From 48d5cad87c3a4998d0bda16ccfb5c60dfe4de5fb Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 15 Feb 2006 15:10:22 -0800 Subject: [XFRM]: Fix SNAT-related crash in xfrm4_output_finish When a packet matching an IPsec policy is SNATed so it doesn't match any policy anymore it looses its xfrm bundle, which makes xfrm4_output_finish crash because of a NULL pointer dereference. This patch directs these packets to the original output path instead. Since the packets have already passed the POST_ROUTING hook, but need to start at the beginning of the original output path which includes another POST_ROUTING invocation, a flag is added to the IPCB to indicate that the packet was rerouted and doesn't need to pass the POST_ROUTING hook again. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter.h | 19 +++++++++++++++---- include/net/ip.h | 1 + include/net/xfrm.h | 1 - net/ipv4/ip_gre.c | 3 ++- net/ipv4/ip_output.c | 16 ++++++++++------ net/ipv4/ipip.c | 3 ++- net/ipv4/xfrm4_output.c | 13 ++++++++++--- 7 files changed, 40 insertions(+), 16 deletions(-) diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 4cf6088625c..3ca3d9ee78a 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -184,8 +184,11 @@ static inline int nf_hook_thresh(int pf, unsigned int hook, struct sk_buff **pskb, struct net_device *indev, struct net_device *outdev, - int (*okfn)(struct sk_buff *), int thresh) + int (*okfn)(struct sk_buff *), int thresh, + int cond) { + if (!cond) + return 1; #ifndef CONFIG_NETFILTER_DEBUG if (list_empty(&nf_hooks[pf][hook])) return 1; @@ -197,7 +200,7 @@ static inline int nf_hook(int pf, unsigned int hook, struct sk_buff **pskb, struct net_device *indev, struct net_device *outdev, int (*okfn)(struct sk_buff *)) { - return nf_hook_thresh(pf, hook, pskb, indev, outdev, okfn, INT_MIN); + return nf_hook_thresh(pf, hook, pskb, indev, outdev, okfn, INT_MIN, 1); } /* Activate hook; either okfn or kfree_skb called, unless a hook @@ -224,7 +227,13 @@ static inline int nf_hook(int pf, unsigned int hook, struct sk_buff **pskb, #define NF_HOOK_THRESH(pf, hook, skb, indev, outdev, okfn, thresh) \ ({int __ret; \ -if ((__ret=nf_hook_thresh(pf, hook, &(skb), indev, outdev, okfn, thresh)) == 1)\ +if ((__ret=nf_hook_thresh(pf, hook, &(skb), indev, outdev, okfn, thresh, 1)) == 1)\ + __ret = (okfn)(skb); \ +__ret;}) + +#define NF_HOOK_COND(pf, hook, skb, indev, outdev, okfn, cond) \ +({int __ret; \ +if ((__ret=nf_hook_thresh(pf, hook, &(skb), indev, outdev, okfn, INT_MIN, cond)) == 1)\ __ret = (okfn)(skb); \ __ret;}) @@ -295,11 +304,13 @@ extern struct proc_dir_entry *proc_net_netfilter; #else /* !CONFIG_NETFILTER */ #define NF_HOOK(pf, hook, skb, indev, outdev, okfn) (okfn)(skb) +#define NF_HOOK_COND(pf, hook, skb, indev, outdev, okfn, cond) (okfn)(skb) static inline int nf_hook_thresh(int pf, unsigned int hook, struct sk_buff **pskb, struct net_device *indev, struct net_device *outdev, - int (*okfn)(struct sk_buff *), int thresh) + int (*okfn)(struct sk_buff *), int thresh, + int cond) { return okfn(*pskb); } diff --git a/include/net/ip.h b/include/net/ip.h index 8de0697b364..fab3d5b3ab1 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -41,6 +41,7 @@ struct inet_skb_parm #define IPSKB_XFRM_TUNNEL_SIZE 2 #define IPSKB_XFRM_TRANSFORMED 4 #define IPSKB_FRAG_COMPLETE 8 +#define IPSKB_REROUTED 16 }; struct ipcm_cookie diff --git a/include/net/xfrm.h b/include/net/xfrm.h index d09ca0e7d13..d6111a2f0a2 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -866,7 +866,6 @@ extern int xfrm_state_mtu(struct xfrm_state *x, int mtu); extern int xfrm_init_state(struct xfrm_state *x); extern int xfrm4_rcv(struct sk_buff *skb); extern int xfrm4_output(struct sk_buff *skb); -extern int xfrm4_output_finish(struct sk_buff *skb); extern int xfrm4_tunnel_register(struct xfrm_tunnel *handler); extern int xfrm4_tunnel_deregister(struct xfrm_tunnel *handler); extern int xfrm6_rcv_spi(struct sk_buff **pskb, u32 spi); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index abe23923e4e..9981dcd68f1 