Auto merge of rust-lang#123402 - workingjubilee:rollup-0j5ihn6, r=wor…

…kingjubilee

Rollup of 4 pull requests

Successful merges:

 - rust-lang#122411 ( Provide cabi_realloc on wasm32-wasip2 by default )
 - rust-lang#123349 (Fix capture analysis for by-move closure bodies)
 - rust-lang#123359 (Link against libc++abi and libunwind as well when building LLVM wrappers on AIX)
 - rust-lang#123388 (use a consistent style for links)

r? `@ghost`
`@rustbot` modify labels: rollup

compiler/rustc_llvm/build.rs

@@ -391,6 +391,12 @@ fn main() {
         }
     }
 
+    // libc++abi and libunwind have to be specified explicitly on AIX.
+    if target.contains("aix") {
+        println!("cargo:rustc-link-lib=c++abi");
+        println!("cargo:rustc-link-lib=unwind");
+    }
+
     // Libstdc++ depends on pthread which Rust doesn't link on MinGW
     // since nothing else requires it.
     if target.ends_with("windows-gnu") {

compiler/rustc_mir_transform/src/coroutine/by_move_body.rs

@@ -1,7 +1,66 @@
-//! A MIR pass which duplicates a coroutine's body and removes any derefs which
-//! would be present for upvars that are taken by-ref. The result of which will
-//! be a coroutine body that takes all of its upvars by-move, and which we stash
-//! into the `CoroutineInfo` for all coroutines returned by coroutine-closures.
+//! This pass constructs a second coroutine body sufficient for return from
+//! `FnOnce`/`AsyncFnOnce` implementations for coroutine-closures (e.g. async closures).
+//!
+//! Consider an async closure like:
+//! ```rust
+//! #![feature(async_closure)]
+//!
+//! let x = vec![1, 2, 3];
+//!
+//! let closure = async move || {
+//!     println!("{x:#?}");
+//! };
+//! ```
+//!
+//! This desugars to something like:
+//! ```rust,ignore (invalid-borrowck)
+//! let x = vec![1, 2, 3];
+//!
+//! let closure = move || {
+//!     async {
+//!         println!("{x:#?}");
+//!     }
+//! };
+//! ```
+//!
+//! Important to note here is that while the outer closure *moves* `x: Vec<i32>`
+//! into its upvars, the inner `async` coroutine simply captures a ref of `x`.
+//! This is the "magic" of async closures -- the futures that they return are
+//! allowed to borrow from their parent closure's upvars.
+//!
+//! However, what happens when we call `closure` with `AsyncFnOnce` (or `FnOnce`,
+//! since all async closures implement that too)? Well, recall the signature:
+//! ```
+//! use std::future::Future;
+//! pub trait AsyncFnOnce<Args>
+//! {
+//!     type CallOnceFuture: Future<Output = Self::Output>;
+//!     type Output;
+//!     fn async_call_once(
+//!         self,
+//!         args: Args
+//!     ) -> Self::CallOnceFuture;
+//! }
+//! ```
+//!
+//! This signature *consumes* the async closure (`self`) and returns a `CallOnceFuture`.
+//! How do we deal with the fact that the coroutine is supposed to take a reference
+//! to the captured `x` from the parent closure, when that parent closure has been
+//! destroyed?
+//!
+//! This is the second piece of magic of async closures. We can simply create a
+//! *second* `async` coroutine body where that `x` that was previously captured
+//! by reference is now captured by value. This means that we consume the outer
+//! closure and return a new coroutine that will hold onto all of these captures,
+//! and drop them when it is finished (i.e. after it has been `.await`ed).
+//!
+//! We do this with the analysis below, which detects the captures that come from
+//! borrowing from the outer closure, and we simply peel off a `deref` projection
+//! from them. This second body is stored alongside the first body, and optimized
+//! with it in lockstep. When we need to resolve a body for `FnOnce` or `AsyncFnOnce`,
+//! we use this "by move" body instead.
+
+use itertools::Itertools;
 
 use rustc_data_structures::unord::UnordSet;
 use rustc_hir as hir;
@@ -14,6 +73,8 @@ pub struct ByMoveBody;
 
 impl<'tcx> MirPass<'tcx> for ByMoveBody {
     fn run_pass(&self, tcx: TyCtxt<'tcx>, body: &mut mir::Body<'tcx>) {
+        // We only need to generate by-move coroutine bodies for coroutines that come
+        // from coroutine-closures.
         let Some(coroutine_def_id) = body.source.def_id().as_local() else {
             return;
         };
@@ -22,44 +83,70 @@ impl<'tcx> MirPass<'tcx> for ByMoveBody {
         else {
             return;
         };
+
+        // Also, let's skip processing any bodies with errors, since there's no guarantee
+        // the MIR body will be constructed well.
         let coroutine_ty = body.local_decls[ty::CAPTURE_STRUCT_LOCAL].ty;
         if coroutine_ty.references_error() {
             return;
         }
-        let ty::Coroutine(_, args) = *coroutine_ty.kind() else { bug!("{body:#?}") };
 
