From dab4e1f06cabb6834de14264394ccab197007302 Mon Sep 17 00:00:00 2001 From: Martynas Pumputis Date: Sat, 7 Oct 2023 10:14:14 +0200 Subject: bpf: Derive source IP addr via bpf_*_fib_lookup() Extend the bpf_fib_lookup() helper by making it to return the source IPv4/IPv6 address if the BPF_FIB_LOOKUP_SRC flag is set. For example, the following snippet can be used to derive the desired source IP address: struct bpf_fib_lookup p = { .ipv4_dst = ip4->daddr }; ret = bpf_skb_fib_lookup(skb, p, sizeof(p), BPF_FIB_LOOKUP_SRC | BPF_FIB_LOOKUP_SKIP_NEIGH); if (ret != BPF_FIB_LKUP_RET_SUCCESS) return TC_ACT_SHOT; /* the p.ipv4_src now contains the source address */ The inability to derive the proper source address may cause malfunctions in BPF-based dataplanes for hosts containing netdevs with more than one routable IP address or for multi-homed hosts. For example, Cilium implements packet masquerading in BPF. If an egressing netdev to which the Cilium's BPF prog is attached has multiple IP addresses, then only one [hardcoded] IP address can be used for masquerading. This breaks connectivity if any other IP address should have been selected instead, for example, when a public and private addresses are attached to the same egress interface. The change was tested with Cilium [1]. Nikolay Aleksandrov helped to figure out the IPv6 addr selection. [1]: https://github.com/cilium/cilium/pull/28283 Signed-off-by: Martynas Pumputis Link: https://lore.kernel.org/r/20231007081415.33502-2-m@lambda.lt Signed-off-by: Martin KaFai Lau --- net/core/filter.c | 18 +++++++++++++++++- net/ipv6/af_inet6.c | 1 + 2 files changed, 18 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/core/filter.c b/net/core/filter.c index a094694899c9..3880bf0b740d 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5850,6 +5850,9 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, params->rt_metric = res.fi->fib_priority; params->ifindex = dev->ifindex; + if (flags & BPF_FIB_LOOKUP_SRC) + params->ipv4_src = fib_result_prefsrc(net, &res); + /* xdp and cls_bpf programs are run in RCU-bh so * rcu_read_lock_bh is not needed here */ @@ -5992,6 +5995,18 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, params->rt_metric = res.f6i->fib6_metric; params->ifindex = dev->ifindex; + if (flags & BPF_FIB_LOOKUP_SRC) { + if (res.f6i->fib6_prefsrc.plen) { + *src = res.f6i->fib6_prefsrc.addr; + } else { + err = ipv6_bpf_stub->ipv6_dev_get_saddr(net, dev, + &fl6.daddr, 0, + src); + if (err) + return BPF_FIB_LKUP_RET_NO_SRC_ADDR; + } + } + if (flags & BPF_FIB_LOOKUP_SKIP_NEIGH) goto set_fwd_params; @@ -6010,7 +6025,8 @@ set_fwd_params: #endif #define BPF_FIB_LOOKUP_MASK (BPF_FIB_LOOKUP_DIRECT | BPF_FIB_LOOKUP_OUTPUT | \ - BPF_FIB_LOOKUP_SKIP_NEIGH | BPF_FIB_LOOKUP_TBID) + BPF_FIB_LOOKUP_SKIP_NEIGH | BPF_FIB_LOOKUP_TBID | \ + BPF_FIB_LOOKUP_SRC) BPF_CALL_4(bpf_xdp_fib_lookup, struct xdp_buff *, ctx, struct bpf_fib_lookup *, params, int, plen, u32, flags) diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index c6ad0d6e99b5..6337fb4504fd 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -1061,6 +1061,7 @@ static const struct ipv6_bpf_stub ipv6_bpf_stub_impl = { .udp6_lib_lookup = __udp6_lib_lookup, .ipv6_setsockopt = do_ipv6_setsockopt, .ipv6_getsockopt = do_ipv6_getsockopt, + .ipv6_dev_get_saddr = ipv6_dev_get_saddr, }; static int __init inet6_init(void) -- cgit v1.2.3 From fefba7d1ae198dcbf8b3b432de46a4e29f8dbd8c Mon Sep 17 00:00:00 2001 From: Daan De Meyer Date: Wed, 11 Oct 2023 20:51:04 +0200 Subject: bpf: Propagate modified uaddrlen from cgroup sockaddr programs As prep for adding unix socket support to the cgroup sockaddr hooks, let's propagate the sockaddr length back to the caller after running a bpf cgroup sockaddr hook program. While not important for AF_INET or AF_INET6, the sockaddr length is important when working with AF_UNIX sockaddrs as the size of the sockaddr cannot be determined just from the address family or the sockaddr's contents. __cgroup_bpf_run_filter_sock_addr() is modified to take the uaddrlen as an input/output argument. After running the program, the modified sockaddr length is stored in the uaddrlen pointer. Signed-off-by: Daan De Meyer Link: https://lore.kernel.org/r/20231011185113.140426-3-daan.j.demeyer@gmail.