Re: [Qemu-devel] [PATCH 07/19] target/ppc: Make special ORs match x86 pause and don't generate on mttcg

[David Gibson]

On Mon, Jan 28, 2019 at 10:46:13AM +0100, Cédric Le Goater wrote:
> From: Benjamin Herrenschmidt <address@hidden>
> 
> There's no point in going out of translation on an SMT OR with
> mttcg since the backend won't do anything useful such as pausing,
> it's only useful on traditional TCG to give time to other
> processors.

Is it actively harmful in the MTTCG case, or just pointless?

> 
> Signed-off-by: Benjamin Herrenschmidt <address@hidden>
> Signed-off-by: Cédric Le Goater <address@hidden>
> ---
>  target/ppc/translate.c | 6 ++++--
>  1 file changed, 4 insertions(+), 2 deletions(-)
> 
> diff --git a/target/ppc/translate.c b/target/ppc/translate.c
> index e169c43643a1..7d40a1fbe6bd 100644
> --- a/target/ppc/translate.c
> +++ b/target/ppc/translate.c
> @@ -1580,7 +1580,7 @@ static void gen_pause(DisasContext *ctx)
>      tcg_temp_free_i32(t0);
>  
>      /* Stop translation, this gives other CPUs a chance to run */
> -    gen_exception_nip(ctx, EXCP_HLT, ctx->base.pc_next);
> +    gen_exception_nip(ctx, EXCP_INTERRUPT, ctx->base.pc_next);

I don't see how this change relates to the rest.

>  }
>  #endif /* defined(TARGET_PPC64) */
>  
> @@ -1662,7 +1662,9 @@ static void gen_or(DisasContext *ctx)
>           * than no-op, e.g., miso(rs=26), yield(27), mdoio(29), mdoom(30),
>           * and all currently undefined.
>           */
> -        gen_pause(ctx);
> +        if (!mttcg_enabled) {
> +            gen_pause(ctx);
> +        }
>  #endif
>  #endif
>      }

-- 
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