We want to have a tighter control on what ports we bind to in
the BPF_CGROUP_INET{4,6}_CONNECT hooks even if it means
connect() becomes slightly more expensive. The expensive part
comes from the fact that we now need to call inet_csk_get_port()
that verifies that the port is not used and allocates an entry
in the hash table for it.
Since we can't rely on "snum || !bind_address_no_port" to prevent
us from calling POST_BIND hook anymore, let's add another bind flag
to indicate that the call site is BPF program.
v5:
* fix wrong AF_INET (should be AF_INET6) in the bpf program for v6
v3:
* More bpf_bind documentation refinements (Martin KaFai Lau)
* Add UDP tests as well (Martin KaFai Lau)
* Don't start the thread, just do socket+bind+listen (Martin KaFai Lau)
v2:
* Update documentation (Andrey Ignatov)
* Pass BIND_FORCE_ADDRESS_NO_PORT conditionally (Andrey Ignatov)
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20200508174611.228805-5-sdf@google.com
#define BIND_FORCE_ADDRESS_NO_PORT (1 << 0)
/* Grab and release socket lock. */
#define BIND_WITH_LOCK (1 << 1)
+/* Called from BPF program. */
+#define BIND_FROM_BPF (1 << 2)
int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
u32 flags);
int inet_getname(struct socket *sock, struct sockaddr *uaddr,
*
* This helper works for IPv4 and IPv6, TCP and UDP sockets. The
* domain (*addr*\ **->sa_family**) must be **AF_INET** (or
- * **AF_INET6**). Looking for a free port to bind to can be
- * expensive, therefore binding to port is not permitted by the
- * helper: *addr*\ **->sin_port** (or **sin6_port**, respectively)
- * must be set to zero.
+ * **AF_INET6**). It's advised to pass zero port (**sin_port**
+ * or **sin6_port**) which triggers IP_BIND_ADDRESS_NO_PORT-like
+ * behavior and lets the kernel efficiently pick up an unused
+ * port as long as 4-tuple is unique. Passing non-zero port might
+ * lead to degraded performance.
* Return
* 0 on success, or a negative error in case of failure.
*
{
#ifdef CONFIG_INET
struct sock *sk = ctx->sk;
+ u32 flags = BIND_FROM_BPF;
int err;
- /* Binding to port can be expensive so it's prohibited in the helper.
- * Only binding to IP is supported.
- */
err = -EINVAL;
if (addr_len < offsetofend(struct sockaddr, sa_family))
return err;
if (addr->sa_family == AF_INET) {
if (addr_len < sizeof(struct sockaddr_in))
return err;
- if (((struct sockaddr_in *)addr)->sin_port != htons(0))
- return err;
- return __inet_bind(sk, addr, addr_len,
- BIND_FORCE_ADDRESS_NO_PORT);
+ if (((struct sockaddr_in *)addr)->sin_port == htons(0))
+ flags |= BIND_FORCE_ADDRESS_NO_PORT;
+ return __inet_bind(sk, addr, addr_len, flags);
#if IS_ENABLED(CONFIG_IPV6)
} else if (addr->sa_family == AF_INET6) {
if (addr_len < SIN6_LEN_RFC2133)
return err;
- if (((struct sockaddr_in6 *)addr)->sin6_port != htons(0))
- return err;
+ if (((struct sockaddr_in6 *)addr)->sin6_port == htons(0))
+ flags |= BIND_FORCE_ADDRESS_NO_PORT;
/* ipv6_bpf_stub cannot be NULL, since it's called from
* bpf_cgroup_inet6_connect hook and ipv6 is already loaded
*/
- return ipv6_bpf_stub->inet6_bind(sk, addr, addr_len,
- BIND_FORCE_ADDRESS_NO_PORT);
+ return ipv6_bpf_stub->inet6_bind(sk, addr, addr_len, flags);
#endif /* CONFIG_IPV6 */
}
#endif /* CONFIG_INET */
err = -EADDRINUSE;
goto out_release_sock;
}
- err = BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk);
- if (err) {
- inet->inet_saddr = inet->inet_rcv_saddr = 0;
- goto out_release_sock;
+ if (!(flags & BIND_FROM_BPF)) {
+ err = BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk);
+ if (err) {
+ inet->inet_saddr = inet->inet_rcv_saddr = 0;
+ goto out_release_sock;
+ }
}
}
err = -EADDRINUSE;
goto out;
}
- err = BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk);
- if (err) {
- sk->sk_ipv6only = saved_ipv6only;
- inet_reset_saddr(sk);
- goto out;
+ if (!(flags & BIND_FROM_BPF)) {
+ err = BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk);
+ if (err) {
+ sk->sk_ipv6only = saved_ipv6only;
+ inet_reset_saddr(sk);
+ goto out;
+ }
}
}
*
* This helper works for IPv4 and IPv6, TCP and UDP sockets. The
* domain (*addr*\ **->sa_family**) must be **AF_INET** (or
- * **AF_INET6**). Looking for a free port to bind to can be
- * expensive, therefore binding to port is not permitted by the
- * helper: *addr*\ **->sin_port** (or **sin6_port**, respectively)
- * must be set to zero.
+ * **AF_INET6**). It's advised to pass zero port (**sin_port**
+ * or **sin6_port**) which triggers IP_BIND_ADDRESS_NO_PORT-like
+ * behavior and lets the kernel efficiently pick up an unused
+ * port as long as 4-tuple is unique. Passing non-zero port might
+ * lead to degraded performance.
