diff --git a/book.toml b/book.toml index dc7b49a..cf98b4e 100644 --- a/book.toml +++ b/book.toml @@ -35,4 +35,4 @@ git-repository-url = "https://github.com/rust-lang/nomicon" "./atomics.html" = "./atomics/atomics.html" [rust] -edition = "2018" +edition = "2021" diff --git a/src/beneath-std.md b/src/beneath-std.md index 6f05182..02a02bd 100644 --- a/src/beneath-std.md +++ b/src/beneath-std.md @@ -1,10 +1,108 @@ -# Beneath std +# Beneath `std` -This section documents (or will document) features that are provided by the standard library and -that `#![no_std]` developers have to deal with (i.e. provide) to build `#![no_std]` binary crates. A -(likely incomplete) list of such features is shown below: +This section documents features that are normally provided by the `std` crate and +that `#![no_std]` developers have to deal with (i.e. provide) to build +`#![no_std]` binary crates. -- `#[lang = "eh_personality"]` -- `#[lang = "start"]` -- `#[lang = "termination"]` -- `#[panic_implementation]` +## Using `libc` + +In order to build a `#[no_std]` executable we will need `libc` as a dependency. +We can specify this using our `Cargo.toml` file: + +```toml +[dependencies] +libc = { version = "0.2.146", default-features = false } +``` + +Note that the default features have been disabled. This is a critical step - +**the default features of `libc` include the `std` crate and so must be +disabled.** + +Alternatively, we can use the unstable `rustc_private` private feature together +with an `extern crate libc;` declaration as shown in the examples below. + +## Writing an executable without `std` + +We will probably need a nightly version of the compiler to produce +a `#![no_std]` executable because on many platforms, we have to provide the +`eh_personality` [lang item], which is unstable. + +Controlling the entry point is possible in two ways: the `#[start]` attribute, +or overriding the default shim for the C `main` function with your own. +Additionally, it's required to define a [panic handler function](panic-handler.html). + +The function marked `#[start]` is passed the command line parameters +in the same format as C (aside from the exact integer types being used): + +```rust +#![feature(start, lang_items, core_intrinsics, rustc_private)] +#![allow(internal_features)] +#![no_std] + +// Necessary for `panic = "unwind"` builds on some platforms. +#![feature(panic_unwind)] +extern crate unwind; + +// Pull in the system libc library for what crt0.o likely requires. +extern crate libc; + +use core::panic::PanicInfo; + +// Entry point for this program. +#[start] +fn main(_argc: isize, _argv: *const *const u8) -> isize { + 0 +} + +// These functions are used by the compiler, but not for an empty program like this. +// They are normally provided by `std`. +#[lang = "eh_personality"] +fn rust_eh_personality() {} +#[panic_handler] +fn panic_handler(_info: &PanicInfo) -> ! { core::intrinsics::abort() } +``` + +To override the compiler-inserted `main` shim, we have to disable it +with `#![no_main]` and then create the appropriate symbol with the +correct ABI and the correct name, which requires overriding the +compiler's name mangling too: + +```rust +#![feature(lang_items, core_intrinsics, rustc_private)] +#![allow(internal_features)] +#![no_std] +#![no_main] + +// Necessary for `panic = "unwind"` builds on some platforms. +#![feature(panic_unwind)] +extern crate unwind; + +// Pull in the system libc library for what crt0.o likely requires. +extern crate libc; + +use core::ffi::{c_char, c_int}; +use core::panic::PanicInfo; + +// Entry point for this program. +#[no_mangle] // ensure that this symbol is included in the output as `main` +extern "C" fn main(_argc: c_int, _argv: *const *const c_char) -> c_int { + 0 +} + +// These functions are used by the compiler, but not for an empty program like this. +// They are normally provided by `std`. +#[lang = "eh_personality"] +fn rust_eh_personality() {} +#[panic_handler] +fn panic_handler(_info: &PanicInfo) -> ! { core::intrinsics::abort() } +``` + +If you are working with a target that doesn't have binary releases of the +standard library available via rustup (this probably means you are building the +`core` crate yourself) and need compiler-rt intrinsics (i.e. you are probably +getting linker errors when building an executable: +``undefined reference to `__aeabi_memcpy'``), you need to manually link to the +[`compiler_builtins` crate] to get those intrinsics and solve the linker errors. + +[`compiler_builtins` crate]: https://crates.io/crates/compiler_builtins +[lang item]: https://doc.rust-lang.org/nightly/unstable-book/language-features/lang-items.html diff --git a/src/borrow-splitting.md b/src/borrow-splitting.md index 3d13ff9..08b6d0d 100644 --- a/src/borrow-splitting.md +++ b/src/borrow-splitting.md @@ -159,7 +159,7 @@ impl<'a, T> Iterator for IterMut<'a, T> { type Item = &'a mut T; fn next(&mut self) -> Option { - let slice = mem::replace(&mut self.0, &mut []); + let slice = mem::take(&mut self.0); if slice.is_empty() { return None; } let (l, r) = slice.split_at_mut(1); @@ -170,7 +170,7 @@ impl<'a, T> Iterator for IterMut<'a, T> { impl<'a, T> DoubleEndedIterator for IterMut<'a, T> { fn next_back(&mut self) -> Option { - let slice = mem::replace(&mut self.0, &mut []); + let slice = mem::take(&mut self.0); if slice.is_empty() { return None; } let new_len = slice.len() - 1; diff --git a/src/dropck.md b/src/dropck.md index 7594021..4063d56 100644 --- a/src/dropck.md +++ b/src/dropck.md @@ -250,7 +250,7 @@ fn main() { inspector: None, days: Box::new(1), }; - world.inspector = Some(Inspector(&world.days, "gatget")); + world.inspector = Some(Inspector(&world.days, "gadget")); } ``` diff --git a/src/exception-safety.md b/src/exception-safety.md index ca1a394..762b38b 100644 --- a/src/exception-safety.md +++ b/src/exception-safety.md @@ -161,9 +161,9 @@ impl<'a, T> Hole<'a, T> { unsafe { let elt = ptr::read(&data[pos]); Hole { - data: data, + data, elt: Some(elt), - pos: pos, + pos, } } } @@ -172,7 +172,7 @@ impl<'a, T> Hole<'a, T> { fn removed(&self) -> &T { self.elt.as_ref().unwrap() } - unsafe fn get(&self, index: usize) -> &T { &self.data[index] } + fn get(&self, index: usize) -> &T { &self.data[index] } unsafe fn move_to(&mut self, index: usize) { let index_ptr: *const _ = &self.data[index]; diff --git a/src/ffi.md b/src/ffi.md index 9b0ff98..b76f0b2 100644 --- a/src/ffi.md +++ b/src/ffi.md @@ -258,7 +258,7 @@ pub extern "C" fn hello_from_rust() { # fn main() {} ``` -The `extern "C"` makes this function adhere to the C calling convention, as discussed above in "[Foreign Calling Conventions]". +The `extern "C"` makes this function adhere to the C calling convention, as discussed below in "[Foreign Calling Conventions]". The `no_mangle` attribute turns off Rust's name mangling, so that it has a well defined symbol to link to. Then, to compile Rust code as a shared library that can be called from C, add the following to your `Cargo.toml`: @@ -586,6 +586,7 @@ are: * `aapcs` * `cdecl` * `fastcall` +* `thiscall` * `vectorcall` This is currently hidden behind the `abi_vectorcall` gate and is subject to change. * `Rust` @@ -659,7 +660,8 @@ Certain Rust types are defined to never be `null`. This includes references (`&T `&mut T`), boxes (`Box`), and function pointers (`extern "abi" fn()`). When interfacing with C, pointers that might be `null` are often used, which would seem to require some messy `transmute`s and/or unsafe code to handle conversions to/from Rust types. -However, the language provides a workaround. +However, trying to construct/work with these invalid values **is undefined behavior**, +so you should use the following workaround instead. As a special case, an `enum` is eligible for the "nullable pointer optimization" if it contains exactly two variants, one of which contains no data and the other contains a field of one of the @@ -720,17 +722,20 @@ No `transmute` required! ## FFI and unwinding -It’s important to be mindful of unwinding when working with FFI. Each -non-`Rust` ABI comes in two variants, one with `-unwind` suffix and one without. If -you expect Rust `panic`s or foreign (e.g. C++) exceptions to cross an FFI -boundary, that boundary must use the appropriate `-unwind` ABI string (note -that compiling with `panic=abort` will still cause `panic!