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf-cgroup.h | 73 +++++++++++++++++++++++----------------------- include/linux/filter.h | 1 + kernel/bpf/cgroup.c | 17 +++++++++-- net/ipv4/af_inet.c | 7 +++-- net/ipv4/ping.c | 2 +- net/ipv4/tcp_ipv4.c | 2 +- net/ipv4/udp.c | 9 ++++-- net/ipv6/af_inet6.c | 9 +++--- net/ipv6/ping.c | 2 +- net/ipv6/tcp_ipv6.c | 2 +- net/ipv6/udp.c | 6 ++-- 11 files changed, 76 insertions(+), 54 deletions(-) (limited to 'net') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 8506690dbb9c..31561e789715 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -120,6 +120,7 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk, int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, struct sockaddr *uaddr, + int *uaddrlen, enum cgroup_bpf_attach_type atype, void *t_ctx, u32 *flags); @@ -230,22 +231,22 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, #define BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk) \ BPF_CGROUP_RUN_SK_PROG(sk, CGROUP_INET6_POST_BIND) -#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, atype) \ +#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, atype) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(atype)) \ - __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype, \ - NULL, NULL); \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, uaddrlen, \ + atype, NULL, NULL); \ __ret; \ }) -#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, atype, t_ctx) \ +#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, atype, t_ctx) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(atype)) { \ lock_sock(sk); \ - __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype, \ - t_ctx, NULL); \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, uaddrlen, \ + atype, t_ctx, NULL); \ release_sock(sk); \ } \ __ret; \ @@ -256,14 +257,14 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, * (at bit position 0) is to indicate CAP_NET_BIND_SERVICE capability check * should be bypassed (BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE). */ -#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, atype, bind_flags) \ +#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, uaddrlen, atype, bind_flags) \ ({ \ u32 __flags = 0; \ int __ret = 0; \ if (cgroup_bpf_enabled(atype)) { \ lock_sock(sk); \ - __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype, \ - NULL, &__flags); \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, uaddrlen, \ + atype, NULL, &__flags); \ release_sock(sk); \ if (__flags & BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE) \ *bind_flags |= BIND_NO_CAP_NET_BIND_SERVICE; \ @@ -276,29 +277,29 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, cgroup_bpf_enabled(CGROUP_INET6_CONNECT)) && \ (sk)->sk_prot->pre_connect) -#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG(sk, uaddr, CGROUP_INET4_CONNECT) +#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, CGROUP_INET4_CONNECT) -#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG(sk, uaddr, CGROUP_INET6_CONNECT) +#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, CGROUP_INET6_CONNECT) -#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_INET4_CONNECT, NULL) +#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_INET4_CONNECT, NULL) -#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_INET6_CONNECT, NULL) +#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_INET6_CONNECT, NULL) -#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, t_ctx) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP4_SENDMSG, t_ctx) +#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, 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, CGROUP_UDP6_SENDMSG, t_ctx) +#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP6_SENDMSG, t_ctx) -#define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP4_RECVMSG, NULL) +#define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP4_RECVMSG, NULL) -#define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP6_RECVMSG, NULL) +#define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP6_RECVMSG, NULL) /* The SOCK_OPS"_SK" macro should be used when sock_ops->sk is not a * fullsock and its parent fullsock cannot be traced by @@ -477,24 +478,24 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, } #define cgroup_bpf_enabled(atype) (0) -#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, atype, t_ctx) ({ 0; }) -#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, atype) ({ 0; }) +#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, atype, t_ctx) ({ 0; }) +#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, atype) ({ 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; }) #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, atype, flags) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, uaddrlen, atype, flags) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr) ({ 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_UDP4_RECVMSG_LOCK(sk, uaddr) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr, uaddrlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, uaddrlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(atype, major, minor, access) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos) ({ 0; }) diff --git a/include/linux/filter.h b/include/linux/filter.h index ff7ecc89d3dd..bcd2bc15ff56 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1335,6 +1335,7 @@ struct bpf_sock_addr_kern { */ u64 tmp_reg; void *t_ctx; /* Attach type specific context. */ + u32 uaddrlen; }; struct bpf_sock_ops_kern { diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 03b3d4492980..ac37bd53aee0 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1450,6 +1450,9 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); * provided by user sockaddr * @sk: sock struct that will use sockaddr * @uaddr: sockaddr struct provided by user + * @uaddrlen: Pointer to the size of the sockaddr struct provided by user. It is + * read-only for AF_INET[6] uaddr but can be modified for AF_UNIX + * uaddr. * @atype: The type of program to be executed * @t_ctx: Pointer to attach type specific context * @flags: Pointer to u32 which contains higher bits of BPF program @@ -1462,6 +1465,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); */ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, struct sockaddr *uaddr, + int *uaddrlen, enum cgroup_bpf_attach_type atype, void *t_ctx, u32 *flags) @@ -1473,6 +1477,7 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, }; struct sockaddr_storage unspec; struct cgroup *cgrp; + int ret; /* Check socket family since not all sockets represent network * endpoint (e.g. AF_UNIX). @@ -1483,11 +1488,19 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, if (!ctx.uaddr) { memset(&unspec, 0, sizeof(unspec)); ctx.uaddr = (struct sockaddr *)&unspec; + ctx.uaddrlen = 0; + } else { + ctx.uaddrlen = *uaddrlen; } cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); - return bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run, - 0, flags); + ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run, + 0, flags); + + if (!ret && uaddr) + *uaddrlen = ctx.uaddrlen; + + return ret; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_addr); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 3d2e30e20473..7e27ad37b939 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -452,7 +452,7 @@ int inet_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len) /* BPF prog is run before any checks are done so that if the prog * changes context in a wrong way it will be caught. */ - err = BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, + err = BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, &addr_len, CGROUP_INET4_BIND, &flags); if (err) return err; @@ -788,6 +788,7 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr, struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); DECLARE_SOCKADDR(struct sockaddr_in *, sin, uaddr); + int sin_addr_len = sizeof(*sin); sin->sin_family = AF_INET; lock_sock(sk); @@ -800,7 +801,7 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr, } sin->sin_port = inet->inet_dport; sin->sin_addr.s_addr = inet->inet_daddr; - BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, + BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, &sin_addr_len, CGROUP_INET4_GETPEERNAME); } else { __be32 addr = inet->inet_rcv_saddr; @@ -808,7 +809,7 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr, addr = inet->inet_saddr; sin->sin_port = inet->inet_sport; sin->sin_addr.s_addr = addr; - BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, + BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, &sin_addr_len, CGROUP_INET4_GETSOCKNAME); } release_sock(sk); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 4dd809b7b188..2887177822c9 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -301,7 +301,7 @@ static int ping_pre_connect(struct sock *sk, struct sockaddr *uaddr, if (addr_len < sizeof(struct sockaddr_in)) return -EINVAL; - return BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr); + return BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, &addr_len); } /* Checks the bind address and possibly modifies sk->sk_bound_dev_if. */ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index f13eb7e23d03..7c18dd3ce011 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -194,7 +194,7 @@ static int tcp_v4_pre_connect(struct sock *sk, struct sockaddr *uaddr, sock_owned_by_me(sk); - return BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr); + return BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr, &addr_len); } /* This will initiate an outgoing connection. */ diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index c3ff984b6354..7b21a51dd25a 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1143,7 +1143,9 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (cgroup_bpf_enabled(CGROUP_UDP4_SENDMSG) && !connected) { err = BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, - (struct sockaddr *)usin, &ipc.addr); + (struct sockaddr *)usin, + &msg->msg_namelen, + &ipc.addr); if (err) goto out_free; if (usin) { @@ -1865,7 +1867,8 @@ try_again: *addr_len = sizeof(*sin); BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, - (struct sockaddr *)sin); + (struct sockaddr *)sin, + addr_len); } if (udp_test_bit(GRO_ENABLED, sk)) @@ -1904,7 +1907,7 @@ int udp_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (addr_len < sizeof(struct sockaddr_in)) return -EINVAL; - return BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr); + return BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, &addr_len); } EXPORT_SYMBOL(udp_pre_connect); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 6337fb4504fd..c35d302a3da9 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -454,7 +454,7 @@ int inet6_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len) /* BPF prog is run before any checks are done so that if the prog * changes context in a wrong way it will be caught. */ - err = BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, + err = BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, &addr_len, CGROUP_INET6_BIND, &flags); if (err) return err; @@ -520,6 +520,7 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct sockaddr_in6 *sin = (struct sockaddr_in6 *)uaddr; + int sin_addr_len = sizeof(*sin); struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); @@ -539,7 +540,7 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, sin->sin6_addr = sk->sk_v6_daddr; if (inet6_test_bit(SNDFLOW, sk)) sin->sin6_flowinfo = np->flow_label; - BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, + BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, &sin_addr_len, CGROUP_INET6_GETPEERNAME); } else { if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) @@ -547,13 +548,13 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, else sin->sin6_addr = sk->sk_v6_rcv_saddr; sin->sin6_port = inet->inet_sport; - BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, + BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, &sin_addr_len, CGROUP_INET6_GETSOCKNAME); } sin->sin6_scope_id = ipv6_iface_scope_id(&sin->sin6_addr, sk->sk_bound_dev_if); release_sock(sk); - return sizeof(*sin); + return sin_addr_len; } EXPORT_SYMBOL(inet6_getname); diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index e8fb0d275cc2..d2098dd4ceae 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -56,7 +56,7 @@ static int ping_v6_pre_connect(struct sock *sk, struct sockaddr *uaddr, if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; - return BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr); + return BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, &addr_len); } static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 94afb8d0f2d0..3a1e76a2d33e 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -135,7 +135,7 @@ static int tcp_v6_pre_connect(struct sock *sk, struct sockaddr *uaddr, sock_owned_by_me(sk); - return BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr); + return BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, &addr_len); } static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 5e9312eefed0..622b10a549f7 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -410,7 +410,8 @@ try_again: *addr_len = sizeof(*sin6); BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, - (struct sockaddr *)sin6); + (struct sockaddr *)sin6, + addr_len); } if (udp_test_bit(GRO_ENABLED, sk)) @@ -1157,7 +1158,7 @@ static int udpv6_pre_connect(struct sock *sk, struct sockaddr *uaddr, if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; - return BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr); + return BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, &addr_len); } /** @@ -1510,6 +1511,7 @@ do_udp_sendmsg: if (cgroup_bpf_enabled(CGROUP_UDP6_SENDMSG) && !connected) { err = BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, (struct sockaddr *)sin6, + &addr_len, &fl6->saddr); if (err) goto out_no_dst; -- cgit v1.2.3 From 53e380d21441909b12b6e0782b77187ae4b971c4 Mon Sep 17 00:00:00 2001 From: Daan De Meyer Date: Wed, 11 Oct 2023 20:51:05 +0200 Subject: bpf: Add bpf_sock_addr_set_sun_path() to allow writing unix sockaddr from bpf As prep for adding unix socket support to the cgroup sockaddr hooks, let's add a kfunc bpf_sock_addr_set_sun_path() that allows modifying a unix sockaddr from bpf. While this is already possible for AF_INET and AF_INET6, we'll need this kfunc when we add unix socket support since modifying the address for those requires modifying both the address and the sockaddr length. Signed-off-by: Daan De Meyer Link: https://lore.kernel.org/r/20231011185113.140426-4-daan.j.demeyer@gmail.com Signed-off-by: Martin KaFai Lau --- kernel/bpf/btf.c | 1 + net/core/filter.c | 35 ++++++++++++++++++++++++++++++++++- 2 files changed, 35 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 69101200c124..15d71d2986d3 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -7850,6 +7850,7 @@ static int bpf_prog_type_to_kfunc_hook(enum bpf_prog_type prog_type) case BPF_PROG_TYPE_SYSCALL: return BTF_KFUNC_HOOK_SYSCALL; case