This patchset contains some abstractions needed by the Rust
implementation of the Binder driver for passing data between userspace,
kernelspace, and directly into other processes.
These abstractions do not exactly match what was included in the Rust
Binder RFC - I have made various improvements and simplifications since
then. Nonetheless, please see the Rust Binder RFC [1] to get an
understanding for how this will be used:
Users of "rust: add userspace pointers"
and "rust: add typed accessors for userspace pointers":
rust_binder: add binderfs support to Rust binder
rust_binder: add threading support
rust_binder: add nodes and context managers
rust_binder: add oneway transactions
rust_binder: add death notifications
rust_binder: send nodes in transactions
rust_binder: add BINDER_TYPE_PTR support
rust_binder: add BINDER_TYPE_FDA support
rust_binder: add process freezing
Users of "rust: add abstraction for `struct page`":
rust_binder: add oneway transactions
rust_binder: add vma shrinker
Especially the second patch with typed accessors needs review. It
contains a Rust analogy for when the C-side skips `check_object_size`,
and I would be very happy to receive feedback about whether I am going
about this in a reasonable way.
Links: https://lore.kernel.org/rust-for-linux/[email protected]/ [1]
Signed-off-by: Alice Ryhl <[email protected]>
---
Changes in v2:
- Rename user_ptr module to uaccess.
- Use srctree-relative links.
- Improve documentation.
- Rename UserSlicePtr to UserSlice.
- Make read_to_end append to the buffer.
- Use named fields for uaccess types.
- Add examples.
- Use _copy_from/to_user to skip check_object_size.
- Rename traits and move to kernel::types.
- Remove PAGE_MASK constant.
- Rename page methods to say _raw.
- Link to v1: https://lore.kernel.org/r/[email protected]
---
Alice Ryhl (2):
rust: uaccess: add typed accessors for userspace pointers
rust: add abstraction for `struct page`
Arnd Bergmann (1):
uaccess: always export _copy_[from|to]_user with CONFIG_RUST
Wedson Almeida Filho (1):
rust: uaccess: add userspace pointers
include/linux/uaccess.h | 37 ++--
lib/usercopy.c | 30 +---
rust/bindings/bindings_helper.h | 1 +
rust/helpers.c | 34 ++++
rust/kernel/lib.rs | 2 +
rust/kernel/page.rs | 209 ++++++++++++++++++++++
rust/kernel/types.rs | 67 +++++++
rust/kernel/uaccess.rs | 387 ++++++++++++++++++++++++++++++++++++++++
8 files changed, 727 insertions(+), 40 deletions(-)
---
base-commit: f090f0d0eea9666a96702b29bc9a64cbabee85c5
change-id: 20231128-alice-mm-bc533456cee8
Best regards,
--
Alice Ryhl <[email protected]>
From: Arnd Bergmann <[email protected]>
Rust code needs to be able to access _copy_from_user and _copy_to_user
so that it can skip the check_copy_size check in cases where the length
is known at compile-time, mirroring the logic for when C code will skip
check_copy_size. To do this, we ensure that exported versions of these
methods are available when CONFIG_RUST is enabled.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Alice Ryhl <[email protected]>
---
include/linux/uaccess.h | 37 +++++++++++++++++++++++--------------
lib/usercopy.c | 30 ++++--------------------------
2 files changed, 27 insertions(+), 40 deletions(-)
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 3064314f4832..835aa175d0ee 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -138,13 +138,18 @@ __copy_to_user(void __user *to, const void *from, unsigned long n)
return raw_copy_to_user(to, from, n);
}
-#ifdef INLINE_COPY_FROM_USER
static inline __must_check unsigned long
-_copy_from_user(void *to, const void __user *from, unsigned long n)
+_inline_copy_from_user(void *to, const void __user *from, unsigned long n)
{
unsigned long res = n;
might_fault();
if (!should_fail_usercopy() && likely(access_ok(from, n))) {
+ /*
+ * Ensure that bad access_ok() speculation will not
+ * lead to nasty side effects *after* the copy is
+ * finished:
+ */
+ barrier_nospec();
instrument_copy_from_user_before(to, from, n);
res = raw_copy_from_user(to, from, n);
instrument_copy_from_user_after(to, from, n, res);
@@ -153,14 +158,11 @@ _copy_from_user(void *to, const void __user *from, unsigned long n)
memset(to + (n - res), 0, res);
return res;
}
-#else
extern __must_check unsigned long
_copy_from_user(void *, const void __user *, unsigned long);
-#endif
-#ifdef INLINE_COPY_TO_USER
static inline __must_check unsigned long
-_copy_to_user(void __user *to, const void *from, unsigned long n)
+_inline_copy_to_user(void __user *to, const void *from, unsigned long n)
{
might_fault();
if (should_fail_usercopy())
@@ -171,25 +173,32 @@ _copy_to_user(void __user *to, const void *from, unsigned long n)
}
return n;
}
-#else
extern __must_check unsigned long
_copy_to_user(void __user *, const void *, unsigned long);
-#endif
static __always_inline unsigned long __must_check
copy_from_user(void *to, const void __user *from, unsigned long n)
{
- if (check_copy_size(to, n, false))
- n = _copy_from_user(to, from, n);
- return n;
+ if (!check_copy_size(to, n, false))
+ return n;
+#ifdef INLINE_COPY_FROM_USER
+ return _inline_copy_from_user(to, from, n);
+#else
+ return _copy_from_user(to, from, n);
+#endif
}
static __always_inline unsigned long __must_check
copy_to_user(void __user *to, const void *from, unsigned long n)
{
- if (check_copy_size(from, n, true))
- n = _copy_to_user(to, from, n);
- return n;
+ if (!check_copy_size(from, n, true))
+ return n;
+
+#ifdef INLINE_COPY_TO_USER
+ return _inline_copy_to_user(to, from, n);
+#else
+ return _copy_to_user(to, from, n);
+#endif
}
#ifndef copy_mc_to_kernel
diff --git a/lib/usercopy.c b/lib/usercopy.c
index d29fe29c6849..de7f30618293 100644
--- a/lib/usercopy.c
+++ b/lib/usercopy.c
@@ -7,40 +7,18 @@
/* out-of-line parts */
-#ifndef INLINE_COPY_FROM_USER
+#if !defined(INLINE_COPY_FROM_USER) || defined(CONFIG_RUST)
unsigned long _copy_from_user(void *to, const void __user *from, unsigned long n)
{
- unsigned long res = n;
- might_fault();
- if (!should_fail_usercopy() && likely(access_ok(from, n))) {
- /*
- * Ensure that bad access_ok() speculation will not
- * lead to nasty side effects *after* the copy is
- * finished:
- */
- barrier_nospec();
- instrument_copy_from_user_before(to, from, n);
- res = raw_copy_from_user(to, from, n);
- instrument_copy_from_user_after(to, from, n, res);
- }
- if (unlikely(res))
- memset(to + (n - res), 0, res);
- return res;
+ return _inline_copy_from_user(to, from, n);
}
EXPORT_SYMBOL(_copy_from_user);
#endif
-#ifndef INLINE_COPY_TO_USER
+#if !defined(INLINE_COPY_TO_USER) || defined(CONFIG_RUST)
unsigned long _copy_to_user(void __user *to, const void *from, unsigned long n)
{
- might_fault();
- if (should_fail_usercopy())
- return n;
- if (likely(access_ok(to, n))) {
- instrument_copy_to_user(to, from, n);
- n = raw_copy_to_user(to, from, n);
- }
- return n;
+ return _inline_copy_to_user(to, from, n);
}
EXPORT_SYMBOL(_copy_to_user);
#endif
--
2.43.0.594.gd9cf4e227d-goog
Adds a new struct called `Page` that wraps a pointer to `struct page`.
This struct is assumed to hold ownership over the page, so that Rust
code can allocate and manage pages directly.
The page type has various methods for reading and writing into the page.
These methods will temporarily map the page to allow the operation. All
of these methods use a helper that takes an offset and length, performs
bounds checks, and returns a pointer to the given offset in the page.
This patch only adds support for pages of order zero, as that is all
Rust Binder needs. However, it is written to make it easy to add support
for higher-order pages in the future. To do that, you would add a const
generic parameter to `Page` that specifies the order. Most of the
methods do not need to be adjusted, as the logic for dealing with
mapping multiple pages at once can be isolated to just the
`with_pointer_into_page` method. Finally, the struct can be renamed to
`Pages<ORDER>`, and the type alias `Page = Pages<0>` can be introduced.
Rust Binder needs to manage pages directly as that is how transactions
are delivered: Each process has an mmap'd region for incoming
transactions. When an incoming transaction arrives, the Binder driver
will choose a region in the mmap, allocate and map the relevant pages
manually, and copy the incoming transaction directly into the page. This
architecture allows the driver to copy transactions directly from the
address space of one process to another, without an intermediate copy
to a kernel buffer.
