This patch adds a more convenient method for reading C strings from
userspace. Logic is added to NUL-terminate the buffer when necessary so
that a &CStr can be returned.

Note that we treat attempts to read past `self.length` as a fault, so
this returns EFAULT if that limit is exceeded before `buf.len()` is
reached.

Signed-off-by: Alice Ryhl <aliceryhl@google.com>
---
 rust/kernel/uaccess.rs | 53 +++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 52 insertions(+), 1 deletion(-)

diff --git a/rust/kernel/uaccess.rs b/rust/kernel/uaccess.rs
index a7b123915e9aa2329f376d67cad93e2fc17ae017..978205289d297a4001a51fa40ac29039bff73672 100644
--- a/rust/kernel/uaccess.rs
+++ b/rust/kernel/uaccess.rs
@@ -293,6 +293,58 @@ pub fn read_all<A: Allocator>(mut self, buf: &mut Vec<u8, A>, flags: Flags) -> R
         unsafe { buf.set_len(buf.len() + len) };
         Ok(())
     }
+
+    /// Read a NUL-terminated string from userspace and return it.
+    ///
+    /// The string is read into `buf` and a NUL-terminator is added if the end of `buf` is reached.
+    /// Since there must be space to add a NUL-terminator, the buffer must not be empty. The
+    /// returned `&CStr` points into `buf`.
+    ///
+    /// Fails with [`EFAULT`] if the read happens on a bad address (some data may have been
+    /// copied).
+    #[doc(alias = "strncpy_from_user")]
+    pub fn strcpy_into_buf<'buf>(self, buf: &'buf mut [u8]) -> Result<&'buf CStr> {
+        if buf.is_empty() {
+            return Err(EINVAL);
+        }
+
+        // SAFETY: The types are compatible and `strncpy_from_user` doesn't write uninitialized
+        // bytes to `buf`.
+        let mut dst = unsafe { &mut *(buf as *mut [u8] as *mut [MaybeUninit<u8>]) };
+
+        // We never read more than `self.length` bytes.
+        if dst.len() > self.length {
+            dst = &mut dst[..self.length];
+        }
+
+        let mut len = raw_strncpy_from_user(self.ptr, dst)?;
+        if len < dst.len() {
+            // Add one to include the NUL-terminator.
+            len += 1;
+        } else if len < buf.len() {
+            // This implies that len == dst.len() < buf.len().
+            //
+            // This means that we could not fill the entire buffer, but we had to stop reading
+            // because we hit the `self.length` limit of this `UserSliceReader`. Since we did not
+            // fill the buffer, we treat this case as if we tried to read past the `self.length`
+            // limit and received a page fault, which is consistent with other `UserSliceReader`
+            // methods that also return page faults when you exceed `self.length`.
+            return Err(EFAULT);
+        } else {
+            // This implies that len == buf.len().
+            //
+            // This means that we filled the buffer exactly. In this case, we add a NUL-terminator
+            // and return it. Unlike the `len < dst.len()` branch, don't modify `len` because it
+            // already represents the length including the NUL-terminator.
+            //
+            // SAFETY: Due to the check at the beginning, the buffer is not empty.
+            unsafe { *buf.last_mut().unwrap_unchecked() = 0 };
+        }
+
+        // SAFETY: `raw_strncpy_from_user` guarantees that this range of bytes represents a
+        // NUL-terminated string with the only NUL byte being at the end.
+        Ok(unsafe { CStr::from_bytes_with_nul_unchecked(&buf[..len]) })
+    }
 }
 
 /// A writer for [`UserSlice`].
@@ -383,7 +435,6 @@ pub fn write<T: AsBytes>(&mut self, value: &T) -> Result {
 /// initialized and non-zero. Furthermore, if `len < buf.len()`, then `buf[len]` is a NUL byte.
 /// Unsafe code may rely on these guarantees.
 #[inline]
-#[expect(dead_code)]
 fn raw_strncpy_from_user(ptr: UserPtr, buf: &mut [MaybeUninit<u8>]) -> Result<usize> {
     // CAST: Slice lengths are guaranteed to be `<= isize::MAX`.
     let len = buf.len() as isize;

