Auto merge of #94468 - Amanieu:global_asm_sym, r=nagisa

Implement sym operands for global_asm!

Tracking issue: #93333

This PR is pretty much a complete rewrite of `sym` operand support for inline assembly so that the same implementation can be shared by `asm!` and `global_asm!`. The main changes are:
- At the AST level, `sym` is represented as a special `InlineAsmSym` AST node containing a path instead of an `Expr`.
- At the HIR level, `sym` is split into `SymStatic` and `SymFn` depending on whether the path resolves to a static during AST lowering (defaults to `SynFn` if `get_early_res` fails).
  - `SymFn` is just an `AnonConst`. It runs through typeck and we just collect the resulting type at the end. An error is emitted if the type is not a `FnDef`.
  - `SymStatic` directly holds a path and the `DefId` of the `static` that it is pointing to.
- The representation at the MIR level is mostly unchanged. There is a minor change to THIR where `SymFn` is a constant instead of an expression.
- At the codegen level we need to apply the target's symbol mangling to the result of `tcx.symbol_name()` depending on the target. This is done by calling the LLVM name mangler, which handles all of the details.
  - On Mach-O, all symbols have a leading underscore.
  - On x86 Windows, different mangling is used for cdecl, stdcall, fastcall and vectorcall.
  - No mangling is needed on other platforms.

r? `@nagisa`
cc `@eddyb`

5 files changed, 52 insertions, 11 deletions

diff --git a/compiler/rustc_codegen_llvm/src/asm.rs b/compiler/rustc_codegen_llvm/src/asm.rs
index 91d132eb343..dff32007918 100644
--- a/compiler/rustc_codegen_llvm/src/asm.rs
+++ b/compiler/rustc_codegen_llvm/src/asm.rs
@@ -312,11 +312,11 @@ impl<'ll, 'tcx> AsmBuilderMethods<'tcx> for Builder<'_, 'll, 'tcx> {
     }
 }
 
-impl AsmMethods for CodegenCx<'_, '_> {
+impl<'tcx> AsmMethods<'tcx> for CodegenCx<'_, 'tcx> {
     fn codegen_global_asm(
         &self,
         template: &[InlineAsmTemplatePiece],
-        operands: &[GlobalAsmOperandRef],
+        operands: &[GlobalAsmOperandRef<'tcx>],
         options: InlineAsmOptions,
         _line_spans: &[Span],
     ) {
@@ -342,6 +342,29 @@ impl AsmMethods for CodegenCx<'_, '_> {
                             // here unlike normal inline assembly.
                             template_str.push_str(string);
                         }
+                        GlobalAsmOperandRef::SymFn { instance } => {
+                            let llval = self.get_fn(instance);
+                            self.add_compiler_used_global(llval);
+                            let symbol = llvm::build_string(|s| unsafe {
+                                llvm::LLVMRustGetMangledName(llval, s);
+                            })
+                            .expect("symbol is not valid UTF-8");
+                            template_str.push_str(&symbol);
+                        }
+                        GlobalAsmOperandRef::SymStatic { def_id } => {
+                            let llval = self
+                                .renamed_statics
+                                .borrow()
+                                .get(&def_id)
+                                .copied()
+                                .unwrap_or_else(|| self.get_static(def_id));
+                            self.add_compiler_used_global(llval);
+                            let symbol = llvm::build_string(|s| unsafe {
+                                llvm::LLVMRustGetMangledName(llval, s);
+                            })
+                            .expect("symbol is not valid UTF-8");
+                            template_str.push_str(&symbol);
+                        }
                     }
                 }
             }
diff --git a/compiler/rustc_codegen_llvm/src/base.rs b/compiler/rustc_codegen_llvm/src/base.rs
index dd3ada44389..c163c7d8692 100644
--- a/compiler/rustc_codegen_llvm/src/base.rs
+++ b/compiler/rustc_codegen_llvm/src/base.rs
@@ -99,15 +99,6 @@ pub fn compile_codegen_unit(tcx: TyCtxt<'_>, cgu_name: Symbol) -> (ModuleCodegen
                 attributes::apply_to_llfn(entry, llvm::AttributePlace::Function, &attrs);
             }
 
