Merge tag 'drm-rust-next-2026-03-30' of https://gitlab.freedesktop.org/drm/rust/kernel into drm-next

DRM Rust changes for v7.1-rc1

- DMA:
  - Rework the DMA coherent API: introduce Coherent<T> as a generalized
    container for arbitrary types, replacing the slice-only
    CoherentAllocation<T>. Add CoherentBox for memory initialization
    before exposing a buffer to hardware (converting to Coherent when
    ready), and CoherentHandle for allocations without kernel mapping.

  - Add Coherent::init() / init_with_attrs() for one-shot initialization
    via pin-init, and from-slice constructors for both Coherent and
    CoherentBox

  - Add uaccess write_dma() for copying from DMA buffers to userspace
    and BinaryWriter support for Coherent<T>

- DRM:
  - Add GPU buddy allocator abstraction

  - Add DRM shmem GEM helper abstraction

  - Allow drm::Device to dispatch work and delayed work items to driver
    private data

  - Add impl_aref_for_gem_obj!() macro to reduce GEM refcount
    boilerplate, and introduce DriverObject::Args for constructor
    context

  - Add dma_resv_lock helper and raw_dma_resv() accessor on GEM objects

  - Clean up imports across the DRM module

- I/O:
  - Merged via a signed tag from the driver-core tree: register!() macro
    and I/O infrastructure improvements (IoCapable refactor, RelaxedMmio
    wrapper, IoLoc trait, generic accessors, write_reg /
    LocatedRegister)

- Nova (Core):
  - Fix and harden the GSP command queue: correct write pointer
    advancing, empty slot handling, and ring buffer indexing; add mutex
    locking and make Cmdq a pinned type; distinguish wait vs no-wait
    commands

  - Add support for large RPCs via continuation records, splitting
    oversized commands across multiple queue slots

  - Simplify GSP sequencer and message handling code: remove unused
    trait and Display impls, derive Debug and Zeroable where applicable,
    warn on unconsumed message data

  - Refactor Falcon firmware handling: create DMA objects lazily, add
    PIO upload support, and use the Generic Bootloader to boot FWSEC on
    Turing

  - Convert all register definitions (PMC, PBUS, PFB, GC6, FUSE, PDISP,
    Falcon) to the kernel register!() macro; add bounded_enum macro to
    define enums usable as register fields

  - Migrate all DMA usage to the new Coherent, CoherentBox, and
    CoherentHandle APIs

  - Harden firmware parsing with checked arithmetic throughout FWSEC,
    Booter, RISC-V parsing paths

  - Add debugfs support for reading GSP-RM log buffers; replace
    module_pci_driver!() with explicit module init to support
    module-level debugfs setup

  - Fix auxiliary device registration for multi-GPU systems

  - Various cleanups: import style, firmware parsing refactoring,
    framebuffer size logging

- Rust:
  - Add interop::list module providing a C linked list interface

  - Extend num::Bounded with shift operations, into_bool(), and const
    get() to support register bitfield manipulation

  - Enable the generic_arg_infer Rust feature and add EMSGSIZE error
    code

- Tyr:
  - Adopt vertical import style per kernel Rust guidelines

  - Clarify driver/device type names and use DRM device type alias
    consistently across the driver

  - Fix GPU model/version decoding in GpuInfo

- Workqueue:
  - Add ARef<T> support for work and delayed work

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: "Danilo Krummrich" <dakr@kernel.org>
Link: https://patch.msgid.link/DHGH4BLT03BU.ZJH5U52WE8BY@kernel.org

1 files changed, 490 insertions, 290 deletions

diff --git a/rust/kernel/io.rs b/rust/kernel/io.rs
index e5fba6bf6db0..fcc7678fd9e3 100644
--- a/rust/kernel/io.rs
+++ b/rust/kernel/io.rs
@@ -11,10 +11,14 @@ use crate::{
 
 pub mod mem;
 pub mod poll;
+pub mod register;
 pub mod resource;
 
+pub use crate::register;
 pub use resource::Resource;
 
+use register::LocatedRegister;
+
 /// Physical address type.
 ///
 /// This is a type alias to either `u32` or `u64` depending on the config option
@@ -137,177 +141,6 @@ impl<const SIZE: usize> MmioRaw<SIZE> {
 #[repr(transparent)]
 pub struct Mmio<const SIZE: usize = 0>(MmioRaw<SIZE>);
 
