Merge branch 'bpf: Add socket destroy capability'

Aditi Ghag says:

====================

This patch set adds the capability to destroy sockets in BPF. We plan to
use the capability in Cilium to force client sockets to reconnect when
their remote load-balancing backends are deleted. The other use case is
on-the-fly policy enforcement where existing socket connections
prevented by policies need to be terminated.

The use cases, and more details around
the selected approach were presented at LPC 2022 -
https://lpc.events/event/16/contributions/1358/.
RFC discussion -
https://lore.kernel.org/netdev/CABG=zsBEh-P4NXk23eBJw7eajB5YJeRS7oPXnTAzs=yob4EMoQ@mail.gmail.com/T/#u.
v8 patch series -
https://lore.kernel.org/bpf/20230517175359.527917-1-aditi.ghag@isovalent.com/

v9 highlights:
Address review comments:
Martin:
- Rearranged the kfunc filter patch, and added the missing break
  statement.
- Squashed the extended selftest/bpf patch.
Yonghong:
- Revised commit message for patch 1.

(Below notes are same as v8 patch series that are still relevant. Refer to
earlier patch series versions for other notes.)
- I hit a snag while writing the kfunc where verifier complained about the
  `sock_common` type passed from TCP iterator. With kfuncs, there don't
  seem to be any options available to pass BTF type hints to the verifier
  (equivalent of `ARG_PTR_TO_BTF_ID_SOCK_COMMON`, as was the case with the
  helper).  As a result, I changed the argument type of the sock_destory
  kfunc to `sock_common`.
====================

Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>

5 files changed, 412 insertions, 0 deletions

diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c
index 596caa176582..a105c0cd008a 100644
--- a/tools/testing/selftests/bpf/network_helpers.c
+++ b/tools/testing/selftests/bpf/network_helpers.c
@@ -427,3 +427,26 @@ void close_netns(struct nstoken *token)
 	close(token->orig_netns_fd);
 	free(token);
 }
+
+int get_socket_local_port(int sock_fd)
+{
+	struct sockaddr_storage addr;
+	socklen_t addrlen = sizeof(addr);
+	int err;
+
+	err = getsockname(sock_fd, (struct sockaddr *)&addr, &addrlen);
+	if (err < 0)
+		return err;
+
+	if (addr.ss_family == AF_INET) {
+		struct sockaddr_in *sin = (struct sockaddr_in *)&addr;
+
+		return sin->sin_port;
+	} else if (addr.ss_family == AF_INET6) {
+		struct sockaddr_in6 *sin = (struct sockaddr_in6 *)&addr;
+
+		return sin->sin6_port;
+	}
+
+	return -1;
+}
diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h
index f882c691b790..694185644da6 100644
--- a/tools/testing/selftests/bpf/network_helpers.h
+++ b/tools/testing/selftests/bpf/network_helpers.h
@@ -56,6 +56,7 @@ int fastopen_connect(int server_fd, const char *data, unsigned int data_len,
 int make_sockaddr(int family, const char *addr_str, __u16 port,
 		  struct sockaddr_storage *addr, socklen_t *len);
 char *ping_command(int family);
+int get_socket_local_port(int sock_fd);
 
