diff options
89 files changed, 12552 insertions, 51 deletions
diff --git a/.gitignore b/.gitignore index 265959544978..5da004814678 100644 --- a/.gitignore +++ b/.gitignore @@ -37,6 +37,8 @@ *.o *.o.* *.patch +*.rmeta +*.rsi *.s *.so *.so.dbg @@ -97,6 +99,7 @@ modules.order !.gitattributes !.gitignore !.mailmap +!.rustfmt.toml # # Generated include files @@ -162,3 +165,6 @@ x509.genkey # Documentation toolchain sphinx_*/ + +# Rust analyzer configuration +/rust-project.json diff --git a/.rustfmt.toml b/.rustfmt.toml new file mode 100644 index 000000000000..3de5cc497465 --- /dev/null +++ b/.rustfmt.toml @@ -0,0 +1,12 @@ +edition = "2021" +newline_style = "Unix" + +# Unstable options that help catching some mistakes in formatting and that we may want to enable +# when they become stable. +# +# They are kept here since they are useful to run from time to time. +#format_code_in_doc_comments = true +#reorder_impl_items = true +#comment_width = 100 +#wrap_comments = true +#normalize_comments = true diff --git a/Documentation/core-api/printk-formats.rst b/Documentation/core-api/printk-formats.rst index 5e89497ba314..dbe1aacc79d0 100644 --- a/Documentation/core-api/printk-formats.rst +++ b/Documentation/core-api/printk-formats.rst @@ -625,6 +625,16 @@ Examples:: %p4cc Y10 little-endian (0x20303159) %p4cc NV12 big-endian (0xb231564e) +Rust +---- + +:: + + %pA + +Only intended to be used from Rust code to format ``core::fmt::Arguments``. +Do *not* use it from C. + Thanks ====== diff --git a/Documentation/doc-guide/kernel-doc.rst b/Documentation/doc-guide/kernel-doc.rst index 9c779bd7a751..1dcbd7332476 100644 --- a/Documentation/doc-guide/kernel-doc.rst +++ b/Documentation/doc-guide/kernel-doc.rst @@ -14,6 +14,9 @@ when it is embedded in source files. reasons. The kernel source contains tens of thousands of kernel-doc comments. Please stick to the style described here. +.. note:: kernel-doc does not cover Rust code: please see + Documentation/rust/general-information.rst instead. + The kernel-doc structure is extracted from the comments, and proper `Sphinx C Domain`_ function and type descriptions with anchors are generated from them. The descriptions are filtered for special kernel-doc diff --git a/Documentation/index.rst b/Documentation/index.rst index 85eab6e990ab..bf6aa681c960 100644 --- a/Documentation/index.rst +++ b/Documentation/index.rst @@ -58,6 +58,7 @@ Various other manuals with useful information for all kernel developers. trace/index fault-injection/index livepatch/index + rust/index User-oriented documentation diff --git a/Documentation/kbuild/kbuild.rst b/Documentation/kbuild/kbuild.rst index ef19b9c13523..08f575e6236c 100644 --- a/Documentation/kbuild/kbuild.rst +++ b/Documentation/kbuild/kbuild.rst @@ -48,6 +48,10 @@ KCFLAGS ------- Additional options to the C compiler (for built-in and modules). +KRUSTFLAGS +---------- +Additional options to the Rust compiler (for built-in and modules). + CFLAGS_KERNEL ------------- Additional options for $(CC) when used to compile @@ -57,6 +61,15 @@ CFLAGS_MODULE ------------- Additional module specific options to use for $(CC). +RUSTFLAGS_KERNEL +---------------- +Additional options for $(RUSTC) when used to compile +code that is compiled as built-in. + +RUSTFLAGS_MODULE +---------------- +Additional module specific options to use for $(RUSTC). + LDFLAGS_MODULE -------------- Additional options used for $(LD) when linking modules. @@ -69,6 +82,10 @@ HOSTCXXFLAGS ------------ Additional flags to be passed to $(HOSTCXX) when building host programs. +HOSTRUSTFLAGS +------------- +Additional flags to be passed to $(HOSTRUSTC) when building host programs. + HOSTLDFLAGS ----------- Additional flags to be passed when linking host programs. diff --git a/Documentation/kbuild/makefiles.rst b/Documentation/kbuild/makefiles.rst index 11a296e52d68..5ea1e72d89c8 100644 --- a/Documentation/kbuild/makefiles.rst +++ b/Documentation/kbuild/makefiles.rst @@ -29,8 +29,9 @@ This document describes the Linux kernel Makefiles. --- 4.1 Simple Host Program --- 4.2 Composite Host Programs --- 4.3 Using C++ for host programs - --- 4.4 Controlling compiler options for host programs - --- 4.5 When host programs are actually built + --- 4.4 Using Rust for host programs + --- 4.5 Controlling compiler options for host programs + --- 4.6 When host programs are actually built === 5 Userspace Program support --- 5.1 Simple Userspace Program @@ -835,7 +836,24 @@ Both possibilities are described in the following. qconf-cxxobjs := qconf.o qconf-objs := check.o -4.4 Controlling compiler options for host programs +4.4 Using Rust for host programs +-------------------------------- + + Kbuild offers support for host programs written in Rust. However, + since a Rust toolchain is not mandatory for kernel compilation, + it may only be used in scenarios where Rust is required to be + available (e.g. when ``CONFIG_RUST`` is enabled). + + Example:: + + hostprogs := target + target-rust := y + + Kbuild will compile ``target`` using ``target.rs`` as the crate root, + located in the same directory as the ``Makefile``. The crate may + consist of several source files (see ``samples/rust/hostprogs``). + +4.5 Controlling compiler options for host programs -------------------------------------------------- When compiling host programs, it is possible to set specific flags. @@ -867,7 +885,7 @@ Both possibilities are described in the following. When linking qconf, it will be passed the extra option "-L$(QTDIR)/lib". -4.5 When host programs are actually built +4.6 When host programs are actually built ----------------------------------------- Kbuild will only build host-programs when they are referenced @@ -1181,6 +1199,17 @@ When kbuild executes, the following steps are followed (roughly): The first example utilises the trick that a config option expands to 'y' when selected. + KBUILD_RUSTFLAGS + $(RUSTC) compiler flags + + Default value - see top level Makefile + Append or modify as required per architecture. + + Often, the KBUILD_RUSTFLAGS variable depends on the configuration. + + Note that target specification file generation (for ``--target``) + is handled in ``scripts/generate_rust_target.rs``. + KBUILD_AFLAGS_KERNEL Assembler options specific for built-in @@ -1208,6 +1237,19 @@ When kbuild executes, the following steps are followed (roughly): are used for $(CC). From commandline CFLAGS_MODULE shall be used (see kbuild.rst). + KBUILD_RUSTFLAGS_KERNEL + $(RUSTC) options specific for built-in + + $(KBUILD_RUSTFLAGS_KERNEL) contains extra Rust compiler flags used to + compile resident kernel code. + + KBUILD_RUSTFLAGS_MODULE + Options for $(RUSTC) when building modules + + $(KBUILD_RUSTFLAGS_MODULE) is used to add arch-specific options that + are used for $(RUSTC). + From commandline RUSTFLAGS_MODULE shall be used (see kbuild.rst). + KBUILD_LDFLAGS_MODULE Options for $(LD) when linking modules diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst index 19c286c23786..9a90197989dd 100644 --- a/Documentation/process/changes.rst +++ b/Documentation/process/changes.rst @@ -31,6 +31,8 @@ you probably needn't concern yourself with pcmciautils. ====================== =============== ======================================== GNU C 5.1 gcc --version Clang/LLVM (optional) 11.0.0 clang --version +Rust (optional) 1.62.0 rustc --version +bindgen (optional) 0.56.0 bindgen --version GNU make 3.81 make --version bash 4.2 bash --version binutils 2.23 ld -v @@ -80,6 +82,29 @@ kernels. Older releases aren't guaranteed to work, and we may drop workarounds from the kernel that were used to support older versions. Please see additional docs on :ref:`Building Linux with Clang/LLVM <kbuild_llvm>`. +Rust (optional) +--------------- + +A particular version of the Rust toolchain is required. Newer versions may or +may not work because the kernel depends on some unstable Rust features, for +the moment. + +Each Rust toolchain comes with several "components", some of which are required +(like ``rustc``) and some that are optional. The ``rust-src`` component (which +is optional) needs to be installed to build the kernel. Other components are +useful for developing. + +Please see Documentation/rust/quick-start.rst for instructions on how to +satisfy the build requirements of Rust support. In particular, the ``Makefile`` +target ``rustavailable`` is useful to check why the Rust toolchain may not +be detected. + +bindgen (optional) +------------------ + +``bindgen`` is used to generate the Rust bindings to the C side of the kernel. +It depends on ``libclang``. + Make ---- @@ -348,6 +373,12 @@ Sphinx Please see :ref:`sphinx_install` in :ref:`Documentation/doc-guide/sphinx.rst <sphinxdoc>` for details about Sphinx requirements. +rustdoc +------- + +``rustdoc`` is used to generate the documentation for Rust code. Please see +Documentation/rust/general-information.rst for more information. + Getting updated software ======================== @@ -364,6 +395,16 @@ Clang/LLVM - :ref:`Getting LLVM <getting_llvm>`. +Rust +---- + +- Documentation/rust/quick-start.rst. + +bindgen +------- + +- Documentation/rust/quick-start.rst. + Make ---- diff --git a/Documentation/rust/arch-support.rst b/Documentation/rust/arch-support.rst new file mode 100644 index 000000000000..6982b63775da --- /dev/null +++ b/Documentation/rust/arch-support.rst @@ -0,0 +1,19 @@ +.. SPDX-License-Identifier: GPL-2.0 + +Arch Support +============ + +Currently, the Rust compiler (``rustc``) uses LLVM for code generation, +which limits the supported architectures that can be targeted. In addition, +support for building the kernel with LLVM/Clang varies (please see +Documentation/kbuild/llvm.rst). This support is needed for ``bindgen`` +which uses ``libclang``. + +Below is a general summary of architectures that currently work. Level of +support corresponds to ``S`` values in the ``MAINTAINERS`` file. + +============ ================ ============================================== +Architecture Level of support Constraints +============ ================ ============================================== +``x86`` Maintained ``x86_64`` only. +============ ================ ============================================== diff --git a/Documentation/rust/coding-guidelines.rst b/Documentation/rust/coding-guidelines.rst new file mode 100644 index 000000000000..aa8ed082613e --- /dev/null +++ b/Documentation/rust/coding-guidelines.rst @@ -0,0 +1,216 @@ +.. SPDX-License-Identifier: GPL-2.0 + +Coding Guidelines +================= + +This document describes how to write Rust code in the kernel. + + +Style & formatting +------------------ + +The code should be formatted using ``rustfmt``. In this way, a person +contributing from time to time to the kernel does not need to learn and +remember one more style guide. More importantly, reviewers and maintainers +do not need to spend time pointing out style issues anymore, and thus +less patch roundtrips may be needed to land a change. + +.. note:: Conventions on comments and documentation are not checked by + ``rustfmt``. Thus those are still needed to be taken care of. + +The default settings of ``rustfmt`` are used. This means the idiomatic Rust +style is followed. For instance, 4 spaces are used for indentation rather +than tabs. + +It is convenient to instruct editors/IDEs to format while typing, +when saving or at commit time. However, if for some reason reformatting +the entire kernel Rust sources is needed at some point, the following can be +run:: + + make LLVM=1 rustfmt + +It is also possible to check if everything is formatted (printing a diff +otherwise), for instance for a CI, with:: + + make LLVM=1 rustfmtcheck + +Like ``clang-format`` for the rest of the kernel, ``rustfmt`` works on +individual files, and does not require a kernel configuration. Sometimes it may +even work with broken code. + + +Comments +-------- + +"Normal" comments (i.e. ``//``, rather than code documentation which starts +with ``///`` or ``//!``) are written in Markdown the same way as documentation +comments are, even though they will not be rendered. This improves consistency, +simplifies the rules and allows to move content between the two kinds of +comments more easily. For instance: + +.. code-block:: rust + + // `object` is ready to be handled now. + f(object); + +Furthermore, just like documentation, comments are capitalized at the beginning +of a sentence and ended with a period (even if it is a single sentence). This +includes ``// SAFETY:``, ``// TODO:`` and other "tagged" comments, e.g.: + +.. code-block:: rust + + // FIXME: The error should be handled properly. + +Comments should not be used for documentation purposes: comments are intended +for implementation details, not users. This distinction is useful even if the +reader of the source file is both an implementor and a user of an API. In fact, +sometimes it is useful to use both comments and documentation at the same time. +For instance, for a ``TODO`` list or to comment on the documentation itself. +For the latter case, comments can be inserted in the middle; that is, closer to +the line of documentation to be commented. For any other case, comments are +written after the documentation, e.g.: + +.. code-block:: rust + + /// Returns a new [`Foo`]. + /// + /// # Examples + /// + // TODO: Find a better example. + /// ``` + /// let foo = f(42); + /// ``` + // FIXME: Use fallible approach. + pub fn f(x: i32) -> Foo { + // ... + } + +One special kind of comments are the ``// SAFETY:`` comments. These must appear +before every ``unsafe`` block, and they explain why the code inside the block is +correct/sound, i.e. why it cannot trigger undefined behavior in any case, e.g.: + +.. code-block:: rust + + // SAFETY: `p` is valid by the safety requirements. + unsafe { *p = 0; } + +``// SAFETY:`` comments are not to be confused with the ``# Safety`` sections +in code documentation. ``# Safety`` sections specify the contract that callers +(for functions) or implementors (for traits) need to abide by. ``// SAFETY:`` +comments show why a call (for functions) or implementation (for traits) actually +respects the preconditions stated in a ``# Safety`` section or the language +reference. + + +Code documentation +------------------ + +Rust kernel code is not documented like C kernel code (i.e. via kernel-doc). +Instead, the usual system for documenting Rust code is used: the ``rustdoc`` +tool, which uses Markdown (a lightweight markup language). + +To learn Markdown, there are many guides available out there. For instance, +the one at: + + https://commonmark.org/help/ + +This is how a well-documented Rust function may look like: + +.. code-block:: rust + + /// Returns the contained [`Some`] value, consuming the `self` value, + /// without checking that the value is not [`None`]. + /// + /// # Safety + /// + /// Calling this method on [`None`] is *[undefined behavior]*. + /// + /// [undefined behavior]: https://doc.rust-lang.org/reference/behavior-considered-undefined.html + /// + /// # Examples + /// + /// ``` + /// let x = Some("air"); + /// assert_eq!(unsafe { x.unwrap_unchecked() }, "air"); + /// ``` + pub unsafe fn unwrap_unchecked(self) -> T { + match self { + Some(val) => val, + + // SAFETY: The safety contract must be upheld by the caller. + None => unsafe { hint::unreachable_unchecked() }, + } + } + +This example showcases a few ``rustdoc`` features and some conventions followed +in the kernel: + + - The first paragraph must be a single sentence briefly describing what + the documented item does. Further explanations must go in extra paragraphs. + + - Unsafe functions must document their safety preconditions under + a ``# Safety`` section. + + - While not shown here, if a function may panic, the conditions under which + that happens must be described under a ``# Panics`` section. + + Please note that panicking should be very rare and used only with a good + reason. In almost all cases, a fallible approach should be used, typically + returning a ``Result``. + + - If providing examples of usage would help readers, they must be written in + a section called ``# Examples``. + + - Rust items (functions, types, constants...) must be linked appropriately + (``rustdoc`` will create a link automatically). + + - Any ``unsafe`` block must be preceded by a ``// SAFETY:`` comment + describing why the code inside is sound. + + While sometimes the reason might look trivial and therefore unneeded, + writing these comments is not just a good way of documenting what has been + taken into account, but most importantly, it provides a way to know that + there are no *extra* implicit constraints. + +To learn more about how to write documentation for Rust and extra features, +please take a look at the ``rustdoc`` book at: + + https://doc.rust-lang.org/rustdoc/how-to-write-documentation.html + + +Naming +------ + +Rust kernel code follows the usual Rust naming conventions: + + https://rust-lang.github.io/api-guidelines/naming.html + +When existing C concepts (e.g. macros, functions, objects...) are wrapped into +a Rust abstraction, a name as close as reasonably possible to the C side should +be used in order to avoid confusion and to improve readability when switching +back and forth between the C and Rust sides. For instance, macros such as +``pr_info`` from C are named the same in the Rust side. + +Having said that, casing should be adjusted to follow the Rust naming +conventions, and namespacing introduced by modules and types should not be +repeated in the item names. For instance, when wrapping constants like: + +.. code-block:: c + + #define GPIO_LINE_DIRECTION_IN 0 + #define GPIO_LINE_DIRECTION_OUT 1 + +The equivalent in Rust may look like (ignoring documentation): + +.. code-block:: rust + + pub mod gpio { + pub enum LineDirection { + In = bindings::GPIO_LINE_DIRECTION_IN as _, + Out = bindings::GPIO_LINE_DIRECTION_OUT as _, + } + } + +That is, the equivalent of ``GPIO_LINE_DIRECTION_IN`` would be referred to as +``gpio::LineDirection::In``. In particular, it should not be named +``gpio::gpio_line_direction::GPIO_LINE_DIRECTION_IN``. diff --git a/Documentation/rust/general-information.rst b/Documentation/rust/general-information.rst new file mode 100644 index 000000000000..49029ee82e55 --- /dev/null +++ b/Documentation/rust/general-information.rst @@ -0,0 +1,79 @@ +.. SPDX-License-Identifier: GPL-2.0 + +General Information +=================== + +This document contains useful information to know when working with +the Rust support in the kernel. + + +Code documentation +------------------ + +Rust kernel code is documented using ``rustdoc``, its built-in documentation +generator. + +The generated HTML docs include integrated search, linked items (e.g. types, +functions, constants), source code, etc. They may be read at (TODO: link when +in mainline and generated alongside the rest of the documentation): + + http://kernel.org/ + +The docs can also be easily generated and read locally. This is quite fast +(same order as compiling the code itself) and no special tools or environment +are needed. This has the added advantage that they will be tailored to +the particular kernel configuration used. To generate them, use the ``rustdoc`` +target with the same invocation used for compilation, e.g.:: + + make LLVM=1 rustdoc + +To read the docs locally in your web browser, run e.g.:: + + xdg-open rust/doc/kernel/index.html + +To learn about how to write the documentation, please see coding-guidelines.rst. + + +Extra lints +----------- + +While ``rustc`` is a very helpful compiler, some extra lints and analyses are +available via ``clippy``, a Rust linter. To enable it, pass ``CLIPPY=1`` to +the same invocation used for compilation, e.g.:: + + make LLVM=1 CLIPPY=1 + +Please note that Clippy may change code generation, thus it should not be +enabled while building a production kernel. + + +Abstractions vs. bindings +------------------------- + +Abstractions are Rust code wrapping kernel functionality from the C side. + +In order to use functions and types from the C side, bindings are created. +Bindings are the declarations for Rust of those functions and types from +the C side. + +For instance, one may write a ``Mutex`` abstraction in Rust which wraps +a ``struct mutex`` from the C side and calls its functions through the bindings. + +Abstractions are not available for all the kernel internal APIs and concepts, +but it is intended that coverage is expanded as time goes on. "Leaf" modules +(e.g. drivers) should not use the C bindings directly. Instead, subsystems +should provide as-safe-as-possible abstractions as needed. + + +Conditional compilation +----------------------- + +Rust code has access to conditional compilation based on the kernel +configuration: + +.. code-block:: rust + + #[cfg(CONFIG_X)] // Enabled (`y` or `m`) + #[cfg(CONFIG_X="y")] // Enabled as a built-in (`y`) + #[cfg(CONFIG_X="m")] // Enabled as a module (`m`) + #[cfg(not(CONFIG_X))] // Disabled diff --git a/Documentation/rust/index.rst b/Documentation/rust/index.rst new file mode 100644 index 000000000000..4ae8c66b94fa --- /dev/null +++ b/Documentation/rust/index.rst @@ -0,0 +1,22 @@ +.. SPDX-License-Identifier: GPL-2.0 + +Rust +==== + +Documentation related to Rust within the kernel. To start using Rust +in the kernel, please read the quick-start.rst guide. + +.. toctree:: + :maxdepth: 1 + + quick-start + general-information + coding-guidelines + arch-support + +.. only:: subproject and html + + Indices + ======= + + * :ref:`genindex` diff --git a/Documentation/rust/quick-start.rst b/Documentation/rust/quick-start.rst new file mode 100644 index 000000000000..13b7744b1e27 --- /dev/null +++ b/Documentation/rust/quick-start.rst @@ -0,0 +1,232 @@ +.. SPDX-License-Identifier: GPL-2.0 + +Quick Start +=========== + +This document describes how to get started with kernel development in Rust. + + +Requirements: Building +---------------------- + +This section explains how to fetch the tools needed for building. + +Some of these requirements might be available from Linux distributions +under names like ``rustc``, ``rust-src``, ``rust-bindgen``, etc. However, +at the time of writing, they are likely not to be recent enough unless +the distribution tracks the latest releases. + +To easily check whether the requirements are met, the following target +can be used:: + + make LLVM=1 rustavailable + +This triggers the same logic used by Kconfig to determine whether +``RUST_IS_AVAILABLE`` should be enabled; but it also explains why not +if that is the case. + + +rustc +***** + +A particular version of the Rust compiler is required. Newer versions may or +may not work because, for the moment, the kernel depends on some unstable +Rust features. + +If ``rustup`` is being used, enter the checked out source code directory +and run:: + + rustup override set $(scripts/min-tool-version.sh rustc) + +Otherwise, fetch a standalone installer or install ``rustup`` from: + + https://www.rust-lang.org + + +Rust standard library source +**************************** + +The Rust standard library source is required because the build system will +cross-compile ``core`` and ``alloc``. + +If ``rustup`` is being used, run:: + + rustup component add rust-src + +The components are installed per toolchain, thus upgrading the Rust compiler +version later on requires re-adding the component. + +Otherwise, if a standalone installer is used, the Rust repository may be cloned +into the installation folder of the toolchain:: + + git clone --recurse-submodules \ + --branch $(scripts/min-tool-version.sh rustc) \ + https://github.com/rust-lang/rust \ + $(rustc --print sysroot)/lib/rustlib/src/rust + +In this case, upgrading the Rust compiler version later on requires manually +updating this clone. + + +libclang +******** + +``libclang`` (part of LLVM) is used by ``bindgen`` to understand the C code +in the kernel, which means LLVM needs to be installed; like when the kernel +is compiled with ``CC=clang`` or ``LLVM=1``. + +Linux distributions are likely to have a suitable one available, so it is +best to check that first. + +There are also some binaries for several systems and architectures uploaded at: + + https://releases.llvm.org/download.html + +Otherwise, building LLVM takes quite a while, but it is not a complex process: + + https://llvm.org/docs/GettingStarted.html#getting-the-source-code-and-building-llvm + +Please see Documentation/kbuild/llvm.rst for more information and further ways +to fetch pre-built releases and distribution packages. + + +bindgen +******* + +The bindings to the C side of the kernel are generated at build time using +the ``bindgen`` tool. A particular version is required. + +Install it via (note that this will download and build the tool from source):: + + cargo install --locked --version $(scripts/min-tool-version.sh bindgen) bindgen + + +Requirements: Developing +------------------------ + +This section explains how to fetch the tools needed for developing. That is, +they are not needed when just building the kernel. + + +rustfmt +******* + +The ``rustfmt`` tool is used to automatically format all the Rust kernel code, +including the generated C bindings (for details, please see +coding-guidelines.rst). + +If ``rustup`` is being used, its ``default`` profile already installs the tool, +thus nothing needs to be done. If another profile is being used, the component +can be installed manually:: + + rustup component add rustfmt + +The standalone installers also come with ``rustfmt``. + + +clippy +****** + +``clippy`` is a Rust linter. Running it provides extra warnings for Rust code. +It can be run by passing ``CLIPPY=1`` to ``make`` (for details, please see +general-information.rst). + +If ``rustup`` is being used, its ``default`` profile already installs the tool, +thus nothing needs to be done. If another profile is being used, the component +can be installed manually:: + + rustup component add clippy + +The standalone installers also come with ``clippy``. + + +cargo +***** + +``cargo`` is the Rust native build system. It is currently required to run +the tests since it is used to build a custom standard library that contains +the facilities provided by the custom ``alloc`` in the kernel. The tests can +be run using the ``rusttest`` Make target. + +If ``rustup`` is being used, all the profiles already install the tool, +thus nothing needs to be done. + +The standalone installers also come with ``cargo``. + + +rustdoc +******* + +``rustdoc`` is the documentation tool for Rust. It generates pretty HTML +documentation for Rust code (for details, please see +general-information.rst). + +``rustdoc`` is also used to test the examples provided in documented Rust code +(called doctests or documentation tests). The ``rusttest`` Make target uses +this feature. + +If ``rustup`` is being used, all the profiles already install the tool, +thus nothing needs to be done. + +The standalone installers also come with ``rustdoc``. + + +rust-analyzer +************* + +The `rust-analyzer <https://rust-analyzer.github.io/>`_ language server can +be used with many editors to enable syntax highlighting, completion, go to +definition, and other features. + +``rust-analyzer`` needs a configuration file, ``rust-project.json``, which +can be generated by the ``rust-analyzer`` Make target. + + +Configuration +------------- + +``Rust support`` (``CONFIG_RUST``) needs to be enabled in the ``General setup`` +menu. The option is only shown if a suitable Rust toolchain is found (see +above), as long as the other requirements are met. In turn, this will make +visible the rest of options that depend on Rust. + +Afterwards, go to:: + + Kernel hacking + -> Sample kernel code + -> Rust samples + +And enable some sample modules either as built-in or as loadable. + + +Building +-------- + +Building a kernel with a complete LLVM toolchain is the best supported setup +at the moment. That is:: + + make LLVM=1 + +For architectures that do not support a full LLVM toolchain, use:: + + make CC=clang + +Using GCC also works for some configurations, but it is very experimental at +the moment. + + +Hacking +------- + +To dive deeper, take a look at the source code of the samples +at ``samples/rust/``, the Rust support code under ``rust/`` and +the ``Rust hacking`` menu under ``Kernel hacking``. + +If GDB/Binutils is used and Rust symbols are not getting demangled, the reason +is the toolchain does not support Rust's new v0 mangling scheme yet. +There are a few ways out: + + - Install a newer release (GDB >= 10.2, Binutils >= 2.36). + + - Some versions of GDB (e.g. vanilla GDB 10.1) are able to use + the pre-demangled names embedded in the debug info (``CONFIG_DEBUG_INFO``). diff --git a/MAINTAINERS b/MAINTAINERS index dcf675bbfbe9..c82daad19c3d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -17755,6 +17755,24 @@ F: include/rv/ F: kernel/trace/rv/ F: tools/verification/ +RUST +M: Miguel Ojeda <ojeda@kernel.org> +M: Alex Gaynor <alex.gaynor@gmail.com> +M: Wedson Almeida Filho <wedsonaf@gmail.com> +R: Boqun Feng <boqun.feng@gmail.com> +R: Gary Guo <gary@garyguo.net> +R: Björn Roy Baron <bjorn3_gh@protonmail.com> +L: rust-for-linux@vger.kernel.org +S: Supported +W: https://github.com/Rust-for-Linux/linux +B: https://github.com/Rust-for-Linux/linux/issues +T: git https://github.com/Rust-for-Linux/linux.git rust-next +F: Documentation/rust/ +F: rust/ +F: samples/rust/ +F: scripts/*rust* +K: \b(?i:rust)\b + RXRPC SOCKETS (AF_RXRPC) M: David Howells <dhowells@redhat.com> M: Marc Dionne <marc.dionne@auristor.com> @@ -120,6 +120,15 @@ endif export KBUILD_CHECKSRC +# Enable "clippy" (a linter) as part of the Rust compilation. +# +# Use 'make CLIPPY=1' to enable it. +ifeq ("$(origin CLIPPY)", "command line") + KBUILD_CLIPPY := $(CLIPPY) +endif + +export KBUILD_CLIPPY + # Use make M=dir or set the environment variable KBUILD_EXTMOD to specify the # directory of external module to build. Setting M= takes precedence. ifeq ("$(origin M)", "command line") @@ -270,14 +279,14 @@ no-dot-config-targets := $(clean-targets) \ cscope gtags TAGS tags help% %docs check% coccicheck \ $(version_h) headers headers_% archheaders archscripts \ %asm-generic kernelversion %src-pkg dt_binding_check \ - outputmakefile + outputmakefile rustavailable rustfmt rustfmtcheck # Installation targets should not require compiler. Unfortunately, vdso_install # is an exception where build artifacts may be updated. This must be fixed. no-compiler-targets := $(no-dot-config-targets) install dtbs_install \ headers_install modules_install kernelrelease image_name no-sync-config-targets := $(no-dot-config-targets) %install kernelrelease \ image_name -single-targets := %.a %.i %.ko %.lds %.ll %.lst %.mod %.o %.s %.symtypes %/ +single-targets := %.a %.i %.rsi %.ko %.lds %.ll %.lst %.mod %.o %.s %.symtypes %/ config-build := mixed-build := @@ -439,6 +448,7 @@ else HOSTCC = gcc HOSTCXX = g++ endif +HOSTRUSTC = rustc HOSTPKG_CONFIG = pkg-config KBUILD_USERHOSTCFLAGS := -Wall -Wmissing-prototypes -Wstrict-prototypes \ @@ -447,8 +457,26 @@ KBUILD_USERHOSTCFLAGS := -Wall -Wmissing-prototypes -Wstrict-prototypes \ KBUILD_USERCFLAGS := $(KBUILD_USERHOSTCFLAGS) $(USERCFLAGS) KBUILD_USERLDFLAGS := $(USERLDFLAGS) +# These flags apply to all Rust code in the tree, including the kernel and +# host programs. +export rust_common_flags := --edition=2021 \ + -Zbinary_dep_depinfo=y \ + -Dunsafe_op_in_unsafe_fn -Drust_2018_idioms \ + -Dunreachable_pub -Dnon_ascii_idents \ + -Wmissing_docs \ + -Drustdoc::missing_crate_level_docs \ + -Dclippy::correctness -Dclippy::style \ + -Dclippy::suspicious -Dclippy::complexity \ + -Dclippy::perf \ + -Dclippy::let_unit_value -Dclippy::mut_mut \ + -Dclippy::needless_bitwise_bool \ + -Dclippy::needless_continue \ + -Wclippy::dbg_macro + KBUILD_HOSTCFLAGS := $(KBUILD_USERHOSTCFLAGS) $(HOST_LFS_CFLAGS) $(HOSTCFLAGS) KBUILD_HOSTCXXFLAGS := -Wall -O2 $(HOST_LFS_CFLAGS) $(HOSTCXXFLAGS) +KBUILD_HOSTRUSTFLAGS := $(rust_common_flags) -O -Cstrip=debuginfo \ + -Zallow-features= $(HOSTRUSTFLAGS) KBUILD_HOSTLDFLAGS := $(HOST_LFS_LDFLAGS) $(HOSTLDFLAGS) KBUILD_HOSTLDLIBS := $(HOST_LFS_LIBS) $(HOSTLDLIBS) @@ -473,6 +501,12 @@ OBJDUMP = $(CROSS_COMPILE)objdump READELF = $(CROSS_COMPILE)readelf STRIP = $(CROSS_COMPILE)strip endif +RUSTC = rustc +RUSTDOC = rustdoc +RUSTFMT = rustfmt +CLIPPY_DRIVER = clippy-driver +BINDGEN = bindgen +CARGO = cargo PAHOLE = pahole RESOLVE_BTFIDS = $(objtree)/tools/bpf/resolve_btfids/resolve_btfids LEX = flex @@ -498,9 +532,11 @@ CHECKFLAGS := -D__linux__ -Dlinux -D__STDC__ -Dunix -D__unix__ \ -Wbitwise -Wno-return-void -Wno-unknown-attribute $(CF) NOSTDINC_FLAGS := CFLAGS_MODULE = +RUSTFLAGS_MODULE = AFLAGS_MODULE = LDFLAGS_MODULE = CFLAGS_KERNEL = +RUSTFLAGS_KERNEL = AFLAGS_KERNEL = LDFLAGS_vmlinux = @@ -529,15 +565,43 @@ KBUILD_CFLAGS := -Wall -Wundef -Werror=strict-prototypes -Wno-trigraphs \ -Werror=return-type -Wno-format-security \ -std=gnu11 KBUILD_CPPFLAGS := -D__KERNEL__ +KBUILD_RUSTFLAGS := $(rust_common_flags) \ + --target=$(objtree)/rust/target.json \ + -Cpanic=abort -Cembed-bitcode=n -Clto=n \ + -Cforce-unwind-tables=n -Ccodegen-units=1 \ + -Csymbol-mangling-version=v0 \ + -Crelocation-model=static \ + -Zfunction-sections=n \ + -Dclippy::float_arithmetic + KBUILD_AFLAGS_KERNEL := KBUILD_CFLAGS_KERNEL := +KBUILD_RUSTFLAGS_KERNEL := KBUILD_AFLAGS_MODULE := -DMODULE KBUILD_CFLAGS_MODULE := -DMODULE +KBUILD_RUSTFLAGS_MODULE := --cfg MODULE KBUILD_LDFLAGS_MODULE := KBUILD_LDFLAGS := CLANG_FLAGS := +ifeq ($(KBUILD_CLIPPY),1) + RUSTC_OR_CLIPPY_QUIET := CLIPPY + RUSTC_OR_CLIPPY = $(CLIPPY_DRIVER) +else + RUSTC_OR_CLIPPY_QUIET := RUSTC + RUSTC_OR_CLIPPY = $(RUSTC) +endif + +ifdef RUST_LIB_SRC + export RUST_LIB_SRC +endif + +# Allows the usage of unstable features in stable compilers. +export RUSTC_BOOTSTRAP := 1 + export ARCH SRCARCH CONFIG_SHELL BASH HOSTCC KBUILD_HOSTCFLAGS CROSS_COMPILE LD CC HOSTPKG_CONFIG +export RUSTC RUSTDOC RUSTFMT RUSTC_OR_CLIPPY_QUIET RUSTC_OR_CLIPPY BINDGEN CARGO +export HOSTRUSTC KBUILD_HOSTRUSTFLAGS export CPP AR NM STRIP OBJCOPY OBJDUMP READELF PAHOLE RESOLVE_BTFIDS LEX YACC AWK INSTALLKERNEL export PERL PYTHON3 CHECK CHECKFLAGS MAKE UTS_MACHINE HOSTCXX export KGZIP KBZIP2 KLZOP LZMA LZ4 XZ ZSTD @@ -546,9 +610,10 @@ export KBUILD_USERCFLAGS KBUILD_USERLDFLAGS export KBUILD_CPPFLAGS NOSTDINC_FLAGS LINUXINCLUDE OBJCOPYFLAGS KBUILD_LDFLAGS export KBUILD_CFLAGS CFLAGS_KERNEL CFLAGS_MODULE +export KBUILD_RUSTFLAGS RUSTFLAGS_KERNEL RUSTFLAGS_MODULE export KBUILD_AFLAGS AFLAGS_KERNEL AFLAGS_MODULE -export KBUILD_AFLAGS_MODULE KBUILD_CFLAGS_MODULE KBUILD_LDFLAGS_MODULE -export KBUILD_AFLAGS_KERNEL KBUILD_CFLAGS_KERNEL +export KBUILD_AFLAGS_MODULE KBUILD_CFLAGS_MODULE KBUILD_RUSTFLAGS_MODULE KBUILD_LDFLAGS_MODULE +export KBUILD_AFLAGS_KERNEL KBUILD_CFLAGS_KERNEL KBUILD_RUSTFLAGS_KERNEL export PAHOLE_FLAGS # Files to ignore in find ... statements @@ -729,7 +794,7 @@ $(KCONFIG_CONFIG): # # Do not use $(call cmd,...) here. That would suppress prompts from syncconfig, # so you cannot notice that Kconfig is waiting for the user input. -%/config/auto.conf %/config/auto.conf.cmd %/generated/autoconf.h: $(KCONFIG_CONFIG) +%/config/auto.conf %/config/auto.conf.cmd %/generated/autoconf.h %/generated/rustc_cfg: $(KCONFIG_CONFIG) $(Q)$(kecho) " SYNC $@" $(Q)$(MAKE) -f $(srctree)/Makefile syncconfig else # !may-sync-config @@ -758,10 +823,17 @@ KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member) ifdef CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE KBUILD_CFLAGS += -O2 +KBUILD_RUSTFLAGS += -Copt-level=2 else ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE KBUILD_CFLAGS += -Os +KBUILD_RUSTFLAGS += -Copt-level=s endif +# Always set `debug-assertions` and `overflow-checks` because their default +# depends on `opt-level` and `debug-assertions`, respectively. +KBUILD_RUSTFLAGS += -Cdebug-assertions=$(if $(CONFIG_RUST_DEBUG_ASSERTIONS),y,n) +KBUILD_RUSTFLAGS += -Coverflow-checks=$(if $(CONFIG_RUST_OVERFLOW_CHECKS),y,n) + # Tell gcc to never replace conditional load with a non-conditional one ifdef CONFIG_CC_IS_GCC # gcc-10 renamed --param=allow-store-data-races=0 to @@ -792,6 +864,9 @@ KBUILD_CFLAGS-$(CONFIG_WERROR) += -Werror KBUILD_CFLAGS-$(CONFIG_CC_NO_ARRAY_BOUNDS) += -Wno-array-bounds KBUILD_CFLAGS += $(KBUILD_CFLAGS-y) $(CONFIG_CC_IMPLICIT_FALLTHROUGH) +KBUILD_RUSTFLAGS-$(CONFIG_WERROR) += -Dwarnings +KBUILD_RUSTFLAGS += $(KBUILD_RUSTFLAGS-y) + ifdef CONFIG_CC_IS_CLANG KBUILD_CPPFLAGS += -Qunused-arguments # The kernel builds with '-std=gnu11' so use of GNU extensions is acceptable. @@ -812,12 +887,15 @@ KBUILD_CFLAGS += $(call cc-disable-warning, dangling-pointer) ifdef CONFIG_FRAME_POINTER KBUILD_CFLAGS += -fno-omit-frame-pointer -fno-optimize-sibling-calls +KBUILD_RUSTFLAGS += -Cforce-frame-pointers=y else # Some targets (ARM with Thumb2, for example), can't be built with frame # pointers. For those, we don't have FUNCTION_TRACER automatically # select FRAME_POINTER. However, FUNCTION_TRACER adds -pg, and this is # incompatible with -fomit-frame-pointer with current GCC, so we don't use # -fomit-frame-pointer with FUNCTION_TRACER. +# In the Rust target specification, "frame-pointer" is set explicitly +# to "may-omit". ifndef CONFIG_FUNCTION_TRACER KBUILD_CFLAGS += -fomit-frame-pointer endif @@ -882,8 +960,10 @@ ifdef CONFIG_DEBUG_SECTION_MISMATCH KBUILD_CFLAGS += -fno-inline-functions-called-once endif +# `rustc`'s `-Zfunction-sections` applies to data too (as of 1.59.0). ifdef CONFIG_LD_DEAD_CODE_DATA_ELIMINATION KBUILD_CFLAGS_KERNEL += -ffunction-sections -fdata-sections +KBUILD_RUSTFLAGS_KERNEL += -Zfunction-sections=y LDFLAGS_vmlinux += --gc-sections endif @@ -1026,10 +1106,11 @@ include $(addprefix $(srctree)/, $(include-y)) # Do not add $(call cc-option,...) below this line. When you build the kernel # from the clean source tree, the GCC plugins do not exist at this point. -# Add user supplied CPPFLAGS, AFLAGS and CFLAGS as the last assignments +# Add user supplied CPPFLAGS, AFLAGS, CFLAGS and RUSTFLAGS as the last assignments KBUILD_CPPFLAGS += $(KCPPFLAGS) KBUILD_AFLAGS += $(KAFLAGS) KBUILD_CFLAGS += $(KCFLAGS) +KBUILD_RUSTFLAGS += $(KRUSTFLAGS) KBUILD_LDFLAGS_MODULE += --build-id=sha1 LDFLAGS_vmlinux += --build-id=sha1 @@ -1104,6 +1185,7 @@ ifeq ($(KBUILD_EXTMOD),) core-y += kernel/ certs/ mm/ fs/ ipc/ security/ crypto/ core-$(CONFIG_BLOCK) += block/ core-$(CONFIG_IO_URING) += io_uring/ +core-$(CONFIG_RUST) += rust/ vmlinux-dirs := $(patsubst %/,%,$(filter %/, \ $(core-y) $(core-m) $(drivers-y) $(drivers-m) \ @@ -1206,6 +1288,10 @@ prepare0: archprepare # All the preparing.. prepare: prepare0 +ifdef CONFIG_RUST + $(Q)$(CONFIG_SHELL) $(srctree)/scripts/rust_is_available.sh -v + $(Q)$(MAKE) $(build)=rust +endif PHONY += remove-stale-files remove-stale-files: @@ -1499,7 +1585,7 @@ endif # CONFIG_MODULES # Directories & files removed with 'make clean' CLEAN_FILES += include/ksym vmlinux.symvers modules-only.symvers \ modules.builtin modules.builtin.modinfo modules.nsdeps \ - compile_commands.json .thinlto-cache + compile_commands.json .thinlto-cache rust/test rust/doc # Directories & files removed with 'make mrproper' MRPROPER_FILES += include/config include/generated \ @@ -1510,7 +1596,8 @@ MRPROPER_FILES += include/config include/generated \ certs/signing_key.pem \ certs/x509.genkey \ vmlinux-gdb.py \ - *.spec + *.spec \ + rust/target.json rust/libmacros.so # clean - Delete most, but leave enough to build external modules # @@ -1535,6 +1622,9 @@ $(mrproper-dirs): mrproper: clean $(mrproper-dirs) $(call cmd,rmfiles) + @find . $(RCS_FIND_IGNORE) \ + \( -name '*.rmeta' \) \ + -type f -print | xargs rm -f # distclean # @@ -1622,6 +1712,24 @@ help: @echo ' kselftest-merge - Merge all the config dependencies of' @echo ' kselftest to existing .config.' @echo '' + @echo 'Rust targets:' + @echo ' rustavailable - Checks whether the Rust toolchain is' + @echo ' available and, if not, explains why.' + @echo ' rustfmt - Reformat all the Rust code in the kernel' + @echo ' rustfmtcheck - Checks if all the Rust code in the kernel' + @echo ' is formatted, printing a diff otherwise.' + @echo ' rustdoc - Generate Rust documentation' + @echo ' (requires kernel .config)' + @echo ' rusttest - Runs the Rust tests' + @echo ' (requires kernel .config; downloads external repos)' + @echo ' rust-analyzer - Generate rust-project.json rust-analyzer support file' + @echo ' (requires kernel .config)' + @echo ' dir/file.[os] - Build specified target only' + @echo ' dir/file.rsi - Build macro expanded source, similar to C preprocessing.' + @echo ' Run with RUSTFMT=n to skip reformatting if needed.' + @echo ' The output is not intended to be compilable.' + @echo ' dir/file.ll - Build the LLVM assembly file' + @echo '' @$(if $(dtstree), \ echo 'Devicetree:'; \ echo '* dtbs - Build device tree blobs for enabled boards'; \ @@ -1694,6 +1802,52 @@ PHONY += $(DOC_TARGETS) $(DOC_TARGETS): $(Q)$(MAKE) $(build)=Documentation $@ + +# Rust targets +# --------------------------------------------------------------------------- + +# "Is Rust available?" target +PHONY += rustavailable +rustavailable: + $(Q)$(CONFIG_SHELL) $(srctree)/scripts/rust_is_available.sh -v && echo "Rust is available!" + +# Documentation target +# +# Using the singular to avoid running afoul of `no-dot-config-targets`. +PHONY += rustdoc +rustdoc: prepare + $(Q)$(MAKE) $(build)=rust $@ + +# Testing target +PHONY += rusttest +rusttest: prepare + $(Q)$(MAKE) $(build)=rust $@ + +# Formatting targets +PHONY += rustfmt rustfmtcheck + +# We skip `rust/alloc` since we want to minimize the diff w.r.t. upstream. +# +# We match using absolute paths since `find` does not resolve them +# when matching, which is a problem when e.g. `srctree` is `..`. +# We `grep` afterwards in order to remove the directory entry itself. +rustfmt: + $(Q)find $(abs_srctree) -type f -name '*.rs' \ + -o -path $(abs_srctree)/rust/alloc -prune \ + -o -path $(abs_objtree)/rust/test -prune \ + | grep -Fv $(abs_srctree)/rust/alloc \ + | grep -Fv $(abs_objtree)/rust/test \ + | grep -Fv generated \ + | xargs $(RUSTFMT) $(rustfmt_flags) + +rustfmtcheck: rustfmt_flags = --check +rustfmtcheck: rustfmt + +# IDE support targets +PHONY += rust-analyzer +rust-analyzer: + $(Q)$(MAKE) $(build)=rust $@ + # Misc # --------------------------------------------------------------------------- @@ -1861,7 +2015,7 @@ $(clean-dirs): clean: $(clean-dirs) $(call cmd,rmfiles) @find $(or $(KBUILD_EXTMOD), .) $(RCS_FIND_IGNORE) \ - \( -name '*.[aios]' -o -name '*.ko' -o -name '.*.cmd' \ + \( -name '*.[aios]' -o -name '*.rsi' -o -name '*.ko' -o -name '.*.cmd' \ -o -name '*.ko.*' \ -o -name '*.dtb' -o -name '*.dtbo' -o -name '*.dtb.S' -o -name '*.dt.yaml' \ -o -name '*.dwo' -o -name '*.lst' \ diff --git a/arch/Kconfig b/arch/Kconfig index 8b311e400ec1..d9b4ae0fc805 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -355,6 +355,12 @@ config HAVE_RSEQ This symbol should be selected by an architecture if it supports an implementation of restartable sequences. +config HAVE_RUST + bool + help + This symbol should be selected by an architecture if it + supports Rust. + config HAVE_FUNCTION_ARG_ACCESS_API bool help diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index f9920f1341c8..3ca198742b10 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -257,6 +257,7 @@ config X86 select HAVE_STATIC_CALL_INLINE if HAVE_OBJTOOL select HAVE_PREEMPT_DYNAMIC_CALL select HAVE_RSEQ + select HAVE_RUST if X86_64 select HAVE_SYSCALL_TRACEPOINTS select HAVE_UACCESS_VALIDATION if HAVE_OBJTOOL select HAVE_UNSTABLE_SCHED_CLOCK diff --git a/arch/x86/Makefile b/arch/x86/Makefile index bafbd905e6e7..2d7e640674c6 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -68,6 +68,7 @@ export BITS # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=53383 # KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -mno-avx +KBUILD_RUSTFLAGS += -Ctarget-feature=-sse,-sse2,-sse3,-ssse3,-sse4.1,-sse4.2,-avx,-avx2 ifeq ($(CONFIG_X86_KERNEL_IBT),y) # @@ -155,8 +156,17 @@ else cflags-$(CONFIG_GENERIC_CPU) += -mtune=generic KBUILD_CFLAGS += $(cflags-y) + rustflags-$(CONFIG_MK8) += -Ctarget-cpu=k8 + rustflags-$(CONFIG_MPSC) += -Ctarget-cpu=nocona + rustflags-$(CONFIG_MCORE2) += -Ctarget-cpu=core2 + rustflags-$(CONFIG_MATOM) += -Ctarget-cpu=atom + rustflags-$(CONFIG_GENERIC_CPU) += -Ztune-cpu=generic + KBUILD_RUSTFLAGS += $(rustflags-y) + KBUILD_CFLAGS += -mno-red-zone KBUILD_CFLAGS += -mcmodel=kernel + KBUILD_RUSTFLAGS += -Cno-redzone=y + KBUILD_RUSTFLAGS += -Ccode-model=kernel endif # diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 4f2a819fd60a..50b3f6b9502e 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -4,8 +4,12 @@ #ifndef __ASSEMBLY__ +/* + * Skipped when running bindgen due to a libclang issue; + * see https://github.com/rust-lang/rust-bindgen/issues/2244. + */ #if defined(CONFIG_DEBUG_INFO_BTF) && defined(CONFIG_PAHOLE_HAS_BTF_TAG) && \ - __has_attribute(btf_type_tag) + __has_attribute(btf_type_tag) && !defined(__BINDGEN__) # define BTF_TYPE_TAG(value) __attribute__((btf_type_tag(#value))) #else # define BTF_TYPE_TAG(value) /* nothing */ diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h index ad39636e0c3f..649faac31ddb 100644 --- a/include/linux/kallsyms.h +++ b/include/linux/kallsyms.h @@ -15,7 +15,7 @@ #include <asm/sections.h> -#define KSYM_NAME_LEN 128 +#define KSYM_NAME_LEN 512 #define KSYM_SYMBOL_LEN (sizeof("%s+%#lx/%#lx [%s %s]") + \ (KSYM_NAME_LEN - 1) + \ 2*(BITS_PER_LONG*3/10) + (MODULE_NAME_LEN - 1) + \ diff --git a/init/Kconfig b/init/Kconfig index 532362fcfe31..a078cb026523 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -60,6 +60,17 @@ config LLD_VERSION default $(ld-version) if LD_IS_LLD default 0 +config RUST_IS_AVAILABLE + def_bool $(success,$(srctree)/scripts/rust_is_available.sh) + help + This shows whether a suitable Rust toolchain is available (found). + + Please see Documentation/rust/quick-start.rst for instructions on how + to satify the build requirements of Rust support. + + In particular, the Makefile target 'rustavailable' is useful to check + why the Rust toolchain is not being detected. + config CC_CAN_LINK bool default $(success,$(srctree)/scripts/cc-can-link.sh $(CC) $(CLANG_FLAGS) $(USERCFLAGS) $(USERLDFLAGS) $(m64-flag)) if 64BIT @@ -147,7 +158,8 @@ config WERROR default COMPILE_TEST help A kernel build should not cause any compiler warnings, and this - enables the '-Werror' flag to enforce that rule by default. + enables the '-Werror' (for C) and '-Dwarnings' (for Rust) flags + to enforce that rule by default. However, if you have a new (or very old) compiler with odd and unusual warnings, or you have some architecture with problems, @@ -1899,6 +1911,38 @@ config PROFILING Say Y here to enable the extended profiling support mechanisms used by profilers. +config RUST + bool "Rust support" + depends on HAVE_RUST + depends on RUST_IS_AVAILABLE + depends on !MODVERSIONS + depends on !GCC_PLUGINS + depends on !RANDSTRUCT + depends on !DEBUG_INFO_BTF + select CONSTRUCTORS + help + Enables Rust support in the kernel. + + This allows other Rust-related options, like drivers written in Rust, + to be selected. + + It is also required to be able to load external kernel modules + written in Rust. + + See Documentation/rust/ for more information. + + If unsure, say N. + +config RUSTC_VERSION_TEXT + string + depends on RUST + default $(shell,command -v $(RUSTC) >/dev/null 2>&1 && $(RUSTC) --version || echo n) + +config BINDGEN_VERSION_TEXT + string + depends on RUST + default $(shell,command -v $(BINDGEN) >/dev/null 2>&1 && $(BINDGEN) --version || echo n) + # # Place an empty function call at each tracepoint site. Can be # dynamically changed for a probe function. diff --git a/kernel/configs/rust.config b/kernel/configs/rust.config new file mode 100644 index 000000000000..38a7c5362c9c --- /dev/null +++ b/kernel/configs/rust.config @@ -0,0 +1 @@ +CONFIG_RUST=y diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 3e7e2c2ad2f7..fc5e26348d25 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -50,12 +50,20 @@ static unsigned int kallsyms_expand_symbol(unsigned int off, data = &kallsyms_names[off]; len = *data; data++; + off++; + + /* If MSB is 1, it is a "big" symbol, so needs an additional byte. */ + if ((len & 0x80) != 0) { + len = (len & 0x7F) | (*data << 7); + data++; + off++; + } /* * Update the offset to return the offset for the next symbol on * the compressed stream. */ - off += len + 1; + off += len; /* * For every byte on the compressed symbol data, copy the table @@ -108,7 +116,7 @@ static char kallsyms_get_symbol_type(unsigned int off) static unsigned int get_symbol_offset(unsigned long pos) { const u8 *name; - int i; + int i, len; /* * Use the closest marker we have. We have markers every 256 positions, @@ -122,8 +130,18 @@ static unsigned int get_symbol_offset(unsigned long pos) * so we just need to add the len to the current pointer for every * symbol we wish to skip. */ - for (i = 0; i < (pos & 0xFF); i++) - name = name + (*name) + 1; + for (i = 0; i < (pos & 0xFF); i++) { + len = *name; + + /* + * If MSB is 1, it is a "big" symbol, so we need to look into + * the next byte (and skip it, too). + */ + if ((len & 0x80) != 0) + len = ((len & 0x7F) | (name[1] << 7)) + 1; + + name = name + len + 1; + } return name - kallsyms_names; } diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c index bc475e62279d..ec06ce59d728 100644 --- a/kernel/livepatch/core.c +++ b/kernel/livepatch/core.c @@ -213,7 +213,7 @@ static int klp_resolve_symbols(Elf_Shdr *sechdrs, const char *strtab, * we use the smallest/strictest upper bound possible (56, based on * the current definition of MODULE_NAME_LEN) to prevent overflows. */ - BUILD_BUG_ON(MODULE_NAME_LEN < 56 || KSYM_NAME_LEN != 128); + BUILD_BUG_ON(MODULE_NAME_LEN < 56 || KSYM_NAME_LEN != 512); relas = (Elf_Rela *) relasec->sh_addr; /* For each rela in this klp relocation section */ @@ -227,7 +227,7 @@ static int klp_resolve_symbols(Elf_Shdr *sechdrs, const char *strtab, /* Format: .klp.sym.sym_objname.sym_name,sympos */ cnt = sscanf(strtab + sym->st_name, - ".klp.sym.%55[^.].%127[^,],%lu", + ".klp.sym.%55[^.].%511[^,],%lu", sym_objname, sym_name, &sympos); if (cnt != 3) { pr_err("symbol %s has an incorrectly formatted name\n", diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index d3e5f36bb01e..e62271da937f 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -2710,6 +2710,40 @@ config HYPERV_TESTING endmenu # "Kernel Testing and Coverage" +menu "Rust hacking" + +config RUST_DEBUG_ASSERTIONS + bool "Debug assertions" + depends on RUST + help + Enables rustc's `-Cdebug-assertions` codegen option. + + This flag lets you turn `cfg(debug_assertions)` conditional + compilation on or off. This can be used to enable extra debugging + code in development but not in production. For example, it controls + the behavior of the standard library's `debug_assert!` macro. + + Note that this will apply to all Rust code, including `core`. + + If unsure, say N. + +config RUST_OVERFLOW_CHECKS + bool "Overflow checks" + default y + depends on RUST + help + Enables rustc's `-Coverflow-checks` codegen option. + + This flag allows you to control the behavior of runtime integer + overflow. When overflow-checks are enabled, a Rust panic will occur + on overflow. + + Note that this will apply to all Rust code, including `core`. + + If unsure, say Y. + +endmenu # "Rust" + source "Documentation/Kconfig" endmenu # Kernel hacking diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 3c1853a9d1c0..c414a8d9f1ea 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -2246,6 +2246,9 @@ int __init no_hash_pointers_enable(char *str) } early_param("no_hash_pointers", no_hash_pointers_enable); +/* Used for Rust formatting ('%pA'). */ +char *rust_fmt_argument(char *buf, char *end, void *ptr); + /* * Show a '%p' thing. A kernel extension is that the '%p' is followed * by an extra set of alphanumeric characters that are extended format @@ -2372,6 +2375,10 @@ early_param("no_hash_pointers", no_hash_pointers_enable); * * Note: The default behaviour (unadorned %p) is to hash the address, * rendering it useful as a unique identifier. + * + * There is also a '%pA' format specifier, but it is only intended to be used + * from Rust code to format core::fmt::Arguments. Do *not* use it from C. + * See rust/kernel/print.rs for details. */ static noinline_for_stack char *pointer(const char *fmt, char *buf, char *end, void *ptr, @@ -2444,6 +2451,12 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr, return device_node_string(buf, end, ptr, spec, fmt + 1); case 'f': return fwnode_string(buf, end, ptr, spec, fmt + 1); + case 'A': + if (!IS_ENABLED(CONFIG_RUST)) { + WARN_ONCE(1, "Please remove %%pA from non-Rust code\n"); + return error_string(buf, end, "(%pA?)", spec); + } + return rust_fmt_argument(buf, end, ptr); case 'x': return pointer_string(buf, end, ptr, spec); case 'e': diff --git a/rust/.gitignore b/rust/.gitignore new file mode 100644 index 000000000000..9bd1af8e05a1 --- /dev/null +++ b/rust/.gitignore @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0 + +target.json +bindings_generated.rs +bindings_helpers_generated.rs +exports_*_generated.h +doc/ +test/ diff --git a/rust/Makefile b/rust/Makefile new file mode 100644 index 000000000000..7700d3853404 --- /dev/null +++ b/rust/Makefile @@ -0,0 +1,381 @@ +# SPDX-License-Identifier: GPL-2.0 + +always-$(CONFIG_RUST) += target.json +no-clean-files += target.json + +obj-$(CONFIG_RUST) += core.o compiler_builtins.o +always-$(CONFIG_RUST) += exports_core_generated.h + +# Missing prototypes are expected in the helpers since these are exported +# for Rust only, thus there is no header nor prototypes. +obj-$(CONFIG_RUST) += helpers.o +CFLAGS_REMOVE_helpers.o = -Wmissing-prototypes -Wmissing-declarations + +always-$(CONFIG_RUST) += libmacros.so +no-clean-files += libmacros.so + +always-$(CONFIG_RUST) += bindings/bindings_generated.rs bindings/bindings_helpers_generated.rs +obj-$(CONFIG_RUST) += alloc.o bindings.o kernel.o +always-$(CONFIG_RUST) += exports_alloc_generated.h exports_bindings_generated.h \ + exports_kernel_generated.h + +obj-$(CONFIG_RUST) += exports.o + +# Avoids running `$(RUSTC)` for the sysroot when it may not be available. +ifdef CONFIG_RUST + +# `$(rust_flags)` is passed in case the user added `--sysroot`. +rustc_sysroot := $(shell $(RUSTC) $(rust_flags) --print sysroot) +rustc_host_target := $(shell $(RUSTC) --version --verbose | grep -F 'host: ' | cut -d' ' -f2) +RUST_LIB_SRC ?