diff options
Diffstat (limited to 'rust/kernel/str.rs')
| -rw-r--r-- | rust/kernel/str.rs | 816 |
1 files changed, 544 insertions, 272 deletions
diff --git a/rust/kernel/str.rs b/rust/kernel/str.rs index c9dd3bf59e34..fa87779d2253 100644 --- a/rust/kernel/str.rs +++ b/rust/kernel/str.rs @@ -2,20 +2,166 @@ //! String representations. -use alloc::alloc::AllocError; -use alloc::vec::Vec; -use core::fmt::{self, Write}; -use core::ops::{self, Deref, Index}; - use crate::{ - bindings, - error::{code::*, Error}, + alloc::{flags::*, AllocError, KVec}, + error::{to_result, Result}, + fmt::{self, Write}, + prelude::*, +}; +use core::{ + marker::PhantomData, + ops::{Deref, DerefMut, Index}, }; +pub use crate::prelude::CStr; + +pub mod parse_int; + /// 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]; +#[repr(transparent)] +pub struct BStr([u8]); + +impl BStr { + /// Returns the length of this string. + #[inline] + pub const fn len(&self) -> usize { + self.0.len() + } + + /// Returns `true` if the string is empty. + #[inline] + pub const fn is_empty(&self) -> bool { + self.len() == 0 + } + + /// Creates a [`BStr`] from a `[u8]`. + #[inline] + pub const fn from_bytes(bytes: &[u8]) -> &Self { + // SAFETY: `BStr` is transparent to `[u8]`. + unsafe { &*(core::ptr::from_ref(bytes) as *const BStr) } + } + + /// Strip a prefix from `self`. Delegates to [`slice::strip_prefix`]. + /// + /// # Examples + /// + /// ``` + /// # use kernel::b_str; + /// assert_eq!(Some(b_str!("bar")), b_str!("foobar").strip_prefix(b_str!("foo"))); + /// assert_eq!(None, b_str!("foobar").strip_prefix(b_str!("bar"))); + /// assert_eq!(Some(b_str!("foobar")), b_str!("foobar").strip_prefix(b_str!(""))); + /// assert_eq!(Some(b_str!("")), b_str!("foobar").strip_prefix(b_str!("foobar"))); + /// ``` + pub fn strip_prefix(&self, pattern: impl AsRef<Self>) -> Option<&BStr> { + self.deref() + .strip_prefix(pattern.as_ref().deref()) + .map(Self::from_bytes) + } +} + +impl fmt::Display for BStr { + /// Formats printable ASCII characters, escaping the rest. + /// + /// ``` + /// # use kernel::{prelude::fmt, b_str, str::{BStr, CString}}; + /// let ascii = b_str!("Hello, BStr!"); + /// let s = CString::try_from_fmt(fmt!("{ascii}"))?; + /// assert_eq!(s.to_bytes(), "Hello, BStr!".as_bytes()); + /// + /// let non_ascii = b_str!("🦀"); + /// let s = CString::try_from_fmt(fmt!("{non_ascii}"))?; + /// assert_eq!(s.to_bytes(), "\\xf0\\x9f\\xa6\\x80".as_bytes()); + /// # Ok::<(), kernel::error::Error>(()) + /// ``` + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + for &b in &self.0 { + match b { + // Common escape codes. + b'\t' => f.write_str("\\t")?, + b'\n' => f.write_str("\\n")?, + b'\r' => f.write_str("\\r")?, + // Printable characters. + 0x20..=0x7e => f.write_char(b as char)?, + _ => write!(f, "\\x{b:02x}")?, + } + } + Ok(()) + } +} + +impl fmt::Debug for BStr { + /// Formats printable ASCII characters with a double quote on either end, + /// escaping the rest. + /// + /// ``` + /// # use kernel::{prelude::fmt, b_str, str::{BStr, CString}}; + /// // Embedded double quotes are escaped. + /// let ascii = b_str!("Hello, \"BStr\"!"); + /// let s = CString::try_from_fmt(fmt!("{ascii:?}"))?; + /// assert_eq!(s.to_bytes(), "\"Hello, \\\"BStr\\\"!\"".as_bytes()); + /// + /// let non_ascii = b_str!