[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CADasFoCrWPg3=kchWzJX5vDeymV9wiL7GnPxWDg4rQETyF5TeA@mail.gmail.com>
Date: Tue, 25 Jun 2019 13:26:21 -0700
From: Luke Nelson <lukenels@...washington.edu>
To: Jiong Wang <jiong.wang@...ronome.com>
Cc: Luke Nelson <luke.r.nels@...il.com>, Xi Wang <xi.wang@...il.com>,
Palmer Dabbelt <palmer@...ive.com>,
Albert Ou <aou@...s.berkeley.edu>,
Alexei Starovoitov <ast@...nel.org>,
Daniel Borkmann <daniel@...earbox.net>,
Martin KaFai Lau <kafai@...com>,
Song Liu <songliubraving@...com>, Yonghong Song <yhs@...com>,
Björn Töpel <bjorn.topel@...il.com>,
linux-riscv@...ts.infradead.org, linux-kernel@...r.kernel.org,
netdev@...r.kernel.org, bpf@...r.kernel.org
Subject: Re: [RFC PATCH bpf-next] RV32G eBPF JIT
On Mon, Jun 24, 2019 at 9:45 AM Jiong Wang <jiong.wang@...ronome.com> wrote:
>
> Looks to me 32-bit optimization is not enabled.
>
> If you define bpf_jit_needs_zext to return true
>
> bool bpf_jit_needs_zext(void)
> {
> return true;
> }
>
> Then you don't need to zero high 32-bit when writing 32-bit sub-register
> and you just need to implement the explicit zero extension insn which is a
> special variant of BPF_MOV. This can save quite a few instructions. RV64
> and arches like arm has implemented this, please search
> "aux->verifier_zext".
>
> And there is a doc for this optimization:
>
> https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git/tree/Documentation/bpf/bpf_design_QA.rst#n168
Thanks for the pointer. I'll add this optimization before sending out
an updated version of the patch.
– Luke
Powered by blists - more mailing lists