samples/bpf: Add example of ipv4 and ipv6 forwarding in XDP

Simple example of fast-path forwarding. It has a serious flaw
in not verifying the egress device index supports XDP forwarding.
If the egress device does not packets are dropped.

Take this only as a simple example of fast-path forwarding.

Signed-off-by: David Ahern <dsahern@gmail.com>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

4 files changed, 258 insertions, 0 deletions

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 8e0c7fb..28513d6 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -46,6 +46,7 @@ hostprogs-y += syscall_tp
 hostprogs-y += cpustat
 hostprogs-y += xdp_adjust_tail
 hostprogs-y += xdpsock
+hostprogs-y += xdp_fwd
 
 # Libbpf dependencies
 LIBBPF := ../../tools/lib/bpf/bpf.o ../../tools/lib/bpf/nlattr.o
@@ -100,6 +101,7 @@ syscall_tp-objs := bpf_load.o $(LIBBPF) syscall_tp_user.o
 cpustat-objs := bpf_load.o $(LIBBPF) cpustat_user.o
 xdp_adjust_tail-objs := bpf_load.o $(LIBBPF) xdp_adjust_tail_user.o
 xdpsock-objs := bpf_load.o $(LIBBPF) xdpsock_user.o
+xdp_fwd-objs := bpf_load.o $(LIBBPF) xdp_fwd_user.o
 
 # Tell kbuild to always build the programs
 always := $(hostprogs-y)
@@ -154,6 +156,7 @@ always += syscall_tp_kern.o
 always += cpustat_kern.o
 always += xdp_adjust_tail_kern.o
 always += xdpsock_kern.o
+always += xdp_fwd_kern.o
 
