diff options
Diffstat (limited to 'rust/kernel/str.rs')
| -rw-r--r-- | rust/kernel/str.rs | 529 |
1 files changed, 527 insertions, 2 deletions
diff --git a/rust/kernel/str.rs b/rust/kernel/str.rs index e45ff220ae50..874003e39cba 100644 --- a/rust/kernel/str.rs +++ b/rust/kernel/str.rs @@ -2,7 +2,383 @@ //! String representations. -use core::fmt; +use alloc::vec::Vec; +use core::fmt::{self, Write}; +use core::ops::{self, Deref, Index}; + +use crate::{bindings, error::code::*, Error}; + +/// Byte string without UTF-8 validity guarantee. +/// +/// `BStr` is simply an alias to `[u8]`, but has a more evident semantical meaning. +pub type BStr = [u8]; + +/// Creates a new [`BStr`] from a string literal. +/// +/// `b_str!` converts the supplied string literal to byte string, so non-ASCII +/// characters can be included. +/// +/// # Examples +/// +/// ``` +/// # use kernel::b_str; +/// # use kernel::str::BStr; +/// const MY_BSTR: &BStr = b_str!("My awesome BStr!"); +/// ``` +#[macro_export] +macro_rules! b_str { + ($str:literal) => {{ + const S: &'static str = $str; + const C: &'static $crate::str::BStr = S.as_bytes(); + C + }}; +} + +/// Possible errors when using conversion functions in [`CStr`]. +#[derive(Debug, Clone, Copy)] +pub enum CStrConvertError { + /// Supplied bytes contain an interior `NUL`. + InteriorNul, + + /// Supplied bytes are not terminated by `NUL`. + NotNulTerminated, +} + +impl From<CStrConvertError> for Error { + #[inline] + fn from(_: CStrConvertError) -> Error { + EINVAL + } +} + +/// A string that is guaranteed to have exactly one `NUL` byte, which is at the +/// end. +/// +/// Used for interoperability with kernel APIs that take C strings. +#[repr(transparent)] +pub struct CStr([u8]); + +impl CStr { + /// Returns the length of this string excluding `NUL`. + #[inline] + pub const fn len(&self) -> usize { + self.len_with_nul() - 1 + } + + /// Returns the length of this string with `NUL`. + #[inline] + pub const fn len_with_nul(&self) -> usize { + // SAFETY: This is one of the invariant of `CStr`. + // We add a `unreachable_unchecked` here to hint the optimizer that + // the value returned from this function is non-zero. + if self.0.is_empty() { + unsafe { core::hint::unreachable_unchecked() }; + } + self.0.len() + } + + /// Returns `true` if the string only includes `NUL`. + #[inline] + pub const fn is_empty(&self) -> bool { + self.len() == 0 + } + + /// Wraps a raw C string pointer. + /// + /// # Safety + /// + /// `ptr` must be a valid pointer to a `NUL`-terminated C string, and it must + /// last at least `'a`. When `CStr` is alive, the memory pointed by `ptr` + /// must not be mutated. + #[inline] + pub unsafe fn from_char_ptr<'a>(ptr: *const core::ffi::c_char) -> &'a Self { + // SAFETY: The safety precondition guarantees `ptr` is a valid pointer + // to a `NUL`-terminated C string. + let len = unsafe { bindings::strlen(ptr) } + 1; + // SAFETY: Lifetime guaranteed by the safety precondition. + let bytes = unsafe { core::slice::from_raw_parts(ptr as _, len as _) }; + // SAFETY: As `len` is returned by `strlen`, `bytes` does not contain interior `NUL`. + // As we have added 1 to `len`, the last byte is known to be `NUL`. + unsafe { Self::from_bytes_with_nul_unchecked(bytes) } + } + + /// Creates a [`CStr`] from a `[u8]`. + /// + /// The provided slice must be `NUL`-terminated, does not contain any + /// interior `NUL` bytes. + pub const fn from_bytes_with_nul(bytes: &[u8]) -> Result<&Self, CStrConvertError> { + if bytes.is_empty() { + return Err(CStrConvertError::NotNulTerminated); + } + if bytes[bytes.len() - 1] != 0 { + return Err(CStrConvertError::NotNulTerminated); + } + let mut i = 0; + // `i + 1 < bytes.len()` allows LLVM to optimize away bounds checking, + // while it couldn't optimize away bounds checks for `i < bytes.len() - 1`. + while i + 1 < bytes.len() { + if bytes[i] == 0 { + return Err(CStrConvertError::InteriorNul); + } + i += 1; + } + // SAFETY: We just checked that all properties hold. + Ok(unsafe { Self::from_bytes_with_nul_unchecked(bytes) }) + } + + /// Creates a [`CStr`] from a `[u8]`, panic if input is not valid. + /// + /// This function is only meant to be used by `c_str!