` to immediately -abort the process, regardless of which ABI is specified by the function that -`panic`s). +It’s important to be mindful of unwinding when working with FFI. Most +ABI strings come in two variants, one with an `-unwind` suffix and one without. +The `Rust` ABI always permits unwinding, so there is no `Rust-unwind` ABI. +If you expect Rust `panic`s or foreign (e.g. C++) exceptions to cross an FFI +boundary, that boundary must use the appropriate `-unwind` ABI string. Conversely, if you do not expect unwinding to cross an ABI boundary, use one of -the non-`unwind` ABI strings (other than `Rust`, which always permits -unwinding). If an unwinding operation does encounter an ABI boundary that is +the non-`unwind` ABI strings. + +> Note: Compiling with `panic=abort` will still cause `panic!` to immediately +abort the process, regardless of which ABI is specified by the function that +`panic`s. + +If an unwinding operation does encounter an ABI boundary that is not permitted to unwind, the behavior depends on the source of the unwinding (Rust `panic` or a foreign exception): diff --git a/src/intro.md b/src/intro.md index 4e77ffa..323c0ce 100644 --- a/src/intro.md +++ b/src/intro.md @@ -39,7 +39,7 @@ Topics that are within the scope of this book include: the meaning of (un)safety The Rustonomicon is not a place to exhaustively describe the semantics and guarantees of every single API in the standard library, nor is it a place to exhaustively describe every feature of Rust. -Unless otherwise noted, Rust code in this book uses the Rust 2018 edition. +Unless otherwise noted, Rust code in this book uses the Rust 2021 edition. [trpl]: ../book/index.html [ref]: ../reference/index.html diff --git a/src/leaking.md b/src/leaking.md index ea29595..d90fed5 100644 --- a/src/leaking.md +++ b/src/leaking.md @@ -134,10 +134,10 @@ impl Rc { // Wouldn't it be nice if heap::allocate worked like this? let ptr = heap::allocate::>(); ptr::write(ptr, RcBox { - data: data, + data, ref_count: 1, }); - Rc { ptr: ptr } + Rc { ptr } } } @@ -194,7 +194,7 @@ pub fn scoped<'a, F>(f: F) -> JoinGuard<'a> ``` Here `f` is some closure for the other thread to execute. Saying that -`F: Send +'a` is saying that it closes over data that lives for `'a`, and it +`F: Send + 'a` is saying that it closes over data that lives for `'a`, and it either owns that data or the data was Sync (implying `&data` is Send). Because JoinGuard has a lifetime, it keeps all the data it closes over diff --git a/src/lifetime-mismatch.md b/src/lifetime-mismatch.md index 0494d49..ecb6cf2 100644 --- a/src/lifetime-mismatch.md +++ b/src/lifetime-mismatch.md @@ -65,7 +65,7 @@ fn main() { The lifetime system is forced to extend the `&mut foo` to have lifetime `'c`, due to the lifetime of `loan` and `mutate_and_share`'s signature. Then when we -try to call `share`, and it sees we're trying to alias that `&'c mut foo` and +try to call `share`, it sees we're trying to alias that `&'c mut foo` and blows up in our face! This program is clearly correct according to the reference semantics we actually @@ -74,9 +74,9 @@ care about, but the lifetime system is too coarse-grained to handle that. ## Improperly reduced borrows The following code fails to compile, because Rust sees that a variable, `map`, -is borrowed twice, and can not infer that the first borrow stops to be needed +is borrowed twice, and can not infer that the first borrow ceases to be needed before the second one occurs. This is caused by Rust conservatively falling back -to using a whole scope for the first borow. This will eventually get fixed. +to using a whole scope for the first borrow. This will eventually get fixed. ```rust,compile_fail # use std::collections::HashMap; diff --git a/src/lifetimes.md b/src/lifetimes.md index ef86b7b..f55ea8c 100644 --- a/src/lifetimes.md +++ b/src/lifetimes.md @@ -55,7 +55,7 @@ likely desugar to the following: let y: &'b i32 = &'b x; 'c: { // ditto on 'c - let z: &'c &'b i32 = &'c y; + let z: &'c &'b i32 = &'c y; // "a reference to a reference to an i32" (with lifetimes annotated) } } } diff --git a/src/other-reprs.md b/src/other-reprs.md index 93da729..228b22b 100644 --- a/src/other-reprs.md +++ b/src/other-reprs.md @@ -56,24 +56,26 @@ compiled as normal.) ## repr(transparent) -This can only be used on structs with a single non-zero-sized field (there may -be additional zero-sized fields). The effect is that the layout and ABI of the -whole struct is guaranteed to be the same as that one field. +`#[repr(transparent)]` can only be used on a struct or single-variant enum that has a single non-zero-sized field (there may be additional zero-sized fields). +The effect is that the layout and ABI of the whole struct/enum is guaranteed to be the same as that one field. + +> NOTE: There's a `transparent_unions` nightly feature to apply `repr(transparent)` to unions, +> but it hasn't been stabilized due to design concerns. See the [tracking issue][issue-60405] for more details. The goal is to make it possible to transmute between the single field and the -struct. An example of that is [`UnsafeCell`], which can be transmuted into +struct/enum. An example of that is [`UnsafeCell`], which can be transmuted into the type it wraps ([`UnsafeCell`] also uses the unstable [no_niche][no-niche-pull], so its ABI is not actually guaranteed to be the same when nested in other types). -Also, passing the struct through FFI where the inner field type is expected on -the other side is guaranteed to work. In particular, this is necessary for `struct -Foo(f32)` to always have the same ABI as `f32`. +Also, passing the struct/enum through FFI where the inner field type is expected on +the other side is guaranteed to work. In particular, this is necessary for +`struct Foo(f32)` or `enum Foo { Bar(f32) }` to always have the same ABI as `f32`. This repr is only considered part of the public ABI of a type if either the single field is `pub`, or if its layout is documented in prose. Otherwise, the layout should not be relied upon by other crates. -More details are in the [RFC][rfc-transparent]. +More details are in the [RFC 1758][rfc-transparent] and the [RFC 2645][rfc-transparent-unions-enums]. ## repr(u*), repr(i*) @@ -153,8 +155,10 @@ This is a modifier on `repr(C)` and `repr(Rust)`. It is incompatible with [unsafe code guidelines]: https://rust-lang.github.io/unsafe-code-guidelines/layout.html [drop flags]: drop-flags.html [ub loads]: https://github.com/rust-lang/rust/issues/27060 +[issue-60405]: https://github.com/rust-lang/rust/issues/60405 [`UnsafeCell`]: ../std/cell/struct.UnsafeCell.html [rfc-transparent]: https://github.com/rust-lang/rfcs/blob/master/text/1758-repr-transparent.md +[rfc-transparent-unions-enums]: https://rust-lang.github.io/rfcs/2645-transparent-unions.html [really-tagged]: https://github.com/rust-lang/rfcs/blob/master/text/2195-really-tagged-unions.md [rust-bindgen]: https://rust-lang.github.io/rust-bindgen/ [cbindgen]: https://github.com/eqrion/cbindgen diff --git a/src/phantom-data.md b/src/phantom-data.md index ca1c2c2..cd2428d 100644 --- a/src/phantom-data.md +++ b/src/phantom-data.md @@ -24,7 +24,7 @@ We do this using `PhantomData`, which is a special marker type. `PhantomData` consumes no space, but simulates a field of the given type for the purpose of static analysis. This was deemed to be less error-prone than explicitly telling the type-system the kind of variance that you want, while also providing other -useful things such as the information needed by drop check. +useful things such as auto traits and the information needed by drop check. Iter logically contains a bunch of `&'a T`s, so this is exactly what we tell the `PhantomData` to simulate: @@ -106,7 +106,14 @@ that that `Vec` _owns_ values of type `T` (more precisely: may use values of in its `Drop` implementation), and Rust will thus not allow them to _dangle_ should a `Vec` be dropped. -**Adding an extra `_owns_T: PhantomData` field is thus _superfluous_ and accomplishes nothing**. +When a type already has a `Drop impl`, **adding an extra `_owns_T: PhantomData` field +is thus _superfluous_ and accomplishes nothing**, dropck-wise (it still affects variance +and auto-traits). + + - (advanced edge case: if the type containing the `PhantomData` has no `Drop` impl at all, + but still has drop glue (by having _another_ field with drop glue), then the + dropck/`#[may_dangle]` considerations mentioned herein do apply as well: a `PhantomData` + field will then require `T` to be droppable whenever the containing type goes out of scope). ___ @@ -234,14 +241,18 @@ standard library made a utility for itself called `Unique` which: Here’s a table of all the wonderful ways `PhantomData` could be used: -| Phantom type | `'a` | `T` | -|-----------------------------|-----------|---------------------------| -| `PhantomData` | - | covariant (with drop check) | -| `PhantomData<&'a T>` | covariant | covariant | -| `PhantomData<&'a mut T>` | covariant | invariant | -| `PhantomData<*const T>` | - | covariant | -| `PhantomData<*mut T>` | - | invariant | -| `PhantomData` | - | contravariant | -| `PhantomData T>` | - | covariant | -| `PhantomData T>` | - | invariant | -| `PhantomData>` | invariant | - | +| Phantom type | variance of `'a` | variance of `T` | `Send`/`Sync`
