From cc31d43b4154ad5a7d8aa5543255a93b7e89edc2 Mon Sep 17 00:00:00 2001 From: Pau Espin Pedrol Date: Fri, 6 Jan 2017 20:33:27 +0100 Subject: netfilter: use fwmark_reflect in nf_send_reset Otherwise, RST packets generated by ipt_REJECT always have mark 0 when the routing is checked later in the same code path. Fixes: e110861f8609 ("net: add a sysctl to reflect the fwmark on replies") Cc: Lorenzo Colitti Signed-off-by: Pau Espin Pedrol Signed-off-by: Pablo Neira Ayuso --- net/ipv6/netfilter/nf_reject_ipv6.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'net/ipv6') diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index 10090400c72f..eedee5d108d9 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -157,6 +157,7 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook) fl6.fl6_sport = otcph->dest; fl6.fl6_dport = otcph->source; fl6.flowi6_oif = l3mdev_master_ifindex(skb_dst(oldskb)->dev); + fl6.flowi6_mark = IP6_REPLY_MARK(net, oldskb->mark); security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6)); dst = ip6_route_output(net, NULL, &fl6); if (dst->error) { @@ -180,6 +181,8 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook) skb_dst_set(nskb, dst); + nskb->mark = fl6.flowi6_mark; + skb_reserve(nskb, hh_len + dst->header_len); ip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_TCP, ip6_dst_hoplimit(dst)); -- cgit v1.2.3 From bf99b4ded5f8a4767dbb9d180626f06c51f9881f Mon Sep 17 00:00:00 2001 From: Pau Espin Pedrol Date: Fri, 6 Jan 2017 20:33:28 +0100 Subject: tcp: fix mark propagation with fwmark_reflect enabled Otherwise, RST packets generated by the TCP stack for non-existing sockets always have mark 0. The mark from the original packet is assigned to the netns_ipv4/6 socket used to send the response so that it can get copied into the response skb when the socket sends it. Fixes: e110861f8609 ("net: add a sysctl to reflect the fwmark on replies") Cc: Lorenzo Colitti Signed-off-by: Pau Espin Pedrol Signed-off-by: Pablo Neira Ayuso --- net/ipv4/ip_output.c | 1 + net/ipv6/tcp_ipv6.c | 1 + 2 files changed, 2 insertions(+) (limited to 'net/ipv6') diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index fac275c48108..b67719f45953 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1629,6 +1629,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, sk->sk_protocol = ip_hdr(skb)->protocol; sk->sk_bound_dev_if = arg->bound_dev_if; sk->sk_sndbuf = sysctl_wmem_default; + sk->sk_mark = fl4.flowi4_mark; err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base, len, 0, &ipc, &rt, MSG_DONTWAIT); if (unlikely(err)) { diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 73bc8fc68acd..2b20622a5824 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -840,6 +840,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL); if (!IS_ERR(dst)) { skb_dst_set(buff, dst); + ctl_sk->sk_mark = fl6.flowi6_mark; ip6_xmit(ctl_sk, buff, &fl6, NULL, tclass); TCP_INC_STATS(net, TCP_MIB_OUTSEGS); if (rst) -- cgit v1.2.3 From 6443ebc3fdd6f3c766d9442c18be274b3d736050 Mon Sep 17 00:00:00 2001 From: Liping Zhang Date: Sat, 7 Jan 2017 20:49:18 +0800 Subject: netfilter: rpfilter: fix incorrect loopback packet judgment Currently, we check the existing rtable in PREROUTING hook, if RTCF_LOCAL is set, we assume that the packet is loopback. But this assumption is incorrect, for example, a packet encapsulated in ipsec transport mode was received and routed to local, after decapsulation, it would be delivered to local again, and the rtable was not dropped, so RTCF_LOCAL check would trigger. But actually, the packet was not loopback. So for these normal loopback packets, we can check whether the in device is IFF_LOOPBACK or not. For these locally generated broadcast/multicast, we can check whether the skb->pkt_type is PACKET_LOOPBACK or not. Finally, there's a subtle difference between