Commit 7ba9d103 authored by David S. Miller's avatar David S. Miller
Browse files

Merge branch 'mpls-fragmentation-and-gso-fixes' 



David Ahern says:

====================
net: mpls: fragmentation and gso fixes for locally originated traffic

This series fixes mtu and fragmentation for tunnels using lwtunnel
output redirect, and fixes GSO for MPLS for locally originated traffic
reported by Lennert Buytenhek.

A follow on series will address fragmentation and GSO for forwarded
MPLS traffic. Hardware offload of GSO with MPLS also needs to be
addressed.

Simon: Can you verify this works with OVS for single and multiple
       labels?

v4
- more updates to mpls_gso_segment per Alex's comments (thanks, Alex)
- updates to teaching OVS about marking MPLS labels as the network header

v3
- updates to mpls_gso_segment per Alex's comments
- dropped skb->encapsulation = 1 from mpls_xmit per Alex's comment

v2
- consistent use of network_header in skb to fix GSO for MPLS
- update MPLS code in OVS to network_header and inner_network_header
====================

Tested-by: default avatarSimon Horman <simon.horman@netronome.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parents 41852497 607fca9a

drivers/net/veth.c

+1 −0
Original line number Diff line number Diff line
@@ -340,6 +340,7 @@ static void veth_setup(struct net_device *dev) 


	dev->hw_features = VETH_FEATURES;

	dev->hw_enc_features = VETH_FEATURES;

	dev->mpls_features = NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE;

}



/*

include/net/lwtunnel.h

+44 −0
Original line number Diff line number Diff line
@@ -13,6 +13,13 @@ 
/* lw tunnel state flags */

#define LWTUNNEL_STATE_OUTPUT_REDIRECT	BIT(0)

#define LWTUNNEL_STATE_INPUT_REDIRECT	BIT(1)

#define LWTUNNEL_STATE_XMIT_REDIRECT	BIT(2)



enum {

	LWTUNNEL_XMIT_DONE,

	LWTUNNEL_XMIT_CONTINUE,

};





struct lwtunnel_state {

	__u16		type;
@@ -21,6 +28,7 @@ struct lwtunnel_state { 
	int		(*orig_output)(struct net *net, struct sock *sk, struct sk_buff *skb);

	int		(*orig_input)(struct sk_buff *);

	int             len;

	__u16		headroom;

	__u8            data[0];

};
@@ -34,6 +42,7 @@ struct lwtunnel_encap_ops { 
			  struct lwtunnel_state *lwtstate);

	int (*get_encap_size)(struct lwtunnel_state *lwtstate);

	int (*cmp_encap)(struct lwtunnel_state *a, struct lwtunnel_state *b);

	int (*xmit)(struct sk_buff *skb);

};



#ifdef CONFIG_LWTUNNEL
@@ -75,6 +84,24 @@ static inline bool lwtunnel_input_redirect(struct lwtunnel_state *lwtstate) 


	return false;

}



static inline bool lwtunnel_xmit_redirect(struct lwtunnel_state *lwtstate)

{

	if (lwtstate && (lwtstate->flags & LWTUNNEL_STATE_XMIT_REDIRECT))

		return true;



	return false;

}



static inline unsigned int lwtunnel_headroom(struct lwtunnel_state *lwtstate,

					     unsigned int mtu)

{

	if (lwtunnel_xmit_redirect(lwtstate) && lwtstate->headroom < mtu)

		return lwtstate->headroom;



	return 0;

}



int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op,

			   unsigned int num);

int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op,
@@ -90,6 +117,7 @@ struct lwtunnel_state *lwtunnel_state_alloc(int hdr_len); 
int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b);

int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb);

int lwtunnel_input(struct sk_buff *skb);

int lwtunnel_xmit(struct sk_buff *skb);



#else
@@ -117,6 +145,17 @@ static inline bool lwtunnel_input_redirect(struct lwtunnel_state *lwtstate) 
	return false;

}



static inline bool lwtunnel_xmit_redirect(struct lwtunnel_state *lwtstate)

{

	return false;

}



static inline unsigned int lwtunnel_headroom(struct lwtunnel_state *lwtstate,

					     unsigned int mtu)

{

	return 0;

}



static inline int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op,

					 unsigned int num)

{
@@ -170,6 +209,11 @@ static inline int lwtunnel_input(struct sk_buff *skb) 
	return -EOPNOTSUPP;

}



static inline int lwtunnel_xmit(struct sk_buff *skb)

{

	return -EOPNOTSUPP;

}



#endif /* CONFIG_LWTUNNEL */



#define MODULE_ALIAS_RTNL_LWT(encap_type) MODULE_ALIAS("rtnl-lwt-" __stringify(encap_type))

net/core/lwtunnel.c

+35 −0
Original line number Diff line number Diff line
@@ -251,6 +251,41 @@ drop: 
}

EXPORT_SYMBOL(lwtunnel_output);



int lwtunnel_xmit(struct sk_buff *skb)

{

	struct dst_entry *dst = skb_dst(skb);

	const struct lwtunnel_encap_ops *ops;

	struct lwtunnel_state *lwtstate;

	int ret = -EINVAL;



	if (!dst)

		goto drop;



	lwtstate = dst->lwtstate;



	if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||

	    lwtstate->type > LWTUNNEL_ENCAP_MAX)

		return 0;



	ret = -EOPNOTSUPP;

	rcu_read_lock();

	ops = rcu_dereference(lwtun_encaps[lwtstate->type]);

	if (likely(ops && ops->xmit))

		ret = ops->xmit(skb);

	rcu_read_unlock();



	if (ret == -EOPNOTSUPP)

		goto drop;



	return ret;



drop:

	kfree_skb(skb);



	return ret;

}

EXPORT_SYMBOL(lwtunnel_xmit);



int lwtunnel_input(struct sk_buff *skb)

{

	struct dst_entry *dst = skb_dst(skb);

net/ipv4/ip_output.c

+8 −0
Original line number Diff line number Diff line
@@ -73,6 +73,7 @@ 
#include <net/icmp.h>

#include <net/checksum.h>

#include <net/inetpeer.h>

#include <net/lwtunnel.h>

#include <linux/igmp.h>

#include <linux/netfilter_ipv4.h>

#include <linux/netfilter_bridge.h>
@@ -197,6 +198,13 @@ static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *s 
		skb = skb2;

	}



	if (lwtunnel_xmit_redirect(dst->lwtstate)) {

		int res = lwtunnel_xmit(skb);



		if (res < 0 || res == LWTUNNEL_XMIT_DONE)

			return res;

	}



	rcu_read_lock_bh();

	nexthop = (__force u32) rt_nexthop(rt, ip_hdr(skb)->daddr);

	neigh = __ipv4_neigh_lookup_noref(dev, nexthop);

net/ipv4/route.c

+3 −1
Original line number Diff line number Diff line
@@ -1246,7 +1246,9 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) 
			mtu = 576;

	}



	return min_t(unsigned int, mtu, IP_MAX_MTU);

	mtu = min_t(unsigned int, mtu, IP_MAX_MTU);



	return mtu - lwtunnel_headroom(dst->lwtstate, mtu);

}



static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr)

CRA Git | Maintained and supported by SUSTech CRA and CCSE