Auto merge of rust-lang#134177 - matthiaskrgr:rollup-hgp8q60, r=matthiaskrgr

Rollup of 6 pull requests

Successful merges:

 - rust-lang#132975 (De-duplicate and improve definition of core::ffi::c_char)
 - rust-lang#133598 (Change `GetManyMutError` to match T-libs-api decision)
 - rust-lang#134148 (add comments in check_expr_field)
 - rust-lang#134163 (coverage: Rearrange the code for embedding per-function coverage metadata)
 - rust-lang#134165 (wasm(32|64): update alignment string)
 - rust-lang#134170 (Subtree update of `rust-analyzer`)

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

Author: bors

alloc/src/slice.rs

@@ -27,6 +27,8 @@ pub use core::slice::ArrayChunksMut;
 pub use core::slice::ArrayWindows;
 #[stable(feature = "inherent_ascii_escape", since = "1.60.0")]
 pub use core::slice::EscapeAscii;
+#[unstable(feature = "get_many_mut", issue = "104642")]
+pub use core::slice::GetManyMutError;
 #[stable(feature = "slice_get_slice", since = "1.28.0")]
 pub use core::slice::SliceIndex;
 #[cfg(not(no_global_oom_handling))]

core/src/error.rs

@@ -1076,4 +1076,4 @@ impl Error for crate::time::TryFromFloatSecsError {}
 impl Error for crate::ffi::FromBytesUntilNulError {}
 
 #[unstable(feature = "get_many_mut", issue = "104642")]
-impl<const N: usize> Error for crate::slice::GetManyMutError<N> {}
+impl Error for crate::slice::GetManyMutError {}

core/src/ffi/mod.rs

@@ -91,59 +91,86 @@ pub type c_ssize_t = isize;
 