-/// Internal helper macros used to invoke C MMIO read functions.
-///
-/// This macro is intended to be used by higher-level MMIO access macros (io_define_read) and
-/// provides a unified expansion for infallible vs. fallible read semantics. It emits a direct call
-/// into the corresponding C helper and performs the required cast to the Rust return type.
-///
-/// # Parameters
-///
-/// * `$c_fn` – The C function performing the MMIO read.
-/// * `$self` – The I/O backend object.
-/// * `$ty` – The type of the value to be read.
-/// * `$addr` – The MMIO address to read.
-///
-/// This macro does not perform any validation; all invariants must be upheld by the higher-level
-/// abstraction invoking it.
-macro_rules! call_mmio_read {
-    (infallible, $c_fn:ident, $self:ident, $type:ty, $addr:expr) => {
-        // SAFETY: By the type invariant `addr` is a valid address for MMIO operations.
-        unsafe { bindings::$c_fn($addr as *const c_void) as $type }
-    };
-
-    (fallible, $c_fn:ident, $self:ident, $type:ty, $addr:expr) => {{
-        // SAFETY: By the type invariant `addr` is a valid address for MMIO operations.
-        Ok(unsafe { bindings::$c_fn($addr as *const c_void) as $type })
-    }};
-}
-
-/// Internal helper macros used to invoke C MMIO write functions.
-///
-/// This macro is intended to be used by higher-level MMIO access macros (io_define_write) and
-/// provides a unified expansion for infallible vs. fallible write semantics. It emits a direct call
-/// into the corresponding C helper and performs the required cast to the Rust return type.
-///
-/// # Parameters
-///
-/// * `$c_fn` – The C function performing the MMIO write.
-/// * `$self` – The I/O backend object.
-/// * `$ty` – The type of the written value.
-/// * `$addr` – The MMIO address to write.
-/// * `$value` – The value to write.
-///
-/// This macro does not perform any validation; all invariants must be upheld by the higher-level
-/// abstraction invoking it.
-macro_rules! call_mmio_write {
-    (infallible, $c_fn:ident, $self:ident, $ty:ty, $addr:expr, $value:expr) => {
-        // SAFETY: By the type invariant `addr` is a valid address for MMIO operations.
-        unsafe { bindings::$c_fn($value, $addr as *mut c_void) }
-    };
-
-    (fallible, $c_fn:ident, $self:ident, $ty:ty, $addr:expr, $value:expr) => {{
-        // SAFETY: By the type invariant `addr` is a valid address for MMIO operations.
-        unsafe { bindings::$c_fn($value, $addr as *mut c_void) };
-        Ok(())
-    }};
-}
-
-/// Generates an accessor method for reading from an I/O backend.
-///
-/// This macro reduces boilerplate by automatically generating either compile-time bounds-checked
-/// (infallible) or runtime bounds-checked (fallible) read methods. It abstracts the address
-/// calculation and bounds checking, and delegates the actual I/O read operation to a specified
-/// helper macro, making it generic over different I/O backends.
-///
-/// # Parameters
-///
-/// * `infallible` / `fallible` - Determines the bounds-checking strategy. `infallible` relies on
-///   `IoKnownSize` for compile-time checks and returns the value directly. `fallible` performs
-///   runtime checks against `maxsize()` and returns a `Result<T>`.
-/// * `$(#[$attr:meta])*` - Optional attributes to apply to the generated method (e.g.,
-///   `#[cfg(CONFIG_64BIT)]` or inline directives).
-/// * `$vis:vis` - The visibility of the generated method (e.g., `pub`).
-/// * `$name:ident` / `$try_name:ident` - The name of the generated method (e.g., `read32`,
-///   `try_read8`).
-/// * `$call_macro:ident` - The backend-specific helper macro used to emit the actual I/O call
-///   (e.g., `call_mmio_read`).
-/// * `$c_fn:ident` - The backend-specific C function or identifier to be passed into the
-///   `$call_macro`.
-/// * `$type_name:ty` - The Rust type of the value being read (e.g., `u8`, `u32`).
-#[macro_export]
-macro_rules! io_define_read {
-    (infallible, $(#[$attr:meta])* $vis:vis $name:ident, $call_macro:ident($c_fn:ident) ->
-     $type_name:ty) => {
-        /// Read IO data from a given offset known at compile time.
-        ///
-        /// Bound checks are performed on compile time, hence if the offset is not known at compile
-        /// time, the build will fail.
-        $(#[$attr])*
-        // Always inline to optimize out error path of `io_addr_assert`.
-        #[inline(always)]
-        $vis fn $name(&self, offset: usize) -> $type_name {
-            let addr = self.io_addr_assert::<$type_name>(offset);
-
-            // SAFETY: By the type invariant `addr` is a valid address for IO operations.
-            $call_macro!(infallible, $c_fn, self, $type_name, addr)
-        }
-    };
-
-    (fallible, $(#[$attr:meta])* $vis:vis $try_name:ident, $call_macro:ident($c_fn:ident) ->
-     $type_name:ty) => {
-        /// Read IO data from a given offset.
-        ///
-        /// Bound checks are performed on runtime, it fails if the offset (plus the type size) is
-        /// out of bounds.
-        $(#[$attr])*
-        $vis fn $try_name(&self, offset: usize) -> Result<$type_name> {
-            let addr = self.io_addr::<$type_name>(offset)?;
-
-            // SAFETY: By the type invariant `addr` is a valid address for IO operations.
-            $call_macro!(fallible, $c_fn, self, $type_name, addr)
-        }
-    };
-}
-pub use io_define_read;
-
-/// Generates an accessor method for writing to an I/O backend.
-///
-/// This macro reduces boilerplate by automatically generating either compile-time bounds-checked
-/// (infallible) or runtime bounds-checked (fallible) write methods. It abstracts the address
-/// calculation and bounds checking, and delegates the actual I/O write operation to a specified
-/// helper macro, making it generic over different I/O backends.
-///
-/// # Parameters
-///
-/// * `infallible` / `fallible` - Determines the bounds-checking strategy. `infallible` relies on
-///   `IoKnownSize` for compile-time checks and returns `()`. `fallible` performs runtime checks
-///   against `maxsize()` and returns a `Result`.
-/// * `$(#[$attr:meta])*` - Optional attributes to apply to the generated method (e.g.,
-///   `#[cfg(CONFIG_64BIT)]` or inline directives).
-/// * `$vis:vis` - The visibility of the generated method (e.g., `pub`).
-/// * `$name:ident` / `$try_name:ident` - The name of the generated method (e.g., `write32`,
-///   `try_write8`).
-/// * `$call_macro:ident` - The backend-specific helper macro used to emit the actual I/O call
-///   (e.g., `call_mmio_write`).
-/// * `$c_fn:ident` - The backend-specific C function or identifier to be passed into the
-///   `$call_macro`.
-/// * `$type_name:ty` - The Rust type of the value being written (e.g., `u8`, `u32`). Note the use
-///   of `<-` before the type to denote a write operation.
-#[macro_export]
-macro_rules! io_define_write {
-    (infallible, $(#[$attr:meta])* $vis:vis $name:ident, $call_macro:ident($c_fn:ident) <-
-     $type_name:ty) => {
-        /// Write IO data from a given offset known at compile time.
-        ///
-        /// Bound checks are performed on compile time, hence if the offset is not known at compile
-        /// time, the build will fail.
-        $(#[$attr])*
-        // Always inline to optimize out error path of `io_addr_assert`.
-        #[inline(always)]
-        $vis fn $name(&self, value: $type_name, offset: usize) {
-            let addr = self.io_addr_assert::<$type_name>(offset);
-
-            $call_macro!(infallible, $c_fn, self, $type_name, addr, value);
-        }
-    };
-
-    (fallible, $(#[$attr:meta])* $vis:vis $try_name:ident, $call_macro:ident($c_fn:ident) <-
-     $type_name:ty) => {
-        /// Write IO data from a given offset.
-        ///
-        /// Bound checks are performed on runtime, it fails if the offset (plus the type size) is
-        /// out of bounds.
-        $(#[$attr])*
-        $vis fn $try_name(&self, value: $type_name, offset: usize) -> Result {
-            let addr = self.io_addr::<$type_name>(offset)?;
-
-            $call_macro!(fallible, $c_fn, self, $type_name, addr, value)
-        }
-    };
-}
-pub use io_define_write;
-
 /// Checks whether an access of type `U` at the given `offset`
 /// is valid within this region.
 #[inline]
@@ -320,14 +153,74 @@ const fn offset_valid<U>(offset: usize, size: usize) -> bool {
     }
 }
 
