Auto merge of #147197 - matthiaskrgr:rollup-du5e4pv, r=matthiaskrgr

Rollup of 6 pull requests

Successful merges:

 - #142506 (Add `Path::has_trailing_sep` and related methods)
 - #146886 (Add repr(align(2)) to RcInner and ArcInner)
 - #147166 (several small `proc_macro` cleanups)
 - #147172 (bootstrap: build bootstrap docs with in-tree rustdoc)
 - #147181 (cg_llvm: Replace enum `MetadataType` with a list of `MetadataKindId` constants)
 - #147187 (remove unnecessary test directives)

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

Author: bors

compiler/rustc_codegen_llvm/src/context.rs

@@ -34,7 +34,7 @@ use smallvec::SmallVec;
 use crate::back::write::to_llvm_code_model;
 use crate::callee::get_fn;
 use crate::debuginfo::metadata::apply_vcall_visibility_metadata;
-use crate::llvm::Metadata;
+use crate::llvm::{Metadata, MetadataKindId};
 use crate::type_::Type;
 use crate::value::Value;
 use crate::{attributes, common, coverageinfo, debuginfo, llvm, llvm_util};
@@ -1006,11 +1006,11 @@ impl<'ll, CX: Borrow<SCx<'ll>>> GenericCx<'ll, CX> {
     pub(crate) fn set_metadata<'a>(
         &self,
         val: &'a Value,
-        kind_id: impl Into<llvm::MetadataKindId>,
+        kind_id: MetadataKindId,
         md: &'ll Metadata,
     ) {
         let node = self.get_metadata_value(md);
-        llvm::LLVMSetMetadata(val, kind_id.into(), node);
+        llvm::LLVMSetMetadata(val, kind_id, node);
     }
 }
 

compiler/rustc_codegen_llvm/src/debuginfo/metadata.rs

@@ -1611,16 +1611,12 @@ pub(crate) fn apply_vcall_visibility_metadata<'ll, 'tcx>(
         let v = [llvm::LLVMValueAsMetadata(cx.const_usize(0)), typeid];
         llvm::LLVMRustGlobalAddMetadata(
             vtable,
-            llvm::MD_type as c_uint,
+            llvm::MD_type,
             llvm::LLVMMDNodeInContext2(cx.llcx, v.as_ptr(), v.len()),
         );
         let vcall_visibility = llvm::LLVMValueAsMetadata(cx.const_u64(vcall_visibility as u64));
         let vcall_visibility_metadata = llvm::LLVMMDNodeInContext2(cx.llcx, &vcall_visibility, 1);
-        llvm::LLVMGlobalSetMetadata(
-            vtable,
-            llvm::MetadataType::MD_vcall_visibility as c_uint,
-            vcall_visibility_metadata,
-        );
+        llvm::LLVMGlobalSetMetadata(vtable, llvm::MD_vcall_visibility, vcall_visibility_metadata);
     }
 }
 

compiler/rustc_codegen_llvm/src/llvm/ffi.rs

@@ -29,6 +29,7 @@ use super::debuginfo::{
     DITemplateTypeParameter, DIType, DebugEmissionKind, DebugNameTableKind,
 };
 use crate::llvm;
+use crate::llvm::MetadataKindId;
 
 /// In the LLVM-C API, boolean values are passed as `typedef int LLVMBool`,
 /// which has a different ABI from Rust or C++ `bool`.
@@ -513,31 +514,6 @@ pub(crate) enum FileType {
     ObjectFile,
 }
 
-/// LLVMMetadataType
-#[derive(Copy, Clone)]
-#[repr(C)]
-#[expect(dead_code, reason = "Some variants are unused, but are kept to match LLVM-C")]
-pub(crate) enum MetadataType {
-    MD_dbg = 0,
-    MD_tbaa = 1,
-    MD_prof = 2,
-    MD_fpmath = 3,
-    MD_range = 4,
-    MD_tbaa_struct = 5,
-    MD_invariant_load = 6,
-    MD_alias_scope = 7,
-    MD_noalias = 8,
-    MD_nontemporal = 9,
-    MD_mem_parallel_loop_access = 10,
-    MD_nonnull = 11,
-    MD_unpredictable = 15,
-    MD_align = 17,
-    MD_type = 19,
-    MD_vcall_visibility = 28,
-    MD_noundef = 29,
-    MD_kcfi_type = 36,
-}
-
 /// Must match the layout of `LLVMInlineAsmDialect`.
 #[derive(Copy, Clone, PartialEq)]
 #[repr(C)]
@@ -1035,16 +1011,6 @@ pub(crate) type GetSymbolsCallback =
     unsafe extern "C" fn(*mut c_void, *const c_char) -> *mut c_void;
 pub(crate) type GetSymbolsErrorCallback = unsafe extern "C" fn(*const c_char) -> *mut c_void;
 
