fix(parser): read the segment-absolute rendering FS:0
The toolchain's disassembler prints the segment-prefixed disp32 absolute as FS:0, but the bare-name branch read the segment register alone and dropped the offset, so MOVQ FS:0, DX silently encoded a register move. The colon-offset form now lowers to the same segment-absolute operand the 0(FS) spelling takes. Assisted-by: GLM 5.3 Flash
This commit is contained in:
1 parent
abc2d32b83
commit
a829b8f321
2 files changed
+63
No files matched your search
@@ -0,0 +1,48 @@
|
||||
// Copyright (c) 2026 Petr Balvín <opensource@petrbalvin.org> (https://petrbalvin.org)
|
||||
// SPDX-License-Identifier: BSD-3-Clause
|
||||
|
||||
package asm
|
||||
|
||||
import (
|
||||
"encoding/hex"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"sourcedock.dev/petrbalvin/gasm-sdk/parser"
|
||||
)
|
||||
|
||||
// TestRenderedTextEncodes pins the encoder against the disassembler's
|
||||
// renderings: every line here is a text the toolchain's own decoder prints
|
||||
// for bytes its assembler produced (the disasm package's parity fixtures),
|
||||
// so assembling the printed text must reproduce those bytes. Each row was
|
||||
// read back through the toolchain's decoder; the hex is the fixture's.
|
||||
func TestRenderedTextEncodes(t *testing.T) {
|
||||
for _, tt := range []struct {
|
||||
text string
|
||||
want string
|
||||
}{
|
||||
// The segment-absolute rendering lowers to the FS-prefixed disp32
|
||||
// absolute, exactly what the 0(FS) spelling encodes.
|
||||
{"MOVQ FS:0, DX", "64488b142500000000"},
|
||||
} {
|
||||
src := "TEXT \u00b7k(SB), NOSPLIT, $0\n\t" + tt.text + "\n\tRET\n"
|
||||
f, errs := parser.Parse("k.s", src)
|
||||
if len(errs) > 0 {
|
||||
t.Errorf("%s: parse: %v", tt.text, errs[0])
|
||||
continue
|
||||
}
|
||||
img, err := AssembleFile(f)
|
||||
if err != nil {
|
||||
t.Errorf("%s: assemble: %v", tt.text, err)
|
||||
continue
|
||||
}
|
||||
fn := img.Funcs[0]
|
||||
code := img.Code[fn.Offset : fn.Offset+fn.Size]
|
||||
// The no-fallthrough rule appends the RET; the pinned instruction is
|
||||
// the prefix.
|
||||
got := hex.EncodeToString(code)
|
||||
if !strings.HasPrefix(got, tt.want) {
|
||||
t.Errorf("%s: bytes %s, want prefix %s", tt.text, got, tt.want)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -678,6 +678,21 @@ func parseAddress(g []token.Token) ast.Address {
|
||||
i++
|
||||
}
|
||||
}
|
||||
// Segment-absolute in the rendering spelling: FS:0 and GS:0. The
|
||||
// colon-offset form is what the toolchain's disassembler prints for the
|
||||
// segment-prefixed disp32 absolute, so the rendered text must re-encode;
|
||||
// without it the segment register alone parsed and the offset vanished.
|
||||
// The base field naming the segment lowers to the same operand the
|
||||
// 0(FS) spelling takes.
|
||||
if len(g) >= 3 && g[0].Kind == token.Ident && g[1].Kind == token.Colon &&
|
||||
(g[0].Text == "FS" || g[0].Text == "GS") {
|
||||
if v, rest, ok := foldExpr(g[2:]); ok && len(rest) == 0 {
|
||||
addr.Base = g[0].Text
|
||||
addr.Offset = v
|
||||
addr.HasOff = true
|
||||
return addr
|
||||
}
|
||||
}
|
||||
// Bare name (register, label or symbol) possibly with an arm64 shift.
|
||||
if addr.Base == "" && addr.Sym == nil && g[0].Kind == token.Ident {
|
||||
sym := &ast.Symbol{Pos: g[0].Pos}
|
||||
|
||||
Reference in new issue
Block a user