feat(asm): the TLS access pair in the toolchain's one-instruction form

Assisted-by: GLM 5.3 Flash

asm/assemble.go

@@ -38,10 +38,25 @@ func Assemble(t *ast.Text) ([]byte, map[string]int, error) {
 // rejects SB operands outright (single-function assembly cannot resolve
 // them).  When allowExternal is set, a reference to a symbol no GLOBL in the
 // file defines is recorded as an external relocation instead of failing
-// the object-file emitters resolve it at link time.
+// the object-file emitters resolve it at link time.  goos selects the TLS
+// access form: the empty default behaves as linux.
 type linkInfo struct {
 	symbols       map[string]bool
 	allowExternal bool
+	goos          string
+}
+
+// tlsOneInsn reports the one-instruction TLS form, obj6.go's
+// CanUse1InsnTLS for the GOOS gasm supports: the bare TLS load nops out and
+// the (TLS*1) index folds to a segment-absolute access.  Windows and plan9
+// keep the two-instruction form; shared linux does too, which gasm's raw
+// path does not model and therefore does not select.
+func (l *linkInfo) tlsOneInsn() bool {
+	switch l.goos {
+	case "", "linux", "freebsd":
+		return true
+	}
+	return false
 }
 
 // sbPatch is a function-relative static-symbol relocation: the disp32 field
@@ -834,6 +849,15 @@ func encodeNormal(s *ast.Instr, fi frameInfo, link *linkInfo) ([]byte, []sbPatch
 		}
 		return e.out, ps, nil, nil
 	}
+	// MOVQ/MOVL TLS, r: the bare TLS load.  The toolchain's progedit nops
+	// it out on the one-instruction TLS systems (linux and freebsd, not
+	// shared) and encodes the segment-prefixed load elsewhere; get_tls(r),
+	// the macro GOROOT's go_tls.h defines, expands to exactly this
+	// statement, and the toolchain's pairing pass removes it whenever the
+	// following instruction's (TLS*1) index folds.
+	if (mnemUpper == "MOVQ" || mnemUpper == "MOVL") && len(s.Operands) == 2 && isBareTLS(s.Operands[0]) {
+		return encodeTLSBaseLoad(s, fi, link)
+	}
 	_, size := splitSize(mnemUpper)
 	if size == 0 {
 		size = 8
@@ -853,10 +877,67 @@ func encodeNormal(s *ast.Instr, fi frameInfo, link *linkInfo) ([]byte, []sbPatch
 	ps := make([]sbPatch, len(e.patches))
 	for i, p := range e.patches {
 		ps[i] = sbPatch{off: p.off, name: p.name, addend: p.addend}
+		if p.tls {
+			ps[i].kind = RelTLSLE
+		}
 	}
 	return e.out, ps, e.floatPoolList(), nil
 }
 
+// isBareTLS reports whether the operand is the bare TLS pseudo-register
+// load source, the expansion of go_tls.h's get_tls(r) macro.
+func isBareTLS(op *ast.Operand) bool {
+	return op.Kind == ast.OpAddr && op.Addr.Sym != nil &&
+		op.Addr.Sym.Pseudo == "" && op.Addr.Sym.Name == "TLS" &&
+		op.Addr.Base == "" && op.Addr.Index == ""
+}
+
+// encodeTLSBaseLoad assembles MOVQ/MOVL TLS, r.  On the one-instruction TLS
+// systems (linux and freebsd outside -shared, obj6.go's CanUse1InsnTLS) the
+// statement nops out: the following (TLS*1) access folds to a direct
+// segment-absolute load.  The two-instruction systems keep the segment load,
+// nine bytes with the R_TLSLE patch site at the disp32.
+func encodeTLSBaseLoad(s *ast.Instr, fi frameInfo, link *linkInfo) ([]byte, []sbPatch, []floatPoolEntry, error) {
+	_, size := splitSize(strings.ToUpper(s.Mnemonic.Text))
+	if size == 0 {
+		size = 8
+	}
+	dst, err := operandFromAST("MOVQ", s.Operands[1], 8, fi, link)
+	if err != nil {
+		return nil, nil, nil, err
+	}
+	reg, ok := dst.(Reg)
+	if !ok || reg.isVec() {
+		return nil, nil, nil, fmt.Errorf("TLS: destination must be a general register")
+	}
+	if link == nil || link.tlsOneInsn() {
+		return nil, nil, nil, nil // noped out
+	}
+	seg := byte(0x64) // FS
+	if link.goos == "windows" {
+		seg = 0x65 // GS
+	}
+	e := &enc{}
+	i := &instr{
+		prefix: seg,
+		rexW:   size == 8,
+		rexR:   reg.idx >= 8,
+		opcode: []byte{0x8B},
+		modrm:  0x04 | (reg.idx&7)<<3,
+		sib:    0x25,
+		disp:   le32(0),
+		tls:    true,
+	}
+	if err := e.emit(i); err != nil {
+		return nil, nil, nil, err
+	}
+	ps := make([]sbPatch, len(e.patches))
+	for i, p := range e.patches {
+		ps[i] = sbPatch{off: p.off, name: p.name, addend: p.addend, kind: RelTLSLE}
+	}
+	return e.out, ps, nil, nil
+}
+
 // encodeBookkeeping accepts-and-ignores FUNCDATA and PCDATA at the statement
 // level, before operand conversion: the toolchain's shapes are FUNCDATA
 // $n, sym(SB) and PCDATA $n, $m, and neither contributes a byte to the
@@ -1108,6 +1189,19 @@ func operandFromAST(mnemUpper string, op *ast.Operand, size int, fi frameInfo, l
 			}
 			m := Mem{Base: base, Disp: a.Offset, HasBase: true, Size: size}
 			if a.Index != "" {
+				if a.Index == "TLS" {
+					// off(base)(TLS*1): the thread-local annotation.  The
+					// one-instruction TLS form folds it to off(TLS), the
+					// segment-prefixed absolute whose disp32 carries an
+					// R_TLS_LE patch site; the base register disappears
+					// from the encoding, exactly as the toolchain's
+					// progedit rewrites the address.
+					seg := byte(0x64) // FS on linux, freebsd, plan9
+					if link != nil && link.goos == "windows" {
+						seg = 0x65 // GS
+					}
+					return TLSMem{Disp: a.Offset, Size: size, Seg: seg}, nil
+				}
 				idx, ok := ParseReg(a.Index)
 				if !ok {
 					return nil, fmt.Errorf("unknown index register %q", a.Index)