-#[derive(Copy, Clone)]
-#[repr(transparent)]
-pub(crate) struct MetadataKindId(c_uint);
-
-impl From<MetadataType> for MetadataKindId {
-    fn from(value: MetadataType) -> Self {
-        Self(value as c_uint)
-    }
-}
-
 unsafe extern "C" {
     // Create and destroy contexts.
     pub(crate) fn LLVMContextDispose(C: &'static mut Context);
@@ -1139,7 +1105,11 @@ unsafe extern "C" {
     pub(crate) fn LLVMSetValueName2(Val: &Value, Name: *const c_char, NameLen: size_t);
     pub(crate) fn LLVMReplaceAllUsesWith<'a>(OldVal: &'a Value, NewVal: &'a Value);
     pub(crate) safe fn LLVMSetMetadata<'a>(Val: &'a Value, KindID: MetadataKindId, Node: &'a Value);
-    pub(crate) fn LLVMGlobalSetMetadata<'a>(Val: &'a Value, KindID: c_uint, Metadata: &'a Metadata);
+    pub(crate) fn LLVMGlobalSetMetadata<'a>(
+        Val: &'a Value,
+        KindID: MetadataKindId,
+        Metadata: &'a Metadata,
+    );
     pub(crate) safe fn LLVMValueAsMetadata(Node: &Value) -> &Metadata;
 
     // Operations on constants of any type
@@ -2059,7 +2029,7 @@ unsafe extern "C" {
     // Operations on all values
     pub(crate) fn LLVMRustGlobalAddMetadata<'a>(
         Val: &'a Value,
-        KindID: c_uint,
+        KindID: MetadataKindId,
         Metadata: &'a Metadata,
     );
     pub(crate) fn LLVMRustIsNonGVFunctionPointerTy(Val: &Value) -> bool;