("😺"); + /// let s = CString::try_from_fmt(fmt!("{non_ascii:?}"))?; + /// assert_eq!(s.to_bytes(), "\"\\xf0\\x9f\\x98\\xba\"".as_bytes()); + /// # Ok::<(), kernel::error::Error>(()) + /// ``` + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + f.write_char('"')?; + for &b in &self.0 { + match b { + // Common escape codes. + b'\t' => f.write_str("\\t")?, + b'\n' => f.write_str("\\n")?, + b'\r' => f.write_str("\\r")?, + // String escape characters. + b'\"' => f.write_str("\\\"")?, + b'\\' => f.write_str("\\\\")?, + // Printable characters. + 0x20..=0x7e => f.write_char(b as char)?, + _ => write!(f, "\\x{b:02x}")?, + } + } + f.write_char('"') + } +} + +impl Deref for BStr { + type Target = [u8]; + + #[inline] + fn deref(&self) -> &Self::Target { + &self.0 + } +} + +impl PartialEq for BStr { + fn eq(&self, other: &Self) -> bool { + self.deref().eq(other.deref()) + } +} + +impl<Idx> Index<Idx> for BStr +where + [u8]: Index<Idx, Output = [u8]>, +{ + type Output = Self; + + fn index(&self, index: Idx) -> &Self::Output { + BStr::from_bytes(&self.0[index]) + } +} + +impl AsRef<BStr> for [u8] { + fn as_ref(&self) -> &BStr { + BStr::from_bytes(self) + } +} + +impl AsRef<BStr> for BStr { + fn as_ref(&self) -> &BStr { + self + } +} /// Creates a new [`BStr`] from a string literal. /// @@ -33,60 +179,28 @@ pub type BStr = [u8]; macro_rules! b_str { ($str:literal) => {{ const S: &'static str = $str; - const C: &'static $crate::str::BStr = S.as_bytes(); + const C: &'static $crate::str::BStr = $crate::str::BStr::from_bytes(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 - } +/// Returns a C pointer to the string. +// It is a free function rather than a method on an extension trait because: +// +// - error[E0379]: functions in trait impls cannot be declared const +#[inline] +pub const fn as_char_ptr_in_const_context(c_str: &CStr) -> *const c_char { + c_str.as_ptr().cast() } -/// 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() - } +mod private { + pub trait Sealed {} - /// Returns `true` if the string only includes `NUL`. - #[inline] - pub const fn is_empty(&self) -> bool { - self.len() == 0 - } + impl Sealed for super::CStr {} +} +/// Extensions to [`CStr`]. +pub trait CStrExt: private::Sealed { /// Wraps a raw C string pointer. /// /// # Safety @@ -94,238 +208,171 @@ impl CStr { /// `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) }) - } + // This function exists to paper over the fact that `CStr::from_ptr` takes a `*const + // core::ffi::c_char` rather than a `*const crate::ffi::c_char`. + unsafe fn from_char_ptr<'a>(ptr: *const c_char) -> &'a Self; - /// Creates a [`CStr`] from a `[u8]` without performing any additional - /// checks. + /// Creates a mutable [`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) } - } + unsafe fn from_bytes_with_nul_unchecked_mut(bytes: &mut [u8]) -> &mut Self; /// 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 _ - } + // This function exists to paper over the fact that `CStr::as_ptr` returns a `*const + // core::ffi::c_char` rather than a `*const crate::ffi::c_char`. + fn as_char_ptr(&self) -> *const c_char; - /// 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 - } + /// Convert this [`CStr`] into a [`CString`] by allocating memory and + /// copying over the string data. + fn