= $(rustc_sysroot)/lib/rustlib/src/rust/library + +ifeq ($(quiet),silent_) +cargo_quiet=-q +rust_test_quiet=-q +rustdoc_test_quiet=--test-args -q +else ifeq ($(quiet),quiet_) +rust_test_quiet=-q +rustdoc_test_quiet=--test-args -q +else +cargo_quiet=--verbose +endif + +core-cfgs = \ + --cfg no_fp_fmt_parse + +alloc-cfgs = \ + --cfg no_fmt \ + --cfg no_global_oom_handling \ + --cfg no_macros \ + --cfg no_rc \ + --cfg no_str \ + --cfg no_string \ + --cfg no_sync \ + --cfg no_thin + +quiet_cmd_rustdoc = RUSTDOC $(if $(rustdoc_host),H, ) $< + cmd_rustdoc = \ + OBJTREE=$(abspath $(objtree)) \ + $(RUSTDOC) $(if $(rustdoc_host),$(rust_common_flags),$(rust_flags)) \ + $(rustc_target_flags) -L$(objtree)/$(obj) \ + --output $(objtree)/$(obj)/doc \ + --crate-name $(subst rustdoc-,,$@) \ + @$(objtree)/include/generated/rustc_cfg $< + +# The `html_logo_url` and `html_favicon_url` forms of the `doc` attribute +# can be used to specify a custom logo. However: +# - The given value is used as-is, thus it cannot be relative or a local file +# (unlike the non-custom case) since the generated docs have subfolders. +# - It requires adding it to every crate. +# - It requires changing `core` which comes from the sysroot. +# +# Using `-Zcrate-attr` would solve the last two points, but not the first. +# The https://github.com/rust-lang/rfcs/pull/3226 RFC suggests two new +# command-like flags to solve the issue. Meanwhile, we use the non-custom case +# and then retouch the generated files. +rustdoc: rustdoc-core rustdoc-macros rustdoc-compiler_builtins \ + rustdoc-alloc rustdoc-kernel + $(Q)cp $(srctree)/Documentation/images/logo.svg $(objtree)/$(obj)/doc + $(Q)cp $(srctree)/Documentation/images/COPYING-logo $(objtree)/$(obj)/doc + $(Q)find $(objtree)/$(obj)/doc -name '*.html' -type f -print0 | xargs -0 sed -Ei \ + -e 's:rust-logo\.svg:logo.svg:g' \ + -e 's:rust-logo\.png:logo.svg:g' \ + -e 's:favicon\.svg:logo.svg:g' \ + -e 's:<link rel="alternate icon" type="image/png" href="[./]*favicon-(16x16|32x32)\.png">::g' + $(Q)echo '.logo-container > img { object-fit: contain; }' \ + >> $(objtree)/$(obj)/doc/rustdoc.css + +rustdoc-macros: private rustdoc_host = yes +rustdoc-macros: private rustc_target_flags = --crate-type proc-macro \ + --extern proc_macro +rustdoc-macros: $(src)/macros/lib.rs FORCE + $(call if_changed,rustdoc) + +rustdoc-core: private rustc_target_flags = $(core-cfgs) +rustdoc-core: $(RUST_LIB_SRC)/core/src/lib.rs FORCE + $(call if_changed,rustdoc) + +rustdoc-compiler_builtins: $(src)/compiler_builtins.rs rustdoc-core FORCE + $(call if_changed,rustdoc) + +# We need to allow `rustdoc::broken_intra_doc_links` because some +# `no_global_oom_handling` functions refer to non-`no_global_oom_handling` +# functions. Ideally `rustdoc` would have a way to distinguish broken links +# due to things that are "configured out" vs. entirely non-existing ones. +rustdoc-alloc: private rustc_target_flags = $(alloc-cfgs) \ + -Arustdoc::broken_intra_doc_links +rustdoc-alloc: $(src)/alloc/lib.rs rustdoc-core rustdoc-compiler_builtins FORCE + $(call if_changed,rustdoc) + +rustdoc-kernel: private rustc_target_flags = --extern alloc \ + --extern macros=$(objtree)/$(obj)/libmacros.so \ + --extern bindings +rustdoc-kernel: $(src)/kernel/lib.rs rustdoc-core rustdoc-macros \ + rustdoc-compiler_builtins rustdoc-alloc $(obj)/libmacros.so \ + $(obj)/bindings.o FORCE + $(call if_changed,rustdoc) + +quiet_cmd_rustc_test_library = RUSTC TL $< + cmd_rustc_test_library = \ + OBJTREE=$(abspath $(objtree)) \ + $(RUSTC) $(rust_common_flags) \ + @$(objtree)/include/generated/rustc_cfg $(rustc_target_flags) \ + --crate-type $(if $(rustc_test_library_proc),proc-macro,rlib) \ + --out-dir $(objtree)/$(obj)/test --cfg testlib \ + --sysroot $(objtree)/$(obj)/test/sysroot \ + -L$(objtree)/$(obj)/test \ + --crate-name $(subst rusttest-,,$(subst rusttestlib-,,$@)) $< + +rusttestlib-macros: private rustc_target_flags = --extern proc_macro +rusttestlib-macros: private rustc_test_library_proc = yes +rusttestlib-macros: $(src)/macros/lib.rs rusttest-prepare FORCE + $(call if_changed,rustc_test_library) + +rusttestlib-bindings: $(src)/bindings/lib.rs rusttest-prepare FORCE + $(call if_changed,rustc_test_library) + +quiet_cmd_rustdoc_test = RUSTDOC T $< + cmd_rustdoc_test = \ + OBJTREE=$(abspath $(objtree)) \ + $(RUSTDOC) --test $(rust_common_flags) \ + @$(objtree)/include/generated/rustc_cfg \ + $(rustc_target_flags) $(rustdoc_test_target_flags) \ + --sysroot $(objtree)/$(obj)/test/sysroot $(rustdoc_test_quiet) \ + -L$(objtree)/$(obj)/test --output $(objtree)/$(obj)/doc \ + --crate-name $(subst rusttest-,,$@) $< + +# We cannot use `-Zpanic-abort-tests` because some tests are dynamic, +# so for the moment we skip `-Cpanic=abort`. +quiet_cmd_rustc_test = RUSTC T $< + cmd_rustc_test = \ + OBJTREE=$(abspath $(objtree)) \ + $(RUSTC) --test $(rust_common_flags) \ + @$(objtree)/include/generated/rustc_cfg \ + $(rustc_target_flags) --out-dir $(objtree)/$(obj)/test \ + --sysroot $(objtree)/$(obj)/test/sysroot \ + -L$(objtree)/$(obj)/test \ + --crate-name $(subst rusttest-,,$@) $<; \ + $(objtree)/$(obj)/test/$(subst rusttest-,,$@) $(rust_test_quiet) \ + $(rustc_test_run_flags) + +rusttest: rusttest-macros rusttest-kernel + +# This prepares a custom sysroot with our custom `alloc` instead of +# the standard one. +# +# This requires several hacks: +# - Unlike `core` and `alloc`, `std` depends on more than a dozen crates, +# including third-party crates that need to be downloaded, plus custom +# `build.rs` steps. Thus hardcoding things here is not maintainable. +# - `cargo` knows how to build the standard library, but it is an unstable +# feature so far (`-Zbuild-std`). +# - `cargo` only considers the use case of building the standard library +# to use it in a given package. Thus we need to create a dummy package +# and pick the generated libraries from there. +# - Since we only keep a subset of upstream `alloc` in-tree, we need +# to recreate it on the fly by putting our sources on top. +# - The usual ways of modifying the dependency graph in `cargo` do not seem +# to apply for the `-Zbuild-std` steps, thus we have to mislead it +# by modifying the sources in the sysroot. +# - To avoid messing with the user's Rust installation, we create a clone +# of the sysroot. However, `cargo` ignores `RUSTFLAGS` in the `-Zbuild-std` +# steps, thus we use a wrapper binary passed via `RUSTC` to pass the flag. +# +# In the future, we hope to avoid the whole ordeal by either: +# - Making the `test` crate not depend on `std` (either improving upstream +# or having our own custom crate). +# - Making the tests run in kernel space (requires the previous point). +# - Making `std` and friends be more like a "normal" crate, so that +# `-Zbuild-std` and related hacks are not needed. +quiet_cmd_rustsysroot = RUSTSYSROOT + cmd_rustsysroot = \ + rm -rf $(objtree)/$(obj)/test; \ + mkdir -p $(objtree)/$(obj)/test; \ + cp -a $(rustc_sysroot) $(objtree)/$(obj)/test/sysroot; \ + cp -r $(srctree)/$(src)/alloc/* \ + $(objtree)/$(obj)/test/sysroot/lib/rustlib/src/rust/library/alloc/src; \ + echo '\#!/bin/sh' > $(objtree)/$(obj)/test/rustc_sysroot; \ + echo "$(RUSTC) --sysroot=$(abspath $(objtree)/$(obj)/test/sysroot) \"\$$@\"" \ + >> $(objtree)/$(obj)/test/rustc_sysroot; \ + chmod u+x $(objtree)/$(obj)/test/rustc_sysroot; \ + $(CARGO) -q new $(objtree)/$(obj)/test/dummy; \ + RUSTC=$(objtree)/$(obj)/test/rustc_sysroot $(CARGO) $(cargo_quiet) \ + test -Zbuild-std --target $(rustc_host_target) \ + --manifest-path $(objtree)/$(obj)/test/dummy/Cargo.toml; \ + rm $(objtree)/$(obj)/test/sysroot/lib/rustlib/$(rustc_host_target)/lib/*; \ + cp $(objtree)/$(obj)/test/dummy/target/$(rustc_host_target)/debug/deps/* \ + $(objtree)/$(obj)/test/sysroot/lib/rustlib/$(rustc_host_target)/lib + +rusttest-prepare: FORCE + $(call if_changed,rustsysroot) + +rusttest-macros: private rustc_target_flags = --extern proc_macro +rusttest-macros: private rustdoc_test_target_flags = --crate-type proc-macro +rusttest-macros: $(src)/macros/lib.rs rusttest-prepare FORCE + $(call if_changed,rustc_test) + $(call if_changed,rustdoc_test) + +rusttest-kernel: private rustc_target_flags = --extern alloc \ + --extern macros --extern bindings +rusttest-kernel: $(src)/kernel/lib.rs rusttest-prepare \ + rusttestlib-macros rusttestlib-bindings FORCE + $(call if_changed,rustc_test) + $(call if_changed,rustc_test_library) + +filechk_rust_target = $(objtree)/scripts/generate_rust_target < $< + +$(obj)/target.json: $(objtree)/include/config/auto.conf FORCE + $(call filechk,rust_target) + +ifdef CONFIG_CC_IS_CLANG +bindgen_c_flags = $(c_flags) +else +# bindgen relies on libclang to parse C. Ideally, bindgen would support a GCC +# plugin backend and/or the Clang driver would be perfectly compatible with GCC. +# +# For the moment, here we are tweaking the flags on the fly. This is a hack, +# and some kernel configurations may not work (e.g. `GCC_PLUGIN_RANDSTRUCT` +# if we end up using one of those structs). +bindgen_skip_c_flags := -mno-fp-ret-in-387 -mpreferred-stack-boundary=% \ + -mskip-rax-setup -mgeneral-regs-only -msign-return-address=% \ + -mindirect-branch=thunk-extern -mindirect-branch-register \ + -mfunction-return=thunk-extern -mrecord-mcount -mabi=lp64 \ + -mindirect-branch-cs-prefix -mstack-protector-guard% -mtraceback=no \ + -mno-pointers-to-nested-functions -mno-string \ + -mno-strict-align -mstrict-align \ + -fconserve-stack -falign-jumps=% -falign-loops=% \ + -femit-struct-debug-baseonly -fno-ipa-cp-clone -fno-ipa-sra \ + -fno-partial-inlining -fplugin-arg-arm_ssp_per_task_plugin-% \ + -fno-reorder-blocks -fno-allow-store-data-races -fasan-shadow-offset=% \ + -fzero-call-used-regs=% -fno-stack-clash-protection \ + -fno-inline-functions-called-once \ + --param=% --param asan-% + +# Derived from `scripts/Makefile.clang`. +BINDGEN_TARGET_x86 := x86_64-linux-gnu +BINDGEN_TARGET := $(BINDGEN_TARGET_$(SRCARCH)) + +# All warnings are inhibited since GCC builds are very experimental, +# many GCC warnings are not supported by Clang, they may only appear in +# some configurations, with new GCC versions, etc. +bindgen_extra_c_flags = -w --target=$(BINDGEN_TARGET) + +bindgen_c_flags = $(filter-out $(bindgen_skip_c_flags), $(c_flags)) \ + $(bindgen_extra_c_flags) +endif + +ifdef CONFIG_LTO +bindgen_c_flags_lto = $(filter-out $(CC_FLAGS_LTO), $(bindgen_c_flags)) +else +bindgen_c_flags_lto = $(bindgen_c_flags) +endif + +bindgen_c_flags_final = $(bindgen_c_flags_lto) -D__BINDGEN__ + +quiet_cmd_bindgen = BINDGEN $@ + cmd_bindgen = \ + $(BINDGEN) $< $(bindgen_target_flags) \ + --use-core --with-derive-default --ctypes-prefix core::ffi --no-layout-tests \ + --no-debug '.*' \ + --size_t-is-usize -o $@ -- $(bindgen_c_flags_final) -DMODULE \ + $(bindgen_target_cflags) $(bindgen_target_extra) + +$(obj)/bindings/bindings_generated.rs: private bindgen_target_flags = \ + $(shell grep -v '^\#\|^$$' $(srctree)/$(src)/bindgen_parameters) +$(obj)/bindings/bindings_generated.rs: $(src)/bindings/bindings_helper.h \ + $(src)/bindgen_parameters FORCE + $(call if_changed_dep,bindgen) + +# See `CFLAGS_REMOVE_helpers.o` above. In addition, Clang on C does not warn +# with `-Wmissing-declarations` (unlike GCC), so it is not strictly needed here +# given it is `libclang`; but for consistency, future Clang changes and/or +# a potential future GCC backend for `bindgen`, we disable it too. +$(obj)/bindings/bindings_helpers_generated.rs: private bindgen_target_flags = \ + --blacklist-type '.*' --whitelist-var '' \ + --whitelist-function 'rust_helper_.*' +$(obj)/bindings/bindings_helpers_generated.rs: private bindgen_target_cflags = \ + -I$(objtree)/$(obj) -Wno-missing-prototypes -Wno-missing-declarations +$(obj)/bindings/bindings_helpers_generated.rs: private bindgen_target_extra = ; \ + sed -Ei 's/pub fn rust_helper_([a-zA-Z0-9_]*)/#[link_name="rust_helper_\1"]\n pub fn \1/g' $@ +$(obj)/bindings/bindings_helpers_generated.rs: $(src)/helpers.c FORCE + $(call if_changed_dep,bindgen) + +quiet_cmd_exports = EXPORTS $@ + cmd_exports = \ + $(NM) -p --defined-only $< \ + | grep -E ' (T|R|D) ' | cut -d ' ' -f 3 \ + | xargs -Isymbol \ + echo 'EXPORT_SYMBOL_RUST_GPL(symbol);' > $@ + +$(obj)/exports_core_generated.h: $(obj)/core.o FORCE + $(call if_changed,exports) + +$(obj)/exports_alloc_generated.h: $(obj)/alloc.o FORCE + $(call if_changed,exports) + +$(obj)/exports_bindings_generated.h: $(obj)/bindings.o FORCE + $(call if_changed,exports) + +$(obj)/exports_kernel_generated.h: $(obj)/kernel.o FORCE + $(call if_changed,exports) + +quiet_cmd_rustc_procmacro = $(RUSTC_OR_CLIPPY_QUIET) P $@ + cmd_rustc_procmacro = \ + $(RUSTC_OR_CLIPPY) $(rust_common_flags) \ + --emit=dep-info,link --extern proc_macro \ + --crate-type proc-macro --out-dir $(objtree)/$(obj) \ + --crate-name $(patsubst lib%.so,%,$(notdir $@)) $<; \ + mv $(objtree)/$(obj)/$(patsubst lib%.so,%,$(notdir $@)).d $(depfile); \ + sed -i '/^\#/d' $(depfile) + +# Procedural macros can only be used with the `rustc` that compiled it. +# Therefore, to get `libmacros.so` automatically recompiled when the compiler +# version changes, we add `core.o` as a dependency (even if it is not needed). +$(obj)/libmacros.so: $(src)/macros/lib.rs $(obj)/core.o FORCE + $(call if_changed_dep,rustc_procmacro) + +quiet_cmd_rustc_library = $(if $(skip_clippy),RUSTC,$(RUSTC_OR_CLIPPY_QUIET)) L $@ + cmd_rustc_library = \ + OBJTREE=$(abspath $(objtree)) \ + $(if $(skip_clippy),$(RUSTC),$(RUSTC_OR_CLIPPY)) \ + $(filter-out $(skip_flags),$(rust_flags) $(rustc_target_flags)) \ + --emit=dep-info,obj,metadata --crate-type rlib \ + --out-dir $(objtree)/$(obj) -L$(objtree)/$(obj) \ + --crate-name $(patsubst %.o,%,$(notdir $@)) $<; \ + mv $(objtree)/$(obj)/$(patsubst %.o,%,$(notdir $@)).d $(depfile); \ + sed -i '/^\#/d' $(depfile) \ + $(if $(rustc_objcopy),;$(OBJCOPY) $(rustc_objcopy) $@) + +rust-analyzer: + $(Q)$(srctree)/scripts/generate_rust_analyzer.py $(srctree) $(objtree) \ + $(RUST_LIB_SRC) > $(objtree)/rust-project.json + +$(obj)/core.o: private skip_clippy = 1 +$(obj)/core.o: private skip_flags = -Dunreachable_pub +$(obj)/core.o: private rustc_target_flags = $(core-cfgs) +$(obj)/core.o: $(RUST_LIB_SRC)/core/src/lib.rs $(obj)/target.json FORCE + $(call if_changed_dep,rustc_library) + +$(obj)/compiler_builtins.o: private rustc_objcopy = -w -W '__*' +$(obj)/compiler_builtins.o: $(src)/compiler_builtins.rs $(obj)/core.o FORCE + $(call if_changed_dep,rustc_library) + +$(obj)/alloc.o: private skip_clippy = 1 +$(obj)/alloc.o: private skip_flags = -Dunreachable_pub +$(obj)/alloc.o: private rustc_target_flags = $(alloc-cfgs) +$(obj)/alloc.o: $(src)/alloc/lib.rs $(obj)/compiler_builtins.o FORCE + $(call if_changed_dep,rustc_library) + +$(obj)/bindings.o: $(src)/bindings/lib.rs \ + $(obj)/compiler_builtins.o \ + $(obj)/bindings/bindings_generated.rs \ + $(obj)/bindings/bindings_helpers_generated.rs FORCE + $(call if_changed_dep,rustc_library) + +$(obj)/kernel.o: private rustc_target_flags = --extern alloc \ + --extern macros --extern bindings +$(obj)/kernel.o: $(src)/kernel/lib.rs $(obj)/alloc.o \ + $(obj)/libmacros.so $(obj)/bindings.o FORCE + $(call if_changed_dep,rustc_library) + +endif # CONFIG_RUST diff --git a/rust/alloc/README.md b/rust/alloc/README.md new file mode 100644 index 000000000000..c89c753720b5 --- /dev/null +++ b/rust/alloc/README.md @@ -0,0 +1,33 @@ +# `alloc` + +These source files come from the Rust standard library, hosted in +the <https://github.com/rust-lang/rust> repository, licensed under +"Apache-2.0 OR MIT" and adapted for kernel use. For copyright details, +see <https://github.com/rust-lang/rust/blob/master/COPYRIGHT>. + +Please note that these files should be kept as close as possible to +upstream. In general, only additions should be performed (e.g. new +methods). Eventually, changes should make it into upstream so that, +at some point, this fork can be dropped from the kernel tree. + + +## Rationale + +On one hand, kernel folks wanted to keep `alloc` in-tree to have more +freedom in both workflow and actual features if actually needed +(e.g. receiver types if we ended up using them), which is reasonable. + +On the other hand, Rust folks wanted to keep `alloc` as close as +upstream as possible and avoid as much divergence as possible, which +is also reasonable. + +We agreed on a middle-ground: we would keep a subset of `alloc` +in-tree that would be as small and as close as possible to upstream. +Then, upstream can start adding the functions that we add to `alloc` +etc., until we reach a point where the kernel already knows exactly +what it needs in `alloc` and all the new methods are merged into +upstream, so that we can drop `alloc` from the kernel tree and go back +to using the upstream one. + +By doing this, the kernel can go a bit faster now, and Rust can +slowly incorporate and discuss the changes as needed. diff --git a/rust/alloc/alloc.rs b/rust/alloc/alloc.rs new file mode 100644 index 000000000000..ca224a541770 --- /dev/null +++ b/rust/alloc/alloc.rs @@ -0,0 +1,440 @@ +// SPDX-License-Identifier: Apache-2.0 OR MIT + +//! Memory allocation APIs + +#![stable(feature = "alloc_module", since = "1.28.0")] + +#[cfg(not(test))] +use core::intrinsics; +use core::intrinsics::{min_align_of_val, size_of_val}; + +use core::ptr::Unique; +#[cfg(not(test))] +use core::ptr::{self, NonNull}; + +#[stable(feature = "alloc_module", since = "1.28.0")] +#[doc(inline)] +pub use core::alloc::*; + +use core::marker::Destruct; + +#[cfg(test)] +mod tests; + +extern "Rust" { + // These are the magic symbols to call the global allocator. rustc generates + // them to call `__rg_alloc` etc. if there is a `#[global_allocator]` attribute + // (the code expanding that attribute macro generates those functions), or to call + // the default implementations in libstd (`__rdl_alloc` etc. in `library/std/src/alloc.rs`) + // otherwise. + // The rustc fork of LLVM also special-cases these function names to be able to optimize them + // like `malloc`, `realloc`, and `free`, respectively. + #[rustc_allocator] + #[rustc_allocator_nounwind] + fn __rust_alloc(size: usize, align: usize) -> *mut u8; + #[rustc_allocator_nounwind] + fn __rust_dealloc(ptr: *mut u8, size: usize, align: usize); + #[rustc_allocator_nounwind] + fn __rust_realloc(ptr: *mut u8, old_size: usize, align: usize, new_size: usize) -> *mut u8; + #[rustc_allocator_nounwind] + fn __rust_alloc_zeroed(size: usize, align: usize) -> *mut u8; +} + +/// The global memory allocator. +/// +/// This type implements the [`Allocator`] trait by forwarding calls +/// to the allocator registered with the `#[global_allocator]` attribute +/// if there is one, or the `std` crate’s default. +/// +/// Note: while this type is unstable, the functionality it provides can be +/// accessed through the [free functions in `alloc`](self#functions). +#[unstable(feature = "allocator_api", issue = "32838")] +#[derive(Copy, Clone, Default, Debug)] +#[cfg(not(test))] +pub struct Global; + +#[cfg(test)] +pub use std::alloc::Global; + +/// Allocate memory with the global allocator. +/// +/// This function forwards calls to the [`GlobalAlloc::alloc`] method +/// of the allocator registered with the `#[global_allocator]` attribute +/// if there is one, or the `std` crate’s default. +/// +/// This function is expected to be deprecated in favor of the `alloc` method +/// of the [`Global`] type when it and the [`Allocator`] trait become stable. +/// +/// # Safety +/// +/// See [`GlobalAlloc::alloc`]. +/// +/// # Examples +/// +/// ``` +/// use std::alloc::{alloc, dealloc, Layout}; +/// +/// unsafe { +/// let layout = Layout::new::<u16>(); +/// let ptr = alloc(layout); +/// +/// *(ptr as *mut u16) = 42; +/// assert_eq!(*(ptr as *mut u16), 42); +/// +/// dealloc(ptr, layout); +/// } +/// ``` +#[stable(feature = "global_alloc", since = "1.28.0")] +#[must_use = "losing the pointer will leak memory"] +#[inline] +pub unsafe fn alloc(layout: Layout) -> *mut u8 { + unsafe { __rust_alloc(layout.size(), layout.align()) } +} + +/// Deallocate memory with the global allocator. +/// +/// This function forwards calls to the [`GlobalAlloc::dealloc`] method +/// of the allocator registered with the `#[global_allocator]` attribute +/// if there is one, or the `std` crate’s default. +/// +/// This function is expected to be deprecated in favor of the `dealloc` method +/// of the [`Global`] type when it and the [`Allocator`] trait become stable. +/// +/// # Safety +/// +/// See [`GlobalAlloc::dealloc`]. +#[stable(feature = "global_alloc", since = "1.28.0")] +#[inline] +pub unsafe fn dealloc(ptr: *mut u8, layout: Layout) { + unsafe { __rust_dealloc(ptr, layout.size(), layout.align()) } +} + +/// Reallocate memory with the global allocator. +/// +/// This function forwards calls to the [`GlobalAlloc::realloc`] method +/// of the allocator registered with the `#[global_allocator]` attribute +/// if there is one, or the `std` crate’s default. +/// +/// This function is expected to be deprecated in favor of the `realloc` method +/// of the [`Global`] type when it and the [`Allocator`] trait become stable. +/// +/// # Safety +/// +/// See [`GlobalAlloc::realloc`]. +#[stable(feature = "global_alloc", since = "1.28.0")] +#[must_use = "losing the pointer will leak memory"] +#[inline] +pub unsafe fn realloc(ptr: *mut u8, layout: Layout, new_size: usize) -> *mut u8 { + unsafe { __rust_realloc(ptr, layout.size(), layout.align(), new_size) } +} + +/// Allocate zero-initialized memory with the global allocator. +/// +/// This function forwards calls to the [`GlobalAlloc::alloc_zeroed`] method +/// of the allocator registered with the `#[global_allocator]` attribute +/// if there is one, or the `std` crate’s default. +/// +/// This function is expected to be deprecated in favor of the `alloc_zeroed` method +/// of the [`Global`] type when it and the [`Allocator`] trait become stable. +/// +/// # Safety +/// +/// See [`GlobalAlloc::alloc_zeroed`]. +/// +/// # Examples +/// +/// ``` +/// use std::alloc::{alloc_zeroed, dealloc, Layout}; +/// +/// unsafe { +/// let layout = Layout::new::<u16>(); +/// let ptr = alloc_zeroed(layout); +/// +/// assert_eq!(*(ptr as *mut u16), 0); +/// +/// dealloc(ptr, layout); +/// } +/// ``` +#[stable(feature = "global_alloc", since = "1.28.0")] +#[must_use = "losing the pointer will leak memory"] +#[inline] +pub unsafe fn alloc_zeroed(layout: Layout) -> *mut u8 { + unsafe { __rust_alloc_zeroed(layout.size(), layout.align()) } +} + +#[cfg(not(test))] +impl Global { + #[inline] + fn alloc_impl(&self, layout: Layout, zeroed: bool) -> Result<NonNull<[u8]>, AllocError> { + match layout.size() { + 0 => Ok(NonNull::slice_from_raw_parts(layout.dangling(), 0)), + // SAFETY: `layout` is non-zero in size, + size => unsafe { + let raw_ptr = if zeroed { alloc_zeroed(layout) } else { alloc(layout) }; + let ptr = NonNull::new(raw_ptr).ok_or(AllocError)?; + Ok(NonNull::slice_from_raw_parts(ptr, size)) + }, + } + } + + // SAFETY: Same as `Allocator::grow` + #[inline] + unsafe fn grow_impl( + &self, + ptr: NonNull<u8>, + old_layout: Layout, + new_layout: Layout, + zeroed: bool, + ) -> Result<NonNull<[u8]>, AllocError> { + debug_assert!( + new_layout.size() >= old_layout.size(), + "`new_layout.size()` must be greater than or equal to `old_layout.size()`" + ); + + match old_layout.size() { + 0 => self.alloc_impl(new_layout, zeroed), + + // SAFETY: `new_size` is non-zero as `old_size` is greater than or equal to `new_size` + // as required by safety conditions. Other conditions must be upheld by the caller + old_size if old_layout.align() == new_layout.align() => unsafe { + let new_size = new_layout.size(); + + // `realloc` probably checks for `new_size >= old_layout.size()` or something similar. + intrinsics::assume(new_size >= old_layout.size()); + + let raw_ptr = realloc(ptr.as_ptr(), old_layout, new_size); + let ptr = NonNull::new(raw_ptr).ok_or(AllocError)?; + if zeroed { + raw_ptr.add(old_size).write_bytes(0, new_size - old_size); + } + Ok(NonNull::slice_from_raw_parts(ptr, new_size)) + }, + + // SAFETY: because `new_layout.size()` must be greater than or equal to `old_size`, + // both the old and new memory allocation are valid for reads and writes for `old_size` + // bytes. Also, because the old allocation wasn't yet deallocated, it cannot overlap + // `new_ptr`. Thus, the call to `copy_nonoverlapping` is safe. The safety contract + // for `dealloc` must be upheld by the caller. + old_size => unsafe { + let new_ptr = self.alloc_impl(new_layout, zeroed)?; + ptr::copy_nonoverlapping(ptr.as_ptr(), new_ptr.as_mut_ptr(), old_size); + self.deallocate(ptr, old_layout); + Ok(new_ptr) + }, + } + } +} + +#[unstable(feature = "allocator_api", issue = "32838")] +#[cfg(not(test))] +unsafe impl Allocator for Global { + #[inline] + fn allocate(&self, layout: Layout) -> Result<NonNull<[u8]>, AllocError> { + self.alloc_impl(layout, false) + } + + #[inline] + fn allocate_zeroed(&self, layout: Layout) -> Result<NonNull<[u8]>, AllocError> { + self.alloc_impl(layout, true) + } + + #[inline] + unsafe fn deallocate(&self, ptr: NonNull<u8>, layout: Layout) { + if layout.size() != 0 { + // SAFETY: `layout` is non-zero in size, + // other conditions must be upheld by the caller + unsafe { dealloc(ptr.as_ptr(), layout) } + } + } + + #[inline] + unsafe fn grow( + &self, + ptr: NonNull<u8>, + old_layout: Layout, + new_layout: Layout, + ) -> Result<NonNull<[u8]>, AllocError> { + // SAFETY: all conditions must be upheld by the caller + unsafe { self.grow_impl(ptr, old_layout, new_layout, false) } + } + + #[inline] + unsafe fn grow_zeroed( + &self, + ptr: NonNull<u8>, + old_layout: Layout, + new_layout: Layout, + ) -> Result<NonNull<[u8]>, AllocError> { + // SAFETY: all conditions must be upheld by the caller + unsafe { self.grow_impl(ptr, old_layout, new_layout, true) } + } + + #[inline] + unsafe fn shrink( + &self, + ptr: NonNull<u8>, + old_layout: Layout, + new_layout: Layout, + ) -> Result<NonNull<[u8]>, AllocError> { + debug_assert!( + new_layout.size() <= old_layout.size(), + "`new_layout.size()` must be smaller than or equal to `old_layout.size()`" + ); + + match new_layout.size() { + // SAFETY: conditions must be upheld by the caller + 0 => unsafe { + self.deallocate(ptr, old_layout); + Ok(NonNull::slice_from_raw_parts(new_layout.dangling(), 0)) + }, + + // SAFETY: `new_size` is non-zero. Other conditions must be upheld by the caller + new_size if old_layout.align() == new_layout.align() => unsafe { + // `realloc` probably checks for `new_size <= old_layout.size()` or something similar. + intrinsics::assume(new_size <= old_layout.size()); + + let raw_ptr = realloc(ptr.as_ptr(), old_layout, new_size); + let ptr = NonNull::new(raw_ptr).ok_or(AllocError)?; + Ok(NonNull::slice_from_raw_parts(ptr, new_size)) + }, + + // SAFETY: because `new_size` must be smaller than or equal to `old_layout.size()`, + // both the old and new memory allocation are valid for reads and writes for `new_size` + // bytes. Also, because the old allocation wasn't yet deallocated, it cannot overlap + // `new_ptr`. Thus, the call to `copy_nonoverlapping` is safe. The safety contract + // for `dealloc` must be upheld by the caller. + new_size => unsafe { + let new_ptr = self.allocate(new_layout)?; + ptr::copy_nonoverlapping(ptr.as_ptr(), new_ptr.as_mut_ptr(), new_size); + self.deallocate(ptr, old_layout); + Ok(new_ptr) + }, + } + } +} + +/// The allocator for unique pointers. +#[cfg(all(not(no_global_oom_handling), not(test)))] +#[lang = "exchange_malloc"] +#[inline] +unsafe fn exchange_malloc(size: usize, align: usize) -> *mut u8 { + let layout = unsafe { Layout::from_size_align_unchecked(size, align) }; + match Global.allocate(layout) { + Ok(ptr) => ptr.as_mut_ptr(), + Err(_) => handle_alloc_error(layout), + } +} + +#[cfg_attr(not(test), lang = "box_free")] +#[inline] +#[rustc_const_unstable(feature = "const_box", issue = "92521")] +// This signature has to be the same as `Box`, otherwise an ICE will happen. +// When an additional parameter to `Box` is added (like `A: Allocator`), this has to be added here as +// well. +// For example if `Box` is changed to `struct Box<T: ?Sized, A: Allocator>(Unique<T>, A)`, +// this function has to be changed to `fn box_free<T: ?Sized, A: Allocator>(Unique<T>, A)` as well. +pub(crate) const unsafe fn box_free<T: ?Sized, A: ~const Allocator + ~const Destruct>( + ptr: Unique<T>, + alloc: A, +) { + unsafe { + let size = size_of_val(ptr.as_ref()); + let align = min_align_of_val(ptr.as_ref()); + let layout = Layout::from_size_align_unchecked(size, align); + alloc.deallocate(From::from(ptr.cast()), layout) + } +} + +// # Allocation error handler + +#[cfg(not(no_global_oom_handling))] +extern "Rust" { + // This is the magic symbol to call the global alloc error handler. rustc generates + // it to call `__rg_oom` if there is a `#[alloc_error_handler]`, or to call the + // default implementations below (`__rdl_oom`) otherwise. + fn __rust_alloc_error_handler(size: usize, align: usize) -> !; +} + +/// Abort on memory allocation error or failure. +/// +/// Callers of memory allocation APIs wishing to abort computation +/// in response to an allocation error are encouraged to call this function, +/// rather than directly invoking `panic!` or similar. +/// +/// The default behavior of this function is to print a message to standard error +/// and abort the process. +/// It can be replaced with [`set_alloc_error_hook`] and [`take_alloc_error_hook`]. +/// +/// [`set_alloc_error_hook`]: ../../std/alloc/fn.set_alloc_error_hook.html +/// [`take_alloc_error_hook`]: ../../std/alloc/fn.take_alloc_error_hook.html +#[stable(feature = "global_alloc", since = "1.28.0")] +#[rustc_const_unstable(feature = "const_alloc_error", issue = "92523")] +#[cfg(all(not(no_global_oom_handling), not(test)))] +#[cold] +pub const fn handle_alloc_error(layout: Layout) -> ! { + const fn ct_error(_: Layout) -> ! { + panic!("allocation failed"); + } + + fn rt_error(layout: Layout) -> ! { + unsafe { + __rust_alloc_error_handler(layout.size(), layout.align()); + } + } + + unsafe { core::intrinsics::const_eval_select((layout,), ct_error, rt_error) } +} + +// For alloc test `std::alloc::handle_alloc_error` can be used directly. +#[cfg(all(not(no_global_oom_handling), test))] +pub use std::alloc::handle_alloc_error; + +#[cfg(all(not(no_global_oom_handling), not(test)))] +#[doc(hidden)] +#[allow(unused_attributes)] +#[unstable(feature = "alloc_internals", issue = "none")] +pub mod __alloc_error_handler { + use crate::alloc::Layout; + + // called via generated `__rust_alloc_error_handler` + + // if there is no `#[alloc_error_handler]` + #[rustc_std_internal_symbol] + pub unsafe extern "C-unwind" fn __rdl_oom(size: usize, _align: usize) -> ! { + panic!("memory allocation of {size} bytes failed") + } + + // if there is an `#[alloc_error_handler]` + #[rustc_std_internal_symbol] + pub unsafe extern "C-unwind" fn __rg_oom(size: usize, align: usize) -> ! { + let layout = unsafe { Layout::from_size_align_unchecked(size, align) }; + extern "Rust" { + #[lang = "oom"] + fn oom_impl(layout: Layout) -> !; + } + unsafe { oom_impl(layout) } + } +} + +/// Specialize clones into pre-allocated, uninitialized memory. +/// Used by `Box::clone` and `Rc`/`Arc::make_mut`. +pub(crate) trait WriteCloneIntoRaw: Sized { + unsafe fn write_clone_into_raw(&self, target: *mut Self); +} + +impl<T: Clone> WriteCloneIntoRaw for T { + #[inline] + default unsafe fn write_clone_into_raw(&self, target: *mut Self) { + // Having allocated *first* may allow the optimizer to create + // the cloned value in-place, skipping the local and move. + unsafe { target.write(self.clone()) }; + } +} + +impl<T: Copy> WriteCloneIntoRaw for T { + #[inline] + unsafe fn write_clone_into_raw(&self, target: *mut Self) { + // We can always copy in-place, without ever involving a local value. + unsafe { target.copy_from_nonoverlapping(self, 1) }; + } +} diff --git a/rust/alloc/borrow.rs b/rust/alloc/borrow.rs new file mode 100644 index 000000000000..dde4957200d4 --- /dev/null +++ b/rust/alloc/borrow.rs @@ -0,0 +1,498 @@ +// SPDX-License-Identifier: Apache-2.0 OR MIT + +//! A module for working with borrowed data. + +#![stable(feature = "rust1", since = "1.0.0")] + +use core::cmp::Ordering; +use core::hash::{Hash, Hasher}; +use core::ops::Deref; +#[cfg(not(no_global_oom_handling))] +use core::ops::{Add, AddAssign}; + +#[stable(feature = "rust1", since = "1.0.0")] +pub use core::borrow::{Borrow, BorrowMut}; + +use core::fmt; +#[cfg(not(no_global_oom_handling))] +use crate::string::String; + +use Cow::*; + +#[stable(feature = "rust1", since = "1.0.0")] +impl<'a, B: ?Sized> Borrow<B> for Cow<'a, B> +where + B: ToOwned, + <B as ToOwned>::Owned: 'a, +{ + fn borrow(&self) -> &B { + &**self + } +} + +/// A generalization of `Clone` to borrowed data. +/// +/// Some types make it possible to go from borrowed to owned, usually by +/// implementing the `Clone` trait. But `Clone` works only for going from `&T` +/// to `T`. The `ToOwned` trait generalizes `Clone` to construct owned data +/// from any borrow of a given type. +#[cfg_attr(not(test), rustc_diagnostic_item = "ToOwned")] +#[stable(feature = "rust1", since = "1.0.0")] +pub trait ToOwned { + /// The resulting type after obtaining ownership. + #[stable(feature = "rust1", since = "1.0.0")] + type Owned: Borrow<Self>; + + /// Creates owned data from borrowed data, usually by cloning. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// let s: &str = "a"; + /// let ss: String = s.to_owned(); + /// + /// let v: &[i32] = &[1, 2]; + /// let vv: Vec<i32> = v.to_owned(); + /// ``` + #[stable(feature = "rust1", since = "1.0.0")] + #[must_use = "cloning is often expensive and is not expected to have side effects"] + fn to_owned(&self) -> Self::Owned; + + /// Uses borrowed data to replace owned data, usually by cloning. + /// + /// This is borrow-generalized version of `Clone::clone_from`. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// # #![feature(toowned_clone_into)] + /// let mut s: String = String::new(); + /// "hello".clone_into(&mut s); + /// + /// let mut v: Vec<i32> = Vec::new(); + /// [1, 2][..].clone_into(&mut v); + /// ``` + #[unstable(feature = "toowned_clone_into", reason = "recently added", issue = "41263")] + fn clone_into(&self, target: &mut Self::Owned) { + *target = self.to_owned(); + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<T> ToOwned for T +where + T: Clone, +{ + type Owned = T; + fn to_owned(&self) -> T { + self.clone() + } + + fn clone_into(&self, target: &mut T) { + target.clone_from(self); + } +} + +/// A clone-on-write smart pointer. +/// +/// The type `Cow` is a smart pointer providing clone-on-write functionality: it +/// can enclose and provide immutable access to borrowed data, and clone the +/// data lazily when mutation or ownership is required. The type is designed to +/// work with general borrowed data via the `Borrow` trait. +/// +/// `Cow` implements `Deref`, which means that you can call +/// non-mutating methods directly on the data it encloses. If mutation +/// is desired, `to_mut` will obtain a mutable reference to an owned +/// value, cloning if necessary. +/// +/// If you need reference-counting pointers, note that +/// [`Rc::make_mut`][crate::rc::Rc::make_mut] and +/// [`Arc::make_mut`][crate::sync::Arc::make_mut] can provide clone-on-write +/// functionality as well. +/// +/// # Examples +/// +/// ``` +/// use std::borrow::Cow; +/// +/// fn abs_all(input: &mut Cow<[i32]>) { +/// for i in 0..input.len() { +/// let v = input[i]; +/// if v < 0 { +/// // Clones into a vector if not already owned. +/// input.to_mut()[i] = -v; +/// } +/// } +/// } +/// +/// // No clone occurs because `input` doesn't need to be mutated. +/// let slice = [0, 1, 2]; +/// let mut input = Cow::from(&slice[..]); +/// abs_all(&mut input); +/// +/// // Clone occurs because `input` needs to be mutated. +/// let slice = [-1, 0, 1]; +/// let mut input = Cow::from(&slice[..]); +/// abs_all(&mut input); +/// +/// // No clone occurs because `input` is already owned. +/// let mut input = Cow::from(vec![-1, 0, 1]); +/// abs_all(&mut input); +/// ``` +/// +/// Another example showing how to keep `Cow` in a struct: +/// +/// ``` +/// use std::borrow::Cow; +/// +/// struct Items<'a, X: 'a> where [X]: ToOwned<Owned = Vec<X>> { +/// values: Cow<'a, [X]>, +/// } +/// +/// impl<'a, X: Clone + 'a> Items<'a, X> where [X]: ToOwned<Owned = Vec<X>> { +/// fn new(v: Cow<'a, [X]>) -> Self { +/// Items { values: v } +/// } +/// } +/// +/// // Creates a container from borrowed values of a slice +/// let readonly = [1, 2]; +/// let borrowed = Items::new((&readonly[..]).into()); +/// match borrowed { +/// Items { values: Cow::Borrowed(b) } => println!("borrowed {b:?}"), +/// _ => panic!("expect borrowed value"), +/// } +/// +/// let mut clone_on_write = borrowed; +/// // Mutates the data from slice into owned vec and pushes a new value on top +/// clone_on_write.values.to_mut().push(3); +/// println!("clone_on_write = {:?}", clone_on_write.values); +/// +/// // The data was mutated. Let's check it out. +/// match clone_on_write { +/// Items { values: Cow::Owned(_) } => println!("clone_on_write contains owned data"), +/// _ => panic!("expect owned data"), +/// } +/// ``` +#[stable(feature = "rust1", since = "1.0.0")] +#[cfg_attr(not(test), rustc_diagnostic_item = "Cow")] +pub enum Cow<'a, B: ?Sized + 'a> +where + B: ToOwned, +{ + /// Borrowed data. + #[stable(feature = "rust1", since = "1.0.0")] + Borrowed(#[stable(feature = "rust1", since = "1.0.0")] &'a B), + + /// Owned data. + #[stable(feature = "rust1", since = "1.0.0")] + Owned(#[stable(feature = "rust1", since = "1.0.0")] <B as ToOwned>::Owned), +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<B: ?Sized + ToOwned> Clone for Cow<'_, B> { + fn clone(&self) -> Self { + match *self { + Borrowed(b) => Borrowed(b), + Owned(ref o) => { + let b: &B = o.borrow(); + Owned(b.to_owned()) + } + } + } + + fn clone_from(&mut self, source: &Self) { + match (self, source) { + (&mut Owned(ref mut dest), &Owned(ref o)) => o.borrow().clone_into(dest), + (t, s) => *t = s.clone(), + } + } +} + +impl<B: ?Sized + ToOwned> Cow<'_, B> { + /// Returns true if the data is borrowed, i.e. if `to_mut` would require additional work. + /// + /// # Examples + /// + /// ``` + /// #![feature(cow_is_borrowed)] + /// use std::borrow::Cow; + /// + /// let cow = Cow::Borrowed("moo"); + /// assert!(cow.is_borrowed()); + /// + /// let bull: Cow<'_, str> = Cow::Owned("...moo?".to_string()); + /// assert!(!bull.is_borrowed()); + /// ``` + #[unstable(feature = "cow_is_borrowed", issue = "65143")] + #[rustc_const_unstable(feature = "const_cow_is_borrowed", issue = "65143")] + pub const fn is_borrowed(&self) -> bool { + match *self { + Borrowed(_) => true, + Owned(_) => false, + } + } + + /// Returns true if the data is owned, i.e. if `to_mut` would be a no-op. + /// + /// # Examples + /// + /// ``` + /// #![feature(cow_is_borrowed)] + /// use std::borrow::Cow; + /// + /// let cow: Cow<'_, str> = Cow::Owned("moo".to_string()); + /// assert!(cow.is_owned()); + /// + /// let bull = Cow::Borrowed("...moo?"); + /// assert!(!bull.is_owned()); + /// ``` + #[unstable(feature = "cow_is_borrowed", issue = "65143")] + #[rustc_const_unstable(feature = "const_cow_is_borrowed", issue = "65143")] + pub const fn is_owned(&self) -> bool { + !self.is_borrowed() + } + + /// Acquires a mutable reference to the owned form of the data. + /// + /// Clones the data if it is not already owned. + /// + /// # Examples + /// + /// ``` + /// use std::borrow::Cow; + /// + /// let mut cow = Cow::Borrowed("foo"); + /// cow.to_mut().make_ascii_uppercase(); + /// + /// assert_eq!( + /// cow, + /// Cow::Owned(String::from("FOO")) as Cow<str> + /// ); + /// ``` + #[stable(feature = "rust1", since = "1.0.0")] + pub fn to_mut(&mut self) -> &mut <B as ToOwned>::Owned { + match *self { + Borrowed(borrowed) => { + *self = Owned(borrowed.to_owned()); + match *self { + Borrowed(..) => unreachable!(), + Owned(ref mut owned) => owned, + } + } + Owned(ref mut owned) => owned, + } + } + + /// Extracts the owned data. + /// + /// Clones the data if it is not already owned. + /// + /// # Examples + /// + /// Calling `into_owned` on a `Cow::Borrowed` returns a clone of the borrowed data: + /// + /// ``` + /// use std::borrow::Cow; + /// + /// let s = "Hello world!"; + /// let cow = Cow::Borrowed(s); + /// + /// assert_eq!( + /// cow.into_owned(), + /// String::from(s) + /// ); + /// ``` + /// + /// Calling `into_owned` on a `Cow::Owned` returns the owned data. The data is moved out of the + /// `Cow` without being cloned. + /// + /// ``` + /// use std::borrow::Cow; + /// + /// let s = "Hello world!"; + /// let cow: Cow<str> = Cow::Owned(String::from(s)); + /// + /// assert_eq!( + /// cow.into_owned(), + /// String::from(s) + /// ); + /// ``` + #[stable(feature = "rust1", since = "1.0.0")] + pub fn into_owned(self) -> <B as ToOwned>::Owned { + match self { + Borrowed(borrowed) => borrowed.to_owned(), + Owned(owned) => owned, + } + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +#[rustc_const_unstable(feature = "const_deref", issue = "88955")] +impl<B: ?Sized + ToOwned> const Deref for Cow<'_, B> +where + B::Owned: ~const Borrow<B>, +{ + type Target = B; + + fn deref(&self) -> &B { + match *self { + Borrowed(borrowed) => borrowed, + Owned(ref owned) => owned.borrow(), + } + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<B: ?Sized> Eq for Cow<'_, B> where B: Eq + ToOwned {} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<B: ?Sized> Ord for Cow<'_, B> +where + B: Ord + ToOwned, +{ + #[inline] + fn cmp(&self, other: &Self) -> Ordering { + Ord::cmp(&**self, &**other) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<'a, 'b, B: ?Sized, C: ?Sized> PartialEq<Cow<'b, C>> for Cow<'a, B> +where + B: PartialEq<C> + ToOwned, + C: ToOwned, +{ + #[inline] + fn eq(&self, other: &Cow<'b, C>) -> bool { + PartialEq::eq(&**self, &**other) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<'a, B: ?Sized> PartialOrd for Cow<'a, B> +where + B: PartialOrd + ToOwned, +{ + #[inline] + fn partial_cmp(&self, other: &Cow<'a, B>) -> Option<Ordering> { + PartialOrd::partial_cmp(&**self, &**other) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<B: ?Sized> fmt::Debug for Cow<'_, B> +where + B: fmt::Debug + ToOwned<Owned: fmt::Debug>, +{ + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + match *self { + Borrowed(ref b) => fmt::Debug::fmt(b, f), + Owned(ref o) => fmt::Debug::fmt(o, f), + } + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<B: ?Sized> fmt::Display for Cow<'_, B> +where + B: fmt::Display + ToOwned<Owned: fmt::Display>, +{ + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + match *self { + Borrowed(ref b) => fmt::Display::fmt(b, f), + Owned(ref o) => fmt::Display::fmt(o, f), + } + } +} + +#[stable(feature = "default", since = "1.11.0")] +impl<B: ?Sized> Default for Cow<'_, B> +where + B: ToOwned<Owned: Default>, +{ + /// Creates an owned Cow<'a, B> with the default value for the contained owned value. + fn default() -> Self { + Owned(<B as ToOwned>::Owned::default()) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<B: ?Sized> Hash for Cow<'_, B> +where + B: Hash + ToOwned, +{ + #[inline] + fn hash<H: Hasher>(&self, state: &mut H) { + Hash::hash(&**self, state) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<T: ?Sized + ToOwned> AsRef<T> for Cow<'_, T> { + fn as_ref(&self) -> &T { + self + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "cow_add", since = "1.14.0")] +impl<'a> Add<&'a str> for Cow<'a, str> { + type Output = Cow<'a, str>; + + #[inline] + fn add(mut self, rhs: &'a str) -> Self::Output { + self += rhs; + self + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "cow_add", since = "1.14.0")] +impl<'a> Add<Cow<'a, str>> for Cow<'a, str> { + type Output = Cow<'a, str>; + + #[inline] + fn add(mut self, rhs: Cow<'a, str>) -> Self::Output { + self += rhs; + self + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "cow_add", since = "1.14.0")] +impl<'a> AddAssign<&'a str> for Cow<'a, str> { + fn add_assign(&mut self, rhs: &'a str) { + if self.is_empty() { + *self = Cow::Borrowed(rhs) + } else if !rhs.is_empty() { + if let Cow::Borrowed(lhs) = *self { + let mut s = String::with_capacity(lhs.len() + rhs.len()); + s.push_str(lhs); + *self = Cow::Owned(s); + } + self.to_mut().push_str(rhs); + } + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "cow_add", since = "1.14.0")] +impl<'a> AddAssign<Cow<'a, str>> for Cow<'a, str> { + fn add_assign(&mut self, rhs: Cow<'a, str>) { + if self.is_empty() { + *self = rhs + } else if !rhs.is_empty() { + if let Cow::Borrowed(lhs) = *self { + let mut s = String::with_capacity(lhs.len() + rhs.len()); + s.push_str(lhs); + *self = Cow::Owned(s); + } + self.to_mut().push_str(&rhs); + } + } +} diff --git a/rust/alloc/boxed.rs b/rust/alloc/boxed.rs new file mode 100644 index 000000000000..dcfe87b14f3a --- /dev/null +++ b/rust/alloc/boxed.rs @@ -0,0 +1,2028 @@ +// SPDX-License-Identifier: Apache-2.0 OR MIT + +//! A pointer type for heap allocation. +//! +//! [`Box<T>`], casually referred to as a 'box', provides the simplest form of +//! heap allocation in Rust. Boxes provide ownership for this allocation, and +//! drop their contents when they go out of scope. Boxes also ensure that they +//! never allocate more than `isize::MAX` bytes. +//! +//! # Examples +//! +//! Move a value from the stack to the heap by creating a [`Box`]: +//! +//! ``` +//! let val: u8 = 5; +//! let boxed: Box<u8> = Box::new(val); +//! ``` +//! +//! Move a value from a [`Box`] back to the stack by [dereferencing]: +//! +//! ``` +//! let boxed: Box<u8> = Box::new(5); +//! let val: u8 = *boxed; +//! ``` +//! +//! Creating a recursive data structure: +//! +//! ``` +//! #[derive(Debug)] +//! enum List<T> { +//! Cons(T, Box<List<T>>), +//! Nil, +//! } +//! +//! let list: List<i32> = List::Cons(1, Box::new(List::Cons(2, Box::new(List::Nil)))); +//! println!("{list:?}"); +//! ``` +//! +//! This will print `Cons(1, Cons(2, Nil))`. +//! +//! Recursive structures must be boxed, because if the definition of `Cons` +//! looked like this: +//! +//! ```compile_fail,E0072 +//! # enum List<T> { +//! Cons(T, List<T>), +//! # } +//! ``` +//! +//! It wouldn't work. This is because the size of a `List` depends on how many +//! elements are in the list, and so we don't know how much memory to allocate +//! for a `Cons`. By introducing a [`Box<T>`], which has a defined size, we know how +//! big `Cons` needs to be. +//! +//! # Memory layout +//! +//! For non-zero-sized values, a [`Box`] will use the [`Global`] allocator for +//! its allocation. It is valid to convert both ways between a [`Box`] and a +//! raw pointer allocated with the [`Global`] allocator, given that the +//! [`Layout`] used with the allocator is correct for the type. More precisely, +//! a `value: *mut T` that has been allocated with the [`Global`] allocator +//! with `Layout::for_value(&*value)` may be converted into a box using +//! [`Box::<T>::from_raw(value)`]. Conversely, the memory backing a `value: *mut +//! T` obtained from [`Box::<T>::into_raw`] may be deallocated using the +//! [`Global`] allocator with [`Layout::for_value(&*value)`]. +//! +//! For zero-sized values, the `Box` pointer still has to be [valid] for reads +//! and writes and sufficiently aligned. In particular, casting any aligned +//! non-zero integer literal to a raw pointer produces a valid pointer, but a +//! pointer pointing into previously allocated memory that since got freed is +//! not valid. The recommended way to build a Box to a ZST if `Box::new` cannot +//! be used is to use [`ptr::NonNull::dangling`]. +//! +//! So long as `T: Sized`, a `Box<T>` is guaranteed to be represented +//! as a single pointer and is also ABI-compatible with C pointers +//! (i.e. the C type `T*`). This means that if you have extern "C" +//! Rust functions that will be called from C, you can define those +//! Rust functions using `Box<T>` types, and use `T*` as corresponding +//! type on the C side. As an example, consider this C header which +//! declares functions that create and destroy some kind of `Foo` +//! value: +//! +//! ```c +//! /* C header */ +//! +//! /* Returns ownership to the caller */ +//! struct Foo* foo_new(void); +//! +//! /* Takes ownership from the caller; no-op when invoked with null */ +//! void foo_delete(struct Foo*); +//! ``` +//! +//! These two functions might be implemented in Rust as follows. Here, the +//! `struct Foo*` type from C is translated to `Box<Foo>`, which captures +//! the ownership constraints. Note also that the nullable argument to +//! `foo_delete` is represented in Rust as `Option<Box<Foo>>`, since `Box<Foo>` +//! cannot be null. +//! +//! ``` +//! #[repr(C)] +//! pub struct Foo; +//! +//! #[no_mangle] +//! pub extern "C" fn foo_new() -> Box<Foo> { +//! Box::new(Foo) +//! } +//! +//! #[no_mangle] +//! pub extern "C" fn foo_delete(_: Option<Box<Foo>>) {} +//! ``` +//! +//! Even though `Box<T>` has the same representation and C ABI as a C pointer, +//! this does not mean that you can convert an arbitrary `T*` into a `Box<T>` +//! and expect things to work. `Box<T>` values will always be fully aligned, +//! non-null pointers. Moreover, the destructor for `Box<T>` will attempt to +//! free the value with the global allocator. In general, the best practice +//! is to only use `Box<T>` for pointers that originated from the global +//! allocator. +//! +//! **Important.** At least at present, you should avoid using +//! `Box<T>` types for functions that are defined in C but invoked +//! from Rust. In those cases, you should directly mirror the C types +//! as closely as possible. Using types like `Box<T>` where the C +//! definition is just using `T*` can lead to undefined behavior, as +//! described in [rust-lang/unsafe-code-guidelines#198][ucg#198]. +//! +//! [ucg#198]: https://github.com/rust-lang/unsafe-code-guidelines/issues/198 +//! [dereferencing]: core::ops::Deref +//! [`Box::<T>::from_raw(value)`]: Box::from_raw +//! [`Global`]: crate::alloc::Global +//! [`Layout`]: crate::alloc::Layout +//! [`Layout::for_value(&*value)`]: crate::alloc::Layout::for_value +//! [valid]: ptr#safety + +#![stable(feature = "rust1", since = "1.0.0")] + +use core::any::Any; +use core::async_iter::AsyncIterator; +use core::borrow; +use core::cmp::Ordering; +use core::convert::{From, TryFrom}; +use core::fmt; +use core::future::Future; +use core::hash::{Hash, Hasher}; +#[cfg(not(no_global_oom_handling))] +use core::iter::FromIterator; +use core::iter::{FusedIterator, Iterator}; +use core::marker::{Destruct, Unpin, Unsize}; +use core::mem; +use core::ops::{ + CoerceUnsized, Deref, DerefMut, DispatchFromDyn, Generator, GeneratorState, Receiver, +}; +use core::pin::Pin; +use core::ptr::{self, Unique}; +use core::task::{Context, Poll}; + +#[cfg(not(no_global_oom_handling))] +use crate::alloc::{handle_alloc_error, WriteCloneIntoRaw}; +use crate::alloc::{AllocError, Allocator, Global, Layout}; +#[cfg(not(no_global_oom_handling))] +use crate::borrow::Cow; +use crate::raw_vec::RawVec; +#[cfg(not(no_global_oom_handling))] +use crate::str::from_boxed_utf8_unchecked; +#[cfg(not(no_global_oom_handling))] +use crate::vec::Vec; + +#[cfg(not(no_thin))] +#[unstable(feature = "thin_box", issue = "92791")] +pub use thin::ThinBox; + +#[cfg(not(no_thin))] +mod thin; + +/// A pointer type for heap allocation. +/// +/// See the [module-level documentation](../../std/boxed/index.html) for more. +#[lang = "owned_box"] +#[fundamental] +#[stable(feature = "rust1", since = "1.0.0")] +// The declaration of the `Box` struct must be kept in sync with the +// `alloc::alloc::box_free` function or ICEs will happen. See the comment +// on `box_free` for more details. +pub struct Box< + T: ?Sized, + #[unstable(feature = "allocator_api", issue = "32838")] A: Allocator = Global, +>(Unique<T>, A); + +impl<T> Box<T> { + /// Allocates memory on the heap and then places `x` into it. + /// + /// This doesn't actually allocate if `T` is zero-sized. + /// + /// # Examples + /// + /// ``` + /// let five = Box::new(5); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[inline(always)] + #[stable(feature = "rust1", since = "1.0.0")] + #[must_use] + pub fn new(x: T) -> Self { + box x + } + + /// Constructs a new box with uninitialized contents. + /// + /// # Examples + /// + /// ``` + /// #![feature(new_uninit)] + /// + /// let mut five = Box::<u32>::new_uninit(); + /// + /// let five = unsafe { + /// // Deferred initialization: + /// five.as_mut_ptr().write(5); + /// + /// five.assume_init() + /// }; + /// + /// assert_eq!(*five, 5) + /// ``` + #[cfg(not(no_global_oom_handling))] + #[unstable(feature = "new_uninit", issue = "63291")] + #[must_use] + #[inline] + pub fn new_uninit() -> Box<mem::MaybeUninit<T>> { + Self::new_uninit_in(Global) + } + + /// Constructs a new `Box` with uninitialized contents, with the memory + /// being filled with `0` bytes. + /// + /// See [`MaybeUninit::zeroed`][zeroed] for examples of correct and incorrect usage + /// of this method. + /// + /// # Examples + /// + /// ``` + /// #![feature(new_uninit)] + /// + /// let zero = Box::<u32>::new_zeroed(); + /// let zero = unsafe { zero.assume_init() }; + /// + /// assert_eq!