Re: [PATCH 3/3] [NET] Add IP(V6)_PMTUDISC_RPOBE

[Andi Kleen <andi@firstfloor.org>]

John Heffner <jheffner@psc.edu> writes:

> Add IP(V6)_PMTUDISC_PROBE value for IP(V6)_MTU_DISCOVER.  This option forces
> us not to fragment, but does not make use of the kernel path MTU discovery. 
> That is, it allows for user-mode MTU probing (or, packetization-layer path
> MTU discovery).  This is particularly useful for diagnostic utilities, like
> traceroute/tracepath.

You should probably send a manpages update to the manpages maintainer too
(cc'ed with fullquote)

-Andi

> 
> Signed-off-by: John Heffner <jheffner@psc.edu>
> ---
>  include/linux/in.h       |    1 +
>  include/linux/in6.h      |    1 +
>  include/linux/skbuff.h   |    3 ++-
>  include/net/ip.h         |    2 +-
>  net/core/skbuff.c        |    2 ++
>  net/ipv4/ip_output.c     |   14 ++++++++++----
>  net/ipv4/ip_sockglue.c   |    2 +-
>  net/ipv4/raw.c           |    3 +++
>  net/ipv6/ip6_output.c    |   12 ++++++++----
>  net/ipv6/ipv6_sockglue.c |    2 +-
>  net/ipv6/raw.c           |    3 +++
>  11 files changed, 33 insertions(+), 12 deletions(-)
> 
> diff --git a/include/linux/in.h b/include/linux/in.h
> index 1912e7c..2dc1f8a 100644
> --- a/include/linux/in.h
> +++ b/include/linux/in.h
> @@ -83,6 +83,7 @@ struct in_addr {
>  #define IP_PMTUDISC_DONT		0	/* Never send DF frames */
>  #define IP_PMTUDISC_WANT		1	/* Use per route hints	*/
>  #define IP_PMTUDISC_DO			2	/* Always DF		*/
> +#define IP_PMTUDISC_PROBE		3	/* Ignore dst pmtu	*/
>  
>  #define IP_MULTICAST_IF			32
>  #define IP_MULTICAST_TTL 		33
> diff --git a/include/linux/in6.h b/include/linux/in6.h
> index 4e8350a..d559fac 100644
> --- a/include/linux/in6.h
> +++ b/include/linux/in6.h
> @@ -179,6 +179,7 @@ struct in6_flowlabel_req
>  #define IPV6_PMTUDISC_DONT		0
>  #define IPV6_PMTUDISC_WANT		1
>  #define IPV6_PMTUDISC_DO		2
> +#define IPV6_PMTUDISC_PROBE		3
>  
>  /* Flowlabel */
>  #define IPV6_FLOWLABEL_MGR	32
> diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
> index 4ff3940..64038b4 100644
> --- a/include/linux/skbuff.h
> +++ b/include/linux/skbuff.h
> @@ -284,7 +284,8 @@ struct sk_buff {
>  				nfctinfo:3;
>  	__u8			pkt_type:3,
>  				fclone:2,
> -				ipvs_property:1;
> +				ipvs_property:1,
> +				ign_dst_mtu;
>  	__be16			protocol;
>  
>  	void			(*destructor)(struct sk_buff *skb);
> diff --git a/include/net/ip.h b/include/net/ip.h
> index e79c3e3..f5874a3 100644
> --- a/include/net/ip.h
> +++ b/include/net/ip.h
> @@ -201,7 +201,7 @@ int ip_decrease_ttl(struct iphdr *iph)
>  static inline
>  int ip_dont_fragment(struct sock *sk, struct dst_entry *dst)
>  {
> -	return (inet_sk(sk)->pmtudisc == IP_PMTUDISC_DO ||
> +	return (inet_sk(sk)->pmtudisc >= IP_PMTUDISC_DO ||
>  		(inet_sk(sk)->pmtudisc == IP_PMTUDISC_WANT &&
>  		 !(dst_metric(dst, RTAX_LOCK)&(1<<RTAX_MTU))));
>  }
> diff --git a/net/core/skbuff.c b/net/core/skbuff.c
