diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 30d15e64b99337a1627be3675ebf56e842bbdfd4..975fb4cf1bb743ccff5fae92e82df582533c0ff2 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -66,7 +66,8 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk, int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, struct sockaddr *uaddr, - enum bpf_attach_type type); + enum bpf_attach_type type, + void *t_ctx); int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, struct bpf_sock_ops_kern *sock_ops, @@ -120,16 +121,18 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, ({ \ int __ret = 0; \ if (cgroup_bpf_enabled) \ - __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type); \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \ + NULL); \ __ret; \ }) -#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type) \ +#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, type, t_ctx) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled) { \ lock_sock(sk); \ - __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type); \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, type, \ + t_ctx); \ release_sock(sk); \ } \ __ret; \ @@ -151,10 +154,16 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET6_CONNECT) #define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET4_CONNECT) + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET4_CONNECT, NULL) #define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET6_CONNECT) + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET6_CONNECT, NULL) + +#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, t_ctx) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_UDP4_SENDMSG, t_ctx) + +#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_UDP6_SENDMSG, t_ctx) #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) \ ({ \ @@ -185,6 +194,7 @@ struct cgroup_bpf {}; static inline void cgroup_bpf_put(struct cgroup *cgrp) {} static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; } +#define cgroup_bpf_enabled (0) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0) #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) @@ -197,6 +207,8 @@ static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; } #define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; }) diff --git a/include/linux/filter.h b/include/linux/filter.h index d358d1815c1652592b16b1940930b0d70dc9c782..d90abdaea94b254b5b7b0309d592fbb5380d7d6f 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1010,6 +1010,7 @@ struct bpf_sock_addr_kern { * only two (src and dst) are available at convert_ctx_access time */ u64 tmp_reg; + void *t_ctx; /* Attach type specific context. */ }; struct bpf_sock_ops_kern { diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 9b8c6e310e9a9666aefec27c74451954711d6bde..cc68787f2d974d114f268b2c4992961b2fb2a1f2 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -160,6 +160,8 @@ enum bpf_attach_type { BPF_CGROUP_INET6_CONNECT, BPF_CGROUP_INET4_POST_BIND, BPF_CGROUP_INET6_POST_BIND, + BPF_CGROUP_UDP4_SENDMSG, + BPF_CGROUP_UDP6_SENDMSG, __MAX_BPF_ATTACH_TYPE }; @@ -2363,6 +2365,12 @@ struct bpf_sock_addr { __u32 family; /* Allows 4-byte read, but no write */ __u32 type; /* Allows 4-byte read, but no write */ __u32 protocol; /* Allows 4-byte read, but no write */ + __u32 msg_src_ip4; /* Allows 1,2,4-byte read an 4-byte write. + * Stored in network byte order. + */ + __u32 msg_src_ip6[4]; /* Allows 1,2,4-byte read an 4-byte write. + * Stored in network byte order. + */ }; /* User bpf_sock_ops struct to access socket values and specify request ops diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 43171a0bb02b793949fda41abe4dc6299351266b..f7c00bd6f8e49ca9cc4e6ee323b01f718aebd9ec 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -500,6 +500,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); * @sk: sock struct that will use sockaddr * @uaddr: sockaddr struct provided by user * @type: The type of program to be exectuted + * @t_ctx: Pointer to attach type specific context * * socket is expected to be of type INET or INET6. * @@ -508,12 +509,15 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); */ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, struct sockaddr *uaddr, - enum bpf_attach_type type) + enum bpf_attach_type type, + void *t_ctx) { struct bpf_sock_addr_kern ctx = { .sk = sk, .uaddr = uaddr, + .t_ctx = t_ctx, }; + struct sockaddr_storage unspec; struct cgroup *cgrp; int ret; @@ -523,6 +527,11 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6) return 0; + if (!ctx.uaddr) { + memset(&unspec, 0, sizeof(unspec)); + ctx.uaddr = (struct sockaddr *)&unspec; + } + cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], &ctx, BPF_PROG_RUN); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 388d4feda3486d8a86cd6b687f502716844c1929..e254526d6744ed622dcdd066358d5559943a14be 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1249,6 +1249,8 @@ bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type, case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UDP4_SENDMSG: + case BPF_CGROUP_UDP6_SENDMSG: return 0; default: return -EINVAL; @@ -1565,6 +1567,8 @@ static int bpf_prog_attach(const union bpf_attr *attr) case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UDP4_SENDMSG: + case BPF_CGROUP_UDP6_SENDMSG: ptype = BPF_PROG_TYPE_CGROUP_SOCK_ADDR; break; case BPF_CGROUP_SOCK_OPS: @@ -1635,6 +1639,8 @@ static int bpf_prog_detach(const union bpf_attr *attr) case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UDP4_SENDMSG: + case BPF_CGROUP_UDP6_SENDMSG: ptype = BPF_PROG_TYPE_CGROUP_SOCK_ADDR; break; case BPF_CGROUP_SOCK_OPS: @@ -1692,6 +1698,8 @@ static int bpf_prog_query(const union bpf_attr *attr, case BPF_CGROUP_INET6_POST_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UDP4_SENDMSG: + case BPF_CGROUP_UDP6_SENDMSG: case BPF_CGROUP_SOCK_OPS: case BPF_CGROUP_DEVICE: break; diff --git a/net/core/filter.c b/net/core/filter.c index acf1f4fb99d1dfdc6d1da1faf5092135c5ac2dd3..24e6ce8be567e6750e4a4e0e3275de4e33860ab5 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5299,6 +5299,7 @@ static bool sock_addr_is_valid_access(int off, int size, switch (prog->expected_attach_type) { case BPF_CGROUP_INET4_BIND: case BPF_CGROUP_INET4_CONNECT: + case BPF_CGROUP_UDP4_SENDMSG: break; default: return false; @@ -5308,6 +5309,24 @@ static bool sock_addr_is_valid_access(int off, int size, switch (prog->expected_attach_type) { case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UDP6_SENDMSG: + break; + default: + return false; + } + break; + case bpf_ctx_range(struct bpf_sock_addr, msg_src_ip4): + switch (prog->expected_attach_type) { + case BPF_CGROUP_UDP4_SENDMSG: + break; + default: + return false; + } + break; + case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0], + msg_src_ip6[3]): + switch (prog->expected_attach_type) { + case BPF_CGROUP_UDP6_SENDMSG: break; default: return false; @@ -5318,6 +5337,9 @@ static bool sock_addr_is_valid_access(int off, int size, switch (off) { case bpf_ctx_range(struct bpf_sock_addr, user_ip4): case bpf_ctx_range_till(struct bpf_sock_addr, user_ip6[0], user_ip6[3]): + case bpf_ctx_range(struct bpf_sock_addr, msg_src_ip4): + case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0], + msg_src_ip6[3]): /* Only narrow read access allowed for now. */ if (type == BPF_READ) { bpf_ctx_record_field_size(info, size_default); @@ -6072,6 +6094,23 @@ static u32 sock_addr_convert_ctx_access(enum bpf_access_type type, *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, SK_FL_PROTO_SHIFT); break; + + case offsetof(struct bpf_sock_addr, msg_src_ip4): + /* Treat t_ctx as struct in_addr for msg_src_ip4. */ + SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( + struct bpf_sock_addr_kern, struct in_addr, t_ctx, + s_addr, BPF_SIZE(si->code), 0, tmp_reg); + break; + + case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0], + msg_src_ip6[3]): + off = si->off; + off -= offsetof(struct bpf_sock_addr, msg_src_ip6[0]); + /* Treat t_ctx as struct in6_addr for msg_src_ip6. */ + SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF( + struct bpf_sock_addr_kern, struct in6_addr, t_ctx, + s6_addr32[0], BPF_SIZE(si->code), off, tmp_reg); + break; } return insn - insn_buf; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index d71f1f3e11555af02f1b04a865d3aaba3a8be406..3c27d00b57308bf1dd59ff5eac746798fa3511bc 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -901,6 +901,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct inet_sock *inet = inet_sk(sk); struct udp_sock *up = udp_sk(sk); + DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name); struct flowi4 fl4_stack; struct flowi4 *fl4; int ulen = len; @@ -955,8 +956,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) /* * Get and verify the address. */ - if (msg->msg_name) { - DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name); + if (usin) { if (msg->msg_namelen < sizeof(*usin)) return -EINVAL; if (usin->sin_family != AF_INET) { @@ -1010,6 +1010,22 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) rcu_read_unlock(); } + if (cgroup_bpf_enabled && !connected) { + err = BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, + (struct sockaddr *)usin, &ipc.addr); + if (err) + goto out_free; + if (usin) { + if (usin->sin_port == 0) { + /* BPF program set invalid port. Reject it. */ + err = -EINVAL; + goto out_free; + } + daddr = usin->sin_addr.s_addr; + dport = usin->sin_port; + } + } + saddr = ipc.addr; ipc.addr = faddr = daddr; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 426c9d2b418d59ee8bbb5bb8a0735fccd0241dcc..9f729a7b8cf049960f96786590e5834f96837f19 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1316,6 +1316,29 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl6.saddr = np->saddr; fl6.fl6_sport = inet->inet_sport; + if (cgroup_bpf_enabled && !connected) { + err = BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, + (struct sockaddr *)sin6, &fl6.saddr); + if (err) + goto out_no_dst; + if (sin6) { + if (ipv6_addr_v4mapped(&sin6->sin6_addr)) { + /* BPF program rewrote IPv6-only by IPv4-mapped + * IPv6. It's currently unsupported. + */ + err = -ENOTSUPP; + goto out_no_dst; + } + if (sin6->sin6_port == 0) { + /* BPF program set invalid port. Reject it. */ + err = -EINVAL; + goto out_no_dst; + } + fl6.fl6_dport = sin6->sin6_port; + fl6.daddr = sin6->sin6_addr; + } + } + final_p = fl6_update_dst(&fl6, opt, &final); if (final_p) connected = false; @@ -1395,6 +1418,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) out: dst_release(dst); +out_no_dst: fl6_sock_release(flowlabel); txopt_put(opt_to_free); if (!err) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 9b8c6e310e9a9666aefec27c74451954711d6bde..cc68787f2d974d114f268b2c4992961b2fb2a1f2 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -160,6 +160,8 @@ enum bpf_attach_type { BPF_CGROUP_INET6_CONNECT, BPF_CGROUP_INET4_POST_BIND, BPF_CGROUP_INET6_POST_BIND, + BPF_CGROUP_UDP4_SENDMSG, + BPF_CGROUP_UDP6_SENDMSG, __MAX_BPF_ATTACH_TYPE }; @@ -2363,6 +2365,12 @@ struct bpf_sock_addr { __u32 family; /* Allows 4-byte read, but no write */ __u32 type; /* Allows 4-byte read, but no write */ __u32 protocol; /* Allows 4-byte read, but no write */ + __u32 msg_src_ip4; /* Allows 1,2,4-byte read an 4-byte write. + * Stored in network byte order. + */ + __u32 msg_src_ip6[4]; /* Allows 1,2,4-byte read an 4-byte write. + * Stored in network byte order. + */ }; /* User bpf_sock_ops struct to access socket values and specify request ops diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index d20411ebfa2f0b14fd63a5a776205f595e4b4d25..b1a60ac8424ea1cd0edd4214f589099f214a36e9 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -2043,6 +2043,8 @@ static const struct { BPF_SA_PROG_SEC("cgroup/bind6", BPF_CGROUP_INET6_BIND), BPF_SA_PROG_SEC("cgroup/connect4", BPF_CGROUP_INET4_CONNECT), BPF_SA_PROG_SEC("cgroup/connect6", BPF_CGROUP_INET6_CONNECT), + BPF_SA_PROG_SEC("cgroup/sendmsg4", BPF_CGROUP_UDP4_SENDMSG), + BPF_SA_PROG_SEC("cgroup/sendmsg6", BPF_CGROUP_UDP6_SENDMSG), BPF_S_PROG_SEC("cgroup/post_bind4", BPF_CGROUP_INET4_POST_BIND), BPF_S_PROG_SEC("cgroup/post_bind6", BPF_CGROUP_INET6_POST_BIND), }; diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 