This code is based on Wedson's page abstractions from the old rust
branch, but it has been modified by Alice by removing the incomplete
support for higher-order pages, and by introducing the `with_*` helpers
to consolidate the bounds checking logic into a single place.
Co-developed-by: Wedson Almeida Filho <[email protected]>
Signed-off-by: Wedson Almeida Filho <[email protected]>
Signed-off-by: Alice Ryhl <[email protected]>
---
rust/bindings/bindings_helper.h | 1 +
rust/helpers.c | 20 ++++
rust/kernel/lib.rs | 1 +
rust/kernel/page.rs | 209 ++++++++++++++++++++++++++++++++++++++++
4 files changed, 231 insertions(+)
diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h
index 936651110c39..b5b7fa7bd456 100644
--- a/rust/bindings/bindings_helper.h
+++ b/rust/bindings/bindings_helper.h
@@ -22,3 +22,4 @@
const size_t RUST_CONST_HELPER_ARCH_SLAB_MINALIGN = ARCH_SLAB_MINALIGN;
const gfp_t RUST_CONST_HELPER_GFP_KERNEL = GFP_KERNEL;
const gfp_t RUST_CONST_HELPER___GFP_ZERO = __GFP_ZERO;
+const gfp_t RUST_CONST_HELPER___GFP_HIGHMEM = ___GFP_HIGHMEM;
diff --git a/rust/helpers.c b/rust/helpers.c
index 312b6fcb49d5..298d2ee16e61 100644
--- a/rust/helpers.c
+++ b/rust/helpers.c
@@ -25,6 +25,8 @@
#include <linux/build_bug.h>
#include <linux/err.h>
#include <linux/errname.h>
+#include <linux/gfp.h>
+#include <linux/highmem.h>
#include <linux/mutex.h>
#include <linux/refcount.h>
#include <linux/sched/signal.h>
@@ -93,6 +95,24 @@ int rust_helper_signal_pending(struct task_struct *t)
}
EXPORT_SYMBOL_GPL(rust_helper_signal_pending);
+struct page *rust_helper_alloc_pages(gfp_t gfp_mask, unsigned int order)
+{
+ return alloc_pages(gfp_mask, order);
+}
+EXPORT_SYMBOL_GPL(rust_helper_alloc_pages);
+
+void *rust_helper_kmap_local_page(struct page *page)
+{
+ return kmap_local_page(page);
+}
+EXPORT_SYMBOL_GPL(rust_helper_kmap_local_page);
+
+void rust_helper_kunmap_local(const void *addr)
+{
+ kunmap_local(addr);
+}
+EXPORT_SYMBOL_GPL(rust_helper_kunmap_local);
+
refcount_t rust_helper_REFCOUNT_INIT(int n)
{
return (refcount_t)REFCOUNT_INIT(n);
diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
index 5a03aafcbb69..59ee6dd6f7c6 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -40,6 +40,7 @@
pub mod kunit;
#[cfg(CONFIG_NET)]
pub mod net;
+pub mod page;
pub mod prelude;
pub mod print;
mod static_assert;
diff --git a/rust/kernel/page.rs b/rust/kernel/page.rs
new file mode 100644
index 000000000000..ac253744f94b
--- /dev/null
+++ b/rust/kernel/page.rs
@@ -0,0 +1,209 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Kernel page allocation and management.
+
+use crate::{bindings, error::code::*, error::Result, uaccess::UserSliceReader};
+use core::{
+ alloc::AllocError,
+ ptr::{self, NonNull},
+};
+
+/// A bitwise shift for the page size.
+pub const PAGE_SHIFT: usize = bindings::PAGE_SHIFT as usize;
+/// The number of bytes in a page.
+pub const PAGE_SIZE: usize = 1 << PAGE_SHIFT;
+
+/// A pointer to a page that owns the page allocation.
+///
+/// # Invariants
+///
+/// The pointer points at a page, and has ownership over the page.
+pub struct Page {
+ page: NonNull<bindings::page>,
+}
+
+// SAFETY: It is safe to transfer page allocations between threads.
+unsafe impl Send for Page {}
+
+// SAFETY: As long as the safety requirements for `&self` methods on this type
+// are followed, there is no problem with calling them in parallel.
+unsafe impl Sync for Page {}
+
+impl Page {
+ /// Allocates a new page.
+ pub fn new() -> Result<Self, AllocError> {
+ // SAFETY: These are the correct arguments to allocate a single page.
+ let page = unsafe {
+ bindings::alloc_pages(
+ bindings::GFP_KERNEL | bindings::__GFP_ZERO | bindings::__GFP_HIGHMEM,
+ 0,
+ )
+ };
+
+ let page = NonNull::new(page).ok_or(AllocError)?;
+ // INVARIANT: We checked that the allocation succeeded.
+ Ok(Self { page })
+ }
+
+ /// Returns a raw pointer to the page.
+ pub fn as_ptr(&self) -> *mut bindings::page {
+ self.page.as_ptr()
+ }
+
+ /// Runs a piece of code with this page mapped to an address.
+ ///
+ /// The page is unmapped when this call returns.
+ ///
+ /// It is up to the caller to use the provided raw pointer correctly.
+ pub fn with_page_mapped<T>(&self, f: impl FnOnce(*mut u8) -> T) -> T {
+ // SAFETY: `page` is valid due to the type invariants on `Page`.
+ let mapped_addr = unsafe { bindings::kmap_local_page(self.as_ptr()) };
+
+ let res = f(mapped_addr.cast());
+
+ // SAFETY: This unmaps the page mapped above.
+ //
+ // Since this API takes the user code as a closure, it can only be used
+ // in a manner where the pages are unmapped in reverse order. This is as
+ // required by `kunmap_local`.
+ //
+ // In other words, if this call to `kunmap_local` happens when a
+ // different page should be unmapped first, then there must necessarily
+ // be a call to `kmap_local_page` other than the call just above in
+ // `with_page_mapped` that made that possible. In this case, it is the
+ // unsafe block that wraps that other call that is incorrect.
+ unsafe { bindings::kunmap_local(mapped_addr) };
+
+ res
+ }
+
+ /// Runs a piece of code with a raw pointer to a slice of this page, with
+ /// bounds checking.
+ ///
+ /// If `f` is called, then it will be called with a pointer that points at
+ /// `off` bytes into the page, and the pointer will be valid for at least
+ /// `len` bytes. The pointer is only valid on this task, as this method uses
+ /// a local mapping.
+ ///
+ /// If `off` and `len` refers to a region outside of this page, then this
+ /// method returns `EINVAL` and does not call `f`.
+ ///
+ /// It is up to the caller to use the provided raw pointer correctly.
+ pub fn with_pointer_into_page<T>(
+ &self,
+ off: usize,
+ len: usize,
+ f: impl FnOnce(*mut u8) -> Result<T>,
+ ) -> Result<T> {
+ let bounds_ok = off <= PAGE_SIZE && len <= PAGE_SIZE && (off + len) <= PAGE_SIZE;
+
+ if bounds_ok {
+ self.with_page_mapped(move |page_addr| {
+ // SAFETY: The `off` integer is at most `PAGE_SIZE`, so this pointer offset will
+ // result in a pointer that is in bounds or one off the end of the page.
+ f(unsafe { page_addr.add(off) })
+ })
+ } else {
+ Err(EINVAL)
+ }
+ }
+
+ /// Maps the page and reads from it into the given buffer.
+ ///
+ /// This method will perform bounds checks on the page offset. If `offset ..
+ /// offset+len` goes outside ot the page, then this call returns `EINVAL`.
+ ///
+ /// # Safety
+ ///
+ /// * Callers must ensure that `dst` is valid for writing `len` bytes.
+ /// * Callers must ensure that this call does not race with a write to the
+ /// same page that overlaps with this read.
+ pub unsafe fn read_raw(&self, dst: *mut u8, offset: usize, len: usize) -> Result {
+ self.with_pointer_into_page(offset, len, move |src| {
+ // SAFETY: If `with_pointer_into_page` calls into this closure, then
+ // it has performed a bounds check and guarantees that `src` is
+ // valid for `len` bytes.
+ //
+ // There caller guarantees that there is no data race.
+ unsafe { ptr::copy(src, dst, len) };
+ Ok(())
+ })
+ }
+
+ /// Maps the page and writes into it from the given buffer.
+ ///
+ /// This method will perform bounds checks on the page offset. If `offset ..
+ /// offset+len` goes outside ot the page, then this call returns `EINVAL`.
