_coherent_mask(&self, mask: DmaMask) -> Result { + // SAFETY: + // - By the type invariant of `device::Device`, `self.as_ref().as_raw()` is valid. + // - The safety requirement of this function guarantees that there are no concurrent calls + // to DMA allocation and mapping primitives using this mask. + to_result(unsafe { bindings::dma_set_coherent_mask(self.as_ref().as_raw(), mask.value()) }) + } + + /// Set up the device's DMA addressing capabilities. + /// + /// This is a combination of [`Device::dma_set_mask`] and [`Device::dma_set_coherent_mask`]. + /// + /// This method is usually called once from `probe()` as soon as the device capabilities are + /// known. + /// + /// # Safety + /// + /// This method must not be called concurrently with any DMA allocation or mapping primitives, + /// such as [`CoherentAllocation::alloc_attrs`]. + unsafe fn dma_set_mask_and_coherent(&self, mask: DmaMask) -> Result { + // SAFETY: + // - By the type invariant of `device::Device`, `self.as_ref().as_raw()` is valid. + // - The safety requirement of this function guarantees that there are no concurrent calls + // to DMA allocation and mapping primitives using this mask. + to_result(unsafe { + bindings::dma_set_mask_and_coherent(self.as_ref().as_raw(), mask.value()) + }) + } +} + +/// A DMA mask that holds a bitmask with the lowest `n` bits set. +/// +/// Use [`DmaMask::new`] or [`DmaMask::try_new`] to construct a value. Values +/// are guaranteed to never exceed the bit width of `u64`. +/// +/// This is the Rust equivalent of the C macro `DMA_BIT_MASK()`. +#[derive(Debug, Clone, Copy, PartialEq, Eq)] +pub struct DmaMask(u64); + +impl DmaMask { + /// Constructs a `DmaMask` with the lowest `n` bits set to `1`. + /// + /// For `n <= 64`, sets exactly the lowest `n` bits. + /// For `n > 64`, results in a build error. + /// + /// # Examples + /// + /// ``` + /// use kernel::dma::DmaMask; + /// + /// let mask0 = DmaMask::new::<0>(); + /// assert_eq!(mask0.value(), 0); + /// + /// let mask1 = DmaMask::new::<1>(); + /// assert_eq!(mask1.value(), 0b1); + /// + /// let mask64 = DmaMask::new::<64>(); + /// assert_eq!(mask64.value(), u64::MAX); + /// + /// // Build failure. + /// // let mask_overflow = DmaMask::new::<100>(); + /// ``` + #[inline] + pub const fn new<const N: u32>() -> Self { + let Ok(mask) = Self::try_new(N) else { + build_error!("Invalid DMA Mask."); + }; + + mask + } + + /// Constructs a `DmaMask` with the lowest `n` bits set to `1`. + /// + /// For `n <= 64`, sets exactly the lowest `n` bits. + /// For `n > 64`, returns [`EINVAL`]. + /// + /// # Examples + /// + /// ``` + /// use kernel::dma::DmaMask; + /// + /// let mask0 = DmaMask::try_new(0)?; + /// assert_eq!(mask0.value(), 0); + /// + /// let mask1 = DmaMask::try_new(1)?; + /// assert_eq!(mask1.value(), 0b1); + /// + /// let mask64 = DmaMask::try_new(64)?; + /// assert_eq!(mask64.value(), u64::MAX); + /// + /// let mask_overflow = DmaMask::try_new(100); + /// assert!(mask_overflow.is_err()); + /// # Ok::<(), Error>(()) + /// ``` + #[inline] + pub const fn try_new(n: u32) -> Result<Self> { + Ok(Self(match n { + 0 => 0, + 1..=64 => u64::MAX >> (64 - n), + _ => return Err(EINVAL), + })) + } + + /// Returns the underlying `u64` bitmask value. + #[inline] + pub const fn value(&self) -> u64 { + self.0 + } +} + /// Possible attributes associated with a DMA mapping. /// /// They can be combined with the operators `|`, `&`, and `!