(or lack thereof) | dangling `'a` or `T` in drop glue
(_e.g._, `#[may_dangle] Drop`) | +|-----------------------------|:----------------:|:-----------------:|:-----------------------------------------:|:------------------------------------------------:| +| `PhantomData` | - | **cov**ariant | inherited | disallowed ("owns `T`") | +| `PhantomData<&'a T>` | **cov**ariant | **cov**ariant | `Send + Sync`
requires
`T : Sync` | allowed | +| `PhantomData<&'a mut T>` | **cov**ariant | **inv**ariant | inherited | allowed | +| `PhantomData<*const T>` | - | **cov**ariant | `!Send + !Sync` | allowed | +| `PhantomData<*mut T>` | - | **inv**ariant | `!Send + !Sync` | allowed | +| `PhantomData` | - | **contra**variant | `Send + Sync` | allowed | +| `PhantomData T>` | - | **cov**ariant | `Send + Sync` | allowed | +| `PhantomData T>` | - | **inv**ariant | `Send + Sync` | allowed | +| `PhantomData>` | **inv**ariant | - | `Send + !Sync` | allowed | + + - Note: opting out of the `Unpin` auto-trait requires the dedicated [`PhantomPinned`] type instead. + +[`PhantomPinned`]: ../core/marker/struct.PhantomPinned.html diff --git a/src/races.md b/src/races.md index cb78ac6..d5f1ea0 100644 --- a/src/races.md +++ b/src/races.md @@ -6,26 +6,28 @@ Safe Rust guarantees an absence of data races, which are defined as: * one or more of them is a write * one or more of them is unsynchronized -A data race has Undefined Behavior, and is therefore impossible to perform -in Safe Rust. Data races are *mostly* prevented through Rust's ownership system: +A data race has Undefined Behavior, and is therefore impossible to perform in +Safe Rust. Data races are *mostly* prevented through Rust's ownership system: it's impossible to alias a mutable reference, so it's impossible to perform a data race. Interior mutability makes this more complicated, which is largely why -we have the Send and Sync traits (see below). +we have the Send and Sync traits (see the next section for more on this). **However Rust does not prevent general race conditions.** -This is pretty fundamentally impossible, and probably honestly undesirable. Your -hardware is racy, your OS is racy, the other programs on your computer are racy, -and the world this all runs in is racy. Any system that could genuinely claim to -prevent *all* race conditions would be pretty awful to use, if not just -incorrect. +This is mathematically impossible in situations where you do not control the +scheduler, which is true for the normal OS environment. If you do control +preemption, it _can be_ possible to prevent general races - this technique is +used by frameworks such as [RTIC](https://github.com/rtic-rs/rtic). However, +actually having control over scheduling is a very uncommon case. -So it's perfectly "fine" for a Safe Rust program to get deadlocked or do -something nonsensical with incorrect synchronization. Obviously such a program -isn't very good, but Rust can only hold your hand so far. Still, a race -condition can't violate memory safety in a Rust program on its own. Only in -conjunction with some other unsafe code can a race condition actually violate -memory safety. For instance: +For this reason, it is considered "safe" for Rust to get deadlocked or do +something nonsensical with incorrect synchronization: this is known as a general +race condition or resource race. Obviously such a program isn't very good, but +Rust of course cannot prevent all logic errors. + +In any case, a race condition cannot violate memory safety in a Rust program on +its own. Only in conjunction with some other unsafe code can a race condition +actually violate memory safety. For instance, a correct program looks like this: ```rust,no_run use std::thread; @@ -58,6 +60,9 @@ thread::spawn(move || { println!("{}", data[idx.load(Ordering::SeqCst)]); ``` +We can cause a data race if we instead do the bound check in advance, and then +unsafely access the data with an unchecked value: + ```rust,no_run use std::thread; use std::sync::atomic::{AtomicUsize, Ordering}; diff --git a/src/send-and-sync.md b/src/send-and-sync.md index 34539da..808a5c3 100644 --- a/src/send-and-sync.md +++ b/src/send-and-sync.md @@ -94,6 +94,7 @@ to the heap. use std::{ mem::{align_of, size_of}, ptr, + cmp::max, }; struct Carton(ptr::NonNull); @@ -105,8 +106,8 @@ impl Carton { let mut memptr: *mut T = ptr::null_mut(); unsafe { let ret = libc::posix_memalign( - (&mut memptr).cast(), - align_of::(), + (&mut memptr as *mut *mut T).cast(), + max(align_of::(), size_of::()), size_of::() ); assert_eq!(ret, 0, "Failed to allocate or invalid alignment"); diff --git a/src/subtyping.md b/src/subtyping.md index 91e870e..4c45b2d 100644 --- a/src/subtyping.md +++ b/src/subtyping.md @@ -1,189 +1,166 @@ # Subtyping and Variance -Subtyping is a relationship between types that allows statically typed -languages to be a bit more flexible and permissive. +Rust uses lifetimes to track the relationships between borrows and ownership. +However, a naive implementation of lifetimes would be either too restrictive, +or permit undefined behavior. -Subtyping in Rust is a bit different from subtyping in other languages. This -makes it harder to give simple examples, which is a problem since subtyping, -and especially variance, is already hard to understand properly. As in, -even compiler writers mess it up all the time. +In order to allow flexible usage of lifetimes +while also preventing their misuse, Rust uses **subtyping** and **variance**. -To keep things simple, this section will consider a small extension to the -Rust language that adds a new and simpler subtyping relationship. After -establishing concepts and issues under this simpler system, -we will then relate it back to how subtyping actually occurs in Rust. - -So here's our simple extension, *Objective Rust*, featuring three new types: +Let's start with an example. ```rust -trait Animal { - fn snuggle(&self); - fn eat(&mut self); -} - -trait Cat: Animal { - fn meow(&self); +// Note: debug expects two parameters with the *same* lifetime +fn debug<'a>(a: &'a str, b: &'a str) { + println!("a = {a:?} b = {b:?}"); } -trait Dog: Animal { - fn bark(&self); +fn main() { + let hello: &'static str = "hello"; + { + let world = String::from("world"); + let world = &world; // 'world has a shorter lifetime than 'static + debug(hello, world); + } } ``` -But unlike normal traits, we can use them as concrete and sized types, just like structs. - -Now, say we have a very simple function that takes an Animal, like this: +In a conservative implementation of lifetimes, since `hello` and `world` have different lifetimes, +we might see the following error: - -```rust,ignore -fn love(pet: Animal) { - pet.snuggle(); -} +```text +error[E0308]: mismatched types + --> src/main.rs:10:16 + | +10 | debug(hello, world); + | ^ + | | + | expected `&'static str`, found struct `&'world str` ``` -By default, static types must match *exactly* for a program to compile. As such, -this code won't compile: +This would be rather unfortunate. In this case, +what we want is to accept any type that lives *at least as long* as `'world`. +Let's try using subtyping with our lifetimes. - -```rust,ignore -let mr_snuggles: Cat = ...; -love(mr_snuggles); // ERROR: expected Animal, found Cat -``` +## Subtyping -Mr. Snuggles is a Cat, and Cats aren't *exactly* Animals, so we can't love him! 