+ ///
+ /// # Safety
+ ///
+ /// * Callers must ensure that `src` is valid for reading `len` bytes.
+ /// * Callers must ensure that this call does not race with a read or write
+ /// to the same page that overlaps with this write.
+ pub unsafe fn write_raw(&self, src: *const u8, offset: usize, len: usize) -> Result {
+ self.with_pointer_into_page(offset, len, move |dst| {
+ // SAFETY: If `with_pointer_into_page` calls into this closure, then
+ // it has performed a bounds check and guarantees that `dst` is
+ // valid for `len` bytes.
+ //
+ // There caller guarantees that there is no data race.
+ unsafe { ptr::copy(src, dst, len) };
+ Ok(())
+ })
+ }
+
+ /// Maps the page and zeroes the given slice.
+ ///
+ /// This method will perform bounds checks on the page offset. If `offset ..
+ /// offset+len` goes outside ot the page, then this call returns `EINVAL`.
+ ///
+ /// # Safety
+ ///
+ /// Callers must ensure that this call does not race with a read or write to
+ /// the same page that overlaps with this write.
+ pub unsafe fn fill_zero(&self, offset: usize, len: usize) -> Result {
+ self.with_pointer_into_page(offset, len, move |dst| {
+ // SAFETY: If `with_pointer_into_page` calls into this closure, then
+ // it has performed a bounds check and guarantees that `dst` is
+ // valid for `len` bytes.
+ //
+ // There caller guarantees that there is no data race.
+ unsafe { ptr::write_bytes(dst, 0u8, len) };
+ Ok(())
+ })
+ }
+
+ /// Copies data from userspace into this page.
+ ///
+ /// This method will perform bounds checks on the page offset. If `offset ..
+ /// offset+len` goes outside ot the page, then this call returns `EINVAL`.
+ ///
+ /// # Safety
+ ///
+ /// Callers must ensure that this call does not race with a read or write to
+ /// the same page that overlaps with this write.
+ pub unsafe fn copy_from_user_slice(
+ &self,
+ reader: &mut UserSliceReader,
+ offset: usize,
+ len: usize,
+ ) -> Result {
+ self.with_pointer_into_page(offset, len, move |dst| {
+ // SAFETY: If `with_pointer_into_page` calls into this closure, then
+ // it has performed a bounds check and guarantees that `dst` is
+ // valid for `len` bytes.
+ //
+ // There caller guarantees that there is no data race when writing
+ // to `dst`.
+ unsafe { reader.read_raw(dst, len) }
+ })
+ }
+}
+
+impl Drop for Page {
+ fn drop(&mut self) {
+ // SAFETY: By the type invariants, we have ownership of the page and can
+ // free it.
+ unsafe { bindings::__free_pages(self.page.as_ptr(), 0) };
+ }
+}
--
2.43.0.594.gd9cf4e227d-goog
Add safe methods for reading and writing Rust values to and from
userspace pointers.
The C methods for copying to/from userspace use a function called
`check_object_size` to verify that the kernel pointer is not dangling.
However, this check is skipped when the length is a compile-time
constant, with the assumption that such cases trivially have a correct
kernel pointer.
In this patch, we apply the same optimization to the typed accessors.
For both methods, the size of the operation is known at compile time to
be size_of of the type being read or written. Since the C side doesn't
provide a variant that skips only this check, we create custom helpers
for this purpose.
The majority of reads and writes to userspace pointers in the Rust
Binder driver uses these accessor methods. Benchmarking has found that
skipping the `check_object_size` check makes a big difference for the
cases being skipped here. (And that the check doesn't make a difference
for the cases that use the raw read/write methods.)
This code is based on something that was originally written by Wedson on
the old rust branch. It was modified by Alice to skip the
`check_object_size` check, and to update various comments, including the
notes about kernel pointers in `WritableToBytes`.
Co-developed-by: Wedson Almeida Filho <[email protected]>
Signed-off-by: Wedson Almeida Filho <[email protected]>
Signed-off-by: Alice Ryhl <[email protected]>
---
rust/kernel/types.rs | 67 ++++++++++++++++++++++++++++++++++++++++++++
rust/kernel/uaccess.rs | 75 +++++++++++++++++++++++++++++++++++++++++++++++++-
2 files changed, 141 insertions(+), 1 deletion(-)
diff --git a/rust/kernel/types.rs b/rust/kernel/types.rs
index fdb778e65d79..33d175a3a6ed 100644
--- a/rust/kernel/types.rs
+++ b/rust/kernel/types.rs
@@ -387,3 +387,70 @@ pub enum Either<L, R> {
/// Constructs an instance of [`Either`] containing a value of type `R`.
Right(R),
}
+
+/// Types for which any bit pattern is valid.
+///
+/// Not all types are valid for all values. For example, a `bool` must be either
+/// zero or one, so reading arbitrary bytes into something that contains a
+/// `bool` is not okay.
+///
+/// It's okay for the type to have padding, as initializing those bytes has no
+/// effect.
+///
+/// # Safety
+///
+/// All bit-patterns must be valid for this type.
+pub unsafe trait FromBytes {}
+
+// SAFETY: All bit patterns are acceptable values of the types below.
+unsafe impl FromBytes for u8 {}
+unsafe impl FromBytes for u16 {}
+unsafe impl FromBytes for u32 {}
+unsafe impl FromBytes for u64 {}
+unsafe impl FromBytes for usize {}
+unsafe impl FromBytes for i8 {}
+unsafe impl FromBytes for i16 {}
+unsafe impl FromBytes for i32 {}
+unsafe impl FromBytes for i64 {}
+unsafe impl FromBytes for isize {}
+// SAFETY: If all bit patterns are acceptable for individual values in an array,
+// then all bit patterns are also acceptable for arrays of that type.
+unsafe impl<T: FromBytes> FromBytes for [T] {}
+unsafe impl<T: FromBytes, const N: usize> FromBytes for [T; N] {}
+
+/// Types that can be viewed as an immutable slice of initialized bytes.
+///
+/// If a struct implements this trait, then it is okay to copy it byte-for-byte
+/// to userspace. This means that it should not have any padding, as padding
+/// bytes are uninitialized. Reading uninitialized memory is not just undefined
+/// behavior, it may even lead to leaking sensitive information on the stack to
+/// userspace.
+///
+/// The struct should also not hold kernel pointers, as kernel pointer addresses
+/// are also considered sensitive. However, leaking kernel pointers is not
+/// considered undefined behavior by Rust, so this is a correctness requirement,
+/// but not a safety requirement.
+///
+/// # Safety
+///
+/// Values of this type may not contain any uninitialized bytes.
+pub unsafe trait AsBytes {}
+
+// SAFETY: Instances of the following types have no uninitialized portions.
+unsafe impl AsBytes for u8 {}
+unsafe impl AsBytes for u16 {}
+unsafe impl AsBytes for u32 {}
+unsafe impl AsBytes for u64 {}
+unsafe impl AsBytes for usize {}
+unsafe impl AsBytes for i8 {}
+unsafe impl AsBytes for i16 {}
+unsafe impl AsBytes for i32 {}
+unsafe impl AsBytes for i64 {}
+unsafe impl AsBytes for isize {}
+unsafe impl AsBytes for bool {}
+unsafe impl AsBytes for char {}
+unsafe impl AsBytes for str {}
+// SAFETY: If individual values in an array have no uninitialized portions, then
+// the the array itself does not have any uninitialized portions either.
+unsafe impl<T: AsBytes> AsBytes for [T] {}
+unsafe impl<T: AsBytes, const N: usize> AsBytes for [T; N] {}
diff --git a/rust/kernel/uaccess.rs b/rust/kernel/uaccess.rs
index f07821184bd6..71a00177a4b9 100644
--- a/rust/kernel/uaccess.rs
+++ b/rust/kernel/uaccess.rs
@@ -4,9 +4,15 @@
//!
//! C header: [`include/linux/uaccess.h`](srctree/include/linux/uaccess.h)
-use crate::{bindings, error::code::*, error::Result};
+use crate::{
+ bindings,
+ error::code::*,
+ error::Result,
+ types::{AsBytes, FromBytes},
+};
use alloc::vec::Vec;
use core::ffi::{c_ulong, c_void};
+use core::mem::{size_of, MaybeUninit};
/// A pointer to an area in userspace memory, which can be either read-only or
/// read-write.
@@ -237,6 +243,41 @@ pub unsafe fn read_raw(&mut self, out: *mut u8, len: usize) -> Result {
Ok(())
}
+ /// Reads a value of the specified type.
+ ///
+ /// Fails with `EFAULT` if the read encounters a page fault.
