From mboxrd@z Thu Jan 1 00:00:00 1970 From: Toke =?utf-8?Q?H=C3=B8iland-J=C3=B8rgensen?= Subject: Re: [PATCH] samples/bpf: Add xdp_sample_pkts example Date: Mon, 04 Jun 2018 15:02:32 +0200 Message-ID: <87r2lm1z87.fsf@toke.dk> References: <20180530164524.21760-1-toke@toke.dk> <87a7sgcg7i.fsf@toke.dk> <672f2d99-f44d-7605-7c07-e9b6315f0bcd@iogearbox.net> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable Cc: Networking To: Daniel Borkmann , Song Liu Return-path: Received: from mail.toke.dk ([52.28.52.200]:34909 "EHLO mail.toke.dk" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752680AbeFDNCf (ORCPT ); Mon, 4 Jun 2018 09:02:35 -0400 In-Reply-To: <672f2d99-f44d-7605-7c07-e9b6315f0bcd@iogearbox.net> Sender: netdev-owner@vger.kernel.org List-ID: Daniel Borkmann writes: > On 06/02/2018 06:22 AM, Daniel Borkmann wrote: >> On 05/31/2018 11:44 AM, Toke H=C3=B8iland-J=C3=B8rgensen wrote: >>> Song Liu writes: >>> >>>> On Wed, May 30, 2018 at 9:45 AM, Toke H=C3=B8iland-J=C3=B8rgensen wrote: >>>>> This adds an example program showing how to sample packets from XDP u= sing >>>>> the perf event buffer. The example userspace program just prints the >>>>> ethernet header for every packet sampled. >>>>> >>>>> Most of the userspace code is borrowed from other examples, most nota= bly >>>>> trace_output. >>>>> >>>>> Note that the example only works when everything runs on CPU0; so >>>>> suitable smp_affinity needs to be set on the device. Some drivers seem >>>>> to reset smp_affinity when loading an XDP program, so it may be >>>>> necessary to change it after starting the example userspace program. >>>> >>>> Why does this only works when everything runs on CPU0? Is this >>>> something we can improve? >>> >>> Yeah, good question. Basically, the call from XDP to >>> bpf_perf_event_output() will fail with -EOPNOTSUPP. I tracked this down >>> to this if statement in __bpf_perf_event_output() in bpf_trace.c: >>> >>>> if (unlikely(event->oncpu !=3D cpu)) >>>> return -EOPNOTSUPP; >>> >>> I *think* that the way to fix this is for the userspace program to open >>> a perf file descriptor for each CPU in the system and poll all of them, >>> in which case the XDP program can pass the BPF_F_CURRENT_CPU flag to >>> access the right one. >> That is correct, you need one perf fd per cpu, and map them accordingly >> into the map slots when you use BPF_F_CURRENT_CPU. > > Given this is a sample that users are likely to copy from, I think it wou= ld > be great if you could fix this up so you can just pass in BPF_F_CURRENT_C= PU > eventually. Thanks for working on this, Toke! You're welcome! And yup, I was planning to. I'll need to add a new function to the trace helpers that can poll more than one fd; just haven't gotten around to it yet. :) -Toke