feat(asm): the operand forms and defines GOROOT writes

Assisted-by: GLM 5.3 Flash

asm/assemble.go

@@ -86,6 +86,10 @@ func assemble(t *ast.Text, link *linkInfo) ([]byte, []sbPatch, map[string]int, [
 	// outgrows the short form.
 	long := make([]bool, len(t.Body))
 	sizes := make([]int, len(t.Body))
+	numTargets := make([]int, len(t.Body))
+	for i := range numTargets {
+		numTargets[i] = -1
+	}
 	offsets := map[string]int{}
 	pcs := make([]int, len(t.Body))
 	var guardJBlong, guardJBElong, moreJMPlong bool
@@ -94,6 +98,10 @@ func assemble(t *ast.Text, link *linkInfo) ([]byte, []sbPatch, map[string]int, [
 	for {
 		guard := fi.guardLen(guardJBlong, guardJBElong)
 		pos := guard + len(fi.prologue)
+		for i := range numTargets {
+			numTargets[i] = -1
+		}
+		idxAtPc := map[int]int{}
 		for i, stmt := range t.Body {
 			switch s := stmt.(type) {
 			case *ast.Label:
@@ -105,12 +113,78 @@ func assemble(t *ast.Text, link *linkInfo) ([]byte, []sbPatch, map[string]int, [
 				}
 				sizes[i] = sz
 				pcs[i] = pos
+				idxAtPc[pos] = i
 				pos += sz
 			}
 		}
 		bodyLen := pos - (guard + len(fi.prologue))
 		// Expand any short jump whose displacement no longer fits rel8.
 		changed := false
+		// Numeric ±N(PC) jumps resolve against this iteration's layout; the
+		// emission pass reads the same table after the loop converges.  A
+		// target that is itself an unconditional local JMP is chased to the
+		// ultimate target: the toolchain's brloop pass collapses branch-to-
+		// branch chains before it encodes, so matching its bytes requires
+		// the same redirection.
+		for i := range numTargets {
+			numTargets[i] = -1
+		}
+		for i, stmt := range t.Body {
+			s, ok := stmt.(*ast.Instr)
+			if !ok {
+				continue
+			}
+			if len(s.Operands) == 1 {
+				if n, isNum := pcJumpOffset(s.Operands[0]); isNum {
+					if target, okT := pcJumpTarget(t, i, n, pcs); okT {
+						numTargets[i] = target
+					}
+				}
+			}
+		}
+		for i := range numTargets {
+			if numTargets[i] < 0 {
+				continue
+			}
+			tgt := numTargets[i]
+			for hop := 0; hop < len(t.Body); hop++ {
+				idx, ok := idxAtPc[tgt]
+				if !ok {
+					break
+				}
+				in, ok := t.Body[idx].(*ast.Instr)
+				if !ok || strings.ToUpper(in.Mnemonic.Text) != "JMP" || len(in.Operands) != 1 {
+					break
+				}
+				if name, isLabel := labelName(in.Operands[0]); isLabel {
+					tgt = offsets[resolve(name)]
+					continue
+				}
+				if n, isNum := pcJumpOffset(in.Operands[0]); isNum {
+					next, okT := pcJumpTarget(t, idx, n, pcs)
+					if !okT {
+						break
+					}
+					tgt = next
+					continue
+				}
+				break // JMP through a register or memory: the chain ends
+			}
+			numTargets[i] = tgt
+		}
+		for i, stmt := range t.Body {
+			s, ok := stmt.(*ast.Instr)
+			if !ok {
+				continue
+			}
+			if numTargets[i] >= 0 && !long[i] {
+				rel := int64(numTargets[i] - (pcs[i] + jumpSize(strings.ToUpper(s.Mnemonic.Text), false)))
+				if !fits8(rel) {
+					long[i] = true
+					changed = true
+				}
+			}
+		}
 		for i, stmt := range t.Body {
 			s, ok := stmt.(*ast.Instr)
 			if !ok {
@@ -232,7 +306,7 @@ func assemble(t *ast.Text, link *linkInfo) ([]byte, []sbPatch, map[string]int, [
 				spadjStep{pos + epi, 0},
 			)
 		}
-		code, ps, pool, err := encodeInstr(s, pos, offsets, fi, long[i], resolve, link)
+		code, ps, pool, err := encodeInstr(s, pos, offsets, fi, long[i], resolve, link, numTargets[i])
 		if err != nil {
 			return nil, nil, nil, nil, nil, nil, fmt.Errorf("%s: %w", s.Mnemonic.Text, err)
 		}
@@ -428,6 +502,37 @@ func computeFrame(t *ast.Text) frameInfo {
 	return fi
 }
 
