Re: [Qemu-devel] [PATCH v3 4/5] target-ppc: add lxvh8x and stxvh8x

[David Gibson]

On Fri, Sep 16, 2016 at 04:21:50PM +0530, Nikunj A Dadhania wrote:
> lxvh8x:  Load VSX Vector Halfword*8
> stxvh8x:  Store VSX Vector Halfword*8
> 
> Signed-off-by: Nikunj A Dadhania <address@hidden>
> ---
>  target-ppc/helper.h                 |  1 +
>  target-ppc/mem_helper.c             |  6 ++++
>  target-ppc/translate/vsx-impl.inc.c | 59 
> +++++++++++++++++++++++++++++++++++++
>  target-ppc/translate/vsx-ops.inc.c  |  2 ++
>  4 files changed, 68 insertions(+)
> 
> diff --git a/target-ppc/helper.h b/target-ppc/helper.h
> index 9f6705d..ae91c3b 100644
> --- a/target-ppc/helper.h
> +++ b/target-ppc/helper.h
> @@ -298,6 +298,7 @@ DEF_HELPER_3(lvebx, void, env, avr, tl)
>  DEF_HELPER_3(lvehx, void, env, avr, tl)
>  DEF_HELPER_3(lvewx, void, env, avr, tl)
>  DEF_HELPER_1(deposit32x2, i64, i64)
> +DEF_HELPER_1(bswap16x4, i64, i64)
>  DEF_HELPER_3(stvebx, void, env, avr, tl)
>  DEF_HELPER_3(stvehx, void, env, avr, tl)
>  DEF_HELPER_3(stvewx, void, env, avr, tl)
> diff --git a/target-ppc/mem_helper.c b/target-ppc/mem_helper.c
> index 86e493e..26d5617 100644
> --- a/target-ppc/mem_helper.c
> +++ b/target-ppc/mem_helper.c
> @@ -290,6 +290,12 @@ uint64_t helper_deposit32x2(uint64_t x)
>      return deposit64((x >> 32), 32, 32, (x));
>  }
>  
> +uint64_t helper_bswap16x4(uint64_t x)
> +{
> +    uint64_t m = 0x00ff00ff00ff00ffull;
> +    return ((x & m) << 8) | ((x >> 8) & m);
> +}
> +
>  #undef HI_IDX
>  #undef LO_IDX
>  
> diff --git a/target-ppc/translate/vsx-impl.inc.c 
> b/target-ppc/translate/vsx-impl.inc.c
> index a3868f6..9e7588d 100644
> --- a/target-ppc/translate/vsx-impl.inc.c
> +++ b/target-ppc/translate/vsx-impl.inc.c
> @@ -93,6 +93,36 @@ static void gen_lxvw4x(DisasContext *ctx)
>      tcg_temp_free(EA);
>  }
>  
> +static void gen_lxvh8x(DisasContext *ctx)
> +{
> +    TCGv EA;
> +    TCGv_i64 xth = cpu_vsrh(xT(ctx->opcode));
> +    TCGv_i64 xtl = cpu_vsrl(xT(ctx->opcode));
> +
> +    if (unlikely(!ctx->vsx_enabled)) {
> +        gen_exception(ctx, POWERPC_EXCP_VSXU);
> +        return;
> +    }
> +    gen_set_access_type(ctx, ACCESS_INT);
> +    EA = tcg_temp_new();
> +    gen_addr_reg_index(ctx, EA);
> +
> +    if (ctx->le_mode) {
> +        tcg_gen_qemu_ld_i64(xth, EA, ctx->mem_idx, MO_BEQ);
> +        gen_helper_bswap16x4(xth, xth);
> +        tcg_gen_addi_tl(EA, EA, 8);
> +        tcg_gen_qemu_ld_i64(xtl, EA, ctx->mem_idx, MO_BEQ);
> +        gen_helper_bswap16x4(xtl, xtl);
> +    } else {
> +        tcg_gen_qemu_ld_i64(xth, EA, ctx->mem_idx, MO_LEQ);
> +        gen_helper_deposit32x2(xth, xth);
> +        tcg_gen_addi_tl(EA, EA, 8);
> +        tcg_gen_qemu_ld_i64(xtl, EA, ctx->mem_idx, MO_LEQ);
> +        gen_helper_deposit32x2(xtl, xtl);

The BE path still looks wrong.  In fact, it's almost as wrong as it
could possibly be.

The LE load means the bytes of each halfword will be in the wrong
order.  It also means lower-address halfwords will end up in less
significant halfwords internally, which is also wrong.  Finally the
deposit32x2 will get pairs of halfwords in the right relative order,
but the order of the halfwords within the pair will still be wrong.

I really think you need to make yourself some testcases for these...

I think what you actually want is a BE load in all cases (which gets
the halfword order correct), then apply the 16x4 bswap if and only if
you're in LE mode, to get the bytes within each halfword in the right
order.