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -830,7 +830,8 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) skb->h.raw = skb->nh.raw; skb->nh.raw = skb_push(skb, gre_hlen); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); - IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE|IPSKB_XFRM_TRANSFORMED); + IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | + IPSKB_REROUTED); dst_release(skb->dst); skb->dst = &rt->u.dst; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 3324fbfe528..57d290d89ec 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -207,8 +207,10 @@ static inline int ip_finish_output(struct sk_buff *skb) { #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM) /* Policy lookup after SNAT yielded a new policy */ - if (skb->dst->xfrm != NULL) - return xfrm4_output_finish(skb); + if (skb->dst->xfrm != NULL) { + IPCB(skb)->flags |= IPSKB_REROUTED; + return dst_output(skb); + } #endif if (skb->len > dst_mtu(skb->dst) && !(skb_shinfo(skb)->ufo_size || skb_shinfo(skb)->tso_size)) @@ -271,8 +273,9 @@ int ip_mc_output(struct sk_buff *skb) newskb->dev, ip_dev_loopback_xmit); } - return NF_HOOK(PF_INET, NF_IP_POST_ROUTING, skb, NULL, skb->dev, - ip_finish_output); + return NF_HOOK_COND(PF_INET, NF_IP_POST_ROUTING, skb, NULL, skb->dev, + ip_finish_output, + !(IPCB(skb)->flags & IPSKB_REROUTED)); } int ip_output(struct sk_buff *skb) @@ -284,8 +287,9 @@ int ip_output(struct sk_buff *skb) skb->dev = dev; skb->protocol = htons(ETH_P_IP); - return NF_HOOK(PF_INET, NF_IP_POST_ROUTING, skb, NULL, dev, - ip_finish_output); + return NF_HOOK_COND(PF_INET, NF_IP_POST_ROUTING, skb, NULL, dev, + ip_finish_output, + !(IPCB(skb)->flags & IPSKB_REROUTED)); } int ip_queue_xmit(struct sk_buff *skb, int ipfragok) diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index e5cbe72c6b8..03d13742a4b 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -622,7 +622,8 @@ static int ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) skb->h.raw = skb->nh.raw; skb->nh.raw = skb_push(skb, sizeof(struct iphdr)); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); - IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE|IPSKB_XFRM_TRANSFORMED); + IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | + IPSKB_REROUTED); dst_release(skb->dst); skb->dst = &rt->u.dst; diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index d4df0ddd424..32ad229b4fe 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -152,10 +152,16 @@ error_nolock: goto out_exit; } -int xfrm4_output_finish(struct sk_buff *skb) +static int xfrm4_output_finish(struct sk_buff *skb) { int err; +#ifdef CONFIG_NETFILTER + if (!skb->dst->xfrm) { + IPCB(skb)->flags |= IPSKB_REROUTED; + return dst_output(skb); + } +#endif while (likely((err = xfrm4_output_one(skb)) == 0)) { nf_reset(skb); @@ -178,6 +184,7 @@ int xfrm4_output_finish(struct sk_buff *skb) int xfrm4_output(struct sk_buff *skb) { - return NF_HOOK(PF_INET, NF_IP_POST_ROUTING, skb, NULL, skb->dst->dev, - xfrm4_output_finish); + return NF_HOOK_COND(PF_INET, NF_IP_POST_ROUTING, skb, NULL, skb->dst->dev, + xfrm4_output_finish, + !(IPCB(skb)->flags & IPSKB_REROUTED)); } -- cgit v1.2.3 From 9c92d3486434e7310cb288587953e2dae4a79701 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 15 Feb 2006 15:18:19 -0800 Subject: [NETFILTER]: Don't invoke okfn in CONFIG_NETFILTER=n variant of nf_hook() nf_hook() is supposed to call the netfilter hook and return control of the packet back to the caller in case it may pass, the okfn is only used for queueing. