On Wed, 11 Aug 2021 at 00:26, Richard Henderson <richard.hender...@linaro.org> wrote: > > We need to be able to represent VEX.W on a 32-bit host, where REX.W > will always be zero. Fixes the encoding for VPSLLVQ and VPSRLVQ. > > Resolves: https://gitlab.com/qemu-project/qemu/-/issues/385 > Signed-off-by: Richard Henderson <richard.hender...@linaro.org> > --- > tcg/i386/tcg-target.c.inc | 13 +++++++------ > 1 file changed, 7 insertions(+), 6 deletions(-) > > diff --git a/tcg/i386/tcg-target.c.inc b/tcg/i386/tcg-target.c.inc > index 98d924b91a..997510109d 100644 > --- a/tcg/i386/tcg-target.c.inc > +++ b/tcg/i386/tcg-target.c.inc > @@ -241,8 +241,9 @@ static bool tcg_target_const_match(int64_t val, TCGType > type, int ct) > #define P_EXT 0x100 /* 0x0f opcode prefix */ > #define P_EXT38 0x200 /* 0x0f 0x38 opcode prefix */ > #define P_DATA16 0x400 /* 0x66 opcode prefix */ > +#define P_VEXW 0x1000 /* Set VEX.W = 1 */ > #if TCG_TARGET_REG_BITS == 64 > -# define P_REXW 0x1000 /* Set REX.W = 1 */ > +# define P_REXW P_VEXW /* Set REX.W = 1; match VEXW */ > # define P_REXB_R 0x2000 /* REG field as byte register */ > # define P_REXB_RM 0x4000 /* R/M field as byte register */ > # define P_GS 0x8000 /* gs segment override */ > @@ -410,13 +411,13 @@ static bool tcg_target_const_match(int64_t val, TCGType > type, int ct) > #define OPC_VPBROADCASTW (0x79 | P_EXT38 | P_DATA16) > #define OPC_VPBROADCASTD (0x58 | P_EXT38 | P_DATA16) > #define OPC_VPBROADCASTQ (0x59 | P_EXT38 | P_DATA16) > -#define OPC_VPERMQ (0x00 | P_EXT3A | P_DATA16 | P_REXW) > +#define OPC_VPERMQ (0x00 | P_EXT3A | P_DATA16 | P_VEXW) > #define OPC_VPERM2I128 (0x46 | P_EXT3A | P_DATA16 | P_VEXL) > #define OPC_VPSLLVD (0x47 | P_EXT38 | P_DATA16) > -#define OPC_VPSLLVQ (0x47 | P_EXT38 | P_DATA16 | P_REXW) > +#define OPC_VPSLLVQ (0x47 | P_EXT38 | P_DATA16 | P_VEXW) > #define OPC_VPSRAVD (0x46 | P_EXT38 | P_DATA16) > #define OPC_VPSRLVD (0x45 | P_EXT38 | P_DATA16) > -#define OPC_VPSRLVQ (0x45 | P_EXT38 | P_DATA16 | P_REXW) > +#define OPC_VPSRLVQ (0x45 | P_EXT38 | P_DATA16 | P_VEXW) > #define OPC_VZEROUPPER (0x77 | P_EXT) > #define OPC_XCHG_ax_r32 (0x90) > > @@ -576,7 +577,7 @@ static void tcg_out_vex_opc(TCGContext *s, int opc, int > r, int v, > > /* Use the two byte form if possible, which cannot encode > VEX.W, VEX.B, VEX.X, or an m-mmmm field other than P_EXT. */ > - if ((opc & (P_EXT | P_EXT38 | P_EXT3A | P_REXW)) == P_EXT > + if ((opc & (P_EXT | P_EXT38 | P_EXT3A | P_VEXW)) == P_EXT > && ((rm | index) & 8) == 0) { > /* Two byte VEX prefix. */ > tcg_out8(s, 0xc5); > @@ -601,7 +602,7 @@ static void tcg_out_vex_opc(TCGContext *s, int opc, int > r, int v, > tmp |= (rm & 8 ? 0 : 0x20); /* VEX.B */ > tcg_out8(s, tmp); > > - tmp = (opc & P_REXW ? 0x80 : 0); /* VEX.W */ > + tmp = (opc & P_VEXW ? 0x80 : 0); /* VEX.W */ > } > > tmp |= (opc & P_VEXL ? 0x04 : 0); /* VEX.L */
These changes look OK as far as they go, but it's not clear to me why the other places that set P_REXW are all OK to use P_REXW and not P_VEXW. For instance tcg_out_mov() sets rexw = P_REXW and some of the codepaths there will then pass that into tcg_out_vex_modrm() which ends up in tcg_out_vex_opc(). More generally, is there somewhere we can assert that we didn't try to use a REXW prefix for i386 codegen rather than just silently ignoring it ? thanks -- PMM