 HOSTCFLAGS += -I$(objtree)/usr/include
 HOSTCFLAGS += -I$(srctree)/tools/lib/
@@ -201,6 +204,7 @@ HOSTLOADLIBES_syscall_tp += -lelf
 HOSTLOADLIBES_cpustat += -lelf
 HOSTLOADLIBES_xdp_adjust_tail += -lelf
 HOSTLOADLIBES_xdpsock += -lelf -pthread
+HOSTLOADLIBES_xdp_fwd += -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/xdp_fwd_kern.c b/samples/bpf/xdp_fwd_kern.c
new file mode 100644
index 0000000..cdf4fc3
--- /dev/null
+++ b/samples/bpf/xdp_fwd_kern.c
@@ -0,0 +1,115 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2017-18 David Ahern <dsahern@gmail.com>
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#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"
+
+#define IPV6_FLOWINFO_MASK              cpu_to_be32(0x0FFFFFFF)
+
+struct bpf_map_def SEC("maps") tx_port = {
+	.type = BPF_MAP_TYPE_DEVMAP,
+	.key_size = sizeof(int),
+	.value_size = sizeof(int),
+	.max_entries = 64,
+};
+
+static __always_inline int xdp_fwd_flags(struct xdp_md *ctx, u32 flags)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+	struct bpf_fib_lookup fib_params;
+	struct ethhdr *eth = data;
+	int out_index;
+	u16 h_proto;
+	u64 nh_off;
+
+	nh_off = sizeof(*eth);
+	if (data + nh_off > data_end)
+		return XDP_DROP;
+
+	__builtin_memset(&fib_params, 0, sizeof(fib_params));
+
+	h_proto = eth->h_proto;
+	if (h_proto == htons(ETH_P_IP)) {
+		struct iphdr *iph = data + nh_off;
+
+		if (iph + 1 > data_end)
+			return XDP_DROP;
+
+		fib_params.family	= AF_INET;
+		fib_params.tos		= iph->tos;
+		fib_params.l4_protocol	= iph->protocol;
+		fib_params.sport	= 0;
+		fib_params.dport	= 0;
+		fib_params.tot_len	= ntohs(iph->tot_len);
+		fib_params.ipv4_src	= iph->saddr;
+		fib_params.ipv4_dst	= iph->daddr;
+	} else if (h_proto == htons(ETH_P_IPV6)) {
+		struct in6_addr *src = (struct in6_addr *) fib_params.ipv6_src;
+		struct in6_addr *dst = (struct in6_addr *) fib_params.ipv6_dst;
+		struct ipv6hdr *iph = data + nh_off;
+
+		if (iph + 1 > data_end)
+			return XDP_DROP;
+
+		fib_params.family	= AF_INET6;
+		fib_params.flowlabel	= *(__be32 *)iph & IPV6_FLOWINFO_MASK;
+		fib_params.l4_protocol	= iph->nexthdr;
+		fib_params.sport	= 0;
+		fib_params.dport	= 0;
+		fib_params.tot_len	= ntohs(iph->payload_len);
+		*src			= iph->saddr;
+		*dst			= iph->daddr;
+	} else {
+		return XDP_PASS;
+	}
+
+	fib_params.ifindex = ctx->ingress_ifindex;
+
+	out_index = bpf_fib_lookup(ctx, &fib_params, sizeof(fib_params), flags);
+
+	/* verify egress index has xdp support
+	 * TO-DO bpf_map_lookup_elem(&tx_port, &key) fails with
+	 *       cannot pass map_type 14 into func bpf_map_lookup_elem#1:
+	 * NOTE: without verification that egress index supports XDP
+	 *       forwarding packets are dropped.
+	 */
+	if (out_index > 0) {
+		memcpy(eth->h_dest, fib_params.dmac, ETH_ALEN);
+		memcpy(eth->h_source, fib_params.smac, ETH_ALEN);
+		return bpf_redirect_map(&tx_port, out_index, 0);
+	}
+
+	return XDP_PASS;
+}
+
+SEC("xdp_fwd")
+int xdp_fwd_prog(struct xdp_md *ctx)
+{
+	return xdp_fwd_flags(ctx, 0);
+}
+
+SEC("xdp_fwd_direct")
+int xdp_fwd_direct_prog(struct xdp_md *ctx)
+{
+	return xdp_fwd_flags(ctx, BPF_FIB_LOOKUP_DIRECT);
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/samples/bpf/xdp_fwd_user.c b/samples/bpf/xdp_fwd_user.c
new file mode 100644
index 0000000..9c6606f
--- /dev/null
+++ b/samples/bpf/xdp_fwd_user.c
@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2017-18 David Ahern <dsahern@gmail.com>
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/bpf.h>
+#include <linux/if_link.h>
+#include <linux/limits.h>
+#include <net/if.h>
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <string.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <libgen.h>
+
+#include "bpf_load.h"
+#include "bpf_util.h"
+#include "libbpf.h"
+
+
+static int do_attach(int idx, int fd, const char *name)
+{
+	int err;
+
+	err = bpf_set_link_xdp_fd(idx, fd, 0);
+	if (err < 0)
+		printf("ERROR: failed to attach program to %s\n", name);
+
+	return err;
+}
+
+static int do_detach(int idx, const char *name)
+{
+	int err;
+
+	err = bpf_set_link_xdp_fd(idx, -1, 0);
+	if (err < 0)
+		printf("ERROR: failed to detach program from %s\n", name);
+
+	return err;
+}
+
+static void usage(const char *prog)
+{
+	fprintf(stderr,
+		"usage: %s [OPTS] interface-list\n"
+		"\nOPTS:\n"
+		"    -d    detach program\n"
+		"    -D    direct table lookups (skip fib rules)\n",
+		prog);
+}
+
+int main(int argc, char **argv)
+{
+	char filename[PATH_MAX];
+	int opt, i, idx, err;
+	int prog_id = 0;
+	int attach = 1;
+	int ret = 0;
+
+	while ((opt = getopt(argc, argv, ":dD")) != -1) {
+		switch (opt) {
+		case 'd':
+			attach = 0;
+			break;
+		case 'D':
+			prog_id = 1;
+			break;
+		default:
+			usage(basename(argv[0]));
+			return 1;
+		}
+	}
+
+	if (optind == argc) {
+		usage(basename(argv[0]));
+		return 1;
+	}
+
+	if (attach) {
+		snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+		if (access(filename, O_RDONLY) < 0) {
+			printf("error accessing file %s: %s\n",
+				filename, strerror(errno));
+			return 1;
+		}
+
+		if (load_bpf_file(filename)) {
+			printf("%s", bpf_log_buf);
+			return 1;
+		}
+
+		if (!prog_fd[prog_id]) {
+			printf("load_bpf_file: %s\n", strerror(errno));
+			return 1;
+		}
+	}
+	if (attach) {
+		for (i = 1; i < 64; ++i)
+			bpf_map_update_elem(map_fd[0], &i, &i, 0);
+	}
+
+	for (i = optind; i < argc; ++i) {
+		idx = if_nametoindex(argv[i]);
+		if (!idx)
+			idx = strtoul(argv[i], NULL, 0);
+
+		if (!idx) {
+			fprintf(stderr, "Invalid arg\n");
+			return 1;
+		}
+		if (!attach) {
+			err = do_detach(idx, argv[i]);
+			if (err)
+				ret = err;
+		} else {
+			err = do_attach(idx, prog_fd[prog_id], argv[i]);
+			if (err)
+				ret = err;
+		}
+	}
+
+	return ret;
+}
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 265f8e0..2375d06 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -103,6 +103,9 @@ static int (*bpf_skb_get_xfrm_state)(void *ctx, int index, void *state,
 	(void *) BPF_FUNC_skb_get_xfrm_state;
 static int (*bpf_get_stack)(void *ctx, void *buf, int size, int flags) =
 	(void *) BPF_FUNC_get_stack;
+static int (*bpf_fib_lookup)(void *ctx, struct bpf_fib_lookup *params,
+			     int plen, __u32 flags) =
+	(void *) BPF_FUNC_fib_lookup;
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions