Re: [PATCH v1 bpf-next 05/11] tcp: Migrate TCP_NEW_SYN_RECV requests.

From: Martin KaFai Lau <kafai@fb.com>
To: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Cc: "David S . Miller" <davem@davemloft.net>,
	Jakub Kicinski <kuba@kernel.org>,
	Eric Dumazet <edumazet@google.com>,
	Alexei Starovoitov <ast@kernel.org>,
	Daniel Borkmann <daniel@iogearbox.net>,
	Benjamin Herrenschmidt <benh@amazon.com>,
	Kuniyuki Iwashima <kuni1840@gmail.com>,
	<osa-contribution-log@amazon.com>, <bpf@vger.kernel.org>,
	<netdev@vger.kernel.org>, <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH v1 bpf-next 05/11] tcp: Migrate TCP_NEW_SYN_RECV requests.
Date: Wed, 9 Dec 2020 16:07:07 -0800	[thread overview]
Message-ID: <20201210000707.cxm2r57mbsq2p6uu@kafai-mbp.dhcp.thefacebook.com> (raw)
In-Reply-To: <20201201144418.35045-6-kuniyu@amazon.co.jp>

On Tue, Dec 01, 2020 at 11:44:12PM +0900, Kuniyuki Iwashima wrote:
> This patch renames reuseport_select_sock() to __reuseport_select_sock() and
> adds two wrapper function of it to pass the migration type defined in the
> previous commit.
> 
>   reuseport_select_sock          : BPF_SK_REUSEPORT_MIGRATE_NO
>   reuseport_select_migrated_sock : BPF_SK_REUSEPORT_MIGRATE_REQUEST
> 
> As mentioned before, we have to select a new listener for TCP_NEW_SYN_RECV
> requests at receiving the final ACK or sending a SYN+ACK. Therefore, this
> patch also changes the code to call reuseport_select_migrated_sock() even
> if the listening socket is TCP_CLOSE. If we can pick out a listening socket
> from the reuseport group, we rewrite request_sock.rsk_listener and resume
> processing the request.
> 
> Reviewed-by: Benjamin Herrenschmidt <benh@amazon.com>
> Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
> ---
>  include/net/inet_connection_sock.h | 12 +++++++++++
>  include/net/request_sock.h         | 13 ++++++++++++
>  include/net/sock_reuseport.h       |  8 +++----
>  net/core/sock_reuseport.c          | 34 ++++++++++++++++++++++++------
>  net/ipv4/inet_connection_sock.c    | 13 ++++++++++--
>  net/ipv4/tcp_ipv4.c                |  9 ++++++--
>  net/ipv6/tcp_ipv6.c                |  9 ++++++--
>  7 files changed, 81 insertions(+), 17 deletions(-)
> 
> diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
> index 2ea2d743f8fc..1e0958f5eb21 100644
> --- a/include/net/inet_connection_sock.h
> +++ b/include/net/inet_connection_sock.h
> @@ -272,6 +272,18 @@ static inline void inet_csk_reqsk_queue_added(struct sock *sk)
>  	reqsk_queue_added(&inet_csk(sk)->icsk_accept_queue);
>  }
>  
> +static inline void inet_csk_reqsk_queue_migrated(struct sock *sk,
> +						 struct sock *nsk,
> +						 struct request_sock *req)
> +{
> +	reqsk_queue_migrated(&inet_csk(sk)->icsk_accept_queue,
> +			     &inet_csk(nsk)->icsk_accept_queue,
> +			     req);
> +	sock_put(sk);
not sure if it is safe to do here.
IIUC, when the req->rsk_refcnt is held, it also holds a refcnt
to req->rsk_listener such that sock_hold(req->rsk_listener) is
safe because its sk_refcnt is not zero.

> +	sock_hold(nsk);
> +	req->rsk_listener = nsk;
> +}
> +

[ ... ]

> diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
> index 361efe55b1ad..e71653c6eae2 100644
> --- a/net/ipv4/inet_connection_sock.c
> +++ b/net/ipv4/inet_connection_sock.c
> @@ -743,8 +743,17 @@ static void reqsk_timer_handler(struct timer_list *t)
>  	struct request_sock_queue *queue = &icsk->icsk_accept_queue;
>  	int max_syn_ack_retries, qlen, expire = 0, resend = 0;
>  
> -	if (inet_sk_state_load(sk_listener) != TCP_LISTEN)
> -		goto drop;
> +	if (inet_sk_state_load(sk_listener) != TCP_LISTEN) {
> +		sk_listener = reuseport_select_migrated_sock(sk_listener,
> +							     req_to_sk(req)->sk_hash, NULL);
> +		if (!sk_listener) {
> +			sk_listener = req->rsk_listener;
> +			goto drop;
> +		}
> +		inet_csk_reqsk_queue_migrated(req->rsk_listener, sk_listener, req);
> +		icsk = inet_csk(sk_listener);
> +		queue = &icsk->icsk_accept_queue;
> +	}
>  
>  	max_syn_ack_retries = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_synack_retries;
>  	/* Normally all the openreqs are young and become mature
> diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
> index e4b31e70bd30..9a9aa27c6069 100644
> --- a/net/ipv4/tcp_ipv4.c
> +++ b/net/ipv4/tcp_ipv4.c
> @@ -1973,8 +1973,13 @@ int tcp_v4_rcv(struct sk_buff *skb)
>  			goto csum_error;
>  		}
>  		if (unlikely(sk->sk_state != TCP_LISTEN)) {
> -			inet_csk_reqsk_queue_drop_and_put(sk, req);
> -			goto lookup;
> +			nsk = reuseport_select_migrated_sock(sk, req_to_sk(req)->sk_hash, skb);
> +			if (!nsk) {
> +				inet_csk_reqsk_queue_drop_and_put(sk, req);
> +				goto lookup;
> +			}
> +			inet_csk_reqsk_queue_migrated(sk, nsk, req);
> +			sk = nsk;
>  		}
>  		/* We own a reference on the listener, increase it again
>  		 * as we might lose it too soon.
> diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
> index 992cbf3eb9e3..ff11f3c0cb96 100644
> --- a/net/ipv6/tcp_ipv6.c
> +++ b/net/ipv6/tcp_ipv6.c
> @@ -1635,8 +1635,13 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb)
>  			goto csum_error;
>  		}
>  		if (unlikely(sk->sk_state != TCP_LISTEN)) {
> -			inet_csk_reqsk_queue_drop_and_put(sk, req);
> -			goto lookup;
> +			nsk = reuseport_select_migrated_sock(sk, req_to_sk(req)->sk_hash, skb);
> +			if (!nsk) {
> +				inet_csk_reqsk_queue_drop_and_put(sk, req);
> +				goto lookup;
> +			}
> +			inet_csk_reqsk_queue_migrated(sk, nsk, req);
> +			sk = nsk;
>  		}
>  		sock_hold(sk);
For example, this sock_hold(sk).  sk here is req->rsk_listener.

>  		refcounted = true;
> -- 
> 2.17.2 (Apple Git-113)
>