😿 +Subtyping is the idea that one type can be used in place of another. -This is annoying because Cats *are* Animals. They support every operation -an Animal supports, so intuitively `love` shouldn't care if we pass it a `Cat`. -We should be able to just **forget** the non-animal parts of our `Cat`, as they -aren't necessary to love it. +Let's define that `Sub` is a subtype of `Super` (we'll be using the notation `Sub <: Super` throughout this chapter). -This is exactly the problem that *subtyping* is intended to fix. Because Cats are just -Animals **and more**, we say Cat is a *subtype* of Animal (because Cats are a *subset* -of all the Animals). Equivalently, we say that Animal is a *supertype* of Cat. -With subtypes, we can tweak our overly strict static type system -with a simple rule: anywhere a value of type `T` is expected, we will also -accept values that are subtypes of `T`. +What this is suggesting to us is that the set of *requirements* that `Super` defines +are completely satisfied by `Sub`. `Sub` may then have more requirements. -Or more concretely: anywhere an Animal is expected, a Cat or Dog will also work. +Now, in order to use subtyping with lifetimes, we need to define the requirement of a lifetime: -As we will see throughout the rest of this section, subtyping is a lot more complicated -and subtle than this, but this simple rule is a very good 99% intuition. And unless you -write unsafe code, the compiler will automatically handle all the corner cases for you. +> `'a` defines a region of code. -But this is the Rustonomicon. We're writing unsafe code, so we need to understand how -this stuff really works, and how we can mess it up. +Now that we have a defined set of requirements for lifetimes, we can define how they relate to each other: -The core problem is that this rule, naively applied, will lead to *meowing Dogs*. That is, -we can convince someone that a Dog is actually a Cat. This completely destroys the fabric -of our static type system, making it worse than useless (and leading to Undefined Behavior). +> `'long <: 'short` if and only if `'long` defines a region of code that **completely contains** `'short`. -Here's a simple example of this happening when we apply subtyping in a completely naive -"find and replace" way. +`'long` may define a region larger than `'short`, but that still fits our definition. - -```rust,ignore -fn evil_feeder(pet: &mut Animal) { - let spike: Dog = ...; +> As we will see throughout the rest of this chapter, +subtyping is a lot more complicated and subtle than this, +but this simple rule is a very good 99% intuition. +And unless you write unsafe code, the compiler will automatically handle all the corner cases for you. + +> But this is the Rustonomicon. We're writing unsafe code, +so we need to understand how this stuff really works, and how we can mess it up. - // `pet` is an Animal, and Dog is a subtype of Animal, - // so this should be fine, right..? - *pet = spike; +Going back to our example above, we can say that `'static <: 'world`. +For now, let's also accept the idea that subtypes of lifetimes can be passed through references +(more on this in [Variance](#variance)), +_e.g._ `&'static str` is a subtype of `&'world str`, then we can "downgrade" `&'static str` into a `&'world str`. +With that, the example above will compile: + +```rust +fn debug<'a>(a: &'a str, b: &'a str) { + println!("a = {a:?} b = {b:?}"); } fn main() { - let mut mr_snuggles: Cat = ...; - evil_feeder(&mut mr_snuggles); // Replaces mr_snuggles with a Dog - mr_snuggles.meow(); // OH NO, MEOWING DOG! + let hello: &'static str = "hello"; + { + let world = String::from("world"); + let world = &world; // 'world has a shorter lifetime than 'static + debug(hello, world); // hello silently downgrades from `&'static str` into `&'world str` + } } ``` -Clearly, we need a more robust system than "find and replace". That system is *variance*, -which is a set of rules governing how subtyping should compose. Most importantly, variance -defines situations where subtyping should be disabled. - -But before we get into variance, let's take a quick peek at where subtyping actually occurs in -Rust: *lifetimes*! - -> NOTE: The typed-ness of lifetimes is a fairly arbitrary construct that some -> disagree with. However it simplifies our analysis to treat lifetimes -> and types uniformly. +## Variance -Lifetimes are just regions of code, and regions can be partially ordered with the *contains* -(outlives) relationship. Subtyping on lifetimes is in terms of that relationship: -if `'big: 'small` ("big contains small" or "big outlives small"), then `'big` is a subtype -of `'small`. This is a large source of confusion, because it seems backwards -to many: the bigger region is a *subtype* of the smaller region. But it makes -sense if you consider our Animal example: Cat is an Animal *and more*, -just as `'big` is `'small` *and more*. +Above, we glossed over the fact that `'static <: 'b` implied that `&'static T <: &'b T`. This uses a property known as _variance_. +It's not always as simple as this example, though. To understand that, let's try to extend this example a bit: -Put another way, if someone wants a reference that lives for `'small`, -usually what they actually mean is that they want a reference that lives -for *at least* `'small`. They don't actually care if the lifetimes match -exactly. So it should be ok for us to **forget** that something lives for -`'big` and only remember that it lives for `'small`. +```rust,compile_fail,E0597 +fn assign(input: &mut T, val: T) { + *input = val; +} -The meowing dog problem for lifetimes will result in us being able to -store a short-lived reference in a place that expects a longer-lived one, -creating a dangling reference and letting us use-after-free. +fn main() { + let mut hello: &'static str = "hello"; + { + let world = String::from("world"); + assign(&mut hello, &world); + } + println!("{hello}"); // use after free 😿 +} +``` -It will be useful to note that `'static`, the forever lifetime, is a subtype of -every lifetime because by definition it outlives everything. We will be using -this relationship in later examples to keep them as simple as possible. +In `assign`, we are setting the `hello` reference to point to `world`. +But then `world` goes out of scope, before the later use of `hello` in the println! -With all that said, we still have no idea how to actually *use* subtyping of lifetimes, -because nothing ever has type `'a`. Lifetimes only occur as part of some larger type -like `&'a u32` or `IterMut<'a, u32>`. To apply lifetime subtyping, we need to know -how to compose subtyping. Once again, we need *variance*. +This is a classic use-after-free bug! -## Variance +Our first instinct might be to blame the `assign` impl, but there's really nothing wrong here. +It shouldn't be surprising that we might want to assign a `T` into a `T`. -Variance is where things get a bit complicated. +The problem is that we cannot assume that `&mut &'static str` and `&mut &'b str` are compatible. +This means that `&mut &'static str` **cannot** be a *subtype* of `&mut &'b str`, +even if `'static` is a subtype of `'b`. -Variance is a property that *type constructors* have with respect to their -arguments. A type constructor in Rust is any generic type with unbound arguments. -For instance `Vec` is a type constructor that takes a type `T` and returns -`Vec`. `&` and `&mut` are type constructors that take two inputs: a -lifetime, and a type to point to. +Variance is the concept that Rust borrows to define relationships about subtypes through their generic parameters. -> NOTE: For convenience we will often refer to `F` as a type constructor just so +> NOTE: For convenience we will define a generic type `F` so > that we can easily talk about `T`. Hopefully this is clear in context. -A type constructor F's *variance* is how the subtyping of its inputs affects the +The type `F`'s *variance* is how the subtyping of its inputs affects the subtyping of its outputs. There are three kinds of variance in Rust. Given two types `Sub` and `Super`, where `Sub` is a subtype of `Super`: -* `F` is *covariant* if `F` is a subtype of `F` (subtyping "passes through") -* `F` is *contravariant* if `F` is a subtype of `F` (subtyping is "inverted") -* `F` is *invariant* otherwise (no subtyping relationship exists) +* `F` is **covariant** if `F` is a subtype of `F` (the subtype property is passed through) +* `F` is **contravariant** if `F` is a subtype of `F` (the subtype property is "inverted") +* `F` is **invariant** otherwise (no subtyping relationship exists) -If `F` has multiple type parameters, we can talk about the individual variances -by saying that, for example, `F` is covariant over `T` and invariant over `U`. +If we remember from the above examples, +it was ok for us to treat `&'a T` as a subtype of `&'b T` if `'a <: 'b`, +therefore we can say that `&'a T` is *covariant* over `'a`. -It is very useful to keep in mind that covariance is, in practical terms, "the" -variance. Almost all consideration of variance is in terms of whether something -should be covariant or invariant. Actually witnessing contravariance is quite difficult -in Rust, though it does in fact exist. +Also, we saw that it was not ok for us to treat `&mut &'a U` as a subtype of `&mut &'b U`, +therefore we can say that `&mut T` is *invariant* over `T` -Here is a table of important variances which the rest of this section will be devoted -to trying to explain: +Here is a table of some other generic types and their variances: -| | | 'a | T | U | -|---|-----------------|:---------:|:-----------------:|:---------:| -| * | `&'a T ` | covariant | covariant | | -| * | `&'a mut T` | covariant | invariant | | -| * | `Box` | | covariant | | -| | `Vec` | | covariant | | -| * | `UnsafeCell` | | invariant | | -| | `Cell` | | invariant | | -| * | `fn(T) -> U` | | **contra**variant | covariant | -| | `*const T` | | covariant | | -| | `*mut T` | | invariant | | +| | 'a | T | U | +|-----------------|:---------:|:-----------------:|:---------:| +| `&'a T ` | covariant | covariant | | +| `&'a mut T` | covariant | invariant | | +| `Box` | | covariant | | +| `Vec` | | covariant | | +| `UnsafeCell` | | invariant | | +| `Cell` | | invariant | | +| `fn(T) -> U` | | **contra**variant | covariant | +| `*const T` | | covariant | | +| `*mut T` | | invariant | | -The types with \*'s are the ones we will be focusing on, as they are in -some sense "fundamental". All the others can be understood by analogy to the others: +Some of these can be explained simply in relation to the others: * `Vec` and all other owning pointers and collections follow the same logic as `Box` * `Cell` and all other interior mutability types follow the same logic as `UnsafeCell` +* `UnsafeCell` having interior mutability gives it the same variance properties as `&mut T` * `*const T` follows the logic of `&T` * `*mut T` follows the logic of `&mut T` (or `UnsafeCell`) @@ -197,116 +174,45 @@ For more types, see the ["Variance" section][variance-table] on the reference. > take references with specific lifetimes (as opposed to the usual "any lifetime", > which gets into higher rank lifetimes, which work independently of subtyping). -Ok, that's enough type theory! Let's try to apply the concept of variance to Rust -and look at some examples. - -First off, let's revisit the meowing dog example: - - -```rust,ignore -fn evil_feeder(pet: &mut Animal) { - let spike: Dog = ...; - - // `pet` is an Animal, and Dog is a subtype of Animal, - // so this should be fine, right..? - *pet = spike; -} +Now that we have some more formal understanding of variance, +let's go through some more examples in more detail. -fn main() { - let mut mr_snuggles: Cat = ...; - evil_feeder(&mut mr_snuggles); // Replaces mr_snuggles with a Dog - mr_snuggles.meow(); // OH NO, MEOWING DOG! -} -``` - -If we look at our table of variances, we see that `&mut T` is *invariant* over `T`. -As it turns out, this completely fixes the issue! With invariance, the fact that -Cat is a subtype of Animal doesn't matter; `&mut Cat` still won't be a subtype of -`&mut Animal`. The static type checker will then correctly stop us from passing -a Cat into `evil_feeder`. - -The soundness of subtyping is based on the idea that it's ok to forget unnecessary -details. But with references, there's always someone that remembers those details: -the value being referenced. That value expects those details to keep being true, -and may behave incorrectly if its expectations are violated. - -The problem with making `&mut T` covariant over `T` is that it gives us the power -to modify the original value *when we don't remember all of its constraints*. -And so, we can make someone have a Dog when they're certain they still have a Cat. - -With that established, we can easily see why `&T` being covariant over `T` *is* -sound: it doesn't let you modify the value, only look at it. Without any way to -mutate, there's no way for us to mess with any details. We can also see why -`UnsafeCell` and all the other interior mutability types must be invariant: they -make `&T` work like `&mut T`! - -Now what about the lifetime on references? Why is it ok for both kinds of references -to be covariant over their lifetimes? Well, here's a two-pronged argument: - -First and foremost, subtyping references based on their lifetimes is *the entire point -of subtyping in Rust*. The only reason we have subtyping is so we can pass -long-lived things where short-lived things are expected. So it better work! - -Second, and more seriously, lifetimes are only a part of the reference itself. The -type of the referent is shared knowledge, which is why adjusting that type in only -one place (the reference) can lead to issues. But if you shrink down a reference's -lifetime when you hand it to someone, that lifetime information isn't shared in -any way. There are now two independent references with independent lifetimes. -There's no way to mess with original reference's lifetime using the other one. - -Or rather, the only way to mess with someone's lifetime is to build a meowing dog. -But as soon as you try to build a meowing dog, the lifetime should be wrapped up -in an invariant type, preventing the lifetime from being shrunk. To understand this -better, let's port the meowing dog problem over to real Rust. - -In the meowing dog problem we take a subtype (Cat), convert it into a supertype -(Animal), and then use that fact to overwrite the subtype with a value that satisfies -the constraints of the supertype but not the subtype (Dog). - -So with lifetimes, we want to take a long-lived thing, convert it into a -short-lived thing, and then use that to write something that doesn't live long -enough into the place expecting something long-lived. - -Here it is: - -```rust,compile_fail -fn evil_feeder(input: &mut T, val: T) { +```rust,compile_fail,E0597 +fn assign(input: &mut T, val: T) { *input = val; } fn main() { - let mut mr_snuggles: &'static str = "meow! :3"; // mr. snuggles forever!! + let mut hello: &'static str = "hello"; { - let spike = String::from("bark! >:V"); - let spike_str: &str = &spike; // Only lives for the block - evil_feeder(&mut mr_snuggles, spike_str); // EVIL! + let world = String::from("world"); + assign(&mut hello, &world); } - println!("{}", mr_snuggles); // Use after free? + println!("{hello}"); } ``` And what do we get when we run this? ```text -error[E0597]: `spike` does not live long enough - --> src/main.rs:9:31 +error[E0597]: `world` does not live long enough + --> src/main.rs:9:28 | -6 | let mut mr_snuggles: &'static str = "meow! :3"; // mr. snuggles forever!! - | ------------ type annotation requires that `spike` is borrowed for `'static` +6 | let mut hello: &'static str = "hello"; + | ------------ type annotation requires that `world` is borrowed for `'static` ... -9 | let spike_str: &str = &spike; // Only lives for the block - | ^^^^^^ borrowed value does not live long enough -10 | evil_feeder(&mut mr_snuggles, spike_str); // EVIL! -11 | } - | - `spike` dropped here while still borrowed +9 | assign(&mut hello, &world); + | ^^^^^^ borrowed value does not live long enough +10 | } + | - `world` dropped here while still borrowed ``` Good, it doesn't compile! Let's break down what's happening here in detail. -First let's look at the new `evil_feeder` function: +First let's look at the `assign` function: ```rust -fn evil_feeder(input: &mut T, val: T) { +fn assign(input: &mut T, val: T) { *input = val; } ``` @@ -315,60 +221,43 @@ All it does is take a mutable reference and a value and overwrite the referent w What's important about this function is that it creates a type equality constraint. It clearly says in its signature the referent and the value must be the *exact same* type. -Meanwhile, in the caller we pass in `&mut &'static str` and `&'spike_str str`. +Meanwhile, in the caller we pass in `&mut &'static str` and `&'world str`. Because `&mut T` is invariant over `T`, the compiler concludes it can't apply any subtyping to the first argument, and so `T` must be exactly `&'static str`. -The other argument is only an `&'a str`, which *is* covariant over `'a`. So the compiler -adopts a constraint: `&'spike_str str` must be a subtype of `&'static str` (inclusive), -which in turn implies `'spike_str` must be a subtype of `'static` (inclusive). Which is to say, -`'spike_str` must contain `'static`. But only one thing contains `'static` -- `'static` itself! +This is counter to the `&T` case: -This is why we get an error when we try to assign `&spike` to `spike_str`. The -compiler has worked backwards to conclude `spike_str` must live forever, and `&spike` -simply can't live that long. +```rust +fn debug(a: T, b: T) { + println!