 struct nstoken;
 /**
diff --git a/tools/testing/selftests/bpf/prog_tests/sock_destroy.c b/tools/testing/selftests/bpf/prog_tests/sock_destroy.c
new file mode 100644
index 000000000000..b0583309a94e
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/sock_destroy.c
@@ -0,0 +1,221 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <bpf/bpf_endian.h>
+
+#include "sock_destroy_prog.skel.h"
+#include "sock_destroy_prog_fail.skel.h"
+#include "network_helpers.h"
+
+#define TEST_NS "sock_destroy_netns"
+
+static void start_iter_sockets(struct bpf_program *prog)
+{
+	struct bpf_link *link;
+	char buf[50] = {};
+	int iter_fd, len;
+
+	link = bpf_program__attach_iter(prog, NULL);
+	if (!ASSERT_OK_PTR(link, "attach_iter"))
+		return;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	if (!ASSERT_GE(iter_fd, 0, "create_iter"))
+		goto free_link;
+
+	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
+		;
+	ASSERT_GE(len, 0, "read");
+
+	close(iter_fd);
+
+free_link:
+	bpf_link__destroy(link);
+}
+
+static void test_tcp_client(struct sock_destroy_prog *skel)
+{
+	int serv = -1, clien = -1, accept_serv = -1, n;
+
+	serv = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0);
+	if (!ASSERT_GE(serv, 0, "start_server"))
+		goto cleanup;
+
+	clien = connect_to_fd(serv, 0);
+	if (!ASSERT_GE(clien, 0, "connect_to_fd"))
+		goto cleanup;
+
+	accept_serv = accept(serv, NULL, NULL);
+	if (!ASSERT_GE(accept_serv, 0, "serv accept"))
+		goto cleanup;
+
+	n = send(clien, "t", 1, 0);
+	if (!ASSERT_EQ(n, 1, "client send"))
+		goto cleanup;
+
+	/* Run iterator program that destroys connected client sockets. */
+	start_iter_sockets(skel->progs.iter_tcp6_client);
+
+	n = send(clien, "t", 1, 0);
+	if (!ASSERT_LT(n, 0, "client_send on destroyed socket"))
+		goto cleanup;
+	ASSERT_EQ(errno, ECONNABORTED, "error code on destroyed socket");
+
+cleanup:
+	if (clien != -1)
+		close(clien);
+	if (accept_serv != -1)
+		close(accept_serv);
+	if (serv != -1)
+		close(serv);
+}
+
+static void test_tcp_server(struct sock_destroy_prog *skel)
+{
+	int serv = -1, clien = -1, accept_serv = -1, n, serv_port;
+
+	serv = start_server(AF_INET6, SOCK_STREAM, NULL, 0, 0);
+	if (!ASSERT_GE(serv, 0, "start_server"))
+		goto cleanup;
+	serv_port = get_socket_local_port(serv);
+	if (!ASSERT_GE(serv_port, 0, "get_sock_local_port"))
+		goto cleanup;
+	skel->bss->serv_port = (__be16) serv_port;
+
+	clien = connect_to_fd(serv, 0);
+	if (!ASSERT_GE(clien, 0, "connect_to_fd"))
+		goto cleanup;
+
+	accept_serv = accept(serv, NULL, NULL);
+	if (!ASSERT_GE(accept_serv, 0, "serv accept"))
+		goto cleanup;
+
+	n = send(clien, "t", 1, 0);
+	if (!ASSERT_EQ(n, 1, "client send"))
+		goto cleanup;
+
+	/* Run iterator program that destroys server sockets. */
+	start_iter_sockets(skel->progs.iter_tcp6_server);
+
+	n = send(clien, "t", 1, 0);
+	if (!ASSERT_LT(n, 0, "client_send on destroyed socket"))
+		goto cleanup;
+	ASSERT_EQ(errno, ECONNRESET, "error code on destroyed socket");
+
+cleanup:
+	if (clien != -1)
+		close(clien);
+	if (accept_serv != -1)
+		close(accept_serv);
+	if (serv != -1)
+		close(serv);
+}
+
+static void test_udp_client(struct sock_destroy_prog *skel)
+{
+	int serv = -1, clien = -1, n = 0;
+
+	serv = start_server(AF_INET6, SOCK_DGRAM, NULL, 0, 0);
