On Wed, Mar 31, 2021 at 04:32 AM CEST, Cong Wang wrote:
> From: Cong Wang <[email protected]>
>
> Currently sockmap calls into each protocol to update the struct
> proto and replace it. This certainly won't work when the protocol
> is implemented as a module, for example, AF_UNIX.
>
> Introduce a new ops sk->sk_prot->psock_update_sk_prot(), so each
> protocol can implement its own way to replace the struct proto.
> This also helps get rid of symbol dependencies on CONFIG_INET.
>
> Cc: John Fastabend <[email protected]>
> Cc: Daniel Borkmann <[email protected]>
> Cc: Jakub Sitnicki <[email protected]>
> Cc: Lorenz Bauer <[email protected]>
> Signed-off-by: Cong Wang <[email protected]>
> ---
[...]
> diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
> index 4a0478b17243..38952aaee3a1 100644
> --- a/net/ipv4/udp.c
> +++ b/net/ipv4/udp.c
> @@ -2849,6 +2849,9 @@ struct proto udp_prot = {
> .unhash = udp_lib_unhash,
> .rehash = udp_v4_rehash,
> .get_port = udp_v4_get_port,
> +#ifdef CONFIG_BPF_SYSCALL
> + .psock_update_sk_prot = udp_bpf_update_proto,
> +#endif
> .memory_allocated = &udp_memory_allocated,
> .sysctl_mem = sysctl_udp_mem,
> .sysctl_wmem_offset = offsetof(struct net,
> ipv4.sysctl_udp_wmem_min),
> diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c
> index 7a94791efc1a..6001f93cd3a0 100644
> --- a/net/ipv4/udp_bpf.c
> +++ b/net/ipv4/udp_bpf.c
> @@ -41,12 +41,23 @@ static int __init udp_bpf_v4_build_proto(void)
> }
> core_initcall(udp_bpf_v4_build_proto);
>
> -struct proto *udp_bpf_get_proto(struct sock *sk, struct sk_psock *psock)
> +int udp_bpf_update_proto(struct sock *sk, bool restore)
> {
> int family = sk->sk_family == AF_INET ? UDP_BPF_IPV4 : UDP_BPF_IPV6;
> + struct sk_psock *psock = sk_psock(sk);
> +
> + if (restore) {
> + sk->sk_write_space = psock->saved_write_space;
> + /* Pairs with lockless read in sk_clone_lock() */
Just to clarify. UDP sockets don't get cloned, so the above comment
apply.
> + WRITE_ONCE(sk->sk_prot, psock->sk_proto);
> + return 0;
> + }
>
> if (sk->sk_family == AF_INET6)
> udp_bpf_check_v6_needs_rebuild(psock->sk_proto);
>
> - return &udp_bpf_prots[family];
> + /* Pairs with lockless read in sk_clone_lock() */
> + WRITE_ONCE(sk->sk_prot, &udp_bpf_prots[family]);
> + return 0;
> }
> +EXPORT_SYMBOL_GPL(udp_bpf_update_proto);
[...]
