[PATCHv3 bpf-next] samples/bpf: add xdp program on egress for xdp_redirect_map

[Hangbin Liu <liuhangbin@gmail.com>]

This patch add a xdp program on egress to show that we can modify
the packet on egress. In this sample we will set the pkt's src
mac to egress's mac address. The xdp_prog will be attached when
-X option supplied.

Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
---
v3:
a) modify the src mac address based on egress mac

v2:
a) use pkt counter instead of IP ttl modification on egress program
b) make the egress program selectable by option -X
---
 samples/bpf/xdp_redirect_map_kern.c |  60 ++++++++++-
 samples/bpf/xdp_redirect_map_user.c | 153 ++++++++++++++++++++--------
 2 files changed, 168 insertions(+), 45 deletions(-)

diff --git a/samples/bpf/xdp_redirect_map_kern.c b/samples/bpf/xdp_redirect_map_kern.c
index 6489352ab7a4..6b2164722649 100644
--- a/samples/bpf/xdp_redirect_map_kern.c
+++ b/samples/bpf/xdp_redirect_map_kern.c
@@ -19,12 +19,22 @@
 #include <linux/ipv6.h>
 #include <bpf/bpf_helpers.h>
 
+/* The 2nd xdp prog on egress does not support skb mode, so we define two
+ * maps, tx_port_general and tx_port_native.
+ */
 struct {
 	__uint(type, BPF_MAP_TYPE_DEVMAP);
 	__uint(key_size, sizeof(int));
 	__uint(value_size, sizeof(int));
 	__uint(max_entries, 100);
-} tx_port SEC(".maps");
+} tx_port_general SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_DEVMAP);
+	__uint(key_size, sizeof(int));
+	__uint(value_size, sizeof(struct bpf_devmap_val));
+	__uint(max_entries, 100);
+} tx_port_native SEC(".maps");
 
 /* Count RX packets, as XDP bpf_prog doesn't get direct TX-success
  * feedback.  Redirect TX errors can be caught via a tracepoint.
@@ -36,6 +46,14 @@ struct {
 	__uint(max_entries, 1);
 } rxcnt SEC(".maps");
 
+/* map to stroe egress interface mac address */
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, u32);
+	__type(value, __be64);
+	__uint(max_entries, 1);
+} tx_mac SEC(".maps");
+
 static void swap_src_dst_mac(void *data)
 {
 	unsigned short *p = data;
@@ -52,17 +70,16 @@ static void swap_src_dst_mac(void *data)
 	p[5] = dst[2];
 }
 
-SEC("xdp_redirect_map")
-int xdp_redirect_map_prog(struct xdp_md *ctx)
+static int xdp_redirect_map(struct xdp_md *ctx, void *redirect_map)
 {
 	void *data_end = (void *)(long)ctx->data_end;
 	void *data = (void *)(long)ctx->data;
 	struct ethhdr *eth = data;
 	int rc = XDP_DROP;
-	int vport, port = 0, m = 0;
 	long *value;
 	u32 key = 0;
 	u64 nh_off;
+	int vport;
 
 	nh_off = sizeof(*eth);
 	if (data + nh_off > data_end)
@@ -79,7 +96,40 @@ int xdp_redirect_map_prog(struct xdp_md *ctx)
 	swap_src_dst_mac(data);
 
 	/* send packet out physical port */
-	return bpf_redirect_map(&tx_port, vport, 0);
+	return bpf_redirect_map(redirect_map, vport, 0);
+}
+
+SEC("xdp_redirect_general")
+int xdp_redirect_map_general(struct xdp_md *ctx)
+{
+	return xdp_redirect_map(ctx, &tx_port_general);
+}
+
+SEC("xdp_redirect_native")
+int xdp_redirect_map_native(struct xdp_md *ctx)
+{
+	return xdp_redirect_map(ctx, &tx_port_native);
+}
+
+SEC("xdp_devmap/map_prog")
+int xdp_redirect_map_egress(struct xdp_md *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+	struct ethhdr *eth = data;
+	__be64 *mac;
+	u32 key = 0;
+	u64 nh_off;
+
+	nh_off = sizeof(*eth);
+	if (data + nh_off > data_end)
+		return XDP_DROP;
+
+	mac = bpf_map_lookup_elem(&tx_mac, &key);
+	if (mac)
+		__builtin_memcpy(eth->h_source, mac, ETH_ALEN);
+
+	return XDP_PASS;
 }
 
