[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <CAMEtUuwuQzYknOm4qqYFa2By=zCOpkk4_zp=_2BuPavg-rPc-A@mail.gmail.com>
Date: Thu, 10 Jul 2014 11:51:08 +0200
From: Alexei Starovoitov <ast@...mgrid.com>
To: Will Deacon <will.deacon@....com>
Cc: Zi Shen Lim <zlim.lnx@...il.com>,
Catalin Marinas <Catalin.Marinas@....com>,
"David S. Miller" <davem@...emloft.net>,
Daniel Borkmann <dborkman@...hat.com>,
Chema Gonzalez <chema@...gle.com>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
"linux-arm-kernel@...ts.infradead.org"
<linux-arm-kernel@...ts.infradead.org>,
"netdev@...r.kernel.org" <netdev@...r.kernel.org>
Subject: Re: [PATCH RFCv2] arm64: eBPF JIT compiler
On Wed, Jul 9, 2014 at 3:00 PM, Will Deacon <will.deacon@....com> wrote:
> On Tue, Jul 08, 2014 at 08:06:53AM +0100, Zi Shen Lim wrote:
>>
>> 1. Implement remaining classes of eBPF instructions: ST|MEM, STX|XADD
>> which currently do not have corresponding test cases in test_bpf.
>
> I can help out with atomics, if you need it. Are the memory barrier
> semantics well-defined for eBPF?
There are no barrier or cmpxchg instructions in eBPF, since such use case
doesn't exist yet. There is only xadd that is equivalent to atomic_add
which can be JITed as exclusive load/store on arm64.
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists