[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <87zhnagati.fsf@netronome.com>
Date: Sat, 25 May 2019 10:09:13 +0100
From: Jiong Wang <jiong.wang@...ronome.com>
To: Alexei Starovoitov <alexei.starovoitov@...il.com>
Cc: Jiong Wang <jiong.wang@...ronome.com>, daniel@...earbox.net,
bpf@...r.kernel.org, netdev@...r.kernel.org,
oss-drivers@...ronome.com, davem@...emloft.net,
paul.burton@...s.com, udknight@...il.com, zlim.lnx@...il.com,
illusionist.neo@...il.com, naveen.n.rao@...ux.ibm.com,
sandipan@...ux.ibm.com, schwidefsky@...ibm.com,
heiko.carstens@...ibm.com, jakub.kicinski@...ronome.com
Subject: Re: [PATCH v9 bpf-next 00/17] bpf: eliminate zero extensions for sub-register writes
Alexei Starovoitov writes:
> On Fri, May 24, 2019 at 11:25:11PM +0100, Jiong Wang wrote:
>> v9:
>> - Split patch 5 in v8.
>> make bpf uapi header file sync a separate patch. (Alexei)
>
> 9th time's a charm? ;)
Yup :), it's all good things and helped us reaching a solution that fits
verifier's existing infra.
> Applied.
> Thanks a lot for all the hard work.
> It's a great milestone.
Thanks. And I guess the answer to the question:
"Q: BPF 32-bit subregister requirements"
inside Documentation/bpf/bpf_design_QA.rst now could be updated to
mention LLVM and JIT back-ends 32-bit supports, will send out an update on
this.
> Please follow up with an optimization for bpf_patch_insn_data()
> to make it scaleable and undo that workaround in scale tests.
Sure, will do.
Regards,
Jiong
Powered by blists - more mailing lists