-/// Marker trait indicating that an I/O backend supports operations of a certain type.
+/// Trait indicating that an I/O backend supports operations of a certain type and providing an
+/// implementation for these operations.
 ///
 /// Different I/O backends can implement this trait to expose only the operations they support.
 ///
 /// For example, a PCI configuration space may implement `IoCapable<u8>`, `IoCapable<u16>`,
 /// and `IoCapable<u32>`, but not `IoCapable<u64>`, while an MMIO region on a 64-bit
 /// system might implement all four.
-pub trait IoCapable<T> {}
+pub trait IoCapable<T> {
+    /// Performs an I/O read of type `T` at `address` and returns the result.
+    ///
+    /// # Safety
+    ///
+    /// The range `[address..address + size_of::<T>()]` must be within the bounds of `Self`.
+    unsafe fn io_read(&self, address: usize) -> T;
+
+    /// Performs an I/O write of `value` at `address`.
+    ///
+    /// # Safety
+    ///
+    /// The range `[address..address + size_of::<T>()]` must be within the bounds of `Self`.
+    unsafe fn io_write(&self, value: T, address: usize);
+}
+
+/// Describes a given I/O location: its offset, width, and type to convert the raw value from and
+/// into.
+///
+/// This trait is the key abstraction allowing [`Io::read`], [`Io::write`], and [`Io::update`] (and
+/// their fallible [`try_read`](Io::try_read), [`try_write`](Io::try_write) and
+/// [`try_update`](Io::try_update) counterparts) to work uniformly with both raw [`usize`] offsets
+/// (for primitive types like [`u32`]) and typed ones (like those generated by the [`register!`]
+/// macro).
+///
+/// An `IoLoc<T>` carries three pieces of information:
+///
+/// - The offset to access (returned by [`IoLoc::offset`]),
+/// - The width of the access (determined by [`IoLoc::IoType`]),
+/// - The type `T` in which the raw data is returned or provided.
+///
+/// `T` and `IoLoc::IoType` may differ: for instance, a typed register has `T` = the register type
+/// with its bitfields, and `IoType` = its backing primitive (e.g. `u32`).
+pub trait IoLoc<T> {
+    /// Size ([`u8`], [`u16`], etc) of the I/O performed on the returned [`offset`](IoLoc::offset).
+    type IoType: Into<T> + From<T>;
+
+    /// Consumes `self` and returns the offset of this location.
+    fn offset(self) -> usize;
+}
+
+/// Implements [`IoLoc<$ty>`] for [`usize`], allowing [`usize`] to be used as a parameter of
+/// [`Io::read`] and [`Io::write`].
+macro_rules! impl_usize_ioloc {
+    ($($ty:ty),*) => {
+        $(
+            impl IoLoc<$ty> for usize {
+                type IoType = $ty;
+
+                #[inline(always)]
+                fn offset(self) -> usize {
+                    self
+                }
+            }
+        )*
+    }
+}
+
+// Provide the ability to read any primitive type from a [`usize`].
+impl_usize_ioloc!(u8, u16, u32, u64);
 