nft fib expr and xtables rpfilter extension, user can add the following nft rule to do strict rpfilter check: # nft add rule x y meta iif eth0 fib saddr . iif oif != eth0 drop So when the packet is loopback, it's better to store the in device instead of the LOOPBACK_IFINDEX, otherwise, after adding the above nft rule, locally generated broad/multicast packets will be dropped incorrectly. Fixes: f83a7ea2075c ("netfilter: xt_rpfilter: skip locally generated broadcast/multicast, too") Fixes: f6d0cbcf09c5 ("netfilter: nf_tables: add fib expression") Signed-off-by: Liping Zhang Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nft_fib.h | 6 ++++++ net/ipv4/netfilter/ipt_rpfilter.c | 8 ++++---- net/ipv4/netfilter/nft_fib_ipv4.c | 15 +++++---------- net/ipv6/netfilter/ip6t_rpfilter.c | 8 ++++---- net/ipv6/netfilter/nft_fib_ipv6.c | 13 ++++--------- 5 files changed, 23 insertions(+), 27 deletions(-) (limited to 'net/ipv6') diff --git a/include/net/netfilter/nft_fib.h b/include/net/netfilter/nft_fib.h index cbedda077db2..5ceb2205e4e3 100644 --- a/include/net/netfilter/nft_fib.h +++ b/include/net/netfilter/nft_fib.h @@ -9,6 +9,12 @@ struct nft_fib { extern const struct nla_policy nft_fib_policy[]; +static inline bool +nft_fib_is_loopback(const struct sk_buff *skb, const struct net_device *in) +{ + return skb->pkt_type == PACKET_LOOPBACK || in->flags & IFF_LOOPBACK; +} + int nft_fib_dump(struct sk_buff *skb, const struct nft_expr *expr); int nft_fib_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]); diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c index f273098e48fd..37fb9552e858 100644 --- a/net/ipv4/netfilter/ipt_rpfilter.c +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -63,10 +63,10 @@ static bool rpfilter_lookup_reverse(struct net *net, struct flowi4 *fl4, return dev_match || flags & XT_RPFILTER_LOOSE; } -static bool rpfilter_is_local(const struct sk_buff *skb) +static bool +rpfilter_is_loopback(const struct sk_buff *skb, const struct net_device *in) { - const struct rtable *rt = skb_rtable(skb); - return rt && (rt->rt_flags & RTCF_LOCAL); + return skb->pkt_type == PACKET_LOOPBACK || in->flags & IFF_LOOPBACK; } static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) @@ -79,7 +79,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) info = par->matchinfo; invert = info->flags & XT_RPFILTER_INVERT; - if (rpfilter_is_local(skb)) + if (rpfilter_is_loopback(skb, xt_in(par))) return true ^ invert; iph = ip_hdr(skb); diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c index 965b1a161369..2981291910dd 100644 --- a/net/ipv4/netfilter/nft_fib_ipv4.c +++ b/net/ipv4/netfilter/nft_fib_ipv4.c @@ -26,13 +26,6 @@ static __be32 get_saddr(__be32 addr) return addr; } -static bool fib4_is_local(const struct sk_buff *skb) -{ - const struct rtable *rt = skb_rtable(skb); - - return rt && (rt->rt_flags & RTCF_LOCAL); -} - #define DSCP_BITS 0xfc void nft_fib4_eval_type(const struct nft_expr *expr, struct nft_regs *regs, @@ -95,8 +88,10 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs, else oif = NULL; - if (nft_hook(pkt) == NF_INET_PRE_ROUTING && fib4_is_local(pkt->skb)) { - nft_fib_store_result(dest, priv->result, pkt, LOOPBACK_IFINDEX); + if (nft_hook(pkt) == NF_INET_PRE_ROUTING && + nft_fib_is_loopback(pkt->skb, nft_in(pkt))) { + nft_fib_store_result(dest, priv->result, pkt, + nft_in(pkt)->ifindex); return; } @@ -131,7 +126,7 @@ void nft_fib4_eval(const struct nft_expr *expr, struct nft_regs *regs, switch (res.type) { case RTN_UNICAST: break; - case RTN_LOCAL: /* should not appear here, see fib4_is_local() above */ + case RTN_LOCAL: /* Should not see RTN_LOCAL here */ return; default: break; diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c index d5263dc364a9..b12e61b7b16c 100644 --- a/net/ipv6/netfilter/ip6t_rpfilter.c +++ b/net/ipv6/netfilter/ip6t_rpfilter.c @@ -72,10 +72,10 @@ static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb, return ret; } -static bool rpfilter_is_local(const struct sk_buff *skb) +static bool +rpfilter_is_loopback(const struct sk_buff *skb, const struct net_device *in) { - const struct rt6_info *rt = (const void *) skb_dst(skb); - return rt && (rt->rt6i_flags & RTF_LOCAL); + return skb->pkt_type == PACKET_LOOPBACK || in->flags & IFF_LOOPBACK; } static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) @@ -85,7 +85,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) struct ipv6hdr *iph; bool invert = info->flags & XT_RPFILTER_INVERT; - if (rpfilter_is_local(skb)) + if (rpfilter_is_loopback(skb, xt_in(par))) return true ^ invert; iph = ipv6_hdr(skb); diff --git a/net/ipv6/netfilter/nft_fib_ipv6.c b/net/ipv6/netfilter/nft_fib_ipv6.c index c947aad8bcc6..765facf03d45 100644 --- a/net/ipv6/netfilter/nft_fib_ipv6.c +++ b/net/ipv6/netfilter/nft_fib_ipv6.c @@ -18,13 +18,6 @@ #include #include -static bool fib6_is_local(const struct sk_buff *skb) -{ - const struct rt6_info *rt = (const void *)skb_dst(skb); - - return rt && (rt->rt6i_flags & RTF_LOCAL); -} - static int get_ifindex(const struct net_device *dev) { return dev ? dev->ifindex : 0; @@ -164,8 +157,10 @@ void nft_fib6_eval(const struct nft_expr *expr, struct nft_regs *regs, lookup_flags = nft_fib6_flowi_init(&fl6, priv, pkt, oif); - if (nft_hook(pkt) == NF_INET_PRE_ROUTING && fib6_is_local(pkt->skb)) { - nft_fib_store_result(dest, priv->result, pkt, LOOPBACK_IFINDEX); + if (nft_hook(pkt) == NF_INET_PRE_ROUTING && + nft_fib_is_loopback(pkt->skb, nft_in(pkt))) { + nft_fib_store_result(dest, priv->result, pkt, + nft_in(pkt)->ifindex); return; } -- cgit v1.2.3 From 9ed59592e3e379b2e9557dc1d9e9ec8fcbb33f16 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 17 Jan 2017 14:57:36 -0800 Subject: lwtunnel: fix autoload of lwt modules Trying to add an mpls encap route when the MPLS modules are not loaded hangs. For example: CONFIG_MPLS=y CONFIG_NET_MPLS_GSO=m CONFIG_MPLS_ROUTING=m CONFIG_MPLS_IPTUNNEL=m $ ip route add 10.10.10.10/32 encap mpls 100 via inet 10.100.1.2 The ip command hangs: root 880 826 0 21:25 pts/0 00:00:00 ip route add 10.10.10.10/32 encap mpls 100 via inet 10.100.1.2 $ cat /proc/880/stack [] call_usermodehelper_exec+0xd6/0x134 [] __request_module+0x27b/0x30a [] lwtunnel_build_state+0xe4/0x178 [] fib_create_info+0x47f/0xdd4 [] fib_table_insert+0x90/0x41f [] inet_rtm_newroute+0x4b/0x52 ... modprobe is trying to load rtnl-lwt-MPLS: root 881 5 0 21:25 ? 00:00:00 /sbin/modprobe -q -- rtnl-lwt-MPLS and it hangs after loading mpls_router: $ cat /proc/881/stack [] rtnl_lock+0x12/0x14 [] register_netdevice_notifier+0x16/0x179 [] mpls_init+0x25/0x1000 [mpls_router] [] do_one_initcall+0x8e/0x13f [] do_init_module+0x5a/0x1e5 [] load_module+0x13bd/0x17d6 ... The problem is that lwtunnel_build_state is called with rtnl lock held preventing mpls_init from registering. Given the potential references held by the time lwtunnel_build_state it can not drop the rtnl lock to the load module. So, extract the module loading code from lwtunnel_build_state into a new function to validate the encap type. The new function is called while converting the user request into a fib_config which is well before any table, device or fib entries are examined. Fixes: 745041e2aaf1 ("lwtunnel: autoload of lwt modules") Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/lwtunnel.h | 11 +++++++++ net/core/lwtunnel.c | 62 ++++++++++++++++++++++++++++++++++++++++++++----- net/ipv4/fib_frontend.c | 8 +++++++ net/ipv6/route.c | 12 +++++++++- 4 files changed, 86 insertions(+), 7 deletions(-) (limited to 'net/ipv6') diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h index d4c1c75b8862..0b585f1fd340 100644 --- a/include/net/lwtunnel.h +++ b/include/net/lwtunnel.h @@ -105,6 +105,8 @@ 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, unsigned int num); +int lwtunnel_valid_encap_type(u16 encap_type); +int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len); int lwtunnel_build_state(struct net_device *dev, u16 encap_type, struct nlattr *encap, unsigned int family, const void *cfg, @@ -168,6 +170,15 @@ static inline int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op, return -EOPNOTSUPP; } +static inline int lwtunnel_valid_encap_type(u16 encap_type) +{ + return -EOPNOTSUPP; +} +static inline int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len) +{ + return -EOPNOTSUPP; +} + static inline int lwtunnel_build_state(struct net_device *dev, u16 encap_type, struct nlattr *encap, unsigned int family, const void *cfg, diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c index a5d4e866ce88..47b1dd65947b 100644 --- a/net/core/lwtunnel.c +++ b/net/core/lwtunnel.c @@ -26,6 +26,7 @@ #include #include #include +#include #ifdef CONFIG_MODULES @@ -114,25 +115,74 @@ int lwtunnel_build_state(struct net_device *dev, u16 encap_type, ret = -EOPNOTSUPP; rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[encap_type]); + if (likely(ops && ops->build_state)) + ret = ops->build_state(dev, encap, family, cfg, lws); + rcu_read_unlock(); + + return ret; +} +EXPORT_SYMBOL(lwtunnel_build_state); + +int lwtunnel_valid_encap_type(u16 encap_type) +{ + const struct lwtunnel_encap_ops *ops; + int ret = -EINVAL; + + if (encap_type == LWTUNNEL_ENCAP_NONE || + encap_type > LWTUNNEL_ENCAP_MAX) + return ret; + + rcu_read_lock(); + ops = rcu_dereference(lwtun_encaps[encap_type]); + rcu_read_unlock(); #ifdef CONFIG_MODULES if (!ops) { const char *encap_type_str = lwtunnel_encap_str(encap_type); if (encap_type_str) { - rcu_read_unlock(); + __rtnl_unlock(); request_module("rtnl-lwt-%s", encap_type_str); + rtnl_lock(); + rcu_read_lock(); ops = rcu_dereference(lwtun_encaps[encap_type]); + rcu_read_unlock(); } } #endif - if (likely(ops && ops->build_state)) - ret = ops->build_state(dev, encap, family, cfg, lws); - rcu_read_unlock(); + return ops ? 0 : -EOPNOTSUPP; +} +EXPORT_SYMBOL(lwtunnel_valid_encap_type); - return ret; +int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining) +{ + struct rtnexthop *rtnh = (struct rtnexthop *)attr; + struct nlattr *nla_entype; + struct nlattr *attrs; + struct nlattr *nla; + u16 encap_type; + int attrlen; + + while (rtnh_ok(rtnh, remaining)) { + attrlen = rtnh_attrlen(rtnh); + if (attrlen > 0) { + attrs = rtnh_attrs(rtnh); + nla = nla_find(attrs, attrlen, RTA_ENCAP); + nla_entype = nla_find(attrs, attrlen, RTA_ENCAP_TYPE); + + if (nla_entype) { + encap_type = nla_get_u16(nla_entype); + + if (lwtunnel_valid_encap_type(encap_type) != 0) + return -EOPNOTSUPP; + } + } + rtnh = rtnh_next(rtnh, &remaining); + } + + return 0; } -EXPORT_SYMBOL(lwtunnel_build_state); +EXPORT_SYMBOL(lwtunnel_valid_encap_type_attr); void lwtstate_free(struct lwtunnel_state *lws) { diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index eae0332b0e8c..7db2ad2e82d3 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -46,6 +46,7 @@ #include #include #include +#include #include #ifndef CONFIG_IP_MULTIPLE_TABLES @@ -677,6 +678,10 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, cfg->fc_mx_len = nla_len(attr); break; case RTA_MULTIPATH: + err = lwtunnel_valid_encap_type_attr(nla_data(attr), + nla_len(attr)); + if (err < 0) + goto errout; cfg->fc_mp = nla_data(attr); cfg->fc_mp_len = nla_len(attr); break; @@ -691,6 +696,9 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, break; case RTA_ENCAP_TYPE: cfg->fc_encap_type = nla_get_u16(attr); + err = lwtunnel_valid_encap_type(cfg->fc_encap_type); + if (err < 0) + goto errout; break; } } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 4f6b067c8753..7ea85370c11c 