(*zero, 0) + /// ``` + /// + /// [zeroed]: mem::MaybeUninit::zeroed + #[cfg(not(no_global_oom_handling))] + #[inline] + #[unstable(feature = "new_uninit", issue = "63291")] + #[must_use] + pub fn new_zeroed() -> Box<mem::MaybeUninit<T>> { + Self::new_zeroed_in(Global) + } + + /// Constructs a new `Pin<Box<T>>`. If `T` does not implement `Unpin`, then + /// `x` will be pinned in memory and unable to be moved. + #[cfg(not(no_global_oom_handling))] + #[stable(feature = "pin", since = "1.33.0")] + #[must_use] + #[inline(always)] + pub fn pin(x: T) -> Pin<Box<T>> { + (box x).into() + } + + /// Allocates memory on the heap then places `x` into it, + /// returning an error if the allocation fails + /// + /// This doesn't actually allocate if `T` is zero-sized. + /// + /// # Examples + /// + /// ``` + /// #![feature(allocator_api)] + /// + /// let five = Box::try_new(5)?; + /// # Ok::<(), std::alloc::AllocError>(()) + /// ``` + #[unstable(feature = "allocator_api", issue = "32838")] + #[inline] + pub fn try_new(x: T) -> Result<Self, AllocError> { + Self::try_new_in(x, Global) + } + + /// Constructs a new box with uninitialized contents on the heap, + /// returning an error if the allocation fails + /// + /// # Examples + /// + /// ``` + /// #![feature(allocator_api, new_uninit)] + /// + /// let mut five = Box::<u32>::try_new_uninit()?; + /// + /// let five = unsafe { + /// // Deferred initialization: + /// five.as_mut_ptr().write(5); + /// + /// five.assume_init() + /// }; + /// + /// assert_eq!(*five, 5); + /// # Ok::<(), std::alloc::AllocError>(()) + /// ``` + #[unstable(feature = "allocator_api", issue = "32838")] + // #[unstable(feature = "new_uninit", issue = "63291")] + #[inline] + pub fn try_new_uninit() -> Result<Box<mem::MaybeUninit<T>>, AllocError> { + Box::try_new_uninit_in(Global) + } + + /// Constructs a new `Box` with uninitialized contents, with the memory + /// being filled with `0` bytes on the heap + /// + /// See [`MaybeUninit::zeroed`][zeroed] for examples of correct and incorrect usage + /// of this method. + /// + /// # Examples + /// + /// ``` + /// #![feature(allocator_api, new_uninit)] + /// + /// let zero = Box::<u32>::try_new_zeroed()?; + /// let zero = unsafe { zero.assume_init() }; + /// + /// assert_eq!(*zero, 0); + /// # Ok::<(), std::alloc::AllocError>(()) + /// ``` + /// + /// [zeroed]: mem::MaybeUninit::zeroed + #[unstable(feature = "allocator_api", issue = "32838")] + // #[unstable(feature = "new_uninit", issue = "63291")] + #[inline] + pub fn try_new_zeroed() -> Result<Box<mem::MaybeUninit<T>>, AllocError> { + Box::try_new_zeroed_in(Global) + } +} + +impl<T, A: Allocator> Box<T, A> { + /// Allocates memory in the given allocator then places `x` into it. + /// + /// This doesn't actually allocate if `T` is zero-sized. + /// + /// # Examples + /// + /// ``` + /// #![feature(allocator_api)] + /// + /// use std::alloc::System; + /// + /// let five = Box::new_in(5, System); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[unstable(feature = "allocator_api", issue = "32838")] + #[rustc_const_unstable(feature = "const_box", issue = "92521")] + #[must_use] + #[inline] + pub const fn new_in(x: T, alloc: A) -> Self + where + A: ~const Allocator + ~const Destruct, + { + let mut boxed = Self::new_uninit_in(alloc); + unsafe { + boxed.as_mut_ptr().write(x); + boxed.assume_init() + } + } + + /// Allocates memory in the given allocator then places `x` into it, + /// returning an error if the allocation fails + /// + /// This doesn't actually allocate if `T` is zero-sized. + /// + /// # Examples + /// + /// ``` + /// #![feature(allocator_api)] + /// + /// use std::alloc::System; + /// + /// let five = Box::try_new_in(5, System)?; + /// # Ok::<(), std::alloc::AllocError>(()) + /// ``` + #[unstable(feature = "allocator_api", issue = "32838")] + #[rustc_const_unstable(feature = "const_box", issue = "92521")] + #[inline] + pub const fn try_new_in(x: T, alloc: A) -> Result<Self, AllocError> + where + T: ~const Destruct, + A: ~const Allocator + ~const Destruct, + { + let mut boxed = Self::try_new_uninit_in(alloc)?; + unsafe { + boxed.as_mut_ptr().write(x); + Ok(boxed.assume_init()) + } + } + + /// Constructs a new box with uninitialized contents in the provided allocator. + /// + /// # Examples + /// + /// ``` + /// #![feature(allocator_api, new_uninit)] + /// + /// use std::alloc::System; + /// + /// let mut five = Box::<u32, _>::new_uninit_in(System); + /// + /// let five = unsafe { + /// // Deferred initialization: + /// five.as_mut_ptr().write(5); + /// + /// five.assume_init() + /// }; + /// + /// assert_eq!(*five, 5) + /// ``` + #[unstable(feature = "allocator_api", issue = "32838")] + #[rustc_const_unstable(feature = "const_box", issue = "92521")] + #[cfg(not(no_global_oom_handling))] + #[must_use] + // #[unstable(feature = "new_uninit", issue = "63291")] + pub const fn new_uninit_in(alloc: A) -> Box<mem::MaybeUninit<T>, A> + where + A: ~const Allocator + ~const Destruct, + { + let layout = Layout::new::<mem::MaybeUninit<T>>(); + // NOTE: Prefer match over unwrap_or_else since closure sometimes not inlineable. + // That would make code size bigger. + match Box::try_new_uninit_in(alloc) { + Ok(m) => m, + Err(_) => handle_alloc_error(layout), + } + } + + /// Constructs a new box with uninitialized contents in the provided allocator, + /// returning an error if the allocation fails + /// + /// # Examples + /// + /// ``` + /// #![feature(allocator_api, new_uninit)] + /// + /// use std::alloc::System; + /// + /// let mut five = Box::<u32, _>::try_new_uninit_in(System)?; + /// + /// let five = unsafe { + /// // Deferred initialization: + /// five.as_mut_ptr().write(5); + /// + /// five.assume_init() + /// }; + /// + /// assert_eq!(*five, 5); + /// # Ok::<(), std::alloc::AllocError>(()) + /// ``` + #[unstable(feature = "allocator_api", issue = "32838")] + // #[unstable(feature = "new_uninit", issue = "63291")] + #[rustc_const_unstable(feature = "const_box", issue = "92521")] + pub const fn try_new_uninit_in(alloc: A) -> Result<Box<mem::MaybeUninit<T>, A>, AllocError> + where + A: ~const Allocator + ~const Destruct, + { + let layout = Layout::new::<mem::MaybeUninit<T>>(); + let ptr = alloc.allocate(layout)?.cast(); + unsafe { Ok(Box::from_raw_in(ptr.as_ptr(), alloc)) } + } + + /// Constructs a new `Box` with uninitialized contents, with the memory + /// being filled with `0` bytes in the provided allocator. + /// + /// See [`MaybeUninit::zeroed`][zeroed] for examples of correct and incorrect usage + /// of this method. + /// + /// # Examples + /// + /// ``` + /// #![feature(allocator_api, new_uninit)] + /// + /// use std::alloc::System; + /// + /// let zero = Box::<u32, _>::new_zeroed_in(System); + /// let zero = unsafe { zero.assume_init() }; + /// + /// assert_eq!(*zero, 0) + /// ``` + /// + /// [zeroed]: mem::MaybeUninit::zeroed + #[unstable(feature = "allocator_api", issue = "32838")] + #[rustc_const_unstable(feature = "const_box", issue = "92521")] + #[cfg(not(no_global_oom_handling))] + // #[unstable(feature = "new_uninit", issue = "63291")] + #[must_use] + pub const fn new_zeroed_in(alloc: A) -> Box<mem::MaybeUninit<T>, A> + where + A: ~const Allocator + ~const Destruct, + { + let layout = Layout::new::<mem::MaybeUninit<T>>(); + // NOTE: Prefer match over unwrap_or_else since closure sometimes not inlineable. + // That would make code size bigger. + match Box::try_new_zeroed_in(alloc) { + Ok(m) => m, + Err(_) => handle_alloc_error(layout), + } + } + + /// Constructs a new `Box` with uninitialized contents, with the memory + /// being filled with `0` bytes in the provided allocator, + /// returning an error if the allocation fails, + /// + /// See [`MaybeUninit::zeroed`][zeroed] for examples of correct and incorrect usage + /// of this method. + /// + /// # Examples + /// + /// ``` + /// #![feature(allocator_api, new_uninit)] + /// + /// use std::alloc::System; + /// + /// let zero = Box::<u32, _>::try_new_zeroed_in(System)?; + /// let zero = unsafe { zero.assume_init() }; + /// + /// assert_eq!(*zero, 0); + /// # Ok::<(), std::alloc::AllocError>(()) + /// ``` + /// + /// [zeroed]: mem::MaybeUninit::zeroed + #[unstable(feature = "allocator_api", issue = "32838")] + // #[unstable(feature = "new_uninit", issue = "63291")] + #[rustc_const_unstable(feature = "const_box", issue = "92521")] + pub const fn try_new_zeroed_in(alloc: A) -> Result<Box<mem::MaybeUninit<T>, A>, AllocError> + where + A: ~const Allocator + ~const Destruct, + { + let layout = Layout::new::<mem::MaybeUninit<T>>(); + let ptr = alloc.allocate_zeroed(layout)?.cast(); + unsafe { Ok(Box::from_raw_in(ptr.as_ptr(), alloc)) } + } + + /// Constructs a new `Pin<Box<T, A>>`. If `T` does not implement `Unpin`, then + /// `x` will be pinned in memory and unable to be moved. + #[cfg(not(no_global_oom_handling))] + #[unstable(feature = "allocator_api", issue = "32838")] + #[rustc_const_unstable(feature = "const_box", issue = "92521")] + #[must_use] + #[inline(always)] + pub const fn pin_in(x: T, alloc: A) -> Pin<Self> + where + A: 'static + ~const Allocator + ~const Destruct, + { + Self::into_pin(Self::new_in(x, alloc)) + } + + /// Converts a `Box<T>` into a `Box<[T]>` + /// + /// This conversion does not allocate on the heap and happens in place. + #[unstable(feature = "box_into_boxed_slice", issue = "71582")] + #[rustc_const_unstable(feature = "const_box", issue = "92521")] + pub const fn into_boxed_slice(boxed: Self) -> Box<[T], A> { + let (raw, alloc) = Box::into_raw_with_allocator(boxed); + unsafe { Box::from_raw_in(raw as *mut [T; 1], alloc) } + } + + /// Consumes the `Box`, returning the wrapped value. + /// + /// # Examples + /// + /// ``` + /// #![feature(box_into_inner)] + /// + /// let c = Box::new(5); + /// + /// assert_eq!(Box::into_inner(c), 5); + /// ``` + #[unstable(feature = "box_into_inner", issue = "80437")] + #[rustc_const_unstable(feature = "const_box", issue = "92521")] + #[inline] + pub const fn into_inner(boxed: Self) -> T + where + Self: ~const Destruct, + { + *boxed + } +} + +impl<T> Box<[T]> { + /// Constructs a new boxed slice with uninitialized contents. + /// + /// # Examples + /// + /// ``` + /// #![feature(new_uninit)] + /// + /// let mut values = Box::<[u32]>::new_uninit_slice(3); + /// + /// let values = unsafe { + /// // Deferred initialization: + /// values[0].as_mut_ptr().write(1); + /// values[1].as_mut_ptr().write(2); + /// values[2].as_mut_ptr().write(3); + /// + /// values.assume_init() + /// }; + /// + /// assert_eq!(*values, [1, 2, 3]) + /// ``` + #[cfg(not(no_global_oom_handling))] + #[unstable(feature = "new_uninit", issue = "63291")] + #[must_use] + pub fn new_uninit_slice(len: usize) -> Box<[mem::MaybeUninit<T>]> { + unsafe { RawVec::with_capacity(len).into_box(len) } + } + + /// Constructs a new boxed slice with uninitialized contents, with the memory + /// being filled with `0` bytes. + /// + /// See [`MaybeUninit::zeroed`][zeroed] for examples of correct and incorrect usage + /// of this method. + /// + /// # Examples + /// + /// ``` + /// #![feature(new_uninit)] + /// + /// let values = Box::<[u32]>::new_zeroed_slice(3); + /// let values = unsafe { values.assume_init() }; + /// + /// assert_eq!(*values, [0, 0, 0]) + /// ``` + /// + /// [zeroed]: mem::MaybeUninit::zeroed + #[cfg(not(no_global_oom_handling))] + #[unstable(feature = "new_uninit", issue = "63291")] + #[must_use] + pub fn new_zeroed_slice(len: usize) -> Box<[mem::MaybeUninit<T>]> { + unsafe { RawVec::with_capacity_zeroed(len).into_box(len) } + } + + /// Constructs a new boxed slice with uninitialized contents. Returns an error if + /// the allocation fails + /// + /// # Examples + /// + /// ``` + /// #![feature(allocator_api, new_uninit)] + /// + /// let mut values = Box::<[u32]>::try_new_uninit_slice(3)?; + /// let values = unsafe { + /// // Deferred initialization: + /// values[0].as_mut_ptr().write(1); + /// values[1].as_mut_ptr().write(2); + /// values[2].as_mut_ptr().write(3); + /// values.assume_init() + /// }; + /// + /// assert_eq!(*values, [1, 2, 3]); + /// # Ok::<(), std::alloc::AllocError>(()) + /// ``` + #[unstable(feature = "allocator_api", issue = "32838")] + #[inline] + pub fn try_new_uninit_slice(len: usize) -> Result<Box<[mem::MaybeUninit<T>]>, AllocError> { + unsafe { + let layout = match Layout::array::<mem::MaybeUninit<T>>(len) { + Ok(l) => l, + Err(_) => return Err(AllocError), + }; + let ptr = Global.allocate(layout)?; + Ok(RawVec::from_raw_parts_in(ptr.as_mut_ptr() as *mut _, len, Global).into_box(len)) + } + } + + /// Constructs a new boxed slice with uninitialized contents, with the memory + /// being filled with `0` bytes. Returns an error if the allocation fails + /// + /// See [`MaybeUninit::zeroed`][zeroed] for examples of correct and incorrect usage + /// of this method. + /// + /// # Examples + /// + /// ``` + /// #![feature(allocator_api, new_uninit)] + /// + /// let values = Box::<[u32]>::try_new_zeroed_slice(3)?; + /// let values = unsafe { values.assume_init() }; + /// + /// assert_eq!(*values, [0, 0, 0]); + /// # Ok::<(), std::alloc::AllocError>(()) + /// ``` + /// + /// [zeroed]: mem::MaybeUninit::zeroed + #[unstable(feature = "allocator_api", issue = "32838")] + #[inline] + pub fn try_new_zeroed_slice(len: usize) -> Result<Box<[mem::MaybeUninit<T>]>, AllocError> { + unsafe { + let layout = match Layout::array::<mem::MaybeUninit<T>>(len) { + Ok(l) => l, + Err(_) => return Err(AllocError), + }; + let ptr = Global.allocate_zeroed(layout)?; + Ok(RawVec::from_raw_parts_in(ptr.as_mut_ptr() as *mut _, len, Global).into_box(len)) + } + } +} + +impl<T, A: Allocator> Box<[T], A> { + /// Constructs a new boxed slice with uninitialized contents in the provided allocator. + /// + /// # Examples + /// + /// ``` + /// #![feature(allocator_api, new_uninit)] + /// + /// use std::alloc::System; + /// + /// let mut values = Box::<[u32], _>::new_uninit_slice_in(3, System); + /// + /// let values = unsafe { + /// // Deferred initialization: + /// values[0].as_mut_ptr().write(1); + /// values[1].as_mut_ptr().write(2); + /// values[2].as_mut_ptr().write(3); + /// + /// values.assume_init() + /// }; + /// + /// assert_eq!(*values, [1, 2, 3]) + /// ``` + #[cfg(not(no_global_oom_handling))] + #[unstable(feature = "allocator_api", issue = "32838")] + // #[unstable(feature = "new_uninit", issue = "63291")] + #[must_use] + pub fn new_uninit_slice_in(len: usize, alloc: A) -> Box<[mem::MaybeUninit<T>], A> { + unsafe { RawVec::with_capacity_in(len, alloc).into_box(len) } + } + + /// Constructs a new boxed slice with uninitialized contents in the provided allocator, + /// with the memory being filled with `0` bytes. + /// + /// See [`MaybeUninit::zeroed`][zeroed] for examples of correct and incorrect usage + /// of this method. + /// + /// # Examples + /// + /// ``` + /// #![feature(allocator_api, new_uninit)] + /// + /// use std::alloc::System; + /// + /// let values = Box::<[u32], _>::new_zeroed_slice_in(3, System); + /// let values = unsafe { values.assume_init() }; + /// + /// assert_eq!(*values, [0, 0, 0]) + /// ``` + /// + /// [zeroed]: mem::MaybeUninit::zeroed + #[cfg(not(no_global_oom_handling))] + #[unstable(feature = "allocator_api", issue = "32838")] + // #[unstable(feature = "new_uninit", issue = "63291")] + #[must_use] + pub fn new_zeroed_slice_in(len: usize, alloc: A) -> Box<[mem::MaybeUninit<T>], A> { + unsafe { RawVec::with_capacity_zeroed_in(len, alloc).into_box(len) } + } +} + +impl<T, A: Allocator> Box<mem::MaybeUninit<T>, A> { + /// Converts to `Box<T, A>`. + /// + /// # Safety + /// + /// As with [`MaybeUninit::assume_init`], + /// it is up to the caller to guarantee that the value + /// really is in an initialized state. + /// Calling this when the content is not yet fully initialized + /// causes immediate undefined behavior. + /// + /// [`MaybeUninit::assume_init`]: mem::MaybeUninit::assume_init + /// + /// # Examples + /// + /// ``` + /// #![feature(new_uninit)] + /// + /// let mut five = Box::<u32>::new_uninit(); + /// + /// let five: Box<u32> = unsafe { + /// // Deferred initialization: + /// five.as_mut_ptr().write(5); + /// + /// five.assume_init() + /// }; + /// + /// assert_eq!(*five, 5) + /// ``` + #[unstable(feature = "new_uninit", issue = "63291")] + #[rustc_const_unstable(feature = "const_box", issue = "92521")] + #[inline] + pub const unsafe fn assume_init(self) -> Box<T, A> { + let (raw, alloc) = Box::into_raw_with_allocator(self); + unsafe { Box::from_raw_in(raw as *mut T, alloc) } + } + + /// Writes the value and converts to `Box<T, A>`. + /// + /// This method converts the box similarly to [`Box::assume_init`] but + /// writes `value` into it before conversion thus guaranteeing safety. + /// In some scenarios use of this method may improve performance because + /// the compiler may be able to optimize copying from stack. + /// + /// # Examples + /// + /// ``` + /// #![feature(new_uninit)] + /// + /// let big_box = Box::<[usize; 1024]>::new_uninit(); + /// + /// let mut array = [0; 1024]; + /// for (i, place) in array.iter_mut().enumerate() { + /// *place = i; + /// } + /// + /// // The optimizer may be able to elide this copy, so previous code writes + /// // to heap directly. + /// let big_box = Box::write(big_box, array); + /// + /// for (i, x) in big_box.iter().enumerate() { + /// assert_eq!(*x, i); + /// } + /// ``` + #[unstable(feature = "new_uninit", issue = "63291")] + #[rustc_const_unstable(feature = "const_box", issue = "92521")] + #[inline] + pub const fn write(mut boxed: Self, value: T) -> Box<T, A> { + unsafe { + (*boxed).write(value); + boxed.assume_init() + } + } +} + +impl<T, A: Allocator> Box<[mem::MaybeUninit<T>], A> { + /// Converts to `Box<[T], A>`. + /// + /// # Safety + /// + /// As with [`MaybeUninit::assume_init`], + /// it is up to the caller to guarantee that the values + /// really are in an initialized state. + /// Calling this when the content is not yet fully initialized + /// causes immediate undefined behavior. + /// + /// [`MaybeUninit::assume_init`]: mem::MaybeUninit::assume_init + /// + /// # Examples + /// + /// ``` + /// #![feature(new_uninit)] + /// + /// let mut values = Box::<[u32]>::new_uninit_slice(3); + /// + /// let values = unsafe { + /// // Deferred initialization: + /// values[0].as_mut_ptr().write(1); + /// values[1].as_mut_ptr().write(2); + /// values[2].as_mut_ptr().write(3); + /// + /// values.assume_init() + /// }; + /// + /// assert_eq!(*values, [1, 2, 3]) + /// ``` + #[unstable(feature = "new_uninit", issue = "63291")] + #[inline] + pub unsafe fn assume_init(self) -> Box<[T], A> { + let (raw, alloc) = Box::into_raw_with_allocator(self); + unsafe { Box::from_raw_in(raw as *mut [T], alloc) } + } +} + +impl<T: ?Sized> Box<T> { + /// Constructs a box from a raw pointer. + /// + /// After calling this function, the raw pointer is owned by the + /// resulting `Box`. Specifically, the `Box` destructor will call + /// the destructor of `T` and free the allocated memory. For this + /// to be safe, the memory must have been allocated in accordance + /// with the [memory layout] used by `Box` . + /// + /// # Safety + /// + /// This function is unsafe because improper use may lead to + /// memory problems. For example, a double-free may occur if the + /// function is called twice on the same raw pointer. + /// + /// The safety conditions are described in the [memory layout] section. + /// + /// # Examples + /// + /// Recreate a `Box` which was previously converted to a raw pointer + /// using [`Box::into_raw`]: + /// ``` + /// let x = Box::new(5); + /// let ptr = Box::into_raw(x); + /// let x = unsafe { Box::from_raw(ptr) }; + /// ``` + /// Manually create a `Box` from scratch by using the global allocator: + /// ``` + /// use std::alloc::{alloc, Layout}; + /// + /// unsafe { + /// let ptr = alloc(Layout::new::<i32>()) as *mut i32; + /// // In general .write is required to avoid attempting to destruct + /// // the (uninitialized) previous contents of `ptr`, though for this + /// // simple example `*ptr = 5` would have worked as well. + /// ptr.write(5); + /// let x = Box::from_raw(ptr); + /// } + /// ``` + /// + /// [memory layout]: self#memory-layout + /// [`Layout`]: crate::Layout + #[stable(feature = "box_raw", since = "1.4.0")] + #[inline] + pub unsafe fn from_raw(raw: *mut T) -> Self { + unsafe { Self::from_raw_in(raw, Global) } + } +} + +impl<T: ?Sized, A: Allocator> Box<T, A> { + /// Constructs a box from a raw pointer in the given allocator. + /// + /// After calling this function, the raw pointer is owned by the + /// resulting `Box`. Specifically, the `Box` destructor will call + /// the destructor of `T` and free the allocated memory. For this + /// to be safe, the memory must have been allocated in accordance + /// with the [memory layout] used by `Box` . + /// + /// # Safety + /// + /// This function is unsafe because improper use may lead to + /// memory problems. For example, a double-free may occur if the + /// function is called twice on the same raw pointer. + /// + /// + /// # Examples + /// + /// Recreate a `Box` which was previously converted to a raw pointer + /// using [`Box::into_raw_with_allocator`]: + /// ``` + /// #![feature(allocator_api)] + /// + /// use std::alloc::System; + /// + /// let x = Box::new_in(5, System); + /// let (ptr, alloc) = Box::into_raw_with_allocator(x); + /// let x = unsafe { Box::from_raw_in(ptr, alloc) }; + /// ``` + /// Manually create a `Box` from scratch by using the system allocator: + /// ``` + /// #![feature(allocator_api, slice_ptr_get)] + /// + /// use std::alloc::{Allocator, Layout, System}; + /// + /// unsafe { + /// let ptr = System.allocate(Layout::new::<i32>())?.as_mut_ptr() as *mut i32; + /// // In general .write is required to avoid attempting to destruct + /// // the (uninitialized) previous contents of `ptr`, though for this + /// // simple example `*ptr = 5` would have worked as well. + /// ptr.write(5); + /// let x = Box::from_raw_in(ptr, System); + /// } + /// # Ok::<(), std::alloc::AllocError>(()) + /// ``` + /// + /// [memory layout]: self#memory-layout + /// [`Layout`]: crate::Layout + #[unstable(feature = "allocator_api", issue = "32838")] + #[rustc_const_unstable(feature = "const_box", issue = "92521")] + #[inline] + pub const unsafe fn from_raw_in(raw: *mut T, alloc: A) -> Self { + Box(unsafe { Unique::new_unchecked(raw) }, alloc) + } + + /// Consumes the `Box`, returning a wrapped raw pointer. + /// + /// The pointer will be properly aligned and non-null. + /// + /// After calling this function, the caller is responsible for the + /// memory previously managed by the `Box`. In particular, the + /// caller should properly destroy `T` and release the memory, taking + /// into account the [memory layout] used by `Box`. The easiest way to + /// do this is to convert the raw pointer back into a `Box` with the + /// [`Box::from_raw`] function, allowing the `Box` destructor to perform + /// the cleanup. + /// + /// Note: this is an associated function, which means that you have + /// to call it as `Box::into_raw(b)` instead of `b.into_raw()`. This + /// is so that there is no conflict with a method on the inner type. + /// + /// # Examples + /// Converting the raw pointer back into a `Box` with [`Box::from_raw`] + /// for automatic cleanup: + /// ``` + /// let x = Box::new(String::from("Hello")); + /// let ptr = Box::into_raw(x); + /// let x = unsafe { Box::from_raw(ptr) }; + /// ``` + /// Manual cleanup by explicitly running the destructor and deallocating + /// the memory: + /// ``` + /// use std::alloc::{dealloc, Layout}; + /// use std::ptr; + /// + /// let x = Box::new(String::from("Hello")); + /// let p = Box::into_raw(x); + /// unsafe { + /// ptr::drop_in_place(p); + /// dealloc(p as *mut u8, Layout::new::<String>()); + /// } + /// ``` + /// + /// [memory layout]: self#memory-layout + #[stable(feature = "box_raw", since = "1.4.0")] + #[inline] + pub fn into_raw(b: Self) -> *mut T { + Self::into_raw_with_allocator(b).0 + } + + /// Consumes the `Box`, returning a wrapped raw pointer and the allocator. + /// + /// The pointer will be properly aligned and non-null. + /// + /// After calling this function, the caller is responsible for the + /// memory previously managed by the `Box`. In particular, the + /// caller should properly destroy `T` and release the memory, taking + /// into account the [memory layout] used by `Box`. The easiest way to + /// do this is to convert the raw pointer back into a `Box` with the + /// [`Box::from_raw_in`] function, allowing the `Box` destructor to perform + /// the cleanup. + /// + /// Note: this is an associated function, which means that you have + /// to call it as `Box::into_raw_with_allocator(b)` instead of `b.into_raw_with_allocator()`. This + /// is so that there is no conflict with a method on the inner type. + /// + /// # Examples + /// Converting the raw pointer back into a `Box` with [`Box::from_raw_in`] + /// for automatic cleanup: + /// ``` + /// #![feature(allocator_api)] + /// + /// use std::alloc::System; + /// + /// let x = Box::new_in(String::from("Hello"), System); + /// let (ptr, alloc) = Box::into_raw_with_allocator(x); + /// let x = unsafe { Box::from_raw_in(ptr, alloc) }; + /// ``` + /// Manual cleanup by explicitly running the destructor and deallocating + /// the memory: + /// ``` + /// #![feature(allocator_api)] + /// + /// use std::alloc::{Allocator, Layout, System}; + /// use std::ptr::{self, NonNull}; + /// + /// let x = Box::new_in(String::from("Hello"), System); + /// let (ptr, alloc) = Box::into_raw_with_allocator(x); + /// unsafe { + /// ptr::drop_in_place(ptr); + /// let non_null = NonNull::new_unchecked(ptr); + /// alloc.deallocate(non_null.cast(), Layout::new::<String>()); + /// } + /// ``` + /// + /// [memory layout]: self#memory-layout + #[unstable(feature = "allocator_api", issue = "32838")] + #[rustc_const_unstable(feature = "const_box", issue = "92521")] + #[inline] + pub const fn into_raw_with_allocator(b: Self) -> (*mut T, A) { + let (leaked, alloc) = Box::into_unique(b); + (leaked.as_ptr(), alloc) + } + + #[unstable( + feature = "ptr_internals", + issue = "none", + reason = "use `Box::leak(b).into()` or `Unique::from(Box::leak(b))` instead" + )] + #[rustc_const_unstable(feature = "const_box", issue = "92521")] + #[inline] + #[doc(hidden)] + pub const fn into_unique(b: Self) -> (Unique<T>, A) { + // Box is recognized as a "unique pointer" by Stacked Borrows, but internally it is a + // raw pointer for the type system. Turning it directly into a raw pointer would not be + // recognized as "releasing" the unique pointer to permit aliased raw accesses, + // so all raw pointer methods have to go through `Box::leak`. Turning *that* to a raw pointer + // behaves correctly. + let alloc = unsafe { ptr::read(&b.1) }; + (Unique::from(Box::leak(b)), alloc) + } + + /// Returns a reference to the underlying allocator. + /// + /// Note: this is an associated function, which means that you have + /// to call it as `Box::allocator(&b)` instead of `b.allocator()`. This + /// is so that there is no conflict with a method on the inner type. + #[unstable(feature = "allocator_api", issue = "32838")] + #[rustc_const_unstable(feature = "const_box", issue = "92521")] + #[inline] + pub const fn allocator(b: &Self) -> &A { + &b.1 + } + + /// Consumes and leaks the `Box`, returning a mutable reference, + /// `&'a mut T`. Note that the type `T` must outlive the chosen lifetime + /// `'a`. If the type has only static references, or none at all, then this + /// may be chosen to be `'static`. + /// + /// This function is mainly useful for data that lives for the remainder of + /// the program's life. Dropping the returned reference will cause a memory + /// leak. If this is not acceptable, the reference should first be wrapped + /// with the [`Box::from_raw`] function producing a `Box`. This `Box` can + /// then be dropped which will properly destroy `T` and release the + /// allocated memory. + /// + /// Note: this is an associated function, which means that you have + /// to call it as `Box::leak(b)` instead of `b.leak()`. This + /// is so that there is no conflict with a method on the inner type. + /// + /// # Examples + /// + /// Simple usage: + /// + /// ``` + /// let x = Box::new(41); + /// let static_ref: &'static mut usize = Box::leak(x); + /// *static_ref += 1; + /// assert_eq!(*static_ref, 42); + /// ``` + /// + /// Unsized data: + /// + /// ``` + /// let x = vec![1, 2, 3].into_boxed_slice(); + /// let static_ref = Box::leak(x); + /// static_ref[0] = 4; + /// assert_eq!(*static_ref, [4, 2, 3]); + /// ``` + #[stable(feature = "box_leak", since = "1.26.0")] + #[rustc_const_unstable(feature = "const_box", issue = "92521")] + #[inline] + pub const fn leak<'a>(b: Self) -> &'a mut T + where + A: 'a, + { + unsafe { &mut *mem::ManuallyDrop::new(b).0.as_ptr() } + } + + /// Converts a `Box<T>` into a `Pin<Box<T>>` + /// + /// This conversion does not allocate on the heap and happens in place. + /// + /// This is also available via [`From`]. + #[unstable(feature = "box_into_pin", issue = "62370")] + #[rustc_const_unstable(feature = "const_box", issue = "92521")] + pub const fn into_pin(boxed: Self) -> Pin<Self> + where + A: 'static, + { + // It's not possible to move or replace the insides of a `Pin<Box<T>>` + // when `T: !Unpin`, so it's safe to pin it directly without any + // additional requirements. + unsafe { Pin::new_unchecked(boxed) } + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +unsafe impl<#[may_dangle] T: ?Sized, A: Allocator> Drop for Box<T, A> { + fn drop(&mut self) { + // FIXME: Do nothing, drop is currently performed by compiler. + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +impl<T: Default> Default for Box<T> { + /// Creates a `Box<T>`, with the `Default` value for T. + fn default() -> Self { + box T::default() + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +#[rustc_const_unstable(feature = "const_default_impls", issue = "87864")] +impl<T> const Default for Box<[T]> { + fn default() -> Self { + let ptr: Unique<[T]> = Unique::<[T; 0]>::dangling(); + Box(ptr, Global) + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "default_box_extra", since = "1.17.0")] +#[rustc_const_unstable(feature = "const_default_impls", issue = "87864")] +impl const Default for Box<str> { + fn default() -> Self { + // SAFETY: This is the same as `Unique::cast<U>` but with an unsized `U = str`. + let ptr: Unique<str> = unsafe { + let bytes: Unique<[u8]> = Unique::<[u8; 0]>::dangling(); + Unique::new_unchecked(bytes.as_ptr() as *mut str) + }; + Box(ptr, Global) + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +impl<T: Clone, A: Allocator + Clone> Clone for Box<T, A> { + /// Returns a new box with a `clone()` of this box's contents. + /// + /// # Examples + /// + /// ``` + /// let x = Box::new(5); + /// let y = x.clone(); + /// + /// // The value is the same + /// assert_eq!(x, y); + /// + /// // But they are unique objects + /// assert_ne!(&*x as *const i32, &*y as *const i32); + /// ``` + #[inline] + fn clone(&self) -> Self { + // Pre-allocate memory to allow writing the cloned value directly. + let mut boxed = Self::new_uninit_in(self.1.clone()); + unsafe { + (**self).write_clone_into_raw(boxed.as_mut_ptr()); + boxed.assume_init() + } + } + + /// Copies `source`'s contents into `self` without creating a new allocation. + /// + /// # Examples + /// + /// ``` + /// let x = Box::new(5); + /// let mut y = Box::new(10); + /// let yp: *const i32 = &*y; + /// + /// y.clone_from(&x); + /// + /// // The value is the same + /// assert_eq!(x, y); + /// + /// // And no allocation occurred + /// assert_eq!(yp, &*y); + /// ``` + #[inline] + fn clone_from(&mut self, source: &Self) { + (**self).clone_from(&(**source)); + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "box_slice_clone", since = "1.3.0")] +impl Clone for Box<str> { + fn clone(&self) -> Self { + // this makes a copy of the data + let buf: Box<[u8]> = self.as_bytes().into(); + unsafe { from_boxed_utf8_unchecked(buf) } + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<T: ?Sized + PartialEq, A: Allocator> PartialEq for Box<T, A> { + #[inline] + fn eq(&self, other: &Self) -> bool { + PartialEq::eq(&**self, &**other) + } + #[inline] + fn ne(&self, other: &Self) -> bool { + PartialEq::ne(&**self, &**other) + } +} +#[stable(feature = "rust1", since = "1.0.0")] +impl<T: ?Sized + PartialOrd, A: Allocator> PartialOrd for Box<T, A> { + #[inline] + fn partial_cmp(&self, other: &Self) -> Option<Ordering> { + PartialOrd::partial_cmp(&**self, &**other) + } + #[inline] + fn lt(&self, other: &Self) -> bool { + PartialOrd::lt(&**self, &**other) + } + #[inline] + fn le(&self, other: &Self) -> bool { + PartialOrd::le(&**self, &**other) + } + #[inline] + fn ge(&self, other: &Self) -> bool { + PartialOrd::ge(&**self, &**other) + } + #[inline] + fn gt(&self, other: &Self) -> bool { + PartialOrd::gt(&**self, &**other) + } +} +#[stable(feature = "rust1", since = "1.0.0")] +impl<T: ?Sized + Ord, A: Allocator> Ord for Box<T, A> { + #[inline] + fn cmp(&self, other: &Self) -> Ordering { + Ord::cmp(&**self, &**other) + } +} +#[stable(feature = "rust1", since = "1.0.0")] +impl<T: ?Sized + Eq, A: Allocator> Eq for Box<T, A> {} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<T: ?Sized + Hash, A: Allocator> Hash for Box<T, A> { + fn hash<H: Hasher>(&self, state: &mut H) { + (**self).hash(state); + } +} + +#[stable(feature = "indirect_hasher_impl", since = "1.22.0")] +impl<T: ?Sized + Hasher, A: Allocator> Hasher for Box<T, A> { + fn finish(&self) -> u64 { + (**self).finish() + } + fn write(&mut self, bytes: &[u8]) { + (**self).write(bytes) + } + fn write_u8(&mut self, i: u8) { + (**self).write_u8(i) + } + fn write_u16(&mut self, i: u16) { + (**self).write_u16(i) + } + fn write_u32(&mut self, i: u32) { + (**self).write_u32(i) + } + fn write_u64(&mut self, i: u64) { + (**self).write_u64(i) + } + fn write_u128(&mut self, i: u128) { + (**self).write_u128(i) + } + fn write_usize(&mut self, i: usize) { + (**self).write_usize(i) + } + fn write_i8(&mut self, i: i8) { + (**self).write_i8(i) + } + fn write_i16(&mut self, i: i16) { + (**self).write_i16(i) + } + fn write_i32(&mut self, i: i32) { + (**self).write_i32(i) + } + fn write_i64(&mut self, i: i64) { + (**self).write_i64(i) + } + fn write_i128(&mut self, i: i128) { + (**self).write_i128(i) + } + fn write_isize(&mut self, i: isize) { + (**self).write_isize(i) + } + fn write_length_prefix(&mut self, len: usize) { + (**self).write_length_prefix(len) + } + fn write_str(&mut self, s: &str) { + (**self).write_str(s) + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "from_for_ptrs", since = "1.6.0")] +impl<T> From<T> for Box<T> { + /// Converts a `T` into a `Box<T>` + /// + /// The conversion allocates on the heap and moves `t` + /// from the stack into it. + /// + /// # Examples + /// + /// ```rust + /// let x = 5; + /// let boxed = Box::new(5); + /// + /// assert_eq!(Box::from(x), boxed); + /// ``` + fn from(t: T) -> Self { + Box::new(t) + } +} + +#[stable(feature = "pin", since = "1.33.0")] +#[rustc_const_unstable(feature = "const_box", issue = "92521")] +impl<T: ?Sized, A: Allocator> const From<Box<T, A>> for Pin<Box<T, A>> +where + A: 'static, +{ + /// Converts a `Box<T>` into a `Pin<Box<T>>` + /// + /// This conversion does not allocate on the heap and happens in place. + fn from(boxed: Box<T, A>) -> Self { + Box::into_pin(boxed) + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "box_from_slice", since = "1.17.0")] +impl<T: Copy> From<&[T]> for Box<[T]> { + /// Converts a `&[T]` into a `Box<[T]>` + /// + /// This conversion allocates on the heap + /// and performs a copy of `slice`. + /// + /// # Examples + /// ```rust + /// // create a &[u8] which will be used to create a Box<[u8]> + /// let slice: &[u8] = &[104, 101, 108, 108, 111]; + /// let boxed_slice: Box<[u8]> = Box::from(slice); + /// + /// println!("{boxed_slice:?}"); + /// ``` + fn from(slice: &[T]) -> Box<[T]> { + let len = slice.len(); + let buf = RawVec::with_capacity(len); + unsafe { + ptr::copy_nonoverlapping(slice.as_ptr(), buf.ptr(), len); + buf.into_box(slice.len()).assume_init() + } + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "box_from_cow", since = "1.45.0")] +impl<T: Copy> From<Cow<'_, [T]>> for Box<[T]> { + /// Converts a `Cow<'_, [T]>` into a `Box<[T]>` + /// + /// When `cow` is the `Cow::Borrowed` variant, this + /// conversion allocates on the heap and copies the + /// underlying slice. Otherwise, it will try to reuse the owned + /// `Vec`'s allocation. + #[inline] + fn from(cow: Cow<'_, [T]>) -> Box<[T]> { + match cow { + Cow::Borrowed(slice) => Box::from(slice), + Cow::Owned(slice) => Box::from(slice), + } + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "box_from_slice", since = "1.17.0")] +impl From<&str> for Box<str> { + /// Converts a `&str` into a `Box<str>` + /// + /// This conversion allocates on the heap + /// and performs a copy of `s`. + /// + /// # Examples + /// + /// ```rust + /// let boxed: Box<str> = Box::from("hello"); + /// println!("{boxed}"); + /// ``` + #[inline] + fn from(s: &str) -> Box<str> { + unsafe { from_boxed_utf8_unchecked(Box::from(s.as_bytes())) } + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "box_from_cow", since = "1.45.0")] +impl From<Cow<'_, str>> for Box<str> { + /// Converts a `Cow<'_, str>` into a `Box<str>` + /// + /// When `cow` is the `Cow::Borrowed` variant, this + /// conversion allocates on the heap and copies the + /// underlying `str`. Otherwise, it will try to reuse the owned + /// `String`'s allocation. + /// + /// # Examples + /// + /// ```rust + /// use std::borrow::Cow; + /// + /// let unboxed = Cow::Borrowed("hello"); + /// let boxed: Box<str> = Box::from(unboxed); + /// println!("{boxed}"); + /// ``` + /// + /// ```rust + /// # use std::borrow::Cow; + /// let unboxed = Cow::Owned("hello".to_string()); + /// let boxed: Box<str> = Box::from(unboxed); + /// println!("{boxed}"); + /// ``` + #[inline] + fn from(cow: Cow<'_, str>) -> Box<str> { + match cow { + Cow::Borrowed(s) => Box::from(s), + Cow::Owned(s) => Box::from(s), + } + } +} + +#[stable(feature = "boxed_str_conv", since = "1.19.0")] +impl<A: Allocator> From<Box<str, A>> for Box<[u8], A> { + /// Converts a `Box<str>` into a `Box<[u8]>` + /// + /// This conversion does not allocate on the heap and happens in place. + /// + /// # Examples + /// ```rust + /// // create a Box<str> which will be used to create a Box<[u8]> + /// let boxed: Box<str> = Box::from("hello"); + /// let boxed_str: Box<[u8]> = Box::from(boxed); + /// + /// // create a &[u8] which will be used to create a Box<[u8]> + /// let slice: &[u8] = &[104, 101, 108, 108, 111]; + /// let boxed_slice = Box::from(slice); + /// + /// assert_eq!(boxed_slice, boxed_str); + /// ``` + #[inline] + fn from(s: Box<str, A>) -> Self { + let (raw, alloc) = Box::into_raw_with_allocator(s); + unsafe { Box::from_raw_in(raw as *mut [u8], alloc) } + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "box_from_array", since = "1.45.0")] +impl<T, const N: usize> From<[T; N]> for Box<[T]> { + /// Converts a `[T; N]` into a `Box<[T]>` + /// + /// This conversion moves the array to newly heap-allocated memory. + /// + /// # Examples + /// + /// ```rust + /// let boxed: Box<[u8]> = Box::from([4, 2]); + /// println!("{boxed:?}"); + /// ``` + fn from(array: [T; N]) -> Box<[T]> { + box array + } +} + +#[stable(feature = "boxed_slice_try_from", since = "1.43.0")] +impl<T, const N: usize> TryFrom<Box<[T]>> for Box<[T; N]> { + type Error = Box<[T]>; + + /// Attempts to convert a `Box<[T]>` into a `Box<[T; N]>`. + /// + /// The conversion occurs in-place and does not require a + /// new memory allocation. + /// + /// # Errors + /// + /// Returns the old `Box<[T]>` in the `Err` variant if + /// `boxed_slice.len()` does not equal `N`. + fn try_from(boxed_slice: Box<[T]>) -> Result<Self, Self::Error> { + if boxed_slice.len() == N { + Ok(unsafe { Box::from_raw(Box::into_raw(boxed_slice) as *mut [T; N]) }) + } else { + Err(boxed_slice) + } + } +} + +impl<A: Allocator> Box<dyn Any, A> { + /// Attempt to downcast the box to a concrete type. + /// + /// # Examples + /// + /// ``` + /// use std::any::Any; + /// + /// fn print_if_string(value: Box<dyn Any>) { + /// if let Ok(string) = value.downcast::<String>() { + /// println!("String ({}): {}", string.len(), string); + /// } + /// } + /// + /// let my_string = "Hello World".to_string(); + /// print_if_string(Box::new(my_string)); + /// print_if_string(Box::new(0i8)); + /// ``` + #[inline] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn downcast<T: Any>(self) -> Result<Box<T, A>, Self> { + if self.is::<T>() { unsafe { Ok(self.downcast_unchecked::<T>()) } } else { Err(self) } + } + + /// Downcasts the box to a concrete type. + /// + /// For a safe alternative see [`downcast`]. + /// + /// # Examples + /// + /// ``` + /// #![feature(downcast_unchecked)] + /// + /// use std::any::Any; + /// + /// let x: Box<dyn Any> = Box::new(1_usize); + /// + /// unsafe { + /// assert_eq!(*x.downcast_unchecked::<usize>(), 1); + /// } + /// ``` + /// + /// # Safety + /// + /// The contained value must be of type `T`. Calling this method + /// with the incorrect type is *undefined behavior*. + /// + /// [`downcast`]: Self::downcast + #[inline] + #[unstable(feature = "downcast_unchecked", issue = "90850")] + pub unsafe fn downcast_unchecked<T: Any>(self) -> Box<T, A> { + debug_assert!(self.is::<T>()); + unsafe { + let (raw, alloc): (*mut dyn Any, _) = Box::into_raw_with_allocator(self); + Box::from_raw_in(raw as *mut T, alloc) + } + } +} + +impl<A: Allocator> Box<dyn Any + Send, A> { + /// Attempt to downcast the box to a concrete type. + /// + /// # Examples + /// + /// ``` + /// use std::any::Any; + /// + /// fn print_if_string(value: Box<dyn Any + Send>) { + /// if let Ok(string) = value.downcast::<String>() { + /// println!("String ({}): {}", string.len(), string); + /// } + /// } + /// + /// let my_string = "Hello World".to_string(); + /// print_if_string(Box::new(my_string)); + /// print_if_string(Box::new(0i8)); + /// ``` + #[inline] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn downcast<T: Any>(self) -> Result<Box<T, A>, Self> { + if self.is::<T>() { unsafe { Ok(self.downcast_unchecked::<T>()) } } else { Err(self) } + } + + /// Downcasts the box to a concrete type. + /// + /// For a safe alternative see [`downcast`]. + /// + /// # Examples + /// + /// ``` + /// #![feature(downcast_unchecked)] + /// + /// use std::any::Any; + /// + /// let x: Box<dyn Any + Send> = Box::new(1_usize); + /// + /// unsafe { + /// assert_eq!(*x.downcast_unchecked::<usize>(), 1); + /// } + /// ``` + /// + /// # Safety + /// + /// The contained value must be of type `T`. Calling this method + /// with the incorrect type is *undefined behavior*. + /// + /// [`downcast`]: Self::downcast + #[inline] + #[unstable(feature = "downcast_unchecked", issue = "90850")] + pub unsafe fn downcast_unchecked<T: Any>(self) -> Box<T, A> { + debug_assert!(self.is::<T>()); + unsafe { + let (raw, alloc): (*mut (dyn Any + Send), _) = Box::into_raw_with_allocator(self); + Box::from_raw_in(raw as *mut T, alloc) + } + } +} + +impl<A: Allocator> Box<dyn Any + Send + Sync, A> { + /// Attempt to downcast the box to a concrete type. + /// + /// # Examples + /// + /// ``` + /// use std::any::Any; + /// + /// fn print_if_string(value: Box<dyn Any + Send + Sync>) { + /// if let Ok(string) = value.downcast::<String>() { + /// println!("String ({}): {}", string.len(), string); + /// } + /// } + /// + /// let my_string = "Hello World".to_string(); + /// print_if_string(Box::new(my_string)); + /// print_if_string(Box::new(0i8)); + /// ``` + #[inline] + #[stable(feature = "box_send_sync_any_downcast", since = "1.51.0")] + pub fn downcast<T: Any>(self) -> Result<Box<T, A>, Self> { + if self.is::<T>() { unsafe { Ok(self.downcast_unchecked::<T>()) } } else { Err(self) } + } + + /// Downcasts the box to a concrete type. + /// + /// For a safe alternative see [`downcast`]. + /// + /// # Examples + /// + /// ``` + /// #![feature(downcast_unchecked)] + /// + /// use std::any::Any; + /// + /// let x: Box<dyn Any + Send + Sync> = Box::new(1_usize); + /// + /// unsafe { + /// assert_eq!(*x.downcast_unchecked::<usize>(), 1); + /// } + /// ``` + /// + /// # Safety + /// + /// The contained value must be of type `T`. Calling this method + /// with the incorrect type is *undefined behavior*. + /// + /// [`downcast`]: Self::downcast + #[inline] + #[unstable(feature = "downcast_unchecked", issue = "90850")] + pub unsafe fn downcast_unchecked<T: Any>(self) -> Box<T, A> { + debug_assert!(self.is::<T>()); + unsafe { + let (raw, alloc): (*mut (dyn Any + Send + Sync), _) = + Box::into_raw_with_allocator(self); + Box::from_raw_in(raw as *mut T, alloc) + } + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<T: fmt::Display + ?Sized, A: Allocator> fmt::Display for Box<T, A> { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + fmt::Display::fmt(&**self, f) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<T: fmt::Debug + ?Sized, A: Allocator> fmt::Debug for Box<T, A> { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + fmt::Debug::fmt(&**self, f) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<T: ?Sized, A: Allocator> fmt::Pointer for Box<T, A> { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + // It's not possible to extract the inner Uniq directly from the Box, + // instead we cast it to a *const which aliases the Unique + let ptr: *const T = &**self; + fmt::Pointer::fmt(&ptr, f) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +#[rustc_const_unstable(feature = "const_box", issue = "92521")] +impl<T: ?Sized, A: Allocator> const Deref for Box<T, A> { + type Target = T; + + fn deref(&self) -> &T { + &**self + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +#[rustc_const_unstable(feature = "const_box", issue = "92521")] +impl<T: ?Sized, A: Allocator> const DerefMut for Box<T, A> { + fn deref_mut(&mut self) -> &mut T { + &mut **self + } +} + +#[unstable(feature = "receiver_trait", issue = "none")] +impl<T: ?Sized, A: Allocator> Receiver for Box<T, A> {} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<I: Iterator + ?Sized, A: Allocator> Iterator for Box<I, A> { + type Item = I::Item; + fn next(&mut self) -> Option<I::Item> { + (**self).next() + } + fn size_hint(&self) -> (usize, Option<usize>) { + (**self).size_hint() + } + fn nth(&mut self, n: usize) -> Option<I::Item> { + (**self).nth(n) + } + fn last(self) -> Option<I::Item> { + BoxIter::last(self) + } +} + +trait BoxIter { + type Item; + fn last(self) -> Option<Self::Item>; +} + +impl<I: Iterator + ?Sized, A: Allocator> BoxIter for Box<I, A> { + type Item = I::Item; + default fn last(self) -> Option<I::Item> { + #[inline] + fn some<T>(_: Option<T>, x: T) -> Option<T> { + Some(x) + } + + self.fold(None, some) + } +} + +/// Specialization for sized `I`s that uses `I`s implementation of `last()` +/// instead of the default. +#[stable(feature = "rust1", since = "1.0.0")] +impl<I: Iterator, A: Allocator> BoxIter for Box<I, A> { + fn last(self) -> Option<I::Item> { + (*self).last() + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<I: DoubleEndedIterator + ?Sized, A: Allocator> DoubleEndedIterator for Box<I, A> { + fn next_back(&mut self) -> Option<I::Item> { + (**self).next_back() + } + fn nth_back(&mut self, n: usize) -> Option<I::Item> { + (**self).nth_back(n) + } +} +#[stable(feature = "rust1", since = "1.0.0")] +impl<I: ExactSizeIterator + ?Sized, A: Allocator> ExactSizeIterator for Box<I, A> { + fn len(&self) -> usize { + (**self).len() + } + fn is_empty(&self) -> bool { + (**self).is_empty() + } +} + +#[stable(feature = "fused", since = "1.26.0")] +impl<I: FusedIterator + ?Sized, A: Allocator> FusedIterator for Box<I, A> {} + +#[stable(feature = "boxed_closure_impls", since = "1.35.0")] +impl<Args, F: FnOnce<Args> + ?Sized, A: Allocator> FnOnce<Args> for Box<F, A> { + type Output = <F as FnOnce<Args>>::Output; + + extern "rust-call" fn call_once(self, args: Args) -> Self::Output { + <F as FnOnce<Args>>::call_once(*self, args) + } +} + +#[stable(feature = "boxed_closure_impls", since = "1.35.0")] +impl<Args, F: FnMut<Args> + ?Sized, A: Allocator> FnMut<Args> for Box<F, A> { + extern "rust-call" fn call_mut(&mut self, args: Args) -> Self::Output { + <F as FnMut<Args>>::call_mut(self, args) + } +} + +#[stable(feature = "boxed_closure_impls", since = "1.35.0")] +impl<Args, F: Fn<Args> + ?Sized, A: Allocator> Fn<Args> for Box<F, A> { + extern "rust-call" fn call(&self, args: Args) -> Self::Output { + <F as Fn<Args>>::call(self, args) + } +} + +#[unstable(feature = "coerce_unsized", issue = "27732")] +impl<T: ?Sized + Unsize<U>, U: ?Sized, A: Allocator> CoerceUnsized<Box<U, A>> for Box<T, A> {} + +#[unstable(feature = "dispatch_from_dyn", issue = "none")] +impl<T: ?Sized + Unsize<U>, U: ?Sized> DispatchFromDyn<Box<U>> for Box<T, Global> {} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "boxed_slice_from_iter", since = "1.32.0")] +impl<I> FromIterator<I> for Box<[I]> { + fn from_iter<T: IntoIterator<Item = I>>(iter: T) -> Self { + iter.into_iter().collect::<Vec<_>>().into_boxed_slice() + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "box_slice_clone", since = "1.3.0")] +impl<T: Clone, A: Allocator + Clone> Clone for Box<[T], A> { + fn clone(&self) -> Self { + let alloc = Box::allocator(self).clone(); + self.to_vec_in(alloc).into_boxed_slice() + } + + fn clone_from(&mut self, other: &Self) { + if self.len() == other.len() { + self.clone_from_slice(&other); + } else { + *self = other.clone(); + } + } +} + +#[stable(feature = "box_borrow", since = "1.1.0")] +impl<T: ?Sized, A: Allocator> borrow::Borrow<T> for Box<T, A> { + fn borrow(&self) -> &T { + &**self + } +} + +#[stable(feature = "box_borrow", since = "1.1.0")] +impl<T: ?Sized, A: Allocator> borrow::BorrowMut<T> for Box<T, A> { + fn borrow_mut(&mut self) -> &mut T { + &mut **self + } +} + +#[stable(since = "1.5.0", feature = "smart_ptr_as_ref")] +impl<T: ?Sized, A: Allocator> AsRef<T> for Box<T, A> { + fn as_ref(&self) -> &T { + &**self + } +} + +#[stable(since = "1.5.0", feature = "smart_ptr_as_ref")] +impl<T: ?Sized, A: Allocator> AsMut<T> for Box<T, A> { + fn as_mut(&mut self) -> &mut T { + &mut **self + } +} + +/* Nota bene + * + * We could have chosen not to add this impl, and instead have written a + * function of Pin<Box<T>> to Pin<T>. Such a function would not be sound, + * because Box<T> implements Unpin even when T does not, as a result of + * this impl. + * + * We chose this API instead of the alternative for a few reasons: + * - Logically, it is helpful to understand pinning in regard to the + * memory region being pointed to. For this reason none of the + * standard library pointer types support projecting through a pin + * (Box<T> is the only pointer type in std for which this would be + * safe.) + * - It is in practice very useful to have Box<T> be unconditionally + * Unpin because of trait objects, for which the structural auto + * trait functionality does not apply (e.g., Box<dyn Foo> would + * otherwise not be Unpin). + * + * Another type with the same semantics as Box but only a conditional + * implementation of `Unpin` (where `T: Unpin`) would be valid/safe, and + * could have a method to project a Pin<T> from it. + */ +#[stable(feature = "pin", since = "1.33.0")] +#[rustc_const_unstable(feature = "const_box", issue = "92521")] +impl<T: ?Sized, A: Allocator> const Unpin for Box<T, A> where A: 'static {} + +#[unstable(feature = "generator_trait", issue = "43122")] +impl<G: ?Sized + Generator<R> + Unpin, R, A: Allocator> Generator<R> for Box<G, A> +where + A: 'static, +{ + type Yield = G::Yield; + type Return = G::Return; + + fn resume(mut self: Pin<&mut Self>, arg: R) -> GeneratorState<Self::Yield, Self::Return> { + G::resume(Pin::new(&mut *self), arg) + } +} + +#[unstable(feature = "generator_trait", issue = "43122")] +impl<G: ?Sized + Generator<R>, R, A: Allocator> Generator<R> for Pin<Box<G, A>> +where + A: 'static, +{ + type Yield = G::Yield; + type Return = G::Return; + + fn resume(mut self: Pin<&mut Self>, arg: R) -> GeneratorState<Self::Yield, Self::Return> { + G::resume((*self).as_mut(), arg) + } +} + +#[stable(feature = "futures_api", since = "1.36.0")] +impl<F: ?Sized + Future + Unpin, A: Allocator> Future for Box<F, A> +where + A: 'static, +{ + type Output = F::Output; + + fn poll(mut self: Pin<&mut Self>, cx: &mut Context<'_>) -> Poll<Self::Output> { + F::poll(Pin::new(&mut *self), cx) + } +} + +#[unstable(feature = "async_iterator", issue = "79024")] +impl<S: ?Sized + AsyncIterator + Unpin> AsyncIterator for Box<S> { + type Item = S::Item; + + fn poll_next(mut self: Pin<&mut Self>, cx: &mut Context<'_>) -> Poll<Option<Self::Item>> { + Pin::new(&mut **self).poll_next(cx) + } + + fn size_hint(&self) -> (usize, Option<usize>) { + (**self).size_hint() + } +} diff --git a/rust/alloc/collections/mod.rs b/rust/alloc/collections/mod.rs new file mode 100644 index 000000000000..1eec265b28f8 --- /dev/null +++ b/rust/alloc/collections/mod.rs @@ -0,0 +1,156 @@ +// SPDX-License-Identifier: Apache-2.0 OR MIT + +//! Collection types. + +#![stable(feature = "rust1", since = "1.0.0")] + +#[cfg(not(no_global_oom_handling))] +pub mod binary_heap; +#[cfg(not(no_global_oom_handling))] +mod btree; +#[cfg(not(no_global_oom_handling))] +pub mod linked_list; +#[cfg(not(no_global_oom_handling))] +pub mod vec_deque; + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +pub mod btree_map { + //! An ordered map based on a B-Tree. + #[stable(feature = "rust1", since = "1.0.0")] + pub use super::btree::map::*; +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +pub mod btree_set { + //! An ordered set based on a B-Tree. + #[stable(feature = "rust1", since = "1.0.0")] + pub use super::btree::set::*; +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +#[doc(no_inline)] +pub use binary_heap::BinaryHeap; + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +#[doc(no_inline)] +pub use btree_map::BTreeMap; + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +#[doc(no_inline)] +pub use btree_set::BTreeSet; + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +#[doc(no_inline)] +pub use linked_list::LinkedList; + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +#[doc(no_inline)] +pub use vec_deque::VecDeque; + +use crate::alloc::{Layout, LayoutError}; +use core::fmt::Display; + +/// The error type for `try_reserve` methods. +#[derive(Clone, PartialEq, Eq, Debug)] +#[stable(feature = "try_reserve", since = "1.57.0")] +pub struct TryReserveError { + kind: TryReserveErrorKind, +} + +impl TryReserveError { + /// Details about the allocation that caused the error + #[inline] + #[must_use] + #[unstable( + feature = "try_reserve_kind", + reason = "Uncertain how much info should be exposed", + issue = "48043" + )] + pub fn kind(&self) -> TryReserveErrorKind { + self.kind.clone() + } +} + +/// Details of the allocation that caused a `TryReserveError` +#[derive(Clone, PartialEq, Eq, Debug)] +#[unstable( + feature = "try_reserve_kind", + reason = "Uncertain how much info should be exposed", + issue = "48043" +)] +pub enum TryReserveErrorKind { + /// Error due to the computed capacity exceeding the collection's maximum + /// (usually `isize::MAX` bytes). + CapacityOverflow, + + /// The memory allocator returned an error + AllocError { + /// The layout of allocation request that failed + layout: Layout, + + #[doc(hidden)] + #[unstable( + feature = "container_error_extra", + issue = "none", + reason = "\ + Enable exposing the allocator’s custom error value \ + if an associated type is added in the future: \ + https://github.com/rust-lang/wg-allocators/issues/23" + )] + non_exhaustive: (), + }, +} + +#[unstable( + feature = "try_reserve_kind", + reason = "Uncertain how much info should be exposed", + issue = "48043" +)] +impl From<TryReserveErrorKind> for TryReserveError { + #[inline] + fn from(kind: TryReserveErrorKind) -> Self { + Self { kind } + } +} + +#[unstable(feature = "try_reserve_kind", reason = "new API", issue = "48043")] +impl From<LayoutError> for TryReserveErrorKind { + /// Always evaluates to [`TryReserveErrorKind::CapacityOverflow`]. + #[inline] + fn from(_: LayoutError) -> Self { + TryReserveErrorKind::CapacityOverflow + } +} + +#[stable(feature = "try_reserve", since = "1.57.0")] +impl Display for TryReserveError { + fn fmt( + &self, + fmt: &mut core::fmt::Formatter<'_>, + ) -> core::result::Result<(), core::fmt::Error> { + fmt.write_str("memory allocation failed")?; + let reason = match self.kind { + TryReserveErrorKind::CapacityOverflow => { + " because the computed capacity exceeded the collection's maximum" + } + TryReserveErrorKind::AllocError { .. } => { + " because the memory allocator returned a error" + } + }; + fmt.write_str(reason) + } +} + +/// An intermediate trait for specialization of `Extend`. +#[doc(hidden)] +trait SpecExtend<I: IntoIterator> { + /// Extends `self` with the contents of the given iterator. + fn spec_extend(&mut self, iter: I); +} diff --git a/rust/alloc/lib.rs b/rust/alloc/lib.rs new file mode 100644 index 000000000000..233bcd5e4654 --- /dev/null +++ b/rust/alloc/lib.rs @@ -0,0 +1,244 @@ +// SPDX-License-Identifier: Apache-2.0 OR MIT + +//! # The Rust core allocation and collections library +//! +//! This library provides smart pointers and collections for managing +//! heap-allocated values. +//! +//! This library, like libcore, normally doesn’t need to be used directly +//! since its contents are re-exported in the [`std` crate](../std/index.html). +//! Crates that use the `#![no_std]` attribute however will typically +//! not depend on `std`, so they’d use this crate instead. +//! +//! ## Boxed values +//! +//! The [`Box`] type is a smart pointer type. There can only be one owner of a +//! [`Box`], and the owner can decide to mutate the contents, which live on the +//! heap. +//! +//! This type can be sent among threads efficiently as the size of a `Box` value +//! is the same as that of a pointer. Tree-like data structures are often built +//! with boxes because each node often has only one owner, the parent. +//! +//! ## Reference counted pointers +//! +//! The [`Rc`] type is a non-threadsafe reference-counted pointer type intended +//! for sharing memory within a thread. An [`Rc`] pointer wraps a type, `T`, and +//! only allows access to `&T`, a shared reference. +//! +//! This type is useful when inherited mutability (such as using [`Box`]) is too +//! constraining for an application, and is often paired with the [`Cell`] or +//! [`RefCell`] types in order to allow mutation. +//! +//! ## Atomically reference counted pointers +//! +//! The [`Arc`] type is the threadsafe equivalent of the [`Rc`] type. It +//! provides all the same functionality of [`Rc`], except it requires that the +//! contained type `T` is shareable. Additionally, [`Arc<T>`][`Arc`] is itself +//! sendable while [`Rc<T>`][`Rc`] is not. +//! +//! This type allows for shared access to the contained data, and is often +//! paired with synchronization primitives such as mutexes to allow mutation of +//! shared resources. +//! +//! ## Collections +//! +//! Implementations of the most common general purpose data structures are +//! defined in this library. They are re-exported through the +//! [standard collections library](../std/collections/index.html). +//! +//! ## Heap interfaces +//! +//! The [`alloc`](alloc/index.html) module defines the low-level interface to the +//! default global allocator. It is not compatible with the libc allocator API. +//! +//! [`Arc`]: sync +//! [`Box`]: boxed +//! [`Cell`]: core::cell +//! [`Rc`]: rc +//! [`RefCell`]: core::cell + +// To run liballoc tests without x.py without ending up with two copies of liballoc, Miri needs to be +// able to "empty" this crate. See <https://github.com/rust-lang/miri-test-libstd/issues/4>. +// rustc itself never sets the feature, so this line has no affect there. +#![cfg(any(not(feature = "miri-test-libstd"), test, doctest))] +#![allow(unused_attributes)] +#![stable(feature = "alloc", since = "1.36.0")] +#![doc( + html_playground_url = "https://play.rust-lang.org/", + issue_tracker_base_url = "https://github.com/rust-lang/rust/issues/", + test(no_crate_inject, attr(allow(unused_variables), deny(warnings))) +)] +#![doc(cfg_hide( + not(test), + not(any(test, bootstrap)), + any(not(feature = "miri-test-libstd"), test, doctest), + no_global_oom_handling, + not(no_global_oom_handling), + target_has_atomic = "ptr" +))] +#![no_std] +#![needs_allocator] +// +// Lints: +#![deny(unsafe_op_in_unsafe_fn)] +#![warn(deprecated_in_future)] +#![warn(missing_debug_implementations)] +#![warn(missing_docs)] +#![allow(explicit_outlives_requirements)] +// +// Library features: +#![cfg_attr(not(no_global_oom_handling), feature(alloc_c_string))] +#![feature(alloc_layout_extra)] +#![feature(allocator_api)] +#![feature(array_chunks)] +#![feature(array_methods)] +#![feature(array_windows)] +#![feature(assert_matches)] +#![feature(async_iterator)] +#![feature(coerce_unsized)] +#![cfg_attr(not(no_global_oom_handling), feature(const_alloc_error))] +#![feature(const_box)] +#![cfg_attr(not(no_global_oom_handling), feature(const_btree_new))] +#![feature(const_cow_is_borrowed)] +#![feature(const_convert)] +#![feature(const_size_of_val)] +#![feature(const_align_of_val)] +#![feature(const_ptr_read)] +#![feature(const_maybe_uninit_write)] +#![feature(const_maybe_uninit_as_mut_ptr)] +#![feature(const_refs_to_cell)] +#![feature(core_c_str)] +#![feature(core_intrinsics)] +#![feature(core_ffi_c)] +#![feature(const_eval_select)] +#![feature(const_pin)] +#![feature(cstr_from_bytes_until_nul)] +#![feature(dispatch_from_dyn)] +#![feature(exact_size_is_empty)] +#![feature(extend_one)] +#![feature(fmt_internals)] +#![feature(fn_traits)] +#![feature(hasher_prefixfree_extras)] +#![feature(inplace_iteration)] +#![feature(iter_advance_by)] +#![feature(layout_for_ptr)] +#![feature(maybe_uninit_slice)] +#![cfg_attr(test, feature(new_uninit))] +#![feature(nonnull_slice_from_raw_parts)] +#![feature(pattern)] +#![feature(ptr_internals)] +#![feature(ptr_metadata)] +#![feature(ptr_sub_ptr)] +#![feature(receiver_trait)] +#![feature(set_ptr_value)] +#![feature(slice_group_by)] +#![feature(slice_ptr_get)] +#![feature(slice_ptr_len)] +#![feature(slice_range)] +#![feature(str_internals)] +#![feature(strict_provenance)] +#![feature(trusted_len)] +#![feature(trusted_random_access)] +#![feature(try_trait_v2)] +#![feature(unchecked_math)] +#![feature(unicode_internals)] +#![feature(unsize)] +// +// Language features: +#![feature(allocator_internals)] +#![feature(allow_internal_unstable)] +#![feature(associated_type_bounds)] +#![feature(box_syntax)] +#![feature(cfg_sanitize)] +#![feature(const_deref)] +#![feature(const_mut_refs)] +#![feature(const_ptr_write)] +#![feature(const_precise_live_drops)] +#![feature(const_trait_impl)] +#![feature(const_try)] +#![feature(dropck_eyepatch)] +#![feature(exclusive_range_pattern)] +#![feature(fundamental)] +#![cfg_attr(not(test), feature(generator_trait))] +#![feature(hashmap_internals)] +#![feature(lang_items)] +#![feature(let_else)] +#![feature(min_specialization)] +#![feature(negative_impls)] +#![feature(never_type)] +#![feature(nll)] // Not necessary, but here to test the `nll` feature. +#![feature(rustc_allow_const_fn_unstable)] +#![feature(rustc_attrs)] +#![feature(slice_internals)] +#![feature(staged_api)] +#![cfg_attr(test, feature(test))] +#![feature(unboxed_closures)] +#![feature(unsized_fn_params)] +#![feature(c_unwind)] +// +// Rustdoc features: +#![feature(doc_cfg)] +#![feature(doc_cfg_hide)] +// Technically, this is a bug in rustdoc: rustdoc sees the documentation on `#[lang = slice_alloc]` +// blocks is for `&[T]`, which also has documentation using this feature in `core`, and gets mad +// that the feature-gate isn't enabled. Ideally, it wouldn't check for the feature gate for docs +// from other crates, but since this can only appear for lang items, it doesn't seem worth fixing. +#![feature(intra_doc_pointers)] + +// Allow testing this library +#[cfg(test)] +#[macro_use] +extern crate std; +#[cfg(test)] +extern crate test; + +// Module with internal macros used by other modules (needs to be included before other modules). +#[cfg(not(no_macros))] +#[macro_use] +mod macros; + +mod raw_vec; + +// Heaps provided for low-level allocation strategies + +pub mod alloc; + +// Primitive types using the heaps above + +// Need to conditionally define the mod from `boxed.rs` to avoid +// duplicating the lang-items when building in test cfg; but also need +// to allow code to have `use boxed::Box;` declarations. +#[cfg(not(test))] +pub mod boxed; +#[cfg(test)] +mod boxed { + pub use std::boxed::Box; +} +pub mod borrow; +pub mod collections; +#[cfg(not(no_global_oom_handling))] +pub mod ffi; +#[cfg(not(no_fmt))] +pub mod fmt; +#[cfg(not(no_rc))] +pub mod rc; +pub mod slice; +#[cfg(not(no_str))] +pub mod str; +#[cfg(not(no_string))] +pub mod string; +#[cfg(not(no_sync))] +#[cfg(target_has_atomic = "ptr")] +pub mod sync; +#[cfg(all(not(no_global_oom_handling), target_has_atomic = "ptr"))] +pub mod task; +#[cfg(test)] +mod tests; +pub mod vec; + +#[doc(hidden)] +#[unstable(feature = "liballoc_internals", issue = "none", reason = "implementation detail")] +pub mod __export { + pub use core::format_args; +} diff --git a/rust/alloc/raw_vec.rs b/rust/alloc/raw_vec.rs new file mode 100644 index 000000000000..daf5f2da7168 --- /dev/null +++ b/rust/alloc/raw_vec.rs @@ -0,0 +1,527 @@ +// SPDX-License-Identifier: Apache-2.0 OR MIT + +#![unstable(feature = "raw_vec_internals", reason = "unstable const warnings", issue = "none")] + +use core::alloc::LayoutError; +use core::cmp; +use core::intrinsics; +use core::mem::{self, ManuallyDrop, MaybeUninit}; +use core::ops::Drop; +use core::ptr::{self, NonNull, Unique}; +use core::slice; + +#[cfg(not(no_global_oom_handling))] +use crate::alloc::handle_alloc_error; +use crate::alloc::{Allocator, Global, Layout}; +use crate::boxed::Box; +use crate::collections::TryReserveError; +use crate::collections::TryReserveErrorKind::*; + +#[cfg(test)] +mod tests; + +#[cfg(not(no_global_oom_handling))] +enum AllocInit { + /// The contents of the new memory are uninitialized. + Uninitialized, + /// The new memory is guaranteed to be zeroed. + Zeroed, +} + +/// A low-level utility for more ergonomically allocating, reallocating, and deallocating +/// a buffer of memory on the heap without having to worry about all the corner cases +/// involved. This type is excellent for building your own data structures like Vec and VecDeque. +/// In particular: +/// +/// * Produces `Unique::dangling()` on zero-sized types. +/// * Produces `Unique::dangling()` on zero-length allocations. +/// * Avoids freeing `Unique::dangling()`. +/// * Catches all overflows in capacity computations (promotes them to "capacity overflow" panics). +/// * Guards against 32-bit systems allocating more than isize::MAX bytes. +/// * Guards against overflowing your length. +/// * Calls `handle_alloc_error` for fallible allocations. +/// * Contains a `ptr::Unique` and thus endows the user with all related benefits. +/// * Uses the excess returned from the allocator to use the largest available capacity. +/// +/// This type does not in anyway inspect the memory that it manages. When dropped it *will* +/// free its memory, but it *won't* try to drop its contents. It is up to the user of `RawVec` +/// to handle the actual things *stored* inside of a `RawVec`. +/// +/// Note that the excess of a zero-sized types is always infinite, so `capacity()` always returns +/// `usize::MAX`. This means that you need to be careful when round-tripping this type with a +/// `Box<[T]>`, since `capacity()` won't yield the length. +#[allow(missing_debug_implementations)] +pub(crate) struct RawVec<T, A: Allocator = Global> { + ptr: Unique<T>, + cap: usize, + alloc: A, +} + +impl<T> RawVec<T, Global> { + /// HACK(Centril): This exists because stable `const fn` can only call stable `const fn`, so + /// they cannot call `Self::new()`. + /// + /// If you change `RawVec<T>::new` or dependencies, please take care to not introduce anything + /// that would truly const-call something unstable. + pub const NEW: Self = Self::new(); + + /// Creates the biggest possible `RawVec` (on the system heap) + /// without allocating. If `T` has positive size, then this makes a + /// `RawVec` with capacity `0`. If `T` is zero-sized, then it makes a + /// `RawVec` with capacity `usize::MAX`. Useful for implementing + /// delayed allocation. + #[must_use] + pub const fn new() -> Self { + Self::new_in(Global) + } + + /// Creates a `RawVec` (on the system heap) with exactly the + /// capacity and alignment requirements for a `[T; capacity]`. This is + /// equivalent to calling `RawVec::new` when `capacity` is `0` or `T` is + /// zero-sized. Note that if `T` is zero-sized this means you will + /// *not* get a `RawVec` with the requested capacity. + /// + /// # Panics + /// + /// Panics if the requested capacity exceeds `isize::MAX` bytes. + /// + /// # Aborts + /// + /// Aborts on OOM. + #[cfg(not(any(no_global_oom_handling, test)))] + #[must_use] + #[inline] + pub fn with_capacity(capacity: usize) -> Self { + Self::with_capacity_in(capacity, Global) + } + + /// Like `with_capacity`, but guarantees the buffer is zeroed. + #[cfg(not(any(no_global_oom_handling, test)))] + #[must_use] + #[inline] + pub fn with_capacity_zeroed(capacity: usize) -> Self { + Self::with_capacity_zeroed_in(capacity, Global) + } +} + +impl<T, A: Allocator> RawVec<T, A> { + // Tiny Vecs are dumb. Skip to: + // - 8 if the element size is 1, because any heap allocators is likely + // to round up a request of less than 8 bytes to at least 8 bytes. + // - 4 if elements are moderate-sized (<= 1 KiB). + // - 1 otherwise, to avoid wasting too much space for very short Vecs. + pub(crate) const MIN_NON_ZERO_CAP: usize = if mem::size_of::<T>() == 1 { + 8 + } else if mem::size_of::<T>() <= 1024 { + 4 + } else { + 1 + }; + + /// Like `new`, but parameterized over the choice of allocator for + /// the returned `RawVec`. + pub const fn new_in(alloc: A) -> Self { + // `cap: 0` means "unallocated". zero-sized types are ignored. + Self { ptr: Unique::dangling(), cap: 0, alloc } + } + + /// Like `with_capacity`, but parameterized over the choice of + /// allocator for the returned `RawVec`. + #[cfg(not(no_global_oom_handling))] + #[inline] + pub fn with_capacity_in(capacity: usize, alloc: A) -> Self { + Self::allocate_in(capacity, AllocInit::Uninitialized, alloc) + } + + /// Like `with_capacity_zeroed`, but parameterized over the choice + /// of allocator for the returned `RawVec`. + #[cfg(not(no_global_oom_handling))] + #[inline] + pub fn with_capacity_zeroed_in(capacity: usize, alloc: A) -> Self { + Self::allocate_in(capacity, AllocInit::Zeroed, alloc) + } + + /// Converts the entire buffer into `Box<[MaybeUninit<T>]>` with the specified `len`. + /// + /// Note that this will correctly reconstitute any `cap` changes + /// that may have been performed. (See description of type for details.) + /// + /// # Safety + /// + /// * `len` must be greater than or equal to the most recently requested capacity, and + /// * `len` must be less than or equal to `self.capacity()`. + /// + /// Note, that the requested capacity and `self.capacity()` could differ, as + /// an allocator could overallocate and return a greater memory block than requested. + pub unsafe fn into_box(self, len: usize) -> Box<[MaybeUninit<T>], A> { + // Sanity-check one half of the safety requirement (we cannot check the other half). + debug_assert!( + len <= self.capacity(), + "`len` must be smaller than or equal to `self.capacity()`" + ); + + let me = ManuallyDrop::new(self); + unsafe { + let slice = slice::from_raw_parts_mut(me.ptr() as *mut MaybeUninit<T>, len); + Box::from_raw_in(slice, ptr::read(&me.alloc)) + } + } + + #[cfg(not(no_global_oom_handling))] + fn allocate_in(capacity: usize, init: AllocInit, alloc: A) -> Self { + // Don't allocate here because `Drop` will not deallocate when `capacity` is 0. + if mem::size_of::<T>() == 0 || capacity == 0 { + Self::new_in(alloc) + } else { + // We avoid `unwrap_or_else` here because it bloats the amount of + // LLVM IR generated. + let layout = match Layout::array::<T>(capacity) { + Ok(layout) => layout, + Err(_) => capacity_overflow(), + }; + match alloc_guard(layout.size()) { + Ok(_) => {} + Err(_) => capacity_overflow(), + } + let result = match init { + AllocInit::Uninitialized => alloc.allocate(layout), + AllocInit::Zeroed => alloc.allocate_zeroed(layout), + }; + let ptr = match result { + Ok(ptr) => ptr, + Err(_) => handle_alloc_error(layout), + }; + + // Allocators currently return a `NonNull<[u8]>` whose length + // matches the size requested. If that ever changes, the capacity + // here should change to `ptr.len() / mem::size_of::<T>()`. + Self { + ptr: unsafe { Unique::new_unchecked(ptr.cast().as_ptr()) }, + cap: capacity, + alloc, + } + } + } + + /// Reconstitutes a `RawVec` from a pointer, capacity, and allocator. + /// + /// # Safety + /// + /// The `ptr` must be allocated (via the given allocator `alloc`), and with the given + /// `capacity`. + /// The `capacity` cannot exceed `isize::MAX` for sized types. (only a concern on 32-bit + /// systems). ZST vectors may have a capacity up to `usize::MAX`. + /// If the `ptr` and `capacity` come from a `RawVec` created via `alloc`, then this is + /// guaranteed. + #[inline] + pub unsafe fn from_raw_parts_in(ptr: *mut T, capacity: usize, alloc: A) -> Self { + Self { ptr: unsafe { Unique::new_unchecked(ptr) }, cap: capacity, alloc } + } + + /// Gets a raw pointer to the start of the allocation. Note that this is + /// `Unique::dangling()` if `capacity == 0` or `T` is zero-sized. In the former case, you must + /// be careful. + #[inline] + pub fn ptr(&self) -> *mut T { + self.ptr.as_ptr() + } + + /// Gets the capacity of the allocation. + /// + /// This will always be `usize::MAX` if `T` is zero-sized. + #[inline(always)] + pub fn capacity(&self) -> usize { + if mem::size_of::<T>() == 0 { usize::MAX } else { self.cap } + } + + /// Returns a shared reference to the allocator backing this `RawVec`. + pub fn allocator(&self) -> &A { + &self.alloc + } + + fn current_memory(&self) -> Option<(NonNull<u8>, Layout)> { + if mem::size_of::<T>() == 0 || self.cap == 0 { + None + } else { + // We have an allocated chunk of memory, so we can bypass runtime + // checks to get our current layout. + unsafe { + let layout = Layout::array::<T>(self.cap).unwrap_unchecked(); + Some((self.ptr.cast().into(), layout)) + } + } + } + + /// Ensures that the buffer contains at least enough space to hold `len + + /// additional` elements. If it doesn't already have enough capacity, will + /// reallocate enough space plus comfortable slack space to get amortized + /// *O*(1) behavior. Will limit this behavior if it would needlessly cause + /// itself to panic. + /// + /// If `len` exceeds `self.capacity()`, this may fail to actually allocate + /// the requested space. This is not really unsafe, but the unsafe + /// code *you* write that relies on the behavior of this function may break. + /// + /// This is ideal for implementing a bulk-push operation like `extend`. + /// + /// # Panics + /// + /// Panics if the new capacity exceeds `isize::MAX` bytes. + /// + /// # Aborts + /// + /// Aborts on OOM. + #[cfg(not(no_global_oom_handling))] + #[inline] + pub fn reserve(&mut self, len: usize, additional: usize) { + // Callers expect this function to be very cheap when there is already sufficient capacity. + // Therefore, we move all the resizing and error-handling logic from grow_amortized and + // handle_reserve behind a call, while making sure that this function is likely to be + // inlined as just a comparison and a call if the comparison fails. + #[cold] + fn do_reserve_and_handle<T, A: Allocator>( + slf: &mut RawVec<T, A>, + len: usize, + additional: usize, + ) { + handle_reserve(slf.grow_amortized(len, additional)); + } + + if self.needs_to_grow(len, additional) { + do_reserve_and_handle(self, len, additional); + } + } + + /// A specialized version of `reserve()` used only by the hot and + /// oft-instantiated `Vec::push()`, which does its own capacity check. + #[cfg(not(no_global_oom_handling))] + #[inline(never)] + pub fn reserve_for_push(&mut self, len: usize) { + handle_reserve(self.grow_amortized(len, 1)); + } + + /// The same as `reserve`, but returns on errors instead of panicking or aborting. + pub fn try_reserve(&mut self, len: usize, additional: usize) -> Result<(), TryReserveError> { + if self.needs_to_grow(len, additional) { + self.grow_amortized(len, additional) + } else { + Ok(()) + } + } + + /// The same as `reserve_for_push`, but returns on errors instead of panicking or aborting. + #[inline(never)] + pub fn try_reserve_for_push(&mut self, len: usize) -> Result<(), TryReserveError> { + self.grow_amortized(len, 1) + } + + /// Ensures that the buffer contains at least enough space to hold `len + + /// additional` elements. If it doesn't already, will reallocate the + /// minimum possible amount of memory necessary. Generally this will be + /// exactly the amount of memory necessary, but in principle the allocator + /// is free to give back more than we asked for. + /// + /// If `len` exceeds `self.capacity()`, this may fail to actually allocate + /// the requested space. This is not really unsafe, but the unsafe code + /// *you* write that relies on the behavior of this function may break. + /// + /// # Panics + /// + /// Panics if the new capacity exceeds `isize::MAX` bytes. + /// + /// # Aborts + /// + /// Aborts on OOM. + #[cfg(not(no_global_oom_handling))] + pub fn reserve_exact(&mut self, len: usize, additional: usize) { + handle_reserve(self.try_reserve_exact(len, additional)); + } + + /// The same as `reserve_exact`, but returns on errors instead of panicking or aborting. + pub fn try_reserve_exact( + &mut self, + len: usize, + additional: usize, + ) -> Result<(), TryReserveError> { + if self.needs_to_grow(len, additional) { self.grow_exact(len, additional) } else { Ok(()) } + } + + /// Shrinks the buffer down to the specified capacity. If the given amount + /// is 0, actually completely deallocates. + /// + /// # Panics + /// + /// Panics if the given amount is *larger* than the current capacity. + /// + /// # Aborts + /// + /// Aborts on OOM. + #[cfg(not(no_global_oom_handling))] + pub fn shrink_to_fit(&mut self, cap: usize) { + handle_reserve(self.shrink(cap)); + } +} + +impl<T, A: Allocator> RawVec<T, A> { + /// Returns if the buffer needs to grow to fulfill the needed extra capacity. + /// Mainly used to make inlining reserve-calls possible without inlining `grow`. + fn needs_to_grow(&self, len: usize, additional: usize) -> bool { + additional > self.capacity().wrapping_sub(len) + } + + fn set_ptr_and_cap(&mut self, ptr: NonNull<[u8]>, cap: usize) { + // Allocators currently return a `NonNull<[u8]>` whose length matches + // the size requested. If that ever changes, the capacity here should + // change to `ptr.len() / mem::size_of::<T>()`. + self.ptr = unsafe { Unique::new_unchecked(ptr.cast().as_ptr()) }; + self.cap = cap; + } + + // This method is usually instantiated many times. So we want it to be as + // small as possible, to improve compile times. But we also want as much of + // its contents to be statically computable as possible, to make the + // generated code run faster. Therefore, this method is carefully written + // so that all of the code that depends on `T` is within it, while as much + // of the code that doesn't depend on `T` as possible is in functions that + // are non-generic over `T`. + fn grow_amortized(&mut self, len: usize, additional: usize) -> Result<(), TryReserveError> { + // This is ensured by the calling contexts. + debug_assert!(additional > 0); + + if mem::size_of::<T>() == 0 { + // Since we return a capacity of `usize::MAX` when `elem_size` is + // 0, getting to here necessarily means the `RawVec` is overfull. + return Err(CapacityOverflow.into()); + } + + // Nothing we can really do about these checks, sadly. + let required_cap = len.checked_add(additional).ok_or(CapacityOverflow)?; + + // This guarantees exponential growth. The doubling cannot overflow + // because `cap <= isize::MAX` and the type of `cap` is `usize`. + let cap = cmp::max(self.cap * 2, required_cap); + let cap = cmp::max(Self::MIN_NON_ZERO_CAP, cap); + + let new_layout = Layout::array::<T>(cap); + + // `finish_grow` is non-generic over `T`. + let ptr = finish_grow(new_layout, self.current_memory(), &mut self.alloc)?; + self.set_ptr_and_cap(ptr, cap); + Ok(()) + } + + // The constraints on this method are much the same as those on + // `grow_amortized`, but this method is usually instantiated less often so + // it's less critical. + fn grow_exact(&mut self, len: usize, additional: usize) -> Result<(), TryReserveError> { + if mem::size_of::<T>() == 0 { + // Since we return a capacity of `usize::MAX` when the type size is + // 0, getting to here necessarily means the `RawVec` is overfull. + return Err(CapacityOverflow.into()); + } + + let cap = len.checked_add(additional).ok_or(CapacityOverflow)?; + let new_layout = Layout::array::<T>(cap); + + // `finish_grow` is non-generic over `T`. + let ptr = finish_grow(new_layout, self.current_memory(), &mut self.alloc)?; + self.set_ptr_and_cap(ptr, cap); + Ok(()) + } + + #[allow(dead_code)] + fn shrink(&mut self, cap: usize) -> Result<(), TryReserveError> { + assert!(cap <= self.capacity(), "Tried to shrink to a larger capacity"); + + let (ptr, layout) = if let Some(mem) = self.current_memory() { mem } else { return Ok(()) }; + + let ptr = unsafe { + // `Layout::array` cannot overflow here because it would have + // overflowed earlier when capacity was larger. + let new_layout = Layout::array::<T>(cap).unwrap_unchecked(); + self.alloc + .shrink(ptr, layout, new_layout) + .map_err(|_| AllocError { layout: new_layout, non_exhaustive: () })? + }; + self.set_ptr_and_cap(ptr, cap); + Ok(()) + } +} + +// This function is outside `RawVec` to minimize compile times. See the comment +// above `RawVec::grow_amortized` for details. (The `A` parameter isn't +// significant, because the number of different `A` types seen in practice is +// much smaller than the number of `T` types.) +#[inline(never)] +fn finish_grow<A>( + new_layout: Result<Layout, LayoutError>, + current_memory: Option<(NonNull<u8>, Layout)>, + alloc: &mut A, +) -> Result<NonNull<[u8]>, TryReserveError> +where + A: Allocator, +{ + // Check for the error here to minimize the size of `RawVec::grow_*`. + let new_layout = new_layout.map_err(|_| CapacityOverflow)?; + + alloc_guard(new_layout.size())?; + + let memory = if let Some((ptr, old_layout)) = current_memory { + debug_assert_eq!(old_layout.align(), new_layout.align()); + unsafe { + // The allocator checks for alignment equality + intrinsics::assume(old_layout.align() == new_layout.align()); + alloc.grow(ptr, old_layout, new_layout) + } + } else { + alloc.allocate(new_layout) + }; + + memory.map_err(|_| AllocError { layout: new_layout, non_exhaustive: () }.into()) +} + +unsafe impl<#[may_dangle] T, A: Allocator> Drop for RawVec<T, A> { + /// Frees the memory owned by the `RawVec` *without* trying to drop its contents. + fn drop(&mut self) { + if let Some((ptr, layout)) = self.current_memory() { + unsafe { self.alloc.deallocate(ptr, layout) } + } + } +} + +// Central function for reserve error handling. +#[cfg(not(no_global_oom_handling))] +#[inline] +fn handle_reserve(result: Result<(), TryReserveError>) { + match result.map_err(|e| e.kind()) { + Err(CapacityOverflow) => capacity_overflow(), + Err(AllocError { layout, .. }) => handle_alloc_error(layout), + Ok(()) => { /* yay */ } + } +} + +// We need to guarantee the following: +// * We don't ever allocate `> isize::MAX` byte-size objects. +// * We don't overflow `usize::MAX` and actually allocate too little. +// +// On 64-bit we just need to check for overflow since trying to allocate +// `> isize::MAX` bytes will surely fail. On 32-bit and 16-bit we need to add +// an extra guard for this in case we're running on a platform which can use +// all 4GB in user-space, e.g., PAE or x32. + +#[inline] +fn alloc_guard(alloc_size: usize) -> Result<(), TryReserveError> { + if usize::BITS < 64 && alloc_size > isize::MAX as usize { + Err(CapacityOverflow.into()) + } else { + Ok(()) + } +} + +// One central function responsible for reporting capacity overflows. This'll +// ensure that the code generation related to these panics is minimal as there's +// only one location which panics rather than a bunch throughout the module. +#[cfg(not(no_global_oom_handling))] +fn capacity_overflow() -> ! { + panic!("capacity overflow"); +} diff --git a/rust/alloc/slice.rs b/rust/alloc/slice.rs new file mode 100644 index 000000000000..e444e97fa145 --- /dev/null +++ b/rust/alloc/slice.rs @@ -0,0 +1,1204 @@ +// SPDX-License-Identifier: Apache-2.0 OR MIT + +//! A dynamically-sized view into a contiguous sequence, `[T]`. +//! +//! *[See also the slice primitive type](slice).* +//! +//! Slices are a view into a block of memory represented as a pointer and a +//! length. +//! +//! ``` +//! // slicing a Vec +//! let vec = vec![1, 2, 3]; +//! let int_slice = &vec[..]; +//! // coercing an array to a slice +//! let str_slice: &[&str] = &["one", "two", "three"]; +//! ``` +//! +//! Slices are either mutable or shared. The shared slice type is `&[T]`, +//! while the mutable slice type is `&mut [T]`, where `T` represents the element +//! type. For example, you can mutate the block of memory that a mutable slice +//! points to: +//! +//! ``` +//! let x = &mut [1, 2, 3]; +//! x[1] = 7; +//! assert_eq!(x, &[1, 7, 3]); +//! ``` +//! +//! Here are some of the things this module contains: +//! +//! ## Structs +//! +//! There are several structs that are useful for slices, such as [`Iter`], which +//! represents iteration over a slice. +//! +//! ## Trait Implementations +//! +//! There are several implementations of common traits for slices. Some examples +//! include: +//! +//! * [`Clone`] +//! * [`Eq`], [`Ord`] - for slices whose element type are [`Eq`] or [`Ord`]. +//! * [`Hash`] - for slices whose element type is [`Hash`]. +//! +//! ## Iteration +//! +//! The slices implement `IntoIterator`. The iterator yields references to the +//! slice elements. +//! +//! ``` +//! let numbers = &[0, 1, 2]; +//! for n in numbers { +//! println!("{n} is a number!"); +//! } +//! ``` +//! +//! The mutable slice yields mutable references to the elements: +//! +//! ``` +//! let mut scores = [7, 8, 9]; +//! for score in &mut scores[..] { +//! *score += 1; +//! } +//! ``` +//! +//! This iterator yields mutable references to the slice's elements, so while +//! the element type of the slice is `i32`, the element type of the iterator is +//! `&mut i32`. +//! +//! * [`.iter`] and [`.iter_mut`] are the explicit methods to return the default +//! iterators. +//! * Further methods that return iterators are [`.split`], [`.splitn`], +//! [`.chunks`], [`.windows`] and more. +//! +//! [`Hash`]: core::hash::Hash +//! [`.iter`]: slice::iter +//! [`.iter_mut`]: slice::iter_mut +//! [`.split`]: slice::split +//! [`.splitn`]: slice::splitn +//! [`.chunks`]: slice::chunks +//! [`.windows`]: slice::windows +#![stable(feature = "rust1", since = "1.0.0")] +// Many of the usings in this module are only used in the test configuration. +// It's cleaner to just turn off the unused_imports warning than to fix them. +#![cfg_attr(test, allow(unused_imports, dead_code))] + +use core::borrow::{Borrow, BorrowMut}; +#[cfg(not(no_global_oom_handling))] +use core::cmp::Ordering::{self, Less}; +#[cfg(not(no_global_oom_handling))] +use core::mem; +#[cfg(not(no_global_oom_handling))] +use core::mem::size_of; +#[cfg(not(no_global_oom_handling))] +use core::ptr; + +use crate::alloc::Allocator; +#[cfg(not(no_global_oom_handling))] +use crate::alloc::Global; +#[cfg(not(no_global_oom_handling))] +use crate::borrow::ToOwned; +use crate::boxed::Box; +use crate::vec::Vec; + +#[unstable(feature = "slice_range", issue = "76393")] +pub use core::slice::range; +#[unstable(feature = "array_chunks", issue = "74985")] +pub use core::slice::ArrayChunks; +#[unstable(feature = "array_chunks", issue = "74985")] +pub use core::slice::ArrayChunksMut; +#[unstable(feature = "array_windows", issue = "75027")] +pub use core::slice::ArrayWindows; +#[stable(feature = "inherent_ascii_escape", since = "1.60.0")] +pub use core::slice::EscapeAscii; +#[stable(feature = "slice_get_slice", since = "1.28.0")] +pub use core::slice::SliceIndex; +#[stable(feature = "from_ref", since = "1.28.0")] +pub use core::slice::{from_mut, from_ref}; +#[stable(feature = "rust1", since = "1.0.0")] +pub use core::slice::{from_raw_parts, from_raw_parts_mut}; +#[stable(feature = "rust1", since = "1.0.0")] +pub use core::slice::{Chunks, Windows}; +#[stable(feature = "chunks_exact", since = "1.31.0")] +pub use core::slice::{ChunksExact, ChunksExactMut}; +#[stable(feature = "rust1", since = "1.0.0")] +pub use core::slice::{ChunksMut, Split, SplitMut}; +#[unstable(feature = "slice_group_by", issue = "80552")] +pub use core::slice::{GroupBy, GroupByMut}; +#[stable(feature = "rust1", since = "1.0.0")] +pub use core::slice::{Iter, IterMut}; +#[stable(feature = "rchunks", since = "1.31.0")] +pub use core::slice::{RChunks, RChunksExact, RChunksExactMut, RChunksMut}; +#[stable(feature = "slice_rsplit", since = "1.27.0")] +pub use core::slice::{RSplit, RSplitMut}; +#[stable(feature = "rust1", since = "1.0.0")] +pub use core::slice::{RSplitN, RSplitNMut, SplitN, SplitNMut}; +#[stable(feature = "split_inclusive", since = "1.51.0")] +pub use core::slice::{SplitInclusive, SplitInclusiveMut}; + +//////////////////////////////////////////////////////////////////////////////// +// Basic slice extension methods +//////////////////////////////////////////////////////////////////////////////// + +// HACK(japaric) needed for the implementation of `vec!` macro during testing +// N.B., see the `hack` module in this file for more details. +#[cfg(test)] +pub use hack::into_vec; + +// HACK(japaric) needed for the implementation of `Vec::clone` during testing +// N.B., see the `hack` module in this file for more details. +#[cfg(test)] +pub use hack::to_vec; + +// HACK(japaric): With cfg(test) `impl [T]` is not available, these three +// functions are actually methods that are in `impl [T]` but not in +// `core::slice::SliceExt` - we need to supply these functions for the +// `test_permutations` test +pub(crate) mod hack { + use core::alloc::Allocator; + + use crate::boxed::Box; + use crate::vec::Vec; + + // We shouldn't add inline attribute to this since this is used in + // `vec!` macro mostly and causes perf regression. See #71204 for + // discussion and perf results. + pub fn into_vec<T, A: Allocator>(b: Box<[T], A>) -> Vec<T, A> { + unsafe { + let len = b.len(); + let (b, alloc) = Box::into_raw_with_allocator(b); + Vec::from_raw_parts_in(b as *mut T, len, len, alloc) + } + } + + #[cfg(not(no_global_oom_handling))] + #[inline] + pub fn to_vec<T: ConvertVec, A: Allocator>(s: &[T], alloc: A) -> Vec<T, A> { + T::to_vec(s, alloc) + } + + #[cfg(not(no_global_oom_handling))] + pub trait ConvertVec { + fn to_vec<A: Allocator>(s: &[Self], alloc: A) -> Vec<Self, A> + where + Self: Sized; + } + + #[cfg(not(no_global_oom_handling))] + impl<T: Clone> ConvertVec for T { + #[inline] + default fn to_vec<A: Allocator>(s: &[Self], alloc: A) -> Vec<Self, A> { + struct DropGuard<'a, T, A: Allocator> { + vec: &'a mut Vec<T, A>, + num_init: usize, + } + impl<'a, T, A: Allocator> Drop for DropGuard<'a, T, A> { + #[inline] + fn drop(&mut self) { + // SAFETY: + // items were marked initialized in the loop below + unsafe { + self.vec.set_len(self.num_init); + } + } + } + let mut vec = Vec::with_capacity_in(s.len(), alloc); + let mut guard = DropGuard { vec: &mut vec, num_init: 0 }; + let slots = guard.vec.spare_capacity_mut(); + // .take(slots.len()) is necessary for LLVM to remove bounds checks + // and has better codegen than zip. + for (i, b) in s.iter().enumerate().take(slots.len()) { + guard.num_init = i; + slots[i].write(b.clone()); + } + core::mem::forget(guard); + // SAFETY: + // the vec was allocated and initialized above to at least this length. + unsafe { + vec.set_len(s.len()); + } + vec + } + } + + #[cfg(not(no_global_oom_handling))] + impl<T: Copy> ConvertVec for T { + #[inline] + fn to_vec<A: Allocator>(s: &[Self], alloc: A) -> Vec<Self, A> { + let mut v = Vec::with_capacity_in(s.len(), alloc); + // SAFETY: + // allocated above with the capacity of `s`, and initialize to `s.len()` in + // ptr::copy_to_non_overlapping below. + unsafe { + s.as_ptr().copy_to_nonoverlapping(v.as_mut_ptr(), s.len()); + v.set_len(s.len()); + } + v + } + } +} + +#[cfg(not(test))] +impl<T> [T] { + /// Sorts the slice. + /// + /// This sort is stable (i.e., does not reorder equal elements) and *O*(*n* \* log(*n*)) worst-case. + /// + /// When applicable, unstable sorting is preferred because it is generally faster than stable + /// sorting and it doesn't allocate auxiliary memory. + /// See [`sort_unstable`](slice::sort_unstable). + /// + /// # Current implementation + /// + /// The current algorithm is an adaptive, iterative merge sort inspired by + /// [timsort](https://en.wikipedia.org/wiki/Timsort). + /// It is designed to be very fast in cases where the slice is nearly sorted, or consists of + /// two or more sorted sequences concatenated one after another. + /// + /// Also, it allocates temporary storage half the size of `self`, but for short slices a + /// non-allocating insertion sort is used instead. + /// + /// # Examples + /// + /// ``` + /// let mut v = [-5, 4, 1, -3, 2]; + /// + /// v.sort(); + /// assert!(v == [-5, -3, 1, 2, 4]); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[rustc_allow_incoherent_impl] + #[stable(feature = "rust1", since = "1.0.0")] + #[inline] + pub fn sort(&mut self) + where + T: Ord, + { + merge_sort(self, |a, b| a.lt(b)); + } + + /// Sorts the slice with a comparator function. + /// + /// This sort is stable (i.e., does not reorder equal elements) and *O*(*n* \* log(*n*)) worst-case. + /// + /// The comparator function must define a total ordering for the elements in the slice. If + /// the ordering is not total, the order of the elements is unspecified. An order is a + /// total order if it is (for all `a`, `b` and `c`): + /// + /// * total and antisymmetric: exactly one of `a < b`, `a == b` or `a > b` is true, and + /// * transitive, `a < b` and `b < c` implies `a < c`. The same must hold for both `==` and `>`. + /// + /// For example, while [`f64`] doesn't implement [`Ord`] because `NaN != NaN`, we can use + /// `partial_cmp` as our sort function when we know the slice doesn't contain a `NaN`. + /// + /// ``` + /// let mut floats = [5f64, 4.0, 1.0, 3.0, 2.0]; + /// floats.sort_by(|a, b| a.partial_cmp(b).unwrap()); + /// assert_eq!(floats, [1.0, 2.0, 3.0, 4.0, 5.0]); + /// ``` + /// + /// When applicable, unstable sorting is preferred because it is generally faster than stable + /// sorting and it doesn't allocate auxiliary memory. + /// See [`sort_unstable_by`](slice::sort_unstable_by). + /// + /// # Current implementation + /// + /// The current algorithm is an adaptive, iterative merge sort inspired by + /// [timsort](https://en.wikipedia.org/wiki/Timsort). + /// It is designed to be very fast in cases where the slice is nearly sorted, or consists of + /// two or more sorted sequences concatenated one after another. + /// + /// Also, it allocates temporary storage half the size of `self`, but for short slices a + /// non-allocating insertion sort is used instead. + /// + /// # Examples + /// + /// ``` + /// let mut v = [5, 4, 1, 3, 2]; + /// v.sort_by(|a, b| a.cmp(b)); + /// assert!(v == [1, 2, 3, 4, 5]); + /// + /// // reverse sorting + /// v.sort_by(|a, b| b.cmp(a)); + /// assert!(v == [5, 4, 3, 2, 1]); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[rustc_allow_incoherent_impl] + #[stable(feature = "rust1", since = "1.0.0")] + #[inline] + pub fn sort_by<F>(&mut self, mut compare: F) + where + F: FnMut(&T, &T) -> Ordering, + { + merge_sort(self, |a, b| compare(a, b) == Less); + } + + /// Sorts the slice with a key extraction function. + /// + /// This sort is stable (i.e., does not reorder equal elements) and *O*(*m* \* *n* \* log(*n*)) + /// worst-case, where the key function is *O*(*m*). + /// + /// For expensive key functions (e.g. functions that are not simple property accesses or + /// basic operations), [`sort_by_cached_key`](slice::sort_by_cached_key) is likely to be + /// significantly faster, as it does not recompute element keys. + /// + /// When applicable, unstable sorting is preferred because it is generally faster than stable + /// sorting and it doesn't allocate auxiliary memory. + /// See [`sort_unstable_by_key`](slice::sort_unstable_by_key). + /// + /// # Current implementation + /// + /// The current algorithm is an adaptive, iterative merge sort inspired by + /// [timsort](https://en.wikipedia.org/wiki/Timsort). + /// It is designed to be very fast in cases where the slice is nearly sorted, or consists of + /// two or more sorted sequences concatenated one after another. + /// + /// Also, it allocates temporary storage half the size of `self`, but for short slices a + /// non-allocating insertion sort is used instead. + /// + /// # Examples + /// + /// ``` + /// let mut v = [-5i32, 4, 1, -3, 2]; + /// + /// v.sort_by_key(|k| k.abs()); + /// assert!(v == [1, 2, -3, 4, -5]); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[rustc_allow_incoherent_impl] + #[stable(feature = "slice_sort_by_key", since = "1.7.0")] + #[inline] + pub fn sort_by_key<K, F>(&mut self, mut f: F) + where + F: FnMut(&T) -> K, + K: Ord, + { + merge_sort(self, |a, b| f(a).lt(&f(b))); + } + + /// Sorts the slice with a key extraction function. + /// + /// During sorting, the key function is called at most once per element, by using + /// temporary storage to remember the results of key evaluation. + /// The order of calls to the key function is unspecified and may change in future versions + /// of the standard library. + /// + /// This sort is stable (i.e., does not reorder equal elements) and *O*(*m* \* *n* + *n* \* log(*n*)) + /// worst-case, where the key function is *O*(*m*). + /// + /// For simple key functions (e.g., functions that are property accesses or + /// basic operations), [`sort_by_key`](slice::sort_by_key) is likely to be + /// faster. + /// + /// # Current implementation + /// + /// The current algorithm is based on [pattern-defeating quicksort][pdqsort] by Orson Peters, + /// which combines the fast average case of randomized quicksort with the fast worst case of + /// heapsort, while achieving linear time on slices with certain patterns. It uses some + /// randomization to avoid degenerate cases, but with a fixed seed to always provide + /// deterministic behavior. + /// + /// In the worst case, the algorithm allocates temporary storage in a `Vec<(K, usize)>` the + /// length of the slice. + /// + /// # Examples + /// + /// ``` + /// let mut v = [-5i32, 4, 32, -3, 2]; + /// + /// v.sort_by_cached_key(|k| k.to_string()); + /// assert!(v == [-3, -5, 2, 32, 4]); + /// ``` + /// + /// [pdqsort]: https://github.com/orlp/pdqsort + #[cfg(not(no_global_oom_handling))] + #[rustc_allow_incoherent_impl] + #[stable(feature = "slice_sort_by_cached_key", since = "1.34.0")] + #[inline] + pub fn sort_by_cached_key<K, F>(&mut self, f: F) + where + F: FnMut(&T) -> K, + K: Ord, + { + // Helper macro for indexing our vector by the smallest possible type, to reduce allocation. + macro_rules! sort_by_key { + ($t:ty, $slice:ident, $f:ident) => {{ + let mut indices: Vec<_> = + $slice.iter().map($f).enumerate().map(|(i, k)| (k, i as $t)).collect(); + // The elements of `indices` are unique, as they are indexed, so any sort will be + // stable with respect to the original slice. We use `sort_unstable` here because + // it requires less memory allocation. + indices.sort_unstable(); + for i in 0..$slice.len() { + let mut index = indices[i].1; + while (index as usize) < i { + index = indices[index as usize].1; + } + indices[i].1 = index; + $slice.swap(i, index as usize); + } + }}; + } + + let sz_u8 = mem::size_of::<(K, u8)>(); + let sz_u16 = mem::size_of::<(K, u16)>(); + let sz_u32 = mem::size_of::<(K, u32)>(); + let sz_usize = mem::size_of::<(K, usize)>(); + + let len = self.len(); + if len < 2 { + return; + } + if sz_u8 < sz_u16 && len <= (u8::MAX as usize) { + return sort_by_key!(u8, self, f); + } + if sz_u16 < sz_u32 && len <= (u16::MAX as usize) { + return sort_by_key!(u16, self, f); + } + if sz_u32 < sz_usize && len <= (u32::MAX as usize) { + return sort_by_key!(u32, self, f); + } + sort_by_key!(usize, self, f) + } + + /// Copies `self` into a new `Vec`. + /// + /// # Examples + /// + /// ``` + /// let s = [10, 40, 30]; + /// let x = s.to_vec(); + /// // Here, `s` and `x` can be modified independently. + /// ``` + #[cfg(not(no_global_oom_handling))] + #[rustc_allow_incoherent_impl] + #[rustc_conversion_suggestion] + #[stable(feature = "rust1", since = "1.0.0")] + #[inline] + pub fn to_vec(&self) -> Vec<T> + where + T: Clone, + { + self.to_vec_in(Global) + } + + /// Copies `self` into a new `Vec` with an allocator. + /// + /// # Examples + /// + /// ``` + /// #![feature(allocator_api)] + /// + /// use std::alloc::System; + /// + /// let s = [10, 40, 30]; + /// let x = s.to_vec_in(System); + /// // Here, `s` and `x` can be modified independently. + /// ``` + #[cfg(not(no_global_oom_handling))] + #[rustc_allow_incoherent_impl] + #[inline] + #[unstable(feature = "allocator_api", issue = "32838")] + pub fn to_vec_in<A: Allocator>(&self, alloc: A) -> Vec<T, A> + where + T: Clone, + { + // N.B., see the `hack` module in this file for more details. + hack::to_vec(self, alloc) + } + + /// Converts `self` into a vector without clones or allocation. + /// + /// The resulting vector can be converted back into a box via + /// `Vec<T>`'s `into_boxed_slice` method. + /// + /// # Examples + /// + /// ``` + /// let s: Box<[i32]> = Box::new([10, 40, 30]); + /// let x = s.into_vec(); + /// // `s` cannot be used anymore because it has been converted into `x`. + /// + /// assert_eq!(x, vec![10, 40, 30]); + /// ``` + #[rustc_allow_incoherent_impl] + #[stable(feature = "rust1", since = "1.0.0")] + #[inline] + pub fn into_vec<A: Allocator>(self: Box<Self, A>) -> Vec<T, A> { + // N.B., see the `hack` module in this file for more details. + hack::into_vec(self) + } + + /// Creates a vector by repeating a slice `n` times. + /// + /// # Panics + /// + /// This function will panic if the capacity would overflow. + /// + /// # Examples + /// + /// Basic usage: + /// + /// ``` + /// assert_eq!([1, 2].repeat(3), vec![1, 2, 1, 2, 1, 2]); + /// ``` + /// + /// A panic upon overflow: + /// + /// ```should_panic + /// // this will panic at runtime + /// b"0123456789abcdef".repeat(usize::MAX); + /// ``` + #[rustc_allow_incoherent_impl] + #[cfg(not(no_global_oom_handling))] + #[stable(feature = "repeat_generic_slice", since = "1.40.0")] + pub fn repeat(&self, n: usize) -> Vec<T> + where + T: Copy, + { + if n == 0 { + return Vec::new(); + } + + // If `n` is larger than zero, it can be split as + // `n = 2^expn + rem (2^expn > rem, expn >= 0, rem >= 0)`. + // `2^expn` is the number represented by the leftmost '1' bit of `n`, + // and `rem` is the remaining part of `n`. + + // Using `Vec` to access `set_len()`. + let capacity = self.len().checked_mul(n).expect("capacity overflow"); + let mut buf = Vec::with_capacity(capacity); + + // `2^expn` repetition is done by doubling `buf` `expn`-times. + buf.extend(self); + { + let mut m = n >> 1; + // If `m > 0`, there are remaining bits up to the leftmost '1'. + while m > 0 { + // `buf.extend(buf)`: + unsafe { + ptr::copy_nonoverlapping( + buf.as_ptr(), + (buf.as_mut_ptr() as *mut T).add(buf.len()), + buf.len(), + ); + // `buf` has capacity of `self.len() * n`. + let buf_len = buf.len(); + buf.set_len(buf_len * 2); + } + + m >>= 1; + } + } + + // `rem` (`= n - 2^expn`) repetition is done by copying + // first `rem` repetitions from `buf` itself. + let rem_len = capacity - buf.len(); // `self.len() * rem` + if rem_len > 0 { + // `buf.extend(buf[0 .. rem_len])`: + unsafe { + // This is non-overlapping since `2^expn > rem`. + ptr::copy_nonoverlapping( + buf.as_ptr(), + (buf.as_mut_ptr() as *mut T).add(buf.len()), + rem_len, + ); + // `buf.len() + rem_len` equals to `buf.capacity()` (`= self.len() * n`). + buf.set_len(capacity); + } + } + buf + } + + /// Flattens a slice of `T` into a single value `Self::Output`. + /// + /// # Examples + /// + /// ``` + /// assert_eq!(["hello", "world"].concat(), "helloworld"); + /// assert_eq!([[1, 2], [3, 4]].concat(), [1, 2, 3, 4]); + /// ``` + #[rustc_allow_incoherent_impl] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn concat<Item: ?Sized>(&self) -> <Self as Concat<Item>>::Output + where + Self: Concat<Item>, + { + Concat::concat(self) + } + + /// Flattens a slice of `T` into a single value `Self::Output`, placing a + /// given separator between each. + /// + /// # Examples + /// + /// ``` + /// assert_eq!(["hello", "world"].join(" "), "hello world"); + /// assert_eq!([[1, 2], [3, 4]].join(&0), [1, 2, 0, 3, 4]); + /// assert_eq!([[1, 2], [3, 4]].join(&[0, 0][..]), [1, 2, 0, 0, 3, 4]); + /// ``` + #[rustc_allow_incoherent_impl] + #[stable(feature = "rename_connect_to_join", since = "1.3.0")] + pub fn join<Separator>(&self, sep: Separator) -> <Self as Join<Separator>>::Output + where + Self: Join<Separator>, + { + Join::join(self, sep) + } + + /// Flattens a slice of `T` into a single value `Self::Output`, placing a + /// given separator between each. + /// + /// # Examples + /// + /// ``` + /// # #![allow(deprecated)] + /// assert_eq!(["hello", "world"].connect(" "), "hello world"); + /// assert_eq!