+	if (!ASSERT_GE(serv, 0, "start_server"))
+		goto cleanup;
+
+	clien = connect_to_fd(serv, 0);
+	if (!ASSERT_GE(clien, 0, "connect_to_fd"))
+		goto cleanup;
+
+	n = send(clien, "t", 1, 0);
+	if (!ASSERT_EQ(n, 1, "client send"))
+		goto cleanup;
+
+	/* Run iterator program that destroys sockets. */
+	start_iter_sockets(skel->progs.iter_udp6_client);
+
+	n = send(clien, "t", 1, 0);
+	if (!ASSERT_LT(n, 0, "client_send on destroyed socket"))
+		goto cleanup;
+	/* UDP sockets have an overriding error code after they are disconnected,
+	 * so we don't check for ECONNABORTED error code.
+	 */
+
+cleanup:
+	if (clien != -1)
+		close(clien);
+	if (serv != -1)
+		close(serv);
+}
+
+static void test_udp_server(struct sock_destroy_prog *skel)
+{
+	int *listen_fds = NULL, n, i, serv_port;
+	unsigned int num_listens = 5;
+	char buf[1];
+
+	/* Start reuseport servers. */
+	listen_fds = start_reuseport_server(AF_INET6, SOCK_DGRAM,
+					    "::1", 0, 0, num_listens);
+	if (!ASSERT_OK_PTR(listen_fds, "start_reuseport_server"))
+		goto cleanup;
+	serv_port = get_socket_local_port(listen_fds[0]);
+	if (!ASSERT_GE(serv_port, 0, "get_sock_local_port"))
+		goto cleanup;
+	skel->bss->serv_port = (__be16) serv_port;
+
+	/* Run iterator program that destroys server sockets. */
+	start_iter_sockets(skel->progs.iter_udp6_server);
+
+	for (i = 0; i < num_listens; ++i) {
+		n = read(listen_fds[i], buf, sizeof(buf));
+		if (!ASSERT_EQ(n, -1, "read") ||
+		    !ASSERT_EQ(errno, ECONNABORTED, "error code on destroyed socket"))
+			break;
+	}
+	ASSERT_EQ(i, num_listens, "server socket");
+
+cleanup:
+	free_fds(listen_fds, num_listens);
+}
+
+void test_sock_destroy(void)
+{
+	struct sock_destroy_prog *skel;
+	struct nstoken *nstoken = NULL;
+	int cgroup_fd;
+
+	skel = sock_destroy_prog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	cgroup_fd = test__join_cgroup("/sock_destroy");
+	if (!ASSERT_GE(cgroup_fd, 0, "join_cgroup"))
+		goto cleanup;
+
+	skel->links.sock_connect = bpf_program__attach_cgroup(
+		skel->progs.sock_connect, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links.sock_connect, "prog_attach"))
+		goto cleanup;
+
+	SYS(cleanup, "ip netns add %s", TEST_NS);
+	SYS(cleanup, "ip -net %s link set dev lo up", TEST_NS);
+
+	nstoken = open_netns(TEST_NS);
+	if (!ASSERT_OK_PTR(nstoken, "open_netns"))
+		goto cleanup;
+
+	if (test__start_subtest("tcp_client"))
+		test_tcp_client(skel);
+	if (test__start_subtest("tcp_server"))
+		test_tcp_server(skel);
+	if (test__start_subtest("udp_client"))
+		test_udp_client(skel);
+	if (test__start_subtest("udp_server"))
+		test_udp_server(skel);
+
+	RUN_TESTS(sock_destroy_prog_fail);
+
+cleanup:
+	if (nstoken)
+		close_netns(nstoken);
+	SYS_NOFAIL("ip netns del " TEST_NS " &> /dev/null");
+	if (cgroup_fd >= 0)
+		close(cgroup_fd);
+	sock_destroy_prog__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/sock_destroy_prog.c b/tools/testing/selftests/bpf/progs/sock_destroy_prog.c
new file mode 100644
index 000000000000..9e0bf7a54cec
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/sock_destroy_prog.c
@@ -0,0 +1,145 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#include "bpf_tracing_net.h"
+
+__be16 serv_port = 0;
+
+int bpf_sock_destroy(struct sock_common *sk) __ksym;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u64);