 /// Types implementing this trait (e.g. MMIO BARs or PCI config regions)
 /// can perform I/O operations on regions of memory.
@@ -369,146 +262,445 @@ pub trait Io {
 
     /// Fallible 8-bit read with runtime bounds check.
     #[inline(always)]
-    fn try_read8(&self, _offset: usize) -> Result<u8>
+    fn try_read8(&self, offset: usize) -> Result<u8>
     where
         Self: IoCapable<u8>,
     {
-        build_error!("Backend does not support fallible 8-bit read")
+        self.try_read(offset)
     }
 
     /// Fallible 16-bit read with runtime bounds check.
     #[inline(always)]
-    fn try_read16(&self, _offset: usize) -> Result<u16>
+    fn try_read16(&self, offset: usize) -> Result<u16>
     where
         Self: IoCapable<u16>,
     {
-        build_error!("Backend does not support fallible 16-bit read")
+        self.try_read(offset)
     }
 
     /// Fallible 32-bit read with runtime bounds check.
     #[inline(always)]
-    fn try_read32(&self, _offset: usize) -> Result<u32>
+    fn try_read32(&self, offset: usize) -> Result<u32>
     where
         Self: IoCapable<u32>,
     {
-        build_error!("Backend does not support fallible 32-bit read")
+        self.try_read(offset)
     }
 
     /// Fallible 64-bit read with runtime bounds check.
     #[inline(always)]
-    fn try_read64(&self, _offset: usize) -> Result<u64>
+    fn try_read64(&self, offset: usize) -> Result<u64>
     where
         Self: IoCapable<u64>,
     {
-        build_error!("Backend does not support fallible 64-bit read")
+        self.try_read(offset)
     }
 
     /// Fallible 8-bit write with runtime bounds check.
     #[inline(always)]
-    fn try_write8(&self, _value: u8, _offset: usize) -> Result
+    fn try_write8(&self, value: u8, offset: usize) -> Result
     where
         Self: IoCapable<u8>,
     {
-        build_error!("Backend does not support fallible 8-bit write")
+        self.try_write(offset, value)
     }
 
     /// Fallible 16-bit write with runtime bounds check.
     #[inline(always)]
-    fn try_write16(&self, _value: u16, _offset: usize) -> Result
+    fn try_write16(&self, value: u16, offset: usize) -> Result
     where
         Self: IoCapable<u16>,
     {
-        build_error!("Backend does not support fallible 16-bit write")
+        self.try_write(offset, value)
     }
 
     /// Fallible 32-bit write with runtime bounds check.
     #[inline(always)]
-    fn try_write32(&self, _value: u32, _offset: usize) -> Result
+    fn try_write32(&self, value: u32, offset: usize) -> Result
     where
         Self: IoCapable<u32>,
     {
-        build_error!("Backend does not support fallible 32-bit write")
+        self.try_write(offset, value)
     }
 
     /// Fallible 64-bit write with runtime bounds check.
     #[inline(always)]
-    fn try_write64(&self, _value: u64, _offset: usize) -> Result
+    fn try_write64(&self, value: u64, offset: usize) -> Result
     where
         Self: IoCapable<u64>,
     {
-        build_error!("Backend does not support fallible 64-bit write")
+        self.try_write(offset, value)
     }
 
     /// Infallible 8-bit read with compile-time bounds check.
     #[inline(always)]
-    fn read8(&self, _offset: usize) -> u8
+    fn read8(&self, offset: usize) -> u8
     where
         Self: IoKnownSize + IoCapable<u8>,
     {
-        build_error!("Backend does not support infallible 8-bit read")
+        self.read(offset)
     }
 
     /// Infallible 16-bit read with compile-time bounds check.
     #[inline(always)]
-    fn read16(&self, _offset: usize) -> u16
+    fn read16(&self, offset: usize) -> u16
     where
         Self: IoKnownSize + IoCapable<u16>,
     {
-        build_error!("Backend does not support infallible 16-bit read")
+        self.read(offset)
     }
 
     /// Infallible 32-bit read with compile-time bounds check.
     #[inline(always)]
-    fn read32(&self, _offset: usize) -> u32
+    fn read32(&self, offset: usize) -> u32
     where
         Self: IoKnownSize + IoCapable<u32>,
     {
-        build_error!("Backend does not support infallible 32-bit read")
+        self.read(offset)
     }
 