 mod c_char_definition {
     cfg_if! {
-        // These are the targets on which c_char is unsigned.
-        if #[cfg(any(
-            all(
-                target_os = "linux",
-                any(
-                    target_arch = "aarch64",
-                    target_arch = "arm",
-                    target_arch = "hexagon",
-                    target_arch = "powerpc",
-                    target_arch = "powerpc64",
-                    target_arch = "s390x",
-                    target_arch = "riscv64",
-                    target_arch = "riscv32",
-                    target_arch = "csky"
-                )
-            ),
-            all(target_os = "android", any(target_arch = "aarch64", target_arch = "arm")),
-            all(target_os = "l4re", target_arch = "x86_64"),
-            all(
-                any(target_os = "freebsd", target_os = "openbsd", target_os = "rtems"),
-                any(
-                    target_arch = "aarch64",
-                    target_arch = "arm",
-                    target_arch = "powerpc",
-                    target_arch = "powerpc64",
-                    target_arch = "riscv64"
-                )
-            ),
-            all(
-                target_os = "netbsd",
-                any(
-                    target_arch = "aarch64",
-                    target_arch = "arm",
-                    target_arch = "powerpc",
-                    target_arch = "riscv64"
-                )
-            ),
-            all(
-                target_os = "vxworks",
-                any(
-                    target_arch = "aarch64",
-                    target_arch = "arm",
-                    target_arch = "powerpc64",
-                    target_arch = "powerpc"
-                )
-            ),
-            all(
-                target_os = "fuchsia",
-                any(target_arch = "aarch64", target_arch = "riscv64")
-            ),
-            all(target_os = "nto", target_arch = "aarch64"),
-            target_os = "horizon",
-            target_os = "aix",
+        // These are the targets on which c_char is unsigned. Usually the
+        // signedness is the same for all target_os values on a given architecture
+        // but there are some exceptions (see isSignedCharDefault() in clang).
+        //
+        // aarch64:
+        //   Section 10 "Arm C and C++ language mappings" in Procedure Call Standard for the Arm®
+        //   64-bit Architecture (AArch64) says C/C++ char is unsigned byte.
+        //   https://github.com/ARM-software/abi-aa/blob/2024Q3/aapcs64/aapcs64.rst#arm-c-and-c-language-mappings
+        // arm:
+        //   Section 8 "Arm C and C++ Language Mappings" in Procedure Call Standard for the Arm®
+        //   Architecture says C/C++ char is unsigned byte.
+        //   https://github.com/ARM-software/abi-aa/blob/2024Q3/aapcs32/aapcs32.rst#arm-c-and-c-language-mappings
+        // csky:
+        //   Section 2.1.2 "Primary Data Type" in C-SKY V2 CPU Applications Binary Interface
+        //   Standards Manual says ANSI C char is unsigned byte.
+        //   https://github.com/c-sky/csky-doc/blob/9f7121f7d40970ba5cc0f15716da033db2bb9d07/C-SKY_V2_CPU_Applications_Binary_Interface_Standards_Manual.pdf
+        //   Note: this doesn't seem to match Clang's default (https://github.com/rust-lang/rust/issues/129945).
+        // hexagon:
+        //   Section 3.1 "Basic data type" in Qualcomm Hexagon™ Application
+        //   Binary Interface User Guide says "By default, the `char` data type is unsigned."
+        //   https://docs.qualcomm.com/bundle/publicresource/80-N2040-23_REV_K_Qualcomm_Hexagon_Application_Binary_Interface_User_Guide.pdf
+        // msp430:
+        //   Section 2.1 "Basic Types" in MSP430 Embedded Application Binary
+        //   Interface says "The char type is unsigned by default".
+        //   https://www.ti.com/lit/an/slaa534a/slaa534a.pdf
+        //   Note: this doesn't seem to match Clang's default (https://github.com/rust-lang/rust/issues/129945).
+        // powerpc/powerpc64:
+        //   - PPC32 SysV: "Table 3-1 Scalar Types" in System V Application Binary Interface PowerPC
+        //     Processor Supplement says ANSI C char is unsigned byte
+        //     https://refspecs.linuxfoundation.org/elf/elfspec_ppc.pdf
+        //   - PPC64 ELFv1: Section 3.1.4 "Fundamental Types" in 64-bit PowerPC ELF Application
+        //     Binary Interface Supplement 1.9 says ANSI C is unsigned byte
+        //     https://refspecs.linuxfoundation.org/ELF/ppc64/PPC-elf64abi.html#FUND-TYPE
+        //   - PPC64 ELFv2: Section 2.1.2.2 "Fundamental Types" in 64-Bit ELF V2 ABI Specification
+        //     says char is unsigned byte
+        //     https://openpowerfoundation.org/specifications/64bitelfabi/
+        //   - AIX: XL C for AIX Language Reference says "By default, char behaves like an unsigned char."
+        //     https://www.ibm.com/docs/en/xl-c-aix/13.1.3?topic=specifiers-character-types
+        // riscv32/riscv64:
+        //   C/C++ type representations section in RISC-V Calling Conventions
+        //   page in RISC-V ELF psABI Document says "char is unsigned."
+        //   https://github.com/riscv-non-isa/riscv-elf-psabi-doc/blob/draft-20240829-13bfa9f54634cb60d86b9b333e109f077805b4b3/riscv-cc.adoc#cc-type-representations
+        // s390x:
+        //   - ELF: "Table 1.1.: Scalar types" in ELF Application Binary Interface s390x Supplement
+        //     Version 1.6.1 categorize ISO C char in unsigned integer
+        //     https://github.com/IBM/s390x-abi/releases/tag/v1.6.1
+        //   - z/OS: XL C/C++ Language Reference says: "By default, char behaves like an unsigned char."
+        //     https://www.ibm.com/docs/en/zos/3.1.0?topic=specifiers-character-types
+        // Xtensa:
+        //   - "The char type is unsigned by default for Xtensa processors."
+        //
+        // On the following operating systems, c_char is signed by default, regardless of architecture.
+        // Darwin (macOS, iOS, etc.):
+        //   Apple targets' c_char is signed by default even on arm
+        //   https://developer.apple.com/documentation/xcode/writing-arm64-code-for-apple-platforms#Handle-data-types-and-data-alignment-properly
+        // Windows:
+        //   Windows MSVC C++ Language Reference says "Microsoft-specific: Variables of type char
+        //   are promoted to int as if from type signed char by default, unless the /J compilation
+        //   option is used."
+        //   https://learn.microsoft.com/en-us/cpp/cpp/fundamental-types-cpp?view=msvc-170#character-types)
+        // L4RE:
+        //   The kernel builds with -funsigned-char on all targets (but useserspace follows the
+        //   architecture defaults). As we only have a target for userspace apps so there are no
+        //   special cases for L4RE below.
+        if #[cfg(all(
+            not(windows),
+            not(target_vendor = "apple"),
+            any(
+                target_arch = "aarch64",
+                target_arch = "arm",
+                target_arch = "csky",
+                target_arch = "hexagon",
+                target_arch = "msp430",
+                target_arch = "powerpc",
+                target_arch = "powerpc64",
+                target_arch = "riscv64",
+                target_arch = "riscv32",
+                target_arch = "s390x",
+                target_arch = "xtensa",
+            )
         ))] {
             pub type c_char = u8;
         } else {

