From c13a84a830a208fb3443628773c8ca0557773cc7 Mon Sep 17 00:00:00 2001 From: Michal Kubeček Date: Wed, 11 Sep 2013 10:17:27 +0200 Subject: netfilter: nf_conntrack: use RCU safe kfree for conntrack extensions Commit 68b80f11 (netfilter: nf_nat: fix RCU races) introduced RCU protection for freeing extension data when reallocation moves them to a new location. We need the same protection when freeing them in nf_ct_ext_free() in order to prevent a use-after-free by other threads referencing a NAT extension data via bysource list. Signed-off-by: Michal Kubecek Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack_extend.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h index ff95434e50ca..88a1d4060d52 100644 --- a/include/net/netfilter/nf_conntrack_extend.h +++ b/include/net/netfilter/nf_conntrack_extend.h @@ -86,7 +86,7 @@ static inline void nf_ct_ext_destroy(struct nf_conn *ct) static inline void nf_ct_ext_free(struct nf_conn *ct) { if (ct->ext) - kfree(ct->ext); + kfree_rcu(ct->ext, rcu); } /* Add this type, returns pointer to data or NULL. */ -- cgit v1.2.3 From 35e4237973665c8a1ad4e3f7a7cb87573deaa24a Mon Sep 17 00:00:00 2001 From: Joseph Gasparakis Date: Fri, 13 Sep 2013 07:34:13 -0700 Subject: vxlan: Fix sparse warnings This patch fixes sparse warnings when incorrectly handling the port number and using int instead of unsigned int iterating through &vn->sock_list[]. Keeping the port as __be16 also makes things clearer wrt endianess. Also, it was pointed out that vxlan_get_rx_port() had unnecessary checks which got removed. Signed-off-by: Joseph Gasparakis Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 18 ++++++++---------- include/linux/netdevice.h | 8 ++++---- 2 files changed, 12 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index bf64b4191dcc..2400b1beddd5 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -564,7 +564,7 @@ static void vxlan_notify_add_rx_port(struct sock *sk) struct net_device *dev; struct net *net = sock_net(sk); sa_family_t sa_family = sk->sk_family; - u16 port = htons(inet_sk(sk)->inet_sport); + __be16 port = inet_sk(sk)->inet_sport; rcu_read_lock(); for_each_netdev_rcu(net, dev) { @@ -581,7 +581,7 @@ static void vxlan_notify_del_rx_port(struct sock *sk) struct net_device *dev; struct net *net = sock_net(sk); sa_family_t sa_family = sk->sk_family; - u16 port = htons(inet_sk(sk)->inet_sport); + __be16 port = inet_sk(sk)->inet_sport; rcu_read_lock(); for_each_netdev_rcu(net, dev) { @@ -2021,7 +2021,8 @@ static struct device_type vxlan_type = { }; /* Calls the ndo_add_vxlan_port of the caller in order to - * supply the listening VXLAN udp ports. + * supply the listening VXLAN udp ports. Callers are expected + * to implement the ndo_add_vxlan_port. */ void vxlan_get_rx_port(struct net_device *dev) { @@ -2029,16 +2030,13 @@ void vxlan_get_rx_port(struct net_device *dev) struct net *net = dev_net(dev); struct vxlan_net *vn = net_generic(net, vxlan_net_id); sa_family_t sa_family; - u16 port; - int i; - - if (!dev || !dev->netdev_ops || !dev->netdev_ops->ndo_add_vxlan_port) - return; + __be16 port; + unsigned int i; spin_lock(&vn->sock_lock); for (i = 0; i < PORT_HASH_SIZE; ++i) { - hlist_for_each_entry_rcu(vs, vs_head(net, i), hlist) { - port = htons(inet_sk(vs->sock->sk)->inet_sport); + hlist_for_each_entry_rcu(vs, &vn->sock_list[i], hlist) { + port = inet_sk(vs->sock->sk)->inet_sport; sa_family = vs->sock->sk->sk_family; dev->netdev_ops->ndo_add_vxlan_port(dev, sa_family, port); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 041b42a305f6..3de49aca4519 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -950,14 +950,14 @@ struct netdev_phys_port_id { * multiple net devices on single physical port. * * void (*ndo_add_vxlan_port)(struct net_device *dev, - * sa_family_t sa_family, __u16 port); + * sa_family_t sa_family, __be16 port); * Called by vxlan to notiy a driver about the UDP port and socket * address family that vxlan is listnening to. It is called only when * a new port starts listening. The operation is protected by the * vxlan_net->sock_lock. * * void (*ndo_del_vxlan_port)(struct net_device *dev, - * sa_family_t sa_family, __u16 port); + * sa_family_t sa_family, __be16 port); * Called by vxlan to notify the driver about a UDP port and socket * address family that vxlan is not listening to anymore. The operation * is protected by the vxlan_net->sock_lock. @@ -1093,10 +1093,10 @@ struct net_device_ops { struct netdev_phys_port_id *ppid); void (*ndo_add_vxlan_port)(struct net_device *dev, sa_family_t sa_family, - __u16 port); + __be16 port); void (*ndo_del_vxlan_port)(struct net_device *dev, sa_family_t sa_family, - __u16 port); + __be16 port); }; /* -- cgit v1.2.3 From 0f1799ba1a5db4c48b72ac2da2dc70d8c190a73d Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Mon, 16 Sep 2013 20:04:53 +0200 Subject: netfilter: ipset: Consistent userspace testing with nomatch flag The "nomatch" commandline flag should invert the matching at testing, similarly to the --return-nomatch flag of the "set" match of iptables. Until now it worked with the elements with "nomatch" flag only. From now on it works with elements without the flag too, i.e: # ipset n test hash:net # ipset a test 10.0.0.0/24 nomatch # ipset t test 10.0.0.1 10.0.0.1 is NOT in set test. # ipset t test 10.0.0.1 nomatch 10.0.0.1 is in set test. # ipset a test 192.168.0.0/24 # ipset t test 192.168.0.1 192.168.0.1 is in set test. # ipset t test 192.168.0.1 nomatch 192.168.0.1 is NOT in set test. Before the patch the results were ... # ipset t test 192.168.0.1 192.168.0.1 is in set test. # ipset t test 192.168.0.1 nomatch 192.168.0.1 is in set test. Signed-off-by: Jozsef Kadlecsik --- include/linux/netfilter/ipset/ip_set.h | 6 ++++-- net/netfilter/ipset/ip_set_core.c | 3 +-- net/netfilter/ipset/ip_set_hash_ipportnet.c | 4 ++-- net/netfilter/ipset/ip_set_hash_net.c | 4 ++-- net/netfilter/ipset/ip_set_hash_netiface.c | 4 ++-- net/netfilter/ipset/ip_set_hash_netport.c | 4 ++-- 6 files changed, 13 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index d80e2753847c..9ac9fbde7b61 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -296,10 +296,12 @@ ip_set_eexist(int ret, u32 flags) /* Match elements marked with nomatch */ static inline bool -ip_set_enomatch(int ret, u32 flags, enum ipset_adt adt) +ip_set_enomatch(int ret, u32 flags, enum ipset_adt adt, struct ip_set *set) { return adt == IPSET_TEST && - ret == -ENOTEMPTY && ((flags >> 16) & IPSET_FLAG_NOMATCH); + (set->type->features & IPSET_TYPE_NOMATCH) && + ((flags >> 16) & IPSET_FLAG_NOMATCH) && + (ret > 0 || ret == -ENOTEMPTY); } /* Check the NLA_F_NET_BYTEORDER flag */ diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index f77139007983..c8c303c3386f 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1489,8 +1489,7 @@ ip_set_utest(struct sock *ctnl, struct sk_buff *skb, if (ret == -EAGAIN) ret = 1; - return (ret < 0 && ret != -ENOTEMPTY) ? ret : - ret > 0 ? 0 : -IPSET_ERR_EXIST; + return ret > 0 ? 0 : -IPSET_ERR_EXIST; } /* Get headed data of a set */ diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index c6a525373be4..f15f3e28b9c3 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -260,7 +260,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], e.ip = htonl(ip); e.ip2 = htonl(ip2_from & ip_set_hostmask(e.cidr + 1)); ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } @@ -544,7 +544,7 @@ hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) { ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index da740ceb56ae..223e9f546d0f 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -199,7 +199,7 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_TEST || !tb[IPSET_ATTR_IP_TO]) { e.ip = htonl(ip & ip_set_hostmask(e.cidr)); ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret: ip_set_eexist(ret, flags) ? 