From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mail-qk1-f181.google.com (mail-qk1-f181.google.com [209.85.222.181]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 61CD7204095; Mon, 3 Feb 2025 11:50:41 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.222.181 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1738583444; cv=none; b=aoEWnsVkKSYr08MS2mfmLwbtqUf8/KyJ1oSQ4unLaHlqCRnNPKY4xzetqn3hH5L1SXoJEG2qyWx7d0HXev/v1n76ARYuOa6+ySC5/M8nsV+ymLyJZxvK5jGoG+MUsCVrd7iWHl4HL5rG64V5NJeakvJ6LLqoKgySxoVfZq70TwQ= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1738583444; c=relaxed/simple; bh=gnEvj0qvIvmU2oVDiZardE2SbQD4dkrDcUwohMuTduo=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=buvcsjca7ENj/HomH33Dm7HArLUsTKlGqsTt35lGtfBXf3pDfZhKsmBPzfmuNBUFvV9graNtnmCo/wZjDnhVCXX1s19qMG93KMCLEFz+c1SaX93k5p8hR0qGYmh76OaB/KXZfO/OFdzx/wHLY6JEF/V0CNj3O9WIC14zrGMti/g= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com; spf=pass smtp.mailfrom=gmail.com; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b=Z6bGQwD4; arc=none smtp.client-ip=209.85.222.181 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=gmail.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="Z6bGQwD4" Received: by mail-qk1-f181.google.com with SMTP id af79cd13be357-7b6f53c12adso374890385a.1; Mon, 03 Feb 2025 03:50:41 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1738583440; x=1739188240; darn=vger.kernel.org; h=cc:to:in-reply-to:references:message-id:content-transfer-encoding :mime-version:subject:date:from:from:to:cc:subject:date:message-id :reply-to; bh=zeVAzPKfSNYNKB2nHDfHMxYheyBSx+D996etKjt1JVQ=; b=Z6bGQwD4yYGR/XVUVYiMeyRiPzd7ZtwO9b8LzrlRT6PmWx0UIwC3VkDjgO5uoAwt6P e30EYH/ScbiOgg4JdUUjStbyeelmNznQMrzcwXDFa+e6bUN6fItd0ERBl6/NVx9cyJBp UR944xfj37zfWvglLxhnnfjmbsjaIRNEdakTesFqYzdZX2UZ2SsDltNgo2VVPIlkGDBF MkmGsz4rX/SPYHr8xyJKiEHvIYblEuqQAZyovKhtR9rjrObAVYG7P+W6gdtCkwIUsA6E uVnpQoddF2xRaygMfZaE8JrSIZgn7ZKTcFM2QzvBMgUPimsf/+Wr0iicC2cHWNr/Apqx +dFQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1738583440; x=1739188240; h=cc:to:in-reply-to:references:message-id:content-transfer-encoding :mime-version:subject:date:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=zeVAzPKfSNYNKB2nHDfHMxYheyBSx+D996etKjt1JVQ=; b=wlRP3A5jf1BKbrAYlKuJ15iOG+57SAgY5nV30HN/15alUGirgHi/x2Pbernyr03OKj qZnLXxJ4jBN9rLa6FtSYLoMxFMsBoFtO+iHl+04RWp7NkM1WRIBlyozd14QTsNxeHLry QtjDk9FP5mH6/BGCdEMTzNnIcWUTknfI9cMG6VNVATStyywvU7eVSLd5zpZ9v5tC2V3P XnoctXFHuO9D8kOyq0DYN+bRShXrIctj9F35Al5qSP4MVyi/M11RRygrN6mrjlTNSFr1 Avm8KI5oo/cobXquhIMQEtQus2UOwWbDTkmmLjK1iY42ZubOzPDLBHNijsviAqsmy4+i Zy9g== X-Forwarded-Encrypted: i=1; AJvYcCW9ATcOUrMCWg6OO2Yu8eu2ll4p7Z+bxopOedZbT7gpHWy47yOwQ8UABS0k/koaXrvjlcTQ5cnsXJ9tHEU=@vger.kernel.org X-Gm-Message-State: AOJu0YyT6i6i14YGttCxUvNNJAQuwP9DtzEqeBcm7ABqJrXrL+cknVVR Dd+leFoBbX2yUJlxiETYswqoRLXFPJhF2FUo4qS0bYIhNQrpxWypscnl3+BYhxc= X-Gm-Gg: ASbGncsVp0x/xmdaFqS1poqBsgxN0GKGgLxjSKnr3MfdUQmVg44i696B2d3ivoyMU9/ qksZHzLed2qwv1DJpqAVsRuYcHSXdSZN6Ky0anI9RIWt1yzAcKrHwd1y8TFQqS/u6GhRJ3ZAgL+ SdXBslGXvKbIdJNLIWchKai8amFuW6HVRoQW85jKmQOeH60Nw4Ln67hdOOdrlM8q2LH+zG0aiJj tyNc6C9v58/ojQM6eK4xpdMxO2+KEK1ZrUDYIqp7XriavBkyjWPPxXt2SMau2/cFLs3hyDptXMb O1Q1MJvkzWeBJKbGLVcn6pUdXfr7N7DKvotPGlw= X-Google-Smtp-Source: AGHT+IGjxkNZaKOPFBlc0Eh8Bl3tpbQ1Xc6fXP9vpb/ptnR6D+Erxeb9ysj0AJUth/lUePYUk1PhUw== X-Received: by 2002:a0c:aa5b:0:b0:6e2:49d0:6897 with SMTP id 6a1803df08f44-6e249d06ae0mr184977116d6.24.1738583439835; Mon, 03 Feb 2025 03:50:39 -0800 (PST) Received: from tamird-mac.local ([2600:4041:5be7:7c00:f07f:fb14:288d:6f1e]) by smtp.gmail.com with ESMTPSA id 6a1803df08f44-6e254835641sm49537626d6.62.2025.02.03.03.50.37 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 03 Feb 2025 03:50:38 -0800 (PST) From: Tamir Duberstein Date: Mon, 03 Feb 2025 06:50:32 -0500 Subject: [PATCH v8 2/4] rust: replace `CStr` with `core::ffi::CStr` Precedence: bulk X-Mailing-List: rust-for-linux@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 8bit Message-Id: <20250203-cstr-core-v8-2-cb3f26e78686@gmail.com> References: <20250203-cstr-core-v8-0-cb3f26e78686@gmail.com> In-Reply-To: <20250203-cstr-core-v8-0-cb3f26e78686@gmail.com> To: Michal Rostecki , Miguel Ojeda , Alex Gaynor , Boqun Feng , Gary Guo , =?utf-8?q?Bj=C3=B6rn_Roy_Baron?= , Benno Lossin , Andreas Hindborg , Alice Ryhl , Trevor Gross Cc: rust-for-linux@vger.kernel.org, linux-kernel@vger.kernel.org, Tamir Duberstein X-Mailer: b4 0.15-dev `std::ffi::CStr` was moved to `core::ffi::CStr` in Rust 1.64. Replace `kernel::str::CStr` with `core::ffi::CStr` now that we can. C-String literals were added in Rust 1.77. Opportunistically replace instances of `kernel::c_str!` with C-String literals where other code changes were already necessary; the rest will be done in a later commit. Signed-off-by: Tamir Duberstein --- rust/kernel/device.rs | 4 +- rust/kernel/error.rs | 4 +- rust/kernel/kunit.rs | 4 +- rust/kernel/miscdevice.rs | 2 +- rust/kernel/net/phy.rs | 2 +- rust/kernel/of.rs | 2 +- rust/kernel/prelude.rs | 5 +- rust/kernel/seq_file.rs | 4 +- rust/kernel/str.rs | 407 +++++++++++----------------------------- rust/kernel/sync/condvar.rs | 2 +- rust/kernel/sync/lock.rs | 2 +- rust/kernel/sync/lock/global.rs | 2 +- 12 files changed, 126 insertions(+), 314 deletions(-) diff --git a/rust/kernel/device.rs b/rust/kernel/device.rs index db2d9658ba47..df4bfa5f51ea 100644 --- a/rust/kernel/device.rs +++ b/rust/kernel/device.rs @@ -12,7 +12,7 @@ use core::{fmt, ptr}; #[cfg(CONFIG_PRINTK)] -use crate::c_str; +use crate::str::CStrExt as _; /// A reference-counted device. /// @@ -176,7 +176,7 @@ unsafe fn printk(&self, klevel: &[u8], msg: fmt::Arguments<'_>) { bindings::_dev_printk( klevel as *const _ as *const crate::ffi::c_char, self.as_raw(), - c_str!