netdev - Re: [PATCH] ipv4: Early TCP socket demux.

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <CABa6K_Ge-Y1ne3iBcN1HSRN+G4bW6hSAHYFGKuA5QKW6CT3grQ@mail.gmail.com>
Date:	Tue, 19 Jun 2012 12:43:27 +0800
From:	Changli Gao <xiaosuo@...il.com>
To:	David Miller <davem@...emloft.net>
Cc:	netdev@...r.kernel.org, Tom Herbert <therbert@...gle.com>
Subject: Re: [PATCH] ipv4: Early TCP socket demux.

On Tue, Jun 19, 2012 at 10:40 AM, David Miller <davem@...emloft.net> wrote:
> @@ -324,19 +324,34 @@ static int ip_rcv_finish(struct sk_buff *skb)
>         *      how the packet travels inside Linux networking.
>         */
>        if (skb_dst(skb) == NULL) {
> -               int err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
> -                                              iph->tos, skb->dev);
> -               if (unlikely(err)) {
> -                       if (err == -EHOSTUNREACH)
> -                               IP_INC_STATS_BH(dev_net(skb->dev),
> -                                               IPSTATS_MIB_INADDRERRORS);
> -                       else if (err == -ENETUNREACH)
> -                               IP_INC_STATS_BH(dev_net(skb->dev),
> -                                               IPSTATS_MIB_INNOROUTES);
> -                       else if (err == -EXDEV)
> -                               NET_INC_STATS_BH(dev_net(skb->dev),
> -                                                LINUX_MIB_IPRPFILTER);
> -                       goto drop;
> +               const struct net_protocol *ipprot;
> +               int protocol = iph->protocol;
> +               int hash, err;
> +
> +               hash = protocol & (MAX_INET_PROTOS - 1);
> +
> +               rcu_read_lock();
> +               ipprot = rcu_dereference(inet_protos[hash]);
> +               err = -ENOENT;
> +               if (ipprot && ipprot->early_demux)
> +                       err = ipprot->early_demux(skb);

I am afraid that this lookup with hurt the performance of the
forwarding path. A knob?

If this approach is acceptable, maybe we can use sockets to do finer RFS.

Thanks.

-- 
Regards,
Changli Gao(xiaosuo@...il.com)
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html