@@ -1657,6 +1657,7 @@ struct sk_buff *sock_omalloc(struct sock *sk, unsigned long size,
void skb_orphan_partial(struct sk_buff *skb);
void sock_rfree(struct sk_buff *skb);
void sock_efree(struct sk_buff *skb);
+void sock_pfree(struct sk_buff *skb);
#ifdef CONFIG_INET
void sock_edemux(struct sk_buff *skb);
#else
@@ -2526,6 +2527,12 @@ 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)
+{
+ return skb->destructor == sock_pfree;
+}
+
static inline struct sock *skb_steal_sock(struct sk_buff *skb)
{
if (skb->sk) {
@@ -2950,6 +2950,28 @@ union bpf_attr {
* restricted to raw_tracepoint bpf programs.
* Return
* 0 on success, or a negative error in case of failure.
+ *
+ * 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.
+ * * **-ENETUNREACH** Socket is unreachable (wrong netns).
+ * * **-ENOENT** Socket is unavailable for assignment.
+ * * **-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), \
@@ -3073,7 +3095,8 @@ union bpf_attr {
FN(jiffies64), \
FN(read_branch_records), \
FN(get_ns_current_pid_tgid), \
- FN(xdp_output),
+ FN(xdp_output), \
+ FN(sk_assign),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
@@ -5860,6 +5860,35 @@ 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(sk->sk_reuseport))
+ return -ESOCKTNOSUPPORT;
+ if (unlikely(dev_net(skb->dev) != sock_net(sk)))
+ return -ENETUNREACH;
+ 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)
@@ -6153,6 +6182,8 @@ 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);
@@ -2071,6 +2071,15 @@ 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.
+ */
+void sock_pfree(struct sk_buff *skb)
+{
+ sock_edemux(skb);
+}
+EXPORT_SYMBOL(sock_pfree);
+
kuid_t sock_i_uid(struct sock *sk)
{
kuid_t uid;
@@ -509,7 +509,8 @@ 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;
@@ -285,7 +285,8 @@ 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:
@@ -53,6 +53,8 @@ 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 (filter_res != TC_ACT_OK)
+ skb_orphan(skb);
rcu_read_unlock();
/* A BPF program may overwrite the default action opcode.
@@ -2950,6 +2950,28 @@ union bpf_attr {
* restricted to raw_tracepoint bpf programs.
* Return
* 0 on success, or a negative error in case of failure.
+ *
+ * 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.
+ * * **-ENETUNREACH** Socket is unreachable (wrong netns).
+ * * **-ENOENT** Socket is unavailable for assignment.
+ * * **-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), \
@@ -3073,7 +3095,8 @@ union bpf_attr {
FN(jiffies64), \
FN(read_branch_records), \
FN(get_ns_current_pid_tgid), \
- FN(xdp_output),
+ FN(xdp_output), \
+ FN(sk_assign),
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
* function eBPF program intends to call
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. Signed-off-by: Joe Stringer <joe@wand.net.nz> --- v2: Use skb->destructor to determine socket prefetch usage instead of introducing a new metadata_dst Restrict socket assign to same netns as TC device Restrict assigning reuseport sockets Adjust commit wording v1: Initial version --- include/net/sock.h | 7 +++++++ include/uapi/linux/bpf.h | 25 ++++++++++++++++++++++++- net/core/filter.c | 31 +++++++++++++++++++++++++++++++ net/core/sock.c | 9 +++++++++ net/ipv4/ip_input.c | 3 ++- net/ipv6/ip6_input.c | 3 ++- net/sched/act_bpf.c | 2 ++ tools/include/uapi/linux/bpf.h | 25 ++++++++++++++++++++++++- 8 files changed, 101 insertions(+), 4 deletions(-)