     /// Infallible 64-bit read with compile-time bounds check.
     #[inline(always)]
-    fn read64(&self, _offset: usize) -> u64
+    fn read64(&self, offset: usize) -> u64
     where
         Self: IoKnownSize + IoCapable<u64>,
     {
-        build_error!("Backend does not support infallible 64-bit read")
+        self.read(offset)
     }
 
     /// Infallible 8-bit write with compile-time bounds check.
     #[inline(always)]
-    fn write8(&self, _value: u8, _offset: usize)
+    fn write8(&self, value: u8, offset: usize)
     where
         Self: IoKnownSize + IoCapable<u8>,
     {
-        build_error!("Backend does not support infallible 8-bit write")
+        self.write(offset, value)
     }
 
     /// Infallible 16-bit write with compile-time bounds check.
     #[inline(always)]
-    fn write16(&self, _value: u16, _offset: usize)
+    fn write16(&self, value: u16, offset: usize)
     where
         Self: IoKnownSize + IoCapable<u16>,
     {
-        build_error!("Backend does not support infallible 16-bit write")
+        self.write(offset, value)
     }
 
     /// Infallible 32-bit write with compile-time bounds check.
     #[inline(always)]
-    fn write32(&self, _value: u32, _offset: usize)
+    fn write32(&self, value: u32, offset: usize)
     where
         Self: IoKnownSize + IoCapable<u32>,
     {
-        build_error!("Backend does not support infallible 32-bit write")
+        self.write(offset, value)
     }
 
