Add sample for adding simple drop program to link
Add a sample program that only drops packets at the BPF_PROG_TYPE_XDP_RX
hook of a link. With the drop-only program, observed single core rate is
~20Mpps.
Other tests were run, for instance without the dropcnt increment or
without reading from the packet header, the packet rate was mostly
unchanged.
$ perf record -a samples/bpf/xdp1 $(</sys/class/net/eth0/ifindex)
proto 17: 20403027 drops/s
./pktgen_sample03_burst_single_flow.sh -i $DEV -d $IP -m $MAC -t 4
Running... ctrl^C to stop
Device: eth4@0
Result: OK: 11791017(c11788327+d2689) usec, 59622913 (60byte,0frags)
5056638pps 2427Mb/sec (2427186240bps) errors: 0
Device: eth4@1
Result: OK: 11791012(c11787906+d3106) usec, 60526944 (60byte,0frags)
5133311pps 2463Mb/sec (2463989280bps) errors: 0
Device: eth4@2
Result: OK: 11791019(c11788249+d2769) usec, 59868091 (60byte,0frags)
5077431pps 2437Mb/sec (2437166880bps) errors: 0
Device: eth4@3
Result: OK: 11795039(c11792403+d2636) usec, 59483181 (60byte,0frags)
5043067pps 2420Mb/sec (2420672160bps) errors: 0
perf report --no-children:
26.05% ksoftirqd/0 [mlx4_en] [k] mlx4_en_process_rx_cq
17.84% ksoftirqd/0 [mlx4_en] [k] mlx4_en_alloc_frags
5.52% ksoftirqd/0 [mlx4_en] [k] mlx4_en_free_frag
4.90% swapper [kernel.vmlinux] [k] poll_idle
4.14% ksoftirqd/0 [kernel.vmlinux] [k] get_page_from_freelist
2.78% ksoftirqd/0 [kernel.vmlinux] [k] __free_pages_ok
2.57% ksoftirqd/0 [kernel.vmlinux] [k] bpf_map_lookup_elem
2.51% swapper [mlx4_en] [k] mlx4_en_process_rx_cq
1.94% ksoftirqd/0 [kernel.vmlinux] [k] percpu_array_map_lookup_elem
1.45% swapper [mlx4_en] [k] mlx4_en_alloc_frags
1.35% ksoftirqd/0 [kernel.vmlinux] [k] free_one_page
1.33% swapper [kernel.vmlinux] [k] intel_idle
1.04% ksoftirqd/0 [mlx4_en] [k] 0x000000000001c5c5
0.96% ksoftirqd/0 [mlx4_en] [k] 0x000000000001c58d
0.93% ksoftirqd/0 [mlx4_en] [k] 0x000000000001c6ee
0.92% ksoftirqd/0 [mlx4_en] [k] 0x000000000001c6b9
0.89% ksoftirqd/0 [kernel.vmlinux] [k] __alloc_pages_nodemask
0.83% ksoftirqd/0 [mlx4_en] [k] 0x000000000001c686
0.83% ksoftirqd/0 [mlx4_en] [k] 0x000000000001c5d5
0.78% ksoftirqd/0 [mlx4_en] [k] mlx4_alloc_pages.isra.23
0.77% ksoftirqd/0 [mlx4_en] [k] 0x000000000001c5b4
0.77% ksoftirqd/0 [kernel.vmlinux] [k] net_rx_action
machine specs:
receiver - Intel E5-1630 v3 @ 3.70GHz
sender - Intel E5645 @ 2.40GHz
Mellanox ConnectX-3 @40G
Signed-off-by: Brenden Blanco <bblanco@plumgrid.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/samples/bpf/xdp1_kern.c b/samples/bpf/xdp1_kern.c
new file mode 100644
index 0000000..e7dd8ac
--- /dev/null
+++ b/samples/bpf/xdp1_kern.c
@@ -0,0 +1,93 @@
+/* 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 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;
+ 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;
+
+ return rc;
+}
+
+char _license[] SEC("license") = "GPL";