@@ -1479,6 +1479,12 @@ static void tcg_out_qemu_st_direct(TCGContext *s, TCGReg datalo, TCGReg datahi,
switch (memop & MO_SIZE) {
case MO_8:
+ /* In 32-bit mode, 8-byte stores can only happen from [abcd]x.
+ Use the scratch register if necessary. */
+ if (TCG_TARGET_REG_BITS == 32 && datalo >= 4) {
+ tcg_out_mov(s, TCG_TYPE_I32, scratch, datalo);
+ datalo = scratch;
+ }
tcg_out_modrm_offset(s, OPC_MOVB_EvGv + P_REXB_R + seg,
datalo, base, ofs);
break;
@@ -2084,7 +2090,7 @@ static const TCGTargetOpDef x86_op_defs[] = {
{ INDEX_op_qemu_ld32, { "r", "L" } },
{ INDEX_op_qemu_ld64, { "r", "r", "L" } },
- { INDEX_op_qemu_st8, { "cb", "L" } },
+ { INDEX_op_qemu_st8, { "L", "L" } },
{ INDEX_op_qemu_st16, { "L", "L" } },
{ INDEX_op_qemu_st32, { "L", "L" } },
{ INDEX_op_qemu_st64, { "L", "L", "L" } },
@@ -2096,7 +2102,7 @@ static const TCGTargetOpDef x86_op_defs[] = {
{ INDEX_op_qemu_ld32, { "r", "L", "L" } },
{ INDEX_op_qemu_ld64, { "r", "r", "L", "L" } },
- { INDEX_op_qemu_st8, { "cb", "L", "L" } },
+ { INDEX_op_qemu_st8, { "L", "L", "L" } },
{ INDEX_op_qemu_st16, { "L", "L", "L" } },
{ INDEX_op_qemu_st32, { "L", "L", "L" } },
{ INDEX_op_qemu_st64, { "L", "L", "L", "L" } },
Once we form a combined qemu_st_i32 opcode, we won't be able to have separate constraints based on size. This one is fairly easy to work around, since eax is available as a scratch register. When storing variable data, this tends to merely exchange one mov for another. E.g. -: mov %esi,%ecx ... -: mov %cl,(%edx) +: mov %esi,%eax +: mov %al,(%edx) Where we do have a regression is when storing constant data, in which we may load the constant into edi, when only ecx/ebx ought to be used. The proper way to recover this regression is to allow constants as arguments to qemu_st_i32, so that we never load the constant data into a register at all, must less the wrong register. TBD. Signed-off-by: Richard Henderson <rth@twiddle.net> --- tcg/i386/tcg-target.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-)