     /// Infallible 64-bit write with compile-time bounds check.
     #[inline(always)]
-    fn write64(&self, _value: u64, _offset: usize)
+    fn write64(&self, value: u64, offset: usize)
     where
         Self: IoKnownSize + IoCapable<u64>,
     {
-        build_error!("Backend does not support infallible 64-bit write")
+        self.write(offset, value)
+    }
+
+    /// Generic fallible read with runtime bounds check.
+    ///
+    /// # Examples
+    ///
+    /// Read a primitive type from an I/O address:
+    ///
+    /// ```no_run
+    /// use kernel::io::{
+    ///     Io,
+    ///     Mmio,
+    /// };
+    ///
+    /// fn do_reads(io: &Mmio) -> Result {
+    ///     // 32-bit read from address `0x10`.
+    ///     let v: u32 = io.try_read(0x10)?;
+    ///
+    ///     // 8-bit read from address `0xfff`.
+    ///     let v: u8 = io.try_read(0xfff)?;
+    ///
+    ///     Ok(())
+    /// }
+    /// ```
+    #[inline(always)]
+    fn try_read<T, L>(&self, location: L) -> Result<T>
+    where
+        L: IoLoc<T>,
+        Self: IoCapable<L::IoType>,
+    {
+        let address = self.io_addr::<L::IoType>(location.offset())?;
+
+        // SAFETY: `address` has been validated by `io_addr`.
+        Ok(unsafe { self.io_read(address) }.into())
+    }
+
+    /// Generic fallible write with runtime bounds check.
+    ///
+    /// # Examples
+    ///
+    /// Write a primitive type to an I/O address:
+    ///
+    /// ```no_run
+    /// use kernel::io::{
+    ///     Io,
+    ///     Mmio,
+    /// };
+    ///
+    /// fn do_writes(io: &Mmio) -> Result {
+    ///     // 32-bit write of value `1` at address `0x10`.
+    ///     io.try_write(0x10, 1u32)?;
+    ///
+    ///     // 8-bit write of value `0xff` at address `0xfff`.
+    ///     io.try_write(0xfff, 0xffu8)?;
+    ///
+    ///     Ok(())
+    /// }
+    /// ```
+    #[inline(always)]
+    fn try_write<T, L>(&self, location: L, value: T) -> Result
+    where
+        L: IoLoc<T>,
+        Self: IoCapable<L::IoType>,
+    {
+        let address = self.io_addr::<L::IoType>(location.offset())?;
+        let io_value = value.into();
+
+        // SAFETY: `address` has been validated by `io_addr`.
+        unsafe { self.io_write(io_value, address) }
+
+        Ok(())
+    }
+
+    /// Generic fallible write of a fully-located register value.
+    ///
+    /// # Examples
+    ///
+    /// Tuples carrying a location and a value can be used with this method:
+    ///
+    /// ```no_run
+    /// use kernel::io::{
+    ///     register,
+    ///     Io,
+    ///     Mmio,
+    /// };
+    ///
+    /// register! {
+    ///     VERSION(u32) @ 0x100 {
+    ///         15:8 major;
+    ///         7:0  minor;
+    ///     }
+    /// }
+    ///
+    /// impl VERSION {
+    ///     fn new(major: u8, minor: u8) -> Self {
+    ///         VERSION::zeroed().with_major(major).with_minor(minor)
+    ///     }
+    /// }
+    ///
+    /// fn do_write_reg(io: &Mmio) -> Result {
+    ///
+    ///     io.try_write_reg(VERSION::new(1, 0))
+    /// }
+    /// ```
+    #[inline(always)]
+    fn try_write_reg<T, L, V>(&self, value: V) -> Result
+    where
+        L: IoLoc<T>,
+        V: LocatedRegister<Location = L, Value = T>,
+        Self: IoCapable<L::IoType>,
+    {
+        let (location, value) = value.into_io_op();
+
+        self.try_write(location, value)
+    }
+
+    /// Generic fallible update with runtime bounds check.
+    ///
+    /// Note: this does not perform any synchronization. The caller is responsible for ensuring
+    /// exclusive access if required.
+    ///
+    /// # Examples
+    ///
+    /// Read the u32 value at address `0x10`, increment it, and store the updated value back:
+    ///
+    /// ```no_run
+    /// use kernel::io::{
+    ///     Io,
+    ///     Mmio,
+    /// };
+    ///
+    /// fn do_update(io: &Mmio<0x1000>) -> Result {
+    ///     io.try_update(0x10, |v: u32| {
+    ///         v + 1
+    ///     })
+    /// }
+    /// ```
+    #[inline(always)]
+    fn try_update<T, L, F>(&self, location: L, f: F) -> Result
+    where
+        L: IoLoc<T>,
+        Self: IoCapable<L::IoType>,
+        F: FnOnce(T) -> T,
+    {
+        let address = self.io_addr::<L::IoType>(location.offset())?;
+
+        // SAFETY: `address` has been validated by `io_addr`.
+        let value: T = unsafe { self.io_read(address) }.into();
+        let io_value = f(value).into();
+
+        // SAFETY: `address` has been validated by `io_addr`.
+        unsafe { self.io_write(io_value, address) }
+
+        Ok(())
+    }
+
+    /// Generic infallible read with compile-time bounds check.
+    ///
+    /// # Examples
+    ///
+    /// Read a primitive type from an I/O address:
+    ///
+    /// ```no_run
+    /// use kernel::io::{
+    ///     Io,
+    ///     Mmio,
+    /// };
+    ///
+    /// fn do_reads(io: &Mmio<0x1000>) {
+    ///     // 32-bit read from address `0x10`.
+    ///     let v: u32 = io.read(0x10);
+    ///
+    ///     // 8-bit read from the top of the I/O space.
+    ///     let v: u8 = io.read(0xfff);
+    /// }
+    /// ```
+    #[inline(always)]
+    fn read<T, L>(&self, location: L) -> T
+    where
+        L: IoLoc<T>,
+        Self: IoKnownSize + IoCapable<L::IoType>,
+    {
+        let address = self.io_addr_assert::<L::IoType>(location.offset());
+
+        // SAFETY: `address` has been validated by `io_addr_assert`.
+        unsafe { self.io_read(address) }.into()
+    }
+
+    /// Generic infallible write with compile-time bounds check.
+    ///
+    /// # Examples
+    ///
+    /// Write a primitive type to an I/O address:
+    ///
+    /// ```no_run
+    /// use kernel::io::{
+    ///     Io,
+    ///     Mmio,
+    /// };
+    ///
+    /// fn do_writes(io: &Mmio<0x1000>) {
+    ///     // 32-bit write of value `1` at address `0x10`.
+    ///     io.write(0x10, 1u32);
+    ///
+    ///     // 8-bit write of value `0xff` at the top of the I/O space.
+    ///     io.write(0xfff, 0xffu8);
+    /// }
+    /// ```
+    #[inline(always)]
+    fn write<T, L>(&self, location: L, value: T)
+    where
+        L: IoLoc<T>,
+        Self: IoKnownSize + IoCapable<L::IoType>,
+    {
+        let address = self.io_addr_assert::<L::IoType>(location.offset());
+        let io_value = value.into();
+
+        // SAFETY: `address` has been validated by `io_addr_assert`.
+        unsafe { self.io_write(io_value, address) }
+    }
+
+    /// Generic infallible write of a fully-located register value.
+    ///
+    /// # Examples
+    ///
+    /// Tuples carrying a location and a value can be used with this method:
+    ///
+    /// ```no_run
+    /// use kernel::io::{
+    ///     register,
+    ///     Io,
+    ///     Mmio,
+    /// };
+    ///
+    /// register! {
+    ///     VERSION(u32) @ 0x100 {
+    ///         15:8 major;
+    ///         7:0  minor;
+    ///     }
+    /// }
+    ///
+    /// impl VERSION {
+    ///     fn new(major: u8, minor: u8) -> Self {
+    ///         VERSION::zeroed().with_major(major).with_minor(minor)
+    ///     }
+    /// }
+    ///
+    /// fn do_write_reg(io: &Mmio<0x1000>) {
+    ///     io.write_reg(VERSION::new(1, 0));
+    /// }
+    /// ```
+    #[inline(always)]
+    fn write_reg<T, L, V>(&self, value: V)
+    where
+        L: IoLoc<T>,
+        V: LocatedRegister<Location = L, Value = T>,
+        Self: IoKnownSize + IoCapable<L::IoType>,
+    {
+        let (location, value) = value.into_io_op();
+
+        self.write(location, value)
+    }
+
+    /// Generic infallible update with compile-time bounds check.
+    ///
+    /// Note: this does not perform any synchronization. The caller is responsible for ensuring
+    /// exclusive access if required.
+    ///
+    /// # Examples
+    ///
+    /// Read the u32 value at address `0x10`, increment it, and store the updated value back:
+    ///
+    /// ```no_run
+    /// use kernel::io::{
+    ///     Io,
+    ///     Mmio,
+    /// };
+    ///
+    /// fn do_update(io: &Mmio<0x1000>) {
+    ///     io.update(0x10, |v: u32| {
+    ///         v + 1
+    ///     })
+    /// }
+    /// ```
+    #[inline(always)]
+    fn update<T, L, F>(&self, location: L, f: F)
+    where
+        L: IoLoc<T>,
+        Self: IoKnownSize + IoCapable<L::IoType> + Sized,
+        F: FnOnce(T) -> T,
+    {
+        let address = self.io_addr_assert::<L::IoType>(location.offset());
+
+        // SAFETY: `address` has been validated by `io_addr_assert`.
+        let value: T = unsafe { self.io_read(address) }.into();
+        let io_value = f(value).into();
+
+        // SAFETY: `address` has been validated by `io_addr_assert`.
+        unsafe { self.io_write(io_value, address) }
     }
 }
 