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 3ca3d9ee78a..46889693984 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -318,7 +318,7 @@ static inline int nf_hook(int pf, unsigned int hook, struct sk_buff **pskb, struct net_device *indev, struct net_device *outdev, int (*okfn)(struct sk_buff *)) { - return okfn(*pskb); + return 1; } static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} struct flowi; -- cgit v1.2.3 From deac0ccdb4da16b68539d75edecf26162de05150 Mon Sep 17 00:00:00 2001 From: Yasuyuki Kozakai Date: Wed, 15 Feb 2006 15:21:31 -0800 Subject: [NETFILTER]: x_tables: fix dependencies of conntrack related modules NF_CONNTRACK_MARK is bool and depends on NF_CONNTRACK which is tristate. If a variable depends on NF_CONNTRACK_MARK and doesn't take care about NF_CONNTRACK, it can be y even if NF_CONNTRACK isn't y. NF_CT_ACCT have same issue, too. Signed-off-by: Yasuyuki Kozakai Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- net/netfilter/Kconfig | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 0e550127fa7..a8e5544da93 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -126,7 +126,7 @@ config NETFILTER_XT_TARGET_CONNMARK tristate '"CONNMARK" target support' depends on NETFILTER_XTABLES depends on IP_NF_MANGLE || IP6_NF_MANGLE - depends on (IP_NF_CONNTRACK && IP_NF_CONNTRACK_MARK) || (NF_CONNTRACK_MARK && NF_CONNTRACK_IPV4) + depends on (IP_NF_CONNTRACK && IP_NF_CONNTRACK_MARK) || (NF_CONNTRACK_MARK && NF_CONNTRACK) help This option adds a `CONNMARK' target, which allows one to manipulate the connection mark value. Similar to the MARK target, but @@ -187,7 +187,7 @@ config NETFILTER_XT_MATCH_COMMENT config NETFILTER_XT_MATCH_CONNBYTES tristate '"connbytes" per-connection counter match support' depends on NETFILTER_XTABLES - depends on (IP_NF_CONNTRACK && IP_NF_CT_ACCT) || NF_CT_ACCT + depends on (IP_NF_CONNTRACK && IP_NF_CT_ACCT) || (NF_CT_ACCT && NF_CONNTRACK) help This option adds a `connbytes' match, which allows you to match the number of bytes and/or packets for each direction within a connection. @@ -198,7 +198,7 @@ config NETFILTER_XT_MATCH_CONNBYTES config NETFILTER_XT_MATCH_CONNMARK tristate '"connmark" connection mark match support' depends on NETFILTER_XTABLES - depends on (IP_NF_CONNTRACK && IP_NF_CONNTRACK_MARK) || NF_CONNTRACK_MARK + depends on (IP_NF_CONNTRACK && IP_NF_CONNTRACK_MARK) || (NF_CONNTRACK_MARK && NF_CONNTRACK) help This option adds a `connmark' match, which allows you to match the connection mark value previously set for the session by `CONNMARK'. -- cgit v1.2.3 From 7d3cdc6b554137a7a0534ce38b155a63a3117f27 Mon Sep 17 00:00:00 2001 From: Yasuyuki Kozakai Date: Wed, 15 Feb 2006 15:22:21 -0800 Subject: [NETFILTER]: nf_conntrack: move registration of __nf_ct_attach Move registration of __nf_ct_attach to nf_conntrack_core to make it usable for IPv6 connection tracking as well. Signed-off-by: Yasuyuki Kozakai Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 5 ----- net/netfilter/nf_conntrack_core.c | 5 +++++ 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 167619f638c..6c8624a5493 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -529,15 +529,10 @@ static int init_or_cleanup(int init) goto cleanup_localinops; } #endif - - /* For use by REJECT target */ - ip_ct_attach = __nf_conntrack_attach; - return ret; cleanup: synchronize_net(); - ip_ct_attach = NULL; #ifdef CONFIG_SYSCTL unregister_sysctl_table(nf_ct_ipv4_sysctl_header); cleanup_localinops: diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 0ce337a1d97..d622ddf08bb 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1556,6 +1556,8 @@ void nf_conntrack_cleanup(void) { int i; + ip_ct_attach = NULL; + /* This makes sure all current packets have passed through netfilter framework. Roll on, two-stage module delete... */ @@ -1715,6 +1717,9 @@ int __init nf_conntrack_init(void) nf_ct_l3protos[i] = &nf_conntrack_generic_l3proto; write_unlock_bh(&nf_conntrack_lock); + /* For use by REJECT target */ + ip_ct_attach = __nf_conntrack_attach; + /* Set up fake conntrack: - to never be deleted, not in any hashes */ atomic_set(&nf_conntrack_untracked.ct_general.use, 1); -- cgit v1.2.3 From 08857fa745ab6ce46601960d2774490e1cef2cff Mon Sep 17 00:00:00 2001 From: Yasuyuki Kozakai Date: Wed, 15 Feb 2006 15:23:28 -0800 Subject: [NETFILTER]: nf_conntrack: attach conntrack to TCP RST generated by ip6t_REJECT TCP RSTs generated by the REJECT target should be associated with the conntrack of the original TCP packet. Since the conntrack entry is usually not is the hash tables, it must be manually attached. Signed-off-by: Yasuyuki Kozakai Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- net/ipv6/netfilter/ip6t_REJECT.