diff options
| -rw-r--r-- | include/net/inet_common.h | 2 | ||||
| -rw-r--r-- | include/uapi/linux/bpf.h | 9 | ||||
| -rw-r--r-- | net/core/filter.c | 18 | ||||
| -rw-r--r-- | net/ipv4/af_inet.c | 10 | ||||
| -rw-r--r-- | net/ipv6/af_inet6.c | 12 | ||||
| -rw-r--r-- | tools/include/uapi/linux/bpf.h | 9 | ||||
| -rw-r--r-- | tools/testing/selftests/bpf/prog_tests/connect_force_port.c | 115 | ||||
| -rw-r--r-- | tools/testing/selftests/bpf/progs/connect_force_port4.c | 28 | ||||
| -rw-r--r-- | tools/testing/selftests/bpf/progs/connect_force_port6.c | 28 |
9 files changed, 203 insertions, 28 deletions
diff --git a/include/net/inet_common.h b/include/net/inet_common.h index c38f4f7d660a..cb2818862919 100644 --- a/include/net/inet_common.h +++ b/include/net/inet_common.h @@ -39,6 +39,8 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); #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, diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index b3643e27e264..6e5e7caa3739 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1994,10 +1994,11 @@ union bpf_attr { * * 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. * diff --git a/net/core/filter.c b/net/core/filter.c index fa9ddab5dd1f..da0634979f53 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4525,32 +4525,28 @@ BPF_CALL_3(bpf_bind, struct bpf_sock_addr_kern *, ctx, struct sockaddr *, addr, { #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 */ diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 68e74b1b0f26..fcf0d12a407a 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -526,10 +526,12 @@ int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, 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; + } } } diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 552c2592b81c..771a462a8322 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -407,11 +407,13 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, 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; + } } } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index b3643e27e264..6e5e7caa3739 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1994,10 +1994,11 @@ union bpf_attr { * * 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. * diff --git a/tools/testing/selftests/bpf/prog_tests/connect_force_port.c b/tools/testing/selftests/bpf/prog_tests/connect_force_port.c new file mode 100644 index 000000000000..47fbb20cb6a6 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/connect_force_port.c @@ -0,0 +1,115 @@ +// 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); +} diff --git a/tools/testing/selftests/bpf/progs/connect_force_port4.c b/tools/testing/selftests/bpf/progs/connect_force_port4.c new file mode 100644 index 000000000000..1b8eb34b2db0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/connect_force_port4.c @@ -0,0 +1,28 @@ +// 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; +} diff --git a/tools/testing/selftests/bpf/progs/connect_force_port6.c b/tools/testing/selftests/bpf/progs/connect_force_port6.c new file mode 100644 index 000000000000..ae6f7d750b4c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/connect_force_port6.c @@ -0,0 +1,28 @@ +// 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; +} |