Message-ID: <20250704-iov-iter-v2-1-e69aa7c1f40e@google.com>
Date: Fri, 04 Jul 2025 09:26:00 +0000
From: Alice Ryhl <aliceryhl@...gle.com>
To: Greg Kroah-Hartman <gregkh@...uxfoundation.org>, Alexander Viro <viro@...iv.linux.org.uk>, 
	Arnd Bergmann <arnd@...db.de>, Miguel Ojeda <ojeda@...nel.org>
Cc: Boqun Feng <boqun.feng@...il.com>, Gary Guo <gary@...yguo.net>, 
	"Björn Roy Baron" <bjorn3_gh@...tonmail.com>, Andreas Hindborg <a.hindborg@...nel.org>, 
	Trevor Gross <tmgross@...ch.edu>, Danilo Krummrich <dakr@...nel.org>, Matthew Maurer <mmaurer@...gle.com>, 
	Lee Jones <lee@...nel.org>, linux-kernel@...r.kernel.org, 
	rust-for-linux@...r.kernel.org, Alice Ryhl <aliceryhl@...gle.com>, 
	Benno Lossin <lossin@...nel.org>
Subject: [PATCH v2 1/4] rust: iov: add iov_iter abstractions for ITER_SOURCE

This adds abstractions for the iov_iter type in the case where
data_source is ITER_SOURCE. This will make Rust implementations of
fops->write_iter possible.

This series only has support for using existing IO vectors created by C
code. Additional abstractions will be needed to support the creation of
IO vectors in Rust code.

These abstractions make the assumption that `struct iov_iter` does not
have internal self-references, which implies that it is valid to move it
between different local variables.

Signed-off-by: Alice Ryhl <aliceryhl@...gle.com>
---
 rust/kernel/iov.rs | 152 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 rust/kernel/lib.rs |   1 +
 2 files changed, 153 insertions(+)