to_cstring(&self) -> Result<CString, AllocError>; - /// Yields a [`&str`] slice if the [`CStr`] contains valid UTF-8. + /// Converts this [`CStr`] to its ASCII lower case equivalent in-place. /// - /// 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. + /// ASCII letters 'A' to 'Z' are mapped to 'a' to 'z', + /// but non-ASCII letters are unchanged. /// - /// # Examples + /// To return a new lowercased value without modifying the existing one, use + /// [`to_ascii_lowercase()`]. /// - /// ``` - /// # 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()) - } + /// [`to_ascii_lowercase()`]: #method.to_ascii_lowercase + fn make_ascii_lowercase(&mut self); - /// Unsafely convert this [`CStr`] into a [`&str`], without checking for - /// valid UTF-8. + /// Converts this [`CStr`] to its ASCII upper case equivalent in-place. /// - /// # Safety + /// ASCII letters 'a' to 'z' are mapped to 'A' to 'Z', + /// but non-ASCII letters are unchanged. /// - /// The contents must be valid UTF-8. + /// To return a new uppercased value without modifying the existing one, use + /// [`to_ascii_uppercase()`]. /// - /// # Examples + /// [`to_ascii_uppercase()`]: #method.to_ascii_uppercase + fn make_ascii_uppercase(&mut self); + + /// Returns a copy of this [`CString`] where each character is mapped to its + /// ASCII lower case equivalent. /// - /// ``` - /// # 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()) } - } + /// ASCII letters 'A' to 'Z' are mapped to 'a' to 'z', + /// but non-ASCII letters are unchanged. + /// + /// To lowercase the value in-place, use [`make_ascii_lowercase`]. + /// + /// [`make_ascii_lowercase`]: str::make_ascii_lowercase + fn to_ascii_lowercase(&self) -> Result<CString, AllocError>; - /// Convert this [`CStr`] into a [`CString`] by allocating memory and - /// copying over the string data. - pub fn to_cstring(&self) -> Result<CString, AllocError> { - CString::try_from(self) - } + /// Returns a copy of this [`CString`] where each character is mapped to its + /// ASCII upper case equivalent. + /// + /// ASCII letters 'a' to 'z' are mapped to 'A' to 'Z', + /// but non-ASCII letters are unchanged. + /// + /// To uppercase the value in-place, use [`make_ascii_uppercase`]. + /// + /// [`make_ascii_uppercase`]: str::make_ascii_uppercase + fn to_ascii_uppercase(&self) -> Result<CString, AllocError>; } impl fmt::Display for CStr { /// Formats printable ASCII characters, escaping the rest. /// /// ``` - /// # use kernel::c_str; + /// # use kernel::prelude::fmt; /// # 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 penguin = c"🐧"; + /// let s = CString::try_from_fmt(fmt!("{penguin}"))?; + /// assert_eq!(s.to_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()); + /// let ascii = c"so \"cool\""; + /// let s = CString::try_from_fmt(fmt!("{ascii}"))?; + /// assert_eq!(s.to_bytes_with_nul(), "so \"cool\"\0".as_bytes()); + /// # Ok::<(), kernel::error::Error>(()) /// ``` fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { - for &c in self.as_bytes() { + for &c in self.to_bytes() { if (0x20..0x7f).contains(&c) { // Printable character. f.write_char(c as char)?; } else { - write!(f, "\\x{:02x}", c)?; + write!(f, "\\x{c:02x}")?; } } 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("\"") - } +/// Converts a mutable C string to a mutable byte slice. +/// +/// # Safety +/// +/// The caller must ensure that the slice ends in a NUL byte and contains no other NUL bytes before +/// the borrow ends and the underlying [`CStr`] is used. +unsafe fn to_bytes_mut(s: &mut CStr) -> &mut [u8] { + // SAFETY: the cast from `&CStr` to `&[u8]` is safe since `CStr` has the same layout as `&[u8]` + // (this is technically not guaranteed, but we rely on it here). The pointer dereference is + // safe since it comes from a mutable reference which is guaranteed to be valid for writes. + unsafe { &mut *(core::ptr::from_mut(s) as *mut [u8]) } } -impl AsRef<BStr> for CStr { +impl CStrExt for CStr { #[inline] - fn as_ref(&self) -> &BStr { - self.as_bytes() + unsafe fn from_char_ptr<'a>(ptr: *const c_char) -> &'a Self { + // SAFETY: The safety preconditions are the same as for `CStr::from_ptr`. + unsafe { CStr::from_ptr(ptr.cast()) } } -} -impl Deref for CStr { - type Target = BStr; + #[inline] + unsafe fn from_bytes_with_nul_unchecked_mut(bytes: &mut [u8]) -> &mut Self { + // SAFETY: the cast from `&[u8]` to `&CStr` is safe since the properties of `bytes` are + // guaranteed by the safety precondition and `CStr` has the same layout as `&[u8]` (this is + // technically not guaranteed, but we rely on it here). The pointer dereference is safe + // since it comes from a mutable reference which is guaranteed to be valid for writes. + unsafe { &mut *(core::ptr::from_mut(bytes) as *mut CStr) } + } #[inline] - fn deref(&self) -> &Self::Target { - self.as_bytes() + fn as_char_ptr(&self) -> *const c_char { + self.as_ptr().cast() } -} -impl Index<ops::RangeFrom<usize>> for CStr { - type Output = CStr; + fn to_cstring(&self) -> Result<CString, AllocError> { + CString::try_from(self) + } - #[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..]) } + fn make_ascii_lowercase(&mut self) { + // SAFETY: This doesn't introduce or remove NUL bytes in the C string. + unsafe { to_bytes_mut(self) }.make_ascii_lowercase(); } -} -impl Index<ops::RangeFull> for CStr { - type Output = CStr; + fn make_ascii_uppercase(&mut self) { + // SAFETY: This doesn't introduce or remove NUL bytes in the C string. + unsafe { to_bytes_mut(self) }.make_ascii_uppercase(); + } - #[inline] - fn index(&self, _index: ops::RangeFull) -> &Self::Output { - self + fn to_ascii_lowercase(&self) -> Result<CString, AllocError> { + let mut s = self.to_cstring()?; + + s.make_ascii_lowercase(); + + Ok(s) } -} -mod private { - use core::ops; + fn to_ascii_uppercase(&self) -> Result<CString, AllocError> { + let mut s = self.to_cstring()?; - // Marker trait for index types that can be forward to `BStr`. - pub trait CStrIndex {} + s.make_ascii_uppercase(); - impl CStrIndex for usize {} - impl CStrIndex for ops::Range<usize> {} - impl CStrIndex for ops::RangeInclusive<usize> {} - impl CStrIndex for ops::RangeToInclusive<usize> {} + Ok(s) + } } -impl<Idx> Index<Idx> for CStr -where - Idx: private::CStrIndex, - BStr: Index<Idx>, -{ - type Output = <BStr as Index<Idx>>::Output; - +impl AsRef<BStr> for CStr { #[inline] - fn index(&self, index: Idx) -> &Self::Output { - &self.as_bytes()[index] + fn as_ref(&self) -> &BStr { + BStr::from_bytes(self.to_bytes()) } } @@ -352,32 +399,116 @@ macro_rules! c_str { }}; } -#[cfg(test)] +#[kunit_tests(rust_kernel_str)] mod tests { use super::*; + impl From<core::ffi::FromBytesWithNulError> for Error { + #[inline] + fn from(_: core::ffi::FromBytesWithNulError) -> Error { + EINVAL + } + } + + macro_rules! format { + ($($f:tt)*) => ({ + CString::try_from_fmt(fmt!