compiler/rustc_codegen_llvm/src/llvm/metadata_kind.rs

@@ -0,0 +1,71 @@
+use libc::c_uint;
+
+pub(crate) use self::fixed_kinds::*;
+
+#[derive(Copy, Clone)]
+#[repr(transparent)]
+pub(crate) struct MetadataKindId(c_uint);
+
+macro_rules! declare_fixed_metadata_kinds {
+    (
+        $(
+            FIXED_MD_KIND($variant:ident, $value:literal)
+        )*
+    ) => {
+        // Use a submodule to group all declarations into one `#[expect(..)]`.
+        #[expect(dead_code)]
+        mod fixed_kinds {
+            use super::MetadataKindId;
+            $(
+                #[expect(non_upper_case_globals)]
+                pub(crate) const $variant: MetadataKindId = MetadataKindId($value);
+            )*
+        }
+    };
+}
+
+// Must be kept in sync with the corresponding static assertions in `RustWrapper.cpp`.
+declare_fixed_metadata_kinds! {
+    FIXED_MD_KIND(MD_dbg, 0)
+    FIXED_MD_KIND(MD_tbaa, 1)
+    FIXED_MD_KIND(MD_prof, 2)
+    FIXED_MD_KIND(MD_fpmath, 3)
+    FIXED_MD_KIND(MD_range, 4)
+    FIXED_MD_KIND(MD_tbaa_struct, 5)
+    FIXED_MD_KIND(MD_invariant_load, 6)
+    FIXED_MD_KIND(MD_alias_scope, 7)
+    FIXED_MD_KIND(MD_noalias, 8)
+    FIXED_MD_KIND(MD_nontemporal, 9)
+    FIXED_MD_KIND(MD_mem_parallel_loop_access, 10)
+    FIXED_MD_KIND(MD_nonnull, 11)
+    FIXED_MD_KIND(MD_dereferenceable, 12)
+    FIXED_MD_KIND(MD_dereferenceable_or_null, 13)
+    FIXED_MD_KIND(MD_make_implicit, 14)
+    FIXED_MD_KIND(MD_unpredictable, 15)
+    FIXED_MD_KIND(MD_invariant_group, 16)
+    FIXED_MD_KIND(MD_align, 17)
+    FIXED_MD_KIND(MD_loop, 18)
+    FIXED_MD_KIND(MD_type, 19)
+    FIXED_MD_KIND(MD_section_prefix, 20)
+    FIXED_MD_KIND(MD_absolute_symbol, 21)
+    FIXED_MD_KIND(MD_associated, 22)
+    FIXED_MD_KIND(MD_callees, 23)
+    FIXED_MD_KIND(MD_irr_loop, 24)
+    FIXED_MD_KIND(MD_access_group, 25)
+    FIXED_MD_KIND(MD_callback, 26)
+    FIXED_MD_KIND(MD_preserve_access_index, 27)
+    FIXED_MD_KIND(MD_vcall_visibility, 28)
+    FIXED_MD_KIND(MD_noundef, 29)
+    FIXED_MD_KIND(MD_annotation, 30)
+    FIXED_MD_KIND(MD_nosanitize, 31)
+    FIXED_MD_KIND(MD_func_sanitize, 32)
+    FIXED_MD_KIND(MD_exclude, 33)
+    FIXED_MD_KIND(MD_memprof, 34)
+    FIXED_MD_KIND(MD_callsite, 35)
+    FIXED_MD_KIND(MD_kcfi_type, 36)
+    FIXED_MD_KIND(MD_pcsections, 37)
+    FIXED_MD_KIND(MD_DIAssignID, 38)
+    FIXED_MD_KIND(MD_coro_outside_frame, 39)
+    FIXED_MD_KIND(MD_mmra, 40)
+    FIXED_MD_KIND(MD_noalias_addrspace, 41)
+}

compiler/rustc_codegen_llvm/src/llvm/mod.rs

@@ -11,13 +11,14 @@ use rustc_llvm::RustString;
 
 pub(crate) use self::CallConv::*;
 pub(crate) use self::CodeGenOptSize::*;
-pub(crate) use self::MetadataType::*;
 pub(crate) use self::ffi::*;
+pub(crate) use self::metadata_kind::*;
 use crate::common::AsCCharPtr;
 
 pub(crate) mod diagnostic;
 pub(crate) mod enzyme_ffi;
 mod ffi;
+mod metadata_kind;
 
 pub(crate) use self::enzyme_ffi::*;
 

compiler/rustc_codegen_llvm/src/type_.rs

@@ -306,7 +306,7 @@ impl<'ll, 'tcx> TypeMembershipCodegenMethods<'tcx> for CodegenCx<'ll, 'tcx> {
             let v = [llvm::LLVMValueAsMetadata(self.const_usize(0)), typeid_metadata];
             llvm::LLVMRustGlobalAddMetadata(
                 function,
-                llvm::MD_type as c_uint,
+                llvm::MD_type,
                 llvm::LLVMMDNodeInContext2(self.llcx, v.as_ptr(), v.len()),
             )
         }
@@ -318,7 +318,7 @@ impl<'ll, 'tcx> TypeMembershipCodegenMethods<'tcx> for CodegenCx<'ll, 'tcx> {
             let v = [llvm::LLVMValueAsMetadata(self.const_usize(0)), typeid_metadata];
             llvm::LLVMGlobalSetMetadata(
                 function,
-                llvm::MD_type as c_uint,
+                llvm::MD_type,
                 llvm::LLVMMDNodeInContext2(self.llcx, v.as_ptr(), v.len()),
             )
         }
@@ -333,7 +333,7 @@ impl<'ll, 'tcx> TypeMembershipCodegenMethods<'tcx> for CodegenCx<'ll, 'tcx> {
         unsafe {
             llvm::LLVMRustGlobalAddMetadata(
                 function,
-                llvm::MD_kcfi_type as c_uint,
+                llvm::MD_kcfi_type,
                 llvm::LLVMMDNodeInContext2(
                     self.llcx,
                     &llvm::LLVMValueAsMetadata(kcfi_type_metadata),
@@ -348,7 +348,7 @@ impl<'ll, 'tcx> TypeMembershipCodegenMethods<'tcx> for CodegenCx<'ll, 'tcx> {
         unsafe {
             llvm::LLVMGlobalSetMetadata(
                 function,
-                llvm::MD_kcfi_type as c_uint,
+                llvm::MD_kcfi_type,
                 llvm::LLVMMDNodeInContext2(
                     self.llcx,
                     &llvm::LLVMValueAsMetadata(kcfi_type_metadata),