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2896,6 +2896,11 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, if (tb[RTA_MULTIPATH]) { cfg->fc_mp = nla_data(tb[RTA_MULTIPATH]); cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]); + + err = lwtunnel_valid_encap_type_attr(cfg->fc_mp, + cfg->fc_mp_len); + if (err < 0) + goto errout; } if (tb[RTA_PREF]) { @@ -2909,9 +2914,14 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, if (tb[RTA_ENCAP]) cfg->fc_encap = tb[RTA_ENCAP]; - if (tb[RTA_ENCAP_TYPE]) + if (tb[RTA_ENCAP_TYPE]) { cfg->fc_encap_type = nla_get_u16(tb[RTA_ENCAP_TYPE]); + err = lwtunnel_valid_encap_type(cfg->fc_encap_type); + if (err < 0) + goto errout; + } + if (tb[RTA_EXPIRES]) { unsigned long timeout = addrconf_timeout_fixup(nla_get_u32(tb[RTA_EXPIRES]), HZ); -- cgit v1.2.3 From 03e4deff4987f79c34112c5ba4eb195d4f9382b0 Mon Sep 17 00:00:00 2001 From: Kefeng Wang Date: Thu, 19 Jan 2017 16:26:21 +0800 Subject: ipv6: addrconf: Avoid addrconf_disable_change() using RCU read-side lock Just like commit 4acd4945cd1e ("ipv6: addrconf: Avoid calling netdevice notifiers with RCU read-side lock"), it is unnecessary to make addrconf_disable_change() use RCU iteration over the netdev list, since it already holds the RTNL lock, or we may meet Illegal context switch in RCU read-side critical section. Signed-off-by: Kefeng Wang Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index c1e124bc8e1e..f60e88e56255 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5540,8 +5540,7 @@ static void addrconf_disable_change(struct net *net, __s32 newf) struct net_device *dev; struct inet6_dev *idev; - rcu_read_lock(); - for_each_netdev_rcu(net, dev) { + for_each_netdev(net, dev) { idev = __in6_dev_get(dev); if (idev) { int changed = (!idev->cnf.disable_ipv6) ^ (!newf); @@ -5550,7 +5549,6 @@ static void addrconf_disable_change(struct net *net, __s32 newf) dev_disable_change(idev); } } - rcu_read_unlock(); } static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int newf) -- cgit v1.2.3 From e363116b90906f326c9cde5473b4b9a99ba476df Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 20 Jan 2017 07:57:42 -0800 Subject: ipv6: seg6_genl_set_tunsrc() must check kmemdup() return value seg6_genl_get_tunsrc() and set_tun_src() do not handle tun_src being possibly NULL, so we must check kmemdup() return value and abort if it is NULL Fixes: 915d7e5e5930 ("ipv6: sr: add code base for control plane support of SR-IPv6") Signed-off-by: Eric Dumazet Cc: David Lebrun Acked-by: David Lebrun Signed-off-by: David S. Miller --- net/ipv6/seg6.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/ipv6') diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index b172d85c650a..a855eb325b03 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -176,6 +176,8 @@ static int seg6_genl_set_tunsrc(struct sk_buff *skb, struct genl_info *info) val = nla_data(info->attrs[SEG6_ATTR_DST]); t_new = kmemdup(val, sizeof(*val), GFP_KERNEL); + if (!t_new) + return -ENOMEM; mutex_lock(&sdata->lock); -- cgit v1.2.3 From 21b995a9cb093fff33ec91d7cb3822b882a90a1e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 23 Jan 2017 16:43:05 -0800 Subject: ip6_tunnel: must reload ipv6h in ip6ip6_tnl_xmit() Since ip6_tnl_parse_tlv_enc_lim() can call pskb_may_pull(), we must reload any pointer that was related to skb->head (or skb->data), or risk use after free. Fixes: c12b395a4664 ("gre: Support GRE over IPv6") Signed-off-by: Eric Dumazet Cc: Dmitry Kozlov Signed-off-by: David S. Miller --- net/ipv6/ip6_gre.c | 3 +++ net/ipv6/ip6_tunnel.c | 2 ++ 2 files changed, 5 insertions(+) (limited to 'net/ipv6') diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 75b6108234dd..558631860d91 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -582,6 +582,9 @@ static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev) return -1; offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb)); + /* ip6_tnl_parse_tlv_enc_lim() might have reallocated skb->head */ + ipv6h = ipv6_hdr(skb); + if (offset > 0) { struct ipv6_tlv_tnl_enc_lim *tel; tel = (struct ipv6_tlv_tnl_enc_lim *)&skb_network_header(skb)[offset]; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 753d6d0860fb..02923f956ac8 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1303,6 +1303,8 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) fl6.flowlabel = key->label; } else { offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb)); + /* ip6_tnl_parse_tlv_enc_lim() might have reallocated skb->head */ + ipv6h = ipv6_hdr(skb); if (offset > 0) { struct ipv6_tlv_tnl_enc_lim *tel; -- cgit v1.2.3 From fbfa743a9d2a0ffa24251764f10afc13eb21e739 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 23 Jan 2017 16:43:06 -0800 Subject: ipv6: fix ip6_tnl_parse_tlv_enc_lim() This function suffers from multiple issues. First one is that pskb_may_pull() may reallocate skb->head, so the 'raw' pointer needs either to be reloaded or not used at all. Second issue is that NEXTHDR_DEST handling does not validate that the options are present in skb->data, so we might read garbage or access non existent memory. With help from Willem de Bruijn. Signed-off-by: Eric Dumazet Reported-by: Dmitry Vyukov Cc: Willem de Bruijn Signed-off-by: David S. Miller --- net/ipv6/ip6_tunnel.c | 34 ++++++++++++++++++++++------------ 1 file changed, 22 insertions(+), 12 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 02923f956ac8..ff8ee06491c3 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -400,18 +400,19 @@ ip6_tnl_dev_uninit(struct net_device *dev) __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw) { - const struct ipv6hdr *ipv6h = (const struct ipv6hdr *) raw; - __u8 nexthdr = ipv6h->nexthdr; - __u16 off = sizeof(*ipv6h); + const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)raw; + unsigned int nhoff = raw - skb->data; + unsigned int off = nhoff + sizeof(*ipv6h); + u8 next, nexthdr = ipv6h->nexthdr; while (ipv6_ext_hdr(nexthdr) && nexthdr != NEXTHDR_NONE) { - __u16 optlen = 0; struct ipv6_opt_hdr *hdr; - if (raw + off + sizeof(*hdr) > skb->data && - !pskb_may_pull(skb, raw - skb->data + off + sizeof (*hdr))) + u16 optlen; + + if (!pskb_may_pull(skb, off + sizeof(*hdr))) break; - hdr = (struct ipv6_opt_hdr *) (raw + off); + hdr = (struct ipv6_opt_hdr *)(skb->data + off); if (nexthdr == NEXTHDR_FRAGMENT) { struct frag_hdr *frag_hdr = (struct frag_hdr *) hdr; if (frag_hdr->frag_off) @@ -422,20 +423,29 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw) } else { optlen = ipv6_optlen(hdr); } + /* cache hdr->nexthdr, since pskb_may_pull() might + * invalidate hdr + */ + next = hdr->nexthdr; if (nexthdr == NEXTHDR_DEST) { - __u16 i = off + 2; + u16 i = 2; + + /* Remember : hdr is no longer valid at this point. */ + if (!pskb_may_pull(skb, off + optlen)) + break; + while (1) { struct ipv6_tlv_tnl_enc_lim *tel; /* No more room for encapsulation limit */ - if (i + sizeof (*tel) > off + optlen) + if (i + sizeof(*tel) > optlen) break; - tel = (struct ipv6_tlv_tnl_enc_lim *) &raw[i]; + tel = (struct ipv6_tlv_tnl_enc_lim *) skb->data + off + i; /* return index of option if found and valid */ if (tel->type == IPV6_TLV_TNL_ENCAP_LIMIT && tel->length == 1) - return i; + return i + off - nhoff; /* else jump to next option */ if (tel->type) i += tel->length + 2; @@ -443,7 +453,7 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw) i++; } } - nexthdr = hdr->nexthdr; + nexthdr = next; off += optlen; } return 0; -- cgit v1.2.3 From 88ff7334f25909802140e690c0e16433e485b0a0 Mon Sep 17 00:00:00 2001 From: Robert Shearman Date: Tue, 24 Jan 2017 16:26:47 +0000 Subject: net: Specify the owning module for lwtunnel ops Modules implementing lwtunnel ops