("%pA").as_char_ptr(), + c"%pA".as_char_ptr(), &msg as *const _ as *const crate::ffi::c_void, ) }; diff --git a/rust/kernel/error.rs b/rust/kernel/error.rs index f6ecf09cb65f..cff9204d9dd6 100644 --- a/rust/kernel/error.rs +++ b/rust/kernel/error.rs @@ -163,6 +163,8 @@ pub fn name(&self) -> Option<&'static CStr> { if ptr.is_null() { None } else { + use crate::str::CStrExt as _; + // SAFETY: The string returned by `errname` is static and `NUL`-terminated. Some(unsafe { CStr::from_char_ptr(ptr) }) } @@ -187,7 +189,7 @@ fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { Some(name) => f .debug_tuple( // SAFETY: These strings are ASCII-only. - unsafe { core::str::from_utf8_unchecked(name) }, + unsafe { core::str::from_utf8_unchecked(name.to_bytes()) }, ) .finish(), } diff --git a/rust/kernel/kunit.rs b/rust/kernel/kunit.rs index 630b947c708c..d858757aeace 100644 --- a/rust/kernel/kunit.rs +++ b/rust/kernel/kunit.rs @@ -101,12 +101,12 @@ unsafe impl Sync for Location {} unsafe impl Sync for UnaryAssert {} static LOCATION: Location = Location($crate::bindings::kunit_loc { - file: FILE.as_char_ptr(), + file: $crate::str::as_char_ptr_in_const_context(FILE), line: LINE, }); static ASSERTION: UnaryAssert = UnaryAssert($crate::bindings::kunit_unary_assert { assert: $crate::bindings::kunit_assert {}, - condition: CONDITION.as_char_ptr(), + condition: $crate::str::as_char_ptr_in_const_context(CONDITION), expected_true: true, }); diff --git a/rust/kernel/miscdevice.rs b/rust/kernel/miscdevice.rs index e14433b2ab9d..78c150270080 100644 --- a/rust/kernel/miscdevice.rs +++ b/rust/kernel/miscdevice.rs @@ -34,7 +34,7 @@ pub const fn into_raw(self) -> bindings::miscdevice { // SAFETY: All zeros is valid for this C type. let mut result: bindings::miscdevice = unsafe { MaybeUninit::zeroed().assume_init() }; result.minor = bindings::MISC_DYNAMIC_MINOR as _; - result.name = self.name.as_char_ptr(); + result.name = crate::str::as_char_ptr_in_const_context(self.name); result.fops = create_vtable::(); result } diff --git a/rust/kernel/net/phy.rs b/rust/kernel/net/phy.rs index bb654a28dab3..73df0f55f94e 100644 --- a/rust/kernel/net/phy.rs +++ b/rust/kernel/net/phy.rs @@ -504,7 +504,7 @@ unsafe impl Sync for DriverVTable {} pub const fn create_phy_driver() -> DriverVTable { // INVARIANT: All the fields of `struct phy_driver` are initialized properly. DriverVTable(Opaque::new(bindings::phy_driver { - name: T::NAME.as_char_ptr().cast_mut(), + name: crate::str::as_char_ptr_in_const_context(T::NAME), flags: T::FLAGS, phy_id: T::PHY_DEVICE_ID.id, phy_id_mask: T::PHY_DEVICE_ID.mask_as_int(), diff --git a/rust/kernel/of.rs b/rust/kernel/of.rs index 04f2d8ef29cb..12ea65df46de 100644 --- a/rust/kernel/of.rs +++ b/rust/kernel/of.rs @@ -29,7 +29,7 @@ fn index(&self) -> usize { impl DeviceId { /// Create a new device id from an OF 'compatible' string. pub const fn new(compatible: &'static CStr) -> Self { - let src = compatible.as_bytes_with_nul(); + let src = compatible.to_bytes_with_nul(); // Replace with `bindings::of_device_id::default()` once stabilized for `const`. // SAFETY: FFI type is valid to be zero-initialized. let mut of: bindings::of_device_id = unsafe { core::mem::zeroed() }; diff --git a/rust/kernel/prelude.rs b/rust/kernel/prelude.rs index dde2e0649790..96e7029c27da 100644 --- a/rust/kernel/prelude.rs +++ b/rust/kernel/prelude.rs @@ -34,7 +34,10 @@ pub use super::error::{code::*, Error, Result}; -pub use super::{str::CStr, ThisModule}; +pub use super::{ + str::{CStr, CStrExt as _}, + ThisModule, +}; pub use super::init::{InPlaceInit, InPlaceWrite, Init, PinInit}; diff --git a/rust/kernel/seq_file.rs b/rust/kernel/seq_file.rs index 04947c672979..073a38e6991f 100644 --- a/rust/kernel/seq_file.rs +++ b/rust/kernel/seq_file.rs @@ -4,7 +4,7 @@ //! //! C header: [`include/linux/seq_file.h`](srctree/include/linux/seq_file.h) -use crate::{bindings, c_str, types::NotThreadSafe, types::Opaque}; +use crate::{bindings, str::CStrExt as _, types::NotThreadSafe, types::Opaque}; /// A utility for generating the contents of a seq file. #[repr(transparent)] @@ -35,7 +35,7 @@ pub fn call_printf(&self, args: core::fmt::Arguments<'_>) { unsafe { bindings::seq_printf( self.inner.get(), - c_str!("%pA").as_char_ptr(), + c"%pA".as_char_ptr(), &args as *const _ as *const crate::ffi::c_void, ); } diff --git a/rust/kernel/str.rs b/rust/kernel/str.rs index c273f1367607..13dd2f6cc572 100644 --- a/rust/kernel/str.rs +++ b/rust/kernel/str.rs @@ -4,7 +4,7 @@ use crate::alloc::{flags::*, AllocError, KVec}; use core::fmt::{self, Write}; -use core::ops::{self, Deref, DerefMut, Index}; +use core::ops::{Deref, DerefMut}; use crate::error::{code::*, Error}; @@ -45,11 +45,11 @@ pub const fn from_bytes(bytes: &[u8]) -> &Self { /// # use kernel::{fmt, b_str, str::CString}; /// let ascii = b_str!("Hello, BStr!"); /// let s = CString::try_from_fmt(fmt!("{}", ascii.display()))?; - /// assert_eq!(s.as_bytes(), "Hello, BStr!".as_bytes()); + /// assert_eq!(s.to_bytes(), "Hello, BStr!".as_bytes()); /// /// let non_ascii = b_str!("🦀"); /// let s = CString::try_from_fmt(fmt!("{}", non_ascii.display()))?; - /// assert_eq!(s.as_bytes(), "\\xf0\\x9f\\xa6\\x80".as_bytes()); + /// assert_eq!(s.to_bytes(), "\\xf0\\x9f\\xa6\\x80".as_bytes()); /// # Ok::<(), kernel::error::Error>(()) /// ``` #[inline] @@ -74,11 +74,11 @@ pub fn display(&self) -> Display<'_> { /// # use kernel::{fmt, b_str, str::CString}; /// let ascii = b_str!("Hello, BStr!"); /// let s = CString::try_from_fmt(fmt!("{}", ascii.display()))?; -/// assert_eq!(s.as_bytes(), "Hello, BStr!".as_bytes()); +/// assert_eq!(s.to_bytes(), "Hello, BStr!".as_bytes()); /// /// let non_ascii = b_str!("🦀"); /// let s = CString::try_from_fmt(fmt!("{}", non_ascii.display()))?; -/// assert_eq!(s.as_bytes(), "\\xf0\\x9f\\xa6\\x80".as_bytes()); +/// assert_eq!(s.to_bytes(), "\\xf0\\x9f\\xa6\\x80".as_bytes()); /// # Ok::<(), kernel::error::Error>(()) /// ``` /// @@ -120,11 +120,11 @@ impl fmt::Debug for BStr { /// // Embedded double quotes are escaped. /// let ascii = b_str!("Hello, \"BStr\"!"); /// let s = CString::try_from_fmt(fmt!("{:?}", ascii))?; - /// assert_eq!