BPF_PROG_TYPE_CGROUP_SKB: + case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: return BTF_KFUNC_HOOK_CGROUP_SKB; case BPF_PROG_TYPE_SCHED_ACT: return BTF_KFUNC_HOOK_SCHED_ACT; diff --git a/net/core/filter.c b/net/core/filter.c index 3880bf0b740d..ff0bd9f20b95 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -81,6 +81,7 @@ #include #include #include +#include static const struct bpf_func_proto * bpf_sk_base_func_proto(enum bpf_func_id func_id); @@ -11768,6 +11769,27 @@ __bpf_kfunc int bpf_dynptr_from_xdp(struct xdp_buff *xdp, u64 flags, return 0; } + +__bpf_kfunc int bpf_sock_addr_set_sun_path(struct bpf_sock_addr_kern *sa_kern, + const u8 *sun_path, u32 sun_path__sz) +{ + struct sockaddr_un *un; + + if (sa_kern->sk->sk_family != AF_UNIX) + return -EINVAL; + + /* We do not allow changing the address to unnamed or larger than the + * maximum allowed address size for a unix sockaddr. + */ + if (sun_path__sz == 0 || sun_path__sz > UNIX_PATH_MAX) + return -EINVAL; + + un = (struct sockaddr_un *)sa_kern->uaddr; + memcpy(un->sun_path, sun_path, sun_path__sz); + sa_kern->uaddrlen = offsetof(struct sockaddr_un, sun_path) + sun_path__sz; + + return 0; +} __diag_pop(); int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags, @@ -11792,6 +11814,10 @@ BTF_SET8_START(bpf_kfunc_check_set_xdp) BTF_ID_FLAGS(func, bpf_dynptr_from_xdp) BTF_SET8_END(bpf_kfunc_check_set_xdp) +BTF_SET8_START(bpf_kfunc_check_set_sock_addr) +BTF_ID_FLAGS(func, bpf_sock_addr_set_sun_path) +BTF_SET8_END(bpf_kfunc_check_set_sock_addr) + static const struct btf_kfunc_id_set bpf_kfunc_set_skb = { .owner = THIS_MODULE, .set = &bpf_kfunc_check_set_skb, @@ -11802,6 +11828,11 @@ static const struct btf_kfunc_id_set bpf_kfunc_set_xdp = { .set = &bpf_kfunc_check_set_xdp, }; +static const struct btf_kfunc_id_set bpf_kfunc_set_sock_addr = { + .owner = THIS_MODULE, + .set = &bpf_kfunc_check_set_sock_addr, +}; + static int __init bpf_kfunc_init(void) { int ret; @@ -11816,7 +11847,9 @@ static int __init bpf_kfunc_init(void) ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_XMIT, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_SEG6LOCAL, &bpf_kfunc_set_skb); ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_NETFILTER, &bpf_kfunc_set_skb); - return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &bpf_kfunc_set_xdp); + ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &bpf_kfunc_set_xdp); + return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, + &bpf_kfunc_set_sock_addr); } late_initcall(bpf_kfunc_init); -- cgit v1.2.3 From 859051dd165ec6cc915f0f2114699021144fd249 Mon Sep 17 00:00:00 2001 From: Daan De Meyer Date: Wed, 11 Oct 2023 20:51:06 +0200 Subject: bpf: Implement cgroup sockaddr hooks for unix sockets These hooks allows intercepting connect(), getsockname(), getpeername(), sendmsg() and recvmsg() for unix sockets. The unix socket hooks get write access to the address length because the address length is not fixed when dealing with unix sockets and needs to be modified when a unix socket address is modified by the hook. Because abstract socket unix addresses start with a NUL byte, we cannot recalculate the socket address in kernelspace after running the hook by calculating the length of the unix socket path using strlen(). These hooks can be used when users want to multiplex syscall to a single unix socket to multiple different processes behind the scenes by redirecting the connect() and other syscalls to process specific sockets. We do not implement support for intercepting bind() because when using bind() with unix sockets with a pathname address, this creates an inode in the filesystem which must be cleaned up. If we rewrite the address, the user might try to clean up the wrong file, leaking the socket in the filesystem where it is never cleaned up. Until we figure out a solution for this (and a use case for intercepting bind()), we opt to not allow rewriting the sockaddr in bind() calls. We also implement recvmsg() support for connected streams so that after a connect() that is modified by a sockaddr hook, any corresponding recmvsg() on the connected socket can also be modified to make the connected program think it is connected to the "intended" remote. Reviewed-by: Kuniyuki Iwashima Signed-off-by: Daan De Meyer Link: https://lore.kernel.org/r/20231011185113.140426-5-daan.j.demeyer@gmail.