` macro, so + /// crates using `c_str!` macro don't have to enable `const_panic` feature. + #[doc(hidden)] + pub const fn from_bytes_with_nul_unwrap(bytes: &[u8]) -> &Self { + match Self::from_bytes_with_nul(bytes) { + Ok(v) => v, + Err(_) => panic!("string contains interior NUL"), + } + } + + /// Creates a [`CStr`] from a `[u8]` without performing any additional + /// checks. + /// + /// # Safety + /// + /// `bytes` *must* end with a `NUL` byte, and should only have a single + /// `NUL` byte (or the string will be truncated). + #[inline] + pub const unsafe fn from_bytes_with_nul_unchecked(bytes: &[u8]) -> &CStr { + // SAFETY: Properties of `bytes` guaranteed by the safety precondition. + unsafe { core::mem::transmute(bytes) } + } + + /// Returns a C pointer to the string. + #[inline] + pub const fn as_char_ptr(&self) -> *const core::ffi::c_char { + self.0.as_ptr() as _ + } + + /// Convert the string to a byte slice without the trailing 0 byte. + #[inline] + pub fn as_bytes(&self) -> &[u8] { + &self.0[..self.len()] + } + + /// Convert the string to a byte slice containing the trailing 0 byte. + #[inline] + pub const fn as_bytes_with_nul(&self) -> &[u8] { + &self.0 + } + + /// Yields a [`&str`] slice if the [`CStr`] contains valid UTF-8. + /// + /// If the contents of the [`CStr`] are valid UTF-8 data, this + /// function will return the corresponding [`&str`] slice. Otherwise, + /// it will return an error with details of where UTF-8 validation failed. + /// + /// # Examples + /// + /// ``` + /// # use kernel::str::CStr; + /// let cstr = CStr::from_bytes_with_nul(b"foo\0").unwrap(); + /// assert_eq!(cstr.to_str(), Ok("foo")); + /// ``` + #[inline] + pub fn to_str(&self) -> Result<&str, core::str::Utf8Error> { + core::str::from_utf8(self.as_bytes()) + } + + /// Unsafely convert this [`CStr`] into a [`&str`], without checking for + /// valid UTF-8. + /// + /// # Safety + /// + /// The contents must be valid UTF-8. + /// + /// # Examples + /// + /// ``` + /// # use kernel::c_str; + /// # use kernel::str::CStr; + /// // SAFETY: String literals are guaranteed to be valid UTF-8 + /// // by the Rust compiler. + /// let bar = c_str!("ツ"); + /// assert_eq!(unsafe { bar.as_str_unchecked() }, "ツ"); + /// ``` + #[inline] + pub unsafe fn as_str_unchecked(&self) -> &str { + unsafe { core::str::from_utf8_unchecked(self.as_bytes()) } + } +} + +impl fmt::Display for CStr { + /// Formats printable ASCII characters, escaping the rest. + /// + /// ``` + /// # use kernel::c_str; + /// # use kernel::str::CStr; + /// # use kernel::str::CString; + /// let penguin = c_str!("🐧"); + /// let s = CString::try_from_fmt(fmt!("{}", penguin)).unwrap(); + /// assert_eq!(s.as_bytes_with_nul(), "\\xf0\\x9f\\x90\\xa7\0".as_bytes()); + /// + /// let ascii = c_str!("so \"cool\""); + /// let s = CString::try_from_fmt(fmt!("{}", ascii)).unwrap(); + /// assert_eq!(s.as_bytes_with_nul(), "so \"cool\"\0".as_bytes()); + /// ``` + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + for &c in self.as_bytes() { + if (0x20..0x7f).contains(&c) { + // Printable character. + f.write_char(c as char)?; + } else { + write!(f, "\\x{:02x}", c)?; + } + } + Ok(()) + } +} + +impl fmt::Debug for CStr { + /// Formats printable ASCII characters with a double quote on either end, escaping the rest. + /// + /// ``` + /// # use kernel::c_str; + /// # use kernel::str::CStr; + /// # use kernel::str::CString; + /// let penguin = c_str!("🐧"); + /// let s = CString::try_from_fmt(fmt!("{:?}", penguin)).unwrap(); + /// assert_eq!(s.as_bytes_with_nul(), "\"\\xf0\\x9f\\x90\\xa7\"\0".as_bytes()); + /// + /// // Embedded double quotes are escaped. + /// let ascii = c_str!("so \"cool\""); + /// let s = CString::try_from_fmt(fmt!("{:?}", ascii)).unwrap(); + /// assert_eq!(s.as_bytes_with_nul(), "\"so \\\"cool\\\"\"\0".as_bytes()); + /// ``` + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + f.write_str("\"")?; + for &c in self.as_bytes() { + match c { + // Printable characters. + b'\"' => f.write_str("\\\"")?, + 0x20..