> index 702fa8f..5c8515c 100644
> --- a/net/core/skbuff.c
> +++ b/net/core/skbuff.c
> @@ -474,6 +474,7 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
>  #if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
>  	C(ipvs_property);
>  #endif
> +	C(ign_dst_mtu);
>  	C(protocol);
>  	n->destructor = NULL;
>  	C(mark);
> @@ -549,6 +550,7 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
>  #if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
>  	new->ipvs_property = old->ipvs_property;
>  #endif
> +	new->ign_dst_mtu	= old->ign_dst_mtu;
>  #ifdef CONFIG_BRIDGE_NETFILTER
>  	new->nf_bridge	= old->nf_bridge;
>  	nf_bridge_get(old->nf_bridge);
> diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
> index 90bdd53..a7e8944 100644
> --- a/net/ipv4/ip_output.c
> +++ b/net/ipv4/ip_output.c
> @@ -201,7 +201,8 @@ static inline int ip_finish_output(struct sk_buff *skb)
>  		return dst_output(skb);
>  	}
>  #endif
> -	if (skb->len > dst_mtu(skb->dst) && !skb_is_gso(skb))
> +	if (skb->len > dst_mtu(skb->dst) &&
> +	    !skb->ign_dst_mtu && !skb_is_gso(skb))
>  		return ip_fragment(skb, ip_finish_output2);
>  	else
>  		return ip_finish_output2(skb);
> @@ -801,7 +802,9 @@ int ip_append_data(struct sock *sk,
>  			inet->cork.addr = ipc->addr;
>  		}
>  		dst_hold(&rt->u.dst);
> -		inet->cork.fragsize = mtu = dst_mtu(rt->u.dst.path);
> +		inet->cork.fragsize = mtu = inet->pmtudisc == IP_PMTUDISC_PROBE ?
> +		                            rt->u.dst.dev->mtu :
> +		                            dst_mtu(rt->u.dst.path);
>  		inet->cork.rt = rt;
>  		inet->cork.length = 0;
>  		sk->sk_sndmsg_page = NULL;
> @@ -1220,13 +1223,16 @@ int ip_push_pending_frames(struct sock *sk)
>  	 * to fragment the frame generated here. No matter, what transforms
>  	 * how transforms change size of the packet, it will come out.
>  	 */
> -	if (inet->pmtudisc != IP_PMTUDISC_DO)
> +	if (inet->pmtudisc < IP_PMTUDISC_DO)
>  		skb->local_df = 1;
>  
> +	if (inet->pmtudisc == IP_PMTUDISC_PROBE)
> +		skb->ign_dst_mtu = 1;
> +
>  	/* DF bit is set when we want to see DF on outgoing frames.
>  	 * If local_df is set too, we still allow to fragment this frame
>  	 * locally. */
> -	if (inet->pmtudisc == IP_PMTUDISC_DO ||
> +	if (inet->pmtudisc >= IP_PMTUDISC_DO ||
>  	    (skb->len <= dst_mtu(&rt->u.dst) &&
>  	     ip_dont_fragment(sk, &rt->u.dst)))
>  		df = htons(IP_DF);
> diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
> index 23048d9..98fa088 100644
> --- a/net/ipv4/ip_sockglue.c
> +++ b/net/ipv4/ip_sockglue.c
> @@ -536,7 +536,7 @@ static int do_ip_setsockopt(struct sock *sk, int level,
>  			inet->hdrincl = val ? 1 : 0;
>  			break;
>  		case IP_MTU_DISCOVER:
> -			if (val<0 || val>2)
> +			if (val<0 || val>3)
>  				goto e_inval;
>  			inet->pmtudisc = val;
>  			break;
> diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
> index f252f4e..f562262 100644
> --- a/net/ipv4/raw.c
> +++ b/net/ipv4/raw.c