(s.as_bytes(), "\"Hello, \\\"BStr\\\"!\"".as_bytes()); + /// 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.as_bytes(), "\"\\xf0\\x9f\\x98\\xba\"".as_bytes()); + /// assert_eq!(s.to_bytes(), "\"\\xf0\\x9f\\x98\\xba\"".as_bytes()); /// # Ok::<(), kernel::error::Error>(()) /// ``` fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { @@ -177,55 +177,19 @@ macro_rules! b_str { }}; } -/// Possible errors when using conversion functions in [`CStr`]. -#[derive(Debug, Clone, Copy)] -pub enum CStrConvertError { - /// Supplied bytes contain an interior `NUL`. - InteriorNul, +pub use core::ffi::CStr; - /// Supplied bytes are not terminated by `NUL`. - NotNulTerminated, +/// 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 crate::ffi::c_char { + c_str.as_ptr().cast() } -impl From 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 { - if self.0.is_empty() { - // 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. - 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 - } - +/// Extensions to [`CStr`]. +pub trait CStrExt { /// Wraps a raw C string pointer. /// /// # Safety @@ -233,54 +197,9 @@ pub const fn is_empty(&self) -> bool { /// `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 crate::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) }; - // 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]` 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) } - } + // 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 crate::ffi::c_char) -> &'a Self; /// Creates a mutable [`CStr`] from a `[u8]` without performing any /// additional checks. @@ -289,77 +208,16 @@ pub const fn from_bytes_with_nul(bytes: &[u8]) -> Result<&Self, CStrConvertError /// /// `bytes` *must* end with a `NUL` byte, and should only have a single /// `NUL` byte (or the string will be truncated). - #[inline] - pub unsafe fn from_bytes_with_nul_unchecked_mut(bytes: &mut [u8]) -> &mut CStr { - // SAFETY: Properties of `bytes` guaranteed by the safety precondition. - unsafe { &mut *(bytes as *mut [u8] as *mut CStr) } - } + 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 crate::ffi::c_char { - self.0.as_ptr() - } - - /// Convert the string to a byte slice without the trailing `NUL` byte. - #[inline] - pub fn as_bytes(&self) -> &[u8] { - &self.0[..self.len()] - } - - /// Convert the string to a byte slice containing the trailing `NUL` 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")?; - /// assert_eq!(cstr.to_str(), Ok("foo")); - /// # Ok::<(), kernel::error::Error>(()) - /// ``` - #[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; - /// let bar = c_str!("ツ"); - /// // SAFETY: String literals are guaranteed to be valid UTF-8 - /// // by the Rust compiler. - /// assert_eq!