> +    }
> +    tcg_temp_free(EA);
> +}
> +
>  #define VSX_STORE_SCALAR(name, operation)                     \
>  static void gen_##name(DisasContext *ctx)                     \
>  {                                                             \
> @@ -152,6 +182,35 @@ static void gen_stxvw4x(DisasContext *ctx)
>      tcg_temp_free(EA);
>  }
>  
> +static void gen_stxvh8x(DisasContext *ctx)
> +{
> +    TCGv_i64 xsh = cpu_vsrh(xS(ctx->opcode));
> +    TCGv_i64 xsl = cpu_vsrl(xS(ctx->opcode));
> +    TCGv EA;
> +
> +    if (unlikely(!ctx->vsx_enabled)) {
> +        gen_exception(ctx, POWERPC_EXCP_VSXU);
> +        return;
> +    }
> +    gen_set_access_type(ctx, ACCESS_INT);
> +    EA = tcg_temp_new();
> +    gen_addr_reg_index(ctx, EA);
> +    if (ctx->le_mode) {
> +        gen_helper_bswap16x4(xsh, xsh);
> +        tcg_gen_qemu_st_i64(xsh, EA, ctx->mem_idx, MO_BEQ);
> +        tcg_gen_addi_tl(EA, EA, 8);
> +        gen_helper_bswap16x4(xsl, xsl);
> +        tcg_gen_qemu_st_i64(xsl, EA, ctx->mem_idx, MO_BEQ);
> +    } else {
> +        gen_helper_deposit32x2(xsh, xsh);
> +        tcg_gen_qemu_st_i64(xsh, EA, ctx->mem_idx, MO_LEQ);
> +        tcg_gen_addi_tl(EA, EA, 8);
> +        gen_helper_deposit32x2(xsl, xsl);
> +        tcg_gen_qemu_st_i64(xsl, EA, ctx->mem_idx, MO_LEQ);

Same problems as the load side.

> +    }
> +    tcg_temp_free(EA);
> +}
> +
>  #define MV_VSRW(name, tcgop1, tcgop2, target, source)           \
>  static void gen_##name(DisasContext *ctx)                       \
>  {                                                               \
> diff --git a/target-ppc/translate/vsx-ops.inc.c 
> b/target-ppc/translate/vsx-ops.inc.c
> index 414b73b..21f9064 100644
> --- a/target-ppc/translate/vsx-ops.inc.c
> +++ b/target-ppc/translate/vsx-ops.inc.c
> @@ -7,6 +7,7 @@ GEN_HANDLER_E(lxsspx, 0x1F, 0x0C, 0x10, 0, PPC_NONE, 
> PPC2_VSX207),
>  GEN_HANDLER_E(lxvd2x, 0x1F, 0x0C, 0x1A, 0, PPC_NONE, PPC2_VSX),
>  GEN_HANDLER_E(lxvdsx, 0x1F, 0x0C, 0x0A, 0, PPC_NONE, PPC2_VSX),
>  GEN_HANDLER_E(lxvw4x, 0x1F, 0x0C, 0x18, 0, PPC_NONE, PPC2_VSX),
> +GEN_HANDLER_E(lxvh8x, 0x1F, 0x0C, 0x19, 0, PPC_NONE,  PPC2_ISA300),
>  
>  GEN_HANDLER_E(stxsdx, 0x1F, 0xC, 0x16, 0, PPC_NONE, PPC2_VSX),
>  GEN_HANDLER_E(stxsibx, 0x1F, 0xD, 0x1C, 0, PPC_NONE, PPC2_ISA300),
> @@ -15,6 +16,7 @@ GEN_HANDLER_E(stxsiwx, 0x1F, 0xC, 0x04, 0, PPC_NONE, 
> PPC2_VSX207),
>  GEN_HANDLER_E(stxsspx, 0x1F, 0xC, 0x14, 0, PPC_NONE, PPC2_VSX207),
>  GEN_HANDLER_E(stxvd2x, 0x1F, 0xC, 0x1E, 0, PPC_NONE, PPC2_VSX),
>  GEN_HANDLER_E(stxvw4x, 0x1F, 0xC, 0x1C, 0, PPC_NONE, PPC2_VSX),
> +GEN_HANDLER_E(stxvh8x, 0x1F, 0x0C, 0x1D, 0, PPC_NONE,  PPC2_ISA300),
>  
>  GEN_HANDLER_E(mfvsrwz, 0x1F, 0x13, 0x03, 0x0000F800, PPC_NONE, PPC2_VSX207),
>  GEN_HANDLER_E(mtvsrwa, 0x1F, 0x13, 0x06, 0x0000F800, PPC_NONE, PPC2_VSX207),

-- 
David Gibson                    | I'll have my music baroque, and my code
david AT gibson.dropbear.id.au  | minimalist, thank you.  NOT _the_ _other_
                                | _way_ _around_!
http://www.ozlabs.org/~dgibson

signature.asc
Description: PGP signature