From: Jesper Dangaard Brouer <brouer@redhat.com>
To: Lorenzo Bianconi <lorenzo@kernel.org>
Cc: bpf@vger.kernel.org, netdev@vger.kernel.org, davem@davemloft.net,
ast@kernel.org, daniel@iogearbox.net, toke@redhat.com,
lorenzo.bianconi@redhat.com, dsahern@kernel.org,
brouer@redhat.com
Subject: Re: [PATCH v2 bpf-next 4/8] bpf: cpumap: add the possibility to attach an eBPF program to cpumap
Date: Mon, 22 Jun 2020 11:48:37 +0200 [thread overview]
Message-ID: <20200622114837.278adefa@carbon> (raw)
In-Reply-To: <734113565894cb8447d1526e6a93eaf6ae994c2d.1592606391.git.lorenzo@kernel.org>
On Sat, 20 Jun 2020 00:57:20 +0200
Lorenzo Bianconi <lorenzo@kernel.org> wrote:
> +static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
> + void **xdp_frames, int n,
> + struct xdp_cpumap_stats *stats)
> +{
> + struct xdp_rxq_info rxq;
I do think we can merge this code as-is (and I actually re-factored this
code offlist), but I have some optimizations I would like to try out.
E.g. as I've tried to explain over IRC, it will be possible to avoid
having to reconstruct xdp_rxq_info here, as we can use the
expected_attach_type and remap the BPF instructions to use info from
xdp_frame. I want to benchmark it first, to see if it is worth it (we
will only save 2 store operations in a likely cache-hot area).
> + struct bpf_prog *prog;
> + struct xdp_buff xdp;
> + int i, nframes = 0;
> +
> + if (!rcpu->prog)
> + return n;
> +
> + xdp_set_return_frame_no_direct();
> + xdp.rxq = &rxq;
> +
> + rcu_read_lock();
> +
> + prog = READ_ONCE(rcpu->prog);
> + for (i = 0; i < n; i++) {
> + struct xdp_frame *xdpf = xdp_frames[i];
> + u32 act;
> + int err;
> +
> + rxq.dev = xdpf->dev_rx;
> + rxq.mem = xdpf->mem;
> + /* TODO: report queue_index to xdp_rxq_info */
> +
> + xdp_convert_frame_to_buff(xdpf, &xdp);
> +
> + act = bpf_prog_run_xdp(prog, &xdp);
> + switch (act) {
> + case XDP_PASS:
> + err = xdp_update_frame_from_buff(&xdp, xdpf);
> + if (err < 0) {
> + xdp_return_frame(xdpf);
> + stats->drop++;
> + } else {
> + xdp_frames[nframes++] = xdpf;
> + stats->pass++;
> + }
> + break;
> + default:
> + bpf_warn_invalid_xdp_action(act);
> + /* fallthrough */
> + case XDP_DROP:
> + xdp_return_frame(xdpf);
> + stats->drop++;
> + break;
> + }
> + }
> +
> + rcu_read_unlock();
> + xdp_clear_return_frame_no_direct();
> +
> + return nframes;
> +}
--
Best regards,
Jesper Dangaard Brouer
MSc.CS, Principal Kernel Engineer at Red Hat
LinkedIn: http://www.linkedin.com/in/brouer
next prev parent reply other threads:[~2020-06-22 9:48 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-06-19 22:57 [PATCH v2 bpf-next 0/8] introduce support for XDP programs in CPUMAP Lorenzo Bianconi
2020-06-19 22:57 ` [PATCH v2 bpf-next 1/8] net: Refactor xdp_convert_buff_to_frame Lorenzo Bianconi
2020-06-21 15:15 ` Jesper Dangaard Brouer
2020-06-22 11:48 ` Lorenzo Bianconi
2020-06-19 22:57 ` [PATCH v2 bpf-next 2/8] samples/bpf: xdp_redirect_cpu_user: do not update bpf maps in option loop Lorenzo Bianconi
2020-06-21 15:26 ` Jesper Dangaard Brouer
2020-06-19 22:57 ` [PATCH v2 bpf-next 3/8] cpumap: formalize map value as a named struct Lorenzo Bianconi
2020-06-22 9:33 ` Jesper Dangaard Brouer
2020-06-22 11:50 ` Lorenzo Bianconi
2020-06-19 22:57 ` [PATCH v2 bpf-next 4/8] bpf: cpumap: add the possibility to attach an eBPF program to cpumap Lorenzo Bianconi
2020-06-22 9:48 ` Jesper Dangaard Brouer [this message]
2020-06-23 14:56 ` Jesper Dangaard Brouer
2020-06-23 15:23 ` Jesper Dangaard Brouer
2020-06-19 22:57 ` [PATCH v2 bpf-next 5/8] bpf: cpumap: implement XDP_REDIRECT for eBPF programs attached to map entries Lorenzo Bianconi
2020-06-19 22:57 ` [PATCH v2 bpf-next 6/8] libbpf: add SEC name for xdp programs attached to CPUMAP Lorenzo Bianconi
2020-06-23 5:50 ` Andrii Nakryiko
2020-06-19 22:57 ` [PATCH v2 bpf-next 7/8] samples/bpf: xdp_redirect_cpu: load a eBPF program on cpumap Lorenzo Bianconi
2020-06-19 22:57 ` [PATCH v2 bpf-next 8/8] selftest: add tests for XDP programs in CPUMAP entries Lorenzo Bianconi
2020-06-23 5:55 ` Andrii Nakryiko
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200622114837.278adefa@carbon \
--to=brouer@redhat.com \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=dsahern@kernel.org \
--cc=lorenzo.bianconi@redhat.com \
--cc=lorenzo@kernel.org \
--cc=netdev@vger.kernel.org \
--cc=toke@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).