+ pub fn read<T: FromBytes>(&mut self) -> Result<T> {
+ let len = size_of::<T>();
+ if len > self.length {
+ return Err(EFAULT);
+ }
+ let Ok(len_ulong) = c_ulong::try_from(len) else {
+ return Err(EFAULT);
+ };
+ let mut out: MaybeUninit<T> = MaybeUninit::uninit();
+ // SAFETY: The local variable `out` is valid for writing `size_of::<T>()` bytes.
+ //
+ // By using the _copy_from_user variant, we skip the check_object_size
+ // check that verifies the kernel pointer. This mirrors the logic on the
+ // C side that skips the check when the length is a compile-time
+ // constant.
+ let res = unsafe {
+ bindings::_copy_from_user(out.as_mut_ptr().cast::<c_void>(), self.ptr, len_ulong)
+ };
+ if res != 0 {
+ return Err(EFAULT);
+ }
+ // Since this is not a pointer to a valid object in our program,
+ // we cannot use `add`, which has C-style rules for defined
+ // behavior.
+ self.ptr = self.ptr.wrapping_byte_add(len);
+ self.length -= len;
+ // SAFETY: The read above has initialized all bytes in `out`, and since
+ // `T` implements `FromBytes`, any bit-pattern is a valid value for this
+ // type.
+ Ok(unsafe { out.assume_init() })
+ }
+
/// Reads the entirety of the user slice, appending it to the end of the
/// provided buffer.
///
@@ -311,4 +352,36 @@ pub fn write_slice(&mut self, data: &[u8]) -> Result {
// `len`, so the pointer is valid for reading `len` bytes.
unsafe { self.write_raw(ptr, len) }
}
+
+ /// Writes the provided Rust value to this userspace pointer.
+ ///
+ /// Fails with `EFAULT` if the write encounters a page fault.
+ pub fn write<T: AsBytes>(&mut self, value: &T) -> Result {
+ let len = size_of::<T>();
+ if len > self.length {
+ return Err(EFAULT);
+ }
+ let Ok(len_ulong) = c_ulong::try_from(len) else {
+ return Err(EFAULT);
+ };
+ // SAFETY: The reference points to a value of type `T`, so it is valid
+ // for reading `size_of::<T>()` bytes.
+ //
+ // By using the _copy_to_user variant, we skip the check_object_size
+ // check that verifies the kernel pointer. This mirrors the logic on the
+ // C side that skips the check when the length is a compile-time
+ // constant.
+ let res = unsafe {
+ bindings::_copy_to_user(self.ptr, (value as *const T).cast::<c_void>(), len_ulong)
+ };
+ if res != 0 {
+ return Err(EFAULT);
+ }
+ // Since this is not a pointer to a valid object in our program,
+ // we cannot use `add`, which has C-style rules for defined
+ // behavior.
+ self.ptr = self.ptr.wrapping_byte_add(len);
+ self.length -= len;
+ Ok(())
+ }
}
--
2.43.0.594.gd9cf4e227d-goog
From: Wedson Almeida Filho <[email protected]>
A pointer to an area in userspace memory, which can be either read-only
or read-write.
All methods on this struct are safe: invalid pointers return `EFAULT`.
Concurrent access, *including data races to/from userspace memory*, is
permitted, because fundamentally another userspace thread/process could
always be modifying memory at the same time (in the same way that
userspace Rust's `std::io` permits data races with the contents of
files on disk). In the presence of a race, the exact byte values
read/written are unspecified but the operation is well-defined.
Kernelspace code should validate its copy of data after completing a
read, and not expect that multiple reads of the same address will return
the same value.
These APIs are designed to make it difficult to accidentally write
TOCTOU bugs. Every time you read from a memory location, the pointer is
advanced by the length so that you cannot use that reader to read the
same memory location twice. Preventing double-fetches avoids TOCTOU
bugs. This is accomplished by taking `self` by value to prevent
obtaining multiple readers on a given `UserSlicePtr`, and the readers
only permitting forward reads. If double-fetching a memory location is
necessary for some reason, then that is done by creating multiple
readers to the same memory location.
Constructing a `UserSlicePtr` performs no checks on the provided
address and length, it can safely be constructed inside a kernel thread
with no current userspace process. Reads and writes wrap the kernel APIs
`copy_from_user` and `copy_to_user`, which check the memory map of the
current process and enforce that the address range is within the user
range (no additional calls to `access_ok` are needed).
This code is based on something that was originally written by Wedson on
the old rust branch. It was modified by Alice by removing the
`IoBufferReader` and `IoBufferWriter` traits, introducing the
`MAX_USER_OP_LEN` constant, and various changes to the comments and
documentation.
Signed-off-by: Wedson Almeida Filho <[email protected]>
Co-developed-by: Alice Ryhl <[email protected]>
Signed-off-by: Alice Ryhl <[email protected]>
---
rust/helpers.c | 14 +++
rust/kernel/lib.rs | 1 +
rust/kernel/uaccess.rs | 314 +++++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 329 insertions(+)
diff --git a/rust/helpers.c b/rust/helpers.c
index 70e59efd92bc..312b6fcb49d5 100644
--- a/rust/helpers.c
+++ b/rust/helpers.c
@@ -38,6 +38,20 @@ __noreturn void rust_helper_BUG(void)
}
EXPORT_SYMBOL_GPL(rust_helper_BUG);
+unsigned long rust_helper_copy_from_user(void *to, const void __user *from,
+ unsigned long n)
+{
+ return copy_from_user(to, from, n);
+}
+EXPORT_SYMBOL_GPL(rust_helper_copy_from_user);
+
+unsigned long rust_helper_copy_to_user(void __user *to, const void *from,
+ unsigned long n)
+{
+ return copy_to_user(to, from, n);
+}
+EXPORT_SYMBOL_GPL(rust_helper_copy_to_user);
+
void rust_helper_mutex_lock(struct mutex *lock)
{
mutex_lock(lock);
diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
index b89ecf4e97a0..5a03aafcbb69 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -50,6 +50,7 @@
pub mod task;
pub mod time;
pub mod types;
+pub mod uaccess;
pub mod workqueue;
#[doc(hidden)]
diff --git a/rust/kernel/uaccess.rs b/rust/kernel/uaccess.rs
new file mode 100644
index 000000000000..f07821184bd6
--- /dev/null
+++ b/rust/kernel/uaccess.rs
@@ -0,0 +1,314 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! User pointers.
+//!
+//! C header: [`include/linux/uaccess.h`](srctree/include/linux/uaccess.h)
+
+use crate::{bindings, error::code::*, error::Result};
+use alloc::vec::Vec;
+use core::ffi::{c_ulong, c_void};
+
+/// A pointer to an area in userspace memory, which can be either read-only or
+/// read-write.
+///
+/// All methods on this struct are safe: attempting to read or write invalid
+/// pointers will return `EFAULT`. Concurrent access, *including data races
+/// to/from userspace memory*, is permitted, because fundamentally another
+/// userspace thread/process could always be modifying memory at the same time
+/// (in the same way that userspace Rust's [`std::io`] permits data races with
+/// the contents of files on disk). In the presence of a race, the exact byte
+/// values read/written are unspecified but the operation is well-defined.
+/// Kernelspace code should validate its copy of data after completing a read,
+/// and not expect that multiple reads of the same address will return the same
+/// value.
+///
+/// These APIs are designed to make it difficult to accidentally write TOCTOU
+/// (time-of-check to time-of-use) bugs. Every time a memory location is read,
+/// the reader's position is advanced by the read length and the next read will
+/// start from there. This helps prevent accidentally reading the same location
+/// twice and causing a TOCTOU bug.
+///
+/// Creating a [`UserSliceReader`] and/or [`UserSliceWriter`] consumes the
+/// `UserSlice`, helping ensure that there aren't multiple readers or writers to
+/// the same location.
+///
+/// If double-fetching a memory location is necessary for some reason, then that
+/// is done by creating multiple readers to the same memory location, e.g. using
+/// [`clone_reader`].
+///
+/// # Examples
+///
+/// Takes a region of userspace memory from the current process, and modify it
+/// by adding one to every byte in the region.
+///
+/// ```no_run
+/// use alloc::vec::Vec;
+/// use core::ffi::c_void;
+/// use kernel::error::Result;
+/// use kernel::uaccess::UserSlice;
+///
+/// pub fn bytes_add_one(uptr: *mut c_void, len: usize) -> Result<()> {
+/// let (read, mut write) = UserSlice::new(uptr, len).reader_writer();
+///
+/// let mut buf = Vec::new();
+/// read.read_all(&mut buf)?;
+///
+/// for b in &mut buf {
+/// *b = b.wrapping_add(1);
+/// }
+///
+/// write.write_slice(&buf)?;
+/// Ok(())
+/// }
+/// ```
+///
+/// Example illustrating a TOCTOU (time-of-check to time-of-use) bug.