 /* Redirect require an XDP bpf_prog loaded on the TX device */
diff --git a/samples/bpf/xdp_redirect_map_user.c b/samples/bpf/xdp_redirect_map_user.c
index 31131b6e7782..19636045c8dc 100644
--- a/samples/bpf/xdp_redirect_map_user.c
+++ b/samples/bpf/xdp_redirect_map_user.c
@@ -14,6 +14,10 @@
 #include <unistd.h>
 #include <libgen.h>
 #include <sys/resource.h>
+#include <sys/ioctl.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
 
 #include "bpf_util.h"
 #include <bpf/bpf.h>
@@ -21,7 +25,8 @@
 
 static int ifindex_in;
 static int ifindex_out;
-static bool ifindex_out_xdp_dummy_attached = true;
+static bool ifindex_out_xdp_dummy_attached = false;
+static bool xdp_devmap_attached = false;
 static __u32 prog_id;
 static __u32 dummy_prog_id;
 
@@ -83,6 +88,29 @@ static void poll_stats(int interval, int ifindex)
 	}
 }
 
+static int get_mac_addr(unsigned int ifindex_out, void *mac_addr)
+{
+	struct ifreq ifr;
+	char ifname[IF_NAMESIZE];
+	int fd = socket(PF_INET, SOCK_DGRAM, IPPROTO_IP);
+
+	if (fd < 0)
+		return -1;
+
+	if (!if_indextoname(ifindex_out, ifname))
+		return -1;
+
+	strcpy(ifr.ifr_name, ifname);
+
+	if (ioctl(fd, SIOCGIFHWADDR, &ifr) != 0)
+		return -1;
+
+	memcpy(mac_addr, ifr.ifr_hwaddr.sa_data, 6 * sizeof(char));
+	close(fd);
+
+	return 0;
+}
+
 static void usage(const char *prog)
 {
 	fprintf(stderr,
@@ -90,24 +118,26 @@ static void usage(const char *prog)
 		"OPTS:\n"
 		"    -S    use skb-mode\n"
 		"    -N    enforce native mode\n"
-		"    -F    force loading prog\n",
+		"    -F    force loading prog\n"
+		"    -X    load xdp program on egress\n",
 		prog);
 }
 
 int main(int argc, char **argv)
 {
 	struct bpf_prog_load_attr prog_load_attr = {
-		.prog_type	= BPF_PROG_TYPE_XDP,
+		.prog_type	= BPF_PROG_TYPE_UNSPEC,
 	};
-	struct bpf_program *prog, *dummy_prog;
+	struct bpf_program *prog, *dummy_prog, *devmap_prog;
+	int prog_fd, dummy_prog_fd, devmap_prog_fd = -1;
+	int tx_port_map_fd, tx_mac_map_fd;
+	struct bpf_devmap_val devmap_val;
 	struct bpf_prog_info info = {};
 	__u32 info_len = sizeof(info);
-	int prog_fd, dummy_prog_fd;
-	const char *optstr = "FSN";
+	const char *optstr = "FSNX";
 	struct bpf_object *obj;
 	int ret, opt, key = 0;
 	char filename[256];
-	int tx_port_map_fd;
 
 	while ((opt = getopt(argc, argv, optstr)) != -1) {
 		switch (opt) {
@@ -120,6 +150,9 @@ int main(int argc, char **argv)
 		case 'F':
 			xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
 			break;
+		case 'X':
+			xdp_devmap_attached = true;
+			break;
 		default:
 			usage(basename(argv[0]));
 			return 1;
@@ -150,67 +183,107 @@ int main(int argc, char **argv)
 	if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd))
 		return 1;
 
-	prog = bpf_program__next(NULL, obj);
-	dummy_prog = bpf_program__next(prog, obj);
-	if (!prog || !dummy_prog) {
-		printf("finding a prog in obj file failed\n");
-		return 1;
+	if (xdp_flags & XDP_FLAGS_SKB_MODE) {
+		prog = bpf_object__find_program_by_title(obj, "xdp_redirect_general");
+		tx_port_map_fd = bpf_object__find_map_fd_by_name(obj, "tx_port_general");
+	} else {
+		prog = bpf_object__find_program_by_title(obj, "xdp_redirect_native");
+		tx_port_map_fd = bpf_object__find_map_fd_by_name(obj, "tx_port_native");
 	}
-	/* bpf_prog_load_xattr gives us the pointer to first prog's fd,
-	 * so we're missing only the fd for dummy prog
-	 */
-	dummy_prog_fd = bpf_program__fd(dummy_prog);
-	if (prog_fd < 0 || dummy_prog_fd < 0) {
-		printf("bpf_prog_load_xattr: %s\n", strerror(errno));
-		return 1;
+	prog_fd = bpf_program__fd(prog);
+	if (!prog || prog_fd < 0 || tx_port_map_fd < 0) {
+		printf("finding prog/tx_port_map in obj file failed\n");
+		goto out;
 	}
 
