bpf: xdp: Add XDP example for head adjustment

The XDP prog checks if the incoming packet matches any VIP:PORT
combination in the BPF hashmap.  If it is, it will encapsulate
the packet with a IPv4/v6 header as instructed by the value of
the BPF hashmap and then XDP_TX it out.

The VIP:PORT -> IP-Encap-Info can be specified by the cmd args
of the user prog.

Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

8 files changed, 630 insertions, 93 deletions

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 00cd3081c038..f2219c1489e5 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -33,6 +33,7 @@ hostprogs-y += trace_event
 hostprogs-y += sampleip
 hostprogs-y += tc_l2_redirect
 hostprogs-y += lwt_len_hist
+hostprogs-y += xdp_tx_iptunnel
 
 test_lru_dist-objs := test_lru_dist.o libbpf.o
 sock_example-objs := sock_example.o libbpf.o
@@ -67,6 +68,7 @@ trace_event-objs := bpf_load.o libbpf.o trace_event_user.o
 sampleip-objs := bpf_load.o libbpf.o sampleip_user.o
 tc_l2_redirect-objs := bpf_load.o libbpf.o tc_l2_redirect_user.o
 lwt_len_hist-objs := bpf_load.o libbpf.o lwt_len_hist_user.o
+xdp_tx_iptunnel-objs := bpf_load.o libbpf.o xdp_tx_iptunnel_user.o
 
 # Tell kbuild to always build the programs
 always := $(hostprogs-y)
@@ -99,6 +101,7 @@ always += test_current_task_under_cgroup_kern.o
 always += trace_event_kern.o
 always += sampleip_kern.o
 always += lwt_len_hist_kern.o
+always += xdp_tx_iptunnel_kern.o
 
 HOSTCFLAGS += -I$(objtree)/usr/include
 HOSTCFLAGS += -I$(srctree)/tools/testing/selftests/bpf/
@@ -129,6 +132,7 @@ HOSTLOADLIBES_trace_event += -lelf
 HOSTLOADLIBES_sampleip += -lelf
 HOSTLOADLIBES_tc_l2_redirect += -l elf
 HOSTLOADLIBES_lwt_len_hist += -l elf
+HOSTLOADLIBES_xdp_tx_iptunnel += -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/bpf_helpers.h b/samples/bpf/bpf_helpers.h
index 8370a6e3839d..faaffe2e139a 100644
--- a/samples/bpf/bpf_helpers.h
+++ b/samples/bpf/bpf_helpers.h
@@ -57,6 +57,8 @@ static int (*bpf_skb_set_tunnel_opt)(void *ctx, void *md, int size) =
         (void *) BPF_FUNC_skb_set_tunnel_opt;
 static unsigned long long (*bpf_get_prandom_u32)(void) =
         (void *) BPF_FUNC_get_prandom_u32;
+static int (*bpf_xdp_adjust_head)(void *ctx, int offset) =
+        (void *) BPF_FUNC_xdp_adjust_head;
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions
diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
index 49b45ccbe153..e30b6de94f2e 100644
--- a/samples/bpf/bpf_load.c
+++ b/samples/bpf/bpf_load.c
@@ -12,6 +12,10 @@
 #include <linux/bpf.h>
 #include <linux/filter.h>
 #include <linux/perf_event.h>
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+#include <sys/types.h>
+#include <sys/socket.h>
 #include <sys/syscall.h>
 #include <sys/ioctl.h>
 #include <sys/mman.h>
@@ -450,3 +454,93 @@ struct ksym *ksym_search(long key)
         /* out of range. return _stext */
         return &syms[0];
 }
+
+int set_link_xdp_fd(int ifindex, int fd)
+{
+        struct sockaddr_nl sa;
+        int sock, seq = 0, len, ret = -1;
+        char buf[4096];
+        struct nlattr *nla, *nla_xdp;
+        struct {
+                struct nlmsghdr  nh;
+                struct ifinfomsg ifinfo;
+                char             attrbuf[64];
+        } req;
+        struct nlmsghdr *nh;
+        struct nlmsgerr *err;
+
+        memset(&sa, 0, sizeof(sa));
+        sa.nl_family = AF_NETLINK;
+
+        sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+        if (sock < 0) {
+                printf("open netlink socket: %s\n", strerror(errno));
+                return -1;
+        }
+
+        if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) {
+                printf("bind to netlink: %s\n", strerror(errno));
+                goto cleanup;
+        }
+
+        memset(&req, 0, sizeof(req));
+        req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
+        req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
+        req.nh.nlmsg_type = RTM_SETLINK;
+        req.nh.nlmsg_pid = 0;
+        req.nh.nlmsg_seq = ++seq;
+        req.ifinfo.ifi_family = AF_UNSPEC;
+        req.ifinfo.ifi_index = ifindex;
+        nla = (struct nlattr *)(((char *)&req)
+                                + NLMSG_ALIGN(req.nh.nlmsg_len));
+        nla->nla_type = NLA_F_NESTED | 43/*IFLA_XDP*/;
+
+        nla_xdp = (struct nlattr *)((char *)nla + NLA_HDRLEN);
+        nla_xdp->nla_type = 1/*IFLA_XDP_FD*/;
+        nla_xdp->nla_len = NLA_HDRLEN + sizeof(int);
+        memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd));
+        nla->nla_len = NLA_HDRLEN + nla_xdp->nla_len;
+
+        req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len);
+
+        if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
+                printf("send to netlink: %s\n", strerror(errno));
+                goto cleanup;
+        }
+
+        len = recv(sock, buf, sizeof(buf), 0);
+        if (len < 0) {
+                printf("recv from netlink: %s\n", strerror(errno));
+                goto cleanup;
+        }
+
+        for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len);
+             nh = NLMSG_NEXT(nh, len)) {
+                if (nh->nlmsg_pid != getpid()) {
+                        printf("Wrong pid %d, expected %d\n",
+                               nh->nlmsg_pid, getpid());
+                        goto cleanup;
+                }
+                if (nh->nlmsg_seq != seq) {
+                        printf("Wrong seq %d, expected %d\n",
+                               nh->nlmsg_seq, seq);
+                        goto cleanup;
+                }
+                switch (nh->nlmsg_type) {
+                case NLMSG_ERROR:
+                        err = (struct nlmsgerr *)NLMSG_DATA(nh);
+                        if (!err->error)
+                                continue;
+                        printf("nlmsg error %s\n", strerror(-err->error));
+                        goto cleanup;
+                case NLMSG_DONE:
+                        break;
+                }
+        }
+
+        ret = 0;
+
+cleanup:
+        close(sock);
+        return ret;
+}
diff --git a/samples/bpf/bpf_load.h b/samples/bpf/bpf_load.h
index 4adeeef53ad6..fb46a421ab41 100644
--- a/samples/bpf/bpf_load.h
+++ b/samples/bpf/bpf_load.h
@@ -31,4 +31,5 @@ struct ksym {
 
 int load_kallsyms(void);
 struct ksym *ksym_search(long key);
+int set_link_xdp_fd(int ifindex, int fd);
 #endif
diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c
index 2b2150d6d6f7..5f040a0d7712 100644
--- a/samples/bpf/xdp1_user.c
+++ b/samples/bpf/xdp1_user.c
@@ -5,111 +5,18 @@
  * License as published by the Free Software Foundation.
  */
 #include <linux/bpf.h>
-#include <linux/netlink.h>
-#include <linux/rtnetlink.h>
 #include <assert.h>
 #include <errno.h>
 #include <signal.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
-#include <sys/socket.h>
 #include <unistd.h>