+// pcJumpOffset recognises the numeric relative jump operand ±N(PC) and
+// returns N: the toolchain counts instructions, not bytes, so +2(PC) targets
+// the second instruction boundary after the branch.
+func pcJumpOffset(op *ast.Operand) (int, bool) {
+	if op.Kind != ast.OpAddr || op.Addr.Base != "PC" {
+		return 0, false
+	}
+	return int(op.Addr.Offset), true
+}
+
+// pcJumpTarget resolves a numeric jump at statement index j: N counts the
+// instruction statements after the jump itself (N = 0 is the jump's own
+// address, the classic park loop), and the target is the start of the Nth
+// one.  It reports false when the count runs past the end of the function.
+func pcJumpTarget(t *ast.Text, j, n int, pcs []int) (int, bool) {
+	if n == 0 {
+		return pcs[j], true
+	}
+	seen := 0
+	for k := j + 1; k < len(t.Body); k++ {
+		if _, ok := t.Body[k].(*ast.Instr); !ok {
+			continue
+		}
+		seen++
+		if seen == n {
+			return pcs[k], true
+		}
+	}
+	return 0, false
+}
+
 // hasCall reports whether the function body contains a CALL instruction.
 func hasCall(t *ast.Text) bool {
 	for _, stmt := range t.Body {
@@ -602,7 +707,7 @@ func instrSize(s *ast.Instr, fi frameInfo, long bool, link *linkInfo) (int, erro
 		}
 		return jumpSize(mnem, long), nil
 	}
-	code, _, _, err := encodeInstr(s, 0, nil, fi, false, nil, link)
+	code, _, _, err := encodeInstr(s, 0, nil, fi, false, nil, link, -1)
 	if err != nil {
 		return 0, err
 	}
@@ -637,7 +742,7 @@ func jumpSize(mnem string, long bool) int {
 // (relative to pc, the instruction's own offset).  A RET in a frame-pointer
 // function is prefixed with the epilogue.  resolve, when non-nil, redirects a
 // jump label through the jump-to-jump chain before the offset lookup.
-func encodeInstr(s *ast.Instr, pc int, offsets map[string]int, fi frameInfo, long bool, resolve func(string) string, link *linkInfo) ([]byte, []sbPatch, []floatPoolEntry, error) {
+func encodeInstr(s *ast.Instr, pc int, offsets map[string]int, fi frameInfo, long bool, resolve func(string) string, link *linkInfo, numTarget int) ([]byte, []sbPatch, []floatPoolEntry, error) {
 	mnem := strings.ToUpper(s.Mnemonic.Text)
 
 	var prefix []byte
@@ -677,7 +782,7 @@ func encodeInstr(s *ast.Instr, pc int, offsets map[string]int, fi frameInfo, lon
 			}
 			return append(prefix, code...), nil, nil, nil
 		}
-		code, err = encodeJump(s, mnem, pc+len(prefix), offsets, long, resolve)
+		code, err = encodeJump(s, mnem, pc+len(prefix), offsets, long, resolve, numTarget)
 	} else {
 		code, ps, pool, err = encodeNormal(s, fi, link)
 	}
@@ -703,6 +808,32 @@ func encodeNormal(s *ast.Instr, fi frameInfo, link *linkInfo) ([]byte, []sbPatch
 		}
 		return code, nil, nil, nil
 	}
+	// MOVQ $sym±off(SB), r64: the toolchain assembles a symbol immediate as
+	// LEAQ disp32(RIP), r64 with an R_PCREL relocation at the disp32 field,
+	// never as a 64-bit absolute immediate (verified against go tool asm).
+	// MOVD is the MOVQ alias; the narrower widths reject the form outright.
+	if (mnemUpper == "MOVQ" || mnemUpper == "MOVD") && len(s.Operands) == 2 &&
+		s.Operands[0].Kind == ast.OpImmediate && s.Operands[0].Imm.Sym != nil &&
+		s.Operands[0].Imm.Sym.Pseudo == "SB" {
+		mem := &ast.Operand{Kind: ast.OpAddr, Addr: ast.Address{Sym: s.Operands[0].Imm.Sym}}
+		src, err := operandFromAST(mnemUpper, mem, 8, fi, link)
+		if err != nil {
+			return nil, nil, nil, err
+		}
+		dst, err := operandFromAST(mnemUpper, s.Operands[1], 8, fi, link)
+		if err != nil {
+			return nil, nil, nil, err
+		}
+		e := &enc{}
+		if err := e.encodeLea([]Operand{src, dst}, 8); 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}
+		}
+		return e.out, ps, nil, nil
+	}
 	_, size := splitSize(mnemUpper)
 	if size == 0 {
 		size = 8
@@ -753,21 +884,29 @@ func encodeBookkeeping(upper string, s *ast.Instr) ([]byte, error) {
 }
 