@@ -534,14 +726,36 @@ pub trait IoKnownSize: Io {
     }
 }
 
-// MMIO regions support 8, 16, and 32-bit accesses.
-impl<const SIZE: usize> IoCapable<u8> for Mmio<SIZE> {}
-impl<const SIZE: usize> IoCapable<u16> for Mmio<SIZE> {}
-impl<const SIZE: usize> IoCapable<u32> for Mmio<SIZE> {}
+/// Implements [`IoCapable`] on `$mmio` for `$ty` using `$read_fn` and `$write_fn`.
+macro_rules! impl_mmio_io_capable {
+    ($mmio:ident, $(#[$attr:meta])* $ty:ty, $read_fn:ident, $write_fn:ident) => {
+        $(#[$attr])*
+        impl<const SIZE: usize> IoCapable<$ty> for $mmio<SIZE> {
+            unsafe fn io_read(&self, address: usize) -> $ty {
+                // SAFETY: By the trait invariant `address` is a valid address for MMIO operations.
+                unsafe { bindings::$read_fn(address as *const c_void) }
+            }
+
+            unsafe fn io_write(&self, value: $ty, address: usize) {
+                // SAFETY: By the trait invariant `address` is a valid address for MMIO operations.
+                unsafe { bindings::$write_fn(value, address as *mut c_void) }
+            }
+        }
+    };
+}
 
+// MMIO regions support 8, 16, and 32-bit accesses.
+impl_mmio_io_capable!(Mmio, u8, readb, writeb);
+impl_mmio_io_capable!(Mmio, u16, readw, writew);
+impl_mmio_io_capable!(Mmio, u32, readl, writel);
 // MMIO regions on 64-bit systems also support 64-bit accesses.
-#[cfg(CONFIG_64BIT)]
-impl<const SIZE: usize> IoCapable<u64> for Mmio<SIZE> {}
+impl_mmio_io_capable!(
+    Mmio,
+    #[cfg(CONFIG_64BIT)]
+    u64,
+    readq,
+    writeq
+);
 
 impl<const SIZE: usize> Io for Mmio<SIZE> {
     /// Returns the base address of this mapping.
@@ -555,46 +769,6 @@ impl<const SIZE: usize> Io for Mmio<SIZE> {
     fn maxsize(&self) -> usize {
         self.0.maxsize()
     }
-
-    io_define_read!(fallible, try_read8, call_mmio_read(readb) -> u8);
-    io_define_read!(fallible, try_read16, call_mmio_read(readw) -> u16);
-    io_define_read!(fallible, try_read32, call_mmio_read(readl) -> u32);
-    io_define_read!(
-        fallible,
-        #[cfg(CONFIG_64BIT)]
-        try_read64,
-        call_mmio_read(readq) -> u64
-    );
-
-    io_define_write!(fallible, try_write8, call_mmio_write(writeb) <- u8);
-    io_define_write!(fallible, try_write16, call_mmio_write(writew) <- u16);
-    io_define_write!(fallible, try_write32, call_mmio_write(writel) <- u32);
-    io_define_write!(
-        fallible,
-        #[cfg(CONFIG_64BIT)]
-        try_write64,
-        call_mmio_write(writeq) <- u64
-    );
-
-    io_define_read!(infallible, read8, call_mmio_read(readb) -> u8);
-    io_define_read!(infallible, read16, call_mmio_read(readw) -> u16);
-    io_define_read!(infallible, read32, call_mmio_read(readl) -> u32);
-    io_define_read!(
-        infallible,
-        #[cfg(CONFIG_64BIT)]
-        read64,
-        call_mmio_read(readq) -> u64
-    );
-
-    io_define_write!(infallible, write8, call_mmio_write(writeb) <- u8);
-    io_define_write!(infallible, write16, call_mmio_write(writew) <- u16);
-    io_define_write!(infallible, write32, call_mmio_write(writel) <- u32);
-    io_define_write!(
-        infallible,
-        #[cfg(CONFIG_64BIT)]
-        write64,
-        call_mmio_write(writeq) <- u64
-    );
 }
 