([[1, 2], [3, 4]].connect(&0), [1, 2, 0, 3, 4]); + /// ``` + #[rustc_allow_incoherent_impl] + #[stable(feature = "rust1", since = "1.0.0")] + #[deprecated(since = "1.3.0", note = "renamed to join")] + pub fn connect<Separator>(&self, sep: Separator) -> <Self as Join<Separator>>::Output + where + Self: Join<Separator>, + { + Join::join(self, sep) + } +} + +#[cfg(not(test))] +impl [u8] { + /// Returns a vector containing a copy of this slice where each byte + /// 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`]: slice::make_ascii_uppercase + #[cfg(not(no_global_oom_handling))] + #[rustc_allow_incoherent_impl] + #[must_use = "this returns the uppercase bytes as a new Vec, \ + without modifying the original"] + #[stable(feature = "ascii_methods_on_intrinsics", since = "1.23.0")] + #[inline] + pub fn to_ascii_uppercase(&self) -> Vec<u8> { + let mut me = self.to_vec(); + me.make_ascii_uppercase(); + me + } + + /// Returns a vector containing a copy of this slice where each byte + /// is mapped to its ASCII lower case equivalent. + /// + /// 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`]: slice::make_ascii_lowercase + #[cfg(not(no_global_oom_handling))] + #[rustc_allow_incoherent_impl] + #[must_use = "this returns the lowercase bytes as a new Vec, \ + without modifying the original"] + #[stable(feature = "ascii_methods_on_intrinsics", since = "1.23.0")] + #[inline] + pub fn to_ascii_lowercase(&self) -> Vec<u8> { + let mut me = self.to_vec(); + me.make_ascii_lowercase(); + me + } +} + +//////////////////////////////////////////////////////////////////////////////// +// Extension traits for slices over specific kinds of data +//////////////////////////////////////////////////////////////////////////////// + +/// Helper trait for [`[T]::concat`](slice::concat). +/// +/// Note: the `Item` type parameter is not used in this trait, +/// but it allows impls to be more generic. +/// Without it, we get this error: +/// +/// ```error +/// error[E0207]: the type parameter `T` is not constrained by the impl trait, self type, or predica +/// --> src/liballoc/slice.rs:608:6 +/// | +/// 608 | impl<T: Clone, V: Borrow<[T]>> Concat for [V] { +/// | ^ unconstrained type parameter +/// ``` +/// +/// This is because there could exist `V` types with multiple `Borrow<[_]>` impls, +/// such that multiple `T` types would apply: +/// +/// ``` +/// # #[allow(dead_code)] +/// pub struct Foo(Vec<u32>, Vec<String>); +/// +/// impl std::borrow::Borrow<[u32]> for Foo { +/// fn borrow(&self) -> &[u32] { &self.0 } +/// } +/// +/// impl std::borrow::Borrow<[String]> for Foo { +/// fn borrow(&self) -> &[String] { &self.1 } +/// } +/// ``` +#[unstable(feature = "slice_concat_trait", issue = "27747")] +pub trait Concat<Item: ?Sized> { + #[unstable(feature = "slice_concat_trait", issue = "27747")] + /// The resulting type after concatenation + type Output; + + /// Implementation of [`[T]::concat`](slice::concat) + #[unstable(feature = "slice_concat_trait", issue = "27747")] + fn concat(slice: &Self) -> Self::Output; +} + +/// Helper trait for [`[T]::join`](slice::join) +#[unstable(feature = "slice_concat_trait", issue = "27747")] +pub trait Join<Separator> { + #[unstable(feature = "slice_concat_trait", issue = "27747")] + /// The resulting type after concatenation + type Output; + + /// Implementation of [`[T]::join`](slice::join) + #[unstable(feature = "slice_concat_trait", issue = "27747")] + fn join(slice: &Self, sep: Separator) -> Self::Output; +} + +#[cfg(not(no_global_oom_handling))] +#[unstable(feature = "slice_concat_ext", issue = "27747")] +impl<T: Clone, V: Borrow<[T]>> Concat<T> for [V] { + type Output = Vec<T>; + + fn concat(slice: &Self) -> Vec<T> { + let size = slice.iter().map(|slice| slice.borrow().len()).sum(); + let mut result = Vec::with_capacity(size); + for v in slice { + result.extend_from_slice(v.borrow()) + } + result + } +} + +#[cfg(not(no_global_oom_handling))] +#[unstable(feature = "slice_concat_ext", issue = "27747")] +impl<T: Clone, V: Borrow<[T]>> Join<&T> for [V] { + type Output = Vec<T>; + + fn join(slice: &Self, sep: &T) -> Vec<T> { + let mut iter = slice.iter(); + let first = match iter.next() { + Some(first) => first, + None => return vec![], + }; + let size = slice.iter().map(|v| v.borrow().len()).sum::<usize>() + slice.len() - 1; + let mut result = Vec::with_capacity(size); + result.extend_from_slice(first.borrow()); + + for v in iter { + result.push(sep.clone()); + result.extend_from_slice(v.borrow()) + } + result + } +} + +#[cfg(not(no_global_oom_handling))] +#[unstable(feature = "slice_concat_ext", issue = "27747")] +impl<T: Clone, V: Borrow<[T]>> Join<&[T]> for [V] { + type Output = Vec<T>; + + fn join(slice: &Self, sep: &[T]) -> Vec<T> { + let mut iter = slice.iter(); + let first = match iter.next() { + Some(first) => first, + None => return vec![], + }; + let size = + slice.iter().map(|v| v.borrow().len()).sum::<usize>() + sep.len() * (slice.len() - 1); + let mut result = Vec::with_capacity(size); + result.extend_from_slice(first.borrow()); + + for v in iter { + result.extend_from_slice(sep); + result.extend_from_slice(v.borrow()) + } + result + } +} + +//////////////////////////////////////////////////////////////////////////////// +// Standard trait implementations for slices +//////////////////////////////////////////////////////////////////////////////// + +#[stable(feature = "rust1", since = "1.0.0")] +impl<T> Borrow<[T]> for Vec<T> { + fn borrow(&self) -> &[T] { + &self[..] + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<T> BorrowMut<[T]> for Vec<T> { + fn borrow_mut(&mut self) -> &mut [T] { + &mut self[..] + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +impl<T: Clone> ToOwned for [T] { + type Owned = Vec<T>; + #[cfg(not(test))] + fn to_owned(&self) -> Vec<T> { + self.to_vec() + } + + #[cfg(test)] + fn to_owned(&self) -> Vec<T> { + hack::to_vec(self, Global) + } + + fn clone_into(&self, target: &mut Vec<T>) { + // drop anything in target that will not be overwritten + target.truncate(self.len()); + + // target.len <= self.len due to the truncate above, so the + // slices here are always in-bounds. + let (init, tail) = self.split_at(target.len()); + + // reuse the contained values' allocations/resources. + target.clone_from_slice(init); + target.extend_from_slice(tail); + } +} + +//////////////////////////////////////////////////////////////////////////////// +// Sorting +//////////////////////////////////////////////////////////////////////////////// + +/// Inserts `v[0]` into pre-sorted sequence `v[1..]` so that whole `v[..]` becomes sorted. +/// +/// This is the integral subroutine of insertion sort. +#[cfg(not(no_global_oom_handling))] +fn insert_head<T, F>(v: &mut [T], is_less: &mut F) +where + F: FnMut(&T, &T) -> bool, +{ + if v.len() >= 2 && is_less(&v[1], &v[0]) { + unsafe { + // There are three ways to implement insertion here: + // + // 1. Swap adjacent elements until the first one gets to its final destination. + // However, this way we copy data around more than is necessary. If elements are big + // structures (costly to copy), this method will be slow. + // + // 2. Iterate until the right place for the first element is found. Then shift the + // elements succeeding it to make room for it and finally place it into the + // remaining hole. This is a good method. + // + // 3. Copy the first element into a temporary variable. Iterate until the right place + // for it is found. As we go along, copy every traversed element into the slot + // preceding it. Finally, copy data from the temporary variable into the remaining + // hole. This method is very good. Benchmarks demonstrated slightly better + // performance than with the 2nd method. + // + // All methods were benchmarked, and the 3rd showed best results. So we chose that one. + let tmp = mem::ManuallyDrop::new(ptr::read(&v[0])); + + // Intermediate state of the insertion process is always tracked by `hole`, which + // serves two purposes: + // 1. Protects integrity of `v` from panics in `is_less`. + // 2. Fills the remaining hole in `v` in the end. + // + // Panic safety: + // + // If `is_less` panics at any point during the process, `hole` will get dropped and + // fill the hole in `v` with `tmp`, thus ensuring that `v` still holds every object it + // initially held exactly once. + let mut hole = InsertionHole { src: &*tmp, dest: &mut v[1] }; + ptr::copy_nonoverlapping(&v[1], &mut v[0], 1); + + for i in 2..v.len() { + if !is_less(&v[i], &*tmp) { + break; + } + ptr::copy_nonoverlapping(&v[i], &mut v[i - 1], 1); + hole.dest = &mut v[i]; + } + // `hole` gets dropped and thus copies `tmp` into the remaining hole in `v`. + } + } + + // When dropped, copies from `src` into `dest`. + struct InsertionHole<T> { + src: *const T, + dest: *mut T, + } + + impl<T> Drop for InsertionHole<T> { + fn drop(&mut self) { + unsafe { + ptr::copy_nonoverlapping(self.src, self.dest, 1); + } + } + } +} + +/// Merges non-decreasing runs `v[..mid]` and `v[mid..]` using `buf` as temporary storage, and +/// stores the result into `v[..]`. +/// +/// # Safety +/// +/// The two slices must be non-empty and `mid` must be in bounds. Buffer `buf` must be long enough +/// to hold a copy of the shorter slice. Also, `T` must not be a zero-sized type. +#[cfg(not(no_global_oom_handling))] +unsafe fn merge<T, F>(v: &mut [T], mid: usize, buf: *mut T, is_less: &mut F) +where + F: FnMut(&T, &T) -> bool, +{ + let len = v.len(); + let v = v.as_mut_ptr(); + let (v_mid, v_end) = unsafe { (v.add(mid), v.add(len)) }; + + // The merge process first copies the shorter run into `buf`. Then it traces the newly copied + // run and the longer run forwards (or backwards), comparing their next unconsumed elements and + // copying the lesser (or greater) one into `v`. + // + // As soon as the shorter run is fully consumed, the process is done. If the longer run gets + // consumed first, then we must copy whatever is left of the shorter run into the remaining + // hole in `v`. + // + // Intermediate state of the process is always tracked by `hole`, which serves two purposes: + // 1. Protects integrity of `v` from panics in `is_less`. + // 2. Fills the remaining hole in `v` if the longer run gets consumed first. + // + // Panic safety: + // + // If `is_less` panics at any point during the process, `hole` will get dropped and fill the + // hole in `v` with the unconsumed range in `buf`, thus ensuring that `v` still holds every + // object it initially held exactly once. + let mut hole; + + if mid <= len - mid { + // The left run is shorter. + unsafe { + ptr::copy_nonoverlapping(v, buf, mid); + hole = MergeHole { start: buf, end: buf.add(mid), dest: v }; + } + + // Initially, these pointers point to the beginnings of their arrays. + let left = &mut hole.start; + let mut right = v_mid; + let out = &mut hole.dest; + + while *left < hole.end && right < v_end { + // Consume the lesser side. + // If equal, prefer the left run to maintain stability. + unsafe { + let to_copy = if is_less(&*right, &**left) { + get_and_increment(&mut right) + } else { + get_and_increment(left) + }; + ptr::copy_nonoverlapping(to_copy, get_and_increment(out), 1); + } + } + } else { + // The right run is shorter. + unsafe { + ptr::copy_nonoverlapping(v_mid, buf, len - mid); + hole = MergeHole { start: buf, end: buf.add(len - mid), dest: v_mid }; + } + + // Initially, these pointers point past the ends of their arrays. + let left = &mut hole.dest; + let right = &mut hole.end; + let mut out = v_end; + + while v < *left && buf < *right { + // Consume the greater side. + // If equal, prefer the right run to maintain stability. + unsafe { + let to_copy = if is_less(&*right.offset(-1), &*left.offset(-1)) { + decrement_and_get(left) + } else { + decrement_and_get(right) + }; + ptr::copy_nonoverlapping(to_copy, decrement_and_get(&mut out), 1); + } + } + } + // Finally, `hole` gets dropped. If the shorter run was not fully consumed, whatever remains of + // it will now be copied into the hole in `v`. + + unsafe fn get_and_increment<T>(ptr: &mut *mut T) -> *mut T { + let old = *ptr; + *ptr = unsafe { ptr.offset(1) }; + old + } + + unsafe fn decrement_and_get<T>(ptr: &mut *mut T) -> *mut T { + *ptr = unsafe { ptr.offset(-1) }; + *ptr + } + + // When dropped, copies the range `start..end` into `dest..`. + struct MergeHole<T> { + start: *mut T, + end: *mut T, + dest: *mut T, + } + + impl<T> Drop for MergeHole<T> { + fn drop(&mut self) { + // `T` is not a zero-sized type, and these are pointers into a slice's elements. + unsafe { + let len = self.end.sub_ptr(self.start); + ptr::copy_nonoverlapping(self.start, self.dest, len); + } + } + } +} + +/// This merge sort borrows some (but not all) ideas from TimSort, which is described in detail +/// [here](https://github.com/python/cpython/blob/main/Objects/listsort.txt). +/// +/// The algorithm identifies strictly descending and non-descending subsequences, which are called +/// natural runs. There is a stack of pending runs yet to be merged. Each newly found run is pushed +/// onto the stack, and then some pairs of adjacent runs are merged until these two invariants are +/// satisfied: +/// +/// 1. for every `i` in `1..runs.len()`: `runs[i - 1].len > runs[i].len` +/// 2. for every `i` in `2..runs.len()`: `runs[i - 2].len > runs[i - 1].len + runs[i].len` +/// +/// The invariants ensure that the total running time is *O*(*n* \* log(*n*)) worst-case. +#[cfg(not(no_global_oom_handling))] +fn merge_sort<T, F>(v: &mut [T], mut is_less: F) +where + F: FnMut(&T, &T) -> bool, +{ + // Slices of up to this length get sorted using insertion sort. + const MAX_INSERTION: usize = 20; + // Very short runs are extended using insertion sort to span at least this many elements. + const MIN_RUN: usize = 10; + + // Sorting has no meaningful behavior on zero-sized types. + if size_of::<T>() == 0 { + return; + } + + let len = v.len(); + + // Short arrays get sorted in-place via insertion sort to avoid allocations. + if len <= MAX_INSERTION { + if len >= 2 { + for i in (0..len - 1).rev() { + insert_head(&mut v[i..], &mut is_less); + } + } + return; + } + + // Allocate a buffer to use as scratch memory. We keep the length 0 so we can keep in it + // shallow copies of the contents of `v` without risking the dtors running on copies if + // `is_less` panics. When merging two sorted runs, this buffer holds a copy of the shorter run, + // which will always have length at most `len / 2`. + let mut buf = Vec::with_capacity(len / 2); + + // In order to identify natural runs in `v`, we traverse it backwards. That might seem like a + // strange decision, but consider the fact that merges more often go in the opposite direction + // (forwards). According to benchmarks, merging forwards is slightly faster than merging + // backwards. To conclude, identifying runs by traversing backwards improves performance. + let mut runs = vec![]; + let mut end = len; + while end > 0 { + // Find the next natural run, and reverse it if it's strictly descending. + let mut start = end - 1; + if start > 0 { + start -= 1; + unsafe { + if is_less(v.get_unchecked(start + 1), v.get_unchecked(start)) { + while start > 0 && is_less(v.get_unchecked(start), v.get_unchecked(start - 1)) { + start -= 1; + } + v[start..end].reverse(); + } else { + while start > 0 && !is_less(v.get_unchecked(start), v.get_unchecked(start - 1)) + { + start -= 1; + } + } + } + } + + // Insert some more elements into the run if it's too short. Insertion sort is faster than + // merge sort on short sequences, so this significantly improves performance. + while start > 0 && end - start < MIN_RUN { + start -= 1; + insert_head(&mut v[start..end], &mut is_less); + } + + // Push this run onto the stack. + runs.push(Run { start, len: end - start }); + end = start; + + // Merge some pairs of adjacent runs to satisfy the invariants. + while let Some(r) = collapse(&runs) { + let left = runs[r + 1]; + let right = runs[r]; + unsafe { + merge( + &mut v[left.start..right.start + right.len], + left.len, + buf.as_mut_ptr(), + &mut is_less, + ); + } + runs[r] = Run { start: left.start, len: left.len + right.len }; + runs.remove(r + 1); + } + } + + // Finally, exactly one run must remain in the stack. + debug_assert!(runs.len() == 1 && runs[0].start == 0 && runs[0].len == len); + + // Examines the stack of runs and identifies the next pair of runs to merge. More specifically, + // if `Some(r)` is returned, that means `runs[r]` and `runs[r + 1]` must be merged next. If the + // algorithm should continue building a new run instead, `None` is returned. + // + // TimSort is infamous for its buggy implementations, as described here: + // http://envisage-project.eu/timsort-specification-and-verification/ + // + // The gist of the story is: we must enforce the invariants on the top four runs on the stack. + // Enforcing them on just top three is not sufficient to ensure that the invariants will still + // hold for *all* runs in the stack. + // + // This function correctly checks invariants for the top four runs. Additionally, if the top + // run starts at index 0, it will always demand a merge operation until the stack is fully + // collapsed, in order to complete the sort. + #[inline] + fn collapse(runs: &[Run]) -> Option<usize> { + let n = runs.len(); + if n >= 2 + && (runs[n - 1].start == 0 + || runs[n - 2].len <= runs[n - 1].len + || (n >= 3 && runs[n - 3].len <= runs[n - 2].len + runs[n - 1].len) + || (n >= 4 && runs[n - 4].len <= runs[n - 3].len + runs[n - 2].len)) + { + if n >= 3 && runs[n - 3].len < runs[n - 1].len { Some(n - 3) } else { Some(n - 2) } + } else { + None + } + } + + #[derive(Clone, Copy)] + struct Run { + start: usize, + len: usize, + } +} diff --git a/rust/alloc/vec/drain.rs b/rust/alloc/vec/drain.rs new file mode 100644 index 000000000000..b6a5f98e4fcd --- /dev/null +++ b/rust/alloc/vec/drain.rs @@ -0,0 +1,186 @@ +// SPDX-License-Identifier: Apache-2.0 OR MIT + +use crate::alloc::{Allocator, Global}; +use core::fmt; +use core::iter::{FusedIterator, TrustedLen}; +use core::mem; +use core::ptr::{self, NonNull}; +use core::slice::{self}; + +use super::Vec; + +/// A draining iterator for `Vec<T>`. +/// +/// This `struct` is created by [`Vec::drain`]. +/// See its documentation for more. +/// +/// # Example +/// +/// ``` +/// let mut v = vec![0, 1, 2]; +/// let iter: std::vec::Drain<_> = v.drain(..); +/// ``` +#[stable(feature = "drain", since = "1.6.0")] +pub struct Drain< + 'a, + T: 'a, + #[unstable(feature = "allocator_api", issue = "32838")] A: Allocator + 'a = Global, +> { + /// Index of tail to preserve + pub(super) tail_start: usize, + /// Length of tail + pub(super) tail_len: usize, + /// Current remaining range to remove + pub(super) iter: slice::Iter<'a, T>, + pub(super) vec: NonNull<Vec<T, A>>, +} + +#[stable(feature = "collection_debug", since = "1.17.0")] +impl<T: fmt::Debug, A: Allocator> fmt::Debug for Drain<'_, T, A> { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + f.debug_tuple("Drain").field(&self.iter.as_slice()).finish() + } +} + +impl<'a, T, A: Allocator> Drain<'a, T, A> { + /// Returns the remaining items of this iterator as a slice. + /// + /// # Examples + /// + /// ``` + /// let mut vec = vec!['a', 'b', 'c']; + /// let mut drain = vec.drain(..); + /// assert_eq!(drain.as_slice(), &['a', 'b', 'c']); + /// let _ = drain.next().unwrap(); + /// assert_eq!(drain.as_slice(), &['b', 'c']); + /// ``` + #[must_use] + #[stable(feature = "vec_drain_as_slice", since = "1.46.0")] + pub fn as_slice(&self) -> &[T] { + self.iter.as_slice() + } + + /// Returns a reference to the underlying allocator. + #[unstable(feature = "allocator_api", issue = "32838")] + #[must_use] + #[inline] + pub fn allocator(&self) -> &A { + unsafe { self.vec.as_ref().allocator() } + } +} + +#[stable(feature = "vec_drain_as_slice", since = "1.46.0")] +impl<'a, T, A: Allocator> AsRef<[T]> for Drain<'a, T, A> { + fn as_ref(&self) -> &[T] { + self.as_slice() + } +} + +#[stable(feature = "drain", since = "1.6.0")] +unsafe impl<T: Sync, A: Sync + Allocator> Sync for Drain<'_, T, A> {} +#[stable(feature = "drain", since = "1.6.0")] +unsafe impl<T: Send, A: Send + Allocator> Send for Drain<'_, T, A> {} + +#[stable(feature = "drain", since = "1.6.0")] +impl<T, A: Allocator> Iterator for Drain<'_, T, A> { + type Item = T; + + #[inline] + fn next(&mut self) -> Option<T> { + self.iter.next().map(|elt| unsafe { ptr::read(elt as *const _) }) + } + + fn size_hint(&self) -> (usize, Option<usize>) { + self.iter.size_hint() + } +} + +#[stable(feature = "drain", since = "1.6.0")] +impl<T, A: Allocator> DoubleEndedIterator for Drain<'_, T, A> { + #[inline] + fn next_back(&mut self) -> Option<T> { + self.iter.next_back().map(|elt| unsafe { ptr::read(elt as *const _) }) + } +} + +#[stable(feature = "drain", since = "1.6.0")] +impl<T, A: Allocator> Drop for Drain<'_, T, A> { + fn drop(&mut self) { + /// Moves back the un-`Drain`ed elements to restore the original `Vec`. + struct DropGuard<'r, 'a, T, A: Allocator>(&'r mut Drain<'a, T, A>); + + impl<'r, 'a, T, A: Allocator> Drop for DropGuard<'r, 'a, T, A> { + fn drop(&mut self) { + if self.0.tail_len > 0 { + unsafe { + let source_vec = self.0.vec.as_mut(); + // memmove back untouched tail, update to new length + let start = source_vec.len(); + let tail = self.0.tail_start; + if tail != start { + let src = source_vec.as_ptr().add(tail); + let dst = source_vec.as_mut_ptr().add(start); + ptr::copy(src, dst, self.0.tail_len); + } + source_vec.set_len(start + self.0.tail_len); + } + } + } + } + + let iter = mem::replace(&mut self.iter, (&mut []).iter()); + let drop_len = iter.len(); + + let mut vec = self.vec; + + if mem::size_of::<T>() == 0 { + // ZSTs have no identity, so we don't need to move them around, we only need to drop the correct amount. + // this can be achieved by manipulating the Vec length instead of moving values out from `iter`. + unsafe { + let vec = vec.as_mut(); + let old_len = vec.len(); + vec.set_len(old_len + drop_len + self.tail_len); + vec.truncate(old_len + self.tail_len); + } + + return; + } + + // ensure elements are moved back into their appropriate places, even when drop_in_place panics + let _guard = DropGuard(self); + + if drop_len == 0 { + return; + } + + // as_slice() must only be called when iter.len() is > 0 because + // vec::Splice modifies vec::Drain fields and may grow the vec which would invalidate + // the iterator's internal pointers. Creating a reference to deallocated memory + // is invalid even when it is zero-length + let drop_ptr = iter.as_slice().as_ptr(); + + unsafe { + // drop_ptr comes from a slice::Iter which only gives us a &[T] but for drop_in_place + // a pointer with mutable provenance is necessary. Therefore we must reconstruct + // it from the original vec but also avoid creating a &mut to the front since that could + // invalidate raw pointers to it which some unsafe code might rely on. + let vec_ptr = vec.as_mut().as_mut_ptr(); + let drop_offset = drop_ptr.sub_ptr(vec_ptr); + let to_drop = ptr::slice_from_raw_parts_mut(vec_ptr.add(drop_offset), drop_len); + ptr::drop_in_place(to_drop); + } + } +} + +#[stable(feature = "drain", since = "1.6.0")] +impl<T, A: Allocator> ExactSizeIterator for Drain<'_, T, A> { + fn is_empty(&self) -> bool { + self.iter.is_empty() + } +} + +#[unstable(feature = "trusted_len", issue = "37572")] +unsafe impl<T, A: Allocator> TrustedLen for Drain<'_, T, A> {} + +#[stable(feature = "fused", since = "1.26.0")] +impl<T, A: Allocator> FusedIterator for Drain<'_, T, A> {} diff --git a/rust/alloc/vec/drain_filter.rs b/rust/alloc/vec/drain_filter.rs new file mode 100644 index 000000000000..b04fce041622 --- /dev/null +++ b/rust/alloc/vec/drain_filter.rs @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: Apache-2.0 OR MIT + +use crate::alloc::{Allocator, Global}; +use core::ptr::{self}; +use core::slice::{self}; + +use super::Vec; + +/// An iterator which uses a closure to determine if an element should be removed. +/// +/// This struct is created by [`Vec::drain_filter`]. +/// See its documentation for more. +/// +/// # Example +/// +/// ``` +/// #![feature(drain_filter)] +/// +/// let mut v = vec![0, 1, 2]; +/// let iter: std::vec::DrainFilter<_, _> = v.drain_filter(|x| *x % 2 == 0); +/// ``` +#[unstable(feature = "drain_filter", reason = "recently added", issue = "43244")] +#[derive(Debug)] +pub struct DrainFilter< + 'a, + T, + F, + #[unstable(feature = "allocator_api", issue = "32838")] A: Allocator = Global, +> where + F: FnMut(&mut T) -> bool, +{ + pub(super) vec: &'a mut Vec<T, A>, + /// The index of the item that will be inspected by the next call to `next`. + pub(super) idx: usize, + /// The number of items that have been drained (removed) thus far. + pub(super) del: usize, + /// The original length of `vec` prior to draining. + pub(super) old_len: usize, + /// The filter test predicate. + pub(super) pred: F, + /// A flag that indicates a panic has occurred in the filter test predicate. + /// This is used as a hint in the drop implementation to prevent consumption + /// of the remainder of the `DrainFilter`. Any unprocessed items will be + /// backshifted in the `vec`, but no further items will be dropped or + /// tested by the filter predicate. + pub(super) panic_flag: bool, +} + +impl<T, F, A: Allocator> DrainFilter<'_, T, F, A> +where + F: FnMut(&mut T) -> bool, +{ + /// Returns a reference to the underlying allocator. + #[unstable(feature = "allocator_api", issue = "32838")] + #[inline] + pub fn allocator(&self) -> &A { + self.vec.allocator() + } +} + +#[unstable(feature = "drain_filter", reason = "recently added", issue = "43244")] +impl<T, F, A: Allocator> Iterator for DrainFilter<'_, T, F, A> +where + F: FnMut(&mut T) -> bool, +{ + type Item = T; + + fn next(&mut self) -> Option<T> { + unsafe { + while self.idx < self.old_len { + let i = self.idx; + let v = slice::from_raw_parts_mut(self.vec.as_mut_ptr(), self.old_len); + self.panic_flag = true; + let drained = (self.pred)(&mut v[i]); + self.panic_flag = false; + // Update the index *after* the predicate is called. If the index + // is updated prior and the predicate panics, the element at this + // index would be leaked. + self.idx += 1; + if drained { + self.del += 1; + return Some(ptr::read(&v[i])); + } else if self.del > 0 { + let del = self.del; + let src: *const T = &v[i]; + let dst: *mut T = &mut v[i - del]; + ptr::copy_nonoverlapping(src, dst, 1); + } + } + None + } + } + + fn size_hint(&self) -> (usize, Option<usize>) { + (0, Some(self.old_len - self.idx)) + } +} + +#[unstable(feature = "drain_filter", reason = "recently added", issue = "43244")] +impl<T, F, A: Allocator> Drop for DrainFilter<'_, T, F, A> +where + F: FnMut(&mut T) -> bool, +{ + fn drop(&mut self) { + struct BackshiftOnDrop<'a, 'b, T, F, A: Allocator> + where + F: FnMut(&mut T) -> bool, + { + drain: &'b mut DrainFilter<'a, T, F, A>, + } + + impl<'a, 'b, T, F, A: Allocator> Drop for BackshiftOnDrop<'a, 'b, T, F, A> + where + F: FnMut(&mut T) -> bool, + { + fn drop(&mut self) { + unsafe { + if self.drain.idx < self.drain.old_len && self.drain.del > 0 { + // This is a pretty messed up state, and there isn't really an + // obviously right thing to do. We don't want to keep trying + // to execute `pred`, so we just backshift all the unprocessed + // elements and tell the vec that they still exist. The backshift + // is required to prevent a double-drop of the last successfully + // drained item prior to a panic in the predicate. + let ptr = self.drain.vec.as_mut_ptr(); + let src = ptr.add(self.drain.idx); + let dst = src.sub(self.drain.del); + let tail_len = self.drain.old_len - self.drain.idx; + src.copy_to(dst, tail_len); + } + self.drain.vec.set_len(self.drain.old_len - self.drain.del); + } + } + } + + let backshift = BackshiftOnDrop { drain: self }; + + // Attempt to consume any remaining elements if the filter predicate + // has not yet panicked. We'll backshift any remaining elements + // whether we've already panicked or if the consumption here panics. + if !backshift.drain.panic_flag { + backshift.drain.for_each(drop); + } + } +} diff --git a/rust/alloc/vec/into_iter.rs b/rust/alloc/vec/into_iter.rs new file mode 100644 index 000000000000..f7a50e76691e --- /dev/null +++ b/rust/alloc/vec/into_iter.rs @@ -0,0 +1,366 @@ +// SPDX-License-Identifier: Apache-2.0 OR MIT + +#[cfg(not(no_global_oom_handling))] +use super::AsVecIntoIter; +use crate::alloc::{Allocator, Global}; +use crate::raw_vec::RawVec; +use core::fmt; +use core::intrinsics::arith_offset; +use core::iter::{ + FusedIterator, InPlaceIterable, SourceIter, TrustedLen, TrustedRandomAccessNoCoerce, +}; +use core::marker::PhantomData; +use core::mem::{self, ManuallyDrop}; +#[cfg(not(no_global_oom_handling))] +use core::ops::Deref; +use core::ptr::{self, NonNull}; +use core::slice::{self}; + +/// An iterator that moves out of a vector. +/// +/// This `struct` is created by the `into_iter` method on [`Vec`](super::Vec) +/// (provided by the [`IntoIterator`] trait). +/// +/// # Example +/// +/// ``` +/// let v = vec![0, 1, 2]; +/// let iter: std::vec::IntoIter<_> = v.into_iter(); +/// ``` +#[stable(feature = "rust1", since = "1.0.0")] +#[rustc_insignificant_dtor] +pub struct IntoIter< + T, + #[unstable(feature = "allocator_api", issue = "32838")] A: Allocator = Global, +> { + pub(super) buf: NonNull<T>, + pub(super) phantom: PhantomData<T>, + pub(super) cap: usize, + // the drop impl reconstructs a RawVec from buf, cap and alloc + // to avoid dropping the allocator twice we need to wrap it into ManuallyDrop + pub(super) alloc: ManuallyDrop<A>, + pub(super) ptr: *const T, + pub(super) end: *const T, +} + +#[stable(feature = "vec_intoiter_debug", since = "1.13.0")] +impl<T: fmt::Debug, A: Allocator> fmt::Debug for IntoIter<T, A> { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + f.debug_tuple("IntoIter").field(&self.as_slice()).finish() + } +} + +impl<T, A: Allocator> IntoIter<T, A> { + /// Returns the remaining items of this iterator as a slice. + /// + /// # Examples + /// + /// ``` + /// let vec = vec!['a', 'b', 'c']; + /// let mut into_iter = vec.into_iter(); + /// assert_eq!(into_iter.as_slice(), &['a', 'b', 'c']); + /// let _ = into_iter.next().unwrap(); + /// assert_eq!(into_iter.as_slice(), &['b', 'c']); + /// ``` + #[stable(feature = "vec_into_iter_as_slice", since = "1.15.0")] + pub fn as_slice(&self) -> &[T] { + unsafe { slice::from_raw_parts(self.ptr, self.len()) } + } + + /// Returns the remaining items of this iterator as a mutable slice. + /// + /// # Examples + /// + /// ``` + /// let vec = vec!['a', 'b', 'c']; + /// let mut into_iter = vec.into_iter(); + /// assert_eq!(into_iter.as_slice(), &['a', 'b', 'c']); + /// into_iter.as_mut_slice()[2] = 'z'; + /// assert_eq!(into_iter.next().unwrap(), 'a'); + /// assert_eq!(into_iter.next().unwrap(), 'b'); + /// assert_eq!(into_iter.next().unwrap(), 'z'); + /// ``` + #[stable(feature = "vec_into_iter_as_slice", since = "1.15.0")] + pub fn as_mut_slice(&mut self) -> &mut [T] { + unsafe { &mut *self.as_raw_mut_slice() } + } + + /// Returns a reference to the underlying allocator. + #[unstable(feature = "allocator_api", issue = "32838")] + #[inline] + pub fn allocator(&self) -> &A { + &self.alloc + } + + fn as_raw_mut_slice(&mut self) -> *mut [T] { + ptr::slice_from_raw_parts_mut(self.ptr as *mut T, self.len()) + } + + /// Drops remaining elements and relinquishes the backing allocation. + /// + /// This is roughly equivalent to the following, but more efficient + /// + /// ``` + /// # let mut into_iter = Vec::<u8>::with_capacity(10).into_iter(); + /// (&mut into_iter).for_each(core::mem::drop); + /// unsafe { core::ptr::write(&mut into_iter, Vec::new().into_iter()); } + /// ``` + /// + /// This method is used by in-place iteration, refer to the vec::in_place_collect + /// documentation for an overview. + #[cfg(not(no_global_oom_handling))] + pub(super) fn forget_allocation_drop_remaining(&mut self) { + let remaining = self.as_raw_mut_slice(); + + // overwrite the individual fields instead of creating a new + // struct and then overwriting &mut self. + // this creates less assembly + self.cap = 0; + self.buf = unsafe { NonNull::new_unchecked(RawVec::NEW.ptr()) }; + self.ptr = self.buf.as_ptr(); + self.end = self.buf.as_ptr(); + + unsafe { + ptr::drop_in_place(remaining); + } + } + + /// Forgets to Drop the remaining elements while still allowing the backing allocation to be freed. + #[allow(dead_code)] + pub(crate) fn forget_remaining_elements(&mut self) { + self.ptr = self.end; + } +} + +#[stable(feature = "vec_intoiter_as_ref", since = "1.46.0")] +impl<T, A: Allocator> AsRef<[T]> for IntoIter<T, A> { + fn as_ref(&self) -> &[T] { + self.as_slice() + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +unsafe impl<T: Send, A: Allocator + Send> Send for IntoIter<T, A> {} +#[stable(feature = "rust1", since = "1.0.0")] +unsafe impl<T: Sync, A: Allocator + Sync> Sync for IntoIter<T, A> {} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<T, A: Allocator> Iterator for IntoIter<T, A> { + type Item = T; + + #[inline] + fn next(&mut self) -> Option<T> { + if self.ptr as *const _ == self.end { + None + } else if mem::size_of::<T>() == 0 { + // purposefully don't use 'ptr.offset' because for + // vectors with 0-size elements this would return the + // same pointer. + self.ptr = unsafe { arith_offset(self.ptr as *const i8, 1) as *mut T }; + + // Make up a value of this ZST. + Some(unsafe { mem::zeroed() }) + } else { + let old = self.ptr; + self.ptr = unsafe { self.ptr.offset(1) }; + + Some(unsafe { ptr::read(old) }) + } + } + + #[inline] + fn size_hint(&self) -> (usize, Option<usize>) { + let exact = if mem::size_of::<T>() == 0 { + self.end.addr().wrapping_sub(self.ptr.addr()) + } else { + unsafe { self.end.sub_ptr(self.ptr) } + }; + (exact, Some(exact)) + } + + #[inline] + fn advance_by(&mut self, n: usize) -> Result<(), usize> { + let step_size = self.len().min(n); + let to_drop = ptr::slice_from_raw_parts_mut(self.ptr as *mut T, step_size); + if mem::size_of::<T>() == 0 { + // SAFETY: due to unchecked casts of unsigned amounts to signed offsets the wraparound + // effectively results in unsigned pointers representing positions 0..usize::MAX, + // which is valid for ZSTs. + self.ptr = unsafe { arith_offset(self.ptr as *const i8, step_size as isize) as *mut T } + } else { + // SAFETY: the min() above ensures that step_size is in bounds + self.ptr = unsafe { self.ptr.add(step_size) }; + } + // SAFETY: the min() above ensures that step_size is in bounds + unsafe { + ptr::drop_in_place(to_drop); + } + if step_size < n { + return Err(step_size); + } + Ok(()) + } + + #[inline] + fn count(self) -> usize { + self.len() + } + + unsafe fn __iterator_get_unchecked(&mut self, i: usize) -> Self::Item + where + Self: TrustedRandomAccessNoCoerce, + { + // SAFETY: the caller must guarantee that `i` is in bounds of the + // `Vec<T>`, so `i` cannot overflow an `isize`, and the `self.ptr.add(i)` + // is guaranteed to pointer to an element of the `Vec<T>` and + // thus guaranteed to be valid to dereference. + // + // Also note the implementation of `Self: TrustedRandomAccess` requires + // that `T: Copy` so reading elements from the buffer doesn't invalidate + // them for `Drop`. + unsafe { + if mem::size_of::<T>() == 0 { mem::zeroed() } else { ptr::read(self.ptr.add(i)) } + } + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<T, A: Allocator> DoubleEndedIterator for IntoIter<T, A> { + #[inline] + fn next_back(&mut self) -> Option<T> { + if self.end == self.ptr { + None + } else if mem::size_of::<T>() == 0 { + // See above for why 'ptr.offset' isn't used + self.end = unsafe { arith_offset(self.end as *const i8, -1) as *mut T }; + + // Make up a value of this ZST. + Some(unsafe { mem::zeroed() }) + } else { + self.end = unsafe { self.end.offset(-1) }; + + Some(unsafe { ptr::read(self.end) }) + } + } + + #[inline] + fn advance_back_by(&mut self, n: usize) -> Result<(), usize> { + let step_size = self.len().min(n); + if mem::size_of::<T>() == 0 { + // SAFETY: same as for advance_by() + self.end = unsafe { + arith_offset(self.end as *const i8, step_size.wrapping_neg() as isize) as *mut T + } + } else { + // SAFETY: same as for advance_by() + self.end = unsafe { self.end.offset(step_size.wrapping_neg() as isize) }; + } + let to_drop = ptr::slice_from_raw_parts_mut(self.end as *mut T, step_size); + // SAFETY: same as for advance_by() + unsafe { + ptr::drop_in_place(to_drop); + } + if step_size < n { + return Err(step_size); + } + Ok(()) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<T, A: Allocator> ExactSizeIterator for IntoIter<T, A> { + fn is_empty(&self) -> bool { + self.ptr == self.end + } +} + +#[stable(feature = "fused", since = "1.26.0")] +impl<T, A: Allocator> FusedIterator for IntoIter<T, A> {} + +#[unstable(feature = "trusted_len", issue = "37572")] +unsafe impl<T, A: Allocator> TrustedLen for IntoIter<T, A> {} + +#[doc(hidden)] +#[unstable(issue = "none", feature = "std_internals")] +#[rustc_unsafe_specialization_marker] +pub trait NonDrop {} + +// T: Copy as approximation for !Drop since get_unchecked does not advance self.ptr +// and thus we can't implement drop-handling +#[unstable(issue = "none", feature = "std_internals")] +impl<T: Copy> NonDrop for T {} + +#[doc(hidden)] +#[unstable(issue = "none", feature = "std_internals")] +// TrustedRandomAccess (without NoCoerce) must not be implemented because +// subtypes/supertypes of `T` might not be `NonDrop` +unsafe impl<T, A: Allocator> TrustedRandomAccessNoCoerce for IntoIter<T, A> +where + T: NonDrop, +{ + const MAY_HAVE_SIDE_EFFECT: bool = false; +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "vec_into_iter_clone", since = "1.8.0")] +impl<T: Clone, A: Allocator + Clone> Clone for IntoIter<T, A> { + #[cfg(not(test))] + fn clone(&self) -> Self { + self.as_slice().to_vec_in(self.alloc.deref().clone()).into_iter() + } + #[cfg(test)] + fn clone(&self) -> Self { + crate::slice::to_vec(self.as_slice(), self.alloc.deref().clone()).into_iter() + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +unsafe impl<#[may_dangle] T, A: Allocator> Drop for IntoIter<T, A> { + fn drop(&mut self) { + struct DropGuard<'a, T, A: Allocator>(&'a mut IntoIter<T, A>); + + impl<T, A: Allocator> Drop for DropGuard<'_, T, A> { + fn drop(&mut self) { + unsafe { + // `IntoIter::alloc` is not used anymore after this and will be dropped by RawVec + let alloc = ManuallyDrop::take(&mut self.0.alloc); + // RawVec handles deallocation + let _ = RawVec::from_raw_parts_in(self.0.buf.as_ptr(), self.0.cap, alloc); + } + } + } + + let guard = DropGuard(self); + // destroy the remaining elements + unsafe { + ptr::drop_in_place(guard.0.as_raw_mut_slice()); + } + // now `guard` will be dropped and do the rest + } +} + +// In addition to the SAFETY invariants of the following three unsafe traits +// also refer to the vec::in_place_collect module documentation to get an overview +#[unstable(issue = "none", feature = "inplace_iteration")] +#[doc(hidden)] +unsafe impl<T, A: Allocator> InPlaceIterable for IntoIter<T, A> {} + +#[unstable(issue = "none", feature = "inplace_iteration")] +#[doc(hidden)] +unsafe impl<T, A: Allocator> SourceIter for IntoIter<T, A> { + type Source = Self; + + #[inline] + unsafe fn as_inner(&mut self) -> &mut Self::Source { + self + } +} + +#[cfg(not(no_global_oom_handling))] +unsafe impl<T> AsVecIntoIter for IntoIter<T> { + type Item = T; + + fn as_into_iter(&mut self) -> &mut IntoIter<Self::Item> { + self + } +} diff --git a/rust/alloc/vec/is_zero.rs b/rust/alloc/vec/is_zero.rs new file mode 100644 index 000000000000..377f3d172777 --- /dev/null +++ b/rust/alloc/vec/is_zero.rs @@ -0,0 +1,120 @@ +// SPDX-License-Identifier: Apache-2.0 OR MIT + +use crate::boxed::Box; + +#[rustc_specialization_trait] +pub(super) unsafe trait IsZero { + /// Whether this value's representation is all zeros + fn is_zero(&self) -> bool; +} + +macro_rules! impl_is_zero { + ($t:ty, $is_zero:expr) => { + unsafe impl IsZero for $t { + #[inline] + fn is_zero(&self) -> bool { + $is_zero(*self) + } + } + }; +} + +impl_is_zero!(i16, |x| x == 0); +impl_is_zero!(i32, |x| x == 0); +impl_is_zero!(i64, |x| x == 0); +impl_is_zero!(i128, |x| x == 0); +impl_is_zero!(isize, |x| x == 0); + +impl_is_zero!(u16, |x| x == 0); +impl_is_zero!(u32, |x| x == 0); +impl_is_zero!(u64, |x| x == 0); +impl_is_zero!(u128, |x| x == 0); +impl_is_zero!(usize, |x| x == 0); + +impl_is_zero!(bool, |x| x == false); +impl_is_zero!(char, |x| x == '\0'); + +impl_is_zero!(f32, |x: f32| x.to_bits() == 0); +impl_is_zero!(f64, |x: f64| x.to_bits() == 0); + +unsafe impl<T> IsZero for *const T { + #[inline] + fn is_zero(&self) -> bool { + (*self).is_null() + } +} + +unsafe impl<T> IsZero for *mut T { + #[inline] + fn is_zero(&self) -> bool { + (*self).is_null() + } +} + +unsafe impl<T: IsZero, const N: usize> IsZero for [T; N] { + #[inline] + fn is_zero(&self) -> bool { + // Because this is generated as a runtime check, it's not obvious that + // it's worth doing if the array is really long. The threshold here + // is largely arbitrary, but was picked because as of 2022-05-01 LLVM + // can const-fold the check in `vec![[0; 32]; n]` but not in + // `vec![[0; 64]; n]`: https://godbolt.org/z/WTzjzfs5b + // Feel free to tweak if you have better evidence. + + N <= 32 && self.iter().all(IsZero::is_zero) + } +} + +// `Option<&T>` and `Option<Box<T>>` are guaranteed to represent `None` as null. +// For fat pointers, the bytes that would be the pointer metadata in the `Some` +// variant are padding in the `None` variant, so ignoring them and +// zero-initializing instead is ok. +// `Option<&mut T>` never implements `Clone`, so there's no need for an impl of +// `SpecFromElem`. + +unsafe impl<T: ?Sized> IsZero for Option<&T> { + #[inline] + fn is_zero(&self) -> bool { + self.is_none() + } +} + +unsafe impl<T: ?Sized> IsZero for Option<Box<T>> { + #[inline] + fn is_zero(&self) -> bool { + self.is_none() + } +} + +// `Option<num::NonZeroU32>` and similar have a representation guarantee that +// they're the same size as the corresponding `u32` type, as well as a guarantee +// that transmuting between `NonZeroU32` and `Option<num::NonZeroU32>` works. +// While the documentation officially makes it UB to transmute from `None`, +// we're the standard library so we can make extra inferences, and we know that +// the only niche available to represent `None` is the one that's all zeros. + +macro_rules! impl_is_zero_option_of_nonzero { + ($($t:ident,)+) => {$( + unsafe impl IsZero for Option<core::num::$t> { + #[inline] + fn is_zero(&self) -> bool { + self.is_none() + } + } + )+}; +} + +impl_is_zero_option_of_nonzero!( + NonZeroU8, + NonZeroU16, + NonZeroU32, + NonZeroU64, + NonZeroU128, + NonZeroI8, + NonZeroI16, + NonZeroI32, + NonZeroI64, + NonZeroI128, + NonZeroUsize, + NonZeroIsize, +); diff --git a/rust/alloc/vec/mod.rs b/rust/alloc/vec/mod.rs new file mode 100644 index 000000000000..540787804cc2 --- /dev/null +++ b/rust/alloc/vec/mod.rs @@ -0,0 +1,3140 @@ +// SPDX-License-Identifier: Apache-2.0 OR MIT + +//! A contiguous growable array type with heap-allocated contents, written +//! `Vec<T>`. +//! +//! Vectors have *O*(1) indexing, amortized *O*(1) push (to the end) and +//! *O*(1) pop (from the end). +//! +//! Vectors ensure they never allocate more than `isize::MAX` bytes. +//! +//! # Examples +//! +//! You can explicitly create a [`Vec`] with [`Vec::new`]: +//! +//! ``` +//! let v: Vec<i32> = Vec::new(); +//! ``` +//! +//! ...or by using the [`vec!`] macro: +//! +//! ``` +//! let v: Vec<i32> = vec![]; +//! +//! let v = vec![1, 2, 3, 4, 5]; +//! +//! let v = vec![0; 10]; // ten zeroes +//! ``` +//! +//! You can [`push`] values onto the end of a vector (which will grow the vector +//! as needed): +//! +//! ``` +//! let mut v = vec![1, 2]; +//! +//! v.push(3); +//! ``` +//! +//! Popping values works in much the same way: +//! +//! ``` +//! let mut v = vec![1, 2]; +//! +//! let two = v.pop(); +//! ``` +//! +//! Vectors also support indexing (through the [`Index`] and [`IndexMut`] traits): +//! +//! ``` +//! let mut v = vec![1, 2, 3]; +//! let three = v[2]; +//! v[1] = v[1] + 5; +//! ``` +//! +//! [`push`]: Vec::push + +#![stable(feature = "rust1", since = "1.0.0")] + +#[cfg(not(no_global_oom_handling))] +use core::cmp; +use core::cmp::Ordering; +use core::convert::TryFrom; +use core::fmt; +use core::hash::{Hash, Hasher}; +use core::intrinsics::{arith_offset, assume}; +use core::iter; +#[cfg(not(no_global_oom_handling))] +use core::iter::FromIterator; +use core::marker::PhantomData; +use core::mem::{self, ManuallyDrop, MaybeUninit}; +use core::ops::{self, Index, IndexMut, Range, RangeBounds}; +use core::ptr::{self, NonNull}; +use core::slice::{self, SliceIndex}; + +use crate::alloc::{Allocator, Global}; +use crate::borrow::{Cow, ToOwned}; +use crate::boxed::Box; +use crate::collections::TryReserveError; +use crate::raw_vec::RawVec; + +#[unstable(feature = "drain_filter", reason = "recently added", issue = "43244")] +pub use self::drain_filter::DrainFilter; + +mod drain_filter; + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "vec_splice", since = "1.21.0")] +pub use self::splice::Splice; + +#[cfg(not(no_global_oom_handling))] +mod splice; + +#[stable(feature = "drain", since = "1.6.0")] +pub use self::drain::Drain; + +mod drain; + +#[cfg(not(no_global_oom_handling))] +mod cow; + +#[cfg(not(no_global_oom_handling))] +pub(crate) use self::in_place_collect::AsVecIntoIter; +#[stable(feature = "rust1", since = "1.0.0")] +pub use self::into_iter::IntoIter; + +mod into_iter; + +#[cfg(not(no_global_oom_handling))] +use self::is_zero::IsZero; + +mod is_zero; + +#[cfg(not(no_global_oom_handling))] +mod in_place_collect; + +mod partial_eq; + +#[cfg(not(no_global_oom_handling))] +use self::spec_from_elem::SpecFromElem; + +#[cfg(not(no_global_oom_handling))] +mod spec_from_elem; + +#[cfg(not(no_global_oom_handling))] +use self::set_len_on_drop::SetLenOnDrop; + +#[cfg(not(no_global_oom_handling))] +mod set_len_on_drop; + +#[cfg(not(no_global_oom_handling))] +use self::in_place_drop::InPlaceDrop; + +#[cfg(not(no_global_oom_handling))] +mod in_place_drop; + +#[cfg(not(no_global_oom_handling))] +use self::spec_from_iter_nested::SpecFromIterNested; + +#[cfg(not(no_global_oom_handling))] +mod spec_from_iter_nested; + +#[cfg(not(no_global_oom_handling))] +use self::spec_from_iter::SpecFromIter; + +#[cfg(not(no_global_oom_handling))] +mod spec_from_iter; + +#[cfg(not(no_global_oom_handling))] +use self::spec_extend::SpecExtend; + +#[cfg(not(no_global_oom_handling))] +mod spec_extend; + +/// A contiguous growable array type, written as `Vec<T>`, short for 'vector'. +/// +/// # Examples +/// +/// ``` +/// let mut vec = Vec::new(); +/// vec.push(1); +/// vec.push(2); +/// +/// assert_eq!(vec.len(), 2); +/// assert_eq!(vec[0], 1); +/// +/// assert_eq!(vec.pop(), Some(2)); +/// assert_eq!(vec.len(), 1); +/// +/// vec[0] = 7; +/// assert_eq!(vec[0], 7); +/// +/// vec.extend([1, 2, 3].iter().copied()); +/// +/// for x in &vec { +/// println!("{x}"); +/// } +/// assert_eq!(vec, [7, 1, 2, 3]); +/// ``` +/// +/// The [`vec!`] macro is provided for convenient initialization: +/// +/// ``` +/// let mut vec1 = vec![1, 2, 3]; +/// vec1.push(4); +/// let vec2 = Vec::from([1, 2, 3, 4]); +/// assert_eq!(vec1, vec2); +/// ``` +/// +/// It can also initialize each element of a `Vec<T>` with a given value. +/// This may be more efficient than performing allocation and initialization +/// in separate steps, especially when initializing a vector of zeros: +/// +/// ``` +/// let vec = vec![0; 5]; +/// assert_eq!(vec, [0, 0, 0, 0, 0]); +/// +/// // The following is equivalent, but potentially slower: +/// let mut vec = Vec::with_capacity(5); +/// vec.resize(5, 0); +/// assert_eq!(vec, [0, 0, 0, 0, 0]); +/// ``` +/// +/// For more information, see +/// [Capacity and Reallocation](#capacity-and-reallocation). +/// +/// Use a `Vec<T>` as an efficient stack: +/// +/// ``` +/// let mut stack = Vec::new(); +/// +/// stack.push(1); +/// stack.push(2); +/// stack.push(3); +/// +/// while let Some(top) = stack.pop() { +/// // Prints 3, 2, 1 +/// println!("{top}"); +/// } +/// ``` +/// +/// # Indexing +/// +/// The `Vec` type allows to access values by index, because it implements the +/// [`Index`] trait. An example will be more explicit: +/// +/// ``` +/// let v = vec![0, 2, 4, 6]; +/// println!("{}", v[1]); // it will display '2' +/// ``` +/// +/// However be careful: if you try to access an index which isn't in the `Vec`, +/// your software will panic! You cannot do this: +/// +/// ```should_panic +/// let v = vec![0, 2, 4, 6]; +/// println!("{}", v[6]); // it will panic! +/// ``` +/// +/// Use [`get`] and [`get_mut`] if you want to check whether the index is in +/// the `Vec`. +/// +/// # Slicing +/// +/// A `Vec` can be mutable. On the other hand, slices are read-only objects. +/// To get a [slice][prim@slice], use [`&`]. Example: +/// +/// ``` +/// fn read_slice(slice: &[usize]) { +/// // ... +/// } +/// +/// let v = vec![0, 1]; +/// read_slice(&v); +/// +/// // ... and that's all! +/// // you can also do it like this: +/// let u: &[usize] = &v; +/// // or like this: +/// let u: &[_] = &v; +/// ``` +/// +/// In Rust, it's more common to pass slices as arguments rather than vectors +/// when you just want to provide read access. The same goes for [`String`] and +/// [`&str`]. +/// +/// # Capacity and reallocation +/// +/// The capacity of a vector is the amount of space allocated for any future +/// elements that will be added onto the vector. This is not to be confused with +/// the *length* of a vector, which specifies the number of actual elements +/// within the vector. If a vector's length exceeds its capacity, its capacity +/// will automatically be increased, but its elements will have to be +/// reallocated. +/// +/// For example, a vector with capacity 10 and length 0 would be an empty vector +/// with space for 10 more elements. Pushing 10 or fewer elements onto the +/// vector will not change its capacity or cause reallocation to occur. However, +/// if the vector's length is increased to 11, it will have to reallocate, which +/// can be slow. For this reason, it is recommended to use [`Vec::with_capacity`] +/// whenever possible to specify how big the vector is expected to get. +/// +/// # Guarantees +/// +/// Due to its incredibly fundamental nature, `Vec` makes a lot of guarantees +/// about its design. This ensures that it's as low-overhead as possible in +/// the general case, and can be correctly manipulated in primitive ways +/// by unsafe code. Note that these guarantees refer to an unqualified `Vec<T>`. +/// If additional type parameters are added (e.g., to support custom allocators), +/// overriding their defaults may change the behavior. +/// +/// Most fundamentally, `Vec` is and always will be a (pointer, capacity, length) +/// triplet. No more, no less. The order of these fields is completely +/// unspecified, and you should use the appropriate methods to modify these. +/// The pointer will never be null, so this type is null-pointer-optimized. +/// +/// However, the pointer might not actually point to allocated memory. In particular, +/// if you construct a `Vec` with capacity 0 via [`Vec::new`], [`vec![]`][`vec!`], +/// [`Vec::with_capacity(0)`][`Vec::with_capacity`], or by calling [`shrink_to_fit`] +/// on an empty Vec, it will not allocate memory. Similarly, if you store zero-sized +/// types inside a `Vec`, it will not allocate space for them. *Note that in this case +/// the `Vec` might not report a [`capacity`] of 0*. `Vec` will allocate if and only +/// if <code>[mem::size_of::\<T>]\() * [capacity]\() > 0</code>. In general, `Vec`'s allocation +/// details are very subtle --- if you intend to allocate memory using a `Vec` +/// and use it for something else (either to pass to unsafe code, or to build your +/// own memory-backed collection), be sure to deallocate this memory by using +/// `from_raw_parts` to recover the `Vec` and then dropping it. +/// +/// If a `Vec` *has* allocated memory, then the memory it points to is on the heap +/// (as defined by the allocator Rust is configured to use by default), and its +/// pointer points to [`len`] initialized, contiguous elements in order (what +/// you would see if you coerced it to a slice), followed by <code>[capacity] - [len]</code> +/// logically uninitialized, contiguous elements. +/// +/// A vector containing the elements `'a'` and `'b'` with capacity 4 can be +/// visualized as below. The top part is the `Vec` struct, it contains a +/// pointer to the head of the allocation in the heap, length and capacity. +/// The bottom part is the allocation on the heap, a contiguous memory block. +/// +/// ```text +/// ptr len capacity +/// +--------+--------+--------+ +/// | 0x0123 | 2 | 4 | +/// +--------+--------+--------+ +/// | +/// v +/// Heap +--------+--------+--------+--------+ +/// | 'a' | 'b' | uninit | uninit | +/// +--------+--------+--------+--------+ +/// ``` +/// +/// - **uninit** represents memory that is not initialized, see [`MaybeUninit`]. +/// - Note: the ABI is not stable and `Vec` makes no guarantees about its memory +/// layout (including the order of fields). +/// +/// `Vec` will never perform a "small optimization" where elements are actually +/// stored on the stack for two reasons: +/// +/// * It would make it more difficult for unsafe code to correctly manipulate +/// a `Vec`. The contents of a `Vec` wouldn't have a stable address if it were +/// only moved, and it would be more difficult to determine if a `Vec` had +/// actually allocated memory. +/// +/// * It would penalize the general case, incurring an additional branch +/// on every access. +/// +/// `Vec` will never automatically shrink itself, even if completely empty. This +/// ensures no unnecessary allocations or deallocations occur. Emptying a `Vec` +/// and then filling it back up to the same [`len`] should incur no calls to +/// the allocator. If you wish to free up unused memory, use +/// [`shrink_to_fit`] or [`shrink_to`]. +/// +/// [`push`] and [`insert`] will never (re)allocate if the reported capacity is +/// sufficient. [`push`] and [`insert`] *will* (re)allocate if +/// <code>[len] == [capacity]</code>. That is, the reported capacity is completely +/// accurate, and can be relied on. It can even be used to manually free the memory +/// allocated by a `Vec` if desired. Bulk insertion methods *may* reallocate, even +/// when not necessary. +/// +/// `Vec` does not guarantee any particular growth strategy when reallocating +/// when full, nor when [`reserve`] is called. The current strategy is basic +/// and it may prove desirable to use a non-constant growth factor. Whatever +/// strategy is used will of course guarantee *O*(1) amortized [`push`]. +/// +/// `vec![x; n]`, `vec![a, b, c, d]`, and +/// [`Vec::with_capacity(n)`][`Vec::with_capacity`], will all produce a `Vec` +/// with exactly the requested capacity. If <code>[len] == [capacity]</code>, +/// (as is the case for the [`vec!