($($f)*))?.to_str()? + }) + } + + const ALL_ASCII_CHARS: &str = + "\\x01\\x02\\x03\\x04\\x05\\x06\\x07\\x08\\x09\\x0a\\x0b\\x0c\\x0d\\x0e\\x0f\ + \\x10\\x11\\x12\\x13\\x14\\x15\\x16\\x17\\x18\\x19\\x1a\\x1b\\x1c\\x1d\\x1e\\x1f \ + !\"#$%&'()*+,-./0123456789:;<=>?@\ + ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\\x7f\ + \\x80\\x81\\x82\\x83\\x84\\x85\\x86\\x87\\x88\\x89\\x8a\\x8b\\x8c\\x8d\\x8e\\x8f\ + \\x90\\x91\\x92\\x93\\x94\\x95\\x96\\x97\\x98\\x99\\x9a\\x9b\\x9c\\x9d\\x9e\\x9f\ + \\xa0\\xa1\\xa2\\xa3\\xa4\\xa5\\xa6\\xa7\\xa8\\xa9\\xaa\\xab\\xac\\xad\\xae\\xaf\ + \\xb0\\xb1\\xb2\\xb3\\xb4\\xb5\\xb6\\xb7\\xb8\\xb9\\xba\\xbb\\xbc\\xbd\\xbe\\xbf\ + \\xc0\\xc1\\xc2\\xc3\\xc4\\xc5\\xc6\\xc7\\xc8\\xc9\\xca\\xcb\\xcc\\xcd\\xce\\xcf\ + \\xd0\\xd1\\xd2\\xd3\\xd4\\xd5\\xd6\\xd7\\xd8\\xd9\\xda\\xdb\\xdc\\xdd\\xde\\xdf\ + \\xe0\\xe1\\xe2\\xe3\\xe4\\xe5\\xe6\\xe7\\xe8\\xe9\\xea\\xeb\\xec\\xed\\xee\\xef\ + \\xf0\\xf1\\xf2\\xf3\\xf4\\xf5\\xf6\\xf7\\xf8\\xf9\\xfa\\xfb\\xfc\\xfd\\xfe\\xff"; + #[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(); + fn test_cstr_to_str() -> Result { + let cstr = c"\xf0\x9f\xa6\x80"; + let checked_str = cstr.to_str()?; assert_eq!(checked_str, "🦀"); + Ok(()) + } + + #[test] + fn test_cstr_to_str_invalid_utf8() -> Result { + let cstr = c"\xc3\x28"; + assert!(cstr.to_str().is_err()); + Ok(()) + } + + #[test] + fn test_cstr_display() -> Result { + let hello_world = c"hello, world!"; + assert_eq!(format!("{hello_world}"), "hello, world!"); + let non_printables = c"\x01\x09\x0a"; + assert_eq!(format!("{non_printables}"), "\\x01\\x09\\x0a"); + let non_ascii = c"d\xe9j\xe0 vu"; + assert_eq!(format!("{non_ascii}"), "d\\xe9j\\xe0 vu"); + let good_bytes = c"\xf0\x9f\xa6\x80"; + assert_eq!(format!("{good_bytes}"), "\\xf0\\x9f\\xa6\\x80"); + Ok(()) + } + + #[test] + fn test_cstr_display_all_bytes() -> Result { + let mut bytes: [u8; 256] = [0; 256]; + // fill `bytes` with [1..=255] + [0] + for i in u8::MIN..=u8::MAX { + bytes[i as usize] = i.wrapping_add(1); + } + let cstr = CStr::from_bytes_with_nul(&bytes)?; + assert_eq!(format!("{cstr}"), ALL_ASCII_CHARS); + Ok(()) + } + + #[test] + fn test_cstr_debug() -> Result { + let hello_world = c"hello, world!"; + assert_eq!(format!("{hello_world:?}"), "\"hello, world!\""); + let non_printables = c"\x01\x09\x0a"; + assert_eq!(format!("{non_printables:?}"), "\"\\x01\\t\\n\""); + let non_ascii = c"d\xe9j\xe0 vu"; + assert_eq!(format!("{non_ascii:?}"), "\"d\\xe9j\\xe0 vu\""); + Ok(()) } #[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(); + fn test_bstr_display() -> Result { + let hello_world = BStr::from_bytes(b"hello, world!"); + assert_eq!(format!("{hello_world}"), "hello, world!"); + let escapes = BStr::from_bytes(b"_\t_\n_\r_\\_\'_\"_"); + assert_eq!(format!("{escapes}"), "_\\t_\\n_\\r_\\_'_\"_"); + let others = BStr::from_bytes(b"\x01"); + assert_eq!(format!("{others}"), "\\x01"); + let non_ascii = BStr::from_bytes(b"d\xe9j\xe0 vu"); + assert_eq!(format!("{non_ascii}"), "d\\xe9j\\xe0 vu"); + let good_bytes = BStr::from_bytes(b"\xf0\x9f\xa6\x80"); + assert_eq!