+///
+/// ```no_run
+/// use alloc::vec::Vec;
+/// use core::ffi::c_void;
+/// use kernel::error::{code::EINVAL, Result};
+/// use kernel::uaccess::UserSlice;
+///
+/// /// Returns whether the data in this region is valid.
+/// fn is_valid(uptr: *mut c_void, len: usize) -> Result<bool> {
+/// let read = UserSlice::new(uptr, len).reader();
+///
+/// let mut buf = Vec::new();
+/// read.read_all(&mut buf)?;
+///
+/// todo!()
+/// }
+///
+/// /// Returns the bytes behind this user pointer if they are valid.
+/// pub fn get_bytes_if_valid(uptr: *mut c_void, len: usize) -> Result<Vec<u8>> {
+/// if !is_valid(uptr, len)? {
+/// return Err(EINVAL);
+/// }
+///
+/// let read = UserSlice::new(uptr, len).reader();
+///
+/// let mut buf = Vec::new();
+/// read.read_all(&mut buf)?;
+///
+/// // THIS IS A BUG! The bytes could have changed since we checked them.
+/// //
+/// // To avoid this kind of bug, don't call `UserSlice::new` multiple
+/// // times with the same address.
+/// Ok(buf)
+/// }
+/// ```
+///
+/// [`std::io`]: https://doc.rust-lang.org/std/io/index.html
+/// [`clone_reader`]: UserSliceReader::clone_reader
+pub struct UserSlice {
+ ptr: *mut c_void,
+ length: usize,
+}
+
+impl UserSlice {
+ /// Constructs a user slice from a raw pointer and a length in bytes.
+ ///
+ /// Constructing a [`UserSlice`] performs no checks on the provided address
+ /// and length, it can safely be constructed inside a kernel thread with no
+ /// current userspace process. Reads and writes wrap the kernel APIs
+ /// `copy_from_user` and `copy_to_user`, which check the memory map of the
+ /// current process and enforce that the address range is within the user
+ /// range (no additional calls to `access_ok` are needed).
+ ///
+ /// Callers must be careful to avoid time-of-check-time-of-use
+ /// (TOCTOU) issues. The simplest way is to create a single instance of
+ /// [`UserSlice`] per user memory block as it reads each byte at
+ /// most once.
+ pub fn new(ptr: *mut c_void, length: usize) -> Self {
+ UserSlice { ptr, length }
+ }
+
+ /// Reads the entirety of the user slice, appending it to the end of the
+ /// provided buffer.
+ ///
+ /// Fails with `EFAULT` if the read encounters a page fault.
+ pub fn read_all(self, buf: &mut Vec<u8>) -> Result<()> {
+ self.reader().read_all(buf)
+ }
+
+ /// Constructs a [`UserSliceReader`].
+ pub fn reader(self) -> UserSliceReader {
+ UserSliceReader {
+ ptr: self.ptr,
+ length: self.length,
+ }
+ }
+
+ /// Constructs a [`UserSliceWriter`].
+ pub fn writer(self) -> UserSliceWriter {
+ UserSliceWriter {
+ ptr: self.ptr,
+ length: self.length,
+ }
+ }
+
+ /// Constructs both a [`UserSliceReader`] and a [`UserSliceWriter`].
+ ///
+ /// Usually when this is used, you will first read the data, and then
+ /// overwrite it afterwards.
+ pub fn reader_writer(self) -> (UserSliceReader, UserSliceWriter) {
+ (
+ UserSliceReader {
+ ptr: self.ptr,
+ length: self.length,
+ },
+ UserSliceWriter {
+ ptr: self.ptr,
+ length: self.length,
+ },
+ )
+ }
+}
+
+/// A reader for [`UserSlice`].
+///
+/// Used to incrementally read from the user slice.
+pub struct UserSliceReader {
+ ptr: *mut c_void,
+ length: usize,
+}
+
+impl UserSliceReader {
+ /// Skip the provided number of bytes.
+ ///
+ /// Returns an error if skipping more than the length of the buffer.
+ pub fn skip(&mut self, num_skip: usize) -> Result {
+ // Update `self.length` first since that's the fallible part of this
+ // operation.
+ self.length = self.length.checked_sub(num_skip).ok_or(EFAULT)?;
+ self.ptr = self.ptr.wrapping_byte_add(num_skip);
+ Ok(())
+ }
+
+ /// Create a reader that can access the same range of data.
+ ///
+ /// Reading from the clone does not advance the current reader.
+ ///
+ /// The caller should take care to not introduce TOCTOU issues, as described
+ /// in the documentation for [`UserSlice`].
+ pub fn clone_reader(&self) -> UserSliceReader {
+ UserSliceReader {
+ ptr: self.ptr,
+ length: self.length,
+ }
+ }
+
+ /// Returns the number of bytes left to be read from this reader.
+ ///
+ /// Note that even reading less than this number of bytes may fail.
+ pub fn len(&self) -> usize {
+ self.length
+ }
+
+ /// Returns `true` if no data is available in the io buffer.
+ pub fn is_empty(&self) -> bool {
+ self.length == 0
+ }
+
+ /// Reads raw data from the user slice into a raw kernel buffer.
+ ///
+ /// Fails with `EFAULT` if the read encounters a page fault.
+ ///
+ /// # Safety
+ ///
+ /// The `out` pointer must be valid for writing `len` bytes.
+ pub unsafe fn read_raw(&mut self, out: *mut u8, len: usize) -> Result {
+ if len > self.length {
+ return Err(EFAULT);
+ }
+ let Ok(len_ulong) = c_ulong::try_from(len) else {
+ return Err(EFAULT);
+ };
+ // SAFETY: The caller promises that `out` is valid for writing `len` bytes.
+ let res = unsafe { bindings::copy_from_user(out.cast::<c_void>(), self.ptr, len_ulong) };
+ if res != 0 {
+ return Err(EFAULT);
+ }
+ // Userspace pointers are not directly dereferencable by the kernel, so
+ // we cannot use `add`, which has C-style rules for defined behavior.
+ self.ptr = self.ptr.wrapping_byte_add(len);
+ self.length -= len;
+ Ok(())
+ }
+
+ /// Reads the entirety of the user slice, appending it to the end of the
+ /// provided buffer.
+ ///
+ /// Fails with `EFAULT` if the read encounters a page fault.
+ pub fn read_all(mut self, buf: &mut Vec<u8>) -> Result<()> {
+ buf.try_reserve(self.length)?;
+
+ // SAFETY: The call to `try_reserve` was successful, so the spare
+ // capacity is at least `self.length` bytes long.
+ unsafe { self.read_raw(buf.spare_capacity_mut().as_mut_ptr().cast(), self.length)? };
+
+ // SAFETY: Since the call to `read_raw` was successful, so the next
+ // `len` bytes of the vector have been initialized.
+ unsafe { buf.set_len(buf.len() + self.length) };
+ Ok(())
+ }
+}
+
+/// A writer for [`UserSlice`].
+///
+/// Used to incrementally write into the user slice.
+pub struct UserSliceWriter {
+ ptr: *mut c_void,
+ length: usize,
+}
+
+impl UserSliceWriter {
+ /// Returns the amount of space remaining in this buffer.
+ ///
+ /// Note that even writing less than this number of bytes may fail.
+ pub fn len(&self) -> usize {
+ self.length
+ }
+
+ /// Returns `true` if no more data can be written to this buffer.
+ pub fn is_empty(&self) -> bool {
+ self.length == 0
+ }
+
+ /// Writes raw data to this user pointer from a raw kernel buffer.
+ ///
+ /// Fails with `EFAULT` if the write encounters a page fault.
+ ///
+ /// # Safety
+ ///
+ /// The `data` pointer must be valid for reading `len` bytes.
+ pub unsafe fn write_raw(&mut self, data: *const u8, len: usize) -> Result {
+ if len > self.length {
+ return Err(EFAULT);
+ }
+ let Ok(len_ulong) = c_ulong::try_from(len) else {
+ return Err(EFAULT);
+ };
+ let res = unsafe { bindings::copy_to_user(self.ptr, data.cast::<c_void>(), len_ulong) };
+ if res != 0 {
+ return Err(EFAULT);
+ }
+ // Userspace pointers are not directly dereferencable by the kernel, so
+ // we cannot use `add`, which has C-style rules for defined behavior.
+ self.ptr = self.ptr.wrapping_byte_add(len);
+ self.length -= len;
+ Ok(())
+ }
+
+ /// Writes the provided slice to this user pointer.
+ ///
+ /// Fails with `EFAULT` if the write encounters a page fault.
+ pub fn write_slice(&mut self, data: &[u8]) -> Result {
+ let len = data.len();
+ let ptr = data.as_ptr();
+ // SAFETY: The pointer originates from a reference to a slice of length
+ // `len`, so the pointer is valid for reading `len` bytes.