should not be allowed to unload while there is state alive using those ops, so specify the owning module for all lwtunnel ops. Signed-off-by: Robert Shearman Signed-off-by: David S. Miller --- include/net/lwtunnel.h | 2 ++ net/core/lwt_bpf.c | 1 + net/ipv4/ip_tunnel_core.c | 2 ++ net/ipv6/ila/ila_lwt.c | 1 + net/ipv6/seg6_iptunnel.c | 1 + net/mpls/mpls_iptunnel.c | 1 + 6 files changed, 8 insertions(+) (limited to 'net/ipv6') diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h index 0b585f1fd340..73dd87647460 100644 --- a/include/net/lwtunnel.h +++ b/include/net/lwtunnel.h @@ -44,6 +44,8 @@ struct lwtunnel_encap_ops { 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); + + struct module *owner; }; #ifdef CONFIG_LWTUNNEL diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index 71bb3e2eca08..b3eef90b2df9 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -386,6 +386,7 @@ static const struct lwtunnel_encap_ops bpf_encap_ops = { .fill_encap = bpf_fill_encap_info, .get_encap_size = bpf_encap_nlsize, .cmp_encap = bpf_encap_cmp, + .owner = THIS_MODULE, }; static int __init bpf_lwt_init(void) diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index fed3d29f9eb3..0fd1976ab63b 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -313,6 +313,7 @@ static const struct lwtunnel_encap_ops ip_tun_lwt_ops = { .fill_encap = ip_tun_fill_encap_info, .get_encap_size = ip_tun_encap_nlsize, .cmp_encap = ip_tun_cmp_encap, + .owner = THIS_MODULE, }; static const struct nla_policy ip6_tun_policy[LWTUNNEL_IP6_MAX + 1] = { @@ -403,6 +404,7 @@ static const struct lwtunnel_encap_ops ip6_tun_lwt_ops = { .fill_encap = ip6_tun_fill_encap_info, .get_encap_size = ip6_tun_encap_nlsize, .cmp_encap = ip_tun_cmp_encap, + .owner = THIS_MODULE, }; void __init ip_tunnel_core_init(void) diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c index a7bc54ab46e2..13b5e85fe0d5 100644 --- a/net/ipv6/ila/ila_lwt.c +++ b/net/ipv6/ila/ila_lwt.c @@ -238,6 +238,7 @@ static const struct lwtunnel_encap_ops ila_encap_ops = { .fill_encap = ila_fill_encap_info, .get_encap_size = ila_encap_nlsize, .cmp_encap = ila_encap_cmp, + .owner = THIS_MODULE, }; int ila_lwt_init(void) diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 1d60cb132835..c46f8cbf5ab5 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -422,6 +422,7 @@ static const struct lwtunnel_encap_ops seg6_iptun_ops = { .fill_encap = seg6_fill_encap_info, .get_encap_size = seg6_encap_nlsize, .cmp_encap = seg6_encap_cmp, + .owner = THIS_MODULE, }; int __init seg6_iptunnel_init(void) diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c index 2f7ccd934416..1d281c1ff7c1 100644 --- a/net/mpls/mpls_iptunnel.c +++ b/net/mpls/mpls_iptunnel.c @@ -215,6 +215,7 @@ static const struct lwtunnel_encap_ops mpls_iptun_ops = { .fill_encap = mpls_fill_encap_info, .get_encap_size = mpls_encap_nlsize, .cmp_encap = mpls_encap_cmp, + .owner = THIS_MODULE, }; static int __init mpls_iptunnel_init(void) -- cgit v1.2.3 From 92e55f412cffd016cc245a74278cb4d7b89bb3bc Mon Sep 17 00:00:00 2001 From: Pablo Neira Date: Thu, 26 Jan 2017 22:56:21 +0100 Subject: tcp: don't annotate mark on control socket from tcp_v6_send_response() Unlike ipv4, this control socket is shared by all cpus so we cannot use it as scratchpad area to annotate the mark that we pass to ip6_xmit(). Add a new parameter to ip6_xmit() to indicate the mark. The SCTP socket family caches the flowi6 structure in the sctp_transport structure, so we cannot use to carry the mark unless we later on reset it back, which I discarded since it looks ugly to me. Fixes: bf99b4ded5f8 ("tcp: fix mark propagation with fwmark_reflect enabled") Suggested-by: Eric Dumazet Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- include/net/ipv6.h | 2 +- net/dccp/ipv6.c | 4 ++-- net/ipv6/inet6_connection_sock.c | 2 +- net/ipv6/ip6_output.c | 4 ++-- net/ipv6/tcp_ipv6.c | 5 ++--- net/sctp/ipv6.c | 3 ++- 6 files changed, 10 insertions(+), 10 deletions(-) (limited to 'net/ipv6') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 487e57391664..7afe991e900e 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -871,7 +871,7 @@ int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb); * upper-layer output functions */ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, - struct ipv6_txoptions *opt, int tclass); + __u32 mark, struct ipv6_txoptions *opt, int tclass); int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr); diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index adfc790f7193..c4e879c02186 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -227,7 +227,7 @@ static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); - err = ip6_xmit(sk, skb, &fl6, opt, np->tclass); + err = ip6_xmit(sk, skb, &fl6, sk->sk_mark, opt, np->tclass); rcu_read_unlock(); err = net_xmit_eval(err); } @@ -281,7 +281,7 @@ static void dccp_v6_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb) dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL); if (!IS_ERR(dst)) { skb_dst_set(skb, dst); - ip6_xmit(ctl_sk, skb, &fl6, NULL, 0); + ip6_xmit(ctl_sk, skb, &fl6, 0, NULL, 0); DCCP_INC_STATS(DCCP_MIB_OUTSEGS); DCCP_INC_STATS(DCCP_MIB_OUTRSTS); return; diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 7396e75e161b..75c308239243 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -176,7 +176,7 @@ int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl_unused /* Restore final destination back after routing done */ fl6.daddr = sk->sk_v6_daddr; - res = ip6_xmit(sk, skb, &fl6, rcu_dereference(np->opt), + res = ip6_xmit(sk, skb, &fl6, sk->sk_mark, rcu_dereference(np->opt), np->tclass); rcu_read_unlock(); return res; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 38122d04fadc..2c0df09e9036 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -172,7 +172,7 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb) * which are using proper atomic operations or spinlocks. */ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, - struct ipv6_txoptions *opt, int tclass) + __u32 mark, struct ipv6_txoptions *opt, int tclass) { struct net *net = sock_net(sk); const struct ipv6_pinfo *np = inet6_sk(sk); @@ -240,7 +240,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, skb->protocol = htons(ETH_P_IPV6); skb->priority = sk->sk_priority; - skb->mark = sk->sk_mark; + skb->mark = mark; mtu = dst_mtu(dst); if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) { diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 2b20622a5824..cb8929681dc7 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -469,7 +469,7 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, opt = ireq->ipv6_opt; if (!opt) opt = rcu_dereference(np->opt); - err = ip6_xmit(sk, skb, fl6, opt, np->tclass); + err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt, np->tclass); rcu_read_unlock(); err = net_xmit_eval(err); } @@ -840,8 +840,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL); if (!IS_ERR(dst)) { skb_dst_set(buff, dst); - ctl_sk->sk_mark = fl6.flowi6_mark; - ip6_xmit(ctl_sk, buff, &fl6, NULL, tclass); + ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL, tclass); TCP_INC_STATS(net, TCP_MIB_OUTSEGS); if (rst) TCP_INC_STATS(net, TCP_MIB_OUTRSTS); diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 5ed8e79bf102..64dfd35ccdcc 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -222,7 +222,8 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport) SCTP_INC_STATS(sock_net(sk), SCTP_MIB_OUTSCTPPACKS); rcu_read_lock(); - res = ip6_xmit(sk, skb, fl6, rcu_dereference(np->opt), np->tclass); + res = ip6_xmit(sk, skb, fl6, sk->sk_mark, rcu_dereference(np->opt), + np->tclass); rcu_read_unlock(); return res; } -- cgit v1.2.3