* Return
* 0 on success, or a negative error in case of failure.
*
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "cgroup_helpers.h"
+#include "network_helpers.h"
+
+static int verify_port(int family, int fd, int expected)
+{
+ struct sockaddr_storage addr;
+ socklen_t len = sizeof(addr);
+ __u16 port;
+
+ if (getsockname(fd, (struct sockaddr *)&addr, &len)) {
+ log_err("Failed to get server addr");
+ return -1;
+ }
+
+ if (family == AF_INET)
+ port = ((struct sockaddr_in *)&addr)->sin_port;
+ else
+ port = ((struct sockaddr_in6 *)&addr)->sin6_port;
+
+ if (ntohs(port) != expected) {
+ log_err("Unexpected port %d, expected %d", ntohs(port),
+ expected);
+ return -1;
+ }
+
+ return 0;
+}
+
+static int run_test(int cgroup_fd, int server_fd, int family, int type)
+{
+ struct bpf_prog_load_attr attr = {
+ .prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+ };
+ struct bpf_object *obj;
+ int expected_port;
+ int prog_fd;
+ int err;
+ int fd;
+
+ if (family == AF_INET) {
+ attr.file = "./connect_force_port4.o";
+ attr.expected_attach_type = BPF_CGROUP_INET4_CONNECT;
+ expected_port = 22222;
+ } else {
+ attr.file = "./connect_force_port6.o";
+ attr.expected_attach_type = BPF_CGROUP_INET6_CONNECT;
+ expected_port = 22223;
+ }
+
+ err = bpf_prog_load_xattr(&attr, &obj, &prog_fd);
+ if (err) {
+ log_err("Failed to load BPF object");
+ return -1;
+ }
+
+ err = bpf_prog_attach(prog_fd, cgroup_fd, attr.expected_attach_type,
+ 0);
+ if (err) {
+ log_err("Failed to attach BPF program");
+ goto close_bpf_object;
+ }
+
+ fd = connect_to_fd(family, type, server_fd);
+ if (fd < 0) {
+ err = -1;
+ goto close_bpf_object;
+ }
+
+ err = verify_port(family, fd, expected_port);
+
+ close(fd);
+
+close_bpf_object:
+ bpf_object__close(obj);
+ return err;
+}
+
+void test_connect_force_port(void)
+{
+ int server_fd, cgroup_fd;
+
+ cgroup_fd = test__join_cgroup("/connect_force_port");
+ if (CHECK_FAIL(cgroup_fd < 0))
+ return;
+
+ server_fd = start_server(AF_INET, SOCK_STREAM);
+ if (CHECK_FAIL(server_fd < 0))
+ goto close_cgroup_fd;
+ CHECK_FAIL(run_test(cgroup_fd, server_fd, AF_INET, SOCK_STREAM));
+ close(server_fd);
+
+ server_fd = start_server(AF_INET6, SOCK_STREAM);
+ if (CHECK_FAIL(server_fd < 0))
+ goto close_cgroup_fd;
+ CHECK_FAIL(run_test(cgroup_fd, server_fd, AF_INET6, SOCK_STREAM));
+ close(server_fd);
+
+ server_fd = start_server(AF_INET, SOCK_DGRAM);
+ if (CHECK_FAIL(server_fd < 0))
+ goto close_cgroup_fd;
+ CHECK_FAIL(run_test(cgroup_fd, server_fd, AF_INET, SOCK_DGRAM));
+ close(server_fd);
+
+ server_fd = start_server(AF_INET6, SOCK_DGRAM);
+ if (CHECK_FAIL(server_fd < 0))
+ goto close_cgroup_fd;
+ CHECK_FAIL(run_test(cgroup_fd, server_fd, AF_INET6, SOCK_DGRAM));
+ close(server_fd);
+
+close_cgroup_fd:
+ close(cgroup_fd);
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <string.h>
+
+#include <linux/bpf.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <sys/socket.h>
+
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+char _license[] SEC("license") = "GPL";
+int _version SEC("version") = 1;
+
+SEC("cgroup/connect4")
+int _connect4(struct bpf_sock_addr *ctx)
+{
+ struct sockaddr_in sa = {};
+
+ sa.sin_family = AF_INET;
+ sa.sin_port = bpf_htons(22222);
+ sa.sin_addr.s_addr = bpf_htonl(0x7f000001); /* 127.0.0.1 */
+
+ if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0)
+ return 0;
+
+ return 1;
+}
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+#include <string.h>
+
+#include <linux/bpf.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <sys/socket.h>
+
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+char _license[] SEC("license") = "GPL";
+int _version SEC("version") = 1;
+
+SEC("cgroup/connect6")
+int _connect6(struct bpf_sock_addr *ctx)
+{
+ struct sockaddr_in6 sa = {};
+
+ sa.sin6_family = AF_INET6;
+ sa.sin6_port = bpf_htons(22223);
+ sa.sin6_addr.s6_addr32[3] = bpf_htonl(1); /* ::1 */
+
+ if (bpf_bind(ctx, (struct sockaddr *)&sa, sizeof(sa)) != 0)
+ return 0;
+
+ return 1;
+}
projects / platform / kernel / linux-starfive.git / commitdiff