(unsafe { bar.as_str_unchecked() }, "ツ"); - /// ``` - #[inline] - pub unsafe fn as_str_unchecked(&self) -> &str { - // SAFETY: TODO. - unsafe { core::str::from_utf8_unchecked(self.as_bytes()) } - } + // 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 crate::ffi::c_char; /// Convert this [`CStr`] into a [`CString`] by allocating memory and /// copying over the string data. - pub fn to_cstring(&self) -> Result { - CString::try_from(self) - } + fn to_cstring(&self) -> Result; /// Converts this [`CStr`] to its ASCII lower case equivalent in-place. /// @@ -370,11 +228,7 @@ pub fn to_cstring(&self) -> Result { /// [`to_ascii_lowercase()`]. /// /// [`to_ascii_lowercase()`]: #method.to_ascii_lowercase - pub fn make_ascii_lowercase(&mut self) { - // INVARIANT: This doesn't introduce or remove NUL bytes in the C - // string. - self.0.make_ascii_lowercase(); - } + fn make_ascii_lowercase(&mut self); /// Converts this [`CStr`] to its ASCII upper case equivalent in-place. /// @@ -385,11 +239,7 @@ pub fn make_ascii_lowercase(&mut self) { /// [`to_ascii_uppercase()`]. /// /// [`to_ascii_uppercase()`]: #method.to_ascii_uppercase - pub fn make_ascii_uppercase(&mut self) { - // INVARIANT: This doesn't introduce or remove NUL bytes in the C - // string. - self.0.make_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. @@ -400,13 +250,7 @@ pub fn make_ascii_uppercase(&mut self) { /// To lowercase the value in-place, use [`make_ascii_lowercase`]. /// /// [`make_ascii_lowercase`]: str::make_ascii_lowercase - pub fn to_ascii_lowercase(&self) -> Result { - let mut s = self.to_cstring()?; - - s.make_ascii_lowercase(); - - Ok(s) - } + fn to_ascii_lowercase(&self) -> Result; /// Returns a copy of this [`CString`] where each character is mapped to its /// ASCII upper case equivalent. @@ -417,13 +261,7 @@ pub fn to_ascii_lowercase(&self) -> Result { /// To uppercase the value in-place, use [`make_ascii_uppercase`]. /// /// [`make_ascii_uppercase`]: str::make_ascii_uppercase - pub fn to_ascii_uppercase(&self) -> Result { - let mut s = self.to_cstring()?; - - s.make_ascii_uppercase(); - - Ok(s) - } + fn to_ascii_uppercase(&self) -> Result; /// Returns an object that implements [`Display`] for safely printing a [`CStr`] that may /// contain non-Unicode data. If you would like an implementation which escapes the [`CStr`] @@ -440,113 +278,93 @@ pub fn to_ascii_uppercase(&self) -> Result { /// # use kernel::str::CString; /// let penguin = c_str!("🐧"); /// let s = CString::try_from_fmt(fmt!("{}", penguin.display()))?; - /// assert_eq!(s.as_bytes_with_nul(), "\\xf0\\x9f\\x90\\xa7\0".as_bytes()); + /// 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.display()))?; - /// assert_eq!(s.as_bytes_with_nul(), "so \"cool\"\0".as_bytes()); + /// assert_eq!(s.to_bytes_with_nul(), "so \"cool\"\0".as_bytes()); /// # Ok::<(), kernel::error::Error>(()) /// ``` - #[inline] - pub fn display(&self) -> Display<'_> { - Display { - inner: self, - escape_common: false, - } - } + fn display(&self) -> Display<'_>; } -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::fmt; - /// # use kernel::str::CString; - /// let penguin = c_str!("🐧"); - /// let s = CString::try_from_fmt(fmt!("{:?