-        let coroutine_kind = args.as_coroutine().kind_ty().to_opt_closure_kind().unwrap();
+        let ty::Coroutine(_, coroutine_args) = *coroutine_ty.kind() else { bug!("{body:#?}") };
+        // We don't need to generate a by-move coroutine if the kind of the coroutine is
+        // already `FnOnce` -- that means that any upvars that the closure consumes have
+        // already been taken by-value.
+        let coroutine_kind = coroutine_args.as_coroutine().kind_ty().to_opt_closure_kind().unwrap();
         if coroutine_kind == ty::ClosureKind::FnOnce {
             return;
         }
 
+        let parent_def_id = tcx.local_parent(coroutine_def_id);
+        let ty::CoroutineClosure(_, parent_args) =
+            *tcx.type_of(parent_def_id).instantiate_identity().kind()
+        else {
+            bug!();
+        };
+        let parent_closure_args = parent_args.as_coroutine_closure();
+        let num_args = parent_closure_args
+            .coroutine_closure_sig()
+            .skip_binder()
+            .tupled_inputs_ty
+            .tuple_fields()
+            .len();
+
         let mut by_ref_fields = UnordSet::default();
-        let by_move_upvars = Ty::new_tup_from_iter(
-            tcx,
-            tcx.closure_captures(coroutine_def_id).iter().enumerate().map(|(idx, capture)| {
-                if capture.is_by_ref() {
-                    by_ref_fields.insert(FieldIdx::from_usize(idx));
-                }
-                capture.place.ty()
-            }),
-        );
-        let by_move_coroutine_ty = Ty::new_coroutine(
-            tcx,
-            coroutine_def_id.to_def_id(),
-            ty::CoroutineArgs::new(
+        for (idx, (coroutine_capture, parent_capture)) in tcx
+            .closure_captures(coroutine_def_id)
+            .iter()
+            // By construction we capture all the args first.
+            .skip(num_args)
+            .zip_eq(tcx.closure_captures(parent_def_id))
+            .enumerate()
+        {
+            // This upvar is captured by-move from the parent closure, but by-ref
+            // from the inner async block. That means that it's being borrowed from
+            // the outer closure body -- we need to change the coroutine to take the
+            // upvar by value.
+            if coroutine_capture.is_by_ref() && !parent_capture.is_by_ref() {
+                by_ref_fields.insert(FieldIdx::from_usize(num_args + idx));
+            }
+
+            // Make sure we're actually talking about the same capture.
+            // FIXME(async_closures): We could look at the `hir::Upvar` instead?
+            assert_eq!(coroutine_capture.place.ty(), parent_capture.place.ty());
+        }
+
+        let by_move_coroutine_ty = tcx
+            .instantiate_bound_regions_with_erased(parent_closure_args.coroutine_closure_sig())
+            .to_coroutine_given_kind_and_upvars(
                 tcx,
-                ty::CoroutineArgsParts {
-                    parent_args: args.as_coroutine().parent_args(),
-                    kind_ty: Ty::from_closure_kind(tcx, ty::ClosureKind::FnOnce),
-                    resume_ty: args.as_coroutine().resume_ty(),
-                    yield_ty: args.as_coroutine().yield_ty(),
-                    return_ty: args.as_coroutine().return_ty(),
-                    witness: args.as_coroutine().witness(),
-                    tupled_upvars_ty: by_move_upvars,
-                },
-            )
-            .args,
-        );
+                parent_closure_args.parent_args(),
+                coroutine_def_id.to_def_id(),
+                ty::ClosureKind::FnOnce,
+                tcx.lifetimes.re_erased,
+                parent_closure_args.tupled_upvars_ty(),
+                parent_closure_args.coroutine_captures_by_ref_ty(),
+            );
 
         let mut by_move_body = body.clone();
         MakeByMoveBody { tcx, by_ref_fields, by_move_coroutine_ty }.visit_body(&mut by_move_body);