+ unsafe { self.write_raw(ptr, len) }
+ }
+}
--
2.43.0.594.gd9cf4e227d-goog
> + /// Reads the entirety of the user slice, appending it to the end of the
> + /// provided buffer.
> + ///
> + /// Fails with `EFAULT` if the read encounters a page fault.
> + pub fn read_all(self, buf: &mut Vec<u8>) -> Result<()> {
> + self.reader().read_all(buf)
> + }
I think there is also no need to give an explicit `()` for the
generic type parameter here as it is the default (applies to some
other methods in this patch as well).
> -#else
> extern __must_check unsigned long
> _copy_from_user(void *, const void __user *, unsigned long);
> -#endif
This function is now unconditionally declared, but only defined if
`!defined(INLINE_COPY_FROM_USER) || defined(CONFIG_RUST)`, i.e., in the
common case where it is inlined and Rust is disabled this can lead to
link-time problems if someone decides to use it.
> +/// If a struct implements this trait, then it is okay to copy it byte-for-byte
> +/// to userspace. This means that it should not have any padding, as padding
> +/// bytes are uninitialized. Reading uninitialized memory is not just undefined
> +/// behavior, it may even lead to leaking sensitive information on the stack to
> +/// userspace.
This feels a bit too restrictive to me. Isn't it okay to copy types with
padding if it is ensured that the padding is always initialized?
I recall that in C one occasionally does a `memset` for structs that are
copied to user space. I imagine that one could have a Rust
abstraction/macro that makes it easy to define custom types that can
always guarantee that all padding bytes are initialized. Such types
would then qualify for being copied to user space if all field do so as
well.
This could be a significant quality-of-life improvement for drivers
as it can be tedious to define struct without padding.
- Best Valentin
On Thu, Feb 8, 2024 at 11:57 PM Valentin Obst <[email protected]> wrote:
>
> > +/// If a struct implements this trait, then it is okay to copy it byte-for-byte
> > +/// to userspace. This means that it should not have any padding, as padding
> > +/// bytes are uninitialized. Reading uninitialized memory is not just undefined
> > +/// behavior, it may even lead to leaking sensitive information on the stack to
> > +/// userspace.
>
> This feels a bit too restrictive to me. Isn't it okay to copy types with
> padding if it is ensured that the padding is always initialized?
>
> I recall that in C one occasionally does a `memset` for structs that are
> copied to user space. I imagine that one could have a Rust
> abstraction/macro that makes it easy to define custom types that can
> always guarantee that all padding bytes are initialized. Such types
> would then qualify for being copied to user space if all field do so as
> well.
>
> This could be a significant quality-of-life improvement for drivers
> as it can be tedious to define struct without padding.
I don't think we should go that route. For example:
let struct_1 = ..;
memset(&mut struct_1, 0);
let struct_2 = struct_1;
Even though struct_1 has its padding zeroed here, that is not the case
for struct_2. When Rust performs a typed copy/move, the padding is not
copied.
Anyway, there is a work-around. Define your struct with MaybeUninit:
// INVARIANT: All bytes always initialized.
struct MyWrapper(MaybeUninit<bindings::c_struct>);
impl Default for MyWrapper {
fn default() -> Self {
MyWrapper(MaybeUninit::zeroed())
}
}
Unlike the bare struct, things wrapped in MaybeUninit always have
their padding preserved. Then, you can implement the trait for this
wrapper, since its padding is always initialized even if that is not
true for the wrapped struct.
Alice
On Thu, Feb 8, 2024 at 11:54 PM Valentin Obst <[email protected]> wrote:
>
> > + /// Reads the entirety of the user slice, appending it to the end of the
> > + /// provided buffer.
> > + ///
> > + /// Fails with `EFAULT` if the read encounters a page fault.
> > + pub fn read_all(self, buf: &mut Vec<u8>) -> Result<()> {
> > + self.reader().read_all(buf)
> > + }
>
> I think there is also no need to give an explicit `()` for the
> generic type parameter here as it is the default (applies to some
> other methods in this patch as well).
I'll change this if I send a v3, but I don't think it's that important.
Alice
On Thu, Feb 8, 2024, at 23:56, Valentin Obst wrote:
>> -#else
>> extern __must_check unsigned long
>> _copy_from_user(void *, const void __user *, unsigned long);
>> -#endif
>
> This function is now unconditionally declared, but only defined if
> `!defined(INLINE_COPY_FROM_USER) || defined(CONFIG_RUST)`, i.e., in the
> common case where it is inlined and Rust is disabled this can lead to
> link-time problems if someone decides to use it.
Yes, that is intentional.
If someone tries to use it when the declaration is not there,
they just get a compile-time error, which is not all that
different from a link-time error in practice.
It's unlikely to make a difference here, but enclosing
declarations in an #ifdef is annoying when you want to
reference it from somewhere that is parsed by the compiler
but not called without the respective options.
The if(IS_ENABLED()) and PTR_IF() constructs in particular
only work when the unused functions are still declared.
Arnd
>>> -#else
>>> extern __must_check unsigned long
>>> _copy_from_user(void *, const void __user *, unsigned long);
>>> -#endif
>>
>> This function is now unconditionally declared, but only defined if
>> `!defined(INLINE_COPY_FROM_USER) || defined(CONFIG_RUST)`, i.e., in the
>> common case where it is inlined and Rust is disabled this can lead to
>> link-time problems if someone decides to use it.
>
> Yes, that is intentional.
>
> If someone tries to use it when the declaration is not there,
> they just get a compile-time error, which is not all that
> different from a link-time error in practice.
>
> It's unlikely to make a difference here, but enclosing
> declarations in an #ifdef is annoying when you want to
> reference it from somewhere that is parsed by the compiler
> but not called without the respective options.
>
> The if(IS_ENABLED()) and PTR_IF() constructs in particular
> only work when the unused functions are still declared.
I see, thanks for the explanation.
- Best Valentin
>
> Arnd
> > > +/// If a struct implements this trait, then it is okay to copy it byte-for-byte
> > > +/// to userspace. This means that it should not have any padding, as padding
> > > +/// bytes are uninitialized. Reading uninitialized memory is not just undefined
> > > +/// behavior, it may even lead to leaking sensitive information on the stack to
> > > +/// userspace.
> >
> > This feels a bit too restrictive to me. Isn't it okay to copy types with
> > padding if it is ensured that the padding is always initialized?
> >
> > I recall that in C one occasionally does a `memset` for structs that are
> > copied to user space. I imagine that one could have a Rust
> > abstraction/macro that makes it easy to define custom types that can
> > always guarantee that all padding bytes are initialized. Such types
> > would then qualify for being copied to user space if all field do so as
> > well.
> >
> > This could be a significant quality-of-life improvement for drivers
> > as it can be tedious to define struct without padding.
>
> I don't think we should go that route. For example:
>
> let struct_1 = ..;
> memset(&mut struct_1, 0);
> let struct_2 = struct_1;
>
> Even though struct_1 has its padding zeroed here, that is not the case
> for struct_2. When Rust performs a typed copy/move, the padding is not
> copied.
>
> Anyway, there is a work-around. Define your struct with MaybeUninit:
>
> // INVARIANT: All bytes always initialized.
> struct MyWrapper(MaybeUninit<bindings::c_struct>);
>
> impl Default for MyWrapper {
> fn default() -> Self {
> MyWrapper(MaybeUninit::zeroed())
> }
> }
>
> Unlike the bare struct, things wrapped in MaybeUninit always have
> their padding preserved. Then, you can implement the trait for this
> wrapper, since its padding is always initialized even if that is not
> true for the wrapped struct.
Yea, I see the issue posed by moving values around. What I had in mind
was some library code that makes achieving the above behavior more
ergonomic and semantically clearer (in the sense that without the
surrounding comments it might not be immediately clear to someone
reading the code why you are doing things that way). My reply was
mainly about gauging interest into such a feature.
However, this really is independent from this patch and could always be
added later. I agree with mentioning padding in the comment and see
nothing blocking here.
- Best Valentin
>
> Alice
On Thu, Feb 08, 2024 at 03:47:52PM +0000, Alice Ryhl wrote:
> From: Arnd Bergmann <[email protected]>
>
> Rust code needs to be able to access _copy_from_user and _copy_to_user
> so that it can skip the check_copy_size check in cases where the length
> is known at compile-time, mirroring the logic for when C code will skip
> check_copy_size. To do this, we ensure that exported versions of these
> methods are available when CONFIG_RUST is enabled.