`] macro), then a `Vec<T>` can be converted to +/// and from a [`Box<[T]>`][owned slice] without reallocating or moving the elements. +/// +/// `Vec` will not specifically overwrite any data that is removed from it, +/// but also won't specifically preserve it. Its uninitialized memory is +/// scratch space that it may use however it wants. It will generally just do +/// whatever is most efficient or otherwise easy to implement. Do not rely on +/// removed data to be erased for security purposes. Even if you drop a `Vec`, its +/// buffer may simply be reused by another allocation. Even if you zero a `Vec`'s memory +/// first, that might not actually happen because the optimizer does not consider +/// this a side-effect that must be preserved. There is one case which we will +/// not break, however: using `unsafe` code to write to the excess capacity, +/// and then increasing the length to match, is always valid. +/// +/// Currently, `Vec` does not guarantee the order in which elements are dropped. +/// The order has changed in the past and may change again. +/// +/// [`get`]: ../../std/vec/struct.Vec.html#method.get +/// [`get_mut`]: ../../std/vec/struct.Vec.html#method.get_mut +/// [`String`]: crate::string::String +/// [`&str`]: type@str +/// [`shrink_to_fit`]: Vec::shrink_to_fit +/// [`shrink_to`]: Vec::shrink_to +/// [capacity]: Vec::capacity +/// [`capacity`]: Vec::capacity +/// [mem::size_of::\<T>]: core::mem::size_of +/// [len]: Vec::len +/// [`len`]: Vec::len +/// [`push`]: Vec::push +/// [`insert`]: Vec::insert +/// [`reserve`]: Vec::reserve +/// [`MaybeUninit`]: core::mem::MaybeUninit +/// [owned slice]: Box +#[stable(feature = "rust1", since = "1.0.0")] +#[cfg_attr(not(test), rustc_diagnostic_item = "Vec")] +#[rustc_insignificant_dtor] +pub struct Vec<T, #[unstable(feature = "allocator_api", issue = "32838")] A: Allocator = Global> { + buf: RawVec<T, A>, + len: usize, +} + +//////////////////////////////////////////////////////////////////////////////// +// Inherent methods +//////////////////////////////////////////////////////////////////////////////// + +impl<T> Vec<T> { + /// Constructs a new, empty `Vec<T>`. + /// + /// The vector will not allocate until elements are pushed onto it. + /// + /// # Examples + /// + /// ``` + /// # #![allow(unused_mut)] + /// let mut vec: Vec<i32> = Vec::new(); + /// ``` + #[inline] + #[rustc_const_stable(feature = "const_vec_new", since = "1.39.0")] + #[stable(feature = "rust1", since = "1.0.0")] + #[must_use] + pub const fn new() -> Self { + Vec { buf: RawVec::NEW, len: 0 } + } + + /// Constructs a new, empty `Vec<T>` with the specified capacity. + /// + /// The vector will be able to hold exactly `capacity` elements without + /// reallocating. If `capacity` is 0, the vector will not allocate. + /// + /// It is important to note that although the returned vector has the + /// *capacity* specified, the vector will have a zero *length*. For an + /// explanation of the difference between length and capacity, see + /// *[Capacity and reallocation]*. + /// + /// [Capacity and reallocation]: #capacity-and-reallocation + /// + /// # Panics + /// + /// Panics if the new capacity exceeds `isize::MAX` bytes. + /// + /// # Examples + /// + /// ``` + /// let mut vec = Vec::with_capacity(10); + /// + /// // The vector contains no items, even though it has capacity for more + /// assert_eq!(vec.len(), 0); + /// assert_eq!(vec.capacity(), 10); + /// + /// // These are all done without reallocating... + /// for i in 0..10 { + /// vec.push(i); + /// } + /// assert_eq!(vec.len(), 10); + /// assert_eq!(vec.capacity(), 10); + /// + /// // ...but this may make the vector reallocate + /// vec.push(11); + /// assert_eq!(vec.len(), 11); + /// assert!(vec.capacity() >= 11); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[inline] + #[stable(feature = "rust1", since = "1.0.0")] + #[must_use] + pub fn with_capacity(capacity: usize) -> Self { + Self::with_capacity_in(capacity, Global) + } + + /// Creates a `Vec<T>` directly from the raw components of another vector. + /// + /// # Safety + /// + /// This is highly unsafe, due to the number of invariants that aren't + /// checked: + /// + /// * `ptr` needs to have been previously allocated via [`String`]/`Vec<T>` + /// (at least, it's highly likely to be incorrect if it wasn't). + /// * `T` needs to have the same alignment as what `ptr` was allocated with. + /// (`T` having a less strict alignment is not sufficient, the alignment really + /// needs to be equal to satisfy the [`dealloc`] requirement that memory must be + /// allocated and deallocated with the same layout.) + /// * The size of `T` times the `capacity` (ie. the allocated size in bytes) needs + /// to be the same size as the pointer was allocated with. (Because similar to + /// alignment, [`dealloc`] must be called with the same layout `size`.) + /// * `length` needs to be less than or equal to `capacity`. + /// + /// Violating these may cause problems like corrupting the allocator's + /// internal data structures. For example it is normally **not** safe + /// to build a `Vec<u8>` from a pointer to a C `char` array with length + /// `size_t`, doing so is only safe if the array was initially allocated by + /// a `Vec` or `String`. + /// It's also not safe to build one from a `Vec<u16>` and its length, because + /// the allocator cares about the alignment, and these two types have different + /// alignments. The buffer was allocated with alignment 2 (for `u16`), but after + /// turning it into a `Vec<u8>` it'll be deallocated with alignment 1. To avoid + /// these issues, it is often preferable to do casting/transmuting using + /// [`slice::from_raw_parts`] instead. + /// + /// The ownership of `ptr` is effectively transferred to the + /// `Vec<T>` which may then deallocate, reallocate or change the + /// contents of memory pointed to by the pointer at will. Ensure + /// that nothing else uses the pointer after calling this + /// function. + /// + /// [`String`]: crate::string::String + /// [`dealloc`]: crate::alloc::GlobalAlloc::dealloc + /// + /// # Examples + /// + /// ``` + /// use std::ptr; + /// use std::mem; + /// + /// let v = vec![1, 2, 3]; + /// + // FIXME Update this when vec_into_raw_parts is stabilized + /// // Prevent running `v`'s destructor so we are in complete control + /// // of the allocation. + /// let mut v = mem::ManuallyDrop::new(v); + /// + /// // Pull out the various important pieces of information about `v` + /// let p = v.as_mut_ptr(); + /// let len = v.len(); + /// let cap = v.capacity(); + /// + /// unsafe { + /// // Overwrite memory with 4, 5, 6 + /// for i in 0..len as isize { + /// ptr::write(p.offset(i), 4 + i); + /// } + /// + /// // Put everything back together into a Vec + /// let rebuilt = Vec::from_raw_parts(p, len, cap); + /// assert_eq!(rebuilt, [4, 5, 6]); + /// } + /// ``` + #[inline] + #[stable(feature = "rust1", since = "1.0.0")] + pub unsafe fn from_raw_parts(ptr: *mut T, length: usize, capacity: usize) -> Self { + unsafe { Self::from_raw_parts_in(ptr, length, capacity, Global) } + } +} + +impl<T, A: Allocator> Vec<T, A> { + /// Constructs a new, empty `Vec<T, A>`. + /// + /// The vector will not allocate until elements are pushed onto it. + /// + /// # Examples + /// + /// ``` + /// #![feature(allocator_api)] + /// + /// use std::alloc::System; + /// + /// # #[allow(unused_mut)] + /// let mut vec: Vec<i32, _> = Vec::new_in(System); + /// ``` + #[inline] + #[unstable(feature = "allocator_api", issue = "32838")] + pub const fn new_in(alloc: A) -> Self { + Vec { buf: RawVec::new_in(alloc), len: 0 } + } + + /// Constructs a new, empty `Vec<T, A>` with the specified capacity with the provided + /// allocator. + /// + /// The vector will be able to hold exactly `capacity` elements without + /// reallocating. If `capacity` is 0, the vector will not allocate. + /// + /// It is important to note that although the returned vector has the + /// *capacity* specified, the vector will have a zero *length*. For an + /// explanation of the difference between length and capacity, see + /// *[Capacity and reallocation]*. + /// + /// [Capacity and reallocation]: #capacity-and-reallocation + /// + /// # Panics + /// + /// Panics if the new capacity exceeds `isize::MAX` bytes. + /// + /// # Examples + /// + /// ``` + /// #![feature(allocator_api)] + /// + /// use std::alloc::System; + /// + /// let mut vec = Vec::with_capacity_in(10, System); + /// + /// // The vector contains no items, even though it has capacity for more + /// assert_eq!(vec.len(), 0); + /// assert_eq!(vec.capacity(), 10); + /// + /// // These are all done without reallocating... + /// for i in 0..10 { + /// vec.push(i); + /// } + /// assert_eq!(vec.len(), 10); + /// assert_eq!(vec.capacity(), 10); + /// + /// // ...but this may make the vector reallocate + /// vec.push(11); + /// assert_eq!(vec.len(), 11); + /// assert!(vec.capacity() >= 11); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[inline] + #[unstable(feature = "allocator_api", issue = "32838")] + pub fn with_capacity_in(capacity: usize, alloc: A) -> Self { + Vec { buf: RawVec::with_capacity_in(capacity, alloc), len: 0 } + } + + /// Creates a `Vec<T, A>` directly from the raw components of another vector. + /// + /// # Safety + /// + /// This is highly unsafe, due to the number of invariants that aren't + /// checked: + /// + /// * `ptr` needs to have been previously allocated via [`String`]/`Vec<T>` + /// (at least, it's highly likely to be incorrect if it wasn't). + /// * `T` needs to have the same size and alignment as what `ptr` was allocated with. + /// (`T` having a less strict alignment is not sufficient, the alignment really + /// needs to be equal to satisfy the [`dealloc`] requirement that memory must be + /// allocated and deallocated with the same layout.) + /// * `length` needs to be less than or equal to `capacity`. + /// * `capacity` needs to be the capacity that the pointer was allocated with. + /// + /// Violating these may cause problems like corrupting the allocator's + /// internal data structures. For example it is **not** safe + /// to build a `Vec<u8>` from a pointer to a C `char` array with length `size_t`. + /// It's also not safe to build one from a `Vec<u16>` and its length, because + /// the allocator cares about the alignment, and these two types have different + /// alignments. The buffer was allocated with alignment 2 (for `u16`), but after + /// turning it into a `Vec<u8>` it'll be deallocated with alignment 1. + /// + /// The ownership of `ptr` is effectively transferred to the + /// `Vec<T>` which may then deallocate, reallocate or change the + /// contents of memory pointed to by the pointer at will. Ensure + /// that nothing else uses the pointer after calling this + /// function. + /// + /// [`String`]: crate::string::String + /// [`dealloc`]: crate::alloc::GlobalAlloc::dealloc + /// + /// # Examples + /// + /// ``` + /// #![feature(allocator_api)] + /// + /// use std::alloc::System; + /// + /// use std::ptr; + /// use std::mem; + /// + /// let mut v = Vec::with_capacity_in(3, System); + /// v.push(1); + /// v.push(2); + /// v.push(3); + /// + // FIXME Update this when vec_into_raw_parts is stabilized + /// // Prevent running `v`'s destructor so we are in complete control + /// // of the allocation. + /// let mut v = mem::ManuallyDrop::new(v); + /// + /// // Pull out the various important pieces of information about `v` + /// let p = v.as_mut_ptr(); + /// let len = v.len(); + /// let cap = v.capacity(); + /// let alloc = v.allocator(); + /// + /// unsafe { + /// // Overwrite memory with 4, 5, 6 + /// for i in 0..len as isize { + /// ptr::write(p.offset(i), 4 + i); + /// } + /// + /// // Put everything back together into a Vec + /// let rebuilt = Vec::from_raw_parts_in(p, len, cap, alloc.clone()); + /// assert_eq!(rebuilt, [4, 5, 6]); + /// } + /// ``` + #[inline] + #[unstable(feature = "allocator_api", issue = "32838")] + pub unsafe fn from_raw_parts_in(ptr: *mut T, length: usize, capacity: usize, alloc: A) -> Self { + unsafe { Vec { buf: RawVec::from_raw_parts_in(ptr, capacity, alloc), len: length } } + } + + /// Decomposes a `Vec<T>` into its raw components. + /// + /// Returns the raw pointer to the underlying data, the length of + /// the vector (in elements), and the allocated capacity of the + /// data (in elements). These are the same arguments in the same + /// order as the arguments to [`from_raw_parts`]. + /// + /// After calling this function, the caller is responsible for the + /// memory previously managed by the `Vec`. The only way to do + /// this is to convert the raw pointer, length, and capacity back + /// into a `Vec` with the [`from_raw_parts`] function, allowing + /// the destructor to perform the cleanup. + /// + /// [`from_raw_parts`]: Vec::from_raw_parts + /// + /// # Examples + /// + /// ``` + /// #![feature(vec_into_raw_parts)] + /// let v: Vec<i32> = vec![-1, 0, 1]; + /// + /// let (ptr, len, cap) = v.into_raw_parts(); + /// + /// let rebuilt = unsafe { + /// // We can now make changes to the components, such as + /// // transmuting the raw pointer to a compatible type. + /// let ptr = ptr as *mut u32; + /// + /// Vec::from_raw_parts(ptr, len, cap) + /// }; + /// assert_eq!(rebuilt, [4294967295, 0, 1]); + /// ``` + #[unstable(feature = "vec_into_raw_parts", reason = "new API", issue = "65816")] + pub fn into_raw_parts(self) -> (*mut T, usize, usize) { + let mut me = ManuallyDrop::new(self); + (me.as_mut_ptr(), me.len(), me.capacity()) + } + + /// Decomposes a `Vec<T>` into its raw components. + /// + /// Returns the raw pointer to the underlying data, the length of the vector (in elements), + /// the allocated capacity of the data (in elements), and the allocator. These are the same + /// arguments in the same order as the arguments to [`from_raw_parts_in`]. + /// + /// After calling this function, the caller is responsible for the + /// memory previously managed by the `Vec`. The only way to do + /// this is to convert the raw pointer, length, and capacity back + /// into a `Vec` with the [`from_raw_parts_in`] function, allowing + /// the destructor to perform the cleanup. + /// + /// [`from_raw_parts_in`]: Vec::from_raw_parts_in + /// + /// # Examples + /// + /// ``` + /// #![feature(allocator_api, vec_into_raw_parts)] + /// + /// use std::alloc::System; + /// + /// let mut v: Vec<i32, System> = Vec::new_in(System); + /// v.push(-1); + /// v.push(0); + /// v.push(1); + /// + /// let (ptr, len, cap, alloc) = v.into_raw_parts_with_alloc(); + /// + /// let rebuilt = unsafe { + /// // We can now make changes to the components, such as + /// // transmuting the raw pointer to a compatible type. + /// let ptr = ptr as *mut u32; + /// + /// Vec::from_raw_parts_in(ptr, len, cap, alloc) + /// }; + /// assert_eq!(rebuilt, [4294967295, 0, 1]); + /// ``` + #[unstable(feature = "allocator_api", issue = "32838")] + // #[unstable(feature = "vec_into_raw_parts", reason = "new API", issue = "65816")] + pub fn into_raw_parts_with_alloc(self) -> (*mut T, usize, usize, A) { + let mut me = ManuallyDrop::new(self); + let len = me.len(); + let capacity = me.capacity(); + let ptr = me.as_mut_ptr(); + let alloc = unsafe { ptr::read(me.allocator()) }; + (ptr, len, capacity, alloc) + } + + /// Returns the number of elements the vector can hold without + /// reallocating. + /// + /// # Examples + /// + /// ``` + /// let vec: Vec<i32> = Vec::with_capacity(10); + /// assert_eq!(vec.capacity(), 10); + /// ``` + #[inline] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn capacity(&self) -> usize { + self.buf.capacity() + } + + /// Reserves capacity for at least `additional` more elements to be inserted + /// in the given `Vec<T>`. The collection may reserve more space to avoid + /// frequent reallocations. After calling `reserve`, capacity will be + /// greater than or equal to `self.len() + additional`. Does nothing if + /// capacity is already sufficient. + /// + /// # Panics + /// + /// Panics if the new capacity exceeds `isize::MAX` bytes. + /// + /// # Examples + /// + /// ``` + /// let mut vec = vec![1]; + /// vec.reserve(10); + /// assert!(vec.capacity() >= 11); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn reserve(&mut self, additional: usize) { + self.buf.reserve(self.len, additional); + } + + /// Reserves the minimum capacity for exactly `additional` more elements to + /// be inserted in the given `Vec<T>`. After calling `reserve_exact`, + /// capacity will be greater than or equal to `self.len() + additional`. + /// Does nothing if the capacity is already sufficient. + /// + /// Note that the allocator may give the collection more space than it + /// requests. Therefore, capacity can not be relied upon to be precisely + /// minimal. Prefer [`reserve`] if future insertions are expected. + /// + /// [`reserve`]: Vec::reserve + /// + /// # Panics + /// + /// Panics if the new capacity exceeds `isize::MAX` bytes. + /// + /// # Examples + /// + /// ``` + /// let mut vec = vec![1]; + /// vec.reserve_exact(10); + /// assert!(vec.capacity() >= 11); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn reserve_exact(&mut self, additional: usize) { + self.buf.reserve_exact(self.len, additional); + } + + /// Tries to reserve capacity for at least `additional` more elements to be inserted + /// in the given `Vec<T>`. The collection may reserve more space to avoid + /// frequent reallocations. After calling `try_reserve`, capacity will be + /// greater than or equal to `self.len() + additional`. Does nothing if + /// capacity is already sufficient. + /// + /// # Errors + /// + /// If the capacity overflows, or the allocator reports a failure, then an error + /// is returned. + /// + /// # Examples + /// + /// ``` + /// use std::collections::TryReserveError; + /// + /// fn process_data(data: &[u32]) -> Result<Vec<u32>, TryReserveError> { + /// let mut output = Vec::new(); + /// + /// // Pre-reserve the memory, exiting if we can't + /// output.try_reserve(data.len())?; + /// + /// // Now we know this can't OOM in the middle of our complex work + /// output.extend(data.iter().map(|&val| { + /// val * 2 + 5 // very complicated + /// })); + /// + /// Ok(output) + /// } + /// # process_data(&[1, 2, 3]).expect("why is the test harness OOMing on 12 bytes?"); + /// ``` + #[stable(feature = "try_reserve", since = "1.57.0")] + pub fn try_reserve(&mut self, additional: usize) -> Result<(), TryReserveError> { + self.buf.try_reserve(self.len, additional) + } + + /// Tries to reserve the minimum capacity for exactly `additional` + /// elements to be inserted in the given `Vec<T>`. After calling + /// `try_reserve_exact`, capacity will be greater than or equal to + /// `self.len() + additional` if it returns `Ok(())`. + /// Does nothing if the capacity is already sufficient. + /// + /// Note that the allocator may give the collection more space than it + /// requests. Therefore, capacity can not be relied upon to be precisely + /// minimal. Prefer [`try_reserve`] if future insertions are expected. + /// + /// [`try_reserve`]: Vec::try_reserve + /// + /// # Errors + /// + /// If the capacity overflows, or the allocator reports a failure, then an error + /// is returned. + /// + /// # Examples + /// + /// ``` + /// use std::collections::TryReserveError; + /// + /// fn process_data(data: &[u32]) -> Result<Vec<u32>, TryReserveError> { + /// let mut output = Vec::new(); + /// + /// // Pre-reserve the memory, exiting if we can't + /// output.try_reserve_exact(data.len())?; + /// + /// // Now we know this can't OOM in the middle of our complex work + /// output.extend(data.iter().map(|&val| { + /// val * 2 + 5 // very complicated + /// })); + /// + /// Ok(output) + /// } + /// # process_data(&[1, 2, 3]).expect("why is the test harness OOMing on 12 bytes?"); + /// ``` + #[stable(feature = "try_reserve", since = "1.57.0")] + pub fn try_reserve_exact(&mut self, additional: usize) -> Result<(), TryReserveError> { + self.buf.try_reserve_exact(self.len, additional) + } + + /// Shrinks the capacity of the vector as much as possible. + /// + /// It will drop down as close as possible to the length but the allocator + /// may still inform the vector that there is space for a few more elements. + /// + /// # Examples + /// + /// ``` + /// let mut vec = Vec::with_capacity(10); + /// vec.extend([1, 2, 3]); + /// assert_eq!(vec.capacity(), 10); + /// vec.shrink_to_fit(); + /// assert!(vec.capacity() >= 3); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn shrink_to_fit(&mut self) { + // The capacity is never less than the length, and there's nothing to do when + // they are equal, so we can avoid the panic case in `RawVec::shrink_to_fit` + // by only calling it with a greater capacity. + if self.capacity() > self.len { + self.buf.shrink_to_fit(self.len); + } + } + + /// Shrinks the capacity of the vector with a lower bound. + /// + /// The capacity will remain at least as large as both the length + /// and the supplied value. + /// + /// If the current capacity is less than the lower limit, this is a no-op. + /// + /// # Examples + /// + /// ``` + /// let mut vec = Vec::with_capacity(10); + /// vec.extend([1, 2, 3]); + /// assert_eq!(vec.capacity(), 10); + /// vec.shrink_to(4); + /// assert!(vec.capacity() >= 4); + /// vec.shrink_to(0); + /// assert!(vec.capacity() >= 3); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[stable(feature = "shrink_to", since = "1.56.0")] + pub fn shrink_to(&mut self, min_capacity: usize) { + if self.capacity() > min_capacity { + self.buf.shrink_to_fit(cmp::max(self.len, min_capacity)); + } + } + + /// Converts the vector into [`Box<[T]>`][owned slice]. + /// + /// Note that this will drop any excess capacity. + /// + /// [owned slice]: Box + /// + /// # Examples + /// + /// ``` + /// let v = vec![1, 2, 3]; + /// + /// let slice = v.into_boxed_slice(); + /// ``` + /// + /// Any excess capacity is removed: + /// + /// ``` + /// let mut vec = Vec::with_capacity(10); + /// vec.extend([1, 2, 3]); + /// + /// assert_eq!(vec.capacity(), 10); + /// let slice = vec.into_boxed_slice(); + /// assert_eq!(slice.into_vec().capacity(), 3); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn into_boxed_slice(mut self) -> Box<[T], A> { + unsafe { + self.shrink_to_fit(); + let me = ManuallyDrop::new(self); + let buf = ptr::read(&me.buf); + let len = me.len(); + buf.into_box(len).assume_init() + } + } + + /// Shortens the vector, keeping the first `len` elements and dropping + /// the rest. + /// + /// If `len` is greater than the vector's current length, this has no + /// effect. + /// + /// The [`drain`] method can emulate `truncate`, but causes the excess + /// elements to be returned instead of dropped. + /// + /// Note that this method has no effect on the allocated capacity + /// of the vector. + /// + /// # Examples + /// + /// Truncating a five element vector to two elements: + /// + /// ``` + /// let mut vec = vec![1, 2, 3, 4, 5]; + /// vec.truncate(2); + /// assert_eq!(vec, [1, 2]); + /// ``` + /// + /// No truncation occurs when `len` is greater than the vector's current + /// length: + /// + /// ``` + /// let mut vec = vec![1, 2, 3]; + /// vec.truncate(8); + /// assert_eq!(vec, [1, 2, 3]); + /// ``` + /// + /// Truncating when `len == 0` is equivalent to calling the [`clear`] + /// method. + /// + /// ``` + /// let mut vec = vec![1, 2, 3]; + /// vec.truncate(0); + /// assert_eq!(vec, []); + /// ``` + /// + /// [`clear`]: Vec::clear + /// [`drain`]: Vec::drain + #[stable(feature = "rust1", since = "1.0.0")] + pub fn truncate(&mut self, len: usize) { + // This is safe because: + // + // * the slice passed to `drop_in_place` is valid; the `len > self.len` + // case avoids creating an invalid slice, and + // * the `len` of the vector is shrunk before calling `drop_in_place`, + // such that no value will be dropped twice in case `drop_in_place` + // were to panic once (if it panics twice, the program aborts). + unsafe { + // Note: It's intentional that this is `>` and not `>=`. + // Changing it to `>=` has negative performance + // implications in some cases. See #78884 for more. + if len > self.len { + return; + } + let remaining_len = self.len - len; + let s = ptr::slice_from_raw_parts_mut(self.as_mut_ptr().add(len), remaining_len); + self.len = len; + ptr::drop_in_place(s); + } + } + + /// Extracts a slice containing the entire vector. + /// + /// Equivalent to `&s[..]`. + /// + /// # Examples + /// + /// ``` + /// use std::io::{self, Write}; + /// let buffer = vec![1, 2, 3, 5, 8]; + /// io::sink().write(buffer.as_slice()).unwrap(); + /// ``` + #[inline] + #[stable(feature = "vec_as_slice", since = "1.7.0")] + pub fn as_slice(&self) -> &[T] { + self + } + + /// Extracts a mutable slice of the entire vector. + /// + /// Equivalent to `&mut s[..]`. + /// + /// # Examples + /// + /// ``` + /// use std::io::{self, Read}; + /// let mut buffer = vec![0; 3]; + /// io::repeat(0b101).read_exact(buffer.as_mut_slice()).unwrap(); + /// ``` + #[inline] + #[stable(feature = "vec_as_slice", since = "1.7.0")] + pub fn as_mut_slice(&mut self) -> &mut [T] { + self + } + + /// Returns a raw pointer to the vector's buffer. + /// + /// The caller must ensure that the vector outlives the pointer this + /// function returns, or else it will end up pointing to garbage. + /// Modifying the vector may cause its buffer to be reallocated, + /// which would also make any pointers to it invalid. + /// + /// The caller must also ensure that the memory the pointer (non-transitively) points to + /// is never written to (except inside an `UnsafeCell`) using this pointer or any pointer + /// derived from it. If you need to mutate the contents of the slice, use [`as_mut_ptr`]. + /// + /// # Examples + /// + /// ``` + /// let x = vec![1, 2, 4]; + /// let x_ptr = x.as_ptr(); + /// + /// unsafe { + /// for i in 0..x.len() { + /// assert_eq!(*x_ptr.add(i), 1 << i); + /// } + /// } + /// ``` + /// + /// [`as_mut_ptr`]: Vec::as_mut_ptr + #[stable(feature = "vec_as_ptr", since = "1.37.0")] + #[inline] + pub fn as_ptr(&self) -> *const T { + // We shadow the slice method of the same name to avoid going through + // `deref`, which creates an intermediate reference. + let ptr = self.buf.ptr(); + unsafe { + assume(!ptr.is_null()); + } + ptr + } + + /// Returns an unsafe mutable pointer to the vector's buffer. + /// + /// The caller must ensure that the vector outlives the pointer this + /// function returns, or else it will end up pointing to garbage. + /// Modifying the vector may cause its buffer to be reallocated, + /// which would also make any pointers to it invalid. + /// + /// # Examples + /// + /// ``` + /// // Allocate vector big enough for 4 elements. + /// let size = 4; + /// let mut x: Vec<i32> = Vec::with_capacity(size); + /// let x_ptr = x.as_mut_ptr(); + /// + /// // Initialize elements via raw pointer writes, then set length. + /// unsafe { + /// for i in 0..size { + /// *x_ptr.add(i) = i as i32; + /// } + /// x.set_len(size); + /// } + /// assert_eq!(&*x, &[0, 1, 2, 3]); + /// ``` + #[stable(feature = "vec_as_ptr", since = "1.37.0")] + #[inline] + pub fn as_mut_ptr(&mut self) -> *mut T { + // We shadow the slice method of the same name to avoid going through + // `deref_mut`, which creates an intermediate reference. + let ptr = self.buf.ptr(); + unsafe { + assume(!ptr.is_null()); + } + ptr + } + + /// Returns a reference to the underlying allocator. + #[unstable(feature = "allocator_api", issue = "32838")] + #[inline] + pub fn allocator(&self) -> &A { + self.buf.allocator() + } + + /// Forces the length of the vector to `new_len`. + /// + /// This is a low-level operation that maintains none of the normal + /// invariants of the type. Normally changing the length of a vector + /// is done using one of the safe operations instead, such as + /// [`truncate`], [`resize`], [`extend`], or [`clear`]. + /// + /// [`truncate`]: Vec::truncate + /// [`resize`]: Vec::resize + /// [`extend`]: Extend::extend + /// [`clear`]: Vec::clear + /// + /// # Safety + /// + /// - `new_len` must be less than or equal to [`capacity()`]. + /// - The elements at `old_len..new_len` must be initialized. + /// + /// [`capacity()`]: Vec::capacity + /// + /// # Examples + /// + /// This method can be useful for situations in which the vector + /// is serving as a buffer for other code, particularly over FFI: + /// + /// ```no_run + /// # #![allow(dead_code)] + /// # // This is just a minimal skeleton for the doc example; + /// # // don't use this as a starting point for a real library. + /// # pub struct StreamWrapper { strm: *mut std::ffi::c_void } + /// # const Z_OK: i32 = 0; + /// # extern "C" { + /// # fn deflateGetDictionary( + /// # strm: *mut std::ffi::c_void, + /// # dictionary: *mut u8, + /// # dictLength: *mut usize, + /// # ) -> i32; + /// # } + /// # impl StreamWrapper { + /// pub fn get_dictionary(&self) -> Option<Vec<u8>> { + /// // Per the FFI method's docs, "32768 bytes is always enough". + /// let mut dict = Vec::with_capacity(32_768); + /// let mut dict_length = 0; + /// // SAFETY: When `deflateGetDictionary` returns `Z_OK`, it holds that: + /// // 1. `dict_length` elements were initialized. + /// // 2. `dict_length` <= the capacity (32_768) + /// // which makes `set_len` safe to call. + /// unsafe { + /// // Make the FFI call... + /// let r = deflateGetDictionary(self.strm, dict.as_mut_ptr(), &mut dict_length); + /// if r == Z_OK { + /// // ...and update the length to what was initialized. + /// dict.set_len(dict_length); + /// Some(dict) + /// } else { + /// None + /// } + /// } + /// } + /// # } + /// ``` + /// + /// While the following example is sound, there is a memory leak since + /// the inner vectors were not freed prior to the `set_len` call: + /// + /// ``` + /// let mut vec = vec![vec![1, 0, 0], + /// vec![0, 1, 0], + /// vec![0, 0, 1]]; + /// // SAFETY: + /// // 1. `old_len..0` is empty so no elements need to be initialized. + /// // 2. `0 <= capacity` always holds whatever `capacity` is. + /// unsafe { + /// vec.set_len(0); + /// } + /// ``` + /// + /// Normally, here, one would use [`clear`] instead to correctly drop + /// the contents and thus not leak memory. + #[inline] + #[stable(feature = "rust1", since = "1.0.0")] + pub unsafe fn set_len(&mut self, new_len: usize) { + debug_assert!(new_len <= self.capacity()); + + self.len = new_len; + } + + /// Removes an element from the vector and returns it. + /// + /// The removed element is replaced by the last element of the vector. + /// + /// This does not preserve ordering, but is *O*(1). + /// If you need to preserve the element order, use [`remove`] instead. + /// + /// [`remove`]: Vec::remove + /// + /// # Panics + /// + /// Panics if `index` is out of bounds. + /// + /// # Examples + /// + /// ``` + /// let mut v = vec!["foo", "bar", "baz", "qux"]; + /// + /// assert_eq!(v.swap_remove(1), "bar"); + /// assert_eq!(v, ["foo", "qux", "baz"]); + /// + /// assert_eq!(v.swap_remove(0), "foo"); + /// assert_eq!(v, ["baz", "qux"]); + /// ``` + #[inline] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn swap_remove(&mut self, index: usize) -> T { + #[cold] + #[inline(never)] + fn assert_failed(index: usize, len: usize) -> ! { + panic!("swap_remove index (is {index}) should be < len (is {len})"); + } + + let len = self.len(); + if index >= len { + assert_failed(index, len); + } + unsafe { + // We replace self[index] with the last element. Note that if the + // bounds check above succeeds there must be a last element (which + // can be self[index] itself). + let value = ptr::read(self.as_ptr().add(index)); + let base_ptr = self.as_mut_ptr(); + ptr::copy(base_ptr.add(len - 1), base_ptr.add(index), 1); + self.set_len(len - 1); + value + } + } + + /// Inserts an element at position `index` within the vector, shifting all + /// elements after it to the right. + /// + /// # Panics + /// + /// Panics if `index > len`. + /// + /// # Examples + /// + /// ``` + /// let mut vec = vec![1, 2, 3]; + /// vec.insert(1, 4); + /// assert_eq!(vec, [1, 4, 2, 3]); + /// vec.insert(4, 5); + /// assert_eq!(vec, [1, 4, 2, 3, 5]); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn insert(&mut self, index: usize, element: T) { + #[cold] + #[inline(never)] + fn assert_failed(index: usize, len: usize) -> ! { + panic!("insertion index (is {index}) should be <= len (is {len})"); + } + + let len = self.len(); + if index > len { + assert_failed(index, len); + } + + // space for the new element + if len == self.buf.capacity() { + self.reserve(1); + } + + unsafe { + // infallible + // The spot to put the new value + { + let p = self.as_mut_ptr().add(index); + // Shift everything over to make space. (Duplicating the + // `index`th element into two consecutive places.) + ptr::copy(p, p.offset(1), len - index); + // Write it in, overwriting the first copy of the `index`th + // element. + ptr::write(p, element); + } + self.set_len(len + 1); + } + } + + /// Removes and returns the element at position `index` within the vector, + /// shifting all elements after it to the left. + /// + /// Note: Because this shifts over the remaining elements, it has a + /// worst-case performance of *O*(*n*). If you don't need the order of elements + /// to be preserved, use [`swap_remove`] instead. If you'd like to remove + /// elements from the beginning of the `Vec`, consider using + /// [`VecDeque::pop_front`] instead. + /// + /// [`swap_remove`]: Vec::swap_remove + /// [`VecDeque::pop_front`]: crate::collections::VecDeque::pop_front + /// + /// # Panics + /// + /// Panics if `index` is out of bounds. + /// + /// # Examples + /// + /// ``` + /// let mut v = vec![1, 2, 3]; + /// assert_eq!(v.remove(1), 2); + /// assert_eq!(v, [1, 3]); + /// ``` + #[stable(feature = "rust1", since = "1.0.0")] + #[track_caller] + pub fn remove(&mut self, index: usize) -> T { + #[cold] + #[inline(never)] + #[track_caller] + fn assert_failed(index: usize, len: usize) -> ! { + panic!("removal index (is {index}) should be < len (is {len})"); + } + + let len = self.len(); + if index >= len { + assert_failed(index, len); + } + unsafe { + // infallible + let ret; + { + // the place we are taking from. + let ptr = self.as_mut_ptr().add(index); + // copy it out, unsafely having a copy of the value on + // the stack and in the vector at the same time. + ret = ptr::read(ptr); + + // Shift everything down to fill in that spot. + ptr::copy(ptr.offset(1), ptr, len - index - 1); + } + self.set_len(len - 1); + ret + } + } + + /// Retains only the elements specified by the predicate. + /// + /// In other words, remove all elements `e` for which `f(&e)` returns `false`. + /// This method operates in place, visiting each element exactly once in the + /// original order, and preserves the order of the retained elements. + /// + /// # Examples + /// + /// ``` + /// let mut vec = vec![1, 2, 3, 4]; + /// vec.retain(|&x| x % 2 == 0); + /// assert_eq!(vec, [2, 4]); + /// ``` + /// + /// Because the elements are visited exactly once in the original order, + /// external state may be used to decide which elements to keep. + /// + /// ``` + /// let mut vec = vec![1, 2, 3, 4, 5]; + /// let keep = [false, true, true, false, true]; + /// let mut iter = keep.iter(); + /// vec.retain(|_| *iter.next().unwrap()); + /// assert_eq!(vec, [2, 3, 5]); + /// ``` + #[stable(feature = "rust1", since = "1.0.0")] + pub fn retain<F>(&mut self, mut f: F) + where + F: FnMut(&T) -> bool, + { + self.retain_mut(|elem| f(elem)); + } + + /// Retains only the elements specified by the predicate, passing a mutable reference to it. + /// + /// In other words, remove all elements `e` such that `f(&mut e)` returns `false`. + /// This method operates in place, visiting each element exactly once in the + /// original order, and preserves the order of the retained elements. + /// + /// # Examples + /// + /// ``` + /// let mut vec = vec![1, 2, 3, 4]; + /// vec.retain_mut(|x| if *x > 3 { + /// false + /// } else { + /// *x += 1; + /// true + /// }); + /// assert_eq!(vec, [2, 3, 4]); + /// ``` + #[stable(feature = "vec_retain_mut", since = "1.61.0")] + pub fn retain_mut<F>(&mut self, mut f: F) + where + F: FnMut(&mut T) -> bool, + { + let original_len = self.len(); + // Avoid double drop if the drop guard is not executed, + // since we may make some holes during the process. + unsafe { self.set_len(0) }; + + // Vec: [Kept, Kept, Hole, Hole, Hole, Hole, Unchecked, Unchecked] + // |<- processed len ->| ^- next to check + // |<- deleted cnt ->| + // |<- original_len ->| + // Kept: Elements which predicate returns true on. + // Hole: Moved or dropped element slot. + // Unchecked: Unchecked valid elements. + // + // This drop guard will be invoked when predicate or `drop` of element panicked. + // It shifts unchecked elements to cover holes and `set_len` to the correct length. + // In cases when predicate and `drop` never panick, it will be optimized out. + struct BackshiftOnDrop<'a, T, A: Allocator> { + v: &'a mut Vec<T, A>, + processed_len: usize, + deleted_cnt: usize, + original_len: usize, + } + + impl<T, A: Allocator> Drop for BackshiftOnDrop<'_, T, A> { + fn drop(&mut self) { + if self.deleted_cnt > 0 { + // SAFETY: Trailing unchecked items must be valid since we never touch them. + unsafe { + ptr::copy( + self.v.as_ptr().add(self.processed_len), + self.v.as_mut_ptr().add(self.processed_len - self.deleted_cnt), + self.original_len - self.processed_len, + ); + } + } + // SAFETY: After filling holes, all items are in contiguous memory. + unsafe { + self.v.set_len(self.original_len - self.deleted_cnt); + } + } + } + + let mut g = BackshiftOnDrop { v: self, processed_len: 0, deleted_cnt: 0, original_len }; + + fn process_loop<F, T, A: Allocator, const DELETED: bool>( + original_len: usize, + f: &mut F, + g: &mut BackshiftOnDrop<'_, T, A>, + ) where + F: FnMut(&mut T) -> bool, + { + while g.processed_len != original_len { + // SAFETY: Unchecked element must be valid. + let cur = unsafe { &mut *g.v.as_mut_ptr().add(g.processed_len) }; + if !f(cur) { + // Advance early to avoid double drop if `drop_in_place` panicked. + g.processed_len += 1; + g.deleted_cnt += 1; + // SAFETY: We never touch this element again after dropped. + unsafe { ptr::drop_in_place(cur) }; + // We already advanced the counter. + if DELETED { + continue; + } else { + break; + } + } + if DELETED { + // SAFETY: `deleted_cnt` > 0, so the hole slot must not overlap with current element. + // We use copy for move, and never touch this element again. + unsafe { + let hole_slot = g.v.as_mut_ptr().add(g.processed_len - g.deleted_cnt); + ptr::copy_nonoverlapping(cur, hole_slot, 1); + } + } + g.processed_len += 1; + } + } + + // Stage 1: Nothing was deleted. + process_loop::<F, T, A, false>(original_len, &mut f, &mut g); + + // Stage 2: Some elements were deleted. + process_loop::<F, T, A, true>(original_len, &mut f, &mut g); + + // All item are processed. This can be optimized to `set_len` by LLVM. + drop(g); + } + + /// Removes all but the first of consecutive elements in the vector that resolve to the same + /// key. + /// + /// If the vector is sorted, this removes all duplicates. + /// + /// # Examples + /// + /// ``` + /// let mut vec = vec![10, 20, 21, 30, 20]; + /// + /// vec.dedup_by_key(|i| *i / 10); + /// + /// assert_eq!(vec, [10, 20, 30, 20]); + /// ``` + #[stable(feature = "dedup_by", since = "1.16.0")] + #[inline] + pub fn dedup_by_key<F, K>(&mut self, mut key: F) + where + F: FnMut(&mut T) -> K, + K: PartialEq, + { + self.dedup_by(|a, b| key(a) == key(b)) + } + + /// Removes all but the first of consecutive elements in the vector satisfying a given equality + /// relation. + /// + /// The `same_bucket` function is passed references to two elements from the vector and + /// must determine if the elements compare equal. The elements are passed in opposite order + /// from their order in the slice, so if `same_bucket(a, b)` returns `true`, `a` is removed. + /// + /// If the vector is sorted, this removes all duplicates. + /// + /// # Examples + /// + /// ``` + /// let mut vec = vec!["foo", "bar", "Bar", "baz", "bar"]; + /// + /// vec.dedup_by(|a, b| a.eq_ignore_ascii_case(b)); + /// + /// assert_eq!(vec, ["foo", "bar", "baz", "bar"]); + /// ``` + #[stable(feature = "dedup_by", since = "1.16.0")] + pub fn dedup_by<F>(&mut self, mut same_bucket: F) + where + F: FnMut(&mut T, &mut T) -> bool, + { + let len = self.len(); + if len <= 1 { + return; + } + + /* INVARIANT: vec.len() > read >= write > write-1 >= 0 */ + struct FillGapOnDrop<'a, T, A: core::alloc::Allocator> { + /* Offset of the element we want to check if it is duplicate */ + read: usize, + + /* Offset of the place where we want to place the non-duplicate + * when we find it. */ + write: usize, + + /* The Vec that would need correction if `same_bucket` panicked */ + vec: &'a mut Vec<T, A>, + } + + impl<'a, T, A: core::alloc::Allocator> Drop for FillGapOnDrop<'a, T, A> { + fn drop(&mut self) { + /* This code gets executed when `same_bucket` panics */ + + /* SAFETY: invariant guarantees that `read - write` + * and `len - read` never overflow and that the copy is always + * in-bounds. */ + unsafe { + let ptr = self.vec.as_mut_ptr(); + let len = self.vec.len(); + + /* How many items were left when `same_bucket` panicked. + * Basically vec[read..].len() */ + let items_left = len.wrapping_sub(self.read); + + /* Pointer to first item in vec[write..write+items_left] slice */ + let dropped_ptr = ptr.add(self.write); + /* Pointer to first item in vec[read..] slice */ + let valid_ptr = ptr.add(self.read); + + /* Copy `vec[read..]` to `vec[write..write+items_left]`. + * The slices can overlap, so `copy_nonoverlapping` cannot be used */ + ptr::copy(valid_ptr, dropped_ptr, items_left); + + /* How many items have been already dropped + * Basically vec[read..write].len() */ + let dropped = self.read.wrapping_sub(self.write); + + self.vec.set_len(len - dropped); + } + } + } + + let mut gap = FillGapOnDrop { read: 1, write: 1, vec: self }; + let ptr = gap.vec.as_mut_ptr(); + + /* Drop items while going through Vec, it should be more efficient than + * doing slice partition_dedup + truncate */ + + /* SAFETY: Because of the invariant, read_ptr, prev_ptr and write_ptr + * are always in-bounds and read_ptr never aliases prev_ptr */ + unsafe { + while gap.read < len { + let read_ptr = ptr.add(gap.read); + let prev_ptr = ptr.add(gap.write.wrapping_sub(1)); + + if same_bucket(&mut *read_ptr, &mut *prev_ptr) { + // Increase `gap.read` now since the drop may panic. + gap.read += 1; + /* We have found duplicate, drop it in-place */ + ptr::drop_in_place(read_ptr); + } else { + let write_ptr = ptr.add(gap.write); + + /* Because `read_ptr` can be equal to `write_ptr`, we either + * have to use `copy` or conditional `copy_nonoverlapping`. + * Looks like the first option is faster. */ + ptr::copy(read_ptr, write_ptr, 1); + + /* We have filled that place, so go further */ + gap.write += 1; + gap.read += 1; + } + } + + /* Technically we could let `gap` clean up with its Drop, but + * when `same_bucket` is guaranteed to not panic, this bloats a little + * the codegen, so we just do it manually */ + gap.vec.set_len(gap.write); + mem::forget(gap); + } + } + + /// Appends an element to the back of a collection. + /// + /// # Panics + /// + /// Panics if the new capacity exceeds `isize::MAX` bytes. + /// + /// # Examples + /// + /// ``` + /// let mut vec = vec![1, 2]; + /// vec.push(3); + /// assert_eq!(vec, [1, 2, 3]); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[inline] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn push(&mut self, value: T) { + // This will panic or abort if we would allocate > isize::MAX bytes + // or if the length increment would overflow for zero-sized types. + if self.len == self.buf.capacity() { + self.buf.reserve_for_push(self.len); + } + unsafe { + let end = self.as_mut_ptr().add(self.len); + ptr::write(end, value); + self.len += 1; + } + } + + /// Tries to append an element to the back of a collection. + /// + /// # Examples + /// + /// ``` + /// let mut vec = vec![1, 2]; + /// vec.try_push(3).unwrap(); + /// assert_eq!(vec, [1, 2, 3]); + /// ``` + #[inline] + #[stable(feature = "kernel", since = "1.0.0")] + pub fn try_push(&mut self, value: T) -> Result<(), TryReserveError> { + if self.len == self.buf.capacity() { + self.buf.try_reserve_for_push(self.len)?; + } + unsafe { + let end = self.as_mut_ptr().add(self.len); + ptr::write(end, value); + self.len += 1; + } + Ok(()) + } + + /// Removes the last element from a vector and returns it, or [`None`] if it + /// is empty. + /// + /// If you'd like to pop the first element, consider using + /// [`VecDeque::pop_front`] instead. + /// + /// [`VecDeque::pop_front`]: crate::collections::VecDeque::pop_front + /// + /// # Examples + /// + /// ``` + /// let mut vec = vec![1, 2, 3]; + /// assert_eq!(vec.pop(), Some(3)); + /// assert_eq!(vec, [1, 2]); + /// ``` + #[inline] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn pop(&mut self) -> Option<T> { + if self.len == 0 { + None + } else { + unsafe { + self.len -= 1; + Some(ptr::read(self.as_ptr().add(self.len()))) + } + } + } + + /// Moves all the elements of `other` into `self`, leaving `other` empty. + /// + /// # Panics + /// + /// Panics if the number of elements in the vector overflows a `usize`. + /// + /// # Examples + /// + /// ``` + /// let mut vec = vec![1, 2, 3]; + /// let mut vec2 = vec![4, 5, 6]; + /// vec.append(&mut vec2); + /// assert_eq!(vec, [1, 2, 3, 4, 5, 6]); + /// assert_eq!(vec2, []); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[inline] + #[stable(feature = "append", since = "1.4.0")] + pub fn append(&mut self, other: &mut Self) { + unsafe { + self.append_elements(other.as_slice() as _); + other.set_len(0); + } + } + + /// Appends elements to `self` from other buffer. + #[cfg(not(no_global_oom_handling))] + #[inline] + unsafe fn append_elements(&mut self, other: *const [T]) { + let count = unsafe { (*other).len() }; + self.reserve(count); + let len = self.len(); + unsafe { ptr::copy_nonoverlapping(other as *const T, self.as_mut_ptr().add(len), count) }; + self.len += count; + } + + /// Removes the specified range from the vector in bulk, returning all + /// removed elements as an iterator. If the iterator is dropped before + /// being fully consumed, it drops the remaining removed elements. + /// + /// The returned iterator keeps a mutable borrow on the vector to optimize + /// its implementation. + /// + /// # Panics + /// + /// Panics if the starting point is greater than the end point or if + /// the end point is greater than the length of the vector. + /// + /// # Leaking + /// + /// If the returned iterator goes out of scope without being dropped (due to + /// [`mem::forget`], for example), the vector may have lost and leaked + /// elements arbitrarily, including elements outside the range. + /// + /// # Examples + /// + /// ``` + /// let mut v = vec![1, 2, 3]; + /// let u: Vec<_> = v.drain(1..).collect(); + /// assert_eq!(v, &[1]); + /// assert_eq!(u, &[2, 3]); + /// + /// // A full range clears the vector, like `clear()` does + /// v.drain(..); + /// assert_eq!(v, &[]); + /// ``` + #[stable(feature = "drain", since = "1.6.0")] + pub fn drain<R>(&mut self, range: R) -> Drain<'_, T, A> + where + R: RangeBounds<usize>, + { + // Memory safety + // + // When the Drain is first created, it shortens the length of + // the source vector to make sure no uninitialized or moved-from elements + // are accessible at all if the Drain's destructor never gets to run. + // + // Drain will ptr::read out the values to remove. + // When finished, remaining tail of the vec is copied back to cover + // the hole, and the vector length is restored to the new length. + // + let len = self.len(); + let Range { start, end } = slice::range(range, ..len); + + unsafe { + // set self.vec length's to start, to be safe in case Drain is leaked + self.set_len(start); + // Use the borrow in the IterMut to indicate borrowing behavior of the + // whole Drain iterator (like &mut T). + let range_slice = slice::from_raw_parts_mut(self.as_mut_ptr().add(start), end - start); + Drain { + tail_start: end, + tail_len: len - end, + iter: range_slice.iter(), + vec: NonNull::from(self), + } + } + } + + /// Clears the vector, removing all values. + /// + /// Note that this method has no effect on the allocated capacity + /// of the vector. + /// + /// # Examples + /// + /// ``` + /// let mut v = vec![1, 2, 3]; + /// + /// v.clear(); + /// + /// assert!(v.is_empty()); + /// ``` + #[inline] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn clear(&mut self) { + let elems: *mut [T] = self.as_mut_slice(); + + // SAFETY: + // - `elems` comes directly from `as_mut_slice` and is therefore valid. + // - Setting `self.len` before calling `drop_in_place` means that, + // if an element's `Drop` impl panics, the vector's `Drop` impl will + // do nothing (leaking the rest of the elements) instead of dropping + // some twice. + unsafe { + self.len = 0; + ptr::drop_in_place(elems); + } + } + + /// Returns the number of elements in the vector, also referred to + /// as its 'length'. + /// + /// # Examples + /// + /// ``` + /// let a = vec![1, 2, 3]; + /// assert_eq!(a.len(), 3); + /// ``` + #[inline] + #[stable(feature = "rust1", since = "1.0.0")] + pub fn len(&self) -> usize { + self.len + } + + /// Returns `true` if the vector contains no elements. + /// + /// # Examples + /// + /// ``` + /// let mut v = Vec::new(); + /// assert!(v.is_empty()); + /// + /// v.push(1); + /// assert!(!v.is_empty()); + /// ``` + #[stable(feature = "rust1", since = "1.0.0")] + pub fn is_empty(&self) -> bool { + self.len() == 0 + } + + /// Splits the collection into two at the given index. + /// + /// Returns a newly allocated vector containing the elements in the range + /// `[at, len)`. After the call, the original vector will be left containing + /// the elements `[0, at)` with its previous capacity unchanged. + /// + /// # Panics + /// + /// Panics if `at > len`. + /// + /// # Examples + /// + /// ``` + /// let mut vec = vec![1, 2, 3]; + /// let vec2 = vec.split_off(1); + /// assert_eq!(vec, [1]); + /// assert_eq!(vec2, [2, 3]); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[inline] + #[must_use = "use `.truncate()` if you don't need the other half"] + #[stable(feature = "split_off", since = "1.4.0")] + pub fn split_off(&mut self, at: usize) -> Self + where + A: Clone, + { + #[cold] + #[inline(never)] + fn assert_failed(at: usize, len: usize) -> ! { + panic!("`at` split index (is {at}) should be <= len (is {len})"); + } + + if at > self.len() { + assert_failed(at, self.len()); + } + + if at == 0 { + // the new vector can take over the original buffer and avoid the copy + return mem::replace( + self, + Vec::with_capacity_in(self.capacity(), self.allocator().clone()), + ); + } + + let other_len = self.len - at; + let mut other = Vec::with_capacity_in(other_len, self.allocator().clone()); + + // Unsafely `set_len` and copy items to `other`. + unsafe { + self.set_len(at); + other.set_len(other_len); + + ptr::copy_nonoverlapping(self.as_ptr().add(at), other.as_mut_ptr(), other.len()); + } + other + } + + /// Resizes the `Vec` in-place so that `len` is equal to `new_len`. + /// + /// If `new_len` is greater than `len`, the `Vec` is extended by the + /// difference, with each additional slot filled with the result of + /// calling the closure `f`. The return values from `f` will end up + /// in the `Vec` in the order they have been generated. + /// + /// If `new_len` is less than `len`, the `Vec` is simply truncated. + /// + /// This method uses a closure to create new values on every push. If + /// you'd rather [`Clone`] a given value, use [`Vec::resize`]. If you + /// want to use the [`Default`] trait to generate values, you can + /// pass [`Default::default`] as the second argument. + /// + /// # Examples + /// + /// ``` + /// let mut vec = vec![1, 2, 3]; + /// vec.resize_with(5, Default::default); + /// assert_eq!(vec, [1, 2, 3, 0, 0]); + /// + /// let mut vec = vec![]; + /// let mut p = 1; + /// vec.resize_with(4, || { p *= 2; p }); + /// assert_eq!(vec, [2, 4, 8, 16]); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[stable(feature = "vec_resize_with", since = "1.33.0")] + pub fn resize_with<F>(&mut self, new_len: usize, f: F) + where + F: FnMut() -> T, + { + let len = self.len(); + if new_len > len { + self.extend_with(new_len - len, ExtendFunc(f)); + } else { + self.truncate(new_len); + } + } + + /// Consumes and leaks the `Vec`, returning a mutable reference to the contents, + /// `&'a mut [T]`. Note that the type `T` must outlive the chosen lifetime + /// `'a`. If the type has only static references, or none at all, then this + /// may be chosen to be `'static`. + /// + /// As of Rust 1.57, this method does not reallocate or shrink the `Vec`, + /// so the leaked allocation may include unused capacity that is not part + /// of the returned slice. + /// + /// This function is mainly useful for data that lives for the remainder of + /// the program's life. Dropping the returned reference will cause a memory + /// leak. + /// + /// # Examples + /// + /// Simple usage: + /// + /// ``` + /// let x = vec![1, 2, 3]; + /// let static_ref: &'static mut [usize] = x.leak(); + /// static_ref[0] += 1; + /// assert_eq!(static_ref, &[2, 2, 3]); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[stable(feature = "vec_leak", since = "1.47.0")] + #[inline] + pub fn leak<'a>(self) -> &'a mut [T] + where + A: 'a, + { + let mut me = ManuallyDrop::new(self); + unsafe { slice::from_raw_parts_mut(me.as_mut_ptr(), me.len) } + } + + /// Returns the remaining spare capacity of the vector as a slice of + /// `MaybeUninit<T>`. + /// + /// The returned slice can be used to fill the vector with data (e.g. by + /// reading from a file) before marking the data as initialized using the + /// [`set_len`] method. + /// + /// [`set_len`]: Vec::set_len + /// + /// # Examples + /// + /// ``` + /// // Allocate vector big enough for 10 elements. + /// let mut v = Vec::with_capacity(10); + /// + /// // Fill in the first 3 elements. + /// let uninit = v.spare_capacity_mut(); + /// uninit[0].write(0); + /// uninit[1].write(1); + /// uninit[2].write(2); + /// + /// // Mark the first 3 elements of the vector as being initialized. + /// unsafe { + /// v.set_len(3); + /// } + /// + /// assert_eq!(&v, &[0, 1, 2]); + /// ``` + #[stable(feature = "vec_spare_capacity", since = "1.60.0")] + #[inline] + pub fn spare_capacity_mut(&mut self) -> &mut [MaybeUninit<T>] { + // Note: + // This method is not implemented in terms of `split_at_spare_mut`, + // to prevent invalidation of pointers to the buffer. + unsafe { + slice::from_raw_parts_mut( + self.as_mut_ptr().add(self.len) as *mut MaybeUninit<T>, + self.buf.capacity() - self.len, + ) + } + } + + /// Returns vector content as a slice of `T`, along with the remaining spare + /// capacity of the vector as a slice of `MaybeUninit<T>`. + /// + /// The returned spare capacity slice can be used to fill the vector with data + /// (e.g. by reading from a file) before marking the data as initialized using + /// the [`set_len`] method. + /// + /// [`set_len`]: Vec::set_len + /// + /// Note that this is a low-level API, which should be used with care for + /// optimization purposes. If you need to append data to a `Vec` + /// you can use [`push`], [`extend`], [`extend_from_slice`], + /// [`extend_from_within`], [`insert`], [`append`], [`resize`] or + /// [`resize_with`], depending on your exact needs. + /// + /// [`push`]: Vec::push + /// [`extend`]: Vec::extend + /// [`extend_from_slice`]: Vec::extend_from_slice + /// [`extend_from_within`]: Vec::extend_from_within + /// [`insert`]: Vec::insert + /// [`append`]: Vec::append + /// [`resize`]: Vec::resize + /// [`resize_with`]: Vec::resize_with + /// + /// # Examples + /// + /// ``` + /// #![feature(vec_split_at_spare)] + /// + /// let mut v = vec![1, 1, 2]; + /// + /// // Reserve additional space big enough for 10 elements. + /// v.reserve(10); + /// + /// let (init, uninit) = v.split_at_spare_mut(); + /// let sum = init.iter().copied().sum::<u32>(); + /// + /// // Fill in the next 4 elements. + /// uninit[0].write(sum); + /// uninit[1].write(sum * 2); + /// uninit[2].write(sum * 3); + /// uninit[3].write(sum * 4); + /// + /// // Mark the 4 elements of the vector as being initialized. + /// unsafe { + /// let len = v.len(); + /// v.set_len(len + 4); + /// } + /// + /// assert_eq!