+} tcp_conn_sockets SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u64);
+} udp_conn_sockets SEC(".maps");
+
+SEC("cgroup/connect6")
+int sock_connect(struct bpf_sock_addr *ctx)
+{
+	__u64 sock_cookie = 0;
+	int key = 0;
+	__u32 keyc = 0;
+
+	if (ctx->family != AF_INET6 || ctx->user_family != AF_INET6)
+		return 1;
+
+	sock_cookie = bpf_get_socket_cookie(ctx);
+	if (ctx->protocol == IPPROTO_TCP)
+		bpf_map_update_elem(&tcp_conn_sockets, &key, &sock_cookie, 0);
+	else if (ctx->protocol == IPPROTO_UDP)
+		bpf_map_update_elem(&udp_conn_sockets, &keyc, &sock_cookie, 0);
+	else
+		return 1;
+
+	return 1;
+}
+
+SEC("iter/tcp")
+int iter_tcp6_client(struct bpf_iter__tcp *ctx)
+{
+	struct sock_common *sk_common = ctx->sk_common;
+	__u64 sock_cookie = 0;
+	__u64 *val;
+	int key = 0;
+
+	if (!sk_common)
+		return 0;
+
+	if (sk_common->skc_family != AF_INET6)
+		return 0;
+
+	sock_cookie  = bpf_get_socket_cookie(sk_common);
+	val = bpf_map_lookup_elem(&tcp_conn_sockets, &key);
+	if (!val)
+		return 0;
+	/* Destroy connected client sockets. */
+	if (sock_cookie == *val)
+		bpf_sock_destroy(sk_common);
+
+	return 0;
+}
+
+SEC("iter/tcp")
+int iter_tcp6_server(struct bpf_iter__tcp *ctx)
+{
+	struct sock_common *sk_common = ctx->sk_common;
+	const struct inet_connection_sock *icsk;
+	const struct inet_sock *inet;
+	struct tcp6_sock *tcp_sk;
+	__be16 srcp;
+
+	if (!sk_common)
+		return 0;
+
+	if (sk_common->skc_family != AF_INET6)
+		return 0;
+
+	tcp_sk = bpf_skc_to_tcp6_sock(sk_common);
+	if (!tcp_sk)
+		return 0;
+
+	icsk = &tcp_sk->tcp.inet_conn;
+	inet = &icsk->icsk_inet;
+	srcp = inet->inet_sport;
+
+	/* Destroy server sockets. */
+	if (srcp == serv_port)
+		bpf_sock_destroy(sk_common);
+
+	return 0;
+}
+
+
+SEC("iter/udp")
+int iter_udp6_client(struct bpf_iter__udp *ctx)
+{
+	struct udp_sock *udp_sk = ctx->udp_sk;
+	struct sock *sk = (struct sock *) udp_sk;
+	__u64 sock_cookie = 0, *val;
+	int key = 0;
+
+	if (!sk)
+		return 0;
+
+	sock_cookie  = bpf_get_socket_cookie(sk);
+	val = bpf_map_lookup_elem(&udp_conn_sockets, &key);
+	if (!val)
+		return 0;
+	/* Destroy connected client sockets. */
+	if (sock_cookie == *val)
+		bpf_sock_destroy((struct sock_common *)sk);
+
+	return 0;
+}
+
+SEC("iter/udp")
+int iter_udp6_server(struct bpf_iter__udp *ctx)
+{
+	struct udp_sock *udp_sk = ctx->udp_sk;
+	struct sock *sk = (struct sock *) udp_sk;
+	struct inet_sock *inet;
+	__be16 srcp;
+
+	if (!sk)
+		return 0;
+
+	inet = &udp_sk->inet;
+	srcp = inet->inet_sport;
+	if (srcp == serv_port)
+		bpf_sock_destroy((struct sock_common *)sk);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/sock_destroy_prog_fail.c b/tools/testing/selftests/bpf/progs/sock_destroy_prog_fail.c
new file mode 100644
index 000000000000..dd6850b58e25
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/sock_destroy_prog_fail.c
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "vmlinux.h"
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+int bpf_sock_destroy(struct sock_common *sk) __ksym;
+
+SEC("tp_btf/tcp_destroy_sock")
+__failure __msg("calling kernel function bpf_sock_destroy is not allowed")
+int BPF_PROG(trace_tcp_destroy_sock, struct sock *sk)
+{
+	/* should not load */
+	bpf_sock_destroy((struct sock_common *)sk);
+
+	return 0;
+}
+