-            // Run replace-all-uses-with for statics that need it
-            for &(old_g, new_g) in cx.statics_to_rauw().borrow().iter() {
-                unsafe {
-                    let bitcast = llvm::LLVMConstPointerCast(new_g, cx.val_ty(old_g));
-                    llvm::LLVMReplaceAllUsesWith(old_g, bitcast);
-                    llvm::LLVMDeleteGlobal(old_g);
-                }
-            }
-
             // Finalize code coverage by injecting the coverage map. Note, the coverage map will
             // also be added to the `llvm.compiler.used` variable, created next.
             if cx.sess().instrument_coverage() {
@@ -122,6 +113,16 @@ pub fn compile_codegen_unit(tcx: TyCtxt<'_>, cgu_name: Symbol) -> (ModuleCodegen
                 cx.create_compiler_used_variable()
             }
 
+            // Run replace-all-uses-with for statics that need it. This must
+            // happen after the llvm.used variables are created.
+            for &(old_g, new_g) in cx.statics_to_rauw().borrow().iter() {
+                unsafe {
+                    let bitcast = llvm::LLVMConstPointerCast(new_g, cx.val_ty(old_g));
+                    llvm::LLVMReplaceAllUsesWith(old_g, bitcast);
+                    llvm::LLVMDeleteGlobal(old_g);
+                }
+            }
+
             // Finalize debuginfo
             if cx.sess().opts.debuginfo != DebugInfo::None {
                 cx.debuginfo_finalize();
diff --git a/compiler/rustc_codegen_llvm/src/consts.rs b/compiler/rustc_codegen_llvm/src/consts.rs
index cb4073528e1..4d3f3f318b8 100644
--- a/compiler/rustc_codegen_llvm/src/consts.rs
+++ b/compiler/rustc_codegen_llvm/src/consts.rs
@@ -412,6 +412,13 @@ impl<'ll> StaticMethods for CodegenCx<'ll, '_> {
                 llvm::LLVMRustSetLinkage(new_g, linkage);
                 llvm::LLVMRustSetVisibility(new_g, visibility);
 
+                // The old global has had its name removed but is returned by
+                // get_static since it is in the instance cache. Provide an
+                // alternative lookup that points to the new global so that
+                // global_asm! can compute the correct mangled symbol name
+                // for the global.
+                self.renamed_statics.borrow_mut().insert(def_id, new_g);
+
                 // To avoid breaking any invariants, we leave around the old
                 // global for the moment; we'll replace all references to it
                 // with the new global later. (See base::codegen_backend.)
diff --git a/compiler/rustc_codegen_llvm/src/context.rs b/compiler/rustc_codegen_llvm/src/context.rs
index 98cf873ebbd..d296ee3b42c 100644
--- a/compiler/rustc_codegen_llvm/src/context.rs
+++ b/compiler/rustc_codegen_llvm/src/context.rs
@@ -14,6 +14,7 @@ use rustc_codegen_ssa::traits::*;
 use rustc_data_structures::base_n;
 use rustc_data_structures::fx::FxHashMap;
 use rustc_data_structures::small_c_str::SmallCStr;
+use rustc_hir::def_id::DefId;
 use rustc_middle::mir::mono::CodegenUnit;
 use rustc_middle::ty::layout::{
     FnAbiError, FnAbiOfHelpers, FnAbiRequest, HasParamEnv, LayoutError, LayoutOfHelpers,
@@ -105,6 +106,12 @@ pub struct CodegenCx<'ll, 'tcx> {
 
     /// A counter that is used for generating local symbol names
     local_gen_sym_counter: Cell<usize>,
+
+    /// `codegen_static` will sometimes create a second global variable with a
+    /// different type and clear the symbol name of the original global.
+    /// `global_asm!` needs to be able to find this new global so that it can
+    /// compute the correct mangled symbol name to insert into the asm.
+    pub renamed_statics: RefCell<FxHashMap<DefId, &'ll Value>>,
 }
 
 pub struct TypeLowering<'ll> {
@@ -436,6 +443,7 @@ impl<'ll, 'tcx> CodegenCx<'ll, 'tcx> {
             rust_try_fn: Cell::new(None),
             intrinsics: Default::default(),
             local_gen_sym_counter: Cell::new(0),
+            renamed_statics: Default::default(),
         }
     }
 
diff --git a/compiler/rustc_codegen_llvm/src/llvm/ffi.rs b/compiler/rustc_codegen_llvm/src/llvm/ffi.rs
index 375b9927c86..7f533b0552a 100644
--- a/compiler/rustc_codegen_llvm/src/llvm/ffi.rs
+++ b/compiler/rustc_codegen_llvm/src/llvm/ffi.rs
@@ -2537,4 +2537,6 @@ extern "C" {
         remark_passes_len: usize,
     );
 
+    #[allow(improper_ctypes)]
+    pub fn LLVMRustGetMangledName(V: &Value, out: &RustString);
 }