("a = {a:?} b = {b:?}"); +} +``` -So even though references are covariant over their lifetimes, they "inherit" invariance -whenever they're put into a context that could do something bad with that. In this case, -we inherited invariance as soon as we put our reference inside an `&mut T`. +where similarly `a` and `b` must have the same type `T`. +But since `&'a T` *is* covariant over `'a`, we are allowed to perform subtyping. +So the compiler decides that `&'static str` can become `&'b str` if and only if +`&'static str` is a subtype of `&'b str`, which will hold if `'static <: 'b`. +This is true, so the compiler is happy to continue compiling this code. -As it turns out, the argument for why it's ok for Box (and Vec, Hashmap, etc.) to -be covariant is pretty similar to the argument for why it's ok for -lifetimes to be covariant: as soon as you try to stuff them in something like a -mutable reference, they inherit invariance and you're prevented from doing anything -bad. +As it turns out, the argument for why it's ok for Box (and Vec, HashMap, etc.) to be covariant is pretty similar to the argument for why it's ok for lifetimes to be covariant: as soon as you try to stuff them in something like a mutable reference, they inherit invariance and you're prevented from doing anything bad. -However Box makes it easier to focus on by-value aspect of references that we -partially glossed over. +However Box makes it easier to focus on the by-value aspect of references that we partially glossed over. -Unlike a lot of languages which allow values to be freely aliased at all times, -Rust has a very strict rule: if you're allowed to mutate or move a value, you -are guaranteed to be the only one with access to it. +Unlike a lot of languages which allow values to be freely aliased at all times, Rust has a very strict rule: if you're allowed to mutate or move a value, you are guaranteed to be the only one with access to it. Consider the following code: - ```rust,ignore -let mr_snuggles: Box = ..; -let spike: Box = ..; +let hello: Box<&'static str> = Box::new("hello"); -let mut pet: Box; -pet = mr_snuggles; -pet = spike; +let mut world: Box<&'b str>; +world = hello; ``` -There is no problem at all with the fact that we have forgotten that `mr_snuggles` was a Cat, -or that we overwrote him with a Dog, because as soon as we moved mr_snuggles to a variable -that only knew he was an Animal, **we destroyed the only thing in the universe that -remembered he was a Cat**! - -In contrast to the argument about immutable references being soundly covariant because they -don't let you change anything, owned values can be covariant because they make you -change *everything*. There is no connection between old locations and new locations. -Applying by-value subtyping is an irreversible act of knowledge destruction, and -without any memory of how things used to be, no one can be tricked into acting on -that old information! +There is no problem at all with the fact that we have forgotten that `hello` was alive for `'static`, +because as soon as we moved `hello` to a variable that only knew it was alive for `'b`, +**we destroyed the only thing in the universe that remembered it lived for longer**! Only one thing left to explain: function pointers. @@ -376,43 +265,75 @@ To see why `fn(T) -> U` should be covariant over `U`, consider the following sig ```rust,ignore -fn get_animal() -> Animal; +fn get_str() -> &'a str; ``` -This function claims to produce an Animal. As such, it is perfectly valid to +This function claims to produce a `str` bound by some liftime `'a`. As such, it is perfectly valid to provide a function with the following signature instead: ```rust,ignore -fn get_animal() -> Cat; +fn get_static() -> &'static str; ``` -After all, Cats are Animals, so always producing a Cat is a perfectly valid way -to produce Animals. Or to relate it back to real Rust: if we need a function -that is supposed to produce something that lives for `'short`, it's perfectly -fine for it to produce something that lives for `'long`. We don't care, we can -just forget that fact. +So when the function is called, all it's expecting is a `&str` which lives at least the lifetime of `'a`, +it doesn't matter if the value actually lives longer. However, the same logic does not apply to *arguments*. Consider trying to satisfy: ```rust,ignore -fn handle_animal(Animal); +fn store_ref(&'a str); ``` with: ```rust,ignore -fn handle_animal(Cat); +fn store_static(&'static str); ``` -The first function can accept Dogs, but the second function absolutely can't. +The first function can accept any string reference as long as it lives at least for `'a`, +but the second cannot accept a string reference that lives for any duration less than `'static`, +which would cause a conflict. Covariance doesn't work here. But if we flip it around, it actually *does* -work! If we need a function that can handle Cats, a function that can handle *any* -Animal will surely work fine. Or to relate it back to real Rust: if we need a -function that can handle anything that lives for at least `'long`, it's perfectly -fine for it to be able to handle anything that lives for at least `'short`. +work! If we need a function that can handle `&'static str`, a function that can handle *any* reference lifetime +will surely work fine. + +Let's see this in practice + +```rust,compile_fail +# use std::cell::RefCell; +thread_local! { + pub static StaticVecs: RefCell> = RefCell::new(Vec::new()); +} + +/// saves the input given into a thread local `Vec<&'static str>` +fn store(input: &'static str) { + StaticVecs.with_borrow_mut(|v| v.push(input)); +} + +/// Calls the function with it's input (must have the same lifetime!) +fn demo<'a>(input: &'a str, f: fn(&'a str)) { + f(input); +} + +fn main() { + demo("hello", store); // "hello" is 'static. Can call `store` fine + + { + let smuggle = String::from("smuggle"); + + // `&smuggle` is not static. If we were to call `store` with `&smuggle`, + // we would have pushed an invalid lifetime into the `StaticVecs`. + // Therefore, `fn(&'static str)` cannot be a subtype of `fn(&'a str)` + demo(&smuggle, store); + } + + // use after free 😿 + StaticVecs.with_borrow(|v| println!("{v:?