> @@ -302,6 +302,9 @@ static int raw_send_hdrinc(struct sock *sk, void *from, size_t length,
>  	if (err)
>  		goto error_fault;
>  
> +	if (inet->pmtudisc == IP_PMTUDISC_PROBE)
> +		skb->ign_dst_mtu = 1;
> +
>  	/* We don't modify invalid header */
>  	if (length >= sizeof(*iph) && iph->ihl * 4U <= length) {
>  		if (!iph->saddr)
> diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
> index 711dfc3..8b8c04b 100644
> --- a/net/ipv6/ip6_output.c
> +++ b/net/ipv6/ip6_output.c
> @@ -139,8 +139,8 @@ static int ip6_output2(struct sk_buff *skb)
>  
>  int ip6_output(struct sk_buff *skb)
>  {
> -	if ((skb->len > dst_mtu(skb->dst) && !skb_is_gso(skb)) ||
> -				dst_allfrag(skb->dst))
> +	if ((skb->len > dst_mtu(skb->dst) && !skb->ign_dst_mtu &&
> +	     !skb_is_gso(skb)) || dst_allfrag(skb->dst))
>  		return ip6_fragment(skb, ip6_output2);
>  	else
>  		return ip6_output2(skb);
> @@ -574,7 +574,7 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
>  	hlen = ip6_find_1stfragopt(skb, &prevhdr);
>  	nexthdr = *prevhdr;
>  
> -	mtu = dst_mtu(&rt->u.dst);
> +	mtu = skb->ign_dst_mtu ? skb->len : dst_mtu(&rt->u.dst);
>  	if (np && np->frag_size < mtu) {
>  		if (np->frag_size)
>  			mtu = np->frag_size;
> @@ -1015,7 +1015,8 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
>  		inet->cork.fl = *fl;
>  		np->cork.hop_limit = hlimit;
>  		np->cork.tclass = tclass;
> -		mtu = dst_mtu(rt->u.dst.path);
> +		mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
> +		      rt->u.dst.dev->mtu : dst_mtu(rt->u.dst.path);
>  		if (np->frag_size < mtu) {
>  			if (np->frag_size)
>  				mtu = np->frag_size;
> @@ -1303,6 +1304,9 @@ int ip6_push_pending_frames(struct sock *sk)
>  		tmp_skb->sk = NULL;
>  	}
>  
> +	if (np->pmtudisc == IPV6_PMTUDISC_PROBE)
> +		skb->ign_dst_mtu = 1;
> +
>  	ipv6_addr_copy(final_dst, &fl->fl6_dst);
>  	__skb_pull(skb, skb->h.raw - skb->nh.raw);
>  	if (opt && opt->opt_flen)
> diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
> index f5f9582..6e88597 100644
> --- a/net/ipv6/ipv6_sockglue.c
> +++ b/net/ipv6/ipv6_sockglue.c
> @@ -694,7 +694,7 @@ done:
>  		retv = ip6_ra_control(sk, val, NULL);
>  		break;
>  	case IPV6_MTU_DISCOVER:
> -		if (val<0 || val>2)
> +		if (val<0 || val>3)
>  			goto e_inval;
>  		np->pmtudisc = val;
>  		retv = 0;
> diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
> index 75db277..9ef0946 100644
> --- a/net/ipv6/raw.c
> +++ b/net/ipv6/raw.c
> @@ -587,6 +587,9 @@ static int rawv6_send_hdrinc(struct sock *sk, void *from, int length,
>  	if (err)
>  		goto error_fault;
>  
> +	if (np->pmtudisc == IPV6_PMTUDISC_PROBE)
> +		skb->ign_dst_mtu = 1;
> +
>  	IP6_INC_STATS(rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS);
>  	err = NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, rt->u.dst.dev,
>  		      dst_output);
> -- 
> 1.5.0.2.gc260-dirty
> 
> -
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html