compiler/rustc_llvm/llvm-wrapper/RustWrapper.cpp

@@ -1824,3 +1824,55 @@ extern "C" size_t LLVMRustEnzymeGetMaxTypeDepth() {
   return 6; // Default fallback depth
 }
 #endif
+
+// Statically assert that the fixed metadata kind IDs declared in
+// `metadata_kind.rs` match the ones actually used by LLVM.
+#define FIXED_MD_KIND(VARIANT, VALUE)                                          \
+  static_assert(::llvm::LLVMContext::VARIANT == VALUE);
+// Must be kept in sync with the corresponding list in `metadata_kind.rs`.
+FIXED_MD_KIND(MD_dbg, 0)
+FIXED_MD_KIND(MD_tbaa, 1)
+FIXED_MD_KIND(MD_prof, 2)
+FIXED_MD_KIND(MD_fpmath, 3)
+FIXED_MD_KIND(MD_range, 4)
+FIXED_MD_KIND(MD_tbaa_struct, 5)
+FIXED_MD_KIND(MD_invariant_load, 6)
+FIXED_MD_KIND(MD_alias_scope, 7)
+FIXED_MD_KIND(MD_noalias, 8)
+FIXED_MD_KIND(MD_nontemporal, 9)
+FIXED_MD_KIND(MD_mem_parallel_loop_access, 10)
+FIXED_MD_KIND(MD_nonnull, 11)
+FIXED_MD_KIND(MD_dereferenceable, 12)
+FIXED_MD_KIND(MD_dereferenceable_or_null, 13)
+FIXED_MD_KIND(MD_make_implicit, 14)
+FIXED_MD_KIND(MD_unpredictable, 15)
+FIXED_MD_KIND(MD_invariant_group, 16)
+FIXED_MD_KIND(MD_align, 17)
+FIXED_MD_KIND(MD_loop, 18)
+FIXED_MD_KIND(MD_type, 19)
+FIXED_MD_KIND(MD_section_prefix, 20)
+FIXED_MD_KIND(MD_absolute_symbol, 21)
+FIXED_MD_KIND(MD_associated, 22)
+FIXED_MD_KIND(MD_callees, 23)
+FIXED_MD_KIND(MD_irr_loop, 24)
+FIXED_MD_KIND(MD_access_group, 25)
+FIXED_MD_KIND(MD_callback, 26)
+FIXED_MD_KIND(MD_preserve_access_index, 27)
+FIXED_MD_KIND(MD_vcall_visibility, 28)
+FIXED_MD_KIND(MD_noundef, 29)
+FIXED_MD_KIND(MD_annotation, 30)
+FIXED_MD_KIND(MD_nosanitize, 31)
+FIXED_MD_KIND(MD_func_sanitize, 32)
+FIXED_MD_KIND(MD_exclude, 33)
+FIXED_MD_KIND(MD_memprof, 34)
+FIXED_MD_KIND(MD_callsite, 35)
+FIXED_MD_KIND(MD_kcfi_type, 36)
+FIXED_MD_KIND(MD_pcsections, 37)
+FIXED_MD_KIND(MD_DIAssignID, 38)
+FIXED_MD_KIND(MD_coro_outside_frame, 39)
+FIXED_MD_KIND(MD_mmra, 40)
+FIXED_MD_KIND(MD_noalias_addrspace, 41)
+// If some fixed metadata kinds are not present and consistent in all supported
+// LLVM versions, it's fine to omit them from this list; in that case Rust-side
+// code cannot declare them as fixed IDs and must look them up by name instead.
+#undef FIXED_MD_KIND