}")); +} +``` And that's why function types, unlike anything else in the language, are **contra**variant over their arguments. diff --git a/src/transmutes.md b/src/transmutes.md index 1f6d7d5..eea8668 100644 --- a/src/transmutes.md +++ b/src/transmutes.md @@ -2,7 +2,7 @@ Get out of our way type system! We're going to reinterpret these bits or die trying! Even though this book is all about doing things that are unsafe, I -really can't emphasize that you should deeply think about finding Another Way +really can't emphasize enough that you should deeply think about finding Another Way than the operations covered in this section. This is really, truly, the most horribly unsafe thing you can do in Rust. The guardrails here are dental floss. diff --git a/src/unbounded-lifetimes.md b/src/unbounded-lifetimes.md index 03febd6..9ca2a2f 100644 --- a/src/unbounded-lifetimes.md +++ b/src/unbounded-lifetimes.md @@ -1,13 +1,13 @@ # Unbounded Lifetimes Unsafe code can often end up producing references or lifetimes out of thin air. -Such lifetimes come into the world as *unbounded*. The most common source of this -is dereferencing a raw pointer, which produces a reference with an unbounded lifetime. -Such a lifetime becomes as big as context demands. This is in fact more powerful -than simply becoming `'static`, because for instance `&'static &'a T` -will fail to typecheck, but the unbound lifetime will perfectly mold into -`&'a &'a T` as needed. However for most intents and purposes, such an unbounded -lifetime can be regarded as `'static`. +Such lifetimes come into the world as *unbounded*. The most common source of +this is taking a reference to a dereferenced raw pointer, which produces a +reference with an unbounded lifetime. Such a lifetime becomes as big as context +demands. This is in fact more powerful than simply becoming `'static`, because +for instance `&'static &'a T` will fail to typecheck, but the unbound lifetime +will perfectly mold into `&'a &'a T` as needed. However for most intents and +purposes, such an unbounded lifetime can be regarded as `'static`. Almost no reference is `'static`, so this is probably wrong. `transmute` and `transmute_copy` are the two other primary offenders. One should endeavor to @@ -17,17 +17,25 @@ boundaries. Given a function, any output lifetimes that don't derive from inputs are unbounded. For instance: - -```rust,ignore -fn get_str<'a>() -> &'a str; + +```rust,no_run +fn get_str<'a>(s: *const String) -> &'a str { + unsafe { &*s } +} + +fn main() { + let soon_dropped = String::from("hello"); + let dangling = get_str(&soon_dropped); + drop(soon_dropped); + println!("Invalid str: {}", dangling); // Invalid str: gӚ_` +} ``` -will produce an `&str` with an unbounded lifetime. The easiest way to avoid -unbounded lifetimes is to use lifetime elision at the function boundary. -If an output lifetime is elided, then it *must* be bounded by an input lifetime. -Of course it might be bounded by the *wrong* lifetime, but this will usually -just cause a compiler error, rather than allow memory safety to be trivially -violated. +The easiest way to avoid unbounded lifetimes is to use lifetime elision at the +function boundary. If an output lifetime is elided, then it *must* be bounded by +an input lifetime. Of course it might be bounded by the *wrong* lifetime, but +this will usually just cause a compiler error, rather than allow memory safety +to be trivially violated. Within a function, bounding lifetimes is more error-prone. The safest and easiest way to bound a lifetime is to return it from a function with a bound lifetime. diff --git a/src/unchecked-uninit.md b/src/unchecked-uninit.md index c61415c..b3dd31c 100644 --- a/src/unchecked-uninit.md +++ b/src/unchecked-uninit.md @@ -11,7 +11,7 @@ Unsafe Rust gives us a powerful tool to handle this problem: [`MaybeUninit`]. This type can be used to handle memory that has not been fully initialized yet. -With `MaybeUninit`, we can initialize an array element-for-element as follows: +With `MaybeUninit`, we can initialize an array element by element as follows: ```rust use std::mem::{self, MaybeUninit}; @@ -79,8 +79,7 @@ This code proceeds in three steps: acknowledge that by providing appropriate methods). It's worth spending a bit more time on the loop in the middle, and in particular -the assignment operator and its interaction with `drop`. If we would have -written something like: +the assignment operator and its interaction with `drop`. If we wrote something like: ```rust,ignore @@ -88,7 +87,7 @@ written something like: ``` we would actually overwrite a `Box`, leading to `drop` of uninitialized -data, which will cause much sadness and pain. +data, which would cause much sadness and pain. The correct alternative, if for some reason we cannot use `MaybeUninit::new`, is to use the [`ptr`] module. In particular, it provides three functions that allow @@ -97,7 +96,7 @@ us to assign bytes to a location in memory without dropping the old value: * `ptr::write(ptr, val)` takes a `val` and moves it into the address pointed to by `ptr`. -* `ptr::copy(src, dest, count)` copies the bits that `count` T's would occupy +* `ptr::copy(src, dest, count)` copies the bits that `count` T items would occupy from src to dest. (this is equivalent to C's memmove -- note that the argument order is reversed!) * `ptr::copy_nonoverlapping(src, dest, count)` does what `copy` does, but a @@ -105,8 +104,8 @@ us to assign bytes to a location in memory without dropping the old value: (this is equivalent to C's memcpy -- note that the argument order is reversed!) It should go without saying that these functions, if misused, will cause serious -havoc or just straight up Undefined Behavior. The only things that these -functions *themselves* require is that the locations you want to read and write +havoc or just straight up Undefined Behavior. The only requirement of these +functions *themselves* is that the locations you want to read and write are allocated and properly aligned. However, the ways writing arbitrary bits to arbitrary locations of memory can break things are basically uncountable! diff --git a/src/vec/vec-alloc.md b/src/vec/vec-alloc.md index 6c69c93..2495473 100644 --- a/src/vec/vec-alloc.md +++ b/src/vec/vec-alloc.md @@ -28,7 +28,6 @@ impl Vec { ptr: NonNull::dangling(), len: 0, cap: 0, - _marker: PhantomData, } } } diff --git a/src/vec/vec-drain.md b/src/vec/vec-drain.md index 7a0e7f8..763c82a 100644 --- a/src/vec/vec-drain.md +++ b/src/vec/vec-drain.md @@ -93,7 +93,7 @@ impl IntoIterator for Vec { mem::forget(self); IntoIter { - iter: iter, + iter, _buf: buf, } } @@ -135,18 +135,16 @@ impl<'a, T> Drop for Drain<'a, T> { impl Vec { pub fn drain(&mut self) -> Drain { - unsafe { - let iter = RawValIter::new(&self); + let iter = unsafe { RawValIter::new(&self) }; - // this is a mem::forget safety thing. If Drain is forgotten, we just - // leak the whole Vec's contents. Also we need to do this *eventually* - // anyway, so why not do it now? - self.len = 0; + // this is a mem::forget safety thing. If Drain is forgotten, we just + // leak the whole Vec's contents. Also we need to do this *eventually* + // anyway, so why not do it now? + self.len = 0; - Drain { - iter: iter, - vec: PhantomData, - } + Drain { + iter, + vec: PhantomData, } } } diff --git a/src/vec/vec-final.md b/src/vec/vec-final.md index 1f8af37..1f73036 100644 --- a/src/vec/vec-final.md +++ b/src/vec/vec-final.md @@ -10,7 +10,6 @@ use std::ptr::{self, NonNull}; struct RawVec { ptr: NonNull, cap: usize, - _marker: PhantomData, } unsafe impl Send for RawVec {} @@ -24,8 +23,7 @@ impl RawVec { // `NonNull::dangling()` doubles as "unallocated" and "zero-sized allocation" RawVec { ptr: NonNull::dangling(), - cap: cap, - _marker: PhantomData, + cap, } } @@ -129,7 +127,7 @@ impl Vec { pub fn insert(&mut self, index: usize, elem: T) { assert!(index <= self.len, "index out of bounds"); - if self.cap() == self.len { + if self.len == self.cap() { self.buf.grow(); } @@ -140,14 +138,17 @@ impl Vec { self.len - index, ); ptr::write(self.ptr().add(index), elem); - self.len += 1; } + + self.len += 1; } pub fn remove(&mut self, index: usize) -> T { assert!(index < self.len, "index out of bounds"); + + self.len -= 1; + unsafe { - self.len -= 1; let result = ptr::read(self.ptr().add(index)); ptr::copy( self.ptr().add(index + 1), @@ -159,18 +160,16 @@ impl Vec { } pub fn drain(&mut self) -> Drain { - unsafe { - let iter = RawValIter::new(&self); + let iter = unsafe { RawValIter::new(&self) }; - // this is a mem::forget safety thing. If Drain is forgotten, we just - // leak the whole Vec's contents. Also we need to do this *eventually* - // anyway, so why not do it now? - self.len = 0; + // this is a mem::forget safety thing. If Drain is forgotten, we just + // leak the whole Vec's contents. Also we need to do this *eventually* + // anyway, so why not do it now? + self.len = 0; - Drain { - iter: iter, - vec: PhantomData, - } + Drain { + iter, + vec: PhantomData, } } } @@ -199,15 +198,15 @@ impl IntoIterator for Vec { type Item = T; type IntoIter = IntoIter; fn into_iter(self) -> IntoIter { - unsafe { - let iter = RawValIter::new(&self); - let buf = ptr::read(&self.buf); - mem::forget(self); + let (iter, buf) = unsafe { + (RawValIter::new(&self), ptr::read(&self.buf)) + }; - IntoIter { - iter: iter, - _buf: buf, - } + mem::forget(self); + + IntoIter { + iter, + _buf: buf, } } } diff --git a/src/vec/vec-insert-remove.md b/src/vec/vec-insert-remove.md index 57283f9..2acee65 100644 --- a/src/vec/vec-insert-remove.md +++ b/src/vec/vec-insert-remove.md @@ -18,16 +18,19 @@ pub fn insert(&mut self, index: usize, elem: T) { // Note: `<=` because it's valid to insert after everything // which would be equivalent to push. assert!