(&v, &[1, 1, 2, 4, 8, 12, 16]); + /// ``` + #[unstable(feature = "vec_split_at_spare", issue = "81944")] + #[inline] + pub fn split_at_spare_mut(&mut self) -> (&mut [T], &mut [MaybeUninit<T>]) { + // SAFETY: + // - len is ignored and so never changed + let (init, spare, _) = unsafe { self.split_at_spare_mut_with_len() }; + (init, spare) + } + + /// Safety: changing returned .2 (&mut usize) is considered the same as calling `.set_len(_)`. + /// + /// This method provides unique access to all vec parts at once in `extend_from_within`. + unsafe fn split_at_spare_mut_with_len( + &mut self, + ) -> (&mut [T], &mut [MaybeUninit<T>], &mut usize) { + let ptr = self.as_mut_ptr(); + // SAFETY: + // - `ptr` is guaranteed to be valid for `self.len` elements + // - but the allocation extends out to `self.buf.capacity()` elements, possibly + // uninitialized + let spare_ptr = unsafe { ptr.add(self.len) }; + let spare_ptr = spare_ptr.cast::<MaybeUninit<T>>(); + let spare_len = self.buf.capacity() - self.len; + + // SAFETY: + // - `ptr` is guaranteed to be valid for `self.len` elements + // - `spare_ptr` is pointing one element past the buffer, so it doesn't overlap with `initialized` + unsafe { + let initialized = slice::from_raw_parts_mut(ptr, self.len); + let spare = slice::from_raw_parts_mut(spare_ptr, spare_len); + + (initialized, spare, &mut self.len) + } + } +} + +impl<T: Clone, A: Allocator> Vec<T, A> { + /// Resizes the `Vec` in-place so that `len` is equal to `new_len`. + /// + /// If `new_len` is greater than `len`, the `Vec` is extended by the + /// difference, with each additional slot filled with `value`. + /// If `new_len` is less than `len`, the `Vec` is simply truncated. + /// + /// This method requires `T` to implement [`Clone`], + /// in order to be able to clone the passed value. + /// If you need more flexibility (or want to rely on [`Default`] instead of + /// [`Clone`]), use [`Vec::resize_with`]. + /// If you only need to resize to a smaller size, use [`Vec::truncate`]. + /// + /// # Examples + /// + /// ``` + /// let mut vec = vec!["hello"]; + /// vec.resize(3, "world"); + /// assert_eq!(vec, ["hello", "world", "world"]); + /// + /// let mut vec = vec![1, 2, 3, 4]; + /// vec.resize(2, 0); + /// assert_eq!(vec, [1, 2]); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[stable(feature = "vec_resize", since = "1.5.0")] + pub fn resize(&mut self, new_len: usize, value: T) { + let len = self.len(); + + if new_len > len { + self.extend_with(new_len - len, ExtendElement(value)) + } else { + self.truncate(new_len); + } + } + + /// Clones and appends all elements in a slice to the `Vec`. + /// + /// Iterates over the slice `other`, clones each element, and then appends + /// it to this `Vec`. The `other` slice is traversed in-order. + /// + /// Note that this function is same as [`extend`] except that it is + /// specialized to work with slices instead. If and when Rust gets + /// specialization this function will likely be deprecated (but still + /// available). + /// + /// # Examples + /// + /// ``` + /// let mut vec = vec![1]; + /// vec.extend_from_slice(&[2, 3, 4]); + /// assert_eq!(vec, [1, 2, 3, 4]); + /// ``` + /// + /// [`extend`]: Vec::extend + #[cfg(not(no_global_oom_handling))] + #[stable(feature = "vec_extend_from_slice", since = "1.6.0")] + pub fn extend_from_slice(&mut self, other: &[T]) { + self.spec_extend(other.iter()) + } + + /// Copies elements from `src` range to the end of the vector. + /// + /// # Panics + /// + /// Panics if the starting point is greater than the end point or if + /// the end point is greater than the length of the vector. + /// + /// # Examples + /// + /// ``` + /// let mut vec = vec![0, 1, 2, 3, 4]; + /// + /// vec.extend_from_within(2..); + /// assert_eq!(vec, [0, 1, 2, 3, 4, 2, 3, 4]); + /// + /// vec.extend_from_within(..2); + /// assert_eq!(vec, [0, 1, 2, 3, 4, 2, 3, 4, 0, 1]); + /// + /// vec.extend_from_within(4..8); + /// assert_eq!(vec, [0, 1, 2, 3, 4, 2, 3, 4, 0, 1, 4, 2, 3, 4]); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[stable(feature = "vec_extend_from_within", since = "1.53.0")] + pub fn extend_from_within<R>(&mut self, src: R) + where + R: RangeBounds<usize>, + { + let range = slice::range(src, ..self.len()); + self.reserve(range.len()); + + // SAFETY: + // - `slice::range` guarantees that the given range is valid for indexing self + unsafe { + self.spec_extend_from_within(range); + } + } +} + +impl<T, A: Allocator, const N: usize> Vec<[T; N], A> { + /// Takes a `Vec<[T; N]>` and flattens it into a `Vec<T>`. + /// + /// # Panics + /// + /// Panics if the length of the resulting vector would overflow a `usize`. + /// + /// This is only possible when flattening a vector of arrays of zero-sized + /// types, and thus tends to be irrelevant in practice. If + /// `size_of::<T>() > 0`, this will never panic. + /// + /// # Examples + /// + /// ``` + /// #![feature(slice_flatten)] + /// + /// let mut vec = vec![[1, 2, 3], [4, 5, 6], [7, 8, 9]]; + /// assert_eq!(vec.pop(), Some([7, 8, 9])); + /// + /// let mut flattened = vec.into_flattened(); + /// assert_eq!(flattened.pop(), Some(6)); + /// ``` + #[unstable(feature = "slice_flatten", issue = "95629")] + pub fn into_flattened(self) -> Vec<T, A> { + let (ptr, len, cap, alloc) = self.into_raw_parts_with_alloc(); + let (new_len, new_cap) = if mem::size_of::<T>() == 0 { + (len.checked_mul(N).expect("vec len overflow"), usize::MAX) + } else { + // SAFETY: + // - `cap * N` cannot overflow because the allocation is already in + // the address space. + // - Each `[T; N]` has `N` valid elements, so there are `len * N` + // valid elements in the allocation. + unsafe { (len.unchecked_mul(N), cap.unchecked_mul(N)) } + }; + // SAFETY: + // - `ptr` was allocated by `self` + // - `ptr` is well-aligned because `[T; N]` has the same alignment as `T`. + // - `new_cap` refers to the same sized allocation as `cap` because + // `new_cap * size_of::<T>()` == `cap * size_of::<[T; N]>()` + // - `len` <= `cap`, so `len * N` <= `cap * N`. + unsafe { Vec::<T, A>::from_raw_parts_in(ptr.cast(), new_len, new_cap, alloc) } + } +} + +// This code generalizes `extend_with_{element,default}`. +trait ExtendWith<T> { + fn next(&mut self) -> T; + fn last(self) -> T; +} + +struct ExtendElement<T>(T); +impl<T: Clone> ExtendWith<T> for ExtendElement<T> { + fn next(&mut self) -> T { + self.0.clone() + } + fn last(self) -> T { + self.0 + } +} + +struct ExtendFunc<F>(F); +impl<T, F: FnMut() -> T> ExtendWith<T> for ExtendFunc<F> { + fn next(&mut self) -> T { + (self.0)() + } + fn last(mut self) -> T { + (self.0)() + } +} + +impl<T, A: Allocator> Vec<T, A> { + #[cfg(not(no_global_oom_handling))] + /// Extend the vector by `n` values, using the given generator. + fn extend_with<E: ExtendWith<T>>(&mut self, n: usize, mut value: E) { + self.reserve(n); + + unsafe { + let mut ptr = self.as_mut_ptr().add(self.len()); + // Use SetLenOnDrop to work around bug where compiler + // might not realize the store through `ptr` through self.set_len() + // don't alias. + let mut local_len = SetLenOnDrop::new(&mut self.len); + + // Write all elements except the last one + for _ in 1..n { + ptr::write(ptr, value.next()); + ptr = ptr.offset(1); + // Increment the length in every step in case next() panics + local_len.increment_len(1); + } + + if n > 0 { + // We can write the last element directly without cloning needlessly + ptr::write(ptr, value.last()); + local_len.increment_len(1); + } + + // len set by scope guard + } + } +} + +impl<T: PartialEq, A: Allocator> Vec<T, A> { + /// Removes consecutive repeated elements in the vector according to the + /// [`PartialEq`] trait implementation. + /// + /// If the vector is sorted, this removes all duplicates. + /// + /// # Examples + /// + /// ``` + /// let mut vec = vec![1, 2, 2, 3, 2]; + /// + /// vec.dedup(); + /// + /// assert_eq!(vec, [1, 2, 3, 2]); + /// ``` + #[stable(feature = "rust1", since = "1.0.0")] + #[inline] + pub fn dedup(&mut self) { + self.dedup_by(|a, b| a == b) + } +} + +//////////////////////////////////////////////////////////////////////////////// +// Internal methods and functions +//////////////////////////////////////////////////////////////////////////////// + +#[doc(hidden)] +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +pub fn from_elem<T: Clone>(elem: T, n: usize) -> Vec<T> { + <T as SpecFromElem>::from_elem(elem, n, Global) +} + +#[doc(hidden)] +#[cfg(not(no_global_oom_handling))] +#[unstable(feature = "allocator_api", issue = "32838")] +pub fn from_elem_in<T: Clone, A: Allocator>(elem: T, n: usize, alloc: A) -> Vec<T, A> { + <T as SpecFromElem>::from_elem(elem, n, alloc) +} + +trait ExtendFromWithinSpec { + /// # Safety + /// + /// - `src` needs to be valid index + /// - `self.capacity() - self.len()` must be `>= src.len()` + unsafe fn spec_extend_from_within(&mut self, src: Range<usize>); +} + +impl<T: Clone, A: Allocator> ExtendFromWithinSpec for Vec<T, A> { + default unsafe fn spec_extend_from_within(&mut self, src: Range<usize>) { + // SAFETY: + // - len is increased only after initializing elements + let (this, spare, len) = unsafe { self.split_at_spare_mut_with_len() }; + + // SAFETY: + // - caller guaratees that src is a valid index + let to_clone = unsafe { this.get_unchecked(src) }; + + iter::zip(to_clone, spare) + .map(|(src, dst)| dst.write(src.clone())) + // Note: + // - Element was just initialized with `MaybeUninit::write`, so it's ok to increase len + // - len is increased after each element to prevent leaks (see issue #82533) + .for_each(|_| *len += 1); + } +} + +impl<T: Copy, A: Allocator> ExtendFromWithinSpec for Vec<T, A> { + unsafe fn spec_extend_from_within(&mut self, src: Range<usize>) { + let count = src.len(); + { + let (init, spare) = self.split_at_spare_mut(); + + // SAFETY: + // - caller guaratees that `src` is a valid index + let source = unsafe { init.get_unchecked(src) }; + + // SAFETY: + // - Both pointers are created from unique slice references (`&mut [_]`) + // so they are valid and do not overlap. + // - Elements are :Copy so it's OK to to copy them, without doing + // anything with the original values + // - `count` is equal to the len of `source`, so source is valid for + // `count` reads + // - `.reserve(count)` guarantees that `spare.len() >= count` so spare + // is valid for `count` writes + unsafe { ptr::copy_nonoverlapping(source.as_ptr(), spare.as_mut_ptr() as _, count) }; + } + + // SAFETY: + // - The elements were just initialized by `copy_nonoverlapping` + self.len += count; + } +} + +//////////////////////////////////////////////////////////////////////////////// +// Common trait implementations for Vec +//////////////////////////////////////////////////////////////////////////////// + +#[stable(feature = "rust1", since = "1.0.0")] +impl<T, A: Allocator> ops::Deref for Vec<T, A> { + type Target = [T]; + + fn deref(&self) -> &[T] { + unsafe { slice::from_raw_parts(self.as_ptr(), self.len) } + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<T, A: Allocator> ops::DerefMut for Vec<T, A> { + fn deref_mut(&mut self) -> &mut [T] { + unsafe { slice::from_raw_parts_mut(self.as_mut_ptr(), self.len) } + } +} + +#[cfg(not(no_global_oom_handling))] +trait SpecCloneFrom { + fn clone_from(this: &mut Self, other: &Self); +} + +#[cfg(not(no_global_oom_handling))] +impl<T: Clone, A: Allocator> SpecCloneFrom for Vec<T, A> { + default fn clone_from(this: &mut Self, other: &Self) { + // drop anything that will not be overwritten + this.truncate(other.len()); + + // self.len <= other.len due to the truncate above, so the + // slices here are always in-bounds. + let (init, tail) = other.split_at(this.len()); + + // reuse the contained values' allocations/resources. + this.clone_from_slice(init); + this.extend_from_slice(tail); + } +} + +#[cfg(not(no_global_oom_handling))] +impl<T: Copy, A: Allocator> SpecCloneFrom for Vec<T, A> { + fn clone_from(this: &mut Self, other: &Self) { + this.clear(); + this.extend_from_slice(other); + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +impl<T: Clone, A: Allocator + Clone> Clone for Vec<T, A> { + #[cfg(not(test))] + fn clone(&self) -> Self { + let alloc = self.allocator().clone(); + <[T]>::to_vec_in(&**self, alloc) + } + + // HACK(japaric): with cfg(test) the inherent `[T]::to_vec` method, which is + // required for this method definition, is not available. Instead use the + // `slice::to_vec` function which is only available with cfg(test) + // NB see the slice::hack module in slice.rs for more information + #[cfg(test)] + fn clone(&self) -> Self { + let alloc = self.allocator().clone(); + crate::slice::to_vec(&**self, alloc) + } + + fn clone_from(&mut self, other: &Self) { + SpecCloneFrom::clone_from(self, other) + } +} + +/// The hash of a vector is the same as that of the corresponding slice, +/// as required by the `core::borrow::Borrow` implementation. +/// +/// ``` +/// #![feature(build_hasher_simple_hash_one)] +/// use std::hash::BuildHasher; +/// +/// let b = std::collections::hash_map::RandomState::new(); +/// let v: Vec<u8> = vec![0xa8, 0x3c, 0x09]; +/// let s: &[u8] = &[0xa8, 0x3c, 0x09]; +/// assert_eq!(b.hash_one(v), b.hash_one(s)); +/// ``` +#[stable(feature = "rust1", since = "1.0.0")] +impl<T: Hash, A: Allocator> Hash for Vec<T, A> { + #[inline] + fn hash<H: Hasher>(&self, state: &mut H) { + Hash::hash(&**self, state) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +#[rustc_on_unimplemented( + message = "vector indices are of type `usize` or ranges of `usize`", + label = "vector indices are of type `usize` or ranges of `usize`" +)] +impl<T, I: SliceIndex<[T]>, A: Allocator> Index<I> for Vec<T, A> { + type Output = I::Output; + + #[inline] + fn index(&self, index: I) -> &Self::Output { + Index::index(&**self, index) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +#[rustc_on_unimplemented( + message = "vector indices are of type `usize` or ranges of `usize`", + label = "vector indices are of type `usize` or ranges of `usize`" +)] +impl<T, I: SliceIndex<[T]>, A: Allocator> IndexMut<I> for Vec<T, A> { + #[inline] + fn index_mut(&mut self, index: I) -> &mut Self::Output { + IndexMut::index_mut(&mut **self, index) + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +impl<T> FromIterator<T> for Vec<T> { + #[inline] + fn from_iter<I: IntoIterator<Item = T>>(iter: I) -> Vec<T> { + <Self as SpecFromIter<T, I::IntoIter>>::from_iter(iter.into_iter()) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<T, A: Allocator> IntoIterator for Vec<T, A> { + type Item = T; + type IntoIter = IntoIter<T, A>; + + /// Creates a consuming iterator, that is, one that moves each value out of + /// the vector (from start to end). The vector cannot be used after calling + /// this. + /// + /// # Examples + /// + /// ``` + /// let v = vec!["a".to_string(), "b".to_string()]; + /// for s in v.into_iter() { + /// // s has type String, not &String + /// println!("{s}"); + /// } + /// ``` + #[inline] + fn into_iter(self) -> IntoIter<T, A> { + unsafe { + let mut me = ManuallyDrop::new(self); + let alloc = ManuallyDrop::new(ptr::read(me.allocator())); + let begin = me.as_mut_ptr(); + let end = if mem::size_of::<T>() == 0 { + arith_offset(begin as *const i8, me.len() as isize) as *const T + } else { + begin.add(me.len()) as *const T + }; + let cap = me.buf.capacity(); + IntoIter { + buf: NonNull::new_unchecked(begin), + phantom: PhantomData, + cap, + alloc, + ptr: begin, + end, + } + } + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<'a, T, A: Allocator> IntoIterator for &'a Vec<T, A> { + type Item = &'a T; + type IntoIter = slice::Iter<'a, T>; + + fn into_iter(self) -> slice::Iter<'a, T> { + self.iter() + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<'a, T, A: Allocator> IntoIterator for &'a mut Vec<T, A> { + type Item = &'a mut T; + type IntoIter = slice::IterMut<'a, T>; + + fn into_iter(self) -> slice::IterMut<'a, T> { + self.iter_mut() + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +impl<T, A: Allocator> Extend<T> for Vec<T, A> { + #[inline] + fn extend<I: IntoIterator<Item = T>>(&mut self, iter: I) { + <Self as SpecExtend<T, I::IntoIter>>::spec_extend(self, iter.into_iter()) + } + + #[inline] + fn extend_one(&mut self, item: T) { + self.push(item); + } + + #[inline] + fn extend_reserve(&mut self, additional: usize) { + self.reserve(additional); + } +} + +impl<T, A: Allocator> Vec<T, A> { + // leaf method to which various SpecFrom/SpecExtend implementations delegate when + // they have no further optimizations to apply + #[cfg(not(no_global_oom_handling))] + fn extend_desugared<I: Iterator<Item = T>>(&mut self, mut iterator: I) { + // This is the case for a general iterator. + // + // This function should be the moral equivalent of: + // + // for item in iterator { + // self.push(item); + // } + while let Some(element) = iterator.next() { + let len = self.len(); + if len == self.capacity() { + let (lower, _) = iterator.size_hint(); + self.reserve(lower.saturating_add(1)); + } + unsafe { + ptr::write(self.as_mut_ptr().add(len), element); + // Since next() executes user code which can panic we have to bump the length + // after each step. + // NB can't overflow since we would have had to alloc the address space + self.set_len(len + 1); + } + } + } + + /// Creates a splicing iterator that replaces the specified range in the vector + /// with the given `replace_with` iterator and yields the removed items. + /// `replace_with` does not need to be the same length as `range`. + /// + /// `range` is removed even if the iterator is not consumed until the end. + /// + /// It is unspecified how many elements are removed from the vector + /// if the `Splice` value is leaked. + /// + /// The input iterator `replace_with` is only consumed when the `Splice` value is dropped. + /// + /// This is optimal if: + /// + /// * The tail (elements in the vector after `range`) is empty, + /// * or `replace_with` yields fewer or equal elements than `range`’s length + /// * or the lower bound of its `size_hint()` is exact. + /// + /// Otherwise, a temporary vector is allocated and the tail is moved twice. + /// + /// # Panics + /// + /// Panics if the starting point is greater than the end point or if + /// the end point is greater than the length of the vector. + /// + /// # Examples + /// + /// ``` + /// let mut v = vec![1, 2, 3, 4]; + /// let new = [7, 8, 9]; + /// let u: Vec<_> = v.splice(1..3, new).collect(); + /// assert_eq!(v, &[1, 7, 8, 9, 4]); + /// assert_eq!(u, &[2, 3]); + /// ``` + #[cfg(not(no_global_oom_handling))] + #[inline] + #[stable(feature = "vec_splice", since = "1.21.0")] + pub fn splice<R, I>(&mut self, range: R, replace_with: I) -> Splice<'_, I::IntoIter, A> + where + R: RangeBounds<usize>, + I: IntoIterator<Item = T>, + { + Splice { drain: self.drain(range), replace_with: replace_with.into_iter() } + } + + /// Creates an iterator which uses a closure to determine if an element should be removed. + /// + /// If the closure returns true, then the element is removed and yielded. + /// If the closure returns false, the element will remain in the vector and will not be yielded + /// by the iterator. + /// + /// Using this method is equivalent to the following code: + /// + /// ``` + /// # let some_predicate = |x: &mut i32| { *x == 2 || *x == 3 || *x == 6 }; + /// # let mut vec = vec![1, 2, 3, 4, 5, 6]; + /// let mut i = 0; + /// while i < vec.len() { + /// if some_predicate(&mut vec[i]) { + /// let val = vec.remove(i); + /// // your code here + /// } else { + /// i += 1; + /// } + /// } + /// + /// # assert_eq!(vec, vec![1, 4, 5]); + /// ``` + /// + /// But `drain_filter` is easier to use. `drain_filter` is also more efficient, + /// because it can backshift the elements of the array in bulk. + /// + /// Note that `drain_filter` also lets you mutate every element in the filter closure, + /// regardless of whether you choose to keep or remove it. + /// + /// # Examples + /// + /// Splitting an array into evens and odds, reusing the original allocation: + /// + /// ``` + /// #![feature(drain_filter)] + /// let mut numbers = vec![1, 2, 3, 4, 5, 6, 8, 9, 11, 13, 14, 15]; + /// + /// let evens = numbers.drain_filter(|x| *x % 2 == 0).collect::<Vec<_>>(); + /// let odds = numbers; + /// + /// assert_eq!(evens, vec![2, 4, 6, 8, 14]); + /// assert_eq!(odds, vec![1, 3, 5, 9, 11, 13, 15]); + /// ``` + #[unstable(feature = "drain_filter", reason = "recently added", issue = "43244")] + pub fn drain_filter<F>(&mut self, filter: F) -> DrainFilter<'_, T, F, A> + where + F: FnMut(&mut T) -> bool, + { + let old_len = self.len(); + + // Guard against us getting leaked (leak amplification) + unsafe { + self.set_len(0); + } + + DrainFilter { vec: self, idx: 0, del: 0, old_len, pred: filter, panic_flag: false } + } +} + +/// Extend implementation that copies elements out of references before pushing them onto the Vec. +/// +/// This implementation is specialized for slice iterators, where it uses [`copy_from_slice`] to +/// append the entire slice at once. +/// +/// [`copy_from_slice`]: slice::copy_from_slice +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "extend_ref", since = "1.2.0")] +impl<'a, T: Copy + 'a, A: Allocator + 'a> Extend<&'a T> for Vec<T, A> { + fn extend<I: IntoIterator<Item = &'a T>>(&mut self, iter: I) { + self.spec_extend(iter.into_iter()) + } + + #[inline] + fn extend_one(&mut self, &item: &'a T) { + self.push(item); + } + + #[inline] + fn extend_reserve(&mut self, additional: usize) { + self.reserve(additional); + } +} + +/// Implements comparison of vectors, [lexicographically](core::cmp::Ord#lexicographical-comparison). +#[stable(feature = "rust1", since = "1.0.0")] +impl<T: PartialOrd, A: Allocator> PartialOrd for Vec<T, A> { + #[inline] + fn partial_cmp(&self, other: &Self) -> Option<Ordering> { + PartialOrd::partial_cmp(&**self, &**other) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<T: Eq, A: Allocator> Eq for Vec<T, A> {} + +/// Implements ordering of vectors, [lexicographically](core::cmp::Ord#lexicographical-comparison). +#[stable(feature = "rust1", since = "1.0.0")] +impl<T: Ord, A: Allocator> Ord for Vec<T, A> { + #[inline] + fn cmp(&self, other: &Self) -> Ordering { + Ord::cmp(&**self, &**other) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +unsafe impl<#[may_dangle] T, A: Allocator> Drop for Vec<T, A> { + fn drop(&mut self) { + unsafe { + // use drop for [T] + // use a raw slice to refer to the elements of the vector as weakest necessary type; + // could avoid questions of validity in certain cases + ptr::drop_in_place(ptr::slice_from_raw_parts_mut(self.as_mut_ptr(), self.len)) + } + // RawVec handles deallocation + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +#[rustc_const_unstable(feature = "const_default_impls", issue = "87864")] +impl<T> const Default for Vec<T> { + /// Creates an empty `Vec<T>`. + fn default() -> Vec<T> { + Vec::new() + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<T: fmt::Debug, A: Allocator> fmt::Debug for Vec<T, A> { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + fmt::Debug::fmt(&**self, f) + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<T, A: Allocator> AsRef<Vec<T, A>> for Vec<T, A> { + fn as_ref(&self) -> &Vec<T, A> { + self + } +} + +#[stable(feature = "vec_as_mut", since = "1.5.0")] +impl<T, A: Allocator> AsMut<Vec<T, A>> for Vec<T, A> { + fn as_mut(&mut self) -> &mut Vec<T, A> { + self + } +} + +#[stable(feature = "rust1", since = "1.0.0")] +impl<T, A: Allocator> AsRef<[T]> for Vec<T, A> { + fn as_ref(&self) -> &[T] { + self + } +} + +#[stable(feature = "vec_as_mut", since = "1.5.0")] +impl<T, A: Allocator> AsMut<[T]> for Vec<T, A> { + fn as_mut(&mut self) -> &mut [T] { + self + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +impl<T: Clone> From<&[T]> for Vec<T> { + /// Allocate a `Vec<T>` and fill it by cloning `s`'s items. + /// + /// # Examples + /// + /// ``` + /// assert_eq!(Vec::from(&[1, 2, 3][..]), vec![1, 2, 3]); + /// ``` + #[cfg(not(test))] + fn from(s: &[T]) -> Vec<T> { + s.to_vec() + } + #[cfg(test)] + fn from(s: &[T]) -> Vec<T> { + crate::slice::to_vec(s, Global) + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "vec_from_mut", since = "1.19.0")] +impl<T: Clone> From<&mut [T]> for Vec<T> { + /// Allocate a `Vec<T>` and fill it by cloning `s`'s items. + /// + /// # Examples + /// + /// ``` + /// assert_eq!(Vec::from(&mut [1, 2, 3][..]), vec![1, 2, 3]); + /// ``` + #[cfg(not(test))] + fn from(s: &mut [T]) -> Vec<T> { + s.to_vec() + } + #[cfg(test)] + fn from(s: &mut [T]) -> Vec<T> { + crate::slice::to_vec(s, Global) + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "vec_from_array", since = "1.44.0")] +impl<T, const N: usize> From<[T; N]> for Vec<T> { + /// Allocate a `Vec<T>` and move `s`'s items into it. + /// + /// # Examples + /// + /// ``` + /// assert_eq!(Vec::from([1, 2, 3]), vec![1, 2, 3]); + /// ``` + #[cfg(not(test))] + fn from(s: [T; N]) -> Vec<T> { + <[T]>::into_vec(box s) + } + + #[cfg(test)] + fn from(s: [T; N]) -> Vec<T> { + crate::slice::into_vec(box s) + } +} + +#[stable(feature = "vec_from_cow_slice", since = "1.14.0")] +impl<'a, T> From<Cow<'a, [T]>> for Vec<T> +where + [T]: ToOwned<Owned = Vec<T>>, +{ + /// Convert a clone-on-write slice into a vector. + /// + /// If `s` already owns a `Vec<T>`, it will be returned directly. + /// If `s` is borrowing a slice, a new `Vec<T>` will be allocated and + /// filled by cloning `s`'s items into it. + /// + /// # Examples + /// + /// ``` + /// # use std::borrow::Cow; + /// let o: Cow<[i32]> = Cow::Owned(vec![1, 2, 3]); + /// let b: Cow<[i32]> = Cow::Borrowed(&[1, 2, 3]); + /// assert_eq!(Vec::from(o), Vec::from(b)); + /// ``` + fn from(s: Cow<'a, [T]>) -> Vec<T> { + s.into_owned() + } +} + +// note: test pulls in libstd, which causes errors here +#[cfg(not(test))] +#[stable(feature = "vec_from_box", since = "1.18.0")] +impl<T, A: Allocator> From<Box<[T], A>> for Vec<T, A> { + /// Convert a boxed slice into a vector by transferring ownership of + /// the existing heap allocation. + /// + /// # Examples + /// + /// ``` + /// let b: Box<[i32]> = vec![1, 2, 3].into_boxed_slice(); + /// assert_eq!(Vec::from(b), vec![1, 2, 3]); + /// ``` + fn from(s: Box<[T], A>) -> Self { + s.into_vec() + } +} + +// note: test pulls in libstd, which causes errors here +#[cfg(not(no_global_oom_handling))] +#[cfg(not(test))] +#[stable(feature = "box_from_vec", since = "1.20.0")] +impl<T, A: Allocator> From<Vec<T, A>> for Box<[T], A> { + /// Convert a vector into a boxed slice. + /// + /// If `v` has excess capacity, its items will be moved into a + /// newly-allocated buffer with exactly the right capacity. + /// + /// # Examples + /// + /// ``` + /// assert_eq!(Box::from(vec![1, 2, 3]), vec![1, 2, 3].into_boxed_slice()); + /// ``` + fn from(v: Vec<T, A>) -> Self { + v.into_boxed_slice() + } +} + +#[cfg(not(no_global_oom_handling))] +#[stable(feature = "rust1", since = "1.0.0")] +impl From<&str> for Vec<u8> { + /// Allocate a `Vec<u8>` and fill it with a UTF-8 string. + /// + /// # Examples + /// + /// ``` + /// assert_eq!(Vec::from("123"), vec![b'1', b'2', b'3']); + /// ``` + fn from(s: &str) -> Vec<u8> { + From::from(s.as_bytes()) + } +} + +#[stable(feature = "array_try_from_vec", since = "1.48.0")] +impl<T, A: Allocator, const N: usize> TryFrom<Vec<T, A>> for [T; N] { + type Error = Vec<T, A>; + + /// Gets the entire contents of the `Vec<T>` as an array, + /// if its size exactly matches that of the requested array. + /// + /// # Examples + /// + /// ``` + /// assert_eq!(vec![1, 2, 3].try_into(), Ok([1, 2, 3])); + /// assert_eq!(<Vec<i32>>::new().try_into(), Ok([])); + /// ``` + /// + /// If the length doesn't match, the input comes back in `Err`: + /// ``` + /// let r: Result<[i32; 4], _> = (0..10).collect::<Vec<_>>().try_into(); + /// assert_eq!(r, Err(vec![0, 1, 2, 3, 4, 5, 6, 7, 8, 9])); + /// ``` + /// + /// If you're fine with just getting a prefix of the `Vec<T>`, + /// you can call [`.truncate(N)`](Vec::truncate) first. + /// ``` + /// let mut v = String::from("hello world").into_bytes(); + /// v.sort(); + /// v.truncate(2); + /// let [a, b]: [_; 2] = v.try_into().unwrap(); + /// assert_eq!(a, b' '); + /// assert_eq!(b, b'd'); + /// ``` + fn try_from(mut vec: Vec<T, A>) -> Result<[T; N], Vec<T, A>> { + if vec.len() != N { + return Err(vec); + } + + // SAFETY: `.set_len(0)` is always sound. + unsafe { vec.set_len(0) }; + + // SAFETY: A `Vec`'s pointer is always aligned properly, and + // the alignment the array needs is the same as the items. + // We checked earlier that we have sufficient items. + // The items will not double-drop as the `set_len` + // tells the `Vec` not to also drop them. + let array = unsafe { ptr::read(vec.as_ptr() as *const [T; N]) }; + Ok(array) + } +} diff --git a/rust/alloc/vec/partial_eq.rs b/rust/alloc/vec/partial_eq.rs new file mode 100644 index 000000000000..10ad4e492287 --- /dev/null +++ b/rust/alloc/vec/partial_eq.rs @@ -0,0 +1,49 @@ +// SPDX-License-Identifier: Apache-2.0 OR MIT + +use crate::alloc::Allocator; +#[cfg(not(no_global_oom_handling))] +use crate::borrow::Cow; + +use super::Vec; + +macro_rules! __impl_slice_eq1 { + ([$($vars:tt)*] $lhs:ty, $rhs:ty $(where $ty:ty: $bound:ident)?, #[$stability:meta]) => { + #[$stability] + impl<T, U, $($vars)*> PartialEq<$rhs> for $lhs + where + T: PartialEq<U>, + $($ty: $bound)? + { + #[inline] + fn eq(&self, other: &$rhs) -> bool { self[..] == other[..] } + #[inline] + fn ne(&self, other: &$rhs) -> bool { self[..] != other[..] } + } + } +} + +__impl_slice_eq1! { [A1: Allocator, A2: Allocator] Vec<T, A1>, Vec<U, A2>, #[stable(feature = "rust1", since = "1.0.0")] } +__impl_slice_eq1! { [A: Allocator] Vec<T, A>, &[U], #[stable(feature = "rust1", since = "1.0.0")] } +__impl_slice_eq1! { [A: Allocator] Vec<T, A>, &mut [U], #[stable(feature = "rust1", since = "1.0.0")] } +__impl_slice_eq1! { [A: Allocator] &[T], Vec<U, A>, #[stable(feature = "partialeq_vec_for_ref_slice", since = "1.46.0")] } +__impl_slice_eq1! { [A: Allocator] &mut [T], Vec<U, A>, #[stable(feature = "partialeq_vec_for_ref_slice", since = "1.46.0")] } +__impl_slice_eq1! { [A: Allocator] Vec<T, A>, [U], #[stable(feature = "partialeq_vec_for_slice", since = "1.48.0")] } +__impl_slice_eq1! { [A: Allocator] [T], Vec<U, A>, #[stable(feature = "partialeq_vec_for_slice", since = "1.48.0")] } +#[cfg(not(no_global_oom_handling))] +__impl_slice_eq1! { [A: Allocator] Cow<'_, [T]>, Vec<U, A> where T: Clone, #[stable(feature = "rust1", since = "1.0.0")] } +#[cfg(not(no_global_oom_handling))] +__impl_slice_eq1! { [] Cow<'_, [T]>, &[U] where T: Clone, #[stable(feature = "rust1", since = "1.0.0")] } +#[cfg(not(no_global_oom_handling))] +__impl_slice_eq1! { [] Cow<'_, [T]>, &mut [U] where T: Clone, #[stable(feature = "rust1", since = "1.0.0")] } +__impl_slice_eq1! { [A: Allocator, const N: usize] Vec<T, A>, [U; N], #[stable(feature = "rust1", since = "1.0.0")] } +__impl_slice_eq1! { [A: Allocator, const N: usize] Vec<T, A>, &[U; N], #[stable(feature = "rust1", since = "1.0.0")] } + +// NOTE: some less important impls are omitted to reduce code bloat +// FIXME(Centril): Reconsider this? +//__impl_slice_eq1! { [const N: usize] Vec<A>, &mut [B; N], } +//__impl_slice_eq1! { [const N: usize] [A; N], Vec<B>, } +//__impl_slice_eq1! { [const N: usize] &[A; N], Vec<B>, } +//__impl_slice_eq1! { [const N: usize] &mut [A; N], Vec<B>, } +//__impl_slice_eq1! { [const N: usize] Cow<'a, [A]>, [B; N], } +//__impl_slice_eq1! { [const N: usize] Cow<'a, [A]>, &[B; N], } +//__impl_slice_eq1! { [const N: usize] Cow<'a, [A]>, &mut [B; N], } diff --git a/rust/bindgen_parameters b/rust/bindgen_parameters new file mode 100644 index 000000000000..be4963bf7203 --- /dev/null +++ b/rust/bindgen_parameters @@ -0,0 +1,21 @@ +# SPDX-License-Identifier: GPL-2.0 + +--opaque-type xregs_state +--opaque-type desc_struct +--opaque-type arch_lbr_state +--opaque-type local_apic + +# Packed type cannot transitively contain a `#[repr(align)]` type. +--opaque-type x86_msi_data +--opaque-type x86_msi_addr_lo + +# `try` is a reserved keyword since Rust 2018; solved in `bindgen` v0.59.2, +# commit 2aed6b021680 ("context: Escape the try keyword properly"). +--opaque-type kunit_try_catch + +# If SMP is disabled, `arch_spinlock_t` is defined as a ZST which triggers a Rust +# warning. We don't need to peek into it anyway. +--opaque-type spinlock + +# `seccomp`'s comment gets understood as a doctest +--no-doc-comments diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h new file mode 100644 index 000000000000..c48bc284214a --- /dev/null +++ b/rust/bindings/bindings_helper.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Header that contains the code (mostly headers) for which Rust bindings + * will be automatically generated by `bindgen`. + * + * Sorted alphabetically. + */ + +#include <linux/slab.h> + +/* `bindgen` gets confused at certain things. */ +const gfp_t BINDINGS_GFP_KERNEL = GFP_KERNEL; +const gfp_t BINDINGS___GFP_ZERO = __GFP_ZERO; diff --git a/rust/bindings/lib.rs b/rust/bindings/lib.rs new file mode 100644 index 000000000000..6c50ee62c56b --- /dev/null +++ b/rust/bindings/lib.rs @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Bindings. +//! +//! Imports the generated bindings by `bindgen`. +//! +//! This crate may not be directly used. If you need a kernel C API that is +//! not ported or wrapped in the `kernel` crate, then do so first instead of +//! using this crate. + +#![no_std] +#![feature(core_ffi_c)] +// See <https://github.com/rust-lang/rust-bindgen/issues/1651>. +#![cfg_attr(test, allow(deref_nullptr))] +#![cfg_attr(test, allow(unaligned_references))] +#![cfg_attr(test, allow(unsafe_op_in_unsafe_fn))] +#![allow( + clippy::all, + missing_docs, + non_camel_case_types, + non_upper_case_globals, + non_snake_case, + improper_ctypes, + unreachable_pub, + unsafe_op_in_unsafe_fn +)] + +mod bindings_raw { + // Use glob import here to expose all helpers. + // Symbols defined within the module will take precedence to the glob import. + pub use super::bindings_helper::*; + include!(concat!( + env!("OBJTREE"), + "/rust/bindings/bindings_generated.rs" + )); +} + +// When both a directly exposed symbol and a helper exists for the same function, +// the directly exposed symbol is preferred and the helper becomes dead code, so +// ignore the warning here. +#[allow(dead_code)] +mod bindings_helper { + // Import the generated bindings for types. + include!(concat!( + env!("OBJTREE"), + "/rust/bindings/bindings_helpers_generated.rs" + )); +} + +pub use bindings_raw::*; + +pub const GFP_KERNEL: gfp_t = BINDINGS_GFP_KERNEL; +pub const __GFP_ZERO: gfp_t = BINDINGS___GFP_ZERO; diff --git a/rust/compiler_builtins.rs b/rust/compiler_builtins.rs new file mode 100644 index 000000000000..f8f39a3e6855 --- /dev/null +++ b/rust/compiler_builtins.rs @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Our own `compiler_builtins`. +//! +//! Rust provides [`compiler_builtins`] as a port of LLVM's [`compiler-rt`]. +//! Since we do not need the vast majority of them, we avoid the dependency +//! by providing this file. +//! +//! At the moment, some builtins are required that should not be. For instance, +//! [`core`] has 128-bit integers functionality which we should not be compiling +//! in. We will work with upstream [`core`] to provide feature flags to disable +//! the parts we do not need. For the moment, we define them to [`panic!`] at +//! runtime for simplicity to catch mistakes, instead of performing surgery +//! on `core.o`. +//! +//! In any case, all these symbols are weakened to ensure we do not override +//! those that may be provided by the rest of the kernel. +//! +//! [`compiler_builtins`]: https://github.com/rust-lang/compiler-builtins +//! [`compiler-rt`]: https://compiler-rt.llvm.org/ + +#![feature(compiler_builtins)] +#![compiler_builtins] +#![no_builtins] +#![no_std] + +macro_rules! define_panicking_intrinsics( + ($reason: tt, { $($ident: ident, )* }) => { + $( + #[doc(hidden)] + #[no_mangle] + pub extern "C" fn $ident() { + panic!($reason); + } + )* + } +); + +define_panicking_intrinsics!("`f32` should not be used", { + __eqsf2, + __gesf2, + __lesf2, + __nesf2, + __unordsf2, +}); + +define_panicking_intrinsics!("`f64` should not be used", { + __unorddf2, +}); + +define_panicking_intrinsics!("`i128` should not be used", { + __ashrti3, + __muloti4, + __multi3, +}); + +define_panicking_intrinsics!("`u128` should not be used", { + __ashlti3, + __lshrti3, + __udivmodti4, + __udivti3, + __umodti3, +}); diff --git a/rust/exports.c b/rust/exports.c new file mode 100644 index 000000000000..bb7cc64cecd0 --- /dev/null +++ b/rust/exports.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * A hack to export Rust symbols for loadable modules without having to redo + * the entire `include/linux/export.h` logic in Rust. + * + * This requires the Rust's new/future `v0` mangling scheme because the default + * one ("legacy") uses invalid characters for C identifiers (thus we cannot use + * the `EXPORT_SYMBOL_*` macros). + * + * All symbols are exported as GPL-only to guarantee no GPL-only feature is + * accidentally exposed. + */ + +#include <linux/module.h> + +#define EXPORT_SYMBOL_RUST_GPL(sym) extern int sym; EXPORT_SYMBOL_GPL(sym) + +#include "exports_core_generated.h" +#include "exports_alloc_generated.h" +#include "exports_bindings_generated.h" +#include "exports_kernel_generated.h" diff --git a/rust/helpers.c b/rust/helpers.c new file mode 100644 index 000000000000..b4f15eee2ffd --- /dev/null +++ b/rust/helpers.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Non-trivial C macros cannot be used in Rust. Similarly, inlined C functions + * cannot be called either. This file explicitly creates functions ("helpers") + * that wrap those so that they can be called from Rust. + * + * Even though Rust kernel modules should never use directly the bindings, some + * of these helpers need to be exported because Rust generics and inlined + * functions may not get their code generated in the crate where they are + * defined. Other helpers, called from non-inline functions, may not be + * exported, in principle. However, in general, the Rust compiler does not + * guarantee codegen will be performed for a non-inline function either. + * Therefore, this file exports all the helpers. In the future, this may be + * revisited to reduce the number of exports after the compiler is informed + * about the places codegen is required. + * + * All symbols are exported as GPL-only to guarantee no GPL-only feature is + * accidentally exposed. + */ + +#include <linux/bug.h> +#include <linux/build_bug.h> + +__noreturn void rust_helper_BUG(void) +{ + BUG(); +} +EXPORT_SYMBOL_GPL(rust_helper_BUG); + +/* + * We use `bindgen`'s `--size_t-is-usize` option to bind the C `size_t` type + * as the Rust `usize` type, so we can use it in contexts where Rust + * expects a `usize` like slice (array) indices. `usize` is defined to be + * the same as C's `uintptr_t` type (can hold any pointer) but not + * necessarily the same as `size_t` (can hold the size of any single + * object). Most modern platforms use the same concrete integer type for + * both of them, but in case we find ourselves on a platform where + * that's not true, fail early instead of risking ABI or + * integer-overflow issues. + * + * If your platform fails this assertion, it means that you are in + * danger of integer-overflow bugs (even if you attempt to remove + * `--size_t-is-usize`). It may be easiest to change the kernel ABI on + * your platform such that `size_t` matches `uintptr_t` (i.e., to increase + * `size_t`, because `uintptr_t` has to be at least as big as `size_t`). + */ +static_assert( + sizeof(size_t) == sizeof(uintptr_t) && + __alignof__(size_t) == __alignof__(uintptr_t), + "Rust code expects C `size_t` to match Rust `usize`" +); diff --git a/rust/kernel/allocator.rs b/rust/kernel/allocator.rs new file mode 100644 index 000000000000..397a3dd57a9b --- /dev/null +++ b/rust/kernel/allocator.rs @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Allocator support. + +use core::alloc::{GlobalAlloc, Layout}; +use core::ptr; + +use crate::bindings; + +struct KernelAllocator; + +unsafe impl GlobalAlloc for KernelAllocator { + unsafe fn alloc(&self, layout: Layout) -> *mut u8 { + // `krealloc()` is used instead of `kmalloc()` because the latter is + // an inline function and cannot be bound to as a result. + unsafe { bindings::krealloc(ptr::null(), layout.size(), bindings::GFP_KERNEL) as *mut u8 } + } + + unsafe fn dealloc(&self, ptr: *mut u8, _layout: Layout) { + unsafe { + bindings::kfree(ptr as *const core::ffi::c_void); + } + } +} + +#[global_allocator] +static ALLOCATOR: KernelAllocator = KernelAllocator; + +// `rustc` only generates these for some crate types. Even then, we would need +// to extract the object file that has them from the archive. For the moment, +// let's generate them ourselves instead. +// +// Note that `#[no_mangle]` implies exported too, nowadays. +#[no_mangle] +fn __rust_alloc(size: usize, _align: usize) -> *mut u8 { + unsafe { bindings::krealloc(core::ptr::null(), size, bindings::GFP_KERNEL) as *mut u8 } +} + +#[no_mangle] +fn __rust_dealloc(ptr: *mut u8, _size: usize, _align: usize) { + unsafe { bindings::kfree(ptr as *const core::ffi::c_void) }; +} + +#[no_mangle] +fn __rust_realloc(ptr: *mut u8, _old_size: usize, _align: usize, new_size: usize) -> *mut u8 { + unsafe { + bindings::krealloc( + ptr as *const core::ffi::c_void, + new_size, + bindings::GFP_KERNEL, + ) as *mut u8 + } +} + +#[no_mangle] +fn __rust_alloc_zeroed(size: usize, _align: usize) -> *mut u8 { + unsafe { + bindings::krealloc( + core::ptr::null(), + size, + bindings::GFP_KERNEL | bindings::__GFP_ZERO, + ) as *mut u8 + } +} diff --git a/rust/kernel/error.rs b/rust/kernel/error.rs new file mode 100644 index 000000000000..466b2a8fe569 --- /dev/null +++ b/rust/kernel/error.rs @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Kernel errors. +//! +//! C header: [`include/uapi/asm-generic/errno-base.h`](../../../include/uapi/asm-generic/errno-base.h) + +use alloc::collections::TryReserveError; + +/// Contains the C-compatible error codes. +pub mod code { + /// Out of memory. + pub const ENOMEM: super::Error = super::Error(-(crate::bindings::ENOMEM as i32)); +} + +/// Generic integer kernel error. +/// +/// The kernel defines a set of integer generic error codes based on C and +/// POSIX ones. These codes may have a more specific meaning in some contexts. +/// +/// # Invariants +/// +/// The value is a valid `errno` (i.e. `>= -MAX_ERRNO && < 0`). +#[derive(Clone, Copy, PartialEq, Eq)] +pub struct Error(core::ffi::c_int); + +impl Error { + /// Returns the kernel error code. + pub fn to_kernel_errno(self) -> core::ffi::c_int { + self.0 + } +} + +impl From<TryReserveError> for Error { + fn from(_: TryReserveError) -> Error { + code::ENOMEM + } +} + +/// A [`Result`] with an [`Error`] error type. +/// +/// To be used as the return type for functions that may fail. +/// +/// # Error codes in C and Rust +/// +/// In C, it is common that functions indicate success or failure through +/// their return value; modifying or returning extra data through non-`const` +/// pointer parameters. In particular, in the kernel, functions that may fail +/// typically return an `int` that represents a generic error code. We model +/// those as [`Error`]. +/// +/// In Rust, it is idiomatic to model functions that may fail as returning +/// a [`Result`]. Since in the kernel many functions return an error code, +/// [`Result`] is a type alias for a [`core::result::Result`] that uses +/// [`Error`] as its error type. +/// +/// Note that even if a function does not return anything when it succeeds, +/// it should still be modeled as returning a `Result` rather than +/// just an [`Error`]. +pub type Result<T = ()> = core::result::Result<T, Error>; diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs new file mode 100644 index 000000000000..abd46261d385 --- /dev/null +++ b/rust/kernel/lib.rs @@ -0,0 +1,78 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! The `kernel` crate. +//! +//! This crate contains the kernel APIs that have been ported or wrapped for +//! usage by Rust code in the kernel and is shared by all of them. +//! +//! In other words, all the rest of the Rust code in the kernel (e.g. kernel +//! modules written in Rust) depends on [`core`], [`alloc`] and this crate. +//! +//! If you need a kernel C API that is not ported or wrapped yet here, then +//! do so first instead of bypassing this crate. + +#![no_std] +#![feature(core_ffi_c)] + +// Ensure conditional compilation based on the kernel configuration works; +// otherwise we may silently break things like initcall handling. +#[cfg(not(CONFIG_RUST))] +compile_error!("Missing kernel configuration for conditional compilation"); + +#[cfg(not(test))] +#[cfg(not(testlib))] +mod allocator; +pub mod error; +pub mod prelude; +pub mod print; +pub mod str; + +#[doc(hidden)] +pub use bindings; +pub use macros; + +/// Prefix to appear before log messages printed from within the `kernel` crate. +const __LOG_PREFIX: &[u8] = b"rust_kernel\0"; + +/// The top level entrypoint to implementing a kernel module. +/// +/// For any teardown or cleanup operations, your type may implement [`Drop`]. +pub trait Module: Sized + Sync { + /// Called at module initialization time. + /// + /// Use this method to perform whatever setup or registration your module + /// should do. + /// + /// Equivalent to the `module_init` macro in the C API. + fn init(module: &'static ThisModule) -> error::Result<Self>; +} + +/// Equivalent to `THIS_MODULE` in the C API. +/// +/// C header: `include/linux/export.h` +pub struct ThisModule(*mut bindings::module); + +// SAFETY: `THIS_MODULE` may be used from all threads within a module. +unsafe impl Sync for ThisModule {} + +impl ThisModule { + /// Creates a [`ThisModule`] given the `THIS_MODULE` pointer. + /// + /// # Safety + /// + /// The pointer must be equal to the right `THIS_MODULE`. + pub const unsafe fn from_ptr(ptr: *mut bindings::module) -> ThisModule { + ThisModule(ptr) + } +} + +#[cfg(not(any(testlib, test)))] +#[panic_handler] +fn panic(info: &core::panic::PanicInfo<'_>) -> ! { + pr_emerg!("{}\n", info); + // SAFETY: FFI call. + unsafe { bindings::BUG() }; + // Bindgen currently does not recognize `__noreturn` so `BUG` returns `()` + // instead of `!`. See <https://github.com/rust-lang/rust-bindgen/issues/2094>. + loop {} +} diff --git a/rust/kernel/prelude.rs b/rust/kernel/prelude.rs new file mode 100644 index 000000000000..495e22250726 --- /dev/null +++ b/rust/kernel/prelude.rs @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! The `kernel` prelude. +//! +//! These are the most common items used by Rust code in the kernel, +//! intended to be imported by all Rust code, for convenience. +//! +//! # Examples +//! +//! ``` +//! use kernel::prelude::*; +//! ``` + +pub use super::{ + error::{Error, Result}, + pr_emerg, pr_info, ThisModule, +}; +pub use alloc::{boxed::Box, vec::Vec}; +pub use core::pin::Pin; +pub use macros::module; diff --git a/rust/kernel/print.rs b/rust/kernel/print.rs new file mode 100644 index 000000000000..55db5a1ba752 --- /dev/null +++ b/rust/kernel/print.rs @@ -0,0 +1,198 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Printing facilities. +//! +//! C header: [`include/linux/printk.h`](../../../../include/linux/printk.h) +//! +//! Reference: <https://www.kernel.org/doc/html/latest/core-api/printk-basics.html> + +use core::{ + ffi::{c_char, c_void}, + fmt, +}; + +use crate::str::RawFormatter; + +#[cfg(CONFIG_PRINTK)] +use crate::bindings; + +// Called from `vsprintf` with format specifier `%pA`. +#[no_mangle] +unsafe fn rust_fmt_argument(buf: *mut c_char, end: *mut c_char, ptr: *const c_void) -> *mut c_char { + use fmt::Write; + // SAFETY: The C contract guarantees that `buf` is valid if it's less than `end`. + let mut w = unsafe { RawFormatter::from_ptrs(buf.cast(), end.cast()) }; + let _ = w.write_fmt(unsafe { *(ptr as *const fmt::Arguments<'_>) }); + w.pos().cast() +} + +/// Format strings. +/// +/// Public but hidden since it should only be used from public macros. +#[doc(hidden)] +pub mod format_strings { + use crate::bindings; + + /// The length we copy from the `KERN_*` kernel prefixes. + const LENGTH_PREFIX: usize = 2; + + /// The length of the fixed format strings. + pub const LENGTH: usize = 10; + + /// Generates a fixed format string for the kernel's [`_printk`]. + /// + /// The format string is always the same for a given level, i.e. for a + /// given `prefix`, which are the kernel's `KERN_*` constants. + /// + /// [`_printk`]: ../../../../include/linux/printk.h + const fn generate(is_cont: bool, prefix: &[u8; 3]) -> [u8; LENGTH] { + // Ensure the `KERN_*` macros are what we expect. + assert!(prefix[0] == b'\x01'); + if is_cont { + assert!(prefix[1] == b'c'); + } else { + assert!(prefix[1] >= b'0' && prefix[1] <= b'7'); + } + assert!(prefix[2] == b'\x00'); + + let suffix: &[u8; LENGTH - LENGTH_PREFIX] = if is_cont { + b"%pA\0\0\0\0\0" + } else { + b"%s: %pA\0" + }; + + [ + prefix[0], prefix[1], suffix[0], suffix[1], suffix[2], suffix[3], suffix[4], suffix[5], + suffix[6], suffix[7], + ] + } + + // Generate the format strings at compile-time. + // + // This avoids the compiler generating the contents on the fly in the stack. + // + // Furthermore, `static` instead of `const` is used to share the strings + // for all the kernel. + pub static EMERG: [u8; LENGTH] = generate(false, bindings::KERN_EMERG); + pub static INFO: [u8; LENGTH] = generate(false, bindings::KERN_INFO); +} + +/// Prints a message via the kernel's [`_printk`]. +/// +/// Public but hidden since it should only be used from public macros. +/// +/// # Safety +/// +/// The format string must be one of the ones in [`format_strings`], and +/// the module name must be null-terminated. +/// +/// [`_printk`]: ../../../../include/linux/_printk.h +#[doc(hidden)] +#[cfg_attr(not(CONFIG_PRINTK), allow(unused_variables))] +pub unsafe fn call_printk( + format_string: &[u8; format_strings::LENGTH], + module_name: &[u8], + args: fmt::Arguments<'_>, +) { + // `_printk` does not seem to fail in any path. + #[cfg(CONFIG_PRINTK)] + unsafe { + bindings::_printk( + format_string.as_ptr() as _, + module_name.as_ptr(), + &args as *const _ as *const c_void, + ); + } +} + +/// Performs formatting and forwards the string to [`call_printk`]. +/// +/// Public but hidden since it should only be used from public macros. +#[doc(hidden)] +#[cfg(not(testlib))] +#[macro_export] +#[allow(clippy::crate_in_macro_def)] +macro_rules! print_macro ( + // The non-continuation cases (most of them, e.g. `INFO`). + ($format_string:path, $($arg:tt)+) => ( + // SAFETY: This hidden macro should only be called by the documented + // printing macros which ensure the format string is one of the fixed + // ones. All `__LOG_PREFIX`s are null-terminated as they are generated + // by the `module!` proc macro or fixed values defined in a kernel + // crate. + unsafe { + $crate::print::call_printk( + &$format_string, + crate::__LOG_PREFIX, + format_args!($($arg)+), + ); + } + ); +); + +/// Stub for doctests +#[cfg(testlib)] +#[macro_export] +macro_rules! print_macro ( + ($format_string:path, $e:expr, $($arg:tt)+) => ( + () + ); +); + +// We could use a macro to generate these macros. However, doing so ends +// up being a bit ugly: it requires the dollar token trick to escape `$` as +// well as playing with the `doc` attribute. Furthermore, they cannot be easily +// imported in the prelude due to [1]. So, for the moment, we just write them +// manually, like in the C side; while keeping most of the logic in another +// macro, i.e. [`print_macro`]. +// +// [1]: https://github.com/rust-lang/rust/issues/52234 + +/// Prints an emergency-level message (level 0). +/// +/// Use this level if the system is unusable. +/// +/// Equivalent to the kernel's [`pr_emerg`] macro. +/// +/// Mimics the interface of [`std::print!`]. See [`core::fmt`] and +/// `alloc::format!` for information about the formatting syntax. +/// +/// [`pr_emerg`]: https://www.kernel.org/doc/html/latest/core-api/printk-basics.html#c.pr_emerg +/// [`std::print!`]: https://doc.rust-lang.org/std/macro.print.html +/// +/// # Examples +/// +/// ``` +/// pr_emerg!("hello {}\n", "there"); +/// ``` +#[macro_export] +macro_rules! pr_emerg ( + ($($arg:tt)*) => ( + $crate::print_macro!($crate::print::format_strings::EMERG, $($arg)*) + ) +); + +/// Prints an info-level message (level 6). +/// +/// Use this level for informational messages. +/// +/// Equivalent to the kernel's [`pr_info`] macro. +/// +/// Mimics the interface of [`std::print!`]. See [`core::fmt`] and +/// `alloc::format!` for information about the formatting syntax. +/// +/// [`pr_info`]: https://www.kernel.org/doc/html/latest/core-api/printk-basics.html#c.pr_info +/// [`std::print!`]: https://doc.rust-lang.org/std/macro.print.html +/// +/// # Examples +/// +/// ``` +/// pr_info!("hello {}\n", "there"); +/// ``` +#[macro_export] +#[doc(alias = "print")] +macro_rules! pr_info ( + ($($arg:tt)*) => ( + $crate::print_macro!