From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S966357AbcIZJAq (ORCPT ); Mon, 26 Sep 2016 05:00:46 -0400 Received: from www62.your-server.de ([213.133.104.62]:45057 "EHLO www62.your-server.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S965449AbcIZJAn (ORCPT ); Mon, 26 Sep 2016 05:00:43 -0400 Message-ID: <57E8E3B4.5030606@iogearbox.net> Date: Mon, 26 Sep 2016 11:00:36 +0200 From: Daniel Borkmann User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:31.0) Gecko/20100101 Thunderbird/31.7.0 MIME-Version: 1.0 To: "Naveen N. Rao" , Alexei Starovoitov CC: Ananth N Mavinakayanahalli , Alexei Starovoitov , netdev@vger.kernel.org, linux-kernel@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, "David S. Miller" Subject: Re: [PATCH 2/3] bpf powerpc: implement support for tail calls References: <40b65ab2bb3a48837ab047a70887de3ccd70c56b.1474661927.git.naveen.n.rao@linux.vnet.ibm.com> <57E5ADD2.7090308@iogearbox.net> <20160924073025.GB48071@ast-mbp.thefacebook.com> <20160926085622.GG15470@naverao1-tp.localdomain> In-Reply-To: <20160926085622.GG15470@naverao1-tp.localdomain> Content-Type: text/plain; charset=windows-1252; format=flowed Content-Transfer-Encoding: 7bit X-Authenticated-Sender: daniel@iogearbox.net Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 09/26/2016 10:56 AM, Naveen N. Rao wrote: > On 2016/09/24 03:30AM, Alexei Starovoitov wrote: >> On Sat, Sep 24, 2016 at 12:33:54AM +0200, Daniel Borkmann wrote: >>> On 09/23/2016 10:35 PM, Naveen N. Rao wrote: >>>> Tail calls allow JIT'ed eBPF programs to call into other JIT'ed eBPF >>>> programs. This can be achieved either by: >>>> (1) retaining the stack setup by the first eBPF program and having all >>>> subsequent eBPF programs re-using it, or, >>>> (2) by unwinding/tearing down the stack and having each eBPF program >>>> deal with its own stack as it sees fit. >>>> >>>> To ensure that this does not create loops, there is a limit to how many >>>> tail calls can be done (currently 32). This requires the JIT'ed code to >>>> maintain a count of the number of tail calls done so far. >>>> >>>> Approach (1) is simple, but requires every eBPF program to have (almost) >>>> the same prologue/epilogue, regardless of whether they need it. This is >>>> inefficient for small eBPF programs which may not sometimes need a >>>> prologue at all. As such, to minimize impact of tail call >>>> implementation, we use approach (2) here which needs each eBPF program >>>> in the chain to use its own prologue/epilogue. This is not ideal when >>>> many tail calls are involved and when all the eBPF programs in the chain >>>> have similar prologue/epilogue. However, the impact is restricted to >>>> programs that do tail calls. Individual eBPF programs are not affected. >>>> >>>> We maintain the tail call count in a fixed location on the stack and >>>> updated tail call count values are passed in through this. The very >>>> first eBPF program in a chain sets this up to 0 (the first 2 >>>> instructions). Subsequent tail calls skip the first two eBPF JIT >>>> instructions to maintain the count. For programs that don't do tail >>>> calls themselves, the first two instructions are NOPs. >>>> >>>> Signed-off-by: Naveen N. Rao >>> >>> Thanks for adding support, Naveen, that's really great! I think 2) seems >>> fine as well in this context as prologue size can vary quite a bit here, >>> and depending on program types likelihood of tail call usage as well (but >>> I wouldn't expect deep nesting). Thanks a lot! >> >> Great stuff. In this circumstances approach 2 makes sense to me as well. > > Alexie, Daniel, > Thanks for the quick review! The patches would go via Michael's tree (same way as with the JIT itself in the past), right?