(index <= self.len, "index out of bounds"); - if self.cap == self.len { self.grow(); } + if self.len == self.cap { self.grow(); } unsafe { // ptr::copy(src, dest, len): "copy from src to dest len elems" - ptr::copy(self.ptr.as_ptr().add(index), - self.ptr.as_ptr().add(index + 1), - self.len - index); + ptr::copy( + self.ptr.as_ptr().add(index), + self.ptr.as_ptr().add(index + 1), + self.len - index, + ); ptr::write(self.ptr.as_ptr().add(index), elem); - self.len += 1; } + + self.len += 1; } ``` @@ -42,9 +45,11 @@ pub fn remove(&mut self, index: usize) -> T { unsafe { self.len -= 1; let result = ptr::read(self.ptr.as_ptr().add(index)); - ptr::copy(self.ptr.as_ptr().add(index + 1), - self.ptr.as_ptr().add(index), - self.len - index); + ptr::copy( + self.ptr.as_ptr().add(index + 1), + self.ptr.as_ptr().add(index), + self.len - index, + ); result } } diff --git a/src/vec/vec-into-iter.md b/src/vec/vec-into-iter.md index 61782e3..ad22ff9 100644 --- a/src/vec/vec-into-iter.md +++ b/src/vec/vec-into-iter.md @@ -49,7 +49,6 @@ pub struct IntoIter { cap: usize, start: *const T, end: *const T, - _marker: PhantomData, } ``` @@ -61,27 +60,24 @@ impl IntoIterator for Vec { type Item = T; type IntoIter = IntoIter; fn into_iter(self) -> IntoIter { - // Can't destructure Vec since it's Drop - let ptr = self.ptr; - let cap = self.cap; - let len = self.len; - // Make sure not to drop Vec since that would free the buffer - mem::forget(self); - - unsafe { - IntoIter { - buf: ptr, - cap: cap, - start: ptr.as_ptr(), - end: if cap == 0 { - // can't offset off this pointer, it's not allocated! - ptr.as_ptr() - } else { - ptr.as_ptr().add(len) - }, - _marker: PhantomData, - } + let vec = ManuallyDrop::new(self); + + // Can't destructure Vec since it's Drop + let ptr = vec.ptr; + let cap = vec.cap; + let len = vec.len; + + IntoIter { + buf: ptr, + cap, + start: ptr.as_ptr(), + end: if cap == 0 { + // can't offset off this pointer, it's not allocated! + ptr.as_ptr() + } else { + unsafe { ptr.as_ptr().add(len) } + }, } } } diff --git a/src/vec/vec-layout.md b/src/vec/vec-layout.md index c1c1afc..695485f 100644 --- a/src/vec/vec-layout.md +++ b/src/vec/vec-layout.md @@ -15,13 +15,10 @@ pub struct Vec { } ``` -And indeed this would compile. Unfortunately, it would be incorrect. First, the +And indeed this would compile. Unfortunately, it would be too strict. The compiler will give us too strict variance. So a `&Vec<&'static str>` -couldn't be used where an `&Vec<&'a str>` was expected. More importantly, it -will give incorrect ownership information to the drop checker, as it will -conservatively assume we don't own any values of type `T`. See [the chapter -on ownership and lifetimes][ownership] for all the details on variance and -drop check. +couldn't be used where a `&Vec<&'a str>` was expected. See [the chapter +on ownership and lifetimes][ownership] for all the details on variance. As we saw in the ownership chapter, the standard library uses `Unique` in place of `*mut T` when it has a raw pointer to an allocation that it owns. Unique is unstable, @@ -30,26 +27,24 @@ so we'd like to not use it if possible, though. As a recap, Unique is a wrapper around a raw pointer that declares that: * We are covariant over `T` -* We may own a value of type `T` (for drop check) +* We may own a value of type `T` (this is not relevant for our example here, but see + [the chapter on PhantomData][phantom-data] on why the real `std::vec::Vec` needs this) * We are Send/Sync if `T` is Send/Sync * Our pointer is never null (so `Option>` is null-pointer-optimized) We can implement all of the above requirements in stable Rust. To do this, instead of using `Unique` we will use [`NonNull`][NonNull], another wrapper around a raw pointer, which gives us two of the above properties, namely it is covariant -over `T` and is declared to never be null. By adding a `PhantomData` (for drop -check) and implementing Send/Sync if `T` is, we get the same results as using -`Unique`: +over `T` and is declared to never be null. By implementing Send/Sync if `T` is, +we get the same results as using `Unique`: ```rust use std::ptr::NonNull; -use std::marker::PhantomData; pub struct Vec { ptr: NonNull, cap: usize, len: usize, - _marker: PhantomData, } unsafe impl Send for Vec {} @@ -58,4 +53,5 @@ unsafe impl Sync for Vec {} ``` [ownership]: ../ownership.html +[phantom-data]: ../phantom-data.md [NonNull]: ../../std/ptr/struct.NonNull.html diff --git a/src/vec/vec-raw.md b/src/vec/vec-raw.md index e86537b..a251b4a 100644 --- a/src/vec/vec-raw.md +++ b/src/vec/vec-raw.md @@ -13,7 +13,6 @@ allocating, growing, and freeing: struct RawVec { ptr: NonNull, cap: usize, - _marker: PhantomData, } unsafe impl Send for RawVec {} @@ -25,23 +24,17 @@ impl RawVec { RawVec { ptr: NonNull::dangling(), cap: 0, - _marker: PhantomData, } } fn grow(&mut self) { - let (new_cap, new_layout) = if self.cap == 0 { - (1, Layout::array::(1).unwrap()) - } else { - // This can't overflow because we ensure self.cap <= isize::MAX. - let new_cap = 2 * self.cap; - - // Layout::array checks that the number of bytes is <= usize::MAX, - // but this is redundant since old_layout.size() <= isize::MAX, - // so the `unwrap` should never fail. - let new_layout = Layout::array::(new_cap).unwrap(); - (new_cap, new_layout) - }; + // This can't overflow because we ensure self.cap <= isize::MAX. + let new_cap = if self.cap == 0 { 1 } else { 2 * self.cap }; + + // Layout::array checks that the number of bytes is <= usize::MAX, + // but this is redundant since old_layout.size() <= isize::MAX, + // so the `unwrap` should never fail. + let new_layout = Layout::array::(new_cap).unwrap(); // Ensure that the new allocation doesn't exceed `isize::MAX` bytes. assert!(new_layout.size() <= isize::MAX as usize, "Allocation too large"); @@ -138,23 +131,21 @@ impl IntoIterator for Vec { type Item = T; type IntoIter = IntoIter; fn into_iter(self) -> IntoIter { - unsafe { - // need to use ptr::read to unsafely move the buf out since it's - // not Copy, and Vec implements Drop (so we can't destructure it). - let buf = ptr::read(&self.buf); - let len = self.len; - mem::forget(self); - - IntoIter { - start: buf.ptr.as_ptr(), - end: if buf.cap == 0 { - // can't offset off of a pointer unless it's part of an allocation - buf.ptr.as_ptr() - } else { - buf.ptr.as_ptr().add(len) - }, - _buf: buf, - } + // need to use ptr::read to unsafely move the buf out since it's + // not Copy, and Vec implements Drop (so we can't destructure it). + let buf = unsafe { ptr::read(&self.buf) }; + let len = self.len; + mem::forget(self); + + IntoIter { + start: buf.ptr.as_ptr(), + end: if buf.cap == 0 { + // can't offset off of a pointer unless it's part of an allocation + buf.ptr.as_ptr() + } else { + unsafe { buf.ptr.as_ptr().add(len) } + }, + _buf: buf, } } } diff --git a/src/vec/vec-zsts.md b/src/vec/vec-zsts.md index 73a97ba..6715f94 100644 --- a/src/vec/vec-zsts.md +++ b/src/vec/vec-zsts.md @@ -33,14 +33,13 @@ method of `RawVec`. ```rust,ignore impl RawVec { fn new() -> Self { - // !0 is usize::MAX. This branch should be stripped at compile time. - let cap = if mem::size_of::() == 0 { !0 } else { 0 }; + // This branch should be stripped at compile time. + let cap = if mem::size_of::() == 0 { usize::MAX } else { 0 }; // `NonNull::dangling()` doubles as "unallocated" and "zero-sized allocation" RawVec { ptr: NonNull::dangling(), - cap: cap, - _marker: PhantomData, + cap, } } diff --git a/src/what-unsafe-does.md b/src/what-unsafe-does.md index 64694ee..67fbe8a 100644 --- a/src/what-unsafe-does.md +++ b/src/what-unsafe-does.md @@ -71,8 +71,7 @@ Rust considers it "safe" to: * Deadlock * Have a [race condition][race] * Leak memory -* Fail to call destructors -* Overflow integers +* Overflow integers (with the built-in operators such as `+` etc.) * Abort the program * Delete the production database