85044448bbc79548d019502926c7e09eac8b1e12..a1b66da965d0f216fea2d5d472d65d026411efc9 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -34,7 +34,7 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test sockmap_tcp_msg_prog.o connect4_prog.o connect6_prog.o test_adjust_tail.o \ test_btf_haskv.o test_btf_nokv.o test_sockmap_kern.o test_tunnel_kern.o \ test_get_stack_rawtp.o test_sockmap_kern.o test_sockhash_kern.o \ - test_lwt_seg6local.o + test_lwt_seg6local.o sendmsg4_prog.o sendmsg6_prog.o # Order correspond to 'make run_tests' order TEST_PROGS := test_kmod.sh \ diff --git a/tools/testing/selftests/bpf/sendmsg4_prog.c b/tools/testing/selftests/bpf/sendmsg4_prog.c new file mode 100644 index 0000000000000000000000000000000000000000..a91536b1c47e37b7ffcac9d7a23b549708cdf2f5 --- /dev/null +++ b/tools/testing/selftests/bpf/sendmsg4_prog.c @@ -0,0 +1,49 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018 Facebook + +#include +#include +#include + +#include "bpf_helpers.h" +#include "bpf_endian.h" + +#define SRC1_IP4 0xAC100001U /* 172.16.0.1 */ +#define SRC2_IP4 0x00000000U +#define SRC_REWRITE_IP4 0x7f000004U +#define DST_IP4 0xC0A801FEU /* 192.168.1.254 */ +#define DST_REWRITE_IP4 0x7f000001U +#define DST_PORT 4040 +#define DST_REWRITE_PORT4 4444 + +int _version SEC("version") = 1; + +SEC("cgroup/sendmsg4") +int sendmsg_v4_prog(struct bpf_sock_addr *ctx) +{ + if (ctx->type != SOCK_DGRAM) + return 0; + + /* Rewrite source. */ + if (ctx->msg_src_ip4 == bpf_htonl(SRC1_IP4) || + ctx->msg_src_ip4 == bpf_htonl(SRC2_IP4)) { + ctx->msg_src_ip4 = bpf_htonl(SRC_REWRITE_IP4); + } else { + /* Unexpected source. Reject sendmsg. */ + return 0; + } + + /* Rewrite destination. */ + if ((ctx->user_ip4 >> 24) == (bpf_htonl(DST_IP4) >> 24) && + ctx->user_port == bpf_htons(DST_PORT)) { + ctx->user_ip4 = bpf_htonl(DST_REWRITE_IP4); + ctx->user_port = bpf_htons(DST_REWRITE_PORT4); + } else { + /* Unexpected source. Reject sendmsg. */ + return 0; + } + + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/sendmsg6_prog.c b/tools/testing/selftests/bpf/sendmsg6_prog.c new file mode 100644 index 0000000000000000000000000000000000000000..5aeaa284fc47493decf0fc55b31de7c8a734ac6d --- /dev/null +++ b/tools/testing/selftests/bpf/sendmsg6_prog.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018 Facebook + +#include +#include +#include + +#include "bpf_helpers.h" +#include "bpf_endian.h" + +#define SRC_REWRITE_IP6_0 0 +#define SRC_REWRITE_IP6_1 0 +#define SRC_REWRITE_IP6_2 0 +#define SRC_REWRITE_IP6_3 6 + +#define DST_REWRITE_IP6_0 0 +#define DST_REWRITE_IP6_1 0 +#define DST_REWRITE_IP6_2 0 +#define DST_REWRITE_IP6_3 1 + +#define DST_REWRITE_PORT6 6666 + +int _version SEC("version") = 1; + +SEC("cgroup/sendmsg6") +int sendmsg_v6_prog(struct bpf_sock_addr *ctx) +{ + if (ctx->type != SOCK_DGRAM) + return 0; + + /* Rewrite source. */ + if (ctx->msg_src_ip6[3] == bpf_htonl(1) || + ctx->msg_src_ip6[3] == bpf_htonl(0)) { + ctx->msg_src_ip6[0] = bpf_htonl(SRC_REWRITE_IP6_0); + ctx->msg_src_ip6[1] = bpf_htonl(SRC_REWRITE_IP6_1); + ctx->msg_src_ip6[2] = bpf_htonl(SRC_REWRITE_IP6_2); + ctx->msg_src_ip6[3] = bpf_htonl(SRC_REWRITE_IP6_3); + } else { + /* Unexpected source. Reject sendmsg. */ + return 0; + } + + /* Rewrite destination. */ + if ((ctx->user_ip6[0] & 0xFFFF) == bpf_htons(0xFACE) && + ctx->user_ip6[0] >> 16 == bpf_htons(0xB00C)) { + ctx->user_ip6[0] = bpf_htonl(DST_REWRITE_IP6_0); + ctx->user_ip6[1] = bpf_htonl(DST_REWRITE_IP6_1); + ctx->user_ip6[2] = bpf_htonl(DST_REWRITE_IP6_2); + ctx->user_ip6[3] = bpf_htonl(DST_REWRITE_IP6_3); + + ctx->user_port = bpf_htons(DST_REWRITE_PORT6); + } else { + /* Unexpected destination. Reject sendmsg. */ + return 0; + } + + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c index 2950f80ba7fb9f8770cb92bde50003d3c6186e78..a5e76b9219b9d86ab83d92d9f4964fea5d30c915 100644 --- a/tools/testing/selftests/bpf/test_sock_addr.c +++ b/tools/testing/selftests/bpf/test_sock_addr.c @@ -1,12 +1,16 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2018 Facebook +#define _GNU_SOURCE + #include #include #include #include +#include #include +#include #include #include @@ -17,34 +21,465 @@ #include "cgroup_helpers.h" #include "bpf_rlimit.h" +#ifndef ENOTSUPP +# define ENOTSUPP 524 +#endif + +#ifndef ARRAY_SIZE +# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + #define CG_PATH "/foo" #define CONNECT4_PROG_PATH "./connect4_prog.o" #define CONNECT6_PROG_PATH "./connect6_prog.o" +#define SENDMSG4_PROG_PATH "./sendmsg4_prog.o" +#define SENDMSG6_PROG_PATH "./sendmsg6_prog.o" #define SERV4_IP "192.168.1.254" #define SERV4_REWRITE_IP "127.0.0.1" +#define SRC4_IP "172.16.0.1" +#define SRC4_REWRITE_IP "127.0.0.4" #define SERV4_PORT 4040 #define SERV4_REWRITE_PORT 4444 #define SERV6_IP "face:b00c:1234:5678::abcd" #define SERV6_REWRITE_IP "::1" +#define SERV6_V4MAPPED_IP "::ffff:192.168.0.4" +#define SRC6_IP "::1" +#define SRC6_REWRITE_IP "::6" #define SERV6_PORT 6060 #define SERV6_REWRITE_PORT 6666 #define INET_NTOP_BUF 40 -typedef int (*load_fn)(enum bpf_attach_type, const char *comment); +struct sock_addr_test; + +typedef int (*load_fn)(const struct sock_addr_test *test); typedef int (*info_fn)(int, struct sockaddr *, socklen_t *); -struct program { - enum bpf_attach_type type; - load_fn loadfn; - int fd; - const char *name; - enum bpf_attach_type invalid_type; +char bpf_log_buf[BPF_LOG_BUF_SIZE]; + +struct sock_addr_test { + const char *descr; + /* BPF prog properties */ + load_fn loadfn; + enum bpf_attach_type expected_attach_type; + enum bpf_attach_type attach_type; + /* Socket properties */ + int domain; + int type; + /* IP:port pairs for BPF prog to override */ + const char *requested_ip; + unsigned short requested_port; + const char *expected_ip; + unsigned short expected_port; + const char *expected_src_ip; + /* Expected test result */ + enum { + LOAD_REJECT, + ATTACH_REJECT, + SYSCALL_EPERM, + SYSCALL_ENOTSUPP, + SUCCESS, + } expected_result; }; -char bpf_log_buf[BPF_LOG_BUF_SIZE]; +static int bind4_prog_load(const struct sock_addr_test *test); +static int bind6_prog_load(const