>
> Signed-off-by: Arnd Bergmann <[email protected]>
> Signed-off-by: Alice Ryhl <[email protected]>
> ---
> include/linux/uaccess.h | 37 +++++++++++++++++++++++--------------
> lib/usercopy.c | 30 ++++--------------------------
> 2 files changed, 27 insertions(+), 40 deletions(-)
>
> diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
> index 3064314f4832..835aa175d0ee 100644
> --- a/include/linux/uaccess.h
> +++ b/include/linux/uaccess.h
> @@ -138,13 +138,18 @@ __copy_to_user(void __user *to, const void *from, unsigned long n)
> return raw_copy_to_user(to, from, n);
> }
>
> -#ifdef INLINE_COPY_FROM_USER
> static inline __must_check unsigned long
> -_copy_from_user(void *to, const void __user *from, unsigned long n)
> +_inline_copy_from_user(void *to, const void __user *from, unsigned long n)
> {
> unsigned long res = n;
> might_fault();
> if (!should_fail_usercopy() && likely(access_ok(from, n))) {
> + /*
> + * Ensure that bad access_ok() speculation will not
> + * lead to nasty side effects *after* the copy is
> + * finished:
> + */
> + barrier_nospec();
This means all callers just gained this barrier. That's a behavioral
change -- is it intentional here? I don't see it mentioned in the commit
log.
Also did this get tested with the CONFIG_TEST_USER_COPY tests? I would
expect it to be fine, but better to check and mention it in the commit
log.
-Kees
> instrument_copy_from_user_before(to, from, n);
> res = raw_copy_from_user(to, from, n);
> instrument_copy_from_user_after(to, from, n, res);
> @@ -153,14 +158,11 @@ _copy_from_user(void *to, const void __user *from, unsigned long n)
> memset(to + (n - res), 0, res);
> return res;
> }
> -#else
> extern __must_check unsigned long
> _copy_from_user(void *, const void __user *, unsigned long);
> -#endif
>
> -#ifdef INLINE_COPY_TO_USER
> static inline __must_check unsigned long
> -_copy_to_user(void __user *to, const void *from, unsigned long n)
> +_inline_copy_to_user(void __user *to, const void *from, unsigned long n)
> {
> might_fault();
> if (should_fail_usercopy())
> @@ -171,25 +173,32 @@ _copy_to_user(void __user *to, const void *from, unsigned long n)
> }
> return n;
> }
> -#else
> extern __must_check unsigned long
> _copy_to_user(void __user *, const void *, unsigned long);
> -#endif
>
> static __always_inline unsigned long __must_check
> copy_from_user(void *to, const void __user *from, unsigned long n)
> {
> - if (check_copy_size(to, n, false))
> - n = _copy_from_user(to, from, n);
> - return n;
> + if (!check_copy_size(to, n, false))
> + return n;
> +#ifdef INLINE_COPY_FROM_USER
> + return _inline_copy_from_user(to, from, n);
> +#else
> + return _copy_from_user(to, from, n);
> +#endif
> }
>
> static __always_inline unsigned long __must_check
> copy_to_user(void __user *to, const void *from, unsigned long n)
> {
> - if (check_copy_size(from, n, true))
> - n = _copy_to_user(to, from, n);
> - return n;
> + if (!check_copy_size(from, n, true))
> + return n;
> +
> +#ifdef INLINE_COPY_TO_USER
> + return _inline_copy_to_user(to, from, n);
> +#else
> + return _copy_to_user(to, from, n);
> +#endif
> }
>
> #ifndef copy_mc_to_kernel
> diff --git a/lib/usercopy.c b/lib/usercopy.c
> index d29fe29c6849..de7f30618293 100644
> --- a/lib/usercopy.c
> +++ b/lib/usercopy.c
> @@ -7,40 +7,18 @@
>
> /* out-of-line parts */
>
> -#ifndef INLINE_COPY_FROM_USER
> +#if !defined(INLINE_COPY_FROM_USER) || defined(CONFIG_RUST)
> unsigned long _copy_from_user(void *to, const void __user *from, unsigned long n)
> {
> - unsigned long res = n;
> - might_fault();
> - if (!should_fail_usercopy() && likely(access_ok(from, n))) {
> - /*
> - * Ensure that bad access_ok() speculation will not
> - * lead to nasty side effects *after* the copy is
> - * finished:
> - */
> - barrier_nospec();
> - instrument_copy_from_user_before(to, from, n);
> - res = raw_copy_from_user(to, from, n);
> - instrument_copy_from_user_after(to, from, n, res);
> - }
> - if (unlikely(res))
> - memset(to + (n - res), 0, res);
> - return res;
> + return _inline_copy_from_user(to, from, n);
> }
> EXPORT_SYMBOL(_copy_from_user);
> #endif
>
> -#ifndef INLINE_COPY_TO_USER
> +#if !defined(INLINE_COPY_TO_USER) || defined(CONFIG_RUST)
> unsigned long _copy_to_user(void __user *to, const void *from, unsigned long n)
> {
> - might_fault();
> - if (should_fail_usercopy())
> - return n;
> - if (likely(access_ok(to, n))) {
> - instrument_copy_to_user(to, from, n);
> - n = raw_copy_to_user(to, from, n);
> - }
> - return n;
> + return _inline_copy_to_user(to, from, n);
> }
> EXPORT_SYMBOL(_copy_to_user);
> #endif
>
> --
> 2.43.0.594.gd9cf4e227d-goog
>
--
Kees Cook
On 2/8/24 12:47, Alice Ryhl wrote:
> [...]
> + /// Maps the page and reads from it into the given buffer.
> + ///
> + /// This method will perform bounds checks on the page offset. If `offset ..
> + /// offset+len` goes outside ot the page, then this call returns `EINVAL`.
> + ///
> + /// # Safety
> + ///
> + /// * Callers must ensure that `dst` is valid for writing `len` bytes.
> + /// * Callers must ensure that this call does not race with a write to the
> + /// same page that overlaps with this read.
This safety section says that a call mustn't race with a page that
overlaps this read, hmmmmm.
> + pub unsafe fn read_raw(&self, dst: *mut u8, offset: usize, len: usize) -> Result {
> + self.with_pointer_into_page(offset, len, move |src| {
> + // SAFETY: If `with_pointer_into_page` calls into this closure, then
> + // it has performed a bounds check and guarantees that `src` is
> + // valid for `len` bytes.
> + //
> + // There caller guarantees that there is no data race.
> + unsafe { ptr::copy(src, dst, len) };
If `src` and `dst` overlap then wouldn't that be a bad idea? If so then
how about mentioning that callers have to ensure that `dst` does not
overlap with the page that's being read and use
`core::ptr::copy_nonoverlapping` instead, otherwise the doc comment
could mention that `dst` can overlap.
> + Ok(())
> + })
> + }
> +
> + /// Maps the page and writes into it from the given buffer.
> + ///
> + /// This method will perform bounds checks on the page offset. If `offset ..
> + /// offset+len` goes outside ot the page, then this call returns `EINVAL`.
> + ///
> + /// # Safety
> + ///
> + /// * Callers must ensure that `src` is valid for reading `len` bytes.
> + /// * Callers must ensure that this call does not race with a read or write
> + /// to the same page that overlaps with this write.
> + pub unsafe fn write_raw(&self, src: *const u8, offset: usize, len: usize) -> Result {
> + self.with_pointer_into_page(offset, len, move |dst| {
> + // SAFETY: If `with_pointer_into_page` calls into this closure, then
> + // it has performed a bounds check and guarantees that `dst` is
> + // valid for `len` bytes.
> + //
> + // There caller guarantees that there is no data race.
> + unsafe { ptr::copy(src, dst, len) };
Same as above
> + Ok(())
> + })
> + }
> [...]
On Sat, Feb 10, 2024, at 01:15, Kees Cook wrote:
> On Thu, Feb 08, 2024 at 03:47:52PM +0000, Alice Ryhl wrote:
>> unsigned long res = n;
>> might_fault();
>> if (!should_fail_usercopy() && likely(access_ok(from, n))) {
>> + /*
>> + * Ensure that bad access_ok() speculation will not
>> + * lead to nasty side effects *after* the copy is
>> + * finished:
>> + */
>> + barrier_nospec();
>
> This means all callers just gained this barrier. That's a behavioral
> change -- is it intentional here? I don't see it mentioned in the commit
> log.
My bad, I probably should have explained it when I did the
patch as this is very subtle:
The barrier_nospec() definition is a nop on everything other
than x86 and powerpc, but those two were using the out-of-line
version that did in fact use it.
After this patch, the out-of-line function calls the inline
function, so it needs to be added here to keep the behavior
unchanged on the architectures that need it. For the rest,
this change has no effect.