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf-cgroup-defs.h | 5 +++++ include/linux/bpf-cgroup.h | 17 +++++++++++++++++ include/uapi/linux/bpf.h | 13 +++++++++---- kernel/bpf/cgroup.c | 11 +++++++++-- kernel/bpf/syscall.c | 15 +++++++++++++++ kernel/bpf/verifier.c | 5 ++++- net/core/filter.c | 14 ++++++++++++-- net/unix/af_unix.c | 35 ++++++++++++++++++++++++++++++++++- tools/include/uapi/linux/bpf.h | 13 +++++++++---- 9 files changed, 114 insertions(+), 14 deletions(-) (limited to 'net') diff --git a/include/linux/bpf-cgroup-defs.h b/include/linux/bpf-cgroup-defs.h index 7b121bd780eb..0985221d5478 100644 --- a/include/linux/bpf-cgroup-defs.h +++ b/include/linux/bpf-cgroup-defs.h @@ -28,19 +28,24 @@ enum cgroup_bpf_attach_type { CGROUP_INET6_BIND, CGROUP_INET4_CONNECT, CGROUP_INET6_CONNECT, + CGROUP_UNIX_CONNECT, CGROUP_INET4_POST_BIND, CGROUP_INET6_POST_BIND, CGROUP_UDP4_SENDMSG, CGROUP_UDP6_SENDMSG, + CGROUP_UNIX_SENDMSG, CGROUP_SYSCTL, CGROUP_UDP4_RECVMSG, CGROUP_UDP6_RECVMSG, + CGROUP_UNIX_RECVMSG, CGROUP_GETSOCKOPT, CGROUP_SETSOCKOPT, CGROUP_INET4_GETPEERNAME, CGROUP_INET6_GETPEERNAME, + CGROUP_UNIX_GETPEERNAME, CGROUP_INET4_GETSOCKNAME, CGROUP_INET6_GETSOCKNAME, + CGROUP_UNIX_GETSOCKNAME, CGROUP_INET_SOCK_RELEASE, CGROUP_LSM_START, CGROUP_LSM_END = CGROUP_LSM_START + CGROUP_LSM_NUM - 1, diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 31561e789715..98b8cea904fe 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -48,19 +48,24 @@ to_cgroup_bpf_attach_type(enum bpf_attach_type attach_type) CGROUP_ATYPE(CGROUP_INET6_BIND); CGROUP_ATYPE(CGROUP_INET4_CONNECT); CGROUP_ATYPE(CGROUP_INET6_CONNECT); + CGROUP_ATYPE(CGROUP_UNIX_CONNECT); CGROUP_ATYPE(CGROUP_INET4_POST_BIND); CGROUP_ATYPE(CGROUP_INET6_POST_BIND); CGROUP_ATYPE(CGROUP_UDP4_SENDMSG); CGROUP_ATYPE(CGROUP_UDP6_SENDMSG); + CGROUP_ATYPE(CGROUP_UNIX_SENDMSG); CGROUP_ATYPE(CGROUP_SYSCTL); CGROUP_ATYPE(CGROUP_UDP4_RECVMSG); CGROUP_ATYPE(CGROUP_UDP6_RECVMSG); + CGROUP_ATYPE(CGROUP_UNIX_RECVMSG); CGROUP_ATYPE(CGROUP_GETSOCKOPT); CGROUP_ATYPE(CGROUP_SETSOCKOPT); CGROUP_ATYPE(CGROUP_INET4_GETPEERNAME); CGROUP_ATYPE(CGROUP_INET6_GETPEERNAME); + CGROUP_ATYPE(CGROUP_UNIX_GETPEERNAME); CGROUP_ATYPE(CGROUP_INET4_GETSOCKNAME); CGROUP_ATYPE(CGROUP_INET6_GETSOCKNAME); + CGROUP_ATYPE(CGROUP_UNIX_GETSOCKNAME); CGROUP_ATYPE(CGROUP_INET_SOCK_RELEASE); default: return CGROUP_BPF_ATTACH_TYPE_INVALID; @@ -289,18 +294,27 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, #define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, uaddrlen) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_INET6_CONNECT, NULL) +#define BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_CONNECT, NULL) + #define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP4_SENDMSG, t_ctx) #define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP6_SENDMSG, t_ctx) +#define BPF_CGROUP_RUN_PROG_UNIX_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_SENDMSG, t_ctx) + #define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr, uaddrlen) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP4_RECVMSG, NULL) #define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr, uaddrlen) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP6_RECVMSG, NULL) +#define BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_RECVMSG, NULL) + /* The SOCK_OPS"_SK" macro should be used when sock_ops->sk is not a * fullsock and its parent fullsock cannot be traced by * sk_to_full_sk(). @@ -492,10 +506,13 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UNIX_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(atype, major, minor, access) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos) ({ 0; }) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e0aa457f94a9..7ba61b75bc0e 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1047,6 +1047,11 @@ enum bpf_attach_type { BPF_TCX_INGRESS, BPF_TCX_EGRESS, BPF_TRACE_UPROBE_MULTI, + BPF_CGROUP_UNIX_CONNECT, + BPF_CGROUP_UNIX_SENDMSG, + BPF_CGROUP_UNIX_RECVMSG, + BPF_CGROUP_UNIX_GETPEERNAME, + BPF_CGROUP_UNIX_GETSOCKNAME, __MAX_BPF_ATTACH_TYPE }; @@ -2704,8 +2709,8 @@ union bpf_attr { * *bpf_socket* should be one of the following: * * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**. - * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT** - * and **BPF_CGROUP_INET6_CONNECT**. + * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**, + * **BPF_CGROUP_INET6_CONNECT** and **BPF_CGROUP_UNIX_CONNECT**. * * This helper actually implements a subset of **setsockopt()**. * It supports the following *level*\ s: @@ -2943,8 +2948,8 @@ union bpf_attr { * *bpf_socket* should be one of the following: * * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**. - * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT** - * and **BPF_CGROUP_INET6_CONNECT**. + * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**, + * **BPF_CGROUP_INET6_CONNECT** and **BPF_CGROUP_UNIX_CONNECT**. * * This helper actually implements a subset of **getsockopt()**. * It supports the same set of *optname*\ s that is supported by diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index ac37bd53aee0..74ad2215e1ba 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1458,7 +1458,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); * @flags: Pointer to u32 which contains higher bits of BPF