library/alloc/src/rc.rs

@@ -277,7 +277,9 @@ use crate::vec::Vec;
 // This is repr(C) to future-proof against possible field-reordering, which
 // would interfere with otherwise safe [into|from]_raw() of transmutable
 // inner types.
-#[repr(C)]
+// repr(align(2)) (forcing alignment to at least 2) is required because usize
+// has 1-byte alignment on AVR.
+#[repr(C, align(2))]
 struct RcInner<T: ?Sized> {
     strong: Cell<usize>,
     weak: Cell<usize>,

library/alloc/src/sync.rs

@@ -341,7 +341,7 @@ pub struct Weak<
     // but it is not necessarily a valid pointer.
     // `Weak::new` sets this to `usize::MAX` so that it doesn’t need
     // to allocate space on the heap. That's not a value a real pointer
-    // will ever have because RcInner has alignment at least 2.
+    // will ever have because ArcInner has alignment at least 2.
     ptr: NonNull<ArcInner<T>>,
     alloc: A,
 }
@@ -366,7 +366,9 @@ impl<T: ?Sized, A: Allocator> fmt::Debug for Weak<T, A> {
 // This is repr(C) to future-proof against possible field-reordering, which
 // would interfere with otherwise safe [into|from]_raw() of transmutable
 // inner types.
-#[repr(C)]
+// Unlike RcInner, repr(align(2)) is not strictly required because atomic types
+// have the alignment same as its size, but we use it for consistency and clarity.
+#[repr(C, align(2))]
 struct ArcInner<T: ?Sized> {
     strong: Atomic<usize>,
 
@@ -1613,9 +1615,9 @@ impl<T: ?Sized, A: Allocator> Arc<T, A> {
     pub fn as_ptr(this: &Self) -> *const T {
         let ptr: *mut ArcInner<T> = NonNull::as_ptr(this.ptr);
 
-        // SAFETY: This cannot go through Deref::deref or RcInnerPtr::inner because
+        // SAFETY: This cannot go through Deref::deref or ArcInnerPtr::inner because
         // this is required to retain raw/mut provenance such that e.g. `get_mut` can
-        // write through the pointer after the Rc is recovered through `from_raw`.
+        // write through the pointer after the Arc is recovered through `from_raw`.
         unsafe { &raw mut (*ptr).data }
     }
 
@@ -2450,7 +2452,7 @@ impl<T: ?Sized, A: Allocator> Arc<T, A> {
     /// If any other `Arc` or [`Weak`] pointers to the same allocation exist, then
     /// they must not be dereferenced or have active borrows for the duration
     /// of the returned borrow, and their inner type must be exactly the same as the
-    /// inner type of this Rc (including lifetimes). This is trivially the case if no
+    /// inner type of this Arc (including lifetimes). This is trivially the case if no
     /// such pointers exist, for example immediately after `Arc::new`.
     ///
     /// # Examples
@@ -3022,7 +3024,7 @@ impl<T: ?Sized, A: Allocator> Weak<T, A> {
             // Otherwise, we're guaranteed the pointer came from a nondangling Weak.
             // SAFETY: data_offset is safe to call, as ptr references a real (potentially dropped) T.
             let offset = unsafe { data_offset(ptr) };
-            // Thus, we reverse the offset to get the whole RcInner.
+            // Thus, we reverse the offset to get the whole ArcInner.
             // SAFETY: the pointer originated from a Weak, so this offset is safe.
             unsafe { ptr.byte_sub(offset) as *mut ArcInner<T> }
         };
@@ -4015,7 +4017,7 @@ impl<T: ?Sized, A: Allocator> Unpin for Arc<T, A> {}
 /// valid instance of T, but the T is allowed to be dropped.
 unsafe fn data_offset<T: ?Sized>(ptr: *const T) -> usize {
     // Align the unsized value to the end of the ArcInner.
-    // Because RcInner is repr(C), it will always be the last field in memory.
+    // Because ArcInner is repr(C), it will always be the last field in memory.
     // SAFETY: since the only unsized types possible are slices, trait objects,
     // and extern types, the input safety requirement is currently enough to
     // satisfy the requirements of align_of_val_raw; this is an implementation