0 : ret; } @@ -396,7 +396,7 @@ hash_net6_uadt(struct ip_set *set, struct nlattr *tb[], ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index 84ae6f6ce624..7d798d5d5cd3 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -368,7 +368,7 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_TEST || !tb[IPSET_ATTR_IP_TO]) { e.ip = htonl(ip & ip_set_hostmask(e.cidr)); ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } @@ -634,7 +634,7 @@ hash_netiface6_uadt(struct ip_set *set, struct nlattr *tb[], ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index 9a0869853be5..09d6690bee6f 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -244,7 +244,7 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_TEST || !(with_ports || tb[IPSET_ATTR_IP_TO])) { e.ip = htonl(ip & ip_set_hostmask(e.cidr + 1)); ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } @@ -489,7 +489,7 @@ hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) { ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } -- cgit v1.2.3 From 703133de331a7a7df47f31fb9de51dc6f68a9de8 Mon Sep 17 00:00:00 2001 From: Ansis Atteka Date: Wed, 18 Sep 2013 15:29:53 -0700 Subject: ip: generate unique IP identificator if local fragmentation is allowed If local fragmentation is allowed, then ip_select_ident() and ip_select_ident_more() need to generate unique IDs to ensure correct defragmentation on the peer. For example, if IPsec (tunnel mode) has to encrypt large skbs that have local_df bit set, then all IP fragments that belonged to different ESP datagrams would have used the same identificator. If one of these IP fragments would get lost or reordered, then peer could possibly stitch together wrong IP fragments that did not belong to the same datagram. This would lead to a packet loss or data corruption. Signed-off-by: Ansis Atteka Signed-off-by: David S. Miller --- drivers/net/ppp/pptp.c | 2 +- include/net/ip.h | 12 ++++++++---- net/ipv4/igmp.c | 4 ++-- net/ipv4/inetpeer.c | 4 ++-- net/ipv4/ip_output.c | 6 +++--- net/ipv4/ipmr.c | 2 +- net/ipv4/raw.c | 2 +- net/ipv4/xfrm4_mode_tunnel.c | 2 +- net/netfilter/ipvs/ip_vs_xmit.c | 2 +- 9 files changed, 20 insertions(+), 16 deletions(-) (limited to 'include') diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c index 6fa5ae00039f..01805319e1e0 100644 --- a/drivers/net/ppp/pptp.c +++ b/drivers/net/ppp/pptp.c @@ -281,7 +281,7 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb) nf_reset(skb); skb->ip_summed = CHECKSUM_NONE; - ip_select_ident(iph, &rt->dst, NULL); + ip_select_ident(skb, &rt->dst, NULL); ip_send_check(iph); ip_local_out(skb); diff --git a/include/net/ip.h b/include/net/ip.h index 48f55979d842..5e5268807a1c 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -264,9 +264,11 @@ int ip_dont_fragment(struct sock *sk, struct dst_entry *dst) extern void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more); -static inline void ip_select_ident(struct iphdr *iph, struct dst_entry *dst, struct sock *sk) +static inline void ip_select_ident(struct sk_buff *skb, struct dst_entry *dst, struct sock *sk) { - if (iph->frag_off & htons(IP_DF)) { + struct iphdr *iph = ip_hdr(skb); + + if ((iph->frag_off & htons(IP_DF)) && !skb->local_df) { /* This is only to work around buggy Windows95/2000 * VJ compression implementations. If the ID field * does not change, they drop every other packet in @@ -278,9 +280,11 @@ static inline void ip_select_ident(struct iphdr *iph, struct dst_entry *dst, str __ip_select_ident(iph, dst, 0); } -static inline void ip_select_ident_more(struct iphdr *iph, struct dst_entry *dst, struct sock *sk, int more) +static inline void ip_select_ident_more(struct sk_buff *skb, struct dst_entry *dst, struct sock *sk, int more) { - if (iph->frag_off & htons(IP_DF)) { + struct iphdr *iph = ip_hdr(skb); + + if ((iph->frag_off & htons(IP_DF)) && !skb->local_df) { if (sk && inet_sk(sk)->inet_daddr) { iph->id = htons(inet_sk(sk)->inet_id); inet_sk(sk)->inet_id += 1 + more; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index d6c0e64ec97f..dace87f06e5f 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -369,7 +369,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) pip->saddr = fl4.saddr; pip->protocol = IPPROTO_IGMP; pip->tot_len = 0; /* filled in later */ - ip_select_ident(pip, &rt->dst, NULL); + ip_select_ident(skb, &rt->dst, NULL); ((u8 *)&pip[1])[0] = IPOPT_RA; ((u8 *)&pip[1])[1] = 4; ((u8 *)&pip[1])[2] = 0; @@ -714,7 +714,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, iph->daddr = dst; iph->saddr = fl4.saddr; iph->protocol = IPPROTO_IGMP; - ip_select_ident(iph, &rt->dst, NULL); + ip_select_ident(skb, &rt->dst, NULL); ((u8 *)&iph[1])[0] = IPOPT_RA; ((u8 *)&iph[1])[1] = 4; ((u8 *)&iph[1])[2] = 0; diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index 000e3d239d64..33d5537881ed 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -32,8 +32,8 @@ * At the moment of writing this notes identifier of IP packets is generated * to be unpredictable using this code only for packets subjected * (actually or potentially) to defragmentation. I.e. DF packets less than - * PMTU in size uses a constant ID and do not use this code (see - * ip_select_ident() in include/net/ip.h). + * PMTU in size when local fragmentation is disabled use a constant ID and do + * not use this code (see ip_select_ident() in include/net/ip.h). * * Route cache entries hold references to our nodes. * New cache entries get references via lookup by destination IP address in diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index eae2e262fbe5..a04d872c54f9 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -148,7 +148,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk, iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr); iph->saddr = saddr; iph->protocol = sk->sk_protocol; - ip_select_ident(iph, &rt->dst, sk); + ip_select_ident(skb, &rt->dst, sk); if (opt && opt->opt.optlen) { iph->ihl += opt->opt.optlen>>2; @@ -386,7 +386,7 @@ packet_routed: ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0); } - ip_select_ident_more(iph, &rt->dst, sk, + ip_select_ident_more(skb, &rt->dst, sk, (skb_shinfo(skb)->gso_segs ?: 1) - 1); skb->priority = sk->sk_priority; @@ -1324,7 +1324,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, iph->ttl = ttl; iph->protocol = sk->sk_protocol; ip_copy_addrs(iph, fl4); - ip_select_ident(iph, &rt->dst, sk); + ip_select_ident(skb, &rt->dst, sk); if (opt) { iph->ihl += opt->optlen>>2; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 9ae54b09254f..62212c772a4b 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1658,7 +1658,7 @@ static void ip_encap(struct sk_buff *skb, __be32 saddr, __be32 daddr) iph->protocol = IPPROTO_IPIP; iph->ihl = 5; iph->tot_len = htons(skb->len); - ip_select_ident(iph, skb_dst(skb), NULL); + ip_select_ident(skb, skb_dst(skb), NULL); ip_send_check(iph); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index a86c7ae71881..bfec521c717f 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -387,7 +387,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, iph->check = 0; iph->tot_len = htons(length); if (!iph->id) - ip_select_ident(iph, &rt->dst, NULL); + ip_select_ident(skb, &rt->dst, NULL); iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); } diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index eb1dd4d643f2..b5663c37f089 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -117,7 +117,7 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ? 0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF)); - ip_select_ident(top_iph, dst->child, NULL); + ip_select_ident(skb, dst->child, NULL); top_iph->ttl = ip4_dst_hoplimit(dst->child); diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index b75ff6429a04..c47444e4cf8c 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -883,7 +883,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, iph->daddr = cp->daddr.ip; iph->saddr = saddr; iph->ttl = old_iph->ttl; - ip_select_ident(iph, &rt->dst, NULL); + ip_select_ident(skb, &rt->dst, NULL); /* Another hack: avoid icmp_send in ip_fragment */ skb->local_df = 1; -- cgit v1.2.3