program * return value (OR'ed together). * - * socket is expected to be of type INET or INET6. + * socket is expected to be of type INET, INET6 or UNIX. * * This function will return %-EPERM if an attached program is found and * returned value != 1 during execution. In all other cases, 0 is returned. @@ -1482,7 +1482,8 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, /* Check socket family since not all sockets represent network * endpoint (e.g. AF_UNIX). */ - if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6) + if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6 && + sk->sk_family != AF_UNIX) return 0; if (!ctx.uaddr) { @@ -2533,10 +2534,13 @@ cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_CGROUP_SOCK_OPS: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: + case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: + case BPF_CGROUP_UNIX_GETSOCKNAME: return NULL; default: return &bpf_get_retval_proto; @@ -2548,10 +2552,13 @@ cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_CGROUP_SOCK_OPS: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: + case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: + case BPF_CGROUP_UNIX_GETSOCKNAME: return NULL; default: return &bpf_set_retval_proto; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 6b5280f14a53..8677837f3deb 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2446,14 +2446,19 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: + case BPF_CGROUP_UNIX_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: + case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: + case BPF_CGROUP_UNIX_RECVMSG: return 0; default: return -EINVAL; @@ -3678,14 +3683,19 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type) case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: + case BPF_CGROUP_UNIX_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: + case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: + case BPF_CGROUP_UNIX_RECVMSG: return BPF_PROG_TYPE_CGROUP_SOCK_ADDR; case BPF_CGROUP_SOCK_OPS: return BPF_PROG_TYPE_SOCK_OPS; @@ -3942,14 +3952,19 @@ 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_UNIX_CONNECT: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: + case BPF_CGROUP_UNIX_GETSOCKNAME: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: + case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: + case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_SOCK_OPS: case BPF_CGROUP_DEVICE: case BPF_CGROUP_SYSCTL: diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index eed7350e15f4..e777f50401b6 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -14797,10 +14797,13 @@ static int check_return_code(struct bpf_verifier_env *env, int regno) case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: if (env->prog->expected_attach_type == BPF_CGROUP_UDP4_RECVMSG || env->prog->expected_attach_type == BPF_CGROUP_UDP6_RECVMSG || + env->prog->expected_attach_type == BPF_CGROUP_UNIX_RECVMSG || env->prog->expected_attach_type == BPF_CGROUP_INET4_GETPEERNAME || env->prog->expected_attach_type == BPF_CGROUP_INET6_GETPEERNAME || + env->prog->expected_attach_type == BPF_CGROUP_UNIX_GETPEERNAME || env->prog->expected_attach_type == BPF_CGROUP_INET4_GETSOCKNAME || - env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME) + env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME || + env->prog->expected_attach_type == BPF_CGROUP_UNIX_GETSOCKNAME) range = tnum_range(1, 1); if (env->prog->expected_attach_type == BPF_CGROUP_INET4_BIND || env->prog->expected_attach_type == BPF_CGROUP_INET6_BIND) diff --git a/net/core/filter.c b/net/core/filter.c index ff0bd9f20b95..cc2e4babc85f 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7875,14 +7875,19 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: + case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: + case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: + case BPF_CGROUP_UNIX_GETSOCKNAME: return &bpf_sock_addr_setsockopt_proto; default: return NULL; @@ -7893,14 +7898,19 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: + case BPF_CGROUP_UNIX_CONNECT: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: + case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_UDP4_SENDMSG: case BPF_CGROUP_UDP6_SENDMSG: + case BPF_CGROUP_UNIX_SENDMSG: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: + case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: + case BPF_CGROUP_UNIX_GETSOCKNAME: return &bpf_sock_addr_getsockopt_proto; default: return NULL; @@ -8948,8 +8958,8 @@ static bool sock_addr_is_valid_access(int off, int size, if (off % size != 0) return false; - /* Disallow access to IPv6 fields from IPv4 contex and vise - * versa. + /* Disallow access to fields not belonging to the attach type's address + * family. */ switch (off) { case bpf_ctx_range(struct