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 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/net') 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[]); -- 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 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/net') 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, -- cgit v1.2.3 From de70185de0333783154863278ac87bfbbc54e384 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 24 Jan 2017 00:51:41 +0100 Subject: netfilter: nf_tables: deconstify walk callback function The flush operation needs to modify set and element objects, so let's deconstify this. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 924325c46aab..7dfdb517f0be 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -207,9 +207,9 @@ struct nft_set_iter { unsigned int skip; int err; int (*fn)(const struct nft_ctx *ctx, - const struct nft_set *set, + struct nft_set *set, const struct nft_set_iter *iter, - const struct nft_set_elem *elem); + struct nft_set_elem *elem); }; /** @@ -301,7 +301,7 @@ struct nft_set_ops { void (*remove)(const struct nft_set *set, const struct nft_set_elem *elem); void (*walk)(const struct nft_ctx *ctx, - const struct nft_set *set, + struct nft_set *set, struct nft_set_iter *iter); unsigned int (*privsize)(const struct nlattr * const nla[]); -- 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 ++ 1 file changed, 2 insertions(+) (limited to 'include/net') 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 -- 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 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') 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); -- cgit v1.2.3 From 90427ef5d2a4b9a24079889bf16afdcdaebc4240 Mon Sep 17 00:00:00 2001 From: Dimitris Michailidis Date: Mon, 30 Jan 2017 14:09:42 -0800 Subject: ipv6: fix flow labels when the traffic class is non-0 ip6_make_flowlabel() determines the flow label for IPv6 packets. It's supposed to be passed a flow label, which it returns as is if non-0 and in some other cases, otherwise it calculates a new value. The problem is callers often pass a flowi6.flowlabel, which may also contain traffic class bits. If the traffic class is non-0 ip6_make_flowlabel() mistakes the non-0 it gets as a flow label and returns the whole thing. Thus it can return a 'flow label' longer than 20b and the low 20b of that is typically 0 resulting in packets with 0 label. Moreover, different packets of a flow may be labeled differently. For a TCP flow with ECN non-payload and payload packets get different labels as exemplified by this pair of consecutive packets: (pure ACK) Internet Protocol Version 6, Src: 2002:af5:11a3::, Dst: 2002:af5:11a2:: 0110 .... = Version: 6 .... 0000 0000 .... .... .... .... .... = Traffic Class: 0x00 (DSCP: CS0, ECN: Not-ECT) .... 0000 00.. .... .... .... .... .... = Differentiated Services Codepoint: Default (0) .... .... ..00 .... .... .... .... .... = Explicit Congestion Notification: Not ECN-Capable Transport (0) .... .... .... 0001 1100 1110 0100 1001 = Flow Label: 0x1ce49 Payload Length: 32 Next Header: TCP (6) (payload) Internet Protocol Version 6, Src: 2002:af5:11a3::, Dst: 2002:af5:11a2:: 0110 .... = Version: 6 .... 0000 0010 .... .... .... .... .... = Traffic Class: 0x02 (DSCP: CS0, ECN: ECT(0)) .... 0000 00.. .... .... .... .... .... = Differentiated Services Codepoint: Default (0) .... .... ..10 .... .... .... .... .... = Explicit Congestion Notification: ECN-Capable Transport codepoint '10' (2) .... .... .... 0000 0000 0000 0000 0000 = Flow Label: 0x00000 Payload Length: 688 Next Header: TCP (6) This patch allows ip6_make_flowlabel() to be passed more than just a flow label and has it extract the part it really wants. This was simpler than modifying the callers. With this patch packets like the above become Internet Protocol Version 6, Src: 2002:af5:11a3::, Dst: 2002:af5:11a2:: 0110 .... = Version: 6 .... 0000 0000 .... .... .... .... .... = Traffic Class: 0x00 (DSCP: CS0, ECN: Not-ECT) .... 0000 00.. .... .... .... .... .... = Differentiated Services Codepoint: Default (0) .... .... ..00 .... .... .... .... .... = Explicit Congestion Notification: Not ECN-Capable Transport (0) .... .... .... 1010 1111 1010 0101 1110 = Flow Label: 0xafa5e Payload Length: 32 Next Header: TCP (6) Internet Protocol Version 6, Src: 2002:af5:11a3::, Dst: 2002:af5:11a2:: 0110 .... = Version: 6 .... 0000 0010 .... .... .... .... .... = Traffic Class: 0x02 (DSCP: CS0, ECN: ECT(0)) .... 0000 00.. .... .... .... .... .... = Differentiated Services Codepoint: Default (0) .... .... ..10 .... .... .... .... .... = Explicit Congestion Notification: ECN-Capable Transport codepoint '10' (2) .... .... .... 