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index c745717b4ce..0e6d1d4bbd5 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -160,6 +160,8 @@ static void send_reset(struct sk_buff *oldskb) csum_partial((char *)tcph, sizeof(struct tcphdr), 0)); + nf_ct_attach(nskb, oldskb); + NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, nskb, NULL, nskb->dst->dev, dst_output); } -- cgit v1.2.3 From 763ecff1879b3877f57f20fc9e79599aef59359f Mon Sep 17 00:00:00 2001 From: Yasuyuki Kozakai Date: Wed, 15 Feb 2006 15:24:15 -0800 Subject: [NETFILTER]: nf_conntrack: attach conntrack to locally generated ICMPv6 error Locally generated ICMPv6 errors should be associated with the conntrack of the original packet. Since the conntrack entry may not be in the hash tables (for the first packet), it must be manually attached. Signed-off-by: Yasuyuki Kozakai Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- net/ipv6/icmp.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index fcf883183ce..21eb725e885 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -42,6 +42,7 @@ #include #include #include +#include #ifdef CONFIG_SYSCTL #include @@ -255,6 +256,7 @@ out: struct icmpv6_msg { struct sk_buff *skb; int offset; + uint8_t type; }; static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) @@ -266,6 +268,8 @@ static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, st csum = skb_copy_and_csum_bits(org_skb, msg->offset + offset, to, len, csum); skb->csum = csum_block_add(skb->csum, csum, odd); + if (!(msg->type & ICMPV6_INFOMSG_MASK)) + nf_ct_attach(skb, org_skb); return 0; } @@ -403,6 +407,7 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info, msg.skb = skb; msg.offset = skb->nh.raw - skb->data; + msg.type = type; len = skb->len - msg.offset; len = min_t(unsigned int, len, IPV6_MIN_MTU - sizeof(struct ipv6hdr) -sizeof(struct icmp6hdr)); @@ -500,6 +505,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb) msg.skb = skb; msg.offset = 0; + msg.type = ICMPV6_ECHO_REPLY; err = ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr), sizeof(struct icmp6hdr), hlimit, tclass, NULL, &fl, -- cgit v1.2.3 From 7c6de05884b9fcc7ef621e2ab198ba93d85f46aa Mon Sep 17 00:00:00 2001 From: Yasuyuki Kozakai Date: Wed, 15 Feb 2006 15:25:18 -0800 Subject: [NETFILTER]: nf_conntrack: Fix TCP/UDP HW checksum handling for IPv6 packet If skb->ip_summed is CHECKSUM_HW here, skb->csum includes checksum of actual IPv6 header and extension headers. Then such excess checksum must be subtruct when nf_conntrack calculates TCP/UDP checksum with pseudo IPv6 header. Spotted by Ben Skeggs. Signed-off-by: Yasuyuki Kozakai Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- net/netfilter/nf_conntrack_proto_tcp.c | 4 +++- net/netfilter/nf_conntrack_proto_udp.c | 4 +++- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index df99138c3b3..6492ed66fb3 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -864,7 +864,9 @@ static int csum6(const struct sk_buff *skb, unsigned int dataoff) { return csum_ipv6_magic(&skb->nh.ipv6h->saddr, &skb->nh.ipv6h->daddr, skb->len - dataoff, IPPROTO_TCP, - skb->ip_summed == CHECKSUM_HW ? skb->csum + skb->ip_summed == CHECKSUM_HW + ? csum_sub(skb->csum, + skb_checksum(skb, 0, dataoff, 0)) : skb_checksum(skb, dataoff, skb->len - dataoff, 0)); } diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 4264dd079a1..831d206344e 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -161,7 +161,9 @@ static int csum6(const struct sk_buff *skb, unsigned int dataoff) { return csum_ipv6_magic(&skb->nh.ipv6h->saddr, &skb->nh.ipv6h->daddr, skb->len - dataoff, IPPROTO_UDP, - skb->ip_summed == CHECKSUM_HW ? skb->csum + skb->ip_summed == CHECKSUM_HW + ? csum_sub(skb->csum, + skb_checksum(skb, 0, dataoff, 0)) : skb_checksum(skb, dataoff, skb->len - dataoff, 0)); } -- cgit v1.2.3