bpf_sock_addr, user_ip4): diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 3e8a04a13668..e10d07c76044 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -116,6 +116,7 @@ #include #include #include +#include #include "scm.h" @@ -1381,6 +1382,10 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr, if (err) goto out; + err = BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, addr, &alen); + if (err) + goto out; + if ((test_bit(SOCK_PASSCRED, &sock->flags) || test_bit(SOCK_PASSPIDFD, &sock->flags)) && !unix_sk(sk)->addr) { @@ -1490,6 +1495,10 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, if (err) goto out; + err = BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, uaddr, &addr_len); + if (err) + goto out; + if ((test_bit(SOCK_PASSCRED, &sock->flags) || test_bit(SOCK_PASSPIDFD, &sock->flags)) && !u->addr) { err = unix_autobind(sk); @@ -1770,6 +1779,13 @@ static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int peer) } else { err = addr->len; memcpy(sunaddr, addr->name, addr->len); + + if (peer) + BPF_CGROUP_RUN_SA_PROG(sk, uaddr, &err, + CGROUP_UNIX_GETPEERNAME); + else + BPF_CGROUP_RUN_SA_PROG(sk, uaddr, &err, + CGROUP_UNIX_GETSOCKNAME); } sock_put(sk); out: @@ -1922,6 +1938,13 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, err = unix_validate_addr(sunaddr, msg->msg_namelen); if (err) goto out; + + err = BPF_CGROUP_RUN_PROG_UNIX_SENDMSG_LOCK(sk, + msg->msg_name, + &msg->msg_namelen, + NULL); + if (err) + goto out; } else { sunaddr = NULL; err = -ENOTCONN; @@ -2390,9 +2413,14 @@ int __unix_dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t size, EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND); - if (msg->msg_name) + if (msg->msg_name) { unix_copy_addr(msg, skb->sk); + BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk, + msg->msg_name, + &msg->msg_namelen); + } + if (size > skb->len - skip) size = skb->len - skip; else if (size < skb->len - skip) @@ -2744,6 +2772,11 @@ unlock: DECLARE_SOCKADDR(struct sockaddr_un *, sunaddr, state->msg->msg_name); unix_copy_addr(state->msg, skb->sk); + + BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk, + state->msg->msg_name, + &state->msg->msg_namelen); + sunaddr = NULL; } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index e0aa457f94a9..7ba61b75bc0e 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1047,6 +1047,11 @@ enum bpf_attach_type { BPF_TCX_INGRESS, BPF_TCX_EGRESS, BPF_TRACE_UPROBE_MULTI, + BPF_CGROUP_UNIX_CONNECT, + BPF_CGROUP_UNIX_SENDMSG, + BPF_CGROUP_UNIX_RECVMSG, + BPF_CGROUP_UNIX_GETPEERNAME, + BPF_CGROUP_UNIX_GETSOCKNAME, __MAX_BPF_ATTACH_TYPE }; @@ -2704,8 +2709,8 @@ union bpf_attr { * *bpf_socket* should be one of the following: * * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**. - * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT** - * and **BPF_CGROUP_INET6_CONNECT**. + * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**, + * **BPF_CGROUP_INET6_CONNECT** and **BPF_CGROUP_UNIX_CONNECT**. * * This helper actually implements a subset of **setsockopt()**. * It supports the following *level*\ s: @@ -2943,8 +2948,8 @@ union bpf_attr { * *bpf_socket* should be one of the following: * * * **struct bpf_sock_ops** for **BPF_PROG_TYPE_SOCK_OPS**. - * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT** - * and **BPF_CGROUP_INET6_CONNECT**. + * * **struct bpf_sock_addr** for **BPF_CGROUP_INET4_CONNECT**, + * **BPF_CGROUP_INET6_CONNECT** and **BPF_CGROUP_UNIX_CONNECT**. * * This helper actually implements a subset of **getsockopt()**. * It supports the same set of *optname*\ s that is supported by -- cgit v1.2.3 From 9c1292eca243821249fa99f40175b0660d9329e3 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Fri, 13 Oct 2023 11:57:02 -0700 Subject: net/bpf: Avoid unused "sin_addr_len" warning when CONFIG_CGROUP_BPF is not set It was reported that there is a compiler warning on the unused variable "sin_addr_len" in af_inet.c when CONFIG_CGROUP_BPF is not set. This patch is to address it similar to the ipv6 counterpart in inet6_getname(). It is to "return sin_addr_len;" instead of "return sizeof(*sin);". Fixes: fefba7d1ae19 ("bpf: Propagate modified uaddrlen from cgroup sockaddr programs") Reported-by: Stephen Rothwell Signed-off-by: Martin KaFai Lau Signed-off-by: Andrii Nakryiko Reviewed-by: Kuniyuki Iwashima Link: https://lore.kernel.org/bpf/20231013185702.3993710-1-martin.lau@linux.dev Closes: https://lore.kernel.org/bpf/20231013114007.2fb09691@canb.auug.org.au/ --- net/ipv4/af_inet.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 7e27ad37b939..5ce275b2d7ef 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -814,7 +814,7 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr, } release_sock(sk); memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); - return sizeof(*sin); + return sin_addr_len; } EXPORT_SYMBOL(inet_getname); -- cgit v1.2.3