library/std/src/fs.rs

@@ -37,7 +37,7 @@ use crate::time::SystemTime;
 ///
 /// # Examples
 ///
-/// Creates a new file and write bytes to it (you can also use [`write()`]):
+/// Creates a new file and write bytes to it (you can also use [`write`]):
 ///
 /// ```no_run
 /// use std::fs::File;
@@ -2018,7 +2018,7 @@ pub fn rename<P: AsRef<Path>, Q: AsRef<Path>>(from: P, to: Q) -> io::Result<()>
 /// the length of the `to` file as reported by `metadata`.
 ///
 /// If you want to copy the contents of one file to another and you’re
-/// working with [`File`]s, see the [`io::copy()`] function.
+/// working with [`File`]s, see the [`io::copy`](io::copy()) function.
 ///
 /// # Platform-specific behavior
 ///

library/std/src/sys/pal/mod.rs

@@ -37,12 +37,12 @@ cfg_if::cfg_if! {
     } else if #[cfg(target_os = "hermit")] {
         mod hermit;
         pub use self::hermit::*;
-    } else if #[cfg(target_os = "wasi")] {
-        mod wasi;
-        pub use self::wasi::*;
     } else if #[cfg(all(target_os = "wasi", target_env = "p2"))] {
         mod wasip2;
         pub use self::wasip2::*;
+    } else if #[cfg(target_os = "wasi")] {
+        mod wasi;
+        pub use self::wasi::*;
     } else if #[cfg(target_family = "wasm")] {
         mod wasm;
         pub use self::wasm::*;

library/std/src/sys/pal/wasip2/cabi_realloc.rs

@@ -0,0 +1,65 @@
+//! This module contains a canonical definition of the `cabi_realloc` function
+//! for the component model.
+//!
+//! The component model's canonical ABI for representing datatypes in memory
+//! makes use of this function when transferring lists and strings, for example.
+//! This function behaves like C's `realloc` but also takes alignment into
+//! account.
+//!
+//! Components are notably not required to export this function, but nearly
+//! all components end up doing so currently. This definition in the standard
+//! library removes the need for all compilations to define this themselves.
+//!
+//! More information about the canonical ABI can be found at
+//! <https://github.com/WebAssembly/component-model/blob/main/design/mvp/CanonicalABI.md>
+//!
+//! Note that the name of this function is not standardized in the canonical ABI
+//! at this time. Instead it's a convention of the "componentization process"
+//! where a core wasm module is converted to a component to use this name.
+//! Additionally this is not the only possible definition of this function, so
+//! this is defined as a "weak" symbol. This means that other definitions are
+//! allowed to overwrite it if they are present in a compilation.
+
+use crate::alloc::{self, Layout};
+use crate::ptr;
+
+#[used]
+static FORCE_CODEGEN_OF_CABI_REALLOC: unsafe extern "C" fn(
+    *mut u8,
+    usize,
+    usize,
+    usize,
+) -> *mut u8 = cabi_realloc;
+
+#[linkage = "weak"]
+#[no_mangle]
+pub unsafe extern "C" fn cabi_realloc(
+    old_ptr: *mut u8,
+    old_len: usize,
+    align: usize,
+    new_len: usize,
+) -> *mut u8 {
+    let layout;
+    let ptr = if old_len == 0 {
+        if new_len == 0 {
+            return ptr::without_provenance_mut(align);
+        }
+        layout = Layout::from_size_align_unchecked(new_len, align);
+        alloc::alloc(layout)
+    } else {
+        debug_assert_ne!(new_len, 0, "non-zero old_len requires non-zero new_len!");
+        layout = Layout::from_size_align_unchecked(old_len, align);
+        alloc::realloc(old_ptr, layout, new_len)
+    };
+    if ptr.is_null() {
+        // Print a nice message in debug mode, but in release mode don't
+        // pull in so many dependencies related to printing so just emit an
+        // `unreachable` instruction.
+        if cfg!(debug_assertions) {
+            alloc::handle_alloc_error(layout);
+        } else {
+            super::abort_internal();
+        }
+    }
+    return ptr;
+}

library/std/src/sys/pal/wasip2/mod.rs

@@ -10,8 +10,6 @@
 pub mod alloc;
 #[path = "../wasi/args.rs"]
 pub mod args;
-#[path = "../unix/cmath.rs"]
-pub mod cmath;
 #[path = "../wasi/env.rs"]
 pub mod env;
 #[path = "../wasi/fd.rs"]
@@ -28,10 +26,6 @@ pub mod io;
 pub mod net;
 #[path = "../wasi/os.rs"]
 pub mod os;
-#[path = "../unix/os_str.rs"]
-pub mod os_str;
-#[path = "../unix/path.rs"]
-pub mod path;
 #[path = "../unsupported/pipe.rs"]
 pub mod pipe;
 #[path = "../unsupported/process.rs"]
@@ -72,3 +66,5 @@ pub use helpers::decode_error_kind;
 use helpers::err2io;
 pub use helpers::hashmap_random_keys;
 pub use helpers::is_interrupted;
+
+mod cabi_realloc;