(format!("{good_bytes}"), "\\xf0\\x9f\\xa6\\x80"); + Ok(()) } #[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, "🐧"); + fn test_bstr_debug() -> Result { + let hello_world = BStr::from_bytes(b"hello, world!"); + assert_eq!(format!("{hello_world:?}"), "\"hello, world!\""); + let escapes = BStr::from_bytes(b"_\t_\n_\r_\\_\'_\"_"); + assert_eq!(format!("{escapes:?}"), "\"_\\t_\\n_\\r_\\\\_'_\\\"_\""); + let others = BStr::from_bytes(b"\x01"); + assert_eq!(format!("{others:?}"), "\"\\x01\""); + let non_ascii = BStr::from_bytes(b"d\xe9j\xe0 vu"); + assert_eq!(format!("{non_ascii:?}"), "\"d\\xe9j\\xe0 vu\""); + let good_bytes = BStr::from_bytes(b"\xf0\x9f\xa6\x80"); + assert_eq!(format!("{good_bytes:?}"), "\"\\xf0\\x9f\\xa6\\x80\""); + Ok(()) } } @@ -390,7 +521,7 @@ mod tests { /// /// The memory region between `pos` (inclusive) and `end` (exclusive) is valid for writes if `pos` /// is less than `end`. -pub(crate) struct RawFormatter { +pub struct RawFormatter { // Use `usize` to use `saturating_*` functions. beg: usize, pos: usize, @@ -417,9 +548,9 @@ impl RawFormatter { pub(crate) unsafe fn from_ptrs(pos: *mut u8, end: *mut u8) -> Self { // INVARIANT: The safety requirements guarantee the type invariants. Self { - beg: pos as _, - pos: pos as _, - end: end as _, + beg: pos as usize, + pos: pos as usize, + end: end as usize, } } @@ -431,7 +562,7 @@ impl RawFormatter { /// 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 + // INVARIANT: We ensure that `end` is never less than `buf`, and the safety requirements // guarantees that the memory region is valid for writes. Self { pos, @@ -444,11 +575,11 @@ impl RawFormatter { /// /// N.B. It may point to invalid memory. pub(crate) fn pos(&self) -> *mut u8 { - self.pos as _ + self.pos as *mut u8 } - /// Return the number of bytes written to the formatter. - pub(crate) fn bytes_written(&self) -> usize { + /// Returns the number of bytes written to the formatter. + pub fn bytes_written(&self) -> usize { self.pos - self.beg } } @@ -482,9 +613,9 @@ impl fmt::Write for RawFormatter { /// 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); +pub struct Formatter<'a>(RawFormatter, PhantomData<&'a mut ()>); -impl Formatter { +impl Formatter<'_> { /// Creates a new instance of [`Formatter`] with the given buffer. /// /// # Safety @@ -493,11 +624,18 @@ impl Formatter { /// 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) }) + Self(unsafe { RawFormatter::from_buffer(buf, len) }, PhantomData) + } + + /// Create a new [`Self`] instance. + pub fn new(buffer: &mut [u8]) -> Self { + // SAFETY: `buffer` is valid for writes for the entire length for + // the lifetime of `Self`. + unsafe { Formatter::from_buffer(buffer.as_mut_ptr(), buffer.len()) } } } -impl Deref for Formatter { +impl Deref for Formatter<'_> { type Target = RawFormatter; fn deref(&self) -> &Self::Target { @@ -505,7 +643,7 @@ impl Deref for Formatter { } } -impl fmt::Write for Formatter { +impl fmt::Write for Formatter<'_> { fn write_str(&mut self, s: &str) -> fmt::Result { self.0.write_str(s)?; @@ -518,6 +656,132 @@ impl fmt::Write for Formatter { } } +/// A mutable reference to a byte buffer where a string can be written into. +/// +/// The buffer will be automatically null terminated after