Re: [PATCH v1 bpf-next 03/11] tcp: Migrate TCP_ESTABLISHED/TCP_SYN_RECV sockets in accept queues.

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 03/11] tcp: Migrate TCP_ESTABLISHED/TCP_SYN_RECV sockets in accept queues.
Date: Fri, 4 Dec 2020 17:42:41 -0800	[thread overview]
Message-ID: <20201205014241.afrcicgewlnyrzfu@kafai-mbp.dhcp.thefacebook.com> (raw)
In-Reply-To: <20201201144418.35045-4-kuniyu@amazon.co.jp>

On Tue, Dec 01, 2020 at 11:44:10PM +0900, Kuniyuki Iwashima wrote:
[ ... ]
> diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
> index fd133516ac0e..60d7c1f28809 100644
> --- a/net/core/sock_reuseport.c
> +++ b/net/core/sock_reuseport.c
> @@ -216,9 +216,11 @@ int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany)
>  }
>  EXPORT_SYMBOL(reuseport_add_sock);
>  
> -void reuseport_detach_sock(struct sock *sk)
> +struct sock *reuseport_detach_sock(struct sock *sk)
>  {
>  	struct sock_reuseport *reuse;
> +	struct bpf_prog *prog;
> +	struct sock *nsk = NULL;
>  	int i;
>  
>  	spin_lock_bh(&reuseport_lock);
> @@ -242,8 +244,12 @@ void reuseport_detach_sock(struct sock *sk)
>  
>  		reuse->num_socks--;
>  		reuse->socks[i] = reuse->socks[reuse->num_socks];
> +		prog = rcu_dereference(reuse->prog);
Is it under rcu_read_lock() here?

>  
>  		if (sk->sk_protocol == IPPROTO_TCP) {
> +			if (reuse->num_socks && !prog)
> +				nsk = i == reuse->num_socks ? reuse->socks[i - 1] : reuse->socks[i];
> +
>  			reuse->num_closed_socks++;
>  			reuse->socks[reuse->max_socks - reuse->num_closed_socks] = sk;
>  		} else {
> @@ -264,6 +270,8 @@ void reuseport_detach_sock(struct sock *sk)
>  		call_rcu(&reuse->rcu, reuseport_free_rcu);
>  out:
>  	spin_unlock_bh(&reuseport_lock);
> +
> +	return nsk;
>  }
>  EXPORT_SYMBOL(reuseport_detach_sock);
>  
> diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
> index 1451aa9712b0..b27241ea96bd 100644
> --- a/net/ipv4/inet_connection_sock.c
> +++ b/net/ipv4/inet_connection_sock.c
> @@ -992,6 +992,36 @@ struct sock *inet_csk_reqsk_queue_add(struct sock *sk,
>  }
>  EXPORT_SYMBOL(inet_csk_reqsk_queue_add);
>  
> +void inet_csk_reqsk_queue_migrate(struct sock *sk, struct sock *nsk)
> +{
> +	struct request_sock_queue *old_accept_queue, *new_accept_queue;
> +
> +	old_accept_queue = &inet_csk(sk)->icsk_accept_queue;
> +	new_accept_queue = &inet_csk(nsk)->icsk_accept_queue;
> +
> +	spin_lock(&old_accept_queue->rskq_lock);
> +	spin_lock(&new_accept_queue->rskq_lock);
I am also not very thrilled on this double spin_lock.
Can this be done in (or like) inet_csk_listen_stop() instead?

> +
> +	if (old_accept_queue->rskq_accept_head) {
> +		if (new_accept_queue->rskq_accept_head)
> +			old_accept_queue->rskq_accept_tail->dl_next =
> +				new_accept_queue->rskq_accept_head;
> +		else
> +			new_accept_queue->rskq_accept_tail = old_accept_queue->rskq_accept_tail;
> +
> +		new_accept_queue->rskq_accept_head = old_accept_queue->rskq_accept_head;
> +		old_accept_queue->rskq_accept_head = NULL;
> +		old_accept_queue->rskq_accept_tail = NULL;
> +
> +		WRITE_ONCE(nsk->sk_ack_backlog, nsk->sk_ack_backlog + sk->sk_ack_backlog);
> +		WRITE_ONCE(sk->sk_ack_backlog, 0);
> +	}
> +
> +	spin_unlock(&new_accept_queue->rskq_lock);
> +	spin_unlock(&old_accept_queue->rskq_lock);
> +}
> +EXPORT_SYMBOL(inet_csk_reqsk_queue_migrate);
> +
>  struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child,
>  					 struct request_sock *req, bool own_req)
>  {
> diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
> index 45fb450b4522..545538a6bfac 100644
> --- a/net/ipv4/inet_hashtables.c
> +++ b/net/ipv4/inet_hashtables.c
> @@ -681,6 +681,7 @@ void inet_unhash(struct sock *sk)
>  {
>  	struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
>  	struct inet_listen_hashbucket *ilb = NULL;
> +	struct sock *nsk;
>  	spinlock_t *lock;
>  
>  	if (sk_unhashed(sk))
> @@ -696,8 +697,12 @@ void inet_unhash(struct sock *sk)
>  	if (sk_unhashed(sk))
>  		goto unlock;
>  
> -	if (rcu_access_pointer(sk->sk_reuseport_cb))
> -		reuseport_detach_sock(sk);
> +	if (rcu_access_pointer(sk->sk_reuseport_cb)) {
> +		nsk = reuseport_detach_sock(sk);
> +		if (nsk)
> +			inet_csk_reqsk_queue_migrate(sk, nsk);
> +	}
> +
>  	if (ilb) {
>  		inet_unhash2(hashinfo, sk);
>  		ilb->count--;
> -- 
> 2.17.2 (Apple Git-113)
>