($crate::print::format_strings::INFO, $($arg)*) + ) +); diff --git a/rust/kernel/str.rs b/rust/kernel/str.rs new file mode 100644 index 000000000000..e45ff220ae50 --- /dev/null +++ b/rust/kernel/str.rs @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! String representations. + +use core::fmt; + +/// Allows formatting of [`fmt::Arguments`] into a raw buffer. +/// +/// It does not fail if callers write past the end of the buffer so that they can calculate the +/// size required to fit everything. +/// +/// # Invariants +/// +/// The memory region between `pos` (inclusive) and `end` (exclusive) is valid for writes if `pos` +/// 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 the given buffer pointers. + /// + /// # Safety + /// + /// If `pos` is less than `end`, then the region between `pos` (inclusive) and `end` + /// (exclusive) must be valid for writes for the lifetime of the returned [`RawFormatter`]. + pub(crate) unsafe fn from_ptrs(pos: *mut u8, end: *mut u8) -> Self { + // INVARIANT: The safety requierments guarantee the type invariants. + Self { + beg: pos as _, + pos: pos as _, + end: end as _, + } + } + + /// Returns the current insert position. + /// + /// N.B. It may point to invalid memory. + pub(crate) fn pos(&self) -> *mut u8 { + self.pos as _ + } +} + +impl fmt::Write for RawFormatter { + fn write_str(&mut self, s: &str) -> fmt::Result { + // `pos` value after writing `len` bytes. This does not have to be bounded by `end`, but we + // don't want it to wrap around to 0. + let pos_new = self.pos.saturating_add(s.len()); + + // Amount that we can copy. `saturating_sub` ensures we get 0 if `pos` goes past `end`. + let len_to_copy = core::cmp::min(pos_new, self.end).saturating_sub(self.pos); + + if len_to_copy > 0 { + // SAFETY: If `len_to_copy` is non-zero, then we know `pos` has not gone past `end` + // yet, so it is valid for write per the type invariants. + unsafe { + core::ptr::copy_nonoverlapping( + s.as_bytes().as_ptr(), + self.pos as *mut u8, + len_to_copy, + ) + }; + } + + self.pos = pos_new; + Ok(()) + } +} diff --git a/rust/macros/helpers.rs b/rust/macros/helpers.rs new file mode 100644 index 000000000000..cdc7dc6135d2 --- /dev/null +++ b/rust/macros/helpers.rs @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 + +use proc_macro::{token_stream, TokenTree}; + +pub(crate) fn try_ident(it: &mut token_stream::IntoIter) -> Option<String> { + if let Some(TokenTree::Ident(ident)) = it.next() { + Some(ident.to_string()) + } else { + None + } +} + +pub(crate) fn try_literal(it: &mut token_stream::IntoIter) -> Option<String> { + if let Some(TokenTree::Literal(literal)) = it.next() { + Some(literal.to_string()) + } else { + None + } +} + +pub(crate) fn try_byte_string(it: &mut token_stream::IntoIter) -> Option<String> { + try_literal(it).and_then(|byte_string| { + if byte_string.starts_with("b\"") && byte_string.ends_with('\"') { + Some(byte_string[2..byte_string.len() - 1].to_string()) + } else { + None + } + }) +} + +pub(crate) fn expect_ident(it: &mut token_stream::IntoIter) -> String { + try_ident(it).expect("Expected Ident") +} + +pub(crate) fn expect_punct(it: &mut token_stream::IntoIter) -> char { + if let TokenTree::Punct(punct) = it.next().expect("Reached end of token stream for Punct") { + punct.as_char() + } else { + panic!("Expected Punct"); + } +} + +pub(crate) fn expect_byte_string(it: &mut token_stream::IntoIter) -> String { + try_byte_string(it).expect("Expected byte string") +} + +pub(crate) fn expect_end(it: &mut token_stream::IntoIter) { + if it.next().is_some() { + panic!("Expected end"); + } +} diff --git a/rust/macros/lib.rs b/rust/macros/lib.rs new file mode 100644 index 000000000000..91764bfb1f89 --- /dev/null +++ b/rust/macros/lib.rs @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Crate for all kernel procedural macros. + +mod helpers; +mod module; + +use proc_macro::TokenStream; + +/// Declares a kernel module. +/// +/// The `type` argument should be a type which implements the [`Module`] +/// trait. Also accepts various forms of kernel metadata. +/// +/// C header: [`include/linux/moduleparam.h`](../../../include/linux/moduleparam.h) +/// +/// [`Module`]: ../kernel/trait.Module.html +/// +/// # Examples +/// +/// ```ignore +/// use kernel::prelude::*; +/// +/// module!{ +/// type: MyModule, +/// name: b"my_kernel_module", +/// author: b"Rust for Linux Contributors", +/// description: b"My very own kernel module!", +/// license: b"GPL", +/// params: { +/// my_i32: i32 { +/// default: 42, +/// permissions: 0o000, +/// description: b"Example of i32", +/// }, +/// writeable_i32: i32 { +/// default: 42, +/// permissions: 0o644, +/// description: b"Example of i32", +/// }, +/// }, +/// } +/// +/// struct MyModule; +/// +/// impl kernel::Module for MyModule { +/// fn init() -> Result<Self> { +/// // If the parameter is writeable, then the kparam lock must be +/// // taken to read the parameter: +/// { +/// let lock = THIS_MODULE.kernel_param_lock(); +/// pr_info!("i32 param is: {}\n", writeable_i32.read(&lock)); +/// } +/// // If the parameter is read only, it can be read without locking +/// // the kernel parameters: +/// pr_info!("i32 param is: {}\n", my_i32.read()); +/// Ok(Self) +/// } +/// } +/// ``` +/// +/// # Supported argument types +/// - `type`: type which implements the [`Module`] trait (required). +/// - `name`: byte array of the name of the kernel module (required). +/// - `author`: byte array of the author of the kernel module. +/// - `description`: byte array of the description of the kernel module. +/// - `license`: byte array of the license of the kernel module (required). +/// - `alias`: byte array of alias name of the kernel module. +#[proc_macro] +pub fn module(ts: TokenStream) -> TokenStream { + module::module(ts) +} diff --git a/rust/macros/module.rs b/rust/macros/module.rs new file mode 100644 index 000000000000..186a5b8be23c --- /dev/null +++ b/rust/macros/module.rs @@ -0,0 +1,282 @@ +// SPDX-License-Identifier: GPL-2.0 + +use crate::helpers::*; +use proc_macro::{token_stream, Literal, TokenStream, TokenTree}; +use std::fmt::Write; + +struct ModInfoBuilder<'a> { + module: &'a str, + counter: usize, + buffer: String, +} + +impl<'a> ModInfoBuilder<'a> { + fn new(module: &'a str) -> Self { + ModInfoBuilder { + module, + counter: 0, + buffer: String::new(), + } + } + + fn emit_base(&mut self, field: &str, content: &str, builtin: bool) { + let string = if builtin { + // Built-in modules prefix their modinfo strings by `module.`. + format!( + "{module}.{field}={content}\0", + module = self.module, + field = field, + content = content + ) + } else { + // Loadable modules' modinfo strings go as-is. + format!("{field}={content}\0", field = field, content = content) + }; + + write!( + &mut self.buffer, + " + {cfg} + #[doc(hidden)] + #[link_section = \".modinfo\"] + #[used] + pub static __{module}_{counter}: [u8; {length}] = *{string}; + ", + cfg = if builtin { + "#[cfg(not(MODULE))]" + } else { + "#[cfg(MODULE)]" + }, + module = self.module.to_uppercase(), + counter = self.counter, + length = string.len(), + string = Literal::byte_string(string.as_bytes()), + ) + .unwrap(); + + self.counter += 1; + } + + fn emit_only_builtin(&mut self, field: &str, content: &str) { + self.emit_base(field, content, true) + } + + fn emit_only_loadable(&mut self, field: &str, content: &str) { + self.emit_base(field, content, false) + } + + fn emit(&mut self, field: &str, content: &str) { + self.emit_only_builtin(field, content); + self.emit_only_loadable(field, content); + } +} + +#[derive(Debug, Default)] +struct ModuleInfo { + type_: String, + license: String, + name: String, + author: Option<String>, + description: Option<String>, + alias: Option<String>, +} + +impl ModuleInfo { + fn parse(it: &mut token_stream::IntoIter) -> Self { + let mut info = ModuleInfo::default(); + + const EXPECTED_KEYS: &[&str] = + &["type", "name", "author", "description", "license", "alias"]; + const REQUIRED_KEYS: &[&str] = &["type", "name", "license"]; + let mut seen_keys = Vec::new(); + + loop { + let key = match it.next() { + Some(TokenTree::Ident(ident)) => ident.to_string(), + Some(_) => panic!("Expected Ident or end"), + None => break, + }; + + if seen_keys.contains(&key) { + panic!( + "Duplicated key \"{}\". Keys can only be specified once.", + key + ); + } + + assert_eq!(expect_punct(it), ':'); + + match key.as_str() { + "type" => info.type_ = expect_ident(it), + "name" => info.name = expect_byte_string(it), + "author" => info.author = Some(expect_byte_string(it)), + "description" => info.description = Some(expect_byte_string(it)), + "license" => info.license = expect_byte_string(it), + "alias" => info.alias = Some(expect_byte_string(it)), + _ => panic!( + "Unknown key \"{}\". Valid keys are: {:?}.", + key, EXPECTED_KEYS + ), + } + + assert_eq!(expect_punct(it), ','); + + seen_keys.push(key); + } + + expect_end(it); + + for key in REQUIRED_KEYS { + if !seen_keys.iter().any(|e| e == key) { + panic!("Missing required key \"{}\".", key); + } + } + + let mut ordered_keys: Vec<&str> = Vec::new(); + for key in EXPECTED_KEYS { + if seen_keys.iter().any(|e| e == key) { + ordered_keys.push(key); + } + } + + if seen_keys != ordered_keys { + panic!( + "Keys are not ordered as expected. Order them like: {:?}.", + ordered_keys + ); + } + + info + } +} + +pub(crate) fn module(ts: TokenStream) -> TokenStream { + let mut it = ts.into_iter(); + + let info = ModuleInfo::parse(&mut it); + + let mut modinfo = ModInfoBuilder::new(info.name.as_ref()); + if let Some(author) = info.author { + modinfo.emit("author", &author); + } + if let Some(description) = info.description { + modinfo.emit("description", &description); + } + modinfo.emit("license", &info.license); + if let Some(alias) = info.alias { + modinfo.emit("alias", &alias); + } + + // Built-in modules also export the `file` modinfo string. + let file = + std::env::var("RUST_MODFILE").expect("Unable to fetch RUST_MODFILE environmental variable"); + modinfo.emit_only_builtin("file", &file); + + format!( + " + /// The module name. + /// + /// Used by the printing macros, e.g. [`info!`]. + const __LOG_PREFIX: &[u8] = b\"{name}\\0\"; + + /// The \"Rust loadable module\" mark, for `scripts/is_rust_module.sh`. + // + // This may be best done another way later on, e.g. as a new modinfo + // key or a new section. For the moment, keep it simple. + #[cfg(MODULE)] + #[doc(hidden)] + #[used] + static __IS_RUST_MODULE: () = (); + + static mut __MOD: Option<{type_}> = None; + + // SAFETY: `__this_module` is constructed by the kernel at load time and will not be + // freed until the module is unloaded. + #[cfg(MODULE)] + static THIS_MODULE: kernel::ThisModule = unsafe {{ + kernel::ThisModule::from_ptr(&kernel::bindings::__this_module as *const _ as *mut _) + }}; + #[cfg(not(MODULE))] + static THIS_MODULE: kernel::ThisModule = unsafe {{ + kernel::ThisModule::from_ptr(core::ptr::null_mut()) + }}; + + // Loadable modules need to export the `{{init,cleanup}}_module` identifiers. + #[cfg(MODULE)] + #[doc(hidden)] + #[no_mangle] + pub extern \"C\" fn init_module() -> core::ffi::c_int {{ + __init() + }} + + #[cfg(MODULE)] + #[doc(hidden)] + #[no_mangle] + pub extern \"C\" fn cleanup_module() {{ + __exit() + }} + + // Built-in modules are initialized through an initcall pointer + // and the identifiers need to be unique. + #[cfg(not(MODULE))] + #[cfg(not(CONFIG_HAVE_ARCH_PREL32_RELOCATIONS))] + #[doc(hidden)] + #[link_section = \"{initcall_section}\"] + #[used] + pub static __{name}_initcall: extern \"C\" fn() -> core::ffi::c_int = __{name}_init; + + #[cfg(not(MODULE))] + #[cfg(CONFIG_HAVE_ARCH_PREL32_RELOCATIONS)] + core::arch::global_asm!( + r#\".section \"{initcall_section}\", \"a\" + __{name}_initcall: + .long __{name}_init - . + .previous + \"# + ); + + #[cfg(not(MODULE))] + #[doc(hidden)] + #[no_mangle] + pub extern \"C\" fn __{name}_init() -> core::ffi::c_int {{ + __init() + }} + + #[cfg(not(MODULE))] + #[doc(hidden)] + #[no_mangle] + pub extern \"C\" fn __{name}_exit() {{ + __exit() + }} + + fn __init() -> core::ffi::c_int {{ + match <{type_} as kernel::Module>::init(&THIS_MODULE) {{ + Ok(m) => {{ + unsafe {{ + __MOD = Some(m); + }} + return 0; + }} + Err(e) => {{ + return e.to_kernel_errno(); + }} + }} + }} + + fn __exit() {{ + unsafe {{ + // Invokes `drop()` on `__MOD`, which should be used for cleanup. + __MOD = None; + }} + }} + + {modinfo} + ", + type_ = info.type_, + name = info.name, + modinfo = modinfo.buffer, + initcall_section = ".initcall6.init" + ) + .parse() + .expect("Error parsing formatted string into token stream.") +} diff --git a/samples/Kconfig b/samples/Kconfig index 470ee3baf2e1..0d81c00289ee 100644 --- a/samples/Kconfig +++ b/samples/Kconfig @@ -263,6 +263,8 @@ config SAMPLE_CORESIGHT_SYSCFG This demonstrates how a user may create their own CoreSight configurations and easily load them into the system at runtime. +source "samples/rust/Kconfig" + endif # SAMPLES config HAVE_SAMPLE_FTRACE_DIRECT diff --git a/samples/Makefile b/samples/Makefile index 701e912ab5af..9832ef3f8fcb 100644 --- a/samples/Makefile +++ b/samples/Makefile @@ -35,3 +35,4 @@ subdir-$(CONFIG_SAMPLE_WATCH_QUEUE) += watch_queue obj-$(CONFIG_DEBUG_KMEMLEAK_TEST) += kmemleak/ obj-$(CONFIG_SAMPLE_CORESIGHT_SYSCFG) += coresight/ obj-$(CONFIG_SAMPLE_FPROBE) += fprobe/ +obj-$(CONFIG_SAMPLES_RUST) += rust/ diff --git a/samples/rust/Kconfig b/samples/rust/Kconfig new file mode 100644 index 000000000000..841e0906e943 --- /dev/null +++ b/samples/rust/Kconfig @@ -0,0 +1,30 @@ +# SPDX-License-Identifier: GPL-2.0 + +menuconfig SAMPLES_RUST + bool "Rust samples" + depends on RUST + help + You can build sample Rust kernel code here. + + If unsure, say N. + +if SAMPLES_RUST + +config SAMPLE_RUST_MINIMAL + tristate "Minimal" + help + This option builds the Rust minimal module sample. + + To compile this as a module, choose M here: + the module will be called rust_minimal. + + If unsure, say N. + +config SAMPLE_RUST_HOSTPROGS + bool "Host programs" + help + This option builds the Rust host program samples. + + If unsure, say N. + +endif # SAMPLES_RUST diff --git a/samples/rust/Makefile b/samples/rust/Makefile new file mode 100644 index 000000000000..1daba5f8658a --- /dev/null +++ b/samples/rust/Makefile @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-$(CONFIG_SAMPLE_RUST_MINIMAL) += rust_minimal.o + +subdir-$(CONFIG_SAMPLE_RUST_HOSTPROGS) += hostprogs diff --git a/samples/rust/hostprogs/.gitignore b/samples/rust/hostprogs/.gitignore new file mode 100644 index 000000000000..a6c173da5048 --- /dev/null +++ b/samples/rust/hostprogs/.gitignore @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +single diff --git a/samples/rust/hostprogs/Makefile b/samples/rust/hostprogs/Makefile new file mode 100644 index 000000000000..8ddcbd7416db --- /dev/null +++ b/samples/rust/hostprogs/Makefile @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 + +hostprogs-always-y := single + +single-rust := y diff --git a/samples/rust/hostprogs/a.rs b/samples/rust/hostprogs/a.rs new file mode 100644 index 000000000000..f7a4a3d0f4e0 --- /dev/null +++ b/samples/rust/hostprogs/a.rs @@ -0,0 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Rust single host program sample: module `a`. + +pub(crate) fn f(x: i32) { + println!("The number is {}.", x); +} diff --git a/samples/rust/hostprogs/b.rs b/samples/rust/hostprogs/b.rs new file mode 100644 index 000000000000..c1675890648f --- /dev/null +++ b/samples/rust/hostprogs/b.rs @@ -0,0 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Rust single host program sample: module `b`. + +pub(crate) const CONSTANT: i32 = 42; diff --git a/samples/rust/hostprogs/single.rs b/samples/rust/hostprogs/single.rs new file mode 100644 index 000000000000..8c48a119339a --- /dev/null +++ b/samples/rust/hostprogs/single.rs @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Rust single host program sample. + +mod a; +mod b; + +fn main() { + println!("Hello world!"); + + a::f(b::CONSTANT); +} diff --git a/samples/rust/rust_minimal.rs b/samples/rust/rust_minimal.rs new file mode 100644 index 000000000000..54ad17685742 --- /dev/null +++ b/samples/rust/rust_minimal.rs @@ -0,0 +1,38 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Rust minimal sample. + +use kernel::prelude::*; + +module! { + type: RustMinimal, + name: b"rust_minimal", + author: b"Rust for Linux Contributors", + description: b"Rust minimal sample", + license: b"GPL", +} + +struct RustMinimal { + numbers: Vec<i32>, +} + +impl kernel::Module for RustMinimal { + fn init(_module: &'static ThisModule) -> Result<Self> { + pr_info!("Rust minimal sample (init)\n"); + pr_info!("Am I built-in? {}\n", !cfg!(MODULE)); + + let mut numbers = Vec::new(); + numbers.try_push(72)?; + numbers.try_push(108)?; + numbers.try_push(200)?; + + Ok(RustMinimal { numbers }) + } +} + +impl Drop for RustMinimal { + fn drop(&mut self) { + pr_info!("My numbers are {:?}\n", self.numbers); + pr_info!("Rust minimal sample (exit)\n"); + } +} diff --git a/scripts/.gitignore b/scripts/.gitignore index eed308bef604..b7aec8eb1bd4 100644 --- a/scripts/.gitignore +++ b/scripts/.gitignore @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only /asn1_compiler /bin2c +/generate_rust_target /insert-sys-cert /kallsyms /module.lds diff --git a/scripts/Kconfig.include b/scripts/Kconfig.include index a0ccceb22cf8..274125307ebd 100644 --- a/scripts/Kconfig.include +++ b/scripts/Kconfig.include @@ -36,12 +36,12 @@ ld-option = $(success,$(LD) -v $(1)) as-instr = $(success,printf "%b\n" "$(1)" | $(CC) $(CLANG_FLAGS) -c -x assembler -o /dev/null -) # check if $(CC) and $(LD) exist -$(error-if,$(failure,command -v $(CC)),compiler '$(CC)' not found) +$(error-if,$(failure,command -v $(CC)),C compiler '$(CC)' not found) $(error-if,$(failure,command -v $(LD)),linker '$(LD)' not found) -# Get the compiler name, version, and error out if it is not supported. +# Get the C compiler name, version, and error out if it is not supported. cc-info := $(shell,$(srctree)/scripts/cc-version.sh $(CC)) -$(error-if,$(success,test -z "$(cc-info)"),Sorry$(comma) this compiler is not supported.) +$(error-if,$(success,test -z "$(cc-info)"),Sorry$(comma) this C compiler is not supported.) cc-name := $(shell,set -- $(cc-info) && echo $1) cc-version := $(shell,set -- $(cc-info) && echo $2) diff --git a/scripts/Makefile b/scripts/Makefile index f084f08ed176..1575af84d557 100644 --- a/scripts/Makefile +++ b/scripts/Makefile @@ -10,6 +10,9 @@ hostprogs-always-$(CONFIG_BUILDTIME_TABLE_SORT) += sorttable hostprogs-always-$(CONFIG_ASN1) += asn1_compiler hostprogs-always-$(CONFIG_MODULE_SIG_FORMAT) += sign-file hostprogs-always-$(CONFIG_SYSTEM_EXTRA_CERTIFICATE) += insert-sys-cert +hostprogs-always-$(CONFIG_RUST) += generate_rust_target + +generate_rust_target-rust := y HOSTCFLAGS_sorttable.o = -I$(srctree)/tools/include HOSTLDLIBS_sorttable = -lpthread diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 784f46d41959..27be77c0d6d8 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -26,6 +26,7 @@ EXTRA_CPPFLAGS := EXTRA_LDFLAGS := asflags-y := ccflags-y := +rustflags-y := cppflags-y := ldflags-y := @@ -271,6 +272,65 @@ quiet_cmd_cc_lst_c = MKLST $@ $(obj)/%.lst: $(src)/%.c FORCE $(call if_changed_dep,cc_lst_c) +# Compile Rust sources (.rs) +# --------------------------------------------------------------------------- + +rust_allowed_features := core_ffi_c + +rust_common_cmd = \ + RUST_MODFILE=$(modfile) $(RUSTC_OR_CLIPPY) $(rust_flags) \ + -Zallow-features=$(rust_allowed_features) \ + -Zcrate-attr=no_std \ + -Zcrate-attr='feature($(rust_allowed_features))' \ + --extern alloc --extern kernel \ + --crate-type rlib --out-dir $(obj) -L $(objtree)/rust/ \ + --crate-name $(basename $(notdir $@)) + +rust_handle_depfile = \ + mv $(obj)/$(basename $(notdir $@)).d $(depfile); \ + sed -i '/^\#/d' $(depfile) + +# `--emit=obj`, `--emit=asm` and `--emit=llvm-ir` imply a single codegen unit +# will be used. We explicitly request `-Ccodegen-units=1` in any case, and +# the compiler shows a warning if it is not 1. However, if we ever stop +# requesting it explicitly and we start using some other `--emit` that does not +# imply it (and for which codegen is performed), then we would be out of sync, +# i.e. the outputs we would get for the different single targets (e.g. `.ll`) +# would not match each other. + +quiet_cmd_rustc_o_rs = $(RUSTC_OR_CLIPPY_QUIET) $(quiet_modtag) $@ + cmd_rustc_o_rs = \ + $(rust_common_cmd) --emit=dep-info,obj $<; \ + $(rust_handle_depfile) + +$(obj)/%.o: $(src)/%.rs FORCE + $(call if_changed_dep,rustc_o_rs) + +quiet_cmd_rustc_rsi_rs = $(RUSTC_OR_CLIPPY_QUIET) $(quiet_modtag) $@ + cmd_rustc_rsi_rs = \ + $(rust_common_cmd) --emit=dep-info -Zunpretty=expanded $< >$@; \ + command -v $(RUSTFMT) >/dev/null && $(RUSTFMT) $@; \ + $(rust_handle_depfile) + +$(obj)/%.rsi: $(src)/%.rs FORCE + $(call if_changed_dep,rustc_rsi_rs) + +quiet_cmd_rustc_s_rs = $(RUSTC_OR_CLIPPY_QUIET) $(quiet_modtag) $@ + cmd_rustc_s_rs = \ + $(rust_common_cmd) --emit=dep-info,asm $<; \ + $(rust_handle_depfile) + +$(obj)/%.s: $(src)/%.rs FORCE + $(call if_changed_dep,rustc_s_rs) + +quiet_cmd_rustc_ll_rs = $(RUSTC_OR_CLIPPY_QUIET) $(quiet_modtag) $@ + cmd_rustc_ll_rs = \ + $(rust_common_cmd) --emit=dep-info,llvm-ir $<; \ + $(rust_handle_depfile) + +$(obj)/%.ll: $(src)/%.rs FORCE + $(call if_changed_dep,rustc_ll_rs) + # Compile assembler sources (.S) # --------------------------------------------------------------------------- diff --git a/scripts/Makefile.debug b/scripts/Makefile.debug index 8cf1cb22dd93..332c486f705f 100644 --- a/scripts/Makefile.debug +++ b/scripts/Makefile.debug @@ -1,4 +1,6 @@ DEBUG_CFLAGS := +DEBUG_RUSTFLAGS := + debug-flags-y := -g ifdef CONFIG_DEBUG_INFO_SPLIT @@ -17,9 +19,12 @@ KBUILD_AFLAGS += $(debug-flags-y) ifdef CONFIG_DEBUG_INFO_REDUCED DEBUG_CFLAGS += -fno-var-tracking +DEBUG_RUSTFLAGS += -Cdebuginfo=1 ifdef CONFIG_CC_IS_GCC DEBUG_CFLAGS += -femit-struct-debug-baseonly endif +else +DEBUG_RUSTFLAGS += -Cdebuginfo=2 endif ifdef CONFIG_DEBUG_INFO_COMPRESSED @@ -30,3 +35,6 @@ endif KBUILD_CFLAGS += $(DEBUG_CFLAGS) export DEBUG_CFLAGS + +KBUILD_RUSTFLAGS += $(DEBUG_RUSTFLAGS) +export DEBUG_RUSTFLAGS diff --git a/scripts/Makefile.host b/scripts/Makefile.host index 278b4d6ac945..da133780b751 100644 --- a/scripts/Makefile.host +++ b/scripts/Makefile.host @@ -22,6 +22,8 @@ $(obj)/%.tab.c $(obj)/%.tab.h: $(src)/%.y FORCE # to preprocess a data file. # # Both C and C++ are supported, but preferred language is C for such utilities. +# Rust is also supported, but it may only be used in scenarios where a Rust +# toolchain is required to be available (e.g. when `CONFIG_RUST` is enabled). # # Sample syntax (see Documentation/kbuild/makefiles.rst for reference) # hostprogs := bin2hex @@ -37,15 +39,20 @@ $(obj)/%.tab.c $(obj)/%.tab.h: $(src)/%.y FORCE # qconf-objs := menu.o # Will compile qconf as a C++ program, and menu as a C program. # They are linked as C++ code to the executable qconf +# +# hostprogs := target +# target-rust := y +# Will compile `target` as a Rust program, using `target.rs` as the crate root. +# The crate may consist of several source files. # C code # Executables compiled from a single .c file host-csingle := $(foreach m,$(hostprogs), \ - $(if $($(m)-objs)$($(m)-cxxobjs),,$(m))) + $(if $($(m)-objs)$($(m)-cxxobjs)$($(m)-rust),,$(m))) # C executables linked based on several .o files host-cmulti := $(foreach m,$(hostprogs),\ - $(if $($(m)-cxxobjs),,$(if $($(m)-objs),$(m)))) + $(if $($(m)-cxxobjs)$($(m)-rust),,$(if $($(m)-objs),$(m)))) # Object (.o) files compiled from .c files host-cobjs := $(sort $(foreach m,$(hostprogs),$($(m)-objs))) @@ -58,11 +65,17 @@ host-cxxmulti := $(foreach m,$(hostprogs),$(if $($(m)-cxxobjs),$(m))) # C++ Object (.o) files compiled from .cc files host-cxxobjs := $(sort $(foreach m,$(host-cxxmulti),$($(m)-cxxobjs))) +# Rust code +# Executables compiled from a single Rust crate (which may consist of +# one or more .rs files) +host-rust := $(foreach m,$(hostprogs),$(if $($(m)-rust),$(m))) + host-csingle := $(addprefix $(obj)/,$(host-csingle)) host-cmulti := $(addprefix $(obj)/,$(host-cmulti)) host-cobjs := $(addprefix $(obj)/,$(host-cobjs)) host-cxxmulti := $(addprefix $(obj)/,$(host-cxxmulti)) host-cxxobjs := $(addprefix $(obj)/,$(host-cxxobjs)) +host-rust := $(addprefix $(obj)/,$(host-rust)) ##### # Handle options to gcc. Support building with separate output directory @@ -71,6 +84,8 @@ _hostc_flags = $(KBUILD_HOSTCFLAGS) $(HOST_EXTRACFLAGS) \ $(HOSTCFLAGS_$(target-stem).o) _hostcxx_flags = $(KBUILD_HOSTCXXFLAGS) $(HOST_EXTRACXXFLAGS) \ $(HOSTCXXFLAGS_$(target-stem).o) +_hostrust_flags = $(KBUILD_HOSTRUSTFLAGS) $(HOST_EXTRARUSTFLAGS) \ + $(HOSTRUSTFLAGS_$(target-stem)) # $(objtree)/$(obj) for including generated headers from checkin source files ifeq ($(KBUILD_EXTMOD),) @@ -82,6 +97,7 @@ endif hostc_flags = -Wp,-MMD,$(depfile) $(_hostc_flags) hostcxx_flags = -Wp,-MMD,$(depfile) $(_hostcxx_flags) +hostrust_flags = $(_hostrust_flags) ##### # Compile programs on the host @@ -128,5 +144,17 @@ quiet_cmd_host-cxxobjs = HOSTCXX $@ $(host-cxxobjs): $(obj)/%.o: $(src)/%.cc FORCE $(call if_changed_dep,host-cxxobjs) +# Create executable from a single Rust crate (which may consist of +# one or more `.rs` files) +# host-rust -> Executable +quiet_cmd_host-rust = HOSTRUSTC $@ + cmd_host-rust = \ + $(HOSTRUSTC) $(hostrust_flags) --emit=dep-info,link \ + --out-dir=$(obj)/ $<; \ + mv $(obj)/$(target-stem).d $(depfile); \ + sed -i '/^\#/d' $(depfile) +$(host-rust): $(obj)/%: $(src)/%.rs FORCE + $(call if_changed_dep,host-rust) + targets += $(host-csingle) $(host-cmulti) $(host-cobjs) \ - $(host-cxxmulti) $(host-cxxobjs) + $(host-cxxmulti) $(host-cxxobjs) $(host-rust) diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 3fb6a99e78c4..c88b98b5dc44 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -8,6 +8,7 @@ ldflags-y += $(EXTRA_LDFLAGS) # flags that take effect in current and sub directories KBUILD_AFLAGS += $(subdir-asflags-y) KBUILD_CFLAGS += $(subdir-ccflags-y) +KBUILD_RUSTFLAGS += $(subdir-rustflags-y) # Figure out what we need to build from the various variables # =========================================================================== @@ -128,6 +129,10 @@ _c_flags = $(filter-out $(CFLAGS_REMOVE_$(target-stem).o), \ $(filter-out $(ccflags-remove-y), \ $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) $(ccflags-y)) \ $(CFLAGS_$(target-stem).o)) +_rust_flags = $(filter-out $(RUSTFLAGS_REMOVE_$(target-stem).o), \ + $(filter-out $(rustflags-remove-y), \ + $(KBUILD_RUSTFLAGS) $(rustflags-y)) \ + $(RUSTFLAGS_$(target-stem).o)) _a_flags = $(filter-out $(AFLAGS_REMOVE_$(target-stem).o), \ $(filter-out $(asflags-remove-y), \ $(KBUILD_CPPFLAGS) $(KBUILD_AFLAGS) $(asflags-y)) \ @@ -202,6 +207,11 @@ modkern_cflags = \ $(KBUILD_CFLAGS_MODULE) $(CFLAGS_MODULE), \ $(KBUILD_CFLAGS_KERNEL) $(CFLAGS_KERNEL) $(modfile_flags)) +modkern_rustflags = \ + $(if $(part-of-module), \ + $(KBUILD_RUSTFLAGS_MODULE) $(RUSTFLAGS_MODULE), \ + $(KBUILD_RUSTFLAGS_KERNEL) $(RUSTFLAGS_KERNEL)) + modkern_aflags = $(if $(part-of-module), \ $(KBUILD_AFLAGS_MODULE) $(AFLAGS_MODULE), \ $(KBUILD_AFLAGS_KERNEL) $(AFLAGS_KERNEL)) @@ -211,6 +221,8 @@ c_flags = -Wp,-MMD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) \ $(_c_flags) $(modkern_cflags) \ $(basename_flags) $(modname_flags) +rust_flags = $(_rust_flags) $(modkern_rustflags) @$(objtree)/include/generated/rustc_cfg + a_flags = -Wp,-MMD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) \ $(_a_flags) $(modkern_aflags) diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal index 35100e981f4a..9a1fa6aa30fe 100644 --- a/scripts/Makefile.modfinal +++ b/scripts/Makefile.modfinal @@ -39,11 +39,13 @@ quiet_cmd_ld_ko_o = LD [M] $@ quiet_cmd_btf_ko = BTF [M] $@ cmd_btf_ko = \ - if [ -f vmlinux ]; then \ + if [ ! -f vmlinux ]; then \ + printf "Skipping BTF generation for %s due to unavailability of vmlinux\n" $@ 1>&2; \ + elif [ -n "$(CONFIG_RUST)" ] && $(srctree)/scripts/is_rust_module.sh $@; then \ + printf "Skipping BTF generation for %s because it's a Rust module\n" $@ 1>&2; \ + else \ LLVM_OBJCOPY="$(OBJCOPY)" $(PAHOLE) -J $(PAHOLE_FLAGS) --btf_base vmlinux $@; \ $(RESOLVE_BTFIDS) -b vmlinux $@; \ - else \ - printf "Skipping BTF generation for %s due to unavailability of vmlinux\n" $@ 1>&2; \ fi; # Same as newer-prereqs, but allows to exclude specified extra dependencies diff --git a/scripts/cc-version.sh b/scripts/cc-version.sh index f1952c522466..2401c86fcf53 100755 --- a/scripts/cc-version.sh +++ b/scripts/cc-version.sh @@ -1,13 +1,13 @@ #!/bin/sh # SPDX-License-Identifier: GPL-2.0 # -# Print the compiler name and its version in a 5 or 6-digit form. +# Print the C compiler name and its version in a 5 or 6-digit form. # Also, perform the minimum version check. set -e -# Print the compiler name and some version components. -get_compiler_info() +# Print the C compiler name and some version components. +get_c_compiler_info() { cat <<- EOF | "$@" -E -P -x c - 2>/dev/null #if defined(__clang__) @@ -32,7 +32,7 @@ get_canonical_version() # $@ instead of $1 because multiple words might be given, e.g. CC="ccache gcc". orig_args="$@" -set -- $(get_compiler_info "$@") +set -- $(get_c_compiler_info "$@") name=$1 @@ -52,7 +52,7 @@ ICC) min_version=$($min_tool_version icc) ;; *) - echo "$orig_args: unknown compiler" >&2 + echo "$orig_args: unknown C compiler" >&2 exit 1 ;; esac @@ -62,7 +62,7 @@ min_cversion=$(get_canonical_version $min_version) if [ "$cversion" -lt "$min_cversion" ]; then echo >&2 "***" - echo >&2 "*** Compiler is too old." + echo >&2 "*** C compiler is too old." echo >&2 "*** Your $name version: $version" echo >&2 "*** Minimum $name version: $min_version" echo >&2 "***" diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 4aa09e0cb86a..c8a616a9d034 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -3616,7 +3616,7 @@ sub process { my $comment = ""; if ($realfile =~ /\.(h|s|S)$/) { $comment = '/*'; - } elsif ($realfile =~ /\.(c|dts|dtsi)$/) { + } elsif ($realfile =~ /\.(c|rs|dts|dtsi)$/) { $comment = '//'; } elsif (($checklicenseline == 2) || $realfile =~ /\.(sh|pl|py|awk|tc|yaml)$/) { $comment = '#'; @@ -3664,7 +3664,7 @@ sub process { } # check we are in a valid source file if not then ignore this hunk - next if ($realfile !~ /\.(h|c|s|S|sh|dtsi|dts)$/); + next if ($realfile !~ /\.(h|c|rs|s|S|sh|dtsi|dts)$/); # check for using SPDX-License-Identifier on the wrong line number if ($realline != $checklicenseline && @@ -6783,15 +6783,19 @@ sub process { } if ($bad_specifier ne "") { my $stat_real = get_stat_real($linenr, $lc); + my $msg_level = \&WARN; my $ext_type = "Invalid"; my $use = ""; if ($bad_specifier =~ /p[Ff]/) { $use = " - use %pS instead"; $use =~ s/pS/ps/ if ($bad_specifier =~ /pf/); + } elsif ($bad_specifier =~ /pA/) { + $use = " - '%pA' is only intended to be used from Rust code"; + $msg_level = \&ERROR; } - WARN("VSPRINTF_POINTER_EXTENSION", - "$ext_type vsprintf pointer extension '$bad_specifier'$use\n" . "$here\n$stat_real\n"); + &{$msg_level}("VSPRINTF_POINTER_EXTENSION", + "$ext_type vsprintf pointer extension '$bad_specifier'$use\n" . "$here\n$stat_real\n"); } } } diff --git a/scripts/decode_stacktrace.sh b/scripts/decode_stacktrace.sh index 7075e26ab2c4..564c5632e1a2 100755 --- a/scripts/decode_stacktrace.sh +++ b/scripts/decode_stacktrace.sh @@ -8,6 +8,14 @@ usage() { echo " $0 -r <release> | <vmlinux> [<base path>|auto] [<modules path>]" } +# Try to find a Rust demangler +if type llvm-cxxfilt >/dev/null 2>&1 ; then + cppfilt=llvm-cxxfilt +elif type c++filt >/dev/null 2>&1 ; then + cppfilt=c++filt + cppfilt_opts=-i +fi + if [[ $1 == "-r" ]] ; then vmlinux="" basepath="auto" @@ -180,6 +188,12 @@ parse_symbol() { # In the case of inlines, move everything to same line code=${code//$'\n'/' '} + # Demangle if the name looks like a Rust symbol and if + # we got a Rust demangler + if [[ $name =~ ^_R && $cppfilt != "" ]] ; then + name=$("$cppfilt" "$cppfilt_opts" "$name") + fi + # Replace old address with pretty line numbers symbol="$segment$name ($code)" } diff --git a/scripts/generate_rust_analyzer.py b/scripts/generate_rust_analyzer.py new file mode 100755 index 000000000000..75bb611bd751 --- /dev/null +++ b/scripts/generate_rust_analyzer.py @@ -0,0 +1,135 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +"""generate_rust_analyzer - Generates the `rust-project.json` file for `rust-analyzer`. +""" + +import argparse +import json +import logging +import pathlib +import sys + +def generate_crates(srctree, objtree, sysroot_src): + # Generate the configuration list. + cfg = [] + with open(objtree / "include" / "generated" / "rustc_cfg") as fd: + for line in fd: + line = line.replace("--cfg=", "") + line = line.replace("\n", "") + cfg.append(line) + + # Now fill the crates list -- dependencies need to come first. + # + # Avoid O(n^2) iterations by keeping a map of indexes. + crates = [] + crates_indexes = {} + + def append_crate(display_name, root_module, deps, cfg=[], is_workspace_member=True, is_proc_macro=False): + crates_indexes[display_name] = len(crates) + crates.append({ + "display_name": display_name, + "root_module": str(root_module), + "is_workspace_member": is_workspace_member, + "is_proc_macro": is_proc_macro, + "deps": [{"crate": crates_indexes[dep], "name": dep} for dep in deps], + "cfg": cfg, + "edition": "2021", + "env": { + "RUST_MODFILE": "This is only for rust-analyzer" + } + }) + + # First, the ones in `rust/` since they are a bit special. + append_crate( + "core", + sysroot_src / "core" / "src" / "lib.rs", + [], + is_workspace_member=False, + ) + + append_crate( + "compiler_builtins", + srctree / "rust" / "compiler_builtins.rs", + [], + ) + + append_crate( + "alloc", + srctree / "rust" / "alloc" / "lib.rs", + ["core", "compiler_builtins"], + ) + + append_crate( + "macros", + srctree / "rust" / "macros" / "lib.rs", + [], + is_proc_macro=True, + ) + crates[-1]["proc_macro_dylib_path"] = "rust/libmacros.so" + + append_crate( + "bindings", + srctree / "rust"/ "bindings" / "lib.rs", + ["core"], + cfg=cfg, + ) + crates[-1]["env"]["OBJTREE"] = str(objtree.resolve(True)) + + append_crate( + "kernel", + srctree / "rust" / "kernel" / "lib.rs", + ["core", "alloc", "macros", "bindings"], + cfg=cfg, + ) + crates[-1]["source"] = { + "include_dirs": [ + str(srctree / "rust" / "kernel"), + str(objtree / "rust") + ], + "exclude_dirs": [], + } + + # Then, the rest outside of `rust/`. + # + # We explicitly mention the top-level folders we want to cover. + for folder in ("samples", "drivers"): + for path in (srctree / folder).rglob("*.rs"): + logging.info("Checking %s", path) + name = path.name.replace(".rs", "") + + # Skip those that are not crate roots. + if f"{name}.o" not in open(path.parent / "Makefile").read(): + continue + + logging.info("Adding %s", name) + append_crate( + name, + path, + ["core", "alloc", "kernel"], + cfg=cfg, + ) + + return crates + +def main(): + parser = argparse.ArgumentParser() + parser.add_argument('--verbose', '-v', action='store_true') + parser.add_argument("srctree", type=pathlib.Path) + parser.add_argument("objtree", type=pathlib.Path) + parser.add_argument("sysroot_src", type=pathlib.Path) + args = parser.parse_args() + + logging.basicConfig( + format="[%(asctime)s] [%(levelname)s] %(message)s", + level=logging.INFO if args.verbose else logging.WARNING + ) + + rust_project = { + "crates": generate_crates(args.srctree, args.objtree, args.sysroot_src), + "sysroot_src": str(args.sysroot_src), + } + + json.dump(rust_project, sys.stdout, sort_keys=True, indent=4) + +if __name__ == "__main__": + main() diff --git a/scripts/generate_rust_target.rs b/scripts/generate_rust_target.rs new file mode 100644 index 000000000000..3c6cbe2b278d --- /dev/null +++ b/scripts/generate_rust_target.rs @@ -0,0 +1,182 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! The custom target specification file generator for `rustc`. +//! +//! To configure a target from scratch, a JSON-encoded file has to be passed +//! to `rustc` (introduced in [RFC 131]). These options and the file itself are +//! unstable. Eventually, `rustc` should provide a way to do this in a stable +//! manner. For instance, via command-line arguments. Therefore, this file +//! should avoid using keys which can be set via `-C` or `-Z` options. +//! +//! [RFC 131]: https://rust-lang.github.io/rfcs/0131-target-specification.html + +use std::{ + collections::HashMap, + fmt::{Display, Formatter, Result}, + io::BufRead, +}; + +enum Value { + Boolean(bool), + Number(i32), + String(String), + Object(Object), +} + +type Object = Vec<(String, Value)>; + +/// Minimal "almost JSON" generator (e.g. no `null`s, no arrays, no escaping), +/// enough for this purpose. +impl Display for Value { + fn fmt(&self, formatter: &mut Formatter<'_>) -> Result { + match self { + Value::Boolean(boolean) => write!(formatter, "{}", boolean), + Value::Number(number) => write!(formatter, "{}", number), + Value::String(string) => write!(formatter, "\"{}\"", string), + Value::Object(object) => { + formatter.write_str("{")?; + if let [ref rest @ .., ref last] = object[..] { + for (key, value) in rest { + write!(formatter, "\"{}\": {},", key, value)?; + } + write!(formatter, "\"{}\": {}", last.0, last.1)?; + } + formatter.write_str("}") + } + } + } +} + +struct TargetSpec(Object); + +impl TargetSpec { + fn new() -> TargetSpec { + TargetSpec(Vec::new()) + } +} + +trait Push<T> { + fn push(&mut self, key: &str, value: T); +} + +impl Push<bool> for TargetSpec { + fn push(&mut self, key: &str, value: bool) { + self.0.push((key.to_string(), Value::Boolean(value))); + } +} + +impl Push<i32> for TargetSpec { + fn push(&mut self, key: &str, value: i32) { + self.0.push((key.to_string(), Value::Number(value))); + } +} + +impl Push<String> for TargetSpec { + fn push(&mut self, key: &str, value: String) { + self.0.push((key.to_string(), Value::String(value))); + } +} + +impl Push<&str> for TargetSpec { + fn push(&mut self, key: &str, value: &str) { + self.push(key, value.to_string()); + } +} + +impl Push<Object> for TargetSpec { + fn push(&mut self, key: &str, value: Object) { + self.0.push((key.to_string(), Value::Object(value))); + } +} + +impl Display for TargetSpec { + fn fmt(&self, formatter: &mut Formatter<'_>) -> Result { + // We add some newlines for clarity. + formatter.write_str("{\n")?; + if let [ref rest @ .., ref last] = self.0[..] { + for (key, value) in rest { + write!(formatter, " \"{}\": {},\n", key, value)?; + } + write!(formatter, " \"{}\": {}\n", last.0, last.1)?; + } + formatter.write_str("}") + } +} + +struct KernelConfig(HashMap<String, String>); + +impl KernelConfig { + /// Parses `include/config/auto.conf` from `stdin`. + fn from_stdin() -> KernelConfig { + let mut result = HashMap::new(); + + let stdin = std::io::stdin(); + let mut handle = stdin.lock(); + let mut line = String::new(); + + loop { + line.clear(); + + if handle.read_line(&mut line).unwrap() == 0 { + break; + } + + if line.starts_with('#') { + continue; + } + + let (key, value) = line.split_once('=').expect("Missing `=` in line."); + result.insert(key.to_string(), value.trim_end_matches('\n').to_string()); + } + + KernelConfig(result) + } + + /// Does the option exist in the configuration (any value)? + /// + /// The argument must be passed without the `CONFIG_` prefix. + /// This avoids repetition and it also avoids `fixdep` making us + /// depend on it. + fn has(&self, option: &str) -> bool { + let option = "CONFIG_".to_owned() + option; + self.0.contains_key(&option) + } +} + +fn main() { + let cfg = KernelConfig::from_stdin(); + let mut ts = TargetSpec::new(); + + // `llvm-target`s are taken from `scripts/Makefile.clang`. + if cfg.has("X86_64") { + ts.push("arch", "x86_64"); + ts.push( + "data-layout", + "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128", + ); + let mut features = "-3dnow,-3dnowa,-mmx,+soft-float".to_string(); + if cfg.has("RETPOLINE") { + features += ",+retpoline-external-thunk"; + } + ts.push("features", features); + ts.push("llvm-target", "x86_64-linux-gnu"); + ts.push("target-pointer-width", "64"); + } else { + panic!("Unsupported architecture"); + } + + ts.push("emit-debug-gdb-scripts", false); + ts.push("frame-pointer", "may-omit"); + ts.push( + "stack-probes", + vec![("kind".to_string(), Value::String("none".to_string()))], + ); + + // Everything else is LE, whether `CPU_LITTLE_ENDIAN` is declared or not + // (e.g. x86). It is also `rustc`'s default. + if cfg.has("CPU_BIG_ENDIAN") { + ts.push("target-endian", "big"); + } + + println!("{}", ts); +} diff --git a/scripts/is_rust_module.sh b/scripts/is_rust_module.sh new file mode 100755 index 000000000000..28b3831a7593 --- /dev/null +++ b/scripts/is_rust_module.sh @@ -0,0 +1,16 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# is_rust_module.sh module.ko +# +# Returns `0` if `module.ko` is a Rust module, `1` otherwise. + +set -e + +# Using the `16_` prefix ensures other symbols with the same substring +# are not picked up (even if it would be unlikely). The last part is +# used just in case LLVM decides to use the `.` suffix. +# +# In the future, checking for the `.comment` section may be another +# option, see https://github.com/rust-lang/rust/pull/97550. +${NM} "$*" | grep -qE '^[0-9a-fA-F]+ r _R[^[:space:]]+16___IS_RUST_MODULE[^[:space:]]*$' diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index f18e6dfc68c5..c4793301a27e 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -27,7 +27,23 @@ #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof(arr[0])) -#define KSYM_NAME_LEN 128 +#define _stringify_1(x) #x +#define _stringify(x) _stringify_1(x) + +#define KSYM_NAME_LEN 512 + +/* + * A substantially bigger size than the current maximum. + * + * It cannot be defined as an expression because it gets stringified + * for the fscanf() format string. Therefore, a _Static_assert() is + * used instead to maintain the relationship with KSYM_NAME_LEN. + */ +#define KSYM_NAME_LEN_BUFFER 2048 +_Static_assert( + KSYM_NAME_LEN_BUFFER == KSYM_NAME_LEN * 4, + "Please keep KSYM_NAME_LEN_BUFFER in sync with KSYM_NAME_LEN" +); struct sym_entry { unsigned long long addr; @@ -198,15 +214,15 @@ static void check_symbol_range(const char *sym, unsigned long long addr, static struct sym_entry *read_symbol(FILE *in) { - char name[500], type; + char name[KSYM_NAME_LEN_BUFFER+1], type; unsigned long long addr; unsigned int len; struct sym_entry *sym; int rc; - rc = fscanf(in, "%llx %c %499s\n", &addr, &type, name); + rc = fscanf(in, "%llx %c %" _stringify(KSYM_NAME_LEN_BUFFER) "s\n", &addr, &type, name); if (rc != 3) { - if (rc != EOF && fgets(name, 500, in) == NULL) + if (rc != EOF && fgets(name, ARRAY_SIZE(name), in) == NULL) fprintf(stderr, "Read error or end of file.\n"); return NULL; } @@ -471,12 +487,35 @@ static void write_src(void) if ((i & 0xFF) == 0) markers[i >> 8] = off; - printf("\t.byte 0x%02x", table[i]->len); + /* There cannot be any symbol of length zero. */ + if (table[i]->len == 0) { + fprintf(stderr, "kallsyms failure: " + "unexpected zero symbol length\n"); + exit(EXIT_FAILURE); + } + + /* Only lengths that fit in up-to-two-byte ULEB128 are supported. */ + if (table[i]->len > 0x3FFF) { + fprintf(stderr, "kallsyms failure: " + "unexpected huge symbol length\n"); + exit(EXIT_FAILURE); + } + + /* Encode length with ULEB128. */ + if (table[i]->len <= 0x7F) { + /* Most symbols use a single byte for the length. */ + printf("\t.byte 0x%02x", table[i]->len); + off += table[i]->len + 1; + } else { + /* "Big" symbols use two bytes. */ + printf("\t.byte 0x%02x, 0x%02x", + (table[i]->len & 0x7F) | 0x80, + (table[i]->len >> 7) & 0x7F); + off += table[i]->len + 2; + } for (k = 0; k < table[i]->len; k++) printf(", 0x%02x", table[i]->sym[k]); printf("\n"); - - off += table[i]->len + 1; } printf("\n"); diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c index c4340c90e172..b7c9f1dd5e42 100644 --- a/scripts/kconfig/confdata.c +++ b/scripts/kconfig/confdata.c @@ -216,6 +216,13 @@ static const char *conf_get_autoheader_name(void) return name ? name : "include/generated/autoconf.h"; } +static const char *conf_get_rustccfg_name(void) +{ + char *name = getenv("KCONFIG_RUSTCCFG"); + + return name ? name : "include/generated/rustc_cfg"; +} + static int conf_set_sym_val(struct symbol *sym, int def, int def_flags, char *p) { char *p2; @@ -605,6 +612,9 @@ static const struct comment_style comment_style_c = { static void conf_write_heading(FILE *fp, const struct comment_style *cs) { + if (!cs) + return; + fprintf(fp, "%s\n", cs->prefix); fprintf(fp, "%s Automatically generated file; DO NOT EDIT.\n", @@ -745,6 +755,65 @@ static void print_symbol_for_c(FILE *fp, struct symbol *sym) free(escaped); } +static void print_symbol_for_rustccfg(FILE *fp, struct symbol *sym) +{ + const char *val; + const char *val_prefix = ""; + char *val_prefixed = NULL; + size_t val_prefixed_len; + char *escaped = NULL; + + if (sym->type == S_UNKNOWN) + return; + + val = sym_get_string_value(sym); + + switch (sym->type) { + case S_BOOLEAN: + case S_TRISTATE: + /* + * We do not care about disabled ones, i.e. no need for + * what otherwise are "comments" in other printers. + */ + if (*val == 'n') + return; + + /* + * To have similar functionality to the C macro `IS_ENABLED()` + * we provide an empty `--cfg CONFIG_X` here in both `y` + * and `m` cases. + * + * Then, the common `fprintf()` below will also give us + * a `--cfg CONFIG_X="y"` or `--cfg CONFIG_X="m"`, which can + * be used as the equivalent of `IS_BUILTIN()`/`IS_MODULE()`. + */ + fprintf(fp, "--cfg=%s%s\n", CONFIG_, sym->name); + break; + case S_HEX: + if (val[0] != '0' || (val[1] != 'x' && val[1] != 'X')) + val_prefix = "0x"; + break; + default: + break; + } + + if (strlen(val_prefix) > 0) { + val_prefixed_len = strlen(val) + strlen(val_prefix) + 1; + val_prefixed = xmalloc(val_prefixed_len); + snprintf(val_prefixed, val_prefixed_len, "%s%s", val_prefix, val); + val = val_prefixed; + } + + /* All values get escaped: the `--cfg` option only takes strings */ + escaped = escape_string_value(val); + val = escaped; + + fprintf(fp, "--cfg=%s%s=%s\n", CONFIG_, sym->name, val); + + free(escaped); + free(val_prefixed); +} + /* * Write out a minimal config. * All values that has default values are skipped as this is redundant. @@ -1132,6 +1201,12 @@ int conf_write_autoconf(int overwrite) if (ret) return ret; + ret = __conf_write_autoconf(conf_get_rustccfg_name(), + print_symbol_for_rustccfg, + NULL); + if (ret) + return ret; + /* * Create include/config/auto.conf. This must be the last step because * Kbuild has a dependency on auto.conf and this marks the successful diff --git a/scripts/min-tool-version.sh b/scripts/min-tool-version.sh index 250925aab101..b6593eac5003 100755 --- a/scripts/min-tool-version.sh +++ b/scripts/min-tool-version.sh @@ -30,6 +30,12 @@ llvm) echo 11.0.0 fi ;; +rustc) + echo 1.62.0 + ;; +bindgen) + echo 0.56.0 + ;; *) echo "$1: unknown tool" >&2 exit 1 diff --git a/scripts/rust_is_available.sh b/scripts/rust_is_available.sh new file mode 100755 index 000000000000..aebbf1913970 --- /dev/null +++ b/scripts/rust_is_available.sh @@ -0,0 +1,160 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Tests whether a suitable Rust toolchain is available. +# +# Pass `-v` for human output and more checks (as warnings). + +set -e + +min_tool_version=$(dirname $0)/min-tool-version.sh + +# Convert the version string x.y.z to a canonical up-to-7-digits form. +# +# Note that this function uses one more digit (compared to other +# instances in other version scripts) to give a bit more space to +# `rustc` since it will reach 1.100.0 in late 2026. +get_canonical_version() +{ + IFS=. + set -- $1 + echo $((100000 * $1 + 100 * $2 + $3)) +} + +# Check that the Rust compiler exists. +if ! command -v "$RUSTC" >/dev/null; then + if [ "$1" = -v ]; then + echo >&2 "***" + echo >&2 "*** Rust compiler '$RUSTC' could not be found." + echo >&2 "***" + fi + exit 1 +fi + +# Check that the Rust bindings generator exists. +if ! command -v "$BINDGEN" >/dev/null; then + if [ "$1" = -v ]; then + echo >&2 "***" + echo >&2 "*** Rust bindings generator '$BINDGEN' could not be found." + echo >&2 "***" + fi + exit 1 +fi + +# Check that the Rust compiler version is suitable. +# +# Non-stable and distributions' versions may have a version suffix, e.g. `-dev`. +rust_compiler_version=$( \ + LC_ALL=C "$RUSTC" --version 2>/dev/null \ + | head -n 1 \ + | grep -oE '[0-9]+\.[0-9]+\.[0-9]+' \ +) +rust_compiler_min_version=$($min_tool_version rustc) +rust_compiler_cversion=$(get_canonical_version $rust_compiler_version) +rust_compiler_min_cversion=$(get_canonical_version $rust_compiler_min_version) +if [ "$rust_compiler_cversion" -lt "$rust_compiler_min_cversion" ]; then + if [ "$1" = -v ]; then + echo >&2 "***" + echo >&2 "*** Rust compiler '$RUSTC' is too old." + echo >&2 "*** Your version: $rust_compiler_version" + echo >&2 "*** Minimum version: $rust_compiler_min_version" + echo >&2 "***" + fi + exit 1 +fi +if [ "$1" = -v ] && [ "$rust_compiler_cversion" -gt "$rust_compiler_min_cversion" ]; then + echo >&2 "***" + echo >&2 "*** Rust compiler '$RUSTC' is too new. This may or may not work." + echo >&2 "*** Your version: $rust_compiler_version" + echo >&2 "*** Expected version: $rust_compiler_min_version" + echo >&2 "***" +fi + +# Check that the Rust bindings generator is suitable. +# +# Non-stable and distributions' versions may have a version suffix, e.g. `-dev`. +rust_bindings_generator_version=$( \ + LC_ALL=C "$BINDGEN" --version 2>/dev/null \ + | head -n 1 \ + | grep -oE '[0-9]+\.[0-9]+\.[0-9]+' \ +) +rust_bindings_generator_min_version=$($min_tool_version bindgen) +rust_bindings_generator_cversion=$(get_canonical_version $rust_bindings_generator_version) +rust_bindings_generator_min_cversion=$(get_canonical_version $rust_bindings_generator_min_version) +if [ "$rust_bindings_generator_cversion" -lt "$rust_bindings_generator_min_cversion" ]; then + if [ "$1" = -v ]; then + echo >&2 "***" + echo >&2 "*** Rust bindings generator '$BINDGEN' is too old." + echo >&2 "*** Your version: $rust_bindings_generator_version" + echo >&2 "*** Minimum version: $rust_bindings_generator_min_version" + echo >&2 "***" + fi + exit 1 +fi +if [ "$1" = -v ] && [ "$rust_bindings_generator_cversion" -gt "$rust_bindings_generator_min_cversion" ]; then + echo >&2 "***" + echo >&2 "*** Rust bindings generator '$BINDGEN' is too new. This may or may not work." + echo >&2 "*** Your version: $rust_bindings_generator_version" + echo >&2 "*** Expected version: $rust_bindings_generator_min_version" + echo >&2 "***" +fi + +# Check that the `libclang` used by the Rust bindings generator is suitable. +bindgen_libclang_version=$( \ + LC_ALL=C "$BINDGEN" $(dirname $0)/rust_is_available_bindgen_libclang.h 2>&1 >/dev/null \ + | grep -F 'clang version ' \ + | grep -oE '[0-9]+\.[0-9]+\.[0-9]+' \ + | head -n 1 \ +) +bindgen_libclang_min_version=$($min_tool_version llvm) +bindgen_libclang_cversion=$(get_canonical_version $bindgen_libclang_version) +bindgen_libclang_min_cversion=$(get_canonical_version $bindgen_libclang_min_version) +if [ "$bindgen_libclang_cversion" -lt "$bindgen_libclang_min_cversion" ]; then + if [ "$1" = -v ]; then + echo >&2 "***" + echo >&2 "*** libclang (used by the Rust bindings generator '$BINDGEN') is too old." + echo >&2 "*** Your version: $bindgen_libclang_version" + echo >&2 "*** Minimum version: $bindgen_libclang_min_version" + echo >&2 "***" + fi + exit 1 +fi + +# If the C compiler is Clang, then we can also check whether its version +# matches the `libclang` version used by the Rust bindings generator. +# +# In the future, we might be able to perform a full version check, see +# https://github.com/rust-lang/rust-bindgen/issues/2138. +if [ "$1" = -v ]; then + cc_name=$($(dirname $0)/cc-version.sh "$CC" | cut -f1 -d' ') + if [ "$cc_name" = Clang ]; then + clang_version=$( \ + LC_ALL=C "$CC" --version 2>/dev/null \ + | sed -nE '1s:.*version ([0-9]+\.[0-9]+\.[0-9]+).*:\1:p' + ) + if [ "$clang_version" != "$bindgen_libclang_version" ]; then + echo >&2 "***" + echo >&2 "*** libclang (used by the Rust bindings generator '$BINDGEN')" + echo >&2 "*** version does not match Clang's. This may be a problem." + echo >&2 "*** libclang version: $bindgen_libclang_version" + echo >&2 "*** Clang version: $clang_version" + echo >&2 "***" + fi + fi +fi + +# Check that the source code for the `core` standard library exists. +# +# `$KRUSTFLAGS` is passed in case the user added `--sysroot`. +rustc_sysroot=$("$RUSTC" $KRUSTFLAGS --print sysroot) +rustc_src=${RUST_LIB_SRC:-"$rustc_sysroot/lib/rustlib/src/rust/library"} +rustc_src_core="$rustc_src/core/src/lib.rs" +if [ ! -e "$rustc_src_core" ]; then + if [ "$1" = -v ]; then + echo >&2 "***" + echo >&2 "*** Source code for the 'core' standard library could not be found" + echo >&2 "*** at '$rustc_src_core'." + echo >&2 "***" + fi + exit 1 +fi diff --git a/scripts/rust_is_available_bindgen_libclang.h b/scripts/rust_is_available_bindgen_libclang.h new file mode 100644 index 000000000000..0ef6db10d674 --- /dev/null +++ b/scripts/rust_is_available_bindgen_libclang.h @@ -0,0 +1,2 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#pragma message("clang version " __clang_version__) diff --git a/tools/include/linux/kallsyms.h b/tools/include/linux/kallsyms.h index efb6c3f5f2a9..5a37ccbec54f 100644 --- a/tools/include/linux/kallsyms.h +++ b/tools/include/linux/kallsyms.h @@ -6,7 +6,7 @@ #include <stdio.h> #include <unistd.h> -#define KSYM_NAME_LEN 128 +#define KSYM_NAME_LEN 512 struct module; diff --git a/tools/lib/perf/include/perf/event.h b/tools/lib/perf/include/perf/event.h index 93bf93a59c99..d8ae4e944467 100644 --- a/tools/lib/perf/include/perf/event.h +++ b/tools/lib/perf/include/perf/event.h @@ -97,7 +97,7 @@ struct perf_record_throttle { }; #ifndef KSYM_NAME_LEN -#define KSYM_NAME_LEN 256 +#define KSYM_NAME_LEN 512 #endif struct perf_record_ksymbol { diff --git a/tools/lib/symbol/kallsyms.h b/tools/lib/symbol/kallsyms.h index 72ab9870454b..542f9b059c3b 100644 --- a/tools/lib/symbol/kallsyms.h +++ b/tools/lib/symbol/kallsyms.h @@ -7,7 +7,7 @@ #include <linux/types.h> #ifndef KSYM_NAME_LEN -#define KSYM_NAME_LEN 256 +#define KSYM_NAME_LEN 512 #endif static inline u8 kallsyms2elf_binding(char type) |