the last written character. +/// +/// # Invariants +/// +/// * The first byte of `buffer` is always zero. +/// * The length of `buffer` is at least 1. +pub(crate) struct NullTerminatedFormatter<'a> { + buffer: &'a mut [u8], +} + +impl<'a> NullTerminatedFormatter<'a> { + /// Create a new [`Self`] instance. + pub(crate) fn new(buffer: &'a mut [u8]) -> Option<NullTerminatedFormatter<'a>> { + *(buffer.first_mut()?) = 0; + + // INVARIANT: + // - We wrote zero to the first byte above. + // - If buffer was not at least length 1, `buffer.first_mut()` would return None. + Some(Self { buffer }) + } +} + +impl Write for NullTerminatedFormatter<'_> { + fn write_str(&mut self, s: &str) -> fmt::Result { + let bytes = s.as_bytes(); + let len = bytes.len(); + + // We want space for a zero. By type invariant, buffer length is always at least 1, so no + // underflow. + if len > self.buffer.len() - 1 { + return Err(fmt::Error); + } + + let buffer = core::mem::take(&mut self.buffer); + // We break the zero start invariant for a short while. + buffer[..len].copy_from_slice(bytes); + // INVARIANT: We checked above that buffer will have size at least 1 after this assignment. + self.buffer = &mut buffer[len..]; + + // INVARIANT: We write zero to the first byte of the buffer. + self.buffer[0] = 0; + + Ok(()) + } +} + +/// # Safety +/// +/// - `string` must point to a null terminated string that is valid for read. +unsafe fn kstrtobool_raw(string: *const u8) -> Result<bool> { + let mut result: bool = false; + + // SAFETY: + // - By function safety requirement, `string` is a valid null-terminated string. + // - `result` is a valid `bool` that we own. + to_result(unsafe { bindings::kstrtobool(string, &mut result) })?; + Ok(result) +} + +/// Convert common user inputs into boolean values using the kernel's `kstrtobool` function. +/// +/// This routine returns `Ok(bool)` if the first character is one of 'YyTt1NnFf0', or +/// \[oO\]\[NnFf\] for "on" and "off". Otherwise it will return `Err(EINVAL)`. +/// +/// # Examples +/// +/// ``` +/// # use kernel::str::kstrtobool; +/// +/// // Lowercase +/// assert_eq!(kstrtobool(c"true"), Ok(true)); +/// assert_eq!(kstrtobool(c"tr"), Ok(true)); +/// assert_eq!(kstrtobool(c"t"), Ok(true)); +/// assert_eq!(kstrtobool(c"twrong"), Ok(true)); +/// assert_eq!(kstrtobool(c"false"), Ok(false)); +/// assert_eq!(kstrtobool(c"f"), Ok(false)); +/// assert_eq!(kstrtobool(c"yes"), Ok(true)); +/// assert_eq!(kstrtobool(c"no"), Ok(false)); +/// assert_eq!(kstrtobool(c"on"), Ok(true)); +/// assert_eq!(kstrtobool(c"off"), Ok(false)); +/// +/// // Camel case +/// assert_eq!(kstrtobool(c"True"), Ok(true)); +/// assert_eq!(kstrtobool(c"False"), Ok(false)); +/// assert_eq!(kstrtobool(c"Yes"), Ok(true)); +/// assert_eq!(kstrtobool(c"No"), Ok(false)); +/// assert_eq!(kstrtobool(c"On"), Ok(true)); +/// assert_eq!(kstrtobool(c"Off"), Ok(false)); +/// +/// // All caps +/// assert_eq!(kstrtobool(c"TRUE"), Ok(true)); +/// assert_eq!(kstrtobool(c"FALSE"), Ok(false)); +/// assert_eq!(kstrtobool(c"YES"), Ok(true)); +/// assert_eq!(kstrtobool(c"NO"), Ok(false)); +/// assert_eq!(kstrtobool(c"ON"), Ok(true)); +/// assert_eq!(kstrtobool(c"OFF"), Ok(false)); +/// +/// // Numeric +/// assert_eq!(kstrtobool(c"1"), Ok(true)); +/// assert_eq!