struct sock_addr_test *test); +static int connect4_prog_load(const struct sock_addr_test *test); +static int connect6_prog_load(const struct sock_addr_test *test); +static int sendmsg_deny_prog_load(const struct sock_addr_test *test); +static int sendmsg4_rw_asm_prog_load(const struct sock_addr_test *test); +static int sendmsg4_rw_c_prog_load(const struct sock_addr_test *test); +static int sendmsg6_rw_asm_prog_load(const struct sock_addr_test *test); +static int sendmsg6_rw_c_prog_load(const struct sock_addr_test *test); +static int sendmsg6_rw_v4mapped_prog_load(const struct sock_addr_test *test); + +static struct sock_addr_test tests[] = { + /* bind */ + { + "bind4: load prog with wrong expected attach type", + bind4_prog_load, + BPF_CGROUP_INET6_BIND, + BPF_CGROUP_INET4_BIND, + AF_INET, + SOCK_STREAM, + NULL, + 0, + NULL, + 0, + NULL, + LOAD_REJECT, + }, + { + "bind4: attach prog with wrong attach type", + bind4_prog_load, + BPF_CGROUP_INET4_BIND, + BPF_CGROUP_INET6_BIND, + AF_INET, + SOCK_STREAM, + NULL, + 0, + NULL, + 0, + NULL, + ATTACH_REJECT, + }, + { + "bind4: rewrite IP & TCP port in", + bind4_prog_load, + BPF_CGROUP_INET4_BIND, + BPF_CGROUP_INET4_BIND, + AF_INET, + SOCK_STREAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + NULL, + SUCCESS, + }, + { + "bind4: rewrite IP & UDP port in", + bind4_prog_load, + BPF_CGROUP_INET4_BIND, + BPF_CGROUP_INET4_BIND, + AF_INET, + SOCK_DGRAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + NULL, + SUCCESS, + }, + { + "bind6: load prog with wrong expected attach type", + bind6_prog_load, + BPF_CGROUP_INET4_BIND, + BPF_CGROUP_INET6_BIND, + AF_INET6, + SOCK_STREAM, + NULL, + 0, + NULL, + 0, + NULL, + LOAD_REJECT, + }, + { + "bind6: attach prog with wrong attach type", + bind6_prog_load, + BPF_CGROUP_INET6_BIND, + BPF_CGROUP_INET4_BIND, + AF_INET, + SOCK_STREAM, + NULL, + 0, + NULL, + 0, + NULL, + ATTACH_REJECT, + }, + { + "bind6: rewrite IP & TCP port in", + bind6_prog_load, + BPF_CGROUP_INET6_BIND, + BPF_CGROUP_INET6_BIND, + AF_INET6, + SOCK_STREAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + NULL, + SUCCESS, + }, + { + "bind6: rewrite IP & UDP port in", + bind6_prog_load, + BPF_CGROUP_INET6_BIND, + BPF_CGROUP_INET6_BIND, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + NULL, + SUCCESS, + }, + + /* connect */ + { + "connect4: load prog with wrong expected attach type", + connect4_prog_load, + BPF_CGROUP_INET6_CONNECT, + BPF_CGROUP_INET4_CONNECT, + AF_INET, + SOCK_STREAM, + NULL, + 0, + NULL, + 0, + NULL, + LOAD_REJECT, + }, + { + "connect4: attach prog with wrong attach type", + connect4_prog_load, + BPF_CGROUP_INET4_CONNECT, + BPF_CGROUP_INET6_CONNECT, + AF_INET, + SOCK_STREAM, + NULL, + 0, + NULL, + 0, + NULL, + ATTACH_REJECT, + }, + { + "connect4: rewrite IP & TCP port", + connect4_prog_load, + BPF_CGROUP_INET4_CONNECT, + BPF_CGROUP_INET4_CONNECT, + AF_INET, + SOCK_STREAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SRC4_REWRITE_IP, + SUCCESS, + }, + { + "connect4: rewrite IP & UDP port", + connect4_prog_load, + BPF_CGROUP_INET4_CONNECT, + BPF_CGROUP_INET4_CONNECT, + AF_INET, + SOCK_DGRAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SRC4_REWRITE_IP, + SUCCESS, + }, + { + "connect6: load prog with wrong expected attach type", + connect6_prog_load, + BPF_CGROUP_INET4_CONNECT, + BPF_CGROUP_INET6_CONNECT, + AF_INET6, + SOCK_STREAM, + NULL, + 0, + NULL, + 0, + NULL, + LOAD_REJECT, + }, + { + "connect6: attach prog with wrong attach type", + connect6_prog_load, + BPF_CGROUP_INET6_CONNECT, + BPF_CGROUP_INET4_CONNECT, + AF_INET, + SOCK_STREAM, + NULL, + 0, + NULL, + 0, + NULL, + ATTACH_REJECT, + }, + { + "connect6: rewrite IP & TCP port", + connect6_prog_load, + BPF_CGROUP_INET6_CONNECT, + BPF_CGROUP_INET6_CONNECT, + AF_INET6, + SOCK_STREAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SUCCESS, + }, + { + "connect6: rewrite IP & UDP port", + connect6_prog_load, + BPF_CGROUP_INET6_CONNECT, + BPF_CGROUP_INET6_CONNECT, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SUCCESS, + }, + + /* sendmsg */ + { + "sendmsg4: load prog with wrong expected attach type", + sendmsg4_rw_asm_prog_load, + BPF_CGROUP_UDP6_SENDMSG, + BPF_CGROUP_UDP4_SENDMSG, + AF_INET, + SOCK_DGRAM, + NULL, + 0, + NULL, + 0, + NULL, + LOAD_REJECT, + }, + { + "sendmsg4: attach prog with wrong attach type", + sendmsg4_rw_asm_prog_load, + BPF_CGROUP_UDP4_SENDMSG, + BPF_CGROUP_UDP6_SENDMSG, + AF_INET, + SOCK_DGRAM, + NULL, + 0, + NULL, + 0, + NULL, + ATTACH_REJECT, + }, + { + "sendmsg4: rewrite IP & port (asm)", + sendmsg4_rw_asm_prog_load, + BPF_CGROUP_UDP4_SENDMSG, + BPF_CGROUP_UDP4_SENDMSG, + AF_INET, + SOCK_DGRAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SRC4_REWRITE_IP, + SUCCESS, + }, + { + "sendmsg4: rewrite IP & port (C)", + sendmsg4_rw_c_prog_load, + BPF_CGROUP_UDP4_SENDMSG, + BPF_CGROUP_UDP4_SENDMSG, + AF_INET, + SOCK_DGRAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SRC4_REWRITE_IP, + SUCCESS, + }, + { + "sendmsg4: deny call", + sendmsg_deny_prog_load, + BPF_CGROUP_UDP4_SENDMSG, + BPF_CGROUP_UDP4_SENDMSG, + AF_INET, + SOCK_DGRAM, + SERV4_IP, + SERV4_PORT, + SERV4_REWRITE_IP, + SERV4_REWRITE_PORT, + SRC4_REWRITE_IP, + SYSCALL_EPERM, + }, + { + "sendmsg6: load prog with wrong expected attach type", + sendmsg6_rw_asm_prog_load, + BPF_CGROUP_UDP4_SENDMSG, + BPF_CGROUP_UDP6_SENDMSG, + AF_INET6, + SOCK_DGRAM, + NULL, + 0, + NULL, + 0, + NULL, + LOAD_REJECT, + }, + { + "sendmsg6: attach prog with wrong attach type", + sendmsg6_rw_asm_prog_load, + BPF_CGROUP_UDP6_SENDMSG, + BPF_CGROUP_UDP4_SENDMSG, + AF_INET6, + SOCK_DGRAM, + NULL, + 0, + NULL, + 0, + NULL, + ATTACH_REJECT, + }, + { + "sendmsg6: rewrite IP & port (asm)", + sendmsg6_rw_asm_prog_load, + BPF_CGROUP_UDP6_SENDMSG, + BPF_CGROUP_UDP6_SENDMSG, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SUCCESS, + }, + { + "sendmsg6: rewrite IP & port (C)", + sendmsg6_rw_c_prog_load, + BPF_CGROUP_UDP6_SENDMSG, + BPF_CGROUP_UDP6_SENDMSG, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SUCCESS, + }, + { + "sendmsg6: IPv4-mapped