Arnd
On Sat, Feb 10, 2024 at 5:23 AM Martin Rodriguez Reboredo
<[email protected]> wrote:
>
> On 2/8/24 12:47, Alice Ryhl wrote:
> > [...]
> > + /// Maps the page and reads from it into the given buffer.
> > + ///
> > + /// This method will perform bounds checks on the page offset. If `offset ..
> > + /// offset+len` goes outside ot the page, then this call returns `EINVAL`.
> > + ///
> > + /// # Safety
> > + ///
> > + /// * Callers must ensure that `dst` is valid for writing `len` bytes.
> > + /// * Callers must ensure that this call does not race with a write to the
> > + /// same page that overlaps with this read.
>
> This safety section says that a call mustn't race with a page that
> overlaps this read, hmmmmm.
Is there a question here?
> > + pub unsafe fn read_raw(&self, dst: *mut u8, offset: usize, len: usize) -> Result {
> > + self.with_pointer_into_page(offset, len, move |src| {
> > + // SAFETY: If `with_pointer_into_page` calls into this closure, then
> > + // it has performed a bounds check and guarantees that `src` is
> > + // valid for `len` bytes.
> > + //
> > + // There caller guarantees that there is no data race.
> > + unsafe { ptr::copy(src, dst, len) };
>
> If `src` and `dst` overlap then wouldn't that be a bad idea? If so then
> how about mentioning that callers have to ensure that `dst` does not
> overlap with the page that's being read and use
> `core::ptr::copy_nonoverlapping` instead, otherwise the doc comment
> could mention that `dst` can overlap.
I'll use copy_nonoverlapping. Thanks for the suggestion.
Alice
On 2/12/24 06:36, Alice Ryhl wrote:
> On Sat, Feb 10, 2024 at 5:23 AM Martin Rodriguez Reboredo
> <[email protected]> wrote:
>>
>> On 2/8/24 12:47, Alice Ryhl wrote:
>>> [...]
>>> + /// Maps the page and reads from it into the given buffer.
>>> + ///
>>> + /// This method will perform bounds checks on the page offset. If `offset ..
>>> + /// offset+len` goes outside ot the page, then this call returns `EINVAL`.
>>> + ///
>>> + /// # Safety
>>> + ///
>>> + /// * Callers must ensure that `dst` is valid for writing `len` bytes.
>>> + /// * Callers must ensure that this call does not race with a write to the
>>> + /// same page that overlaps with this read.
>>
>> This safety section says that a call mustn't race with a page that
>> overlaps this read, hmmmmm.
>
> Is there a question here?
I've said more like introducing the next point, but if you want to use
`copy_nonoverlapping` then the safety section should mention that both
`src` and `dst` memory areas are forbidden to be overlapping.
> [...]
> I'll use copy_nonoverlapping. Thanks for the suggestion.
>
> Alice
You're welcome.
On Sat, Feb 10, 2024 at 1:15 AM Kees Cook <[email protected]> wrote:
>
> On Thu, Feb 08, 2024 at 03:47:52PM +0000, Alice Ryhl wrote:
> > unsigned long res = n;
> > might_fault();
> > if (!should_fail_usercopy() && likely(access_ok(from, n))) {
> > + /*
> > + * Ensure that bad access_ok() speculation will not
> > + * lead to nasty side effects *after* the copy is
> > + * finished:
> > + */
> > + barrier_nospec();
>
> This means all callers just gained this barrier. That's a behavioral
> change -- is it intentional here? I don't see it mentioned in the commit
> log.
>
> Also did this get tested with the CONFIG_TEST_USER_COPY tests? I would
> expect it to be fine, but better to check and mention it in the commit
> log.
I just ran this with CONFIG_TEST_USER_COPY on x86 using the Android
cuttlefish emulator and it passed there. I also verified that it fails
if I remove the access_ok check. However, the tests succeed even if
the barrier_nospec() call is removed.
That said, it seems like it fails to compile on some other platforms.
It seems like we need to add #include <linux/nospec.h> to uaccess.h to
fix it.
Alice
On Thu, Feb 8, 2024 at 4:48 PM Alice Ryhl <[email protected]> wrote:
> + /// Reads the entirety of the user slice, appending it to the end of the
> + /// provided buffer.
> + ///
> + /// Fails with `EFAULT` if the read encounters a page fault.
> + pub fn read_all(mut self, buf: &mut Vec<u8>) -> Result<()> {
> + buf.try_reserve(self.length)?;
> +
> + // SAFETY: The call to `try_reserve` was successful, so the spare
> + // capacity is at least `self.length` bytes long.
> + unsafe { self.read_raw(buf.spare_capacity_mut().as_mut_ptr().cast(), self.length)? };
> +
> + // SAFETY: Since the call to `read_raw` was successful, so the next
> + // `len` bytes of the vector have been initialized.
> + unsafe { buf.set_len(buf.len() + self.length) };
> + Ok(())
> + }
There's a bug here, since read_raw changes self.length. It will be
fixed in the next version.
Alice
On 8/2/24 16:47, Alice Ryhl wrote:
> + /// Create a reader that can access the same range of data.
> + ///
> + /// Reading from the clone does not advance the current reader.
> + ///
> + /// The caller should take care to not introduce TOCTOU issues, as described
> + /// in the documentation for [`UserSlice`].
> + pub fn clone_reader(&self) -> UserSliceReader {
> + UserSliceReader {
> + ptr: self.ptr,
> + length: self.length,
> + }
> + }
Just out of curiosity, is there any reason why this is not implemented
in terms of the Clone trait?
--
Carlos López
Security Engineer
SUSE Software Solutions
On Tue, Feb 27, 2024 at 11:05 AM Carlos López <[email protected]> wrote:
>
>
> On 8/2/24 16:47, Alice Ryhl wrote:
> > + /// Create a reader that can access the same range of data.
> > + ///
> > + /// Reading from the clone does not advance the current reader.
> > + ///
> > + /// The caller should take care to not introduce TOCTOU issues, as described
> > + /// in the documentation for [`UserSlice`].
> > + pub fn clone_reader(&self) -> UserSliceReader {
> > + UserSliceReader {
> > + ptr: self.ptr,
> > + length: self.length,
> > + }
> > + }
>
> Just out of curiosity, is there any reason why this is not implemented
> in terms of the Clone trait?
I think people find a non-Clone-trait method higher friction than just
calling .clone(), so this nudges people towards not using it if they
don't really need it.
But really, it could go either way. It would be okay to use the Clone trait.
Alice
Hi Alice,
Alice Ryhl <[email protected]> writes:
> Adds a new struct called `Page` that wraps a pointer to `struct page`.
> This struct is assumed to hold ownership over the page, so that Rust
> code can allocate and manage pages directly.
<cut>
> +/// A bitwise shift for the page size.
> +pub const PAGE_SHIFT: usize = bindings::PAGE_SHIFT as usize;
> +/// The number of bytes in a page.
> +pub const PAGE_SIZE: usize = 1 << PAGE_SHIFT;
For consistency, could we get page size from bindings as well? The folio
patches already do this [1].
BR Andreas
[1] https://lore.kernel.org/rust-for-linux/[email protected]/
On Thu, Feb 08, 2024 at 03:47:54PM +0000, Alice Ryhl wrote:
> +impl Page {
> + /// Allocates a new page.
> + pub fn new() -> Result<Self, AllocError> {
> + // SAFETY: These are the correct arguments to allocate a single page.
> + let page = unsafe {
> + bindings::alloc_pages(
> + bindings::GFP_KERNEL | bindings::__GFP_ZERO | bindings::__GFP_HIGHMEM,
I thought I raised this last time, but this is over-specialised for
Binder's purposes. Many places that want to allocate a page want
different GFP flags from this; they shouldn't even be the default flags.
So either what you're defining here is a BinderPage, or new() needs
to take GFP flags.
On Tue, Feb 27, 2024 at 4:37 PM Matthew Wilcox <[email protected]> wrote:
>
> On Thu, Feb 08, 2024 at 03:47:54PM +0000, Alice Ryhl wrote:
> > +impl Page {
> > + /// Allocates a new page.
> > + pub fn new() -> Result<Self, AllocError> {
> > + // SAFETY: These are the correct arguments to allocate a single page.
> > + let page = unsafe {
> > + bindings::alloc_pages(
> > + bindings::GFP_KERNEL | bindings::__GFP_ZERO | bindings::__GFP_HIGHMEM,
>
> I thought I raised this last time, but this is over-specialised for
> Binder's purposes. Many places that want to allocate a page want
> different GFP flags from this; they shouldn't even be the default flags.
> So either what you're defining here is a BinderPage, or new() needs
> to take GFP flags.
Ah, yeah, sorry. I never got around to figuring that out.
I can change it to take GFP flags.
Thank you for taking another look!
Alice