=0x7e => f.write_char(c as char)?, + _ => write!(f, "\\x{:02x}", c)?, + } + } + f.write_str("\"") + } +} + +impl AsRef<BStr> for CStr { + #[inline] + fn as_ref(&self) -> &BStr { + self.as_bytes() + } +} + +impl Deref for CStr { + type Target = BStr; + + #[inline] + fn deref(&self) -> &Self::Target { + self.as_bytes() + } +} + +impl Index<ops::RangeFrom<usize>> for CStr { + type Output = CStr; + + #[inline] + fn index(&self, index: ops::RangeFrom<usize>) -> &Self::Output { + // Delegate bounds checking to slice. + // Assign to _ to mute clippy's unnecessary operation warning. + let _ = &self.as_bytes()[index.start..]; + // SAFETY: We just checked the bounds. + unsafe { Self::from_bytes_with_nul_unchecked(&self.0[index.start..]) } + } +} + +impl Index<ops::RangeFull> for CStr { + type Output = CStr; + + #[inline] + fn index(&self, _index: ops::RangeFull) -> &Self::Output { + self + } +} + +mod private { + use core::ops; + + // Marker trait for index types that can be forward to `BStr`. + pub trait CStrIndex {} + + impl CStrIndex for usize {} + impl CStrIndex for ops::Range<usize> {} + impl CStrIndex for ops::RangeInclusive<usize> {} + impl CStrIndex for ops::RangeToInclusive<usize> {} +} + +impl<Idx> Index<Idx> for CStr +where + Idx: private::CStrIndex, + BStr: Index<Idx>, +{ + type Output = <BStr as Index<Idx>>::Output; + + #[inline] + fn index(&self, index: Idx) -> &Self::Output { + &self.as_bytes()[index] + } +} + +/// Creates a new [`CStr`] from a string literal. +/// +/// The string literal should not contain any `NUL` bytes. +/// +/// # Examples +/// +/// ``` +/// # use kernel::c_str; +/// # use kernel::str::CStr; +/// const MY_CSTR: &CStr = c_str!("My awesome CStr!"); +/// ``` +#[macro_export] +macro_rules! c_str { + ($str:expr) => {{ + const S: &str = concat!($str, "\0"); + const C: &$crate::str::CStr = $crate::str::CStr::from_bytes_with_nul_unwrap(S.as_bytes()); + C + }}; +} + +#[cfg(test)] +mod tests { + use super::*; + + #[test] + fn test_cstr_to_str() { + let good_bytes = b"\xf0\x9f\xa6\x80\0"; + let checked_cstr = CStr::from_bytes_with_nul(good_bytes).unwrap(); + let checked_str = checked_cstr.to_str().unwrap(); + assert_eq!(checked_str, "🦀"); + } + + #[test] + #[should_panic] + fn test_cstr_to_str_panic() { + let bad_bytes = b"\xc3\x28\0"; + let checked_cstr = CStr::from_bytes_with_nul(bad_bytes).unwrap(); + checked_cstr.to_str().unwrap(); + } + + #[test] + fn test_cstr_as_str_unchecked() { + let good_bytes = b"\xf0\x9f\x90\xA7\0"; + let checked_cstr = CStr::from_bytes_with_nul(good_bytes).unwrap(); + let unchecked_str = unsafe { checked_cstr.as_str_unchecked() }; + assert_eq!(unchecked_str, "🐧"); + } +} /// Allows formatting of [`fmt::Arguments`] into a raw buffer. /// @@ -15,13 +391,22 @@ use core::fmt; /// is less than `end`. pub(crate) struct RawFormatter { // Use `usize` to use `saturating_*` functions. - #[allow(dead_code)] beg: usize, pos: usize, end: usize, } impl RawFormatter { + /// Creates a new instance of [`RawFormatter`] with an empty buffer. + fn new() -> Self { + // INVARIANT: The buffer is empty, so the region that needs to be writable is empty. + Self { + beg: 0, + pos: 0, + end: 0, + } + } + /// Creates a new instance of [`RawFormatter`] with the given buffer pointers. /// /// # Safety @@ -37,12 +422,34 @@ impl RawFormatter { } } + /// Creates a new instance of [`RawFormatter`] with the given buffer. + /// + /// # Safety + /// + /// The memory region starting at `buf` and extending for `len` bytes must be valid for writes + /// for the lifetime of the returned [`RawFormatter`]. + pub(crate) unsafe fn from_buffer(buf: *mut u8, len: usize) -> Self { + let pos = buf as usize; + // INVARIANT: We ensure that `end` is never less then `buf`, and the safety requirements + // guarantees that the memory region is valid for writes. + Self { + pos, + beg: pos, + end: pos.saturating_add(len), + } + } + /// Returns the current insert position. /// /// N.B. It may point to invalid memory. pub(crate) fn pos(&self) -> *mut u8 { self.pos as _ } + + /// Return the number of bytes written to the formatter. + pub(crate) fn bytes_written(&self) -> usize { + self.pos - self.beg + } } impl fmt::Write for RawFormatter { @@ -70,3 +477,121 @@ impl fmt::Write for RawFormatter { Ok(()) } } + +/// Allows formatting of [`fmt::Arguments`] into a raw buffer. +/// +/// Fails if callers attempt to write more than will fit in the buffer. +pub(crate) struct Formatter(RawFormatter); + +impl Formatter { + /// Creates a new instance of [`Formatter`] with the given buffer. + /// + /// # Safety + /// + /// The memory region starting at `buf` and extending for `len` bytes must be valid for writes + /// for the lifetime of the returned [`Formatter`]. + pub(crate) unsafe fn from_buffer(buf: *mut u8, len: usize) -> Self { + // SAFETY: The safety requirements of this function satisfy those of the callee. + Self(unsafe { RawFormatter::from_buffer(buf, len) }) + } +} + +impl Deref for Formatter { + type Target = RawFormatter; + + fn deref(&self) -> &Self::Target { + &self.0 + } +} + +impl fmt::Write for Formatter { + fn write_str(&mut self, s: &str) -> fmt::Result { + self.0.write_str(s)?; + + // Fail the request if we go past the end of the buffer. + if self.0.pos > self.0.end { + Err(fmt::Error) + } else { + Ok(()) + } + } +} + +/// An owned string that is guaranteed to have exactly one `NUL` byte, which is at the end. +/// +/// Used for interoperability with kernel APIs that take C strings. +/// +/// # Invariants +/// +/// The string is always `NUL`-terminated and contains no other `NUL` bytes. +/// +/// # Examples +/// +/// ``` +/// use kernel::str::CString; +/// +/// let s = CString::try_from_fmt(fmt!("{}{}{}", "abc", 10, 20)).unwrap(); +/// assert_eq!(s.as_bytes_with_nul(), "abc1020\0".as_bytes()); +/// +/// let tmp = "testing"; +/// let s = CString::try_from_fmt(fmt!("{tmp}{}", 123)).unwrap(); +/// assert_eq!(s.as_bytes_with_nul(), "testing123\0".as_bytes()); +/// +/// // This fails because it has an embedded `NUL` byte. +/// let s = CString::try_from_fmt(fmt!("a\0b{}", 123)); +/// assert_eq!(s.is_ok(), false); +/// ``` +pub struct CString { + buf: Vec<u8>, +} + +impl CString { + /// Creates an instance of [`CString`] from the given formatted arguments. + pub fn try_from_fmt(args: fmt::Arguments<'_>) -> Result<Self, Error> { + // Calculate the size needed (formatted string plus `NUL` terminator). + let mut f = RawFormatter::new(); + f.write_fmt(args)?; + f.write_str("\0")?; + let size = f.bytes_written(); + + // Allocate a vector with the required number of bytes, and write to it. + let mut buf = Vec::try_with_capacity(size)?; + // SAFETY: The buffer stored in `buf` is at least of size `size` and is valid for writes. + let mut f = unsafe { Formatter::from_buffer(buf.as_mut_ptr(), size) }; + f.write_fmt(args)?; + f.write_str("\0")?; + + // SAFETY: The number of bytes that can be written to `f` is bounded by `size`, which is + // `buf`'s capacity. The contents of the buffer have been initialised by writes to `f`. + unsafe { buf.set_len(f.bytes_written()) }; + + // Check that there are no `NUL` bytes before the end. + // SAFETY: The buffer is valid for read because `f.bytes_written()` is bounded by `size` + // (which the minimum buffer size) and is non-zero (we wrote at least the `NUL` terminator) + // so `f.bytes_written() - 1` doesn't underflow. + let ptr = unsafe { bindings::memchr(buf.as_ptr().cast(), 0, (f.bytes_written() - 1) as _) }; + if !ptr.is_null() { + return Err(EINVAL); + } + + // INVARIANT: We wrote the `NUL` terminator and checked above that no other `NUL` bytes + // exist in the buffer. + Ok(Self { buf }) + } +} + +impl Deref for CString { + type Target = CStr; + + fn deref(&self) -> &Self::Target { + // SAFETY: The type invariants guarantee that the string is `NUL`-terminated and that no + // other `NUL` bytes exist. + unsafe { CStr::from_bytes_with_nul_unchecked(self.buf.as_slice()) } + } +} + +/// A convenience alias for [`core::format_args`]. +#[macro_export] +macro_rules! fmt { + ($($f:tt)*) => ( core::format_args!($($f)*) ) +} |