[Top][All Lists]

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Qemu-riscv] [Qemu-devel] [PATCH 0/2] target/riscv: Bugfixes found i

From: Richard Henderson
Subject: Re: [Qemu-riscv] [Qemu-devel] [PATCH 0/2] target/riscv: Bugfixes found in decodetree conversion
Date: Fri, 9 Nov 2018 07:14:24 +0100
User-agent: Mozilla/5.0 (X11; Linux x86_64; rv:60.0) Gecko/20100101 Thunderbird/60.2.1

On 11/8/18 8:12 PM, Palmer Dabbelt wrote:
> * We don't take advantage of the ordering bits on fences, which could allow us
>  to emit less conservative fences.  This would presumably increase  
> performance.


> * We treat fences as NOPs under "#ifndef CONFIG_USER_ONLY", which is a bug.

Ah yes, I'd forgotten this one.  This is a bug, in that multi-threaded user
programs do not get the memory ordering that they requested.

Hard to see, obviously, since the emulator has its own memory operations,
barriers, and locks.  But once we have a lot of the hot path of the user
program compiled, there's a lot less of that.

>     case OPC_RISC_FENCE:
>         if (ctx->opcode & 0x1000) {
>             /* FENCE_I is a no-op in QEMU,
>              * however we need to end the translation block */
> @@ -1777,7 +1776,6 @@ static void decode_RV32_64G(CPURISCVState *env,
> DisasContext *ctx)
>             /* FENCE is a full memory barrier. */
>             tcg_gen_mb(TCG_MO_ALL | TCG_BAR_SC);
>         }
> -#endif
>         break;

Yes, this is minimally correct.


reply via email to

[Prev in Thread] Current Thread [Next in Thread]