[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Wed, 2 Feb 2022 22:01:46 +0800
From: "D. Wythe" <alibuda@...ux.alibaba.com>
To: Tony Lu <tonylu@...ux.alibaba.com>
Cc: kgraul@...ux.ibm.com, kuba@...nel.org, davem@...emloft.net,
netdev@...r.kernel.org, linux-s390@...r.kernel.org,
linux-rdma@...r.kernel.org, matthieu.baerts@...sares.net
Subject: Re: [PATCH v2 net-next 2/3] net/smc: Limits backlog connections
The overhead will certainly exist, but compared with the benefits, I
think it should be acceptable. If you do care, maybe we can add a switch
to control it.
> I am wondering if there would introduce more overhead, compared with
> original implement?
>
>> +
>> +drop:
>> + dst_release(dst);
>> + tcp_listendrop(sk);
>> + return NULL;
>> +}
>> +
>> static struct smc_hashinfo smc_v4_hashinfo = {
>> .lock = __RW_LOCK_UNLOCKED(smc_v4_hashinfo.lock),
>> };
>> @@ -1491,6 +1519,9 @@ static void smc_listen_out(struct smc_sock *new_smc)
>> struct smc_sock *lsmc = new_smc->listen_smc;
>> struct sock *newsmcsk = &new_smc->sk;
>>
>> + if (tcp_sk(new_smc->clcsock->sk)->syn_smc)
>> + atomic_dec(&lsmc->smc_pendings);
>> +
>> if (lsmc->sk.sk_state == SMC_LISTEN) {
>> lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING);
>> smc_accept_enqueue(&lsmc->sk, newsmcsk);
>> @@ -2096,6 +2127,9 @@ static void smc_tcp_listen_work(struct work_struct *work)
>> if (!new_smc)
>> continue;
>>
>> + if (tcp_sk(new_smc->clcsock->sk)->syn_smc)
>> + atomic_inc(&lsmc->smc_pendings);
>> +
>> new_smc->listen_smc = lsmc;
>> new_smc->use_fallback = lsmc->use_fallback;
>> new_smc->fallback_rsn = lsmc->fallback_rsn;
>> @@ -2163,6 +2197,15 @@ static int smc_listen(struct socket *sock, int backlog)
>> smc->clcsock->sk->sk_data_ready = smc_clcsock_data_ready;
>> smc->clcsock->sk->sk_user_data =
>> (void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY);
>> +
>> + /* save origin ops */
>> + smc->ori_af_ops = inet_csk(smc->clcsock->sk)->icsk_af_ops;
>> +
>> + smc->af_ops = *smc->ori_af_ops;
>> + smc->af_ops.syn_recv_sock = smc_tcp_syn_recv_sock;
>> +
>> + inet_csk(smc->clcsock->sk)->icsk_af_ops = &smc->af_ops;
>
Only save syn_recv_sock? Maybe this comment is confusing,
‘Copy the origin ops’ is better, the origin ops is pointer to a const
structure, we must copy it all, and repointer it to our structure. so
the copy/save is necessary.
Thanks.
> Consider to save syn_recv_sock this field only? There seems no need to
> save this ops all.
>
> Thank you,
> Tony Lu
Powered by blists - more mailing lists