From: Cong Wang <cong.w...@bytedance.com>
Add two test cases to ensure redirection between two
AF_UNIX sockets or two UDP sockets work.
Cc: John Fastabend <john.fastab...@gmail.com>
Cc: Daniel Borkmann <dan...@iogearbox.net>
Cc: Jakub Sitnicki <ja...@cloudflare.com>
Cc: Lorenz Bauer <l...@cloudflare.com>
Signed-off-by: Cong Wang <cong.w...@bytedance.com>
---
.../selftests/bpf/prog_tests/sockmap_listen.c | 241 ++++++++++++++++++
.../selftests/bpf/progs/test_sockmap_listen.c | 20 ++
2 files changed, 261 insertions(+)
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index c26e6bf05e49..8f52302165a6 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -1441,6 +1441,8 @@ static const char *family_str(sa_family_t family)
return "IPv4";
case AF_INET6:
return "IPv6";
+ case AF_UNIX:
+ return "Unix";
default:
return "unknown";
}
@@ -1563,6 +1565,239 @@ static void test_redir(struct test_sockmap_listen
*skel, struct bpf_map *map,
}
}
+static void udp_redir_to_connected(int family, int sotype, int sock_mapfd,
+ int verd_mapfd, enum redir_mode mode)
+{
+ const char *log_prefix = redir_mode_str(mode);
+ struct sockaddr_storage addr;
+ int c0, c1, p0, p1;
+ unsigned int pass;
+ socklen_t len;
+ int err, n;
+ u64 value;
+ u32 key;
+ char b;
+
+ zero_verdict_count(verd_mapfd);
+
+ p0 = socket_loopback(family, sotype | SOCK_NONBLOCK);
+ if (p0 < 0)
+ return;
+ len = sizeof(addr);
+ err = xgetsockname(p0, sockaddr(&addr), &len);
+ if (err)
+ goto close_peer0;
+
+ c0 = xsocket(family, sotype | SOCK_NONBLOCK, 0);
+ if (c0 < 0)
+ goto close_peer0;
+ err = xconnect(c0, sockaddr(&addr), len);
+ if (err)
+ goto close_cli0;
+ err = xgetsockname(c0, sockaddr(&addr), &len);
+ if (err)
+ goto close_cli0;
+ err = xconnect(p0, sockaddr(&addr), len);
+ if (err)
+ goto close_cli0;
+
+ p1 = socket_loopback(family, sotype | SOCK_NONBLOCK);
+ if (p1 < 0)
+ goto close_cli0;
+ err = xgetsockname(p1, sockaddr(&addr), &len);
+ if (err)
+ goto close_cli0;
+
+ c1 = xsocket(family, sotype | SOCK_NONBLOCK, 0);
+ if (c1 < 0)
+ goto close_peer1;
+ err = xconnect(c1, sockaddr(&addr), len);
+ if (err)
+ goto close_cli1;
+ err = xgetsockname(c1, sockaddr(&addr), &len);
+ if (err)
+ goto close_cli1;
+ err = xconnect(p1, sockaddr(&addr), len);
+ if (err)
+ goto close_cli1;
+
+ key = 0;
+ value = p0;
+ err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST);
+ if (err)
+ goto close_cli1;
+
+ key = 1;
+ value = p1;
+ err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST);
+ if (err)
+ goto close_cli1;
+
+ n = write(c1, "a", 1);
+ if (n < 0)
+ FAIL_ERRNO("%s: write", log_prefix);
+ if (n == 0)
+ FAIL("%s: incomplete write", log_prefix);
+ if (n < 1)
+ goto close_cli1;
+
+ key = SK_PASS;
+ err = xbpf_map_lookup_elem(verd_mapfd, &key, &pass);
+ if (err)
+ goto close_cli1;
+ if (pass != 1)
+ FAIL("%s: want pass count 1, have %d", log_prefix, pass);
+
+ n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1);
+ if (n < 0)
+ FAIL_ERRNO("%s: read", log_prefix);
+ if (n == 0)
+ FAIL("%s: incomplete read", log_prefix);
+
+close_cli1:
+ xclose(c1);
+close_peer1:
+ xclose(p1);
+close_cli0:
+ xclose(c0);
+close_peer0:
+ xclose(p0);
+}
+
+static void udp_skb_redir_to_connected(struct test_sockmap_listen *skel,
+ struct bpf_map *inner_map, int
family,
+ int sotype)
+{
+ int verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
+ int verdict_map = bpf_map__fd(skel->maps.verdict_map);
+ int sock_map = bpf_map__fd(inner_map);
+ int err;
+
+ err = xbpf_prog_attach(verdict, sock_map, BPF_SK_SKB_VERDICT, 0);
+ if (err)
+ return;
+
+ skel->bss->test_ingress = false;
+ udp_redir_to_connected(family, sotype, sock_map, verdict_map,
+ REDIR_EGRESS);
+ skel->bss->test_ingress = true;
+ udp_redir_to_connected(family, sotype, sock_map, verdict_map,
+ REDIR_INGRESS);
+
+ xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT);
+}
+
+static void test_udp_redir(struct test_sockmap_listen *skel, struct bpf_map
*map,
+ int family)
+{
+ const char *family_name, *map_name;
+ char s[MAX_TEST_NAME];
+
+ family_name = family_str(family);
+ map_name = map_type_str(map);
+ snprintf(s, sizeof(s), "%s %s %s", map_name, family_name, __func__);
+ if (!test__start_subtest(s))
+ return;
+ udp_skb_redir_to_connected(skel, map, family, SOCK_DGRAM);
