netdev - Re: [PATCH 2/2] ipv4: Initialize on-stack cork more efficiently.

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: <1304745104.2821.590.camel@edumazet-laptop>
Date:	Sat, 07 May 2011 07:11:44 +0200
From:	Eric Dumazet <eric.dumazet@...il.com>
To:	David Miller <davem@...emloft.net>
Cc:	netdev@...r.kernel.org, herbert@...dor.apana.org.au
Subject: Re: [PATCH 2/2] ipv4: Initialize on-stack cork more efficiently.

Le samedi 07 mai 2011 à 00:35 +0200, Eric Dumazet a écrit :
> Le vendredi 06 mai 2011 à 15:26 -0700, David Miller a écrit :
> > ip_setup_cork() explicitly initializes every member of
> > inet_cork except flags, addr, and opt.  So we can simply
> > set those three members to zero instead of using a
> > memset() via an empty struct assignment.
> > 
> > Signed-off-by: David S. Miller <davem@...emloft.net>
> > ---
> >  net/ipv4/ip_output.c |    5 ++++-
> >  1 files changed, 4 insertions(+), 1 deletions(-)
> > 
> > diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
> > index eb0647a..5f5fe4f 100644
> > --- a/net/ipv4/ip_output.c
> > +++ b/net/ipv4/ip_output.c
> > @@ -1408,7 +1408,7 @@ struct sk_buff *ip_make_skb(struct sock *sk,
> >  			    struct ipcm_cookie *ipc, struct rtable **rtp,
> >  			    unsigned int flags)
> >  {
> > -	struct inet_cork cork = {};
> > +	struct inet_cork cork;
> >  	struct sk_buff_head queue;
> >  	int err;
> >  
> > @@ -1417,6 +1417,9 @@ struct sk_buff *ip_make_skb(struct sock *sk,
> >  
> >  	__skb_queue_head_init(&queue);
> >  
> > +	cork.flags = 0;
> > +	cork.addr = 0;
> > +	cork.opt = 0;
> >  	err = ip_setup_cork(sk, &cork, ipc, rtp);
> >  	if (err)
> >  		return ERR_PTR(err);
> 
> Very nice, thanks for finishing this stuff :)
> 
> Acked-by: Eric Dumazet <eric.dumazet@...il.com>
> 

By the way, when I spotted this "struct inet_cork cork = {};" to be
optimized, my idea was to add yet another case of fastpath to UDP send :

For small datagrams (most UDP uses : RTP, DNS...),
perform the user->kernel copy before route lookup, so that we can
perform an RCU route lookup. This would tremendously speedup UDP, since
the refcount handling is our last hot spot (not counting qdisc if
present)

   PerfTop:   16142 irqs/sec  kernel:97.5%  exact:  0.0% [1000Hz cycles],  (all, 16 CPUs)
-----------------------------------------------------------------------------------------------------------

             samples  pcnt function                 DSO
             _______ _____ ________________________ ______________________

            16735.00 24.2% __ip_route_output_key    vmlinux               
             9706.00 14.1% dst_release              vmlinux               
             6754.00  9.8% __ip_make_skb            vmlinux               
             5737.00  8.3% udp_send_skb             vmlinux               
             5384.00  7.8% ip_finish_output         vmlinux               
             3578.00  5.2% udp_sendmsg              vmlinux               
             1435.00  2.1% copy_user_generic_string vmlinux               
             1358.00  2.0% ia32_sysenter_target     vmlinux               
             1095.00  1.6% __ip_append_data         vmlinux               
              832.00  1.2% kfree                    vmlinux               
              794.00  1.2% __memset                 vmlinux               
              677.00  1.0% fget_light               vmlinux               
              641.00  0.9% sock_wfree               vmlinux               
              637.00  0.9% dev_queue_xmit           vmlinux               


--
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