From ca4c3fc24e293719fe7410c4e63da9b6bc633b83 Mon Sep 17 00:00:00 2001 From: "fan.du" Date: Tue, 30 Jul 2013 08:33:53 +0800 Subject: net: split rt_genid for ipv4 and ipv6 Current net name space has only one genid for both IPv4 and IPv6, it has below drawbacks: - Add/delete an IPv4 address will invalidate all IPv6 routing table entries. - Insert/remove XFRM policy will also invalidate both IPv4/IPv6 routing table entries even when the policy is only applied for one address family. Thus, this patch attempt to split one genid for two to cater for IPv4 and IPv6 separately in a fine granularity. Signed-off-by: Fan Du Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/ipv4/route.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'net/ipv4/route.c') diff --git a/net/ipv4/route.c b/net/ipv4/route.c index a9a54a236832..e805481eff72 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -435,12 +435,12 @@ static inline int ip_rt_proc_init(void) static inline bool rt_is_expired(const struct rtable *rth) { - return rth->rt_genid != rt_genid(dev_net(rth->dst.dev)); + return rth->rt_genid != rt_genid_ipv4(dev_net(rth->dst.dev)); } void rt_cache_flush(struct net *net) { - rt_genid_bump(net); + rt_genid_bump_ipv4(net); } static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, @@ -1458,7 +1458,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, #endif rth->dst.output = ip_rt_bug; - rth->rt_genid = rt_genid(dev_net(dev)); + rth->rt_genid = rt_genid_ipv4(dev_net(dev)); rth->rt_flags = RTCF_MULTICAST; rth->rt_type = RTN_MULTICAST; rth->rt_is_input= 1; @@ -1589,7 +1589,7 @@ static int __mkroute_input(struct sk_buff *skb, goto cleanup; } - rth->rt_genid = rt_genid(dev_net(rth->dst.dev)); + rth->rt_genid = rt_genid_ipv4(dev_net(rth->dst.dev)); rth->rt_flags = flags; rth->rt_type = res->type; rth->rt_is_input = 1; @@ -1760,7 +1760,7 @@ local_input: rth->dst.tclassid = itag; #endif - rth->rt_genid = rt_genid(net); + rth->rt_genid = rt_genid_ipv4(net); rth->rt_flags = flags|RTCF_LOCAL; rth->rt_type = res.type; rth->rt_is_input = 1; @@ -1945,7 +1945,7 @@ add: rth->dst.output = ip_output; - rth->rt_genid = rt_genid(dev_net(dev_out)); + rth->rt_genid = rt_genid_ipv4(dev_net(dev_out)); rth->rt_flags = flags; rth->rt_type = type; rth->rt_is_input = 0; @@ -2227,7 +2227,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or rt->rt_iif = ort->rt_iif; rt->rt_pmtu = ort->rt_pmtu; - rt->rt_genid = rt_genid(net); + rt->rt_genid = rt_genid_ipv4(net); rt->rt_flags = ort->rt_flags; rt->rt_type = ort->rt_type; rt->rt_gateway = ort->rt_gateway; @@ -2665,7 +2665,7 @@ static __net_initdata struct pernet_operations sysctl_route_ops = { static __net_init int rt_genid_init(struct net *net) { - atomic_set(&net->rt_genid, 0); + atomic_set(&net->ipv4.rt_genid, 0); atomic_set(&net->fnhe_genid, 0); get_random_bytes(&net->ipv4.dev_addr_genid, sizeof(net->ipv4.dev_addr_genid)); -- cgit v1.2.3 From 734d2725db879f3f6fcdc2b1d2a5deae105f5e95 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 18 Aug 2013 19:08:07 -0700 Subject: ipv4: raise IP_MAX_MTU to theoretical limit As discussed last year [1], there is no compelling reason to limit IPv4 MTU to 0xFFF0, while real limit is 0xFFFF [1] : http://marc.info/?l=linux-netdev&m=135607247609434&w=2 Willem raised this issue again because some of our internal regression tests broke after lo mtu being set to 65536. IP_MTU reports 0xFFF0, and the test attempts to send a RAW datagram of mtu + 1 bytes, expecting the send() to fail, but it does not. Alexey raised interesting points about TCP MSS, that should be addressed in follow-up patches in TCP stack if needed, as someone could also set an odd mtu anyway. Signed-off-by: Eric Dumazet Cc: Alexey Kuznetsov Cc: Willem de Bruijn Signed-off-by: David S. Miller --- net/ipv4/route.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'net/ipv4/route.c') diff --git a/net/ipv4/route.c b/net/ipv4/route.c index e805481eff72..727f4365bcdf 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -112,7 +112,8 @@ #define RT_FL_TOS(oldflp4) \ ((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK)) -#define IP_MAX_MTU 0xFFF0 +/* IPv4 datagram length is stored into 16bit field (tot_len) */ +#define IP_MAX_MTU 0xFFFF #define RT_GC_TIMEOUT (300*HZ) @@ -1227,10 +1228,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) mtu = 576; } - if (mtu > IP_MAX_MTU) - mtu = IP_MAX_MTU; - - return mtu; + return min_t(unsigned int, mtu, IP_MAX_MTU); } static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr) -- cgit v1.2.3