+}
+
+static void unix_redir_to_connected(int sotype, int sock_mapfd,
+ int verd_mapfd, enum redir_mode mode)
+{
+ const char *log_prefix = redir_mode_str(mode);
+ int c0, c1, p0, p1;
+ unsigned int pass;
+ int err, n;
+ int sfd[2];
+ u64 value;
+ u32 key;
+ char b;
+
+ zero_verdict_count(verd_mapfd);
+
+ if (socketpair(AF_UNIX, sotype | SOCK_NONBLOCK, 0, sfd))
+ return;
+ c0 = sfd[0], p0 = sfd[1];
+
+ if (socketpair(AF_UNIX, sotype | SOCK_NONBLOCK, 0, sfd))
+ goto close0;
+ c1 = sfd[0], p1 = sfd[1];
+
+ key = 0;
+ value = p0;
+ err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST);
+ if (err)
+ goto close;
+
+ key = 1;
+ value = p1;
+ err = xbpf_map_update_elem(sock_mapfd, &key, &value, BPF_NOEXIST);
+ if (err)
+ goto close;
+
+ n = write(c1, "a", 1);
+ if (n < 0)
+ FAIL_ERRNO("%s: write", log_prefix);
+ if (n == 0)
+ FAIL("%s: incomplete write", log_prefix);
+ if (n < 1)
+ goto close;
+
+ key = SK_PASS;
+ err = xbpf_map_lookup_elem(verd_mapfd, &key, &pass);
+ if (err)
+ goto close;
+ if (pass != 1)
+ FAIL("%s: want pass count 1, have %d", log_prefix, pass);
+
+ n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1);
+ if (n < 0)
+ FAIL_ERRNO("%s: read", log_prefix);
+ if (n == 0)
+ FAIL("%s: incomplete read", log_prefix);
+
+close:
+ xclose(c1);
+ xclose(p1);
+close0:
+ xclose(c0);
+ xclose(p0);
+}
+
+static void unix_skb_redir_to_connected(struct test_sockmap_listen *skel,
+ struct bpf_map *inner_map, int sotype)
+{
+ int verdict = bpf_program__fd(skel->progs.prog_skb_verdict);
+ int verdict_map = bpf_map__fd(skel->maps.verdict_map);
+ int sock_map = bpf_map__fd(inner_map);
+ int err;
+
+ err = xbpf_prog_attach(verdict, sock_map, BPF_SK_SKB_VERDICT, 0);
+ if (err)
+ return;
+
+ skel->bss->test_ingress = false;
+ unix_redir_to_connected(sotype, sock_map, verdict_map, REDIR_EGRESS);
+ skel->bss->test_ingress = true;
+ unix_redir_to_connected(sotype, sock_map, verdict_map, REDIR_INGRESS);
+
+ xbpf_prog_detach2(verdict, sock_map, BPF_SK_SKB_VERDICT);
+}
+
+static void test_unix_redir(struct test_sockmap_listen *skel, struct bpf_map
*map,
+ int sotype)
+{
+ const char *family_name, *map_name;
+ char s[MAX_TEST_NAME];
+
+ family_name = family_str(AF_UNIX);
+ map_name = map_type_str(map);
+ snprintf(s, sizeof(s), "%s %s %s", map_name, family_name, __func__);
+ if (!test__start_subtest(s))
+ return;
+ unix_skb_redir_to_connected(skel, map, sotype);
+}
+
static void test_reuseport(struct test_sockmap_listen *skel,
struct bpf_map *map, int family, int sotype)
{
@@ -1626,10 +1861,16 @@ void test_sockmap_listen(void)
skel->bss->test_sockmap = true;
run_tests(skel, skel->maps.sock_map, AF_INET);
run_tests(skel, skel->maps.sock_map, AF_INET6);
+ test_udp_redir(skel, skel->maps.sock_map, AF_INET);
+ test_udp_redir(skel, skel->maps.sock_map, AF_INET6);
+ test_unix_redir(skel, skel->maps.sock_map, SOCK_DGRAM);
skel->bss->test_sockmap = false;
run_tests(skel, skel->maps.sock_hash, AF_INET);
run_tests(skel, skel->maps.sock_hash, AF_INET6);
+ test_udp_redir(skel, skel->maps.sock_hash, AF_INET);
+ test_udp_redir(skel, skel->maps.sock_hash, AF_INET6);
+ test_unix_redir(skel, skel->maps.sock_hash, SOCK_DGRAM);
test_sockmap_listen__destroy(skel);
}
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
index fa221141e9c1..49537c78e34a 100644
--- a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
@@ -29,6 +29,7 @@ struct {
} verdict_map SEC(".maps");
static volatile bool test_sockmap; /* toggled by user-space */
+static volatile bool test_ingress; /* toggled by user-space */
SEC("sk_skb/stream_parser")
int prog_stream_parser(struct __sk_buff *skb)
@@ -55,6 +56,25 @@ int prog_stream_verdict(struct __sk_buff *skb)
return verdict;
}
+SEC("sk_skb/skb_verdict")
+int prog_skb_verdict(struct __sk_buff *skb)
+{
+ unsigned int *count;
+ __u32 zero = 0;
+ int verdict;
+
+ if (test_sockmap)
+ verdict = bpf_sk_redirect_map(skb, &sock_map, zero,
test_ingress ? BPF_F_INGRESS : 0);
+ else
+ verdict = bpf_sk_redirect_hash(skb, &sock_hash, &zero,
test_ingress ? BPF_F_INGRESS : 0);
+
+ count = bpf_map_lookup_elem(&verdict_map, &verdict);
+ if (count)
+ (*count)++;
+
+ return verdict;
+}
+
SEC("sk_msg")
int prog_msg_verdict(struct sk_msg_md *msg)
{
--
2.25.1