1010 1111 1010 0101 1110 = Flow Label: 0xafa5e Payload Length: 688 Next Header: TCP (6) Signed-off-by: Dimitris Michailidis Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ipv6.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/net') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 7afe991e900e..dbf0abba33b8 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -776,6 +776,11 @@ static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb, { u32 hash; + /* @flowlabel may include more than a flow label, eg, the traffic class. + * Here we want only the flow label value. + */ + flowlabel &= IPV6_FLOWLABEL_MASK; + if (flowlabel || net->ipv6.sysctl.auto_flowlabels == IP6_AUTO_FLOW_LABEL_OFF || (!autolabel && -- cgit v1.2.3 From d71b7896886345c53ef1d84bda2bc758554f5d61 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 3 Feb 2017 00:03:26 -0800 Subject: netlabel: out of bound access in cipso_v4_validate() syzkaller found another out of bound access in ip_options_compile(), or more exactly in cipso_v4_validate() Fixes: 20e2a8648596 ("cipso: handle CIPSO options correctly when NetLabel is disabled") Fixes: 446fda4f2682 ("[NetLabel]: CIPSOv4 engine") Signed-off-by: Eric Dumazet Reported-by: Dmitry Vyukov Cc: Paul Moore Acked-by: Paul Moore Signed-off-by: David S. Miller --- include/net/cipso_ipv4.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/net') diff --git a/include/net/cipso_ipv4.h b/include/net/cipso_ipv4.h index 3ebb168b9afc..a34b141f125f 100644 --- a/include/net/cipso_ipv4.h +++ b/include/net/cipso_ipv4.h @@ -309,6 +309,10 @@ static inline int cipso_v4_validate(const struct sk_buff *skb, } for (opt_iter = 6; opt_iter < opt_len;) { + if (opt_iter + 1 == opt_len) { + err_offset = opt_iter; + goto out; + } tag_len = opt[opt_iter + 1]; if ((tag_len == 0) || (tag_len > (opt_len - opt_iter))) { err_offset = opt_iter + 1; -- cgit v1.2.3 From 69629464e0b587f3711739b3aa2bcdaf2e075276 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 5 Feb 2017 09:25:24 -0800 Subject: udp: properly cope with csum errors Dmitry reported that UDP sockets being destroyed would trigger the WARN_ON(atomic_read(&sk->sk_rmem_alloc)); in inet_sock_destruct() It turns out we do not properly destroy skb(s) that have wrong UDP checksum. Thanks again to syzkaller team. Fixes : 7c13f97ffde6 ("udp: do fwd memory scheduling on dequeue") Reported-by: Dmitry Vyukov Signed-off-by: Eric Dumazet Cc: Paolo Abeni Cc: Hannes Frederic Sowa Acked-by: Paolo Abeni Signed-off-by: David S. Miller --- include/net/sock.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/sock.h b/include/net/sock.h index f0e867f58722..c4f5e6fca17c 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2006,7 +2006,9 @@ void sk_reset_timer(struct sock *sk, struct timer_list *timer, void sk_stop_timer(struct sock *sk, struct timer_list *timer); int __sk_queue_drop_skb(struct sock *sk, struct sk_buff *skb, - unsigned int flags); + unsigned int flags, + void (*destructor)(struct sock *sk, + struct sk_buff *skb)); int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb); -- cgit v1.2.3 From 2bd137de531367fb573d90150d1872cb2a2095f7 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 8 Feb 2017 09:29:00 -0800 Subject: lwtunnel: valid encap attr check should return 0 when lwtunnel is disabled An error was reported upgrading to 4.9.8: root@Typhoon:~# ip route add default table 210 nexthop dev eth0 via 10.68.64.1 weight 1 nexthop dev eth0 via 10.68.64.2 weight 1 RTNETLINK answers: Operation not supported The problem occurs when CONFIG_LWTUNNEL is not enabled and a multipath route is submitted. The point of lwtunnel_valid_encap_type_attr is catch modules that need to be loaded before any references are taken with rntl held. With CONFIG_LWTUNNEL disabled, there will be no modules to load so the lwtunnel_valid_encap_type_attr stub should just return 0. Fixes: 9ed59592e3e3 ("lwtunnel: fix autoload of lwt modules") Reported-by: pupilla@libero.it Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/net/lwtunnel.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h index 73dd87647460..0388b9c5f5e2 100644 --- a/include/net/lwtunnel.h +++ b/include/net/lwtunnel.h @@ -178,7 +178,10 @@ static inline int lwtunnel_valid_encap_type(u16 encap_type) } static inline int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len) { - return -EOPNOTSUPP; + /* return 0 since we are not walking attr looking for + * RTA_ENCAP_TYPE attribute on nexthops. + */ + return 0; } static inline int lwtunnel_build_state(struct net_device *dev, u16 encap_type, -- cgit v1.2.3