diff --git a/rust/kernel/iov.rs b/rust/kernel/iov.rs
new file mode 100644
index 0000000000000000000000000000000000000000..b4d7ec14c57a561a01cd65b6bdf0f94b1b373b84
--- /dev/null
+++ b/rust/kernel/iov.rs
@@ -0,0 +1,152 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Copyright (C) 2025 Google LLC.
+
+//! IO vectors.
+//!
+//! C headers: [`include/linux/iov_iter.h`](srctree/include/linux/iov_iter.h),
+//! [`include/linux/uio.h`](srctree/include/linux/uio.h)
+
+use crate::{
+    alloc::{Allocator, Flags},
+    bindings,
+    prelude::*,
+    types::Opaque,
+};
+use core::{marker::PhantomData, mem::MaybeUninit, slice};
+
+const ITER_SOURCE: bool = bindings::ITER_SOURCE != 0;
+
+/// An IO vector that acts as a source of data.
+///
+/// The data may come from many different sources. This includes both things in kernel-space and
+/// reading from userspace. It's not necessarily the case that the data source is immutable, so
+/// rewinding the IO vector to read the same data twice is not guaranteed to result in the same
+/// bytes. It's also possible that the data source is mapped in a thread-local manner using e.g.
+/// `kmap_local_page()`, so this type is not `Send` to ensure that the mapping is read from the
+/// right context in that scenario.
+///
+/// # Invariants
+///
+/// Must hold a valid `struct iov_iter` with `data_source` set to `ITER_SOURCE`. For the duration
+/// of `'data`, it must be safe to read the data in this IO vector.
+#[repr(transparent)]
+pub struct IovIterSource<'data> {
+    iov: Opaque<bindings::iov_iter>,
+    /// Represent to the type system that this value contains a pointer to readable data it does
+    /// not own.
+    _source: PhantomData<&'data [u8]>,
+}
+
+impl<'data> IovIterSource<'data> {
+    /// Obtain an `IovIterSource` from a raw pointer.
+    ///
+    /// # Safety
+    ///
+    /// * For the duration of `'iov`, the `struct iov_iter` must remain valid and must not be
+    ///   accessed except through the returned reference.
+    /// * For the duration of `'data`, the buffers backing this IO vector must be valid for
+    ///   reading.
+    #[track_caller]
+    #[inline]
+    pub unsafe fn from_raw<'iov>(ptr: *mut bindings::iov_iter) -> &'iov mut IovIterSource<'data> {
+        // SAFETY: The caller ensures that `ptr` is valid.
+        let data_source = unsafe { (*ptr).data_source };
+        assert_eq!(data_source, ITER_SOURCE);
+
+        // SAFETY: The caller ensures the struct invariants for the right durations.
+        unsafe { &mut *ptr.cast::<IovIterSource<'data>>() }
+    }
+
+    /// Access this as a raw `struct iov_iter`.
+    #[inline]
+    pub fn as_raw(&mut self) -> *mut bindings::iov_iter {
+        self.iov.get()
+    }
+
+    /// Returns the number of bytes available in this IO vector.
+    ///
+    /// Note that this may overestimate the number of bytes. For example, reading from userspace
+    /// memory could fail with `EFAULT`, which will be treated as the end of the IO vector.
+    #[inline]
+    pub fn len(&self) -> usize {
+        // SAFETY: It is safe to access the `count` field.
+        unsafe {
+            (*self.iov.get())
+                .__bindgen_anon_1
+                .__bindgen_anon_1
+                .as_ref()
+                .count
+        }
+    }
+
+    /// Returns whether there are any bytes left in this IO vector.
+    ///
+    /// This may return `true` even if there are no more bytes available. For example, reading from
+    /// userspace memory could fail with `EFAULT`, which will be treated as the end of the IO vector.
+    #[inline]
+    pub fn is_empty(&self) -> bool {
+        self.len() == 0
+    }
+
+    /// Advance this IO vector by `bytes` bytes.
+    ///
+    /// If `bytes` is larger than the size of this IO vector, it is advanced to the end.
+    #[inline]
+    pub fn advance(&mut self, bytes: usize) {
+        // SAFETY: `self.iov` is a valid IO vector.
+        unsafe { bindings::iov_iter_advance(self.as_raw(), bytes) };
+    }
+
+    /// Advance this IO vector backwards by `bytes` bytes.
+    ///
+    /// # Safety
+    ///
+    /// The IO vector must not be reverted to before its beginning.
+    #[inline]
+    pub unsafe fn revert(&mut self, bytes: usize) {
+        // SAFETY: `self.iov` is a valid IO vector, and `bytes` is in bounds.
+        unsafe { bindings::iov_iter_revert(self.as_raw(), bytes) };
+    }
+
+    /// Read data from this IO vector.
+    ///
+    /// Returns the number of bytes that have been copied.
+    #[inline]
+    pub fn copy_from_iter(&mut self, out: &mut [u8]) -> usize {
+        // SAFETY: We will not write uninitialized bytes to `out`.
+        let out = unsafe { &mut *(out as *mut [u8] as *mut [MaybeUninit<u8>]) };
+
+        self.copy_from_iter_raw(out).len()
+    }
+
+    /// Read data from this IO vector and append it to a vector.
+    ///
+    /// Returns the number of bytes that have been copied.
+    #[inline]
+    pub fn copy_from_iter_vec<A: Allocator>(
+        &mut self,
+        out: &mut Vec<u8, A>,
+        flags: Flags,
+    ) -> Result<usize> {
+        out.reserve(self.len(), flags)?;
+        let len = self.copy_from_iter_raw(out.spare_capacity_mut()).len();
+        // SAFETY: The next `len` bytes of the vector have been initialized.
+        unsafe { out.inc_len(len) };
+        Ok(len)
+    }
+
+    /// Read data from this IO vector into potentially uninitialized memory.
+    ///
+    /// Returns the sub-slice of the output that has been initialized. If the returned slice is
+    /// shorter than the input buffer, then the entire IO vector has been read.
+    #[inline]
+    pub fn copy_from_iter_raw(&mut self, out: &mut [MaybeUninit<u8>]) -> &mut [u8] {
+        // SAFETY: `out` is valid for `out.len()` bytes.
+        let len =
+            unsafe { bindings::_copy_from_iter(out.as_mut_ptr().cast(), out.len(), self.as_raw()) };
+
+        // SAFETY: We just initialized the first `len` bytes of `out`.
+        unsafe { slice::from_raw_parts_mut(out.as_mut_ptr().cast(), len) }
+    }
+}
diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
index 6b4774b2b1c37f4da1866e993be6230bc6715841..278b6fdee62156f4ed997c13fa10bd2fb0fa3ad6 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -81,6 +81,7 @@
 pub mod init;
 pub mod io;
 pub mod ioctl;
+pub mod iov;
 pub mod jump_label;
 #[cfg(CONFIG_KUNIT)]
 pub mod kunit;

-- 
2.50.0.727.gbf7dc18ff4-goog

Powered by blists - more mailing lists