`. @@ -89,7 +231,7 @@ pub mod attrs { /// 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 + /// Hints 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); @@ -97,7 +239,7 @@ pub mod attrs { /// `__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 + /// Indicates 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); } @@ -105,7 +247,7 @@ pub mod attrs { /// 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. +/// large coherent 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 @@ -114,9 +256,11 @@ pub mod attrs { /// /// # Invariants /// -/// For the lifetime of an instance of [`CoherentAllocation`], the `cpu_addr` is a valid pointer -/// to an allocated region of consistent memory and `dma_handle` is the DMA address base of -/// the region. +/// - For the lifetime of an instance of [`CoherentAllocation`], the `cpu_addr` is a valid pointer +/// to an allocated region of coherent memory and `dma_handle` is the DMA address base of the +/// region. +/// - The size in bytes of the allocation is equal to `size_of::<T> * count`. +/// - `size_of::<T> * count` fits into a `usize`. // TODO // // DMA allocations potentially carry device resources (e.g.IOMMU mappings), hence for soundness @@ -130,7 +274,7 @@ pub mod attrs { // Hence, find a way to revoke the device resources of a `CoherentAllocation`, but not the // entire `CoherentAllocation` including the allocated memory itself. pub struct CoherentAllocation<T: AsBytes + FromBytes> { - dev: ARef<Device>, + dev: ARef<device::Device>, dma_handle: bindings::dma_addr_t, count: usize, cpu_addr: *mut T, @@ -138,7 +282,7 @@ pub struct CoherentAllocation<T: AsBytes + FromBytes> { } impl<T: AsBytes + FromBytes> CoherentAllocation<T> { - /// Allocates a region of `size_of::<T> * count` of consistent memory. + /// Allocates a region of `size_of::<T> * count` of coherent memory. /// /// # Examples /// @@ -152,7 +296,7 @@ impl<T: AsBytes + FromBytes> CoherentAllocation<T> { /// # Ok::<(), Error>(()) } /// ``` pub fn alloc_attrs( - dev: &Device<Bound>, + dev: &device::Device<Bound>, count: usize, gfp_flags: kernel::alloc::Flags, dma_attrs: Attrs, @@ -179,9 +323,12 @@ impl<T: AsBytes + FromBytes> CoherentAllocation<T> { 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. + // 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. + // - The allocated `size` is equal to `size_of::<T> * count`. + // - The allocated `size` fits into a `usize`. Ok(Self { dev: dev.into(), dma_handle, @@ -194,13 +341,28 @@ impl<T: AsBytes + FromBytes> CoherentAllocation<T> { /// Performs the same functionality as [`CoherentAllocation::alloc_attrs`], except the /// `dma_attrs` is 0 by default. pub fn alloc_coherent( - dev: &Device<Bound>, + dev: &device::Device<Bound>, count: usize, gfp_flags: kernel::alloc::Flags, ) -> Result<CoherentAllocation<T>> { CoherentAllocation::alloc_attrs(dev, count, gfp_flags, Attrs(0)) } + /// Returns the number of elements `T` in this allocation. + /// + /// Note that this is not the size of the allocation in bytes, which is provided by + /// [`Self::size`]. + pub fn count(&self) -> usize { + self.count + } + + /// Returns the size in bytes of this allocation. + pub fn size(&self) -> usize { + // INVARIANT: The type invariant of `Self` guarantees that `size_of::<T> * count` fits into + // a `usize`. + self.count * core::mem::size_of::<T>() + } + /// Returns the base address to the allocated region in the CPU's virtual address space. pub fn start_ptr(&self) -> *const T { self.cpu_addr @@ -212,12 +374,113 @@ impl<T: AsBytes + FromBytes> CoherentAllocation<T> { self.cpu_addr } - /// Returns a DMA handle which may given to the device as the DMA address base of + /// Returns a DMA handle which may be given to the device as the DMA address base of /// the region. pub fn dma_handle(&self) -> bindings::dma_addr_t { self.dma_handle } + /// Returns a DMA handle starting at `offset` (in units of `T`) which may be given to the + /// device as the DMA address base of the region. + /// + /// Returns `EINVAL` if `offset` is not within the bounds of the allocation. + pub fn dma_handle_with_offset(&self, offset: usize) -> Result<bindings::dma_addr_t> { + if offset >= self.count { + Err(EINVAL) + } else { + // INVARIANT: The type invariant of `Self` guarantees that `size_of::<T> * count` fits + // into a `usize`, and `offset` is inferior to `count`. + Ok(self.dma_handle + (offset * core::mem::size_of::<T>()) as bindings::dma_addr_t) + } + } + + /// Common helper to validate a range applied from the allocated region in the CPU's virtual + /// address space. + fn validate_range(&self, offset: usize, count: usize) -> Result { + if offset.checked_add(count).ok_or(EOVERFLOW)? > self.count { + return Err(EINVAL); + } + Ok(()) + } + + /// Returns the data from the region starting from `offset` as a slice. + /// `offset` and `count` are in units of `T`, not the number of bytes. + /// + /// For ringbuffer type of r/w access or use-cases where the pointer to the live data is needed, + /// [`CoherentAllocation::start_ptr`] or [`CoherentAllocation::start_ptr_mut`] could be used + /// instead. + /// + /// # Safety + /// + /// * Callers must ensure that the device does not read/write to/from memory while the returned + /// slice is live. + /// * Callers must ensure that this call does not race with a write to the same region while + /// the returned slice is live. + pub unsafe fn as_slice(&self, offset: usize, count: usize) -> Result<&[T]> { + self.validate_range(offset, count)?; + // SAFETY: + // - The pointer is valid due to type invariant on `CoherentAllocation`, + // we've just checked that the range and index is within bounds. The immutability of the + // data is also guaranteed by the safety requirements of the function. + // - `offset + count` can't overflow since it is smaller than `self.count` and we've checked + // that `self.count` won't overflow early in the constructor. + Ok(unsafe { core::slice::from_raw_parts(self.cpu_addr.add(offset), count) }) + } + + /// Performs the same functionality as [`CoherentAllocation::as_slice`], except that a mutable + /// slice is returned. + /// + /// # Safety + /// + /// * Callers must ensure that the device does not read/write to/from memory while the returned + /// slice is live. + /// * Callers must ensure that this call does not race with a read or write to the same region + /// while the returned slice is live. + pub unsafe fn as_slice_mut(&self, offset: usize, count: usize) -> Result<&mut [T]> { + self.validate_range(offset, count)?; + // SAFETY: + // - The pointer is valid due to type invariant on `CoherentAllocation`, + // we've just checked that the range and index is within bounds. The immutability of the + // data is also guaranteed by the safety requirements of the function. + // - `offset + count` can't overflow since it is smaller than `self.count` and we've checked + // that `self.count` won't overflow early in the constructor. + Ok(unsafe { core::slice::from_raw_parts_mut(self.cpu_addr.add(offset), count) }) + } + + /// Writes data to the region starting from `offset`. `offset` is in units of `T`, not the + /// number of bytes. + /// + /// # Safety + /// + /// * Callers must ensure that the device does not read/write to/from memory while the returned + /// slice is live. + /// * Callers must ensure that this call does not race with a read or write to the same region + /// that overlaps with this write. + /// + /// # Examples + /// + /// ``` + /// # fn test(alloc: &mut kernel::dma::CoherentAllocation<u8>) -> Result { + /// let somedata: [u8; 4] = [0xf; 4]; + /// let buf: &[u8] = &somedata; + /// // SAFETY: There is no concurrent HW operation on the device and no other R/W access to the + /// // region. + /// unsafe { alloc.write(buf, 0)?; } + /// # Ok::<(), Error>(()) } + /// ``` + pub unsafe fn write(&self, src: &[T], offset: usize) -> Result { + self.validate_range(offset, src.len())?; + // SAFETY: + // - The pointer is valid due to type invariant on `CoherentAllocation` + // and we've just checked that the range and index is within bounds. + // - `offset + count` can't overflow since it is smaller than `self.count` and we've checked + // that `self.count` won't overflow early in the constructor. + unsafe { + core::ptr::copy_nonoverlapping(src.as_ptr(), self.cpu_addr.add(offset), src.len()) + }; + Ok(()) + } + /// Returns a pointer to an element from the region with bounds checking. `offset` is in /// units of `T`, not the number of bytes. /// @@ -328,20 +591,24 @@ unsafe impl<T: AsBytes + FromBytes + Send> Send for CoherentAllocation<T> {} #[macro_export] macro_rules! dma_read { ($dma:expr, $idx: expr, $($field:tt)*) => {{ - let item = $crate::dma::CoherentAllocation::item_from_index(&$dma, $idx)?; - // SAFETY: `item_from_index` ensures that `item` is always a valid pointer and can be - // dereferenced. The compiler also further validates the expression on whether `field` - // is a member of `item` when expanded by the macro. - unsafe { - let ptr_field = ::core::ptr::addr_of!((*item) $($field)*); - $crate::dma::CoherentAllocation::field_read(&$dma, ptr_field) - } + (|| -> ::core::result::Result<_, $crate::error::Error> { + let item = $crate::dma::CoherentAllocation::item_from_index(&$dma, $idx)?; + // SAFETY: `item_from_index` ensures that `item` is always a valid pointer and can be + // dereferenced. The compiler also further validates the expression on whether `field` + // is a member of `item` when expanded by the macro. + unsafe { + let ptr_field = ::core::ptr::addr_of!((*item) $($field)*); + ::core::result::Result::Ok( + $crate::dma::CoherentAllocation::field_read(&$dma, ptr_field) + ) + } + })() }}; ($dma:ident [ $idx:expr ] $($field:tt)* ) => { - $crate::dma_read!($dma, $idx, $($field)*); + $crate::dma_read!($dma, $idx, $($field)*) }; ($($dma:ident).* [ $idx:expr ] $($field:tt)* ) => { - $crate::dma_read!($($dma).*, $idx, $($field)*); + $crate::dma_read!($($dma).*, $idx, $($field)*) }; } @@ -368,24 +635,30 @@ macro_rules! dma_read { #[macro_export] macro_rules! dma_write { ($dma:ident [ $idx:expr ] $($field:tt)*) => {{ - $crate::dma_write!($dma, $idx, $($field)*); + $crate::dma_write!($dma, $idx, $($field)*) }}; ($($dma:ident).* [ $idx:expr ] $($field:tt)* ) => {{ - $crate::dma_write!($($dma).*, $idx, $($field)*); + $crate::dma_write!($($dma).*, $idx, $($field)*) }}; ($dma:expr, $idx: expr, = $val:expr) => { - let item = $crate::dma::CoherentAllocation::item_from_index(&$dma, $idx)?; - // SAFETY: `item_from_index` ensures that `item` is always a valid item. - unsafe { $crate::dma::CoherentAllocation::field_write(&$dma, item, $val) } + (|| -> ::core::result::Result<_, $crate::error::Error> { + let item = $crate::dma::CoherentAllocation::item_from_index(&$dma, $idx)?; + // SAFETY: `item_from_index` ensures that `item` is always a valid item. + unsafe { $crate::dma::CoherentAllocation::field_write(&$dma, item, $val) } + ::core::result::Result::Ok(()) + })() }; ($dma:expr, $idx: expr, $(.$field:ident)* = $val:expr) => { - let item = $crate::dma::CoherentAllocation::item_from_index(&$dma, $idx)?; - // SAFETY: `item_from_index` ensures that `item` is always a valid pointer and can be - // dereferenced. The compiler also further validates the expression on whether `field` - // is a member of `item` when expanded by the macro. - unsafe { - let ptr_field = ::core::ptr::addr_of_mut!((*item) $(.$field)*); - $crate::dma::CoherentAllocation::field_write(&$dma, ptr_field, $val) - } + (|| -> ::core::result::Result<_, $crate::error::Error> { + let item = $crate::dma::CoherentAllocation::item_from_index(&$dma, $idx)?; + // SAFETY: `item_from_index` ensures that `item` is always a valid pointer and can be + // dereferenced. The compiler also further validates the expression on whether `field` + // is a member of `item` when expanded by the macro. + unsafe { + let ptr_field = ::core::ptr::addr_of_mut!((*item) $(.$field)*); + $crate::dma::CoherentAllocation::field_write(&$dma, ptr_field, $val) + } + ::core::result::Result::Ok(()) + })() }; } |