IPv6", + sendmsg6_rw_v4mapped_prog_load, + BPF_CGROUP_UDP6_SENDMSG, + BPF_CGROUP_UDP6_SENDMSG, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SYSCALL_ENOTSUPP, + }, + { + "sendmsg6: deny call", + sendmsg_deny_prog_load, + BPF_CGROUP_UDP6_SENDMSG, + BPF_CGROUP_UDP6_SENDMSG, + AF_INET6, + SOCK_DGRAM, + SERV6_IP, + SERV6_PORT, + SERV6_REWRITE_IP, + SERV6_REWRITE_PORT, + SRC6_REWRITE_IP, + SYSCALL_EPERM, + }, +}; static int mk_sockaddr(int domain, const char *ip, unsigned short port, struct sockaddr *addr, socklen_t addr_len) @@ -84,25 +519,23 @@ static int mk_sockaddr(int domain, const char *ip, unsigned short port, return 0; } -static int load_insns(enum bpf_attach_type attach_type, - const struct bpf_insn *insns, size_t insns_cnt, - const char *comment) +static int load_insns(const struct sock_addr_test *test, + const struct bpf_insn *insns, size_t insns_cnt) { struct bpf_load_program_attr load_attr; int ret; memset(&load_attr, 0, sizeof(struct bpf_load_program_attr)); load_attr.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR; - load_attr.expected_attach_type = attach_type; + load_attr.expected_attach_type = test->expected_attach_type; load_attr.insns = insns; load_attr.insns_cnt = insns_cnt; load_attr.license = "GPL"; ret = bpf_load_program_xattr(&load_attr, bpf_log_buf, BPF_LOG_BUF_SIZE); - if (ret < 0 && comment) { - log_err(">>> Loading %s program error.\n" - ">>> Output from verifier:\n%s\n-------\n", - comment, bpf_log_buf); + if (ret < 0 && test->expected_result != LOAD_REJECT) { + log_err(">>> Loading program error.\n" + ">>> Verifier output:\n%s\n-------\n", bpf_log_buf); } return ret; @@ -119,8 +552,7 @@ static int load_insns(enum bpf_attach_type attach_type, * to count jumps properly. */ -static int bind4_prog_load(enum bpf_attach_type attach_type, - const char *comment) +static int bind4_prog_load(const struct sock_addr_test *test) { union { uint8_t u4_addr8[4]; @@ -186,12 +618,10 @@ static int bind4_prog_load(enum bpf_attach_type attach_type, BPF_EXIT_INSN(), }; - return load_insns(attach_type, insns, - sizeof(insns) / sizeof(struct bpf_insn), comment); + return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn)); } -static int bind6_prog_load(enum bpf_attach_type attach_type, - const char *comment) +static int bind6_prog_load(const struct sock_addr_test *test) { struct sockaddr_in6 addr6_rw; struct in6_addr ip6; @@ -254,13 +684,10 @@ static int bind6_prog_load(enum bpf_attach_type attach_type, BPF_EXIT_INSN(), }; - return load_insns(attach_type, insns, - sizeof(insns) / sizeof(struct bpf_insn), comment); + return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn)); } -static int connect_prog_load_path(const char *path, - enum bpf_attach_type attach_type, - const char *comment) +static int load_path(const struct sock_addr_test *test, const char *path) { struct bpf_prog_load_attr attr; struct bpf_object *obj; @@ -269,75 +696,218 @@ static int connect_prog_load_path(const char *path, memset(&attr, 0, sizeof(struct bpf_prog_load_attr)); attr.file = path; attr.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR; - attr.expected_attach_type = attach_type; + attr.expected_attach_type = test->expected_attach_type; if (bpf_prog_load_xattr(&attr, &obj, &prog_fd)) { - if (comment) - log_err(">>> Loading %s program at %s error.\n", - comment, path); + if (test->expected_result != LOAD_REJECT) + log_err(">>> Loading program (%s) error.\n", path); return -1; } return prog_fd; } -static int connect4_prog_load(enum bpf_attach_type attach_type, - const char *comment) +static int connect4_prog_load(const struct sock_addr_test *test) { - return connect_prog_load_path(CONNECT4_PROG_PATH, attach_type, comment); + return load_path(test, CONNECT4_PROG_PATH); } -static int connect6_prog_load(enum bpf_attach_type attach_type, - const char *comment) +static int connect6_prog_load(const struct sock_addr_test *test) { - return connect_prog_load_path(CONNECT6_PROG_PATH, attach_type, comment); + return load_path(test, CONNECT6_PROG_PATH); } -static void print_ip_port(int sockfd, info_fn fn, const char *fmt) +static int sendmsg_deny_prog_load(const struct sock_addr_test *test) { - char addr_buf[INET_NTOP_BUF]; - struct sockaddr_storage addr; - struct sockaddr_in6 *addr6; - struct sockaddr_in *addr4; - socklen_t addr_len; - unsigned short port; - void *nip; - - addr_len = sizeof(struct sockaddr_storage); - memset(&addr, 0, addr_len); - - if (fn(sockfd, (struct sockaddr *)&addr, (socklen_t *)&addr_len) == 0) { - if (addr.ss_family == AF_INET) { - addr4 = (struct sockaddr_in *)&addr; - nip = (void *)&addr4->sin_addr; - port = ntohs(addr4->sin_port); - } else if (addr.ss_family == AF_INET6) { - addr6 = (struct sockaddr_in6 *)&addr; - nip = (void *)&addr6->sin6_addr; - port = ntohs(addr6->sin6_port); - } else { - return; - } - const char *addr_str = - inet_ntop(addr.ss_family, nip, addr_buf, INET_NTOP_BUF); - printf(fmt, addr_str ? addr_str : "??", port); + struct bpf_insn insns[] = { + /* return 0 */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn)); +} + +static int sendmsg4_rw_asm_prog_load(const struct sock_addr_test *test) +{ + struct sockaddr_in dst4_rw_addr; + struct in_addr src4_rw_ip; + + if (inet_pton(AF_INET, SRC4_REWRITE_IP, (void *)&src4_rw_ip) != 1) { + log_err("Invalid IPv4: %s", SRC4_REWRITE_IP); + return -1; + } + + if (mk_sockaddr(AF_INET, SERV4_REWRITE_IP, SERV4_REWRITE_PORT, + (struct sockaddr *)&dst4_rw_addr, + sizeof(dst4_rw_addr)) == -1) + return -1; + + struct bpf_insn insns[] = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + + /* if (sk.family == AF_INET && */ + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, + offsetof(struct bpf_sock_addr, family)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET, 8), + + /* sk.type == SOCK_DGRAM) { */ + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, + offsetof(struct bpf_sock_addr, type)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_DGRAM, 6), + + /* msg_src_ip4 = src4_rw_ip */ + BPF_MOV32_IMM(BPF_REG_7, src4_rw_ip.s_addr), + BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7, + offsetof(struct bpf_sock_addr, msg_src_ip4)), + + /* user_ip4 = dst4_rw_addr.sin_addr */ + BPF_MOV32_IMM(BPF_REG_7, dst4_rw_addr.sin_addr.s_addr), + BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7, + offsetof(struct bpf_sock_addr, user_ip4)), + + /* user_port = dst4_rw_addr.sin_port */ + BPF_MOV32_IMM(BPF_REG_7, dst4_rw_addr.sin_port), + BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7, + offsetof(struct bpf_sock_addr, user_port)), + /* } */ + + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }; + + return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn)); +} + +static int sendmsg4_rw_c_prog_load(const struct sock_addr_test *test) +{ + return load_path(test, SENDMSG4_PROG_PATH); +} + +static int sendmsg6_rw_dst_asm_prog_load(const struct sock_addr_test *test, + const char *rw_dst_ip) +{ + struct sockaddr_in6 dst6_rw_addr; + struct in6_addr src6_rw_ip; + + if (inet_pton(AF_INET6, SRC6_REWRITE_IP, (void *)&src6_rw_ip) != 1) { + log_err("Invalid IPv6: %s", SRC6_REWRITE_IP); + return -1; + } + + if (mk_sockaddr(AF_INET6, rw_dst_ip, SERV6_REWRITE_PORT, + (struct sockaddr *)&dst6_rw_addr, + sizeof(dst6_rw_addr)) == -1) + return -1; + + struct bpf_insn insns[] = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + + /* if (sk.family == AF_INET6) { */ + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, + offsetof(struct bpf_sock_addr, family)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET6, 18), + +#define STORE_IPV6_WORD_N(DST, SRC, N) \ + BPF_MOV32_IMM(BPF_REG_7, SRC[N]), \ + BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7, \ + offsetof(struct bpf_sock_addr, DST[N])) + +#define STORE_IPV6(DST, SRC) \ + STORE_IPV6_WORD_N(DST, SRC, 0), \ + STORE_IPV6_WORD_N(DST, SRC, 1), \ + STORE_IPV6_WORD_N(DST, SRC, 2), \ + STORE_IPV6_WORD_N(DST, SRC, 3) + + STORE_IPV6(msg_src_ip6, src6_rw_ip.s6_addr32), + STORE_IPV6(user_ip6, dst6_rw_addr.sin6_addr.s6_addr32), + + /* user_port = dst6_rw_addr.sin6_port */ + BPF_MOV32_IMM(BPF_REG_7, dst6_rw_addr.sin6_port), + BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7, + offsetof(struct bpf_sock_addr, user_port)), + + /* } */ + + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }; + + return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn)); +} + +static int sendmsg6_rw_asm_prog_load(const struct sock_addr_test *test) +{ + return sendmsg6_rw_dst_asm_prog_load(test, SERV6_REWRITE_IP); +} + +static int sendmsg6_rw_v4mapped_prog_load(const struct sock_addr_test *test) +{ + return sendmsg6_rw_dst_asm_prog_load(test, SERV6_V4MAPPED_IP); +} + +static int sendmsg6_rw_c_prog_load(const struct sock_addr_test *test) +{ + return load_path(test, SENDMSG6_PROG_PATH); +} + +static int cmp_addr(const struct sockaddr_storage *addr1, + const struct sockaddr_storage *addr2, int cmp_port) +{ + const struct sockaddr_in *four1, *four2; + const struct sockaddr_in6 *six1, *six2; + + if (addr1->ss_family != addr2->ss_family) + return -1; + + if (addr1->ss_family == AF_INET) { + four1 = (const struct sockaddr_in *)addr1; + four2 = (const struct sockaddr_in *)addr2; + return !((four1->sin_port == four2->sin_port || !cmp_port) && + four1->sin_addr.s_addr == four2->sin_addr.s_addr); + } else if (addr1->ss_family == AF_INET6) { + six1 = (const struct sockaddr_in6 *)addr1; + six2 = (const struct sockaddr_in6 *)addr2; + return !((six1->sin6_port == six2->sin6_port || !cmp_port) && + !memcmp(&six1->sin6_addr, &six2->sin6_addr, + sizeof(struct in6_addr))); } + + return -1; } -static void print_local_ip_port(int sockfd, const char *fmt) +static int cmp_sock_addr(info_fn fn, int sock1, + const struct sockaddr_storage *addr2, int cmp_port) { - print_ip_port(sockfd, getsockname, fmt); + struct sockaddr_storage addr1; + socklen_t len1 = sizeof(addr1); + + memset(&addr1, 0, len1); + if (fn(sock1, (struct sockaddr *)&addr1, (socklen_t *)&len1) != 0) + return -1; + + return cmp_addr(&addr1, addr2, cmp_port); +} + +static int cmp_local_ip(int sock1, const struct sockaddr_storage *addr2) +{ + return cmp_sock_addr(getsockname, sock1, addr2, /*cmp_port*/ 0); } -static void print_remote_ip_port(int sockfd, const char *fmt) +static int cmp_local_addr(int sock1, const struct sockaddr_storage *addr2) { - print_ip_port(sockfd, getpeername, fmt); + return cmp_sock_addr(getsockname, sock1, addr2, /*cmp_port*/ 1); +} + +static int cmp_peer_addr(int sock1, const struct sockaddr_storage *addr2) +{ + return cmp_sock_addr(getpeername, sock1, addr2, /*cmp_port*/ 1); } static int start_server(int type, const struct sockaddr_storage *addr, socklen_t addr_len) { - int fd; fd = socket(addr->ss_family, type, 0); @@ -358,8 +928,6 @@ static int start_server(int type, const struct sockaddr_storage *addr, } } - print_local_ip_port(fd, "\t Actual: bind(%s, %d)\n"); - goto out; close_out: close(fd); @@ -372,19 +940,19 @@ static int connect_to_server(int type, const struct sockaddr_storage *addr, socklen_t addr_len) { int domain; - int fd; + int fd = -1; domain = addr->ss_family; if (domain != AF_INET && domain != AF_INET6) { log_err("Unsupported address family"); - return -1; + goto err; } fd = socket(domain, type, 0); if (fd == -1) { - log_err("Failed to creating client socket"); - return -1; + log_err("Failed to create client socket"); + goto err; } if (connect(fd, (const struct sockaddr *)addr, addr_len) == -1) { @@ -392,162 +960,394 @@ static int connect_to_server(int type, const struct sockaddr_storage *addr, goto err; } - print_remote_ip_port(fd, "\t Actual: connect(%s, %d)"); - print_local_ip_port(fd, " from (%s, %d)\n"); + goto out; +err: + close(fd); + fd = -1; +out: + return fd; +} + +int init_pktinfo(int domain, struct cmsghdr *cmsg) +{ + struct in6_pktinfo *pktinfo6; + struct in_pktinfo *pktinfo4; + + if (domain == AF_INET) { + cmsg->cmsg_level = SOL_IP; + cmsg->cmsg_type = IP_PKTINFO; + cmsg->cmsg_len = CMSG_LEN(sizeof(struct in_pktinfo)); + pktinfo4 = (struct in_pktinfo *)CMSG_DATA(cmsg); + memset(pktinfo4, 0, sizeof(struct in_pktinfo)); + if (inet_pton(domain, SRC4_IP, + (void *)&pktinfo4->ipi_spec_dst) != 1) + return -1; + } else if (domain == AF_INET6) { + cmsg->cmsg_level = SOL_IPV6; + cmsg->cmsg_type = IPV6_PKTINFO; + cmsg->cmsg_len = CMSG_LEN(sizeof(struct in6_pktinfo)); + pktinfo6 = (struct in6_pktinfo *)CMSG_DATA(cmsg); + memset(pktinfo6, 0, sizeof(struct in6_pktinfo)); + if (inet_pton(domain, SRC6_IP, + (void *)&pktinfo6->ipi6_addr) != 1) + return -1; + } else { + return -1; + } return 0; +} + +static int sendmsg_to_server(const struct sockaddr_storage *addr, + socklen_t addr_len, int set_cmsg, int *syscall_err) +{ + union { + char buf[CMSG_SPACE(sizeof(struct in6_pktinfo))]; + struct cmsghdr align; + } control6; + union { + char buf[CMSG_SPACE(sizeof(struct in_pktinfo))]; + struct cmsghdr align; + } control4; + struct msghdr hdr; + struct iovec iov; + char data = 'a'; + int domain; + int fd = -1; + + domain = addr->ss_family; + + if (domain != AF_INET && domain != AF_INET6) { + log_err("Unsupported address family"); + goto err; + } + + fd = socket(domain, SOCK_DGRAM, 0); + if (fd == -1) { + log_err("Failed to create client socket"); + goto err; + } + + memset(&iov, 0, sizeof(iov)); + iov.iov_base = &data; + iov.iov_len = sizeof(data); + + memset(&hdr, 0, sizeof(hdr)); + hdr.msg_name = (void *)addr; + hdr.msg_namelen = addr_len; + hdr.msg_iov = &iov; + hdr.msg_iovlen = 1; + + if (set_cmsg) { + if (domain == AF_INET) { + hdr.msg_control = &control4; + hdr.msg_controllen = sizeof(control4.buf); + } else if (domain == AF_INET6) { + hdr.msg_control = &control6; + hdr.msg_controllen = sizeof(control6.buf); + } + if (init_pktinfo(domain, CMSG_FIRSTHDR(&hdr))) { + log_err("Fail to init pktinfo"); + goto err; + } + } + + if (sendmsg(fd, &hdr, 0) != sizeof(data)) { + log_err("Fail to send message to server"); + *syscall_err = errno; + goto err; + } + + goto out; err: close(fd); - return -1; + fd = -1; +out: + return fd; } -static void print_test_case_num(int domain, int type) +static int recvmsg_from_client(int sockfd, struct sockaddr_storage *src_addr) { - static int test_num; - - printf("Test case #%d (%s/%s):\n", ++test_num, - (domain == AF_INET ? "IPv4" : - domain == AF_INET6 ? "IPv6" : - "unknown_domain"), - (type == SOCK_STREAM ? "TCP" : - type == SOCK_DGRAM ? "UDP" : - "unknown_type")); + struct timeval tv; + struct msghdr hdr; + struct iovec iov; + char data[64]; + fd_set rfds; + + FD_ZERO(&rfds); + FD_SET(sockfd, &rfds); + + tv.tv_sec = 2; + tv.tv_usec = 0; + + if (select(sockfd + 1, &rfds, NULL, NULL, &tv) <= 0 || + !FD_ISSET(sockfd, &rfds)) + return -1; + + memset(&iov, 0, sizeof(iov)); + iov.iov_base = data; + iov.iov_len = sizeof(data); + + memset(&hdr, 0, sizeof(hdr)); + hdr.msg_name = src_addr; + hdr.msg_namelen = sizeof(struct sockaddr_storage); + hdr.msg_iov = &iov; + hdr.msg_iovlen = 1; + + return recvmsg(sockfd, &hdr, 0); } -static int run_test_case(int domain, int type, const char *ip, - unsigned short port) +static int init_addrs(const struct sock_addr_test *test, + struct sockaddr_storage *requested_addr, + struct sockaddr_storage *expected_addr, + struct sockaddr_storage *expected_src_addr) { - struct sockaddr_storage addr; - socklen_t addr_len = sizeof(addr); + socklen_t addr_len = sizeof(struct sockaddr_storage); + + if (mk_sockaddr(test->domain, test->expected_ip, test->expected_port, + (struct sockaddr *)expected_addr, addr_len) == -1) + goto err; + + if (mk_sockaddr(test->domain, test->requested_ip, test->requested_port, + (struct sockaddr *)requested_addr, addr_len) == -1) + goto err; + + if (test->expected_src_ip && + mk_sockaddr(test->domain, test->expected_src_ip, 0, + (struct sockaddr *)expected_src_addr, addr_len) == -1) + goto err; + + return 0; +err: + return -1; +} + +static int run_bind_test_case(const struct sock_addr_test *test) +{ + socklen_t addr_len = sizeof(struct sockaddr_storage); + struct sockaddr_storage requested_addr; + struct sockaddr_storage expected_addr; + int clientfd = -1; int servfd = -1; int err = 0; - print_test_case_num(domain, type); - - if (mk_sockaddr(domain, ip, port, (struct sockaddr *)&addr, - addr_len) == -1) - return -1; + if (init_addrs(test, &requested_addr, &expected_addr, NULL)) + goto err; - printf("\tRequested: bind(%s, %d) ..\n", ip, port); - servfd = start_server(type, &addr, addr_len); + servfd = start_server(test->type, &requested_addr, addr_len); if (servfd == -1) goto err; - printf("\tRequested: connect(%s, %d) from (*, *) ..\n", ip, port); - if (connect_to_server(type, &addr, addr_len)) + if (cmp_local_addr(servfd, &expected_addr)) + goto err; + + /* Try to connect to server just in case */ + clientfd = connect_to_server(test->type, &expected_addr, addr_len); + if (clientfd == -1) goto err; goto out; err: err = -1; out: + close(clientfd); close(servfd); return err; } -static void close_progs_fds(struct program *progs, size_t prog_cnt) +static int run_connect_test_case(const struct sock_addr_test *test) { - size_t i; + socklen_t addr_len = sizeof(struct sockaddr_storage); + struct sockaddr_storage expected_src_addr; + struct sockaddr_storage requested_addr; + struct sockaddr_storage expected_addr; + int clientfd = -1; + int servfd = -1; + int err = 0; - for (i = 0; i < prog_cnt; ++i) { - close(progs[i].fd); - progs[i].fd = -1; - } + if (init_addrs(test, &requested_addr, &expected_addr, + &expected_src_addr)) + goto err; + + /* Prepare server to connect to */ + servfd = start_server(test->type, &expected_addr, addr_len); + if (servfd == -1) + goto err; + + clientfd = connect_to_server(test->type, &requested_addr, addr_len); + if (clientfd == -1) + goto err; + + /* Make sure src and dst addrs were overridden properly */ + if (cmp_peer_addr(clientfd, &expected_addr)) + goto err; + + if (cmp_local_ip(clientfd, &expected_src_addr)) + goto err; + + goto out; +err: + err = -1; +out: + close(clientfd); + close(servfd); + return err; } -static int load_and_attach_progs(int cgfd, struct program *progs, - size_t prog_cnt) +static int run_sendmsg_test_case(const struct sock_addr_test *test) { - size_t i; - - for (i = 0; i < prog_cnt; ++i) { - printf("Load %s with invalid type (can pollute stderr) ", - progs[i].name); - fflush(stdout); - progs[i].fd = progs[i].loadfn(progs[i].invalid_type, NULL); - if (progs[i].fd != -1) { - log_err("Load with invalid type