From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756771AbbEUQne (ORCPT ); Thu, 21 May 2015 12:43:34 -0400 Received: from mail-la0-f49.google.com ([209.85.215.49]:34622 "EHLO mail-la0-f49.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756698AbbEUQn1 (ORCPT ); Thu, 21 May 2015 12:43:27 -0400 MIME-Version: 1.0 In-Reply-To: <555E0A93.2020803@plumgrid.com> References: <1432079946-9878-1-git-send-email-ast@plumgrid.com> <1432079946-9878-2-git-send-email-ast@plumgrid.com> <555BD2E4.5050608@plumgrid.com> <555E0A93.2020803@plumgrid.com> From: Andy Lutomirski Date: Thu, 21 May 2015 09:43:05 -0700 Message-ID: Subject: Re: [PATCH net-next 1/4] bpf: allow bpf programs to tail-call other bpf programs To: Alexei Starovoitov Cc: "David S. Miller" , Ingo Molnar , Daniel Borkmann , Michael Holzheu , Zi Shen Lim , Linux API , Network Development , "linux-kernel@vger.kernel.org" Content-Type: text/plain; charset=UTF-8 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Thu, May 21, 2015 at 9:40 AM, Alexei Starovoitov wrote: > On 5/21/15 9:20 AM, Andy Lutomirski wrote: >> >> >> What I mean is: why do we need the interface to be "look up this index >> in an array and just to what it references" as a single atomic >> instruction? Can't we break it down into first "look up this index in >> an array" and then "do this tail call"? > > > I've actually considered to do this split and do first part as map lookup > and 2nd as 'tail call to this ptr' insn, but it turned out to be > painful: verifier gets more complicated, ctx pointer needs to kept > somewhere, JITs need to special case two things instead of one. > Also I couldn't see a use case for exposing program pointer to the > program itself. I've explored this path only because it felt more > traditional 'goto *ptr' like, but adding new PTR_TO_PROG type to > verifier looked wasteful. At some point, I think that it would be worth extending the verifier to support more general non-integral scalar types. "Pointer to tail-call target" would be just one of them. "Pointer to skb" might be nice as a real first-class scalar type that lives in a register as opposed to just being magic typed context. We'd still need some way to stick fds into a map, but that's not really the verifier's problem. --Andy