}", penguin))?; - /// 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))?; - /// assert_eq!(s.as_bytes_with_nul(), "\"so \\\"cool\\\"\"\0".as_bytes()); - /// # Ok::<(), kernel::error::Error>(()) - /// ``` - 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 *(s as *mut CStr as *mut [u8]) } } -impl AsRef for CStr { +impl CStrExt for CStr { #[inline] - fn as_ref(&self) -> &BStr { - BStr::from_bytes(self.as_bytes()) + unsafe fn from_char_ptr<'a>(ptr: *const crate::ffi::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 *(bytes as *mut [u8] as *mut CStr) } + } #[inline] - fn deref(&self) -> &Self::Target { - self.as_ref() + fn as_char_ptr(&self) -> *const crate::ffi::c_char { + self.as_ptr().cast() } -} -impl Index> for CStr { - type Output = CStr; + fn to_cstring(&self) -> Result { + CString::try_from(self) + } - #[inline] - fn index(&self, index: ops::RangeFrom) -> &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 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 { + let mut s = self.to_cstring()?; + + s.make_ascii_lowercase(); + + Ok(s) } -} -mod private { - use core::ops; + fn to_ascii_uppercase(&self) -> Result { + 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 {} - impl CStrIndex for ops::RangeInclusive {} - impl CStrIndex for ops::RangeToInclusive {} -} + Ok(s) + } -impl Index for CStr -where - Idx: private::CStrIndex, - BStr: Index, -{ - type Output = >::Output; + #[inline] + fn display(&self) -> Display<'_> { + Display { + inner: self.as_ref(), + escape_common: false, + } + } +} +impl AsRef for CStr { #[inline] - fn index(&self, index: Idx) -> &Self::Output { - &self.as_ref()[index] + fn as_ref(&self) -> &BStr { + BStr::from_bytes(self.to_bytes()) } } @@ -630,25 +448,15 @@ fn test_cstr_to_str_panic() { 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(); - // SAFETY: The contents come from a string literal which contains valid UTF-8. - let unchecked_str = unsafe { checked_cstr.as_str_unchecked() }; - assert_eq!(unchecked_str, "🐧"); - } - #[test] fn test_cstr_display() { - let hello_world = CStr::from_bytes_with_nul(b"hello, world!\0").unwrap(); - assert_eq!(format!("{}", hello_world.display()), "hello, world!"); - let non_printables = CStr::from_bytes_with_nul(b"\x01\x09\x0a\0").unwrap(); - assert_eq!(format!("{}", non_printables.display()), "\\x01\\x09\\x0a"); - let non_ascii = CStr::from_bytes_with_nul(b"d\xe9j\xe0 vu\0").unwrap(); - assert_eq!(format!("{}", non_ascii.display()), "d\\xe9j\\xe0 vu"); - let good_bytes = CStr::from_bytes_with_nul(b"\xf0\x9f\xa6\x80\0").unwrap(); - assert_eq!(format!("{}", good_bytes.display()), "\\xf0\\x9f\\xa6\\x80"); + assert_eq!(format!("{}", c"hello, world!".display()), "hello, world!"); + assert_eq!(format!("{}", c"\x01\x09\x0a".display()), "\\x01\\x09\\x0a"); + assert_eq!(format!("{}", c"d\xe9j\xe0 vu".display()), "d\\xe9j\\xe0 vu"); + assert_eq!( + format!