 // encodeJump encodes a JMP/CALL/Jcc with a relative offset resolved from the
-// target label, in the short (rel8) or long (rel32) form.
-func encodeJump(s *ast.Instr, mnem string, pc int, offsets map[string]int, long bool, resolve func(string) string) ([]byte, error) {
+// target label or from a numeric ±N(PC) instruction count, in the short
+// (rel8) or long (rel32) form.  numTarget is the resolved byte offset of a
+// numeric operand, negative when the operand is not one.
+func encodeJump(s *ast.Instr, mnem string, pc int, offsets map[string]int, long bool, resolve func(string) string, numTarget int) ([]byte, error) {
 	if len(s.Operands) != 1 {
 		return nil, fmt.Errorf("jump expects 1 operand, got %d", len(s.Operands))
 	}
-	name, ok := labelName(s.Operands[0])
-	if !ok {
+	name, isLabel := labelName(s.Operands[0])
+	if !isLabel && numTarget < 0 {
 		return nil, fmt.Errorf("jump target must be a local label")
 	}
-	if resolve != nil && mnem != "CALL" {
-		name = resolve(name)
-	}
-	target, ok := offsets[name]
-	if !ok {
-		return nil, fmt.Errorf("undefined label %q", name)
+	var target int
+	if isLabel {
+		if resolve != nil && mnem != "CALL" {
+			name = resolve(name)
+		}
+		t, ok := offsets[name]
+		if !ok {
+			return nil, fmt.Errorf("undefined label %q", name)
+		}
+		target = t
+	} else {
+		target = numTarget
 	}
 	rel := int64(target - (pc + jumpSize(mnem, long)))
 
@@ -841,6 +980,11 @@ func indirectJumpTarget(s *ast.Instr) bool {
 		return false
 	}
 	a := s.Operands[0].Addr
+	// ±N(PC) is the numeric relative form, the PC counts instructions from
+	// the branch: relative, not indirect.
+	if a.Base == "PC" || a.Index == "PC" {
+		return false
+	}
 	if a.Base != "" || a.Index != "" {
 		return true
 	}

asm/kernels_differential_test.go

@@ -130,6 +130,7 @@ func TestDifferentialKernels(t *testing.T) {
 		{filepath.Join("..", "testdata", "verify", "quadreg_amd64.s"), "", false},
 		{filepath.Join("..", "testdata", "verify", "floatimm_amd64.s"), "", false},
 		{filepath.Join("..", "testdata", "verify", "bookkeep_amd64.s"), "", false},
+		{filepath.Join("..", "testdata", "verify", "forms_amd64.s"), "", false},
 		{filepath.Join("..", "testdata", "verify", "datarel_arm64.s"), "arm64", true},
 		{filepath.Join("..", "testdata", "verify", "divslash_arm64.s"), "arm64", true},
 	} {

asm/link.go

@@ -166,6 +166,13 @@ func AssembleFile(f *ast.File) (*Image, error) {
 	for _, d := range dataSyms {
 		known[d.name] = true
 	}
+	// TEXT symbols are file-level definitions too: a symbol immediate
+	// ($fn(SB)) may name one, exactly as a data reference names a GLOBL.
+	for _, d := range f.Decls {
+		if t, ok := d.(*ast.Text); ok {
+			known[t.Name.Name] = true
+		}
+	}
 	link := &linkInfo{symbols: known, allowExternal: true}
 	poolSeen := map[string]bool{}