From 9974c2cee8693e36f58853e2f1664beb037bbdd9 Mon Sep 17 00:00:00 2001 From: Joe Stringer Date: Sun, 29 Mar 2020 15:53:38 -0700 Subject: [PATCH] BACKPORT: bpf: Add socket assign support Add support for TPROXY via a new bpf helper, bpf_sk_assign(). This helper requires the BPF program to discover the socket via a call to bpf_sk*_lookup_*(), then pass this socket to the new helper. The helper takes its own reference to the socket in addition to any existing reference that may or may not currently be obtained for the duration of BPF processing. For the destination socket to receive the traffic, the traffic must be routed towards that socket via local route. The simplest example route is below, but in practice you may want to route traffic more narrowly (eg by CIDR): $ ip route add local default dev lo This patch avoids trying to introduce an extra bit into the skb->sk, as that would require more invasive changes to all code interacting with the socket to ensure that the bit is handled correctly, such as all error-handling cases along the path from the helper in BPF through to the orphan path in the input. Instead, we opt to use the destructor variable to switch on the prefetch of the socket. Change-Id: I66c9fce30fea682d2acaa741a6bbd46857083ed2 Signed-off-by: Joe Stringer Signed-off-by: Alexei Starovoitov Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20200329225342.16317-2-joe@wand.net.nz --- include/net/sock.h | 11 +++++++++++ include/uapi/linux/bpf.h | 22 ++++++++++++++++++++++ net/core/filter.c | 31 +++++++++++++++++++++++++++++++ net/core/sock.c | 11 +++++++++++ net/ipv4/ip_input.c | 3 ++- net/ipv6/ip6_input.c | 3 ++- net/sched/act_bpf.c | 3 +++ tools/include/uapi/linux/bpf.h | 22 ++++++++++++++++++++++ 8 files changed, 104 insertions(+), 2 deletions(-) diff --git a/include/net/sock.h b/include/net/sock.h index a8335a0b9ee2..91e8401d8cc7 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1688,6 +1688,7 @@ void sock_rfree(struct sk_buff *skb); void sock_efree(struct sk_buff *skb); #ifdef CONFIG_INET void sock_edemux(struct sk_buff *skb); +void sock_pfree(struct sk_buff *skb); #else #define sock_edemux sock_efree #endif @@ -2600,6 +2601,16 @@ void sock_net_set(struct sock *sk, struct net *net) write_pnet(&sk->sk_net, net); } +static inline bool +skb_sk_is_prefetched(struct sk_buff *skb) +{ +#ifdef CONFIG_INET + return skb->destructor == sock_pfree; +#else + return false; +#endif /* CONFIG_INET */ +} + static inline struct sock *skb_steal_sock(struct sk_buff *skb) { if (skb->sk) { diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 701f5e20de67..27d6937d5cdf 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2995,6 +2995,28 @@ union bpf_attr { * **bpf_get_current_cgroup_id**\ (). * Return * The id is returned or 0 in case the id could not be retrieved. + * + * int bpf_sk_assign(struct sk_buff *skb, struct bpf_sock *sk, u64 flags) + * Description + * Assign the *sk* to the *skb*. When combined with appropriate + * routing configuration to receive the packet towards the socket, + * will cause *skb* to be delivered to the specified socket. + * Subsequent redirection of *skb* via **bpf_redirect**\ (), + * **bpf_clone_redirect**\ () or other methods outside of BPF may + * interfere with successful delivery to the socket. + * + * This operation is only valid from TC ingress path. + * + * The *flags* argument must be zero. + * Return + * 0 on success, or a negative errno in case of failure. + * + * * **-EINVAL** Unsupported flags specified. + * * **-ENOENT** Socket is unavailable for assignment. + * * **-ENETUNREACH** Socket is unreachable (wrong netns). + * * **-EOPNOTSUPP** Unsupported operation, for example a + * call from outside of TC ingress. + * * **-ESOCKTNOSUPPORT** Socket type not supported (reuseport). */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ diff --git a/net/core/filter.c b/net/core/filter.c index 3c3edab298dc..d213d079f474 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -6028,6 +6028,35 @@ static const struct bpf_func_proto bpf_tcp_gen_syncookie_proto = { .arg5_type = ARG_CONST_SIZE, }; +BPF_CALL_3(bpf_sk_assign, struct sk_buff *, skb, struct sock *, sk, u64, flags) +{ + if (flags != 0) + return -EINVAL; + if (!skb_at_tc_ingress(skb)) + return -EOPNOTSUPP; + if (unlikely(dev_net(skb->dev) != sock_net(sk))) + return -ENETUNREACH; + if (unlikely(sk->sk_reuseport)) + return -ESOCKTNOSUPPORT; + if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) + return -ENOENT; + + skb_orphan(skb); + skb->sk = sk; + skb->destructor = sock_pfree; + + return 0; +} + +static const struct bpf_func_proto bpf_sk_assign_proto = { + .func = bpf_sk_assign, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_SOCK_COMMON, + .arg3_type = ARG_ANYTHING, +}; + #endif /* CONFIG_INET */ bool bpf_helper_changes_pkt_data(void *func) @@ -6363,6 +6392,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_skb_ecn_set_ce_proto; case BPF_FUNC_tcp_gen_syncookie: return &bpf_tcp_gen_syncookie_proto; + case BPF_FUNC_sk_assign: + return &bpf_sk_assign_proto; #endif default: return bpf_base_func_proto(func_id); diff --git a/net/core/sock.c b/net/core/sock.c index bd7ff423201d..ac53ada12a4b 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2089,6 +2089,17 @@ void sock_efree(struct sk_buff *skb) } EXPORT_SYMBOL(sock_efree); +/* Buffer destructor for prefetch/receive path where reference count may + * not be held, e.g. for listen sockets. + */ +#ifdef CONFIG_INET +void sock_pfree(struct sk_buff *skb) +{ + sock_gen_put(skb->sk); +} +EXPORT_SYMBOL(sock_pfree); +#endif /* CONFIG_INET */ + kuid_t sock_i_uid(struct sock *sk) { kuid_t uid; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 1464e2738211..001a35dbc3d8 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -501,7 +501,8 @@ static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net) IPCB(skb)->iif = skb->skb_iif; /* Must drop socket now because of tproxy. */ - skb_orphan(skb); + if (!skb_sk_is_prefetched(skb)) + skb_orphan(skb); return skb; diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index ebf90bce063a..4d857d44060d 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -257,7 +257,8 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev, rcu_read_unlock(); /* Must drop socket now because of tproxy. */ - skb_orphan(skb); + if (!skb_sk_is_prefetched(skb)) + skb_orphan(skb); return skb; err: diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index b7d83d01841b..0b015ce802a4 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -12,6 +12,7 @@ #include #include +#include #include #include @@ -53,6 +54,8 @@ static int tcf_bpf_act(struct sk_buff *skb, const struct tc_action *act, bpf_compute_data_pointers(skb); filter_res = BPF_PROG_RUN(filter, skb); } + if (skb_sk_is_prefetched(skb) && filter_res != TC_ACT_OK) + skb_orphan(skb); rcu_read_unlock(); /* A BPF program may overwrite the default action opcode. diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 3e5a5857f693..c08b6349fbd3 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2959,6 +2959,28 @@ union bpf_attr { * **bpf_get_current_cgroup_id**\ (). * Return * The id is returned or 0 in case the id could not be retrieved. + * + * int bpf_sk_assign(struct sk_buff *skb, struct bpf_sock *sk, u64 flags) + * Description + * Assign the *sk* to the *skb*. When combined with appropriate + * routing configuration to receive the packet towards the socket, + * will cause *skb* to be delivered to the specified socket. + * Subsequent redirection of *skb* via **bpf_redirect**\ (), + * **bpf_clone_redirect**\ () or other methods outside of BPF may + * interfere with successful delivery to the socket. + * + * This operation is only valid from TC ingress path. + * + * The *flags* argument must be zero. + * Return + * 0 on success, or a negative errno in case of failure. + * + * * **-EINVAL** Unsupported flags specified. + * * **-ENOENT** Socket is unavailable for assignment. + * * **-ENETUNREACH** Socket is unreachable (wrong netns). + * * **-EOPNOTSUPP** Unsupported operation, for example a + * call from outside of TC ingress. + * * **-ESOCKTNOSUPPORT** Socket type not supported (reuseport). */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \