feat(amd64): LOCK and REP prefixes, literal data pseudo-ops and ADJSP

Assisted-by: GLM 5.3 Flash

testdata/verify/pfx_amd64.s

@@ -0,0 +1,103 @@
+// Instruction prefixes: LOCK, REP and REPN.  go tool asm encodes each
+// statement as a standalone one-byte instruction with a PC of its own (F0,
+// F3 and F2 respectively); the statement that follows is encoded unaware of
+// it, and nothing validates the pairing.  The shapes are the runtime's
+// atomic read-modify-write family and the string moves, every result folded
+// back.
+
+#include "textflag.h"
+
+// func cas64(ptr *uint64, old, new uint64) bool
+TEXT ·cas64(SB), NOSPLIT, $0-25
+	MOVQ     ptr+0(FP), BX
+	MOVQ     old+8(FP), AX
+	MOVQ     new+16(FP), CX
+	LOCK
+	CMPXCHGQ CX, 0(BX)
+	SETEQ    ret+24(FP)
+	RET
+
+// func casloop(addr *uint64, v uint64) uint64
+// The runtime's Or64 shape: a LOCK inside a branch loop, the backward jump
+// measuring over the prefix statement's own byte.
+TEXT ·casloop(SB), NOSPLIT, $0-24
+	MOVQ     addr+0(FP), BX
+	MOVQ     v+8(FP), CX
+
+loop:
+	MOVQ     CX, DX
+	MOVQ     (BX), AX
+	ORQ      AX, DX
+	LOCK
+	CMPXCHGQ DX, (BX)
+	JNZ      loop
+	MOVQ     AX, ret+16(FP)
+	RET
+
+// func xadd64(p *uint64, v uint64) uint64
+TEXT ·xadd64(SB), NOSPLIT, $0-24
+	MOVQ  p+0(FP), AX
+	MOVQ  v+8(FP), BX
+	LOCK
+	XADDQ BX, (AX)
+	MOVQ  AX, ret+16(FP)
+	RET
+
+// func xaddw(p *uint16, v uint16) uint16
+TEXT ·xaddw(SB), NOSPLIT, $0-12
+	MOVQ  p+0(FP), AX
+	MOVW  v+8(FP), BX
+	LOCK
+	XADDW BX, (AX)
+	MOVW  AX, ret+8(FP)
+	RET
+
+// func lockarith(p *uint64)
+TEXT ·lockarith(SB), NOSPLIT, $0-8
+	MOVQ p+0(FP), AX
+	LOCK
+	ORQ  CX, (AX)
+	LOCK
+	ANDL CX, (AX)
+	LOCK
+	INCQ (AX)
+	LOCK
+	DECQ (AX)
+	LOCK
+	ORB  BX, (AX)
+	RET
+
+// func repstring(dst, src *byte, n int)
+// The memmove shapes: forward copy by quadwords, backward tails.
+TEXT ·repstring(SB), NOSPLIT, $0-24
+	MOVQ  dst+0(FP), DI
+	MOVQ  src+8(FP), SI
+	REP
+	MOVSQ
+	REP
+	MOVSB
+	REPN
+	MOVSB
+	REP
+	STOSQ
+	REP
+	STOSB
+	RET
+
+// func pfxlabel()
+// Labels pinned on prefix statements' own bytes: pfx: sits on the LOCK,
+// mid: on the REPN.
+TEXT ·pfxlabel(SB), NOSPLIT, $0-0
+pfx:
+	LOCK
+	XCHGL BX, (AX)
+	JMP   done
+
+mid:
+	REPN
+	MOVSB
+
+done:
+	REP
+	STOSB
+	RET