Re: [PATCH v10 12/12] bpf: add sample for xdp forwarding and rewrite

[Tom Herbert <tom@herbertland.com>]

On Tue, Jul 19, 2016 at 12:16 PM, Brenden Blanco <bblanco@plumgrid.com> wrote:
> Add a sample that rewrites and forwards packets out on the same
> interface. Observed single core forwarding performance of ~10Mpps.
>
> Since the mlx4 driver under test recycles every single packet page, the
> perf output shows almost exclusively just the ring management and bpf
> program work. Slowdowns are likely occurring due to cache misses.
>
> Signed-off-by: Brenden Blanco <bblanco@plumgrid.com>
> ---
>  samples/bpf/Makefile    |   5 +++
>  samples/bpf/xdp2_kern.c | 114 ++++++++++++++++++++++++++++++++++++++++++++++++
>  2 files changed, 119 insertions(+)
>  create mode 100644 samples/bpf/xdp2_kern.c
>
> diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
> index 0e4ab3a..d2d2b35 100644
> --- a/samples/bpf/Makefile
> +++ b/samples/bpf/Makefile
> @@ -22,6 +22,7 @@ hostprogs-y += map_perf_test
>  hostprogs-y += test_overhead
>  hostprogs-y += test_cgrp2_array_pin
>  hostprogs-y += xdp1
> +hostprogs-y += xdp2
>
>  test_verifier-objs := test_verifier.o libbpf.o
>  test_maps-objs := test_maps.o libbpf.o
> @@ -44,6 +45,8 @@ map_perf_test-objs := bpf_load.o libbpf.o map_perf_test_user.o
>  test_overhead-objs := bpf_load.o libbpf.o test_overhead_user.o
>  test_cgrp2_array_pin-objs := libbpf.o test_cgrp2_array_pin.o
>  xdp1-objs := bpf_load.o libbpf.o xdp1_user.o
> +# reuse xdp1 source intentionally
> +xdp2-objs := bpf_load.o libbpf.o xdp1_user.o
>
>  # Tell kbuild to always build the programs
>  always := $(hostprogs-y)
> @@ -67,6 +70,7 @@ always += test_overhead_kprobe_kern.o
>  always += parse_varlen.o parse_simple.o parse_ldabs.o
>  always += test_cgrp2_tc_kern.o
>  always += xdp1_kern.o
> +always += xdp2_kern.o
>
>  HOSTCFLAGS += -I$(objtree)/usr/include
>
> @@ -88,6 +92,7 @@ HOSTLOADLIBES_spintest += -lelf
>  HOSTLOADLIBES_map_perf_test += -lelf -lrt
>  HOSTLOADLIBES_test_overhead += -lelf -lrt
>  HOSTLOADLIBES_xdp1 += -lelf
> +HOSTLOADLIBES_xdp2 += -lelf
>
>  # Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline:
>  #  make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang
> diff --git a/samples/bpf/xdp2_kern.c b/samples/bpf/xdp2_kern.c
> new file mode 100644
> index 0000000..38fe7e1
> --- /dev/null
> +++ b/samples/bpf/xdp2_kern.c
> @@ -0,0 +1,114 @@
> +/* Copyright (c) 2016 PLUMgrid
> + *
> + * This program is free software; you can redistribute it and/or
> + * modify it under the terms of version 2 of the GNU General Public
> + * License as published by the Free Software Foundation.
> + */
> +#define KBUILD_MODNAME "foo"
> +#include <uapi/linux/bpf.h>
> +#include <linux/in.h>
> +#include <linux/if_ether.h>
> +#include <linux/if_packet.h>
> +#include <linux/if_vlan.h>
> +#include <linux/ip.h>
> +#include <linux/ipv6.h>
> +#include "bpf_helpers.h"
> +
> +struct bpf_map_def SEC("maps") dropcnt = {
> +       .type = BPF_MAP_TYPE_PERCPU_ARRAY,
> +       .key_size = sizeof(u32),
> +       .value_size = sizeof(long),
> +       .max_entries = 256,
> +};
> +
> +static void swap_src_dst_mac(void *data)
> +{
> +       unsigned short *p = data;
> +       unsigned short dst[3];
> +
> +       dst[0] = p[0];
> +       dst[1] = p[1];
> +       dst[2] = p[2];
> +       p[0] = p[3];
> +       p[1] = p[4];
> +       p[2] = p[5];
> +       p[3] = dst[0];
> +       p[4] = dst[1];
> +       p[5] = dst[2];
> +}
> +
> +static int parse_ipv4(void *data, u64 nh_off, void *data_end)
> +{
> +       struct iphdr *iph = data + nh_off;
> +
> +       if (iph + 1 > data_end)
> +               return 0;
> +       return iph->protocol;
> +}
> +
> +static int parse_ipv6(void *data, u64 nh_off, void *data_end)
> +{
> +       struct ipv6hdr *ip6h = data + nh_off;
> +
> +       if (ip6h + 1 > data_end)
> +               return 0;
> +       return ip6h->nexthdr;
> +}
> +
> +SEC("xdp1")
> +int xdp_prog1(struct xdp_md *ctx)
> +{
> +       void *data_end = (void *)(long)ctx->data_end;
> +       void *data = (void *)(long)ctx->data;

Brendan,

It seems that the cast to long here is done because data_end and data
are u32s in xdp_md. So the effect is that we are upcasting a
thirty-bit integer into a sixty-four bit pointer (in fact without the
cast we see compiler warnings). I don't understand how this can be
correct. Can you shed some light on this?

Thanks,
Tom

> +       struct ethhdr *eth = data;
> +       int rc = XDP_DROP;
> +       long *value;
> +       u16 h_proto;
> +       u64 nh_off;
> +       u32 index;
> +
> +       nh_off = sizeof(*eth);
> +       if (data + nh_off > data_end)
> +               return rc;
> +
> +       h_proto = eth->h_proto;
> +
> +       if (h_proto == htons(ETH_P_8021Q) || h_proto == htons(ETH_P_8021AD)) {
> +               struct vlan_hdr *vhdr;
> +
> +               vhdr = data + nh_off;
> +               nh_off += sizeof(struct vlan_hdr);
> +               if (data + nh_off > data_end)
> +                       return rc;
> +               h_proto = vhdr->h_vlan_encapsulated_proto;
> +       }
> +       if (h_proto == htons(ETH_P_8021Q) || h_proto == htons(ETH_P_8021AD)) {
> +               struct vlan_hdr *vhdr;
> +
> +               vhdr = data + nh_off;
> +               nh_off += sizeof(struct vlan_hdr);
> +               if (data + nh_off > data_end)
> +                       return rc;
> +               h_proto = vhdr->h_vlan_encapsulated_proto;
> +       }
> +
> +       if (h_proto == htons(ETH_P_IP))
> +               index = parse_ipv4(data, nh_off, data_end);
> +       else if (h_proto == htons(ETH_P_IPV6))
> +               index = parse_ipv6(data, nh_off, data_end);
> +       else
> +               index = 0;
> +
> +       value = bpf_map_lookup_elem(&dropcnt, &index);
> +       if (value)
> +               *value += 1;
> +
> +       if (index == 17) {
> +               swap_src_dst_mac(data);
> +               rc = XDP_TX;
> +       }
> +
> +       return rc;
> +}
> +
> +char _license[] SEC("license") = "GPL";
> --
> 2.8.2
>