-	tx_port_map_fd = bpf_object__find_map_fd_by_name(obj, "tx_port");
 	rxcnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rxcnt");
-	if (tx_port_map_fd < 0 || rxcnt_map_fd < 0) {
+	tx_mac_map_fd = bpf_object__find_map_fd_by_name(obj, "tx_mac");
+	if (rxcnt_map_fd < 0 || tx_mac_map_fd < 0) {
 		printf("bpf_object__find_map_fd_by_name failed\n");
-		return 1;
+		goto out;
 	}
 
 	if (bpf_set_link_xdp_fd(ifindex_in, prog_fd, xdp_flags) < 0) {
 		printf("ERROR: link set xdp fd failed on %d\n", ifindex_in);
-		return 1;
+		goto out;
 	}
 
 	ret = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
 	if (ret) {
 		printf("can't get prog info - %s\n", strerror(errno));
-		return ret;
+		goto out;
 	}
 	prog_id = info.id;
 
-	/* Loading dummy XDP prog on out-device */
-	if (bpf_set_link_xdp_fd(ifindex_out, dummy_prog_fd,
-			    (xdp_flags | XDP_FLAGS_UPDATE_IF_NOEXIST)) < 0) {
-		printf("WARN: link set xdp fd failed on %d\n", ifindex_out);
-		ifindex_out_xdp_dummy_attached = false;
-	}
+	/* If -X supplied, load 2nd xdp prog on egress.
+	 * If not, just load dummy prog on egress.
+	 */
+	if (xdp_devmap_attached) {
+		unsigned char mac_addr[6];
 
-	memset(&info, 0, sizeof(info));
-	ret = bpf_obj_get_info_by_fd(dummy_prog_fd, &info, &info_len);
-	if (ret) {
-		printf("can't get prog info - %s\n", strerror(errno));
-		return ret;
+		devmap_prog = bpf_object__find_program_by_title(obj, "xdp_devmap/map_prog");
+		if (!devmap_prog) {
+			printf("finding devmap_prog in obj file failed\n");
+			goto out;
+		}
+		devmap_prog_fd = bpf_program__fd(devmap_prog);
+		if (devmap_prog_fd < 0) {
+			printf("finding devmap_prog fd failed\n");
+			goto out;
+		}
+
+		if (get_mac_addr(ifindex_out, mac_addr) < 0) {
+			printf("get interface %d mac failed\n", ifindex_out);
+			goto out;
+		}
+
+		ret = bpf_map_update_elem(tx_mac_map_fd, &key, mac_addr, 0);
+		if (ret) {
+			perror("bpf_update_elem tx_mac_map_fd");
+			goto out;
+		}
+	} else if (ifindex_in != ifindex_out) {
+		dummy_prog = bpf_object__find_program_by_title(obj, "xdp_redirect_dummy");
+		if (!dummy_prog) {
+			printf("finding dummy_prog in obj file failed\n");
+			goto out;
+		}
+
+		dummy_prog_fd = bpf_program__fd(dummy_prog);
+		if (dummy_prog_fd < 0) {
+			printf("find dummy_prog fd failed\n");
+			goto out;
+		}
+
+		if (bpf_set_link_xdp_fd(ifindex_out, dummy_prog_fd,
+					(xdp_flags | XDP_FLAGS_UPDATE_IF_NOEXIST)) == 0) {
+			ifindex_out_xdp_dummy_attached = true;
+		} else {
+			printf("WARN: link set xdp fd failed on %d\n", ifindex_out);
+		}
+
+		memset(&info, 0, sizeof(info));
+		ret = bpf_obj_get_info_by_fd(dummy_prog_fd, &info, &info_len);
+		if (ret) {
+			printf("can't get prog info - %s\n", strerror(errno));
+		}
+		dummy_prog_id = info.id;
 	}
-	dummy_prog_id = info.id;
 
 	signal(SIGINT, int_exit);
 	signal(SIGTERM, int_exit);
 
-	/* populate virtual to physical port map */
-	ret = bpf_map_update_elem(tx_port_map_fd, &key, &ifindex_out, 0);
+	devmap_val.ifindex = ifindex_out;
+	devmap_val.bpf_prog.fd = devmap_prog_fd;
+	ret = bpf_map_update_elem(tx_port_map_fd, &key, &devmap_val, 0);
 	if (ret) {
-		perror("bpf_update_elem");
+		perror("bpf_update_elem tx_port_map_fd");
 		goto out;
 	}
 
 	poll_stats(2, ifindex_out);
 
 out:
-	return 0;
+	bpf_object__close(obj);
+	return 1;
 }
-- 
2.26.2