fix(asm): add cross-package GOOBJ resolution for riscv64, loong64, arm64

Assisted-by: MiMo V2.5 Pro

asm/arm64_assemble.go

@@ -192,9 +192,9 @@ func encodeARM64Instr(instr *ast.Instr, pc int, offsets map[string]int, fi arm64
 		}
 		return a64wordLE(uint32(immFromOperand(ops[0]))), nil
 	case "B":
-		return encodeARM64Branch(mnem, ops, pc, offsets, false, resolve)
+		return encodeARM64Branch(mnem, ops, pc, offsets, false, relocs, resolve)
 	case "BL", "CALL":
-		return encodeARM64Branch(mnem, ops, pc, offsets, true, resolve)
+		return encodeARM64Branch(mnem, ops, pc, offsets, true, relocs, resolve)
 	case "MOV", "MOVD", "MOVW", "MOVWU", "MOVH", "MOVHU", "MOVB", "MOVBU",
 		"FMOVS", "FMOVD":
 		return encodeARM64Mov(instr, mnem, fi, relocs)
@@ -300,7 +300,7 @@ func encodeARM64Instr(instr *ast.Instr, pc int, offsets map[string]int, fi arm64
 // ---- branch encoding ----
 
 // encodeARM64Branch encodes an unconditional branch (B/BL) to a label.
-func encodeARM64Branch(mnem string, ops []*ast.Operand, pc int, offsets map[string]int, link bool, resolve func(string) string) ([]byte, error) {
+func encodeARM64Branch(mnem string, ops []*ast.Operand, pc int, offsets map[string]int, link bool, relocs *[]Reloc, resolve func(string) string) ([]byte, error) {
 	if len(ops) != 1 {
 		return nil, fmt.Errorf("%s expects 1 operand, got %d", mnem, len(ops))
 	}
@@ -308,6 +308,15 @@ func encodeARM64Branch(mnem string, ops []*ast.Operand, pc int, offsets map[stri
 
 	// External symbol reference: BL sym(SB).
 	if link && op.Addr.Sym != nil && op.Addr.Sym.Pseudo == "SB" {
+		if relocs != nil {
+			*relocs = append(*relocs, Reloc{
+				Off:    0,
+				After:  4,
+				Name:   op.Addr.Sym.Name,
+				Addend: op.Addr.Sym.Offset,
+				Kind:   RelArm64Branch,
+			})
+		}
 		// Emit BL with zero offset; the linker fills in the target.
 		return a64wordLE(a64Branch(1, 0)), nil
 	}
@@ -1324,5 +1333,6 @@ func AssembleFileARM64(f *ast.File) (*Image, error) {
 		})
 	}
 
+	markExternals(img, dataSyms)
 	return img, nil
 }

asm/elfarm64.go

@@ -16,6 +16,7 @@ const (
 	// AArch64 relocation types (the ELF psABI).
 	rArm64PrelPgHi21   = 275 // R_AARCH64_ADR_PREL_PG_HI21 (ADRP page)
 	rArm64AddAbsLo12NC = 277 // R_AARCH64_ADD_ABS_LO12_NC (ADD/STR/LDR page offset)
+	rArm64Call26       = 283 // R_AARCH64_CALL26 (BL instruction)
 )
 
 // ELFAARCH64Object returns the image as an ELF64 relocatable object file for
@@ -94,10 +95,14 @@ func (img *Image) ELFAARCH64Object() ([]byte, error) {
 			if !ok {
 				return nil, fmt.Errorf("relocation references unknown symbol %q", r.Name)
 			}
-			typ := uint32(rArm64PrelPgHi21)
-			if r.Kind == RelArm64Addr && r.Off%4 == 4 {
-				// The second instruction in an ADRP pair uses ADD_ABS_LO12_NC.
+			var typ uint32
+			switch {
+			case r.Kind == RelArm64Branch:
+				typ = rArm64Call26
+			case r.Kind == RelArm64Addr && r.Off%4 == 4:
 				typ = rArm64AddAbsLo12NC
+			default:
+				typ = rArm64PrelPgHi21
 			}
 			relas = append(relas, elfRela{
 				off:    uint64(fn.Offset + r.Off),

asm/goobjarm64.go

@@ -24,14 +24,17 @@ func (img *Image) GOObjectAARCH64(pkgPath, srcPath string) ([]byte, error) {
 		return nil, err
 	}
 	return img.emitGOObject(pkgPath, srcPath, pre, 4, func(r Reloc) (uint16, uint8) {
+		if r.Kind == RelArm64Branch {
+			return relocArm64Branch, 4
+		}
 		return relocArm64Addr, 4
 	})
 }
 
-// arm64 relocation types (cmd/internal/objabi).  R_ADDRARM64 resolves an
-// ADRP+ADD/LDR/STR pair to a symbol's address.
+// arm64 relocation types (cmd/internal/objabi).
 const (
-	relocArm64Addr = 9 // R_ADDRARM64
+	relocArm64Addr   = 3 // R_ADDRARM64 — ADRP+ADD/LDR/STR pair
+	relocArm64Branch = 9 // R_CALLARM64 — BL instruction
 )
 
 // toolchainObjectPreambleAARCH64 returns the "go object ...\n!\n" header

asm/link.go

@@ -97,6 +97,7 @@ const (
 	RelLoong64AddrHi                    // R_LOONG64_ADDR_HI (pcalau12i)
 	RelLoong64AddrLo                    // R_LOONG64_ADDR_LO (addi.d/ld/st)
 	RelArm64Addr                        // R_ADDRARM64 (ADRP + ADD/LDR/STR pair)
+	RelArm64Branch                      // R_CALLARM64 (BL instruction)
 )
 
 type Reloc struct {
@@ -302,6 +303,7 @@ func AssembleFileRISCV(f *ast.File) (*Image, error) {
 		})
 	}
 
+	markExternals(img, dataSyms)
 	return img, nil
 }
 
@@ -373,9 +375,38 @@ func AssembleFileLOONG64(f *ast.File) (*Image, error) {
 		})
 	}
 
+	markExternals(img, dataSyms)
 	return img, nil
 }
 
+// markExternals identifies relocations that reference symbols not defined in
+// the file (neither a GLOBL/DATA symbol nor a TEXT function) and records them
+// as external.  The non-amd64 architectures emit relocations for every SB
+// reference; this post-processing step distinguishes file-local from external.
+func markExternals(img *Image, dataSyms []dataSym) {
+	known := make(map[string]bool, len(dataSyms)+len(img.Funcs))
+	for _, d := range dataSyms {
+		known[d.name] = true
+	}
+	for _, fn := range img.Funcs {
+		known[fn.Name] = true
+	}
+	externals := map[string]bool{}
+	for i := range img.Funcs {
+		for j := range img.Funcs[i].Relocs {
+			r := &img.Funcs[i].Relocs[j]
+			if !known[r.Name] {
+				r.External = true
+				externals[r.Name] = true
+			}
+		}
+	}
+	for name := range externals {
+		img.Externals = append(img.Externals, name)
+	}
+	sort.Strings(img.Externals)
+}
+
 // dataSym is one GLOBL symbol and its DATA initialiser.
 type dataSym struct {
 	name   string