compiler: move global handling from ir to compiler package

This is part of a larger rafactor that tries to shrink the ir package
and in general tries to shrink the amount of state that is kept around
in the compiler. The end goal is being able to compile packages
independent of each other, linking them together in a later stage. Along
the way, it cleans up lots of old cruft that has accumulated over the
months.

This refactor also results in globals being loaded lazily. This may be a
problem for some specific programs but will probably change back in a
commit in the near future.

compiler/compiler.go

@@ -3,6 +3,7 @@ package compiler
 import (
 	"errors"
 	"fmt"
+	"go/ast"
 	"go/build"
 	"go/constant"
 	"go/token"
@@ -66,6 +67,7 @@ type Compiler struct {
 	interfaceInvokeWrappers []interfaceInvokeWrapper
 	ir                      *ir.Program
 	diagnostics             []error
+	astComments             map[string]*ast.CommentGroup
 }
 
 type Frame struct {
@@ -275,20 +277,7 @@ func (c *Compiler) Compile(mainPath string) []error {
 
 	var frames []*Frame
 
-	// Declare all globals.
-	for _, g := range c.ir.Globals {
-		typ := g.Type().(*types.Pointer).Elem()
-		llvmType := c.getLLVMType(typ)
-		global := c.mod.NamedGlobal(g.LinkName())
-		if global.IsNil() {
-			global = llvm.AddGlobal(c.mod, llvmType, g.LinkName())
-		}
-		g.LLVMGlobal = global
-		if !g.IsExtern() {
-			global.SetLinkage(llvm.InternalLinkage)
-			global.SetInitializer(c.getZeroValue(llvmType))
-		}
-	}
+	c.loadASTComments(lprogram)
 
 	// Declare all functions.
 	for _, f := range c.ir.Functions {
@@ -1357,9 +1346,9 @@ func (c *Compiler) getValue(frame *Frame, expr ssa.Value) llvm.Value {
 		}
 		return c.createFuncValue(fn.LLVMFn, llvm.Undef(c.i8ptrType), fn.Signature)
 	case *ssa.Global:
-		value := c.ir.GetGlobal(expr).LLVMGlobal
+		value := c.getGlobal(expr)
 		if value.IsNil() {
-			c.addError(expr.Pos(), "global not found: "+c.ir.GetGlobal(expr).LinkName())
+			c.addError(expr.Pos(), "global not found: "+expr.RelString(nil))
 			return llvm.Undef(c.getLLVMType(expr.Type()))
 		}
 		return value
@@ -2511,8 +2500,8 @@ func (c *Compiler) parseUnOp(frame *Frame, unop *ssa.UnOp) (llvm.Value, error) {
 			//     var C.add unsafe.Pointer
 			// Instead of a load from the global, create a bitcast of the
 			// function pointer itself.
-			global := c.ir.GetGlobal(unop.X.(*ssa.Global))
-			name := global.LinkName()[:len(global.LinkName())-len("$funcaddr")]
+			globalName := c.getGlobalInfo(unop.X.(*ssa.Global)).linkName
+			name := globalName[:len(globalName)-len("$funcaddr")]
 			fn := c.mod.NamedFunction(name)
 			if fn.IsNil() {
 				return llvm.Value{}, c.makeError(unop.Pos(), "cgo function not found: "+name)

compiler/symbol.go

@@ -0,0 +1,107 @@
+package compiler
+
+// This file manages symbols, that is, functions and globals. It reads their
+// pragmas, determines the link name, etc.
+
+import (
+	"go/ast"
+	"go/token"
+	"go/types"
+	"strings"
+
+	"github.com/tinygo-org/tinygo/loader"
+	"golang.org/x/tools/go/ssa"
+	"tinygo.org/x/go-llvm"
+)
+
+// globalInfo contains some information about a specific global. By default,
+// linkName is equal to .RelString(nil) on a global and extern is false, but for
+// some symbols this is different (due to //go:extern for example).
+type globalInfo struct {
+	linkName string // go:extern
+	extern   bool   // go:extern
+}
+
+// loadASTComments loads comments on globals from the AST, for use later in the
+// program. In particular, they are required for //go:extern pragmas on globals.
+func (c *Compiler) loadASTComments(lprogram *loader.Program) {
+	c.astComments = map[string]*ast.CommentGroup{}
+	for _, pkgInfo := range lprogram.Sorted() {
+		for _, file := range pkgInfo.Files {
+			for _, decl := range file.Decls {
+				switch decl := decl.(type) {
+				case *ast.GenDecl:
+					switch decl.Tok {
+					case token.VAR:
+						if len(decl.Specs) != 1 {
+							continue
+						}
+						for _, spec := range decl.Specs {
+							switch spec := spec.(type) {
+							case *ast.ValueSpec: // decl.Tok == token.VAR
+								for _, name := range spec.Names {
+									id := pkgInfo.Pkg.Path() + "." + name.Name
+									c.astComments[id] = decl.Doc
+								}
+							}
+						}
+					}
+				}
+			}
+		}
+	}
+}
+
+// getGlobal returns a LLVM IR global value for a Go SSA global. It is added to
+// the LLVM IR if it has not been added already.
+func (c *Compiler) getGlobal(g *ssa.Global) llvm.Value {
+	info := c.getGlobalInfo(g)
+	llvmGlobal := c.mod.NamedGlobal(info.linkName)
+	if llvmGlobal.IsNil() {
+		llvmType := c.getLLVMType(g.Type().(*types.Pointer).Elem())
+		llvmGlobal = llvm.AddGlobal(c.mod, llvmType, info.linkName)
+		if !info.extern {
+			llvmGlobal.SetInitializer(c.getZeroValue(llvmType))
+			llvmGlobal.SetLinkage(llvm.InternalLinkage)
+		}
+	}
+	return llvmGlobal
+}
+
+// getGlobalInfo returns some information about a specific global.
+func (c *Compiler) getGlobalInfo(g *ssa.Global) globalInfo {
+	info := globalInfo{}
+	if strings.HasPrefix(g.Name(), "C.") {
+		// Created by CGo: such a name cannot be created by regular C code.
+		info.linkName = g.Name()[2:]
+		info.extern = true
+	} else {
+		// Pick the default linkName.
+		info.linkName = g.RelString(nil)
+		// Check for //go: pragmas, which may change the link name (among
+		// others).
+		doc := c.astComments[info.linkName]
+		if doc != nil {
+			info.parsePragmas(doc)
+		}
+	}
+	return info
+}
+
+// Parse //go: pragma comments from the source. In particular, it parses the
+// //go:extern pragma on globals.
+func (info *globalInfo) parsePragmas(doc *ast.CommentGroup) {
+	for _, comment := range doc.List {
+		if !strings.HasPrefix(comment.Text, "//go:") {
+			continue
+		}
+		parts := strings.Fields(comment.Text)
+		switch parts[0] {
+		case "//go:extern":
+			info.extern = true
+			if len(parts) == 2 {
+				info.linkName = parts[1]
+			}
+		}
+	}
+}