-- 
2.49.0.967.g6a0df3ecc3-goog

On Mon, May 05, 2025 at 12:17:32PM +0000, Alice Ryhl wrote:
> +    /// Read a NUL-terminated string from userspace and return it.
> +    ///
> +    /// The string is read into `buf` and a NUL-terminator is added if the end of `buf` is reached.
> +    /// Since there must be space to add a NUL-terminator, the buffer must not be empty. The
> +    /// returned `&CStr` points into `buf`.
> +    ///
> +    /// Fails with [`EFAULT`] if the read happens on a bad address (some data may have been
> +    /// copied).
> +    #[doc(alias = "strncpy_from_user")]
> +    pub fn strcpy_into_buf<'buf>(self, buf: &'buf mut [u8]) -> Result<&'buf CStr> {
> +        if buf.is_empty() {
> +            return Err(EINVAL);
> +        }
> +
> +        // SAFETY: The types are compatible and `strncpy_from_user` doesn't write uninitialized
> +        // bytes to `buf`.
> +        let mut dst = unsafe { &mut *(buf as *mut [u8] as *mut [MaybeUninit<u8>]) };
> +
> +        // We never read more than `self.length` bytes.
> +        if dst.len() > self.length {
> +            dst = &mut dst[..self.length];
> +        }
> +
> +        let mut len = raw_strncpy_from_user(self.ptr, dst)?;
> +        if len < dst.len() {
> +            // Add one to include the NUL-terminator.
> +            len += 1;
> +        } else if len < buf.len() {
> +            // This implies that len == dst.len() < buf.len().
> +            //
> +            // This means that we could not fill the entire buffer, but we had to stop reading
> +            // because we hit the `self.length` limit of this `UserSliceReader`. Since we did not
> +            // fill the buffer, we treat this case as if we tried to read past the `self.length`
> +            // limit and received a page fault, which is consistent with other `UserSliceReader`
> +            // methods that also return page faults when you exceed `self.length`.
> +            return Err(EFAULT);
> +        } else {
> +            // This implies that len == buf.len().
> +            //
> +            // This means that we filled the buffer exactly. In this case, we add a NUL-terminator
> +            // and return it. Unlike the `len < dst.len()` branch, don't modify `len` because it
> +            // already represents the length including the NUL-terminator.
> +            //
> +            // SAFETY: Due to the check at the beginning, the buffer is not empty.
> +            unsafe { *buf.last_mut().unwrap_unchecked() = 0 };
> +        }
> +
> +        // SAFETY: `raw_strncpy_from_user` guarantees that this range of bytes represents a
> +        // NUL-terminated string with the only NUL byte being at the end.

This isn't true if we hit the else case above, no?

With that fixed,

	Reviewed-by: Danilo Krummrich <dakr@kernel.org>

On Mon, May 05, 2025 at 06:22:31PM +0200, Danilo Krummrich wrote:
> On Mon, May 05, 2025 at 12:17:32PM +0000, Alice Ryhl wrote:
> > +    /// Read a NUL-terminated string from userspace and return it.
> > +    ///
> > +    /// The string is read into `buf` and a NUL-terminator is added if the end of `buf` is reached.
> > +    /// Since there must be space to add a NUL-terminator, the buffer must not be empty. The
> > +    /// returned `&CStr` points into `buf`.
> > +    ///
> > +    /// Fails with [`EFAULT`] if the read happens on a bad address (some data may have been
> > +    /// copied).
> > +    #[doc(alias = "strncpy_from_user")]
> > +    pub fn strcpy_into_buf<'buf>(self, buf: &'buf mut [u8]) -> Result<&'buf CStr> {
> > +        if buf.is_empty() {
> > +            return Err(EINVAL);
> > +        }
> > +
> > +        // SAFETY: The types are compatible and `strncpy_from_user` doesn't write uninitialized
> > +        // bytes to `buf`.
> > +        let mut dst = unsafe { &mut *(buf as *mut [u8] as *mut [MaybeUninit<u8>]) };
> > +
> > +        // We never read more than `self.length` bytes.
> > +        if dst.len() > self.length {
> > +            dst = &mut dst[..self.length];
> > +        }
> > +
> > +        let mut len = raw_strncpy_from_user(self.ptr, dst)?;
> > +        if len < dst.len() {
> > +            // Add one to include the NUL-terminator.
> > +            len += 1;
> > +        } else if len < buf.len() {
> > +            // This implies that len == dst.len() < buf.len().
> > +            //
> > +            // This means that we could not fill the entire buffer, but we had to stop reading
> > +            // because we hit the `self.length` limit of this `UserSliceReader`. Since we did not
> > +            // fill the buffer, we treat this case as if we tried to read past the `self.length`
> > +            // limit and received a page fault, which is consistent with other `UserSliceReader`
> > +            // methods that also return page faults when you exceed `self.length`.
> > +            return Err(EFAULT);
> > +        } else {
> > +            // This implies that len == buf.len().
> > +            //
> > +            // This means that we filled the buffer exactly. In this case, we add a NUL-terminator
> > +            // and return it. Unlike the `len < dst.len()` branch, don't modify `len` because it
> > +            // already represents the length including the NUL-terminator.
> > +            //
> > +            // SAFETY: Due to the check at the beginning, the buffer is not empty.
> > +            unsafe { *buf.last_mut().unwrap_unchecked() = 0 };
> > +        }
> > +
> > +        // SAFETY: `raw_strncpy_from_user` guarantees that this range of bytes represents a
> > +        // NUL-terminated string with the only NUL byte being at the end.
> 
> This isn't true if we hit the else case above, no?
> 
> With that fixed,
> 
> 	Reviewed-by: Danilo Krummrich <dakr@kernel.org>

I guess the wording is a bit off. I will update to this:

// SAFETY: There are two cases:
// * If we hit the `len < dst.len()` case, then `raw_strncpy_from_user`
//   guarantees that this slice contains exactly one NUL byte at the end
//   of the string.
// * Otherwise, `raw_strncpy_from_user` guarantees that the string
//   contained no NUL bytes, and we have since added a NUL byte at the
//   end.

Alice