(kstrtobool(c"0"), Ok(false)); +/// +/// // Invalid input +/// assert_eq!(kstrtobool(c"invalid"), Err(EINVAL)); +/// assert_eq!(kstrtobool(c"2"), Err(EINVAL)); +/// ``` +pub fn kstrtobool(string: &CStr) -> Result<bool> { + // SAFETY: + // - The pointer returned by `CStr::as_char_ptr` is guaranteed to be + // null terminated. + // - `string` is live and thus the string is valid for read. + unsafe { kstrtobool_raw(string.as_char_ptr()) } +} + +/// Convert `&[u8]` to `bool` by deferring to [`kernel::str::kstrtobool`]. +/// +/// Only considers at most the first two bytes of `bytes`. +pub fn kstrtobool_bytes(bytes: &[u8]) -> Result<bool> { + // `ktostrbool` only considers the first two bytes of the input. + let stack_string = [*bytes.first().unwrap_or(&0), *bytes.get(1).unwrap_or(&0), 0]; + // SAFETY: `stack_string` is null terminated and it is live on the stack so + // it is valid for read. + unsafe { kstrtobool_raw(stack_string.as_ptr()) } +} + /// 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. @@ -529,21 +793,22 @@ impl fmt::Write for Formatter { /// # Examples /// /// ``` -/// use kernel::str::CString; +/// use kernel::{str::CString, prelude::fmt}; /// -/// let s = CString::try_from_fmt(fmt!("{}{}{}", "abc", 10, 20)).unwrap(); -/// assert_eq!(s.as_bytes_with_nul(), "abc1020\0".as_bytes()); +/// let s = CString::try_from_fmt(fmt!("{}{}{}", "abc", 10, 20))?; +/// assert_eq!(s.to_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()); +/// let s = CString::try_from_fmt(fmt!("{tmp}{}", 123))?; +/// assert_eq!(s.to_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); +/// # Ok::<(), kernel::error::Error>(()) /// ``` pub struct CString { - buf: Vec<u8>, + buf: KVec<u8>, } impl CString { @@ -556,7 +821,7 @@ impl CString { 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)?; + let mut buf = KVec::with_capacity(size, GFP_KERNEL)?; // 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)?; @@ -564,13 +829,13 @@ impl CString { // 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()) }; + unsafe { buf.inc_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 _) }; + let ptr = unsafe { bindings::memchr(buf.as_ptr().cast(), 0, f.bytes_written() - 1) }; if !ptr.is_null() { return Err(EINVAL); } @@ -591,14 +856,21 @@ impl Deref for CString { } } +impl DerefMut for CString { + fn deref_mut(&mut self) -> &mut Self::Target { + // SAFETY: A `CString` is always NUL-terminated and contains no other + // NUL bytes. + unsafe { CStr::from_bytes_with_nul_unchecked_mut(self.buf.as_mut_slice()) } + } +} + impl<'a> TryFrom<&'a CStr> for CString { type Error = AllocError; fn try_from(cstr: &'a CStr) -> Result<CString, AllocError> { - let mut buf = Vec::new(); + let mut buf = KVec::new(); - buf.try_extend_from_slice(cstr.as_bytes_with_nul()) - .map_err(|_| AllocError)?; + buf.extend_from_slice(cstr.to_bytes_with_nul(), GFP_KERNEL)?; // INVARIANT: The `CStr` and `CString` types have the same invariants for // the string data, and we copied it over without changes. @@ -606,8 +878,8 @@ impl<'a> TryFrom<&'a CStr> for CString { } } -/// A convenience alias for [`core::format_args`]. -#[macro_export] -macro_rules! fmt { - ($($f:tt)*) => ( core::format_args!($($f)*) ) +impl fmt::Debug for CString { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + fmt::Debug::fmt(&**self, f) + } } |