("{}", c"\xf0\x9f\xa6\x80".display()), + "\\xf0\\x9f\\xa6\\x80" + ); } #[test] @@ -664,14 +472,13 @@ fn test_cstr_display_all_bytes() { #[test] fn test_cstr_debug() { - let hello_world = CStr::from_bytes_with_nul(b"hello, world!\0").unwrap(); - assert_eq!(format!("{:?}", hello_world), "\"hello, world!\""); - let non_printables = CStr::from_bytes_with_nul(b"\x01\x09\x0a\0").unwrap(); - assert_eq!(format!("{:?}", non_printables), "\"\\x01\\x09\\x0a\""); - let non_ascii = CStr::from_bytes_with_nul(b"d\xe9j\xe0 vu\0").unwrap(); - assert_eq!(format!("{:?}", non_ascii), "\"d\\xe9j\\xe0 vu\""); - let good_bytes = CStr::from_bytes_with_nul(b"\xf0\x9f\xa6\x80\0").unwrap(); - assert_eq!(format!("{:?}", good_bytes), "\"\\xf0\\x9f\\xa6\\x80\""); + assert_eq!(format!("{:?}", c"hello, world!"), "\"hello, world!\""); + assert_eq!(format!("{:?}", c"\x01\x09\x0a"), "\"\\x01\\t\\n\""); + assert_eq!(format!("{:?}", c"d\xe9j\xe0 vu"), "\"d\\xe9j\\xe0 vu\""); + assert_eq!( + format!("{:?}", c"\xf0\x9f\xa6\x80"), + "\"\\xf0\\x9f\\xa6\\x80\"" + ); } #[test] @@ -851,14 +658,14 @@ fn write_str(&mut self, s: &str) -> fmt::Result { /// # Examples /// /// ``` -/// use kernel::{str::CString, fmt}; +/// use kernel::{fmt, str::CString}; /// /// let s = CString::try_from_fmt(fmt!("{}{}{}", "abc", 10, 20))?; -/// assert_eq!(s.as_bytes_with_nul(), "abc1020\0".as_bytes()); +/// assert_eq!(s.to_bytes_with_nul(), "abc1020\0".as_bytes()); /// /// let tmp = "testing"; /// let s = CString::try_from_fmt(fmt!("{tmp}{}", 123))?; -/// assert_eq!(s.as_bytes_with_nul(), "testing123\0".as_bytes()); +/// 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)); @@ -928,7 +735,7 @@ impl<'a> TryFrom<&'a CStr> for CString { fn try_from(cstr: &'a CStr) -> Result { let mut buf = KVec::new(); - buf.extend_from_slice(cstr.as_bytes_with_nul(), GFP_KERNEL)?; + 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. diff --git a/rust/kernel/sync/condvar.rs b/rust/kernel/sync/condvar.rs index 7df565038d7d..7901aa040f0e 100644 --- a/rust/kernel/sync/condvar.rs +++ b/rust/kernel/sync/condvar.rs @@ -10,7 +10,7 @@ ffi::{c_int, c_long}, init::PinInit, pin_init, - str::CStr, + str::{CStr, CStrExt as _}, task::{MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE, TASK_NORMAL, TASK_UNINTERRUPTIBLE}, time::Jiffies, types::Opaque, diff --git a/rust/kernel/sync/lock.rs b/rust/kernel/sync/lock.rs index eb80048e0110..37f1a6a53b12 100644 --- a/rust/kernel/sync/lock.rs +++ b/rust/kernel/sync/lock.rs @@ -9,7 +9,7 @@ use crate::{ init::PinInit, pin_init, - str::CStr, + str::{CStr, CStrExt as _}, types::{NotThreadSafe, Opaque, ScopeGuard}, }; use core::{cell::UnsafeCell, marker::PhantomPinned}; diff --git a/rust/kernel/sync/lock/global.rs b/rust/kernel/sync/lock/global.rs index 480ee724e3cc..6a28f5b60482 100644 --- a/rust/kernel/sync/lock/global.rs +++ b/rust/kernel/sync/lock/global.rs @@ -5,7 +5,7 @@ //! Support for defining statics containing locks. use crate::{ - str::CStr, + str::{CStr, CStrExt as _}, sync::lock::{Backend, Guard, Lock}, sync::{LockClassKey, LockedBy}, types::Opaque, -- 2.48.1