Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit f87c10a8 authored by Hannes Frederic Sowa's avatar Hannes Frederic Sowa Committed by David S. Miller
Browse files

ipv4: introduce ip_dst_mtu_maybe_forward and protect forwarding path against pmtu spoofing 



While forwarding we should not use the protocol path mtu to calculate
the mtu for a forwarded packet but instead use the interface mtu.

We mark forwarded skbs in ip_forward with IPSKB_FORWARDED, which was
introduced for multicast forwarding. But as it does not conflict with
our usage in unicast code path it is perfect for reuse.

I moved the functions ip_sk_accept_pmtu, ip_sk_use_pmtu and ip_skb_dst_mtu
along with the new ip_dst_mtu_maybe_forward to net/ip.h to fix circular
dependencies because of IPSKB_FORWARDED.

Because someone might have written a software which does probe
destinations manually and expects the kernel to honour those path mtus
I introduced a new per-namespace "ip_forward_use_pmtu" knob so someone
can disable this new behaviour. We also still use mtus which are locked on a
route for forwarding.

The reason for this change is, that path mtus information can be injected
into the kernel via e.g. icmp_err protocol handler without verification
of local sockets. As such, this could cause the IPv4 forwarding path to
wrongfully emit fragmentation needed notifications or start to fragment
packets along a path.

Tunnel and ipsec output paths clear IPCB again, thus IPSKB_FORWARDED
won't be set and further fragmentation logic will use the path mtu to
determine the fragmentation size. They also recheck packet size with
help of path mtu discovery and report appropriate errors.

Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: David Miller <davem@davemloft.net>
Cc: John Heffner <johnwheffner@gmail.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: default avatarHannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 6c76a07a

Documentation/networking/ip-sysctl.txt

+13 −0
Original line number Diff line number Diff line
@@ -32,6 +32,19 @@ ip_no_pmtu_disc - INTEGER 
min_pmtu - INTEGER

	default 552 - minimum discovered Path MTU



ip_forward_use_pmtu - BOOLEAN

	By default we don't trust protocol path MTUs while forwarding

	because they could be easily forged and can lead to unwanted

	fragmentation by the router.

	You only need to enable this if you have user-space software

	which tries to discover path mtus by itself and depends on the

	kernel honoring this information. This is normally not the

	case.

	Default: 0 (disabled)

	Possible values:

	0 - disabled

	1 - enabled



route/max_size - INTEGER

	Maximum number of routes allowed in the kernel.  Increase

	this when using large numbers of interfaces and/or routes.

include/net/ip.h

+33 −0
Original line number Diff line number Diff line
@@ -263,6 +263,39 @@ int ip_dont_fragment(struct sock *sk, struct dst_entry *dst) 
		 !(dst_metric_locked(dst, RTAX_MTU)));

}



static inline bool ip_sk_accept_pmtu(const struct sock *sk)

{

	return inet_sk(sk)->pmtudisc != IP_PMTUDISC_INTERFACE;

}



static inline bool ip_sk_use_pmtu(const struct sock *sk)

{

	return inet_sk(sk)->pmtudisc < IP_PMTUDISC_PROBE;

}



static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst,

						    bool forwarding)

{

	struct net *net = dev_net(dst->dev);



	if (net->ipv4.sysctl_ip_fwd_use_pmtu ||

	    dst_metric_locked(dst, RTAX_MTU) ||

	    !forwarding)

		return dst_mtu(dst);



	return min(dst->dev->mtu, IP_MAX_MTU);

}



static inline unsigned int ip_skb_dst_mtu(const struct sk_buff *skb)

{

	if (!skb->sk || ip_sk_use_pmtu(skb->sk)) {

		bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED;

		return ip_dst_mtu_maybe_forward(skb_dst(skb), forwarding);

	} else {

		return min(skb_dst(skb)->dev->mtu, IP_MAX_MTU);

	}

}



void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more);



static inline void ip_select_ident(struct sk_buff *skb, struct dst_entry *dst, struct sock *sk)

include/net/netns/ipv4.h

+1 −0
Original line number Diff line number Diff line
@@ -70,6 +70,7 @@ struct netns_ipv4 { 


	int sysctl_tcp_ecn;

	int sysctl_ip_no_pmtu_disc;

	int sysctl_ip_fwd_use_pmtu;



	kgid_t sysctl_ping_group_range[2];

include/net/route.h

+3 −16
Original line number Diff line number Diff line
@@ -36,6 +36,9 @@ 
#include <linux/cache.h>

#include <linux/security.h>



/* IPv4 datagram length is stored into 16bit field (tot_len) */

#define IP_MAX_MTU	0xFFFFU



#define RTO_ONLINK	0x01



#define RT_CONN_FLAGS(sk)   (RT_TOS(inet_sk(sk)->tos) | sock_flag(sk, SOCK_LOCALROUTE))
@@ -311,20 +314,4 @@ static inline int ip4_dst_hoplimit(const struct dst_entry *dst) 
	return hoplimit;

}



static inline bool ip_sk_accept_pmtu(const struct sock *sk)

{

	return inet_sk(sk)->pmtudisc != IP_PMTUDISC_INTERFACE;

}



static inline bool ip_sk_use_pmtu(const struct sock *sk)

{

	return inet_sk(sk)->pmtudisc < IP_PMTUDISC_PROBE;

}



static inline int ip_skb_dst_mtu(const struct sk_buff *skb)

{

	return (!skb->sk || ip_sk_use_pmtu(skb->sk)) ?

	       dst_mtu(skb_dst(skb)) : skb_dst(skb)->dev->mtu;

}



#endif	/* _ROUTE_H */

net/ipv4/ip_forward.c

+5 −2
Original line number Diff line number Diff line
@@ -54,6 +54,7 @@ static int ip_forward_finish(struct sk_buff *skb) 


int ip_forward(struct sk_buff *skb)

{

	u32 mtu;

	struct iphdr *iph;	/* Our header */

	struct rtable *rt;	/* Route we use */

	struct ip_options *opt	= &(IPCB(skb)->opt);
@@ -88,11 +89,13 @@ int ip_forward(struct sk_buff *skb) 
	if (opt->is_strictroute && rt->rt_uses_gateway)

		goto sr_failed;



	if (unlikely(skb->len > dst_mtu(&rt->dst) && !skb_is_gso(skb) &&

	IPCB(skb)->flags |= IPSKB_FORWARDED;

	mtu = ip_dst_mtu_maybe_forward(&rt->dst, true);

	if (unlikely(skb->len > mtu && !skb_is_gso(skb) &&

		     (ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) {

		IP_INC_STATS(dev_net(rt->dst.dev), IPSTATS_MIB_FRAGFAILS);

		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,

			  htonl(dst_mtu(&rt->dst)));

			  htonl(mtu));

		goto drop;

	}