core/src/slice/mod.rs

@@ -4629,13 +4629,11 @@ impl<T> [T] {
     pub fn get_many_mut<I, const N: usize>(
         &mut self,
         indices: [I; N],
-    ) -> Result<[&mut I::Output; N], GetManyMutError<N>>
+    ) -> Result<[&mut I::Output; N], GetManyMutError>
     where
         I: GetManyMutIndex + SliceIndex<Self>,
     {
-        if !get_many_check_valid(&indices, self.len()) {
-            return Err(GetManyMutError { _private: () });
-        }
+        get_many_check_valid(&indices, self.len())?;
         // SAFETY: The `get_many_check_valid()` call checked that all indices
         // are disjunct and in bounds.
         unsafe { Ok(self.get_many_unchecked_mut(indices)) }
@@ -4978,53 +4976,59 @@ impl<T, const N: usize> SlicePattern for [T; N] {
 /// This will do `binomial(N + 1, 2) = N * (N + 1) / 2 = 0, 1, 3, 6, 10, ..`
 /// comparison operations.
 #[inline]
-fn get_many_check_valid<I: GetManyMutIndex, const N: usize>(indices: &[I; N], len: usize) -> bool {
+fn get_many_check_valid<I: GetManyMutIndex, const N: usize>(
+    indices: &[I; N],
+    len: usize,
+) -> Result<(), GetManyMutError> {
     // NB: The optimizer should inline the loops into a sequence
     // of instructions without additional branching.
-    let mut valid = true;
     for (i, idx) in indices.iter().enumerate() {
-        valid &= idx.is_in_bounds(len);
+        if !idx.is_in_bounds(len) {
+            return Err(GetManyMutError::IndexOutOfBounds);
+        }
         for idx2 in &indices[..i] {
-            valid &= !idx.is_overlapping(idx2);
+            if idx.is_overlapping(idx2) {
+                return Err(GetManyMutError::OverlappingIndices);
+            }
         }
     }
-    valid
+    Ok(())
 }
 
-/// The error type returned by [`get_many_mut<N>`][`slice::get_many_mut`].
+/// The error type returned by [`get_many_mut`][`slice::get_many_mut`].
 ///
 /// It indicates one of two possible errors:
 /// - An index is out-of-bounds.
-/// - The same index appeared multiple times in the array.
+/// - The same index appeared multiple times in the array
+///   (or different but overlapping indices when ranges are provided).
 ///
 /// # Examples
 ///
 /// ```
 /// #![feature(get_many_mut)]
+/// use std::slice::GetManyMutError;
 ///
 /// let v = &mut [1, 2, 3];
-/// assert!(v.get_many_mut([0, 999]).is_err());
-/// assert!(v.get_many_mut([1, 1]).is_err());
+/// assert_eq!(v.get_many_mut([0, 999]), Err(GetManyMutError::IndexOutOfBounds));
+/// assert_eq!(v.get_many_mut([1, 1]), Err(GetManyMutError::OverlappingIndices));
 /// ```
 #[unstable(feature = "get_many_mut", issue = "104642")]
-// NB: The N here is there to be forward-compatible with adding more details
-// to the error type at a later point
-#[derive(Clone, PartialEq, Eq)]
-pub struct GetManyMutError<const N: usize> {
-    _private: (),
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub enum GetManyMutError {
+    /// An index provided was out-of-bounds for the slice.
+    IndexOutOfBounds,
+    /// Two indices provided were overlapping.
+    OverlappingIndices,
 }
 
 #[unstable(feature = "get_many_mut", issue = "104642")]
-impl<const N: usize> fmt::Debug for GetManyMutError<N> {
+impl fmt::Display for GetManyMutError {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        f.debug_struct("GetManyMutError").finish_non_exhaustive()
-    }
-}
-
-#[unstable(feature = "get_many_mut", issue = "104642")]
-impl<const N: usize> fmt::Display for GetManyMutError<N> {
-    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        fmt::Display::fmt("an index is out of bounds or appeared multiple times in the array", f)
+        let msg = match self {
+            GetManyMutError::IndexOutOfBounds => "an index is out of bounds",
+            GetManyMutError::OverlappingIndices => "there were overlapping indices",
+        };
+        fmt::Display::fmt(msg, f)
     }
 }