accepted for %s", - progs[i].name); - goto err; - } - printf("... REJECTED\n"); + socklen_t addr_len = sizeof(struct sockaddr_storage); + struct sockaddr_storage expected_src_addr; + struct sockaddr_storage requested_addr; + struct sockaddr_storage expected_addr; + struct sockaddr_storage real_src_addr; + int clientfd = -1; + int servfd = -1; + int set_cmsg; + int err = 0; + + if (test->type != SOCK_DGRAM) + goto err; - printf("Load %s with valid type", progs[i].name); - progs[i].fd = progs[i].loadfn(progs[i].type, progs[i].name); - if (progs[i].fd == -1) { - log_err("Failed to load program %s", progs[i].name); + if (init_addrs(test, &requested_addr, &expected_addr, + &expected_src_addr)) + goto err; + + /* Prepare server to sendmsg to */ + servfd = start_server(test->type, &expected_addr, addr_len); + if (servfd == -1) + goto err; + + for (set_cmsg = 0; set_cmsg <= 1; ++set_cmsg) { + if (clientfd >= 0) + close(clientfd); + + clientfd = sendmsg_to_server(&requested_addr, addr_len, + set_cmsg, &err); + if (err) + goto out; + else if (clientfd == -1) goto err; - } - printf(" ... OK\n"); - printf("Attach %s with invalid type", progs[i].name); - if (bpf_prog_attach(progs[i].fd, cgfd, progs[i].invalid_type, - BPF_F_ALLOW_OVERRIDE) != -1) { - log_err("Attach with invalid type accepted for %s", - progs[i].name); + /* Try to receive message on server instead of using + * getpeername(2) on client socket, to check that client's + * destination address was rewritten properly, since + * getpeername(2) doesn't work with unconnected datagram + * sockets. + * + * Get source address from recvmsg(2) as well to make sure + * source was rewritten properly: getsockname(2) can't be used + * since socket is unconnected and source defined for one + * specific packet may differ from the one used by default and + * returned by getsockname(2). + */ + if (recvmsg_from_client(servfd, &real_src_addr) == -1) goto err; - } - printf(" ... REJECTED\n"); - printf("Attach %s with valid type", progs[i].name); - if (bpf_prog_attach(progs[i].fd, cgfd, progs[i].type, - BPF_F_ALLOW_OVERRIDE) == -1) { - log_err("Failed to attach program %s", progs[i].name); + if (cmp_addr(&real_src_addr, &expected_src_addr, /*cmp_port*/0)) goto err; - } - printf(" ... OK\n"); } - return 0; + goto out; err: - close_progs_fds(progs, prog_cnt); - return -1; + err = -1; +out: + close(clientfd); + close(servfd); + return err; } -static int run_domain_test(int domain, int cgfd, struct program *progs, - size_t prog_cnt, const char *ip, unsigned short port) +static int run_test_case(int cgfd, const struct sock_addr_test *test) { + int progfd = -1; int err = 0; - if (load_and_attach_progs(cgfd, progs, prog_cnt) == -1) + printf("Test case: %s .. ", test->descr); + + progfd = test->loadfn(test); + if (test->expected_result == LOAD_REJECT && progfd < 0) + goto out; + else if (test->expected_result == LOAD_REJECT || progfd < 0) + goto err; + + err = bpf_prog_attach(progfd, cgfd, test->attach_type, + BPF_F_ALLOW_OVERRIDE); + if (test->expected_result == ATTACH_REJECT && err) { + err = 0; /* error was expected, reset it */ + goto out; + } else if (test->expected_result == ATTACH_REJECT || err) { goto err; + } - if (run_test_case(domain, SOCK_STREAM, ip, port) == -1) + switch (test->attach_type) { + case BPF_CGROUP_INET4_BIND: + case BPF_CGROUP_INET6_BIND: + err = run_bind_test_case(test); + break; + case BPF_CGROUP_INET4_CONNECT: + case BPF_CGROUP_INET6_CONNECT: + err = run_connect_test_case(test); + break; + case BPF_CGROUP_UDP4_SENDMSG: + case BPF_CGROUP_UDP6_SENDMSG: + err = run_sendmsg_test_case(test); + break; + default: goto err; + } + + if (test->expected_result == SYSCALL_EPERM && err == EPERM) { + err = 0; /* error was expected, reset it */ + goto out; + } + + if (test->expected_result == SYSCALL_ENOTSUPP && err == ENOTSUPP) { + err = 0; /* error was expected, reset it */ + goto out; + } - if (run_test_case(domain, SOCK_DGRAM, ip, port) == -1) + if (err || test->expected_result != SUCCESS) goto err; goto out; err: err = -1; out: - close_progs_fds(progs, prog_cnt); + /* Detaching w/o checking return code: best effort attempt. */ + if (progfd != -1) + bpf_prog_detach(cgfd, test->attach_type); + close(progfd); + printf("[%s]\n", err ? "FAIL" : "PASS"); return err; } -static int run_test(void) +static int run_tests(int cgfd) +{ + int passes = 0; + int fails = 0; + int i; + + for (i = 0; i < ARRAY_SIZE(tests); ++i) { + if (run_test_case(cgfd, &tests[i])) + ++fails; + else + ++passes; + } + printf("Summary: %d PASSED, %d FAILED\n", passes, fails); + return fails ? -1 : 0; +} + +int main(int argc, char **argv) { - size_t inet6_prog_cnt; - size_t inet_prog_cnt; int cgfd = -1; int err = 0; - struct program inet6_progs[] = { - {BPF_CGROUP_INET6_BIND, bind6_prog_load, -1, "bind6", - BPF_CGROUP_INET4_BIND}, - {BPF_CGROUP_INET6_CONNECT, connect6_prog_load, -1, "connect6", - BPF_CGROUP_INET4_CONNECT}, - }; - inet6_prog_cnt = sizeof(inet6_progs) / sizeof(struct program); - - struct program inet_progs[] = { - {BPF_CGROUP_INET4_BIND, bind4_prog_load, -1, "bind4", - BPF_CGROUP_INET6_BIND}, - {BPF_CGROUP_INET4_CONNECT, connect4_prog_load, -1, "connect4", - BPF_CGROUP_INET6_CONNECT}, - }; - inet_prog_cnt = sizeof(inet_progs) / sizeof(struct program); + if (argc < 2) { + fprintf(stderr, + "%s has to be run via %s.sh. Skip direct run.\n", + argv[0], argv[0]); + exit(err); + } if (setup_cgroup_environment()) goto err; @@ -559,12 +1359,7 @@ static int run_test(void) if (join_cgroup(CG_PATH)) goto err; - if (run_domain_test(AF_INET, cgfd, inet_progs, inet_prog_cnt, SERV4_IP, - SERV4_PORT) == -1) - goto err; - - if (run_domain_test(AF_INET6, cgfd, inet6_progs, inet6_prog_cnt, - SERV6_IP, SERV6_PORT) == -1) + if (run_tests(cgfd)) goto err; goto out; @@ -573,17 +1368,5 @@ static int run_test(void) out: close(cgfd); cleanup_cgroup_environment(); - printf(err ? "### FAIL\n" : "### SUCCESS\n"); return err; } - -int main(int argc, char **argv) -{ - if (argc < 2) { - fprintf(stderr, - "%s has to be run via %s.sh. Skip direct run.\n", - argv[0], argv[0]); - exit(0); - } - return run_test(); -}