 impl<const SIZE: usize> IoKnownSize for Mmio<SIZE> {
@@ -612,44 +786,70 @@ impl<const SIZE: usize> Mmio<SIZE> {
         // SAFETY: `Mmio` is a transparent wrapper around `MmioRaw`.
         unsafe { &*core::ptr::from_ref(raw).cast() }
     }
+}
+
+/// [`Mmio`] wrapper using relaxed accessors.
+///
+/// This type provides an implementation of [`Io`] that uses relaxed I/O MMIO operands instead of
+/// the regular ones.
+///
+/// See [`Mmio::relaxed`] for a usage example.
+#[repr(transparent)]
+pub struct RelaxedMmio<const SIZE: usize = 0>(Mmio<SIZE>);
+
+impl<const SIZE: usize> Io for RelaxedMmio<SIZE> {
+    #[inline]
+    fn addr(&self) -> usize {
+        self.0.addr()
+    }
 
-    io_define_read!(infallible, pub read8_relaxed, call_mmio_read(readb_relaxed) -> u8);
-    io_define_read!(infallible, pub read16_relaxed, call_mmio_read(readw_relaxed) -> u16);
-    io_define_read!(infallible, pub read32_relaxed, call_mmio_read(readl_relaxed) -> u32);
-    io_define_read!(
-        infallible,
-        #[cfg(CONFIG_64BIT)]
-        pub read64_relaxed,
-        call_mmio_read(readq_relaxed) -> u64
-    );
-
-    io_define_read!(fallible, pub try_read8_relaxed, call_mmio_read(readb_relaxed) -> u8);
-    io_define_read!(fallible, pub try_read16_relaxed, call_mmio_read(readw_relaxed) -> u16);
-    io_define_read!(fallible, pub try_read32_relaxed, call_mmio_read(readl_relaxed) -> u32);
-    io_define_read!(
-        fallible,
-        #[cfg(CONFIG_64BIT)]
-        pub try_read64_relaxed,
-        call_mmio_read(readq_relaxed) -> u64
-    );
-
-    io_define_write!(infallible, pub write8_relaxed, call_mmio_write(writeb_relaxed) <- u8);
-    io_define_write!(infallible, pub write16_relaxed, call_mmio_write(writew_relaxed) <- u16);
-    io_define_write!(infallible, pub write32_relaxed, call_mmio_write(writel_relaxed) <- u32);
-    io_define_write!(
-        infallible,
-        #[cfg(CONFIG_64BIT)]
-        pub write64_relaxed,
-        call_mmio_write(writeq_relaxed) <- u64
-    );
-
-    io_define_write!(fallible, pub try_write8_relaxed, call_mmio_write(writeb_relaxed) <- u8);
-    io_define_write!(fallible, pub try_write16_relaxed, call_mmio_write(writew_relaxed) <- u16);
-    io_define_write!(fallible, pub try_write32_relaxed, call_mmio_write(writel_relaxed) <- u32);
-    io_define_write!(
-        fallible,
-        #[cfg(CONFIG_64BIT)]
-        pub try_write64_relaxed,
-        call_mmio_write(writeq_relaxed) <- u64
-    );
+    #[inline]
+    fn maxsize(&self) -> usize {
+        self.0.maxsize()
+    }
+}
+
+impl<const SIZE: usize> IoKnownSize for RelaxedMmio<SIZE> {
+    const MIN_SIZE: usize = SIZE;
 }
+
+impl<const SIZE: usize> Mmio<SIZE> {
+    /// Returns a [`RelaxedMmio`] reference that performs relaxed I/O operations.
+    ///
+    /// Relaxed accessors do not provide ordering guarantees with respect to DMA or memory accesses
+    /// and can be used when such ordering is not required.
+    ///
+    /// # Examples
+    ///
+    /// ```no_run
+    /// use kernel::io::{
+    ///     Io,
+    ///     Mmio,
+    ///     RelaxedMmio,
+    /// };
+    ///
+    /// fn do_io(io: &Mmio<0x100>) {
+    ///     // The access is performed using `readl_relaxed` instead of `readl`.
+    ///     let v = io.relaxed().read32(0x10);
+    /// }
+    ///
+    /// ```
+    pub fn relaxed(&self) -> &RelaxedMmio<SIZE> {
+        // SAFETY: `RelaxedMmio` is `#[repr(transparent)]` over `Mmio`, so `Mmio<SIZE>` and
+        // `RelaxedMmio<SIZE>` have identical layout.
+        unsafe { core::mem::transmute(self) }
+    }
+}
+
+// MMIO regions support 8, 16, and 32-bit accesses.
+impl_mmio_io_capable!(RelaxedMmio, u8, readb_relaxed, writeb_relaxed);
+impl_mmio_io_capable!(RelaxedMmio, u16, readw_relaxed, writew_relaxed);
+impl_mmio_io_capable!(RelaxedMmio, u32, readl_relaxed, writel_relaxed);
+// MMIO regions on 64-bit systems also support 64-bit accesses.
+impl_mmio_io_capable!(
+    RelaxedMmio,
+    #[cfg(CONFIG_64BIT)]
+    u64,
+    readq_relaxed,
+    writeq_relaxed
+);